Namespace(aa='rand-m9-mstd0.5-inc1', auto_resume=True, batch_size=512, cfg_path='iFormer_s.yaml', clip_grad=None, color_jitter=0.4, crop_pct=None, cutmix=1.0, cutmix_minmax=None, data_path='imagenet', data_set='IMNET', device='cuda', disable_eval=False, dist_backend='nccl', dist_eval=True, dist_on_itp=False, dist_url='env://', distillation_alpha=0.5, distillation_tau=1.0, distillation_type='none', distributed=True, drop_path=0, enable_wandb=False, epochs=300, eval=False, eval_data_path=None, finetune='', gpu=0, head_init_scale=1.0, imagenet_default_mean_and_std=True, input_size=224, layer_decay=1.0, layer_scale_init_value=0, local_rank=-1, log_dir=None, lr=0.004, min_lr=1e-06, mixup=0.8, mixup_mode='batch', mixup_prob=1.0, mixup_switch_prob=0.5, model='iFormer_s', model_ema=False, model_ema_decay=0.9999, model_ema_eval=False, model_ema_force_cpu=False, model_key='model|module', model_prefix='', momentum=0.9, nb_classes=1000, num_workers=16, opt='adamw', opt_betas=None, opt_eps=1e-08, output_dir='', pin_mem=True, project='iFormer', rank=0, recount=1, remode='pixel', reprob=0.25, resplit=False, resume='', save_ckpt=True, save_ckpt_freq=1, save_ckpt_num=3, seed=0, smoothing=0.1, start_epoch=0, teacher_model='regnety_160', teacher_path='regnety_160-a5fe301d.pth', train_interpolation='bicubic', update_freq=1, use_amp=False, wandb_ckpt=False, warmup_epochs=20, warmup_steps=-1, weight_decay=0.05, weight_decay_end=None, world_size=8)
Transform = 
RandomResizedCropAndInterpolation(size=(224, 224), scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BICUBIC)
RandomHorizontalFlip(p=0.5)
<timm.data.auto_augment.RandAugment object at 0x7f9e39a0e490>
ToTensor()
Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))
<timm.data.random_erasing.RandomErasing object at 0x7f9e39a0c760>
---------------------------
reading from datapath imagenet
Number of the class = 1000
Transform = 
Resize(size=256, interpolation=bicubic, max_size=None, antialias=warn)
CenterCrop(size=(224, 224))
ToTensor()
Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
---------------------------
reading from datapath imagenet
Number of the class = 1000
Sampler_train = <torch.utils.data.distributed.DistributedSampler object at 0x7f9e39a0ca90>
Mixup is activated!
Model = iFormer(
  (downsample_layers): ModuleList(
    (0): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(3, 16, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), bias=False)
        (bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (1): GELU(approximate='none')
      (2): EdgeResidual(
        (conv_exp_bn1): Conv2d_BN(
          (c): Conv2d(16, 64, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (act): GELU(approximate='none')
        (conv_pwl_bn2): Conv2d_BN(
          (c): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (1): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (2): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(64, 176, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (3): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(176, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
  )
  (stages): ModuleList(
    (0): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(32, 32, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=32, bias=False)
                (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(32, 32, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=32, bias=False)
                (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (1): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(64, 64, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=64, bias=False)
                (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(64, 64, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=64, bias=False)
                (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (2): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (2): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (3): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (4): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (5): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (6): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (7): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (8): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (9): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(176, 176, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=176, bias=False)
              (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (10): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(176, 352, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (11): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 528, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(528, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(528, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (12): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(176, 176, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=176, bias=False)
              (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (13): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(176, 352, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (14): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 528, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(528, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(528, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (15): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(176, 176, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=176, bias=False)
              (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (16): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(176, 88, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(88, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(176, 352, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (17): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 528, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(528, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(528, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (18): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(176, 176, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=176, bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(176, 704, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(704, 176, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (3): Sequential(
      (0): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320, bias=False)
              (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (1): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(320, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (2): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(320, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (3): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320, bias=False)
              (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (4): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(320, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (5): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(320, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
  )
  (classifier): Classfier(
    (classifier): BN_Linear(
      (bn): BatchNorm1d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (l): Linear(in_features=320, out_features=1000, bias=True)
    )
  )
)
number of params: 6563368
LR = 0.00400000
Batch size = 4096
Update frequent = 1
Number of training examples = 1281167
Number of training training per epoch = 312
Param groups = {
  "decay": {
    "weight_decay": 0.05,
    "params": [
      "downsample_layers.0.0.c.weight",
      "downsample_layers.0.2.conv_exp_bn1.c.weight",
      "downsample_layers.0.2.conv_pwl_bn2.c.weight",
      "downsample_layers.1.0.c.weight",
      "downsample_layers.2.0.c.weight",
      "downsample_layers.3.0.c.weight",
      "stages.0.0.block.token_channel_mixer.m.0.c.weight",
      "stages.0.0.block.token_channel_mixer.m.1.c.weight",
      "stages.0.0.block.token_channel_mixer.m.3.c.weight",
      "stages.0.1.block.token_channel_mixer.m.0.c.weight",
      "stages.0.1.block.token_channel_mixer.m.1.c.weight",
      "stages.0.1.block.token_channel_mixer.m.3.c.weight",
      "stages.1.0.block.token_channel_mixer.m.0.c.weight",
      "stages.1.0.block.token_channel_mixer.m.1.c.weight",
      "stages.1.0.block.token_channel_mixer.m.3.c.weight",
      "stages.1.1.block.token_channel_mixer.m.0.c.weight",
      "stages.1.1.block.token_channel_mixer.m.1.c.weight",
      "stages.1.1.block.token_channel_mixer.m.3.c.weight",
      "stages.2.0.block.token_channel_mixer.m.0.c.weight",
      "stages.2.0.block.token_channel_mixer.m.1.c.weight",
      "stages.2.0.block.token_channel_mixer.m.3.c.weight",
      "stages.2.1.block.token_channel_mixer.m.0.c.weight",
      "stages.2.1.block.token_channel_mixer.m.1.c.weight",
      "stages.2.1.block.token_channel_mixer.m.3.c.weight",
      "stages.2.2.block.token_channel_mixer.m.0.c.weight",
      "stages.2.2.block.token_channel_mixer.m.1.c.weight",
      "stages.2.2.block.token_channel_mixer.m.3.c.weight",
      "stages.2.3.block.token_channel_mixer.m.0.c.weight",
      "stages.2.3.block.token_channel_mixer.m.1.c.weight",
      "stages.2.3.block.token_channel_mixer.m.3.c.weight",
      "stages.2.4.block.token_channel_mixer.m.0.c.weight",
      "stages.2.4.block.token_channel_mixer.m.1.c.weight",
      "stages.2.4.block.token_channel_mixer.m.3.c.weight",
      "stages.2.5.block.token_channel_mixer.m.0.c.weight",
      "stages.2.5.block.token_channel_mixer.m.1.c.weight",
      "stages.2.5.block.token_channel_mixer.m.3.c.weight",
      "stages.2.6.block.token_channel_mixer.m.0.c.weight",
      "stages.2.6.block.token_channel_mixer.m.1.c.weight",
      "stages.2.6.block.token_channel_mixer.m.3.c.weight",
      "stages.2.7.block.token_channel_mixer.m.0.c.weight",
      "stages.2.7.block.token_channel_mixer.m.1.c.weight",
      "stages.2.7.block.token_channel_mixer.m.3.c.weight",
      "stages.2.8.block.token_channel_mixer.m.0.c.weight",
      "stages.2.8.block.token_channel_mixer.m.1.c.weight",
      "stages.2.8.block.token_channel_mixer.m.3.c.weight",
      "stages.2.9.block.cpe.m.c.weight",
      "stages.2.10.block.token_channel_mixer.m.q.c.weight",
      "stages.2.10.block.token_channel_mixer.m.k.c.weight",
      "stages.2.10.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.10.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.11.block.channel_mixer.m.0.c.weight",
      "stages.2.11.block.channel_mixer.m.2.c.weight",
      "stages.2.12.block.cpe.m.c.weight",
      "stages.2.13.block.token_channel_mixer.m.q.c.weight",
      "stages.2.13.block.token_channel_mixer.m.k.c.weight",
      "stages.2.13.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.13.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.14.block.channel_mixer.m.0.c.weight",
      "stages.2.14.block.channel_mixer.m.2.c.weight",
      "stages.2.15.block.cpe.m.c.weight",
      "stages.2.16.block.token_channel_mixer.m.q.c.weight",
      "stages.2.16.block.token_channel_mixer.m.k.c.weight",
      "stages.2.16.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.16.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.17.block.channel_mixer.m.0.c.weight",
      "stages.2.17.block.channel_mixer.m.2.c.weight",
      "stages.2.18.block.token_channel_mixer.m.0.c.weight",
      "stages.2.18.block.token_channel_mixer.m.1.c.weight",
      "stages.2.18.block.token_channel_mixer.m.3.c.weight",
      "stages.3.0.block.cpe.m.c.weight",
      "stages.3.1.block.token_channel_mixer.m.q.c.weight",
      "stages.3.1.block.token_channel_mixer.m.k.c.weight",
      "stages.3.1.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.3.1.block.token_channel_mixer.m.proj.c.weight",
      "stages.3.2.block.channel_mixer.m.0.c.weight",
      "stages.3.2.block.channel_mixer.m.2.c.weight",
      "stages.3.3.block.cpe.m.c.weight",
      "stages.3.4.block.token_channel_mixer.m.q.c.weight",
      "stages.3.4.block.token_channel_mixer.m.k.c.weight",
      "stages.3.4.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.3.4.block.token_channel_mixer.m.proj.c.weight",
      "stages.3.5.block.channel_mixer.m.0.c.weight",
      "stages.3.5.block.channel_mixer.m.2.c.weight",
      "classifier.classifier.l.weight"
    ],
    "lr_scale": 1.0
  },
  "no_decay": {
    "weight_decay": 0.0,
    "params": [
      "downsample_layers.0.0.bn.weight",
      "downsample_layers.0.0.bn.bias",
      "downsample_layers.0.2.conv_exp_bn1.bn.weight",
      "downsample_layers.0.2.conv_exp_bn1.bn.bias",
      "downsample_layers.0.2.conv_pwl_bn2.bn.weight",
      "downsample_layers.0.2.conv_pwl_bn2.bn.bias",
      "downsample_layers.1.0.bn.weight",
      "downsample_layers.1.0.bn.bias",
      "downsample_layers.2.0.bn.weight",
      "downsample_layers.2.0.bn.bias",
      "downsample_layers.3.0.bn.weight",
      "downsample_layers.3.0.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.8.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.8.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.8.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.9.block.cpe.m.bn.weight",
      "stages.2.9.block.cpe.m.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.11.block.channel_mixer.m.0.bn.weight",
      "stages.2.11.block.channel_mixer.m.0.bn.bias",
      "stages.2.11.block.channel_mixer.m.2.bn.weight",
      "stages.2.11.block.channel_mixer.m.2.bn.bias",
      "stages.2.12.block.cpe.m.bn.weight",
      "stages.2.12.block.cpe.m.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.14.block.channel_mixer.m.0.bn.weight",
      "stages.2.14.block.channel_mixer.m.0.bn.bias",
      "stages.2.14.block.channel_mixer.m.2.bn.weight",
      "stages.2.14.block.channel_mixer.m.2.bn.bias",
      "stages.2.15.block.cpe.m.bn.weight",
      "stages.2.15.block.cpe.m.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.17.block.channel_mixer.m.0.bn.weight",
      "stages.2.17.block.channel_mixer.m.0.bn.bias",
      "stages.2.17.block.channel_mixer.m.2.bn.weight",
      "stages.2.17.block.channel_mixer.m.2.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.3.bn.bias",
      "stages.3.0.block.cpe.m.bn.weight",
      "stages.3.0.block.cpe.m.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.q.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.q.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.k.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.k.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.proj.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.proj.bn.bias",
      "stages.3.2.block.channel_mixer.m.0.bn.weight",
      "stages.3.2.block.channel_mixer.m.0.bn.bias",
      "stages.3.2.block.channel_mixer.m.2.bn.weight",
      "stages.3.2.block.channel_mixer.m.2.bn.bias",
      "stages.3.3.block.cpe.m.bn.weight",
      "stages.3.3.block.cpe.m.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.q.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.q.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.k.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.k.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.proj.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.proj.bn.bias",
      "stages.3.5.block.channel_mixer.m.0.bn.weight",
      "stages.3.5.block.channel_mixer.m.0.bn.bias",
      "stages.3.5.block.channel_mixer.m.2.bn.weight",
      "stages.3.5.block.channel_mixer.m.2.bn.bias",
      "classifier.classifier.bn.weight",
      "classifier.classifier.bn.bias",
      "classifier.classifier.l.bias"
    ],
    "lr_scale": 1.0
  }
}
Use Cosine LR scheduler
Set warmup steps = 6240
Set warmup steps = 0
Max WD = 0.0500000, Min WD = 0.0500000
criterion = SoftTargetCrossEntropy()
Auto resume checkpoint: 
Start training for 300 epochs
Epoch: [0]  [  0/312]  eta: 3:16:50  lr: 0.000000  min_lr: 0.000000  loss: 6.9722 (6.9722)  weight_decay: 0.0500 (0.0500)  time: 37.8531  data: 11.5697  max mem: 31830
Epoch: [0]  [ 10/312]  eta: 0:20:56  lr: 0.000006  min_lr: 0.000006  loss: 6.9640 (6.9669)  weight_decay: 0.0500 (0.0500)  time: 4.1619  data: 1.0522  max mem: 31830
Epoch: [0]  [ 20/312]  eta: 0:11:52  lr: 0.000013  min_lr: 0.000013  loss: 6.9630 (6.9659)  weight_decay: 0.0500 (0.0500)  time: 0.6700  data: 0.0006  max mem: 31830
Epoch: [0]  [ 30/312]  eta: 0:08:29  lr: 0.000019  min_lr: 0.000019  loss: 6.9558 (6.9614)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0007  max mem: 31830
Epoch: [0]  [ 40/312]  eta: 0:06:37  lr: 0.000026  min_lr: 0.000026  loss: 6.9449 (6.9560)  weight_decay: 0.0500 (0.0500)  time: 0.4297  data: 0.0008  max mem: 31830
Epoch: [0]  [ 50/312]  eta: 0:05:27  lr: 0.000032  min_lr: 0.000032  loss: 6.9285 (6.9506)  weight_decay: 0.0500 (0.0500)  time: 0.3927  data: 0.0010  max mem: 31830
Epoch: [0]  [ 60/312]  eta: 0:04:40  lr: 0.000038  min_lr: 0.000038  loss: 6.9191 (6.9448)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0011  max mem: 31830
Epoch: [0]  [ 70/312]  eta: 0:04:04  lr: 0.000045  min_lr: 0.000045  loss: 6.9062 (6.9375)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0009  max mem: 31830
Epoch: [0]  [ 80/312]  eta: 0:03:36  lr: 0.000051  min_lr: 0.000051  loss: 6.8889 (6.9309)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0010  max mem: 31830
Epoch: [0]  [ 90/312]  eta: 0:03:15  lr: 0.000058  min_lr: 0.000058  loss: 6.8814 (6.9247)  weight_decay: 0.0500 (0.0500)  time: 0.4141  data: 0.0010  max mem: 31830
Epoch: [0]  [100/312]  eta: 0:02:58  lr: 0.000064  min_lr: 0.000064  loss: 6.8735 (6.9196)  weight_decay: 0.0500 (0.0500)  time: 0.4743  data: 0.0010  max mem: 31830
Epoch: [0]  [110/312]  eta: 0:02:43  lr: 0.000071  min_lr: 0.000071  loss: 6.8609 (6.9136)  weight_decay: 0.0500 (0.0500)  time: 0.5009  data: 0.0300  max mem: 31830
Epoch: [0]  [120/312]  eta: 0:02:32  lr: 0.000077  min_lr: 0.000077  loss: 6.8474 (6.9081)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0640  max mem: 31830
Epoch: [0]  [130/312]  eta: 0:02:21  lr: 0.000083  min_lr: 0.000083  loss: 6.8343 (6.9017)  weight_decay: 0.0500 (0.0500)  time: 0.5726  data: 0.0532  max mem: 31830
Epoch: [0]  [140/312]  eta: 0:02:09  lr: 0.000090  min_lr: 0.000090  loss: 6.8178 (6.8953)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0379  max mem: 31830
Epoch: [0]  [150/312]  eta: 0:02:00  lr: 0.000096  min_lr: 0.000096  loss: 6.8005 (6.8881)  weight_decay: 0.0500 (0.0500)  time: 0.5510  data: 0.0481  max mem: 31830
Epoch: [0]  [160/312]  eta: 0:01:50  lr: 0.000103  min_lr: 0.000103  loss: 6.7893 (6.8825)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0293  max mem: 31830
Epoch: [0]  [170/312]  eta: 0:01:41  lr: 0.000109  min_lr: 0.000109  loss: 6.7898 (6.8767)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0171  max mem: 31830
Epoch: [0]  [180/312]  eta: 0:01:33  lr: 0.000115  min_lr: 0.000115  loss: 6.7766 (6.8703)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0174  max mem: 31830
Epoch: [0]  [190/312]  eta: 0:01:25  lr: 0.000122  min_lr: 0.000122  loss: 6.7422 (6.8636)  weight_decay: 0.0500 (0.0500)  time: 0.5653  data: 0.0147  max mem: 31830
Epoch: [0]  [200/312]  eta: 0:01:17  lr: 0.000128  min_lr: 0.000128  loss: 6.7266 (6.8565)  weight_decay: 0.0500 (0.0500)  time: 0.5552  data: 0.0334  max mem: 31830
Epoch: [0]  [210/312]  eta: 0:01:09  lr: 0.000135  min_lr: 0.000135  loss: 6.7067 (6.8493)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0199  max mem: 31830
Epoch: [0]  [220/312]  eta: 0:01:02  lr: 0.000141  min_lr: 0.000141  loss: 6.7040 (6.8422)  weight_decay: 0.0500 (0.0500)  time: 0.5228  data: 0.0086  max mem: 31830
Epoch: [0]  [230/312]  eta: 0:00:54  lr: 0.000147  min_lr: 0.000147  loss: 6.7020 (6.8357)  weight_decay: 0.0500 (0.0500)  time: 0.5535  data: 0.0246  max mem: 31830
Epoch: [0]  [240/312]  eta: 0:00:47  lr: 0.000154  min_lr: 0.000154  loss: 6.6919 (6.8293)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0170  max mem: 31830
Epoch: [0]  [250/312]  eta: 0:00:40  lr: 0.000160  min_lr: 0.000160  loss: 6.6728 (6.8220)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.0012  max mem: 31830
Epoch: [0]  [260/312]  eta: 0:00:33  lr: 0.000167  min_lr: 0.000167  loss: 6.6372 (6.8157)  weight_decay: 0.0500 (0.0500)  time: 0.5006  data: 0.0012  max mem: 31830
Epoch: [0]  [270/312]  eta: 0:00:27  lr: 0.000173  min_lr: 0.000173  loss: 6.6140 (6.8086)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0013  max mem: 31830
Epoch: [0]  [280/312]  eta: 0:00:20  lr: 0.000180  min_lr: 0.000180  loss: 6.6773 (6.8043)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0106  max mem: 31830
Epoch: [0]  [290/312]  eta: 0:00:14  lr: 0.000186  min_lr: 0.000186  loss: 6.6773 (6.7977)  weight_decay: 0.0500 (0.0500)  time: 0.4941  data: 0.0101  max mem: 31830
Epoch: [0]  [300/312]  eta: 0:00:07  lr: 0.000192  min_lr: 0.000192  loss: 6.5680 (6.7907)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0002  max mem: 31830
Epoch: [0]  [310/312]  eta: 0:00:01  lr: 0.000199  min_lr: 0.000199  loss: 6.6019 (6.7856)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0001  max mem: 31830
Epoch: [0]  [311/312]  eta: 0:00:00  lr: 0.000199  min_lr: 0.000199  loss: 6.6019 (6.7854)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0001  max mem: 31830
Epoch: [0] Total time: 0:03:17 (0.6322 s / it)
Averaged stats: lr: 0.000199  min_lr: 0.000199  loss: 6.6019 (6.7896)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:02:50  loss: 5.9981 (5.9981)  acc1: 2.3438 (2.3438)  acc5: 8.7240 (8.7240)  time: 18.9928  data: 9.2849  max mem: 31830
Test:  [8/9]  eta: 0:00:02  loss: 6.1236 (6.0550)  acc1: 2.3438 (2.5280)  acc5: 7.6823 (8.2720)  time: 2.4318  data: 1.0317  max mem: 31830
Test: Total time: 0:00:22 (2.4565 s / it)
* Acc@1 2.494 Acc@5 8.190 loss 6.061
Accuracy of the model on the 50000 test images: 2.5%
Max accuracy: 2.49%
Epoch: [1]  [  0/312]  eta: 1:25:57  lr: 0.000200  min_lr: 0.000200  loss: 6.6504 (6.6504)  weight_decay: 0.0500 (0.0500)  time: 16.5308  data: 9.3008  max mem: 31830
Epoch: [1]  [ 10/312]  eta: 0:09:19  lr: 0.000206  min_lr: 0.000206  loss: 6.6886 (6.6645)  weight_decay: 0.0500 (0.0500)  time: 1.8543  data: 0.8459  max mem: 31830
Epoch: [1]  [ 20/312]  eta: 0:05:40  lr: 0.000213  min_lr: 0.000213  loss: 6.6436 (6.6347)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0006  max mem: 31830
Epoch: [1]  [ 30/312]  eta: 0:04:18  lr: 0.000219  min_lr: 0.000219  loss: 6.6345 (6.6315)  weight_decay: 0.0500 (0.0500)  time: 0.4015  data: 0.0014  max mem: 31830
Epoch: [1]  [ 40/312]  eta: 0:03:34  lr: 0.000226  min_lr: 0.000226  loss: 6.6247 (6.6234)  weight_decay: 0.0500 (0.0500)  time: 0.3926  data: 0.0015  max mem: 31830
Epoch: [1]  [ 50/312]  eta: 0:03:06  lr: 0.000232  min_lr: 0.000232  loss: 6.5778 (6.6128)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0010  max mem: 31830
Epoch: [1]  [ 60/312]  eta: 0:02:46  lr: 0.000238  min_lr: 0.000238  loss: 6.5772 (6.6052)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0009  max mem: 31830
Epoch: [1]  [ 70/312]  eta: 0:02:31  lr: 0.000245  min_lr: 0.000245  loss: 6.5721 (6.5946)  weight_decay: 0.0500 (0.0500)  time: 0.4088  data: 0.0007  max mem: 31830
Epoch: [1]  [ 80/312]  eta: 0:02:23  lr: 0.000251  min_lr: 0.000251  loss: 6.5356 (6.5855)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0311  max mem: 31830
Epoch: [1]  [ 90/312]  eta: 0:02:15  lr: 0.000258  min_lr: 0.000258  loss: 6.5717 (6.5862)  weight_decay: 0.0500 (0.0500)  time: 0.5433  data: 0.0312  max mem: 31830
Epoch: [1]  [100/312]  eta: 0:02:07  lr: 0.000264  min_lr: 0.000264  loss: 6.5801 (6.5846)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0008  max mem: 31830
Epoch: [1]  [110/312]  eta: 0:02:00  lr: 0.000271  min_lr: 0.000271  loss: 6.5496 (6.5736)  weight_decay: 0.0500 (0.0500)  time: 0.5385  data: 0.0279  max mem: 31830
Epoch: [1]  [120/312]  eta: 0:01:53  lr: 0.000277  min_lr: 0.000277  loss: 6.5496 (6.5761)  weight_decay: 0.0500 (0.0500)  time: 0.5332  data: 0.0280  max mem: 31830
Epoch: [1]  [130/312]  eta: 0:01:48  lr: 0.000283  min_lr: 0.000283  loss: 6.5796 (6.5732)  weight_decay: 0.0500 (0.0500)  time: 0.5821  data: 0.0271  max mem: 31830
Epoch: [1]  [140/312]  eta: 0:01:40  lr: 0.000290  min_lr: 0.000290  loss: 6.5169 (6.5645)  weight_decay: 0.0500 (0.0500)  time: 0.5359  data: 0.0270  max mem: 31830
Epoch: [1]  [150/312]  eta: 0:01:34  lr: 0.000296  min_lr: 0.000296  loss: 6.4193 (6.5525)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.0233  max mem: 31830
Epoch: [1]  [160/312]  eta: 0:01:28  lr: 0.000303  min_lr: 0.000303  loss: 6.3877 (6.5432)  weight_decay: 0.0500 (0.0500)  time: 0.5802  data: 0.0488  max mem: 31830
Epoch: [1]  [170/312]  eta: 0:01:22  lr: 0.000309  min_lr: 0.000309  loss: 6.4297 (6.5415)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0264  max mem: 31830
Epoch: [1]  [180/312]  eta: 0:01:16  lr: 0.000315  min_lr: 0.000315  loss: 6.5121 (6.5383)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0143  max mem: 31830
Epoch: [1]  [190/312]  eta: 0:01:10  lr: 0.000322  min_lr: 0.000322  loss: 6.4382 (6.5314)  weight_decay: 0.0500 (0.0500)  time: 0.5562  data: 0.0378  max mem: 31830
Epoch: [1]  [200/312]  eta: 0:01:04  lr: 0.000328  min_lr: 0.000328  loss: 6.4909 (6.5330)  weight_decay: 0.0500 (0.0500)  time: 0.5416  data: 0.0242  max mem: 31830
Epoch: [1]  [210/312]  eta: 0:00:58  lr: 0.000335  min_lr: 0.000335  loss: 6.5280 (6.5266)  weight_decay: 0.0500 (0.0500)  time: 0.5549  data: 0.0164  max mem: 31830
Epoch: [1]  [220/312]  eta: 0:00:52  lr: 0.000341  min_lr: 0.000341  loss: 6.4454 (6.5204)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0165  max mem: 31830
Epoch: [1]  [230/312]  eta: 0:00:46  lr: 0.000347  min_lr: 0.000347  loss: 6.4435 (6.5133)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0014  max mem: 31830
Epoch: [1]  [240/312]  eta: 0:00:40  lr: 0.000354  min_lr: 0.000354  loss: 6.4527 (6.5095)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0142  max mem: 31830
Epoch: [1]  [250/312]  eta: 0:00:35  lr: 0.000360  min_lr: 0.000360  loss: 6.4989 (6.5078)  weight_decay: 0.0500 (0.0500)  time: 0.5595  data: 0.0136  max mem: 31830
Epoch: [1]  [260/312]  eta: 0:00:29  lr: 0.000367  min_lr: 0.000367  loss: 6.4831 (6.5042)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0010  max mem: 31830
Epoch: [1]  [270/312]  eta: 0:00:23  lr: 0.000373  min_lr: 0.000373  loss: 6.4831 (6.5024)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0013  max mem: 31830
Epoch: [1]  [280/312]  eta: 0:00:18  lr: 0.000380  min_lr: 0.000380  loss: 6.4589 (6.4986)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.0027  max mem: 31830
Epoch: [1]  [290/312]  eta: 0:00:12  lr: 0.000386  min_lr: 0.000386  loss: 6.3656 (6.4923)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0149  max mem: 31830
Epoch: [1]  [300/312]  eta: 0:00:06  lr: 0.000392  min_lr: 0.000392  loss: 6.3291 (6.4883)  weight_decay: 0.0500 (0.0500)  time: 0.4821  data: 0.0131  max mem: 31830
Epoch: [1]  [310/312]  eta: 0:00:01  lr: 0.000399  min_lr: 0.000399  loss: 6.3793 (6.4863)  weight_decay: 0.0500 (0.0500)  time: 0.3902  data: 0.0001  max mem: 31830
Epoch: [1]  [311/312]  eta: 0:00:00  lr: 0.000399  min_lr: 0.000399  loss: 6.3793 (6.4860)  weight_decay: 0.0500 (0.0500)  time: 0.3900  data: 0.0001  max mem: 31830
Epoch: [1] Total time: 0:02:54 (0.5596 s / it)
Averaged stats: lr: 0.000399  min_lr: 0.000399  loss: 6.3793 (6.4801)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 5.3462 (5.3462)  acc1: 5.8594 (5.8594)  acc5: 18.2292 (18.2292)  time: 8.2714  data: 8.1108  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 5.3691 (5.2772)  acc1: 6.9010 (6.9440)  acc5: 18.8802 (19.2640)  time: 1.0384  data: 0.9013  max mem: 31830
Test: Total time: 0:00:09 (1.0492 s / it)
* Acc@1 6.640 Acc@5 18.794 loss 5.298
Accuracy of the model on the 50000 test images: 6.6%
Max accuracy: 6.64%
Epoch: [2]  [  0/312]  eta: 1:00:58  lr: 0.000400  min_lr: 0.000400  loss: 6.4787 (6.4787)  weight_decay: 0.0500 (0.0500)  time: 11.7262  data: 10.6984  max mem: 31830
Epoch: [2]  [ 10/312]  eta: 0:08:31  lr: 0.000406  min_lr: 0.000406  loss: 6.2693 (6.3393)  weight_decay: 0.0500 (0.0500)  time: 1.6944  data: 1.0951  max mem: 31830
Epoch: [2]  [ 20/312]  eta: 0:05:28  lr: 0.000413  min_lr: 0.000413  loss: 6.2479 (6.2879)  weight_decay: 0.0500 (0.0500)  time: 0.5943  data: 0.0987  max mem: 31830
Epoch: [2]  [ 30/312]  eta: 0:04:10  lr: 0.000419  min_lr: 0.000419  loss: 6.2473 (6.2969)  weight_decay: 0.0500 (0.0500)  time: 0.4465  data: 0.0318  max mem: 31830
Epoch: [2]  [ 40/312]  eta: 0:03:28  lr: 0.000426  min_lr: 0.000426  loss: 6.2288 (6.2695)  weight_decay: 0.0500 (0.0500)  time: 0.3921  data: 0.0008  max mem: 31830
Epoch: [2]  [ 50/312]  eta: 0:03:14  lr: 0.000432  min_lr: 0.000432  loss: 6.3390 (6.2949)  weight_decay: 0.0500 (0.0500)  time: 0.5182  data: 0.0496  max mem: 31830
Epoch: [2]  [ 60/312]  eta: 0:02:52  lr: 0.000439  min_lr: 0.000439  loss: 6.3319 (6.2854)  weight_decay: 0.0500 (0.0500)  time: 0.5188  data: 0.0496  max mem: 31830
Epoch: [2]  [ 70/312]  eta: 0:02:40  lr: 0.000445  min_lr: 0.000445  loss: 6.1671 (6.2749)  weight_decay: 0.0500 (0.0500)  time: 0.4627  data: 0.0397  max mem: 31830
Epoch: [2]  [ 80/312]  eta: 0:02:32  lr: 0.000451  min_lr: 0.000451  loss: 6.0527 (6.2674)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0771  max mem: 31830
Epoch: [2]  [ 90/312]  eta: 0:02:20  lr: 0.000458  min_lr: 0.000458  loss: 6.0483 (6.2535)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0792  max mem: 31830
Epoch: [2]  [100/312]  eta: 0:02:13  lr: 0.000464  min_lr: 0.000464  loss: 6.1451 (6.2461)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.1091  max mem: 31830
Epoch: [2]  [110/312]  eta: 0:02:02  lr: 0.000471  min_lr: 0.000471  loss: 6.2515 (6.2498)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0680  max mem: 31830
Epoch: [2]  [120/312]  eta: 0:01:57  lr: 0.000477  min_lr: 0.000477  loss: 6.3441 (6.2550)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0842  max mem: 31830
Epoch: [2]  [130/312]  eta: 0:01:52  lr: 0.000483  min_lr: 0.000483  loss: 6.3255 (6.2480)  weight_decay: 0.0500 (0.0500)  time: 0.6703  data: 0.1436  max mem: 31830
Epoch: [2]  [140/312]  eta: 0:01:43  lr: 0.000490  min_lr: 0.000490  loss: 6.2996 (6.2523)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0602  max mem: 31830
Epoch: [2]  [150/312]  eta: 0:01:37  lr: 0.000496  min_lr: 0.000496  loss: 6.3539 (6.2515)  weight_decay: 0.0500 (0.0500)  time: 0.4844  data: 0.0384  max mem: 31830
Epoch: [2]  [160/312]  eta: 0:01:31  lr: 0.000503  min_lr: 0.000503  loss: 6.2417 (6.2454)  weight_decay: 0.0500 (0.0500)  time: 0.6136  data: 0.0383  max mem: 31830
Epoch: [2]  [170/312]  eta: 0:01:24  lr: 0.000509  min_lr: 0.000509  loss: 6.2321 (6.2449)  weight_decay: 0.0500 (0.0500)  time: 0.5795  data: 0.0529  max mem: 31830
Epoch: [2]  [180/312]  eta: 0:01:18  lr: 0.000515  min_lr: 0.000515  loss: 6.2033 (6.2376)  weight_decay: 0.0500 (0.0500)  time: 0.5407  data: 0.0599  max mem: 31830
Epoch: [2]  [190/312]  eta: 0:01:11  lr: 0.000522  min_lr: 0.000522  loss: 6.0490 (6.2255)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0077  max mem: 31830
Epoch: [2]  [200/312]  eta: 0:01:05  lr: 0.000528  min_lr: 0.000528  loss: 5.9704 (6.2223)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0162  max mem: 31830
Epoch: [2]  [210/312]  eta: 0:00:59  lr: 0.000535  min_lr: 0.000535  loss: 6.0944 (6.2123)  weight_decay: 0.0500 (0.0500)  time: 0.6115  data: 0.0394  max mem: 31830
Epoch: [2]  [220/312]  eta: 0:00:53  lr: 0.000541  min_lr: 0.000541  loss: 5.9553 (6.2053)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0241  max mem: 31830
Epoch: [2]  [230/312]  eta: 0:00:47  lr: 0.000548  min_lr: 0.000548  loss: 6.2336 (6.2051)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0284  max mem: 31830
Epoch: [2]  [240/312]  eta: 0:00:41  lr: 0.000554  min_lr: 0.000554  loss: 6.1610 (6.2003)  weight_decay: 0.0500 (0.0500)  time: 0.6184  data: 0.0284  max mem: 31830
Epoch: [2]  [250/312]  eta: 0:00:35  lr: 0.000560  min_lr: 0.000560  loss: 6.0957 (6.1974)  weight_decay: 0.0500 (0.0500)  time: 0.5081  data: 0.0010  max mem: 31830
Epoch: [2]  [260/312]  eta: 0:00:30  lr: 0.000567  min_lr: 0.000567  loss: 6.0992 (6.1896)  weight_decay: 0.0500 (0.0500)  time: 0.5559  data: 0.0012  max mem: 31830
Epoch: [2]  [270/312]  eta: 0:00:24  lr: 0.000573  min_lr: 0.000573  loss: 6.0992 (6.1851)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0011  max mem: 31830
Epoch: [2]  [280/312]  eta: 0:00:18  lr: 0.000580  min_lr: 0.000580  loss: 6.1705 (6.1829)  weight_decay: 0.0500 (0.0500)  time: 0.5309  data: 0.0177  max mem: 31830
Epoch: [2]  [290/312]  eta: 0:00:12  lr: 0.000586  min_lr: 0.000586  loss: 6.2102 (6.1783)  weight_decay: 0.0500 (0.0500)  time: 0.5588  data: 0.0174  max mem: 31830
Epoch: [2]  [300/312]  eta: 0:00:06  lr: 0.000592  min_lr: 0.000592  loss: 6.2940 (6.1810)  weight_decay: 0.0500 (0.0500)  time: 0.4154  data: 0.0002  max mem: 31830
Epoch: [2]  [310/312]  eta: 0:00:01  lr: 0.000599  min_lr: 0.000599  loss: 6.2074 (6.1779)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [2]  [311/312]  eta: 0:00:00  lr: 0.000599  min_lr: 0.000599  loss: 6.1962 (6.1761)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [2] Total time: 0:02:55 (0.5635 s / it)
Averaged stats: lr: 0.000599  min_lr: 0.000599  loss: 6.1962 (6.1902)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 4.6660 (4.6660)  acc1: 12.3698 (12.3698)  acc5: 33.2031 (33.2031)  time: 8.5542  data: 8.3884  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 4.6660 (4.6685)  acc1: 12.3698 (12.7520)  acc5: 30.7292 (30.4800)  time: 1.0670  data: 0.9321  max mem: 31830
Test: Total time: 0:00:09 (1.0798 s / it)
* Acc@1 12.790 Acc@5 30.774 loss 4.678
Accuracy of the model on the 50000 test images: 12.8%
Max accuracy: 12.79%
Epoch: [3]  [  0/312]  eta: 0:59:57  lr: 0.000600  min_lr: 0.000600  loss: 6.3499 (6.3499)  weight_decay: 0.0500 (0.0500)  time: 11.5307  data: 9.6134  max mem: 31830
Epoch: [3]  [ 10/312]  eta: 0:08:59  lr: 0.000607  min_lr: 0.000607  loss: 6.1024 (5.9832)  weight_decay: 0.0500 (0.0500)  time: 1.7854  data: 0.9217  max mem: 31830
Epoch: [3]  [ 20/312]  eta: 0:05:35  lr: 0.000613  min_lr: 0.000613  loss: 5.9341 (5.9603)  weight_decay: 0.0500 (0.0500)  time: 0.6301  data: 0.0265  max mem: 31830
Epoch: [3]  [ 30/312]  eta: 0:04:15  lr: 0.000619  min_lr: 0.000619  loss: 6.0637 (6.0113)  weight_decay: 0.0500 (0.0500)  time: 0.4235  data: 0.0012  max mem: 31830
Epoch: [3]  [ 40/312]  eta: 0:03:33  lr: 0.000626  min_lr: 0.000626  loss: 6.2302 (6.0392)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0013  max mem: 31830
Epoch: [3]  [ 50/312]  eta: 0:03:05  lr: 0.000632  min_lr: 0.000632  loss: 6.2302 (6.0398)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0009  max mem: 31830
Epoch: [3]  [ 60/312]  eta: 0:02:45  lr: 0.000639  min_lr: 0.000639  loss: 6.0975 (6.0254)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [3]  [ 70/312]  eta: 0:02:38  lr: 0.000645  min_lr: 0.000645  loss: 6.0422 (6.0218)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0008  max mem: 31830
Epoch: [3]  [ 80/312]  eta: 0:02:25  lr: 0.000651  min_lr: 0.000651  loss: 6.1398 (6.0318)  weight_decay: 0.0500 (0.0500)  time: 0.5433  data: 0.0008  max mem: 31830
Epoch: [3]  [ 90/312]  eta: 0:02:21  lr: 0.000658  min_lr: 0.000658  loss: 6.0550 (6.0109)  weight_decay: 0.0500 (0.0500)  time: 0.5870  data: 0.0009  max mem: 31830
Epoch: [3]  [100/312]  eta: 0:02:15  lr: 0.000664  min_lr: 0.000664  loss: 6.0158 (6.0056)  weight_decay: 0.0500 (0.0500)  time: 0.6888  data: 0.0010  max mem: 31830
Epoch: [3]  [110/312]  eta: 0:02:05  lr: 0.000671  min_lr: 0.000671  loss: 6.1521 (6.0078)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0008  max mem: 31830
Epoch: [3]  [120/312]  eta: 0:02:00  lr: 0.000677  min_lr: 0.000677  loss: 6.1738 (6.0139)  weight_decay: 0.0500 (0.0500)  time: 0.5614  data: 0.0016  max mem: 31830
Epoch: [3]  [130/312]  eta: 0:01:54  lr: 0.000683  min_lr: 0.000683  loss: 6.1256 (6.0107)  weight_decay: 0.0500 (0.0500)  time: 0.6449  data: 0.0135  max mem: 31830
Epoch: [3]  [140/312]  eta: 0:01:45  lr: 0.000690  min_lr: 0.000690  loss: 5.9193 (5.9999)  weight_decay: 0.0500 (0.0500)  time: 0.5308  data: 0.0129  max mem: 31830
Epoch: [3]  [150/312]  eta: 0:01:40  lr: 0.000696  min_lr: 0.000696  loss: 5.8741 (5.9950)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0011  max mem: 31830
Epoch: [3]  [160/312]  eta: 0:01:32  lr: 0.000703  min_lr: 0.000703  loss: 6.0213 (5.9902)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0014  max mem: 31830
Epoch: [3]  [170/312]  eta: 0:01:25  lr: 0.000709  min_lr: 0.000709  loss: 6.0602 (5.9878)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0014  max mem: 31830
Epoch: [3]  [180/312]  eta: 0:01:19  lr: 0.000715  min_lr: 0.000715  loss: 6.1115 (5.9910)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0009  max mem: 31830
Epoch: [3]  [190/312]  eta: 0:01:12  lr: 0.000722  min_lr: 0.000722  loss: 6.1115 (5.9902)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0009  max mem: 31830
Epoch: [3]  [200/312]  eta: 0:01:07  lr: 0.000728  min_lr: 0.000728  loss: 5.9150 (5.9849)  weight_decay: 0.0500 (0.0500)  time: 0.5684  data: 0.0142  max mem: 31830
Epoch: [3]  [210/312]  eta: 0:01:00  lr: 0.000735  min_lr: 0.000735  loss: 6.0420 (5.9845)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.0143  max mem: 31830
Epoch: [3]  [220/312]  eta: 0:00:53  lr: 0.000741  min_lr: 0.000741  loss: 6.0835 (5.9805)  weight_decay: 0.0500 (0.0500)  time: 0.4534  data: 0.0012  max mem: 31830
Epoch: [3]  [230/312]  eta: 0:00:48  lr: 0.000748  min_lr: 0.000748  loss: 5.8718 (5.9703)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0148  max mem: 31830
Epoch: [3]  [240/312]  eta: 0:00:41  lr: 0.000754  min_lr: 0.000754  loss: 6.0586 (5.9770)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0145  max mem: 31830
Epoch: [3]  [250/312]  eta: 0:00:36  lr: 0.000760  min_lr: 0.000760  loss: 6.1952 (5.9822)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0009  max mem: 31830
Epoch: [3]  [260/312]  eta: 0:00:30  lr: 0.000767  min_lr: 0.000767  loss: 5.9343 (5.9757)  weight_decay: 0.0500 (0.0500)  time: 0.6352  data: 0.0012  max mem: 31830
Epoch: [3]  [270/312]  eta: 0:00:24  lr: 0.000773  min_lr: 0.000773  loss: 5.9343 (5.9768)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0011  max mem: 31830
Epoch: [3]  [280/312]  eta: 0:00:18  lr: 0.000780  min_lr: 0.000780  loss: 6.0168 (5.9725)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0027  max mem: 31830
Epoch: [3]  [290/312]  eta: 0:00:12  lr: 0.000786  min_lr: 0.000786  loss: 5.8306 (5.9653)  weight_decay: 0.0500 (0.0500)  time: 0.5362  data: 0.0024  max mem: 31830
Epoch: [3]  [300/312]  eta: 0:00:06  lr: 0.000792  min_lr: 0.000792  loss: 5.8135 (5.9600)  weight_decay: 0.0500 (0.0500)  time: 0.4508  data: 0.0002  max mem: 31830
Epoch: [3]  [310/312]  eta: 0:00:01  lr: 0.000799  min_lr: 0.000799  loss: 5.9637 (5.9580)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [3]  [311/312]  eta: 0:00:00  lr: 0.000799  min_lr: 0.000799  loss: 5.9637 (5.9565)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [3] Total time: 0:02:57 (0.5674 s / it)
Averaged stats: lr: 0.000799  min_lr: 0.000799  loss: 5.9637 (5.9440)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 3.9941 (3.9941)  acc1: 22.9167 (22.9167)  acc5: 47.3958 (47.3958)  time: 7.8229  data: 7.6559  max mem: 31830
Test:  [8/9]  eta: 0:00:00  loss: 3.9989 (4.0573)  acc1: 19.9219 (20.6080)  acc5: 46.2240 (43.0560)  time: 0.9876  data: 0.8508  max mem: 31830
Test: Total time: 0:00:09 (1.0095 s / it)
* Acc@1 20.268 Acc@5 42.884 loss 4.045
Accuracy of the model on the 50000 test images: 20.3%
Max accuracy: 20.27%
Epoch: [4]  [  0/312]  eta: 1:00:53  lr: 0.000800  min_lr: 0.000800  loss: 5.1157 (5.1157)  weight_decay: 0.0500 (0.0500)  time: 11.7091  data: 9.3921  max mem: 31830
Epoch: [4]  [ 10/312]  eta: 0:09:02  lr: 0.000807  min_lr: 0.000807  loss: 5.9250 (5.7658)  weight_decay: 0.0500 (0.0500)  time: 1.7965  data: 0.9464  max mem: 31830
Epoch: [4]  [ 20/312]  eta: 0:05:43  lr: 0.000813  min_lr: 0.000813  loss: 5.9769 (5.8683)  weight_decay: 0.0500 (0.0500)  time: 0.6512  data: 0.0793  max mem: 31830
Epoch: [4]  [ 30/312]  eta: 0:04:21  lr: 0.000819  min_lr: 0.000819  loss: 6.0460 (5.8725)  weight_decay: 0.0500 (0.0500)  time: 0.4470  data: 0.0288  max mem: 31830
Epoch: [4]  [ 40/312]  eta: 0:03:36  lr: 0.000826  min_lr: 0.000826  loss: 6.0460 (5.8911)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0008  max mem: 31830
Epoch: [4]  [ 50/312]  eta: 0:03:08  lr: 0.000832  min_lr: 0.000832  loss: 5.9397 (5.8743)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0009  max mem: 31830
Epoch: [4]  [ 60/312]  eta: 0:02:47  lr: 0.000839  min_lr: 0.000839  loss: 5.8100 (5.8490)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0008  max mem: 31830
Epoch: [4]  [ 70/312]  eta: 0:02:32  lr: 0.000845  min_lr: 0.000845  loss: 5.6358 (5.8112)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0008  max mem: 31830
Epoch: [4]  [ 80/312]  eta: 0:02:22  lr: 0.000851  min_lr: 0.000851  loss: 5.6089 (5.7983)  weight_decay: 0.0500 (0.0500)  time: 0.4495  data: 0.0017  max mem: 31830
Epoch: [4]  [ 90/312]  eta: 0:02:15  lr: 0.000858  min_lr: 0.000858  loss: 5.9747 (5.8036)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0231  max mem: 31830
Epoch: [4]  [100/312]  eta: 0:02:09  lr: 0.000864  min_lr: 0.000864  loss: 5.8814 (5.8050)  weight_decay: 0.0500 (0.0500)  time: 0.6022  data: 0.0360  max mem: 31830
Epoch: [4]  [110/312]  eta: 0:02:01  lr: 0.000871  min_lr: 0.000871  loss: 5.8917 (5.8140)  weight_decay: 0.0500 (0.0500)  time: 0.5637  data: 0.0281  max mem: 31830
Epoch: [4]  [120/312]  eta: 0:01:55  lr: 0.000877  min_lr: 0.000877  loss: 5.9969 (5.8225)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0256  max mem: 31830
Epoch: [4]  [130/312]  eta: 0:01:50  lr: 0.000883  min_lr: 0.000883  loss: 5.9897 (5.8263)  weight_decay: 0.0500 (0.0500)  time: 0.6524  data: 0.0123  max mem: 31830
Epoch: [4]  [140/312]  eta: 0:01:42  lr: 0.000890  min_lr: 0.000890  loss: 5.9584 (5.8269)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0009  max mem: 31830
Epoch: [4]  [150/312]  eta: 0:01:36  lr: 0.000896  min_lr: 0.000896  loss: 5.9195 (5.8203)  weight_decay: 0.0500 (0.0500)  time: 0.5006  data: 0.0012  max mem: 31830
Epoch: [4]  [160/312]  eta: 0:01:30  lr: 0.000903  min_lr: 0.000903  loss: 5.8587 (5.8234)  weight_decay: 0.0500 (0.0500)  time: 0.5870  data: 0.0012  max mem: 31830
Epoch: [4]  [170/312]  eta: 0:01:23  lr: 0.000909  min_lr: 0.000909  loss: 5.8571 (5.8158)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0010  max mem: 31830
Epoch: [4]  [180/312]  eta: 0:01:17  lr: 0.000916  min_lr: 0.000916  loss: 5.7691 (5.8052)  weight_decay: 0.0500 (0.0500)  time: 0.5684  data: 0.0015  max mem: 31830
Epoch: [4]  [190/312]  eta: 0:01:11  lr: 0.000922  min_lr: 0.000922  loss: 5.7910 (5.8006)  weight_decay: 0.0500 (0.0500)  time: 0.5706  data: 0.0014  max mem: 31830
Epoch: [4]  [200/312]  eta: 0:01:06  lr: 0.000928  min_lr: 0.000928  loss: 5.8410 (5.7987)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0124  max mem: 31830
Epoch: [4]  [210/312]  eta: 0:00:59  lr: 0.000935  min_lr: 0.000935  loss: 5.9812 (5.7969)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0123  max mem: 31830
Epoch: [4]  [220/312]  eta: 0:00:53  lr: 0.000941  min_lr: 0.000941  loss: 5.8797 (5.7951)  weight_decay: 0.0500 (0.0500)  time: 0.4785  data: 0.0311  max mem: 31830
Epoch: [4]  [230/312]  eta: 0:00:48  lr: 0.000948  min_lr: 0.000948  loss: 5.7882 (5.7812)  weight_decay: 0.0500 (0.0500)  time: 0.6045  data: 0.0539  max mem: 31830
Epoch: [4]  [240/312]  eta: 0:00:41  lr: 0.000954  min_lr: 0.000954  loss: 5.2377 (5.7626)  weight_decay: 0.0500 (0.0500)  time: 0.6129  data: 0.0234  max mem: 31830
Epoch: [4]  [250/312]  eta: 0:00:35  lr: 0.000960  min_lr: 0.000960  loss: 5.2813 (5.7491)  weight_decay: 0.0500 (0.0500)  time: 0.4618  data: 0.0126  max mem: 31830
Epoch: [4]  [260/312]  eta: 0:00:30  lr: 0.000967  min_lr: 0.000967  loss: 5.6692 (5.7541)  weight_decay: 0.0500 (0.0500)  time: 0.6028  data: 0.0127  max mem: 31830
Epoch: [4]  [270/312]  eta: 0:00:24  lr: 0.000973  min_lr: 0.000973  loss: 5.8747 (5.7528)  weight_decay: 0.0500 (0.0500)  time: 0.6125  data: 0.0112  max mem: 31830
Epoch: [4]  [280/312]  eta: 0:00:18  lr: 0.000980  min_lr: 0.000980  loss: 5.6997 (5.7480)  weight_decay: 0.0500 (0.0500)  time: 0.4939  data: 0.0402  max mem: 31830
Epoch: [4]  [290/312]  eta: 0:00:12  lr: 0.000986  min_lr: 0.000986  loss: 5.6049 (5.7442)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0296  max mem: 31830
Epoch: [4]  [300/312]  eta: 0:00:06  lr: 0.000992  min_lr: 0.000992  loss: 5.5098 (5.7346)  weight_decay: 0.0500 (0.0500)  time: 0.4434  data: 0.0002  max mem: 31830
Epoch: [4]  [310/312]  eta: 0:00:01  lr: 0.000999  min_lr: 0.000999  loss: 5.5545 (5.7322)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [4]  [311/312]  eta: 0:00:00  lr: 0.001000  min_lr: 0.001000  loss: 5.5484 (5.7302)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [4] Total time: 0:02:56 (0.5659 s / it)
Averaged stats: lr: 0.001000  min_lr: 0.001000  loss: 5.5484 (5.7123)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 3.4743 (3.4743)  acc1: 32.0312 (32.0312)  acc5: 55.7292 (55.7292)  time: 7.8229  data: 7.6627  max mem: 31830
Test:  [8/9]  eta: 0:00:00  loss: 3.5867 (3.5897)  acc1: 27.9948 (27.4880)  acc5: 52.0833 (51.2800)  time: 0.9865  data: 0.8515  max mem: 31830
Test: Total time: 0:00:09 (1.0013 s / it)
* Acc@1 27.240 Acc@5 51.932 loss 3.571
Accuracy of the model on the 50000 test images: 27.2%
Max accuracy: 27.24%
Epoch: [5]  [  0/312]  eta: 1:02:06  lr: 0.001000  min_lr: 0.001000  loss: 4.7372 (4.7372)  weight_decay: 0.0500 (0.0500)  time: 11.9451  data: 10.0609  max mem: 31830
Epoch: [5]  [ 10/312]  eta: 0:08:29  lr: 0.001007  min_lr: 0.001007  loss: 5.3198 (5.2899)  weight_decay: 0.0500 (0.0500)  time: 1.6868  data: 0.9152  max mem: 31830
Epoch: [5]  [ 20/312]  eta: 0:05:23  lr: 0.001013  min_lr: 0.001013  loss: 5.3219 (5.3997)  weight_decay: 0.0500 (0.0500)  time: 0.5676  data: 0.0141  max mem: 31830
Epoch: [5]  [ 30/312]  eta: 0:04:07  lr: 0.001019  min_lr: 0.001019  loss: 5.7086 (5.4992)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0145  max mem: 31830
Epoch: [5]  [ 40/312]  eta: 0:03:26  lr: 0.001026  min_lr: 0.001026  loss: 5.7769 (5.5773)  weight_decay: 0.0500 (0.0500)  time: 0.3942  data: 0.0011  max mem: 31830
Epoch: [5]  [ 50/312]  eta: 0:03:02  lr: 0.001032  min_lr: 0.001032  loss: 5.7206 (5.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0009  max mem: 31830
Epoch: [5]  [ 60/312]  eta: 0:02:46  lr: 0.001039  min_lr: 0.001039  loss: 5.6062 (5.5853)  weight_decay: 0.0500 (0.0500)  time: 0.4606  data: 0.0010  max mem: 31830
Epoch: [5]  [ 70/312]  eta: 0:02:40  lr: 0.001045  min_lr: 0.001045  loss: 5.5905 (5.5946)  weight_decay: 0.0500 (0.0500)  time: 0.5785  data: 0.0009  max mem: 31830
Epoch: [5]  [ 80/312]  eta: 0:02:28  lr: 0.001051  min_lr: 0.001051  loss: 5.7066 (5.5943)  weight_decay: 0.0500 (0.0500)  time: 0.5710  data: 0.0007  max mem: 31830
Epoch: [5]  [ 90/312]  eta: 0:02:18  lr: 0.001058  min_lr: 0.001058  loss: 5.3940 (5.5460)  weight_decay: 0.0500 (0.0500)  time: 0.4826  data: 0.0007  max mem: 31830
Epoch: [5]  [100/312]  eta: 0:02:11  lr: 0.001064  min_lr: 0.001064  loss: 5.1315 (5.5140)  weight_decay: 0.0500 (0.0500)  time: 0.5461  data: 0.0008  max mem: 31830
Epoch: [5]  [110/312]  eta: 0:02:01  lr: 0.001071  min_lr: 0.001071  loss: 5.4206 (5.5170)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.0015  max mem: 31830
Epoch: [5]  [120/312]  eta: 0:01:56  lr: 0.001077  min_lr: 0.001077  loss: 5.7812 (5.5196)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0015  max mem: 31830
Epoch: [5]  [130/312]  eta: 0:01:50  lr: 0.001084  min_lr: 0.001084  loss: 5.6965 (5.5220)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.0008  max mem: 31830
Epoch: [5]  [140/312]  eta: 0:01:42  lr: 0.001090  min_lr: 0.001090  loss: 5.7849 (5.5439)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0014  max mem: 31830
Epoch: [5]  [150/312]  eta: 0:01:36  lr: 0.001096  min_lr: 0.001096  loss: 5.6334 (5.5364)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0254  max mem: 31830
Epoch: [5]  [160/312]  eta: 0:01:29  lr: 0.001103  min_lr: 0.001103  loss: 5.4229 (5.5271)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0373  max mem: 31830
Epoch: [5]  [170/312]  eta: 0:01:23  lr: 0.001109  min_lr: 0.001109  loss: 5.8033 (5.5382)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0132  max mem: 31830
Epoch: [5]  [180/312]  eta: 0:01:17  lr: 0.001116  min_lr: 0.001116  loss: 5.8141 (5.5325)  weight_decay: 0.0500 (0.0500)  time: 0.5813  data: 0.0009  max mem: 31830
Epoch: [5]  [190/312]  eta: 0:01:10  lr: 0.001122  min_lr: 0.001122  loss: 5.2757 (5.5242)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0010  max mem: 31830
Epoch: [5]  [200/312]  eta: 0:01:05  lr: 0.001128  min_lr: 0.001128  loss: 5.3089 (5.5202)  weight_decay: 0.0500 (0.0500)  time: 0.5392  data: 0.0009  max mem: 31830
Epoch: [5]  [210/312]  eta: 0:00:59  lr: 0.001135  min_lr: 0.001135  loss: 5.5961 (5.5233)  weight_decay: 0.0500 (0.0500)  time: 0.5869  data: 0.0015  max mem: 31830
Epoch: [5]  [220/312]  eta: 0:00:53  lr: 0.001141  min_lr: 0.001141  loss: 5.7166 (5.5253)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0015  max mem: 31830
Epoch: [5]  [230/312]  eta: 0:00:47  lr: 0.001148  min_lr: 0.001148  loss: 5.6169 (5.5175)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.0008  max mem: 31830
Epoch: [5]  [240/312]  eta: 0:00:41  lr: 0.001154  min_lr: 0.001154  loss: 5.6477 (5.5235)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0009  max mem: 31830
Epoch: [5]  [250/312]  eta: 0:00:35  lr: 0.001160  min_lr: 0.001160  loss: 5.6485 (5.5156)  weight_decay: 0.0500 (0.0500)  time: 0.5362  data: 0.0010  max mem: 31830
Epoch: [5]  [260/312]  eta: 0:00:30  lr: 0.001167  min_lr: 0.001167  loss: 5.4466 (5.5169)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.0010  max mem: 31830
Epoch: [5]  [270/312]  eta: 0:00:24  lr: 0.001173  min_lr: 0.001173  loss: 5.7107 (5.5193)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.0016  max mem: 31830
Epoch: [5]  [280/312]  eta: 0:00:18  lr: 0.001180  min_lr: 0.001180  loss: 5.6062 (5.5154)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0034  max mem: 31830
Epoch: [5]  [290/312]  eta: 0:00:12  lr: 0.001186  min_lr: 0.001186  loss: 5.3503 (5.5051)  weight_decay: 0.0500 (0.0500)  time: 0.5531  data: 0.0023  max mem: 31830
Epoch: [5]  [300/312]  eta: 0:00:06  lr: 0.001192  min_lr: 0.001192  loss: 5.2611 (5.5010)  weight_decay: 0.0500 (0.0500)  time: 0.4738  data: 0.0002  max mem: 31830
Epoch: [5]  [310/312]  eta: 0:00:01  lr: 0.001199  min_lr: 0.001199  loss: 5.3857 (5.4907)  weight_decay: 0.0500 (0.0500)  time: 0.4243  data: 0.0001  max mem: 31830
Epoch: [5]  [311/312]  eta: 0:00:00  lr: 0.001200  min_lr: 0.001200  loss: 5.3857 (5.4893)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [5] Total time: 0:02:56 (0.5643 s / it)
Averaged stats: lr: 0.001200  min_lr: 0.001200  loss: 5.3857 (5.5097)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 3.1711 (3.1711)  acc1: 38.1510 (38.1510)  acc5: 62.1094 (62.1094)  time: 8.5334  data: 8.3734  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 3.3861 (3.2658)  acc1: 32.9427 (33.1680)  acc5: 56.3802 (57.1840)  time: 1.0700  data: 0.9304  max mem: 31830
Test: Total time: 0:00:09 (1.0797 s / it)
* Acc@1 33.042 Acc@5 58.296 loss 3.257
Accuracy of the model on the 50000 test images: 33.0%
Max accuracy: 33.04%
Epoch: [6]  [  0/312]  eta: 1:03:36  lr: 0.001200  min_lr: 0.001200  loss: 5.9734 (5.9734)  weight_decay: 0.0500 (0.0500)  time: 12.2339  data: 9.6518  max mem: 31830
Epoch: [6]  [ 10/312]  eta: 0:08:53  lr: 0.001207  min_lr: 0.001207  loss: 5.7149 (5.5714)  weight_decay: 0.0500 (0.0500)  time: 1.7653  data: 0.9795  max mem: 31830
Epoch: [6]  [ 20/312]  eta: 0:05:42  lr: 0.001213  min_lr: 0.001213  loss: 5.5950 (5.4658)  weight_decay: 0.0500 (0.0500)  time: 0.6196  data: 0.0565  max mem: 31830
Epoch: [6]  [ 30/312]  eta: 0:04:20  lr: 0.001219  min_lr: 0.001219  loss: 5.3236 (5.4186)  weight_decay: 0.0500 (0.0500)  time: 0.4600  data: 0.0008  max mem: 31830
Epoch: [6]  [ 40/312]  eta: 0:03:35  lr: 0.001226  min_lr: 0.001226  loss: 5.2699 (5.4137)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0008  max mem: 31830
Epoch: [6]  [ 50/312]  eta: 0:03:07  lr: 0.001232  min_lr: 0.001232  loss: 5.1904 (5.3302)  weight_decay: 0.0500 (0.0500)  time: 0.3939  data: 0.0008  max mem: 31830
Epoch: [6]  [ 60/312]  eta: 0:02:46  lr: 0.001239  min_lr: 0.001239  loss: 5.0719 (5.3118)  weight_decay: 0.0500 (0.0500)  time: 0.3934  data: 0.0011  max mem: 31830
Epoch: [6]  [ 70/312]  eta: 0:02:33  lr: 0.001245  min_lr: 0.001245  loss: 5.3329 (5.3154)  weight_decay: 0.0500 (0.0500)  time: 0.4255  data: 0.0010  max mem: 31830
Epoch: [6]  [ 80/312]  eta: 0:02:26  lr: 0.001251  min_lr: 0.001251  loss: 5.3329 (5.2955)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0008  max mem: 31830
Epoch: [6]  [ 90/312]  eta: 0:02:16  lr: 0.001258  min_lr: 0.001258  loss: 5.3643 (5.3014)  weight_decay: 0.0500 (0.0500)  time: 0.5432  data: 0.0132  max mem: 31830
Epoch: [6]  [100/312]  eta: 0:02:08  lr: 0.001264  min_lr: 0.001264  loss: 5.3643 (5.2867)  weight_decay: 0.0500 (0.0500)  time: 0.5089  data: 0.0133  max mem: 31830
Epoch: [6]  [110/312]  eta: 0:01:59  lr: 0.001271  min_lr: 0.001271  loss: 5.1952 (5.2837)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0008  max mem: 31830
Epoch: [6]  [120/312]  eta: 0:01:53  lr: 0.001277  min_lr: 0.001277  loss: 5.2242 (5.2779)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0007  max mem: 31830
Epoch: [6]  [130/312]  eta: 0:01:47  lr: 0.001284  min_lr: 0.001284  loss: 5.3742 (5.2812)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0010  max mem: 31830
Epoch: [6]  [140/312]  eta: 0:01:40  lr: 0.001290  min_lr: 0.001290  loss: 5.5252 (5.2998)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0229  max mem: 31830
Epoch: [6]  [150/312]  eta: 0:01:34  lr: 0.001296  min_lr: 0.001296  loss: 5.6558 (5.3075)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0229  max mem: 31830
Epoch: [6]  [160/312]  eta: 0:01:28  lr: 0.001303  min_lr: 0.001303  loss: 5.6435 (5.3217)  weight_decay: 0.0500 (0.0500)  time: 0.5650  data: 0.0056  max mem: 31830
Epoch: [6]  [170/312]  eta: 0:01:21  lr: 0.001309  min_lr: 0.001309  loss: 5.6364 (5.3245)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0185  max mem: 31830
Epoch: [6]  [180/312]  eta: 0:01:16  lr: 0.001316  min_lr: 0.001316  loss: 5.3011 (5.3225)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0139  max mem: 31830
Epoch: [6]  [190/312]  eta: 0:01:09  lr: 0.001322  min_lr: 0.001322  loss: 5.1522 (5.3096)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0131  max mem: 31830
Epoch: [6]  [200/312]  eta: 0:01:03  lr: 0.001328  min_lr: 0.001328  loss: 5.3400 (5.3218)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0130  max mem: 31830
Epoch: [6]  [210/312]  eta: 0:00:58  lr: 0.001335  min_lr: 0.001335  loss: 5.3400 (5.3103)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0070  max mem: 31830
Epoch: [6]  [220/312]  eta: 0:00:52  lr: 0.001341  min_lr: 0.001341  loss: 5.4815 (5.3241)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0198  max mem: 31830
Epoch: [6]  [230/312]  eta: 0:00:46  lr: 0.001348  min_lr: 0.001348  loss: 5.5894 (5.3164)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0137  max mem: 31830
Epoch: [6]  [240/312]  eta: 0:00:40  lr: 0.001354  min_lr: 0.001354  loss: 5.2789 (5.3138)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0009  max mem: 31830
Epoch: [6]  [250/312]  eta: 0:00:35  lr: 0.001360  min_lr: 0.001360  loss: 5.3972 (5.3142)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.0142  max mem: 31830
Epoch: [6]  [260/312]  eta: 0:00:29  lr: 0.001367  min_lr: 0.001367  loss: 5.5022 (5.3180)  weight_decay: 0.0500 (0.0500)  time: 0.5339  data: 0.0147  max mem: 31830
Epoch: [6]  [270/312]  eta: 0:00:23  lr: 0.001373  min_lr: 0.001373  loss: 5.5990 (5.3215)  weight_decay: 0.0500 (0.0500)  time: 0.5898  data: 0.0017  max mem: 31830
Epoch: [6]  [280/312]  eta: 0:00:18  lr: 0.001380  min_lr: 0.001380  loss: 5.3745 (5.3210)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0024  max mem: 31830
Epoch: [6]  [290/312]  eta: 0:00:12  lr: 0.001386  min_lr: 0.001386  loss: 5.5195 (5.3238)  weight_decay: 0.0500 (0.0500)  time: 0.5283  data: 0.0199  max mem: 31830
Epoch: [6]  [300/312]  eta: 0:00:06  lr: 0.001393  min_lr: 0.001393  loss: 5.5195 (5.3217)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0182  max mem: 31830
Epoch: [6]  [310/312]  eta: 0:00:01  lr: 0.001399  min_lr: 0.001399  loss: 5.3746 (5.3209)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0001  max mem: 31830
Epoch: [6]  [311/312]  eta: 0:00:00  lr: 0.001400  min_lr: 0.001400  loss: 5.2753 (5.3186)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0001  max mem: 31830
Epoch: [6] Total time: 0:02:54 (0.5578 s / it)
Averaged stats: lr: 0.001400  min_lr: 0.001400  loss: 5.2753 (5.3235)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 2.6598 (2.6598)  acc1: 46.2240 (46.2240)  acc5: 69.7917 (69.7917)  time: 8.3539  data: 8.1869  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.9884 (2.8885)  acc1: 38.9323 (39.3600)  acc5: 64.8438 (64.1440)  time: 1.0449  data: 0.9098  max mem: 31830
Test: Total time: 0:00:09 (1.0571 s / it)
* Acc@1 38.940 Acc@5 65.122 loss 2.878
Accuracy of the model on the 50000 test images: 38.9%
Max accuracy: 38.94%
Epoch: [7]  [  0/312]  eta: 1:01:33  lr: 0.001400  min_lr: 0.001400  loss: 5.5799 (5.5799)  weight_decay: 0.0500 (0.0500)  time: 11.8392  data: 8.2234  max mem: 31830
Epoch: [7]  [ 10/312]  eta: 0:08:43  lr: 0.001407  min_lr: 0.001407  loss: 5.6494 (5.4770)  weight_decay: 0.0500 (0.0500)  time: 1.7332  data: 0.9306  max mem: 31830
Epoch: [7]  [ 20/312]  eta: 0:05:19  lr: 0.001413  min_lr: 0.001413  loss: 5.3233 (5.2295)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.1013  max mem: 31830
Epoch: [7]  [ 30/312]  eta: 0:04:06  lr: 0.001419  min_lr: 0.001419  loss: 5.1490 (5.2290)  weight_decay: 0.0500 (0.0500)  time: 0.4003  data: 0.0090  max mem: 31830
Epoch: [7]  [ 40/312]  eta: 0:03:26  lr: 0.001426  min_lr: 0.001426  loss: 4.9855 (5.1471)  weight_decay: 0.0500 (0.0500)  time: 0.4047  data: 0.0095  max mem: 31830
Epoch: [7]  [ 50/312]  eta: 0:02:59  lr: 0.001432  min_lr: 0.001432  loss: 4.9855 (5.1349)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0016  max mem: 31830
Epoch: [7]  [ 60/312]  eta: 0:02:40  lr: 0.001439  min_lr: 0.001439  loss: 5.0658 (5.1335)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0008  max mem: 31830
Epoch: [7]  [ 70/312]  eta: 0:02:31  lr: 0.001445  min_lr: 0.001445  loss: 4.9916 (5.1276)  weight_decay: 0.0500 (0.0500)  time: 0.4791  data: 0.0009  max mem: 31830
Epoch: [7]  [ 80/312]  eta: 0:02:22  lr: 0.001452  min_lr: 0.001452  loss: 5.3007 (5.1490)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.0137  max mem: 31830
Epoch: [7]  [ 90/312]  eta: 0:02:13  lr: 0.001458  min_lr: 0.001458  loss: 5.3789 (5.1655)  weight_decay: 0.0500 (0.0500)  time: 0.5055  data: 0.0272  max mem: 31830
Epoch: [7]  [100/312]  eta: 0:02:08  lr: 0.001464  min_lr: 0.001464  loss: 5.2474 (5.1504)  weight_decay: 0.0500 (0.0500)  time: 0.5570  data: 0.0316  max mem: 31830
Epoch: [7]  [110/312]  eta: 0:01:58  lr: 0.001471  min_lr: 0.001471  loss: 5.2474 (5.1524)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0180  max mem: 31830
Epoch: [7]  [120/312]  eta: 0:01:52  lr: 0.001477  min_lr: 0.001477  loss: 5.3254 (5.1516)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0291  max mem: 31830
Epoch: [7]  [130/312]  eta: 0:01:48  lr: 0.001484  min_lr: 0.001484  loss: 5.3432 (5.1570)  weight_decay: 0.0500 (0.0500)  time: 0.6436  data: 0.0546  max mem: 31830
Epoch: [7]  [140/312]  eta: 0:01:39  lr: 0.001490  min_lr: 0.001490  loss: 5.4234 (5.1762)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0271  max mem: 31830
Epoch: [7]  [150/312]  eta: 0:01:34  lr: 0.001496  min_lr: 0.001496  loss: 5.4805 (5.1862)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0090  max mem: 31830
Epoch: [7]  [160/312]  eta: 0:01:27  lr: 0.001503  min_lr: 0.001503  loss: 5.2615 (5.1808)  weight_decay: 0.0500 (0.0500)  time: 0.5610  data: 0.0085  max mem: 31830
Epoch: [7]  [170/312]  eta: 0:01:21  lr: 0.001509  min_lr: 0.001509  loss: 5.1380 (5.1803)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0080  max mem: 31830
Epoch: [7]  [180/312]  eta: 0:01:16  lr: 0.001516  min_lr: 0.001516  loss: 5.0691 (5.1727)  weight_decay: 0.0500 (0.0500)  time: 0.6009  data: 0.0076  max mem: 31830
Epoch: [7]  [190/312]  eta: 0:01:09  lr: 0.001522  min_lr: 0.001522  loss: 5.0691 (5.1645)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0008  max mem: 31830
Epoch: [7]  [200/312]  eta: 0:01:04  lr: 0.001528  min_lr: 0.001528  loss: 5.3028 (5.1690)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0068  max mem: 31830
Epoch: [7]  [210/312]  eta: 0:00:58  lr: 0.001535  min_lr: 0.001535  loss: 5.2415 (5.1579)  weight_decay: 0.0500 (0.0500)  time: 0.6310  data: 0.0068  max mem: 31830
Epoch: [7]  [220/312]  eta: 0:00:52  lr: 0.001541  min_lr: 0.001541  loss: 5.2648 (5.1647)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0008  max mem: 31830
Epoch: [7]  [230/312]  eta: 0:00:46  lr: 0.001548  min_lr: 0.001548  loss: 5.5210 (5.1645)  weight_decay: 0.0500 (0.0500)  time: 0.5159  data: 0.0009  max mem: 31830
Epoch: [7]  [240/312]  eta: 0:00:40  lr: 0.001554  min_lr: 0.001554  loss: 4.9795 (5.1565)  weight_decay: 0.0500 (0.0500)  time: 0.5391  data: 0.0009  max mem: 31830
Epoch: [7]  [250/312]  eta: 0:00:35  lr: 0.001561  min_lr: 0.001561  loss: 5.1681 (5.1585)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0009  max mem: 31830
Epoch: [7]  [260/312]  eta: 0:00:29  lr: 0.001567  min_lr: 0.001567  loss: 5.3423 (5.1622)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0010  max mem: 31830
Epoch: [7]  [270/312]  eta: 0:00:23  lr: 0.001573  min_lr: 0.001573  loss: 5.4128 (5.1718)  weight_decay: 0.0500 (0.0500)  time: 0.4796  data: 0.0009  max mem: 31830
Epoch: [7]  [280/312]  eta: 0:00:18  lr: 0.001580  min_lr: 0.001580  loss: 5.0460 (5.1587)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0081  max mem: 31830
Epoch: [7]  [290/312]  eta: 0:00:12  lr: 0.001586  min_lr: 0.001586  loss: 4.8457 (5.1574)  weight_decay: 0.0500 (0.0500)  time: 0.6201  data: 0.0079  max mem: 31830
Epoch: [7]  [300/312]  eta: 0:00:06  lr: 0.001593  min_lr: 0.001593  loss: 5.3374 (5.1561)  weight_decay: 0.0500 (0.0500)  time: 0.4816  data: 0.0002  max mem: 31830
Epoch: [7]  [310/312]  eta: 0:00:01  lr: 0.001599  min_lr: 0.001599  loss: 5.1155 (5.1573)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [7]  [311/312]  eta: 0:00:00  lr: 0.001600  min_lr: 0.001600  loss: 5.1155 (5.1555)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [7] Total time: 0:02:53 (0.5559 s / it)
Averaged stats: lr: 0.001600  min_lr: 0.001600  loss: 5.1155 (5.1724)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 2.5812 (2.5812)  acc1: 48.9583 (48.9583)  acc5: 71.6146 (71.6146)  time: 8.2477  data: 8.0846  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.8744 (2.8088)  acc1: 40.6250 (41.6960)  acc5: 69.2708 (66.8000)  time: 1.0339  data: 0.8984  max mem: 31830
Test: Total time: 0:00:09 (1.0511 s / it)
* Acc@1 41.576 Acc@5 67.666 loss 2.785
Accuracy of the model on the 50000 test images: 41.6%
Max accuracy: 41.58%
Epoch: [8]  [  0/312]  eta: 0:55:07  lr: 0.001600  min_lr: 0.001600  loss: 4.7096 (4.7096)  weight_decay: 0.0500 (0.0500)  time: 10.6022  data: 10.1889  max mem: 31830
Epoch: [8]  [ 10/312]  eta: 0:07:58  lr: 0.001607  min_lr: 0.001607  loss: 4.7762 (4.9526)  weight_decay: 0.0500 (0.0500)  time: 1.5834  data: 0.9270  max mem: 31830
Epoch: [8]  [ 20/312]  eta: 0:05:16  lr: 0.001613  min_lr: 0.001613  loss: 5.0659 (5.0925)  weight_decay: 0.0500 (0.0500)  time: 0.6070  data: 0.0135  max mem: 31830
Epoch: [8]  [ 30/312]  eta: 0:04:03  lr: 0.001619  min_lr: 0.001619  loss: 5.3415 (5.1560)  weight_decay: 0.0500 (0.0500)  time: 0.4653  data: 0.0134  max mem: 31830
Epoch: [8]  [ 40/312]  eta: 0:03:23  lr: 0.001626  min_lr: 0.001626  loss: 5.3593 (5.1596)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0006  max mem: 31830
Epoch: [8]  [ 50/312]  eta: 0:03:08  lr: 0.001632  min_lr: 0.001632  loss: 5.0112 (5.1324)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0587  max mem: 31830
Epoch: [8]  [ 60/312]  eta: 0:02:47  lr: 0.001639  min_lr: 0.001639  loss: 5.4510 (5.1851)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0587  max mem: 31830
Epoch: [8]  [ 70/312]  eta: 0:02:40  lr: 0.001645  min_lr: 0.001645  loss: 5.4606 (5.2054)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0781  max mem: 31830
Epoch: [8]  [ 80/312]  eta: 0:02:28  lr: 0.001652  min_lr: 0.001652  loss: 5.2667 (5.1949)  weight_decay: 0.0500 (0.0500)  time: 0.5676  data: 0.0781  max mem: 31830
Epoch: [8]  [ 90/312]  eta: 0:02:19  lr: 0.001658  min_lr: 0.001658  loss: 5.1160 (5.1901)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0775  max mem: 31830
Epoch: [8]  [100/312]  eta: 0:02:13  lr: 0.001664  min_lr: 0.001664  loss: 5.1150 (5.1619)  weight_decay: 0.0500 (0.0500)  time: 0.5763  data: 0.1515  max mem: 31830
Epoch: [8]  [110/312]  eta: 0:02:02  lr: 0.001671  min_lr: 0.001671  loss: 4.9911 (5.1606)  weight_decay: 0.0500 (0.0500)  time: 0.5010  data: 0.0748  max mem: 31830
Epoch: [8]  [120/312]  eta: 0:01:56  lr: 0.001677  min_lr: 0.001677  loss: 5.2880 (5.1422)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0178  max mem: 31830
Epoch: [8]  [130/312]  eta: 0:01:51  lr: 0.001684  min_lr: 0.001684  loss: 5.2248 (5.1444)  weight_decay: 0.0500 (0.0500)  time: 0.6370  data: 0.0459  max mem: 31830
Epoch: [8]  [140/312]  eta: 0:01:42  lr: 0.001690  min_lr: 0.001690  loss: 5.2248 (5.1431)  weight_decay: 0.0500 (0.0500)  time: 0.5354  data: 0.0290  max mem: 31830
Epoch: [8]  [150/312]  eta: 0:01:36  lr: 0.001696  min_lr: 0.001696  loss: 5.4007 (5.1578)  weight_decay: 0.0500 (0.0500)  time: 0.4749  data: 0.0324  max mem: 31830
Epoch: [8]  [160/312]  eta: 0:01:30  lr: 0.001703  min_lr: 0.001703  loss: 5.4899 (5.1469)  weight_decay: 0.0500 (0.0500)  time: 0.5737  data: 0.0827  max mem: 31830
Epoch: [8]  [170/312]  eta: 0:01:22  lr: 0.001709  min_lr: 0.001709  loss: 5.1527 (5.1445)  weight_decay: 0.0500 (0.0500)  time: 0.4930  data: 0.0512  max mem: 31830
Epoch: [8]  [180/312]  eta: 0:01:17  lr: 0.001716  min_lr: 0.001716  loss: 5.3850 (5.1458)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0321  max mem: 31830
Epoch: [8]  [190/312]  eta: 0:01:10  lr: 0.001722  min_lr: 0.001722  loss: 5.4049 (5.1514)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0322  max mem: 31830
Epoch: [8]  [200/312]  eta: 0:01:04  lr: 0.001728  min_lr: 0.001728  loss: 5.3629 (5.1526)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0009  max mem: 31830
Epoch: [8]  [210/312]  eta: 0:00:59  lr: 0.001735  min_lr: 0.001735  loss: 5.4098 (5.1652)  weight_decay: 0.0500 (0.0500)  time: 0.6266  data: 0.0187  max mem: 31830
Epoch: [8]  [220/312]  eta: 0:00:52  lr: 0.001741  min_lr: 0.001741  loss: 5.2487 (5.1614)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0187  max mem: 31830
Epoch: [8]  [230/312]  eta: 0:00:47  lr: 0.001748  min_lr: 0.001748  loss: 5.1663 (5.1648)  weight_decay: 0.0500 (0.0500)  time: 0.5186  data: 0.0007  max mem: 31830
Epoch: [8]  [240/312]  eta: 0:00:41  lr: 0.001754  min_lr: 0.001754  loss: 5.2439 (5.1558)  weight_decay: 0.0500 (0.0500)  time: 0.6120  data: 0.0007  max mem: 31830
Epoch: [8]  [250/312]  eta: 0:00:35  lr: 0.001761  min_lr: 0.001761  loss: 4.8270 (5.1460)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0130  max mem: 31830
Epoch: [8]  [260/312]  eta: 0:00:29  lr: 0.001767  min_lr: 0.001767  loss: 5.0748 (5.1378)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0130  max mem: 31830
Epoch: [8]  [270/312]  eta: 0:00:23  lr: 0.001773  min_lr: 0.001773  loss: 5.2390 (5.1386)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0007  max mem: 31830
Epoch: [8]  [280/312]  eta: 0:00:18  lr: 0.001780  min_lr: 0.001780  loss: 5.3376 (5.1371)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0026  max mem: 31830
Epoch: [8]  [290/312]  eta: 0:00:12  lr: 0.001786  min_lr: 0.001786  loss: 4.7285 (5.1226)  weight_decay: 0.0500 (0.0500)  time: 0.5969  data: 0.0023  max mem: 31830
Epoch: [8]  [300/312]  eta: 0:00:06  lr: 0.001793  min_lr: 0.001793  loss: 4.6931 (5.1135)  weight_decay: 0.0500 (0.0500)  time: 0.4620  data: 0.0002  max mem: 31830
Epoch: [8]  [310/312]  eta: 0:00:01  lr: 0.001799  min_lr: 0.001799  loss: 5.1652 (5.1110)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [8]  [311/312]  eta: 0:00:00  lr: 0.001800  min_lr: 0.001800  loss: 5.1196 (5.1111)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [8] Total time: 0:02:54 (0.5585 s / it)
Averaged stats: lr: 0.001800  min_lr: 0.001800  loss: 5.1196 (5.0439)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 2.3291 (2.3291)  acc1: 52.4740 (52.4740)  acc5: 75.9115 (75.9115)  time: 8.4501  data: 8.2918  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.5969 (2.5646)  acc1: 44.0104 (44.9600)  acc5: 73.6979 (71.4720)  time: 1.0647  data: 0.9214  max mem: 31830
Test: Total time: 0:00:09 (1.0741 s / it)
* Acc@1 45.346 Acc@5 71.530 loss 2.554
Accuracy of the model on the 50000 test images: 45.3%
Max accuracy: 45.35%
Epoch: [9]  [  0/312]  eta: 0:59:31  lr: 0.001800  min_lr: 0.001800  loss: 5.2095 (5.2095)  weight_decay: 0.0500 (0.0500)  time: 11.4458  data: 9.5497  max mem: 31830
Epoch: [9]  [ 10/312]  eta: 0:09:02  lr: 0.001807  min_lr: 0.001807  loss: 5.2933 (5.0286)  weight_decay: 0.0500 (0.0500)  time: 1.7971  data: 1.0317  max mem: 31830
Epoch: [9]  [ 20/312]  eta: 0:05:30  lr: 0.001813  min_lr: 0.001813  loss: 5.2933 (5.0165)  weight_decay: 0.0500 (0.0500)  time: 0.6144  data: 0.0903  max mem: 31830
Epoch: [9]  [ 30/312]  eta: 0:04:12  lr: 0.001820  min_lr: 0.001820  loss: 4.9281 (4.9707)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0007  max mem: 31830
Epoch: [9]  [ 40/312]  eta: 0:03:29  lr: 0.001826  min_lr: 0.001826  loss: 4.7779 (4.9258)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0007  max mem: 31830
Epoch: [9]  [ 50/312]  eta: 0:03:03  lr: 0.001832  min_lr: 0.001832  loss: 4.4935 (4.8483)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0007  max mem: 31830
Epoch: [9]  [ 60/312]  eta: 0:02:43  lr: 0.001839  min_lr: 0.001839  loss: 4.4935 (4.8278)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0009  max mem: 31830
Epoch: [9]  [ 70/312]  eta: 0:02:31  lr: 0.001845  min_lr: 0.001845  loss: 4.7007 (4.8281)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0009  max mem: 31830
Epoch: [9]  [ 80/312]  eta: 0:02:23  lr: 0.001852  min_lr: 0.001852  loss: 4.6793 (4.8118)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0008  max mem: 31830
Epoch: [9]  [ 90/312]  eta: 0:02:13  lr: 0.001858  min_lr: 0.001858  loss: 5.0694 (4.8553)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0007  max mem: 31830
Epoch: [9]  [100/312]  eta: 0:02:06  lr: 0.001864  min_lr: 0.001864  loss: 5.0850 (4.8446)  weight_decay: 0.0500 (0.0500)  time: 0.4969  data: 0.0008  max mem: 31830
Epoch: [9]  [110/312]  eta: 0:01:59  lr: 0.001871  min_lr: 0.001871  loss: 4.8824 (4.8630)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0013  max mem: 31830
Epoch: [9]  [120/312]  eta: 0:01:53  lr: 0.001877  min_lr: 0.001877  loss: 5.2070 (4.8813)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0012  max mem: 31830
Epoch: [9]  [130/312]  eta: 0:01:45  lr: 0.001884  min_lr: 0.001884  loss: 5.2070 (4.9066)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0008  max mem: 31830
Epoch: [9]  [140/312]  eta: 0:01:40  lr: 0.001890  min_lr: 0.001890  loss: 5.0382 (4.8960)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.0011  max mem: 31830
Epoch: [9]  [150/312]  eta: 0:01:35  lr: 0.001896  min_lr: 0.001896  loss: 4.8242 (4.8921)  weight_decay: 0.0500 (0.0500)  time: 0.6361  data: 0.0076  max mem: 31830
Epoch: [9]  [160/312]  eta: 0:01:27  lr: 0.001903  min_lr: 0.001903  loss: 4.8527 (4.8961)  weight_decay: 0.0500 (0.0500)  time: 0.5053  data: 0.0072  max mem: 31830
Epoch: [9]  [170/312]  eta: 0:01:22  lr: 0.001909  min_lr: 0.001909  loss: 5.1195 (4.9086)  weight_decay: 0.0500 (0.0500)  time: 0.5390  data: 0.0011  max mem: 31830
Epoch: [9]  [180/312]  eta: 0:01:15  lr: 0.001916  min_lr: 0.001916  loss: 5.0305 (4.8972)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0133  max mem: 31830
Epoch: [9]  [190/312]  eta: 0:01:10  lr: 0.001922  min_lr: 0.001922  loss: 4.9597 (4.9016)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0129  max mem: 31830
Epoch: [9]  [200/312]  eta: 0:01:04  lr: 0.001929  min_lr: 0.001929  loss: 4.9134 (4.8998)  weight_decay: 0.0500 (0.0500)  time: 0.6119  data: 0.0008  max mem: 31830
Epoch: [9]  [210/312]  eta: 0:00:57  lr: 0.001935  min_lr: 0.001935  loss: 5.0859 (4.9113)  weight_decay: 0.0500 (0.0500)  time: 0.5112  data: 0.0008  max mem: 31830
Epoch: [9]  [220/312]  eta: 0:00:52  lr: 0.001941  min_lr: 0.001941  loss: 4.9835 (4.9000)  weight_decay: 0.0500 (0.0500)  time: 0.5389  data: 0.0140  max mem: 31830
Epoch: [9]  [230/312]  eta: 0:00:47  lr: 0.001948  min_lr: 0.001948  loss: 4.9861 (4.9115)  weight_decay: 0.0500 (0.0500)  time: 0.6422  data: 0.0140  max mem: 31830
Epoch: [9]  [240/312]  eta: 0:00:40  lr: 0.001954  min_lr: 0.001954  loss: 5.1564 (4.9079)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0008  max mem: 31830
Epoch: [9]  [250/312]  eta: 0:00:35  lr: 0.001961  min_lr: 0.001961  loss: 5.0470 (4.9086)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0009  max mem: 31830
Epoch: [9]  [260/312]  eta: 0:00:29  lr: 0.001967  min_lr: 0.001967  loss: 5.0022 (4.9006)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0023  max mem: 31830
Epoch: [9]  [270/312]  eta: 0:00:23  lr: 0.001973  min_lr: 0.001973  loss: 4.8471 (4.8996)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0023  max mem: 31830
Epoch: [9]  [280/312]  eta: 0:00:18  lr: 0.001980  min_lr: 0.001980  loss: 4.8195 (4.8886)  weight_decay: 0.0500 (0.0500)  time: 0.6297  data: 0.0034  max mem: 31830
Epoch: [9]  [290/312]  eta: 0:00:12  lr: 0.001986  min_lr: 0.001986  loss: 5.1079 (4.8970)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0031  max mem: 31830
Epoch: [9]  [300/312]  eta: 0:00:06  lr: 0.001993  min_lr: 0.001993  loss: 5.1257 (4.8942)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0002  max mem: 31830
Epoch: [9]  [310/312]  eta: 0:00:01  lr: 0.001999  min_lr: 0.001999  loss: 4.9248 (4.8985)  weight_decay: 0.0500 (0.0500)  time: 0.4314  data: 0.0001  max mem: 31830
Epoch: [9]  [311/312]  eta: 0:00:00  lr: 0.002000  min_lr: 0.002000  loss: 4.9248 (4.8998)  weight_decay: 0.0500 (0.0500)  time: 0.4312  data: 0.0001  max mem: 31830
Epoch: [9] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.002000  min_lr: 0.002000  loss: 4.9248 (4.9435)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 2.2287 (2.2287)  acc1: 53.9062 (53.9062)  acc5: 78.3854 (78.3854)  time: 8.6543  data: 8.4869  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.5481 (2.4603)  acc1: 46.0938 (46.8160)  acc5: 72.3958 (72.3200)  time: 1.0785  data: 0.9430  max mem: 31830
Test: Total time: 0:00:09 (1.1036 s / it)
* Acc@1 47.398 Acc@5 73.298 loss 2.441
Accuracy of the model on the 50000 test images: 47.4%
Max accuracy: 47.40%
Epoch: [10]  [  0/312]  eta: 0:59:30  lr: 0.002000  min_lr: 0.002000  loss: 4.9756 (4.9756)  weight_decay: 0.0500 (0.0500)  time: 11.4441  data: 9.3121  max mem: 31830
Epoch: [10]  [ 10/312]  eta: 0:08:17  lr: 0.002007  min_lr: 0.002007  loss: 4.9756 (4.9106)  weight_decay: 0.0500 (0.0500)  time: 1.6461  data: 0.9159  max mem: 31830
Epoch: [10]  [ 20/312]  eta: 0:05:18  lr: 0.002013  min_lr: 0.002013  loss: 4.7538 (4.7587)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0860  max mem: 31830
Epoch: [10]  [ 30/312]  eta: 0:04:05  lr: 0.002020  min_lr: 0.002020  loss: 4.8417 (4.8002)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0488  max mem: 31830
Epoch: [10]  [ 40/312]  eta: 0:03:24  lr: 0.002026  min_lr: 0.002026  loss: 5.1179 (4.8121)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0017  max mem: 31830
Epoch: [10]  [ 50/312]  eta: 0:03:06  lr: 0.002032  min_lr: 0.002032  loss: 4.9234 (4.8435)  weight_decay: 0.0500 (0.0500)  time: 0.4702  data: 0.0274  max mem: 31830
Epoch: [10]  [ 60/312]  eta: 0:02:46  lr: 0.002039  min_lr: 0.002039  loss: 4.9234 (4.8622)  weight_decay: 0.0500 (0.0500)  time: 0.4702  data: 0.0271  max mem: 31830
Epoch: [10]  [ 70/312]  eta: 0:02:37  lr: 0.002045  min_lr: 0.002045  loss: 4.8601 (4.8344)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0767  max mem: 31830
Epoch: [10]  [ 80/312]  eta: 0:02:27  lr: 0.002052  min_lr: 0.002052  loss: 4.9972 (4.8546)  weight_decay: 0.0500 (0.0500)  time: 0.5580  data: 0.0901  max mem: 31830
Epoch: [10]  [ 90/312]  eta: 0:02:18  lr: 0.002058  min_lr: 0.002058  loss: 5.1398 (4.8651)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0689  max mem: 31830
Epoch: [10]  [100/312]  eta: 0:02:12  lr: 0.002064  min_lr: 0.002064  loss: 5.1398 (4.8761)  weight_decay: 0.0500 (0.0500)  time: 0.5804  data: 0.0914  max mem: 31830
Epoch: [10]  [110/312]  eta: 0:02:02  lr: 0.002071  min_lr: 0.002071  loss: 5.0387 (4.8817)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0366  max mem: 31830
Epoch: [10]  [120/312]  eta: 0:01:56  lr: 0.002077  min_lr: 0.002077  loss: 5.2321 (4.9214)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.0061  max mem: 31830
Epoch: [10]  [130/312]  eta: 0:01:50  lr: 0.002084  min_lr: 0.002084  loss: 5.2321 (4.9178)  weight_decay: 0.0500 (0.0500)  time: 0.6152  data: 0.0311  max mem: 31830
Epoch: [10]  [140/312]  eta: 0:01:41  lr: 0.002090  min_lr: 0.002090  loss: 4.6950 (4.9145)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0258  max mem: 31830
Epoch: [10]  [150/312]  eta: 0:01:36  lr: 0.002096  min_lr: 0.002096  loss: 4.6950 (4.9017)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0186  max mem: 31830
Epoch: [10]  [160/312]  eta: 0:01:29  lr: 0.002103  min_lr: 0.002103  loss: 4.6202 (4.8911)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0186  max mem: 31830
Epoch: [10]  [170/312]  eta: 0:01:23  lr: 0.002109  min_lr: 0.002109  loss: 4.7294 (4.8903)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0452  max mem: 31830
Epoch: [10]  [180/312]  eta: 0:01:17  lr: 0.002116  min_lr: 0.002116  loss: 4.8670 (4.8907)  weight_decay: 0.0500 (0.0500)  time: 0.5876  data: 0.0824  max mem: 31830
Epoch: [10]  [190/312]  eta: 0:01:10  lr: 0.002122  min_lr: 0.002122  loss: 5.1838 (4.9028)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0381  max mem: 31830
Epoch: [10]  [200/312]  eta: 0:01:05  lr: 0.002129  min_lr: 0.002129  loss: 5.1838 (4.9061)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0516  max mem: 31830
Epoch: [10]  [210/312]  eta: 0:00:59  lr: 0.002135  min_lr: 0.002135  loss: 4.9543 (4.8877)  weight_decay: 0.0500 (0.0500)  time: 0.6299  data: 0.0633  max mem: 31830
Epoch: [10]  [220/312]  eta: 0:00:53  lr: 0.002141  min_lr: 0.002141  loss: 4.4531 (4.8736)  weight_decay: 0.0500 (0.0500)  time: 0.5391  data: 0.0365  max mem: 31830
Epoch: [10]  [230/312]  eta: 0:00:47  lr: 0.002148  min_lr: 0.002148  loss: 4.9272 (4.8761)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.0247  max mem: 31830
Epoch: [10]  [240/312]  eta: 0:00:41  lr: 0.002154  min_lr: 0.002154  loss: 5.0296 (4.8767)  weight_decay: 0.0500 (0.0500)  time: 0.5678  data: 0.0146  max mem: 31830
Epoch: [10]  [250/312]  eta: 0:00:35  lr: 0.002161  min_lr: 0.002161  loss: 4.9171 (4.8753)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0447  max mem: 31830
Epoch: [10]  [260/312]  eta: 0:00:29  lr: 0.002167  min_lr: 0.002167  loss: 5.0021 (4.8768)  weight_decay: 0.0500 (0.0500)  time: 0.5462  data: 0.0623  max mem: 31830
Epoch: [10]  [270/312]  eta: 0:00:23  lr: 0.002173  min_lr: 0.002173  loss: 5.0690 (4.8811)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0322  max mem: 31830
Epoch: [10]  [280/312]  eta: 0:00:18  lr: 0.002180  min_lr: 0.002180  loss: 4.7691 (4.8703)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0252  max mem: 31830
Epoch: [10]  [290/312]  eta: 0:00:12  lr: 0.002186  min_lr: 0.002186  loss: 4.8998 (4.8760)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.0249  max mem: 31830
Epoch: [10]  [300/312]  eta: 0:00:06  lr: 0.002193  min_lr: 0.002193  loss: 5.1695 (4.8724)  weight_decay: 0.0500 (0.0500)  time: 0.4505  data: 0.0002  max mem: 31830
Epoch: [10]  [310/312]  eta: 0:00:01  lr: 0.002199  min_lr: 0.002199  loss: 4.8877 (4.8669)  weight_decay: 0.0500 (0.0500)  time: 0.3909  data: 0.0001  max mem: 31830
Epoch: [10]  [311/312]  eta: 0:00:00  lr: 0.002200  min_lr: 0.002200  loss: 4.8877 (4.8659)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [10] Total time: 0:02:54 (0.5606 s / it)
Averaged stats: lr: 0.002200  min_lr: 0.002200  loss: 4.8877 (4.8539)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 2.1441 (2.1441)  acc1: 56.3802 (56.3802)  acc5: 79.0365 (79.0365)  time: 8.6089  data: 8.4417  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.4066 (2.3542)  acc1: 49.3490 (48.8320)  acc5: 74.3490 (74.3840)  time: 1.0727  data: 0.9380  max mem: 31830
Test: Total time: 0:00:09 (1.0867 s / it)
* Acc@1 49.142 Acc@5 74.742 loss 2.342
Accuracy of the model on the 50000 test images: 49.1%
Max accuracy: 49.14%
Epoch: [11]  [  0/312]  eta: 1:01:15  lr: 0.002200  min_lr: 0.002200  loss: 5.2694 (5.2694)  weight_decay: 0.0500 (0.0500)  time: 11.7804  data: 10.2826  max mem: 31830
Epoch: [11]  [ 10/312]  eta: 0:08:20  lr: 0.002207  min_lr: 0.002207  loss: 4.5000 (4.7204)  weight_decay: 0.0500 (0.0500)  time: 1.6585  data: 0.9750  max mem: 31830
Epoch: [11]  [ 20/312]  eta: 0:05:22  lr: 0.002213  min_lr: 0.002213  loss: 4.7001 (4.7411)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.0347  max mem: 31830
Epoch: [11]  [ 30/312]  eta: 0:04:07  lr: 0.002220  min_lr: 0.002220  loss: 5.0531 (4.7869)  weight_decay: 0.0500 (0.0500)  time: 0.4476  data: 0.0130  max mem: 31830
Epoch: [11]  [ 40/312]  eta: 0:03:26  lr: 0.002226  min_lr: 0.002226  loss: 4.5439 (4.6984)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0008  max mem: 31830
Epoch: [11]  [ 50/312]  eta: 0:03:02  lr: 0.002232  min_lr: 0.002232  loss: 4.6333 (4.7104)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0141  max mem: 31830
Epoch: [11]  [ 60/312]  eta: 0:02:42  lr: 0.002239  min_lr: 0.002239  loss: 4.6832 (4.7361)  weight_decay: 0.0500 (0.0500)  time: 0.4099  data: 0.0143  max mem: 31830
Epoch: [11]  [ 70/312]  eta: 0:02:32  lr: 0.002245  min_lr: 0.002245  loss: 4.7299 (4.7302)  weight_decay: 0.0500 (0.0500)  time: 0.4673  data: 0.0720  max mem: 31830
Epoch: [11]  [ 80/312]  eta: 0:02:23  lr: 0.002252  min_lr: 0.002252  loss: 4.7808 (4.7498)  weight_decay: 0.0500 (0.0500)  time: 0.5428  data: 0.1397  max mem: 31830
Epoch: [11]  [ 90/312]  eta: 0:02:13  lr: 0.002258  min_lr: 0.002258  loss: 4.7083 (4.7316)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0688  max mem: 31830
Epoch: [11]  [100/312]  eta: 0:02:09  lr: 0.002264  min_lr: 0.002264  loss: 4.7619 (4.7424)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.0977  max mem: 31830
Epoch: [11]  [110/312]  eta: 0:01:59  lr: 0.002271  min_lr: 0.002271  loss: 4.6749 (4.7247)  weight_decay: 0.0500 (0.0500)  time: 0.5441  data: 0.0982  max mem: 31830
Epoch: [11]  [120/312]  eta: 0:01:54  lr: 0.002277  min_lr: 0.002277  loss: 4.6183 (4.7298)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0600  max mem: 31830
Epoch: [11]  [130/312]  eta: 0:01:47  lr: 0.002284  min_lr: 0.002284  loss: 5.0815 (4.7550)  weight_decay: 0.0500 (0.0500)  time: 0.5954  data: 0.1246  max mem: 31830
Epoch: [11]  [140/312]  eta: 0:01:41  lr: 0.002290  min_lr: 0.002290  loss: 5.0848 (4.7609)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0660  max mem: 31830
Epoch: [11]  [150/312]  eta: 0:01:35  lr: 0.002297  min_lr: 0.002297  loss: 5.0333 (4.7724)  weight_decay: 0.0500 (0.0500)  time: 0.5863  data: 0.0134  max mem: 31830
Epoch: [11]  [160/312]  eta: 0:01:28  lr: 0.002303  min_lr: 0.002303  loss: 4.9764 (4.7779)  weight_decay: 0.0500 (0.0500)  time: 0.5543  data: 0.0495  max mem: 31830
Epoch: [11]  [170/312]  eta: 0:01:22  lr: 0.002309  min_lr: 0.002309  loss: 4.9549 (4.7646)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0371  max mem: 31830
Epoch: [11]  [180/312]  eta: 0:01:16  lr: 0.002316  min_lr: 0.002316  loss: 5.0187 (4.7797)  weight_decay: 0.0500 (0.0500)  time: 0.5743  data: 0.0252  max mem: 31830
Epoch: [11]  [190/312]  eta: 0:01:09  lr: 0.002322  min_lr: 0.002322  loss: 5.0042 (4.7834)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0250  max mem: 31830
Epoch: [11]  [200/312]  eta: 0:01:04  lr: 0.002329  min_lr: 0.002329  loss: 4.9106 (4.7949)  weight_decay: 0.0500 (0.0500)  time: 0.5179  data: 0.0078  max mem: 31830
Epoch: [11]  [210/312]  eta: 0:00:58  lr: 0.002335  min_lr: 0.002335  loss: 4.9014 (4.7941)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0078  max mem: 31830
Epoch: [11]  [220/312]  eta: 0:00:52  lr: 0.002341  min_lr: 0.002341  loss: 4.9228 (4.8042)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0007  max mem: 31830
Epoch: [11]  [230/312]  eta: 0:00:46  lr: 0.002348  min_lr: 0.002348  loss: 5.0237 (4.7998)  weight_decay: 0.0500 (0.0500)  time: 0.5616  data: 0.0322  max mem: 31830
Epoch: [11]  [240/312]  eta: 0:00:40  lr: 0.002354  min_lr: 0.002354  loss: 4.9856 (4.8020)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0322  max mem: 31830
Epoch: [11]  [250/312]  eta: 0:00:35  lr: 0.002361  min_lr: 0.002361  loss: 4.9527 (4.8017)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0307  max mem: 31830
Epoch: [11]  [260/312]  eta: 0:00:29  lr: 0.002367  min_lr: 0.002367  loss: 4.8205 (4.7992)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.0464  max mem: 31830
Epoch: [11]  [270/312]  eta: 0:00:23  lr: 0.002373  min_lr: 0.002373  loss: 4.8293 (4.7960)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0165  max mem: 31830
Epoch: [11]  [280/312]  eta: 0:00:18  lr: 0.002380  min_lr: 0.002380  loss: 4.8020 (4.7917)  weight_decay: 0.0500 (0.0500)  time: 0.4979  data: 0.0376  max mem: 31830
Epoch: [11]  [290/312]  eta: 0:00:12  lr: 0.002386  min_lr: 0.002386  loss: 4.7752 (4.7981)  weight_decay: 0.0500 (0.0500)  time: 0.5565  data: 0.0703  max mem: 31830
Epoch: [11]  [300/312]  eta: 0:00:06  lr: 0.002393  min_lr: 0.002393  loss: 5.0988 (4.8008)  weight_decay: 0.0500 (0.0500)  time: 0.4810  data: 0.0332  max mem: 31830
Epoch: [11]  [310/312]  eta: 0:00:01  lr: 0.002399  min_lr: 0.002399  loss: 4.9520 (4.8054)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0001  max mem: 31830
Epoch: [11]  [311/312]  eta: 0:00:00  lr: 0.002400  min_lr: 0.002400  loss: 4.9520 (4.8056)  weight_decay: 0.0500 (0.0500)  time: 0.4122  data: 0.0001  max mem: 31830
Epoch: [11] Total time: 0:02:53 (0.5547 s / it)
Averaged stats: lr: 0.002400  min_lr: 0.002400  loss: 4.9520 (4.7691)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 2.1648 (2.1648)  acc1: 58.2031 (58.2031)  acc5: 81.3802 (81.3802)  time: 8.3976  data: 8.2129  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.4896 (2.3422)  acc1: 50.0000 (51.7440)  acc5: 74.4792 (75.9040)  time: 1.0655  data: 0.9126  max mem: 31830
Test: Total time: 0:00:09 (1.0812 s / it)
* Acc@1 51.108 Acc@5 76.188 loss 2.351
Accuracy of the model on the 50000 test images: 51.1%
Max accuracy: 51.11%
Epoch: [12]  [  0/312]  eta: 0:58:11  lr: 0.002400  min_lr: 0.002400  loss: 4.9979 (4.9979)  weight_decay: 0.0500 (0.0500)  time: 11.1910  data: 9.7796  max mem: 31830
Epoch: [12]  [ 10/312]  eta: 0:07:07  lr: 0.002407  min_lr: 0.002407  loss: 4.6553 (4.5600)  weight_decay: 0.0500 (0.0500)  time: 1.4156  data: 0.9149  max mem: 31830
Epoch: [12]  [ 20/312]  eta: 0:05:18  lr: 0.002413  min_lr: 0.002413  loss: 4.7889 (4.7033)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0929  max mem: 31830
Epoch: [12]  [ 30/312]  eta: 0:04:04  lr: 0.002420  min_lr: 0.002420  loss: 4.9533 (4.7125)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0790  max mem: 31830
Epoch: [12]  [ 40/312]  eta: 0:03:44  lr: 0.002426  min_lr: 0.002426  loss: 4.9256 (4.7339)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0716  max mem: 31830
Epoch: [12]  [ 50/312]  eta: 0:03:16  lr: 0.002432  min_lr: 0.002432  loss: 4.9773 (4.7417)  weight_decay: 0.0500 (0.0500)  time: 0.5698  data: 0.0716  max mem: 31830
Epoch: [12]  [ 60/312]  eta: 0:02:54  lr: 0.002439  min_lr: 0.002439  loss: 4.7911 (4.7348)  weight_decay: 0.0500 (0.0500)  time: 0.4161  data: 0.0007  max mem: 31830
Epoch: [12]  [ 70/312]  eta: 0:02:39  lr: 0.002445  min_lr: 0.002445  loss: 4.6876 (4.6956)  weight_decay: 0.0500 (0.0500)  time: 0.4249  data: 0.0012  max mem: 31830
Epoch: [12]  [ 80/312]  eta: 0:02:30  lr: 0.002452  min_lr: 0.002452  loss: 4.9065 (4.7278)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0423  max mem: 31830
Epoch: [12]  [ 90/312]  eta: 0:02:19  lr: 0.002458  min_lr: 0.002458  loss: 5.0303 (4.7326)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0791  max mem: 31830
Epoch: [12]  [100/312]  eta: 0:02:13  lr: 0.002464  min_lr: 0.002464  loss: 4.9618 (4.7130)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.1028  max mem: 31830
Epoch: [12]  [110/312]  eta: 0:02:02  lr: 0.002471  min_lr: 0.002471  loss: 5.0225 (4.7222)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0653  max mem: 31830
Epoch: [12]  [120/312]  eta: 0:01:57  lr: 0.002477  min_lr: 0.002477  loss: 4.7697 (4.7055)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0624  max mem: 31830
Epoch: [12]  [130/312]  eta: 0:01:50  lr: 0.002484  min_lr: 0.002484  loss: 4.7697 (4.7098)  weight_decay: 0.0500 (0.0500)  time: 0.6034  data: 0.0763  max mem: 31830
Epoch: [12]  [140/312]  eta: 0:01:42  lr: 0.002490  min_lr: 0.002490  loss: 4.8158 (4.6924)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0390  max mem: 31830
Epoch: [12]  [150/312]  eta: 0:01:36  lr: 0.002497  min_lr: 0.002497  loss: 4.6390 (4.6887)  weight_decay: 0.0500 (0.0500)  time: 0.5283  data: 0.0488  max mem: 31830
Epoch: [12]  [160/312]  eta: 0:01:30  lr: 0.002503  min_lr: 0.002503  loss: 4.6207 (4.6781)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0500  max mem: 31830
Epoch: [12]  [170/312]  eta: 0:01:22  lr: 0.002509  min_lr: 0.002509  loss: 4.6458 (4.6846)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0262  max mem: 31830
Epoch: [12]  [180/312]  eta: 0:01:17  lr: 0.002516  min_lr: 0.002516  loss: 4.7062 (4.6834)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0319  max mem: 31830
Epoch: [12]  [190/312]  eta: 0:01:10  lr: 0.002522  min_lr: 0.002522  loss: 4.8725 (4.6798)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0320  max mem: 31830
Epoch: [12]  [200/312]  eta: 0:01:04  lr: 0.002529  min_lr: 0.002529  loss: 4.7752 (4.6723)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0140  max mem: 31830
Epoch: [12]  [210/312]  eta: 0:00:59  lr: 0.002535  min_lr: 0.002535  loss: 4.7548 (4.6648)  weight_decay: 0.0500 (0.0500)  time: 0.6321  data: 0.0267  max mem: 31830
Epoch: [12]  [220/312]  eta: 0:00:52  lr: 0.002541  min_lr: 0.002541  loss: 4.7548 (4.6715)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0261  max mem: 31830
Epoch: [12]  [230/312]  eta: 0:00:47  lr: 0.002548  min_lr: 0.002548  loss: 4.8052 (4.6789)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0191  max mem: 31830
Epoch: [12]  [240/312]  eta: 0:00:41  lr: 0.002554  min_lr: 0.002554  loss: 4.8052 (4.6824)  weight_decay: 0.0500 (0.0500)  time: 0.6102  data: 0.0196  max mem: 31830
Epoch: [12]  [250/312]  eta: 0:00:35  lr: 0.002561  min_lr: 0.002561  loss: 4.8539 (4.6876)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0138  max mem: 31830
Epoch: [12]  [260/312]  eta: 0:00:29  lr: 0.002567  min_lr: 0.002567  loss: 5.0394 (4.6873)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0007  max mem: 31830
Epoch: [12]  [270/312]  eta: 0:00:23  lr: 0.002573  min_lr: 0.002573  loss: 4.5453 (4.6795)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0008  max mem: 31830
Epoch: [12]  [280/312]  eta: 0:00:18  lr: 0.002580  min_lr: 0.002580  loss: 4.7113 (4.6892)  weight_decay: 0.0500 (0.0500)  time: 0.4995  data: 0.0164  max mem: 31830
Epoch: [12]  [290/312]  eta: 0:00:12  lr: 0.002586  min_lr: 0.002586  loss: 4.7079 (4.6829)  weight_decay: 0.0500 (0.0500)  time: 0.5639  data: 0.0161  max mem: 31830
Epoch: [12]  [300/312]  eta: 0:00:06  lr: 0.002593  min_lr: 0.002593  loss: 4.8433 (4.6958)  weight_decay: 0.0500 (0.0500)  time: 0.4633  data: 0.0002  max mem: 31830
Epoch: [12]  [310/312]  eta: 0:00:01  lr: 0.002599  min_lr: 0.002599  loss: 5.0547 (4.7064)  weight_decay: 0.0500 (0.0500)  time: 0.3897  data: 0.0001  max mem: 31830
Epoch: [12]  [311/312]  eta: 0:00:00  lr: 0.002600  min_lr: 0.002600  loss: 5.0547 (4.7090)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [12] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.002600  min_lr: 0.002600  loss: 5.0547 (4.7106)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.9121 (1.9121)  acc1: 60.5469 (60.5469)  acc5: 84.7656 (84.7656)  time: 8.5757  data: 8.4158  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.5086 (2.2888)  acc1: 51.8229 (52.3680)  acc5: 76.3021 (77.7760)  time: 1.0736  data: 0.9351  max mem: 31830
Test: Total time: 0:00:09 (1.0902 s / it)
* Acc@1 52.520 Acc@5 77.420 loss 2.296
Accuracy of the model on the 50000 test images: 52.5%
Max accuracy: 52.52%
Epoch: [13]  [  0/312]  eta: 1:00:30  lr: 0.002600  min_lr: 0.002600  loss: 4.9793 (4.9793)  weight_decay: 0.0500 (0.0500)  time: 11.6348  data: 8.9621  max mem: 31830
Epoch: [13]  [ 10/312]  eta: 0:08:21  lr: 0.002607  min_lr: 0.002607  loss: 4.2405 (4.4079)  weight_decay: 0.0500 (0.0500)  time: 1.6602  data: 0.9710  max mem: 31830
Epoch: [13]  [ 20/312]  eta: 0:05:19  lr: 0.002613  min_lr: 0.002613  loss: 4.2405 (4.4674)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0904  max mem: 31830
Epoch: [13]  [ 30/312]  eta: 0:04:05  lr: 0.002620  min_lr: 0.002620  loss: 4.3068 (4.4032)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0047  max mem: 31830
Epoch: [13]  [ 40/312]  eta: 0:03:25  lr: 0.002626  min_lr: 0.002626  loss: 4.5044 (4.4738)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0008  max mem: 31830
Epoch: [13]  [ 50/312]  eta: 0:03:03  lr: 0.002632  min_lr: 0.002632  loss: 4.5201 (4.4455)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0190  max mem: 31830
Epoch: [13]  [ 60/312]  eta: 0:02:43  lr: 0.002639  min_lr: 0.002639  loss: 4.5853 (4.4907)  weight_decay: 0.0500 (0.0500)  time: 0.4298  data: 0.0195  max mem: 31830
Epoch: [13]  [ 70/312]  eta: 0:02:36  lr: 0.002645  min_lr: 0.002645  loss: 4.6827 (4.5171)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0561  max mem: 31830
Epoch: [13]  [ 80/312]  eta: 0:02:26  lr: 0.002652  min_lr: 0.002652  loss: 4.6408 (4.5098)  weight_decay: 0.0500 (0.0500)  time: 0.5757  data: 0.0557  max mem: 31830
Epoch: [13]  [ 90/312]  eta: 0:02:16  lr: 0.002658  min_lr: 0.002658  loss: 4.5667 (4.5144)  weight_decay: 0.0500 (0.0500)  time: 0.4992  data: 0.0390  max mem: 31830
Epoch: [13]  [100/312]  eta: 0:02:09  lr: 0.002665  min_lr: 0.002665  loss: 4.6464 (4.5450)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0744  max mem: 31830
Epoch: [13]  [110/312]  eta: 0:01:59  lr: 0.002671  min_lr: 0.002671  loss: 4.8063 (4.5594)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0364  max mem: 31830
Epoch: [13]  [120/312]  eta: 0:01:53  lr: 0.002677  min_lr: 0.002677  loss: 4.9256 (4.5851)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0412  max mem: 31830
Epoch: [13]  [130/312]  eta: 0:01:47  lr: 0.002684  min_lr: 0.002684  loss: 4.8205 (4.5858)  weight_decay: 0.0500 (0.0500)  time: 0.5785  data: 0.0867  max mem: 31830
Epoch: [13]  [140/312]  eta: 0:01:39  lr: 0.002690  min_lr: 0.002690  loss: 4.6310 (4.5865)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0587  max mem: 31830
Epoch: [13]  [150/312]  eta: 0:01:34  lr: 0.002697  min_lr: 0.002697  loss: 4.7107 (4.5878)  weight_decay: 0.0500 (0.0500)  time: 0.5165  data: 0.0660  max mem: 31830
Epoch: [13]  [160/312]  eta: 0:01:27  lr: 0.002703  min_lr: 0.002703  loss: 4.7513 (4.6008)  weight_decay: 0.0500 (0.0500)  time: 0.5710  data: 0.0537  max mem: 31830
Epoch: [13]  [170/312]  eta: 0:01:21  lr: 0.002709  min_lr: 0.002709  loss: 4.8534 (4.6005)  weight_decay: 0.0500 (0.0500)  time: 0.5037  data: 0.0482  max mem: 31830
Epoch: [13]  [180/312]  eta: 0:01:15  lr: 0.002716  min_lr: 0.002716  loss: 4.4678 (4.5834)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.1108  max mem: 31830
Epoch: [13]  [190/312]  eta: 0:01:09  lr: 0.002722  min_lr: 0.002722  loss: 4.4678 (4.5918)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0634  max mem: 31830
Epoch: [13]  [200/312]  eta: 0:01:03  lr: 0.002729  min_lr: 0.002729  loss: 5.0890 (4.6075)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0447  max mem: 31830
Epoch: [13]  [210/312]  eta: 0:00:58  lr: 0.002735  min_lr: 0.002735  loss: 4.7466 (4.5958)  weight_decay: 0.0500 (0.0500)  time: 0.5853  data: 0.0698  max mem: 31830
Epoch: [13]  [220/312]  eta: 0:00:51  lr: 0.002741  min_lr: 0.002741  loss: 4.3356 (4.5930)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.0494  max mem: 31830
Epoch: [13]  [230/312]  eta: 0:00:46  lr: 0.002748  min_lr: 0.002748  loss: 4.5961 (4.5943)  weight_decay: 0.0500 (0.0500)  time: 0.5316  data: 0.0690  max mem: 31830
Epoch: [13]  [240/312]  eta: 0:00:40  lr: 0.002754  min_lr: 0.002754  loss: 4.7650 (4.5978)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0454  max mem: 31830
Epoch: [13]  [250/312]  eta: 0:00:34  lr: 0.002761  min_lr: 0.002761  loss: 4.4786 (4.5852)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0511  max mem: 31830
Epoch: [13]  [260/312]  eta: 0:00:29  lr: 0.002767  min_lr: 0.002767  loss: 4.7791 (4.5967)  weight_decay: 0.0500 (0.0500)  time: 0.5642  data: 0.0815  max mem: 31830
Epoch: [13]  [270/312]  eta: 0:00:23  lr: 0.002774  min_lr: 0.002774  loss: 5.0046 (4.6028)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0312  max mem: 31830
Epoch: [13]  [280/312]  eta: 0:00:17  lr: 0.002780  min_lr: 0.002780  loss: 4.7775 (4.5969)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0280  max mem: 31830
Epoch: [13]  [290/312]  eta: 0:00:12  lr: 0.002786  min_lr: 0.002786  loss: 4.3404 (4.5913)  weight_decay: 0.0500 (0.0500)  time: 0.5583  data: 0.0437  max mem: 31830
Epoch: [13]  [300/312]  eta: 0:00:06  lr: 0.002793  min_lr: 0.002793  loss: 4.8540 (4.5942)  weight_decay: 0.0500 (0.0500)  time: 0.4591  data: 0.0161  max mem: 31830
Epoch: [13]  [310/312]  eta: 0:00:01  lr: 0.002799  min_lr: 0.002799  loss: 4.8874 (4.5926)  weight_decay: 0.0500 (0.0500)  time: 0.4085  data: 0.0001  max mem: 31830
Epoch: [13]  [311/312]  eta: 0:00:00  lr: 0.002800  min_lr: 0.002800  loss: 4.8874 (4.5925)  weight_decay: 0.0500 (0.0500)  time: 0.4084  data: 0.0001  max mem: 31830
Epoch: [13] Total time: 0:02:52 (0.5528 s / it)
Averaged stats: lr: 0.002800  min_lr: 0.002800  loss: 4.8874 (4.6574)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.8653 (1.8653)  acc1: 61.4583 (61.4583)  acc5: 81.7708 (81.7708)  time: 8.6030  data: 8.4354  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1942 (2.1093)  acc1: 54.2969 (54.4480)  acc5: 79.4271 (78.7840)  time: 1.0734  data: 0.9373  max mem: 31830
Test: Total time: 0:00:09 (1.0869 s / it)
* Acc@1 54.654 Acc@5 79.382 loss 2.103
Accuracy of the model on the 50000 test images: 54.7%
Max accuracy: 54.65%
Epoch: [14]  [  0/312]  eta: 0:59:27  lr: 0.002800  min_lr: 0.002800  loss: 4.7797 (4.7797)  weight_decay: 0.0500 (0.0500)  time: 11.4329  data: 11.0386  max mem: 31830
Epoch: [14]  [ 10/312]  eta: 0:08:02  lr: 0.002807  min_lr: 0.002807  loss: 4.7797 (4.5426)  weight_decay: 0.0500 (0.0500)  time: 1.5961  data: 1.0040  max mem: 31830
Epoch: [14]  [ 20/312]  eta: 0:05:14  lr: 0.002813  min_lr: 0.002813  loss: 4.7325 (4.5361)  weight_decay: 0.0500 (0.0500)  time: 0.5596  data: 0.0595  max mem: 31830
Epoch: [14]  [ 30/312]  eta: 0:04:02  lr: 0.002820  min_lr: 0.002820  loss: 4.9004 (4.6307)  weight_decay: 0.0500 (0.0500)  time: 0.4531  data: 0.0595  max mem: 31830
Epoch: [14]  [ 40/312]  eta: 0:03:22  lr: 0.002826  min_lr: 0.002826  loss: 4.8907 (4.6627)  weight_decay: 0.0500 (0.0500)  time: 0.3978  data: 0.0007  max mem: 31830
Epoch: [14]  [ 50/312]  eta: 0:03:03  lr: 0.002833  min_lr: 0.002833  loss: 4.6693 (4.6017)  weight_decay: 0.0500 (0.0500)  time: 0.4594  data: 0.0666  max mem: 31830
Epoch: [14]  [ 60/312]  eta: 0:02:44  lr: 0.002839  min_lr: 0.002839  loss: 4.5151 (4.5850)  weight_decay: 0.0500 (0.0500)  time: 0.4561  data: 0.0668  max mem: 31830
Epoch: [14]  [ 70/312]  eta: 0:02:35  lr: 0.002845  min_lr: 0.002845  loss: 4.8295 (4.6087)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.1003  max mem: 31830
Epoch: [14]  [ 80/312]  eta: 0:02:26  lr: 0.002852  min_lr: 0.002852  loss: 4.9510 (4.6305)  weight_decay: 0.0500 (0.0500)  time: 0.5712  data: 0.1778  max mem: 31830
Epoch: [14]  [ 90/312]  eta: 0:02:15  lr: 0.002858  min_lr: 0.002858  loss: 4.8148 (4.5942)  weight_decay: 0.0500 (0.0500)  time: 0.4969  data: 0.0916  max mem: 31830
Epoch: [14]  [100/312]  eta: 0:02:10  lr: 0.002865  min_lr: 0.002865  loss: 4.7330 (4.6215)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.1087  max mem: 31830
Epoch: [14]  [110/312]  eta: 0:01:59  lr: 0.002871  min_lr: 0.002871  loss: 4.9031 (4.6293)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0955  max mem: 31830
Epoch: [14]  [120/312]  eta: 0:01:55  lr: 0.002877  min_lr: 0.002877  loss: 4.8109 (4.6202)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0764  max mem: 31830
Epoch: [14]  [130/312]  eta: 0:01:49  lr: 0.002884  min_lr: 0.002884  loss: 4.7581 (4.6168)  weight_decay: 0.0500 (0.0500)  time: 0.6424  data: 0.1163  max mem: 31830
Epoch: [14]  [140/312]  eta: 0:01:41  lr: 0.002890  min_lr: 0.002890  loss: 4.8237 (4.6202)  weight_decay: 0.0500 (0.0500)  time: 0.5180  data: 0.0405  max mem: 31830
Epoch: [14]  [150/312]  eta: 0:01:36  lr: 0.002897  min_lr: 0.002897  loss: 4.8900 (4.6148)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0139  max mem: 31830
Epoch: [14]  [160/312]  eta: 0:01:28  lr: 0.002903  min_lr: 0.002903  loss: 4.9111 (4.6175)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0139  max mem: 31830
Epoch: [14]  [170/312]  eta: 0:01:22  lr: 0.002909  min_lr: 0.002909  loss: 4.6142 (4.6031)  weight_decay: 0.0500 (0.0500)  time: 0.4824  data: 0.0149  max mem: 31830
Epoch: [14]  [180/312]  eta: 0:01:16  lr: 0.002916  min_lr: 0.002916  loss: 4.6846 (4.6133)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0289  max mem: 31830
Epoch: [14]  [190/312]  eta: 0:01:09  lr: 0.002922  min_lr: 0.002922  loss: 4.9624 (4.6230)  weight_decay: 0.0500 (0.0500)  time: 0.5068  data: 0.0147  max mem: 31830
Epoch: [14]  [200/312]  eta: 0:01:04  lr: 0.002929  min_lr: 0.002929  loss: 4.8771 (4.6241)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0147  max mem: 31830
Epoch: [14]  [210/312]  eta: 0:00:59  lr: 0.002935  min_lr: 0.002935  loss: 4.7902 (4.6265)  weight_decay: 0.0500 (0.0500)  time: 0.6379  data: 0.0429  max mem: 31830
Epoch: [14]  [220/312]  eta: 0:00:52  lr: 0.002941  min_lr: 0.002941  loss: 4.7832 (4.6302)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0291  max mem: 31830
Epoch: [14]  [230/312]  eta: 0:00:47  lr: 0.002948  min_lr: 0.002948  loss: 4.6938 (4.6317)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0013  max mem: 31830
Epoch: [14]  [240/312]  eta: 0:00:40  lr: 0.002954  min_lr: 0.002954  loss: 4.4998 (4.6179)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0013  max mem: 31830
Epoch: [14]  [250/312]  eta: 0:00:35  lr: 0.002961  min_lr: 0.002961  loss: 4.6090 (4.6245)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0007  max mem: 31830
Epoch: [14]  [260/312]  eta: 0:00:29  lr: 0.002967  min_lr: 0.002967  loss: 4.8276 (4.6217)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.0007  max mem: 31830
Epoch: [14]  [270/312]  eta: 0:00:23  lr: 0.002974  min_lr: 0.002974  loss: 4.8276 (4.6259)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0010  max mem: 31830
Epoch: [14]  [280/312]  eta: 0:00:18  lr: 0.002980  min_lr: 0.002980  loss: 4.7901 (4.6222)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.0025  max mem: 31830
Epoch: [14]  [290/312]  eta: 0:00:12  lr: 0.002986  min_lr: 0.002986  loss: 4.7922 (4.6305)  weight_decay: 0.0500 (0.0500)  time: 0.5639  data: 0.0117  max mem: 31830
Epoch: [14]  [300/312]  eta: 0:00:06  lr: 0.002993  min_lr: 0.002993  loss: 4.8453 (4.6341)  weight_decay: 0.0500 (0.0500)  time: 0.4566  data: 0.0100  max mem: 31830
Epoch: [14]  [310/312]  eta: 0:00:01  lr: 0.002999  min_lr: 0.002999  loss: 4.7612 (4.6343)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [14]  [311/312]  eta: 0:00:00  lr: 0.003000  min_lr: 0.003000  loss: 4.7612 (4.6366)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [14] Total time: 0:02:53 (0.5563 s / it)
Averaged stats: lr: 0.003000  min_lr: 0.003000  loss: 4.7612 (4.6199)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 2.0681 (2.0681)  acc1: 61.4583 (61.4583)  acc5: 82.6823 (82.6823)  time: 8.6968  data: 8.5379  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.3346 (2.2757)  acc1: 52.4740 (53.5200)  acc5: 78.5156 (78.0800)  time: 1.0891  data: 0.9487  max mem: 31830
Test: Total time: 0:00:09 (1.1089 s / it)
* Acc@1 53.488 Acc@5 78.388 loss 2.268
Accuracy of the model on the 50000 test images: 53.5%
Max accuracy: 54.65%
Epoch: [15]  [  0/312]  eta: 1:00:40  lr: 0.003000  min_lr: 0.003000  loss: 4.5051 (4.5051)  weight_decay: 0.0500 (0.0500)  time: 11.6683  data: 10.4192  max mem: 31830
Epoch: [15]  [ 10/312]  eta: 0:08:10  lr: 0.003007  min_lr: 0.003007  loss: 4.9210 (4.7079)  weight_decay: 0.0500 (0.0500)  time: 1.6240  data: 0.9482  max mem: 31830
Epoch: [15]  [ 20/312]  eta: 0:05:27  lr: 0.003013  min_lr: 0.003013  loss: 4.9390 (4.8051)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.0137  max mem: 31830
Epoch: [15]  [ 30/312]  eta: 0:04:10  lr: 0.003020  min_lr: 0.003020  loss: 4.5629 (4.6863)  weight_decay: 0.0500 (0.0500)  time: 0.4823  data: 0.0134  max mem: 31830
Epoch: [15]  [ 40/312]  eta: 0:03:28  lr: 0.003026  min_lr: 0.003026  loss: 4.7054 (4.6905)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0006  max mem: 31830
Epoch: [15]  [ 50/312]  eta: 0:03:03  lr: 0.003033  min_lr: 0.003033  loss: 4.7054 (4.6310)  weight_decay: 0.0500 (0.0500)  time: 0.4075  data: 0.0008  max mem: 31830
Epoch: [15]  [ 60/312]  eta: 0:02:43  lr: 0.003039  min_lr: 0.003039  loss: 4.6789 (4.6531)  weight_decay: 0.0500 (0.0500)  time: 0.4048  data: 0.0009  max mem: 31830
Epoch: [15]  [ 70/312]  eta: 0:02:35  lr: 0.003045  min_lr: 0.003045  loss: 4.9335 (4.6411)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0537  max mem: 31830
Epoch: [15]  [ 80/312]  eta: 0:02:27  lr: 0.003052  min_lr: 0.003052  loss: 4.7726 (4.6050)  weight_decay: 0.0500 (0.0500)  time: 0.6038  data: 0.1178  max mem: 31830
Epoch: [15]  [ 90/312]  eta: 0:02:15  lr: 0.003058  min_lr: 0.003058  loss: 4.5403 (4.5927)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0657  max mem: 31830
Epoch: [15]  [100/312]  eta: 0:02:10  lr: 0.003065  min_lr: 0.003065  loss: 4.5058 (4.5866)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0607  max mem: 31830
Epoch: [15]  [110/312]  eta: 0:02:00  lr: 0.003071  min_lr: 0.003071  loss: 4.7249 (4.5893)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0600  max mem: 31830
Epoch: [15]  [120/312]  eta: 0:01:55  lr: 0.003077  min_lr: 0.003077  loss: 4.7840 (4.5822)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0481  max mem: 31830
Epoch: [15]  [130/312]  eta: 0:01:49  lr: 0.003084  min_lr: 0.003084  loss: 4.5993 (4.5740)  weight_decay: 0.0500 (0.0500)  time: 0.6498  data: 0.0757  max mem: 31830
Epoch: [15]  [140/312]  eta: 0:01:41  lr: 0.003090  min_lr: 0.003090  loss: 4.6989 (4.5780)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0285  max mem: 31830
Epoch: [15]  [150/312]  eta: 0:01:35  lr: 0.003097  min_lr: 0.003097  loss: 4.5581 (4.5643)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0138  max mem: 31830
Epoch: [15]  [160/312]  eta: 0:01:29  lr: 0.003103  min_lr: 0.003103  loss: 4.5359 (4.5717)  weight_decay: 0.0500 (0.0500)  time: 0.5827  data: 0.0538  max mem: 31830
Epoch: [15]  [170/312]  eta: 0:01:22  lr: 0.003109  min_lr: 0.003109  loss: 4.8365 (4.5696)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0410  max mem: 31830
Epoch: [15]  [180/312]  eta: 0:01:16  lr: 0.003116  min_lr: 0.003116  loss: 4.4955 (4.5535)  weight_decay: 0.0500 (0.0500)  time: 0.5165  data: 0.0738  max mem: 31830
Epoch: [15]  [190/312]  eta: 0:01:09  lr: 0.003122  min_lr: 0.003122  loss: 4.1606 (4.5335)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0736  max mem: 31830
Epoch: [15]  [200/312]  eta: 0:01:04  lr: 0.003129  min_lr: 0.003129  loss: 4.2214 (4.5319)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0570  max mem: 31830
Epoch: [15]  [210/312]  eta: 0:00:58  lr: 0.003135  min_lr: 0.003135  loss: 4.5314 (4.5289)  weight_decay: 0.0500 (0.0500)  time: 0.6348  data: 0.1514  max mem: 31830
Epoch: [15]  [220/312]  eta: 0:00:52  lr: 0.003142  min_lr: 0.003142  loss: 4.4546 (4.5178)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0953  max mem: 31830
Epoch: [15]  [230/312]  eta: 0:00:46  lr: 0.003148  min_lr: 0.003148  loss: 4.3562 (4.5162)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0668  max mem: 31830
Epoch: [15]  [240/312]  eta: 0:00:41  lr: 0.003154  min_lr: 0.003154  loss: 4.6211 (4.5223)  weight_decay: 0.0500 (0.0500)  time: 0.6202  data: 0.1223  max mem: 31830
Epoch: [15]  [250/312]  eta: 0:00:35  lr: 0.003161  min_lr: 0.003161  loss: 4.7366 (4.5230)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0691  max mem: 31830
Epoch: [15]  [260/312]  eta: 0:00:29  lr: 0.003167  min_lr: 0.003167  loss: 4.8208 (4.5367)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0648  max mem: 31830
Epoch: [15]  [270/312]  eta: 0:00:23  lr: 0.003174  min_lr: 0.003174  loss: 4.8208 (4.5358)  weight_decay: 0.0500 (0.0500)  time: 0.4899  data: 0.0520  max mem: 31830
Epoch: [15]  [280/312]  eta: 0:00:17  lr: 0.003180  min_lr: 0.003180  loss: 4.5859 (4.5389)  weight_decay: 0.0500 (0.0500)  time: 0.4874  data: 0.0650  max mem: 31830
Epoch: [15]  [290/312]  eta: 0:00:12  lr: 0.003186  min_lr: 0.003186  loss: 4.4135 (4.5315)  weight_decay: 0.0500 (0.0500)  time: 0.5941  data: 0.1530  max mem: 31830
Epoch: [15]  [300/312]  eta: 0:00:06  lr: 0.003193  min_lr: 0.003193  loss: 4.7808 (4.5425)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0971  max mem: 31830
Epoch: [15]  [310/312]  eta: 0:00:01  lr: 0.003199  min_lr: 0.003199  loss: 4.7830 (4.5451)  weight_decay: 0.0500 (0.0500)  time: 0.3891  data: 0.0089  max mem: 31830
Epoch: [15]  [311/312]  eta: 0:00:00  lr: 0.003200  min_lr: 0.003200  loss: 4.7808 (4.5455)  weight_decay: 0.0500 (0.0500)  time: 0.3890  data: 0.0089  max mem: 31830
Epoch: [15] Total time: 0:02:53 (0.5553 s / it)
Averaged stats: lr: 0.003200  min_lr: 0.003200  loss: 4.7808 (4.5341)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.7486 (1.7486)  acc1: 61.4583 (61.4583)  acc5: 85.2865 (85.2865)  time: 7.9460  data: 7.7845  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1160 (2.0340)  acc1: 54.9479 (55.8560)  acc5: 80.3385 (80.1920)  time: 1.0212  data: 0.8855  max mem: 31830
Test: Total time: 0:00:09 (1.0314 s / it)
* Acc@1 55.966 Acc@5 80.374 loss 2.038
Accuracy of the model on the 50000 test images: 56.0%
Max accuracy: 55.97%
Epoch: [16]  [  0/312]  eta: 1:04:10  lr: 0.003201  min_lr: 0.003201  loss: 4.5071 (4.5071)  weight_decay: 0.0500 (0.0500)  time: 12.3404  data: 11.9319  max mem: 31830
Epoch: [16]  [ 10/312]  eta: 0:08:08  lr: 0.003207  min_lr: 0.003207  loss: 4.7158 (4.6324)  weight_decay: 0.0500 (0.0500)  time: 1.6171  data: 1.0855  max mem: 31830
Epoch: [16]  [ 20/312]  eta: 0:05:19  lr: 0.003213  min_lr: 0.003213  loss: 4.6993 (4.6255)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.0670  max mem: 31830
Epoch: [16]  [ 30/312]  eta: 0:04:05  lr: 0.003220  min_lr: 0.003220  loss: 4.6618 (4.5688)  weight_decay: 0.0500 (0.0500)  time: 0.4595  data: 0.0669  max mem: 31830
Epoch: [16]  [ 40/312]  eta: 0:03:25  lr: 0.003226  min_lr: 0.003226  loss: 4.3889 (4.5206)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0014  max mem: 31830
Epoch: [16]  [ 50/312]  eta: 0:03:06  lr: 0.003233  min_lr: 0.003233  loss: 4.5158 (4.5086)  weight_decay: 0.0500 (0.0500)  time: 0.4701  data: 0.0591  max mem: 31830
Epoch: [16]  [ 60/312]  eta: 0:02:46  lr: 0.003239  min_lr: 0.003239  loss: 4.4864 (4.4949)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0584  max mem: 31830
Epoch: [16]  [ 70/312]  eta: 0:02:39  lr: 0.003245  min_lr: 0.003245  loss: 4.7075 (4.5296)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0866  max mem: 31830
Epoch: [16]  [ 80/312]  eta: 0:02:30  lr: 0.003252  min_lr: 0.003252  loss: 4.8245 (4.5022)  weight_decay: 0.0500 (0.0500)  time: 0.6065  data: 0.1718  max mem: 31830
Epoch: [16]  [ 90/312]  eta: 0:02:19  lr: 0.003258  min_lr: 0.003258  loss: 4.6792 (4.5131)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0858  max mem: 31830
Epoch: [16]  [100/312]  eta: 0:02:12  lr: 0.003265  min_lr: 0.003265  loss: 4.5863 (4.4875)  weight_decay: 0.0500 (0.0500)  time: 0.5308  data: 0.0650  max mem: 31830
Epoch: [16]  [110/312]  eta: 0:02:01  lr: 0.003271  min_lr: 0.003271  loss: 4.4039 (4.4874)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0650  max mem: 31830
Epoch: [16]  [120/312]  eta: 0:01:56  lr: 0.003277  min_lr: 0.003277  loss: 4.4263 (4.4907)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0515  max mem: 31830
Epoch: [16]  [130/312]  eta: 0:01:50  lr: 0.003284  min_lr: 0.003284  loss: 4.4263 (4.4826)  weight_decay: 0.0500 (0.0500)  time: 0.6317  data: 0.0961  max mem: 31830
Epoch: [16]  [140/312]  eta: 0:01:41  lr: 0.003290  min_lr: 0.003290  loss: 4.4699 (4.4991)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0460  max mem: 31830
Epoch: [16]  [150/312]  eta: 0:01:36  lr: 0.003297  min_lr: 0.003297  loss: 4.7549 (4.5143)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0291  max mem: 31830
Epoch: [16]  [160/312]  eta: 0:01:29  lr: 0.003303  min_lr: 0.003303  loss: 4.6975 (4.5084)  weight_decay: 0.0500 (0.0500)  time: 0.5434  data: 0.0586  max mem: 31830
Epoch: [16]  [170/312]  eta: 0:01:22  lr: 0.003310  min_lr: 0.003310  loss: 4.6254 (4.5220)  weight_decay: 0.0500 (0.0500)  time: 0.4828  data: 0.0309  max mem: 31830
Epoch: [16]  [180/312]  eta: 0:01:16  lr: 0.003316  min_lr: 0.003316  loss: 4.6523 (4.5147)  weight_decay: 0.0500 (0.0500)  time: 0.5558  data: 0.0263  max mem: 31830
Epoch: [16]  [190/312]  eta: 0:01:09  lr: 0.003322  min_lr: 0.003322  loss: 4.6523 (4.5264)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0262  max mem: 31830
Epoch: [16]  [200/312]  eta: 0:01:04  lr: 0.003329  min_lr: 0.003329  loss: 4.4479 (4.5128)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0355  max mem: 31830
Epoch: [16]  [210/312]  eta: 0:00:58  lr: 0.003335  min_lr: 0.003335  loss: 4.5260 (4.5236)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.0584  max mem: 31830
Epoch: [16]  [220/312]  eta: 0:00:52  lr: 0.003342  min_lr: 0.003342  loss: 4.8056 (4.5240)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0237  max mem: 31830
Epoch: [16]  [230/312]  eta: 0:00:47  lr: 0.003348  min_lr: 0.003348  loss: 4.7167 (4.5354)  weight_decay: 0.0500 (0.0500)  time: 0.5557  data: 0.0201  max mem: 31830
Epoch: [16]  [240/312]  eta: 0:00:41  lr: 0.003354  min_lr: 0.003354  loss: 4.6759 (4.5280)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0202  max mem: 31830
Epoch: [16]  [250/312]  eta: 0:00:35  lr: 0.003361  min_lr: 0.003361  loss: 4.7964 (4.5356)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0011  max mem: 31830
Epoch: [16]  [260/312]  eta: 0:00:29  lr: 0.003367  min_lr: 0.003367  loss: 4.8550 (4.5349)  weight_decay: 0.0500 (0.0500)  time: 0.6075  data: 0.0021  max mem: 31830
Epoch: [16]  [270/312]  eta: 0:00:23  lr: 0.003374  min_lr: 0.003374  loss: 4.7850 (4.5384)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0026  max mem: 31830
Epoch: [16]  [280/312]  eta: 0:00:18  lr: 0.003380  min_lr: 0.003380  loss: 4.7398 (4.5396)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0030  max mem: 31830
Epoch: [16]  [290/312]  eta: 0:00:12  lr: 0.003386  min_lr: 0.003386  loss: 4.6208 (4.5365)  weight_decay: 0.0500 (0.0500)  time: 0.5713  data: 0.0021  max mem: 31830
Epoch: [16]  [300/312]  eta: 0:00:06  lr: 0.003393  min_lr: 0.003393  loss: 4.7300 (4.5419)  weight_decay: 0.0500 (0.0500)  time: 0.4445  data: 0.0002  max mem: 31830
Epoch: [16]  [310/312]  eta: 0:00:01  lr: 0.003399  min_lr: 0.003399  loss: 4.8675 (4.5488)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [16]  [311/312]  eta: 0:00:00  lr: 0.003400  min_lr: 0.003400  loss: 4.7718 (4.5490)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [16] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.003400  min_lr: 0.003400  loss: 4.7718 (4.5219)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.8701 (1.8701)  acc1: 64.0625 (64.0625)  acc5: 83.7240 (83.7240)  time: 8.1720  data: 8.0086  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.3306 (2.1610)  acc1: 55.2083 (56.2560)  acc5: 79.4271 (80.1600)  time: 1.0602  data: 0.9258  max mem: 31830
Test: Total time: 0:00:09 (1.0711 s / it)
* Acc@1 55.796 Acc@5 80.108 loss 2.164
Accuracy of the model on the 50000 test images: 55.8%
Max accuracy: 55.97%
Epoch: [17]  [  0/312]  eta: 0:59:13  lr: 0.003401  min_lr: 0.003401  loss: 4.1997 (4.1997)  weight_decay: 0.0500 (0.0500)  time: 11.3887  data: 8.2244  max mem: 31830
Epoch: [17]  [ 10/312]  eta: 0:08:06  lr: 0.003407  min_lr: 0.003407  loss: 4.1997 (4.2708)  weight_decay: 0.0500 (0.0500)  time: 1.6126  data: 0.8903  max mem: 31830
Epoch: [17]  [ 20/312]  eta: 0:05:29  lr: 0.003413  min_lr: 0.003413  loss: 4.4390 (4.3560)  weight_decay: 0.0500 (0.0500)  time: 0.6140  data: 0.0788  max mem: 31830
Epoch: [17]  [ 30/312]  eta: 0:04:10  lr: 0.003420  min_lr: 0.003420  loss: 4.2390 (4.3339)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0006  max mem: 31830
Epoch: [17]  [ 40/312]  eta: 0:03:28  lr: 0.003426  min_lr: 0.003426  loss: 4.7676 (4.4111)  weight_decay: 0.0500 (0.0500)  time: 0.3906  data: 0.0007  max mem: 31830
Epoch: [17]  [ 50/312]  eta: 0:03:09  lr: 0.003433  min_lr: 0.003433  loss: 4.8522 (4.4533)  weight_decay: 0.0500 (0.0500)  time: 0.4648  data: 0.0011  max mem: 31830
Epoch: [17]  [ 60/312]  eta: 0:02:48  lr: 0.003439  min_lr: 0.003439  loss: 4.6143 (4.4398)  weight_decay: 0.0500 (0.0500)  time: 0.4649  data: 0.0018  max mem: 31830
Epoch: [17]  [ 70/312]  eta: 0:02:40  lr: 0.003445  min_lr: 0.003445  loss: 4.2968 (4.4298)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0320  max mem: 31830
Epoch: [17]  [ 80/312]  eta: 0:02:30  lr: 0.003452  min_lr: 0.003452  loss: 4.4741 (4.4193)  weight_decay: 0.0500 (0.0500)  time: 0.5899  data: 0.0436  max mem: 31830
Epoch: [17]  [ 90/312]  eta: 0:02:19  lr: 0.003458  min_lr: 0.003458  loss: 4.5164 (4.4248)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0310  max mem: 31830
Epoch: [17]  [100/312]  eta: 0:02:13  lr: 0.003465  min_lr: 0.003465  loss: 4.6896 (4.4556)  weight_decay: 0.0500 (0.0500)  time: 0.5517  data: 0.0562  max mem: 31830
Epoch: [17]  [110/312]  eta: 0:02:02  lr: 0.003471  min_lr: 0.003471  loss: 4.7418 (4.4668)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0383  max mem: 31830
Epoch: [17]  [120/312]  eta: 0:01:57  lr: 0.003477  min_lr: 0.003477  loss: 4.5380 (4.4432)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0305  max mem: 31830
Epoch: [17]  [130/312]  eta: 0:01:51  lr: 0.003484  min_lr: 0.003484  loss: 4.6014 (4.4447)  weight_decay: 0.0500 (0.0500)  time: 0.6206  data: 0.0581  max mem: 31830
Epoch: [17]  [140/312]  eta: 0:01:42  lr: 0.003490  min_lr: 0.003490  loss: 4.6129 (4.4467)  weight_decay: 0.0500 (0.0500)  time: 0.5004  data: 0.0284  max mem: 31830
Epoch: [17]  [150/312]  eta: 0:01:36  lr: 0.003497  min_lr: 0.003497  loss: 4.5546 (4.4520)  weight_decay: 0.0500 (0.0500)  time: 0.5014  data: 0.0268  max mem: 31830
Epoch: [17]  [160/312]  eta: 0:01:30  lr: 0.003503  min_lr: 0.003503  loss: 4.7609 (4.4640)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.0269  max mem: 31830
Epoch: [17]  [170/312]  eta: 0:01:23  lr: 0.003510  min_lr: 0.003510  loss: 4.7609 (4.4677)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0233  max mem: 31830
Epoch: [17]  [180/312]  eta: 0:01:17  lr: 0.003516  min_lr: 0.003516  loss: 4.4119 (4.4512)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0463  max mem: 31830
Epoch: [17]  [190/312]  eta: 0:01:10  lr: 0.003522  min_lr: 0.003522  loss: 4.5330 (4.4633)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0241  max mem: 31830
Epoch: [17]  [200/312]  eta: 0:01:04  lr: 0.003529  min_lr: 0.003529  loss: 4.6983 (4.4634)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0369  max mem: 31830
Epoch: [17]  [210/312]  eta: 0:00:59  lr: 0.003535  min_lr: 0.003535  loss: 4.2562 (4.4579)  weight_decay: 0.0500 (0.0500)  time: 0.6366  data: 0.0614  max mem: 31830
Epoch: [17]  [220/312]  eta: 0:00:52  lr: 0.003542  min_lr: 0.003542  loss: 4.7021 (4.4692)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0257  max mem: 31830
Epoch: [17]  [230/312]  eta: 0:00:47  lr: 0.003548  min_lr: 0.003548  loss: 4.5939 (4.4576)  weight_decay: 0.0500 (0.0500)  time: 0.5179  data: 0.0136  max mem: 31830
Epoch: [17]  [240/312]  eta: 0:00:41  lr: 0.003554  min_lr: 0.003554  loss: 4.4315 (4.4544)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0134  max mem: 31830
Epoch: [17]  [250/312]  eta: 0:00:35  lr: 0.003561  min_lr: 0.003561  loss: 4.4633 (4.4496)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0066  max mem: 31830
Epoch: [17]  [260/312]  eta: 0:00:29  lr: 0.003567  min_lr: 0.003567  loss: 4.4980 (4.4511)  weight_decay: 0.0500 (0.0500)  time: 0.6369  data: 0.0067  max mem: 31830
Epoch: [17]  [270/312]  eta: 0:00:23  lr: 0.003574  min_lr: 0.003574  loss: 4.3136 (4.4445)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0008  max mem: 31830
Epoch: [17]  [280/312]  eta: 0:00:18  lr: 0.003580  min_lr: 0.003580  loss: 4.5400 (4.4450)  weight_decay: 0.0500 (0.0500)  time: 0.4952  data: 0.0023  max mem: 31830
Epoch: [17]  [290/312]  eta: 0:00:12  lr: 0.003586  min_lr: 0.003586  loss: 4.6849 (4.4530)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0021  max mem: 31830
Epoch: [17]  [300/312]  eta: 0:00:06  lr: 0.003593  min_lr: 0.003593  loss: 4.6753 (4.4467)  weight_decay: 0.0500 (0.0500)  time: 0.4429  data: 0.0002  max mem: 31830
Epoch: [17]  [310/312]  eta: 0:00:01  lr: 0.003599  min_lr: 0.003599  loss: 4.5568 (4.4482)  weight_decay: 0.0500 (0.0500)  time: 0.3837  data: 0.0001  max mem: 31830
Epoch: [17]  [311/312]  eta: 0:00:00  lr: 0.003600  min_lr: 0.003600  loss: 4.6429 (4.4498)  weight_decay: 0.0500 (0.0500)  time: 0.3836  data: 0.0001  max mem: 31830
Epoch: [17] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.003600  min_lr: 0.003600  loss: 4.6429 (4.4769)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 1.8336 (1.8336)  acc1: 62.2396 (62.2396)  acc5: 83.7240 (83.7240)  time: 7.8788  data: 7.7193  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1585 (2.0097)  acc1: 54.5573 (56.4000)  acc5: 79.6875 (80.7360)  time: 1.0863  data: 0.9526  max mem: 31830
Test: Total time: 0:00:09 (1.0980 s / it)
* Acc@1 56.488 Acc@5 80.948 loss 2.011
Accuracy of the model on the 50000 test images: 56.5%
Max accuracy: 56.49%
Epoch: [18]  [  0/312]  eta: 1:03:39  lr: 0.003601  min_lr: 0.003601  loss: 3.7434 (3.7434)  weight_decay: 0.0500 (0.0500)  time: 12.2425  data: 9.1240  max mem: 31830
Epoch: [18]  [ 10/312]  eta: 0:09:15  lr: 0.003607  min_lr: 0.003607  loss: 4.6586 (4.5476)  weight_decay: 0.0500 (0.0500)  time: 1.8408  data: 0.8880  max mem: 31830
Epoch: [18]  [ 20/312]  eta: 0:05:35  lr: 0.003613  min_lr: 0.003613  loss: 4.7750 (4.6437)  weight_decay: 0.0500 (0.0500)  time: 0.5943  data: 0.0325  max mem: 31830
Epoch: [18]  [ 30/312]  eta: 0:04:15  lr: 0.003620  min_lr: 0.003620  loss: 4.7035 (4.5352)  weight_decay: 0.0500 (0.0500)  time: 0.3936  data: 0.0006  max mem: 31830
Epoch: [18]  [ 40/312]  eta: 0:03:33  lr: 0.003626  min_lr: 0.003626  loss: 4.3814 (4.4835)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0007  max mem: 31830
Epoch: [18]  [ 50/312]  eta: 0:03:05  lr: 0.003633  min_lr: 0.003633  loss: 4.3395 (4.4837)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0007  max mem: 31830
Epoch: [18]  [ 60/312]  eta: 0:02:45  lr: 0.003639  min_lr: 0.003639  loss: 4.3772 (4.4702)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0007  max mem: 31830
Epoch: [18]  [ 70/312]  eta: 0:02:30  lr: 0.003645  min_lr: 0.003645  loss: 4.5055 (4.4753)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0008  max mem: 31830
Epoch: [18]  [ 80/312]  eta: 0:02:22  lr: 0.003652  min_lr: 0.003652  loss: 4.5258 (4.4820)  weight_decay: 0.0500 (0.0500)  time: 0.4813  data: 0.0127  max mem: 31830
Epoch: [18]  [ 90/312]  eta: 0:02:13  lr: 0.003658  min_lr: 0.003658  loss: 4.7314 (4.4826)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0127  max mem: 31830
Epoch: [18]  [100/312]  eta: 0:02:07  lr: 0.003665  min_lr: 0.003665  loss: 4.3881 (4.4534)  weight_decay: 0.0500 (0.0500)  time: 0.5467  data: 0.0141  max mem: 31830
Epoch: [18]  [110/312]  eta: 0:01:59  lr: 0.003671  min_lr: 0.003671  loss: 4.2862 (4.4487)  weight_decay: 0.0500 (0.0500)  time: 0.5593  data: 0.0261  max mem: 31830
Epoch: [18]  [120/312]  eta: 0:01:52  lr: 0.003678  min_lr: 0.003678  loss: 4.3800 (4.4297)  weight_decay: 0.0500 (0.0500)  time: 0.5111  data: 0.0131  max mem: 31830
Epoch: [18]  [130/312]  eta: 0:01:46  lr: 0.003684  min_lr: 0.003684  loss: 4.3800 (4.4303)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0153  max mem: 31830
Epoch: [18]  [140/312]  eta: 0:01:40  lr: 0.003690  min_lr: 0.003690  loss: 4.6130 (4.4415)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0157  max mem: 31830
Epoch: [18]  [150/312]  eta: 0:01:34  lr: 0.003697  min_lr: 0.003697  loss: 4.6709 (4.4517)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0193  max mem: 31830
Epoch: [18]  [160/312]  eta: 0:01:28  lr: 0.003703  min_lr: 0.003703  loss: 4.6290 (4.4491)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0313  max mem: 31830
Epoch: [18]  [170/312]  eta: 0:01:21  lr: 0.003710  min_lr: 0.003710  loss: 4.5746 (4.4384)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0134  max mem: 31830
Epoch: [18]  [180/312]  eta: 0:01:16  lr: 0.003716  min_lr: 0.003716  loss: 4.2059 (4.4299)  weight_decay: 0.0500 (0.0500)  time: 0.5874  data: 0.0009  max mem: 31830
Epoch: [18]  [190/312]  eta: 0:01:10  lr: 0.003722  min_lr: 0.003722  loss: 4.4229 (4.4400)  weight_decay: 0.0500 (0.0500)  time: 0.5641  data: 0.0007  max mem: 31830
Epoch: [18]  [200/312]  eta: 0:01:04  lr: 0.003729  min_lr: 0.003729  loss: 4.3503 (4.4275)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0023  max mem: 31830
Epoch: [18]  [210/312]  eta: 0:00:58  lr: 0.003735  min_lr: 0.003735  loss: 4.6947 (4.4463)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0024  max mem: 31830
Epoch: [18]  [220/312]  eta: 0:00:52  lr: 0.003742  min_lr: 0.003742  loss: 4.7750 (4.4529)  weight_decay: 0.0500 (0.0500)  time: 0.5586  data: 0.0010  max mem: 31830
Epoch: [18]  [230/312]  eta: 0:00:46  lr: 0.003748  min_lr: 0.003748  loss: 4.5169 (4.4498)  weight_decay: 0.0500 (0.0500)  time: 0.5628  data: 0.0012  max mem: 31830
Epoch: [18]  [240/312]  eta: 0:00:41  lr: 0.003754  min_lr: 0.003754  loss: 4.3524 (4.4432)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0140  max mem: 31830
Epoch: [18]  [250/312]  eta: 0:00:35  lr: 0.003761  min_lr: 0.003761  loss: 4.6620 (4.4617)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0137  max mem: 31830
Epoch: [18]  [260/312]  eta: 0:00:29  lr: 0.003767  min_lr: 0.003767  loss: 4.9537 (4.4801)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0137  max mem: 31830
Epoch: [18]  [270/312]  eta: 0:00:23  lr: 0.003774  min_lr: 0.003774  loss: 4.8350 (4.4833)  weight_decay: 0.0500 (0.0500)  time: 0.5811  data: 0.0144  max mem: 31830
Epoch: [18]  [280/312]  eta: 0:00:18  lr: 0.003780  min_lr: 0.003780  loss: 4.3038 (4.4672)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0025  max mem: 31830
Epoch: [18]  [290/312]  eta: 0:00:12  lr: 0.003787  min_lr: 0.003787  loss: 4.1539 (4.4666)  weight_decay: 0.0500 (0.0500)  time: 0.5799  data: 0.0016  max mem: 31830
Epoch: [18]  [300/312]  eta: 0:00:06  lr: 0.003793  min_lr: 0.003793  loss: 4.5880 (4.4649)  weight_decay: 0.0500 (0.0500)  time: 0.4995  data: 0.0002  max mem: 31830
Epoch: [18]  [310/312]  eta: 0:00:01  lr: 0.003799  min_lr: 0.003799  loss: 4.6720 (4.4662)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [18]  [311/312]  eta: 0:00:00  lr: 0.003800  min_lr: 0.003800  loss: 4.7098 (4.4672)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [18] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.003800  min_lr: 0.003800  loss: 4.7098 (4.4478)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.6737 (1.6737)  acc1: 68.2292 (68.2292)  acc5: 87.7604 (87.7604)  time: 8.6247  data: 8.4577  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1507 (2.0241)  acc1: 56.2500 (58.7360)  acc5: 80.9896 (82.4960)  time: 1.0747  data: 0.9398  max mem: 31830
Test: Total time: 0:00:09 (1.0845 s / it)
* Acc@1 57.922 Acc@5 82.164 loss 2.037
Accuracy of the model on the 50000 test images: 57.9%
Max accuracy: 57.92%
Epoch: [19]  [  0/312]  eta: 1:00:18  lr: 0.003801  min_lr: 0.003801  loss: 4.8797 (4.8797)  weight_decay: 0.0500 (0.0500)  time: 11.5989  data: 9.7866  max mem: 31830
Epoch: [19]  [ 10/312]  eta: 0:08:30  lr: 0.003807  min_lr: 0.003807  loss: 4.8516 (4.6953)  weight_decay: 0.0500 (0.0500)  time: 1.6916  data: 0.9798  max mem: 31830
Epoch: [19]  [ 20/312]  eta: 0:05:32  lr: 0.003813  min_lr: 0.003813  loss: 4.6591 (4.5824)  weight_decay: 0.0500 (0.0500)  time: 0.6150  data: 0.0609  max mem: 31830
Epoch: [19]  [ 30/312]  eta: 0:04:13  lr: 0.003820  min_lr: 0.003820  loss: 4.4861 (4.4360)  weight_decay: 0.0500 (0.0500)  time: 0.4627  data: 0.0117  max mem: 31830
Epoch: [19]  [ 40/312]  eta: 0:03:31  lr: 0.003826  min_lr: 0.003826  loss: 4.5464 (4.4879)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0007  max mem: 31830
Epoch: [19]  [ 50/312]  eta: 0:03:04  lr: 0.003833  min_lr: 0.003833  loss: 4.7945 (4.4936)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0007  max mem: 31830
Epoch: [19]  [ 60/312]  eta: 0:02:44  lr: 0.003839  min_lr: 0.003839  loss: 4.5710 (4.5063)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0008  max mem: 31830
Epoch: [19]  [ 70/312]  eta: 0:02:31  lr: 0.003845  min_lr: 0.003845  loss: 4.4911 (4.4898)  weight_decay: 0.0500 (0.0500)  time: 0.4298  data: 0.0008  max mem: 31830
Epoch: [19]  [ 80/312]  eta: 0:02:22  lr: 0.003852  min_lr: 0.003852  loss: 4.6458 (4.5011)  weight_decay: 0.0500 (0.0500)  time: 0.4960  data: 0.0010  max mem: 31830
Epoch: [19]  [ 90/312]  eta: 0:02:14  lr: 0.003858  min_lr: 0.003858  loss: 4.6458 (4.5022)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0255  max mem: 31830
Epoch: [19]  [100/312]  eta: 0:02:09  lr: 0.003865  min_lr: 0.003865  loss: 4.5464 (4.4777)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0555  max mem: 31830
Epoch: [19]  [110/312]  eta: 0:01:59  lr: 0.003871  min_lr: 0.003871  loss: 4.2054 (4.4518)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0309  max mem: 31830
Epoch: [19]  [120/312]  eta: 0:01:53  lr: 0.003878  min_lr: 0.003878  loss: 4.3283 (4.4434)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0163  max mem: 31830
Epoch: [19]  [130/312]  eta: 0:01:48  lr: 0.003884  min_lr: 0.003884  loss: 4.3353 (4.4413)  weight_decay: 0.0500 (0.0500)  time: 0.6331  data: 0.0163  max mem: 31830
Epoch: [19]  [140/312]  eta: 0:01:40  lr: 0.003890  min_lr: 0.003890  loss: 4.7130 (4.4661)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0119  max mem: 31830
Epoch: [19]  [150/312]  eta: 0:01:34  lr: 0.003897  min_lr: 0.003897  loss: 4.8089 (4.4769)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0120  max mem: 31830
Epoch: [19]  [160/312]  eta: 0:01:27  lr: 0.003903  min_lr: 0.003903  loss: 4.5436 (4.4759)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0008  max mem: 31830
Epoch: [19]  [170/312]  eta: 0:01:21  lr: 0.003910  min_lr: 0.003910  loss: 4.4702 (4.4703)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0076  max mem: 31830
Epoch: [19]  [180/312]  eta: 0:01:16  lr: 0.003916  min_lr: 0.003916  loss: 4.0062 (4.4562)  weight_decay: 0.0500 (0.0500)  time: 0.5955  data: 0.0077  max mem: 31830
Epoch: [19]  [190/312]  eta: 0:01:09  lr: 0.003922  min_lr: 0.003922  loss: 4.2581 (4.4519)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0007  max mem: 31830
Epoch: [19]  [200/312]  eta: 0:01:04  lr: 0.003929  min_lr: 0.003929  loss: 4.2581 (4.4440)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0068  max mem: 31830
Epoch: [19]  [210/312]  eta: 0:00:58  lr: 0.003935  min_lr: 0.003935  loss: 4.0885 (4.4324)  weight_decay: 0.0500 (0.0500)  time: 0.5874  data: 0.0068  max mem: 31830
Epoch: [19]  [220/312]  eta: 0:00:52  lr: 0.003942  min_lr: 0.003942  loss: 4.2438 (4.4285)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0007  max mem: 31830
Epoch: [19]  [230/312]  eta: 0:00:46  lr: 0.003948  min_lr: 0.003948  loss: 4.2499 (4.4246)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0057  max mem: 31830
Epoch: [19]  [240/312]  eta: 0:00:40  lr: 0.003954  min_lr: 0.003954  loss: 4.3090 (4.4284)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0057  max mem: 31830
Epoch: [19]  [250/312]  eta: 0:00:35  lr: 0.003961  min_lr: 0.003961  loss: 4.6319 (4.4371)  weight_decay: 0.0500 (0.0500)  time: 0.5526  data: 0.0068  max mem: 31830
Epoch: [19]  [260/312]  eta: 0:00:29  lr: 0.003967  min_lr: 0.003967  loss: 4.6952 (4.4388)  weight_decay: 0.0500 (0.0500)  time: 0.6477  data: 0.0198  max mem: 31830
Epoch: [19]  [270/312]  eta: 0:00:23  lr: 0.003974  min_lr: 0.003974  loss: 4.6726 (4.4425)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0136  max mem: 31830
Epoch: [19]  [280/312]  eta: 0:00:18  lr: 0.003980  min_lr: 0.003980  loss: 4.4035 (4.4297)  weight_decay: 0.0500 (0.0500)  time: 0.4945  data: 0.0024  max mem: 31830
Epoch: [19]  [290/312]  eta: 0:00:12  lr: 0.003987  min_lr: 0.003987  loss: 4.0082 (4.4211)  weight_decay: 0.0500 (0.0500)  time: 0.5785  data: 0.0022  max mem: 31830
Epoch: [19]  [300/312]  eta: 0:00:06  lr: 0.003993  min_lr: 0.003993  loss: 4.4022 (4.4163)  weight_decay: 0.0500 (0.0500)  time: 0.4793  data: 0.0002  max mem: 31830
Epoch: [19]  [310/312]  eta: 0:00:01  lr: 0.003999  min_lr: 0.003999  loss: 4.4980 (4.4216)  weight_decay: 0.0500 (0.0500)  time: 0.3885  data: 0.0001  max mem: 31830
Epoch: [19]  [311/312]  eta: 0:00:00  lr: 0.004000  min_lr: 0.004000  loss: 4.4980 (4.4220)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [19] Total time: 0:02:53 (0.5548 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 4.4980 (4.4127)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.8757 (1.8757)  acc1: 65.2344 (65.2344)  acc5: 85.9375 (85.9375)  time: 8.6964  data: 8.5360  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.2868 (2.1369)  acc1: 53.7760 (56.1760)  acc5: 80.3385 (80.0800)  time: 1.0874  data: 0.9485  max mem: 31830
Test: Total time: 0:00:09 (1.1082 s / it)
* Acc@1 56.736 Acc@5 80.384 loss 2.138
Accuracy of the model on the 50000 test images: 56.7%
Max accuracy: 57.92%
Epoch: [20]  [  0/312]  eta: 1:01:52  lr: 0.004000  min_lr: 0.004000  loss: 4.5739 (4.5739)  weight_decay: 0.0500 (0.0500)  time: 11.8994  data: 8.8019  max mem: 31830
Epoch: [20]  [ 10/312]  eta: 0:09:07  lr: 0.004000  min_lr: 0.004000  loss: 4.7649 (4.7238)  weight_decay: 0.0500 (0.0500)  time: 1.8137  data: 0.9880  max mem: 31830
Epoch: [20]  [ 20/312]  eta: 0:05:40  lr: 0.004000  min_lr: 0.004000  loss: 4.5588 (4.5798)  weight_decay: 0.0500 (0.0500)  time: 0.6296  data: 0.1371  max mem: 31830
Epoch: [20]  [ 30/312]  eta: 0:04:19  lr: 0.004000  min_lr: 0.004000  loss: 4.5299 (4.6354)  weight_decay: 0.0500 (0.0500)  time: 0.4272  data: 0.0342  max mem: 31830
Epoch: [20]  [ 40/312]  eta: 0:03:35  lr: 0.004000  min_lr: 0.004000  loss: 4.6178 (4.5596)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0008  max mem: 31830
Epoch: [20]  [ 50/312]  eta: 0:03:07  lr: 0.004000  min_lr: 0.004000  loss: 4.5734 (4.5626)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0008  max mem: 31830
Epoch: [20]  [ 60/312]  eta: 0:02:47  lr: 0.004000  min_lr: 0.004000  loss: 4.6292 (4.5808)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0011  max mem: 31830
Epoch: [20]  [ 70/312]  eta: 0:02:31  lr: 0.004000  min_lr: 0.004000  loss: 4.8256 (4.6212)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0010  max mem: 31830
Epoch: [20]  [ 80/312]  eta: 0:02:22  lr: 0.004000  min_lr: 0.004000  loss: 4.6531 (4.5782)  weight_decay: 0.0500 (0.0500)  time: 0.4576  data: 0.0140  max mem: 31830
Epoch: [20]  [ 90/312]  eta: 0:02:14  lr: 0.004000  min_lr: 0.004000  loss: 4.5892 (4.5641)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0377  max mem: 31830
Epoch: [20]  [100/312]  eta: 0:02:06  lr: 0.004000  min_lr: 0.004000  loss: 4.5570 (4.5462)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0434  max mem: 31830
Epoch: [20]  [110/312]  eta: 0:02:00  lr: 0.004000  min_lr: 0.004000  loss: 4.5570 (4.5318)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.0460  max mem: 31830
Epoch: [20]  [120/312]  eta: 0:01:52  lr: 0.004000  min_lr: 0.004000  loss: 4.6782 (4.5190)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0271  max mem: 31830
Epoch: [20]  [130/312]  eta: 0:01:45  lr: 0.004000  min_lr: 0.004000  loss: 4.7003 (4.5163)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0349  max mem: 31830
Epoch: [20]  [140/312]  eta: 0:01:39  lr: 0.004000  min_lr: 0.004000  loss: 4.7003 (4.5255)  weight_decay: 0.0500 (0.0500)  time: 0.5501  data: 0.0641  max mem: 31830
Epoch: [20]  [150/312]  eta: 0:01:33  lr: 0.004000  min_lr: 0.004000  loss: 4.6280 (4.5134)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0355  max mem: 31830
Epoch: [20]  [160/312]  eta: 0:01:27  lr: 0.004000  min_lr: 0.004000  loss: 4.3095 (4.5038)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.0551  max mem: 31830
Epoch: [20]  [170/312]  eta: 0:01:21  lr: 0.004000  min_lr: 0.004000  loss: 4.3405 (4.4982)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0655  max mem: 31830
Epoch: [20]  [180/312]  eta: 0:01:15  lr: 0.004000  min_lr: 0.004000  loss: 4.6666 (4.5108)  weight_decay: 0.0500 (0.0500)  time: 0.5462  data: 0.0229  max mem: 31830
Epoch: [20]  [190/312]  eta: 0:01:09  lr: 0.004000  min_lr: 0.004000  loss: 4.4830 (4.4937)  weight_decay: 0.0500 (0.0500)  time: 0.5695  data: 0.0431  max mem: 31830
Epoch: [20]  [200/312]  eta: 0:01:04  lr: 0.004000  min_lr: 0.004000  loss: 4.3316 (4.4881)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0368  max mem: 31830
Epoch: [20]  [210/312]  eta: 0:00:58  lr: 0.004000  min_lr: 0.004000  loss: 4.4265 (4.4714)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0293  max mem: 31830
Epoch: [20]  [220/312]  eta: 0:00:52  lr: 0.004000  min_lr: 0.004000  loss: 4.0813 (4.4587)  weight_decay: 0.0500 (0.0500)  time: 0.5413  data: 0.0292  max mem: 31830
Epoch: [20]  [230/312]  eta: 0:00:47  lr: 0.004000  min_lr: 0.004000  loss: 4.0648 (4.4472)  weight_decay: 0.0500 (0.0500)  time: 0.6022  data: 0.0010  max mem: 31830
Epoch: [20]  [240/312]  eta: 0:00:41  lr: 0.004000  min_lr: 0.004000  loss: 4.0309 (4.4328)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.0102  max mem: 31830
Epoch: [20]  [250/312]  eta: 0:00:35  lr: 0.004000  min_lr: 0.004000  loss: 4.2840 (4.4324)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0100  max mem: 31830
Epoch: [20]  [260/312]  eta: 0:00:29  lr: 0.004000  min_lr: 0.004000  loss: 4.5614 (4.4223)  weight_decay: 0.0500 (0.0500)  time: 0.5962  data: 0.0008  max mem: 31830
Epoch: [20]  [270/312]  eta: 0:00:23  lr: 0.004000  min_lr: 0.004000  loss: 4.6225 (4.4302)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0007  max mem: 31830
Epoch: [20]  [280/312]  eta: 0:00:18  lr: 0.004000  min_lr: 0.004000  loss: 4.6671 (4.4261)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0019  max mem: 31830
Epoch: [20]  [290/312]  eta: 0:00:12  lr: 0.004000  min_lr: 0.004000  loss: 4.4774 (4.4250)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0016  max mem: 31830
Epoch: [20]  [300/312]  eta: 0:00:06  lr: 0.004000  min_lr: 0.004000  loss: 4.6358 (4.4310)  weight_decay: 0.0500 (0.0500)  time: 0.4760  data: 0.0002  max mem: 31830
Epoch: [20]  [310/312]  eta: 0:00:01  lr: 0.004000  min_lr: 0.004000  loss: 4.5422 (4.4335)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0002  max mem: 31830
Epoch: [20]  [311/312]  eta: 0:00:00  lr: 0.004000  min_lr: 0.004000  loss: 4.6358 (4.4345)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 31830
Epoch: [20] Total time: 0:02:54 (0.5597 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 4.6358 (4.3947)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.7954 (1.7954)  acc1: 65.2344 (65.2344)  acc5: 85.9375 (85.9375)  time: 8.2760  data: 8.1147  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.2745 (2.1198)  acc1: 54.5573 (56.3200)  acc5: 80.3385 (80.3360)  time: 1.0708  data: 0.9360  max mem: 31830
Test: Total time: 0:00:09 (1.0825 s / it)
* Acc@1 56.276 Acc@5 80.560 loss 2.127
Accuracy of the model on the 50000 test images: 56.3%
Max accuracy: 57.92%
Epoch: [21]  [  0/312]  eta: 1:03:32  lr: 0.004000  min_lr: 0.004000  loss: 3.7242 (3.7242)  weight_decay: 0.0500 (0.0500)  time: 12.2200  data: 8.7956  max mem: 31830
Epoch: [21]  [ 10/312]  eta: 0:08:41  lr: 0.004000  min_lr: 0.004000  loss: 4.1001 (4.2290)  weight_decay: 0.0500 (0.0500)  time: 1.7285  data: 0.9963  max mem: 31830
Epoch: [21]  [ 20/312]  eta: 0:05:24  lr: 0.004000  min_lr: 0.004000  loss: 4.4738 (4.4419)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.1085  max mem: 31830
Epoch: [21]  [ 30/312]  eta: 0:04:08  lr: 0.004000  min_lr: 0.004000  loss: 4.5598 (4.3302)  weight_decay: 0.0500 (0.0500)  time: 0.4176  data: 0.0006  max mem: 31830
Epoch: [21]  [ 40/312]  eta: 0:03:27  lr: 0.004000  min_lr: 0.004000  loss: 4.4359 (4.3808)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0007  max mem: 31830
Epoch: [21]  [ 50/312]  eta: 0:03:02  lr: 0.004000  min_lr: 0.004000  loss: 4.5102 (4.3740)  weight_decay: 0.0500 (0.0500)  time: 0.4072  data: 0.0008  max mem: 31830
Epoch: [21]  [ 60/312]  eta: 0:02:42  lr: 0.004000  min_lr: 0.004000  loss: 4.2484 (4.3296)  weight_decay: 0.0500 (0.0500)  time: 0.4068  data: 0.0015  max mem: 31830
Epoch: [21]  [ 70/312]  eta: 0:02:35  lr: 0.004000  min_lr: 0.004000  loss: 4.4347 (4.3697)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0182  max mem: 31830
Epoch: [21]  [ 80/312]  eta: 0:02:27  lr: 0.004000  min_lr: 0.004000  loss: 4.5518 (4.3436)  weight_decay: 0.0500 (0.0500)  time: 0.5967  data: 0.0181  max mem: 31830
Epoch: [21]  [ 90/312]  eta: 0:02:15  lr: 0.004000  min_lr: 0.004000  loss: 4.5940 (4.3512)  weight_decay: 0.0500 (0.0500)  time: 0.4858  data: 0.0016  max mem: 31830
Epoch: [21]  [100/312]  eta: 0:02:08  lr: 0.004000  min_lr: 0.004000  loss: 4.2569 (4.3460)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0132  max mem: 31830
Epoch: [21]  [110/312]  eta: 0:01:59  lr: 0.004000  min_lr: 0.004000  loss: 4.2926 (4.3368)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0132  max mem: 31830
Epoch: [21]  [120/312]  eta: 0:01:54  lr: 0.004000  min_lr: 0.004000  loss: 4.2926 (4.3172)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0152  max mem: 31830
Epoch: [21]  [130/312]  eta: 0:01:47  lr: 0.004000  min_lr: 0.004000  loss: 4.1774 (4.3029)  weight_decay: 0.0500 (0.0500)  time: 0.5996  data: 0.0156  max mem: 31830
Epoch: [21]  [140/312]  eta: 0:01:39  lr: 0.004000  min_lr: 0.004000  loss: 4.2914 (4.2884)  weight_decay: 0.0500 (0.0500)  time: 0.5004  data: 0.0017  max mem: 31830
Epoch: [21]  [150/312]  eta: 0:01:34  lr: 0.004000  min_lr: 0.004000  loss: 4.5387 (4.3100)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0019  max mem: 31830
Epoch: [21]  [160/312]  eta: 0:01:28  lr: 0.004000  min_lr: 0.004000  loss: 4.6324 (4.3157)  weight_decay: 0.0500 (0.0500)  time: 0.5795  data: 0.0015  max mem: 31830
Epoch: [21]  [170/312]  eta: 0:01:22  lr: 0.004000  min_lr: 0.004000  loss: 4.5582 (4.3369)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0123  max mem: 31830
Epoch: [21]  [180/312]  eta: 0:01:16  lr: 0.004000  min_lr: 0.004000  loss: 4.5582 (4.3369)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.0122  max mem: 31830
Epoch: [21]  [190/312]  eta: 0:01:09  lr: 0.004000  min_lr: 0.004000  loss: 4.2753 (4.3266)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0008  max mem: 31830
Epoch: [21]  [200/312]  eta: 0:01:04  lr: 0.004000  min_lr: 0.004000  loss: 4.0055 (4.3081)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0008  max mem: 31830
Epoch: [21]  [210/312]  eta: 0:00:58  lr: 0.004000  min_lr: 0.004000  loss: 4.1832 (4.3080)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.0009  max mem: 31830
Epoch: [21]  [220/312]  eta: 0:00:52  lr: 0.004000  min_lr: 0.004000  loss: 4.2010 (4.2976)  weight_decay: 0.0500 (0.0500)  time: 0.5768  data: 0.0009  max mem: 31830
Epoch: [21]  [230/312]  eta: 0:00:46  lr: 0.004000  min_lr: 0.004000  loss: 4.2914 (4.3050)  weight_decay: 0.0500 (0.0500)  time: 0.5309  data: 0.0008  max mem: 31830
Epoch: [21]  [240/312]  eta: 0:00:41  lr: 0.004000  min_lr: 0.004000  loss: 4.7515 (4.3210)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0007  max mem: 31830
Epoch: [21]  [250/312]  eta: 0:00:35  lr: 0.004000  min_lr: 0.004000  loss: 4.7398 (4.3227)  weight_decay: 0.0500 (0.0500)  time: 0.6797  data: 0.0008  max mem: 31830
Epoch: [21]  [260/312]  eta: 0:00:29  lr: 0.004000  min_lr: 0.004000  loss: 4.4231 (4.3190)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.0014  max mem: 31830
Epoch: [21]  [270/312]  eta: 0:00:24  lr: 0.004000  min_lr: 0.004000  loss: 4.3843 (4.3225)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0014  max mem: 31830
Epoch: [21]  [280/312]  eta: 0:00:18  lr: 0.004000  min_lr: 0.004000  loss: 4.2527 (4.3197)  weight_decay: 0.0500 (0.0500)  time: 0.4832  data: 0.0025  max mem: 31830
Epoch: [21]  [290/312]  eta: 0:00:12  lr: 0.004000  min_lr: 0.004000  loss: 4.4269 (4.3243)  weight_decay: 0.0500 (0.0500)  time: 0.5184  data: 0.0022  max mem: 31830
Epoch: [21]  [300/312]  eta: 0:00:06  lr: 0.004000  min_lr: 0.004000  loss: 3.9781 (4.3133)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0002  max mem: 31830
Epoch: [21]  [310/312]  eta: 0:00:01  lr: 0.003999  min_lr: 0.003999  loss: 3.9769 (4.3129)  weight_decay: 0.0500 (0.0500)  time: 0.3932  data: 0.0001  max mem: 31830
Epoch: [21]  [311/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.9744 (4.3118)  weight_decay: 0.0500 (0.0500)  time: 0.3931  data: 0.0001  max mem: 31830
Epoch: [21] Total time: 0:02:54 (0.5609 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 3.9744 (4.3250)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.7251 (1.7251)  acc1: 63.9323 (63.9323)  acc5: 85.6771 (85.6771)  time: 8.4638  data: 8.3038  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1835 (1.9958)  acc1: 56.5104 (57.7280)  acc5: 81.2500 (81.8240)  time: 1.0585  data: 0.9227  max mem: 31830
Test: Total time: 0:00:09 (1.0759 s / it)
* Acc@1 57.610 Acc@5 81.868 loss 1.994
Accuracy of the model on the 50000 test images: 57.6%
Max accuracy: 57.92%
Epoch: [22]  [  0/312]  eta: 1:02:12  lr: 0.003999  min_lr: 0.003999  loss: 4.0321 (4.0321)  weight_decay: 0.0500 (0.0500)  time: 11.9641  data: 9.0847  max mem: 31830
Epoch: [22]  [ 10/312]  eta: 0:09:01  lr: 0.003999  min_lr: 0.003999  loss: 4.3452 (4.4249)  weight_decay: 0.0500 (0.0500)  time: 1.7924  data: 0.9885  max mem: 31830
Epoch: [22]  [ 20/312]  eta: 0:05:28  lr: 0.003999  min_lr: 0.003999  loss: 4.3366 (4.2894)  weight_decay: 0.0500 (0.0500)  time: 0.5823  data: 0.0900  max mem: 31830
Epoch: [22]  [ 30/312]  eta: 0:04:11  lr: 0.003999  min_lr: 0.003999  loss: 4.3366 (4.2994)  weight_decay: 0.0500 (0.0500)  time: 0.3945  data: 0.0013  max mem: 31830
Epoch: [22]  [ 40/312]  eta: 0:03:29  lr: 0.003999  min_lr: 0.003999  loss: 4.4379 (4.2521)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0022  max mem: 31830
Epoch: [22]  [ 50/312]  eta: 0:03:02  lr: 0.003999  min_lr: 0.003999  loss: 4.2246 (4.2524)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0019  max mem: 31830
Epoch: [22]  [ 60/312]  eta: 0:02:43  lr: 0.003999  min_lr: 0.003999  loss: 4.1956 (4.2449)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0007  max mem: 31830
Epoch: [22]  [ 70/312]  eta: 0:02:29  lr: 0.003999  min_lr: 0.003999  loss: 4.3717 (4.2770)  weight_decay: 0.0500 (0.0500)  time: 0.4211  data: 0.0007  max mem: 31830
Epoch: [22]  [ 80/312]  eta: 0:02:22  lr: 0.003999  min_lr: 0.003999  loss: 4.3547 (4.2607)  weight_decay: 0.0500 (0.0500)  time: 0.5033  data: 0.0208  max mem: 31830
Epoch: [22]  [ 90/312]  eta: 0:02:13  lr: 0.003999  min_lr: 0.003999  loss: 4.2147 (4.2389)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0208  max mem: 31830
Epoch: [22]  [100/312]  eta: 0:02:06  lr: 0.003999  min_lr: 0.003999  loss: 4.4926 (4.2601)  weight_decay: 0.0500 (0.0500)  time: 0.5439  data: 0.0270  max mem: 31830
Epoch: [22]  [110/312]  eta: 0:01:58  lr: 0.003999  min_lr: 0.003999  loss: 4.3192 (4.2488)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0270  max mem: 31830
Epoch: [22]  [120/312]  eta: 0:01:53  lr: 0.003999  min_lr: 0.003999  loss: 4.3970 (4.2616)  weight_decay: 0.0500 (0.0500)  time: 0.5607  data: 0.0393  max mem: 31830
Epoch: [22]  [130/312]  eta: 0:01:46  lr: 0.003999  min_lr: 0.003999  loss: 4.4033 (4.2589)  weight_decay: 0.0500 (0.0500)  time: 0.5808  data: 0.0406  max mem: 31830
Epoch: [22]  [140/312]  eta: 0:01:40  lr: 0.003999  min_lr: 0.003999  loss: 3.9334 (4.2278)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0070  max mem: 31830
Epoch: [22]  [150/312]  eta: 0:01:33  lr: 0.003999  min_lr: 0.003999  loss: 3.9094 (4.2331)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.0057  max mem: 31830
Epoch: [22]  [160/312]  eta: 0:01:27  lr: 0.003999  min_lr: 0.003999  loss: 4.4370 (4.2365)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0134  max mem: 31830
Epoch: [22]  [170/312]  eta: 0:01:21  lr: 0.003999  min_lr: 0.003999  loss: 4.4716 (4.2443)  weight_decay: 0.0500 (0.0500)  time: 0.5629  data: 0.0259  max mem: 31830
Epoch: [22]  [180/312]  eta: 0:01:15  lr: 0.003999  min_lr: 0.003999  loss: 4.4082 (4.2338)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0133  max mem: 31830
Epoch: [22]  [190/312]  eta: 0:01:09  lr: 0.003999  min_lr: 0.003999  loss: 4.4082 (4.2329)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0178  max mem: 31830
Epoch: [22]  [200/312]  eta: 0:01:03  lr: 0.003999  min_lr: 0.003999  loss: 4.6480 (4.2490)  weight_decay: 0.0500 (0.0500)  time: 0.5620  data: 0.0323  max mem: 31830
Epoch: [22]  [210/312]  eta: 0:00:57  lr: 0.003999  min_lr: 0.003999  loss: 4.4980 (4.2442)  weight_decay: 0.0500 (0.0500)  time: 0.5682  data: 0.0154  max mem: 31830
Epoch: [22]  [220/312]  eta: 0:00:51  lr: 0.003999  min_lr: 0.003999  loss: 4.1728 (4.2332)  weight_decay: 0.0500 (0.0500)  time: 0.4875  data: 0.0012  max mem: 31830
Epoch: [22]  [230/312]  eta: 0:00:46  lr: 0.003999  min_lr: 0.003999  loss: 4.2920 (4.2400)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0142  max mem: 31830
Epoch: [22]  [240/312]  eta: 0:00:40  lr: 0.003999  min_lr: 0.003999  loss: 4.4269 (4.2433)  weight_decay: 0.0500 (0.0500)  time: 0.5769  data: 0.0141  max mem: 31830
Epoch: [22]  [250/312]  eta: 0:00:34  lr: 0.003999  min_lr: 0.003999  loss: 3.9683 (4.2372)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0149  max mem: 31830
Epoch: [22]  [260/312]  eta: 0:00:29  lr: 0.003999  min_lr: 0.003999  loss: 4.0343 (4.2373)  weight_decay: 0.0500 (0.0500)  time: 0.5478  data: 0.0277  max mem: 31830
Epoch: [22]  [270/312]  eta: 0:00:23  lr: 0.003999  min_lr: 0.003999  loss: 4.2796 (4.2427)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0139  max mem: 31830
Epoch: [22]  [280/312]  eta: 0:00:17  lr: 0.003999  min_lr: 0.003999  loss: 4.3528 (4.2428)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0020  max mem: 31830
Epoch: [22]  [290/312]  eta: 0:00:12  lr: 0.003999  min_lr: 0.003999  loss: 4.6891 (4.2639)  weight_decay: 0.0500 (0.0500)  time: 0.5928  data: 0.0017  max mem: 31830
Epoch: [22]  [300/312]  eta: 0:00:06  lr: 0.003999  min_lr: 0.003999  loss: 4.8608 (4.2759)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.0084  max mem: 31830
Epoch: [22]  [310/312]  eta: 0:00:01  lr: 0.003999  min_lr: 0.003999  loss: 4.6285 (4.2798)  weight_decay: 0.0500 (0.0500)  time: 0.4052  data: 0.0084  max mem: 31830
Epoch: [22]  [311/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 4.6285 (4.2827)  weight_decay: 0.0500 (0.0500)  time: 0.4051  data: 0.0084  max mem: 31830
Epoch: [22] Total time: 0:02:52 (0.5539 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 4.6285 (4.3111)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.9199 (1.9199)  acc1: 61.0677 (61.0677)  acc5: 86.5885 (86.5885)  time: 8.1765  data: 8.0098  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1964 (2.0919)  acc1: 55.4688 (57.1680)  acc5: 80.9896 (81.6960)  time: 1.0476  data: 0.9124  max mem: 31830
Test: Total time: 0:00:09 (1.0603 s / it)
* Acc@1 57.158 Acc@5 81.564 loss 2.103
Accuracy of the model on the 50000 test images: 57.2%
Max accuracy: 57.92%
Epoch: [23]  [  0/312]  eta: 1:03:07  lr: 0.003999  min_lr: 0.003999  loss: 4.4213 (4.4213)  weight_decay: 0.0500 (0.0500)  time: 12.1397  data: 10.5487  max mem: 31830
Epoch: [23]  [ 10/312]  eta: 0:08:26  lr: 0.003999  min_lr: 0.003999  loss: 3.9982 (3.8569)  weight_decay: 0.0500 (0.0500)  time: 1.6766  data: 0.9600  max mem: 31830
Epoch: [23]  [ 20/312]  eta: 0:05:29  lr: 0.003999  min_lr: 0.003999  loss: 4.2804 (4.1393)  weight_decay: 0.0500 (0.0500)  time: 0.5770  data: 0.0009  max mem: 31830
Epoch: [23]  [ 30/312]  eta: 0:04:11  lr: 0.003999  min_lr: 0.003999  loss: 4.3239 (4.1280)  weight_decay: 0.0500 (0.0500)  time: 0.4618  data: 0.0009  max mem: 31830
Epoch: [23]  [ 40/312]  eta: 0:03:29  lr: 0.003999  min_lr: 0.003999  loss: 4.2156 (4.1892)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0008  max mem: 31830
Epoch: [23]  [ 50/312]  eta: 0:03:07  lr: 0.003999  min_lr: 0.003999  loss: 4.3120 (4.2166)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0006  max mem: 31830
Epoch: [23]  [ 60/312]  eta: 0:02:46  lr: 0.003999  min_lr: 0.003999  loss: 4.4336 (4.2431)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0006  max mem: 31830
Epoch: [23]  [ 70/312]  eta: 0:02:39  lr: 0.003999  min_lr: 0.003999  loss: 4.4208 (4.2541)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0008  max mem: 31830
Epoch: [23]  [ 80/312]  eta: 0:02:30  lr: 0.003999  min_lr: 0.003999  loss: 4.4208 (4.2710)  weight_decay: 0.0500 (0.0500)  time: 0.6107  data: 0.0009  max mem: 31830
Epoch: [23]  [ 90/312]  eta: 0:02:17  lr: 0.003999  min_lr: 0.003999  loss: 4.6391 (4.3162)  weight_decay: 0.0500 (0.0500)  time: 0.4827  data: 0.0007  max mem: 31830
Epoch: [23]  [100/312]  eta: 0:02:13  lr: 0.003999  min_lr: 0.003999  loss: 4.6267 (4.3196)  weight_decay: 0.0500 (0.0500)  time: 0.5540  data: 0.0009  max mem: 31830
Epoch: [23]  [110/312]  eta: 0:02:03  lr: 0.003999  min_lr: 0.003999  loss: 3.9978 (4.2824)  weight_decay: 0.0500 (0.0500)  time: 0.5775  data: 0.0009  max mem: 31830
Epoch: [23]  [120/312]  eta: 0:01:57  lr: 0.003999  min_lr: 0.003999  loss: 4.2820 (4.2825)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0010  max mem: 31830
Epoch: [23]  [130/312]  eta: 0:01:51  lr: 0.003999  min_lr: 0.003999  loss: 4.3526 (4.2861)  weight_decay: 0.0500 (0.0500)  time: 0.6026  data: 0.0150  max mem: 31830
Epoch: [23]  [140/312]  eta: 0:01:42  lr: 0.003999  min_lr: 0.003999  loss: 4.2496 (4.2916)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0150  max mem: 31830
Epoch: [23]  [150/312]  eta: 0:01:37  lr: 0.003998  min_lr: 0.003998  loss: 4.2024 (4.2831)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0009  max mem: 31830
Epoch: [23]  [160/312]  eta: 0:01:31  lr: 0.003998  min_lr: 0.003998  loss: 4.1964 (4.2731)  weight_decay: 0.0500 (0.0500)  time: 0.6073  data: 0.0008  max mem: 31830
Epoch: [23]  [170/312]  eta: 0:01:23  lr: 0.003998  min_lr: 0.003998  loss: 4.4099 (4.2953)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0007  max mem: 31830
Epoch: [23]  [180/312]  eta: 0:01:18  lr: 0.003998  min_lr: 0.003998  loss: 4.4612 (4.2949)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0008  max mem: 31830
Epoch: [23]  [190/312]  eta: 0:01:11  lr: 0.003998  min_lr: 0.003998  loss: 4.2544 (4.2886)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0014  max mem: 31830
Epoch: [23]  [200/312]  eta: 0:01:05  lr: 0.003998  min_lr: 0.003998  loss: 4.4065 (4.2915)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0014  max mem: 31830
Epoch: [23]  [210/312]  eta: 0:00:59  lr: 0.003998  min_lr: 0.003998  loss: 4.4111 (4.2922)  weight_decay: 0.0500 (0.0500)  time: 0.6170  data: 0.0009  max mem: 31830
Epoch: [23]  [220/312]  eta: 0:00:53  lr: 0.003998  min_lr: 0.003998  loss: 4.2826 (4.2881)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0008  max mem: 31830
Epoch: [23]  [230/312]  eta: 0:00:47  lr: 0.003998  min_lr: 0.003998  loss: 4.1796 (4.2770)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0008  max mem: 31830
Epoch: [23]  [240/312]  eta: 0:00:41  lr: 0.003998  min_lr: 0.003998  loss: 4.3824 (4.2756)  weight_decay: 0.0500 (0.0500)  time: 0.6366  data: 0.0008  max mem: 31830
Epoch: [23]  [250/312]  eta: 0:00:35  lr: 0.003998  min_lr: 0.003998  loss: 4.4232 (4.2809)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0008  max mem: 31830
Epoch: [23]  [260/312]  eta: 0:00:30  lr: 0.003998  min_lr: 0.003998  loss: 4.2350 (4.2711)  weight_decay: 0.0500 (0.0500)  time: 0.5057  data: 0.0008  max mem: 31830
Epoch: [23]  [270/312]  eta: 0:00:24  lr: 0.003998  min_lr: 0.003998  loss: 4.0295 (4.2637)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0008  max mem: 31830
Epoch: [23]  [280/312]  eta: 0:00:18  lr: 0.003998  min_lr: 0.003998  loss: 4.1868 (4.2613)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0025  max mem: 31830
Epoch: [23]  [290/312]  eta: 0:00:12  lr: 0.003998  min_lr: 0.003998  loss: 4.5602 (4.2718)  weight_decay: 0.0500 (0.0500)  time: 0.5560  data: 0.0022  max mem: 31830
Epoch: [23]  [300/312]  eta: 0:00:06  lr: 0.003998  min_lr: 0.003998  loss: 4.4507 (4.2728)  weight_decay: 0.0500 (0.0500)  time: 0.4415  data: 0.0002  max mem: 31830
Epoch: [23]  [310/312]  eta: 0:00:01  lr: 0.003998  min_lr: 0.003998  loss: 4.2592 (4.2717)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [23]  [311/312]  eta: 0:00:00  lr: 0.003998  min_lr: 0.003998  loss: 4.2275 (4.2676)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [23] Total time: 0:02:55 (0.5616 s / it)
Averaged stats: lr: 0.003998  min_lr: 0.003998  loss: 4.2275 (4.2817)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.6982 (1.6982)  acc1: 65.6250 (65.6250)  acc5: 88.0208 (88.0208)  time: 9.0886  data: 8.9228  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1202 (1.9458)  acc1: 57.6823 (58.0960)  acc5: 81.1198 (82.5600)  time: 1.1265  data: 0.9915  max mem: 31830
Test: Total time: 0:00:10 (1.1419 s / it)
* Acc@1 58.482 Acc@5 82.226 loss 1.952
Accuracy of the model on the 50000 test images: 58.5%
Max accuracy: 58.48%
Epoch: [24]  [  0/312]  eta: 1:00:36  lr: 0.003998  min_lr: 0.003998  loss: 4.5868 (4.5868)  weight_decay: 0.0500 (0.0500)  time: 11.6565  data: 9.9788  max mem: 31830
Epoch: [24]  [ 10/312]  eta: 0:07:49  lr: 0.003998  min_lr: 0.003998  loss: 4.5001 (4.3281)  weight_decay: 0.0500 (0.0500)  time: 1.5535  data: 1.0063  max mem: 31830
Epoch: [24]  [ 20/312]  eta: 0:05:21  lr: 0.003998  min_lr: 0.003998  loss: 4.1875 (4.1750)  weight_decay: 0.0500 (0.0500)  time: 0.5718  data: 0.0982  max mem: 31830
Epoch: [24]  [ 30/312]  eta: 0:04:06  lr: 0.003998  min_lr: 0.003998  loss: 4.1129 (4.1949)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0441  max mem: 31830
Epoch: [24]  [ 40/312]  eta: 0:03:26  lr: 0.003998  min_lr: 0.003998  loss: 4.2923 (4.1886)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0009  max mem: 31830
Epoch: [24]  [ 50/312]  eta: 0:03:08  lr: 0.003998  min_lr: 0.003998  loss: 4.1585 (4.1674)  weight_decay: 0.0500 (0.0500)  time: 0.4786  data: 0.0581  max mem: 31830
Epoch: [24]  [ 60/312]  eta: 0:02:47  lr: 0.003998  min_lr: 0.003998  loss: 4.2678 (4.2271)  weight_decay: 0.0500 (0.0500)  time: 0.4761  data: 0.0581  max mem: 31830
Epoch: [24]  [ 70/312]  eta: 0:02:39  lr: 0.003998  min_lr: 0.003998  loss: 4.2754 (4.1882)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0646  max mem: 31830
Epoch: [24]  [ 80/312]  eta: 0:02:27  lr: 0.003998  min_lr: 0.003998  loss: 3.9550 (4.1468)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0646  max mem: 31830
Epoch: [24]  [ 90/312]  eta: 0:02:18  lr: 0.003998  min_lr: 0.003998  loss: 4.1997 (4.1686)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0646  max mem: 31830
Epoch: [24]  [100/312]  eta: 0:02:13  lr: 0.003998  min_lr: 0.003998  loss: 4.3940 (4.1841)  weight_decay: 0.0500 (0.0500)  time: 0.6061  data: 0.1470  max mem: 31830
Epoch: [24]  [110/312]  eta: 0:02:02  lr: 0.003998  min_lr: 0.003998  loss: 4.3607 (4.1812)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0836  max mem: 31830
Epoch: [24]  [120/312]  eta: 0:01:57  lr: 0.003998  min_lr: 0.003998  loss: 4.4446 (4.1927)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0679  max mem: 31830
Epoch: [24]  [130/312]  eta: 0:01:50  lr: 0.003998  min_lr: 0.003998  loss: 4.5536 (4.1932)  weight_decay: 0.0500 (0.0500)  time: 0.6041  data: 0.1232  max mem: 31830
Epoch: [24]  [140/312]  eta: 0:01:41  lr: 0.003998  min_lr: 0.003998  loss: 4.4922 (4.2026)  weight_decay: 0.0500 (0.0500)  time: 0.4818  data: 0.0564  max mem: 31830
Epoch: [24]  [150/312]  eta: 0:01:36  lr: 0.003997  min_lr: 0.003997  loss: 4.3928 (4.2020)  weight_decay: 0.0500 (0.0500)  time: 0.5036  data: 0.0667  max mem: 31830
Epoch: [24]  [160/312]  eta: 0:01:29  lr: 0.003997  min_lr: 0.003997  loss: 4.1460 (4.2037)  weight_decay: 0.0500 (0.0500)  time: 0.5605  data: 0.0785  max mem: 31830
Epoch: [24]  [170/312]  eta: 0:01:22  lr: 0.003997  min_lr: 0.003997  loss: 4.3011 (4.2095)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0786  max mem: 31830
Epoch: [24]  [180/312]  eta: 0:01:17  lr: 0.003997  min_lr: 0.003997  loss: 4.5142 (4.2311)  weight_decay: 0.0500 (0.0500)  time: 0.5610  data: 0.1234  max mem: 31830
Epoch: [24]  [190/312]  eta: 0:01:10  lr: 0.003997  min_lr: 0.003997  loss: 4.5438 (4.2180)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0573  max mem: 31830
Epoch: [24]  [200/312]  eta: 0:01:04  lr: 0.003997  min_lr: 0.003997  loss: 4.1372 (4.2222)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0481  max mem: 31830
Epoch: [24]  [210/312]  eta: 0:00:59  lr: 0.003997  min_lr: 0.003997  loss: 4.3673 (4.2325)  weight_decay: 0.0500 (0.0500)  time: 0.6191  data: 0.1168  max mem: 31830
Epoch: [24]  [220/312]  eta: 0:00:52  lr: 0.003997  min_lr: 0.003997  loss: 4.5663 (4.2452)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0696  max mem: 31830
Epoch: [24]  [230/312]  eta: 0:00:46  lr: 0.003997  min_lr: 0.003997  loss: 4.0934 (4.2251)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0858  max mem: 31830
Epoch: [24]  [240/312]  eta: 0:00:40  lr: 0.003997  min_lr: 0.003997  loss: 3.8471 (4.2159)  weight_decay: 0.0500 (0.0500)  time: 0.5401  data: 0.0856  max mem: 31830
Epoch: [24]  [250/312]  eta: 0:00:35  lr: 0.003997  min_lr: 0.003997  loss: 4.2058 (4.2183)  weight_decay: 0.0500 (0.0500)  time: 0.5689  data: 0.0884  max mem: 31830
Epoch: [24]  [260/312]  eta: 0:00:29  lr: 0.003997  min_lr: 0.003997  loss: 4.1616 (4.2146)  weight_decay: 0.0500 (0.0500)  time: 0.5869  data: 0.1441  max mem: 31830
Epoch: [24]  [270/312]  eta: 0:00:23  lr: 0.003997  min_lr: 0.003997  loss: 4.0462 (4.2138)  weight_decay: 0.0500 (0.0500)  time: 0.4589  data: 0.0564  max mem: 31830
Epoch: [24]  [280/312]  eta: 0:00:18  lr: 0.003997  min_lr: 0.003997  loss: 4.1221 (4.2109)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0833  max mem: 31830
Epoch: [24]  [290/312]  eta: 0:00:12  lr: 0.003997  min_lr: 0.003997  loss: 4.1221 (4.2092)  weight_decay: 0.0500 (0.0500)  time: 0.5635  data: 0.1269  max mem: 31830
Epoch: [24]  [300/312]  eta: 0:00:06  lr: 0.003997  min_lr: 0.003997  loss: 4.1916 (4.2136)  weight_decay: 0.0500 (0.0500)  time: 0.4595  data: 0.0441  max mem: 31830
Epoch: [24]  [310/312]  eta: 0:00:01  lr: 0.003997  min_lr: 0.003997  loss: 4.1916 (4.2129)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [24]  [311/312]  eta: 0:00:00  lr: 0.003997  min_lr: 0.003997  loss: 4.1916 (4.2088)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [24] Total time: 0:02:53 (0.5546 s / it)
Averaged stats: lr: 0.003997  min_lr: 0.003997  loss: 4.1916 (4.2596)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6301 (1.6301)  acc1: 63.9323 (63.9323)  acc5: 87.5000 (87.5000)  time: 8.2773  data: 8.1176  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0620 (1.9179)  acc1: 56.9010 (58.8000)  acc5: 81.6406 (82.4480)  time: 1.0369  data: 0.9020  max mem: 31830
Test: Total time: 0:00:09 (1.0492 s / it)
* Acc@1 58.792 Acc@5 82.666 loss 1.929
Accuracy of the model on the 50000 test images: 58.8%
Max accuracy: 58.79%
Epoch: [25]  [  0/312]  eta: 1:03:38  lr: 0.003997  min_lr: 0.003997  loss: 5.2336 (5.2336)  weight_decay: 0.0500 (0.0500)  time: 12.2402  data: 8.7471  max mem: 31830
Epoch: [25]  [ 10/312]  eta: 0:08:56  lr: 0.003997  min_lr: 0.003997  loss: 4.3720 (4.4117)  weight_decay: 0.0500 (0.0500)  time: 1.7752  data: 1.0126  max mem: 31830
Epoch: [25]  [ 20/312]  eta: 0:05:29  lr: 0.003997  min_lr: 0.003997  loss: 4.3359 (4.3867)  weight_decay: 0.0500 (0.0500)  time: 0.5711  data: 0.1198  max mem: 31830
Epoch: [25]  [ 30/312]  eta: 0:04:11  lr: 0.003997  min_lr: 0.003997  loss: 4.3205 (4.2853)  weight_decay: 0.0500 (0.0500)  time: 0.4067  data: 0.0014  max mem: 31830
Epoch: [25]  [ 40/312]  eta: 0:03:30  lr: 0.003997  min_lr: 0.003997  loss: 4.1988 (4.2580)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0021  max mem: 31830
Epoch: [25]  [ 50/312]  eta: 0:03:03  lr: 0.003997  min_lr: 0.003997  loss: 4.5784 (4.2921)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0015  max mem: 31830
Epoch: [25]  [ 60/312]  eta: 0:02:43  lr: 0.003997  min_lr: 0.003997  loss: 4.5373 (4.2572)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0009  max mem: 31830
Epoch: [25]  [ 70/312]  eta: 0:02:31  lr: 0.003997  min_lr: 0.003997  loss: 4.4053 (4.2896)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0008  max mem: 31830
Epoch: [25]  [ 80/312]  eta: 0:02:24  lr: 0.003997  min_lr: 0.003997  loss: 4.4053 (4.2836)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0263  max mem: 31830
Epoch: [25]  [ 90/312]  eta: 0:02:13  lr: 0.003996  min_lr: 0.003996  loss: 4.3955 (4.2742)  weight_decay: 0.0500 (0.0500)  time: 0.5251  data: 0.0425  max mem: 31830
Epoch: [25]  [100/312]  eta: 0:02:06  lr: 0.003996  min_lr: 0.003996  loss: 4.4359 (4.2782)  weight_decay: 0.0500 (0.0500)  time: 0.4984  data: 0.0298  max mem: 31830
Epoch: [25]  [110/312]  eta: 0:01:59  lr: 0.003996  min_lr: 0.003996  loss: 4.4221 (4.2916)  weight_decay: 0.0500 (0.0500)  time: 0.5483  data: 0.0474  max mem: 31830
Epoch: [25]  [120/312]  eta: 0:01:54  lr: 0.003996  min_lr: 0.003996  loss: 4.1422 (4.2644)  weight_decay: 0.0500 (0.0500)  time: 0.5843  data: 0.0898  max mem: 31830
Epoch: [25]  [130/312]  eta: 0:01:47  lr: 0.003996  min_lr: 0.003996  loss: 4.0779 (4.2613)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0560  max mem: 31830
Epoch: [25]  [140/312]  eta: 0:01:39  lr: 0.003996  min_lr: 0.003996  loss: 4.3692 (4.2659)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0222  max mem: 31830
Epoch: [25]  [150/312]  eta: 0:01:33  lr: 0.003996  min_lr: 0.003996  loss: 4.4390 (4.2730)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0364  max mem: 31830
Epoch: [25]  [160/312]  eta: 0:01:28  lr: 0.003996  min_lr: 0.003996  loss: 4.3402 (4.2608)  weight_decay: 0.0500 (0.0500)  time: 0.5967  data: 0.0514  max mem: 31830
Epoch: [25]  [170/312]  eta: 0:01:21  lr: 0.003996  min_lr: 0.003996  loss: 4.0371 (4.2339)  weight_decay: 0.0500 (0.0500)  time: 0.5489  data: 0.0649  max mem: 31830
Epoch: [25]  [180/312]  eta: 0:01:16  lr: 0.003996  min_lr: 0.003996  loss: 3.9887 (4.2329)  weight_decay: 0.0500 (0.0500)  time: 0.5364  data: 0.0292  max mem: 31830
Epoch: [25]  [190/312]  eta: 0:01:09  lr: 0.003996  min_lr: 0.003996  loss: 4.1661 (4.2295)  weight_decay: 0.0500 (0.0500)  time: 0.5605  data: 0.0294  max mem: 31830
Epoch: [25]  [200/312]  eta: 0:01:03  lr: 0.003996  min_lr: 0.003996  loss: 4.1661 (4.2273)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0352  max mem: 31830
Epoch: [25]  [210/312]  eta: 0:00:58  lr: 0.003996  min_lr: 0.003996  loss: 4.0621 (4.2249)  weight_decay: 0.0500 (0.0500)  time: 0.5725  data: 0.0078  max mem: 31830
Epoch: [25]  [220/312]  eta: 0:00:52  lr: 0.003996  min_lr: 0.003996  loss: 4.1387 (4.2273)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0242  max mem: 31830
Epoch: [25]  [230/312]  eta: 0:00:46  lr: 0.003996  min_lr: 0.003996  loss: 4.0559 (4.2176)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0240  max mem: 31830
Epoch: [25]  [240/312]  eta: 0:00:41  lr: 0.003996  min_lr: 0.003996  loss: 4.0810 (4.2189)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.0397  max mem: 31830
Epoch: [25]  [250/312]  eta: 0:00:35  lr: 0.003996  min_lr: 0.003996  loss: 4.1023 (4.2056)  weight_decay: 0.0500 (0.0500)  time: 0.5529  data: 0.0899  max mem: 31830
Epoch: [25]  [260/312]  eta: 0:00:29  lr: 0.003996  min_lr: 0.003996  loss: 4.1485 (4.2021)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0511  max mem: 31830
Epoch: [25]  [270/312]  eta: 0:00:23  lr: 0.003996  min_lr: 0.003996  loss: 4.4512 (4.2105)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0384  max mem: 31830
Epoch: [25]  [280/312]  eta: 0:00:18  lr: 0.003996  min_lr: 0.003996  loss: 4.5598 (4.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5602  data: 0.0576  max mem: 31830
Epoch: [25]  [290/312]  eta: 0:00:12  lr: 0.003996  min_lr: 0.003996  loss: 4.5374 (4.2208)  weight_decay: 0.0500 (0.0500)  time: 0.5302  data: 0.0197  max mem: 31830
Epoch: [25]  [300/312]  eta: 0:00:06  lr: 0.003996  min_lr: 0.003996  loss: 4.3965 (4.2216)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0002  max mem: 31830
Epoch: [25]  [310/312]  eta: 0:00:01  lr: 0.003995  min_lr: 0.003995  loss: 4.2272 (4.2182)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [25]  [311/312]  eta: 0:00:00  lr: 0.003995  min_lr: 0.003995  loss: 4.2247 (4.2182)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [25] Total time: 0:02:53 (0.5555 s / it)
Averaged stats: lr: 0.003995  min_lr: 0.003995  loss: 4.2247 (4.2420)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.7730 (1.7730)  acc1: 64.9740 (64.9740)  acc5: 88.4115 (88.4115)  time: 8.5845  data: 8.4174  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0820 (1.9612)  acc1: 59.5052 (59.1200)  acc5: 83.0729 (83.2480)  time: 1.0707  data: 0.9353  max mem: 31830
Test: Total time: 0:00:09 (1.0815 s / it)
* Acc@1 59.170 Acc@5 82.772 loss 1.988
Accuracy of the model on the 50000 test images: 59.2%
Max accuracy: 59.17%
Epoch: [26]  [  0/312]  eta: 1:02:54  lr: 0.003995  min_lr: 0.003995  loss: 4.6224 (4.6224)  weight_decay: 0.0500 (0.0500)  time: 12.0974  data: 9.6450  max mem: 31830
Epoch: [26]  [ 10/312]  eta: 0:08:28  lr: 0.003995  min_lr: 0.003995  loss: 4.3402 (4.2273)  weight_decay: 0.0500 (0.0500)  time: 1.6828  data: 0.9522  max mem: 31830
Epoch: [26]  [ 20/312]  eta: 0:05:26  lr: 0.003995  min_lr: 0.003995  loss: 4.1665 (4.2062)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0641  max mem: 31830
Epoch: [26]  [ 30/312]  eta: 0:04:09  lr: 0.003995  min_lr: 0.003995  loss: 4.1136 (4.2070)  weight_decay: 0.0500 (0.0500)  time: 0.4446  data: 0.0235  max mem: 31830
Epoch: [26]  [ 40/312]  eta: 0:03:28  lr: 0.003995  min_lr: 0.003995  loss: 4.1136 (4.1848)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0013  max mem: 31830
Epoch: [26]  [ 50/312]  eta: 0:03:02  lr: 0.003995  min_lr: 0.003995  loss: 4.2111 (4.1582)  weight_decay: 0.0500 (0.0500)  time: 0.4080  data: 0.0009  max mem: 31830
Epoch: [26]  [ 60/312]  eta: 0:02:43  lr: 0.003995  min_lr: 0.003995  loss: 4.3288 (4.1769)  weight_decay: 0.0500 (0.0500)  time: 0.4042  data: 0.0008  max mem: 31830
Epoch: [26]  [ 70/312]  eta: 0:02:33  lr: 0.003995  min_lr: 0.003995  loss: 4.3241 (4.1718)  weight_decay: 0.0500 (0.0500)  time: 0.4765  data: 0.0009  max mem: 31830
Epoch: [26]  [ 80/312]  eta: 0:02:26  lr: 0.003995  min_lr: 0.003995  loss: 4.3407 (4.1794)  weight_decay: 0.0500 (0.0500)  time: 0.5809  data: 0.0158  max mem: 31830
Epoch: [26]  [ 90/312]  eta: 0:02:14  lr: 0.003995  min_lr: 0.003995  loss: 4.2984 (4.1795)  weight_decay: 0.0500 (0.0500)  time: 0.4981  data: 0.0157  max mem: 31830
Epoch: [26]  [100/312]  eta: 0:02:10  lr: 0.003995  min_lr: 0.003995  loss: 4.2691 (4.1822)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0512  max mem: 31830
Epoch: [26]  [110/312]  eta: 0:02:00  lr: 0.003995  min_lr: 0.003995  loss: 4.2691 (4.1789)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0511  max mem: 31830
Epoch: [26]  [120/312]  eta: 0:01:54  lr: 0.003995  min_lr: 0.003995  loss: 3.7005 (4.1525)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0124  max mem: 31830
Epoch: [26]  [130/312]  eta: 0:01:48  lr: 0.003995  min_lr: 0.003995  loss: 3.7611 (4.1503)  weight_decay: 0.0500 (0.0500)  time: 0.5948  data: 0.0242  max mem: 31830
Epoch: [26]  [140/312]  eta: 0:01:40  lr: 0.003995  min_lr: 0.003995  loss: 4.3221 (4.1605)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0126  max mem: 31830
Epoch: [26]  [150/312]  eta: 0:01:35  lr: 0.003995  min_lr: 0.003995  loss: 4.4745 (4.1759)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0401  max mem: 31830
Epoch: [26]  [160/312]  eta: 0:01:29  lr: 0.003995  min_lr: 0.003995  loss: 4.5275 (4.1971)  weight_decay: 0.0500 (0.0500)  time: 0.6204  data: 0.0643  max mem: 31830
Epoch: [26]  [170/312]  eta: 0:01:21  lr: 0.003995  min_lr: 0.003995  loss: 4.4038 (4.1986)  weight_decay: 0.0500 (0.0500)  time: 0.4884  data: 0.0249  max mem: 31830
Epoch: [26]  [180/312]  eta: 0:01:16  lr: 0.003995  min_lr: 0.003995  loss: 4.2231 (4.2076)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0282  max mem: 31830
Epoch: [26]  [190/312]  eta: 0:01:09  lr: 0.003995  min_lr: 0.003995  loss: 4.0476 (4.1988)  weight_decay: 0.0500 (0.0500)  time: 0.5416  data: 0.0283  max mem: 31830
Epoch: [26]  [200/312]  eta: 0:01:04  lr: 0.003994  min_lr: 0.003994  loss: 3.9656 (4.1929)  weight_decay: 0.0500 (0.0500)  time: 0.5596  data: 0.0008  max mem: 31830
Epoch: [26]  [210/312]  eta: 0:00:58  lr: 0.003994  min_lr: 0.003994  loss: 4.3099 (4.1951)  weight_decay: 0.0500 (0.0500)  time: 0.6164  data: 0.0008  max mem: 31830
Epoch: [26]  [220/312]  eta: 0:00:52  lr: 0.003994  min_lr: 0.003994  loss: 4.3483 (4.1902)  weight_decay: 0.0500 (0.0500)  time: 0.4833  data: 0.0008  max mem: 31830
Epoch: [26]  [230/312]  eta: 0:00:46  lr: 0.003994  min_lr: 0.003994  loss: 4.2672 (4.1957)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0132  max mem: 31830
Epoch: [26]  [240/312]  eta: 0:00:41  lr: 0.003994  min_lr: 0.003994  loss: 4.2672 (4.1872)  weight_decay: 0.0500 (0.0500)  time: 0.6634  data: 0.0139  max mem: 31830
Epoch: [26]  [250/312]  eta: 0:00:35  lr: 0.003994  min_lr: 0.003994  loss: 4.3563 (4.1995)  weight_decay: 0.0500 (0.0500)  time: 0.5758  data: 0.0017  max mem: 31830
Epoch: [26]  [260/312]  eta: 0:00:29  lr: 0.003994  min_lr: 0.003994  loss: 4.5407 (4.1940)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0016  max mem: 31830
Epoch: [26]  [270/312]  eta: 0:00:23  lr: 0.003994  min_lr: 0.003994  loss: 4.1972 (4.1956)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0020  max mem: 31830
Epoch: [26]  [280/312]  eta: 0:00:18  lr: 0.003994  min_lr: 0.003994  loss: 4.2602 (4.2021)  weight_decay: 0.0500 (0.0500)  time: 0.5337  data: 0.0026  max mem: 31830
Epoch: [26]  [290/312]  eta: 0:00:12  lr: 0.003994  min_lr: 0.003994  loss: 4.2788 (4.2039)  weight_decay: 0.0500 (0.0500)  time: 0.5654  data: 0.0017  max mem: 31830
Epoch: [26]  [300/312]  eta: 0:00:06  lr: 0.003994  min_lr: 0.003994  loss: 4.2788 (4.2056)  weight_decay: 0.0500 (0.0500)  time: 0.4221  data: 0.0002  max mem: 31830
Epoch: [26]  [310/312]  eta: 0:00:01  lr: 0.003994  min_lr: 0.003994  loss: 4.1390 (4.1973)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [26]  [311/312]  eta: 0:00:00  lr: 0.003994  min_lr: 0.003994  loss: 4.1390 (4.1982)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [26] Total time: 0:02:54 (0.5598 s / it)
Averaged stats: lr: 0.003994  min_lr: 0.003994  loss: 4.1390 (4.2027)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.9365 (1.9365)  acc1: 64.7135 (64.7135)  acc5: 87.7604 (87.7604)  time: 8.5790  data: 8.4119  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1686 (2.0247)  acc1: 58.2031 (59.0880)  acc5: 82.5521 (82.6560)  time: 1.0744  data: 0.9347  max mem: 31830
Test: Total time: 0:00:09 (1.0847 s / it)
* Acc@1 59.052 Acc@5 82.914 loss 2.009
Accuracy of the model on the 50000 test images: 59.1%
Max accuracy: 59.17%
Epoch: [27]  [  0/312]  eta: 1:01:02  lr: 0.003994  min_lr: 0.003994  loss: 4.1573 (4.1573)  weight_decay: 0.0500 (0.0500)  time: 11.7389  data: 9.2969  max mem: 31830
Epoch: [27]  [ 10/312]  eta: 0:08:08  lr: 0.003994  min_lr: 0.003994  loss: 4.1573 (4.0085)  weight_decay: 0.0500 (0.0500)  time: 1.6164  data: 1.0184  max mem: 31830
Epoch: [27]  [ 20/312]  eta: 0:05:35  lr: 0.003994  min_lr: 0.003994  loss: 4.4423 (4.2417)  weight_decay: 0.0500 (0.0500)  time: 0.6212  data: 0.1391  max mem: 31830
Epoch: [27]  [ 30/312]  eta: 0:04:15  lr: 0.003994  min_lr: 0.003994  loss: 4.4874 (4.2671)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0442  max mem: 31830
Epoch: [27]  [ 40/312]  eta: 0:03:32  lr: 0.003994  min_lr: 0.003994  loss: 4.4544 (4.2765)  weight_decay: 0.0500 (0.0500)  time: 0.3932  data: 0.0010  max mem: 31830
Epoch: [27]  [ 50/312]  eta: 0:03:08  lr: 0.003994  min_lr: 0.003994  loss: 4.2298 (4.2180)  weight_decay: 0.0500 (0.0500)  time: 0.4254  data: 0.0010  max mem: 31830
Epoch: [27]  [ 60/312]  eta: 0:02:47  lr: 0.003993  min_lr: 0.003993  loss: 3.9788 (4.1721)  weight_decay: 0.0500 (0.0500)  time: 0.4276  data: 0.0009  max mem: 31830
Epoch: [27]  [ 70/312]  eta: 0:02:37  lr: 0.003993  min_lr: 0.003993  loss: 4.1380 (4.2119)  weight_decay: 0.0500 (0.0500)  time: 0.4868  data: 0.0126  max mem: 31830
Epoch: [27]  [ 80/312]  eta: 0:02:28  lr: 0.003993  min_lr: 0.003993  loss: 4.4976 (4.2284)  weight_decay: 0.0500 (0.0500)  time: 0.5631  data: 0.0124  max mem: 31830
Epoch: [27]  [ 90/312]  eta: 0:02:19  lr: 0.003993  min_lr: 0.003993  loss: 4.4237 (4.2335)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0390  max mem: 31830
Epoch: [27]  [100/312]  eta: 0:02:12  lr: 0.003993  min_lr: 0.003993  loss: 4.2881 (4.2325)  weight_decay: 0.0500 (0.0500)  time: 0.5600  data: 0.0462  max mem: 31830
Epoch: [27]  [110/312]  eta: 0:02:01  lr: 0.003993  min_lr: 0.003993  loss: 4.4094 (4.2368)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0085  max mem: 31830
Epoch: [27]  [120/312]  eta: 0:01:57  lr: 0.003993  min_lr: 0.003993  loss: 4.4200 (4.2473)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0344  max mem: 31830
Epoch: [27]  [130/312]  eta: 0:01:49  lr: 0.003993  min_lr: 0.003993  loss: 4.5000 (4.2569)  weight_decay: 0.0500 (0.0500)  time: 0.5899  data: 0.0341  max mem: 31830
Epoch: [27]  [140/312]  eta: 0:01:40  lr: 0.003993  min_lr: 0.003993  loss: 4.3844 (4.2537)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0011  max mem: 31830
Epoch: [27]  [150/312]  eta: 0:01:35  lr: 0.003993  min_lr: 0.003993  loss: 4.3126 (4.2488)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0488  max mem: 31830
Epoch: [27]  [160/312]  eta: 0:01:29  lr: 0.003993  min_lr: 0.003993  loss: 4.2717 (4.2250)  weight_decay: 0.0500 (0.0500)  time: 0.5846  data: 0.0487  max mem: 31830
Epoch: [27]  [170/312]  eta: 0:01:22  lr: 0.003993  min_lr: 0.003993  loss: 4.3189 (4.2446)  weight_decay: 0.0500 (0.0500)  time: 0.4694  data: 0.0265  max mem: 31830
Epoch: [27]  [180/312]  eta: 0:01:16  lr: 0.003993  min_lr: 0.003993  loss: 4.4622 (4.2484)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0659  max mem: 31830
Epoch: [27]  [190/312]  eta: 0:01:09  lr: 0.003993  min_lr: 0.003993  loss: 4.3331 (4.2449)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0402  max mem: 31830
Epoch: [27]  [200/312]  eta: 0:01:04  lr: 0.003993  min_lr: 0.003993  loss: 4.2808 (4.2516)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0594  max mem: 31830
Epoch: [27]  [210/312]  eta: 0:00:58  lr: 0.003993  min_lr: 0.003993  loss: 4.2116 (4.2438)  weight_decay: 0.0500 (0.0500)  time: 0.6266  data: 0.0706  max mem: 31830
Epoch: [27]  [220/312]  eta: 0:00:52  lr: 0.003993  min_lr: 0.003993  loss: 4.3658 (4.2499)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0449  max mem: 31830
Epoch: [27]  [230/312]  eta: 0:00:46  lr: 0.003992  min_lr: 0.003992  loss: 4.3658 (4.2444)  weight_decay: 0.0500 (0.0500)  time: 0.5436  data: 0.0730  max mem: 31830
Epoch: [27]  [240/312]  eta: 0:00:40  lr: 0.003992  min_lr: 0.003992  loss: 4.1133 (4.2278)  weight_decay: 0.0500 (0.0500)  time: 0.5372  data: 0.0400  max mem: 31830
Epoch: [27]  [250/312]  eta: 0:00:35  lr: 0.003992  min_lr: 0.003992  loss: 4.1538 (4.2269)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0457  max mem: 31830
Epoch: [27]  [260/312]  eta: 0:00:29  lr: 0.003992  min_lr: 0.003992  loss: 4.0083 (4.2116)  weight_decay: 0.0500 (0.0500)  time: 0.5980  data: 0.1013  max mem: 31830
Epoch: [27]  [270/312]  eta: 0:00:23  lr: 0.003992  min_lr: 0.003992  loss: 3.9149 (4.2085)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0565  max mem: 31830
Epoch: [27]  [280/312]  eta: 0:00:18  lr: 0.003992  min_lr: 0.003992  loss: 4.3820 (4.2146)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0427  max mem: 31830
Epoch: [27]  [290/312]  eta: 0:00:12  lr: 0.003992  min_lr: 0.003992  loss: 4.2238 (4.2091)  weight_decay: 0.0500 (0.0500)  time: 0.5804  data: 0.0741  max mem: 31830
Epoch: [27]  [300/312]  eta: 0:00:06  lr: 0.003992  min_lr: 0.003992  loss: 4.1263 (4.2129)  weight_decay: 0.0500 (0.0500)  time: 0.4582  data: 0.0320  max mem: 31830
Epoch: [27]  [310/312]  eta: 0:00:01  lr: 0.003992  min_lr: 0.003992  loss: 4.4489 (4.2120)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [27]  [311/312]  eta: 0:00:00  lr: 0.003992  min_lr: 0.003992  loss: 4.4489 (4.2128)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [27] Total time: 0:02:53 (0.5556 s / it)
Averaged stats: lr: 0.003992  min_lr: 0.003992  loss: 4.4489 (4.1921)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.8411 (1.8411)  acc1: 65.2344 (65.2344)  acc5: 87.8906 (87.8906)  time: 8.8508  data: 8.6836  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1479 (2.0518)  acc1: 57.8125 (58.8000)  acc5: 82.2917 (82.8640)  time: 1.1008  data: 0.9649  max mem: 31830
Test: Total time: 0:00:10 (1.1260 s / it)
* Acc@1 58.650 Acc@5 82.922 loss 2.063
Accuracy of the model on the 50000 test images: 58.7%
Max accuracy: 59.17%
Epoch: [28]  [  0/312]  eta: 1:03:07  lr: 0.003992  min_lr: 0.003992  loss: 4.9395 (4.9395)  weight_decay: 0.0500 (0.0500)  time: 12.1389  data: 9.3582  max mem: 31830
Epoch: [28]  [ 10/312]  eta: 0:07:58  lr: 0.003992  min_lr: 0.003992  loss: 4.4823 (4.4029)  weight_decay: 0.0500 (0.0500)  time: 1.5856  data: 0.9640  max mem: 31830
Epoch: [28]  [ 20/312]  eta: 0:05:13  lr: 0.003992  min_lr: 0.003992  loss: 4.4443 (4.3833)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.1089  max mem: 31830
Epoch: [28]  [ 30/312]  eta: 0:04:01  lr: 0.003992  min_lr: 0.003992  loss: 4.3726 (4.3489)  weight_decay: 0.0500 (0.0500)  time: 0.4541  data: 0.0470  max mem: 31830
Epoch: [28]  [ 40/312]  eta: 0:03:27  lr: 0.003992  min_lr: 0.003992  loss: 4.2210 (4.3172)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0007  max mem: 31830
Epoch: [28]  [ 50/312]  eta: 0:03:10  lr: 0.003992  min_lr: 0.003992  loss: 4.3702 (4.3000)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.0690  max mem: 31830
Epoch: [28]  [ 60/312]  eta: 0:02:49  lr: 0.003992  min_lr: 0.003992  loss: 4.4535 (4.2981)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0691  max mem: 31830
Epoch: [28]  [ 70/312]  eta: 0:02:41  lr: 0.003991  min_lr: 0.003991  loss: 4.1688 (4.2479)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0703  max mem: 31830
Epoch: [28]  [ 80/312]  eta: 0:02:31  lr: 0.003991  min_lr: 0.003991  loss: 3.9390 (4.2413)  weight_decay: 0.0500 (0.0500)  time: 0.5909  data: 0.0834  max mem: 31830
Epoch: [28]  [ 90/312]  eta: 0:02:21  lr: 0.003991  min_lr: 0.003991  loss: 4.1474 (4.2390)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0674  max mem: 31830
Epoch: [28]  [100/312]  eta: 0:02:14  lr: 0.003991  min_lr: 0.003991  loss: 4.1971 (4.2370)  weight_decay: 0.0500 (0.0500)  time: 0.5639  data: 0.1125  max mem: 31830
Epoch: [28]  [110/312]  eta: 0:02:03  lr: 0.003991  min_lr: 0.003991  loss: 4.3432 (4.2469)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0592  max mem: 31830
Epoch: [28]  [120/312]  eta: 0:01:57  lr: 0.003991  min_lr: 0.003991  loss: 4.2470 (4.2314)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0426  max mem: 31830
Epoch: [28]  [130/312]  eta: 0:01:50  lr: 0.003991  min_lr: 0.003991  loss: 4.0400 (4.2202)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0423  max mem: 31830
Epoch: [28]  [140/312]  eta: 0:01:42  lr: 0.003991  min_lr: 0.003991  loss: 4.2919 (4.2159)  weight_decay: 0.0500 (0.0500)  time: 0.4839  data: 0.0370  max mem: 31830
Epoch: [28]  [150/312]  eta: 0:01:36  lr: 0.003991  min_lr: 0.003991  loss: 4.3953 (4.2146)  weight_decay: 0.0500 (0.0500)  time: 0.5459  data: 0.0838  max mem: 31830
Epoch: [28]  [160/312]  eta: 0:01:30  lr: 0.003991  min_lr: 0.003991  loss: 4.2905 (4.2020)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.0475  max mem: 31830
Epoch: [28]  [170/312]  eta: 0:01:23  lr: 0.003991  min_lr: 0.003991  loss: 4.0012 (4.1877)  weight_decay: 0.0500 (0.0500)  time: 0.5106  data: 0.0490  max mem: 31830
Epoch: [28]  [180/312]  eta: 0:01:17  lr: 0.003991  min_lr: 0.003991  loss: 4.2182 (4.1968)  weight_decay: 0.0500 (0.0500)  time: 0.5414  data: 0.0846  max mem: 31830
Epoch: [28]  [190/312]  eta: 0:01:10  lr: 0.003991  min_lr: 0.003991  loss: 4.3151 (4.2005)  weight_decay: 0.0500 (0.0500)  time: 0.5030  data: 0.0464  max mem: 31830
Epoch: [28]  [200/312]  eta: 0:01:05  lr: 0.003991  min_lr: 0.003991  loss: 4.3151 (4.2119)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0707  max mem: 31830
Epoch: [28]  [210/312]  eta: 0:00:59  lr: 0.003991  min_lr: 0.003991  loss: 4.1741 (4.1995)  weight_decay: 0.0500 (0.0500)  time: 0.5948  data: 0.0844  max mem: 31830
Epoch: [28]  [220/312]  eta: 0:00:52  lr: 0.003990  min_lr: 0.003990  loss: 3.8594 (4.1952)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0455  max mem: 31830
Epoch: [28]  [230/312]  eta: 0:00:47  lr: 0.003990  min_lr: 0.003990  loss: 4.6050 (4.2172)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0569  max mem: 31830
Epoch: [28]  [240/312]  eta: 0:00:41  lr: 0.003990  min_lr: 0.003990  loss: 4.4912 (4.2080)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0365  max mem: 31830
Epoch: [28]  [250/312]  eta: 0:00:35  lr: 0.003990  min_lr: 0.003990  loss: 4.2407 (4.2093)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0531  max mem: 31830
Epoch: [28]  [260/312]  eta: 0:00:29  lr: 0.003990  min_lr: 0.003990  loss: 4.2407 (4.2051)  weight_decay: 0.0500 (0.0500)  time: 0.5502  data: 0.1039  max mem: 31830
Epoch: [28]  [270/312]  eta: 0:00:23  lr: 0.003990  min_lr: 0.003990  loss: 3.9929 (4.1857)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0616  max mem: 31830
Epoch: [28]  [280/312]  eta: 0:00:18  lr: 0.003990  min_lr: 0.003990  loss: 3.8704 (4.1805)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0699  max mem: 31830
Epoch: [28]  [290/312]  eta: 0:00:12  lr: 0.003990  min_lr: 0.003990  loss: 4.2952 (4.1859)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.0794  max mem: 31830
Epoch: [28]  [300/312]  eta: 0:00:06  lr: 0.003990  min_lr: 0.003990  loss: 4.3637 (4.1877)  weight_decay: 0.0500 (0.0500)  time: 0.4641  data: 0.0254  max mem: 31830
Epoch: [28]  [310/312]  eta: 0:00:01  lr: 0.003990  min_lr: 0.003990  loss: 3.9859 (4.1803)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0061  max mem: 31830
Epoch: [28]  [311/312]  eta: 0:00:00  lr: 0.003990  min_lr: 0.003990  loss: 3.8743 (4.1771)  weight_decay: 0.0500 (0.0500)  time: 0.3863  data: 0.0061  max mem: 31830
Epoch: [28] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.003990  min_lr: 0.003990  loss: 3.8743 (4.1447)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.5863 (1.5863)  acc1: 66.9271 (66.9271)  acc5: 88.4115 (88.4115)  time: 8.0400  data: 7.8730  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9735 (1.8404)  acc1: 60.4167 (60.2720)  acc5: 82.4219 (83.8080)  time: 1.0248  data: 0.8900  max mem: 31830
Test: Total time: 0:00:09 (1.0369 s / it)
* Acc@1 60.648 Acc@5 83.786 loss 1.857
Accuracy of the model on the 50000 test images: 60.6%
Max accuracy: 60.65%
Epoch: [29]  [  0/312]  eta: 1:04:07  lr: 0.003990  min_lr: 0.003990  loss: 3.2824 (3.2824)  weight_decay: 0.0500 (0.0500)  time: 12.3331  data: 10.8565  max mem: 31830
Epoch: [29]  [ 10/312]  eta: 0:08:41  lr: 0.003990  min_lr: 0.003990  loss: 4.1928 (4.0307)  weight_decay: 0.0500 (0.0500)  time: 1.7272  data: 0.9875  max mem: 31830
Epoch: [29]  [ 20/312]  eta: 0:05:29  lr: 0.003990  min_lr: 0.003990  loss: 4.1928 (4.0421)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0236  max mem: 31830
Epoch: [29]  [ 30/312]  eta: 0:04:11  lr: 0.003990  min_lr: 0.003990  loss: 4.2878 (4.0932)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0238  max mem: 31830
Epoch: [29]  [ 40/312]  eta: 0:03:30  lr: 0.003990  min_lr: 0.003990  loss: 4.3096 (4.1076)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0007  max mem: 31830
Epoch: [29]  [ 50/312]  eta: 0:03:03  lr: 0.003989  min_lr: 0.003989  loss: 4.1375 (4.1165)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0009  max mem: 31830
Epoch: [29]  [ 60/312]  eta: 0:02:43  lr: 0.003989  min_lr: 0.003989  loss: 4.1933 (4.1512)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0010  max mem: 31830
Epoch: [29]  [ 70/312]  eta: 0:02:31  lr: 0.003989  min_lr: 0.003989  loss: 4.1933 (4.1008)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0137  max mem: 31830
Epoch: [29]  [ 80/312]  eta: 0:02:24  lr: 0.003989  min_lr: 0.003989  loss: 4.0280 (4.0966)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0537  max mem: 31830
Epoch: [29]  [ 90/312]  eta: 0:02:12  lr: 0.003989  min_lr: 0.003989  loss: 4.1905 (4.0929)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0407  max mem: 31830
Epoch: [29]  [100/312]  eta: 0:02:07  lr: 0.003989  min_lr: 0.003989  loss: 4.2519 (4.0975)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.0555  max mem: 31830
Epoch: [29]  [110/312]  eta: 0:01:59  lr: 0.003989  min_lr: 0.003989  loss: 4.0544 (4.0856)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0717  max mem: 31830
Epoch: [29]  [120/312]  eta: 0:01:53  lr: 0.003989  min_lr: 0.003989  loss: 4.0544 (4.1031)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0504  max mem: 31830
Epoch: [29]  [130/312]  eta: 0:01:47  lr: 0.003989  min_lr: 0.003989  loss: 4.2163 (4.0850)  weight_decay: 0.0500 (0.0500)  time: 0.6127  data: 0.0713  max mem: 31830
Epoch: [29]  [140/312]  eta: 0:01:39  lr: 0.003989  min_lr: 0.003989  loss: 3.9566 (4.0846)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0380  max mem: 31830
Epoch: [29]  [150/312]  eta: 0:01:34  lr: 0.003989  min_lr: 0.003989  loss: 3.9566 (4.0904)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0277  max mem: 31830
Epoch: [29]  [160/312]  eta: 0:01:28  lr: 0.003989  min_lr: 0.003989  loss: 4.3183 (4.0912)  weight_decay: 0.0500 (0.0500)  time: 0.6013  data: 0.0407  max mem: 31830
Epoch: [29]  [170/312]  eta: 0:01:22  lr: 0.003989  min_lr: 0.003989  loss: 4.4637 (4.1127)  weight_decay: 0.0500 (0.0500)  time: 0.5436  data: 0.0430  max mem: 31830
Epoch: [29]  [180/312]  eta: 0:01:16  lr: 0.003988  min_lr: 0.003988  loss: 4.3815 (4.1123)  weight_decay: 0.0500 (0.0500)  time: 0.5760  data: 0.0588  max mem: 31830
Epoch: [29]  [190/312]  eta: 0:01:09  lr: 0.003988  min_lr: 0.003988  loss: 4.0476 (4.1105)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0296  max mem: 31830
Epoch: [29]  [200/312]  eta: 0:01:04  lr: 0.003988  min_lr: 0.003988  loss: 3.8663 (4.0994)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0473  max mem: 31830
Epoch: [29]  [210/312]  eta: 0:00:58  lr: 0.003988  min_lr: 0.003988  loss: 4.0158 (4.1035)  weight_decay: 0.0500 (0.0500)  time: 0.5905  data: 0.0472  max mem: 31830
Epoch: [29]  [220/312]  eta: 0:00:52  lr: 0.003988  min_lr: 0.003988  loss: 4.3413 (4.1116)  weight_decay: 0.0500 (0.0500)  time: 0.4699  data: 0.0209  max mem: 31830
Epoch: [29]  [230/312]  eta: 0:00:46  lr: 0.003988  min_lr: 0.003988  loss: 4.3374 (4.1204)  weight_decay: 0.0500 (0.0500)  time: 0.5494  data: 0.0542  max mem: 31830
Epoch: [29]  [240/312]  eta: 0:00:40  lr: 0.003988  min_lr: 0.003988  loss: 4.3085 (4.1209)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.0341  max mem: 31830
Epoch: [29]  [250/312]  eta: 0:00:35  lr: 0.003988  min_lr: 0.003988  loss: 4.1883 (4.1131)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0287  max mem: 31830
Epoch: [29]  [260/312]  eta: 0:00:29  lr: 0.003988  min_lr: 0.003988  loss: 4.2988 (4.1221)  weight_decay: 0.0500 (0.0500)  time: 0.6010  data: 0.0723  max mem: 31830
Epoch: [29]  [270/312]  eta: 0:00:23  lr: 0.003988  min_lr: 0.003988  loss: 4.3214 (4.1161)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0445  max mem: 31830
Epoch: [29]  [280/312]  eta: 0:00:18  lr: 0.003988  min_lr: 0.003988  loss: 3.8529 (4.1079)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0471  max mem: 31830
Epoch: [29]  [290/312]  eta: 0:00:12  lr: 0.003988  min_lr: 0.003988  loss: 4.0476 (4.1042)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0469  max mem: 31830
Epoch: [29]  [300/312]  eta: 0:00:06  lr: 0.003988  min_lr: 0.003988  loss: 3.9363 (4.0994)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0225  max mem: 31830
Epoch: [29]  [310/312]  eta: 0:00:01  lr: 0.003987  min_lr: 0.003987  loss: 4.1454 (4.1039)  weight_decay: 0.0500 (0.0500)  time: 0.4146  data: 0.0224  max mem: 31830
Epoch: [29]  [311/312]  eta: 0:00:00  lr: 0.003987  min_lr: 0.003987  loss: 4.1454 (4.1048)  weight_decay: 0.0500 (0.0500)  time: 0.3928  data: 0.0001  max mem: 31830
Epoch: [29] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.003987  min_lr: 0.003987  loss: 4.1454 (4.1298)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.5657 (1.5657)  acc1: 65.7552 (65.7552)  acc5: 87.7604 (87.7604)  time: 8.7881  data: 8.6211  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9747 (1.8607)  acc1: 57.1615 (59.0080)  acc5: 83.4635 (83.3760)  time: 1.0944  data: 0.9580  max mem: 31830
Test: Total time: 0:00:10 (1.1119 s / it)
* Acc@1 59.704 Acc@5 83.386 loss 1.865
Accuracy of the model on the 50000 test images: 59.7%
Max accuracy: 60.65%
Epoch: [30]  [  0/312]  eta: 1:02:39  lr: 0.003987  min_lr: 0.003987  loss: 4.8158 (4.8158)  weight_decay: 0.0500 (0.0500)  time: 12.0494  data: 8.5747  max mem: 31830
Epoch: [30]  [ 10/312]  eta: 0:09:11  lr: 0.003987  min_lr: 0.003987  loss: 4.4483 (4.3674)  weight_decay: 0.0500 (0.0500)  time: 1.8274  data: 0.9643  max mem: 31830
Epoch: [30]  [ 20/312]  eta: 0:05:34  lr: 0.003987  min_lr: 0.003987  loss: 4.3212 (4.2049)  weight_decay: 0.0500 (0.0500)  time: 0.5990  data: 0.1020  max mem: 31830
Epoch: [30]  [ 30/312]  eta: 0:04:14  lr: 0.003987  min_lr: 0.003987  loss: 4.0692 (4.1922)  weight_decay: 0.0500 (0.0500)  time: 0.3920  data: 0.0007  max mem: 31830
Epoch: [30]  [ 40/312]  eta: 0:03:31  lr: 0.003987  min_lr: 0.003987  loss: 4.3018 (4.1800)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0007  max mem: 31830
Epoch: [30]  [ 50/312]  eta: 0:03:04  lr: 0.003987  min_lr: 0.003987  loss: 4.3985 (4.2028)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [30]  [ 60/312]  eta: 0:02:44  lr: 0.003987  min_lr: 0.003987  loss: 4.4952 (4.2334)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0008  max mem: 31830
Epoch: [30]  [ 70/312]  eta: 0:02:32  lr: 0.003987  min_lr: 0.003987  loss: 4.4127 (4.2422)  weight_decay: 0.0500 (0.0500)  time: 0.4475  data: 0.0008  max mem: 31830
Epoch: [30]  [ 80/312]  eta: 0:02:22  lr: 0.003987  min_lr: 0.003987  loss: 4.2683 (4.2304)  weight_decay: 0.0500 (0.0500)  time: 0.4964  data: 0.0407  max mem: 31830
Epoch: [30]  [ 90/312]  eta: 0:02:15  lr: 0.003987  min_lr: 0.003987  loss: 4.2492 (4.2321)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0653  max mem: 31830
Epoch: [30]  [100/312]  eta: 0:02:05  lr: 0.003987  min_lr: 0.003987  loss: 4.1000 (4.2009)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0374  max mem: 31830
Epoch: [30]  [110/312]  eta: 0:02:00  lr: 0.003987  min_lr: 0.003987  loss: 4.1726 (4.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0543  max mem: 31830
Epoch: [30]  [120/312]  eta: 0:01:53  lr: 0.003986  min_lr: 0.003986  loss: 4.3819 (4.2193)  weight_decay: 0.0500 (0.0500)  time: 0.5980  data: 0.0702  max mem: 31830
Epoch: [30]  [130/312]  eta: 0:01:45  lr: 0.003986  min_lr: 0.003986  loss: 4.3203 (4.2208)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0423  max mem: 31830
Epoch: [30]  [140/312]  eta: 0:01:40  lr: 0.003986  min_lr: 0.003986  loss: 4.1216 (4.2166)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0430  max mem: 31830
Epoch: [30]  [150/312]  eta: 0:01:34  lr: 0.003986  min_lr: 0.003986  loss: 3.6216 (4.1680)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0293  max mem: 31830
Epoch: [30]  [160/312]  eta: 0:01:27  lr: 0.003986  min_lr: 0.003986  loss: 3.5059 (4.1573)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0390  max mem: 31830
Epoch: [30]  [170/312]  eta: 0:01:22  lr: 0.003986  min_lr: 0.003986  loss: 4.1241 (4.1604)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0681  max mem: 31830
Epoch: [30]  [180/312]  eta: 0:01:15  lr: 0.003986  min_lr: 0.003986  loss: 4.3460 (4.1736)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0413  max mem: 31830
Epoch: [30]  [190/312]  eta: 0:01:09  lr: 0.003986  min_lr: 0.003986  loss: 4.1464 (4.1650)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0593  max mem: 31830
Epoch: [30]  [200/312]  eta: 0:01:04  lr: 0.003986  min_lr: 0.003986  loss: 4.0827 (4.1675)  weight_decay: 0.0500 (0.0500)  time: 0.5882  data: 0.0603  max mem: 31830
Epoch: [30]  [210/312]  eta: 0:00:58  lr: 0.003986  min_lr: 0.003986  loss: 4.3459 (4.1691)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0265  max mem: 31830
Epoch: [30]  [220/312]  eta: 0:00:52  lr: 0.003986  min_lr: 0.003986  loss: 4.0611 (4.1649)  weight_decay: 0.0500 (0.0500)  time: 0.5543  data: 0.0219  max mem: 31830
Epoch: [30]  [230/312]  eta: 0:00:46  lr: 0.003986  min_lr: 0.003986  loss: 4.1773 (4.1625)  weight_decay: 0.0500 (0.0500)  time: 0.5662  data: 0.0327  max mem: 31830
Epoch: [30]  [240/312]  eta: 0:00:40  lr: 0.003985  min_lr: 0.003985  loss: 4.1830 (4.1566)  weight_decay: 0.0500 (0.0500)  time: 0.5396  data: 0.0411  max mem: 31830
Epoch: [30]  [250/312]  eta: 0:00:35  lr: 0.003985  min_lr: 0.003985  loss: 4.1361 (4.1569)  weight_decay: 0.0500 (0.0500)  time: 0.5565  data: 0.0177  max mem: 31830
Epoch: [30]  [260/312]  eta: 0:00:29  lr: 0.003985  min_lr: 0.003985  loss: 4.0143 (4.1465)  weight_decay: 0.0500 (0.0500)  time: 0.4990  data: 0.0072  max mem: 31830
Epoch: [30]  [270/312]  eta: 0:00:23  lr: 0.003985  min_lr: 0.003985  loss: 4.1348 (4.1530)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0430  max mem: 31830
Epoch: [30]  [280/312]  eta: 0:00:18  lr: 0.003985  min_lr: 0.003985  loss: 4.0138 (4.1383)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.0387  max mem: 31830
Epoch: [30]  [290/312]  eta: 0:00:12  lr: 0.003985  min_lr: 0.003985  loss: 4.0103 (4.1406)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0019  max mem: 31830
Epoch: [30]  [300/312]  eta: 0:00:06  lr: 0.003985  min_lr: 0.003985  loss: 4.2351 (4.1433)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0006  max mem: 31830
Epoch: [30]  [310/312]  eta: 0:00:01  lr: 0.003985  min_lr: 0.003985  loss: 4.3950 (4.1514)  weight_decay: 0.0500 (0.0500)  time: 0.4154  data: 0.0005  max mem: 31830
Epoch: [30]  [311/312]  eta: 0:00:00  lr: 0.003985  min_lr: 0.003985  loss: 4.3634 (4.1521)  weight_decay: 0.0500 (0.0500)  time: 0.4148  data: 0.0001  max mem: 31830
Epoch: [30] Total time: 0:02:53 (0.5563 s / it)
Averaged stats: lr: 0.003985  min_lr: 0.003985  loss: 4.3634 (4.1174)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.8627 (1.8627)  acc1: 63.4115 (63.4115)  acc5: 88.0208 (88.0208)  time: 8.5407  data: 8.3733  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1958 (2.0750)  acc1: 58.8542 (58.5920)  acc5: 82.1615 (83.0880)  time: 1.0659  data: 0.9305  max mem: 31830
Test: Total time: 0:00:09 (1.0841 s / it)
* Acc@1 59.600 Acc@5 83.200 loss 2.070
Accuracy of the model on the 50000 test images: 59.6%
Max accuracy: 60.65%
Epoch: [31]  [  0/312]  eta: 1:02:16  lr: 0.003985  min_lr: 0.003985  loss: 3.6815 (3.6815)  weight_decay: 0.0500 (0.0500)  time: 11.9773  data: 11.0095  max mem: 31830
Epoch: [31]  [ 10/312]  eta: 0:08:12  lr: 0.003985  min_lr: 0.003985  loss: 4.4212 (4.3094)  weight_decay: 0.0500 (0.0500)  time: 1.6306  data: 1.0014  max mem: 31830
Epoch: [31]  [ 20/312]  eta: 0:05:23  lr: 0.003985  min_lr: 0.003985  loss: 4.2804 (4.2232)  weight_decay: 0.0500 (0.0500)  time: 0.5659  data: 0.0760  max mem: 31830
Epoch: [31]  [ 30/312]  eta: 0:04:08  lr: 0.003985  min_lr: 0.003985  loss: 4.1730 (4.2523)  weight_decay: 0.0500 (0.0500)  time: 0.4676  data: 0.0762  max mem: 31830
Epoch: [31]  [ 40/312]  eta: 0:03:26  lr: 0.003984  min_lr: 0.003984  loss: 4.3163 (4.2770)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0008  max mem: 31830
Epoch: [31]  [ 50/312]  eta: 0:03:08  lr: 0.003984  min_lr: 0.003984  loss: 4.2980 (4.1940)  weight_decay: 0.0500 (0.0500)  time: 0.4675  data: 0.0558  max mem: 31830
Epoch: [31]  [ 60/312]  eta: 0:02:47  lr: 0.003984  min_lr: 0.003984  loss: 4.2352 (4.2103)  weight_decay: 0.0500 (0.0500)  time: 0.4694  data: 0.0560  max mem: 31830
Epoch: [31]  [ 70/312]  eta: 0:02:37  lr: 0.003984  min_lr: 0.003984  loss: 4.3233 (4.1874)  weight_decay: 0.0500 (0.0500)  time: 0.4821  data: 0.0748  max mem: 31830
Epoch: [31]  [ 80/312]  eta: 0:02:29  lr: 0.003984  min_lr: 0.003984  loss: 4.1100 (4.1631)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1392  max mem: 31830
Epoch: [31]  [ 90/312]  eta: 0:02:18  lr: 0.003984  min_lr: 0.003984  loss: 4.1335 (4.1596)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0652  max mem: 31830
Epoch: [31]  [100/312]  eta: 0:02:12  lr: 0.003984  min_lr: 0.003984  loss: 4.0113 (4.1348)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0465  max mem: 31830
Epoch: [31]  [110/312]  eta: 0:02:01  lr: 0.003984  min_lr: 0.003984  loss: 4.0113 (4.1306)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0465  max mem: 31830
Epoch: [31]  [120/312]  eta: 0:01:56  lr: 0.003984  min_lr: 0.003984  loss: 4.1679 (4.1389)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0503  max mem: 31830
Epoch: [31]  [130/312]  eta: 0:01:50  lr: 0.003984  min_lr: 0.003984  loss: 4.1438 (4.1357)  weight_decay: 0.0500 (0.0500)  time: 0.6439  data: 0.1104  max mem: 31830
Epoch: [31]  [140/312]  eta: 0:01:42  lr: 0.003984  min_lr: 0.003984  loss: 4.1130 (4.1242)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0610  max mem: 31830
Epoch: [31]  [150/312]  eta: 0:01:35  lr: 0.003983  min_lr: 0.003983  loss: 4.2411 (4.1240)  weight_decay: 0.0500 (0.0500)  time: 0.4764  data: 0.0494  max mem: 31830
Epoch: [31]  [160/312]  eta: 0:01:29  lr: 0.003983  min_lr: 0.003983  loss: 4.2411 (4.1197)  weight_decay: 0.0500 (0.0500)  time: 0.5482  data: 0.1192  max mem: 31830
Epoch: [31]  [170/312]  eta: 0:01:22  lr: 0.003983  min_lr: 0.003983  loss: 4.1911 (4.1192)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0708  max mem: 31830
Epoch: [31]  [180/312]  eta: 0:01:17  lr: 0.003983  min_lr: 0.003983  loss: 3.9299 (4.1048)  weight_decay: 0.0500 (0.0500)  time: 0.5810  data: 0.0774  max mem: 31830
Epoch: [31]  [190/312]  eta: 0:01:10  lr: 0.003983  min_lr: 0.003983  loss: 4.1361 (4.1041)  weight_decay: 0.0500 (0.0500)  time: 0.5474  data: 0.0774  max mem: 31830
Epoch: [31]  [200/312]  eta: 0:01:04  lr: 0.003983  min_lr: 0.003983  loss: 4.0685 (4.1007)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0345  max mem: 31830
Epoch: [31]  [210/312]  eta: 0:00:59  lr: 0.003983  min_lr: 0.003983  loss: 4.3276 (4.1099)  weight_decay: 0.0500 (0.0500)  time: 0.6314  data: 0.0741  max mem: 31830
Epoch: [31]  [220/312]  eta: 0:00:52  lr: 0.003983  min_lr: 0.003983  loss: 4.3276 (4.1119)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0407  max mem: 31830
Epoch: [31]  [230/312]  eta: 0:00:47  lr: 0.003983  min_lr: 0.003983  loss: 4.1397 (4.0982)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0415  max mem: 31830
Epoch: [31]  [240/312]  eta: 0:00:41  lr: 0.003983  min_lr: 0.003983  loss: 3.9091 (4.1021)  weight_decay: 0.0500 (0.0500)  time: 0.5636  data: 0.0911  max mem: 31830
Epoch: [31]  [250/312]  eta: 0:00:35  lr: 0.003982  min_lr: 0.003982  loss: 4.3655 (4.1063)  weight_decay: 0.0500 (0.0500)  time: 0.4748  data: 0.0507  max mem: 31830
Epoch: [31]  [260/312]  eta: 0:00:29  lr: 0.003982  min_lr: 0.003982  loss: 4.3860 (4.1098)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0682  max mem: 31830
Epoch: [31]  [270/312]  eta: 0:00:23  lr: 0.003982  min_lr: 0.003982  loss: 4.3561 (4.1093)  weight_decay: 0.0500 (0.0500)  time: 0.5838  data: 0.0683  max mem: 31830
Epoch: [31]  [280/312]  eta: 0:00:18  lr: 0.003982  min_lr: 0.003982  loss: 4.1346 (4.1094)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0808  max mem: 31830
Epoch: [31]  [290/312]  eta: 0:00:12  lr: 0.003982  min_lr: 0.003982  loss: 3.8915 (4.0997)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.1133  max mem: 31830
Epoch: [31]  [300/312]  eta: 0:00:06  lr: 0.003982  min_lr: 0.003982  loss: 3.8824 (4.0987)  weight_decay: 0.0500 (0.0500)  time: 0.4677  data: 0.0330  max mem: 31830
Epoch: [31]  [310/312]  eta: 0:00:01  lr: 0.003982  min_lr: 0.003982  loss: 4.3331 (4.1050)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [31]  [311/312]  eta: 0:00:00  lr: 0.003982  min_lr: 0.003982  loss: 4.3331 (4.1044)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [31] Total time: 0:02:54 (0.5602 s / it)
Averaged stats: lr: 0.003982  min_lr: 0.003982  loss: 4.3331 (4.0997)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.7055 (1.7055)  acc1: 66.6667 (66.6667)  acc5: 86.9792 (86.9792)  time: 8.2539  data: 8.0897  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1508 (1.9387)  acc1: 60.0260 (60.1600)  acc5: 81.5104 (83.4080)  time: 1.0360  data: 0.8989  max mem: 31830
Test: Total time: 0:00:09 (1.0475 s / it)
* Acc@1 60.122 Acc@5 83.350 loss 1.956
Accuracy of the model on the 50000 test images: 60.1%
Max accuracy: 60.65%
Epoch: [32]  [  0/312]  eta: 0:55:34  lr: 0.003982  min_lr: 0.003982  loss: 3.6687 (3.6687)  weight_decay: 0.0500 (0.0500)  time: 10.6885  data: 9.4708  max mem: 31830
Epoch: [32]  [ 10/312]  eta: 0:08:51  lr: 0.003982  min_lr: 0.003982  loss: 3.9779 (3.9032)  weight_decay: 0.0500 (0.0500)  time: 1.7606  data: 0.8697  max mem: 31830
Epoch: [32]  [ 20/312]  eta: 0:05:30  lr: 0.003982  min_lr: 0.003982  loss: 4.0264 (3.9901)  weight_decay: 0.0500 (0.0500)  time: 0.6523  data: 0.0296  max mem: 31830
Epoch: [32]  [ 30/312]  eta: 0:04:12  lr: 0.003982  min_lr: 0.003982  loss: 4.1526 (4.0930)  weight_decay: 0.0500 (0.0500)  time: 0.4178  data: 0.0260  max mem: 31830
Epoch: [32]  [ 40/312]  eta: 0:03:30  lr: 0.003982  min_lr: 0.003982  loss: 4.3375 (4.1147)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0021  max mem: 31830
Epoch: [32]  [ 50/312]  eta: 0:03:03  lr: 0.003981  min_lr: 0.003981  loss: 4.3912 (4.1697)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0014  max mem: 31830
Epoch: [32]  [ 60/312]  eta: 0:02:43  lr: 0.003981  min_lr: 0.003981  loss: 4.4148 (4.1674)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0008  max mem: 31830
Epoch: [32]  [ 70/312]  eta: 0:02:31  lr: 0.003981  min_lr: 0.003981  loss: 4.3056 (4.1487)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0007  max mem: 31830
Epoch: [32]  [ 80/312]  eta: 0:02:23  lr: 0.003981  min_lr: 0.003981  loss: 4.2866 (4.1755)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0146  max mem: 31830
Epoch: [32]  [ 90/312]  eta: 0:02:13  lr: 0.003981  min_lr: 0.003981  loss: 4.3393 (4.1799)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0282  max mem: 31830
Epoch: [32]  [100/312]  eta: 0:02:06  lr: 0.003981  min_lr: 0.003981  loss: 4.1652 (4.1875)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0263  max mem: 31830
Epoch: [32]  [110/312]  eta: 0:01:59  lr: 0.003981  min_lr: 0.003981  loss: 4.2564 (4.1834)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0565  max mem: 31830
Epoch: [32]  [120/312]  eta: 0:01:52  lr: 0.003981  min_lr: 0.003981  loss: 4.2416 (4.1630)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0451  max mem: 31830
Epoch: [32]  [130/312]  eta: 0:01:46  lr: 0.003981  min_lr: 0.003981  loss: 4.2416 (4.1727)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0322  max mem: 31830
Epoch: [32]  [140/312]  eta: 0:01:39  lr: 0.003981  min_lr: 0.003981  loss: 4.2191 (4.1740)  weight_decay: 0.0500 (0.0500)  time: 0.5457  data: 0.0625  max mem: 31830
Epoch: [32]  [150/312]  eta: 0:01:33  lr: 0.003980  min_lr: 0.003980  loss: 4.1556 (4.1670)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0317  max mem: 31830
Epoch: [32]  [160/312]  eta: 0:01:27  lr: 0.003980  min_lr: 0.003980  loss: 4.2342 (4.1647)  weight_decay: 0.0500 (0.0500)  time: 0.5638  data: 0.0289  max mem: 31830
Epoch: [32]  [170/312]  eta: 0:01:21  lr: 0.003980  min_lr: 0.003980  loss: 4.2374 (4.1582)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0429  max mem: 31830
Epoch: [32]  [180/312]  eta: 0:01:15  lr: 0.003980  min_lr: 0.003980  loss: 3.9649 (4.1442)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0148  max mem: 31830
Epoch: [32]  [190/312]  eta: 0:01:09  lr: 0.003980  min_lr: 0.003980  loss: 4.1547 (4.1565)  weight_decay: 0.0500 (0.0500)  time: 0.5474  data: 0.0151  max mem: 31830
Epoch: [32]  [200/312]  eta: 0:01:04  lr: 0.003980  min_lr: 0.003980  loss: 4.4024 (4.1538)  weight_decay: 0.0500 (0.0500)  time: 0.5938  data: 0.0151  max mem: 31830
Epoch: [32]  [210/312]  eta: 0:00:57  lr: 0.003980  min_lr: 0.003980  loss: 4.3589 (4.1566)  weight_decay: 0.0500 (0.0500)  time: 0.5451  data: 0.0009  max mem: 31830
Epoch: [32]  [220/312]  eta: 0:00:52  lr: 0.003980  min_lr: 0.003980  loss: 4.3406 (4.1613)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0011  max mem: 31830
Epoch: [32]  [230/312]  eta: 0:00:46  lr: 0.003980  min_lr: 0.003980  loss: 4.2041 (4.1551)  weight_decay: 0.0500 (0.0500)  time: 0.5846  data: 0.0010  max mem: 31830
Epoch: [32]  [240/312]  eta: 0:00:40  lr: 0.003980  min_lr: 0.003980  loss: 4.2008 (4.1459)  weight_decay: 0.0500 (0.0500)  time: 0.5635  data: 0.0015  max mem: 31830
Epoch: [32]  [250/312]  eta: 0:00:35  lr: 0.003979  min_lr: 0.003979  loss: 4.0224 (4.1373)  weight_decay: 0.0500 (0.0500)  time: 0.5442  data: 0.0027  max mem: 31830
Epoch: [32]  [260/312]  eta: 0:00:29  lr: 0.003979  min_lr: 0.003979  loss: 4.1315 (4.1359)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0081  max mem: 31830
Epoch: [32]  [270/312]  eta: 0:00:23  lr: 0.003979  min_lr: 0.003979  loss: 4.4405 (4.1552)  weight_decay: 0.0500 (0.0500)  time: 0.4893  data: 0.0069  max mem: 31830
Epoch: [32]  [280/312]  eta: 0:00:18  lr: 0.003979  min_lr: 0.003979  loss: 4.4865 (4.1649)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0021  max mem: 31830
Epoch: [32]  [290/312]  eta: 0:00:12  lr: 0.003979  min_lr: 0.003979  loss: 4.1201 (4.1517)  weight_decay: 0.0500 (0.0500)  time: 0.5866  data: 0.0082  max mem: 31830
Epoch: [32]  [300/312]  eta: 0:00:06  lr: 0.003979  min_lr: 0.003979  loss: 4.1201 (4.1550)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0065  max mem: 31830
Epoch: [32]  [310/312]  eta: 0:00:01  lr: 0.003979  min_lr: 0.003979  loss: 4.2438 (4.1511)  weight_decay: 0.0500 (0.0500)  time: 0.3823  data: 0.0002  max mem: 31830
Epoch: [32]  [311/312]  eta: 0:00:00  lr: 0.003979  min_lr: 0.003979  loss: 4.2665 (4.1536)  weight_decay: 0.0500 (0.0500)  time: 0.3818  data: 0.0002  max mem: 31830
Epoch: [32] Total time: 0:02:53 (0.5550 s / it)
Averaged stats: lr: 0.003979  min_lr: 0.003979  loss: 4.2665 (4.0865)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.7429 (1.7429)  acc1: 67.3177 (67.3177)  acc5: 87.8906 (87.8906)  time: 8.6621  data: 8.4946  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9961 (1.9479)  acc1: 60.6771 (59.8720)  acc5: 82.1615 (83.3120)  time: 1.0791  data: 0.9439  max mem: 31830
Test: Total time: 0:00:09 (1.0897 s / it)
* Acc@1 60.292 Acc@5 83.408 loss 1.960
Accuracy of the model on the 50000 test images: 60.3%
Max accuracy: 60.65%
Epoch: [33]  [  0/312]  eta: 1:03:28  lr: 0.003979  min_lr: 0.003979  loss: 3.9347 (3.9347)  weight_decay: 0.0500 (0.0500)  time: 12.2078  data: 8.3274  max mem: 31830
Epoch: [33]  [ 10/312]  eta: 0:08:56  lr: 0.003979  min_lr: 0.003979  loss: 4.4363 (4.4280)  weight_decay: 0.0500 (0.0500)  time: 1.7750  data: 0.9417  max mem: 31830
Epoch: [33]  [ 20/312]  eta: 0:05:25  lr: 0.003979  min_lr: 0.003979  loss: 4.0755 (4.0734)  weight_decay: 0.0500 (0.0500)  time: 0.5604  data: 0.1019  max mem: 31830
Epoch: [33]  [ 30/312]  eta: 0:04:09  lr: 0.003978  min_lr: 0.003978  loss: 3.8397 (4.0611)  weight_decay: 0.0500 (0.0500)  time: 0.3944  data: 0.0007  max mem: 31830
Epoch: [33]  [ 40/312]  eta: 0:03:28  lr: 0.003978  min_lr: 0.003978  loss: 4.0141 (4.0809)  weight_decay: 0.0500 (0.0500)  time: 0.4010  data: 0.0007  max mem: 31830
Epoch: [33]  [ 50/312]  eta: 0:03:01  lr: 0.003978  min_lr: 0.003978  loss: 4.1711 (4.1156)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0007  max mem: 31830
Epoch: [33]  [ 60/312]  eta: 0:02:42  lr: 0.003978  min_lr: 0.003978  loss: 4.2693 (4.1281)  weight_decay: 0.0500 (0.0500)  time: 0.3986  data: 0.0008  max mem: 31830
Epoch: [33]  [ 70/312]  eta: 0:02:29  lr: 0.003978  min_lr: 0.003978  loss: 4.1895 (4.1259)  weight_decay: 0.0500 (0.0500)  time: 0.4201  data: 0.0247  max mem: 31830
Epoch: [33]  [ 80/312]  eta: 0:02:21  lr: 0.003978  min_lr: 0.003978  loss: 4.0066 (4.0865)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0399  max mem: 31830
Epoch: [33]  [ 90/312]  eta: 0:02:14  lr: 0.003978  min_lr: 0.003978  loss: 3.6196 (4.0545)  weight_decay: 0.0500 (0.0500)  time: 0.5613  data: 0.0160  max mem: 31830
Epoch: [33]  [100/312]  eta: 0:02:06  lr: 0.003978  min_lr: 0.003978  loss: 4.0513 (4.0687)  weight_decay: 0.0500 (0.0500)  time: 0.5240  data: 0.0423  max mem: 31830
Epoch: [33]  [110/312]  eta: 0:01:58  lr: 0.003978  min_lr: 0.003978  loss: 3.9398 (4.0386)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0482  max mem: 31830
Epoch: [33]  [120/312]  eta: 0:01:53  lr: 0.003977  min_lr: 0.003977  loss: 3.9225 (4.0544)  weight_decay: 0.0500 (0.0500)  time: 0.5874  data: 0.0213  max mem: 31830
Epoch: [33]  [130/312]  eta: 0:01:46  lr: 0.003977  min_lr: 0.003977  loss: 4.2377 (4.0520)  weight_decay: 0.0500 (0.0500)  time: 0.5641  data: 0.0526  max mem: 31830
Epoch: [33]  [140/312]  eta: 0:01:40  lr: 0.003977  min_lr: 0.003977  loss: 3.9586 (4.0443)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0437  max mem: 31830
Epoch: [33]  [150/312]  eta: 0:01:33  lr: 0.003977  min_lr: 0.003977  loss: 3.9456 (4.0411)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0410  max mem: 31830
Epoch: [33]  [160/312]  eta: 0:01:27  lr: 0.003977  min_lr: 0.003977  loss: 3.9345 (4.0425)  weight_decay: 0.0500 (0.0500)  time: 0.5362  data: 0.0648  max mem: 31830
Epoch: [33]  [170/312]  eta: 0:01:22  lr: 0.003977  min_lr: 0.003977  loss: 4.0271 (4.0381)  weight_decay: 0.0500 (0.0500)  time: 0.6050  data: 0.0304  max mem: 31830
Epoch: [33]  [180/312]  eta: 0:01:15  lr: 0.003977  min_lr: 0.003977  loss: 4.2878 (4.0556)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0124  max mem: 31830
Epoch: [33]  [190/312]  eta: 0:01:09  lr: 0.003977  min_lr: 0.003977  loss: 4.3339 (4.0567)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0123  max mem: 31830
Epoch: [33]  [200/312]  eta: 0:01:04  lr: 0.003977  min_lr: 0.003977  loss: 3.9817 (4.0477)  weight_decay: 0.0500 (0.0500)  time: 0.6246  data: 0.0223  max mem: 31830
Epoch: [33]  [210/312]  eta: 0:00:58  lr: 0.003977  min_lr: 0.003977  loss: 4.1978 (4.0595)  weight_decay: 0.0500 (0.0500)  time: 0.5739  data: 0.0413  max mem: 31830
Epoch: [33]  [220/312]  eta: 0:00:52  lr: 0.003976  min_lr: 0.003976  loss: 4.1978 (4.0623)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0198  max mem: 31830
Epoch: [33]  [230/312]  eta: 0:00:46  lr: 0.003976  min_lr: 0.003976  loss: 4.1005 (4.0599)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0007  max mem: 31830
Epoch: [33]  [240/312]  eta: 0:00:40  lr: 0.003976  min_lr: 0.003976  loss: 3.8484 (4.0609)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.0129  max mem: 31830
Epoch: [33]  [250/312]  eta: 0:00:35  lr: 0.003976  min_lr: 0.003976  loss: 3.7833 (4.0560)  weight_decay: 0.0500 (0.0500)  time: 0.6148  data: 0.0130  max mem: 31830
Epoch: [33]  [260/312]  eta: 0:00:29  lr: 0.003976  min_lr: 0.003976  loss: 4.3376 (4.0611)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0010  max mem: 31830
Epoch: [33]  [270/312]  eta: 0:00:23  lr: 0.003976  min_lr: 0.003976  loss: 3.7343 (4.0409)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0013  max mem: 31830
Epoch: [33]  [280/312]  eta: 0:00:18  lr: 0.003976  min_lr: 0.003976  loss: 3.6874 (4.0440)  weight_decay: 0.0500 (0.0500)  time: 0.6248  data: 0.0161  max mem: 31830
Epoch: [33]  [290/312]  eta: 0:00:12  lr: 0.003976  min_lr: 0.003976  loss: 4.1367 (4.0479)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0155  max mem: 31830
Epoch: [33]  [300/312]  eta: 0:00:06  lr: 0.003976  min_lr: 0.003976  loss: 3.9929 (4.0375)  weight_decay: 0.0500 (0.0500)  time: 0.4317  data: 0.0003  max mem: 31830
Epoch: [33]  [310/312]  eta: 0:00:01  lr: 0.003975  min_lr: 0.003975  loss: 3.7959 (4.0358)  weight_decay: 0.0500 (0.0500)  time: 0.4148  data: 0.0001  max mem: 31830
Epoch: [33]  [311/312]  eta: 0:00:00  lr: 0.003975  min_lr: 0.003975  loss: 3.7959 (4.0371)  weight_decay: 0.0500 (0.0500)  time: 0.4146  data: 0.0001  max mem: 31830
Epoch: [33] Total time: 0:02:53 (0.5560 s / it)
Averaged stats: lr: 0.003975  min_lr: 0.003975  loss: 3.7959 (4.0819)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6486 (1.6486)  acc1: 65.2344 (65.2344)  acc5: 87.8906 (87.8906)  time: 8.2455  data: 8.0786  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8864 (1.8162)  acc1: 59.6354 (60.8320)  acc5: 82.6823 (84.1600)  time: 1.0383  data: 0.9024  max mem: 31830
Test: Total time: 0:00:09 (1.0477 s / it)
* Acc@1 60.942 Acc@5 84.386 loss 1.807
Accuracy of the model on the 50000 test images: 60.9%
Max accuracy: 60.94%
Epoch: [34]  [  0/312]  eta: 0:57:53  lr: 0.003975  min_lr: 0.003975  loss: 4.3599 (4.3599)  weight_decay: 0.0500 (0.0500)  time: 11.1333  data: 8.7842  max mem: 31830
Epoch: [34]  [ 10/312]  eta: 0:08:26  lr: 0.003975  min_lr: 0.003975  loss: 3.9596 (3.9604)  weight_decay: 0.0500 (0.0500)  time: 1.6785  data: 0.9216  max mem: 31830
Epoch: [34]  [ 20/312]  eta: 0:05:31  lr: 0.003975  min_lr: 0.003975  loss: 3.9212 (3.9651)  weight_decay: 0.0500 (0.0500)  time: 0.6356  data: 0.0681  max mem: 31830
Epoch: [34]  [ 30/312]  eta: 0:04:13  lr: 0.003975  min_lr: 0.003975  loss: 4.3959 (4.1204)  weight_decay: 0.0500 (0.0500)  time: 0.4684  data: 0.0007  max mem: 31830
Epoch: [34]  [ 40/312]  eta: 0:03:30  lr: 0.003975  min_lr: 0.003975  loss: 4.3959 (4.0740)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0007  max mem: 31830
Epoch: [34]  [ 50/312]  eta: 0:03:03  lr: 0.003975  min_lr: 0.003975  loss: 3.8046 (4.0281)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0007  max mem: 31830
Epoch: [34]  [ 60/312]  eta: 0:02:44  lr: 0.003975  min_lr: 0.003975  loss: 3.8286 (4.0335)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0014  max mem: 31830
Epoch: [34]  [ 70/312]  eta: 0:02:33  lr: 0.003975  min_lr: 0.003975  loss: 4.1464 (4.0366)  weight_decay: 0.0500 (0.0500)  time: 0.4658  data: 0.0016  max mem: 31830
Epoch: [34]  [ 80/312]  eta: 0:02:25  lr: 0.003974  min_lr: 0.003974  loss: 4.2114 (4.0809)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0362  max mem: 31830
Epoch: [34]  [ 90/312]  eta: 0:02:14  lr: 0.003974  min_lr: 0.003974  loss: 4.2114 (4.0833)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0367  max mem: 31830
Epoch: [34]  [100/312]  eta: 0:02:08  lr: 0.003974  min_lr: 0.003974  loss: 4.1523 (4.0909)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0366  max mem: 31830
Epoch: [34]  [110/312]  eta: 0:01:58  lr: 0.003974  min_lr: 0.003974  loss: 4.3049 (4.0787)  weight_decay: 0.0500 (0.0500)  time: 0.4823  data: 0.0360  max mem: 31830
Epoch: [34]  [120/312]  eta: 0:01:52  lr: 0.003974  min_lr: 0.003974  loss: 4.2487 (4.0716)  weight_decay: 0.0500 (0.0500)  time: 0.5016  data: 0.0507  max mem: 31830
Epoch: [34]  [130/312]  eta: 0:01:47  lr: 0.003974  min_lr: 0.003974  loss: 4.2514 (4.0892)  weight_decay: 0.0500 (0.0500)  time: 0.6331  data: 0.0995  max mem: 31830
Epoch: [34]  [140/312]  eta: 0:01:39  lr: 0.003974  min_lr: 0.003974  loss: 4.3358 (4.0924)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0497  max mem: 31830
Epoch: [34]  [150/312]  eta: 0:01:34  lr: 0.003974  min_lr: 0.003974  loss: 4.1900 (4.0953)  weight_decay: 0.0500 (0.0500)  time: 0.5107  data: 0.0141  max mem: 31830
Epoch: [34]  [160/312]  eta: 0:01:28  lr: 0.003974  min_lr: 0.003974  loss: 4.0248 (4.0910)  weight_decay: 0.0500 (0.0500)  time: 0.6055  data: 0.0290  max mem: 31830
Epoch: [34]  [170/312]  eta: 0:01:21  lr: 0.003973  min_lr: 0.003973  loss: 4.0248 (4.0810)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0158  max mem: 31830
Epoch: [34]  [180/312]  eta: 0:01:16  lr: 0.003973  min_lr: 0.003973  loss: 4.1861 (4.0865)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0445  max mem: 31830
Epoch: [34]  [190/312]  eta: 0:01:09  lr: 0.003973  min_lr: 0.003973  loss: 4.1067 (4.0665)  weight_decay: 0.0500 (0.0500)  time: 0.5401  data: 0.0445  max mem: 31830
Epoch: [34]  [200/312]  eta: 0:01:03  lr: 0.003973  min_lr: 0.003973  loss: 4.1084 (4.0653)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0169  max mem: 31830
Epoch: [34]  [210/312]  eta: 0:00:58  lr: 0.003973  min_lr: 0.003973  loss: 4.2274 (4.0667)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0169  max mem: 31830
Epoch: [34]  [220/312]  eta: 0:00:51  lr: 0.003973  min_lr: 0.003973  loss: 3.9709 (4.0545)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0136  max mem: 31830
Epoch: [34]  [230/312]  eta: 0:00:46  lr: 0.003973  min_lr: 0.003973  loss: 4.1709 (4.0612)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0137  max mem: 31830
Epoch: [34]  [240/312]  eta: 0:00:40  lr: 0.003973  min_lr: 0.003973  loss: 4.2651 (4.0631)  weight_decay: 0.0500 (0.0500)  time: 0.5562  data: 0.0008  max mem: 31830
Epoch: [34]  [250/312]  eta: 0:00:34  lr: 0.003972  min_lr: 0.003972  loss: 4.2819 (4.0642)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0275  max mem: 31830
Epoch: [34]  [260/312]  eta: 0:00:29  lr: 0.003972  min_lr: 0.003972  loss: 4.2819 (4.0705)  weight_decay: 0.0500 (0.0500)  time: 0.5786  data: 0.0364  max mem: 31830
Epoch: [34]  [270/312]  eta: 0:00:23  lr: 0.003972  min_lr: 0.003972  loss: 4.2056 (4.0721)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0096  max mem: 31830
Epoch: [34]  [280/312]  eta: 0:00:17  lr: 0.003972  min_lr: 0.003972  loss: 4.2056 (4.0716)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0061  max mem: 31830
Epoch: [34]  [290/312]  eta: 0:00:12  lr: 0.003972  min_lr: 0.003972  loss: 4.1770 (4.0647)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0059  max mem: 31830
Epoch: [34]  [300/312]  eta: 0:00:06  lr: 0.003972  min_lr: 0.003972  loss: 3.9577 (4.0652)  weight_decay: 0.0500 (0.0500)  time: 0.4768  data: 0.0095  max mem: 31830
Epoch: [34]  [310/312]  eta: 0:00:01  lr: 0.003972  min_lr: 0.003972  loss: 4.0258 (4.0582)  weight_decay: 0.0500 (0.0500)  time: 0.4292  data: 0.0094  max mem: 31830
Epoch: [34]  [311/312]  eta: 0:00:00  lr: 0.003972  min_lr: 0.003972  loss: 4.0258 (4.0560)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [34] Total time: 0:02:52 (0.5538 s / it)
Averaged stats: lr: 0.003972  min_lr: 0.003972  loss: 4.0258 (4.0815)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.5505 (1.5505)  acc1: 71.0938 (71.0938)  acc5: 89.1927 (89.1927)  time: 8.4520  data: 8.2846  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9430 (1.8659)  acc1: 61.5885 (61.5840)  acc5: 83.8542 (84.6880)  time: 1.0568  data: 0.9206  max mem: 31830
Test: Total time: 0:00:09 (1.0752 s / it)
* Acc@1 61.590 Acc@5 84.584 loss 1.868
Accuracy of the model on the 50000 test images: 61.6%
Max accuracy: 61.59%
Epoch: [35]  [  0/312]  eta: 1:00:52  lr: 0.003972  min_lr: 0.003972  loss: 3.5188 (3.5188)  weight_decay: 0.0500 (0.0500)  time: 11.7067  data: 10.6764  max mem: 31830
Epoch: [35]  [ 10/312]  eta: 0:08:27  lr: 0.003972  min_lr: 0.003972  loss: 3.8181 (3.8961)  weight_decay: 0.0500 (0.0500)  time: 1.6820  data: 1.0132  max mem: 31830
Epoch: [35]  [ 20/312]  eta: 0:05:24  lr: 0.003972  min_lr: 0.003972  loss: 3.8492 (3.9248)  weight_decay: 0.0500 (0.0500)  time: 0.5806  data: 0.0590  max mem: 31830
Epoch: [35]  [ 30/312]  eta: 0:04:08  lr: 0.003971  min_lr: 0.003971  loss: 4.1525 (4.0507)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0360  max mem: 31830
Epoch: [35]  [ 40/312]  eta: 0:03:27  lr: 0.003971  min_lr: 0.003971  loss: 4.1906 (4.0181)  weight_decay: 0.0500 (0.0500)  time: 0.3942  data: 0.0007  max mem: 31830
Epoch: [35]  [ 50/312]  eta: 0:03:00  lr: 0.003971  min_lr: 0.003971  loss: 4.1638 (4.0425)  weight_decay: 0.0500 (0.0500)  time: 0.3936  data: 0.0007  max mem: 31830
Epoch: [35]  [ 60/312]  eta: 0:02:41  lr: 0.003971  min_lr: 0.003971  loss: 4.3289 (4.0708)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0010  max mem: 31830
Epoch: [35]  [ 70/312]  eta: 0:02:32  lr: 0.003971  min_lr: 0.003971  loss: 4.1670 (4.0407)  weight_decay: 0.0500 (0.0500)  time: 0.4784  data: 0.0725  max mem: 31830
Epoch: [35]  [ 80/312]  eta: 0:02:26  lr: 0.003971  min_lr: 0.003971  loss: 4.2065 (4.0577)  weight_decay: 0.0500 (0.0500)  time: 0.6060  data: 0.1206  max mem: 31830
Epoch: [35]  [ 90/312]  eta: 0:02:16  lr: 0.003971  min_lr: 0.003971  loss: 4.2750 (4.0860)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0726  max mem: 31830
Epoch: [35]  [100/312]  eta: 0:02:09  lr: 0.003971  min_lr: 0.003971  loss: 4.3387 (4.1063)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.0612  max mem: 31830
Epoch: [35]  [110/312]  eta: 0:01:59  lr: 0.003970  min_lr: 0.003970  loss: 4.1301 (4.1057)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0385  max mem: 31830
Epoch: [35]  [120/312]  eta: 0:01:54  lr: 0.003970  min_lr: 0.003970  loss: 4.1060 (4.0919)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0294  max mem: 31830
Epoch: [35]  [130/312]  eta: 0:01:48  lr: 0.003970  min_lr: 0.003970  loss: 4.0683 (4.0972)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.0423  max mem: 31830
Epoch: [35]  [140/312]  eta: 0:01:40  lr: 0.003970  min_lr: 0.003970  loss: 4.1685 (4.0876)  weight_decay: 0.0500 (0.0500)  time: 0.4869  data: 0.0144  max mem: 31830
Epoch: [35]  [150/312]  eta: 0:01:34  lr: 0.003970  min_lr: 0.003970  loss: 4.3105 (4.0973)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0350  max mem: 31830
Epoch: [35]  [160/312]  eta: 0:01:29  lr: 0.003970  min_lr: 0.003970  loss: 4.2898 (4.0854)  weight_decay: 0.0500 (0.0500)  time: 0.6127  data: 0.0689  max mem: 31830
Epoch: [35]  [170/312]  eta: 0:01:21  lr: 0.003970  min_lr: 0.003970  loss: 3.7193 (4.0771)  weight_decay: 0.0500 (0.0500)  time: 0.4945  data: 0.0347  max mem: 31830
Epoch: [35]  [180/312]  eta: 0:01:16  lr: 0.003970  min_lr: 0.003970  loss: 4.3102 (4.0827)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0372  max mem: 31830
Epoch: [35]  [190/312]  eta: 0:01:09  lr: 0.003969  min_lr: 0.003969  loss: 4.0166 (4.0700)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.0372  max mem: 31830
Epoch: [35]  [200/312]  eta: 0:01:03  lr: 0.003969  min_lr: 0.003969  loss: 4.0166 (4.0670)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0229  max mem: 31830
Epoch: [35]  [210/312]  eta: 0:00:58  lr: 0.003969  min_lr: 0.003969  loss: 4.2318 (4.0785)  weight_decay: 0.0500 (0.0500)  time: 0.6243  data: 0.0446  max mem: 31830
Epoch: [35]  [220/312]  eta: 0:00:52  lr: 0.003969  min_lr: 0.003969  loss: 4.1672 (4.0754)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0227  max mem: 31830
Epoch: [35]  [230/312]  eta: 0:00:46  lr: 0.003969  min_lr: 0.003969  loss: 4.3014 (4.0900)  weight_decay: 0.0500 (0.0500)  time: 0.4868  data: 0.0301  max mem: 31830
Epoch: [35]  [240/312]  eta: 0:00:40  lr: 0.003969  min_lr: 0.003969  loss: 4.1284 (4.0859)  weight_decay: 0.0500 (0.0500)  time: 0.5804  data: 0.0757  max mem: 31830
Epoch: [35]  [250/312]  eta: 0:00:34  lr: 0.003969  min_lr: 0.003969  loss: 3.9902 (4.0819)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.0465  max mem: 31830
Epoch: [35]  [260/312]  eta: 0:00:29  lr: 0.003969  min_lr: 0.003969  loss: 4.0480 (4.0764)  weight_decay: 0.0500 (0.0500)  time: 0.5262  data: 0.0285  max mem: 31830
Epoch: [35]  [270/312]  eta: 0:00:23  lr: 0.003968  min_lr: 0.003968  loss: 3.9847 (4.0661)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0299  max mem: 31830
Epoch: [35]  [280/312]  eta: 0:00:17  lr: 0.003968  min_lr: 0.003968  loss: 4.1343 (4.0706)  weight_decay: 0.0500 (0.0500)  time: 0.5159  data: 0.0412  max mem: 31830
Epoch: [35]  [290/312]  eta: 0:00:12  lr: 0.003968  min_lr: 0.003968  loss: 4.2966 (4.0641)  weight_decay: 0.0500 (0.0500)  time: 0.5940  data: 0.0636  max mem: 31830
Epoch: [35]  [300/312]  eta: 0:00:06  lr: 0.003968  min_lr: 0.003968  loss: 4.2029 (4.0644)  weight_decay: 0.0500 (0.0500)  time: 0.4674  data: 0.0243  max mem: 31830
Epoch: [35]  [310/312]  eta: 0:00:01  lr: 0.003968  min_lr: 0.003968  loss: 4.3703 (4.0709)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [35]  [311/312]  eta: 0:00:00  lr: 0.003968  min_lr: 0.003968  loss: 4.3703 (4.0721)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [35] Total time: 0:02:52 (0.5522 s / it)
Averaged stats: lr: 0.003968  min_lr: 0.003968  loss: 4.3703 (4.0309)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.7371 (1.7371)  acc1: 66.6667 (66.6667)  acc5: 86.5885 (86.5885)  time: 8.6153  data: 8.4478  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1402 (1.9628)  acc1: 57.0312 (58.2880)  acc5: 80.9896 (81.5680)  time: 1.0735  data: 0.9387  max mem: 31830
Test: Total time: 0:00:09 (1.0990 s / it)
* Acc@1 57.770 Acc@5 81.814 loss 1.971
Accuracy of the model on the 50000 test images: 57.8%
Max accuracy: 61.59%
Epoch: [36]  [  0/312]  eta: 1:01:11  lr: 0.003968  min_lr: 0.003968  loss: 4.3159 (4.3159)  weight_decay: 0.0500 (0.0500)  time: 11.7666  data: 9.0574  max mem: 31830
Epoch: [36]  [ 10/312]  eta: 0:08:20  lr: 0.003968  min_lr: 0.003968  loss: 4.0440 (3.9257)  weight_decay: 0.0500 (0.0500)  time: 1.6581  data: 0.9201  max mem: 31830
Epoch: [36]  [ 20/312]  eta: 0:05:27  lr: 0.003968  min_lr: 0.003968  loss: 3.8115 (3.9160)  weight_decay: 0.0500 (0.0500)  time: 0.5908  data: 0.0641  max mem: 31830
Epoch: [36]  [ 30/312]  eta: 0:04:10  lr: 0.003967  min_lr: 0.003967  loss: 4.1098 (3.9260)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0112  max mem: 31830
Epoch: [36]  [ 40/312]  eta: 0:03:29  lr: 0.003967  min_lr: 0.003967  loss: 4.1098 (3.9574)  weight_decay: 0.0500 (0.0500)  time: 0.3986  data: 0.0007  max mem: 31830
Epoch: [36]  [ 50/312]  eta: 0:03:02  lr: 0.003967  min_lr: 0.003967  loss: 3.9067 (3.9168)  weight_decay: 0.0500 (0.0500)  time: 0.4017  data: 0.0016  max mem: 31830
Epoch: [36]  [ 60/312]  eta: 0:02:43  lr: 0.003967  min_lr: 0.003967  loss: 4.0736 (3.9644)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0025  max mem: 31830
Epoch: [36]  [ 70/312]  eta: 0:02:39  lr: 0.003967  min_lr: 0.003967  loss: 4.3425 (3.9923)  weight_decay: 0.0500 (0.0500)  time: 0.5657  data: 0.0308  max mem: 31830
Epoch: [36]  [ 80/312]  eta: 0:02:29  lr: 0.003967  min_lr: 0.003967  loss: 4.1942 (4.0040)  weight_decay: 0.0500 (0.0500)  time: 0.6333  data: 0.0299  max mem: 31830
Epoch: [36]  [ 90/312]  eta: 0:02:21  lr: 0.003967  min_lr: 0.003967  loss: 4.0772 (4.0104)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.0007  max mem: 31830
Epoch: [36]  [100/312]  eta: 0:02:13  lr: 0.003967  min_lr: 0.003967  loss: 4.0772 (4.0067)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0007  max mem: 31830
Epoch: [36]  [110/312]  eta: 0:02:02  lr: 0.003966  min_lr: 0.003966  loss: 4.2186 (4.0340)  weight_decay: 0.0500 (0.0500)  time: 0.4790  data: 0.0010  max mem: 31830
Epoch: [36]  [120/312]  eta: 0:01:57  lr: 0.003966  min_lr: 0.003966  loss: 4.3132 (4.0492)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.0153  max mem: 31830
Epoch: [36]  [130/312]  eta: 0:01:50  lr: 0.003966  min_lr: 0.003966  loss: 4.2259 (4.0467)  weight_decay: 0.0500 (0.0500)  time: 0.6119  data: 0.0153  max mem: 31830
Epoch: [36]  [140/312]  eta: 0:01:42  lr: 0.003966  min_lr: 0.003966  loss: 4.2259 (4.0551)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0011  max mem: 31830
Epoch: [36]  [150/312]  eta: 0:01:36  lr: 0.003966  min_lr: 0.003966  loss: 4.3137 (4.0580)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0016  max mem: 31830
Epoch: [36]  [160/312]  eta: 0:01:29  lr: 0.003966  min_lr: 0.003966  loss: 4.1238 (4.0513)  weight_decay: 0.0500 (0.0500)  time: 0.5522  data: 0.0016  max mem: 31830
Epoch: [36]  [170/312]  eta: 0:01:22  lr: 0.003966  min_lr: 0.003966  loss: 4.0179 (4.0446)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0009  max mem: 31830
Epoch: [36]  [180/312]  eta: 0:01:17  lr: 0.003966  min_lr: 0.003966  loss: 3.9628 (4.0393)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0011  max mem: 31830
Epoch: [36]  [190/312]  eta: 0:01:10  lr: 0.003965  min_lr: 0.003965  loss: 4.3230 (4.0580)  weight_decay: 0.0500 (0.0500)  time: 0.5166  data: 0.0009  max mem: 31830
Epoch: [36]  [200/312]  eta: 0:01:05  lr: 0.003965  min_lr: 0.003965  loss: 4.2538 (4.0618)  weight_decay: 0.0500 (0.0500)  time: 0.5565  data: 0.0057  max mem: 31830
Epoch: [36]  [210/312]  eta: 0:00:59  lr: 0.003965  min_lr: 0.003965  loss: 3.8755 (4.0570)  weight_decay: 0.0500 (0.0500)  time: 0.6008  data: 0.0056  max mem: 31830
Epoch: [36]  [220/312]  eta: 0:00:52  lr: 0.003965  min_lr: 0.003965  loss: 4.1755 (4.0612)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0203  max mem: 31830
Epoch: [36]  [230/312]  eta: 0:00:47  lr: 0.003965  min_lr: 0.003965  loss: 4.2783 (4.0706)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0205  max mem: 31830
Epoch: [36]  [240/312]  eta: 0:00:41  lr: 0.003965  min_lr: 0.003965  loss: 4.2783 (4.0698)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.0017  max mem: 31830
Epoch: [36]  [250/312]  eta: 0:00:35  lr: 0.003965  min_lr: 0.003965  loss: 4.2846 (4.0741)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0025  max mem: 31830
Epoch: [36]  [260/312]  eta: 0:00:29  lr: 0.003964  min_lr: 0.003964  loss: 4.3213 (4.0820)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0081  max mem: 31830
Epoch: [36]  [270/312]  eta: 0:00:23  lr: 0.003964  min_lr: 0.003964  loss: 4.3738 (4.0979)  weight_decay: 0.0500 (0.0500)  time: 0.5058  data: 0.0072  max mem: 31830
Epoch: [36]  [280/312]  eta: 0:00:18  lr: 0.003964  min_lr: 0.003964  loss: 4.3631 (4.1052)  weight_decay: 0.0500 (0.0500)  time: 0.5637  data: 0.0284  max mem: 31830
Epoch: [36]  [290/312]  eta: 0:00:12  lr: 0.003964  min_lr: 0.003964  loss: 4.1735 (4.0958)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0280  max mem: 31830
Epoch: [36]  [300/312]  eta: 0:00:06  lr: 0.003964  min_lr: 0.003964  loss: 3.9547 (4.0879)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0002  max mem: 31830
Epoch: [36]  [310/312]  eta: 0:00:01  lr: 0.003964  min_lr: 0.003964  loss: 4.1752 (4.0905)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0001  max mem: 31830
Epoch: [36]  [311/312]  eta: 0:00:00  lr: 0.003964  min_lr: 0.003964  loss: 3.9822 (4.0886)  weight_decay: 0.0500 (0.0500)  time: 0.3912  data: 0.0001  max mem: 31830
Epoch: [36] Total time: 0:02:53 (0.5568 s / it)
Averaged stats: lr: 0.003964  min_lr: 0.003964  loss: 3.9822 (4.0752)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.5088 (1.5088)  acc1: 69.9219 (69.9219)  acc5: 91.0156 (91.0156)  time: 8.5599  data: 8.3926  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9621 (1.8036)  acc1: 59.3750 (60.6080)  acc5: 82.6823 (84.3200)  time: 1.0680  data: 0.9326  max mem: 31830
Test: Total time: 0:00:09 (1.0795 s / it)
* Acc@1 61.322 Acc@5 84.750 loss 1.802
Accuracy of the model on the 50000 test images: 61.3%
Max accuracy: 61.59%
Epoch: [37]  [  0/312]  eta: 1:02:13  lr: 0.003964  min_lr: 0.003964  loss: 4.9654 (4.9654)  weight_decay: 0.0500 (0.0500)  time: 11.9656  data: 9.5398  max mem: 31830
Epoch: [37]  [ 10/312]  eta: 0:08:59  lr: 0.003964  min_lr: 0.003964  loss: 4.3365 (4.2569)  weight_decay: 0.0500 (0.0500)  time: 1.7856  data: 0.9639  max mem: 31830
Epoch: [37]  [ 20/312]  eta: 0:05:27  lr: 0.003963  min_lr: 0.003963  loss: 4.0412 (4.0514)  weight_decay: 0.0500 (0.0500)  time: 0.5788  data: 0.0535  max mem: 31830
Epoch: [37]  [ 30/312]  eta: 0:04:10  lr: 0.003963  min_lr: 0.003963  loss: 3.8147 (4.0234)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0007  max mem: 31830
Epoch: [37]  [ 40/312]  eta: 0:03:29  lr: 0.003963  min_lr: 0.003963  loss: 3.8109 (3.9326)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0015  max mem: 31830
Epoch: [37]  [ 50/312]  eta: 0:03:02  lr: 0.003963  min_lr: 0.003963  loss: 3.8614 (3.9234)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0015  max mem: 31830
Epoch: [37]  [ 60/312]  eta: 0:02:42  lr: 0.003963  min_lr: 0.003963  loss: 4.1275 (3.9608)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0006  max mem: 31830
Epoch: [37]  [ 70/312]  eta: 0:02:30  lr: 0.003963  min_lr: 0.003963  loss: 4.1738 (3.9661)  weight_decay: 0.0500 (0.0500)  time: 0.4286  data: 0.0006  max mem: 31830
Epoch: [37]  [ 80/312]  eta: 0:02:23  lr: 0.003963  min_lr: 0.003963  loss: 3.8746 (3.9451)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0061  max mem: 31830
Epoch: [37]  [ 90/312]  eta: 0:02:13  lr: 0.003963  min_lr: 0.003963  loss: 3.8931 (3.9546)  weight_decay: 0.0500 (0.0500)  time: 0.5417  data: 0.0061  max mem: 31830
Epoch: [37]  [100/312]  eta: 0:02:07  lr: 0.003962  min_lr: 0.003962  loss: 4.0917 (3.9658)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0011  max mem: 31830
Epoch: [37]  [110/312]  eta: 0:01:59  lr: 0.003962  min_lr: 0.003962  loss: 4.2317 (3.9650)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.0021  max mem: 31830
Epoch: [37]  [120/312]  eta: 0:01:53  lr: 0.003962  min_lr: 0.003962  loss: 4.3490 (4.0004)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0078  max mem: 31830
Epoch: [37]  [130/312]  eta: 0:01:46  lr: 0.003962  min_lr: 0.003962  loss: 3.9787 (3.9874)  weight_decay: 0.0500 (0.0500)  time: 0.5545  data: 0.0135  max mem: 31830
Epoch: [37]  [140/312]  eta: 0:01:40  lr: 0.003962  min_lr: 0.003962  loss: 3.7810 (3.9871)  weight_decay: 0.0500 (0.0500)  time: 0.5434  data: 0.0076  max mem: 31830
Epoch: [37]  [150/312]  eta: 0:01:34  lr: 0.003962  min_lr: 0.003962  loss: 4.1002 (3.9964)  weight_decay: 0.0500 (0.0500)  time: 0.5695  data: 0.0013  max mem: 31830
Epoch: [37]  [160/312]  eta: 0:01:28  lr: 0.003962  min_lr: 0.003962  loss: 4.1002 (3.9987)  weight_decay: 0.0500 (0.0500)  time: 0.5731  data: 0.0018  max mem: 31830
Epoch: [37]  [170/312]  eta: 0:01:21  lr: 0.003961  min_lr: 0.003961  loss: 4.2630 (4.0028)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0015  max mem: 31830
Epoch: [37]  [180/312]  eta: 0:01:16  lr: 0.003961  min_lr: 0.003961  loss: 3.8211 (3.9830)  weight_decay: 0.0500 (0.0500)  time: 0.5673  data: 0.0009  max mem: 31830
Epoch: [37]  [190/312]  eta: 0:01:09  lr: 0.003961  min_lr: 0.003961  loss: 3.8211 (3.9790)  weight_decay: 0.0500 (0.0500)  time: 0.5372  data: 0.0149  max mem: 31830
Epoch: [37]  [200/312]  eta: 0:01:03  lr: 0.003961  min_lr: 0.003961  loss: 4.0740 (3.9820)  weight_decay: 0.0500 (0.0500)  time: 0.4775  data: 0.0149  max mem: 31830
Epoch: [37]  [210/312]  eta: 0:00:58  lr: 0.003961  min_lr: 0.003961  loss: 4.0050 (3.9692)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.0144  max mem: 31830
Epoch: [37]  [220/312]  eta: 0:00:52  lr: 0.003961  min_lr: 0.003961  loss: 4.0302 (3.9773)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0144  max mem: 31830
Epoch: [37]  [230/312]  eta: 0:00:47  lr: 0.003961  min_lr: 0.003961  loss: 4.1673 (3.9766)  weight_decay: 0.0500 (0.0500)  time: 0.5777  data: 0.0009  max mem: 31830
Epoch: [37]  [240/312]  eta: 0:00:41  lr: 0.003960  min_lr: 0.003960  loss: 4.1249 (3.9834)  weight_decay: 0.0500 (0.0500)  time: 0.6025  data: 0.0008  max mem: 31830
Epoch: [37]  [250/312]  eta: 0:00:35  lr: 0.003960  min_lr: 0.003960  loss: 4.0578 (3.9787)  weight_decay: 0.0500 (0.0500)  time: 0.4700  data: 0.0008  max mem: 31830
Epoch: [37]  [260/312]  eta: 0:00:29  lr: 0.003960  min_lr: 0.003960  loss: 4.0335 (3.9848)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0013  max mem: 31830
Epoch: [37]  [270/312]  eta: 0:00:23  lr: 0.003960  min_lr: 0.003960  loss: 4.3282 (3.9970)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0012  max mem: 31830
Epoch: [37]  [280/312]  eta: 0:00:18  lr: 0.003960  min_lr: 0.003960  loss: 4.4335 (3.9982)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0045  max mem: 31830
Epoch: [37]  [290/312]  eta: 0:00:12  lr: 0.003960  min_lr: 0.003960  loss: 4.0090 (3.9944)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.0042  max mem: 31830
Epoch: [37]  [300/312]  eta: 0:00:06  lr: 0.003960  min_lr: 0.003960  loss: 4.0727 (3.9974)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0002  max mem: 31830
Epoch: [37]  [310/312]  eta: 0:00:01  lr: 0.003959  min_lr: 0.003959  loss: 4.2845 (4.0075)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0001  max mem: 31830
Epoch: [37]  [311/312]  eta: 0:00:00  lr: 0.003959  min_lr: 0.003959  loss: 4.2028 (4.0045)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0001  max mem: 31830
Epoch: [37] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.003959  min_lr: 0.003959  loss: 4.2028 (4.0430)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.9370 (1.9370)  acc1: 67.1875 (67.1875)  acc5: 89.1927 (89.1927)  time: 8.9043  data: 8.7432  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.2393 (2.1091)  acc1: 59.3750 (60.8320)  acc5: 83.3333 (84.1120)  time: 1.1095  data: 0.9715  max mem: 31830
Test: Total time: 0:00:10 (1.1327 s / it)
* Acc@1 60.746 Acc@5 83.818 loss 2.109
Accuracy of the model on the 50000 test images: 60.7%
Max accuracy: 61.59%
Epoch: [38]  [  0/312]  eta: 1:01:48  lr: 0.003959  min_lr: 0.003959  loss: 3.0783 (3.0783)  weight_decay: 0.0500 (0.0500)  time: 11.8865  data: 8.8745  max mem: 31830
Epoch: [38]  [ 10/312]  eta: 0:08:25  lr: 0.003959  min_lr: 0.003959  loss: 3.9299 (3.7799)  weight_decay: 0.0500 (0.0500)  time: 1.6730  data: 0.9543  max mem: 31830
Epoch: [38]  [ 20/312]  eta: 0:05:17  lr: 0.003959  min_lr: 0.003959  loss: 3.9895 (3.9103)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0815  max mem: 31830
Epoch: [38]  [ 30/312]  eta: 0:04:03  lr: 0.003959  min_lr: 0.003959  loss: 4.0567 (3.8875)  weight_decay: 0.0500 (0.0500)  time: 0.4195  data: 0.0010  max mem: 31830
Epoch: [38]  [ 40/312]  eta: 0:03:24  lr: 0.003959  min_lr: 0.003959  loss: 4.2621 (3.9343)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [38]  [ 50/312]  eta: 0:03:04  lr: 0.003959  min_lr: 0.003959  loss: 4.2621 (3.9897)  weight_decay: 0.0500 (0.0500)  time: 0.4576  data: 0.0006  max mem: 31830
Epoch: [38]  [ 60/312]  eta: 0:02:44  lr: 0.003958  min_lr: 0.003958  loss: 4.1838 (3.9857)  weight_decay: 0.0500 (0.0500)  time: 0.4553  data: 0.0008  max mem: 31830
Epoch: [38]  [ 70/312]  eta: 0:02:36  lr: 0.003958  min_lr: 0.003958  loss: 4.1726 (4.0113)  weight_decay: 0.0500 (0.0500)  time: 0.4916  data: 0.0246  max mem: 31830
Epoch: [38]  [ 80/312]  eta: 0:02:27  lr: 0.003958  min_lr: 0.003958  loss: 3.9052 (3.9852)  weight_decay: 0.0500 (0.0500)  time: 0.5764  data: 0.0528  max mem: 31830
Epoch: [38]  [ 90/312]  eta: 0:02:16  lr: 0.003958  min_lr: 0.003958  loss: 3.9303 (3.9978)  weight_decay: 0.0500 (0.0500)  time: 0.5094  data: 0.0542  max mem: 31830
Epoch: [38]  [100/312]  eta: 0:02:09  lr: 0.003958  min_lr: 0.003958  loss: 4.1787 (3.9889)  weight_decay: 0.0500 (0.0500)  time: 0.5157  data: 0.0778  max mem: 31830
Epoch: [38]  [110/312]  eta: 0:01:59  lr: 0.003958  min_lr: 0.003958  loss: 4.1787 (3.9996)  weight_decay: 0.0500 (0.0500)  time: 0.4851  data: 0.0526  max mem: 31830
Epoch: [38]  [120/312]  eta: 0:01:54  lr: 0.003958  min_lr: 0.003958  loss: 4.1508 (4.0046)  weight_decay: 0.0500 (0.0500)  time: 0.5155  data: 0.0581  max mem: 31830
Epoch: [38]  [130/312]  eta: 0:01:49  lr: 0.003957  min_lr: 0.003957  loss: 3.8501 (3.9855)  weight_decay: 0.0500 (0.0500)  time: 0.6398  data: 0.1224  max mem: 31830
Epoch: [38]  [140/312]  eta: 0:01:40  lr: 0.003957  min_lr: 0.003957  loss: 3.8501 (3.9871)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0650  max mem: 31830
Epoch: [38]  [150/312]  eta: 0:01:35  lr: 0.003957  min_lr: 0.003957  loss: 4.3108 (4.0005)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0374  max mem: 31830
Epoch: [38]  [160/312]  eta: 0:01:29  lr: 0.003957  min_lr: 0.003957  loss: 4.2578 (4.0016)  weight_decay: 0.0500 (0.0500)  time: 0.6051  data: 0.0380  max mem: 31830
Epoch: [38]  [170/312]  eta: 0:01:22  lr: 0.003957  min_lr: 0.003957  loss: 3.7991 (4.0008)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0393  max mem: 31830
Epoch: [38]  [180/312]  eta: 0:01:16  lr: 0.003957  min_lr: 0.003957  loss: 4.1487 (4.0014)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0625  max mem: 31830
Epoch: [38]  [190/312]  eta: 0:01:09  lr: 0.003957  min_lr: 0.003957  loss: 4.1487 (4.0075)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0246  max mem: 31830
Epoch: [38]  [200/312]  eta: 0:01:04  lr: 0.003956  min_lr: 0.003956  loss: 4.0802 (4.0131)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0530  max mem: 31830
Epoch: [38]  [210/312]  eta: 0:00:58  lr: 0.003956  min_lr: 0.003956  loss: 4.2276 (4.0169)  weight_decay: 0.0500 (0.0500)  time: 0.6128  data: 0.0642  max mem: 31830
Epoch: [38]  [220/312]  eta: 0:00:52  lr: 0.003956  min_lr: 0.003956  loss: 4.2713 (4.0297)  weight_decay: 0.0500 (0.0500)  time: 0.4902  data: 0.0119  max mem: 31830
Epoch: [38]  [230/312]  eta: 0:00:46  lr: 0.003956  min_lr: 0.003956  loss: 4.0854 (4.0230)  weight_decay: 0.0500 (0.0500)  time: 0.4919  data: 0.0180  max mem: 31830
Epoch: [38]  [240/312]  eta: 0:00:40  lr: 0.003956  min_lr: 0.003956  loss: 3.8774 (4.0085)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0180  max mem: 31830
Epoch: [38]  [250/312]  eta: 0:00:35  lr: 0.003956  min_lr: 0.003956  loss: 3.6640 (4.0008)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0283  max mem: 31830
Epoch: [38]  [260/312]  eta: 0:00:29  lr: 0.003956  min_lr: 0.003956  loss: 3.8842 (4.0041)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0285  max mem: 31830
Epoch: [38]  [270/312]  eta: 0:00:23  lr: 0.003955  min_lr: 0.003955  loss: 3.9712 (3.9982)  weight_decay: 0.0500 (0.0500)  time: 0.4873  data: 0.0010  max mem: 31830
Epoch: [38]  [280/312]  eta: 0:00:18  lr: 0.003955  min_lr: 0.003955  loss: 3.8801 (3.9883)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0070  max mem: 31830
Epoch: [38]  [290/312]  eta: 0:00:12  lr: 0.003955  min_lr: 0.003955  loss: 3.8474 (3.9870)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0068  max mem: 31830
Epoch: [38]  [300/312]  eta: 0:00:06  lr: 0.003955  min_lr: 0.003955  loss: 3.8793 (3.9848)  weight_decay: 0.0500 (0.0500)  time: 0.4760  data: 0.0002  max mem: 31830
Epoch: [38]  [310/312]  eta: 0:00:01  lr: 0.003955  min_lr: 0.003955  loss: 4.1156 (3.9882)  weight_decay: 0.0500 (0.0500)  time: 0.3846  data: 0.0001  max mem: 31830
Epoch: [38]  [311/312]  eta: 0:00:00  lr: 0.003955  min_lr: 0.003955  loss: 4.1156 (3.9882)  weight_decay: 0.0500 (0.0500)  time: 0.3844  data: 0.0001  max mem: 31830
Epoch: [38] Total time: 0:02:53 (0.5552 s / it)
Averaged stats: lr: 0.003955  min_lr: 0.003955  loss: 4.1156 (4.0216)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.4419 (1.4419)  acc1: 68.7500 (68.7500)  acc5: 89.0625 (89.0625)  time: 8.6307  data: 8.4630  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8594 (1.7356)  acc1: 59.8958 (61.1840)  acc5: 83.7240 (84.7040)  time: 1.0762  data: 0.9404  max mem: 31830
Test: Total time: 0:00:10 (1.1116 s / it)
* Acc@1 61.936 Acc@5 84.942 loss 1.740
Accuracy of the model on the 50000 test images: 61.9%
Max accuracy: 61.94%
Epoch: [39]  [  0/312]  eta: 1:01:25  lr: 0.003955  min_lr: 0.003955  loss: 4.1719 (4.1719)  weight_decay: 0.0500 (0.0500)  time: 11.8116  data: 10.1607  max mem: 31830
Epoch: [39]  [ 10/312]  eta: 0:08:43  lr: 0.003955  min_lr: 0.003955  loss: 3.7081 (3.8404)  weight_decay: 0.0500 (0.0500)  time: 1.7321  data: 0.9544  max mem: 31830
Epoch: [39]  [ 20/312]  eta: 0:05:28  lr: 0.003954  min_lr: 0.003954  loss: 3.7081 (3.7841)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0418  max mem: 31830
Epoch: [39]  [ 30/312]  eta: 0:04:10  lr: 0.003954  min_lr: 0.003954  loss: 3.7790 (3.7925)  weight_decay: 0.0500 (0.0500)  time: 0.4254  data: 0.0253  max mem: 31830
Epoch: [39]  [ 40/312]  eta: 0:03:29  lr: 0.003954  min_lr: 0.003954  loss: 3.7907 (3.7921)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0009  max mem: 31830
Epoch: [39]  [ 50/312]  eta: 0:03:02  lr: 0.003954  min_lr: 0.003954  loss: 3.9699 (3.8279)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0010  max mem: 31830
Epoch: [39]  [ 60/312]  eta: 0:02:43  lr: 0.003954  min_lr: 0.003954  loss: 3.9327 (3.8396)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [39]  [ 70/312]  eta: 0:02:30  lr: 0.003954  min_lr: 0.003954  loss: 3.9844 (3.8669)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0374  max mem: 31830
Epoch: [39]  [ 80/312]  eta: 0:02:24  lr: 0.003954  min_lr: 0.003954  loss: 4.2003 (3.8807)  weight_decay: 0.0500 (0.0500)  time: 0.5530  data: 0.1313  max mem: 31830
Epoch: [39]  [ 90/312]  eta: 0:02:12  lr: 0.003953  min_lr: 0.003953  loss: 4.0609 (3.9088)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0945  max mem: 31830
Epoch: [39]  [100/312]  eta: 0:02:06  lr: 0.003953  min_lr: 0.003953  loss: 4.1525 (3.9306)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0760  max mem: 31830
Epoch: [39]  [110/312]  eta: 0:01:57  lr: 0.003953  min_lr: 0.003953  loss: 4.0202 (3.9090)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0760  max mem: 31830
Epoch: [39]  [120/312]  eta: 0:01:52  lr: 0.003953  min_lr: 0.003953  loss: 4.0202 (3.9356)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0563  max mem: 31830
Epoch: [39]  [130/312]  eta: 0:01:49  lr: 0.003953  min_lr: 0.003953  loss: 4.1595 (3.9472)  weight_decay: 0.0500 (0.0500)  time: 0.6949  data: 0.1275  max mem: 31830
Epoch: [39]  [140/312]  eta: 0:01:40  lr: 0.003953  min_lr: 0.003953  loss: 4.0986 (3.9517)  weight_decay: 0.0500 (0.0500)  time: 0.5799  data: 0.0720  max mem: 31830
Epoch: [39]  [150/312]  eta: 0:01:33  lr: 0.003952  min_lr: 0.003952  loss: 4.0667 (3.9576)  weight_decay: 0.0500 (0.0500)  time: 0.4517  data: 0.0247  max mem: 31830
Epoch: [39]  [160/312]  eta: 0:01:28  lr: 0.003952  min_lr: 0.003952  loss: 4.2151 (3.9706)  weight_decay: 0.0500 (0.0500)  time: 0.5564  data: 0.0610  max mem: 31830
Epoch: [39]  [170/312]  eta: 0:01:21  lr: 0.003952  min_lr: 0.003952  loss: 4.1869 (3.9642)  weight_decay: 0.0500 (0.0500)  time: 0.5362  data: 0.0576  max mem: 31830
Epoch: [39]  [180/312]  eta: 0:01:15  lr: 0.003952  min_lr: 0.003952  loss: 4.1869 (3.9720)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0697  max mem: 31830
Epoch: [39]  [190/312]  eta: 0:01:09  lr: 0.003952  min_lr: 0.003952  loss: 4.1195 (3.9660)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0492  max mem: 31830
Epoch: [39]  [200/312]  eta: 0:01:03  lr: 0.003952  min_lr: 0.003952  loss: 3.8156 (3.9482)  weight_decay: 0.0500 (0.0500)  time: 0.5264  data: 0.0375  max mem: 31830
Epoch: [39]  [210/312]  eta: 0:00:58  lr: 0.003951  min_lr: 0.003951  loss: 3.6526 (3.9436)  weight_decay: 0.0500 (0.0500)  time: 0.5934  data: 0.0674  max mem: 31830
Epoch: [39]  [220/312]  eta: 0:00:52  lr: 0.003951  min_lr: 0.003951  loss: 4.1544 (3.9467)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.0306  max mem: 31830
Epoch: [39]  [230/312]  eta: 0:00:46  lr: 0.003951  min_lr: 0.003951  loss: 4.0763 (3.9367)  weight_decay: 0.0500 (0.0500)  time: 0.5611  data: 0.0132  max mem: 31830
Epoch: [39]  [240/312]  eta: 0:00:41  lr: 0.003951  min_lr: 0.003951  loss: 4.0142 (3.9439)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0134  max mem: 31830
Epoch: [39]  [250/312]  eta: 0:00:35  lr: 0.003951  min_lr: 0.003951  loss: 4.0142 (3.9357)  weight_decay: 0.0500 (0.0500)  time: 0.6193  data: 0.0009  max mem: 31830
Epoch: [39]  [260/312]  eta: 0:00:29  lr: 0.003951  min_lr: 0.003951  loss: 3.9635 (3.9403)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0008  max mem: 31830
Epoch: [39]  [270/312]  eta: 0:00:23  lr: 0.003951  min_lr: 0.003951  loss: 3.8663 (3.9303)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0009  max mem: 31830
Epoch: [39]  [280/312]  eta: 0:00:18  lr: 0.003950  min_lr: 0.003950  loss: 3.9300 (3.9335)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0022  max mem: 31830
Epoch: [39]  [290/312]  eta: 0:00:12  lr: 0.003950  min_lr: 0.003950  loss: 4.0599 (3.9296)  weight_decay: 0.0500 (0.0500)  time: 0.5476  data: 0.0019  max mem: 31830
Epoch: [39]  [300/312]  eta: 0:00:06  lr: 0.003950  min_lr: 0.003950  loss: 3.9921 (3.9355)  weight_decay: 0.0500 (0.0500)  time: 0.5207  data: 0.0003  max mem: 31830
Epoch: [39]  [310/312]  eta: 0:00:01  lr: 0.003950  min_lr: 0.003950  loss: 3.9839 (3.9352)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0002  max mem: 31830
Epoch: [39]  [311/312]  eta: 0:00:00  lr: 0.003950  min_lr: 0.003950  loss: 3.9921 (3.9360)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0001  max mem: 31830
Epoch: [39] Total time: 0:02:54 (0.5602 s / it)
Averaged stats: lr: 0.003950  min_lr: 0.003950  loss: 3.9921 (4.0033)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.7094 (1.7094)  acc1: 67.5781 (67.5781)  acc5: 88.5417 (88.5417)  time: 9.0214  data: 8.8608  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0181 (1.9010)  acc1: 60.0260 (60.5920)  acc5: 83.2031 (84.2400)  time: 1.1235  data: 0.9846  max mem: 31830
Test: Total time: 0:00:10 (1.1498 s / it)
* Acc@1 60.614 Acc@5 84.014 loss 1.913
Accuracy of the model on the 50000 test images: 60.6%
Max accuracy: 61.94%
Epoch: [40]  [  0/312]  eta: 1:01:30  lr: 0.003950  min_lr: 0.003950  loss: 3.5959 (3.5959)  weight_decay: 0.0500 (0.0500)  time: 11.8300  data: 11.4399  max mem: 31830
Epoch: [40]  [ 10/312]  eta: 0:09:10  lr: 0.003950  min_lr: 0.003950  loss: 3.9014 (3.7949)  weight_decay: 0.0500 (0.0500)  time: 1.8244  data: 1.0405  max mem: 31830
Epoch: [40]  [ 20/312]  eta: 0:05:33  lr: 0.003950  min_lr: 0.003950  loss: 4.0325 (3.9439)  weight_decay: 0.0500 (0.0500)  time: 0.6072  data: 0.0006  max mem: 31830
Epoch: [40]  [ 30/312]  eta: 0:04:14  lr: 0.003949  min_lr: 0.003949  loss: 4.2207 (3.9992)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0007  max mem: 31830
Epoch: [40]  [ 40/312]  eta: 0:03:32  lr: 0.003949  min_lr: 0.003949  loss: 4.2317 (4.0563)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [40]  [ 50/312]  eta: 0:03:04  lr: 0.003949  min_lr: 0.003949  loss: 4.2317 (4.0685)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0010  max mem: 31830
Epoch: [40]  [ 60/312]  eta: 0:02:45  lr: 0.003949  min_lr: 0.003949  loss: 4.0334 (4.0389)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [40]  [ 70/312]  eta: 0:02:29  lr: 0.003949  min_lr: 0.003949  loss: 3.9540 (4.0396)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0007  max mem: 31830
Epoch: [40]  [ 80/312]  eta: 0:02:21  lr: 0.003949  min_lr: 0.003949  loss: 4.2121 (4.0242)  weight_decay: 0.0500 (0.0500)  time: 0.4681  data: 0.0196  max mem: 31830
Epoch: [40]  [ 90/312]  eta: 0:02:13  lr: 0.003948  min_lr: 0.003948  loss: 3.9041 (4.0092)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0306  max mem: 31830
Epoch: [40]  [100/312]  eta: 0:02:07  lr: 0.003948  min_lr: 0.003948  loss: 4.1506 (4.0301)  weight_decay: 0.0500 (0.0500)  time: 0.5642  data: 0.0663  max mem: 31830
Epoch: [40]  [110/312]  eta: 0:01:59  lr: 0.003948  min_lr: 0.003948  loss: 4.3011 (4.0483)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0694  max mem: 31830
Epoch: [40]  [120/312]  eta: 0:01:52  lr: 0.003948  min_lr: 0.003948  loss: 3.9917 (4.0355)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0329  max mem: 31830
Epoch: [40]  [130/312]  eta: 0:01:47  lr: 0.003948  min_lr: 0.003948  loss: 3.8307 (4.0205)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0433  max mem: 31830
Epoch: [40]  [140/312]  eta: 0:01:40  lr: 0.003948  min_lr: 0.003948  loss: 4.2891 (4.0247)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0432  max mem: 31830
Epoch: [40]  [150/312]  eta: 0:01:34  lr: 0.003947  min_lr: 0.003947  loss: 4.2891 (4.0278)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0296  max mem: 31830
Epoch: [40]  [160/312]  eta: 0:01:27  lr: 0.003947  min_lr: 0.003947  loss: 4.1549 (4.0225)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.0245  max mem: 31830
Epoch: [40]  [170/312]  eta: 0:01:22  lr: 0.003947  min_lr: 0.003947  loss: 4.0714 (4.0224)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0200  max mem: 31830
Epoch: [40]  [180/312]  eta: 0:01:17  lr: 0.003947  min_lr: 0.003947  loss: 4.0917 (4.0261)  weight_decay: 0.0500 (0.0500)  time: 0.6811  data: 0.0077  max mem: 31830
Epoch: [40]  [190/312]  eta: 0:01:10  lr: 0.003947  min_lr: 0.003947  loss: 4.1395 (4.0327)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0014  max mem: 31830
Epoch: [40]  [200/312]  eta: 0:01:05  lr: 0.003947  min_lr: 0.003947  loss: 4.2084 (4.0415)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0012  max mem: 31830
Epoch: [40]  [210/312]  eta: 0:01:00  lr: 0.003946  min_lr: 0.003946  loss: 4.2356 (4.0420)  weight_decay: 0.0500 (0.0500)  time: 0.7045  data: 0.0251  max mem: 31830
Epoch: [40]  [220/312]  eta: 0:00:53  lr: 0.003946  min_lr: 0.003946  loss: 4.2374 (4.0445)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0247  max mem: 31830
Epoch: [40]  [230/312]  eta: 0:00:48  lr: 0.003946  min_lr: 0.003946  loss: 4.1757 (4.0373)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0007  max mem: 31830
Epoch: [40]  [240/312]  eta: 0:00:41  lr: 0.003946  min_lr: 0.003946  loss: 4.1757 (4.0458)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0011  max mem: 31830
Epoch: [40]  [250/312]  eta: 0:00:36  lr: 0.003946  min_lr: 0.003946  loss: 4.2900 (4.0480)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0012  max mem: 31830
Epoch: [40]  [260/312]  eta: 0:00:30  lr: 0.003946  min_lr: 0.003946  loss: 4.2462 (4.0469)  weight_decay: 0.0500 (0.0500)  time: 0.6171  data: 0.0010  max mem: 31830
Epoch: [40]  [270/312]  eta: 0:00:24  lr: 0.003945  min_lr: 0.003945  loss: 3.6650 (4.0327)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.0008  max mem: 31830
Epoch: [40]  [280/312]  eta: 0:00:18  lr: 0.003945  min_lr: 0.003945  loss: 3.7694 (4.0335)  weight_decay: 0.0500 (0.0500)  time: 0.4982  data: 0.0040  max mem: 31830
Epoch: [40]  [290/312]  eta: 0:00:12  lr: 0.003945  min_lr: 0.003945  loss: 4.2382 (4.0449)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0038  max mem: 31830
Epoch: [40]  [300/312]  eta: 0:00:06  lr: 0.003945  min_lr: 0.003945  loss: 4.2148 (4.0364)  weight_decay: 0.0500 (0.0500)  time: 0.4259  data: 0.0002  max mem: 31830
Epoch: [40]  [310/312]  eta: 0:00:01  lr: 0.003945  min_lr: 0.003945  loss: 3.7186 (4.0311)  weight_decay: 0.0500 (0.0500)  time: 0.3804  data: 0.0001  max mem: 31830
Epoch: [40]  [311/312]  eta: 0:00:00  lr: 0.003945  min_lr: 0.003945  loss: 3.7186 (4.0307)  weight_decay: 0.0500 (0.0500)  time: 0.3804  data: 0.0001  max mem: 31830
Epoch: [40] Total time: 0:02:55 (0.5636 s / it)
Averaged stats: lr: 0.003945  min_lr: 0.003945  loss: 3.7186 (4.0143)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.8036 (1.8036)  acc1: 72.0052 (72.0052)  acc5: 89.3229 (89.3229)  time: 8.3589  data: 8.1920  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9548 (1.9102)  acc1: 63.5417 (62.6560)  acc5: 84.1146 (84.8960)  time: 1.0506  data: 0.9103  max mem: 31830
Test: Total time: 0:00:09 (1.0624 s / it)
* Acc@1 62.376 Acc@5 84.902 loss 1.931
Accuracy of the model on the 50000 test images: 62.4%
Max accuracy: 62.38%
Epoch: [41]  [  0/312]  eta: 0:58:52  lr: 0.003945  min_lr: 0.003945  loss: 3.2269 (3.2269)  weight_decay: 0.0500 (0.0500)  time: 11.3226  data: 10.9265  max mem: 31830
Epoch: [41]  [ 10/312]  eta: 0:08:08  lr: 0.003945  min_lr: 0.003945  loss: 3.4328 (3.7609)  weight_decay: 0.0500 (0.0500)  time: 1.6161  data: 0.9949  max mem: 31830
Epoch: [41]  [ 20/312]  eta: 0:05:17  lr: 0.003944  min_lr: 0.003944  loss: 4.1210 (3.9531)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0615  max mem: 31830
Epoch: [41]  [ 30/312]  eta: 0:04:03  lr: 0.003944  min_lr: 0.003944  loss: 4.2487 (3.9637)  weight_decay: 0.0500 (0.0500)  time: 0.4512  data: 0.0610  max mem: 31830
Epoch: [41]  [ 40/312]  eta: 0:03:24  lr: 0.003944  min_lr: 0.003944  loss: 4.2064 (4.0323)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0008  max mem: 31830
Epoch: [41]  [ 50/312]  eta: 0:02:59  lr: 0.003944  min_lr: 0.003944  loss: 3.9990 (3.9850)  weight_decay: 0.0500 (0.0500)  time: 0.4049  data: 0.0073  max mem: 31830
Epoch: [41]  [ 60/312]  eta: 0:02:41  lr: 0.003944  min_lr: 0.003944  loss: 3.9751 (4.0302)  weight_decay: 0.0500 (0.0500)  time: 0.4134  data: 0.0074  max mem: 31830
Epoch: [41]  [ 70/312]  eta: 0:02:32  lr: 0.003944  min_lr: 0.003944  loss: 3.8307 (3.9740)  weight_decay: 0.0500 (0.0500)  time: 0.4950  data: 0.0686  max mem: 31830
Epoch: [41]  [ 80/312]  eta: 0:02:25  lr: 0.003943  min_lr: 0.003943  loss: 3.8269 (3.9996)  weight_decay: 0.0500 (0.0500)  time: 0.5874  data: 0.1690  max mem: 31830
Epoch: [41]  [ 90/312]  eta: 0:02:13  lr: 0.003943  min_lr: 0.003943  loss: 4.2086 (3.9999)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.1014  max mem: 31830
Epoch: [41]  [100/312]  eta: 0:02:07  lr: 0.003943  min_lr: 0.003943  loss: 4.2438 (4.0037)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0779  max mem: 31830
Epoch: [41]  [110/312]  eta: 0:01:57  lr: 0.003943  min_lr: 0.003943  loss: 4.3121 (4.0178)  weight_decay: 0.0500 (0.0500)  time: 0.4985  data: 0.0779  max mem: 31830
Epoch: [41]  [120/312]  eta: 0:01:52  lr: 0.003943  min_lr: 0.003943  loss: 4.3252 (4.0293)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0789  max mem: 31830
Epoch: [41]  [130/312]  eta: 0:01:47  lr: 0.003943  min_lr: 0.003943  loss: 4.2886 (4.0471)  weight_decay: 0.0500 (0.0500)  time: 0.6239  data: 0.1750  max mem: 31830
Epoch: [41]  [140/312]  eta: 0:01:39  lr: 0.003942  min_lr: 0.003942  loss: 3.9889 (4.0253)  weight_decay: 0.0500 (0.0500)  time: 0.5179  data: 0.0969  max mem: 31830
Epoch: [41]  [150/312]  eta: 0:01:33  lr: 0.003942  min_lr: 0.003942  loss: 3.9421 (4.0297)  weight_decay: 0.0500 (0.0500)  time: 0.4867  data: 0.0909  max mem: 31830
Epoch: [41]  [160/312]  eta: 0:01:28  lr: 0.003942  min_lr: 0.003942  loss: 4.1634 (4.0226)  weight_decay: 0.0500 (0.0500)  time: 0.6096  data: 0.1712  max mem: 31830
Epoch: [41]  [170/312]  eta: 0:01:20  lr: 0.003942  min_lr: 0.003942  loss: 4.0517 (4.0292)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0810  max mem: 31830
Epoch: [41]  [180/312]  eta: 0:01:15  lr: 0.003942  min_lr: 0.003942  loss: 4.0982 (4.0284)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0646  max mem: 31830
Epoch: [41]  [190/312]  eta: 0:01:08  lr: 0.003942  min_lr: 0.003942  loss: 4.0916 (4.0152)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0646  max mem: 31830
Epoch: [41]  [200/312]  eta: 0:01:03  lr: 0.003941  min_lr: 0.003941  loss: 3.8813 (4.0077)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0939  max mem: 31830
Epoch: [41]  [210/312]  eta: 0:00:58  lr: 0.003941  min_lr: 0.003941  loss: 3.8966 (3.9934)  weight_decay: 0.0500 (0.0500)  time: 0.6375  data: 0.1732  max mem: 31830
Epoch: [41]  [220/312]  eta: 0:00:51  lr: 0.003941  min_lr: 0.003941  loss: 4.2592 (4.0048)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0804  max mem: 31830
Epoch: [41]  [230/312]  eta: 0:00:46  lr: 0.003941  min_lr: 0.003941  loss: 4.4362 (4.0237)  weight_decay: 0.0500 (0.0500)  time: 0.4776  data: 0.0654  max mem: 31830
Epoch: [41]  [240/312]  eta: 0:00:40  lr: 0.003941  min_lr: 0.003941  loss: 4.2522 (4.0233)  weight_decay: 0.0500 (0.0500)  time: 0.5954  data: 0.1401  max mem: 31830
Epoch: [41]  [250/312]  eta: 0:00:34  lr: 0.003940  min_lr: 0.003940  loss: 4.1832 (4.0252)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.0757  max mem: 31830
Epoch: [41]  [260/312]  eta: 0:00:29  lr: 0.003940  min_lr: 0.003940  loss: 4.2318 (4.0318)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.0834  max mem: 31830
Epoch: [41]  [270/312]  eta: 0:00:23  lr: 0.003940  min_lr: 0.003940  loss: 4.1788 (4.0289)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0834  max mem: 31830
Epoch: [41]  [280/312]  eta: 0:00:17  lr: 0.003940  min_lr: 0.003940  loss: 3.7416 (4.0172)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0745  max mem: 31830
Epoch: [41]  [290/312]  eta: 0:00:12  lr: 0.003940  min_lr: 0.003940  loss: 3.8526 (4.0120)  weight_decay: 0.0500 (0.0500)  time: 0.5996  data: 0.1292  max mem: 31830
Epoch: [41]  [300/312]  eta: 0:00:06  lr: 0.003940  min_lr: 0.003940  loss: 4.2044 (4.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4714  data: 0.0551  max mem: 31830
Epoch: [41]  [310/312]  eta: 0:00:01  lr: 0.003939  min_lr: 0.003939  loss: 4.3301 (4.0239)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [41]  [311/312]  eta: 0:00:00  lr: 0.003939  min_lr: 0.003939  loss: 4.3301 (4.0259)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [41] Total time: 0:02:51 (0.5492 s / it)
Averaged stats: lr: 0.003939  min_lr: 0.003939  loss: 4.3301 (3.9818)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.7206 (1.7206)  acc1: 66.6667 (66.6667)  acc5: 87.5000 (87.5000)  time: 8.3289  data: 8.1704  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0881 (2.0073)  acc1: 57.5521 (59.6480)  acc5: 82.4219 (83.4560)  time: 1.0419  data: 0.9079  max mem: 31830
Test: Total time: 0:00:09 (1.0512 s / it)
* Acc@1 59.710 Acc@5 83.170 loss 2.006
Accuracy of the model on the 50000 test images: 59.7%
Max accuracy: 62.38%
Epoch: [42]  [  0/312]  eta: 1:02:43  lr: 0.003939  min_lr: 0.003939  loss: 4.7850 (4.7850)  weight_decay: 0.0500 (0.0500)  time: 12.0625  data: 8.3178  max mem: 31830
Epoch: [42]  [ 10/312]  eta: 0:08:18  lr: 0.003939  min_lr: 0.003939  loss: 3.9676 (3.8722)  weight_decay: 0.0500 (0.0500)  time: 1.6495  data: 0.9569  max mem: 31830
Epoch: [42]  [ 20/312]  eta: 0:05:25  lr: 0.003939  min_lr: 0.003939  loss: 3.9676 (3.9448)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.1108  max mem: 31830
Epoch: [42]  [ 30/312]  eta: 0:04:09  lr: 0.003939  min_lr: 0.003939  loss: 4.0530 (3.9238)  weight_decay: 0.0500 (0.0500)  time: 0.4625  data: 0.0009  max mem: 31830
Epoch: [42]  [ 40/312]  eta: 0:03:27  lr: 0.003939  min_lr: 0.003939  loss: 4.1204 (3.9527)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0010  max mem: 31830
Epoch: [42]  [ 50/312]  eta: 0:03:05  lr: 0.003939  min_lr: 0.003939  loss: 4.2989 (4.0370)  weight_decay: 0.0500 (0.0500)  time: 0.4317  data: 0.0017  max mem: 31830
Epoch: [42]  [ 60/312]  eta: 0:02:45  lr: 0.003938  min_lr: 0.003938  loss: 4.0916 (3.9847)  weight_decay: 0.0500 (0.0500)  time: 0.4306  data: 0.0017  max mem: 31830
Epoch: [42]  [ 70/312]  eta: 0:02:38  lr: 0.003938  min_lr: 0.003938  loss: 3.7454 (3.9713)  weight_decay: 0.0500 (0.0500)  time: 0.5228  data: 0.0244  max mem: 31830
Epoch: [42]  [ 80/312]  eta: 0:02:30  lr: 0.003938  min_lr: 0.003938  loss: 4.0666 (4.0028)  weight_decay: 0.0500 (0.0500)  time: 0.6223  data: 0.0242  max mem: 31830
Epoch: [42]  [ 90/312]  eta: 0:02:17  lr: 0.003938  min_lr: 0.003938  loss: 3.8990 (3.9712)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0069  max mem: 31830
Epoch: [42]  [100/312]  eta: 0:02:11  lr: 0.003938  min_lr: 0.003938  loss: 3.8772 (3.9640)  weight_decay: 0.0500 (0.0500)  time: 0.5077  data: 0.0312  max mem: 31830
Epoch: [42]  [110/312]  eta: 0:02:01  lr: 0.003937  min_lr: 0.003937  loss: 4.2753 (4.0025)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0258  max mem: 31830
Epoch: [42]  [120/312]  eta: 0:01:54  lr: 0.003937  min_lr: 0.003937  loss: 4.2206 (4.0014)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0259  max mem: 31830
Epoch: [42]  [130/312]  eta: 0:01:49  lr: 0.003937  min_lr: 0.003937  loss: 3.9199 (4.0049)  weight_decay: 0.0500 (0.0500)  time: 0.6022  data: 0.0509  max mem: 31830
Epoch: [42]  [140/312]  eta: 0:01:40  lr: 0.003937  min_lr: 0.003937  loss: 3.8450 (3.9782)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0266  max mem: 31830
Epoch: [42]  [150/312]  eta: 0:01:34  lr: 0.003937  min_lr: 0.003937  loss: 3.8450 (3.9786)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0375  max mem: 31830
Epoch: [42]  [160/312]  eta: 0:01:29  lr: 0.003937  min_lr: 0.003937  loss: 4.0770 (3.9818)  weight_decay: 0.0500 (0.0500)  time: 0.6012  data: 0.0523  max mem: 31830
Epoch: [42]  [170/312]  eta: 0:01:22  lr: 0.003936  min_lr: 0.003936  loss: 3.7916 (3.9634)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0380  max mem: 31830
Epoch: [42]  [180/312]  eta: 0:01:16  lr: 0.003936  min_lr: 0.003936  loss: 3.7703 (3.9626)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0532  max mem: 31830
Epoch: [42]  [190/312]  eta: 0:01:09  lr: 0.003936  min_lr: 0.003936  loss: 4.3543 (3.9771)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0308  max mem: 31830
Epoch: [42]  [200/312]  eta: 0:01:04  lr: 0.003936  min_lr: 0.003936  loss: 4.0466 (3.9606)  weight_decay: 0.0500 (0.0500)  time: 0.4943  data: 0.0234  max mem: 31830
Epoch: [42]  [210/312]  eta: 0:00:58  lr: 0.003936  min_lr: 0.003936  loss: 3.5944 (3.9469)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0344  max mem: 31830
Epoch: [42]  [220/312]  eta: 0:00:51  lr: 0.003935  min_lr: 0.003935  loss: 3.9212 (3.9501)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0118  max mem: 31830
Epoch: [42]  [230/312]  eta: 0:00:46  lr: 0.003935  min_lr: 0.003935  loss: 3.9384 (3.9483)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0334  max mem: 31830
Epoch: [42]  [240/312]  eta: 0:00:40  lr: 0.003935  min_lr: 0.003935  loss: 3.9384 (3.9510)  weight_decay: 0.0500 (0.0500)  time: 0.6192  data: 0.0335  max mem: 31830
Epoch: [42]  [250/312]  eta: 0:00:34  lr: 0.003935  min_lr: 0.003935  loss: 4.1750 (3.9555)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0232  max mem: 31830
Epoch: [42]  [260/312]  eta: 0:00:29  lr: 0.003935  min_lr: 0.003935  loss: 4.1433 (3.9561)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0437  max mem: 31830
Epoch: [42]  [270/312]  eta: 0:00:23  lr: 0.003935  min_lr: 0.003935  loss: 4.2822 (3.9691)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0214  max mem: 31830
Epoch: [42]  [280/312]  eta: 0:00:17  lr: 0.003934  min_lr: 0.003934  loss: 4.2822 (3.9745)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.0360  max mem: 31830
Epoch: [42]  [290/312]  eta: 0:00:12  lr: 0.003934  min_lr: 0.003934  loss: 3.9800 (3.9667)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0566  max mem: 31830
Epoch: [42]  [300/312]  eta: 0:00:06  lr: 0.003934  min_lr: 0.003934  loss: 3.4482 (3.9486)  weight_decay: 0.0500 (0.0500)  time: 0.4854  data: 0.0211  max mem: 31830
Epoch: [42]  [310/312]  eta: 0:00:01  lr: 0.003934  min_lr: 0.003934  loss: 3.5961 (3.9494)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [42]  [311/312]  eta: 0:00:00  lr: 0.003934  min_lr: 0.003934  loss: 3.6413 (3.9490)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [42] Total time: 0:02:52 (0.5542 s / it)
Averaged stats: lr: 0.003934  min_lr: 0.003934  loss: 3.6413 (3.9979)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.6943 (1.6943)  acc1: 69.0104 (69.0104)  acc5: 87.8906 (87.8906)  time: 8.7601  data: 8.5929  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9183 (1.8067)  acc1: 61.1979 (62.1440)  acc5: 83.8542 (84.4640)  time: 1.0900  data: 0.9548  max mem: 31830
Test: Total time: 0:00:09 (1.1035 s / it)
* Acc@1 61.688 Acc@5 84.554 loss 1.821
Accuracy of the model on the 50000 test images: 61.7%
Max accuracy: 62.38%
Epoch: [43]  [  0/312]  eta: 1:01:00  lr: 0.003934  min_lr: 0.003934  loss: 4.1696 (4.1696)  weight_decay: 0.0500 (0.0500)  time: 11.7310  data: 8.5789  max mem: 31830
Epoch: [43]  [ 10/312]  eta: 0:08:09  lr: 0.003934  min_lr: 0.003934  loss: 4.0190 (3.8320)  weight_decay: 0.0500 (0.0500)  time: 1.6205  data: 0.9646  max mem: 31830
Epoch: [43]  [ 20/312]  eta: 0:05:31  lr: 0.003933  min_lr: 0.003933  loss: 4.1386 (4.0892)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.1020  max mem: 31830
Epoch: [43]  [ 30/312]  eta: 0:04:12  lr: 0.003933  min_lr: 0.003933  loss: 4.2255 (4.1123)  weight_decay: 0.0500 (0.0500)  time: 0.4976  data: 0.0008  max mem: 31830
Epoch: [43]  [ 40/312]  eta: 0:03:30  lr: 0.003933  min_lr: 0.003933  loss: 4.0231 (4.0764)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0007  max mem: 31830
Epoch: [43]  [ 50/312]  eta: 0:03:03  lr: 0.003933  min_lr: 0.003933  loss: 4.2085 (4.0854)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0007  max mem: 31830
Epoch: [43]  [ 60/312]  eta: 0:02:45  lr: 0.003933  min_lr: 0.003933  loss: 4.1935 (4.0494)  weight_decay: 0.0500 (0.0500)  time: 0.4221  data: 0.0009  max mem: 31830
Epoch: [43]  [ 70/312]  eta: 0:02:37  lr: 0.003932  min_lr: 0.003932  loss: 3.7274 (4.0090)  weight_decay: 0.0500 (0.0500)  time: 0.5237  data: 0.0406  max mem: 31830
Epoch: [43]  [ 80/312]  eta: 0:02:27  lr: 0.003932  min_lr: 0.003932  loss: 4.0962 (4.0254)  weight_decay: 0.0500 (0.0500)  time: 0.5712  data: 0.0580  max mem: 31830
Epoch: [43]  [ 90/312]  eta: 0:02:16  lr: 0.003932  min_lr: 0.003932  loss: 4.1914 (4.0211)  weight_decay: 0.0500 (0.0500)  time: 0.4813  data: 0.0316  max mem: 31830
Epoch: [43]  [100/312]  eta: 0:02:12  lr: 0.003932  min_lr: 0.003932  loss: 4.0181 (4.0110)  weight_decay: 0.0500 (0.0500)  time: 0.5764  data: 0.0659  max mem: 31830
Epoch: [43]  [110/312]  eta: 0:02:02  lr: 0.003932  min_lr: 0.003932  loss: 3.6535 (3.9556)  weight_decay: 0.0500 (0.0500)  time: 0.5585  data: 0.0526  max mem: 31830
Epoch: [43]  [120/312]  eta: 0:01:55  lr: 0.003932  min_lr: 0.003932  loss: 3.7735 (3.9676)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0079  max mem: 31830
Epoch: [43]  [130/312]  eta: 0:01:48  lr: 0.003931  min_lr: 0.003931  loss: 3.9460 (3.9529)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.0496  max mem: 31830
Epoch: [43]  [140/312]  eta: 0:01:40  lr: 0.003931  min_lr: 0.003931  loss: 3.9460 (3.9557)  weight_decay: 0.0500 (0.0500)  time: 0.4811  data: 0.0434  max mem: 31830
Epoch: [43]  [150/312]  eta: 0:01:35  lr: 0.003931  min_lr: 0.003931  loss: 3.9544 (3.9428)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0436  max mem: 31830
Epoch: [43]  [160/312]  eta: 0:01:28  lr: 0.003931  min_lr: 0.003931  loss: 3.9413 (3.9468)  weight_decay: 0.0500 (0.0500)  time: 0.5732  data: 0.0987  max mem: 31830
Epoch: [43]  [170/312]  eta: 0:01:22  lr: 0.003931  min_lr: 0.003931  loss: 4.0904 (3.9464)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0568  max mem: 31830
Epoch: [43]  [180/312]  eta: 0:01:16  lr: 0.003930  min_lr: 0.003930  loss: 3.7421 (3.9339)  weight_decay: 0.0500 (0.0500)  time: 0.5688  data: 0.0630  max mem: 31830
Epoch: [43]  [190/312]  eta: 0:01:10  lr: 0.003930  min_lr: 0.003930  loss: 3.6092 (3.9296)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0635  max mem: 31830
Epoch: [43]  [200/312]  eta: 0:01:04  lr: 0.003930  min_lr: 0.003930  loss: 4.1980 (3.9346)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0771  max mem: 31830
Epoch: [43]  [210/312]  eta: 0:00:59  lr: 0.003930  min_lr: 0.003930  loss: 4.2318 (3.9411)  weight_decay: 0.0500 (0.0500)  time: 0.6113  data: 0.1509  max mem: 31830
Epoch: [43]  [220/312]  eta: 0:00:52  lr: 0.003930  min_lr: 0.003930  loss: 4.0787 (3.9345)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0751  max mem: 31830
Epoch: [43]  [230/312]  eta: 0:00:47  lr: 0.003930  min_lr: 0.003930  loss: 3.5977 (3.9193)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0574  max mem: 31830
Epoch: [43]  [240/312]  eta: 0:00:41  lr: 0.003929  min_lr: 0.003929  loss: 3.3852 (3.9017)  weight_decay: 0.0500 (0.0500)  time: 0.6200  data: 0.1172  max mem: 31830
Epoch: [43]  [250/312]  eta: 0:00:35  lr: 0.003929  min_lr: 0.003929  loss: 3.7908 (3.9061)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0605  max mem: 31830
Epoch: [43]  [260/312]  eta: 0:00:29  lr: 0.003929  min_lr: 0.003929  loss: 4.1973 (3.9133)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0648  max mem: 31830
Epoch: [43]  [270/312]  eta: 0:00:23  lr: 0.003929  min_lr: 0.003929  loss: 4.2679 (3.9170)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0648  max mem: 31830
Epoch: [43]  [280/312]  eta: 0:00:18  lr: 0.003929  min_lr: 0.003929  loss: 4.1680 (3.9163)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0687  max mem: 31830
Epoch: [43]  [290/312]  eta: 0:00:12  lr: 0.003928  min_lr: 0.003928  loss: 3.8250 (3.9112)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0987  max mem: 31830
Epoch: [43]  [300/312]  eta: 0:00:06  lr: 0.003928  min_lr: 0.003928  loss: 3.9902 (3.9197)  weight_decay: 0.0500 (0.0500)  time: 0.4729  data: 0.0305  max mem: 31830
Epoch: [43]  [310/312]  eta: 0:00:01  lr: 0.003928  min_lr: 0.003928  loss: 4.1359 (3.9240)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [43]  [311/312]  eta: 0:00:00  lr: 0.003928  min_lr: 0.003928  loss: 4.1133 (3.9203)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [43] Total time: 0:02:54 (0.5591 s / it)
Averaged stats: lr: 0.003928  min_lr: 0.003928  loss: 4.1133 (3.9639)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5477 (1.5477)  acc1: 68.8802 (68.8802)  acc5: 90.1042 (90.1042)  time: 8.3802  data: 8.2176  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8426 (1.7832)  acc1: 60.2865 (62.1600)  acc5: 83.8542 (84.9760)  time: 1.0506  data: 0.9131  max mem: 31830
Test: Total time: 0:00:09 (1.0604 s / it)
* Acc@1 62.352 Acc@5 84.954 loss 1.793
Accuracy of the model on the 50000 test images: 62.4%
Max accuracy: 62.38%
Epoch: [44]  [  0/312]  eta: 1:02:29  lr: 0.003928  min_lr: 0.003928  loss: 4.0454 (4.0454)  weight_decay: 0.0500 (0.0500)  time: 12.0185  data: 10.8190  max mem: 31830
Epoch: [44]  [ 10/312]  eta: 0:08:00  lr: 0.003928  min_lr: 0.003928  loss: 3.9428 (3.9208)  weight_decay: 0.0500 (0.0500)  time: 1.5912  data: 1.0121  max mem: 31830
Epoch: [44]  [ 20/312]  eta: 0:05:34  lr: 0.003928  min_lr: 0.003928  loss: 3.9428 (3.9927)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.0379  max mem: 31830
Epoch: [44]  [ 30/312]  eta: 0:04:14  lr: 0.003927  min_lr: 0.003927  loss: 4.0443 (4.0022)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0226  max mem: 31830
Epoch: [44]  [ 40/312]  eta: 0:03:33  lr: 0.003927  min_lr: 0.003927  loss: 4.0443 (4.0081)  weight_decay: 0.0500 (0.0500)  time: 0.4052  data: 0.0008  max mem: 31830
Epoch: [44]  [ 50/312]  eta: 0:03:06  lr: 0.003927  min_lr: 0.003927  loss: 4.4205 (4.0768)  weight_decay: 0.0500 (0.0500)  time: 0.4225  data: 0.0008  max mem: 31830
Epoch: [44]  [ 60/312]  eta: 0:02:48  lr: 0.003927  min_lr: 0.003927  loss: 4.3158 (4.0522)  weight_decay: 0.0500 (0.0500)  time: 0.4296  data: 0.0017  max mem: 31830
Epoch: [44]  [ 70/312]  eta: 0:02:43  lr: 0.003927  min_lr: 0.003927  loss: 3.9562 (4.0486)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0018  max mem: 31830
Epoch: [44]  [ 80/312]  eta: 0:02:29  lr: 0.003926  min_lr: 0.003926  loss: 3.6910 (4.0045)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0188  max mem: 31830
Epoch: [44]  [ 90/312]  eta: 0:02:19  lr: 0.003926  min_lr: 0.003926  loss: 3.8411 (3.9883)  weight_decay: 0.0500 (0.0500)  time: 0.4725  data: 0.0187  max mem: 31830
Epoch: [44]  [100/312]  eta: 0:02:14  lr: 0.003926  min_lr: 0.003926  loss: 3.9854 (3.9768)  weight_decay: 0.0500 (0.0500)  time: 0.5970  data: 0.0007  max mem: 31830
Epoch: [44]  [110/312]  eta: 0:02:04  lr: 0.003926  min_lr: 0.003926  loss: 4.0151 (3.9730)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0008  max mem: 31830
Epoch: [44]  [120/312]  eta: 0:01:56  lr: 0.003926  min_lr: 0.003926  loss: 4.1546 (3.9770)  weight_decay: 0.0500 (0.0500)  time: 0.4737  data: 0.0009  max mem: 31830
Epoch: [44]  [130/312]  eta: 0:01:49  lr: 0.003925  min_lr: 0.003925  loss: 4.0854 (3.9994)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0009  max mem: 31830
Epoch: [44]  [140/312]  eta: 0:01:42  lr: 0.003925  min_lr: 0.003925  loss: 4.0499 (3.9931)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0008  max mem: 31830
Epoch: [44]  [150/312]  eta: 0:01:36  lr: 0.003925  min_lr: 0.003925  loss: 3.9478 (3.9870)  weight_decay: 0.0500 (0.0500)  time: 0.5781  data: 0.0133  max mem: 31830
Epoch: [44]  [160/312]  eta: 0:01:28  lr: 0.003925  min_lr: 0.003925  loss: 3.9478 (3.9775)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0133  max mem: 31830
Epoch: [44]  [170/312]  eta: 0:01:23  lr: 0.003925  min_lr: 0.003925  loss: 4.2023 (3.9871)  weight_decay: 0.0500 (0.0500)  time: 0.5186  data: 0.0009  max mem: 31830
Epoch: [44]  [180/312]  eta: 0:01:18  lr: 0.003924  min_lr: 0.003924  loss: 4.1853 (3.9790)  weight_decay: 0.0500 (0.0500)  time: 0.6379  data: 0.0012  max mem: 31830
Epoch: [44]  [190/312]  eta: 0:01:10  lr: 0.003924  min_lr: 0.003924  loss: 3.9764 (3.9736)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0011  max mem: 31830
Epoch: [44]  [200/312]  eta: 0:01:05  lr: 0.003924  min_lr: 0.003924  loss: 3.8576 (3.9668)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0009  max mem: 31830
Epoch: [44]  [210/312]  eta: 0:00:58  lr: 0.003924  min_lr: 0.003924  loss: 3.9562 (3.9605)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0010  max mem: 31830
Epoch: [44]  [220/312]  eta: 0:00:52  lr: 0.003924  min_lr: 0.003924  loss: 3.9562 (3.9533)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0010  max mem: 31830
Epoch: [44]  [230/312]  eta: 0:00:47  lr: 0.003923  min_lr: 0.003923  loss: 3.9168 (3.9450)  weight_decay: 0.0500 (0.0500)  time: 0.6155  data: 0.0129  max mem: 31830
Epoch: [44]  [240/312]  eta: 0:00:41  lr: 0.003923  min_lr: 0.003923  loss: 3.9797 (3.9452)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0131  max mem: 31830
Epoch: [44]  [250/312]  eta: 0:00:35  lr: 0.003923  min_lr: 0.003923  loss: 3.9220 (3.9369)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0011  max mem: 31830
Epoch: [44]  [260/312]  eta: 0:00:29  lr: 0.003923  min_lr: 0.003923  loss: 4.1242 (3.9474)  weight_decay: 0.0500 (0.0500)  time: 0.6372  data: 0.0016  max mem: 31830
Epoch: [44]  [270/312]  eta: 0:00:23  lr: 0.003923  min_lr: 0.003923  loss: 4.2914 (3.9633)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0020  max mem: 31830
Epoch: [44]  [280/312]  eta: 0:00:18  lr: 0.003922  min_lr: 0.003922  loss: 4.2488 (3.9658)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0026  max mem: 31830
Epoch: [44]  [290/312]  eta: 0:00:12  lr: 0.003922  min_lr: 0.003922  loss: 4.1786 (3.9708)  weight_decay: 0.0500 (0.0500)  time: 0.4865  data: 0.0018  max mem: 31830
Epoch: [44]  [300/312]  eta: 0:00:06  lr: 0.003922  min_lr: 0.003922  loss: 4.0593 (3.9727)  weight_decay: 0.0500 (0.0500)  time: 0.4414  data: 0.0002  max mem: 31830
Epoch: [44]  [310/312]  eta: 0:00:01  lr: 0.003922  min_lr: 0.003922  loss: 3.9342 (3.9712)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0001  max mem: 31830
Epoch: [44]  [311/312]  eta: 0:00:00  lr: 0.003922  min_lr: 0.003922  loss: 4.0187 (3.9721)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [44] Total time: 0:02:54 (0.5597 s / it)
Averaged stats: lr: 0.003922  min_lr: 0.003922  loss: 4.0187 (3.9475)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6444 (1.6444)  acc1: 71.6146 (71.6146)  acc5: 89.5833 (89.5833)  time: 8.3041  data: 8.1434  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1900 (1.9546)  acc1: 59.3750 (62.7520)  acc5: 82.5521 (84.4800)  time: 1.0603  data: 0.9249  max mem: 31830
Test: Total time: 0:00:09 (1.0704 s / it)
* Acc@1 62.374 Acc@5 84.980 loss 1.957
Accuracy of the model on the 50000 test images: 62.4%
Max accuracy: 62.38%
Epoch: [45]  [  0/312]  eta: 0:58:54  lr: 0.003922  min_lr: 0.003922  loss: 2.9819 (2.9819)  weight_decay: 0.0500 (0.0500)  time: 11.3272  data: 9.8452  max mem: 31830
Epoch: [45]  [ 10/312]  eta: 0:08:19  lr: 0.003922  min_lr: 0.003922  loss: 4.1175 (3.9651)  weight_decay: 0.0500 (0.0500)  time: 1.6535  data: 0.9766  max mem: 31830
Epoch: [45]  [ 20/312]  eta: 0:05:21  lr: 0.003921  min_lr: 0.003921  loss: 3.8264 (3.8772)  weight_decay: 0.0500 (0.0500)  time: 0.5913  data: 0.0453  max mem: 31830
Epoch: [45]  [ 30/312]  eta: 0:04:08  lr: 0.003921  min_lr: 0.003921  loss: 4.0498 (4.0084)  weight_decay: 0.0500 (0.0500)  time: 0.4579  data: 0.0128  max mem: 31830
Epoch: [45]  [ 40/312]  eta: 0:03:27  lr: 0.003921  min_lr: 0.003921  loss: 4.2032 (4.0455)  weight_decay: 0.0500 (0.0500)  time: 0.4065  data: 0.0128  max mem: 31830
Epoch: [45]  [ 50/312]  eta: 0:03:03  lr: 0.003921  min_lr: 0.003921  loss: 4.1318 (4.0824)  weight_decay: 0.0500 (0.0500)  time: 0.4219  data: 0.0016  max mem: 31830
Epoch: [45]  [ 60/312]  eta: 0:02:44  lr: 0.003921  min_lr: 0.003921  loss: 4.0549 (4.0571)  weight_decay: 0.0500 (0.0500)  time: 0.4221  data: 0.0015  max mem: 31830
Epoch: [45]  [ 70/312]  eta: 0:02:32  lr: 0.003920  min_lr: 0.003920  loss: 3.7349 (4.0213)  weight_decay: 0.0500 (0.0500)  time: 0.4497  data: 0.0375  max mem: 31830
Epoch: [45]  [ 80/312]  eta: 0:02:24  lr: 0.003920  min_lr: 0.003920  loss: 3.7172 (3.9941)  weight_decay: 0.0500 (0.0500)  time: 0.5436  data: 0.1095  max mem: 31830
Epoch: [45]  [ 90/312]  eta: 0:02:15  lr: 0.003920  min_lr: 0.003920  loss: 3.9976 (3.9951)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0986  max mem: 31830
Epoch: [45]  [100/312]  eta: 0:02:10  lr: 0.003920  min_lr: 0.003920  loss: 4.0541 (3.9950)  weight_decay: 0.0500 (0.0500)  time: 0.5788  data: 0.1067  max mem: 31830
Epoch: [45]  [110/312]  eta: 0:02:00  lr: 0.003920  min_lr: 0.003920  loss: 4.2393 (4.0118)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0812  max mem: 31830
Epoch: [45]  [120/312]  eta: 0:01:55  lr: 0.003919  min_lr: 0.003919  loss: 4.2122 (4.0073)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0488  max mem: 31830
Epoch: [45]  [130/312]  eta: 0:01:48  lr: 0.003919  min_lr: 0.003919  loss: 3.9619 (3.9964)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0614  max mem: 31830
Epoch: [45]  [140/312]  eta: 0:01:40  lr: 0.003919  min_lr: 0.003919  loss: 3.8217 (3.9844)  weight_decay: 0.0500 (0.0500)  time: 0.4817  data: 0.0137  max mem: 31830
Epoch: [45]  [150/312]  eta: 0:01:34  lr: 0.003919  min_lr: 0.003919  loss: 4.1989 (4.0052)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0309  max mem: 31830
Epoch: [45]  [160/312]  eta: 0:01:28  lr: 0.003919  min_lr: 0.003919  loss: 4.3054 (4.0162)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0309  max mem: 31830
Epoch: [45]  [170/312]  eta: 0:01:21  lr: 0.003918  min_lr: 0.003918  loss: 3.7644 (3.9835)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0129  max mem: 31830
Epoch: [45]  [180/312]  eta: 0:01:16  lr: 0.003918  min_lr: 0.003918  loss: 3.4480 (3.9704)  weight_decay: 0.0500 (0.0500)  time: 0.5684  data: 0.0131  max mem: 31830
Epoch: [45]  [190/312]  eta: 0:01:09  lr: 0.003918  min_lr: 0.003918  loss: 3.9515 (3.9609)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0010  max mem: 31830
Epoch: [45]  [200/312]  eta: 0:01:04  lr: 0.003918  min_lr: 0.003918  loss: 4.0915 (3.9660)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0008  max mem: 31830
Epoch: [45]  [210/312]  eta: 0:00:58  lr: 0.003918  min_lr: 0.003918  loss: 4.1029 (3.9710)  weight_decay: 0.0500 (0.0500)  time: 0.5698  data: 0.0009  max mem: 31830
Epoch: [45]  [220/312]  eta: 0:00:52  lr: 0.003917  min_lr: 0.003917  loss: 3.9540 (3.9670)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0008  max mem: 31830
Epoch: [45]  [230/312]  eta: 0:00:46  lr: 0.003917  min_lr: 0.003917  loss: 3.8049 (3.9648)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0007  max mem: 31830
Epoch: [45]  [240/312]  eta: 0:00:40  lr: 0.003917  min_lr: 0.003917  loss: 3.7149 (3.9585)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.0007  max mem: 31830
Epoch: [45]  [250/312]  eta: 0:00:35  lr: 0.003917  min_lr: 0.003917  loss: 3.9508 (3.9659)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0015  max mem: 31830
Epoch: [45]  [260/312]  eta: 0:00:29  lr: 0.003917  min_lr: 0.003917  loss: 3.9864 (3.9665)  weight_decay: 0.0500 (0.0500)  time: 0.5833  data: 0.0018  max mem: 31830
Epoch: [45]  [270/312]  eta: 0:00:23  lr: 0.003916  min_lr: 0.003916  loss: 3.8060 (3.9548)  weight_decay: 0.0500 (0.0500)  time: 0.6107  data: 0.0011  max mem: 31830
Epoch: [45]  [280/312]  eta: 0:00:18  lr: 0.003916  min_lr: 0.003916  loss: 3.9089 (3.9602)  weight_decay: 0.0500 (0.0500)  time: 0.5672  data: 0.0151  max mem: 31830
Epoch: [45]  [290/312]  eta: 0:00:12  lr: 0.003916  min_lr: 0.003916  loss: 4.1254 (3.9606)  weight_decay: 0.0500 (0.0500)  time: 0.5747  data: 0.0146  max mem: 31830
Epoch: [45]  [300/312]  eta: 0:00:06  lr: 0.003916  min_lr: 0.003916  loss: 4.0067 (3.9594)  weight_decay: 0.0500 (0.0500)  time: 0.4630  data: 0.0002  max mem: 31830
Epoch: [45]  [310/312]  eta: 0:00:01  lr: 0.003916  min_lr: 0.003916  loss: 3.9936 (3.9625)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [45]  [311/312]  eta: 0:00:00  lr: 0.003916  min_lr: 0.003916  loss: 3.9936 (3.9639)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [45] Total time: 0:02:54 (0.5602 s / it)
Averaged stats: lr: 0.003916  min_lr: 0.003916  loss: 3.9936 (3.9634)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4673 (1.4673)  acc1: 70.0521 (70.0521)  acc5: 90.7552 (90.7552)  time: 8.3658  data: 8.1988  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9766 (1.7873)  acc1: 60.0260 (62.0320)  acc5: 84.1146 (85.3600)  time: 1.0537  data: 0.9111  max mem: 31830
Test: Total time: 0:00:09 (1.0648 s / it)
* Acc@1 61.918 Acc@5 84.908 loss 1.794
Accuracy of the model on the 50000 test images: 61.9%
Max accuracy: 62.38%
Epoch: [46]  [  0/312]  eta: 1:01:54  lr: 0.003916  min_lr: 0.003916  loss: 3.9643 (3.9643)  weight_decay: 0.0500 (0.0500)  time: 11.9041  data: 11.5054  max mem: 31830
Epoch: [46]  [ 10/312]  eta: 0:08:23  lr: 0.003915  min_lr: 0.003915  loss: 4.0312 (3.8497)  weight_decay: 0.0500 (0.0500)  time: 1.6668  data: 1.0466  max mem: 31830
Epoch: [46]  [ 20/312]  eta: 0:05:23  lr: 0.003915  min_lr: 0.003915  loss: 4.0312 (3.9451)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0520  max mem: 31830
Epoch: [46]  [ 30/312]  eta: 0:04:07  lr: 0.003915  min_lr: 0.003915  loss: 4.2718 (3.9872)  weight_decay: 0.0500 (0.0500)  time: 0.4447  data: 0.0521  max mem: 31830
Epoch: [46]  [ 40/312]  eta: 0:03:26  lr: 0.003915  min_lr: 0.003915  loss: 4.1131 (3.9807)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0009  max mem: 31830
Epoch: [46]  [ 50/312]  eta: 0:03:06  lr: 0.003914  min_lr: 0.003914  loss: 4.0952 (4.0317)  weight_decay: 0.0500 (0.0500)  time: 0.4562  data: 0.0628  max mem: 31830
Epoch: [46]  [ 60/312]  eta: 0:02:46  lr: 0.003914  min_lr: 0.003914  loss: 4.1011 (4.0411)  weight_decay: 0.0500 (0.0500)  time: 0.4543  data: 0.0628  max mem: 31830
Epoch: [46]  [ 70/312]  eta: 0:02:37  lr: 0.003914  min_lr: 0.003914  loss: 4.1037 (4.0262)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.1028  max mem: 31830
Epoch: [46]  [ 80/312]  eta: 0:02:28  lr: 0.003914  min_lr: 0.003914  loss: 4.1037 (4.0393)  weight_decay: 0.0500 (0.0500)  time: 0.5744  data: 0.1806  max mem: 31830
Epoch: [46]  [ 90/312]  eta: 0:02:15  lr: 0.003914  min_lr: 0.003914  loss: 4.1188 (4.0216)  weight_decay: 0.0500 (0.0500)  time: 0.4710  data: 0.0787  max mem: 31830
Epoch: [46]  [100/312]  eta: 0:02:09  lr: 0.003913  min_lr: 0.003913  loss: 4.0816 (4.0322)  weight_decay: 0.0500 (0.0500)  time: 0.5013  data: 0.1011  max mem: 31830
Epoch: [46]  [110/312]  eta: 0:01:59  lr: 0.003913  min_lr: 0.003913  loss: 4.1898 (4.0314)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.1009  max mem: 31830
Epoch: [46]  [120/312]  eta: 0:01:54  lr: 0.003913  min_lr: 0.003913  loss: 4.2879 (4.0631)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.1260  max mem: 31830
Epoch: [46]  [130/312]  eta: 0:01:48  lr: 0.003913  min_lr: 0.003913  loss: 4.2630 (4.0529)  weight_decay: 0.0500 (0.0500)  time: 0.6245  data: 0.2280  max mem: 31830
Epoch: [46]  [140/312]  eta: 0:01:40  lr: 0.003913  min_lr: 0.003913  loss: 4.1507 (4.0638)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.1027  max mem: 31830
Epoch: [46]  [150/312]  eta: 0:01:35  lr: 0.003912  min_lr: 0.003912  loss: 4.0960 (4.0537)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1241  max mem: 31830
Epoch: [46]  [160/312]  eta: 0:01:29  lr: 0.003912  min_lr: 0.003912  loss: 4.0439 (4.0517)  weight_decay: 0.0500 (0.0500)  time: 0.6188  data: 0.2258  max mem: 31830
Epoch: [46]  [170/312]  eta: 0:01:21  lr: 0.003912  min_lr: 0.003912  loss: 4.0912 (4.0570)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.1030  max mem: 31830
Epoch: [46]  [180/312]  eta: 0:01:16  lr: 0.003912  min_lr: 0.003912  loss: 4.1341 (4.0552)  weight_decay: 0.0500 (0.0500)  time: 0.5086  data: 0.1174  max mem: 31830
Epoch: [46]  [190/312]  eta: 0:01:09  lr: 0.003912  min_lr: 0.003912  loss: 4.1924 (4.0520)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.1168  max mem: 31830
Epoch: [46]  [200/312]  eta: 0:01:04  lr: 0.003911  min_lr: 0.003911  loss: 4.0681 (4.0514)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.1127  max mem: 31830
Epoch: [46]  [210/312]  eta: 0:00:58  lr: 0.003911  min_lr: 0.003911  loss: 4.0166 (4.0433)  weight_decay: 0.0500 (0.0500)  time: 0.6426  data: 0.2123  max mem: 31830
Epoch: [46]  [220/312]  eta: 0:00:52  lr: 0.003911  min_lr: 0.003911  loss: 4.0166 (4.0372)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.1002  max mem: 31830
Epoch: [46]  [230/312]  eta: 0:00:46  lr: 0.003911  min_lr: 0.003911  loss: 4.1361 (4.0366)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.1318  max mem: 31830
Epoch: [46]  [240/312]  eta: 0:00:41  lr: 0.003910  min_lr: 0.003910  loss: 4.1361 (4.0348)  weight_decay: 0.0500 (0.0500)  time: 0.6475  data: 0.2494  max mem: 31830
Epoch: [46]  [250/312]  eta: 0:00:35  lr: 0.003910  min_lr: 0.003910  loss: 4.1985 (4.0403)  weight_decay: 0.0500 (0.0500)  time: 0.5140  data: 0.1182  max mem: 31830
Epoch: [46]  [260/312]  eta: 0:00:29  lr: 0.003910  min_lr: 0.003910  loss: 4.3182 (4.0521)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.1217  max mem: 31830
Epoch: [46]  [270/312]  eta: 0:00:23  lr: 0.003910  min_lr: 0.003910  loss: 4.2051 (4.0501)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.1218  max mem: 31830
Epoch: [46]  [280/312]  eta: 0:00:18  lr: 0.003910  min_lr: 0.003910  loss: 4.0686 (4.0449)  weight_decay: 0.0500 (0.0500)  time: 0.4993  data: 0.0998  max mem: 31830
Epoch: [46]  [290/312]  eta: 0:00:12  lr: 0.003909  min_lr: 0.003909  loss: 4.0707 (4.0387)  weight_decay: 0.0500 (0.0500)  time: 0.5931  data: 0.2005  max mem: 31830
Epoch: [46]  [300/312]  eta: 0:00:06  lr: 0.003909  min_lr: 0.003909  loss: 3.9986 (4.0303)  weight_decay: 0.0500 (0.0500)  time: 0.4866  data: 0.1012  max mem: 31830
Epoch: [46]  [310/312]  eta: 0:00:01  lr: 0.003909  min_lr: 0.003909  loss: 3.8751 (4.0283)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [46]  [311/312]  eta: 0:00:00  lr: 0.003909  min_lr: 0.003909  loss: 4.0999 (4.0292)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [46] Total time: 0:02:53 (0.5568 s / it)
Averaged stats: lr: 0.003909  min_lr: 0.003909  loss: 4.0999 (3.9473)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.6786 (1.6786)  acc1: 69.9219 (69.9219)  acc5: 89.3229 (89.3229)  time: 8.6994  data: 8.5323  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9428 (1.8815)  acc1: 58.8542 (61.0080)  acc5: 84.1146 (85.4080)  time: 1.0831  data: 0.9481  max mem: 31830
Test: Total time: 0:00:09 (1.0941 s / it)
* Acc@1 61.480 Acc@5 84.864 loss 1.889
Accuracy of the model on the 50000 test images: 61.5%
Max accuracy: 62.38%
Epoch: [47]  [  0/312]  eta: 0:58:11  lr: 0.003909  min_lr: 0.003909  loss: 4.2772 (4.2772)  weight_decay: 0.0500 (0.0500)  time: 11.1920  data: 8.2159  max mem: 31830
Epoch: [47]  [ 10/312]  eta: 0:08:11  lr: 0.003909  min_lr: 0.003909  loss: 4.0785 (3.9210)  weight_decay: 0.0500 (0.0500)  time: 1.6277  data: 1.0049  max mem: 31830
Epoch: [47]  [ 20/312]  eta: 0:05:23  lr: 0.003909  min_lr: 0.003909  loss: 3.9478 (3.8076)  weight_decay: 0.0500 (0.0500)  time: 0.6043  data: 0.1799  max mem: 31830
Epoch: [47]  [ 30/312]  eta: 0:04:08  lr: 0.003908  min_lr: 0.003908  loss: 3.4697 (3.6756)  weight_decay: 0.0500 (0.0500)  time: 0.4686  data: 0.0386  max mem: 31830
Epoch: [47]  [ 40/312]  eta: 0:03:27  lr: 0.003908  min_lr: 0.003908  loss: 3.6209 (3.6933)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [47]  [ 50/312]  eta: 0:03:08  lr: 0.003908  min_lr: 0.003908  loss: 3.9891 (3.7361)  weight_decay: 0.0500 (0.0500)  time: 0.4722  data: 0.0010  max mem: 31830
Epoch: [47]  [ 60/312]  eta: 0:02:48  lr: 0.003908  min_lr: 0.003908  loss: 3.9521 (3.7478)  weight_decay: 0.0500 (0.0500)  time: 0.4739  data: 0.0008  max mem: 31830
Epoch: [47]  [ 70/312]  eta: 0:02:40  lr: 0.003907  min_lr: 0.003907  loss: 3.9521 (3.7685)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0007  max mem: 31830
Epoch: [47]  [ 80/312]  eta: 0:02:30  lr: 0.003907  min_lr: 0.003907  loss: 4.0286 (3.7873)  weight_decay: 0.0500 (0.0500)  time: 0.5894  data: 0.0007  max mem: 31830
Epoch: [47]  [ 90/312]  eta: 0:02:20  lr: 0.003907  min_lr: 0.003907  loss: 3.9855 (3.8065)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0131  max mem: 31830
Epoch: [47]  [100/312]  eta: 0:02:13  lr: 0.003907  min_lr: 0.003907  loss: 4.0260 (3.8088)  weight_decay: 0.0500 (0.0500)  time: 0.5540  data: 0.0389  max mem: 31830
Epoch: [47]  [110/312]  eta: 0:02:02  lr: 0.003907  min_lr: 0.003907  loss: 3.6510 (3.7984)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0266  max mem: 31830
Epoch: [47]  [120/312]  eta: 0:01:57  lr: 0.003906  min_lr: 0.003906  loss: 3.8369 (3.7972)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0071  max mem: 31830
Epoch: [47]  [130/312]  eta: 0:01:51  lr: 0.003906  min_lr: 0.003906  loss: 4.0238 (3.8289)  weight_decay: 0.0500 (0.0500)  time: 0.6297  data: 0.0070  max mem: 31830
Epoch: [47]  [140/312]  eta: 0:01:42  lr: 0.003906  min_lr: 0.003906  loss: 4.1253 (3.8441)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0008  max mem: 31830
Epoch: [47]  [150/312]  eta: 0:01:36  lr: 0.003906  min_lr: 0.003906  loss: 4.0383 (3.8491)  weight_decay: 0.0500 (0.0500)  time: 0.5011  data: 0.0012  max mem: 31830
Epoch: [47]  [160/312]  eta: 0:01:30  lr: 0.003905  min_lr: 0.003905  loss: 3.5359 (3.8303)  weight_decay: 0.0500 (0.0500)  time: 0.5705  data: 0.0011  max mem: 31830
Epoch: [47]  [170/312]  eta: 0:01:23  lr: 0.003905  min_lr: 0.003905  loss: 3.8308 (3.8513)  weight_decay: 0.0500 (0.0500)  time: 0.5036  data: 0.0007  max mem: 31830
Epoch: [47]  [180/312]  eta: 0:01:17  lr: 0.003905  min_lr: 0.003905  loss: 4.2429 (3.8654)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.0009  max mem: 31830
Epoch: [47]  [190/312]  eta: 0:01:10  lr: 0.003905  min_lr: 0.003905  loss: 4.1263 (3.8717)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0011  max mem: 31830
Epoch: [47]  [200/312]  eta: 0:01:05  lr: 0.003905  min_lr: 0.003905  loss: 3.9986 (3.8775)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0011  max mem: 31830
Epoch: [47]  [210/312]  eta: 0:00:59  lr: 0.003904  min_lr: 0.003904  loss: 4.0606 (3.8809)  weight_decay: 0.0500 (0.0500)  time: 0.6124  data: 0.0020  max mem: 31830
Epoch: [47]  [220/312]  eta: 0:00:52  lr: 0.003904  min_lr: 0.003904  loss: 4.0606 (3.8836)  weight_decay: 0.0500 (0.0500)  time: 0.4857  data: 0.0026  max mem: 31830
Epoch: [47]  [230/312]  eta: 0:00:47  lr: 0.003904  min_lr: 0.003904  loss: 4.1639 (3.8821)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0014  max mem: 31830
Epoch: [47]  [240/312]  eta: 0:00:41  lr: 0.003904  min_lr: 0.003904  loss: 4.1639 (3.8834)  weight_decay: 0.0500 (0.0500)  time: 0.5975  data: 0.0006  max mem: 31830
Epoch: [47]  [250/312]  eta: 0:00:35  lr: 0.003904  min_lr: 0.003904  loss: 4.2936 (3.8975)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0006  max mem: 31830
Epoch: [47]  [260/312]  eta: 0:00:29  lr: 0.003903  min_lr: 0.003903  loss: 4.2900 (3.8993)  weight_decay: 0.0500 (0.0500)  time: 0.5620  data: 0.0008  max mem: 31830
Epoch: [47]  [270/312]  eta: 0:00:23  lr: 0.003903  min_lr: 0.003903  loss: 3.8991 (3.8904)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0009  max mem: 31830
Epoch: [47]  [280/312]  eta: 0:00:18  lr: 0.003903  min_lr: 0.003903  loss: 3.8991 (3.8937)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0142  max mem: 31830
Epoch: [47]  [290/312]  eta: 0:00:12  lr: 0.003903  min_lr: 0.003903  loss: 4.1758 (3.9004)  weight_decay: 0.0500 (0.0500)  time: 0.5966  data: 0.0139  max mem: 31830
Epoch: [47]  [300/312]  eta: 0:00:06  lr: 0.003902  min_lr: 0.003902  loss: 4.1172 (3.9036)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0002  max mem: 31830
Epoch: [47]  [310/312]  eta: 0:00:01  lr: 0.003902  min_lr: 0.003902  loss: 3.8380 (3.8950)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [47]  [311/312]  eta: 0:00:00  lr: 0.003902  min_lr: 0.003902  loss: 3.8380 (3.8978)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [47] Total time: 0:02:54 (0.5607 s / it)
Averaged stats: lr: 0.003902  min_lr: 0.003902  loss: 3.8380 (3.9308)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3877 (1.3877)  acc1: 71.2240 (71.2240)  acc5: 90.3646 (90.3646)  time: 8.4845  data: 8.3170  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7777 (1.6837)  acc1: 62.2396 (63.3440)  acc5: 87.1094 (86.2080)  time: 1.0660  data: 0.9242  max mem: 31830
Test: Total time: 0:00:09 (1.0763 s / it)
* Acc@1 63.418 Acc@5 86.090 loss 1.688
Accuracy of the model on the 50000 test images: 63.4%
Max accuracy: 63.42%
Epoch: [48]  [  0/312]  eta: 0:59:37  lr: 0.003902  min_lr: 0.003902  loss: 3.6783 (3.6783)  weight_decay: 0.0500 (0.0500)  time: 11.4664  data: 10.0655  max mem: 31830
Epoch: [48]  [ 10/312]  eta: 0:07:50  lr: 0.003902  min_lr: 0.003902  loss: 4.1366 (3.9430)  weight_decay: 0.0500 (0.0500)  time: 1.5576  data: 0.9550  max mem: 31830
Epoch: [48]  [ 20/312]  eta: 0:05:37  lr: 0.003902  min_lr: 0.003902  loss: 4.1713 (3.9536)  weight_decay: 0.0500 (0.0500)  time: 0.6411  data: 0.0665  max mem: 31830
Epoch: [48]  [ 30/312]  eta: 0:04:16  lr: 0.003901  min_lr: 0.003901  loss: 4.1791 (4.0210)  weight_decay: 0.0500 (0.0500)  time: 0.5517  data: 0.0449  max mem: 31830
Epoch: [48]  [ 40/312]  eta: 0:03:33  lr: 0.003901  min_lr: 0.003901  loss: 4.1791 (3.9914)  weight_decay: 0.0500 (0.0500)  time: 0.3909  data: 0.0006  max mem: 31830
Epoch: [48]  [ 50/312]  eta: 0:03:05  lr: 0.003901  min_lr: 0.003901  loss: 3.8750 (3.9585)  weight_decay: 0.0500 (0.0500)  time: 0.3945  data: 0.0013  max mem: 31830
Epoch: [48]  [ 60/312]  eta: 0:02:45  lr: 0.003901  min_lr: 0.003901  loss: 3.9723 (3.9532)  weight_decay: 0.0500 (0.0500)  time: 0.3941  data: 0.0013  max mem: 31830
Epoch: [48]  [ 70/312]  eta: 0:02:34  lr: 0.003901  min_lr: 0.003901  loss: 4.0035 (3.9320)  weight_decay: 0.0500 (0.0500)  time: 0.4617  data: 0.0315  max mem: 31830
Epoch: [48]  [ 80/312]  eta: 0:02:24  lr: 0.003900  min_lr: 0.003900  loss: 3.7843 (3.9150)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.0940  max mem: 31830
Epoch: [48]  [ 90/312]  eta: 0:02:17  lr: 0.003900  min_lr: 0.003900  loss: 3.7594 (3.8815)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0632  max mem: 31830
Epoch: [48]  [100/312]  eta: 0:02:12  lr: 0.003900  min_lr: 0.003900  loss: 4.0826 (3.8984)  weight_decay: 0.0500 (0.0500)  time: 0.6281  data: 0.0389  max mem: 31830
Epoch: [48]  [110/312]  eta: 0:02:01  lr: 0.003900  min_lr: 0.003900  loss: 4.1074 (3.8939)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0389  max mem: 31830
Epoch: [48]  [120/312]  eta: 0:01:56  lr: 0.003899  min_lr: 0.003899  loss: 4.1000 (3.9198)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0268  max mem: 31830
Epoch: [48]  [130/312]  eta: 0:01:48  lr: 0.003899  min_lr: 0.003899  loss: 4.1000 (3.9023)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0406  max mem: 31830
Epoch: [48]  [140/312]  eta: 0:01:42  lr: 0.003899  min_lr: 0.003899  loss: 4.2163 (3.9265)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0146  max mem: 31830
Epoch: [48]  [150/312]  eta: 0:01:36  lr: 0.003899  min_lr: 0.003899  loss: 4.2794 (3.9300)  weight_decay: 0.0500 (0.0500)  time: 0.5972  data: 0.0069  max mem: 31830
Epoch: [48]  [160/312]  eta: 0:01:28  lr: 0.003899  min_lr: 0.003899  loss: 3.8376 (3.9167)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0308  max mem: 31830
Epoch: [48]  [170/312]  eta: 0:01:22  lr: 0.003898  min_lr: 0.003898  loss: 3.9678 (3.9291)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0248  max mem: 31830
Epoch: [48]  [180/312]  eta: 0:01:17  lr: 0.003898  min_lr: 0.003898  loss: 4.1157 (3.9381)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.0233  max mem: 31830
Epoch: [48]  [190/312]  eta: 0:01:10  lr: 0.003898  min_lr: 0.003898  loss: 4.0813 (3.9408)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0231  max mem: 31830
Epoch: [48]  [200/312]  eta: 0:01:04  lr: 0.003898  min_lr: 0.003898  loss: 4.0750 (3.9435)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0122  max mem: 31830
Epoch: [48]  [210/312]  eta: 0:00:58  lr: 0.003897  min_lr: 0.003897  loss: 4.0779 (3.9501)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0261  max mem: 31830
Epoch: [48]  [220/312]  eta: 0:00:52  lr: 0.003897  min_lr: 0.003897  loss: 4.1262 (3.9431)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0147  max mem: 31830
Epoch: [48]  [230/312]  eta: 0:00:46  lr: 0.003897  min_lr: 0.003897  loss: 3.9955 (3.9414)  weight_decay: 0.0500 (0.0500)  time: 0.5686  data: 0.0490  max mem: 31830
Epoch: [48]  [240/312]  eta: 0:00:40  lr: 0.003897  min_lr: 0.003897  loss: 3.9955 (3.9392)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0948  max mem: 31830
Epoch: [48]  [250/312]  eta: 0:00:35  lr: 0.003897  min_lr: 0.003897  loss: 4.1164 (3.9429)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0468  max mem: 31830
Epoch: [48]  [260/312]  eta: 0:00:29  lr: 0.003896  min_lr: 0.003896  loss: 4.1234 (3.9425)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.0150  max mem: 31830
Epoch: [48]  [270/312]  eta: 0:00:23  lr: 0.003896  min_lr: 0.003896  loss: 4.1541 (3.9468)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0149  max mem: 31830
Epoch: [48]  [280/312]  eta: 0:00:18  lr: 0.003896  min_lr: 0.003896  loss: 4.1541 (3.9461)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0024  max mem: 31830
Epoch: [48]  [290/312]  eta: 0:00:12  lr: 0.003896  min_lr: 0.003896  loss: 4.0422 (3.9447)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0131  max mem: 31830
Epoch: [48]  [300/312]  eta: 0:00:06  lr: 0.003895  min_lr: 0.003895  loss: 4.1535 (3.9511)  weight_decay: 0.0500 (0.0500)  time: 0.4620  data: 0.0111  max mem: 31830
Epoch: [48]  [310/312]  eta: 0:00:01  lr: 0.003895  min_lr: 0.003895  loss: 4.1758 (3.9497)  weight_decay: 0.0500 (0.0500)  time: 0.4268  data: 0.0001  max mem: 31830
Epoch: [48]  [311/312]  eta: 0:00:00  lr: 0.003895  min_lr: 0.003895  loss: 4.1535 (3.9487)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [48] Total time: 0:02:53 (0.5558 s / it)
Averaged stats: lr: 0.003895  min_lr: 0.003895  loss: 4.1535 (3.9459)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5596 (1.5596)  acc1: 69.5312 (69.5312)  acc5: 91.4062 (91.4062)  time: 8.3665  data: 8.2067  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0462 (1.8214)  acc1: 62.6302 (63.8880)  acc5: 84.8958 (86.3520)  time: 1.0610  data: 0.9191  max mem: 31830
Test: Total time: 0:00:09 (1.0709 s / it)
* Acc@1 63.820 Acc@5 86.188 loss 1.830
Accuracy of the model on the 50000 test images: 63.8%
Max accuracy: 63.82%
Epoch: [49]  [  0/312]  eta: 1:02:30  lr: 0.003895  min_lr: 0.003895  loss: 4.2423 (4.2423)  weight_decay: 0.0500 (0.0500)  time: 12.0221  data: 11.6213  max mem: 31830
Epoch: [49]  [ 10/312]  eta: 0:08:44  lr: 0.003895  min_lr: 0.003895  loss: 4.1641 (4.1335)  weight_decay: 0.0500 (0.0500)  time: 1.7375  data: 1.0578  max mem: 31830
Epoch: [49]  [ 20/312]  eta: 0:05:20  lr: 0.003895  min_lr: 0.003895  loss: 3.9723 (3.8918)  weight_decay: 0.0500 (0.0500)  time: 0.5507  data: 0.0010  max mem: 31830
Epoch: [49]  [ 30/312]  eta: 0:04:05  lr: 0.003894  min_lr: 0.003894  loss: 3.9723 (3.9134)  weight_decay: 0.0500 (0.0500)  time: 0.3934  data: 0.0015  max mem: 31830
Epoch: [49]  [ 40/312]  eta: 0:03:25  lr: 0.003894  min_lr: 0.003894  loss: 3.9825 (3.8530)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0015  max mem: 31830
Epoch: [49]  [ 50/312]  eta: 0:02:59  lr: 0.003894  min_lr: 0.003894  loss: 3.8365 (3.8506)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0007  max mem: 31830
Epoch: [49]  [ 60/312]  eta: 0:02:42  lr: 0.003894  min_lr: 0.003894  loss: 3.7412 (3.8329)  weight_decay: 0.0500 (0.0500)  time: 0.4199  data: 0.0008  max mem: 31830
Epoch: [49]  [ 70/312]  eta: 0:02:33  lr: 0.003893  min_lr: 0.003893  loss: 4.1654 (3.9030)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0473  max mem: 31830
Epoch: [49]  [ 80/312]  eta: 0:02:23  lr: 0.003893  min_lr: 0.003893  loss: 4.1654 (3.9132)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.1061  max mem: 31830
Epoch: [49]  [ 90/312]  eta: 0:02:14  lr: 0.003893  min_lr: 0.003893  loss: 4.0062 (3.9356)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0601  max mem: 31830
Epoch: [49]  [100/312]  eta: 0:02:08  lr: 0.003893  min_lr: 0.003893  loss: 4.0588 (3.9330)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.0505  max mem: 31830
Epoch: [49]  [110/312]  eta: 0:01:58  lr: 0.003893  min_lr: 0.003893  loss: 3.7394 (3.8977)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0499  max mem: 31830
Epoch: [49]  [120/312]  eta: 0:01:54  lr: 0.003892  min_lr: 0.003892  loss: 3.4312 (3.8924)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0523  max mem: 31830
Epoch: [49]  [130/312]  eta: 0:01:46  lr: 0.003892  min_lr: 0.003892  loss: 3.9155 (3.9050)  weight_decay: 0.0500 (0.0500)  time: 0.5675  data: 0.0714  max mem: 31830
Epoch: [49]  [140/312]  eta: 0:01:40  lr: 0.003892  min_lr: 0.003892  loss: 3.9155 (3.8924)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.0199  max mem: 31830
Epoch: [49]  [150/312]  eta: 0:01:34  lr: 0.003892  min_lr: 0.003892  loss: 3.6843 (3.8951)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0290  max mem: 31830
Epoch: [49]  [160/312]  eta: 0:01:28  lr: 0.003891  min_lr: 0.003891  loss: 3.9347 (3.9023)  weight_decay: 0.0500 (0.0500)  time: 0.5428  data: 0.0556  max mem: 31830
Epoch: [49]  [170/312]  eta: 0:01:22  lr: 0.003891  min_lr: 0.003891  loss: 4.0515 (3.8932)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0276  max mem: 31830
Epoch: [49]  [180/312]  eta: 0:01:16  lr: 0.003891  min_lr: 0.003891  loss: 3.7737 (3.8857)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0230  max mem: 31830
Epoch: [49]  [190/312]  eta: 0:01:10  lr: 0.003891  min_lr: 0.003891  loss: 3.7737 (3.8795)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0239  max mem: 31830
Epoch: [49]  [200/312]  eta: 0:01:04  lr: 0.003890  min_lr: 0.003890  loss: 3.9825 (3.8946)  weight_decay: 0.0500 (0.0500)  time: 0.5930  data: 0.0156  max mem: 31830
Epoch: [49]  [210/312]  eta: 0:00:58  lr: 0.003890  min_lr: 0.003890  loss: 4.2083 (3.9069)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0269  max mem: 31830
Epoch: [49]  [220/312]  eta: 0:00:52  lr: 0.003890  min_lr: 0.003890  loss: 4.1921 (3.9020)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0131  max mem: 31830
Epoch: [49]  [230/312]  eta: 0:00:47  lr: 0.003890  min_lr: 0.003890  loss: 4.1859 (3.9101)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.0250  max mem: 31830
Epoch: [49]  [240/312]  eta: 0:00:41  lr: 0.003889  min_lr: 0.003889  loss: 4.1859 (3.9179)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0429  max mem: 31830
Epoch: [49]  [250/312]  eta: 0:00:35  lr: 0.003889  min_lr: 0.003889  loss: 4.0137 (3.9151)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0186  max mem: 31830
Epoch: [49]  [260/312]  eta: 0:00:29  lr: 0.003889  min_lr: 0.003889  loss: 4.1458 (3.9204)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0140  max mem: 31830
Epoch: [49]  [270/312]  eta: 0:00:23  lr: 0.003889  min_lr: 0.003889  loss: 4.1333 (3.9183)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0145  max mem: 31830
Epoch: [49]  [280/312]  eta: 0:00:18  lr: 0.003889  min_lr: 0.003889  loss: 4.1376 (3.9289)  weight_decay: 0.0500 (0.0500)  time: 0.6120  data: 0.0177  max mem: 31830
Epoch: [49]  [290/312]  eta: 0:00:12  lr: 0.003888  min_lr: 0.003888  loss: 4.2684 (3.9360)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0332  max mem: 31830
Epoch: [49]  [300/312]  eta: 0:00:06  lr: 0.003888  min_lr: 0.003888  loss: 3.9649 (3.9266)  weight_decay: 0.0500 (0.0500)  time: 0.4453  data: 0.0164  max mem: 31830
Epoch: [49]  [310/312]  eta: 0:00:01  lr: 0.003888  min_lr: 0.003888  loss: 3.5492 (3.9221)  weight_decay: 0.0500 (0.0500)  time: 0.4219  data: 0.0001  max mem: 31830
Epoch: [49]  [311/312]  eta: 0:00:00  lr: 0.003888  min_lr: 0.003888  loss: 3.8276 (3.9230)  weight_decay: 0.0500 (0.0500)  time: 0.4218  data: 0.0001  max mem: 31830
Epoch: [49] Total time: 0:02:54 (0.5585 s / it)
Averaged stats: lr: 0.003888  min_lr: 0.003888  loss: 3.8276 (3.9315)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.7635 (1.7635)  acc1: 67.8385 (67.8385)  acc5: 88.8021 (88.8021)  time: 8.5054  data: 8.3377  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1056 (1.9446)  acc1: 59.6354 (61.6000)  acc5: 81.9010 (83.9840)  time: 1.0619  data: 0.9265  max mem: 31830
Test: Total time: 0:00:09 (1.0804 s / it)
* Acc@1 61.216 Acc@5 84.084 loss 1.960
Accuracy of the model on the 50000 test images: 61.2%
Max accuracy: 63.82%
Epoch: [50]  [  0/312]  eta: 1:04:14  lr: 0.003888  min_lr: 0.003888  loss: 3.8335 (3.8335)  weight_decay: 0.0500 (0.0500)  time: 12.3540  data: 11.2330  max mem: 31830
Epoch: [50]  [ 10/312]  eta: 0:08:38  lr: 0.003888  min_lr: 0.003888  loss: 4.1091 (3.9290)  weight_decay: 0.0500 (0.0500)  time: 1.7154  data: 1.0217  max mem: 31830
Epoch: [50]  [ 20/312]  eta: 0:05:31  lr: 0.003887  min_lr: 0.003887  loss: 4.1526 (4.0344)  weight_decay: 0.0500 (0.0500)  time: 0.5757  data: 0.0581  max mem: 31830
Epoch: [50]  [ 30/312]  eta: 0:04:13  lr: 0.003887  min_lr: 0.003887  loss: 4.2250 (4.0577)  weight_decay: 0.0500 (0.0500)  time: 0.4499  data: 0.0582  max mem: 31830
Epoch: [50]  [ 40/312]  eta: 0:03:31  lr: 0.003887  min_lr: 0.003887  loss: 3.9893 (4.0220)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0007  max mem: 31830
Epoch: [50]  [ 50/312]  eta: 0:03:03  lr: 0.003887  min_lr: 0.003887  loss: 3.6368 (3.9379)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0008  max mem: 31830
Epoch: [50]  [ 60/312]  eta: 0:02:44  lr: 0.003886  min_lr: 0.003886  loss: 3.8532 (3.9656)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0008  max mem: 31830
Epoch: [50]  [ 70/312]  eta: 0:02:34  lr: 0.003886  min_lr: 0.003886  loss: 4.0559 (3.9626)  weight_decay: 0.0500 (0.0500)  time: 0.4714  data: 0.0412  max mem: 31830
Epoch: [50]  [ 80/312]  eta: 0:02:25  lr: 0.003886  min_lr: 0.003886  loss: 4.1838 (3.9605)  weight_decay: 0.0500 (0.0500)  time: 0.5588  data: 0.1073  max mem: 31830
Epoch: [50]  [ 90/312]  eta: 0:02:13  lr: 0.003886  min_lr: 0.003886  loss: 3.8043 (3.9326)  weight_decay: 0.0500 (0.0500)  time: 0.4853  data: 0.0669  max mem: 31830
Epoch: [50]  [100/312]  eta: 0:02:08  lr: 0.003885  min_lr: 0.003885  loss: 4.1079 (3.9338)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0543  max mem: 31830
Epoch: [50]  [110/312]  eta: 0:01:59  lr: 0.003885  min_lr: 0.003885  loss: 4.1222 (3.9437)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0545  max mem: 31830
Epoch: [50]  [120/312]  eta: 0:01:53  lr: 0.003885  min_lr: 0.003885  loss: 4.1252 (3.9511)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0202  max mem: 31830
Epoch: [50]  [130/312]  eta: 0:01:47  lr: 0.003885  min_lr: 0.003885  loss: 3.9460 (3.9323)  weight_decay: 0.0500 (0.0500)  time: 0.5778  data: 0.0330  max mem: 31830
Epoch: [50]  [140/312]  eta: 0:01:40  lr: 0.003884  min_lr: 0.003884  loss: 3.9460 (3.9346)  weight_decay: 0.0500 (0.0500)  time: 0.5215  data: 0.0138  max mem: 31830
Epoch: [50]  [150/312]  eta: 0:01:34  lr: 0.003884  min_lr: 0.003884  loss: 4.1349 (3.9484)  weight_decay: 0.0500 (0.0500)  time: 0.5674  data: 0.0009  max mem: 31830
Epoch: [50]  [160/312]  eta: 0:01:29  lr: 0.003884  min_lr: 0.003884  loss: 4.1629 (3.9521)  weight_decay: 0.0500 (0.0500)  time: 0.6134  data: 0.0023  max mem: 31830
Epoch: [50]  [170/312]  eta: 0:01:22  lr: 0.003884  min_lr: 0.003884  loss: 4.0919 (3.9443)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0024  max mem: 31830
Epoch: [50]  [180/312]  eta: 0:01:16  lr: 0.003883  min_lr: 0.003883  loss: 3.8870 (3.9343)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0135  max mem: 31830
Epoch: [50]  [190/312]  eta: 0:01:09  lr: 0.003883  min_lr: 0.003883  loss: 3.7213 (3.9296)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0139  max mem: 31830
Epoch: [50]  [200/312]  eta: 0:01:04  lr: 0.003883  min_lr: 0.003883  loss: 4.1270 (3.9418)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0151  max mem: 31830
Epoch: [50]  [210/312]  eta: 0:00:58  lr: 0.003883  min_lr: 0.003883  loss: 4.0871 (3.9378)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0146  max mem: 31830
Epoch: [50]  [220/312]  eta: 0:00:52  lr: 0.003883  min_lr: 0.003883  loss: 3.9510 (3.9450)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0009  max mem: 31830
Epoch: [50]  [230/312]  eta: 0:00:46  lr: 0.003882  min_lr: 0.003882  loss: 4.0077 (3.9479)  weight_decay: 0.0500 (0.0500)  time: 0.5847  data: 0.0150  max mem: 31830
Epoch: [50]  [240/312]  eta: 0:00:41  lr: 0.003882  min_lr: 0.003882  loss: 3.9984 (3.9519)  weight_decay: 0.0500 (0.0500)  time: 0.5849  data: 0.0149  max mem: 31830
Epoch: [50]  [250/312]  eta: 0:00:35  lr: 0.003882  min_lr: 0.003882  loss: 4.0382 (3.9477)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0010  max mem: 31830
Epoch: [50]  [260/312]  eta: 0:00:29  lr: 0.003882  min_lr: 0.003882  loss: 4.1574 (3.9542)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0008  max mem: 31830
Epoch: [50]  [270/312]  eta: 0:00:23  lr: 0.003881  min_lr: 0.003881  loss: 4.1167 (3.9556)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0143  max mem: 31830
Epoch: [50]  [280/312]  eta: 0:00:18  lr: 0.003881  min_lr: 0.003881  loss: 4.1282 (3.9648)  weight_decay: 0.0500 (0.0500)  time: 0.5742  data: 0.0158  max mem: 31830
Epoch: [50]  [290/312]  eta: 0:00:12  lr: 0.003881  min_lr: 0.003881  loss: 4.1757 (3.9670)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.0020  max mem: 31830
Epoch: [50]  [300/312]  eta: 0:00:06  lr: 0.003881  min_lr: 0.003881  loss: 4.0914 (3.9686)  weight_decay: 0.0500 (0.0500)  time: 0.4563  data: 0.0003  max mem: 31830
Epoch: [50]  [310/312]  eta: 0:00:01  lr: 0.003880  min_lr: 0.003880  loss: 4.0914 (3.9655)  weight_decay: 0.0500 (0.0500)  time: 0.4142  data: 0.0001  max mem: 31830
Epoch: [50]  [311/312]  eta: 0:00:00  lr: 0.003880  min_lr: 0.003880  loss: 3.7710 (3.9620)  weight_decay: 0.0500 (0.0500)  time: 0.4141  data: 0.0001  max mem: 31830
Epoch: [50] Total time: 0:02:53 (0.5572 s / it)
Averaged stats: lr: 0.003880  min_lr: 0.003880  loss: 3.7710 (3.9360)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4234 (1.4234)  acc1: 71.6146 (71.6146)  acc5: 92.4479 (92.4479)  time: 8.3439  data: 8.1763  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7394 (1.6495)  acc1: 62.7604 (64.4800)  acc5: 85.6771 (86.6720)  time: 1.0456  data: 0.9086  max mem: 31830
Test: Total time: 0:00:09 (1.0565 s / it)
* Acc@1 64.468 Acc@5 86.518 loss 1.665
Accuracy of the model on the 50000 test images: 64.5%
Max accuracy: 64.47%
Epoch: [51]  [  0/312]  eta: 1:02:10  lr: 0.003880  min_lr: 0.003880  loss: 4.1681 (4.1681)  weight_decay: 0.0500 (0.0500)  time: 11.9566  data: 9.4475  max mem: 31830
Epoch: [51]  [ 10/312]  eta: 0:08:45  lr: 0.003880  min_lr: 0.003880  loss: 3.8847 (3.7958)  weight_decay: 0.0500 (0.0500)  time: 1.7411  data: 1.0096  max mem: 31830
Epoch: [51]  [ 20/312]  eta: 0:05:20  lr: 0.003880  min_lr: 0.003880  loss: 3.4161 (3.5923)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0833  max mem: 31830
Epoch: [51]  [ 30/312]  eta: 0:04:05  lr: 0.003880  min_lr: 0.003880  loss: 3.7213 (3.7100)  weight_decay: 0.0500 (0.0500)  time: 0.3923  data: 0.0008  max mem: 31830
Epoch: [51]  [ 40/312]  eta: 0:03:25  lr: 0.003879  min_lr: 0.003879  loss: 3.9464 (3.7182)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0015  max mem: 31830
Epoch: [51]  [ 50/312]  eta: 0:02:59  lr: 0.003879  min_lr: 0.003879  loss: 3.9464 (3.7629)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0021  max mem: 31830
Epoch: [51]  [ 60/312]  eta: 0:02:40  lr: 0.003879  min_lr: 0.003879  loss: 4.1229 (3.7764)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0015  max mem: 31830
Epoch: [51]  [ 70/312]  eta: 0:02:31  lr: 0.003879  min_lr: 0.003879  loss: 4.0829 (3.7760)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0128  max mem: 31830
Epoch: [51]  [ 80/312]  eta: 0:02:23  lr: 0.003878  min_lr: 0.003878  loss: 3.6216 (3.7592)  weight_decay: 0.0500 (0.0500)  time: 0.5666  data: 0.0133  max mem: 31830
Epoch: [51]  [ 90/312]  eta: 0:02:13  lr: 0.003878  min_lr: 0.003878  loss: 3.9628 (3.8053)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0143  max mem: 31830
Epoch: [51]  [100/312]  eta: 0:02:05  lr: 0.003878  min_lr: 0.003878  loss: 4.0268 (3.8011)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0191  max mem: 31830
Epoch: [51]  [110/312]  eta: 0:01:59  lr: 0.003878  min_lr: 0.003878  loss: 4.0239 (3.8183)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0060  max mem: 31830
Epoch: [51]  [120/312]  eta: 0:01:52  lr: 0.003877  min_lr: 0.003877  loss: 4.0239 (3.8181)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0195  max mem: 31830
Epoch: [51]  [130/312]  eta: 0:01:46  lr: 0.003877  min_lr: 0.003877  loss: 3.9924 (3.8263)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0196  max mem: 31830
Epoch: [51]  [140/312]  eta: 0:01:39  lr: 0.003877  min_lr: 0.003877  loss: 3.9924 (3.8275)  weight_decay: 0.0500 (0.0500)  time: 0.5557  data: 0.0011  max mem: 31830
Epoch: [51]  [150/312]  eta: 0:01:33  lr: 0.003877  min_lr: 0.003877  loss: 3.7475 (3.8279)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0133  max mem: 31830
Epoch: [51]  [160/312]  eta: 0:01:27  lr: 0.003876  min_lr: 0.003876  loss: 4.0346 (3.8327)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.0130  max mem: 31830
Epoch: [51]  [170/312]  eta: 0:01:20  lr: 0.003876  min_lr: 0.003876  loss: 4.1353 (3.8526)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0182  max mem: 31830
Epoch: [51]  [180/312]  eta: 0:01:14  lr: 0.003876  min_lr: 0.003876  loss: 4.1081 (3.8484)  weight_decay: 0.0500 (0.0500)  time: 0.5203  data: 0.0318  max mem: 31830
Epoch: [51]  [190/312]  eta: 0:01:09  lr: 0.003876  min_lr: 0.003876  loss: 3.9743 (3.8386)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0150  max mem: 31830
Epoch: [51]  [200/312]  eta: 0:01:03  lr: 0.003875  min_lr: 0.003875  loss: 3.7083 (3.8395)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0143  max mem: 31830
Epoch: [51]  [210/312]  eta: 0:00:57  lr: 0.003875  min_lr: 0.003875  loss: 3.8333 (3.8415)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0142  max mem: 31830
Epoch: [51]  [220/312]  eta: 0:00:51  lr: 0.003875  min_lr: 0.003875  loss: 3.9353 (3.8448)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0194  max mem: 31830
Epoch: [51]  [230/312]  eta: 0:00:45  lr: 0.003875  min_lr: 0.003875  loss: 4.1164 (3.8554)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0190  max mem: 31830
Epoch: [51]  [240/312]  eta: 0:00:40  lr: 0.003874  min_lr: 0.003874  loss: 4.1281 (3.8664)  weight_decay: 0.0500 (0.0500)  time: 0.5652  data: 0.0188  max mem: 31830
Epoch: [51]  [250/312]  eta: 0:00:34  lr: 0.003874  min_lr: 0.003874  loss: 4.0363 (3.8701)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0314  max mem: 31830
Epoch: [51]  [260/312]  eta: 0:00:28  lr: 0.003874  min_lr: 0.003874  loss: 4.0363 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0137  max mem: 31830
Epoch: [51]  [270/312]  eta: 0:00:23  lr: 0.003874  min_lr: 0.003874  loss: 3.7628 (3.8569)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0271  max mem: 31830
Epoch: [51]  [280/312]  eta: 0:00:17  lr: 0.003873  min_lr: 0.003873  loss: 3.7628 (3.8618)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0406  max mem: 31830
Epoch: [51]  [290/312]  eta: 0:00:12  lr: 0.003873  min_lr: 0.003873  loss: 4.1941 (3.8728)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0142  max mem: 31830
Epoch: [51]  [300/312]  eta: 0:00:06  lr: 0.003873  min_lr: 0.003873  loss: 4.2034 (3.8782)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0130  max mem: 31830
Epoch: [51]  [310/312]  eta: 0:00:01  lr: 0.003873  min_lr: 0.003873  loss: 4.1801 (3.8761)  weight_decay: 0.0500 (0.0500)  time: 0.4039  data: 0.0129  max mem: 31830
Epoch: [51]  [311/312]  eta: 0:00:00  lr: 0.003873  min_lr: 0.003873  loss: 4.1801 (3.8764)  weight_decay: 0.0500 (0.0500)  time: 0.4031  data: 0.0129  max mem: 31830
Epoch: [51] Total time: 0:02:51 (0.5508 s / it)
Averaged stats: lr: 0.003873  min_lr: 0.003873  loss: 4.1801 (3.9267)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.8467 (1.8467)  acc1: 68.0990 (68.0990)  acc5: 89.7135 (89.7135)  time: 8.6207  data: 8.4537  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0968 (2.0025)  acc1: 60.5469 (61.4720)  acc5: 83.8542 (84.7680)  time: 1.0813  data: 0.9394  max mem: 31830
Test: Total time: 0:00:09 (1.0913 s / it)
* Acc@1 61.832 Acc@5 85.016 loss 2.000
Accuracy of the model on the 50000 test images: 61.8%
Max accuracy: 64.47%
Epoch: [52]  [  0/312]  eta: 1:02:22  lr: 0.003873  min_lr: 0.003873  loss: 3.9582 (3.9582)  weight_decay: 0.0500 (0.0500)  time: 11.9957  data: 11.6022  max mem: 31830
Epoch: [52]  [ 10/312]  eta: 0:08:44  lr: 0.003872  min_lr: 0.003872  loss: 3.9830 (3.8460)  weight_decay: 0.0500 (0.0500)  time: 1.7367  data: 1.0552  max mem: 31830
Epoch: [52]  [ 20/312]  eta: 0:05:30  lr: 0.003872  min_lr: 0.003872  loss: 3.9830 (3.8164)  weight_decay: 0.0500 (0.0500)  time: 0.5887  data: 0.0006  max mem: 31830
Epoch: [52]  [ 30/312]  eta: 0:04:12  lr: 0.003872  min_lr: 0.003872  loss: 3.7258 (3.7786)  weight_decay: 0.0500 (0.0500)  time: 0.4308  data: 0.0007  max mem: 31830
Epoch: [52]  [ 40/312]  eta: 0:03:30  lr: 0.003871  min_lr: 0.003871  loss: 3.9122 (3.8572)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0006  max mem: 31830
Epoch: [52]  [ 50/312]  eta: 0:03:03  lr: 0.003871  min_lr: 0.003871  loss: 4.0380 (3.8197)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0008  max mem: 31830
Epoch: [52]  [ 60/312]  eta: 0:02:44  lr: 0.003871  min_lr: 0.003871  loss: 4.0304 (3.8455)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0010  max mem: 31830
Epoch: [52]  [ 70/312]  eta: 0:02:34  lr: 0.003871  min_lr: 0.003871  loss: 3.9150 (3.8430)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0182  max mem: 31830
Epoch: [52]  [ 80/312]  eta: 0:02:24  lr: 0.003870  min_lr: 0.003870  loss: 3.7798 (3.8216)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0583  max mem: 31830
Epoch: [52]  [ 90/312]  eta: 0:02:12  lr: 0.003870  min_lr: 0.003870  loss: 3.8844 (3.8484)  weight_decay: 0.0500 (0.0500)  time: 0.4575  data: 0.0410  max mem: 31830
Epoch: [52]  [100/312]  eta: 0:02:09  lr: 0.003870  min_lr: 0.003870  loss: 3.9606 (3.8555)  weight_decay: 0.0500 (0.0500)  time: 0.5640  data: 0.0666  max mem: 31830
Epoch: [52]  [110/312]  eta: 0:01:59  lr: 0.003870  min_lr: 0.003870  loss: 3.9514 (3.8565)  weight_decay: 0.0500 (0.0500)  time: 0.5565  data: 0.0665  max mem: 31830
Epoch: [52]  [120/312]  eta: 0:01:53  lr: 0.003869  min_lr: 0.003869  loss: 3.9793 (3.8506)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0187  max mem: 31830
Epoch: [52]  [130/312]  eta: 0:01:47  lr: 0.003869  min_lr: 0.003869  loss: 3.6135 (3.8359)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0353  max mem: 31830
Epoch: [52]  [140/312]  eta: 0:01:39  lr: 0.003869  min_lr: 0.003869  loss: 4.0233 (3.8460)  weight_decay: 0.0500 (0.0500)  time: 0.5112  data: 0.0172  max mem: 31830
Epoch: [52]  [150/312]  eta: 0:01:34  lr: 0.003869  min_lr: 0.003869  loss: 4.0978 (3.8485)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0007  max mem: 31830
Epoch: [52]  [160/312]  eta: 0:01:29  lr: 0.003868  min_lr: 0.003868  loss: 3.9701 (3.8448)  weight_decay: 0.0500 (0.0500)  time: 0.6374  data: 0.0129  max mem: 31830
Epoch: [52]  [170/312]  eta: 0:01:22  lr: 0.003868  min_lr: 0.003868  loss: 4.0138 (3.8541)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.0317  max mem: 31830
Epoch: [52]  [180/312]  eta: 0:01:16  lr: 0.003868  min_lr: 0.003868  loss: 4.0200 (3.8513)  weight_decay: 0.0500 (0.0500)  time: 0.5005  data: 0.0201  max mem: 31830
Epoch: [52]  [190/312]  eta: 0:01:09  lr: 0.003868  min_lr: 0.003868  loss: 3.9397 (3.8628)  weight_decay: 0.0500 (0.0500)  time: 0.4747  data: 0.0126  max mem: 31830
Epoch: [52]  [200/312]  eta: 0:01:04  lr: 0.003867  min_lr: 0.003867  loss: 3.7873 (3.8565)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0298  max mem: 31830
Epoch: [52]  [210/312]  eta: 0:00:58  lr: 0.003867  min_lr: 0.003867  loss: 3.7440 (3.8561)  weight_decay: 0.0500 (0.0500)  time: 0.6100  data: 0.0186  max mem: 31830
Epoch: [52]  [220/312]  eta: 0:00:52  lr: 0.003867  min_lr: 0.003867  loss: 4.0805 (3.8802)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0378  max mem: 31830
Epoch: [52]  [230/312]  eta: 0:00:46  lr: 0.003867  min_lr: 0.003867  loss: 3.9576 (3.8666)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0507  max mem: 31830
Epoch: [52]  [240/312]  eta: 0:00:40  lr: 0.003866  min_lr: 0.003866  loss: 3.7740 (3.8640)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0137  max mem: 31830
Epoch: [52]  [250/312]  eta: 0:00:35  lr: 0.003866  min_lr: 0.003866  loss: 4.1515 (3.8706)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0245  max mem: 31830
Epoch: [52]  [260/312]  eta: 0:00:29  lr: 0.003866  min_lr: 0.003866  loss: 3.8619 (3.8717)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0246  max mem: 31830
Epoch: [52]  [270/312]  eta: 0:00:23  lr: 0.003866  min_lr: 0.003866  loss: 3.8619 (3.8717)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0249  max mem: 31830
Epoch: [52]  [280/312]  eta: 0:00:18  lr: 0.003865  min_lr: 0.003865  loss: 4.0876 (3.8805)  weight_decay: 0.0500 (0.0500)  time: 0.5615  data: 0.0380  max mem: 31830
Epoch: [52]  [290/312]  eta: 0:00:12  lr: 0.003865  min_lr: 0.003865  loss: 4.2628 (3.8908)  weight_decay: 0.0500 (0.0500)  time: 0.5653  data: 0.0138  max mem: 31830
Epoch: [52]  [300/312]  eta: 0:00:06  lr: 0.003865  min_lr: 0.003865  loss: 4.1452 (3.8880)  weight_decay: 0.0500 (0.0500)  time: 0.4620  data: 0.0165  max mem: 31830
Epoch: [52]  [310/312]  eta: 0:00:01  lr: 0.003865  min_lr: 0.003865  loss: 3.6630 (3.8836)  weight_decay: 0.0500 (0.0500)  time: 0.4067  data: 0.0164  max mem: 31830
Epoch: [52]  [311/312]  eta: 0:00:00  lr: 0.003865  min_lr: 0.003865  loss: 3.6465 (3.8802)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0164  max mem: 31830
Epoch: [52] Total time: 0:02:53 (0.5566 s / it)
Averaged stats: lr: 0.003865  min_lr: 0.003865  loss: 3.6465 (3.9074)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.2432 (1.2432)  acc1: 70.5729 (70.5729)  acc5: 92.0573 (92.0573)  time: 8.5507  data: 8.3831  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7094 (1.5041)  acc1: 63.0208 (65.1040)  acc5: 85.5469 (87.3600)  time: 1.0674  data: 0.9315  max mem: 31830
Test: Total time: 0:00:09 (1.0842 s / it)
* Acc@1 65.288 Acc@5 87.178 loss 1.512
Accuracy of the model on the 50000 test images: 65.3%
Max accuracy: 65.29%
Epoch: [53]  [  0/312]  eta: 0:59:58  lr: 0.003865  min_lr: 0.003865  loss: 4.0958 (4.0958)  weight_decay: 0.0500 (0.0500)  time: 11.5348  data: 10.1394  max mem: 31830
Epoch: [53]  [ 10/312]  eta: 0:08:05  lr: 0.003864  min_lr: 0.003864  loss: 4.0958 (3.8773)  weight_decay: 0.0500 (0.0500)  time: 1.6088  data: 0.9224  max mem: 31830
Epoch: [53]  [ 20/312]  eta: 0:05:31  lr: 0.003864  min_lr: 0.003864  loss: 3.7497 (3.6998)  weight_decay: 0.0500 (0.0500)  time: 0.6155  data: 0.0497  max mem: 31830
Epoch: [53]  [ 30/312]  eta: 0:04:13  lr: 0.003864  min_lr: 0.003864  loss: 3.7497 (3.7847)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0497  max mem: 31830
Epoch: [53]  [ 40/312]  eta: 0:03:30  lr: 0.003863  min_lr: 0.003863  loss: 3.9693 (3.8126)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0007  max mem: 31830
Epoch: [53]  [ 50/312]  eta: 0:03:03  lr: 0.003863  min_lr: 0.003863  loss: 4.1995 (3.8899)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0007  max mem: 31830
Epoch: [53]  [ 60/312]  eta: 0:02:43  lr: 0.003863  min_lr: 0.003863  loss: 4.1995 (3.8595)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0008  max mem: 31830
Epoch: [53]  [ 70/312]  eta: 0:02:37  lr: 0.003863  min_lr: 0.003863  loss: 3.8420 (3.8681)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0596  max mem: 31830
Epoch: [53]  [ 80/312]  eta: 0:02:26  lr: 0.003862  min_lr: 0.003862  loss: 4.0298 (3.8715)  weight_decay: 0.0500 (0.0500)  time: 0.5767  data: 0.0595  max mem: 31830
Epoch: [53]  [ 90/312]  eta: 0:02:17  lr: 0.003862  min_lr: 0.003862  loss: 4.0392 (3.8704)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0391  max mem: 31830
Epoch: [53]  [100/312]  eta: 0:02:11  lr: 0.003862  min_lr: 0.003862  loss: 4.0208 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 0.5718  data: 0.0749  max mem: 31830
Epoch: [53]  [110/312]  eta: 0:02:01  lr: 0.003862  min_lr: 0.003862  loss: 4.1318 (3.8782)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0364  max mem: 31830
Epoch: [53]  [120/312]  eta: 0:01:55  lr: 0.003861  min_lr: 0.003861  loss: 4.1528 (3.8695)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.0409  max mem: 31830
Epoch: [53]  [130/312]  eta: 0:01:48  lr: 0.003861  min_lr: 0.003861  loss: 4.0892 (3.8655)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.0555  max mem: 31830
Epoch: [53]  [140/312]  eta: 0:01:40  lr: 0.003861  min_lr: 0.003861  loss: 3.9961 (3.8638)  weight_decay: 0.0500 (0.0500)  time: 0.4686  data: 0.0153  max mem: 31830
Epoch: [53]  [150/312]  eta: 0:01:34  lr: 0.003861  min_lr: 0.003861  loss: 3.9097 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 0.4826  data: 0.0584  max mem: 31830
Epoch: [53]  [160/312]  eta: 0:01:28  lr: 0.003860  min_lr: 0.003860  loss: 4.0857 (3.8835)  weight_decay: 0.0500 (0.0500)  time: 0.5682  data: 0.1451  max mem: 31830
Epoch: [53]  [170/312]  eta: 0:01:21  lr: 0.003860  min_lr: 0.003860  loss: 4.2343 (3.9018)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0881  max mem: 31830
Epoch: [53]  [180/312]  eta: 0:01:15  lr: 0.003860  min_lr: 0.003860  loss: 4.2032 (3.9027)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.0705  max mem: 31830
Epoch: [53]  [190/312]  eta: 0:01:08  lr: 0.003860  min_lr: 0.003860  loss: 3.8319 (3.8894)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0702  max mem: 31830
Epoch: [53]  [200/312]  eta: 0:01:03  lr: 0.003859  min_lr: 0.003859  loss: 3.8900 (3.8874)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.1235  max mem: 31830
Epoch: [53]  [210/312]  eta: 0:00:58  lr: 0.003859  min_lr: 0.003859  loss: 4.0076 (3.8962)  weight_decay: 0.0500 (0.0500)  time: 0.6355  data: 0.2158  max mem: 31830
Epoch: [53]  [220/312]  eta: 0:00:51  lr: 0.003859  min_lr: 0.003859  loss: 4.1251 (3.9051)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0933  max mem: 31830
Epoch: [53]  [230/312]  eta: 0:00:46  lr: 0.003858  min_lr: 0.003858  loss: 4.1513 (3.9133)  weight_decay: 0.0500 (0.0500)  time: 0.5727  data: 0.1818  max mem: 31830
Epoch: [53]  [240/312]  eta: 0:00:41  lr: 0.003858  min_lr: 0.003858  loss: 4.2504 (3.9290)  weight_decay: 0.0500 (0.0500)  time: 0.6708  data: 0.2799  max mem: 31830
Epoch: [53]  [250/312]  eta: 0:00:34  lr: 0.003858  min_lr: 0.003858  loss: 4.0564 (3.9186)  weight_decay: 0.0500 (0.0500)  time: 0.4920  data: 0.0987  max mem: 31830
Epoch: [53]  [260/312]  eta: 0:00:29  lr: 0.003858  min_lr: 0.003858  loss: 3.4696 (3.9041)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.1158  max mem: 31830
Epoch: [53]  [270/312]  eta: 0:00:23  lr: 0.003857  min_lr: 0.003857  loss: 3.7655 (3.9061)  weight_decay: 0.0500 (0.0500)  time: 0.5116  data: 0.1165  max mem: 31830
Epoch: [53]  [280/312]  eta: 0:00:17  lr: 0.003857  min_lr: 0.003857  loss: 3.9048 (3.8920)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0975  max mem: 31830
Epoch: [53]  [290/312]  eta: 0:00:12  lr: 0.003857  min_lr: 0.003857  loss: 3.9048 (3.8986)  weight_decay: 0.0500 (0.0500)  time: 0.5820  data: 0.1916  max mem: 31830
Epoch: [53]  [300/312]  eta: 0:00:06  lr: 0.003857  min_lr: 0.003857  loss: 4.1844 (3.9047)  weight_decay: 0.0500 (0.0500)  time: 0.4793  data: 0.0953  max mem: 31830
Epoch: [53]  [310/312]  eta: 0:00:01  lr: 0.003856  min_lr: 0.003856  loss: 4.1742 (3.9095)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [53]  [311/312]  eta: 0:00:00  lr: 0.003856  min_lr: 0.003856  loss: 4.1742 (3.9123)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [53] Total time: 0:02:52 (0.5531 s / it)
Averaged stats: lr: 0.003856  min_lr: 0.003856  loss: 4.1742 (3.9185)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.7235 (1.7235)  acc1: 72.3958 (72.3958)  acc5: 90.7552 (90.7552)  time: 8.3094  data: 8.1423  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9679 (1.9032)  acc1: 63.8021 (64.0960)  acc5: 85.8073 (86.1280)  time: 1.0416  data: 0.9055  max mem: 31830
Test: Total time: 0:00:09 (1.0511 s / it)
* Acc@1 63.446 Acc@5 86.158 loss 1.918
Accuracy of the model on the 50000 test images: 63.4%
Max accuracy: 65.29%
Epoch: [54]  [  0/312]  eta: 0:59:10  lr: 0.003856  min_lr: 0.003856  loss: 4.7134 (4.7134)  weight_decay: 0.0500 (0.0500)  time: 11.3795  data: 8.8607  max mem: 31830
Epoch: [54]  [ 10/312]  eta: 0:09:33  lr: 0.003856  min_lr: 0.003856  loss: 3.7606 (3.7301)  weight_decay: 0.0500 (0.0500)  time: 1.8981  data: 1.0495  max mem: 31830
Epoch: [54]  [ 20/312]  eta: 0:05:44  lr: 0.003856  min_lr: 0.003856  loss: 3.9509 (3.9333)  weight_decay: 0.0500 (0.0500)  time: 0.6687  data: 0.1344  max mem: 31830
Epoch: [54]  [ 30/312]  eta: 0:04:21  lr: 0.003855  min_lr: 0.003855  loss: 4.1377 (3.9183)  weight_decay: 0.0500 (0.0500)  time: 0.3926  data: 0.0012  max mem: 31830
Epoch: [54]  [ 40/312]  eta: 0:03:36  lr: 0.003855  min_lr: 0.003855  loss: 3.9604 (3.8997)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0013  max mem: 31830
Epoch: [54]  [ 50/312]  eta: 0:03:08  lr: 0.003855  min_lr: 0.003855  loss: 3.8537 (3.8861)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0008  max mem: 31830
Epoch: [54]  [ 60/312]  eta: 0:02:48  lr: 0.003855  min_lr: 0.003855  loss: 3.7288 (3.8323)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0011  max mem: 31830
Epoch: [54]  [ 70/312]  eta: 0:02:32  lr: 0.003854  min_lr: 0.003854  loss: 4.1733 (3.8779)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0012  max mem: 31830
Epoch: [54]  [ 80/312]  eta: 0:02:22  lr: 0.003854  min_lr: 0.003854  loss: 4.1542 (3.8537)  weight_decay: 0.0500 (0.0500)  time: 0.4566  data: 0.0326  max mem: 31830
Epoch: [54]  [ 90/312]  eta: 0:02:15  lr: 0.003854  min_lr: 0.003854  loss: 3.6989 (3.8348)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0477  max mem: 31830
Epoch: [54]  [100/312]  eta: 0:02:08  lr: 0.003854  min_lr: 0.003854  loss: 3.9711 (3.8639)  weight_decay: 0.0500 (0.0500)  time: 0.5579  data: 0.0588  max mem: 31830
Epoch: [54]  [110/312]  eta: 0:02:01  lr: 0.003853  min_lr: 0.003853  loss: 4.2065 (3.8769)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.0820  max mem: 31830
Epoch: [54]  [120/312]  eta: 0:01:53  lr: 0.003853  min_lr: 0.003853  loss: 4.0495 (3.8661)  weight_decay: 0.0500 (0.0500)  time: 0.5161  data: 0.0678  max mem: 31830
Epoch: [54]  [130/312]  eta: 0:01:47  lr: 0.003853  min_lr: 0.003853  loss: 4.0271 (3.8790)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0716  max mem: 31830
Epoch: [54]  [140/312]  eta: 0:01:40  lr: 0.003852  min_lr: 0.003852  loss: 3.9131 (3.8633)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0622  max mem: 31830
Epoch: [54]  [150/312]  eta: 0:01:34  lr: 0.003852  min_lr: 0.003852  loss: 3.8629 (3.8736)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0437  max mem: 31830
Epoch: [54]  [160/312]  eta: 0:01:28  lr: 0.003852  min_lr: 0.003852  loss: 4.1543 (3.8750)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.0405  max mem: 31830
Epoch: [54]  [170/312]  eta: 0:01:22  lr: 0.003852  min_lr: 0.003852  loss: 3.9661 (3.8668)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0489  max mem: 31830
Epoch: [54]  [180/312]  eta: 0:01:16  lr: 0.003851  min_lr: 0.003851  loss: 3.5716 (3.8520)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0662  max mem: 31830
Epoch: [54]  [190/312]  eta: 0:01:10  lr: 0.003851  min_lr: 0.003851  loss: 3.5716 (3.8425)  weight_decay: 0.0500 (0.0500)  time: 0.5784  data: 0.0676  max mem: 31830
Epoch: [54]  [200/312]  eta: 0:01:04  lr: 0.003851  min_lr: 0.003851  loss: 3.9992 (3.8469)  weight_decay: 0.0500 (0.0500)  time: 0.5282  data: 0.0484  max mem: 31830
Epoch: [54]  [210/312]  eta: 0:00:58  lr: 0.003851  min_lr: 0.003851  loss: 3.9992 (3.8430)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0509  max mem: 31830
Epoch: [54]  [220/312]  eta: 0:00:52  lr: 0.003850  min_lr: 0.003850  loss: 3.7768 (3.8441)  weight_decay: 0.0500 (0.0500)  time: 0.5542  data: 0.0825  max mem: 31830
Epoch: [54]  [230/312]  eta: 0:00:46  lr: 0.003850  min_lr: 0.003850  loss: 4.0434 (3.8477)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0464  max mem: 31830
Epoch: [54]  [240/312]  eta: 0:00:41  lr: 0.003850  min_lr: 0.003850  loss: 4.0788 (3.8613)  weight_decay: 0.0500 (0.0500)  time: 0.5526  data: 0.0310  max mem: 31830
Epoch: [54]  [250/312]  eta: 0:00:35  lr: 0.003849  min_lr: 0.003849  loss: 4.0713 (3.8609)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0311  max mem: 31830
Epoch: [54]  [260/312]  eta: 0:00:29  lr: 0.003849  min_lr: 0.003849  loss: 3.9393 (3.8643)  weight_decay: 0.0500 (0.0500)  time: 0.5711  data: 0.0383  max mem: 31830
Epoch: [54]  [270/312]  eta: 0:00:23  lr: 0.003849  min_lr: 0.003849  loss: 4.1728 (3.8740)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0483  max mem: 31830
Epoch: [54]  [280/312]  eta: 0:00:18  lr: 0.003849  min_lr: 0.003849  loss: 3.9098 (3.8661)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0406  max mem: 31830
Epoch: [54]  [290/312]  eta: 0:00:12  lr: 0.003848  min_lr: 0.003848  loss: 3.9098 (3.8695)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0467  max mem: 31830
Epoch: [54]  [300/312]  eta: 0:00:06  lr: 0.003848  min_lr: 0.003848  loss: 4.1418 (3.8732)  weight_decay: 0.0500 (0.0500)  time: 0.4850  data: 0.0166  max mem: 31830
Epoch: [54]  [310/312]  eta: 0:00:01  lr: 0.003848  min_lr: 0.003848  loss: 4.0424 (3.8807)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0002  max mem: 31830
Epoch: [54]  [311/312]  eta: 0:00:00  lr: 0.003848  min_lr: 0.003848  loss: 4.1418 (3.8827)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0002  max mem: 31830
Epoch: [54] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.003848  min_lr: 0.003848  loss: 4.1418 (3.8913)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.7085 (1.7085)  acc1: 67.5781 (67.5781)  acc5: 88.2812 (88.2812)  time: 8.8798  data: 8.7122  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1014 (1.9622)  acc1: 59.3750 (60.8000)  acc5: 81.9010 (83.4080)  time: 1.1035  data: 0.9681  max mem: 31830
Test: Total time: 0:00:10 (1.1338 s / it)
* Acc@1 60.302 Acc@5 83.182 loss 1.968
Accuracy of the model on the 50000 test images: 60.3%
Max accuracy: 65.29%
Epoch: [55]  [  0/312]  eta: 1:04:08  lr: 0.003848  min_lr: 0.003848  loss: 4.7023 (4.7023)  weight_decay: 0.0500 (0.0500)  time: 12.3351  data: 9.8105  max mem: 31830
Epoch: [55]  [ 10/312]  eta: 0:09:29  lr: 0.003848  min_lr: 0.003848  loss: 3.9166 (3.9112)  weight_decay: 0.0500 (0.0500)  time: 1.8842  data: 1.0600  max mem: 31830
Epoch: [55]  [ 20/312]  eta: 0:05:41  lr: 0.003847  min_lr: 0.003847  loss: 3.8318 (3.8421)  weight_decay: 0.0500 (0.0500)  time: 0.6125  data: 0.0928  max mem: 31830
Epoch: [55]  [ 30/312]  eta: 0:04:19  lr: 0.003847  min_lr: 0.003847  loss: 3.6198 (3.7206)  weight_decay: 0.0500 (0.0500)  time: 0.3920  data: 0.0007  max mem: 31830
Epoch: [55]  [ 40/312]  eta: 0:03:36  lr: 0.003847  min_lr: 0.003847  loss: 3.8986 (3.7959)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0008  max mem: 31830
Epoch: [55]  [ 50/312]  eta: 0:03:07  lr: 0.003846  min_lr: 0.003846  loss: 3.9483 (3.8283)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [55]  [ 60/312]  eta: 0:02:47  lr: 0.003846  min_lr: 0.003846  loss: 3.9323 (3.8304)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0007  max mem: 31830
Epoch: [55]  [ 70/312]  eta: 0:02:32  lr: 0.003846  min_lr: 0.003846  loss: 3.7347 (3.8064)  weight_decay: 0.0500 (0.0500)  time: 0.4098  data: 0.0009  max mem: 31830
Epoch: [55]  [ 80/312]  eta: 0:02:24  lr: 0.003846  min_lr: 0.003846  loss: 3.7347 (3.8153)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.0272  max mem: 31830
Epoch: [55]  [ 90/312]  eta: 0:02:15  lr: 0.003845  min_lr: 0.003845  loss: 4.1239 (3.8467)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0273  max mem: 31830
Epoch: [55]  [100/312]  eta: 0:02:09  lr: 0.003845  min_lr: 0.003845  loss: 4.0555 (3.8646)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0140  max mem: 31830
Epoch: [55]  [110/312]  eta: 0:02:01  lr: 0.003845  min_lr: 0.003845  loss: 3.9263 (3.8565)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0293  max mem: 31830
Epoch: [55]  [120/312]  eta: 0:01:53  lr: 0.003844  min_lr: 0.003844  loss: 3.7932 (3.8421)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0313  max mem: 31830
Epoch: [55]  [130/312]  eta: 0:01:48  lr: 0.003844  min_lr: 0.003844  loss: 4.0450 (3.8657)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0710  max mem: 31830
Epoch: [55]  [140/312]  eta: 0:01:40  lr: 0.003844  min_lr: 0.003844  loss: 4.0287 (3.8683)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0562  max mem: 31830
Epoch: [55]  [150/312]  eta: 0:01:35  lr: 0.003844  min_lr: 0.003844  loss: 4.0272 (3.8759)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0712  max mem: 31830
Epoch: [55]  [160/312]  eta: 0:01:29  lr: 0.003843  min_lr: 0.003843  loss: 4.0570 (3.8789)  weight_decay: 0.0500 (0.0500)  time: 0.6076  data: 0.1464  max mem: 31830
Epoch: [55]  [170/312]  eta: 0:01:22  lr: 0.003843  min_lr: 0.003843  loss: 4.0570 (3.8873)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0761  max mem: 31830
Epoch: [55]  [180/312]  eta: 0:01:16  lr: 0.003843  min_lr: 0.003843  loss: 3.9801 (3.8788)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0633  max mem: 31830
Epoch: [55]  [190/312]  eta: 0:01:11  lr: 0.003843  min_lr: 0.003843  loss: 3.7010 (3.8735)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.1649  max mem: 31830
Epoch: [55]  [200/312]  eta: 0:01:04  lr: 0.003842  min_lr: 0.003842  loss: 3.9943 (3.8698)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.1025  max mem: 31830
Epoch: [55]  [210/312]  eta: 0:00:58  lr: 0.003842  min_lr: 0.003842  loss: 4.0800 (3.8715)  weight_decay: 0.0500 (0.0500)  time: 0.5018  data: 0.0793  max mem: 31830
Epoch: [55]  [220/312]  eta: 0:00:52  lr: 0.003842  min_lr: 0.003842  loss: 3.9128 (3.8559)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0795  max mem: 31830
Epoch: [55]  [230/312]  eta: 0:00:46  lr: 0.003841  min_lr: 0.003841  loss: 3.5478 (3.8581)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.1172  max mem: 31830
Epoch: [55]  [240/312]  eta: 0:00:41  lr: 0.003841  min_lr: 0.003841  loss: 4.0295 (3.8636)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.2060  max mem: 31830
Epoch: [55]  [250/312]  eta: 0:00:35  lr: 0.003841  min_lr: 0.003841  loss: 4.0627 (3.8687)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0904  max mem: 31830
Epoch: [55]  [260/312]  eta: 0:00:29  lr: 0.003841  min_lr: 0.003841  loss: 4.0627 (3.8766)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.1203  max mem: 31830
Epoch: [55]  [270/312]  eta: 0:00:23  lr: 0.003840  min_lr: 0.003840  loss: 4.0357 (3.8759)  weight_decay: 0.0500 (0.0500)  time: 0.6299  data: 0.2097  max mem: 31830
Epoch: [55]  [280/312]  eta: 0:00:18  lr: 0.003840  min_lr: 0.003840  loss: 3.9335 (3.8784)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0924  max mem: 31830
Epoch: [55]  [290/312]  eta: 0:00:12  lr: 0.003840  min_lr: 0.003840  loss: 3.7771 (3.8693)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0931  max mem: 31830
Epoch: [55]  [300/312]  eta: 0:00:06  lr: 0.003839  min_lr: 0.003839  loss: 3.5799 (3.8589)  weight_decay: 0.0500 (0.0500)  time: 0.5009  data: 0.0909  max mem: 31830
Epoch: [55]  [310/312]  eta: 0:00:01  lr: 0.003839  min_lr: 0.003839  loss: 3.9872 (3.8667)  weight_decay: 0.0500 (0.0500)  time: 0.4072  data: 0.0176  max mem: 31830
Epoch: [55]  [311/312]  eta: 0:00:00  lr: 0.003839  min_lr: 0.003839  loss: 3.9872 (3.8630)  weight_decay: 0.0500 (0.0500)  time: 0.4070  data: 0.0176  max mem: 31830
Epoch: [55] Total time: 0:02:54 (0.5599 s / it)
Averaged stats: lr: 0.003839  min_lr: 0.003839  loss: 3.9872 (3.8584)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.6345 (1.6345)  acc1: 69.7917 (69.7917)  acc5: 91.7969 (91.7969)  time: 8.0233  data: 7.8564  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9896 (1.8353)  acc1: 61.4583 (63.3600)  acc5: 84.1146 (85.6960)  time: 1.0648  data: 0.9297  max mem: 31830
Test: Total time: 0:00:09 (1.0755 s / it)
* Acc@1 63.282 Acc@5 85.852 loss 1.834
Accuracy of the model on the 50000 test images: 63.3%
Max accuracy: 65.29%
Epoch: [56]  [  0/312]  eta: 1:03:00  lr: 0.003839  min_lr: 0.003839  loss: 3.5683 (3.5683)  weight_decay: 0.0500 (0.0500)  time: 12.1166  data: 11.2434  max mem: 31830
Epoch: [56]  [ 10/312]  eta: 0:08:35  lr: 0.003839  min_lr: 0.003839  loss: 3.9809 (3.8114)  weight_decay: 0.0500 (0.0500)  time: 1.7054  data: 1.0787  max mem: 31830
Epoch: [56]  [ 20/312]  eta: 0:05:31  lr: 0.003839  min_lr: 0.003839  loss: 4.0677 (3.8448)  weight_decay: 0.0500 (0.0500)  time: 0.5868  data: 0.0314  max mem: 31830
Epoch: [56]  [ 30/312]  eta: 0:04:12  lr: 0.003838  min_lr: 0.003838  loss: 3.8479 (3.7388)  weight_decay: 0.0500 (0.0500)  time: 0.4520  data: 0.0008  max mem: 31830
Epoch: [56]  [ 40/312]  eta: 0:03:30  lr: 0.003838  min_lr: 0.003838  loss: 3.8879 (3.8067)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0009  max mem: 31830
Epoch: [56]  [ 50/312]  eta: 0:03:07  lr: 0.003838  min_lr: 0.003838  loss: 4.2796 (3.8841)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0009  max mem: 31830
Epoch: [56]  [ 60/312]  eta: 0:02:46  lr: 0.003837  min_lr: 0.003837  loss: 4.1711 (3.8401)  weight_decay: 0.0500 (0.0500)  time: 0.4283  data: 0.0010  max mem: 31830
Epoch: [56]  [ 70/312]  eta: 0:02:38  lr: 0.003837  min_lr: 0.003837  loss: 4.1630 (3.8728)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0294  max mem: 31830
Epoch: [56]  [ 80/312]  eta: 0:02:30  lr: 0.003837  min_lr: 0.003837  loss: 3.9160 (3.8391)  weight_decay: 0.0500 (0.0500)  time: 0.6095  data: 0.0292  max mem: 31830
Epoch: [56]  [ 90/312]  eta: 0:02:19  lr: 0.003837  min_lr: 0.003837  loss: 3.6355 (3.8267)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0294  max mem: 31830
Epoch: [56]  [100/312]  eta: 0:02:12  lr: 0.003836  min_lr: 0.003836  loss: 4.1106 (3.8583)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0409  max mem: 31830
Epoch: [56]  [110/312]  eta: 0:02:01  lr: 0.003836  min_lr: 0.003836  loss: 4.1106 (3.8569)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0123  max mem: 31830
Epoch: [56]  [120/312]  eta: 0:01:57  lr: 0.003836  min_lr: 0.003836  loss: 4.0217 (3.8675)  weight_decay: 0.0500 (0.0500)  time: 0.5417  data: 0.0334  max mem: 31830
Epoch: [56]  [130/312]  eta: 0:01:50  lr: 0.003835  min_lr: 0.003835  loss: 4.0217 (3.8735)  weight_decay: 0.0500 (0.0500)  time: 0.6398  data: 0.0509  max mem: 31830
Epoch: [56]  [140/312]  eta: 0:01:42  lr: 0.003835  min_lr: 0.003835  loss: 3.9840 (3.8770)  weight_decay: 0.0500 (0.0500)  time: 0.4955  data: 0.0183  max mem: 31830
Epoch: [56]  [150/312]  eta: 0:01:37  lr: 0.003835  min_lr: 0.003835  loss: 4.0118 (3.8750)  weight_decay: 0.0500 (0.0500)  time: 0.5427  data: 0.0310  max mem: 31830
Epoch: [56]  [160/312]  eta: 0:01:30  lr: 0.003835  min_lr: 0.003835  loss: 3.7170 (3.8625)  weight_decay: 0.0500 (0.0500)  time: 0.6290  data: 0.0312  max mem: 31830
Epoch: [56]  [170/312]  eta: 0:01:23  lr: 0.003834  min_lr: 0.003834  loss: 4.0524 (3.8795)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.0351  max mem: 31830
Epoch: [56]  [180/312]  eta: 0:01:17  lr: 0.003834  min_lr: 0.003834  loss: 4.0220 (3.8674)  weight_decay: 0.0500 (0.0500)  time: 0.5182  data: 0.0495  max mem: 31830
Epoch: [56]  [190/312]  eta: 0:01:10  lr: 0.003834  min_lr: 0.003834  loss: 4.0220 (3.8741)  weight_decay: 0.0500 (0.0500)  time: 0.4899  data: 0.0154  max mem: 31830
Epoch: [56]  [200/312]  eta: 0:01:05  lr: 0.003833  min_lr: 0.003833  loss: 4.0832 (3.8784)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0296  max mem: 31830
Epoch: [56]  [210/312]  eta: 0:00:59  lr: 0.003833  min_lr: 0.003833  loss: 4.0241 (3.8727)  weight_decay: 0.0500 (0.0500)  time: 0.6526  data: 0.0640  max mem: 31830
Epoch: [56]  [220/312]  eta: 0:00:53  lr: 0.003833  min_lr: 0.003833  loss: 3.3171 (3.8506)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0353  max mem: 31830
Epoch: [56]  [230/312]  eta: 0:00:47  lr: 0.003833  min_lr: 0.003833  loss: 3.6893 (3.8577)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0180  max mem: 31830
Epoch: [56]  [240/312]  eta: 0:00:41  lr: 0.003832  min_lr: 0.003832  loss: 4.0484 (3.8588)  weight_decay: 0.0500 (0.0500)  time: 0.5839  data: 0.0181  max mem: 31830
Epoch: [56]  [250/312]  eta: 0:00:35  lr: 0.003832  min_lr: 0.003832  loss: 3.7754 (3.8570)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0225  max mem: 31830
Epoch: [56]  [260/312]  eta: 0:00:29  lr: 0.003832  min_lr: 0.003832  loss: 3.7537 (3.8544)  weight_decay: 0.0500 (0.0500)  time: 0.5456  data: 0.0389  max mem: 31830
Epoch: [56]  [270/312]  eta: 0:00:23  lr: 0.003831  min_lr: 0.003831  loss: 4.0163 (3.8596)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0172  max mem: 31830
Epoch: [56]  [280/312]  eta: 0:00:18  lr: 0.003831  min_lr: 0.003831  loss: 4.0665 (3.8646)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0022  max mem: 31830
Epoch: [56]  [290/312]  eta: 0:00:12  lr: 0.003831  min_lr: 0.003831  loss: 4.0721 (3.8710)  weight_decay: 0.0500 (0.0500)  time: 0.5851  data: 0.0020  max mem: 31830
Epoch: [56]  [300/312]  eta: 0:00:06  lr: 0.003831  min_lr: 0.003831  loss: 4.2680 (3.8742)  weight_decay: 0.0500 (0.0500)  time: 0.4633  data: 0.0002  max mem: 31830
Epoch: [56]  [310/312]  eta: 0:00:01  lr: 0.003830  min_lr: 0.003830  loss: 3.8213 (3.8678)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [56]  [311/312]  eta: 0:00:00  lr: 0.003830  min_lr: 0.003830  loss: 4.0941 (3.8686)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [56] Total time: 0:02:55 (0.5614 s / it)
Averaged stats: lr: 0.003830  min_lr: 0.003830  loss: 4.0941 (3.8738)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.6038 (1.6038)  acc1: 69.2708 (69.2708)  acc5: 91.0156 (91.0156)  time: 8.5396  data: 8.3721  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0833 (1.8524)  acc1: 60.2865 (62.7040)  acc5: 83.0729 (84.9600)  time: 1.0657  data: 0.9303  max mem: 31830
Test: Total time: 0:00:09 (1.0886 s / it)
* Acc@1 62.190 Acc@5 84.946 loss 1.862
Accuracy of the model on the 50000 test images: 62.2%
Max accuracy: 65.29%
Epoch: [57]  [  0/312]  eta: 1:03:36  lr: 0.003830  min_lr: 0.003830  loss: 2.9631 (2.9631)  weight_decay: 0.0500 (0.0500)  time: 12.2329  data: 9.4037  max mem: 31830
Epoch: [57]  [ 10/312]  eta: 0:08:25  lr: 0.003830  min_lr: 0.003830  loss: 3.9805 (3.7712)  weight_decay: 0.0500 (0.0500)  time: 1.6751  data: 1.0616  max mem: 31830
Epoch: [57]  [ 20/312]  eta: 0:05:14  lr: 0.003830  min_lr: 0.003830  loss: 3.9451 (3.8083)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.1141  max mem: 31830
Epoch: [57]  [ 30/312]  eta: 0:04:01  lr: 0.003829  min_lr: 0.003829  loss: 3.9451 (3.8578)  weight_decay: 0.0500 (0.0500)  time: 0.4088  data: 0.0009  max mem: 31830
Epoch: [57]  [ 40/312]  eta: 0:03:22  lr: 0.003829  min_lr: 0.003829  loss: 3.9276 (3.7834)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0009  max mem: 31830
Epoch: [57]  [ 50/312]  eta: 0:03:02  lr: 0.003829  min_lr: 0.003829  loss: 3.6290 (3.7919)  weight_decay: 0.0500 (0.0500)  time: 0.4429  data: 0.0237  max mem: 31830
Epoch: [57]  [ 60/312]  eta: 0:02:42  lr: 0.003828  min_lr: 0.003828  loss: 4.0545 (3.8208)  weight_decay: 0.0500 (0.0500)  time: 0.4394  data: 0.0238  max mem: 31830
Epoch: [57]  [ 70/312]  eta: 0:02:34  lr: 0.003828  min_lr: 0.003828  loss: 3.8809 (3.7995)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0685  max mem: 31830
Epoch: [57]  [ 80/312]  eta: 0:02:27  lr: 0.003828  min_lr: 0.003828  loss: 3.5949 (3.7991)  weight_decay: 0.0500 (0.0500)  time: 0.6019  data: 0.0830  max mem: 31830
Epoch: [57]  [ 90/312]  eta: 0:02:17  lr: 0.003828  min_lr: 0.003828  loss: 3.9328 (3.8202)  weight_decay: 0.0500 (0.0500)  time: 0.5513  data: 0.0638  max mem: 31830
Epoch: [57]  [100/312]  eta: 0:02:10  lr: 0.003827  min_lr: 0.003827  loss: 3.7751 (3.8035)  weight_decay: 0.0500 (0.0500)  time: 0.5409  data: 0.0876  max mem: 31830
Epoch: [57]  [110/312]  eta: 0:02:00  lr: 0.003827  min_lr: 0.003827  loss: 3.8777 (3.8147)  weight_decay: 0.0500 (0.0500)  time: 0.4933  data: 0.0390  max mem: 31830
Epoch: [57]  [120/312]  eta: 0:01:55  lr: 0.003827  min_lr: 0.003827  loss: 4.1418 (3.8229)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0412  max mem: 31830
Epoch: [57]  [130/312]  eta: 0:01:48  lr: 0.003826  min_lr: 0.003826  loss: 4.1418 (3.8413)  weight_decay: 0.0500 (0.0500)  time: 0.5928  data: 0.0413  max mem: 31830
Epoch: [57]  [140/312]  eta: 0:01:40  lr: 0.003826  min_lr: 0.003826  loss: 4.1683 (3.8499)  weight_decay: 0.0500 (0.0500)  time: 0.4982  data: 0.0284  max mem: 31830
Epoch: [57]  [150/312]  eta: 0:01:35  lr: 0.003826  min_lr: 0.003826  loss: 3.8662 (3.8395)  weight_decay: 0.0500 (0.0500)  time: 0.5581  data: 0.0943  max mem: 31830
Epoch: [57]  [160/312]  eta: 0:01:29  lr: 0.003825  min_lr: 0.003825  loss: 3.8853 (3.8513)  weight_decay: 0.0500 (0.0500)  time: 0.5989  data: 0.0666  max mem: 31830
Epoch: [57]  [170/312]  eta: 0:01:22  lr: 0.003825  min_lr: 0.003825  loss: 3.7733 (3.8370)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0662  max mem: 31830
Epoch: [57]  [180/312]  eta: 0:01:16  lr: 0.003825  min_lr: 0.003825  loss: 3.6326 (3.8357)  weight_decay: 0.0500 (0.0500)  time: 0.5450  data: 0.0912  max mem: 31830
Epoch: [57]  [190/312]  eta: 0:01:09  lr: 0.003825  min_lr: 0.003825  loss: 4.0994 (3.8486)  weight_decay: 0.0500 (0.0500)  time: 0.4768  data: 0.0266  max mem: 31830
Epoch: [57]  [200/312]  eta: 0:01:04  lr: 0.003824  min_lr: 0.003824  loss: 3.9730 (3.8325)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0565  max mem: 31830
Epoch: [57]  [210/312]  eta: 0:00:58  lr: 0.003824  min_lr: 0.003824  loss: 3.6371 (3.8250)  weight_decay: 0.0500 (0.0500)  time: 0.5978  data: 0.0557  max mem: 31830
Epoch: [57]  [220/312]  eta: 0:00:52  lr: 0.003824  min_lr: 0.003824  loss: 4.0359 (3.8326)  weight_decay: 0.0500 (0.0500)  time: 0.4959  data: 0.0412  max mem: 31830
Epoch: [57]  [230/312]  eta: 0:00:47  lr: 0.003823  min_lr: 0.003823  loss: 4.1172 (3.8368)  weight_decay: 0.0500 (0.0500)  time: 0.5661  data: 0.1169  max mem: 31830
Epoch: [57]  [240/312]  eta: 0:00:41  lr: 0.003823  min_lr: 0.003823  loss: 3.9416 (3.8447)  weight_decay: 0.0500 (0.0500)  time: 0.5770  data: 0.0765  max mem: 31830
Epoch: [57]  [250/312]  eta: 0:00:35  lr: 0.003823  min_lr: 0.003823  loss: 3.7698 (3.8417)  weight_decay: 0.0500 (0.0500)  time: 0.5036  data: 0.0615  max mem: 31830
Epoch: [57]  [260/312]  eta: 0:00:29  lr: 0.003823  min_lr: 0.003823  loss: 3.7810 (3.8429)  weight_decay: 0.0500 (0.0500)  time: 0.5892  data: 0.1206  max mem: 31830
Epoch: [57]  [270/312]  eta: 0:00:23  lr: 0.003822  min_lr: 0.003822  loss: 4.0374 (3.8354)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0603  max mem: 31830
Epoch: [57]  [280/312]  eta: 0:00:18  lr: 0.003822  min_lr: 0.003822  loss: 4.0030 (3.8382)  weight_decay: 0.0500 (0.0500)  time: 0.4827  data: 0.0481  max mem: 31830
Epoch: [57]  [290/312]  eta: 0:00:12  lr: 0.003822  min_lr: 0.003822  loss: 4.1395 (3.8462)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0474  max mem: 31830
Epoch: [57]  [300/312]  eta: 0:00:06  lr: 0.003821  min_lr: 0.003821  loss: 4.2015 (3.8485)  weight_decay: 0.0500 (0.0500)  time: 0.4737  data: 0.0398  max mem: 31830
Epoch: [57]  [310/312]  eta: 0:00:01  lr: 0.003821  min_lr: 0.003821  loss: 4.2053 (3.8606)  weight_decay: 0.0500 (0.0500)  time: 0.4197  data: 0.0397  max mem: 31830
Epoch: [57]  [311/312]  eta: 0:00:00  lr: 0.003821  min_lr: 0.003821  loss: 4.2053 (3.8620)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [57] Total time: 0:02:53 (0.5573 s / it)
Averaged stats: lr: 0.003821  min_lr: 0.003821  loss: 4.2053 (3.8901)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.7541 (1.7541)  acc1: 67.9688 (67.9688)  acc5: 88.2812 (88.2812)  time: 8.7041  data: 8.5443  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9418 (1.8616)  acc1: 61.1979 (62.4960)  acc5: 85.2865 (85.2480)  time: 1.0864  data: 0.9494  max mem: 31830
Test: Total time: 0:00:10 (1.1141 s / it)
* Acc@1 62.242 Acc@5 84.880 loss 1.867
Accuracy of the model on the 50000 test images: 62.2%
Max accuracy: 65.29%
Epoch: [58]  [  0/312]  eta: 1:02:53  lr: 0.003821  min_lr: 0.003821  loss: 4.2667 (4.2667)  weight_decay: 0.0500 (0.0500)  time: 12.0939  data: 10.6284  max mem: 31830
Epoch: [58]  [ 10/312]  eta: 0:08:28  lr: 0.003821  min_lr: 0.003821  loss: 4.2146 (4.0403)  weight_decay: 0.0500 (0.0500)  time: 1.6838  data: 0.9926  max mem: 31830
Epoch: [58]  [ 20/312]  eta: 0:05:35  lr: 0.003820  min_lr: 0.003820  loss: 4.1305 (3.9737)  weight_decay: 0.0500 (0.0500)  time: 0.6005  data: 0.0432  max mem: 31830
Epoch: [58]  [ 30/312]  eta: 0:04:15  lr: 0.003820  min_lr: 0.003820  loss: 3.9629 (3.9451)  weight_decay: 0.0500 (0.0500)  time: 0.4796  data: 0.0290  max mem: 31830
Epoch: [58]  [ 40/312]  eta: 0:03:32  lr: 0.003820  min_lr: 0.003820  loss: 3.8822 (3.9058)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0019  max mem: 31830
Epoch: [58]  [ 50/312]  eta: 0:03:05  lr: 0.003820  min_lr: 0.003820  loss: 3.8772 (3.8927)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0024  max mem: 31830
Epoch: [58]  [ 60/312]  eta: 0:02:45  lr: 0.003819  min_lr: 0.003819  loss: 3.8772 (3.8826)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0012  max mem: 31830
Epoch: [58]  [ 70/312]  eta: 0:02:33  lr: 0.003819  min_lr: 0.003819  loss: 3.8851 (3.8682)  weight_decay: 0.0500 (0.0500)  time: 0.4446  data: 0.0411  max mem: 31830
Epoch: [58]  [ 80/312]  eta: 0:02:25  lr: 0.003819  min_lr: 0.003819  loss: 4.0794 (3.8949)  weight_decay: 0.0500 (0.0500)  time: 0.5338  data: 0.1304  max mem: 31830
Epoch: [58]  [ 90/312]  eta: 0:02:14  lr: 0.003818  min_lr: 0.003818  loss: 4.1043 (3.8890)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0902  max mem: 31830
Epoch: [58]  [100/312]  eta: 0:02:08  lr: 0.003818  min_lr: 0.003818  loss: 4.0803 (3.9016)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0886  max mem: 31830
Epoch: [58]  [110/312]  eta: 0:01:58  lr: 0.003818  min_lr: 0.003818  loss: 4.0999 (3.9036)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.0884  max mem: 31830
Epoch: [58]  [120/312]  eta: 0:01:54  lr: 0.003817  min_lr: 0.003817  loss: 4.0345 (3.9229)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0774  max mem: 31830
Epoch: [58]  [130/312]  eta: 0:01:48  lr: 0.003817  min_lr: 0.003817  loss: 4.0459 (3.9276)  weight_decay: 0.0500 (0.0500)  time: 0.6427  data: 0.1384  max mem: 31830
Epoch: [58]  [140/312]  eta: 0:01:39  lr: 0.003817  min_lr: 0.003817  loss: 4.1704 (3.9323)  weight_decay: 0.0500 (0.0500)  time: 0.5052  data: 0.0617  max mem: 31830
Epoch: [58]  [150/312]  eta: 0:01:34  lr: 0.003817  min_lr: 0.003817  loss: 4.1756 (3.9390)  weight_decay: 0.0500 (0.0500)  time: 0.5107  data: 0.0458  max mem: 31830
Epoch: [58]  [160/312]  eta: 0:01:28  lr: 0.003816  min_lr: 0.003816  loss: 4.2680 (3.9511)  weight_decay: 0.0500 (0.0500)  time: 0.5870  data: 0.0658  max mem: 31830
Epoch: [58]  [170/312]  eta: 0:01:21  lr: 0.003816  min_lr: 0.003816  loss: 4.1523 (3.9615)  weight_decay: 0.0500 (0.0500)  time: 0.4968  data: 0.0434  max mem: 31830
Epoch: [58]  [180/312]  eta: 0:01:16  lr: 0.003816  min_lr: 0.003816  loss: 4.1523 (3.9681)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0649  max mem: 31830
Epoch: [58]  [190/312]  eta: 0:01:09  lr: 0.003815  min_lr: 0.003815  loss: 4.1701 (3.9701)  weight_decay: 0.0500 (0.0500)  time: 0.4977  data: 0.0421  max mem: 31830
Epoch: [58]  [200/312]  eta: 0:01:03  lr: 0.003815  min_lr: 0.003815  loss: 3.7820 (3.9550)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0597  max mem: 31830
Epoch: [58]  [210/312]  eta: 0:00:58  lr: 0.003815  min_lr: 0.003815  loss: 3.7321 (3.9597)  weight_decay: 0.0500 (0.0500)  time: 0.6325  data: 0.1052  max mem: 31830
Epoch: [58]  [220/312]  eta: 0:00:51  lr: 0.003814  min_lr: 0.003814  loss: 4.0153 (3.9555)  weight_decay: 0.0500 (0.0500)  time: 0.5037  data: 0.0462  max mem: 31830
Epoch: [58]  [230/312]  eta: 0:00:46  lr: 0.003814  min_lr: 0.003814  loss: 4.0528 (3.9592)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0620  max mem: 31830
Epoch: [58]  [240/312]  eta: 0:00:40  lr: 0.003814  min_lr: 0.003814  loss: 4.1048 (3.9586)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.0862  max mem: 31830
Epoch: [58]  [250/312]  eta: 0:00:34  lr: 0.003813  min_lr: 0.003813  loss: 3.8534 (3.9450)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0250  max mem: 31830
Epoch: [58]  [260/312]  eta: 0:00:29  lr: 0.003813  min_lr: 0.003813  loss: 3.5108 (3.9370)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.0262  max mem: 31830
Epoch: [58]  [270/312]  eta: 0:00:23  lr: 0.003813  min_lr: 0.003813  loss: 3.8548 (3.9329)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0261  max mem: 31830
Epoch: [58]  [280/312]  eta: 0:00:17  lr: 0.003813  min_lr: 0.003813  loss: 3.9472 (3.9329)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0304  max mem: 31830
Epoch: [58]  [290/312]  eta: 0:00:12  lr: 0.003812  min_lr: 0.003812  loss: 4.1153 (3.9380)  weight_decay: 0.0500 (0.0500)  time: 0.6078  data: 0.0511  max mem: 31830
Epoch: [58]  [300/312]  eta: 0:00:06  lr: 0.003812  min_lr: 0.003812  loss: 4.1493 (3.9362)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0211  max mem: 31830
Epoch: [58]  [310/312]  eta: 0:00:01  lr: 0.003812  min_lr: 0.003812  loss: 4.0120 (3.9371)  weight_decay: 0.0500 (0.0500)  time: 0.3909  data: 0.0001  max mem: 31830
Epoch: [58]  [311/312]  eta: 0:00:00  lr: 0.003812  min_lr: 0.003812  loss: 4.0294 (3.9374)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [58] Total time: 0:02:53 (0.5547 s / it)
Averaged stats: lr: 0.003812  min_lr: 0.003812  loss: 4.0294 (3.8836)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.6479 (1.6479)  acc1: 69.2708 (69.2708)  acc5: 90.3646 (90.3646)  time: 8.4996  data: 8.3370  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0033 (1.8885)  acc1: 59.7656 (62.1760)  acc5: 84.5052 (84.9760)  time: 1.0609  data: 0.9264  max mem: 31830
Test: Total time: 0:00:09 (1.0709 s / it)
* Acc@1 62.476 Acc@5 85.336 loss 1.874
Accuracy of the model on the 50000 test images: 62.5%
Max accuracy: 65.29%
Epoch: [59]  [  0/312]  eta: 1:02:15  lr: 0.003812  min_lr: 0.003812  loss: 3.6615 (3.6615)  weight_decay: 0.0500 (0.0500)  time: 11.9720  data: 9.1303  max mem: 31830
Epoch: [59]  [ 10/312]  eta: 0:08:16  lr: 0.003811  min_lr: 0.003811  loss: 4.2690 (4.0270)  weight_decay: 0.0500 (0.0500)  time: 1.6451  data: 1.0290  max mem: 31830
Epoch: [59]  [ 20/312]  eta: 0:05:33  lr: 0.003811  min_lr: 0.003811  loss: 3.8102 (3.8670)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.1436  max mem: 31830
Epoch: [59]  [ 30/312]  eta: 0:04:13  lr: 0.003811  min_lr: 0.003811  loss: 3.7772 (3.8708)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0345  max mem: 31830
Epoch: [59]  [ 40/312]  eta: 0:03:31  lr: 0.003810  min_lr: 0.003810  loss: 3.9995 (3.8407)  weight_decay: 0.0500 (0.0500)  time: 0.3917  data: 0.0006  max mem: 31830
Epoch: [59]  [ 50/312]  eta: 0:03:04  lr: 0.003810  min_lr: 0.003810  loss: 3.5621 (3.8062)  weight_decay: 0.0500 (0.0500)  time: 0.4024  data: 0.0007  max mem: 31830
Epoch: [59]  [ 60/312]  eta: 0:02:44  lr: 0.003810  min_lr: 0.003810  loss: 3.5621 (3.7755)  weight_decay: 0.0500 (0.0500)  time: 0.4026  data: 0.0007  max mem: 31830
Epoch: [59]  [ 70/312]  eta: 0:02:36  lr: 0.003809  min_lr: 0.003809  loss: 3.9721 (3.8413)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0146  max mem: 31830
Epoch: [59]  [ 80/312]  eta: 0:02:28  lr: 0.003809  min_lr: 0.003809  loss: 4.1410 (3.8296)  weight_decay: 0.0500 (0.0500)  time: 0.5928  data: 0.0408  max mem: 31830
Epoch: [59]  [ 90/312]  eta: 0:02:15  lr: 0.003809  min_lr: 0.003809  loss: 3.6968 (3.8487)  weight_decay: 0.0500 (0.0500)  time: 0.4981  data: 0.0269  max mem: 31830
Epoch: [59]  [100/312]  eta: 0:02:12  lr: 0.003809  min_lr: 0.003809  loss: 4.0841 (3.8561)  weight_decay: 0.0500 (0.0500)  time: 0.5692  data: 0.0598  max mem: 31830
Epoch: [59]  [110/312]  eta: 0:02:02  lr: 0.003808  min_lr: 0.003808  loss: 4.1444 (3.8764)  weight_decay: 0.0500 (0.0500)  time: 0.5676  data: 0.0597  max mem: 31830
Epoch: [59]  [120/312]  eta: 0:01:55  lr: 0.003808  min_lr: 0.003808  loss: 4.0564 (3.8788)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0226  max mem: 31830
Epoch: [59]  [130/312]  eta: 0:01:50  lr: 0.003808  min_lr: 0.003808  loss: 3.6512 (3.8577)  weight_decay: 0.0500 (0.0500)  time: 0.6371  data: 0.0629  max mem: 31830
Epoch: [59]  [140/312]  eta: 0:01:42  lr: 0.003807  min_lr: 0.003807  loss: 3.4867 (3.8418)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0409  max mem: 31830
Epoch: [59]  [150/312]  eta: 0:01:35  lr: 0.003807  min_lr: 0.003807  loss: 4.0152 (3.8580)  weight_decay: 0.0500 (0.0500)  time: 0.4684  data: 0.0233  max mem: 31830
Epoch: [59]  [160/312]  eta: 0:01:30  lr: 0.003807  min_lr: 0.003807  loss: 4.0152 (3.8370)  weight_decay: 0.0500 (0.0500)  time: 0.5791  data: 0.0672  max mem: 31830
Epoch: [59]  [170/312]  eta: 0:01:22  lr: 0.003806  min_lr: 0.003806  loss: 3.6820 (3.8413)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0449  max mem: 31830
Epoch: [59]  [180/312]  eta: 0:01:17  lr: 0.003806  min_lr: 0.003806  loss: 3.7362 (3.8368)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0557  max mem: 31830
Epoch: [59]  [190/312]  eta: 0:01:10  lr: 0.003806  min_lr: 0.003806  loss: 3.7362 (3.8356)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0553  max mem: 31830
Epoch: [59]  [200/312]  eta: 0:01:04  lr: 0.003805  min_lr: 0.003805  loss: 4.1139 (3.8428)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0685  max mem: 31830
Epoch: [59]  [210/312]  eta: 0:00:58  lr: 0.003805  min_lr: 0.003805  loss: 4.0772 (3.8406)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.1091  max mem: 31830
Epoch: [59]  [220/312]  eta: 0:00:52  lr: 0.003805  min_lr: 0.003805  loss: 3.8652 (3.8207)  weight_decay: 0.0500 (0.0500)  time: 0.4725  data: 0.0412  max mem: 31830
Epoch: [59]  [230/312]  eta: 0:00:46  lr: 0.003805  min_lr: 0.003805  loss: 3.4418 (3.8213)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0644  max mem: 31830
Epoch: [59]  [240/312]  eta: 0:00:41  lr: 0.003804  min_lr: 0.003804  loss: 3.9909 (3.8313)  weight_decay: 0.0500 (0.0500)  time: 0.6325  data: 0.1077  max mem: 31830
Epoch: [59]  [250/312]  eta: 0:00:35  lr: 0.003804  min_lr: 0.003804  loss: 4.1619 (3.8370)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0569  max mem: 31830
Epoch: [59]  [260/312]  eta: 0:00:29  lr: 0.003804  min_lr: 0.003804  loss: 4.1275 (3.8399)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0654  max mem: 31830
Epoch: [59]  [270/312]  eta: 0:00:23  lr: 0.003803  min_lr: 0.003803  loss: 3.8191 (3.8305)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0526  max mem: 31830
Epoch: [59]  [280/312]  eta: 0:00:18  lr: 0.003803  min_lr: 0.003803  loss: 3.9640 (3.8374)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0377  max mem: 31830
Epoch: [59]  [290/312]  eta: 0:00:12  lr: 0.003803  min_lr: 0.003803  loss: 4.1132 (3.8446)  weight_decay: 0.0500 (0.0500)  time: 0.5679  data: 0.0805  max mem: 31830
Epoch: [59]  [300/312]  eta: 0:00:06  lr: 0.003802  min_lr: 0.003802  loss: 4.0481 (3.8369)  weight_decay: 0.0500 (0.0500)  time: 0.4783  data: 0.0433  max mem: 31830
Epoch: [59]  [310/312]  eta: 0:00:01  lr: 0.003802  min_lr: 0.003802  loss: 3.4925 (3.8299)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [59]  [311/312]  eta: 0:00:00  lr: 0.003802  min_lr: 0.003802  loss: 3.5002 (3.8301)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [59] Total time: 0:02:53 (0.5573 s / it)
Averaged stats: lr: 0.003802  min_lr: 0.003802  loss: 3.5002 (3.8681)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5025 (1.5025)  acc1: 69.9219 (69.9219)  acc5: 89.3229 (89.3229)  time: 8.4021  data: 8.2348  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8639 (1.6918)  acc1: 61.7188 (63.6320)  acc5: 84.1146 (85.6800)  time: 1.0570  data: 0.9151  max mem: 31830
Test: Total time: 0:00:09 (1.0879 s / it)
* Acc@1 63.566 Acc@5 85.916 loss 1.692
Accuracy of the model on the 50000 test images: 63.6%
Max accuracy: 65.29%
Epoch: [60]  [  0/312]  eta: 0:59:01  lr: 0.003802  min_lr: 0.003802  loss: 3.7834 (3.7834)  weight_decay: 0.0500 (0.0500)  time: 11.3501  data: 9.6185  max mem: 31830
Epoch: [60]  [ 10/312]  eta: 0:08:00  lr: 0.003802  min_lr: 0.003802  loss: 3.7834 (3.8598)  weight_decay: 0.0500 (0.0500)  time: 1.5917  data: 0.9378  max mem: 31830
Epoch: [60]  [ 20/312]  eta: 0:05:24  lr: 0.003801  min_lr: 0.003801  loss: 3.7686 (3.7665)  weight_decay: 0.0500 (0.0500)  time: 0.5994  data: 0.0544  max mem: 31830
Epoch: [60]  [ 30/312]  eta: 0:04:08  lr: 0.003801  min_lr: 0.003801  loss: 3.8503 (3.7694)  weight_decay: 0.0500 (0.0500)  time: 0.4919  data: 0.0198  max mem: 31830
Epoch: [60]  [ 40/312]  eta: 0:03:28  lr: 0.003801  min_lr: 0.003801  loss: 3.7461 (3.7482)  weight_decay: 0.0500 (0.0500)  time: 0.4010  data: 0.0007  max mem: 31830
Epoch: [60]  [ 50/312]  eta: 0:03:07  lr: 0.003800  min_lr: 0.003800  loss: 3.8716 (3.7898)  weight_decay: 0.0500 (0.0500)  time: 0.4602  data: 0.0007  max mem: 31830
Epoch: [60]  [ 60/312]  eta: 0:02:47  lr: 0.003800  min_lr: 0.003800  loss: 4.0408 (3.8074)  weight_decay: 0.0500 (0.0500)  time: 0.4584  data: 0.0008  max mem: 31830
Epoch: [60]  [ 70/312]  eta: 0:02:38  lr: 0.003800  min_lr: 0.003800  loss: 3.8936 (3.8212)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0010  max mem: 31830
Epoch: [60]  [ 80/312]  eta: 0:02:27  lr: 0.003799  min_lr: 0.003799  loss: 4.0143 (3.8459)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0010  max mem: 31830
Epoch: [60]  [ 90/312]  eta: 0:02:18  lr: 0.003799  min_lr: 0.003799  loss: 4.0143 (3.8533)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0119  max mem: 31830
Epoch: [60]  [100/312]  eta: 0:02:12  lr: 0.003799  min_lr: 0.003799  loss: 3.7894 (3.8401)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.0119  max mem: 31830
Epoch: [60]  [110/312]  eta: 0:02:02  lr: 0.003799  min_lr: 0.003799  loss: 3.7677 (3.8363)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0063  max mem: 31830
Epoch: [60]  [120/312]  eta: 0:01:56  lr: 0.003798  min_lr: 0.003798  loss: 4.0528 (3.8345)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0303  max mem: 31830
Epoch: [60]  [130/312]  eta: 0:01:50  lr: 0.003798  min_lr: 0.003798  loss: 3.8668 (3.8098)  weight_decay: 0.0500 (0.0500)  time: 0.6290  data: 0.0248  max mem: 31830
Epoch: [60]  [140/312]  eta: 0:01:42  lr: 0.003798  min_lr: 0.003798  loss: 3.8668 (3.8152)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0217  max mem: 31830
Epoch: [60]  [150/312]  eta: 0:01:37  lr: 0.003797  min_lr: 0.003797  loss: 4.0307 (3.8282)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0415  max mem: 31830
Epoch: [60]  [160/312]  eta: 0:01:29  lr: 0.003797  min_lr: 0.003797  loss: 4.1264 (3.8337)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0208  max mem: 31830
Epoch: [60]  [170/312]  eta: 0:01:23  lr: 0.003797  min_lr: 0.003797  loss: 4.0636 (3.8555)  weight_decay: 0.0500 (0.0500)  time: 0.4919  data: 0.0106  max mem: 31830
Epoch: [60]  [180/312]  eta: 0:01:17  lr: 0.003796  min_lr: 0.003796  loss: 4.0828 (3.8626)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.0212  max mem: 31830
Epoch: [60]  [190/312]  eta: 0:01:10  lr: 0.003796  min_lr: 0.003796  loss: 3.9039 (3.8548)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0115  max mem: 31830
Epoch: [60]  [200/312]  eta: 0:01:05  lr: 0.003796  min_lr: 0.003796  loss: 3.8875 (3.8510)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0122  max mem: 31830
Epoch: [60]  [210/312]  eta: 0:00:59  lr: 0.003795  min_lr: 0.003795  loss: 3.9679 (3.8613)  weight_decay: 0.0500 (0.0500)  time: 0.6065  data: 0.0122  max mem: 31830
Epoch: [60]  [220/312]  eta: 0:00:52  lr: 0.003795  min_lr: 0.003795  loss: 3.8744 (3.8496)  weight_decay: 0.0500 (0.0500)  time: 0.4950  data: 0.0008  max mem: 31830
Epoch: [60]  [230/312]  eta: 0:00:47  lr: 0.003795  min_lr: 0.003795  loss: 3.8206 (3.8510)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0128  max mem: 31830
Epoch: [60]  [240/312]  eta: 0:00:41  lr: 0.003794  min_lr: 0.003794  loss: 3.6155 (3.8375)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.0129  max mem: 31830
Epoch: [60]  [250/312]  eta: 0:00:35  lr: 0.003794  min_lr: 0.003794  loss: 3.8355 (3.8444)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0243  max mem: 31830
Epoch: [60]  [260/312]  eta: 0:00:29  lr: 0.003794  min_lr: 0.003794  loss: 4.0412 (3.8494)  weight_decay: 0.0500 (0.0500)  time: 0.5729  data: 0.0348  max mem: 31830
Epoch: [60]  [270/312]  eta: 0:00:23  lr: 0.003793  min_lr: 0.003793  loss: 4.1157 (3.8457)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0241  max mem: 31830
Epoch: [60]  [280/312]  eta: 0:00:18  lr: 0.003793  min_lr: 0.003793  loss: 3.8886 (3.8421)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.0299  max mem: 31830
Epoch: [60]  [290/312]  eta: 0:00:12  lr: 0.003793  min_lr: 0.003793  loss: 3.9538 (3.8474)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0169  max mem: 31830
Epoch: [60]  [300/312]  eta: 0:00:06  lr: 0.003793  min_lr: 0.003793  loss: 3.9584 (3.8475)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0002  max mem: 31830
Epoch: [60]  [310/312]  eta: 0:00:01  lr: 0.003792  min_lr: 0.003792  loss: 3.9584 (3.8441)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [60]  [311/312]  eta: 0:00:00  lr: 0.003792  min_lr: 0.003792  loss: 3.9726 (3.8447)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [60] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.003792  min_lr: 0.003792  loss: 3.9726 (3.8710)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.6115 (1.6115)  acc1: 70.7031 (70.7031)  acc5: 90.7552 (90.7552)  time: 8.4058  data: 8.2455  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0176 (1.8979)  acc1: 61.5885 (63.5360)  acc5: 83.5938 (85.8080)  time: 1.0502  data: 0.9162  max mem: 31830
Test: Total time: 0:00:09 (1.0598 s / it)
* Acc@1 63.450 Acc@5 85.828 loss 1.896
Accuracy of the model on the 50000 test images: 63.5%
Max accuracy: 65.29%
Epoch: [61]  [  0/312]  eta: 1:00:57  lr: 0.003792  min_lr: 0.003792  loss: 4.2458 (4.2458)  weight_decay: 0.0500 (0.0500)  time: 11.7240  data: 8.8361  max mem: 31830
Epoch: [61]  [ 10/312]  eta: 0:08:28  lr: 0.003792  min_lr: 0.003792  loss: 3.5218 (3.5997)  weight_decay: 0.0500 (0.0500)  time: 1.6849  data: 1.0101  max mem: 31830
Epoch: [61]  [ 20/312]  eta: 0:05:22  lr: 0.003792  min_lr: 0.003792  loss: 3.6271 (3.7259)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.1141  max mem: 31830
Epoch: [61]  [ 30/312]  eta: 0:04:06  lr: 0.003791  min_lr: 0.003791  loss: 3.9446 (3.8023)  weight_decay: 0.0500 (0.0500)  time: 0.4288  data: 0.0008  max mem: 31830
Epoch: [61]  [ 40/312]  eta: 0:03:25  lr: 0.003791  min_lr: 0.003791  loss: 3.9867 (3.8667)  weight_decay: 0.0500 (0.0500)  time: 0.3926  data: 0.0007  max mem: 31830
Epoch: [61]  [ 50/312]  eta: 0:03:05  lr: 0.003791  min_lr: 0.003791  loss: 4.1487 (3.9002)  weight_decay: 0.0500 (0.0500)  time: 0.4462  data: 0.0012  max mem: 31830
Epoch: [61]  [ 60/312]  eta: 0:02:44  lr: 0.003790  min_lr: 0.003790  loss: 3.8253 (3.8547)  weight_decay: 0.0500 (0.0500)  time: 0.4453  data: 0.0013  max mem: 31830
Epoch: [61]  [ 70/312]  eta: 0:02:36  lr: 0.003790  min_lr: 0.003790  loss: 3.8253 (3.9009)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0418  max mem: 31830
Epoch: [61]  [ 80/312]  eta: 0:02:24  lr: 0.003790  min_lr: 0.003790  loss: 4.2291 (3.9349)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0418  max mem: 31830
Epoch: [61]  [ 90/312]  eta: 0:02:16  lr: 0.003789  min_lr: 0.003789  loss: 4.1007 (3.9143)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0537  max mem: 31830
Epoch: [61]  [100/312]  eta: 0:02:10  lr: 0.003789  min_lr: 0.003789  loss: 3.7251 (3.8738)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.1045  max mem: 31830
Epoch: [61]  [110/312]  eta: 0:02:00  lr: 0.003789  min_lr: 0.003789  loss: 3.7159 (3.8629)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0515  max mem: 31830
Epoch: [61]  [120/312]  eta: 0:01:54  lr: 0.003788  min_lr: 0.003788  loss: 3.9276 (3.8634)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0490  max mem: 31830
Epoch: [61]  [130/312]  eta: 0:01:48  lr: 0.003788  min_lr: 0.003788  loss: 4.0547 (3.8555)  weight_decay: 0.0500 (0.0500)  time: 0.6222  data: 0.0979  max mem: 31830
Epoch: [61]  [140/312]  eta: 0:01:40  lr: 0.003788  min_lr: 0.003788  loss: 4.1857 (3.8746)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0497  max mem: 31830
Epoch: [61]  [150/312]  eta: 0:01:35  lr: 0.003787  min_lr: 0.003787  loss: 4.1994 (3.8819)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0702  max mem: 31830
Epoch: [61]  [160/312]  eta: 0:01:28  lr: 0.003787  min_lr: 0.003787  loss: 4.1178 (3.8861)  weight_decay: 0.0500 (0.0500)  time: 0.5855  data: 0.0703  max mem: 31830
Epoch: [61]  [170/312]  eta: 0:01:22  lr: 0.003787  min_lr: 0.003787  loss: 4.1004 (3.8914)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0515  max mem: 31830
Epoch: [61]  [180/312]  eta: 0:01:16  lr: 0.003786  min_lr: 0.003786  loss: 4.1797 (3.8950)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.1239  max mem: 31830
Epoch: [61]  [190/312]  eta: 0:01:09  lr: 0.003786  min_lr: 0.003786  loss: 4.1214 (3.9081)  weight_decay: 0.0500 (0.0500)  time: 0.5186  data: 0.0732  max mem: 31830
Epoch: [61]  [200/312]  eta: 0:01:04  lr: 0.003786  min_lr: 0.003786  loss: 4.0917 (3.9198)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0659  max mem: 31830
Epoch: [61]  [210/312]  eta: 0:00:58  lr: 0.003785  min_lr: 0.003785  loss: 4.0707 (3.9191)  weight_decay: 0.0500 (0.0500)  time: 0.6155  data: 0.1497  max mem: 31830
Epoch: [61]  [220/312]  eta: 0:00:52  lr: 0.003785  min_lr: 0.003785  loss: 3.9686 (3.9050)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0845  max mem: 31830
Epoch: [61]  [230/312]  eta: 0:00:46  lr: 0.003785  min_lr: 0.003785  loss: 3.8871 (3.9002)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0608  max mem: 31830
Epoch: [61]  [240/312]  eta: 0:00:40  lr: 0.003784  min_lr: 0.003784  loss: 3.8266 (3.8922)  weight_decay: 0.0500 (0.0500)  time: 0.5687  data: 0.0608  max mem: 31830
Epoch: [61]  [250/312]  eta: 0:00:35  lr: 0.003784  min_lr: 0.003784  loss: 3.5165 (3.8807)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0634  max mem: 31830
Epoch: [61]  [260/312]  eta: 0:00:29  lr: 0.003784  min_lr: 0.003784  loss: 3.9091 (3.8851)  weight_decay: 0.0500 (0.0500)  time: 0.5568  data: 0.1175  max mem: 31830
Epoch: [61]  [270/312]  eta: 0:00:23  lr: 0.003783  min_lr: 0.003783  loss: 4.0259 (3.8864)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0551  max mem: 31830
Epoch: [61]  [280/312]  eta: 0:00:18  lr: 0.003783  min_lr: 0.003783  loss: 3.9468 (3.8874)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0694  max mem: 31830
Epoch: [61]  [290/312]  eta: 0:00:12  lr: 0.003783  min_lr: 0.003783  loss: 3.8639 (3.8826)  weight_decay: 0.0500 (0.0500)  time: 0.6363  data: 0.1471  max mem: 31830
Epoch: [61]  [300/312]  eta: 0:00:06  lr: 0.003782  min_lr: 0.003782  loss: 3.7010 (3.8740)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0784  max mem: 31830
Epoch: [61]  [310/312]  eta: 0:00:01  lr: 0.003782  min_lr: 0.003782  loss: 3.8064 (3.8775)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [61]  [311/312]  eta: 0:00:00  lr: 0.003782  min_lr: 0.003782  loss: 3.8375 (3.8782)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [61] Total time: 0:02:54 (0.5580 s / it)
Averaged stats: lr: 0.003782  min_lr: 0.003782  loss: 3.8375 (3.8801)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5555 (1.5555)  acc1: 68.8802 (68.8802)  acc5: 89.1927 (89.1927)  time: 8.4171  data: 8.2328  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8693 (1.7765)  acc1: 62.7604 (62.6720)  acc5: 85.6771 (85.5360)  time: 1.0613  data: 0.9234  max mem: 31830
Test: Total time: 0:00:09 (1.0728 s / it)
* Acc@1 62.640 Acc@5 85.778 loss 1.783
Accuracy of the model on the 50000 test images: 62.6%
Max accuracy: 65.29%
Epoch: [62]  [  0/312]  eta: 1:02:12  lr: 0.003782  min_lr: 0.003782  loss: 4.2691 (4.2691)  weight_decay: 0.0500 (0.0500)  time: 11.9646  data: 11.2219  max mem: 31830
Epoch: [62]  [ 10/312]  eta: 0:08:10  lr: 0.003782  min_lr: 0.003782  loss: 4.0756 (3.8849)  weight_decay: 0.0500 (0.0500)  time: 1.6237  data: 1.0213  max mem: 31830
Epoch: [62]  [ 20/312]  eta: 0:05:23  lr: 0.003781  min_lr: 0.003781  loss: 4.0309 (3.9060)  weight_decay: 0.0500 (0.0500)  time: 0.5651  data: 0.0269  max mem: 31830
Epoch: [62]  [ 30/312]  eta: 0:04:07  lr: 0.003781  min_lr: 0.003781  loss: 3.7136 (3.7940)  weight_decay: 0.0500 (0.0500)  time: 0.4677  data: 0.0266  max mem: 31830
Epoch: [62]  [ 40/312]  eta: 0:03:26  lr: 0.003781  min_lr: 0.003781  loss: 3.7136 (3.7713)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0007  max mem: 31830
Epoch: [62]  [ 50/312]  eta: 0:03:04  lr: 0.003780  min_lr: 0.003780  loss: 3.6944 (3.7152)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0132  max mem: 31830
Epoch: [62]  [ 60/312]  eta: 0:02:44  lr: 0.003780  min_lr: 0.003780  loss: 3.7730 (3.7648)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0133  max mem: 31830
Epoch: [62]  [ 70/312]  eta: 0:02:34  lr: 0.003780  min_lr: 0.003780  loss: 4.0499 (3.7917)  weight_decay: 0.0500 (0.0500)  time: 0.4748  data: 0.0527  max mem: 31830
Epoch: [62]  [ 80/312]  eta: 0:02:26  lr: 0.003779  min_lr: 0.003779  loss: 4.1598 (3.8565)  weight_decay: 0.0500 (0.0500)  time: 0.5624  data: 0.1256  max mem: 31830
Epoch: [62]  [ 90/312]  eta: 0:02:14  lr: 0.003779  min_lr: 0.003779  loss: 4.1543 (3.8495)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0736  max mem: 31830
Epoch: [62]  [100/312]  eta: 0:02:10  lr: 0.003779  min_lr: 0.003779  loss: 4.0217 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.0820  max mem: 31830
Epoch: [62]  [110/312]  eta: 0:02:00  lr: 0.003778  min_lr: 0.003778  loss: 4.1091 (3.8792)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0821  max mem: 31830
Epoch: [62]  [120/312]  eta: 0:01:54  lr: 0.003778  min_lr: 0.003778  loss: 4.0955 (3.8813)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0601  max mem: 31830
Epoch: [62]  [130/312]  eta: 0:01:49  lr: 0.003778  min_lr: 0.003778  loss: 4.0349 (3.8878)  weight_decay: 0.0500 (0.0500)  time: 0.6243  data: 0.1275  max mem: 31830
Epoch: [62]  [140/312]  eta: 0:01:40  lr: 0.003777  min_lr: 0.003777  loss: 4.1910 (3.9023)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0803  max mem: 31830
Epoch: [62]  [150/312]  eta: 0:01:35  lr: 0.003777  min_lr: 0.003777  loss: 4.0932 (3.8994)  weight_decay: 0.0500 (0.0500)  time: 0.5409  data: 0.0891  max mem: 31830
Epoch: [62]  [160/312]  eta: 0:01:29  lr: 0.003777  min_lr: 0.003777  loss: 3.8921 (3.8893)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.0770  max mem: 31830
Epoch: [62]  [170/312]  eta: 0:01:22  lr: 0.003776  min_lr: 0.003776  loss: 3.8631 (3.8809)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0449  max mem: 31830
Epoch: [62]  [180/312]  eta: 0:01:17  lr: 0.003776  min_lr: 0.003776  loss: 4.0129 (3.8825)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.0567  max mem: 31830
Epoch: [62]  [190/312]  eta: 0:01:10  lr: 0.003776  min_lr: 0.003776  loss: 3.8774 (3.8871)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0126  max mem: 31830
Epoch: [62]  [200/312]  eta: 0:01:04  lr: 0.003775  min_lr: 0.003775  loss: 4.1288 (3.8910)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0145  max mem: 31830
Epoch: [62]  [210/312]  eta: 0:00:58  lr: 0.003775  min_lr: 0.003775  loss: 4.1288 (3.8912)  weight_decay: 0.0500 (0.0500)  time: 0.5656  data: 0.0145  max mem: 31830
Epoch: [62]  [220/312]  eta: 0:00:52  lr: 0.003775  min_lr: 0.003775  loss: 4.0500 (3.8936)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0008  max mem: 31830
Epoch: [62]  [230/312]  eta: 0:00:47  lr: 0.003774  min_lr: 0.003774  loss: 4.0500 (3.9024)  weight_decay: 0.0500 (0.0500)  time: 0.5659  data: 0.0059  max mem: 31830
Epoch: [62]  [240/312]  eta: 0:00:41  lr: 0.003774  min_lr: 0.003774  loss: 4.0070 (3.8965)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0059  max mem: 31830
Epoch: [62]  [250/312]  eta: 0:00:35  lr: 0.003774  min_lr: 0.003774  loss: 3.8865 (3.8971)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0008  max mem: 31830
Epoch: [62]  [260/312]  eta: 0:00:29  lr: 0.003774  min_lr: 0.003774  loss: 3.9158 (3.8979)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0011  max mem: 31830
Epoch: [62]  [270/312]  eta: 0:00:23  lr: 0.003773  min_lr: 0.003773  loss: 3.9665 (3.9007)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0017  max mem: 31830
Epoch: [62]  [280/312]  eta: 0:00:18  lr: 0.003773  min_lr: 0.003773  loss: 3.8810 (3.9021)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0163  max mem: 31830
Epoch: [62]  [290/312]  eta: 0:00:12  lr: 0.003773  min_lr: 0.003773  loss: 4.1571 (3.9028)  weight_decay: 0.0500 (0.0500)  time: 0.5364  data: 0.0236  max mem: 31830
Epoch: [62]  [300/312]  eta: 0:00:06  lr: 0.003772  min_lr: 0.003772  loss: 4.0152 (3.8961)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0085  max mem: 31830
Epoch: [62]  [310/312]  eta: 0:00:01  lr: 0.003772  min_lr: 0.003772  loss: 3.5960 (3.8885)  weight_decay: 0.0500 (0.0500)  time: 0.4196  data: 0.0001  max mem: 31830
Epoch: [62]  [311/312]  eta: 0:00:00  lr: 0.003772  min_lr: 0.003772  loss: 3.5960 (3.8854)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [62] Total time: 0:02:53 (0.5568 s / it)
Averaged stats: lr: 0.003772  min_lr: 0.003772  loss: 3.5960 (3.8446)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.3999 (1.3999)  acc1: 70.9635 (70.9635)  acc5: 91.1458 (91.1458)  time: 8.1972  data: 8.0296  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9644 (1.7716)  acc1: 61.0677 (63.8080)  acc5: 84.3750 (85.4560)  time: 1.0279  data: 0.8923  max mem: 31830
Test: Total time: 0:00:09 (1.0409 s / it)
* Acc@1 63.786 Acc@5 86.054 loss 1.774
Accuracy of the model on the 50000 test images: 63.8%
Max accuracy: 65.29%
Epoch: [63]  [  0/312]  eta: 0:59:54  lr: 0.003772  min_lr: 0.003772  loss: 3.1349 (3.1349)  weight_decay: 0.0500 (0.0500)  time: 11.5217  data: 10.2754  max mem: 31830
Epoch: [63]  [ 10/312]  eta: 0:08:11  lr: 0.003771  min_lr: 0.003771  loss: 3.9985 (3.7565)  weight_decay: 0.0500 (0.0500)  time: 1.6266  data: 0.9837  max mem: 31830
Epoch: [63]  [ 20/312]  eta: 0:05:28  lr: 0.003771  min_lr: 0.003771  loss: 3.9218 (3.7606)  weight_decay: 0.0500 (0.0500)  time: 0.6059  data: 0.0899  max mem: 31830
Epoch: [63]  [ 30/312]  eta: 0:04:11  lr: 0.003771  min_lr: 0.003771  loss: 3.8749 (3.7918)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0630  max mem: 31830
Epoch: [63]  [ 40/312]  eta: 0:03:29  lr: 0.003770  min_lr: 0.003770  loss: 4.0181 (3.8272)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0007  max mem: 31830
Epoch: [63]  [ 50/312]  eta: 0:03:11  lr: 0.003770  min_lr: 0.003770  loss: 4.0919 (3.8641)  weight_decay: 0.0500 (0.0500)  time: 0.4883  data: 0.0184  max mem: 31830
Epoch: [63]  [ 60/312]  eta: 0:02:50  lr: 0.003770  min_lr: 0.003770  loss: 3.6708 (3.7939)  weight_decay: 0.0500 (0.0500)  time: 0.4851  data: 0.0185  max mem: 31830
Epoch: [63]  [ 70/312]  eta: 0:02:40  lr: 0.003769  min_lr: 0.003769  loss: 3.6708 (3.8466)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0175  max mem: 31830
Epoch: [63]  [ 80/312]  eta: 0:02:31  lr: 0.003769  min_lr: 0.003769  loss: 4.1203 (3.8499)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.0175  max mem: 31830
Epoch: [63]  [ 90/312]  eta: 0:02:19  lr: 0.003769  min_lr: 0.003769  loss: 3.9772 (3.8551)  weight_decay: 0.0500 (0.0500)  time: 0.4990  data: 0.0190  max mem: 31830
Epoch: [63]  [100/312]  eta: 0:02:13  lr: 0.003768  min_lr: 0.003768  loss: 3.9220 (3.8441)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0583  max mem: 31830
Epoch: [63]  [110/312]  eta: 0:02:02  lr: 0.003768  min_lr: 0.003768  loss: 4.0751 (3.8671)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0400  max mem: 31830
Epoch: [63]  [120/312]  eta: 0:01:55  lr: 0.003768  min_lr: 0.003768  loss: 3.9936 (3.8440)  weight_decay: 0.0500 (0.0500)  time: 0.4725  data: 0.0272  max mem: 31830
Epoch: [63]  [130/312]  eta: 0:01:50  lr: 0.003767  min_lr: 0.003767  loss: 3.6697 (3.8401)  weight_decay: 0.0500 (0.0500)  time: 0.5923  data: 0.0800  max mem: 31830
Epoch: [63]  [140/312]  eta: 0:01:41  lr: 0.003767  min_lr: 0.003767  loss: 3.8630 (3.8225)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0540  max mem: 31830
Epoch: [63]  [150/312]  eta: 0:01:36  lr: 0.003767  min_lr: 0.003767  loss: 3.8609 (3.8222)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0385  max mem: 31830
Epoch: [63]  [160/312]  eta: 0:01:29  lr: 0.003766  min_lr: 0.003766  loss: 3.7994 (3.8113)  weight_decay: 0.0500 (0.0500)  time: 0.5928  data: 0.0607  max mem: 31830
Epoch: [63]  [170/312]  eta: 0:01:22  lr: 0.003766  min_lr: 0.003766  loss: 3.7639 (3.8020)  weight_decay: 0.0500 (0.0500)  time: 0.4820  data: 0.0374  max mem: 31830
Epoch: [63]  [180/312]  eta: 0:01:17  lr: 0.003766  min_lr: 0.003766  loss: 3.9979 (3.8095)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0660  max mem: 31830
Epoch: [63]  [190/312]  eta: 0:01:10  lr: 0.003765  min_lr: 0.003765  loss: 4.0233 (3.8090)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0522  max mem: 31830
Epoch: [63]  [200/312]  eta: 0:01:04  lr: 0.003765  min_lr: 0.003765  loss: 3.8843 (3.8044)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0505  max mem: 31830
Epoch: [63]  [210/312]  eta: 0:00:58  lr: 0.003765  min_lr: 0.003765  loss: 3.9209 (3.8159)  weight_decay: 0.0500 (0.0500)  time: 0.6100  data: 0.0828  max mem: 31830
Epoch: [63]  [220/312]  eta: 0:00:52  lr: 0.003764  min_lr: 0.003764  loss: 3.7929 (3.8132)  weight_decay: 0.0500 (0.0500)  time: 0.4752  data: 0.0332  max mem: 31830
Epoch: [63]  [230/312]  eta: 0:00:47  lr: 0.003764  min_lr: 0.003764  loss: 4.0962 (3.8258)  weight_decay: 0.0500 (0.0500)  time: 0.5437  data: 0.0368  max mem: 31830
Epoch: [63]  [240/312]  eta: 0:00:41  lr: 0.003764  min_lr: 0.003764  loss: 4.1201 (3.8336)  weight_decay: 0.0500 (0.0500)  time: 0.5951  data: 0.0368  max mem: 31830
Epoch: [63]  [250/312]  eta: 0:00:35  lr: 0.003763  min_lr: 0.003763  loss: 3.7182 (3.8311)  weight_decay: 0.0500 (0.0500)  time: 0.4841  data: 0.0146  max mem: 31830
Epoch: [63]  [260/312]  eta: 0:00:29  lr: 0.003763  min_lr: 0.003763  loss: 3.8435 (3.8349)  weight_decay: 0.0500 (0.0500)  time: 0.5661  data: 0.0508  max mem: 31830
Epoch: [63]  [270/312]  eta: 0:00:23  lr: 0.003763  min_lr: 0.003763  loss: 3.8435 (3.8383)  weight_decay: 0.0500 (0.0500)  time: 0.5280  data: 0.0372  max mem: 31830
Epoch: [63]  [280/312]  eta: 0:00:18  lr: 0.003762  min_lr: 0.003762  loss: 3.8438 (3.8460)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0295  max mem: 31830
Epoch: [63]  [290/312]  eta: 0:00:12  lr: 0.003762  min_lr: 0.003762  loss: 3.8248 (3.8400)  weight_decay: 0.0500 (0.0500)  time: 0.6025  data: 0.0339  max mem: 31830
Epoch: [63]  [300/312]  eta: 0:00:06  lr: 0.003762  min_lr: 0.003762  loss: 3.8248 (3.8451)  weight_decay: 0.0500 (0.0500)  time: 0.4491  data: 0.0050  max mem: 31830
Epoch: [63]  [310/312]  eta: 0:00:01  lr: 0.003761  min_lr: 0.003761  loss: 4.0153 (3.8436)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [63]  [311/312]  eta: 0:00:00  lr: 0.003761  min_lr: 0.003761  loss: 4.0133 (3.8426)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [63] Total time: 0:02:54 (0.5582 s / it)
Averaged stats: lr: 0.003761  min_lr: 0.003761  loss: 4.0133 (3.8548)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.5488 (1.5488)  acc1: 73.1771 (73.1771)  acc5: 91.2760 (91.2760)  time: 8.4566  data: 8.2874  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9036 (1.8171)  acc1: 65.3646 (65.7920)  acc5: 86.8490 (86.8640)  time: 1.0587  data: 0.9209  max mem: 31830
Test: Total time: 0:00:09 (1.0684 s / it)
* Acc@1 64.912 Acc@5 86.676 loss 1.833
Accuracy of the model on the 50000 test images: 64.9%
Max accuracy: 65.29%
Epoch: [64]  [  0/312]  eta: 1:01:56  lr: 0.003761  min_lr: 0.003761  loss: 3.6926 (3.6926)  weight_decay: 0.0500 (0.0500)  time: 11.9133  data: 11.5176  max mem: 31830
Epoch: [64]  [ 10/312]  eta: 0:08:36  lr: 0.003761  min_lr: 0.003761  loss: 3.7196 (3.7897)  weight_decay: 0.0500 (0.0500)  time: 1.7108  data: 1.0477  max mem: 31830
Epoch: [64]  [ 20/312]  eta: 0:05:28  lr: 0.003761  min_lr: 0.003761  loss: 3.7298 (3.7227)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0174  max mem: 31830
Epoch: [64]  [ 30/312]  eta: 0:04:10  lr: 0.003760  min_lr: 0.003760  loss: 3.7948 (3.7454)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0175  max mem: 31830
Epoch: [64]  [ 40/312]  eta: 0:03:28  lr: 0.003760  min_lr: 0.003760  loss: 3.7522 (3.7617)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0008  max mem: 31830
Epoch: [64]  [ 50/312]  eta: 0:03:02  lr: 0.003760  min_lr: 0.003760  loss: 4.0023 (3.8053)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0007  max mem: 31830
Epoch: [64]  [ 60/312]  eta: 0:02:43  lr: 0.003759  min_lr: 0.003759  loss: 4.0209 (3.8023)  weight_decay: 0.0500 (0.0500)  time: 0.4020  data: 0.0006  max mem: 31830
Epoch: [64]  [ 70/312]  eta: 0:02:35  lr: 0.003759  min_lr: 0.003759  loss: 4.0453 (3.8524)  weight_decay: 0.0500 (0.0500)  time: 0.5094  data: 0.0260  max mem: 31830
Epoch: [64]  [ 80/312]  eta: 0:02:28  lr: 0.003759  min_lr: 0.003759  loss: 4.1910 (3.8718)  weight_decay: 0.0500 (0.0500)  time: 0.6103  data: 0.0454  max mem: 31830
Epoch: [64]  [ 90/312]  eta: 0:02:16  lr: 0.003758  min_lr: 0.003758  loss: 3.9784 (3.8611)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0308  max mem: 31830
Epoch: [64]  [100/312]  eta: 0:02:10  lr: 0.003758  min_lr: 0.003758  loss: 3.9784 (3.8721)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0402  max mem: 31830
Epoch: [64]  [110/312]  eta: 0:01:59  lr: 0.003757  min_lr: 0.003757  loss: 4.0746 (3.8923)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0295  max mem: 31830
Epoch: [64]  [120/312]  eta: 0:01:54  lr: 0.003757  min_lr: 0.003757  loss: 3.9176 (3.8805)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0542  max mem: 31830
Epoch: [64]  [130/312]  eta: 0:01:48  lr: 0.003757  min_lr: 0.003757  loss: 4.0003 (3.9092)  weight_decay: 0.0500 (0.0500)  time: 0.6252  data: 0.1036  max mem: 31830
Epoch: [64]  [140/312]  eta: 0:01:40  lr: 0.003756  min_lr: 0.003756  loss: 4.1443 (3.9024)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0501  max mem: 31830
Epoch: [64]  [150/312]  eta: 0:01:34  lr: 0.003756  min_lr: 0.003756  loss: 3.5772 (3.8751)  weight_decay: 0.0500 (0.0500)  time: 0.5058  data: 0.0358  max mem: 31830
Epoch: [64]  [160/312]  eta: 0:01:29  lr: 0.003756  min_lr: 0.003756  loss: 3.7144 (3.8673)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.0911  max mem: 31830
Epoch: [64]  [170/312]  eta: 0:01:22  lr: 0.003755  min_lr: 0.003755  loss: 3.8079 (3.8646)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0559  max mem: 31830
Epoch: [64]  [180/312]  eta: 0:01:16  lr: 0.003755  min_lr: 0.003755  loss: 3.7366 (3.8608)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0308  max mem: 31830
Epoch: [64]  [190/312]  eta: 0:01:09  lr: 0.003755  min_lr: 0.003755  loss: 3.8345 (3.8641)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0308  max mem: 31830
Epoch: [64]  [200/312]  eta: 0:01:04  lr: 0.003754  min_lr: 0.003754  loss: 3.8459 (3.8552)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0142  max mem: 31830
Epoch: [64]  [210/312]  eta: 0:00:59  lr: 0.003754  min_lr: 0.003754  loss: 3.7147 (3.8490)  weight_decay: 0.0500 (0.0500)  time: 0.6375  data: 0.0206  max mem: 31830
Epoch: [64]  [220/312]  eta: 0:00:52  lr: 0.003754  min_lr: 0.003754  loss: 3.5693 (3.8398)  weight_decay: 0.0500 (0.0500)  time: 0.5127  data: 0.0079  max mem: 31830
Epoch: [64]  [230/312]  eta: 0:00:47  lr: 0.003753  min_lr: 0.003753  loss: 3.6803 (3.8407)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0149  max mem: 31830
Epoch: [64]  [240/312]  eta: 0:00:41  lr: 0.003753  min_lr: 0.003753  loss: 3.9610 (3.8359)  weight_decay: 0.0500 (0.0500)  time: 0.6382  data: 0.0142  max mem: 31830
Epoch: [64]  [250/312]  eta: 0:00:35  lr: 0.003753  min_lr: 0.003753  loss: 3.9528 (3.8367)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0253  max mem: 31830
Epoch: [64]  [260/312]  eta: 0:00:29  lr: 0.003752  min_lr: 0.003752  loss: 3.9119 (3.8360)  weight_decay: 0.0500 (0.0500)  time: 0.4937  data: 0.0260  max mem: 31830
Epoch: [64]  [270/312]  eta: 0:00:23  lr: 0.003752  min_lr: 0.003752  loss: 3.8498 (3.8344)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0016  max mem: 31830
Epoch: [64]  [280/312]  eta: 0:00:18  lr: 0.003752  min_lr: 0.003752  loss: 4.0829 (3.8405)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.0021  max mem: 31830
Epoch: [64]  [290/312]  eta: 0:00:12  lr: 0.003751  min_lr: 0.003751  loss: 3.9501 (3.8327)  weight_decay: 0.0500 (0.0500)  time: 0.6432  data: 0.0054  max mem: 31830
Epoch: [64]  [300/312]  eta: 0:00:06  lr: 0.003751  min_lr: 0.003751  loss: 3.5580 (3.8302)  weight_decay: 0.0500 (0.0500)  time: 0.4840  data: 0.0038  max mem: 31830
Epoch: [64]  [310/312]  eta: 0:00:01  lr: 0.003751  min_lr: 0.003751  loss: 3.8814 (3.8302)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [64]  [311/312]  eta: 0:00:00  lr: 0.003751  min_lr: 0.003751  loss: 3.8964 (3.8321)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [64] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.003751  min_lr: 0.003751  loss: 3.8964 (3.8383)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.7927 (1.7927)  acc1: 67.5781 (67.5781)  acc5: 89.1927 (89.1927)  time: 8.7524  data: 8.5889  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1342 (2.0585)  acc1: 60.9375 (60.9760)  acc5: 84.2448 (84.4160)  time: 1.0908  data: 0.9544  max mem: 31830
Test: Total time: 0:00:10 (1.1198 s / it)
* Acc@1 61.374 Acc@5 84.478 loss 2.063
Accuracy of the model on the 50000 test images: 61.4%
Max accuracy: 65.29%
Epoch: [65]  [  0/312]  eta: 1:00:28  lr: 0.003751  min_lr: 0.003751  loss: 4.3236 (4.3236)  weight_decay: 0.0500 (0.0500)  time: 11.6287  data: 10.2800  max mem: 31830
Epoch: [65]  [ 10/312]  eta: 0:08:39  lr: 0.003750  min_lr: 0.003750  loss: 4.2108 (3.9601)  weight_decay: 0.0500 (0.0500)  time: 1.7192  data: 0.9643  max mem: 31830
Epoch: [65]  [ 20/312]  eta: 0:05:37  lr: 0.003750  min_lr: 0.003750  loss: 4.1003 (3.9291)  weight_decay: 0.0500 (0.0500)  time: 0.6327  data: 0.0167  max mem: 31830
Epoch: [65]  [ 30/312]  eta: 0:04:16  lr: 0.003749  min_lr: 0.003749  loss: 3.9833 (3.8528)  weight_decay: 0.0500 (0.0500)  time: 0.4651  data: 0.0015  max mem: 31830
Epoch: [65]  [ 40/312]  eta: 0:03:33  lr: 0.003749  min_lr: 0.003749  loss: 3.8637 (3.8455)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0016  max mem: 31830
Epoch: [65]  [ 50/312]  eta: 0:03:05  lr: 0.003749  min_lr: 0.003749  loss: 3.8892 (3.8410)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0010  max mem: 31830
Epoch: [65]  [ 60/312]  eta: 0:02:45  lr: 0.003748  min_lr: 0.003748  loss: 3.9206 (3.8908)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0010  max mem: 31830
Epoch: [65]  [ 70/312]  eta: 0:02:31  lr: 0.003748  min_lr: 0.003748  loss: 3.6954 (3.8287)  weight_decay: 0.0500 (0.0500)  time: 0.4149  data: 0.0007  max mem: 31830
Epoch: [65]  [ 80/312]  eta: 0:02:22  lr: 0.003748  min_lr: 0.003748  loss: 3.3029 (3.7909)  weight_decay: 0.0500 (0.0500)  time: 0.4767  data: 0.0283  max mem: 31830
Epoch: [65]  [ 90/312]  eta: 0:02:13  lr: 0.003747  min_lr: 0.003747  loss: 3.7124 (3.8193)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0420  max mem: 31830
Epoch: [65]  [100/312]  eta: 0:02:08  lr: 0.003747  min_lr: 0.003747  loss: 4.0007 (3.8236)  weight_decay: 0.0500 (0.0500)  time: 0.5655  data: 0.0548  max mem: 31830
Epoch: [65]  [110/312]  eta: 0:01:58  lr: 0.003747  min_lr: 0.003747  loss: 4.0007 (3.8358)  weight_decay: 0.0500 (0.0500)  time: 0.5106  data: 0.0458  max mem: 31830
Epoch: [65]  [120/312]  eta: 0:01:54  lr: 0.003746  min_lr: 0.003746  loss: 3.9022 (3.8334)  weight_decay: 0.0500 (0.0500)  time: 0.5623  data: 0.0497  max mem: 31830
Epoch: [65]  [130/312]  eta: 0:01:47  lr: 0.003746  min_lr: 0.003746  loss: 3.6758 (3.8178)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.0458  max mem: 31830
Epoch: [65]  [140/312]  eta: 0:01:40  lr: 0.003746  min_lr: 0.003746  loss: 3.9088 (3.8283)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0016  max mem: 31830
Epoch: [65]  [150/312]  eta: 0:01:35  lr: 0.003745  min_lr: 0.003745  loss: 4.0541 (3.8433)  weight_decay: 0.0500 (0.0500)  time: 0.5728  data: 0.0007  max mem: 31830
Epoch: [65]  [160/312]  eta: 0:01:27  lr: 0.003745  min_lr: 0.003745  loss: 3.9295 (3.8337)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0010  max mem: 31830
Epoch: [65]  [170/312]  eta: 0:01:22  lr: 0.003745  min_lr: 0.003745  loss: 3.7429 (3.8249)  weight_decay: 0.0500 (0.0500)  time: 0.5352  data: 0.0011  max mem: 31830
Epoch: [65]  [180/312]  eta: 0:01:17  lr: 0.003744  min_lr: 0.003744  loss: 3.9084 (3.8361)  weight_decay: 0.0500 (0.0500)  time: 0.6513  data: 0.0009  max mem: 31830
Epoch: [65]  [190/312]  eta: 0:01:10  lr: 0.003744  min_lr: 0.003744  loss: 3.9652 (3.8398)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0126  max mem: 31830
Epoch: [65]  [200/312]  eta: 0:01:04  lr: 0.003744  min_lr: 0.003744  loss: 3.9753 (3.8451)  weight_decay: 0.0500 (0.0500)  time: 0.4920  data: 0.0181  max mem: 31830
Epoch: [65]  [210/312]  eta: 0:00:58  lr: 0.003743  min_lr: 0.003743  loss: 3.9976 (3.8490)  weight_decay: 0.0500 (0.0500)  time: 0.5308  data: 0.0064  max mem: 31830
Epoch: [65]  [220/312]  eta: 0:00:52  lr: 0.003743  min_lr: 0.003743  loss: 3.6517 (3.8398)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0008  max mem: 31830
Epoch: [65]  [230/312]  eta: 0:00:47  lr: 0.003742  min_lr: 0.003742  loss: 3.9129 (3.8456)  weight_decay: 0.0500 (0.0500)  time: 0.5986  data: 0.0011  max mem: 31830
Epoch: [65]  [240/312]  eta: 0:00:40  lr: 0.003742  min_lr: 0.003742  loss: 4.0632 (3.8488)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0011  max mem: 31830
Epoch: [65]  [250/312]  eta: 0:00:35  lr: 0.003742  min_lr: 0.003742  loss: 4.0589 (3.8467)  weight_decay: 0.0500 (0.0500)  time: 0.4772  data: 0.0007  max mem: 31830
Epoch: [65]  [260/312]  eta: 0:00:29  lr: 0.003741  min_lr: 0.003741  loss: 4.2082 (3.8590)  weight_decay: 0.0500 (0.0500)  time: 0.6128  data: 0.0144  max mem: 31830
Epoch: [65]  [270/312]  eta: 0:00:23  lr: 0.003741  min_lr: 0.003741  loss: 3.9874 (3.8590)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0144  max mem: 31830
Epoch: [65]  [280/312]  eta: 0:00:18  lr: 0.003741  min_lr: 0.003741  loss: 3.6863 (3.8518)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0026  max mem: 31830
Epoch: [65]  [290/312]  eta: 0:00:12  lr: 0.003740  min_lr: 0.003740  loss: 4.0895 (3.8613)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0027  max mem: 31830
Epoch: [65]  [300/312]  eta: 0:00:06  lr: 0.003740  min_lr: 0.003740  loss: 4.1202 (3.8616)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0006  max mem: 31830
Epoch: [65]  [310/312]  eta: 0:00:01  lr: 0.003740  min_lr: 0.003740  loss: 4.0340 (3.8701)  weight_decay: 0.0500 (0.0500)  time: 0.4158  data: 0.0001  max mem: 31830
Epoch: [65]  [311/312]  eta: 0:00:00  lr: 0.003740  min_lr: 0.003740  loss: 4.0340 (3.8673)  weight_decay: 0.0500 (0.0500)  time: 0.4158  data: 0.0001  max mem: 31830
Epoch: [65] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.003740  min_lr: 0.003740  loss: 4.0340 (3.8528)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.5493 (1.5493)  acc1: 70.7031 (70.7031)  acc5: 89.3229 (89.3229)  time: 8.8352  data: 8.6676  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8816 (1.7581)  acc1: 62.6302 (63.3600)  acc5: 84.7656 (85.5040)  time: 1.0982  data: 0.9631  max mem: 31830
Test: Total time: 0:00:10 (1.1325 s / it)
* Acc@1 63.664 Acc@5 86.106 loss 1.759
Accuracy of the model on the 50000 test images: 63.7%
Max accuracy: 65.29%
Epoch: [66]  [  0/312]  eta: 1:02:30  lr: 0.003740  min_lr: 0.003740  loss: 4.2261 (4.2261)  weight_decay: 0.0500 (0.0500)  time: 12.0223  data: 9.6291  max mem: 31830
Epoch: [66]  [ 10/312]  eta: 0:08:42  lr: 0.003739  min_lr: 0.003739  loss: 4.1260 (4.0575)  weight_decay: 0.0500 (0.0500)  time: 1.7302  data: 0.9588  max mem: 31830
Epoch: [66]  [ 20/312]  eta: 0:05:25  lr: 0.003739  min_lr: 0.003739  loss: 4.0664 (4.0532)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0705  max mem: 31830
Epoch: [66]  [ 30/312]  eta: 0:04:09  lr: 0.003738  min_lr: 0.003738  loss: 4.0664 (4.0218)  weight_decay: 0.0500 (0.0500)  time: 0.4180  data: 0.0250  max mem: 31830
Epoch: [66]  [ 40/312]  eta: 0:03:27  lr: 0.003738  min_lr: 0.003738  loss: 3.9696 (3.9496)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0007  max mem: 31830
Epoch: [66]  [ 50/312]  eta: 0:03:01  lr: 0.003738  min_lr: 0.003738  loss: 3.8292 (3.9046)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0007  max mem: 31830
Epoch: [66]  [ 60/312]  eta: 0:02:42  lr: 0.003737  min_lr: 0.003737  loss: 4.0295 (3.9296)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0010  max mem: 31830
Epoch: [66]  [ 70/312]  eta: 0:02:30  lr: 0.003737  min_lr: 0.003737  loss: 4.0370 (3.9250)  weight_decay: 0.0500 (0.0500)  time: 0.4496  data: 0.0509  max mem: 31830
Epoch: [66]  [ 80/312]  eta: 0:02:24  lr: 0.003737  min_lr: 0.003737  loss: 3.7496 (3.9016)  weight_decay: 0.0500 (0.0500)  time: 0.5529  data: 0.0988  max mem: 31830
Epoch: [66]  [ 90/312]  eta: 0:02:14  lr: 0.003736  min_lr: 0.003736  loss: 3.8497 (3.9139)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0853  max mem: 31830
Epoch: [66]  [100/312]  eta: 0:02:06  lr: 0.003736  min_lr: 0.003736  loss: 3.9182 (3.9043)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0913  max mem: 31830
Epoch: [66]  [110/312]  eta: 0:01:57  lr: 0.003736  min_lr: 0.003736  loss: 3.8770 (3.9042)  weight_decay: 0.0500 (0.0500)  time: 0.4893  data: 0.0549  max mem: 31830
Epoch: [66]  [120/312]  eta: 0:01:52  lr: 0.003735  min_lr: 0.003735  loss: 3.8878 (3.8967)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0637  max mem: 31830
Epoch: [66]  [130/312]  eta: 0:01:47  lr: 0.003735  min_lr: 0.003735  loss: 3.8878 (3.8883)  weight_decay: 0.0500 (0.0500)  time: 0.6274  data: 0.1263  max mem: 31830
Epoch: [66]  [140/312]  eta: 0:01:39  lr: 0.003735  min_lr: 0.003735  loss: 3.9115 (3.8873)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0639  max mem: 31830
Epoch: [66]  [150/312]  eta: 0:01:34  lr: 0.003734  min_lr: 0.003734  loss: 3.9082 (3.8757)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0549  max mem: 31830
Epoch: [66]  [160/312]  eta: 0:01:27  lr: 0.003734  min_lr: 0.003734  loss: 3.9082 (3.8806)  weight_decay: 0.0500 (0.0500)  time: 0.5805  data: 0.0675  max mem: 31830
Epoch: [66]  [170/312]  eta: 0:01:20  lr: 0.003733  min_lr: 0.003733  loss: 4.0212 (3.8811)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.0264  max mem: 31830
Epoch: [66]  [180/312]  eta: 0:01:15  lr: 0.003733  min_lr: 0.003733  loss: 4.0212 (3.8821)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0530  max mem: 31830
Epoch: [66]  [190/312]  eta: 0:01:09  lr: 0.003733  min_lr: 0.003733  loss: 4.0881 (3.8848)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0405  max mem: 31830
Epoch: [66]  [200/312]  eta: 0:01:03  lr: 0.003732  min_lr: 0.003732  loss: 4.1905 (3.8848)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0404  max mem: 31830
Epoch: [66]  [210/312]  eta: 0:00:58  lr: 0.003732  min_lr: 0.003732  loss: 3.5196 (3.8616)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.0765  max mem: 31830
Epoch: [66]  [220/312]  eta: 0:00:51  lr: 0.003732  min_lr: 0.003732  loss: 4.1356 (3.8722)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0370  max mem: 31830
Epoch: [66]  [230/312]  eta: 0:00:46  lr: 0.003731  min_lr: 0.003731  loss: 4.1459 (3.8789)  weight_decay: 0.0500 (0.0500)  time: 0.5295  data: 0.0399  max mem: 31830
Epoch: [66]  [240/312]  eta: 0:00:40  lr: 0.003731  min_lr: 0.003731  loss: 4.0446 (3.8782)  weight_decay: 0.0500 (0.0500)  time: 0.5655  data: 0.0537  max mem: 31830
Epoch: [66]  [250/312]  eta: 0:00:34  lr: 0.003731  min_lr: 0.003731  loss: 4.1361 (3.8869)  weight_decay: 0.0500 (0.0500)  time: 0.5060  data: 0.0550  max mem: 31830
Epoch: [66]  [260/312]  eta: 0:00:29  lr: 0.003730  min_lr: 0.003730  loss: 3.9161 (3.8770)  weight_decay: 0.0500 (0.0500)  time: 0.5743  data: 0.0920  max mem: 31830
Epoch: [66]  [270/312]  eta: 0:00:23  lr: 0.003730  min_lr: 0.003730  loss: 3.8185 (3.8704)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.0517  max mem: 31830
Epoch: [66]  [280/312]  eta: 0:00:17  lr: 0.003730  min_lr: 0.003730  loss: 3.8185 (3.8636)  weight_decay: 0.0500 (0.0500)  time: 0.5128  data: 0.0484  max mem: 31830
Epoch: [66]  [290/312]  eta: 0:00:12  lr: 0.003729  min_lr: 0.003729  loss: 3.7787 (3.8628)  weight_decay: 0.0500 (0.0500)  time: 0.6119  data: 0.1143  max mem: 31830
Epoch: [66]  [300/312]  eta: 0:00:06  lr: 0.003729  min_lr: 0.003729  loss: 3.9237 (3.8670)  weight_decay: 0.0500 (0.0500)  time: 0.4886  data: 0.0665  max mem: 31830
Epoch: [66]  [310/312]  eta: 0:00:01  lr: 0.003728  min_lr: 0.003728  loss: 3.8929 (3.8652)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [66]  [311/312]  eta: 0:00:00  lr: 0.003728  min_lr: 0.003728  loss: 3.9237 (3.8666)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [66] Total time: 0:02:52 (0.5535 s / it)
Averaged stats: lr: 0.003728  min_lr: 0.003728  loss: 3.9237 (3.8415)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.9270 (1.9270)  acc1: 68.3594 (68.3594)  acc5: 87.8906 (87.8906)  time: 8.0352  data: 7.8705  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9834 (1.9388)  acc1: 61.7188 (62.0320)  acc5: 85.4167 (85.0720)  time: 1.0167  data: 0.8815  max mem: 31830
Test: Total time: 0:00:09 (1.0271 s / it)
* Acc@1 62.320 Acc@5 85.000 loss 1.946
Accuracy of the model on the 50000 test images: 62.3%
Max accuracy: 65.29%
Epoch: [67]  [  0/312]  eta: 1:04:45  lr: 0.003728  min_lr: 0.003728  loss: 3.5077 (3.5077)  weight_decay: 0.0500 (0.0500)  time: 12.4537  data: 10.2350  max mem: 31830
Epoch: [67]  [ 10/312]  eta: 0:08:14  lr: 0.003728  min_lr: 0.003728  loss: 3.6564 (3.7291)  weight_decay: 0.0500 (0.0500)  time: 1.6381  data: 0.9310  max mem: 31830
Epoch: [67]  [ 20/312]  eta: 0:05:21  lr: 0.003728  min_lr: 0.003728  loss: 3.8891 (3.8287)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0010  max mem: 31830
Epoch: [67]  [ 30/312]  eta: 0:04:06  lr: 0.003727  min_lr: 0.003727  loss: 4.0476 (3.7817)  weight_decay: 0.0500 (0.0500)  time: 0.4528  data: 0.0010  max mem: 31830
Epoch: [67]  [ 40/312]  eta: 0:03:26  lr: 0.003727  min_lr: 0.003727  loss: 3.4805 (3.7215)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0007  max mem: 31830
Epoch: [67]  [ 50/312]  eta: 0:03:07  lr: 0.003727  min_lr: 0.003727  loss: 3.9296 (3.7920)  weight_decay: 0.0500 (0.0500)  time: 0.4723  data: 0.0212  max mem: 31830
Epoch: [67]  [ 60/312]  eta: 0:02:47  lr: 0.003726  min_lr: 0.003726  loss: 4.0063 (3.7822)  weight_decay: 0.0500 (0.0500)  time: 0.4691  data: 0.0211  max mem: 31830
Epoch: [67]  [ 70/312]  eta: 0:02:40  lr: 0.003726  min_lr: 0.003726  loss: 3.9645 (3.7810)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0489  max mem: 31830
Epoch: [67]  [ 80/312]  eta: 0:02:30  lr: 0.003725  min_lr: 0.003725  loss: 3.7252 (3.7796)  weight_decay: 0.0500 (0.0500)  time: 0.5989  data: 0.0491  max mem: 31830
Epoch: [67]  [ 90/312]  eta: 0:02:19  lr: 0.003725  min_lr: 0.003725  loss: 3.7484 (3.7860)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0445  max mem: 31830
Epoch: [67]  [100/312]  eta: 0:02:12  lr: 0.003725  min_lr: 0.003725  loss: 3.9132 (3.8013)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0783  max mem: 31830
Epoch: [67]  [110/312]  eta: 0:02:01  lr: 0.003724  min_lr: 0.003724  loss: 3.9034 (3.7926)  weight_decay: 0.0500 (0.0500)  time: 0.4892  data: 0.0358  max mem: 31830
Epoch: [67]  [120/312]  eta: 0:01:56  lr: 0.003724  min_lr: 0.003724  loss: 3.7977 (3.7730)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0598  max mem: 31830
Epoch: [67]  [130/312]  eta: 0:01:49  lr: 0.003724  min_lr: 0.003724  loss: 3.8812 (3.7715)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.1022  max mem: 31830
Epoch: [67]  [140/312]  eta: 0:01:41  lr: 0.003723  min_lr: 0.003723  loss: 3.8812 (3.7836)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0444  max mem: 31830
Epoch: [67]  [150/312]  eta: 0:01:36  lr: 0.003723  min_lr: 0.003723  loss: 3.8513 (3.7796)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0727  max mem: 31830
Epoch: [67]  [160/312]  eta: 0:01:29  lr: 0.003723  min_lr: 0.003723  loss: 3.8247 (3.7872)  weight_decay: 0.0500 (0.0500)  time: 0.5871  data: 0.0726  max mem: 31830
Epoch: [67]  [170/312]  eta: 0:01:22  lr: 0.003722  min_lr: 0.003722  loss: 3.8247 (3.7786)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0503  max mem: 31830
Epoch: [67]  [180/312]  eta: 0:01:17  lr: 0.003722  min_lr: 0.003722  loss: 3.6804 (3.7737)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.1011  max mem: 31830
Epoch: [67]  [190/312]  eta: 0:01:10  lr: 0.003721  min_lr: 0.003721  loss: 3.9788 (3.7774)  weight_decay: 0.0500 (0.0500)  time: 0.4976  data: 0.0514  max mem: 31830
Epoch: [67]  [200/312]  eta: 0:01:04  lr: 0.003721  min_lr: 0.003721  loss: 4.0295 (3.7779)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0589  max mem: 31830
Epoch: [67]  [210/312]  eta: 0:00:58  lr: 0.003721  min_lr: 0.003721  loss: 3.7280 (3.7730)  weight_decay: 0.0500 (0.0500)  time: 0.6042  data: 0.0997  max mem: 31830
Epoch: [67]  [220/312]  eta: 0:00:52  lr: 0.003720  min_lr: 0.003720  loss: 3.5703 (3.7635)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0415  max mem: 31830
Epoch: [67]  [230/312]  eta: 0:00:46  lr: 0.003720  min_lr: 0.003720  loss: 3.6671 (3.7657)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0383  max mem: 31830
Epoch: [67]  [240/312]  eta: 0:00:41  lr: 0.003720  min_lr: 0.003720  loss: 3.7595 (3.7690)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.0385  max mem: 31830
Epoch: [67]  [250/312]  eta: 0:00:34  lr: 0.003719  min_lr: 0.003719  loss: 4.1316 (3.7805)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0227  max mem: 31830
Epoch: [67]  [260/312]  eta: 0:00:29  lr: 0.003719  min_lr: 0.003719  loss: 4.0574 (3.7809)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0468  max mem: 31830
Epoch: [67]  [270/312]  eta: 0:00:23  lr: 0.003719  min_lr: 0.003719  loss: 3.7978 (3.7799)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0250  max mem: 31830
Epoch: [67]  [280/312]  eta: 0:00:17  lr: 0.003718  min_lr: 0.003718  loss: 3.8580 (3.7789)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0143  max mem: 31830
Epoch: [67]  [290/312]  eta: 0:00:12  lr: 0.003718  min_lr: 0.003718  loss: 4.0186 (3.7926)  weight_decay: 0.0500 (0.0500)  time: 0.5719  data: 0.0256  max mem: 31830
Epoch: [67]  [300/312]  eta: 0:00:06  lr: 0.003717  min_lr: 0.003717  loss: 4.1489 (3.7978)  weight_decay: 0.0500 (0.0500)  time: 0.4677  data: 0.0118  max mem: 31830
Epoch: [67]  [310/312]  eta: 0:00:01  lr: 0.003717  min_lr: 0.003717  loss: 4.0932 (3.8028)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [67]  [311/312]  eta: 0:00:00  lr: 0.003717  min_lr: 0.003717  loss: 4.0932 (3.8052)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [67] Total time: 0:02:52 (0.5521 s / it)
Averaged stats: lr: 0.003717  min_lr: 0.003717  loss: 4.0932 (3.8402)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.4118 (1.4118)  acc1: 70.4427 (70.4427)  acc5: 90.7552 (90.7552)  time: 8.8923  data: 8.7280  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8980 (1.7259)  acc1: 59.8958 (62.1600)  acc5: 84.1146 (85.7280)  time: 1.1056  data: 0.9699  max mem: 31830
Test: Total time: 0:00:10 (1.1208 s / it)
* Acc@1 62.474 Acc@5 85.236 loss 1.725
Accuracy of the model on the 50000 test images: 62.5%
Max accuracy: 65.29%
Epoch: [68]  [  0/312]  eta: 0:58:12  lr: 0.003717  min_lr: 0.003717  loss: 4.0405 (4.0405)  weight_decay: 0.0500 (0.0500)  time: 11.1940  data: 10.4912  max mem: 31830
Epoch: [68]  [ 10/312]  eta: 0:09:01  lr: 0.003717  min_lr: 0.003717  loss: 4.0241 (3.8080)  weight_decay: 0.0500 (0.0500)  time: 1.7936  data: 0.9881  max mem: 31830
Epoch: [68]  [ 20/312]  eta: 0:05:45  lr: 0.003716  min_lr: 0.003716  loss: 3.9407 (3.8028)  weight_decay: 0.0500 (0.0500)  time: 0.6834  data: 0.0192  max mem: 31830
Epoch: [68]  [ 30/312]  eta: 0:04:21  lr: 0.003716  min_lr: 0.003716  loss: 3.8777 (3.8437)  weight_decay: 0.0500 (0.0500)  time: 0.4527  data: 0.0008  max mem: 31830
Epoch: [68]  [ 40/312]  eta: 0:03:37  lr: 0.003715  min_lr: 0.003715  loss: 3.8777 (3.8276)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0008  max mem: 31830
Epoch: [68]  [ 50/312]  eta: 0:03:09  lr: 0.003715  min_lr: 0.003715  loss: 3.9847 (3.8230)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0010  max mem: 31830
Epoch: [68]  [ 60/312]  eta: 0:02:48  lr: 0.003715  min_lr: 0.003715  loss: 3.9847 (3.8334)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0011  max mem: 31830
Epoch: [68]  [ 70/312]  eta: 0:02:32  lr: 0.003714  min_lr: 0.003714  loss: 4.0661 (3.8517)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [68]  [ 80/312]  eta: 0:02:23  lr: 0.003714  min_lr: 0.003714  loss: 3.7610 (3.8115)  weight_decay: 0.0500 (0.0500)  time: 0.4682  data: 0.0006  max mem: 31830
Epoch: [68]  [ 90/312]  eta: 0:02:14  lr: 0.003714  min_lr: 0.003714  loss: 3.5433 (3.7804)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0577  max mem: 31830
Epoch: [68]  [100/312]  eta: 0:02:09  lr: 0.003713  min_lr: 0.003713  loss: 3.2414 (3.7254)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.1073  max mem: 31830
Epoch: [68]  [110/312]  eta: 0:01:59  lr: 0.003713  min_lr: 0.003713  loss: 3.3702 (3.7455)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0505  max mem: 31830
Epoch: [68]  [120/312]  eta: 0:01:53  lr: 0.003713  min_lr: 0.003713  loss: 4.0334 (3.7589)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0575  max mem: 31830
Epoch: [68]  [130/312]  eta: 0:01:47  lr: 0.003712  min_lr: 0.003712  loss: 3.9179 (3.7701)  weight_decay: 0.0500 (0.0500)  time: 0.6060  data: 0.1007  max mem: 31830
Epoch: [68]  [140/312]  eta: 0:01:41  lr: 0.003712  min_lr: 0.003712  loss: 3.9988 (3.7876)  weight_decay: 0.0500 (0.0500)  time: 0.5590  data: 0.0600  max mem: 31830
Epoch: [68]  [150/312]  eta: 0:01:35  lr: 0.003711  min_lr: 0.003711  loss: 4.0905 (3.8029)  weight_decay: 0.0500 (0.0500)  time: 0.5557  data: 0.0355  max mem: 31830
Epoch: [68]  [160/312]  eta: 0:01:28  lr: 0.003711  min_lr: 0.003711  loss: 4.0762 (3.8103)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0403  max mem: 31830
Epoch: [68]  [170/312]  eta: 0:01:22  lr: 0.003711  min_lr: 0.003711  loss: 3.7493 (3.7947)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0647  max mem: 31830
Epoch: [68]  [180/312]  eta: 0:01:17  lr: 0.003710  min_lr: 0.003710  loss: 3.6314 (3.8028)  weight_decay: 0.0500 (0.0500)  time: 0.6284  data: 0.0746  max mem: 31830
Epoch: [68]  [190/312]  eta: 0:01:10  lr: 0.003710  min_lr: 0.003710  loss: 3.6335 (3.8010)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0441  max mem: 31830
Epoch: [68]  [200/312]  eta: 0:01:04  lr: 0.003710  min_lr: 0.003710  loss: 3.6335 (3.7963)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0476  max mem: 31830
Epoch: [68]  [210/312]  eta: 0:00:58  lr: 0.003709  min_lr: 0.003709  loss: 3.8630 (3.7964)  weight_decay: 0.0500 (0.0500)  time: 0.5483  data: 0.0677  max mem: 31830
Epoch: [68]  [220/312]  eta: 0:00:52  lr: 0.003709  min_lr: 0.003709  loss: 3.7434 (3.7921)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0339  max mem: 31830
Epoch: [68]  [230/312]  eta: 0:00:47  lr: 0.003708  min_lr: 0.003708  loss: 3.6920 (3.7902)  weight_decay: 0.0500 (0.0500)  time: 0.6365  data: 0.0117  max mem: 31830
Epoch: [68]  [240/312]  eta: 0:00:41  lr: 0.003708  min_lr: 0.003708  loss: 3.7506 (3.7900)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0117  max mem: 31830
Epoch: [68]  [250/312]  eta: 0:00:35  lr: 0.003708  min_lr: 0.003708  loss: 3.8089 (3.7793)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0008  max mem: 31830
Epoch: [68]  [260/312]  eta: 0:00:30  lr: 0.003707  min_lr: 0.003707  loss: 3.8089 (3.7857)  weight_decay: 0.0500 (0.0500)  time: 0.6613  data: 0.0009  max mem: 31830
Epoch: [68]  [270/312]  eta: 0:00:24  lr: 0.003707  min_lr: 0.003707  loss: 3.9401 (3.7883)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0010  max mem: 31830
Epoch: [68]  [280/312]  eta: 0:00:18  lr: 0.003707  min_lr: 0.003707  loss: 3.7410 (3.7816)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0024  max mem: 31830
Epoch: [68]  [290/312]  eta: 0:00:12  lr: 0.003706  min_lr: 0.003706  loss: 3.4638 (3.7776)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.0020  max mem: 31830
Epoch: [68]  [300/312]  eta: 0:00:06  lr: 0.003706  min_lr: 0.003706  loss: 3.8760 (3.7748)  weight_decay: 0.0500 (0.0500)  time: 0.4188  data: 0.0002  max mem: 31830
Epoch: [68]  [310/312]  eta: 0:00:01  lr: 0.003705  min_lr: 0.003705  loss: 3.9871 (3.7812)  weight_decay: 0.0500 (0.0500)  time: 0.4045  data: 0.0001  max mem: 31830
Epoch: [68]  [311/312]  eta: 0:00:00  lr: 0.003705  min_lr: 0.003705  loss: 3.9871 (3.7825)  weight_decay: 0.0500 (0.0500)  time: 0.4044  data: 0.0001  max mem: 31830
Epoch: [68] Total time: 0:02:55 (0.5626 s / it)
Averaged stats: lr: 0.003705  min_lr: 0.003705  loss: 3.9871 (3.8445)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.5619 (1.5619)  acc1: 71.2240 (71.2240)  acc5: 90.4948 (90.4948)  time: 8.7490  data: 8.5816  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0380 (1.8511)  acc1: 61.5885 (63.5200)  acc5: 83.8542 (85.6160)  time: 1.0892  data: 0.9536  max mem: 31830
Test: Total time: 0:00:10 (1.1239 s / it)
* Acc@1 63.270 Acc@5 85.830 loss 1.861
Accuracy of the model on the 50000 test images: 63.3%
Max accuracy: 65.29%
Epoch: [69]  [  0/312]  eta: 1:02:44  lr: 0.003705  min_lr: 0.003705  loss: 3.0856 (3.0856)  weight_decay: 0.0500 (0.0500)  time: 12.0652  data: 8.9402  max mem: 31830
Epoch: [69]  [ 10/312]  eta: 0:08:50  lr: 0.003705  min_lr: 0.003705  loss: 3.1678 (3.4971)  weight_decay: 0.0500 (0.0500)  time: 1.7572  data: 0.9810  max mem: 31830
Epoch: [69]  [ 20/312]  eta: 0:05:29  lr: 0.003705  min_lr: 0.003705  loss: 3.3578 (3.5975)  weight_decay: 0.0500 (0.0500)  time: 0.5825  data: 0.1177  max mem: 31830
Epoch: [69]  [ 30/312]  eta: 0:04:11  lr: 0.003704  min_lr: 0.003704  loss: 3.3612 (3.5663)  weight_decay: 0.0500 (0.0500)  time: 0.4170  data: 0.0256  max mem: 31830
Epoch: [69]  [ 40/312]  eta: 0:03:30  lr: 0.003704  min_lr: 0.003704  loss: 3.9070 (3.6935)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0009  max mem: 31830
Epoch: [69]  [ 50/312]  eta: 0:03:03  lr: 0.003703  min_lr: 0.003703  loss: 4.0169 (3.7264)  weight_decay: 0.0500 (0.0500)  time: 0.4020  data: 0.0010  max mem: 31830
Epoch: [69]  [ 60/312]  eta: 0:02:43  lr: 0.003703  min_lr: 0.003703  loss: 4.0169 (3.7425)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0009  max mem: 31830
Epoch: [69]  [ 70/312]  eta: 0:02:31  lr: 0.003703  min_lr: 0.003703  loss: 3.7147 (3.6821)  weight_decay: 0.0500 (0.0500)  time: 0.4427  data: 0.0009  max mem: 31830
Epoch: [69]  [ 80/312]  eta: 0:02:22  lr: 0.003702  min_lr: 0.003702  loss: 3.2887 (3.6762)  weight_decay: 0.0500 (0.0500)  time: 0.5040  data: 0.0008  max mem: 31830
Epoch: [69]  [ 90/312]  eta: 0:02:14  lr: 0.003702  min_lr: 0.003702  loss: 3.4596 (3.6624)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0009  max mem: 31830
Epoch: [69]  [100/312]  eta: 0:02:08  lr: 0.003702  min_lr: 0.003702  loss: 3.8214 (3.6913)  weight_decay: 0.0500 (0.0500)  time: 0.5818  data: 0.0010  max mem: 31830
Epoch: [69]  [110/312]  eta: 0:01:58  lr: 0.003701  min_lr: 0.003701  loss: 4.1107 (3.7138)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0010  max mem: 31830
Epoch: [69]  [120/312]  eta: 0:01:53  lr: 0.003701  min_lr: 0.003701  loss: 4.1107 (3.7305)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0010  max mem: 31830
Epoch: [69]  [130/312]  eta: 0:01:46  lr: 0.003700  min_lr: 0.003700  loss: 3.7982 (3.7296)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0082  max mem: 31830
Epoch: [69]  [140/312]  eta: 0:01:39  lr: 0.003700  min_lr: 0.003700  loss: 3.5183 (3.7297)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0083  max mem: 31830
Epoch: [69]  [150/312]  eta: 0:01:34  lr: 0.003700  min_lr: 0.003700  loss: 3.7729 (3.7439)  weight_decay: 0.0500 (0.0500)  time: 0.5920  data: 0.0145  max mem: 31830
Epoch: [69]  [160/312]  eta: 0:01:27  lr: 0.003699  min_lr: 0.003699  loss: 3.7953 (3.7484)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0151  max mem: 31830
Epoch: [69]  [170/312]  eta: 0:01:22  lr: 0.003699  min_lr: 0.003699  loss: 3.9891 (3.7581)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0017  max mem: 31830
Epoch: [69]  [180/312]  eta: 0:01:16  lr: 0.003699  min_lr: 0.003699  loss: 3.9763 (3.7597)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.0142  max mem: 31830
Epoch: [69]  [190/312]  eta: 0:01:09  lr: 0.003698  min_lr: 0.003698  loss: 3.8530 (3.7738)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0140  max mem: 31830
Epoch: [69]  [200/312]  eta: 0:01:04  lr: 0.003698  min_lr: 0.003698  loss: 3.9158 (3.7770)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0012  max mem: 31830
Epoch: [69]  [210/312]  eta: 0:00:57  lr: 0.003697  min_lr: 0.003697  loss: 3.9351 (3.7803)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0013  max mem: 31830
Epoch: [69]  [220/312]  eta: 0:00:52  lr: 0.003697  min_lr: 0.003697  loss: 3.8699 (3.7773)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0013  max mem: 31830
Epoch: [69]  [230/312]  eta: 0:00:46  lr: 0.003697  min_lr: 0.003697  loss: 3.9229 (3.7853)  weight_decay: 0.0500 (0.0500)  time: 0.5825  data: 0.0213  max mem: 31830
Epoch: [69]  [240/312]  eta: 0:00:40  lr: 0.003696  min_lr: 0.003696  loss: 4.1154 (3.7924)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0336  max mem: 31830
Epoch: [69]  [250/312]  eta: 0:00:34  lr: 0.003696  min_lr: 0.003696  loss: 4.1272 (3.7905)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0136  max mem: 31830
Epoch: [69]  [260/312]  eta: 0:00:29  lr: 0.003696  min_lr: 0.003696  loss: 3.9818 (3.7959)  weight_decay: 0.0500 (0.0500)  time: 0.6018  data: 0.0341  max mem: 31830
Epoch: [69]  [270/312]  eta: 0:00:23  lr: 0.003695  min_lr: 0.003695  loss: 3.7619 (3.7867)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0340  max mem: 31830
Epoch: [69]  [280/312]  eta: 0:00:17  lr: 0.003695  min_lr: 0.003695  loss: 4.0941 (3.7952)  weight_decay: 0.0500 (0.0500)  time: 0.5282  data: 0.0380  max mem: 31830
Epoch: [69]  [290/312]  eta: 0:00:12  lr: 0.003694  min_lr: 0.003694  loss: 4.1069 (3.8067)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0732  max mem: 31830
Epoch: [69]  [300/312]  eta: 0:00:06  lr: 0.003694  min_lr: 0.003694  loss: 4.1052 (3.8158)  weight_decay: 0.0500 (0.0500)  time: 0.4679  data: 0.0356  max mem: 31830
Epoch: [69]  [310/312]  eta: 0:00:01  lr: 0.003694  min_lr: 0.003694  loss: 4.0928 (3.8099)  weight_decay: 0.0500 (0.0500)  time: 0.4274  data: 0.0001  max mem: 31830
Epoch: [69]  [311/312]  eta: 0:00:00  lr: 0.003694  min_lr: 0.003694  loss: 3.9668 (3.8083)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [69] Total time: 0:02:52 (0.5536 s / it)
Averaged stats: lr: 0.003694  min_lr: 0.003694  loss: 3.9668 (3.8192)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6597 (1.6597)  acc1: 69.4010 (69.4010)  acc5: 88.4115 (88.4115)  time: 8.2804  data: 8.1180  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0091 (1.8632)  acc1: 63.6719 (63.8240)  acc5: 84.2448 (85.6960)  time: 1.0570  data: 0.9224  max mem: 31830
Test: Total time: 0:00:09 (1.0671 s / it)
* Acc@1 63.970 Acc@5 86.332 loss 1.849
Accuracy of the model on the 50000 test images: 64.0%
Max accuracy: 65.29%
Epoch: [70]  [  0/312]  eta: 1:01:36  lr: 0.003694  min_lr: 0.003694  loss: 4.3699 (4.3699)  weight_decay: 0.0500 (0.0500)  time: 11.8486  data: 11.0117  max mem: 31830
Epoch: [70]  [ 10/312]  eta: 0:08:39  lr: 0.003693  min_lr: 0.003693  loss: 4.0453 (3.7176)  weight_decay: 0.0500 (0.0500)  time: 1.7194  data: 1.0015  max mem: 31830
Epoch: [70]  [ 20/312]  eta: 0:05:25  lr: 0.003693  min_lr: 0.003693  loss: 3.4069 (3.6975)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.0005  max mem: 31830
Epoch: [70]  [ 30/312]  eta: 0:04:09  lr: 0.003692  min_lr: 0.003692  loss: 3.8623 (3.8353)  weight_decay: 0.0500 (0.0500)  time: 0.4259  data: 0.0013  max mem: 31830
Epoch: [70]  [ 40/312]  eta: 0:03:28  lr: 0.003692  min_lr: 0.003692  loss: 4.0631 (3.8529)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0015  max mem: 31830
Epoch: [70]  [ 50/312]  eta: 0:03:03  lr: 0.003692  min_lr: 0.003692  loss: 3.9660 (3.8266)  weight_decay: 0.0500 (0.0500)  time: 0.4131  data: 0.0008  max mem: 31830
Epoch: [70]  [ 60/312]  eta: 0:02:43  lr: 0.003691  min_lr: 0.003691  loss: 3.9660 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 0.4122  data: 0.0007  max mem: 31830
Epoch: [70]  [ 70/312]  eta: 0:02:31  lr: 0.003691  min_lr: 0.003691  loss: 3.8872 (3.8187)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0465  max mem: 31830
Epoch: [70]  [ 80/312]  eta: 0:02:23  lr: 0.003690  min_lr: 0.003690  loss: 3.8632 (3.8469)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.1223  max mem: 31830
Epoch: [70]  [ 90/312]  eta: 0:02:11  lr: 0.003690  min_lr: 0.003690  loss: 4.0696 (3.8567)  weight_decay: 0.0500 (0.0500)  time: 0.4713  data: 0.0779  max mem: 31830
Epoch: [70]  [100/312]  eta: 0:02:05  lr: 0.003690  min_lr: 0.003690  loss: 3.9183 (3.8512)  weight_decay: 0.0500 (0.0500)  time: 0.4919  data: 0.0649  max mem: 31830
Epoch: [70]  [110/312]  eta: 0:01:56  lr: 0.003689  min_lr: 0.003689  loss: 3.8766 (3.8363)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0639  max mem: 31830
Epoch: [70]  [120/312]  eta: 0:01:51  lr: 0.003689  min_lr: 0.003689  loss: 3.7386 (3.8339)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0671  max mem: 31830
Epoch: [70]  [130/312]  eta: 0:01:45  lr: 0.003689  min_lr: 0.003689  loss: 3.7004 (3.8208)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.1514  max mem: 31830
Epoch: [70]  [140/312]  eta: 0:01:38  lr: 0.003688  min_lr: 0.003688  loss: 3.7931 (3.8317)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0854  max mem: 31830
Epoch: [70]  [150/312]  eta: 0:01:32  lr: 0.003688  min_lr: 0.003688  loss: 4.0233 (3.8365)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0669  max mem: 31830
Epoch: [70]  [160/312]  eta: 0:01:27  lr: 0.003687  min_lr: 0.003687  loss: 3.9110 (3.8303)  weight_decay: 0.0500 (0.0500)  time: 0.6021  data: 0.1599  max mem: 31830
Epoch: [70]  [170/312]  eta: 0:01:20  lr: 0.003687  min_lr: 0.003687  loss: 4.0924 (3.8498)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.0994  max mem: 31830
Epoch: [70]  [180/312]  eta: 0:01:15  lr: 0.003687  min_lr: 0.003687  loss: 4.1020 (3.8470)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0995  max mem: 31830
Epoch: [70]  [190/312]  eta: 0:01:08  lr: 0.003686  min_lr: 0.003686  loss: 3.6791 (3.8344)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0940  max mem: 31830
Epoch: [70]  [200/312]  eta: 0:01:03  lr: 0.003686  min_lr: 0.003686  loss: 3.5368 (3.8227)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0698  max mem: 31830
Epoch: [70]  [210/312]  eta: 0:00:57  lr: 0.003685  min_lr: 0.003685  loss: 3.8769 (3.8234)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.1273  max mem: 31830
Epoch: [70]  [220/312]  eta: 0:00:51  lr: 0.003685  min_lr: 0.003685  loss: 3.9621 (3.8236)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0583  max mem: 31830
Epoch: [70]  [230/312]  eta: 0:00:45  lr: 0.003685  min_lr: 0.003685  loss: 4.0127 (3.8354)  weight_decay: 0.0500 (0.0500)  time: 0.4831  data: 0.0493  max mem: 31830
Epoch: [70]  [240/312]  eta: 0:00:40  lr: 0.003684  min_lr: 0.003684  loss: 4.0277 (3.8265)  weight_decay: 0.0500 (0.0500)  time: 0.6086  data: 0.1351  max mem: 31830
Epoch: [70]  [250/312]  eta: 0:00:34  lr: 0.003684  min_lr: 0.003684  loss: 3.5776 (3.8216)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0865  max mem: 31830
Epoch: [70]  [260/312]  eta: 0:00:29  lr: 0.003684  min_lr: 0.003684  loss: 3.5776 (3.8175)  weight_decay: 0.0500 (0.0500)  time: 0.4942  data: 0.0442  max mem: 31830
Epoch: [70]  [270/312]  eta: 0:00:23  lr: 0.003683  min_lr: 0.003683  loss: 3.8728 (3.8226)  weight_decay: 0.0500 (0.0500)  time: 0.5750  data: 0.0442  max mem: 31830
Epoch: [70]  [280/312]  eta: 0:00:17  lr: 0.003683  min_lr: 0.003683  loss: 3.8728 (3.8140)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0402  max mem: 31830
Epoch: [70]  [290/312]  eta: 0:00:12  lr: 0.003682  min_lr: 0.003682  loss: 3.4941 (3.8105)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0528  max mem: 31830
Epoch: [70]  [300/312]  eta: 0:00:06  lr: 0.003682  min_lr: 0.003682  loss: 3.5745 (3.8064)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0130  max mem: 31830
Epoch: [70]  [310/312]  eta: 0:00:01  lr: 0.003682  min_lr: 0.003682  loss: 3.8772 (3.8118)  weight_decay: 0.0500 (0.0500)  time: 0.4082  data: 0.0002  max mem: 31830
Epoch: [70]  [311/312]  eta: 0:00:00  lr: 0.003682  min_lr: 0.003682  loss: 3.8772 (3.8137)  weight_decay: 0.0500 (0.0500)  time: 0.4076  data: 0.0001  max mem: 31830
Epoch: [70] Total time: 0:02:52 (0.5513 s / it)
Averaged stats: lr: 0.003682  min_lr: 0.003682  loss: 3.8772 (3.8293)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.6508 (1.6508)  acc1: 69.4010 (69.4010)  acc5: 90.3646 (90.3646)  time: 8.5988  data: 8.4313  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1515 (1.9338)  acc1: 59.2448 (62.6240)  acc5: 83.8542 (84.8640)  time: 1.0728  data: 0.9369  max mem: 31830
Test: Total time: 0:00:09 (1.0976 s / it)
* Acc@1 62.292 Acc@5 84.756 loss 1.945
Accuracy of the model on the 50000 test images: 62.3%
Max accuracy: 65.29%
Epoch: [71]  [  0/312]  eta: 1:05:04  lr: 0.003681  min_lr: 0.003681  loss: 2.9123 (2.9123)  weight_decay: 0.0500 (0.0500)  time: 12.5142  data: 9.2271  max mem: 31830
Epoch: [71]  [ 10/312]  eta: 0:09:00  lr: 0.003681  min_lr: 0.003681  loss: 3.5834 (3.5759)  weight_decay: 0.0500 (0.0500)  time: 1.7910  data: 1.0181  max mem: 31830
Epoch: [71]  [ 20/312]  eta: 0:05:28  lr: 0.003681  min_lr: 0.003681  loss: 4.0142 (3.7377)  weight_decay: 0.0500 (0.0500)  time: 0.5568  data: 0.0989  max mem: 31830
Epoch: [71]  [ 30/312]  eta: 0:04:11  lr: 0.003680  min_lr: 0.003680  loss: 4.0961 (3.8322)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0007  max mem: 31830
Epoch: [71]  [ 40/312]  eta: 0:03:29  lr: 0.003680  min_lr: 0.003680  loss: 4.1238 (3.7963)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0008  max mem: 31830
Epoch: [71]  [ 50/312]  eta: 0:03:03  lr: 0.003680  min_lr: 0.003680  loss: 3.9815 (3.7856)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0007  max mem: 31830
Epoch: [71]  [ 60/312]  eta: 0:02:43  lr: 0.003679  min_lr: 0.003679  loss: 4.0151 (3.7780)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0009  max mem: 31830
Epoch: [71]  [ 70/312]  eta: 0:02:29  lr: 0.003679  min_lr: 0.003679  loss: 4.0151 (3.8026)  weight_decay: 0.0500 (0.0500)  time: 0.4175  data: 0.0010  max mem: 31830
Epoch: [71]  [ 80/312]  eta: 0:02:23  lr: 0.003678  min_lr: 0.003678  loss: 3.8063 (3.7955)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0125  max mem: 31830
Epoch: [71]  [ 90/312]  eta: 0:02:12  lr: 0.003678  min_lr: 0.003678  loss: 3.7932 (3.7906)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0261  max mem: 31830
Epoch: [71]  [100/312]  eta: 0:02:06  lr: 0.003678  min_lr: 0.003678  loss: 3.8846 (3.8152)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0283  max mem: 31830
Epoch: [71]  [110/312]  eta: 0:01:58  lr: 0.003677  min_lr: 0.003677  loss: 4.1405 (3.8494)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0285  max mem: 31830
Epoch: [71]  [120/312]  eta: 0:01:52  lr: 0.003677  min_lr: 0.003677  loss: 4.1074 (3.8700)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0460  max mem: 31830
Epoch: [71]  [130/312]  eta: 0:01:46  lr: 0.003676  min_lr: 0.003676  loss: 4.1375 (3.8890)  weight_decay: 0.0500 (0.0500)  time: 0.5856  data: 0.0439  max mem: 31830
Epoch: [71]  [140/312]  eta: 0:01:40  lr: 0.003676  min_lr: 0.003676  loss: 3.7888 (3.8664)  weight_decay: 0.0500 (0.0500)  time: 0.5890  data: 0.0126  max mem: 31830
Epoch: [71]  [150/312]  eta: 0:01:33  lr: 0.003676  min_lr: 0.003676  loss: 3.5945 (3.8508)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0281  max mem: 31830
Epoch: [71]  [160/312]  eta: 0:01:27  lr: 0.003675  min_lr: 0.003675  loss: 3.7117 (3.8523)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0355  max mem: 31830
Epoch: [71]  [170/312]  eta: 0:01:21  lr: 0.003675  min_lr: 0.003675  loss: 4.0072 (3.8585)  weight_decay: 0.0500 (0.0500)  time: 0.5379  data: 0.0082  max mem: 31830
Epoch: [71]  [180/312]  eta: 0:01:15  lr: 0.003674  min_lr: 0.003674  loss: 4.2669 (3.8768)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0007  max mem: 31830
Epoch: [71]  [190/312]  eta: 0:01:09  lr: 0.003674  min_lr: 0.003674  loss: 4.1195 (3.8801)  weight_decay: 0.0500 (0.0500)  time: 0.5743  data: 0.0009  max mem: 31830
Epoch: [71]  [200/312]  eta: 0:01:03  lr: 0.003674  min_lr: 0.003674  loss: 3.8263 (3.8769)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0070  max mem: 31830
Epoch: [71]  [210/312]  eta: 0:00:57  lr: 0.003673  min_lr: 0.003673  loss: 3.9669 (3.8853)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0075  max mem: 31830
Epoch: [71]  [220/312]  eta: 0:00:52  lr: 0.003673  min_lr: 0.003673  loss: 3.9618 (3.8771)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0156  max mem: 31830
Epoch: [71]  [230/312]  eta: 0:00:46  lr: 0.003672  min_lr: 0.003672  loss: 3.8523 (3.8796)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0151  max mem: 31830
Epoch: [71]  [240/312]  eta: 0:00:40  lr: 0.003672  min_lr: 0.003672  loss: 3.8708 (3.8799)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0010  max mem: 31830
Epoch: [71]  [250/312]  eta: 0:00:34  lr: 0.003672  min_lr: 0.003672  loss: 3.8708 (3.8836)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0010  max mem: 31830
Epoch: [71]  [260/312]  eta: 0:00:29  lr: 0.003671  min_lr: 0.003671  loss: 3.9742 (3.8765)  weight_decay: 0.0500 (0.0500)  time: 0.5821  data: 0.0152  max mem: 31830
Epoch: [71]  [270/312]  eta: 0:00:23  lr: 0.003671  min_lr: 0.003671  loss: 3.9193 (3.8805)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.0151  max mem: 31830
Epoch: [71]  [280/312]  eta: 0:00:17  lr: 0.003670  min_lr: 0.003670  loss: 3.9821 (3.8806)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0026  max mem: 31830
Epoch: [71]  [290/312]  eta: 0:00:12  lr: 0.003670  min_lr: 0.003670  loss: 4.0281 (3.8842)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0023  max mem: 31830
Epoch: [71]  [300/312]  eta: 0:00:06  lr: 0.003670  min_lr: 0.003670  loss: 4.1026 (3.8888)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0002  max mem: 31830
Epoch: [71]  [310/312]  eta: 0:00:01  lr: 0.003669  min_lr: 0.003669  loss: 4.0788 (3.8928)  weight_decay: 0.0500 (0.0500)  time: 0.4678  data: 0.0001  max mem: 31830
Epoch: [71]  [311/312]  eta: 0:00:00  lr: 0.003669  min_lr: 0.003669  loss: 4.0788 (3.8956)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [71] Total time: 0:02:53 (0.5558 s / it)
Averaged stats: lr: 0.003669  min_lr: 0.003669  loss: 4.0788 (3.8394)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.7675 (1.7675)  acc1: 69.1406 (69.1406)  acc5: 90.1042 (90.1042)  time: 8.4309  data: 8.2639  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9699 (1.9176)  acc1: 62.3698 (63.6640)  acc5: 86.1979 (86.1440)  time: 1.0680  data: 0.9312  max mem: 31830
Test: Total time: 0:00:09 (1.0843 s / it)
* Acc@1 63.638 Acc@5 86.518 loss 1.919
Accuracy of the model on the 50000 test images: 63.6%
Max accuracy: 65.29%
Epoch: [72]  [  0/312]  eta: 1:01:16  lr: 0.003669  min_lr: 0.003669  loss: 3.3809 (3.3809)  weight_decay: 0.0500 (0.0500)  time: 11.7837  data: 11.3815  max mem: 31830
Epoch: [72]  [ 10/312]  eta: 0:08:35  lr: 0.003669  min_lr: 0.003669  loss: 3.8232 (3.6917)  weight_decay: 0.0500 (0.0500)  time: 1.7079  data: 1.0353  max mem: 31830
Epoch: [72]  [ 20/312]  eta: 0:05:23  lr: 0.003668  min_lr: 0.003668  loss: 4.1203 (3.7840)  weight_decay: 0.0500 (0.0500)  time: 0.5740  data: 0.0007  max mem: 31830
Epoch: [72]  [ 30/312]  eta: 0:04:10  lr: 0.003668  min_lr: 0.003668  loss: 3.9806 (3.7446)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0007  max mem: 31830
Epoch: [72]  [ 40/312]  eta: 0:03:28  lr: 0.003668  min_lr: 0.003668  loss: 3.7843 (3.7749)  weight_decay: 0.0500 (0.0500)  time: 0.4092  data: 0.0013  max mem: 31830
Epoch: [72]  [ 50/312]  eta: 0:03:02  lr: 0.003667  min_lr: 0.003667  loss: 4.0284 (3.8598)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0014  max mem: 31830
Epoch: [72]  [ 60/312]  eta: 0:02:42  lr: 0.003667  min_lr: 0.003667  loss: 4.0170 (3.8660)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [72]  [ 70/312]  eta: 0:02:31  lr: 0.003666  min_lr: 0.003666  loss: 3.8344 (3.8548)  weight_decay: 0.0500 (0.0500)  time: 0.4460  data: 0.0264  max mem: 31830
Epoch: [72]  [ 80/312]  eta: 0:02:25  lr: 0.003666  min_lr: 0.003666  loss: 3.6796 (3.8317)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.0821  max mem: 31830
Epoch: [72]  [ 90/312]  eta: 0:02:14  lr: 0.003666  min_lr: 0.003666  loss: 3.7718 (3.8324)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0566  max mem: 31830
Epoch: [72]  [100/312]  eta: 0:02:07  lr: 0.003665  min_lr: 0.003665  loss: 3.7718 (3.8061)  weight_decay: 0.0500 (0.0500)  time: 0.4959  data: 0.0320  max mem: 31830
Epoch: [72]  [110/312]  eta: 0:01:58  lr: 0.003665  min_lr: 0.003665  loss: 3.7913 (3.8244)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0320  max mem: 31830
Epoch: [72]  [120/312]  eta: 0:01:51  lr: 0.003664  min_lr: 0.003664  loss: 4.1562 (3.8240)  weight_decay: 0.0500 (0.0500)  time: 0.4830  data: 0.0410  max mem: 31830
Epoch: [72]  [130/312]  eta: 0:01:46  lr: 0.003664  min_lr: 0.003664  loss: 3.3377 (3.7872)  weight_decay: 0.0500 (0.0500)  time: 0.5825  data: 0.0868  max mem: 31830
Epoch: [72]  [140/312]  eta: 0:01:40  lr: 0.003664  min_lr: 0.003664  loss: 3.7009 (3.8029)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0465  max mem: 31830
Epoch: [72]  [150/312]  eta: 0:01:33  lr: 0.003663  min_lr: 0.003663  loss: 3.9899 (3.8086)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0387  max mem: 31830
Epoch: [72]  [160/312]  eta: 0:01:28  lr: 0.003663  min_lr: 0.003663  loss: 4.0752 (3.8114)  weight_decay: 0.0500 (0.0500)  time: 0.5564  data: 0.0762  max mem: 31830
Epoch: [72]  [170/312]  eta: 0:01:20  lr: 0.003662  min_lr: 0.003662  loss: 4.0489 (3.8221)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0381  max mem: 31830
Epoch: [72]  [180/312]  eta: 0:01:15  lr: 0.003662  min_lr: 0.003662  loss: 4.0159 (3.8275)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0386  max mem: 31830
Epoch: [72]  [190/312]  eta: 0:01:09  lr: 0.003662  min_lr: 0.003662  loss: 4.0966 (3.8391)  weight_decay: 0.0500 (0.0500)  time: 0.5517  data: 0.0389  max mem: 31830
Epoch: [72]  [200/312]  eta: 0:01:03  lr: 0.003661  min_lr: 0.003661  loss: 4.0981 (3.8371)  weight_decay: 0.0500 (0.0500)  time: 0.4952  data: 0.0386  max mem: 31830
Epoch: [72]  [210/312]  eta: 0:00:57  lr: 0.003661  min_lr: 0.003661  loss: 3.6416 (3.8266)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0639  max mem: 31830
Epoch: [72]  [220/312]  eta: 0:00:51  lr: 0.003660  min_lr: 0.003660  loss: 3.6416 (3.8148)  weight_decay: 0.0500 (0.0500)  time: 0.5682  data: 0.0267  max mem: 31830
Epoch: [72]  [230/312]  eta: 0:00:46  lr: 0.003660  min_lr: 0.003660  loss: 3.6409 (3.8014)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0243  max mem: 31830
Epoch: [72]  [240/312]  eta: 0:00:40  lr: 0.003660  min_lr: 0.003660  loss: 3.6409 (3.7995)  weight_decay: 0.0500 (0.0500)  time: 0.6046  data: 0.0483  max mem: 31830
Epoch: [72]  [250/312]  eta: 0:00:34  lr: 0.003659  min_lr: 0.003659  loss: 3.7846 (3.7959)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0251  max mem: 31830
Epoch: [72]  [260/312]  eta: 0:00:29  lr: 0.003659  min_lr: 0.003659  loss: 4.0135 (3.8005)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0179  max mem: 31830
Epoch: [72]  [270/312]  eta: 0:00:23  lr: 0.003658  min_lr: 0.003658  loss: 3.8778 (3.8028)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0179  max mem: 31830
Epoch: [72]  [280/312]  eta: 0:00:17  lr: 0.003658  min_lr: 0.003658  loss: 3.8796 (3.8081)  weight_decay: 0.0500 (0.0500)  time: 0.5184  data: 0.0141  max mem: 31830
Epoch: [72]  [290/312]  eta: 0:00:12  lr: 0.003658  min_lr: 0.003658  loss: 4.0595 (3.8123)  weight_decay: 0.0500 (0.0500)  time: 0.5827  data: 0.0259  max mem: 31830
Epoch: [72]  [300/312]  eta: 0:00:06  lr: 0.003657  min_lr: 0.003657  loss: 4.0354 (3.8147)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0122  max mem: 31830
Epoch: [72]  [310/312]  eta: 0:00:01  lr: 0.003657  min_lr: 0.003657  loss: 3.8942 (3.8051)  weight_decay: 0.0500 (0.0500)  time: 0.3905  data: 0.0001  max mem: 31830
Epoch: [72]  [311/312]  eta: 0:00:00  lr: 0.003657  min_lr: 0.003657  loss: 3.8942 (3.8048)  weight_decay: 0.0500 (0.0500)  time: 0.3903  data: 0.0001  max mem: 31830
Epoch: [72] Total time: 0:02:52 (0.5529 s / it)
Averaged stats: lr: 0.003657  min_lr: 0.003657  loss: 3.8942 (3.8111)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.4605 (1.4605)  acc1: 72.0052 (72.0052)  acc5: 91.0156 (91.0156)  time: 8.1363  data: 7.9689  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8651 (1.7254)  acc1: 60.0260 (63.2800)  acc5: 84.6354 (85.6640)  time: 1.0399  data: 0.9035  max mem: 31830
Test: Total time: 0:00:09 (1.0495 s / it)
* Acc@1 63.458 Acc@5 85.868 loss 1.723
Accuracy of the model on the 50000 test images: 63.5%
Max accuracy: 65.29%
Epoch: [73]  [  0/312]  eta: 0:55:27  lr: 0.003657  min_lr: 0.003657  loss: 4.6644 (4.6644)  weight_decay: 0.0500 (0.0500)  time: 10.6635  data: 9.8145  max mem: 31830
Epoch: [73]  [ 10/312]  eta: 0:08:42  lr: 0.003656  min_lr: 0.003656  loss: 4.0610 (4.1510)  weight_decay: 0.0500 (0.0500)  time: 1.7286  data: 0.9387  max mem: 31830
Epoch: [73]  [ 20/312]  eta: 0:05:31  lr: 0.003656  min_lr: 0.003656  loss: 3.9775 (3.9073)  weight_decay: 0.0500 (0.0500)  time: 0.6571  data: 0.0259  max mem: 31830
Epoch: [73]  [ 30/312]  eta: 0:04:13  lr: 0.003656  min_lr: 0.003656  loss: 4.1335 (3.9895)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0008  max mem: 31830
Epoch: [73]  [ 40/312]  eta: 0:03:30  lr: 0.003655  min_lr: 0.003655  loss: 4.1717 (3.9673)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0008  max mem: 31830
Epoch: [73]  [ 50/312]  eta: 0:03:06  lr: 0.003655  min_lr: 0.003655  loss: 3.7576 (3.8722)  weight_decay: 0.0500 (0.0500)  time: 0.4270  data: 0.0068  max mem: 31830
Epoch: [73]  [ 60/312]  eta: 0:02:46  lr: 0.003654  min_lr: 0.003654  loss: 3.6701 (3.8645)  weight_decay: 0.0500 (0.0500)  time: 0.4299  data: 0.0075  max mem: 31830
Epoch: [73]  [ 70/312]  eta: 0:02:38  lr: 0.003654  min_lr: 0.003654  loss: 3.8614 (3.8574)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0329  max mem: 31830
Epoch: [73]  [ 80/312]  eta: 0:02:30  lr: 0.003654  min_lr: 0.003654  loss: 4.0164 (3.8595)  weight_decay: 0.0500 (0.0500)  time: 0.6104  data: 0.0465  max mem: 31830
Epoch: [73]  [ 90/312]  eta: 0:02:19  lr: 0.003653  min_lr: 0.003653  loss: 3.9868 (3.8276)  weight_decay: 0.0500 (0.0500)  time: 0.5260  data: 0.0275  max mem: 31830
Epoch: [73]  [100/312]  eta: 0:02:12  lr: 0.003653  min_lr: 0.003653  loss: 3.4115 (3.7959)  weight_decay: 0.0500 (0.0500)  time: 0.5378  data: 0.0266  max mem: 31830
Epoch: [73]  [110/312]  eta: 0:02:02  lr: 0.003652  min_lr: 0.003652  loss: 3.6242 (3.7841)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0142  max mem: 31830
Epoch: [73]  [120/312]  eta: 0:01:56  lr: 0.003652  min_lr: 0.003652  loss: 3.9105 (3.7933)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0191  max mem: 31830
Epoch: [73]  [130/312]  eta: 0:01:51  lr: 0.003652  min_lr: 0.003652  loss: 4.0437 (3.7898)  weight_decay: 0.0500 (0.0500)  time: 0.6432  data: 0.0308  max mem: 31830
Epoch: [73]  [140/312]  eta: 0:01:42  lr: 0.003651  min_lr: 0.003651  loss: 4.0437 (3.8102)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0133  max mem: 31830
Epoch: [73]  [150/312]  eta: 0:01:36  lr: 0.003651  min_lr: 0.003651  loss: 3.8172 (3.8021)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0152  max mem: 31830
Epoch: [73]  [160/312]  eta: 0:01:30  lr: 0.003650  min_lr: 0.003650  loss: 3.8793 (3.8050)  weight_decay: 0.0500 (0.0500)  time: 0.5790  data: 0.0146  max mem: 31830
Epoch: [73]  [170/312]  eta: 0:01:23  lr: 0.003650  min_lr: 0.003650  loss: 3.9811 (3.8098)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0140  max mem: 31830
Epoch: [73]  [180/312]  eta: 0:01:17  lr: 0.003649  min_lr: 0.003649  loss: 4.0093 (3.8068)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0142  max mem: 31830
Epoch: [73]  [190/312]  eta: 0:01:10  lr: 0.003649  min_lr: 0.003649  loss: 4.0915 (3.8121)  weight_decay: 0.0500 (0.0500)  time: 0.4858  data: 0.0016  max mem: 31830
Epoch: [73]  [200/312]  eta: 0:01:04  lr: 0.003649  min_lr: 0.003649  loss: 3.9874 (3.8081)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0154  max mem: 31830
Epoch: [73]  [210/312]  eta: 0:00:59  lr: 0.003648  min_lr: 0.003648  loss: 3.7519 (3.8115)  weight_decay: 0.0500 (0.0500)  time: 0.6186  data: 0.0213  max mem: 31830
Epoch: [73]  [220/312]  eta: 0:00:52  lr: 0.003648  min_lr: 0.003648  loss: 4.0230 (3.8152)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0072  max mem: 31830
Epoch: [73]  [230/312]  eta: 0:00:47  lr: 0.003647  min_lr: 0.003647  loss: 4.0230 (3.8167)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0149  max mem: 31830
Epoch: [73]  [240/312]  eta: 0:00:41  lr: 0.003647  min_lr: 0.003647  loss: 4.0138 (3.8273)  weight_decay: 0.0500 (0.0500)  time: 0.6161  data: 0.0316  max mem: 31830
Epoch: [73]  [250/312]  eta: 0:00:35  lr: 0.003647  min_lr: 0.003647  loss: 3.9493 (3.8176)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0179  max mem: 31830
Epoch: [73]  [260/312]  eta: 0:00:29  lr: 0.003646  min_lr: 0.003646  loss: 3.6393 (3.8136)  weight_decay: 0.0500 (0.0500)  time: 0.5306  data: 0.0077  max mem: 31830
Epoch: [73]  [270/312]  eta: 0:00:23  lr: 0.003646  min_lr: 0.003646  loss: 3.7970 (3.8112)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0072  max mem: 31830
Epoch: [73]  [280/312]  eta: 0:00:18  lr: 0.003645  min_lr: 0.003645  loss: 3.6885 (3.8002)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0124  max mem: 31830
Epoch: [73]  [290/312]  eta: 0:00:12  lr: 0.003645  min_lr: 0.003645  loss: 3.5866 (3.7979)  weight_decay: 0.0500 (0.0500)  time: 0.6012  data: 0.0122  max mem: 31830
Epoch: [73]  [300/312]  eta: 0:00:06  lr: 0.003645  min_lr: 0.003645  loss: 3.8619 (3.7952)  weight_decay: 0.0500 (0.0500)  time: 0.4632  data: 0.0002  max mem: 31830
Epoch: [73]  [310/312]  eta: 0:00:01  lr: 0.003644  min_lr: 0.003644  loss: 4.0779 (3.8043)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [73]  [311/312]  eta: 0:00:00  lr: 0.003644  min_lr: 0.003644  loss: 4.0090 (3.8007)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [73] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.003644  min_lr: 0.003644  loss: 4.0090 (3.8201)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.8266 (1.8266)  acc1: 68.7500 (68.7500)  acc5: 87.3698 (87.3698)  time: 9.0514  data: 8.8841  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0764 (1.9540)  acc1: 61.1979 (63.1680)  acc5: 84.6354 (85.2000)  time: 1.1223  data: 0.9872  max mem: 31830
Test: Total time: 0:00:10 (1.1361 s / it)
* Acc@1 62.760 Acc@5 85.290 loss 1.943
Accuracy of the model on the 50000 test images: 62.8%
Max accuracy: 65.29%
Epoch: [74]  [  0/312]  eta: 0:59:30  lr: 0.003644  min_lr: 0.003644  loss: 3.6599 (3.6599)  weight_decay: 0.0500 (0.0500)  time: 11.4451  data: 9.4646  max mem: 31830
Epoch: [74]  [ 10/312]  eta: 0:08:04  lr: 0.003644  min_lr: 0.003644  loss: 4.0729 (3.7767)  weight_decay: 0.0500 (0.0500)  time: 1.6035  data: 0.9971  max mem: 31830
Epoch: [74]  [ 20/312]  eta: 0:05:16  lr: 0.003643  min_lr: 0.003643  loss: 4.1192 (3.8791)  weight_decay: 0.0500 (0.0500)  time: 0.5653  data: 0.0758  max mem: 31830
Epoch: [74]  [ 30/312]  eta: 0:04:03  lr: 0.003643  min_lr: 0.003643  loss: 3.9575 (3.7648)  weight_decay: 0.0500 (0.0500)  time: 0.4554  data: 0.0010  max mem: 31830
Epoch: [74]  [ 40/312]  eta: 0:03:25  lr: 0.003642  min_lr: 0.003642  loss: 3.6196 (3.7808)  weight_decay: 0.0500 (0.0500)  time: 0.4093  data: 0.0007  max mem: 31830
Epoch: [74]  [ 50/312]  eta: 0:03:09  lr: 0.003642  min_lr: 0.003642  loss: 3.6196 (3.7640)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0230  max mem: 31830
Epoch: [74]  [ 60/312]  eta: 0:02:48  lr: 0.003642  min_lr: 0.003642  loss: 3.9022 (3.7791)  weight_decay: 0.0500 (0.0500)  time: 0.4891  data: 0.0231  max mem: 31830
Epoch: [74]  [ 70/312]  eta: 0:02:44  lr: 0.003641  min_lr: 0.003641  loss: 3.8876 (3.7883)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.0836  max mem: 31830
Epoch: [74]  [ 80/312]  eta: 0:02:31  lr: 0.003641  min_lr: 0.003641  loss: 3.7909 (3.7703)  weight_decay: 0.0500 (0.0500)  time: 0.6157  data: 0.0835  max mem: 31830
Epoch: [74]  [ 90/312]  eta: 0:02:20  lr: 0.003640  min_lr: 0.003640  loss: 3.8102 (3.7793)  weight_decay: 0.0500 (0.0500)  time: 0.4653  data: 0.0303  max mem: 31830
Epoch: [74]  [100/312]  eta: 0:02:14  lr: 0.003640  min_lr: 0.003640  loss: 3.8190 (3.7620)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0966  max mem: 31830
Epoch: [74]  [110/312]  eta: 0:02:03  lr: 0.003640  min_lr: 0.003640  loss: 4.0529 (3.7867)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0669  max mem: 31830
Epoch: [74]  [120/312]  eta: 0:01:58  lr: 0.003639  min_lr: 0.003639  loss: 4.1069 (3.7830)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0389  max mem: 31830
Epoch: [74]  [130/312]  eta: 0:01:52  lr: 0.003639  min_lr: 0.003639  loss: 3.8032 (3.7879)  weight_decay: 0.0500 (0.0500)  time: 0.6440  data: 0.0722  max mem: 31830
Epoch: [74]  [140/312]  eta: 0:01:43  lr: 0.003638  min_lr: 0.003638  loss: 3.9017 (3.8000)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0340  max mem: 31830
Epoch: [74]  [150/312]  eta: 0:01:36  lr: 0.003638  min_lr: 0.003638  loss: 3.8918 (3.8119)  weight_decay: 0.0500 (0.0500)  time: 0.4789  data: 0.0125  max mem: 31830
Epoch: [74]  [160/312]  eta: 0:01:30  lr: 0.003638  min_lr: 0.003638  loss: 3.7868 (3.8051)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0126  max mem: 31830
Epoch: [74]  [170/312]  eta: 0:01:23  lr: 0.003637  min_lr: 0.003637  loss: 3.7478 (3.8055)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0475  max mem: 31830
Epoch: [74]  [180/312]  eta: 0:01:17  lr: 0.003637  min_lr: 0.003637  loss: 3.9846 (3.8177)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0710  max mem: 31830
Epoch: [74]  [190/312]  eta: 0:01:10  lr: 0.003636  min_lr: 0.003636  loss: 4.0516 (3.8221)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0244  max mem: 31830
Epoch: [74]  [200/312]  eta: 0:01:05  lr: 0.003636  min_lr: 0.003636  loss: 3.7784 (3.7986)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0475  max mem: 31830
Epoch: [74]  [210/312]  eta: 0:00:59  lr: 0.003635  min_lr: 0.003635  loss: 3.7934 (3.7958)  weight_decay: 0.0500 (0.0500)  time: 0.6702  data: 0.0989  max mem: 31830
Epoch: [74]  [220/312]  eta: 0:00:53  lr: 0.003635  min_lr: 0.003635  loss: 3.9302 (3.8046)  weight_decay: 0.0500 (0.0500)  time: 0.5308  data: 0.0526  max mem: 31830
Epoch: [74]  [230/312]  eta: 0:00:47  lr: 0.003635  min_lr: 0.003635  loss: 4.1243 (3.8145)  weight_decay: 0.0500 (0.0500)  time: 0.5516  data: 0.0546  max mem: 31830
Epoch: [74]  [240/312]  eta: 0:00:41  lr: 0.003634  min_lr: 0.003634  loss: 4.0740 (3.8148)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.0545  max mem: 31830
Epoch: [74]  [250/312]  eta: 0:00:35  lr: 0.003634  min_lr: 0.003634  loss: 3.8773 (3.8092)  weight_decay: 0.0500 (0.0500)  time: 0.5023  data: 0.0419  max mem: 31830
Epoch: [74]  [260/312]  eta: 0:00:30  lr: 0.003633  min_lr: 0.003633  loss: 4.0353 (3.8171)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0894  max mem: 31830
Epoch: [74]  [270/312]  eta: 0:00:23  lr: 0.003633  min_lr: 0.003633  loss: 4.0390 (3.8131)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0485  max mem: 31830
Epoch: [74]  [280/312]  eta: 0:00:18  lr: 0.003633  min_lr: 0.003633  loss: 3.7882 (3.8152)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0261  max mem: 31830
Epoch: [74]  [290/312]  eta: 0:00:12  lr: 0.003632  min_lr: 0.003632  loss: 3.9976 (3.8107)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0451  max mem: 31830
Epoch: [74]  [300/312]  eta: 0:00:06  lr: 0.003632  min_lr: 0.003632  loss: 3.9976 (3.8075)  weight_decay: 0.0500 (0.0500)  time: 0.4449  data: 0.0193  max mem: 31830
Epoch: [74]  [310/312]  eta: 0:00:01  lr: 0.003631  min_lr: 0.003631  loss: 3.8865 (3.8036)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [74]  [311/312]  eta: 0:00:00  lr: 0.003631  min_lr: 0.003631  loss: 3.4257 (3.7995)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [74] Total time: 0:02:55 (0.5610 s / it)
Averaged stats: lr: 0.003631  min_lr: 0.003631  loss: 3.4257 (3.8179)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3030 (1.3030)  acc1: 72.1354 (72.1354)  acc5: 91.0156 (91.0156)  time: 8.5240  data: 8.3566  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7635 (1.6036)  acc1: 63.2812 (64.1440)  acc5: 85.8073 (86.5920)  time: 1.0649  data: 0.9286  max mem: 31830
Test: Total time: 0:00:09 (1.0870 s / it)
* Acc@1 64.088 Acc@5 86.560 loss 1.608
Accuracy of the model on the 50000 test images: 64.1%
Max accuracy: 65.29%
Epoch: [75]  [  0/312]  eta: 1:00:00  lr: 0.003631  min_lr: 0.003631  loss: 4.1203 (4.1203)  weight_decay: 0.0500 (0.0500)  time: 11.5416  data: 9.0692  max mem: 31830
Epoch: [75]  [ 10/312]  eta: 0:08:29  lr: 0.003631  min_lr: 0.003631  loss: 3.6561 (3.5868)  weight_decay: 0.0500 (0.0500)  time: 1.6858  data: 0.9622  max mem: 31830
Epoch: [75]  [ 20/312]  eta: 0:05:19  lr: 0.003630  min_lr: 0.003630  loss: 3.4554 (3.5786)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0760  max mem: 31830
Epoch: [75]  [ 30/312]  eta: 0:04:05  lr: 0.003630  min_lr: 0.003630  loss: 3.9145 (3.6027)  weight_decay: 0.0500 (0.0500)  time: 0.4216  data: 0.0006  max mem: 31830
Epoch: [75]  [ 40/312]  eta: 0:03:24  lr: 0.003630  min_lr: 0.003630  loss: 3.8045 (3.6301)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0008  max mem: 31830
Epoch: [75]  [ 50/312]  eta: 0:03:04  lr: 0.003629  min_lr: 0.003629  loss: 3.8338 (3.6824)  weight_decay: 0.0500 (0.0500)  time: 0.4427  data: 0.0439  max mem: 31830
Epoch: [75]  [ 60/312]  eta: 0:02:44  lr: 0.003629  min_lr: 0.003629  loss: 4.0657 (3.7489)  weight_decay: 0.0500 (0.0500)  time: 0.4446  data: 0.0437  max mem: 31830
Epoch: [75]  [ 70/312]  eta: 0:02:34  lr: 0.003628  min_lr: 0.003628  loss: 4.1128 (3.7603)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0482  max mem: 31830
Epoch: [75]  [ 80/312]  eta: 0:02:25  lr: 0.003628  min_lr: 0.003628  loss: 3.9512 (3.7774)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.1220  max mem: 31830
Epoch: [75]  [ 90/312]  eta: 0:02:14  lr: 0.003627  min_lr: 0.003627  loss: 3.9512 (3.7745)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0744  max mem: 31830
Epoch: [75]  [100/312]  eta: 0:02:07  lr: 0.003627  min_lr: 0.003627  loss: 3.7280 (3.7421)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0776  max mem: 31830
Epoch: [75]  [110/312]  eta: 0:01:58  lr: 0.003627  min_lr: 0.003627  loss: 3.3790 (3.7489)  weight_decay: 0.0500 (0.0500)  time: 0.5160  data: 0.0784  max mem: 31830
Epoch: [75]  [120/312]  eta: 0:01:53  lr: 0.003626  min_lr: 0.003626  loss: 3.9597 (3.7562)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0590  max mem: 31830
Epoch: [75]  [130/312]  eta: 0:01:47  lr: 0.003626  min_lr: 0.003626  loss: 3.8165 (3.7618)  weight_decay: 0.0500 (0.0500)  time: 0.6152  data: 0.1429  max mem: 31830
Epoch: [75]  [140/312]  eta: 0:01:39  lr: 0.003625  min_lr: 0.003625  loss: 3.9331 (3.7581)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0853  max mem: 31830
Epoch: [75]  [150/312]  eta: 0:01:33  lr: 0.003625  min_lr: 0.003625  loss: 3.8054 (3.7679)  weight_decay: 0.0500 (0.0500)  time: 0.4850  data: 0.0806  max mem: 31830
Epoch: [75]  [160/312]  eta: 0:01:28  lr: 0.003625  min_lr: 0.003625  loss: 3.8826 (3.7807)  weight_decay: 0.0500 (0.0500)  time: 0.5836  data: 0.1560  max mem: 31830
Epoch: [75]  [170/312]  eta: 0:01:21  lr: 0.003624  min_lr: 0.003624  loss: 3.9295 (3.7869)  weight_decay: 0.0500 (0.0500)  time: 0.5478  data: 0.0768  max mem: 31830
Epoch: [75]  [180/312]  eta: 0:01:16  lr: 0.003624  min_lr: 0.003624  loss: 4.0254 (3.8012)  weight_decay: 0.0500 (0.0500)  time: 0.5619  data: 0.0694  max mem: 31830
Epoch: [75]  [190/312]  eta: 0:01:09  lr: 0.003623  min_lr: 0.003623  loss: 3.9085 (3.8023)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0687  max mem: 31830
Epoch: [75]  [200/312]  eta: 0:01:04  lr: 0.003623  min_lr: 0.003623  loss: 3.9085 (3.8101)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.0624  max mem: 31830
Epoch: [75]  [210/312]  eta: 0:00:58  lr: 0.003622  min_lr: 0.003622  loss: 4.0945 (3.8241)  weight_decay: 0.0500 (0.0500)  time: 0.6093  data: 0.1125  max mem: 31830
Epoch: [75]  [220/312]  eta: 0:00:52  lr: 0.003622  min_lr: 0.003622  loss: 4.0812 (3.8282)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0508  max mem: 31830
Epoch: [75]  [230/312]  eta: 0:00:46  lr: 0.003622  min_lr: 0.003622  loss: 3.8810 (3.8260)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0558  max mem: 31830
Epoch: [75]  [240/312]  eta: 0:00:40  lr: 0.003621  min_lr: 0.003621  loss: 3.7644 (3.8280)  weight_decay: 0.0500 (0.0500)  time: 0.5802  data: 0.0693  max mem: 31830
Epoch: [75]  [250/312]  eta: 0:00:35  lr: 0.003621  min_lr: 0.003621  loss: 3.7644 (3.8193)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0419  max mem: 31830
Epoch: [75]  [260/312]  eta: 0:00:29  lr: 0.003620  min_lr: 0.003620  loss: 3.8419 (3.8151)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0687  max mem: 31830
Epoch: [75]  [270/312]  eta: 0:00:23  lr: 0.003620  min_lr: 0.003620  loss: 3.8686 (3.8182)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0411  max mem: 31830
Epoch: [75]  [280/312]  eta: 0:00:17  lr: 0.003619  min_lr: 0.003619  loss: 4.1374 (3.8297)  weight_decay: 0.0500 (0.0500)  time: 0.5067  data: 0.0287  max mem: 31830
Epoch: [75]  [290/312]  eta: 0:00:12  lr: 0.003619  min_lr: 0.003619  loss: 4.1428 (3.8271)  weight_decay: 0.0500 (0.0500)  time: 0.5682  data: 0.0478  max mem: 31830
Epoch: [75]  [300/312]  eta: 0:00:06  lr: 0.003619  min_lr: 0.003619  loss: 3.9304 (3.8276)  weight_decay: 0.0500 (0.0500)  time: 0.4765  data: 0.0196  max mem: 31830
Epoch: [75]  [310/312]  eta: 0:00:01  lr: 0.003618  min_lr: 0.003618  loss: 3.7411 (3.8232)  weight_decay: 0.0500 (0.0500)  time: 0.3853  data: 0.0001  max mem: 31830
Epoch: [75]  [311/312]  eta: 0:00:00  lr: 0.003618  min_lr: 0.003618  loss: 3.7411 (3.8237)  weight_decay: 0.0500 (0.0500)  time: 0.3853  data: 0.0001  max mem: 31830
Epoch: [75] Total time: 0:02:52 (0.5537 s / it)
Averaged stats: lr: 0.003618  min_lr: 0.003618  loss: 3.7411 (3.8121)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.3962 (1.3962)  acc1: 70.9635 (70.9635)  acc5: 91.4062 (91.4062)  time: 8.5874  data: 8.4241  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7799 (1.7501)  acc1: 62.3698 (63.4080)  acc5: 86.4583 (86.2720)  time: 1.0738  data: 0.9361  max mem: 31830
Test: Total time: 0:00:09 (1.0933 s / it)
* Acc@1 63.540 Acc@5 86.202 loss 1.752
Accuracy of the model on the 50000 test images: 63.5%
Max accuracy: 65.29%
Epoch: [76]  [  0/312]  eta: 1:00:49  lr: 0.003618  min_lr: 0.003618  loss: 3.9834 (3.9834)  weight_decay: 0.0500 (0.0500)  time: 11.6983  data: 8.0724  max mem: 31830
Epoch: [76]  [ 10/312]  eta: 0:08:36  lr: 0.003618  min_lr: 0.003618  loss: 4.0956 (3.9281)  weight_decay: 0.0500 (0.0500)  time: 1.7108  data: 0.9612  max mem: 31830
Epoch: [76]  [ 20/312]  eta: 0:05:22  lr: 0.003617  min_lr: 0.003617  loss: 3.8818 (3.7800)  weight_decay: 0.0500 (0.0500)  time: 0.5750  data: 0.1257  max mem: 31830
Epoch: [76]  [ 30/312]  eta: 0:04:07  lr: 0.003617  min_lr: 0.003617  loss: 3.6955 (3.7811)  weight_decay: 0.0500 (0.0500)  time: 0.4189  data: 0.0010  max mem: 31830
Epoch: [76]  [ 40/312]  eta: 0:03:26  lr: 0.003616  min_lr: 0.003616  loss: 3.6955 (3.7771)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0007  max mem: 31830
Epoch: [76]  [ 50/312]  eta: 0:03:00  lr: 0.003616  min_lr: 0.003616  loss: 3.9263 (3.7710)  weight_decay: 0.0500 (0.0500)  time: 0.4007  data: 0.0007  max mem: 31830
Epoch: [76]  [ 60/312]  eta: 0:02:41  lr: 0.003616  min_lr: 0.003616  loss: 3.9944 (3.7845)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0008  max mem: 31830
Epoch: [76]  [ 70/312]  eta: 0:02:31  lr: 0.003615  min_lr: 0.003615  loss: 3.7199 (3.7727)  weight_decay: 0.0500 (0.0500)  time: 0.4689  data: 0.0127  max mem: 31830
Epoch: [76]  [ 80/312]  eta: 0:02:24  lr: 0.003615  min_lr: 0.003615  loss: 3.6136 (3.7429)  weight_decay: 0.0500 (0.0500)  time: 0.5677  data: 0.0133  max mem: 31830
Epoch: [76]  [ 90/312]  eta: 0:02:14  lr: 0.003614  min_lr: 0.003614  loss: 3.6912 (3.7382)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0377  max mem: 31830
Epoch: [76]  [100/312]  eta: 0:02:08  lr: 0.003614  min_lr: 0.003614  loss: 3.8243 (3.7398)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0707  max mem: 31830
Epoch: [76]  [110/312]  eta: 0:01:59  lr: 0.003613  min_lr: 0.003613  loss: 3.7731 (3.7376)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0347  max mem: 31830
Epoch: [76]  [120/312]  eta: 0:01:53  lr: 0.003613  min_lr: 0.003613  loss: 3.9277 (3.7542)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0181  max mem: 31830
Epoch: [76]  [130/312]  eta: 0:01:47  lr: 0.003613  min_lr: 0.003613  loss: 3.9950 (3.7545)  weight_decay: 0.0500 (0.0500)  time: 0.6076  data: 0.0340  max mem: 31830
Epoch: [76]  [140/312]  eta: 0:01:39  lr: 0.003612  min_lr: 0.003612  loss: 3.5463 (3.7371)  weight_decay: 0.0500 (0.0500)  time: 0.5094  data: 0.0285  max mem: 31830
Epoch: [76]  [150/312]  eta: 0:01:34  lr: 0.003612  min_lr: 0.003612  loss: 3.7890 (3.7575)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0126  max mem: 31830
Epoch: [76]  [160/312]  eta: 0:01:28  lr: 0.003611  min_lr: 0.003611  loss: 4.0516 (3.7748)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.0111  max mem: 31830
Epoch: [76]  [170/312]  eta: 0:01:22  lr: 0.003611  min_lr: 0.003611  loss: 4.0516 (3.7710)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.0220  max mem: 31830
Epoch: [76]  [180/312]  eta: 0:01:16  lr: 0.003610  min_lr: 0.003610  loss: 4.0103 (3.7780)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0118  max mem: 31830
Epoch: [76]  [190/312]  eta: 0:01:09  lr: 0.003610  min_lr: 0.003610  loss: 4.0103 (3.7822)  weight_decay: 0.0500 (0.0500)  time: 0.4461  data: 0.0007  max mem: 31830
Epoch: [76]  [200/312]  eta: 0:01:04  lr: 0.003610  min_lr: 0.003610  loss: 3.8631 (3.7772)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0138  max mem: 31830
Epoch: [76]  [210/312]  eta: 0:00:58  lr: 0.003609  min_lr: 0.003609  loss: 3.8631 (3.7844)  weight_decay: 0.0500 (0.0500)  time: 0.6072  data: 0.0252  max mem: 31830
Epoch: [76]  [220/312]  eta: 0:00:51  lr: 0.003609  min_lr: 0.003609  loss: 3.9065 (3.7899)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0124  max mem: 31830
Epoch: [76]  [230/312]  eta: 0:00:46  lr: 0.003608  min_lr: 0.003608  loss: 3.8739 (3.7905)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0012  max mem: 31830
Epoch: [76]  [240/312]  eta: 0:00:40  lr: 0.003608  min_lr: 0.003608  loss: 3.8739 (3.7923)  weight_decay: 0.0500 (0.0500)  time: 0.5740  data: 0.0125  max mem: 31830
Epoch: [76]  [250/312]  eta: 0:00:34  lr: 0.003607  min_lr: 0.003607  loss: 3.9950 (3.8026)  weight_decay: 0.0500 (0.0500)  time: 0.4625  data: 0.0122  max mem: 31830
Epoch: [76]  [260/312]  eta: 0:00:29  lr: 0.003607  min_lr: 0.003607  loss: 3.9852 (3.7997)  weight_decay: 0.0500 (0.0500)  time: 0.5859  data: 0.0284  max mem: 31830
Epoch: [76]  [270/312]  eta: 0:00:23  lr: 0.003607  min_lr: 0.003607  loss: 4.0975 (3.8067)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0408  max mem: 31830
Epoch: [76]  [280/312]  eta: 0:00:17  lr: 0.003606  min_lr: 0.003606  loss: 3.9025 (3.8036)  weight_decay: 0.0500 (0.0500)  time: 0.4776  data: 0.0292  max mem: 31830
Epoch: [76]  [290/312]  eta: 0:00:12  lr: 0.003606  min_lr: 0.003606  loss: 3.9703 (3.8048)  weight_decay: 0.0500 (0.0500)  time: 0.5832  data: 0.0302  max mem: 31830
Epoch: [76]  [300/312]  eta: 0:00:06  lr: 0.003605  min_lr: 0.003605  loss: 4.0367 (3.8133)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0333  max mem: 31830
Epoch: [76]  [310/312]  eta: 0:00:01  lr: 0.003605  min_lr: 0.003605  loss: 3.9923 (3.8060)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0197  max mem: 31830
Epoch: [76]  [311/312]  eta: 0:00:00  lr: 0.003605  min_lr: 0.003605  loss: 4.0367 (3.8084)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0197  max mem: 31830
Epoch: [76] Total time: 0:02:53 (0.5548 s / it)
Averaged stats: lr: 0.003605  min_lr: 0.003605  loss: 4.0367 (3.8159)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2516 (1.2516)  acc1: 71.4844 (71.4844)  acc5: 91.5365 (91.5365)  time: 8.7810  data: 8.6157  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7274 (1.5527)  acc1: 63.2812 (65.7440)  acc5: 86.7188 (87.2160)  time: 1.0928  data: 0.9574  max mem: 31830
Test: Total time: 0:00:10 (1.1179 s / it)
* Acc@1 65.560 Acc@5 87.466 loss 1.553
Accuracy of the model on the 50000 test images: 65.6%
Max accuracy: 65.56%
Epoch: [77]  [  0/312]  eta: 0:59:09  lr: 0.003605  min_lr: 0.003605  loss: 4.4964 (4.4964)  weight_decay: 0.0500 (0.0500)  time: 11.3756  data: 9.0275  max mem: 31830
Epoch: [77]  [ 10/312]  eta: 0:08:30  lr: 0.003604  min_lr: 0.003604  loss: 3.2785 (3.4624)  weight_decay: 0.0500 (0.0500)  time: 1.6907  data: 0.9417  max mem: 31830
Epoch: [77]  [ 20/312]  eta: 0:05:23  lr: 0.003604  min_lr: 0.003604  loss: 3.5038 (3.6519)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0670  max mem: 31830
Epoch: [77]  [ 30/312]  eta: 0:04:07  lr: 0.003604  min_lr: 0.003604  loss: 3.9699 (3.7472)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0009  max mem: 31830
Epoch: [77]  [ 40/312]  eta: 0:03:27  lr: 0.003603  min_lr: 0.003603  loss: 3.8719 (3.7145)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0011  max mem: 31830
Epoch: [77]  [ 50/312]  eta: 0:03:02  lr: 0.003603  min_lr: 0.003603  loss: 3.8809 (3.7236)  weight_decay: 0.0500 (0.0500)  time: 0.4149  data: 0.0011  max mem: 31830
Epoch: [77]  [ 60/312]  eta: 0:02:43  lr: 0.003602  min_lr: 0.003602  loss: 3.8846 (3.7264)  weight_decay: 0.0500 (0.0500)  time: 0.4141  data: 0.0008  max mem: 31830
Epoch: [77]  [ 70/312]  eta: 0:02:36  lr: 0.003602  min_lr: 0.003602  loss: 3.9953 (3.7911)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0321  max mem: 31830
Epoch: [77]  [ 80/312]  eta: 0:02:24  lr: 0.003601  min_lr: 0.003601  loss: 4.0127 (3.7958)  weight_decay: 0.0500 (0.0500)  time: 0.5382  data: 0.0327  max mem: 31830
Epoch: [77]  [ 90/312]  eta: 0:02:15  lr: 0.003601  min_lr: 0.003601  loss: 3.8858 (3.7975)  weight_decay: 0.0500 (0.0500)  time: 0.4771  data: 0.0017  max mem: 31830
Epoch: [77]  [100/312]  eta: 0:02:11  lr: 0.003601  min_lr: 0.003601  loss: 3.9133 (3.7779)  weight_decay: 0.0500 (0.0500)  time: 0.6218  data: 0.0571  max mem: 31830
Epoch: [77]  [110/312]  eta: 0:02:01  lr: 0.003600  min_lr: 0.003600  loss: 3.8965 (3.7824)  weight_decay: 0.0500 (0.0500)  time: 0.5600  data: 0.0568  max mem: 31830
Epoch: [77]  [120/312]  eta: 0:01:54  lr: 0.003600  min_lr: 0.003600  loss: 3.9165 (3.8015)  weight_decay: 0.0500 (0.0500)  time: 0.4854  data: 0.0238  max mem: 31830
Epoch: [77]  [130/312]  eta: 0:01:49  lr: 0.003599  min_lr: 0.003599  loss: 4.0527 (3.8034)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.0510  max mem: 31830
Epoch: [77]  [140/312]  eta: 0:01:41  lr: 0.003599  min_lr: 0.003599  loss: 4.0947 (3.8276)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0279  max mem: 31830
Epoch: [77]  [150/312]  eta: 0:01:34  lr: 0.003598  min_lr: 0.003598  loss: 4.0249 (3.8051)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0140  max mem: 31830
Epoch: [77]  [160/312]  eta: 0:01:28  lr: 0.003598  min_lr: 0.003598  loss: 3.8029 (3.8167)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0140  max mem: 31830
Epoch: [77]  [170/312]  eta: 0:01:22  lr: 0.003598  min_lr: 0.003598  loss: 3.9089 (3.8154)  weight_decay: 0.0500 (0.0500)  time: 0.5504  data: 0.0505  max mem: 31830
Epoch: [77]  [180/312]  eta: 0:01:16  lr: 0.003597  min_lr: 0.003597  loss: 3.9660 (3.8188)  weight_decay: 0.0500 (0.0500)  time: 0.5883  data: 0.0926  max mem: 31830
Epoch: [77]  [190/312]  eta: 0:01:09  lr: 0.003597  min_lr: 0.003597  loss: 4.0428 (3.8187)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0435  max mem: 31830
Epoch: [77]  [200/312]  eta: 0:01:04  lr: 0.003596  min_lr: 0.003596  loss: 3.8140 (3.8160)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0447  max mem: 31830
Epoch: [77]  [210/312]  eta: 0:00:58  lr: 0.003596  min_lr: 0.003596  loss: 3.7596 (3.8009)  weight_decay: 0.0500 (0.0500)  time: 0.6082  data: 0.0783  max mem: 31830
Epoch: [77]  [220/312]  eta: 0:00:52  lr: 0.003595  min_lr: 0.003595  loss: 3.8220 (3.8017)  weight_decay: 0.0500 (0.0500)  time: 0.5030  data: 0.0351  max mem: 31830
Epoch: [77]  [230/312]  eta: 0:00:46  lr: 0.003595  min_lr: 0.003595  loss: 3.8220 (3.8001)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0281  max mem: 31830
Epoch: [77]  [240/312]  eta: 0:00:40  lr: 0.003594  min_lr: 0.003594  loss: 3.9494 (3.8081)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0287  max mem: 31830
Epoch: [77]  [250/312]  eta: 0:00:35  lr: 0.003594  min_lr: 0.003594  loss: 3.9256 (3.8123)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0416  max mem: 31830
Epoch: [77]  [260/312]  eta: 0:00:29  lr: 0.003594  min_lr: 0.003594  loss: 3.8835 (3.8096)  weight_decay: 0.0500 (0.0500)  time: 0.5912  data: 0.0811  max mem: 31830
Epoch: [77]  [270/312]  eta: 0:00:23  lr: 0.003593  min_lr: 0.003593  loss: 3.8476 (3.8050)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0410  max mem: 31830
Epoch: [77]  [280/312]  eta: 0:00:18  lr: 0.003593  min_lr: 0.003593  loss: 3.9240 (3.8149)  weight_decay: 0.0500 (0.0500)  time: 0.4861  data: 0.0303  max mem: 31830
Epoch: [77]  [290/312]  eta: 0:00:12  lr: 0.003592  min_lr: 0.003592  loss: 4.0637 (3.8182)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0620  max mem: 31830
Epoch: [77]  [300/312]  eta: 0:00:06  lr: 0.003592  min_lr: 0.003592  loss: 4.0604 (3.8225)  weight_decay: 0.0500 (0.0500)  time: 0.4966  data: 0.0323  max mem: 31830
Epoch: [77]  [310/312]  eta: 0:00:01  lr: 0.003591  min_lr: 0.003591  loss: 3.7311 (3.8175)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [77]  [311/312]  eta: 0:00:00  lr: 0.003591  min_lr: 0.003591  loss: 3.8385 (3.8185)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [77] Total time: 0:02:53 (0.5567 s / it)
Averaged stats: lr: 0.003591  min_lr: 0.003591  loss: 3.8385 (3.8092)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.4569 (1.4569)  acc1: 71.7448 (71.7448)  acc5: 90.6250 (90.6250)  time: 8.3228  data: 8.1552  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9273 (1.7397)  acc1: 63.0208 (65.0400)  acc5: 86.7188 (86.8160)  time: 1.0421  data: 0.9062  max mem: 31830
Test: Total time: 0:00:09 (1.0520 s / it)
* Acc@1 64.836 Acc@5 86.882 loss 1.729
Accuracy of the model on the 50000 test images: 64.8%
Max accuracy: 65.56%
Epoch: [78]  [  0/312]  eta: 1:01:49  lr: 0.003591  min_lr: 0.003591  loss: 2.6971 (2.6971)  weight_decay: 0.0500 (0.0500)  time: 11.8885  data: 9.0221  max mem: 31830
Epoch: [78]  [ 10/312]  eta: 0:08:49  lr: 0.003591  min_lr: 0.003591  loss: 4.0004 (3.7922)  weight_decay: 0.0500 (0.0500)  time: 1.7549  data: 0.8773  max mem: 31830
Epoch: [78]  [ 20/312]  eta: 0:05:22  lr: 0.003590  min_lr: 0.003590  loss: 3.9152 (3.6873)  weight_decay: 0.0500 (0.0500)  time: 0.5654  data: 0.0317  max mem: 31830
Epoch: [78]  [ 30/312]  eta: 0:04:07  lr: 0.003590  min_lr: 0.003590  loss: 3.7425 (3.7285)  weight_decay: 0.0500 (0.0500)  time: 0.3945  data: 0.0007  max mem: 31830
Epoch: [78]  [ 40/312]  eta: 0:03:26  lr: 0.003590  min_lr: 0.003590  loss: 3.7547 (3.7464)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0011  max mem: 31830
Epoch: [78]  [ 50/312]  eta: 0:03:00  lr: 0.003589  min_lr: 0.003589  loss: 3.4543 (3.6754)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0012  max mem: 31830
Epoch: [78]  [ 60/312]  eta: 0:02:41  lr: 0.003589  min_lr: 0.003589  loss: 3.6367 (3.7210)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0008  max mem: 31830
Epoch: [78]  [ 70/312]  eta: 0:02:32  lr: 0.003588  min_lr: 0.003588  loss: 4.0326 (3.7363)  weight_decay: 0.0500 (0.0500)  time: 0.4850  data: 0.0126  max mem: 31830
Epoch: [78]  [ 80/312]  eta: 0:02:24  lr: 0.003588  min_lr: 0.003588  loss: 4.0326 (3.7571)  weight_decay: 0.0500 (0.0500)  time: 0.5706  data: 0.0126  max mem: 31830
Epoch: [78]  [ 90/312]  eta: 0:02:14  lr: 0.003587  min_lr: 0.003587  loss: 3.8044 (3.7424)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0007  max mem: 31830
Epoch: [78]  [100/312]  eta: 0:02:08  lr: 0.003587  min_lr: 0.003587  loss: 3.7772 (3.7356)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0120  max mem: 31830
Epoch: [78]  [110/312]  eta: 0:01:58  lr: 0.003587  min_lr: 0.003587  loss: 3.7772 (3.7231)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0122  max mem: 31830
Epoch: [78]  [120/312]  eta: 0:01:53  lr: 0.003586  min_lr: 0.003586  loss: 3.2205 (3.7082)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0010  max mem: 31830
Epoch: [78]  [130/312]  eta: 0:01:46  lr: 0.003586  min_lr: 0.003586  loss: 3.6470 (3.7158)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.0015  max mem: 31830
Epoch: [78]  [140/312]  eta: 0:01:38  lr: 0.003585  min_lr: 0.003585  loss: 3.8878 (3.7388)  weight_decay: 0.0500 (0.0500)  time: 0.4712  data: 0.0016  max mem: 31830
Epoch: [78]  [150/312]  eta: 0:01:34  lr: 0.003585  min_lr: 0.003585  loss: 3.8878 (3.7416)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0275  max mem: 31830
Epoch: [78]  [160/312]  eta: 0:01:27  lr: 0.003584  min_lr: 0.003584  loss: 3.8634 (3.7477)  weight_decay: 0.0500 (0.0500)  time: 0.6092  data: 0.0276  max mem: 31830
Epoch: [78]  [170/312]  eta: 0:01:21  lr: 0.003584  min_lr: 0.003584  loss: 3.9178 (3.7513)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0117  max mem: 31830
Epoch: [78]  [180/312]  eta: 0:01:15  lr: 0.003583  min_lr: 0.003583  loss: 4.0158 (3.7571)  weight_decay: 0.0500 (0.0500)  time: 0.5411  data: 0.0120  max mem: 31830
Epoch: [78]  [190/312]  eta: 0:01:08  lr: 0.003583  min_lr: 0.003583  loss: 3.9621 (3.7575)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0020  max mem: 31830
Epoch: [78]  [200/312]  eta: 0:01:03  lr: 0.003583  min_lr: 0.003583  loss: 3.9678 (3.7705)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0015  max mem: 31830
Epoch: [78]  [210/312]  eta: 0:00:57  lr: 0.003582  min_lr: 0.003582  loss: 4.0512 (3.7790)  weight_decay: 0.0500 (0.0500)  time: 0.5970  data: 0.0010  max mem: 31830
Epoch: [78]  [220/312]  eta: 0:00:51  lr: 0.003582  min_lr: 0.003582  loss: 3.9065 (3.7798)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0010  max mem: 31830
Epoch: [78]  [230/312]  eta: 0:00:46  lr: 0.003581  min_lr: 0.003581  loss: 3.8343 (3.7769)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0007  max mem: 31830
Epoch: [78]  [240/312]  eta: 0:00:40  lr: 0.003581  min_lr: 0.003581  loss: 4.0719 (3.7876)  weight_decay: 0.0500 (0.0500)  time: 0.6127  data: 0.0007  max mem: 31830
Epoch: [78]  [250/312]  eta: 0:00:34  lr: 0.003580  min_lr: 0.003580  loss: 3.9895 (3.7830)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0009  max mem: 31830
Epoch: [78]  [260/312]  eta: 0:00:29  lr: 0.003580  min_lr: 0.003580  loss: 3.8755 (3.7881)  weight_decay: 0.0500 (0.0500)  time: 0.5451  data: 0.0014  max mem: 31830
Epoch: [78]  [270/312]  eta: 0:00:23  lr: 0.003580  min_lr: 0.003580  loss: 3.8087 (3.7814)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0013  max mem: 31830
Epoch: [78]  [280/312]  eta: 0:00:17  lr: 0.003579  min_lr: 0.003579  loss: 3.6583 (3.7771)  weight_decay: 0.0500 (0.0500)  time: 0.4936  data: 0.0021  max mem: 31830
Epoch: [78]  [290/312]  eta: 0:00:12  lr: 0.003579  min_lr: 0.003579  loss: 4.0125 (3.7876)  weight_decay: 0.0500 (0.0500)  time: 0.5805  data: 0.0019  max mem: 31830
Epoch: [78]  [300/312]  eta: 0:00:06  lr: 0.003578  min_lr: 0.003578  loss: 3.9993 (3.7912)  weight_decay: 0.0500 (0.0500)  time: 0.4869  data: 0.0002  max mem: 31830
Epoch: [78]  [310/312]  eta: 0:00:01  lr: 0.003578  min_lr: 0.003578  loss: 3.8856 (3.7920)  weight_decay: 0.0500 (0.0500)  time: 0.3927  data: 0.0001  max mem: 31830
Epoch: [78]  [311/312]  eta: 0:00:00  lr: 0.003578  min_lr: 0.003578  loss: 3.8856 (3.7933)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [78] Total time: 0:02:52 (0.5527 s / it)
Averaged stats: lr: 0.003578  min_lr: 0.003578  loss: 3.8856 (3.7961)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.6475 (1.6475)  acc1: 71.4844 (71.4844)  acc5: 91.7969 (91.7969)  time: 8.6449  data: 8.4775  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0944 (1.9948)  acc1: 61.3281 (63.5360)  acc5: 85.6771 (85.5520)  time: 1.0773  data: 0.9420  max mem: 31830
Test: Total time: 0:00:09 (1.1058 s / it)
* Acc@1 63.818 Acc@5 85.966 loss 1.984
Accuracy of the model on the 50000 test images: 63.8%
Max accuracy: 65.56%
Epoch: [79]  [  0/312]  eta: 1:00:51  lr: 0.003578  min_lr: 0.003578  loss: 3.3862 (3.3862)  weight_decay: 0.0500 (0.0500)  time: 11.7023  data: 11.3012  max mem: 31830
Epoch: [79]  [ 10/312]  eta: 0:08:12  lr: 0.003577  min_lr: 0.003577  loss: 4.3557 (3.9741)  weight_decay: 0.0500 (0.0500)  time: 1.6321  data: 1.0291  max mem: 31830
Epoch: [79]  [ 20/312]  eta: 0:05:29  lr: 0.003577  min_lr: 0.003577  loss: 4.1940 (3.9250)  weight_decay: 0.0500 (0.0500)  time: 0.5988  data: 0.0645  max mem: 31830
Epoch: [79]  [ 30/312]  eta: 0:04:11  lr: 0.003576  min_lr: 0.003576  loss: 3.8454 (3.8450)  weight_decay: 0.0500 (0.0500)  time: 0.4860  data: 0.0640  max mem: 31830
Epoch: [79]  [ 40/312]  eta: 0:03:29  lr: 0.003576  min_lr: 0.003576  loss: 3.6909 (3.8352)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0008  max mem: 31830
Epoch: [79]  [ 50/312]  eta: 0:03:12  lr: 0.003575  min_lr: 0.003575  loss: 4.0124 (3.8551)  weight_decay: 0.0500 (0.0500)  time: 0.4926  data: 0.0008  max mem: 31830
Epoch: [79]  [ 60/312]  eta: 0:02:51  lr: 0.003575  min_lr: 0.003575  loss: 3.9825 (3.8320)  weight_decay: 0.0500 (0.0500)  time: 0.4914  data: 0.0009  max mem: 31830
Epoch: [79]  [ 70/312]  eta: 0:02:41  lr: 0.003575  min_lr: 0.003575  loss: 3.9473 (3.8364)  weight_decay: 0.0500 (0.0500)  time: 0.4914  data: 0.0146  max mem: 31830
Epoch: [79]  [ 80/312]  eta: 0:02:29  lr: 0.003574  min_lr: 0.003574  loss: 3.9545 (3.8369)  weight_decay: 0.0500 (0.0500)  time: 0.5353  data: 0.0434  max mem: 31830
Epoch: [79]  [ 90/312]  eta: 0:02:19  lr: 0.003574  min_lr: 0.003574  loss: 4.0778 (3.8803)  weight_decay: 0.0500 (0.0500)  time: 0.4853  data: 0.0295  max mem: 31830
Epoch: [79]  [100/312]  eta: 0:02:11  lr: 0.003573  min_lr: 0.003573  loss: 4.1548 (3.9040)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0666  max mem: 31830
Epoch: [79]  [110/312]  eta: 0:02:01  lr: 0.003573  min_lr: 0.003573  loss: 4.0736 (3.9047)  weight_decay: 0.0500 (0.0500)  time: 0.4800  data: 0.0668  max mem: 31830
Epoch: [79]  [120/312]  eta: 0:01:55  lr: 0.003572  min_lr: 0.003572  loss: 3.9406 (3.8972)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0793  max mem: 31830
Epoch: [79]  [130/312]  eta: 0:01:49  lr: 0.003572  min_lr: 0.003572  loss: 3.9477 (3.9084)  weight_decay: 0.0500 (0.0500)  time: 0.6074  data: 0.1448  max mem: 31830
Epoch: [79]  [140/312]  eta: 0:01:40  lr: 0.003571  min_lr: 0.003571  loss: 3.4346 (3.8539)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0665  max mem: 31830
Epoch: [79]  [150/312]  eta: 0:01:35  lr: 0.003571  min_lr: 0.003571  loss: 3.4134 (3.8468)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0692  max mem: 31830
Epoch: [79]  [160/312]  eta: 0:01:29  lr: 0.003571  min_lr: 0.003571  loss: 3.7868 (3.8326)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.1410  max mem: 31830
Epoch: [79]  [170/312]  eta: 0:01:22  lr: 0.003570  min_lr: 0.003570  loss: 3.8893 (3.8359)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0726  max mem: 31830
Epoch: [79]  [180/312]  eta: 0:01:16  lr: 0.003570  min_lr: 0.003570  loss: 3.9537 (3.8282)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0623  max mem: 31830
Epoch: [79]  [190/312]  eta: 0:01:09  lr: 0.003569  min_lr: 0.003569  loss: 3.7957 (3.8245)  weight_decay: 0.0500 (0.0500)  time: 0.4860  data: 0.0630  max mem: 31830
Epoch: [79]  [200/312]  eta: 0:01:04  lr: 0.003569  min_lr: 0.003569  loss: 3.8653 (3.8217)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0803  max mem: 31830
Epoch: [79]  [210/312]  eta: 0:00:58  lr: 0.003568  min_lr: 0.003568  loss: 4.0248 (3.8280)  weight_decay: 0.0500 (0.0500)  time: 0.6025  data: 0.1786  max mem: 31830
Epoch: [79]  [220/312]  eta: 0:00:52  lr: 0.003568  min_lr: 0.003568  loss: 4.0867 (3.8344)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.1004  max mem: 31830
Epoch: [79]  [230/312]  eta: 0:00:46  lr: 0.003567  min_lr: 0.003567  loss: 4.1016 (3.8327)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.1392  max mem: 31830
Epoch: [79]  [240/312]  eta: 0:00:41  lr: 0.003567  min_lr: 0.003567  loss: 4.0033 (3.8400)  weight_decay: 0.0500 (0.0500)  time: 0.6798  data: 0.2870  max mem: 31830
Epoch: [79]  [250/312]  eta: 0:00:35  lr: 0.003567  min_lr: 0.003567  loss: 3.9272 (3.8280)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.1491  max mem: 31830
Epoch: [79]  [260/312]  eta: 0:00:29  lr: 0.003566  min_lr: 0.003566  loss: 3.8299 (3.8244)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.1134  max mem: 31830
Epoch: [79]  [270/312]  eta: 0:00:23  lr: 0.003566  min_lr: 0.003566  loss: 3.6677 (3.8167)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.1133  max mem: 31830
Epoch: [79]  [280/312]  eta: 0:00:18  lr: 0.003565  min_lr: 0.003565  loss: 3.7434 (3.8179)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.1084  max mem: 31830
Epoch: [79]  [290/312]  eta: 0:00:12  lr: 0.003565  min_lr: 0.003565  loss: 4.0277 (3.8122)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1838  max mem: 31830
Epoch: [79]  [300/312]  eta: 0:00:06  lr: 0.003564  min_lr: 0.003564  loss: 3.9595 (3.8149)  weight_decay: 0.0500 (0.0500)  time: 0.4606  data: 0.0758  max mem: 31830
Epoch: [79]  [310/312]  eta: 0:00:01  lr: 0.003564  min_lr: 0.003564  loss: 4.0938 (3.8258)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [79]  [311/312]  eta: 0:00:00  lr: 0.003564  min_lr: 0.003564  loss: 4.0803 (3.8266)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [79] Total time: 0:02:53 (0.5564 s / it)
Averaged stats: lr: 0.003564  min_lr: 0.003564  loss: 4.0803 (3.7919)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.6413 (1.6413)  acc1: 72.2656 (72.2656)  acc5: 89.1927 (89.1927)  time: 8.6604  data: 8.4988  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9546 (1.8307)  acc1: 62.2396 (64.4640)  acc5: 86.4583 (86.1280)  time: 1.0809  data: 0.9444  max mem: 31830
Test: Total time: 0:00:10 (1.1169 s / it)
* Acc@1 64.324 Acc@5 86.460 loss 1.830
Accuracy of the model on the 50000 test images: 64.3%
Max accuracy: 65.56%
Epoch: [80]  [  0/312]  eta: 0:59:42  lr: 0.003564  min_lr: 0.003564  loss: 4.1665 (4.1665)  weight_decay: 0.0500 (0.0500)  time: 11.4838  data: 9.1231  max mem: 31830
Epoch: [80]  [ 10/312]  eta: 0:08:10  lr: 0.003563  min_lr: 0.003563  loss: 4.1028 (3.8332)  weight_decay: 0.0500 (0.0500)  time: 1.6240  data: 1.0444  max mem: 31830
Epoch: [80]  [ 20/312]  eta: 0:05:33  lr: 0.003563  min_lr: 0.003563  loss: 4.0359 (3.9791)  weight_decay: 0.0500 (0.0500)  time: 0.6240  data: 0.1334  max mem: 31830
Epoch: [80]  [ 30/312]  eta: 0:04:13  lr: 0.003562  min_lr: 0.003562  loss: 3.8468 (3.8279)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0155  max mem: 31830
Epoch: [80]  [ 40/312]  eta: 0:03:31  lr: 0.003562  min_lr: 0.003562  loss: 3.8468 (3.8576)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0014  max mem: 31830
Epoch: [80]  [ 50/312]  eta: 0:03:05  lr: 0.003562  min_lr: 0.003562  loss: 3.9866 (3.8533)  weight_decay: 0.0500 (0.0500)  time: 0.4105  data: 0.0018  max mem: 31830
Epoch: [80]  [ 60/312]  eta: 0:02:45  lr: 0.003561  min_lr: 0.003561  loss: 3.9533 (3.8227)  weight_decay: 0.0500 (0.0500)  time: 0.4116  data: 0.0014  max mem: 31830
Epoch: [80]  [ 70/312]  eta: 0:02:37  lr: 0.003561  min_lr: 0.003561  loss: 3.8914 (3.8150)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0305  max mem: 31830
Epoch: [80]  [ 80/312]  eta: 0:02:28  lr: 0.003560  min_lr: 0.003560  loss: 3.9843 (3.8262)  weight_decay: 0.0500 (0.0500)  time: 0.5799  data: 0.0304  max mem: 31830
Epoch: [80]  [ 90/312]  eta: 0:02:17  lr: 0.003560  min_lr: 0.003560  loss: 4.0156 (3.8174)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0305  max mem: 31830
Epoch: [80]  [100/312]  eta: 0:02:12  lr: 0.003559  min_lr: 0.003559  loss: 3.6543 (3.7828)  weight_decay: 0.0500 (0.0500)  time: 0.5675  data: 0.0613  max mem: 31830
Epoch: [80]  [110/312]  eta: 0:02:01  lr: 0.003559  min_lr: 0.003559  loss: 3.5151 (3.7704)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0318  max mem: 31830
Epoch: [80]  [120/312]  eta: 0:01:55  lr: 0.003558  min_lr: 0.003558  loss: 3.8307 (3.7714)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0018  max mem: 31830
Epoch: [80]  [130/312]  eta: 0:01:50  lr: 0.003558  min_lr: 0.003558  loss: 3.8694 (3.7823)  weight_decay: 0.0500 (0.0500)  time: 0.6248  data: 0.0016  max mem: 31830
Epoch: [80]  [140/312]  eta: 0:01:41  lr: 0.003557  min_lr: 0.003557  loss: 3.8694 (3.7827)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0007  max mem: 31830
Epoch: [80]  [150/312]  eta: 0:01:36  lr: 0.003557  min_lr: 0.003557  loss: 3.7038 (3.7678)  weight_decay: 0.0500 (0.0500)  time: 0.5068  data: 0.0008  max mem: 31830
Epoch: [80]  [160/312]  eta: 0:01:30  lr: 0.003557  min_lr: 0.003557  loss: 3.2550 (3.7387)  weight_decay: 0.0500 (0.0500)  time: 0.6003  data: 0.0009  max mem: 31830
Epoch: [80]  [170/312]  eta: 0:01:22  lr: 0.003556  min_lr: 0.003556  loss: 3.4570 (3.7414)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0009  max mem: 31830
Epoch: [80]  [180/312]  eta: 0:01:17  lr: 0.003556  min_lr: 0.003556  loss: 3.7036 (3.7425)  weight_decay: 0.0500 (0.0500)  time: 0.5396  data: 0.0008  max mem: 31830
Epoch: [80]  [190/312]  eta: 0:01:10  lr: 0.003555  min_lr: 0.003555  loss: 3.6779 (3.7379)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0019  max mem: 31830
Epoch: [80]  [200/312]  eta: 0:01:04  lr: 0.003555  min_lr: 0.003555  loss: 3.6779 (3.7348)  weight_decay: 0.0500 (0.0500)  time: 0.4792  data: 0.0019  max mem: 31830
Epoch: [80]  [210/312]  eta: 0:00:59  lr: 0.003554  min_lr: 0.003554  loss: 3.9045 (3.7449)  weight_decay: 0.0500 (0.0500)  time: 0.6168  data: 0.0011  max mem: 31830
Epoch: [80]  [220/312]  eta: 0:00:52  lr: 0.003554  min_lr: 0.003554  loss: 4.1123 (3.7507)  weight_decay: 0.0500 (0.0500)  time: 0.5336  data: 0.0017  max mem: 31830
Epoch: [80]  [230/312]  eta: 0:00:47  lr: 0.003553  min_lr: 0.003553  loss: 3.7998 (3.7380)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.0017  max mem: 31830
Epoch: [80]  [240/312]  eta: 0:00:41  lr: 0.003553  min_lr: 0.003553  loss: 3.8631 (3.7479)  weight_decay: 0.0500 (0.0500)  time: 0.5943  data: 0.0011  max mem: 31830
Epoch: [80]  [250/312]  eta: 0:00:35  lr: 0.003553  min_lr: 0.003553  loss: 4.0527 (3.7610)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0008  max mem: 31830
Epoch: [80]  [260/312]  eta: 0:00:29  lr: 0.003552  min_lr: 0.003552  loss: 4.1009 (3.7769)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0010  max mem: 31830
Epoch: [80]  [270/312]  eta: 0:00:23  lr: 0.003552  min_lr: 0.003552  loss: 4.0751 (3.7841)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0154  max mem: 31830
Epoch: [80]  [280/312]  eta: 0:00:18  lr: 0.003551  min_lr: 0.003551  loss: 3.9981 (3.7853)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0162  max mem: 31830
Epoch: [80]  [290/312]  eta: 0:00:12  lr: 0.003551  min_lr: 0.003551  loss: 3.9385 (3.7885)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0016  max mem: 31830
Epoch: [80]  [300/312]  eta: 0:00:06  lr: 0.003550  min_lr: 0.003550  loss: 3.8536 (3.7844)  weight_decay: 0.0500 (0.0500)  time: 0.4625  data: 0.0002  max mem: 31830
Epoch: [80]  [310/312]  eta: 0:00:01  lr: 0.003550  min_lr: 0.003550  loss: 3.8181 (3.7816)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [80]  [311/312]  eta: 0:00:00  lr: 0.003550  min_lr: 0.003550  loss: 3.8181 (3.7795)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [80] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.003550  min_lr: 0.003550  loss: 3.8181 (3.8130)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.2435 (1.2435)  acc1: 73.5677 (73.5677)  acc5: 91.7969 (91.7969)  time: 8.7498  data: 8.5912  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6455 (1.5369)  acc1: 64.9740 (65.8720)  acc5: 86.3281 (87.1520)  time: 1.0947  data: 0.9547  max mem: 31830
Test: Total time: 0:00:10 (1.1243 s / it)
* Acc@1 65.646 Acc@5 87.460 loss 1.525
Accuracy of the model on the 50000 test images: 65.6%
Max accuracy: 65.65%
Epoch: [81]  [  0/312]  eta: 1:01:58  lr: 0.003550  min_lr: 0.003550  loss: 4.5658 (4.5658)  weight_decay: 0.0500 (0.0500)  time: 11.9197  data: 10.5435  max mem: 31830
Epoch: [81]  [ 10/312]  eta: 0:08:19  lr: 0.003549  min_lr: 0.003549  loss: 4.1917 (3.9813)  weight_decay: 0.0500 (0.0500)  time: 1.6555  data: 0.9590  max mem: 31830
Epoch: [81]  [ 20/312]  eta: 0:05:27  lr: 0.003549  min_lr: 0.003549  loss: 3.9800 (3.8758)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.0006  max mem: 31830
Epoch: [81]  [ 30/312]  eta: 0:04:10  lr: 0.003548  min_lr: 0.003548  loss: 3.9716 (3.8573)  weight_decay: 0.0500 (0.0500)  time: 0.4651  data: 0.0010  max mem: 31830
Epoch: [81]  [ 40/312]  eta: 0:03:28  lr: 0.003548  min_lr: 0.003548  loss: 3.7302 (3.8236)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0010  max mem: 31830
Epoch: [81]  [ 50/312]  eta: 0:03:04  lr: 0.003547  min_lr: 0.003547  loss: 3.7123 (3.8066)  weight_decay: 0.0500 (0.0500)  time: 0.4249  data: 0.0007  max mem: 31830
Epoch: [81]  [ 60/312]  eta: 0:02:45  lr: 0.003547  min_lr: 0.003547  loss: 3.7128 (3.7977)  weight_decay: 0.0500 (0.0500)  time: 0.4251  data: 0.0008  max mem: 31830
Epoch: [81]  [ 70/312]  eta: 0:02:35  lr: 0.003546  min_lr: 0.003546  loss: 3.8577 (3.7878)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0389  max mem: 31830
Epoch: [81]  [ 80/312]  eta: 0:02:27  lr: 0.003546  min_lr: 0.003546  loss: 4.0612 (3.8129)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.0885  max mem: 31830
Epoch: [81]  [ 90/312]  eta: 0:02:16  lr: 0.003546  min_lr: 0.003546  loss: 4.0768 (3.8290)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0505  max mem: 31830
Epoch: [81]  [100/312]  eta: 0:02:09  lr: 0.003545  min_lr: 0.003545  loss: 3.9433 (3.8076)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0539  max mem: 31830
Epoch: [81]  [110/312]  eta: 0:01:59  lr: 0.003545  min_lr: 0.003545  loss: 3.6925 (3.7853)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0538  max mem: 31830
Epoch: [81]  [120/312]  eta: 0:01:54  lr: 0.003544  min_lr: 0.003544  loss: 3.6925 (3.7811)  weight_decay: 0.0500 (0.0500)  time: 0.5031  data: 0.0617  max mem: 31830
Epoch: [81]  [130/312]  eta: 0:01:48  lr: 0.003544  min_lr: 0.003544  loss: 3.9095 (3.7856)  weight_decay: 0.0500 (0.0500)  time: 0.6209  data: 0.1286  max mem: 31830
Epoch: [81]  [140/312]  eta: 0:01:40  lr: 0.003543  min_lr: 0.003543  loss: 3.6563 (3.7745)  weight_decay: 0.0500 (0.0500)  time: 0.5182  data: 0.0677  max mem: 31830
Epoch: [81]  [150/312]  eta: 0:01:35  lr: 0.003543  min_lr: 0.003543  loss: 3.6085 (3.7567)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.0327  max mem: 31830
Epoch: [81]  [160/312]  eta: 0:01:29  lr: 0.003542  min_lr: 0.003542  loss: 3.8526 (3.7715)  weight_decay: 0.0500 (0.0500)  time: 0.6226  data: 0.0506  max mem: 31830
Epoch: [81]  [170/312]  eta: 0:01:22  lr: 0.003542  min_lr: 0.003542  loss: 4.0750 (3.7939)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0195  max mem: 31830
Epoch: [81]  [180/312]  eta: 0:01:16  lr: 0.003541  min_lr: 0.003541  loss: 4.0061 (3.7966)  weight_decay: 0.0500 (0.0500)  time: 0.5407  data: 0.0309  max mem: 31830
Epoch: [81]  [190/312]  eta: 0:01:09  lr: 0.003541  min_lr: 0.003541  loss: 3.7617 (3.7871)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0303  max mem: 31830
Epoch: [81]  [200/312]  eta: 0:01:04  lr: 0.003541  min_lr: 0.003541  loss: 3.2595 (3.7719)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0324  max mem: 31830
Epoch: [81]  [210/312]  eta: 0:00:58  lr: 0.003540  min_lr: 0.003540  loss: 3.8237 (3.7817)  weight_decay: 0.0500 (0.0500)  time: 0.5898  data: 0.0675  max mem: 31830
Epoch: [81]  [220/312]  eta: 0:00:52  lr: 0.003540  min_lr: 0.003540  loss: 4.0751 (3.7812)  weight_decay: 0.0500 (0.0500)  time: 0.5111  data: 0.0359  max mem: 31830
Epoch: [81]  [230/312]  eta: 0:00:47  lr: 0.003539  min_lr: 0.003539  loss: 3.5084 (3.7659)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0281  max mem: 31830
Epoch: [81]  [240/312]  eta: 0:00:41  lr: 0.003539  min_lr: 0.003539  loss: 3.3318 (3.7585)  weight_decay: 0.0500 (0.0500)  time: 0.6092  data: 0.0282  max mem: 31830
Epoch: [81]  [250/312]  eta: 0:00:35  lr: 0.003538  min_lr: 0.003538  loss: 3.7419 (3.7512)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0013  max mem: 31830
Epoch: [81]  [260/312]  eta: 0:00:29  lr: 0.003538  min_lr: 0.003538  loss: 3.3398 (3.7350)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0013  max mem: 31830
Epoch: [81]  [270/312]  eta: 0:00:23  lr: 0.003537  min_lr: 0.003537  loss: 3.3237 (3.7297)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0008  max mem: 31830
Epoch: [81]  [280/312]  eta: 0:00:18  lr: 0.003537  min_lr: 0.003537  loss: 3.8000 (3.7345)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0026  max mem: 31830
Epoch: [81]  [290/312]  eta: 0:00:12  lr: 0.003536  min_lr: 0.003536  loss: 3.9425 (3.7326)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0024  max mem: 31830
Epoch: [81]  [300/312]  eta: 0:00:06  lr: 0.003536  min_lr: 0.003536  loss: 3.9052 (3.7344)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0002  max mem: 31830
Epoch: [81]  [310/312]  eta: 0:00:01  lr: 0.003535  min_lr: 0.003535  loss: 3.9121 (3.7379)  weight_decay: 0.0500 (0.0500)  time: 0.4048  data: 0.0001  max mem: 31830
Epoch: [81]  [311/312]  eta: 0:00:00  lr: 0.003535  min_lr: 0.003535  loss: 3.9052 (3.7382)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [81] Total time: 0:02:54 (0.5590 s / it)
Averaged stats: lr: 0.003535  min_lr: 0.003535  loss: 3.9052 (3.7755)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 1.3677 (1.3677)  acc1: 75.0000 (75.0000)  acc5: 92.4479 (92.4479)  time: 7.8204  data: 7.6600  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8002 (1.6456)  acc1: 63.6719 (66.0000)  acc5: 86.4583 (88.0640)  time: 1.0489  data: 0.9147  max mem: 31830
Test: Total time: 0:00:09 (1.0808 s / it)
* Acc@1 65.776 Acc@5 87.678 loss 1.653
Accuracy of the model on the 50000 test images: 65.8%
Max accuracy: 65.78%
Epoch: [82]  [  0/312]  eta: 1:01:31  lr: 0.003535  min_lr: 0.003535  loss: 3.2058 (3.2058)  weight_decay: 0.0500 (0.0500)  time: 11.8325  data: 11.4390  max mem: 31830
Epoch: [82]  [ 10/312]  eta: 0:08:06  lr: 0.003535  min_lr: 0.003535  loss: 4.0261 (3.8843)  weight_decay: 0.0500 (0.0500)  time: 1.6109  data: 1.0405  max mem: 31830
Epoch: [82]  [ 20/312]  eta: 0:05:22  lr: 0.003534  min_lr: 0.003534  loss: 3.7376 (3.7112)  weight_decay: 0.0500 (0.0500)  time: 0.5684  data: 0.0708  max mem: 31830
Epoch: [82]  [ 30/312]  eta: 0:04:07  lr: 0.003534  min_lr: 0.003534  loss: 3.9216 (3.8597)  weight_decay: 0.0500 (0.0500)  time: 0.4724  data: 0.0710  max mem: 31830
Epoch: [82]  [ 40/312]  eta: 0:03:26  lr: 0.003534  min_lr: 0.003534  loss: 3.9951 (3.8390)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0009  max mem: 31830
Epoch: [82]  [ 50/312]  eta: 0:03:03  lr: 0.003533  min_lr: 0.003533  loss: 3.9417 (3.8261)  weight_decay: 0.0500 (0.0500)  time: 0.4275  data: 0.0248  max mem: 31830
Epoch: [82]  [ 60/312]  eta: 0:02:43  lr: 0.003533  min_lr: 0.003533  loss: 3.8285 (3.7781)  weight_decay: 0.0500 (0.0500)  time: 0.4230  data: 0.0247  max mem: 31830
Epoch: [82]  [ 70/312]  eta: 0:02:37  lr: 0.003532  min_lr: 0.003532  loss: 3.8361 (3.7721)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0979  max mem: 31830
Epoch: [82]  [ 80/312]  eta: 0:02:27  lr: 0.003532  min_lr: 0.003532  loss: 3.8805 (3.7651)  weight_decay: 0.0500 (0.0500)  time: 0.6018  data: 0.1219  max mem: 31830
Epoch: [82]  [ 90/312]  eta: 0:02:18  lr: 0.003531  min_lr: 0.003531  loss: 3.9313 (3.7527)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0858  max mem: 31830
Epoch: [82]  [100/312]  eta: 0:02:12  lr: 0.003531  min_lr: 0.003531  loss: 3.4182 (3.7258)  weight_decay: 0.0500 (0.0500)  time: 0.5668  data: 0.1312  max mem: 31830
Epoch: [82]  [110/312]  eta: 0:02:01  lr: 0.003530  min_lr: 0.003530  loss: 3.4188 (3.7127)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0704  max mem: 31830
Epoch: [82]  [120/312]  eta: 0:01:56  lr: 0.003530  min_lr: 0.003530  loss: 3.7764 (3.7238)  weight_decay: 0.0500 (0.0500)  time: 0.5081  data: 0.0665  max mem: 31830
Epoch: [82]  [130/312]  eta: 0:01:50  lr: 0.003529  min_lr: 0.003529  loss: 3.9500 (3.7354)  weight_decay: 0.0500 (0.0500)  time: 0.6161  data: 0.1307  max mem: 31830
Epoch: [82]  [140/312]  eta: 0:01:41  lr: 0.003529  min_lr: 0.003529  loss: 3.9695 (3.7553)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0661  max mem: 31830
Epoch: [82]  [150/312]  eta: 0:01:36  lr: 0.003528  min_lr: 0.003528  loss: 4.1285 (3.7683)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0875  max mem: 31830
Epoch: [82]  [160/312]  eta: 0:01:29  lr: 0.003528  min_lr: 0.003528  loss: 3.8976 (3.7684)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.0868  max mem: 31830
Epoch: [82]  [170/312]  eta: 0:01:22  lr: 0.003528  min_lr: 0.003528  loss: 3.8008 (3.7596)  weight_decay: 0.0500 (0.0500)  time: 0.4850  data: 0.0658  max mem: 31830
Epoch: [82]  [180/312]  eta: 0:01:17  lr: 0.003527  min_lr: 0.003527  loss: 3.8914 (3.7523)  weight_decay: 0.0500 (0.0500)  time: 0.5716  data: 0.1759  max mem: 31830
Epoch: [82]  [190/312]  eta: 0:01:10  lr: 0.003527  min_lr: 0.003527  loss: 3.5739 (3.7469)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.1108  max mem: 31830
Epoch: [82]  [200/312]  eta: 0:01:04  lr: 0.003526  min_lr: 0.003526  loss: 3.7773 (3.7493)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0856  max mem: 31830
Epoch: [82]  [210/312]  eta: 0:00:58  lr: 0.003526  min_lr: 0.003526  loss: 3.5737 (3.7454)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.1941  max mem: 31830
Epoch: [82]  [220/312]  eta: 0:00:52  lr: 0.003525  min_lr: 0.003525  loss: 3.7999 (3.7566)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.1091  max mem: 31830
Epoch: [82]  [230/312]  eta: 0:00:46  lr: 0.003525  min_lr: 0.003525  loss: 3.7999 (3.7547)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0920  max mem: 31830
Epoch: [82]  [240/312]  eta: 0:00:40  lr: 0.003524  min_lr: 0.003524  loss: 3.8169 (3.7551)  weight_decay: 0.0500 (0.0500)  time: 0.5004  data: 0.0924  max mem: 31830
Epoch: [82]  [250/312]  eta: 0:00:35  lr: 0.003524  min_lr: 0.003524  loss: 3.8231 (3.7579)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.1268  max mem: 31830
Epoch: [82]  [260/312]  eta: 0:00:29  lr: 0.003523  min_lr: 0.003523  loss: 3.7707 (3.7602)  weight_decay: 0.0500 (0.0500)  time: 0.6462  data: 0.2371  max mem: 31830
Epoch: [82]  [270/312]  eta: 0:00:23  lr: 0.003523  min_lr: 0.003523  loss: 4.0045 (3.7740)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.1114  max mem: 31830
Epoch: [82]  [280/312]  eta: 0:00:18  lr: 0.003522  min_lr: 0.003522  loss: 4.1001 (3.7736)  weight_decay: 0.0500 (0.0500)  time: 0.5256  data: 0.1051  max mem: 31830
Epoch: [82]  [290/312]  eta: 0:00:12  lr: 0.003522  min_lr: 0.003522  loss: 4.0838 (3.7818)  weight_decay: 0.0500 (0.0500)  time: 0.6159  data: 0.1634  max mem: 31830
Epoch: [82]  [300/312]  eta: 0:00:06  lr: 0.003521  min_lr: 0.003521  loss: 3.6052 (3.7636)  weight_decay: 0.0500 (0.0500)  time: 0.4788  data: 0.0587  max mem: 31830
Epoch: [82]  [310/312]  eta: 0:00:01  lr: 0.003521  min_lr: 0.003521  loss: 3.4143 (3.7596)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [82]  [311/312]  eta: 0:00:00  lr: 0.003521  min_lr: 0.003521  loss: 3.4143 (3.7598)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [82] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.003521  min_lr: 0.003521  loss: 3.4143 (3.7781)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2930 (1.2930)  acc1: 74.4792 (74.4792)  acc5: 92.7083 (92.7083)  time: 8.8766  data: 8.7165  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5928 (1.5387)  acc1: 64.1927 (65.5200)  acc5: 87.2396 (87.1360)  time: 1.1067  data: 0.9686  max mem: 31830
Test: Total time: 0:00:10 (1.1274 s / it)
* Acc@1 65.536 Acc@5 87.328 loss 1.546
Accuracy of the model on the 50000 test images: 65.5%
Max accuracy: 65.78%
Epoch: [83]  [  0/312]  eta: 1:02:27  lr: 0.003521  min_lr: 0.003521  loss: 4.0495 (4.0495)  weight_decay: 0.0500 (0.0500)  time: 12.0121  data: 10.1276  max mem: 31830
Epoch: [83]  [ 10/312]  eta: 0:08:49  lr: 0.003520  min_lr: 0.003520  loss: 3.6998 (3.4679)  weight_decay: 0.0500 (0.0500)  time: 1.7549  data: 1.0565  max mem: 31830
Epoch: [83]  [ 20/312]  eta: 0:05:23  lr: 0.003520  min_lr: 0.003520  loss: 3.7777 (3.6366)  weight_decay: 0.0500 (0.0500)  time: 0.5611  data: 0.0750  max mem: 31830
Epoch: [83]  [ 30/312]  eta: 0:04:07  lr: 0.003520  min_lr: 0.003520  loss: 3.7848 (3.6787)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0007  max mem: 31830
Epoch: [83]  [ 40/312]  eta: 0:03:27  lr: 0.003519  min_lr: 0.003519  loss: 3.7819 (3.6710)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [83]  [ 50/312]  eta: 0:03:00  lr: 0.003519  min_lr: 0.003519  loss: 3.7819 (3.6892)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [83]  [ 60/312]  eta: 0:02:42  lr: 0.003518  min_lr: 0.003518  loss: 3.5037 (3.6549)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0008  max mem: 31830
Epoch: [83]  [ 70/312]  eta: 0:02:30  lr: 0.003518  min_lr: 0.003518  loss: 3.5596 (3.6779)  weight_decay: 0.0500 (0.0500)  time: 0.4418  data: 0.0248  max mem: 31830
Epoch: [83]  [ 80/312]  eta: 0:02:22  lr: 0.003517  min_lr: 0.003517  loss: 3.9485 (3.6725)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.0508  max mem: 31830
Epoch: [83]  [ 90/312]  eta: 0:02:13  lr: 0.003517  min_lr: 0.003517  loss: 3.6339 (3.6568)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0503  max mem: 31830
Epoch: [83]  [100/312]  eta: 0:02:06  lr: 0.003516  min_lr: 0.003516  loss: 3.6339 (3.6493)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0486  max mem: 31830
Epoch: [83]  [110/312]  eta: 0:01:59  lr: 0.003516  min_lr: 0.003516  loss: 3.7461 (3.6580)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0371  max mem: 31830
Epoch: [83]  [120/312]  eta: 0:01:52  lr: 0.003515  min_lr: 0.003515  loss: 3.8531 (3.6554)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0519  max mem: 31830
Epoch: [83]  [130/312]  eta: 0:01:46  lr: 0.003515  min_lr: 0.003515  loss: 3.8531 (3.6766)  weight_decay: 0.0500 (0.0500)  time: 0.5667  data: 0.0794  max mem: 31830
Epoch: [83]  [140/312]  eta: 0:01:40  lr: 0.003514  min_lr: 0.003514  loss: 3.9948 (3.6832)  weight_decay: 0.0500 (0.0500)  time: 0.5725  data: 0.0403  max mem: 31830
Epoch: [83]  [150/312]  eta: 0:01:33  lr: 0.003514  min_lr: 0.003514  loss: 3.7744 (3.6762)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0298  max mem: 31830
Epoch: [83]  [160/312]  eta: 0:01:27  lr: 0.003513  min_lr: 0.003513  loss: 3.6173 (3.6733)  weight_decay: 0.0500 (0.0500)  time: 0.5338  data: 0.0352  max mem: 31830
Epoch: [83]  [170/312]  eta: 0:01:21  lr: 0.003513  min_lr: 0.003513  loss: 3.6141 (3.6695)  weight_decay: 0.0500 (0.0500)  time: 0.5491  data: 0.0519  max mem: 31830
Epoch: [83]  [180/312]  eta: 0:01:15  lr: 0.003512  min_lr: 0.003512  loss: 3.8560 (3.6774)  weight_decay: 0.0500 (0.0500)  time: 0.5560  data: 0.0901  max mem: 31830
Epoch: [83]  [190/312]  eta: 0:01:09  lr: 0.003512  min_lr: 0.003512  loss: 3.9498 (3.6921)  weight_decay: 0.0500 (0.0500)  time: 0.5478  data: 0.0443  max mem: 31830
Epoch: [83]  [200/312]  eta: 0:01:03  lr: 0.003512  min_lr: 0.003512  loss: 3.8304 (3.6945)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0358  max mem: 31830
Epoch: [83]  [210/312]  eta: 0:00:58  lr: 0.003511  min_lr: 0.003511  loss: 3.7673 (3.6957)  weight_decay: 0.0500 (0.0500)  time: 0.5757  data: 0.0581  max mem: 31830
Epoch: [83]  [220/312]  eta: 0:00:52  lr: 0.003511  min_lr: 0.003511  loss: 3.6202 (3.6927)  weight_decay: 0.0500 (0.0500)  time: 0.6130  data: 0.0232  max mem: 31830
Epoch: [83]  [230/312]  eta: 0:00:46  lr: 0.003510  min_lr: 0.003510  loss: 3.8202 (3.6942)  weight_decay: 0.0500 (0.0500)  time: 0.5089  data: 0.0060  max mem: 31830
Epoch: [83]  [240/312]  eta: 0:00:40  lr: 0.003510  min_lr: 0.003510  loss: 3.6875 (3.6947)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0062  max mem: 31830
Epoch: [83]  [250/312]  eta: 0:00:35  lr: 0.003509  min_lr: 0.003509  loss: 3.4252 (3.6902)  weight_decay: 0.0500 (0.0500)  time: 0.6117  data: 0.0054  max mem: 31830
Epoch: [83]  [260/312]  eta: 0:00:29  lr: 0.003509  min_lr: 0.003509  loss: 3.5327 (3.6914)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0051  max mem: 31830
Epoch: [83]  [270/312]  eta: 0:00:23  lr: 0.003508  min_lr: 0.003508  loss: 3.9310 (3.6930)  weight_decay: 0.0500 (0.0500)  time: 0.5529  data: 0.0008  max mem: 31830
Epoch: [83]  [280/312]  eta: 0:00:18  lr: 0.003508  min_lr: 0.003508  loss: 3.9310 (3.7041)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0019  max mem: 31830
Epoch: [83]  [290/312]  eta: 0:00:12  lr: 0.003507  min_lr: 0.003507  loss: 3.9463 (3.7071)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0219  max mem: 31830
Epoch: [83]  [300/312]  eta: 0:00:06  lr: 0.003507  min_lr: 0.003507  loss: 3.9503 (3.7088)  weight_decay: 0.0500 (0.0500)  time: 0.5208  data: 0.0204  max mem: 31830
Epoch: [83]  [310/312]  eta: 0:00:01  lr: 0.003506  min_lr: 0.003506  loss: 3.6833 (3.7043)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0001  max mem: 31830
Epoch: [83]  [311/312]  eta: 0:00:00  lr: 0.003506  min_lr: 0.003506  loss: 3.7067 (3.7051)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0001  max mem: 31830
Epoch: [83] Total time: 0:02:54 (0.5583 s / it)
Averaged stats: lr: 0.003506  min_lr: 0.003506  loss: 3.7067 (3.7842)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.5956 (1.5956)  acc1: 71.0938 (71.0938)  acc5: 90.1042 (90.1042)  time: 8.4809  data: 8.3183  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8472 (1.7368)  acc1: 63.5417 (65.1040)  acc5: 85.4167 (86.4160)  time: 1.0597  data: 0.9244  max mem: 31830
Test: Total time: 0:00:09 (1.0705 s / it)
* Acc@1 65.048 Acc@5 86.986 loss 1.730
Accuracy of the model on the 50000 test images: 65.0%
Max accuracy: 65.78%
Epoch: [84]  [  0/312]  eta: 1:00:58  lr: 0.003506  min_lr: 0.003506  loss: 3.5285 (3.5285)  weight_decay: 0.0500 (0.0500)  time: 11.7264  data: 10.4591  max mem: 31830
Epoch: [84]  [ 10/312]  eta: 0:08:21  lr: 0.003506  min_lr: 0.003506  loss: 4.0011 (3.8479)  weight_decay: 0.0500 (0.0500)  time: 1.6590  data: 0.9800  max mem: 31830
Epoch: [84]  [ 20/312]  eta: 0:05:25  lr: 0.003505  min_lr: 0.003505  loss: 3.9788 (3.7956)  weight_decay: 0.0500 (0.0500)  time: 0.5831  data: 0.0666  max mem: 31830
Epoch: [84]  [ 30/312]  eta: 0:04:08  lr: 0.003505  min_lr: 0.003505  loss: 3.8502 (3.7571)  weight_decay: 0.0500 (0.0500)  time: 0.4541  data: 0.0510  max mem: 31830
Epoch: [84]  [ 40/312]  eta: 0:03:27  lr: 0.003504  min_lr: 0.003504  loss: 3.8728 (3.7798)  weight_decay: 0.0500 (0.0500)  time: 0.3960  data: 0.0009  max mem: 31830
Epoch: [84]  [ 50/312]  eta: 0:03:06  lr: 0.003504  min_lr: 0.003504  loss: 4.0479 (3.8273)  weight_decay: 0.0500 (0.0500)  time: 0.4516  data: 0.0009  max mem: 31830
Epoch: [84]  [ 60/312]  eta: 0:02:46  lr: 0.003503  min_lr: 0.003503  loss: 4.0170 (3.8302)  weight_decay: 0.0500 (0.0500)  time: 0.4500  data: 0.0011  max mem: 31830
Epoch: [84]  [ 70/312]  eta: 0:02:35  lr: 0.003503  min_lr: 0.003503  loss: 3.9578 (3.8431)  weight_decay: 0.0500 (0.0500)  time: 0.4571  data: 0.0549  max mem: 31830
Epoch: [84]  [ 80/312]  eta: 0:02:26  lr: 0.003502  min_lr: 0.003502  loss: 4.0698 (3.8784)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.1065  max mem: 31830
Epoch: [84]  [ 90/312]  eta: 0:02:14  lr: 0.003502  min_lr: 0.003502  loss: 3.8543 (3.8462)  weight_decay: 0.0500 (0.0500)  time: 0.4847  data: 0.0525  max mem: 31830
Epoch: [84]  [100/312]  eta: 0:02:09  lr: 0.003502  min_lr: 0.003502  loss: 3.7818 (3.8530)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0525  max mem: 31830
Epoch: [84]  [110/312]  eta: 0:01:59  lr: 0.003501  min_lr: 0.003501  loss: 3.7534 (3.8308)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0525  max mem: 31830
Epoch: [84]  [120/312]  eta: 0:01:53  lr: 0.003501  min_lr: 0.003501  loss: 3.7994 (3.8388)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0519  max mem: 31830
Epoch: [84]  [130/312]  eta: 0:01:48  lr: 0.003500  min_lr: 0.003500  loss: 3.9887 (3.8363)  weight_decay: 0.0500 (0.0500)  time: 0.6225  data: 0.1259  max mem: 31830
Epoch: [84]  [140/312]  eta: 0:01:39  lr: 0.003500  min_lr: 0.003500  loss: 3.9521 (3.8447)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0747  max mem: 31830
Epoch: [84]  [150/312]  eta: 0:01:34  lr: 0.003499  min_lr: 0.003499  loss: 3.8079 (3.8302)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.0606  max mem: 31830
Epoch: [84]  [160/312]  eta: 0:01:28  lr: 0.003499  min_lr: 0.003499  loss: 3.8218 (3.8317)  weight_decay: 0.0500 (0.0500)  time: 0.5926  data: 0.1344  max mem: 31830
Epoch: [84]  [170/312]  eta: 0:01:21  lr: 0.003498  min_lr: 0.003498  loss: 4.0559 (3.8366)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0743  max mem: 31830
Epoch: [84]  [180/312]  eta: 0:01:16  lr: 0.003498  min_lr: 0.003498  loss: 3.9916 (3.8379)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.1094  max mem: 31830
Epoch: [84]  [190/312]  eta: 0:01:09  lr: 0.003497  min_lr: 0.003497  loss: 3.7978 (3.8346)  weight_decay: 0.0500 (0.0500)  time: 0.5433  data: 0.1094  max mem: 31830
Epoch: [84]  [200/312]  eta: 0:01:04  lr: 0.003497  min_lr: 0.003497  loss: 3.5356 (3.8251)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0642  max mem: 31830
Epoch: [84]  [210/312]  eta: 0:00:58  lr: 0.003496  min_lr: 0.003496  loss: 4.0486 (3.8334)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.1180  max mem: 31830
Epoch: [84]  [220/312]  eta: 0:00:51  lr: 0.003496  min_lr: 0.003496  loss: 4.0397 (3.8289)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0545  max mem: 31830
Epoch: [84]  [230/312]  eta: 0:00:46  lr: 0.003495  min_lr: 0.003495  loss: 3.9482 (3.8337)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0629  max mem: 31830
Epoch: [84]  [240/312]  eta: 0:00:40  lr: 0.003495  min_lr: 0.003495  loss: 3.8882 (3.8300)  weight_decay: 0.0500 (0.0500)  time: 0.5878  data: 0.1147  max mem: 31830
Epoch: [84]  [250/312]  eta: 0:00:34  lr: 0.003494  min_lr: 0.003494  loss: 3.9283 (3.8333)  weight_decay: 0.0500 (0.0500)  time: 0.5003  data: 0.0526  max mem: 31830
Epoch: [84]  [260/312]  eta: 0:00:29  lr: 0.003494  min_lr: 0.003494  loss: 3.9653 (3.8351)  weight_decay: 0.0500 (0.0500)  time: 0.5632  data: 0.0645  max mem: 31830
Epoch: [84]  [270/312]  eta: 0:00:23  lr: 0.003493  min_lr: 0.003493  loss: 3.7060 (3.8173)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0645  max mem: 31830
Epoch: [84]  [280/312]  eta: 0:00:18  lr: 0.003493  min_lr: 0.003493  loss: 3.5357 (3.8146)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0372  max mem: 31830
Epoch: [84]  [290/312]  eta: 0:00:12  lr: 0.003492  min_lr: 0.003492  loss: 3.7593 (3.8130)  weight_decay: 0.0500 (0.0500)  time: 0.6114  data: 0.0722  max mem: 31830
Epoch: [84]  [300/312]  eta: 0:00:06  lr: 0.003492  min_lr: 0.003492  loss: 3.9456 (3.8158)  weight_decay: 0.0500 (0.0500)  time: 0.4723  data: 0.0354  max mem: 31830
Epoch: [84]  [310/312]  eta: 0:00:01  lr: 0.003492  min_lr: 0.003492  loss: 3.9934 (3.8121)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [84]  [311/312]  eta: 0:00:00  lr: 0.003491  min_lr: 0.003491  loss: 3.9934 (3.8140)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [84] Total time: 0:02:53 (0.5551 s / it)
Averaged stats: lr: 0.003491  min_lr: 0.003491  loss: 3.9934 (3.7639)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.5650 (1.5650)  acc1: 72.2656 (72.2656)  acc5: 90.2344 (90.2344)  time: 8.1965  data: 8.0327  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9655 (1.8853)  acc1: 64.4531 (64.1920)  acc5: 85.2865 (85.8720)  time: 1.0482  data: 0.9137  max mem: 31830
Test: Total time: 0:00:09 (1.0575 s / it)
* Acc@1 64.212 Acc@5 86.294 loss 1.863
Accuracy of the model on the 50000 test images: 64.2%
Max accuracy: 65.78%
Epoch: [85]  [  0/312]  eta: 0:59:38  lr: 0.003491  min_lr: 0.003491  loss: 3.5593 (3.5593)  weight_decay: 0.0500 (0.0500)  time: 11.4706  data: 10.2762  max mem: 31830
Epoch: [85]  [ 10/312]  eta: 0:08:07  lr: 0.003491  min_lr: 0.003491  loss: 3.7807 (3.8370)  weight_decay: 0.0500 (0.0500)  time: 1.6141  data: 1.0830  max mem: 31830
Epoch: [85]  [ 20/312]  eta: 0:05:31  lr: 0.003490  min_lr: 0.003490  loss: 3.9561 (3.9320)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0935  max mem: 31830
Epoch: [85]  [ 30/312]  eta: 0:04:12  lr: 0.003490  min_lr: 0.003490  loss: 3.9810 (3.9265)  weight_decay: 0.0500 (0.0500)  time: 0.5023  data: 0.0121  max mem: 31830
Epoch: [85]  [ 40/312]  eta: 0:03:30  lr: 0.003489  min_lr: 0.003489  loss: 3.9393 (3.8889)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0008  max mem: 31830
Epoch: [85]  [ 50/312]  eta: 0:03:05  lr: 0.003489  min_lr: 0.003489  loss: 4.0884 (3.8943)  weight_decay: 0.0500 (0.0500)  time: 0.4113  data: 0.0007  max mem: 31830
Epoch: [85]  [ 60/312]  eta: 0:02:45  lr: 0.003489  min_lr: 0.003489  loss: 3.8970 (3.8685)  weight_decay: 0.0500 (0.0500)  time: 0.4106  data: 0.0007  max mem: 31830
Epoch: [85]  [ 70/312]  eta: 0:02:36  lr: 0.003488  min_lr: 0.003488  loss: 3.7490 (3.8616)  weight_decay: 0.0500 (0.0500)  time: 0.4906  data: 0.0583  max mem: 31830
Epoch: [85]  [ 80/312]  eta: 0:02:26  lr: 0.003488  min_lr: 0.003488  loss: 3.9250 (3.8387)  weight_decay: 0.0500 (0.0500)  time: 0.5668  data: 0.0984  max mem: 31830
Epoch: [85]  [ 90/312]  eta: 0:02:17  lr: 0.003487  min_lr: 0.003487  loss: 3.8602 (3.8136)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0798  max mem: 31830
Epoch: [85]  [100/312]  eta: 0:02:11  lr: 0.003487  min_lr: 0.003487  loss: 3.5726 (3.7960)  weight_decay: 0.0500 (0.0500)  time: 0.5630  data: 0.0661  max mem: 31830
Epoch: [85]  [110/312]  eta: 0:02:02  lr: 0.003486  min_lr: 0.003486  loss: 3.5160 (3.7811)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0617  max mem: 31830
Epoch: [85]  [120/312]  eta: 0:01:55  lr: 0.003486  min_lr: 0.003486  loss: 3.4151 (3.7515)  weight_decay: 0.0500 (0.0500)  time: 0.5115  data: 0.0589  max mem: 31830
Epoch: [85]  [130/312]  eta: 0:01:48  lr: 0.003485  min_lr: 0.003485  loss: 3.6963 (3.7604)  weight_decay: 0.0500 (0.0500)  time: 0.5564  data: 0.0431  max mem: 31830
Epoch: [85]  [140/312]  eta: 0:01:40  lr: 0.003485  min_lr: 0.003485  loss: 3.9199 (3.7852)  weight_decay: 0.0500 (0.0500)  time: 0.4928  data: 0.0427  max mem: 31830
Epoch: [85]  [150/312]  eta: 0:01:35  lr: 0.003484  min_lr: 0.003484  loss: 4.0667 (3.7984)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0603  max mem: 31830
Epoch: [85]  [160/312]  eta: 0:01:28  lr: 0.003484  min_lr: 0.003484  loss: 4.0667 (3.8136)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0432  max mem: 31830
Epoch: [85]  [170/312]  eta: 0:01:22  lr: 0.003483  min_lr: 0.003483  loss: 3.8162 (3.8097)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0321  max mem: 31830
Epoch: [85]  [180/312]  eta: 0:01:16  lr: 0.003483  min_lr: 0.003483  loss: 3.8162 (3.8133)  weight_decay: 0.0500 (0.0500)  time: 0.6026  data: 0.0664  max mem: 31830
Epoch: [85]  [190/312]  eta: 0:01:09  lr: 0.003482  min_lr: 0.003482  loss: 4.0165 (3.8157)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0413  max mem: 31830
Epoch: [85]  [200/312]  eta: 0:01:04  lr: 0.003482  min_lr: 0.003482  loss: 3.8239 (3.8180)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0575  max mem: 31830
Epoch: [85]  [210/312]  eta: 0:00:59  lr: 0.003481  min_lr: 0.003481  loss: 3.8588 (3.8228)  weight_decay: 0.0500 (0.0500)  time: 0.6441  data: 0.0958  max mem: 31830
Epoch: [85]  [220/312]  eta: 0:00:52  lr: 0.003481  min_lr: 0.003481  loss: 3.6895 (3.8181)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0391  max mem: 31830
Epoch: [85]  [230/312]  eta: 0:00:47  lr: 0.003480  min_lr: 0.003480  loss: 3.4958 (3.8160)  weight_decay: 0.0500 (0.0500)  time: 0.5155  data: 0.0383  max mem: 31830
Epoch: [85]  [240/312]  eta: 0:00:40  lr: 0.003480  min_lr: 0.003480  loss: 3.5138 (3.8009)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0382  max mem: 31830
Epoch: [85]  [250/312]  eta: 0:00:35  lr: 0.003479  min_lr: 0.003479  loss: 3.6331 (3.8031)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0378  max mem: 31830
Epoch: [85]  [260/312]  eta: 0:00:29  lr: 0.003479  min_lr: 0.003479  loss: 3.9127 (3.8049)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0656  max mem: 31830
Epoch: [85]  [270/312]  eta: 0:00:23  lr: 0.003478  min_lr: 0.003478  loss: 4.0505 (3.8110)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0286  max mem: 31830
Epoch: [85]  [280/312]  eta: 0:00:18  lr: 0.003478  min_lr: 0.003478  loss: 3.8633 (3.8065)  weight_decay: 0.0500 (0.0500)  time: 0.5812  data: 0.0359  max mem: 31830
Epoch: [85]  [290/312]  eta: 0:00:12  lr: 0.003477  min_lr: 0.003477  loss: 3.8266 (3.8106)  weight_decay: 0.0500 (0.0500)  time: 0.6065  data: 0.0357  max mem: 31830
Epoch: [85]  [300/312]  eta: 0:00:06  lr: 0.003477  min_lr: 0.003477  loss: 3.9849 (3.8112)  weight_decay: 0.0500 (0.0500)  time: 0.4263  data: 0.0058  max mem: 31830
Epoch: [85]  [310/312]  eta: 0:00:01  lr: 0.003476  min_lr: 0.003476  loss: 3.9942 (3.8151)  weight_decay: 0.0500 (0.0500)  time: 0.3857  data: 0.0057  max mem: 31830
Epoch: [85]  [311/312]  eta: 0:00:00  lr: 0.003476  min_lr: 0.003476  loss: 3.9849 (3.8115)  weight_decay: 0.0500 (0.0500)  time: 0.3857  data: 0.0057  max mem: 31830
Epoch: [85] Total time: 0:02:53 (0.5572 s / it)
Averaged stats: lr: 0.003476  min_lr: 0.003476  loss: 3.9849 (3.7867)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6520 (1.6520)  acc1: 70.1823 (70.1823)  acc5: 90.1042 (90.1042)  time: 8.2560  data: 8.0916  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9304 (1.7993)  acc1: 63.6719 (64.4320)  acc5: 87.5000 (86.6720)  time: 1.0335  data: 0.8992  max mem: 31830
Test: Total time: 0:00:09 (1.0488 s / it)
* Acc@1 64.524 Acc@5 86.426 loss 1.800
Accuracy of the model on the 50000 test images: 64.5%
Max accuracy: 65.78%
Epoch: [86]  [  0/312]  eta: 1:03:45  lr: 0.003476  min_lr: 0.003476  loss: 2.5248 (2.5248)  weight_decay: 0.0500 (0.0500)  time: 12.2605  data: 8.4581  max mem: 31830
Epoch: [86]  [ 10/312]  eta: 0:09:21  lr: 0.003476  min_lr: 0.003476  loss: 3.5639 (3.5056)  weight_decay: 0.0500 (0.0500)  time: 1.8585  data: 0.9860  max mem: 31830
Epoch: [86]  [ 20/312]  eta: 0:05:37  lr: 0.003475  min_lr: 0.003475  loss: 3.8154 (3.7089)  weight_decay: 0.0500 (0.0500)  time: 0.6017  data: 0.1197  max mem: 31830
Epoch: [86]  [ 30/312]  eta: 0:04:17  lr: 0.003475  min_lr: 0.003475  loss: 4.0042 (3.8127)  weight_decay: 0.0500 (0.0500)  time: 0.3924  data: 0.0008  max mem: 31830
Epoch: [86]  [ 40/312]  eta: 0:03:34  lr: 0.003474  min_lr: 0.003474  loss: 3.9757 (3.8397)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0012  max mem: 31830
Epoch: [86]  [ 50/312]  eta: 0:03:06  lr: 0.003474  min_lr: 0.003474  loss: 3.8839 (3.8514)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [86]  [ 60/312]  eta: 0:02:46  lr: 0.003473  min_lr: 0.003473  loss: 3.8486 (3.7999)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0007  max mem: 31830
Epoch: [86]  [ 70/312]  eta: 0:02:30  lr: 0.003473  min_lr: 0.003473  loss: 3.8486 (3.8267)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0007  max mem: 31830
Epoch: [86]  [ 80/312]  eta: 0:02:23  lr: 0.003472  min_lr: 0.003472  loss: 3.8286 (3.8118)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0310  max mem: 31830
Epoch: [86]  [ 90/312]  eta: 0:02:13  lr: 0.003472  min_lr: 0.003472  loss: 3.9284 (3.8182)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0313  max mem: 31830
Epoch: [86]  [100/312]  eta: 0:02:06  lr: 0.003472  min_lr: 0.003472  loss: 3.9425 (3.8002)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0233  max mem: 31830
Epoch: [86]  [110/312]  eta: 0:02:00  lr: 0.003471  min_lr: 0.003471  loss: 3.7881 (3.7969)  weight_decay: 0.0500 (0.0500)  time: 0.5869  data: 0.0554  max mem: 31830
Epoch: [86]  [120/312]  eta: 0:01:52  lr: 0.003471  min_lr: 0.003471  loss: 3.9491 (3.8099)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0332  max mem: 31830
Epoch: [86]  [130/312]  eta: 0:01:46  lr: 0.003470  min_lr: 0.003470  loss: 4.0875 (3.8143)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0140  max mem: 31830
Epoch: [86]  [140/312]  eta: 0:01:39  lr: 0.003470  min_lr: 0.003470  loss: 3.8204 (3.8092)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0141  max mem: 31830
Epoch: [86]  [150/312]  eta: 0:01:33  lr: 0.003469  min_lr: 0.003469  loss: 3.7397 (3.8004)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0147  max mem: 31830
Epoch: [86]  [160/312]  eta: 0:01:27  lr: 0.003469  min_lr: 0.003469  loss: 3.8667 (3.8024)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0274  max mem: 31830
Epoch: [86]  [170/312]  eta: 0:01:20  lr: 0.003468  min_lr: 0.003468  loss: 3.8899 (3.8064)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0141  max mem: 31830
Epoch: [86]  [180/312]  eta: 0:01:15  lr: 0.003468  min_lr: 0.003468  loss: 3.7777 (3.7947)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0142  max mem: 31830
Epoch: [86]  [190/312]  eta: 0:01:09  lr: 0.003467  min_lr: 0.003467  loss: 3.5243 (3.7875)  weight_decay: 0.0500 (0.0500)  time: 0.5834  data: 0.0281  max mem: 31830
Epoch: [86]  [200/312]  eta: 0:01:03  lr: 0.003467  min_lr: 0.003467  loss: 3.8961 (3.7935)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0152  max mem: 31830
Epoch: [86]  [210/312]  eta: 0:00:57  lr: 0.003466  min_lr: 0.003466  loss: 3.9722 (3.7894)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0131  max mem: 31830
Epoch: [86]  [220/312]  eta: 0:00:51  lr: 0.003466  min_lr: 0.003466  loss: 3.9075 (3.7972)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0140  max mem: 31830
Epoch: [86]  [230/312]  eta: 0:00:46  lr: 0.003465  min_lr: 0.003465  loss: 3.7927 (3.7912)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0145  max mem: 31830
Epoch: [86]  [240/312]  eta: 0:00:40  lr: 0.003465  min_lr: 0.003465  loss: 3.5879 (3.7815)  weight_decay: 0.0500 (0.0500)  time: 0.5978  data: 0.0196  max mem: 31830
Epoch: [86]  [250/312]  eta: 0:00:34  lr: 0.003464  min_lr: 0.003464  loss: 3.9607 (3.7871)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0289  max mem: 31830
Epoch: [86]  [260/312]  eta: 0:00:29  lr: 0.003464  min_lr: 0.003464  loss: 4.0724 (3.8023)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0386  max mem: 31830
Epoch: [86]  [270/312]  eta: 0:00:23  lr: 0.003463  min_lr: 0.003463  loss: 4.0090 (3.8012)  weight_decay: 0.0500 (0.0500)  time: 0.5916  data: 0.0212  max mem: 31830
Epoch: [86]  [280/312]  eta: 0:00:17  lr: 0.003463  min_lr: 0.003463  loss: 3.9758 (3.8097)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0069  max mem: 31830
Epoch: [86]  [290/312]  eta: 0:00:12  lr: 0.003462  min_lr: 0.003462  loss: 3.9936 (3.8145)  weight_decay: 0.0500 (0.0500)  time: 0.5303  data: 0.0132  max mem: 31830
Epoch: [86]  [300/312]  eta: 0:00:06  lr: 0.003462  min_lr: 0.003462  loss: 3.8558 (3.8124)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0116  max mem: 31830
Epoch: [86]  [310/312]  eta: 0:00:01  lr: 0.003461  min_lr: 0.003461  loss: 3.9276 (3.8135)  weight_decay: 0.0500 (0.0500)  time: 0.4010  data: 0.0002  max mem: 31830
Epoch: [86]  [311/312]  eta: 0:00:00  lr: 0.003461  min_lr: 0.003461  loss: 3.9276 (3.8092)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0001  max mem: 31830
Epoch: [86] Total time: 0:02:52 (0.5538 s / it)
Averaged stats: lr: 0.003461  min_lr: 0.003461  loss: 3.9276 (3.7592)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.4258 (1.4258)  acc1: 72.2656 (72.2656)  acc5: 90.6250 (90.6250)  time: 8.5460  data: 8.3862  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8621 (1.6926)  acc1: 63.2812 (65.3120)  acc5: 86.1979 (86.7680)  time: 1.0709  data: 0.9319  max mem: 31830
Test: Total time: 0:00:09 (1.0839 s / it)
* Acc@1 64.956 Acc@5 86.770 loss 1.693
Accuracy of the model on the 50000 test images: 65.0%
Max accuracy: 65.78%
Epoch: [87]  [  0/312]  eta: 1:04:54  lr: 0.003461  min_lr: 0.003461  loss: 3.4803 (3.4803)  weight_decay: 0.0500 (0.0500)  time: 12.4827  data: 8.6040  max mem: 31830
Epoch: [87]  [ 10/312]  eta: 0:08:39  lr: 0.003461  min_lr: 0.003461  loss: 3.9825 (4.0507)  weight_decay: 0.0500 (0.0500)  time: 1.7212  data: 1.0015  max mem: 31830
Epoch: [87]  [ 20/312]  eta: 0:05:24  lr: 0.003460  min_lr: 0.003460  loss: 3.9272 (3.9705)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.1209  max mem: 31830
Epoch: [87]  [ 30/312]  eta: 0:04:08  lr: 0.003460  min_lr: 0.003460  loss: 3.7600 (3.8635)  weight_decay: 0.0500 (0.0500)  time: 0.4193  data: 0.0007  max mem: 31830
Epoch: [87]  [ 40/312]  eta: 0:03:27  lr: 0.003459  min_lr: 0.003459  loss: 3.6129 (3.8188)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0008  max mem: 31830
Epoch: [87]  [ 50/312]  eta: 0:03:01  lr: 0.003459  min_lr: 0.003459  loss: 3.8837 (3.8319)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0009  max mem: 31830
Epoch: [87]  [ 60/312]  eta: 0:02:41  lr: 0.003458  min_lr: 0.003458  loss: 3.9777 (3.8321)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0016  max mem: 31830
Epoch: [87]  [ 70/312]  eta: 0:02:33  lr: 0.003458  min_lr: 0.003458  loss: 3.7035 (3.7844)  weight_decay: 0.0500 (0.0500)  time: 0.4899  data: 0.0072  max mem: 31830
Epoch: [87]  [ 80/312]  eta: 0:02:24  lr: 0.003457  min_lr: 0.003457  loss: 3.4852 (3.7558)  weight_decay: 0.0500 (0.0500)  time: 0.5614  data: 0.0065  max mem: 31830
Epoch: [87]  [ 90/312]  eta: 0:02:14  lr: 0.003457  min_lr: 0.003457  loss: 3.4852 (3.7256)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0008  max mem: 31830
Epoch: [87]  [100/312]  eta: 0:02:09  lr: 0.003456  min_lr: 0.003456  loss: 3.3531 (3.6975)  weight_decay: 0.0500 (0.0500)  time: 0.5711  data: 0.0121  max mem: 31830
Epoch: [87]  [110/312]  eta: 0:01:59  lr: 0.003456  min_lr: 0.003456  loss: 3.7818 (3.7263)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0123  max mem: 31830
Epoch: [87]  [120/312]  eta: 0:01:54  lr: 0.003455  min_lr: 0.003455  loss: 3.9920 (3.7469)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0009  max mem: 31830
Epoch: [87]  [130/312]  eta: 0:01:48  lr: 0.003455  min_lr: 0.003455  loss: 3.9503 (3.7521)  weight_decay: 0.0500 (0.0500)  time: 0.6091  data: 0.0008  max mem: 31830
Epoch: [87]  [140/312]  eta: 0:01:39  lr: 0.003454  min_lr: 0.003454  loss: 3.7983 (3.7455)  weight_decay: 0.0500 (0.0500)  time: 0.4938  data: 0.0009  max mem: 31830
Epoch: [87]  [150/312]  eta: 0:01:34  lr: 0.003454  min_lr: 0.003454  loss: 3.9082 (3.7448)  weight_decay: 0.0500 (0.0500)  time: 0.5081  data: 0.0017  max mem: 31830
Epoch: [87]  [160/312]  eta: 0:01:28  lr: 0.003453  min_lr: 0.003453  loss: 3.6549 (3.7415)  weight_decay: 0.0500 (0.0500)  time: 0.5960  data: 0.0065  max mem: 31830
Epoch: [87]  [170/312]  eta: 0:01:22  lr: 0.003453  min_lr: 0.003453  loss: 3.6549 (3.7380)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0055  max mem: 31830
Epoch: [87]  [180/312]  eta: 0:01:16  lr: 0.003452  min_lr: 0.003452  loss: 4.0564 (3.7563)  weight_decay: 0.0500 (0.0500)  time: 0.5345  data: 0.0006  max mem: 31830
Epoch: [87]  [190/312]  eta: 0:01:09  lr: 0.003452  min_lr: 0.003452  loss: 4.0044 (3.7541)  weight_decay: 0.0500 (0.0500)  time: 0.4870  data: 0.0007  max mem: 31830
Epoch: [87]  [200/312]  eta: 0:01:03  lr: 0.003451  min_lr: 0.003451  loss: 3.8276 (3.7438)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0008  max mem: 31830
Epoch: [87]  [210/312]  eta: 0:00:58  lr: 0.003451  min_lr: 0.003451  loss: 3.4855 (3.7370)  weight_decay: 0.0500 (0.0500)  time: 0.6074  data: 0.0009  max mem: 31830
Epoch: [87]  [220/312]  eta: 0:00:51  lr: 0.003450  min_lr: 0.003450  loss: 3.8716 (3.7457)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0008  max mem: 31830
Epoch: [87]  [230/312]  eta: 0:00:46  lr: 0.003450  min_lr: 0.003450  loss: 3.8716 (3.7463)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0010  max mem: 31830
Epoch: [87]  [240/312]  eta: 0:00:40  lr: 0.003449  min_lr: 0.003449  loss: 3.6405 (3.7489)  weight_decay: 0.0500 (0.0500)  time: 0.6156  data: 0.0011  max mem: 31830
Epoch: [87]  [250/312]  eta: 0:00:34  lr: 0.003449  min_lr: 0.003449  loss: 4.0559 (3.7580)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0010  max mem: 31830
Epoch: [87]  [260/312]  eta: 0:00:29  lr: 0.003448  min_lr: 0.003448  loss: 3.9159 (3.7578)  weight_decay: 0.0500 (0.0500)  time: 0.4941  data: 0.0011  max mem: 31830
Epoch: [87]  [270/312]  eta: 0:00:23  lr: 0.003448  min_lr: 0.003448  loss: 3.9159 (3.7535)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0016  max mem: 31830
Epoch: [87]  [280/312]  eta: 0:00:17  lr: 0.003447  min_lr: 0.003447  loss: 3.9203 (3.7537)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0100  max mem: 31830
Epoch: [87]  [290/312]  eta: 0:00:12  lr: 0.003447  min_lr: 0.003447  loss: 3.8654 (3.7495)  weight_decay: 0.0500 (0.0500)  time: 0.6124  data: 0.0090  max mem: 31830
Epoch: [87]  [300/312]  eta: 0:00:06  lr: 0.003446  min_lr: 0.003446  loss: 3.8862 (3.7497)  weight_decay: 0.0500 (0.0500)  time: 0.4859  data: 0.0002  max mem: 31830
Epoch: [87]  [310/312]  eta: 0:00:01  lr: 0.003446  min_lr: 0.003446  loss: 4.0019 (3.7506)  weight_decay: 0.0500 (0.0500)  time: 0.3907  data: 0.0001  max mem: 31830
Epoch: [87]  [311/312]  eta: 0:00:00  lr: 0.003446  min_lr: 0.003446  loss: 3.9543 (3.7512)  weight_decay: 0.0500 (0.0500)  time: 0.3904  data: 0.0001  max mem: 31830
Epoch: [87] Total time: 0:02:52 (0.5531 s / it)
Averaged stats: lr: 0.003446  min_lr: 0.003446  loss: 3.9543 (3.7849)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4527 (1.4527)  acc1: 73.6979 (73.6979)  acc5: 90.7552 (90.7552)  time: 8.3749  data: 8.2078  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9760 (1.8231)  acc1: 62.7604 (64.3840)  acc5: 85.5469 (86.0640)  time: 1.0472  data: 0.9120  max mem: 31830
Test: Total time: 0:00:09 (1.0569 s / it)
* Acc@1 63.982 Acc@5 86.364 loss 1.838
Accuracy of the model on the 50000 test images: 64.0%
Max accuracy: 65.78%
Epoch: [88]  [  0/312]  eta: 1:01:16  lr: 0.003446  min_lr: 0.003446  loss: 2.8686 (2.8686)  weight_decay: 0.0500 (0.0500)  time: 11.7831  data: 11.3863  max mem: 31830
Epoch: [88]  [ 10/312]  eta: 0:08:09  lr: 0.003445  min_lr: 0.003445  loss: 3.3542 (3.4403)  weight_decay: 0.0500 (0.0500)  time: 1.6222  data: 1.0362  max mem: 31830
Epoch: [88]  [ 20/312]  eta: 0:05:29  lr: 0.003445  min_lr: 0.003445  loss: 3.5940 (3.5595)  weight_decay: 0.0500 (0.0500)  time: 0.5956  data: 0.0384  max mem: 31830
Epoch: [88]  [ 30/312]  eta: 0:04:11  lr: 0.003444  min_lr: 0.003444  loss: 3.8373 (3.6643)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0381  max mem: 31830
Epoch: [88]  [ 40/312]  eta: 0:03:29  lr: 0.003444  min_lr: 0.003444  loss: 3.9667 (3.7113)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0006  max mem: 31830
Epoch: [88]  [ 50/312]  eta: 0:03:14  lr: 0.003443  min_lr: 0.003443  loss: 3.8359 (3.7037)  weight_decay: 0.0500 (0.0500)  time: 0.5088  data: 0.0581  max mem: 31830
Epoch: [88]  [ 60/312]  eta: 0:02:52  lr: 0.003443  min_lr: 0.003443  loss: 3.6003 (3.6835)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.0589  max mem: 31830
Epoch: [88]  [ 70/312]  eta: 0:02:45  lr: 0.003442  min_lr: 0.003442  loss: 3.8948 (3.7022)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0498  max mem: 31830
Epoch: [88]  [ 80/312]  eta: 0:02:32  lr: 0.003442  min_lr: 0.003442  loss: 4.0832 (3.7307)  weight_decay: 0.0500 (0.0500)  time: 0.5705  data: 0.0491  max mem: 31830
Epoch: [88]  [ 90/312]  eta: 0:02:21  lr: 0.003441  min_lr: 0.003441  loss: 4.0878 (3.7474)  weight_decay: 0.0500 (0.0500)  time: 0.4819  data: 0.0123  max mem: 31830
Epoch: [88]  [100/312]  eta: 0:02:16  lr: 0.003441  min_lr: 0.003441  loss: 4.0367 (3.7686)  weight_decay: 0.0500 (0.0500)  time: 0.5891  data: 0.0389  max mem: 31830
Epoch: [88]  [110/312]  eta: 0:02:05  lr: 0.003440  min_lr: 0.003440  loss: 3.9651 (3.7545)  weight_decay: 0.0500 (0.0500)  time: 0.5439  data: 0.0273  max mem: 31830
Epoch: [88]  [120/312]  eta: 0:01:57  lr: 0.003440  min_lr: 0.003440  loss: 3.6837 (3.7431)  weight_decay: 0.0500 (0.0500)  time: 0.4671  data: 0.0159  max mem: 31830
Epoch: [88]  [130/312]  eta: 0:01:52  lr: 0.003439  min_lr: 0.003439  loss: 3.6310 (3.7502)  weight_decay: 0.0500 (0.0500)  time: 0.5986  data: 0.0393  max mem: 31830
Epoch: [88]  [140/312]  eta: 0:01:43  lr: 0.003439  min_lr: 0.003439  loss: 3.6726 (3.7418)  weight_decay: 0.0500 (0.0500)  time: 0.5302  data: 0.0242  max mem: 31830
Epoch: [88]  [150/312]  eta: 0:01:38  lr: 0.003438  min_lr: 0.003438  loss: 3.7694 (3.7492)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.0471  max mem: 31830
Epoch: [88]  [160/312]  eta: 0:01:30  lr: 0.003438  min_lr: 0.003438  loss: 3.8304 (3.7445)  weight_decay: 0.0500 (0.0500)  time: 0.5676  data: 0.0472  max mem: 31830
Epoch: [88]  [170/312]  eta: 0:01:24  lr: 0.003437  min_lr: 0.003437  loss: 3.7225 (3.7406)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0349  max mem: 31830
Epoch: [88]  [180/312]  eta: 0:01:18  lr: 0.003437  min_lr: 0.003437  loss: 3.8539 (3.7509)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0791  max mem: 31830
Epoch: [88]  [190/312]  eta: 0:01:11  lr: 0.003436  min_lr: 0.003436  loss: 3.7680 (3.7406)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0451  max mem: 31830
Epoch: [88]  [200/312]  eta: 0:01:05  lr: 0.003436  min_lr: 0.003436  loss: 3.6713 (3.7470)  weight_decay: 0.0500 (0.0500)  time: 0.4692  data: 0.0384  max mem: 31830
Epoch: [88]  [210/312]  eta: 0:00:59  lr: 0.003435  min_lr: 0.003435  loss: 3.9949 (3.7555)  weight_decay: 0.0500 (0.0500)  time: 0.6152  data: 0.1100  max mem: 31830
Epoch: [88]  [220/312]  eta: 0:00:53  lr: 0.003435  min_lr: 0.003435  loss: 3.8338 (3.7369)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0723  max mem: 31830
Epoch: [88]  [230/312]  eta: 0:00:47  lr: 0.003434  min_lr: 0.003434  loss: 3.4829 (3.7393)  weight_decay: 0.0500 (0.0500)  time: 0.5010  data: 0.0528  max mem: 31830
Epoch: [88]  [240/312]  eta: 0:00:41  lr: 0.003434  min_lr: 0.003434  loss: 3.9103 (3.7406)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0528  max mem: 31830
Epoch: [88]  [250/312]  eta: 0:00:35  lr: 0.003433  min_lr: 0.003433  loss: 3.9076 (3.7451)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0550  max mem: 31830
Epoch: [88]  [260/312]  eta: 0:00:30  lr: 0.003433  min_lr: 0.003433  loss: 3.8478 (3.7390)  weight_decay: 0.0500 (0.0500)  time: 0.6263  data: 0.1327  max mem: 31830
Epoch: [88]  [270/312]  eta: 0:00:23  lr: 0.003432  min_lr: 0.003432  loss: 3.9932 (3.7427)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0784  max mem: 31830
Epoch: [88]  [280/312]  eta: 0:00:18  lr: 0.003432  min_lr: 0.003432  loss: 3.7115 (3.7407)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0659  max mem: 31830
Epoch: [88]  [290/312]  eta: 0:00:12  lr: 0.003431  min_lr: 0.003431  loss: 3.6444 (3.7422)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0995  max mem: 31830
Epoch: [88]  [300/312]  eta: 0:00:06  lr: 0.003431  min_lr: 0.003431  loss: 3.9091 (3.7373)  weight_decay: 0.0500 (0.0500)  time: 0.4487  data: 0.0340  max mem: 31830
Epoch: [88]  [310/312]  eta: 0:00:01  lr: 0.003430  min_lr: 0.003430  loss: 3.7107 (3.7343)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [88]  [311/312]  eta: 0:00:00  lr: 0.003430  min_lr: 0.003430  loss: 3.6229 (3.7314)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [88] Total time: 0:02:55 (0.5622 s / it)
Averaged stats: lr: 0.003430  min_lr: 0.003430  loss: 3.6229 (3.7756)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.4233 (1.4233)  acc1: 71.2240 (71.2240)  acc5: 90.3646 (90.3646)  time: 8.5698  data: 8.4055  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8945 (1.6932)  acc1: 63.2812 (64.9440)  acc5: 85.6771 (86.9920)  time: 1.0704  data: 0.9340  max mem: 31830
Test: Total time: 0:00:09 (1.0862 s / it)
* Acc@1 64.384 Acc@5 86.842 loss 1.715
Accuracy of the model on the 50000 test images: 64.4%
Max accuracy: 65.78%
Epoch: [89]  [  0/312]  eta: 1:06:16  lr: 0.003430  min_lr: 0.003430  loss: 4.4904 (4.4904)  weight_decay: 0.0500 (0.0500)  time: 12.7442  data: 11.1475  max mem: 31830
Epoch: [89]  [ 10/312]  eta: 0:08:44  lr: 0.003430  min_lr: 0.003430  loss: 3.9740 (3.9045)  weight_decay: 0.0500 (0.0500)  time: 1.7378  data: 1.0139  max mem: 31830
Epoch: [89]  [ 20/312]  eta: 0:05:30  lr: 0.003429  min_lr: 0.003429  loss: 3.8069 (3.8139)  weight_decay: 0.0500 (0.0500)  time: 0.5516  data: 0.0006  max mem: 31830
Epoch: [89]  [ 30/312]  eta: 0:04:12  lr: 0.003429  min_lr: 0.003429  loss: 3.8065 (3.7846)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0007  max mem: 31830
Epoch: [89]  [ 40/312]  eta: 0:03:30  lr: 0.003428  min_lr: 0.003428  loss: 3.8685 (3.8289)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0007  max mem: 31830
Epoch: [89]  [ 50/312]  eta: 0:03:03  lr: 0.003428  min_lr: 0.003428  loss: 3.9685 (3.8095)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0009  max mem: 31830
Epoch: [89]  [ 60/312]  eta: 0:02:43  lr: 0.003427  min_lr: 0.003427  loss: 4.0213 (3.8275)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0009  max mem: 31830
Epoch: [89]  [ 70/312]  eta: 0:02:31  lr: 0.003427  min_lr: 0.003427  loss: 3.9585 (3.8193)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0008  max mem: 31830
Epoch: [89]  [ 80/312]  eta: 0:02:24  lr: 0.003426  min_lr: 0.003426  loss: 3.9585 (3.8370)  weight_decay: 0.0500 (0.0500)  time: 0.5353  data: 0.0344  max mem: 31830
Epoch: [89]  [ 90/312]  eta: 0:02:13  lr: 0.003426  min_lr: 0.003426  loss: 4.0523 (3.8597)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0345  max mem: 31830
Epoch: [89]  [100/312]  eta: 0:02:07  lr: 0.003425  min_lr: 0.003425  loss: 4.0954 (3.8716)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0011  max mem: 31830
Epoch: [89]  [110/312]  eta: 0:01:58  lr: 0.003425  min_lr: 0.003425  loss: 4.1738 (3.8762)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0115  max mem: 31830
Epoch: [89]  [120/312]  eta: 0:01:53  lr: 0.003424  min_lr: 0.003424  loss: 3.8819 (3.8597)  weight_decay: 0.0500 (0.0500)  time: 0.5396  data: 0.0532  max mem: 31830
Epoch: [89]  [130/312]  eta: 0:01:46  lr: 0.003424  min_lr: 0.003424  loss: 3.7173 (3.8349)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.0820  max mem: 31830
Epoch: [89]  [140/312]  eta: 0:01:39  lr: 0.003423  min_lr: 0.003423  loss: 3.5998 (3.8124)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0402  max mem: 31830
Epoch: [89]  [150/312]  eta: 0:01:33  lr: 0.003423  min_lr: 0.003423  loss: 3.7483 (3.8112)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0506  max mem: 31830
Epoch: [89]  [160/312]  eta: 0:01:27  lr: 0.003422  min_lr: 0.003422  loss: 3.8497 (3.8093)  weight_decay: 0.0500 (0.0500)  time: 0.5687  data: 0.0615  max mem: 31830
Epoch: [89]  [170/312]  eta: 0:01:21  lr: 0.003422  min_lr: 0.003422  loss: 3.6449 (3.7997)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0378  max mem: 31830
Epoch: [89]  [180/312]  eta: 0:01:15  lr: 0.003421  min_lr: 0.003421  loss: 3.8018 (3.8056)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.0837  max mem: 31830
Epoch: [89]  [190/312]  eta: 0:01:09  lr: 0.003421  min_lr: 0.003421  loss: 3.7693 (3.7935)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0586  max mem: 31830
Epoch: [89]  [200/312]  eta: 0:01:03  lr: 0.003420  min_lr: 0.003420  loss: 3.8554 (3.8011)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0323  max mem: 31830
Epoch: [89]  [210/312]  eta: 0:00:58  lr: 0.003420  min_lr: 0.003420  loss: 3.9913 (3.8050)  weight_decay: 0.0500 (0.0500)  time: 0.6270  data: 0.0600  max mem: 31830
Epoch: [89]  [220/312]  eta: 0:00:51  lr: 0.003419  min_lr: 0.003419  loss: 3.7687 (3.7950)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0293  max mem: 31830
Epoch: [89]  [230/312]  eta: 0:00:46  lr: 0.003419  min_lr: 0.003419  loss: 3.6731 (3.7946)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0137  max mem: 31830
Epoch: [89]  [240/312]  eta: 0:00:40  lr: 0.003418  min_lr: 0.003418  loss: 3.8095 (3.7964)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.0140  max mem: 31830
Epoch: [89]  [250/312]  eta: 0:00:34  lr: 0.003418  min_lr: 0.003418  loss: 3.8095 (3.7901)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0139  max mem: 31830
Epoch: [89]  [260/312]  eta: 0:00:29  lr: 0.003417  min_lr: 0.003417  loss: 3.6000 (3.7785)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0138  max mem: 31830
Epoch: [89]  [270/312]  eta: 0:00:23  lr: 0.003416  min_lr: 0.003416  loss: 3.7611 (3.7827)  weight_decay: 0.0500 (0.0500)  time: 0.5203  data: 0.0009  max mem: 31830
Epoch: [89]  [280/312]  eta: 0:00:17  lr: 0.003416  min_lr: 0.003416  loss: 3.9745 (3.7862)  weight_decay: 0.0500 (0.0500)  time: 0.5060  data: 0.0052  max mem: 31830
Epoch: [89]  [290/312]  eta: 0:00:12  lr: 0.003415  min_lr: 0.003415  loss: 3.8729 (3.7859)  weight_decay: 0.0500 (0.0500)  time: 0.5911  data: 0.0180  max mem: 31830
Epoch: [89]  [300/312]  eta: 0:00:06  lr: 0.003415  min_lr: 0.003415  loss: 3.7717 (3.7792)  weight_decay: 0.0500 (0.0500)  time: 0.4990  data: 0.0133  max mem: 31830
Epoch: [89]  [310/312]  eta: 0:00:01  lr: 0.003414  min_lr: 0.003414  loss: 3.9315 (3.7848)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0001  max mem: 31830
Epoch: [89]  [311/312]  eta: 0:00:00  lr: 0.003414  min_lr: 0.003414  loss: 3.8463 (3.7825)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0001  max mem: 31830
Epoch: [89] Total time: 0:02:53 (0.5550 s / it)
Averaged stats: lr: 0.003414  min_lr: 0.003414  loss: 3.8463 (3.7556)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.6554 (1.6554)  acc1: 71.7448 (71.7448)  acc5: 90.7552 (90.7552)  time: 8.2893  data: 8.1254  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0866 (1.9689)  acc1: 61.7188 (63.8880)  acc5: 85.9375 (86.2400)  time: 1.0395  data: 0.9029  max mem: 31830
Test: Total time: 0:00:09 (1.0518 s / it)
* Acc@1 63.668 Acc@5 86.142 loss 1.973
Accuracy of the model on the 50000 test images: 63.7%
Max accuracy: 65.78%
Epoch: [90]  [  0/312]  eta: 1:01:03  lr: 0.003414  min_lr: 0.003414  loss: 3.1240 (3.1240)  weight_decay: 0.0500 (0.0500)  time: 11.7422  data: 10.7310  max mem: 31830
Epoch: [90]  [ 10/312]  eta: 0:08:30  lr: 0.003414  min_lr: 0.003414  loss: 4.0382 (4.0776)  weight_decay: 0.0500 (0.0500)  time: 1.6912  data: 0.9761  max mem: 31830
Epoch: [90]  [ 20/312]  eta: 0:05:26  lr: 0.003413  min_lr: 0.003413  loss: 3.9174 (3.7736)  weight_decay: 0.0500 (0.0500)  time: 0.5860  data: 0.0006  max mem: 31830
Epoch: [90]  [ 30/312]  eta: 0:04:09  lr: 0.003413  min_lr: 0.003413  loss: 3.6552 (3.7695)  weight_decay: 0.0500 (0.0500)  time: 0.4428  data: 0.0007  max mem: 31830
Epoch: [90]  [ 40/312]  eta: 0:03:28  lr: 0.003412  min_lr: 0.003412  loss: 3.7194 (3.7556)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0008  max mem: 31830
Epoch: [90]  [ 50/312]  eta: 0:03:04  lr: 0.003412  min_lr: 0.003412  loss: 3.6846 (3.7422)  weight_decay: 0.0500 (0.0500)  time: 0.4228  data: 0.0008  max mem: 31830
Epoch: [90]  [ 60/312]  eta: 0:02:44  lr: 0.003411  min_lr: 0.003411  loss: 3.5001 (3.6878)  weight_decay: 0.0500 (0.0500)  time: 0.4247  data: 0.0010  max mem: 31830
Epoch: [90]  [ 70/312]  eta: 0:02:33  lr: 0.003411  min_lr: 0.003411  loss: 3.9201 (3.7454)  weight_decay: 0.0500 (0.0500)  time: 0.4567  data: 0.0011  max mem: 31830
Epoch: [90]  [ 80/312]  eta: 0:02:27  lr: 0.003410  min_lr: 0.003410  loss: 4.0145 (3.7354)  weight_decay: 0.0500 (0.0500)  time: 0.5805  data: 0.0009  max mem: 31830
Epoch: [90]  [ 90/312]  eta: 0:02:16  lr: 0.003410  min_lr: 0.003410  loss: 3.8120 (3.7391)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0133  max mem: 31830
Epoch: [90]  [100/312]  eta: 0:02:09  lr: 0.003409  min_lr: 0.003409  loss: 3.8120 (3.7526)  weight_decay: 0.0500 (0.0500)  time: 0.5080  data: 0.0261  max mem: 31830
Epoch: [90]  [110/312]  eta: 0:01:59  lr: 0.003409  min_lr: 0.003409  loss: 3.7905 (3.7433)  weight_decay: 0.0500 (0.0500)  time: 0.4855  data: 0.0142  max mem: 31830
Epoch: [90]  [120/312]  eta: 0:01:54  lr: 0.003408  min_lr: 0.003408  loss: 3.7905 (3.7376)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0196  max mem: 31830
Epoch: [90]  [130/312]  eta: 0:01:49  lr: 0.003408  min_lr: 0.003408  loss: 3.8832 (3.7422)  weight_decay: 0.0500 (0.0500)  time: 0.6463  data: 0.0191  max mem: 31830
Epoch: [90]  [140/312]  eta: 0:01:40  lr: 0.003407  min_lr: 0.003407  loss: 3.5886 (3.7282)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0122  max mem: 31830
Epoch: [90]  [150/312]  eta: 0:01:34  lr: 0.003407  min_lr: 0.003407  loss: 3.8104 (3.7482)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0123  max mem: 31830
Epoch: [90]  [160/312]  eta: 0:01:29  lr: 0.003406  min_lr: 0.003406  loss: 3.9142 (3.7375)  weight_decay: 0.0500 (0.0500)  time: 0.6110  data: 0.0008  max mem: 31830
Epoch: [90]  [170/312]  eta: 0:01:22  lr: 0.003406  min_lr: 0.003406  loss: 3.8191 (3.7355)  weight_decay: 0.0500 (0.0500)  time: 0.5698  data: 0.0007  max mem: 31830
Epoch: [90]  [180/312]  eta: 0:01:16  lr: 0.003405  min_lr: 0.003405  loss: 3.8292 (3.7506)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0009  max mem: 31830
Epoch: [90]  [190/312]  eta: 0:01:09  lr: 0.003405  min_lr: 0.003405  loss: 3.9557 (3.7577)  weight_decay: 0.0500 (0.0500)  time: 0.4822  data: 0.0011  max mem: 31830
Epoch: [90]  [200/312]  eta: 0:01:04  lr: 0.003404  min_lr: 0.003404  loss: 3.8401 (3.7625)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0018  max mem: 31830
Epoch: [90]  [210/312]  eta: 0:00:58  lr: 0.003404  min_lr: 0.003404  loss: 3.6609 (3.7503)  weight_decay: 0.0500 (0.0500)  time: 0.5901  data: 0.0024  max mem: 31830
Epoch: [90]  [220/312]  eta: 0:00:52  lr: 0.003403  min_lr: 0.003403  loss: 3.6609 (3.7468)  weight_decay: 0.0500 (0.0500)  time: 0.5336  data: 0.0130  max mem: 31830
Epoch: [90]  [230/312]  eta: 0:00:46  lr: 0.003403  min_lr: 0.003403  loss: 3.8569 (3.7518)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0123  max mem: 31830
Epoch: [90]  [240/312]  eta: 0:00:41  lr: 0.003402  min_lr: 0.003402  loss: 3.8569 (3.7467)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0008  max mem: 31830
Epoch: [90]  [250/312]  eta: 0:00:35  lr: 0.003402  min_lr: 0.003402  loss: 3.7062 (3.7495)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0015  max mem: 31830
Epoch: [90]  [260/312]  eta: 0:00:29  lr: 0.003401  min_lr: 0.003401  loss: 3.7893 (3.7453)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0025  max mem: 31830
Epoch: [90]  [270/312]  eta: 0:00:23  lr: 0.003401  min_lr: 0.003401  loss: 3.5973 (3.7322)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0021  max mem: 31830
Epoch: [90]  [280/312]  eta: 0:00:18  lr: 0.003400  min_lr: 0.003400  loss: 3.7989 (3.7409)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0028  max mem: 31830
Epoch: [90]  [290/312]  eta: 0:00:12  lr: 0.003400  min_lr: 0.003400  loss: 3.9991 (3.7457)  weight_decay: 0.0500 (0.0500)  time: 0.5655  data: 0.0023  max mem: 31830
Epoch: [90]  [300/312]  eta: 0:00:06  lr: 0.003399  min_lr: 0.003399  loss: 3.7375 (3.7457)  weight_decay: 0.0500 (0.0500)  time: 0.4816  data: 0.0002  max mem: 31830
Epoch: [90]  [310/312]  eta: 0:00:01  lr: 0.003399  min_lr: 0.003399  loss: 3.6798 (3.7412)  weight_decay: 0.0500 (0.0500)  time: 0.4033  data: 0.0002  max mem: 31830
Epoch: [90]  [311/312]  eta: 0:00:00  lr: 0.003398  min_lr: 0.003398  loss: 3.6798 (3.7385)  weight_decay: 0.0500 (0.0500)  time: 0.4030  data: 0.0001  max mem: 31830
Epoch: [90] Total time: 0:02:53 (0.5556 s / it)
Averaged stats: lr: 0.003398  min_lr: 0.003398  loss: 3.6798 (3.7608)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.2027 (1.2027)  acc1: 75.0000 (75.0000)  acc5: 91.9271 (91.9271)  time: 8.0993  data: 7.9339  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6313 (1.5082)  acc1: 64.4531 (66.9120)  acc5: 87.3698 (87.5040)  time: 1.0212  data: 0.8816  max mem: 31830
Test: Total time: 0:00:09 (1.0310 s / it)
* Acc@1 66.640 Acc@5 87.954 loss 1.505
Accuracy of the model on the 50000 test images: 66.6%
Max accuracy: 66.64%
Epoch: [91]  [  0/312]  eta: 0:56:13  lr: 0.003398  min_lr: 0.003398  loss: 3.5637 (3.5637)  weight_decay: 0.0500 (0.0500)  time: 10.8111  data: 10.0540  max mem: 31830
Epoch: [91]  [ 10/312]  eta: 0:07:58  lr: 0.003398  min_lr: 0.003398  loss: 3.8619 (3.6774)  weight_decay: 0.0500 (0.0500)  time: 1.5852  data: 0.9950  max mem: 31830
Epoch: [91]  [ 20/312]  eta: 0:05:33  lr: 0.003397  min_lr: 0.003397  loss: 3.8006 (3.6856)  weight_decay: 0.0500 (0.0500)  time: 0.6583  data: 0.1188  max mem: 31830
Epoch: [91]  [ 30/312]  eta: 0:04:13  lr: 0.003397  min_lr: 0.003397  loss: 3.7657 (3.6960)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0747  max mem: 31830
Epoch: [91]  [ 40/312]  eta: 0:03:31  lr: 0.003396  min_lr: 0.003396  loss: 3.8377 (3.6860)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0008  max mem: 31830
Epoch: [91]  [ 50/312]  eta: 0:03:04  lr: 0.003396  min_lr: 0.003396  loss: 3.5290 (3.6676)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0008  max mem: 31830
Epoch: [91]  [ 60/312]  eta: 0:02:44  lr: 0.003395  min_lr: 0.003395  loss: 3.6653 (3.6732)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0009  max mem: 31830
Epoch: [91]  [ 70/312]  eta: 0:02:34  lr: 0.003395  min_lr: 0.003395  loss: 3.7978 (3.6902)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0549  max mem: 31830
Epoch: [91]  [ 80/312]  eta: 0:02:23  lr: 0.003394  min_lr: 0.003394  loss: 3.9154 (3.6912)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0997  max mem: 31830
Epoch: [91]  [ 90/312]  eta: 0:02:13  lr: 0.003394  min_lr: 0.003394  loss: 3.7712 (3.6824)  weight_decay: 0.0500 (0.0500)  time: 0.4748  data: 0.0709  max mem: 31830
Epoch: [91]  [100/312]  eta: 0:02:08  lr: 0.003393  min_lr: 0.003393  loss: 3.7712 (3.6964)  weight_decay: 0.0500 (0.0500)  time: 0.5594  data: 0.1551  max mem: 31830
Epoch: [91]  [110/312]  eta: 0:01:58  lr: 0.003393  min_lr: 0.003393  loss: 3.8845 (3.7037)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.1298  max mem: 31830
Epoch: [91]  [120/312]  eta: 0:01:52  lr: 0.003392  min_lr: 0.003392  loss: 3.9893 (3.7266)  weight_decay: 0.0500 (0.0500)  time: 0.4992  data: 0.1045  max mem: 31830
Epoch: [91]  [130/312]  eta: 0:01:47  lr: 0.003392  min_lr: 0.003392  loss: 3.7747 (3.7203)  weight_decay: 0.0500 (0.0500)  time: 0.6077  data: 0.1830  max mem: 31830
Epoch: [91]  [140/312]  eta: 0:01:39  lr: 0.003391  min_lr: 0.003391  loss: 3.7422 (3.7212)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0792  max mem: 31830
Epoch: [91]  [150/312]  eta: 0:01:34  lr: 0.003391  min_lr: 0.003391  loss: 3.8480 (3.7294)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0577  max mem: 31830
Epoch: [91]  [160/312]  eta: 0:01:27  lr: 0.003390  min_lr: 0.003390  loss: 3.7315 (3.7305)  weight_decay: 0.0500 (0.0500)  time: 0.5687  data: 0.1120  max mem: 31830
Epoch: [91]  [170/312]  eta: 0:01:21  lr: 0.003390  min_lr: 0.003390  loss: 3.9119 (3.7451)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0552  max mem: 31830
Epoch: [91]  [180/312]  eta: 0:01:16  lr: 0.003389  min_lr: 0.003389  loss: 3.9751 (3.7360)  weight_decay: 0.0500 (0.0500)  time: 0.5957  data: 0.0505  max mem: 31830
Epoch: [91]  [190/312]  eta: 0:01:09  lr: 0.003389  min_lr: 0.003389  loss: 3.9235 (3.7438)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0504  max mem: 31830
Epoch: [91]  [200/312]  eta: 0:01:03  lr: 0.003388  min_lr: 0.003388  loss: 3.9253 (3.7447)  weight_decay: 0.0500 (0.0500)  time: 0.4784  data: 0.0508  max mem: 31830
Epoch: [91]  [210/312]  eta: 0:00:58  lr: 0.003388  min_lr: 0.003388  loss: 3.9424 (3.7501)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.1126  max mem: 31830
Epoch: [91]  [220/312]  eta: 0:00:51  lr: 0.003387  min_lr: 0.003387  loss: 3.9302 (3.7590)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0627  max mem: 31830
Epoch: [91]  [230/312]  eta: 0:00:46  lr: 0.003387  min_lr: 0.003387  loss: 4.0327 (3.7755)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0465  max mem: 31830
Epoch: [91]  [240/312]  eta: 0:00:40  lr: 0.003386  min_lr: 0.003386  loss: 4.0233 (3.7712)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0848  max mem: 31830
Epoch: [91]  [250/312]  eta: 0:00:35  lr: 0.003385  min_lr: 0.003385  loss: 3.8071 (3.7706)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0391  max mem: 31830
Epoch: [91]  [260/312]  eta: 0:00:29  lr: 0.003385  min_lr: 0.003385  loss: 3.8364 (3.7707)  weight_decay: 0.0500 (0.0500)  time: 0.6143  data: 0.0336  max mem: 31830
Epoch: [91]  [270/312]  eta: 0:00:23  lr: 0.003384  min_lr: 0.003384  loss: 3.8914 (3.7786)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0335  max mem: 31830
Epoch: [91]  [280/312]  eta: 0:00:18  lr: 0.003384  min_lr: 0.003384  loss: 3.7666 (3.7724)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0196  max mem: 31830
Epoch: [91]  [290/312]  eta: 0:00:12  lr: 0.003383  min_lr: 0.003383  loss: 3.6627 (3.7752)  weight_decay: 0.0500 (0.0500)  time: 0.5614  data: 0.0635  max mem: 31830
Epoch: [91]  [300/312]  eta: 0:00:06  lr: 0.003383  min_lr: 0.003383  loss: 3.9534 (3.7781)  weight_decay: 0.0500 (0.0500)  time: 0.4761  data: 0.0444  max mem: 31830
Epoch: [91]  [310/312]  eta: 0:00:01  lr: 0.003382  min_lr: 0.003382  loss: 3.9652 (3.7836)  weight_decay: 0.0500 (0.0500)  time: 0.4108  data: 0.0001  max mem: 31830
Epoch: [91]  [311/312]  eta: 0:00:00  lr: 0.003382  min_lr: 0.003382  loss: 3.9694 (3.7849)  weight_decay: 0.0500 (0.0500)  time: 0.4106  data: 0.0001  max mem: 31830
Epoch: [91] Total time: 0:02:53 (0.5550 s / it)
Averaged stats: lr: 0.003382  min_lr: 0.003382  loss: 3.9694 (3.7580)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.6533 (1.6533)  acc1: 70.8333 (70.8333)  acc5: 90.8854 (90.8854)  time: 8.0825  data: 7.9153  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0461 (1.9247)  acc1: 60.6771 (63.0560)  acc5: 84.6354 (86.3040)  time: 1.0149  data: 0.8796  max mem: 31830
Test: Total time: 0:00:09 (1.0268 s / it)
* Acc@1 63.798 Acc@5 86.076 loss 1.931
Accuracy of the model on the 50000 test images: 63.8%
Max accuracy: 66.64%
Epoch: [92]  [  0/312]  eta: 1:03:12  lr: 0.003382  min_lr: 0.003382  loss: 4.4103 (4.4103)  weight_decay: 0.0500 (0.0500)  time: 12.1561  data: 11.1763  max mem: 31830
Epoch: [92]  [ 10/312]  eta: 0:08:25  lr: 0.003382  min_lr: 0.003382  loss: 3.8679 (3.6388)  weight_decay: 0.0500 (0.0500)  time: 1.6739  data: 1.0167  max mem: 31830
Epoch: [92]  [ 20/312]  eta: 0:05:30  lr: 0.003381  min_lr: 0.003381  loss: 3.8679 (3.7772)  weight_decay: 0.0500 (0.0500)  time: 0.5818  data: 0.0143  max mem: 31830
Epoch: [92]  [ 30/312]  eta: 0:04:12  lr: 0.003381  min_lr: 0.003381  loss: 4.0919 (3.8738)  weight_decay: 0.0500 (0.0500)  time: 0.4661  data: 0.0147  max mem: 31830
Epoch: [92]  [ 40/312]  eta: 0:03:30  lr: 0.003380  min_lr: 0.003380  loss: 3.9261 (3.7982)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0011  max mem: 31830
Epoch: [92]  [ 50/312]  eta: 0:03:05  lr: 0.003380  min_lr: 0.003380  loss: 3.8245 (3.8062)  weight_decay: 0.0500 (0.0500)  time: 0.4144  data: 0.0007  max mem: 31830
Epoch: [92]  [ 60/312]  eta: 0:02:45  lr: 0.003379  min_lr: 0.003379  loss: 3.8218 (3.7509)  weight_decay: 0.0500 (0.0500)  time: 0.4144  data: 0.0007  max mem: 31830
Epoch: [92]  [ 70/312]  eta: 0:02:36  lr: 0.003379  min_lr: 0.003379  loss: 3.6497 (3.7108)  weight_decay: 0.0500 (0.0500)  time: 0.4979  data: 0.0300  max mem: 31830
Epoch: [92]  [ 80/312]  eta: 0:02:26  lr: 0.003378  min_lr: 0.003378  loss: 3.5810 (3.7017)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0713  max mem: 31830
Epoch: [92]  [ 90/312]  eta: 0:02:15  lr: 0.003378  min_lr: 0.003378  loss: 3.8184 (3.7153)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0423  max mem: 31830
Epoch: [92]  [100/312]  eta: 0:02:08  lr: 0.003377  min_lr: 0.003377  loss: 3.9004 (3.7221)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0491  max mem: 31830
Epoch: [92]  [110/312]  eta: 0:01:59  lr: 0.003377  min_lr: 0.003377  loss: 3.8713 (3.7159)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0489  max mem: 31830
Epoch: [92]  [120/312]  eta: 0:01:54  lr: 0.003376  min_lr: 0.003376  loss: 3.8173 (3.7159)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0255  max mem: 31830
Epoch: [92]  [130/312]  eta: 0:01:48  lr: 0.003376  min_lr: 0.003376  loss: 3.8796 (3.7216)  weight_decay: 0.0500 (0.0500)  time: 0.5979  data: 0.0626  max mem: 31830
Epoch: [92]  [140/312]  eta: 0:01:40  lr: 0.003375  min_lr: 0.003375  loss: 3.7734 (3.7109)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0499  max mem: 31830
Epoch: [92]  [150/312]  eta: 0:01:34  lr: 0.003374  min_lr: 0.003374  loss: 3.7734 (3.7277)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0402  max mem: 31830
Epoch: [92]  [160/312]  eta: 0:01:28  lr: 0.003374  min_lr: 0.003374  loss: 4.1216 (3.7462)  weight_decay: 0.0500 (0.0500)  time: 0.5566  data: 0.0337  max mem: 31830
Epoch: [92]  [170/312]  eta: 0:01:21  lr: 0.003373  min_lr: 0.003373  loss: 4.1216 (3.7615)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.0203  max mem: 31830
Epoch: [92]  [180/312]  eta: 0:01:16  lr: 0.003373  min_lr: 0.003373  loss: 3.8479 (3.7566)  weight_decay: 0.0500 (0.0500)  time: 0.5539  data: 0.0671  max mem: 31830
Epoch: [92]  [190/312]  eta: 0:01:09  lr: 0.003372  min_lr: 0.003372  loss: 3.7189 (3.7417)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0530  max mem: 31830
Epoch: [92]  [200/312]  eta: 0:01:04  lr: 0.003372  min_lr: 0.003372  loss: 3.6244 (3.7394)  weight_decay: 0.0500 (0.0500)  time: 0.5379  data: 0.0886  max mem: 31830
Epoch: [92]  [210/312]  eta: 0:00:58  lr: 0.003371  min_lr: 0.003371  loss: 3.6326 (3.7362)  weight_decay: 0.0500 (0.0500)  time: 0.6482  data: 0.1237  max mem: 31830
Epoch: [92]  [220/312]  eta: 0:00:52  lr: 0.003371  min_lr: 0.003371  loss: 3.5814 (3.7261)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0702  max mem: 31830
Epoch: [92]  [230/312]  eta: 0:00:46  lr: 0.003370  min_lr: 0.003370  loss: 3.5814 (3.7287)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0819  max mem: 31830
Epoch: [92]  [240/312]  eta: 0:00:40  lr: 0.003370  min_lr: 0.003370  loss: 3.5454 (3.7211)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.0476  max mem: 31830
Epoch: [92]  [250/312]  eta: 0:00:35  lr: 0.003369  min_lr: 0.003369  loss: 3.5454 (3.7152)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0617  max mem: 31830
Epoch: [92]  [260/312]  eta: 0:00:29  lr: 0.003369  min_lr: 0.003369  loss: 3.8833 (3.7235)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.1250  max mem: 31830
Epoch: [92]  [270/312]  eta: 0:00:23  lr: 0.003368  min_lr: 0.003368  loss: 3.8675 (3.7200)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0644  max mem: 31830
Epoch: [92]  [280/312]  eta: 0:00:18  lr: 0.003368  min_lr: 0.003368  loss: 3.8437 (3.7287)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0610  max mem: 31830
Epoch: [92]  [290/312]  eta: 0:00:12  lr: 0.003367  min_lr: 0.003367  loss: 4.0363 (3.7274)  weight_decay: 0.0500 (0.0500)  time: 0.5983  data: 0.0605  max mem: 31830
Epoch: [92]  [300/312]  eta: 0:00:06  lr: 0.003367  min_lr: 0.003367  loss: 3.7589 (3.7273)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0316  max mem: 31830
Epoch: [92]  [310/312]  eta: 0:00:01  lr: 0.003366  min_lr: 0.003366  loss: 3.7589 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.4118  data: 0.0316  max mem: 31830
Epoch: [92]  [311/312]  eta: 0:00:00  lr: 0.003366  min_lr: 0.003366  loss: 3.7247 (3.7219)  weight_decay: 0.0500 (0.0500)  time: 0.4116  data: 0.0316  max mem: 31830
Epoch: [92] Total time: 0:02:54 (0.5586 s / it)
Averaged stats: lr: 0.003366  min_lr: 0.003366  loss: 3.7247 (3.7397)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.7084 (1.7084)  acc1: 74.8698 (74.8698)  acc5: 91.9271 (91.9271)  time: 8.6360  data: 8.4686  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9221 (1.8868)  acc1: 64.5833 (65.4080)  acc5: 85.8073 (86.4800)  time: 1.0762  data: 0.9410  max mem: 31830
Test: Total time: 0:00:09 (1.1104 s / it)
* Acc@1 65.142 Acc@5 86.852 loss 1.891
Accuracy of the model on the 50000 test images: 65.1%
Max accuracy: 66.64%
Epoch: [93]  [  0/312]  eta: 1:01:52  lr: 0.003366  min_lr: 0.003366  loss: 4.1879 (4.1879)  weight_decay: 0.0500 (0.0500)  time: 11.8975  data: 10.0846  max mem: 31830
Epoch: [93]  [ 10/312]  eta: 0:08:13  lr: 0.003365  min_lr: 0.003365  loss: 3.9275 (3.7958)  weight_decay: 0.0500 (0.0500)  time: 1.6328  data: 1.0403  max mem: 31830
Epoch: [93]  [ 20/312]  eta: 0:05:23  lr: 0.003365  min_lr: 0.003365  loss: 3.8020 (3.7768)  weight_decay: 0.0500 (0.0500)  time: 0.5701  data: 0.0960  max mem: 31830
Epoch: [93]  [ 30/312]  eta: 0:04:08  lr: 0.003364  min_lr: 0.003364  loss: 3.7680 (3.7607)  weight_decay: 0.0500 (0.0500)  time: 0.4667  data: 0.0284  max mem: 31830
Epoch: [93]  [ 40/312]  eta: 0:03:27  lr: 0.003364  min_lr: 0.003364  loss: 3.8404 (3.7599)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0008  max mem: 31830
Epoch: [93]  [ 50/312]  eta: 0:03:05  lr: 0.003363  min_lr: 0.003363  loss: 3.9293 (3.7891)  weight_decay: 0.0500 (0.0500)  time: 0.4404  data: 0.0017  max mem: 31830
Epoch: [93]  [ 60/312]  eta: 0:02:46  lr: 0.003363  min_lr: 0.003363  loss: 3.7129 (3.7439)  weight_decay: 0.0500 (0.0500)  time: 0.4457  data: 0.0101  max mem: 31830
Epoch: [93]  [ 70/312]  eta: 0:02:39  lr: 0.003362  min_lr: 0.003362  loss: 3.9585 (3.7781)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0664  max mem: 31830
Epoch: [93]  [ 80/312]  eta: 0:02:28  lr: 0.003362  min_lr: 0.003362  loss: 3.9963 (3.7671)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0891  max mem: 31830
Epoch: [93]  [ 90/312]  eta: 0:02:17  lr: 0.003361  min_lr: 0.003361  loss: 3.6174 (3.7493)  weight_decay: 0.0500 (0.0500)  time: 0.4942  data: 0.0504  max mem: 31830
Epoch: [93]  [100/312]  eta: 0:02:11  lr: 0.003361  min_lr: 0.003361  loss: 3.7040 (3.7515)  weight_decay: 0.0500 (0.0500)  time: 0.5504  data: 0.0858  max mem: 31830
Epoch: [93]  [110/312]  eta: 0:02:01  lr: 0.003360  min_lr: 0.003360  loss: 3.6957 (3.7356)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0673  max mem: 31830
Epoch: [93]  [120/312]  eta: 0:01:56  lr: 0.003360  min_lr: 0.003360  loss: 3.6957 (3.7271)  weight_decay: 0.0500 (0.0500)  time: 0.5165  data: 0.0668  max mem: 31830
Epoch: [93]  [130/312]  eta: 0:01:49  lr: 0.003359  min_lr: 0.003359  loss: 3.8150 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 0.5868  data: 0.0876  max mem: 31830
Epoch: [93]  [140/312]  eta: 0:01:41  lr: 0.003359  min_lr: 0.003359  loss: 3.9970 (3.7439)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0665  max mem: 31830
Epoch: [93]  [150/312]  eta: 0:01:36  lr: 0.003358  min_lr: 0.003358  loss: 3.7891 (3.7412)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.1109  max mem: 31830
Epoch: [93]  [160/312]  eta: 0:01:29  lr: 0.003358  min_lr: 0.003358  loss: 3.6764 (3.7351)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1173  max mem: 31830
Epoch: [93]  [170/312]  eta: 0:01:22  lr: 0.003357  min_lr: 0.003357  loss: 3.5890 (3.7357)  weight_decay: 0.0500 (0.0500)  time: 0.4584  data: 0.0521  max mem: 31830
Epoch: [93]  [180/312]  eta: 0:01:16  lr: 0.003356  min_lr: 0.003356  loss: 3.5854 (3.7212)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0940  max mem: 31830
Epoch: [93]  [190/312]  eta: 0:01:09  lr: 0.003356  min_lr: 0.003356  loss: 3.9106 (3.7283)  weight_decay: 0.0500 (0.0500)  time: 0.5112  data: 0.0939  max mem: 31830
Epoch: [93]  [200/312]  eta: 0:01:04  lr: 0.003355  min_lr: 0.003355  loss: 3.9158 (3.7205)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0812  max mem: 31830
Epoch: [93]  [210/312]  eta: 0:00:58  lr: 0.003355  min_lr: 0.003355  loss: 3.8653 (3.7183)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.1322  max mem: 31830
Epoch: [93]  [220/312]  eta: 0:00:52  lr: 0.003354  min_lr: 0.003354  loss: 3.8653 (3.7249)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0822  max mem: 31830
Epoch: [93]  [230/312]  eta: 0:00:46  lr: 0.003354  min_lr: 0.003354  loss: 3.8968 (3.7163)  weight_decay: 0.0500 (0.0500)  time: 0.5004  data: 0.0984  max mem: 31830
Epoch: [93]  [240/312]  eta: 0:00:40  lr: 0.003353  min_lr: 0.003353  loss: 3.8931 (3.7253)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.1288  max mem: 31830
Epoch: [93]  [250/312]  eta: 0:00:35  lr: 0.003353  min_lr: 0.003353  loss: 3.8202 (3.7138)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0780  max mem: 31830
Epoch: [93]  [260/312]  eta: 0:00:29  lr: 0.003352  min_lr: 0.003352  loss: 3.9315 (3.7310)  weight_decay: 0.0500 (0.0500)  time: 0.5626  data: 0.0915  max mem: 31830
Epoch: [93]  [270/312]  eta: 0:00:23  lr: 0.003352  min_lr: 0.003352  loss: 4.0662 (3.7439)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0751  max mem: 31830
Epoch: [93]  [280/312]  eta: 0:00:17  lr: 0.003351  min_lr: 0.003351  loss: 4.0256 (3.7507)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0757  max mem: 31830
Epoch: [93]  [290/312]  eta: 0:00:12  lr: 0.003351  min_lr: 0.003351  loss: 3.8613 (3.7486)  weight_decay: 0.0500 (0.0500)  time: 0.5901  data: 0.1470  max mem: 31830
Epoch: [93]  [300/312]  eta: 0:00:06  lr: 0.003350  min_lr: 0.003350  loss: 3.7810 (3.7517)  weight_decay: 0.0500 (0.0500)  time: 0.4883  data: 0.0717  max mem: 31830
Epoch: [93]  [310/312]  eta: 0:00:01  lr: 0.003350  min_lr: 0.003350  loss: 3.7982 (3.7517)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [93]  [311/312]  eta: 0:00:00  lr: 0.003350  min_lr: 0.003350  loss: 3.6643 (3.7513)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [93] Total time: 0:02:53 (0.5546 s / it)
Averaged stats: lr: 0.003350  min_lr: 0.003350  loss: 3.6643 (3.7522)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.7531 (1.7531)  acc1: 71.8750 (71.8750)  acc5: 90.2344 (90.2344)  time: 8.7149  data: 8.5479  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1535 (2.0276)  acc1: 60.9375 (63.7440)  acc5: 83.5938 (85.4720)  time: 1.0849  data: 0.9498  max mem: 31830
Test: Total time: 0:00:10 (1.1171 s / it)
* Acc@1 63.740 Acc@5 85.800 loss 2.031
Accuracy of the model on the 50000 test images: 63.7%
Max accuracy: 66.64%
Epoch: [94]  [  0/312]  eta: 1:03:08  lr: 0.003350  min_lr: 0.003350  loss: 4.2089 (4.2089)  weight_decay: 0.0500 (0.0500)  time: 12.1429  data: 9.6249  max mem: 31830
Epoch: [94]  [ 10/312]  eta: 0:08:32  lr: 0.003349  min_lr: 0.003349  loss: 4.0488 (4.0015)  weight_decay: 0.0500 (0.0500)  time: 1.6975  data: 0.9757  max mem: 31830
Epoch: [94]  [ 20/312]  eta: 0:05:43  lr: 0.003348  min_lr: 0.003348  loss: 4.0483 (3.9705)  weight_decay: 0.0500 (0.0500)  time: 0.6282  data: 0.0666  max mem: 31830
Epoch: [94]  [ 30/312]  eta: 0:04:20  lr: 0.003348  min_lr: 0.003348  loss: 3.9888 (3.8667)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.0116  max mem: 31830
Epoch: [94]  [ 40/312]  eta: 0:03:36  lr: 0.003347  min_lr: 0.003347  loss: 3.6207 (3.8297)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0008  max mem: 31830
Epoch: [94]  [ 50/312]  eta: 0:03:08  lr: 0.003347  min_lr: 0.003347  loss: 3.7486 (3.8200)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0008  max mem: 31830
Epoch: [94]  [ 60/312]  eta: 0:02:47  lr: 0.003346  min_lr: 0.003346  loss: 3.7486 (3.7713)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0007  max mem: 31830
Epoch: [94]  [ 70/312]  eta: 0:02:37  lr: 0.003346  min_lr: 0.003346  loss: 3.8795 (3.7988)  weight_decay: 0.0500 (0.0500)  time: 0.4773  data: 0.0007  max mem: 31830
Epoch: [94]  [ 80/312]  eta: 0:02:27  lr: 0.003345  min_lr: 0.003345  loss: 3.9986 (3.7741)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0012  max mem: 31830
Epoch: [94]  [ 90/312]  eta: 0:02:18  lr: 0.003345  min_lr: 0.003345  loss: 3.6139 (3.7741)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0013  max mem: 31830
Epoch: [94]  [100/312]  eta: 0:02:13  lr: 0.003344  min_lr: 0.003344  loss: 3.9011 (3.7699)  weight_decay: 0.0500 (0.0500)  time: 0.6010  data: 0.0009  max mem: 31830
Epoch: [94]  [110/312]  eta: 0:02:03  lr: 0.003344  min_lr: 0.003344  loss: 3.9660 (3.7690)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0008  max mem: 31830
Epoch: [94]  [120/312]  eta: 0:01:56  lr: 0.003343  min_lr: 0.003343  loss: 3.6233 (3.7392)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0015  max mem: 31830
Epoch: [94]  [130/312]  eta: 0:01:50  lr: 0.003343  min_lr: 0.003343  loss: 3.6233 (3.7398)  weight_decay: 0.0500 (0.0500)  time: 0.6051  data: 0.0017  max mem: 31830
Epoch: [94]  [140/312]  eta: 0:01:42  lr: 0.003342  min_lr: 0.003342  loss: 3.9184 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0054  max mem: 31830
Epoch: [94]  [150/312]  eta: 0:01:36  lr: 0.003342  min_lr: 0.003342  loss: 3.9493 (3.7551)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0055  max mem: 31830
Epoch: [94]  [160/312]  eta: 0:01:30  lr: 0.003341  min_lr: 0.003341  loss: 3.9371 (3.7496)  weight_decay: 0.0500 (0.0500)  time: 0.6070  data: 0.0009  max mem: 31830
Epoch: [94]  [170/312]  eta: 0:01:23  lr: 0.003340  min_lr: 0.003340  loss: 3.9529 (3.7678)  weight_decay: 0.0500 (0.0500)  time: 0.5415  data: 0.0007  max mem: 31830
Epoch: [94]  [180/312]  eta: 0:01:17  lr: 0.003340  min_lr: 0.003340  loss: 4.0185 (3.7763)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0007  max mem: 31830
Epoch: [94]  [190/312]  eta: 0:01:10  lr: 0.003339  min_lr: 0.003339  loss: 3.9697 (3.7676)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.0009  max mem: 31830
Epoch: [94]  [200/312]  eta: 0:01:05  lr: 0.003339  min_lr: 0.003339  loss: 3.5504 (3.7594)  weight_decay: 0.0500 (0.0500)  time: 0.5570  data: 0.0059  max mem: 31830
Epoch: [94]  [210/312]  eta: 0:00:59  lr: 0.003338  min_lr: 0.003338  loss: 3.6092 (3.7555)  weight_decay: 0.0500 (0.0500)  time: 0.6389  data: 0.0061  max mem: 31830
Epoch: [94]  [220/312]  eta: 0:00:53  lr: 0.003338  min_lr: 0.003338  loss: 3.6966 (3.7476)  weight_decay: 0.0500 (0.0500)  time: 0.4796  data: 0.0010  max mem: 31830
Epoch: [94]  [230/312]  eta: 0:00:47  lr: 0.003337  min_lr: 0.003337  loss: 3.6966 (3.7512)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0007  max mem: 31830
Epoch: [94]  [240/312]  eta: 0:00:41  lr: 0.003337  min_lr: 0.003337  loss: 3.7356 (3.7498)  weight_decay: 0.0500 (0.0500)  time: 0.6526  data: 0.0010  max mem: 31830
Epoch: [94]  [250/312]  eta: 0:00:35  lr: 0.003336  min_lr: 0.003336  loss: 3.8767 (3.7596)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0017  max mem: 31830
Epoch: [94]  [260/312]  eta: 0:00:30  lr: 0.003336  min_lr: 0.003336  loss: 3.9058 (3.7557)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0016  max mem: 31830
Epoch: [94]  [270/312]  eta: 0:00:23  lr: 0.003335  min_lr: 0.003335  loss: 3.7797 (3.7508)  weight_decay: 0.0500 (0.0500)  time: 0.4771  data: 0.0016  max mem: 31830
Epoch: [94]  [280/312]  eta: 0:00:18  lr: 0.003335  min_lr: 0.003335  loss: 3.6491 (3.7443)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0028  max mem: 31830
Epoch: [94]  [290/312]  eta: 0:00:12  lr: 0.003334  min_lr: 0.003334  loss: 3.4698 (3.7361)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0170  max mem: 31830
Epoch: [94]  [300/312]  eta: 0:00:06  lr: 0.003334  min_lr: 0.003334  loss: 3.3787 (3.7276)  weight_decay: 0.0500 (0.0500)  time: 0.4296  data: 0.0154  max mem: 31830
Epoch: [94]  [310/312]  eta: 0:00:01  lr: 0.003333  min_lr: 0.003333  loss: 3.7876 (3.7402)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [94]  [311/312]  eta: 0:00:00  lr: 0.003333  min_lr: 0.003333  loss: 3.9377 (3.7414)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [94] Total time: 0:02:55 (0.5621 s / it)
Averaged stats: lr: 0.003333  min_lr: 0.003333  loss: 3.9377 (3.7406)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5654 (1.5654)  acc1: 70.0521 (70.0521)  acc5: 88.6719 (88.6719)  time: 8.4254  data: 8.2586  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9120 (1.7957)  acc1: 61.1979 (63.3120)  acc5: 84.8958 (85.5680)  time: 1.0531  data: 0.9177  max mem: 31830
Test: Total time: 0:00:09 (1.0646 s / it)
* Acc@1 63.298 Acc@5 85.920 loss 1.784
Accuracy of the model on the 50000 test images: 63.3%
Max accuracy: 66.64%
Epoch: [95]  [  0/312]  eta: 0:59:49  lr: 0.003333  min_lr: 0.003333  loss: 3.7016 (3.7016)  weight_decay: 0.0500 (0.0500)  time: 11.5053  data: 11.1054  max mem: 31830
Epoch: [95]  [ 10/312]  eta: 0:08:27  lr: 0.003332  min_lr: 0.003332  loss: 3.7016 (3.7833)  weight_decay: 0.0500 (0.0500)  time: 1.6816  data: 1.0101  max mem: 31830
Epoch: [95]  [ 20/312]  eta: 0:05:28  lr: 0.003332  min_lr: 0.003332  loss: 3.6879 (3.6911)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.0273  max mem: 31830
Epoch: [95]  [ 30/312]  eta: 0:04:13  lr: 0.003331  min_lr: 0.003331  loss: 3.7933 (3.7430)  weight_decay: 0.0500 (0.0500)  time: 0.4672  data: 0.0274  max mem: 31830
Epoch: [95]  [ 40/312]  eta: 0:03:31  lr: 0.003331  min_lr: 0.003331  loss: 3.8466 (3.7735)  weight_decay: 0.0500 (0.0500)  time: 0.4121  data: 0.0008  max mem: 31830
Epoch: [95]  [ 50/312]  eta: 0:03:04  lr: 0.003330  min_lr: 0.003330  loss: 3.8527 (3.7941)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0016  max mem: 31830
Epoch: [95]  [ 60/312]  eta: 0:02:44  lr: 0.003330  min_lr: 0.003330  loss: 4.0449 (3.8089)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0014  max mem: 31830
Epoch: [95]  [ 70/312]  eta: 0:02:34  lr: 0.003329  min_lr: 0.003329  loss: 3.8669 (3.7933)  weight_decay: 0.0500 (0.0500)  time: 0.4678  data: 0.0700  max mem: 31830
Epoch: [95]  [ 80/312]  eta: 0:02:26  lr: 0.003329  min_lr: 0.003329  loss: 3.8785 (3.8016)  weight_decay: 0.0500 (0.0500)  time: 0.5702  data: 0.1534  max mem: 31830
Epoch: [95]  [ 90/312]  eta: 0:02:14  lr: 0.003328  min_lr: 0.003328  loss: 3.8785 (3.7864)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0841  max mem: 31830
Epoch: [95]  [100/312]  eta: 0:02:09  lr: 0.003327  min_lr: 0.003327  loss: 3.6892 (3.7700)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0976  max mem: 31830
Epoch: [95]  [110/312]  eta: 0:01:59  lr: 0.003327  min_lr: 0.003327  loss: 3.7270 (3.7673)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0975  max mem: 31830
Epoch: [95]  [120/312]  eta: 0:01:54  lr: 0.003326  min_lr: 0.003326  loss: 3.6663 (3.7597)  weight_decay: 0.0500 (0.0500)  time: 0.5033  data: 0.0646  max mem: 31830
Epoch: [95]  [130/312]  eta: 0:01:48  lr: 0.003326  min_lr: 0.003326  loss: 3.8713 (3.7630)  weight_decay: 0.0500 (0.0500)  time: 0.6000  data: 0.1324  max mem: 31830
Epoch: [95]  [140/312]  eta: 0:01:39  lr: 0.003325  min_lr: 0.003325  loss: 3.6604 (3.7312)  weight_decay: 0.0500 (0.0500)  time: 0.4932  data: 0.0685  max mem: 31830
Epoch: [95]  [150/312]  eta: 0:01:34  lr: 0.003325  min_lr: 0.003325  loss: 3.6047 (3.7387)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0783  max mem: 31830
Epoch: [95]  [160/312]  eta: 0:01:29  lr: 0.003324  min_lr: 0.003324  loss: 3.8862 (3.7470)  weight_decay: 0.0500 (0.0500)  time: 0.6428  data: 0.1514  max mem: 31830
Epoch: [95]  [170/312]  eta: 0:01:22  lr: 0.003324  min_lr: 0.003324  loss: 3.8949 (3.7578)  weight_decay: 0.0500 (0.0500)  time: 0.5507  data: 0.1006  max mem: 31830
Epoch: [95]  [180/312]  eta: 0:01:16  lr: 0.003323  min_lr: 0.003323  loss: 3.8949 (3.7507)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0741  max mem: 31830
Epoch: [95]  [190/312]  eta: 0:01:10  lr: 0.003323  min_lr: 0.003323  loss: 3.9914 (3.7566)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0820  max mem: 31830
Epoch: [95]  [200/312]  eta: 0:01:04  lr: 0.003322  min_lr: 0.003322  loss: 4.0627 (3.7619)  weight_decay: 0.0500 (0.0500)  time: 0.5600  data: 0.1205  max mem: 31830
Epoch: [95]  [210/312]  eta: 0:00:58  lr: 0.003322  min_lr: 0.003322  loss: 3.9108 (3.7632)  weight_decay: 0.0500 (0.0500)  time: 0.5937  data: 0.0860  max mem: 31830
Epoch: [95]  [220/312]  eta: 0:00:53  lr: 0.003321  min_lr: 0.003321  loss: 3.7704 (3.7598)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0851  max mem: 31830
Epoch: [95]  [230/312]  eta: 0:00:46  lr: 0.003320  min_lr: 0.003320  loss: 3.7274 (3.7563)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0850  max mem: 31830
Epoch: [95]  [240/312]  eta: 0:00:41  lr: 0.003320  min_lr: 0.003320  loss: 3.8032 (3.7584)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0826  max mem: 31830
Epoch: [95]  [250/312]  eta: 0:00:35  lr: 0.003319  min_lr: 0.003319  loss: 3.6899 (3.7468)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.1624  max mem: 31830
Epoch: [95]  [260/312]  eta: 0:00:29  lr: 0.003319  min_lr: 0.003319  loss: 3.5523 (3.7421)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0806  max mem: 31830
Epoch: [95]  [270/312]  eta: 0:00:23  lr: 0.003318  min_lr: 0.003318  loss: 3.7984 (3.7449)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0615  max mem: 31830
Epoch: [95]  [280/312]  eta: 0:00:18  lr: 0.003318  min_lr: 0.003318  loss: 3.9697 (3.7365)  weight_decay: 0.0500 (0.0500)  time: 0.5796  data: 0.1052  max mem: 31830
Epoch: [95]  [290/312]  eta: 0:00:12  lr: 0.003317  min_lr: 0.003317  loss: 3.6907 (3.7349)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0442  max mem: 31830
Epoch: [95]  [300/312]  eta: 0:00:06  lr: 0.003317  min_lr: 0.003317  loss: 3.8148 (3.7363)  weight_decay: 0.0500 (0.0500)  time: 0.4200  data: 0.0002  max mem: 31830
Epoch: [95]  [310/312]  eta: 0:00:01  lr: 0.003316  min_lr: 0.003316  loss: 3.9834 (3.7429)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [95]  [311/312]  eta: 0:00:00  lr: 0.003316  min_lr: 0.003316  loss: 3.9834 (3.7435)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [95] Total time: 0:02:54 (0.5582 s / it)
Averaged stats: lr: 0.003316  min_lr: 0.003316  loss: 3.9834 (3.7481)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.5942 (1.5942)  acc1: 71.8750 (71.8750)  acc5: 91.1458 (91.1458)  time: 8.6861  data: 8.5267  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9682 (1.8854)  acc1: 65.4948 (66.6880)  acc5: 87.1094 (87.6320)  time: 1.0874  data: 0.9475  max mem: 31830
Test: Total time: 0:00:10 (1.1208 s / it)
* Acc@1 66.602 Acc@5 87.960 loss 1.872
Accuracy of the model on the 50000 test images: 66.6%
Max accuracy: 66.64%
Epoch: [96]  [  0/312]  eta: 1:09:10  lr: 0.003316  min_lr: 0.003316  loss: 4.5090 (4.5090)  weight_decay: 0.0500 (0.0500)  time: 13.3013  data: 9.8086  max mem: 31830
Epoch: [96]  [ 10/312]  eta: 0:08:50  lr: 0.003316  min_lr: 0.003316  loss: 4.0261 (3.8131)  weight_decay: 0.0500 (0.0500)  time: 1.7558  data: 0.9822  max mem: 31830
Epoch: [96]  [ 20/312]  eta: 0:05:38  lr: 0.003315  min_lr: 0.003315  loss: 4.0261 (3.8996)  weight_decay: 0.0500 (0.0500)  time: 0.5508  data: 0.0746  max mem: 31830
Epoch: [96]  [ 30/312]  eta: 0:04:17  lr: 0.003314  min_lr: 0.003314  loss: 3.9759 (3.7746)  weight_decay: 0.0500 (0.0500)  time: 0.4499  data: 0.0253  max mem: 31830
Epoch: [96]  [ 40/312]  eta: 0:03:34  lr: 0.003314  min_lr: 0.003314  loss: 3.9759 (3.7888)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [96]  [ 50/312]  eta: 0:03:06  lr: 0.003313  min_lr: 0.003313  loss: 3.9920 (3.8010)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [96]  [ 60/312]  eta: 0:02:46  lr: 0.003313  min_lr: 0.003313  loss: 3.7407 (3.7914)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0008  max mem: 31830
Epoch: [96]  [ 70/312]  eta: 0:02:34  lr: 0.003312  min_lr: 0.003312  loss: 3.9083 (3.7865)  weight_decay: 0.0500 (0.0500)  time: 0.4499  data: 0.0008  max mem: 31830
Epoch: [96]  [ 80/312]  eta: 0:02:26  lr: 0.003312  min_lr: 0.003312  loss: 3.8284 (3.7687)  weight_decay: 0.0500 (0.0500)  time: 0.5358  data: 0.0014  max mem: 31830
Epoch: [96]  [ 90/312]  eta: 0:02:16  lr: 0.003311  min_lr: 0.003311  loss: 3.4169 (3.7438)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0269  max mem: 31830
Epoch: [96]  [100/312]  eta: 0:02:10  lr: 0.003311  min_lr: 0.003311  loss: 3.8777 (3.7517)  weight_decay: 0.0500 (0.0500)  time: 0.5513  data: 0.0264  max mem: 31830
Epoch: [96]  [110/312]  eta: 0:02:00  lr: 0.003310  min_lr: 0.003310  loss: 3.9601 (3.7696)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0008  max mem: 31830
Epoch: [96]  [120/312]  eta: 0:01:54  lr: 0.003310  min_lr: 0.003310  loss: 3.8881 (3.7598)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0009  max mem: 31830
Epoch: [96]  [130/312]  eta: 0:01:48  lr: 0.003309  min_lr: 0.003309  loss: 3.6074 (3.7444)  weight_decay: 0.0500 (0.0500)  time: 0.6039  data: 0.0012  max mem: 31830
Epoch: [96]  [140/312]  eta: 0:01:40  lr: 0.003308  min_lr: 0.003308  loss: 3.7883 (3.7401)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0059  max mem: 31830
Epoch: [96]  [150/312]  eta: 0:01:35  lr: 0.003308  min_lr: 0.003308  loss: 3.9891 (3.7652)  weight_decay: 0.0500 (0.0500)  time: 0.5441  data: 0.0203  max mem: 31830
Epoch: [96]  [160/312]  eta: 0:01:28  lr: 0.003307  min_lr: 0.003307  loss: 4.1162 (3.7728)  weight_decay: 0.0500 (0.0500)  time: 0.5885  data: 0.0154  max mem: 31830
Epoch: [96]  [170/312]  eta: 0:01:22  lr: 0.003307  min_lr: 0.003307  loss: 4.0019 (3.7770)  weight_decay: 0.0500 (0.0500)  time: 0.5029  data: 0.0124  max mem: 31830
Epoch: [96]  [180/312]  eta: 0:01:16  lr: 0.003306  min_lr: 0.003306  loss: 4.0045 (3.7866)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0125  max mem: 31830
Epoch: [96]  [190/312]  eta: 0:01:09  lr: 0.003306  min_lr: 0.003306  loss: 3.8964 (3.7830)  weight_decay: 0.0500 (0.0500)  time: 0.4847  data: 0.0009  max mem: 31830
Epoch: [96]  [200/312]  eta: 0:01:04  lr: 0.003305  min_lr: 0.003305  loss: 3.8964 (3.7847)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0145  max mem: 31830
Epoch: [96]  [210/312]  eta: 0:00:58  lr: 0.003305  min_lr: 0.003305  loss: 3.9154 (3.7812)  weight_decay: 0.0500 (0.0500)  time: 0.6049  data: 0.0147  max mem: 31830
Epoch: [96]  [220/312]  eta: 0:00:52  lr: 0.003304  min_lr: 0.003304  loss: 3.9372 (3.7804)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0010  max mem: 31830
Epoch: [96]  [230/312]  eta: 0:00:46  lr: 0.003304  min_lr: 0.003304  loss: 3.8326 (3.7748)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0065  max mem: 31830
Epoch: [96]  [240/312]  eta: 0:00:40  lr: 0.003303  min_lr: 0.003303  loss: 3.7467 (3.7819)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0066  max mem: 31830
Epoch: [96]  [250/312]  eta: 0:00:34  lr: 0.003302  min_lr: 0.003302  loss: 3.7179 (3.7798)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.0015  max mem: 31830
Epoch: [96]  [260/312]  eta: 0:00:29  lr: 0.003302  min_lr: 0.003302  loss: 3.7098 (3.7870)  weight_decay: 0.0500 (0.0500)  time: 0.5821  data: 0.0144  max mem: 31830
Epoch: [96]  [270/312]  eta: 0:00:23  lr: 0.003301  min_lr: 0.003301  loss: 3.6581 (3.7742)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0141  max mem: 31830
Epoch: [96]  [280/312]  eta: 0:00:18  lr: 0.003301  min_lr: 0.003301  loss: 3.4201 (3.7654)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0084  max mem: 31830
Epoch: [96]  [290/312]  eta: 0:00:12  lr: 0.003300  min_lr: 0.003300  loss: 3.6169 (3.7639)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.0079  max mem: 31830
Epoch: [96]  [300/312]  eta: 0:00:06  lr: 0.003300  min_lr: 0.003300  loss: 3.8795 (3.7725)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0003  max mem: 31830
Epoch: [96]  [310/312]  eta: 0:00:01  lr: 0.003299  min_lr: 0.003299  loss: 4.0221 (3.7771)  weight_decay: 0.0500 (0.0500)  time: 0.3924  data: 0.0001  max mem: 31830
Epoch: [96]  [311/312]  eta: 0:00:00  lr: 0.003299  min_lr: 0.003299  loss: 4.0221 (3.7773)  weight_decay: 0.0500 (0.0500)  time: 0.3924  data: 0.0001  max mem: 31830
Epoch: [96] Total time: 0:02:53 (0.5554 s / it)
Averaged stats: lr: 0.003299  min_lr: 0.003299  loss: 4.0221 (3.7692)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.5765 (1.5765)  acc1: 70.9635 (70.9635)  acc5: 88.8021 (88.8021)  time: 8.2757  data: 8.1088  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9459 (1.7943)  acc1: 63.2812 (64.4320)  acc5: 83.7240 (85.9200)  time: 1.0369  data: 0.9011  max mem: 31830
Test: Total time: 0:00:09 (1.0489 s / it)
* Acc@1 64.526 Acc@5 86.614 loss 1.780
Accuracy of the model on the 50000 test images: 64.5%
Max accuracy: 66.64%
Epoch: [97]  [  0/312]  eta: 1:02:55  lr: 0.003299  min_lr: 0.003299  loss: 3.6806 (3.6806)  weight_decay: 0.0500 (0.0500)  time: 12.1024  data: 11.5859  max mem: 31830
Epoch: [97]  [ 10/312]  eta: 0:08:07  lr: 0.003299  min_lr: 0.003299  loss: 3.7228 (3.6687)  weight_decay: 0.0500 (0.0500)  time: 1.6133  data: 1.0538  max mem: 31830
Epoch: [97]  [ 20/312]  eta: 0:05:20  lr: 0.003298  min_lr: 0.003298  loss: 3.7228 (3.6349)  weight_decay: 0.0500 (0.0500)  time: 0.5478  data: 0.0485  max mem: 31830
Epoch: [97]  [ 30/312]  eta: 0:04:05  lr: 0.003297  min_lr: 0.003297  loss: 3.6783 (3.6259)  weight_decay: 0.0500 (0.0500)  time: 0.4631  data: 0.0505  max mem: 31830
Epoch: [97]  [ 40/312]  eta: 0:03:25  lr: 0.003297  min_lr: 0.003297  loss: 3.8333 (3.6951)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0026  max mem: 31830
Epoch: [97]  [ 50/312]  eta: 0:03:09  lr: 0.003296  min_lr: 0.003296  loss: 3.9396 (3.7087)  weight_decay: 0.0500 (0.0500)  time: 0.4939  data: 0.0118  max mem: 31830
Epoch: [97]  [ 60/312]  eta: 0:02:49  lr: 0.003296  min_lr: 0.003296  loss: 3.8535 (3.7354)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0245  max mem: 31830
Epoch: [97]  [ 70/312]  eta: 0:02:40  lr: 0.003295  min_lr: 0.003295  loss: 3.8535 (3.7319)  weight_decay: 0.0500 (0.0500)  time: 0.5052  data: 0.0385  max mem: 31830
Epoch: [97]  [ 80/312]  eta: 0:02:32  lr: 0.003295  min_lr: 0.003295  loss: 3.8156 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0258  max mem: 31830
Epoch: [97]  [ 90/312]  eta: 0:02:21  lr: 0.003294  min_lr: 0.003294  loss: 3.7925 (3.7293)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0467  max mem: 31830
Epoch: [97]  [100/312]  eta: 0:02:13  lr: 0.003294  min_lr: 0.003294  loss: 3.7233 (3.7530)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0586  max mem: 31830
Epoch: [97]  [110/312]  eta: 0:02:02  lr: 0.003293  min_lr: 0.003293  loss: 3.7233 (3.7438)  weight_decay: 0.0500 (0.0500)  time: 0.4761  data: 0.0128  max mem: 31830
Epoch: [97]  [120/312]  eta: 0:01:56  lr: 0.003292  min_lr: 0.003292  loss: 3.7092 (3.7401)  weight_decay: 0.0500 (0.0500)  time: 0.4914  data: 0.0129  max mem: 31830
Epoch: [97]  [130/312]  eta: 0:01:50  lr: 0.003292  min_lr: 0.003292  loss: 3.8626 (3.7431)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0195  max mem: 31830
Epoch: [97]  [140/312]  eta: 0:01:41  lr: 0.003291  min_lr: 0.003291  loss: 3.8920 (3.7299)  weight_decay: 0.0500 (0.0500)  time: 0.4955  data: 0.0075  max mem: 31830
Epoch: [97]  [150/312]  eta: 0:01:35  lr: 0.003291  min_lr: 0.003291  loss: 3.3540 (3.7133)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0009  max mem: 31830
Epoch: [97]  [160/312]  eta: 0:01:30  lr: 0.003290  min_lr: 0.003290  loss: 3.7363 (3.7269)  weight_decay: 0.0500 (0.0500)  time: 0.6140  data: 0.0009  max mem: 31830
Epoch: [97]  [170/312]  eta: 0:01:23  lr: 0.003290  min_lr: 0.003290  loss: 3.9801 (3.7327)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0332  max mem: 31830
Epoch: [97]  [180/312]  eta: 0:01:17  lr: 0.003289  min_lr: 0.003289  loss: 4.0141 (3.7414)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0390  max mem: 31830
Epoch: [97]  [190/312]  eta: 0:01:10  lr: 0.003289  min_lr: 0.003289  loss: 3.9416 (3.7297)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0066  max mem: 31830
Epoch: [97]  [200/312]  eta: 0:01:04  lr: 0.003288  min_lr: 0.003288  loss: 3.9416 (3.7316)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0011  max mem: 31830
Epoch: [97]  [210/312]  eta: 0:00:59  lr: 0.003288  min_lr: 0.003288  loss: 3.8501 (3.7326)  weight_decay: 0.0500 (0.0500)  time: 0.6141  data: 0.0017  max mem: 31830
Epoch: [97]  [220/312]  eta: 0:00:52  lr: 0.003287  min_lr: 0.003287  loss: 3.8501 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0016  max mem: 31830
Epoch: [97]  [230/312]  eta: 0:00:47  lr: 0.003286  min_lr: 0.003286  loss: 3.8944 (3.7429)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0012  max mem: 31830
Epoch: [97]  [240/312]  eta: 0:00:41  lr: 0.003286  min_lr: 0.003286  loss: 3.7439 (3.7407)  weight_decay: 0.0500 (0.0500)  time: 0.6199  data: 0.0011  max mem: 31830
Epoch: [97]  [250/312]  eta: 0:00:35  lr: 0.003285  min_lr: 0.003285  loss: 3.4719 (3.7296)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0014  max mem: 31830
Epoch: [97]  [260/312]  eta: 0:00:29  lr: 0.003285  min_lr: 0.003285  loss: 3.3310 (3.7191)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0011  max mem: 31830
Epoch: [97]  [270/312]  eta: 0:00:23  lr: 0.003284  min_lr: 0.003284  loss: 3.3310 (3.7093)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0008  max mem: 31830
Epoch: [97]  [280/312]  eta: 0:00:18  lr: 0.003284  min_lr: 0.003284  loss: 3.4062 (3.7117)  weight_decay: 0.0500 (0.0500)  time: 0.5541  data: 0.0019  max mem: 31830
Epoch: [97]  [290/312]  eta: 0:00:12  lr: 0.003283  min_lr: 0.003283  loss: 3.8181 (3.7145)  weight_decay: 0.0500 (0.0500)  time: 0.6321  data: 0.0016  max mem: 31830
Epoch: [97]  [300/312]  eta: 0:00:06  lr: 0.003283  min_lr: 0.003283  loss: 3.8016 (3.7071)  weight_decay: 0.0500 (0.0500)  time: 0.4656  data: 0.0002  max mem: 31830
Epoch: [97]  [310/312]  eta: 0:00:01  lr: 0.003282  min_lr: 0.003282  loss: 3.4348 (3.6995)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [97]  [311/312]  eta: 0:00:00  lr: 0.003282  min_lr: 0.003282  loss: 3.4348 (3.7008)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [97] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.003282  min_lr: 0.003282  loss: 3.4348 (3.7370)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2700 (1.2700)  acc1: 75.6510 (75.6510)  acc5: 92.5781 (92.5781)  time: 8.8532  data: 8.6858  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7846 (1.6490)  acc1: 67.1875 (67.6800)  acc5: 86.9792 (87.8560)  time: 1.1012  data: 0.9652  max mem: 31830
Test: Total time: 0:00:10 (1.1315 s / it)
* Acc@1 67.082 Acc@5 88.068 loss 1.641
Accuracy of the model on the 50000 test images: 67.1%
Max accuracy: 67.08%
Epoch: [98]  [  0/312]  eta: 1:03:25  lr: 0.003282  min_lr: 0.003282  loss: 3.8439 (3.8439)  weight_decay: 0.0500 (0.0500)  time: 12.1960  data: 8.7922  max mem: 31830
Epoch: [98]  [ 10/312]  eta: 0:08:20  lr: 0.003281  min_lr: 0.003281  loss: 3.8439 (3.7242)  weight_decay: 0.0500 (0.0500)  time: 1.6575  data: 0.9965  max mem: 31830
Epoch: [98]  [ 20/312]  eta: 0:05:21  lr: 0.003281  min_lr: 0.003281  loss: 3.8705 (3.7516)  weight_decay: 0.0500 (0.0500)  time: 0.5462  data: 0.1218  max mem: 31830
Epoch: [98]  [ 30/312]  eta: 0:04:06  lr: 0.003280  min_lr: 0.003280  loss: 3.9119 (3.7450)  weight_decay: 0.0500 (0.0500)  time: 0.4433  data: 0.0137  max mem: 31830
Epoch: [98]  [ 40/312]  eta: 0:03:25  lr: 0.003280  min_lr: 0.003280  loss: 3.9119 (3.7452)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0015  max mem: 31830
Epoch: [98]  [ 50/312]  eta: 0:03:01  lr: 0.003279  min_lr: 0.003279  loss: 3.8642 (3.7711)  weight_decay: 0.0500 (0.0500)  time: 0.4143  data: 0.0016  max mem: 31830
Epoch: [98]  [ 60/312]  eta: 0:02:42  lr: 0.003279  min_lr: 0.003279  loss: 3.7791 (3.7422)  weight_decay: 0.0500 (0.0500)  time: 0.4150  data: 0.0008  max mem: 31830
Epoch: [98]  [ 70/312]  eta: 0:02:35  lr: 0.003278  min_lr: 0.003278  loss: 3.7203 (3.7292)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0575  max mem: 31830
Epoch: [98]  [ 80/312]  eta: 0:02:25  lr: 0.003278  min_lr: 0.003278  loss: 3.9715 (3.7774)  weight_decay: 0.0500 (0.0500)  time: 0.5812  data: 0.0575  max mem: 31830
Epoch: [98]  [ 90/312]  eta: 0:02:16  lr: 0.003277  min_lr: 0.003277  loss: 4.0058 (3.7848)  weight_decay: 0.0500 (0.0500)  time: 0.5080  data: 0.0507  max mem: 31830
Epoch: [98]  [100/312]  eta: 0:02:11  lr: 0.003276  min_lr: 0.003276  loss: 3.8750 (3.7608)  weight_decay: 0.0500 (0.0500)  time: 0.5810  data: 0.1156  max mem: 31830
Epoch: [98]  [110/312]  eta: 0:02:01  lr: 0.003276  min_lr: 0.003276  loss: 3.3001 (3.7171)  weight_decay: 0.0500 (0.0500)  time: 0.5339  data: 0.0664  max mem: 31830
Epoch: [98]  [120/312]  eta: 0:01:54  lr: 0.003275  min_lr: 0.003275  loss: 3.3801 (3.7210)  weight_decay: 0.0500 (0.0500)  time: 0.4735  data: 0.0256  max mem: 31830
Epoch: [98]  [130/312]  eta: 0:01:47  lr: 0.003275  min_lr: 0.003275  loss: 3.8326 (3.7146)  weight_decay: 0.0500 (0.0500)  time: 0.5544  data: 0.0387  max mem: 31830
Epoch: [98]  [140/312]  eta: 0:01:39  lr: 0.003274  min_lr: 0.003274  loss: 3.8326 (3.7233)  weight_decay: 0.0500 (0.0500)  time: 0.4883  data: 0.0281  max mem: 31830
Epoch: [98]  [150/312]  eta: 0:01:36  lr: 0.003274  min_lr: 0.003274  loss: 3.8545 (3.7299)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0430  max mem: 31830
Epoch: [98]  [160/312]  eta: 0:01:28  lr: 0.003273  min_lr: 0.003273  loss: 3.6969 (3.7253)  weight_decay: 0.0500 (0.0500)  time: 0.6211  data: 0.0299  max mem: 31830
Epoch: [98]  [170/312]  eta: 0:01:21  lr: 0.003273  min_lr: 0.003273  loss: 3.9231 (3.7267)  weight_decay: 0.0500 (0.0500)  time: 0.4517  data: 0.0140  max mem: 31830
Epoch: [98]  [180/312]  eta: 0:01:16  lr: 0.003272  min_lr: 0.003272  loss: 3.9307 (3.7350)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0309  max mem: 31830
Epoch: [98]  [190/312]  eta: 0:01:09  lr: 0.003271  min_lr: 0.003271  loss: 3.9128 (3.7410)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0182  max mem: 31830
Epoch: [98]  [200/312]  eta: 0:01:03  lr: 0.003271  min_lr: 0.003271  loss: 3.9867 (3.7494)  weight_decay: 0.0500 (0.0500)  time: 0.4960  data: 0.0413  max mem: 31830
Epoch: [98]  [210/312]  eta: 0:00:58  lr: 0.003270  min_lr: 0.003270  loss: 3.9019 (3.7475)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.0830  max mem: 31830
Epoch: [98]  [220/312]  eta: 0:00:51  lr: 0.003270  min_lr: 0.003270  loss: 3.8989 (3.7556)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0426  max mem: 31830
Epoch: [98]  [230/312]  eta: 0:00:46  lr: 0.003269  min_lr: 0.003269  loss: 3.8958 (3.7610)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0669  max mem: 31830
Epoch: [98]  [240/312]  eta: 0:00:41  lr: 0.003269  min_lr: 0.003269  loss: 4.0861 (3.7795)  weight_decay: 0.0500 (0.0500)  time: 0.6399  data: 0.1453  max mem: 31830
Epoch: [98]  [250/312]  eta: 0:00:34  lr: 0.003268  min_lr: 0.003268  loss: 4.0477 (3.7868)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0798  max mem: 31830
Epoch: [98]  [260/312]  eta: 0:00:29  lr: 0.003268  min_lr: 0.003268  loss: 3.9647 (3.7832)  weight_decay: 0.0500 (0.0500)  time: 0.5335  data: 0.0998  max mem: 31830
Epoch: [98]  [270/312]  eta: 0:00:23  lr: 0.003267  min_lr: 0.003267  loss: 3.8268 (3.7841)  weight_decay: 0.0500 (0.0500)  time: 0.5477  data: 0.0993  max mem: 31830
Epoch: [98]  [280/312]  eta: 0:00:18  lr: 0.003266  min_lr: 0.003266  loss: 3.8268 (3.7852)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0855  max mem: 31830
Epoch: [98]  [290/312]  eta: 0:00:12  lr: 0.003266  min_lr: 0.003266  loss: 4.0558 (3.7969)  weight_decay: 0.0500 (0.0500)  time: 0.6037  data: 0.1525  max mem: 31830
Epoch: [98]  [300/312]  eta: 0:00:06  lr: 0.003265  min_lr: 0.003265  loss: 4.0010 (3.8003)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0675  max mem: 31830
Epoch: [98]  [310/312]  eta: 0:00:01  lr: 0.003265  min_lr: 0.003265  loss: 3.9258 (3.7960)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [98]  [311/312]  eta: 0:00:00  lr: 0.003265  min_lr: 0.003265  loss: 3.9878 (3.7972)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [98] Total time: 0:02:53 (0.5566 s / it)
Averaged stats: lr: 0.003265  min_lr: 0.003265  loss: 3.9878 (3.7483)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.4183 (1.4183)  acc1: 75.0000 (75.0000)  acc5: 92.1875 (92.1875)  time: 8.8926  data: 8.7254  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8974 (1.7654)  acc1: 64.8438 (65.9840)  acc5: 86.1979 (87.3760)  time: 1.1052  data: 0.9695  max mem: 31830
Test: Total time: 0:00:10 (1.1353 s / it)
* Acc@1 66.136 Acc@5 87.594 loss 1.747
Accuracy of the model on the 50000 test images: 66.1%
Max accuracy: 67.08%
Epoch: [99]  [  0/312]  eta: 0:59:54  lr: 0.003265  min_lr: 0.003265  loss: 3.8493 (3.8493)  weight_decay: 0.0500 (0.0500)  time: 11.5207  data: 9.8298  max mem: 31830
Epoch: [99]  [ 10/312]  eta: 0:07:54  lr: 0.003264  min_lr: 0.003264  loss: 3.6840 (3.5479)  weight_decay: 0.0500 (0.0500)  time: 1.5712  data: 1.0167  max mem: 31830
Epoch: [99]  [ 20/312]  eta: 0:05:14  lr: 0.003264  min_lr: 0.003264  loss: 3.7747 (3.6501)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.1419  max mem: 31830
Epoch: [99]  [ 30/312]  eta: 0:04:02  lr: 0.003263  min_lr: 0.003263  loss: 3.8725 (3.7174)  weight_decay: 0.0500 (0.0500)  time: 0.4664  data: 0.0746  max mem: 31830
Epoch: [99]  [ 40/312]  eta: 0:03:29  lr: 0.003262  min_lr: 0.003262  loss: 3.6895 (3.7159)  weight_decay: 0.0500 (0.0500)  time: 0.4442  data: 0.0016  max mem: 31830
Epoch: [99]  [ 50/312]  eta: 0:03:09  lr: 0.003262  min_lr: 0.003262  loss: 3.9331 (3.7290)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0418  max mem: 31830
Epoch: [99]  [ 60/312]  eta: 0:02:48  lr: 0.003261  min_lr: 0.003261  loss: 3.9331 (3.7137)  weight_decay: 0.0500 (0.0500)  time: 0.4672  data: 0.0411  max mem: 31830
Epoch: [99]  [ 70/312]  eta: 0:02:38  lr: 0.003261  min_lr: 0.003261  loss: 3.7339 (3.6810)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0761  max mem: 31830
Epoch: [99]  [ 80/312]  eta: 0:02:29  lr: 0.003260  min_lr: 0.003260  loss: 3.6308 (3.6762)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.1397  max mem: 31830
Epoch: [99]  [ 90/312]  eta: 0:02:17  lr: 0.003260  min_lr: 0.003260  loss: 3.6962 (3.6873)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0645  max mem: 31830
Epoch: [99]  [100/312]  eta: 0:02:12  lr: 0.003259  min_lr: 0.003259  loss: 3.6962 (3.6791)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0893  max mem: 31830
Epoch: [99]  [110/312]  eta: 0:02:02  lr: 0.003258  min_lr: 0.003258  loss: 3.6898 (3.6764)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0894  max mem: 31830
Epoch: [99]  [120/312]  eta: 0:01:57  lr: 0.003258  min_lr: 0.003258  loss: 3.5977 (3.6658)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0499  max mem: 31830
Epoch: [99]  [130/312]  eta: 0:01:49  lr: 0.003257  min_lr: 0.003257  loss: 3.8042 (3.6799)  weight_decay: 0.0500 (0.0500)  time: 0.5966  data: 0.0499  max mem: 31830
Epoch: [99]  [140/312]  eta: 0:01:41  lr: 0.003257  min_lr: 0.003257  loss: 3.8370 (3.6805)  weight_decay: 0.0500 (0.0500)  time: 0.4691  data: 0.0331  max mem: 31830
Epoch: [99]  [150/312]  eta: 0:01:37  lr: 0.003256  min_lr: 0.003256  loss: 3.7795 (3.6895)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0943  max mem: 31830
Epoch: [99]  [160/312]  eta: 0:01:30  lr: 0.003256  min_lr: 0.003256  loss: 3.9381 (3.7189)  weight_decay: 0.0500 (0.0500)  time: 0.6056  data: 0.0619  max mem: 31830
Epoch: [99]  [170/312]  eta: 0:01:23  lr: 0.003255  min_lr: 0.003255  loss: 4.0530 (3.7266)  weight_decay: 0.0500 (0.0500)  time: 0.4969  data: 0.0309  max mem: 31830
Epoch: [99]  [180/312]  eta: 0:01:17  lr: 0.003255  min_lr: 0.003255  loss: 4.0080 (3.7360)  weight_decay: 0.0500 (0.0500)  time: 0.5613  data: 0.0807  max mem: 31830
Epoch: [99]  [190/312]  eta: 0:01:10  lr: 0.003254  min_lr: 0.003254  loss: 3.9223 (3.7358)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0505  max mem: 31830
Epoch: [99]  [200/312]  eta: 0:01:04  lr: 0.003253  min_lr: 0.003253  loss: 3.9306 (3.7482)  weight_decay: 0.0500 (0.0500)  time: 0.4748  data: 0.0442  max mem: 31830
Epoch: [99]  [210/312]  eta: 0:00:59  lr: 0.003253  min_lr: 0.003253  loss: 3.9306 (3.7570)  weight_decay: 0.0500 (0.0500)  time: 0.6055  data: 0.1031  max mem: 31830
Epoch: [99]  [220/312]  eta: 0:00:52  lr: 0.003252  min_lr: 0.003252  loss: 3.9902 (3.7680)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0597  max mem: 31830
Epoch: [99]  [230/312]  eta: 0:00:47  lr: 0.003252  min_lr: 0.003252  loss: 3.9644 (3.7682)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0492  max mem: 31830
Epoch: [99]  [240/312]  eta: 0:00:41  lr: 0.003251  min_lr: 0.003251  loss: 3.9644 (3.7780)  weight_decay: 0.0500 (0.0500)  time: 0.5264  data: 0.0491  max mem: 31830
Epoch: [99]  [250/312]  eta: 0:00:35  lr: 0.003251  min_lr: 0.003251  loss: 4.0655 (3.7858)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0622  max mem: 31830
Epoch: [99]  [260/312]  eta: 0:00:29  lr: 0.003250  min_lr: 0.003250  loss: 3.9498 (3.7850)  weight_decay: 0.0500 (0.0500)  time: 0.6129  data: 0.1182  max mem: 31830
Epoch: [99]  [270/312]  eta: 0:00:23  lr: 0.003250  min_lr: 0.003250  loss: 3.9212 (3.7875)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0566  max mem: 31830
Epoch: [99]  [280/312]  eta: 0:00:18  lr: 0.003249  min_lr: 0.003249  loss: 3.7366 (3.7779)  weight_decay: 0.0500 (0.0500)  time: 0.5352  data: 0.0371  max mem: 31830
Epoch: [99]  [290/312]  eta: 0:00:12  lr: 0.003248  min_lr: 0.003248  loss: 3.6455 (3.7742)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0541  max mem: 31830
Epoch: [99]  [300/312]  eta: 0:00:06  lr: 0.003248  min_lr: 0.003248  loss: 3.6671 (3.7696)  weight_decay: 0.0500 (0.0500)  time: 0.4150  data: 0.0174  max mem: 31830
Epoch: [99]  [310/312]  eta: 0:00:01  lr: 0.003247  min_lr: 0.003247  loss: 3.5459 (3.7648)  weight_decay: 0.0500 (0.0500)  time: 0.3912  data: 0.0001  max mem: 31830
Epoch: [99]  [311/312]  eta: 0:00:00  lr: 0.003247  min_lr: 0.003247  loss: 3.5459 (3.7657)  weight_decay: 0.0500 (0.0500)  time: 0.3911  data: 0.0001  max mem: 31830
Epoch: [99] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.003247  min_lr: 0.003247  loss: 3.5459 (3.7370)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.4118 (1.4118)  acc1: 73.4375 (73.4375)  acc5: 91.7969 (91.7969)  time: 8.9253  data: 8.7655  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7446 (1.6109)  acc1: 66.0156 (66.8320)  acc5: 86.8490 (87.8560)  time: 1.1138  data: 0.9740  max mem: 31830
Test: Total time: 0:00:10 (1.1476 s / it)
* Acc@1 66.530 Acc@5 87.714 loss 1.610
Accuracy of the model on the 50000 test images: 66.5%
Max accuracy: 67.08%
Epoch: [100]  [  0/312]  eta: 1:02:40  lr: 0.003247  min_lr: 0.003247  loss: 2.9186 (2.9186)  weight_decay: 0.0500 (0.0500)  time: 12.0522  data: 8.3823  max mem: 31830
Epoch: [100]  [ 10/312]  eta: 0:08:45  lr: 0.003247  min_lr: 0.003247  loss: 3.7988 (3.4638)  weight_decay: 0.0500 (0.0500)  time: 1.7391  data: 0.9689  max mem: 31830
Epoch: [100]  [ 20/312]  eta: 0:05:29  lr: 0.003246  min_lr: 0.003246  loss: 3.7988 (3.5746)  weight_decay: 0.0500 (0.0500)  time: 0.5823  data: 0.1475  max mem: 31830
Epoch: [100]  [ 30/312]  eta: 0:04:11  lr: 0.003245  min_lr: 0.003245  loss: 3.8100 (3.6385)  weight_decay: 0.0500 (0.0500)  time: 0.4263  data: 0.0340  max mem: 31830
Epoch: [100]  [ 40/312]  eta: 0:03:29  lr: 0.003245  min_lr: 0.003245  loss: 3.8266 (3.6845)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0007  max mem: 31830
Epoch: [100]  [ 50/312]  eta: 0:03:02  lr: 0.003244  min_lr: 0.003244  loss: 4.0186 (3.7101)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0007  max mem: 31830
Epoch: [100]  [ 60/312]  eta: 0:02:43  lr: 0.003244  min_lr: 0.003244  loss: 4.0186 (3.7108)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0008  max mem: 31830
Epoch: [100]  [ 70/312]  eta: 0:02:32  lr: 0.003243  min_lr: 0.003243  loss: 3.9782 (3.7123)  weight_decay: 0.0500 (0.0500)  time: 0.4554  data: 0.0259  max mem: 31830
Epoch: [100]  [ 80/312]  eta: 0:02:23  lr: 0.003243  min_lr: 0.003243  loss: 3.9582 (3.7374)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0259  max mem: 31830
Epoch: [100]  [ 90/312]  eta: 0:02:15  lr: 0.003242  min_lr: 0.003242  loss: 3.8010 (3.7276)  weight_decay: 0.0500 (0.0500)  time: 0.5391  data: 0.0638  max mem: 31830
Epoch: [100]  [100/312]  eta: 0:02:09  lr: 0.003242  min_lr: 0.003242  loss: 3.4025 (3.6901)  weight_decay: 0.0500 (0.0500)  time: 0.5699  data: 0.1056  max mem: 31830
Epoch: [100]  [110/312]  eta: 0:02:00  lr: 0.003241  min_lr: 0.003241  loss: 3.7092 (3.6965)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0424  max mem: 31830
Epoch: [100]  [120/312]  eta: 0:01:54  lr: 0.003240  min_lr: 0.003240  loss: 3.7092 (3.6708)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0177  max mem: 31830
Epoch: [100]  [130/312]  eta: 0:01:47  lr: 0.003240  min_lr: 0.003240  loss: 3.7666 (3.6884)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0317  max mem: 31830
Epoch: [100]  [140/312]  eta: 0:01:40  lr: 0.003239  min_lr: 0.003239  loss: 4.0731 (3.7190)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0150  max mem: 31830
Epoch: [100]  [150/312]  eta: 0:01:35  lr: 0.003239  min_lr: 0.003239  loss: 3.8021 (3.7052)  weight_decay: 0.0500 (0.0500)  time: 0.6045  data: 0.0137  max mem: 31830
Epoch: [100]  [160/312]  eta: 0:01:28  lr: 0.003238  min_lr: 0.003238  loss: 3.7356 (3.7128)  weight_decay: 0.0500 (0.0500)  time: 0.5494  data: 0.0135  max mem: 31830
Epoch: [100]  [170/312]  eta: 0:01:22  lr: 0.003238  min_lr: 0.003238  loss: 3.8967 (3.7152)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0108  max mem: 31830
Epoch: [100]  [180/312]  eta: 0:01:17  lr: 0.003237  min_lr: 0.003237  loss: 3.7684 (3.7105)  weight_decay: 0.0500 (0.0500)  time: 0.6133  data: 0.0107  max mem: 31830
Epoch: [100]  [190/312]  eta: 0:01:10  lr: 0.003236  min_lr: 0.003236  loss: 4.0177 (3.7313)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0012  max mem: 31830
Epoch: [100]  [200/312]  eta: 0:01:04  lr: 0.003236  min_lr: 0.003236  loss: 3.9655 (3.7229)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0291  max mem: 31830
Epoch: [100]  [210/312]  eta: 0:00:58  lr: 0.003235  min_lr: 0.003235  loss: 3.6227 (3.7236)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0426  max mem: 31830
Epoch: [100]  [220/312]  eta: 0:00:52  lr: 0.003235  min_lr: 0.003235  loss: 3.7628 (3.7282)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.0148  max mem: 31830
Epoch: [100]  [230/312]  eta: 0:00:46  lr: 0.003234  min_lr: 0.003234  loss: 3.9913 (3.7386)  weight_decay: 0.0500 (0.0500)  time: 0.6121  data: 0.0264  max mem: 31830
Epoch: [100]  [240/312]  eta: 0:00:40  lr: 0.003234  min_lr: 0.003234  loss: 4.2122 (3.7490)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0263  max mem: 31830
Epoch: [100]  [250/312]  eta: 0:00:35  lr: 0.003233  min_lr: 0.003233  loss: 3.8914 (3.7463)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0189  max mem: 31830
Epoch: [100]  [260/312]  eta: 0:00:29  lr: 0.003232  min_lr: 0.003232  loss: 3.8177 (3.7496)  weight_decay: 0.0500 (0.0500)  time: 0.6511  data: 0.0323  max mem: 31830
Epoch: [100]  [270/312]  eta: 0:00:23  lr: 0.003232  min_lr: 0.003232  loss: 3.8502 (3.7469)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0141  max mem: 31830
Epoch: [100]  [280/312]  eta: 0:00:18  lr: 0.003231  min_lr: 0.003231  loss: 3.9035 (3.7533)  weight_decay: 0.0500 (0.0500)  time: 0.5237  data: 0.0161  max mem: 31830
Epoch: [100]  [290/312]  eta: 0:00:12  lr: 0.003231  min_lr: 0.003231  loss: 3.9035 (3.7506)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0159  max mem: 31830
Epoch: [100]  [300/312]  eta: 0:00:06  lr: 0.003230  min_lr: 0.003230  loss: 3.9869 (3.7529)  weight_decay: 0.0500 (0.0500)  time: 0.4548  data: 0.0002  max mem: 31830
Epoch: [100]  [310/312]  eta: 0:00:01  lr: 0.003230  min_lr: 0.003230  loss: 3.9026 (3.7505)  weight_decay: 0.0500 (0.0500)  time: 0.4206  data: 0.0001  max mem: 31830
Epoch: [100]  [311/312]  eta: 0:00:00  lr: 0.003230  min_lr: 0.003230  loss: 3.7985 (3.7480)  weight_decay: 0.0500 (0.0500)  time: 0.4204  data: 0.0001  max mem: 31830
Epoch: [100] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.003230  min_lr: 0.003230  loss: 3.7985 (3.7381)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.5215 (1.5215)  acc1: 71.4844 (71.4844)  acc5: 91.4062 (91.4062)  time: 8.7963  data: 8.6290  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8373 (1.7752)  acc1: 63.2812 (64.0000)  acc5: 84.6354 (85.8560)  time: 1.0938  data: 0.9588  max mem: 31830
Test: Total time: 0:00:09 (1.1071 s / it)
* Acc@1 63.798 Acc@5 85.878 loss 1.760
Accuracy of the model on the 50000 test images: 63.8%
Max accuracy: 67.08%
Epoch: [101]  [  0/312]  eta: 1:04:39  lr: 0.003230  min_lr: 0.003230  loss: 3.5931 (3.5931)  weight_decay: 0.0500 (0.0500)  time: 12.4355  data: 9.3607  max mem: 31830
Epoch: [101]  [ 10/312]  eta: 0:09:04  lr: 0.003229  min_lr: 0.003229  loss: 3.8567 (3.9141)  weight_decay: 0.0500 (0.0500)  time: 1.8037  data: 0.9772  max mem: 31830
Epoch: [101]  [ 20/312]  eta: 0:05:29  lr: 0.003228  min_lr: 0.003228  loss: 3.8567 (3.8285)  weight_decay: 0.0500 (0.0500)  time: 0.5633  data: 0.0698  max mem: 31830
Epoch: [101]  [ 30/312]  eta: 0:04:11  lr: 0.003228  min_lr: 0.003228  loss: 3.8223 (3.7393)  weight_decay: 0.0500 (0.0500)  time: 0.3898  data: 0.0008  max mem: 31830
Epoch: [101]  [ 40/312]  eta: 0:03:29  lr: 0.003227  min_lr: 0.003227  loss: 3.1202 (3.6652)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0010  max mem: 31830
Epoch: [101]  [ 50/312]  eta: 0:03:03  lr: 0.003227  min_lr: 0.003227  loss: 3.6092 (3.6592)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0009  max mem: 31830
Epoch: [101]  [ 60/312]  eta: 0:02:43  lr: 0.003226  min_lr: 0.003226  loss: 3.8468 (3.6866)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [101]  [ 70/312]  eta: 0:02:34  lr: 0.003226  min_lr: 0.003226  loss: 4.0169 (3.7328)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0009  max mem: 31830
Epoch: [101]  [ 80/312]  eta: 0:02:25  lr: 0.003225  min_lr: 0.003225  loss: 4.0407 (3.7529)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0160  max mem: 31830
Epoch: [101]  [ 90/312]  eta: 0:02:16  lr: 0.003224  min_lr: 0.003224  loss: 3.8656 (3.7469)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0159  max mem: 31830
Epoch: [101]  [100/312]  eta: 0:02:10  lr: 0.003224  min_lr: 0.003224  loss: 3.6353 (3.7187)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.0009  max mem: 31830
Epoch: [101]  [110/312]  eta: 0:02:00  lr: 0.003223  min_lr: 0.003223  loss: 3.4470 (3.7112)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0018  max mem: 31830
Epoch: [101]  [120/312]  eta: 0:01:55  lr: 0.003223  min_lr: 0.003223  loss: 3.6356 (3.7056)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0017  max mem: 31830
Epoch: [101]  [130/312]  eta: 0:01:49  lr: 0.003222  min_lr: 0.003222  loss: 3.7700 (3.7187)  weight_decay: 0.0500 (0.0500)  time: 0.6380  data: 0.0137  max mem: 31830
Epoch: [101]  [140/312]  eta: 0:01:41  lr: 0.003222  min_lr: 0.003222  loss: 3.9937 (3.7300)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0139  max mem: 31830
Epoch: [101]  [150/312]  eta: 0:01:36  lr: 0.003221  min_lr: 0.003221  loss: 3.8983 (3.7210)  weight_decay: 0.0500 (0.0500)  time: 0.5306  data: 0.0082  max mem: 31830
Epoch: [101]  [160/312]  eta: 0:01:29  lr: 0.003220  min_lr: 0.003220  loss: 3.7637 (3.7289)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0085  max mem: 31830
Epoch: [101]  [170/312]  eta: 0:01:23  lr: 0.003220  min_lr: 0.003220  loss: 4.0141 (3.7470)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0017  max mem: 31830
Epoch: [101]  [180/312]  eta: 0:01:17  lr: 0.003219  min_lr: 0.003219  loss: 3.8496 (3.7367)  weight_decay: 0.0500 (0.0500)  time: 0.5640  data: 0.0133  max mem: 31830
Epoch: [101]  [190/312]  eta: 0:01:10  lr: 0.003219  min_lr: 0.003219  loss: 3.6652 (3.7496)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0383  max mem: 31830
Epoch: [101]  [200/312]  eta: 0:01:05  lr: 0.003218  min_lr: 0.003218  loss: 4.0370 (3.7526)  weight_decay: 0.0500 (0.0500)  time: 0.5623  data: 0.0262  max mem: 31830
Epoch: [101]  [210/312]  eta: 0:00:59  lr: 0.003218  min_lr: 0.003218  loss: 3.8563 (3.7541)  weight_decay: 0.0500 (0.0500)  time: 0.6370  data: 0.0135  max mem: 31830
Epoch: [101]  [220/312]  eta: 0:00:53  lr: 0.003217  min_lr: 0.003217  loss: 3.7035 (3.7478)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0417  max mem: 31830
Epoch: [101]  [230/312]  eta: 0:00:47  lr: 0.003216  min_lr: 0.003216  loss: 3.7085 (3.7408)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0293  max mem: 31830
Epoch: [101]  [240/312]  eta: 0:00:41  lr: 0.003216  min_lr: 0.003216  loss: 3.7139 (3.7464)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.0294  max mem: 31830
Epoch: [101]  [250/312]  eta: 0:00:35  lr: 0.003215  min_lr: 0.003215  loss: 3.9747 (3.7513)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0291  max mem: 31830
Epoch: [101]  [260/312]  eta: 0:00:29  lr: 0.003215  min_lr: 0.003215  loss: 4.0196 (3.7586)  weight_decay: 0.0500 (0.0500)  time: 0.5817  data: 0.0052  max mem: 31830
Epoch: [101]  [270/312]  eta: 0:00:23  lr: 0.003214  min_lr: 0.003214  loss: 4.0472 (3.7605)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0052  max mem: 31830
Epoch: [101]  [280/312]  eta: 0:00:18  lr: 0.003214  min_lr: 0.003214  loss: 3.9920 (3.7659)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0029  max mem: 31830
Epoch: [101]  [290/312]  eta: 0:00:12  lr: 0.003213  min_lr: 0.003213  loss: 3.9039 (3.7676)  weight_decay: 0.0500 (0.0500)  time: 0.6251  data: 0.0027  max mem: 31830
Epoch: [101]  [300/312]  eta: 0:00:06  lr: 0.003212  min_lr: 0.003212  loss: 3.7483 (3.7644)  weight_decay: 0.0500 (0.0500)  time: 0.4958  data: 0.0002  max mem: 31830
Epoch: [101]  [310/312]  eta: 0:00:01  lr: 0.003212  min_lr: 0.003212  loss: 3.8212 (3.7645)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [101]  [311/312]  eta: 0:00:00  lr: 0.003212  min_lr: 0.003212  loss: 3.7847 (3.7632)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [101] Total time: 0:02:56 (0.5643 s / it)
Averaged stats: lr: 0.003212  min_lr: 0.003212  loss: 3.7847 (3.7341)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.6839 (1.6839)  acc1: 70.0521 (70.0521)  acc5: 89.5833 (89.5833)  time: 8.6373  data: 8.4700  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9707 (1.8894)  acc1: 64.8438 (65.7920)  acc5: 86.9792 (87.1680)  time: 1.0757  data: 0.9412  max mem: 31830
Test: Total time: 0:00:09 (1.0988 s / it)
* Acc@1 65.624 Acc@5 87.200 loss 1.889
Accuracy of the model on the 50000 test images: 65.6%
Max accuracy: 67.08%
Epoch: [102]  [  0/312]  eta: 1:02:27  lr: 0.003212  min_lr: 0.003212  loss: 4.3537 (4.3537)  weight_decay: 0.0500 (0.0500)  time: 12.0121  data: 10.6308  max mem: 31830
Epoch: [102]  [ 10/312]  eta: 0:08:24  lr: 0.003211  min_lr: 0.003211  loss: 4.0511 (3.8728)  weight_decay: 0.0500 (0.0500)  time: 1.6709  data: 0.9669  max mem: 31830
Epoch: [102]  [ 20/312]  eta: 0:05:34  lr: 0.003211  min_lr: 0.003211  loss: 3.6341 (3.7269)  weight_decay: 0.0500 (0.0500)  time: 0.6010  data: 0.0368  max mem: 31830
Epoch: [102]  [ 30/312]  eta: 0:04:14  lr: 0.003210  min_lr: 0.003210  loss: 3.5469 (3.6325)  weight_decay: 0.0500 (0.0500)  time: 0.4819  data: 0.0369  max mem: 31830
Epoch: [102]  [ 40/312]  eta: 0:03:32  lr: 0.003209  min_lr: 0.003209  loss: 3.5480 (3.6560)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0009  max mem: 31830
Epoch: [102]  [ 50/312]  eta: 0:03:05  lr: 0.003209  min_lr: 0.003209  loss: 3.8362 (3.6744)  weight_decay: 0.0500 (0.0500)  time: 0.4008  data: 0.0009  max mem: 31830
Epoch: [102]  [ 60/312]  eta: 0:02:45  lr: 0.003208  min_lr: 0.003208  loss: 3.7738 (3.6696)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0008  max mem: 31830
Epoch: [102]  [ 70/312]  eta: 0:02:34  lr: 0.003208  min_lr: 0.003208  loss: 3.5075 (3.6542)  weight_decay: 0.0500 (0.0500)  time: 0.4649  data: 0.0219  max mem: 31830
Epoch: [102]  [ 80/312]  eta: 0:02:25  lr: 0.003207  min_lr: 0.003207  loss: 3.4504 (3.6642)  weight_decay: 0.0500 (0.0500)  time: 0.5506  data: 0.0622  max mem: 31830
Epoch: [102]  [ 90/312]  eta: 0:02:15  lr: 0.003207  min_lr: 0.003207  loss: 3.8277 (3.6785)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.0779  max mem: 31830
Epoch: [102]  [100/312]  eta: 0:02:10  lr: 0.003206  min_lr: 0.003206  loss: 3.9327 (3.7029)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.1002  max mem: 31830
Epoch: [102]  [110/312]  eta: 0:02:00  lr: 0.003205  min_lr: 0.003205  loss: 3.9327 (3.7150)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0634  max mem: 31830
Epoch: [102]  [120/312]  eta: 0:01:54  lr: 0.003205  min_lr: 0.003205  loss: 3.7846 (3.7193)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0513  max mem: 31830
Epoch: [102]  [130/312]  eta: 0:01:48  lr: 0.003204  min_lr: 0.003204  loss: 3.8798 (3.7286)  weight_decay: 0.0500 (0.0500)  time: 0.6152  data: 0.0877  max mem: 31830
Epoch: [102]  [140/312]  eta: 0:01:40  lr: 0.003204  min_lr: 0.003204  loss: 3.8893 (3.7158)  weight_decay: 0.0500 (0.0500)  time: 0.4923  data: 0.0371  max mem: 31830
Epoch: [102]  [150/312]  eta: 0:01:36  lr: 0.003203  min_lr: 0.003203  loss: 3.7762 (3.7085)  weight_decay: 0.0500 (0.0500)  time: 0.5662  data: 0.0600  max mem: 31830
Epoch: [102]  [160/312]  eta: 0:01:29  lr: 0.003203  min_lr: 0.003203  loss: 3.2857 (3.6850)  weight_decay: 0.0500 (0.0500)  time: 0.6384  data: 0.0602  max mem: 31830
Epoch: [102]  [170/312]  eta: 0:01:22  lr: 0.003202  min_lr: 0.003202  loss: 3.5203 (3.6898)  weight_decay: 0.0500 (0.0500)  time: 0.4829  data: 0.0192  max mem: 31830
Epoch: [102]  [180/312]  eta: 0:01:17  lr: 0.003201  min_lr: 0.003201  loss: 3.9035 (3.6944)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0429  max mem: 31830
Epoch: [102]  [190/312]  eta: 0:01:10  lr: 0.003201  min_lr: 0.003201  loss: 3.7244 (3.6831)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0251  max mem: 31830
Epoch: [102]  [200/312]  eta: 0:01:04  lr: 0.003200  min_lr: 0.003200  loss: 3.8172 (3.6916)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0135  max mem: 31830
Epoch: [102]  [210/312]  eta: 0:00:58  lr: 0.003200  min_lr: 0.003200  loss: 3.8779 (3.6936)  weight_decay: 0.0500 (0.0500)  time: 0.5998  data: 0.0403  max mem: 31830
Epoch: [102]  [220/312]  eta: 0:00:52  lr: 0.003199  min_lr: 0.003199  loss: 3.5703 (3.6861)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0281  max mem: 31830
Epoch: [102]  [230/312]  eta: 0:00:46  lr: 0.003199  min_lr: 0.003199  loss: 3.6031 (3.6873)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0266  max mem: 31830
Epoch: [102]  [240/312]  eta: 0:00:41  lr: 0.003198  min_lr: 0.003198  loss: 3.7186 (3.6904)  weight_decay: 0.0500 (0.0500)  time: 0.5807  data: 0.0265  max mem: 31830
Epoch: [102]  [250/312]  eta: 0:00:35  lr: 0.003197  min_lr: 0.003197  loss: 3.8533 (3.6976)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0230  max mem: 31830
Epoch: [102]  [260/312]  eta: 0:00:29  lr: 0.003197  min_lr: 0.003197  loss: 3.8520 (3.7023)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.0289  max mem: 31830
Epoch: [102]  [270/312]  eta: 0:00:23  lr: 0.003196  min_lr: 0.003196  loss: 3.8467 (3.7021)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0066  max mem: 31830
Epoch: [102]  [280/312]  eta: 0:00:18  lr: 0.003196  min_lr: 0.003196  loss: 3.8925 (3.7082)  weight_decay: 0.0500 (0.0500)  time: 0.5113  data: 0.0144  max mem: 31830
Epoch: [102]  [290/312]  eta: 0:00:12  lr: 0.003195  min_lr: 0.003195  loss: 3.8391 (3.7103)  weight_decay: 0.0500 (0.0500)  time: 0.6329  data: 0.0358  max mem: 31830
Epoch: [102]  [300/312]  eta: 0:00:06  lr: 0.003195  min_lr: 0.003195  loss: 3.9780 (3.7235)  weight_decay: 0.0500 (0.0500)  time: 0.5081  data: 0.0219  max mem: 31830
Epoch: [102]  [310/312]  eta: 0:00:01  lr: 0.003194  min_lr: 0.003194  loss: 3.9684 (3.7217)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [102]  [311/312]  eta: 0:00:00  lr: 0.003194  min_lr: 0.003194  loss: 3.9580 (3.7205)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [102] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.003194  min_lr: 0.003194  loss: 3.9580 (3.7256)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4562 (1.4562)  acc1: 75.0000 (75.0000)  acc5: 91.2760 (91.2760)  time: 8.3558  data: 8.1968  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7091 (1.6996)  acc1: 66.5365 (66.4480)  acc5: 87.1094 (87.4240)  time: 1.0488  data: 0.9108  max mem: 31830
Test: Total time: 0:00:09 (1.0577 s / it)
* Acc@1 66.338 Acc@5 87.934 loss 1.694
Accuracy of the model on the 50000 test images: 66.3%
Max accuracy: 67.08%
Epoch: [103]  [  0/312]  eta: 0:58:51  lr: 0.003194  min_lr: 0.003194  loss: 4.4528 (4.4528)  weight_decay: 0.0500 (0.0500)  time: 11.3196  data: 10.9287  max mem: 31830
Epoch: [103]  [ 10/312]  eta: 0:07:55  lr: 0.003193  min_lr: 0.003193  loss: 3.9603 (3.9188)  weight_decay: 0.0500 (0.0500)  time: 1.5757  data: 0.9941  max mem: 31830
Epoch: [103]  [ 20/312]  eta: 0:05:19  lr: 0.003193  min_lr: 0.003193  loss: 3.9595 (3.8663)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.0277  max mem: 31830
Epoch: [103]  [ 30/312]  eta: 0:04:04  lr: 0.003192  min_lr: 0.003192  loss: 3.9205 (3.8699)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0277  max mem: 31830
Epoch: [103]  [ 40/312]  eta: 0:03:27  lr: 0.003192  min_lr: 0.003192  loss: 3.8943 (3.8631)  weight_decay: 0.0500 (0.0500)  time: 0.4147  data: 0.0008  max mem: 31830
Epoch: [103]  [ 50/312]  eta: 0:03:13  lr: 0.003191  min_lr: 0.003191  loss: 4.0058 (3.8634)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0285  max mem: 31830
Epoch: [103]  [ 60/312]  eta: 0:02:52  lr: 0.003190  min_lr: 0.003190  loss: 3.9314 (3.8505)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0408  max mem: 31830
Epoch: [103]  [ 70/312]  eta: 0:02:42  lr: 0.003190  min_lr: 0.003190  loss: 3.7769 (3.8304)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0291  max mem: 31830
Epoch: [103]  [ 80/312]  eta: 0:02:31  lr: 0.003189  min_lr: 0.003189  loss: 3.7748 (3.8312)  weight_decay: 0.0500 (0.0500)  time: 0.5479  data: 0.0168  max mem: 31830
Epoch: [103]  [ 90/312]  eta: 0:02:22  lr: 0.003189  min_lr: 0.003189  loss: 3.8746 (3.8268)  weight_decay: 0.0500 (0.0500)  time: 0.5352  data: 0.0306  max mem: 31830
Epoch: [103]  [100/312]  eta: 0:02:15  lr: 0.003188  min_lr: 0.003188  loss: 3.8479 (3.7930)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.0659  max mem: 31830
Epoch: [103]  [110/312]  eta: 0:02:05  lr: 0.003187  min_lr: 0.003187  loss: 3.7735 (3.8003)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0360  max mem: 31830
Epoch: [103]  [120/312]  eta: 0:01:57  lr: 0.003187  min_lr: 0.003187  loss: 3.8382 (3.7925)  weight_decay: 0.0500 (0.0500)  time: 0.4662  data: 0.0288  max mem: 31830
Epoch: [103]  [130/312]  eta: 0:01:51  lr: 0.003186  min_lr: 0.003186  loss: 3.9109 (3.7921)  weight_decay: 0.0500 (0.0500)  time: 0.5633  data: 0.0288  max mem: 31830
Epoch: [103]  [140/312]  eta: 0:01:43  lr: 0.003186  min_lr: 0.003186  loss: 3.9190 (3.7964)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0457  max mem: 31830
Epoch: [103]  [150/312]  eta: 0:01:37  lr: 0.003185  min_lr: 0.003185  loss: 3.8341 (3.7849)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0748  max mem: 31830
Epoch: [103]  [160/312]  eta: 0:01:29  lr: 0.003185  min_lr: 0.003185  loss: 3.8067 (3.7802)  weight_decay: 0.0500 (0.0500)  time: 0.5053  data: 0.0301  max mem: 31830
Epoch: [103]  [170/312]  eta: 0:01:23  lr: 0.003184  min_lr: 0.003184  loss: 3.8850 (3.7890)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0483  max mem: 31830
Epoch: [103]  [180/312]  eta: 0:01:17  lr: 0.003183  min_lr: 0.003183  loss: 4.0186 (3.7942)  weight_decay: 0.0500 (0.0500)  time: 0.5975  data: 0.0813  max mem: 31830
Epoch: [103]  [190/312]  eta: 0:01:10  lr: 0.003183  min_lr: 0.003183  loss: 3.9256 (3.7923)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0339  max mem: 31830
Epoch: [103]  [200/312]  eta: 0:01:05  lr: 0.003182  min_lr: 0.003182  loss: 3.9251 (3.8012)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0206  max mem: 31830
Epoch: [103]  [210/312]  eta: 0:00:59  lr: 0.003182  min_lr: 0.003182  loss: 4.1252 (3.8122)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0207  max mem: 31830
Epoch: [103]  [220/312]  eta: 0:00:52  lr: 0.003181  min_lr: 0.003181  loss: 3.8460 (3.8003)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0209  max mem: 31830
Epoch: [103]  [230/312]  eta: 0:00:47  lr: 0.003181  min_lr: 0.003181  loss: 3.6013 (3.7898)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0427  max mem: 31830
Epoch: [103]  [240/312]  eta: 0:00:41  lr: 0.003180  min_lr: 0.003180  loss: 3.6149 (3.7874)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0225  max mem: 31830
Epoch: [103]  [250/312]  eta: 0:00:35  lr: 0.003179  min_lr: 0.003179  loss: 3.8677 (3.7921)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0216  max mem: 31830
Epoch: [103]  [260/312]  eta: 0:00:29  lr: 0.003179  min_lr: 0.003179  loss: 3.8677 (3.7873)  weight_decay: 0.0500 (0.0500)  time: 0.5939  data: 0.0599  max mem: 31830
Epoch: [103]  [270/312]  eta: 0:00:23  lr: 0.003178  min_lr: 0.003178  loss: 3.9418 (3.7893)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0390  max mem: 31830
Epoch: [103]  [280/312]  eta: 0:00:18  lr: 0.003178  min_lr: 0.003178  loss: 3.9418 (3.7839)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0233  max mem: 31830
Epoch: [103]  [290/312]  eta: 0:00:12  lr: 0.003177  min_lr: 0.003177  loss: 3.7881 (3.7854)  weight_decay: 0.0500 (0.0500)  time: 0.5540  data: 0.0230  max mem: 31830
Epoch: [103]  [300/312]  eta: 0:00:06  lr: 0.003176  min_lr: 0.003176  loss: 3.7882 (3.7792)  weight_decay: 0.0500 (0.0500)  time: 0.4405  data: 0.0041  max mem: 31830
Epoch: [103]  [310/312]  eta: 0:00:01  lr: 0.003176  min_lr: 0.003176  loss: 3.9599 (3.7869)  weight_decay: 0.0500 (0.0500)  time: 0.3841  data: 0.0040  max mem: 31830
Epoch: [103]  [311/312]  eta: 0:00:00  lr: 0.003176  min_lr: 0.003176  loss: 3.9599 (3.7840)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [103] Total time: 0:02:54 (0.5586 s / it)
Averaged stats: lr: 0.003176  min_lr: 0.003176  loss: 3.9599 (3.7301)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.2481 (1.2481)  acc1: 73.9583 (73.9583)  acc5: 92.0573 (92.0573)  time: 8.4963  data: 8.3288  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6413 (1.5071)  acc1: 65.2344 (66.6720)  acc5: 86.8490 (87.5840)  time: 1.0609  data: 0.9255  max mem: 31830
Test: Total time: 0:00:09 (1.0864 s / it)
* Acc@1 66.518 Acc@5 87.998 loss 1.498
Accuracy of the model on the 50000 test images: 66.5%
Max accuracy: 67.08%
Epoch: [104]  [  0/312]  eta: 0:59:42  lr: 0.003176  min_lr: 0.003176  loss: 3.0859 (3.0859)  weight_decay: 0.0500 (0.0500)  time: 11.4832  data: 9.2161  max mem: 31830
Epoch: [104]  [ 10/312]  eta: 0:08:42  lr: 0.003175  min_lr: 0.003175  loss: 3.5099 (3.5509)  weight_decay: 0.0500 (0.0500)  time: 1.7288  data: 0.9440  max mem: 31830
Epoch: [104]  [ 20/312]  eta: 0:05:18  lr: 0.003175  min_lr: 0.003175  loss: 3.6616 (3.6277)  weight_decay: 0.0500 (0.0500)  time: 0.5713  data: 0.0587  max mem: 31830
Epoch: [104]  [ 30/312]  eta: 0:04:04  lr: 0.003174  min_lr: 0.003174  loss: 3.9885 (3.6827)  weight_decay: 0.0500 (0.0500)  time: 0.3946  data: 0.0007  max mem: 31830
Epoch: [104]  [ 40/312]  eta: 0:03:25  lr: 0.003173  min_lr: 0.003173  loss: 3.9178 (3.6493)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [104]  [ 50/312]  eta: 0:02:59  lr: 0.003173  min_lr: 0.003173  loss: 3.5045 (3.6238)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [104]  [ 60/312]  eta: 0:02:40  lr: 0.003172  min_lr: 0.003172  loss: 3.6701 (3.6468)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [104]  [ 70/312]  eta: 0:02:31  lr: 0.003172  min_lr: 0.003172  loss: 3.6837 (3.6433)  weight_decay: 0.0500 (0.0500)  time: 0.4817  data: 0.0524  max mem: 31830
Epoch: [104]  [ 80/312]  eta: 0:02:25  lr: 0.003171  min_lr: 0.003171  loss: 3.4953 (3.6403)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.0935  max mem: 31830
Epoch: [104]  [ 90/312]  eta: 0:02:15  lr: 0.003171  min_lr: 0.003171  loss: 3.6424 (3.6394)  weight_decay: 0.0500 (0.0500)  time: 0.5573  data: 0.0566  max mem: 31830
Epoch: [104]  [100/312]  eta: 0:02:08  lr: 0.003170  min_lr: 0.003170  loss: 3.7759 (3.6297)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0342  max mem: 31830
Epoch: [104]  [110/312]  eta: 0:01:59  lr: 0.003169  min_lr: 0.003169  loss: 3.5415 (3.6127)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0193  max mem: 31830
Epoch: [104]  [120/312]  eta: 0:01:54  lr: 0.003169  min_lr: 0.003169  loss: 3.8045 (3.6424)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0268  max mem: 31830
Epoch: [104]  [130/312]  eta: 0:01:47  lr: 0.003168  min_lr: 0.003168  loss: 3.9942 (3.6619)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0445  max mem: 31830
Epoch: [104]  [140/312]  eta: 0:01:39  lr: 0.003168  min_lr: 0.003168  loss: 3.8702 (3.6693)  weight_decay: 0.0500 (0.0500)  time: 0.4915  data: 0.0184  max mem: 31830
Epoch: [104]  [150/312]  eta: 0:01:34  lr: 0.003167  min_lr: 0.003167  loss: 3.6011 (3.6644)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0244  max mem: 31830
Epoch: [104]  [160/312]  eta: 0:01:27  lr: 0.003166  min_lr: 0.003166  loss: 3.5005 (3.6633)  weight_decay: 0.0500 (0.0500)  time: 0.5729  data: 0.0244  max mem: 31830
Epoch: [104]  [170/312]  eta: 0:01:21  lr: 0.003166  min_lr: 0.003166  loss: 3.4873 (3.6589)  weight_decay: 0.0500 (0.0500)  time: 0.5157  data: 0.0136  max mem: 31830
Epoch: [104]  [180/312]  eta: 0:01:16  lr: 0.003165  min_lr: 0.003165  loss: 3.4337 (3.6590)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0334  max mem: 31830
Epoch: [104]  [190/312]  eta: 0:01:09  lr: 0.003165  min_lr: 0.003165  loss: 3.9357 (3.6811)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0206  max mem: 31830
Epoch: [104]  [200/312]  eta: 0:01:04  lr: 0.003164  min_lr: 0.003164  loss: 4.0550 (3.6870)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0206  max mem: 31830
Epoch: [104]  [210/312]  eta: 0:00:58  lr: 0.003164  min_lr: 0.003164  loss: 3.7284 (3.6809)  weight_decay: 0.0500 (0.0500)  time: 0.5995  data: 0.0206  max mem: 31830
Epoch: [104]  [220/312]  eta: 0:00:52  lr: 0.003163  min_lr: 0.003163  loss: 3.7284 (3.6854)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0008  max mem: 31830
Epoch: [104]  [230/312]  eta: 0:00:46  lr: 0.003162  min_lr: 0.003162  loss: 3.8898 (3.6872)  weight_decay: 0.0500 (0.0500)  time: 0.5474  data: 0.0136  max mem: 31830
Epoch: [104]  [240/312]  eta: 0:00:41  lr: 0.003162  min_lr: 0.003162  loss: 3.8076 (3.6867)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.0136  max mem: 31830
Epoch: [104]  [250/312]  eta: 0:00:35  lr: 0.003161  min_lr: 0.003161  loss: 3.6749 (3.6829)  weight_decay: 0.0500 (0.0500)  time: 0.5428  data: 0.0126  max mem: 31830
Epoch: [104]  [260/312]  eta: 0:00:29  lr: 0.003161  min_lr: 0.003161  loss: 3.6380 (3.6811)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0126  max mem: 31830
Epoch: [104]  [270/312]  eta: 0:00:24  lr: 0.003160  min_lr: 0.003160  loss: 3.8364 (3.6886)  weight_decay: 0.0500 (0.0500)  time: 0.6887  data: 0.0009  max mem: 31830
Epoch: [104]  [280/312]  eta: 0:00:18  lr: 0.003159  min_lr: 0.003159  loss: 3.9039 (3.6962)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0020  max mem: 31830
Epoch: [104]  [290/312]  eta: 0:00:12  lr: 0.003159  min_lr: 0.003159  loss: 3.9039 (3.7020)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0025  max mem: 31830
Epoch: [104]  [300/312]  eta: 0:00:06  lr: 0.003158  min_lr: 0.003158  loss: 3.7957 (3.6999)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0009  max mem: 31830
Epoch: [104]  [310/312]  eta: 0:00:01  lr: 0.003158  min_lr: 0.003158  loss: 3.6798 (3.7001)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [104]  [311/312]  eta: 0:00:00  lr: 0.003158  min_lr: 0.003158  loss: 3.6798 (3.7022)  weight_decay: 0.0500 (0.0500)  time: 0.3804  data: 0.0001  max mem: 31830
Epoch: [104] Total time: 0:02:55 (0.5619 s / it)
Averaged stats: lr: 0.003158  min_lr: 0.003158  loss: 3.6798 (3.7349)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4206 (1.4206)  acc1: 73.6979 (73.6979)  acc5: 91.0156 (91.0156)  time: 8.3338  data: 8.1660  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7787 (1.6684)  acc1: 66.0156 (65.6640)  acc5: 85.9375 (87.0720)  time: 1.0435  data: 0.9074  max mem: 31830
Test: Total time: 0:00:09 (1.0609 s / it)
* Acc@1 65.794 Acc@5 87.132 loss 1.663
Accuracy of the model on the 50000 test images: 65.8%
Max accuracy: 67.08%
Epoch: [105]  [  0/312]  eta: 1:01:01  lr: 0.003158  min_lr: 0.003158  loss: 2.5031 (2.5031)  weight_decay: 0.0500 (0.0500)  time: 11.7359  data: 11.3386  max mem: 31830
Epoch: [105]  [ 10/312]  eta: 0:09:07  lr: 0.003157  min_lr: 0.003157  loss: 3.8780 (3.6180)  weight_decay: 0.0500 (0.0500)  time: 1.8125  data: 1.0312  max mem: 31830
Epoch: [105]  [ 20/312]  eta: 0:05:31  lr: 0.003156  min_lr: 0.003156  loss: 3.8780 (3.7203)  weight_decay: 0.0500 (0.0500)  time: 0.6055  data: 0.0006  max mem: 31830
Epoch: [105]  [ 30/312]  eta: 0:04:13  lr: 0.003156  min_lr: 0.003156  loss: 3.7027 (3.7306)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0007  max mem: 31830
Epoch: [105]  [ 40/312]  eta: 0:03:31  lr: 0.003155  min_lr: 0.003155  loss: 3.8536 (3.7471)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0007  max mem: 31830
Epoch: [105]  [ 50/312]  eta: 0:03:03  lr: 0.003155  min_lr: 0.003155  loss: 3.8322 (3.7181)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0012  max mem: 31830
Epoch: [105]  [ 60/312]  eta: 0:02:44  lr: 0.003154  min_lr: 0.003154  loss: 3.8322 (3.7456)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0013  max mem: 31830
Epoch: [105]  [ 70/312]  eta: 0:02:31  lr: 0.003153  min_lr: 0.003153  loss: 4.0046 (3.7958)  weight_decay: 0.0500 (0.0500)  time: 0.4273  data: 0.0012  max mem: 31830
Epoch: [105]  [ 80/312]  eta: 0:02:23  lr: 0.003153  min_lr: 0.003153  loss: 3.9254 (3.7755)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0288  max mem: 31830
Epoch: [105]  [ 90/312]  eta: 0:02:13  lr: 0.003152  min_lr: 0.003152  loss: 4.0775 (3.8123)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0284  max mem: 31830
Epoch: [105]  [100/312]  eta: 0:02:08  lr: 0.003152  min_lr: 0.003152  loss: 4.0973 (3.8220)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0159  max mem: 31830
Epoch: [105]  [110/312]  eta: 0:02:01  lr: 0.003151  min_lr: 0.003151  loss: 3.9245 (3.8129)  weight_decay: 0.0500 (0.0500)  time: 0.5932  data: 0.0413  max mem: 31830
Epoch: [105]  [120/312]  eta: 0:01:52  lr: 0.003151  min_lr: 0.003151  loss: 3.7247 (3.7864)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0386  max mem: 31830
Epoch: [105]  [130/312]  eta: 0:01:47  lr: 0.003150  min_lr: 0.003150  loss: 3.6478 (3.7747)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0377  max mem: 31830
Epoch: [105]  [140/312]  eta: 0:01:41  lr: 0.003149  min_lr: 0.003149  loss: 3.6497 (3.7631)  weight_decay: 0.0500 (0.0500)  time: 0.6149  data: 0.0379  max mem: 31830
Epoch: [105]  [150/312]  eta: 0:01:34  lr: 0.003149  min_lr: 0.003149  loss: 3.6938 (3.7621)  weight_decay: 0.0500 (0.0500)  time: 0.5526  data: 0.0426  max mem: 31830
Epoch: [105]  [160/312]  eta: 0:01:30  lr: 0.003148  min_lr: 0.003148  loss: 3.6938 (3.7551)  weight_decay: 0.0500 (0.0500)  time: 0.6021  data: 0.0428  max mem: 31830
Epoch: [105]  [170/312]  eta: 0:01:22  lr: 0.003148  min_lr: 0.003148  loss: 3.7365 (3.7419)  weight_decay: 0.0500 (0.0500)  time: 0.5607  data: 0.0263  max mem: 31830
Epoch: [105]  [180/312]  eta: 0:01:17  lr: 0.003147  min_lr: 0.003147  loss: 3.8480 (3.7613)  weight_decay: 0.0500 (0.0500)  time: 0.5106  data: 0.0136  max mem: 31830
Epoch: [105]  [190/312]  eta: 0:01:11  lr: 0.003146  min_lr: 0.003146  loss: 4.1109 (3.7573)  weight_decay: 0.0500 (0.0500)  time: 0.6336  data: 0.0061  max mem: 31830
Epoch: [105]  [200/312]  eta: 0:01:04  lr: 0.003146  min_lr: 0.003146  loss: 3.5338 (3.7449)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.0061  max mem: 31830
Epoch: [105]  [210/312]  eta: 0:00:59  lr: 0.003145  min_lr: 0.003145  loss: 3.5568 (3.7433)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0010  max mem: 31830
Epoch: [105]  [220/312]  eta: 0:00:53  lr: 0.003145  min_lr: 0.003145  loss: 3.5568 (3.7320)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.0009  max mem: 31830
Epoch: [105]  [230/312]  eta: 0:00:47  lr: 0.003144  min_lr: 0.003144  loss: 3.4467 (3.7281)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0118  max mem: 31830
Epoch: [105]  [240/312]  eta: 0:00:41  lr: 0.003143  min_lr: 0.003143  loss: 3.6546 (3.7213)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0118  max mem: 31830
Epoch: [105]  [250/312]  eta: 0:00:35  lr: 0.003143  min_lr: 0.003143  loss: 3.8122 (3.7292)  weight_decay: 0.0500 (0.0500)  time: 0.4824  data: 0.0008  max mem: 31830
Epoch: [105]  [260/312]  eta: 0:00:29  lr: 0.003142  min_lr: 0.003142  loss: 3.8150 (3.7248)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0057  max mem: 31830
Epoch: [105]  [270/312]  eta: 0:00:24  lr: 0.003142  min_lr: 0.003142  loss: 3.9207 (3.7344)  weight_decay: 0.0500 (0.0500)  time: 0.6528  data: 0.0060  max mem: 31830
Epoch: [105]  [280/312]  eta: 0:00:18  lr: 0.003141  min_lr: 0.003141  loss: 3.9983 (3.7364)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0030  max mem: 31830
Epoch: [105]  [290/312]  eta: 0:00:12  lr: 0.003140  min_lr: 0.003140  loss: 4.0046 (3.7498)  weight_decay: 0.0500 (0.0500)  time: 0.4869  data: 0.0024  max mem: 31830
Epoch: [105]  [300/312]  eta: 0:00:06  lr: 0.003140  min_lr: 0.003140  loss: 3.9531 (3.7574)  weight_decay: 0.0500 (0.0500)  time: 0.4833  data: 0.0002  max mem: 31830
Epoch: [105]  [310/312]  eta: 0:00:01  lr: 0.003139  min_lr: 0.003139  loss: 3.6667 (3.7448)  weight_decay: 0.0500 (0.0500)  time: 0.3900  data: 0.0001  max mem: 31830
Epoch: [105]  [311/312]  eta: 0:00:00  lr: 0.003139  min_lr: 0.003139  loss: 3.7503 (3.7461)  weight_decay: 0.0500 (0.0500)  time: 0.3898  data: 0.0001  max mem: 31830
Epoch: [105] Total time: 0:02:55 (0.5616 s / it)
Averaged stats: lr: 0.003139  min_lr: 0.003139  loss: 3.7503 (3.7174)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.2638 (1.2638)  acc1: 74.4792 (74.4792)  acc5: 92.0573 (92.0573)  time: 8.1087  data: 7.9463  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6655 (1.6025)  acc1: 66.1458 (66.7040)  acc5: 88.2812 (87.3440)  time: 1.0194  data: 0.8852  max mem: 31830
Test: Total time: 0:00:09 (1.0289 s / it)
* Acc@1 66.248 Acc@5 87.570 loss 1.610
Accuracy of the model on the 50000 test images: 66.2%
Max accuracy: 67.08%
Epoch: [106]  [  0/312]  eta: 1:04:18  lr: 0.003139  min_lr: 0.003139  loss: 3.1538 (3.1538)  weight_decay: 0.0500 (0.0500)  time: 12.3668  data: 8.5229  max mem: 31830
Epoch: [106]  [ 10/312]  eta: 0:08:31  lr: 0.003139  min_lr: 0.003139  loss: 3.8036 (3.7825)  weight_decay: 0.0500 (0.0500)  time: 1.6932  data: 0.9924  max mem: 31830
Epoch: [106]  [ 20/312]  eta: 0:05:32  lr: 0.003138  min_lr: 0.003138  loss: 3.8598 (3.8196)  weight_decay: 0.0500 (0.0500)  time: 0.5769  data: 0.1443  max mem: 31830
Epoch: [106]  [ 30/312]  eta: 0:04:13  lr: 0.003137  min_lr: 0.003137  loss: 3.8997 (3.7745)  weight_decay: 0.0500 (0.0500)  time: 0.4640  data: 0.0249  max mem: 31830
Epoch: [106]  [ 40/312]  eta: 0:03:31  lr: 0.003137  min_lr: 0.003137  loss: 3.9437 (3.8451)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0011  max mem: 31830
Epoch: [106]  [ 50/312]  eta: 0:03:03  lr: 0.003136  min_lr: 0.003136  loss: 4.0223 (3.8338)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0010  max mem: 31830
Epoch: [106]  [ 60/312]  eta: 0:02:44  lr: 0.003136  min_lr: 0.003136  loss: 3.8328 (3.8066)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0007  max mem: 31830
Epoch: [106]  [ 70/312]  eta: 0:02:37  lr: 0.003135  min_lr: 0.003135  loss: 3.5005 (3.7273)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0586  max mem: 31830
Epoch: [106]  [ 80/312]  eta: 0:02:29  lr: 0.003134  min_lr: 0.003134  loss: 3.4477 (3.6985)  weight_decay: 0.0500 (0.0500)  time: 0.6154  data: 0.0586  max mem: 31830
Epoch: [106]  [ 90/312]  eta: 0:02:19  lr: 0.003134  min_lr: 0.003134  loss: 3.7561 (3.7185)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0459  max mem: 31830
Epoch: [106]  [100/312]  eta: 0:02:10  lr: 0.003133  min_lr: 0.003133  loss: 3.7554 (3.7184)  weight_decay: 0.0500 (0.0500)  time: 0.4995  data: 0.0605  max mem: 31830
Epoch: [106]  [110/312]  eta: 0:02:00  lr: 0.003133  min_lr: 0.003133  loss: 3.7233 (3.7179)  weight_decay: 0.0500 (0.0500)  time: 0.4548  data: 0.0156  max mem: 31830
Epoch: [106]  [120/312]  eta: 0:01:56  lr: 0.003132  min_lr: 0.003132  loss: 3.9230 (3.7211)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0398  max mem: 31830
Epoch: [106]  [130/312]  eta: 0:01:49  lr: 0.003131  min_lr: 0.003131  loss: 3.7855 (3.7197)  weight_decay: 0.0500 (0.0500)  time: 0.6397  data: 0.0518  max mem: 31830
Epoch: [106]  [140/312]  eta: 0:01:41  lr: 0.003131  min_lr: 0.003131  loss: 3.7480 (3.7083)  weight_decay: 0.0500 (0.0500)  time: 0.4672  data: 0.0130  max mem: 31830
Epoch: [106]  [150/312]  eta: 0:01:35  lr: 0.003130  min_lr: 0.003130  loss: 3.4305 (3.6927)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0392  max mem: 31830
Epoch: [106]  [160/312]  eta: 0:01:29  lr: 0.003130  min_lr: 0.003130  loss: 3.7081 (3.6967)  weight_decay: 0.0500 (0.0500)  time: 0.5940  data: 0.0392  max mem: 31830
Epoch: [106]  [170/312]  eta: 0:01:22  lr: 0.003129  min_lr: 0.003129  loss: 3.9476 (3.7172)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0169  max mem: 31830
Epoch: [106]  [180/312]  eta: 0:01:16  lr: 0.003129  min_lr: 0.003129  loss: 3.9756 (3.7126)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0171  max mem: 31830
Epoch: [106]  [190/312]  eta: 0:01:09  lr: 0.003128  min_lr: 0.003128  loss: 3.7335 (3.7160)  weight_decay: 0.0500 (0.0500)  time: 0.4821  data: 0.0009  max mem: 31830
Epoch: [106]  [200/312]  eta: 0:01:04  lr: 0.003127  min_lr: 0.003127  loss: 3.7335 (3.7190)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0121  max mem: 31830
Epoch: [106]  [210/312]  eta: 0:00:58  lr: 0.003127  min_lr: 0.003127  loss: 3.7259 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.5796  data: 0.0121  max mem: 31830
Epoch: [106]  [220/312]  eta: 0:00:52  lr: 0.003126  min_lr: 0.003126  loss: 3.8856 (3.7281)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0009  max mem: 31830
Epoch: [106]  [230/312]  eta: 0:00:46  lr: 0.003126  min_lr: 0.003126  loss: 3.8856 (3.7351)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.0009  max mem: 31830
Epoch: [106]  [240/312]  eta: 0:00:40  lr: 0.003125  min_lr: 0.003125  loss: 3.7535 (3.7338)  weight_decay: 0.0500 (0.0500)  time: 0.5490  data: 0.0009  max mem: 31830
Epoch: [106]  [250/312]  eta: 0:00:35  lr: 0.003124  min_lr: 0.003124  loss: 3.9123 (3.7444)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0069  max mem: 31830
Epoch: [106]  [260/312]  eta: 0:00:29  lr: 0.003124  min_lr: 0.003124  loss: 4.0158 (3.7523)  weight_decay: 0.0500 (0.0500)  time: 0.6554  data: 0.0069  max mem: 31830
Epoch: [106]  [270/312]  eta: 0:00:23  lr: 0.003123  min_lr: 0.003123  loss: 3.9354 (3.7499)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.0008  max mem: 31830
Epoch: [106]  [280/312]  eta: 0:00:18  lr: 0.003123  min_lr: 0.003123  loss: 3.7886 (3.7556)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0019  max mem: 31830
Epoch: [106]  [290/312]  eta: 0:00:12  lr: 0.003122  min_lr: 0.003122  loss: 3.7362 (3.7502)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0017  max mem: 31830
Epoch: [106]  [300/312]  eta: 0:00:06  lr: 0.003121  min_lr: 0.003121  loss: 3.5060 (3.7365)  weight_decay: 0.0500 (0.0500)  time: 0.4564  data: 0.0002  max mem: 31830
Epoch: [106]  [310/312]  eta: 0:00:01  lr: 0.003121  min_lr: 0.003121  loss: 3.7271 (3.7428)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0001  max mem: 31830
Epoch: [106]  [311/312]  eta: 0:00:00  lr: 0.003121  min_lr: 0.003121  loss: 3.7961 (3.7430)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [106] Total time: 0:02:54 (0.5580 s / it)
Averaged stats: lr: 0.003121  min_lr: 0.003121  loss: 3.7961 (3.7206)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.4580 (1.4580)  acc1: 74.3490 (74.3490)  acc5: 91.5365 (91.5365)  time: 8.5214  data: 8.3619  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8012 (1.6970)  acc1: 64.8438 (66.7840)  acc5: 86.3281 (87.2160)  time: 1.0694  data: 0.9292  max mem: 31830
Test: Total time: 0:00:09 (1.0864 s / it)
* Acc@1 66.326 Acc@5 87.584 loss 1.700
Accuracy of the model on the 50000 test images: 66.3%
Max accuracy: 67.08%
Epoch: [107]  [  0/312]  eta: 1:04:08  lr: 0.003121  min_lr: 0.003121  loss: 4.1114 (4.1114)  weight_decay: 0.0500 (0.0500)  time: 12.3336  data: 9.4364  max mem: 31830
Epoch: [107]  [ 10/312]  eta: 0:09:09  lr: 0.003120  min_lr: 0.003120  loss: 3.8977 (3.7093)  weight_decay: 0.0500 (0.0500)  time: 1.8198  data: 0.9759  max mem: 31830
Epoch: [107]  [ 20/312]  eta: 0:05:32  lr: 0.003119  min_lr: 0.003119  loss: 3.7018 (3.6518)  weight_decay: 0.0500 (0.0500)  time: 0.5795  data: 0.0652  max mem: 31830
Epoch: [107]  [ 30/312]  eta: 0:04:13  lr: 0.003119  min_lr: 0.003119  loss: 3.4100 (3.5237)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0007  max mem: 31830
Epoch: [107]  [ 40/312]  eta: 0:03:31  lr: 0.003118  min_lr: 0.003118  loss: 3.6062 (3.5602)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0008  max mem: 31830
Epoch: [107]  [ 50/312]  eta: 0:03:04  lr: 0.003118  min_lr: 0.003118  loss: 3.7514 (3.5645)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0016  max mem: 31830
Epoch: [107]  [ 60/312]  eta: 0:02:44  lr: 0.003117  min_lr: 0.003117  loss: 3.7433 (3.5790)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0016  max mem: 31830
Epoch: [107]  [ 70/312]  eta: 0:02:29  lr: 0.003116  min_lr: 0.003116  loss: 3.6401 (3.5838)  weight_decay: 0.0500 (0.0500)  time: 0.4053  data: 0.0076  max mem: 31830
Epoch: [107]  [ 80/312]  eta: 0:02:22  lr: 0.003116  min_lr: 0.003116  loss: 3.6401 (3.6065)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0713  max mem: 31830
Epoch: [107]  [ 90/312]  eta: 0:02:13  lr: 0.003115  min_lr: 0.003115  loss: 3.8782 (3.6612)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0911  max mem: 31830
Epoch: [107]  [100/312]  eta: 0:02:06  lr: 0.003115  min_lr: 0.003115  loss: 4.1086 (3.7042)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0684  max mem: 31830
Epoch: [107]  [110/312]  eta: 0:02:00  lr: 0.003114  min_lr: 0.003114  loss: 3.9539 (3.6901)  weight_decay: 0.0500 (0.0500)  time: 0.5887  data: 0.1117  max mem: 31830
Epoch: [107]  [120/312]  eta: 0:01:52  lr: 0.003114  min_lr: 0.003114  loss: 3.9117 (3.7175)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0907  max mem: 31830
Epoch: [107]  [130/312]  eta: 0:01:47  lr: 0.003113  min_lr: 0.003113  loss: 3.9789 (3.7271)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0749  max mem: 31830
Epoch: [107]  [140/312]  eta: 0:01:40  lr: 0.003112  min_lr: 0.003112  loss: 3.9741 (3.7347)  weight_decay: 0.0500 (0.0500)  time: 0.6012  data: 0.0604  max mem: 31830
Epoch: [107]  [150/312]  eta: 0:01:34  lr: 0.003112  min_lr: 0.003112  loss: 3.9315 (3.7441)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0475  max mem: 31830
Epoch: [107]  [160/312]  eta: 0:01:29  lr: 0.003111  min_lr: 0.003111  loss: 3.9476 (3.7443)  weight_decay: 0.0500 (0.0500)  time: 0.6084  data: 0.0890  max mem: 31830
Epoch: [107]  [170/312]  eta: 0:01:22  lr: 0.003111  min_lr: 0.003111  loss: 3.8780 (3.7376)  weight_decay: 0.0500 (0.0500)  time: 0.5545  data: 0.0478  max mem: 31830
Epoch: [107]  [180/312]  eta: 0:01:16  lr: 0.003110  min_lr: 0.003110  loss: 3.8780 (3.7465)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0141  max mem: 31830
Epoch: [107]  [190/312]  eta: 0:01:10  lr: 0.003109  min_lr: 0.003109  loss: 3.9223 (3.7504)  weight_decay: 0.0500 (0.0500)  time: 0.5776  data: 0.0270  max mem: 31830
Epoch: [107]  [200/312]  eta: 0:01:04  lr: 0.003109  min_lr: 0.003109  loss: 3.9082 (3.7482)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0242  max mem: 31830
Epoch: [107]  [210/312]  eta: 0:00:58  lr: 0.003108  min_lr: 0.003108  loss: 3.9082 (3.7531)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0286  max mem: 31830
Epoch: [107]  [220/312]  eta: 0:00:53  lr: 0.003108  min_lr: 0.003108  loss: 3.9626 (3.7521)  weight_decay: 0.0500 (0.0500)  time: 0.6093  data: 0.0182  max mem: 31830
Epoch: [107]  [230/312]  eta: 0:00:46  lr: 0.003107  min_lr: 0.003107  loss: 4.0493 (3.7650)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0306  max mem: 31830
Epoch: [107]  [240/312]  eta: 0:00:41  lr: 0.003106  min_lr: 0.003106  loss: 4.0364 (3.7636)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0454  max mem: 31830
Epoch: [107]  [250/312]  eta: 0:00:35  lr: 0.003106  min_lr: 0.003106  loss: 3.9300 (3.7655)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0299  max mem: 31830
Epoch: [107]  [260/312]  eta: 0:00:29  lr: 0.003105  min_lr: 0.003105  loss: 3.8830 (3.7464)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0318  max mem: 31830
Epoch: [107]  [270/312]  eta: 0:00:23  lr: 0.003105  min_lr: 0.003105  loss: 3.2950 (3.7406)  weight_decay: 0.0500 (0.0500)  time: 0.6150  data: 0.0543  max mem: 31830
Epoch: [107]  [280/312]  eta: 0:00:18  lr: 0.003104  min_lr: 0.003104  loss: 3.6424 (3.7418)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0392  max mem: 31830
Epoch: [107]  [290/312]  eta: 0:00:12  lr: 0.003103  min_lr: 0.003103  loss: 3.8029 (3.7409)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0366  max mem: 31830
Epoch: [107]  [300/312]  eta: 0:00:06  lr: 0.003103  min_lr: 0.003103  loss: 3.6698 (3.7329)  weight_decay: 0.0500 (0.0500)  time: 0.5157  data: 0.0348  max mem: 31830
Epoch: [107]  [310/312]  eta: 0:00:01  lr: 0.003102  min_lr: 0.003102  loss: 3.6698 (3.7289)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [107]  [311/312]  eta: 0:00:00  lr: 0.003102  min_lr: 0.003102  loss: 3.6698 (3.7283)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [107] Total time: 0:02:54 (0.5598 s / it)
Averaged stats: lr: 0.003102  min_lr: 0.003102  loss: 3.6698 (3.7129)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.5242 (1.5242)  acc1: 71.6146 (71.6146)  acc5: 91.4062 (91.4062)  time: 8.2084  data: 8.0425  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9494 (1.8166)  acc1: 64.1927 (65.4080)  acc5: 85.6771 (86.5440)  time: 1.0308  data: 0.8937  max mem: 31830
Test: Total time: 0:00:09 (1.0430 s / it)
* Acc@1 64.924 Acc@5 86.814 loss 1.824
Accuracy of the model on the 50000 test images: 64.9%
Max accuracy: 67.08%
Epoch: [108]  [  0/312]  eta: 0:57:12  lr: 0.003102  min_lr: 0.003102  loss: 3.9615 (3.9615)  weight_decay: 0.0500 (0.0500)  time: 11.0020  data: 9.5990  max mem: 31830
Epoch: [108]  [ 10/312]  eta: 0:08:24  lr: 0.003101  min_lr: 0.003101  loss: 3.9615 (3.6682)  weight_decay: 0.0500 (0.0500)  time: 1.6720  data: 1.0118  max mem: 31830
Epoch: [108]  [ 20/312]  eta: 0:05:28  lr: 0.003101  min_lr: 0.003101  loss: 3.7990 (3.6623)  weight_decay: 0.0500 (0.0500)  time: 0.6321  data: 0.0888  max mem: 31830
Epoch: [108]  [ 30/312]  eta: 0:04:11  lr: 0.003100  min_lr: 0.003100  loss: 3.5034 (3.5434)  weight_decay: 0.0500 (0.0500)  time: 0.4617  data: 0.0126  max mem: 31830
Epoch: [108]  [ 40/312]  eta: 0:03:29  lr: 0.003100  min_lr: 0.003100  loss: 3.5034 (3.5635)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0008  max mem: 31830
Epoch: [108]  [ 50/312]  eta: 0:03:05  lr: 0.003099  min_lr: 0.003099  loss: 3.9035 (3.6516)  weight_decay: 0.0500 (0.0500)  time: 0.4198  data: 0.0015  max mem: 31830
Epoch: [108]  [ 60/312]  eta: 0:02:45  lr: 0.003098  min_lr: 0.003098  loss: 3.7264 (3.6096)  weight_decay: 0.0500 (0.0500)  time: 0.4198  data: 0.0015  max mem: 31830
Epoch: [108]  [ 70/312]  eta: 0:02:34  lr: 0.003098  min_lr: 0.003098  loss: 3.4652 (3.6012)  weight_decay: 0.0500 (0.0500)  time: 0.4718  data: 0.0529  max mem: 31830
Epoch: [108]  [ 80/312]  eta: 0:02:24  lr: 0.003097  min_lr: 0.003097  loss: 3.6740 (3.6186)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.1064  max mem: 31830
Epoch: [108]  [ 90/312]  eta: 0:02:17  lr: 0.003097  min_lr: 0.003097  loss: 3.5083 (3.5984)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0684  max mem: 31830
Epoch: [108]  [100/312]  eta: 0:02:12  lr: 0.003096  min_lr: 0.003096  loss: 3.5133 (3.5969)  weight_decay: 0.0500 (0.0500)  time: 0.6266  data: 0.0451  max mem: 31830
Epoch: [108]  [110/312]  eta: 0:02:01  lr: 0.003095  min_lr: 0.003095  loss: 4.0081 (3.6458)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0314  max mem: 31830
Epoch: [108]  [120/312]  eta: 0:01:56  lr: 0.003095  min_lr: 0.003095  loss: 4.0276 (3.6538)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0148  max mem: 31830
Epoch: [108]  [130/312]  eta: 0:01:50  lr: 0.003094  min_lr: 0.003094  loss: 3.8651 (3.6576)  weight_decay: 0.0500 (0.0500)  time: 0.6305  data: 0.0285  max mem: 31830
Epoch: [108]  [140/312]  eta: 0:01:42  lr: 0.003094  min_lr: 0.003094  loss: 3.9261 (3.6667)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0149  max mem: 31830
Epoch: [108]  [150/312]  eta: 0:01:37  lr: 0.003093  min_lr: 0.003093  loss: 3.9261 (3.6740)  weight_decay: 0.0500 (0.0500)  time: 0.5463  data: 0.0009  max mem: 31830
Epoch: [108]  [160/312]  eta: 0:01:29  lr: 0.003092  min_lr: 0.003092  loss: 3.9410 (3.6852)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0008  max mem: 31830
Epoch: [108]  [170/312]  eta: 0:01:23  lr: 0.003092  min_lr: 0.003092  loss: 4.0184 (3.7053)  weight_decay: 0.0500 (0.0500)  time: 0.4876  data: 0.0007  max mem: 31830
Epoch: [108]  [180/312]  eta: 0:01:17  lr: 0.003091  min_lr: 0.003091  loss: 4.0012 (3.7178)  weight_decay: 0.0500 (0.0500)  time: 0.6083  data: 0.0136  max mem: 31830
Epoch: [108]  [190/312]  eta: 0:01:10  lr: 0.003091  min_lr: 0.003091  loss: 3.8250 (3.7103)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.0137  max mem: 31830
Epoch: [108]  [200/312]  eta: 0:01:05  lr: 0.003090  min_lr: 0.003090  loss: 3.7235 (3.7198)  weight_decay: 0.0500 (0.0500)  time: 0.5031  data: 0.0020  max mem: 31830
Epoch: [108]  [210/312]  eta: 0:00:59  lr: 0.003089  min_lr: 0.003089  loss: 3.7235 (3.7072)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.0023  max mem: 31830
Epoch: [108]  [220/312]  eta: 0:00:52  lr: 0.003089  min_lr: 0.003089  loss: 3.5331 (3.6955)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0011  max mem: 31830
Epoch: [108]  [230/312]  eta: 0:00:47  lr: 0.003088  min_lr: 0.003088  loss: 3.5331 (3.6948)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0007  max mem: 31830
Epoch: [108]  [240/312]  eta: 0:00:41  lr: 0.003088  min_lr: 0.003088  loss: 3.8665 (3.7027)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0189  max mem: 31830
Epoch: [108]  [250/312]  eta: 0:00:35  lr: 0.003087  min_lr: 0.003087  loss: 3.8665 (3.6924)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0188  max mem: 31830
Epoch: [108]  [260/312]  eta: 0:00:29  lr: 0.003086  min_lr: 0.003086  loss: 3.0794 (3.6743)  weight_decay: 0.0500 (0.0500)  time: 0.6135  data: 0.0008  max mem: 31830
Epoch: [108]  [270/312]  eta: 0:00:23  lr: 0.003086  min_lr: 0.003086  loss: 3.4029 (3.6809)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0008  max mem: 31830
Epoch: [108]  [280/312]  eta: 0:00:18  lr: 0.003085  min_lr: 0.003085  loss: 3.8737 (3.6856)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.0020  max mem: 31830
Epoch: [108]  [290/312]  eta: 0:00:12  lr: 0.003085  min_lr: 0.003085  loss: 3.7584 (3.6809)  weight_decay: 0.0500 (0.0500)  time: 0.5946  data: 0.0018  max mem: 31830
Epoch: [108]  [300/312]  eta: 0:00:06  lr: 0.003084  min_lr: 0.003084  loss: 3.6723 (3.6771)  weight_decay: 0.0500 (0.0500)  time: 0.4409  data: 0.0002  max mem: 31830
Epoch: [108]  [310/312]  eta: 0:00:01  lr: 0.003083  min_lr: 0.003083  loss: 3.8853 (3.6836)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [108]  [311/312]  eta: 0:00:00  lr: 0.003083  min_lr: 0.003083  loss: 3.8222 (3.6834)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [108] Total time: 0:02:55 (0.5611 s / it)
Averaged stats: lr: 0.003083  min_lr: 0.003083  loss: 3.8222 (3.7026)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4991 (1.4991)  acc1: 74.3490 (74.3490)  acc5: 89.8438 (89.8438)  time: 8.4266  data: 8.2676  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9057 (1.7920)  acc1: 64.8438 (65.3280)  acc5: 87.6302 (86.6560)  time: 1.0530  data: 0.9187  max mem: 31830
Test: Total time: 0:00:09 (1.0705 s / it)
* Acc@1 64.876 Acc@5 86.846 loss 1.785
Accuracy of the model on the 50000 test images: 64.9%
Max accuracy: 67.08%
Epoch: [109]  [  0/312]  eta: 1:00:50  lr: 0.003083  min_lr: 0.003083  loss: 2.8384 (2.8384)  weight_decay: 0.0500 (0.0500)  time: 11.6989  data: 8.8633  max mem: 31830
Epoch: [109]  [ 10/312]  eta: 0:09:12  lr: 0.003083  min_lr: 0.003083  loss: 3.8376 (3.5790)  weight_decay: 0.0500 (0.0500)  time: 1.8287  data: 1.0017  max mem: 31830
Epoch: [109]  [ 20/312]  eta: 0:05:33  lr: 0.003082  min_lr: 0.003082  loss: 3.6806 (3.6060)  weight_decay: 0.0500 (0.0500)  time: 0.6143  data: 0.1081  max mem: 31830
Epoch: [109]  [ 30/312]  eta: 0:04:14  lr: 0.003081  min_lr: 0.003081  loss: 3.6806 (3.6713)  weight_decay: 0.0500 (0.0500)  time: 0.3906  data: 0.0009  max mem: 31830
Epoch: [109]  [ 40/312]  eta: 0:03:31  lr: 0.003081  min_lr: 0.003081  loss: 3.8683 (3.6661)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0011  max mem: 31830
Epoch: [109]  [ 50/312]  eta: 0:03:04  lr: 0.003080  min_lr: 0.003080  loss: 3.8519 (3.6595)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0009  max mem: 31830
Epoch: [109]  [ 60/312]  eta: 0:02:44  lr: 0.003080  min_lr: 0.003080  loss: 3.8519 (3.6881)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0009  max mem: 31830
Epoch: [109]  [ 70/312]  eta: 0:02:29  lr: 0.003079  min_lr: 0.003079  loss: 3.7975 (3.7072)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0015  max mem: 31830
Epoch: [109]  [ 80/312]  eta: 0:02:20  lr: 0.003078  min_lr: 0.003078  loss: 3.5473 (3.6779)  weight_decay: 0.0500 (0.0500)  time: 0.4646  data: 0.0136  max mem: 31830
Epoch: [109]  [ 90/312]  eta: 0:02:13  lr: 0.003078  min_lr: 0.003078  loss: 3.7065 (3.7052)  weight_decay: 0.0500 (0.0500)  time: 0.5480  data: 0.0379  max mem: 31830
Epoch: [109]  [100/312]  eta: 0:02:05  lr: 0.003077  min_lr: 0.003077  loss: 3.6636 (3.6744)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0258  max mem: 31830
Epoch: [109]  [110/312]  eta: 0:02:00  lr: 0.003077  min_lr: 0.003077  loss: 3.6190 (3.6760)  weight_decay: 0.0500 (0.0500)  time: 0.5563  data: 0.0313  max mem: 31830
Epoch: [109]  [120/312]  eta: 0:01:51  lr: 0.003076  min_lr: 0.003076  loss: 3.7486 (3.6758)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0439  max mem: 31830
Epoch: [109]  [130/312]  eta: 0:01:45  lr: 0.003075  min_lr: 0.003075  loss: 3.8855 (3.6960)  weight_decay: 0.0500 (0.0500)  time: 0.5060  data: 0.0188  max mem: 31830
Epoch: [109]  [140/312]  eta: 0:01:40  lr: 0.003075  min_lr: 0.003075  loss: 3.8200 (3.6801)  weight_decay: 0.0500 (0.0500)  time: 0.5893  data: 0.0168  max mem: 31830
Epoch: [109]  [150/312]  eta: 0:01:33  lr: 0.003074  min_lr: 0.003074  loss: 3.6610 (3.6942)  weight_decay: 0.0500 (0.0500)  time: 0.5489  data: 0.0248  max mem: 31830
Epoch: [109]  [160/312]  eta: 0:01:28  lr: 0.003074  min_lr: 0.003074  loss: 3.9518 (3.6909)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0143  max mem: 31830
Epoch: [109]  [170/312]  eta: 0:01:21  lr: 0.003073  min_lr: 0.003073  loss: 3.5144 (3.6760)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.0126  max mem: 31830
Epoch: [109]  [180/312]  eta: 0:01:15  lr: 0.003072  min_lr: 0.003072  loss: 3.8805 (3.6924)  weight_decay: 0.0500 (0.0500)  time: 0.4983  data: 0.0181  max mem: 31830
Epoch: [109]  [190/312]  eta: 0:01:09  lr: 0.003072  min_lr: 0.003072  loss: 3.6801 (3.6673)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0064  max mem: 31830
Epoch: [109]  [200/312]  eta: 0:01:03  lr: 0.003071  min_lr: 0.003071  loss: 3.2976 (3.6670)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0013  max mem: 31830
Epoch: [109]  [210/312]  eta: 0:00:57  lr: 0.003071  min_lr: 0.003071  loss: 3.5531 (3.6654)  weight_decay: 0.0500 (0.0500)  time: 0.5067  data: 0.0013  max mem: 31830
Epoch: [109]  [220/312]  eta: 0:00:52  lr: 0.003070  min_lr: 0.003070  loss: 3.3262 (3.6471)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.0135  max mem: 31830
Epoch: [109]  [230/312]  eta: 0:00:46  lr: 0.003069  min_lr: 0.003069  loss: 3.6892 (3.6594)  weight_decay: 0.0500 (0.0500)  time: 0.5354  data: 0.0265  max mem: 31830
Epoch: [109]  [240/312]  eta: 0:00:40  lr: 0.003069  min_lr: 0.003069  loss: 3.9700 (3.6587)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0143  max mem: 31830
Epoch: [109]  [250/312]  eta: 0:00:34  lr: 0.003068  min_lr: 0.003068  loss: 3.8315 (3.6560)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0080  max mem: 31830
Epoch: [109]  [260/312]  eta: 0:00:29  lr: 0.003067  min_lr: 0.003067  loss: 3.6897 (3.6579)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0075  max mem: 31830
Epoch: [109]  [270/312]  eta: 0:00:23  lr: 0.003067  min_lr: 0.003067  loss: 3.8429 (3.6631)  weight_decay: 0.0500 (0.0500)  time: 0.5676  data: 0.0141  max mem: 31830
Epoch: [109]  [280/312]  eta: 0:00:17  lr: 0.003066  min_lr: 0.003066  loss: 3.8429 (3.6692)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0151  max mem: 31830
Epoch: [109]  [290/312]  eta: 0:00:12  lr: 0.003066  min_lr: 0.003066  loss: 3.7151 (3.6655)  weight_decay: 0.0500 (0.0500)  time: 0.5716  data: 0.0145  max mem: 31830
Epoch: [109]  [300/312]  eta: 0:00:06  lr: 0.003065  min_lr: 0.003065  loss: 3.7235 (3.6738)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0185  max mem: 31830
Epoch: [109]  [310/312]  eta: 0:00:01  lr: 0.003064  min_lr: 0.003064  loss: 4.0181 (3.6777)  weight_decay: 0.0500 (0.0500)  time: 0.3865  data: 0.0054  max mem: 31830
Epoch: [109]  [311/312]  eta: 0:00:00  lr: 0.003064  min_lr: 0.003064  loss: 3.9159 (3.6784)  weight_decay: 0.0500 (0.0500)  time: 0.3860  data: 0.0054  max mem: 31830
Epoch: [109] Total time: 0:02:53 (0.5552 s / it)
Averaged stats: lr: 0.003064  min_lr: 0.003064  loss: 3.9159 (3.6987)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.3547 (1.3547)  acc1: 73.5677 (73.5677)  acc5: 90.6250 (90.6250)  time: 8.7434  data: 8.5821  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7033 (1.6177)  acc1: 65.6250 (66.3520)  acc5: 88.1510 (87.4240)  time: 1.0912  data: 0.9537  max mem: 31830
Test: Total time: 0:00:10 (1.1237 s / it)
* Acc@1 66.376 Acc@5 87.834 loss 1.626
Accuracy of the model on the 50000 test images: 66.4%
Max accuracy: 67.08%
Epoch: [110]  [  0/312]  eta: 0:59:42  lr: 0.003064  min_lr: 0.003064  loss: 4.0634 (4.0634)  weight_decay: 0.0500 (0.0500)  time: 11.4815  data: 10.9926  max mem: 31830
Epoch: [110]  [ 10/312]  eta: 0:08:37  lr: 0.003064  min_lr: 0.003064  loss: 4.0213 (3.8618)  weight_decay: 0.0500 (0.0500)  time: 1.7142  data: 0.9998  max mem: 31830
Epoch: [110]  [ 20/312]  eta: 0:05:27  lr: 0.003063  min_lr: 0.003063  loss: 3.8606 (3.6064)  weight_decay: 0.0500 (0.0500)  time: 0.6042  data: 0.0412  max mem: 31830
Epoch: [110]  [ 30/312]  eta: 0:04:10  lr: 0.003062  min_lr: 0.003062  loss: 3.3415 (3.5717)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0416  max mem: 31830
Epoch: [110]  [ 40/312]  eta: 0:03:28  lr: 0.003062  min_lr: 0.003062  loss: 3.8853 (3.6560)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0011  max mem: 31830
Epoch: [110]  [ 50/312]  eta: 0:03:02  lr: 0.003061  min_lr: 0.003061  loss: 4.1146 (3.7244)  weight_decay: 0.0500 (0.0500)  time: 0.4014  data: 0.0007  max mem: 31830
Epoch: [110]  [ 60/312]  eta: 0:02:43  lr: 0.003061  min_lr: 0.003061  loss: 3.9776 (3.7433)  weight_decay: 0.0500 (0.0500)  time: 0.4018  data: 0.0006  max mem: 31830
Epoch: [110]  [ 70/312]  eta: 0:02:33  lr: 0.003060  min_lr: 0.003060  loss: 3.9209 (3.7430)  weight_decay: 0.0500 (0.0500)  time: 0.4725  data: 0.0260  max mem: 31830
Epoch: [110]  [ 80/312]  eta: 0:02:24  lr: 0.003059  min_lr: 0.003059  loss: 3.7722 (3.7474)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0509  max mem: 31830
Epoch: [110]  [ 90/312]  eta: 0:02:15  lr: 0.003059  min_lr: 0.003059  loss: 3.8730 (3.7618)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0588  max mem: 31830
Epoch: [110]  [100/312]  eta: 0:02:08  lr: 0.003058  min_lr: 0.003058  loss: 3.6785 (3.7321)  weight_decay: 0.0500 (0.0500)  time: 0.5481  data: 0.0729  max mem: 31830
Epoch: [110]  [110/312]  eta: 0:01:59  lr: 0.003058  min_lr: 0.003058  loss: 3.5423 (3.7176)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0396  max mem: 31830
Epoch: [110]  [120/312]  eta: 0:01:53  lr: 0.003057  min_lr: 0.003057  loss: 3.6275 (3.7177)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0480  max mem: 31830
Epoch: [110]  [130/312]  eta: 0:01:46  lr: 0.003056  min_lr: 0.003056  loss: 3.9792 (3.7239)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0700  max mem: 31830
Epoch: [110]  [140/312]  eta: 0:01:38  lr: 0.003056  min_lr: 0.003056  loss: 3.7384 (3.7139)  weight_decay: 0.0500 (0.0500)  time: 0.4804  data: 0.0233  max mem: 31830
Epoch: [110]  [150/312]  eta: 0:01:33  lr: 0.003055  min_lr: 0.003055  loss: 3.5451 (3.7012)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0481  max mem: 31830
Epoch: [110]  [160/312]  eta: 0:01:27  lr: 0.003055  min_lr: 0.003055  loss: 3.7539 (3.7121)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0865  max mem: 31830
Epoch: [110]  [170/312]  eta: 0:01:20  lr: 0.003054  min_lr: 0.003054  loss: 3.9966 (3.7257)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0736  max mem: 31830
Epoch: [110]  [180/312]  eta: 0:01:15  lr: 0.003053  min_lr: 0.003053  loss: 3.9259 (3.7238)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0997  max mem: 31830
Epoch: [110]  [190/312]  eta: 0:01:08  lr: 0.003053  min_lr: 0.003053  loss: 3.6165 (3.7100)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0658  max mem: 31830
Epoch: [110]  [200/312]  eta: 0:01:03  lr: 0.003052  min_lr: 0.003052  loss: 3.6447 (3.7173)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0476  max mem: 31830
Epoch: [110]  [210/312]  eta: 0:00:57  lr: 0.003051  min_lr: 0.003051  loss: 3.6596 (3.7142)  weight_decay: 0.0500 (0.0500)  time: 0.6164  data: 0.0857  max mem: 31830
Epoch: [110]  [220/312]  eta: 0:00:51  lr: 0.003051  min_lr: 0.003051  loss: 3.7467 (3.7150)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0389  max mem: 31830
Epoch: [110]  [230/312]  eta: 0:00:46  lr: 0.003050  min_lr: 0.003050  loss: 3.9204 (3.7196)  weight_decay: 0.0500 (0.0500)  time: 0.5441  data: 0.0312  max mem: 31830
Epoch: [110]  [240/312]  eta: 0:00:40  lr: 0.003050  min_lr: 0.003050  loss: 3.9176 (3.7139)  weight_decay: 0.0500 (0.0500)  time: 0.5807  data: 0.0439  max mem: 31830
Epoch: [110]  [250/312]  eta: 0:00:34  lr: 0.003049  min_lr: 0.003049  loss: 3.7208 (3.7083)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0416  max mem: 31830
Epoch: [110]  [260/312]  eta: 0:00:29  lr: 0.003048  min_lr: 0.003048  loss: 3.7717 (3.7091)  weight_decay: 0.0500 (0.0500)  time: 0.5719  data: 0.0292  max mem: 31830
Epoch: [110]  [270/312]  eta: 0:00:23  lr: 0.003048  min_lr: 0.003048  loss: 3.7790 (3.7136)  weight_decay: 0.0500 (0.0500)  time: 0.4728  data: 0.0010  max mem: 31830
Epoch: [110]  [280/312]  eta: 0:00:17  lr: 0.003047  min_lr: 0.003047  loss: 3.7063 (3.7066)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0295  max mem: 31830
Epoch: [110]  [290/312]  eta: 0:00:12  lr: 0.003047  min_lr: 0.003047  loss: 3.6402 (3.7048)  weight_decay: 0.0500 (0.0500)  time: 0.5747  data: 0.0418  max mem: 31830
Epoch: [110]  [300/312]  eta: 0:00:06  lr: 0.003046  min_lr: 0.003046  loss: 3.6402 (3.6933)  weight_decay: 0.0500 (0.0500)  time: 0.4607  data: 0.0127  max mem: 31830
Epoch: [110]  [310/312]  eta: 0:00:01  lr: 0.003045  min_lr: 0.003045  loss: 3.6602 (3.6907)  weight_decay: 0.0500 (0.0500)  time: 0.3893  data: 0.0001  max mem: 31830
Epoch: [110]  [311/312]  eta: 0:00:00  lr: 0.003045  min_lr: 0.003045  loss: 3.6602 (3.6915)  weight_decay: 0.0500 (0.0500)  time: 0.3886  data: 0.0001  max mem: 31830
Epoch: [110] Total time: 0:02:51 (0.5507 s / it)
Averaged stats: lr: 0.003045  min_lr: 0.003045  loss: 3.6602 (3.7082)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.2785 (1.2785)  acc1: 73.9583 (73.9583)  acc5: 92.5781 (92.5781)  time: 8.1647  data: 7.9978  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6712 (1.5972)  acc1: 64.8438 (65.6320)  acc5: 87.7604 (87.5200)  time: 1.0447  data: 0.9069  max mem: 31830
Test: Total time: 0:00:09 (1.0563 s / it)
* Acc@1 65.790 Acc@5 87.760 loss 1.595
Accuracy of the model on the 50000 test images: 65.8%
Max accuracy: 67.08%
Epoch: [111]  [  0/312]  eta: 1:01:50  lr: 0.003045  min_lr: 0.003045  loss: 4.0583 (4.0583)  weight_decay: 0.0500 (0.0500)  time: 11.8919  data: 11.4782  max mem: 31830
Epoch: [111]  [ 10/312]  eta: 0:09:01  lr: 0.003045  min_lr: 0.003045  loss: 3.3748 (3.4386)  weight_decay: 0.0500 (0.0500)  time: 1.7921  data: 1.0453  max mem: 31830
Epoch: [111]  [ 20/312]  eta: 0:05:29  lr: 0.003044  min_lr: 0.003044  loss: 3.3748 (3.5218)  weight_decay: 0.0500 (0.0500)  time: 0.5894  data: 0.0014  max mem: 31830
Epoch: [111]  [ 30/312]  eta: 0:04:11  lr: 0.003043  min_lr: 0.003043  loss: 3.5673 (3.5321)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0007  max mem: 31830
Epoch: [111]  [ 40/312]  eta: 0:03:30  lr: 0.003043  min_lr: 0.003043  loss: 3.6965 (3.6189)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0007  max mem: 31830
Epoch: [111]  [ 50/312]  eta: 0:03:03  lr: 0.003042  min_lr: 0.003042  loss: 3.8299 (3.5846)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0008  max mem: 31830
Epoch: [111]  [ 60/312]  eta: 0:02:43  lr: 0.003042  min_lr: 0.003042  loss: 3.8628 (3.6783)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0010  max mem: 31830
Epoch: [111]  [ 70/312]  eta: 0:02:29  lr: 0.003041  min_lr: 0.003041  loss: 4.1020 (3.7255)  weight_decay: 0.0500 (0.0500)  time: 0.4097  data: 0.0015  max mem: 31830
Epoch: [111]  [ 80/312]  eta: 0:02:23  lr: 0.003040  min_lr: 0.003040  loss: 4.0525 (3.7737)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0070  max mem: 31830
Epoch: [111]  [ 90/312]  eta: 0:02:15  lr: 0.003040  min_lr: 0.003040  loss: 3.9825 (3.7650)  weight_decay: 0.0500 (0.0500)  time: 0.5754  data: 0.0064  max mem: 31830
Epoch: [111]  [100/312]  eta: 0:02:06  lr: 0.003039  min_lr: 0.003039  loss: 3.9033 (3.7681)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0204  max mem: 31830
Epoch: [111]  [110/312]  eta: 0:02:01  lr: 0.003038  min_lr: 0.003038  loss: 3.6907 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 0.5608  data: 0.0343  max mem: 31830
Epoch: [111]  [120/312]  eta: 0:01:52  lr: 0.003038  min_lr: 0.003038  loss: 3.6285 (3.7515)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0148  max mem: 31830
Epoch: [111]  [130/312]  eta: 0:01:47  lr: 0.003037  min_lr: 0.003037  loss: 3.9802 (3.7612)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0363  max mem: 31830
Epoch: [111]  [140/312]  eta: 0:01:40  lr: 0.003037  min_lr: 0.003037  loss: 4.0442 (3.7702)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0362  max mem: 31830
Epoch: [111]  [150/312]  eta: 0:01:34  lr: 0.003036  min_lr: 0.003036  loss: 3.9512 (3.7757)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0364  max mem: 31830
Epoch: [111]  [160/312]  eta: 0:01:29  lr: 0.003035  min_lr: 0.003035  loss: 3.7090 (3.7592)  weight_decay: 0.0500 (0.0500)  time: 0.6474  data: 0.0551  max mem: 31830
Epoch: [111]  [170/312]  eta: 0:01:22  lr: 0.003035  min_lr: 0.003035  loss: 3.4591 (3.7445)  weight_decay: 0.0500 (0.0500)  time: 0.5573  data: 0.0195  max mem: 31830
Epoch: [111]  [180/312]  eta: 0:01:17  lr: 0.003034  min_lr: 0.003034  loss: 3.8423 (3.7488)  weight_decay: 0.0500 (0.0500)  time: 0.5725  data: 0.0140  max mem: 31830
Epoch: [111]  [190/312]  eta: 0:01:12  lr: 0.003034  min_lr: 0.003034  loss: 3.8423 (3.7444)  weight_decay: 0.0500 (0.0500)  time: 0.6958  data: 0.0287  max mem: 31830
Epoch: [111]  [200/312]  eta: 0:01:05  lr: 0.003033  min_lr: 0.003033  loss: 3.7253 (3.7465)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0156  max mem: 31830
Epoch: [111]  [210/312]  eta: 0:00:59  lr: 0.003032  min_lr: 0.003032  loss: 3.8874 (3.7496)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0010  max mem: 31830
Epoch: [111]  [220/312]  eta: 0:00:53  lr: 0.003032  min_lr: 0.003032  loss: 3.7950 (3.7493)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0008  max mem: 31830
Epoch: [111]  [230/312]  eta: 0:00:47  lr: 0.003031  min_lr: 0.003031  loss: 3.8248 (3.7553)  weight_decay: 0.0500 (0.0500)  time: 0.5405  data: 0.0007  max mem: 31830
Epoch: [111]  [240/312]  eta: 0:00:42  lr: 0.003030  min_lr: 0.003030  loss: 3.9175 (3.7591)  weight_decay: 0.0500 (0.0500)  time: 0.7200  data: 0.0010  max mem: 31830
Epoch: [111]  [250/312]  eta: 0:00:36  lr: 0.003030  min_lr: 0.003030  loss: 3.9175 (3.7524)  weight_decay: 0.0500 (0.0500)  time: 0.5789  data: 0.0010  max mem: 31830
Epoch: [111]  [260/312]  eta: 0:00:30  lr: 0.003029  min_lr: 0.003029  loss: 3.5603 (3.7417)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0017  max mem: 31830
Epoch: [111]  [270/312]  eta: 0:00:24  lr: 0.003029  min_lr: 0.003029  loss: 3.9034 (3.7472)  weight_decay: 0.0500 (0.0500)  time: 0.6080  data: 0.0019  max mem: 31830
Epoch: [111]  [280/312]  eta: 0:00:18  lr: 0.003028  min_lr: 0.003028  loss: 3.6055 (3.7404)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0046  max mem: 31830
Epoch: [111]  [290/312]  eta: 0:00:12  lr: 0.003027  min_lr: 0.003027  loss: 3.7304 (3.7423)  weight_decay: 0.0500 (0.0500)  time: 0.4606  data: 0.0040  max mem: 31830
Epoch: [111]  [300/312]  eta: 0:00:06  lr: 0.003027  min_lr: 0.003027  loss: 3.9524 (3.7474)  weight_decay: 0.0500 (0.0500)  time: 0.4506  data: 0.0002  max mem: 31830
Epoch: [111]  [310/312]  eta: 0:00:01  lr: 0.003026  min_lr: 0.003026  loss: 3.6508 (3.7409)  weight_decay: 0.0500 (0.0500)  time: 0.3804  data: 0.0001  max mem: 31830
Epoch: [111]  [311/312]  eta: 0:00:00  lr: 0.003026  min_lr: 0.003026  loss: 3.6508 (3.7422)  weight_decay: 0.0500 (0.0500)  time: 0.3804  data: 0.0001  max mem: 31830
Epoch: [111] Total time: 0:02:56 (0.5664 s / it)
Averaged stats: lr: 0.003026  min_lr: 0.003026  loss: 3.6508 (3.7013)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.7503 (1.7503)  acc1: 69.0104 (69.0104)  acc5: 89.5833 (89.5833)  time: 8.0861  data: 7.9273  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.1737 (2.0093)  acc1: 60.9375 (62.3360)  acc5: 83.7240 (85.3120)  time: 1.0168  data: 0.8809  max mem: 31830
Test: Total time: 0:00:09 (1.0271 s / it)
* Acc@1 62.644 Acc@5 85.228 loss 2.004
Accuracy of the model on the 50000 test images: 62.6%
Max accuracy: 67.08%
Epoch: [112]  [  0/312]  eta: 1:04:06  lr: 0.003026  min_lr: 0.003026  loss: 3.9253 (3.9253)  weight_decay: 0.0500 (0.0500)  time: 12.3296  data: 11.9334  max mem: 31830
Epoch: [112]  [ 10/312]  eta: 0:09:00  lr: 0.003025  min_lr: 0.003025  loss: 3.9877 (3.9883)  weight_decay: 0.0500 (0.0500)  time: 1.7887  data: 1.0858  max mem: 31830
Epoch: [112]  [ 20/312]  eta: 0:05:39  lr: 0.003025  min_lr: 0.003025  loss: 3.9628 (3.9309)  weight_decay: 0.0500 (0.0500)  time: 0.6045  data: 0.0450  max mem: 31830
Epoch: [112]  [ 30/312]  eta: 0:04:17  lr: 0.003024  min_lr: 0.003024  loss: 3.7874 (3.8714)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0448  max mem: 31830
Epoch: [112]  [ 40/312]  eta: 0:03:34  lr: 0.003024  min_lr: 0.003024  loss: 3.3698 (3.7263)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0007  max mem: 31830
Epoch: [112]  [ 50/312]  eta: 0:03:06  lr: 0.003023  min_lr: 0.003023  loss: 3.2658 (3.7035)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0008  max mem: 31830
Epoch: [112]  [ 60/312]  eta: 0:02:46  lr: 0.003022  min_lr: 0.003022  loss: 3.7254 (3.7142)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0008  max mem: 31830
Epoch: [112]  [ 70/312]  eta: 0:02:30  lr: 0.003022  min_lr: 0.003022  loss: 3.6471 (3.6802)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0008  max mem: 31830
Epoch: [112]  [ 80/312]  eta: 0:02:21  lr: 0.003021  min_lr: 0.003021  loss: 3.3634 (3.6696)  weight_decay: 0.0500 (0.0500)  time: 0.4626  data: 0.0129  max mem: 31830
Epoch: [112]  [ 90/312]  eta: 0:02:13  lr: 0.003020  min_lr: 0.003020  loss: 3.7560 (3.6659)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0240  max mem: 31830
Epoch: [112]  [100/312]  eta: 0:02:07  lr: 0.003020  min_lr: 0.003020  loss: 3.7734 (3.6656)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.0255  max mem: 31830
Epoch: [112]  [110/312]  eta: 0:01:59  lr: 0.003019  min_lr: 0.003019  loss: 3.8767 (3.6693)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0145  max mem: 31830
Epoch: [112]  [120/312]  eta: 0:01:52  lr: 0.003019  min_lr: 0.003019  loss: 3.5849 (3.6578)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0140  max mem: 31830
Epoch: [112]  [130/312]  eta: 0:01:46  lr: 0.003018  min_lr: 0.003018  loss: 3.9082 (3.6727)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0261  max mem: 31830
Epoch: [112]  [140/312]  eta: 0:01:40  lr: 0.003017  min_lr: 0.003017  loss: 3.7718 (3.6550)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.0130  max mem: 31830
Epoch: [112]  [150/312]  eta: 0:01:33  lr: 0.003017  min_lr: 0.003017  loss: 3.6659 (3.6743)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0150  max mem: 31830
Epoch: [112]  [160/312]  eta: 0:01:27  lr: 0.003016  min_lr: 0.003016  loss: 3.6213 (3.6612)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0149  max mem: 31830
Epoch: [112]  [170/312]  eta: 0:01:21  lr: 0.003016  min_lr: 0.003016  loss: 3.8362 (3.6735)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0006  max mem: 31830
Epoch: [112]  [180/312]  eta: 0:01:16  lr: 0.003015  min_lr: 0.003015  loss: 3.9847 (3.6931)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.0007  max mem: 31830
Epoch: [112]  [190/312]  eta: 0:01:11  lr: 0.003014  min_lr: 0.003014  loss: 4.0269 (3.7088)  weight_decay: 0.0500 (0.0500)  time: 0.6796  data: 0.0007  max mem: 31830
Epoch: [112]  [200/312]  eta: 0:01:04  lr: 0.003014  min_lr: 0.003014  loss: 3.9452 (3.7105)  weight_decay: 0.0500 (0.0500)  time: 0.5262  data: 0.0136  max mem: 31830
Epoch: [112]  [210/312]  eta: 0:00:59  lr: 0.003013  min_lr: 0.003013  loss: 3.9395 (3.7152)  weight_decay: 0.0500 (0.0500)  time: 0.5617  data: 0.0212  max mem: 31830
Epoch: [112]  [220/312]  eta: 0:00:53  lr: 0.003012  min_lr: 0.003012  loss: 3.9934 (3.7206)  weight_decay: 0.0500 (0.0500)  time: 0.6580  data: 0.0084  max mem: 31830
Epoch: [112]  [230/312]  eta: 0:00:47  lr: 0.003012  min_lr: 0.003012  loss: 4.0276 (3.7260)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0010  max mem: 31830
Epoch: [112]  [240/312]  eta: 0:00:41  lr: 0.003011  min_lr: 0.003011  loss: 3.9704 (3.7331)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0260  max mem: 31830
Epoch: [112]  [250/312]  eta: 0:00:35  lr: 0.003011  min_lr: 0.003011  loss: 3.7980 (3.7366)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0391  max mem: 31830
Epoch: [112]  [260/312]  eta: 0:00:30  lr: 0.003010  min_lr: 0.003010  loss: 3.8970 (3.7453)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0142  max mem: 31830
Epoch: [112]  [270/312]  eta: 0:00:24  lr: 0.003009  min_lr: 0.003009  loss: 4.0854 (3.7473)  weight_decay: 0.0500 (0.0500)  time: 0.6694  data: 0.0008  max mem: 31830
Epoch: [112]  [280/312]  eta: 0:00:18  lr: 0.003009  min_lr: 0.003009  loss: 3.7439 (3.7452)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0066  max mem: 31830
Epoch: [112]  [290/312]  eta: 0:00:12  lr: 0.003008  min_lr: 0.003008  loss: 3.6860 (3.7461)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0211  max mem: 31830
Epoch: [112]  [300/312]  eta: 0:00:06  lr: 0.003007  min_lr: 0.003007  loss: 3.8021 (3.7499)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0149  max mem: 31830
Epoch: [112]  [310/312]  eta: 0:00:01  lr: 0.003007  min_lr: 0.003007  loss: 3.9908 (3.7621)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [112]  [311/312]  eta: 0:00:00  lr: 0.003007  min_lr: 0.003007  loss: 3.9791 (3.7588)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [112] Total time: 0:02:56 (0.5651 s / it)
Averaged stats: lr: 0.003007  min_lr: 0.003007  loss: 3.9791 (3.7155)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2534 (1.2534)  acc1: 75.2604 (75.2604)  acc5: 92.0573 (92.0573)  time: 8.8729  data: 8.7058  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6845 (1.5858)  acc1: 64.5833 (65.8080)  acc5: 88.2812 (87.6800)  time: 1.1026  data: 0.9674  max mem: 31830
Test: Total time: 0:00:10 (1.1128 s / it)
* Acc@1 66.018 Acc@5 87.676 loss 1.580
Accuracy of the model on the 50000 test images: 66.0%
Max accuracy: 67.08%
Epoch: [113]  [  0/312]  eta: 1:04:02  lr: 0.003007  min_lr: 0.003007  loss: 4.3345 (4.3345)  weight_decay: 0.0500 (0.0500)  time: 12.3141  data: 10.0684  max mem: 31830
Epoch: [113]  [ 10/312]  eta: 0:08:07  lr: 0.003006  min_lr: 0.003006  loss: 3.9249 (3.6797)  weight_decay: 0.0500 (0.0500)  time: 1.6139  data: 1.0396  max mem: 31830
Epoch: [113]  [ 20/312]  eta: 0:05:18  lr: 0.003005  min_lr: 0.003005  loss: 3.6435 (3.6056)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.1291  max mem: 31830
Epoch: [113]  [ 30/312]  eta: 0:04:04  lr: 0.003005  min_lr: 0.003005  loss: 3.5229 (3.5848)  weight_decay: 0.0500 (0.0500)  time: 0.4571  data: 0.0611  max mem: 31830
Epoch: [113]  [ 40/312]  eta: 0:03:24  lr: 0.003004  min_lr: 0.003004  loss: 3.4802 (3.5725)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0007  max mem: 31830
Epoch: [113]  [ 50/312]  eta: 0:03:07  lr: 0.003004  min_lr: 0.003004  loss: 3.5323 (3.5880)  weight_decay: 0.0500 (0.0500)  time: 0.4775  data: 0.0710  max mem: 31830
Epoch: [113]  [ 60/312]  eta: 0:02:46  lr: 0.003003  min_lr: 0.003003  loss: 3.6051 (3.6263)  weight_decay: 0.0500 (0.0500)  time: 0.4779  data: 0.0709  max mem: 31830
Epoch: [113]  [ 70/312]  eta: 0:02:38  lr: 0.003002  min_lr: 0.003002  loss: 3.6051 (3.6163)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0883  max mem: 31830
Epoch: [113]  [ 80/312]  eta: 0:02:29  lr: 0.003002  min_lr: 0.003002  loss: 3.8019 (3.6178)  weight_decay: 0.0500 (0.0500)  time: 0.5895  data: 0.1400  max mem: 31830
Epoch: [113]  [ 90/312]  eta: 0:02:18  lr: 0.003001  min_lr: 0.003001  loss: 3.6370 (3.6076)  weight_decay: 0.0500 (0.0500)  time: 0.5128  data: 0.0877  max mem: 31830
Epoch: [113]  [100/312]  eta: 0:02:11  lr: 0.003000  min_lr: 0.003000  loss: 3.5271 (3.5893)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.1147  max mem: 31830
Epoch: [113]  [110/312]  eta: 0:02:01  lr: 0.003000  min_lr: 0.003000  loss: 3.5024 (3.5914)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.0794  max mem: 31830
Epoch: [113]  [120/312]  eta: 0:01:55  lr: 0.002999  min_lr: 0.002999  loss: 3.5877 (3.5888)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0970  max mem: 31830
Epoch: [113]  [130/312]  eta: 0:01:50  lr: 0.002999  min_lr: 0.002999  loss: 3.5877 (3.5947)  weight_decay: 0.0500 (0.0500)  time: 0.6420  data: 0.1753  max mem: 31830
Epoch: [113]  [140/312]  eta: 0:01:41  lr: 0.002998  min_lr: 0.002998  loss: 3.3745 (3.5644)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0790  max mem: 31830
Epoch: [113]  [150/312]  eta: 0:01:35  lr: 0.002997  min_lr: 0.002997  loss: 3.3745 (3.5679)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.0747  max mem: 31830
Epoch: [113]  [160/312]  eta: 0:01:29  lr: 0.002997  min_lr: 0.002997  loss: 3.7914 (3.5795)  weight_decay: 0.0500 (0.0500)  time: 0.5867  data: 0.1695  max mem: 31830
Epoch: [113]  [170/312]  eta: 0:01:22  lr: 0.002996  min_lr: 0.002996  loss: 3.6972 (3.5870)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0957  max mem: 31830
Epoch: [113]  [180/312]  eta: 0:01:16  lr: 0.002996  min_lr: 0.002996  loss: 3.8540 (3.5988)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0978  max mem: 31830
Epoch: [113]  [190/312]  eta: 0:01:09  lr: 0.002995  min_lr: 0.002995  loss: 3.7963 (3.6046)  weight_decay: 0.0500 (0.0500)  time: 0.5003  data: 0.0986  max mem: 31830
Epoch: [113]  [200/312]  eta: 0:01:04  lr: 0.002994  min_lr: 0.002994  loss: 3.6506 (3.5988)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.1051  max mem: 31830
Epoch: [113]  [210/312]  eta: 0:00:58  lr: 0.002994  min_lr: 0.002994  loss: 3.6506 (3.6080)  weight_decay: 0.0500 (0.0500)  time: 0.6166  data: 0.2025  max mem: 31830
Epoch: [113]  [220/312]  eta: 0:00:52  lr: 0.002993  min_lr: 0.002993  loss: 3.8239 (3.6174)  weight_decay: 0.0500 (0.0500)  time: 0.5053  data: 0.0990  max mem: 31830
Epoch: [113]  [230/312]  eta: 0:00:46  lr: 0.002992  min_lr: 0.002992  loss: 3.9029 (3.6233)  weight_decay: 0.0500 (0.0500)  time: 0.5037  data: 0.1126  max mem: 31830
Epoch: [113]  [240/312]  eta: 0:00:41  lr: 0.002992  min_lr: 0.002992  loss: 3.9029 (3.6260)  weight_decay: 0.0500 (0.0500)  time: 0.6239  data: 0.2308  max mem: 31830
Epoch: [113]  [250/312]  eta: 0:00:35  lr: 0.002991  min_lr: 0.002991  loss: 3.7234 (3.6224)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.1189  max mem: 31830
Epoch: [113]  [260/312]  eta: 0:00:29  lr: 0.002991  min_lr: 0.002991  loss: 3.8283 (3.6298)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0889  max mem: 31830
Epoch: [113]  [270/312]  eta: 0:00:23  lr: 0.002990  min_lr: 0.002990  loss: 3.9116 (3.6352)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0890  max mem: 31830
Epoch: [113]  [280/312]  eta: 0:00:18  lr: 0.002989  min_lr: 0.002989  loss: 3.3487 (3.6226)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0887  max mem: 31830
Epoch: [113]  [290/312]  eta: 0:00:12  lr: 0.002989  min_lr: 0.002989  loss: 3.6946 (3.6304)  weight_decay: 0.0500 (0.0500)  time: 0.6115  data: 0.1501  max mem: 31830
Epoch: [113]  [300/312]  eta: 0:00:06  lr: 0.002988  min_lr: 0.002988  loss: 3.9727 (3.6319)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0618  max mem: 31830
Epoch: [113]  [310/312]  eta: 0:00:01  lr: 0.002987  min_lr: 0.002987  loss: 3.7837 (3.6367)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [113]  [311/312]  eta: 0:00:00  lr: 0.002987  min_lr: 0.002987  loss: 3.9390 (3.6386)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [113] Total time: 0:02:53 (0.5571 s / it)
Averaged stats: lr: 0.002987  min_lr: 0.002987  loss: 3.9390 (3.6926)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 1.3899 (1.3899)  acc1: 72.5260 (72.5260)  acc5: 91.4062 (91.4062)  time: 7.6554  data: 7.4883  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9481 (1.7874)  acc1: 64.0625 (65.3760)  acc5: 86.3281 (86.8640)  time: 1.0276  data: 0.8858  max mem: 31830
Test: Total time: 0:00:09 (1.0395 s / it)
* Acc@1 65.228 Acc@5 87.036 loss 1.800
Accuracy of the model on the 50000 test images: 65.2%
Max accuracy: 67.08%
Epoch: [114]  [  0/312]  eta: 1:01:23  lr: 0.002987  min_lr: 0.002987  loss: 3.2368 (3.2368)  weight_decay: 0.0500 (0.0500)  time: 11.8045  data: 11.4174  max mem: 31830
Epoch: [114]  [ 10/312]  eta: 0:09:05  lr: 0.002987  min_lr: 0.002987  loss: 3.8191 (3.7895)  weight_decay: 0.0500 (0.0500)  time: 1.8064  data: 1.0384  max mem: 31830
Epoch: [114]  [ 20/312]  eta: 0:05:32  lr: 0.002986  min_lr: 0.002986  loss: 3.8693 (3.7528)  weight_decay: 0.0500 (0.0500)  time: 0.6061  data: 0.0092  max mem: 31830
Epoch: [114]  [ 30/312]  eta: 0:04:13  lr: 0.002985  min_lr: 0.002985  loss: 3.9760 (3.7941)  weight_decay: 0.0500 (0.0500)  time: 0.3987  data: 0.0092  max mem: 31830
Epoch: [114]  [ 40/312]  eta: 0:03:31  lr: 0.002985  min_lr: 0.002985  loss: 3.9760 (3.8622)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0007  max mem: 31830
Epoch: [114]  [ 50/312]  eta: 0:03:04  lr: 0.002984  min_lr: 0.002984  loss: 3.9274 (3.8070)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [114]  [ 60/312]  eta: 0:02:44  lr: 0.002984  min_lr: 0.002984  loss: 3.9274 (3.8519)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [114]  [ 70/312]  eta: 0:02:30  lr: 0.002983  min_lr: 0.002983  loss: 4.0100 (3.8212)  weight_decay: 0.0500 (0.0500)  time: 0.4147  data: 0.0009  max mem: 31830
Epoch: [114]  [ 80/312]  eta: 0:02:21  lr: 0.002982  min_lr: 0.002982  loss: 3.4640 (3.7537)  weight_decay: 0.0500 (0.0500)  time: 0.4765  data: 0.0205  max mem: 31830
Epoch: [114]  [ 90/312]  eta: 0:02:13  lr: 0.002982  min_lr: 0.002982  loss: 3.8182 (3.7691)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0209  max mem: 31830
Epoch: [114]  [100/312]  eta: 0:02:05  lr: 0.002981  min_lr: 0.002981  loss: 3.8182 (3.7244)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0510  max mem: 31830
Epoch: [114]  [110/312]  eta: 0:01:59  lr: 0.002980  min_lr: 0.002980  loss: 3.2639 (3.7135)  weight_decay: 0.0500 (0.0500)  time: 0.5479  data: 0.0749  max mem: 31830
Epoch: [114]  [120/312]  eta: 0:01:53  lr: 0.002980  min_lr: 0.002980  loss: 3.8306 (3.6992)  weight_decay: 0.0500 (0.0500)  time: 0.5899  data: 0.0529  max mem: 31830
Epoch: [114]  [130/312]  eta: 0:01:46  lr: 0.002979  min_lr: 0.002979  loss: 3.8306 (3.7058)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0685  max mem: 31830
Epoch: [114]  [140/312]  eta: 0:01:40  lr: 0.002979  min_lr: 0.002979  loss: 3.8384 (3.7019)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0407  max mem: 31830
Epoch: [114]  [150/312]  eta: 0:01:34  lr: 0.002978  min_lr: 0.002978  loss: 3.3393 (3.6693)  weight_decay: 0.0500 (0.0500)  time: 0.5929  data: 0.0333  max mem: 31830
Epoch: [114]  [160/312]  eta: 0:01:27  lr: 0.002977  min_lr: 0.002977  loss: 3.5415 (3.6806)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0583  max mem: 31830
Epoch: [114]  [170/312]  eta: 0:01:22  lr: 0.002977  min_lr: 0.002977  loss: 3.7704 (3.6686)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0398  max mem: 31830
Epoch: [114]  [180/312]  eta: 0:01:15  lr: 0.002976  min_lr: 0.002976  loss: 3.7843 (3.6788)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0458  max mem: 31830
Epoch: [114]  [190/312]  eta: 0:01:10  lr: 0.002975  min_lr: 0.002975  loss: 3.9721 (3.6941)  weight_decay: 0.0500 (0.0500)  time: 0.5428  data: 0.0526  max mem: 31830
Epoch: [114]  [200/312]  eta: 0:01:04  lr: 0.002975  min_lr: 0.002975  loss: 3.6757 (3.6644)  weight_decay: 0.0500 (0.0500)  time: 0.6170  data: 0.0223  max mem: 31830
Epoch: [114]  [210/312]  eta: 0:00:58  lr: 0.002974  min_lr: 0.002974  loss: 3.4919 (3.6644)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0251  max mem: 31830
Epoch: [114]  [220/312]  eta: 0:00:52  lr: 0.002973  min_lr: 0.002973  loss: 3.6866 (3.6699)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0481  max mem: 31830
Epoch: [114]  [230/312]  eta: 0:00:47  lr: 0.002973  min_lr: 0.002973  loss: 3.8087 (3.6819)  weight_decay: 0.0500 (0.0500)  time: 0.6225  data: 0.0495  max mem: 31830
Epoch: [114]  [240/312]  eta: 0:00:41  lr: 0.002972  min_lr: 0.002972  loss: 3.9602 (3.6807)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0620  max mem: 31830
Epoch: [114]  [250/312]  eta: 0:00:35  lr: 0.002972  min_lr: 0.002972  loss: 3.5563 (3.6768)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0372  max mem: 31830
Epoch: [114]  [260/312]  eta: 0:00:29  lr: 0.002971  min_lr: 0.002971  loss: 3.6791 (3.6809)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0310  max mem: 31830
Epoch: [114]  [270/312]  eta: 0:00:23  lr: 0.002970  min_lr: 0.002970  loss: 3.7808 (3.6820)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0547  max mem: 31830
Epoch: [114]  [280/312]  eta: 0:00:18  lr: 0.002970  min_lr: 0.002970  loss: 3.8037 (3.6835)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.0264  max mem: 31830
Epoch: [114]  [290/312]  eta: 0:00:12  lr: 0.002969  min_lr: 0.002969  loss: 3.6457 (3.6738)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0274  max mem: 31830
Epoch: [114]  [300/312]  eta: 0:00:06  lr: 0.002968  min_lr: 0.002968  loss: 3.5069 (3.6680)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0254  max mem: 31830
Epoch: [114]  [310/312]  eta: 0:00:01  lr: 0.002968  min_lr: 0.002968  loss: 3.6538 (3.6706)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0048  max mem: 31830
Epoch: [114]  [311/312]  eta: 0:00:00  lr: 0.002968  min_lr: 0.002968  loss: 3.6538 (3.6693)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0048  max mem: 31830
Epoch: [114] Total time: 0:02:54 (0.5583 s / it)
Averaged stats: lr: 0.002968  min_lr: 0.002968  loss: 3.6538 (3.6874)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2368 (1.2368)  acc1: 75.7812 (75.7812)  acc5: 93.0990 (93.0990)  time: 8.7899  data: 8.6228  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6486 (1.5041)  acc1: 66.4062 (67.3920)  acc5: 87.3698 (88.3680)  time: 1.0931  data: 0.9582  max mem: 31830
Test: Total time: 0:00:09 (1.1033 s / it)
* Acc@1 66.888 Acc@5 88.372 loss 1.510
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 67.08%
Epoch: [115]  [  0/312]  eta: 0:57:54  lr: 0.002968  min_lr: 0.002968  loss: 3.0552 (3.0552)  weight_decay: 0.0500 (0.0500)  time: 11.1367  data: 8.3598  max mem: 31830
Epoch: [115]  [ 10/312]  eta: 0:07:53  lr: 0.002967  min_lr: 0.002967  loss: 3.0552 (3.3083)  weight_decay: 0.0500 (0.0500)  time: 1.5687  data: 0.9248  max mem: 31830
Epoch: [115]  [ 20/312]  eta: 0:05:24  lr: 0.002966  min_lr: 0.002966  loss: 3.4848 (3.4206)  weight_decay: 0.0500 (0.0500)  time: 0.6093  data: 0.1478  max mem: 31830
Epoch: [115]  [ 30/312]  eta: 0:04:08  lr: 0.002966  min_lr: 0.002966  loss: 3.9031 (3.5186)  weight_decay: 0.0500 (0.0500)  time: 0.5006  data: 0.0583  max mem: 31830
Epoch: [115]  [ 40/312]  eta: 0:03:28  lr: 0.002965  min_lr: 0.002965  loss: 3.8963 (3.5569)  weight_decay: 0.0500 (0.0500)  time: 0.4079  data: 0.0015  max mem: 31830
Epoch: [115]  [ 50/312]  eta: 0:03:14  lr: 0.002965  min_lr: 0.002965  loss: 3.7718 (3.5409)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0008  max mem: 31830
Epoch: [115]  [ 60/312]  eta: 0:02:52  lr: 0.002964  min_lr: 0.002964  loss: 3.8403 (3.6044)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0007  max mem: 31830
Epoch: [115]  [ 70/312]  eta: 0:02:41  lr: 0.002963  min_lr: 0.002963  loss: 3.8352 (3.6099)  weight_decay: 0.0500 (0.0500)  time: 0.4771  data: 0.0266  max mem: 31830
Epoch: [115]  [ 80/312]  eta: 0:02:31  lr: 0.002963  min_lr: 0.002963  loss: 3.8459 (3.6602)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0266  max mem: 31830
Epoch: [115]  [ 90/312]  eta: 0:02:21  lr: 0.002962  min_lr: 0.002962  loss: 3.9220 (3.6285)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0010  max mem: 31830
Epoch: [115]  [100/312]  eta: 0:02:14  lr: 0.002961  min_lr: 0.002961  loss: 3.0863 (3.5862)  weight_decay: 0.0500 (0.0500)  time: 0.5646  data: 0.0134  max mem: 31830
Epoch: [115]  [110/312]  eta: 0:02:03  lr: 0.002961  min_lr: 0.002961  loss: 3.5409 (3.6013)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0133  max mem: 31830
Epoch: [115]  [120/312]  eta: 0:01:57  lr: 0.002960  min_lr: 0.002960  loss: 3.7482 (3.5848)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0496  max mem: 31830
Epoch: [115]  [130/312]  eta: 0:01:51  lr: 0.002960  min_lr: 0.002960  loss: 3.4776 (3.5914)  weight_decay: 0.0500 (0.0500)  time: 0.6146  data: 0.1015  max mem: 31830
Epoch: [115]  [140/312]  eta: 0:01:42  lr: 0.002959  min_lr: 0.002959  loss: 3.7042 (3.5868)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0528  max mem: 31830
Epoch: [115]  [150/312]  eta: 0:01:37  lr: 0.002958  min_lr: 0.002958  loss: 3.9004 (3.6099)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0583  max mem: 31830
Epoch: [115]  [160/312]  eta: 0:01:30  lr: 0.002958  min_lr: 0.002958  loss: 3.9004 (3.6153)  weight_decay: 0.0500 (0.0500)  time: 0.5534  data: 0.0585  max mem: 31830
Epoch: [115]  [170/312]  eta: 0:01:23  lr: 0.002957  min_lr: 0.002957  loss: 3.8058 (3.6255)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0246  max mem: 31830
Epoch: [115]  [180/312]  eta: 0:01:18  lr: 0.002956  min_lr: 0.002956  loss: 3.6644 (3.6310)  weight_decay: 0.0500 (0.0500)  time: 0.6148  data: 0.0638  max mem: 31830
Epoch: [115]  [190/312]  eta: 0:01:11  lr: 0.002956  min_lr: 0.002956  loss: 3.6102 (3.6279)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0402  max mem: 31830
Epoch: [115]  [200/312]  eta: 0:01:04  lr: 0.002955  min_lr: 0.002955  loss: 3.4378 (3.6136)  weight_decay: 0.0500 (0.0500)  time: 0.4501  data: 0.0269  max mem: 31830
Epoch: [115]  [210/312]  eta: 0:00:59  lr: 0.002954  min_lr: 0.002954  loss: 3.6473 (3.6219)  weight_decay: 0.0500 (0.0500)  time: 0.5581  data: 0.1002  max mem: 31830
Epoch: [115]  [220/312]  eta: 0:00:52  lr: 0.002954  min_lr: 0.002954  loss: 3.6473 (3.6180)  weight_decay: 0.0500 (0.0500)  time: 0.5052  data: 0.0741  max mem: 31830
Epoch: [115]  [230/312]  eta: 0:00:47  lr: 0.002953  min_lr: 0.002953  loss: 3.6222 (3.6195)  weight_decay: 0.0500 (0.0500)  time: 0.5207  data: 0.0736  max mem: 31830
Epoch: [115]  [240/312]  eta: 0:00:41  lr: 0.002953  min_lr: 0.002953  loss: 3.6310 (3.6192)  weight_decay: 0.0500 (0.0500)  time: 0.5859  data: 0.1036  max mem: 31830
Epoch: [115]  [250/312]  eta: 0:00:35  lr: 0.002952  min_lr: 0.002952  loss: 3.6215 (3.6127)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0320  max mem: 31830
Epoch: [115]  [260/312]  eta: 0:00:29  lr: 0.002951  min_lr: 0.002951  loss: 3.7645 (3.6157)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0147  max mem: 31830
Epoch: [115]  [270/312]  eta: 0:00:23  lr: 0.002951  min_lr: 0.002951  loss: 3.8264 (3.6178)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0141  max mem: 31830
Epoch: [115]  [280/312]  eta: 0:00:18  lr: 0.002950  min_lr: 0.002950  loss: 3.8276 (3.6282)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0025  max mem: 31830
Epoch: [115]  [290/312]  eta: 0:00:12  lr: 0.002949  min_lr: 0.002949  loss: 3.8664 (3.6283)  weight_decay: 0.0500 (0.0500)  time: 0.5632  data: 0.0324  max mem: 31830
Epoch: [115]  [300/312]  eta: 0:00:06  lr: 0.002949  min_lr: 0.002949  loss: 3.5182 (3.6272)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0309  max mem: 31830
Epoch: [115]  [310/312]  eta: 0:00:01  lr: 0.002948  min_lr: 0.002948  loss: 3.6737 (3.6340)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [115]  [311/312]  eta: 0:00:00  lr: 0.002948  min_lr: 0.002948  loss: 3.6778 (3.6344)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [115] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.002948  min_lr: 0.002948  loss: 3.6778 (3.6915)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.6259 (1.6259)  acc1: 74.2188 (74.2188)  acc5: 91.6667 (91.6667)  time: 7.9097  data: 7.7427  max mem: 31830
Test:  [8/9]  eta: 0:00:00  loss: 1.7837 (1.7953)  acc1: 65.2344 (66.4000)  acc5: 87.5000 (87.7760)  time: 0.9995  data: 0.8640  max mem: 31830
Test: Total time: 0:00:09 (1.0090 s / it)
* Acc@1 65.972 Acc@5 87.552 loss 1.802
Accuracy of the model on the 50000 test images: 66.0%
Max accuracy: 67.08%
Epoch: [116]  [  0/312]  eta: 1:01:35  lr: 0.002948  min_lr: 0.002948  loss: 3.7941 (3.7941)  weight_decay: 0.0500 (0.0500)  time: 11.8445  data: 9.4451  max mem: 31830
Epoch: [116]  [ 10/312]  eta: 0:08:33  lr: 0.002947  min_lr: 0.002947  loss: 3.7445 (3.5326)  weight_decay: 0.0500 (0.0500)  time: 1.6993  data: 0.8768  max mem: 31830
Epoch: [116]  [ 20/312]  eta: 0:05:29  lr: 0.002947  min_lr: 0.002947  loss: 3.7445 (3.6149)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0103  max mem: 31830
Epoch: [116]  [ 30/312]  eta: 0:04:11  lr: 0.002946  min_lr: 0.002946  loss: 3.7162 (3.6408)  weight_decay: 0.0500 (0.0500)  time: 0.4486  data: 0.0006  max mem: 31830
Epoch: [116]  [ 40/312]  eta: 0:03:30  lr: 0.002945  min_lr: 0.002945  loss: 3.6624 (3.5921)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0006  max mem: 31830
Epoch: [116]  [ 50/312]  eta: 0:03:03  lr: 0.002945  min_lr: 0.002945  loss: 3.6850 (3.6195)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0007  max mem: 31830
Epoch: [116]  [ 60/312]  eta: 0:02:43  lr: 0.002944  min_lr: 0.002944  loss: 3.7916 (3.6318)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0008  max mem: 31830
Epoch: [116]  [ 70/312]  eta: 0:02:33  lr: 0.002944  min_lr: 0.002944  loss: 3.8147 (3.6704)  weight_decay: 0.0500 (0.0500)  time: 0.4666  data: 0.0008  max mem: 31830
Epoch: [116]  [ 80/312]  eta: 0:02:23  lr: 0.002943  min_lr: 0.002943  loss: 4.0051 (3.6975)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0068  max mem: 31830
Epoch: [116]  [ 90/312]  eta: 0:02:14  lr: 0.002942  min_lr: 0.002942  loss: 3.8826 (3.7158)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.0453  max mem: 31830
Epoch: [116]  [100/312]  eta: 0:02:08  lr: 0.002942  min_lr: 0.002942  loss: 3.8216 (3.7149)  weight_decay: 0.0500 (0.0500)  time: 0.5675  data: 0.1007  max mem: 31830
Epoch: [116]  [110/312]  eta: 0:01:58  lr: 0.002941  min_lr: 0.002941  loss: 4.0292 (3.7169)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0623  max mem: 31830
Epoch: [116]  [120/312]  eta: 0:01:53  lr: 0.002940  min_lr: 0.002940  loss: 3.3868 (3.6941)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0525  max mem: 31830
Epoch: [116]  [130/312]  eta: 0:01:47  lr: 0.002940  min_lr: 0.002940  loss: 3.2819 (3.6789)  weight_decay: 0.0500 (0.0500)  time: 0.6144  data: 0.0882  max mem: 31830
Epoch: [116]  [140/312]  eta: 0:01:39  lr: 0.002939  min_lr: 0.002939  loss: 3.6446 (3.6743)  weight_decay: 0.0500 (0.0500)  time: 0.4915  data: 0.0366  max mem: 31830
Epoch: [116]  [150/312]  eta: 0:01:33  lr: 0.002938  min_lr: 0.002938  loss: 3.4239 (3.6543)  weight_decay: 0.0500 (0.0500)  time: 0.4957  data: 0.0498  max mem: 31830
Epoch: [116]  [160/312]  eta: 0:01:27  lr: 0.002938  min_lr: 0.002938  loss: 3.4239 (3.6593)  weight_decay: 0.0500 (0.0500)  time: 0.5740  data: 0.0550  max mem: 31830
Epoch: [116]  [170/312]  eta: 0:01:21  lr: 0.002937  min_lr: 0.002937  loss: 3.7153 (3.6532)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0531  max mem: 31830
Epoch: [116]  [180/312]  eta: 0:01:15  lr: 0.002937  min_lr: 0.002937  loss: 3.7153 (3.6634)  weight_decay: 0.0500 (0.0500)  time: 0.5406  data: 0.0993  max mem: 31830
Epoch: [116]  [190/312]  eta: 0:01:08  lr: 0.002936  min_lr: 0.002936  loss: 3.9278 (3.6692)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0534  max mem: 31830
Epoch: [116]  [200/312]  eta: 0:01:03  lr: 0.002935  min_lr: 0.002935  loss: 3.7243 (3.6548)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.0774  max mem: 31830
Epoch: [116]  [210/312]  eta: 0:00:58  lr: 0.002935  min_lr: 0.002935  loss: 3.5884 (3.6581)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.1428  max mem: 31830
Epoch: [116]  [220/312]  eta: 0:00:51  lr: 0.002934  min_lr: 0.002934  loss: 3.9740 (3.6591)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0672  max mem: 31830
Epoch: [116]  [230/312]  eta: 0:00:46  lr: 0.002933  min_lr: 0.002933  loss: 3.9040 (3.6624)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0640  max mem: 31830
Epoch: [116]  [240/312]  eta: 0:00:40  lr: 0.002933  min_lr: 0.002933  loss: 3.9040 (3.6650)  weight_decay: 0.0500 (0.0500)  time: 0.5379  data: 0.0639  max mem: 31830
Epoch: [116]  [250/312]  eta: 0:00:34  lr: 0.002932  min_lr: 0.002932  loss: 3.8787 (3.6730)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0530  max mem: 31830
Epoch: [116]  [260/312]  eta: 0:00:29  lr: 0.002931  min_lr: 0.002931  loss: 3.8625 (3.6759)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.0975  max mem: 31830
Epoch: [116]  [270/312]  eta: 0:00:23  lr: 0.002931  min_lr: 0.002931  loss: 3.7066 (3.6742)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0452  max mem: 31830
Epoch: [116]  [280/312]  eta: 0:00:17  lr: 0.002930  min_lr: 0.002930  loss: 3.5996 (3.6632)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0283  max mem: 31830
Epoch: [116]  [290/312]  eta: 0:00:12  lr: 0.002930  min_lr: 0.002930  loss: 3.4080 (3.6545)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.0469  max mem: 31830
Epoch: [116]  [300/312]  eta: 0:00:06  lr: 0.002929  min_lr: 0.002929  loss: 3.7299 (3.6576)  weight_decay: 0.0500 (0.0500)  time: 0.4828  data: 0.0191  max mem: 31830
Epoch: [116]  [310/312]  eta: 0:00:01  lr: 0.002928  min_lr: 0.002928  loss: 3.8041 (3.6607)  weight_decay: 0.0500 (0.0500)  time: 0.4137  data: 0.0001  max mem: 31830
Epoch: [116]  [311/312]  eta: 0:00:00  lr: 0.002928  min_lr: 0.002928  loss: 3.7868 (3.6611)  weight_decay: 0.0500 (0.0500)  time: 0.4136  data: 0.0001  max mem: 31830
Epoch: [116] Total time: 0:02:52 (0.5530 s / it)
Averaged stats: lr: 0.002928  min_lr: 0.002928  loss: 3.7868 (3.6764)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.2443 (1.2443)  acc1: 75.2604 (75.2604)  acc5: 91.9271 (91.9271)  time: 8.4060  data: 8.2387  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7340 (1.5626)  acc1: 65.7552 (67.0080)  acc5: 87.2396 (87.8400)  time: 1.0519  data: 0.9155  max mem: 31830
Test: Total time: 0:00:09 (1.0916 s / it)
* Acc@1 66.860 Acc@5 87.894 loss 1.563
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 67.08%
Epoch: [117]  [  0/312]  eta: 0:56:04  lr: 0.002928  min_lr: 0.002928  loss: 4.5004 (4.5004)  weight_decay: 0.0500 (0.0500)  time: 10.7822  data: 9.6807  max mem: 31830
Epoch: [117]  [ 10/312]  eta: 0:08:12  lr: 0.002928  min_lr: 0.002928  loss: 3.8497 (3.7709)  weight_decay: 0.0500 (0.0500)  time: 1.6308  data: 0.9540  max mem: 31830
Epoch: [117]  [ 20/312]  eta: 0:05:27  lr: 0.002927  min_lr: 0.002927  loss: 3.8497 (3.8455)  weight_decay: 0.0500 (0.0500)  time: 0.6372  data: 0.0604  max mem: 31830
Epoch: [117]  [ 30/312]  eta: 0:04:09  lr: 0.002926  min_lr: 0.002926  loss: 3.6293 (3.7240)  weight_decay: 0.0500 (0.0500)  time: 0.4767  data: 0.0202  max mem: 31830
Epoch: [117]  [ 40/312]  eta: 0:03:28  lr: 0.002926  min_lr: 0.002926  loss: 3.6293 (3.7256)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0011  max mem: 31830
Epoch: [117]  [ 50/312]  eta: 0:03:06  lr: 0.002925  min_lr: 0.002925  loss: 3.6504 (3.6987)  weight_decay: 0.0500 (0.0500)  time: 0.4446  data: 0.0366  max mem: 31830
Epoch: [117]  [ 60/312]  eta: 0:02:47  lr: 0.002924  min_lr: 0.002924  loss: 3.5351 (3.6593)  weight_decay: 0.0500 (0.0500)  time: 0.4511  data: 0.0365  max mem: 31830
Epoch: [117]  [ 70/312]  eta: 0:02:37  lr: 0.002924  min_lr: 0.002924  loss: 3.8815 (3.7014)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0783  max mem: 31830
Epoch: [117]  [ 80/312]  eta: 0:02:28  lr: 0.002923  min_lr: 0.002923  loss: 3.9488 (3.6871)  weight_decay: 0.0500 (0.0500)  time: 0.5710  data: 0.1572  max mem: 31830
Epoch: [117]  [ 90/312]  eta: 0:02:17  lr: 0.002922  min_lr: 0.002922  loss: 3.9036 (3.7008)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0799  max mem: 31830
Epoch: [117]  [100/312]  eta: 0:02:11  lr: 0.002922  min_lr: 0.002922  loss: 3.9580 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0691  max mem: 31830
Epoch: [117]  [110/312]  eta: 0:02:00  lr: 0.002921  min_lr: 0.002921  loss: 3.9106 (3.7177)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0690  max mem: 31830
Epoch: [117]  [120/312]  eta: 0:01:55  lr: 0.002921  min_lr: 0.002921  loss: 3.7513 (3.7061)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0862  max mem: 31830
Epoch: [117]  [130/312]  eta: 0:01:49  lr: 0.002920  min_lr: 0.002920  loss: 3.5554 (3.6848)  weight_decay: 0.0500 (0.0500)  time: 0.6117  data: 0.1417  max mem: 31830
Epoch: [117]  [140/312]  eta: 0:01:41  lr: 0.002919  min_lr: 0.002919  loss: 3.4837 (3.6808)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.0688  max mem: 31830
Epoch: [117]  [150/312]  eta: 0:01:35  lr: 0.002919  min_lr: 0.002919  loss: 3.8268 (3.6874)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0683  max mem: 31830
Epoch: [117]  [160/312]  eta: 0:01:29  lr: 0.002918  min_lr: 0.002918  loss: 3.9471 (3.7001)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.1516  max mem: 31830
Epoch: [117]  [170/312]  eta: 0:01:22  lr: 0.002917  min_lr: 0.002917  loss: 3.9471 (3.7041)  weight_decay: 0.0500 (0.0500)  time: 0.4891  data: 0.0967  max mem: 31830
Epoch: [117]  [180/312]  eta: 0:01:17  lr: 0.002917  min_lr: 0.002917  loss: 3.7092 (3.6874)  weight_decay: 0.0500 (0.0500)  time: 0.5566  data: 0.1000  max mem: 31830
Epoch: [117]  [190/312]  eta: 0:01:10  lr: 0.002916  min_lr: 0.002916  loss: 3.5126 (3.6862)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.1000  max mem: 31830
Epoch: [117]  [200/312]  eta: 0:01:04  lr: 0.002915  min_lr: 0.002915  loss: 3.6774 (3.6800)  weight_decay: 0.0500 (0.0500)  time: 0.5034  data: 0.0497  max mem: 31830
Epoch: [117]  [210/312]  eta: 0:00:58  lr: 0.002915  min_lr: 0.002915  loss: 3.5154 (3.6661)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0886  max mem: 31830
Epoch: [117]  [220/312]  eta: 0:00:52  lr: 0.002914  min_lr: 0.002914  loss: 3.7967 (3.6784)  weight_decay: 0.0500 (0.0500)  time: 0.5088  data: 0.0397  max mem: 31830
Epoch: [117]  [230/312]  eta: 0:00:47  lr: 0.002914  min_lr: 0.002914  loss: 3.8254 (3.6631)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0313  max mem: 31830
Epoch: [117]  [240/312]  eta: 0:00:41  lr: 0.002913  min_lr: 0.002913  loss: 3.6514 (3.6643)  weight_decay: 0.0500 (0.0500)  time: 0.5880  data: 0.0569  max mem: 31830
Epoch: [117]  [250/312]  eta: 0:00:35  lr: 0.002912  min_lr: 0.002912  loss: 3.7537 (3.6738)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0528  max mem: 31830
Epoch: [117]  [260/312]  eta: 0:00:29  lr: 0.002912  min_lr: 0.002912  loss: 4.0062 (3.6848)  weight_decay: 0.0500 (0.0500)  time: 0.5486  data: 0.0652  max mem: 31830
Epoch: [117]  [270/312]  eta: 0:00:23  lr: 0.002911  min_lr: 0.002911  loss: 4.0028 (3.6888)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0389  max mem: 31830
Epoch: [117]  [280/312]  eta: 0:00:18  lr: 0.002910  min_lr: 0.002910  loss: 3.5869 (3.6806)  weight_decay: 0.0500 (0.0500)  time: 0.4952  data: 0.0423  max mem: 31830
Epoch: [117]  [290/312]  eta: 0:00:12  lr: 0.002910  min_lr: 0.002910  loss: 3.5483 (3.6841)  weight_decay: 0.0500 (0.0500)  time: 0.5360  data: 0.0799  max mem: 31830
Epoch: [117]  [300/312]  eta: 0:00:06  lr: 0.002909  min_lr: 0.002909  loss: 3.5763 (3.6807)  weight_decay: 0.0500 (0.0500)  time: 0.4478  data: 0.0380  max mem: 31830
Epoch: [117]  [310/312]  eta: 0:00:01  lr: 0.002908  min_lr: 0.002908  loss: 3.5763 (3.6707)  weight_decay: 0.0500 (0.0500)  time: 0.4018  data: 0.0001  max mem: 31830
Epoch: [117]  [311/312]  eta: 0:00:00  lr: 0.002908  min_lr: 0.002908  loss: 3.5763 (3.6696)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [117] Total time: 0:02:53 (0.5551 s / it)
Averaged stats: lr: 0.002908  min_lr: 0.002908  loss: 3.5763 (3.6920)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2482 (1.2482)  acc1: 73.9583 (73.9583)  acc5: 92.5781 (92.5781)  time: 8.8111  data: 8.6438  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7062 (1.5595)  acc1: 66.0156 (68.0000)  acc5: 88.1510 (88.2720)  time: 1.0956  data: 0.9605  max mem: 31830
Test: Total time: 0:00:09 (1.1082 s / it)
* Acc@1 67.538 Acc@5 88.536 loss 1.556
Accuracy of the model on the 50000 test images: 67.5%
Max accuracy: 67.54%
Epoch: [118]  [  0/312]  eta: 0:58:22  lr: 0.002908  min_lr: 0.002908  loss: 4.2404 (4.2404)  weight_decay: 0.0500 (0.0500)  time: 11.2255  data: 10.7228  max mem: 31830
Epoch: [118]  [ 10/312]  eta: 0:08:13  lr: 0.002908  min_lr: 0.002908  loss: 3.8441 (3.7551)  weight_decay: 0.0500 (0.0500)  time: 1.6348  data: 0.9754  max mem: 31830
Epoch: [118]  [ 20/312]  eta: 0:05:17  lr: 0.002907  min_lr: 0.002907  loss: 3.6973 (3.6115)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0480  max mem: 31830
Epoch: [118]  [ 30/312]  eta: 0:04:03  lr: 0.002906  min_lr: 0.002906  loss: 3.8794 (3.6890)  weight_decay: 0.0500 (0.0500)  time: 0.4414  data: 0.0487  max mem: 31830
Epoch: [118]  [ 40/312]  eta: 0:03:24  lr: 0.002906  min_lr: 0.002906  loss: 3.9040 (3.6397)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0015  max mem: 31830
Epoch: [118]  [ 50/312]  eta: 0:03:03  lr: 0.002905  min_lr: 0.002905  loss: 3.6982 (3.6862)  weight_decay: 0.0500 (0.0500)  time: 0.4449  data: 0.0510  max mem: 31830
Epoch: [118]  [ 60/312]  eta: 0:02:43  lr: 0.002904  min_lr: 0.002904  loss: 3.7993 (3.6827)  weight_decay: 0.0500 (0.0500)  time: 0.4441  data: 0.0509  max mem: 31830
Epoch: [118]  [ 70/312]  eta: 0:02:34  lr: 0.002904  min_lr: 0.002904  loss: 3.7993 (3.6945)  weight_decay: 0.0500 (0.0500)  time: 0.4859  data: 0.0935  max mem: 31830
Epoch: [118]  [ 80/312]  eta: 0:02:26  lr: 0.002903  min_lr: 0.002903  loss: 3.8640 (3.7038)  weight_decay: 0.0500 (0.0500)  time: 0.5755  data: 0.1843  max mem: 31830
Epoch: [118]  [ 90/312]  eta: 0:02:14  lr: 0.002902  min_lr: 0.002902  loss: 3.8434 (3.6823)  weight_decay: 0.0500 (0.0500)  time: 0.4855  data: 0.0916  max mem: 31830
Epoch: [118]  [100/312]  eta: 0:02:08  lr: 0.002902  min_lr: 0.002902  loss: 3.8401 (3.6958)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.1052  max mem: 31830
Epoch: [118]  [110/312]  eta: 0:01:58  lr: 0.002901  min_lr: 0.002901  loss: 3.7760 (3.6765)  weight_decay: 0.0500 (0.0500)  time: 0.4979  data: 0.1051  max mem: 31830
Epoch: [118]  [120/312]  eta: 0:01:53  lr: 0.002901  min_lr: 0.002901  loss: 3.9790 (3.7224)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.1116  max mem: 31830
Epoch: [118]  [130/312]  eta: 0:01:47  lr: 0.002900  min_lr: 0.002900  loss: 3.9040 (3.6984)  weight_decay: 0.0500 (0.0500)  time: 0.6232  data: 0.2277  max mem: 31830
Epoch: [118]  [140/312]  eta: 0:01:39  lr: 0.002899  min_lr: 0.002899  loss: 3.5269 (3.6973)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.1170  max mem: 31830
Epoch: [118]  [150/312]  eta: 0:01:33  lr: 0.002899  min_lr: 0.002899  loss: 3.7449 (3.7173)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.1032  max mem: 31830
Epoch: [118]  [160/312]  eta: 0:01:28  lr: 0.002898  min_lr: 0.002898  loss: 3.8442 (3.7094)  weight_decay: 0.0500 (0.0500)  time: 0.6056  data: 0.2137  max mem: 31830
Epoch: [118]  [170/312]  eta: 0:01:20  lr: 0.002897  min_lr: 0.002897  loss: 3.8442 (3.7222)  weight_decay: 0.0500 (0.0500)  time: 0.5035  data: 0.1114  max mem: 31830
Epoch: [118]  [180/312]  eta: 0:01:15  lr: 0.002897  min_lr: 0.002897  loss: 4.0252 (3.7313)  weight_decay: 0.0500 (0.0500)  time: 0.4936  data: 0.1014  max mem: 31830
Epoch: [118]  [190/312]  eta: 0:01:08  lr: 0.002896  min_lr: 0.002896  loss: 3.8493 (3.7297)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.1021  max mem: 31830
Epoch: [118]  [200/312]  eta: 0:01:03  lr: 0.002895  min_lr: 0.002895  loss: 3.7212 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.1116  max mem: 31830
Epoch: [118]  [210/312]  eta: 0:00:57  lr: 0.002895  min_lr: 0.002895  loss: 3.5818 (3.7085)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.2192  max mem: 31830
Epoch: [118]  [220/312]  eta: 0:00:51  lr: 0.002894  min_lr: 0.002894  loss: 3.7197 (3.7106)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.1090  max mem: 31830
Epoch: [118]  [230/312]  eta: 0:00:46  lr: 0.002893  min_lr: 0.002893  loss: 3.6067 (3.6992)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0943  max mem: 31830
Epoch: [118]  [240/312]  eta: 0:00:40  lr: 0.002893  min_lr: 0.002893  loss: 3.6067 (3.7023)  weight_decay: 0.0500 (0.0500)  time: 0.6072  data: 0.1935  max mem: 31830
Epoch: [118]  [250/312]  eta: 0:00:34  lr: 0.002892  min_lr: 0.002892  loss: 3.9452 (3.7009)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.1002  max mem: 31830
Epoch: [118]  [260/312]  eta: 0:00:29  lr: 0.002892  min_lr: 0.002892  loss: 3.8396 (3.7042)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0925  max mem: 31830
Epoch: [118]  [270/312]  eta: 0:00:23  lr: 0.002891  min_lr: 0.002891  loss: 3.7786 (3.7020)  weight_decay: 0.0500 (0.0500)  time: 0.5179  data: 0.0924  max mem: 31830
Epoch: [118]  [280/312]  eta: 0:00:17  lr: 0.002890  min_lr: 0.002890  loss: 3.5159 (3.6947)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0913  max mem: 31830
Epoch: [118]  [290/312]  eta: 0:00:12  lr: 0.002890  min_lr: 0.002890  loss: 3.5159 (3.6917)  weight_decay: 0.0500 (0.0500)  time: 0.5832  data: 0.1650  max mem: 31830
Epoch: [118]  [300/312]  eta: 0:00:06  lr: 0.002889  min_lr: 0.002889  loss: 3.7628 (3.6988)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0742  max mem: 31830
Epoch: [118]  [310/312]  eta: 0:00:01  lr: 0.002888  min_lr: 0.002888  loss: 3.6361 (3.6871)  weight_decay: 0.0500 (0.0500)  time: 0.3896  data: 0.0001  max mem: 31830
Epoch: [118]  [311/312]  eta: 0:00:00  lr: 0.002888  min_lr: 0.002888  loss: 3.5569 (3.6867)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [118] Total time: 0:02:51 (0.5510 s / it)
Averaged stats: lr: 0.002888  min_lr: 0.002888  loss: 3.5569 (3.6839)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.2696 (1.2696)  acc1: 73.6979 (73.6979)  acc5: 92.0573 (92.0573)  time: 8.3430  data: 8.1834  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7249 (1.5638)  acc1: 64.9740 (66.2400)  acc5: 87.3698 (87.9680)  time: 1.0529  data: 0.9094  max mem: 31830
Test: Total time: 0:00:09 (1.0677 s / it)
* Acc@1 66.396 Acc@5 88.074 loss 1.566
Accuracy of the model on the 50000 test images: 66.4%
Max accuracy: 67.54%
Epoch: [119]  [  0/312]  eta: 1:01:43  lr: 0.002888  min_lr: 0.002888  loss: 4.0821 (4.0821)  weight_decay: 0.0500 (0.0500)  time: 11.8710  data: 9.6379  max mem: 31830
Epoch: [119]  [ 10/312]  eta: 0:08:33  lr: 0.002888  min_lr: 0.002888  loss: 4.0821 (3.9419)  weight_decay: 0.0500 (0.0500)  time: 1.6994  data: 1.0438  max mem: 31830
Epoch: [119]  [ 20/312]  eta: 0:05:31  lr: 0.002887  min_lr: 0.002887  loss: 3.9014 (3.7488)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.1031  max mem: 31830
Epoch: [119]  [ 30/312]  eta: 0:04:13  lr: 0.002886  min_lr: 0.002886  loss: 3.6793 (3.7554)  weight_decay: 0.0500 (0.0500)  time: 0.4590  data: 0.0112  max mem: 31830
Epoch: [119]  [ 40/312]  eta: 0:03:31  lr: 0.002886  min_lr: 0.002886  loss: 3.7697 (3.7007)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0007  max mem: 31830
Epoch: [119]  [ 50/312]  eta: 0:03:05  lr: 0.002885  min_lr: 0.002885  loss: 3.8565 (3.7532)  weight_decay: 0.0500 (0.0500)  time: 0.4148  data: 0.0014  max mem: 31830
Epoch: [119]  [ 60/312]  eta: 0:02:45  lr: 0.002884  min_lr: 0.002884  loss: 3.8565 (3.7367)  weight_decay: 0.0500 (0.0500)  time: 0.4172  data: 0.0015  max mem: 31830
Epoch: [119]  [ 70/312]  eta: 0:02:37  lr: 0.002884  min_lr: 0.002884  loss: 3.4808 (3.6840)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0421  max mem: 31830
Epoch: [119]  [ 80/312]  eta: 0:02:27  lr: 0.002883  min_lr: 0.002883  loss: 3.4593 (3.6498)  weight_decay: 0.0500 (0.0500)  time: 0.5607  data: 0.0574  max mem: 31830
Epoch: [119]  [ 90/312]  eta: 0:02:17  lr: 0.002882  min_lr: 0.002882  loss: 3.7067 (3.6728)  weight_decay: 0.0500 (0.0500)  time: 0.5013  data: 0.0284  max mem: 31830
Epoch: [119]  [100/312]  eta: 0:02:10  lr: 0.002882  min_lr: 0.002882  loss: 3.8619 (3.6677)  weight_decay: 0.0500 (0.0500)  time: 0.5360  data: 0.0685  max mem: 31830
Epoch: [119]  [110/312]  eta: 0:02:00  lr: 0.002881  min_lr: 0.002881  loss: 3.6566 (3.6717)  weight_decay: 0.0500 (0.0500)  time: 0.4881  data: 0.0563  max mem: 31830
Epoch: [119]  [120/312]  eta: 0:01:55  lr: 0.002880  min_lr: 0.002880  loss: 3.6566 (3.6588)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0802  max mem: 31830
Epoch: [119]  [130/312]  eta: 0:01:49  lr: 0.002880  min_lr: 0.002880  loss: 3.4142 (3.6563)  weight_decay: 0.0500 (0.0500)  time: 0.6285  data: 0.1490  max mem: 31830
Epoch: [119]  [140/312]  eta: 0:01:40  lr: 0.002879  min_lr: 0.002879  loss: 3.6086 (3.6618)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0703  max mem: 31830
Epoch: [119]  [150/312]  eta: 0:01:35  lr: 0.002879  min_lr: 0.002879  loss: 3.8403 (3.6694)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0943  max mem: 31830
Epoch: [119]  [160/312]  eta: 0:01:29  lr: 0.002878  min_lr: 0.002878  loss: 3.9182 (3.6832)  weight_decay: 0.0500 (0.0500)  time: 0.6125  data: 0.1848  max mem: 31830
Epoch: [119]  [170/312]  eta: 0:01:21  lr: 0.002877  min_lr: 0.002877  loss: 3.8711 (3.6816)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0927  max mem: 31830
Epoch: [119]  [180/312]  eta: 0:01:16  lr: 0.002877  min_lr: 0.002877  loss: 3.7298 (3.6860)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0996  max mem: 31830
Epoch: [119]  [190/312]  eta: 0:01:09  lr: 0.002876  min_lr: 0.002876  loss: 3.8456 (3.6966)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0990  max mem: 31830
Epoch: [119]  [200/312]  eta: 0:01:04  lr: 0.002875  min_lr: 0.002875  loss: 3.8456 (3.7024)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0833  max mem: 31830
Epoch: [119]  [210/312]  eta: 0:00:58  lr: 0.002875  min_lr: 0.002875  loss: 3.6371 (3.6918)  weight_decay: 0.0500 (0.0500)  time: 0.6527  data: 0.1347  max mem: 31830
Epoch: [119]  [220/312]  eta: 0:00:52  lr: 0.002874  min_lr: 0.002874  loss: 3.7285 (3.7008)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0529  max mem: 31830
Epoch: [119]  [230/312]  eta: 0:00:47  lr: 0.002873  min_lr: 0.002873  loss: 3.8588 (3.7034)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.0493  max mem: 31830
Epoch: [119]  [240/312]  eta: 0:00:41  lr: 0.002873  min_lr: 0.002873  loss: 3.6649 (3.6991)  weight_decay: 0.0500 (0.0500)  time: 0.5708  data: 0.0850  max mem: 31830
Epoch: [119]  [250/312]  eta: 0:00:35  lr: 0.002872  min_lr: 0.002872  loss: 3.4671 (3.6880)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0370  max mem: 31830
Epoch: [119]  [260/312]  eta: 0:00:29  lr: 0.002871  min_lr: 0.002871  loss: 3.6392 (3.6930)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0395  max mem: 31830
Epoch: [119]  [270/312]  eta: 0:00:23  lr: 0.002871  min_lr: 0.002871  loss: 3.9658 (3.7021)  weight_decay: 0.0500 (0.0500)  time: 0.4838  data: 0.0395  max mem: 31830
Epoch: [119]  [280/312]  eta: 0:00:18  lr: 0.002870  min_lr: 0.002870  loss: 3.6871 (3.6933)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0701  max mem: 31830
Epoch: [119]  [290/312]  eta: 0:00:12  lr: 0.002869  min_lr: 0.002869  loss: 3.6762 (3.6962)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.1420  max mem: 31830
Epoch: [119]  [300/312]  eta: 0:00:06  lr: 0.002869  min_lr: 0.002869  loss: 3.8395 (3.6976)  weight_decay: 0.0500 (0.0500)  time: 0.4966  data: 0.0722  max mem: 31830
Epoch: [119]  [310/312]  eta: 0:00:01  lr: 0.002868  min_lr: 0.002868  loss: 3.5905 (3.6908)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [119]  [311/312]  eta: 0:00:00  lr: 0.002868  min_lr: 0.002868  loss: 3.5905 (3.6933)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [119] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.002868  min_lr: 0.002868  loss: 3.5905 (3.6791)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.2509 (1.2509)  acc1: 73.3073 (73.3073)  acc5: 92.1875 (92.1875)  time: 8.3386  data: 8.1710  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5640 (1.4710)  acc1: 66.6667 (67.5040)  acc5: 88.1510 (88.5120)  time: 1.0664  data: 0.9302  max mem: 31830
Test: Total time: 0:00:09 (1.0755 s / it)
* Acc@1 67.624 Acc@5 88.646 loss 1.475
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 67.62%
Epoch: [120]  [  0/312]  eta: 0:58:30  lr: 0.002868  min_lr: 0.002868  loss: 4.1291 (4.1291)  weight_decay: 0.0500 (0.0500)  time: 11.2519  data: 10.6637  max mem: 31830
Epoch: [120]  [ 10/312]  eta: 0:08:03  lr: 0.002867  min_lr: 0.002867  loss: 3.6524 (3.6474)  weight_decay: 0.0500 (0.0500)  time: 1.6010  data: 0.9936  max mem: 31830
Epoch: [120]  [ 20/312]  eta: 0:05:16  lr: 0.002867  min_lr: 0.002867  loss: 3.6524 (3.6296)  weight_decay: 0.0500 (0.0500)  time: 0.5744  data: 0.0386  max mem: 31830
Epoch: [120]  [ 30/312]  eta: 0:04:05  lr: 0.002866  min_lr: 0.002866  loss: 3.7776 (3.5885)  weight_decay: 0.0500 (0.0500)  time: 0.4687  data: 0.0256  max mem: 31830
Epoch: [120]  [ 40/312]  eta: 0:03:25  lr: 0.002865  min_lr: 0.002865  loss: 3.6906 (3.5947)  weight_decay: 0.0500 (0.0500)  time: 0.4093  data: 0.0013  max mem: 31830
Epoch: [120]  [ 50/312]  eta: 0:03:08  lr: 0.002865  min_lr: 0.002865  loss: 3.6293 (3.5949)  weight_decay: 0.0500 (0.0500)  time: 0.4835  data: 0.0336  max mem: 31830
Epoch: [120]  [ 60/312]  eta: 0:02:49  lr: 0.002864  min_lr: 0.002864  loss: 3.5736 (3.5764)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0566  max mem: 31830
Epoch: [120]  [ 70/312]  eta: 0:02:39  lr: 0.002864  min_lr: 0.002864  loss: 3.6677 (3.5980)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0908  max mem: 31830
Epoch: [120]  [ 80/312]  eta: 0:02:28  lr: 0.002863  min_lr: 0.002863  loss: 3.6677 (3.5902)  weight_decay: 0.0500 (0.0500)  time: 0.5364  data: 0.1205  max mem: 31830
Epoch: [120]  [ 90/312]  eta: 0:02:19  lr: 0.002862  min_lr: 0.002862  loss: 3.6032 (3.6016)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0914  max mem: 31830
Epoch: [120]  [100/312]  eta: 0:02:11  lr: 0.002862  min_lr: 0.002862  loss: 3.7332 (3.6137)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.1011  max mem: 31830
Epoch: [120]  [110/312]  eta: 0:02:01  lr: 0.002861  min_lr: 0.002861  loss: 3.8357 (3.6178)  weight_decay: 0.0500 (0.0500)  time: 0.4648  data: 0.0637  max mem: 31830
Epoch: [120]  [120/312]  eta: 0:01:55  lr: 0.002860  min_lr: 0.002860  loss: 3.7452 (3.6270)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.1029  max mem: 31830
Epoch: [120]  [130/312]  eta: 0:01:49  lr: 0.002860  min_lr: 0.002860  loss: 3.7452 (3.6305)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.1835  max mem: 31830
Epoch: [120]  [140/312]  eta: 0:01:41  lr: 0.002859  min_lr: 0.002859  loss: 3.8451 (3.6450)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.1089  max mem: 31830
Epoch: [120]  [150/312]  eta: 0:01:35  lr: 0.002858  min_lr: 0.002858  loss: 3.9287 (3.6595)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.1278  max mem: 31830
Epoch: [120]  [160/312]  eta: 0:01:29  lr: 0.002858  min_lr: 0.002858  loss: 3.7813 (3.6356)  weight_decay: 0.0500 (0.0500)  time: 0.6092  data: 0.2151  max mem: 31830
Epoch: [120]  [170/312]  eta: 0:01:22  lr: 0.002857  min_lr: 0.002857  loss: 3.8045 (3.6436)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.1157  max mem: 31830
Epoch: [120]  [180/312]  eta: 0:01:16  lr: 0.002856  min_lr: 0.002856  loss: 3.8184 (3.6401)  weight_decay: 0.0500 (0.0500)  time: 0.4857  data: 0.0914  max mem: 31830
Epoch: [120]  [190/312]  eta: 0:01:09  lr: 0.002856  min_lr: 0.002856  loss: 3.6731 (3.6390)  weight_decay: 0.0500 (0.0500)  time: 0.4876  data: 0.0913  max mem: 31830
Epoch: [120]  [200/312]  eta: 0:01:04  lr: 0.002855  min_lr: 0.002855  loss: 3.9937 (3.6571)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.1091  max mem: 31830
Epoch: [120]  [210/312]  eta: 0:00:58  lr: 0.002854  min_lr: 0.002854  loss: 4.0638 (3.6683)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.1944  max mem: 31830
Epoch: [120]  [220/312]  eta: 0:00:52  lr: 0.002854  min_lr: 0.002854  loss: 3.8584 (3.6699)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0970  max mem: 31830
Epoch: [120]  [230/312]  eta: 0:00:47  lr: 0.002853  min_lr: 0.002853  loss: 3.7655 (3.6695)  weight_decay: 0.0500 (0.0500)  time: 0.6460  data: 0.0774  max mem: 31830
Epoch: [120]  [240/312]  eta: 0:00:41  lr: 0.002852  min_lr: 0.002852  loss: 3.4357 (3.6611)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.0672  max mem: 31830
Epoch: [120]  [250/312]  eta: 0:00:35  lr: 0.002852  min_lr: 0.002852  loss: 3.6039 (3.6710)  weight_decay: 0.0500 (0.0500)  time: 0.4282  data: 0.0149  max mem: 31830
Epoch: [120]  [260/312]  eta: 0:00:29  lr: 0.002851  min_lr: 0.002851  loss: 3.9232 (3.6753)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0620  max mem: 31830
Epoch: [120]  [270/312]  eta: 0:00:23  lr: 0.002851  min_lr: 0.002851  loss: 3.8868 (3.6753)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0483  max mem: 31830
Epoch: [120]  [280/312]  eta: 0:00:18  lr: 0.002850  min_lr: 0.002850  loss: 3.9108 (3.6828)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0288  max mem: 31830
Epoch: [120]  [290/312]  eta: 0:00:12  lr: 0.002849  min_lr: 0.002849  loss: 3.8685 (3.6835)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0517  max mem: 31830
Epoch: [120]  [300/312]  eta: 0:00:06  lr: 0.002849  min_lr: 0.002849  loss: 3.7347 (3.6799)  weight_decay: 0.0500 (0.0500)  time: 0.4598  data: 0.0232  max mem: 31830
Epoch: [120]  [310/312]  eta: 0:00:01  lr: 0.002848  min_lr: 0.002848  loss: 3.3494 (3.6627)  weight_decay: 0.0500 (0.0500)  time: 0.3902  data: 0.0001  max mem: 31830
Epoch: [120]  [311/312]  eta: 0:00:00  lr: 0.002848  min_lr: 0.002848  loss: 3.0648 (3.6596)  weight_decay: 0.0500 (0.0500)  time: 0.3901  data: 0.0001  max mem: 31830
Epoch: [120] Total time: 0:02:53 (0.5566 s / it)
Averaged stats: lr: 0.002848  min_lr: 0.002848  loss: 3.0648 (3.6736)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.2228 (1.2228)  acc1: 75.0000 (75.0000)  acc5: 92.5781 (92.5781)  time: 8.6257  data: 8.4622  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4920 (1.4014)  acc1: 66.0156 (67.4720)  acc5: 89.3229 (88.9120)  time: 1.0927  data: 0.9574  max mem: 31830
Test: Total time: 0:00:09 (1.1068 s / it)
* Acc@1 67.234 Acc@5 88.686 loss 1.408
Accuracy of the model on the 50000 test images: 67.2%
Max accuracy: 67.62%
Epoch: [121]  [  0/312]  eta: 1:01:41  lr: 0.002848  min_lr: 0.002848  loss: 3.3331 (3.3331)  weight_decay: 0.0500 (0.0500)  time: 11.8634  data: 9.3155  max mem: 31830
Epoch: [121]  [ 10/312]  eta: 0:08:33  lr: 0.002847  min_lr: 0.002847  loss: 3.8940 (3.7479)  weight_decay: 0.0500 (0.0500)  time: 1.7010  data: 1.0207  max mem: 31830
Epoch: [121]  [ 20/312]  eta: 0:05:30  lr: 0.002846  min_lr: 0.002846  loss: 3.8861 (3.7028)  weight_decay: 0.0500 (0.0500)  time: 0.5946  data: 0.0962  max mem: 31830
Epoch: [121]  [ 30/312]  eta: 0:04:12  lr: 0.002846  min_lr: 0.002846  loss: 3.4324 (3.6682)  weight_decay: 0.0500 (0.0500)  time: 0.4523  data: 0.0009  max mem: 31830
Epoch: [121]  [ 40/312]  eta: 0:03:30  lr: 0.002845  min_lr: 0.002845  loss: 3.6463 (3.6567)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0015  max mem: 31830
Epoch: [121]  [ 50/312]  eta: 0:03:05  lr: 0.002845  min_lr: 0.002845  loss: 3.7127 (3.6902)  weight_decay: 0.0500 (0.0500)  time: 0.4168  data: 0.0017  max mem: 31830
Epoch: [121]  [ 60/312]  eta: 0:02:45  lr: 0.002844  min_lr: 0.002844  loss: 3.6539 (3.6410)  weight_decay: 0.0500 (0.0500)  time: 0.4196  data: 0.0008  max mem: 31830
Epoch: [121]  [ 70/312]  eta: 0:02:38  lr: 0.002843  min_lr: 0.002843  loss: 3.5871 (3.6383)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0429  max mem: 31830
Epoch: [121]  [ 80/312]  eta: 0:02:29  lr: 0.002843  min_lr: 0.002843  loss: 3.5871 (3.6239)  weight_decay: 0.0500 (0.0500)  time: 0.6001  data: 0.0429  max mem: 31830
Epoch: [121]  [ 90/312]  eta: 0:02:17  lr: 0.002842  min_lr: 0.002842  loss: 3.5490 (3.6086)  weight_decay: 0.0500 (0.0500)  time: 0.4928  data: 0.0201  max mem: 31830
Epoch: [121]  [100/312]  eta: 0:02:10  lr: 0.002841  min_lr: 0.002841  loss: 3.7065 (3.6311)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0521  max mem: 31830
Epoch: [121]  [110/312]  eta: 0:02:00  lr: 0.002841  min_lr: 0.002841  loss: 3.8400 (3.6323)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0328  max mem: 31830
Epoch: [121]  [120/312]  eta: 0:01:55  lr: 0.002840  min_lr: 0.002840  loss: 3.8052 (3.6406)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0405  max mem: 31830
Epoch: [121]  [130/312]  eta: 0:01:48  lr: 0.002839  min_lr: 0.002839  loss: 4.0232 (3.6700)  weight_decay: 0.0500 (0.0500)  time: 0.5950  data: 0.0719  max mem: 31830
Epoch: [121]  [140/312]  eta: 0:01:40  lr: 0.002839  min_lr: 0.002839  loss: 3.9478 (3.6675)  weight_decay: 0.0500 (0.0500)  time: 0.4731  data: 0.0322  max mem: 31830
Epoch: [121]  [150/312]  eta: 0:01:35  lr: 0.002838  min_lr: 0.002838  loss: 3.8245 (3.6563)  weight_decay: 0.0500 (0.0500)  time: 0.5264  data: 0.0499  max mem: 31830
Epoch: [121]  [160/312]  eta: 0:01:28  lr: 0.002837  min_lr: 0.002837  loss: 3.7902 (3.6585)  weight_decay: 0.0500 (0.0500)  time: 0.6004  data: 0.0559  max mem: 31830
Epoch: [121]  [170/312]  eta: 0:01:22  lr: 0.002837  min_lr: 0.002837  loss: 3.8284 (3.6637)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0359  max mem: 31830
Epoch: [121]  [180/312]  eta: 0:01:16  lr: 0.002836  min_lr: 0.002836  loss: 3.8479 (3.6681)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0611  max mem: 31830
Epoch: [121]  [190/312]  eta: 0:01:09  lr: 0.002835  min_lr: 0.002835  loss: 3.8479 (3.6611)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0320  max mem: 31830
Epoch: [121]  [200/312]  eta: 0:01:03  lr: 0.002835  min_lr: 0.002835  loss: 3.1680 (3.6394)  weight_decay: 0.0500 (0.0500)  time: 0.4770  data: 0.0250  max mem: 31830
Epoch: [121]  [210/312]  eta: 0:00:58  lr: 0.002834  min_lr: 0.002834  loss: 3.6788 (3.6526)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0721  max mem: 31830
Epoch: [121]  [220/312]  eta: 0:00:52  lr: 0.002833  min_lr: 0.002833  loss: 3.6967 (3.6446)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0478  max mem: 31830
Epoch: [121]  [230/312]  eta: 0:00:46  lr: 0.002833  min_lr: 0.002833  loss: 3.4227 (3.6425)  weight_decay: 0.0500 (0.0500)  time: 0.5534  data: 0.0380  max mem: 31830
Epoch: [121]  [240/312]  eta: 0:00:40  lr: 0.002832  min_lr: 0.002832  loss: 3.6676 (3.6433)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0572  max mem: 31830
Epoch: [121]  [250/312]  eta: 0:00:35  lr: 0.002831  min_lr: 0.002831  loss: 3.8007 (3.6494)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0323  max mem: 31830
Epoch: [121]  [260/312]  eta: 0:00:29  lr: 0.002831  min_lr: 0.002831  loss: 3.6537 (3.6376)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.0461  max mem: 31830
Epoch: [121]  [270/312]  eta: 0:00:23  lr: 0.002830  min_lr: 0.002830  loss: 3.6363 (3.6424)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0337  max mem: 31830
Epoch: [121]  [280/312]  eta: 0:00:18  lr: 0.002830  min_lr: 0.002830  loss: 3.6363 (3.6361)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0279  max mem: 31830
Epoch: [121]  [290/312]  eta: 0:00:12  lr: 0.002829  min_lr: 0.002829  loss: 3.5853 (3.6355)  weight_decay: 0.0500 (0.0500)  time: 0.5462  data: 0.0277  max mem: 31830
Epoch: [121]  [300/312]  eta: 0:00:06  lr: 0.002828  min_lr: 0.002828  loss: 3.6153 (3.6327)  weight_decay: 0.0500 (0.0500)  time: 0.4750  data: 0.0002  max mem: 31830
Epoch: [121]  [310/312]  eta: 0:00:01  lr: 0.002828  min_lr: 0.002828  loss: 3.6153 (3.6333)  weight_decay: 0.0500 (0.0500)  time: 0.4544  data: 0.0001  max mem: 31830
Epoch: [121]  [311/312]  eta: 0:00:00  lr: 0.002827  min_lr: 0.002827  loss: 3.6153 (3.6331)  weight_decay: 0.0500 (0.0500)  time: 0.4542  data: 0.0001  max mem: 31830
Epoch: [121] Total time: 0:02:53 (0.5573 s / it)
Averaged stats: lr: 0.002827  min_lr: 0.002827  loss: 3.6153 (3.6467)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3462 (1.3462)  acc1: 76.5625 (76.5625)  acc5: 92.0573 (92.0573)  time: 8.4705  data: 8.3049  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6957 (1.5698)  acc1: 66.5365 (68.4480)  acc5: 87.6302 (88.5920)  time: 1.0577  data: 0.9228  max mem: 31830
Test: Total time: 0:00:09 (1.0690 s / it)
* Acc@1 68.058 Acc@5 88.778 loss 1.570
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 68.06%
Epoch: [122]  [  0/312]  eta: 1:04:15  lr: 0.002827  min_lr: 0.002827  loss: 4.0612 (4.0612)  weight_decay: 0.0500 (0.0500)  time: 12.3563  data: 8.9654  max mem: 31830
Epoch: [122]  [ 10/312]  eta: 0:08:30  lr: 0.002827  min_lr: 0.002827  loss: 3.8498 (3.5415)  weight_decay: 0.0500 (0.0500)  time: 1.6888  data: 1.0218  max mem: 31830
Epoch: [122]  [ 20/312]  eta: 0:05:23  lr: 0.002826  min_lr: 0.002826  loss: 3.4308 (3.4923)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.1144  max mem: 31830
Epoch: [122]  [ 30/312]  eta: 0:04:08  lr: 0.002825  min_lr: 0.002825  loss: 3.6159 (3.5700)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0011  max mem: 31830
Epoch: [122]  [ 40/312]  eta: 0:03:27  lr: 0.002825  min_lr: 0.002825  loss: 3.9995 (3.6827)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0008  max mem: 31830
Epoch: [122]  [ 50/312]  eta: 0:03:03  lr: 0.002824  min_lr: 0.002824  loss: 3.9199 (3.6889)  weight_decay: 0.0500 (0.0500)  time: 0.4184  data: 0.0008  max mem: 31830
Epoch: [122]  [ 60/312]  eta: 0:02:43  lr: 0.002823  min_lr: 0.002823  loss: 3.9199 (3.7131)  weight_decay: 0.0500 (0.0500)  time: 0.4193  data: 0.0016  max mem: 31830
Epoch: [122]  [ 70/312]  eta: 0:02:35  lr: 0.002823  min_lr: 0.002823  loss: 3.9432 (3.7073)  weight_decay: 0.0500 (0.0500)  time: 0.4931  data: 0.0387  max mem: 31830
Epoch: [122]  [ 80/312]  eta: 0:02:24  lr: 0.002822  min_lr: 0.002822  loss: 3.7879 (3.7078)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.0758  max mem: 31830
Epoch: [122]  [ 90/312]  eta: 0:02:13  lr: 0.002822  min_lr: 0.002822  loss: 3.9272 (3.7364)  weight_decay: 0.0500 (0.0500)  time: 0.4675  data: 0.0606  max mem: 31830
Epoch: [122]  [100/312]  eta: 0:02:07  lr: 0.002821  min_lr: 0.002821  loss: 3.8937 (3.7343)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.1315  max mem: 31830
Epoch: [122]  [110/312]  eta: 0:01:58  lr: 0.002820  min_lr: 0.002820  loss: 3.6991 (3.7323)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.1099  max mem: 31830
Epoch: [122]  [120/312]  eta: 0:01:52  lr: 0.002820  min_lr: 0.002820  loss: 3.6902 (3.7077)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0906  max mem: 31830
Epoch: [122]  [130/312]  eta: 0:01:47  lr: 0.002819  min_lr: 0.002819  loss: 3.6685 (3.7049)  weight_decay: 0.0500 (0.0500)  time: 0.6049  data: 0.1778  max mem: 31830
Epoch: [122]  [140/312]  eta: 0:01:39  lr: 0.002818  min_lr: 0.002818  loss: 3.8543 (3.7050)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0882  max mem: 31830
Epoch: [122]  [150/312]  eta: 0:01:33  lr: 0.002818  min_lr: 0.002818  loss: 3.8764 (3.7171)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0664  max mem: 31830
Epoch: [122]  [160/312]  eta: 0:01:27  lr: 0.002817  min_lr: 0.002817  loss: 3.8413 (3.7023)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.0926  max mem: 31830
Epoch: [122]  [170/312]  eta: 0:01:20  lr: 0.002816  min_lr: 0.002816  loss: 3.8310 (3.7110)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0638  max mem: 31830
Epoch: [122]  [180/312]  eta: 0:01:15  lr: 0.002816  min_lr: 0.002816  loss: 3.9052 (3.7133)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.1080  max mem: 31830
Epoch: [122]  [190/312]  eta: 0:01:09  lr: 0.002815  min_lr: 0.002815  loss: 3.8303 (3.7129)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0710  max mem: 31830
Epoch: [122]  [200/312]  eta: 0:01:03  lr: 0.002814  min_lr: 0.002814  loss: 3.7173 (3.7129)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0448  max mem: 31830
Epoch: [122]  [210/312]  eta: 0:00:58  lr: 0.002814  min_lr: 0.002814  loss: 3.8604 (3.7186)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.0708  max mem: 31830
Epoch: [122]  [220/312]  eta: 0:00:52  lr: 0.002813  min_lr: 0.002813  loss: 3.8604 (3.7184)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0267  max mem: 31830
Epoch: [122]  [230/312]  eta: 0:00:46  lr: 0.002812  min_lr: 0.002812  loss: 3.6154 (3.7098)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0165  max mem: 31830
Epoch: [122]  [240/312]  eta: 0:00:40  lr: 0.002812  min_lr: 0.002812  loss: 3.4809 (3.7010)  weight_decay: 0.0500 (0.0500)  time: 0.5552  data: 0.0164  max mem: 31830
Epoch: [122]  [250/312]  eta: 0:00:34  lr: 0.002811  min_lr: 0.002811  loss: 3.4884 (3.6951)  weight_decay: 0.0500 (0.0500)  time: 0.5672  data: 0.0067  max mem: 31830
Epoch: [122]  [260/312]  eta: 0:00:29  lr: 0.002810  min_lr: 0.002810  loss: 3.5857 (3.6856)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0203  max mem: 31830
Epoch: [122]  [270/312]  eta: 0:00:23  lr: 0.002810  min_lr: 0.002810  loss: 3.5826 (3.6786)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0144  max mem: 31830
Epoch: [122]  [280/312]  eta: 0:00:17  lr: 0.002809  min_lr: 0.002809  loss: 3.5890 (3.6751)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0086  max mem: 31830
Epoch: [122]  [290/312]  eta: 0:00:12  lr: 0.002808  min_lr: 0.002808  loss: 3.6237 (3.6763)  weight_decay: 0.0500 (0.0500)  time: 0.5402  data: 0.0082  max mem: 31830
Epoch: [122]  [300/312]  eta: 0:00:06  lr: 0.002808  min_lr: 0.002808  loss: 3.6237 (3.6776)  weight_decay: 0.0500 (0.0500)  time: 0.5128  data: 0.0002  max mem: 31830
Epoch: [122]  [310/312]  eta: 0:00:01  lr: 0.002807  min_lr: 0.002807  loss: 3.6744 (3.6780)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0001  max mem: 31830
Epoch: [122]  [311/312]  eta: 0:00:00  lr: 0.002807  min_lr: 0.002807  loss: 3.6664 (3.6756)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0001  max mem: 31830
Epoch: [122] Total time: 0:02:52 (0.5536 s / it)
Averaged stats: lr: 0.002807  min_lr: 0.002807  loss: 3.6664 (3.6915)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.3474 (1.3474)  acc1: 76.5625 (76.5625)  acc5: 92.8385 (92.8385)  time: 8.3501  data: 8.1916  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6941 (1.6183)  acc1: 66.9271 (67.7600)  acc5: 88.6719 (88.4000)  time: 1.0501  data: 0.9103  max mem: 31830
Test: Total time: 0:00:09 (1.0657 s / it)
* Acc@1 67.672 Acc@5 88.664 loss 1.611
Accuracy of the model on the 50000 test images: 67.7%
Max accuracy: 68.06%
Epoch: [123]  [  0/312]  eta: 1:02:24  lr: 0.002807  min_lr: 0.002807  loss: 3.2093 (3.2093)  weight_decay: 0.0500 (0.0500)  time: 12.0007  data: 8.0041  max mem: 31830
Epoch: [123]  [ 10/312]  eta: 0:08:30  lr: 0.002806  min_lr: 0.002806  loss: 3.8630 (3.5652)  weight_decay: 0.0500 (0.0500)  time: 1.6892  data: 0.8586  max mem: 31830
Epoch: [123]  [ 20/312]  eta: 0:05:22  lr: 0.002806  min_lr: 0.002806  loss: 3.8827 (3.6717)  weight_decay: 0.0500 (0.0500)  time: 0.5584  data: 0.0938  max mem: 31830
Epoch: [123]  [ 30/312]  eta: 0:04:06  lr: 0.002805  min_lr: 0.002805  loss: 3.7660 (3.5751)  weight_decay: 0.0500 (0.0500)  time: 0.4281  data: 0.0221  max mem: 31830
Epoch: [123]  [ 40/312]  eta: 0:03:26  lr: 0.002804  min_lr: 0.002804  loss: 3.5097 (3.5585)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0009  max mem: 31830
Epoch: [123]  [ 50/312]  eta: 0:03:05  lr: 0.002804  min_lr: 0.002804  loss: 3.6249 (3.6070)  weight_decay: 0.0500 (0.0500)  time: 0.4527  data: 0.0012  max mem: 31830
Epoch: [123]  [ 60/312]  eta: 0:02:46  lr: 0.002803  min_lr: 0.002803  loss: 3.9615 (3.6449)  weight_decay: 0.0500 (0.0500)  time: 0.4526  data: 0.0021  max mem: 31830
Epoch: [123]  [ 70/312]  eta: 0:02:40  lr: 0.002802  min_lr: 0.002802  loss: 3.7655 (3.6148)  weight_decay: 0.0500 (0.0500)  time: 0.5378  data: 0.0020  max mem: 31830
Epoch: [123]  [ 80/312]  eta: 0:02:28  lr: 0.002802  min_lr: 0.002802  loss: 3.4902 (3.6079)  weight_decay: 0.0500 (0.0500)  time: 0.5799  data: 0.0010  max mem: 31830
Epoch: [123]  [ 90/312]  eta: 0:02:19  lr: 0.002801  min_lr: 0.002801  loss: 3.4902 (3.6099)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0008  max mem: 31830
Epoch: [123]  [100/312]  eta: 0:02:11  lr: 0.002800  min_lr: 0.002800  loss: 3.7350 (3.6249)  weight_decay: 0.0500 (0.0500)  time: 0.5437  data: 0.0008  max mem: 31830
Epoch: [123]  [110/312]  eta: 0:02:01  lr: 0.002800  min_lr: 0.002800  loss: 3.6567 (3.6151)  weight_decay: 0.0500 (0.0500)  time: 0.4728  data: 0.0008  max mem: 31830
Epoch: [123]  [120/312]  eta: 0:01:55  lr: 0.002799  min_lr: 0.002799  loss: 3.4326 (3.6129)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0008  max mem: 31830
Epoch: [123]  [130/312]  eta: 0:01:49  lr: 0.002798  min_lr: 0.002798  loss: 3.9542 (3.6320)  weight_decay: 0.0500 (0.0500)  time: 0.5984  data: 0.0008  max mem: 31830
Epoch: [123]  [140/312]  eta: 0:01:40  lr: 0.002798  min_lr: 0.002798  loss: 3.9860 (3.6500)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0008  max mem: 31830
Epoch: [123]  [150/312]  eta: 0:01:35  lr: 0.002797  min_lr: 0.002797  loss: 3.8850 (3.6507)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0010  max mem: 31830
Epoch: [123]  [160/312]  eta: 0:01:28  lr: 0.002796  min_lr: 0.002796  loss: 3.6621 (3.6430)  weight_decay: 0.0500 (0.0500)  time: 0.5630  data: 0.0018  max mem: 31830
Epoch: [123]  [170/312]  eta: 0:01:22  lr: 0.002796  min_lr: 0.002796  loss: 3.3464 (3.6344)  weight_decay: 0.0500 (0.0500)  time: 0.4913  data: 0.0016  max mem: 31830
Epoch: [123]  [180/312]  eta: 0:01:16  lr: 0.002795  min_lr: 0.002795  loss: 3.5206 (3.6338)  weight_decay: 0.0500 (0.0500)  time: 0.5614  data: 0.0008  max mem: 31830
Epoch: [123]  [190/312]  eta: 0:01:09  lr: 0.002794  min_lr: 0.002794  loss: 3.6121 (3.6299)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0008  max mem: 31830
Epoch: [123]  [200/312]  eta: 0:01:04  lr: 0.002794  min_lr: 0.002794  loss: 3.7381 (3.6374)  weight_decay: 0.0500 (0.0500)  time: 0.5060  data: 0.0059  max mem: 31830
Epoch: [123]  [210/312]  eta: 0:00:58  lr: 0.002793  min_lr: 0.002793  loss: 3.8693 (3.6299)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.0062  max mem: 31830
Epoch: [123]  [220/312]  eta: 0:00:52  lr: 0.002792  min_lr: 0.002792  loss: 3.6540 (3.6267)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0015  max mem: 31830
Epoch: [123]  [230/312]  eta: 0:00:46  lr: 0.002792  min_lr: 0.002792  loss: 3.7616 (3.6313)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0014  max mem: 31830
Epoch: [123]  [240/312]  eta: 0:00:40  lr: 0.002791  min_lr: 0.002791  loss: 3.9025 (3.6320)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0008  max mem: 31830
Epoch: [123]  [250/312]  eta: 0:00:35  lr: 0.002790  min_lr: 0.002790  loss: 3.7277 (3.6346)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0012  max mem: 31830
Epoch: [123]  [260/312]  eta: 0:00:29  lr: 0.002790  min_lr: 0.002790  loss: 3.7277 (3.6380)  weight_decay: 0.0500 (0.0500)  time: 0.5699  data: 0.0013  max mem: 31830
Epoch: [123]  [270/312]  eta: 0:00:23  lr: 0.002789  min_lr: 0.002789  loss: 3.7018 (3.6324)  weight_decay: 0.0500 (0.0500)  time: 0.5237  data: 0.0139  max mem: 31830
Epoch: [123]  [280/312]  eta: 0:00:18  lr: 0.002788  min_lr: 0.002788  loss: 3.6455 (3.6339)  weight_decay: 0.0500 (0.0500)  time: 0.4923  data: 0.0150  max mem: 31830
Epoch: [123]  [290/312]  eta: 0:00:12  lr: 0.002788  min_lr: 0.002788  loss: 3.5101 (3.6302)  weight_decay: 0.0500 (0.0500)  time: 0.5647  data: 0.0261  max mem: 31830
Epoch: [123]  [300/312]  eta: 0:00:06  lr: 0.002787  min_lr: 0.002787  loss: 3.7721 (3.6314)  weight_decay: 0.0500 (0.0500)  time: 0.4845  data: 0.0245  max mem: 31830
Epoch: [123]  [310/312]  eta: 0:00:01  lr: 0.002786  min_lr: 0.002786  loss: 3.6707 (3.6326)  weight_decay: 0.0500 (0.0500)  time: 0.3899  data: 0.0001  max mem: 31830
Epoch: [123]  [311/312]  eta: 0:00:00  lr: 0.002786  min_lr: 0.002786  loss: 3.7721 (3.6333)  weight_decay: 0.0500 (0.0500)  time: 0.3897  data: 0.0001  max mem: 31830
Epoch: [123] Total time: 0:02:53 (0.5557 s / it)
Averaged stats: lr: 0.002786  min_lr: 0.002786  loss: 3.7721 (3.6595)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4526 (1.4526)  acc1: 74.8698 (74.8698)  acc5: 93.2292 (93.2292)  time: 8.3679  data: 8.2014  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7784 (1.6440)  acc1: 65.7552 (68.1440)  acc5: 87.5000 (88.6720)  time: 1.0715  data: 0.9281  max mem: 31830
Test: Total time: 0:00:09 (1.0823 s / it)
* Acc@1 68.096 Acc@5 89.028 loss 1.643
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 68.10%
Epoch: [124]  [  0/312]  eta: 1:01:58  lr: 0.002786  min_lr: 0.002786  loss: 2.7687 (2.7687)  weight_decay: 0.0500 (0.0500)  time: 11.9189  data: 9.5922  max mem: 31830
Epoch: [124]  [ 10/312]  eta: 0:08:19  lr: 0.002786  min_lr: 0.002786  loss: 3.7084 (3.6353)  weight_decay: 0.0500 (0.0500)  time: 1.6551  data: 0.9636  max mem: 31830
Epoch: [124]  [ 20/312]  eta: 0:05:23  lr: 0.002785  min_lr: 0.002785  loss: 3.7084 (3.6612)  weight_decay: 0.0500 (0.0500)  time: 0.5682  data: 0.0507  max mem: 31830
Epoch: [124]  [ 30/312]  eta: 0:04:08  lr: 0.002784  min_lr: 0.002784  loss: 3.8558 (3.6580)  weight_decay: 0.0500 (0.0500)  time: 0.4541  data: 0.0006  max mem: 31830
Epoch: [124]  [ 40/312]  eta: 0:03:27  lr: 0.002784  min_lr: 0.002784  loss: 3.8597 (3.6320)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0007  max mem: 31830
Epoch: [124]  [ 50/312]  eta: 0:03:06  lr: 0.002783  min_lr: 0.002783  loss: 3.9802 (3.7050)  weight_decay: 0.0500 (0.0500)  time: 0.4481  data: 0.0007  max mem: 31830
Epoch: [124]  [ 60/312]  eta: 0:02:46  lr: 0.002782  min_lr: 0.002782  loss: 3.9459 (3.6976)  weight_decay: 0.0500 (0.0500)  time: 0.4452  data: 0.0008  max mem: 31830
Epoch: [124]  [ 70/312]  eta: 0:02:36  lr: 0.002782  min_lr: 0.002782  loss: 3.7684 (3.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4837  data: 0.0008  max mem: 31830
Epoch: [124]  [ 80/312]  eta: 0:02:28  lr: 0.002781  min_lr: 0.002781  loss: 3.4115 (3.6374)  weight_decay: 0.0500 (0.0500)  time: 0.5762  data: 0.0007  max mem: 31830
Epoch: [124]  [ 90/312]  eta: 0:02:17  lr: 0.002780  min_lr: 0.002780  loss: 3.5185 (3.6366)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0006  max mem: 31830
Epoch: [124]  [100/312]  eta: 0:02:09  lr: 0.002780  min_lr: 0.002780  loss: 3.7131 (3.6332)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0008  max mem: 31830
Epoch: [124]  [110/312]  eta: 0:01:59  lr: 0.002779  min_lr: 0.002779  loss: 3.8714 (3.6503)  weight_decay: 0.0500 (0.0500)  time: 0.4877  data: 0.0141  max mem: 31830
Epoch: [124]  [120/312]  eta: 0:01:54  lr: 0.002778  min_lr: 0.002778  loss: 3.9280 (3.6445)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.0140  max mem: 31830
Epoch: [124]  [130/312]  eta: 0:01:47  lr: 0.002778  min_lr: 0.002778  loss: 3.4082 (3.6168)  weight_decay: 0.0500 (0.0500)  time: 0.5891  data: 0.0024  max mem: 31830
Epoch: [124]  [140/312]  eta: 0:01:39  lr: 0.002777  min_lr: 0.002777  loss: 3.1125 (3.5910)  weight_decay: 0.0500 (0.0500)  time: 0.4632  data: 0.0026  max mem: 31830
Epoch: [124]  [150/312]  eta: 0:01:34  lr: 0.002776  min_lr: 0.002776  loss: 3.3157 (3.5893)  weight_decay: 0.0500 (0.0500)  time: 0.5312  data: 0.0015  max mem: 31830
Epoch: [124]  [160/312]  eta: 0:01:28  lr: 0.002776  min_lr: 0.002776  loss: 3.6369 (3.5828)  weight_decay: 0.0500 (0.0500)  time: 0.5877  data: 0.0077  max mem: 31830
Epoch: [124]  [170/312]  eta: 0:01:21  lr: 0.002775  min_lr: 0.002775  loss: 3.5784 (3.5752)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0070  max mem: 31830
Epoch: [124]  [180/312]  eta: 0:01:16  lr: 0.002774  min_lr: 0.002774  loss: 3.7657 (3.5925)  weight_decay: 0.0500 (0.0500)  time: 0.5837  data: 0.0084  max mem: 31830
Epoch: [124]  [190/312]  eta: 0:01:09  lr: 0.002774  min_lr: 0.002774  loss: 3.9512 (3.6034)  weight_decay: 0.0500 (0.0500)  time: 0.5434  data: 0.0090  max mem: 31830
Epoch: [124]  [200/312]  eta: 0:01:03  lr: 0.002773  min_lr: 0.002773  loss: 3.9512 (3.6153)  weight_decay: 0.0500 (0.0500)  time: 0.4884  data: 0.0014  max mem: 31830
Epoch: [124]  [210/312]  eta: 0:00:58  lr: 0.002772  min_lr: 0.002772  loss: 3.9687 (3.6293)  weight_decay: 0.0500 (0.0500)  time: 0.6225  data: 0.0010  max mem: 31830
Epoch: [124]  [220/312]  eta: 0:00:52  lr: 0.002772  min_lr: 0.002772  loss: 3.8589 (3.6404)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0009  max mem: 31830
Epoch: [124]  [230/312]  eta: 0:00:46  lr: 0.002771  min_lr: 0.002771  loss: 3.8198 (3.6416)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0008  max mem: 31830
Epoch: [124]  [240/312]  eta: 0:00:40  lr: 0.002770  min_lr: 0.002770  loss: 3.6987 (3.6337)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.0011  max mem: 31830
Epoch: [124]  [250/312]  eta: 0:00:35  lr: 0.002770  min_lr: 0.002770  loss: 3.3935 (3.6298)  weight_decay: 0.0500 (0.0500)  time: 0.5603  data: 0.0012  max mem: 31830
Epoch: [124]  [260/312]  eta: 0:00:29  lr: 0.002769  min_lr: 0.002769  loss: 3.5745 (3.6300)  weight_decay: 0.0500 (0.0500)  time: 0.6580  data: 0.0275  max mem: 31830
Epoch: [124]  [270/312]  eta: 0:00:23  lr: 0.002768  min_lr: 0.002768  loss: 4.0624 (3.6483)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0274  max mem: 31830
Epoch: [124]  [280/312]  eta: 0:00:18  lr: 0.002768  min_lr: 0.002768  loss: 3.9651 (3.6396)  weight_decay: 0.0500 (0.0500)  time: 0.5283  data: 0.0024  max mem: 31830
Epoch: [124]  [290/312]  eta: 0:00:12  lr: 0.002767  min_lr: 0.002767  loss: 3.5148 (3.6402)  weight_decay: 0.0500 (0.0500)  time: 0.5664  data: 0.0021  max mem: 31830
Epoch: [124]  [300/312]  eta: 0:00:06  lr: 0.002766  min_lr: 0.002766  loss: 3.8676 (3.6482)  weight_decay: 0.0500 (0.0500)  time: 0.4484  data: 0.0002  max mem: 31830
Epoch: [124]  [310/312]  eta: 0:00:01  lr: 0.002766  min_lr: 0.002766  loss: 3.7175 (3.6464)  weight_decay: 0.0500 (0.0500)  time: 0.4021  data: 0.0001  max mem: 31830
Epoch: [124]  [311/312]  eta: 0:00:00  lr: 0.002766  min_lr: 0.002766  loss: 3.6950 (3.6452)  weight_decay: 0.0500 (0.0500)  time: 0.4020  data: 0.0001  max mem: 31830
Epoch: [124] Total time: 0:02:54 (0.5580 s / it)
Averaged stats: lr: 0.002766  min_lr: 0.002766  loss: 3.6950 (3.6597)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.3445 (1.3445)  acc1: 76.5625 (76.5625)  acc5: 92.4479 (92.4479)  time: 7.9998  data: 7.8328  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6966 (1.5975)  acc1: 67.3177 (68.7200)  acc5: 88.1510 (88.7200)  time: 1.0106  data: 0.8720  max mem: 31830
Test: Total time: 0:00:09 (1.0208 s / it)
* Acc@1 68.130 Acc@5 88.914 loss 1.604
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 68.13%
Epoch: [125]  [  0/312]  eta: 0:59:25  lr: 0.002766  min_lr: 0.002766  loss: 3.9826 (3.9826)  weight_decay: 0.0500 (0.0500)  time: 11.4266  data: 8.8844  max mem: 31830
Epoch: [125]  [ 10/312]  eta: 0:08:43  lr: 0.002765  min_lr: 0.002765  loss: 3.4293 (3.5008)  weight_decay: 0.0500 (0.0500)  time: 1.7345  data: 0.9516  max mem: 31830
Epoch: [125]  [ 20/312]  eta: 0:05:22  lr: 0.002764  min_lr: 0.002764  loss: 3.3357 (3.4308)  weight_decay: 0.0500 (0.0500)  time: 0.5880  data: 0.0795  max mem: 31830
Epoch: [125]  [ 30/312]  eta: 0:04:07  lr: 0.002764  min_lr: 0.002764  loss: 3.6490 (3.5119)  weight_decay: 0.0500 (0.0500)  time: 0.4053  data: 0.0008  max mem: 31830
Epoch: [125]  [ 40/312]  eta: 0:03:26  lr: 0.002763  min_lr: 0.002763  loss: 3.8608 (3.5489)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0007  max mem: 31830
Epoch: [125]  [ 50/312]  eta: 0:03:00  lr: 0.002762  min_lr: 0.002762  loss: 3.9604 (3.6427)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [125]  [ 60/312]  eta: 0:02:41  lr: 0.002762  min_lr: 0.002762  loss: 3.8426 (3.6154)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0010  max mem: 31830
Epoch: [125]  [ 70/312]  eta: 0:02:31  lr: 0.002761  min_lr: 0.002761  loss: 3.8205 (3.6428)  weight_decay: 0.0500 (0.0500)  time: 0.4676  data: 0.0012  max mem: 31830
Epoch: [125]  [ 80/312]  eta: 0:02:24  lr: 0.002760  min_lr: 0.002760  loss: 3.8421 (3.6742)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0011  max mem: 31830
Epoch: [125]  [ 90/312]  eta: 0:02:14  lr: 0.002760  min_lr: 0.002760  loss: 3.9598 (3.6895)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0008  max mem: 31830
Epoch: [125]  [100/312]  eta: 0:02:07  lr: 0.002759  min_lr: 0.002759  loss: 3.8441 (3.6722)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0010  max mem: 31830
Epoch: [125]  [110/312]  eta: 0:01:59  lr: 0.002758  min_lr: 0.002758  loss: 3.8441 (3.6925)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0011  max mem: 31830
Epoch: [125]  [120/312]  eta: 0:01:52  lr: 0.002758  min_lr: 0.002758  loss: 3.8741 (3.6939)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0065  max mem: 31830
Epoch: [125]  [130/312]  eta: 0:01:47  lr: 0.002757  min_lr: 0.002757  loss: 3.8344 (3.6871)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.0071  max mem: 31830
Epoch: [125]  [140/312]  eta: 0:01:39  lr: 0.002756  min_lr: 0.002756  loss: 3.7458 (3.6785)  weight_decay: 0.0500 (0.0500)  time: 0.5337  data: 0.0015  max mem: 31830
Epoch: [125]  [150/312]  eta: 0:01:34  lr: 0.002756  min_lr: 0.002756  loss: 3.4231 (3.6622)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0010  max mem: 31830
Epoch: [125]  [160/312]  eta: 0:01:28  lr: 0.002755  min_lr: 0.002755  loss: 3.8392 (3.6561)  weight_decay: 0.0500 (0.0500)  time: 0.5830  data: 0.0140  max mem: 31830
Epoch: [125]  [170/312]  eta: 0:01:21  lr: 0.002754  min_lr: 0.002754  loss: 3.6050 (3.6552)  weight_decay: 0.0500 (0.0500)  time: 0.5080  data: 0.0139  max mem: 31830
Epoch: [125]  [180/312]  eta: 0:01:15  lr: 0.002754  min_lr: 0.002754  loss: 3.8567 (3.6761)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0016  max mem: 31830
Epoch: [125]  [190/312]  eta: 0:01:09  lr: 0.002753  min_lr: 0.002753  loss: 3.8255 (3.6742)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.0073  max mem: 31830
Epoch: [125]  [200/312]  eta: 0:01:03  lr: 0.002752  min_lr: 0.002752  loss: 3.7256 (3.6817)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0129  max mem: 31830
Epoch: [125]  [210/312]  eta: 0:00:57  lr: 0.002752  min_lr: 0.002752  loss: 3.8825 (3.6803)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0073  max mem: 31830
Epoch: [125]  [220/312]  eta: 0:00:51  lr: 0.002751  min_lr: 0.002751  loss: 3.8075 (3.6837)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0009  max mem: 31830
Epoch: [125]  [230/312]  eta: 0:00:46  lr: 0.002750  min_lr: 0.002750  loss: 3.8075 (3.6832)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0011  max mem: 31830
Epoch: [125]  [240/312]  eta: 0:00:40  lr: 0.002750  min_lr: 0.002750  loss: 3.7439 (3.6772)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0011  max mem: 31830
Epoch: [125]  [250/312]  eta: 0:00:34  lr: 0.002749  min_lr: 0.002749  loss: 3.5577 (3.6726)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0022  max mem: 31830
Epoch: [125]  [260/312]  eta: 0:00:29  lr: 0.002748  min_lr: 0.002748  loss: 3.8381 (3.6822)  weight_decay: 0.0500 (0.0500)  time: 0.5510  data: 0.0024  max mem: 31830
Epoch: [125]  [270/312]  eta: 0:00:23  lr: 0.002748  min_lr: 0.002748  loss: 3.7514 (3.6764)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0009  max mem: 31830
Epoch: [125]  [280/312]  eta: 0:00:17  lr: 0.002747  min_lr: 0.002747  loss: 3.5655 (3.6757)  weight_decay: 0.0500 (0.0500)  time: 0.5007  data: 0.0028  max mem: 31830
Epoch: [125]  [290/312]  eta: 0:00:12  lr: 0.002746  min_lr: 0.002746  loss: 3.4755 (3.6682)  weight_decay: 0.0500 (0.0500)  time: 0.5464  data: 0.0025  max mem: 31830
Epoch: [125]  [300/312]  eta: 0:00:06  lr: 0.002746  min_lr: 0.002746  loss: 3.3600 (3.6631)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0002  max mem: 31830
Epoch: [125]  [310/312]  eta: 0:00:01  lr: 0.002745  min_lr: 0.002745  loss: 3.5683 (3.6693)  weight_decay: 0.0500 (0.0500)  time: 0.4015  data: 0.0002  max mem: 31830
Epoch: [125]  [311/312]  eta: 0:00:00  lr: 0.002745  min_lr: 0.002745  loss: 3.5683 (3.6662)  weight_decay: 0.0500 (0.0500)  time: 0.4007  data: 0.0001  max mem: 31830
Epoch: [125] Total time: 0:02:52 (0.5535 s / it)
Averaged stats: lr: 0.002745  min_lr: 0.002745  loss: 3.5683 (3.6854)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.7155 (1.7155)  acc1: 71.6146 (71.6146)  acc5: 91.1458 (91.1458)  time: 7.9548  data: 7.7877  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7632 (1.7257)  acc1: 68.3594 (67.2320)  acc5: 88.5417 (88.1920)  time: 1.0534  data: 0.9187  max mem: 31830
Test: Total time: 0:00:09 (1.0645 s / it)
* Acc@1 67.234 Acc@5 88.380 loss 1.715
Accuracy of the model on the 50000 test images: 67.2%
Max accuracy: 68.13%
Epoch: [126]  [  0/312]  eta: 1:02:52  lr: 0.002745  min_lr: 0.002745  loss: 3.4286 (3.4286)  weight_decay: 0.0500 (0.0500)  time: 12.0905  data: 9.7369  max mem: 31830
Epoch: [126]  [ 10/312]  eta: 0:08:48  lr: 0.002744  min_lr: 0.002744  loss: 3.6583 (3.7869)  weight_decay: 0.0500 (0.0500)  time: 1.7497  data: 1.0415  max mem: 31830
Epoch: [126]  [ 20/312]  eta: 0:05:25  lr: 0.002744  min_lr: 0.002744  loss: 3.5510 (3.5352)  weight_decay: 0.0500 (0.0500)  time: 0.5668  data: 0.0862  max mem: 31830
Epoch: [126]  [ 30/312]  eta: 0:04:09  lr: 0.002743  min_lr: 0.002743  loss: 3.2434 (3.5134)  weight_decay: 0.0500 (0.0500)  time: 0.4083  data: 0.0009  max mem: 31830
Epoch: [126]  [ 40/312]  eta: 0:03:27  lr: 0.002742  min_lr: 0.002742  loss: 3.6124 (3.5912)  weight_decay: 0.0500 (0.0500)  time: 0.3944  data: 0.0010  max mem: 31830
Epoch: [126]  [ 50/312]  eta: 0:03:01  lr: 0.002742  min_lr: 0.002742  loss: 3.8854 (3.6251)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0008  max mem: 31830
Epoch: [126]  [ 60/312]  eta: 0:02:42  lr: 0.002741  min_lr: 0.002741  loss: 3.7469 (3.6134)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0008  max mem: 31830
Epoch: [126]  [ 70/312]  eta: 0:02:31  lr: 0.002740  min_lr: 0.002740  loss: 3.8591 (3.6248)  weight_decay: 0.0500 (0.0500)  time: 0.4626  data: 0.0388  max mem: 31830
Epoch: [126]  [ 80/312]  eta: 0:02:24  lr: 0.002740  min_lr: 0.002740  loss: 3.8930 (3.6182)  weight_decay: 0.0500 (0.0500)  time: 0.5662  data: 0.0852  max mem: 31830
Epoch: [126]  [ 90/312]  eta: 0:02:13  lr: 0.002739  min_lr: 0.002739  loss: 3.9889 (3.6658)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0610  max mem: 31830
Epoch: [126]  [100/312]  eta: 0:02:08  lr: 0.002738  min_lr: 0.002738  loss: 3.9336 (3.6619)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0762  max mem: 31830
Epoch: [126]  [110/312]  eta: 0:01:59  lr: 0.002738  min_lr: 0.002738  loss: 3.8623 (3.6754)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0632  max mem: 31830
Epoch: [126]  [120/312]  eta: 0:01:53  lr: 0.002737  min_lr: 0.002737  loss: 3.8570 (3.6740)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0455  max mem: 31830
Epoch: [126]  [130/312]  eta: 0:01:47  lr: 0.002736  min_lr: 0.002736  loss: 3.6081 (3.6603)  weight_decay: 0.0500 (0.0500)  time: 0.5876  data: 0.0765  max mem: 31830
Epoch: [126]  [140/312]  eta: 0:01:39  lr: 0.002736  min_lr: 0.002736  loss: 3.6245 (3.6667)  weight_decay: 0.0500 (0.0500)  time: 0.4829  data: 0.0347  max mem: 31830
Epoch: [126]  [150/312]  eta: 0:01:33  lr: 0.002735  min_lr: 0.002735  loss: 3.7325 (3.6645)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0312  max mem: 31830
Epoch: [126]  [160/312]  eta: 0:01:28  lr: 0.002734  min_lr: 0.002734  loss: 3.7316 (3.6649)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.0721  max mem: 31830
Epoch: [126]  [170/312]  eta: 0:01:21  lr: 0.002734  min_lr: 0.002734  loss: 3.7936 (3.6759)  weight_decay: 0.0500 (0.0500)  time: 0.5360  data: 0.0440  max mem: 31830
Epoch: [126]  [180/312]  eta: 0:01:15  lr: 0.002733  min_lr: 0.002733  loss: 3.7842 (3.6654)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0252  max mem: 31830
Epoch: [126]  [190/312]  eta: 0:01:09  lr: 0.002732  min_lr: 0.002732  loss: 3.7478 (3.6720)  weight_decay: 0.0500 (0.0500)  time: 0.5236  data: 0.0251  max mem: 31830
Epoch: [126]  [200/312]  eta: 0:01:03  lr: 0.002732  min_lr: 0.002732  loss: 3.8737 (3.6735)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0289  max mem: 31830
Epoch: [126]  [210/312]  eta: 0:00:58  lr: 0.002731  min_lr: 0.002731  loss: 3.9842 (3.6915)  weight_decay: 0.0500 (0.0500)  time: 0.6165  data: 0.0578  max mem: 31830
Epoch: [126]  [220/312]  eta: 0:00:51  lr: 0.002730  min_lr: 0.002730  loss: 3.9122 (3.6891)  weight_decay: 0.0500 (0.0500)  time: 0.5251  data: 0.0298  max mem: 31830
Epoch: [126]  [230/312]  eta: 0:00:46  lr: 0.002730  min_lr: 0.002730  loss: 3.5615 (3.6791)  weight_decay: 0.0500 (0.0500)  time: 0.5480  data: 0.0068  max mem: 31830
Epoch: [126]  [240/312]  eta: 0:00:40  lr: 0.002729  min_lr: 0.002729  loss: 3.3706 (3.6688)  weight_decay: 0.0500 (0.0500)  time: 0.6143  data: 0.0071  max mem: 31830
Epoch: [126]  [250/312]  eta: 0:00:34  lr: 0.002728  min_lr: 0.002728  loss: 3.7884 (3.6644)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0027  max mem: 31830
Epoch: [126]  [260/312]  eta: 0:00:29  lr: 0.002728  min_lr: 0.002728  loss: 3.7294 (3.6665)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0025  max mem: 31830
Epoch: [126]  [270/312]  eta: 0:00:23  lr: 0.002727  min_lr: 0.002727  loss: 3.8287 (3.6764)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0008  max mem: 31830
Epoch: [126]  [280/312]  eta: 0:00:17  lr: 0.002726  min_lr: 0.002726  loss: 3.8975 (3.6820)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0047  max mem: 31830
Epoch: [126]  [290/312]  eta: 0:00:12  lr: 0.002726  min_lr: 0.002726  loss: 3.8897 (3.6821)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0236  max mem: 31830
Epoch: [126]  [300/312]  eta: 0:00:06  lr: 0.002725  min_lr: 0.002725  loss: 3.7155 (3.6772)  weight_decay: 0.0500 (0.0500)  time: 0.4826  data: 0.0296  max mem: 31830
Epoch: [126]  [310/312]  eta: 0:00:01  lr: 0.002724  min_lr: 0.002724  loss: 3.7225 (3.6822)  weight_decay: 0.0500 (0.0500)  time: 0.3911  data: 0.0103  max mem: 31830
Epoch: [126]  [311/312]  eta: 0:00:00  lr: 0.002724  min_lr: 0.002724  loss: 3.7359 (3.6833)  weight_decay: 0.0500 (0.0500)  time: 0.3908  data: 0.0103  max mem: 31830
Epoch: [126] Total time: 0:02:52 (0.5537 s / it)
Averaged stats: lr: 0.002724  min_lr: 0.002724  loss: 3.7359 (3.6769)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 1.5726 (1.5726)  acc1: 74.0885 (74.0885)  acc5: 91.5365 (91.5365)  time: 7.6862  data: 7.5193  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9547 (1.8171)  acc1: 65.3646 (66.8000)  acc5: 88.1510 (88.5440)  time: 1.0237  data: 0.8887  max mem: 31830
Test: Total time: 0:00:09 (1.0357 s / it)
* Acc@1 66.944 Acc@5 87.990 loss 1.824
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 68.13%
Epoch: [127]  [  0/312]  eta: 1:04:10  lr: 0.002724  min_lr: 0.002724  loss: 3.4910 (3.4910)  weight_decay: 0.0500 (0.0500)  time: 12.3398  data: 9.0967  max mem: 31830
Epoch: [127]  [ 10/312]  eta: 0:08:52  lr: 0.002723  min_lr: 0.002723  loss: 3.4910 (3.6342)  weight_decay: 0.0500 (0.0500)  time: 1.7621  data: 0.9700  max mem: 31830
Epoch: [127]  [ 20/312]  eta: 0:05:30  lr: 0.002723  min_lr: 0.002723  loss: 3.7963 (3.6833)  weight_decay: 0.0500 (0.0500)  time: 0.5716  data: 0.0790  max mem: 31830
Epoch: [127]  [ 30/312]  eta: 0:04:12  lr: 0.002722  min_lr: 0.002722  loss: 3.8834 (3.6719)  weight_decay: 0.0500 (0.0500)  time: 0.4194  data: 0.0007  max mem: 31830
Epoch: [127]  [ 40/312]  eta: 0:03:30  lr: 0.002721  min_lr: 0.002721  loss: 3.6022 (3.6255)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0006  max mem: 31830
Epoch: [127]  [ 50/312]  eta: 0:03:04  lr: 0.002721  min_lr: 0.002721  loss: 3.7501 (3.6383)  weight_decay: 0.0500 (0.0500)  time: 0.4118  data: 0.0007  max mem: 31830
Epoch: [127]  [ 60/312]  eta: 0:02:45  lr: 0.002720  min_lr: 0.002720  loss: 3.8516 (3.6625)  weight_decay: 0.0500 (0.0500)  time: 0.4144  data: 0.0007  max mem: 31830
Epoch: [127]  [ 70/312]  eta: 0:02:35  lr: 0.002719  min_lr: 0.002719  loss: 3.8516 (3.6748)  weight_decay: 0.0500 (0.0500)  time: 0.4779  data: 0.0007  max mem: 31830
Epoch: [127]  [ 80/312]  eta: 0:02:26  lr: 0.002719  min_lr: 0.002719  loss: 3.8601 (3.6603)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0007  max mem: 31830
Epoch: [127]  [ 90/312]  eta: 0:02:16  lr: 0.002718  min_lr: 0.002718  loss: 3.7120 (3.6570)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0008  max mem: 31830
Epoch: [127]  [100/312]  eta: 0:02:10  lr: 0.002717  min_lr: 0.002717  loss: 3.8045 (3.6821)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0009  max mem: 31830
Epoch: [127]  [110/312]  eta: 0:02:00  lr: 0.002717  min_lr: 0.002717  loss: 3.9397 (3.6865)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0008  max mem: 31830
Epoch: [127]  [120/312]  eta: 0:01:55  lr: 0.002716  min_lr: 0.002716  loss: 3.8395 (3.6832)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0012  max mem: 31830
Epoch: [127]  [130/312]  eta: 0:01:49  lr: 0.002715  min_lr: 0.002715  loss: 3.9070 (3.6824)  weight_decay: 0.0500 (0.0500)  time: 0.6279  data: 0.0022  max mem: 31830
Epoch: [127]  [140/312]  eta: 0:01:41  lr: 0.002715  min_lr: 0.002715  loss: 3.9148 (3.6783)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0017  max mem: 31830
Epoch: [127]  [150/312]  eta: 0:01:36  lr: 0.002714  min_lr: 0.002714  loss: 3.7354 (3.6731)  weight_decay: 0.0500 (0.0500)  time: 0.5664  data: 0.0007  max mem: 31830
Epoch: [127]  [160/312]  eta: 0:01:28  lr: 0.002713  min_lr: 0.002713  loss: 3.5967 (3.6584)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0010  max mem: 31830
Epoch: [127]  [170/312]  eta: 0:01:23  lr: 0.002713  min_lr: 0.002713  loss: 3.5572 (3.6484)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0012  max mem: 31830
Epoch: [127]  [180/312]  eta: 0:01:17  lr: 0.002712  min_lr: 0.002712  loss: 3.6041 (3.6425)  weight_decay: 0.0500 (0.0500)  time: 0.5804  data: 0.0010  max mem: 31830
Epoch: [127]  [190/312]  eta: 0:01:10  lr: 0.002711  min_lr: 0.002711  loss: 3.8289 (3.6628)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0008  max mem: 31830
Epoch: [127]  [200/312]  eta: 0:01:05  lr: 0.002711  min_lr: 0.002711  loss: 3.8631 (3.6570)  weight_decay: 0.0500 (0.0500)  time: 0.5775  data: 0.0008  max mem: 31830
Epoch: [127]  [210/312]  eta: 0:00:59  lr: 0.002710  min_lr: 0.002710  loss: 3.7768 (3.6592)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0009  max mem: 31830
Epoch: [127]  [220/312]  eta: 0:00:52  lr: 0.002709  min_lr: 0.002709  loss: 3.7204 (3.6449)  weight_decay: 0.0500 (0.0500)  time: 0.4824  data: 0.0008  max mem: 31830
Epoch: [127]  [230/312]  eta: 0:00:47  lr: 0.002709  min_lr: 0.002709  loss: 3.7204 (3.6505)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0009  max mem: 31830
Epoch: [127]  [240/312]  eta: 0:00:40  lr: 0.002708  min_lr: 0.002708  loss: 3.7867 (3.6509)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0010  max mem: 31830
Epoch: [127]  [250/312]  eta: 0:00:35  lr: 0.002707  min_lr: 0.002707  loss: 3.8472 (3.6627)  weight_decay: 0.0500 (0.0500)  time: 0.5413  data: 0.0010  max mem: 31830
Epoch: [127]  [260/312]  eta: 0:00:29  lr: 0.002707  min_lr: 0.002707  loss: 3.7194 (3.6512)  weight_decay: 0.0500 (0.0500)  time: 0.6142  data: 0.0009  max mem: 31830
Epoch: [127]  [270/312]  eta: 0:00:23  lr: 0.002706  min_lr: 0.002706  loss: 3.4013 (3.6450)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0014  max mem: 31830
Epoch: [127]  [280/312]  eta: 0:00:18  lr: 0.002705  min_lr: 0.002705  loss: 3.4013 (3.6432)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0048  max mem: 31830
Epoch: [127]  [290/312]  eta: 0:00:12  lr: 0.002705  min_lr: 0.002705  loss: 3.8133 (3.6463)  weight_decay: 0.0500 (0.0500)  time: 0.5873  data: 0.0039  max mem: 31830
Epoch: [127]  [300/312]  eta: 0:00:06  lr: 0.002704  min_lr: 0.002704  loss: 3.7577 (3.6490)  weight_decay: 0.0500 (0.0500)  time: 0.4487  data: 0.0002  max mem: 31830
Epoch: [127]  [310/312]  eta: 0:00:01  lr: 0.002703  min_lr: 0.002703  loss: 3.6571 (3.6439)  weight_decay: 0.0500 (0.0500)  time: 0.3915  data: 0.0001  max mem: 31830
Epoch: [127]  [311/312]  eta: 0:00:00  lr: 0.002703  min_lr: 0.002703  loss: 3.6571 (3.6412)  weight_decay: 0.0500 (0.0500)  time: 0.3913  data: 0.0001  max mem: 31830
Epoch: [127] Total time: 0:02:55 (0.5614 s / it)
Averaged stats: lr: 0.002703  min_lr: 0.002703  loss: 3.6571 (3.6471)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:24  loss: 1.2028 (1.2028)  acc1: 75.9115 (75.9115)  acc5: 92.3177 (92.3177)  time: 9.3624  data: 9.1971  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5508 (1.4508)  acc1: 64.8438 (67.2800)  acc5: 87.8906 (88.3360)  time: 1.1572  data: 1.0219  max mem: 31830
Test: Total time: 0:00:10 (1.1697 s / it)
* Acc@1 67.316 Acc@5 88.502 loss 1.461
Accuracy of the model on the 50000 test images: 67.3%
Max accuracy: 68.13%
Epoch: [128]  [  0/312]  eta: 1:05:22  lr: 0.002703  min_lr: 0.002703  loss: 4.0219 (4.0219)  weight_decay: 0.0500 (0.0500)  time: 12.5721  data: 12.1718  max mem: 31830
Epoch: [128]  [ 10/312]  eta: 0:08:21  lr: 0.002702  min_lr: 0.002702  loss: 4.0640 (3.9642)  weight_decay: 0.0500 (0.0500)  time: 1.6604  data: 1.1071  max mem: 31830
Epoch: [128]  [ 20/312]  eta: 0:05:25  lr: 0.002702  min_lr: 0.002702  loss: 4.0147 (3.8391)  weight_decay: 0.0500 (0.0500)  time: 0.5427  data: 0.0552  max mem: 31830
Epoch: [128]  [ 30/312]  eta: 0:04:08  lr: 0.002701  min_lr: 0.002701  loss: 3.6538 (3.7355)  weight_decay: 0.0500 (0.0500)  time: 0.4544  data: 0.0552  max mem: 31830
Epoch: [128]  [ 40/312]  eta: 0:03:28  lr: 0.002700  min_lr: 0.002700  loss: 3.6538 (3.6881)  weight_decay: 0.0500 (0.0500)  time: 0.4035  data: 0.0007  max mem: 31830
Epoch: [128]  [ 50/312]  eta: 0:03:08  lr: 0.002700  min_lr: 0.002700  loss: 3.7462 (3.7341)  weight_decay: 0.0500 (0.0500)  time: 0.4702  data: 0.0126  max mem: 31830
Epoch: [128]  [ 60/312]  eta: 0:02:47  lr: 0.002699  min_lr: 0.002699  loss: 3.8401 (3.7458)  weight_decay: 0.0500 (0.0500)  time: 0.4581  data: 0.0125  max mem: 31830
Epoch: [128]  [ 70/312]  eta: 0:02:39  lr: 0.002698  min_lr: 0.002698  loss: 3.8401 (3.7318)  weight_decay: 0.0500 (0.0500)  time: 0.4988  data: 0.0897  max mem: 31830
Epoch: [128]  [ 80/312]  eta: 0:02:31  lr: 0.002698  min_lr: 0.002698  loss: 3.6318 (3.7117)  weight_decay: 0.0500 (0.0500)  time: 0.6068  data: 0.1488  max mem: 31830
Epoch: [128]  [ 90/312]  eta: 0:02:19  lr: 0.002697  min_lr: 0.002697  loss: 3.2047 (3.6694)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0599  max mem: 31830
Epoch: [128]  [100/312]  eta: 0:02:11  lr: 0.002696  min_lr: 0.002696  loss: 3.3684 (3.6656)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0505  max mem: 31830
Epoch: [128]  [110/312]  eta: 0:02:01  lr: 0.002696  min_lr: 0.002696  loss: 3.5436 (3.6488)  weight_decay: 0.0500 (0.0500)  time: 0.4880  data: 0.0504  max mem: 31830
Epoch: [128]  [120/312]  eta: 0:01:56  lr: 0.002695  min_lr: 0.002695  loss: 3.5436 (3.6414)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0644  max mem: 31830
Epoch: [128]  [130/312]  eta: 0:01:51  lr: 0.002694  min_lr: 0.002694  loss: 3.7154 (3.6490)  weight_decay: 0.0500 (0.0500)  time: 0.6799  data: 0.1033  max mem: 31830
Epoch: [128]  [140/312]  eta: 0:01:42  lr: 0.002694  min_lr: 0.002694  loss: 3.8565 (3.6572)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0397  max mem: 31830
Epoch: [128]  [150/312]  eta: 0:01:37  lr: 0.002693  min_lr: 0.002693  loss: 3.8694 (3.6516)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0138  max mem: 31830
Epoch: [128]  [160/312]  eta: 0:01:30  lr: 0.002692  min_lr: 0.002692  loss: 3.9069 (3.6684)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0418  max mem: 31830
Epoch: [128]  [170/312]  eta: 0:01:22  lr: 0.002692  min_lr: 0.002692  loss: 3.9746 (3.6591)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0288  max mem: 31830
Epoch: [128]  [180/312]  eta: 0:01:17  lr: 0.002691  min_lr: 0.002691  loss: 3.8682 (3.6650)  weight_decay: 0.0500 (0.0500)  time: 0.5623  data: 0.0899  max mem: 31830
Epoch: [128]  [190/312]  eta: 0:01:10  lr: 0.002690  min_lr: 0.002690  loss: 3.5383 (3.6497)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0899  max mem: 31830
Epoch: [128]  [200/312]  eta: 0:01:05  lr: 0.002690  min_lr: 0.002690  loss: 3.4986 (3.6484)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.0373  max mem: 31830
Epoch: [128]  [210/312]  eta: 0:00:59  lr: 0.002689  min_lr: 0.002689  loss: 3.8240 (3.6606)  weight_decay: 0.0500 (0.0500)  time: 0.6652  data: 0.0561  max mem: 31830
Epoch: [128]  [220/312]  eta: 0:00:53  lr: 0.002688  min_lr: 0.002688  loss: 3.8274 (3.6584)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.0309  max mem: 31830
Epoch: [128]  [230/312]  eta: 0:00:47  lr: 0.002688  min_lr: 0.002688  loss: 3.5452 (3.6580)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0123  max mem: 31830
Epoch: [128]  [240/312]  eta: 0:00:41  lr: 0.002687  min_lr: 0.002687  loss: 3.6774 (3.6591)  weight_decay: 0.0500 (0.0500)  time: 0.5545  data: 0.0014  max mem: 31830
Epoch: [128]  [250/312]  eta: 0:00:35  lr: 0.002686  min_lr: 0.002686  loss: 3.4875 (3.6538)  weight_decay: 0.0500 (0.0500)  time: 0.4621  data: 0.0055  max mem: 31830
Epoch: [128]  [260/312]  eta: 0:00:29  lr: 0.002686  min_lr: 0.002686  loss: 3.5005 (3.6531)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0291  max mem: 31830
Epoch: [128]  [270/312]  eta: 0:00:23  lr: 0.002685  min_lr: 0.002685  loss: 3.5923 (3.6576)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0384  max mem: 31830
Epoch: [128]  [280/312]  eta: 0:00:18  lr: 0.002684  min_lr: 0.002684  loss: 3.7627 (3.6557)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0545  max mem: 31830
Epoch: [128]  [290/312]  eta: 0:00:12  lr: 0.002684  min_lr: 0.002684  loss: 3.7557 (3.6551)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0789  max mem: 31830
Epoch: [128]  [300/312]  eta: 0:00:06  lr: 0.002683  min_lr: 0.002683  loss: 3.6251 (3.6502)  weight_decay: 0.0500 (0.0500)  time: 0.4459  data: 0.0384  max mem: 31830
Epoch: [128]  [310/312]  eta: 0:00:01  lr: 0.002682  min_lr: 0.002682  loss: 3.5455 (3.6453)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [128]  [311/312]  eta: 0:00:00  lr: 0.002682  min_lr: 0.002682  loss: 3.5455 (3.6466)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [128] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.002682  min_lr: 0.002682  loss: 3.5455 (3.6519)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.2789 (1.2789)  acc1: 75.5208 (75.5208)  acc5: 92.9688 (92.9688)  time: 9.0698  data: 8.9031  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6404 (1.5522)  acc1: 64.0625 (67.4560)  acc5: 89.1927 (88.2880)  time: 1.1262  data: 0.9893  max mem: 31830
Test: Total time: 0:00:10 (1.1395 s / it)
* Acc@1 67.824 Acc@5 88.514 loss 1.540
Accuracy of the model on the 50000 test images: 67.8%
Max accuracy: 68.13%
Epoch: [129]  [  0/312]  eta: 1:05:58  lr: 0.002682  min_lr: 0.002682  loss: 3.9807 (3.9807)  weight_decay: 0.0500 (0.0500)  time: 12.6877  data: 8.5458  max mem: 31830
Epoch: [129]  [ 10/312]  eta: 0:08:53  lr: 0.002681  min_lr: 0.002681  loss: 3.8304 (3.7607)  weight_decay: 0.0500 (0.0500)  time: 1.7667  data: 1.0377  max mem: 31830
Epoch: [129]  [ 20/312]  eta: 0:05:35  lr: 0.002681  min_lr: 0.002681  loss: 3.8304 (3.8589)  weight_decay: 0.0500 (0.0500)  time: 0.5737  data: 0.1448  max mem: 31830
Epoch: [129]  [ 30/312]  eta: 0:04:16  lr: 0.002680  min_lr: 0.002680  loss: 3.8305 (3.8407)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0022  max mem: 31830
Epoch: [129]  [ 40/312]  eta: 0:03:33  lr: 0.002679  min_lr: 0.002679  loss: 3.8764 (3.8747)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0013  max mem: 31830
Epoch: [129]  [ 50/312]  eta: 0:03:06  lr: 0.002679  min_lr: 0.002679  loss: 3.8809 (3.8570)  weight_decay: 0.0500 (0.0500)  time: 0.4074  data: 0.0010  max mem: 31830
Epoch: [129]  [ 60/312]  eta: 0:02:46  lr: 0.002678  min_lr: 0.002678  loss: 3.9378 (3.8604)  weight_decay: 0.0500 (0.0500)  time: 0.4067  data: 0.0015  max mem: 31830
Epoch: [129]  [ 70/312]  eta: 0:02:37  lr: 0.002677  min_lr: 0.002677  loss: 3.8569 (3.8296)  weight_decay: 0.0500 (0.0500)  time: 0.4930  data: 0.0015  max mem: 31830
Epoch: [129]  [ 80/312]  eta: 0:02:30  lr: 0.002677  min_lr: 0.002677  loss: 3.6122 (3.7936)  weight_decay: 0.0500 (0.0500)  time: 0.6123  data: 0.0008  max mem: 31830
Epoch: [129]  [ 90/312]  eta: 0:02:18  lr: 0.002676  min_lr: 0.002676  loss: 3.5683 (3.7581)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0008  max mem: 31830
Epoch: [129]  [100/312]  eta: 0:02:11  lr: 0.002675  min_lr: 0.002675  loss: 3.5683 (3.7325)  weight_decay: 0.0500 (0.0500)  time: 0.5014  data: 0.0009  max mem: 31830
Epoch: [129]  [110/312]  eta: 0:02:01  lr: 0.002675  min_lr: 0.002675  loss: 3.6437 (3.7260)  weight_decay: 0.0500 (0.0500)  time: 0.4885  data: 0.0011  max mem: 31830
Epoch: [129]  [120/312]  eta: 0:01:55  lr: 0.002674  min_lr: 0.002674  loss: 3.7338 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0010  max mem: 31830
Epoch: [129]  [130/312]  eta: 0:01:50  lr: 0.002673  min_lr: 0.002673  loss: 3.7623 (3.7230)  weight_decay: 0.0500 (0.0500)  time: 0.6424  data: 0.0134  max mem: 31830
Epoch: [129]  [140/312]  eta: 0:01:41  lr: 0.002673  min_lr: 0.002673  loss: 3.8017 (3.7338)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0141  max mem: 31830
Epoch: [129]  [150/312]  eta: 0:01:36  lr: 0.002672  min_lr: 0.002672  loss: 3.8785 (3.7282)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0016  max mem: 31830
Epoch: [129]  [160/312]  eta: 0:01:30  lr: 0.002671  min_lr: 0.002671  loss: 3.4497 (3.7025)  weight_decay: 0.0500 (0.0500)  time: 0.6364  data: 0.0017  max mem: 31830
Epoch: [129]  [170/312]  eta: 0:01:23  lr: 0.002671  min_lr: 0.002671  loss: 3.4468 (3.6962)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0274  max mem: 31830
Epoch: [129]  [180/312]  eta: 0:01:17  lr: 0.002670  min_lr: 0.002670  loss: 3.5881 (3.6988)  weight_decay: 0.0500 (0.0500)  time: 0.5055  data: 0.0266  max mem: 31830
Epoch: [129]  [190/312]  eta: 0:01:10  lr: 0.002669  min_lr: 0.002669  loss: 3.5990 (3.6884)  weight_decay: 0.0500 (0.0500)  time: 0.4784  data: 0.0009  max mem: 31830
Epoch: [129]  [200/312]  eta: 0:01:04  lr: 0.002668  min_lr: 0.002668  loss: 3.8062 (3.6946)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0134  max mem: 31830
Epoch: [129]  [210/312]  eta: 0:00:59  lr: 0.002668  min_lr: 0.002668  loss: 3.9312 (3.7043)  weight_decay: 0.0500 (0.0500)  time: 0.6293  data: 0.0263  max mem: 31830
Epoch: [129]  [220/312]  eta: 0:00:52  lr: 0.002667  min_lr: 0.002667  loss: 4.0010 (3.7162)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0139  max mem: 31830
Epoch: [129]  [230/312]  eta: 0:00:47  lr: 0.002666  min_lr: 0.002666  loss: 3.7849 (3.7181)  weight_decay: 0.0500 (0.0500)  time: 0.4945  data: 0.0010  max mem: 31830
Epoch: [129]  [240/312]  eta: 0:00:41  lr: 0.002666  min_lr: 0.002666  loss: 3.7718 (3.7263)  weight_decay: 0.0500 (0.0500)  time: 0.6033  data: 0.0010  max mem: 31830
Epoch: [129]  [250/312]  eta: 0:00:35  lr: 0.002665  min_lr: 0.002665  loss: 3.7544 (3.7218)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0008  max mem: 31830
Epoch: [129]  [260/312]  eta: 0:00:29  lr: 0.002664  min_lr: 0.002664  loss: 3.7544 (3.7211)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.0008  max mem: 31830
Epoch: [129]  [270/312]  eta: 0:00:23  lr: 0.002664  min_lr: 0.002664  loss: 3.8471 (3.7218)  weight_decay: 0.0500 (0.0500)  time: 0.4876  data: 0.0008  max mem: 31830
Epoch: [129]  [280/312]  eta: 0:00:18  lr: 0.002663  min_lr: 0.002663  loss: 3.7412 (3.7235)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0047  max mem: 31830
Epoch: [129]  [290/312]  eta: 0:00:12  lr: 0.002662  min_lr: 0.002662  loss: 3.6292 (3.7157)  weight_decay: 0.0500 (0.0500)  time: 0.6063  data: 0.0107  max mem: 31830
Epoch: [129]  [300/312]  eta: 0:00:06  lr: 0.002662  min_lr: 0.002662  loss: 3.4343 (3.7048)  weight_decay: 0.0500 (0.0500)  time: 0.4905  data: 0.0066  max mem: 31830
Epoch: [129]  [310/312]  eta: 0:00:01  lr: 0.002661  min_lr: 0.002661  loss: 3.3055 (3.6958)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0002  max mem: 31830
Epoch: [129]  [311/312]  eta: 0:00:00  lr: 0.002661  min_lr: 0.002661  loss: 3.3055 (3.6941)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0002  max mem: 31830
Epoch: [129] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.002661  min_lr: 0.002661  loss: 3.3055 (3.6613)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 1.2959 (1.2959)  acc1: 73.5677 (73.5677)  acc5: 89.9740 (89.9740)  time: 9.1506  data: 8.9834  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5682 (1.4334)  acc1: 64.9740 (67.2480)  acc5: 88.2812 (88.1920)  time: 1.1331  data: 0.9982  max mem: 31830
Test: Total time: 0:00:10 (1.1476 s / it)
* Acc@1 67.564 Acc@5 88.484 loss 1.428
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 68.13%
Epoch: [130]  [  0/312]  eta: 1:02:23  lr: 0.002661  min_lr: 0.002661  loss: 3.3465 (3.3465)  weight_decay: 0.0500 (0.0500)  time: 11.9971  data: 10.7945  max mem: 31830
Epoch: [130]  [ 10/312]  eta: 0:08:26  lr: 0.002660  min_lr: 0.002660  loss: 3.9803 (3.8691)  weight_decay: 0.0500 (0.0500)  time: 1.6761  data: 0.9830  max mem: 31830
Epoch: [130]  [ 20/312]  eta: 0:05:30  lr: 0.002660  min_lr: 0.002660  loss: 3.9095 (3.8070)  weight_decay: 0.0500 (0.0500)  time: 0.5885  data: 0.0166  max mem: 31830
Epoch: [130]  [ 30/312]  eta: 0:04:12  lr: 0.002659  min_lr: 0.002659  loss: 3.7516 (3.7170)  weight_decay: 0.0500 (0.0500)  time: 0.4651  data: 0.0160  max mem: 31830
Epoch: [130]  [ 40/312]  eta: 0:03:30  lr: 0.002658  min_lr: 0.002658  loss: 3.7832 (3.6900)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0007  max mem: 31830
Epoch: [130]  [ 50/312]  eta: 0:03:09  lr: 0.002657  min_lr: 0.002657  loss: 3.7827 (3.6631)  weight_decay: 0.0500 (0.0500)  time: 0.4580  data: 0.0142  max mem: 31830
Epoch: [130]  [ 60/312]  eta: 0:02:48  lr: 0.002657  min_lr: 0.002657  loss: 3.7827 (3.6600)  weight_decay: 0.0500 (0.0500)  time: 0.4543  data: 0.0142  max mem: 31830
Epoch: [130]  [ 70/312]  eta: 0:02:39  lr: 0.002656  min_lr: 0.002656  loss: 3.6887 (3.6428)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0547  max mem: 31830
Epoch: [130]  [ 80/312]  eta: 0:02:29  lr: 0.002655  min_lr: 0.002655  loss: 3.6887 (3.6400)  weight_decay: 0.0500 (0.0500)  time: 0.5630  data: 0.1119  max mem: 31830
Epoch: [130]  [ 90/312]  eta: 0:02:20  lr: 0.002655  min_lr: 0.002655  loss: 3.7783 (3.6375)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0580  max mem: 31830
Epoch: [130]  [100/312]  eta: 0:02:13  lr: 0.002654  min_lr: 0.002654  loss: 3.6878 (3.6378)  weight_decay: 0.0500 (0.0500)  time: 0.5779  data: 0.0260  max mem: 31830
Epoch: [130]  [110/312]  eta: 0:02:03  lr: 0.002653  min_lr: 0.002653  loss: 3.8119 (3.6609)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0258  max mem: 31830
Epoch: [130]  [120/312]  eta: 0:01:57  lr: 0.002653  min_lr: 0.002653  loss: 3.6859 (3.6471)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0434  max mem: 31830
Epoch: [130]  [130/312]  eta: 0:01:51  lr: 0.002652  min_lr: 0.002652  loss: 3.3783 (3.6270)  weight_decay: 0.0500 (0.0500)  time: 0.6247  data: 0.0583  max mem: 31830
Epoch: [130]  [140/312]  eta: 0:01:43  lr: 0.002651  min_lr: 0.002651  loss: 3.5757 (3.6172)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0409  max mem: 31830
Epoch: [130]  [150/312]  eta: 0:01:37  lr: 0.002651  min_lr: 0.002651  loss: 3.7751 (3.6177)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.0587  max mem: 31830
Epoch: [130]  [160/312]  eta: 0:01:30  lr: 0.002650  min_lr: 0.002650  loss: 3.7990 (3.6317)  weight_decay: 0.0500 (0.0500)  time: 0.5645  data: 0.0334  max mem: 31830
Epoch: [130]  [170/312]  eta: 0:01:24  lr: 0.002649  min_lr: 0.002649  loss: 3.8181 (3.6407)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0008  max mem: 31830
Epoch: [130]  [180/312]  eta: 0:01:18  lr: 0.002649  min_lr: 0.002649  loss: 3.6517 (3.6332)  weight_decay: 0.0500 (0.0500)  time: 0.5565  data: 0.0149  max mem: 31830
Epoch: [130]  [190/312]  eta: 0:01:11  lr: 0.002648  min_lr: 0.002648  loss: 3.6634 (3.6385)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0326  max mem: 31830
Epoch: [130]  [200/312]  eta: 0:01:05  lr: 0.002647  min_lr: 0.002647  loss: 3.7103 (3.6317)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0517  max mem: 31830
Epoch: [130]  [210/312]  eta: 0:00:59  lr: 0.002647  min_lr: 0.002647  loss: 3.4910 (3.6220)  weight_decay: 0.0500 (0.0500)  time: 0.6148  data: 0.0340  max mem: 31830
Epoch: [130]  [220/312]  eta: 0:00:53  lr: 0.002646  min_lr: 0.002646  loss: 3.5049 (3.6208)  weight_decay: 0.0500 (0.0500)  time: 0.5019  data: 0.0208  max mem: 31830
Epoch: [130]  [230/312]  eta: 0:00:47  lr: 0.002645  min_lr: 0.002645  loss: 3.5771 (3.6151)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0387  max mem: 31830
Epoch: [130]  [240/312]  eta: 0:00:41  lr: 0.002645  min_lr: 0.002645  loss: 3.5771 (3.6133)  weight_decay: 0.0500 (0.0500)  time: 0.5402  data: 0.0242  max mem: 31830
Epoch: [130]  [250/312]  eta: 0:00:35  lr: 0.002644  min_lr: 0.002644  loss: 3.6960 (3.6170)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0287  max mem: 31830
Epoch: [130]  [260/312]  eta: 0:00:29  lr: 0.002643  min_lr: 0.002643  loss: 3.6960 (3.6159)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0445  max mem: 31830
Epoch: [130]  [270/312]  eta: 0:00:23  lr: 0.002643  min_lr: 0.002643  loss: 3.5601 (3.6071)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0228  max mem: 31830
Epoch: [130]  [280/312]  eta: 0:00:18  lr: 0.002642  min_lr: 0.002642  loss: 3.3410 (3.5987)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0419  max mem: 31830
Epoch: [130]  [290/312]  eta: 0:00:12  lr: 0.002641  min_lr: 0.002641  loss: 3.4678 (3.5956)  weight_decay: 0.0500 (0.0500)  time: 0.5946  data: 0.0704  max mem: 31830
Epoch: [130]  [300/312]  eta: 0:00:06  lr: 0.002640  min_lr: 0.002640  loss: 3.6198 (3.6028)  weight_decay: 0.0500 (0.0500)  time: 0.4604  data: 0.0295  max mem: 31830
Epoch: [130]  [310/312]  eta: 0:00:01  lr: 0.002640  min_lr: 0.002640  loss: 3.9488 (3.6104)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [130]  [311/312]  eta: 0:00:00  lr: 0.002640  min_lr: 0.002640  loss: 3.9922 (3.6118)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [130] Total time: 0:02:55 (0.5618 s / it)
Averaged stats: lr: 0.002640  min_lr: 0.002640  loss: 3.9922 (3.6566)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.1986 (1.1986)  acc1: 77.2135 (77.2135)  acc5: 93.3594 (93.3594)  time: 8.4295  data: 8.2605  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7167 (1.6386)  acc1: 65.4948 (68.1280)  acc5: 89.4531 (88.7840)  time: 1.0751  data: 0.9324  max mem: 31830
Test: Total time: 0:00:09 (1.0879 s / it)
* Acc@1 67.646 Acc@5 88.618 loss 1.643
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 68.13%
Epoch: [131]  [  0/312]  eta: 1:05:34  lr: 0.002640  min_lr: 0.002640  loss: 2.8548 (2.8548)  weight_decay: 0.0500 (0.0500)  time: 12.6113  data: 9.2529  max mem: 31830
Epoch: [131]  [ 10/312]  eta: 0:09:03  lr: 0.002639  min_lr: 0.002639  loss: 3.4756 (3.4779)  weight_decay: 0.0500 (0.0500)  time: 1.8002  data: 1.1451  max mem: 31830
Epoch: [131]  [ 20/312]  eta: 0:05:35  lr: 0.002638  min_lr: 0.002638  loss: 3.4567 (3.3962)  weight_decay: 0.0500 (0.0500)  time: 0.5743  data: 0.1678  max mem: 31830
Epoch: [131]  [ 30/312]  eta: 0:04:15  lr: 0.002638  min_lr: 0.002638  loss: 3.6797 (3.5405)  weight_decay: 0.0500 (0.0500)  time: 0.4142  data: 0.0012  max mem: 31830
Epoch: [131]  [ 40/312]  eta: 0:03:32  lr: 0.002637  min_lr: 0.002637  loss: 3.8562 (3.4895)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0008  max mem: 31830
Epoch: [131]  [ 50/312]  eta: 0:03:05  lr: 0.002636  min_lr: 0.002636  loss: 3.5538 (3.5321)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0007  max mem: 31830
Epoch: [131]  [ 60/312]  eta: 0:02:45  lr: 0.002636  min_lr: 0.002636  loss: 3.5546 (3.5397)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0007  max mem: 31830
Epoch: [131]  [ 70/312]  eta: 0:02:38  lr: 0.002635  min_lr: 0.002635  loss: 3.3711 (3.5136)  weight_decay: 0.0500 (0.0500)  time: 0.5161  data: 0.0010  max mem: 31830
Epoch: [131]  [ 80/312]  eta: 0:02:25  lr: 0.002634  min_lr: 0.002634  loss: 3.4991 (3.5183)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.0011  max mem: 31830
Epoch: [131]  [ 90/312]  eta: 0:02:15  lr: 0.002634  min_lr: 0.002634  loss: 3.6113 (3.5283)  weight_decay: 0.0500 (0.0500)  time: 0.4549  data: 0.0018  max mem: 31830
Epoch: [131]  [100/312]  eta: 0:02:09  lr: 0.002633  min_lr: 0.002633  loss: 3.6113 (3.5397)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.0306  max mem: 31830
Epoch: [131]  [110/312]  eta: 0:01:59  lr: 0.002632  min_lr: 0.002632  loss: 3.8066 (3.5560)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0297  max mem: 31830
Epoch: [131]  [120/312]  eta: 0:01:54  lr: 0.002631  min_lr: 0.002631  loss: 3.8543 (3.5714)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0300  max mem: 31830
Epoch: [131]  [130/312]  eta: 0:01:50  lr: 0.002631  min_lr: 0.002631  loss: 3.7407 (3.5754)  weight_decay: 0.0500 (0.0500)  time: 0.7019  data: 0.0301  max mem: 31830
Epoch: [131]  [140/312]  eta: 0:01:42  lr: 0.002630  min_lr: 0.002630  loss: 3.7407 (3.5868)  weight_decay: 0.0500 (0.0500)  time: 0.5746  data: 0.0010  max mem: 31830
Epoch: [131]  [150/312]  eta: 0:01:36  lr: 0.002629  min_lr: 0.002629  loss: 3.8201 (3.5955)  weight_decay: 0.0500 (0.0500)  time: 0.4926  data: 0.0009  max mem: 31830
Epoch: [131]  [160/312]  eta: 0:01:29  lr: 0.002629  min_lr: 0.002629  loss: 3.8442 (3.6108)  weight_decay: 0.0500 (0.0500)  time: 0.5451  data: 0.0014  max mem: 31830
Epoch: [131]  [170/312]  eta: 0:01:22  lr: 0.002628  min_lr: 0.002628  loss: 3.7967 (3.6063)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.0106  max mem: 31830
Epoch: [131]  [180/312]  eta: 0:01:17  lr: 0.002627  min_lr: 0.002627  loss: 3.6974 (3.6114)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0109  max mem: 31830
Epoch: [131]  [190/312]  eta: 0:01:10  lr: 0.002627  min_lr: 0.002627  loss: 3.5453 (3.6073)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0016  max mem: 31830
Epoch: [131]  [200/312]  eta: 0:01:04  lr: 0.002626  min_lr: 0.002626  loss: 3.6401 (3.6192)  weight_decay: 0.0500 (0.0500)  time: 0.4929  data: 0.0008  max mem: 31830
Epoch: [131]  [210/312]  eta: 0:00:58  lr: 0.002625  min_lr: 0.002625  loss: 3.8483 (3.6229)  weight_decay: 0.0500 (0.0500)  time: 0.5644  data: 0.0008  max mem: 31830
Epoch: [131]  [220/312]  eta: 0:00:52  lr: 0.002625  min_lr: 0.002625  loss: 3.9177 (3.6299)  weight_decay: 0.0500 (0.0500)  time: 0.4835  data: 0.0014  max mem: 31830
Epoch: [131]  [230/312]  eta: 0:00:46  lr: 0.002624  min_lr: 0.002624  loss: 3.8196 (3.6391)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0467  max mem: 31830
Epoch: [131]  [240/312]  eta: 0:00:40  lr: 0.002623  min_lr: 0.002623  loss: 3.8124 (3.6442)  weight_decay: 0.0500 (0.0500)  time: 0.5864  data: 0.0617  max mem: 31830
Epoch: [131]  [250/312]  eta: 0:00:35  lr: 0.002623  min_lr: 0.002623  loss: 3.9532 (3.6482)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0312  max mem: 31830
Epoch: [131]  [260/312]  eta: 0:00:29  lr: 0.002622  min_lr: 0.002622  loss: 3.9216 (3.6525)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0625  max mem: 31830
Epoch: [131]  [270/312]  eta: 0:00:23  lr: 0.002621  min_lr: 0.002621  loss: 3.9569 (3.6674)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0763  max mem: 31830
Epoch: [131]  [280/312]  eta: 0:00:18  lr: 0.002621  min_lr: 0.002621  loss: 4.1048 (3.6738)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0406  max mem: 31830
Epoch: [131]  [290/312]  eta: 0:00:12  lr: 0.002620  min_lr: 0.002620  loss: 3.7908 (3.6711)  weight_decay: 0.0500 (0.0500)  time: 0.6054  data: 0.0201  max mem: 31830
Epoch: [131]  [300/312]  eta: 0:00:06  lr: 0.002619  min_lr: 0.002619  loss: 3.7908 (3.6698)  weight_decay: 0.0500 (0.0500)  time: 0.4977  data: 0.0086  max mem: 31830
Epoch: [131]  [310/312]  eta: 0:00:01  lr: 0.002619  min_lr: 0.002619  loss: 3.6015 (3.6700)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [131]  [311/312]  eta: 0:00:00  lr: 0.002618  min_lr: 0.002618  loss: 3.6015 (3.6710)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [131] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.002618  min_lr: 0.002618  loss: 3.6015 (3.6319)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.4372 (1.4372)  acc1: 74.7396 (74.7396)  acc5: 91.2760 (91.2760)  time: 9.0860  data: 8.9187  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8501 (1.7528)  acc1: 65.1042 (67.0080)  acc5: 88.1510 (87.4880)  time: 1.1263  data: 0.9910  max mem: 31830
Test: Total time: 0:00:10 (1.1493 s / it)
* Acc@1 66.830 Acc@5 87.836 loss 1.751
Accuracy of the model on the 50000 test images: 66.8%
Max accuracy: 68.13%
Epoch: [132]  [  0/312]  eta: 1:01:16  lr: 0.002618  min_lr: 0.002618  loss: 2.7078 (2.7078)  weight_decay: 0.0500 (0.0500)  time: 11.7823  data: 9.4652  max mem: 31830
Epoch: [132]  [ 10/312]  eta: 0:08:43  lr: 0.002618  min_lr: 0.002618  loss: 3.7529 (3.5999)  weight_decay: 0.0500 (0.0500)  time: 1.7325  data: 1.1048  max mem: 31830
Epoch: [132]  [ 20/312]  eta: 0:05:20  lr: 0.002617  min_lr: 0.002617  loss: 3.7529 (3.6424)  weight_decay: 0.0500 (0.0500)  time: 0.5620  data: 0.1347  max mem: 31830
Epoch: [132]  [ 30/312]  eta: 0:04:05  lr: 0.002616  min_lr: 0.002616  loss: 3.8268 (3.6509)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0006  max mem: 31830
Epoch: [132]  [ 40/312]  eta: 0:03:25  lr: 0.002616  min_lr: 0.002616  loss: 3.4465 (3.5884)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0007  max mem: 31830
Epoch: [132]  [ 50/312]  eta: 0:03:01  lr: 0.002615  min_lr: 0.002615  loss: 3.4465 (3.5642)  weight_decay: 0.0500 (0.0500)  time: 0.4144  data: 0.0007  max mem: 31830
Epoch: [132]  [ 60/312]  eta: 0:02:42  lr: 0.002614  min_lr: 0.002614  loss: 3.5791 (3.5531)  weight_decay: 0.0500 (0.0500)  time: 0.4150  data: 0.0010  max mem: 31830
Epoch: [132]  [ 70/312]  eta: 0:02:35  lr: 0.002614  min_lr: 0.002614  loss: 3.5791 (3.5427)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0996  max mem: 31830
Epoch: [132]  [ 80/312]  eta: 0:02:27  lr: 0.002613  min_lr: 0.002613  loss: 3.6125 (3.5370)  weight_decay: 0.0500 (0.0500)  time: 0.6028  data: 0.1621  max mem: 31830
Epoch: [132]  [ 90/312]  eta: 0:02:15  lr: 0.002612  min_lr: 0.002612  loss: 3.6561 (3.5713)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0763  max mem: 31830
Epoch: [132]  [100/312]  eta: 0:02:10  lr: 0.002612  min_lr: 0.002612  loss: 3.8923 (3.6144)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0952  max mem: 31830
Epoch: [132]  [110/312]  eta: 0:02:00  lr: 0.002611  min_lr: 0.002611  loss: 3.9655 (3.6342)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0824  max mem: 31830
Epoch: [132]  [120/312]  eta: 0:01:55  lr: 0.002610  min_lr: 0.002610  loss: 3.9506 (3.6379)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0533  max mem: 31830
Epoch: [132]  [130/312]  eta: 0:01:49  lr: 0.002609  min_lr: 0.002609  loss: 3.7272 (3.6348)  weight_decay: 0.0500 (0.0500)  time: 0.6326  data: 0.0858  max mem: 31830
Epoch: [132]  [140/312]  eta: 0:01:41  lr: 0.002609  min_lr: 0.002609  loss: 3.7089 (3.6231)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0332  max mem: 31830
Epoch: [132]  [150/312]  eta: 0:01:36  lr: 0.002608  min_lr: 0.002608  loss: 3.6897 (3.6209)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0548  max mem: 31830
Epoch: [132]  [160/312]  eta: 0:01:30  lr: 0.002607  min_lr: 0.002607  loss: 3.6348 (3.6057)  weight_decay: 0.0500 (0.0500)  time: 0.6235  data: 0.0674  max mem: 31830
Epoch: [132]  [170/312]  eta: 0:01:22  lr: 0.002607  min_lr: 0.002607  loss: 3.5262 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0385  max mem: 31830
Epoch: [132]  [180/312]  eta: 0:01:17  lr: 0.002606  min_lr: 0.002606  loss: 3.7380 (3.6140)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0543  max mem: 31830
Epoch: [132]  [190/312]  eta: 0:01:10  lr: 0.002605  min_lr: 0.002605  loss: 3.9570 (3.6234)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0289  max mem: 31830
Epoch: [132]  [200/312]  eta: 0:01:05  lr: 0.002605  min_lr: 0.002605  loss: 3.8745 (3.6273)  weight_decay: 0.0500 (0.0500)  time: 0.5530  data: 0.0372  max mem: 31830
Epoch: [132]  [210/312]  eta: 0:00:59  lr: 0.002604  min_lr: 0.002604  loss: 3.6945 (3.6324)  weight_decay: 0.0500 (0.0500)  time: 0.6615  data: 0.0373  max mem: 31830
Epoch: [132]  [220/312]  eta: 0:00:52  lr: 0.002603  min_lr: 0.002603  loss: 3.6945 (3.6335)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0013  max mem: 31830
Epoch: [132]  [230/312]  eta: 0:00:47  lr: 0.002603  min_lr: 0.002603  loss: 3.7113 (3.6375)  weight_decay: 0.0500 (0.0500)  time: 0.4976  data: 0.0014  max mem: 31830
Epoch: [132]  [240/312]  eta: 0:00:41  lr: 0.002602  min_lr: 0.002602  loss: 3.4845 (3.6240)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0009  max mem: 31830
Epoch: [132]  [250/312]  eta: 0:00:35  lr: 0.002601  min_lr: 0.002601  loss: 3.4812 (3.6274)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0068  max mem: 31830
Epoch: [132]  [260/312]  eta: 0:00:29  lr: 0.002601  min_lr: 0.002601  loss: 3.8152 (3.6364)  weight_decay: 0.0500 (0.0500)  time: 0.5554  data: 0.0315  max mem: 31830
Epoch: [132]  [270/312]  eta: 0:00:23  lr: 0.002600  min_lr: 0.002600  loss: 3.9391 (3.6340)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0256  max mem: 31830
Epoch: [132]  [280/312]  eta: 0:00:18  lr: 0.002599  min_lr: 0.002599  loss: 3.6752 (3.6234)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0378  max mem: 31830
Epoch: [132]  [290/312]  eta: 0:00:12  lr: 0.002599  min_lr: 0.002599  loss: 3.6603 (3.6243)  weight_decay: 0.0500 (0.0500)  time: 0.6159  data: 0.0417  max mem: 31830
Epoch: [132]  [300/312]  eta: 0:00:06  lr: 0.002598  min_lr: 0.002598  loss: 3.7088 (3.6260)  weight_decay: 0.0500 (0.0500)  time: 0.4738  data: 0.0045  max mem: 31830
Epoch: [132]  [310/312]  eta: 0:00:01  lr: 0.002597  min_lr: 0.002597  loss: 3.6998 (3.6261)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [132]  [311/312]  eta: 0:00:00  lr: 0.002597  min_lr: 0.002597  loss: 3.6998 (3.6274)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [132] Total time: 0:02:55 (0.5613 s / it)
Averaged stats: lr: 0.002597  min_lr: 0.002597  loss: 3.6998 (3.6550)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:24  loss: 1.4983 (1.4983)  acc1: 72.3958 (72.3958)  acc5: 90.7552 (90.7552)  time: 9.4409  data: 9.2736  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9271 (1.7806)  acc1: 62.1094 (65.0720)  acc5: 85.6771 (86.8480)  time: 1.1667  data: 1.0305  max mem: 31830
Test: Total time: 0:00:10 (1.1840 s / it)
* Acc@1 65.306 Acc@5 87.094 loss 1.773
Accuracy of the model on the 50000 test images: 65.3%
Max accuracy: 68.13%
Epoch: [133]  [  0/312]  eta: 1:07:25  lr: 0.002597  min_lr: 0.002597  loss: 2.5621 (2.5621)  weight_decay: 0.0500 (0.0500)  time: 12.9669  data: 12.0038  max mem: 31830
Epoch: [133]  [ 10/312]  eta: 0:09:12  lr: 0.002596  min_lr: 0.002596  loss: 3.7405 (3.4166)  weight_decay: 0.0500 (0.0500)  time: 1.8297  data: 1.0919  max mem: 31830
Epoch: [133]  [ 20/312]  eta: 0:05:47  lr: 0.002596  min_lr: 0.002596  loss: 3.8268 (3.5613)  weight_decay: 0.0500 (0.0500)  time: 0.6010  data: 0.0215  max mem: 31830
Epoch: [133]  [ 30/312]  eta: 0:04:23  lr: 0.002595  min_lr: 0.002595  loss: 3.8383 (3.4899)  weight_decay: 0.0500 (0.0500)  time: 0.4429  data: 0.0217  max mem: 31830
Epoch: [133]  [ 40/312]  eta: 0:03:38  lr: 0.002594  min_lr: 0.002594  loss: 3.7436 (3.5317)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [133]  [ 50/312]  eta: 0:03:09  lr: 0.002594  min_lr: 0.002594  loss: 3.7436 (3.5319)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0013  max mem: 31830
Epoch: [133]  [ 60/312]  eta: 0:02:49  lr: 0.002593  min_lr: 0.002593  loss: 3.6903 (3.5439)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0013  max mem: 31830
Epoch: [133]  [ 70/312]  eta: 0:02:33  lr: 0.002592  min_lr: 0.002592  loss: 3.9033 (3.6173)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0015  max mem: 31830
Epoch: [133]  [ 80/312]  eta: 0:02:25  lr: 0.002592  min_lr: 0.002592  loss: 3.8303 (3.6291)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0019  max mem: 31830
Epoch: [133]  [ 90/312]  eta: 0:02:15  lr: 0.002591  min_lr: 0.002591  loss: 3.7304 (3.6441)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0136  max mem: 31830
Epoch: [133]  [100/312]  eta: 0:02:10  lr: 0.002590  min_lr: 0.002590  loss: 3.7734 (3.6490)  weight_decay: 0.0500 (0.0500)  time: 0.5733  data: 0.0198  max mem: 31830
Epoch: [133]  [110/312]  eta: 0:02:00  lr: 0.002589  min_lr: 0.002589  loss: 3.5566 (3.6162)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0211  max mem: 31830
Epoch: [133]  [120/312]  eta: 0:01:54  lr: 0.002589  min_lr: 0.002589  loss: 3.4918 (3.6200)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.0145  max mem: 31830
Epoch: [133]  [130/312]  eta: 0:01:48  lr: 0.002588  min_lr: 0.002588  loss: 3.7475 (3.6237)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.0141  max mem: 31830
Epoch: [133]  [140/312]  eta: 0:01:40  lr: 0.002587  min_lr: 0.002587  loss: 3.5707 (3.6106)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0142  max mem: 31830
Epoch: [133]  [150/312]  eta: 0:01:35  lr: 0.002587  min_lr: 0.002587  loss: 3.4610 (3.5891)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0009  max mem: 31830
Epoch: [133]  [160/312]  eta: 0:01:28  lr: 0.002586  min_lr: 0.002586  loss: 3.4969 (3.5977)  weight_decay: 0.0500 (0.0500)  time: 0.5827  data: 0.0093  max mem: 31830
Epoch: [133]  [170/312]  eta: 0:01:21  lr: 0.002585  min_lr: 0.002585  loss: 3.8448 (3.5969)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0097  max mem: 31830
Epoch: [133]  [180/312]  eta: 0:01:16  lr: 0.002585  min_lr: 0.002585  loss: 3.8448 (3.5983)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0242  max mem: 31830
Epoch: [133]  [190/312]  eta: 0:01:10  lr: 0.002584  min_lr: 0.002584  loss: 3.6716 (3.5913)  weight_decay: 0.0500 (0.0500)  time: 0.5734  data: 0.0389  max mem: 31830
Epoch: [133]  [200/312]  eta: 0:01:04  lr: 0.002583  min_lr: 0.002583  loss: 3.5234 (3.5986)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0162  max mem: 31830
Epoch: [133]  [210/312]  eta: 0:00:58  lr: 0.002583  min_lr: 0.002583  loss: 3.5234 (3.5916)  weight_decay: 0.0500 (0.0500)  time: 0.5755  data: 0.0174  max mem: 31830
Epoch: [133]  [220/312]  eta: 0:00:52  lr: 0.002582  min_lr: 0.002582  loss: 3.5367 (3.5911)  weight_decay: 0.0500 (0.0500)  time: 0.5708  data: 0.0358  max mem: 31830
Epoch: [133]  [230/312]  eta: 0:00:46  lr: 0.002581  min_lr: 0.002581  loss: 3.5367 (3.5893)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0312  max mem: 31830
Epoch: [133]  [240/312]  eta: 0:00:41  lr: 0.002581  min_lr: 0.002581  loss: 3.6891 (3.5870)  weight_decay: 0.0500 (0.0500)  time: 0.5679  data: 0.0228  max mem: 31830
Epoch: [133]  [250/312]  eta: 0:00:35  lr: 0.002580  min_lr: 0.002580  loss: 3.7536 (3.5892)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0110  max mem: 31830
Epoch: [133]  [260/312]  eta: 0:00:29  lr: 0.002579  min_lr: 0.002579  loss: 3.7404 (3.5801)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0165  max mem: 31830
Epoch: [133]  [270/312]  eta: 0:00:23  lr: 0.002578  min_lr: 0.002578  loss: 3.5361 (3.5803)  weight_decay: 0.0500 (0.0500)  time: 0.5440  data: 0.0322  max mem: 31830
Epoch: [133]  [280/312]  eta: 0:00:18  lr: 0.002578  min_lr: 0.002578  loss: 3.5567 (3.5748)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0314  max mem: 31830
Epoch: [133]  [290/312]  eta: 0:00:12  lr: 0.002577  min_lr: 0.002577  loss: 3.8013 (3.5792)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0155  max mem: 31830
Epoch: [133]  [300/312]  eta: 0:00:06  lr: 0.002576  min_lr: 0.002576  loss: 3.8013 (3.5830)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0002  max mem: 31830
Epoch: [133]  [310/312]  eta: 0:00:01  lr: 0.002576  min_lr: 0.002576  loss: 3.7074 (3.5791)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0002  max mem: 31830
Epoch: [133]  [311/312]  eta: 0:00:00  lr: 0.002576  min_lr: 0.002576  loss: 3.7194 (3.5796)  weight_decay: 0.0500 (0.0500)  time: 0.4051  data: 0.0002  max mem: 31830
Epoch: [133] Total time: 0:02:54 (0.5609 s / it)
Averaged stats: lr: 0.002576  min_lr: 0.002576  loss: 3.7194 (3.6164)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.3785 (1.3785)  acc1: 75.0000 (75.0000)  acc5: 92.9688 (92.9688)  time: 8.6741  data: 8.5067  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7235 (1.6455)  acc1: 67.4479 (67.8240)  acc5: 88.2812 (88.4320)  time: 1.0821  data: 0.9457  max mem: 31830
Test: Total time: 0:00:09 (1.0957 s / it)
* Acc@1 67.924 Acc@5 88.550 loss 1.640
Accuracy of the model on the 50000 test images: 67.9%
Max accuracy: 68.13%
Epoch: [134]  [  0/312]  eta: 1:03:58  lr: 0.002576  min_lr: 0.002576  loss: 4.2824 (4.2824)  weight_decay: 0.0500 (0.0500)  time: 12.3024  data: 8.9136  max mem: 31830
Epoch: [134]  [ 10/312]  eta: 0:09:01  lr: 0.002575  min_lr: 0.002575  loss: 3.8158 (3.5723)  weight_decay: 0.0500 (0.0500)  time: 1.7947  data: 0.9736  max mem: 31830
Epoch: [134]  [ 20/312]  eta: 0:05:57  lr: 0.002574  min_lr: 0.002574  loss: 3.6145 (3.4705)  weight_decay: 0.0500 (0.0500)  time: 0.6701  data: 0.1778  max mem: 31830
Epoch: [134]  [ 30/312]  eta: 0:04:28  lr: 0.002573  min_lr: 0.002573  loss: 3.1499 (3.4196)  weight_decay: 0.0500 (0.0500)  time: 0.4913  data: 0.0885  max mem: 31830
Epoch: [134]  [ 40/312]  eta: 0:03:42  lr: 0.002573  min_lr: 0.002573  loss: 3.4654 (3.4810)  weight_decay: 0.0500 (0.0500)  time: 0.3911  data: 0.0011  max mem: 31830
Epoch: [134]  [ 50/312]  eta: 0:03:12  lr: 0.002572  min_lr: 0.002572  loss: 3.6938 (3.5050)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0011  max mem: 31830
Epoch: [134]  [ 60/312]  eta: 0:02:51  lr: 0.002571  min_lr: 0.002571  loss: 3.6574 (3.5081)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0008  max mem: 31830
Epoch: [134]  [ 70/312]  eta: 0:02:34  lr: 0.002571  min_lr: 0.002571  loss: 3.6574 (3.5309)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0008  max mem: 31830
Epoch: [134]  [ 80/312]  eta: 0:02:27  lr: 0.002570  min_lr: 0.002570  loss: 3.7240 (3.5405)  weight_decay: 0.0500 (0.0500)  time: 0.5003  data: 0.0007  max mem: 31830
Epoch: [134]  [ 90/312]  eta: 0:02:15  lr: 0.002569  min_lr: 0.002569  loss: 3.7429 (3.5482)  weight_decay: 0.0500 (0.0500)  time: 0.5111  data: 0.0135  max mem: 31830
Epoch: [134]  [100/312]  eta: 0:02:10  lr: 0.002569  min_lr: 0.002569  loss: 3.9570 (3.5992)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0320  max mem: 31830
Epoch: [134]  [110/312]  eta: 0:02:00  lr: 0.002568  min_lr: 0.002568  loss: 4.0356 (3.6005)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0192  max mem: 31830
Epoch: [134]  [120/312]  eta: 0:01:53  lr: 0.002567  min_lr: 0.002567  loss: 3.6082 (3.5963)  weight_decay: 0.0500 (0.0500)  time: 0.4758  data: 0.0144  max mem: 31830
Epoch: [134]  [130/312]  eta: 0:01:48  lr: 0.002567  min_lr: 0.002567  loss: 3.4829 (3.5874)  weight_decay: 0.0500 (0.0500)  time: 0.6068  data: 0.0287  max mem: 31830
Epoch: [134]  [140/312]  eta: 0:01:40  lr: 0.002566  min_lr: 0.002566  loss: 3.6198 (3.5957)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0306  max mem: 31830
Epoch: [134]  [150/312]  eta: 0:01:35  lr: 0.002565  min_lr: 0.002565  loss: 3.7050 (3.6160)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0428  max mem: 31830
Epoch: [134]  [160/312]  eta: 0:01:28  lr: 0.002565  min_lr: 0.002565  loss: 3.8842 (3.6194)  weight_decay: 0.0500 (0.0500)  time: 0.5751  data: 0.0274  max mem: 31830
Epoch: [134]  [170/312]  eta: 0:01:21  lr: 0.002564  min_lr: 0.002564  loss: 3.7457 (3.6139)  weight_decay: 0.0500 (0.0500)  time: 0.4960  data: 0.0308  max mem: 31830
Epoch: [134]  [180/312]  eta: 0:01:16  lr: 0.002563  min_lr: 0.002563  loss: 3.8524 (3.6384)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0606  max mem: 31830
Epoch: [134]  [190/312]  eta: 0:01:09  lr: 0.002562  min_lr: 0.002562  loss: 3.9866 (3.6354)  weight_decay: 0.0500 (0.0500)  time: 0.5437  data: 0.0307  max mem: 31830
Epoch: [134]  [200/312]  eta: 0:01:04  lr: 0.002562  min_lr: 0.002562  loss: 3.6439 (3.6417)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0203  max mem: 31830
Epoch: [134]  [210/312]  eta: 0:00:58  lr: 0.002561  min_lr: 0.002561  loss: 3.6439 (3.6334)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.0597  max mem: 31830
Epoch: [134]  [220/312]  eta: 0:00:52  lr: 0.002560  min_lr: 0.002560  loss: 3.7262 (3.6323)  weight_decay: 0.0500 (0.0500)  time: 0.5522  data: 0.0402  max mem: 31830
Epoch: [134]  [230/312]  eta: 0:00:46  lr: 0.002560  min_lr: 0.002560  loss: 3.7262 (3.6423)  weight_decay: 0.0500 (0.0500)  time: 0.4942  data: 0.0331  max mem: 31830
Epoch: [134]  [240/312]  eta: 0:00:40  lr: 0.002559  min_lr: 0.002559  loss: 3.8105 (3.6440)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0331  max mem: 31830
Epoch: [134]  [250/312]  eta: 0:00:35  lr: 0.002558  min_lr: 0.002558  loss: 3.7808 (3.6462)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0330  max mem: 31830
Epoch: [134]  [260/312]  eta: 0:00:29  lr: 0.002558  min_lr: 0.002558  loss: 3.7808 (3.6478)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0529  max mem: 31830
Epoch: [134]  [270/312]  eta: 0:00:23  lr: 0.002557  min_lr: 0.002557  loss: 3.5246 (3.6443)  weight_decay: 0.0500 (0.0500)  time: 0.5566  data: 0.0319  max mem: 31830
Epoch: [134]  [280/312]  eta: 0:00:18  lr: 0.002556  min_lr: 0.002556  loss: 3.7682 (3.6423)  weight_decay: 0.0500 (0.0500)  time: 0.5953  data: 0.0399  max mem: 31830
Epoch: [134]  [290/312]  eta: 0:00:12  lr: 0.002556  min_lr: 0.002556  loss: 3.7837 (3.6354)  weight_decay: 0.0500 (0.0500)  time: 0.5439  data: 0.0284  max mem: 31830
Epoch: [134]  [300/312]  eta: 0:00:06  lr: 0.002555  min_lr: 0.002555  loss: 3.5756 (3.6329)  weight_decay: 0.0500 (0.0500)  time: 0.4658  data: 0.0072  max mem: 31830
Epoch: [134]  [310/312]  eta: 0:00:01  lr: 0.002554  min_lr: 0.002554  loss: 3.7077 (3.6424)  weight_decay: 0.0500 (0.0500)  time: 0.4257  data: 0.0071  max mem: 31830
Epoch: [134]  [311/312]  eta: 0:00:00  lr: 0.002554  min_lr: 0.002554  loss: 3.6776 (3.6404)  weight_decay: 0.0500 (0.0500)  time: 0.4255  data: 0.0071  max mem: 31830
Epoch: [134] Total time: 0:02:54 (0.5592 s / it)
Averaged stats: lr: 0.002554  min_lr: 0.002554  loss: 3.6776 (3.6439)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:25  loss: 1.4082 (1.4082)  acc1: 76.0417 (76.0417)  acc5: 91.6667 (91.6667)  time: 9.5299  data: 9.3628  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6733 (1.6400)  acc1: 67.1875 (68.1600)  acc5: 88.6719 (88.3840)  time: 1.1761  data: 1.0404  max mem: 31830
Test: Total time: 0:00:10 (1.1961 s / it)
* Acc@1 67.602 Acc@5 88.640 loss 1.642
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 68.13%
Epoch: [135]  [  0/312]  eta: 1:00:45  lr: 0.002554  min_lr: 0.002554  loss: 4.4396 (4.4396)  weight_decay: 0.0500 (0.0500)  time: 11.6849  data: 8.9635  max mem: 31830
Epoch: [135]  [ 10/312]  eta: 0:09:31  lr: 0.002553  min_lr: 0.002553  loss: 3.5919 (3.5514)  weight_decay: 0.0500 (0.0500)  time: 1.8911  data: 0.9883  max mem: 31830
Epoch: [135]  [ 20/312]  eta: 0:05:43  lr: 0.002553  min_lr: 0.002553  loss: 3.6177 (3.7085)  weight_decay: 0.0500 (0.0500)  time: 0.6521  data: 0.0957  max mem: 31830
Epoch: [135]  [ 30/312]  eta: 0:04:25  lr: 0.002552  min_lr: 0.002552  loss: 3.6872 (3.6661)  weight_decay: 0.0500 (0.0500)  time: 0.4212  data: 0.0261  max mem: 31830
Epoch: [135]  [ 40/312]  eta: 0:03:40  lr: 0.002551  min_lr: 0.002551  loss: 3.5445 (3.5953)  weight_decay: 0.0500 (0.0500)  time: 0.4249  data: 0.0263  max mem: 31830
Epoch: [135]  [ 50/312]  eta: 0:03:11  lr: 0.002551  min_lr: 0.002551  loss: 3.5445 (3.5785)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [135]  [ 60/312]  eta: 0:02:50  lr: 0.002550  min_lr: 0.002550  loss: 3.8404 (3.6263)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [135]  [ 70/312]  eta: 0:02:34  lr: 0.002549  min_lr: 0.002549  loss: 3.9698 (3.6346)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [135]  [ 80/312]  eta: 0:02:25  lr: 0.002549  min_lr: 0.002549  loss: 3.9698 (3.6725)  weight_decay: 0.0500 (0.0500)  time: 0.4794  data: 0.0016  max mem: 31830
Epoch: [135]  [ 90/312]  eta: 0:02:16  lr: 0.002548  min_lr: 0.002548  loss: 3.7480 (3.6517)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0200  max mem: 31830
Epoch: [135]  [100/312]  eta: 0:02:08  lr: 0.002547  min_lr: 0.002547  loss: 3.6784 (3.6609)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.0306  max mem: 31830
Epoch: [135]  [110/312]  eta: 0:02:02  lr: 0.002546  min_lr: 0.002546  loss: 3.7585 (3.6623)  weight_decay: 0.0500 (0.0500)  time: 0.5701  data: 0.0370  max mem: 31830
Epoch: [135]  [120/312]  eta: 0:01:54  lr: 0.002546  min_lr: 0.002546  loss: 3.8353 (3.6700)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0428  max mem: 31830
Epoch: [135]  [130/312]  eta: 0:01:48  lr: 0.002545  min_lr: 0.002545  loss: 3.7026 (3.6539)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0373  max mem: 31830
Epoch: [135]  [140/312]  eta: 0:01:40  lr: 0.002544  min_lr: 0.002544  loss: 3.7665 (3.6825)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0327  max mem: 31830
Epoch: [135]  [150/312]  eta: 0:01:35  lr: 0.002544  min_lr: 0.002544  loss: 3.7665 (3.6519)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0435  max mem: 31830
Epoch: [135]  [160/312]  eta: 0:01:29  lr: 0.002543  min_lr: 0.002543  loss: 3.3822 (3.6521)  weight_decay: 0.0500 (0.0500)  time: 0.5891  data: 0.0432  max mem: 31830
Epoch: [135]  [170/312]  eta: 0:01:22  lr: 0.002542  min_lr: 0.002542  loss: 3.7339 (3.6367)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0309  max mem: 31830
Epoch: [135]  [180/312]  eta: 0:01:16  lr: 0.002542  min_lr: 0.002542  loss: 3.7339 (3.6367)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0716  max mem: 31830
Epoch: [135]  [190/312]  eta: 0:01:10  lr: 0.002541  min_lr: 0.002541  loss: 3.7848 (3.6444)  weight_decay: 0.0500 (0.0500)  time: 0.5831  data: 0.0592  max mem: 31830
Epoch: [135]  [200/312]  eta: 0:01:04  lr: 0.002540  min_lr: 0.002540  loss: 3.7623 (3.6513)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0576  max mem: 31830
Epoch: [135]  [210/312]  eta: 0:00:59  lr: 0.002540  min_lr: 0.002540  loss: 3.8328 (3.6638)  weight_decay: 0.0500 (0.0500)  time: 0.6092  data: 0.1005  max mem: 31830
Epoch: [135]  [220/312]  eta: 0:00:52  lr: 0.002539  min_lr: 0.002539  loss: 3.8328 (3.6632)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0490  max mem: 31830
Epoch: [135]  [230/312]  eta: 0:00:47  lr: 0.002538  min_lr: 0.002538  loss: 3.8172 (3.6616)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0404  max mem: 31830
Epoch: [135]  [240/312]  eta: 0:00:41  lr: 0.002537  min_lr: 0.002537  loss: 3.7976 (3.6582)  weight_decay: 0.0500 (0.0500)  time: 0.5900  data: 0.0406  max mem: 31830
Epoch: [135]  [250/312]  eta: 0:00:35  lr: 0.002537  min_lr: 0.002537  loss: 3.7560 (3.6553)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0320  max mem: 31830
Epoch: [135]  [260/312]  eta: 0:00:29  lr: 0.002536  min_lr: 0.002536  loss: 3.7560 (3.6500)  weight_decay: 0.0500 (0.0500)  time: 0.5701  data: 0.0553  max mem: 31830
Epoch: [135]  [270/312]  eta: 0:00:24  lr: 0.002535  min_lr: 0.002535  loss: 3.6708 (3.6470)  weight_decay: 0.0500 (0.0500)  time: 0.6293  data: 0.0242  max mem: 31830
Epoch: [135]  [280/312]  eta: 0:00:18  lr: 0.002535  min_lr: 0.002535  loss: 3.7034 (3.6513)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0196  max mem: 31830
Epoch: [135]  [290/312]  eta: 0:00:12  lr: 0.002534  min_lr: 0.002534  loss: 3.9276 (3.6573)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0326  max mem: 31830
Epoch: [135]  [300/312]  eta: 0:00:06  lr: 0.002533  min_lr: 0.002533  loss: 3.7448 (3.6524)  weight_decay: 0.0500 (0.0500)  time: 0.4913  data: 0.0135  max mem: 31830
Epoch: [135]  [310/312]  eta: 0:00:01  lr: 0.002533  min_lr: 0.002533  loss: 3.6113 (3.6525)  weight_decay: 0.0500 (0.0500)  time: 0.3926  data: 0.0001  max mem: 31830
Epoch: [135]  [311/312]  eta: 0:00:00  lr: 0.002533  min_lr: 0.002533  loss: 3.6113 (3.6529)  weight_decay: 0.0500 (0.0500)  time: 0.3924  data: 0.0001  max mem: 31830
Epoch: [135] Total time: 0:02:55 (0.5639 s / it)
Averaged stats: lr: 0.002533  min_lr: 0.002533  loss: 3.6113 (3.6289)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.4761 (1.4761)  acc1: 77.3438 (77.3438)  acc5: 92.5781 (92.5781)  time: 8.9313  data: 8.7639  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7158 (1.6864)  acc1: 68.7500 (68.7680)  acc5: 89.3229 (89.0080)  time: 1.1105  data: 0.9738  max mem: 31830
Test: Total time: 0:00:10 (1.1232 s / it)
* Acc@1 68.254 Acc@5 88.946 loss 1.688
Accuracy of the model on the 50000 test images: 68.3%
Max accuracy: 68.25%
Epoch: [136]  [  0/312]  eta: 0:57:30  lr: 0.002532  min_lr: 0.002532  loss: 3.9622 (3.9622)  weight_decay: 0.0500 (0.0500)  time: 11.0605  data: 10.6673  max mem: 31830
Epoch: [136]  [ 10/312]  eta: 0:08:47  lr: 0.002532  min_lr: 0.002532  loss: 3.4386 (3.4416)  weight_decay: 0.0500 (0.0500)  time: 1.7452  data: 0.9702  max mem: 31830
Epoch: [136]  [ 20/312]  eta: 0:05:29  lr: 0.002531  min_lr: 0.002531  loss: 3.6160 (3.5710)  weight_decay: 0.0500 (0.0500)  time: 0.6323  data: 0.0324  max mem: 31830
Epoch: [136]  [ 30/312]  eta: 0:04:11  lr: 0.002530  min_lr: 0.002530  loss: 3.7455 (3.5855)  weight_decay: 0.0500 (0.0500)  time: 0.4246  data: 0.0326  max mem: 31830
Epoch: [136]  [ 40/312]  eta: 0:03:30  lr: 0.002530  min_lr: 0.002530  loss: 3.6598 (3.5784)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0015  max mem: 31830
Epoch: [136]  [ 50/312]  eta: 0:03:05  lr: 0.002529  min_lr: 0.002529  loss: 3.6537 (3.6100)  weight_decay: 0.0500 (0.0500)  time: 0.4162  data: 0.0197  max mem: 31830
Epoch: [136]  [ 60/312]  eta: 0:02:45  lr: 0.002528  min_lr: 0.002528  loss: 3.8152 (3.6233)  weight_decay: 0.0500 (0.0500)  time: 0.4134  data: 0.0189  max mem: 31830
Epoch: [136]  [ 70/312]  eta: 0:02:36  lr: 0.002528  min_lr: 0.002528  loss: 3.9776 (3.6610)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0967  max mem: 31830
Epoch: [136]  [ 80/312]  eta: 0:02:22  lr: 0.002527  min_lr: 0.002527  loss: 3.9776 (3.6657)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.0967  max mem: 31830
Epoch: [136]  [ 90/312]  eta: 0:02:17  lr: 0.002526  min_lr: 0.002526  loss: 3.7723 (3.6710)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.1352  max mem: 31830
Epoch: [136]  [100/312]  eta: 0:02:11  lr: 0.002526  min_lr: 0.002526  loss: 3.6401 (3.6583)  weight_decay: 0.0500 (0.0500)  time: 0.6526  data: 0.2607  max mem: 31830
Epoch: [136]  [110/312]  eta: 0:02:01  lr: 0.002525  min_lr: 0.002525  loss: 3.6720 (3.6657)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.1269  max mem: 31830
Epoch: [136]  [120/312]  eta: 0:01:55  lr: 0.002524  min_lr: 0.002524  loss: 3.7597 (3.6564)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.1064  max mem: 31830
Epoch: [136]  [130/312]  eta: 0:01:49  lr: 0.002523  min_lr: 0.002523  loss: 3.0499 (3.6055)  weight_decay: 0.0500 (0.0500)  time: 0.6128  data: 0.2141  max mem: 31830
Epoch: [136]  [140/312]  eta: 0:01:41  lr: 0.002523  min_lr: 0.002523  loss: 3.6964 (3.6276)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.1097  max mem: 31830
Epoch: [136]  [150/312]  eta: 0:01:35  lr: 0.002522  min_lr: 0.002522  loss: 3.7346 (3.6246)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.1113  max mem: 31830
Epoch: [136]  [160/312]  eta: 0:01:27  lr: 0.002521  min_lr: 0.002521  loss: 3.7084 (3.6235)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.1105  max mem: 31830
Epoch: [136]  [170/312]  eta: 0:01:22  lr: 0.002521  min_lr: 0.002521  loss: 3.7439 (3.6148)  weight_decay: 0.0500 (0.0500)  time: 0.4869  data: 0.0916  max mem: 31830
Epoch: [136]  [180/312]  eta: 0:01:16  lr: 0.002520  min_lr: 0.002520  loss: 3.6013 (3.6062)  weight_decay: 0.0500 (0.0500)  time: 0.6226  data: 0.2235  max mem: 31830
Epoch: [136]  [190/312]  eta: 0:01:09  lr: 0.002519  min_lr: 0.002519  loss: 3.6013 (3.6066)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.1326  max mem: 31830
Epoch: [136]  [200/312]  eta: 0:01:04  lr: 0.002519  min_lr: 0.002519  loss: 3.6828 (3.6053)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.1204  max mem: 31830
Epoch: [136]  [210/312]  eta: 0:00:59  lr: 0.002518  min_lr: 0.002518  loss: 3.8953 (3.6136)  weight_decay: 0.0500 (0.0500)  time: 0.6597  data: 0.2651  max mem: 31830
Epoch: [136]  [220/312]  eta: 0:00:52  lr: 0.002517  min_lr: 0.002517  loss: 3.9782 (3.6253)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.1456  max mem: 31830
Epoch: [136]  [230/312]  eta: 0:00:47  lr: 0.002516  min_lr: 0.002516  loss: 3.9439 (3.6162)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.1075  max mem: 31830
Epoch: [136]  [240/312]  eta: 0:00:40  lr: 0.002516  min_lr: 0.002516  loss: 3.5528 (3.6086)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.1074  max mem: 31830
Epoch: [136]  [250/312]  eta: 0:00:35  lr: 0.002515  min_lr: 0.002515  loss: 3.8029 (3.6084)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0944  max mem: 31830
Epoch: [136]  [260/312]  eta: 0:00:29  lr: 0.002514  min_lr: 0.002514  loss: 3.5208 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.5919  data: 0.1978  max mem: 31830
Epoch: [136]  [270/312]  eta: 0:00:23  lr: 0.002514  min_lr: 0.002514  loss: 3.5208 (3.6010)  weight_decay: 0.0500 (0.0500)  time: 0.5009  data: 0.1047  max mem: 31830
Epoch: [136]  [280/312]  eta: 0:00:18  lr: 0.002513  min_lr: 0.002513  loss: 3.3902 (3.5965)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.1215  max mem: 31830
Epoch: [136]  [290/312]  eta: 0:00:12  lr: 0.002512  min_lr: 0.002512  loss: 3.6237 (3.6001)  weight_decay: 0.0500 (0.0500)  time: 0.6106  data: 0.2080  max mem: 31830
Epoch: [136]  [300/312]  eta: 0:00:06  lr: 0.002512  min_lr: 0.002512  loss: 3.7274 (3.6050)  weight_decay: 0.0500 (0.0500)  time: 0.5030  data: 0.0874  max mem: 31830
Epoch: [136]  [310/312]  eta: 0:00:01  lr: 0.002511  min_lr: 0.002511  loss: 3.8749 (3.6121)  weight_decay: 0.0500 (0.0500)  time: 0.4026  data: 0.0001  max mem: 31830
Epoch: [136]  [311/312]  eta: 0:00:00  lr: 0.002511  min_lr: 0.002511  loss: 3.8749 (3.6124)  weight_decay: 0.0500 (0.0500)  time: 0.4023  data: 0.0001  max mem: 31830
Epoch: [136] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.002511  min_lr: 0.002511  loss: 3.8749 (3.6275)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3405 (1.3405)  acc1: 76.4323 (76.4323)  acc5: 91.7969 (91.7969)  time: 8.5356  data: 8.3745  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7890 (1.6237)  acc1: 64.8438 (67.5200)  acc5: 86.9792 (88.0480)  time: 1.0681  data: 0.9306  max mem: 31830
Test: Total time: 0:00:09 (1.0794 s / it)
* Acc@1 67.368 Acc@5 88.472 loss 1.612
Accuracy of the model on the 50000 test images: 67.4%
Max accuracy: 68.25%
Epoch: [137]  [  0/312]  eta: 1:04:19  lr: 0.002511  min_lr: 0.002511  loss: 4.0995 (4.0995)  weight_decay: 0.0500 (0.0500)  time: 12.3718  data: 8.7507  max mem: 31830
Epoch: [137]  [ 10/312]  eta: 0:08:28  lr: 0.002510  min_lr: 0.002510  loss: 3.6288 (3.4733)  weight_decay: 0.0500 (0.0500)  time: 1.6828  data: 0.9412  max mem: 31830
Epoch: [137]  [ 20/312]  eta: 0:05:24  lr: 0.002509  min_lr: 0.002509  loss: 3.6288 (3.5678)  weight_decay: 0.0500 (0.0500)  time: 0.5492  data: 0.1101  max mem: 31830
Epoch: [137]  [ 30/312]  eta: 0:04:08  lr: 0.002509  min_lr: 0.002509  loss: 3.8012 (3.5572)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0306  max mem: 31830
Epoch: [137]  [ 40/312]  eta: 0:03:28  lr: 0.002508  min_lr: 0.002508  loss: 3.6509 (3.5239)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0010  max mem: 31830
Epoch: [137]  [ 50/312]  eta: 0:03:02  lr: 0.002507  min_lr: 0.002507  loss: 3.5085 (3.5253)  weight_decay: 0.0500 (0.0500)  time: 0.4098  data: 0.0007  max mem: 31830
Epoch: [137]  [ 60/312]  eta: 0:02:43  lr: 0.002507  min_lr: 0.002507  loss: 3.6571 (3.5760)  weight_decay: 0.0500 (0.0500)  time: 0.4087  data: 0.0007  max mem: 31830
Epoch: [137]  [ 70/312]  eta: 0:02:33  lr: 0.002506  min_lr: 0.002506  loss: 3.6981 (3.5564)  weight_decay: 0.0500 (0.0500)  time: 0.4769  data: 0.0195  max mem: 31830
Epoch: [137]  [ 80/312]  eta: 0:02:24  lr: 0.002505  min_lr: 0.002505  loss: 3.6981 (3.5946)  weight_decay: 0.0500 (0.0500)  time: 0.5530  data: 0.0685  max mem: 31830
Epoch: [137]  [ 90/312]  eta: 0:02:15  lr: 0.002505  min_lr: 0.002505  loss: 3.7364 (3.5873)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0498  max mem: 31830
Epoch: [137]  [100/312]  eta: 0:02:08  lr: 0.002504  min_lr: 0.002504  loss: 3.6354 (3.5956)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0550  max mem: 31830
Epoch: [137]  [110/312]  eta: 0:01:58  lr: 0.002503  min_lr: 0.002503  loss: 3.6354 (3.5905)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0550  max mem: 31830
Epoch: [137]  [120/312]  eta: 0:01:53  lr: 0.002502  min_lr: 0.002502  loss: 3.8290 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0820  max mem: 31830
Epoch: [137]  [130/312]  eta: 0:01:47  lr: 0.002502  min_lr: 0.002502  loss: 3.9099 (3.6203)  weight_decay: 0.0500 (0.0500)  time: 0.6039  data: 0.1587  max mem: 31830
Epoch: [137]  [140/312]  eta: 0:01:39  lr: 0.002501  min_lr: 0.002501  loss: 3.8453 (3.6115)  weight_decay: 0.0500 (0.0500)  time: 0.4968  data: 0.0776  max mem: 31830
Epoch: [137]  [150/312]  eta: 0:01:33  lr: 0.002500  min_lr: 0.002500  loss: 3.2708 (3.5880)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0869  max mem: 31830
Epoch: [137]  [160/312]  eta: 0:01:28  lr: 0.002500  min_lr: 0.002500  loss: 3.5762 (3.5974)  weight_decay: 0.0500 (0.0500)  time: 0.6269  data: 0.1702  max mem: 31830
Epoch: [137]  [170/312]  eta: 0:01:21  lr: 0.002499  min_lr: 0.002499  loss: 3.8128 (3.6057)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0840  max mem: 31830
Epoch: [137]  [180/312]  eta: 0:01:15  lr: 0.002498  min_lr: 0.002498  loss: 3.6789 (3.5944)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0707  max mem: 31830
Epoch: [137]  [190/312]  eta: 0:01:09  lr: 0.002498  min_lr: 0.002498  loss: 3.3794 (3.5872)  weight_decay: 0.0500 (0.0500)  time: 0.5385  data: 0.0707  max mem: 31830
Epoch: [137]  [200/312]  eta: 0:01:03  lr: 0.002497  min_lr: 0.002497  loss: 3.1955 (3.5680)  weight_decay: 0.0500 (0.0500)  time: 0.5089  data: 0.0460  max mem: 31830
Epoch: [137]  [210/312]  eta: 0:00:58  lr: 0.002496  min_lr: 0.002496  loss: 3.2648 (3.5738)  weight_decay: 0.0500 (0.0500)  time: 0.6033  data: 0.1088  max mem: 31830
Epoch: [137]  [220/312]  eta: 0:00:51  lr: 0.002495  min_lr: 0.002495  loss: 3.5878 (3.5689)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0641  max mem: 31830
Epoch: [137]  [230/312]  eta: 0:00:46  lr: 0.002495  min_lr: 0.002495  loss: 3.5878 (3.5699)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0692  max mem: 31830
Epoch: [137]  [240/312]  eta: 0:00:40  lr: 0.002494  min_lr: 0.002494  loss: 3.8054 (3.5775)  weight_decay: 0.0500 (0.0500)  time: 0.6265  data: 0.1295  max mem: 31830
Epoch: [137]  [250/312]  eta: 0:00:34  lr: 0.002493  min_lr: 0.002493  loss: 3.8261 (3.5684)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0617  max mem: 31830
Epoch: [137]  [260/312]  eta: 0:00:29  lr: 0.002493  min_lr: 0.002493  loss: 3.5473 (3.5726)  weight_decay: 0.0500 (0.0500)  time: 0.5057  data: 0.0741  max mem: 31830
Epoch: [137]  [270/312]  eta: 0:00:23  lr: 0.002492  min_lr: 0.002492  loss: 3.5473 (3.5762)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0741  max mem: 31830
Epoch: [137]  [280/312]  eta: 0:00:17  lr: 0.002491  min_lr: 0.002491  loss: 3.5470 (3.5728)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0586  max mem: 31830
Epoch: [137]  [290/312]  eta: 0:00:12  lr: 0.002491  min_lr: 0.002491  loss: 3.7758 (3.5832)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.1164  max mem: 31830
Epoch: [137]  [300/312]  eta: 0:00:06  lr: 0.002490  min_lr: 0.002490  loss: 3.7981 (3.5848)  weight_decay: 0.0500 (0.0500)  time: 0.4801  data: 0.0582  max mem: 31830
Epoch: [137]  [310/312]  eta: 0:00:01  lr: 0.002489  min_lr: 0.002489  loss: 3.6626 (3.5860)  weight_decay: 0.0500 (0.0500)  time: 0.3927  data: 0.0001  max mem: 31830
Epoch: [137]  [311/312]  eta: 0:00:00  lr: 0.002489  min_lr: 0.002489  loss: 3.6626 (3.5855)  weight_decay: 0.0500 (0.0500)  time: 0.3926  data: 0.0001  max mem: 31830
Epoch: [137] Total time: 0:02:53 (0.5546 s / it)
Averaged stats: lr: 0.002489  min_lr: 0.002489  loss: 3.6626 (3.6168)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.3231 (1.3231)  acc1: 74.8698 (74.8698)  acc5: 91.9271 (91.9271)  time: 7.9470  data: 7.7819  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6934 (1.5738)  acc1: 67.4479 (68.1120)  acc5: 87.5000 (88.2720)  time: 1.0408  data: 0.9001  max mem: 31830
Test: Total time: 0:00:09 (1.0502 s / it)
* Acc@1 67.970 Acc@5 88.586 loss 1.557
Accuracy of the model on the 50000 test images: 68.0%
Max accuracy: 68.25%
Epoch: [138]  [  0/312]  eta: 1:02:59  lr: 0.002489  min_lr: 0.002489  loss: 3.7614 (3.7614)  weight_decay: 0.0500 (0.0500)  time: 12.1137  data: 9.9960  max mem: 31830
Epoch: [138]  [ 10/312]  eta: 0:09:25  lr: 0.002488  min_lr: 0.002488  loss: 3.7614 (3.6584)  weight_decay: 0.0500 (0.0500)  time: 1.8738  data: 1.0554  max mem: 31830
Epoch: [138]  [ 20/312]  eta: 0:05:40  lr: 0.002488  min_lr: 0.002488  loss: 3.8195 (3.7450)  weight_decay: 0.0500 (0.0500)  time: 0.6181  data: 0.0809  max mem: 31830
Epoch: [138]  [ 30/312]  eta: 0:04:18  lr: 0.002487  min_lr: 0.002487  loss: 3.9021 (3.7816)  weight_decay: 0.0500 (0.0500)  time: 0.3894  data: 0.0006  max mem: 31830
Epoch: [138]  [ 40/312]  eta: 0:03:34  lr: 0.002486  min_lr: 0.002486  loss: 3.7868 (3.7892)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0008  max mem: 31830
Epoch: [138]  [ 50/312]  eta: 0:03:06  lr: 0.002486  min_lr: 0.002486  loss: 3.7868 (3.7439)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0009  max mem: 31830
Epoch: [138]  [ 60/312]  eta: 0:02:46  lr: 0.002485  min_lr: 0.002485  loss: 3.8346 (3.7384)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0010  max mem: 31830
Epoch: [138]  [ 70/312]  eta: 0:02:31  lr: 0.002484  min_lr: 0.002484  loss: 3.5586 (3.6913)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [138]  [ 80/312]  eta: 0:02:23  lr: 0.002483  min_lr: 0.002483  loss: 3.3127 (3.6372)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0123  max mem: 31830
Epoch: [138]  [ 90/312]  eta: 0:02:14  lr: 0.002483  min_lr: 0.002483  loss: 3.6932 (3.6539)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0249  max mem: 31830
Epoch: [138]  [100/312]  eta: 0:02:07  lr: 0.002482  min_lr: 0.002482  loss: 3.6932 (3.6309)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0516  max mem: 31830
Epoch: [138]  [110/312]  eta: 0:02:02  lr: 0.002481  min_lr: 0.002481  loss: 3.5419 (3.6163)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0768  max mem: 31830
Epoch: [138]  [120/312]  eta: 0:01:53  lr: 0.002481  min_lr: 0.002481  loss: 3.7351 (3.6433)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0387  max mem: 31830
Epoch: [138]  [130/312]  eta: 0:01:47  lr: 0.002480  min_lr: 0.002480  loss: 3.9797 (3.6528)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0305  max mem: 31830
Epoch: [138]  [140/312]  eta: 0:01:42  lr: 0.002479  min_lr: 0.002479  loss: 3.8925 (3.6478)  weight_decay: 0.0500 (0.0500)  time: 0.6141  data: 0.0515  max mem: 31830
Epoch: [138]  [150/312]  eta: 0:01:35  lr: 0.002479  min_lr: 0.002479  loss: 3.6686 (3.6493)  weight_decay: 0.0500 (0.0500)  time: 0.5664  data: 0.0218  max mem: 31830
Epoch: [138]  [160/312]  eta: 0:01:29  lr: 0.002478  min_lr: 0.002478  loss: 3.7896 (3.6577)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0131  max mem: 31830
Epoch: [138]  [170/312]  eta: 0:01:22  lr: 0.002477  min_lr: 0.002477  loss: 3.7687 (3.6526)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0229  max mem: 31830
Epoch: [138]  [180/312]  eta: 0:01:17  lr: 0.002476  min_lr: 0.002476  loss: 3.7652 (3.6674)  weight_decay: 0.0500 (0.0500)  time: 0.5554  data: 0.0121  max mem: 31830
Epoch: [138]  [190/312]  eta: 0:01:11  lr: 0.002476  min_lr: 0.002476  loss: 3.9322 (3.6764)  weight_decay: 0.0500 (0.0500)  time: 0.6202  data: 0.0144  max mem: 31830
Epoch: [138]  [200/312]  eta: 0:01:04  lr: 0.002475  min_lr: 0.002475  loss: 3.9903 (3.6919)  weight_decay: 0.0500 (0.0500)  time: 0.5014  data: 0.0271  max mem: 31830
Epoch: [138]  [210/312]  eta: 0:00:58  lr: 0.002474  min_lr: 0.002474  loss: 3.9450 (3.6851)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0363  max mem: 31830
Epoch: [138]  [220/312]  eta: 0:00:53  lr: 0.002474  min_lr: 0.002474  loss: 3.5529 (3.6840)  weight_decay: 0.0500 (0.0500)  time: 0.6328  data: 0.0222  max mem: 31830
Epoch: [138]  [230/312]  eta: 0:00:47  lr: 0.002473  min_lr: 0.002473  loss: 3.8420 (3.6890)  weight_decay: 0.0500 (0.0500)  time: 0.5366  data: 0.0116  max mem: 31830
Epoch: [138]  [240/312]  eta: 0:00:41  lr: 0.002472  min_lr: 0.002472  loss: 3.8804 (3.6977)  weight_decay: 0.0500 (0.0500)  time: 0.5018  data: 0.0126  max mem: 31830
Epoch: [138]  [250/312]  eta: 0:00:35  lr: 0.002472  min_lr: 0.002472  loss: 3.6697 (3.6797)  weight_decay: 0.0500 (0.0500)  time: 0.5108  data: 0.0020  max mem: 31830
Epoch: [138]  [260/312]  eta: 0:00:29  lr: 0.002471  min_lr: 0.002471  loss: 3.6567 (3.6838)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0080  max mem: 31830
Epoch: [138]  [270/312]  eta: 0:00:24  lr: 0.002470  min_lr: 0.002470  loss: 3.8370 (3.6815)  weight_decay: 0.0500 (0.0500)  time: 0.6244  data: 0.0274  max mem: 31830
Epoch: [138]  [280/312]  eta: 0:00:18  lr: 0.002470  min_lr: 0.002470  loss: 3.7369 (3.6802)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0226  max mem: 31830
Epoch: [138]  [290/312]  eta: 0:00:12  lr: 0.002469  min_lr: 0.002469  loss: 3.7010 (3.6839)  weight_decay: 0.0500 (0.0500)  time: 0.5037  data: 0.0161  max mem: 31830
Epoch: [138]  [300/312]  eta: 0:00:06  lr: 0.002468  min_lr: 0.002468  loss: 3.7044 (3.6767)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0137  max mem: 31830
Epoch: [138]  [310/312]  eta: 0:00:01  lr: 0.002467  min_lr: 0.002467  loss: 3.4919 (3.6734)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [138]  [311/312]  eta: 0:00:00  lr: 0.002467  min_lr: 0.002467  loss: 3.4919 (3.6731)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [138] Total time: 0:02:54 (0.5597 s / it)
Averaged stats: lr: 0.002467  min_lr: 0.002467  loss: 3.4919 (3.6399)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.4840 (1.4840)  acc1: 75.2604 (75.2604)  acc5: 92.3177 (92.3177)  time: 8.4538  data: 8.2864  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8321 (1.7624)  acc1: 69.0104 (68.3360)  acc5: 88.5417 (88.5920)  time: 1.0563  data: 0.9208  max mem: 31830
Test: Total time: 0:00:09 (1.0658 s / it)
* Acc@1 68.138 Acc@5 88.790 loss 1.754
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 68.25%
Epoch: [139]  [  0/312]  eta: 1:03:52  lr: 0.002467  min_lr: 0.002467  loss: 4.4065 (4.4065)  weight_decay: 0.0500 (0.0500)  time: 12.2850  data: 10.0952  max mem: 31830
Epoch: [139]  [ 10/312]  eta: 0:08:26  lr: 0.002467  min_lr: 0.002467  loss: 3.7813 (3.6345)  weight_decay: 0.0500 (0.0500)  time: 1.6780  data: 0.9985  max mem: 31830
Epoch: [139]  [ 20/312]  eta: 0:05:32  lr: 0.002466  min_lr: 0.002466  loss: 3.7813 (3.7388)  weight_decay: 0.0500 (0.0500)  time: 0.5804  data: 0.0448  max mem: 31830
Epoch: [139]  [ 30/312]  eta: 0:04:13  lr: 0.002465  min_lr: 0.002465  loss: 3.8230 (3.6737)  weight_decay: 0.0500 (0.0500)  time: 0.4718  data: 0.0007  max mem: 31830
Epoch: [139]  [ 40/312]  eta: 0:03:31  lr: 0.002464  min_lr: 0.002464  loss: 3.6323 (3.6564)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0007  max mem: 31830
Epoch: [139]  [ 50/312]  eta: 0:03:09  lr: 0.002464  min_lr: 0.002464  loss: 3.7591 (3.6673)  weight_decay: 0.0500 (0.0500)  time: 0.4543  data: 0.0007  max mem: 31830
Epoch: [139]  [ 60/312]  eta: 0:02:49  lr: 0.002463  min_lr: 0.002463  loss: 3.9061 (3.7030)  weight_decay: 0.0500 (0.0500)  time: 0.4529  data: 0.0006  max mem: 31830
Epoch: [139]  [ 70/312]  eta: 0:02:38  lr: 0.002462  min_lr: 0.002462  loss: 3.8692 (3.7016)  weight_decay: 0.0500 (0.0500)  time: 0.4825  data: 0.0121  max mem: 31830
Epoch: [139]  [ 80/312]  eta: 0:02:31  lr: 0.002462  min_lr: 0.002462  loss: 3.5873 (3.6945)  weight_decay: 0.0500 (0.0500)  time: 0.5923  data: 0.0375  max mem: 31830
Epoch: [139]  [ 90/312]  eta: 0:02:18  lr: 0.002461  min_lr: 0.002461  loss: 3.7643 (3.6996)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0260  max mem: 31830
Epoch: [139]  [100/312]  eta: 0:02:11  lr: 0.002460  min_lr: 0.002460  loss: 3.7230 (3.6856)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0052  max mem: 31830
Epoch: [139]  [110/312]  eta: 0:02:01  lr: 0.002460  min_lr: 0.002460  loss: 3.6184 (3.6859)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0053  max mem: 31830
Epoch: [139]  [120/312]  eta: 0:01:54  lr: 0.002459  min_lr: 0.002459  loss: 3.5901 (3.6614)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0329  max mem: 31830
Epoch: [139]  [130/312]  eta: 0:01:50  lr: 0.002458  min_lr: 0.002458  loss: 3.4644 (3.6383)  weight_decay: 0.0500 (0.0500)  time: 0.6474  data: 0.0972  max mem: 31830
Epoch: [139]  [140/312]  eta: 0:01:41  lr: 0.002457  min_lr: 0.002457  loss: 3.5178 (3.6394)  weight_decay: 0.0500 (0.0500)  time: 0.5569  data: 0.0651  max mem: 31830
Epoch: [139]  [150/312]  eta: 0:01:35  lr: 0.002457  min_lr: 0.002457  loss: 3.5396 (3.6275)  weight_decay: 0.0500 (0.0500)  time: 0.4820  data: 0.0131  max mem: 31830
Epoch: [139]  [160/312]  eta: 0:01:29  lr: 0.002456  min_lr: 0.002456  loss: 3.5730 (3.6315)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0132  max mem: 31830
Epoch: [139]  [170/312]  eta: 0:01:22  lr: 0.002455  min_lr: 0.002455  loss: 3.7661 (3.6236)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0074  max mem: 31830
Epoch: [139]  [180/312]  eta: 0:01:16  lr: 0.002455  min_lr: 0.002455  loss: 3.5651 (3.6288)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0075  max mem: 31830
Epoch: [139]  [190/312]  eta: 0:01:09  lr: 0.002454  min_lr: 0.002454  loss: 3.7384 (3.6320)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0010  max mem: 31830
Epoch: [139]  [200/312]  eta: 0:01:04  lr: 0.002453  min_lr: 0.002453  loss: 3.6141 (3.6263)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0010  max mem: 31830
Epoch: [139]  [210/312]  eta: 0:00:59  lr: 0.002453  min_lr: 0.002453  loss: 3.4299 (3.6159)  weight_decay: 0.0500 (0.0500)  time: 0.6385  data: 0.0014  max mem: 31830
Epoch: [139]  [220/312]  eta: 0:00:52  lr: 0.002452  min_lr: 0.002452  loss: 3.6273 (3.6163)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0022  max mem: 31830
Epoch: [139]  [230/312]  eta: 0:00:47  lr: 0.002451  min_lr: 0.002451  loss: 3.8668 (3.6212)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0031  max mem: 31830
Epoch: [139]  [240/312]  eta: 0:00:41  lr: 0.002450  min_lr: 0.002450  loss: 3.8772 (3.6237)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0022  max mem: 31830
Epoch: [139]  [250/312]  eta: 0:00:35  lr: 0.002450  min_lr: 0.002450  loss: 3.7041 (3.6205)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0201  max mem: 31830
Epoch: [139]  [260/312]  eta: 0:00:29  lr: 0.002449  min_lr: 0.002449  loss: 3.3662 (3.6151)  weight_decay: 0.0500 (0.0500)  time: 0.6110  data: 0.0202  max mem: 31830
Epoch: [139]  [270/312]  eta: 0:00:23  lr: 0.002448  min_lr: 0.002448  loss: 3.4347 (3.6088)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0008  max mem: 31830
Epoch: [139]  [280/312]  eta: 0:00:18  lr: 0.002448  min_lr: 0.002448  loss: 3.7459 (3.6180)  weight_decay: 0.0500 (0.0500)  time: 0.5593  data: 0.0029  max mem: 31830
Epoch: [139]  [290/312]  eta: 0:00:12  lr: 0.002447  min_lr: 0.002447  loss: 3.7453 (3.6173)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.0026  max mem: 31830
Epoch: [139]  [300/312]  eta: 0:00:06  lr: 0.002446  min_lr: 0.002446  loss: 3.5873 (3.6212)  weight_decay: 0.0500 (0.0500)  time: 0.4553  data: 0.0002  max mem: 31830
Epoch: [139]  [310/312]  eta: 0:00:01  lr: 0.002446  min_lr: 0.002446  loss: 3.5637 (3.6179)  weight_decay: 0.0500 (0.0500)  time: 0.4173  data: 0.0001  max mem: 31830
Epoch: [139]  [311/312]  eta: 0:00:00  lr: 0.002446  min_lr: 0.002446  loss: 3.5637 (3.6192)  weight_decay: 0.0500 (0.0500)  time: 0.4172  data: 0.0001  max mem: 31830
Epoch: [139] Total time: 0:02:55 (0.5615 s / it)
Averaged stats: lr: 0.002446  min_lr: 0.002446  loss: 3.5637 (3.6231)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1270 (1.1270)  acc1: 77.3438 (77.3438)  acc5: 93.3594 (93.3594)  time: 8.6526  data: 8.4833  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6134 (1.4584)  acc1: 67.7083 (69.2480)  acc5: 89.3229 (89.5840)  time: 1.0787  data: 0.9427  max mem: 31830
Test: Total time: 0:00:09 (1.1016 s / it)
* Acc@1 69.300 Acc@5 89.726 loss 1.456
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 69.30%
Epoch: [140]  [  0/312]  eta: 0:59:07  lr: 0.002445  min_lr: 0.002445  loss: 3.1181 (3.1181)  weight_decay: 0.0500 (0.0500)  time: 11.3687  data: 9.2563  max mem: 31830
Epoch: [140]  [ 10/312]  eta: 0:09:11  lr: 0.002445  min_lr: 0.002445  loss: 3.9553 (3.8360)  weight_decay: 0.0500 (0.0500)  time: 1.8257  data: 0.9228  max mem: 31830
Epoch: [140]  [ 20/312]  eta: 0:05:33  lr: 0.002444  min_lr: 0.002444  loss: 3.9109 (3.7824)  weight_decay: 0.0500 (0.0500)  time: 0.6291  data: 0.0450  max mem: 31830
Epoch: [140]  [ 30/312]  eta: 0:04:14  lr: 0.002443  min_lr: 0.002443  loss: 3.7251 (3.7030)  weight_decay: 0.0500 (0.0500)  time: 0.3925  data: 0.0006  max mem: 31830
Epoch: [140]  [ 40/312]  eta: 0:03:31  lr: 0.002443  min_lr: 0.002443  loss: 3.8338 (3.7413)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0006  max mem: 31830
Epoch: [140]  [ 50/312]  eta: 0:03:04  lr: 0.002442  min_lr: 0.002442  loss: 3.8033 (3.6769)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0007  max mem: 31830
Epoch: [140]  [ 60/312]  eta: 0:02:44  lr: 0.002441  min_lr: 0.002441  loss: 3.7353 (3.6611)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0012  max mem: 31830
Epoch: [140]  [ 70/312]  eta: 0:02:29  lr: 0.002441  min_lr: 0.002441  loss: 3.8394 (3.6538)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0011  max mem: 31830
Epoch: [140]  [ 80/312]  eta: 0:02:21  lr: 0.002440  min_lr: 0.002440  loss: 3.7390 (3.6497)  weight_decay: 0.0500 (0.0500)  time: 0.4853  data: 0.0065  max mem: 31830
Epoch: [140]  [ 90/312]  eta: 0:02:13  lr: 0.002439  min_lr: 0.002439  loss: 3.6634 (3.6084)  weight_decay: 0.0500 (0.0500)  time: 0.5429  data: 0.0114  max mem: 31830
Epoch: [140]  [100/312]  eta: 0:02:06  lr: 0.002438  min_lr: 0.002438  loss: 3.5691 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.5317  data: 0.0056  max mem: 31830
Epoch: [140]  [110/312]  eta: 0:01:59  lr: 0.002438  min_lr: 0.002438  loss: 3.7700 (3.6061)  weight_decay: 0.0500 (0.0500)  time: 0.5442  data: 0.0112  max mem: 31830
Epoch: [140]  [120/312]  eta: 0:01:52  lr: 0.002437  min_lr: 0.002437  loss: 3.6854 (3.5747)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0246  max mem: 31830
Epoch: [140]  [130/312]  eta: 0:01:47  lr: 0.002436  min_lr: 0.002436  loss: 3.2627 (3.5714)  weight_decay: 0.0500 (0.0500)  time: 0.5815  data: 0.0147  max mem: 31830
Epoch: [140]  [140/312]  eta: 0:01:39  lr: 0.002436  min_lr: 0.002436  loss: 3.9018 (3.5923)  weight_decay: 0.0500 (0.0500)  time: 0.5336  data: 0.0136  max mem: 31830
Epoch: [140]  [150/312]  eta: 0:01:34  lr: 0.002435  min_lr: 0.002435  loss: 3.9329 (3.6042)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0130  max mem: 31830
Epoch: [140]  [160/312]  eta: 0:01:27  lr: 0.002434  min_lr: 0.002434  loss: 3.6968 (3.5978)  weight_decay: 0.0500 (0.0500)  time: 0.5815  data: 0.0009  max mem: 31830
Epoch: [140]  [170/312]  eta: 0:01:21  lr: 0.002434  min_lr: 0.002434  loss: 3.6968 (3.6093)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0021  max mem: 31830
Epoch: [140]  [180/312]  eta: 0:01:15  lr: 0.002433  min_lr: 0.002433  loss: 3.8489 (3.6113)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0022  max mem: 31830
Epoch: [140]  [190/312]  eta: 0:01:09  lr: 0.002432  min_lr: 0.002432  loss: 3.5671 (3.6013)  weight_decay: 0.0500 (0.0500)  time: 0.5904  data: 0.0008  max mem: 31830
Epoch: [140]  [200/312]  eta: 0:01:03  lr: 0.002431  min_lr: 0.002431  loss: 3.5523 (3.5993)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0007  max mem: 31830
Epoch: [140]  [210/312]  eta: 0:00:58  lr: 0.002431  min_lr: 0.002431  loss: 3.6785 (3.5932)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0008  max mem: 31830
Epoch: [140]  [220/312]  eta: 0:00:51  lr: 0.002430  min_lr: 0.002430  loss: 3.7318 (3.5891)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0007  max mem: 31830
Epoch: [140]  [230/312]  eta: 0:00:46  lr: 0.002429  min_lr: 0.002429  loss: 3.7754 (3.6001)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0007  max mem: 31830
Epoch: [140]  [240/312]  eta: 0:00:40  lr: 0.002429  min_lr: 0.002429  loss: 3.8876 (3.6088)  weight_decay: 0.0500 (0.0500)  time: 0.6300  data: 0.0008  max mem: 31830
Epoch: [140]  [250/312]  eta: 0:00:34  lr: 0.002428  min_lr: 0.002428  loss: 3.8876 (3.6149)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0010  max mem: 31830
Epoch: [140]  [260/312]  eta: 0:00:29  lr: 0.002427  min_lr: 0.002427  loss: 3.7214 (3.6118)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0010  max mem: 31830
Epoch: [140]  [270/312]  eta: 0:00:23  lr: 0.002426  min_lr: 0.002426  loss: 3.7140 (3.6118)  weight_decay: 0.0500 (0.0500)  time: 0.5887  data: 0.0008  max mem: 31830
Epoch: [140]  [280/312]  eta: 0:00:18  lr: 0.002426  min_lr: 0.002426  loss: 3.7140 (3.6069)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0029  max mem: 31830
Epoch: [140]  [290/312]  eta: 0:00:12  lr: 0.002425  min_lr: 0.002425  loss: 3.8009 (3.6149)  weight_decay: 0.0500 (0.0500)  time: 0.5330  data: 0.0027  max mem: 31830
Epoch: [140]  [300/312]  eta: 0:00:06  lr: 0.002424  min_lr: 0.002424  loss: 3.8009 (3.6216)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.0002  max mem: 31830
Epoch: [140]  [310/312]  eta: 0:00:01  lr: 0.002424  min_lr: 0.002424  loss: 3.6950 (3.6180)  weight_decay: 0.0500 (0.0500)  time: 0.4163  data: 0.0001  max mem: 31830
Epoch: [140]  [311/312]  eta: 0:00:00  lr: 0.002424  min_lr: 0.002424  loss: 3.7605 (3.6188)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [140] Total time: 0:02:53 (0.5565 s / it)
Averaged stats: lr: 0.002424  min_lr: 0.002424  loss: 3.7605 (3.6460)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.4121 (1.4121)  acc1: 74.0885 (74.0885)  acc5: 93.6198 (93.6198)  time: 8.2689  data: 8.1047  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8003 (1.6674)  acc1: 65.8854 (68.0160)  acc5: 88.1510 (89.0560)  time: 1.0441  data: 0.9006  max mem: 31830
Test: Total time: 0:00:09 (1.0542 s / it)
* Acc@1 67.866 Acc@5 88.912 loss 1.675
Accuracy of the model on the 50000 test images: 67.9%
Max accuracy: 69.30%
Epoch: [141]  [  0/312]  eta: 1:03:04  lr: 0.002424  min_lr: 0.002424  loss: 3.8645 (3.8645)  weight_decay: 0.0500 (0.0500)  time: 12.1306  data: 8.8109  max mem: 31830
Epoch: [141]  [ 10/312]  eta: 0:08:43  lr: 0.002423  min_lr: 0.002423  loss: 3.8645 (3.7839)  weight_decay: 0.0500 (0.0500)  time: 1.7331  data: 1.0039  max mem: 31830
Epoch: [141]  [ 20/312]  eta: 0:05:22  lr: 0.002422  min_lr: 0.002422  loss: 3.5588 (3.6475)  weight_decay: 0.0500 (0.0500)  time: 0.5532  data: 0.1187  max mem: 31830
Epoch: [141]  [ 30/312]  eta: 0:04:06  lr: 0.002421  min_lr: 0.002421  loss: 3.4676 (3.5414)  weight_decay: 0.0500 (0.0500)  time: 0.4039  data: 0.0075  max mem: 31830
Epoch: [141]  [ 40/312]  eta: 0:03:26  lr: 0.002421  min_lr: 0.002421  loss: 3.5240 (3.6075)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0011  max mem: 31830
Epoch: [141]  [ 50/312]  eta: 0:03:00  lr: 0.002420  min_lr: 0.002420  loss: 3.8446 (3.6543)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [141]  [ 60/312]  eta: 0:02:41  lr: 0.002419  min_lr: 0.002419  loss: 3.7843 (3.6532)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0009  max mem: 31830
Epoch: [141]  [ 70/312]  eta: 0:02:31  lr: 0.002419  min_lr: 0.002419  loss: 3.6679 (3.6331)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0247  max mem: 31830
Epoch: [141]  [ 80/312]  eta: 0:02:23  lr: 0.002418  min_lr: 0.002418  loss: 3.6239 (3.6427)  weight_decay: 0.0500 (0.0500)  time: 0.5484  data: 0.0578  max mem: 31830
Epoch: [141]  [ 90/312]  eta: 0:02:12  lr: 0.002417  min_lr: 0.002417  loss: 3.7975 (3.6445)  weight_decay: 0.0500 (0.0500)  time: 0.4913  data: 0.0448  max mem: 31830
Epoch: [141]  [100/312]  eta: 0:02:06  lr: 0.002417  min_lr: 0.002417  loss: 3.7754 (3.6265)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0572  max mem: 31830
Epoch: [141]  [110/312]  eta: 0:01:59  lr: 0.002416  min_lr: 0.002416  loss: 3.6407 (3.6263)  weight_decay: 0.0500 (0.0500)  time: 0.5645  data: 0.0464  max mem: 31830
Epoch: [141]  [120/312]  eta: 0:01:52  lr: 0.002415  min_lr: 0.002415  loss: 3.8318 (3.6480)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0136  max mem: 31830
Epoch: [141]  [130/312]  eta: 0:01:47  lr: 0.002414  min_lr: 0.002414  loss: 3.8318 (3.6604)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.0283  max mem: 31830
Epoch: [141]  [140/312]  eta: 0:01:39  lr: 0.002414  min_lr: 0.002414  loss: 3.7878 (3.6601)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0154  max mem: 31830
Epoch: [141]  [150/312]  eta: 0:01:33  lr: 0.002413  min_lr: 0.002413  loss: 3.7878 (3.6531)  weight_decay: 0.0500 (0.0500)  time: 0.5013  data: 0.0244  max mem: 31830
Epoch: [141]  [160/312]  eta: 0:01:27  lr: 0.002412  min_lr: 0.002412  loss: 3.7867 (3.6575)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.0250  max mem: 31830
Epoch: [141]  [170/312]  eta: 0:01:21  lr: 0.002412  min_lr: 0.002412  loss: 3.8907 (3.6703)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0151  max mem: 31830
Epoch: [141]  [180/312]  eta: 0:01:15  lr: 0.002411  min_lr: 0.002411  loss: 3.8407 (3.6708)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0269  max mem: 31830
Epoch: [141]  [190/312]  eta: 0:01:09  lr: 0.002410  min_lr: 0.002410  loss: 3.8958 (3.6726)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0130  max mem: 31830
Epoch: [141]  [200/312]  eta: 0:01:03  lr: 0.002409  min_lr: 0.002409  loss: 3.9193 (3.6833)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0249  max mem: 31830
Epoch: [141]  [210/312]  eta: 0:00:57  lr: 0.002409  min_lr: 0.002409  loss: 4.0846 (3.6951)  weight_decay: 0.0500 (0.0500)  time: 0.5825  data: 0.0360  max mem: 31830
Epoch: [141]  [220/312]  eta: 0:00:52  lr: 0.002408  min_lr: 0.002408  loss: 3.7208 (3.6835)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0120  max mem: 31830
Epoch: [141]  [230/312]  eta: 0:00:46  lr: 0.002407  min_lr: 0.002407  loss: 3.6231 (3.6797)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0124  max mem: 31830
Epoch: [141]  [240/312]  eta: 0:00:40  lr: 0.002407  min_lr: 0.002407  loss: 3.7201 (3.6791)  weight_decay: 0.0500 (0.0500)  time: 0.5430  data: 0.0124  max mem: 31830
Epoch: [141]  [250/312]  eta: 0:00:34  lr: 0.002406  min_lr: 0.002406  loss: 3.8219 (3.6864)  weight_decay: 0.0500 (0.0500)  time: 0.5544  data: 0.0245  max mem: 31830
Epoch: [141]  [260/312]  eta: 0:00:29  lr: 0.002405  min_lr: 0.002405  loss: 3.8219 (3.6888)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0491  max mem: 31830
Epoch: [141]  [270/312]  eta: 0:00:23  lr: 0.002405  min_lr: 0.002405  loss: 3.7907 (3.6855)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0263  max mem: 31830
Epoch: [141]  [280/312]  eta: 0:00:17  lr: 0.002404  min_lr: 0.002404  loss: 3.6522 (3.6894)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.0212  max mem: 31830
Epoch: [141]  [290/312]  eta: 0:00:12  lr: 0.002403  min_lr: 0.002403  loss: 3.6116 (3.6797)  weight_decay: 0.0500 (0.0500)  time: 0.5764  data: 0.0315  max mem: 31830
Epoch: [141]  [300/312]  eta: 0:00:06  lr: 0.002402  min_lr: 0.002402  loss: 3.4358 (3.6722)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0116  max mem: 31830
Epoch: [141]  [310/312]  eta: 0:00:01  lr: 0.002402  min_lr: 0.002402  loss: 3.6902 (3.6763)  weight_decay: 0.0500 (0.0500)  time: 0.4234  data: 0.0002  max mem: 31830
Epoch: [141]  [311/312]  eta: 0:00:00  lr: 0.002402  min_lr: 0.002402  loss: 3.8419 (3.6768)  weight_decay: 0.0500 (0.0500)  time: 0.4224  data: 0.0002  max mem: 31830
Epoch: [141] Total time: 0:02:52 (0.5539 s / it)
Averaged stats: lr: 0.002402  min_lr: 0.002402  loss: 3.8419 (3.6424)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3987 (1.3987)  acc1: 75.7812 (75.7812)  acc5: 91.0156 (91.0156)  time: 8.4757  data: 8.3081  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7638 (1.6119)  acc1: 65.1042 (68.5440)  acc5: 88.1510 (88.9280)  time: 1.0602  data: 0.9251  max mem: 31830
Test: Total time: 0:00:09 (1.0776 s / it)
* Acc@1 67.994 Acc@5 88.736 loss 1.623
Accuracy of the model on the 50000 test images: 68.0%
Max accuracy: 69.30%
Epoch: [142]  [  0/312]  eta: 1:06:15  lr: 0.002402  min_lr: 0.002402  loss: 2.5730 (2.5730)  weight_decay: 0.0500 (0.0500)  time: 12.7411  data: 11.0912  max mem: 31830
Epoch: [142]  [ 10/312]  eta: 0:08:46  lr: 0.002401  min_lr: 0.002401  loss: 3.7346 (3.5584)  weight_decay: 0.0500 (0.0500)  time: 1.7438  data: 1.0098  max mem: 31830
Epoch: [142]  [ 20/312]  eta: 0:05:35  lr: 0.002400  min_lr: 0.002400  loss: 3.5497 (3.5047)  weight_decay: 0.0500 (0.0500)  time: 0.5698  data: 0.0013  max mem: 31830
Epoch: [142]  [ 30/312]  eta: 0:04:15  lr: 0.002399  min_lr: 0.002399  loss: 3.4717 (3.5706)  weight_decay: 0.0500 (0.0500)  time: 0.4475  data: 0.0008  max mem: 31830
Epoch: [142]  [ 40/312]  eta: 0:03:32  lr: 0.002399  min_lr: 0.002399  loss: 3.7523 (3.5720)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0008  max mem: 31830
Epoch: [142]  [ 50/312]  eta: 0:03:05  lr: 0.002398  min_lr: 0.002398  loss: 3.9154 (3.6515)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0007  max mem: 31830
Epoch: [142]  [ 60/312]  eta: 0:02:45  lr: 0.002397  min_lr: 0.002397  loss: 3.9317 (3.6687)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0007  max mem: 31830
Epoch: [142]  [ 70/312]  eta: 0:02:32  lr: 0.002397  min_lr: 0.002397  loss: 3.7548 (3.6498)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0010  max mem: 31830
Epoch: [142]  [ 80/312]  eta: 0:02:23  lr: 0.002396  min_lr: 0.002396  loss: 3.7875 (3.6722)  weight_decay: 0.0500 (0.0500)  time: 0.4992  data: 0.0188  max mem: 31830
Epoch: [142]  [ 90/312]  eta: 0:02:14  lr: 0.002395  min_lr: 0.002395  loss: 3.7993 (3.6681)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0364  max mem: 31830
Epoch: [142]  [100/312]  eta: 0:02:08  lr: 0.002395  min_lr: 0.002395  loss: 3.7057 (3.6558)  weight_decay: 0.0500 (0.0500)  time: 0.5602  data: 0.0186  max mem: 31830
Epoch: [142]  [110/312]  eta: 0:01:59  lr: 0.002394  min_lr: 0.002394  loss: 3.5184 (3.6238)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0179  max mem: 31830
Epoch: [142]  [120/312]  eta: 0:01:52  lr: 0.002393  min_lr: 0.002393  loss: 3.3842 (3.6096)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0178  max mem: 31830
Epoch: [142]  [130/312]  eta: 0:01:46  lr: 0.002392  min_lr: 0.002392  loss: 3.6753 (3.6141)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0057  max mem: 31830
Epoch: [142]  [140/312]  eta: 0:01:40  lr: 0.002392  min_lr: 0.002392  loss: 3.6753 (3.6103)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0234  max mem: 31830
Epoch: [142]  [150/312]  eta: 0:01:33  lr: 0.002391  min_lr: 0.002391  loss: 3.4977 (3.5945)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0187  max mem: 31830
Epoch: [142]  [160/312]  eta: 0:01:27  lr: 0.002390  min_lr: 0.002390  loss: 3.6293 (3.6042)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0192  max mem: 31830
Epoch: [142]  [170/312]  eta: 0:01:21  lr: 0.002390  min_lr: 0.002390  loss: 3.6611 (3.5994)  weight_decay: 0.0500 (0.0500)  time: 0.5336  data: 0.0317  max mem: 31830
Epoch: [142]  [180/312]  eta: 0:01:15  lr: 0.002389  min_lr: 0.002389  loss: 3.6460 (3.5951)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0136  max mem: 31830
Epoch: [142]  [190/312]  eta: 0:01:09  lr: 0.002388  min_lr: 0.002388  loss: 3.7640 (3.6058)  weight_decay: 0.0500 (0.0500)  time: 0.5283  data: 0.0246  max mem: 31830
Epoch: [142]  [200/312]  eta: 0:01:03  lr: 0.002387  min_lr: 0.002387  loss: 3.7614 (3.6004)  weight_decay: 0.0500 (0.0500)  time: 0.5450  data: 0.0314  max mem: 31830
Epoch: [142]  [210/312]  eta: 0:00:57  lr: 0.002387  min_lr: 0.002387  loss: 3.5789 (3.5948)  weight_decay: 0.0500 (0.0500)  time: 0.5568  data: 0.0325  max mem: 31830
Epoch: [142]  [220/312]  eta: 0:00:52  lr: 0.002386  min_lr: 0.002386  loss: 3.5181 (3.5880)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0568  max mem: 31830
Epoch: [142]  [230/312]  eta: 0:00:46  lr: 0.002385  min_lr: 0.002385  loss: 3.4422 (3.5789)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0319  max mem: 31830
Epoch: [142]  [240/312]  eta: 0:00:40  lr: 0.002385  min_lr: 0.002385  loss: 3.8515 (3.5910)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0137  max mem: 31830
Epoch: [142]  [250/312]  eta: 0:00:34  lr: 0.002384  min_lr: 0.002384  loss: 3.8289 (3.5882)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0320  max mem: 31830
Epoch: [142]  [260/312]  eta: 0:00:29  lr: 0.002383  min_lr: 0.002383  loss: 3.6316 (3.5850)  weight_decay: 0.0500 (0.0500)  time: 0.5304  data: 0.0194  max mem: 31830
Epoch: [142]  [270/312]  eta: 0:00:23  lr: 0.002383  min_lr: 0.002383  loss: 3.6480 (3.5863)  weight_decay: 0.0500 (0.0500)  time: 0.5998  data: 0.0299  max mem: 31830
Epoch: [142]  [280/312]  eta: 0:00:17  lr: 0.002382  min_lr: 0.002382  loss: 3.8704 (3.5898)  weight_decay: 0.0500 (0.0500)  time: 0.5516  data: 0.0307  max mem: 31830
Epoch: [142]  [290/312]  eta: 0:00:12  lr: 0.002381  min_lr: 0.002381  loss: 3.6304 (3.5928)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0204  max mem: 31830
Epoch: [142]  [300/312]  eta: 0:00:06  lr: 0.002380  min_lr: 0.002380  loss: 3.6304 (3.5940)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0295  max mem: 31830
Epoch: [142]  [310/312]  eta: 0:00:01  lr: 0.002380  min_lr: 0.002380  loss: 3.7948 (3.5985)  weight_decay: 0.0500 (0.0500)  time: 0.4031  data: 0.0106  max mem: 31830
Epoch: [142]  [311/312]  eta: 0:00:00  lr: 0.002380  min_lr: 0.002380  loss: 3.7948 (3.5970)  weight_decay: 0.0500 (0.0500)  time: 0.4023  data: 0.0106  max mem: 31830
Epoch: [142] Total time: 0:02:53 (0.5547 s / it)
Averaged stats: lr: 0.002380  min_lr: 0.002380  loss: 3.7948 (3.6122)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3578 (1.3578)  acc1: 74.3490 (74.3490)  acc5: 92.5781 (92.5781)  time: 8.4494  data: 8.2877  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7345 (1.6477)  acc1: 65.1042 (67.4720)  acc5: 86.7188 (88.2240)  time: 1.0565  data: 0.9210  max mem: 31830
Test: Total time: 0:00:09 (1.0662 s / it)
* Acc@1 67.632 Acc@5 88.218 loss 1.643
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 69.30%
Epoch: [143]  [  0/312]  eta: 1:03:10  lr: 0.002380  min_lr: 0.002380  loss: 3.1704 (3.1704)  weight_decay: 0.0500 (0.0500)  time: 12.1504  data: 9.6469  max mem: 31830
Epoch: [143]  [ 10/312]  eta: 0:08:57  lr: 0.002379  min_lr: 0.002379  loss: 3.9896 (3.6659)  weight_decay: 0.0500 (0.0500)  time: 1.7795  data: 1.0078  max mem: 31830
Epoch: [143]  [ 20/312]  eta: 0:05:26  lr: 0.002378  min_lr: 0.002378  loss: 3.7867 (3.5833)  weight_decay: 0.0500 (0.0500)  time: 0.5656  data: 0.0723  max mem: 31830
Epoch: [143]  [ 30/312]  eta: 0:04:09  lr: 0.002377  min_lr: 0.002377  loss: 3.7867 (3.6451)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0012  max mem: 31830
Epoch: [143]  [ 40/312]  eta: 0:03:28  lr: 0.002377  min_lr: 0.002377  loss: 3.8921 (3.6303)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0018  max mem: 31830
Epoch: [143]  [ 50/312]  eta: 0:03:02  lr: 0.002376  min_lr: 0.002376  loss: 3.7139 (3.6458)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0013  max mem: 31830
Epoch: [143]  [ 60/312]  eta: 0:02:42  lr: 0.002375  min_lr: 0.002375  loss: 3.6647 (3.6011)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0008  max mem: 31830
Epoch: [143]  [ 70/312]  eta: 0:02:30  lr: 0.002375  min_lr: 0.002375  loss: 3.4742 (3.6074)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0008  max mem: 31830
Epoch: [143]  [ 80/312]  eta: 0:02:23  lr: 0.002374  min_lr: 0.002374  loss: 3.5113 (3.5791)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0122  max mem: 31830
Epoch: [143]  [ 90/312]  eta: 0:02:15  lr: 0.002373  min_lr: 0.002373  loss: 3.5628 (3.5982)  weight_decay: 0.0500 (0.0500)  time: 0.5591  data: 0.0122  max mem: 31830
Epoch: [143]  [100/312]  eta: 0:02:07  lr: 0.002373  min_lr: 0.002373  loss: 3.8630 (3.6246)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0008  max mem: 31830
Epoch: [143]  [110/312]  eta: 0:01:59  lr: 0.002372  min_lr: 0.002372  loss: 3.9096 (3.6399)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0115  max mem: 31830
Epoch: [143]  [120/312]  eta: 0:01:53  lr: 0.002371  min_lr: 0.002371  loss: 3.8676 (3.6468)  weight_decay: 0.0500 (0.0500)  time: 0.5140  data: 0.0170  max mem: 31830
Epoch: [143]  [130/312]  eta: 0:01:46  lr: 0.002370  min_lr: 0.002370  loss: 3.7854 (3.6530)  weight_decay: 0.0500 (0.0500)  time: 0.5512  data: 0.0063  max mem: 31830
Epoch: [143]  [140/312]  eta: 0:01:40  lr: 0.002370  min_lr: 0.002370  loss: 3.7992 (3.6480)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0134  max mem: 31830
Epoch: [143]  [150/312]  eta: 0:01:34  lr: 0.002369  min_lr: 0.002369  loss: 3.6287 (3.6359)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0135  max mem: 31830
Epoch: [143]  [160/312]  eta: 0:01:27  lr: 0.002368  min_lr: 0.002368  loss: 3.6540 (3.6347)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.0137  max mem: 31830
Epoch: [143]  [170/312]  eta: 0:01:22  lr: 0.002368  min_lr: 0.002368  loss: 3.7638 (3.6361)  weight_decay: 0.0500 (0.0500)  time: 0.5666  data: 0.0362  max mem: 31830
Epoch: [143]  [180/312]  eta: 0:01:16  lr: 0.002367  min_lr: 0.002367  loss: 3.7702 (3.6355)  weight_decay: 0.0500 (0.0500)  time: 0.5936  data: 0.0237  max mem: 31830
Epoch: [143]  [190/312]  eta: 0:01:09  lr: 0.002366  min_lr: 0.002366  loss: 3.8178 (3.6405)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0125  max mem: 31830
Epoch: [143]  [200/312]  eta: 0:01:04  lr: 0.002365  min_lr: 0.002365  loss: 3.7695 (3.6297)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0225  max mem: 31830
Epoch: [143]  [210/312]  eta: 0:00:58  lr: 0.002365  min_lr: 0.002365  loss: 3.5986 (3.6243)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0109  max mem: 31830
Epoch: [143]  [220/312]  eta: 0:00:52  lr: 0.002364  min_lr: 0.002364  loss: 3.5991 (3.6226)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0010  max mem: 31830
Epoch: [143]  [230/312]  eta: 0:00:47  lr: 0.002363  min_lr: 0.002363  loss: 3.5925 (3.6171)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0018  max mem: 31830
Epoch: [143]  [240/312]  eta: 0:00:40  lr: 0.002363  min_lr: 0.002363  loss: 3.4698 (3.6122)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0016  max mem: 31830
Epoch: [143]  [250/312]  eta: 0:00:35  lr: 0.002362  min_lr: 0.002362  loss: 3.4393 (3.6014)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0008  max mem: 31830
Epoch: [143]  [260/312]  eta: 0:00:29  lr: 0.002361  min_lr: 0.002361  loss: 3.4393 (3.6012)  weight_decay: 0.0500 (0.0500)  time: 0.6284  data: 0.0009  max mem: 31830
Epoch: [143]  [270/312]  eta: 0:00:23  lr: 0.002360  min_lr: 0.002360  loss: 3.7804 (3.6059)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0009  max mem: 31830
Epoch: [143]  [280/312]  eta: 0:00:18  lr: 0.002360  min_lr: 0.002360  loss: 3.7804 (3.6048)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0031  max mem: 31830
Epoch: [143]  [290/312]  eta: 0:00:12  lr: 0.002359  min_lr: 0.002359  loss: 3.5891 (3.6014)  weight_decay: 0.0500 (0.0500)  time: 0.5507  data: 0.0027  max mem: 31830
Epoch: [143]  [300/312]  eta: 0:00:06  lr: 0.002358  min_lr: 0.002358  loss: 3.9033 (3.6026)  weight_decay: 0.0500 (0.0500)  time: 0.4730  data: 0.0002  max mem: 31830
Epoch: [143]  [310/312]  eta: 0:00:01  lr: 0.002358  min_lr: 0.002358  loss: 3.7431 (3.5991)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0002  max mem: 31830
Epoch: [143]  [311/312]  eta: 0:00:00  lr: 0.002358  min_lr: 0.002358  loss: 3.7431 (3.5990)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [143] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.002358  min_lr: 0.002358  loss: 3.7431 (3.5969)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.2304 (1.2304)  acc1: 76.0417 (76.0417)  acc5: 92.0573 (92.0573)  time: 8.2776  data: 8.1132  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5476 (1.4392)  acc1: 67.5781 (69.3760)  acc5: 89.4531 (89.1360)  time: 1.0681  data: 0.9259  max mem: 31830
Test: Total time: 0:00:09 (1.0787 s / it)
* Acc@1 69.032 Acc@5 89.444 loss 1.451
Accuracy of the model on the 50000 test images: 69.0%
Max accuracy: 69.30%
Epoch: [144]  [  0/312]  eta: 0:59:07  lr: 0.002358  min_lr: 0.002358  loss: 3.8299 (3.8299)  weight_decay: 0.0500 (0.0500)  time: 11.3717  data: 8.4190  max mem: 31830
Epoch: [144]  [ 10/312]  eta: 0:08:18  lr: 0.002357  min_lr: 0.002357  loss: 3.8641 (3.5629)  weight_decay: 0.0500 (0.0500)  time: 1.6508  data: 0.9543  max mem: 31830
Epoch: [144]  [ 20/312]  eta: 0:05:31  lr: 0.002356  min_lr: 0.002356  loss: 3.8641 (3.6797)  weight_decay: 0.0500 (0.0500)  time: 0.6249  data: 0.1044  max mem: 31830
Epoch: [144]  [ 30/312]  eta: 0:04:13  lr: 0.002355  min_lr: 0.002355  loss: 3.6871 (3.6805)  weight_decay: 0.0500 (0.0500)  time: 0.4836  data: 0.0009  max mem: 31830
Epoch: [144]  [ 40/312]  eta: 0:03:30  lr: 0.002355  min_lr: 0.002355  loss: 3.6871 (3.6467)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0008  max mem: 31830
Epoch: [144]  [ 50/312]  eta: 0:03:07  lr: 0.002354  min_lr: 0.002354  loss: 3.7017 (3.6389)  weight_decay: 0.0500 (0.0500)  time: 0.4369  data: 0.0007  max mem: 31830
Epoch: [144]  [ 60/312]  eta: 0:02:47  lr: 0.002353  min_lr: 0.002353  loss: 3.4795 (3.5946)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0008  max mem: 31830
Epoch: [144]  [ 70/312]  eta: 0:02:40  lr: 0.002353  min_lr: 0.002353  loss: 3.6225 (3.6257)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0486  max mem: 31830
Epoch: [144]  [ 80/312]  eta: 0:02:27  lr: 0.002352  min_lr: 0.002352  loss: 3.7818 (3.6434)  weight_decay: 0.0500 (0.0500)  time: 0.5435  data: 0.0485  max mem: 31830
Epoch: [144]  [ 90/312]  eta: 0:02:19  lr: 0.002351  min_lr: 0.002351  loss: 3.6683 (3.6380)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0122  max mem: 31830
Epoch: [144]  [100/312]  eta: 0:02:12  lr: 0.002350  min_lr: 0.002350  loss: 3.5714 (3.6354)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.0384  max mem: 31830
Epoch: [144]  [110/312]  eta: 0:02:02  lr: 0.002350  min_lr: 0.002350  loss: 3.7134 (3.6470)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0276  max mem: 31830
Epoch: [144]  [120/312]  eta: 0:01:56  lr: 0.002349  min_lr: 0.002349  loss: 3.7134 (3.6457)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0016  max mem: 31830
Epoch: [144]  [130/312]  eta: 0:01:50  lr: 0.002348  min_lr: 0.002348  loss: 3.5919 (3.6317)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.0204  max mem: 31830
Epoch: [144]  [140/312]  eta: 0:01:42  lr: 0.002348  min_lr: 0.002348  loss: 3.5354 (3.6317)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0204  max mem: 31830
Epoch: [144]  [150/312]  eta: 0:01:35  lr: 0.002347  min_lr: 0.002347  loss: 3.7922 (3.6462)  weight_decay: 0.0500 (0.0500)  time: 0.4854  data: 0.0010  max mem: 31830
Epoch: [144]  [160/312]  eta: 0:01:29  lr: 0.002346  min_lr: 0.002346  loss: 3.8107 (3.6581)  weight_decay: 0.0500 (0.0500)  time: 0.5115  data: 0.0016  max mem: 31830
Epoch: [144]  [170/312]  eta: 0:01:23  lr: 0.002345  min_lr: 0.002345  loss: 3.8568 (3.6672)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0138  max mem: 31830
Epoch: [144]  [180/312]  eta: 0:01:17  lr: 0.002345  min_lr: 0.002345  loss: 3.7762 (3.6643)  weight_decay: 0.0500 (0.0500)  time: 0.5993  data: 0.0518  max mem: 31830
Epoch: [144]  [190/312]  eta: 0:01:10  lr: 0.002344  min_lr: 0.002344  loss: 3.7473 (3.6629)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0393  max mem: 31830
Epoch: [144]  [200/312]  eta: 0:01:04  lr: 0.002343  min_lr: 0.002343  loss: 3.7706 (3.6556)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0127  max mem: 31830
Epoch: [144]  [210/312]  eta: 0:00:59  lr: 0.002343  min_lr: 0.002343  loss: 3.6992 (3.6545)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0432  max mem: 31830
Epoch: [144]  [220/312]  eta: 0:00:52  lr: 0.002342  min_lr: 0.002342  loss: 3.8468 (3.6635)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0313  max mem: 31830
Epoch: [144]  [230/312]  eta: 0:00:47  lr: 0.002341  min_lr: 0.002341  loss: 3.7913 (3.6505)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0260  max mem: 31830
Epoch: [144]  [240/312]  eta: 0:00:41  lr: 0.002341  min_lr: 0.002341  loss: 3.5739 (3.6511)  weight_decay: 0.0500 (0.0500)  time: 0.5506  data: 0.0381  max mem: 31830
Epoch: [144]  [250/312]  eta: 0:00:35  lr: 0.002340  min_lr: 0.002340  loss: 3.7667 (3.6556)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0376  max mem: 31830
Epoch: [144]  [260/312]  eta: 0:00:29  lr: 0.002339  min_lr: 0.002339  loss: 3.7326 (3.6553)  weight_decay: 0.0500 (0.0500)  time: 0.5940  data: 0.0596  max mem: 31830
Epoch: [144]  [270/312]  eta: 0:00:23  lr: 0.002338  min_lr: 0.002338  loss: 3.5327 (3.6468)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0350  max mem: 31830
Epoch: [144]  [280/312]  eta: 0:00:18  lr: 0.002338  min_lr: 0.002338  loss: 3.7693 (3.6483)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0299  max mem: 31830
Epoch: [144]  [290/312]  eta: 0:00:12  lr: 0.002337  min_lr: 0.002337  loss: 3.6483 (3.6453)  weight_decay: 0.0500 (0.0500)  time: 0.5976  data: 0.0377  max mem: 31830
Epoch: [144]  [300/312]  eta: 0:00:06  lr: 0.002336  min_lr: 0.002336  loss: 3.6118 (3.6445)  weight_decay: 0.0500 (0.0500)  time: 0.4570  data: 0.0083  max mem: 31830
Epoch: [144]  [310/312]  eta: 0:00:01  lr: 0.002336  min_lr: 0.002336  loss: 3.7161 (3.6451)  weight_decay: 0.0500 (0.0500)  time: 0.3820  data: 0.0001  max mem: 31830
Epoch: [144]  [311/312]  eta: 0:00:00  lr: 0.002335  min_lr: 0.002335  loss: 3.6582 (3.6450)  weight_decay: 0.0500 (0.0500)  time: 0.3819  data: 0.0001  max mem: 31830
Epoch: [144] Total time: 0:02:54 (0.5595 s / it)
Averaged stats: lr: 0.002335  min_lr: 0.002335  loss: 3.6582 (3.6051)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.3834 (1.3834)  acc1: 74.4792 (74.4792)  acc5: 92.1875 (92.1875)  time: 8.0991  data: 7.9326  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5733 (1.5135)  acc1: 67.4479 (68.6400)  acc5: 88.2812 (89.2480)  time: 1.0687  data: 0.9338  max mem: 31830
Test: Total time: 0:00:09 (1.0807 s / it)
* Acc@1 68.864 Acc@5 89.332 loss 1.515
Accuracy of the model on the 50000 test images: 68.9%
Max accuracy: 69.30%
Epoch: [145]  [  0/312]  eta: 1:05:11  lr: 0.002335  min_lr: 0.002335  loss: 2.4766 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 12.5379  data: 8.9833  max mem: 31830
Epoch: [145]  [ 10/312]  eta: 0:09:30  lr: 0.002335  min_lr: 0.002335  loss: 2.9547 (3.2200)  weight_decay: 0.0500 (0.0500)  time: 1.8879  data: 0.9295  max mem: 31830
Epoch: [145]  [ 20/312]  eta: 0:05:42  lr: 0.002334  min_lr: 0.002334  loss: 3.6398 (3.4614)  weight_decay: 0.0500 (0.0500)  time: 0.6058  data: 0.0623  max mem: 31830
Epoch: [145]  [ 30/312]  eta: 0:04:20  lr: 0.002333  min_lr: 0.002333  loss: 3.8448 (3.5591)  weight_decay: 0.0500 (0.0500)  time: 0.3941  data: 0.0007  max mem: 31830
Epoch: [145]  [ 40/312]  eta: 0:03:36  lr: 0.002333  min_lr: 0.002333  loss: 3.8608 (3.5814)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0007  max mem: 31830
Epoch: [145]  [ 50/312]  eta: 0:03:08  lr: 0.002332  min_lr: 0.002332  loss: 3.7452 (3.6066)  weight_decay: 0.0500 (0.0500)  time: 0.3977  data: 0.0007  max mem: 31830
Epoch: [145]  [ 60/312]  eta: 0:02:47  lr: 0.002331  min_lr: 0.002331  loss: 3.9029 (3.6476)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0008  max mem: 31830
Epoch: [145]  [ 70/312]  eta: 0:02:31  lr: 0.002330  min_lr: 0.002330  loss: 3.8955 (3.6790)  weight_decay: 0.0500 (0.0500)  time: 0.3923  data: 0.0008  max mem: 31830
Epoch: [145]  [ 80/312]  eta: 0:02:23  lr: 0.002330  min_lr: 0.002330  loss: 3.8086 (3.6665)  weight_decay: 0.0500 (0.0500)  time: 0.4831  data: 0.0189  max mem: 31830
Epoch: [145]  [ 90/312]  eta: 0:02:16  lr: 0.002329  min_lr: 0.002329  loss: 3.4228 (3.6224)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0191  max mem: 31830
Epoch: [145]  [100/312]  eta: 0:02:07  lr: 0.002328  min_lr: 0.002328  loss: 3.4922 (3.6152)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0305  max mem: 31830
Epoch: [145]  [110/312]  eta: 0:02:01  lr: 0.002328  min_lr: 0.002328  loss: 3.7738 (3.6146)  weight_decay: 0.0500 (0.0500)  time: 0.5527  data: 0.0689  max mem: 31830
Epoch: [145]  [120/312]  eta: 0:01:53  lr: 0.002327  min_lr: 0.002327  loss: 3.6680 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0400  max mem: 31830
Epoch: [145]  [130/312]  eta: 0:01:48  lr: 0.002326  min_lr: 0.002326  loss: 3.3236 (3.5932)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0640  max mem: 31830
Epoch: [145]  [140/312]  eta: 0:01:40  lr: 0.002326  min_lr: 0.002326  loss: 3.1707 (3.5594)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0634  max mem: 31830
Epoch: [145]  [150/312]  eta: 0:01:34  lr: 0.002325  min_lr: 0.002325  loss: 3.6609 (3.5901)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0760  max mem: 31830
Epoch: [145]  [160/312]  eta: 0:01:29  lr: 0.002324  min_lr: 0.002324  loss: 4.0047 (3.6048)  weight_decay: 0.0500 (0.0500)  time: 0.6121  data: 0.1372  max mem: 31830
Epoch: [145]  [170/312]  eta: 0:01:22  lr: 0.002323  min_lr: 0.002323  loss: 3.7461 (3.5987)  weight_decay: 0.0500 (0.0500)  time: 0.5777  data: 0.0621  max mem: 31830
Epoch: [145]  [180/312]  eta: 0:01:16  lr: 0.002323  min_lr: 0.002323  loss: 3.6227 (3.5996)  weight_decay: 0.0500 (0.0500)  time: 0.4817  data: 0.0487  max mem: 31830
Epoch: [145]  [190/312]  eta: 0:01:10  lr: 0.002322  min_lr: 0.002322  loss: 3.8116 (3.6062)  weight_decay: 0.0500 (0.0500)  time: 0.5638  data: 0.0997  max mem: 31830
Epoch: [145]  [200/312]  eta: 0:01:04  lr: 0.002321  min_lr: 0.002321  loss: 3.8362 (3.6027)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0530  max mem: 31830
Epoch: [145]  [210/312]  eta: 0:00:58  lr: 0.002321  min_lr: 0.002321  loss: 3.6691 (3.5984)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0384  max mem: 31830
Epoch: [145]  [220/312]  eta: 0:00:52  lr: 0.002320  min_lr: 0.002320  loss: 3.6840 (3.5977)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0372  max mem: 31830
Epoch: [145]  [230/312]  eta: 0:00:46  lr: 0.002319  min_lr: 0.002319  loss: 3.6232 (3.5945)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.0655  max mem: 31830
Epoch: [145]  [240/312]  eta: 0:00:41  lr: 0.002318  min_lr: 0.002318  loss: 3.5744 (3.5996)  weight_decay: 0.0500 (0.0500)  time: 0.5904  data: 0.1392  max mem: 31830
Epoch: [145]  [250/312]  eta: 0:00:35  lr: 0.002318  min_lr: 0.002318  loss: 3.9020 (3.6095)  weight_decay: 0.0500 (0.0500)  time: 0.5675  data: 0.0745  max mem: 31830
Epoch: [145]  [260/312]  eta: 0:00:29  lr: 0.002317  min_lr: 0.002317  loss: 3.8764 (3.6027)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0725  max mem: 31830
Epoch: [145]  [270/312]  eta: 0:00:24  lr: 0.002316  min_lr: 0.002316  loss: 3.6281 (3.6028)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.1676  max mem: 31830
Epoch: [145]  [280/312]  eta: 0:00:18  lr: 0.002316  min_lr: 0.002316  loss: 3.4895 (3.5979)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0973  max mem: 31830
Epoch: [145]  [290/312]  eta: 0:00:12  lr: 0.002315  min_lr: 0.002315  loss: 3.2255 (3.5903)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0890  max mem: 31830
Epoch: [145]  [300/312]  eta: 0:00:06  lr: 0.002314  min_lr: 0.002314  loss: 3.1572 (3.5787)  weight_decay: 0.0500 (0.0500)  time: 0.5157  data: 0.0872  max mem: 31830
Epoch: [145]  [310/312]  eta: 0:00:01  lr: 0.002313  min_lr: 0.002313  loss: 3.4052 (3.5816)  weight_decay: 0.0500 (0.0500)  time: 0.4084  data: 0.0107  max mem: 31830
Epoch: [145]  [311/312]  eta: 0:00:00  lr: 0.002313  min_lr: 0.002313  loss: 3.5019 (3.5823)  weight_decay: 0.0500 (0.0500)  time: 0.4078  data: 0.0107  max mem: 31830
Epoch: [145] Total time: 0:02:55 (0.5609 s / it)
Averaged stats: lr: 0.002313  min_lr: 0.002313  loss: 3.5019 (3.6153)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.2256 (1.2256)  acc1: 77.6042 (77.6042)  acc5: 92.5781 (92.5781)  time: 8.2615  data: 8.0946  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6045 (1.4697)  acc1: 67.8385 (69.7760)  acc5: 89.4531 (89.3440)  time: 1.0536  data: 0.9169  max mem: 31830
Test: Total time: 0:00:09 (1.0641 s / it)
* Acc@1 69.456 Acc@5 89.660 loss 1.469
Accuracy of the model on the 50000 test images: 69.5%
Max accuracy: 69.46%
Epoch: [146]  [  0/312]  eta: 0:55:10  lr: 0.002313  min_lr: 0.002313  loss: 4.3818 (4.3818)  weight_decay: 0.0500 (0.0500)  time: 10.6094  data: 9.9675  max mem: 31830
Epoch: [146]  [ 10/312]  eta: 0:08:43  lr: 0.002313  min_lr: 0.002313  loss: 3.8731 (3.7329)  weight_decay: 0.0500 (0.0500)  time: 1.7339  data: 1.0067  max mem: 31830
Epoch: [146]  [ 20/312]  eta: 0:05:21  lr: 0.002312  min_lr: 0.002312  loss: 3.4610 (3.5058)  weight_decay: 0.0500 (0.0500)  time: 0.6249  data: 0.0564  max mem: 31830
Epoch: [146]  [ 30/312]  eta: 0:04:06  lr: 0.002311  min_lr: 0.002311  loss: 3.4083 (3.5318)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0014  max mem: 31830
Epoch: [146]  [ 40/312]  eta: 0:03:26  lr: 0.002310  min_lr: 0.002310  loss: 3.7585 (3.5804)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0008  max mem: 31830
Epoch: [146]  [ 50/312]  eta: 0:03:00  lr: 0.002310  min_lr: 0.002310  loss: 3.7339 (3.5483)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0007  max mem: 31830
Epoch: [146]  [ 60/312]  eta: 0:02:41  lr: 0.002309  min_lr: 0.002309  loss: 3.6995 (3.5774)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0008  max mem: 31830
Epoch: [146]  [ 70/312]  eta: 0:02:27  lr: 0.002308  min_lr: 0.002308  loss: 3.5802 (3.5541)  weight_decay: 0.0500 (0.0500)  time: 0.4114  data: 0.0129  max mem: 31830
Epoch: [146]  [ 80/312]  eta: 0:02:20  lr: 0.002308  min_lr: 0.002308  loss: 3.4371 (3.5421)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0829  max mem: 31830
Epoch: [146]  [ 90/312]  eta: 0:02:11  lr: 0.002307  min_lr: 0.002307  loss: 3.5248 (3.5353)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0872  max mem: 31830
Epoch: [146]  [100/312]  eta: 0:02:05  lr: 0.002306  min_lr: 0.002306  loss: 3.3927 (3.5067)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0382  max mem: 31830
Epoch: [146]  [110/312]  eta: 0:01:58  lr: 0.002305  min_lr: 0.002305  loss: 3.3927 (3.5254)  weight_decay: 0.0500 (0.0500)  time: 0.5540  data: 0.0468  max mem: 31830
Epoch: [146]  [120/312]  eta: 0:01:52  lr: 0.002305  min_lr: 0.002305  loss: 3.8433 (3.5522)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0500  max mem: 31830
Epoch: [146]  [130/312]  eta: 0:01:45  lr: 0.002304  min_lr: 0.002304  loss: 3.7760 (3.5627)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0476  max mem: 31830
Epoch: [146]  [140/312]  eta: 0:01:39  lr: 0.002303  min_lr: 0.002303  loss: 3.6961 (3.5666)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0234  max mem: 31830
Epoch: [146]  [150/312]  eta: 0:01:33  lr: 0.002303  min_lr: 0.002303  loss: 3.8506 (3.5895)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0254  max mem: 31830
Epoch: [146]  [160/312]  eta: 0:01:27  lr: 0.002302  min_lr: 0.002302  loss: 3.5925 (3.5689)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.0499  max mem: 31830
Epoch: [146]  [170/312]  eta: 0:01:21  lr: 0.002301  min_lr: 0.002301  loss: 3.5755 (3.5871)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0255  max mem: 31830
Epoch: [146]  [180/312]  eta: 0:01:14  lr: 0.002301  min_lr: 0.002301  loss: 3.8661 (3.5846)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0136  max mem: 31830
Epoch: [146]  [190/312]  eta: 0:01:09  lr: 0.002300  min_lr: 0.002300  loss: 3.7027 (3.5842)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0135  max mem: 31830
Epoch: [146]  [200/312]  eta: 0:01:03  lr: 0.002299  min_lr: 0.002299  loss: 3.5117 (3.5775)  weight_decay: 0.0500 (0.0500)  time: 0.5570  data: 0.0135  max mem: 31830
Epoch: [146]  [210/312]  eta: 0:00:57  lr: 0.002298  min_lr: 0.002298  loss: 3.5910 (3.5796)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0257  max mem: 31830
Epoch: [146]  [220/312]  eta: 0:00:51  lr: 0.002298  min_lr: 0.002298  loss: 3.7898 (3.5841)  weight_decay: 0.0500 (0.0500)  time: 0.5304  data: 0.0131  max mem: 31830
Epoch: [146]  [230/312]  eta: 0:00:46  lr: 0.002297  min_lr: 0.002297  loss: 3.7898 (3.5885)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0128  max mem: 31830
Epoch: [146]  [240/312]  eta: 0:00:40  lr: 0.002296  min_lr: 0.002296  loss: 3.6296 (3.5825)  weight_decay: 0.0500 (0.0500)  time: 0.6109  data: 0.0414  max mem: 31830
Epoch: [146]  [250/312]  eta: 0:00:34  lr: 0.002296  min_lr: 0.002296  loss: 3.5671 (3.5763)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0301  max mem: 31830
Epoch: [146]  [260/312]  eta: 0:00:29  lr: 0.002295  min_lr: 0.002295  loss: 3.3169 (3.5693)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0242  max mem: 31830
Epoch: [146]  [270/312]  eta: 0:00:23  lr: 0.002294  min_lr: 0.002294  loss: 3.6507 (3.5715)  weight_decay: 0.0500 (0.0500)  time: 0.5482  data: 0.0236  max mem: 31830
Epoch: [146]  [280/312]  eta: 0:00:17  lr: 0.002293  min_lr: 0.002293  loss: 3.8828 (3.5762)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0202  max mem: 31830
Epoch: [146]  [290/312]  eta: 0:00:12  lr: 0.002293  min_lr: 0.002293  loss: 3.8828 (3.5723)  weight_decay: 0.0500 (0.0500)  time: 0.6510  data: 0.0306  max mem: 31830
Epoch: [146]  [300/312]  eta: 0:00:06  lr: 0.002292  min_lr: 0.002292  loss: 3.6718 (3.5752)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0108  max mem: 31830
Epoch: [146]  [310/312]  eta: 0:00:01  lr: 0.002291  min_lr: 0.002291  loss: 3.6718 (3.5675)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [146]  [311/312]  eta: 0:00:00  lr: 0.002291  min_lr: 0.002291  loss: 3.6718 (3.5638)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [146] Total time: 0:02:53 (0.5569 s / it)
Averaged stats: lr: 0.002291  min_lr: 0.002291  loss: 3.6718 (3.5986)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.1275 (1.1275)  acc1: 76.9531 (76.9531)  acc5: 93.2292 (93.2292)  time: 8.8604  data: 8.6931  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5216 (1.3875)  acc1: 69.4010 (69.8080)  acc5: 90.1042 (89.8720)  time: 1.1007  data: 0.9660  max mem: 31830
Test: Total time: 0:00:10 (1.1453 s / it)
* Acc@1 69.746 Acc@5 89.846 loss 1.391
Accuracy of the model on the 50000 test images: 69.7%
Max accuracy: 69.75%
Epoch: [147]  [  0/312]  eta: 1:04:03  lr: 0.002291  min_lr: 0.002291  loss: 2.8592 (2.8592)  weight_decay: 0.0500 (0.0500)  time: 12.3176  data: 10.7761  max mem: 31830
Epoch: [147]  [ 10/312]  eta: 0:09:00  lr: 0.002290  min_lr: 0.002290  loss: 3.2138 (3.2549)  weight_decay: 0.0500 (0.0500)  time: 1.7882  data: 1.0317  max mem: 31830
Epoch: [147]  [ 20/312]  eta: 0:05:37  lr: 0.002290  min_lr: 0.002290  loss: 3.5849 (3.4472)  weight_decay: 0.0500 (0.0500)  time: 0.5974  data: 0.0290  max mem: 31830
Epoch: [147]  [ 30/312]  eta: 0:04:16  lr: 0.002289  min_lr: 0.002289  loss: 3.7607 (3.4676)  weight_decay: 0.0500 (0.0500)  time: 0.4288  data: 0.0016  max mem: 31830
Epoch: [147]  [ 40/312]  eta: 0:03:33  lr: 0.002288  min_lr: 0.002288  loss: 3.7412 (3.4696)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0023  max mem: 31830
Epoch: [147]  [ 50/312]  eta: 0:03:06  lr: 0.002288  min_lr: 0.002288  loss: 3.5086 (3.4740)  weight_decay: 0.0500 (0.0500)  time: 0.4007  data: 0.0021  max mem: 31830
Epoch: [147]  [ 60/312]  eta: 0:02:46  lr: 0.002287  min_lr: 0.002287  loss: 3.6571 (3.5130)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0014  max mem: 31830
Epoch: [147]  [ 70/312]  eta: 0:02:30  lr: 0.002286  min_lr: 0.002286  loss: 3.8546 (3.5416)  weight_decay: 0.0500 (0.0500)  time: 0.4011  data: 0.0009  max mem: 31830
Epoch: [147]  [ 80/312]  eta: 0:02:22  lr: 0.002285  min_lr: 0.002285  loss: 3.8598 (3.5669)  weight_decay: 0.0500 (0.0500)  time: 0.4834  data: 0.0119  max mem: 31830
Epoch: [147]  [ 90/312]  eta: 0:02:13  lr: 0.002285  min_lr: 0.002285  loss: 3.8120 (3.5726)  weight_decay: 0.0500 (0.0500)  time: 0.5281  data: 0.0242  max mem: 31830
Epoch: [147]  [100/312]  eta: 0:02:06  lr: 0.002284  min_lr: 0.002284  loss: 3.6830 (3.5749)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0436  max mem: 31830
Epoch: [147]  [110/312]  eta: 0:02:00  lr: 0.002283  min_lr: 0.002283  loss: 3.6830 (3.5879)  weight_decay: 0.0500 (0.0500)  time: 0.5615  data: 0.0377  max mem: 31830
Epoch: [147]  [120/312]  eta: 0:01:53  lr: 0.002283  min_lr: 0.002283  loss: 3.7363 (3.5748)  weight_decay: 0.0500 (0.0500)  time: 0.5559  data: 0.0316  max mem: 31830
Epoch: [147]  [130/312]  eta: 0:01:47  lr: 0.002282  min_lr: 0.002282  loss: 3.7313 (3.5815)  weight_decay: 0.0500 (0.0500)  time: 0.5594  data: 0.0250  max mem: 31830
Epoch: [147]  [140/312]  eta: 0:01:40  lr: 0.002281  min_lr: 0.002281  loss: 3.7313 (3.5863)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0124  max mem: 31830
Epoch: [147]  [150/312]  eta: 0:01:34  lr: 0.002280  min_lr: 0.002280  loss: 3.8040 (3.5852)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0251  max mem: 31830
Epoch: [147]  [160/312]  eta: 0:01:28  lr: 0.002280  min_lr: 0.002280  loss: 3.8020 (3.5911)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0136  max mem: 31830
Epoch: [147]  [170/312]  eta: 0:01:22  lr: 0.002279  min_lr: 0.002279  loss: 3.7082 (3.6043)  weight_decay: 0.0500 (0.0500)  time: 0.5457  data: 0.0145  max mem: 31830
Epoch: [147]  [180/312]  eta: 0:01:15  lr: 0.002278  min_lr: 0.002278  loss: 3.5472 (3.5866)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0145  max mem: 31830
Epoch: [147]  [190/312]  eta: 0:01:10  lr: 0.002278  min_lr: 0.002278  loss: 3.5472 (3.5943)  weight_decay: 0.0500 (0.0500)  time: 0.5539  data: 0.0016  max mem: 31830
Epoch: [147]  [200/312]  eta: 0:01:03  lr: 0.002277  min_lr: 0.002277  loss: 3.7381 (3.5923)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0116  max mem: 31830
Epoch: [147]  [210/312]  eta: 0:00:58  lr: 0.002276  min_lr: 0.002276  loss: 3.5758 (3.5877)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.0110  max mem: 31830
Epoch: [147]  [220/312]  eta: 0:00:52  lr: 0.002275  min_lr: 0.002275  loss: 3.5758 (3.5906)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0218  max mem: 31830
Epoch: [147]  [230/312]  eta: 0:00:46  lr: 0.002275  min_lr: 0.002275  loss: 3.8344 (3.5899)  weight_decay: 0.0500 (0.0500)  time: 0.5583  data: 0.0217  max mem: 31830
Epoch: [147]  [240/312]  eta: 0:00:41  lr: 0.002274  min_lr: 0.002274  loss: 3.7529 (3.5869)  weight_decay: 0.0500 (0.0500)  time: 0.6050  data: 0.0009  max mem: 31830
Epoch: [147]  [250/312]  eta: 0:00:35  lr: 0.002273  min_lr: 0.002273  loss: 3.8400 (3.5926)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0044  max mem: 31830
Epoch: [147]  [260/312]  eta: 0:00:29  lr: 0.002273  min_lr: 0.002273  loss: 3.8532 (3.5940)  weight_decay: 0.0500 (0.0500)  time: 0.5038  data: 0.0043  max mem: 31830
Epoch: [147]  [270/312]  eta: 0:00:23  lr: 0.002272  min_lr: 0.002272  loss: 3.7603 (3.5927)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0009  max mem: 31830
Epoch: [147]  [280/312]  eta: 0:00:18  lr: 0.002271  min_lr: 0.002271  loss: 3.8165 (3.6032)  weight_decay: 0.0500 (0.0500)  time: 0.5552  data: 0.0027  max mem: 31830
Epoch: [147]  [290/312]  eta: 0:00:12  lr: 0.002270  min_lr: 0.002270  loss: 3.9029 (3.6061)  weight_decay: 0.0500 (0.0500)  time: 0.5140  data: 0.0027  max mem: 31830
Epoch: [147]  [300/312]  eta: 0:00:06  lr: 0.002270  min_lr: 0.002270  loss: 3.5353 (3.6052)  weight_decay: 0.0500 (0.0500)  time: 0.4916  data: 0.0122  max mem: 31830
Epoch: [147]  [310/312]  eta: 0:00:01  lr: 0.002269  min_lr: 0.002269  loss: 3.9137 (3.6137)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0119  max mem: 31830
Epoch: [147]  [311/312]  eta: 0:00:00  lr: 0.002269  min_lr: 0.002269  loss: 3.9137 (3.6115)  weight_decay: 0.0500 (0.0500)  time: 0.4293  data: 0.0001  max mem: 31830
Epoch: [147] Total time: 0:02:54 (0.5580 s / it)
Averaged stats: lr: 0.002269  min_lr: 0.002269  loss: 3.9137 (3.6019)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.5020 (1.5020)  acc1: 73.1771 (73.1771)  acc5: 91.5365 (91.5365)  time: 8.9125  data: 8.7452  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7731 (1.6815)  acc1: 67.3177 (68.0320)  acc5: 88.4115 (88.7520)  time: 1.1081  data: 0.9718  max mem: 31830
Test: Total time: 0:00:10 (1.1220 s / it)
* Acc@1 68.134 Acc@5 88.960 loss 1.677
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 69.75%
Epoch: [148]  [  0/312]  eta: 1:04:44  lr: 0.002269  min_lr: 0.002269  loss: 3.7384 (3.7384)  weight_decay: 0.0500 (0.0500)  time: 12.4494  data: 11.4678  max mem: 31830
Epoch: [148]  [ 10/312]  eta: 0:08:08  lr: 0.002268  min_lr: 0.002268  loss: 3.7384 (3.6118)  weight_decay: 0.0500 (0.0500)  time: 1.6191  data: 1.0430  max mem: 31830
Epoch: [148]  [ 20/312]  eta: 0:05:27  lr: 0.002267  min_lr: 0.002267  loss: 3.7999 (3.7936)  weight_decay: 0.0500 (0.0500)  time: 0.5563  data: 0.0464  max mem: 31830
Epoch: [148]  [ 30/312]  eta: 0:04:10  lr: 0.002267  min_lr: 0.002267  loss: 3.7473 (3.6861)  weight_decay: 0.0500 (0.0500)  time: 0.4870  data: 0.0465  max mem: 31830
Epoch: [148]  [ 40/312]  eta: 0:03:29  lr: 0.002266  min_lr: 0.002266  loss: 3.5618 (3.6690)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0007  max mem: 31830
Epoch: [148]  [ 50/312]  eta: 0:03:04  lr: 0.002265  min_lr: 0.002265  loss: 3.8193 (3.6743)  weight_decay: 0.0500 (0.0500)  time: 0.4176  data: 0.0215  max mem: 31830
Epoch: [148]  [ 60/312]  eta: 0:02:44  lr: 0.002265  min_lr: 0.002265  loss: 3.7640 (3.6507)  weight_decay: 0.0500 (0.0500)  time: 0.4162  data: 0.0215  max mem: 31830
Epoch: [148]  [ 70/312]  eta: 0:02:38  lr: 0.002264  min_lr: 0.002264  loss: 3.5942 (3.6208)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0707  max mem: 31830
Epoch: [148]  [ 80/312]  eta: 0:02:27  lr: 0.002263  min_lr: 0.002263  loss: 3.5813 (3.6379)  weight_decay: 0.0500 (0.0500)  time: 0.5889  data: 0.0945  max mem: 31830
Epoch: [148]  [ 90/312]  eta: 0:02:16  lr: 0.002262  min_lr: 0.002262  loss: 3.6840 (3.6416)  weight_decay: 0.0500 (0.0500)  time: 0.4889  data: 0.0492  max mem: 31830
Epoch: [148]  [100/312]  eta: 0:02:11  lr: 0.002262  min_lr: 0.002262  loss: 3.6840 (3.6299)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0969  max mem: 31830
Epoch: [148]  [110/312]  eta: 0:02:00  lr: 0.002261  min_lr: 0.002261  loss: 3.7455 (3.6415)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0722  max mem: 31830
Epoch: [148]  [120/312]  eta: 0:01:55  lr: 0.002260  min_lr: 0.002260  loss: 3.8185 (3.6489)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0708  max mem: 31830
Epoch: [148]  [130/312]  eta: 0:01:50  lr: 0.002260  min_lr: 0.002260  loss: 3.4527 (3.6251)  weight_decay: 0.0500 (0.0500)  time: 0.6623  data: 0.1171  max mem: 31830
Epoch: [148]  [140/312]  eta: 0:01:42  lr: 0.002259  min_lr: 0.002259  loss: 3.6951 (3.6415)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0470  max mem: 31830
Epoch: [148]  [150/312]  eta: 0:01:36  lr: 0.002258  min_lr: 0.002258  loss: 3.8460 (3.6423)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0262  max mem: 31830
Epoch: [148]  [160/312]  eta: 0:01:29  lr: 0.002257  min_lr: 0.002257  loss: 3.8983 (3.6517)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0263  max mem: 31830
Epoch: [148]  [170/312]  eta: 0:01:22  lr: 0.002257  min_lr: 0.002257  loss: 3.8307 (3.6496)  weight_decay: 0.0500 (0.0500)  time: 0.4668  data: 0.0120  max mem: 31830
Epoch: [148]  [180/312]  eta: 0:01:17  lr: 0.002256  min_lr: 0.002256  loss: 3.6462 (3.6404)  weight_decay: 0.0500 (0.0500)  time: 0.5405  data: 0.0625  max mem: 31830
Epoch: [148]  [190/312]  eta: 0:01:10  lr: 0.002255  min_lr: 0.002255  loss: 3.7450 (3.6513)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0519  max mem: 31830
Epoch: [148]  [200/312]  eta: 0:01:04  lr: 0.002255  min_lr: 0.002255  loss: 3.7431 (3.6505)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.0505  max mem: 31830
Epoch: [148]  [210/312]  eta: 0:00:58  lr: 0.002254  min_lr: 0.002254  loss: 3.6329 (3.6450)  weight_decay: 0.0500 (0.0500)  time: 0.6019  data: 0.0934  max mem: 31830
Epoch: [148]  [220/312]  eta: 0:00:52  lr: 0.002253  min_lr: 0.002253  loss: 3.4382 (3.6473)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0442  max mem: 31830
Epoch: [148]  [230/312]  eta: 0:00:47  lr: 0.002253  min_lr: 0.002253  loss: 3.9006 (3.6522)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0120  max mem: 31830
Epoch: [148]  [240/312]  eta: 0:00:40  lr: 0.002252  min_lr: 0.002252  loss: 3.8528 (3.6557)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0128  max mem: 31830
Epoch: [148]  [250/312]  eta: 0:00:35  lr: 0.002251  min_lr: 0.002251  loss: 3.7701 (3.6486)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0016  max mem: 31830
Epoch: [148]  [260/312]  eta: 0:00:29  lr: 0.002250  min_lr: 0.002250  loss: 3.3650 (3.6370)  weight_decay: 0.0500 (0.0500)  time: 0.6210  data: 0.0016  max mem: 31830
Epoch: [148]  [270/312]  eta: 0:00:23  lr: 0.002250  min_lr: 0.002250  loss: 3.2778 (3.6324)  weight_decay: 0.0500 (0.0500)  time: 0.4962  data: 0.0015  max mem: 31830
Epoch: [148]  [280/312]  eta: 0:00:18  lr: 0.002249  min_lr: 0.002249  loss: 3.7384 (3.6388)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0045  max mem: 31830
Epoch: [148]  [290/312]  eta: 0:00:12  lr: 0.002248  min_lr: 0.002248  loss: 3.8626 (3.6409)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0043  max mem: 31830
Epoch: [148]  [300/312]  eta: 0:00:06  lr: 0.002248  min_lr: 0.002248  loss: 3.5506 (3.6355)  weight_decay: 0.0500 (0.0500)  time: 0.4290  data: 0.0002  max mem: 31830
Epoch: [148]  [310/312]  eta: 0:00:01  lr: 0.002247  min_lr: 0.002247  loss: 3.5129 (3.6312)  weight_decay: 0.0500 (0.0500)  time: 0.4088  data: 0.0001  max mem: 31830
Epoch: [148]  [311/312]  eta: 0:00:00  lr: 0.002247  min_lr: 0.002247  loss: 3.5773 (3.6322)  weight_decay: 0.0500 (0.0500)  time: 0.4087  data: 0.0001  max mem: 31830
Epoch: [148] Total time: 0:02:53 (0.5567 s / it)
Averaged stats: lr: 0.002247  min_lr: 0.002247  loss: 3.5773 (3.5990)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.2715 (1.2715)  acc1: 73.3073 (73.3073)  acc5: 92.1875 (92.1875)  time: 8.5618  data: 8.3959  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6505 (1.5564)  acc1: 65.3646 (66.7680)  acc5: 88.1510 (88.5600)  time: 1.0682  data: 0.9330  max mem: 31830
Test: Total time: 0:00:09 (1.0788 s / it)
* Acc@1 67.154 Acc@5 88.340 loss 1.554
Accuracy of the model on the 50000 test images: 67.2%
Max accuracy: 69.75%
Epoch: [149]  [  0/312]  eta: 1:05:09  lr: 0.002247  min_lr: 0.002247  loss: 4.0283 (4.0283)  weight_decay: 0.0500 (0.0500)  time: 12.5291  data: 11.8158  max mem: 31830
Epoch: [149]  [ 10/312]  eta: 0:09:12  lr: 0.002246  min_lr: 0.002246  loss: 3.3826 (3.3907)  weight_decay: 0.0500 (0.0500)  time: 1.8309  data: 1.0749  max mem: 31830
Epoch: [149]  [ 20/312]  eta: 0:05:35  lr: 0.002245  min_lr: 0.002245  loss: 3.1532 (3.4133)  weight_decay: 0.0500 (0.0500)  time: 0.5791  data: 0.0064  max mem: 31830
Epoch: [149]  [ 30/312]  eta: 0:04:15  lr: 0.002245  min_lr: 0.002245  loss: 3.7162 (3.4752)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0065  max mem: 31830
Epoch: [149]  [ 40/312]  eta: 0:03:33  lr: 0.002244  min_lr: 0.002244  loss: 3.8017 (3.4872)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0008  max mem: 31830
Epoch: [149]  [ 50/312]  eta: 0:03:05  lr: 0.002243  min_lr: 0.002243  loss: 3.7578 (3.4978)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0006  max mem: 31830
Epoch: [149]  [ 60/312]  eta: 0:02:45  lr: 0.002242  min_lr: 0.002242  loss: 3.6764 (3.5166)  weight_decay: 0.0500 (0.0500)  time: 0.3945  data: 0.0006  max mem: 31830
Epoch: [149]  [ 70/312]  eta: 0:02:30  lr: 0.002242  min_lr: 0.002242  loss: 3.5571 (3.4893)  weight_decay: 0.0500 (0.0500)  time: 0.4071  data: 0.0007  max mem: 31830
Epoch: [149]  [ 80/312]  eta: 0:02:21  lr: 0.002241  min_lr: 0.002241  loss: 3.5571 (3.5201)  weight_decay: 0.0500 (0.0500)  time: 0.4762  data: 0.0265  max mem: 31830
Epoch: [149]  [ 90/312]  eta: 0:02:14  lr: 0.002240  min_lr: 0.002240  loss: 3.8551 (3.5480)  weight_decay: 0.0500 (0.0500)  time: 0.5543  data: 0.0391  max mem: 31830
Epoch: [149]  [100/312]  eta: 0:02:07  lr: 0.002240  min_lr: 0.002240  loss: 3.7409 (3.5455)  weight_decay: 0.0500 (0.0500)  time: 0.5573  data: 0.0180  max mem: 31830
Epoch: [149]  [110/312]  eta: 0:01:59  lr: 0.002239  min_lr: 0.002239  loss: 3.7409 (3.5505)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0178  max mem: 31830
Epoch: [149]  [120/312]  eta: 0:01:52  lr: 0.002238  min_lr: 0.002238  loss: 3.8412 (3.5643)  weight_decay: 0.0500 (0.0500)  time: 0.5057  data: 0.0596  max mem: 31830
Epoch: [149]  [130/312]  eta: 0:01:46  lr: 0.002237  min_lr: 0.002237  loss: 3.8377 (3.5440)  weight_decay: 0.0500 (0.0500)  time: 0.5541  data: 0.0828  max mem: 31830
Epoch: [149]  [140/312]  eta: 0:01:39  lr: 0.002237  min_lr: 0.002237  loss: 3.4720 (3.5427)  weight_decay: 0.0500 (0.0500)  time: 0.5566  data: 0.0611  max mem: 31830
Epoch: [149]  [150/312]  eta: 0:01:33  lr: 0.002236  min_lr: 0.002236  loss: 3.7790 (3.5666)  weight_decay: 0.0500 (0.0500)  time: 0.5433  data: 0.0606  max mem: 31830
Epoch: [149]  [160/312]  eta: 0:01:27  lr: 0.002235  min_lr: 0.002235  loss: 3.8414 (3.5738)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.0749  max mem: 31830
Epoch: [149]  [170/312]  eta: 0:01:21  lr: 0.002235  min_lr: 0.002235  loss: 3.7627 (3.5631)  weight_decay: 0.0500 (0.0500)  time: 0.5567  data: 0.0941  max mem: 31830
Epoch: [149]  [180/312]  eta: 0:01:15  lr: 0.002234  min_lr: 0.002234  loss: 3.6582 (3.5685)  weight_decay: 0.0500 (0.0500)  time: 0.5675  data: 0.0720  max mem: 31830
Epoch: [149]  [190/312]  eta: 0:01:09  lr: 0.002233  min_lr: 0.002233  loss: 3.7134 (3.5723)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0795  max mem: 31830
Epoch: [149]  [200/312]  eta: 0:01:04  lr: 0.002232  min_lr: 0.002232  loss: 3.6657 (3.5620)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.1092  max mem: 31830
Epoch: [149]  [210/312]  eta: 0:00:58  lr: 0.002232  min_lr: 0.002232  loss: 3.4041 (3.5613)  weight_decay: 0.0500 (0.0500)  time: 0.5918  data: 0.0607  max mem: 31830
Epoch: [149]  [220/312]  eta: 0:00:52  lr: 0.002231  min_lr: 0.002231  loss: 3.2129 (3.5454)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0504  max mem: 31830
Epoch: [149]  [230/312]  eta: 0:00:46  lr: 0.002230  min_lr: 0.002230  loss: 3.7151 (3.5588)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0499  max mem: 31830
Epoch: [149]  [240/312]  eta: 0:00:40  lr: 0.002230  min_lr: 0.002230  loss: 3.7706 (3.5597)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0267  max mem: 31830
Epoch: [149]  [250/312]  eta: 0:00:35  lr: 0.002229  min_lr: 0.002229  loss: 3.5393 (3.5530)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0253  max mem: 31830
Epoch: [149]  [260/312]  eta: 0:00:29  lr: 0.002228  min_lr: 0.002228  loss: 3.0838 (3.5403)  weight_decay: 0.0500 (0.0500)  time: 0.6146  data: 0.0195  max mem: 31830
Epoch: [149]  [270/312]  eta: 0:00:23  lr: 0.002227  min_lr: 0.002227  loss: 3.2917 (3.5388)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0081  max mem: 31830
Epoch: [149]  [280/312]  eta: 0:00:18  lr: 0.002227  min_lr: 0.002227  loss: 3.7024 (3.5479)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0085  max mem: 31830
Epoch: [149]  [290/312]  eta: 0:00:12  lr: 0.002226  min_lr: 0.002226  loss: 3.8718 (3.5612)  weight_decay: 0.0500 (0.0500)  time: 0.6243  data: 0.0083  max mem: 31830
Epoch: [149]  [300/312]  eta: 0:00:06  lr: 0.002225  min_lr: 0.002225  loss: 3.8190 (3.5677)  weight_decay: 0.0500 (0.0500)  time: 0.4959  data: 0.0002  max mem: 31830
Epoch: [149]  [310/312]  eta: 0:00:01  lr: 0.002225  min_lr: 0.002225  loss: 3.8741 (3.5761)  weight_decay: 0.0500 (0.0500)  time: 0.3815  data: 0.0001  max mem: 31830
Epoch: [149]  [311/312]  eta: 0:00:00  lr: 0.002224  min_lr: 0.002224  loss: 3.8741 (3.5764)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [149] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.002224  min_lr: 0.002224  loss: 3.8741 (3.6116)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.4736 (1.4736)  acc1: 75.3906 (75.3906)  acc5: 92.0573 (92.0573)  time: 8.2346  data: 8.0670  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7795 (1.6181)  acc1: 65.4948 (68.6240)  acc5: 88.0208 (89.1040)  time: 1.0379  data: 0.8964  max mem: 31830
Test: Total time: 0:00:09 (1.0487 s / it)
* Acc@1 68.732 Acc@5 89.358 loss 1.611
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 69.75%
Epoch: [150]  [  0/312]  eta: 1:02:14  lr: 0.002224  min_lr: 0.002224  loss: 2.7911 (2.7911)  weight_decay: 0.0500 (0.0500)  time: 11.9701  data: 8.8574  max mem: 31830
Epoch: [150]  [ 10/312]  eta: 0:09:10  lr: 0.002224  min_lr: 0.002224  loss: 3.6565 (3.4495)  weight_decay: 0.0500 (0.0500)  time: 1.8234  data: 0.9399  max mem: 31830
Epoch: [150]  [ 20/312]  eta: 0:05:32  lr: 0.002223  min_lr: 0.002223  loss: 3.6827 (3.5866)  weight_decay: 0.0500 (0.0500)  time: 0.5972  data: 0.0744  max mem: 31830
Epoch: [150]  [ 30/312]  eta: 0:04:13  lr: 0.002222  min_lr: 0.002222  loss: 3.7584 (3.6724)  weight_decay: 0.0500 (0.0500)  time: 0.3887  data: 0.0007  max mem: 31830
Epoch: [150]  [ 40/312]  eta: 0:03:30  lr: 0.002222  min_lr: 0.002222  loss: 3.8751 (3.6690)  weight_decay: 0.0500 (0.0500)  time: 0.3945  data: 0.0013  max mem: 31830
Epoch: [150]  [ 50/312]  eta: 0:03:03  lr: 0.002221  min_lr: 0.002221  loss: 3.6267 (3.6198)  weight_decay: 0.0500 (0.0500)  time: 0.3978  data: 0.0013  max mem: 31830
Epoch: [150]  [ 60/312]  eta: 0:02:44  lr: 0.002220  min_lr: 0.002220  loss: 3.7529 (3.6326)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0008  max mem: 31830
Epoch: [150]  [ 70/312]  eta: 0:02:34  lr: 0.002219  min_lr: 0.002219  loss: 3.7529 (3.6031)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0008  max mem: 31830
Epoch: [150]  [ 80/312]  eta: 0:02:27  lr: 0.002219  min_lr: 0.002219  loss: 3.6355 (3.5869)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0014  max mem: 31830
Epoch: [150]  [ 90/312]  eta: 0:02:15  lr: 0.002218  min_lr: 0.002218  loss: 3.7725 (3.6182)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0013  max mem: 31830
Epoch: [150]  [100/312]  eta: 0:02:10  lr: 0.002217  min_lr: 0.002217  loss: 3.7350 (3.6005)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0010  max mem: 31830
Epoch: [150]  [110/312]  eta: 0:02:00  lr: 0.002217  min_lr: 0.002217  loss: 3.4622 (3.5875)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0012  max mem: 31830
Epoch: [150]  [120/312]  eta: 0:01:55  lr: 0.002216  min_lr: 0.002216  loss: 3.4622 (3.5755)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0009  max mem: 31830
Epoch: [150]  [130/312]  eta: 0:01:49  lr: 0.002215  min_lr: 0.002215  loss: 3.8526 (3.5793)  weight_decay: 0.0500 (0.0500)  time: 0.6525  data: 0.0010  max mem: 31830
Epoch: [150]  [140/312]  eta: 0:01:41  lr: 0.002214  min_lr: 0.002214  loss: 3.8954 (3.6058)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0109  max mem: 31830
Epoch: [150]  [150/312]  eta: 0:01:35  lr: 0.002214  min_lr: 0.002214  loss: 3.9231 (3.6175)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0108  max mem: 31830
Epoch: [150]  [160/312]  eta: 0:01:30  lr: 0.002213  min_lr: 0.002213  loss: 3.7667 (3.6286)  weight_decay: 0.0500 (0.0500)  time: 0.6292  data: 0.0018  max mem: 31830
Epoch: [150]  [170/312]  eta: 0:01:23  lr: 0.002212  min_lr: 0.002212  loss: 3.7129 (3.6303)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0139  max mem: 31830
Epoch: [150]  [180/312]  eta: 0:01:17  lr: 0.002212  min_lr: 0.002212  loss: 3.5913 (3.6156)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.0196  max mem: 31830
Epoch: [150]  [190/312]  eta: 0:01:10  lr: 0.002211  min_lr: 0.002211  loss: 3.1922 (3.6078)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0074  max mem: 31830
Epoch: [150]  [200/312]  eta: 0:01:04  lr: 0.002210  min_lr: 0.002210  loss: 3.8025 (3.6140)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0008  max mem: 31830
Epoch: [150]  [210/312]  eta: 0:00:59  lr: 0.002209  min_lr: 0.002209  loss: 3.8742 (3.6298)  weight_decay: 0.0500 (0.0500)  time: 0.6425  data: 0.0114  max mem: 31830
Epoch: [150]  [220/312]  eta: 0:00:52  lr: 0.002209  min_lr: 0.002209  loss: 3.8806 (3.6336)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0113  max mem: 31830
Epoch: [150]  [230/312]  eta: 0:00:47  lr: 0.002208  min_lr: 0.002208  loss: 3.7232 (3.6288)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0007  max mem: 31830
Epoch: [150]  [240/312]  eta: 0:00:41  lr: 0.002207  min_lr: 0.002207  loss: 3.6970 (3.6388)  weight_decay: 0.0500 (0.0500)  time: 0.6053  data: 0.0211  max mem: 31830
Epoch: [150]  [250/312]  eta: 0:00:35  lr: 0.002207  min_lr: 0.002207  loss: 3.7988 (3.6379)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0211  max mem: 31830
Epoch: [150]  [260/312]  eta: 0:00:29  lr: 0.002206  min_lr: 0.002206  loss: 3.4455 (3.6243)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.0009  max mem: 31830
Epoch: [150]  [270/312]  eta: 0:00:23  lr: 0.002205  min_lr: 0.002205  loss: 3.3027 (3.6160)  weight_decay: 0.0500 (0.0500)  time: 0.5316  data: 0.0009  max mem: 31830
Epoch: [150]  [280/312]  eta: 0:00:18  lr: 0.002204  min_lr: 0.002204  loss: 3.7762 (3.6221)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0028  max mem: 31830
Epoch: [150]  [290/312]  eta: 0:00:12  lr: 0.002204  min_lr: 0.002204  loss: 3.7762 (3.6215)  weight_decay: 0.0500 (0.0500)  time: 0.5854  data: 0.0030  max mem: 31830
Epoch: [150]  [300/312]  eta: 0:00:06  lr: 0.002203  min_lr: 0.002203  loss: 3.6473 (3.6205)  weight_decay: 0.0500 (0.0500)  time: 0.4777  data: 0.0006  max mem: 31830
Epoch: [150]  [310/312]  eta: 0:00:01  lr: 0.002202  min_lr: 0.002202  loss: 3.6767 (3.6190)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [150]  [311/312]  eta: 0:00:00  lr: 0.002202  min_lr: 0.002202  loss: 3.7158 (3.6208)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [150] Total time: 0:02:54 (0.5598 s / it)
Averaged stats: lr: 0.002202  min_lr: 0.002202  loss: 3.7158 (3.5960)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.4997 (1.4997)  acc1: 74.2188 (74.2188)  acc5: 91.2760 (91.2760)  time: 8.3791  data: 8.2123  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5845 (1.5720)  acc1: 68.4896 (68.5280)  acc5: 88.8021 (88.7680)  time: 1.0478  data: 0.9126  max mem: 31830
Test: Total time: 0:00:09 (1.0579 s / it)
* Acc@1 68.168 Acc@5 88.874 loss 1.576
Accuracy of the model on the 50000 test images: 68.2%
Max accuracy: 69.75%
Epoch: [151]  [  0/312]  eta: 1:04:27  lr: 0.002202  min_lr: 0.002202  loss: 3.1000 (3.1000)  weight_decay: 0.0500 (0.0500)  time: 12.3968  data: 10.3931  max mem: 31830
Epoch: [151]  [ 10/312]  eta: 0:09:29  lr: 0.002201  min_lr: 0.002201  loss: 3.2985 (3.3402)  weight_decay: 0.0500 (0.0500)  time: 1.8870  data: 0.9646  max mem: 31830
Epoch: [151]  [ 20/312]  eta: 0:05:42  lr: 0.002201  min_lr: 0.002201  loss: 3.2555 (3.3300)  weight_decay: 0.0500 (0.0500)  time: 0.6114  data: 0.0112  max mem: 31830
Epoch: [151]  [ 30/312]  eta: 0:04:20  lr: 0.002200  min_lr: 0.002200  loss: 3.6198 (3.4876)  weight_decay: 0.0500 (0.0500)  time: 0.3929  data: 0.0006  max mem: 31830
Epoch: [151]  [ 40/312]  eta: 0:03:36  lr: 0.002199  min_lr: 0.002199  loss: 3.6198 (3.4832)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0007  max mem: 31830
Epoch: [151]  [ 50/312]  eta: 0:03:08  lr: 0.002198  min_lr: 0.002198  loss: 3.7674 (3.5582)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0007  max mem: 31830
Epoch: [151]  [ 60/312]  eta: 0:02:47  lr: 0.002198  min_lr: 0.002198  loss: 3.7674 (3.5461)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0007  max mem: 31830
Epoch: [151]  [ 70/312]  eta: 0:02:32  lr: 0.002197  min_lr: 0.002197  loss: 3.6118 (3.5710)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0014  max mem: 31830
Epoch: [151]  [ 80/312]  eta: 0:02:25  lr: 0.002196  min_lr: 0.002196  loss: 3.5239 (3.5282)  weight_decay: 0.0500 (0.0500)  time: 0.5014  data: 0.0014  max mem: 31830
Epoch: [151]  [ 90/312]  eta: 0:02:15  lr: 0.002196  min_lr: 0.002196  loss: 3.4734 (3.5310)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0126  max mem: 31830
Epoch: [151]  [100/312]  eta: 0:02:09  lr: 0.002195  min_lr: 0.002195  loss: 3.6235 (3.5325)  weight_decay: 0.0500 (0.0500)  time: 0.5502  data: 0.0126  max mem: 31830
Epoch: [151]  [110/312]  eta: 0:02:01  lr: 0.002194  min_lr: 0.002194  loss: 3.8074 (3.5557)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0007  max mem: 31830
Epoch: [151]  [120/312]  eta: 0:01:53  lr: 0.002193  min_lr: 0.002193  loss: 3.7871 (3.5544)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0007  max mem: 31830
Epoch: [151]  [130/312]  eta: 0:01:47  lr: 0.002193  min_lr: 0.002193  loss: 3.7871 (3.5690)  weight_decay: 0.0500 (0.0500)  time: 0.5608  data: 0.0091  max mem: 31830
Epoch: [151]  [140/312]  eta: 0:01:41  lr: 0.002192  min_lr: 0.002192  loss: 3.7919 (3.5670)  weight_decay: 0.0500 (0.0500)  time: 0.5746  data: 0.0091  max mem: 31830
Epoch: [151]  [150/312]  eta: 0:01:35  lr: 0.002191  min_lr: 0.002191  loss: 3.7935 (3.5788)  weight_decay: 0.0500 (0.0500)  time: 0.5700  data: 0.0141  max mem: 31830
Epoch: [151]  [160/312]  eta: 0:01:29  lr: 0.002191  min_lr: 0.002191  loss: 3.7954 (3.5880)  weight_decay: 0.0500 (0.0500)  time: 0.5659  data: 0.0337  max mem: 31830
Epoch: [151]  [170/312]  eta: 0:01:23  lr: 0.002190  min_lr: 0.002190  loss: 3.6940 (3.5842)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0206  max mem: 31830
Epoch: [151]  [180/312]  eta: 0:01:16  lr: 0.002189  min_lr: 0.002189  loss: 3.6946 (3.5990)  weight_decay: 0.0500 (0.0500)  time: 0.5162  data: 0.0009  max mem: 31830
Epoch: [151]  [190/312]  eta: 0:01:10  lr: 0.002188  min_lr: 0.002188  loss: 3.5305 (3.5823)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0008  max mem: 31830
Epoch: [151]  [200/312]  eta: 0:01:05  lr: 0.002188  min_lr: 0.002188  loss: 3.5305 (3.5826)  weight_decay: 0.0500 (0.0500)  time: 0.6105  data: 0.0008  max mem: 31830
Epoch: [151]  [210/312]  eta: 0:00:58  lr: 0.002187  min_lr: 0.002187  loss: 3.5731 (3.5780)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.0120  max mem: 31830
Epoch: [151]  [220/312]  eta: 0:00:52  lr: 0.002186  min_lr: 0.002186  loss: 3.7571 (3.5881)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0127  max mem: 31830
Epoch: [151]  [230/312]  eta: 0:00:47  lr: 0.002186  min_lr: 0.002186  loss: 3.8349 (3.5885)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0015  max mem: 31830
Epoch: [151]  [240/312]  eta: 0:00:41  lr: 0.002185  min_lr: 0.002185  loss: 3.7556 (3.5914)  weight_decay: 0.0500 (0.0500)  time: 0.5663  data: 0.0008  max mem: 31830
Epoch: [151]  [250/312]  eta: 0:00:35  lr: 0.002184  min_lr: 0.002184  loss: 3.7556 (3.5951)  weight_decay: 0.0500 (0.0500)  time: 0.5517  data: 0.0007  max mem: 31830
Epoch: [151]  [260/312]  eta: 0:00:29  lr: 0.002183  min_lr: 0.002183  loss: 3.8021 (3.5914)  weight_decay: 0.0500 (0.0500)  time: 0.5452  data: 0.0134  max mem: 31830
Epoch: [151]  [270/312]  eta: 0:00:23  lr: 0.002183  min_lr: 0.002183  loss: 3.5308 (3.5905)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0134  max mem: 31830
Epoch: [151]  [280/312]  eta: 0:00:18  lr: 0.002182  min_lr: 0.002182  loss: 3.5308 (3.5907)  weight_decay: 0.0500 (0.0500)  time: 0.5588  data: 0.0019  max mem: 31830
Epoch: [151]  [290/312]  eta: 0:00:12  lr: 0.002181  min_lr: 0.002181  loss: 3.5690 (3.5944)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.0179  max mem: 31830
Epoch: [151]  [300/312]  eta: 0:00:06  lr: 0.002181  min_lr: 0.002181  loss: 3.8209 (3.6010)  weight_decay: 0.0500 (0.0500)  time: 0.4632  data: 0.0260  max mem: 31830
Epoch: [151]  [310/312]  eta: 0:00:01  lr: 0.002180  min_lr: 0.002180  loss: 3.7279 (3.6044)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0097  max mem: 31830
Epoch: [151]  [311/312]  eta: 0:00:00  lr: 0.002180  min_lr: 0.002180  loss: 3.7279 (3.6052)  weight_decay: 0.0500 (0.0500)  time: 0.3904  data: 0.0097  max mem: 31830
Epoch: [151] Total time: 0:02:55 (0.5619 s / it)
Averaged stats: lr: 0.002180  min_lr: 0.002180  loss: 3.7279 (3.5927)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.3163 (1.3163)  acc1: 77.6042 (77.6042)  acc5: 92.9688 (92.9688)  time: 8.3339  data: 8.1668  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6827 (1.5923)  acc1: 69.5312 (68.8160)  acc5: 88.4115 (88.8000)  time: 1.0440  data: 0.9075  max mem: 31830
Test: Total time: 0:00:09 (1.0535 s / it)
* Acc@1 68.514 Acc@5 89.280 loss 1.583
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 69.75%
Epoch: [152]  [  0/312]  eta: 1:06:23  lr: 0.002180  min_lr: 0.002180  loss: 3.9196 (3.9196)  weight_decay: 0.0500 (0.0500)  time: 12.7667  data: 9.6972  max mem: 31830
Epoch: [152]  [ 10/312]  eta: 0:09:12  lr: 0.002179  min_lr: 0.002179  loss: 3.7273 (3.7436)  weight_decay: 0.0500 (0.0500)  time: 1.8288  data: 0.9686  max mem: 31830
Epoch: [152]  [ 20/312]  eta: 0:05:49  lr: 0.002178  min_lr: 0.002178  loss: 3.6932 (3.6766)  weight_decay: 0.0500 (0.0500)  time: 0.6186  data: 0.0483  max mem: 31830
Epoch: [152]  [ 30/312]  eta: 0:04:25  lr: 0.002178  min_lr: 0.002178  loss: 3.5438 (3.5875)  weight_decay: 0.0500 (0.0500)  time: 0.4509  data: 0.0008  max mem: 31830
Epoch: [152]  [ 40/312]  eta: 0:03:39  lr: 0.002177  min_lr: 0.002177  loss: 3.5438 (3.5507)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0008  max mem: 31830
Epoch: [152]  [ 50/312]  eta: 0:03:10  lr: 0.002176  min_lr: 0.002176  loss: 3.8193 (3.6192)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0014  max mem: 31830
Epoch: [152]  [ 60/312]  eta: 0:02:49  lr: 0.002175  min_lr: 0.002175  loss: 3.8285 (3.6158)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0014  max mem: 31830
Epoch: [152]  [ 70/312]  eta: 0:02:33  lr: 0.002175  min_lr: 0.002175  loss: 3.6353 (3.6164)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0007  max mem: 31830
Epoch: [152]  [ 80/312]  eta: 0:02:22  lr: 0.002174  min_lr: 0.002174  loss: 3.4862 (3.5973)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0148  max mem: 31830
Epoch: [152]  [ 90/312]  eta: 0:02:18  lr: 0.002173  min_lr: 0.002173  loss: 3.4082 (3.5691)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0680  max mem: 31830
Epoch: [152]  [100/312]  eta: 0:02:08  lr: 0.002173  min_lr: 0.002173  loss: 3.7275 (3.5826)  weight_decay: 0.0500 (0.0500)  time: 0.5583  data: 0.0540  max mem: 31830
Epoch: [152]  [110/312]  eta: 0:02:01  lr: 0.002172  min_lr: 0.002172  loss: 3.8554 (3.5972)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.0127  max mem: 31830
Epoch: [152]  [120/312]  eta: 0:01:55  lr: 0.002171  min_lr: 0.002171  loss: 3.7159 (3.6030)  weight_decay: 0.0500 (0.0500)  time: 0.5950  data: 0.0507  max mem: 31830
Epoch: [152]  [130/312]  eta: 0:01:47  lr: 0.002170  min_lr: 0.002170  loss: 3.6951 (3.5959)  weight_decay: 0.0500 (0.0500)  time: 0.5556  data: 0.0390  max mem: 31830
Epoch: [152]  [140/312]  eta: 0:01:41  lr: 0.002170  min_lr: 0.002170  loss: 3.7208 (3.5963)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0374  max mem: 31830
Epoch: [152]  [150/312]  eta: 0:01:34  lr: 0.002169  min_lr: 0.002169  loss: 3.7154 (3.5843)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0374  max mem: 31830
Epoch: [152]  [160/312]  eta: 0:01:28  lr: 0.002168  min_lr: 0.002168  loss: 3.7154 (3.5876)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0153  max mem: 31830
Epoch: [152]  [170/312]  eta: 0:01:22  lr: 0.002168  min_lr: 0.002168  loss: 3.7276 (3.5901)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0280  max mem: 31830
Epoch: [152]  [180/312]  eta: 0:01:16  lr: 0.002167  min_lr: 0.002167  loss: 3.6979 (3.5939)  weight_decay: 0.0500 (0.0500)  time: 0.5573  data: 0.0137  max mem: 31830
Epoch: [152]  [190/312]  eta: 0:01:10  lr: 0.002166  min_lr: 0.002166  loss: 3.6482 (3.5894)  weight_decay: 0.0500 (0.0500)  time: 0.5536  data: 0.0198  max mem: 31830
Epoch: [152]  [200/312]  eta: 0:01:04  lr: 0.002165  min_lr: 0.002165  loss: 3.6360 (3.5917)  weight_decay: 0.0500 (0.0500)  time: 0.5635  data: 0.0314  max mem: 31830
Epoch: [152]  [210/312]  eta: 0:00:58  lr: 0.002165  min_lr: 0.002165  loss: 3.5236 (3.5879)  weight_decay: 0.0500 (0.0500)  time: 0.5480  data: 0.0125  max mem: 31830
Epoch: [152]  [220/312]  eta: 0:00:52  lr: 0.002164  min_lr: 0.002164  loss: 3.6893 (3.5959)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0010  max mem: 31830
Epoch: [152]  [230/312]  eta: 0:00:46  lr: 0.002163  min_lr: 0.002163  loss: 3.7246 (3.5913)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0011  max mem: 31830
Epoch: [152]  [240/312]  eta: 0:00:41  lr: 0.002163  min_lr: 0.002163  loss: 3.7246 (3.5948)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0010  max mem: 31830
Epoch: [152]  [250/312]  eta: 0:00:35  lr: 0.002162  min_lr: 0.002162  loss: 3.7824 (3.6004)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.0241  max mem: 31830
Epoch: [152]  [260/312]  eta: 0:00:29  lr: 0.002161  min_lr: 0.002161  loss: 3.7028 (3.5921)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0246  max mem: 31830
Epoch: [152]  [270/312]  eta: 0:00:24  lr: 0.002160  min_lr: 0.002160  loss: 3.8126 (3.5987)  weight_decay: 0.0500 (0.0500)  time: 0.5556  data: 0.0264  max mem: 31830
Epoch: [152]  [280/312]  eta: 0:00:18  lr: 0.002160  min_lr: 0.002160  loss: 3.8361 (3.5999)  weight_decay: 0.0500 (0.0500)  time: 0.6020  data: 0.0271  max mem: 31830
Epoch: [152]  [290/312]  eta: 0:00:12  lr: 0.002159  min_lr: 0.002159  loss: 3.8693 (3.6073)  weight_decay: 0.0500 (0.0500)  time: 0.5416  data: 0.0017  max mem: 31830
Epoch: [152]  [300/312]  eta: 0:00:06  lr: 0.002158  min_lr: 0.002158  loss: 3.8559 (3.6093)  weight_decay: 0.0500 (0.0500)  time: 0.4774  data: 0.0002  max mem: 31830
Epoch: [152]  [310/312]  eta: 0:00:01  lr: 0.002158  min_lr: 0.002158  loss: 3.6962 (3.6031)  weight_decay: 0.0500 (0.0500)  time: 0.4071  data: 0.0001  max mem: 31830
Epoch: [152]  [311/312]  eta: 0:00:00  lr: 0.002157  min_lr: 0.002157  loss: 3.6962 (3.6048)  weight_decay: 0.0500 (0.0500)  time: 0.4069  data: 0.0001  max mem: 31830
Epoch: [152] Total time: 0:02:55 (0.5624 s / it)
Averaged stats: lr: 0.002157  min_lr: 0.002157  loss: 3.6962 (3.5944)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.2397 (1.2397)  acc1: 76.8229 (76.8229)  acc5: 93.4896 (93.4896)  time: 8.0359  data: 7.8775  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6136 (1.5042)  acc1: 66.7969 (69.0400)  acc5: 89.1927 (89.6640)  time: 1.0093  data: 0.8754  max mem: 31830
Test: Total time: 0:00:09 (1.0206 s / it)
* Acc@1 68.718 Acc@5 89.556 loss 1.511
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 69.75%
Epoch: [153]  [  0/312]  eta: 1:02:25  lr: 0.002157  min_lr: 0.002157  loss: 3.3802 (3.3802)  weight_decay: 0.0500 (0.0500)  time: 12.0056  data: 10.9989  max mem: 31830
Epoch: [153]  [ 10/312]  eta: 0:08:45  lr: 0.002157  min_lr: 0.002157  loss: 3.7474 (3.6718)  weight_decay: 0.0500 (0.0500)  time: 1.7394  data: 1.0005  max mem: 31830
Epoch: [153]  [ 20/312]  eta: 0:05:29  lr: 0.002156  min_lr: 0.002156  loss: 3.7698 (3.7563)  weight_decay: 0.0500 (0.0500)  time: 0.5860  data: 0.0007  max mem: 31830
Epoch: [153]  [ 30/312]  eta: 0:04:12  lr: 0.002155  min_lr: 0.002155  loss: 3.8249 (3.7192)  weight_decay: 0.0500 (0.0500)  time: 0.4294  data: 0.0007  max mem: 31830
Epoch: [153]  [ 40/312]  eta: 0:03:30  lr: 0.002155  min_lr: 0.002155  loss: 3.6751 (3.7271)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0007  max mem: 31830
Epoch: [153]  [ 50/312]  eta: 0:03:04  lr: 0.002154  min_lr: 0.002154  loss: 3.6537 (3.7208)  weight_decay: 0.0500 (0.0500)  time: 0.4124  data: 0.0007  max mem: 31830
Epoch: [153]  [ 60/312]  eta: 0:02:45  lr: 0.002153  min_lr: 0.002153  loss: 3.8465 (3.7597)  weight_decay: 0.0500 (0.0500)  time: 0.4138  data: 0.0017  max mem: 31830
Epoch: [153]  [ 70/312]  eta: 0:02:38  lr: 0.002152  min_lr: 0.002152  loss: 3.8099 (3.7119)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0019  max mem: 31830
Epoch: [153]  [ 80/312]  eta: 0:02:28  lr: 0.002152  min_lr: 0.002152  loss: 3.4489 (3.6827)  weight_decay: 0.0500 (0.0500)  time: 0.5959  data: 0.0011  max mem: 31830
Epoch: [153]  [ 90/312]  eta: 0:02:18  lr: 0.002151  min_lr: 0.002151  loss: 3.6264 (3.6906)  weight_decay: 0.0500 (0.0500)  time: 0.5080  data: 0.0009  max mem: 31830
Epoch: [153]  [100/312]  eta: 0:02:12  lr: 0.002150  min_lr: 0.002150  loss: 3.6448 (3.6716)  weight_decay: 0.0500 (0.0500)  time: 0.5582  data: 0.0015  max mem: 31830
Epoch: [153]  [110/312]  eta: 0:02:01  lr: 0.002149  min_lr: 0.002149  loss: 3.5005 (3.6574)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0015  max mem: 31830
Epoch: [153]  [120/312]  eta: 0:01:56  lr: 0.002149  min_lr: 0.002149  loss: 3.6732 (3.6587)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0008  max mem: 31830
Epoch: [153]  [130/312]  eta: 0:01:49  lr: 0.002148  min_lr: 0.002148  loss: 3.6816 (3.6542)  weight_decay: 0.0500 (0.0500)  time: 0.5952  data: 0.0014  max mem: 31830
Epoch: [153]  [140/312]  eta: 0:01:41  lr: 0.002147  min_lr: 0.002147  loss: 3.8395 (3.6666)  weight_decay: 0.0500 (0.0500)  time: 0.4767  data: 0.0014  max mem: 31830
Epoch: [153]  [150/312]  eta: 0:01:36  lr: 0.002147  min_lr: 0.002147  loss: 3.9164 (3.6645)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0205  max mem: 31830
Epoch: [153]  [160/312]  eta: 0:01:29  lr: 0.002146  min_lr: 0.002146  loss: 3.5828 (3.6549)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.0208  max mem: 31830
Epoch: [153]  [170/312]  eta: 0:01:23  lr: 0.002145  min_lr: 0.002145  loss: 3.8328 (3.6646)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0017  max mem: 31830
Epoch: [153]  [180/312]  eta: 0:01:17  lr: 0.002144  min_lr: 0.002144  loss: 3.7558 (3.6621)  weight_decay: 0.0500 (0.0500)  time: 0.6006  data: 0.0016  max mem: 31830
Epoch: [153]  [190/312]  eta: 0:01:10  lr: 0.002144  min_lr: 0.002144  loss: 3.4207 (3.6466)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0014  max mem: 31830
Epoch: [153]  [200/312]  eta: 0:01:05  lr: 0.002143  min_lr: 0.002143  loss: 3.5384 (3.6483)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0143  max mem: 31830
Epoch: [153]  [210/312]  eta: 0:00:58  lr: 0.002142  min_lr: 0.002142  loss: 3.6204 (3.6453)  weight_decay: 0.0500 (0.0500)  time: 0.5668  data: 0.0138  max mem: 31830
Epoch: [153]  [220/312]  eta: 0:00:53  lr: 0.002142  min_lr: 0.002142  loss: 3.6024 (3.6379)  weight_decay: 0.0500 (0.0500)  time: 0.5380  data: 0.0012  max mem: 31830
Epoch: [153]  [230/312]  eta: 0:00:47  lr: 0.002141  min_lr: 0.002141  loss: 3.5939 (3.6339)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0012  max mem: 31830
Epoch: [153]  [240/312]  eta: 0:00:41  lr: 0.002140  min_lr: 0.002140  loss: 3.3336 (3.6221)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0019  max mem: 31830
Epoch: [153]  [250/312]  eta: 0:00:35  lr: 0.002139  min_lr: 0.002139  loss: 3.3756 (3.6226)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0150  max mem: 31830
Epoch: [153]  [260/312]  eta: 0:00:29  lr: 0.002139  min_lr: 0.002139  loss: 3.7656 (3.6298)  weight_decay: 0.0500 (0.0500)  time: 0.5727  data: 0.0152  max mem: 31830
Epoch: [153]  [270/312]  eta: 0:00:23  lr: 0.002138  min_lr: 0.002138  loss: 3.9229 (3.6356)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0020  max mem: 31830
Epoch: [153]  [280/312]  eta: 0:00:18  lr: 0.002137  min_lr: 0.002137  loss: 3.9213 (3.6432)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0021  max mem: 31830
Epoch: [153]  [290/312]  eta: 0:00:12  lr: 0.002137  min_lr: 0.002137  loss: 3.7303 (3.6403)  weight_decay: 0.0500 (0.0500)  time: 0.5438  data: 0.0019  max mem: 31830
Epoch: [153]  [300/312]  eta: 0:00:06  lr: 0.002136  min_lr: 0.002136  loss: 3.6821 (3.6442)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0002  max mem: 31830
Epoch: [153]  [310/312]  eta: 0:00:01  lr: 0.002135  min_lr: 0.002135  loss: 3.8396 (3.6456)  weight_decay: 0.0500 (0.0500)  time: 0.4548  data: 0.0002  max mem: 31830
Epoch: [153]  [311/312]  eta: 0:00:00  lr: 0.002135  min_lr: 0.002135  loss: 3.8428 (3.6465)  weight_decay: 0.0500 (0.0500)  time: 0.4178  data: 0.0001  max mem: 31830
Epoch: [153] Total time: 0:02:56 (0.5651 s / it)
Averaged stats: lr: 0.002135  min_lr: 0.002135  loss: 3.8428 (3.5933)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.5612 (1.5612)  acc1: 77.3438 (77.3438)  acc5: 92.4479 (92.4479)  time: 8.4158  data: 8.2488  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.9562 (1.8319)  acc1: 66.6667 (69.2640)  acc5: 88.2812 (88.8000)  time: 1.0527  data: 0.9166  max mem: 31830
Test: Total time: 0:00:09 (1.0621 s / it)
* Acc@1 68.824 Acc@5 89.152 loss 1.838
Accuracy of the model on the 50000 test images: 68.8%
Max accuracy: 69.75%
Epoch: [154]  [  0/312]  eta: 1:03:42  lr: 0.002135  min_lr: 0.002135  loss: 3.8016 (3.8016)  weight_decay: 0.0500 (0.0500)  time: 12.2526  data: 10.1643  max mem: 31830
Epoch: [154]  [ 10/312]  eta: 0:08:46  lr: 0.002134  min_lr: 0.002134  loss: 3.8016 (3.5893)  weight_decay: 0.0500 (0.0500)  time: 1.7445  data: 0.9246  max mem: 31830
Epoch: [154]  [ 20/312]  eta: 0:05:33  lr: 0.002134  min_lr: 0.002134  loss: 3.7955 (3.5678)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.0257  max mem: 31830
Epoch: [154]  [ 30/312]  eta: 0:04:14  lr: 0.002133  min_lr: 0.002133  loss: 3.5951 (3.5112)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0259  max mem: 31830
Epoch: [154]  [ 40/312]  eta: 0:03:31  lr: 0.002132  min_lr: 0.002132  loss: 3.2684 (3.5029)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0011  max mem: 31830
Epoch: [154]  [ 50/312]  eta: 0:03:06  lr: 0.002131  min_lr: 0.002131  loss: 3.2188 (3.4312)  weight_decay: 0.0500 (0.0500)  time: 0.4175  data: 0.0010  max mem: 31830
Epoch: [154]  [ 60/312]  eta: 0:02:46  lr: 0.002131  min_lr: 0.002131  loss: 3.2706 (3.4612)  weight_decay: 0.0500 (0.0500)  time: 0.4172  data: 0.0008  max mem: 31830
Epoch: [154]  [ 70/312]  eta: 0:02:37  lr: 0.002130  min_lr: 0.002130  loss: 3.4966 (3.4613)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0008  max mem: 31830
Epoch: [154]  [ 80/312]  eta: 0:02:29  lr: 0.002129  min_lr: 0.002129  loss: 3.5240 (3.4952)  weight_decay: 0.0500 (0.0500)  time: 0.5963  data: 0.0010  max mem: 31830
Epoch: [154]  [ 90/312]  eta: 0:02:18  lr: 0.002129  min_lr: 0.002129  loss: 3.6329 (3.4929)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0013  max mem: 31830
Epoch: [154]  [100/312]  eta: 0:02:11  lr: 0.002128  min_lr: 0.002128  loss: 3.6329 (3.4876)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0012  max mem: 31830
Epoch: [154]  [110/312]  eta: 0:02:01  lr: 0.002127  min_lr: 0.002127  loss: 3.7391 (3.5208)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.0015  max mem: 31830
Epoch: [154]  [120/312]  eta: 0:01:55  lr: 0.002126  min_lr: 0.002126  loss: 3.8118 (3.5348)  weight_decay: 0.0500 (0.0500)  time: 0.4916  data: 0.0014  max mem: 31830
Epoch: [154]  [130/312]  eta: 0:01:49  lr: 0.002126  min_lr: 0.002126  loss: 3.6695 (3.5199)  weight_decay: 0.0500 (0.0500)  time: 0.6195  data: 0.0008  max mem: 31830
Epoch: [154]  [140/312]  eta: 0:01:41  lr: 0.002125  min_lr: 0.002125  loss: 3.6828 (3.5368)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0009  max mem: 31830
Epoch: [154]  [150/312]  eta: 0:01:35  lr: 0.002124  min_lr: 0.002124  loss: 3.7075 (3.5164)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0010  max mem: 31830
Epoch: [154]  [160/312]  eta: 0:01:29  lr: 0.002124  min_lr: 0.002124  loss: 3.5293 (3.5261)  weight_decay: 0.0500 (0.0500)  time: 0.5926  data: 0.0009  max mem: 31830
Epoch: [154]  [170/312]  eta: 0:01:22  lr: 0.002123  min_lr: 0.002123  loss: 3.7236 (3.5388)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0012  max mem: 31830
Epoch: [154]  [180/312]  eta: 0:01:16  lr: 0.002122  min_lr: 0.002122  loss: 3.8856 (3.5479)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0015  max mem: 31830
Epoch: [154]  [190/312]  eta: 0:01:09  lr: 0.002121  min_lr: 0.002121  loss: 3.8447 (3.5683)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0016  max mem: 31830
Epoch: [154]  [200/312]  eta: 0:01:04  lr: 0.002121  min_lr: 0.002121  loss: 3.8295 (3.5776)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0014  max mem: 31830
Epoch: [154]  [210/312]  eta: 0:00:58  lr: 0.002120  min_lr: 0.002120  loss: 3.7617 (3.5732)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.0010  max mem: 31830
Epoch: [154]  [220/312]  eta: 0:00:52  lr: 0.002119  min_lr: 0.002119  loss: 3.6965 (3.5695)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0115  max mem: 31830
Epoch: [154]  [230/312]  eta: 0:00:46  lr: 0.002118  min_lr: 0.002118  loss: 3.5868 (3.5687)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0244  max mem: 31830
Epoch: [154]  [240/312]  eta: 0:00:41  lr: 0.002118  min_lr: 0.002118  loss: 3.9226 (3.5876)  weight_decay: 0.0500 (0.0500)  time: 0.5973  data: 0.0138  max mem: 31830
Epoch: [154]  [250/312]  eta: 0:00:35  lr: 0.002117  min_lr: 0.002117  loss: 3.8931 (3.5821)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0007  max mem: 31830
Epoch: [154]  [260/312]  eta: 0:00:29  lr: 0.002116  min_lr: 0.002116  loss: 3.2865 (3.5719)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0007  max mem: 31830
Epoch: [154]  [270/312]  eta: 0:00:23  lr: 0.002116  min_lr: 0.002116  loss: 3.1654 (3.5612)  weight_decay: 0.0500 (0.0500)  time: 0.5672  data: 0.0007  max mem: 31830
Epoch: [154]  [280/312]  eta: 0:00:18  lr: 0.002115  min_lr: 0.002115  loss: 3.5201 (3.5600)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0020  max mem: 31830
Epoch: [154]  [290/312]  eta: 0:00:12  lr: 0.002114  min_lr: 0.002114  loss: 3.7917 (3.5712)  weight_decay: 0.0500 (0.0500)  time: 0.5718  data: 0.0018  max mem: 31830
Epoch: [154]  [300/312]  eta: 0:00:06  lr: 0.002113  min_lr: 0.002113  loss: 3.8110 (3.5689)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0002  max mem: 31830
Epoch: [154]  [310/312]  eta: 0:00:01  lr: 0.002113  min_lr: 0.002113  loss: 3.7240 (3.5682)  weight_decay: 0.0500 (0.0500)  time: 0.3864  data: 0.0002  max mem: 31830
Epoch: [154]  [311/312]  eta: 0:00:00  lr: 0.002113  min_lr: 0.002113  loss: 3.7924 (3.5697)  weight_decay: 0.0500 (0.0500)  time: 0.3862  data: 0.0001  max mem: 31830
Epoch: [154] Total time: 0:02:54 (0.5600 s / it)
Averaged stats: lr: 0.002113  min_lr: 0.002113  loss: 3.7924 (3.5747)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1756 (1.1756)  acc1: 76.9531 (76.9531)  acc5: 93.3594 (93.3594)  time: 7.9492  data: 7.7879  max mem: 31830
Test:  [8/9]  eta: 0:00:00  loss: 1.7225 (1.5597)  acc1: 68.0990 (69.2000)  acc5: 88.6719 (89.2160)  time: 0.9997  data: 0.8656  max mem: 31830
Test: Total time: 0:00:09 (1.0118 s / it)
* Acc@1 68.952 Acc@5 89.512 loss 1.566
Accuracy of the model on the 50000 test images: 69.0%
Max accuracy: 69.75%
Epoch: [155]  [  0/312]  eta: 1:06:20  lr: 0.002113  min_lr: 0.002113  loss: 3.8836 (3.8836)  weight_decay: 0.0500 (0.0500)  time: 12.7589  data: 9.8694  max mem: 31830
Epoch: [155]  [ 10/312]  eta: 0:09:15  lr: 0.002112  min_lr: 0.002112  loss: 3.8243 (3.7193)  weight_decay: 0.0500 (0.0500)  time: 1.8397  data: 0.9674  max mem: 31830
Epoch: [155]  [ 20/312]  eta: 0:05:44  lr: 0.002111  min_lr: 0.002111  loss: 3.7945 (3.7129)  weight_decay: 0.0500 (0.0500)  time: 0.6026  data: 0.0389  max mem: 31830
Epoch: [155]  [ 30/312]  eta: 0:04:21  lr: 0.002110  min_lr: 0.002110  loss: 3.7138 (3.6917)  weight_decay: 0.0500 (0.0500)  time: 0.4265  data: 0.0013  max mem: 31830
Epoch: [155]  [ 40/312]  eta: 0:03:37  lr: 0.002110  min_lr: 0.002110  loss: 3.8459 (3.7543)  weight_decay: 0.0500 (0.0500)  time: 0.3977  data: 0.0014  max mem: 31830
Epoch: [155]  [ 50/312]  eta: 0:03:08  lr: 0.002109  min_lr: 0.002109  loss: 3.8459 (3.7041)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0010  max mem: 31830
Epoch: [155]  [ 60/312]  eta: 0:02:48  lr: 0.002108  min_lr: 0.002108  loss: 3.6448 (3.6998)  weight_decay: 0.0500 (0.0500)  time: 0.4025  data: 0.0009  max mem: 31830
Epoch: [155]  [ 70/312]  eta: 0:02:34  lr: 0.002108  min_lr: 0.002108  loss: 3.6448 (3.6623)  weight_decay: 0.0500 (0.0500)  time: 0.4298  data: 0.0008  max mem: 31830
Epoch: [155]  [ 80/312]  eta: 0:02:27  lr: 0.002107  min_lr: 0.002107  loss: 3.8434 (3.7098)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0009  max mem: 31830
Epoch: [155]  [ 90/312]  eta: 0:02:16  lr: 0.002106  min_lr: 0.002106  loss: 3.7352 (3.7002)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0123  max mem: 31830
Epoch: [155]  [100/312]  eta: 0:02:09  lr: 0.002105  min_lr: 0.002105  loss: 3.6136 (3.6865)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0122  max mem: 31830
Epoch: [155]  [110/312]  eta: 0:02:00  lr: 0.002105  min_lr: 0.002105  loss: 3.5927 (3.6521)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0104  max mem: 31830
Epoch: [155]  [120/312]  eta: 0:01:54  lr: 0.002104  min_lr: 0.002104  loss: 3.7505 (3.6645)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0338  max mem: 31830
Epoch: [155]  [130/312]  eta: 0:01:49  lr: 0.002103  min_lr: 0.002103  loss: 3.8825 (3.6621)  weight_decay: 0.0500 (0.0500)  time: 0.6123  data: 0.0332  max mem: 31830
Epoch: [155]  [140/312]  eta: 0:01:41  lr: 0.002103  min_lr: 0.002103  loss: 3.4770 (3.6586)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0237  max mem: 31830
Epoch: [155]  [150/312]  eta: 0:01:35  lr: 0.002102  min_lr: 0.002102  loss: 3.6090 (3.6612)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0148  max mem: 31830
Epoch: [155]  [160/312]  eta: 0:01:29  lr: 0.002101  min_lr: 0.002101  loss: 3.5940 (3.6465)  weight_decay: 0.0500 (0.0500)  time: 0.6015  data: 0.0126  max mem: 31830
Epoch: [155]  [170/312]  eta: 0:01:23  lr: 0.002100  min_lr: 0.002100  loss: 3.4036 (3.6405)  weight_decay: 0.0500 (0.0500)  time: 0.5429  data: 0.0188  max mem: 31830
Epoch: [155]  [180/312]  eta: 0:01:17  lr: 0.002100  min_lr: 0.002100  loss: 3.3968 (3.6300)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0077  max mem: 31830
Epoch: [155]  [190/312]  eta: 0:01:10  lr: 0.002099  min_lr: 0.002099  loss: 3.2927 (3.6164)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0164  max mem: 31830
Epoch: [155]  [200/312]  eta: 0:01:04  lr: 0.002098  min_lr: 0.002098  loss: 3.7071 (3.6321)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0159  max mem: 31830
Epoch: [155]  [210/312]  eta: 0:00:59  lr: 0.002098  min_lr: 0.002098  loss: 3.7744 (3.6253)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0015  max mem: 31830
Epoch: [155]  [220/312]  eta: 0:00:52  lr: 0.002097  min_lr: 0.002097  loss: 3.5504 (3.6210)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0021  max mem: 31830
Epoch: [155]  [230/312]  eta: 0:00:47  lr: 0.002096  min_lr: 0.002096  loss: 3.6033 (3.6190)  weight_decay: 0.0500 (0.0500)  time: 0.5481  data: 0.0132  max mem: 31830
Epoch: [155]  [240/312]  eta: 0:00:41  lr: 0.002095  min_lr: 0.002095  loss: 3.7375 (3.6138)  weight_decay: 0.0500 (0.0500)  time: 0.6165  data: 0.0126  max mem: 31830
Epoch: [155]  [250/312]  eta: 0:00:35  lr: 0.002095  min_lr: 0.002095  loss: 3.7559 (3.6140)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0008  max mem: 31830
Epoch: [155]  [260/312]  eta: 0:00:29  lr: 0.002094  min_lr: 0.002094  loss: 3.8779 (3.6181)  weight_decay: 0.0500 (0.0500)  time: 0.5358  data: 0.0013  max mem: 31830
Epoch: [155]  [270/312]  eta: 0:00:23  lr: 0.002093  min_lr: 0.002093  loss: 3.8888 (3.6238)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0012  max mem: 31830
Epoch: [155]  [280/312]  eta: 0:00:18  lr: 0.002093  min_lr: 0.002093  loss: 3.5446 (3.6157)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0020  max mem: 31830
Epoch: [155]  [290/312]  eta: 0:00:12  lr: 0.002092  min_lr: 0.002092  loss: 3.5205 (3.6193)  weight_decay: 0.0500 (0.0500)  time: 0.5959  data: 0.0018  max mem: 31830
Epoch: [155]  [300/312]  eta: 0:00:06  lr: 0.002091  min_lr: 0.002091  loss: 3.5551 (3.6106)  weight_decay: 0.0500 (0.0500)  time: 0.4861  data: 0.0002  max mem: 31830
Epoch: [155]  [310/312]  eta: 0:00:01  lr: 0.002090  min_lr: 0.002090  loss: 3.5747 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [155]  [311/312]  eta: 0:00:00  lr: 0.002090  min_lr: 0.002090  loss: 3.2998 (3.6010)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [155] Total time: 0:02:55 (0.5627 s / it)
Averaged stats: lr: 0.002090  min_lr: 0.002090  loss: 3.2998 (3.5882)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.1677 (1.1677)  acc1: 76.9531 (76.9531)  acc5: 92.4479 (92.4479)  time: 8.8439  data: 8.6766  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5440 (1.3976)  acc1: 69.0104 (70.1920)  acc5: 88.9323 (89.4720)  time: 1.1000  data: 0.9641  max mem: 31830
Test: Total time: 0:00:10 (1.1333 s / it)
* Acc@1 70.038 Acc@5 89.964 loss 1.391
Accuracy of the model on the 50000 test images: 70.0%
Max accuracy: 70.04%
Epoch: [156]  [  0/312]  eta: 1:03:25  lr: 0.002090  min_lr: 0.002090  loss: 3.8754 (3.8754)  weight_decay: 0.0500 (0.0500)  time: 12.1982  data: 9.1094  max mem: 31830
Epoch: [156]  [ 10/312]  eta: 0:08:22  lr: 0.002089  min_lr: 0.002089  loss: 3.8288 (3.8804)  weight_decay: 0.0500 (0.0500)  time: 1.6645  data: 1.0342  max mem: 31830
Epoch: [156]  [ 20/312]  eta: 0:05:28  lr: 0.002089  min_lr: 0.002089  loss: 3.6451 (3.6939)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.1137  max mem: 31830
Epoch: [156]  [ 30/312]  eta: 0:04:10  lr: 0.002088  min_lr: 0.002088  loss: 3.2664 (3.5985)  weight_decay: 0.0500 (0.0500)  time: 0.4633  data: 0.0008  max mem: 31830
Epoch: [156]  [ 40/312]  eta: 0:03:29  lr: 0.002087  min_lr: 0.002087  loss: 3.2664 (3.5706)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0008  max mem: 31830
Epoch: [156]  [ 50/312]  eta: 0:03:05  lr: 0.002087  min_lr: 0.002087  loss: 3.4660 (3.5467)  weight_decay: 0.0500 (0.0500)  time: 0.4269  data: 0.0008  max mem: 31830
Epoch: [156]  [ 60/312]  eta: 0:02:45  lr: 0.002086  min_lr: 0.002086  loss: 3.5539 (3.5516)  weight_decay: 0.0500 (0.0500)  time: 0.4271  data: 0.0008  max mem: 31830
Epoch: [156]  [ 70/312]  eta: 0:02:38  lr: 0.002085  min_lr: 0.002085  loss: 3.6214 (3.5585)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0464  max mem: 31830
Epoch: [156]  [ 80/312]  eta: 0:02:28  lr: 0.002084  min_lr: 0.002084  loss: 3.7927 (3.5734)  weight_decay: 0.0500 (0.0500)  time: 0.5885  data: 0.0465  max mem: 31830
Epoch: [156]  [ 90/312]  eta: 0:02:17  lr: 0.002084  min_lr: 0.002084  loss: 3.8255 (3.6029)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0303  max mem: 31830
Epoch: [156]  [100/312]  eta: 0:02:11  lr: 0.002083  min_lr: 0.002083  loss: 3.6590 (3.5835)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0621  max mem: 31830
Epoch: [156]  [110/312]  eta: 0:02:00  lr: 0.002082  min_lr: 0.002082  loss: 3.6411 (3.5902)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0327  max mem: 31830
Epoch: [156]  [120/312]  eta: 0:01:54  lr: 0.002082  min_lr: 0.002082  loss: 3.6398 (3.5726)  weight_decay: 0.0500 (0.0500)  time: 0.5013  data: 0.0443  max mem: 31830
Epoch: [156]  [130/312]  eta: 0:01:49  lr: 0.002081  min_lr: 0.002081  loss: 3.7163 (3.5827)  weight_decay: 0.0500 (0.0500)  time: 0.6340  data: 0.0876  max mem: 31830
Epoch: [156]  [140/312]  eta: 0:01:42  lr: 0.002080  min_lr: 0.002080  loss: 3.8230 (3.5973)  weight_decay: 0.0500 (0.0500)  time: 0.5646  data: 0.0561  max mem: 31830
Epoch: [156]  [150/312]  eta: 0:01:37  lr: 0.002079  min_lr: 0.002079  loss: 3.6810 (3.5917)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.0587  max mem: 31830
Epoch: [156]  [160/312]  eta: 0:01:30  lr: 0.002079  min_lr: 0.002079  loss: 3.5649 (3.5780)  weight_decay: 0.0500 (0.0500)  time: 0.5977  data: 0.0467  max mem: 31830
Epoch: [156]  [170/312]  eta: 0:01:23  lr: 0.002078  min_lr: 0.002078  loss: 3.4050 (3.5612)  weight_decay: 0.0500 (0.0500)  time: 0.4721  data: 0.0165  max mem: 31830
Epoch: [156]  [180/312]  eta: 0:01:17  lr: 0.002077  min_lr: 0.002077  loss: 3.5065 (3.5585)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0419  max mem: 31830
Epoch: [156]  [190/312]  eta: 0:01:10  lr: 0.002077  min_lr: 0.002077  loss: 3.5253 (3.5581)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0277  max mem: 31830
Epoch: [156]  [200/312]  eta: 0:01:04  lr: 0.002076  min_lr: 0.002076  loss: 3.5286 (3.5567)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0168  max mem: 31830
Epoch: [156]  [210/312]  eta: 0:00:59  lr: 0.002075  min_lr: 0.002075  loss: 3.7054 (3.5712)  weight_decay: 0.0500 (0.0500)  time: 0.5970  data: 0.0333  max mem: 31830
Epoch: [156]  [220/312]  eta: 0:00:52  lr: 0.002074  min_lr: 0.002074  loss: 3.8585 (3.5817)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0186  max mem: 31830
Epoch: [156]  [230/312]  eta: 0:00:47  lr: 0.002074  min_lr: 0.002074  loss: 3.8585 (3.5870)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0010  max mem: 31830
Epoch: [156]  [240/312]  eta: 0:00:41  lr: 0.002073  min_lr: 0.002073  loss: 3.8630 (3.5988)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0011  max mem: 31830
Epoch: [156]  [250/312]  eta: 0:00:35  lr: 0.002072  min_lr: 0.002072  loss: 3.8882 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0135  max mem: 31830
Epoch: [156]  [260/312]  eta: 0:00:29  lr: 0.002072  min_lr: 0.002072  loss: 3.5600 (3.6036)  weight_decay: 0.0500 (0.0500)  time: 0.5790  data: 0.0133  max mem: 31830
Epoch: [156]  [270/312]  eta: 0:00:23  lr: 0.002071  min_lr: 0.002071  loss: 3.7832 (3.6107)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0007  max mem: 31830
Epoch: [156]  [280/312]  eta: 0:00:18  lr: 0.002070  min_lr: 0.002070  loss: 3.7026 (3.5972)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0020  max mem: 31830
Epoch: [156]  [290/312]  eta: 0:00:12  lr: 0.002069  min_lr: 0.002069  loss: 3.5089 (3.6003)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0018  max mem: 31830
Epoch: [156]  [300/312]  eta: 0:00:06  lr: 0.002069  min_lr: 0.002069  loss: 3.7577 (3.6022)  weight_decay: 0.0500 (0.0500)  time: 0.4610  data: 0.0002  max mem: 31830
Epoch: [156]  [310/312]  eta: 0:00:01  lr: 0.002068  min_lr: 0.002068  loss: 3.8020 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.4193  data: 0.0001  max mem: 31830
Epoch: [156]  [311/312]  eta: 0:00:00  lr: 0.002068  min_lr: 0.002068  loss: 3.8530 (3.6117)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [156] Total time: 0:02:55 (0.5613 s / it)
Averaged stats: lr: 0.002068  min_lr: 0.002068  loss: 3.8530 (3.5705)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.6738 (1.6738)  acc1: 74.8698 (74.8698)  acc5: 92.7083 (92.7083)  time: 8.5000  data: 8.3324  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8675 (1.7889)  acc1: 67.9688 (68.9600)  acc5: 89.3229 (89.5840)  time: 1.0677  data: 0.9259  max mem: 31830
Test: Total time: 0:00:09 (1.0778 s / it)
* Acc@1 69.214 Acc@5 89.474 loss 1.802
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 70.04%
Epoch: [157]  [  0/312]  eta: 1:03:05  lr: 0.002068  min_lr: 0.002068  loss: 3.9783 (3.9783)  weight_decay: 0.0500 (0.0500)  time: 12.1326  data: 8.4065  max mem: 31830
Epoch: [157]  [ 10/312]  eta: 0:08:37  lr: 0.002067  min_lr: 0.002067  loss: 3.7872 (3.4736)  weight_decay: 0.0500 (0.0500)  time: 1.7149  data: 1.0264  max mem: 31830
Epoch: [157]  [ 20/312]  eta: 0:05:33  lr: 0.002066  min_lr: 0.002066  loss: 3.3099 (3.4712)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.1445  max mem: 31830
Epoch: [157]  [ 30/312]  eta: 0:04:14  lr: 0.002066  min_lr: 0.002066  loss: 3.8048 (3.6113)  weight_decay: 0.0500 (0.0500)  time: 0.4550  data: 0.0006  max mem: 31830
Epoch: [157]  [ 40/312]  eta: 0:03:31  lr: 0.002065  min_lr: 0.002065  loss: 3.8338 (3.5934)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0006  max mem: 31830
Epoch: [157]  [ 50/312]  eta: 0:03:04  lr: 0.002064  min_lr: 0.002064  loss: 3.5154 (3.5531)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0007  max mem: 31830
Epoch: [157]  [ 60/312]  eta: 0:02:44  lr: 0.002063  min_lr: 0.002063  loss: 3.4884 (3.5314)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0008  max mem: 31830
Epoch: [157]  [ 70/312]  eta: 0:02:39  lr: 0.002063  min_lr: 0.002063  loss: 3.6405 (3.5583)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0010  max mem: 31830
Epoch: [157]  [ 80/312]  eta: 0:02:29  lr: 0.002062  min_lr: 0.002062  loss: 3.7223 (3.5608)  weight_decay: 0.0500 (0.0500)  time: 0.6123  data: 0.0018  max mem: 31830
Epoch: [157]  [ 90/312]  eta: 0:02:17  lr: 0.002061  min_lr: 0.002061  loss: 3.6425 (3.5375)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0016  max mem: 31830
Epoch: [157]  [100/312]  eta: 0:02:11  lr: 0.002061  min_lr: 0.002061  loss: 3.4565 (3.5445)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0011  max mem: 31830
Epoch: [157]  [110/312]  eta: 0:02:01  lr: 0.002060  min_lr: 0.002060  loss: 3.6835 (3.5717)  weight_decay: 0.0500 (0.0500)  time: 0.5414  data: 0.0012  max mem: 31830
Epoch: [157]  [120/312]  eta: 0:01:56  lr: 0.002059  min_lr: 0.002059  loss: 3.7315 (3.5701)  weight_decay: 0.0500 (0.0500)  time: 0.5184  data: 0.0015  max mem: 31830
Epoch: [157]  [130/312]  eta: 0:01:50  lr: 0.002058  min_lr: 0.002058  loss: 3.7315 (3.5878)  weight_decay: 0.0500 (0.0500)  time: 0.6166  data: 0.0014  max mem: 31830
Epoch: [157]  [140/312]  eta: 0:01:41  lr: 0.002058  min_lr: 0.002058  loss: 3.6728 (3.5659)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.0009  max mem: 31830
Epoch: [157]  [150/312]  eta: 0:01:36  lr: 0.002057  min_lr: 0.002057  loss: 3.5314 (3.5612)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0011  max mem: 31830
Epoch: [157]  [160/312]  eta: 0:01:29  lr: 0.002056  min_lr: 0.002056  loss: 3.5830 (3.5592)  weight_decay: 0.0500 (0.0500)  time: 0.5883  data: 0.0011  max mem: 31830
Epoch: [157]  [170/312]  eta: 0:01:23  lr: 0.002056  min_lr: 0.002056  loss: 3.7780 (3.5566)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0187  max mem: 31830
Epoch: [157]  [180/312]  eta: 0:01:17  lr: 0.002055  min_lr: 0.002055  loss: 3.7780 (3.5656)  weight_decay: 0.0500 (0.0500)  time: 0.5508  data: 0.0190  max mem: 31830
Epoch: [157]  [190/312]  eta: 0:01:10  lr: 0.002054  min_lr: 0.002054  loss: 3.6601 (3.5701)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0012  max mem: 31830
Epoch: [157]  [200/312]  eta: 0:01:05  lr: 0.002053  min_lr: 0.002053  loss: 3.7662 (3.5749)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0009  max mem: 31830
Epoch: [157]  [210/312]  eta: 0:00:59  lr: 0.002053  min_lr: 0.002053  loss: 3.8220 (3.5854)  weight_decay: 0.0500 (0.0500)  time: 0.6225  data: 0.0016  max mem: 31830
Epoch: [157]  [220/312]  eta: 0:00:52  lr: 0.002052  min_lr: 0.002052  loss: 3.7782 (3.5844)  weight_decay: 0.0500 (0.0500)  time: 0.4955  data: 0.0018  max mem: 31830
Epoch: [157]  [230/312]  eta: 0:00:47  lr: 0.002051  min_lr: 0.002051  loss: 3.8581 (3.5930)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0073  max mem: 31830
Epoch: [157]  [240/312]  eta: 0:00:41  lr: 0.002051  min_lr: 0.002051  loss: 3.8437 (3.5986)  weight_decay: 0.0500 (0.0500)  time: 0.5835  data: 0.0071  max mem: 31830
Epoch: [157]  [250/312]  eta: 0:00:35  lr: 0.002050  min_lr: 0.002050  loss: 3.6778 (3.5950)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0007  max mem: 31830
Epoch: [157]  [260/312]  eta: 0:00:29  lr: 0.002049  min_lr: 0.002049  loss: 3.4762 (3.5835)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0007  max mem: 31830
Epoch: [157]  [270/312]  eta: 0:00:23  lr: 0.002048  min_lr: 0.002048  loss: 3.4762 (3.5799)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0013  max mem: 31830
Epoch: [157]  [280/312]  eta: 0:00:18  lr: 0.002048  min_lr: 0.002048  loss: 3.6126 (3.5857)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0026  max mem: 31830
Epoch: [157]  [290/312]  eta: 0:00:12  lr: 0.002047  min_lr: 0.002047  loss: 3.7202 (3.5939)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.0123  max mem: 31830
Epoch: [157]  [300/312]  eta: 0:00:06  lr: 0.002046  min_lr: 0.002046  loss: 3.8175 (3.5885)  weight_decay: 0.0500 (0.0500)  time: 0.4645  data: 0.0107  max mem: 31830
Epoch: [157]  [310/312]  eta: 0:00:01  lr: 0.002046  min_lr: 0.002046  loss: 3.7940 (3.5894)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [157]  [311/312]  eta: 0:00:00  lr: 0.002045  min_lr: 0.002045  loss: 3.7722 (3.5889)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [157] Total time: 0:02:54 (0.5586 s / it)
Averaged stats: lr: 0.002045  min_lr: 0.002045  loss: 3.7722 (3.5779)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.3683 (1.3683)  acc1: 76.1719 (76.1719)  acc5: 91.7969 (91.7969)  time: 8.7748  data: 8.6085  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.8438 (1.6947)  acc1: 66.2760 (68.2400)  acc5: 88.9323 (88.7520)  time: 1.0917  data: 0.9566  max mem: 31830
Test: Total time: 0:00:09 (1.1070 s / it)
* Acc@1 68.200 Acc@5 89.018 loss 1.693
Accuracy of the model on the 50000 test images: 68.2%
Max accuracy: 70.04%
Epoch: [158]  [  0/312]  eta: 1:03:20  lr: 0.002045  min_lr: 0.002045  loss: 4.2067 (4.2067)  weight_decay: 0.0500 (0.0500)  time: 12.1820  data: 11.7901  max mem: 31830
Epoch: [158]  [ 10/312]  eta: 0:09:04  lr: 0.002045  min_lr: 0.002045  loss: 3.6689 (3.8211)  weight_decay: 0.0500 (0.0500)  time: 1.8024  data: 1.0723  max mem: 31830
Epoch: [158]  [ 20/312]  eta: 0:05:37  lr: 0.002044  min_lr: 0.002044  loss: 3.4137 (3.5514)  weight_decay: 0.0500 (0.0500)  time: 0.6045  data: 0.0014  max mem: 31830
Epoch: [158]  [ 30/312]  eta: 0:04:17  lr: 0.002043  min_lr: 0.002043  loss: 3.2287 (3.5037)  weight_decay: 0.0500 (0.0500)  time: 0.4215  data: 0.0015  max mem: 31830
Epoch: [158]  [ 40/312]  eta: 0:03:33  lr: 0.002042  min_lr: 0.002042  loss: 3.5530 (3.5311)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0008  max mem: 31830
Epoch: [158]  [ 50/312]  eta: 0:03:05  lr: 0.002042  min_lr: 0.002042  loss: 3.7364 (3.5835)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0008  max mem: 31830
Epoch: [158]  [ 60/312]  eta: 0:02:46  lr: 0.002041  min_lr: 0.002041  loss: 3.8080 (3.6111)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0009  max mem: 31830
Epoch: [158]  [ 70/312]  eta: 0:02:32  lr: 0.002040  min_lr: 0.002040  loss: 3.7939 (3.6210)  weight_decay: 0.0500 (0.0500)  time: 0.4298  data: 0.0012  max mem: 31830
Epoch: [158]  [ 80/312]  eta: 0:02:25  lr: 0.002040  min_lr: 0.002040  loss: 3.8032 (3.6434)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0527  max mem: 31830
Epoch: [158]  [ 90/312]  eta: 0:02:13  lr: 0.002039  min_lr: 0.002039  loss: 3.8186 (3.6476)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0523  max mem: 31830
Epoch: [158]  [100/312]  eta: 0:02:08  lr: 0.002038  min_lr: 0.002038  loss: 3.8423 (3.6766)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0511  max mem: 31830
Epoch: [158]  [110/312]  eta: 0:02:00  lr: 0.002037  min_lr: 0.002037  loss: 3.8019 (3.6678)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0512  max mem: 31830
Epoch: [158]  [120/312]  eta: 0:01:54  lr: 0.002037  min_lr: 0.002037  loss: 3.6757 (3.6527)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0386  max mem: 31830
Epoch: [158]  [130/312]  eta: 0:01:49  lr: 0.002036  min_lr: 0.002036  loss: 3.6757 (3.6417)  weight_decay: 0.0500 (0.0500)  time: 0.6396  data: 0.0624  max mem: 31830
Epoch: [158]  [140/312]  eta: 0:01:41  lr: 0.002035  min_lr: 0.002035  loss: 3.5354 (3.6311)  weight_decay: 0.0500 (0.0500)  time: 0.5402  data: 0.0247  max mem: 31830
Epoch: [158]  [150/312]  eta: 0:01:35  lr: 0.002035  min_lr: 0.002035  loss: 3.5702 (3.6282)  weight_decay: 0.0500 (0.0500)  time: 0.5162  data: 0.0141  max mem: 31830
Epoch: [158]  [160/312]  eta: 0:01:28  lr: 0.002034  min_lr: 0.002034  loss: 3.7298 (3.6379)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0142  max mem: 31830
Epoch: [158]  [170/312]  eta: 0:01:22  lr: 0.002033  min_lr: 0.002033  loss: 3.6712 (3.6353)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0016  max mem: 31830
Epoch: [158]  [180/312]  eta: 0:01:17  lr: 0.002032  min_lr: 0.002032  loss: 3.6288 (3.6242)  weight_decay: 0.0500 (0.0500)  time: 0.6556  data: 0.0078  max mem: 31830
Epoch: [158]  [190/312]  eta: 0:01:10  lr: 0.002032  min_lr: 0.002032  loss: 3.6811 (3.6121)  weight_decay: 0.0500 (0.0500)  time: 0.5549  data: 0.0080  max mem: 31830
Epoch: [158]  [200/312]  eta: 0:01:05  lr: 0.002031  min_lr: 0.002031  loss: 3.5117 (3.6054)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0074  max mem: 31830
Epoch: [158]  [210/312]  eta: 0:00:59  lr: 0.002030  min_lr: 0.002030  loss: 3.6212 (3.6045)  weight_decay: 0.0500 (0.0500)  time: 0.6601  data: 0.0065  max mem: 31830
Epoch: [158]  [220/312]  eta: 0:00:53  lr: 0.002030  min_lr: 0.002030  loss: 3.7585 (3.6113)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0010  max mem: 31830
Epoch: [158]  [230/312]  eta: 0:00:47  lr: 0.002029  min_lr: 0.002029  loss: 3.8015 (3.6040)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0011  max mem: 31830
Epoch: [158]  [240/312]  eta: 0:00:41  lr: 0.002028  min_lr: 0.002028  loss: 3.2815 (3.5936)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0011  max mem: 31830
Epoch: [158]  [250/312]  eta: 0:00:35  lr: 0.002027  min_lr: 0.002027  loss: 3.6519 (3.5927)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0008  max mem: 31830
Epoch: [158]  [260/312]  eta: 0:00:30  lr: 0.002027  min_lr: 0.002027  loss: 3.8053 (3.5879)  weight_decay: 0.0500 (0.0500)  time: 0.6499  data: 0.0061  max mem: 31830
Epoch: [158]  [270/312]  eta: 0:00:24  lr: 0.002026  min_lr: 0.002026  loss: 3.5682 (3.5812)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0060  max mem: 31830
Epoch: [158]  [280/312]  eta: 0:00:18  lr: 0.002025  min_lr: 0.002025  loss: 3.6626 (3.5829)  weight_decay: 0.0500 (0.0500)  time: 0.5429  data: 0.0079  max mem: 31830
Epoch: [158]  [290/312]  eta: 0:00:12  lr: 0.002025  min_lr: 0.002025  loss: 3.6599 (3.5774)  weight_decay: 0.0500 (0.0500)  time: 0.5753  data: 0.0213  max mem: 31830
Epoch: [158]  [300/312]  eta: 0:00:06  lr: 0.002024  min_lr: 0.002024  loss: 3.5283 (3.5821)  weight_decay: 0.0500 (0.0500)  time: 0.4226  data: 0.0138  max mem: 31830
Epoch: [158]  [310/312]  eta: 0:00:01  lr: 0.002023  min_lr: 0.002023  loss: 3.4612 (3.5748)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [158]  [311/312]  eta: 0:00:00  lr: 0.002023  min_lr: 0.002023  loss: 3.4612 (3.5756)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [158] Total time: 0:02:55 (0.5640 s / it)
Averaged stats: lr: 0.002023  min_lr: 0.002023  loss: 3.4612 (3.5516)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.3191 (1.3191)  acc1: 75.6510 (75.6510)  acc5: 92.5781 (92.5781)  time: 8.4302  data: 8.2625  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5035 (1.4321)  acc1: 67.8385 (69.5520)  acc5: 89.1927 (89.6640)  time: 1.0539  data: 0.9181  max mem: 31830
Test: Total time: 0:00:09 (1.0650 s / it)
* Acc@1 69.412 Acc@5 89.578 loss 1.433
Accuracy of the model on the 50000 test images: 69.4%
Max accuracy: 70.04%
Epoch: [159]  [  0/312]  eta: 1:00:08  lr: 0.002023  min_lr: 0.002023  loss: 4.2735 (4.2735)  weight_decay: 0.0500 (0.0500)  time: 11.5646  data: 8.6751  max mem: 31830
Epoch: [159]  [ 10/312]  eta: 0:07:57  lr: 0.002022  min_lr: 0.002022  loss: 3.7277 (3.5981)  weight_decay: 0.0500 (0.0500)  time: 1.5799  data: 0.9664  max mem: 31830
Epoch: [159]  [ 20/312]  eta: 0:05:22  lr: 0.002021  min_lr: 0.002021  loss: 3.6511 (3.5384)  weight_decay: 0.0500 (0.0500)  time: 0.5810  data: 0.1157  max mem: 31830
Epoch: [159]  [ 30/312]  eta: 0:04:06  lr: 0.002021  min_lr: 0.002021  loss: 3.4195 (3.4969)  weight_decay: 0.0500 (0.0500)  time: 0.4884  data: 0.0184  max mem: 31830
Epoch: [159]  [ 40/312]  eta: 0:03:30  lr: 0.002020  min_lr: 0.002020  loss: 3.8436 (3.5349)  weight_decay: 0.0500 (0.0500)  time: 0.4265  data: 0.0010  max mem: 31830
Epoch: [159]  [ 50/312]  eta: 0:03:10  lr: 0.002019  min_lr: 0.002019  loss: 3.8436 (3.5372)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0012  max mem: 31830
Epoch: [159]  [ 60/312]  eta: 0:02:50  lr: 0.002019  min_lr: 0.002019  loss: 3.6624 (3.5109)  weight_decay: 0.0500 (0.0500)  time: 0.4837  data: 0.0011  max mem: 31830
Epoch: [159]  [ 70/312]  eta: 0:02:39  lr: 0.002018  min_lr: 0.002018  loss: 3.6344 (3.5216)  weight_decay: 0.0500 (0.0500)  time: 0.4822  data: 0.0014  max mem: 31830
Epoch: [159]  [ 80/312]  eta: 0:02:31  lr: 0.002017  min_lr: 0.002017  loss: 3.6613 (3.5509)  weight_decay: 0.0500 (0.0500)  time: 0.5782  data: 0.0151  max mem: 31830
Epoch: [159]  [ 90/312]  eta: 0:02:20  lr: 0.002016  min_lr: 0.002016  loss: 3.6986 (3.5427)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.0145  max mem: 31830
Epoch: [159]  [100/312]  eta: 0:02:13  lr: 0.002016  min_lr: 0.002016  loss: 3.4442 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0144  max mem: 31830
Epoch: [159]  [110/312]  eta: 0:02:02  lr: 0.002015  min_lr: 0.002015  loss: 3.1934 (3.5088)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0143  max mem: 31830
Epoch: [159]  [120/312]  eta: 0:01:56  lr: 0.002014  min_lr: 0.002014  loss: 3.3045 (3.5097)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0009  max mem: 31830
Epoch: [159]  [130/312]  eta: 0:01:50  lr: 0.002014  min_lr: 0.002014  loss: 3.7376 (3.5348)  weight_decay: 0.0500 (0.0500)  time: 0.5982  data: 0.0069  max mem: 31830
Epoch: [159]  [140/312]  eta: 0:01:42  lr: 0.002013  min_lr: 0.002013  loss: 3.7376 (3.5323)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0072  max mem: 31830
Epoch: [159]  [150/312]  eta: 0:01:37  lr: 0.002012  min_lr: 0.002012  loss: 3.3148 (3.5190)  weight_decay: 0.0500 (0.0500)  time: 0.5663  data: 0.0017  max mem: 31830
Epoch: [159]  [160/312]  eta: 0:01:30  lr: 0.002011  min_lr: 0.002011  loss: 3.5807 (3.5377)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0012  max mem: 31830
Epoch: [159]  [170/312]  eta: 0:01:23  lr: 0.002011  min_lr: 0.002011  loss: 3.7847 (3.5254)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0016  max mem: 31830
Epoch: [159]  [180/312]  eta: 0:01:17  lr: 0.002010  min_lr: 0.002010  loss: 3.7385 (3.5345)  weight_decay: 0.0500 (0.0500)  time: 0.5713  data: 0.0016  max mem: 31830
Epoch: [159]  [190/312]  eta: 0:01:10  lr: 0.002009  min_lr: 0.002009  loss: 3.7770 (3.5358)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0007  max mem: 31830
Epoch: [159]  [200/312]  eta: 0:01:05  lr: 0.002009  min_lr: 0.002009  loss: 3.7770 (3.5409)  weight_decay: 0.0500 (0.0500)  time: 0.5280  data: 0.0008  max mem: 31830
Epoch: [159]  [210/312]  eta: 0:00:59  lr: 0.002008  min_lr: 0.002008  loss: 3.8390 (3.5510)  weight_decay: 0.0500 (0.0500)  time: 0.6146  data: 0.0241  max mem: 31830
Epoch: [159]  [220/312]  eta: 0:00:52  lr: 0.002007  min_lr: 0.002007  loss: 3.8390 (3.5556)  weight_decay: 0.0500 (0.0500)  time: 0.4847  data: 0.0240  max mem: 31830
Epoch: [159]  [230/312]  eta: 0:00:47  lr: 0.002006  min_lr: 0.002006  loss: 3.6013 (3.5542)  weight_decay: 0.0500 (0.0500)  time: 0.4707  data: 0.0135  max mem: 31830
Epoch: [159]  [240/312]  eta: 0:00:41  lr: 0.002006  min_lr: 0.002006  loss: 3.5861 (3.5530)  weight_decay: 0.0500 (0.0500)  time: 0.5900  data: 0.0138  max mem: 31830
Epoch: [159]  [250/312]  eta: 0:00:35  lr: 0.002005  min_lr: 0.002005  loss: 3.4964 (3.5425)  weight_decay: 0.0500 (0.0500)  time: 0.5411  data: 0.0277  max mem: 31830
Epoch: [159]  [260/312]  eta: 0:00:29  lr: 0.002004  min_lr: 0.002004  loss: 3.6358 (3.5515)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0275  max mem: 31830
Epoch: [159]  [270/312]  eta: 0:00:23  lr: 0.002004  min_lr: 0.002004  loss: 3.7566 (3.5617)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0008  max mem: 31830
Epoch: [159]  [280/312]  eta: 0:00:18  lr: 0.002003  min_lr: 0.002003  loss: 3.7219 (3.5624)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0019  max mem: 31830
Epoch: [159]  [290/312]  eta: 0:00:12  lr: 0.002002  min_lr: 0.002002  loss: 3.7867 (3.5690)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0017  max mem: 31830
Epoch: [159]  [300/312]  eta: 0:00:06  lr: 0.002001  min_lr: 0.002001  loss: 3.8337 (3.5721)  weight_decay: 0.0500 (0.0500)  time: 0.4544  data: 0.0002  max mem: 31830
Epoch: [159]  [310/312]  eta: 0:00:01  lr: 0.002001  min_lr: 0.002001  loss: 3.8495 (3.5795)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [159]  [311/312]  eta: 0:00:00  lr: 0.002001  min_lr: 0.002001  loss: 3.8337 (3.5770)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [159] Total time: 0:02:54 (0.5588 s / it)
Averaged stats: lr: 0.002001  min_lr: 0.002001  loss: 3.8337 (3.5739)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.5723 (1.5723)  acc1: 74.7396 (74.7396)  acc5: 92.0573 (92.0573)  time: 8.8375  data: 8.6738  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7623 (1.6733)  acc1: 67.5781 (68.6720)  acc5: 89.3229 (89.4080)  time: 1.0994  data: 0.9638  max mem: 31830
Test: Total time: 0:00:10 (1.1330 s / it)
* Acc@1 68.920 Acc@5 89.154 loss 1.672
Accuracy of the model on the 50000 test images: 68.9%
Max accuracy: 70.04%
Epoch: [160]  [  0/312]  eta: 1:02:44  lr: 0.002001  min_lr: 0.002001  loss: 3.0919 (3.0919)  weight_decay: 0.0500 (0.0500)  time: 12.0666  data: 11.4776  max mem: 31830
Epoch: [160]  [ 10/312]  eta: 0:08:09  lr: 0.002000  min_lr: 0.002000  loss: 3.6625 (3.7300)  weight_decay: 0.0500 (0.0500)  time: 1.6195  data: 1.0439  max mem: 31830
Epoch: [160]  [ 20/312]  eta: 0:05:35  lr: 0.001999  min_lr: 0.001999  loss: 3.8507 (3.8191)  weight_decay: 0.0500 (0.0500)  time: 0.6016  data: 0.0403  max mem: 31830
Epoch: [160]  [ 30/312]  eta: 0:04:15  lr: 0.001998  min_lr: 0.001998  loss: 3.9519 (3.8028)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0405  max mem: 31830
Epoch: [160]  [ 40/312]  eta: 0:03:37  lr: 0.001998  min_lr: 0.001998  loss: 3.7870 (3.7064)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0009  max mem: 31830
Epoch: [160]  [ 50/312]  eta: 0:03:17  lr: 0.001997  min_lr: 0.001997  loss: 3.3951 (3.6283)  weight_decay: 0.0500 (0.0500)  time: 0.5161  data: 0.0008  max mem: 31830
Epoch: [160]  [ 60/312]  eta: 0:02:54  lr: 0.001996  min_lr: 0.001996  loss: 3.5978 (3.6605)  weight_decay: 0.0500 (0.0500)  time: 0.4724  data: 0.0012  max mem: 31830
Epoch: [160]  [ 70/312]  eta: 0:02:44  lr: 0.001995  min_lr: 0.001995  loss: 3.8122 (3.6770)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0218  max mem: 31830
Epoch: [160]  [ 80/312]  eta: 0:02:32  lr: 0.001995  min_lr: 0.001995  loss: 3.6430 (3.6262)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0212  max mem: 31830
Epoch: [160]  [ 90/312]  eta: 0:02:22  lr: 0.001994  min_lr: 0.001994  loss: 3.3173 (3.5958)  weight_decay: 0.0500 (0.0500)  time: 0.5043  data: 0.0547  max mem: 31830
Epoch: [160]  [100/312]  eta: 0:02:15  lr: 0.001993  min_lr: 0.001993  loss: 3.3641 (3.5726)  weight_decay: 0.0500 (0.0500)  time: 0.5775  data: 0.1088  max mem: 31830
Epoch: [160]  [110/312]  eta: 0:02:04  lr: 0.001993  min_lr: 0.001993  loss: 3.5588 (3.5816)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0553  max mem: 31830
Epoch: [160]  [120/312]  eta: 0:01:58  lr: 0.001992  min_lr: 0.001992  loss: 3.5376 (3.5432)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0635  max mem: 31830
Epoch: [160]  [130/312]  eta: 0:01:51  lr: 0.001991  min_lr: 0.001991  loss: 3.5376 (3.5501)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.0638  max mem: 31830
Epoch: [160]  [140/312]  eta: 0:01:44  lr: 0.001990  min_lr: 0.001990  loss: 3.8567 (3.5647)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0496  max mem: 31830
Epoch: [160]  [150/312]  eta: 0:01:38  lr: 0.001990  min_lr: 0.001990  loss: 3.8359 (3.5809)  weight_decay: 0.0500 (0.0500)  time: 0.5537  data: 0.0912  max mem: 31830
Epoch: [160]  [160/312]  eta: 0:01:30  lr: 0.001989  min_lr: 0.001989  loss: 3.7582 (3.5822)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0487  max mem: 31830
Epoch: [160]  [170/312]  eta: 0:01:24  lr: 0.001988  min_lr: 0.001988  loss: 3.6474 (3.5779)  weight_decay: 0.0500 (0.0500)  time: 0.4874  data: 0.0412  max mem: 31830
Epoch: [160]  [180/312]  eta: 0:01:18  lr: 0.001988  min_lr: 0.001988  loss: 3.6474 (3.5761)  weight_decay: 0.0500 (0.0500)  time: 0.6058  data: 0.1217  max mem: 31830
Epoch: [160]  [190/312]  eta: 0:01:11  lr: 0.001987  min_lr: 0.001987  loss: 3.4725 (3.5546)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0869  max mem: 31830
Epoch: [160]  [200/312]  eta: 0:01:05  lr: 0.001986  min_lr: 0.001986  loss: 3.5806 (3.5624)  weight_decay: 0.0500 (0.0500)  time: 0.4836  data: 0.0516  max mem: 31830
Epoch: [160]  [210/312]  eta: 0:00:59  lr: 0.001985  min_lr: 0.001985  loss: 3.4903 (3.5439)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0516  max mem: 31830
Epoch: [160]  [220/312]  eta: 0:00:53  lr: 0.001985  min_lr: 0.001985  loss: 3.2723 (3.5436)  weight_decay: 0.0500 (0.0500)  time: 0.5128  data: 0.0659  max mem: 31830
Epoch: [160]  [230/312]  eta: 0:00:47  lr: 0.001984  min_lr: 0.001984  loss: 3.6183 (3.5404)  weight_decay: 0.0500 (0.0500)  time: 0.5775  data: 0.1407  max mem: 31830
Epoch: [160]  [240/312]  eta: 0:00:41  lr: 0.001983  min_lr: 0.001983  loss: 3.7477 (3.5449)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0754  max mem: 31830
Epoch: [160]  [250/312]  eta: 0:00:35  lr: 0.001983  min_lr: 0.001983  loss: 3.7715 (3.5452)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0612  max mem: 31830
Epoch: [160]  [260/312]  eta: 0:00:30  lr: 0.001982  min_lr: 0.001982  loss: 3.4524 (3.5426)  weight_decay: 0.0500 (0.0500)  time: 0.6191  data: 0.1279  max mem: 31830
Epoch: [160]  [270/312]  eta: 0:00:23  lr: 0.001981  min_lr: 0.001981  loss: 3.4608 (3.5494)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0673  max mem: 31830
Epoch: [160]  [280/312]  eta: 0:00:18  lr: 0.001980  min_lr: 0.001980  loss: 3.7725 (3.5466)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0552  max mem: 31830
Epoch: [160]  [290/312]  eta: 0:00:12  lr: 0.001980  min_lr: 0.001980  loss: 3.7725 (3.5541)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0725  max mem: 31830
Epoch: [160]  [300/312]  eta: 0:00:06  lr: 0.001979  min_lr: 0.001979  loss: 3.6828 (3.5527)  weight_decay: 0.0500 (0.0500)  time: 0.4498  data: 0.0401  max mem: 31830
Epoch: [160]  [310/312]  eta: 0:00:01  lr: 0.001978  min_lr: 0.001978  loss: 3.5745 (3.5526)  weight_decay: 0.0500 (0.0500)  time: 0.4028  data: 0.0225  max mem: 31830
Epoch: [160]  [311/312]  eta: 0:00:00  lr: 0.001978  min_lr: 0.001978  loss: 3.5745 (3.5536)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [160] Total time: 0:02:55 (0.5610 s / it)
Averaged stats: lr: 0.001978  min_lr: 0.001978  loss: 3.5745 (3.5493)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.2100 (1.2100)  acc1: 77.2135 (77.2135)  acc5: 92.9688 (92.9688)  time: 8.6915  data: 8.5238  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5377 (1.4303)  acc1: 68.7500 (70.0000)  acc5: 89.3229 (89.8880)  time: 1.0844  data: 0.9472  max mem: 31830
Test: Total time: 0:00:09 (1.0958 s / it)
* Acc@1 69.962 Acc@5 89.928 loss 1.434
Accuracy of the model on the 50000 test images: 70.0%
Max accuracy: 70.04%
Epoch: [161]  [  0/312]  eta: 1:07:19  lr: 0.001978  min_lr: 0.001978  loss: 3.2194 (3.2194)  weight_decay: 0.0500 (0.0500)  time: 12.9464  data: 12.5494  max mem: 31830
Epoch: [161]  [ 10/312]  eta: 0:09:33  lr: 0.001977  min_lr: 0.001977  loss: 3.7599 (3.4831)  weight_decay: 0.0500 (0.0500)  time: 1.9005  data: 1.1429  max mem: 31830
Epoch: [161]  [ 20/312]  eta: 0:05:52  lr: 0.001977  min_lr: 0.001977  loss: 3.7655 (3.5073)  weight_decay: 0.0500 (0.0500)  time: 0.6213  data: 0.0141  max mem: 31830
Epoch: [161]  [ 30/312]  eta: 0:04:27  lr: 0.001976  min_lr: 0.001976  loss: 3.6199 (3.5029)  weight_decay: 0.0500 (0.0500)  time: 0.4228  data: 0.0137  max mem: 31830
Epoch: [161]  [ 40/312]  eta: 0:03:41  lr: 0.001975  min_lr: 0.001975  loss: 3.6199 (3.5488)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0015  max mem: 31830
Epoch: [161]  [ 50/312]  eta: 0:03:11  lr: 0.001974  min_lr: 0.001974  loss: 3.6775 (3.5410)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0022  max mem: 31830
Epoch: [161]  [ 60/312]  eta: 0:02:50  lr: 0.001974  min_lr: 0.001974  loss: 3.7161 (3.5750)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0021  max mem: 31830
Epoch: [161]  [ 70/312]  eta: 0:02:34  lr: 0.001973  min_lr: 0.001973  loss: 3.6424 (3.5497)  weight_decay: 0.0500 (0.0500)  time: 0.3946  data: 0.0014  max mem: 31830
Epoch: [161]  [ 80/312]  eta: 0:02:23  lr: 0.001972  min_lr: 0.001972  loss: 3.1542 (3.5265)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0217  max mem: 31830
Epoch: [161]  [ 90/312]  eta: 0:02:15  lr: 0.001972  min_lr: 0.001972  loss: 3.1428 (3.5154)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0459  max mem: 31830
Epoch: [161]  [100/312]  eta: 0:02:09  lr: 0.001971  min_lr: 0.001971  loss: 3.6038 (3.5381)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.0506  max mem: 31830
Epoch: [161]  [110/312]  eta: 0:02:01  lr: 0.001970  min_lr: 0.001970  loss: 3.8130 (3.5536)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0800  max mem: 31830
Epoch: [161]  [120/312]  eta: 0:01:55  lr: 0.001969  min_lr: 0.001969  loss: 3.6767 (3.5629)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0899  max mem: 31830
Epoch: [161]  [130/312]  eta: 0:01:48  lr: 0.001969  min_lr: 0.001969  loss: 3.6358 (3.5472)  weight_decay: 0.0500 (0.0500)  time: 0.5620  data: 0.0745  max mem: 31830
Epoch: [161]  [140/312]  eta: 0:01:43  lr: 0.001968  min_lr: 0.001968  loss: 3.6956 (3.5569)  weight_decay: 0.0500 (0.0500)  time: 0.6117  data: 0.0584  max mem: 31830
Epoch: [161]  [150/312]  eta: 0:01:36  lr: 0.001967  min_lr: 0.001967  loss: 3.8309 (3.5653)  weight_decay: 0.0500 (0.0500)  time: 0.5935  data: 0.0763  max mem: 31830
Epoch: [161]  [160/312]  eta: 0:01:31  lr: 0.001967  min_lr: 0.001967  loss: 3.7708 (3.5684)  weight_decay: 0.0500 (0.0500)  time: 0.5953  data: 0.1164  max mem: 31830
Epoch: [161]  [170/312]  eta: 0:01:23  lr: 0.001966  min_lr: 0.001966  loss: 3.7708 (3.5949)  weight_decay: 0.0500 (0.0500)  time: 0.5410  data: 0.0603  max mem: 31830
Epoch: [161]  [180/312]  eta: 0:01:18  lr: 0.001965  min_lr: 0.001965  loss: 4.0071 (3.6064)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0507  max mem: 31830
Epoch: [161]  [190/312]  eta: 0:01:12  lr: 0.001964  min_lr: 0.001964  loss: 3.7853 (3.6125)  weight_decay: 0.0500 (0.0500)  time: 0.6325  data: 0.0509  max mem: 31830
Epoch: [161]  [200/312]  eta: 0:01:05  lr: 0.001964  min_lr: 0.001964  loss: 3.7403 (3.6205)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0179  max mem: 31830
Epoch: [161]  [210/312]  eta: 0:01:00  lr: 0.001963  min_lr: 0.001963  loss: 3.8246 (3.6244)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.0392  max mem: 31830
Epoch: [161]  [220/312]  eta: 0:00:54  lr: 0.001962  min_lr: 0.001962  loss: 3.7926 (3.6277)  weight_decay: 0.0500 (0.0500)  time: 0.6669  data: 0.0225  max mem: 31830
Epoch: [161]  [230/312]  eta: 0:00:47  lr: 0.001962  min_lr: 0.001962  loss: 3.7926 (3.6366)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0072  max mem: 31830
Epoch: [161]  [240/312]  eta: 0:00:42  lr: 0.001961  min_lr: 0.001961  loss: 3.8092 (3.6374)  weight_decay: 0.0500 (0.0500)  time: 0.5663  data: 0.0464  max mem: 31830
Epoch: [161]  [250/312]  eta: 0:00:36  lr: 0.001960  min_lr: 0.001960  loss: 3.7390 (3.6311)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0403  max mem: 31830
Epoch: [161]  [260/312]  eta: 0:00:30  lr: 0.001959  min_lr: 0.001959  loss: 3.4703 (3.6223)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0453  max mem: 31830
Epoch: [161]  [270/312]  eta: 0:00:24  lr: 0.001959  min_lr: 0.001959  loss: 3.7429 (3.6251)  weight_decay: 0.0500 (0.0500)  time: 0.6057  data: 0.0453  max mem: 31830
Epoch: [161]  [280/312]  eta: 0:00:18  lr: 0.001958  min_lr: 0.001958  loss: 3.7780 (3.6205)  weight_decay: 0.0500 (0.0500)  time: 0.5055  data: 0.0367  max mem: 31830
Epoch: [161]  [290/312]  eta: 0:00:12  lr: 0.001957  min_lr: 0.001957  loss: 3.3347 (3.6138)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0663  max mem: 31830
Epoch: [161]  [300/312]  eta: 0:00:06  lr: 0.001956  min_lr: 0.001956  loss: 3.5184 (3.6127)  weight_decay: 0.0500 (0.0500)  time: 0.4737  data: 0.0303  max mem: 31830
Epoch: [161]  [310/312]  eta: 0:00:01  lr: 0.001956  min_lr: 0.001956  loss: 3.8104 (3.6207)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [161]  [311/312]  eta: 0:00:00  lr: 0.001956  min_lr: 0.001956  loss: 3.8124 (3.6221)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [161] Total time: 0:02:58 (0.5705 s / it)
Averaged stats: lr: 0.001956  min_lr: 0.001956  loss: 3.8124 (3.5634)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:25  loss: 1.2302 (1.2302)  acc1: 78.2552 (78.2552)  acc5: 94.1406 (94.1406)  time: 9.4691  data: 9.3015  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6005 (1.5503)  acc1: 69.2708 (70.2560)  acc5: 88.6719 (89.6640)  time: 1.1698  data: 1.0336  max mem: 31830
Test: Total time: 0:00:10 (1.1913 s / it)
* Acc@1 69.552 Acc@5 89.546 loss 1.548
Accuracy of the model on the 50000 test images: 69.6%
Max accuracy: 70.04%
Epoch: [162]  [  0/312]  eta: 1:02:49  lr: 0.001956  min_lr: 0.001956  loss: 3.9184 (3.9184)  weight_decay: 0.0500 (0.0500)  time: 12.0821  data: 8.6130  max mem: 31830
Epoch: [162]  [ 10/312]  eta: 0:09:01  lr: 0.001955  min_lr: 0.001955  loss: 3.8113 (3.7821)  weight_decay: 0.0500 (0.0500)  time: 1.7923  data: 1.0720  max mem: 31830
Epoch: [162]  [ 20/312]  eta: 0:05:36  lr: 0.001954  min_lr: 0.001954  loss: 3.7009 (3.6548)  weight_decay: 0.0500 (0.0500)  time: 0.6061  data: 0.1594  max mem: 31830
Epoch: [162]  [ 30/312]  eta: 0:04:15  lr: 0.001953  min_lr: 0.001953  loss: 3.6631 (3.7016)  weight_decay: 0.0500 (0.0500)  time: 0.4212  data: 0.0010  max mem: 31830
Epoch: [162]  [ 40/312]  eta: 0:03:33  lr: 0.001953  min_lr: 0.001953  loss: 3.8440 (3.6660)  weight_decay: 0.0500 (0.0500)  time: 0.3978  data: 0.0009  max mem: 31830
Epoch: [162]  [ 50/312]  eta: 0:03:05  lr: 0.001952  min_lr: 0.001952  loss: 3.7782 (3.6338)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0008  max mem: 31830
Epoch: [162]  [ 60/312]  eta: 0:02:45  lr: 0.001951  min_lr: 0.001951  loss: 3.3323 (3.5922)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0009  max mem: 31830
Epoch: [162]  [ 70/312]  eta: 0:02:38  lr: 0.001951  min_lr: 0.001951  loss: 3.4180 (3.5744)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0210  max mem: 31830
Epoch: [162]  [ 80/312]  eta: 0:02:29  lr: 0.001950  min_lr: 0.001950  loss: 3.4740 (3.5404)  weight_decay: 0.0500 (0.0500)  time: 0.6088  data: 0.0210  max mem: 31830
Epoch: [162]  [ 90/312]  eta: 0:02:18  lr: 0.001949  min_lr: 0.001949  loss: 3.1423 (3.5047)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0356  max mem: 31830
Epoch: [162]  [100/312]  eta: 0:02:13  lr: 0.001948  min_lr: 0.001948  loss: 3.7305 (3.5349)  weight_decay: 0.0500 (0.0500)  time: 0.5564  data: 0.0819  max mem: 31830
Epoch: [162]  [110/312]  eta: 0:02:02  lr: 0.001948  min_lr: 0.001948  loss: 3.2817 (3.4946)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0474  max mem: 31830
Epoch: [162]  [120/312]  eta: 0:01:56  lr: 0.001947  min_lr: 0.001947  loss: 3.2817 (3.5106)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0232  max mem: 31830
Epoch: [162]  [130/312]  eta: 0:01:52  lr: 0.001946  min_lr: 0.001946  loss: 3.8767 (3.5232)  weight_decay: 0.0500 (0.0500)  time: 0.6603  data: 0.0955  max mem: 31830
Epoch: [162]  [140/312]  eta: 0:01:43  lr: 0.001946  min_lr: 0.001946  loss: 3.8713 (3.5297)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0738  max mem: 31830
Epoch: [162]  [150/312]  eta: 0:01:36  lr: 0.001945  min_lr: 0.001945  loss: 3.8519 (3.5502)  weight_decay: 0.0500 (0.0500)  time: 0.4834  data: 0.0250  max mem: 31830
Epoch: [162]  [160/312]  eta: 0:01:30  lr: 0.001944  min_lr: 0.001944  loss: 3.7790 (3.5575)  weight_decay: 0.0500 (0.0500)  time: 0.5652  data: 0.0248  max mem: 31830
Epoch: [162]  [170/312]  eta: 0:01:23  lr: 0.001943  min_lr: 0.001943  loss: 3.7724 (3.5656)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0389  max mem: 31830
Epoch: [162]  [180/312]  eta: 0:01:17  lr: 0.001943  min_lr: 0.001943  loss: 3.8787 (3.5776)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.0539  max mem: 31830
Epoch: [162]  [190/312]  eta: 0:01:11  lr: 0.001942  min_lr: 0.001942  loss: 3.8654 (3.5825)  weight_decay: 0.0500 (0.0500)  time: 0.5401  data: 0.0369  max mem: 31830
Epoch: [162]  [200/312]  eta: 0:01:05  lr: 0.001941  min_lr: 0.001941  loss: 3.8634 (3.5909)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0296  max mem: 31830
Epoch: [162]  [210/312]  eta: 0:00:59  lr: 0.001941  min_lr: 0.001941  loss: 3.7051 (3.5798)  weight_decay: 0.0500 (0.0500)  time: 0.5672  data: 0.0427  max mem: 31830
Epoch: [162]  [220/312]  eta: 0:00:53  lr: 0.001940  min_lr: 0.001940  loss: 3.3120 (3.5666)  weight_decay: 0.0500 (0.0500)  time: 0.5690  data: 0.0501  max mem: 31830
Epoch: [162]  [230/312]  eta: 0:00:47  lr: 0.001939  min_lr: 0.001939  loss: 3.4134 (3.5631)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0220  max mem: 31830
Epoch: [162]  [240/312]  eta: 0:00:41  lr: 0.001938  min_lr: 0.001938  loss: 3.4452 (3.5469)  weight_decay: 0.0500 (0.0500)  time: 0.5713  data: 0.0346  max mem: 31830
Epoch: [162]  [250/312]  eta: 0:00:35  lr: 0.001938  min_lr: 0.001938  loss: 3.4452 (3.5448)  weight_decay: 0.0500 (0.0500)  time: 0.5880  data: 0.0515  max mem: 31830
Epoch: [162]  [260/312]  eta: 0:00:29  lr: 0.001937  min_lr: 0.001937  loss: 3.4650 (3.5414)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0441  max mem: 31830
Epoch: [162]  [270/312]  eta: 0:00:24  lr: 0.001936  min_lr: 0.001936  loss: 3.7231 (3.5473)  weight_decay: 0.0500 (0.0500)  time: 0.5262  data: 0.0389  max mem: 31830
Epoch: [162]  [280/312]  eta: 0:00:18  lr: 0.001936  min_lr: 0.001936  loss: 3.6995 (3.5409)  weight_decay: 0.0500 (0.0500)  time: 0.4976  data: 0.0253  max mem: 31830
Epoch: [162]  [290/312]  eta: 0:00:12  lr: 0.001935  min_lr: 0.001935  loss: 3.8094 (3.5504)  weight_decay: 0.0500 (0.0500)  time: 0.5467  data: 0.0447  max mem: 31830
Epoch: [162]  [300/312]  eta: 0:00:06  lr: 0.001934  min_lr: 0.001934  loss: 3.8766 (3.5558)  weight_decay: 0.0500 (0.0500)  time: 0.5088  data: 0.0376  max mem: 31830
Epoch: [162]  [310/312]  eta: 0:00:01  lr: 0.001933  min_lr: 0.001933  loss: 3.8766 (3.5626)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0002  max mem: 31830
Epoch: [162]  [311/312]  eta: 0:00:00  lr: 0.001933  min_lr: 0.001933  loss: 3.8493 (3.5585)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [162] Total time: 0:02:55 (0.5634 s / it)
Averaged stats: lr: 0.001933  min_lr: 0.001933  loss: 3.8493 (3.5743)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:30  loss: 1.6016 (1.6016)  acc1: 76.4323 (76.4323)  acc5: 93.3594 (93.3594)  time: 10.0481  data: 9.8889  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 2.0528 (1.9304)  acc1: 68.6198 (68.8640)  acc5: 88.5417 (89.1520)  time: 1.2383  data: 1.0988  max mem: 31830
Test: Total time: 0:00:11 (1.2700 s / it)
* Acc@1 68.846 Acc@5 89.138 loss 1.942
Accuracy of the model on the 50000 test images: 68.8%
Max accuracy: 70.04%
Epoch: [163]  [  0/312]  eta: 1:02:32  lr: 0.001933  min_lr: 0.001933  loss: 3.1747 (3.1747)  weight_decay: 0.0500 (0.0500)  time: 12.0281  data: 10.6024  max mem: 31830
Epoch: [163]  [ 10/312]  eta: 0:08:25  lr: 0.001932  min_lr: 0.001932  loss: 3.9969 (3.8534)  weight_decay: 0.0500 (0.0500)  time: 1.6745  data: 1.0189  max mem: 31830
Epoch: [163]  [ 20/312]  eta: 0:05:26  lr: 0.001932  min_lr: 0.001932  loss: 3.8953 (3.7859)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0678  max mem: 31830
Epoch: [163]  [ 30/312]  eta: 0:04:09  lr: 0.001931  min_lr: 0.001931  loss: 3.8099 (3.7307)  weight_decay: 0.0500 (0.0500)  time: 0.4524  data: 0.0380  max mem: 31830
Epoch: [163]  [ 40/312]  eta: 0:03:28  lr: 0.001930  min_lr: 0.001930  loss: 3.7790 (3.7387)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0011  max mem: 31830
Epoch: [163]  [ 50/312]  eta: 0:03:02  lr: 0.001930  min_lr: 0.001930  loss: 3.7786 (3.7102)  weight_decay: 0.0500 (0.0500)  time: 0.4025  data: 0.0075  max mem: 31830
Epoch: [163]  [ 60/312]  eta: 0:02:43  lr: 0.001929  min_lr: 0.001929  loss: 3.6895 (3.7128)  weight_decay: 0.0500 (0.0500)  time: 0.4007  data: 0.0073  max mem: 31830
Epoch: [163]  [ 70/312]  eta: 0:02:36  lr: 0.001928  min_lr: 0.001928  loss: 3.6922 (3.7133)  weight_decay: 0.0500 (0.0500)  time: 0.5235  data: 0.0838  max mem: 31830
Epoch: [163]  [ 80/312]  eta: 0:02:26  lr: 0.001927  min_lr: 0.001927  loss: 3.6922 (3.6862)  weight_decay: 0.0500 (0.0500)  time: 0.5818  data: 0.0907  max mem: 31830
Epoch: [163]  [ 90/312]  eta: 0:02:17  lr: 0.001927  min_lr: 0.001927  loss: 3.7084 (3.6753)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0758  max mem: 31830
Epoch: [163]  [100/312]  eta: 0:02:10  lr: 0.001926  min_lr: 0.001926  loss: 3.7821 (3.6815)  weight_decay: 0.0500 (0.0500)  time: 0.5656  data: 0.1283  max mem: 31830
Epoch: [163]  [110/312]  eta: 0:02:00  lr: 0.001925  min_lr: 0.001925  loss: 3.7821 (3.6612)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0602  max mem: 31830
Epoch: [163]  [120/312]  eta: 0:01:54  lr: 0.001925  min_lr: 0.001925  loss: 3.6886 (3.6726)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0639  max mem: 31830
Epoch: [163]  [130/312]  eta: 0:01:48  lr: 0.001924  min_lr: 0.001924  loss: 3.4621 (3.6391)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.1415  max mem: 31830
Epoch: [163]  [140/312]  eta: 0:01:40  lr: 0.001923  min_lr: 0.001923  loss: 3.3698 (3.6205)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.0784  max mem: 31830
Epoch: [163]  [150/312]  eta: 0:01:34  lr: 0.001922  min_lr: 0.001922  loss: 3.6474 (3.6145)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0732  max mem: 31830
Epoch: [163]  [160/312]  eta: 0:01:28  lr: 0.001922  min_lr: 0.001922  loss: 3.6474 (3.6060)  weight_decay: 0.0500 (0.0500)  time: 0.5580  data: 0.0921  max mem: 31830
Epoch: [163]  [170/312]  eta: 0:01:21  lr: 0.001921  min_lr: 0.001921  loss: 3.6718 (3.6021)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0753  max mem: 31830
Epoch: [163]  [180/312]  eta: 0:01:16  lr: 0.001920  min_lr: 0.001920  loss: 3.7859 (3.6093)  weight_decay: 0.0500 (0.0500)  time: 0.5550  data: 0.1116  max mem: 31830
Epoch: [163]  [190/312]  eta: 0:01:09  lr: 0.001920  min_lr: 0.001920  loss: 3.7897 (3.6090)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0560  max mem: 31830
Epoch: [163]  [200/312]  eta: 0:01:03  lr: 0.001919  min_lr: 0.001919  loss: 3.7250 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0602  max mem: 31830
Epoch: [163]  [210/312]  eta: 0:00:58  lr: 0.001918  min_lr: 0.001918  loss: 3.7250 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.6370  data: 0.1381  max mem: 31830
Epoch: [163]  [220/312]  eta: 0:00:52  lr: 0.001917  min_lr: 0.001917  loss: 3.2252 (3.5972)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0798  max mem: 31830
Epoch: [163]  [230/312]  eta: 0:00:46  lr: 0.001917  min_lr: 0.001917  loss: 3.3701 (3.5964)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0757  max mem: 31830
Epoch: [163]  [240/312]  eta: 0:00:40  lr: 0.001916  min_lr: 0.001916  loss: 3.7773 (3.6028)  weight_decay: 0.0500 (0.0500)  time: 0.5835  data: 0.1080  max mem: 31830
Epoch: [163]  [250/312]  eta: 0:00:34  lr: 0.001915  min_lr: 0.001915  loss: 3.7510 (3.6025)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0484  max mem: 31830
Epoch: [163]  [260/312]  eta: 0:00:29  lr: 0.001915  min_lr: 0.001915  loss: 3.6788 (3.6020)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0987  max mem: 31830
Epoch: [163]  [270/312]  eta: 0:00:23  lr: 0.001914  min_lr: 0.001914  loss: 3.6837 (3.5985)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0847  max mem: 31830
Epoch: [163]  [280/312]  eta: 0:00:17  lr: 0.001913  min_lr: 0.001913  loss: 3.5761 (3.5806)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0753  max mem: 31830
Epoch: [163]  [290/312]  eta: 0:00:12  lr: 0.001912  min_lr: 0.001912  loss: 3.4934 (3.5787)  weight_decay: 0.0500 (0.0500)  time: 0.6225  data: 0.1318  max mem: 31830
Epoch: [163]  [300/312]  eta: 0:00:06  lr: 0.001912  min_lr: 0.001912  loss: 3.7444 (3.5827)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0571  max mem: 31830
Epoch: [163]  [310/312]  eta: 0:00:01  lr: 0.001911  min_lr: 0.001911  loss: 3.8115 (3.5878)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [163]  [311/312]  eta: 0:00:00  lr: 0.001911  min_lr: 0.001911  loss: 3.8011 (3.5847)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [163] Total time: 0:02:52 (0.5542 s / it)
Averaged stats: lr: 0.001911  min_lr: 0.001911  loss: 3.8011 (3.5454)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:24  loss: 1.3234 (1.3234)  acc1: 76.1719 (76.1719)  acc5: 93.0990 (93.0990)  time: 9.3985  data: 9.2393  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5849 (1.5268)  acc1: 68.7500 (69.5200)  acc5: 89.5833 (89.7120)  time: 1.1633  data: 1.0267  max mem: 31830
Test: Total time: 0:00:10 (1.1867 s / it)
* Acc@1 69.476 Acc@5 89.878 loss 1.521
Accuracy of the model on the 50000 test images: 69.5%
Max accuracy: 70.04%
Epoch: [164]  [  0/312]  eta: 1:01:40  lr: 0.001911  min_lr: 0.001911  loss: 3.8963 (3.8963)  weight_decay: 0.0500 (0.0500)  time: 11.8620  data: 11.4658  max mem: 31830
Epoch: [164]  [ 10/312]  eta: 0:08:06  lr: 0.001910  min_lr: 0.001910  loss: 3.4788 (3.3554)  weight_decay: 0.0500 (0.0500)  time: 1.6126  data: 1.0430  max mem: 31830
Epoch: [164]  [ 20/312]  eta: 0:05:28  lr: 0.001909  min_lr: 0.001909  loss: 3.4797 (3.4971)  weight_decay: 0.0500 (0.0500)  time: 0.5876  data: 0.0778  max mem: 31830
Epoch: [164]  [ 30/312]  eta: 0:04:10  lr: 0.001909  min_lr: 0.001909  loss: 3.7504 (3.5349)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0779  max mem: 31830
Epoch: [164]  [ 40/312]  eta: 0:03:29  lr: 0.001908  min_lr: 0.001908  loss: 3.6029 (3.4790)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0010  max mem: 31830
Epoch: [164]  [ 50/312]  eta: 0:03:18  lr: 0.001907  min_lr: 0.001907  loss: 3.3959 (3.4306)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0010  max mem: 31830
Epoch: [164]  [ 60/312]  eta: 0:02:55  lr: 0.001906  min_lr: 0.001906  loss: 3.3572 (3.3981)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.0020  max mem: 31830
Epoch: [164]  [ 70/312]  eta: 0:02:44  lr: 0.001906  min_lr: 0.001906  loss: 3.3085 (3.3777)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0166  max mem: 31830
Epoch: [164]  [ 80/312]  eta: 0:02:31  lr: 0.001905  min_lr: 0.001905  loss: 3.0528 (3.3517)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0287  max mem: 31830
Epoch: [164]  [ 90/312]  eta: 0:02:21  lr: 0.001904  min_lr: 0.001904  loss: 3.7229 (3.3765)  weight_decay: 0.0500 (0.0500)  time: 0.4854  data: 0.0142  max mem: 31830
Epoch: [164]  [100/312]  eta: 0:02:15  lr: 0.001904  min_lr: 0.001904  loss: 3.7331 (3.4039)  weight_decay: 0.0500 (0.0500)  time: 0.5770  data: 0.0356  max mem: 31830
Epoch: [164]  [110/312]  eta: 0:02:04  lr: 0.001903  min_lr: 0.001903  loss: 3.6701 (3.4084)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0355  max mem: 31830
Epoch: [164]  [120/312]  eta: 0:01:58  lr: 0.001902  min_lr: 0.001902  loss: 3.6496 (3.4182)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0398  max mem: 31830
Epoch: [164]  [130/312]  eta: 0:01:52  lr: 0.001901  min_lr: 0.001901  loss: 3.7896 (3.4589)  weight_decay: 0.0500 (0.0500)  time: 0.6297  data: 0.0856  max mem: 31830
Epoch: [164]  [140/312]  eta: 0:01:43  lr: 0.001901  min_lr: 0.001901  loss: 3.7648 (3.4529)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0466  max mem: 31830
Epoch: [164]  [150/312]  eta: 0:01:37  lr: 0.001900  min_lr: 0.001900  loss: 3.4321 (3.4362)  weight_decay: 0.0500 (0.0500)  time: 0.4867  data: 0.0218  max mem: 31830
Epoch: [164]  [160/312]  eta: 0:01:31  lr: 0.001899  min_lr: 0.001899  loss: 3.7383 (3.4481)  weight_decay: 0.0500 (0.0500)  time: 0.6008  data: 0.0221  max mem: 31830
Epoch: [164]  [170/312]  eta: 0:01:24  lr: 0.001899  min_lr: 0.001899  loss: 3.7481 (3.4545)  weight_decay: 0.0500 (0.0500)  time: 0.5786  data: 0.0115  max mem: 31830
Epoch: [164]  [180/312]  eta: 0:01:18  lr: 0.001898  min_lr: 0.001898  loss: 3.7481 (3.4650)  weight_decay: 0.0500 (0.0500)  time: 0.5309  data: 0.0257  max mem: 31830
Epoch: [164]  [190/312]  eta: 0:01:11  lr: 0.001897  min_lr: 0.001897  loss: 3.8182 (3.4791)  weight_decay: 0.0500 (0.0500)  time: 0.4641  data: 0.0154  max mem: 31830
Epoch: [164]  [200/312]  eta: 0:01:05  lr: 0.001896  min_lr: 0.001896  loss: 3.6693 (3.4840)  weight_decay: 0.0500 (0.0500)  time: 0.4795  data: 0.0154  max mem: 31830
Epoch: [164]  [210/312]  eta: 0:00:59  lr: 0.001896  min_lr: 0.001896  loss: 3.6012 (3.4738)  weight_decay: 0.0500 (0.0500)  time: 0.6029  data: 0.0154  max mem: 31830
Epoch: [164]  [220/312]  eta: 0:00:53  lr: 0.001895  min_lr: 0.001895  loss: 3.6820 (3.4879)  weight_decay: 0.0500 (0.0500)  time: 0.5277  data: 0.0096  max mem: 31830
Epoch: [164]  [230/312]  eta: 0:00:47  lr: 0.001894  min_lr: 0.001894  loss: 3.6820 (3.4902)  weight_decay: 0.0500 (0.0500)  time: 0.4851  data: 0.0097  max mem: 31830
Epoch: [164]  [240/312]  eta: 0:00:41  lr: 0.001894  min_lr: 0.001894  loss: 3.5321 (3.4901)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0441  max mem: 31830
Epoch: [164]  [250/312]  eta: 0:00:35  lr: 0.001893  min_lr: 0.001893  loss: 3.7550 (3.5050)  weight_decay: 0.0500 (0.0500)  time: 0.5061  data: 0.0439  max mem: 31830
Epoch: [164]  [260/312]  eta: 0:00:29  lr: 0.001892  min_lr: 0.001892  loss: 3.8188 (3.5129)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0373  max mem: 31830
Epoch: [164]  [270/312]  eta: 0:00:23  lr: 0.001891  min_lr: 0.001891  loss: 3.7174 (3.5147)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0373  max mem: 31830
Epoch: [164]  [280/312]  eta: 0:00:18  lr: 0.001891  min_lr: 0.001891  loss: 3.7174 (3.5201)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0303  max mem: 31830
Epoch: [164]  [290/312]  eta: 0:00:12  lr: 0.001890  min_lr: 0.001890  loss: 3.6127 (3.5194)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0337  max mem: 31830
Epoch: [164]  [300/312]  eta: 0:00:06  lr: 0.001889  min_lr: 0.001889  loss: 3.6728 (3.5255)  weight_decay: 0.0500 (0.0500)  time: 0.4478  data: 0.0038  max mem: 31830
Epoch: [164]  [310/312]  eta: 0:00:01  lr: 0.001889  min_lr: 0.001889  loss: 3.5953 (3.5188)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [164]  [311/312]  eta: 0:00:00  lr: 0.001888  min_lr: 0.001888  loss: 3.5953 (3.5152)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [164] Total time: 0:02:54 (0.5607 s / it)
Averaged stats: lr: 0.001888  min_lr: 0.001888  loss: 3.5953 (3.5610)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.2403 (1.2403)  acc1: 77.9948 (77.9948)  acc5: 93.4896 (93.4896)  time: 8.2483  data: 8.0804  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5786 (1.4598)  acc1: 67.8385 (70.0800)  acc5: 89.3229 (90.0960)  time: 1.0342  data: 0.8979  max mem: 31830
Test: Total time: 0:00:09 (1.0505 s / it)
* Acc@1 70.200 Acc@5 90.130 loss 1.456
Accuracy of the model on the 50000 test images: 70.2%
Max accuracy: 70.20%
Epoch: [165]  [  0/312]  eta: 1:00:32  lr: 0.001888  min_lr: 0.001888  loss: 3.1902 (3.1902)  weight_decay: 0.0500 (0.0500)  time: 11.6423  data: 11.2516  max mem: 31830
Epoch: [165]  [ 10/312]  eta: 0:08:34  lr: 0.001888  min_lr: 0.001888  loss: 3.2237 (3.2643)  weight_decay: 0.0500 (0.0500)  time: 1.7029  data: 1.0790  max mem: 31830
Epoch: [165]  [ 20/312]  eta: 0:05:26  lr: 0.001887  min_lr: 0.001887  loss: 3.6625 (3.4547)  weight_decay: 0.0500 (0.0500)  time: 0.5916  data: 0.0737  max mem: 31830
Epoch: [165]  [ 30/312]  eta: 0:04:09  lr: 0.001886  min_lr: 0.001886  loss: 3.6921 (3.4834)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0433  max mem: 31830
Epoch: [165]  [ 40/312]  eta: 0:03:28  lr: 0.001886  min_lr: 0.001886  loss: 3.5424 (3.5058)  weight_decay: 0.0500 (0.0500)  time: 0.3964  data: 0.0009  max mem: 31830
Epoch: [165]  [ 50/312]  eta: 0:03:01  lr: 0.001885  min_lr: 0.001885  loss: 3.7864 (3.5846)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0009  max mem: 31830
Epoch: [165]  [ 60/312]  eta: 0:02:42  lr: 0.001884  min_lr: 0.001884  loss: 3.8488 (3.6039)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0009  max mem: 31830
Epoch: [165]  [ 70/312]  eta: 0:02:32  lr: 0.001883  min_lr: 0.001883  loss: 3.4463 (3.5697)  weight_decay: 0.0500 (0.0500)  time: 0.4721  data: 0.0796  max mem: 31830
Epoch: [165]  [ 80/312]  eta: 0:02:25  lr: 0.001883  min_lr: 0.001883  loss: 3.7183 (3.5922)  weight_decay: 0.0500 (0.0500)  time: 0.5823  data: 0.1869  max mem: 31830
Epoch: [165]  [ 90/312]  eta: 0:02:13  lr: 0.001882  min_lr: 0.001882  loss: 3.7183 (3.5511)  weight_decay: 0.0500 (0.0500)  time: 0.5043  data: 0.1082  max mem: 31830
Epoch: [165]  [100/312]  eta: 0:02:07  lr: 0.001881  min_lr: 0.001881  loss: 3.4425 (3.5602)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0926  max mem: 31830
Epoch: [165]  [110/312]  eta: 0:01:57  lr: 0.001880  min_lr: 0.001880  loss: 3.6457 (3.5600)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0941  max mem: 31830
Epoch: [165]  [120/312]  eta: 0:01:52  lr: 0.001880  min_lr: 0.001880  loss: 3.7049 (3.5778)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0939  max mem: 31830
Epoch: [165]  [130/312]  eta: 0:01:47  lr: 0.001879  min_lr: 0.001879  loss: 3.7966 (3.5912)  weight_decay: 0.0500 (0.0500)  time: 0.6163  data: 0.1825  max mem: 31830
Epoch: [165]  [140/312]  eta: 0:01:38  lr: 0.001878  min_lr: 0.001878  loss: 3.8190 (3.6015)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0907  max mem: 31830
Epoch: [165]  [150/312]  eta: 0:01:33  lr: 0.001878  min_lr: 0.001878  loss: 3.5396 (3.5822)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.1061  max mem: 31830
Epoch: [165]  [160/312]  eta: 0:01:28  lr: 0.001877  min_lr: 0.001877  loss: 3.7600 (3.6019)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.1644  max mem: 31830
Epoch: [165]  [170/312]  eta: 0:01:21  lr: 0.001876  min_lr: 0.001876  loss: 3.7638 (3.5954)  weight_decay: 0.0500 (0.0500)  time: 0.5138  data: 0.0884  max mem: 31830
Epoch: [165]  [180/312]  eta: 0:01:15  lr: 0.001875  min_lr: 0.001875  loss: 3.3601 (3.5809)  weight_decay: 0.0500 (0.0500)  time: 0.5308  data: 0.0846  max mem: 31830
Epoch: [165]  [190/312]  eta: 0:01:09  lr: 0.001875  min_lr: 0.001875  loss: 3.6793 (3.5880)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0557  max mem: 31830
Epoch: [165]  [200/312]  eta: 0:01:03  lr: 0.001874  min_lr: 0.001874  loss: 3.7876 (3.5896)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0396  max mem: 31830
Epoch: [165]  [210/312]  eta: 0:00:58  lr: 0.001873  min_lr: 0.001873  loss: 3.6823 (3.5873)  weight_decay: 0.0500 (0.0500)  time: 0.6075  data: 0.1339  max mem: 31830
Epoch: [165]  [220/312]  eta: 0:00:51  lr: 0.001873  min_lr: 0.001873  loss: 3.3930 (3.5730)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0958  max mem: 31830
Epoch: [165]  [230/312]  eta: 0:00:46  lr: 0.001872  min_lr: 0.001872  loss: 3.3979 (3.5744)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0969  max mem: 31830
Epoch: [165]  [240/312]  eta: 0:00:40  lr: 0.001871  min_lr: 0.001871  loss: 3.5425 (3.5688)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.1464  max mem: 31830
Epoch: [165]  [250/312]  eta: 0:00:34  lr: 0.001870  min_lr: 0.001870  loss: 3.2857 (3.5595)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0847  max mem: 31830
Epoch: [165]  [260/312]  eta: 0:00:29  lr: 0.001870  min_lr: 0.001870  loss: 3.7360 (3.5690)  weight_decay: 0.0500 (0.0500)  time: 0.5240  data: 0.0891  max mem: 31830
Epoch: [165]  [270/312]  eta: 0:00:23  lr: 0.001869  min_lr: 0.001869  loss: 3.8286 (3.5724)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0547  max mem: 31830
Epoch: [165]  [280/312]  eta: 0:00:17  lr: 0.001868  min_lr: 0.001868  loss: 3.6449 (3.5675)  weight_decay: 0.0500 (0.0500)  time: 0.5467  data: 0.0629  max mem: 31830
Epoch: [165]  [290/312]  eta: 0:00:12  lr: 0.001868  min_lr: 0.001868  loss: 3.2554 (3.5529)  weight_decay: 0.0500 (0.0500)  time: 0.5898  data: 0.1188  max mem: 31830
Epoch: [165]  [300/312]  eta: 0:00:06  lr: 0.001867  min_lr: 0.001867  loss: 3.2554 (3.5526)  weight_decay: 0.0500 (0.0500)  time: 0.4752  data: 0.0564  max mem: 31830
Epoch: [165]  [310/312]  eta: 0:00:01  lr: 0.001866  min_lr: 0.001866  loss: 3.6264 (3.5569)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0002  max mem: 31830
Epoch: [165]  [311/312]  eta: 0:00:00  lr: 0.001866  min_lr: 0.001866  loss: 3.6048 (3.5533)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0002  max mem: 31830
Epoch: [165] Total time: 0:02:52 (0.5517 s / it)
Averaged stats: lr: 0.001866  min_lr: 0.001866  loss: 3.6048 (3.5566)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:23  loss: 1.1823 (1.1823)  acc1: 77.8646 (77.8646)  acc5: 95.3125 (95.3125)  time: 9.2782  data: 9.1197  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4523 (1.3987)  acc1: 71.4844 (71.6960)  acc5: 90.7552 (90.8480)  time: 1.1512  data: 1.0134  max mem: 31830
Test: Total time: 0:00:10 (1.1812 s / it)
* Acc@1 70.840 Acc@5 90.594 loss 1.414
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 70.84%
Epoch: [166]  [  0/312]  eta: 1:07:04  lr: 0.001866  min_lr: 0.001866  loss: 3.5647 (3.5647)  weight_decay: 0.0500 (0.0500)  time: 12.8976  data: 12.4998  max mem: 31830
Epoch: [166]  [ 10/312]  eta: 0:08:59  lr: 0.001865  min_lr: 0.001865  loss: 3.5841 (3.5161)  weight_decay: 0.0500 (0.0500)  time: 1.7875  data: 1.1372  max mem: 31830
Epoch: [166]  [ 20/312]  eta: 0:05:43  lr: 0.001865  min_lr: 0.001865  loss: 3.5655 (3.5565)  weight_decay: 0.0500 (0.0500)  time: 0.5889  data: 0.0586  max mem: 31830
Epoch: [166]  [ 30/312]  eta: 0:04:20  lr: 0.001864  min_lr: 0.001864  loss: 3.5404 (3.5404)  weight_decay: 0.0500 (0.0500)  time: 0.4502  data: 0.0589  max mem: 31830
Epoch: [166]  [ 40/312]  eta: 0:03:36  lr: 0.001863  min_lr: 0.001863  loss: 3.5124 (3.5164)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0014  max mem: 31830
Epoch: [166]  [ 50/312]  eta: 0:03:08  lr: 0.001862  min_lr: 0.001862  loss: 3.6255 (3.5228)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0011  max mem: 31830
Epoch: [166]  [ 60/312]  eta: 0:02:47  lr: 0.001862  min_lr: 0.001862  loss: 3.6141 (3.5057)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0009  max mem: 31830
Epoch: [166]  [ 70/312]  eta: 0:02:31  lr: 0.001861  min_lr: 0.001861  loss: 3.4954 (3.5012)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0009  max mem: 31830
Epoch: [166]  [ 80/312]  eta: 0:02:24  lr: 0.001860  min_lr: 0.001860  loss: 3.4954 (3.5072)  weight_decay: 0.0500 (0.0500)  time: 0.5019  data: 0.1043  max mem: 31830
Epoch: [166]  [ 90/312]  eta: 0:02:13  lr: 0.001860  min_lr: 0.001860  loss: 3.4344 (3.4911)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.1044  max mem: 31830
Epoch: [166]  [100/312]  eta: 0:02:07  lr: 0.001859  min_lr: 0.001859  loss: 3.7745 (3.5392)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0925  max mem: 31830
Epoch: [166]  [110/312]  eta: 0:01:58  lr: 0.001858  min_lr: 0.001858  loss: 3.8486 (3.5427)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0923  max mem: 31830
Epoch: [166]  [120/312]  eta: 0:01:52  lr: 0.001857  min_lr: 0.001857  loss: 3.8486 (3.5601)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.1075  max mem: 31830
Epoch: [166]  [130/312]  eta: 0:01:47  lr: 0.001857  min_lr: 0.001857  loss: 3.8671 (3.5577)  weight_decay: 0.0500 (0.0500)  time: 0.6305  data: 0.2186  max mem: 31830
Epoch: [166]  [140/312]  eta: 0:01:39  lr: 0.001856  min_lr: 0.001856  loss: 3.8039 (3.5770)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.1118  max mem: 31830
Epoch: [166]  [150/312]  eta: 0:01:35  lr: 0.001855  min_lr: 0.001855  loss: 3.6925 (3.5777)  weight_decay: 0.0500 (0.0500)  time: 0.5692  data: 0.1713  max mem: 31830
Epoch: [166]  [160/312]  eta: 0:01:29  lr: 0.001855  min_lr: 0.001855  loss: 3.5432 (3.5732)  weight_decay: 0.0500 (0.0500)  time: 0.6803  data: 0.2809  max mem: 31830
Epoch: [166]  [170/312]  eta: 0:01:22  lr: 0.001854  min_lr: 0.001854  loss: 3.6329 (3.5804)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.1103  max mem: 31830
Epoch: [166]  [180/312]  eta: 0:01:16  lr: 0.001853  min_lr: 0.001853  loss: 3.6329 (3.5779)  weight_decay: 0.0500 (0.0500)  time: 0.4993  data: 0.1008  max mem: 31830
Epoch: [166]  [190/312]  eta: 0:01:09  lr: 0.001852  min_lr: 0.001852  loss: 3.7357 (3.5754)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.1010  max mem: 31830
Epoch: [166]  [200/312]  eta: 0:01:04  lr: 0.001852  min_lr: 0.001852  loss: 3.4875 (3.5709)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.1057  max mem: 31830
Epoch: [166]  [210/312]  eta: 0:00:58  lr: 0.001851  min_lr: 0.001851  loss: 3.4875 (3.5723)  weight_decay: 0.0500 (0.0500)  time: 0.6329  data: 0.2359  max mem: 31830
Epoch: [166]  [220/312]  eta: 0:00:52  lr: 0.001850  min_lr: 0.001850  loss: 3.5701 (3.5720)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.1311  max mem: 31830
Epoch: [166]  [230/312]  eta: 0:00:46  lr: 0.001849  min_lr: 0.001849  loss: 3.7141 (3.5725)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.1098  max mem: 31830
Epoch: [166]  [240/312]  eta: 0:00:41  lr: 0.001849  min_lr: 0.001849  loss: 3.5738 (3.5648)  weight_decay: 0.0500 (0.0500)  time: 0.6256  data: 0.2316  max mem: 31830
Epoch: [166]  [250/312]  eta: 0:00:35  lr: 0.001848  min_lr: 0.001848  loss: 3.7894 (3.5756)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.1225  max mem: 31830
Epoch: [166]  [260/312]  eta: 0:00:29  lr: 0.001847  min_lr: 0.001847  loss: 3.6794 (3.5618)  weight_decay: 0.0500 (0.0500)  time: 0.5018  data: 0.1068  max mem: 31830
Epoch: [166]  [270/312]  eta: 0:00:23  lr: 0.001847  min_lr: 0.001847  loss: 3.4349 (3.5618)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.1281  max mem: 31830
Epoch: [166]  [280/312]  eta: 0:00:18  lr: 0.001846  min_lr: 0.001846  loss: 3.5427 (3.5570)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.1396  max mem: 31830
Epoch: [166]  [290/312]  eta: 0:00:12  lr: 0.001845  min_lr: 0.001845  loss: 3.7112 (3.5618)  weight_decay: 0.0500 (0.0500)  time: 0.6166  data: 0.2227  max mem: 31830
Epoch: [166]  [300/312]  eta: 0:00:06  lr: 0.001844  min_lr: 0.001844  loss: 3.8366 (3.5586)  weight_decay: 0.0500 (0.0500)  time: 0.4927  data: 0.1048  max mem: 31830
Epoch: [166]  [310/312]  eta: 0:00:01  lr: 0.001844  min_lr: 0.001844  loss: 3.6884 (3.5593)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [166]  [311/312]  eta: 0:00:00  lr: 0.001844  min_lr: 0.001844  loss: 3.6884 (3.5573)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [166] Total time: 0:02:54 (0.5581 s / it)
Averaged stats: lr: 0.001844  min_lr: 0.001844  loss: 3.6884 (3.5429)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1745 (1.1745)  acc1: 78.6458 (78.6458)  acc5: 93.7500 (93.7500)  time: 8.5851  data: 8.4174  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5281 (1.5093)  acc1: 68.6198 (69.2640)  acc5: 88.6719 (89.4400)  time: 1.0701  data: 0.9354  max mem: 31830
Test: Total time: 0:00:09 (1.0845 s / it)
* Acc@1 69.268 Acc@5 89.354 loss 1.514
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 70.84%
Epoch: [167]  [  0/312]  eta: 1:00:18  lr: 0.001844  min_lr: 0.001844  loss: 3.3916 (3.3916)  weight_decay: 0.0500 (0.0500)  time: 11.5963  data: 8.8524  max mem: 31830
Epoch: [167]  [ 10/312]  eta: 0:09:06  lr: 0.001843  min_lr: 0.001843  loss: 3.4488 (3.5570)  weight_decay: 0.0500 (0.0500)  time: 1.8083  data: 0.8768  max mem: 31830
Epoch: [167]  [ 20/312]  eta: 0:05:34  lr: 0.001842  min_lr: 0.001842  loss: 3.6762 (3.6830)  weight_decay: 0.0500 (0.0500)  time: 0.6231  data: 0.0555  max mem: 31830
Epoch: [167]  [ 30/312]  eta: 0:04:14  lr: 0.001841  min_lr: 0.001841  loss: 3.8143 (3.7324)  weight_decay: 0.0500 (0.0500)  time: 0.4053  data: 0.0170  max mem: 31830
Epoch: [167]  [ 40/312]  eta: 0:03:32  lr: 0.001841  min_lr: 0.001841  loss: 3.7916 (3.7138)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0018  max mem: 31830
Epoch: [167]  [ 50/312]  eta: 0:03:04  lr: 0.001840  min_lr: 0.001840  loss: 3.6726 (3.6991)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0015  max mem: 31830
Epoch: [167]  [ 60/312]  eta: 0:02:44  lr: 0.001839  min_lr: 0.001839  loss: 3.7033 (3.7086)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0013  max mem: 31830
Epoch: [167]  [ 70/312]  eta: 0:02:34  lr: 0.001839  min_lr: 0.001839  loss: 3.6649 (3.6993)  weight_decay: 0.0500 (0.0500)  time: 0.4637  data: 0.0010  max mem: 31830
Epoch: [167]  [ 80/312]  eta: 0:02:22  lr: 0.001838  min_lr: 0.001838  loss: 3.5499 (3.6677)  weight_decay: 0.0500 (0.0500)  time: 0.4976  data: 0.0255  max mem: 31830
Epoch: [167]  [ 90/312]  eta: 0:02:15  lr: 0.001837  min_lr: 0.001837  loss: 3.5499 (3.6486)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0255  max mem: 31830
Epoch: [167]  [100/312]  eta: 0:02:09  lr: 0.001836  min_lr: 0.001836  loss: 3.5522 (3.6339)  weight_decay: 0.0500 (0.0500)  time: 0.5967  data: 0.0173  max mem: 31830
Epoch: [167]  [110/312]  eta: 0:02:00  lr: 0.001836  min_lr: 0.001836  loss: 3.6945 (3.6279)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0320  max mem: 31830
Epoch: [167]  [120/312]  eta: 0:01:53  lr: 0.001835  min_lr: 0.001835  loss: 3.7902 (3.6353)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0158  max mem: 31830
Epoch: [167]  [130/312]  eta: 0:01:48  lr: 0.001834  min_lr: 0.001834  loss: 3.8286 (3.6470)  weight_decay: 0.0500 (0.0500)  time: 0.6090  data: 0.0306  max mem: 31830
Epoch: [167]  [140/312]  eta: 0:01:41  lr: 0.001834  min_lr: 0.001834  loss: 3.9059 (3.6481)  weight_decay: 0.0500 (0.0500)  time: 0.5516  data: 0.0476  max mem: 31830
Epoch: [167]  [150/312]  eta: 0:01:35  lr: 0.001833  min_lr: 0.001833  loss: 3.9059 (3.6546)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0182  max mem: 31830
Epoch: [167]  [160/312]  eta: 0:01:28  lr: 0.001832  min_lr: 0.001832  loss: 3.7212 (3.6345)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0193  max mem: 31830
Epoch: [167]  [170/312]  eta: 0:01:23  lr: 0.001831  min_lr: 0.001831  loss: 3.4335 (3.6249)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.0193  max mem: 31830
Epoch: [167]  [180/312]  eta: 0:01:17  lr: 0.001831  min_lr: 0.001831  loss: 3.4797 (3.6230)  weight_decay: 0.0500 (0.0500)  time: 0.6521  data: 0.0238  max mem: 31830
Epoch: [167]  [190/312]  eta: 0:01:11  lr: 0.001830  min_lr: 0.001830  loss: 3.5078 (3.6136)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0463  max mem: 31830
Epoch: [167]  [200/312]  eta: 0:01:05  lr: 0.001829  min_lr: 0.001829  loss: 3.5739 (3.6138)  weight_decay: 0.0500 (0.0500)  time: 0.5162  data: 0.0235  max mem: 31830
Epoch: [167]  [210/312]  eta: 0:00:59  lr: 0.001829  min_lr: 0.001829  loss: 3.7857 (3.6159)  weight_decay: 0.0500 (0.0500)  time: 0.6102  data: 0.0082  max mem: 31830
Epoch: [167]  [220/312]  eta: 0:00:53  lr: 0.001828  min_lr: 0.001828  loss: 3.7387 (3.6172)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0164  max mem: 31830
Epoch: [167]  [230/312]  eta: 0:00:47  lr: 0.001827  min_lr: 0.001827  loss: 3.7585 (3.6210)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0092  max mem: 31830
Epoch: [167]  [240/312]  eta: 0:00:41  lr: 0.001826  min_lr: 0.001826  loss: 3.6914 (3.6069)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0148  max mem: 31830
Epoch: [167]  [250/312]  eta: 0:00:35  lr: 0.001826  min_lr: 0.001826  loss: 3.0636 (3.5923)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.0155  max mem: 31830
Epoch: [167]  [260/312]  eta: 0:00:30  lr: 0.001825  min_lr: 0.001825  loss: 3.6460 (3.5942)  weight_decay: 0.0500 (0.0500)  time: 0.6342  data: 0.0016  max mem: 31830
Epoch: [167]  [270/312]  eta: 0:00:23  lr: 0.001824  min_lr: 0.001824  loss: 3.6567 (3.5957)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0009  max mem: 31830
Epoch: [167]  [280/312]  eta: 0:00:18  lr: 0.001824  min_lr: 0.001824  loss: 3.7374 (3.6033)  weight_decay: 0.0500 (0.0500)  time: 0.5251  data: 0.0020  max mem: 31830
Epoch: [167]  [290/312]  eta: 0:00:12  lr: 0.001823  min_lr: 0.001823  loss: 3.8230 (3.6087)  weight_decay: 0.0500 (0.0500)  time: 0.5884  data: 0.0017  max mem: 31830
Epoch: [167]  [300/312]  eta: 0:00:06  lr: 0.001822  min_lr: 0.001822  loss: 3.8230 (3.6048)  weight_decay: 0.0500 (0.0500)  time: 0.4546  data: 0.0002  max mem: 31830
Epoch: [167]  [310/312]  eta: 0:00:01  lr: 0.001821  min_lr: 0.001821  loss: 3.8124 (3.6122)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [167]  [311/312]  eta: 0:00:00  lr: 0.001821  min_lr: 0.001821  loss: 3.8124 (3.6122)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [167] Total time: 0:02:55 (0.5632 s / it)
Averaged stats: lr: 0.001821  min_lr: 0.001821  loss: 3.8124 (3.5664)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 1.5370 (1.5370)  acc1: 75.0000 (75.0000)  acc5: 92.4479 (92.4479)  time: 9.2129  data: 9.0457  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7558 (1.6999)  acc1: 67.0573 (68.7040)  acc5: 89.3229 (89.5040)  time: 1.1401  data: 1.0051  max mem: 31830
Test: Total time: 0:00:10 (1.1592 s / it)
* Acc@1 69.068 Acc@5 89.288 loss 1.708
Accuracy of the model on the 50000 test images: 69.1%
Max accuracy: 70.84%
Epoch: [168]  [  0/312]  eta: 1:00:12  lr: 0.001821  min_lr: 0.001821  loss: 3.6352 (3.6352)  weight_decay: 0.0500 (0.0500)  time: 11.5773  data: 9.7543  max mem: 31830
Epoch: [168]  [ 10/312]  eta: 0:09:17  lr: 0.001821  min_lr: 0.001821  loss: 3.6429 (3.5278)  weight_decay: 0.0500 (0.0500)  time: 1.8471  data: 1.0789  max mem: 31830
Epoch: [168]  [ 20/312]  eta: 0:05:36  lr: 0.001820  min_lr: 0.001820  loss: 3.5116 (3.4625)  weight_decay: 0.0500 (0.0500)  time: 0.6297  data: 0.1060  max mem: 31830
Epoch: [168]  [ 30/312]  eta: 0:04:16  lr: 0.001819  min_lr: 0.001819  loss: 3.5135 (3.5080)  weight_decay: 0.0500 (0.0500)  time: 0.3922  data: 0.0008  max mem: 31830
Epoch: [168]  [ 40/312]  eta: 0:03:33  lr: 0.001818  min_lr: 0.001818  loss: 3.6362 (3.5108)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0009  max mem: 31830
Epoch: [168]  [ 50/312]  eta: 0:03:05  lr: 0.001818  min_lr: 0.001818  loss: 3.7464 (3.5632)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0009  max mem: 31830
Epoch: [168]  [ 60/312]  eta: 0:02:45  lr: 0.001817  min_lr: 0.001817  loss: 3.7932 (3.5688)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0009  max mem: 31830
Epoch: [168]  [ 70/312]  eta: 0:02:30  lr: 0.001816  min_lr: 0.001816  loss: 3.6624 (3.5238)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0008  max mem: 31830
Epoch: [168]  [ 80/312]  eta: 0:02:21  lr: 0.001816  min_lr: 0.001816  loss: 3.3225 (3.5298)  weight_decay: 0.0500 (0.0500)  time: 0.4569  data: 0.0545  max mem: 31830
Epoch: [168]  [ 90/312]  eta: 0:02:12  lr: 0.001815  min_lr: 0.001815  loss: 3.3394 (3.5117)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0969  max mem: 31830
Epoch: [168]  [100/312]  eta: 0:02:06  lr: 0.001814  min_lr: 0.001814  loss: 3.5469 (3.5199)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0678  max mem: 31830
Epoch: [168]  [110/312]  eta: 0:02:01  lr: 0.001813  min_lr: 0.001813  loss: 3.7112 (3.5188)  weight_decay: 0.0500 (0.0500)  time: 0.6150  data: 0.0514  max mem: 31830
Epoch: [168]  [120/312]  eta: 0:01:52  lr: 0.001813  min_lr: 0.001813  loss: 3.7189 (3.5283)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0268  max mem: 31830
Epoch: [168]  [130/312]  eta: 0:01:47  lr: 0.001812  min_lr: 0.001812  loss: 3.7861 (3.5476)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0294  max mem: 31830
Epoch: [168]  [140/312]  eta: 0:01:39  lr: 0.001811  min_lr: 0.001811  loss: 3.7955 (3.5639)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0294  max mem: 31830
Epoch: [168]  [150/312]  eta: 0:01:33  lr: 0.001811  min_lr: 0.001811  loss: 3.7730 (3.5674)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0223  max mem: 31830
Epoch: [168]  [160/312]  eta: 0:01:28  lr: 0.001810  min_lr: 0.001810  loss: 3.7717 (3.5784)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.0679  max mem: 31830
Epoch: [168]  [170/312]  eta: 0:01:21  lr: 0.001809  min_lr: 0.001809  loss: 3.7085 (3.5887)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0463  max mem: 31830
Epoch: [168]  [180/312]  eta: 0:01:15  lr: 0.001808  min_lr: 0.001808  loss: 3.6676 (3.5799)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0269  max mem: 31830
Epoch: [168]  [190/312]  eta: 0:01:10  lr: 0.001808  min_lr: 0.001808  loss: 3.6676 (3.5789)  weight_decay: 0.0500 (0.0500)  time: 0.5854  data: 0.0860  max mem: 31830
Epoch: [168]  [200/312]  eta: 0:01:04  lr: 0.001807  min_lr: 0.001807  loss: 3.6876 (3.5873)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.1109  max mem: 31830
Epoch: [168]  [210/312]  eta: 0:00:58  lr: 0.001806  min_lr: 0.001806  loss: 3.6876 (3.5762)  weight_decay: 0.0500 (0.0500)  time: 0.5484  data: 0.0670  max mem: 31830
Epoch: [168]  [220/312]  eta: 0:00:52  lr: 0.001806  min_lr: 0.001806  loss: 3.5346 (3.5778)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0295  max mem: 31830
Epoch: [168]  [230/312]  eta: 0:00:46  lr: 0.001805  min_lr: 0.001805  loss: 3.5346 (3.5720)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0284  max mem: 31830
Epoch: [168]  [240/312]  eta: 0:00:40  lr: 0.001804  min_lr: 0.001804  loss: 3.2910 (3.5611)  weight_decay: 0.0500 (0.0500)  time: 0.5647  data: 0.0726  max mem: 31830
Epoch: [168]  [250/312]  eta: 0:00:34  lr: 0.001803  min_lr: 0.001803  loss: 3.2041 (3.5464)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0658  max mem: 31830
Epoch: [168]  [260/312]  eta: 0:00:29  lr: 0.001803  min_lr: 0.001803  loss: 3.2041 (3.5351)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0616  max mem: 31830
Epoch: [168]  [270/312]  eta: 0:00:23  lr: 0.001802  min_lr: 0.001802  loss: 3.4685 (3.5319)  weight_decay: 0.0500 (0.0500)  time: 0.6226  data: 0.1151  max mem: 31830
Epoch: [168]  [280/312]  eta: 0:00:17  lr: 0.001801  min_lr: 0.001801  loss: 3.7587 (3.5429)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0634  max mem: 31830
Epoch: [168]  [290/312]  eta: 0:00:12  lr: 0.001801  min_lr: 0.001801  loss: 3.7587 (3.5422)  weight_decay: 0.0500 (0.0500)  time: 0.4959  data: 0.0460  max mem: 31830
Epoch: [168]  [300/312]  eta: 0:00:06  lr: 0.001800  min_lr: 0.001800  loss: 3.7128 (3.5464)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0438  max mem: 31830
Epoch: [168]  [310/312]  eta: 0:00:01  lr: 0.001799  min_lr: 0.001799  loss: 3.7487 (3.5474)  weight_decay: 0.0500 (0.0500)  time: 0.4220  data: 0.0067  max mem: 31830
Epoch: [168]  [311/312]  eta: 0:00:00  lr: 0.001799  min_lr: 0.001799  loss: 3.7559 (3.5481)  weight_decay: 0.0500 (0.0500)  time: 0.4216  data: 0.0067  max mem: 31830
Epoch: [168] Total time: 0:02:53 (0.5573 s / it)
Averaged stats: lr: 0.001799  min_lr: 0.001799  loss: 3.7559 (3.5237)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1663 (1.1663)  acc1: 78.7760 (78.7760)  acc5: 94.0104 (94.0104)  time: 8.6400  data: 8.4759  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5342 (1.4728)  acc1: 67.1875 (70.2880)  acc5: 89.5833 (90.1600)  time: 1.0776  data: 0.9419  max mem: 31830
Test: Total time: 0:00:09 (1.0932 s / it)
* Acc@1 69.870 Acc@5 90.136 loss 1.476
Accuracy of the model on the 50000 test images: 69.9%
Max accuracy: 70.84%
Epoch: [169]  [  0/312]  eta: 1:01:23  lr: 0.001799  min_lr: 0.001799  loss: 3.7933 (3.7933)  weight_decay: 0.0500 (0.0500)  time: 11.8065  data: 11.4149  max mem: 31830
Epoch: [169]  [ 10/312]  eta: 0:08:40  lr: 0.001798  min_lr: 0.001798  loss: 3.6862 (3.4177)  weight_decay: 0.0500 (0.0500)  time: 1.7232  data: 1.0387  max mem: 31830
Epoch: [169]  [ 20/312]  eta: 0:05:32  lr: 0.001798  min_lr: 0.001798  loss: 3.6862 (3.4524)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.0519  max mem: 31830
Epoch: [169]  [ 30/312]  eta: 0:04:13  lr: 0.001797  min_lr: 0.001797  loss: 3.7889 (3.5793)  weight_decay: 0.0500 (0.0500)  time: 0.4472  data: 0.0517  max mem: 31830
Epoch: [169]  [ 40/312]  eta: 0:03:31  lr: 0.001796  min_lr: 0.001796  loss: 3.6144 (3.5546)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0008  max mem: 31830
Epoch: [169]  [ 50/312]  eta: 0:03:04  lr: 0.001795  min_lr: 0.001795  loss: 3.3035 (3.4686)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [169]  [ 60/312]  eta: 0:02:44  lr: 0.001795  min_lr: 0.001795  loss: 3.2061 (3.4581)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0009  max mem: 31830
Epoch: [169]  [ 70/312]  eta: 0:02:31  lr: 0.001794  min_lr: 0.001794  loss: 3.5946 (3.4927)  weight_decay: 0.0500 (0.0500)  time: 0.4297  data: 0.0211  max mem: 31830
Epoch: [169]  [ 80/312]  eta: 0:02:24  lr: 0.001793  min_lr: 0.001793  loss: 3.6722 (3.4902)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0839  max mem: 31830
Epoch: [169]  [ 90/312]  eta: 0:02:13  lr: 0.001792  min_lr: 0.001792  loss: 3.3710 (3.4731)  weight_decay: 0.0500 (0.0500)  time: 0.5019  data: 0.0637  max mem: 31830
Epoch: [169]  [100/312]  eta: 0:02:09  lr: 0.001792  min_lr: 0.001792  loss: 3.3220 (3.4765)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0460  max mem: 31830
Epoch: [169]  [110/312]  eta: 0:01:59  lr: 0.001791  min_lr: 0.001791  loss: 3.4271 (3.4750)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0520  max mem: 31830
Epoch: [169]  [120/312]  eta: 0:01:52  lr: 0.001790  min_lr: 0.001790  loss: 3.4271 (3.4580)  weight_decay: 0.0500 (0.0500)  time: 0.4750  data: 0.0383  max mem: 31830
Epoch: [169]  [130/312]  eta: 0:01:47  lr: 0.001790  min_lr: 0.001790  loss: 3.5699 (3.4789)  weight_decay: 0.0500 (0.0500)  time: 0.5849  data: 0.0629  max mem: 31830
Epoch: [169]  [140/312]  eta: 0:01:40  lr: 0.001789  min_lr: 0.001789  loss: 3.6820 (3.4819)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0317  max mem: 31830
Epoch: [169]  [150/312]  eta: 0:01:34  lr: 0.001788  min_lr: 0.001788  loss: 3.7455 (3.4877)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0320  max mem: 31830
Epoch: [169]  [160/312]  eta: 0:01:28  lr: 0.001787  min_lr: 0.001787  loss: 3.7455 (3.4962)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0488  max mem: 31830
Epoch: [169]  [170/312]  eta: 0:01:21  lr: 0.001787  min_lr: 0.001787  loss: 3.5009 (3.4823)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0485  max mem: 31830
Epoch: [169]  [180/312]  eta: 0:01:15  lr: 0.001786  min_lr: 0.001786  loss: 3.2713 (3.4661)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0518  max mem: 31830
Epoch: [169]  [190/312]  eta: 0:01:09  lr: 0.001785  min_lr: 0.001785  loss: 3.3928 (3.4718)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0218  max mem: 31830
Epoch: [169]  [200/312]  eta: 0:01:03  lr: 0.001785  min_lr: 0.001785  loss: 3.7452 (3.4816)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0299  max mem: 31830
Epoch: [169]  [210/312]  eta: 0:00:58  lr: 0.001784  min_lr: 0.001784  loss: 3.6806 (3.4864)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.0437  max mem: 31830
Epoch: [169]  [220/312]  eta: 0:00:52  lr: 0.001783  min_lr: 0.001783  loss: 3.6373 (3.4930)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0151  max mem: 31830
Epoch: [169]  [230/312]  eta: 0:00:46  lr: 0.001782  min_lr: 0.001782  loss: 3.5264 (3.4851)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0094  max mem: 31830
Epoch: [169]  [240/312]  eta: 0:00:40  lr: 0.001782  min_lr: 0.001782  loss: 3.4759 (3.4844)  weight_decay: 0.0500 (0.0500)  time: 0.5492  data: 0.0097  max mem: 31830
Epoch: [169]  [250/312]  eta: 0:00:34  lr: 0.001781  min_lr: 0.001781  loss: 3.6972 (3.4872)  weight_decay: 0.0500 (0.0500)  time: 0.4986  data: 0.0055  max mem: 31830
Epoch: [169]  [260/312]  eta: 0:00:29  lr: 0.001780  min_lr: 0.001780  loss: 3.7442 (3.4922)  weight_decay: 0.0500 (0.0500)  time: 0.5579  data: 0.0174  max mem: 31830
Epoch: [169]  [270/312]  eta: 0:00:23  lr: 0.001780  min_lr: 0.001780  loss: 3.7122 (3.4971)  weight_decay: 0.0500 (0.0500)  time: 0.6155  data: 0.0133  max mem: 31830
Epoch: [169]  [280/312]  eta: 0:00:17  lr: 0.001779  min_lr: 0.001779  loss: 3.7101 (3.5001)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0152  max mem: 31830
Epoch: [169]  [290/312]  eta: 0:00:12  lr: 0.001778  min_lr: 0.001778  loss: 3.7289 (3.5028)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0280  max mem: 31830
Epoch: [169]  [300/312]  eta: 0:00:06  lr: 0.001777  min_lr: 0.001777  loss: 3.6210 (3.5080)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0136  max mem: 31830
Epoch: [169]  [310/312]  eta: 0:00:01  lr: 0.001777  min_lr: 0.001777  loss: 3.6623 (3.5151)  weight_decay: 0.0500 (0.0500)  time: 0.4107  data: 0.0002  max mem: 31830
Epoch: [169]  [311/312]  eta: 0:00:00  lr: 0.001777  min_lr: 0.001777  loss: 3.7608 (3.5162)  weight_decay: 0.0500 (0.0500)  time: 0.3946  data: 0.0002  max mem: 31830
Epoch: [169] Total time: 0:02:53 (0.5563 s / it)
Averaged stats: lr: 0.001777  min_lr: 0.001777  loss: 3.7608 (3.5283)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1404 (1.1404)  acc1: 78.2552 (78.2552)  acc5: 95.1823 (95.1823)  time: 8.6116  data: 8.4464  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6839 (1.5353)  acc1: 69.0104 (70.8960)  acc5: 89.7135 (90.4640)  time: 1.0734  data: 0.9386  max mem: 31830
Test: Total time: 0:00:09 (1.0829 s / it)
* Acc@1 71.000 Acc@5 90.304 loss 1.540
Accuracy of the model on the 50000 test images: 71.0%
Max accuracy: 71.00%
Epoch: [170]  [  0/312]  eta: 0:58:54  lr: 0.001777  min_lr: 0.001777  loss: 2.4884 (2.4884)  weight_decay: 0.0500 (0.0500)  time: 11.3301  data: 10.9341  max mem: 31830
Epoch: [170]  [ 10/312]  eta: 0:08:22  lr: 0.001776  min_lr: 0.001776  loss: 3.6663 (3.3926)  weight_decay: 0.0500 (0.0500)  time: 1.6633  data: 0.9946  max mem: 31830
Epoch: [170]  [ 20/312]  eta: 0:05:27  lr: 0.001775  min_lr: 0.001775  loss: 3.7022 (3.5227)  weight_decay: 0.0500 (0.0500)  time: 0.6117  data: 0.0677  max mem: 31830
Epoch: [170]  [ 30/312]  eta: 0:04:10  lr: 0.001774  min_lr: 0.001774  loss: 3.6877 (3.4737)  weight_decay: 0.0500 (0.0500)  time: 0.4636  data: 0.0677  max mem: 31830
Epoch: [170]  [ 40/312]  eta: 0:03:29  lr: 0.001774  min_lr: 0.001774  loss: 3.5103 (3.4784)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0008  max mem: 31830
Epoch: [170]  [ 50/312]  eta: 0:03:02  lr: 0.001773  min_lr: 0.001773  loss: 3.5255 (3.4613)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0009  max mem: 31830
Epoch: [170]  [ 60/312]  eta: 0:02:43  lr: 0.001772  min_lr: 0.001772  loss: 3.7266 (3.4843)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0011  max mem: 31830
Epoch: [170]  [ 70/312]  eta: 0:02:32  lr: 0.001772  min_lr: 0.001772  loss: 3.7266 (3.4803)  weight_decay: 0.0500 (0.0500)  time: 0.4555  data: 0.0648  max mem: 31830
Epoch: [170]  [ 80/312]  eta: 0:02:22  lr: 0.001771  min_lr: 0.001771  loss: 3.7784 (3.5183)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.1170  max mem: 31830
Epoch: [170]  [ 90/312]  eta: 0:02:14  lr: 0.001770  min_lr: 0.001770  loss: 3.7075 (3.5015)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0985  max mem: 31830
Epoch: [170]  [100/312]  eta: 0:02:07  lr: 0.001769  min_lr: 0.001769  loss: 3.5195 (3.5113)  weight_decay: 0.0500 (0.0500)  time: 0.5640  data: 0.1069  max mem: 31830
Epoch: [170]  [110/312]  eta: 0:01:58  lr: 0.001769  min_lr: 0.001769  loss: 3.5195 (3.5142)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0634  max mem: 31830
Epoch: [170]  [120/312]  eta: 0:01:53  lr: 0.001768  min_lr: 0.001768  loss: 3.6145 (3.5367)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0707  max mem: 31830
Epoch: [170]  [130/312]  eta: 0:01:46  lr: 0.001767  min_lr: 0.001767  loss: 3.7660 (3.5212)  weight_decay: 0.0500 (0.0500)  time: 0.5677  data: 0.1134  max mem: 31830
Epoch: [170]  [140/312]  eta: 0:01:39  lr: 0.001767  min_lr: 0.001767  loss: 3.3305 (3.5046)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0508  max mem: 31830
Epoch: [170]  [150/312]  eta: 0:01:33  lr: 0.001766  min_lr: 0.001766  loss: 3.6328 (3.5122)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0688  max mem: 31830
Epoch: [170]  [160/312]  eta: 0:01:27  lr: 0.001765  min_lr: 0.001765  loss: 3.6328 (3.5014)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0998  max mem: 31830
Epoch: [170]  [170/312]  eta: 0:01:21  lr: 0.001764  min_lr: 0.001764  loss: 3.3504 (3.4879)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.0514  max mem: 31830
Epoch: [170]  [180/312]  eta: 0:01:15  lr: 0.001764  min_lr: 0.001764  loss: 3.4705 (3.4894)  weight_decay: 0.0500 (0.0500)  time: 0.5157  data: 0.0546  max mem: 31830
Epoch: [170]  [190/312]  eta: 0:01:09  lr: 0.001763  min_lr: 0.001763  loss: 3.8278 (3.4964)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0419  max mem: 31830
Epoch: [170]  [200/312]  eta: 0:01:04  lr: 0.001762  min_lr: 0.001762  loss: 3.7311 (3.4894)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.0299  max mem: 31830
Epoch: [170]  [210/312]  eta: 0:00:58  lr: 0.001762  min_lr: 0.001762  loss: 3.5043 (3.4890)  weight_decay: 0.0500 (0.0500)  time: 0.5628  data: 0.0899  max mem: 31830
Epoch: [170]  [220/312]  eta: 0:00:52  lr: 0.001761  min_lr: 0.001761  loss: 3.7260 (3.4902)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0623  max mem: 31830
Epoch: [170]  [230/312]  eta: 0:00:46  lr: 0.001760  min_lr: 0.001760  loss: 3.4101 (3.4822)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0330  max mem: 31830
Epoch: [170]  [240/312]  eta: 0:00:40  lr: 0.001759  min_lr: 0.001759  loss: 3.6033 (3.4953)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0617  max mem: 31830
Epoch: [170]  [250/312]  eta: 0:00:35  lr: 0.001759  min_lr: 0.001759  loss: 3.6993 (3.4921)  weight_decay: 0.0500 (0.0500)  time: 0.5844  data: 0.0443  max mem: 31830
Epoch: [170]  [260/312]  eta: 0:00:29  lr: 0.001758  min_lr: 0.001758  loss: 3.5261 (3.4936)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0331  max mem: 31830
Epoch: [170]  [270/312]  eta: 0:00:23  lr: 0.001757  min_lr: 0.001757  loss: 3.5320 (3.4932)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0196  max mem: 31830
Epoch: [170]  [280/312]  eta: 0:00:18  lr: 0.001757  min_lr: 0.001757  loss: 3.5320 (3.4873)  weight_decay: 0.0500 (0.0500)  time: 0.6068  data: 0.0165  max mem: 31830
Epoch: [170]  [290/312]  eta: 0:00:12  lr: 0.001756  min_lr: 0.001756  loss: 3.7076 (3.4888)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0269  max mem: 31830
Epoch: [170]  [300/312]  eta: 0:00:06  lr: 0.001755  min_lr: 0.001755  loss: 3.6404 (3.4925)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0121  max mem: 31830
Epoch: [170]  [310/312]  eta: 0:00:01  lr: 0.001754  min_lr: 0.001754  loss: 3.4628 (3.4904)  weight_decay: 0.0500 (0.0500)  time: 0.4220  data: 0.0002  max mem: 31830
Epoch: [170]  [311/312]  eta: 0:00:00  lr: 0.001754  min_lr: 0.001754  loss: 3.4628 (3.4878)  weight_decay: 0.0500 (0.0500)  time: 0.4212  data: 0.0002  max mem: 31830
Epoch: [170] Total time: 0:02:52 (0.5542 s / it)
Averaged stats: lr: 0.001754  min_lr: 0.001754  loss: 3.4628 (3.5334)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.2405 (1.2405)  acc1: 77.6042 (77.6042)  acc5: 93.7500 (93.7500)  time: 9.0325  data: 8.8651  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6097 (1.5071)  acc1: 70.4427 (70.4640)  acc5: 90.1042 (89.9680)  time: 1.1209  data: 0.9851  max mem: 31830
Test: Total time: 0:00:10 (1.1456 s / it)
* Acc@1 70.168 Acc@5 90.336 loss 1.509
Accuracy of the model on the 50000 test images: 70.2%
Max accuracy: 71.00%
Epoch: [171]  [  0/312]  eta: 1:02:13  lr: 0.001754  min_lr: 0.001754  loss: 3.9556 (3.9556)  weight_decay: 0.0500 (0.0500)  time: 11.9678  data: 8.5448  max mem: 31830
Epoch: [171]  [ 10/312]  eta: 0:08:42  lr: 0.001754  min_lr: 0.001754  loss: 3.8185 (3.7163)  weight_decay: 0.0500 (0.0500)  time: 1.7304  data: 1.0208  max mem: 31830
Epoch: [171]  [ 20/312]  eta: 0:05:52  lr: 0.001753  min_lr: 0.001753  loss: 3.7278 (3.6533)  weight_decay: 0.0500 (0.0500)  time: 0.6680  data: 0.2052  max mem: 31830
Epoch: [171]  [ 30/312]  eta: 0:04:25  lr: 0.001752  min_lr: 0.001752  loss: 3.4557 (3.4991)  weight_decay: 0.0500 (0.0500)  time: 0.5086  data: 0.0714  max mem: 31830
Epoch: [171]  [ 40/312]  eta: 0:03:40  lr: 0.001751  min_lr: 0.001751  loss: 3.2238 (3.4663)  weight_decay: 0.0500 (0.0500)  time: 0.3940  data: 0.0008  max mem: 31830
Epoch: [171]  [ 50/312]  eta: 0:03:11  lr: 0.001751  min_lr: 0.001751  loss: 3.4029 (3.4708)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0013  max mem: 31830
Epoch: [171]  [ 60/312]  eta: 0:02:50  lr: 0.001750  min_lr: 0.001750  loss: 3.6444 (3.4882)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0018  max mem: 31830
Epoch: [171]  [ 70/312]  eta: 0:02:33  lr: 0.001749  min_lr: 0.001749  loss: 3.7229 (3.4974)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0020  max mem: 31830
Epoch: [171]  [ 80/312]  eta: 0:02:21  lr: 0.001749  min_lr: 0.001749  loss: 3.5491 (3.4902)  weight_decay: 0.0500 (0.0500)  time: 0.4148  data: 0.0182  max mem: 31830
Epoch: [171]  [ 90/312]  eta: 0:02:15  lr: 0.001748  min_lr: 0.001748  loss: 3.5491 (3.4851)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0862  max mem: 31830
Epoch: [171]  [100/312]  eta: 0:02:09  lr: 0.001747  min_lr: 0.001747  loss: 3.6831 (3.4971)  weight_decay: 0.0500 (0.0500)  time: 0.6072  data: 0.1210  max mem: 31830
Epoch: [171]  [110/312]  eta: 0:02:00  lr: 0.001747  min_lr: 0.001747  loss: 3.2580 (3.4732)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0525  max mem: 31830
Epoch: [171]  [120/312]  eta: 0:01:55  lr: 0.001746  min_lr: 0.001746  loss: 3.3586 (3.4821)  weight_decay: 0.0500 (0.0500)  time: 0.5698  data: 0.1199  max mem: 31830
Epoch: [171]  [130/312]  eta: 0:01:49  lr: 0.001745  min_lr: 0.001745  loss: 3.4485 (3.4675)  weight_decay: 0.0500 (0.0500)  time: 0.6344  data: 0.2141  max mem: 31830
Epoch: [171]  [140/312]  eta: 0:01:41  lr: 0.001744  min_lr: 0.001744  loss: 3.4562 (3.4896)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0952  max mem: 31830
Epoch: [171]  [150/312]  eta: 0:01:36  lr: 0.001744  min_lr: 0.001744  loss: 3.8475 (3.4969)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.1117  max mem: 31830
Epoch: [171]  [160/312]  eta: 0:01:29  lr: 0.001743  min_lr: 0.001743  loss: 3.6297 (3.5009)  weight_decay: 0.0500 (0.0500)  time: 0.5828  data: 0.1203  max mem: 31830
Epoch: [171]  [170/312]  eta: 0:01:23  lr: 0.001742  min_lr: 0.001742  loss: 3.6297 (3.5060)  weight_decay: 0.0500 (0.0500)  time: 0.5383  data: 0.1063  max mem: 31830
Epoch: [171]  [180/312]  eta: 0:01:17  lr: 0.001742  min_lr: 0.001742  loss: 3.7192 (3.5189)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.1793  max mem: 31830
Epoch: [171]  [190/312]  eta: 0:01:10  lr: 0.001741  min_lr: 0.001741  loss: 3.7033 (3.5114)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0829  max mem: 31830
Epoch: [171]  [200/312]  eta: 0:01:04  lr: 0.001740  min_lr: 0.001740  loss: 3.6428 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 0.5127  data: 0.0805  max mem: 31830
Epoch: [171]  [210/312]  eta: 0:00:59  lr: 0.001739  min_lr: 0.001739  loss: 3.6721 (3.5199)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.1521  max mem: 31830
Epoch: [171]  [220/312]  eta: 0:00:53  lr: 0.001739  min_lr: 0.001739  loss: 3.6569 (3.5222)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0729  max mem: 31830
Epoch: [171]  [230/312]  eta: 0:00:47  lr: 0.001738  min_lr: 0.001738  loss: 3.6728 (3.5243)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0818  max mem: 31830
Epoch: [171]  [240/312]  eta: 0:00:41  lr: 0.001737  min_lr: 0.001737  loss: 3.7802 (3.5387)  weight_decay: 0.0500 (0.0500)  time: 0.5736  data: 0.0995  max mem: 31830
Epoch: [171]  [250/312]  eta: 0:00:35  lr: 0.001737  min_lr: 0.001737  loss: 3.8450 (3.5434)  weight_decay: 0.0500 (0.0500)  time: 0.5616  data: 0.0870  max mem: 31830
Epoch: [171]  [260/312]  eta: 0:00:29  lr: 0.001736  min_lr: 0.001736  loss: 3.5811 (3.5428)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.1228  max mem: 31830
Epoch: [171]  [270/312]  eta: 0:00:24  lr: 0.001735  min_lr: 0.001735  loss: 3.5811 (3.5349)  weight_decay: 0.0500 (0.0500)  time: 0.5616  data: 0.0544  max mem: 31830
Epoch: [171]  [280/312]  eta: 0:00:18  lr: 0.001734  min_lr: 0.001734  loss: 3.4438 (3.5321)  weight_decay: 0.0500 (0.0500)  time: 0.5304  data: 0.0643  max mem: 31830
Epoch: [171]  [290/312]  eta: 0:00:12  lr: 0.001734  min_lr: 0.001734  loss: 3.3900 (3.5211)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.1036  max mem: 31830
Epoch: [171]  [300/312]  eta: 0:00:06  lr: 0.001733  min_lr: 0.001733  loss: 3.4829 (3.5231)  weight_decay: 0.0500 (0.0500)  time: 0.4734  data: 0.0399  max mem: 31830
Epoch: [171]  [310/312]  eta: 0:00:01  lr: 0.001732  min_lr: 0.001732  loss: 3.4177 (3.5110)  weight_decay: 0.0500 (0.0500)  time: 0.3844  data: 0.0001  max mem: 31830
Epoch: [171]  [311/312]  eta: 0:00:00  lr: 0.001732  min_lr: 0.001732  loss: 3.3096 (3.5103)  weight_decay: 0.0500 (0.0500)  time: 0.3843  data: 0.0001  max mem: 31830
Epoch: [171] Total time: 0:02:55 (0.5631 s / it)
Averaged stats: lr: 0.001732  min_lr: 0.001732  loss: 3.3096 (3.5382)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.0076 (1.0076)  acc1: 77.7344 (77.7344)  acc5: 93.6198 (93.6198)  time: 8.9455  data: 8.7783  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3477 (1.2634)  acc1: 70.0521 (71.3440)  acc5: 91.4062 (90.6560)  time: 1.1114  data: 0.9754  max mem: 31830
Test: Total time: 0:00:10 (1.1256 s / it)
* Acc@1 71.160 Acc@5 90.728 loss 1.265
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 71.16%
Epoch: [172]  [  0/312]  eta: 0:58:01  lr: 0.001732  min_lr: 0.001732  loss: 3.5257 (3.5257)  weight_decay: 0.0500 (0.0500)  time: 11.1578  data: 9.9052  max mem: 31830
Epoch: [172]  [ 10/312]  eta: 0:09:14  lr: 0.001731  min_lr: 0.001731  loss: 3.5257 (3.3534)  weight_decay: 0.0500 (0.0500)  time: 1.8376  data: 1.1859  max mem: 31830
Epoch: [172]  [ 20/312]  eta: 0:05:34  lr: 0.001731  min_lr: 0.001731  loss: 3.5972 (3.4788)  weight_decay: 0.0500 (0.0500)  time: 0.6464  data: 0.1574  max mem: 31830
Epoch: [172]  [ 30/312]  eta: 0:04:15  lr: 0.001730  min_lr: 0.001730  loss: 3.7302 (3.4908)  weight_decay: 0.0500 (0.0500)  time: 0.3935  data: 0.0011  max mem: 31830
Epoch: [172]  [ 40/312]  eta: 0:03:32  lr: 0.001729  min_lr: 0.001729  loss: 3.7302 (3.5700)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0015  max mem: 31830
Epoch: [172]  [ 50/312]  eta: 0:03:05  lr: 0.001729  min_lr: 0.001729  loss: 3.6816 (3.5459)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0020  max mem: 31830
Epoch: [172]  [ 60/312]  eta: 0:02:45  lr: 0.001728  min_lr: 0.001728  loss: 3.6549 (3.5448)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0017  max mem: 31830
Epoch: [172]  [ 70/312]  eta: 0:02:30  lr: 0.001727  min_lr: 0.001727  loss: 3.6204 (3.5265)  weight_decay: 0.0500 (0.0500)  time: 0.4026  data: 0.0008  max mem: 31830
Epoch: [172]  [ 80/312]  eta: 0:02:22  lr: 0.001726  min_lr: 0.001726  loss: 3.6805 (3.5454)  weight_decay: 0.0500 (0.0500)  time: 0.4793  data: 0.0656  max mem: 31830
Epoch: [172]  [ 90/312]  eta: 0:02:13  lr: 0.001726  min_lr: 0.001726  loss: 3.6258 (3.5410)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0849  max mem: 31830
Epoch: [172]  [100/312]  eta: 0:02:06  lr: 0.001725  min_lr: 0.001725  loss: 3.6258 (3.5406)  weight_decay: 0.0500 (0.0500)  time: 0.5306  data: 0.0836  max mem: 31830
Epoch: [172]  [110/312]  eta: 0:02:00  lr: 0.001724  min_lr: 0.001724  loss: 3.4814 (3.5267)  weight_decay: 0.0500 (0.0500)  time: 0.5700  data: 0.1435  max mem: 31830
Epoch: [172]  [120/312]  eta: 0:01:53  lr: 0.001724  min_lr: 0.001724  loss: 3.5804 (3.5363)  weight_decay: 0.0500 (0.0500)  time: 0.5655  data: 0.0950  max mem: 31830
Epoch: [172]  [130/312]  eta: 0:01:47  lr: 0.001723  min_lr: 0.001723  loss: 3.5804 (3.5213)  weight_decay: 0.0500 (0.0500)  time: 0.5626  data: 0.0670  max mem: 31830
Epoch: [172]  [140/312]  eta: 0:01:41  lr: 0.001722  min_lr: 0.001722  loss: 3.4531 (3.5253)  weight_decay: 0.0500 (0.0500)  time: 0.5884  data: 0.1081  max mem: 31830
Epoch: [172]  [150/312]  eta: 0:01:34  lr: 0.001721  min_lr: 0.001721  loss: 3.6592 (3.5231)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0573  max mem: 31830
Epoch: [172]  [160/312]  eta: 0:01:28  lr: 0.001721  min_lr: 0.001721  loss: 3.6774 (3.5389)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0583  max mem: 31830
Epoch: [172]  [170/312]  eta: 0:01:21  lr: 0.001720  min_lr: 0.001720  loss: 3.7521 (3.5435)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0816  max mem: 31830
Epoch: [172]  [180/312]  eta: 0:01:16  lr: 0.001719  min_lr: 0.001719  loss: 3.7775 (3.5521)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0707  max mem: 31830
Epoch: [172]  [190/312]  eta: 0:01:10  lr: 0.001719  min_lr: 0.001719  loss: 3.7881 (3.5527)  weight_decay: 0.0500 (0.0500)  time: 0.5920  data: 0.1425  max mem: 31830
Epoch: [172]  [200/312]  eta: 0:01:04  lr: 0.001718  min_lr: 0.001718  loss: 3.6073 (3.5437)  weight_decay: 0.0500 (0.0500)  time: 0.5660  data: 0.1589  max mem: 31830
Epoch: [172]  [210/312]  eta: 0:00:58  lr: 0.001717  min_lr: 0.001717  loss: 3.6581 (3.5439)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.1240  max mem: 31830
Epoch: [172]  [220/312]  eta: 0:00:52  lr: 0.001716  min_lr: 0.001716  loss: 3.8350 (3.5515)  weight_decay: 0.0500 (0.0500)  time: 0.5741  data: 0.1821  max mem: 31830
Epoch: [172]  [230/312]  eta: 0:00:46  lr: 0.001716  min_lr: 0.001716  loss: 3.6372 (3.5531)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.1216  max mem: 31830
Epoch: [172]  [240/312]  eta: 0:00:40  lr: 0.001715  min_lr: 0.001715  loss: 3.5964 (3.5559)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.1012  max mem: 31830
Epoch: [172]  [250/312]  eta: 0:00:35  lr: 0.001714  min_lr: 0.001714  loss: 3.5231 (3.5482)  weight_decay: 0.0500 (0.0500)  time: 0.5747  data: 0.1472  max mem: 31830
Epoch: [172]  [260/312]  eta: 0:00:29  lr: 0.001714  min_lr: 0.001714  loss: 3.5231 (3.5440)  weight_decay: 0.0500 (0.0500)  time: 0.5385  data: 0.1082  max mem: 31830
Epoch: [172]  [270/312]  eta: 0:00:23  lr: 0.001713  min_lr: 0.001713  loss: 3.7031 (3.5434)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.1636  max mem: 31830
Epoch: [172]  [280/312]  eta: 0:00:18  lr: 0.001712  min_lr: 0.001712  loss: 3.7290 (3.5508)  weight_decay: 0.0500 (0.0500)  time: 0.5699  data: 0.1680  max mem: 31830
Epoch: [172]  [290/312]  eta: 0:00:12  lr: 0.001711  min_lr: 0.001711  loss: 3.6947 (3.5527)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.1112  max mem: 31830
Epoch: [172]  [300/312]  eta: 0:00:06  lr: 0.001711  min_lr: 0.001711  loss: 3.4727 (3.5522)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0926  max mem: 31830
Epoch: [172]  [310/312]  eta: 0:00:01  lr: 0.001710  min_lr: 0.001710  loss: 3.3942 (3.5444)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0476  max mem: 31830
Epoch: [172]  [311/312]  eta: 0:00:00  lr: 0.001710  min_lr: 0.001710  loss: 3.3942 (3.5434)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0476  max mem: 31830
Epoch: [172] Total time: 0:02:54 (0.5605 s / it)
Averaged stats: lr: 0.001710  min_lr: 0.001710  loss: 3.3942 (3.5207)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.2491 (1.2491)  acc1: 78.9062 (78.9062)  acc5: 92.9688 (92.9688)  time: 8.6773  data: 8.5093  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5779 (1.4729)  acc1: 68.4896 (71.1840)  acc5: 89.1927 (89.8560)  time: 1.0811  data: 0.9456  max mem: 31830
Test: Total time: 0:00:10 (1.1124 s / it)
* Acc@1 70.638 Acc@5 90.018 loss 1.484
Accuracy of the model on the 50000 test images: 70.6%
Max accuracy: 71.16%
Epoch: [173]  [  0/312]  eta: 1:04:29  lr: 0.001710  min_lr: 0.001710  loss: 4.2323 (4.2323)  weight_decay: 0.0500 (0.0500)  time: 12.4021  data: 8.4883  max mem: 31830
Epoch: [173]  [ 10/312]  eta: 0:08:40  lr: 0.001709  min_lr: 0.001709  loss: 3.4589 (3.3747)  weight_decay: 0.0500 (0.0500)  time: 1.7222  data: 1.0157  max mem: 31830
Epoch: [173]  [ 20/312]  eta: 0:05:39  lr: 0.001708  min_lr: 0.001708  loss: 3.6492 (3.4207)  weight_decay: 0.0500 (0.0500)  time: 0.6020  data: 0.1346  max mem: 31830
Epoch: [173]  [ 30/312]  eta: 0:04:18  lr: 0.001708  min_lr: 0.001708  loss: 3.7050 (3.4029)  weight_decay: 0.0500 (0.0500)  time: 0.4711  data: 0.0007  max mem: 31830
Epoch: [173]  [ 40/312]  eta: 0:03:34  lr: 0.001707  min_lr: 0.001707  loss: 3.6898 (3.4079)  weight_decay: 0.0500 (0.0500)  time: 0.3935  data: 0.0007  max mem: 31830
Epoch: [173]  [ 50/312]  eta: 0:03:06  lr: 0.001706  min_lr: 0.001706  loss: 3.6898 (3.4494)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0011  max mem: 31830
Epoch: [173]  [ 60/312]  eta: 0:02:46  lr: 0.001706  min_lr: 0.001706  loss: 3.7530 (3.5035)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0012  max mem: 31830
Epoch: [173]  [ 70/312]  eta: 0:02:33  lr: 0.001705  min_lr: 0.001705  loss: 3.6950 (3.4817)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0009  max mem: 31830
Epoch: [173]  [ 80/312]  eta: 0:02:25  lr: 0.001704  min_lr: 0.001704  loss: 3.5199 (3.5113)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0482  max mem: 31830
Epoch: [173]  [ 90/312]  eta: 0:02:14  lr: 0.001703  min_lr: 0.001703  loss: 3.8159 (3.5311)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0704  max mem: 31830
Epoch: [173]  [100/312]  eta: 0:02:08  lr: 0.001703  min_lr: 0.001703  loss: 3.6939 (3.5343)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0691  max mem: 31830
Epoch: [173]  [110/312]  eta: 0:01:59  lr: 0.001702  min_lr: 0.001702  loss: 3.7605 (3.5476)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0907  max mem: 31830
Epoch: [173]  [120/312]  eta: 0:01:55  lr: 0.001701  min_lr: 0.001701  loss: 3.7428 (3.5425)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.1257  max mem: 31830
Epoch: [173]  [130/312]  eta: 0:01:48  lr: 0.001701  min_lr: 0.001701  loss: 3.3891 (3.5121)  weight_decay: 0.0500 (0.0500)  time: 0.5942  data: 0.0821  max mem: 31830
Epoch: [173]  [140/312]  eta: 0:01:40  lr: 0.001700  min_lr: 0.001700  loss: 3.5529 (3.5270)  weight_decay: 0.0500 (0.0500)  time: 0.4651  data: 0.0216  max mem: 31830
Epoch: [173]  [150/312]  eta: 0:01:33  lr: 0.001699  min_lr: 0.001699  loss: 3.4609 (3.4995)  weight_decay: 0.0500 (0.0500)  time: 0.4837  data: 0.0268  max mem: 31830
Epoch: [173]  [160/312]  eta: 0:01:28  lr: 0.001699  min_lr: 0.001699  loss: 3.4609 (3.4983)  weight_decay: 0.0500 (0.0500)  time: 0.5667  data: 0.0709  max mem: 31830
Epoch: [173]  [170/312]  eta: 0:01:22  lr: 0.001698  min_lr: 0.001698  loss: 3.6022 (3.4927)  weight_decay: 0.0500 (0.0500)  time: 0.5911  data: 0.1345  max mem: 31830
Epoch: [173]  [180/312]  eta: 0:01:15  lr: 0.001697  min_lr: 0.001697  loss: 3.5126 (3.4963)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0697  max mem: 31830
Epoch: [173]  [190/312]  eta: 0:01:09  lr: 0.001696  min_lr: 0.001696  loss: 3.5413 (3.4829)  weight_decay: 0.0500 (0.0500)  time: 0.4986  data: 0.0654  max mem: 31830
Epoch: [173]  [200/312]  eta: 0:01:04  lr: 0.001696  min_lr: 0.001696  loss: 3.5610 (3.4948)  weight_decay: 0.0500 (0.0500)  time: 0.5995  data: 0.1543  max mem: 31830
Epoch: [173]  [210/312]  eta: 0:00:58  lr: 0.001695  min_lr: 0.001695  loss: 3.7130 (3.5002)  weight_decay: 0.0500 (0.0500)  time: 0.5512  data: 0.0897  max mem: 31830
Epoch: [173]  [220/312]  eta: 0:00:52  lr: 0.001694  min_lr: 0.001694  loss: 3.7038 (3.5062)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0672  max mem: 31830
Epoch: [173]  [230/312]  eta: 0:00:46  lr: 0.001694  min_lr: 0.001694  loss: 3.6451 (3.5124)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.0823  max mem: 31830
Epoch: [173]  [240/312]  eta: 0:00:40  lr: 0.001693  min_lr: 0.001693  loss: 3.6451 (3.5130)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.0674  max mem: 31830
Epoch: [173]  [250/312]  eta: 0:00:35  lr: 0.001692  min_lr: 0.001692  loss: 3.5552 (3.5123)  weight_decay: 0.0500 (0.0500)  time: 0.5732  data: 0.1410  max mem: 31830
Epoch: [173]  [260/312]  eta: 0:00:29  lr: 0.001691  min_lr: 0.001691  loss: 3.7189 (3.5174)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0896  max mem: 31830
Epoch: [173]  [270/312]  eta: 0:00:23  lr: 0.001691  min_lr: 0.001691  loss: 3.7189 (3.5180)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0588  max mem: 31830
Epoch: [173]  [280/312]  eta: 0:00:18  lr: 0.001690  min_lr: 0.001690  loss: 3.6704 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 0.6376  data: 0.1331  max mem: 31830
Epoch: [173]  [290/312]  eta: 0:00:12  lr: 0.001689  min_lr: 0.001689  loss: 3.7665 (3.5298)  weight_decay: 0.0500 (0.0500)  time: 0.5380  data: 0.0747  max mem: 31830
Epoch: [173]  [300/312]  eta: 0:00:06  lr: 0.001689  min_lr: 0.001689  loss: 3.7103 (3.5293)  weight_decay: 0.0500 (0.0500)  time: 0.4544  data: 0.0339  max mem: 31830
Epoch: [173]  [310/312]  eta: 0:00:01  lr: 0.001688  min_lr: 0.001688  loss: 3.6839 (3.5281)  weight_decay: 0.0500 (0.0500)  time: 0.4498  data: 0.0339  max mem: 31830
Epoch: [173]  [311/312]  eta: 0:00:00  lr: 0.001688  min_lr: 0.001688  loss: 3.6839 (3.5275)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0339  max mem: 31830
Epoch: [173] Total time: 0:02:54 (0.5591 s / it)
Averaged stats: lr: 0.001688  min_lr: 0.001688  loss: 3.6839 (3.5280)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.2532 (1.2532)  acc1: 78.2552 (78.2552)  acc5: 95.1823 (95.1823)  time: 8.7278  data: 8.5602  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6042 (1.5153)  acc1: 70.4427 (71.0080)  acc5: 90.1042 (90.4000)  time: 1.0870  data: 0.9512  max mem: 31830
Test: Total time: 0:00:09 (1.1091 s / it)
* Acc@1 71.074 Acc@5 90.558 loss 1.519
Accuracy of the model on the 50000 test images: 71.1%
Max accuracy: 71.16%
Epoch: [174]  [  0/312]  eta: 1:03:02  lr: 0.001688  min_lr: 0.001688  loss: 3.4021 (3.4021)  weight_decay: 0.0500 (0.0500)  time: 12.1245  data: 11.7293  max mem: 31830
Epoch: [174]  [ 10/312]  eta: 0:08:21  lr: 0.001687  min_lr: 0.001687  loss: 3.5414 (3.5402)  weight_decay: 0.0500 (0.0500)  time: 1.6622  data: 1.0668  max mem: 31830
Epoch: [174]  [ 20/312]  eta: 0:05:24  lr: 0.001686  min_lr: 0.001686  loss: 3.5650 (3.5127)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0420  max mem: 31830
Epoch: [174]  [ 30/312]  eta: 0:04:08  lr: 0.001686  min_lr: 0.001686  loss: 3.5650 (3.5056)  weight_decay: 0.0500 (0.0500)  time: 0.4511  data: 0.0423  max mem: 31830
Epoch: [174]  [ 40/312]  eta: 0:03:27  lr: 0.001685  min_lr: 0.001685  loss: 3.6780 (3.5233)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0013  max mem: 31830
Epoch: [174]  [ 50/312]  eta: 0:03:05  lr: 0.001684  min_lr: 0.001684  loss: 3.6780 (3.5095)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0289  max mem: 31830
Epoch: [174]  [ 60/312]  eta: 0:02:45  lr: 0.001683  min_lr: 0.001683  loss: 3.2357 (3.4658)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0286  max mem: 31830
Epoch: [174]  [ 70/312]  eta: 0:02:34  lr: 0.001683  min_lr: 0.001683  loss: 3.2357 (3.4194)  weight_decay: 0.0500 (0.0500)  time: 0.4649  data: 0.0686  max mem: 31830
Epoch: [174]  [ 80/312]  eta: 0:02:27  lr: 0.001682  min_lr: 0.001682  loss: 3.4078 (3.4038)  weight_decay: 0.0500 (0.0500)  time: 0.5715  data: 0.1594  max mem: 31830
Epoch: [174]  [ 90/312]  eta: 0:02:16  lr: 0.001681  min_lr: 0.001681  loss: 3.5007 (3.4224)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0919  max mem: 31830
Epoch: [174]  [100/312]  eta: 0:02:10  lr: 0.001681  min_lr: 0.001681  loss: 3.7795 (3.4648)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0768  max mem: 31830
Epoch: [174]  [110/312]  eta: 0:01:59  lr: 0.001680  min_lr: 0.001680  loss: 3.6444 (3.4696)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0767  max mem: 31830
Epoch: [174]  [120/312]  eta: 0:01:53  lr: 0.001679  min_lr: 0.001679  loss: 3.4233 (3.4296)  weight_decay: 0.0500 (0.0500)  time: 0.4923  data: 0.0553  max mem: 31830
Epoch: [174]  [130/312]  eta: 0:01:48  lr: 0.001678  min_lr: 0.001678  loss: 3.1999 (3.4336)  weight_decay: 0.0500 (0.0500)  time: 0.6145  data: 0.1169  max mem: 31830
Epoch: [174]  [140/312]  eta: 0:01:40  lr: 0.001678  min_lr: 0.001678  loss: 3.5097 (3.4388)  weight_decay: 0.0500 (0.0500)  time: 0.5159  data: 0.0626  max mem: 31830
Epoch: [174]  [150/312]  eta: 0:01:35  lr: 0.001677  min_lr: 0.001677  loss: 3.5734 (3.4586)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0196  max mem: 31830
Epoch: [174]  [160/312]  eta: 0:01:29  lr: 0.001676  min_lr: 0.001676  loss: 3.3760 (3.4428)  weight_decay: 0.0500 (0.0500)  time: 0.6260  data: 0.0472  max mem: 31830
Epoch: [174]  [170/312]  eta: 0:01:22  lr: 0.001676  min_lr: 0.001676  loss: 3.2625 (3.4450)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0465  max mem: 31830
Epoch: [174]  [180/312]  eta: 0:01:16  lr: 0.001675  min_lr: 0.001675  loss: 3.7321 (3.4465)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0194  max mem: 31830
Epoch: [174]  [190/312]  eta: 0:01:10  lr: 0.001674  min_lr: 0.001674  loss: 3.7321 (3.4651)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0365  max mem: 31830
Epoch: [174]  [200/312]  eta: 0:01:04  lr: 0.001674  min_lr: 0.001674  loss: 3.6638 (3.4587)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0594  max mem: 31830
Epoch: [174]  [210/312]  eta: 0:00:58  lr: 0.001673  min_lr: 0.001673  loss: 3.4163 (3.4669)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0242  max mem: 31830
Epoch: [174]  [220/312]  eta: 0:00:52  lr: 0.001672  min_lr: 0.001672  loss: 3.7644 (3.4753)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0369  max mem: 31830
Epoch: [174]  [230/312]  eta: 0:00:46  lr: 0.001671  min_lr: 0.001671  loss: 3.7644 (3.4752)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0368  max mem: 31830
Epoch: [174]  [240/312]  eta: 0:00:41  lr: 0.001671  min_lr: 0.001671  loss: 3.5346 (3.4780)  weight_decay: 0.0500 (0.0500)  time: 0.6026  data: 0.0210  max mem: 31830
Epoch: [174]  [250/312]  eta: 0:00:35  lr: 0.001670  min_lr: 0.001670  loss: 3.5346 (3.4744)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0442  max mem: 31830
Epoch: [174]  [260/312]  eta: 0:00:29  lr: 0.001669  min_lr: 0.001669  loss: 3.6072 (3.4742)  weight_decay: 0.0500 (0.0500)  time: 0.5338  data: 0.0244  max mem: 31830
Epoch: [174]  [270/312]  eta: 0:00:23  lr: 0.001669  min_lr: 0.001669  loss: 3.7106 (3.4812)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0675  max mem: 31830
Epoch: [174]  [280/312]  eta: 0:00:18  lr: 0.001668  min_lr: 0.001668  loss: 3.7369 (3.4910)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0859  max mem: 31830
Epoch: [174]  [290/312]  eta: 0:00:12  lr: 0.001667  min_lr: 0.001667  loss: 3.7251 (3.4959)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0194  max mem: 31830
Epoch: [174]  [300/312]  eta: 0:00:06  lr: 0.001666  min_lr: 0.001666  loss: 3.6949 (3.5006)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0415  max mem: 31830
Epoch: [174]  [310/312]  eta: 0:00:01  lr: 0.001666  min_lr: 0.001666  loss: 3.6882 (3.5081)  weight_decay: 0.0500 (0.0500)  time: 0.4219  data: 0.0415  max mem: 31830
Epoch: [174]  [311/312]  eta: 0:00:00  lr: 0.001666  min_lr: 0.001666  loss: 3.6882 (3.5108)  weight_decay: 0.0500 (0.0500)  time: 0.4217  data: 0.0415  max mem: 31830
Epoch: [174] Total time: 0:02:53 (0.5570 s / it)
Averaged stats: lr: 0.001666  min_lr: 0.001666  loss: 3.6882 (3.5208)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.3198 (1.3198)  acc1: 75.5208 (75.5208)  acc5: 94.1406 (94.1406)  time: 8.5618  data: 8.3939  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6114 (1.5159)  acc1: 70.5729 (71.3120)  acc5: 90.2344 (90.5600)  time: 1.0736  data: 0.9327  max mem: 31830
Test: Total time: 0:00:09 (1.0980 s / it)
* Acc@1 71.182 Acc@5 90.744 loss 1.516
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 71.18%
Epoch: [175]  [  0/312]  eta: 0:58:13  lr: 0.001666  min_lr: 0.001666  loss: 4.0785 (4.0785)  weight_decay: 0.0500 (0.0500)  time: 11.1980  data: 9.1377  max mem: 31830
Epoch: [175]  [ 10/312]  eta: 0:07:52  lr: 0.001665  min_lr: 0.001665  loss: 3.4919 (3.3484)  weight_decay: 0.0500 (0.0500)  time: 1.5639  data: 0.9700  max mem: 31830
Epoch: [175]  [ 20/312]  eta: 0:05:26  lr: 0.001664  min_lr: 0.001664  loss: 3.6017 (3.4318)  weight_decay: 0.0500 (0.0500)  time: 0.6159  data: 0.1428  max mem: 31830
Epoch: [175]  [ 30/312]  eta: 0:04:10  lr: 0.001663  min_lr: 0.001663  loss: 3.7086 (3.5118)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0666  max mem: 31830
Epoch: [175]  [ 40/312]  eta: 0:03:28  lr: 0.001663  min_lr: 0.001663  loss: 3.6602 (3.4824)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0008  max mem: 31830
Epoch: [175]  [ 50/312]  eta: 0:03:09  lr: 0.001662  min_lr: 0.001662  loss: 3.3548 (3.4579)  weight_decay: 0.0500 (0.0500)  time: 0.4726  data: 0.0590  max mem: 31830
Epoch: [175]  [ 60/312]  eta: 0:02:48  lr: 0.001661  min_lr: 0.001661  loss: 3.3092 (3.4630)  weight_decay: 0.0500 (0.0500)  time: 0.4712  data: 0.0590  max mem: 31830
Epoch: [175]  [ 70/312]  eta: 0:02:42  lr: 0.001661  min_lr: 0.001661  loss: 3.4716 (3.4502)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0807  max mem: 31830
Epoch: [175]  [ 80/312]  eta: 0:02:30  lr: 0.001660  min_lr: 0.001660  loss: 3.5143 (3.4834)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0808  max mem: 31830
Epoch: [175]  [ 90/312]  eta: 0:02:19  lr: 0.001659  min_lr: 0.001659  loss: 3.6048 (3.4774)  weight_decay: 0.0500 (0.0500)  time: 0.4716  data: 0.0267  max mem: 31830
Epoch: [175]  [100/312]  eta: 0:02:14  lr: 0.001658  min_lr: 0.001658  loss: 3.1447 (3.4465)  weight_decay: 0.0500 (0.0500)  time: 0.5750  data: 0.0973  max mem: 31830
Epoch: [175]  [110/312]  eta: 0:02:03  lr: 0.001658  min_lr: 0.001658  loss: 3.0412 (3.4211)  weight_decay: 0.0500 (0.0500)  time: 0.5478  data: 0.0719  max mem: 31830
Epoch: [175]  [120/312]  eta: 0:01:57  lr: 0.001657  min_lr: 0.001657  loss: 3.4161 (3.4366)  weight_decay: 0.0500 (0.0500)  time: 0.4874  data: 0.0367  max mem: 31830
Epoch: [175]  [130/312]  eta: 0:01:50  lr: 0.001656  min_lr: 0.001656  loss: 3.4161 (3.4222)  weight_decay: 0.0500 (0.0500)  time: 0.5820  data: 0.0697  max mem: 31830
Epoch: [175]  [140/312]  eta: 0:01:42  lr: 0.001656  min_lr: 0.001656  loss: 3.3251 (3.4148)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0348  max mem: 31830
Epoch: [175]  [150/312]  eta: 0:01:37  lr: 0.001655  min_lr: 0.001655  loss: 3.2925 (3.4187)  weight_decay: 0.0500 (0.0500)  time: 0.5501  data: 0.0887  max mem: 31830
Epoch: [175]  [160/312]  eta: 0:01:29  lr: 0.001654  min_lr: 0.001654  loss: 3.5352 (3.4241)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0881  max mem: 31830
Epoch: [175]  [170/312]  eta: 0:01:23  lr: 0.001654  min_lr: 0.001654  loss: 3.3972 (3.4161)  weight_decay: 0.0500 (0.0500)  time: 0.4794  data: 0.0455  max mem: 31830
Epoch: [175]  [180/312]  eta: 0:01:17  lr: 0.001653  min_lr: 0.001653  loss: 3.3830 (3.4243)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.1368  max mem: 31830
Epoch: [175]  [190/312]  eta: 0:01:10  lr: 0.001652  min_lr: 0.001652  loss: 3.6420 (3.4286)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0921  max mem: 31830
Epoch: [175]  [200/312]  eta: 0:01:05  lr: 0.001651  min_lr: 0.001651  loss: 3.6998 (3.4375)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0736  max mem: 31830
Epoch: [175]  [210/312]  eta: 0:00:59  lr: 0.001651  min_lr: 0.001651  loss: 3.6468 (3.4374)  weight_decay: 0.0500 (0.0500)  time: 0.6330  data: 0.1499  max mem: 31830
Epoch: [175]  [220/312]  eta: 0:00:53  lr: 0.001650  min_lr: 0.001650  loss: 3.5914 (3.4420)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0771  max mem: 31830
Epoch: [175]  [230/312]  eta: 0:00:47  lr: 0.001649  min_lr: 0.001649  loss: 3.6182 (3.4479)  weight_decay: 0.0500 (0.0500)  time: 0.4887  data: 0.0573  max mem: 31830
Epoch: [175]  [240/312]  eta: 0:00:41  lr: 0.001649  min_lr: 0.001649  loss: 3.2921 (3.4406)  weight_decay: 0.0500 (0.0500)  time: 0.5405  data: 0.0573  max mem: 31830
Epoch: [175]  [250/312]  eta: 0:00:35  lr: 0.001648  min_lr: 0.001648  loss: 3.7565 (3.4556)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0689  max mem: 31830
Epoch: [175]  [260/312]  eta: 0:00:29  lr: 0.001647  min_lr: 0.001647  loss: 3.7565 (3.4496)  weight_decay: 0.0500 (0.0500)  time: 0.5730  data: 0.1473  max mem: 31830
Epoch: [175]  [270/312]  eta: 0:00:23  lr: 0.001646  min_lr: 0.001646  loss: 3.5657 (3.4583)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0791  max mem: 31830
Epoch: [175]  [280/312]  eta: 0:00:18  lr: 0.001646  min_lr: 0.001646  loss: 3.8163 (3.4688)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0651  max mem: 31830
Epoch: [175]  [290/312]  eta: 0:00:12  lr: 0.001645  min_lr: 0.001645  loss: 3.6673 (3.4684)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0872  max mem: 31830
Epoch: [175]  [300/312]  eta: 0:00:06  lr: 0.001644  min_lr: 0.001644  loss: 3.7616 (3.4829)  weight_decay: 0.0500 (0.0500)  time: 0.4530  data: 0.0226  max mem: 31830
Epoch: [175]  [310/312]  eta: 0:00:01  lr: 0.001644  min_lr: 0.001644  loss: 3.8145 (3.4856)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0002  max mem: 31830
Epoch: [175]  [311/312]  eta: 0:00:00  lr: 0.001644  min_lr: 0.001644  loss: 3.7837 (3.4849)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [175] Total time: 0:02:54 (0.5578 s / it)
Averaged stats: lr: 0.001644  min_lr: 0.001644  loss: 3.7837 (3.5116)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1372 (1.1372)  acc1: 77.4740 (77.4740)  acc5: 94.0104 (94.0104)  time: 8.6528  data: 8.4825  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5251 (1.3903)  acc1: 69.1406 (71.3920)  acc5: 90.6250 (90.9920)  time: 1.0799  data: 0.9426  max mem: 31830
Test: Total time: 0:00:09 (1.0990 s / it)
* Acc@1 71.088 Acc@5 90.796 loss 1.396
Accuracy of the model on the 50000 test images: 71.1%
Max accuracy: 71.18%
Epoch: [176]  [  0/312]  eta: 1:03:49  lr: 0.001643  min_lr: 0.001643  loss: 4.1758 (4.1758)  weight_decay: 0.0500 (0.0500)  time: 12.2737  data: 10.8716  max mem: 31830
Epoch: [176]  [ 10/312]  eta: 0:08:39  lr: 0.001643  min_lr: 0.001643  loss: 3.7034 (3.5002)  weight_decay: 0.0500 (0.0500)  time: 1.7197  data: 1.0399  max mem: 31830
Epoch: [176]  [ 20/312]  eta: 0:05:36  lr: 0.001642  min_lr: 0.001642  loss: 3.3694 (3.4827)  weight_decay: 0.0500 (0.0500)  time: 0.5980  data: 0.0586  max mem: 31830
Epoch: [176]  [ 30/312]  eta: 0:04:16  lr: 0.001641  min_lr: 0.001641  loss: 3.6223 (3.5168)  weight_decay: 0.0500 (0.0500)  time: 0.4639  data: 0.0307  max mem: 31830
Epoch: [176]  [ 40/312]  eta: 0:03:33  lr: 0.001641  min_lr: 0.001641  loss: 3.5552 (3.4629)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0009  max mem: 31830
Epoch: [176]  [ 50/312]  eta: 0:03:05  lr: 0.001640  min_lr: 0.001640  loss: 3.5552 (3.4732)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0009  max mem: 31830
Epoch: [176]  [ 60/312]  eta: 0:02:45  lr: 0.001639  min_lr: 0.001639  loss: 3.6370 (3.4263)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0012  max mem: 31830
Epoch: [176]  [ 70/312]  eta: 0:02:32  lr: 0.001639  min_lr: 0.001639  loss: 3.6465 (3.4348)  weight_decay: 0.0500 (0.0500)  time: 0.4305  data: 0.0208  max mem: 31830
Epoch: [176]  [ 80/312]  eta: 0:02:25  lr: 0.001638  min_lr: 0.001638  loss: 3.6540 (3.4312)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.1104  max mem: 31830
Epoch: [176]  [ 90/312]  eta: 0:02:13  lr: 0.001637  min_lr: 0.001637  loss: 3.4118 (3.4252)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.1036  max mem: 31830
Epoch: [176]  [100/312]  eta: 0:02:07  lr: 0.001636  min_lr: 0.001636  loss: 3.3761 (3.4215)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0821  max mem: 31830
Epoch: [176]  [110/312]  eta: 0:01:59  lr: 0.001636  min_lr: 0.001636  loss: 3.2718 (3.4384)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0693  max mem: 31830
Epoch: [176]  [120/312]  eta: 0:01:53  lr: 0.001635  min_lr: 0.001635  loss: 3.8311 (3.4500)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0701  max mem: 31830
Epoch: [176]  [130/312]  eta: 0:01:46  lr: 0.001634  min_lr: 0.001634  loss: 3.5208 (3.4361)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.1237  max mem: 31830
Epoch: [176]  [140/312]  eta: 0:01:39  lr: 0.001634  min_lr: 0.001634  loss: 3.5208 (3.4440)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0548  max mem: 31830
Epoch: [176]  [150/312]  eta: 0:01:34  lr: 0.001633  min_lr: 0.001633  loss: 3.5401 (3.4544)  weight_decay: 0.0500 (0.0500)  time: 0.5820  data: 0.0431  max mem: 31830
Epoch: [176]  [160/312]  eta: 0:01:28  lr: 0.001632  min_lr: 0.001632  loss: 3.6563 (3.4730)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0942  max mem: 31830
Epoch: [176]  [170/312]  eta: 0:01:21  lr: 0.001631  min_lr: 0.001631  loss: 3.6563 (3.4699)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0533  max mem: 31830
Epoch: [176]  [180/312]  eta: 0:01:16  lr: 0.001631  min_lr: 0.001631  loss: 3.6530 (3.4781)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0551  max mem: 31830
Epoch: [176]  [190/312]  eta: 0:01:09  lr: 0.001630  min_lr: 0.001630  loss: 3.6530 (3.4782)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0679  max mem: 31830
Epoch: [176]  [200/312]  eta: 0:01:03  lr: 0.001629  min_lr: 0.001629  loss: 3.5144 (3.4799)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0895  max mem: 31830
Epoch: [176]  [210/312]  eta: 0:00:58  lr: 0.001629  min_lr: 0.001629  loss: 3.7315 (3.4892)  weight_decay: 0.0500 (0.0500)  time: 0.6159  data: 0.1525  max mem: 31830
Epoch: [176]  [220/312]  eta: 0:00:51  lr: 0.001628  min_lr: 0.001628  loss: 3.7798 (3.4928)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0776  max mem: 31830
Epoch: [176]  [230/312]  eta: 0:00:46  lr: 0.001627  min_lr: 0.001627  loss: 3.6143 (3.4898)  weight_decay: 0.0500 (0.0500)  time: 0.4764  data: 0.0783  max mem: 31830
Epoch: [176]  [240/312]  eta: 0:00:40  lr: 0.001627  min_lr: 0.001627  loss: 3.5870 (3.4860)  weight_decay: 0.0500 (0.0500)  time: 0.5953  data: 0.1986  max mem: 31830
Epoch: [176]  [250/312]  eta: 0:00:34  lr: 0.001626  min_lr: 0.001626  loss: 3.6409 (3.4838)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.1211  max mem: 31830
Epoch: [176]  [260/312]  eta: 0:00:29  lr: 0.001625  min_lr: 0.001625  loss: 3.7132 (3.4873)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.1016  max mem: 31830
Epoch: [176]  [270/312]  eta: 0:00:23  lr: 0.001624  min_lr: 0.001624  loss: 3.7132 (3.4896)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.1032  max mem: 31830
Epoch: [176]  [280/312]  eta: 0:00:17  lr: 0.001624  min_lr: 0.001624  loss: 3.7654 (3.4906)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0880  max mem: 31830
Epoch: [176]  [290/312]  eta: 0:00:12  lr: 0.001623  min_lr: 0.001623  loss: 3.7654 (3.4951)  weight_decay: 0.0500 (0.0500)  time: 0.6113  data: 0.1976  max mem: 31830
Epoch: [176]  [300/312]  eta: 0:00:06  lr: 0.001622  min_lr: 0.001622  loss: 3.6594 (3.4963)  weight_decay: 0.0500 (0.0500)  time: 0.4981  data: 0.1115  max mem: 31830
Epoch: [176]  [310/312]  eta: 0:00:01  lr: 0.001622  min_lr: 0.001622  loss: 3.6621 (3.5015)  weight_decay: 0.0500 (0.0500)  time: 0.3833  data: 0.0027  max mem: 31830
Epoch: [176]  [311/312]  eta: 0:00:00  lr: 0.001621  min_lr: 0.001621  loss: 3.5423 (3.5000)  weight_decay: 0.0500 (0.0500)  time: 0.3831  data: 0.0027  max mem: 31830
Epoch: [176] Total time: 0:02:52 (0.5530 s / it)
Averaged stats: lr: 0.001621  min_lr: 0.001621  loss: 3.5423 (3.5056)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:24  loss: 1.2102 (1.2102)  acc1: 79.5573 (79.5573)  acc5: 94.2708 (94.2708)  time: 9.3934  data: 9.2263  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4976 (1.4273)  acc1: 71.3542 (72.4000)  acc5: 90.8854 (90.8960)  time: 1.1602  data: 1.0252  max mem: 31830
Test: Total time: 0:00:10 (1.1844 s / it)
* Acc@1 71.816 Acc@5 91.134 loss 1.433
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 71.82%
Epoch: [177]  [  0/312]  eta: 1:02:11  lr: 0.001621  min_lr: 0.001621  loss: 3.6099 (3.6099)  weight_decay: 0.0500 (0.0500)  time: 11.9607  data: 9.8606  max mem: 31830
Epoch: [177]  [ 10/312]  eta: 0:08:32  lr: 0.001621  min_lr: 0.001621  loss: 3.6099 (3.5999)  weight_decay: 0.0500 (0.0500)  time: 1.6985  data: 1.1348  max mem: 31830
Epoch: [177]  [ 20/312]  eta: 0:05:37  lr: 0.001620  min_lr: 0.001620  loss: 3.3509 (3.4175)  weight_decay: 0.0500 (0.0500)  time: 0.6153  data: 0.1877  max mem: 31830
Epoch: [177]  [ 30/312]  eta: 0:04:17  lr: 0.001619  min_lr: 0.001619  loss: 3.3509 (3.4913)  weight_decay: 0.0500 (0.0500)  time: 0.4786  data: 0.0570  max mem: 31830
Epoch: [177]  [ 40/312]  eta: 0:03:33  lr: 0.001619  min_lr: 0.001619  loss: 3.4451 (3.4118)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0008  max mem: 31830
Epoch: [177]  [ 50/312]  eta: 0:03:05  lr: 0.001618  min_lr: 0.001618  loss: 3.3501 (3.4320)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0017  max mem: 31830
Epoch: [177]  [ 60/312]  eta: 0:02:45  lr: 0.001617  min_lr: 0.001617  loss: 3.6941 (3.4470)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0017  max mem: 31830
Epoch: [177]  [ 70/312]  eta: 0:02:36  lr: 0.001616  min_lr: 0.001616  loss: 3.3511 (3.4328)  weight_decay: 0.0500 (0.0500)  time: 0.4914  data: 0.0601  max mem: 31830
Epoch: [177]  [ 80/312]  eta: 0:02:25  lr: 0.001616  min_lr: 0.001616  loss: 3.4248 (3.4506)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0602  max mem: 31830
Epoch: [177]  [ 90/312]  eta: 0:02:18  lr: 0.001615  min_lr: 0.001615  loss: 3.6104 (3.4542)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0947  max mem: 31830
Epoch: [177]  [100/312]  eta: 0:02:10  lr: 0.001614  min_lr: 0.001614  loss: 3.6021 (3.4494)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.1587  max mem: 31830
Epoch: [177]  [110/312]  eta: 0:02:00  lr: 0.001614  min_lr: 0.001614  loss: 3.6921 (3.4677)  weight_decay: 0.0500 (0.0500)  time: 0.4825  data: 0.0649  max mem: 31830
Epoch: [177]  [120/312]  eta: 0:01:55  lr: 0.001613  min_lr: 0.001613  loss: 3.7511 (3.4768)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0838  max mem: 31830
Epoch: [177]  [130/312]  eta: 0:01:49  lr: 0.001612  min_lr: 0.001612  loss: 3.7581 (3.4837)  weight_decay: 0.0500 (0.0500)  time: 0.6350  data: 0.1809  max mem: 31830
Epoch: [177]  [140/312]  eta: 0:01:41  lr: 0.001612  min_lr: 0.001612  loss: 3.7355 (3.4891)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0979  max mem: 31830
Epoch: [177]  [150/312]  eta: 0:01:34  lr: 0.001611  min_lr: 0.001611  loss: 3.7355 (3.5113)  weight_decay: 0.0500 (0.0500)  time: 0.4683  data: 0.0734  max mem: 31830
Epoch: [177]  [160/312]  eta: 0:01:27  lr: 0.001610  min_lr: 0.001610  loss: 3.6338 (3.5025)  weight_decay: 0.0500 (0.0500)  time: 0.4943  data: 0.0793  max mem: 31830
Epoch: [177]  [170/312]  eta: 0:01:22  lr: 0.001609  min_lr: 0.001609  loss: 3.4570 (3.5065)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0934  max mem: 31830
Epoch: [177]  [180/312]  eta: 0:01:16  lr: 0.001609  min_lr: 0.001609  loss: 3.4719 (3.4961)  weight_decay: 0.0500 (0.0500)  time: 0.5938  data: 0.1619  max mem: 31830
Epoch: [177]  [190/312]  eta: 0:01:09  lr: 0.001608  min_lr: 0.001608  loss: 3.5827 (3.5055)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0837  max mem: 31830
Epoch: [177]  [200/312]  eta: 0:01:04  lr: 0.001607  min_lr: 0.001607  loss: 3.7429 (3.5126)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0822  max mem: 31830
Epoch: [177]  [210/312]  eta: 0:00:58  lr: 0.001607  min_lr: 0.001607  loss: 3.7664 (3.5111)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.1702  max mem: 31830
Epoch: [177]  [220/312]  eta: 0:00:52  lr: 0.001606  min_lr: 0.001606  loss: 3.6083 (3.5146)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0978  max mem: 31830
Epoch: [177]  [230/312]  eta: 0:00:46  lr: 0.001605  min_lr: 0.001605  loss: 3.6763 (3.5153)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0819  max mem: 31830
Epoch: [177]  [240/312]  eta: 0:00:40  lr: 0.001604  min_lr: 0.001604  loss: 3.6263 (3.5122)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.1331  max mem: 31830
Epoch: [177]  [250/312]  eta: 0:00:35  lr: 0.001604  min_lr: 0.001604  loss: 3.6744 (3.5122)  weight_decay: 0.0500 (0.0500)  time: 0.5410  data: 0.1061  max mem: 31830
Epoch: [177]  [260/312]  eta: 0:00:29  lr: 0.001603  min_lr: 0.001603  loss: 3.7865 (3.5231)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.0925  max mem: 31830
Epoch: [177]  [270/312]  eta: 0:00:23  lr: 0.001602  min_lr: 0.001602  loss: 3.7483 (3.5240)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0767  max mem: 31830
Epoch: [177]  [280/312]  eta: 0:00:18  lr: 0.001602  min_lr: 0.001602  loss: 3.5268 (3.5113)  weight_decay: 0.0500 (0.0500)  time: 0.5401  data: 0.0855  max mem: 31830
Epoch: [177]  [290/312]  eta: 0:00:12  lr: 0.001601  min_lr: 0.001601  loss: 3.5755 (3.5183)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0693  max mem: 31830
Epoch: [177]  [300/312]  eta: 0:00:06  lr: 0.001600  min_lr: 0.001600  loss: 3.7940 (3.5223)  weight_decay: 0.0500 (0.0500)  time: 0.5002  data: 0.0221  max mem: 31830
Epoch: [177]  [310/312]  eta: 0:00:01  lr: 0.001600  min_lr: 0.001600  loss: 3.7966 (3.5244)  weight_decay: 0.0500 (0.0500)  time: 0.3902  data: 0.0001  max mem: 31830
Epoch: [177]  [311/312]  eta: 0:00:00  lr: 0.001599  min_lr: 0.001599  loss: 3.8005 (3.5271)  weight_decay: 0.0500 (0.0500)  time: 0.3900  data: 0.0001  max mem: 31830
Epoch: [177] Total time: 0:02:54 (0.5585 s / it)
Averaged stats: lr: 0.001599  min_lr: 0.001599  loss: 3.8005 (3.5196)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.2873 (1.2873)  acc1: 77.7344 (77.7344)  acc5: 92.5781 (92.5781)  time: 8.4775  data: 8.3093  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.7263 (1.6379)  acc1: 69.0104 (69.7600)  acc5: 89.1927 (89.3920)  time: 1.0586  data: 0.9233  max mem: 31830
Test: Total time: 0:00:09 (1.0732 s / it)
* Acc@1 69.700 Acc@5 89.812 loss 1.650
Accuracy of the model on the 50000 test images: 69.7%
Max accuracy: 71.82%
Epoch: [178]  [  0/312]  eta: 1:03:07  lr: 0.001599  min_lr: 0.001599  loss: 3.8401 (3.8401)  weight_decay: 0.0500 (0.0500)  time: 12.1379  data: 11.6993  max mem: 31830
Epoch: [178]  [ 10/312]  eta: 0:09:12  lr: 0.001599  min_lr: 0.001599  loss: 3.5530 (3.2730)  weight_decay: 0.0500 (0.0500)  time: 1.8309  data: 1.0643  max mem: 31830
Epoch: [178]  [ 20/312]  eta: 0:05:34  lr: 0.001598  min_lr: 0.001598  loss: 3.5815 (3.4768)  weight_decay: 0.0500 (0.0500)  time: 0.5960  data: 0.0008  max mem: 31830
Epoch: [178]  [ 30/312]  eta: 0:04:14  lr: 0.001597  min_lr: 0.001597  loss: 3.7785 (3.5499)  weight_decay: 0.0500 (0.0500)  time: 0.3928  data: 0.0007  max mem: 31830
Epoch: [178]  [ 40/312]  eta: 0:03:32  lr: 0.001597  min_lr: 0.001597  loss: 3.6703 (3.4771)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0008  max mem: 31830
Epoch: [178]  [ 50/312]  eta: 0:03:04  lr: 0.001596  min_lr: 0.001596  loss: 3.5388 (3.5121)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0013  max mem: 31830
Epoch: [178]  [ 60/312]  eta: 0:02:45  lr: 0.001595  min_lr: 0.001595  loss: 3.6408 (3.5065)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0013  max mem: 31830
Epoch: [178]  [ 70/312]  eta: 0:02:31  lr: 0.001594  min_lr: 0.001594  loss: 3.6796 (3.5314)  weight_decay: 0.0500 (0.0500)  time: 0.4272  data: 0.0009  max mem: 31830
Epoch: [178]  [ 80/312]  eta: 0:02:25  lr: 0.001594  min_lr: 0.001594  loss: 3.6679 (3.5270)  weight_decay: 0.0500 (0.0500)  time: 0.5396  data: 0.0225  max mem: 31830
Epoch: [178]  [ 90/312]  eta: 0:02:16  lr: 0.001593  min_lr: 0.001593  loss: 3.5034 (3.5418)  weight_decay: 0.0500 (0.0500)  time: 0.5690  data: 0.0225  max mem: 31830
Epoch: [178]  [100/312]  eta: 0:02:06  lr: 0.001592  min_lr: 0.001592  loss: 3.6692 (3.5417)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0067  max mem: 31830
Epoch: [178]  [110/312]  eta: 0:02:01  lr: 0.001592  min_lr: 0.001592  loss: 3.5067 (3.5216)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0121  max mem: 31830
Epoch: [178]  [120/312]  eta: 0:01:55  lr: 0.001591  min_lr: 0.001591  loss: 3.2669 (3.5013)  weight_decay: 0.0500 (0.0500)  time: 0.6148  data: 0.0263  max mem: 31830
Epoch: [178]  [130/312]  eta: 0:01:47  lr: 0.001590  min_lr: 0.001590  loss: 3.5132 (3.5041)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0266  max mem: 31830
Epoch: [178]  [140/312]  eta: 0:01:41  lr: 0.001590  min_lr: 0.001590  loss: 3.5506 (3.4939)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0072  max mem: 31830
Epoch: [178]  [150/312]  eta: 0:01:36  lr: 0.001589  min_lr: 0.001589  loss: 3.6342 (3.4992)  weight_decay: 0.0500 (0.0500)  time: 0.6119  data: 0.0015  max mem: 31830
Epoch: [178]  [160/312]  eta: 0:01:29  lr: 0.001588  min_lr: 0.001588  loss: 3.7740 (3.5162)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0062  max mem: 31830
Epoch: [178]  [170/312]  eta: 0:01:23  lr: 0.001587  min_lr: 0.001587  loss: 3.6647 (3.5138)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0067  max mem: 31830
Epoch: [178]  [180/312]  eta: 0:01:16  lr: 0.001587  min_lr: 0.001587  loss: 3.4056 (3.4976)  weight_decay: 0.0500 (0.0500)  time: 0.5337  data: 0.0155  max mem: 31830
Epoch: [178]  [190/312]  eta: 0:01:11  lr: 0.001586  min_lr: 0.001586  loss: 3.3933 (3.5000)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0411  max mem: 31830
Epoch: [178]  [200/312]  eta: 0:01:05  lr: 0.001585  min_lr: 0.001585  loss: 3.5886 (3.4932)  weight_decay: 0.0500 (0.0500)  time: 0.5940  data: 0.0436  max mem: 31830
Epoch: [178]  [210/312]  eta: 0:00:58  lr: 0.001585  min_lr: 0.001585  loss: 3.5794 (3.4932)  weight_decay: 0.0500 (0.0500)  time: 0.5067  data: 0.0176  max mem: 31830
Epoch: [178]  [220/312]  eta: 0:00:53  lr: 0.001584  min_lr: 0.001584  loss: 3.6355 (3.4979)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0025  max mem: 31830
Epoch: [178]  [230/312]  eta: 0:00:47  lr: 0.001583  min_lr: 0.001583  loss: 3.6355 (3.4934)  weight_decay: 0.0500 (0.0500)  time: 0.6149  data: 0.0234  max mem: 31830
Epoch: [178]  [240/312]  eta: 0:00:41  lr: 0.001583  min_lr: 0.001583  loss: 3.6158 (3.4898)  weight_decay: 0.0500 (0.0500)  time: 0.5453  data: 0.0365  max mem: 31830
Epoch: [178]  [250/312]  eta: 0:00:35  lr: 0.001582  min_lr: 0.001582  loss: 3.5773 (3.4885)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0158  max mem: 31830
Epoch: [178]  [260/312]  eta: 0:00:29  lr: 0.001581  min_lr: 0.001581  loss: 3.5773 (3.4873)  weight_decay: 0.0500 (0.0500)  time: 0.4969  data: 0.0011  max mem: 31830
Epoch: [178]  [270/312]  eta: 0:00:24  lr: 0.001580  min_lr: 0.001580  loss: 3.6489 (3.4918)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0009  max mem: 31830
Epoch: [178]  [280/312]  eta: 0:00:18  lr: 0.001580  min_lr: 0.001580  loss: 3.5239 (3.4917)  weight_decay: 0.0500 (0.0500)  time: 0.6244  data: 0.0041  max mem: 31830
Epoch: [178]  [290/312]  eta: 0:00:12  lr: 0.001579  min_lr: 0.001579  loss: 3.3879 (3.4778)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0037  max mem: 31830
Epoch: [178]  [300/312]  eta: 0:00:06  lr: 0.001578  min_lr: 0.001578  loss: 3.2373 (3.4789)  weight_decay: 0.0500 (0.0500)  time: 0.4558  data: 0.0002  max mem: 31830
Epoch: [178]  [310/312]  eta: 0:00:01  lr: 0.001578  min_lr: 0.001578  loss: 3.4430 (3.4725)  weight_decay: 0.0500 (0.0500)  time: 0.4316  data: 0.0001  max mem: 31830
Epoch: [178]  [311/312]  eta: 0:00:00  lr: 0.001578  min_lr: 0.001578  loss: 3.6845 (3.4732)  weight_decay: 0.0500 (0.0500)  time: 0.4312  data: 0.0001  max mem: 31830
Epoch: [178] Total time: 0:02:55 (0.5622 s / it)
Averaged stats: lr: 0.001578  min_lr: 0.001578  loss: 3.6845 (3.4846)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.2666 (1.2666)  acc1: 77.9948 (77.9948)  acc5: 92.7083 (92.7083)  time: 8.8680  data: 8.7003  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5522 (1.4634)  acc1: 71.8750 (71.4400)  acc5: 89.7135 (90.4160)  time: 1.1152  data: 0.9668  max mem: 31830
Test: Total time: 0:00:10 (1.1334 s / it)
* Acc@1 71.188 Acc@5 90.562 loss 1.464
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 71.82%
Epoch: [179]  [  0/312]  eta: 1:07:10  lr: 0.001577  min_lr: 0.001577  loss: 3.8656 (3.8656)  weight_decay: 0.0500 (0.0500)  time: 12.9198  data: 8.6753  max mem: 31830
Epoch: [179]  [ 10/312]  eta: 0:09:06  lr: 0.001577  min_lr: 0.001577  loss: 3.7667 (3.5680)  weight_decay: 0.0500 (0.0500)  time: 1.8106  data: 0.9360  max mem: 31830
Epoch: [179]  [ 20/312]  eta: 0:05:31  lr: 0.001576  min_lr: 0.001576  loss: 3.7336 (3.6595)  weight_decay: 0.0500 (0.0500)  time: 0.5459  data: 0.0814  max mem: 31830
Epoch: [179]  [ 30/312]  eta: 0:04:13  lr: 0.001575  min_lr: 0.001575  loss: 3.6078 (3.5945)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0008  max mem: 31830
Epoch: [179]  [ 40/312]  eta: 0:03:30  lr: 0.001575  min_lr: 0.001575  loss: 3.5690 (3.5499)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0008  max mem: 31830
Epoch: [179]  [ 50/312]  eta: 0:03:03  lr: 0.001574  min_lr: 0.001574  loss: 3.5754 (3.5773)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0008  max mem: 31830
Epoch: [179]  [ 60/312]  eta: 0:02:43  lr: 0.001573  min_lr: 0.001573  loss: 3.4735 (3.4919)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0012  max mem: 31830
Epoch: [179]  [ 70/312]  eta: 0:02:32  lr: 0.001573  min_lr: 0.001573  loss: 3.5298 (3.5121)  weight_decay: 0.0500 (0.0500)  time: 0.4555  data: 0.0012  max mem: 31830
Epoch: [179]  [ 80/312]  eta: 0:02:24  lr: 0.001572  min_lr: 0.001572  loss: 3.6664 (3.5284)  weight_decay: 0.0500 (0.0500)  time: 0.5386  data: 0.0150  max mem: 31830
Epoch: [179]  [ 90/312]  eta: 0:02:17  lr: 0.001571  min_lr: 0.001571  loss: 3.6868 (3.5329)  weight_decay: 0.0500 (0.0500)  time: 0.5753  data: 0.0404  max mem: 31830
Epoch: [179]  [100/312]  eta: 0:02:10  lr: 0.001570  min_lr: 0.001570  loss: 3.6868 (3.5320)  weight_decay: 0.0500 (0.0500)  time: 0.5791  data: 0.0398  max mem: 31830
Epoch: [179]  [110/312]  eta: 0:02:00  lr: 0.001570  min_lr: 0.001570  loss: 3.6883 (3.5450)  weight_decay: 0.0500 (0.0500)  time: 0.5061  data: 0.0143  max mem: 31830
Epoch: [179]  [120/312]  eta: 0:01:55  lr: 0.001569  min_lr: 0.001569  loss: 3.7112 (3.5365)  weight_decay: 0.0500 (0.0500)  time: 0.5240  data: 0.0009  max mem: 31830
Epoch: [179]  [130/312]  eta: 0:01:49  lr: 0.001568  min_lr: 0.001568  loss: 3.7747 (3.5588)  weight_decay: 0.0500 (0.0500)  time: 0.6101  data: 0.0013  max mem: 31830
Epoch: [179]  [140/312]  eta: 0:01:41  lr: 0.001568  min_lr: 0.001568  loss: 3.8019 (3.5540)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0233  max mem: 31830
Epoch: [179]  [150/312]  eta: 0:01:36  lr: 0.001567  min_lr: 0.001567  loss: 3.6158 (3.5534)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0587  max mem: 31830
Epoch: [179]  [160/312]  eta: 0:01:28  lr: 0.001566  min_lr: 0.001566  loss: 3.5656 (3.5470)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0373  max mem: 31830
Epoch: [179]  [170/312]  eta: 0:01:23  lr: 0.001566  min_lr: 0.001566  loss: 3.5656 (3.5527)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0322  max mem: 31830
Epoch: [179]  [180/312]  eta: 0:01:17  lr: 0.001565  min_lr: 0.001565  loss: 3.3469 (3.5341)  weight_decay: 0.0500 (0.0500)  time: 0.5973  data: 0.0319  max mem: 31830
Epoch: [179]  [190/312]  eta: 0:01:10  lr: 0.001564  min_lr: 0.001564  loss: 3.5112 (3.5349)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.0224  max mem: 31830
Epoch: [179]  [200/312]  eta: 0:01:05  lr: 0.001563  min_lr: 0.001563  loss: 3.6545 (3.5387)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0608  max mem: 31830
Epoch: [179]  [210/312]  eta: 0:00:59  lr: 0.001563  min_lr: 0.001563  loss: 3.7403 (3.5442)  weight_decay: 0.0500 (0.0500)  time: 0.6156  data: 0.0396  max mem: 31830
Epoch: [179]  [220/312]  eta: 0:00:53  lr: 0.001562  min_lr: 0.001562  loss: 3.7582 (3.5443)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0183  max mem: 31830
Epoch: [179]  [230/312]  eta: 0:00:47  lr: 0.001561  min_lr: 0.001561  loss: 3.3683 (3.5323)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0352  max mem: 31830
Epoch: [179]  [240/312]  eta: 0:00:41  lr: 0.001561  min_lr: 0.001561  loss: 3.2964 (3.5346)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0177  max mem: 31830
Epoch: [179]  [250/312]  eta: 0:00:35  lr: 0.001560  min_lr: 0.001560  loss: 3.3381 (3.5268)  weight_decay: 0.0500 (0.0500)  time: 0.5542  data: 0.0240  max mem: 31830
Epoch: [179]  [260/312]  eta: 0:00:29  lr: 0.001559  min_lr: 0.001559  loss: 3.5458 (3.5301)  weight_decay: 0.0500 (0.0500)  time: 0.5946  data: 0.0239  max mem: 31830
Epoch: [179]  [270/312]  eta: 0:00:23  lr: 0.001559  min_lr: 0.001559  loss: 3.5474 (3.5272)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0087  max mem: 31830
Epoch: [179]  [280/312]  eta: 0:00:18  lr: 0.001558  min_lr: 0.001558  loss: 3.3854 (3.5202)  weight_decay: 0.0500 (0.0500)  time: 0.5626  data: 0.0563  max mem: 31830
Epoch: [179]  [290/312]  eta: 0:00:12  lr: 0.001557  min_lr: 0.001557  loss: 3.3925 (3.5216)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.0480  max mem: 31830
Epoch: [179]  [300/312]  eta: 0:00:06  lr: 0.001556  min_lr: 0.001556  loss: 3.3925 (3.5157)  weight_decay: 0.0500 (0.0500)  time: 0.4638  data: 0.0203  max mem: 31830
Epoch: [179]  [310/312]  eta: 0:00:01  lr: 0.001556  min_lr: 0.001556  loss: 3.2212 (3.5116)  weight_decay: 0.0500 (0.0500)  time: 0.4197  data: 0.0202  max mem: 31830
Epoch: [179]  [311/312]  eta: 0:00:00  lr: 0.001556  min_lr: 0.001556  loss: 3.2212 (3.5095)  weight_decay: 0.0500 (0.0500)  time: 0.4196  data: 0.0202  max mem: 31830
Epoch: [179] Total time: 0:02:55 (0.5635 s / it)
Averaged stats: lr: 0.001556  min_lr: 0.001556  loss: 3.2212 (3.5084)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.0524 (1.0524)  acc1: 78.9062 (78.9062)  acc5: 94.5312 (94.5312)  time: 8.0374  data: 7.8667  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4809 (1.3889)  acc1: 68.7500 (71.1840)  acc5: 89.3229 (90.5120)  time: 1.0436  data: 0.9068  max mem: 31830
Test: Total time: 0:00:09 (1.0533 s / it)
* Acc@1 71.262 Acc@5 90.534 loss 1.402
Accuracy of the model on the 50000 test images: 71.3%
Max accuracy: 71.82%
Epoch: [180]  [  0/312]  eta: 1:01:49  lr: 0.001556  min_lr: 0.001556  loss: 3.8436 (3.8436)  weight_decay: 0.0500 (0.0500)  time: 11.8893  data: 10.9167  max mem: 31830
Epoch: [180]  [ 10/312]  eta: 0:08:33  lr: 0.001555  min_lr: 0.001555  loss: 3.4785 (3.5203)  weight_decay: 0.0500 (0.0500)  time: 1.7000  data: 1.1017  max mem: 31830
Epoch: [180]  [ 20/312]  eta: 0:05:21  lr: 0.001554  min_lr: 0.001554  loss: 3.4261 (3.4328)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0875  max mem: 31830
Epoch: [180]  [ 30/312]  eta: 0:04:06  lr: 0.001553  min_lr: 0.001553  loss: 3.7049 (3.5558)  weight_decay: 0.0500 (0.0500)  time: 0.4205  data: 0.0278  max mem: 31830
Epoch: [180]  [ 40/312]  eta: 0:03:26  lr: 0.001553  min_lr: 0.001553  loss: 3.7117 (3.5266)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0007  max mem: 31830
Epoch: [180]  [ 50/312]  eta: 0:03:02  lr: 0.001552  min_lr: 0.001552  loss: 3.5551 (3.4680)  weight_decay: 0.0500 (0.0500)  time: 0.4249  data: 0.0013  max mem: 31830
Epoch: [180]  [ 60/312]  eta: 0:02:43  lr: 0.001551  min_lr: 0.001551  loss: 3.6883 (3.4964)  weight_decay: 0.0500 (0.0500)  time: 0.4233  data: 0.0014  max mem: 31830
Epoch: [180]  [ 70/312]  eta: 0:02:36  lr: 0.001551  min_lr: 0.001551  loss: 3.6047 (3.4596)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0413  max mem: 31830
Epoch: [180]  [ 80/312]  eta: 0:02:26  lr: 0.001550  min_lr: 0.001550  loss: 3.6873 (3.5095)  weight_decay: 0.0500 (0.0500)  time: 0.5877  data: 0.0478  max mem: 31830
Epoch: [180]  [ 90/312]  eta: 0:02:17  lr: 0.001549  min_lr: 0.001549  loss: 3.7458 (3.5329)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0404  max mem: 31830
Epoch: [180]  [100/312]  eta: 0:02:11  lr: 0.001549  min_lr: 0.001549  loss: 3.4718 (3.5021)  weight_decay: 0.0500 (0.0500)  time: 0.5690  data: 0.0893  max mem: 31830
Epoch: [180]  [110/312]  eta: 0:02:01  lr: 0.001548  min_lr: 0.001548  loss: 3.5214 (3.5074)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0563  max mem: 31830
Epoch: [180]  [120/312]  eta: 0:01:55  lr: 0.001547  min_lr: 0.001547  loss: 3.6154 (3.5172)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0458  max mem: 31830
Epoch: [180]  [130/312]  eta: 0:01:50  lr: 0.001546  min_lr: 0.001546  loss: 3.6433 (3.5056)  weight_decay: 0.0500 (0.0500)  time: 0.6372  data: 0.0957  max mem: 31830
Epoch: [180]  [140/312]  eta: 0:01:41  lr: 0.001546  min_lr: 0.001546  loss: 3.3972 (3.5140)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0508  max mem: 31830
Epoch: [180]  [150/312]  eta: 0:01:35  lr: 0.001545  min_lr: 0.001545  loss: 3.4835 (3.5231)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0160  max mem: 31830
Epoch: [180]  [160/312]  eta: 0:01:29  lr: 0.001544  min_lr: 0.001544  loss: 3.9564 (3.5555)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0161  max mem: 31830
Epoch: [180]  [170/312]  eta: 0:01:22  lr: 0.001544  min_lr: 0.001544  loss: 3.9101 (3.5547)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0423  max mem: 31830
Epoch: [180]  [180/312]  eta: 0:01:17  lr: 0.001543  min_lr: 0.001543  loss: 3.6791 (3.5566)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.0855  max mem: 31830
Epoch: [180]  [190/312]  eta: 0:01:10  lr: 0.001542  min_lr: 0.001542  loss: 3.5238 (3.5422)  weight_decay: 0.0500 (0.0500)  time: 0.5599  data: 0.0448  max mem: 31830
Epoch: [180]  [200/312]  eta: 0:01:04  lr: 0.001542  min_lr: 0.001542  loss: 3.5384 (3.5497)  weight_decay: 0.0500 (0.0500)  time: 0.4622  data: 0.0196  max mem: 31830
Epoch: [180]  [210/312]  eta: 0:00:59  lr: 0.001541  min_lr: 0.001541  loss: 3.7158 (3.5504)  weight_decay: 0.0500 (0.0500)  time: 0.6235  data: 0.0753  max mem: 31830
Epoch: [180]  [220/312]  eta: 0:00:52  lr: 0.001540  min_lr: 0.001540  loss: 3.7988 (3.5635)  weight_decay: 0.0500 (0.0500)  time: 0.5552  data: 0.0572  max mem: 31830
Epoch: [180]  [230/312]  eta: 0:00:46  lr: 0.001539  min_lr: 0.001539  loss: 3.8492 (3.5674)  weight_decay: 0.0500 (0.0500)  time: 0.4479  data: 0.0206  max mem: 31830
Epoch: [180]  [240/312]  eta: 0:00:40  lr: 0.001539  min_lr: 0.001539  loss: 3.6488 (3.5678)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0262  max mem: 31830
Epoch: [180]  [250/312]  eta: 0:00:35  lr: 0.001538  min_lr: 0.001538  loss: 3.6132 (3.5673)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0665  max mem: 31830
Epoch: [180]  [260/312]  eta: 0:00:29  lr: 0.001537  min_lr: 0.001537  loss: 3.7281 (3.5698)  weight_decay: 0.0500 (0.0500)  time: 0.5998  data: 0.1023  max mem: 31830
Epoch: [180]  [270/312]  eta: 0:00:23  lr: 0.001537  min_lr: 0.001537  loss: 3.4950 (3.5631)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0431  max mem: 31830
Epoch: [180]  [280/312]  eta: 0:00:18  lr: 0.001536  min_lr: 0.001536  loss: 3.3083 (3.5564)  weight_decay: 0.0500 (0.0500)  time: 0.5277  data: 0.0531  max mem: 31830
Epoch: [180]  [290/312]  eta: 0:00:12  lr: 0.001535  min_lr: 0.001535  loss: 3.6113 (3.5595)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0696  max mem: 31830
Epoch: [180]  [300/312]  eta: 0:00:06  lr: 0.001535  min_lr: 0.001535  loss: 3.5692 (3.5489)  weight_decay: 0.0500 (0.0500)  time: 0.4554  data: 0.0180  max mem: 31830
Epoch: [180]  [310/312]  eta: 0:00:01  lr: 0.001534  min_lr: 0.001534  loss: 3.5582 (3.5494)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0002  max mem: 31830
Epoch: [180]  [311/312]  eta: 0:00:00  lr: 0.001534  min_lr: 0.001534  loss: 3.5582 (3.5459)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0002  max mem: 31830
Epoch: [180] Total time: 0:02:53 (0.5567 s / it)
Averaged stats: lr: 0.001534  min_lr: 0.001534  loss: 3.5582 (3.5020)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.1359 (1.1359)  acc1: 80.2083 (80.2083)  acc5: 94.2708 (94.2708)  time: 8.7315  data: 8.5715  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4261 (1.3445)  acc1: 70.3125 (71.9840)  acc5: 90.7552 (91.0560)  time: 1.0891  data: 0.9525  max mem: 31830
Test: Total time: 0:00:09 (1.1088 s / it)
* Acc@1 72.036 Acc@5 91.000 loss 1.361
Accuracy of the model on the 50000 test images: 72.0%
Max accuracy: 72.04%
Epoch: [181]  [  0/312]  eta: 1:00:49  lr: 0.001534  min_lr: 0.001534  loss: 3.8741 (3.8741)  weight_decay: 0.0500 (0.0500)  time: 11.6973  data: 8.6989  max mem: 31830
Epoch: [181]  [ 10/312]  eta: 0:08:13  lr: 0.001533  min_lr: 0.001533  loss: 3.6870 (3.5984)  weight_decay: 0.0500 (0.0500)  time: 1.6329  data: 0.9460  max mem: 31830
Epoch: [181]  [ 20/312]  eta: 0:05:29  lr: 0.001532  min_lr: 0.001532  loss: 3.6870 (3.5921)  weight_decay: 0.0500 (0.0500)  time: 0.6014  data: 0.1020  max mem: 31830
Epoch: [181]  [ 30/312]  eta: 0:04:12  lr: 0.001532  min_lr: 0.001532  loss: 3.7184 (3.5583)  weight_decay: 0.0500 (0.0500)  time: 0.4881  data: 0.0171  max mem: 31830
Epoch: [181]  [ 40/312]  eta: 0:03:33  lr: 0.001531  min_lr: 0.001531  loss: 3.5327 (3.5740)  weight_decay: 0.0500 (0.0500)  time: 0.4223  data: 0.0267  max mem: 31830
Epoch: [181]  [ 50/312]  eta: 0:03:08  lr: 0.001530  min_lr: 0.001530  loss: 3.6985 (3.5671)  weight_decay: 0.0500 (0.0500)  time: 0.4445  data: 0.0513  max mem: 31830
Epoch: [181]  [ 60/312]  eta: 0:02:47  lr: 0.001530  min_lr: 0.001530  loss: 3.5437 (3.5178)  weight_decay: 0.0500 (0.0500)  time: 0.4197  data: 0.0255  max mem: 31830
Epoch: [181]  [ 70/312]  eta: 0:02:38  lr: 0.001529  min_lr: 0.001529  loss: 3.3693 (3.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0663  max mem: 31830
Epoch: [181]  [ 80/312]  eta: 0:02:31  lr: 0.001528  min_lr: 0.001528  loss: 3.6520 (3.5320)  weight_decay: 0.0500 (0.0500)  time: 0.6177  data: 0.1523  max mem: 31830
Epoch: [181]  [ 90/312]  eta: 0:02:18  lr: 0.001527  min_lr: 0.001527  loss: 3.5495 (3.5303)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0870  max mem: 31830
Epoch: [181]  [100/312]  eta: 0:02:13  lr: 0.001527  min_lr: 0.001527  loss: 3.3120 (3.4907)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0485  max mem: 31830
Epoch: [181]  [110/312]  eta: 0:02:02  lr: 0.001526  min_lr: 0.001526  loss: 3.3120 (3.4952)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0483  max mem: 31830
Epoch: [181]  [120/312]  eta: 0:01:57  lr: 0.001525  min_lr: 0.001525  loss: 3.6491 (3.4865)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0077  max mem: 31830
Epoch: [181]  [130/312]  eta: 0:01:51  lr: 0.001525  min_lr: 0.001525  loss: 3.7084 (3.4973)  weight_decay: 0.0500 (0.0500)  time: 0.6203  data: 0.0080  max mem: 31830
Epoch: [181]  [140/312]  eta: 0:01:42  lr: 0.001524  min_lr: 0.001524  loss: 3.7105 (3.5015)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0013  max mem: 31830
Epoch: [181]  [150/312]  eta: 0:01:37  lr: 0.001523  min_lr: 0.001523  loss: 3.6829 (3.5075)  weight_decay: 0.0500 (0.0500)  time: 0.5295  data: 0.0011  max mem: 31830
Epoch: [181]  [160/312]  eta: 0:01:31  lr: 0.001523  min_lr: 0.001523  loss: 3.5836 (3.5029)  weight_decay: 0.0500 (0.0500)  time: 0.6757  data: 0.0292  max mem: 31830
Epoch: [181]  [170/312]  eta: 0:01:24  lr: 0.001522  min_lr: 0.001522  loss: 3.4956 (3.5000)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0297  max mem: 31830
Epoch: [181]  [180/312]  eta: 0:01:18  lr: 0.001521  min_lr: 0.001521  loss: 3.6754 (3.5110)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0214  max mem: 31830
Epoch: [181]  [190/312]  eta: 0:01:11  lr: 0.001520  min_lr: 0.001520  loss: 3.7132 (3.5081)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0208  max mem: 31830
Epoch: [181]  [200/312]  eta: 0:01:05  lr: 0.001520  min_lr: 0.001520  loss: 3.5022 (3.5091)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0146  max mem: 31830
Epoch: [181]  [210/312]  eta: 0:01:00  lr: 0.001519  min_lr: 0.001519  loss: 3.6181 (3.5176)  weight_decay: 0.0500 (0.0500)  time: 0.6291  data: 0.0210  max mem: 31830
Epoch: [181]  [220/312]  eta: 0:00:53  lr: 0.001518  min_lr: 0.001518  loss: 3.6607 (3.5148)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0073  max mem: 31830
Epoch: [181]  [230/312]  eta: 0:00:47  lr: 0.001518  min_lr: 0.001518  loss: 3.6045 (3.5126)  weight_decay: 0.0500 (0.0500)  time: 0.5432  data: 0.0436  max mem: 31830
Epoch: [181]  [240/312]  eta: 0:00:42  lr: 0.001517  min_lr: 0.001517  loss: 3.5860 (3.5105)  weight_decay: 0.0500 (0.0500)  time: 0.6241  data: 0.0439  max mem: 31830
Epoch: [181]  [250/312]  eta: 0:00:35  lr: 0.001516  min_lr: 0.001516  loss: 3.6116 (3.5145)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0124  max mem: 31830
Epoch: [181]  [260/312]  eta: 0:00:30  lr: 0.001516  min_lr: 0.001516  loss: 3.6453 (3.5145)  weight_decay: 0.0500 (0.0500)  time: 0.5580  data: 0.0430  max mem: 31830
Epoch: [181]  [270/312]  eta: 0:00:24  lr: 0.001515  min_lr: 0.001515  loss: 3.5919 (3.5099)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0318  max mem: 31830
Epoch: [181]  [280/312]  eta: 0:00:18  lr: 0.001514  min_lr: 0.001514  loss: 3.5012 (3.5068)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0135  max mem: 31830
Epoch: [181]  [290/312]  eta: 0:00:12  lr: 0.001513  min_lr: 0.001513  loss: 3.5012 (3.5026)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0132  max mem: 31830
Epoch: [181]  [300/312]  eta: 0:00:06  lr: 0.001513  min_lr: 0.001513  loss: 3.6127 (3.5071)  weight_decay: 0.0500 (0.0500)  time: 0.4198  data: 0.0002  max mem: 31830
Epoch: [181]  [310/312]  eta: 0:00:01  lr: 0.001512  min_lr: 0.001512  loss: 3.6474 (3.5100)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [181]  [311/312]  eta: 0:00:00  lr: 0.001512  min_lr: 0.001512  loss: 3.6474 (3.5082)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [181] Total time: 0:02:55 (0.5624 s / it)
Averaged stats: lr: 0.001512  min_lr: 0.001512  loss: 3.6474 (3.5037)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.1676 (1.1676)  acc1: 78.2552 (78.2552)  acc5: 93.3594 (93.3594)  time: 8.7686  data: 8.6018  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4858 (1.3727)  acc1: 70.0521 (70.7200)  acc5: 90.3646 (90.5440)  time: 1.0911  data: 0.9558  max mem: 31830
Test: Total time: 0:00:10 (1.1203 s / it)
* Acc@1 71.246 Acc@5 90.652 loss 1.381
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 72.04%
Epoch: [182]  [  0/312]  eta: 0:59:34  lr: 0.001512  min_lr: 0.001512  loss: 4.1482 (4.1482)  weight_decay: 0.0500 (0.0500)  time: 11.4559  data: 8.8130  max mem: 31830
Epoch: [182]  [ 10/312]  eta: 0:09:05  lr: 0.001511  min_lr: 0.001511  loss: 3.7326 (3.6424)  weight_decay: 0.0500 (0.0500)  time: 1.8050  data: 0.9969  max mem: 31830
Epoch: [182]  [ 20/312]  eta: 0:05:37  lr: 0.001511  min_lr: 0.001511  loss: 3.5310 (3.4981)  weight_decay: 0.0500 (0.0500)  time: 0.6426  data: 0.1345  max mem: 31830
Epoch: [182]  [ 30/312]  eta: 0:04:17  lr: 0.001510  min_lr: 0.001510  loss: 3.5317 (3.4588)  weight_decay: 0.0500 (0.0500)  time: 0.4220  data: 0.0273  max mem: 31830
Epoch: [182]  [ 40/312]  eta: 0:03:34  lr: 0.001509  min_lr: 0.001509  loss: 3.7422 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0010  max mem: 31830
Epoch: [182]  [ 50/312]  eta: 0:03:06  lr: 0.001508  min_lr: 0.001508  loss: 3.7274 (3.5386)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0010  max mem: 31830
Epoch: [182]  [ 60/312]  eta: 0:02:46  lr: 0.001508  min_lr: 0.001508  loss: 3.6953 (3.5685)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0012  max mem: 31830
Epoch: [182]  [ 70/312]  eta: 0:02:31  lr: 0.001507  min_lr: 0.001507  loss: 3.6422 (3.5594)  weight_decay: 0.0500 (0.0500)  time: 0.4112  data: 0.0010  max mem: 31830
Epoch: [182]  [ 80/312]  eta: 0:02:24  lr: 0.001506  min_lr: 0.001506  loss: 3.4906 (3.5541)  weight_decay: 0.0500 (0.0500)  time: 0.5010  data: 0.0308  max mem: 31830
Epoch: [182]  [ 90/312]  eta: 0:02:15  lr: 0.001506  min_lr: 0.001506  loss: 3.3783 (3.5162)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0976  max mem: 31830
Epoch: [182]  [100/312]  eta: 0:02:08  lr: 0.001505  min_lr: 0.001505  loss: 3.4854 (3.5215)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.1153  max mem: 31830
Epoch: [182]  [110/312]  eta: 0:02:00  lr: 0.001504  min_lr: 0.001504  loss: 3.4574 (3.4920)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0752  max mem: 31830
Epoch: [182]  [120/312]  eta: 0:01:54  lr: 0.001504  min_lr: 0.001504  loss: 3.5097 (3.5104)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0863  max mem: 31830
Epoch: [182]  [130/312]  eta: 0:01:47  lr: 0.001503  min_lr: 0.001503  loss: 3.6695 (3.5117)  weight_decay: 0.0500 (0.0500)  time: 0.5757  data: 0.1034  max mem: 31830
Epoch: [182]  [140/312]  eta: 0:01:39  lr: 0.001502  min_lr: 0.001502  loss: 3.4580 (3.5137)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0588  max mem: 31830
Epoch: [182]  [150/312]  eta: 0:01:34  lr: 0.001501  min_lr: 0.001501  loss: 3.4278 (3.4993)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0761  max mem: 31830
Epoch: [182]  [160/312]  eta: 0:01:27  lr: 0.001501  min_lr: 0.001501  loss: 3.4084 (3.5025)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0766  max mem: 31830
Epoch: [182]  [170/312]  eta: 0:01:22  lr: 0.001500  min_lr: 0.001500  loss: 3.6718 (3.4911)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0701  max mem: 31830
Epoch: [182]  [180/312]  eta: 0:01:16  lr: 0.001499  min_lr: 0.001499  loss: 3.6533 (3.4926)  weight_decay: 0.0500 (0.0500)  time: 0.5866  data: 0.1129  max mem: 31830
Epoch: [182]  [190/312]  eta: 0:01:10  lr: 0.001499  min_lr: 0.001499  loss: 3.7069 (3.4926)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0581  max mem: 31830
Epoch: [182]  [200/312]  eta: 0:01:04  lr: 0.001498  min_lr: 0.001498  loss: 3.7210 (3.4979)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.0594  max mem: 31830
Epoch: [182]  [210/312]  eta: 0:00:58  lr: 0.001497  min_lr: 0.001497  loss: 3.5143 (3.4968)  weight_decay: 0.0500 (0.0500)  time: 0.5951  data: 0.1143  max mem: 31830
Epoch: [182]  [220/312]  eta: 0:00:52  lr: 0.001497  min_lr: 0.001497  loss: 3.4602 (3.4862)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0558  max mem: 31830
Epoch: [182]  [230/312]  eta: 0:00:46  lr: 0.001496  min_lr: 0.001496  loss: 3.6750 (3.4945)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0347  max mem: 31830
Epoch: [182]  [240/312]  eta: 0:00:40  lr: 0.001495  min_lr: 0.001495  loss: 3.6750 (3.4847)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.0351  max mem: 31830
Epoch: [182]  [250/312]  eta: 0:00:35  lr: 0.001495  min_lr: 0.001495  loss: 3.4169 (3.4802)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0220  max mem: 31830
Epoch: [182]  [260/312]  eta: 0:00:29  lr: 0.001494  min_lr: 0.001494  loss: 3.5434 (3.4763)  weight_decay: 0.0500 (0.0500)  time: 0.5916  data: 0.0429  max mem: 31830
Epoch: [182]  [270/312]  eta: 0:00:23  lr: 0.001493  min_lr: 0.001493  loss: 3.6892 (3.4875)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0223  max mem: 31830
Epoch: [182]  [280/312]  eta: 0:00:18  lr: 0.001492  min_lr: 0.001492  loss: 3.7413 (3.4960)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0099  max mem: 31830
Epoch: [182]  [290/312]  eta: 0:00:12  lr: 0.001492  min_lr: 0.001492  loss: 3.6988 (3.4888)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0165  max mem: 31830
Epoch: [182]  [300/312]  eta: 0:00:06  lr: 0.001491  min_lr: 0.001491  loss: 3.3538 (3.4839)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0072  max mem: 31830
Epoch: [182]  [310/312]  eta: 0:00:01  lr: 0.001490  min_lr: 0.001490  loss: 3.4344 (3.4856)  weight_decay: 0.0500 (0.0500)  time: 0.4032  data: 0.0002  max mem: 31830
Epoch: [182]  [311/312]  eta: 0:00:00  lr: 0.001490  min_lr: 0.001490  loss: 3.4505 (3.4868)  weight_decay: 0.0500 (0.0500)  time: 0.4029  data: 0.0002  max mem: 31830
Epoch: [182] Total time: 0:02:54 (0.5592 s / it)
Averaged stats: lr: 0.001490  min_lr: 0.001490  loss: 3.4505 (3.4976)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 1.1779 (1.1779)  acc1: 79.8177 (79.8177)  acc5: 93.8802 (93.8802)  time: 9.1454  data: 8.9783  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5264 (1.4455)  acc1: 70.1823 (71.2640)  acc5: 90.8854 (90.5440)  time: 1.1338  data: 0.9976  max mem: 31830
Test: Total time: 0:00:10 (1.1590 s / it)
* Acc@1 71.228 Acc@5 90.644 loss 1.448
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 72.04%
Epoch: [183]  [  0/312]  eta: 1:02:28  lr: 0.001490  min_lr: 0.001490  loss: 2.9433 (2.9433)  weight_decay: 0.0500 (0.0500)  time: 12.0146  data: 9.6696  max mem: 31830
Epoch: [183]  [ 10/312]  eta: 0:08:31  lr: 0.001490  min_lr: 0.001490  loss: 3.7682 (3.5317)  weight_decay: 0.0500 (0.0500)  time: 1.6929  data: 1.0202  max mem: 31830
Epoch: [183]  [ 20/312]  eta: 0:05:39  lr: 0.001489  min_lr: 0.001489  loss: 3.6876 (3.4538)  weight_decay: 0.0500 (0.0500)  time: 0.6218  data: 0.1267  max mem: 31830
Epoch: [183]  [ 30/312]  eta: 0:04:18  lr: 0.001488  min_lr: 0.001488  loss: 3.6808 (3.5694)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0495  max mem: 31830
Epoch: [183]  [ 40/312]  eta: 0:03:34  lr: 0.001487  min_lr: 0.001487  loss: 3.6377 (3.4477)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0009  max mem: 31830
Epoch: [183]  [ 50/312]  eta: 0:03:06  lr: 0.001487  min_lr: 0.001487  loss: 3.6665 (3.4978)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0009  max mem: 31830
Epoch: [183]  [ 60/312]  eta: 0:02:46  lr: 0.001486  min_lr: 0.001486  loss: 3.6134 (3.5019)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0010  max mem: 31830
Epoch: [183]  [ 70/312]  eta: 0:02:33  lr: 0.001485  min_lr: 0.001485  loss: 3.5433 (3.5063)  weight_decay: 0.0500 (0.0500)  time: 0.4413  data: 0.0201  max mem: 31830
Epoch: [183]  [ 80/312]  eta: 0:02:25  lr: 0.001485  min_lr: 0.001485  loss: 3.4351 (3.4824)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0201  max mem: 31830
Epoch: [183]  [ 90/312]  eta: 0:02:16  lr: 0.001484  min_lr: 0.001484  loss: 3.1014 (3.4530)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0585  max mem: 31830
Epoch: [183]  [100/312]  eta: 0:02:08  lr: 0.001483  min_lr: 0.001483  loss: 3.2719 (3.4489)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0737  max mem: 31830
Epoch: [183]  [110/312]  eta: 0:01:58  lr: 0.001483  min_lr: 0.001483  loss: 3.5097 (3.4665)  weight_decay: 0.0500 (0.0500)  time: 0.4592  data: 0.0165  max mem: 31830
Epoch: [183]  [120/312]  eta: 0:01:53  lr: 0.001482  min_lr: 0.001482  loss: 3.6000 (3.4606)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0459  max mem: 31830
Epoch: [183]  [130/312]  eta: 0:01:48  lr: 0.001481  min_lr: 0.001481  loss: 3.2440 (3.4383)  weight_decay: 0.0500 (0.0500)  time: 0.6330  data: 0.0756  max mem: 31830
Epoch: [183]  [140/312]  eta: 0:01:39  lr: 0.001480  min_lr: 0.001480  loss: 3.1860 (3.4335)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0309  max mem: 31830
Epoch: [183]  [150/312]  eta: 0:01:34  lr: 0.001480  min_lr: 0.001480  loss: 3.4735 (3.4203)  weight_decay: 0.0500 (0.0500)  time: 0.5115  data: 0.0337  max mem: 31830
Epoch: [183]  [160/312]  eta: 0:01:28  lr: 0.001479  min_lr: 0.001479  loss: 3.5349 (3.4253)  weight_decay: 0.0500 (0.0500)  time: 0.5935  data: 0.0335  max mem: 31830
Epoch: [183]  [170/312]  eta: 0:01:21  lr: 0.001478  min_lr: 0.001478  loss: 3.6956 (3.4286)  weight_decay: 0.0500 (0.0500)  time: 0.5251  data: 0.0477  max mem: 31830
Epoch: [183]  [180/312]  eta: 0:01:16  lr: 0.001478  min_lr: 0.001478  loss: 3.7050 (3.4386)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.0797  max mem: 31830
Epoch: [183]  [190/312]  eta: 0:01:09  lr: 0.001477  min_lr: 0.001477  loss: 3.6468 (3.4416)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0332  max mem: 31830
Epoch: [183]  [200/312]  eta: 0:01:03  lr: 0.001476  min_lr: 0.001476  loss: 3.5729 (3.4293)  weight_decay: 0.0500 (0.0500)  time: 0.4992  data: 0.0167  max mem: 31830
Epoch: [183]  [210/312]  eta: 0:00:58  lr: 0.001476  min_lr: 0.001476  loss: 3.5734 (3.4431)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0459  max mem: 31830
Epoch: [183]  [220/312]  eta: 0:00:52  lr: 0.001475  min_lr: 0.001475  loss: 3.7817 (3.4520)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0306  max mem: 31830
Epoch: [183]  [230/312]  eta: 0:00:46  lr: 0.001474  min_lr: 0.001474  loss: 3.7611 (3.4652)  weight_decay: 0.0500 (0.0500)  time: 0.5138  data: 0.0285  max mem: 31830
Epoch: [183]  [240/312]  eta: 0:00:40  lr: 0.001474  min_lr: 0.001474  loss: 3.6045 (3.4623)  weight_decay: 0.0500 (0.0500)  time: 0.5846  data: 0.0284  max mem: 31830
Epoch: [183]  [250/312]  eta: 0:00:34  lr: 0.001473  min_lr: 0.001473  loss: 3.5063 (3.4610)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0194  max mem: 31830
Epoch: [183]  [260/312]  eta: 0:00:29  lr: 0.001472  min_lr: 0.001472  loss: 3.4690 (3.4559)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0402  max mem: 31830
Epoch: [183]  [270/312]  eta: 0:00:23  lr: 0.001471  min_lr: 0.001471  loss: 3.4562 (3.4568)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0218  max mem: 31830
Epoch: [183]  [280/312]  eta: 0:00:18  lr: 0.001471  min_lr: 0.001471  loss: 3.3467 (3.4542)  weight_decay: 0.0500 (0.0500)  time: 0.5307  data: 0.0084  max mem: 31830
Epoch: [183]  [290/312]  eta: 0:00:12  lr: 0.001470  min_lr: 0.001470  loss: 3.6894 (3.4616)  weight_decay: 0.0500 (0.0500)  time: 0.6151  data: 0.0222  max mem: 31830
Epoch: [183]  [300/312]  eta: 0:00:06  lr: 0.001469  min_lr: 0.001469  loss: 3.6465 (3.4514)  weight_decay: 0.0500 (0.0500)  time: 0.4836  data: 0.0143  max mem: 31830
Epoch: [183]  [310/312]  eta: 0:00:01  lr: 0.001469  min_lr: 0.001469  loss: 3.5295 (3.4512)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [183]  [311/312]  eta: 0:00:00  lr: 0.001469  min_lr: 0.001469  loss: 3.5295 (3.4533)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [183] Total time: 0:02:53 (0.5549 s / it)
Averaged stats: lr: 0.001469  min_lr: 0.001469  loss: 3.5295 (3.4724)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.2167 (1.2167)  acc1: 79.1667 (79.1667)  acc5: 93.2292 (93.2292)  time: 8.5868  data: 8.4192  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4660 (1.4003)  acc1: 70.8333 (71.7600)  acc5: 91.0156 (90.8480)  time: 1.0715  data: 0.9356  max mem: 31830
Test: Total time: 0:00:09 (1.0961 s / it)
* Acc@1 71.800 Acc@5 91.006 loss 1.392
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 72.04%
Epoch: [184]  [  0/312]  eta: 1:03:10  lr: 0.001469  min_lr: 0.001469  loss: 4.0513 (4.0513)  weight_decay: 0.0500 (0.0500)  time: 12.1506  data: 10.4446  max mem: 31830
Epoch: [184]  [ 10/312]  eta: 0:08:52  lr: 0.001468  min_lr: 0.001468  loss: 3.6741 (3.6579)  weight_decay: 0.0500 (0.0500)  time: 1.7622  data: 1.0442  max mem: 31830
Epoch: [184]  [ 20/312]  eta: 0:05:36  lr: 0.001467  min_lr: 0.001467  loss: 3.4923 (3.4823)  weight_decay: 0.0500 (0.0500)  time: 0.6015  data: 0.0525  max mem: 31830
Epoch: [184]  [ 30/312]  eta: 0:04:16  lr: 0.001466  min_lr: 0.001466  loss: 3.4081 (3.4864)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0008  max mem: 31830
Epoch: [184]  [ 40/312]  eta: 0:03:33  lr: 0.001466  min_lr: 0.001466  loss: 3.4081 (3.4928)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0015  max mem: 31830
Epoch: [184]  [ 50/312]  eta: 0:03:05  lr: 0.001465  min_lr: 0.001465  loss: 3.6254 (3.4908)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0018  max mem: 31830
Epoch: [184]  [ 60/312]  eta: 0:02:45  lr: 0.001464  min_lr: 0.001464  loss: 3.3683 (3.4260)  weight_decay: 0.0500 (0.0500)  time: 0.3954  data: 0.0011  max mem: 31830
Epoch: [184]  [ 70/312]  eta: 0:02:31  lr: 0.001464  min_lr: 0.001464  loss: 3.3479 (3.4275)  weight_decay: 0.0500 (0.0500)  time: 0.4240  data: 0.0209  max mem: 31830
Epoch: [184]  [ 80/312]  eta: 0:02:23  lr: 0.001463  min_lr: 0.001463  loss: 3.3551 (3.4140)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0796  max mem: 31830
Epoch: [184]  [ 90/312]  eta: 0:02:14  lr: 0.001462  min_lr: 0.001462  loss: 3.2118 (3.4078)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.1266  max mem: 31830
Epoch: [184]  [100/312]  eta: 0:02:08  lr: 0.001462  min_lr: 0.001462  loss: 3.3105 (3.4084)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.1528  max mem: 31830
Epoch: [184]  [110/312]  eta: 0:01:59  lr: 0.001461  min_lr: 0.001461  loss: 3.6975 (3.4338)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0865  max mem: 31830
Epoch: [184]  [120/312]  eta: 0:01:53  lr: 0.001460  min_lr: 0.001460  loss: 3.7221 (3.4361)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0741  max mem: 31830
Epoch: [184]  [130/312]  eta: 0:01:47  lr: 0.001460  min_lr: 0.001460  loss: 3.5143 (3.4457)  weight_decay: 0.0500 (0.0500)  time: 0.5974  data: 0.1813  max mem: 31830
Epoch: [184]  [140/312]  eta: 0:01:39  lr: 0.001459  min_lr: 0.001459  loss: 3.6025 (3.4352)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.1301  max mem: 31830
Epoch: [184]  [150/312]  eta: 0:01:34  lr: 0.001458  min_lr: 0.001458  loss: 3.5261 (3.4391)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.1004  max mem: 31830
Epoch: [184]  [160/312]  eta: 0:01:27  lr: 0.001457  min_lr: 0.001457  loss: 3.6968 (3.4455)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.1093  max mem: 31830
Epoch: [184]  [170/312]  eta: 0:01:22  lr: 0.001457  min_lr: 0.001457  loss: 3.6197 (3.4503)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.1453  max mem: 31830
Epoch: [184]  [180/312]  eta: 0:01:16  lr: 0.001456  min_lr: 0.001456  loss: 3.6386 (3.4720)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.1904  max mem: 31830
Epoch: [184]  [190/312]  eta: 0:01:09  lr: 0.001455  min_lr: 0.001455  loss: 3.6456 (3.4742)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.1066  max mem: 31830
Epoch: [184]  [200/312]  eta: 0:01:03  lr: 0.001455  min_lr: 0.001455  loss: 3.6309 (3.4860)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.1045  max mem: 31830
Epoch: [184]  [210/312]  eta: 0:00:58  lr: 0.001454  min_lr: 0.001454  loss: 3.6634 (3.4950)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.1903  max mem: 31830
Epoch: [184]  [220/312]  eta: 0:00:52  lr: 0.001453  min_lr: 0.001453  loss: 3.6622 (3.4950)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.1850  max mem: 31830
Epoch: [184]  [230/312]  eta: 0:00:46  lr: 0.001453  min_lr: 0.001453  loss: 3.6491 (3.5008)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.1117  max mem: 31830
Epoch: [184]  [240/312]  eta: 0:00:40  lr: 0.001452  min_lr: 0.001452  loss: 3.6614 (3.4983)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.1208  max mem: 31830
Epoch: [184]  [250/312]  eta: 0:00:35  lr: 0.001451  min_lr: 0.001451  loss: 3.6127 (3.4967)  weight_decay: 0.0500 (0.0500)  time: 0.5895  data: 0.1588  max mem: 31830
Epoch: [184]  [260/312]  eta: 0:00:29  lr: 0.001451  min_lr: 0.001451  loss: 3.5964 (3.4954)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.1325  max mem: 31830
Epoch: [184]  [270/312]  eta: 0:00:23  lr: 0.001450  min_lr: 0.001450  loss: 3.5964 (3.4984)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.0938  max mem: 31830
Epoch: [184]  [280/312]  eta: 0:00:18  lr: 0.001449  min_lr: 0.001449  loss: 3.7659 (3.5064)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0630  max mem: 31830
Epoch: [184]  [290/312]  eta: 0:00:12  lr: 0.001448  min_lr: 0.001448  loss: 3.7659 (3.5112)  weight_decay: 0.0500 (0.0500)  time: 0.6057  data: 0.0857  max mem: 31830
Epoch: [184]  [300/312]  eta: 0:00:06  lr: 0.001448  min_lr: 0.001448  loss: 3.5089 (3.5027)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0716  max mem: 31830
Epoch: [184]  [310/312]  eta: 0:00:01  lr: 0.001447  min_lr: 0.001447  loss: 3.3788 (3.4963)  weight_decay: 0.0500 (0.0500)  time: 0.3866  data: 0.0062  max mem: 31830
Epoch: [184]  [311/312]  eta: 0:00:00  lr: 0.001447  min_lr: 0.001447  loss: 3.3788 (3.4975)  weight_decay: 0.0500 (0.0500)  time: 0.3864  data: 0.0062  max mem: 31830
Epoch: [184] Total time: 0:02:54 (0.5596 s / it)
Averaged stats: lr: 0.001447  min_lr: 0.001447  loss: 3.3788 (3.4757)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.2782 (1.2782)  acc1: 79.0365 (79.0365)  acc5: 94.0104 (94.0104)  time: 8.9788  data: 8.8197  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5370 (1.4471)  acc1: 72.2656 (71.6480)  acc5: 88.9323 (90.4640)  time: 1.1197  data: 0.9800  max mem: 31830
Test: Total time: 0:00:10 (1.1500 s / it)
* Acc@1 71.550 Acc@5 90.908 loss 1.436
Accuracy of the model on the 50000 test images: 71.6%
Max accuracy: 72.04%
Epoch: [185]  [  0/312]  eta: 1:03:37  lr: 0.001447  min_lr: 0.001447  loss: 2.6584 (2.6584)  weight_decay: 0.0500 (0.0500)  time: 12.2346  data: 11.7483  max mem: 31830
Epoch: [185]  [ 10/312]  eta: 0:08:25  lr: 0.001446  min_lr: 0.001446  loss: 3.6639 (3.4704)  weight_decay: 0.0500 (0.0500)  time: 1.6726  data: 1.0688  max mem: 31830
Epoch: [185]  [ 20/312]  eta: 0:05:26  lr: 0.001446  min_lr: 0.001446  loss: 3.5352 (3.3614)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0592  max mem: 31830
Epoch: [185]  [ 30/312]  eta: 0:04:09  lr: 0.001445  min_lr: 0.001445  loss: 3.5943 (3.4443)  weight_decay: 0.0500 (0.0500)  time: 0.4518  data: 0.0594  max mem: 31830
Epoch: [185]  [ 40/312]  eta: 0:03:28  lr: 0.001444  min_lr: 0.001444  loss: 3.6425 (3.4296)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0010  max mem: 31830
Epoch: [185]  [ 50/312]  eta: 0:03:07  lr: 0.001444  min_lr: 0.001444  loss: 3.6425 (3.4694)  weight_decay: 0.0500 (0.0500)  time: 0.4527  data: 0.0064  max mem: 31830
Epoch: [185]  [ 60/312]  eta: 0:02:48  lr: 0.001443  min_lr: 0.001443  loss: 3.5898 (3.4670)  weight_decay: 0.0500 (0.0500)  time: 0.4662  data: 0.0065  max mem: 31830
Epoch: [185]  [ 70/312]  eta: 0:02:41  lr: 0.001442  min_lr: 0.001442  loss: 3.6215 (3.4906)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.0218  max mem: 31830
Epoch: [185]  [ 80/312]  eta: 0:02:30  lr: 0.001441  min_lr: 0.001441  loss: 3.6263 (3.5075)  weight_decay: 0.0500 (0.0500)  time: 0.5892  data: 0.0217  max mem: 31830
Epoch: [185]  [ 90/312]  eta: 0:02:19  lr: 0.001441  min_lr: 0.001441  loss: 3.5791 (3.4923)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0073  max mem: 31830
Epoch: [185]  [100/312]  eta: 0:02:14  lr: 0.001440  min_lr: 0.001440  loss: 3.5180 (3.4836)  weight_decay: 0.0500 (0.0500)  time: 0.5708  data: 0.0075  max mem: 31830
Epoch: [185]  [110/312]  eta: 0:02:03  lr: 0.001439  min_lr: 0.001439  loss: 3.3288 (3.4679)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0011  max mem: 31830
Epoch: [185]  [120/312]  eta: 0:01:57  lr: 0.001439  min_lr: 0.001439  loss: 3.4615 (3.4583)  weight_decay: 0.0500 (0.0500)  time: 0.5018  data: 0.0074  max mem: 31830
Epoch: [185]  [130/312]  eta: 0:01:50  lr: 0.001438  min_lr: 0.001438  loss: 3.6055 (3.4716)  weight_decay: 0.0500 (0.0500)  time: 0.5700  data: 0.0076  max mem: 31830
Epoch: [185]  [140/312]  eta: 0:01:42  lr: 0.001437  min_lr: 0.001437  loss: 3.6055 (3.4536)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0014  max mem: 31830
Epoch: [185]  [150/312]  eta: 0:01:37  lr: 0.001437  min_lr: 0.001437  loss: 3.2240 (3.4387)  weight_decay: 0.0500 (0.0500)  time: 0.5603  data: 0.0014  max mem: 31830
Epoch: [185]  [160/312]  eta: 0:01:30  lr: 0.001436  min_lr: 0.001436  loss: 3.0045 (3.4187)  weight_decay: 0.0500 (0.0500)  time: 0.5793  data: 0.0009  max mem: 31830
Epoch: [185]  [170/312]  eta: 0:01:23  lr: 0.001435  min_lr: 0.001435  loss: 3.4230 (3.4331)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0008  max mem: 31830
Epoch: [185]  [180/312]  eta: 0:01:18  lr: 0.001435  min_lr: 0.001435  loss: 3.5953 (3.4282)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0148  max mem: 31830
Epoch: [185]  [190/312]  eta: 0:01:10  lr: 0.001434  min_lr: 0.001434  loss: 3.4385 (3.4251)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0149  max mem: 31830
Epoch: [185]  [200/312]  eta: 0:01:05  lr: 0.001433  min_lr: 0.001433  loss: 3.5610 (3.4244)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0154  max mem: 31830
Epoch: [185]  [210/312]  eta: 0:00:59  lr: 0.001432  min_lr: 0.001432  loss: 3.4222 (3.4184)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.0290  max mem: 31830
Epoch: [185]  [220/312]  eta: 0:00:53  lr: 0.001432  min_lr: 0.001432  loss: 3.4684 (3.4197)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0145  max mem: 31830
Epoch: [185]  [230/312]  eta: 0:00:47  lr: 0.001431  min_lr: 0.001431  loss: 3.6508 (3.4299)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0009  max mem: 31830
Epoch: [185]  [240/312]  eta: 0:00:41  lr: 0.001430  min_lr: 0.001430  loss: 3.6780 (3.4339)  weight_decay: 0.0500 (0.0500)  time: 0.5781  data: 0.0008  max mem: 31830
Epoch: [185]  [250/312]  eta: 0:00:35  lr: 0.001430  min_lr: 0.001430  loss: 3.6040 (3.4376)  weight_decay: 0.0500 (0.0500)  time: 0.4986  data: 0.0010  max mem: 31830
Epoch: [185]  [260/312]  eta: 0:00:30  lr: 0.001429  min_lr: 0.001429  loss: 3.4792 (3.4385)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0088  max mem: 31830
Epoch: [185]  [270/312]  eta: 0:00:23  lr: 0.001428  min_lr: 0.001428  loss: 3.4759 (3.4383)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0092  max mem: 31830
Epoch: [185]  [280/312]  eta: 0:00:18  lr: 0.001428  min_lr: 0.001428  loss: 3.3449 (3.4327)  weight_decay: 0.0500 (0.0500)  time: 0.5437  data: 0.0177  max mem: 31830
Epoch: [185]  [290/312]  eta: 0:00:12  lr: 0.001427  min_lr: 0.001427  loss: 3.4874 (3.4373)  weight_decay: 0.0500 (0.0500)  time: 0.5738  data: 0.0167  max mem: 31830
Epoch: [185]  [300/312]  eta: 0:00:06  lr: 0.001426  min_lr: 0.001426  loss: 3.4874 (3.4392)  weight_decay: 0.0500 (0.0500)  time: 0.4439  data: 0.0002  max mem: 31830
Epoch: [185]  [310/312]  eta: 0:00:01  lr: 0.001426  min_lr: 0.001426  loss: 3.5015 (3.4407)  weight_decay: 0.0500 (0.0500)  time: 0.4057  data: 0.0001  max mem: 31830
Epoch: [185]  [311/312]  eta: 0:00:00  lr: 0.001426  min_lr: 0.001426  loss: 3.5015 (3.4419)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [185] Total time: 0:02:55 (0.5635 s / it)
Averaged stats: lr: 0.001426  min_lr: 0.001426  loss: 3.5015 (3.4816)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0850 (1.0850)  acc1: 81.3802 (81.3802)  acc5: 93.8802 (93.8802)  time: 8.8462  data: 8.6861  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4824 (1.4049)  acc1: 69.6615 (71.7120)  acc5: 91.6667 (90.9280)  time: 1.1037  data: 0.9652  max mem: 31830
Test: Total time: 0:00:10 (1.1253 s / it)
* Acc@1 71.620 Acc@5 90.932 loss 1.407
Accuracy of the model on the 50000 test images: 71.6%
Max accuracy: 72.04%
Epoch: [186]  [  0/312]  eta: 1:05:17  lr: 0.001425  min_lr: 0.001425  loss: 4.0727 (4.0727)  weight_decay: 0.0500 (0.0500)  time: 12.5571  data: 9.9577  max mem: 31830
Epoch: [186]  [ 10/312]  eta: 0:08:56  lr: 0.001425  min_lr: 0.001425  loss: 3.7749 (3.7517)  weight_decay: 0.0500 (0.0500)  time: 1.7748  data: 1.0234  max mem: 31830
Epoch: [186]  [ 20/312]  eta: 0:05:34  lr: 0.001424  min_lr: 0.001424  loss: 3.7749 (3.7663)  weight_decay: 0.0500 (0.0500)  time: 0.5746  data: 0.0654  max mem: 31830
Epoch: [186]  [ 30/312]  eta: 0:04:15  lr: 0.001423  min_lr: 0.001423  loss: 3.7415 (3.7199)  weight_decay: 0.0500 (0.0500)  time: 0.4263  data: 0.0009  max mem: 31830
Epoch: [186]  [ 40/312]  eta: 0:03:32  lr: 0.001423  min_lr: 0.001423  loss: 3.6635 (3.6914)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [186]  [ 50/312]  eta: 0:03:05  lr: 0.001422  min_lr: 0.001422  loss: 3.4278 (3.6313)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [186]  [ 60/312]  eta: 0:02:45  lr: 0.001421  min_lr: 0.001421  loss: 3.2909 (3.5947)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0010  max mem: 31830
Epoch: [186]  [ 70/312]  eta: 0:02:35  lr: 0.001421  min_lr: 0.001421  loss: 3.5667 (3.6148)  weight_decay: 0.0500 (0.0500)  time: 0.4755  data: 0.0009  max mem: 31830
Epoch: [186]  [ 80/312]  eta: 0:02:25  lr: 0.001420  min_lr: 0.001420  loss: 3.6466 (3.6176)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0009  max mem: 31830
Epoch: [186]  [ 90/312]  eta: 0:02:16  lr: 0.001419  min_lr: 0.001419  loss: 3.3962 (3.5770)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0011  max mem: 31830
Epoch: [186]  [100/312]  eta: 0:02:10  lr: 0.001419  min_lr: 0.001419  loss: 3.4509 (3.5884)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0013  max mem: 31830
Epoch: [186]  [110/312]  eta: 0:02:04  lr: 0.001418  min_lr: 0.001418  loss: 3.6425 (3.5748)  weight_decay: 0.0500 (0.0500)  time: 0.6065  data: 0.0021  max mem: 31830
Epoch: [186]  [120/312]  eta: 0:01:55  lr: 0.001417  min_lr: 0.001417  loss: 3.1642 (3.5222)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0066  max mem: 31830
Epoch: [186]  [130/312]  eta: 0:01:50  lr: 0.001416  min_lr: 0.001416  loss: 3.2616 (3.5186)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0447  max mem: 31830
Epoch: [186]  [140/312]  eta: 0:01:44  lr: 0.001416  min_lr: 0.001416  loss: 3.5083 (3.5091)  weight_decay: 0.0500 (0.0500)  time: 0.6360  data: 0.0402  max mem: 31830
Epoch: [186]  [150/312]  eta: 0:01:36  lr: 0.001415  min_lr: 0.001415  loss: 3.4462 (3.5089)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0188  max mem: 31830
Epoch: [186]  [160/312]  eta: 0:01:30  lr: 0.001414  min_lr: 0.001414  loss: 3.6874 (3.5087)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0320  max mem: 31830
Epoch: [186]  [170/312]  eta: 0:01:23  lr: 0.001414  min_lr: 0.001414  loss: 3.6874 (3.5193)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0141  max mem: 31830
Epoch: [186]  [180/312]  eta: 0:01:17  lr: 0.001413  min_lr: 0.001413  loss: 3.6113 (3.5080)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0135  max mem: 31830
Epoch: [186]  [190/312]  eta: 0:01:11  lr: 0.001412  min_lr: 0.001412  loss: 3.2462 (3.5058)  weight_decay: 0.0500 (0.0500)  time: 0.6317  data: 0.0137  max mem: 31830
Epoch: [186]  [200/312]  eta: 0:01:05  lr: 0.001412  min_lr: 0.001412  loss: 3.6050 (3.5039)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0153  max mem: 31830
Epoch: [186]  [210/312]  eta: 0:00:59  lr: 0.001411  min_lr: 0.001411  loss: 3.6743 (3.5048)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0220  max mem: 31830
Epoch: [186]  [220/312]  eta: 0:00:53  lr: 0.001410  min_lr: 0.001410  loss: 3.5680 (3.4977)  weight_decay: 0.0500 (0.0500)  time: 0.6396  data: 0.0077  max mem: 31830
Epoch: [186]  [230/312]  eta: 0:00:47  lr: 0.001410  min_lr: 0.001410  loss: 3.6246 (3.4985)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0200  max mem: 31830
Epoch: [186]  [240/312]  eta: 0:00:41  lr: 0.001409  min_lr: 0.001409  loss: 3.6692 (3.5014)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0199  max mem: 31830
Epoch: [186]  [250/312]  eta: 0:00:35  lr: 0.001408  min_lr: 0.001408  loss: 3.8016 (3.5069)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0067  max mem: 31830
Epoch: [186]  [260/312]  eta: 0:00:29  lr: 0.001408  min_lr: 0.001408  loss: 3.3045 (3.4885)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0076  max mem: 31830
Epoch: [186]  [270/312]  eta: 0:00:24  lr: 0.001407  min_lr: 0.001407  loss: 3.4138 (3.4978)  weight_decay: 0.0500 (0.0500)  time: 0.6148  data: 0.0160  max mem: 31830
Epoch: [186]  [280/312]  eta: 0:00:18  lr: 0.001406  min_lr: 0.001406  loss: 3.8237 (3.4990)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0316  max mem: 31830
Epoch: [186]  [290/312]  eta: 0:00:12  lr: 0.001406  min_lr: 0.001406  loss: 3.6759 (3.5062)  weight_decay: 0.0500 (0.0500)  time: 0.5414  data: 0.0169  max mem: 31830
Epoch: [186]  [300/312]  eta: 0:00:06  lr: 0.001405  min_lr: 0.001405  loss: 3.5546 (3.5027)  weight_decay: 0.0500 (0.0500)  time: 0.4962  data: 0.0092  max mem: 31830
Epoch: [186]  [310/312]  eta: 0:00:01  lr: 0.001404  min_lr: 0.001404  loss: 3.4587 (3.5043)  weight_decay: 0.0500 (0.0500)  time: 0.3891  data: 0.0091  max mem: 31830
Epoch: [186]  [311/312]  eta: 0:00:00  lr: 0.001404  min_lr: 0.001404  loss: 3.4587 (3.5029)  weight_decay: 0.0500 (0.0500)  time: 0.3890  data: 0.0091  max mem: 31830
Epoch: [186] Total time: 0:02:56 (0.5671 s / it)
Averaged stats: lr: 0.001404  min_lr: 0.001404  loss: 3.4587 (3.4847)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1109 (1.1109)  acc1: 77.8646 (77.8646)  acc5: 94.7917 (94.7917)  time: 8.6008  data: 8.4367  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3847 (1.2676)  acc1: 72.9167 (72.6080)  acc5: 90.6250 (91.3600)  time: 1.0732  data: 0.9375  max mem: 31830
Test: Total time: 0:00:09 (1.0963 s / it)
* Acc@1 72.534 Acc@5 91.506 loss 1.270
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.53%
Epoch: [187]  [  0/312]  eta: 1:02:43  lr: 0.001404  min_lr: 0.001404  loss: 3.3659 (3.3659)  weight_decay: 0.0500 (0.0500)  time: 12.0616  data: 10.2718  max mem: 31830
Epoch: [187]  [ 10/312]  eta: 0:08:09  lr: 0.001403  min_lr: 0.001403  loss: 3.3659 (3.3173)  weight_decay: 0.0500 (0.0500)  time: 1.6218  data: 1.1053  max mem: 31830
Epoch: [187]  [ 20/312]  eta: 0:05:37  lr: 0.001403  min_lr: 0.001403  loss: 3.4082 (3.3249)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.1679  max mem: 31830
Epoch: [187]  [ 30/312]  eta: 0:04:16  lr: 0.001402  min_lr: 0.001402  loss: 3.4082 (3.3372)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0739  max mem: 31830
Epoch: [187]  [ 40/312]  eta: 0:03:33  lr: 0.001401  min_lr: 0.001401  loss: 3.3876 (3.3620)  weight_decay: 0.0500 (0.0500)  time: 0.3932  data: 0.0014  max mem: 31830
Epoch: [187]  [ 50/312]  eta: 0:03:07  lr: 0.001401  min_lr: 0.001401  loss: 3.3538 (3.3288)  weight_decay: 0.0500 (0.0500)  time: 0.4206  data: 0.0255  max mem: 31830
Epoch: [187]  [ 60/312]  eta: 0:02:47  lr: 0.001400  min_lr: 0.001400  loss: 3.0842 (3.3272)  weight_decay: 0.0500 (0.0500)  time: 0.4185  data: 0.0249  max mem: 31830
Epoch: [187]  [ 70/312]  eta: 0:02:36  lr: 0.001399  min_lr: 0.001399  loss: 3.5052 (3.3343)  weight_decay: 0.0500 (0.0500)  time: 0.4693  data: 0.0749  max mem: 31830
Epoch: [187]  [ 80/312]  eta: 0:02:28  lr: 0.001399  min_lr: 0.001399  loss: 3.2684 (3.3266)  weight_decay: 0.0500 (0.0500)  time: 0.5687  data: 0.1705  max mem: 31830
Epoch: [187]  [ 90/312]  eta: 0:02:16  lr: 0.001398  min_lr: 0.001398  loss: 3.6942 (3.3902)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0965  max mem: 31830
Epoch: [187]  [100/312]  eta: 0:02:10  lr: 0.001397  min_lr: 0.001397  loss: 3.8205 (3.4086)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.1133  max mem: 31830
Epoch: [187]  [110/312]  eta: 0:02:00  lr: 0.001396  min_lr: 0.001396  loss: 3.5949 (3.3973)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.1135  max mem: 31830
Epoch: [187]  [120/312]  eta: 0:01:54  lr: 0.001396  min_lr: 0.001396  loss: 3.5949 (3.4273)  weight_decay: 0.0500 (0.0500)  time: 0.5088  data: 0.1158  max mem: 31830
Epoch: [187]  [130/312]  eta: 0:01:48  lr: 0.001395  min_lr: 0.001395  loss: 3.8081 (3.4492)  weight_decay: 0.0500 (0.0500)  time: 0.6076  data: 0.2160  max mem: 31830
Epoch: [187]  [140/312]  eta: 0:01:40  lr: 0.001394  min_lr: 0.001394  loss: 3.5690 (3.4445)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.1012  max mem: 31830
Epoch: [187]  [150/312]  eta: 0:01:35  lr: 0.001394  min_lr: 0.001394  loss: 3.6199 (3.4596)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.1320  max mem: 31830
Epoch: [187]  [160/312]  eta: 0:01:28  lr: 0.001393  min_lr: 0.001393  loss: 3.7383 (3.4678)  weight_decay: 0.0500 (0.0500)  time: 0.5976  data: 0.2034  max mem: 31830
Epoch: [187]  [170/312]  eta: 0:01:22  lr: 0.001392  min_lr: 0.001392  loss: 3.5646 (3.4674)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.1351  max mem: 31830
Epoch: [187]  [180/312]  eta: 0:01:17  lr: 0.001392  min_lr: 0.001392  loss: 3.4096 (3.4581)  weight_decay: 0.0500 (0.0500)  time: 0.5817  data: 0.1880  max mem: 31830
Epoch: [187]  [190/312]  eta: 0:01:10  lr: 0.001391  min_lr: 0.001391  loss: 3.4261 (3.4563)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.1257  max mem: 31830
Epoch: [187]  [200/312]  eta: 0:01:04  lr: 0.001390  min_lr: 0.001390  loss: 3.5619 (3.4559)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.1250  max mem: 31830
Epoch: [187]  [210/312]  eta: 0:00:59  lr: 0.001390  min_lr: 0.001390  loss: 3.4163 (3.4423)  weight_decay: 0.0500 (0.0500)  time: 0.6647  data: 0.2305  max mem: 31830
Epoch: [187]  [220/312]  eta: 0:00:52  lr: 0.001389  min_lr: 0.001389  loss: 3.2997 (3.4361)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.1069  max mem: 31830
Epoch: [187]  [230/312]  eta: 0:00:47  lr: 0.001388  min_lr: 0.001388  loss: 3.3389 (3.4348)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0967  max mem: 31830
Epoch: [187]  [240/312]  eta: 0:00:41  lr: 0.001388  min_lr: 0.001388  loss: 3.5349 (3.4349)  weight_decay: 0.0500 (0.0500)  time: 0.5549  data: 0.1156  max mem: 31830
Epoch: [187]  [250/312]  eta: 0:00:35  lr: 0.001387  min_lr: 0.001387  loss: 3.5349 (3.4280)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0781  max mem: 31830
Epoch: [187]  [260/312]  eta: 0:00:29  lr: 0.001386  min_lr: 0.001386  loss: 3.1638 (3.4221)  weight_decay: 0.0500 (0.0500)  time: 0.5762  data: 0.1625  max mem: 31830
Epoch: [187]  [270/312]  eta: 0:00:23  lr: 0.001385  min_lr: 0.001385  loss: 3.4320 (3.4294)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.1046  max mem: 31830
Epoch: [187]  [280/312]  eta: 0:00:18  lr: 0.001385  min_lr: 0.001385  loss: 3.4058 (3.4157)  weight_decay: 0.0500 (0.0500)  time: 0.5541  data: 0.0989  max mem: 31830
Epoch: [187]  [290/312]  eta: 0:00:12  lr: 0.001384  min_lr: 0.001384  loss: 3.1795 (3.4168)  weight_decay: 0.0500 (0.0500)  time: 0.6164  data: 0.1458  max mem: 31830
Epoch: [187]  [300/312]  eta: 0:00:06  lr: 0.001383  min_lr: 0.001383  loss: 3.4635 (3.4172)  weight_decay: 0.0500 (0.0500)  time: 0.4512  data: 0.0479  max mem: 31830
Epoch: [187]  [310/312]  eta: 0:00:01  lr: 0.001383  min_lr: 0.001383  loss: 3.4635 (3.4158)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [187]  [311/312]  eta: 0:00:00  lr: 0.001383  min_lr: 0.001383  loss: 3.4635 (3.4176)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [187] Total time: 0:02:54 (0.5607 s / it)
Averaged stats: lr: 0.001383  min_lr: 0.001383  loss: 3.4635 (3.4692)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0027 (1.0027)  acc1: 77.6042 (77.6042)  acc5: 93.8802 (93.8802)  time: 8.8080  data: 8.6253  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4125 (1.2745)  acc1: 70.3125 (71.7760)  acc5: 89.8438 (90.6880)  time: 1.1064  data: 0.9585  max mem: 31830
Test: Total time: 0:00:10 (1.1327 s / it)
* Acc@1 72.060 Acc@5 91.024 loss 1.270
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.53%
Epoch: [188]  [  0/312]  eta: 0:58:17  lr: 0.001383  min_lr: 0.001383  loss: 3.5481 (3.5481)  weight_decay: 0.0500 (0.0500)  time: 11.2107  data: 10.7678  max mem: 31830
Epoch: [188]  [ 10/312]  eta: 0:07:53  lr: 0.001382  min_lr: 0.001382  loss: 3.5481 (3.4773)  weight_decay: 0.0500 (0.0500)  time: 1.5665  data: 1.0050  max mem: 31830
Epoch: [188]  [ 20/312]  eta: 0:05:18  lr: 0.001381  min_lr: 0.001381  loss: 3.5529 (3.5911)  weight_decay: 0.0500 (0.0500)  time: 0.5864  data: 0.0890  max mem: 31830
Epoch: [188]  [ 30/312]  eta: 0:04:04  lr: 0.001381  min_lr: 0.001381  loss: 3.6839 (3.5608)  weight_decay: 0.0500 (0.0500)  time: 0.4823  data: 0.0755  max mem: 31830
Epoch: [188]  [ 40/312]  eta: 0:03:28  lr: 0.001380  min_lr: 0.001380  loss: 3.6701 (3.5363)  weight_decay: 0.0500 (0.0500)  time: 0.4251  data: 0.0197  max mem: 31830
Epoch: [188]  [ 50/312]  eta: 0:03:13  lr: 0.001379  min_lr: 0.001379  loss: 3.6311 (3.5357)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.1105  max mem: 31830
Epoch: [188]  [ 60/312]  eta: 0:02:51  lr: 0.001379  min_lr: 0.001379  loss: 3.5643 (3.5253)  weight_decay: 0.0500 (0.0500)  time: 0.5031  data: 0.0921  max mem: 31830
Epoch: [188]  [ 70/312]  eta: 0:02:42  lr: 0.001378  min_lr: 0.001378  loss: 3.5509 (3.4971)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0489  max mem: 31830
Epoch: [188]  [ 80/312]  eta: 0:02:32  lr: 0.001377  min_lr: 0.001377  loss: 3.4786 (3.4799)  weight_decay: 0.0500 (0.0500)  time: 0.5936  data: 0.1323  max mem: 31830
Epoch: [188]  [ 90/312]  eta: 0:02:20  lr: 0.001376  min_lr: 0.001376  loss: 3.4786 (3.4852)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0979  max mem: 31830
Epoch: [188]  [100/312]  eta: 0:02:13  lr: 0.001376  min_lr: 0.001376  loss: 3.7091 (3.5040)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.1041  max mem: 31830
Epoch: [188]  [110/312]  eta: 0:02:03  lr: 0.001375  min_lr: 0.001375  loss: 3.7189 (3.5031)  weight_decay: 0.0500 (0.0500)  time: 0.5016  data: 0.0904  max mem: 31830
Epoch: [188]  [120/312]  eta: 0:01:57  lr: 0.001374  min_lr: 0.001374  loss: 3.5156 (3.5065)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.1043  max mem: 31830
Epoch: [188]  [130/312]  eta: 0:01:52  lr: 0.001374  min_lr: 0.001374  loss: 3.5451 (3.5154)  weight_decay: 0.0500 (0.0500)  time: 0.6548  data: 0.1928  max mem: 31830
Epoch: [188]  [140/312]  eta: 0:01:43  lr: 0.001373  min_lr: 0.001373  loss: 3.6660 (3.5228)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0894  max mem: 31830
Epoch: [188]  [150/312]  eta: 0:01:38  lr: 0.001372  min_lr: 0.001372  loss: 3.7604 (3.5240)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0685  max mem: 31830
Epoch: [188]  [160/312]  eta: 0:01:30  lr: 0.001372  min_lr: 0.001372  loss: 3.3787 (3.5050)  weight_decay: 0.0500 (0.0500)  time: 0.5691  data: 0.0685  max mem: 31830
Epoch: [188]  [170/312]  eta: 0:01:23  lr: 0.001371  min_lr: 0.001371  loss: 3.3279 (3.5014)  weight_decay: 0.0500 (0.0500)  time: 0.4705  data: 0.0411  max mem: 31830
Epoch: [188]  [180/312]  eta: 0:01:17  lr: 0.001370  min_lr: 0.001370  loss: 3.3279 (3.4874)  weight_decay: 0.0500 (0.0500)  time: 0.5358  data: 0.1413  max mem: 31830
Epoch: [188]  [190/312]  eta: 0:01:10  lr: 0.001370  min_lr: 0.001370  loss: 3.4764 (3.4881)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.1016  max mem: 31830
Epoch: [188]  [200/312]  eta: 0:01:05  lr: 0.001369  min_lr: 0.001369  loss: 3.4764 (3.4835)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.1233  max mem: 31830
Epoch: [188]  [210/312]  eta: 0:00:59  lr: 0.001368  min_lr: 0.001368  loss: 3.5172 (3.4897)  weight_decay: 0.0500 (0.0500)  time: 0.6042  data: 0.2144  max mem: 31830
Epoch: [188]  [220/312]  eta: 0:00:52  lr: 0.001368  min_lr: 0.001368  loss: 3.5484 (3.4934)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0925  max mem: 31830
Epoch: [188]  [230/312]  eta: 0:00:47  lr: 0.001367  min_lr: 0.001367  loss: 3.5544 (3.5008)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0949  max mem: 31830
Epoch: [188]  [240/312]  eta: 0:00:41  lr: 0.001366  min_lr: 0.001366  loss: 3.5232 (3.4942)  weight_decay: 0.0500 (0.0500)  time: 0.6307  data: 0.2341  max mem: 31830
Epoch: [188]  [250/312]  eta: 0:00:35  lr: 0.001366  min_lr: 0.001366  loss: 3.2733 (3.4872)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.1403  max mem: 31830
Epoch: [188]  [260/312]  eta: 0:00:29  lr: 0.001365  min_lr: 0.001365  loss: 3.2612 (3.4777)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0988  max mem: 31830
Epoch: [188]  [270/312]  eta: 0:00:23  lr: 0.001364  min_lr: 0.001364  loss: 3.3882 (3.4858)  weight_decay: 0.0500 (0.0500)  time: 0.4948  data: 0.0990  max mem: 31830
Epoch: [188]  [280/312]  eta: 0:00:18  lr: 0.001364  min_lr: 0.001364  loss: 3.6551 (3.4831)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.1045  max mem: 31830
Epoch: [188]  [290/312]  eta: 0:00:12  lr: 0.001363  min_lr: 0.001363  loss: 3.3276 (3.4744)  weight_decay: 0.0500 (0.0500)  time: 0.5857  data: 0.1950  max mem: 31830
Epoch: [188]  [300/312]  eta: 0:00:06  lr: 0.001362  min_lr: 0.001362  loss: 3.5030 (3.4835)  weight_decay: 0.0500 (0.0500)  time: 0.4762  data: 0.0915  max mem: 31830
Epoch: [188]  [310/312]  eta: 0:00:01  lr: 0.001361  min_lr: 0.001361  loss: 3.7570 (3.4901)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [188]  [311/312]  eta: 0:00:00  lr: 0.001361  min_lr: 0.001361  loss: 3.7570 (3.4907)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [188] Total time: 0:02:54 (0.5577 s / it)
Averaged stats: lr: 0.001361  min_lr: 0.001361  loss: 3.7570 (3.4963)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.1534 (1.1534)  acc1: 79.6875 (79.6875)  acc5: 94.5312 (94.5312)  time: 8.8132  data: 8.6519  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5517 (1.4969)  acc1: 72.2656 (71.1040)  acc5: 90.7552 (90.8800)  time: 1.1022  data: 0.9614  max mem: 31830
Test: Total time: 0:00:10 (1.1389 s / it)
* Acc@1 71.284 Acc@5 90.906 loss 1.489
Accuracy of the model on the 50000 test images: 71.3%
Max accuracy: 72.53%
Epoch: [189]  [  0/312]  eta: 1:00:15  lr: 0.001361  min_lr: 0.001361  loss: 3.0563 (3.0563)  weight_decay: 0.0500 (0.0500)  time: 11.5892  data: 8.3312  max mem: 31830
Epoch: [189]  [ 10/312]  eta: 0:08:32  lr: 0.001361  min_lr: 0.001361  loss: 3.0563 (3.3188)  weight_decay: 0.0500 (0.0500)  time: 1.6980  data: 1.0522  max mem: 31830
Epoch: [189]  [ 20/312]  eta: 0:05:21  lr: 0.001360  min_lr: 0.001360  loss: 3.5797 (3.4659)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.1625  max mem: 31830
Epoch: [189]  [ 30/312]  eta: 0:04:06  lr: 0.001359  min_lr: 0.001359  loss: 3.6578 (3.4107)  weight_decay: 0.0500 (0.0500)  time: 0.4231  data: 0.0008  max mem: 31830
Epoch: [189]  [ 40/312]  eta: 0:03:26  lr: 0.001359  min_lr: 0.001359  loss: 3.4188 (3.4138)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0018  max mem: 31830
Epoch: [189]  [ 50/312]  eta: 0:03:05  lr: 0.001358  min_lr: 0.001358  loss: 3.4020 (3.4125)  weight_decay: 0.0500 (0.0500)  time: 0.4531  data: 0.0019  max mem: 31830
Epoch: [189]  [ 60/312]  eta: 0:02:49  lr: 0.001357  min_lr: 0.001357  loss: 3.4020 (3.4126)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0016  max mem: 31830
Epoch: [189]  [ 70/312]  eta: 0:02:40  lr: 0.001357  min_lr: 0.001357  loss: 3.5598 (3.4245)  weight_decay: 0.0500 (0.0500)  time: 0.5410  data: 0.0017  max mem: 31830
Epoch: [189]  [ 80/312]  eta: 0:02:31  lr: 0.001356  min_lr: 0.001356  loss: 3.6336 (3.4412)  weight_decay: 0.0500 (0.0500)  time: 0.5953  data: 0.0011  max mem: 31830
Epoch: [189]  [ 90/312]  eta: 0:02:21  lr: 0.001355  min_lr: 0.001355  loss: 3.6025 (3.4090)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0010  max mem: 31830
Epoch: [189]  [100/312]  eta: 0:02:13  lr: 0.001355  min_lr: 0.001355  loss: 3.5800 (3.4209)  weight_decay: 0.0500 (0.0500)  time: 0.5403  data: 0.0010  max mem: 31830
Epoch: [189]  [110/312]  eta: 0:02:02  lr: 0.001354  min_lr: 0.001354  loss: 3.7516 (3.4484)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0011  max mem: 31830
Epoch: [189]  [120/312]  eta: 0:01:58  lr: 0.001353  min_lr: 0.001353  loss: 3.7543 (3.4483)  weight_decay: 0.0500 (0.0500)  time: 0.5392  data: 0.0065  max mem: 31830
Epoch: [189]  [130/312]  eta: 0:01:50  lr: 0.001352  min_lr: 0.001352  loss: 3.6207 (3.4370)  weight_decay: 0.0500 (0.0500)  time: 0.6022  data: 0.0064  max mem: 31830
Epoch: [189]  [140/312]  eta: 0:01:42  lr: 0.001352  min_lr: 0.001352  loss: 3.3264 (3.4380)  weight_decay: 0.0500 (0.0500)  time: 0.4860  data: 0.0008  max mem: 31830
Epoch: [189]  [150/312]  eta: 0:01:38  lr: 0.001351  min_lr: 0.001351  loss: 3.5994 (3.4515)  weight_decay: 0.0500 (0.0500)  time: 0.5900  data: 0.0010  max mem: 31830
Epoch: [189]  [160/312]  eta: 0:01:30  lr: 0.001350  min_lr: 0.001350  loss: 3.6862 (3.4616)  weight_decay: 0.0500 (0.0500)  time: 0.6095  data: 0.0013  max mem: 31830
Epoch: [189]  [170/312]  eta: 0:01:23  lr: 0.001350  min_lr: 0.001350  loss: 3.5369 (3.4536)  weight_decay: 0.0500 (0.0500)  time: 0.4794  data: 0.0149  max mem: 31830
Epoch: [189]  [180/312]  eta: 0:01:18  lr: 0.001349  min_lr: 0.001349  loss: 3.2927 (3.4426)  weight_decay: 0.0500 (0.0500)  time: 0.5836  data: 0.0148  max mem: 31830
Epoch: [189]  [190/312]  eta: 0:01:11  lr: 0.001348  min_lr: 0.001348  loss: 3.5538 (3.4555)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0016  max mem: 31830
Epoch: [189]  [200/312]  eta: 0:01:05  lr: 0.001348  min_lr: 0.001348  loss: 3.5945 (3.4549)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0327  max mem: 31830
Epoch: [189]  [210/312]  eta: 0:00:59  lr: 0.001347  min_lr: 0.001347  loss: 3.5018 (3.4579)  weight_decay: 0.0500 (0.0500)  time: 0.5826  data: 0.0387  max mem: 31830
Epoch: [189]  [220/312]  eta: 0:00:53  lr: 0.001346  min_lr: 0.001346  loss: 3.2871 (3.4455)  weight_decay: 0.0500 (0.0500)  time: 0.5188  data: 0.0077  max mem: 31830
Epoch: [189]  [230/312]  eta: 0:00:47  lr: 0.001346  min_lr: 0.001346  loss: 3.4598 (3.4516)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0165  max mem: 31830
Epoch: [189]  [240/312]  eta: 0:00:41  lr: 0.001345  min_lr: 0.001345  loss: 3.7690 (3.4607)  weight_decay: 0.0500 (0.0500)  time: 0.5739  data: 0.0173  max mem: 31830
Epoch: [189]  [250/312]  eta: 0:00:35  lr: 0.001344  min_lr: 0.001344  loss: 3.7565 (3.4693)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0105  max mem: 31830
Epoch: [189]  [260/312]  eta: 0:00:30  lr: 0.001344  min_lr: 0.001344  loss: 3.6830 (3.4712)  weight_decay: 0.0500 (0.0500)  time: 0.5685  data: 0.0243  max mem: 31830
Epoch: [189]  [270/312]  eta: 0:00:24  lr: 0.001343  min_lr: 0.001343  loss: 3.3264 (3.4737)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0312  max mem: 31830
Epoch: [189]  [280/312]  eta: 0:00:18  lr: 0.001342  min_lr: 0.001342  loss: 3.3982 (3.4692)  weight_decay: 0.0500 (0.0500)  time: 0.5068  data: 0.0372  max mem: 31830
Epoch: [189]  [290/312]  eta: 0:00:12  lr: 0.001342  min_lr: 0.001342  loss: 3.3294 (3.4632)  weight_decay: 0.0500 (0.0500)  time: 0.5699  data: 0.0268  max mem: 31830
Epoch: [189]  [300/312]  eta: 0:00:06  lr: 0.001341  min_lr: 0.001341  loss: 3.3294 (3.4663)  weight_decay: 0.0500 (0.0500)  time: 0.4717  data: 0.0059  max mem: 31830
Epoch: [189]  [310/312]  eta: 0:00:01  lr: 0.001340  min_lr: 0.001340  loss: 3.3241 (3.4577)  weight_decay: 0.0500 (0.0500)  time: 0.3854  data: 0.0001  max mem: 31830
Epoch: [189]  [311/312]  eta: 0:00:00  lr: 0.001340  min_lr: 0.001340  loss: 3.3241 (3.4582)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [189] Total time: 0:02:55 (0.5640 s / it)
Averaged stats: lr: 0.001340  min_lr: 0.001340  loss: 3.3241 (3.4772)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.2886 (1.2886)  acc1: 80.4688 (80.4688)  acc5: 94.9219 (94.9219)  time: 8.7182  data: 8.5508  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5793 (1.4770)  acc1: 71.2240 (73.0880)  acc5: 92.0573 (91.4240)  time: 1.0853  data: 0.9502  max mem: 31830
Test: Total time: 0:00:09 (1.1026 s / it)
* Acc@1 72.740 Acc@5 91.518 loss 1.478
Accuracy of the model on the 50000 test images: 72.7%
Max accuracy: 72.74%
Epoch: [190]  [  0/312]  eta: 1:04:01  lr: 0.001340  min_lr: 0.001340  loss: 3.7385 (3.7385)  weight_decay: 0.0500 (0.0500)  time: 12.3124  data: 8.6671  max mem: 31830
Epoch: [190]  [ 10/312]  eta: 0:08:40  lr: 0.001339  min_lr: 0.001339  loss: 3.7029 (3.3487)  weight_decay: 0.0500 (0.0500)  time: 1.7249  data: 1.0437  max mem: 31830
Epoch: [190]  [ 20/312]  eta: 0:05:25  lr: 0.001339  min_lr: 0.001339  loss: 3.2632 (3.3137)  weight_decay: 0.0500 (0.0500)  time: 0.5538  data: 0.1550  max mem: 31830
Epoch: [190]  [ 30/312]  eta: 0:04:09  lr: 0.001338  min_lr: 0.001338  loss: 3.5374 (3.4270)  weight_decay: 0.0500 (0.0500)  time: 0.4205  data: 0.0147  max mem: 31830
Epoch: [190]  [ 40/312]  eta: 0:03:28  lr: 0.001337  min_lr: 0.001337  loss: 3.6750 (3.4642)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [190]  [ 50/312]  eta: 0:03:01  lr: 0.001337  min_lr: 0.001337  loss: 3.6086 (3.4643)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0010  max mem: 31830
Epoch: [190]  [ 60/312]  eta: 0:02:42  lr: 0.001336  min_lr: 0.001336  loss: 3.4598 (3.4656)  weight_decay: 0.0500 (0.0500)  time: 0.4003  data: 0.0013  max mem: 31830
Epoch: [190]  [ 70/312]  eta: 0:02:33  lr: 0.001335  min_lr: 0.001335  loss: 3.6810 (3.5015)  weight_decay: 0.0500 (0.0500)  time: 0.4842  data: 0.0587  max mem: 31830
Epoch: [190]  [ 80/312]  eta: 0:02:23  lr: 0.001335  min_lr: 0.001335  loss: 3.7611 (3.5126)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0583  max mem: 31830
Epoch: [190]  [ 90/312]  eta: 0:02:15  lr: 0.001334  min_lr: 0.001334  loss: 3.7423 (3.5115)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0690  max mem: 31830
Epoch: [190]  [100/312]  eta: 0:02:08  lr: 0.001333  min_lr: 0.001333  loss: 3.7260 (3.5245)  weight_decay: 0.0500 (0.0500)  time: 0.5522  data: 0.1145  max mem: 31830
Epoch: [190]  [110/312]  eta: 0:01:58  lr: 0.001333  min_lr: 0.001333  loss: 3.6532 (3.5261)  weight_decay: 0.0500 (0.0500)  time: 0.4855  data: 0.0463  max mem: 31830
Epoch: [190]  [120/312]  eta: 0:01:53  lr: 0.001332  min_lr: 0.001332  loss: 3.6033 (3.5219)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0668  max mem: 31830
Epoch: [190]  [130/312]  eta: 0:01:48  lr: 0.001331  min_lr: 0.001331  loss: 3.6047 (3.5114)  weight_decay: 0.0500 (0.0500)  time: 0.6253  data: 0.1226  max mem: 31830
Epoch: [190]  [140/312]  eta: 0:01:39  lr: 0.001331  min_lr: 0.001331  loss: 3.6322 (3.5188)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0566  max mem: 31830
Epoch: [190]  [150/312]  eta: 0:01:34  lr: 0.001330  min_lr: 0.001330  loss: 3.6034 (3.5185)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0695  max mem: 31830
Epoch: [190]  [160/312]  eta: 0:01:27  lr: 0.001329  min_lr: 0.001329  loss: 3.5169 (3.5151)  weight_decay: 0.0500 (0.0500)  time: 0.5637  data: 0.0694  max mem: 31830
Epoch: [190]  [170/312]  eta: 0:01:22  lr: 0.001329  min_lr: 0.001329  loss: 3.4440 (3.5192)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.0430  max mem: 31830
Epoch: [190]  [180/312]  eta: 0:01:16  lr: 0.001328  min_lr: 0.001328  loss: 3.4309 (3.4970)  weight_decay: 0.0500 (0.0500)  time: 0.5887  data: 0.0886  max mem: 31830
Epoch: [190]  [190/312]  eta: 0:01:09  lr: 0.001327  min_lr: 0.001327  loss: 3.3495 (3.4868)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.0471  max mem: 31830
Epoch: [190]  [200/312]  eta: 0:01:04  lr: 0.001327  min_lr: 0.001327  loss: 3.5706 (3.4825)  weight_decay: 0.0500 (0.0500)  time: 0.5282  data: 0.0446  max mem: 31830
Epoch: [190]  [210/312]  eta: 0:00:58  lr: 0.001326  min_lr: 0.001326  loss: 3.5906 (3.4877)  weight_decay: 0.0500 (0.0500)  time: 0.6525  data: 0.0633  max mem: 31830
Epoch: [190]  [220/312]  eta: 0:00:52  lr: 0.001325  min_lr: 0.001325  loss: 3.6121 (3.4915)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0202  max mem: 31830
Epoch: [190]  [230/312]  eta: 0:00:46  lr: 0.001325  min_lr: 0.001325  loss: 3.6121 (3.4902)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0314  max mem: 31830
Epoch: [190]  [240/312]  eta: 0:00:40  lr: 0.001324  min_lr: 0.001324  loss: 3.6701 (3.5004)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0317  max mem: 31830
Epoch: [190]  [250/312]  eta: 0:00:35  lr: 0.001323  min_lr: 0.001323  loss: 3.8190 (3.5093)  weight_decay: 0.0500 (0.0500)  time: 0.5057  data: 0.0287  max mem: 31830
Epoch: [190]  [260/312]  eta: 0:00:29  lr: 0.001322  min_lr: 0.001322  loss: 3.4785 (3.4998)  weight_decay: 0.0500 (0.0500)  time: 0.5941  data: 0.0500  max mem: 31830
Epoch: [190]  [270/312]  eta: 0:00:23  lr: 0.001322  min_lr: 0.001322  loss: 3.3265 (3.4947)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0224  max mem: 31830
Epoch: [190]  [280/312]  eta: 0:00:18  lr: 0.001321  min_lr: 0.001321  loss: 3.6539 (3.5032)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0308  max mem: 31830
Epoch: [190]  [290/312]  eta: 0:00:12  lr: 0.001320  min_lr: 0.001320  loss: 3.7096 (3.4997)  weight_decay: 0.0500 (0.0500)  time: 0.6088  data: 0.0365  max mem: 31830
Epoch: [190]  [300/312]  eta: 0:00:06  lr: 0.001320  min_lr: 0.001320  loss: 3.5732 (3.4997)  weight_decay: 0.0500 (0.0500)  time: 0.4683  data: 0.0064  max mem: 31830
Epoch: [190]  [310/312]  eta: 0:00:01  lr: 0.001319  min_lr: 0.001319  loss: 3.5190 (3.4994)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [190]  [311/312]  eta: 0:00:00  lr: 0.001319  min_lr: 0.001319  loss: 3.5190 (3.5003)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [190] Total time: 0:02:53 (0.5572 s / it)
Averaged stats: lr: 0.001319  min_lr: 0.001319  loss: 3.5190 (3.4549)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9908 (0.9908)  acc1: 80.5990 (80.5990)  acc5: 94.5312 (94.5312)  time: 8.8399  data: 8.6724  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3324 (1.2851)  acc1: 71.6146 (72.7360)  acc5: 91.6667 (91.5040)  time: 1.0994  data: 0.9637  max mem: 31830
Test: Total time: 0:00:10 (1.1277 s / it)
* Acc@1 72.836 Acc@5 91.536 loss 1.273
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 72.84%
Epoch: [191]  [  0/312]  eta: 1:04:00  lr: 0.001319  min_lr: 0.001319  loss: 3.3163 (3.3163)  weight_decay: 0.0500 (0.0500)  time: 12.3085  data: 11.0429  max mem: 31830
Epoch: [191]  [ 10/312]  eta: 0:08:21  lr: 0.001318  min_lr: 0.001318  loss: 3.7009 (3.5920)  weight_decay: 0.0500 (0.0500)  time: 1.6597  data: 1.0050  max mem: 31830
Epoch: [191]  [ 20/312]  eta: 0:05:26  lr: 0.001318  min_lr: 0.001318  loss: 3.6300 (3.4044)  weight_decay: 0.0500 (0.0500)  time: 0.5590  data: 0.0669  max mem: 31830
Epoch: [191]  [ 30/312]  eta: 0:04:10  lr: 0.001317  min_lr: 0.001317  loss: 3.6536 (3.4811)  weight_decay: 0.0500 (0.0500)  time: 0.4615  data: 0.0669  max mem: 31830
Epoch: [191]  [ 40/312]  eta: 0:03:28  lr: 0.001316  min_lr: 0.001316  loss: 3.7681 (3.5492)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0024  max mem: 31830
Epoch: [191]  [ 50/312]  eta: 0:03:07  lr: 0.001316  min_lr: 0.001316  loss: 3.4553 (3.4871)  weight_decay: 0.0500 (0.0500)  time: 0.4500  data: 0.0177  max mem: 31830
Epoch: [191]  [ 60/312]  eta: 0:02:46  lr: 0.001315  min_lr: 0.001315  loss: 3.3065 (3.4528)  weight_decay: 0.0500 (0.0500)  time: 0.4466  data: 0.0163  max mem: 31830
Epoch: [191]  [ 70/312]  eta: 0:02:36  lr: 0.001314  min_lr: 0.001314  loss: 3.1909 (3.4135)  weight_decay: 0.0500 (0.0500)  time: 0.4669  data: 0.0717  max mem: 31830
Epoch: [191]  [ 80/312]  eta: 0:02:28  lr: 0.001314  min_lr: 0.001314  loss: 3.1982 (3.4144)  weight_decay: 0.0500 (0.0500)  time: 0.5736  data: 0.1735  max mem: 31830
Epoch: [191]  [ 90/312]  eta: 0:02:17  lr: 0.001313  min_lr: 0.001313  loss: 3.5350 (3.4232)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.1027  max mem: 31830
Epoch: [191]  [100/312]  eta: 0:02:10  lr: 0.001312  min_lr: 0.001312  loss: 3.1655 (3.3865)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0993  max mem: 31830
Epoch: [191]  [110/312]  eta: 0:02:00  lr: 0.001312  min_lr: 0.001312  loss: 3.1382 (3.3821)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.0992  max mem: 31830
Epoch: [191]  [120/312]  eta: 0:01:56  lr: 0.001311  min_lr: 0.001311  loss: 3.4095 (3.3809)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.0973  max mem: 31830
Epoch: [191]  [130/312]  eta: 0:01:49  lr: 0.001310  min_lr: 0.001310  loss: 3.4725 (3.3849)  weight_decay: 0.0500 (0.0500)  time: 0.6350  data: 0.1380  max mem: 31830
Epoch: [191]  [140/312]  eta: 0:01:41  lr: 0.001310  min_lr: 0.001310  loss: 3.4725 (3.3713)  weight_decay: 0.0500 (0.0500)  time: 0.4826  data: 0.0413  max mem: 31830
Epoch: [191]  [150/312]  eta: 0:01:35  lr: 0.001309  min_lr: 0.001309  loss: 3.3612 (3.3791)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0786  max mem: 31830
Epoch: [191]  [160/312]  eta: 0:01:29  lr: 0.001308  min_lr: 0.001308  loss: 3.6497 (3.3945)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1394  max mem: 31830
Epoch: [191]  [170/312]  eta: 0:01:22  lr: 0.001307  min_lr: 0.001307  loss: 3.5845 (3.3911)  weight_decay: 0.0500 (0.0500)  time: 0.5018  data: 0.0616  max mem: 31830
Epoch: [191]  [180/312]  eta: 0:01:16  lr: 0.001307  min_lr: 0.001307  loss: 3.3824 (3.3879)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0642  max mem: 31830
Epoch: [191]  [190/312]  eta: 0:01:09  lr: 0.001306  min_lr: 0.001306  loss: 3.3824 (3.3882)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0641  max mem: 31830
Epoch: [191]  [200/312]  eta: 0:01:04  lr: 0.001305  min_lr: 0.001305  loss: 3.3936 (3.3831)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.0724  max mem: 31830
Epoch: [191]  [210/312]  eta: 0:00:58  lr: 0.001305  min_lr: 0.001305  loss: 3.4994 (3.3951)  weight_decay: 0.0500 (0.0500)  time: 0.6299  data: 0.1469  max mem: 31830
Epoch: [191]  [220/312]  eta: 0:00:52  lr: 0.001304  min_lr: 0.001304  loss: 3.8263 (3.4102)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0756  max mem: 31830
Epoch: [191]  [230/312]  eta: 0:00:47  lr: 0.001303  min_lr: 0.001303  loss: 3.6801 (3.4118)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0412  max mem: 31830
Epoch: [191]  [240/312]  eta: 0:00:41  lr: 0.001303  min_lr: 0.001303  loss: 3.6360 (3.4159)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0708  max mem: 31830
Epoch: [191]  [250/312]  eta: 0:00:35  lr: 0.001302  min_lr: 0.001302  loss: 3.6045 (3.4148)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0314  max mem: 31830
Epoch: [191]  [260/312]  eta: 0:00:29  lr: 0.001301  min_lr: 0.001301  loss: 3.3527 (3.4067)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0207  max mem: 31830
Epoch: [191]  [270/312]  eta: 0:00:23  lr: 0.001301  min_lr: 0.001301  loss: 3.7049 (3.4171)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0199  max mem: 31830
Epoch: [191]  [280/312]  eta: 0:00:18  lr: 0.001300  min_lr: 0.001300  loss: 3.7222 (3.4254)  weight_decay: 0.0500 (0.0500)  time: 0.5155  data: 0.0252  max mem: 31830
Epoch: [191]  [290/312]  eta: 0:00:12  lr: 0.001299  min_lr: 0.001299  loss: 3.5912 (3.4216)  weight_decay: 0.0500 (0.0500)  time: 0.5983  data: 0.0387  max mem: 31830
Epoch: [191]  [300/312]  eta: 0:00:06  lr: 0.001299  min_lr: 0.001299  loss: 3.3570 (3.4217)  weight_decay: 0.0500 (0.0500)  time: 0.4735  data: 0.0140  max mem: 31830
Epoch: [191]  [310/312]  eta: 0:00:01  lr: 0.001298  min_lr: 0.001298  loss: 3.5258 (3.4276)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0002  max mem: 31830
Epoch: [191]  [311/312]  eta: 0:00:00  lr: 0.001298  min_lr: 0.001298  loss: 3.5864 (3.4298)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [191] Total time: 0:02:54 (0.5586 s / it)
Averaged stats: lr: 0.001298  min_lr: 0.001298  loss: 3.5864 (3.4683)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.1455 (1.1455)  acc1: 79.5573 (79.5573)  acc5: 95.1823 (95.1823)  time: 8.1212  data: 7.9541  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5691 (1.4133)  acc1: 71.7448 (71.7440)  acc5: 89.7135 (90.8640)  time: 1.0789  data: 0.9433  max mem: 31830
Test: Total time: 0:00:09 (1.0873 s / it)
* Acc@1 71.858 Acc@5 91.090 loss 1.423
Accuracy of the model on the 50000 test images: 71.9%
Max accuracy: 72.84%
Epoch: [192]  [  0/312]  eta: 1:02:37  lr: 0.001298  min_lr: 0.001298  loss: 2.6418 (2.6418)  weight_decay: 0.0500 (0.0500)  time: 12.0427  data: 10.7169  max mem: 31830
Epoch: [192]  [ 10/312]  eta: 0:08:41  lr: 0.001297  min_lr: 0.001297  loss: 3.2659 (3.1530)  weight_decay: 0.0500 (0.0500)  time: 1.7253  data: 1.0295  max mem: 31830
Epoch: [192]  [ 20/312]  eta: 0:05:30  lr: 0.001297  min_lr: 0.001297  loss: 3.4484 (3.2834)  weight_decay: 0.0500 (0.0500)  time: 0.5858  data: 0.0672  max mem: 31830
Epoch: [192]  [ 30/312]  eta: 0:04:12  lr: 0.001296  min_lr: 0.001296  loss: 3.4330 (3.2703)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0377  max mem: 31830
Epoch: [192]  [ 40/312]  eta: 0:03:30  lr: 0.001295  min_lr: 0.001295  loss: 3.4330 (3.3813)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0013  max mem: 31830
Epoch: [192]  [ 50/312]  eta: 0:03:06  lr: 0.001295  min_lr: 0.001295  loss: 3.7027 (3.3892)  weight_decay: 0.0500 (0.0500)  time: 0.4249  data: 0.0011  max mem: 31830
Epoch: [192]  [ 60/312]  eta: 0:02:46  lr: 0.001294  min_lr: 0.001294  loss: 3.5511 (3.4148)  weight_decay: 0.0500 (0.0500)  time: 0.4226  data: 0.0011  max mem: 31830
Epoch: [192]  [ 70/312]  eta: 0:02:37  lr: 0.001293  min_lr: 0.001293  loss: 3.5751 (3.4453)  weight_decay: 0.0500 (0.0500)  time: 0.4954  data: 0.0270  max mem: 31830
Epoch: [192]  [ 80/312]  eta: 0:02:28  lr: 0.001293  min_lr: 0.001293  loss: 3.6410 (3.4360)  weight_decay: 0.0500 (0.0500)  time: 0.5909  data: 0.0271  max mem: 31830
Epoch: [192]  [ 90/312]  eta: 0:02:17  lr: 0.001292  min_lr: 0.001292  loss: 3.6410 (3.4551)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0319  max mem: 31830
Epoch: [192]  [100/312]  eta: 0:02:11  lr: 0.001291  min_lr: 0.001291  loss: 3.6831 (3.4665)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0520  max mem: 31830
Epoch: [192]  [110/312]  eta: 0:02:01  lr: 0.001291  min_lr: 0.001291  loss: 3.6451 (3.4586)  weight_decay: 0.0500 (0.0500)  time: 0.5034  data: 0.0211  max mem: 31830
Epoch: [192]  [120/312]  eta: 0:01:56  lr: 0.001290  min_lr: 0.001290  loss: 3.4975 (3.4512)  weight_decay: 0.0500 (0.0500)  time: 0.5389  data: 0.0393  max mem: 31830
Epoch: [192]  [130/312]  eta: 0:01:51  lr: 0.001289  min_lr: 0.001289  loss: 3.5826 (3.4564)  weight_decay: 0.0500 (0.0500)  time: 0.6680  data: 0.0585  max mem: 31830
Epoch: [192]  [140/312]  eta: 0:01:42  lr: 0.001289  min_lr: 0.001289  loss: 3.6587 (3.4701)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0284  max mem: 31830
Epoch: [192]  [150/312]  eta: 0:01:36  lr: 0.001288  min_lr: 0.001288  loss: 3.6742 (3.4896)  weight_decay: 0.0500 (0.0500)  time: 0.5115  data: 0.0245  max mem: 31830
Epoch: [192]  [160/312]  eta: 0:01:30  lr: 0.001287  min_lr: 0.001287  loss: 3.6943 (3.4920)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0162  max mem: 31830
Epoch: [192]  [170/312]  eta: 0:01:23  lr: 0.001286  min_lr: 0.001286  loss: 3.3461 (3.4805)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0161  max mem: 31830
Epoch: [192]  [180/312]  eta: 0:01:17  lr: 0.001286  min_lr: 0.001286  loss: 3.4025 (3.4853)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0378  max mem: 31830
Epoch: [192]  [190/312]  eta: 0:01:10  lr: 0.001285  min_lr: 0.001285  loss: 3.6938 (3.4893)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0231  max mem: 31830
Epoch: [192]  [200/312]  eta: 0:01:04  lr: 0.001284  min_lr: 0.001284  loss: 3.5764 (3.4850)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0221  max mem: 31830
Epoch: [192]  [210/312]  eta: 0:00:59  lr: 0.001284  min_lr: 0.001284  loss: 3.5648 (3.4894)  weight_decay: 0.0500 (0.0500)  time: 0.5901  data: 0.0217  max mem: 31830
Epoch: [192]  [220/312]  eta: 0:00:52  lr: 0.001283  min_lr: 0.001283  loss: 3.6469 (3.4940)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0010  max mem: 31830
Epoch: [192]  [230/312]  eta: 0:00:47  lr: 0.001282  min_lr: 0.001282  loss: 3.6362 (3.4937)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0342  max mem: 31830
Epoch: [192]  [240/312]  eta: 0:00:41  lr: 0.001282  min_lr: 0.001282  loss: 3.5019 (3.4948)  weight_decay: 0.0500 (0.0500)  time: 0.5816  data: 0.0349  max mem: 31830
Epoch: [192]  [250/312]  eta: 0:00:35  lr: 0.001281  min_lr: 0.001281  loss: 3.4668 (3.4990)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0230  max mem: 31830
Epoch: [192]  [260/312]  eta: 0:00:29  lr: 0.001280  min_lr: 0.001280  loss: 3.4909 (3.4974)  weight_decay: 0.0500 (0.0500)  time: 0.5647  data: 0.0393  max mem: 31830
Epoch: [192]  [270/312]  eta: 0:00:23  lr: 0.001280  min_lr: 0.001280  loss: 3.4909 (3.4909)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0178  max mem: 31830
Epoch: [192]  [280/312]  eta: 0:00:18  lr: 0.001279  min_lr: 0.001279  loss: 3.6267 (3.4881)  weight_decay: 0.0500 (0.0500)  time: 0.5435  data: 0.0227  max mem: 31830
Epoch: [192]  [290/312]  eta: 0:00:12  lr: 0.001278  min_lr: 0.001278  loss: 3.5432 (3.4848)  weight_decay: 0.0500 (0.0500)  time: 0.5790  data: 0.0267  max mem: 31830
Epoch: [192]  [300/312]  eta: 0:00:06  lr: 0.001278  min_lr: 0.001278  loss: 3.4164 (3.4852)  weight_decay: 0.0500 (0.0500)  time: 0.4862  data: 0.0167  max mem: 31830
Epoch: [192]  [310/312]  eta: 0:00:01  lr: 0.001277  min_lr: 0.001277  loss: 3.6478 (3.4956)  weight_decay: 0.0500 (0.0500)  time: 0.4259  data: 0.0122  max mem: 31830
Epoch: [192]  [311/312]  eta: 0:00:00  lr: 0.001277  min_lr: 0.001277  loss: 3.5916 (3.4952)  weight_decay: 0.0500 (0.0500)  time: 0.4143  data: 0.0001  max mem: 31830
Epoch: [192] Total time: 0:02:55 (0.5638 s / it)
Averaged stats: lr: 0.001277  min_lr: 0.001277  loss: 3.5916 (3.4563)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.3924 (1.3924)  acc1: 78.1250 (78.1250)  acc5: 94.0104 (94.0104)  time: 8.9490  data: 8.7817  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6684 (1.6056)  acc1: 70.1823 (71.5360)  acc5: 90.6250 (90.8480)  time: 1.1112  data: 0.9758  max mem: 31830
Test: Total time: 0:00:10 (1.1411 s / it)
* Acc@1 71.456 Acc@5 90.896 loss 1.613
Accuracy of the model on the 50000 test images: 71.5%
Max accuracy: 72.84%
Epoch: [193]  [  0/312]  eta: 1:01:42  lr: 0.001277  min_lr: 0.001277  loss: 3.0670 (3.0670)  weight_decay: 0.0500 (0.0500)  time: 11.8656  data: 11.4725  max mem: 31830
Epoch: [193]  [ 10/312]  eta: 0:07:44  lr: 0.001276  min_lr: 0.001276  loss: 3.1130 (3.2131)  weight_decay: 0.0500 (0.0500)  time: 1.5395  data: 1.0437  max mem: 31830
Epoch: [193]  [ 20/312]  eta: 0:05:32  lr: 0.001276  min_lr: 0.001276  loss: 3.2598 (3.4067)  weight_decay: 0.0500 (0.0500)  time: 0.6010  data: 0.0763  max mem: 31830
Epoch: [193]  [ 30/312]  eta: 0:04:12  lr: 0.001275  min_lr: 0.001275  loss: 3.4438 (3.4000)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0764  max mem: 31830
Epoch: [193]  [ 40/312]  eta: 0:03:33  lr: 0.001274  min_lr: 0.001274  loss: 3.4438 (3.3981)  weight_decay: 0.0500 (0.0500)  time: 0.4113  data: 0.0204  max mem: 31830
Epoch: [193]  [ 50/312]  eta: 0:03:09  lr: 0.001274  min_lr: 0.001274  loss: 3.5397 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.4572  data: 0.0268  max mem: 31830
Epoch: [193]  [ 60/312]  eta: 0:02:48  lr: 0.001273  min_lr: 0.001273  loss: 3.5146 (3.3824)  weight_decay: 0.0500 (0.0500)  time: 0.4359  data: 0.0081  max mem: 31830
Epoch: [193]  [ 70/312]  eta: 0:02:39  lr: 0.001272  min_lr: 0.001272  loss: 3.3262 (3.3626)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0505  max mem: 31830
Epoch: [193]  [ 80/312]  eta: 0:02:30  lr: 0.001272  min_lr: 0.001272  loss: 3.5488 (3.4028)  weight_decay: 0.0500 (0.0500)  time: 0.5944  data: 0.1217  max mem: 31830
Epoch: [193]  [ 90/312]  eta: 0:02:18  lr: 0.001271  min_lr: 0.001271  loss: 3.6374 (3.4099)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0728  max mem: 31830
Epoch: [193]  [100/312]  eta: 0:02:12  lr: 0.001270  min_lr: 0.001270  loss: 3.5112 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0679  max mem: 31830
Epoch: [193]  [110/312]  eta: 0:02:01  lr: 0.001270  min_lr: 0.001270  loss: 3.3387 (3.3882)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0679  max mem: 31830
Epoch: [193]  [120/312]  eta: 0:01:56  lr: 0.001269  min_lr: 0.001269  loss: 3.2659 (3.3876)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0447  max mem: 31830
Epoch: [193]  [130/312]  eta: 0:01:49  lr: 0.001268  min_lr: 0.001268  loss: 3.5879 (3.3996)  weight_decay: 0.0500 (0.0500)  time: 0.6021  data: 0.1264  max mem: 31830
Epoch: [193]  [140/312]  eta: 0:01:41  lr: 0.001268  min_lr: 0.001268  loss: 3.6374 (3.4176)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0832  max mem: 31830
Epoch: [193]  [150/312]  eta: 0:01:35  lr: 0.001267  min_lr: 0.001267  loss: 3.6434 (3.4255)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0903  max mem: 31830
Epoch: [193]  [160/312]  eta: 0:01:29  lr: 0.001266  min_lr: 0.001266  loss: 3.3712 (3.4115)  weight_decay: 0.0500 (0.0500)  time: 0.5954  data: 0.1370  max mem: 31830
Epoch: [193]  [170/312]  eta: 0:01:22  lr: 0.001266  min_lr: 0.001266  loss: 3.4471 (3.4237)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0483  max mem: 31830
Epoch: [193]  [180/312]  eta: 0:01:16  lr: 0.001265  min_lr: 0.001265  loss: 3.7284 (3.4270)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0309  max mem: 31830
Epoch: [193]  [190/312]  eta: 0:01:09  lr: 0.001264  min_lr: 0.001264  loss: 3.5888 (3.4344)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0308  max mem: 31830
Epoch: [193]  [200/312]  eta: 0:01:04  lr: 0.001264  min_lr: 0.001264  loss: 3.4896 (3.4230)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0448  max mem: 31830
Epoch: [193]  [210/312]  eta: 0:00:58  lr: 0.001263  min_lr: 0.001263  loss: 3.0816 (3.4204)  weight_decay: 0.0500 (0.0500)  time: 0.6124  data: 0.0716  max mem: 31830
Epoch: [193]  [220/312]  eta: 0:00:52  lr: 0.001262  min_lr: 0.001262  loss: 3.7474 (3.4409)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.0276  max mem: 31830
Epoch: [193]  [230/312]  eta: 0:00:46  lr: 0.001262  min_lr: 0.001262  loss: 3.7361 (3.4434)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0283  max mem: 31830
Epoch: [193]  [240/312]  eta: 0:00:41  lr: 0.001261  min_lr: 0.001261  loss: 3.6248 (3.4408)  weight_decay: 0.0500 (0.0500)  time: 0.5908  data: 0.0406  max mem: 31830
Epoch: [193]  [250/312]  eta: 0:00:35  lr: 0.001260  min_lr: 0.001260  loss: 3.6966 (3.4442)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0281  max mem: 31830
Epoch: [193]  [260/312]  eta: 0:00:29  lr: 0.001260  min_lr: 0.001260  loss: 3.7004 (3.4414)  weight_decay: 0.0500 (0.0500)  time: 0.5407  data: 0.0373  max mem: 31830
Epoch: [193]  [270/312]  eta: 0:00:23  lr: 0.001259  min_lr: 0.001259  loss: 3.4931 (3.4392)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0223  max mem: 31830
Epoch: [193]  [280/312]  eta: 0:00:18  lr: 0.001258  min_lr: 0.001258  loss: 3.2107 (3.4334)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0232  max mem: 31830
Epoch: [193]  [290/312]  eta: 0:00:12  lr: 0.001258  min_lr: 0.001258  loss: 3.1979 (3.4267)  weight_decay: 0.0500 (0.0500)  time: 0.6062  data: 0.0386  max mem: 31830
Epoch: [193]  [300/312]  eta: 0:00:06  lr: 0.001257  min_lr: 0.001257  loss: 3.5288 (3.4365)  weight_decay: 0.0500 (0.0500)  time: 0.4626  data: 0.0159  max mem: 31830
Epoch: [193]  [310/312]  eta: 0:00:01  lr: 0.001256  min_lr: 0.001256  loss: 3.7445 (3.4381)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [193]  [311/312]  eta: 0:00:00  lr: 0.001256  min_lr: 0.001256  loss: 3.7445 (3.4398)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [193] Total time: 0:02:54 (0.5580 s / it)
Averaged stats: lr: 0.001256  min_lr: 0.001256  loss: 3.7445 (3.4697)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1976 (1.1976)  acc1: 79.5573 (79.5573)  acc5: 94.0104 (94.0104)  time: 7.9643  data: 7.7974  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.6306 (1.4990)  acc1: 71.8750 (72.6400)  acc5: 90.3646 (91.0400)  time: 1.0193  data: 0.8831  max mem: 31830
Test: Total time: 0:00:09 (1.0297 s / it)
* Acc@1 72.624 Acc@5 91.348 loss 1.495
Accuracy of the model on the 50000 test images: 72.6%
Max accuracy: 72.84%
Epoch: [194]  [  0/312]  eta: 1:06:03  lr: 0.001256  min_lr: 0.001256  loss: 3.7021 (3.7021)  weight_decay: 0.0500 (0.0500)  time: 12.7032  data: 12.3102  max mem: 31830
Epoch: [194]  [ 10/312]  eta: 0:08:13  lr: 0.001255  min_lr: 0.001255  loss: 3.7244 (3.6567)  weight_decay: 0.0500 (0.0500)  time: 1.6337  data: 1.1196  max mem: 31830
Epoch: [194]  [ 20/312]  eta: 0:05:30  lr: 0.001255  min_lr: 0.001255  loss: 3.7809 (3.7388)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0583  max mem: 31830
Epoch: [194]  [ 30/312]  eta: 0:04:12  lr: 0.001254  min_lr: 0.001254  loss: 3.7845 (3.6749)  weight_decay: 0.0500 (0.0500)  time: 0.4885  data: 0.0584  max mem: 31830
Epoch: [194]  [ 40/312]  eta: 0:03:30  lr: 0.001253  min_lr: 0.001253  loss: 3.4186 (3.5411)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0016  max mem: 31830
Epoch: [194]  [ 50/312]  eta: 0:03:08  lr: 0.001253  min_lr: 0.001253  loss: 3.2195 (3.5029)  weight_decay: 0.0500 (0.0500)  time: 0.4476  data: 0.0512  max mem: 31830
Epoch: [194]  [ 60/312]  eta: 0:02:47  lr: 0.001252  min_lr: 0.001252  loss: 3.5229 (3.5452)  weight_decay: 0.0500 (0.0500)  time: 0.4452  data: 0.0504  max mem: 31830
Epoch: [194]  [ 70/312]  eta: 0:02:41  lr: 0.001251  min_lr: 0.001251  loss: 3.6476 (3.5389)  weight_decay: 0.0500 (0.0500)  time: 0.5316  data: 0.1360  max mem: 31830
Epoch: [194]  [ 80/312]  eta: 0:02:31  lr: 0.001251  min_lr: 0.001251  loss: 3.5550 (3.5329)  weight_decay: 0.0500 (0.0500)  time: 0.6200  data: 0.2244  max mem: 31830
Epoch: [194]  [ 90/312]  eta: 0:02:19  lr: 0.001250  min_lr: 0.001250  loss: 3.6233 (3.5408)  weight_decay: 0.0500 (0.0500)  time: 0.4851  data: 0.0897  max mem: 31830
Epoch: [194]  [100/312]  eta: 0:02:13  lr: 0.001249  min_lr: 0.001249  loss: 3.4362 (3.5172)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.1213  max mem: 31830
Epoch: [194]  [110/312]  eta: 0:02:02  lr: 0.001249  min_lr: 0.001249  loss: 3.5356 (3.5282)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.1210  max mem: 31830
Epoch: [194]  [120/312]  eta: 0:01:56  lr: 0.001248  min_lr: 0.001248  loss: 3.7289 (3.5325)  weight_decay: 0.0500 (0.0500)  time: 0.4989  data: 0.1005  max mem: 31830
Epoch: [194]  [130/312]  eta: 0:01:50  lr: 0.001247  min_lr: 0.001247  loss: 3.5860 (3.5296)  weight_decay: 0.0500 (0.0500)  time: 0.6193  data: 0.2230  max mem: 31830
Epoch: [194]  [140/312]  eta: 0:01:42  lr: 0.001247  min_lr: 0.001247  loss: 3.5427 (3.5246)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.1234  max mem: 31830
Epoch: [194]  [150/312]  eta: 0:01:36  lr: 0.001246  min_lr: 0.001246  loss: 3.6220 (3.5255)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.1093  max mem: 31830
Epoch: [194]  [160/312]  eta: 0:01:31  lr: 0.001245  min_lr: 0.001245  loss: 3.6729 (3.5306)  weight_decay: 0.0500 (0.0500)  time: 0.6351  data: 0.2405  max mem: 31830
Epoch: [194]  [170/312]  eta: 0:01:23  lr: 0.001245  min_lr: 0.001245  loss: 3.6729 (3.5281)  weight_decay: 0.0500 (0.0500)  time: 0.5228  data: 0.1325  max mem: 31830
Epoch: [194]  [180/312]  eta: 0:01:17  lr: 0.001244  min_lr: 0.001244  loss: 3.5854 (3.5181)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.1203  max mem: 31830
Epoch: [194]  [190/312]  eta: 0:01:10  lr: 0.001243  min_lr: 0.001243  loss: 3.5535 (3.5197)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.1196  max mem: 31830
Epoch: [194]  [200/312]  eta: 0:01:05  lr: 0.001243  min_lr: 0.001243  loss: 3.6103 (3.5132)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.1322  max mem: 31830
Epoch: [194]  [210/312]  eta: 0:00:59  lr: 0.001242  min_lr: 0.001242  loss: 3.6178 (3.5218)  weight_decay: 0.0500 (0.0500)  time: 0.6668  data: 0.2710  max mem: 31830
Epoch: [194]  [220/312]  eta: 0:00:53  lr: 0.001241  min_lr: 0.001241  loss: 3.6947 (3.5255)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.1403  max mem: 31830
Epoch: [194]  [230/312]  eta: 0:00:47  lr: 0.001241  min_lr: 0.001241  loss: 3.7704 (3.5356)  weight_decay: 0.0500 (0.0500)  time: 0.5335  data: 0.1392  max mem: 31830
Epoch: [194]  [240/312]  eta: 0:00:42  lr: 0.001240  min_lr: 0.001240  loss: 3.5711 (3.5184)  weight_decay: 0.0500 (0.0500)  time: 0.6353  data: 0.2399  max mem: 31830
Epoch: [194]  [250/312]  eta: 0:00:35  lr: 0.001239  min_lr: 0.001239  loss: 3.0751 (3.5149)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.1025  max mem: 31830
Epoch: [194]  [260/312]  eta: 0:00:30  lr: 0.001239  min_lr: 0.001239  loss: 3.5651 (3.5118)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.1239  max mem: 31830
Epoch: [194]  [270/312]  eta: 0:00:24  lr: 0.001238  min_lr: 0.001238  loss: 3.6601 (3.5127)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.1241  max mem: 31830
Epoch: [194]  [280/312]  eta: 0:00:18  lr: 0.001237  min_lr: 0.001237  loss: 3.6917 (3.5140)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.1190  max mem: 31830
Epoch: [194]  [290/312]  eta: 0:00:12  lr: 0.001237  min_lr: 0.001237  loss: 3.5998 (3.5089)  weight_decay: 0.0500 (0.0500)  time: 0.5733  data: 0.1835  max mem: 31830
Epoch: [194]  [300/312]  eta: 0:00:06  lr: 0.001236  min_lr: 0.001236  loss: 3.6227 (3.5121)  weight_decay: 0.0500 (0.0500)  time: 0.4489  data: 0.0654  max mem: 31830
Epoch: [194]  [310/312]  eta: 0:00:01  lr: 0.001235  min_lr: 0.001235  loss: 3.6303 (3.5201)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [194]  [311/312]  eta: 0:00:00  lr: 0.001235  min_lr: 0.001235  loss: 3.6303 (3.5223)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [194] Total time: 0:02:55 (0.5633 s / it)
Averaged stats: lr: 0.001235  min_lr: 0.001235  loss: 3.6303 (3.4607)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.2706 (1.2706)  acc1: 79.9479 (79.9479)  acc5: 93.7500 (93.7500)  time: 8.4862  data: 8.3262  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5208 (1.4382)  acc1: 72.0052 (72.4800)  acc5: 90.3646 (91.1040)  time: 1.0779  data: 0.9386  max mem: 31830
Test: Total time: 0:00:09 (1.0999 s / it)
* Acc@1 72.532 Acc@5 91.402 loss 1.439
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.84%
Epoch: [195]  [  0/312]  eta: 1:01:35  lr: 0.001235  min_lr: 0.001235  loss: 2.3062 (2.3062)  weight_decay: 0.0500 (0.0500)  time: 11.8450  data: 8.9731  max mem: 31830
Epoch: [195]  [ 10/312]  eta: 0:08:34  lr: 0.001235  min_lr: 0.001235  loss: 3.5354 (3.3876)  weight_decay: 0.0500 (0.0500)  time: 1.7036  data: 1.0884  max mem: 31830
Epoch: [195]  [ 20/312]  eta: 0:05:21  lr: 0.001234  min_lr: 0.001234  loss: 3.2852 (3.2613)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.1502  max mem: 31830
Epoch: [195]  [ 30/312]  eta: 0:04:06  lr: 0.001233  min_lr: 0.001233  loss: 3.3821 (3.2830)  weight_decay: 0.0500 (0.0500)  time: 0.4199  data: 0.0006  max mem: 31830
Epoch: [195]  [ 40/312]  eta: 0:03:26  lr: 0.001233  min_lr: 0.001233  loss: 3.4311 (3.3017)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0008  max mem: 31830
Epoch: [195]  [ 50/312]  eta: 0:03:02  lr: 0.001232  min_lr: 0.001232  loss: 3.4295 (3.3336)  weight_decay: 0.0500 (0.0500)  time: 0.4226  data: 0.0211  max mem: 31830
Epoch: [195]  [ 60/312]  eta: 0:02:43  lr: 0.001231  min_lr: 0.001231  loss: 3.4695 (3.3330)  weight_decay: 0.0500 (0.0500)  time: 0.4221  data: 0.0211  max mem: 31830
Epoch: [195]  [ 70/312]  eta: 0:02:34  lr: 0.001231  min_lr: 0.001231  loss: 3.6158 (3.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0646  max mem: 31830
Epoch: [195]  [ 80/312]  eta: 0:02:24  lr: 0.001230  min_lr: 0.001230  loss: 3.6450 (3.3703)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0928  max mem: 31830
Epoch: [195]  [ 90/312]  eta: 0:02:15  lr: 0.001229  min_lr: 0.001229  loss: 3.6038 (3.3942)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0825  max mem: 31830
Epoch: [195]  [100/312]  eta: 0:02:10  lr: 0.001229  min_lr: 0.001229  loss: 3.3086 (3.3782)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.1549  max mem: 31830
Epoch: [195]  [110/312]  eta: 0:01:59  lr: 0.001228  min_lr: 0.001228  loss: 3.3443 (3.3865)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.1013  max mem: 31830
Epoch: [195]  [120/312]  eta: 0:01:55  lr: 0.001227  min_lr: 0.001227  loss: 3.3443 (3.3894)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.1049  max mem: 31830
Epoch: [195]  [130/312]  eta: 0:01:49  lr: 0.001227  min_lr: 0.001227  loss: 3.2455 (3.3965)  weight_decay: 0.0500 (0.0500)  time: 0.6416  data: 0.1632  max mem: 31830
Epoch: [195]  [140/312]  eta: 0:01:40  lr: 0.001226  min_lr: 0.001226  loss: 3.6593 (3.4135)  weight_decay: 0.0500 (0.0500)  time: 0.5089  data: 0.0591  max mem: 31830
Epoch: [195]  [150/312]  eta: 0:01:35  lr: 0.001225  min_lr: 0.001225  loss: 3.6347 (3.4266)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0615  max mem: 31830
Epoch: [195]  [160/312]  eta: 0:01:28  lr: 0.001225  min_lr: 0.001225  loss: 3.4555 (3.4249)  weight_decay: 0.0500 (0.0500)  time: 0.5681  data: 0.0614  max mem: 31830
Epoch: [195]  [170/312]  eta: 0:01:22  lr: 0.001224  min_lr: 0.001224  loss: 3.1714 (3.4145)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0631  max mem: 31830
Epoch: [195]  [180/312]  eta: 0:01:16  lr: 0.001223  min_lr: 0.001223  loss: 3.3973 (3.4185)  weight_decay: 0.0500 (0.0500)  time: 0.5465  data: 0.1260  max mem: 31830
Epoch: [195]  [190/312]  eta: 0:01:09  lr: 0.001223  min_lr: 0.001223  loss: 3.5166 (3.4174)  weight_decay: 0.0500 (0.0500)  time: 0.4876  data: 0.0637  max mem: 31830
Epoch: [195]  [200/312]  eta: 0:01:04  lr: 0.001222  min_lr: 0.001222  loss: 3.7661 (3.4399)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0929  max mem: 31830
Epoch: [195]  [210/312]  eta: 0:00:58  lr: 0.001221  min_lr: 0.001221  loss: 3.7476 (3.4302)  weight_decay: 0.0500 (0.0500)  time: 0.6492  data: 0.1713  max mem: 31830
Epoch: [195]  [220/312]  eta: 0:00:52  lr: 0.001221  min_lr: 0.001221  loss: 3.3938 (3.4361)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0794  max mem: 31830
Epoch: [195]  [230/312]  eta: 0:00:46  lr: 0.001220  min_lr: 0.001220  loss: 3.5099 (3.4299)  weight_decay: 0.0500 (0.0500)  time: 0.4931  data: 0.0793  max mem: 31830
Epoch: [195]  [240/312]  eta: 0:00:40  lr: 0.001219  min_lr: 0.001219  loss: 3.3445 (3.4254)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0949  max mem: 31830
Epoch: [195]  [250/312]  eta: 0:00:35  lr: 0.001219  min_lr: 0.001219  loss: 3.1994 (3.4183)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0837  max mem: 31830
Epoch: [195]  [260/312]  eta: 0:00:29  lr: 0.001218  min_lr: 0.001218  loss: 3.3221 (3.4161)  weight_decay: 0.0500 (0.0500)  time: 0.5987  data: 0.1355  max mem: 31830
Epoch: [195]  [270/312]  eta: 0:00:23  lr: 0.001217  min_lr: 0.001217  loss: 3.5210 (3.4195)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0683  max mem: 31830
Epoch: [195]  [280/312]  eta: 0:00:18  lr: 0.001217  min_lr: 0.001217  loss: 3.5803 (3.4295)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0830  max mem: 31830
Epoch: [195]  [290/312]  eta: 0:00:12  lr: 0.001216  min_lr: 0.001216  loss: 3.5803 (3.4295)  weight_decay: 0.0500 (0.0500)  time: 0.6475  data: 0.1681  max mem: 31830
Epoch: [195]  [300/312]  eta: 0:00:06  lr: 0.001215  min_lr: 0.001215  loss: 3.4824 (3.4251)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0856  max mem: 31830
Epoch: [195]  [310/312]  eta: 0:00:01  lr: 0.001215  min_lr: 0.001215  loss: 3.6036 (3.4251)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [195]  [311/312]  eta: 0:00:00  lr: 0.001215  min_lr: 0.001215  loss: 3.6563 (3.4261)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [195] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.001215  min_lr: 0.001215  loss: 3.6563 (3.4541)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.0895 (1.0895)  acc1: 81.3802 (81.3802)  acc5: 94.7917 (94.7917)  time: 7.9445  data: 7.7775  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4237 (1.3412)  acc1: 70.4427 (72.8800)  acc5: 91.5365 (91.7120)  time: 1.0319  data: 0.8965  max mem: 31830
Test: Total time: 0:00:09 (1.0443 s / it)
* Acc@1 72.924 Acc@5 91.812 loss 1.336
Accuracy of the model on the 50000 test images: 72.9%
Max accuracy: 72.92%
Epoch: [196]  [  0/312]  eta: 1:04:03  lr: 0.001215  min_lr: 0.001215  loss: 2.6844 (2.6844)  weight_decay: 0.0500 (0.0500)  time: 12.3175  data: 8.0866  max mem: 31830
Epoch: [196]  [ 10/312]  eta: 0:08:50  lr: 0.001214  min_lr: 0.001214  loss: 3.5615 (3.3976)  weight_decay: 0.0500 (0.0500)  time: 1.7568  data: 1.0217  max mem: 31830
Epoch: [196]  [ 20/312]  eta: 0:05:24  lr: 0.001213  min_lr: 0.001213  loss: 3.4333 (3.2049)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.1580  max mem: 31830
Epoch: [196]  [ 30/312]  eta: 0:04:08  lr: 0.001213  min_lr: 0.001213  loss: 3.4662 (3.3471)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0018  max mem: 31830
Epoch: [196]  [ 40/312]  eta: 0:03:27  lr: 0.001212  min_lr: 0.001212  loss: 3.6145 (3.3098)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0024  max mem: 31830
Epoch: [196]  [ 50/312]  eta: 0:03:01  lr: 0.001211  min_lr: 0.001211  loss: 3.1583 (3.2915)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0014  max mem: 31830
Epoch: [196]  [ 60/312]  eta: 0:02:42  lr: 0.001211  min_lr: 0.001211  loss: 3.3681 (3.3077)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0015  max mem: 31830
Epoch: [196]  [ 70/312]  eta: 0:02:31  lr: 0.001210  min_lr: 0.001210  loss: 3.5663 (3.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4517  data: 0.0218  max mem: 31830
Epoch: [196]  [ 80/312]  eta: 0:02:24  lr: 0.001209  min_lr: 0.001209  loss: 3.6507 (3.3952)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0214  max mem: 31830
Epoch: [196]  [ 90/312]  eta: 0:02:13  lr: 0.001209  min_lr: 0.001209  loss: 3.5316 (3.4033)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0144  max mem: 31830
Epoch: [196]  [100/312]  eta: 0:02:08  lr: 0.001208  min_lr: 0.001208  loss: 3.4607 (3.4059)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0344  max mem: 31830
Epoch: [196]  [110/312]  eta: 0:02:00  lr: 0.001207  min_lr: 0.001207  loss: 3.4214 (3.4220)  weight_decay: 0.0500 (0.0500)  time: 0.5703  data: 0.0209  max mem: 31830
Epoch: [196]  [120/312]  eta: 0:01:53  lr: 0.001207  min_lr: 0.001207  loss: 3.6880 (3.4333)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0009  max mem: 31830
Epoch: [196]  [130/312]  eta: 0:01:48  lr: 0.001206  min_lr: 0.001206  loss: 3.3959 (3.4275)  weight_decay: 0.0500 (0.0500)  time: 0.5822  data: 0.0325  max mem: 31830
Epoch: [196]  [140/312]  eta: 0:01:40  lr: 0.001205  min_lr: 0.001205  loss: 3.2024 (3.4173)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0335  max mem: 31830
Epoch: [196]  [150/312]  eta: 0:01:34  lr: 0.001205  min_lr: 0.001205  loss: 3.3953 (3.4218)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0113  max mem: 31830
Epoch: [196]  [160/312]  eta: 0:01:29  lr: 0.001204  min_lr: 0.001204  loss: 3.5575 (3.4317)  weight_decay: 0.0500 (0.0500)  time: 0.6165  data: 0.0309  max mem: 31830
Epoch: [196]  [170/312]  eta: 0:01:21  lr: 0.001203  min_lr: 0.001203  loss: 3.4410 (3.4228)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0216  max mem: 31830
Epoch: [196]  [180/312]  eta: 0:01:16  lr: 0.001203  min_lr: 0.001203  loss: 3.2137 (3.4188)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0073  max mem: 31830
Epoch: [196]  [190/312]  eta: 0:01:10  lr: 0.001202  min_lr: 0.001202  loss: 3.5041 (3.4216)  weight_decay: 0.0500 (0.0500)  time: 0.6097  data: 0.0491  max mem: 31830
Epoch: [196]  [200/312]  eta: 0:01:03  lr: 0.001201  min_lr: 0.001201  loss: 3.5764 (3.4235)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0427  max mem: 31830
Epoch: [196]  [210/312]  eta: 0:00:58  lr: 0.001201  min_lr: 0.001201  loss: 3.5335 (3.4165)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0325  max mem: 31830
Epoch: [196]  [220/312]  eta: 0:00:52  lr: 0.001200  min_lr: 0.001200  loss: 3.5134 (3.4190)  weight_decay: 0.0500 (0.0500)  time: 0.5827  data: 0.0325  max mem: 31830
Epoch: [196]  [230/312]  eta: 0:00:46  lr: 0.001199  min_lr: 0.001199  loss: 3.5656 (3.4263)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0598  max mem: 31830
Epoch: [196]  [240/312]  eta: 0:00:41  lr: 0.001199  min_lr: 0.001199  loss: 3.5872 (3.4229)  weight_decay: 0.0500 (0.0500)  time: 0.5847  data: 0.1240  max mem: 31830
Epoch: [196]  [250/312]  eta: 0:00:35  lr: 0.001198  min_lr: 0.001198  loss: 3.4505 (3.4155)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0656  max mem: 31830
Epoch: [196]  [260/312]  eta: 0:00:29  lr: 0.001197  min_lr: 0.001197  loss: 3.2808 (3.4144)  weight_decay: 0.0500 (0.0500)  time: 0.5638  data: 0.0812  max mem: 31830
Epoch: [196]  [270/312]  eta: 0:00:24  lr: 0.001197  min_lr: 0.001197  loss: 3.3345 (3.4098)  weight_decay: 0.0500 (0.0500)  time: 0.6571  data: 0.1279  max mem: 31830
Epoch: [196]  [280/312]  eta: 0:00:18  lr: 0.001196  min_lr: 0.001196  loss: 3.3619 (3.4134)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0492  max mem: 31830
Epoch: [196]  [290/312]  eta: 0:00:12  lr: 0.001196  min_lr: 0.001196  loss: 3.5806 (3.4169)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0352  max mem: 31830
Epoch: [196]  [300/312]  eta: 0:00:06  lr: 0.001195  min_lr: 0.001195  loss: 3.5806 (3.4168)  weight_decay: 0.0500 (0.0500)  time: 0.4839  data: 0.0338  max mem: 31830
Epoch: [196]  [310/312]  eta: 0:00:01  lr: 0.001194  min_lr: 0.001194  loss: 3.3522 (3.4126)  weight_decay: 0.0500 (0.0500)  time: 0.3853  data: 0.0001  max mem: 31830
Epoch: [196]  [311/312]  eta: 0:00:00  lr: 0.001194  min_lr: 0.001194  loss: 3.4770 (3.4138)  weight_decay: 0.0500 (0.0500)  time: 0.3850  data: 0.0001  max mem: 31830
Epoch: [196] Total time: 0:02:54 (0.5609 s / it)
Averaged stats: lr: 0.001194  min_lr: 0.001194  loss: 3.4770 (3.4272)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.0490 (1.0490)  acc1: 78.7760 (78.7760)  acc5: 93.4896 (93.4896)  time: 8.5466  data: 8.3848  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2992 (1.2607)  acc1: 72.9167 (72.6080)  acc5: 91.6667 (91.3440)  time: 1.0661  data: 0.9317  max mem: 31830
Test: Total time: 0:00:09 (1.0767 s / it)
* Acc@1 72.914 Acc@5 91.632 loss 1.258
Accuracy of the model on the 50000 test images: 72.9%
Max accuracy: 72.92%
Epoch: [197]  [  0/312]  eta: 1:04:04  lr: 0.001194  min_lr: 0.001194  loss: 3.2369 (3.2369)  weight_decay: 0.0500 (0.0500)  time: 12.3225  data: 11.9187  max mem: 31830
Epoch: [197]  [ 10/312]  eta: 0:08:22  lr: 0.001193  min_lr: 0.001193  loss: 3.3537 (3.3617)  weight_decay: 0.0500 (0.0500)  time: 1.6646  data: 1.0841  max mem: 31830
Epoch: [197]  [ 20/312]  eta: 0:05:20  lr: 0.001193  min_lr: 0.001193  loss: 3.6466 (3.4054)  weight_decay: 0.0500 (0.0500)  time: 0.5358  data: 0.0409  max mem: 31830
Epoch: [197]  [ 30/312]  eta: 0:04:06  lr: 0.001192  min_lr: 0.001192  loss: 3.3483 (3.3314)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0412  max mem: 31830
Epoch: [197]  [ 40/312]  eta: 0:03:25  lr: 0.001191  min_lr: 0.001191  loss: 3.0688 (3.2960)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [197]  [ 50/312]  eta: 0:03:05  lr: 0.001191  min_lr: 0.001191  loss: 3.4749 (3.3211)  weight_decay: 0.0500 (0.0500)  time: 0.4487  data: 0.0511  max mem: 31830
Epoch: [197]  [ 60/312]  eta: 0:02:44  lr: 0.001190  min_lr: 0.001190  loss: 3.5476 (3.3364)  weight_decay: 0.0500 (0.0500)  time: 0.4444  data: 0.0510  max mem: 31830
Epoch: [197]  [ 70/312]  eta: 0:02:37  lr: 0.001189  min_lr: 0.001189  loss: 3.5026 (3.3528)  weight_decay: 0.0500 (0.0500)  time: 0.5058  data: 0.1136  max mem: 31830
Epoch: [197]  [ 80/312]  eta: 0:02:29  lr: 0.001189  min_lr: 0.001189  loss: 3.5026 (3.3812)  weight_decay: 0.0500 (0.0500)  time: 0.6144  data: 0.2019  max mem: 31830
Epoch: [197]  [ 90/312]  eta: 0:02:16  lr: 0.001188  min_lr: 0.001188  loss: 3.3929 (3.3734)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0898  max mem: 31830
Epoch: [197]  [100/312]  eta: 0:02:09  lr: 0.001187  min_lr: 0.001187  loss: 3.5126 (3.3763)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0924  max mem: 31830
Epoch: [197]  [110/312]  eta: 0:01:59  lr: 0.001187  min_lr: 0.001187  loss: 3.5991 (3.3815)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0918  max mem: 31830
Epoch: [197]  [120/312]  eta: 0:01:54  lr: 0.001186  min_lr: 0.001186  loss: 3.5559 (3.3777)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.1072  max mem: 31830
Epoch: [197]  [130/312]  eta: 0:01:48  lr: 0.001186  min_lr: 0.001186  loss: 3.5468 (3.3788)  weight_decay: 0.0500 (0.0500)  time: 0.6019  data: 0.1988  max mem: 31830
Epoch: [197]  [140/312]  eta: 0:01:39  lr: 0.001185  min_lr: 0.001185  loss: 3.4585 (3.3738)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0930  max mem: 31830
Epoch: [197]  [150/312]  eta: 0:01:34  lr: 0.001184  min_lr: 0.001184  loss: 3.4089 (3.3796)  weight_decay: 0.0500 (0.0500)  time: 0.5207  data: 0.1287  max mem: 31830
Epoch: [197]  [160/312]  eta: 0:01:28  lr: 0.001184  min_lr: 0.001184  loss: 3.3812 (3.3869)  weight_decay: 0.0500 (0.0500)  time: 0.5979  data: 0.2062  max mem: 31830
Epoch: [197]  [170/312]  eta: 0:01:21  lr: 0.001183  min_lr: 0.001183  loss: 3.3369 (3.3850)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0846  max mem: 31830
Epoch: [197]  [180/312]  eta: 0:01:16  lr: 0.001182  min_lr: 0.001182  loss: 3.4515 (3.3843)  weight_decay: 0.0500 (0.0500)  time: 0.5223  data: 0.0904  max mem: 31830
Epoch: [197]  [190/312]  eta: 0:01:09  lr: 0.001182  min_lr: 0.001182  loss: 3.5446 (3.3940)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0846  max mem: 31830
Epoch: [197]  [200/312]  eta: 0:01:03  lr: 0.001181  min_lr: 0.001181  loss: 3.6505 (3.4053)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0978  max mem: 31830
Epoch: [197]  [210/312]  eta: 0:00:58  lr: 0.001180  min_lr: 0.001180  loss: 3.6004 (3.3993)  weight_decay: 0.0500 (0.0500)  time: 0.6554  data: 0.2158  max mem: 31830
Epoch: [197]  [220/312]  eta: 0:00:52  lr: 0.001180  min_lr: 0.001180  loss: 3.7338 (3.4107)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.1189  max mem: 31830
Epoch: [197]  [230/312]  eta: 0:00:46  lr: 0.001179  min_lr: 0.001179  loss: 3.7796 (3.4152)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.0994  max mem: 31830
Epoch: [197]  [240/312]  eta: 0:00:41  lr: 0.001178  min_lr: 0.001178  loss: 3.6666 (3.4195)  weight_decay: 0.0500 (0.0500)  time: 0.6156  data: 0.1956  max mem: 31830
Epoch: [197]  [250/312]  eta: 0:00:35  lr: 0.001178  min_lr: 0.001178  loss: 3.5879 (3.4215)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0980  max mem: 31830
Epoch: [197]  [260/312]  eta: 0:00:29  lr: 0.001177  min_lr: 0.001177  loss: 3.5403 (3.4173)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.1225  max mem: 31830
Epoch: [197]  [270/312]  eta: 0:00:23  lr: 0.001176  min_lr: 0.001176  loss: 3.5339 (3.4223)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.1218  max mem: 31830
Epoch: [197]  [280/312]  eta: 0:00:18  lr: 0.001176  min_lr: 0.001176  loss: 3.5512 (3.4277)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.1329  max mem: 31830
Epoch: [197]  [290/312]  eta: 0:00:12  lr: 0.001175  min_lr: 0.001175  loss: 3.5978 (3.4317)  weight_decay: 0.0500 (0.0500)  time: 0.6177  data: 0.2236  max mem: 31830
Epoch: [197]  [300/312]  eta: 0:00:06  lr: 0.001174  min_lr: 0.001174  loss: 3.5810 (3.4272)  weight_decay: 0.0500 (0.0500)  time: 0.4759  data: 0.0912  max mem: 31830
Epoch: [197]  [310/312]  eta: 0:00:01  lr: 0.001174  min_lr: 0.001174  loss: 3.2382 (3.4146)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0002  max mem: 31830
Epoch: [197]  [311/312]  eta: 0:00:00  lr: 0.001174  min_lr: 0.001174  loss: 3.2382 (3.4160)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0002  max mem: 31830
Epoch: [197] Total time: 0:02:53 (0.5561 s / it)
Averaged stats: lr: 0.001174  min_lr: 0.001174  loss: 3.2382 (3.4418)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.1301 (1.1301)  acc1: 76.9531 (76.9531)  acc5: 94.1406 (94.1406)  time: 8.8080  data: 8.6387  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3716 (1.3000)  acc1: 71.4844 (72.3680)  acc5: 91.1458 (91.6000)  time: 1.1038  data: 0.9599  max mem: 31830
Test: Total time: 0:00:10 (1.1337 s / it)
* Acc@1 72.568 Acc@5 91.598 loss 1.318
Accuracy of the model on the 50000 test images: 72.6%
Max accuracy: 72.92%
Epoch: [198]  [  0/312]  eta: 1:02:59  lr: 0.001174  min_lr: 0.001174  loss: 3.9177 (3.9177)  weight_decay: 0.0500 (0.0500)  time: 12.1148  data: 9.3205  max mem: 31830
Epoch: [198]  [ 10/312]  eta: 0:08:27  lr: 0.001173  min_lr: 0.001173  loss: 3.7467 (3.7500)  weight_decay: 0.0500 (0.0500)  time: 1.6810  data: 1.0755  max mem: 31830
Epoch: [198]  [ 20/312]  eta: 0:05:48  lr: 0.001172  min_lr: 0.001172  loss: 3.5911 (3.4877)  weight_decay: 0.0500 (0.0500)  time: 0.6462  data: 0.1932  max mem: 31830
Epoch: [198]  [ 30/312]  eta: 0:04:23  lr: 0.001172  min_lr: 0.001172  loss: 3.5911 (3.5201)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0680  max mem: 31830
Epoch: [198]  [ 40/312]  eta: 0:03:38  lr: 0.001171  min_lr: 0.001171  loss: 3.6334 (3.4753)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0006  max mem: 31830
Epoch: [198]  [ 50/312]  eta: 0:03:09  lr: 0.001170  min_lr: 0.001170  loss: 3.4416 (3.4696)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0007  max mem: 31830
Epoch: [198]  [ 60/312]  eta: 0:02:48  lr: 0.001170  min_lr: 0.001170  loss: 3.5971 (3.4334)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0009  max mem: 31830
Epoch: [198]  [ 70/312]  eta: 0:02:32  lr: 0.001169  min_lr: 0.001169  loss: 3.3690 (3.4076)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0016  max mem: 31830
Epoch: [198]  [ 80/312]  eta: 0:02:22  lr: 0.001168  min_lr: 0.001168  loss: 3.2468 (3.3912)  weight_decay: 0.0500 (0.0500)  time: 0.4375  data: 0.0150  max mem: 31830
Epoch: [198]  [ 90/312]  eta: 0:02:12  lr: 0.001168  min_lr: 0.001168  loss: 3.5550 (3.4157)  weight_decay: 0.0500 (0.0500)  time: 0.4633  data: 0.0432  max mem: 31830
Epoch: [198]  [100/312]  eta: 0:02:07  lr: 0.001167  min_lr: 0.001167  loss: 3.5857 (3.4187)  weight_decay: 0.0500 (0.0500)  time: 0.5494  data: 0.0911  max mem: 31830
Epoch: [198]  [110/312]  eta: 0:01:58  lr: 0.001166  min_lr: 0.001166  loss: 3.6714 (3.4335)  weight_decay: 0.0500 (0.0500)  time: 0.5592  data: 0.0625  max mem: 31830
Epoch: [198]  [120/312]  eta: 0:01:53  lr: 0.001166  min_lr: 0.001166  loss: 3.6714 (3.4421)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0502  max mem: 31830
Epoch: [198]  [130/312]  eta: 0:01:47  lr: 0.001165  min_lr: 0.001165  loss: 3.4256 (3.4341)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0936  max mem: 31830
Epoch: [198]  [140/312]  eta: 0:01:39  lr: 0.001164  min_lr: 0.001164  loss: 3.4256 (3.4524)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0445  max mem: 31830
Epoch: [198]  [150/312]  eta: 0:01:34  lr: 0.001164  min_lr: 0.001164  loss: 3.7419 (3.4659)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0607  max mem: 31830
Epoch: [198]  [160/312]  eta: 0:01:28  lr: 0.001163  min_lr: 0.001163  loss: 3.7132 (3.4777)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0861  max mem: 31830
Epoch: [198]  [170/312]  eta: 0:01:22  lr: 0.001162  min_lr: 0.001162  loss: 3.6951 (3.4805)  weight_decay: 0.0500 (0.0500)  time: 0.5493  data: 0.0458  max mem: 31830
Epoch: [198]  [180/312]  eta: 0:01:16  lr: 0.001162  min_lr: 0.001162  loss: 3.6951 (3.4816)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0204  max mem: 31830
Epoch: [198]  [190/312]  eta: 0:01:10  lr: 0.001161  min_lr: 0.001161  loss: 3.5927 (3.4794)  weight_decay: 0.0500 (0.0500)  time: 0.5408  data: 0.0316  max mem: 31830
Epoch: [198]  [200/312]  eta: 0:01:05  lr: 0.001161  min_lr: 0.001161  loss: 3.4117 (3.4714)  weight_decay: 0.0500 (0.0500)  time: 0.6237  data: 0.0684  max mem: 31830
Epoch: [198]  [210/312]  eta: 0:00:58  lr: 0.001160  min_lr: 0.001160  loss: 3.4777 (3.4604)  weight_decay: 0.0500 (0.0500)  time: 0.5413  data: 0.0376  max mem: 31830
Epoch: [198]  [220/312]  eta: 0:00:52  lr: 0.001159  min_lr: 0.001159  loss: 3.5306 (3.4619)  weight_decay: 0.0500 (0.0500)  time: 0.5156  data: 0.0227  max mem: 31830
Epoch: [198]  [230/312]  eta: 0:00:47  lr: 0.001159  min_lr: 0.001159  loss: 3.6429 (3.4663)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.0227  max mem: 31830
Epoch: [198]  [240/312]  eta: 0:00:41  lr: 0.001158  min_lr: 0.001158  loss: 3.6417 (3.4696)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0384  max mem: 31830
Epoch: [198]  [250/312]  eta: 0:00:35  lr: 0.001157  min_lr: 0.001157  loss: 3.5950 (3.4662)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0483  max mem: 31830
Epoch: [198]  [260/312]  eta: 0:00:29  lr: 0.001157  min_lr: 0.001157  loss: 3.3523 (3.4671)  weight_decay: 0.0500 (0.0500)  time: 0.5723  data: 0.0108  max mem: 31830
Epoch: [198]  [270/312]  eta: 0:00:24  lr: 0.001156  min_lr: 0.001156  loss: 3.5287 (3.4623)  weight_decay: 0.0500 (0.0500)  time: 0.5844  data: 0.0179  max mem: 31830
Epoch: [198]  [280/312]  eta: 0:00:18  lr: 0.001155  min_lr: 0.001155  loss: 3.6526 (3.4650)  weight_decay: 0.0500 (0.0500)  time: 0.6282  data: 0.0352  max mem: 31830
Epoch: [198]  [290/312]  eta: 0:00:12  lr: 0.001155  min_lr: 0.001155  loss: 3.4893 (3.4586)  weight_decay: 0.0500 (0.0500)  time: 0.5008  data: 0.0180  max mem: 31830
Epoch: [198]  [300/312]  eta: 0:00:06  lr: 0.001154  min_lr: 0.001154  loss: 3.4675 (3.4592)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0056  max mem: 31830
Epoch: [198]  [310/312]  eta: 0:00:01  lr: 0.001153  min_lr: 0.001153  loss: 3.6441 (3.4575)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0055  max mem: 31830
Epoch: [198]  [311/312]  eta: 0:00:00  lr: 0.001153  min_lr: 0.001153  loss: 3.5156 (3.4552)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0055  max mem: 31830
Epoch: [198] Total time: 0:02:55 (0.5626 s / it)
Averaged stats: lr: 0.001153  min_lr: 0.001153  loss: 3.5156 (3.4402)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0566 (1.0566)  acc1: 80.0781 (80.0781)  acc5: 95.1823 (95.1823)  time: 8.8217  data: 8.6583  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3870 (1.3088)  acc1: 72.2656 (73.1520)  acc5: 92.7083 (91.8560)  time: 1.1003  data: 0.9621  max mem: 31830
Test: Total time: 0:00:10 (1.1151 s / it)
* Acc@1 72.980 Acc@5 91.752 loss 1.316
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 72.98%
Epoch: [199]  [  0/312]  eta: 1:04:38  lr: 0.001153  min_lr: 0.001153  loss: 3.7145 (3.7145)  weight_decay: 0.0500 (0.0500)  time: 12.4313  data: 11.2360  max mem: 31830
Epoch: [199]  [ 10/312]  eta: 0:08:14  lr: 0.001153  min_lr: 0.001153  loss: 3.5170 (3.2509)  weight_decay: 0.0500 (0.0500)  time: 1.6380  data: 1.0691  max mem: 31830
Epoch: [199]  [ 20/312]  eta: 0:05:24  lr: 0.001152  min_lr: 0.001152  loss: 3.1728 (3.2223)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0505  max mem: 31830
Epoch: [199]  [ 30/312]  eta: 0:04:08  lr: 0.001151  min_lr: 0.001151  loss: 3.1728 (3.2494)  weight_decay: 0.0500 (0.0500)  time: 0.4668  data: 0.0248  max mem: 31830
Epoch: [199]  [ 40/312]  eta: 0:03:27  lr: 0.001151  min_lr: 0.001151  loss: 3.3086 (3.2739)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0008  max mem: 31830
Epoch: [199]  [ 50/312]  eta: 0:03:10  lr: 0.001150  min_lr: 0.001150  loss: 3.3432 (3.2851)  weight_decay: 0.0500 (0.0500)  time: 0.4875  data: 0.0366  max mem: 31830
Epoch: [199]  [ 60/312]  eta: 0:02:49  lr: 0.001149  min_lr: 0.001149  loss: 3.4868 (3.3135)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0366  max mem: 31830
Epoch: [199]  [ 70/312]  eta: 0:02:39  lr: 0.001149  min_lr: 0.001149  loss: 3.4868 (3.3276)  weight_decay: 0.0500 (0.0500)  time: 0.4822  data: 0.0197  max mem: 31830
Epoch: [199]  [ 80/312]  eta: 0:02:30  lr: 0.001148  min_lr: 0.001148  loss: 3.4582 (3.3471)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.0696  max mem: 31830
Epoch: [199]  [ 90/312]  eta: 0:02:18  lr: 0.001147  min_lr: 0.001147  loss: 3.6120 (3.3841)  weight_decay: 0.0500 (0.0500)  time: 0.5010  data: 0.0508  max mem: 31830
Epoch: [199]  [100/312]  eta: 0:02:12  lr: 0.001147  min_lr: 0.001147  loss: 3.6287 (3.4010)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0450  max mem: 31830
Epoch: [199]  [110/312]  eta: 0:02:01  lr: 0.001146  min_lr: 0.001146  loss: 3.4364 (3.4059)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.0454  max mem: 31830
Epoch: [199]  [120/312]  eta: 0:01:56  lr: 0.001145  min_lr: 0.001145  loss: 3.4364 (3.3935)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0504  max mem: 31830
Epoch: [199]  [130/312]  eta: 0:01:50  lr: 0.001145  min_lr: 0.001145  loss: 3.4876 (3.3841)  weight_decay: 0.0500 (0.0500)  time: 0.6270  data: 0.0822  max mem: 31830
Epoch: [199]  [140/312]  eta: 0:01:41  lr: 0.001144  min_lr: 0.001144  loss: 3.4876 (3.3868)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0332  max mem: 31830
Epoch: [199]  [150/312]  eta: 0:01:36  lr: 0.001143  min_lr: 0.001143  loss: 3.5413 (3.3821)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0302  max mem: 31830
Epoch: [199]  [160/312]  eta: 0:01:30  lr: 0.001143  min_lr: 0.001143  loss: 3.2902 (3.3887)  weight_decay: 0.0500 (0.0500)  time: 0.6086  data: 0.0631  max mem: 31830
Epoch: [199]  [170/312]  eta: 0:01:22  lr: 0.001142  min_lr: 0.001142  loss: 3.2802 (3.3745)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0339  max mem: 31830
Epoch: [199]  [180/312]  eta: 0:01:16  lr: 0.001142  min_lr: 0.001142  loss: 3.2560 (3.3768)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0160  max mem: 31830
Epoch: [199]  [190/312]  eta: 0:01:09  lr: 0.001141  min_lr: 0.001141  loss: 3.3016 (3.3662)  weight_decay: 0.0500 (0.0500)  time: 0.4750  data: 0.0165  max mem: 31830
Epoch: [199]  [200/312]  eta: 0:01:04  lr: 0.001140  min_lr: 0.001140  loss: 3.3256 (3.3738)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0067  max mem: 31830
Epoch: [199]  [210/312]  eta: 0:00:59  lr: 0.001140  min_lr: 0.001140  loss: 3.5765 (3.3795)  weight_decay: 0.0500 (0.0500)  time: 0.6527  data: 0.0128  max mem: 31830
Epoch: [199]  [220/312]  eta: 0:00:52  lr: 0.001139  min_lr: 0.001139  loss: 3.5593 (3.3841)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0074  max mem: 31830
Epoch: [199]  [230/312]  eta: 0:00:47  lr: 0.001138  min_lr: 0.001138  loss: 3.5287 (3.3849)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0428  max mem: 31830
Epoch: [199]  [240/312]  eta: 0:00:41  lr: 0.001138  min_lr: 0.001138  loss: 3.5536 (3.3851)  weight_decay: 0.0500 (0.0500)  time: 0.6412  data: 0.0428  max mem: 31830
Epoch: [199]  [250/312]  eta: 0:00:35  lr: 0.001137  min_lr: 0.001137  loss: 3.5731 (3.3895)  weight_decay: 0.0500 (0.0500)  time: 0.4953  data: 0.0008  max mem: 31830
Epoch: [199]  [260/312]  eta: 0:00:29  lr: 0.001136  min_lr: 0.001136  loss: 3.6599 (3.3896)  weight_decay: 0.0500 (0.0500)  time: 0.5464  data: 0.0204  max mem: 31830
Epoch: [199]  [270/312]  eta: 0:00:23  lr: 0.001136  min_lr: 0.001136  loss: 3.5919 (3.3930)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0204  max mem: 31830
Epoch: [199]  [280/312]  eta: 0:00:18  lr: 0.001135  min_lr: 0.001135  loss: 3.6724 (3.4018)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0035  max mem: 31830
Epoch: [199]  [290/312]  eta: 0:00:12  lr: 0.001134  min_lr: 0.001134  loss: 3.4277 (3.3894)  weight_decay: 0.0500 (0.0500)  time: 0.5947  data: 0.0032  max mem: 31830
Epoch: [199]  [300/312]  eta: 0:00:06  lr: 0.001134  min_lr: 0.001134  loss: 3.2699 (3.3925)  weight_decay: 0.0500 (0.0500)  time: 0.4722  data: 0.0003  max mem: 31830
Epoch: [199]  [310/312]  eta: 0:00:01  lr: 0.001133  min_lr: 0.001133  loss: 3.5402 (3.3960)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0002  max mem: 31830
Epoch: [199]  [311/312]  eta: 0:00:00  lr: 0.001133  min_lr: 0.001133  loss: 3.5402 (3.3961)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0002  max mem: 31830
Epoch: [199] Total time: 0:02:55 (0.5615 s / it)
Averaged stats: lr: 0.001133  min_lr: 0.001133  loss: 3.5402 (3.4451)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.2355 (1.2355)  acc1: 80.5990 (80.5990)  acc5: 95.4427 (95.4427)  time: 7.8990  data: 7.7347  max mem: 31830
Test:  [8/9]  eta: 0:00:00  loss: 1.5837 (1.4986)  acc1: 73.1771 (73.1360)  acc5: 91.4062 (91.7280)  time: 0.9948  data: 0.8595  max mem: 31830
Test: Total time: 0:00:09 (1.0053 s / it)
* Acc@1 72.860 Acc@5 91.518 loss 1.498
Accuracy of the model on the 50000 test images: 72.9%
Max accuracy: 72.98%
Epoch: [200]  [  0/312]  eta: 1:04:10  lr: 0.001133  min_lr: 0.001133  loss: 4.0743 (4.0743)  weight_decay: 0.0500 (0.0500)  time: 12.3401  data: 10.0024  max mem: 31830
Epoch: [200]  [ 10/312]  eta: 0:09:14  lr: 0.001132  min_lr: 0.001132  loss: 3.3391 (3.2900)  weight_decay: 0.0500 (0.0500)  time: 1.8350  data: 0.9712  max mem: 31830
Epoch: [200]  [ 20/312]  eta: 0:05:45  lr: 0.001132  min_lr: 0.001132  loss: 3.3391 (3.3091)  weight_decay: 0.0500 (0.0500)  time: 0.6258  data: 0.0755  max mem: 31830
Epoch: [200]  [ 30/312]  eta: 0:04:22  lr: 0.001131  min_lr: 0.001131  loss: 3.5037 (3.3278)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0425  max mem: 31830
Epoch: [200]  [ 40/312]  eta: 0:03:37  lr: 0.001130  min_lr: 0.001130  loss: 3.5588 (3.3672)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0014  max mem: 31830
Epoch: [200]  [ 50/312]  eta: 0:03:09  lr: 0.001130  min_lr: 0.001130  loss: 3.6817 (3.4271)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0016  max mem: 31830
Epoch: [200]  [ 60/312]  eta: 0:02:48  lr: 0.001129  min_lr: 0.001129  loss: 3.7292 (3.4393)  weight_decay: 0.0500 (0.0500)  time: 0.4003  data: 0.0020  max mem: 31830
Epoch: [200]  [ 70/312]  eta: 0:02:34  lr: 0.001128  min_lr: 0.001128  loss: 3.4452 (3.4425)  weight_decay: 0.0500 (0.0500)  time: 0.4261  data: 0.0014  max mem: 31830
Epoch: [200]  [ 80/312]  eta: 0:02:25  lr: 0.001128  min_lr: 0.001128  loss: 3.4452 (3.4211)  weight_decay: 0.0500 (0.0500)  time: 0.4955  data: 0.0028  max mem: 31830
Epoch: [200]  [ 90/312]  eta: 0:02:17  lr: 0.001127  min_lr: 0.001127  loss: 3.2663 (3.4005)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0273  max mem: 31830
Epoch: [200]  [100/312]  eta: 0:02:10  lr: 0.001126  min_lr: 0.001126  loss: 3.3694 (3.4053)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0391  max mem: 31830
Epoch: [200]  [110/312]  eta: 0:02:02  lr: 0.001126  min_lr: 0.001126  loss: 3.5744 (3.4159)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0415  max mem: 31830
Epoch: [200]  [120/312]  eta: 0:01:55  lr: 0.001125  min_lr: 0.001125  loss: 3.2453 (3.3747)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0433  max mem: 31830
Epoch: [200]  [130/312]  eta: 0:01:48  lr: 0.001125  min_lr: 0.001125  loss: 3.2453 (3.3825)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0458  max mem: 31830
Epoch: [200]  [140/312]  eta: 0:01:42  lr: 0.001124  min_lr: 0.001124  loss: 3.6978 (3.4084)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0691  max mem: 31830
Epoch: [200]  [150/312]  eta: 0:01:36  lr: 0.001123  min_lr: 0.001123  loss: 3.6978 (3.4147)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.0395  max mem: 31830
Epoch: [200]  [160/312]  eta: 0:01:29  lr: 0.001123  min_lr: 0.001123  loss: 3.4293 (3.4040)  weight_decay: 0.0500 (0.0500)  time: 0.5332  data: 0.0478  max mem: 31830
Epoch: [200]  [170/312]  eta: 0:01:23  lr: 0.001122  min_lr: 0.001122  loss: 3.2293 (3.4046)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0480  max mem: 31830
Epoch: [200]  [180/312]  eta: 0:01:17  lr: 0.001121  min_lr: 0.001121  loss: 3.4432 (3.4103)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0353  max mem: 31830
Epoch: [200]  [190/312]  eta: 0:01:10  lr: 0.001121  min_lr: 0.001121  loss: 3.2589 (3.4028)  weight_decay: 0.0500 (0.0500)  time: 0.5550  data: 0.0651  max mem: 31830
Epoch: [200]  [200/312]  eta: 0:01:05  lr: 0.001120  min_lr: 0.001120  loss: 3.2194 (3.3973)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0318  max mem: 31830
Epoch: [200]  [210/312]  eta: 0:00:58  lr: 0.001119  min_lr: 0.001119  loss: 3.5249 (3.4128)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0305  max mem: 31830
Epoch: [200]  [220/312]  eta: 0:00:53  lr: 0.001119  min_lr: 0.001119  loss: 3.5132 (3.4059)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0609  max mem: 31830
Epoch: [200]  [230/312]  eta: 0:00:47  lr: 0.001118  min_lr: 0.001118  loss: 3.3503 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0325  max mem: 31830
Epoch: [200]  [240/312]  eta: 0:00:41  lr: 0.001117  min_lr: 0.001117  loss: 3.4563 (3.4091)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0335  max mem: 31830
Epoch: [200]  [250/312]  eta: 0:00:35  lr: 0.001117  min_lr: 0.001117  loss: 3.5855 (3.3995)  weight_decay: 0.0500 (0.0500)  time: 0.5459  data: 0.0335  max mem: 31830
Epoch: [200]  [260/312]  eta: 0:00:29  lr: 0.001116  min_lr: 0.001116  loss: 3.5855 (3.4069)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0147  max mem: 31830
Epoch: [200]  [270/312]  eta: 0:00:24  lr: 0.001115  min_lr: 0.001115  loss: 3.7231 (3.4178)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0589  max mem: 31830
Epoch: [200]  [280/312]  eta: 0:00:18  lr: 0.001115  min_lr: 0.001115  loss: 3.6446 (3.4117)  weight_decay: 0.0500 (0.0500)  time: 0.5590  data: 0.0472  max mem: 31830
Epoch: [200]  [290/312]  eta: 0:00:12  lr: 0.001114  min_lr: 0.001114  loss: 3.5393 (3.4227)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0361  max mem: 31830
Epoch: [200]  [300/312]  eta: 0:00:06  lr: 0.001114  min_lr: 0.001114  loss: 3.5453 (3.4268)  weight_decay: 0.0500 (0.0500)  time: 0.4825  data: 0.0338  max mem: 31830
Epoch: [200]  [310/312]  eta: 0:00:01  lr: 0.001113  min_lr: 0.001113  loss: 3.5306 (3.4274)  weight_decay: 0.0500 (0.0500)  time: 0.4050  data: 0.0001  max mem: 31830
Epoch: [200]  [311/312]  eta: 0:00:00  lr: 0.001113  min_lr: 0.001113  loss: 3.5306 (3.4294)  weight_decay: 0.0500 (0.0500)  time: 0.4048  data: 0.0001  max mem: 31830
Epoch: [200] Total time: 0:02:55 (0.5634 s / it)
Averaged stats: lr: 0.001113  min_lr: 0.001113  loss: 3.5306 (3.4411)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.0396 (1.0396)  acc1: 80.2083 (80.2083)  acc5: 94.9219 (94.9219)  time: 8.2287  data: 8.0613  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3621 (1.2752)  acc1: 74.6094 (74.0640)  acc5: 90.7552 (91.6960)  time: 1.0314  data: 0.8958  max mem: 31830
Test: Total time: 0:00:09 (1.0446 s / it)
* Acc@1 73.314 Acc@5 91.804 loss 1.287
Accuracy of the model on the 50000 test images: 73.3%
Max accuracy: 73.31%
Epoch: [201]  [  0/312]  eta: 1:01:05  lr: 0.001113  min_lr: 0.001113  loss: 3.4290 (3.4290)  weight_decay: 0.0500 (0.0500)  time: 11.7494  data: 11.1267  max mem: 31830
Epoch: [201]  [ 10/312]  eta: 0:09:00  lr: 0.001112  min_lr: 0.001112  loss: 3.4290 (3.4156)  weight_decay: 0.0500 (0.0500)  time: 1.7904  data: 1.0607  max mem: 31830
Epoch: [201]  [ 20/312]  eta: 0:05:28  lr: 0.001112  min_lr: 0.001112  loss: 3.4229 (3.4557)  weight_decay: 0.0500 (0.0500)  time: 0.5944  data: 0.0274  max mem: 31830
Epoch: [201]  [ 30/312]  eta: 0:04:11  lr: 0.001111  min_lr: 0.001111  loss: 3.4481 (3.4366)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0009  max mem: 31830
Epoch: [201]  [ 40/312]  eta: 0:03:29  lr: 0.001110  min_lr: 0.001110  loss: 3.4261 (3.3942)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0015  max mem: 31830
Epoch: [201]  [ 50/312]  eta: 0:03:03  lr: 0.001110  min_lr: 0.001110  loss: 3.3023 (3.3585)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0018  max mem: 31830
Epoch: [201]  [ 60/312]  eta: 0:02:43  lr: 0.001109  min_lr: 0.001109  loss: 3.4251 (3.3688)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0017  max mem: 31830
Epoch: [201]  [ 70/312]  eta: 0:02:31  lr: 0.001108  min_lr: 0.001108  loss: 3.5721 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.4397  data: 0.0013  max mem: 31830
Epoch: [201]  [ 80/312]  eta: 0:02:26  lr: 0.001108  min_lr: 0.001108  loss: 3.7408 (3.4144)  weight_decay: 0.0500 (0.0500)  time: 0.5810  data: 0.0083  max mem: 31830
Epoch: [201]  [ 90/312]  eta: 0:02:14  lr: 0.001107  min_lr: 0.001107  loss: 3.3177 (3.4038)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0081  max mem: 31830
Epoch: [201]  [100/312]  eta: 0:02:08  lr: 0.001106  min_lr: 0.001106  loss: 3.4525 (3.4155)  weight_decay: 0.0500 (0.0500)  time: 0.5086  data: 0.0212  max mem: 31830
Epoch: [201]  [110/312]  eta: 0:02:02  lr: 0.001106  min_lr: 0.001106  loss: 3.6784 (3.4298)  weight_decay: 0.0500 (0.0500)  time: 0.5958  data: 0.0214  max mem: 31830
Epoch: [201]  [120/312]  eta: 0:01:54  lr: 0.001105  min_lr: 0.001105  loss: 3.5915 (3.4224)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0011  max mem: 31830
Epoch: [201]  [130/312]  eta: 0:01:48  lr: 0.001104  min_lr: 0.001104  loss: 3.4061 (3.4122)  weight_decay: 0.0500 (0.0500)  time: 0.5607  data: 0.0010  max mem: 31830
Epoch: [201]  [140/312]  eta: 0:01:43  lr: 0.001104  min_lr: 0.001104  loss: 3.3017 (3.3985)  weight_decay: 0.0500 (0.0500)  time: 0.6369  data: 0.0010  max mem: 31830
Epoch: [201]  [150/312]  eta: 0:01:35  lr: 0.001103  min_lr: 0.001103  loss: 3.6130 (3.4225)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0078  max mem: 31830
Epoch: [201]  [160/312]  eta: 0:01:29  lr: 0.001102  min_lr: 0.001102  loss: 3.7368 (3.4326)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0137  max mem: 31830
Epoch: [201]  [170/312]  eta: 0:01:22  lr: 0.001102  min_lr: 0.001102  loss: 3.6786 (3.4376)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0275  max mem: 31830
Epoch: [201]  [180/312]  eta: 0:01:16  lr: 0.001101  min_lr: 0.001101  loss: 3.5525 (3.4383)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0222  max mem: 31830
Epoch: [201]  [190/312]  eta: 0:01:11  lr: 0.001101  min_lr: 0.001101  loss: 3.5634 (3.4552)  weight_decay: 0.0500 (0.0500)  time: 0.6248  data: 0.0075  max mem: 31830
Epoch: [201]  [200/312]  eta: 0:01:04  lr: 0.001100  min_lr: 0.001100  loss: 3.6501 (3.4582)  weight_decay: 0.0500 (0.0500)  time: 0.5481  data: 0.0236  max mem: 31830
Epoch: [201]  [210/312]  eta: 0:00:58  lr: 0.001099  min_lr: 0.001099  loss: 3.5652 (3.4511)  weight_decay: 0.0500 (0.0500)  time: 0.4941  data: 0.0177  max mem: 31830
Epoch: [201]  [220/312]  eta: 0:00:53  lr: 0.001099  min_lr: 0.001099  loss: 3.5652 (3.4540)  weight_decay: 0.0500 (0.0500)  time: 0.6178  data: 0.0009  max mem: 31830
Epoch: [201]  [230/312]  eta: 0:00:47  lr: 0.001098  min_lr: 0.001098  loss: 3.5764 (3.4532)  weight_decay: 0.0500 (0.0500)  time: 0.5486  data: 0.0014  max mem: 31830
Epoch: [201]  [240/312]  eta: 0:00:41  lr: 0.001097  min_lr: 0.001097  loss: 3.5204 (3.4551)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0071  max mem: 31830
Epoch: [201]  [250/312]  eta: 0:00:35  lr: 0.001097  min_lr: 0.001097  loss: 3.4289 (3.4515)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0067  max mem: 31830
Epoch: [201]  [260/312]  eta: 0:00:29  lr: 0.001096  min_lr: 0.001096  loss: 3.4251 (3.4537)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0280  max mem: 31830
Epoch: [201]  [270/312]  eta: 0:00:24  lr: 0.001095  min_lr: 0.001095  loss: 3.7387 (3.4623)  weight_decay: 0.0500 (0.0500)  time: 0.6521  data: 0.0279  max mem: 31830
Epoch: [201]  [280/312]  eta: 0:00:18  lr: 0.001095  min_lr: 0.001095  loss: 3.7387 (3.4601)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0051  max mem: 31830
Epoch: [201]  [290/312]  eta: 0:00:12  lr: 0.001094  min_lr: 0.001094  loss: 3.4396 (3.4574)  weight_decay: 0.0500 (0.0500)  time: 0.4830  data: 0.0101  max mem: 31830
Epoch: [201]  [300/312]  eta: 0:00:06  lr: 0.001094  min_lr: 0.001094  loss: 3.6293 (3.4606)  weight_decay: 0.0500 (0.0500)  time: 0.4726  data: 0.0057  max mem: 31830
Epoch: [201]  [310/312]  eta: 0:00:01  lr: 0.001093  min_lr: 0.001093  loss: 3.6293 (3.4554)  weight_decay: 0.0500 (0.0500)  time: 0.3937  data: 0.0002  max mem: 31830
Epoch: [201]  [311/312]  eta: 0:00:00  lr: 0.001093  min_lr: 0.001093  loss: 3.6293 (3.4514)  weight_decay: 0.0500 (0.0500)  time: 0.3936  data: 0.0001  max mem: 31830
Epoch: [201] Total time: 0:02:55 (0.5623 s / it)
Averaged stats: lr: 0.001093  min_lr: 0.001093  loss: 3.6293 (3.4164)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0862 (1.0862)  acc1: 78.6458 (78.6458)  acc5: 94.6615 (94.6615)  time: 8.8309  data: 8.6632  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3823 (1.3158)  acc1: 71.7448 (72.5120)  acc5: 91.6667 (91.1200)  time: 1.0988  data: 0.9627  max mem: 31830
Test: Total time: 0:00:10 (1.1229 s / it)
* Acc@1 72.688 Acc@5 91.626 loss 1.304
Accuracy of the model on the 50000 test images: 72.7%
Max accuracy: 73.31%
Epoch: [202]  [  0/312]  eta: 1:05:15  lr: 0.001093  min_lr: 0.001093  loss: 3.7286 (3.7286)  weight_decay: 0.0500 (0.0500)  time: 12.5490  data: 10.0084  max mem: 31830
Epoch: [202]  [ 10/312]  eta: 0:08:53  lr: 0.001092  min_lr: 0.001092  loss: 3.6894 (3.4146)  weight_decay: 0.0500 (0.0500)  time: 1.7662  data: 1.1249  max mem: 31830
Epoch: [202]  [ 20/312]  eta: 0:05:26  lr: 0.001091  min_lr: 0.001091  loss: 3.2949 (3.4035)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.1237  max mem: 31830
Epoch: [202]  [ 30/312]  eta: 0:04:09  lr: 0.001091  min_lr: 0.001091  loss: 3.3641 (3.3932)  weight_decay: 0.0500 (0.0500)  time: 0.4003  data: 0.0061  max mem: 31830
Epoch: [202]  [ 40/312]  eta: 0:03:28  lr: 0.001090  min_lr: 0.001090  loss: 3.3641 (3.3745)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0016  max mem: 31830
Epoch: [202]  [ 50/312]  eta: 0:03:01  lr: 0.001090  min_lr: 0.001090  loss: 3.5284 (3.3819)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0015  max mem: 31830
Epoch: [202]  [ 60/312]  eta: 0:02:42  lr: 0.001089  min_lr: 0.001089  loss: 3.5259 (3.4019)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0009  max mem: 31830
Epoch: [202]  [ 70/312]  eta: 0:02:35  lr: 0.001088  min_lr: 0.001088  loss: 3.7082 (3.4532)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0365  max mem: 31830
Epoch: [202]  [ 80/312]  eta: 0:02:26  lr: 0.001088  min_lr: 0.001088  loss: 3.7388 (3.4638)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0365  max mem: 31830
Epoch: [202]  [ 90/312]  eta: 0:02:15  lr: 0.001087  min_lr: 0.001087  loss: 3.4759 (3.4466)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.0370  max mem: 31830
Epoch: [202]  [100/312]  eta: 0:02:09  lr: 0.001086  min_lr: 0.001086  loss: 3.5810 (3.4694)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0497  max mem: 31830
Epoch: [202]  [110/312]  eta: 0:01:59  lr: 0.001086  min_lr: 0.001086  loss: 3.5176 (3.4649)  weight_decay: 0.0500 (0.0500)  time: 0.4930  data: 0.0188  max mem: 31830
Epoch: [202]  [120/312]  eta: 0:01:54  lr: 0.001085  min_lr: 0.001085  loss: 3.2093 (3.4473)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0439  max mem: 31830
Epoch: [202]  [130/312]  eta: 0:01:48  lr: 0.001084  min_lr: 0.001084  loss: 3.1694 (3.4274)  weight_decay: 0.0500 (0.0500)  time: 0.6304  data: 0.0719  max mem: 31830
Epoch: [202]  [140/312]  eta: 0:01:40  lr: 0.001084  min_lr: 0.001084  loss: 3.3183 (3.4134)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.0345  max mem: 31830
Epoch: [202]  [150/312]  eta: 0:01:34  lr: 0.001083  min_lr: 0.001083  loss: 3.5904 (3.4177)  weight_decay: 0.0500 (0.0500)  time: 0.5174  data: 0.0302  max mem: 31830
Epoch: [202]  [160/312]  eta: 0:01:29  lr: 0.001083  min_lr: 0.001083  loss: 3.6538 (3.4216)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0438  max mem: 31830
Epoch: [202]  [170/312]  eta: 0:01:22  lr: 0.001082  min_lr: 0.001082  loss: 3.4594 (3.4134)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0338  max mem: 31830
Epoch: [202]  [180/312]  eta: 0:01:16  lr: 0.001081  min_lr: 0.001081  loss: 3.4419 (3.4118)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0527  max mem: 31830
Epoch: [202]  [190/312]  eta: 0:01:09  lr: 0.001081  min_lr: 0.001081  loss: 3.4852 (3.4130)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0338  max mem: 31830
Epoch: [202]  [200/312]  eta: 0:01:04  lr: 0.001080  min_lr: 0.001080  loss: 3.5607 (3.4205)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0445  max mem: 31830
Epoch: [202]  [210/312]  eta: 0:00:58  lr: 0.001079  min_lr: 0.001079  loss: 3.5607 (3.4178)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0758  max mem: 31830
Epoch: [202]  [220/312]  eta: 0:00:52  lr: 0.001079  min_lr: 0.001079  loss: 3.4283 (3.4169)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0322  max mem: 31830
Epoch: [202]  [230/312]  eta: 0:00:46  lr: 0.001078  min_lr: 0.001078  loss: 3.4560 (3.4167)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0273  max mem: 31830
Epoch: [202]  [240/312]  eta: 0:00:41  lr: 0.001077  min_lr: 0.001077  loss: 3.6017 (3.4246)  weight_decay: 0.0500 (0.0500)  time: 0.6181  data: 0.0705  max mem: 31830
Epoch: [202]  [250/312]  eta: 0:00:35  lr: 0.001077  min_lr: 0.001077  loss: 3.6575 (3.4286)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0443  max mem: 31830
Epoch: [202]  [260/312]  eta: 0:00:29  lr: 0.001076  min_lr: 0.001076  loss: 3.5896 (3.4280)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0383  max mem: 31830
Epoch: [202]  [270/312]  eta: 0:00:23  lr: 0.001075  min_lr: 0.001075  loss: 3.3904 (3.4231)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0432  max mem: 31830
Epoch: [202]  [280/312]  eta: 0:00:18  lr: 0.001075  min_lr: 0.001075  loss: 3.6621 (3.4257)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0373  max mem: 31830
Epoch: [202]  [290/312]  eta: 0:00:12  lr: 0.001074  min_lr: 0.001074  loss: 3.6621 (3.4255)  weight_decay: 0.0500 (0.0500)  time: 0.5913  data: 0.0516  max mem: 31830
Epoch: [202]  [300/312]  eta: 0:00:06  lr: 0.001074  min_lr: 0.001074  loss: 3.6140 (3.4312)  weight_decay: 0.0500 (0.0500)  time: 0.4817  data: 0.0199  max mem: 31830
Epoch: [202]  [310/312]  eta: 0:00:01  lr: 0.001073  min_lr: 0.001073  loss: 3.6917 (3.4381)  weight_decay: 0.0500 (0.0500)  time: 0.3833  data: 0.0002  max mem: 31830
Epoch: [202]  [311/312]  eta: 0:00:00  lr: 0.001073  min_lr: 0.001073  loss: 3.6917 (3.4385)  weight_decay: 0.0500 (0.0500)  time: 0.3828  data: 0.0002  max mem: 31830
Epoch: [202] Total time: 0:02:53 (0.5557 s / it)
Averaged stats: lr: 0.001073  min_lr: 0.001073  loss: 3.6917 (3.4344)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.2102 (1.2102)  acc1: 78.5156 (78.5156)  acc5: 94.2708 (94.2708)  time: 8.6417  data: 8.4729  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4736 (1.4088)  acc1: 73.1771 (72.7200)  acc5: 91.7969 (91.5840)  time: 1.0790  data: 0.9415  max mem: 31830
Test: Total time: 0:00:09 (1.0886 s / it)
* Acc@1 72.822 Acc@5 91.566 loss 1.426
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 73.31%
Epoch: [203]  [  0/312]  eta: 1:00:39  lr: 0.001073  min_lr: 0.001073  loss: 3.8053 (3.8053)  weight_decay: 0.0500 (0.0500)  time: 11.6644  data: 8.4101  max mem: 31830
Epoch: [203]  [ 10/312]  eta: 0:08:28  lr: 0.001072  min_lr: 0.001072  loss: 3.6059 (3.5724)  weight_decay: 0.0500 (0.0500)  time: 1.6838  data: 0.9554  max mem: 31830
Epoch: [203]  [ 20/312]  eta: 0:05:18  lr: 0.001072  min_lr: 0.001072  loss: 3.5520 (3.4379)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.1054  max mem: 31830
Epoch: [203]  [ 30/312]  eta: 0:04:04  lr: 0.001071  min_lr: 0.001071  loss: 3.5009 (3.4405)  weight_decay: 0.0500 (0.0500)  time: 0.4186  data: 0.0009  max mem: 31830
Epoch: [203]  [ 40/312]  eta: 0:03:24  lr: 0.001070  min_lr: 0.001070  loss: 3.6421 (3.4972)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0008  max mem: 31830
Epoch: [203]  [ 50/312]  eta: 0:03:04  lr: 0.001070  min_lr: 0.001070  loss: 3.5919 (3.4717)  weight_decay: 0.0500 (0.0500)  time: 0.4493  data: 0.0185  max mem: 31830
Epoch: [203]  [ 60/312]  eta: 0:02:44  lr: 0.001069  min_lr: 0.001069  loss: 3.5084 (3.4790)  weight_decay: 0.0500 (0.0500)  time: 0.4502  data: 0.0185  max mem: 31830
Epoch: [203]  [ 70/312]  eta: 0:02:35  lr: 0.001068  min_lr: 0.001068  loss: 3.4473 (3.4552)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0383  max mem: 31830
Epoch: [203]  [ 80/312]  eta: 0:02:27  lr: 0.001068  min_lr: 0.001068  loss: 3.5601 (3.4552)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.1292  max mem: 31830
Epoch: [203]  [ 90/312]  eta: 0:02:15  lr: 0.001067  min_lr: 0.001067  loss: 3.6102 (3.4658)  weight_decay: 0.0500 (0.0500)  time: 0.5043  data: 0.0917  max mem: 31830
Epoch: [203]  [100/312]  eta: 0:02:10  lr: 0.001066  min_lr: 0.001066  loss: 3.4290 (3.4532)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0875  max mem: 31830
Epoch: [203]  [110/312]  eta: 0:02:00  lr: 0.001066  min_lr: 0.001066  loss: 3.5391 (3.4573)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0875  max mem: 31830
Epoch: [203]  [120/312]  eta: 0:01:54  lr: 0.001065  min_lr: 0.001065  loss: 3.6485 (3.4664)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0719  max mem: 31830
Epoch: [203]  [130/312]  eta: 0:01:48  lr: 0.001065  min_lr: 0.001065  loss: 3.5227 (3.4561)  weight_decay: 0.0500 (0.0500)  time: 0.6145  data: 0.1162  max mem: 31830
Epoch: [203]  [140/312]  eta: 0:01:41  lr: 0.001064  min_lr: 0.001064  loss: 3.4317 (3.4619)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0582  max mem: 31830
Epoch: [203]  [150/312]  eta: 0:01:35  lr: 0.001063  min_lr: 0.001063  loss: 3.3954 (3.4454)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0429  max mem: 31830
Epoch: [203]  [160/312]  eta: 0:01:29  lr: 0.001063  min_lr: 0.001063  loss: 3.3606 (3.4399)  weight_decay: 0.0500 (0.0500)  time: 0.6100  data: 0.0348  max mem: 31830
Epoch: [203]  [170/312]  eta: 0:01:22  lr: 0.001062  min_lr: 0.001062  loss: 3.5976 (3.4503)  weight_decay: 0.0500 (0.0500)  time: 0.5316  data: 0.0406  max mem: 31830
Epoch: [203]  [180/312]  eta: 0:01:16  lr: 0.001061  min_lr: 0.001061  loss: 3.5976 (3.4408)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0452  max mem: 31830
Epoch: [203]  [190/312]  eta: 0:01:09  lr: 0.001061  min_lr: 0.001061  loss: 3.4495 (3.4383)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0256  max mem: 31830
Epoch: [203]  [200/312]  eta: 0:01:04  lr: 0.001060  min_lr: 0.001060  loss: 3.4495 (3.4391)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0461  max mem: 31830
Epoch: [203]  [210/312]  eta: 0:00:59  lr: 0.001059  min_lr: 0.001059  loss: 3.5781 (3.4457)  weight_decay: 0.0500 (0.0500)  time: 0.6474  data: 0.0509  max mem: 31830
Epoch: [203]  [220/312]  eta: 0:00:52  lr: 0.001059  min_lr: 0.001059  loss: 3.5817 (3.4382)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0211  max mem: 31830
Epoch: [203]  [230/312]  eta: 0:00:46  lr: 0.001058  min_lr: 0.001058  loss: 3.3163 (3.4381)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0009  max mem: 31830
Epoch: [203]  [240/312]  eta: 0:00:41  lr: 0.001058  min_lr: 0.001058  loss: 3.5517 (3.4378)  weight_decay: 0.0500 (0.0500)  time: 0.6313  data: 0.0008  max mem: 31830
Epoch: [203]  [250/312]  eta: 0:00:35  lr: 0.001057  min_lr: 0.001057  loss: 3.3922 (3.4355)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0092  max mem: 31830
Epoch: [203]  [260/312]  eta: 0:00:29  lr: 0.001056  min_lr: 0.001056  loss: 3.3298 (3.4276)  weight_decay: 0.0500 (0.0500)  time: 0.5006  data: 0.0104  max mem: 31830
Epoch: [203]  [270/312]  eta: 0:00:23  lr: 0.001056  min_lr: 0.001056  loss: 3.4658 (3.4210)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0105  max mem: 31830
Epoch: [203]  [280/312]  eta: 0:00:18  lr: 0.001055  min_lr: 0.001055  loss: 3.5664 (3.4226)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0162  max mem: 31830
Epoch: [203]  [290/312]  eta: 0:00:12  lr: 0.001054  min_lr: 0.001054  loss: 3.4766 (3.4176)  weight_decay: 0.0500 (0.0500)  time: 0.5960  data: 0.0257  max mem: 31830
Epoch: [203]  [300/312]  eta: 0:00:06  lr: 0.001054  min_lr: 0.001054  loss: 3.4898 (3.4202)  weight_decay: 0.0500 (0.0500)  time: 0.4742  data: 0.0185  max mem: 31830
Epoch: [203]  [310/312]  eta: 0:00:01  lr: 0.001053  min_lr: 0.001053  loss: 3.6136 (3.4174)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [203]  [311/312]  eta: 0:00:00  lr: 0.001053  min_lr: 0.001053  loss: 3.6136 (3.4189)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [203] Total time: 0:02:54 (0.5596 s / it)
Averaged stats: lr: 0.001053  min_lr: 0.001053  loss: 3.6136 (3.4146)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1714 (1.1714)  acc1: 80.9896 (80.9896)  acc5: 95.4427 (95.4427)  time: 8.6211  data: 8.4537  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5427 (1.4561)  acc1: 72.1354 (73.0560)  acc5: 90.8854 (91.5680)  time: 1.0870  data: 0.9394  max mem: 31830
Test: Total time: 0:00:10 (1.1148 s / it)
* Acc@1 73.184 Acc@5 91.740 loss 1.465
Accuracy of the model on the 50000 test images: 73.2%
Max accuracy: 73.31%
Epoch: [204]  [  0/312]  eta: 1:03:36  lr: 0.001053  min_lr: 0.001053  loss: 2.8065 (2.8065)  weight_decay: 0.0500 (0.0500)  time: 12.2309  data: 11.8307  max mem: 31830
Epoch: [204]  [ 10/312]  eta: 0:08:50  lr: 0.001052  min_lr: 0.001052  loss: 3.2832 (3.3661)  weight_decay: 0.0500 (0.0500)  time: 1.7552  data: 1.0762  max mem: 31830
Epoch: [204]  [ 20/312]  eta: 0:05:27  lr: 0.001052  min_lr: 0.001052  loss: 3.7844 (3.6086)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0187  max mem: 31830
Epoch: [204]  [ 30/312]  eta: 0:04:10  lr: 0.001051  min_lr: 0.001051  loss: 3.6731 (3.5506)  weight_decay: 0.0500 (0.0500)  time: 0.4126  data: 0.0187  max mem: 31830
Epoch: [204]  [ 40/312]  eta: 0:03:29  lr: 0.001050  min_lr: 0.001050  loss: 3.4910 (3.4954)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0008  max mem: 31830
Epoch: [204]  [ 50/312]  eta: 0:03:02  lr: 0.001050  min_lr: 0.001050  loss: 3.4596 (3.4627)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0010  max mem: 31830
Epoch: [204]  [ 60/312]  eta: 0:02:43  lr: 0.001049  min_lr: 0.001049  loss: 3.5601 (3.4435)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0016  max mem: 31830
Epoch: [204]  [ 70/312]  eta: 0:02:31  lr: 0.001049  min_lr: 0.001049  loss: 3.6059 (3.4570)  weight_decay: 0.0500 (0.0500)  time: 0.4499  data: 0.0598  max mem: 31830
Epoch: [204]  [ 80/312]  eta: 0:02:25  lr: 0.001048  min_lr: 0.001048  loss: 3.6000 (3.4509)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.1520  max mem: 31830
Epoch: [204]  [ 90/312]  eta: 0:02:13  lr: 0.001047  min_lr: 0.001047  loss: 3.6131 (3.4626)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0938  max mem: 31830
Epoch: [204]  [100/312]  eta: 0:02:07  lr: 0.001047  min_lr: 0.001047  loss: 3.4361 (3.4400)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0810  max mem: 31830
Epoch: [204]  [110/312]  eta: 0:02:01  lr: 0.001046  min_lr: 0.001046  loss: 3.4361 (3.4544)  weight_decay: 0.0500 (0.0500)  time: 0.5847  data: 0.1492  max mem: 31830
Epoch: [204]  [120/312]  eta: 0:01:53  lr: 0.001045  min_lr: 0.001045  loss: 3.6160 (3.4492)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0980  max mem: 31830
Epoch: [204]  [130/312]  eta: 0:01:47  lr: 0.001045  min_lr: 0.001045  loss: 3.4913 (3.4431)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.1125  max mem: 31830
Epoch: [204]  [140/312]  eta: 0:01:39  lr: 0.001044  min_lr: 0.001044  loss: 3.6503 (3.4569)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0837  max mem: 31830
Epoch: [204]  [150/312]  eta: 0:01:34  lr: 0.001044  min_lr: 0.001044  loss: 3.6738 (3.4610)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0952  max mem: 31830
Epoch: [204]  [160/312]  eta: 0:01:28  lr: 0.001043  min_lr: 0.001043  loss: 3.5971 (3.4518)  weight_decay: 0.0500 (0.0500)  time: 0.6076  data: 0.1787  max mem: 31830
Epoch: [204]  [170/312]  eta: 0:01:21  lr: 0.001042  min_lr: 0.001042  loss: 3.6670 (3.4563)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0843  max mem: 31830
Epoch: [204]  [180/312]  eta: 0:01:16  lr: 0.001042  min_lr: 0.001042  loss: 3.6068 (3.4493)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.1073  max mem: 31830
Epoch: [204]  [190/312]  eta: 0:01:10  lr: 0.001041  min_lr: 0.001041  loss: 3.3527 (3.4433)  weight_decay: 0.0500 (0.0500)  time: 0.6247  data: 0.2026  max mem: 31830
Epoch: [204]  [200/312]  eta: 0:01:03  lr: 0.001040  min_lr: 0.001040  loss: 3.4510 (3.4527)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0965  max mem: 31830
Epoch: [204]  [210/312]  eta: 0:00:58  lr: 0.001040  min_lr: 0.001040  loss: 3.4270 (3.4359)  weight_decay: 0.0500 (0.0500)  time: 0.5349  data: 0.0873  max mem: 31830
Epoch: [204]  [220/312]  eta: 0:00:52  lr: 0.001039  min_lr: 0.001039  loss: 3.6616 (3.4477)  weight_decay: 0.0500 (0.0500)  time: 0.5766  data: 0.0869  max mem: 31830
Epoch: [204]  [230/312]  eta: 0:00:46  lr: 0.001038  min_lr: 0.001038  loss: 3.7428 (3.4551)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0935  max mem: 31830
Epoch: [204]  [240/312]  eta: 0:00:41  lr: 0.001038  min_lr: 0.001038  loss: 3.4664 (3.4522)  weight_decay: 0.0500 (0.0500)  time: 0.5936  data: 0.1975  max mem: 31830
Epoch: [204]  [250/312]  eta: 0:00:35  lr: 0.001037  min_lr: 0.001037  loss: 3.3589 (3.4600)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.1047  max mem: 31830
Epoch: [204]  [260/312]  eta: 0:00:29  lr: 0.001037  min_lr: 0.001037  loss: 3.4715 (3.4611)  weight_decay: 0.0500 (0.0500)  time: 0.5372  data: 0.1199  max mem: 31830
Epoch: [204]  [270/312]  eta: 0:00:23  lr: 0.001036  min_lr: 0.001036  loss: 3.5752 (3.4617)  weight_decay: 0.0500 (0.0500)  time: 0.6178  data: 0.2187  max mem: 31830
Epoch: [204]  [280/312]  eta: 0:00:18  lr: 0.001035  min_lr: 0.001035  loss: 3.5752 (3.4585)  weight_decay: 0.0500 (0.0500)  time: 0.4997  data: 0.1014  max mem: 31830
Epoch: [204]  [290/312]  eta: 0:00:12  lr: 0.001035  min_lr: 0.001035  loss: 3.3522 (3.4530)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.1007  max mem: 31830
Epoch: [204]  [300/312]  eta: 0:00:06  lr: 0.001034  min_lr: 0.001034  loss: 3.2426 (3.4483)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0986  max mem: 31830
Epoch: [204]  [310/312]  eta: 0:00:01  lr: 0.001033  min_lr: 0.001033  loss: 3.4755 (3.4504)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0137  max mem: 31830
Epoch: [204]  [311/312]  eta: 0:00:00  lr: 0.001033  min_lr: 0.001033  loss: 3.5152 (3.4529)  weight_decay: 0.0500 (0.0500)  time: 0.3944  data: 0.0137  max mem: 31830
Epoch: [204] Total time: 0:02:54 (0.5592 s / it)
Averaged stats: lr: 0.001033  min_lr: 0.001033  loss: 3.5152 (3.4324)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.1792 (1.1792)  acc1: 79.5573 (79.5573)  acc5: 95.8333 (95.8333)  time: 8.5211  data: 8.3525  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4113 (1.3722)  acc1: 73.6979 (73.5200)  acc5: 91.9271 (92.0000)  time: 1.0718  data: 0.9281  max mem: 31830
Test: Total time: 0:00:09 (1.1021 s / it)
* Acc@1 73.568 Acc@5 91.962 loss 1.371
Accuracy of the model on the 50000 test images: 73.6%
Max accuracy: 73.57%
Epoch: [205]  [  0/312]  eta: 1:01:59  lr: 0.001033  min_lr: 0.001033  loss: 3.4911 (3.4911)  weight_decay: 0.0500 (0.0500)  time: 11.9225  data: 8.4931  max mem: 31830
Epoch: [205]  [ 10/312]  eta: 0:08:33  lr: 0.001033  min_lr: 0.001033  loss: 3.4911 (3.3026)  weight_decay: 0.0500 (0.0500)  time: 1.7009  data: 1.0343  max mem: 31830
Epoch: [205]  [ 20/312]  eta: 0:05:28  lr: 0.001032  min_lr: 0.001032  loss: 3.5364 (3.3568)  weight_decay: 0.0500 (0.0500)  time: 0.5863  data: 0.1958  max mem: 31830
Epoch: [205]  [ 30/312]  eta: 0:04:11  lr: 0.001031  min_lr: 0.001031  loss: 3.5634 (3.3995)  weight_decay: 0.0500 (0.0500)  time: 0.4448  data: 0.0521  max mem: 31830
Epoch: [205]  [ 40/312]  eta: 0:03:29  lr: 0.001031  min_lr: 0.001031  loss: 3.3484 (3.3762)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0014  max mem: 31830
Epoch: [205]  [ 50/312]  eta: 0:03:02  lr: 0.001030  min_lr: 0.001030  loss: 3.5460 (3.4269)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0013  max mem: 31830
Epoch: [205]  [ 60/312]  eta: 0:02:43  lr: 0.001030  min_lr: 0.001030  loss: 3.5904 (3.4299)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0009  max mem: 31830
Epoch: [205]  [ 70/312]  eta: 0:02:34  lr: 0.001029  min_lr: 0.001029  loss: 3.4766 (3.4200)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0503  max mem: 31830
Epoch: [205]  [ 80/312]  eta: 0:02:27  lr: 0.001028  min_lr: 0.001028  loss: 3.3492 (3.3854)  weight_decay: 0.0500 (0.0500)  time: 0.6037  data: 0.0650  max mem: 31830
Epoch: [205]  [ 90/312]  eta: 0:02:18  lr: 0.001028  min_lr: 0.001028  loss: 3.3512 (3.3920)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.0724  max mem: 31830
Epoch: [205]  [100/312]  eta: 0:02:10  lr: 0.001027  min_lr: 0.001027  loss: 3.5360 (3.3979)  weight_decay: 0.0500 (0.0500)  time: 0.5383  data: 0.0903  max mem: 31830
Epoch: [205]  [110/312]  eta: 0:02:00  lr: 0.001026  min_lr: 0.001026  loss: 3.5726 (3.4065)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0335  max mem: 31830
Epoch: [205]  [120/312]  eta: 0:01:55  lr: 0.001026  min_lr: 0.001026  loss: 3.3990 (3.4030)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0608  max mem: 31830
Epoch: [205]  [130/312]  eta: 0:01:49  lr: 0.001025  min_lr: 0.001025  loss: 3.3990 (3.4014)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0927  max mem: 31830
Epoch: [205]  [140/312]  eta: 0:01:40  lr: 0.001025  min_lr: 0.001025  loss: 3.5385 (3.4091)  weight_decay: 0.0500 (0.0500)  time: 0.4811  data: 0.0326  max mem: 31830
Epoch: [205]  [150/312]  eta: 0:01:35  lr: 0.001024  min_lr: 0.001024  loss: 3.5564 (3.4092)  weight_decay: 0.0500 (0.0500)  time: 0.5092  data: 0.0368  max mem: 31830
Epoch: [205]  [160/312]  eta: 0:01:28  lr: 0.001023  min_lr: 0.001023  loss: 3.3591 (3.3909)  weight_decay: 0.0500 (0.0500)  time: 0.5729  data: 0.0371  max mem: 31830
Epoch: [205]  [170/312]  eta: 0:01:22  lr: 0.001023  min_lr: 0.001023  loss: 3.0716 (3.3847)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0445  max mem: 31830
Epoch: [205]  [180/312]  eta: 0:01:16  lr: 0.001022  min_lr: 0.001022  loss: 3.2056 (3.3785)  weight_decay: 0.0500 (0.0500)  time: 0.5454  data: 0.0755  max mem: 31830
Epoch: [205]  [190/312]  eta: 0:01:09  lr: 0.001021  min_lr: 0.001021  loss: 3.4839 (3.3879)  weight_decay: 0.0500 (0.0500)  time: 0.4802  data: 0.0321  max mem: 31830
Epoch: [205]  [200/312]  eta: 0:01:04  lr: 0.001021  min_lr: 0.001021  loss: 3.2856 (3.3747)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0441  max mem: 31830
Epoch: [205]  [210/312]  eta: 0:00:58  lr: 0.001020  min_lr: 0.001020  loss: 3.2856 (3.3775)  weight_decay: 0.0500 (0.0500)  time: 0.6126  data: 0.0765  max mem: 31830
Epoch: [205]  [220/312]  eta: 0:00:52  lr: 0.001019  min_lr: 0.001019  loss: 3.6831 (3.3906)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0332  max mem: 31830
Epoch: [205]  [230/312]  eta: 0:00:46  lr: 0.001019  min_lr: 0.001019  loss: 3.5830 (3.3801)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0415  max mem: 31830
Epoch: [205]  [240/312]  eta: 0:00:40  lr: 0.001018  min_lr: 0.001018  loss: 3.2871 (3.3774)  weight_decay: 0.0500 (0.0500)  time: 0.5975  data: 0.0417  max mem: 31830
Epoch: [205]  [250/312]  eta: 0:00:35  lr: 0.001018  min_lr: 0.001018  loss: 3.5029 (3.3765)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0329  max mem: 31830
Epoch: [205]  [260/312]  eta: 0:00:29  lr: 0.001017  min_lr: 0.001017  loss: 3.4274 (3.3810)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0781  max mem: 31830
Epoch: [205]  [270/312]  eta: 0:00:23  lr: 0.001016  min_lr: 0.001016  loss: 3.4795 (3.3819)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0460  max mem: 31830
Epoch: [205]  [280/312]  eta: 0:00:17  lr: 0.001016  min_lr: 0.001016  loss: 3.4795 (3.3812)  weight_decay: 0.0500 (0.0500)  time: 0.4817  data: 0.0085  max mem: 31830
Epoch: [205]  [290/312]  eta: 0:00:12  lr: 0.001015  min_lr: 0.001015  loss: 3.5476 (3.3860)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0387  max mem: 31830
Epoch: [205]  [300/312]  eta: 0:00:06  lr: 0.001014  min_lr: 0.001014  loss: 3.6976 (3.3848)  weight_decay: 0.0500 (0.0500)  time: 0.4912  data: 0.0306  max mem: 31830
Epoch: [205]  [310/312]  eta: 0:00:01  lr: 0.001014  min_lr: 0.001014  loss: 3.3326 (3.3794)  weight_decay: 0.0500 (0.0500)  time: 0.3817  data: 0.0002  max mem: 31830
Epoch: [205]  [311/312]  eta: 0:00:00  lr: 0.001014  min_lr: 0.001014  loss: 3.3270 (3.3789)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [205] Total time: 0:02:53 (0.5551 s / it)
Averaged stats: lr: 0.001014  min_lr: 0.001014  loss: 3.3270 (3.4089)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.9697 (0.9697)  acc1: 79.8177 (79.8177)  acc5: 95.4427 (95.4427)  time: 8.7382  data: 8.5779  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3104 (1.2367)  acc1: 73.5677 (73.7120)  acc5: 92.1875 (92.2240)  time: 1.1205  data: 0.9735  max mem: 31830
Test: Total time: 0:00:10 (1.1337 s / it)
* Acc@1 74.044 Acc@5 92.230 loss 1.231
Accuracy of the model on the 50000 test images: 74.0%
Max accuracy: 74.04%
Epoch: [206]  [  0/312]  eta: 1:02:36  lr: 0.001014  min_lr: 0.001014  loss: 3.4156 (3.4156)  weight_decay: 0.0500 (0.0500)  time: 12.0415  data: 11.6416  max mem: 31830
Epoch: [206]  [ 10/312]  eta: 0:08:07  lr: 0.001013  min_lr: 0.001013  loss: 3.2824 (3.3061)  weight_decay: 0.0500 (0.0500)  time: 1.6152  data: 1.0592  max mem: 31830
Epoch: [206]  [ 20/312]  eta: 0:05:22  lr: 0.001012  min_lr: 0.001012  loss: 3.3027 (3.4168)  weight_decay: 0.0500 (0.0500)  time: 0.5568  data: 0.0783  max mem: 31830
Epoch: [206]  [ 30/312]  eta: 0:04:07  lr: 0.001012  min_lr: 0.001012  loss: 3.5666 (3.4830)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0784  max mem: 31830
Epoch: [206]  [ 40/312]  eta: 0:03:28  lr: 0.001011  min_lr: 0.001011  loss: 3.6720 (3.5027)  weight_decay: 0.0500 (0.0500)  time: 0.4143  data: 0.0209  max mem: 31830
Epoch: [206]  [ 50/312]  eta: 0:03:13  lr: 0.001011  min_lr: 0.001011  loss: 3.5136 (3.4429)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.1312  max mem: 31830
Epoch: [206]  [ 60/312]  eta: 0:02:51  lr: 0.001010  min_lr: 0.001010  loss: 3.5136 (3.4707)  weight_decay: 0.0500 (0.0500)  time: 0.5041  data: 0.1112  max mem: 31830
Epoch: [206]  [ 70/312]  eta: 0:02:42  lr: 0.001009  min_lr: 0.001009  loss: 3.5247 (3.4650)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.0926  max mem: 31830
Epoch: [206]  [ 80/312]  eta: 0:02:30  lr: 0.001009  min_lr: 0.001009  loss: 3.3806 (3.4542)  weight_decay: 0.0500 (0.0500)  time: 0.5464  data: 0.1140  max mem: 31830
Epoch: [206]  [ 90/312]  eta: 0:02:20  lr: 0.001008  min_lr: 0.001008  loss: 3.5864 (3.4391)  weight_decay: 0.0500 (0.0500)  time: 0.5038  data: 0.0825  max mem: 31830
Epoch: [206]  [100/312]  eta: 0:02:13  lr: 0.001007  min_lr: 0.001007  loss: 3.5709 (3.4379)  weight_decay: 0.0500 (0.0500)  time: 0.5586  data: 0.1672  max mem: 31830
Epoch: [206]  [110/312]  eta: 0:02:02  lr: 0.001007  min_lr: 0.001007  loss: 3.5675 (3.4418)  weight_decay: 0.0500 (0.0500)  time: 0.4968  data: 0.1068  max mem: 31830
Epoch: [206]  [120/312]  eta: 0:01:56  lr: 0.001006  min_lr: 0.001006  loss: 3.4223 (3.4313)  weight_decay: 0.0500 (0.0500)  time: 0.5007  data: 0.1055  max mem: 31830
Epoch: [206]  [130/312]  eta: 0:01:50  lr: 0.001006  min_lr: 0.001006  loss: 3.2884 (3.4257)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.2138  max mem: 31830
Epoch: [206]  [140/312]  eta: 0:01:42  lr: 0.001005  min_lr: 0.001005  loss: 3.5397 (3.4386)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.1092  max mem: 31830
Epoch: [206]  [150/312]  eta: 0:01:36  lr: 0.001004  min_lr: 0.001004  loss: 3.6716 (3.4470)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0955  max mem: 31830
Epoch: [206]  [160/312]  eta: 0:01:30  lr: 0.001004  min_lr: 0.001004  loss: 3.5781 (3.4234)  weight_decay: 0.0500 (0.0500)  time: 0.6167  data: 0.2264  max mem: 31830
Epoch: [206]  [170/312]  eta: 0:01:23  lr: 0.001003  min_lr: 0.001003  loss: 3.4345 (3.4202)  weight_decay: 0.0500 (0.0500)  time: 0.5237  data: 0.1318  max mem: 31830
Epoch: [206]  [180/312]  eta: 0:01:17  lr: 0.001002  min_lr: 0.001002  loss: 3.4689 (3.4241)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.1117  max mem: 31830
Epoch: [206]  [190/312]  eta: 0:01:10  lr: 0.001002  min_lr: 0.001002  loss: 3.5022 (3.4240)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.1118  max mem: 31830
Epoch: [206]  [200/312]  eta: 0:01:04  lr: 0.001001  min_lr: 0.001001  loss: 3.5830 (3.4298)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.1208  max mem: 31830
Epoch: [206]  [210/312]  eta: 0:00:59  lr: 0.001001  min_lr: 0.001001  loss: 3.6256 (3.4338)  weight_decay: 0.0500 (0.0500)  time: 0.6072  data: 0.2127  max mem: 31830
Epoch: [206]  [220/312]  eta: 0:00:52  lr: 0.001000  min_lr: 0.001000  loss: 3.6142 (3.4332)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0933  max mem: 31830
Epoch: [206]  [230/312]  eta: 0:00:47  lr: 0.000999  min_lr: 0.000999  loss: 3.3580 (3.4265)  weight_decay: 0.0500 (0.0500)  time: 0.5358  data: 0.1115  max mem: 31830
Epoch: [206]  [240/312]  eta: 0:00:41  lr: 0.000999  min_lr: 0.000999  loss: 3.2817 (3.4158)  weight_decay: 0.0500 (0.0500)  time: 0.6533  data: 0.2302  max mem: 31830
Epoch: [206]  [250/312]  eta: 0:00:35  lr: 0.000998  min_lr: 0.000998  loss: 3.3663 (3.4198)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.1198  max mem: 31830
Epoch: [206]  [260/312]  eta: 0:00:29  lr: 0.000998  min_lr: 0.000998  loss: 3.4362 (3.4058)  weight_decay: 0.0500 (0.0500)  time: 0.4907  data: 0.0945  max mem: 31830
Epoch: [206]  [270/312]  eta: 0:00:23  lr: 0.000997  min_lr: 0.000997  loss: 3.4362 (3.4074)  weight_decay: 0.0500 (0.0500)  time: 0.4909  data: 0.0944  max mem: 31830
Epoch: [206]  [280/312]  eta: 0:00:18  lr: 0.000996  min_lr: 0.000996  loss: 3.3830 (3.4024)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.1227  max mem: 31830
Epoch: [206]  [290/312]  eta: 0:00:12  lr: 0.000996  min_lr: 0.000996  loss: 3.3777 (3.4035)  weight_decay: 0.0500 (0.0500)  time: 0.6161  data: 0.2162  max mem: 31830
Epoch: [206]  [300/312]  eta: 0:00:06  lr: 0.000995  min_lr: 0.000995  loss: 3.5235 (3.4021)  weight_decay: 0.0500 (0.0500)  time: 0.4890  data: 0.0940  max mem: 31830
Epoch: [206]  [310/312]  eta: 0:00:01  lr: 0.000994  min_lr: 0.000994  loss: 3.6006 (3.4083)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [206]  [311/312]  eta: 0:00:00  lr: 0.000994  min_lr: 0.000994  loss: 3.6006 (3.4079)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [206] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.000994  min_lr: 0.000994  loss: 3.6006 (3.3897)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.0007 (1.0007)  acc1: 79.0365 (79.0365)  acc5: 94.5312 (94.5312)  time: 8.6691  data: 8.5012  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2814 (1.2603)  acc1: 73.3073 (73.3920)  acc5: 93.4896 (91.9680)  time: 1.0797  data: 0.9447  max mem: 31830
Test: Total time: 0:00:09 (1.0911 s / it)
* Acc@1 73.566 Acc@5 92.108 loss 1.256
Accuracy of the model on the 50000 test images: 73.6%
Max accuracy: 74.04%
Epoch: [207]  [  0/312]  eta: 1:06:53  lr: 0.000994  min_lr: 0.000994  loss: 3.0675 (3.0675)  weight_decay: 0.0500 (0.0500)  time: 12.8651  data: 8.8606  max mem: 31830
Epoch: [207]  [ 10/312]  eta: 0:09:18  lr: 0.000994  min_lr: 0.000994  loss: 3.1350 (3.1992)  weight_decay: 0.0500 (0.0500)  time: 1.8497  data: 1.0098  max mem: 31830
Epoch: [207]  [ 20/312]  eta: 0:05:37  lr: 0.000993  min_lr: 0.000993  loss: 3.3936 (3.4344)  weight_decay: 0.0500 (0.0500)  time: 0.5690  data: 0.1126  max mem: 31830
Epoch: [207]  [ 30/312]  eta: 0:04:16  lr: 0.000992  min_lr: 0.000992  loss: 3.7117 (3.5421)  weight_decay: 0.0500 (0.0500)  time: 0.3921  data: 0.0009  max mem: 31830
Epoch: [207]  [ 40/312]  eta: 0:03:33  lr: 0.000992  min_lr: 0.000992  loss: 3.6106 (3.4845)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [207]  [ 50/312]  eta: 0:03:05  lr: 0.000991  min_lr: 0.000991  loss: 3.5359 (3.4617)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0010  max mem: 31830
Epoch: [207]  [ 60/312]  eta: 0:02:46  lr: 0.000991  min_lr: 0.000991  loss: 3.4225 (3.4334)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [207]  [ 70/312]  eta: 0:02:30  lr: 0.000990  min_lr: 0.000990  loss: 3.4153 (3.4216)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0012  max mem: 31830
Epoch: [207]  [ 80/312]  eta: 0:02:23  lr: 0.000989  min_lr: 0.000989  loss: 3.3855 (3.3709)  weight_decay: 0.0500 (0.0500)  time: 0.4875  data: 0.0073  max mem: 31830
Epoch: [207]  [ 90/312]  eta: 0:02:15  lr: 0.000989  min_lr: 0.000989  loss: 3.2774 (3.3763)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0498  max mem: 31830
Epoch: [207]  [100/312]  eta: 0:02:06  lr: 0.000988  min_lr: 0.000988  loss: 3.5234 (3.3858)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0438  max mem: 31830
Epoch: [207]  [110/312]  eta: 0:01:59  lr: 0.000987  min_lr: 0.000987  loss: 3.5121 (3.3799)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0152  max mem: 31830
Epoch: [207]  [120/312]  eta: 0:01:54  lr: 0.000987  min_lr: 0.000987  loss: 3.4105 (3.3865)  weight_decay: 0.0500 (0.0500)  time: 0.5880  data: 0.0237  max mem: 31830
Epoch: [207]  [130/312]  eta: 0:01:47  lr: 0.000986  min_lr: 0.000986  loss: 3.5283 (3.3929)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0094  max mem: 31830
Epoch: [207]  [140/312]  eta: 0:01:41  lr: 0.000986  min_lr: 0.000986  loss: 3.5283 (3.3827)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.0011  max mem: 31830
Epoch: [207]  [150/312]  eta: 0:01:34  lr: 0.000985  min_lr: 0.000985  loss: 3.2806 (3.3745)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0013  max mem: 31830
Epoch: [207]  [160/312]  eta: 0:01:28  lr: 0.000984  min_lr: 0.000984  loss: 3.5127 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0198  max mem: 31830
Epoch: [207]  [170/312]  eta: 0:01:22  lr: 0.000984  min_lr: 0.000984  loss: 3.7731 (3.3933)  weight_decay: 0.0500 (0.0500)  time: 0.5624  data: 0.0198  max mem: 31830
Epoch: [207]  [180/312]  eta: 0:01:15  lr: 0.000983  min_lr: 0.000983  loss: 3.1969 (3.3828)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0078  max mem: 31830
Epoch: [207]  [190/312]  eta: 0:01:10  lr: 0.000982  min_lr: 0.000982  loss: 3.1874 (3.3800)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0139  max mem: 31830
Epoch: [207]  [200/312]  eta: 0:01:04  lr: 0.000982  min_lr: 0.000982  loss: 3.4049 (3.3829)  weight_decay: 0.0500 (0.0500)  time: 0.5903  data: 0.0077  max mem: 31830
Epoch: [207]  [210/312]  eta: 0:00:58  lr: 0.000981  min_lr: 0.000981  loss: 3.4826 (3.3813)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0075  max mem: 31830
Epoch: [207]  [220/312]  eta: 0:00:52  lr: 0.000981  min_lr: 0.000981  loss: 3.2289 (3.3714)  weight_decay: 0.0500 (0.0500)  time: 0.5493  data: 0.0075  max mem: 31830
Epoch: [207]  [230/312]  eta: 0:00:47  lr: 0.000980  min_lr: 0.000980  loss: 3.3866 (3.3692)  weight_decay: 0.0500 (0.0500)  time: 0.6358  data: 0.0095  max mem: 31830
Epoch: [207]  [240/312]  eta: 0:00:41  lr: 0.000979  min_lr: 0.000979  loss: 3.4708 (3.3653)  weight_decay: 0.0500 (0.0500)  time: 0.5681  data: 0.0097  max mem: 31830
Epoch: [207]  [250/312]  eta: 0:00:35  lr: 0.000979  min_lr: 0.000979  loss: 3.4429 (3.3643)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0019  max mem: 31830
Epoch: [207]  [260/312]  eta: 0:00:29  lr: 0.000978  min_lr: 0.000978  loss: 3.3605 (3.3658)  weight_decay: 0.0500 (0.0500)  time: 0.4934  data: 0.0012  max mem: 31830
Epoch: [207]  [270/312]  eta: 0:00:23  lr: 0.000978  min_lr: 0.000978  loss: 3.2542 (3.3661)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0069  max mem: 31830
Epoch: [207]  [280/312]  eta: 0:00:18  lr: 0.000977  min_lr: 0.000977  loss: 3.5369 (3.3749)  weight_decay: 0.0500 (0.0500)  time: 0.6219  data: 0.0081  max mem: 31830
Epoch: [207]  [290/312]  eta: 0:00:12  lr: 0.000976  min_lr: 0.000976  loss: 3.5941 (3.3795)  weight_decay: 0.0500 (0.0500)  time: 0.5733  data: 0.0164  max mem: 31830
Epoch: [207]  [300/312]  eta: 0:00:06  lr: 0.000976  min_lr: 0.000976  loss: 3.5946 (3.3784)  weight_decay: 0.0500 (0.0500)  time: 0.4563  data: 0.0149  max mem: 31830
Epoch: [207]  [310/312]  eta: 0:00:01  lr: 0.000975  min_lr: 0.000975  loss: 3.6131 (3.3830)  weight_decay: 0.0500 (0.0500)  time: 0.4054  data: 0.0001  max mem: 31830
Epoch: [207]  [311/312]  eta: 0:00:00  lr: 0.000975  min_lr: 0.000975  loss: 3.6385 (3.3850)  weight_decay: 0.0500 (0.0500)  time: 0.4052  data: 0.0001  max mem: 31830
Epoch: [207] Total time: 0:02:55 (0.5610 s / it)
Averaged stats: lr: 0.000975  min_lr: 0.000975  loss: 3.6385 (3.4006)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.0123 (1.0123)  acc1: 81.9010 (81.9010)  acc5: 94.5312 (94.5312)  time: 8.3610  data: 8.1934  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3657 (1.2823)  acc1: 74.6094 (73.8400)  acc5: 91.9271 (92.0000)  time: 1.0477  data: 0.9105  max mem: 31830
Test: Total time: 0:00:09 (1.0585 s / it)
* Acc@1 73.710 Acc@5 92.144 loss 1.276
Accuracy of the model on the 50000 test images: 73.7%
Max accuracy: 74.04%
Epoch: [208]  [  0/312]  eta: 1:01:05  lr: 0.000975  min_lr: 0.000975  loss: 3.3157 (3.3157)  weight_decay: 0.0500 (0.0500)  time: 11.7482  data: 9.8170  max mem: 31830
Epoch: [208]  [ 10/312]  eta: 0:08:24  lr: 0.000974  min_lr: 0.000974  loss: 3.5928 (3.5427)  weight_decay: 0.0500 (0.0500)  time: 1.6697  data: 0.9989  max mem: 31830
Epoch: [208]  [ 20/312]  eta: 0:05:30  lr: 0.000974  min_lr: 0.000974  loss: 3.5928 (3.4572)  weight_decay: 0.0500 (0.0500)  time: 0.6022  data: 0.0666  max mem: 31830
Epoch: [208]  [ 30/312]  eta: 0:04:12  lr: 0.000973  min_lr: 0.000973  loss: 3.3740 (3.4402)  weight_decay: 0.0500 (0.0500)  time: 0.4708  data: 0.0085  max mem: 31830
Epoch: [208]  [ 40/312]  eta: 0:03:30  lr: 0.000972  min_lr: 0.000972  loss: 3.6598 (3.4804)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0008  max mem: 31830
Epoch: [208]  [ 50/312]  eta: 0:03:09  lr: 0.000972  min_lr: 0.000972  loss: 3.5323 (3.4255)  weight_decay: 0.0500 (0.0500)  time: 0.4579  data: 0.0181  max mem: 31830
Epoch: [208]  [ 60/312]  eta: 0:02:48  lr: 0.000971  min_lr: 0.000971  loss: 3.4072 (3.4354)  weight_decay: 0.0500 (0.0500)  time: 0.4548  data: 0.0189  max mem: 31830
Epoch: [208]  [ 70/312]  eta: 0:02:38  lr: 0.000971  min_lr: 0.000971  loss: 3.3702 (3.4092)  weight_decay: 0.0500 (0.0500)  time: 0.4844  data: 0.0545  max mem: 31830
Epoch: [208]  [ 80/312]  eta: 0:02:27  lr: 0.000970  min_lr: 0.000970  loss: 3.3132 (3.4190)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0605  max mem: 31830
Epoch: [208]  [ 90/312]  eta: 0:02:18  lr: 0.000969  min_lr: 0.000969  loss: 3.5546 (3.4174)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0704  max mem: 31830
Epoch: [208]  [100/312]  eta: 0:02:14  lr: 0.000969  min_lr: 0.000969  loss: 3.4853 (3.4220)  weight_decay: 0.0500 (0.0500)  time: 0.6161  data: 0.1612  max mem: 31830
Epoch: [208]  [110/312]  eta: 0:02:03  lr: 0.000968  min_lr: 0.000968  loss: 3.4853 (3.4159)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0985  max mem: 31830
Epoch: [208]  [120/312]  eta: 0:01:55  lr: 0.000968  min_lr: 0.000968  loss: 3.1638 (3.3926)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0353  max mem: 31830
Epoch: [208]  [130/312]  eta: 0:01:49  lr: 0.000967  min_lr: 0.000967  loss: 3.4847 (3.4100)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.1382  max mem: 31830
Epoch: [208]  [140/312]  eta: 0:01:40  lr: 0.000966  min_lr: 0.000966  loss: 3.6484 (3.3968)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.1037  max mem: 31830
Epoch: [208]  [150/312]  eta: 0:01:35  lr: 0.000966  min_lr: 0.000966  loss: 3.5194 (3.4001)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1219  max mem: 31830
Epoch: [208]  [160/312]  eta: 0:01:30  lr: 0.000965  min_lr: 0.000965  loss: 3.4908 (3.3996)  weight_decay: 0.0500 (0.0500)  time: 0.6403  data: 0.2425  max mem: 31830
Epoch: [208]  [170/312]  eta: 0:01:22  lr: 0.000964  min_lr: 0.000964  loss: 3.4069 (3.4093)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.1215  max mem: 31830
Epoch: [208]  [180/312]  eta: 0:01:16  lr: 0.000964  min_lr: 0.000964  loss: 3.3708 (3.3965)  weight_decay: 0.0500 (0.0500)  time: 0.5011  data: 0.1062  max mem: 31830
Epoch: [208]  [190/312]  eta: 0:01:09  lr: 0.000963  min_lr: 0.000963  loss: 3.5307 (3.4075)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.1068  max mem: 31830
Epoch: [208]  [200/312]  eta: 0:01:04  lr: 0.000963  min_lr: 0.000963  loss: 3.5696 (3.4064)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.1109  max mem: 31830
Epoch: [208]  [210/312]  eta: 0:00:58  lr: 0.000962  min_lr: 0.000962  loss: 3.6853 (3.4146)  weight_decay: 0.0500 (0.0500)  time: 0.6199  data: 0.2192  max mem: 31830
Epoch: [208]  [220/312]  eta: 0:00:52  lr: 0.000961  min_lr: 0.000961  loss: 3.7514 (3.4213)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.1098  max mem: 31830
Epoch: [208]  [230/312]  eta: 0:00:46  lr: 0.000961  min_lr: 0.000961  loss: 3.4686 (3.4108)  weight_decay: 0.0500 (0.0500)  time: 0.5068  data: 0.1149  max mem: 31830
Epoch: [208]  [240/312]  eta: 0:00:41  lr: 0.000960  min_lr: 0.000960  loss: 2.8629 (3.4043)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.1855  max mem: 31830
Epoch: [208]  [250/312]  eta: 0:00:35  lr: 0.000960  min_lr: 0.000960  loss: 3.4393 (3.4024)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.1227  max mem: 31830
Epoch: [208]  [260/312]  eta: 0:00:29  lr: 0.000959  min_lr: 0.000959  loss: 3.4355 (3.4048)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.1535  max mem: 31830
Epoch: [208]  [270/312]  eta: 0:00:23  lr: 0.000958  min_lr: 0.000958  loss: 3.4595 (3.4061)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.1022  max mem: 31830
Epoch: [208]  [280/312]  eta: 0:00:18  lr: 0.000958  min_lr: 0.000958  loss: 3.6248 (3.4133)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.1152  max mem: 31830
Epoch: [208]  [290/312]  eta: 0:00:12  lr: 0.000957  min_lr: 0.000957  loss: 3.6456 (3.4227)  weight_decay: 0.0500 (0.0500)  time: 0.6331  data: 0.2288  max mem: 31830
Epoch: [208]  [300/312]  eta: 0:00:06  lr: 0.000956  min_lr: 0.000956  loss: 3.6456 (3.4266)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.1140  max mem: 31830
Epoch: [208]  [310/312]  eta: 0:00:01  lr: 0.000956  min_lr: 0.000956  loss: 3.6502 (3.4370)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [208]  [311/312]  eta: 0:00:00  lr: 0.000956  min_lr: 0.000956  loss: 3.6502 (3.4372)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [208] Total time: 0:02:54 (0.5595 s / it)
Averaged stats: lr: 0.000956  min_lr: 0.000956  loss: 3.6502 (3.4011)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.2410 (1.2410)  acc1: 80.5990 (80.5990)  acc5: 94.4010 (94.4010)  time: 8.1110  data: 7.9440  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.5686 (1.4582)  acc1: 73.0469 (72.8960)  acc5: 91.1458 (91.6480)  time: 1.0566  data: 0.9212  max mem: 31830
Test: Total time: 0:00:09 (1.0661 s / it)
* Acc@1 73.084 Acc@5 91.894 loss 1.454
Accuracy of the model on the 50000 test images: 73.1%
Max accuracy: 74.04%
Epoch: [209]  [  0/312]  eta: 0:58:39  lr: 0.000956  min_lr: 0.000956  loss: 4.0504 (4.0504)  weight_decay: 0.0500 (0.0500)  time: 11.2800  data: 10.7833  max mem: 31830
Epoch: [209]  [ 10/312]  eta: 0:07:59  lr: 0.000955  min_lr: 0.000955  loss: 3.2150 (3.2867)  weight_decay: 0.0500 (0.0500)  time: 1.5884  data: 0.9814  max mem: 31830
Epoch: [209]  [ 20/312]  eta: 0:05:31  lr: 0.000955  min_lr: 0.000955  loss: 3.5511 (3.4450)  weight_decay: 0.0500 (0.0500)  time: 0.6267  data: 0.0010  max mem: 31830
Epoch: [209]  [ 30/312]  eta: 0:04:12  lr: 0.000954  min_lr: 0.000954  loss: 3.5683 (3.3848)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0008  max mem: 31830
Epoch: [209]  [ 40/312]  eta: 0:03:31  lr: 0.000953  min_lr: 0.000953  loss: 3.4364 (3.3664)  weight_decay: 0.0500 (0.0500)  time: 0.4009  data: 0.0009  max mem: 31830
Epoch: [209]  [ 50/312]  eta: 0:03:07  lr: 0.000953  min_lr: 0.000953  loss: 3.4364 (3.3923)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0011  max mem: 31830
Epoch: [209]  [ 60/312]  eta: 0:02:47  lr: 0.000952  min_lr: 0.000952  loss: 3.4823 (3.4244)  weight_decay: 0.0500 (0.0500)  time: 0.4310  data: 0.0011  max mem: 31830
Epoch: [209]  [ 70/312]  eta: 0:02:37  lr: 0.000951  min_lr: 0.000951  loss: 3.4537 (3.4368)  weight_decay: 0.0500 (0.0500)  time: 0.4892  data: 0.0316  max mem: 31830
Epoch: [209]  [ 80/312]  eta: 0:02:31  lr: 0.000951  min_lr: 0.000951  loss: 3.5465 (3.4187)  weight_decay: 0.0500 (0.0500)  time: 0.6250  data: 0.0782  max mem: 31830
Epoch: [209]  [ 90/312]  eta: 0:02:18  lr: 0.000950  min_lr: 0.000950  loss: 3.5465 (3.4172)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0475  max mem: 31830
Epoch: [209]  [100/312]  eta: 0:02:11  lr: 0.000950  min_lr: 0.000950  loss: 3.4785 (3.3900)  weight_decay: 0.0500 (0.0500)  time: 0.4892  data: 0.0486  max mem: 31830
Epoch: [209]  [110/312]  eta: 0:02:01  lr: 0.000949  min_lr: 0.000949  loss: 3.4166 (3.3976)  weight_decay: 0.0500 (0.0500)  time: 0.4879  data: 0.0486  max mem: 31830
Epoch: [209]  [120/312]  eta: 0:01:54  lr: 0.000948  min_lr: 0.000948  loss: 3.5047 (3.3861)  weight_decay: 0.0500 (0.0500)  time: 0.4721  data: 0.0459  max mem: 31830
Epoch: [209]  [130/312]  eta: 0:01:49  lr: 0.000948  min_lr: 0.000948  loss: 3.3683 (3.3669)  weight_decay: 0.0500 (0.0500)  time: 0.5908  data: 0.1175  max mem: 31830
Epoch: [209]  [140/312]  eta: 0:01:41  lr: 0.000947  min_lr: 0.000947  loss: 3.6333 (3.3800)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0981  max mem: 31830
Epoch: [209]  [150/312]  eta: 0:01:34  lr: 0.000947  min_lr: 0.000947  loss: 3.6333 (3.3757)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0845  max mem: 31830
Epoch: [209]  [160/312]  eta: 0:01:29  lr: 0.000946  min_lr: 0.000946  loss: 3.2274 (3.3525)  weight_decay: 0.0500 (0.0500)  time: 0.5836  data: 0.1587  max mem: 31830
Epoch: [209]  [170/312]  eta: 0:01:21  lr: 0.000945  min_lr: 0.000945  loss: 3.5588 (3.3668)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.1008  max mem: 31830
Epoch: [209]  [180/312]  eta: 0:01:16  lr: 0.000945  min_lr: 0.000945  loss: 3.6220 (3.3654)  weight_decay: 0.0500 (0.0500)  time: 0.5457  data: 0.0977  max mem: 31830
Epoch: [209]  [190/312]  eta: 0:01:09  lr: 0.000944  min_lr: 0.000944  loss: 3.3522 (3.3715)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0976  max mem: 31830
Epoch: [209]  [200/312]  eta: 0:01:04  lr: 0.000944  min_lr: 0.000944  loss: 3.5209 (3.3798)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0652  max mem: 31830
Epoch: [209]  [210/312]  eta: 0:00:58  lr: 0.000943  min_lr: 0.000943  loss: 3.6742 (3.3937)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0918  max mem: 31830
Epoch: [209]  [220/312]  eta: 0:00:52  lr: 0.000942  min_lr: 0.000942  loss: 3.7047 (3.4006)  weight_decay: 0.0500 (0.0500)  time: 0.5004  data: 0.0632  max mem: 31830
Epoch: [209]  [230/312]  eta: 0:00:46  lr: 0.000942  min_lr: 0.000942  loss: 3.6787 (3.4098)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0968  max mem: 31830
Epoch: [209]  [240/312]  eta: 0:00:41  lr: 0.000941  min_lr: 0.000941  loss: 3.4997 (3.4130)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.0610  max mem: 31830
Epoch: [209]  [250/312]  eta: 0:00:35  lr: 0.000940  min_lr: 0.000940  loss: 3.5446 (3.4194)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0494  max mem: 31830
Epoch: [209]  [260/312]  eta: 0:00:29  lr: 0.000940  min_lr: 0.000940  loss: 3.6952 (3.4258)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.1278  max mem: 31830
Epoch: [209]  [270/312]  eta: 0:00:23  lr: 0.000939  min_lr: 0.000939  loss: 3.5617 (3.4195)  weight_decay: 0.0500 (0.0500)  time: 0.4743  data: 0.0793  max mem: 31830
Epoch: [209]  [280/312]  eta: 0:00:18  lr: 0.000939  min_lr: 0.000939  loss: 3.6128 (3.4265)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.1008  max mem: 31830
Epoch: [209]  [290/312]  eta: 0:00:12  lr: 0.000938  min_lr: 0.000938  loss: 3.6650 (3.4280)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.1763  max mem: 31830
Epoch: [209]  [300/312]  eta: 0:00:06  lr: 0.000937  min_lr: 0.000937  loss: 3.6101 (3.4359)  weight_decay: 0.0500 (0.0500)  time: 0.4618  data: 0.0761  max mem: 31830
Epoch: [209]  [310/312]  eta: 0:00:01  lr: 0.000937  min_lr: 0.000937  loss: 3.6101 (3.4372)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [209]  [311/312]  eta: 0:00:00  lr: 0.000937  min_lr: 0.000937  loss: 3.6045 (3.4355)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [209] Total time: 0:02:53 (0.5555 s / it)
Averaged stats: lr: 0.000937  min_lr: 0.000937  loss: 3.6045 (3.3998)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1634 (1.1634)  acc1: 79.5573 (79.5573)  acc5: 95.1823 (95.1823)  time: 8.5856  data: 8.4256  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4107 (1.3250)  acc1: 73.0469 (73.5680)  acc5: 92.4479 (92.1760)  time: 1.0771  data: 0.9363  max mem: 31830
Test: Total time: 0:00:09 (1.0896 s / it)
* Acc@1 74.256 Acc@5 92.460 loss 1.321
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 74.26%
Epoch: [210]  [  0/312]  eta: 0:56:38  lr: 0.000937  min_lr: 0.000937  loss: 4.0338 (4.0338)  weight_decay: 0.0500 (0.0500)  time: 10.8938  data: 9.7726  max mem: 31830
Epoch: [210]  [ 10/312]  eta: 0:08:46  lr: 0.000936  min_lr: 0.000936  loss: 3.6200 (3.4763)  weight_decay: 0.0500 (0.0500)  time: 1.7424  data: 1.0659  max mem: 31830
Epoch: [210]  [ 20/312]  eta: 0:05:28  lr: 0.000935  min_lr: 0.000935  loss: 3.7169 (3.5937)  weight_decay: 0.0500 (0.0500)  time: 0.6359  data: 0.0980  max mem: 31830
Epoch: [210]  [ 30/312]  eta: 0:04:11  lr: 0.000935  min_lr: 0.000935  loss: 3.6431 (3.5131)  weight_decay: 0.0500 (0.0500)  time: 0.4222  data: 0.0007  max mem: 31830
Epoch: [210]  [ 40/312]  eta: 0:03:29  lr: 0.000934  min_lr: 0.000934  loss: 3.4837 (3.5144)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0007  max mem: 31830
Epoch: [210]  [ 50/312]  eta: 0:03:02  lr: 0.000934  min_lr: 0.000934  loss: 3.5283 (3.5051)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0007  max mem: 31830
Epoch: [210]  [ 60/312]  eta: 0:02:43  lr: 0.000933  min_lr: 0.000933  loss: 3.5283 (3.4733)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0008  max mem: 31830
Epoch: [210]  [ 70/312]  eta: 0:02:31  lr: 0.000932  min_lr: 0.000932  loss: 3.3912 (3.4395)  weight_decay: 0.0500 (0.0500)  time: 0.4430  data: 0.0507  max mem: 31830
Epoch: [210]  [ 80/312]  eta: 0:02:23  lr: 0.000932  min_lr: 0.000932  loss: 3.1985 (3.4068)  weight_decay: 0.0500 (0.0500)  time: 0.5312  data: 0.1330  max mem: 31830
Epoch: [210]  [ 90/312]  eta: 0:02:14  lr: 0.000931  min_lr: 0.000931  loss: 3.5572 (3.4252)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.1055  max mem: 31830
Epoch: [210]  [100/312]  eta: 0:02:09  lr: 0.000931  min_lr: 0.000931  loss: 3.5041 (3.4061)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.0983  max mem: 31830
Epoch: [210]  [110/312]  eta: 0:02:00  lr: 0.000930  min_lr: 0.000930  loss: 3.1914 (3.3895)  weight_decay: 0.0500 (0.0500)  time: 0.5602  data: 0.1087  max mem: 31830
Epoch: [210]  [120/312]  eta: 0:01:53  lr: 0.000929  min_lr: 0.000929  loss: 3.3229 (3.3864)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0696  max mem: 31830
Epoch: [210]  [130/312]  eta: 0:01:48  lr: 0.000929  min_lr: 0.000929  loss: 3.3615 (3.3724)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.1055  max mem: 31830
Epoch: [210]  [140/312]  eta: 0:01:40  lr: 0.000928  min_lr: 0.000928  loss: 3.3615 (3.3593)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.1030  max mem: 31830
Epoch: [210]  [150/312]  eta: 0:01:35  lr: 0.000928  min_lr: 0.000928  loss: 3.6475 (3.3785)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0344  max mem: 31830
Epoch: [210]  [160/312]  eta: 0:01:28  lr: 0.000927  min_lr: 0.000927  loss: 3.6475 (3.3825)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0301  max mem: 31830
Epoch: [210]  [170/312]  eta: 0:01:22  lr: 0.000926  min_lr: 0.000926  loss: 3.4325 (3.3805)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0301  max mem: 31830
Epoch: [210]  [180/312]  eta: 0:01:16  lr: 0.000926  min_lr: 0.000926  loss: 3.3253 (3.3714)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0204  max mem: 31830
Epoch: [210]  [190/312]  eta: 0:01:10  lr: 0.000925  min_lr: 0.000925  loss: 3.3421 (3.3682)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0542  max mem: 31830
Epoch: [210]  [200/312]  eta: 0:01:04  lr: 0.000925  min_lr: 0.000925  loss: 3.5048 (3.3709)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.0347  max mem: 31830
Epoch: [210]  [210/312]  eta: 0:00:59  lr: 0.000924  min_lr: 0.000924  loss: 3.4991 (3.3721)  weight_decay: 0.0500 (0.0500)  time: 0.6019  data: 0.0171  max mem: 31830
Epoch: [210]  [220/312]  eta: 0:00:52  lr: 0.000923  min_lr: 0.000923  loss: 3.2358 (3.3594)  weight_decay: 0.0500 (0.0500)  time: 0.5303  data: 0.0295  max mem: 31830
Epoch: [210]  [230/312]  eta: 0:00:47  lr: 0.000923  min_lr: 0.000923  loss: 3.2175 (3.3629)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0135  max mem: 31830
Epoch: [210]  [240/312]  eta: 0:00:40  lr: 0.000922  min_lr: 0.000922  loss: 3.6033 (3.3728)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0089  max mem: 31830
Epoch: [210]  [250/312]  eta: 0:00:35  lr: 0.000922  min_lr: 0.000922  loss: 3.6959 (3.3824)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0088  max mem: 31830
Epoch: [210]  [260/312]  eta: 0:00:29  lr: 0.000921  min_lr: 0.000921  loss: 3.4687 (3.3619)  weight_decay: 0.0500 (0.0500)  time: 0.5952  data: 0.0077  max mem: 31830
Epoch: [210]  [270/312]  eta: 0:00:23  lr: 0.000920  min_lr: 0.000920  loss: 3.4934 (3.3730)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0290  max mem: 31830
Epoch: [210]  [280/312]  eta: 0:00:18  lr: 0.000920  min_lr: 0.000920  loss: 3.5976 (3.3779)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0233  max mem: 31830
Epoch: [210]  [290/312]  eta: 0:00:12  lr: 0.000919  min_lr: 0.000919  loss: 3.5463 (3.3770)  weight_decay: 0.0500 (0.0500)  time: 0.6078  data: 0.0344  max mem: 31830
Epoch: [210]  [300/312]  eta: 0:00:06  lr: 0.000918  min_lr: 0.000918  loss: 3.3236 (3.3706)  weight_decay: 0.0500 (0.0500)  time: 0.4735  data: 0.0329  max mem: 31830
Epoch: [210]  [310/312]  eta: 0:00:01  lr: 0.000918  min_lr: 0.000918  loss: 2.9810 (3.3621)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [210]  [311/312]  eta: 0:00:00  lr: 0.000918  min_lr: 0.000918  loss: 2.8156 (3.3585)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [210] Total time: 0:02:54 (0.5606 s / it)
Averaged stats: lr: 0.000918  min_lr: 0.000918  loss: 2.8156 (3.3834)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.9639 (0.9639)  acc1: 81.2500 (81.2500)  acc5: 95.3125 (95.3125)  time: 9.0227  data: 8.8629  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2550 (1.1795)  acc1: 74.4792 (74.5920)  acc5: 92.1875 (92.4000)  time: 1.1239  data: 0.9848  max mem: 31830
Test: Total time: 0:00:10 (1.1522 s / it)
* Acc@1 74.044 Acc@5 92.242 loss 1.184
Accuracy of the model on the 50000 test images: 74.0%
Max accuracy: 74.26%
Epoch: [211]  [  0/312]  eta: 1:03:54  lr: 0.000918  min_lr: 0.000918  loss: 2.9438 (2.9438)  weight_decay: 0.0500 (0.0500)  time: 12.2898  data: 11.7392  max mem: 31830
Epoch: [211]  [ 10/312]  eta: 0:08:19  lr: 0.000917  min_lr: 0.000917  loss: 3.3394 (3.2587)  weight_decay: 0.0500 (0.0500)  time: 1.6554  data: 1.0679  max mem: 31830
Epoch: [211]  [ 20/312]  eta: 0:05:27  lr: 0.000917  min_lr: 0.000917  loss: 3.4828 (3.3955)  weight_decay: 0.0500 (0.0500)  time: 0.5641  data: 0.0009  max mem: 31830
Epoch: [211]  [ 30/312]  eta: 0:04:10  lr: 0.000916  min_lr: 0.000916  loss: 3.5537 (3.3980)  weight_decay: 0.0500 (0.0500)  time: 0.4680  data: 0.0015  max mem: 31830
Epoch: [211]  [ 40/312]  eta: 0:03:29  lr: 0.000915  min_lr: 0.000915  loss: 3.5537 (3.4060)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0015  max mem: 31830
Epoch: [211]  [ 50/312]  eta: 0:03:10  lr: 0.000915  min_lr: 0.000915  loss: 3.5554 (3.4221)  weight_decay: 0.0500 (0.0500)  time: 0.4748  data: 0.0010  max mem: 31830
Epoch: [211]  [ 60/312]  eta: 0:02:49  lr: 0.000914  min_lr: 0.000914  loss: 3.4524 (3.3989)  weight_decay: 0.0500 (0.0500)  time: 0.4755  data: 0.0015  max mem: 31830
Epoch: [211]  [ 70/312]  eta: 0:02:40  lr: 0.000914  min_lr: 0.000914  loss: 3.3262 (3.4049)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0024  max mem: 31830
Epoch: [211]  [ 80/312]  eta: 0:02:30  lr: 0.000913  min_lr: 0.000913  loss: 3.5313 (3.4349)  weight_decay: 0.0500 (0.0500)  time: 0.5661  data: 0.0019  max mem: 31830
Epoch: [211]  [ 90/312]  eta: 0:02:21  lr: 0.000912  min_lr: 0.000912  loss: 3.6138 (3.4409)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0009  max mem: 31830
Epoch: [211]  [100/312]  eta: 0:02:13  lr: 0.000912  min_lr: 0.000912  loss: 3.4788 (3.4293)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.0010  max mem: 31830
Epoch: [211]  [110/312]  eta: 0:02:02  lr: 0.000911  min_lr: 0.000911  loss: 3.5475 (3.4457)  weight_decay: 0.0500 (0.0500)  time: 0.4818  data: 0.0015  max mem: 31830
Epoch: [211]  [120/312]  eta: 0:01:56  lr: 0.000911  min_lr: 0.000911  loss: 3.5618 (3.4328)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0015  max mem: 31830
Epoch: [211]  [130/312]  eta: 0:01:50  lr: 0.000910  min_lr: 0.000910  loss: 3.3007 (3.4218)  weight_decay: 0.0500 (0.0500)  time: 0.5836  data: 0.0350  max mem: 31830
Epoch: [211]  [140/312]  eta: 0:01:41  lr: 0.000909  min_lr: 0.000909  loss: 3.2292 (3.4072)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0353  max mem: 31830
Epoch: [211]  [150/312]  eta: 0:01:35  lr: 0.000909  min_lr: 0.000909  loss: 3.1523 (3.3889)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0014  max mem: 31830
Epoch: [211]  [160/312]  eta: 0:01:28  lr: 0.000908  min_lr: 0.000908  loss: 3.4588 (3.4066)  weight_decay: 0.0500 (0.0500)  time: 0.5559  data: 0.0008  max mem: 31830
Epoch: [211]  [170/312]  eta: 0:01:23  lr: 0.000908  min_lr: 0.000908  loss: 3.6131 (3.4020)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0223  max mem: 31830
Epoch: [211]  [180/312]  eta: 0:01:17  lr: 0.000907  min_lr: 0.000907  loss: 3.5662 (3.4090)  weight_decay: 0.0500 (0.0500)  time: 0.5827  data: 0.0428  max mem: 31830
Epoch: [211]  [190/312]  eta: 0:01:10  lr: 0.000906  min_lr: 0.000906  loss: 3.4799 (3.4020)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0214  max mem: 31830
Epoch: [211]  [200/312]  eta: 0:01:04  lr: 0.000906  min_lr: 0.000906  loss: 3.4799 (3.4048)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0300  max mem: 31830
Epoch: [211]  [210/312]  eta: 0:00:59  lr: 0.000905  min_lr: 0.000905  loss: 3.6468 (3.4068)  weight_decay: 0.0500 (0.0500)  time: 0.6105  data: 0.0300  max mem: 31830
Epoch: [211]  [220/312]  eta: 0:00:52  lr: 0.000905  min_lr: 0.000905  loss: 3.6322 (3.4114)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0011  max mem: 31830
Epoch: [211]  [230/312]  eta: 0:00:47  lr: 0.000904  min_lr: 0.000904  loss: 3.6322 (3.4069)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.0274  max mem: 31830
Epoch: [211]  [240/312]  eta: 0:00:41  lr: 0.000903  min_lr: 0.000903  loss: 3.3728 (3.4059)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.0273  max mem: 31830
Epoch: [211]  [250/312]  eta: 0:00:35  lr: 0.000903  min_lr: 0.000903  loss: 3.5736 (3.4183)  weight_decay: 0.0500 (0.0500)  time: 0.4960  data: 0.0009  max mem: 31830
Epoch: [211]  [260/312]  eta: 0:00:29  lr: 0.000902  min_lr: 0.000902  loss: 3.5591 (3.4188)  weight_decay: 0.0500 (0.0500)  time: 0.5562  data: 0.0007  max mem: 31830
Epoch: [211]  [270/312]  eta: 0:00:23  lr: 0.000902  min_lr: 0.000902  loss: 3.5467 (3.4222)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0008  max mem: 31830
Epoch: [211]  [280/312]  eta: 0:00:18  lr: 0.000901  min_lr: 0.000901  loss: 3.6008 (3.4293)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0067  max mem: 31830
Epoch: [211]  [290/312]  eta: 0:00:12  lr: 0.000900  min_lr: 0.000900  loss: 3.4209 (3.4206)  weight_decay: 0.0500 (0.0500)  time: 0.6144  data: 0.0063  max mem: 31830
Epoch: [211]  [300/312]  eta: 0:00:06  lr: 0.000900  min_lr: 0.000900  loss: 3.4209 (3.4255)  weight_decay: 0.0500 (0.0500)  time: 0.4905  data: 0.0002  max mem: 31830
Epoch: [211]  [310/312]  eta: 0:00:01  lr: 0.000899  min_lr: 0.000899  loss: 3.5260 (3.4262)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [211]  [311/312]  eta: 0:00:00  lr: 0.000899  min_lr: 0.000899  loss: 3.5260 (3.4270)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [211] Total time: 0:02:54 (0.5587 s / it)
Averaged stats: lr: 0.000899  min_lr: 0.000899  loss: 3.5260 (3.3913)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 1.0446 (1.0446)  acc1: 81.6406 (81.6406)  acc5: 95.4427 (95.4427)  time: 9.0579  data: 8.8906  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4279 (1.3423)  acc1: 73.1771 (74.1120)  acc5: 92.4479 (92.0160)  time: 1.1237  data: 0.9879  max mem: 31830
Test: Total time: 0:00:10 (1.1412 s / it)
* Acc@1 74.482 Acc@5 92.418 loss 1.327
Accuracy of the model on the 50000 test images: 74.5%
Max accuracy: 74.48%
Epoch: [212]  [  0/312]  eta: 1:04:37  lr: 0.000899  min_lr: 0.000899  loss: 3.6988 (3.6988)  weight_decay: 0.0500 (0.0500)  time: 12.4278  data: 12.0428  max mem: 31830
Epoch: [212]  [ 10/312]  eta: 0:08:42  lr: 0.000898  min_lr: 0.000898  loss: 3.5849 (3.4143)  weight_decay: 0.0500 (0.0500)  time: 1.7287  data: 1.0952  max mem: 31830
Epoch: [212]  [ 20/312]  eta: 0:05:25  lr: 0.000898  min_lr: 0.000898  loss: 3.5849 (3.4733)  weight_decay: 0.0500 (0.0500)  time: 0.5481  data: 0.0096  max mem: 31830
Epoch: [212]  [ 30/312]  eta: 0:04:09  lr: 0.000897  min_lr: 0.000897  loss: 3.6188 (3.4606)  weight_decay: 0.0500 (0.0500)  time: 0.4188  data: 0.0097  max mem: 31830
Epoch: [212]  [ 40/312]  eta: 0:03:27  lr: 0.000897  min_lr: 0.000897  loss: 3.4324 (3.4075)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0007  max mem: 31830
Epoch: [212]  [ 50/312]  eta: 0:03:01  lr: 0.000896  min_lr: 0.000896  loss: 3.4324 (3.4176)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0009  max mem: 31830
Epoch: [212]  [ 60/312]  eta: 0:02:42  lr: 0.000895  min_lr: 0.000895  loss: 3.6379 (3.4248)  weight_decay: 0.0500 (0.0500)  time: 0.3944  data: 0.0010  max mem: 31830
Epoch: [212]  [ 70/312]  eta: 0:02:31  lr: 0.000895  min_lr: 0.000895  loss: 3.5926 (3.4192)  weight_decay: 0.0500 (0.0500)  time: 0.4644  data: 0.0348  max mem: 31830
Epoch: [212]  [ 80/312]  eta: 0:02:24  lr: 0.000894  min_lr: 0.000894  loss: 3.5527 (3.3870)  weight_decay: 0.0500 (0.0500)  time: 0.5595  data: 0.0616  max mem: 31830
Epoch: [212]  [ 90/312]  eta: 0:02:13  lr: 0.000894  min_lr: 0.000894  loss: 3.5527 (3.4141)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0437  max mem: 31830
Epoch: [212]  [100/312]  eta: 0:02:08  lr: 0.000893  min_lr: 0.000893  loss: 3.6391 (3.4308)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0535  max mem: 31830
Epoch: [212]  [110/312]  eta: 0:02:01  lr: 0.000892  min_lr: 0.000892  loss: 3.4532 (3.4188)  weight_decay: 0.0500 (0.0500)  time: 0.5918  data: 0.0379  max mem: 31830
Epoch: [212]  [120/312]  eta: 0:01:53  lr: 0.000892  min_lr: 0.000892  loss: 3.4488 (3.4018)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0317  max mem: 31830
Epoch: [212]  [130/312]  eta: 0:01:47  lr: 0.000891  min_lr: 0.000891  loss: 3.4790 (3.3936)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0540  max mem: 31830
Epoch: [212]  [140/312]  eta: 0:01:41  lr: 0.000891  min_lr: 0.000891  loss: 3.3513 (3.3897)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0639  max mem: 31830
Epoch: [212]  [150/312]  eta: 0:01:34  lr: 0.000890  min_lr: 0.000890  loss: 3.2175 (3.3821)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0697  max mem: 31830
Epoch: [212]  [160/312]  eta: 0:01:28  lr: 0.000889  min_lr: 0.000889  loss: 3.5512 (3.3925)  weight_decay: 0.0500 (0.0500)  time: 0.4954  data: 0.0295  max mem: 31830
Epoch: [212]  [170/312]  eta: 0:01:21  lr: 0.000889  min_lr: 0.000889  loss: 3.3569 (3.3645)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0493  max mem: 31830
Epoch: [212]  [180/312]  eta: 0:01:16  lr: 0.000888  min_lr: 0.000888  loss: 2.9904 (3.3561)  weight_decay: 0.0500 (0.0500)  time: 0.5513  data: 0.0922  max mem: 31830
Epoch: [212]  [190/312]  eta: 0:01:10  lr: 0.000888  min_lr: 0.000888  loss: 3.2696 (3.3579)  weight_decay: 0.0500 (0.0500)  time: 0.5868  data: 0.0442  max mem: 31830
Epoch: [212]  [200/312]  eta: 0:01:03  lr: 0.000887  min_lr: 0.000887  loss: 3.5118 (3.3621)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0333  max mem: 31830
Epoch: [212]  [210/312]  eta: 0:00:58  lr: 0.000886  min_lr: 0.000886  loss: 3.5118 (3.3675)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.0331  max mem: 31830
Epoch: [212]  [220/312]  eta: 0:00:52  lr: 0.000886  min_lr: 0.000886  loss: 3.5860 (3.3788)  weight_decay: 0.0500 (0.0500)  time: 0.6097  data: 0.0299  max mem: 31830
Epoch: [212]  [230/312]  eta: 0:00:46  lr: 0.000885  min_lr: 0.000885  loss: 3.6338 (3.3850)  weight_decay: 0.0500 (0.0500)  time: 0.5900  data: 0.0700  max mem: 31830
Epoch: [212]  [240/312]  eta: 0:00:40  lr: 0.000885  min_lr: 0.000885  loss: 3.6308 (3.3782)  weight_decay: 0.0500 (0.0500)  time: 0.4946  data: 0.0413  max mem: 31830
Epoch: [212]  [250/312]  eta: 0:00:35  lr: 0.000884  min_lr: 0.000884  loss: 3.5208 (3.3876)  weight_decay: 0.0500 (0.0500)  time: 0.5040  data: 0.0337  max mem: 31830
Epoch: [212]  [260/312]  eta: 0:00:29  lr: 0.000883  min_lr: 0.000883  loss: 3.5208 (3.3879)  weight_decay: 0.0500 (0.0500)  time: 0.5705  data: 0.0769  max mem: 31830
Epoch: [212]  [270/312]  eta: 0:00:23  lr: 0.000883  min_lr: 0.000883  loss: 3.4959 (3.3914)  weight_decay: 0.0500 (0.0500)  time: 0.5950  data: 0.0444  max mem: 31830
Epoch: [212]  [280/312]  eta: 0:00:18  lr: 0.000882  min_lr: 0.000882  loss: 3.4944 (3.3814)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0373  max mem: 31830
Epoch: [212]  [290/312]  eta: 0:00:12  lr: 0.000882  min_lr: 0.000882  loss: 3.5486 (3.3904)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0370  max mem: 31830
Epoch: [212]  [300/312]  eta: 0:00:06  lr: 0.000881  min_lr: 0.000881  loss: 3.6088 (3.3876)  weight_decay: 0.0500 (0.0500)  time: 0.4810  data: 0.0283  max mem: 31830
Epoch: [212]  [310/312]  eta: 0:00:01  lr: 0.000880  min_lr: 0.000880  loss: 3.2433 (3.3779)  weight_decay: 0.0500 (0.0500)  time: 0.4089  data: 0.0282  max mem: 31830
Epoch: [212]  [311/312]  eta: 0:00:00  lr: 0.000880  min_lr: 0.000880  loss: 3.2433 (3.3796)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [212] Total time: 0:02:53 (0.5577 s / it)
Averaged stats: lr: 0.000880  min_lr: 0.000880  loss: 3.2433 (3.3648)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.9237 (0.9237)  acc1: 82.2917 (82.2917)  acc5: 95.0521 (95.0521)  time: 8.7420  data: 8.5746  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3651 (1.2483)  acc1: 73.6979 (74.3360)  acc5: 91.9271 (92.2720)  time: 1.0887  data: 0.9528  max mem: 31830
Test: Total time: 0:00:09 (1.1002 s / it)
* Acc@1 74.248 Acc@5 92.342 loss 1.261
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.48%
Epoch: [213]  [  0/312]  eta: 1:01:13  lr: 0.000880  min_lr: 0.000880  loss: 4.1114 (4.1114)  weight_decay: 0.0500 (0.0500)  time: 11.7727  data: 11.3676  max mem: 31830
Epoch: [213]  [ 10/312]  eta: 0:08:07  lr: 0.000880  min_lr: 0.000880  loss: 3.6206 (3.4762)  weight_decay: 0.0500 (0.0500)  time: 1.6155  data: 1.0343  max mem: 31830
Epoch: [213]  [ 20/312]  eta: 0:05:24  lr: 0.000879  min_lr: 0.000879  loss: 3.3703 (3.3157)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.0880  max mem: 31830
Epoch: [213]  [ 30/312]  eta: 0:04:08  lr: 0.000879  min_lr: 0.000879  loss: 3.3703 (3.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4794  data: 0.0886  max mem: 31830
Epoch: [213]  [ 40/312]  eta: 0:03:29  lr: 0.000878  min_lr: 0.000878  loss: 3.3650 (3.2963)  weight_decay: 0.0500 (0.0500)  time: 0.4092  data: 0.0015  max mem: 31830
Epoch: [213]  [ 50/312]  eta: 0:03:10  lr: 0.000877  min_lr: 0.000877  loss: 3.3650 (3.3251)  weight_decay: 0.0500 (0.0500)  time: 0.4825  data: 0.0564  max mem: 31830
Epoch: [213]  [ 60/312]  eta: 0:02:49  lr: 0.000877  min_lr: 0.000877  loss: 3.6350 (3.3474)  weight_decay: 0.0500 (0.0500)  time: 0.4686  data: 0.0563  max mem: 31830
Epoch: [213]  [ 70/312]  eta: 0:02:39  lr: 0.000876  min_lr: 0.000876  loss: 3.5772 (3.3734)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0946  max mem: 31830
Epoch: [213]  [ 80/312]  eta: 0:02:31  lr: 0.000876  min_lr: 0.000876  loss: 3.5657 (3.3684)  weight_decay: 0.0500 (0.0500)  time: 0.5989  data: 0.2076  max mem: 31830
Epoch: [213]  [ 90/312]  eta: 0:02:18  lr: 0.000875  min_lr: 0.000875  loss: 3.3476 (3.3746)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.1137  max mem: 31830
Epoch: [213]  [100/312]  eta: 0:02:11  lr: 0.000874  min_lr: 0.000874  loss: 3.3544 (3.3776)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.1008  max mem: 31830
Epoch: [213]  [110/312]  eta: 0:02:01  lr: 0.000874  min_lr: 0.000874  loss: 3.5390 (3.3806)  weight_decay: 0.0500 (0.0500)  time: 0.4974  data: 0.1008  max mem: 31830
Epoch: [213]  [120/312]  eta: 0:01:55  lr: 0.000873  min_lr: 0.000873  loss: 3.4050 (3.3849)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0895  max mem: 31830
Epoch: [213]  [130/312]  eta: 0:01:50  lr: 0.000873  min_lr: 0.000873  loss: 3.5691 (3.3923)  weight_decay: 0.0500 (0.0500)  time: 0.6353  data: 0.1111  max mem: 31830
Epoch: [213]  [140/312]  eta: 0:01:42  lr: 0.000872  min_lr: 0.000872  loss: 3.5106 (3.3729)  weight_decay: 0.0500 (0.0500)  time: 0.5442  data: 0.0229  max mem: 31830
Epoch: [213]  [150/312]  eta: 0:01:36  lr: 0.000871  min_lr: 0.000871  loss: 3.0806 (3.3669)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0075  max mem: 31830
Epoch: [213]  [160/312]  eta: 0:01:29  lr: 0.000871  min_lr: 0.000871  loss: 3.3682 (3.3719)  weight_decay: 0.0500 (0.0500)  time: 0.5617  data: 0.0069  max mem: 31830
Epoch: [213]  [170/312]  eta: 0:01:23  lr: 0.000870  min_lr: 0.000870  loss: 3.0974 (3.3531)  weight_decay: 0.0500 (0.0500)  time: 0.5114  data: 0.0009  max mem: 31830
Epoch: [213]  [180/312]  eta: 0:01:17  lr: 0.000870  min_lr: 0.000870  loss: 3.2681 (3.3514)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0087  max mem: 31830
Epoch: [213]  [190/312]  eta: 0:01:10  lr: 0.000869  min_lr: 0.000869  loss: 3.3173 (3.3528)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0090  max mem: 31830
Epoch: [213]  [200/312]  eta: 0:01:04  lr: 0.000868  min_lr: 0.000868  loss: 3.5347 (3.3615)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0073  max mem: 31830
Epoch: [213]  [210/312]  eta: 0:00:59  lr: 0.000868  min_lr: 0.000868  loss: 3.5347 (3.3578)  weight_decay: 0.0500 (0.0500)  time: 0.5895  data: 0.0077  max mem: 31830
Epoch: [213]  [220/312]  eta: 0:00:52  lr: 0.000867  min_lr: 0.000867  loss: 3.4312 (3.3651)  weight_decay: 0.0500 (0.0500)  time: 0.4883  data: 0.0017  max mem: 31830
Epoch: [213]  [230/312]  eta: 0:00:47  lr: 0.000867  min_lr: 0.000867  loss: 3.5766 (3.3692)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0228  max mem: 31830
Epoch: [213]  [240/312]  eta: 0:00:41  lr: 0.000866  min_lr: 0.000866  loss: 3.5517 (3.3626)  weight_decay: 0.0500 (0.0500)  time: 0.5862  data: 0.0226  max mem: 31830
Epoch: [213]  [250/312]  eta: 0:00:35  lr: 0.000865  min_lr: 0.000865  loss: 3.5517 (3.3717)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0009  max mem: 31830
Epoch: [213]  [260/312]  eta: 0:00:29  lr: 0.000865  min_lr: 0.000865  loss: 3.6830 (3.3736)  weight_decay: 0.0500 (0.0500)  time: 0.5388  data: 0.0010  max mem: 31830
Epoch: [213]  [270/312]  eta: 0:00:23  lr: 0.000864  min_lr: 0.000864  loss: 3.6347 (3.3756)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0010  max mem: 31830
Epoch: [213]  [280/312]  eta: 0:00:18  lr: 0.000864  min_lr: 0.000864  loss: 3.4372 (3.3770)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0036  max mem: 31830
Epoch: [213]  [290/312]  eta: 0:00:12  lr: 0.000863  min_lr: 0.000863  loss: 3.3838 (3.3746)  weight_decay: 0.0500 (0.0500)  time: 0.5617  data: 0.0033  max mem: 31830
Epoch: [213]  [300/312]  eta: 0:00:06  lr: 0.000863  min_lr: 0.000863  loss: 3.3838 (3.3733)  weight_decay: 0.0500 (0.0500)  time: 0.4783  data: 0.0002  max mem: 31830
Epoch: [213]  [310/312]  eta: 0:00:01  lr: 0.000862  min_lr: 0.000862  loss: 3.4757 (3.3778)  weight_decay: 0.0500 (0.0500)  time: 0.3987  data: 0.0001  max mem: 31830
Epoch: [213]  [311/312]  eta: 0:00:00  lr: 0.000862  min_lr: 0.000862  loss: 3.5293 (3.3783)  weight_decay: 0.0500 (0.0500)  time: 0.3986  data: 0.0001  max mem: 31830
Epoch: [213] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.000862  min_lr: 0.000862  loss: 3.5293 (3.3774)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.0677 (1.0677)  acc1: 80.5990 (80.5990)  acc5: 95.5729 (95.5729)  time: 8.4587  data: 8.2985  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3367 (1.2861)  acc1: 73.4375 (74.2560)  acc5: 91.9271 (92.0640)  time: 1.1015  data: 0.9669  max mem: 31830
Test: Total time: 0:00:10 (1.1168 s / it)
* Acc@1 74.302 Acc@5 92.152 loss 1.292
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 74.48%
Epoch: [214]  [  0/312]  eta: 1:00:47  lr: 0.000862  min_lr: 0.000862  loss: 3.6590 (3.6590)  weight_decay: 0.0500 (0.0500)  time: 11.6902  data: 10.0405  max mem: 31830
Epoch: [214]  [ 10/312]  eta: 0:08:18  lr: 0.000861  min_lr: 0.000861  loss: 3.6082 (3.4202)  weight_decay: 0.0500 (0.0500)  time: 1.6496  data: 1.0313  max mem: 31830
Epoch: [214]  [ 20/312]  eta: 0:05:27  lr: 0.000861  min_lr: 0.000861  loss: 3.5366 (3.4274)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0657  max mem: 31830
Epoch: [214]  [ 30/312]  eta: 0:04:10  lr: 0.000860  min_lr: 0.000860  loss: 3.4326 (3.4012)  weight_decay: 0.0500 (0.0500)  time: 0.4702  data: 0.0016  max mem: 31830
Epoch: [214]  [ 40/312]  eta: 0:03:28  lr: 0.000859  min_lr: 0.000859  loss: 3.4529 (3.4329)  weight_decay: 0.0500 (0.0500)  time: 0.3944  data: 0.0016  max mem: 31830
Epoch: [214]  [ 50/312]  eta: 0:03:04  lr: 0.000859  min_lr: 0.000859  loss: 3.4984 (3.4125)  weight_decay: 0.0500 (0.0500)  time: 0.4145  data: 0.0008  max mem: 31830
Epoch: [214]  [ 60/312]  eta: 0:02:44  lr: 0.000858  min_lr: 0.000858  loss: 3.6611 (3.4516)  weight_decay: 0.0500 (0.0500)  time: 0.4156  data: 0.0007  max mem: 31830
Epoch: [214]  [ 70/312]  eta: 0:02:40  lr: 0.000858  min_lr: 0.000858  loss: 3.6412 (3.4677)  weight_decay: 0.0500 (0.0500)  time: 0.5593  data: 0.1195  max mem: 31830
Epoch: [214]  [ 80/312]  eta: 0:02:27  lr: 0.000857  min_lr: 0.000857  loss: 3.6412 (3.4861)  weight_decay: 0.0500 (0.0500)  time: 0.5872  data: 0.1197  max mem: 31830
Epoch: [214]  [ 90/312]  eta: 0:02:17  lr: 0.000857  min_lr: 0.000857  loss: 3.7543 (3.5024)  weight_decay: 0.0500 (0.0500)  time: 0.4765  data: 0.0545  max mem: 31830
Epoch: [214]  [100/312]  eta: 0:02:11  lr: 0.000856  min_lr: 0.000856  loss: 3.4189 (3.4896)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.1112  max mem: 31830
Epoch: [214]  [110/312]  eta: 0:02:01  lr: 0.000855  min_lr: 0.000855  loss: 3.4189 (3.4745)  weight_decay: 0.0500 (0.0500)  time: 0.4981  data: 0.0580  max mem: 31830
Epoch: [214]  [120/312]  eta: 0:01:56  lr: 0.000855  min_lr: 0.000855  loss: 3.6175 (3.4634)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0643  max mem: 31830
Epoch: [214]  [130/312]  eta: 0:01:49  lr: 0.000854  min_lr: 0.000854  loss: 3.5295 (3.4386)  weight_decay: 0.0500 (0.0500)  time: 0.6099  data: 0.0828  max mem: 31830
Epoch: [214]  [140/312]  eta: 0:01:41  lr: 0.000854  min_lr: 0.000854  loss: 3.0821 (3.4179)  weight_decay: 0.0500 (0.0500)  time: 0.4894  data: 0.0332  max mem: 31830
Epoch: [214]  [150/312]  eta: 0:01:35  lr: 0.000853  min_lr: 0.000853  loss: 3.3407 (3.4173)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0537  max mem: 31830
Epoch: [214]  [160/312]  eta: 0:01:28  lr: 0.000852  min_lr: 0.000852  loss: 3.5162 (3.4310)  weight_decay: 0.0500 (0.0500)  time: 0.5628  data: 0.0733  max mem: 31830
Epoch: [214]  [170/312]  eta: 0:01:21  lr: 0.000852  min_lr: 0.000852  loss: 3.5450 (3.4294)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0490  max mem: 31830
Epoch: [214]  [180/312]  eta: 0:01:16  lr: 0.000851  min_lr: 0.000851  loss: 3.4867 (3.4314)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0779  max mem: 31830
Epoch: [214]  [190/312]  eta: 0:01:09  lr: 0.000851  min_lr: 0.000851  loss: 3.4976 (3.4248)  weight_decay: 0.0500 (0.0500)  time: 0.5549  data: 0.0632  max mem: 31830
Epoch: [214]  [200/312]  eta: 0:01:04  lr: 0.000850  min_lr: 0.000850  loss: 3.6357 (3.4246)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0640  max mem: 31830
Epoch: [214]  [210/312]  eta: 0:00:58  lr: 0.000849  min_lr: 0.000849  loss: 3.3667 (3.4198)  weight_decay: 0.0500 (0.0500)  time: 0.6245  data: 0.1105  max mem: 31830
Epoch: [214]  [220/312]  eta: 0:00:52  lr: 0.000849  min_lr: 0.000849  loss: 3.3755 (3.4258)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0474  max mem: 31830
Epoch: [214]  [230/312]  eta: 0:00:46  lr: 0.000848  min_lr: 0.000848  loss: 3.3620 (3.4124)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0451  max mem: 31830
Epoch: [214]  [240/312]  eta: 0:00:41  lr: 0.000848  min_lr: 0.000848  loss: 3.0526 (3.4058)  weight_decay: 0.0500 (0.0500)  time: 0.5748  data: 0.0453  max mem: 31830
Epoch: [214]  [250/312]  eta: 0:00:35  lr: 0.000847  min_lr: 0.000847  loss: 3.4084 (3.4114)  weight_decay: 0.0500 (0.0500)  time: 0.4808  data: 0.0067  max mem: 31830
Epoch: [214]  [260/312]  eta: 0:00:29  lr: 0.000846  min_lr: 0.000846  loss: 3.4681 (3.4041)  weight_decay: 0.0500 (0.0500)  time: 0.5951  data: 0.0504  max mem: 31830
Epoch: [214]  [270/312]  eta: 0:00:23  lr: 0.000846  min_lr: 0.000846  loss: 3.2957 (3.4023)  weight_decay: 0.0500 (0.0500)  time: 0.5689  data: 0.0450  max mem: 31830
Epoch: [214]  [280/312]  eta: 0:00:18  lr: 0.000845  min_lr: 0.000845  loss: 3.3816 (3.4017)  weight_decay: 0.0500 (0.0500)  time: 0.4617  data: 0.0066  max mem: 31830
Epoch: [214]  [290/312]  eta: 0:00:12  lr: 0.000845  min_lr: 0.000845  loss: 3.5107 (3.3992)  weight_decay: 0.0500 (0.0500)  time: 0.5895  data: 0.0613  max mem: 31830
Epoch: [214]  [300/312]  eta: 0:00:06  lr: 0.000844  min_lr: 0.000844  loss: 3.5821 (3.4053)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0555  max mem: 31830
Epoch: [214]  [310/312]  eta: 0:00:01  lr: 0.000844  min_lr: 0.000844  loss: 3.5821 (3.4052)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [214]  [311/312]  eta: 0:00:00  lr: 0.000844  min_lr: 0.000844  loss: 3.5479 (3.4051)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [214] Total time: 0:02:54 (0.5587 s / it)
Averaged stats: lr: 0.000844  min_lr: 0.000844  loss: 3.5479 (3.3758)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9876 (0.9876)  acc1: 81.5104 (81.5104)  acc5: 95.9635 (95.9635)  time: 8.8317  data: 8.6656  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3279 (1.2703)  acc1: 74.8698 (74.2240)  acc5: 92.3177 (92.4160)  time: 1.0981  data: 0.9629  max mem: 31830
Test: Total time: 0:00:10 (1.1141 s / it)
* Acc@1 73.808 Acc@5 92.158 loss 1.276
Accuracy of the model on the 50000 test images: 73.8%
Max accuracy: 74.48%
Epoch: [215]  [  0/312]  eta: 1:04:10  lr: 0.000843  min_lr: 0.000843  loss: 2.6914 (2.6914)  weight_decay: 0.0500 (0.0500)  time: 12.3401  data: 8.6839  max mem: 31830
Epoch: [215]  [ 10/312]  eta: 0:08:48  lr: 0.000843  min_lr: 0.000843  loss: 3.2142 (3.0968)  weight_decay: 0.0500 (0.0500)  time: 1.7499  data: 1.0039  max mem: 31830
Epoch: [215]  [ 20/312]  eta: 0:05:40  lr: 0.000842  min_lr: 0.000842  loss: 3.3616 (3.2737)  weight_decay: 0.0500 (0.0500)  time: 0.6065  data: 0.1585  max mem: 31830
Epoch: [215]  [ 30/312]  eta: 0:04:18  lr: 0.000842  min_lr: 0.000842  loss: 2.9923 (3.1684)  weight_decay: 0.0500 (0.0500)  time: 0.4610  data: 0.0409  max mem: 31830
Epoch: [215]  [ 40/312]  eta: 0:03:35  lr: 0.000841  min_lr: 0.000841  loss: 2.9907 (3.1982)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [215]  [ 50/312]  eta: 0:03:07  lr: 0.000841  min_lr: 0.000841  loss: 3.4606 (3.2463)  weight_decay: 0.0500 (0.0500)  time: 0.4003  data: 0.0008  max mem: 31830
Epoch: [215]  [ 60/312]  eta: 0:02:47  lr: 0.000840  min_lr: 0.000840  loss: 3.4729 (3.2513)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0008  max mem: 31830
Epoch: [215]  [ 70/312]  eta: 0:02:32  lr: 0.000839  min_lr: 0.000839  loss: 3.4996 (3.2825)  weight_decay: 0.0500 (0.0500)  time: 0.4119  data: 0.0009  max mem: 31830
Epoch: [215]  [ 80/312]  eta: 0:02:24  lr: 0.000839  min_lr: 0.000839  loss: 3.3875 (3.2885)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0077  max mem: 31830
Epoch: [215]  [ 90/312]  eta: 0:02:14  lr: 0.000838  min_lr: 0.000838  loss: 3.3875 (3.3057)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0220  max mem: 31830
Epoch: [215]  [100/312]  eta: 0:02:10  lr: 0.000838  min_lr: 0.000838  loss: 3.5523 (3.3278)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0206  max mem: 31830
Epoch: [215]  [110/312]  eta: 0:02:00  lr: 0.000837  min_lr: 0.000837  loss: 3.6484 (3.3598)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0062  max mem: 31830
Epoch: [215]  [120/312]  eta: 0:01:55  lr: 0.000836  min_lr: 0.000836  loss: 3.2272 (3.3324)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0322  max mem: 31830
Epoch: [215]  [130/312]  eta: 0:01:48  lr: 0.000836  min_lr: 0.000836  loss: 3.1008 (3.3384)  weight_decay: 0.0500 (0.0500)  time: 0.5905  data: 0.0325  max mem: 31830
Epoch: [215]  [140/312]  eta: 0:01:40  lr: 0.000835  min_lr: 0.000835  loss: 3.3024 (3.3465)  weight_decay: 0.0500 (0.0500)  time: 0.4606  data: 0.0063  max mem: 31830
Epoch: [215]  [150/312]  eta: 0:01:35  lr: 0.000835  min_lr: 0.000835  loss: 3.3024 (3.3428)  weight_decay: 0.0500 (0.0500)  time: 0.5568  data: 0.0103  max mem: 31830
Epoch: [215]  [160/312]  eta: 0:01:29  lr: 0.000834  min_lr: 0.000834  loss: 3.3193 (3.3434)  weight_decay: 0.0500 (0.0500)  time: 0.6163  data: 0.0202  max mem: 31830
Epoch: [215]  [170/312]  eta: 0:01:21  lr: 0.000833  min_lr: 0.000833  loss: 3.4151 (3.3286)  weight_decay: 0.0500 (0.0500)  time: 0.4723  data: 0.0217  max mem: 31830
Epoch: [215]  [180/312]  eta: 0:01:16  lr: 0.000833  min_lr: 0.000833  loss: 3.1455 (3.3208)  weight_decay: 0.0500 (0.0500)  time: 0.5022  data: 0.0260  max mem: 31830
Epoch: [215]  [190/312]  eta: 0:01:10  lr: 0.000832  min_lr: 0.000832  loss: 3.2005 (3.3212)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0203  max mem: 31830
Epoch: [215]  [200/312]  eta: 0:01:04  lr: 0.000832  min_lr: 0.000832  loss: 3.3818 (3.3274)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0166  max mem: 31830
Epoch: [215]  [210/312]  eta: 0:00:58  lr: 0.000831  min_lr: 0.000831  loss: 3.5812 (3.3430)  weight_decay: 0.0500 (0.0500)  time: 0.5744  data: 0.0165  max mem: 31830
Epoch: [215]  [220/312]  eta: 0:00:52  lr: 0.000831  min_lr: 0.000831  loss: 3.5812 (3.3402)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.0008  max mem: 31830
Epoch: [215]  [230/312]  eta: 0:00:46  lr: 0.000830  min_lr: 0.000830  loss: 3.3470 (3.3396)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0068  max mem: 31830
Epoch: [215]  [240/312]  eta: 0:00:41  lr: 0.000829  min_lr: 0.000829  loss: 3.2212 (3.3282)  weight_decay: 0.0500 (0.0500)  time: 0.6200  data: 0.0070  max mem: 31830
Epoch: [215]  [250/312]  eta: 0:00:35  lr: 0.000829  min_lr: 0.000829  loss: 3.0953 (3.3290)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0013  max mem: 31830
Epoch: [215]  [260/312]  eta: 0:00:29  lr: 0.000828  min_lr: 0.000828  loss: 3.2254 (3.3303)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0013  max mem: 31830
Epoch: [215]  [270/312]  eta: 0:00:23  lr: 0.000828  min_lr: 0.000828  loss: 3.4898 (3.3380)  weight_decay: 0.0500 (0.0500)  time: 0.6158  data: 0.0019  max mem: 31830
Epoch: [215]  [280/312]  eta: 0:00:18  lr: 0.000827  min_lr: 0.000827  loss: 3.5902 (3.3430)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0175  max mem: 31830
Epoch: [215]  [290/312]  eta: 0:00:12  lr: 0.000827  min_lr: 0.000827  loss: 3.4484 (3.3411)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0163  max mem: 31830
Epoch: [215]  [300/312]  eta: 0:00:06  lr: 0.000826  min_lr: 0.000826  loss: 3.2866 (3.3346)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0002  max mem: 31830
Epoch: [215]  [310/312]  eta: 0:00:01  lr: 0.000825  min_lr: 0.000825  loss: 3.2949 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [215]  [311/312]  eta: 0:00:00  lr: 0.000825  min_lr: 0.000825  loss: 3.2949 (3.3405)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [215] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.000825  min_lr: 0.000825  loss: 3.2949 (3.3641)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.9897 (0.9897)  acc1: 81.9010 (81.9010)  acc5: 95.8333 (95.8333)  time: 9.1348  data: 8.9677  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3313 (1.2255)  acc1: 73.1771 (74.8640)  acc5: 91.5365 (92.3840)  time: 1.1326  data: 0.9965  max mem: 31830
Test: Total time: 0:00:10 (1.1520 s / it)
* Acc@1 74.894 Acc@5 92.624 loss 1.223
Accuracy of the model on the 50000 test images: 74.9%
Max accuracy: 74.89%
Epoch: [216]  [  0/312]  eta: 1:05:13  lr: 0.000825  min_lr: 0.000825  loss: 3.9849 (3.9849)  weight_decay: 0.0500 (0.0500)  time: 12.5442  data: 12.1444  max mem: 31830
Epoch: [216]  [ 10/312]  eta: 0:09:33  lr: 0.000825  min_lr: 0.000825  loss: 3.3460 (3.2076)  weight_decay: 0.0500 (0.0500)  time: 1.9002  data: 1.1048  max mem: 31830
Epoch: [216]  [ 20/312]  eta: 0:05:47  lr: 0.000824  min_lr: 0.000824  loss: 3.3720 (3.3583)  weight_decay: 0.0500 (0.0500)  time: 0.6207  data: 0.0109  max mem: 31830
Epoch: [216]  [ 30/312]  eta: 0:04:23  lr: 0.000823  min_lr: 0.000823  loss: 3.5493 (3.3316)  weight_decay: 0.0500 (0.0500)  time: 0.4007  data: 0.0110  max mem: 31830
Epoch: [216]  [ 40/312]  eta: 0:03:38  lr: 0.000823  min_lr: 0.000823  loss: 3.4104 (3.3232)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0010  max mem: 31830
Epoch: [216]  [ 50/312]  eta: 0:03:09  lr: 0.000822  min_lr: 0.000822  loss: 3.5402 (3.3556)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0010  max mem: 31830
Epoch: [216]  [ 60/312]  eta: 0:02:48  lr: 0.000822  min_lr: 0.000822  loss: 3.5098 (3.3266)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [216]  [ 70/312]  eta: 0:02:32  lr: 0.000821  min_lr: 0.000821  loss: 3.0349 (3.3259)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [216]  [ 80/312]  eta: 0:02:24  lr: 0.000821  min_lr: 0.000821  loss: 3.6227 (3.3295)  weight_decay: 0.0500 (0.0500)  time: 0.4715  data: 0.0138  max mem: 31830
Epoch: [216]  [ 90/312]  eta: 0:02:14  lr: 0.000820  min_lr: 0.000820  loss: 3.2923 (3.3109)  weight_decay: 0.0500 (0.0500)  time: 0.5166  data: 0.0589  max mem: 31830
Epoch: [216]  [100/312]  eta: 0:02:07  lr: 0.000819  min_lr: 0.000819  loss: 3.3355 (3.2993)  weight_decay: 0.0500 (0.0500)  time: 0.5280  data: 0.0883  max mem: 31830
Epoch: [216]  [110/312]  eta: 0:02:00  lr: 0.000819  min_lr: 0.000819  loss: 3.4522 (3.3269)  weight_decay: 0.0500 (0.0500)  time: 0.5558  data: 0.0717  max mem: 31830
Epoch: [216]  [120/312]  eta: 0:01:53  lr: 0.000818  min_lr: 0.000818  loss: 3.4600 (3.3186)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0293  max mem: 31830
Epoch: [216]  [130/312]  eta: 0:01:46  lr: 0.000818  min_lr: 0.000818  loss: 3.4100 (3.3197)  weight_decay: 0.0500 (0.0500)  time: 0.5281  data: 0.0266  max mem: 31830
Epoch: [216]  [140/312]  eta: 0:01:40  lr: 0.000817  min_lr: 0.000817  loss: 3.2967 (3.2963)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0625  max mem: 31830
Epoch: [216]  [150/312]  eta: 0:01:33  lr: 0.000817  min_lr: 0.000817  loss: 3.2967 (3.3023)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0367  max mem: 31830
Epoch: [216]  [160/312]  eta: 0:01:29  lr: 0.000816  min_lr: 0.000816  loss: 3.2770 (3.2863)  weight_decay: 0.0500 (0.0500)  time: 0.5921  data: 0.0177  max mem: 31830
Epoch: [216]  [170/312]  eta: 0:01:22  lr: 0.000815  min_lr: 0.000815  loss: 3.2770 (3.2995)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0391  max mem: 31830
Epoch: [216]  [180/312]  eta: 0:01:16  lr: 0.000815  min_lr: 0.000815  loss: 3.5683 (3.3141)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0597  max mem: 31830
Epoch: [216]  [190/312]  eta: 0:01:10  lr: 0.000814  min_lr: 0.000814  loss: 3.4447 (3.3162)  weight_decay: 0.0500 (0.0500)  time: 0.6059  data: 0.0517  max mem: 31830
Epoch: [216]  [200/312]  eta: 0:01:04  lr: 0.000814  min_lr: 0.000814  loss: 3.4326 (3.3242)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0245  max mem: 31830
Epoch: [216]  [210/312]  eta: 0:00:58  lr: 0.000813  min_lr: 0.000813  loss: 3.5857 (3.3193)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0247  max mem: 31830
Epoch: [216]  [220/312]  eta: 0:00:52  lr: 0.000812  min_lr: 0.000812  loss: 3.4580 (3.3245)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0238  max mem: 31830
Epoch: [216]  [230/312]  eta: 0:00:46  lr: 0.000812  min_lr: 0.000812  loss: 3.5360 (3.3284)  weight_decay: 0.0500 (0.0500)  time: 0.5504  data: 0.0186  max mem: 31830
Epoch: [216]  [240/312]  eta: 0:00:41  lr: 0.000811  min_lr: 0.000811  loss: 3.6093 (3.3314)  weight_decay: 0.0500 (0.0500)  time: 0.6611  data: 0.0157  max mem: 31830
Epoch: [216]  [250/312]  eta: 0:00:35  lr: 0.000811  min_lr: 0.000811  loss: 3.6897 (3.3365)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0272  max mem: 31830
Epoch: [216]  [260/312]  eta: 0:00:29  lr: 0.000810  min_lr: 0.000810  loss: 3.4680 (3.3338)  weight_decay: 0.0500 (0.0500)  time: 0.5345  data: 0.0207  max mem: 31830
Epoch: [216]  [270/312]  eta: 0:00:24  lr: 0.000810  min_lr: 0.000810  loss: 3.4680 (3.3394)  weight_decay: 0.0500 (0.0500)  time: 0.6305  data: 0.0082  max mem: 31830
Epoch: [216]  [280/312]  eta: 0:00:18  lr: 0.000809  min_lr: 0.000809  loss: 3.6675 (3.3521)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0261  max mem: 31830
Epoch: [216]  [290/312]  eta: 0:00:12  lr: 0.000808  min_lr: 0.000808  loss: 3.5994 (3.3558)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0399  max mem: 31830
Epoch: [216]  [300/312]  eta: 0:00:06  lr: 0.000808  min_lr: 0.000808  loss: 3.2737 (3.3497)  weight_decay: 0.0500 (0.0500)  time: 0.5032  data: 0.0304  max mem: 31830
Epoch: [216]  [310/312]  eta: 0:00:01  lr: 0.000807  min_lr: 0.000807  loss: 3.4486 (3.3551)  weight_decay: 0.0500 (0.0500)  time: 0.3894  data: 0.0090  max mem: 31830
Epoch: [216]  [311/312]  eta: 0:00:00  lr: 0.000807  min_lr: 0.000807  loss: 3.5740 (3.3565)  weight_decay: 0.0500 (0.0500)  time: 0.3892  data: 0.0090  max mem: 31830
Epoch: [216] Total time: 0:02:55 (0.5623 s / it)
Averaged stats: lr: 0.000807  min_lr: 0.000807  loss: 3.5740 (3.3693)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.9683 (0.9683)  acc1: 80.7292 (80.7292)  acc5: 94.9219 (94.9219)  time: 9.1734  data: 9.0095  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2826 (1.2219)  acc1: 73.9583 (74.6240)  acc5: 92.4479 (92.3840)  time: 1.1372  data: 1.0011  max mem: 31830
Test: Total time: 0:00:10 (1.1497 s / it)
* Acc@1 74.970 Acc@5 92.662 loss 1.207
Accuracy of the model on the 50000 test images: 75.0%
Max accuracy: 74.97%
Epoch: [217]  [  0/312]  eta: 1:05:17  lr: 0.000807  min_lr: 0.000807  loss: 3.8372 (3.8372)  weight_decay: 0.0500 (0.0500)  time: 12.5561  data: 8.3010  max mem: 31830
Epoch: [217]  [ 10/312]  eta: 0:09:12  lr: 0.000807  min_lr: 0.000807  loss: 3.6189 (3.4345)  weight_decay: 0.0500 (0.0500)  time: 1.8298  data: 1.0420  max mem: 31830
Epoch: [217]  [ 20/312]  eta: 0:05:33  lr: 0.000806  min_lr: 0.000806  loss: 3.3370 (3.2546)  weight_decay: 0.0500 (0.0500)  time: 0.5719  data: 0.1584  max mem: 31830
Epoch: [217]  [ 30/312]  eta: 0:04:14  lr: 0.000805  min_lr: 0.000805  loss: 3.3560 (3.3425)  weight_decay: 0.0500 (0.0500)  time: 0.3903  data: 0.0007  max mem: 31830
Epoch: [217]  [ 40/312]  eta: 0:03:31  lr: 0.000805  min_lr: 0.000805  loss: 3.5084 (3.3008)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0007  max mem: 31830
Epoch: [217]  [ 50/312]  eta: 0:03:04  lr: 0.000804  min_lr: 0.000804  loss: 3.5267 (3.3438)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0008  max mem: 31830
Epoch: [217]  [ 60/312]  eta: 0:02:44  lr: 0.000804  min_lr: 0.000804  loss: 3.5730 (3.3492)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0014  max mem: 31830
Epoch: [217]  [ 70/312]  eta: 0:02:29  lr: 0.000803  min_lr: 0.000803  loss: 3.1690 (3.3206)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0014  max mem: 31830
Epoch: [217]  [ 80/312]  eta: 0:02:22  lr: 0.000803  min_lr: 0.000803  loss: 3.1043 (3.3087)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0348  max mem: 31830
Epoch: [217]  [ 90/312]  eta: 0:02:14  lr: 0.000802  min_lr: 0.000802  loss: 3.1774 (3.3200)  weight_decay: 0.0500 (0.0500)  time: 0.5629  data: 0.0739  max mem: 31830
Epoch: [217]  [100/312]  eta: 0:02:06  lr: 0.000801  min_lr: 0.000801  loss: 3.6536 (3.3637)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0466  max mem: 31830
Epoch: [217]  [110/312]  eta: 0:02:00  lr: 0.000801  min_lr: 0.000801  loss: 3.6536 (3.3744)  weight_decay: 0.0500 (0.0500)  time: 0.5586  data: 0.0245  max mem: 31830
Epoch: [217]  [120/312]  eta: 0:01:53  lr: 0.000800  min_lr: 0.000800  loss: 3.3881 (3.3674)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.0840  max mem: 31830
Epoch: [217]  [130/312]  eta: 0:01:47  lr: 0.000800  min_lr: 0.000800  loss: 3.3563 (3.3616)  weight_decay: 0.0500 (0.0500)  time: 0.5467  data: 0.0680  max mem: 31830
Epoch: [217]  [140/312]  eta: 0:01:41  lr: 0.000799  min_lr: 0.000799  loss: 3.2135 (3.3551)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.0349  max mem: 31830
Epoch: [217]  [150/312]  eta: 0:01:33  lr: 0.000799  min_lr: 0.000799  loss: 3.0975 (3.3299)  weight_decay: 0.0500 (0.0500)  time: 0.5034  data: 0.0548  max mem: 31830
Epoch: [217]  [160/312]  eta: 0:01:28  lr: 0.000798  min_lr: 0.000798  loss: 3.0906 (3.3217)  weight_decay: 0.0500 (0.0500)  time: 0.5417  data: 0.0996  max mem: 31830
Epoch: [217]  [170/312]  eta: 0:01:22  lr: 0.000797  min_lr: 0.000797  loss: 3.4255 (3.3255)  weight_decay: 0.0500 (0.0500)  time: 0.6120  data: 0.1351  max mem: 31830
Epoch: [217]  [180/312]  eta: 0:01:15  lr: 0.000797  min_lr: 0.000797  loss: 3.5244 (3.3374)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0736  max mem: 31830
Epoch: [217]  [190/312]  eta: 0:01:10  lr: 0.000796  min_lr: 0.000796  loss: 3.5938 (3.3461)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.1177  max mem: 31830
Epoch: [217]  [200/312]  eta: 0:01:04  lr: 0.000796  min_lr: 0.000796  loss: 3.5617 (3.3525)  weight_decay: 0.0500 (0.0500)  time: 0.6171  data: 0.1842  max mem: 31830
Epoch: [217]  [210/312]  eta: 0:00:58  lr: 0.000795  min_lr: 0.000795  loss: 3.4951 (3.3511)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.1049  max mem: 31830
Epoch: [217]  [220/312]  eta: 0:00:52  lr: 0.000794  min_lr: 0.000794  loss: 3.4488 (3.3513)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0987  max mem: 31830
Epoch: [217]  [230/312]  eta: 0:00:46  lr: 0.000794  min_lr: 0.000794  loss: 3.1684 (3.3391)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.1042  max mem: 31830
Epoch: [217]  [240/312]  eta: 0:00:41  lr: 0.000793  min_lr: 0.000793  loss: 3.4000 (3.3425)  weight_decay: 0.0500 (0.0500)  time: 0.5585  data: 0.1210  max mem: 31830
Epoch: [217]  [250/312]  eta: 0:00:35  lr: 0.000793  min_lr: 0.000793  loss: 3.5200 (3.3446)  weight_decay: 0.0500 (0.0500)  time: 0.6176  data: 0.1436  max mem: 31830
Epoch: [217]  [260/312]  eta: 0:00:29  lr: 0.000792  min_lr: 0.000792  loss: 3.4232 (3.3470)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0601  max mem: 31830
Epoch: [217]  [270/312]  eta: 0:00:23  lr: 0.000792  min_lr: 0.000792  loss: 3.4212 (3.3423)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0968  max mem: 31830
Epoch: [217]  [280/312]  eta: 0:00:18  lr: 0.000791  min_lr: 0.000791  loss: 3.5621 (3.3509)  weight_decay: 0.0500 (0.0500)  time: 0.6154  data: 0.1821  max mem: 31830
Epoch: [217]  [290/312]  eta: 0:00:12  lr: 0.000790  min_lr: 0.000790  loss: 3.5359 (3.3434)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0960  max mem: 31830
Epoch: [217]  [300/312]  eta: 0:00:06  lr: 0.000790  min_lr: 0.000790  loss: 3.4561 (3.3465)  weight_decay: 0.0500 (0.0500)  time: 0.4590  data: 0.0345  max mem: 31830
Epoch: [217]  [310/312]  eta: 0:00:01  lr: 0.000789  min_lr: 0.000789  loss: 3.5052 (3.3455)  weight_decay: 0.0500 (0.0500)  time: 0.4209  data: 0.0344  max mem: 31830
Epoch: [217]  [311/312]  eta: 0:00:00  lr: 0.000789  min_lr: 0.000789  loss: 3.5052 (3.3434)  weight_decay: 0.0500 (0.0500)  time: 0.4207  data: 0.0344  max mem: 31830
Epoch: [217] Total time: 0:02:54 (0.5605 s / it)
Averaged stats: lr: 0.000789  min_lr: 0.000789  loss: 3.5052 (3.3602)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.0563 (1.0563)  acc1: 80.2083 (80.2083)  acc5: 94.4010 (94.4010)  time: 8.9841  data: 8.8167  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3193 (1.2055)  acc1: 75.2604 (74.7680)  acc5: 91.7969 (92.4960)  time: 1.1153  data: 0.9797  max mem: 31830
Test: Total time: 0:00:10 (1.1347 s / it)
* Acc@1 75.102 Acc@5 92.762 loss 1.197
Accuracy of the model on the 50000 test images: 75.1%
Max accuracy: 75.10%
Epoch: [218]  [  0/312]  eta: 0:58:15  lr: 0.000789  min_lr: 0.000789  loss: 2.6417 (2.6417)  weight_decay: 0.0500 (0.0500)  time: 11.2025  data: 10.7967  max mem: 31830
Epoch: [218]  [ 10/312]  eta: 0:08:40  lr: 0.000789  min_lr: 0.000789  loss: 3.4534 (3.2772)  weight_decay: 0.0500 (0.0500)  time: 1.7227  data: 1.0073  max mem: 31830
Epoch: [218]  [ 20/312]  eta: 0:05:22  lr: 0.000788  min_lr: 0.000788  loss: 3.5239 (3.4014)  weight_decay: 0.0500 (0.0500)  time: 0.5990  data: 0.0145  max mem: 31830
Epoch: [218]  [ 30/312]  eta: 0:04:07  lr: 0.000788  min_lr: 0.000788  loss: 3.3721 (3.3132)  weight_decay: 0.0500 (0.0500)  time: 0.4111  data: 0.0009  max mem: 31830
Epoch: [218]  [ 40/312]  eta: 0:03:26  lr: 0.000787  min_lr: 0.000787  loss: 3.2268 (3.2960)  weight_decay: 0.0500 (0.0500)  time: 0.3980  data: 0.0010  max mem: 31830
Epoch: [218]  [ 50/312]  eta: 0:03:01  lr: 0.000786  min_lr: 0.000786  loss: 3.3528 (3.3019)  weight_decay: 0.0500 (0.0500)  time: 0.4079  data: 0.0008  max mem: 31830
Epoch: [218]  [ 60/312]  eta: 0:02:42  lr: 0.000786  min_lr: 0.000786  loss: 3.3528 (3.2990)  weight_decay: 0.0500 (0.0500)  time: 0.4066  data: 0.0007  max mem: 31830
Epoch: [218]  [ 70/312]  eta: 0:02:32  lr: 0.000785  min_lr: 0.000785  loss: 3.3479 (3.3032)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0371  max mem: 31830
Epoch: [218]  [ 80/312]  eta: 0:02:25  lr: 0.000785  min_lr: 0.000785  loss: 3.3652 (3.3201)  weight_decay: 0.0500 (0.0500)  time: 0.5678  data: 0.0836  max mem: 31830
Epoch: [218]  [ 90/312]  eta: 0:02:13  lr: 0.000784  min_lr: 0.000784  loss: 3.6016 (3.3505)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0474  max mem: 31830
Epoch: [218]  [100/312]  eta: 0:02:06  lr: 0.000784  min_lr: 0.000784  loss: 3.6016 (3.3559)  weight_decay: 0.0500 (0.0500)  time: 0.4917  data: 0.0697  max mem: 31830
Epoch: [218]  [110/312]  eta: 0:01:58  lr: 0.000783  min_lr: 0.000783  loss: 3.2443 (3.3365)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0695  max mem: 31830
Epoch: [218]  [120/312]  eta: 0:01:53  lr: 0.000782  min_lr: 0.000782  loss: 3.5049 (3.3648)  weight_decay: 0.0500 (0.0500)  time: 0.5604  data: 0.0731  max mem: 31830
Epoch: [218]  [130/312]  eta: 0:01:47  lr: 0.000782  min_lr: 0.000782  loss: 3.4995 (3.3458)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.1491  max mem: 31830
Epoch: [218]  [140/312]  eta: 0:01:40  lr: 0.000781  min_lr: 0.000781  loss: 3.2934 (3.3458)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0778  max mem: 31830
Epoch: [218]  [150/312]  eta: 0:01:34  lr: 0.000781  min_lr: 0.000781  loss: 3.3190 (3.3415)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0367  max mem: 31830
Epoch: [218]  [160/312]  eta: 0:01:27  lr: 0.000780  min_lr: 0.000780  loss: 3.5233 (3.3647)  weight_decay: 0.0500 (0.0500)  time: 0.5440  data: 0.0760  max mem: 31830
Epoch: [218]  [170/312]  eta: 0:01:21  lr: 0.000780  min_lr: 0.000780  loss: 3.6459 (3.3746)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0412  max mem: 31830
Epoch: [218]  [180/312]  eta: 0:01:15  lr: 0.000779  min_lr: 0.000779  loss: 3.5274 (3.3836)  weight_decay: 0.0500 (0.0500)  time: 0.5407  data: 0.0161  max mem: 31830
Epoch: [218]  [190/312]  eta: 0:01:09  lr: 0.000778  min_lr: 0.000778  loss: 3.5274 (3.3821)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0160  max mem: 31830
Epoch: [218]  [200/312]  eta: 0:01:04  lr: 0.000778  min_lr: 0.000778  loss: 3.4713 (3.3837)  weight_decay: 0.0500 (0.0500)  time: 0.6042  data: 0.0309  max mem: 31830
Epoch: [218]  [210/312]  eta: 0:00:58  lr: 0.000777  min_lr: 0.000777  loss: 3.4804 (3.3847)  weight_decay: 0.0500 (0.0500)  time: 0.5957  data: 0.0511  max mem: 31830
Epoch: [218]  [220/312]  eta: 0:00:52  lr: 0.000777  min_lr: 0.000777  loss: 3.4804 (3.3897)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0210  max mem: 31830
Epoch: [218]  [230/312]  eta: 0:00:47  lr: 0.000776  min_lr: 0.000776  loss: 3.5243 (3.3894)  weight_decay: 0.0500 (0.0500)  time: 0.5961  data: 0.0009  max mem: 31830
Epoch: [218]  [240/312]  eta: 0:00:40  lr: 0.000776  min_lr: 0.000776  loss: 3.5338 (3.3928)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0011  max mem: 31830
Epoch: [218]  [250/312]  eta: 0:00:35  lr: 0.000775  min_lr: 0.000775  loss: 3.6135 (3.3962)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0010  max mem: 31830
Epoch: [218]  [260/312]  eta: 0:00:29  lr: 0.000774  min_lr: 0.000774  loss: 3.5141 (3.3981)  weight_decay: 0.0500 (0.0500)  time: 0.6249  data: 0.0079  max mem: 31830
Epoch: [218]  [270/312]  eta: 0:00:23  lr: 0.000774  min_lr: 0.000774  loss: 3.3014 (3.3901)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0078  max mem: 31830
Epoch: [218]  [280/312]  eta: 0:00:18  lr: 0.000773  min_lr: 0.000773  loss: 3.2332 (3.3872)  weight_decay: 0.0500 (0.0500)  time: 0.5731  data: 0.0224  max mem: 31830
Epoch: [218]  [290/312]  eta: 0:00:12  lr: 0.000773  min_lr: 0.000773  loss: 3.4924 (3.3885)  weight_decay: 0.0500 (0.0500)  time: 0.6006  data: 0.0227  max mem: 31830
Epoch: [218]  [300/312]  eta: 0:00:06  lr: 0.000772  min_lr: 0.000772  loss: 3.5907 (3.3956)  weight_decay: 0.0500 (0.0500)  time: 0.4595  data: 0.0008  max mem: 31830
Epoch: [218]  [310/312]  eta: 0:00:01  lr: 0.000772  min_lr: 0.000772  loss: 3.6031 (3.3984)  weight_decay: 0.0500 (0.0500)  time: 0.3923  data: 0.0001  max mem: 31830
Epoch: [218]  [311/312]  eta: 0:00:00  lr: 0.000772  min_lr: 0.000772  loss: 3.5907 (3.3985)  weight_decay: 0.0500 (0.0500)  time: 0.3921  data: 0.0001  max mem: 31830
Epoch: [218] Total time: 0:02:55 (0.5623 s / it)
Averaged stats: lr: 0.000772  min_lr: 0.000772  loss: 3.5907 (3.3662)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.1665 (1.1665)  acc1: 82.5521 (82.5521)  acc5: 94.9219 (94.9219)  time: 8.2875  data: 8.1206  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4343 (1.3620)  acc1: 73.8281 (74.5280)  acc5: 92.9688 (92.4000)  time: 1.0386  data: 0.9024  max mem: 31830
Test: Total time: 0:00:09 (1.0484 s / it)
* Acc@1 74.270 Acc@5 92.404 loss 1.369
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 75.10%
Epoch: [219]  [  0/312]  eta: 1:05:06  lr: 0.000771  min_lr: 0.000771  loss: 3.7546 (3.7546)  weight_decay: 0.0500 (0.0500)  time: 12.5216  data: 10.6953  max mem: 31830
Epoch: [219]  [ 10/312]  eta: 0:08:43  lr: 0.000771  min_lr: 0.000771  loss: 3.4469 (3.4356)  weight_decay: 0.0500 (0.0500)  time: 1.7332  data: 0.9728  max mem: 31830
Epoch: [219]  [ 20/312]  eta: 0:05:27  lr: 0.000770  min_lr: 0.000770  loss: 3.4469 (3.5110)  weight_decay: 0.0500 (0.0500)  time: 0.5512  data: 0.0191  max mem: 31830
Epoch: [219]  [ 30/312]  eta: 0:04:10  lr: 0.000770  min_lr: 0.000770  loss: 3.4765 (3.4677)  weight_decay: 0.0500 (0.0500)  time: 0.4213  data: 0.0192  max mem: 31830
Epoch: [219]  [ 40/312]  eta: 0:03:28  lr: 0.000769  min_lr: 0.000769  loss: 3.5263 (3.4695)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0008  max mem: 31830
Epoch: [219]  [ 50/312]  eta: 0:03:04  lr: 0.000769  min_lr: 0.000769  loss: 3.5460 (3.4894)  weight_decay: 0.0500 (0.0500)  time: 0.4218  data: 0.0009  max mem: 31830
Epoch: [219]  [ 60/312]  eta: 0:02:44  lr: 0.000768  min_lr: 0.000768  loss: 3.5378 (3.4732)  weight_decay: 0.0500 (0.0500)  time: 0.4197  data: 0.0010  max mem: 31830
Epoch: [219]  [ 70/312]  eta: 0:02:36  lr: 0.000767  min_lr: 0.000767  loss: 3.4973 (3.4665)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0133  max mem: 31830
Epoch: [219]  [ 80/312]  eta: 0:02:29  lr: 0.000767  min_lr: 0.000767  loss: 3.5465 (3.4685)  weight_decay: 0.0500 (0.0500)  time: 0.6093  data: 0.0182  max mem: 31830
Epoch: [219]  [ 90/312]  eta: 0:02:18  lr: 0.000766  min_lr: 0.000766  loss: 3.5639 (3.4475)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0058  max mem: 31830
Epoch: [219]  [100/312]  eta: 0:02:13  lr: 0.000766  min_lr: 0.000766  loss: 3.2407 (3.4447)  weight_decay: 0.0500 (0.0500)  time: 0.5732  data: 0.0206  max mem: 31830
Epoch: [219]  [110/312]  eta: 0:02:02  lr: 0.000765  min_lr: 0.000765  loss: 3.6267 (3.4759)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0208  max mem: 31830
Epoch: [219]  [120/312]  eta: 0:01:56  lr: 0.000765  min_lr: 0.000765  loss: 3.6511 (3.4738)  weight_decay: 0.0500 (0.0500)  time: 0.4797  data: 0.0081  max mem: 31830
Epoch: [219]  [130/312]  eta: 0:01:49  lr: 0.000764  min_lr: 0.000764  loss: 3.5187 (3.4528)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0278  max mem: 31830
Epoch: [219]  [140/312]  eta: 0:01:41  lr: 0.000764  min_lr: 0.000764  loss: 3.6403 (3.4638)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0205  max mem: 31830
Epoch: [219]  [150/312]  eta: 0:01:35  lr: 0.000763  min_lr: 0.000763  loss: 3.7139 (3.4560)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0009  max mem: 31830
Epoch: [219]  [160/312]  eta: 0:01:29  lr: 0.000762  min_lr: 0.000762  loss: 3.6369 (3.4491)  weight_decay: 0.0500 (0.0500)  time: 0.5949  data: 0.0011  max mem: 31830
Epoch: [219]  [170/312]  eta: 0:01:22  lr: 0.000762  min_lr: 0.000762  loss: 3.1947 (3.4266)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0062  max mem: 31830
Epoch: [219]  [180/312]  eta: 0:01:17  lr: 0.000761  min_lr: 0.000761  loss: 3.3378 (3.4206)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0242  max mem: 31830
Epoch: [219]  [190/312]  eta: 0:01:10  lr: 0.000761  min_lr: 0.000761  loss: 3.3378 (3.4078)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0191  max mem: 31830
Epoch: [219]  [200/312]  eta: 0:01:04  lr: 0.000760  min_lr: 0.000760  loss: 3.5836 (3.4179)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0056  max mem: 31830
Epoch: [219]  [210/312]  eta: 0:00:58  lr: 0.000760  min_lr: 0.000760  loss: 3.6475 (3.4175)  weight_decay: 0.0500 (0.0500)  time: 0.6076  data: 0.0258  max mem: 31830
Epoch: [219]  [220/312]  eta: 0:00:52  lr: 0.000759  min_lr: 0.000759  loss: 3.5611 (3.4221)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0213  max mem: 31830
Epoch: [219]  [230/312]  eta: 0:00:47  lr: 0.000758  min_lr: 0.000758  loss: 3.5056 (3.4223)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0012  max mem: 31830
Epoch: [219]  [240/312]  eta: 0:00:41  lr: 0.000758  min_lr: 0.000758  loss: 3.6380 (3.4328)  weight_decay: 0.0500 (0.0500)  time: 0.5768  data: 0.0012  max mem: 31830
Epoch: [219]  [250/312]  eta: 0:00:35  lr: 0.000757  min_lr: 0.000757  loss: 3.4570 (3.4216)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0072  max mem: 31830
Epoch: [219]  [260/312]  eta: 0:00:29  lr: 0.000757  min_lr: 0.000757  loss: 3.1166 (3.4194)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0080  max mem: 31830
Epoch: [219]  [270/312]  eta: 0:00:23  lr: 0.000756  min_lr: 0.000756  loss: 3.5270 (3.4199)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0018  max mem: 31830
Epoch: [219]  [280/312]  eta: 0:00:18  lr: 0.000756  min_lr: 0.000756  loss: 3.5011 (3.4132)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0084  max mem: 31830
Epoch: [219]  [290/312]  eta: 0:00:12  lr: 0.000755  min_lr: 0.000755  loss: 3.3994 (3.4123)  weight_decay: 0.0500 (0.0500)  time: 0.5919  data: 0.0080  max mem: 31830
Epoch: [219]  [300/312]  eta: 0:00:06  lr: 0.000755  min_lr: 0.000755  loss: 3.6003 (3.4143)  weight_decay: 0.0500 (0.0500)  time: 0.4728  data: 0.0002  max mem: 31830
Epoch: [219]  [310/312]  eta: 0:00:01  lr: 0.000754  min_lr: 0.000754  loss: 3.2785 (3.4059)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0001  max mem: 31830
Epoch: [219]  [311/312]  eta: 0:00:00  lr: 0.000754  min_lr: 0.000754  loss: 3.1575 (3.4051)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [219] Total time: 0:02:54 (0.5583 s / it)
Averaged stats: lr: 0.000754  min_lr: 0.000754  loss: 3.1575 (3.3621)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.0135 (1.0135)  acc1: 81.7708 (81.7708)  acc5: 95.4427 (95.4427)  time: 8.5740  data: 8.4038  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3677 (1.2701)  acc1: 74.4792 (74.7840)  acc5: 92.3177 (92.3520)  time: 1.0778  data: 0.9399  max mem: 31830
Test: Total time: 0:00:09 (1.0875 s / it)
* Acc@1 74.982 Acc@5 92.644 loss 1.270
Accuracy of the model on the 50000 test images: 75.0%
Max accuracy: 75.10%
Epoch: [220]  [  0/312]  eta: 1:01:20  lr: 0.000754  min_lr: 0.000754  loss: 3.6170 (3.6170)  weight_decay: 0.0500 (0.0500)  time: 11.7958  data: 10.1086  max mem: 31830
Epoch: [220]  [ 10/312]  eta: 0:08:45  lr: 0.000753  min_lr: 0.000753  loss: 3.6219 (3.5503)  weight_decay: 0.0500 (0.0500)  time: 1.7414  data: 1.0492  max mem: 31830
Epoch: [220]  [ 20/312]  eta: 0:05:30  lr: 0.000753  min_lr: 0.000753  loss: 3.6219 (3.5488)  weight_decay: 0.0500 (0.0500)  time: 0.5985  data: 0.1094  max mem: 31830
Epoch: [220]  [ 30/312]  eta: 0:04:12  lr: 0.000752  min_lr: 0.000752  loss: 3.5790 (3.4996)  weight_decay: 0.0500 (0.0500)  time: 0.4304  data: 0.0382  max mem: 31830
Epoch: [220]  [ 40/312]  eta: 0:03:30  lr: 0.000752  min_lr: 0.000752  loss: 3.4677 (3.3792)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0008  max mem: 31830
Epoch: [220]  [ 50/312]  eta: 0:03:03  lr: 0.000751  min_lr: 0.000751  loss: 3.3797 (3.3740)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0019  max mem: 31830
Epoch: [220]  [ 60/312]  eta: 0:02:43  lr: 0.000750  min_lr: 0.000750  loss: 3.3797 (3.3474)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0019  max mem: 31830
Epoch: [220]  [ 70/312]  eta: 0:02:33  lr: 0.000750  min_lr: 0.000750  loss: 3.3360 (3.3403)  weight_decay: 0.0500 (0.0500)  time: 0.4735  data: 0.0754  max mem: 31830
Epoch: [220]  [ 80/312]  eta: 0:02:24  lr: 0.000749  min_lr: 0.000749  loss: 3.6069 (3.3937)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.1360  max mem: 31830
Epoch: [220]  [ 90/312]  eta: 0:02:13  lr: 0.000749  min_lr: 0.000749  loss: 3.7212 (3.4035)  weight_decay: 0.0500 (0.0500)  time: 0.4855  data: 0.0905  max mem: 31830
Epoch: [220]  [100/312]  eta: 0:02:09  lr: 0.000748  min_lr: 0.000748  loss: 3.4524 (3.3845)  weight_decay: 0.0500 (0.0500)  time: 0.5774  data: 0.1203  max mem: 31830
Epoch: [220]  [110/312]  eta: 0:01:59  lr: 0.000748  min_lr: 0.000748  loss: 3.4524 (3.3922)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0912  max mem: 31830
Epoch: [220]  [120/312]  eta: 0:01:53  lr: 0.000747  min_lr: 0.000747  loss: 3.4150 (3.3778)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0706  max mem: 31830
Epoch: [220]  [130/312]  eta: 0:01:48  lr: 0.000747  min_lr: 0.000747  loss: 3.2862 (3.3658)  weight_decay: 0.0500 (0.0500)  time: 0.6064  data: 0.1431  max mem: 31830
Epoch: [220]  [140/312]  eta: 0:01:39  lr: 0.000746  min_lr: 0.000746  loss: 3.2733 (3.3517)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0741  max mem: 31830
Epoch: [220]  [150/312]  eta: 0:01:34  lr: 0.000745  min_lr: 0.000745  loss: 3.3559 (3.3479)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0858  max mem: 31830
Epoch: [220]  [160/312]  eta: 0:01:28  lr: 0.000745  min_lr: 0.000745  loss: 3.4581 (3.3430)  weight_decay: 0.0500 (0.0500)  time: 0.6096  data: 0.1549  max mem: 31830
Epoch: [220]  [170/312]  eta: 0:01:22  lr: 0.000744  min_lr: 0.000744  loss: 3.4581 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0911  max mem: 31830
Epoch: [220]  [180/312]  eta: 0:01:16  lr: 0.000744  min_lr: 0.000744  loss: 3.5123 (3.3423)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0820  max mem: 31830
Epoch: [220]  [190/312]  eta: 0:01:09  lr: 0.000743  min_lr: 0.000743  loss: 3.5481 (3.3597)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0617  max mem: 31830
Epoch: [220]  [200/312]  eta: 0:01:04  lr: 0.000743  min_lr: 0.000743  loss: 3.5268 (3.3591)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0738  max mem: 31830
Epoch: [220]  [210/312]  eta: 0:00:58  lr: 0.000742  min_lr: 0.000742  loss: 3.3932 (3.3519)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.1394  max mem: 31830
Epoch: [220]  [220/312]  eta: 0:00:52  lr: 0.000742  min_lr: 0.000742  loss: 3.4591 (3.3491)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0664  max mem: 31830
Epoch: [220]  [230/312]  eta: 0:00:46  lr: 0.000741  min_lr: 0.000741  loss: 3.3865 (3.3477)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0910  max mem: 31830
Epoch: [220]  [240/312]  eta: 0:00:41  lr: 0.000740  min_lr: 0.000740  loss: 3.2220 (3.3337)  weight_decay: 0.0500 (0.0500)  time: 0.6018  data: 0.1742  max mem: 31830
Epoch: [220]  [250/312]  eta: 0:00:35  lr: 0.000740  min_lr: 0.000740  loss: 3.4581 (3.3447)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0849  max mem: 31830
Epoch: [220]  [260/312]  eta: 0:00:29  lr: 0.000739  min_lr: 0.000739  loss: 3.6447 (3.3458)  weight_decay: 0.0500 (0.0500)  time: 0.5322  data: 0.0747  max mem: 31830
Epoch: [220]  [270/312]  eta: 0:00:23  lr: 0.000739  min_lr: 0.000739  loss: 3.4803 (3.3384)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0742  max mem: 31830
Epoch: [220]  [280/312]  eta: 0:00:18  lr: 0.000738  min_lr: 0.000738  loss: 3.4803 (3.3442)  weight_decay: 0.0500 (0.0500)  time: 0.5905  data: 0.0579  max mem: 31830
Epoch: [220]  [290/312]  eta: 0:00:12  lr: 0.000738  min_lr: 0.000738  loss: 3.5233 (3.3494)  weight_decay: 0.0500 (0.0500)  time: 0.5730  data: 0.0987  max mem: 31830
Epoch: [220]  [300/312]  eta: 0:00:06  lr: 0.000737  min_lr: 0.000737  loss: 3.5891 (3.3579)  weight_decay: 0.0500 (0.0500)  time: 0.4760  data: 0.0417  max mem: 31830
Epoch: [220]  [310/312]  eta: 0:00:01  lr: 0.000736  min_lr: 0.000736  loss: 3.5737 (3.3533)  weight_decay: 0.0500 (0.0500)  time: 0.4284  data: 0.0001  max mem: 31830
Epoch: [220]  [311/312]  eta: 0:00:00  lr: 0.000736  min_lr: 0.000736  loss: 3.5891 (3.3544)  weight_decay: 0.0500 (0.0500)  time: 0.4016  data: 0.0001  max mem: 31830
Epoch: [220] Total time: 0:02:54 (0.5596 s / it)
Averaged stats: lr: 0.000736  min_lr: 0.000736  loss: 3.5891 (3.3470)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.0224 (1.0224)  acc1: 82.4219 (82.4219)  acc5: 95.7031 (95.7031)  time: 8.7160  data: 8.5487  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2995 (1.2272)  acc1: 75.7812 (74.9920)  acc5: 91.7969 (92.4800)  time: 1.0851  data: 0.9499  max mem: 31830
Test: Total time: 0:00:09 (1.0953 s / it)
* Acc@1 74.950 Acc@5 92.668 loss 1.219
Accuracy of the model on the 50000 test images: 75.0%
Max accuracy: 75.10%
Epoch: [221]  [  0/312]  eta: 1:02:00  lr: 0.000736  min_lr: 0.000736  loss: 2.5616 (2.5616)  weight_decay: 0.0500 (0.0500)  time: 11.9250  data: 11.5355  max mem: 31830
Epoch: [221]  [ 10/312]  eta: 0:08:54  lr: 0.000736  min_lr: 0.000736  loss: 3.5780 (3.4892)  weight_decay: 0.0500 (0.0500)  time: 1.7688  data: 1.0492  max mem: 31830
Epoch: [221]  [ 20/312]  eta: 0:05:38  lr: 0.000735  min_lr: 0.000735  loss: 3.5780 (3.5126)  weight_decay: 0.0500 (0.0500)  time: 0.6196  data: 0.0006  max mem: 31830
Epoch: [221]  [ 30/312]  eta: 0:04:17  lr: 0.000735  min_lr: 0.000735  loss: 3.4686 (3.4379)  weight_decay: 0.0500 (0.0500)  time: 0.4428  data: 0.0008  max mem: 31830
Epoch: [221]  [ 40/312]  eta: 0:03:34  lr: 0.000734  min_lr: 0.000734  loss: 3.2654 (3.4211)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0013  max mem: 31830
Epoch: [221]  [ 50/312]  eta: 0:03:06  lr: 0.000734  min_lr: 0.000734  loss: 3.2114 (3.4223)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0012  max mem: 31830
Epoch: [221]  [ 60/312]  eta: 0:02:46  lr: 0.000733  min_lr: 0.000733  loss: 3.5902 (3.4219)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0009  max mem: 31830
Epoch: [221]  [ 70/312]  eta: 0:02:34  lr: 0.000732  min_lr: 0.000732  loss: 3.4823 (3.3985)  weight_decay: 0.0500 (0.0500)  time: 0.4543  data: 0.0010  max mem: 31830
Epoch: [221]  [ 80/312]  eta: 0:02:23  lr: 0.000732  min_lr: 0.000732  loss: 3.3214 (3.3995)  weight_decay: 0.0500 (0.0500)  time: 0.4866  data: 0.0009  max mem: 31830
Epoch: [221]  [ 90/312]  eta: 0:02:17  lr: 0.000731  min_lr: 0.000731  loss: 3.1419 (3.3555)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0163  max mem: 31830
Epoch: [221]  [100/312]  eta: 0:02:11  lr: 0.000731  min_lr: 0.000731  loss: 3.3635 (3.3724)  weight_decay: 0.0500 (0.0500)  time: 0.6307  data: 0.0253  max mem: 31830
Epoch: [221]  [110/312]  eta: 0:02:01  lr: 0.000730  min_lr: 0.000730  loss: 3.6536 (3.4038)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0189  max mem: 31830
Epoch: [221]  [120/312]  eta: 0:01:56  lr: 0.000730  min_lr: 0.000730  loss: 3.6536 (3.3845)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0100  max mem: 31830
Epoch: [221]  [130/312]  eta: 0:01:50  lr: 0.000729  min_lr: 0.000729  loss: 3.1693 (3.3661)  weight_decay: 0.0500 (0.0500)  time: 0.6417  data: 0.0282  max mem: 31830
Epoch: [221]  [140/312]  eta: 0:01:42  lr: 0.000729  min_lr: 0.000729  loss: 3.0404 (3.3484)  weight_decay: 0.0500 (0.0500)  time: 0.5307  data: 0.0281  max mem: 31830
Epoch: [221]  [150/312]  eta: 0:01:35  lr: 0.000728  min_lr: 0.000728  loss: 3.2009 (3.3475)  weight_decay: 0.0500 (0.0500)  time: 0.4862  data: 0.0020  max mem: 31830
Epoch: [221]  [160/312]  eta: 0:01:28  lr: 0.000727  min_lr: 0.000727  loss: 3.3831 (3.3453)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.0022  max mem: 31830
Epoch: [221]  [170/312]  eta: 0:01:23  lr: 0.000727  min_lr: 0.000727  loss: 3.2544 (3.3382)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0014  max mem: 31830
Epoch: [221]  [180/312]  eta: 0:01:17  lr: 0.000726  min_lr: 0.000726  loss: 3.2558 (3.3322)  weight_decay: 0.0500 (0.0500)  time: 0.6188  data: 0.0200  max mem: 31830
Epoch: [221]  [190/312]  eta: 0:01:10  lr: 0.000726  min_lr: 0.000726  loss: 3.2558 (3.3271)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0197  max mem: 31830
Epoch: [221]  [200/312]  eta: 0:01:05  lr: 0.000725  min_lr: 0.000725  loss: 3.3774 (3.3300)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0010  max mem: 31830
Epoch: [221]  [210/312]  eta: 0:00:59  lr: 0.000725  min_lr: 0.000725  loss: 3.4340 (3.3310)  weight_decay: 0.0500 (0.0500)  time: 0.6279  data: 0.0010  max mem: 31830
Epoch: [221]  [220/312]  eta: 0:00:53  lr: 0.000724  min_lr: 0.000724  loss: 3.4999 (3.3350)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0008  max mem: 31830
Epoch: [221]  [230/312]  eta: 0:00:47  lr: 0.000724  min_lr: 0.000724  loss: 3.4999 (3.3410)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0093  max mem: 31830
Epoch: [221]  [240/312]  eta: 0:00:41  lr: 0.000723  min_lr: 0.000723  loss: 3.3651 (3.3354)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0094  max mem: 31830
Epoch: [221]  [250/312]  eta: 0:00:35  lr: 0.000722  min_lr: 0.000722  loss: 3.4010 (3.3372)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.0145  max mem: 31830
Epoch: [221]  [260/312]  eta: 0:00:30  lr: 0.000722  min_lr: 0.000722  loss: 3.4487 (3.3363)  weight_decay: 0.0500 (0.0500)  time: 0.6048  data: 0.0630  max mem: 31830
Epoch: [221]  [270/312]  eta: 0:00:24  lr: 0.000721  min_lr: 0.000721  loss: 3.4386 (3.3444)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0506  max mem: 31830
Epoch: [221]  [280/312]  eta: 0:00:18  lr: 0.000721  min_lr: 0.000721  loss: 3.5995 (3.3448)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0038  max mem: 31830
Epoch: [221]  [290/312]  eta: 0:00:12  lr: 0.000720  min_lr: 0.000720  loss: 3.3736 (3.3348)  weight_decay: 0.0500 (0.0500)  time: 0.5832  data: 0.0305  max mem: 31830
Epoch: [221]  [300/312]  eta: 0:00:06  lr: 0.000720  min_lr: 0.000720  loss: 3.3372 (3.3353)  weight_decay: 0.0500 (0.0500)  time: 0.4712  data: 0.0282  max mem: 31830
Epoch: [221]  [310/312]  eta: 0:00:01  lr: 0.000719  min_lr: 0.000719  loss: 3.3171 (3.3321)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0002  max mem: 31830
Epoch: [221]  [311/312]  eta: 0:00:00  lr: 0.000719  min_lr: 0.000719  loss: 3.3171 (3.3341)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [221] Total time: 0:02:55 (0.5639 s / it)
Averaged stats: lr: 0.000719  min_lr: 0.000719  loss: 3.3171 (3.3503)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.9302 (0.9302)  acc1: 82.0312 (82.0312)  acc5: 95.4427 (95.4427)  time: 8.6274  data: 8.4600  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2820 (1.1958)  acc1: 75.1302 (75.3280)  acc5: 91.5365 (92.2240)  time: 1.0802  data: 0.9401  max mem: 31830
Test: Total time: 0:00:10 (1.1115 s / it)
* Acc@1 75.178 Acc@5 92.644 loss 1.200
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.18%
Epoch: [222]  [  0/312]  eta: 0:56:47  lr: 0.000719  min_lr: 0.000719  loss: 3.5469 (3.5469)  weight_decay: 0.0500 (0.0500)  time: 10.9218  data: 8.3844  max mem: 31830
Epoch: [222]  [ 10/312]  eta: 0:09:01  lr: 0.000719  min_lr: 0.000719  loss: 3.5469 (3.3500)  weight_decay: 0.0500 (0.0500)  time: 1.7938  data: 1.0406  max mem: 31830
Epoch: [222]  [ 20/312]  eta: 0:05:40  lr: 0.000718  min_lr: 0.000718  loss: 3.3317 (3.2950)  weight_decay: 0.0500 (0.0500)  time: 0.6784  data: 0.1977  max mem: 31830
Epoch: [222]  [ 30/312]  eta: 0:04:18  lr: 0.000717  min_lr: 0.000717  loss: 3.4665 (3.3739)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0451  max mem: 31830
Epoch: [222]  [ 40/312]  eta: 0:03:35  lr: 0.000717  min_lr: 0.000717  loss: 3.6128 (3.3531)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0011  max mem: 31830
Epoch: [222]  [ 50/312]  eta: 0:03:06  lr: 0.000716  min_lr: 0.000716  loss: 3.2437 (3.3183)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0010  max mem: 31830
Epoch: [222]  [ 60/312]  eta: 0:02:46  lr: 0.000716  min_lr: 0.000716  loss: 3.3261 (3.3410)  weight_decay: 0.0500 (0.0500)  time: 0.3939  data: 0.0012  max mem: 31830
Epoch: [222]  [ 70/312]  eta: 0:02:33  lr: 0.000715  min_lr: 0.000715  loss: 3.4707 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.4308  data: 0.0015  max mem: 31830
Epoch: [222]  [ 80/312]  eta: 0:02:23  lr: 0.000715  min_lr: 0.000715  loss: 3.4180 (3.3504)  weight_decay: 0.0500 (0.0500)  time: 0.4853  data: 0.0017  max mem: 31830
Epoch: [222]  [ 90/312]  eta: 0:02:17  lr: 0.000714  min_lr: 0.000714  loss: 3.4073 (3.3577)  weight_decay: 0.0500 (0.0500)  time: 0.5617  data: 0.0165  max mem: 31830
Epoch: [222]  [100/312]  eta: 0:02:09  lr: 0.000714  min_lr: 0.000714  loss: 3.5068 (3.3699)  weight_decay: 0.0500 (0.0500)  time: 0.5887  data: 0.0219  max mem: 31830
Epoch: [222]  [110/312]  eta: 0:02:02  lr: 0.000713  min_lr: 0.000713  loss: 3.5555 (3.3652)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0322  max mem: 31830
Epoch: [222]  [120/312]  eta: 0:01:54  lr: 0.000712  min_lr: 0.000712  loss: 3.4328 (3.3682)  weight_decay: 0.0500 (0.0500)  time: 0.5314  data: 0.0381  max mem: 31830
Epoch: [222]  [130/312]  eta: 0:01:49  lr: 0.000712  min_lr: 0.000712  loss: 3.3922 (3.3671)  weight_decay: 0.0500 (0.0500)  time: 0.5840  data: 0.0129  max mem: 31830
Epoch: [222]  [140/312]  eta: 0:01:41  lr: 0.000711  min_lr: 0.000711  loss: 3.2015 (3.3503)  weight_decay: 0.0500 (0.0500)  time: 0.5483  data: 0.0237  max mem: 31830
Epoch: [222]  [150/312]  eta: 0:01:35  lr: 0.000711  min_lr: 0.000711  loss: 3.1514 (3.3429)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0446  max mem: 31830
Epoch: [222]  [160/312]  eta: 0:01:28  lr: 0.000710  min_lr: 0.000710  loss: 3.5873 (3.3627)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0219  max mem: 31830
Epoch: [222]  [170/312]  eta: 0:01:22  lr: 0.000710  min_lr: 0.000710  loss: 3.6872 (3.3794)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0095  max mem: 31830
Epoch: [222]  [180/312]  eta: 0:01:17  lr: 0.000709  min_lr: 0.000709  loss: 3.6355 (3.3857)  weight_decay: 0.0500 (0.0500)  time: 0.6198  data: 0.0095  max mem: 31830
Epoch: [222]  [190/312]  eta: 0:01:10  lr: 0.000709  min_lr: 0.000709  loss: 3.6355 (3.3871)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0224  max mem: 31830
Epoch: [222]  [200/312]  eta: 0:01:04  lr: 0.000708  min_lr: 0.000708  loss: 3.5379 (3.3887)  weight_decay: 0.0500 (0.0500)  time: 0.5185  data: 0.0223  max mem: 31830
Epoch: [222]  [210/312]  eta: 0:00:59  lr: 0.000708  min_lr: 0.000708  loss: 3.4318 (3.3763)  weight_decay: 0.0500 (0.0500)  time: 0.6458  data: 0.0008  max mem: 31830
Epoch: [222]  [220/312]  eta: 0:00:53  lr: 0.000707  min_lr: 0.000707  loss: 3.2534 (3.3749)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0016  max mem: 31830
Epoch: [222]  [230/312]  eta: 0:00:47  lr: 0.000706  min_lr: 0.000706  loss: 3.2516 (3.3695)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0023  max mem: 31830
Epoch: [222]  [240/312]  eta: 0:00:41  lr: 0.000706  min_lr: 0.000706  loss: 3.2436 (3.3615)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0015  max mem: 31830
Epoch: [222]  [250/312]  eta: 0:00:35  lr: 0.000705  min_lr: 0.000705  loss: 3.4212 (3.3610)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0290  max mem: 31830
Epoch: [222]  [260/312]  eta: 0:00:29  lr: 0.000705  min_lr: 0.000705  loss: 3.4816 (3.3603)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.0290  max mem: 31830
Epoch: [222]  [270/312]  eta: 0:00:24  lr: 0.000704  min_lr: 0.000704  loss: 3.3004 (3.3601)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0160  max mem: 31830
Epoch: [222]  [280/312]  eta: 0:00:18  lr: 0.000704  min_lr: 0.000704  loss: 3.3972 (3.3620)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0255  max mem: 31830
Epoch: [222]  [290/312]  eta: 0:00:12  lr: 0.000703  min_lr: 0.000703  loss: 3.4372 (3.3622)  weight_decay: 0.0500 (0.0500)  time: 0.5745  data: 0.0101  max mem: 31830
Epoch: [222]  [300/312]  eta: 0:00:06  lr: 0.000703  min_lr: 0.000703  loss: 3.3099 (3.3557)  weight_decay: 0.0500 (0.0500)  time: 0.4781  data: 0.0002  max mem: 31830
Epoch: [222]  [310/312]  eta: 0:00:01  lr: 0.000702  min_lr: 0.000702  loss: 3.1240 (3.3480)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [222]  [311/312]  eta: 0:00:00  lr: 0.000702  min_lr: 0.000702  loss: 3.1424 (3.3473)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [222] Total time: 0:02:55 (0.5631 s / it)
Averaged stats: lr: 0.000702  min_lr: 0.000702  loss: 3.1424 (3.3701)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.9422 (0.9422)  acc1: 82.6823 (82.6823)  acc5: 95.9635 (95.9635)  time: 9.0331  data: 8.8721  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2923 (1.1744)  acc1: 75.3906 (75.4400)  acc5: 92.3177 (92.8320)  time: 1.1243  data: 0.9859  max mem: 31830
Test: Total time: 0:00:10 (1.1567 s / it)
* Acc@1 75.224 Acc@5 93.032 loss 1.165
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.22%
Epoch: [223]  [  0/312]  eta: 1:02:28  lr: 0.000702  min_lr: 0.000702  loss: 3.1478 (3.1478)  weight_decay: 0.0500 (0.0500)  time: 12.0142  data: 8.5588  max mem: 31830
Epoch: [223]  [ 10/312]  eta: 0:08:28  lr: 0.000701  min_lr: 0.000701  loss: 3.1478 (3.1112)  weight_decay: 0.0500 (0.0500)  time: 1.6829  data: 1.0192  max mem: 31830
Epoch: [223]  [ 20/312]  eta: 0:05:24  lr: 0.000701  min_lr: 0.000701  loss: 3.3940 (3.2270)  weight_decay: 0.0500 (0.0500)  time: 0.5646  data: 0.1379  max mem: 31830
Epoch: [223]  [ 30/312]  eta: 0:04:08  lr: 0.000700  min_lr: 0.000700  loss: 3.2557 (3.2144)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0057  max mem: 31830
Epoch: [223]  [ 40/312]  eta: 0:03:27  lr: 0.000700  min_lr: 0.000700  loss: 3.3921 (3.2771)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [223]  [ 50/312]  eta: 0:03:02  lr: 0.000699  min_lr: 0.000699  loss: 3.3921 (3.2397)  weight_decay: 0.0500 (0.0500)  time: 0.4125  data: 0.0008  max mem: 31830
Epoch: [223]  [ 60/312]  eta: 0:02:43  lr: 0.000699  min_lr: 0.000699  loss: 3.1388 (3.2534)  weight_decay: 0.0500 (0.0500)  time: 0.4096  data: 0.0008  max mem: 31830
Epoch: [223]  [ 70/312]  eta: 0:02:34  lr: 0.000698  min_lr: 0.000698  loss: 3.3245 (3.2541)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0334  max mem: 31830
Epoch: [223]  [ 80/312]  eta: 0:02:27  lr: 0.000698  min_lr: 0.000698  loss: 3.3156 (3.2489)  weight_decay: 0.0500 (0.0500)  time: 0.5939  data: 0.0540  max mem: 31830
Epoch: [223]  [ 90/312]  eta: 0:02:16  lr: 0.000697  min_lr: 0.000697  loss: 3.3189 (3.2738)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0418  max mem: 31830
Epoch: [223]  [100/312]  eta: 0:02:10  lr: 0.000696  min_lr: 0.000696  loss: 3.4209 (3.2678)  weight_decay: 0.0500 (0.0500)  time: 0.5409  data: 0.0346  max mem: 31830
Epoch: [223]  [110/312]  eta: 0:02:00  lr: 0.000696  min_lr: 0.000696  loss: 3.4491 (3.2871)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0142  max mem: 31830
Epoch: [223]  [120/312]  eta: 0:01:54  lr: 0.000695  min_lr: 0.000695  loss: 3.4667 (3.2880)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0067  max mem: 31830
Epoch: [223]  [130/312]  eta: 0:01:49  lr: 0.000695  min_lr: 0.000695  loss: 3.4770 (3.3014)  weight_decay: 0.0500 (0.0500)  time: 0.6186  data: 0.0327  max mem: 31830
Epoch: [223]  [140/312]  eta: 0:01:40  lr: 0.000694  min_lr: 0.000694  loss: 3.4770 (3.3106)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0269  max mem: 31830
Epoch: [223]  [150/312]  eta: 0:01:35  lr: 0.000694  min_lr: 0.000694  loss: 3.3852 (3.3002)  weight_decay: 0.0500 (0.0500)  time: 0.5334  data: 0.0286  max mem: 31830
Epoch: [223]  [160/312]  eta: 0:01:30  lr: 0.000693  min_lr: 0.000693  loss: 3.4201 (3.3239)  weight_decay: 0.0500 (0.0500)  time: 0.6575  data: 0.0285  max mem: 31830
Epoch: [223]  [170/312]  eta: 0:01:23  lr: 0.000693  min_lr: 0.000693  loss: 3.6127 (3.3312)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0184  max mem: 31830
Epoch: [223]  [180/312]  eta: 0:01:17  lr: 0.000692  min_lr: 0.000692  loss: 3.5094 (3.3335)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0185  max mem: 31830
Epoch: [223]  [190/312]  eta: 0:01:10  lr: 0.000692  min_lr: 0.000692  loss: 3.6064 (3.3555)  weight_decay: 0.0500 (0.0500)  time: 0.4903  data: 0.0012  max mem: 31830
Epoch: [223]  [200/312]  eta: 0:01:04  lr: 0.000691  min_lr: 0.000691  loss: 3.5797 (3.3501)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0272  max mem: 31830
Epoch: [223]  [210/312]  eta: 0:00:59  lr: 0.000690  min_lr: 0.000690  loss: 3.3116 (3.3366)  weight_decay: 0.0500 (0.0500)  time: 0.6252  data: 0.0269  max mem: 31830
Epoch: [223]  [220/312]  eta: 0:00:52  lr: 0.000690  min_lr: 0.000690  loss: 3.3962 (3.3399)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0076  max mem: 31830
Epoch: [223]  [230/312]  eta: 0:00:47  lr: 0.000689  min_lr: 0.000689  loss: 3.5535 (3.3457)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.0237  max mem: 31830
Epoch: [223]  [240/312]  eta: 0:00:41  lr: 0.000689  min_lr: 0.000689  loss: 3.4943 (3.3388)  weight_decay: 0.0500 (0.0500)  time: 0.6143  data: 0.0337  max mem: 31830
Epoch: [223]  [250/312]  eta: 0:00:35  lr: 0.000688  min_lr: 0.000688  loss: 3.3895 (3.3379)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0262  max mem: 31830
Epoch: [223]  [260/312]  eta: 0:00:29  lr: 0.000688  min_lr: 0.000688  loss: 3.4517 (3.3409)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0094  max mem: 31830
Epoch: [223]  [270/312]  eta: 0:00:23  lr: 0.000687  min_lr: 0.000687  loss: 3.4898 (3.3481)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0015  max mem: 31830
Epoch: [223]  [280/312]  eta: 0:00:18  lr: 0.000687  min_lr: 0.000687  loss: 3.4898 (3.3386)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0069  max mem: 31830
Epoch: [223]  [290/312]  eta: 0:00:12  lr: 0.000686  min_lr: 0.000686  loss: 3.4631 (3.3406)  weight_decay: 0.0500 (0.0500)  time: 0.6371  data: 0.0145  max mem: 31830
Epoch: [223]  [300/312]  eta: 0:00:06  lr: 0.000686  min_lr: 0.000686  loss: 3.1861 (3.3205)  weight_decay: 0.0500 (0.0500)  time: 0.4889  data: 0.0089  max mem: 31830
Epoch: [223]  [310/312]  eta: 0:00:01  lr: 0.000685  min_lr: 0.000685  loss: 2.9387 (3.3216)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [223]  [311/312]  eta: 0:00:00  lr: 0.000685  min_lr: 0.000685  loss: 2.9387 (3.3205)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [223] Total time: 0:02:54 (0.5605 s / it)
Averaged stats: lr: 0.000685  min_lr: 0.000685  loss: 2.9387 (3.3583)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8828 (0.8828)  acc1: 82.4219 (82.4219)  acc5: 96.6146 (96.6146)  time: 8.5324  data: 8.3707  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2625 (1.1612)  acc1: 74.7396 (75.3280)  acc5: 92.3177 (92.8480)  time: 1.0667  data: 0.9302  max mem: 31830
Test: Total time: 0:00:09 (1.0920 s / it)
* Acc@1 75.324 Acc@5 92.996 loss 1.155
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.32%
Epoch: [224]  [  0/312]  eta: 1:01:59  lr: 0.000685  min_lr: 0.000685  loss: 3.7036 (3.7036)  weight_decay: 0.0500 (0.0500)  time: 11.9225  data: 10.8101  max mem: 31830
Epoch: [224]  [ 10/312]  eta: 0:08:54  lr: 0.000684  min_lr: 0.000684  loss: 3.5017 (3.3406)  weight_decay: 0.0500 (0.0500)  time: 1.7690  data: 1.0487  max mem: 31830
Epoch: [224]  [ 20/312]  eta: 0:05:26  lr: 0.000684  min_lr: 0.000684  loss: 3.5017 (3.3861)  weight_decay: 0.0500 (0.0500)  time: 0.5775  data: 0.0428  max mem: 31830
Epoch: [224]  [ 30/312]  eta: 0:04:09  lr: 0.000683  min_lr: 0.000683  loss: 3.5432 (3.3600)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0071  max mem: 31830
Epoch: [224]  [ 40/312]  eta: 0:03:28  lr: 0.000683  min_lr: 0.000683  loss: 3.6060 (3.3844)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0010  max mem: 31830
Epoch: [224]  [ 50/312]  eta: 0:03:01  lr: 0.000682  min_lr: 0.000682  loss: 3.6404 (3.4321)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0008  max mem: 31830
Epoch: [224]  [ 60/312]  eta: 0:02:42  lr: 0.000682  min_lr: 0.000682  loss: 3.4529 (3.3907)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0009  max mem: 31830
Epoch: [224]  [ 70/312]  eta: 0:02:30  lr: 0.000681  min_lr: 0.000681  loss: 3.1589 (3.3874)  weight_decay: 0.0500 (0.0500)  time: 0.4422  data: 0.0223  max mem: 31830
Epoch: [224]  [ 80/312]  eta: 0:02:23  lr: 0.000681  min_lr: 0.000681  loss: 3.2535 (3.3577)  weight_decay: 0.0500 (0.0500)  time: 0.5393  data: 0.0606  max mem: 31830
Epoch: [224]  [ 90/312]  eta: 0:02:13  lr: 0.000680  min_lr: 0.000680  loss: 3.2386 (3.3432)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0394  max mem: 31830
Epoch: [224]  [100/312]  eta: 0:02:06  lr: 0.000680  min_lr: 0.000680  loss: 3.0616 (3.3242)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0274  max mem: 31830
Epoch: [224]  [110/312]  eta: 0:01:59  lr: 0.000679  min_lr: 0.000679  loss: 3.1788 (3.3192)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0410  max mem: 31830
Epoch: [224]  [120/312]  eta: 0:01:53  lr: 0.000678  min_lr: 0.000678  loss: 3.0616 (3.2935)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0200  max mem: 31830
Epoch: [224]  [130/312]  eta: 0:01:46  lr: 0.000678  min_lr: 0.000678  loss: 3.4252 (3.3053)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0203  max mem: 31830
Epoch: [224]  [140/312]  eta: 0:01:39  lr: 0.000677  min_lr: 0.000677  loss: 3.4988 (3.2919)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0288  max mem: 31830
Epoch: [224]  [150/312]  eta: 0:01:33  lr: 0.000677  min_lr: 0.000677  loss: 3.2309 (3.2782)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0147  max mem: 31830
Epoch: [224]  [160/312]  eta: 0:01:27  lr: 0.000676  min_lr: 0.000676  loss: 3.4242 (3.2902)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0330  max mem: 31830
Epoch: [224]  [170/312]  eta: 0:01:21  lr: 0.000676  min_lr: 0.000676  loss: 3.4360 (3.2866)  weight_decay: 0.0500 (0.0500)  time: 0.5879  data: 0.0329  max mem: 31830
Epoch: [224]  [180/312]  eta: 0:01:15  lr: 0.000675  min_lr: 0.000675  loss: 3.2381 (3.2918)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0297  max mem: 31830
Epoch: [224]  [190/312]  eta: 0:01:09  lr: 0.000675  min_lr: 0.000675  loss: 3.6203 (3.3091)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0581  max mem: 31830
Epoch: [224]  [200/312]  eta: 0:01:03  lr: 0.000674  min_lr: 0.000674  loss: 3.5956 (3.3112)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0293  max mem: 31830
Epoch: [224]  [210/312]  eta: 0:00:58  lr: 0.000674  min_lr: 0.000674  loss: 3.2471 (3.2949)  weight_decay: 0.0500 (0.0500)  time: 0.5504  data: 0.0356  max mem: 31830
Epoch: [224]  [220/312]  eta: 0:00:52  lr: 0.000673  min_lr: 0.000673  loss: 3.0760 (3.2943)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0407  max mem: 31830
Epoch: [224]  [230/312]  eta: 0:00:46  lr: 0.000673  min_lr: 0.000673  loss: 3.3697 (3.3002)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0065  max mem: 31830
Epoch: [224]  [240/312]  eta: 0:00:40  lr: 0.000672  min_lr: 0.000672  loss: 3.5124 (3.3009)  weight_decay: 0.0500 (0.0500)  time: 0.5665  data: 0.0294  max mem: 31830
Epoch: [224]  [250/312]  eta: 0:00:34  lr: 0.000671  min_lr: 0.000671  loss: 2.9867 (3.2932)  weight_decay: 0.0500 (0.0500)  time: 0.5629  data: 0.0559  max mem: 31830
Epoch: [224]  [260/312]  eta: 0:00:29  lr: 0.000671  min_lr: 0.000671  loss: 3.2493 (3.3008)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0541  max mem: 31830
Epoch: [224]  [270/312]  eta: 0:00:23  lr: 0.000670  min_lr: 0.000670  loss: 3.6750 (3.3090)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0849  max mem: 31830
Epoch: [224]  [280/312]  eta: 0:00:17  lr: 0.000670  min_lr: 0.000670  loss: 3.4360 (3.3071)  weight_decay: 0.0500 (0.0500)  time: 0.5504  data: 0.0903  max mem: 31830
Epoch: [224]  [290/312]  eta: 0:00:12  lr: 0.000669  min_lr: 0.000669  loss: 3.2915 (3.2985)  weight_decay: 0.0500 (0.0500)  time: 0.5764  data: 0.0935  max mem: 31830
Epoch: [224]  [300/312]  eta: 0:00:06  lr: 0.000669  min_lr: 0.000669  loss: 3.3242 (3.3050)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0737  max mem: 31830
Epoch: [224]  [310/312]  eta: 0:00:01  lr: 0.000668  min_lr: 0.000668  loss: 3.5498 (3.3113)  weight_decay: 0.0500 (0.0500)  time: 0.3929  data: 0.0123  max mem: 31830
Epoch: [224]  [311/312]  eta: 0:00:00  lr: 0.000668  min_lr: 0.000668  loss: 3.5498 (3.3132)  weight_decay: 0.0500 (0.0500)  time: 0.3930  data: 0.0123  max mem: 31830
Epoch: [224] Total time: 0:02:53 (0.5548 s / it)
Averaged stats: lr: 0.000668  min_lr: 0.000668  loss: 3.5498 (3.3359)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0630 (1.0630)  acc1: 80.9896 (80.9896)  acc5: 96.3542 (96.3542)  time: 8.7803  data: 8.6146  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4490 (1.3482)  acc1: 74.4792 (74.3200)  acc5: 91.9271 (92.3680)  time: 1.0945  data: 0.9573  max mem: 31830
Test: Total time: 0:00:09 (1.1085 s / it)
* Acc@1 74.936 Acc@5 92.770 loss 1.335
Accuracy of the model on the 50000 test images: 74.9%
Max accuracy: 75.32%
Epoch: [225]  [  0/312]  eta: 1:05:54  lr: 0.000668  min_lr: 0.000668  loss: 3.2662 (3.2662)  weight_decay: 0.0500 (0.0500)  time: 12.6751  data: 10.3493  max mem: 31830
Epoch: [225]  [ 10/312]  eta: 0:08:45  lr: 0.000668  min_lr: 0.000668  loss: 3.5220 (3.3735)  weight_decay: 0.0500 (0.0500)  time: 1.7387  data: 1.0346  max mem: 31830
Epoch: [225]  [ 20/312]  eta: 0:05:32  lr: 0.000667  min_lr: 0.000667  loss: 3.4597 (3.3046)  weight_decay: 0.0500 (0.0500)  time: 0.5612  data: 0.0574  max mem: 31830
Epoch: [225]  [ 30/312]  eta: 0:04:13  lr: 0.000667  min_lr: 0.000667  loss: 3.1743 (3.2445)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0064  max mem: 31830
Epoch: [225]  [ 40/312]  eta: 0:03:31  lr: 0.000666  min_lr: 0.000666  loss: 3.4092 (3.3067)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0009  max mem: 31830
Epoch: [225]  [ 50/312]  eta: 0:03:04  lr: 0.000665  min_lr: 0.000665  loss: 3.4609 (3.2811)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0010  max mem: 31830
Epoch: [225]  [ 60/312]  eta: 0:02:44  lr: 0.000665  min_lr: 0.000665  loss: 3.3087 (3.2637)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0011  max mem: 31830
Epoch: [225]  [ 70/312]  eta: 0:02:32  lr: 0.000664  min_lr: 0.000664  loss: 3.5588 (3.3023)  weight_decay: 0.0500 (0.0500)  time: 0.4441  data: 0.0013  max mem: 31830
Epoch: [225]  [ 80/312]  eta: 0:02:26  lr: 0.000664  min_lr: 0.000664  loss: 3.5588 (3.2737)  weight_decay: 0.0500 (0.0500)  time: 0.5611  data: 0.0280  max mem: 31830
Epoch: [225]  [ 90/312]  eta: 0:02:14  lr: 0.000663  min_lr: 0.000663  loss: 3.4424 (3.2980)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0277  max mem: 31830
Epoch: [225]  [100/312]  eta: 0:02:09  lr: 0.000663  min_lr: 0.000663  loss: 3.5906 (3.3214)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.0245  max mem: 31830
Epoch: [225]  [110/312]  eta: 0:01:59  lr: 0.000662  min_lr: 0.000662  loss: 3.2321 (3.3052)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0363  max mem: 31830
Epoch: [225]  [120/312]  eta: 0:01:53  lr: 0.000662  min_lr: 0.000662  loss: 3.2321 (3.3046)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0268  max mem: 31830
Epoch: [225]  [130/312]  eta: 0:01:48  lr: 0.000661  min_lr: 0.000661  loss: 3.5463 (3.3079)  weight_decay: 0.0500 (0.0500)  time: 0.6145  data: 0.0290  max mem: 31830
Epoch: [225]  [140/312]  eta: 0:01:40  lr: 0.000661  min_lr: 0.000661  loss: 3.4996 (3.3203)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0325  max mem: 31830
Epoch: [225]  [150/312]  eta: 0:01:34  lr: 0.000660  min_lr: 0.000660  loss: 3.5611 (3.3334)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0235  max mem: 31830
Epoch: [225]  [160/312]  eta: 0:01:28  lr: 0.000660  min_lr: 0.000660  loss: 3.5934 (3.3323)  weight_decay: 0.0500 (0.0500)  time: 0.5692  data: 0.0119  max mem: 31830
Epoch: [225]  [170/312]  eta: 0:01:21  lr: 0.000659  min_lr: 0.000659  loss: 3.3840 (3.3292)  weight_decay: 0.0500 (0.0500)  time: 0.5302  data: 0.0341  max mem: 31830
Epoch: [225]  [180/312]  eta: 0:01:16  lr: 0.000659  min_lr: 0.000659  loss: 3.5091 (3.3458)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0488  max mem: 31830
Epoch: [225]  [190/312]  eta: 0:01:09  lr: 0.000658  min_lr: 0.000658  loss: 3.5798 (3.3562)  weight_decay: 0.0500 (0.0500)  time: 0.5039  data: 0.0214  max mem: 31830
Epoch: [225]  [200/312]  eta: 0:01:04  lr: 0.000657  min_lr: 0.000657  loss: 3.5636 (3.3536)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.0145  max mem: 31830
Epoch: [225]  [210/312]  eta: 0:00:58  lr: 0.000657  min_lr: 0.000657  loss: 3.4702 (3.3604)  weight_decay: 0.0500 (0.0500)  time: 0.6679  data: 0.0421  max mem: 31830
Epoch: [225]  [220/312]  eta: 0:00:52  lr: 0.000656  min_lr: 0.000656  loss: 3.5030 (3.3639)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0428  max mem: 31830
Epoch: [225]  [230/312]  eta: 0:00:46  lr: 0.000656  min_lr: 0.000656  loss: 3.4713 (3.3590)  weight_decay: 0.0500 (0.0500)  time: 0.4847  data: 0.0152  max mem: 31830
Epoch: [225]  [240/312]  eta: 0:00:41  lr: 0.000655  min_lr: 0.000655  loss: 3.2548 (3.3540)  weight_decay: 0.0500 (0.0500)  time: 0.6222  data: 0.0009  max mem: 31830
Epoch: [225]  [250/312]  eta: 0:00:35  lr: 0.000655  min_lr: 0.000655  loss: 3.4036 (3.3578)  weight_decay: 0.0500 (0.0500)  time: 0.5569  data: 0.0133  max mem: 31830
Epoch: [225]  [260/312]  eta: 0:00:29  lr: 0.000654  min_lr: 0.000654  loss: 3.4810 (3.3583)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0290  max mem: 31830
Epoch: [225]  [270/312]  eta: 0:00:23  lr: 0.000654  min_lr: 0.000654  loss: 3.5473 (3.3559)  weight_decay: 0.0500 (0.0500)  time: 0.4898  data: 0.0166  max mem: 31830
Epoch: [225]  [280/312]  eta: 0:00:18  lr: 0.000653  min_lr: 0.000653  loss: 3.5675 (3.3565)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0039  max mem: 31830
Epoch: [225]  [290/312]  eta: 0:00:12  lr: 0.000653  min_lr: 0.000653  loss: 3.4783 (3.3515)  weight_decay: 0.0500 (0.0500)  time: 0.6288  data: 0.0237  max mem: 31830
Epoch: [225]  [300/312]  eta: 0:00:06  lr: 0.000652  min_lr: 0.000652  loss: 3.3065 (3.3487)  weight_decay: 0.0500 (0.0500)  time: 0.4846  data: 0.0204  max mem: 31830
Epoch: [225]  [310/312]  eta: 0:00:01  lr: 0.000652  min_lr: 0.000652  loss: 3.3969 (3.3488)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0002  max mem: 31830
Epoch: [225]  [311/312]  eta: 0:00:00  lr: 0.000652  min_lr: 0.000652  loss: 3.3969 (3.3473)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [225] Total time: 0:02:54 (0.5584 s / it)
Averaged stats: lr: 0.000652  min_lr: 0.000652  loss: 3.3969 (3.3507)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.0338 (1.0338)  acc1: 82.2917 (82.2917)  acc5: 95.5729 (95.5729)  time: 8.8452  data: 8.6778  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3226 (1.2374)  acc1: 73.5677 (74.4800)  acc5: 92.5781 (92.7040)  time: 1.1008  data: 0.9643  max mem: 31830
Test: Total time: 0:00:10 (1.1160 s / it)
* Acc@1 75.050 Acc@5 92.694 loss 1.238
Accuracy of the model on the 50000 test images: 75.1%
Max accuracy: 75.32%
Epoch: [226]  [  0/312]  eta: 1:03:34  lr: 0.000651  min_lr: 0.000651  loss: 3.3993 (3.3993)  weight_decay: 0.0500 (0.0500)  time: 12.2251  data: 11.5642  max mem: 31830
Epoch: [226]  [ 10/312]  eta: 0:07:55  lr: 0.000651  min_lr: 0.000651  loss: 3.4219 (3.4561)  weight_decay: 0.0500 (0.0500)  time: 1.5755  data: 1.0519  max mem: 31830
Epoch: [226]  [ 20/312]  eta: 0:05:26  lr: 0.000650  min_lr: 0.000650  loss: 3.4219 (3.4832)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.1143  max mem: 31830
Epoch: [226]  [ 30/312]  eta: 0:04:09  lr: 0.000650  min_lr: 0.000650  loss: 3.5384 (3.4834)  weight_decay: 0.0500 (0.0500)  time: 0.5061  data: 0.1144  max mem: 31830
Epoch: [226]  [ 40/312]  eta: 0:03:33  lr: 0.000649  min_lr: 0.000649  loss: 3.4750 (3.4015)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0395  max mem: 31830
Epoch: [226]  [ 50/312]  eta: 0:03:12  lr: 0.000649  min_lr: 0.000649  loss: 3.4388 (3.4064)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.1055  max mem: 31830
Epoch: [226]  [ 60/312]  eta: 0:02:51  lr: 0.000648  min_lr: 0.000648  loss: 3.5505 (3.4099)  weight_decay: 0.0500 (0.0500)  time: 0.4648  data: 0.0667  max mem: 31830
Epoch: [226]  [ 70/312]  eta: 0:02:41  lr: 0.000648  min_lr: 0.000648  loss: 3.4229 (3.3748)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.1040  max mem: 31830
Epoch: [226]  [ 80/312]  eta: 0:02:31  lr: 0.000647  min_lr: 0.000647  loss: 3.2398 (3.3714)  weight_decay: 0.0500 (0.0500)  time: 0.5765  data: 0.1845  max mem: 31830
Epoch: [226]  [ 90/312]  eta: 0:02:18  lr: 0.000647  min_lr: 0.000647  loss: 3.5797 (3.3964)  weight_decay: 0.0500 (0.0500)  time: 0.4745  data: 0.0812  max mem: 31830
Epoch: [226]  [100/312]  eta: 0:02:12  lr: 0.000646  min_lr: 0.000646  loss: 3.5797 (3.3910)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0936  max mem: 31830
Epoch: [226]  [110/312]  eta: 0:02:02  lr: 0.000646  min_lr: 0.000646  loss: 3.4686 (3.3818)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.0959  max mem: 31830
Epoch: [226]  [120/312]  eta: 0:01:56  lr: 0.000645  min_lr: 0.000645  loss: 3.4686 (3.3727)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0632  max mem: 31830
Epoch: [226]  [130/312]  eta: 0:01:49  lr: 0.000645  min_lr: 0.000645  loss: 3.4981 (3.3717)  weight_decay: 0.0500 (0.0500)  time: 0.6040  data: 0.1051  max mem: 31830
Epoch: [226]  [140/312]  eta: 0:01:41  lr: 0.000644  min_lr: 0.000644  loss: 3.5709 (3.3714)  weight_decay: 0.0500 (0.0500)  time: 0.4882  data: 0.0451  max mem: 31830
Epoch: [226]  [150/312]  eta: 0:01:36  lr: 0.000644  min_lr: 0.000644  loss: 3.4683 (3.3814)  weight_decay: 0.0500 (0.0500)  time: 0.5256  data: 0.0392  max mem: 31830
Epoch: [226]  [160/312]  eta: 0:01:30  lr: 0.000643  min_lr: 0.000643  loss: 3.5567 (3.3892)  weight_decay: 0.0500 (0.0500)  time: 0.6310  data: 0.0452  max mem: 31830
Epoch: [226]  [170/312]  eta: 0:01:23  lr: 0.000642  min_lr: 0.000642  loss: 3.4943 (3.3908)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0302  max mem: 31830
Epoch: [226]  [180/312]  eta: 0:01:17  lr: 0.000642  min_lr: 0.000642  loss: 3.4358 (3.3921)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0596  max mem: 31830
Epoch: [226]  [190/312]  eta: 0:01:10  lr: 0.000641  min_lr: 0.000641  loss: 3.5105 (3.3911)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.0362  max mem: 31830
Epoch: [226]  [200/312]  eta: 0:01:04  lr: 0.000641  min_lr: 0.000641  loss: 3.5528 (3.3935)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0124  max mem: 31830
Epoch: [226]  [210/312]  eta: 0:00:59  lr: 0.000640  min_lr: 0.000640  loss: 3.5528 (3.3949)  weight_decay: 0.0500 (0.0500)  time: 0.6122  data: 0.0581  max mem: 31830
Epoch: [226]  [220/312]  eta: 0:00:52  lr: 0.000640  min_lr: 0.000640  loss: 3.5583 (3.3964)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0464  max mem: 31830
Epoch: [226]  [230/312]  eta: 0:00:47  lr: 0.000639  min_lr: 0.000639  loss: 3.4158 (3.3917)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0540  max mem: 31830
Epoch: [226]  [240/312]  eta: 0:00:41  lr: 0.000639  min_lr: 0.000639  loss: 3.0446 (3.3789)  weight_decay: 0.0500 (0.0500)  time: 0.5978  data: 0.1146  max mem: 31830
Epoch: [226]  [250/312]  eta: 0:00:35  lr: 0.000638  min_lr: 0.000638  loss: 3.2875 (3.3776)  weight_decay: 0.0500 (0.0500)  time: 0.4746  data: 0.0615  max mem: 31830
Epoch: [226]  [260/312]  eta: 0:00:29  lr: 0.000638  min_lr: 0.000638  loss: 3.4285 (3.3719)  weight_decay: 0.0500 (0.0500)  time: 0.5111  data: 0.0759  max mem: 31830
Epoch: [226]  [270/312]  eta: 0:00:23  lr: 0.000637  min_lr: 0.000637  loss: 3.3177 (3.3682)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0758  max mem: 31830
Epoch: [226]  [280/312]  eta: 0:00:18  lr: 0.000637  min_lr: 0.000637  loss: 3.1650 (3.3556)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0659  max mem: 31830
Epoch: [226]  [290/312]  eta: 0:00:12  lr: 0.000636  min_lr: 0.000636  loss: 2.6494 (3.3454)  weight_decay: 0.0500 (0.0500)  time: 0.5789  data: 0.0922  max mem: 31830
Epoch: [226]  [300/312]  eta: 0:00:06  lr: 0.000636  min_lr: 0.000636  loss: 3.2521 (3.3474)  weight_decay: 0.0500 (0.0500)  time: 0.4682  data: 0.0267  max mem: 31830
Epoch: [226]  [310/312]  eta: 0:00:01  lr: 0.000635  min_lr: 0.000635  loss: 3.2791 (3.3439)  weight_decay: 0.0500 (0.0500)  time: 0.3831  data: 0.0001  max mem: 31830
Epoch: [226]  [311/312]  eta: 0:00:00  lr: 0.000635  min_lr: 0.000635  loss: 3.2791 (3.3449)  weight_decay: 0.0500 (0.0500)  time: 0.3829  data: 0.0001  max mem: 31830
Epoch: [226] Total time: 0:02:53 (0.5564 s / it)
Averaged stats: lr: 0.000635  min_lr: 0.000635  loss: 3.2791 (3.3452)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.9653 (0.9653)  acc1: 82.6823 (82.6823)  acc5: 96.2240 (96.2240)  time: 8.9105  data: 8.7489  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2691 (1.1726)  acc1: 74.6094 (75.2640)  acc5: 92.5781 (93.1200)  time: 1.1101  data: 0.9722  max mem: 31830
Test: Total time: 0:00:10 (1.1368 s / it)
* Acc@1 75.478 Acc@5 93.038 loss 1.175
Accuracy of the model on the 50000 test images: 75.5%
Max accuracy: 75.48%
Epoch: [227]  [  0/312]  eta: 1:04:09  lr: 0.000635  min_lr: 0.000635  loss: 3.9535 (3.9535)  weight_decay: 0.0500 (0.0500)  time: 12.3388  data: 11.9411  max mem: 31830
Epoch: [227]  [ 10/312]  eta: 0:08:19  lr: 0.000634  min_lr: 0.000634  loss: 3.4412 (3.4582)  weight_decay: 0.0500 (0.0500)  time: 1.6546  data: 1.0862  max mem: 31830
Epoch: [227]  [ 20/312]  eta: 0:05:24  lr: 0.000634  min_lr: 0.000634  loss: 3.2507 (3.2948)  weight_decay: 0.0500 (0.0500)  time: 0.5491  data: 0.0554  max mem: 31830
Epoch: [227]  [ 30/312]  eta: 0:04:08  lr: 0.000633  min_lr: 0.000633  loss: 3.4130 (3.3616)  weight_decay: 0.0500 (0.0500)  time: 0.4558  data: 0.0554  max mem: 31830
Epoch: [227]  [ 40/312]  eta: 0:03:27  lr: 0.000633  min_lr: 0.000633  loss: 3.6156 (3.3885)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0008  max mem: 31830
Epoch: [227]  [ 50/312]  eta: 0:03:06  lr: 0.000632  min_lr: 0.000632  loss: 3.4450 (3.3606)  weight_decay: 0.0500 (0.0500)  time: 0.4471  data: 0.0531  max mem: 31830
Epoch: [227]  [ 60/312]  eta: 0:02:45  lr: 0.000632  min_lr: 0.000632  loss: 3.1987 (3.3190)  weight_decay: 0.0500 (0.0500)  time: 0.4448  data: 0.0532  max mem: 31830
Epoch: [227]  [ 70/312]  eta: 0:02:37  lr: 0.000631  min_lr: 0.000631  loss: 3.2977 (3.3275)  weight_decay: 0.0500 (0.0500)  time: 0.4954  data: 0.1017  max mem: 31830
Epoch: [227]  [ 80/312]  eta: 0:02:28  lr: 0.000631  min_lr: 0.000631  loss: 3.5481 (3.3227)  weight_decay: 0.0500 (0.0500)  time: 0.5840  data: 0.1852  max mem: 31830
Epoch: [227]  [ 90/312]  eta: 0:02:16  lr: 0.000630  min_lr: 0.000630  loss: 3.6532 (3.3503)  weight_decay: 0.0500 (0.0500)  time: 0.4939  data: 0.0979  max mem: 31830
Epoch: [227]  [100/312]  eta: 0:02:11  lr: 0.000630  min_lr: 0.000630  loss: 3.4011 (3.3373)  weight_decay: 0.0500 (0.0500)  time: 0.5330  data: 0.1200  max mem: 31830
Epoch: [227]  [110/312]  eta: 0:02:00  lr: 0.000629  min_lr: 0.000629  loss: 3.2865 (3.3195)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1064  max mem: 31830
Epoch: [227]  [120/312]  eta: 0:01:55  lr: 0.000629  min_lr: 0.000629  loss: 3.4204 (3.3395)  weight_decay: 0.0500 (0.0500)  time: 0.5035  data: 0.0878  max mem: 31830
Epoch: [227]  [130/312]  eta: 0:01:50  lr: 0.000628  min_lr: 0.000628  loss: 3.6158 (3.3583)  weight_decay: 0.0500 (0.0500)  time: 0.6460  data: 0.1784  max mem: 31830
Epoch: [227]  [140/312]  eta: 0:01:41  lr: 0.000628  min_lr: 0.000628  loss: 3.6049 (3.3759)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0915  max mem: 31830
Epoch: [227]  [150/312]  eta: 0:01:35  lr: 0.000627  min_lr: 0.000627  loss: 3.6049 (3.3815)  weight_decay: 0.0500 (0.0500)  time: 0.4736  data: 0.0660  max mem: 31830
Epoch: [227]  [160/312]  eta: 0:01:29  lr: 0.000627  min_lr: 0.000627  loss: 3.4793 (3.3736)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.1150  max mem: 31830
Epoch: [227]  [170/312]  eta: 0:01:22  lr: 0.000626  min_lr: 0.000626  loss: 3.3510 (3.3630)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0955  max mem: 31830
Epoch: [227]  [180/312]  eta: 0:01:17  lr: 0.000626  min_lr: 0.000626  loss: 3.1903 (3.3536)  weight_decay: 0.0500 (0.0500)  time: 0.5689  data: 0.1254  max mem: 31830
Epoch: [227]  [190/312]  eta: 0:01:10  lr: 0.000625  min_lr: 0.000625  loss: 3.4404 (3.3599)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0802  max mem: 31830
Epoch: [227]  [200/312]  eta: 0:01:04  lr: 0.000625  min_lr: 0.000625  loss: 3.4915 (3.3682)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.0657  max mem: 31830
Epoch: [227]  [210/312]  eta: 0:00:58  lr: 0.000624  min_lr: 0.000624  loss: 3.5173 (3.3695)  weight_decay: 0.0500 (0.0500)  time: 0.6197  data: 0.1242  max mem: 31830
Epoch: [227]  [220/312]  eta: 0:00:52  lr: 0.000624  min_lr: 0.000624  loss: 3.6679 (3.3801)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0596  max mem: 31830
Epoch: [227]  [230/312]  eta: 0:00:46  lr: 0.000623  min_lr: 0.000623  loss: 3.6679 (3.3858)  weight_decay: 0.0500 (0.0500)  time: 0.4959  data: 0.0529  max mem: 31830
Epoch: [227]  [240/312]  eta: 0:00:40  lr: 0.000622  min_lr: 0.000622  loss: 3.5145 (3.3768)  weight_decay: 0.0500 (0.0500)  time: 0.5601  data: 0.0597  max mem: 31830
Epoch: [227]  [250/312]  eta: 0:00:35  lr: 0.000622  min_lr: 0.000622  loss: 3.3025 (3.3677)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0624  max mem: 31830
Epoch: [227]  [260/312]  eta: 0:00:29  lr: 0.000621  min_lr: 0.000621  loss: 3.3644 (3.3652)  weight_decay: 0.0500 (0.0500)  time: 0.5680  data: 0.1048  max mem: 31830
Epoch: [227]  [270/312]  eta: 0:00:23  lr: 0.000621  min_lr: 0.000621  loss: 3.1823 (3.3571)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.0500  max mem: 31830
Epoch: [227]  [280/312]  eta: 0:00:18  lr: 0.000620  min_lr: 0.000620  loss: 3.1823 (3.3543)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0323  max mem: 31830
Epoch: [227]  [290/312]  eta: 0:00:12  lr: 0.000620  min_lr: 0.000620  loss: 3.3947 (3.3511)  weight_decay: 0.0500 (0.0500)  time: 0.5969  data: 0.0694  max mem: 31830
Epoch: [227]  [300/312]  eta: 0:00:06  lr: 0.000619  min_lr: 0.000619  loss: 3.4325 (3.3579)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0377  max mem: 31830
Epoch: [227]  [310/312]  eta: 0:00:01  lr: 0.000619  min_lr: 0.000619  loss: 3.4978 (3.3540)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [227]  [311/312]  eta: 0:00:00  lr: 0.000619  min_lr: 0.000619  loss: 3.4978 (3.3529)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [227] Total time: 0:02:53 (0.5564 s / it)
Averaged stats: lr: 0.000619  min_lr: 0.000619  loss: 3.4978 (3.3338)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.9876 (0.9876)  acc1: 82.4219 (82.4219)  acc5: 96.2240 (96.2240)  time: 8.9083  data: 8.7440  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3426 (1.2523)  acc1: 75.7812 (75.5200)  acc5: 93.4896 (93.3120)  time: 1.1075  data: 0.9717  max mem: 31830
Test: Total time: 0:00:10 (1.1186 s / it)
* Acc@1 75.540 Acc@5 93.062 loss 1.248
Accuracy of the model on the 50000 test images: 75.5%
Max accuracy: 75.54%
Epoch: [228]  [  0/312]  eta: 1:01:44  lr: 0.000619  min_lr: 0.000619  loss: 3.6104 (3.6104)  weight_decay: 0.0500 (0.0500)  time: 11.8724  data: 8.6819  max mem: 31830
Epoch: [228]  [ 10/312]  eta: 0:09:12  lr: 0.000618  min_lr: 0.000618  loss: 3.1591 (3.1559)  weight_decay: 0.0500 (0.0500)  time: 1.8306  data: 1.0740  max mem: 31830
Epoch: [228]  [ 20/312]  eta: 0:05:33  lr: 0.000618  min_lr: 0.000618  loss: 3.3832 (3.2909)  weight_decay: 0.0500 (0.0500)  time: 0.6059  data: 0.1569  max mem: 31830
Epoch: [228]  [ 30/312]  eta: 0:04:14  lr: 0.000617  min_lr: 0.000617  loss: 3.4698 (3.2959)  weight_decay: 0.0500 (0.0500)  time: 0.3906  data: 0.0013  max mem: 31830
Epoch: [228]  [ 40/312]  eta: 0:03:31  lr: 0.000617  min_lr: 0.000617  loss: 3.2786 (3.3031)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0014  max mem: 31830
Epoch: [228]  [ 50/312]  eta: 0:03:04  lr: 0.000616  min_lr: 0.000616  loss: 3.4274 (3.3324)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [228]  [ 60/312]  eta: 0:02:44  lr: 0.000616  min_lr: 0.000616  loss: 3.4274 (3.2823)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0009  max mem: 31830
Epoch: [228]  [ 70/312]  eta: 0:02:31  lr: 0.000615  min_lr: 0.000615  loss: 3.1608 (3.2808)  weight_decay: 0.0500 (0.0500)  time: 0.4200  data: 0.0009  max mem: 31830
Epoch: [228]  [ 80/312]  eta: 0:02:22  lr: 0.000615  min_lr: 0.000615  loss: 3.3150 (3.2850)  weight_decay: 0.0500 (0.0500)  time: 0.4888  data: 0.0066  max mem: 31830
Epoch: [228]  [ 90/312]  eta: 0:02:14  lr: 0.000614  min_lr: 0.000614  loss: 3.2827 (3.2841)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0256  max mem: 31830
Epoch: [228]  [100/312]  eta: 0:02:08  lr: 0.000614  min_lr: 0.000614  loss: 3.3613 (3.3011)  weight_decay: 0.0500 (0.0500)  time: 0.5812  data: 0.0341  max mem: 31830
Epoch: [228]  [110/312]  eta: 0:02:00  lr: 0.000613  min_lr: 0.000613  loss: 3.6289 (3.3347)  weight_decay: 0.0500 (0.0500)  time: 0.5596  data: 0.0151  max mem: 31830
Epoch: [228]  [120/312]  eta: 0:01:54  lr: 0.000612  min_lr: 0.000612  loss: 3.5407 (3.3174)  weight_decay: 0.0500 (0.0500)  time: 0.5538  data: 0.0009  max mem: 31830
Epoch: [228]  [130/312]  eta: 0:01:47  lr: 0.000612  min_lr: 0.000612  loss: 3.4209 (3.3189)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0012  max mem: 31830
Epoch: [228]  [140/312]  eta: 0:01:41  lr: 0.000611  min_lr: 0.000611  loss: 3.5527 (3.3310)  weight_decay: 0.0500 (0.0500)  time: 0.5207  data: 0.0149  max mem: 31830
Epoch: [228]  [150/312]  eta: 0:01:34  lr: 0.000611  min_lr: 0.000611  loss: 3.5527 (3.3154)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0195  max mem: 31830
Epoch: [228]  [160/312]  eta: 0:01:28  lr: 0.000610  min_lr: 0.000610  loss: 3.1830 (3.3101)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0058  max mem: 31830
Epoch: [228]  [170/312]  eta: 0:01:23  lr: 0.000610  min_lr: 0.000610  loss: 3.4932 (3.3159)  weight_decay: 0.0500 (0.0500)  time: 0.6123  data: 0.0059  max mem: 31830
Epoch: [228]  [180/312]  eta: 0:01:16  lr: 0.000609  min_lr: 0.000609  loss: 3.7295 (3.3316)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0059  max mem: 31830
Epoch: [228]  [190/312]  eta: 0:01:10  lr: 0.000609  min_lr: 0.000609  loss: 3.2973 (3.3087)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.0009  max mem: 31830
Epoch: [228]  [200/312]  eta: 0:01:05  lr: 0.000608  min_lr: 0.000608  loss: 3.0154 (3.2987)  weight_decay: 0.0500 (0.0500)  time: 0.6272  data: 0.0068  max mem: 31830
Epoch: [228]  [210/312]  eta: 0:00:58  lr: 0.000608  min_lr: 0.000608  loss: 3.1744 (3.2911)  weight_decay: 0.0500 (0.0500)  time: 0.5512  data: 0.0074  max mem: 31830
Epoch: [228]  [220/312]  eta: 0:00:53  lr: 0.000607  min_lr: 0.000607  loss: 3.3551 (3.2848)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0177  max mem: 31830
Epoch: [228]  [230/312]  eta: 0:00:47  lr: 0.000607  min_lr: 0.000607  loss: 3.4106 (3.2846)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0241  max mem: 31830
Epoch: [228]  [240/312]  eta: 0:00:41  lr: 0.000606  min_lr: 0.000606  loss: 3.2857 (3.2783)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0086  max mem: 31830
Epoch: [228]  [250/312]  eta: 0:00:35  lr: 0.000606  min_lr: 0.000606  loss: 3.3660 (3.2813)  weight_decay: 0.0500 (0.0500)  time: 0.6024  data: 0.0016  max mem: 31830
Epoch: [228]  [260/312]  eta: 0:00:29  lr: 0.000605  min_lr: 0.000605  loss: 3.4276 (3.2877)  weight_decay: 0.0500 (0.0500)  time: 0.5727  data: 0.0011  max mem: 31830
Epoch: [228]  [270/312]  eta: 0:00:24  lr: 0.000605  min_lr: 0.000605  loss: 3.4503 (3.2908)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0010  max mem: 31830
Epoch: [228]  [280/312]  eta: 0:00:18  lr: 0.000604  min_lr: 0.000604  loss: 3.5020 (3.2999)  weight_decay: 0.0500 (0.0500)  time: 0.6144  data: 0.0028  max mem: 31830
Epoch: [228]  [290/312]  eta: 0:00:12  lr: 0.000604  min_lr: 0.000604  loss: 3.3148 (3.2869)  weight_decay: 0.0500 (0.0500)  time: 0.5532  data: 0.0025  max mem: 31830
Epoch: [228]  [300/312]  eta: 0:00:06  lr: 0.000603  min_lr: 0.000603  loss: 3.2811 (3.2908)  weight_decay: 0.0500 (0.0500)  time: 0.4311  data: 0.0002  max mem: 31830
Epoch: [228]  [310/312]  eta: 0:00:01  lr: 0.000603  min_lr: 0.000603  loss: 3.5797 (3.3043)  weight_decay: 0.0500 (0.0500)  time: 0.4142  data: 0.0002  max mem: 31830
Epoch: [228]  [311/312]  eta: 0:00:00  lr: 0.000603  min_lr: 0.000603  loss: 3.5760 (3.3047)  weight_decay: 0.0500 (0.0500)  time: 0.4141  data: 0.0002  max mem: 31830
Epoch: [228] Total time: 0:02:55 (0.5635 s / it)
Averaged stats: lr: 0.000603  min_lr: 0.000603  loss: 3.5760 (3.3204)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.0436 (1.0436)  acc1: 81.7708 (81.7708)  acc5: 95.8333 (95.8333)  time: 8.6140  data: 8.4471  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3706 (1.2527)  acc1: 74.6094 (75.1360)  acc5: 91.5365 (92.6880)  time: 1.0734  data: 0.9387  max mem: 31830
Test: Total time: 0:00:09 (1.0850 s / it)
* Acc@1 75.158 Acc@5 92.858 loss 1.262
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.54%
Epoch: [229]  [  0/312]  eta: 1:04:11  lr: 0.000603  min_lr: 0.000603  loss: 2.9002 (2.9002)  weight_decay: 0.0500 (0.0500)  time: 12.3457  data: 11.5394  max mem: 31830
Epoch: [229]  [ 10/312]  eta: 0:09:34  lr: 0.000602  min_lr: 0.000602  loss: 3.4184 (3.3780)  weight_decay: 0.0500 (0.0500)  time: 1.9018  data: 1.0761  max mem: 31830
Epoch: [229]  [ 20/312]  eta: 0:05:45  lr: 0.000602  min_lr: 0.000602  loss: 3.4910 (3.3547)  weight_decay: 0.0500 (0.0500)  time: 0.6267  data: 0.0208  max mem: 31830
Epoch: [229]  [ 30/312]  eta: 0:04:22  lr: 0.000601  min_lr: 0.000601  loss: 3.5054 (3.3674)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0067  max mem: 31830
Epoch: [229]  [ 40/312]  eta: 0:03:37  lr: 0.000601  min_lr: 0.000601  loss: 3.5457 (3.3751)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0012  max mem: 31830
Epoch: [229]  [ 50/312]  eta: 0:03:08  lr: 0.000600  min_lr: 0.000600  loss: 3.5897 (3.3699)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0008  max mem: 31830
Epoch: [229]  [ 60/312]  eta: 0:02:48  lr: 0.000600  min_lr: 0.000600  loss: 3.4636 (3.3461)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0021  max mem: 31830
Epoch: [229]  [ 70/312]  eta: 0:02:32  lr: 0.000599  min_lr: 0.000599  loss: 3.1375 (3.3019)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0023  max mem: 31830
Epoch: [229]  [ 80/312]  eta: 0:02:24  lr: 0.000598  min_lr: 0.000598  loss: 3.1277 (3.2938)  weight_decay: 0.0500 (0.0500)  time: 0.4811  data: 0.0147  max mem: 31830
Epoch: [229]  [ 90/312]  eta: 0:02:15  lr: 0.000598  min_lr: 0.000598  loss: 3.1277 (3.2824)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0664  max mem: 31830
Epoch: [229]  [100/312]  eta: 0:02:09  lr: 0.000597  min_lr: 0.000597  loss: 3.1728 (3.2860)  weight_decay: 0.0500 (0.0500)  time: 0.5612  data: 0.1059  max mem: 31830
Epoch: [229]  [110/312]  eta: 0:02:00  lr: 0.000597  min_lr: 0.000597  loss: 3.2924 (3.2822)  weight_decay: 0.0500 (0.0500)  time: 0.5260  data: 0.0540  max mem: 31830
Epoch: [229]  [120/312]  eta: 0:01:55  lr: 0.000596  min_lr: 0.000596  loss: 3.3879 (3.2882)  weight_decay: 0.0500 (0.0500)  time: 0.5506  data: 0.0650  max mem: 31830
Epoch: [229]  [130/312]  eta: 0:01:49  lr: 0.000596  min_lr: 0.000596  loss: 3.3753 (3.2823)  weight_decay: 0.0500 (0.0500)  time: 0.6329  data: 0.1290  max mem: 31830
Epoch: [229]  [140/312]  eta: 0:01:40  lr: 0.000595  min_lr: 0.000595  loss: 3.3753 (3.2803)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0647  max mem: 31830
Epoch: [229]  [150/312]  eta: 0:01:35  lr: 0.000595  min_lr: 0.000595  loss: 3.4345 (3.2789)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0790  max mem: 31830
Epoch: [229]  [160/312]  eta: 0:01:28  lr: 0.000594  min_lr: 0.000594  loss: 3.3700 (3.2842)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.0791  max mem: 31830
Epoch: [229]  [170/312]  eta: 0:01:22  lr: 0.000594  min_lr: 0.000594  loss: 3.4609 (3.2994)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0621  max mem: 31830
Epoch: [229]  [180/312]  eta: 0:01:17  lr: 0.000593  min_lr: 0.000593  loss: 3.5973 (3.3074)  weight_decay: 0.0500 (0.0500)  time: 0.5831  data: 0.1584  max mem: 31830
Epoch: [229]  [190/312]  eta: 0:01:10  lr: 0.000593  min_lr: 0.000593  loss: 3.4484 (3.3093)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0976  max mem: 31830
Epoch: [229]  [200/312]  eta: 0:01:04  lr: 0.000592  min_lr: 0.000592  loss: 3.2871 (3.2944)  weight_decay: 0.0500 (0.0500)  time: 0.5094  data: 0.0996  max mem: 31830
Epoch: [229]  [210/312]  eta: 0:00:59  lr: 0.000592  min_lr: 0.000592  loss: 3.2819 (3.2959)  weight_decay: 0.0500 (0.0500)  time: 0.6136  data: 0.1892  max mem: 31830
Epoch: [229]  [220/312]  eta: 0:00:52  lr: 0.000591  min_lr: 0.000591  loss: 3.4456 (3.2980)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0908  max mem: 31830
Epoch: [229]  [230/312]  eta: 0:00:47  lr: 0.000591  min_lr: 0.000591  loss: 3.5016 (3.3069)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0744  max mem: 31830
Epoch: [229]  [240/312]  eta: 0:00:41  lr: 0.000590  min_lr: 0.000590  loss: 3.5599 (3.3107)  weight_decay: 0.0500 (0.0500)  time: 0.5671  data: 0.0743  max mem: 31830
Epoch: [229]  [250/312]  eta: 0:00:35  lr: 0.000590  min_lr: 0.000590  loss: 3.6152 (3.3211)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0719  max mem: 31830
Epoch: [229]  [260/312]  eta: 0:00:29  lr: 0.000589  min_lr: 0.000589  loss: 3.5667 (3.3258)  weight_decay: 0.0500 (0.0500)  time: 0.5767  data: 0.1481  max mem: 31830
Epoch: [229]  [270/312]  eta: 0:00:23  lr: 0.000589  min_lr: 0.000589  loss: 3.4203 (3.3229)  weight_decay: 0.0500 (0.0500)  time: 0.5645  data: 0.0770  max mem: 31830
Epoch: [229]  [280/312]  eta: 0:00:18  lr: 0.000588  min_lr: 0.000588  loss: 3.4203 (3.3262)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0751  max mem: 31830
Epoch: [229]  [290/312]  eta: 0:00:12  lr: 0.000588  min_lr: 0.000588  loss: 3.5126 (3.3225)  weight_decay: 0.0500 (0.0500)  time: 0.5919  data: 0.1562  max mem: 31830
Epoch: [229]  [300/312]  eta: 0:00:06  lr: 0.000587  min_lr: 0.000587  loss: 3.5746 (3.3242)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0816  max mem: 31830
Epoch: [229]  [310/312]  eta: 0:00:01  lr: 0.000587  min_lr: 0.000587  loss: 3.6075 (3.3322)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [229]  [311/312]  eta: 0:00:00  lr: 0.000587  min_lr: 0.000587  loss: 3.5754 (3.3322)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [229] Total time: 0:02:55 (0.5620 s / it)
Averaged stats: lr: 0.000587  min_lr: 0.000587  loss: 3.5754 (3.3218)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 1.0261 (1.0261)  acc1: 82.5521 (82.5521)  acc5: 96.2240 (96.2240)  time: 9.1176  data: 8.9505  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.4306 (1.3203)  acc1: 75.6510 (75.3920)  acc5: 92.4479 (92.8320)  time: 1.1292  data: 0.9946  max mem: 31830
Test: Total time: 0:00:10 (1.1401 s / it)
* Acc@1 75.600 Acc@5 93.022 loss 1.325
Accuracy of the model on the 50000 test images: 75.6%
Max accuracy: 75.60%
Epoch: [230]  [  0/312]  eta: 1:02:41  lr: 0.000587  min_lr: 0.000587  loss: 2.5309 (2.5309)  weight_decay: 0.0500 (0.0500)  time: 12.0547  data: 10.8762  max mem: 31830
Epoch: [230]  [ 10/312]  eta: 0:09:07  lr: 0.000586  min_lr: 0.000586  loss: 3.5707 (3.3318)  weight_decay: 0.0500 (0.0500)  time: 1.8116  data: 0.9895  max mem: 31830
Epoch: [230]  [ 20/312]  eta: 0:05:37  lr: 0.000586  min_lr: 0.000586  loss: 3.5762 (3.3385)  weight_decay: 0.0500 (0.0500)  time: 0.6122  data: 0.0266  max mem: 31830
Epoch: [230]  [ 30/312]  eta: 0:04:17  lr: 0.000585  min_lr: 0.000585  loss: 3.0503 (3.2283)  weight_decay: 0.0500 (0.0500)  time: 0.4178  data: 0.0265  max mem: 31830
Epoch: [230]  [ 40/312]  eta: 0:03:34  lr: 0.000585  min_lr: 0.000585  loss: 3.3069 (3.2254)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0007  max mem: 31830
Epoch: [230]  [ 50/312]  eta: 0:03:06  lr: 0.000584  min_lr: 0.000584  loss: 3.3891 (3.2462)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0008  max mem: 31830
Epoch: [230]  [ 60/312]  eta: 0:02:46  lr: 0.000584  min_lr: 0.000584  loss: 3.3647 (3.2298)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [230]  [ 70/312]  eta: 0:02:31  lr: 0.000583  min_lr: 0.000583  loss: 3.4976 (3.2561)  weight_decay: 0.0500 (0.0500)  time: 0.4015  data: 0.0008  max mem: 31830
Epoch: [230]  [ 80/312]  eta: 0:02:22  lr: 0.000583  min_lr: 0.000583  loss: 3.4883 (3.2630)  weight_decay: 0.0500 (0.0500)  time: 0.4776  data: 0.0067  max mem: 31830
Epoch: [230]  [ 90/312]  eta: 0:02:13  lr: 0.000582  min_lr: 0.000582  loss: 3.4447 (3.2768)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0134  max mem: 31830
Epoch: [230]  [100/312]  eta: 0:02:07  lr: 0.000582  min_lr: 0.000582  loss: 3.4442 (3.2697)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0143  max mem: 31830
Epoch: [230]  [110/312]  eta: 0:01:58  lr: 0.000581  min_lr: 0.000581  loss: 3.4379 (3.2664)  weight_decay: 0.0500 (0.0500)  time: 0.5378  data: 0.0138  max mem: 31830
Epoch: [230]  [120/312]  eta: 0:01:52  lr: 0.000581  min_lr: 0.000581  loss: 3.4379 (3.2628)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0125  max mem: 31830
Epoch: [230]  [130/312]  eta: 0:01:48  lr: 0.000580  min_lr: 0.000580  loss: 3.2171 (3.2428)  weight_decay: 0.0500 (0.0500)  time: 0.6288  data: 0.0269  max mem: 31830
Epoch: [230]  [140/312]  eta: 0:01:40  lr: 0.000580  min_lr: 0.000580  loss: 3.1754 (3.2437)  weight_decay: 0.0500 (0.0500)  time: 0.5549  data: 0.0362  max mem: 31830
Epoch: [230]  [150/312]  eta: 0:01:34  lr: 0.000579  min_lr: 0.000579  loss: 3.1696 (3.2365)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0221  max mem: 31830
Epoch: [230]  [160/312]  eta: 0:01:29  lr: 0.000579  min_lr: 0.000579  loss: 3.4142 (3.2357)  weight_decay: 0.0500 (0.0500)  time: 0.6326  data: 0.0077  max mem: 31830
Epoch: [230]  [170/312]  eta: 0:01:22  lr: 0.000578  min_lr: 0.000578  loss: 3.4142 (3.2342)  weight_decay: 0.0500 (0.0500)  time: 0.5207  data: 0.0014  max mem: 31830
Epoch: [230]  [180/312]  eta: 0:01:17  lr: 0.000578  min_lr: 0.000578  loss: 3.4323 (3.2389)  weight_decay: 0.0500 (0.0500)  time: 0.5442  data: 0.0142  max mem: 31830
Epoch: [230]  [190/312]  eta: 0:01:10  lr: 0.000577  min_lr: 0.000577  loss: 3.5486 (3.2514)  weight_decay: 0.0500 (0.0500)  time: 0.5409  data: 0.0148  max mem: 31830
Epoch: [230]  [200/312]  eta: 0:01:04  lr: 0.000577  min_lr: 0.000577  loss: 3.5486 (3.2496)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0026  max mem: 31830
Epoch: [230]  [210/312]  eta: 0:00:59  lr: 0.000576  min_lr: 0.000576  loss: 3.4541 (3.2634)  weight_decay: 0.0500 (0.0500)  time: 0.6621  data: 0.0019  max mem: 31830
Epoch: [230]  [220/312]  eta: 0:00:52  lr: 0.000575  min_lr: 0.000575  loss: 3.5562 (3.2690)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0009  max mem: 31830
Epoch: [230]  [230/312]  eta: 0:00:47  lr: 0.000575  min_lr: 0.000575  loss: 3.5456 (3.2798)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0066  max mem: 31830
Epoch: [230]  [240/312]  eta: 0:00:41  lr: 0.000574  min_lr: 0.000574  loss: 3.6327 (3.2829)  weight_decay: 0.0500 (0.0500)  time: 0.6745  data: 0.0126  max mem: 31830
Epoch: [230]  [250/312]  eta: 0:00:35  lr: 0.000574  min_lr: 0.000574  loss: 3.5284 (3.2876)  weight_decay: 0.0500 (0.0500)  time: 0.5532  data: 0.0131  max mem: 31830
Epoch: [230]  [260/312]  eta: 0:00:30  lr: 0.000573  min_lr: 0.000573  loss: 3.4858 (3.2918)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0071  max mem: 31830
Epoch: [230]  [270/312]  eta: 0:00:23  lr: 0.000573  min_lr: 0.000573  loss: 3.3545 (3.2918)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.0073  max mem: 31830
Epoch: [230]  [280/312]  eta: 0:00:18  lr: 0.000572  min_lr: 0.000572  loss: 3.3545 (3.2881)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0084  max mem: 31830
Epoch: [230]  [290/312]  eta: 0:00:12  lr: 0.000572  min_lr: 0.000572  loss: 3.5078 (3.2900)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0067  max mem: 31830
Epoch: [230]  [300/312]  eta: 0:00:06  lr: 0.000571  min_lr: 0.000571  loss: 3.2440 (3.2839)  weight_decay: 0.0500 (0.0500)  time: 0.4769  data: 0.0052  max mem: 31830
Epoch: [230]  [310/312]  eta: 0:00:01  lr: 0.000571  min_lr: 0.000571  loss: 3.2905 (3.2853)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [230]  [311/312]  eta: 0:00:00  lr: 0.000571  min_lr: 0.000571  loss: 3.2905 (3.2858)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [230] Total time: 0:02:56 (0.5651 s / it)
Averaged stats: lr: 0.000571  min_lr: 0.000571  loss: 3.2905 (3.3108)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.9529 (0.9529)  acc1: 82.1615 (82.1615)  acc5: 95.5729 (95.5729)  time: 9.1254  data: 8.9582  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2982 (1.1877)  acc1: 74.2188 (75.6640)  acc5: 92.4479 (92.9440)  time: 1.1311  data: 0.9954  max mem: 31830
Test: Total time: 0:00:10 (1.1752 s / it)
* Acc@1 75.862 Acc@5 93.164 loss 1.183
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 75.86%
Epoch: [231]  [  0/312]  eta: 1:03:00  lr: 0.000571  min_lr: 0.000571  loss: 3.4786 (3.4786)  weight_decay: 0.0500 (0.0500)  time: 12.1162  data: 9.7862  max mem: 31830
Epoch: [231]  [ 10/312]  eta: 0:09:00  lr: 0.000570  min_lr: 0.000570  loss: 3.6262 (3.4634)  weight_decay: 0.0500 (0.0500)  time: 1.7898  data: 1.0591  max mem: 31830
Epoch: [231]  [ 20/312]  eta: 0:05:28  lr: 0.000570  min_lr: 0.000570  loss: 3.5361 (3.4405)  weight_decay: 0.0500 (0.0500)  time: 0.5769  data: 0.0935  max mem: 31830
Epoch: [231]  [ 30/312]  eta: 0:04:11  lr: 0.000569  min_lr: 0.000569  loss: 3.4328 (3.4091)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0009  max mem: 31830
Epoch: [231]  [ 40/312]  eta: 0:03:29  lr: 0.000569  min_lr: 0.000569  loss: 3.5881 (3.4552)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0010  max mem: 31830
Epoch: [231]  [ 50/312]  eta: 0:03:02  lr: 0.000568  min_lr: 0.000568  loss: 3.6051 (3.4363)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0014  max mem: 31830
Epoch: [231]  [ 60/312]  eta: 0:02:43  lr: 0.000568  min_lr: 0.000568  loss: 3.4083 (3.4047)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0013  max mem: 31830
Epoch: [231]  [ 70/312]  eta: 0:02:28  lr: 0.000567  min_lr: 0.000567  loss: 3.3500 (3.3629)  weight_decay: 0.0500 (0.0500)  time: 0.4024  data: 0.0009  max mem: 31830
Epoch: [231]  [ 80/312]  eta: 0:02:23  lr: 0.000567  min_lr: 0.000567  loss: 3.2057 (3.3495)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0309  max mem: 31830
Epoch: [231]  [ 90/312]  eta: 0:02:13  lr: 0.000566  min_lr: 0.000566  loss: 3.3150 (3.3397)  weight_decay: 0.0500 (0.0500)  time: 0.5586  data: 0.0308  max mem: 31830
Epoch: [231]  [100/312]  eta: 0:02:08  lr: 0.000566  min_lr: 0.000566  loss: 3.1360 (3.3149)  weight_decay: 0.0500 (0.0500)  time: 0.5552  data: 0.0150  max mem: 31830
Epoch: [231]  [110/312]  eta: 0:02:02  lr: 0.000565  min_lr: 0.000565  loss: 3.1765 (3.3097)  weight_decay: 0.0500 (0.0500)  time: 0.6315  data: 0.0442  max mem: 31830
Epoch: [231]  [120/312]  eta: 0:01:53  lr: 0.000565  min_lr: 0.000565  loss: 2.9969 (3.2801)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0302  max mem: 31830
Epoch: [231]  [130/312]  eta: 0:01:48  lr: 0.000564  min_lr: 0.000564  loss: 2.9939 (3.2889)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0013  max mem: 31830
Epoch: [231]  [140/312]  eta: 0:01:41  lr: 0.000564  min_lr: 0.000564  loss: 3.4558 (3.3055)  weight_decay: 0.0500 (0.0500)  time: 0.5911  data: 0.0012  max mem: 31830
Epoch: [231]  [150/312]  eta: 0:01:34  lr: 0.000563  min_lr: 0.000563  loss: 3.4592 (3.3138)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.0010  max mem: 31830
Epoch: [231]  [160/312]  eta: 0:01:29  lr: 0.000563  min_lr: 0.000563  loss: 3.4820 (3.3262)  weight_decay: 0.0500 (0.0500)  time: 0.5912  data: 0.0075  max mem: 31830
Epoch: [231]  [170/312]  eta: 0:01:22  lr: 0.000562  min_lr: 0.000562  loss: 3.6847 (3.3243)  weight_decay: 0.0500 (0.0500)  time: 0.5380  data: 0.0223  max mem: 31830
Epoch: [231]  [180/312]  eta: 0:01:16  lr: 0.000562  min_lr: 0.000562  loss: 3.2910 (3.3118)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0344  max mem: 31830
Epoch: [231]  [190/312]  eta: 0:01:11  lr: 0.000561  min_lr: 0.000561  loss: 3.3777 (3.3207)  weight_decay: 0.0500 (0.0500)  time: 0.6238  data: 0.0264  max mem: 31830
Epoch: [231]  [200/312]  eta: 0:01:04  lr: 0.000561  min_lr: 0.000561  loss: 3.5298 (3.3263)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.0084  max mem: 31830
Epoch: [231]  [210/312]  eta: 0:00:58  lr: 0.000560  min_lr: 0.000560  loss: 3.5257 (3.3360)  weight_decay: 0.0500 (0.0500)  time: 0.5084  data: 0.0237  max mem: 31830
Epoch: [231]  [220/312]  eta: 0:00:53  lr: 0.000560  min_lr: 0.000560  loss: 3.5257 (3.3428)  weight_decay: 0.0500 (0.0500)  time: 0.5929  data: 0.0237  max mem: 31830
Epoch: [231]  [230/312]  eta: 0:00:47  lr: 0.000559  min_lr: 0.000559  loss: 3.5395 (3.3445)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0024  max mem: 31830
Epoch: [231]  [240/312]  eta: 0:00:41  lr: 0.000559  min_lr: 0.000559  loss: 3.4807 (3.3465)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0071  max mem: 31830
Epoch: [231]  [250/312]  eta: 0:00:35  lr: 0.000558  min_lr: 0.000558  loss: 3.2183 (3.3413)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0062  max mem: 31830
Epoch: [231]  [260/312]  eta: 0:00:29  lr: 0.000558  min_lr: 0.000558  loss: 2.9571 (3.3323)  weight_decay: 0.0500 (0.0500)  time: 0.5793  data: 0.0329  max mem: 31830
Epoch: [231]  [270/312]  eta: 0:00:24  lr: 0.000557  min_lr: 0.000557  loss: 3.1117 (3.3287)  weight_decay: 0.0500 (0.0500)  time: 0.6246  data: 0.0330  max mem: 31830
Epoch: [231]  [280/312]  eta: 0:00:18  lr: 0.000557  min_lr: 0.000557  loss: 3.2844 (3.3300)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0020  max mem: 31830
Epoch: [231]  [290/312]  eta: 0:00:12  lr: 0.000556  min_lr: 0.000556  loss: 3.2509 (3.3267)  weight_decay: 0.0500 (0.0500)  time: 0.5007  data: 0.0069  max mem: 31830
Epoch: [231]  [300/312]  eta: 0:00:06  lr: 0.000556  min_lr: 0.000556  loss: 3.1407 (3.3218)  weight_decay: 0.0500 (0.0500)  time: 0.4633  data: 0.0054  max mem: 31830
Epoch: [231]  [310/312]  eta: 0:00:01  lr: 0.000555  min_lr: 0.000555  loss: 3.3705 (3.3172)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0001  max mem: 31830
Epoch: [231]  [311/312]  eta: 0:00:00  lr: 0.000555  min_lr: 0.000555  loss: 3.5072 (3.3182)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0001  max mem: 31830
Epoch: [231] Total time: 0:02:55 (0.5625 s / it)
Averaged stats: lr: 0.000555  min_lr: 0.000555  loss: 3.5072 (3.3119)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.9194 (0.9194)  acc1: 82.9427 (82.9427)  acc5: 95.9635 (95.9635)  time: 7.8595  data: 7.6927  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2894 (1.1703)  acc1: 75.3906 (76.0640)  acc5: 92.8385 (93.3120)  time: 1.0314  data: 0.8960  max mem: 31830
Test: Total time: 0:00:09 (1.0406 s / it)
* Acc@1 75.788 Acc@5 93.192 loss 1.167
Accuracy of the model on the 50000 test images: 75.8%
Max accuracy: 75.86%
Epoch: [232]  [  0/312]  eta: 1:03:33  lr: 0.000555  min_lr: 0.000555  loss: 3.5119 (3.5119)  weight_decay: 0.0500 (0.0500)  time: 12.2240  data: 8.1172  max mem: 31830
Epoch: [232]  [ 10/312]  eta: 0:08:49  lr: 0.000555  min_lr: 0.000555  loss: 3.6192 (3.5449)  weight_decay: 0.0500 (0.0500)  time: 1.7521  data: 0.9475  max mem: 31830
Epoch: [232]  [ 20/312]  eta: 0:05:34  lr: 0.000554  min_lr: 0.000554  loss: 3.4525 (3.3300)  weight_decay: 0.0500 (0.0500)  time: 0.5918  data: 0.1430  max mem: 31830
Epoch: [232]  [ 30/312]  eta: 0:04:15  lr: 0.000554  min_lr: 0.000554  loss: 3.3318 (3.3394)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0284  max mem: 31830
Epoch: [232]  [ 40/312]  eta: 0:03:32  lr: 0.000553  min_lr: 0.000553  loss: 3.3602 (3.2784)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0014  max mem: 31830
Epoch: [232]  [ 50/312]  eta: 0:03:04  lr: 0.000553  min_lr: 0.000553  loss: 3.3806 (3.2695)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0012  max mem: 31830
Epoch: [232]  [ 60/312]  eta: 0:02:45  lr: 0.000552  min_lr: 0.000552  loss: 3.3806 (3.2661)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0009  max mem: 31830
Epoch: [232]  [ 70/312]  eta: 0:02:32  lr: 0.000552  min_lr: 0.000552  loss: 3.5875 (3.2976)  weight_decay: 0.0500 (0.0500)  time: 0.4410  data: 0.0010  max mem: 31830
Epoch: [232]  [ 80/312]  eta: 0:02:25  lr: 0.000551  min_lr: 0.000551  loss: 3.5028 (3.3044)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0146  max mem: 31830
Epoch: [232]  [ 90/312]  eta: 0:02:15  lr: 0.000551  min_lr: 0.000551  loss: 3.3852 (3.3085)  weight_decay: 0.0500 (0.0500)  time: 0.5339  data: 0.0496  max mem: 31830
Epoch: [232]  [100/312]  eta: 0:02:09  lr: 0.000550  min_lr: 0.000550  loss: 3.3231 (3.2889)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0797  max mem: 31830
Epoch: [232]  [110/312]  eta: 0:01:59  lr: 0.000550  min_lr: 0.000550  loss: 3.1605 (3.2766)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0457  max mem: 31830
Epoch: [232]  [120/312]  eta: 0:01:54  lr: 0.000549  min_lr: 0.000549  loss: 3.2725 (3.2804)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0579  max mem: 31830
Epoch: [232]  [130/312]  eta: 0:01:48  lr: 0.000549  min_lr: 0.000549  loss: 3.2725 (3.2491)  weight_decay: 0.0500 (0.0500)  time: 0.6412  data: 0.0845  max mem: 31830
Epoch: [232]  [140/312]  eta: 0:01:40  lr: 0.000548  min_lr: 0.000548  loss: 3.1440 (3.2481)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0425  max mem: 31830
Epoch: [232]  [150/312]  eta: 0:01:35  lr: 0.000548  min_lr: 0.000548  loss: 3.3259 (3.2355)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0608  max mem: 31830
Epoch: [232]  [160/312]  eta: 0:01:28  lr: 0.000547  min_lr: 0.000547  loss: 3.3743 (3.2415)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.0470  max mem: 31830
Epoch: [232]  [170/312]  eta: 0:01:22  lr: 0.000547  min_lr: 0.000547  loss: 3.3400 (3.2509)  weight_decay: 0.0500 (0.0500)  time: 0.5392  data: 0.0702  max mem: 31830
Epoch: [232]  [180/312]  eta: 0:01:16  lr: 0.000546  min_lr: 0.000546  loss: 3.2348 (3.2369)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.1028  max mem: 31830
Epoch: [232]  [190/312]  eta: 0:01:09  lr: 0.000546  min_lr: 0.000546  loss: 3.0563 (3.2328)  weight_decay: 0.0500 (0.0500)  time: 0.4754  data: 0.0341  max mem: 31830
Epoch: [232]  [200/312]  eta: 0:01:03  lr: 0.000545  min_lr: 0.000545  loss: 3.3957 (3.2341)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0660  max mem: 31830
Epoch: [232]  [210/312]  eta: 0:00:58  lr: 0.000545  min_lr: 0.000545  loss: 3.4435 (3.2383)  weight_decay: 0.0500 (0.0500)  time: 0.6035  data: 0.1107  max mem: 31830
Epoch: [232]  [220/312]  eta: 0:00:52  lr: 0.000544  min_lr: 0.000544  loss: 3.2507 (3.2272)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0669  max mem: 31830
Epoch: [232]  [230/312]  eta: 0:00:47  lr: 0.000544  min_lr: 0.000544  loss: 2.9655 (3.2225)  weight_decay: 0.0500 (0.0500)  time: 0.5806  data: 0.0790  max mem: 31830
Epoch: [232]  [240/312]  eta: 0:00:41  lr: 0.000543  min_lr: 0.000543  loss: 3.2612 (3.2232)  weight_decay: 0.0500 (0.0500)  time: 0.6156  data: 0.0588  max mem: 31830
Epoch: [232]  [250/312]  eta: 0:00:35  lr: 0.000543  min_lr: 0.000543  loss: 3.3306 (3.2304)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0491  max mem: 31830
Epoch: [232]  [260/312]  eta: 0:00:29  lr: 0.000542  min_lr: 0.000542  loss: 3.6301 (3.2440)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0895  max mem: 31830
Epoch: [232]  [270/312]  eta: 0:00:23  lr: 0.000542  min_lr: 0.000542  loss: 3.5935 (3.2481)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0930  max mem: 31830
Epoch: [232]  [280/312]  eta: 0:00:18  lr: 0.000541  min_lr: 0.000541  loss: 3.4267 (3.2527)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.1306  max mem: 31830
Epoch: [232]  [290/312]  eta: 0:00:12  lr: 0.000541  min_lr: 0.000541  loss: 3.4267 (3.2438)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0797  max mem: 31830
Epoch: [232]  [300/312]  eta: 0:00:06  lr: 0.000540  min_lr: 0.000540  loss: 3.4985 (3.2471)  weight_decay: 0.0500 (0.0500)  time: 0.4660  data: 0.0400  max mem: 31830
Epoch: [232]  [310/312]  eta: 0:00:01  lr: 0.000540  min_lr: 0.000540  loss: 3.2995 (3.2425)  weight_decay: 0.0500 (0.0500)  time: 0.4191  data: 0.0393  max mem: 31830
Epoch: [232]  [311/312]  eta: 0:00:00  lr: 0.000540  min_lr: 0.000540  loss: 3.2995 (3.2436)  weight_decay: 0.0500 (0.0500)  time: 0.4066  data: 0.0263  max mem: 31830
Epoch: [232] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.000540  min_lr: 0.000540  loss: 3.2995 (3.2970)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.9570 (0.9570)  acc1: 80.2083 (80.2083)  acc5: 95.1823 (95.1823)  time: 9.1736  data: 9.0080  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3254 (1.2172)  acc1: 77.6042 (75.5680)  acc5: 92.7083 (92.9120)  time: 1.1359  data: 1.0010  max mem: 31830
Test: Total time: 0:00:10 (1.1540 s / it)
* Acc@1 75.984 Acc@5 93.198 loss 1.215
Accuracy of the model on the 50000 test images: 76.0%
Max accuracy: 75.98%
Epoch: [233]  [  0/312]  eta: 0:58:33  lr: 0.000540  min_lr: 0.000540  loss: 3.9989 (3.9989)  weight_decay: 0.0500 (0.0500)  time: 11.2619  data: 10.5457  max mem: 31830
Epoch: [233]  [ 10/312]  eta: 0:08:38  lr: 0.000539  min_lr: 0.000539  loss: 3.6049 (3.6339)  weight_decay: 0.0500 (0.0500)  time: 1.7182  data: 1.0847  max mem: 31830
Epoch: [233]  [ 20/312]  eta: 0:05:33  lr: 0.000539  min_lr: 0.000539  loss: 3.5635 (3.5209)  weight_decay: 0.0500 (0.0500)  time: 0.6357  data: 0.1292  max mem: 31830
Epoch: [233]  [ 30/312]  eta: 0:04:14  lr: 0.000538  min_lr: 0.000538  loss: 3.5433 (3.4644)  weight_decay: 0.0500 (0.0500)  time: 0.4523  data: 0.0602  max mem: 31830
Epoch: [233]  [ 40/312]  eta: 0:03:31  lr: 0.000538  min_lr: 0.000538  loss: 3.5441 (3.4606)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0007  max mem: 31830
Epoch: [233]  [ 50/312]  eta: 0:03:06  lr: 0.000537  min_lr: 0.000537  loss: 3.5845 (3.4156)  weight_decay: 0.0500 (0.0500)  time: 0.4155  data: 0.0185  max mem: 31830
Epoch: [233]  [ 60/312]  eta: 0:02:46  lr: 0.000537  min_lr: 0.000537  loss: 3.4814 (3.3992)  weight_decay: 0.0500 (0.0500)  time: 0.4128  data: 0.0186  max mem: 31830
Epoch: [233]  [ 70/312]  eta: 0:02:35  lr: 0.000536  min_lr: 0.000536  loss: 3.4398 (3.3804)  weight_decay: 0.0500 (0.0500)  time: 0.4719  data: 0.0774  max mem: 31830
Epoch: [233]  [ 80/312]  eta: 0:02:29  lr: 0.000536  min_lr: 0.000536  loss: 3.1868 (3.3473)  weight_decay: 0.0500 (0.0500)  time: 0.5922  data: 0.1969  max mem: 31830
Epoch: [233]  [ 90/312]  eta: 0:02:16  lr: 0.000535  min_lr: 0.000535  loss: 3.0231 (3.3185)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.1204  max mem: 31830
Epoch: [233]  [100/312]  eta: 0:02:11  lr: 0.000535  min_lr: 0.000535  loss: 3.4468 (3.3297)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.1400  max mem: 31830
Epoch: [233]  [110/312]  eta: 0:02:01  lr: 0.000534  min_lr: 0.000534  loss: 3.2597 (3.3099)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.1402  max mem: 31830
Epoch: [233]  [120/312]  eta: 0:01:56  lr: 0.000534  min_lr: 0.000534  loss: 3.1816 (3.3134)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.1206  max mem: 31830
Epoch: [233]  [130/312]  eta: 0:01:50  lr: 0.000533  min_lr: 0.000533  loss: 3.4881 (3.3160)  weight_decay: 0.0500 (0.0500)  time: 0.6446  data: 0.2464  max mem: 31830
Epoch: [233]  [140/312]  eta: 0:01:41  lr: 0.000533  min_lr: 0.000533  loss: 3.4567 (3.3172)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.1270  max mem: 31830
Epoch: [233]  [150/312]  eta: 0:01:36  lr: 0.000533  min_lr: 0.000533  loss: 3.4567 (3.3264)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.1108  max mem: 31830
Epoch: [233]  [160/312]  eta: 0:01:30  lr: 0.000532  min_lr: 0.000532  loss: 3.4497 (3.3192)  weight_decay: 0.0500 (0.0500)  time: 0.6157  data: 0.2141  max mem: 31830
Epoch: [233]  [170/312]  eta: 0:01:22  lr: 0.000532  min_lr: 0.000532  loss: 3.4731 (3.3222)  weight_decay: 0.0500 (0.0500)  time: 0.5009  data: 0.1043  max mem: 31830
Epoch: [233]  [180/312]  eta: 0:01:17  lr: 0.000531  min_lr: 0.000531  loss: 3.4984 (3.3209)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.1027  max mem: 31830
Epoch: [233]  [190/312]  eta: 0:01:10  lr: 0.000531  min_lr: 0.000531  loss: 3.4578 (3.3315)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.1025  max mem: 31830
Epoch: [233]  [200/312]  eta: 0:01:05  lr: 0.000530  min_lr: 0.000530  loss: 3.6223 (3.3492)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.1463  max mem: 31830
Epoch: [233]  [210/312]  eta: 0:00:59  lr: 0.000530  min_lr: 0.000530  loss: 3.6358 (3.3361)  weight_decay: 0.0500 (0.0500)  time: 0.6766  data: 0.2788  max mem: 31830
Epoch: [233]  [220/312]  eta: 0:00:53  lr: 0.000529  min_lr: 0.000529  loss: 3.5483 (3.3499)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.1333  max mem: 31830
Epoch: [233]  [230/312]  eta: 0:00:47  lr: 0.000529  min_lr: 0.000529  loss: 3.6050 (3.3410)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.1193  max mem: 31830
Epoch: [233]  [240/312]  eta: 0:00:41  lr: 0.000528  min_lr: 0.000528  loss: 3.3639 (3.3378)  weight_decay: 0.0500 (0.0500)  time: 0.6572  data: 0.2626  max mem: 31830
Epoch: [233]  [250/312]  eta: 0:00:35  lr: 0.000528  min_lr: 0.000528  loss: 3.3606 (3.3396)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.1442  max mem: 31830
Epoch: [233]  [260/312]  eta: 0:00:30  lr: 0.000527  min_lr: 0.000527  loss: 3.4222 (3.3390)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.1104  max mem: 31830
Epoch: [233]  [270/312]  eta: 0:00:23  lr: 0.000527  min_lr: 0.000527  loss: 3.2637 (3.3370)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.1103  max mem: 31830
Epoch: [233]  [280/312]  eta: 0:00:18  lr: 0.000526  min_lr: 0.000526  loss: 3.2637 (3.3422)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.1175  max mem: 31830
Epoch: [233]  [290/312]  eta: 0:00:12  lr: 0.000526  min_lr: 0.000526  loss: 3.6692 (3.3535)  weight_decay: 0.0500 (0.0500)  time: 0.6087  data: 0.2168  max mem: 31830
Epoch: [233]  [300/312]  eta: 0:00:06  lr: 0.000525  min_lr: 0.000525  loss: 3.5649 (3.3581)  weight_decay: 0.0500 (0.0500)  time: 0.4852  data: 0.0999  max mem: 31830
Epoch: [233]  [310/312]  eta: 0:00:01  lr: 0.000525  min_lr: 0.000525  loss: 3.5247 (3.3618)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [233]  [311/312]  eta: 0:00:00  lr: 0.000525  min_lr: 0.000525  loss: 3.5247 (3.3602)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [233] Total time: 0:02:56 (0.5644 s / it)
Averaged stats: lr: 0.000525  min_lr: 0.000525  loss: 3.5247 (3.3158)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.0908 (1.0908)  acc1: 81.7708 (81.7708)  acc5: 95.5729 (95.5729)  time: 8.9840  data: 8.8166  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3541 (1.2799)  acc1: 75.1302 (75.4880)  acc5: 93.2292 (93.0880)  time: 1.1153  data: 0.9797  max mem: 31830
Test: Total time: 0:00:10 (1.1321 s / it)
* Acc@1 75.790 Acc@5 93.200 loss 1.272
Accuracy of the model on the 50000 test images: 75.8%
Max accuracy: 75.98%
Epoch: [234]  [  0/312]  eta: 1:05:48  lr: 0.000525  min_lr: 0.000525  loss: 2.5570 (2.5570)  weight_decay: 0.0500 (0.0500)  time: 12.6562  data: 8.9087  max mem: 31830
Epoch: [234]  [ 10/312]  eta: 0:08:35  lr: 0.000524  min_lr: 0.000524  loss: 3.1879 (3.0697)  weight_decay: 0.0500 (0.0500)  time: 1.7063  data: 0.9676  max mem: 31830
Epoch: [234]  [ 20/312]  eta: 0:05:37  lr: 0.000524  min_lr: 0.000524  loss: 3.2346 (3.1675)  weight_decay: 0.0500 (0.0500)  time: 0.5813  data: 0.1543  max mem: 31830
Epoch: [234]  [ 30/312]  eta: 0:04:16  lr: 0.000523  min_lr: 0.000523  loss: 3.4067 (3.2886)  weight_decay: 0.0500 (0.0500)  time: 0.4732  data: 0.0679  max mem: 31830
Epoch: [234]  [ 40/312]  eta: 0:03:33  lr: 0.000523  min_lr: 0.000523  loss: 3.3503 (3.2610)  weight_decay: 0.0500 (0.0500)  time: 0.3947  data: 0.0007  max mem: 31830
Epoch: [234]  [ 50/312]  eta: 0:03:05  lr: 0.000522  min_lr: 0.000522  loss: 3.1560 (3.2175)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0009  max mem: 31830
Epoch: [234]  [ 60/312]  eta: 0:02:45  lr: 0.000522  min_lr: 0.000522  loss: 3.5179 (3.2902)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0009  max mem: 31830
Epoch: [234]  [ 70/312]  eta: 0:02:33  lr: 0.000521  min_lr: 0.000521  loss: 3.5179 (3.3042)  weight_decay: 0.0500 (0.0500)  time: 0.4397  data: 0.0190  max mem: 31830
Epoch: [234]  [ 80/312]  eta: 0:02:24  lr: 0.000521  min_lr: 0.000521  loss: 3.3122 (3.3047)  weight_decay: 0.0500 (0.0500)  time: 0.5086  data: 0.0557  max mem: 31830
Epoch: [234]  [ 90/312]  eta: 0:02:13  lr: 0.000520  min_lr: 0.000520  loss: 3.5290 (3.3377)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0678  max mem: 31830
Epoch: [234]  [100/312]  eta: 0:02:08  lr: 0.000520  min_lr: 0.000520  loss: 3.4316 (3.3161)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.1130  max mem: 31830
Epoch: [234]  [110/312]  eta: 0:01:58  lr: 0.000519  min_lr: 0.000519  loss: 3.3225 (3.3182)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0830  max mem: 31830
Epoch: [234]  [120/312]  eta: 0:01:53  lr: 0.000519  min_lr: 0.000519  loss: 3.4774 (3.3302)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0889  max mem: 31830
Epoch: [234]  [130/312]  eta: 0:01:47  lr: 0.000518  min_lr: 0.000518  loss: 3.5883 (3.3520)  weight_decay: 0.0500 (0.0500)  time: 0.6171  data: 0.1528  max mem: 31830
Epoch: [234]  [140/312]  eta: 0:01:39  lr: 0.000518  min_lr: 0.000518  loss: 3.4998 (3.3370)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0865  max mem: 31830
Epoch: [234]  [150/312]  eta: 0:01:33  lr: 0.000517  min_lr: 0.000517  loss: 3.3377 (3.3414)  weight_decay: 0.0500 (0.0500)  time: 0.4960  data: 0.0789  max mem: 31830
Epoch: [234]  [160/312]  eta: 0:01:28  lr: 0.000517  min_lr: 0.000517  loss: 3.3116 (3.3419)  weight_decay: 0.0500 (0.0500)  time: 0.6005  data: 0.1395  max mem: 31830
Epoch: [234]  [170/312]  eta: 0:01:22  lr: 0.000516  min_lr: 0.000516  loss: 3.2688 (3.3443)  weight_decay: 0.0500 (0.0500)  time: 0.5704  data: 0.1333  max mem: 31830
Epoch: [234]  [180/312]  eta: 0:01:15  lr: 0.000516  min_lr: 0.000516  loss: 3.4704 (3.3364)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0996  max mem: 31830
Epoch: [234]  [190/312]  eta: 0:01:09  lr: 0.000515  min_lr: 0.000515  loss: 3.5073 (3.3474)  weight_decay: 0.0500 (0.0500)  time: 0.4722  data: 0.0648  max mem: 31830
Epoch: [234]  [200/312]  eta: 0:01:04  lr: 0.000515  min_lr: 0.000515  loss: 3.5882 (3.3527)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.1207  max mem: 31830
Epoch: [234]  [210/312]  eta: 0:00:58  lr: 0.000514  min_lr: 0.000514  loss: 3.5919 (3.3568)  weight_decay: 0.0500 (0.0500)  time: 0.6648  data: 0.1583  max mem: 31830
Epoch: [234]  [220/312]  eta: 0:00:52  lr: 0.000514  min_lr: 0.000514  loss: 3.5462 (3.3599)  weight_decay: 0.0500 (0.0500)  time: 0.5390  data: 0.0714  max mem: 31830
Epoch: [234]  [230/312]  eta: 0:00:46  lr: 0.000514  min_lr: 0.000514  loss: 3.4045 (3.3553)  weight_decay: 0.0500 (0.0500)  time: 0.5067  data: 0.0477  max mem: 31830
Epoch: [234]  [240/312]  eta: 0:00:41  lr: 0.000513  min_lr: 0.000513  loss: 3.2615 (3.3469)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0669  max mem: 31830
Epoch: [234]  [250/312]  eta: 0:00:35  lr: 0.000513  min_lr: 0.000513  loss: 3.3317 (3.3479)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.0933  max mem: 31830
Epoch: [234]  [260/312]  eta: 0:00:29  lr: 0.000512  min_lr: 0.000512  loss: 3.3532 (3.3507)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0746  max mem: 31830
Epoch: [234]  [270/312]  eta: 0:00:23  lr: 0.000512  min_lr: 0.000512  loss: 3.4609 (3.3534)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0804  max mem: 31830
Epoch: [234]  [280/312]  eta: 0:00:18  lr: 0.000511  min_lr: 0.000511  loss: 3.4973 (3.3537)  weight_decay: 0.0500 (0.0500)  time: 0.5884  data: 0.1124  max mem: 31830
Epoch: [234]  [290/312]  eta: 0:00:12  lr: 0.000511  min_lr: 0.000511  loss: 3.1861 (3.3464)  weight_decay: 0.0500 (0.0500)  time: 0.5943  data: 0.0505  max mem: 31830
Epoch: [234]  [300/312]  eta: 0:00:06  lr: 0.000510  min_lr: 0.000510  loss: 3.3482 (3.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4838  data: 0.0270  max mem: 31830
Epoch: [234]  [310/312]  eta: 0:00:01  lr: 0.000510  min_lr: 0.000510  loss: 3.1948 (3.3419)  weight_decay: 0.0500 (0.0500)  time: 0.4073  data: 0.0270  max mem: 31830
Epoch: [234]  [311/312]  eta: 0:00:00  lr: 0.000510  min_lr: 0.000510  loss: 3.1948 (3.3431)  weight_decay: 0.0500 (0.0500)  time: 0.4072  data: 0.0270  max mem: 31830
Epoch: [234] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.000510  min_lr: 0.000510  loss: 3.1948 (3.3096)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9043 (0.9043)  acc1: 81.7708 (81.7708)  acc5: 96.0938 (96.0938)  time: 8.7999  data: 8.6323  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3064 (1.1991)  acc1: 75.9115 (75.5040)  acc5: 93.0990 (93.0720)  time: 1.1148  data: 0.9787  max mem: 31830
Test: Total time: 0:00:10 (1.1245 s / it)
* Acc@1 75.814 Acc@5 93.216 loss 1.196
Accuracy of the model on the 50000 test images: 75.8%
Max accuracy: 75.98%
Epoch: [235]  [  0/312]  eta: 1:06:10  lr: 0.000510  min_lr: 0.000510  loss: 3.5836 (3.5836)  weight_decay: 0.0500 (0.0500)  time: 12.7250  data: 12.1263  max mem: 31830
Epoch: [235]  [ 10/312]  eta: 0:09:05  lr: 0.000509  min_lr: 0.000509  loss: 3.3640 (3.2294)  weight_decay: 0.0500 (0.0500)  time: 1.8070  data: 1.1031  max mem: 31830
Epoch: [235]  [ 20/312]  eta: 0:05:33  lr: 0.000509  min_lr: 0.000509  loss: 3.3640 (3.2354)  weight_decay: 0.0500 (0.0500)  time: 0.5645  data: 0.0007  max mem: 31830
Epoch: [235]  [ 30/312]  eta: 0:04:14  lr: 0.000508  min_lr: 0.000508  loss: 3.5127 (3.2780)  weight_decay: 0.0500 (0.0500)  time: 0.4068  data: 0.0018  max mem: 31830
Epoch: [235]  [ 40/312]  eta: 0:03:32  lr: 0.000508  min_lr: 0.000508  loss: 3.5127 (3.2919)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0019  max mem: 31830
Epoch: [235]  [ 50/312]  eta: 0:03:04  lr: 0.000507  min_lr: 0.000507  loss: 3.4911 (3.3008)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0012  max mem: 31830
Epoch: [235]  [ 60/312]  eta: 0:02:45  lr: 0.000507  min_lr: 0.000507  loss: 3.3839 (3.2925)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0013  max mem: 31830
Epoch: [235]  [ 70/312]  eta: 0:02:31  lr: 0.000506  min_lr: 0.000506  loss: 3.3839 (3.2969)  weight_decay: 0.0500 (0.0500)  time: 0.4198  data: 0.0155  max mem: 31830
Epoch: [235]  [ 80/312]  eta: 0:02:23  lr: 0.000506  min_lr: 0.000506  loss: 3.3611 (3.3048)  weight_decay: 0.0500 (0.0500)  time: 0.4981  data: 0.0695  max mem: 31830
Epoch: [235]  [ 90/312]  eta: 0:02:14  lr: 0.000505  min_lr: 0.000505  loss: 3.3534 (3.2917)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0610  max mem: 31830
Epoch: [235]  [100/312]  eta: 0:02:07  lr: 0.000505  min_lr: 0.000505  loss: 3.3709 (3.3050)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0653  max mem: 31830
Epoch: [235]  [110/312]  eta: 0:02:00  lr: 0.000504  min_lr: 0.000504  loss: 3.3591 (3.2995)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0809  max mem: 31830
Epoch: [235]  [120/312]  eta: 0:01:52  lr: 0.000504  min_lr: 0.000504  loss: 3.3441 (3.3104)  weight_decay: 0.0500 (0.0500)  time: 0.5256  data: 0.0477  max mem: 31830
Epoch: [235]  [130/312]  eta: 0:01:47  lr: 0.000503  min_lr: 0.000503  loss: 3.2642 (3.2981)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0506  max mem: 31830
Epoch: [235]  [140/312]  eta: 0:01:40  lr: 0.000503  min_lr: 0.000503  loss: 3.2642 (3.3102)  weight_decay: 0.0500 (0.0500)  time: 0.5551  data: 0.0402  max mem: 31830
Epoch: [235]  [150/312]  eta: 0:01:34  lr: 0.000502  min_lr: 0.000502  loss: 3.2978 (3.2965)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0426  max mem: 31830
Epoch: [235]  [160/312]  eta: 0:01:27  lr: 0.000502  min_lr: 0.000502  loss: 3.2978 (3.3059)  weight_decay: 0.0500 (0.0500)  time: 0.5392  data: 0.0328  max mem: 31830
Epoch: [235]  [170/312]  eta: 0:01:21  lr: 0.000501  min_lr: 0.000501  loss: 3.5298 (3.3162)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0212  max mem: 31830
Epoch: [235]  [180/312]  eta: 0:01:16  lr: 0.000501  min_lr: 0.000501  loss: 3.3391 (3.3046)  weight_decay: 0.0500 (0.0500)  time: 0.5898  data: 0.0322  max mem: 31830
Epoch: [235]  [190/312]  eta: 0:01:09  lr: 0.000501  min_lr: 0.000501  loss: 3.3649 (3.3076)  weight_decay: 0.0500 (0.0500)  time: 0.5632  data: 0.0232  max mem: 31830
Epoch: [235]  [200/312]  eta: 0:01:04  lr: 0.000500  min_lr: 0.000500  loss: 3.3895 (3.3029)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0199  max mem: 31830
Epoch: [235]  [210/312]  eta: 0:00:58  lr: 0.000500  min_lr: 0.000500  loss: 3.3257 (3.3049)  weight_decay: 0.0500 (0.0500)  time: 0.6262  data: 0.0187  max mem: 31830
Epoch: [235]  [220/312]  eta: 0:00:52  lr: 0.000499  min_lr: 0.000499  loss: 3.3257 (3.3057)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0114  max mem: 31830
Epoch: [235]  [230/312]  eta: 0:00:47  lr: 0.000499  min_lr: 0.000499  loss: 3.2483 (3.2997)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.0069  max mem: 31830
Epoch: [235]  [240/312]  eta: 0:00:41  lr: 0.000498  min_lr: 0.000498  loss: 3.1008 (3.2894)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0199  max mem: 31830
Epoch: [235]  [250/312]  eta: 0:00:35  lr: 0.000498  min_lr: 0.000498  loss: 3.2287 (3.2948)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0481  max mem: 31830
Epoch: [235]  [260/312]  eta: 0:00:29  lr: 0.000497  min_lr: 0.000497  loss: 3.4723 (3.2911)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.0297  max mem: 31830
Epoch: [235]  [270/312]  eta: 0:00:23  lr: 0.000497  min_lr: 0.000497  loss: 3.4069 (3.2933)  weight_decay: 0.0500 (0.0500)  time: 0.5454  data: 0.0467  max mem: 31830
Epoch: [235]  [280/312]  eta: 0:00:18  lr: 0.000496  min_lr: 0.000496  loss: 3.2662 (3.2855)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0506  max mem: 31830
Epoch: [235]  [290/312]  eta: 0:00:12  lr: 0.000496  min_lr: 0.000496  loss: 3.3679 (3.2948)  weight_decay: 0.0500 (0.0500)  time: 0.5788  data: 0.0112  max mem: 31830
Epoch: [235]  [300/312]  eta: 0:00:06  lr: 0.000495  min_lr: 0.000495  loss: 3.4936 (3.2912)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0154  max mem: 31830
Epoch: [235]  [310/312]  eta: 0:00:01  lr: 0.000495  min_lr: 0.000495  loss: 3.4211 (3.2946)  weight_decay: 0.0500 (0.0500)  time: 0.3888  data: 0.0086  max mem: 31830
Epoch: [235]  [311/312]  eta: 0:00:00  lr: 0.000495  min_lr: 0.000495  loss: 3.4622 (3.2955)  weight_decay: 0.0500 (0.0500)  time: 0.3886  data: 0.0086  max mem: 31830
Epoch: [235] Total time: 0:02:55 (0.5613 s / it)
Averaged stats: lr: 0.000495  min_lr: 0.000495  loss: 3.4622 (3.3149)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.9588 (0.9588)  acc1: 82.6823 (82.6823)  acc5: 96.0938 (96.0938)  time: 8.8987  data: 8.7315  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3121 (1.2234)  acc1: 75.9115 (75.9840)  acc5: 92.7083 (93.0400)  time: 1.1060  data: 0.9702  max mem: 31830
Test: Total time: 0:00:10 (1.1162 s / it)
* Acc@1 76.254 Acc@5 93.236 loss 1.225
Accuracy of the model on the 50000 test images: 76.3%
Max accuracy: 76.25%
Epoch: [236]  [  0/312]  eta: 1:04:10  lr: 0.000495  min_lr: 0.000495  loss: 3.3521 (3.3521)  weight_decay: 0.0500 (0.0500)  time: 12.3428  data: 11.4037  max mem: 31830
Epoch: [236]  [ 10/312]  eta: 0:08:37  lr: 0.000494  min_lr: 0.000494  loss: 3.3521 (3.1837)  weight_decay: 0.0500 (0.0500)  time: 1.7134  data: 1.0373  max mem: 31830
Epoch: [236]  [ 20/312]  eta: 0:05:23  lr: 0.000494  min_lr: 0.000494  loss: 3.4366 (3.2508)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0233  max mem: 31830
Epoch: [236]  [ 30/312]  eta: 0:04:07  lr: 0.000493  min_lr: 0.000493  loss: 3.1308 (3.1675)  weight_decay: 0.0500 (0.0500)  time: 0.4164  data: 0.0233  max mem: 31830
Epoch: [236]  [ 40/312]  eta: 0:03:26  lr: 0.000493  min_lr: 0.000493  loss: 3.1308 (3.2255)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0008  max mem: 31830
Epoch: [236]  [ 50/312]  eta: 0:03:00  lr: 0.000492  min_lr: 0.000492  loss: 3.3974 (3.2249)  weight_decay: 0.0500 (0.0500)  time: 0.4023  data: 0.0010  max mem: 31830
Epoch: [236]  [ 60/312]  eta: 0:02:41  lr: 0.000492  min_lr: 0.000492  loss: 3.4185 (3.2516)  weight_decay: 0.0500 (0.0500)  time: 0.4011  data: 0.0016  max mem: 31830
Epoch: [236]  [ 70/312]  eta: 0:02:32  lr: 0.000491  min_lr: 0.000491  loss: 3.3436 (3.2093)  weight_decay: 0.0500 (0.0500)  time: 0.4772  data: 0.0370  max mem: 31830
Epoch: [236]  [ 80/312]  eta: 0:02:24  lr: 0.000491  min_lr: 0.000491  loss: 3.1458 (3.1981)  weight_decay: 0.0500 (0.0500)  time: 0.5636  data: 0.1010  max mem: 31830
Epoch: [236]  [ 90/312]  eta: 0:02:14  lr: 0.000490  min_lr: 0.000490  loss: 3.2305 (3.1964)  weight_decay: 0.0500 (0.0500)  time: 0.5116  data: 0.0662  max mem: 31830
Epoch: [236]  [100/312]  eta: 0:02:08  lr: 0.000490  min_lr: 0.000490  loss: 3.5038 (3.2224)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0428  max mem: 31830
Epoch: [236]  [110/312]  eta: 0:01:59  lr: 0.000490  min_lr: 0.000490  loss: 3.5353 (3.2332)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0421  max mem: 31830
Epoch: [236]  [120/312]  eta: 0:01:53  lr: 0.000489  min_lr: 0.000489  loss: 3.4174 (3.2287)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0581  max mem: 31830
Epoch: [236]  [130/312]  eta: 0:01:47  lr: 0.000489  min_lr: 0.000489  loss: 3.4697 (3.2510)  weight_decay: 0.0500 (0.0500)  time: 0.5926  data: 0.0852  max mem: 31830
Epoch: [236]  [140/312]  eta: 0:01:39  lr: 0.000488  min_lr: 0.000488  loss: 3.3998 (3.2424)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0281  max mem: 31830
Epoch: [236]  [150/312]  eta: 0:01:34  lr: 0.000488  min_lr: 0.000488  loss: 3.1747 (3.2460)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0258  max mem: 31830
Epoch: [236]  [160/312]  eta: 0:01:28  lr: 0.000487  min_lr: 0.000487  loss: 3.3780 (3.2476)  weight_decay: 0.0500 (0.0500)  time: 0.5982  data: 0.0549  max mem: 31830
Epoch: [236]  [170/312]  eta: 0:01:21  lr: 0.000487  min_lr: 0.000487  loss: 3.5519 (3.2611)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0300  max mem: 31830
Epoch: [236]  [180/312]  eta: 0:01:16  lr: 0.000486  min_lr: 0.000486  loss: 3.4124 (3.2561)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0381  max mem: 31830
Epoch: [236]  [190/312]  eta: 0:01:09  lr: 0.000486  min_lr: 0.000486  loss: 3.2497 (3.2616)  weight_decay: 0.0500 (0.0500)  time: 0.5584  data: 0.0388  max mem: 31830
Epoch: [236]  [200/312]  eta: 0:01:04  lr: 0.000485  min_lr: 0.000485  loss: 3.4033 (3.2551)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.0373  max mem: 31830
Epoch: [236]  [210/312]  eta: 0:00:58  lr: 0.000485  min_lr: 0.000485  loss: 3.4964 (3.2715)  weight_decay: 0.0500 (0.0500)  time: 0.5839  data: 0.0660  max mem: 31830
Epoch: [236]  [220/312]  eta: 0:00:52  lr: 0.000484  min_lr: 0.000484  loss: 3.4959 (3.2661)  weight_decay: 0.0500 (0.0500)  time: 0.5372  data: 0.0303  max mem: 31830
Epoch: [236]  [230/312]  eta: 0:00:46  lr: 0.000484  min_lr: 0.000484  loss: 3.2963 (3.2707)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0142  max mem: 31830
Epoch: [236]  [240/312]  eta: 0:00:41  lr: 0.000483  min_lr: 0.000483  loss: 3.2284 (3.2613)  weight_decay: 0.0500 (0.0500)  time: 0.5802  data: 0.0549  max mem: 31830
Epoch: [236]  [250/312]  eta: 0:00:35  lr: 0.000483  min_lr: 0.000483  loss: 3.1298 (3.2565)  weight_decay: 0.0500 (0.0500)  time: 0.5686  data: 0.0416  max mem: 31830
Epoch: [236]  [260/312]  eta: 0:00:29  lr: 0.000482  min_lr: 0.000482  loss: 3.2497 (3.2537)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0427  max mem: 31830
Epoch: [236]  [270/312]  eta: 0:00:23  lr: 0.000482  min_lr: 0.000482  loss: 3.3873 (3.2553)  weight_decay: 0.0500 (0.0500)  time: 0.5509  data: 0.0479  max mem: 31830
Epoch: [236]  [280/312]  eta: 0:00:18  lr: 0.000482  min_lr: 0.000482  loss: 3.5181 (3.2624)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0252  max mem: 31830
Epoch: [236]  [290/312]  eta: 0:00:12  lr: 0.000481  min_lr: 0.000481  loss: 3.4879 (3.2622)  weight_decay: 0.0500 (0.0500)  time: 0.5628  data: 0.0328  max mem: 31830
Epoch: [236]  [300/312]  eta: 0:00:06  lr: 0.000481  min_lr: 0.000481  loss: 3.2330 (3.2600)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0218  max mem: 31830
Epoch: [236]  [310/312]  eta: 0:00:01  lr: 0.000480  min_lr: 0.000480  loss: 3.3526 (3.2617)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0086  max mem: 31830
Epoch: [236]  [311/312]  eta: 0:00:00  lr: 0.000480  min_lr: 0.000480  loss: 3.2330 (3.2587)  weight_decay: 0.0500 (0.0500)  time: 0.3941  data: 0.0086  max mem: 31830
Epoch: [236] Total time: 0:02:53 (0.5577 s / it)
Averaged stats: lr: 0.000480  min_lr: 0.000480  loss: 3.2330 (3.2986)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8564 (0.8564)  acc1: 82.8125 (82.8125)  acc5: 95.7031 (95.7031)  time: 8.7382  data: 8.5744  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2492 (1.1492)  acc1: 75.3906 (75.6000)  acc5: 92.7083 (92.9440)  time: 1.0876  data: 0.9528  max mem: 31830
Test: Total time: 0:00:10 (1.1167 s / it)
* Acc@1 75.918 Acc@5 93.144 loss 1.144
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 76.25%
Epoch: [237]  [  0/312]  eta: 1:07:20  lr: 0.000480  min_lr: 0.000480  loss: 2.5892 (2.5892)  weight_decay: 0.0500 (0.0500)  time: 12.9488  data: 10.2810  max mem: 31830
Epoch: [237]  [ 10/312]  eta: 0:09:07  lr: 0.000480  min_lr: 0.000480  loss: 2.9032 (2.9881)  weight_decay: 0.0500 (0.0500)  time: 1.8123  data: 0.9352  max mem: 31830
Epoch: [237]  [ 20/312]  eta: 0:05:41  lr: 0.000479  min_lr: 0.000479  loss: 3.3952 (3.1405)  weight_decay: 0.0500 (0.0500)  time: 0.5810  data: 0.0384  max mem: 31830
Epoch: [237]  [ 30/312]  eta: 0:04:19  lr: 0.000479  min_lr: 0.000479  loss: 3.3151 (3.1858)  weight_decay: 0.0500 (0.0500)  time: 0.4300  data: 0.0390  max mem: 31830
Epoch: [237]  [ 40/312]  eta: 0:03:35  lr: 0.000478  min_lr: 0.000478  loss: 3.2259 (3.1999)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0020  max mem: 31830
Epoch: [237]  [ 50/312]  eta: 0:03:07  lr: 0.000478  min_lr: 0.000478  loss: 3.5454 (3.2666)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0017  max mem: 31830
Epoch: [237]  [ 60/312]  eta: 0:02:47  lr: 0.000477  min_lr: 0.000477  loss: 3.5506 (3.2695)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0010  max mem: 31830
Epoch: [237]  [ 70/312]  eta: 0:02:31  lr: 0.000477  min_lr: 0.000477  loss: 3.4062 (3.2665)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0008  max mem: 31830
Epoch: [237]  [ 80/312]  eta: 0:02:21  lr: 0.000476  min_lr: 0.000476  loss: 3.4943 (3.2916)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0009  max mem: 31830
Epoch: [237]  [ 90/312]  eta: 0:02:15  lr: 0.000476  min_lr: 0.000476  loss: 3.5410 (3.3037)  weight_decay: 0.0500 (0.0500)  time: 0.5423  data: 0.0338  max mem: 31830
Epoch: [237]  [100/312]  eta: 0:02:05  lr: 0.000475  min_lr: 0.000475  loss: 3.2468 (3.2913)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0494  max mem: 31830
Epoch: [237]  [110/312]  eta: 0:01:59  lr: 0.000475  min_lr: 0.000475  loss: 3.1144 (3.2877)  weight_decay: 0.0500 (0.0500)  time: 0.5196  data: 0.0569  max mem: 31830
Epoch: [237]  [120/312]  eta: 0:01:52  lr: 0.000474  min_lr: 0.000474  loss: 3.4881 (3.2901)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0482  max mem: 31830
Epoch: [237]  [130/312]  eta: 0:01:47  lr: 0.000474  min_lr: 0.000474  loss: 3.2683 (3.2892)  weight_decay: 0.0500 (0.0500)  time: 0.5718  data: 0.0611  max mem: 31830
Epoch: [237]  [140/312]  eta: 0:01:40  lr: 0.000474  min_lr: 0.000474  loss: 3.3817 (3.2953)  weight_decay: 0.0500 (0.0500)  time: 0.5822  data: 0.1010  max mem: 31830
Epoch: [237]  [150/312]  eta: 0:01:33  lr: 0.000473  min_lr: 0.000473  loss: 3.5277 (3.3027)  weight_decay: 0.0500 (0.0500)  time: 0.5053  data: 0.0476  max mem: 31830
Epoch: [237]  [160/312]  eta: 0:01:28  lr: 0.000473  min_lr: 0.000473  loss: 3.2974 (3.2952)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0359  max mem: 31830
Epoch: [237]  [170/312]  eta: 0:01:22  lr: 0.000472  min_lr: 0.000472  loss: 3.3913 (3.3070)  weight_decay: 0.0500 (0.0500)  time: 0.5741  data: 0.0627  max mem: 31830
Epoch: [237]  [180/312]  eta: 0:01:15  lr: 0.000472  min_lr: 0.000472  loss: 3.5428 (3.3256)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0467  max mem: 31830
Epoch: [237]  [190/312]  eta: 0:01:10  lr: 0.000471  min_lr: 0.000471  loss: 3.5720 (3.3248)  weight_decay: 0.0500 (0.0500)  time: 0.5700  data: 0.0556  max mem: 31830
Epoch: [237]  [200/312]  eta: 0:01:03  lr: 0.000471  min_lr: 0.000471  loss: 3.2450 (3.3201)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0365  max mem: 31830
Epoch: [237]  [210/312]  eta: 0:00:58  lr: 0.000470  min_lr: 0.000470  loss: 3.2669 (3.3183)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0335  max mem: 31830
Epoch: [237]  [220/312]  eta: 0:00:52  lr: 0.000470  min_lr: 0.000470  loss: 3.4646 (3.3241)  weight_decay: 0.0500 (0.0500)  time: 0.6516  data: 0.0487  max mem: 31830
Epoch: [237]  [230/312]  eta: 0:00:46  lr: 0.000469  min_lr: 0.000469  loss: 3.3830 (3.3065)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0160  max mem: 31830
Epoch: [237]  [240/312]  eta: 0:00:41  lr: 0.000469  min_lr: 0.000469  loss: 3.3418 (3.3141)  weight_decay: 0.0500 (0.0500)  time: 0.5593  data: 0.0437  max mem: 31830
Epoch: [237]  [250/312]  eta: 0:00:35  lr: 0.000468  min_lr: 0.000468  loss: 3.3571 (3.3116)  weight_decay: 0.0500 (0.0500)  time: 0.6331  data: 0.0437  max mem: 31830
Epoch: [237]  [260/312]  eta: 0:00:29  lr: 0.000468  min_lr: 0.000468  loss: 3.2604 (3.3105)  weight_decay: 0.0500 (0.0500)  time: 0.5160  data: 0.0008  max mem: 31830
Epoch: [237]  [270/312]  eta: 0:00:24  lr: 0.000468  min_lr: 0.000468  loss: 3.2537 (3.2988)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.0008  max mem: 31830
Epoch: [237]  [280/312]  eta: 0:00:18  lr: 0.000467  min_lr: 0.000467  loss: 2.7722 (3.2910)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0046  max mem: 31830
Epoch: [237]  [290/312]  eta: 0:00:12  lr: 0.000467  min_lr: 0.000467  loss: 3.0344 (3.2864)  weight_decay: 0.0500 (0.0500)  time: 0.5037  data: 0.0118  max mem: 31830
Epoch: [237]  [300/312]  eta: 0:00:06  lr: 0.000466  min_lr: 0.000466  loss: 3.3122 (3.2822)  weight_decay: 0.0500 (0.0500)  time: 0.5035  data: 0.0077  max mem: 31830
Epoch: [237]  [310/312]  eta: 0:00:01  lr: 0.000466  min_lr: 0.000466  loss: 3.2504 (3.2848)  weight_decay: 0.0500 (0.0500)  time: 0.3932  data: 0.0002  max mem: 31830
Epoch: [237]  [311/312]  eta: 0:00:00  lr: 0.000466  min_lr: 0.000466  loss: 3.2504 (3.2849)  weight_decay: 0.0500 (0.0500)  time: 0.3930  data: 0.0002  max mem: 31830
Epoch: [237] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.000466  min_lr: 0.000466  loss: 3.2504 (3.2865)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.9633 (0.9633)  acc1: 83.2031 (83.2031)  acc5: 96.0938 (96.0938)  time: 7.9284  data: 7.7659  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2468 (1.1675)  acc1: 76.8229 (76.2720)  acc5: 93.0990 (93.0560)  time: 1.0486  data: 0.9121  max mem: 31830
Test: Total time: 0:00:09 (1.0604 s / it)
* Acc@1 76.464 Acc@5 93.348 loss 1.160
Accuracy of the model on the 50000 test images: 76.5%
Max accuracy: 76.46%
Epoch: [238]  [  0/312]  eta: 1:03:01  lr: 0.000466  min_lr: 0.000466  loss: 3.4360 (3.4360)  weight_decay: 0.0500 (0.0500)  time: 12.1189  data: 8.3222  max mem: 31830
Epoch: [238]  [ 10/312]  eta: 0:08:40  lr: 0.000465  min_lr: 0.000465  loss: 3.3829 (3.3161)  weight_decay: 0.0500 (0.0500)  time: 1.7250  data: 1.0292  max mem: 31830
Epoch: [238]  [ 20/312]  eta: 0:05:21  lr: 0.000465  min_lr: 0.000465  loss: 3.3829 (3.3160)  weight_decay: 0.0500 (0.0500)  time: 0.5494  data: 0.1630  max mem: 31830
Epoch: [238]  [ 30/312]  eta: 0:04:06  lr: 0.000464  min_lr: 0.000464  loss: 3.3902 (3.2697)  weight_decay: 0.0500 (0.0500)  time: 0.4052  data: 0.0140  max mem: 31830
Epoch: [238]  [ 40/312]  eta: 0:03:25  lr: 0.000464  min_lr: 0.000464  loss: 3.4044 (3.2973)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0013  max mem: 31830
Epoch: [238]  [ 50/312]  eta: 0:03:00  lr: 0.000463  min_lr: 0.000463  loss: 3.4044 (3.2979)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0009  max mem: 31830
Epoch: [238]  [ 60/312]  eta: 0:02:41  lr: 0.000463  min_lr: 0.000463  loss: 3.3526 (3.2980)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [238]  [ 70/312]  eta: 0:02:30  lr: 0.000462  min_lr: 0.000462  loss: 3.5259 (3.3328)  weight_decay: 0.0500 (0.0500)  time: 0.4599  data: 0.0171  max mem: 31830
Epoch: [238]  [ 80/312]  eta: 0:02:22  lr: 0.000462  min_lr: 0.000462  loss: 3.5259 (3.3467)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.0812  max mem: 31830
Epoch: [238]  [ 90/312]  eta: 0:02:12  lr: 0.000461  min_lr: 0.000461  loss: 3.4573 (3.3309)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0834  max mem: 31830
Epoch: [238]  [100/312]  eta: 0:02:05  lr: 0.000461  min_lr: 0.000461  loss: 3.5585 (3.3602)  weight_decay: 0.0500 (0.0500)  time: 0.5144  data: 0.0981  max mem: 31830
Epoch: [238]  [110/312]  eta: 0:01:58  lr: 0.000461  min_lr: 0.000461  loss: 3.5572 (3.3550)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.1268  max mem: 31830
Epoch: [238]  [120/312]  eta: 0:01:51  lr: 0.000460  min_lr: 0.000460  loss: 3.3001 (3.3406)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.1264  max mem: 31830
Epoch: [238]  [130/312]  eta: 0:01:46  lr: 0.000460  min_lr: 0.000460  loss: 3.5018 (3.3539)  weight_decay: 0.0500 (0.0500)  time: 0.5963  data: 0.1865  max mem: 31830
Epoch: [238]  [140/312]  eta: 0:01:38  lr: 0.000459  min_lr: 0.000459  loss: 3.6441 (3.3645)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.1079  max mem: 31830
Epoch: [238]  [150/312]  eta: 0:01:32  lr: 0.000459  min_lr: 0.000459  loss: 3.2610 (3.3489)  weight_decay: 0.0500 (0.0500)  time: 0.4856  data: 0.0834  max mem: 31830
Epoch: [238]  [160/312]  eta: 0:01:27  lr: 0.000458  min_lr: 0.000458  loss: 3.2510 (3.3366)  weight_decay: 0.0500 (0.0500)  time: 0.5870  data: 0.1426  max mem: 31830
Epoch: [238]  [170/312]  eta: 0:01:20  lr: 0.000458  min_lr: 0.000458  loss: 3.4113 (3.3384)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0947  max mem: 31830
Epoch: [238]  [180/312]  eta: 0:01:15  lr: 0.000457  min_lr: 0.000457  loss: 3.3620 (3.3266)  weight_decay: 0.0500 (0.0500)  time: 0.5510  data: 0.1145  max mem: 31830
Epoch: [238]  [190/312]  eta: 0:01:09  lr: 0.000457  min_lr: 0.000457  loss: 3.2099 (3.3168)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0849  max mem: 31830
Epoch: [238]  [200/312]  eta: 0:01:03  lr: 0.000456  min_lr: 0.000456  loss: 3.2913 (3.3165)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0496  max mem: 31830
Epoch: [238]  [210/312]  eta: 0:00:57  lr: 0.000456  min_lr: 0.000456  loss: 3.4235 (3.3235)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0874  max mem: 31830
Epoch: [238]  [220/312]  eta: 0:00:52  lr: 0.000456  min_lr: 0.000456  loss: 3.4753 (3.3300)  weight_decay: 0.0500 (0.0500)  time: 0.5667  data: 0.0927  max mem: 31830
Epoch: [238]  [230/312]  eta: 0:00:46  lr: 0.000455  min_lr: 0.000455  loss: 3.4753 (3.3313)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.1068  max mem: 31830
Epoch: [238]  [240/312]  eta: 0:00:40  lr: 0.000455  min_lr: 0.000455  loss: 3.3286 (3.3284)  weight_decay: 0.0500 (0.0500)  time: 0.5344  data: 0.0764  max mem: 31830
Epoch: [238]  [250/312]  eta: 0:00:34  lr: 0.000454  min_lr: 0.000454  loss: 3.3286 (3.3202)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0724  max mem: 31830
Epoch: [238]  [260/312]  eta: 0:00:29  lr: 0.000454  min_lr: 0.000454  loss: 3.1523 (3.3179)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.1103  max mem: 31830
Epoch: [238]  [270/312]  eta: 0:00:23  lr: 0.000453  min_lr: 0.000453  loss: 3.3298 (3.3191)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0629  max mem: 31830
Epoch: [238]  [280/312]  eta: 0:00:17  lr: 0.000453  min_lr: 0.000453  loss: 3.3409 (3.3196)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0668  max mem: 31830
Epoch: [238]  [290/312]  eta: 0:00:12  lr: 0.000452  min_lr: 0.000452  loss: 3.0178 (3.3083)  weight_decay: 0.0500 (0.0500)  time: 0.5972  data: 0.1543  max mem: 31830
Epoch: [238]  [300/312]  eta: 0:00:06  lr: 0.000452  min_lr: 0.000452  loss: 2.9940 (3.3007)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0936  max mem: 31830
Epoch: [238]  [310/312]  eta: 0:00:01  lr: 0.000451  min_lr: 0.000451  loss: 3.3593 (3.3034)  weight_decay: 0.0500 (0.0500)  time: 0.3849  data: 0.0001  max mem: 31830
Epoch: [238]  [311/312]  eta: 0:00:00  lr: 0.000451  min_lr: 0.000451  loss: 3.4838 (3.3040)  weight_decay: 0.0500 (0.0500)  time: 0.3848  data: 0.0001  max mem: 31830
Epoch: [238] Total time: 0:02:52 (0.5544 s / it)
Averaged stats: lr: 0.000451  min_lr: 0.000451  loss: 3.4838 (3.2986)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.9844 (0.9844)  acc1: 83.9844 (83.9844)  acc5: 96.6146 (96.6146)  time: 9.0674  data: 8.9000  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3196 (1.2290)  acc1: 75.6510 (76.1440)  acc5: 92.4479 (93.2480)  time: 1.1307  data: 0.9954  max mem: 31830
Test: Total time: 0:00:10 (1.1660 s / it)
* Acc@1 76.368 Acc@5 93.476 loss 1.228
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.46%
Epoch: [239]  [  0/312]  eta: 1:00:53  lr: 0.000451  min_lr: 0.000451  loss: 3.5801 (3.5801)  weight_decay: 0.0500 (0.0500)  time: 11.7115  data: 11.3271  max mem: 31830
Epoch: [239]  [ 10/312]  eta: 0:08:17  lr: 0.000451  min_lr: 0.000451  loss: 3.3403 (3.2270)  weight_decay: 0.0500 (0.0500)  time: 1.6490  data: 1.0303  max mem: 31830
Epoch: [239]  [ 20/312]  eta: 0:05:21  lr: 0.000450  min_lr: 0.000450  loss: 3.3403 (3.2537)  weight_decay: 0.0500 (0.0500)  time: 0.5721  data: 0.0154  max mem: 31830
Epoch: [239]  [ 30/312]  eta: 0:04:06  lr: 0.000450  min_lr: 0.000450  loss: 3.3537 (3.2834)  weight_decay: 0.0500 (0.0500)  time: 0.4506  data: 0.0156  max mem: 31830
Epoch: [239]  [ 40/312]  eta: 0:03:26  lr: 0.000449  min_lr: 0.000449  loss: 3.5454 (3.3564)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0009  max mem: 31830
Epoch: [239]  [ 50/312]  eta: 0:03:09  lr: 0.000449  min_lr: 0.000449  loss: 3.5142 (3.2952)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0133  max mem: 31830
Epoch: [239]  [ 60/312]  eta: 0:02:48  lr: 0.000449  min_lr: 0.000449  loss: 2.9030 (3.2398)  weight_decay: 0.0500 (0.0500)  time: 0.4839  data: 0.0133  max mem: 31830
Epoch: [239]  [ 70/312]  eta: 0:02:39  lr: 0.000448  min_lr: 0.000448  loss: 3.2619 (3.3012)  weight_decay: 0.0500 (0.0500)  time: 0.4913  data: 0.0172  max mem: 31830
Epoch: [239]  [ 80/312]  eta: 0:02:31  lr: 0.000448  min_lr: 0.000448  loss: 3.5834 (3.3059)  weight_decay: 0.0500 (0.0500)  time: 0.6107  data: 0.0369  max mem: 31830
Epoch: [239]  [ 90/312]  eta: 0:02:20  lr: 0.000447  min_lr: 0.000447  loss: 3.4935 (3.3200)  weight_decay: 0.0500 (0.0500)  time: 0.5383  data: 0.0457  max mem: 31830
Epoch: [239]  [100/312]  eta: 0:02:13  lr: 0.000447  min_lr: 0.000447  loss: 3.4459 (3.3196)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0265  max mem: 31830
Epoch: [239]  [110/312]  eta: 0:02:03  lr: 0.000446  min_lr: 0.000446  loss: 3.3271 (3.3260)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0245  max mem: 31830
Epoch: [239]  [120/312]  eta: 0:01:57  lr: 0.000446  min_lr: 0.000446  loss: 3.4213 (3.3341)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0299  max mem: 31830
Epoch: [239]  [130/312]  eta: 0:01:50  lr: 0.000445  min_lr: 0.000445  loss: 3.4920 (3.3328)  weight_decay: 0.0500 (0.0500)  time: 0.5974  data: 0.0072  max mem: 31830
Epoch: [239]  [140/312]  eta: 0:01:42  lr: 0.000445  min_lr: 0.000445  loss: 3.1007 (3.3228)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0012  max mem: 31830
Epoch: [239]  [150/312]  eta: 0:01:37  lr: 0.000445  min_lr: 0.000445  loss: 3.4205 (3.3305)  weight_decay: 0.0500 (0.0500)  time: 0.5550  data: 0.0397  max mem: 31830
Epoch: [239]  [160/312]  eta: 0:01:31  lr: 0.000444  min_lr: 0.000444  loss: 3.5106 (3.3411)  weight_decay: 0.0500 (0.0500)  time: 0.6405  data: 0.0397  max mem: 31830
Epoch: [239]  [170/312]  eta: 0:01:23  lr: 0.000444  min_lr: 0.000444  loss: 3.4996 (3.3562)  weight_decay: 0.0500 (0.0500)  time: 0.4819  data: 0.0010  max mem: 31830
Epoch: [239]  [180/312]  eta: 0:01:17  lr: 0.000443  min_lr: 0.000443  loss: 3.6154 (3.3591)  weight_decay: 0.0500 (0.0500)  time: 0.5116  data: 0.0011  max mem: 31830
Epoch: [239]  [190/312]  eta: 0:01:11  lr: 0.000443  min_lr: 0.000443  loss: 3.5213 (3.3562)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0290  max mem: 31830
Epoch: [239]  [200/312]  eta: 0:01:05  lr: 0.000442  min_lr: 0.000442  loss: 3.2903 (3.3468)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0461  max mem: 31830
Epoch: [239]  [210/312]  eta: 0:00:59  lr: 0.000442  min_lr: 0.000442  loss: 3.2901 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.0180  max mem: 31830
Epoch: [239]  [220/312]  eta: 0:00:53  lr: 0.000441  min_lr: 0.000441  loss: 3.2901 (3.3403)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0366  max mem: 31830
Epoch: [239]  [230/312]  eta: 0:00:47  lr: 0.000441  min_lr: 0.000441  loss: 3.4115 (3.3446)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0666  max mem: 31830
Epoch: [239]  [240/312]  eta: 0:00:41  lr: 0.000440  min_lr: 0.000440  loss: 3.5881 (3.3523)  weight_decay: 0.0500 (0.0500)  time: 0.5877  data: 0.0312  max mem: 31830
Epoch: [239]  [250/312]  eta: 0:00:35  lr: 0.000440  min_lr: 0.000440  loss: 3.5141 (3.3466)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.0309  max mem: 31830
Epoch: [239]  [260/312]  eta: 0:00:29  lr: 0.000440  min_lr: 0.000440  loss: 3.2141 (3.3365)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0305  max mem: 31830
Epoch: [239]  [270/312]  eta: 0:00:23  lr: 0.000439  min_lr: 0.000439  loss: 3.2141 (3.3321)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0429  max mem: 31830
Epoch: [239]  [280/312]  eta: 0:00:18  lr: 0.000439  min_lr: 0.000439  loss: 3.3694 (3.3308)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0581  max mem: 31830
Epoch: [239]  [290/312]  eta: 0:00:12  lr: 0.000438  min_lr: 0.000438  loss: 3.5494 (3.3370)  weight_decay: 0.0500 (0.0500)  time: 0.5746  data: 0.0158  max mem: 31830
Epoch: [239]  [300/312]  eta: 0:00:06  lr: 0.000438  min_lr: 0.000438  loss: 3.5104 (3.3378)  weight_decay: 0.0500 (0.0500)  time: 0.4858  data: 0.0165  max mem: 31830
Epoch: [239]  [310/312]  eta: 0:00:01  lr: 0.000437  min_lr: 0.000437  loss: 3.3620 (3.3306)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0164  max mem: 31830
Epoch: [239]  [311/312]  eta: 0:00:00  lr: 0.000437  min_lr: 0.000437  loss: 3.4085 (3.3309)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0164  max mem: 31830
Epoch: [239] Total time: 0:02:55 (0.5622 s / it)
Averaged stats: lr: 0.000437  min_lr: 0.000437  loss: 3.4085 (3.2902)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.9797 (0.9797)  acc1: 83.7240 (83.7240)  acc5: 96.0938 (96.0938)  time: 9.0453  data: 8.8862  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2924 (1.2119)  acc1: 74.3490 (75.4560)  acc5: 93.0990 (93.1200)  time: 1.1279  data: 0.9875  max mem: 31830
Test: Total time: 0:00:10 (1.1536 s / it)
* Acc@1 75.988 Acc@5 93.358 loss 1.201
Accuracy of the model on the 50000 test images: 76.0%
Max accuracy: 76.46%
Epoch: [240]  [  0/312]  eta: 1:01:27  lr: 0.000437  min_lr: 0.000437  loss: 2.8968 (2.8968)  weight_decay: 0.0500 (0.0500)  time: 11.8187  data: 9.3182  max mem: 31830
Epoch: [240]  [ 10/312]  eta: 0:08:18  lr: 0.000437  min_lr: 0.000437  loss: 3.4147 (3.4147)  weight_decay: 0.0500 (0.0500)  time: 1.6499  data: 1.0304  max mem: 31830
Epoch: [240]  [ 20/312]  eta: 0:05:14  lr: 0.000436  min_lr: 0.000436  loss: 3.4645 (3.3720)  weight_decay: 0.0500 (0.0500)  time: 0.5414  data: 0.1011  max mem: 31830
Epoch: [240]  [ 30/312]  eta: 0:04:02  lr: 0.000436  min_lr: 0.000436  loss: 3.4638 (3.3611)  weight_decay: 0.0500 (0.0500)  time: 0.4248  data: 0.0007  max mem: 31830
Epoch: [240]  [ 40/312]  eta: 0:03:23  lr: 0.000435  min_lr: 0.000435  loss: 3.3577 (3.3298)  weight_decay: 0.0500 (0.0500)  time: 0.3982  data: 0.0010  max mem: 31830
Epoch: [240]  [ 50/312]  eta: 0:03:04  lr: 0.000435  min_lr: 0.000435  loss: 3.3577 (3.3302)  weight_decay: 0.0500 (0.0500)  time: 0.4622  data: 0.0067  max mem: 31830
Epoch: [240]  [ 60/312]  eta: 0:02:44  lr: 0.000435  min_lr: 0.000435  loss: 3.4573 (3.3434)  weight_decay: 0.0500 (0.0500)  time: 0.4626  data: 0.0065  max mem: 31830
Epoch: [240]  [ 70/312]  eta: 0:02:38  lr: 0.000434  min_lr: 0.000434  loss: 3.4894 (3.3261)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0435  max mem: 31830
Epoch: [240]  [ 80/312]  eta: 0:02:27  lr: 0.000434  min_lr: 0.000434  loss: 3.3094 (3.3106)  weight_decay: 0.0500 (0.0500)  time: 0.5837  data: 0.0435  max mem: 31830
Epoch: [240]  [ 90/312]  eta: 0:02:17  lr: 0.000433  min_lr: 0.000433  loss: 3.2985 (3.2973)  weight_decay: 0.0500 (0.0500)  time: 0.4921  data: 0.0192  max mem: 31830
Epoch: [240]  [100/312]  eta: 0:02:11  lr: 0.000433  min_lr: 0.000433  loss: 3.2985 (3.2880)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0560  max mem: 31830
Epoch: [240]  [110/312]  eta: 0:02:00  lr: 0.000432  min_lr: 0.000432  loss: 3.4562 (3.2866)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0376  max mem: 31830
Epoch: [240]  [120/312]  eta: 0:01:54  lr: 0.000432  min_lr: 0.000432  loss: 3.3989 (3.2853)  weight_decay: 0.0500 (0.0500)  time: 0.4741  data: 0.0214  max mem: 31830
Epoch: [240]  [130/312]  eta: 0:01:47  lr: 0.000431  min_lr: 0.000431  loss: 3.2603 (3.2761)  weight_decay: 0.0500 (0.0500)  time: 0.5578  data: 0.0772  max mem: 31830
Epoch: [240]  [140/312]  eta: 0:01:40  lr: 0.000431  min_lr: 0.000431  loss: 3.1649 (3.2698)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0565  max mem: 31830
Epoch: [240]  [150/312]  eta: 0:01:34  lr: 0.000431  min_lr: 0.000431  loss: 3.2891 (3.2763)  weight_decay: 0.0500 (0.0500)  time: 0.5500  data: 0.0574  max mem: 31830
Epoch: [240]  [160/312]  eta: 0:01:28  lr: 0.000430  min_lr: 0.000430  loss: 3.4252 (3.2764)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.0768  max mem: 31830
Epoch: [240]  [170/312]  eta: 0:01:22  lr: 0.000430  min_lr: 0.000430  loss: 3.5280 (3.2840)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0751  max mem: 31830
Epoch: [240]  [180/312]  eta: 0:01:17  lr: 0.000429  min_lr: 0.000429  loss: 3.4704 (3.2819)  weight_decay: 0.0500 (0.0500)  time: 0.5819  data: 0.1173  max mem: 31830
Epoch: [240]  [190/312]  eta: 0:01:10  lr: 0.000429  min_lr: 0.000429  loss: 3.4704 (3.2788)  weight_decay: 0.0500 (0.0500)  time: 0.5312  data: 0.0624  max mem: 31830
Epoch: [240]  [200/312]  eta: 0:01:04  lr: 0.000428  min_lr: 0.000428  loss: 3.0989 (3.2672)  weight_decay: 0.0500 (0.0500)  time: 0.4843  data: 0.0397  max mem: 31830
Epoch: [240]  [210/312]  eta: 0:00:59  lr: 0.000428  min_lr: 0.000428  loss: 3.2753 (3.2769)  weight_decay: 0.0500 (0.0500)  time: 0.6376  data: 0.0962  max mem: 31830
Epoch: [240]  [220/312]  eta: 0:00:52  lr: 0.000427  min_lr: 0.000427  loss: 3.3922 (3.2746)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0573  max mem: 31830
Epoch: [240]  [230/312]  eta: 0:00:46  lr: 0.000427  min_lr: 0.000427  loss: 3.3922 (3.2857)  weight_decay: 0.0500 (0.0500)  time: 0.4909  data: 0.0328  max mem: 31830
Epoch: [240]  [240/312]  eta: 0:00:40  lr: 0.000427  min_lr: 0.000427  loss: 3.4458 (3.2845)  weight_decay: 0.0500 (0.0500)  time: 0.5434  data: 0.0334  max mem: 31830
Epoch: [240]  [250/312]  eta: 0:00:35  lr: 0.000426  min_lr: 0.000426  loss: 3.4119 (3.2855)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0441  max mem: 31830
Epoch: [240]  [260/312]  eta: 0:00:29  lr: 0.000426  min_lr: 0.000426  loss: 3.2105 (3.2844)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0741  max mem: 31830
Epoch: [240]  [270/312]  eta: 0:00:23  lr: 0.000425  min_lr: 0.000425  loss: 3.3345 (3.2779)  weight_decay: 0.0500 (0.0500)  time: 0.5150  data: 0.0314  max mem: 31830
Epoch: [240]  [280/312]  eta: 0:00:18  lr: 0.000425  min_lr: 0.000425  loss: 3.2913 (3.2736)  weight_decay: 0.0500 (0.0500)  time: 0.5165  data: 0.0486  max mem: 31830
Epoch: [240]  [290/312]  eta: 0:00:12  lr: 0.000424  min_lr: 0.000424  loss: 3.2515 (3.2764)  weight_decay: 0.0500 (0.0500)  time: 0.5781  data: 0.0634  max mem: 31830
Epoch: [240]  [300/312]  eta: 0:00:06  lr: 0.000424  min_lr: 0.000424  loss: 3.4438 (3.2768)  weight_decay: 0.0500 (0.0500)  time: 0.4513  data: 0.0153  max mem: 31830
Epoch: [240]  [310/312]  eta: 0:00:01  lr: 0.000423  min_lr: 0.000423  loss: 3.4375 (3.2788)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [240]  [311/312]  eta: 0:00:00  lr: 0.000423  min_lr: 0.000423  loss: 3.4438 (3.2794)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [240] Total time: 0:02:53 (0.5558 s / it)
Averaged stats: lr: 0.000423  min_lr: 0.000423  loss: 3.4438 (3.2843)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9841 (0.9841)  acc1: 84.2448 (84.2448)  acc5: 96.0938 (96.0938)  time: 8.8384  data: 8.6711  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2524 (1.1904)  acc1: 75.2604 (76.1120)  acc5: 93.0990 (93.6480)  time: 1.0986  data: 0.9635  max mem: 31830
Test: Total time: 0:00:10 (1.1238 s / it)
* Acc@1 76.350 Acc@5 93.500 loss 1.180
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.46%
Epoch: [241]  [  0/312]  eta: 1:04:56  lr: 0.000423  min_lr: 0.000423  loss: 2.1658 (2.1658)  weight_decay: 0.0500 (0.0500)  time: 12.4873  data: 11.3372  max mem: 31830
Epoch: [241]  [ 10/312]  eta: 0:08:31  lr: 0.000423  min_lr: 0.000423  loss: 3.6416 (3.4658)  weight_decay: 0.0500 (0.0500)  time: 1.6932  data: 1.0313  max mem: 31830
Epoch: [241]  [ 20/312]  eta: 0:05:24  lr: 0.000422  min_lr: 0.000422  loss: 3.5854 (3.2648)  weight_decay: 0.0500 (0.0500)  time: 0.5426  data: 0.0417  max mem: 31830
Epoch: [241]  [ 30/312]  eta: 0:04:08  lr: 0.000422  min_lr: 0.000422  loss: 3.3339 (3.3246)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0417  max mem: 31830
Epoch: [241]  [ 40/312]  eta: 0:03:27  lr: 0.000422  min_lr: 0.000422  loss: 3.5823 (3.3777)  weight_decay: 0.0500 (0.0500)  time: 0.3956  data: 0.0008  max mem: 31830
Epoch: [241]  [ 50/312]  eta: 0:03:03  lr: 0.000421  min_lr: 0.000421  loss: 3.5091 (3.3184)  weight_decay: 0.0500 (0.0500)  time: 0.4222  data: 0.0015  max mem: 31830
Epoch: [241]  [ 60/312]  eta: 0:02:44  lr: 0.000421  min_lr: 0.000421  loss: 3.2964 (3.3232)  weight_decay: 0.0500 (0.0500)  time: 0.4229  data: 0.0015  max mem: 31830
Epoch: [241]  [ 70/312]  eta: 0:02:33  lr: 0.000420  min_lr: 0.000420  loss: 3.2379 (3.3006)  weight_decay: 0.0500 (0.0500)  time: 0.4668  data: 0.0310  max mem: 31830
Epoch: [241]  [ 80/312]  eta: 0:02:25  lr: 0.000420  min_lr: 0.000420  loss: 3.1293 (3.2963)  weight_decay: 0.0500 (0.0500)  time: 0.5576  data: 0.1197  max mem: 31830
Epoch: [241]  [ 90/312]  eta: 0:02:13  lr: 0.000419  min_lr: 0.000419  loss: 3.4241 (3.2899)  weight_decay: 0.0500 (0.0500)  time: 0.4862  data: 0.0896  max mem: 31830
Epoch: [241]  [100/312]  eta: 0:02:09  lr: 0.000419  min_lr: 0.000419  loss: 3.4504 (3.2993)  weight_decay: 0.0500 (0.0500)  time: 0.5470  data: 0.1050  max mem: 31830
Epoch: [241]  [110/312]  eta: 0:02:00  lr: 0.000418  min_lr: 0.000418  loss: 3.5120 (3.3068)  weight_decay: 0.0500 (0.0500)  time: 0.5560  data: 0.1135  max mem: 31830
Epoch: [241]  [120/312]  eta: 0:01:53  lr: 0.000418  min_lr: 0.000418  loss: 3.5405 (3.3126)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.0685  max mem: 31830
Epoch: [241]  [130/312]  eta: 0:01:47  lr: 0.000418  min_lr: 0.000418  loss: 3.5487 (3.3148)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0966  max mem: 31830
Epoch: [241]  [140/312]  eta: 0:01:40  lr: 0.000417  min_lr: 0.000417  loss: 3.3952 (3.3167)  weight_decay: 0.0500 (0.0500)  time: 0.5371  data: 0.0770  max mem: 31830
Epoch: [241]  [150/312]  eta: 0:01:34  lr: 0.000417  min_lr: 0.000417  loss: 3.3091 (3.3157)  weight_decay: 0.0500 (0.0500)  time: 0.5441  data: 0.0765  max mem: 31830
Epoch: [241]  [160/312]  eta: 0:01:27  lr: 0.000416  min_lr: 0.000416  loss: 3.4704 (3.3090)  weight_decay: 0.0500 (0.0500)  time: 0.5399  data: 0.0385  max mem: 31830
Epoch: [241]  [170/312]  eta: 0:01:21  lr: 0.000416  min_lr: 0.000416  loss: 3.4099 (3.2974)  weight_decay: 0.0500 (0.0500)  time: 0.4996  data: 0.0324  max mem: 31830
Epoch: [241]  [180/312]  eta: 0:01:16  lr: 0.000415  min_lr: 0.000415  loss: 3.4924 (3.3003)  weight_decay: 0.0500 (0.0500)  time: 0.5828  data: 0.0617  max mem: 31830
Epoch: [241]  [190/312]  eta: 0:01:09  lr: 0.000415  min_lr: 0.000415  loss: 3.4924 (3.2885)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.0315  max mem: 31830
Epoch: [241]  [200/312]  eta: 0:01:04  lr: 0.000415  min_lr: 0.000415  loss: 3.1646 (3.2849)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0431  max mem: 31830
Epoch: [241]  [210/312]  eta: 0:00:58  lr: 0.000414  min_lr: 0.000414  loss: 3.3441 (3.2918)  weight_decay: 0.0500 (0.0500)  time: 0.6159  data: 0.0432  max mem: 31830
Epoch: [241]  [220/312]  eta: 0:00:52  lr: 0.000414  min_lr: 0.000414  loss: 3.4881 (3.2922)  weight_decay: 0.0500 (0.0500)  time: 0.4923  data: 0.0151  max mem: 31830
Epoch: [241]  [230/312]  eta: 0:00:46  lr: 0.000413  min_lr: 0.000413  loss: 3.4675 (3.3000)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0338  max mem: 31830
Epoch: [241]  [240/312]  eta: 0:00:40  lr: 0.000413  min_lr: 0.000413  loss: 3.4107 (3.3025)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.0506  max mem: 31830
Epoch: [241]  [250/312]  eta: 0:00:35  lr: 0.000412  min_lr: 0.000412  loss: 3.3314 (3.3076)  weight_decay: 0.0500 (0.0500)  time: 0.5138  data: 0.0465  max mem: 31830
Epoch: [241]  [260/312]  eta: 0:00:29  lr: 0.000412  min_lr: 0.000412  loss: 3.6273 (3.3141)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.0553  max mem: 31830
Epoch: [241]  [270/312]  eta: 0:00:23  lr: 0.000411  min_lr: 0.000411  loss: 3.5217 (3.3146)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0741  max mem: 31830
Epoch: [241]  [280/312]  eta: 0:00:18  lr: 0.000411  min_lr: 0.000411  loss: 3.4330 (3.3143)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0555  max mem: 31830
Epoch: [241]  [290/312]  eta: 0:00:12  lr: 0.000411  min_lr: 0.000411  loss: 3.2068 (3.3070)  weight_decay: 0.0500 (0.0500)  time: 0.5656  data: 0.0527  max mem: 31830
Epoch: [241]  [300/312]  eta: 0:00:06  lr: 0.000410  min_lr: 0.000410  loss: 3.1445 (3.3056)  weight_decay: 0.0500 (0.0500)  time: 0.4660  data: 0.0409  max mem: 31830
Epoch: [241]  [310/312]  eta: 0:00:01  lr: 0.000410  min_lr: 0.000410  loss: 3.4488 (3.3070)  weight_decay: 0.0500 (0.0500)  time: 0.3905  data: 0.0098  max mem: 31830
Epoch: [241]  [311/312]  eta: 0:00:00  lr: 0.000410  min_lr: 0.000410  loss: 3.4488 (3.3063)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [241] Total time: 0:02:53 (0.5565 s / it)
Averaged stats: lr: 0.000410  min_lr: 0.000410  loss: 3.4488 (3.2892)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.8544 (0.8544)  acc1: 84.3750 (84.3750)  acc5: 95.9635 (95.9635)  time: 8.8236  data: 8.6561  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2027 (1.0980)  acc1: 75.7812 (76.6240)  acc5: 92.5781 (93.2160)  time: 1.0972  data: 0.9619  max mem: 31830
Test: Total time: 0:00:10 (1.1199 s / it)
* Acc@1 76.644 Acc@5 93.452 loss 1.094
Accuracy of the model on the 50000 test images: 76.6%
Max accuracy: 76.64%
Epoch: [242]  [  0/312]  eta: 1:02:30  lr: 0.000410  min_lr: 0.000410  loss: 2.6598 (2.6598)  weight_decay: 0.0500 (0.0500)  time: 12.0200  data: 10.0843  max mem: 31830
Epoch: [242]  [ 10/312]  eta: 0:08:48  lr: 0.000409  min_lr: 0.000409  loss: 3.5943 (3.4543)  weight_decay: 0.0500 (0.0500)  time: 1.7514  data: 0.9987  max mem: 31830
Epoch: [242]  [ 20/312]  eta: 0:05:29  lr: 0.000409  min_lr: 0.000409  loss: 3.5594 (3.3850)  weight_decay: 0.0500 (0.0500)  time: 0.5845  data: 0.0719  max mem: 31830
Epoch: [242]  [ 30/312]  eta: 0:04:11  lr: 0.000408  min_lr: 0.000408  loss: 3.4636 (3.3245)  weight_decay: 0.0500 (0.0500)  time: 0.4197  data: 0.0274  max mem: 31830
Epoch: [242]  [ 40/312]  eta: 0:03:29  lr: 0.000408  min_lr: 0.000408  loss: 3.4006 (3.3036)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0012  max mem: 31830
Epoch: [242]  [ 50/312]  eta: 0:03:02  lr: 0.000407  min_lr: 0.000407  loss: 3.3363 (3.2693)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0011  max mem: 31830
Epoch: [242]  [ 60/312]  eta: 0:02:43  lr: 0.000407  min_lr: 0.000407  loss: 3.2861 (3.2823)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0009  max mem: 31830
Epoch: [242]  [ 70/312]  eta: 0:02:32  lr: 0.000407  min_lr: 0.000407  loss: 3.2802 (3.2805)  weight_decay: 0.0500 (0.0500)  time: 0.4523  data: 0.0561  max mem: 31830
Epoch: [242]  [ 80/312]  eta: 0:02:24  lr: 0.000406  min_lr: 0.000406  loss: 3.3828 (3.3008)  weight_decay: 0.0500 (0.0500)  time: 0.5494  data: 0.1545  max mem: 31830
Epoch: [242]  [ 90/312]  eta: 0:02:13  lr: 0.000406  min_lr: 0.000406  loss: 3.4859 (3.3229)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0992  max mem: 31830
Epoch: [242]  [100/312]  eta: 0:02:07  lr: 0.000405  min_lr: 0.000405  loss: 3.4550 (3.3206)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.1003  max mem: 31830
Epoch: [242]  [110/312]  eta: 0:01:58  lr: 0.000405  min_lr: 0.000405  loss: 3.4513 (3.3251)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.1063  max mem: 31830
Epoch: [242]  [120/312]  eta: 0:01:53  lr: 0.000404  min_lr: 0.000404  loss: 3.3100 (3.3235)  weight_decay: 0.0500 (0.0500)  time: 0.5292  data: 0.1051  max mem: 31830
Epoch: [242]  [130/312]  eta: 0:01:47  lr: 0.000404  min_lr: 0.000404  loss: 3.4355 (3.3331)  weight_decay: 0.0500 (0.0500)  time: 0.6229  data: 0.1874  max mem: 31830
Epoch: [242]  [140/312]  eta: 0:01:39  lr: 0.000404  min_lr: 0.000404  loss: 3.4355 (3.3406)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0891  max mem: 31830
Epoch: [242]  [150/312]  eta: 0:01:34  lr: 0.000403  min_lr: 0.000403  loss: 3.3499 (3.3368)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0894  max mem: 31830
Epoch: [242]  [160/312]  eta: 0:01:28  lr: 0.000403  min_lr: 0.000403  loss: 3.4208 (3.3412)  weight_decay: 0.0500 (0.0500)  time: 0.6068  data: 0.1888  max mem: 31830
Epoch: [242]  [170/312]  eta: 0:01:21  lr: 0.000402  min_lr: 0.000402  loss: 3.4681 (3.3479)  weight_decay: 0.0500 (0.0500)  time: 0.5149  data: 0.1002  max mem: 31830
Epoch: [242]  [180/312]  eta: 0:01:16  lr: 0.000402  min_lr: 0.000402  loss: 3.5512 (3.3471)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0867  max mem: 31830
Epoch: [242]  [190/312]  eta: 0:01:09  lr: 0.000401  min_lr: 0.000401  loss: 3.4042 (3.3382)  weight_decay: 0.0500 (0.0500)  time: 0.5073  data: 0.0869  max mem: 31830
Epoch: [242]  [200/312]  eta: 0:01:03  lr: 0.000401  min_lr: 0.000401  loss: 3.4042 (3.3432)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0780  max mem: 31830
Epoch: [242]  [210/312]  eta: 0:00:58  lr: 0.000401  min_lr: 0.000401  loss: 3.4602 (3.3388)  weight_decay: 0.0500 (0.0500)  time: 0.5985  data: 0.1516  max mem: 31830
Epoch: [242]  [220/312]  eta: 0:00:51  lr: 0.000400  min_lr: 0.000400  loss: 3.3627 (3.3390)  weight_decay: 0.0500 (0.0500)  time: 0.5006  data: 0.0746  max mem: 31830
Epoch: [242]  [230/312]  eta: 0:00:46  lr: 0.000400  min_lr: 0.000400  loss: 3.3943 (3.3373)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0433  max mem: 31830
Epoch: [242]  [240/312]  eta: 0:00:40  lr: 0.000399  min_lr: 0.000399  loss: 3.5582 (3.3445)  weight_decay: 0.0500 (0.0500)  time: 0.5763  data: 0.0719  max mem: 31830
Epoch: [242]  [250/312]  eta: 0:00:34  lr: 0.000399  min_lr: 0.000399  loss: 3.4931 (3.3398)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0295  max mem: 31830
Epoch: [242]  [260/312]  eta: 0:00:29  lr: 0.000398  min_lr: 0.000398  loss: 3.4197 (3.3449)  weight_decay: 0.0500 (0.0500)  time: 0.5822  data: 0.0209  max mem: 31830
Epoch: [242]  [270/312]  eta: 0:00:23  lr: 0.000398  min_lr: 0.000398  loss: 3.4043 (3.3400)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0210  max mem: 31830
Epoch: [242]  [280/312]  eta: 0:00:18  lr: 0.000398  min_lr: 0.000398  loss: 3.3117 (3.3367)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0274  max mem: 31830
Epoch: [242]  [290/312]  eta: 0:00:12  lr: 0.000397  min_lr: 0.000397  loss: 3.3850 (3.3332)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0420  max mem: 31830
Epoch: [242]  [300/312]  eta: 0:00:06  lr: 0.000397  min_lr: 0.000397  loss: 3.4573 (3.3359)  weight_decay: 0.0500 (0.0500)  time: 0.4829  data: 0.0151  max mem: 31830
Epoch: [242]  [310/312]  eta: 0:00:01  lr: 0.000396  min_lr: 0.000396  loss: 3.4342 (3.3249)  weight_decay: 0.0500 (0.0500)  time: 0.4259  data: 0.0002  max mem: 31830
Epoch: [242]  [311/312]  eta: 0:00:00  lr: 0.000396  min_lr: 0.000396  loss: 3.2707 (3.3247)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [242] Total time: 0:02:53 (0.5549 s / it)
Averaged stats: lr: 0.000396  min_lr: 0.000396  loss: 3.2707 (3.2652)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.9084 (0.9084)  acc1: 83.4635 (83.4635)  acc5: 95.8333 (95.8333)  time: 9.0177  data: 8.8504  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2343 (1.1471)  acc1: 78.1250 (76.6720)  acc5: 93.8802 (93.6800)  time: 1.1185  data: 0.9835  max mem: 31830
Test: Total time: 0:00:10 (1.1349 s / it)
* Acc@1 76.676 Acc@5 93.534 loss 1.150
Accuracy of the model on the 50000 test images: 76.7%
Max accuracy: 76.68%
Epoch: [243]  [  0/312]  eta: 1:01:30  lr: 0.000396  min_lr: 0.000396  loss: 2.0551 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 11.8297  data: 8.9897  max mem: 31830
Epoch: [243]  [ 10/312]  eta: 0:08:33  lr: 0.000396  min_lr: 0.000396  loss: 3.4430 (3.1445)  weight_decay: 0.0500 (0.0500)  time: 1.7016  data: 1.0899  max mem: 31830
Epoch: [243]  [ 20/312]  eta: 0:05:25  lr: 0.000395  min_lr: 0.000395  loss: 3.4430 (3.2404)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.1726  max mem: 31830
Epoch: [243]  [ 30/312]  eta: 0:04:08  lr: 0.000395  min_lr: 0.000395  loss: 3.3923 (3.1853)  weight_decay: 0.0500 (0.0500)  time: 0.4301  data: 0.0230  max mem: 31830
Epoch: [243]  [ 40/312]  eta: 0:03:27  lr: 0.000394  min_lr: 0.000394  loss: 3.3923 (3.2367)  weight_decay: 0.0500 (0.0500)  time: 0.3952  data: 0.0011  max mem: 31830
Epoch: [243]  [ 50/312]  eta: 0:03:01  lr: 0.000394  min_lr: 0.000394  loss: 3.4545 (3.2458)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0012  max mem: 31830
Epoch: [243]  [ 60/312]  eta: 0:02:42  lr: 0.000394  min_lr: 0.000394  loss: 3.3550 (3.2469)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0009  max mem: 31830
Epoch: [243]  [ 70/312]  eta: 0:02:33  lr: 0.000393  min_lr: 0.000393  loss: 3.2526 (3.2216)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0383  max mem: 31830
Epoch: [243]  [ 80/312]  eta: 0:02:24  lr: 0.000393  min_lr: 0.000393  loss: 3.1789 (3.2274)  weight_decay: 0.0500 (0.0500)  time: 0.5679  data: 0.0797  max mem: 31830
Epoch: [243]  [ 90/312]  eta: 0:02:14  lr: 0.000392  min_lr: 0.000392  loss: 3.2388 (3.2400)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0423  max mem: 31830
Epoch: [243]  [100/312]  eta: 0:02:08  lr: 0.000392  min_lr: 0.000392  loss: 3.3746 (3.2403)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0385  max mem: 31830
Epoch: [243]  [110/312]  eta: 0:01:58  lr: 0.000391  min_lr: 0.000391  loss: 3.1719 (3.2294)  weight_decay: 0.0500 (0.0500)  time: 0.4984  data: 0.0383  max mem: 31830
Epoch: [243]  [120/312]  eta: 0:01:52  lr: 0.000391  min_lr: 0.000391  loss: 3.1620 (3.2283)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0611  max mem: 31830
Epoch: [243]  [130/312]  eta: 0:01:47  lr: 0.000391  min_lr: 0.000391  loss: 3.3264 (3.2307)  weight_decay: 0.0500 (0.0500)  time: 0.6164  data: 0.1104  max mem: 31830
Epoch: [243]  [140/312]  eta: 0:01:39  lr: 0.000390  min_lr: 0.000390  loss: 3.3264 (3.2343)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0514  max mem: 31830
Epoch: [243]  [150/312]  eta: 0:01:34  lr: 0.000390  min_lr: 0.000390  loss: 3.0984 (3.2212)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0311  max mem: 31830
Epoch: [243]  [160/312]  eta: 0:01:28  lr: 0.000389  min_lr: 0.000389  loss: 3.3082 (3.2260)  weight_decay: 0.0500 (0.0500)  time: 0.5979  data: 0.0298  max mem: 31830
Epoch: [243]  [170/312]  eta: 0:01:21  lr: 0.000389  min_lr: 0.000389  loss: 3.3521 (3.2226)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0012  max mem: 31830
Epoch: [243]  [180/312]  eta: 0:01:15  lr: 0.000388  min_lr: 0.000388  loss: 3.1395 (3.2137)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0020  max mem: 31830
Epoch: [243]  [190/312]  eta: 0:01:09  lr: 0.000388  min_lr: 0.000388  loss: 3.0086 (3.2091)  weight_decay: 0.0500 (0.0500)  time: 0.4934  data: 0.0018  max mem: 31830
Epoch: [243]  [200/312]  eta: 0:01:03  lr: 0.000388  min_lr: 0.000388  loss: 3.0612 (3.2034)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0169  max mem: 31830
Epoch: [243]  [210/312]  eta: 0:00:58  lr: 0.000387  min_lr: 0.000387  loss: 3.3089 (3.2092)  weight_decay: 0.0500 (0.0500)  time: 0.6180  data: 0.0253  max mem: 31830
Epoch: [243]  [220/312]  eta: 0:00:51  lr: 0.000387  min_lr: 0.000387  loss: 3.4953 (3.2154)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0095  max mem: 31830
Epoch: [243]  [230/312]  eta: 0:00:46  lr: 0.000386  min_lr: 0.000386  loss: 3.3521 (3.2145)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0224  max mem: 31830
Epoch: [243]  [240/312]  eta: 0:00:40  lr: 0.000386  min_lr: 0.000386  loss: 3.2980 (3.2100)  weight_decay: 0.0500 (0.0500)  time: 0.6105  data: 0.0400  max mem: 31830
Epoch: [243]  [250/312]  eta: 0:00:34  lr: 0.000385  min_lr: 0.000385  loss: 3.1475 (3.2078)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.0198  max mem: 31830
Epoch: [243]  [260/312]  eta: 0:00:29  lr: 0.000385  min_lr: 0.000385  loss: 3.3817 (3.2183)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.0174  max mem: 31830
Epoch: [243]  [270/312]  eta: 0:00:23  lr: 0.000385  min_lr: 0.000385  loss: 3.5164 (3.2266)  weight_decay: 0.0500 (0.0500)  time: 0.5337  data: 0.0161  max mem: 31830
Epoch: [243]  [280/312]  eta: 0:00:18  lr: 0.000384  min_lr: 0.000384  loss: 3.4701 (3.2280)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0029  max mem: 31830
Epoch: [243]  [290/312]  eta: 0:00:12  lr: 0.000384  min_lr: 0.000384  loss: 3.3263 (3.2319)  weight_decay: 0.0500 (0.0500)  time: 0.6093  data: 0.0032  max mem: 31830
Epoch: [243]  [300/312]  eta: 0:00:06  lr: 0.000383  min_lr: 0.000383  loss: 3.3721 (3.2407)  weight_decay: 0.0500 (0.0500)  time: 0.4906  data: 0.0008  max mem: 31830
Epoch: [243]  [310/312]  eta: 0:00:01  lr: 0.000383  min_lr: 0.000383  loss: 3.5536 (3.2479)  weight_decay: 0.0500 (0.0500)  time: 0.3835  data: 0.0001  max mem: 31830
Epoch: [243]  [311/312]  eta: 0:00:00  lr: 0.000383  min_lr: 0.000383  loss: 3.3920 (3.2484)  weight_decay: 0.0500 (0.0500)  time: 0.3833  data: 0.0001  max mem: 31830
Epoch: [243] Total time: 0:02:53 (0.5560 s / it)
Averaged stats: lr: 0.000383  min_lr: 0.000383  loss: 3.3920 (3.2591)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 1.0478 (1.0478)  acc1: 82.9427 (82.9427)  acc5: 96.2240 (96.2240)  time: 8.8901  data: 8.7293  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3035 (1.2355)  acc1: 76.6927 (76.6240)  acc5: 93.4896 (93.6480)  time: 1.1058  data: 0.9700  max mem: 31830
Test: Total time: 0:00:10 (1.1267 s / it)
* Acc@1 76.446 Acc@5 93.572 loss 1.240
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.68%
Epoch: [244]  [  0/312]  eta: 1:02:28  lr: 0.000383  min_lr: 0.000383  loss: 3.9824 (3.9824)  weight_decay: 0.0500 (0.0500)  time: 12.0133  data: 10.9560  max mem: 31830
Epoch: [244]  [ 10/312]  eta: 0:08:47  lr: 0.000382  min_lr: 0.000382  loss: 3.3917 (3.4146)  weight_decay: 0.0500 (0.0500)  time: 1.7462  data: 1.0539  max mem: 31830
Epoch: [244]  [ 20/312]  eta: 0:05:33  lr: 0.000382  min_lr: 0.000382  loss: 3.3019 (3.3729)  weight_decay: 0.0500 (0.0500)  time: 0.5981  data: 0.0758  max mem: 31830
Epoch: [244]  [ 30/312]  eta: 0:04:14  lr: 0.000382  min_lr: 0.000382  loss: 3.2256 (3.2527)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0445  max mem: 31830
Epoch: [244]  [ 40/312]  eta: 0:03:31  lr: 0.000381  min_lr: 0.000381  loss: 3.2256 (3.2392)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0010  max mem: 31830
Epoch: [244]  [ 50/312]  eta: 0:03:04  lr: 0.000381  min_lr: 0.000381  loss: 3.3836 (3.2493)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0071  max mem: 31830
Epoch: [244]  [ 60/312]  eta: 0:02:44  lr: 0.000380  min_lr: 0.000380  loss: 3.4974 (3.2606)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0073  max mem: 31830
Epoch: [244]  [ 70/312]  eta: 0:02:34  lr: 0.000380  min_lr: 0.000380  loss: 3.4916 (3.2654)  weight_decay: 0.0500 (0.0500)  time: 0.4761  data: 0.0820  max mem: 31830
Epoch: [244]  [ 80/312]  eta: 0:02:25  lr: 0.000379  min_lr: 0.000379  loss: 3.3666 (3.2306)  weight_decay: 0.0500 (0.0500)  time: 0.5463  data: 0.1532  max mem: 31830
Epoch: [244]  [ 90/312]  eta: 0:02:13  lr: 0.000379  min_lr: 0.000379  loss: 3.1289 (3.2435)  weight_decay: 0.0500 (0.0500)  time: 0.4670  data: 0.0724  max mem: 31830
Epoch: [244]  [100/312]  eta: 0:02:08  lr: 0.000379  min_lr: 0.000379  loss: 3.5783 (3.2617)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1087  max mem: 31830
Epoch: [244]  [110/312]  eta: 0:01:58  lr: 0.000378  min_lr: 0.000378  loss: 3.5169 (3.2653)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.1086  max mem: 31830
Epoch: [244]  [120/312]  eta: 0:01:52  lr: 0.000378  min_lr: 0.000378  loss: 3.1891 (3.2539)  weight_decay: 0.0500 (0.0500)  time: 0.4896  data: 0.0673  max mem: 31830
Epoch: [244]  [130/312]  eta: 0:01:47  lr: 0.000377  min_lr: 0.000377  loss: 3.2048 (3.2593)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.1453  max mem: 31830
Epoch: [244]  [140/312]  eta: 0:01:38  lr: 0.000377  min_lr: 0.000377  loss: 3.3731 (3.2629)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0789  max mem: 31830
Epoch: [244]  [150/312]  eta: 0:01:34  lr: 0.000377  min_lr: 0.000377  loss: 3.3731 (3.2702)  weight_decay: 0.0500 (0.0500)  time: 0.5486  data: 0.0768  max mem: 31830
Epoch: [244]  [160/312]  eta: 0:01:28  lr: 0.000376  min_lr: 0.000376  loss: 3.1548 (3.2631)  weight_decay: 0.0500 (0.0500)  time: 0.6340  data: 0.1666  max mem: 31830
Epoch: [244]  [170/312]  eta: 0:01:21  lr: 0.000376  min_lr: 0.000376  loss: 3.1949 (3.2565)  weight_decay: 0.0500 (0.0500)  time: 0.4833  data: 0.0906  max mem: 31830
Epoch: [244]  [180/312]  eta: 0:01:15  lr: 0.000375  min_lr: 0.000375  loss: 3.3343 (3.2564)  weight_decay: 0.0500 (0.0500)  time: 0.5029  data: 0.1014  max mem: 31830
Epoch: [244]  [190/312]  eta: 0:01:08  lr: 0.000375  min_lr: 0.000375  loss: 3.3905 (3.2532)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.1014  max mem: 31830
Epoch: [244]  [200/312]  eta: 0:01:03  lr: 0.000374  min_lr: 0.000374  loss: 3.3723 (3.2527)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.1064  max mem: 31830
Epoch: [244]  [210/312]  eta: 0:00:58  lr: 0.000374  min_lr: 0.000374  loss: 3.2354 (3.2497)  weight_decay: 0.0500 (0.0500)  time: 0.6249  data: 0.2018  max mem: 31830
Epoch: [244]  [220/312]  eta: 0:00:51  lr: 0.000374  min_lr: 0.000374  loss: 3.3072 (3.2517)  weight_decay: 0.0500 (0.0500)  time: 0.5218  data: 0.0962  max mem: 31830
Epoch: [244]  [230/312]  eta: 0:00:46  lr: 0.000373  min_lr: 0.000373  loss: 3.2944 (3.2474)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0984  max mem: 31830
Epoch: [244]  [240/312]  eta: 0:00:40  lr: 0.000373  min_lr: 0.000373  loss: 3.0462 (3.2414)  weight_decay: 0.0500 (0.0500)  time: 0.5972  data: 0.1698  max mem: 31830
Epoch: [244]  [250/312]  eta: 0:00:34  lr: 0.000372  min_lr: 0.000372  loss: 3.1687 (3.2431)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0722  max mem: 31830
Epoch: [244]  [260/312]  eta: 0:00:29  lr: 0.000372  min_lr: 0.000372  loss: 3.2134 (3.2372)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0871  max mem: 31830
Epoch: [244]  [270/312]  eta: 0:00:23  lr: 0.000372  min_lr: 0.000372  loss: 3.2134 (3.2425)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0872  max mem: 31830
Epoch: [244]  [280/312]  eta: 0:00:17  lr: 0.000371  min_lr: 0.000371  loss: 3.6152 (3.2540)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0873  max mem: 31830
Epoch: [244]  [290/312]  eta: 0:00:12  lr: 0.000371  min_lr: 0.000371  loss: 3.6152 (3.2527)  weight_decay: 0.0500 (0.0500)  time: 0.6197  data: 0.1685  max mem: 31830
Epoch: [244]  [300/312]  eta: 0:00:06  lr: 0.000370  min_lr: 0.000370  loss: 3.3164 (3.2509)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0817  max mem: 31830
Epoch: [244]  [310/312]  eta: 0:00:01  lr: 0.000370  min_lr: 0.000370  loss: 3.3044 (3.2522)  weight_decay: 0.0500 (0.0500)  time: 0.3819  data: 0.0001  max mem: 31830
Epoch: [244]  [311/312]  eta: 0:00:00  lr: 0.000370  min_lr: 0.000370  loss: 3.3164 (3.2532)  weight_decay: 0.0500 (0.0500)  time: 0.3817  data: 0.0001  max mem: 31830
Epoch: [244] Total time: 0:02:52 (0.5544 s / it)
Averaged stats: lr: 0.000370  min_lr: 0.000370  loss: 3.3164 (3.2602)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9190 (0.9190)  acc1: 83.9844 (83.9844)  acc5: 96.6146 (96.6146)  time: 8.8214  data: 8.6583  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2427 (1.1362)  acc1: 75.7812 (76.6880)  acc5: 92.7083 (93.7120)  time: 1.0984  data: 0.9621  max mem: 31830
Test: Total time: 0:00:10 (1.1116 s / it)
* Acc@1 76.830 Acc@5 93.654 loss 1.137
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 76.83%
Epoch: [245]  [  0/312]  eta: 1:00:50  lr: 0.000370  min_lr: 0.000370  loss: 2.9643 (2.9643)  weight_decay: 0.0500 (0.0500)  time: 11.7002  data: 11.2998  max mem: 31830
Epoch: [245]  [ 10/312]  eta: 0:08:48  lr: 0.000369  min_lr: 0.000369  loss: 3.3647 (3.4077)  weight_decay: 0.0500 (0.0500)  time: 1.7497  data: 1.0279  max mem: 31830
Epoch: [245]  [ 20/312]  eta: 0:05:29  lr: 0.000369  min_lr: 0.000369  loss: 3.3441 (3.2771)  weight_decay: 0.0500 (0.0500)  time: 0.5982  data: 0.0263  max mem: 31830
Epoch: [245]  [ 30/312]  eta: 0:04:11  lr: 0.000369  min_lr: 0.000369  loss: 3.0055 (3.2116)  weight_decay: 0.0500 (0.0500)  time: 0.4188  data: 0.0263  max mem: 31830
Epoch: [245]  [ 40/312]  eta: 0:03:29  lr: 0.000368  min_lr: 0.000368  loss: 3.3156 (3.2214)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0009  max mem: 31830
Epoch: [245]  [ 50/312]  eta: 0:03:02  lr: 0.000368  min_lr: 0.000368  loss: 3.4115 (3.2351)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0013  max mem: 31830
Epoch: [245]  [ 60/312]  eta: 0:02:43  lr: 0.000367  min_lr: 0.000367  loss: 3.4028 (3.2517)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0015  max mem: 31830
Epoch: [245]  [ 70/312]  eta: 0:02:29  lr: 0.000367  min_lr: 0.000367  loss: 3.2899 (3.2550)  weight_decay: 0.0500 (0.0500)  time: 0.4084  data: 0.0012  max mem: 31830
Epoch: [245]  [ 80/312]  eta: 0:02:22  lr: 0.000366  min_lr: 0.000366  loss: 3.2012 (3.2491)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0312  max mem: 31830
Epoch: [245]  [ 90/312]  eta: 0:02:13  lr: 0.000366  min_lr: 0.000366  loss: 3.1583 (3.2279)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.0369  max mem: 31830
Epoch: [245]  [100/312]  eta: 0:02:06  lr: 0.000366  min_lr: 0.000366  loss: 3.4620 (3.2757)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0374  max mem: 31830
Epoch: [245]  [110/312]  eta: 0:01:59  lr: 0.000365  min_lr: 0.000365  loss: 3.5310 (3.2755)  weight_decay: 0.0500 (0.0500)  time: 0.5401  data: 0.0316  max mem: 31830
Epoch: [245]  [120/312]  eta: 0:01:52  lr: 0.000365  min_lr: 0.000365  loss: 3.4621 (3.2704)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0252  max mem: 31830
Epoch: [245]  [130/312]  eta: 0:01:46  lr: 0.000364  min_lr: 0.000364  loss: 3.4080 (3.2602)  weight_decay: 0.0500 (0.0500)  time: 0.5464  data: 0.0497  max mem: 31830
Epoch: [245]  [140/312]  eta: 0:01:39  lr: 0.000364  min_lr: 0.000364  loss: 3.3302 (3.2681)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0254  max mem: 31830
Epoch: [245]  [150/312]  eta: 0:01:33  lr: 0.000364  min_lr: 0.000364  loss: 3.3826 (3.2800)  weight_decay: 0.0500 (0.0500)  time: 0.5139  data: 0.0150  max mem: 31830
Epoch: [245]  [160/312]  eta: 0:01:27  lr: 0.000363  min_lr: 0.000363  loss: 3.4732 (3.2782)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0151  max mem: 31830
Epoch: [245]  [170/312]  eta: 0:01:21  lr: 0.000363  min_lr: 0.000363  loss: 3.2314 (3.2716)  weight_decay: 0.0500 (0.0500)  time: 0.5734  data: 0.0148  max mem: 31830
Epoch: [245]  [180/312]  eta: 0:01:15  lr: 0.000362  min_lr: 0.000362  loss: 3.2883 (3.2801)  weight_decay: 0.0500 (0.0500)  time: 0.5345  data: 0.0211  max mem: 31830
Epoch: [245]  [190/312]  eta: 0:01:09  lr: 0.000362  min_lr: 0.000362  loss: 3.4776 (3.2831)  weight_decay: 0.0500 (0.0500)  time: 0.5086  data: 0.0085  max mem: 31830
Epoch: [245]  [200/312]  eta: 0:01:03  lr: 0.000362  min_lr: 0.000362  loss: 3.4906 (3.2827)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.0021  max mem: 31830
Epoch: [245]  [210/312]  eta: 0:00:58  lr: 0.000361  min_lr: 0.000361  loss: 3.0898 (3.2676)  weight_decay: 0.0500 (0.0500)  time: 0.5820  data: 0.0059  max mem: 31830
Epoch: [245]  [220/312]  eta: 0:00:52  lr: 0.000361  min_lr: 0.000361  loss: 3.2882 (3.2708)  weight_decay: 0.0500 (0.0500)  time: 0.5605  data: 0.0059  max mem: 31830
Epoch: [245]  [230/312]  eta: 0:00:46  lr: 0.000360  min_lr: 0.000360  loss: 3.3411 (3.2674)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0064  max mem: 31830
Epoch: [245]  [240/312]  eta: 0:00:40  lr: 0.000360  min_lr: 0.000360  loss: 3.4236 (3.2754)  weight_decay: 0.0500 (0.0500)  time: 0.5493  data: 0.0064  max mem: 31830
Epoch: [245]  [250/312]  eta: 0:00:34  lr: 0.000359  min_lr: 0.000359  loss: 3.4228 (3.2819)  weight_decay: 0.0500 (0.0500)  time: 0.5605  data: 0.0072  max mem: 31830
Epoch: [245]  [260/312]  eta: 0:00:29  lr: 0.000359  min_lr: 0.000359  loss: 3.4228 (3.2802)  weight_decay: 0.0500 (0.0500)  time: 0.5282  data: 0.0185  max mem: 31830
Epoch: [245]  [270/312]  eta: 0:00:23  lr: 0.000359  min_lr: 0.000359  loss: 3.3814 (3.2774)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0178  max mem: 31830
Epoch: [245]  [280/312]  eta: 0:00:17  lr: 0.000358  min_lr: 0.000358  loss: 3.3254 (3.2786)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.0277  max mem: 31830
Epoch: [245]  [290/312]  eta: 0:00:12  lr: 0.000358  min_lr: 0.000358  loss: 3.3774 (3.2802)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0278  max mem: 31830
Epoch: [245]  [300/312]  eta: 0:00:06  lr: 0.000357  min_lr: 0.000357  loss: 3.4093 (3.2740)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0062  max mem: 31830
Epoch: [245]  [310/312]  eta: 0:00:01  lr: 0.000357  min_lr: 0.000357  loss: 3.2742 (3.2735)  weight_decay: 0.0500 (0.0500)  time: 0.4214  data: 0.0002  max mem: 31830
Epoch: [245]  [311/312]  eta: 0:00:00  lr: 0.000357  min_lr: 0.000357  loss: 3.2742 (3.2731)  weight_decay: 0.0500 (0.0500)  time: 0.4208  data: 0.0002  max mem: 31830
Epoch: [245] Total time: 0:02:53 (0.5555 s / it)
Averaged stats: lr: 0.000357  min_lr: 0.000357  loss: 3.2742 (3.2751)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.9092 (0.9092)  acc1: 83.7240 (83.7240)  acc5: 95.8333 (95.8333)  time: 9.2148  data: 9.0477  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2175 (1.1192)  acc1: 77.2135 (76.9920)  acc5: 93.2292 (93.4720)  time: 1.1401  data: 1.0054  max mem: 31830
Test: Total time: 0:00:10 (1.1545 s / it)
* Acc@1 77.036 Acc@5 93.724 loss 1.111
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 77.04%
Epoch: [246]  [  0/312]  eta: 1:00:16  lr: 0.000357  min_lr: 0.000357  loss: 3.6547 (3.6547)  weight_decay: 0.0500 (0.0500)  time: 11.5907  data: 8.7632  max mem: 31830
Epoch: [246]  [ 10/312]  eta: 0:08:24  lr: 0.000356  min_lr: 0.000356  loss: 3.1408 (3.1814)  weight_decay: 0.0500 (0.0500)  time: 1.6692  data: 0.9623  max mem: 31830
Epoch: [246]  [ 20/312]  eta: 0:05:29  lr: 0.000356  min_lr: 0.000356  loss: 3.3708 (3.2944)  weight_decay: 0.0500 (0.0500)  time: 0.6059  data: 0.1431  max mem: 31830
Epoch: [246]  [ 30/312]  eta: 0:04:12  lr: 0.000356  min_lr: 0.000356  loss: 3.3976 (3.2724)  weight_decay: 0.0500 (0.0500)  time: 0.4671  data: 0.0524  max mem: 31830
Epoch: [246]  [ 40/312]  eta: 0:03:30  lr: 0.000355  min_lr: 0.000355  loss: 3.3800 (3.2555)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0008  max mem: 31830
Epoch: [246]  [ 50/312]  eta: 0:03:03  lr: 0.000355  min_lr: 0.000355  loss: 3.4069 (3.2758)  weight_decay: 0.0500 (0.0500)  time: 0.3977  data: 0.0009  max mem: 31830
Epoch: [246]  [ 60/312]  eta: 0:02:43  lr: 0.000354  min_lr: 0.000354  loss: 3.5282 (3.2936)  weight_decay: 0.0500 (0.0500)  time: 0.3946  data: 0.0009  max mem: 31830
Epoch: [246]  [ 70/312]  eta: 0:02:35  lr: 0.000354  min_lr: 0.000354  loss: 3.4108 (3.3061)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0673  max mem: 31830
Epoch: [246]  [ 80/312]  eta: 0:02:25  lr: 0.000354  min_lr: 0.000354  loss: 3.4345 (3.3092)  weight_decay: 0.0500 (0.0500)  time: 0.5557  data: 0.1141  max mem: 31830
Epoch: [246]  [ 90/312]  eta: 0:02:15  lr: 0.000353  min_lr: 0.000353  loss: 3.4533 (3.3225)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0882  max mem: 31830
Epoch: [246]  [100/312]  eta: 0:02:11  lr: 0.000353  min_lr: 0.000353  loss: 3.3533 (3.3006)  weight_decay: 0.0500 (0.0500)  time: 0.5912  data: 0.1302  max mem: 31830
Epoch: [246]  [110/312]  eta: 0:02:00  lr: 0.000352  min_lr: 0.000352  loss: 3.3533 (3.3161)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0895  max mem: 31830
Epoch: [246]  [120/312]  eta: 0:01:54  lr: 0.000352  min_lr: 0.000352  loss: 3.4888 (3.3183)  weight_decay: 0.0500 (0.0500)  time: 0.4802  data: 0.0761  max mem: 31830
Epoch: [246]  [130/312]  eta: 0:01:48  lr: 0.000352  min_lr: 0.000352  loss: 3.3454 (3.3167)  weight_decay: 0.0500 (0.0500)  time: 0.5958  data: 0.1677  max mem: 31830
Epoch: [246]  [140/312]  eta: 0:01:40  lr: 0.000351  min_lr: 0.000351  loss: 3.3455 (3.3245)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0923  max mem: 31830
Epoch: [246]  [150/312]  eta: 0:01:34  lr: 0.000351  min_lr: 0.000351  loss: 3.3455 (3.3161)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.1036  max mem: 31830
Epoch: [246]  [160/312]  eta: 0:01:28  lr: 0.000350  min_lr: 0.000350  loss: 3.3029 (3.3107)  weight_decay: 0.0500 (0.0500)  time: 0.5563  data: 0.1299  max mem: 31830
Epoch: [246]  [170/312]  eta: 0:01:22  lr: 0.000350  min_lr: 0.000350  loss: 3.4133 (3.3129)  weight_decay: 0.0500 (0.0500)  time: 0.5431  data: 0.1109  max mem: 31830
Epoch: [246]  [180/312]  eta: 0:01:17  lr: 0.000350  min_lr: 0.000350  loss: 3.4472 (3.3090)  weight_decay: 0.0500 (0.0500)  time: 0.6101  data: 0.1597  max mem: 31830
Epoch: [246]  [190/312]  eta: 0:01:09  lr: 0.000349  min_lr: 0.000349  loss: 3.3325 (3.3095)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.0768  max mem: 31830
Epoch: [246]  [200/312]  eta: 0:01:04  lr: 0.000349  min_lr: 0.000349  loss: 3.2116 (3.3046)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0763  max mem: 31830
Epoch: [246]  [210/312]  eta: 0:00:58  lr: 0.000348  min_lr: 0.000348  loss: 3.1413 (3.2962)  weight_decay: 0.0500 (0.0500)  time: 0.6043  data: 0.1317  max mem: 31830
Epoch: [246]  [220/312]  eta: 0:00:52  lr: 0.000348  min_lr: 0.000348  loss: 3.1680 (3.2950)  weight_decay: 0.0500 (0.0500)  time: 0.4886  data: 0.0572  max mem: 31830
Epoch: [246]  [230/312]  eta: 0:00:46  lr: 0.000348  min_lr: 0.000348  loss: 3.2507 (3.2818)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0591  max mem: 31830
Epoch: [246]  [240/312]  eta: 0:00:40  lr: 0.000347  min_lr: 0.000347  loss: 3.2268 (3.2801)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0591  max mem: 31830
Epoch: [246]  [250/312]  eta: 0:00:35  lr: 0.000347  min_lr: 0.000347  loss: 3.2268 (3.2786)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0671  max mem: 31830
Epoch: [246]  [260/312]  eta: 0:00:29  lr: 0.000346  min_lr: 0.000346  loss: 3.2974 (3.2789)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.1246  max mem: 31830
Epoch: [246]  [270/312]  eta: 0:00:23  lr: 0.000346  min_lr: 0.000346  loss: 3.3804 (3.2785)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.0583  max mem: 31830
Epoch: [246]  [280/312]  eta: 0:00:18  lr: 0.000346  min_lr: 0.000346  loss: 3.3804 (3.2806)  weight_decay: 0.0500 (0.0500)  time: 0.5281  data: 0.0734  max mem: 31830
Epoch: [246]  [290/312]  eta: 0:00:12  lr: 0.000345  min_lr: 0.000345  loss: 3.3553 (3.2777)  weight_decay: 0.0500 (0.0500)  time: 0.5929  data: 0.1040  max mem: 31830
Epoch: [246]  [300/312]  eta: 0:00:06  lr: 0.000345  min_lr: 0.000345  loss: 3.3499 (3.2798)  weight_decay: 0.0500 (0.0500)  time: 0.4534  data: 0.0310  max mem: 31830
Epoch: [246]  [310/312]  eta: 0:00:01  lr: 0.000344  min_lr: 0.000344  loss: 3.3499 (3.2761)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0002  max mem: 31830
Epoch: [246]  [311/312]  eta: 0:00:00  lr: 0.000344  min_lr: 0.000344  loss: 3.3384 (3.2757)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [246] Total time: 0:02:53 (0.5547 s / it)
Averaged stats: lr: 0.000344  min_lr: 0.000344  loss: 3.3384 (3.2712)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.9323 (0.9323)  acc1: 82.4219 (82.4219)  acc5: 96.0938 (96.0938)  time: 8.8952  data: 8.7279  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1885 (1.1030)  acc1: 77.7344 (76.5760)  acc5: 94.2708 (93.5360)  time: 1.1049  data: 0.9698  max mem: 31830
Test: Total time: 0:00:10 (1.1159 s / it)
* Acc@1 76.824 Acc@5 93.638 loss 1.100
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 77.04%
Epoch: [247]  [  0/312]  eta: 1:01:07  lr: 0.000344  min_lr: 0.000344  loss: 3.7143 (3.7143)  weight_decay: 0.0500 (0.0500)  time: 11.7539  data: 9.0615  max mem: 31830
Epoch: [247]  [ 10/312]  eta: 0:08:30  lr: 0.000344  min_lr: 0.000344  loss: 3.6051 (3.4211)  weight_decay: 0.0500 (0.0500)  time: 1.6917  data: 1.0944  max mem: 31830
Epoch: [247]  [ 20/312]  eta: 0:05:31  lr: 0.000343  min_lr: 0.000343  loss: 3.5287 (3.4068)  weight_decay: 0.0500 (0.0500)  time: 0.6044  data: 0.2001  max mem: 31830
Epoch: [247]  [ 30/312]  eta: 0:04:12  lr: 0.000343  min_lr: 0.000343  loss: 3.4279 (3.3854)  weight_decay: 0.0500 (0.0500)  time: 0.4586  data: 0.0516  max mem: 31830
Epoch: [247]  [ 40/312]  eta: 0:03:30  lr: 0.000343  min_lr: 0.000343  loss: 3.4279 (3.3750)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0008  max mem: 31830
Epoch: [247]  [ 50/312]  eta: 0:03:08  lr: 0.000342  min_lr: 0.000342  loss: 3.4647 (3.3665)  weight_decay: 0.0500 (0.0500)  time: 0.4489  data: 0.0008  max mem: 31830
Epoch: [247]  [ 60/312]  eta: 0:02:50  lr: 0.000342  min_lr: 0.000342  loss: 3.3641 (3.3347)  weight_decay: 0.0500 (0.0500)  time: 0.4697  data: 0.0219  max mem: 31830
Epoch: [247]  [ 70/312]  eta: 0:02:41  lr: 0.000341  min_lr: 0.000341  loss: 3.0908 (3.2794)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0596  max mem: 31830
Epoch: [247]  [ 80/312]  eta: 0:02:29  lr: 0.000341  min_lr: 0.000341  loss: 3.4452 (3.2904)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0385  max mem: 31830
Epoch: [247]  [ 90/312]  eta: 0:02:19  lr: 0.000341  min_lr: 0.000341  loss: 3.4550 (3.2976)  weight_decay: 0.0500 (0.0500)  time: 0.4933  data: 0.0381  max mem: 31830
Epoch: [247]  [100/312]  eta: 0:02:13  lr: 0.000340  min_lr: 0.000340  loss: 3.4353 (3.3073)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0855  max mem: 31830
Epoch: [247]  [110/312]  eta: 0:02:02  lr: 0.000340  min_lr: 0.000340  loss: 3.4700 (3.3220)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0484  max mem: 31830
Epoch: [247]  [120/312]  eta: 0:01:56  lr: 0.000339  min_lr: 0.000339  loss: 3.5162 (3.3283)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0680  max mem: 31830
Epoch: [247]  [130/312]  eta: 0:01:50  lr: 0.000339  min_lr: 0.000339  loss: 3.4356 (3.3326)  weight_decay: 0.0500 (0.0500)  time: 0.6298  data: 0.1234  max mem: 31830
Epoch: [247]  [140/312]  eta: 0:01:42  lr: 0.000339  min_lr: 0.000339  loss: 3.4356 (3.3354)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0563  max mem: 31830
Epoch: [247]  [150/312]  eta: 0:01:37  lr: 0.000338  min_lr: 0.000338  loss: 3.4789 (3.3448)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0945  max mem: 31830
Epoch: [247]  [160/312]  eta: 0:01:29  lr: 0.000338  min_lr: 0.000338  loss: 3.5014 (3.3293)  weight_decay: 0.0500 (0.0500)  time: 0.5541  data: 0.0945  max mem: 31830
Epoch: [247]  [170/312]  eta: 0:01:23  lr: 0.000337  min_lr: 0.000337  loss: 3.5258 (3.3401)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0349  max mem: 31830
Epoch: [247]  [180/312]  eta: 0:01:18  lr: 0.000337  min_lr: 0.000337  loss: 3.5332 (3.3403)  weight_decay: 0.0500 (0.0500)  time: 0.6298  data: 0.1052  max mem: 31830
Epoch: [247]  [190/312]  eta: 0:01:11  lr: 0.000337  min_lr: 0.000337  loss: 3.4206 (3.3336)  weight_decay: 0.0500 (0.0500)  time: 0.5206  data: 0.0718  max mem: 31830
Epoch: [247]  [200/312]  eta: 0:01:05  lr: 0.000336  min_lr: 0.000336  loss: 3.4206 (3.3320)  weight_decay: 0.0500 (0.0500)  time: 0.4692  data: 0.0389  max mem: 31830
Epoch: [247]  [210/312]  eta: 0:00:59  lr: 0.000336  min_lr: 0.000336  loss: 3.2931 (3.3224)  weight_decay: 0.0500 (0.0500)  time: 0.5735  data: 0.0750  max mem: 31830
Epoch: [247]  [220/312]  eta: 0:00:53  lr: 0.000335  min_lr: 0.000335  loss: 3.2931 (3.3216)  weight_decay: 0.0500 (0.0500)  time: 0.5662  data: 0.1013  max mem: 31830
Epoch: [247]  [230/312]  eta: 0:00:47  lr: 0.000335  min_lr: 0.000335  loss: 3.4915 (3.3136)  weight_decay: 0.0500 (0.0500)  time: 0.5709  data: 0.1116  max mem: 31830
Epoch: [247]  [240/312]  eta: 0:00:41  lr: 0.000335  min_lr: 0.000335  loss: 3.2416 (3.3148)  weight_decay: 0.0500 (0.0500)  time: 0.5101  data: 0.0504  max mem: 31830
Epoch: [247]  [250/312]  eta: 0:00:35  lr: 0.000334  min_lr: 0.000334  loss: 3.2519 (3.3071)  weight_decay: 0.0500 (0.0500)  time: 0.5335  data: 0.0566  max mem: 31830
Epoch: [247]  [260/312]  eta: 0:00:30  lr: 0.000334  min_lr: 0.000334  loss: 3.5362 (3.3133)  weight_decay: 0.0500 (0.0500)  time: 0.6460  data: 0.0960  max mem: 31830
Epoch: [247]  [270/312]  eta: 0:00:24  lr: 0.000333  min_lr: 0.000333  loss: 3.5221 (3.3107)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0427  max mem: 31830
Epoch: [247]  [280/312]  eta: 0:00:18  lr: 0.000333  min_lr: 0.000333  loss: 3.4159 (3.3163)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0475  max mem: 31830
Epoch: [247]  [290/312]  eta: 0:00:12  lr: 0.000333  min_lr: 0.000333  loss: 3.4710 (3.3231)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0474  max mem: 31830
Epoch: [247]  [300/312]  eta: 0:00:06  lr: 0.000332  min_lr: 0.000332  loss: 3.4710 (3.3181)  weight_decay: 0.0500 (0.0500)  time: 0.4317  data: 0.0162  max mem: 31830
Epoch: [247]  [310/312]  eta: 0:00:01  lr: 0.000332  min_lr: 0.000332  loss: 3.2950 (3.3158)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0161  max mem: 31830
Epoch: [247]  [311/312]  eta: 0:00:00  lr: 0.000332  min_lr: 0.000332  loss: 3.2836 (3.3128)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [247] Total time: 0:02:55 (0.5633 s / it)
Averaged stats: lr: 0.000332  min_lr: 0.000332  loss: 3.2836 (3.2443)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 1.0139 (1.0139)  acc1: 83.2031 (83.2031)  acc5: 96.4844 (96.4844)  time: 7.5141  data: 7.3485  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2698 (1.2093)  acc1: 76.4323 (76.7040)  acc5: 93.8802 (93.4080)  time: 1.0032  data: 0.8684  max mem: 31830
Test: Total time: 0:00:09 (1.0135 s / it)
* Acc@1 76.968 Acc@5 93.730 loss 1.199
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 77.04%
Epoch: [248]  [  0/312]  eta: 1:07:10  lr: 0.000332  min_lr: 0.000332  loss: 2.8022 (2.8022)  weight_decay: 0.0500 (0.0500)  time: 12.9179  data: 11.0274  max mem: 31830
Epoch: [248]  [ 10/312]  eta: 0:08:43  lr: 0.000331  min_lr: 0.000331  loss: 3.3885 (3.3802)  weight_decay: 0.0500 (0.0500)  time: 1.7331  data: 1.0032  max mem: 31830
Epoch: [248]  [ 20/312]  eta: 0:05:30  lr: 0.000331  min_lr: 0.000331  loss: 3.4217 (3.4021)  weight_decay: 0.0500 (0.0500)  time: 0.5436  data: 0.0159  max mem: 31830
Epoch: [248]  [ 30/312]  eta: 0:04:12  lr: 0.000331  min_lr: 0.000331  loss: 3.4829 (3.4119)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0160  max mem: 31830
Epoch: [248]  [ 40/312]  eta: 0:03:30  lr: 0.000330  min_lr: 0.000330  loss: 3.4829 (3.4122)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0009  max mem: 31830
Epoch: [248]  [ 50/312]  eta: 0:03:03  lr: 0.000330  min_lr: 0.000330  loss: 3.5335 (3.4206)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [248]  [ 60/312]  eta: 0:02:43  lr: 0.000329  min_lr: 0.000329  loss: 3.2470 (3.3437)  weight_decay: 0.0500 (0.0500)  time: 0.3968  data: 0.0009  max mem: 31830
Epoch: [248]  [ 70/312]  eta: 0:02:33  lr: 0.000329  min_lr: 0.000329  loss: 2.9320 (3.2961)  weight_decay: 0.0500 (0.0500)  time: 0.4599  data: 0.0639  max mem: 31830
Epoch: [248]  [ 80/312]  eta: 0:02:26  lr: 0.000329  min_lr: 0.000329  loss: 3.1392 (3.2869)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.1422  max mem: 31830
Epoch: [248]  [ 90/312]  eta: 0:02:15  lr: 0.000328  min_lr: 0.000328  loss: 3.3417 (3.2752)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0925  max mem: 31830
Epoch: [248]  [100/312]  eta: 0:02:10  lr: 0.000328  min_lr: 0.000328  loss: 3.3417 (3.2931)  weight_decay: 0.0500 (0.0500)  time: 0.5589  data: 0.0976  max mem: 31830
Epoch: [248]  [110/312]  eta: 0:02:00  lr: 0.000327  min_lr: 0.000327  loss: 3.2884 (3.2861)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.0842  max mem: 31830
Epoch: [248]  [120/312]  eta: 0:01:54  lr: 0.000327  min_lr: 0.000327  loss: 3.2050 (3.2748)  weight_decay: 0.0500 (0.0500)  time: 0.4829  data: 0.0313  max mem: 31830
Epoch: [248]  [130/312]  eta: 0:01:48  lr: 0.000327  min_lr: 0.000327  loss: 3.4317 (3.2800)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0871  max mem: 31830
Epoch: [248]  [140/312]  eta: 0:01:39  lr: 0.000326  min_lr: 0.000326  loss: 3.4556 (3.2749)  weight_decay: 0.0500 (0.0500)  time: 0.4895  data: 0.0566  max mem: 31830
Epoch: [248]  [150/312]  eta: 0:01:34  lr: 0.000326  min_lr: 0.000326  loss: 3.1038 (3.2727)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0616  max mem: 31830
Epoch: [248]  [160/312]  eta: 0:01:28  lr: 0.000325  min_lr: 0.000325  loss: 2.9175 (3.2434)  weight_decay: 0.0500 (0.0500)  time: 0.6033  data: 0.1044  max mem: 31830
Epoch: [248]  [170/312]  eta: 0:01:21  lr: 0.000325  min_lr: 0.000325  loss: 2.9175 (3.2504)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0639  max mem: 31830
Epoch: [248]  [180/312]  eta: 0:01:16  lr: 0.000325  min_lr: 0.000325  loss: 3.2487 (3.2483)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0915  max mem: 31830
Epoch: [248]  [190/312]  eta: 0:01:09  lr: 0.000324  min_lr: 0.000324  loss: 3.2057 (3.2492)  weight_decay: 0.0500 (0.0500)  time: 0.5353  data: 0.1000  max mem: 31830
Epoch: [248]  [200/312]  eta: 0:01:04  lr: 0.000324  min_lr: 0.000324  loss: 3.2057 (3.2418)  weight_decay: 0.0500 (0.0500)  time: 0.5309  data: 0.0782  max mem: 31830
Epoch: [248]  [210/312]  eta: 0:00:58  lr: 0.000323  min_lr: 0.000323  loss: 3.4722 (3.2480)  weight_decay: 0.0500 (0.0500)  time: 0.6023  data: 0.1057  max mem: 31830
Epoch: [248]  [220/312]  eta: 0:00:52  lr: 0.000323  min_lr: 0.000323  loss: 3.4612 (3.2464)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0575  max mem: 31830
Epoch: [248]  [230/312]  eta: 0:00:46  lr: 0.000323  min_lr: 0.000323  loss: 3.4388 (3.2494)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0487  max mem: 31830
Epoch: [248]  [240/312]  eta: 0:00:40  lr: 0.000322  min_lr: 0.000322  loss: 3.5291 (3.2554)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.0808  max mem: 31830
Epoch: [248]  [250/312]  eta: 0:00:35  lr: 0.000322  min_lr: 0.000322  loss: 3.2609 (3.2465)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0332  max mem: 31830
Epoch: [248]  [260/312]  eta: 0:00:29  lr: 0.000322  min_lr: 0.000322  loss: 3.3208 (3.2463)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.0176  max mem: 31830
Epoch: [248]  [270/312]  eta: 0:00:23  lr: 0.000321  min_lr: 0.000321  loss: 3.3522 (3.2392)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0383  max mem: 31830
Epoch: [248]  [280/312]  eta: 0:00:18  lr: 0.000321  min_lr: 0.000321  loss: 3.2265 (3.2325)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0255  max mem: 31830
Epoch: [248]  [290/312]  eta: 0:00:12  lr: 0.000320  min_lr: 0.000320  loss: 3.2821 (3.2351)  weight_decay: 0.0500 (0.0500)  time: 0.5741  data: 0.0178  max mem: 31830
Epoch: [248]  [300/312]  eta: 0:00:06  lr: 0.000320  min_lr: 0.000320  loss: 3.2821 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 0.4599  data: 0.0136  max mem: 31830
Epoch: [248]  [310/312]  eta: 0:00:01  lr: 0.000320  min_lr: 0.000320  loss: 3.0959 (3.2314)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [248]  [311/312]  eta: 0:00:00  lr: 0.000320  min_lr: 0.000320  loss: 3.1135 (3.2317)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [248] Total time: 0:02:53 (0.5573 s / it)
Averaged stats: lr: 0.000320  min_lr: 0.000320  loss: 3.1135 (3.2550)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9635 (0.9635)  acc1: 83.0729 (83.0729)  acc5: 96.3542 (96.3542)  time: 8.5368  data: 8.3742  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2507 (1.1792)  acc1: 77.4740 (76.5280)  acc5: 94.0104 (93.6320)  time: 1.0665  data: 0.9306  max mem: 31830
Test: Total time: 0:00:09 (1.0854 s / it)
* Acc@1 77.040 Acc@5 93.896 loss 1.169
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 77.04%
Epoch: [249]  [  0/312]  eta: 0:55:08  lr: 0.000320  min_lr: 0.000320  loss: 2.1112 (2.1112)  weight_decay: 0.0500 (0.0500)  time: 10.6033  data: 9.6950  max mem: 31830
Epoch: [249]  [ 10/312]  eta: 0:08:45  lr: 0.000319  min_lr: 0.000319  loss: 2.7768 (2.8041)  weight_decay: 0.0500 (0.0500)  time: 1.7406  data: 1.0272  max mem: 31830
Epoch: [249]  [ 20/312]  eta: 0:05:23  lr: 0.000319  min_lr: 0.000319  loss: 3.0233 (2.9679)  weight_decay: 0.0500 (0.0500)  time: 0.6322  data: 0.0891  max mem: 31830
Epoch: [249]  [ 30/312]  eta: 0:04:08  lr: 0.000318  min_lr: 0.000318  loss: 3.1123 (2.9833)  weight_decay: 0.0500 (0.0500)  time: 0.4072  data: 0.0161  max mem: 31830
Epoch: [249]  [ 40/312]  eta: 0:03:27  lr: 0.000318  min_lr: 0.000318  loss: 3.1705 (3.0138)  weight_decay: 0.0500 (0.0500)  time: 0.4021  data: 0.0084  max mem: 31830
Epoch: [249]  [ 50/312]  eta: 0:03:01  lr: 0.000318  min_lr: 0.000318  loss: 3.1705 (3.0253)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0019  max mem: 31830
Epoch: [249]  [ 60/312]  eta: 0:02:42  lr: 0.000317  min_lr: 0.000317  loss: 2.8389 (3.0566)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0012  max mem: 31830
Epoch: [249]  [ 70/312]  eta: 0:02:33  lr: 0.000317  min_lr: 0.000317  loss: 3.4162 (3.0949)  weight_decay: 0.0500 (0.0500)  time: 0.4802  data: 0.0455  max mem: 31830
Epoch: [249]  [ 80/312]  eta: 0:02:23  lr: 0.000316  min_lr: 0.000316  loss: 3.5632 (3.1455)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0618  max mem: 31830
Epoch: [249]  [ 90/312]  eta: 0:02:15  lr: 0.000316  min_lr: 0.000316  loss: 3.5691 (3.1802)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0504  max mem: 31830
Epoch: [249]  [100/312]  eta: 0:02:09  lr: 0.000316  min_lr: 0.000316  loss: 3.4218 (3.1582)  weight_decay: 0.0500 (0.0500)  time: 0.5796  data: 0.0721  max mem: 31830
Epoch: [249]  [110/312]  eta: 0:01:59  lr: 0.000315  min_lr: 0.000315  loss: 3.2986 (3.1856)  weight_decay: 0.0500 (0.0500)  time: 0.4988  data: 0.0388  max mem: 31830
Epoch: [249]  [120/312]  eta: 0:01:53  lr: 0.000315  min_lr: 0.000315  loss: 3.3763 (3.1936)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0370  max mem: 31830
Epoch: [249]  [130/312]  eta: 0:01:47  lr: 0.000314  min_lr: 0.000314  loss: 3.2608 (3.1951)  weight_decay: 0.0500 (0.0500)  time: 0.5869  data: 0.0965  max mem: 31830
Epoch: [249]  [140/312]  eta: 0:01:39  lr: 0.000314  min_lr: 0.000314  loss: 3.1708 (3.1845)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0604  max mem: 31830
Epoch: [249]  [150/312]  eta: 0:01:34  lr: 0.000314  min_lr: 0.000314  loss: 3.1708 (3.1897)  weight_decay: 0.0500 (0.0500)  time: 0.5384  data: 0.0512  max mem: 31830
Epoch: [249]  [160/312]  eta: 0:01:27  lr: 0.000313  min_lr: 0.000313  loss: 3.2607 (3.1889)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0601  max mem: 31830
Epoch: [249]  [170/312]  eta: 0:01:21  lr: 0.000313  min_lr: 0.000313  loss: 3.3282 (3.2023)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0560  max mem: 31830
Epoch: [249]  [180/312]  eta: 0:01:16  lr: 0.000313  min_lr: 0.000313  loss: 3.4942 (3.2152)  weight_decay: 0.0500 (0.0500)  time: 0.6021  data: 0.0946  max mem: 31830
Epoch: [249]  [190/312]  eta: 0:01:09  lr: 0.000312  min_lr: 0.000312  loss: 3.4019 (3.2139)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0573  max mem: 31830
Epoch: [249]  [200/312]  eta: 0:01:04  lr: 0.000312  min_lr: 0.000312  loss: 3.1840 (3.2113)  weight_decay: 0.0500 (0.0500)  time: 0.5166  data: 0.0378  max mem: 31830
Epoch: [249]  [210/312]  eta: 0:00:57  lr: 0.000311  min_lr: 0.000311  loss: 3.0864 (3.2020)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0449  max mem: 31830
Epoch: [249]  [220/312]  eta: 0:00:52  lr: 0.000311  min_lr: 0.000311  loss: 3.2438 (3.2018)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0167  max mem: 31830
Epoch: [249]  [230/312]  eta: 0:00:46  lr: 0.000311  min_lr: 0.000311  loss: 3.4892 (3.2147)  weight_decay: 0.0500 (0.0500)  time: 0.6197  data: 0.0162  max mem: 31830
Epoch: [249]  [240/312]  eta: 0:00:40  lr: 0.000310  min_lr: 0.000310  loss: 3.5765 (3.2275)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0164  max mem: 31830
Epoch: [249]  [250/312]  eta: 0:00:35  lr: 0.000310  min_lr: 0.000310  loss: 3.4897 (3.2258)  weight_decay: 0.0500 (0.0500)  time: 0.5171  data: 0.0149  max mem: 31830
Epoch: [249]  [260/312]  eta: 0:00:29  lr: 0.000309  min_lr: 0.000309  loss: 3.3736 (3.2295)  weight_decay: 0.0500 (0.0500)  time: 0.6047  data: 0.0154  max mem: 31830
Epoch: [249]  [270/312]  eta: 0:00:23  lr: 0.000309  min_lr: 0.000309  loss: 3.4020 (3.2307)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0017  max mem: 31830
Epoch: [249]  [280/312]  eta: 0:00:18  lr: 0.000309  min_lr: 0.000309  loss: 3.3386 (3.2272)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0021  max mem: 31830
Epoch: [249]  [290/312]  eta: 0:00:12  lr: 0.000308  min_lr: 0.000308  loss: 3.3483 (3.2315)  weight_decay: 0.0500 (0.0500)  time: 0.5370  data: 0.0106  max mem: 31830
Epoch: [249]  [300/312]  eta: 0:00:06  lr: 0.000308  min_lr: 0.000308  loss: 3.3385 (3.2299)  weight_decay: 0.0500 (0.0500)  time: 0.4732  data: 0.0090  max mem: 31830
Epoch: [249]  [310/312]  eta: 0:00:01  lr: 0.000308  min_lr: 0.000308  loss: 3.3385 (3.2259)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0001  max mem: 31830
Epoch: [249]  [311/312]  eta: 0:00:00  lr: 0.000308  min_lr: 0.000308  loss: 3.1651 (3.2243)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [249] Total time: 0:02:53 (0.5575 s / it)
Averaged stats: lr: 0.000308  min_lr: 0.000308  loss: 3.1651 (3.2414)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8732 (0.8732)  acc1: 83.2031 (83.2031)  acc5: 96.0938 (96.0938)  time: 8.4111  data: 8.2442  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1735 (1.0882)  acc1: 76.5625 (76.6240)  acc5: 93.7500 (93.6160)  time: 1.0585  data: 0.9228  max mem: 31830
Test: Total time: 0:00:09 (1.0688 s / it)
* Acc@1 77.170 Acc@5 93.794 loss 1.075
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.17%
Epoch: [250]  [  0/312]  eta: 1:02:04  lr: 0.000307  min_lr: 0.000307  loss: 2.7648 (2.7648)  weight_decay: 0.0500 (0.0500)  time: 11.9362  data: 8.6887  max mem: 31830
Epoch: [250]  [ 10/312]  eta: 0:08:21  lr: 0.000307  min_lr: 0.000307  loss: 3.2825 (3.1162)  weight_decay: 0.0500 (0.0500)  time: 1.6600  data: 1.0127  max mem: 31830
Epoch: [250]  [ 20/312]  eta: 0:05:23  lr: 0.000307  min_lr: 0.000307  loss: 3.3096 (3.1384)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.1416  max mem: 31830
Epoch: [250]  [ 30/312]  eta: 0:04:07  lr: 0.000306  min_lr: 0.000306  loss: 3.4389 (3.1388)  weight_decay: 0.0500 (0.0500)  time: 0.4480  data: 0.0194  max mem: 31830
Epoch: [250]  [ 40/312]  eta: 0:03:26  lr: 0.000306  min_lr: 0.000306  loss: 3.4959 (3.2159)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0009  max mem: 31830
Epoch: [250]  [ 50/312]  eta: 0:03:00  lr: 0.000306  min_lr: 0.000306  loss: 3.4353 (3.2046)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0010  max mem: 31830
Epoch: [250]  [ 60/312]  eta: 0:02:41  lr: 0.000305  min_lr: 0.000305  loss: 3.4124 (3.2469)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0009  max mem: 31830
Epoch: [250]  [ 70/312]  eta: 0:02:35  lr: 0.000305  min_lr: 0.000305  loss: 3.3918 (3.2350)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0790  max mem: 31830
Epoch: [250]  [ 80/312]  eta: 0:02:27  lr: 0.000304  min_lr: 0.000304  loss: 3.2730 (3.2175)  weight_decay: 0.0500 (0.0500)  time: 0.6188  data: 0.1232  max mem: 31830
Epoch: [250]  [ 90/312]  eta: 0:02:15  lr: 0.000304  min_lr: 0.000304  loss: 3.2730 (3.2212)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0514  max mem: 31830
Epoch: [250]  [100/312]  eta: 0:02:09  lr: 0.000304  min_lr: 0.000304  loss: 3.5184 (3.2470)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0773  max mem: 31830
Epoch: [250]  [110/312]  eta: 0:01:59  lr: 0.000303  min_lr: 0.000303  loss: 3.4479 (3.2512)  weight_decay: 0.0500 (0.0500)  time: 0.5184  data: 0.0758  max mem: 31830
Epoch: [250]  [120/312]  eta: 0:01:54  lr: 0.000303  min_lr: 0.000303  loss: 3.2796 (3.2454)  weight_decay: 0.0500 (0.0500)  time: 0.5194  data: 0.0643  max mem: 31830
Epoch: [250]  [130/312]  eta: 0:01:48  lr: 0.000303  min_lr: 0.000303  loss: 3.3936 (3.2566)  weight_decay: 0.0500 (0.0500)  time: 0.6025  data: 0.1282  max mem: 31830
Epoch: [250]  [140/312]  eta: 0:01:40  lr: 0.000302  min_lr: 0.000302  loss: 3.4706 (3.2639)  weight_decay: 0.0500 (0.0500)  time: 0.4905  data: 0.0827  max mem: 31830
Epoch: [250]  [150/312]  eta: 0:01:34  lr: 0.000302  min_lr: 0.000302  loss: 3.2942 (3.2550)  weight_decay: 0.0500 (0.0500)  time: 0.5215  data: 0.1025  max mem: 31830
Epoch: [250]  [160/312]  eta: 0:01:29  lr: 0.000301  min_lr: 0.000301  loss: 3.3854 (3.2708)  weight_decay: 0.0500 (0.0500)  time: 0.6178  data: 0.1658  max mem: 31830
Epoch: [250]  [170/312]  eta: 0:01:21  lr: 0.000301  min_lr: 0.000301  loss: 3.4217 (3.2774)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0773  max mem: 31830
Epoch: [250]  [180/312]  eta: 0:01:16  lr: 0.000301  min_lr: 0.000301  loss: 3.3905 (3.2822)  weight_decay: 0.0500 (0.0500)  time: 0.4987  data: 0.0789  max mem: 31830
Epoch: [250]  [190/312]  eta: 0:01:09  lr: 0.000300  min_lr: 0.000300  loss: 3.4510 (3.2821)  weight_decay: 0.0500 (0.0500)  time: 0.5158  data: 0.0965  max mem: 31830
Epoch: [250]  [200/312]  eta: 0:01:03  lr: 0.000300  min_lr: 0.000300  loss: 3.4510 (3.2754)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0921  max mem: 31830
Epoch: [250]  [210/312]  eta: 0:00:58  lr: 0.000299  min_lr: 0.000299  loss: 2.9180 (3.2610)  weight_decay: 0.0500 (0.0500)  time: 0.6085  data: 0.1446  max mem: 31830
Epoch: [250]  [220/312]  eta: 0:00:52  lr: 0.000299  min_lr: 0.000299  loss: 3.3320 (3.2701)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0710  max mem: 31830
Epoch: [250]  [230/312]  eta: 0:00:46  lr: 0.000299  min_lr: 0.000299  loss: 3.4841 (3.2754)  weight_decay: 0.0500 (0.0500)  time: 0.5227  data: 0.0832  max mem: 31830
Epoch: [250]  [240/312]  eta: 0:00:41  lr: 0.000298  min_lr: 0.000298  loss: 3.2882 (3.2725)  weight_decay: 0.0500 (0.0500)  time: 0.6244  data: 0.1626  max mem: 31830
Epoch: [250]  [250/312]  eta: 0:00:34  lr: 0.000298  min_lr: 0.000298  loss: 3.0970 (3.2563)  weight_decay: 0.0500 (0.0500)  time: 0.5080  data: 0.0803  max mem: 31830
Epoch: [250]  [260/312]  eta: 0:00:29  lr: 0.000298  min_lr: 0.000298  loss: 3.0970 (3.2567)  weight_decay: 0.0500 (0.0500)  time: 0.5162  data: 0.0564  max mem: 31830
Epoch: [250]  [270/312]  eta: 0:00:23  lr: 0.000297  min_lr: 0.000297  loss: 3.3784 (3.2531)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.0627  max mem: 31830
Epoch: [250]  [280/312]  eta: 0:00:18  lr: 0.000297  min_lr: 0.000297  loss: 3.1367 (3.2436)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0678  max mem: 31830
Epoch: [250]  [290/312]  eta: 0:00:12  lr: 0.000296  min_lr: 0.000296  loss: 3.1241 (3.2439)  weight_decay: 0.0500 (0.0500)  time: 0.6133  data: 0.1312  max mem: 31830
Epoch: [250]  [300/312]  eta: 0:00:06  lr: 0.000296  min_lr: 0.000296  loss: 3.4224 (3.2507)  weight_decay: 0.0500 (0.0500)  time: 0.4683  data: 0.0702  max mem: 31830
Epoch: [250]  [310/312]  eta: 0:00:01  lr: 0.000296  min_lr: 0.000296  loss: 3.4224 (3.2472)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [250]  [311/312]  eta: 0:00:00  lr: 0.000296  min_lr: 0.000296  loss: 3.4339 (3.2478)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [250] Total time: 0:02:53 (0.5557 s / it)
Averaged stats: lr: 0.000296  min_lr: 0.000296  loss: 3.4339 (3.2384)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.9951 (0.9951)  acc1: 82.2917 (82.2917)  acc5: 96.7448 (96.7448)  time: 8.2179  data: 8.0535  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2893 (1.1854)  acc1: 76.6927 (76.7680)  acc5: 93.4896 (93.6800)  time: 1.0788  data: 0.9438  max mem: 31830
Test: Total time: 0:00:09 (1.0895 s / it)
* Acc@1 77.208 Acc@5 93.840 loss 1.176
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.21%
Epoch: [251]  [  0/312]  eta: 1:01:25  lr: 0.000296  min_lr: 0.000296  loss: 3.8689 (3.8689)  weight_decay: 0.0500 (0.0500)  time: 11.8130  data: 11.4190  max mem: 31830
Epoch: [251]  [ 10/312]  eta: 0:08:16  lr: 0.000295  min_lr: 0.000295  loss: 3.5108 (3.4631)  weight_decay: 0.0500 (0.0500)  time: 1.6432  data: 1.0389  max mem: 31830
Epoch: [251]  [ 20/312]  eta: 0:05:20  lr: 0.000295  min_lr: 0.000295  loss: 3.4213 (3.3855)  weight_decay: 0.0500 (0.0500)  time: 0.5614  data: 0.0008  max mem: 31830
Epoch: [251]  [ 30/312]  eta: 0:04:05  lr: 0.000295  min_lr: 0.000295  loss: 3.2991 (3.2849)  weight_decay: 0.0500 (0.0500)  time: 0.4463  data: 0.0008  max mem: 31830
Epoch: [251]  [ 40/312]  eta: 0:03:25  lr: 0.000294  min_lr: 0.000294  loss: 3.1475 (3.2243)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0008  max mem: 31830
Epoch: [251]  [ 50/312]  eta: 0:03:02  lr: 0.000294  min_lr: 0.000294  loss: 3.0623 (3.2170)  weight_decay: 0.0500 (0.0500)  time: 0.4300  data: 0.0343  max mem: 31830
Epoch: [251]  [ 60/312]  eta: 0:02:43  lr: 0.000293  min_lr: 0.000293  loss: 3.3881 (3.2511)  weight_decay: 0.0500 (0.0500)  time: 0.4292  data: 0.0342  max mem: 31830
Epoch: [251]  [ 70/312]  eta: 0:02:34  lr: 0.000293  min_lr: 0.000293  loss: 3.4801 (3.2722)  weight_decay: 0.0500 (0.0500)  time: 0.4916  data: 0.0950  max mem: 31830
Epoch: [251]  [ 80/312]  eta: 0:02:26  lr: 0.000293  min_lr: 0.000293  loss: 3.1917 (3.2472)  weight_decay: 0.0500 (0.0500)  time: 0.5735  data: 0.1808  max mem: 31830
Epoch: [251]  [ 90/312]  eta: 0:02:15  lr: 0.000292  min_lr: 0.000292  loss: 2.9724 (3.2291)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.1155  max mem: 31830
Epoch: [251]  [100/312]  eta: 0:02:09  lr: 0.000292  min_lr: 0.000292  loss: 3.2566 (3.2358)  weight_decay: 0.0500 (0.0500)  time: 0.5450  data: 0.1453  max mem: 31830
Epoch: [251]  [110/312]  eta: 0:01:59  lr: 0.000292  min_lr: 0.000292  loss: 3.4279 (3.2365)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.1169  max mem: 31830
Epoch: [251]  [120/312]  eta: 0:01:54  lr: 0.000291  min_lr: 0.000291  loss: 2.8560 (3.1910)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.1131  max mem: 31830
Epoch: [251]  [130/312]  eta: 0:01:48  lr: 0.000291  min_lr: 0.000291  loss: 2.7427 (3.1910)  weight_decay: 0.0500 (0.0500)  time: 0.6149  data: 0.2154  max mem: 31830
Epoch: [251]  [140/312]  eta: 0:01:40  lr: 0.000290  min_lr: 0.000290  loss: 3.3967 (3.2062)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.1104  max mem: 31830
Epoch: [251]  [150/312]  eta: 0:01:34  lr: 0.000290  min_lr: 0.000290  loss: 3.3867 (3.2020)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0905  max mem: 31830
Epoch: [251]  [160/312]  eta: 0:01:29  lr: 0.000290  min_lr: 0.000290  loss: 3.1664 (3.2068)  weight_decay: 0.0500 (0.0500)  time: 0.5821  data: 0.1648  max mem: 31830
Epoch: [251]  [170/312]  eta: 0:01:22  lr: 0.000289  min_lr: 0.000289  loss: 3.4386 (3.2084)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.1039  max mem: 31830
Epoch: [251]  [180/312]  eta: 0:01:16  lr: 0.000289  min_lr: 0.000289  loss: 3.4365 (3.2067)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.1161  max mem: 31830
Epoch: [251]  [190/312]  eta: 0:01:09  lr: 0.000289  min_lr: 0.000289  loss: 3.1330 (3.2056)  weight_decay: 0.0500 (0.0500)  time: 0.5279  data: 0.0939  max mem: 31830
Epoch: [251]  [200/312]  eta: 0:01:04  lr: 0.000288  min_lr: 0.000288  loss: 3.3354 (3.2146)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0669  max mem: 31830
Epoch: [251]  [210/312]  eta: 0:00:58  lr: 0.000288  min_lr: 0.000288  loss: 3.4274 (3.2088)  weight_decay: 0.0500 (0.0500)  time: 0.5818  data: 0.1318  max mem: 31830
Epoch: [251]  [220/312]  eta: 0:00:52  lr: 0.000287  min_lr: 0.000287  loss: 3.3837 (3.2193)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0657  max mem: 31830
Epoch: [251]  [230/312]  eta: 0:00:46  lr: 0.000287  min_lr: 0.000287  loss: 3.3837 (3.2188)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0702  max mem: 31830
Epoch: [251]  [240/312]  eta: 0:00:40  lr: 0.000287  min_lr: 0.000287  loss: 3.1739 (3.2220)  weight_decay: 0.0500 (0.0500)  time: 0.5722  data: 0.1431  max mem: 31830
Epoch: [251]  [250/312]  eta: 0:00:35  lr: 0.000286  min_lr: 0.000286  loss: 3.1987 (3.2161)  weight_decay: 0.0500 (0.0500)  time: 0.5351  data: 0.1025  max mem: 31830
Epoch: [251]  [260/312]  eta: 0:00:29  lr: 0.000286  min_lr: 0.000286  loss: 3.1987 (3.2179)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.1137  max mem: 31830
Epoch: [251]  [270/312]  eta: 0:00:23  lr: 0.000286  min_lr: 0.000286  loss: 3.5184 (3.2275)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0854  max mem: 31830
Epoch: [251]  [280/312]  eta: 0:00:18  lr: 0.000285  min_lr: 0.000285  loss: 3.5184 (3.2367)  weight_decay: 0.0500 (0.0500)  time: 0.5229  data: 0.0796  max mem: 31830
Epoch: [251]  [290/312]  eta: 0:00:12  lr: 0.000285  min_lr: 0.000285  loss: 3.4161 (3.2359)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.1451  max mem: 31830
Epoch: [251]  [300/312]  eta: 0:00:06  lr: 0.000284  min_lr: 0.000284  loss: 3.3653 (3.2301)  weight_decay: 0.0500 (0.0500)  time: 0.4647  data: 0.0666  max mem: 31830
Epoch: [251]  [310/312]  eta: 0:00:01  lr: 0.000284  min_lr: 0.000284  loss: 3.3653 (3.2307)  weight_decay: 0.0500 (0.0500)  time: 0.3946  data: 0.0001  max mem: 31830
Epoch: [251]  [311/312]  eta: 0:00:00  lr: 0.000284  min_lr: 0.000284  loss: 3.2753 (3.2289)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [251] Total time: 0:02:53 (0.5553 s / it)
Averaged stats: lr: 0.000284  min_lr: 0.000284  loss: 3.2753 (3.2449)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8718 (0.8718)  acc1: 84.1146 (84.1146)  acc5: 96.0938 (96.0938)  time: 8.7025  data: 8.5348  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2071 (1.1202)  acc1: 76.4323 (76.8640)  acc5: 94.4010 (93.7280)  time: 1.1033  data: 0.9674  max mem: 31830
Test: Total time: 0:00:10 (1.1255 s / it)
* Acc@1 77.290 Acc@5 93.828 loss 1.109
Accuracy of the model on the 50000 test images: 77.3%
Max accuracy: 77.29%
Epoch: [252]  [  0/312]  eta: 1:03:54  lr: 0.000284  min_lr: 0.000284  loss: 2.8213 (2.8213)  weight_decay: 0.0500 (0.0500)  time: 12.2898  data: 9.4742  max mem: 31830
Epoch: [252]  [ 10/312]  eta: 0:09:05  lr: 0.000284  min_lr: 0.000284  loss: 3.5041 (3.2757)  weight_decay: 0.0500 (0.0500)  time: 1.8079  data: 1.0087  max mem: 31830
Epoch: [252]  [ 20/312]  eta: 0:05:30  lr: 0.000283  min_lr: 0.000283  loss: 3.2224 (3.2004)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0814  max mem: 31830
Epoch: [252]  [ 30/312]  eta: 0:04:12  lr: 0.000283  min_lr: 0.000283  loss: 3.2337 (3.2899)  weight_decay: 0.0500 (0.0500)  time: 0.3924  data: 0.0014  max mem: 31830
Epoch: [252]  [ 40/312]  eta: 0:03:30  lr: 0.000283  min_lr: 0.000283  loss: 3.5185 (3.3062)  weight_decay: 0.0500 (0.0500)  time: 0.3948  data: 0.0015  max mem: 31830
Epoch: [252]  [ 50/312]  eta: 0:03:03  lr: 0.000282  min_lr: 0.000282  loss: 3.2727 (3.2689)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0008  max mem: 31830
Epoch: [252]  [ 60/312]  eta: 0:02:43  lr: 0.000282  min_lr: 0.000282  loss: 3.1769 (3.2930)  weight_decay: 0.0500 (0.0500)  time: 0.3977  data: 0.0016  max mem: 31830
Epoch: [252]  [ 70/312]  eta: 0:02:29  lr: 0.000281  min_lr: 0.000281  loss: 3.2161 (3.2773)  weight_decay: 0.0500 (0.0500)  time: 0.4150  data: 0.0016  max mem: 31830
Epoch: [252]  [ 80/312]  eta: 0:02:20  lr: 0.000281  min_lr: 0.000281  loss: 3.3284 (3.2942)  weight_decay: 0.0500 (0.0500)  time: 0.4777  data: 0.0518  max mem: 31830
Epoch: [252]  [ 90/312]  eta: 0:02:15  lr: 0.000281  min_lr: 0.000281  loss: 3.3930 (3.2784)  weight_decay: 0.0500 (0.0500)  time: 0.5840  data: 0.0964  max mem: 31830
Epoch: [252]  [100/312]  eta: 0:02:06  lr: 0.000280  min_lr: 0.000280  loss: 3.2503 (3.2827)  weight_decay: 0.0500 (0.0500)  time: 0.5585  data: 0.0591  max mem: 31830
Epoch: [252]  [110/312]  eta: 0:01:59  lr: 0.000280  min_lr: 0.000280  loss: 3.4792 (3.2862)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0838  max mem: 31830
Epoch: [252]  [120/312]  eta: 0:01:55  lr: 0.000280  min_lr: 0.000280  loss: 3.4704 (3.2812)  weight_decay: 0.0500 (0.0500)  time: 0.6221  data: 0.0758  max mem: 31830
Epoch: [252]  [130/312]  eta: 0:01:48  lr: 0.000279  min_lr: 0.000279  loss: 3.4444 (3.2826)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0598  max mem: 31830
Epoch: [252]  [140/312]  eta: 0:01:41  lr: 0.000279  min_lr: 0.000279  loss: 3.4591 (3.2842)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0869  max mem: 31830
Epoch: [252]  [150/312]  eta: 0:01:33  lr: 0.000279  min_lr: 0.000279  loss: 3.4265 (3.2747)  weight_decay: 0.0500 (0.0500)  time: 0.4863  data: 0.0338  max mem: 31830
Epoch: [252]  [160/312]  eta: 0:01:28  lr: 0.000278  min_lr: 0.000278  loss: 3.1573 (3.2643)  weight_decay: 0.0500 (0.0500)  time: 0.5211  data: 0.0486  max mem: 31830
Epoch: [252]  [170/312]  eta: 0:01:23  lr: 0.000278  min_lr: 0.000278  loss: 3.1178 (3.2536)  weight_decay: 0.0500 (0.0500)  time: 0.6411  data: 0.0981  max mem: 31830
Epoch: [252]  [180/312]  eta: 0:01:16  lr: 0.000277  min_lr: 0.000277  loss: 3.0361 (3.2371)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0504  max mem: 31830
Epoch: [252]  [190/312]  eta: 0:01:10  lr: 0.000277  min_lr: 0.000277  loss: 3.2357 (3.2406)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0770  max mem: 31830
Epoch: [252]  [200/312]  eta: 0:01:04  lr: 0.000277  min_lr: 0.000277  loss: 3.4308 (3.2363)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.0775  max mem: 31830
Epoch: [252]  [210/312]  eta: 0:00:58  lr: 0.000276  min_lr: 0.000276  loss: 3.0444 (3.2352)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0681  max mem: 31830
Epoch: [252]  [220/312]  eta: 0:00:53  lr: 0.000276  min_lr: 0.000276  loss: 3.4193 (3.2366)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1263  max mem: 31830
Epoch: [252]  [230/312]  eta: 0:00:46  lr: 0.000276  min_lr: 0.000276  loss: 3.4193 (3.2354)  weight_decay: 0.0500 (0.0500)  time: 0.5335  data: 0.0599  max mem: 31830
Epoch: [252]  [240/312]  eta: 0:00:41  lr: 0.000275  min_lr: 0.000275  loss: 3.3937 (3.2420)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0847  max mem: 31830
Epoch: [252]  [250/312]  eta: 0:00:35  lr: 0.000275  min_lr: 0.000275  loss: 3.3580 (3.2406)  weight_decay: 0.0500 (0.0500)  time: 0.6498  data: 0.1826  max mem: 31830
Epoch: [252]  [260/312]  eta: 0:00:29  lr: 0.000275  min_lr: 0.000275  loss: 3.1234 (3.2372)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0992  max mem: 31830
Epoch: [252]  [270/312]  eta: 0:00:24  lr: 0.000274  min_lr: 0.000274  loss: 3.0537 (3.2275)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0697  max mem: 31830
Epoch: [252]  [280/312]  eta: 0:00:18  lr: 0.000274  min_lr: 0.000274  loss: 3.2992 (3.2366)  weight_decay: 0.0500 (0.0500)  time: 0.5674  data: 0.0724  max mem: 31830
Epoch: [252]  [290/312]  eta: 0:00:12  lr: 0.000273  min_lr: 0.000273  loss: 3.4497 (3.2384)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0750  max mem: 31830
Epoch: [252]  [300/312]  eta: 0:00:06  lr: 0.000273  min_lr: 0.000273  loss: 3.4583 (3.2470)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0971  max mem: 31830
Epoch: [252]  [310/312]  eta: 0:00:01  lr: 0.000273  min_lr: 0.000273  loss: 3.3256 (3.2413)  weight_decay: 0.0500 (0.0500)  time: 0.4264  data: 0.0253  max mem: 31830
Epoch: [252]  [311/312]  eta: 0:00:00  lr: 0.000273  min_lr: 0.000273  loss: 3.2344 (3.2406)  weight_decay: 0.0500 (0.0500)  time: 0.4262  data: 0.0253  max mem: 31830
Epoch: [252] Total time: 0:02:55 (0.5629 s / it)
Averaged stats: lr: 0.000273  min_lr: 0.000273  loss: 3.2344 (3.2444)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8975 (0.8975)  acc1: 83.8542 (83.8542)  acc5: 96.8750 (96.8750)  time: 8.6220  data: 8.4545  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2187 (1.1443)  acc1: 78.9062 (77.7600)  acc5: 94.1406 (93.8720)  time: 1.0768  data: 0.9408  max mem: 31830
Test: Total time: 0:00:09 (1.1049 s / it)
* Acc@1 77.590 Acc@5 93.978 loss 1.145
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.59%
Epoch: [253]  [  0/312]  eta: 1:01:37  lr: 0.000273  min_lr: 0.000273  loss: 3.7299 (3.7299)  weight_decay: 0.0500 (0.0500)  time: 11.8525  data: 8.7710  max mem: 31830
Epoch: [253]  [ 10/312]  eta: 0:08:24  lr: 0.000272  min_lr: 0.000272  loss: 2.9549 (3.1012)  weight_decay: 0.0500 (0.0500)  time: 1.6712  data: 0.9826  max mem: 31830
Epoch: [253]  [ 20/312]  eta: 0:05:37  lr: 0.000272  min_lr: 0.000272  loss: 3.2130 (3.2312)  weight_decay: 0.0500 (0.0500)  time: 0.6197  data: 0.1636  max mem: 31830
Epoch: [253]  [ 30/312]  eta: 0:04:16  lr: 0.000272  min_lr: 0.000272  loss: 3.2233 (3.1824)  weight_decay: 0.0500 (0.0500)  time: 0.4883  data: 0.0620  max mem: 31830
Epoch: [253]  [ 40/312]  eta: 0:03:32  lr: 0.000271  min_lr: 0.000271  loss: 2.8934 (3.0837)  weight_decay: 0.0500 (0.0500)  time: 0.3921  data: 0.0007  max mem: 31830
Epoch: [253]  [ 50/312]  eta: 0:03:05  lr: 0.000271  min_lr: 0.000271  loss: 2.9768 (3.1357)  weight_decay: 0.0500 (0.0500)  time: 0.3969  data: 0.0016  max mem: 31830
Epoch: [253]  [ 60/312]  eta: 0:02:45  lr: 0.000270  min_lr: 0.000270  loss: 3.3949 (3.1482)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0017  max mem: 31830
Epoch: [253]  [ 70/312]  eta: 0:02:33  lr: 0.000270  min_lr: 0.000270  loss: 3.3061 (3.1729)  weight_decay: 0.0500 (0.0500)  time: 0.4423  data: 0.0170  max mem: 31830
Epoch: [253]  [ 80/312]  eta: 0:02:23  lr: 0.000270  min_lr: 0.000270  loss: 3.2216 (3.1703)  weight_decay: 0.0500 (0.0500)  time: 0.5076  data: 0.0361  max mem: 31830
Epoch: [253]  [ 90/312]  eta: 0:02:13  lr: 0.000269  min_lr: 0.000269  loss: 3.3408 (3.1881)  weight_decay: 0.0500 (0.0500)  time: 0.4940  data: 0.0400  max mem: 31830
Epoch: [253]  [100/312]  eta: 0:02:08  lr: 0.000269  min_lr: 0.000269  loss: 3.3921 (3.1914)  weight_decay: 0.0500 (0.0500)  time: 0.5589  data: 0.0763  max mem: 31830
Epoch: [253]  [110/312]  eta: 0:01:58  lr: 0.000269  min_lr: 0.000269  loss: 3.3921 (3.2137)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0566  max mem: 31830
Epoch: [253]  [120/312]  eta: 0:01:53  lr: 0.000268  min_lr: 0.000268  loss: 3.2751 (3.1977)  weight_decay: 0.0500 (0.0500)  time: 0.5072  data: 0.0548  max mem: 31830
Epoch: [253]  [130/312]  eta: 0:01:46  lr: 0.000268  min_lr: 0.000268  loss: 3.2751 (3.2117)  weight_decay: 0.0500 (0.0500)  time: 0.5843  data: 0.0751  max mem: 31830
Epoch: [253]  [140/312]  eta: 0:01:39  lr: 0.000268  min_lr: 0.000268  loss: 3.3660 (3.2106)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0621  max mem: 31830
Epoch: [253]  [150/312]  eta: 0:01:34  lr: 0.000267  min_lr: 0.000267  loss: 3.3462 (3.1979)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.1041  max mem: 31830
Epoch: [253]  [160/312]  eta: 0:01:27  lr: 0.000267  min_lr: 0.000267  loss: 3.0233 (3.1917)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.0700  max mem: 31830
Epoch: [253]  [170/312]  eta: 0:01:21  lr: 0.000267  min_lr: 0.000267  loss: 3.2529 (3.1866)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0643  max mem: 31830
Epoch: [253]  [180/312]  eta: 0:01:16  lr: 0.000266  min_lr: 0.000266  loss: 2.9707 (3.1776)  weight_decay: 0.0500 (0.0500)  time: 0.5636  data: 0.1055  max mem: 31830
Epoch: [253]  [190/312]  eta: 0:01:09  lr: 0.000266  min_lr: 0.000266  loss: 3.3372 (3.1850)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0485  max mem: 31830
Epoch: [253]  [200/312]  eta: 0:01:03  lr: 0.000265  min_lr: 0.000265  loss: 3.4177 (3.1974)  weight_decay: 0.0500 (0.0500)  time: 0.5155  data: 0.0441  max mem: 31830
Epoch: [253]  [210/312]  eta: 0:00:58  lr: 0.000265  min_lr: 0.000265  loss: 3.4374 (3.1894)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0508  max mem: 31830
Epoch: [253]  [220/312]  eta: 0:00:52  lr: 0.000265  min_lr: 0.000265  loss: 3.1057 (3.1905)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0359  max mem: 31830
Epoch: [253]  [230/312]  eta: 0:00:46  lr: 0.000264  min_lr: 0.000264  loss: 3.4133 (3.2019)  weight_decay: 0.0500 (0.0500)  time: 0.5431  data: 0.0612  max mem: 31830
Epoch: [253]  [240/312]  eta: 0:00:40  lr: 0.000264  min_lr: 0.000264  loss: 3.4056 (3.2033)  weight_decay: 0.0500 (0.0500)  time: 0.5601  data: 0.0330  max mem: 31830
Epoch: [253]  [250/312]  eta: 0:00:34  lr: 0.000264  min_lr: 0.000264  loss: 3.3299 (3.2051)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.0315  max mem: 31830
Epoch: [253]  [260/312]  eta: 0:00:29  lr: 0.000263  min_lr: 0.000263  loss: 3.4483 (3.2113)  weight_decay: 0.0500 (0.0500)  time: 0.5956  data: 0.0647  max mem: 31830
Epoch: [253]  [270/312]  eta: 0:00:23  lr: 0.000263  min_lr: 0.000263  loss: 3.4483 (3.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.0342  max mem: 31830
Epoch: [253]  [280/312]  eta: 0:00:18  lr: 0.000263  min_lr: 0.000263  loss: 3.3656 (3.2163)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0303  max mem: 31830
Epoch: [253]  [290/312]  eta: 0:00:12  lr: 0.000262  min_lr: 0.000262  loss: 3.4681 (3.2263)  weight_decay: 0.0500 (0.0500)  time: 0.5501  data: 0.0428  max mem: 31830
Epoch: [253]  [300/312]  eta: 0:00:06  lr: 0.000262  min_lr: 0.000262  loss: 3.4754 (3.2320)  weight_decay: 0.0500 (0.0500)  time: 0.4615  data: 0.0334  max mem: 31830
Epoch: [253]  [310/312]  eta: 0:00:01  lr: 0.000262  min_lr: 0.000262  loss: 3.6102 (3.2426)  weight_decay: 0.0500 (0.0500)  time: 0.4089  data: 0.0204  max mem: 31830
Epoch: [253]  [311/312]  eta: 0:00:00  lr: 0.000261  min_lr: 0.000261  loss: 3.6545 (3.2449)  weight_decay: 0.0500 (0.0500)  time: 0.3891  data: 0.0002  max mem: 31830
Epoch: [253] Total time: 0:02:53 (0.5551 s / it)
Averaged stats: lr: 0.000261  min_lr: 0.000261  loss: 3.6545 (3.2417)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.0551 (1.0551)  acc1: 83.4635 (83.4635)  acc5: 96.7448 (96.7448)  time: 8.4059  data: 8.2393  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.3348 (1.2690)  acc1: 77.7344 (76.9280)  acc5: 94.4010 (93.5360)  time: 1.0713  data: 0.9361  max mem: 31830
Test: Total time: 0:00:09 (1.0813 s / it)
* Acc@1 77.180 Acc@5 93.690 loss 1.271
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.59%
Epoch: [254]  [  0/312]  eta: 1:02:19  lr: 0.000261  min_lr: 0.000261  loss: 3.7995 (3.7995)  weight_decay: 0.0500 (0.0500)  time: 11.9871  data: 11.0643  max mem: 31830
Epoch: [254]  [ 10/312]  eta: 0:08:23  lr: 0.000261  min_lr: 0.000261  loss: 3.5675 (3.3733)  weight_decay: 0.0500 (0.0500)  time: 1.6661  data: 1.0586  max mem: 31830
Epoch: [254]  [ 20/312]  eta: 0:05:28  lr: 0.000261  min_lr: 0.000261  loss: 3.3582 (3.2477)  weight_decay: 0.0500 (0.0500)  time: 0.5816  data: 0.0709  max mem: 31830
Epoch: [254]  [ 30/312]  eta: 0:04:11  lr: 0.000260  min_lr: 0.000260  loss: 3.3582 (3.2715)  weight_decay: 0.0500 (0.0500)  time: 0.4644  data: 0.0427  max mem: 31830
Epoch: [254]  [ 40/312]  eta: 0:03:29  lr: 0.000260  min_lr: 0.000260  loss: 3.3158 (3.2636)  weight_decay: 0.0500 (0.0500)  time: 0.3959  data: 0.0012  max mem: 31830
Epoch: [254]  [ 50/312]  eta: 0:03:08  lr: 0.000260  min_lr: 0.000260  loss: 3.2006 (3.2192)  weight_decay: 0.0500 (0.0500)  time: 0.4570  data: 0.0491  max mem: 31830
Epoch: [254]  [ 60/312]  eta: 0:02:48  lr: 0.000259  min_lr: 0.000259  loss: 3.2447 (3.2378)  weight_decay: 0.0500 (0.0500)  time: 0.4608  data: 0.0491  max mem: 31830
Epoch: [254]  [ 70/312]  eta: 0:02:39  lr: 0.000259  min_lr: 0.000259  loss: 3.3475 (3.2503)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0746  max mem: 31830
Epoch: [254]  [ 80/312]  eta: 0:02:30  lr: 0.000259  min_lr: 0.000259  loss: 3.3388 (3.2626)  weight_decay: 0.0500 (0.0500)  time: 0.5846  data: 0.1597  max mem: 31830
Epoch: [254]  [ 90/312]  eta: 0:02:17  lr: 0.000258  min_lr: 0.000258  loss: 3.3318 (3.2471)  weight_decay: 0.0500 (0.0500)  time: 0.4844  data: 0.0858  max mem: 31830
Epoch: [254]  [100/312]  eta: 0:02:11  lr: 0.000258  min_lr: 0.000258  loss: 3.3187 (3.2436)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.0871  max mem: 31830
Epoch: [254]  [110/312]  eta: 0:02:01  lr: 0.000258  min_lr: 0.000258  loss: 3.3994 (3.2558)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0879  max mem: 31830
Epoch: [254]  [120/312]  eta: 0:01:55  lr: 0.000257  min_lr: 0.000257  loss: 3.4816 (3.2766)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0645  max mem: 31830
Epoch: [254]  [130/312]  eta: 0:01:49  lr: 0.000257  min_lr: 0.000257  loss: 3.5453 (3.2869)  weight_decay: 0.0500 (0.0500)  time: 0.6155  data: 0.1373  max mem: 31830
Epoch: [254]  [140/312]  eta: 0:01:41  lr: 0.000257  min_lr: 0.000257  loss: 3.2086 (3.2623)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0743  max mem: 31830
Epoch: [254]  [150/312]  eta: 0:01:35  lr: 0.000256  min_lr: 0.000256  loss: 3.0950 (3.2590)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0701  max mem: 31830
Epoch: [254]  [160/312]  eta: 0:01:29  lr: 0.000256  min_lr: 0.000256  loss: 3.1075 (3.2394)  weight_decay: 0.0500 (0.0500)  time: 0.6204  data: 0.1493  max mem: 31830
Epoch: [254]  [170/312]  eta: 0:01:22  lr: 0.000255  min_lr: 0.000255  loss: 3.2264 (3.2512)  weight_decay: 0.0500 (0.0500)  time: 0.5285  data: 0.0800  max mem: 31830
Epoch: [254]  [180/312]  eta: 0:01:17  lr: 0.000255  min_lr: 0.000255  loss: 3.4976 (3.2589)  weight_decay: 0.0500 (0.0500)  time: 0.5219  data: 0.0729  max mem: 31830
Epoch: [254]  [190/312]  eta: 0:01:10  lr: 0.000255  min_lr: 0.000255  loss: 3.4169 (3.2591)  weight_decay: 0.0500 (0.0500)  time: 0.4982  data: 0.0729  max mem: 31830
Epoch: [254]  [200/312]  eta: 0:01:04  lr: 0.000254  min_lr: 0.000254  loss: 3.4849 (3.2680)  weight_decay: 0.0500 (0.0500)  time: 0.4793  data: 0.0858  max mem: 31830
Epoch: [254]  [210/312]  eta: 0:00:59  lr: 0.000254  min_lr: 0.000254  loss: 3.4730 (3.2768)  weight_decay: 0.0500 (0.0500)  time: 0.6305  data: 0.1884  max mem: 31830
Epoch: [254]  [220/312]  eta: 0:00:52  lr: 0.000254  min_lr: 0.000254  loss: 3.4730 (3.2739)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.1035  max mem: 31830
Epoch: [254]  [230/312]  eta: 0:00:46  lr: 0.000253  min_lr: 0.000253  loss: 3.3173 (3.2714)  weight_decay: 0.0500 (0.0500)  time: 0.4990  data: 0.0608  max mem: 31830
Epoch: [254]  [240/312]  eta: 0:00:41  lr: 0.000253  min_lr: 0.000253  loss: 3.4383 (3.2745)  weight_decay: 0.0500 (0.0500)  time: 0.6179  data: 0.1325  max mem: 31830
Epoch: [254]  [250/312]  eta: 0:00:35  lr: 0.000253  min_lr: 0.000253  loss: 3.4186 (3.2682)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0726  max mem: 31830
Epoch: [254]  [260/312]  eta: 0:00:29  lr: 0.000252  min_lr: 0.000252  loss: 3.2750 (3.2640)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0672  max mem: 31830
Epoch: [254]  [270/312]  eta: 0:00:23  lr: 0.000252  min_lr: 0.000252  loss: 3.4588 (3.2722)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0679  max mem: 31830
Epoch: [254]  [280/312]  eta: 0:00:18  lr: 0.000252  min_lr: 0.000252  loss: 3.3807 (3.2667)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0393  max mem: 31830
Epoch: [254]  [290/312]  eta: 0:00:12  lr: 0.000251  min_lr: 0.000251  loss: 3.1609 (3.2563)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0826  max mem: 31830
Epoch: [254]  [300/312]  eta: 0:00:06  lr: 0.000251  min_lr: 0.000251  loss: 3.0405 (3.2497)  weight_decay: 0.0500 (0.0500)  time: 0.4909  data: 0.0445  max mem: 31830
Epoch: [254]  [310/312]  eta: 0:00:01  lr: 0.000251  min_lr: 0.000251  loss: 3.0750 (3.2403)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [254]  [311/312]  eta: 0:00:00  lr: 0.000251  min_lr: 0.000251  loss: 3.0942 (3.2426)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [254] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.000251  min_lr: 0.000251  loss: 3.0942 (3.2313)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:24  loss: 0.9049 (0.9049)  acc1: 84.7656 (84.7656)  acc5: 96.7448 (96.7448)  time: 9.3879  data: 9.2208  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2283 (1.1310)  acc1: 77.6042 (77.5040)  acc5: 94.2708 (93.8080)  time: 1.1597  data: 1.0246  max mem: 31830
Test: Total time: 0:00:10 (1.1726 s / it)
* Acc@1 77.442 Acc@5 93.860 loss 1.129
Accuracy of the model on the 50000 test images: 77.4%
Max accuracy: 77.59%
Epoch: [255]  [  0/312]  eta: 1:02:26  lr: 0.000250  min_lr: 0.000250  loss: 3.9494 (3.9494)  weight_decay: 0.0500 (0.0500)  time: 12.0077  data: 8.9683  max mem: 31830
Epoch: [255]  [ 10/312]  eta: 0:08:18  lr: 0.000250  min_lr: 0.000250  loss: 3.5086 (3.4644)  weight_decay: 0.0500 (0.0500)  time: 1.6513  data: 1.0123  max mem: 31830
Epoch: [255]  [ 20/312]  eta: 0:05:25  lr: 0.000250  min_lr: 0.000250  loss: 3.3663 (3.3127)  weight_decay: 0.0500 (0.0500)  time: 0.5719  data: 0.1271  max mem: 31830
Epoch: [255]  [ 30/312]  eta: 0:04:11  lr: 0.000249  min_lr: 0.000249  loss: 3.2679 (3.2652)  weight_decay: 0.0500 (0.0500)  time: 0.4740  data: 0.0306  max mem: 31830
Epoch: [255]  [ 40/312]  eta: 0:03:29  lr: 0.000249  min_lr: 0.000249  loss: 3.1102 (3.2340)  weight_decay: 0.0500 (0.0500)  time: 0.4070  data: 0.0140  max mem: 31830
Epoch: [255]  [ 50/312]  eta: 0:03:07  lr: 0.000249  min_lr: 0.000249  loss: 3.1882 (3.2000)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0184  max mem: 31830
Epoch: [255]  [ 60/312]  eta: 0:02:46  lr: 0.000248  min_lr: 0.000248  loss: 3.3397 (3.2076)  weight_decay: 0.0500 (0.0500)  time: 0.4412  data: 0.0165  max mem: 31830
Epoch: [255]  [ 70/312]  eta: 0:02:38  lr: 0.000248  min_lr: 0.000248  loss: 3.3502 (3.2244)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.0753  max mem: 31830
Epoch: [255]  [ 80/312]  eta: 0:02:29  lr: 0.000248  min_lr: 0.000248  loss: 2.9690 (3.2018)  weight_decay: 0.0500 (0.0500)  time: 0.5868  data: 0.1205  max mem: 31830
Epoch: [255]  [ 90/312]  eta: 0:02:18  lr: 0.000247  min_lr: 0.000247  loss: 2.9297 (3.2107)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0743  max mem: 31830
Epoch: [255]  [100/312]  eta: 0:02:13  lr: 0.000247  min_lr: 0.000247  loss: 3.3698 (3.1956)  weight_decay: 0.0500 (0.0500)  time: 0.5666  data: 0.0795  max mem: 31830
Epoch: [255]  [110/312]  eta: 0:02:04  lr: 0.000247  min_lr: 0.000247  loss: 3.2534 (3.1831)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.0908  max mem: 31830
Epoch: [255]  [120/312]  eta: 0:01:58  lr: 0.000246  min_lr: 0.000246  loss: 3.1077 (3.1754)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0859  max mem: 31830
Epoch: [255]  [130/312]  eta: 0:01:49  lr: 0.000246  min_lr: 0.000246  loss: 3.2430 (3.1880)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0464  max mem: 31830
Epoch: [255]  [140/312]  eta: 0:01:42  lr: 0.000246  min_lr: 0.000246  loss: 3.2430 (3.1762)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0484  max mem: 31830
Epoch: [255]  [150/312]  eta: 0:01:37  lr: 0.000245  min_lr: 0.000245  loss: 3.0593 (3.1753)  weight_decay: 0.0500 (0.0500)  time: 0.5828  data: 0.1026  max mem: 31830
Epoch: [255]  [160/312]  eta: 0:01:30  lr: 0.000245  min_lr: 0.000245  loss: 3.2595 (3.1763)  weight_decay: 0.0500 (0.0500)  time: 0.5792  data: 0.0555  max mem: 31830
Epoch: [255]  [170/312]  eta: 0:01:23  lr: 0.000245  min_lr: 0.000245  loss: 3.0712 (3.1682)  weight_decay: 0.0500 (0.0500)  time: 0.4968  data: 0.0484  max mem: 31830
Epoch: [255]  [180/312]  eta: 0:01:17  lr: 0.000244  min_lr: 0.000244  loss: 3.2458 (3.1853)  weight_decay: 0.0500 (0.0500)  time: 0.5354  data: 0.0483  max mem: 31830
Epoch: [255]  [190/312]  eta: 0:01:10  lr: 0.000244  min_lr: 0.000244  loss: 3.2909 (3.1894)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.0414  max mem: 31830
Epoch: [255]  [200/312]  eta: 0:01:04  lr: 0.000244  min_lr: 0.000244  loss: 3.2909 (3.1918)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0797  max mem: 31830
Epoch: [255]  [210/312]  eta: 0:00:59  lr: 0.000243  min_lr: 0.000243  loss: 2.9041 (3.1754)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0396  max mem: 31830
Epoch: [255]  [220/312]  eta: 0:00:53  lr: 0.000243  min_lr: 0.000243  loss: 3.1155 (3.1746)  weight_decay: 0.0500 (0.0500)  time: 0.5431  data: 0.0451  max mem: 31830
Epoch: [255]  [230/312]  eta: 0:00:47  lr: 0.000243  min_lr: 0.000243  loss: 3.2066 (3.1711)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0617  max mem: 31830
Epoch: [255]  [240/312]  eta: 0:00:41  lr: 0.000242  min_lr: 0.000242  loss: 3.1759 (3.1726)  weight_decay: 0.0500 (0.0500)  time: 0.5304  data: 0.0178  max mem: 31830
Epoch: [255]  [250/312]  eta: 0:00:35  lr: 0.000242  min_lr: 0.000242  loss: 3.5509 (3.1943)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0505  max mem: 31830
Epoch: [255]  [260/312]  eta: 0:00:29  lr: 0.000242  min_lr: 0.000242  loss: 3.5597 (3.1937)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0508  max mem: 31830
Epoch: [255]  [270/312]  eta: 0:00:23  lr: 0.000241  min_lr: 0.000241  loss: 3.1325 (3.1902)  weight_decay: 0.0500 (0.0500)  time: 0.4483  data: 0.0348  max mem: 31830
Epoch: [255]  [280/312]  eta: 0:00:18  lr: 0.000241  min_lr: 0.000241  loss: 3.0612 (3.1844)  weight_decay: 0.0500 (0.0500)  time: 0.5948  data: 0.1091  max mem: 31830
Epoch: [255]  [290/312]  eta: 0:00:12  lr: 0.000240  min_lr: 0.000240  loss: 3.2053 (3.1895)  weight_decay: 0.0500 (0.0500)  time: 0.5871  data: 0.0752  max mem: 31830
Epoch: [255]  [300/312]  eta: 0:00:06  lr: 0.000240  min_lr: 0.000240  loss: 3.3329 (3.1930)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0221  max mem: 31830
Epoch: [255]  [310/312]  eta: 0:00:01  lr: 0.000240  min_lr: 0.000240  loss: 3.3128 (3.1888)  weight_decay: 0.0500 (0.0500)  time: 0.4021  data: 0.0220  max mem: 31830
Epoch: [255]  [311/312]  eta: 0:00:00  lr: 0.000240  min_lr: 0.000240  loss: 3.3128 (3.1897)  weight_decay: 0.0500 (0.0500)  time: 0.4020  data: 0.0220  max mem: 31830
Epoch: [255] Total time: 0:02:54 (0.5593 s / it)
Averaged stats: lr: 0.000240  min_lr: 0.000240  loss: 3.3128 (3.2142)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8432 (0.8432)  acc1: 84.6354 (84.6354)  acc5: 96.4844 (96.4844)  time: 8.9317  data: 8.7688  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1382 (1.0717)  acc1: 77.6042 (77.6480)  acc5: 94.0104 (94.1280)  time: 1.1096  data: 0.9744  max mem: 31830
Test: Total time: 0:00:10 (1.1200 s / it)
* Acc@1 77.560 Acc@5 94.084 loss 1.072
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.59%
Epoch: [256]  [  0/312]  eta: 1:00:04  lr: 0.000240  min_lr: 0.000240  loss: 3.3026 (3.3026)  weight_decay: 0.0500 (0.0500)  time: 11.5534  data: 10.6758  max mem: 31830
Epoch: [256]  [ 10/312]  eta: 0:08:28  lr: 0.000239  min_lr: 0.000239  loss: 3.2456 (3.1763)  weight_decay: 0.0500 (0.0500)  time: 1.6821  data: 0.9939  max mem: 31830
Epoch: [256]  [ 20/312]  eta: 0:05:33  lr: 0.000239  min_lr: 0.000239  loss: 3.2268 (3.1694)  weight_decay: 0.0500 (0.0500)  time: 0.6223  data: 0.0436  max mem: 31830
Epoch: [256]  [ 30/312]  eta: 0:04:14  lr: 0.000239  min_lr: 0.000239  loss: 3.2028 (3.1932)  weight_decay: 0.0500 (0.0500)  time: 0.4745  data: 0.0313  max mem: 31830
Epoch: [256]  [ 40/312]  eta: 0:03:31  lr: 0.000238  min_lr: 0.000238  loss: 3.1506 (3.1522)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0010  max mem: 31830
Epoch: [256]  [ 50/312]  eta: 0:03:04  lr: 0.000238  min_lr: 0.000238  loss: 3.1498 (3.1630)  weight_decay: 0.0500 (0.0500)  time: 0.3974  data: 0.0009  max mem: 31830
Epoch: [256]  [ 60/312]  eta: 0:02:44  lr: 0.000238  min_lr: 0.000238  loss: 3.4359 (3.1910)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0009  max mem: 31830
Epoch: [256]  [ 70/312]  eta: 0:02:33  lr: 0.000237  min_lr: 0.000237  loss: 3.4261 (3.2006)  weight_decay: 0.0500 (0.0500)  time: 0.4552  data: 0.0499  max mem: 31830
Epoch: [256]  [ 80/312]  eta: 0:02:26  lr: 0.000237  min_lr: 0.000237  loss: 3.4422 (3.2281)  weight_decay: 0.0500 (0.0500)  time: 0.5688  data: 0.1624  max mem: 31830
Epoch: [256]  [ 90/312]  eta: 0:02:14  lr: 0.000237  min_lr: 0.000237  loss: 3.4180 (3.2244)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.1134  max mem: 31830
Epoch: [256]  [100/312]  eta: 0:02:09  lr: 0.000236  min_lr: 0.000236  loss: 3.4407 (3.2463)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.1125  max mem: 31830
Epoch: [256]  [110/312]  eta: 0:01:59  lr: 0.000236  min_lr: 0.000236  loss: 3.4760 (3.2539)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.1178  max mem: 31830
Epoch: [256]  [120/312]  eta: 0:01:53  lr: 0.000236  min_lr: 0.000236  loss: 3.3877 (3.2431)  weight_decay: 0.0500 (0.0500)  time: 0.4881  data: 0.0899  max mem: 31830
Epoch: [256]  [130/312]  eta: 0:01:48  lr: 0.000235  min_lr: 0.000235  loss: 3.3877 (3.2464)  weight_decay: 0.0500 (0.0500)  time: 0.6081  data: 0.1861  max mem: 31830
Epoch: [256]  [140/312]  eta: 0:01:39  lr: 0.000235  min_lr: 0.000235  loss: 3.3424 (3.2440)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.1024  max mem: 31830
Epoch: [256]  [150/312]  eta: 0:01:34  lr: 0.000235  min_lr: 0.000235  loss: 3.3626 (3.2547)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.1223  max mem: 31830
Epoch: [256]  [160/312]  eta: 0:01:29  lr: 0.000234  min_lr: 0.000234  loss: 3.2765 (3.2386)  weight_decay: 0.0500 (0.0500)  time: 0.6425  data: 0.2523  max mem: 31830
Epoch: [256]  [170/312]  eta: 0:01:22  lr: 0.000234  min_lr: 0.000234  loss: 2.9283 (3.2303)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.1308  max mem: 31830
Epoch: [256]  [180/312]  eta: 0:01:16  lr: 0.000234  min_lr: 0.000234  loss: 3.3684 (3.2337)  weight_decay: 0.0500 (0.0500)  time: 0.5088  data: 0.1190  max mem: 31830
Epoch: [256]  [190/312]  eta: 0:01:10  lr: 0.000233  min_lr: 0.000233  loss: 3.2285 (3.2201)  weight_decay: 0.0500 (0.0500)  time: 0.5853  data: 0.1953  max mem: 31830
Epoch: [256]  [200/312]  eta: 0:01:04  lr: 0.000233  min_lr: 0.000233  loss: 3.3100 (3.2194)  weight_decay: 0.0500 (0.0500)  time: 0.5131  data: 0.1190  max mem: 31830
Epoch: [256]  [210/312]  eta: 0:00:58  lr: 0.000233  min_lr: 0.000233  loss: 3.2649 (3.2174)  weight_decay: 0.0500 (0.0500)  time: 0.5525  data: 0.1416  max mem: 31830
Epoch: [256]  [220/312]  eta: 0:00:52  lr: 0.000232  min_lr: 0.000232  loss: 3.3521 (3.2264)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.1005  max mem: 31830
Epoch: [256]  [230/312]  eta: 0:00:46  lr: 0.000232  min_lr: 0.000232  loss: 3.2579 (3.2052)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0959  max mem: 31830
Epoch: [256]  [240/312]  eta: 0:00:41  lr: 0.000232  min_lr: 0.000232  loss: 2.9985 (3.2164)  weight_decay: 0.0500 (0.0500)  time: 0.6104  data: 0.1942  max mem: 31830
Epoch: [256]  [250/312]  eta: 0:00:35  lr: 0.000231  min_lr: 0.000231  loss: 3.3076 (3.2165)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.1001  max mem: 31830
Epoch: [256]  [260/312]  eta: 0:00:29  lr: 0.000231  min_lr: 0.000231  loss: 3.2970 (3.2204)  weight_decay: 0.0500 (0.0500)  time: 0.5364  data: 0.0940  max mem: 31830
Epoch: [256]  [270/312]  eta: 0:00:23  lr: 0.000231  min_lr: 0.000231  loss: 3.3784 (3.2175)  weight_decay: 0.0500 (0.0500)  time: 0.6287  data: 0.2177  max mem: 31830
Epoch: [256]  [280/312]  eta: 0:00:18  lr: 0.000230  min_lr: 0.000230  loss: 3.1996 (3.2125)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.1264  max mem: 31830
Epoch: [256]  [290/312]  eta: 0:00:12  lr: 0.000230  min_lr: 0.000230  loss: 3.3083 (3.2196)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.1356  max mem: 31830
Epoch: [256]  [300/312]  eta: 0:00:06  lr: 0.000230  min_lr: 0.000230  loss: 3.3083 (3.2108)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1338  max mem: 31830
Epoch: [256]  [310/312]  eta: 0:00:01  lr: 0.000229  min_lr: 0.000229  loss: 2.7903 (3.1978)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0002  max mem: 31830
Epoch: [256]  [311/312]  eta: 0:00:00  lr: 0.000229  min_lr: 0.000229  loss: 2.8609 (3.1993)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [256] Total time: 0:02:54 (0.5595 s / it)
Averaged stats: lr: 0.000229  min_lr: 0.000229  loss: 2.8609 (3.2353)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.8587 (0.8587)  acc1: 84.1146 (84.1146)  acc5: 96.8750 (96.8750)  time: 8.7809  data: 8.6136  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1814 (1.0857)  acc1: 79.4271 (77.5520)  acc5: 94.0104 (93.9520)  time: 1.0923  data: 0.9572  max mem: 31830
Test: Total time: 0:00:09 (1.1044 s / it)
* Acc@1 77.550 Acc@5 94.004 loss 1.085
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.59%
Epoch: [257]  [  0/312]  eta: 1:00:46  lr: 0.000229  min_lr: 0.000229  loss: 3.5752 (3.5752)  weight_decay: 0.0500 (0.0500)  time: 11.6882  data: 8.5622  max mem: 31830
Epoch: [257]  [ 10/312]  eta: 0:08:29  lr: 0.000229  min_lr: 0.000229  loss: 3.0432 (3.1726)  weight_decay: 0.0500 (0.0500)  time: 1.6869  data: 0.9981  max mem: 31830
Epoch: [257]  [ 20/312]  eta: 0:05:26  lr: 0.000229  min_lr: 0.000229  loss: 3.0432 (3.2252)  weight_decay: 0.0500 (0.0500)  time: 0.5907  data: 0.1722  max mem: 31830
Epoch: [257]  [ 30/312]  eta: 0:04:10  lr: 0.000228  min_lr: 0.000228  loss: 3.3743 (3.2334)  weight_decay: 0.0500 (0.0500)  time: 0.4467  data: 0.0517  max mem: 31830
Epoch: [257]  [ 40/312]  eta: 0:03:28  lr: 0.000228  min_lr: 0.000228  loss: 3.4074 (3.2430)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [257]  [ 50/312]  eta: 0:03:01  lr: 0.000228  min_lr: 0.000228  loss: 3.4522 (3.2527)  weight_decay: 0.0500 (0.0500)  time: 0.3963  data: 0.0010  max mem: 31830
Epoch: [257]  [ 60/312]  eta: 0:02:42  lr: 0.000227  min_lr: 0.000227  loss: 3.4971 (3.2465)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0023  max mem: 31830
Epoch: [257]  [ 70/312]  eta: 0:02:33  lr: 0.000227  min_lr: 0.000227  loss: 3.4774 (3.2646)  weight_decay: 0.0500 (0.0500)  time: 0.4786  data: 0.0868  max mem: 31830
Epoch: [257]  [ 80/312]  eta: 0:02:27  lr: 0.000227  min_lr: 0.000227  loss: 3.3795 (3.2771)  weight_decay: 0.0500 (0.0500)  time: 0.6122  data: 0.2026  max mem: 31830
Epoch: [257]  [ 90/312]  eta: 0:02:15  lr: 0.000226  min_lr: 0.000226  loss: 3.1184 (3.2624)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.1181  max mem: 31830
Epoch: [257]  [100/312]  eta: 0:02:09  lr: 0.000226  min_lr: 0.000226  loss: 3.2609 (3.2574)  weight_decay: 0.0500 (0.0500)  time: 0.4964  data: 0.0895  max mem: 31830
Epoch: [257]  [110/312]  eta: 0:01:59  lr: 0.000226  min_lr: 0.000226  loss: 3.3046 (3.2477)  weight_decay: 0.0500 (0.0500)  time: 0.4977  data: 0.0896  max mem: 31830
Epoch: [257]  [120/312]  eta: 0:01:53  lr: 0.000225  min_lr: 0.000225  loss: 3.4138 (3.2654)  weight_decay: 0.0500 (0.0500)  time: 0.4892  data: 0.0932  max mem: 31830
Epoch: [257]  [130/312]  eta: 0:01:47  lr: 0.000225  min_lr: 0.000225  loss: 3.4500 (3.2532)  weight_decay: 0.0500 (0.0500)  time: 0.6078  data: 0.1813  max mem: 31830
Epoch: [257]  [140/312]  eta: 0:01:39  lr: 0.000225  min_lr: 0.000225  loss: 3.3237 (3.2583)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0891  max mem: 31830
Epoch: [257]  [150/312]  eta: 0:01:34  lr: 0.000224  min_lr: 0.000224  loss: 3.4290 (3.2761)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0498  max mem: 31830
Epoch: [257]  [160/312]  eta: 0:01:28  lr: 0.000224  min_lr: 0.000224  loss: 3.4768 (3.2726)  weight_decay: 0.0500 (0.0500)  time: 0.5849  data: 0.0778  max mem: 31830
Epoch: [257]  [170/312]  eta: 0:01:21  lr: 0.000224  min_lr: 0.000224  loss: 3.3492 (3.2586)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0882  max mem: 31830
Epoch: [257]  [180/312]  eta: 0:01:16  lr: 0.000223  min_lr: 0.000223  loss: 3.0985 (3.2446)  weight_decay: 0.0500 (0.0500)  time: 0.5904  data: 0.1391  max mem: 31830
Epoch: [257]  [190/312]  eta: 0:01:09  lr: 0.000223  min_lr: 0.000223  loss: 3.0141 (3.2403)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0800  max mem: 31830
Epoch: [257]  [200/312]  eta: 0:01:04  lr: 0.000223  min_lr: 0.000223  loss: 2.9423 (3.2378)  weight_decay: 0.0500 (0.0500)  time: 0.4968  data: 0.0371  max mem: 31830
Epoch: [257]  [210/312]  eta: 0:00:58  lr: 0.000222  min_lr: 0.000222  loss: 3.3777 (3.2517)  weight_decay: 0.0500 (0.0500)  time: 0.5873  data: 0.1021  max mem: 31830
Epoch: [257]  [220/312]  eta: 0:00:51  lr: 0.000222  min_lr: 0.000222  loss: 3.3777 (3.2436)  weight_decay: 0.0500 (0.0500)  time: 0.4857  data: 0.0658  max mem: 31830
Epoch: [257]  [230/312]  eta: 0:00:46  lr: 0.000222  min_lr: 0.000222  loss: 3.2690 (3.2467)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0908  max mem: 31830
Epoch: [257]  [240/312]  eta: 0:00:40  lr: 0.000221  min_lr: 0.000221  loss: 3.3401 (3.2422)  weight_decay: 0.0500 (0.0500)  time: 0.6037  data: 0.1563  max mem: 31830
Epoch: [257]  [250/312]  eta: 0:00:34  lr: 0.000221  min_lr: 0.000221  loss: 3.2458 (3.2392)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0665  max mem: 31830
Epoch: [257]  [260/312]  eta: 0:00:29  lr: 0.000221  min_lr: 0.000221  loss: 3.3109 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0661  max mem: 31830
Epoch: [257]  [270/312]  eta: 0:00:23  lr: 0.000220  min_lr: 0.000220  loss: 3.2934 (3.2309)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.0669  max mem: 31830
Epoch: [257]  [280/312]  eta: 0:00:17  lr: 0.000220  min_lr: 0.000220  loss: 3.1904 (3.2277)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0767  max mem: 31830
Epoch: [257]  [290/312]  eta: 0:00:12  lr: 0.000220  min_lr: 0.000220  loss: 3.1710 (3.2287)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.1285  max mem: 31830
Epoch: [257]  [300/312]  eta: 0:00:06  lr: 0.000219  min_lr: 0.000219  loss: 3.0658 (3.2193)  weight_decay: 0.0500 (0.0500)  time: 0.5065  data: 0.0533  max mem: 31830
Epoch: [257]  [310/312]  eta: 0:00:01  lr: 0.000219  min_lr: 0.000219  loss: 3.1882 (3.2178)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [257]  [311/312]  eta: 0:00:00  lr: 0.000219  min_lr: 0.000219  loss: 3.2662 (3.2184)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [257] Total time: 0:02:53 (0.5548 s / it)
Averaged stats: lr: 0.000219  min_lr: 0.000219  loss: 3.2662 (3.2181)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8827 (0.8827)  acc1: 83.3333 (83.3333)  acc5: 96.0938 (96.0938)  time: 8.2410  data: 8.0728  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1854 (1.1008)  acc1: 79.8177 (77.6160)  acc5: 94.0104 (93.8240)  time: 1.0419  data: 0.9065  max mem: 31830
Test: Total time: 0:00:09 (1.0731 s / it)
* Acc@1 77.544 Acc@5 93.938 loss 1.099
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.59%
Epoch: [258]  [  0/312]  eta: 1:05:31  lr: 0.000219  min_lr: 0.000219  loss: 3.5803 (3.5803)  weight_decay: 0.0500 (0.0500)  time: 12.6001  data: 9.6715  max mem: 31830
Epoch: [258]  [ 10/312]  eta: 0:08:36  lr: 0.000219  min_lr: 0.000219  loss: 3.3817 (3.1569)  weight_decay: 0.0500 (0.0500)  time: 1.7102  data: 1.0695  max mem: 31830
Epoch: [258]  [ 20/312]  eta: 0:05:23  lr: 0.000218  min_lr: 0.000218  loss: 3.4937 (3.2906)  weight_decay: 0.0500 (0.0500)  time: 0.5329  data: 0.1115  max mem: 31830
Epoch: [258]  [ 30/312]  eta: 0:04:07  lr: 0.000218  min_lr: 0.000218  loss: 3.4937 (3.2900)  weight_decay: 0.0500 (0.0500)  time: 0.4215  data: 0.0078  max mem: 31830
Epoch: [258]  [ 40/312]  eta: 0:03:27  lr: 0.000218  min_lr: 0.000218  loss: 3.3019 (3.2795)  weight_decay: 0.0500 (0.0500)  time: 0.3979  data: 0.0013  max mem: 31830
Epoch: [258]  [ 50/312]  eta: 0:03:01  lr: 0.000217  min_lr: 0.000217  loss: 3.1441 (3.2190)  weight_decay: 0.0500 (0.0500)  time: 0.4056  data: 0.0010  max mem: 31830
Epoch: [258]  [ 60/312]  eta: 0:02:42  lr: 0.000217  min_lr: 0.000217  loss: 2.9768 (3.2142)  weight_decay: 0.0500 (0.0500)  time: 0.4056  data: 0.0015  max mem: 31830
Epoch: [258]  [ 70/312]  eta: 0:02:35  lr: 0.000217  min_lr: 0.000217  loss: 3.4878 (3.2392)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0874  max mem: 31830
Epoch: [258]  [ 80/312]  eta: 0:02:25  lr: 0.000216  min_lr: 0.000216  loss: 3.4459 (3.2275)  weight_decay: 0.0500 (0.0500)  time: 0.5793  data: 0.1280  max mem: 31830
Epoch: [258]  [ 90/312]  eta: 0:02:14  lr: 0.000216  min_lr: 0.000216  loss: 3.4271 (3.2441)  weight_decay: 0.0500 (0.0500)  time: 0.4787  data: 0.0595  max mem: 31830
Epoch: [258]  [100/312]  eta: 0:02:08  lr: 0.000216  min_lr: 0.000216  loss: 3.4660 (3.2349)  weight_decay: 0.0500 (0.0500)  time: 0.5038  data: 0.0833  max mem: 31830
Epoch: [258]  [110/312]  eta: 0:01:58  lr: 0.000215  min_lr: 0.000215  loss: 3.2872 (3.2347)  weight_decay: 0.0500 (0.0500)  time: 0.4852  data: 0.0665  max mem: 31830
Epoch: [258]  [120/312]  eta: 0:01:54  lr: 0.000215  min_lr: 0.000215  loss: 3.2872 (3.2463)  weight_decay: 0.0500 (0.0500)  time: 0.5729  data: 0.1227  max mem: 31830
Epoch: [258]  [130/312]  eta: 0:01:47  lr: 0.000215  min_lr: 0.000215  loss: 3.2778 (3.2372)  weight_decay: 0.0500 (0.0500)  time: 0.6392  data: 0.1402  max mem: 31830
Epoch: [258]  [140/312]  eta: 0:01:40  lr: 0.000214  min_lr: 0.000214  loss: 3.2778 (3.2252)  weight_decay: 0.0500 (0.0500)  time: 0.5057  data: 0.0647  max mem: 31830
Epoch: [258]  [150/312]  eta: 0:01:34  lr: 0.000214  min_lr: 0.000214  loss: 3.3162 (3.2309)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0845  max mem: 31830
Epoch: [258]  [160/312]  eta: 0:01:28  lr: 0.000214  min_lr: 0.000214  loss: 3.5531 (3.2497)  weight_decay: 0.0500 (0.0500)  time: 0.5397  data: 0.0685  max mem: 31830
Epoch: [258]  [170/312]  eta: 0:01:22  lr: 0.000213  min_lr: 0.000213  loss: 3.4990 (3.2366)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.0835  max mem: 31830
Epoch: [258]  [180/312]  eta: 0:01:16  lr: 0.000213  min_lr: 0.000213  loss: 2.9667 (3.2337)  weight_decay: 0.0500 (0.0500)  time: 0.5792  data: 0.1064  max mem: 31830
Epoch: [258]  [190/312]  eta: 0:01:09  lr: 0.000213  min_lr: 0.000213  loss: 3.2766 (3.2335)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0796  max mem: 31830
Epoch: [258]  [200/312]  eta: 0:01:04  lr: 0.000212  min_lr: 0.000212  loss: 3.3157 (3.2351)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.1005  max mem: 31830
Epoch: [258]  [210/312]  eta: 0:00:58  lr: 0.000212  min_lr: 0.000212  loss: 3.0466 (3.2226)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.0742  max mem: 31830
Epoch: [258]  [220/312]  eta: 0:00:52  lr: 0.000212  min_lr: 0.000212  loss: 2.9661 (3.2159)  weight_decay: 0.0500 (0.0500)  time: 0.5146  data: 0.0623  max mem: 31830
Epoch: [258]  [230/312]  eta: 0:00:46  lr: 0.000211  min_lr: 0.000211  loss: 3.2074 (3.2153)  weight_decay: 0.0500 (0.0500)  time: 0.5691  data: 0.1195  max mem: 31830
Epoch: [258]  [240/312]  eta: 0:00:40  lr: 0.000211  min_lr: 0.000211  loss: 3.2074 (3.2119)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0582  max mem: 31830
Epoch: [258]  [250/312]  eta: 0:00:35  lr: 0.000211  min_lr: 0.000211  loss: 3.3239 (3.2200)  weight_decay: 0.0500 (0.0500)  time: 0.5495  data: 0.0891  max mem: 31830
Epoch: [258]  [260/312]  eta: 0:00:29  lr: 0.000211  min_lr: 0.000211  loss: 3.4371 (3.2170)  weight_decay: 0.0500 (0.0500)  time: 0.6264  data: 0.1643  max mem: 31830
Epoch: [258]  [270/312]  eta: 0:00:23  lr: 0.000210  min_lr: 0.000210  loss: 3.1261 (3.2077)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0760  max mem: 31830
Epoch: [258]  [280/312]  eta: 0:00:18  lr: 0.000210  min_lr: 0.000210  loss: 3.0184 (3.2045)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.0894  max mem: 31830
Epoch: [258]  [290/312]  eta: 0:00:12  lr: 0.000210  min_lr: 0.000210  loss: 3.2421 (3.2027)  weight_decay: 0.0500 (0.0500)  time: 0.5435  data: 0.0891  max mem: 31830
Epoch: [258]  [300/312]  eta: 0:00:06  lr: 0.000209  min_lr: 0.000209  loss: 3.2968 (3.2039)  weight_decay: 0.0500 (0.0500)  time: 0.4641  data: 0.0555  max mem: 31830
Epoch: [258]  [310/312]  eta: 0:00:01  lr: 0.000209  min_lr: 0.000209  loss: 3.2968 (3.2046)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0555  max mem: 31830
Epoch: [258]  [311/312]  eta: 0:00:00  lr: 0.000209  min_lr: 0.000209  loss: 3.3043 (3.2054)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0554  max mem: 31830
Epoch: [258] Total time: 0:02:54 (0.5586 s / it)
Averaged stats: lr: 0.000209  min_lr: 0.000209  loss: 3.3043 (3.2307)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8940 (0.8940)  acc1: 84.6354 (84.6354)  acc5: 96.4844 (96.4844)  time: 8.9965  data: 8.8293  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2133 (1.1306)  acc1: 79.4271 (78.0960)  acc5: 94.5312 (93.8080)  time: 1.1175  data: 0.9811  max mem: 31830
Test: Total time: 0:00:10 (1.1415 s / it)
* Acc@1 77.958 Acc@5 93.958 loss 1.127
Accuracy of the model on the 50000 test images: 78.0%
Max accuracy: 77.96%
Epoch: [259]  [  0/312]  eta: 0:58:52  lr: 0.000209  min_lr: 0.000209  loss: 3.5904 (3.5904)  weight_decay: 0.0500 (0.0500)  time: 11.3216  data: 9.6335  max mem: 31830
Epoch: [259]  [ 10/312]  eta: 0:07:59  lr: 0.000209  min_lr: 0.000209  loss: 3.3055 (3.2783)  weight_decay: 0.0500 (0.0500)  time: 1.5878  data: 0.9245  max mem: 31830
Epoch: [259]  [ 20/312]  eta: 0:05:36  lr: 0.000208  min_lr: 0.000208  loss: 3.3055 (3.3137)  weight_decay: 0.0500 (0.0500)  time: 0.6446  data: 0.0622  max mem: 31830
Epoch: [259]  [ 30/312]  eta: 0:04:15  lr: 0.000208  min_lr: 0.000208  loss: 3.2360 (3.2930)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0358  max mem: 31830
Epoch: [259]  [ 40/312]  eta: 0:03:33  lr: 0.000208  min_lr: 0.000208  loss: 3.2437 (3.2918)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0012  max mem: 31830
Epoch: [259]  [ 50/312]  eta: 0:03:05  lr: 0.000207  min_lr: 0.000207  loss: 3.3746 (3.2791)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0012  max mem: 31830
Epoch: [259]  [ 60/312]  eta: 0:02:45  lr: 0.000207  min_lr: 0.000207  loss: 3.4217 (3.2972)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0015  max mem: 31830
Epoch: [259]  [ 70/312]  eta: 0:02:37  lr: 0.000207  min_lr: 0.000207  loss: 3.3046 (3.2502)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0017  max mem: 31830
Epoch: [259]  [ 80/312]  eta: 0:02:28  lr: 0.000206  min_lr: 0.000206  loss: 3.3697 (3.2883)  weight_decay: 0.0500 (0.0500)  time: 0.5853  data: 0.0012  max mem: 31830
Epoch: [259]  [ 90/312]  eta: 0:02:18  lr: 0.000206  min_lr: 0.000206  loss: 3.3820 (3.2845)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0019  max mem: 31830
Epoch: [259]  [100/312]  eta: 0:02:11  lr: 0.000206  min_lr: 0.000206  loss: 3.3475 (3.2961)  weight_decay: 0.0500 (0.0500)  time: 0.5380  data: 0.0017  max mem: 31830
Epoch: [259]  [110/312]  eta: 0:02:01  lr: 0.000205  min_lr: 0.000205  loss: 3.5457 (3.3065)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0008  max mem: 31830
Epoch: [259]  [120/312]  eta: 0:01:54  lr: 0.000205  min_lr: 0.000205  loss: 3.4170 (3.3052)  weight_decay: 0.0500 (0.0500)  time: 0.4975  data: 0.0010  max mem: 31830
Epoch: [259]  [130/312]  eta: 0:01:48  lr: 0.000205  min_lr: 0.000205  loss: 3.3885 (3.2995)  weight_decay: 0.0500 (0.0500)  time: 0.5906  data: 0.0014  max mem: 31830
Epoch: [259]  [140/312]  eta: 0:01:40  lr: 0.000204  min_lr: 0.000204  loss: 3.3848 (3.3026)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0012  max mem: 31830
Epoch: [259]  [150/312]  eta: 0:01:35  lr: 0.000204  min_lr: 0.000204  loss: 3.5114 (3.3146)  weight_decay: 0.0500 (0.0500)  time: 0.5152  data: 0.0009  max mem: 31830
Epoch: [259]  [160/312]  eta: 0:01:28  lr: 0.000204  min_lr: 0.000204  loss: 3.5215 (3.3177)  weight_decay: 0.0500 (0.0500)  time: 0.5673  data: 0.0010  max mem: 31830
Epoch: [259]  [170/312]  eta: 0:01:22  lr: 0.000203  min_lr: 0.000203  loss: 3.4684 (3.3182)  weight_decay: 0.0500 (0.0500)  time: 0.5228  data: 0.0065  max mem: 31830
Epoch: [259]  [180/312]  eta: 0:01:16  lr: 0.000203  min_lr: 0.000203  loss: 3.3694 (3.3140)  weight_decay: 0.0500 (0.0500)  time: 0.5693  data: 0.0208  max mem: 31830
Epoch: [259]  [190/312]  eta: 0:01:09  lr: 0.000203  min_lr: 0.000203  loss: 3.4239 (3.3180)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0158  max mem: 31830
Epoch: [259]  [200/312]  eta: 0:01:04  lr: 0.000203  min_lr: 0.000203  loss: 3.4976 (3.3186)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0025  max mem: 31830
Epoch: [259]  [210/312]  eta: 0:00:59  lr: 0.000202  min_lr: 0.000202  loss: 3.3845 (3.3228)  weight_decay: 0.0500 (0.0500)  time: 0.6632  data: 0.0020  max mem: 31830
Epoch: [259]  [220/312]  eta: 0:00:52  lr: 0.000202  min_lr: 0.000202  loss: 3.1618 (3.3035)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0010  max mem: 31830
Epoch: [259]  [230/312]  eta: 0:00:47  lr: 0.000202  min_lr: 0.000202  loss: 3.1618 (3.3053)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0073  max mem: 31830
Epoch: [259]  [240/312]  eta: 0:00:41  lr: 0.000201  min_lr: 0.000201  loss: 3.4043 (3.3001)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0141  max mem: 31830
Epoch: [259]  [250/312]  eta: 0:00:35  lr: 0.000201  min_lr: 0.000201  loss: 3.0478 (3.2865)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0275  max mem: 31830
Epoch: [259]  [260/312]  eta: 0:00:29  lr: 0.000201  min_lr: 0.000201  loss: 3.1868 (3.2859)  weight_decay: 0.0500 (0.0500)  time: 0.6198  data: 0.0213  max mem: 31830
Epoch: [259]  [270/312]  eta: 0:00:24  lr: 0.000200  min_lr: 0.000200  loss: 3.4293 (3.2920)  weight_decay: 0.0500 (0.0500)  time: 0.5806  data: 0.0530  max mem: 31830
Epoch: [259]  [280/312]  eta: 0:00:18  lr: 0.000200  min_lr: 0.000200  loss: 3.3347 (3.2804)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0578  max mem: 31830
Epoch: [259]  [290/312]  eta: 0:00:12  lr: 0.000200  min_lr: 0.000200  loss: 3.2456 (3.2785)  weight_decay: 0.0500 (0.0500)  time: 0.5507  data: 0.0133  max mem: 31830
Epoch: [259]  [300/312]  eta: 0:00:06  lr: 0.000199  min_lr: 0.000199  loss: 3.2921 (3.2735)  weight_decay: 0.0500 (0.0500)  time: 0.4665  data: 0.0076  max mem: 31830
Epoch: [259]  [310/312]  eta: 0:00:01  lr: 0.000199  min_lr: 0.000199  loss: 3.2283 (3.2676)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [259]  [311/312]  eta: 0:00:00  lr: 0.000199  min_lr: 0.000199  loss: 3.2046 (3.2632)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [259] Total time: 0:02:55 (0.5611 s / it)
Averaged stats: lr: 0.000199  min_lr: 0.000199  loss: 3.2046 (3.2322)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8971 (0.8971)  acc1: 84.6354 (84.6354)  acc5: 97.0052 (97.0052)  time: 8.7620  data: 8.5950  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1643 (1.0922)  acc1: 78.6458 (77.9840)  acc5: 93.8802 (94.0960)  time: 1.0897  data: 0.9551  max mem: 31830
Test: Total time: 0:00:09 (1.1013 s / it)
* Acc@1 78.016 Acc@5 94.144 loss 1.091
Accuracy of the model on the 50000 test images: 78.0%
Max accuracy: 78.02%
Epoch: [260]  [  0/312]  eta: 1:01:15  lr: 0.000199  min_lr: 0.000199  loss: 3.4528 (3.4528)  weight_decay: 0.0500 (0.0500)  time: 11.7809  data: 8.6694  max mem: 31830
Epoch: [260]  [ 10/312]  eta: 0:08:23  lr: 0.000199  min_lr: 0.000199  loss: 3.4192 (3.2518)  weight_decay: 0.0500 (0.0500)  time: 1.6668  data: 1.0305  max mem: 31830
Epoch: [260]  [ 20/312]  eta: 0:05:24  lr: 0.000198  min_lr: 0.000198  loss: 3.3922 (3.2588)  weight_decay: 0.0500 (0.0500)  time: 0.5765  data: 0.1600  max mem: 31830
Epoch: [260]  [ 30/312]  eta: 0:04:08  lr: 0.000198  min_lr: 0.000198  loss: 3.4138 (3.2692)  weight_decay: 0.0500 (0.0500)  time: 0.4487  data: 0.0271  max mem: 31830
Epoch: [260]  [ 40/312]  eta: 0:03:27  lr: 0.000198  min_lr: 0.000198  loss: 3.3299 (3.2768)  weight_decay: 0.0500 (0.0500)  time: 0.3985  data: 0.0009  max mem: 31830
Epoch: [260]  [ 50/312]  eta: 0:03:08  lr: 0.000197  min_lr: 0.000197  loss: 3.3212 (3.2441)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0752  max mem: 31830
Epoch: [260]  [ 60/312]  eta: 0:02:48  lr: 0.000197  min_lr: 0.000197  loss: 3.2944 (3.2549)  weight_decay: 0.0500 (0.0500)  time: 0.4713  data: 0.0750  max mem: 31830
Epoch: [260]  [ 70/312]  eta: 0:02:39  lr: 0.000197  min_lr: 0.000197  loss: 3.3238 (3.2670)  weight_decay: 0.0500 (0.0500)  time: 0.5094  data: 0.1106  max mem: 31830
Epoch: [260]  [ 80/312]  eta: 0:02:32  lr: 0.000197  min_lr: 0.000197  loss: 3.1369 (3.2192)  weight_decay: 0.0500 (0.0500)  time: 0.6323  data: 0.2370  max mem: 31830
Epoch: [260]  [ 90/312]  eta: 0:02:19  lr: 0.000196  min_lr: 0.000196  loss: 3.0548 (3.2161)  weight_decay: 0.0500 (0.0500)  time: 0.5203  data: 0.1271  max mem: 31830
Epoch: [260]  [100/312]  eta: 0:02:13  lr: 0.000196  min_lr: 0.000196  loss: 3.1816 (3.1955)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.1169  max mem: 31830
Epoch: [260]  [110/312]  eta: 0:02:02  lr: 0.000196  min_lr: 0.000196  loss: 3.0993 (3.1843)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.1170  max mem: 31830
Epoch: [260]  [120/312]  eta: 0:01:57  lr: 0.000195  min_lr: 0.000195  loss: 3.1870 (3.1994)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.1147  max mem: 31830
Epoch: [260]  [130/312]  eta: 0:01:51  lr: 0.000195  min_lr: 0.000195  loss: 3.2688 (3.1850)  weight_decay: 0.0500 (0.0500)  time: 0.6442  data: 0.2506  max mem: 31830
Epoch: [260]  [140/312]  eta: 0:01:42  lr: 0.000195  min_lr: 0.000195  loss: 3.2688 (3.1965)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.1367  max mem: 31830
Epoch: [260]  [150/312]  eta: 0:01:37  lr: 0.000194  min_lr: 0.000194  loss: 3.4473 (3.1946)  weight_decay: 0.0500 (0.0500)  time: 0.5231  data: 0.1298  max mem: 31830
Epoch: [260]  [160/312]  eta: 0:01:31  lr: 0.000194  min_lr: 0.000194  loss: 3.1442 (3.1913)  weight_decay: 0.0500 (0.0500)  time: 0.6294  data: 0.2345  max mem: 31830
Epoch: [260]  [170/312]  eta: 0:01:23  lr: 0.000194  min_lr: 0.000194  loss: 3.1442 (3.1926)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.1055  max mem: 31830
Epoch: [260]  [180/312]  eta: 0:01:18  lr: 0.000193  min_lr: 0.000193  loss: 3.4225 (3.1917)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.1310  max mem: 31830
Epoch: [260]  [190/312]  eta: 0:01:11  lr: 0.000193  min_lr: 0.000193  loss: 3.4111 (3.1973)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.1310  max mem: 31830
Epoch: [260]  [200/312]  eta: 0:01:05  lr: 0.000193  min_lr: 0.000193  loss: 2.9651 (3.1885)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.1089  max mem: 31830
Epoch: [260]  [210/312]  eta: 0:00:59  lr: 0.000193  min_lr: 0.000193  loss: 2.9651 (3.1847)  weight_decay: 0.0500 (0.0500)  time: 0.6312  data: 0.2367  max mem: 31830
Epoch: [260]  [220/312]  eta: 0:00:53  lr: 0.000192  min_lr: 0.000192  loss: 3.3626 (3.1930)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.1285  max mem: 31830
Epoch: [260]  [230/312]  eta: 0:00:47  lr: 0.000192  min_lr: 0.000192  loss: 3.2482 (3.1886)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.1268  max mem: 31830
Epoch: [260]  [240/312]  eta: 0:00:42  lr: 0.000192  min_lr: 0.000192  loss: 3.2482 (3.1939)  weight_decay: 0.0500 (0.0500)  time: 0.6324  data: 0.2396  max mem: 31830
Epoch: [260]  [250/312]  eta: 0:00:35  lr: 0.000191  min_lr: 0.000191  loss: 3.4780 (3.1960)  weight_decay: 0.0500 (0.0500)  time: 0.5063  data: 0.1136  max mem: 31830
Epoch: [260]  [260/312]  eta: 0:00:30  lr: 0.000191  min_lr: 0.000191  loss: 3.3908 (3.1982)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.1398  max mem: 31830
Epoch: [260]  [270/312]  eta: 0:00:24  lr: 0.000191  min_lr: 0.000191  loss: 3.2837 (3.1912)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.1400  max mem: 31830
Epoch: [260]  [280/312]  eta: 0:00:18  lr: 0.000190  min_lr: 0.000190  loss: 3.2300 (3.1920)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.1205  max mem: 31830
Epoch: [260]  [290/312]  eta: 0:00:12  lr: 0.000190  min_lr: 0.000190  loss: 3.2643 (3.1845)  weight_decay: 0.0500 (0.0500)  time: 0.5779  data: 0.1900  max mem: 31830
Epoch: [260]  [300/312]  eta: 0:00:06  lr: 0.000190  min_lr: 0.000190  loss: 3.0567 (3.1840)  weight_decay: 0.0500 (0.0500)  time: 0.4523  data: 0.0703  max mem: 31830
Epoch: [260]  [310/312]  eta: 0:00:01  lr: 0.000189  min_lr: 0.000189  loss: 3.1814 (3.1855)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [260]  [311/312]  eta: 0:00:00  lr: 0.000189  min_lr: 0.000189  loss: 3.1814 (3.1864)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [260] Total time: 0:02:56 (0.5643 s / it)
Averaged stats: lr: 0.000189  min_lr: 0.000189  loss: 3.1814 (3.2087)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8717 (0.8717)  acc1: 84.3750 (84.3750)  acc5: 96.7448 (96.7448)  time: 8.4924  data: 8.3252  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1656 (1.0821)  acc1: 77.9948 (77.8720)  acc5: 94.6615 (94.1280)  time: 1.0642  data: 0.9294  max mem: 31830
Test: Total time: 0:00:09 (1.0758 s / it)
* Acc@1 78.028 Acc@5 94.190 loss 1.078
Accuracy of the model on the 50000 test images: 78.0%
Max accuracy: 78.03%
Epoch: [261]  [  0/312]  eta: 1:03:59  lr: 0.000189  min_lr: 0.000189  loss: 3.4717 (3.4717)  weight_decay: 0.0500 (0.0500)  time: 12.3060  data: 10.9909  max mem: 31830
Epoch: [261]  [ 10/312]  eta: 0:08:33  lr: 0.000189  min_lr: 0.000189  loss: 3.2547 (3.1123)  weight_decay: 0.0500 (0.0500)  time: 1.7010  data: 1.0529  max mem: 31830
Epoch: [261]  [ 20/312]  eta: 0:05:39  lr: 0.000189  min_lr: 0.000189  loss: 3.3560 (3.2692)  weight_decay: 0.0500 (0.0500)  time: 0.6044  data: 0.0912  max mem: 31830
Epoch: [261]  [ 30/312]  eta: 0:04:17  lr: 0.000188  min_lr: 0.000188  loss: 3.5405 (3.2774)  weight_decay: 0.0500 (0.0500)  time: 0.4813  data: 0.0623  max mem: 31830
Epoch: [261]  [ 40/312]  eta: 0:03:34  lr: 0.000188  min_lr: 0.000188  loss: 3.3535 (3.2475)  weight_decay: 0.0500 (0.0500)  time: 0.3943  data: 0.0010  max mem: 31830
Epoch: [261]  [ 50/312]  eta: 0:03:06  lr: 0.000188  min_lr: 0.000188  loss: 3.2981 (3.2272)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0015  max mem: 31830
Epoch: [261]  [ 60/312]  eta: 0:02:46  lr: 0.000188  min_lr: 0.000188  loss: 3.3697 (3.2163)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0014  max mem: 31830
Epoch: [261]  [ 70/312]  eta: 0:02:37  lr: 0.000187  min_lr: 0.000187  loss: 2.9649 (3.1662)  weight_decay: 0.0500 (0.0500)  time: 0.4951  data: 0.0686  max mem: 31830
Epoch: [261]  [ 80/312]  eta: 0:02:28  lr: 0.000187  min_lr: 0.000187  loss: 2.9827 (3.1546)  weight_decay: 0.0500 (0.0500)  time: 0.5732  data: 0.1013  max mem: 31830
Epoch: [261]  [ 90/312]  eta: 0:02:18  lr: 0.000187  min_lr: 0.000187  loss: 3.2414 (3.1701)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0974  max mem: 31830
Epoch: [261]  [100/312]  eta: 0:02:13  lr: 0.000186  min_lr: 0.000186  loss: 3.4151 (3.1712)  weight_decay: 0.0500 (0.0500)  time: 0.5895  data: 0.1385  max mem: 31830
Epoch: [261]  [110/312]  eta: 0:02:02  lr: 0.000186  min_lr: 0.000186  loss: 3.0969 (3.1579)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0745  max mem: 31830
Epoch: [261]  [120/312]  eta: 0:01:56  lr: 0.000186  min_lr: 0.000186  loss: 3.1086 (3.1567)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0490  max mem: 31830
Epoch: [261]  [130/312]  eta: 0:01:50  lr: 0.000185  min_lr: 0.000185  loss: 3.4042 (3.1761)  weight_decay: 0.0500 (0.0500)  time: 0.6025  data: 0.1103  max mem: 31830
Epoch: [261]  [140/312]  eta: 0:01:41  lr: 0.000185  min_lr: 0.000185  loss: 3.4259 (3.1767)  weight_decay: 0.0500 (0.0500)  time: 0.4999  data: 0.0623  max mem: 31830
Epoch: [261]  [150/312]  eta: 0:01:36  lr: 0.000185  min_lr: 0.000185  loss: 3.2162 (3.1767)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0579  max mem: 31830
Epoch: [261]  [160/312]  eta: 0:01:29  lr: 0.000185  min_lr: 0.000185  loss: 3.1556 (3.1794)  weight_decay: 0.0500 (0.0500)  time: 0.5927  data: 0.0576  max mem: 31830
Epoch: [261]  [170/312]  eta: 0:01:23  lr: 0.000184  min_lr: 0.000184  loss: 3.3094 (3.1810)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0839  max mem: 31830
Epoch: [261]  [180/312]  eta: 0:01:17  lr: 0.000184  min_lr: 0.000184  loss: 3.3139 (3.1788)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.1460  max mem: 31830
Epoch: [261]  [190/312]  eta: 0:01:10  lr: 0.000184  min_lr: 0.000184  loss: 3.3139 (3.1793)  weight_decay: 0.0500 (0.0500)  time: 0.4850  data: 0.0630  max mem: 31830
Epoch: [261]  [200/312]  eta: 0:01:05  lr: 0.000183  min_lr: 0.000183  loss: 3.3887 (3.1959)  weight_decay: 0.0500 (0.0500)  time: 0.5380  data: 0.0846  max mem: 31830
Epoch: [261]  [210/312]  eta: 0:00:59  lr: 0.000183  min_lr: 0.000183  loss: 3.3698 (3.1862)  weight_decay: 0.0500 (0.0500)  time: 0.6200  data: 0.1478  max mem: 31830
Epoch: [261]  [220/312]  eta: 0:00:53  lr: 0.000183  min_lr: 0.000183  loss: 2.9858 (3.1823)  weight_decay: 0.0500 (0.0500)  time: 0.4967  data: 0.0641  max mem: 31830
Epoch: [261]  [230/312]  eta: 0:00:47  lr: 0.000182  min_lr: 0.000182  loss: 3.4212 (3.1990)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0757  max mem: 31830
Epoch: [261]  [240/312]  eta: 0:00:41  lr: 0.000182  min_lr: 0.000182  loss: 3.4586 (3.1991)  weight_decay: 0.0500 (0.0500)  time: 0.5537  data: 0.0756  max mem: 31830
Epoch: [261]  [250/312]  eta: 0:00:35  lr: 0.000182  min_lr: 0.000182  loss: 3.4036 (3.2038)  weight_decay: 0.0500 (0.0500)  time: 0.5755  data: 0.1053  max mem: 31830
Epoch: [261]  [260/312]  eta: 0:00:29  lr: 0.000182  min_lr: 0.000182  loss: 3.4036 (3.2043)  weight_decay: 0.0500 (0.0500)  time: 0.5879  data: 0.1459  max mem: 31830
Epoch: [261]  [270/312]  eta: 0:00:24  lr: 0.000181  min_lr: 0.000181  loss: 3.3408 (3.2001)  weight_decay: 0.0500 (0.0500)  time: 0.5642  data: 0.0414  max mem: 31830
Epoch: [261]  [280/312]  eta: 0:00:18  lr: 0.000181  min_lr: 0.000181  loss: 3.2033 (3.2011)  weight_decay: 0.0500 (0.0500)  time: 0.5503  data: 0.0439  max mem: 31830
Epoch: [261]  [290/312]  eta: 0:00:12  lr: 0.000181  min_lr: 0.000181  loss: 3.2503 (3.1994)  weight_decay: 0.0500 (0.0500)  time: 0.5261  data: 0.0687  max mem: 31830
Epoch: [261]  [300/312]  eta: 0:00:06  lr: 0.000180  min_lr: 0.000180  loss: 3.2287 (3.2020)  weight_decay: 0.0500 (0.0500)  time: 0.4662  data: 0.0253  max mem: 31830
Epoch: [261]  [310/312]  eta: 0:00:01  lr: 0.000180  min_lr: 0.000180  loss: 3.3196 (3.2064)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [261]  [311/312]  eta: 0:00:00  lr: 0.000180  min_lr: 0.000180  loss: 3.2436 (3.2048)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [261] Total time: 0:02:55 (0.5640 s / it)
Averaged stats: lr: 0.000180  min_lr: 0.000180  loss: 3.2436 (3.2198)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.8626 (0.8626)  acc1: 84.6354 (84.6354)  acc5: 96.6146 (96.6146)  time: 8.8692  data: 8.7094  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2025 (1.0903)  acc1: 78.3854 (77.4240)  acc5: 94.4010 (94.0800)  time: 1.1075  data: 0.9678  max mem: 31830
Test: Total time: 0:00:10 (1.1374 s / it)
* Acc@1 77.626 Acc@5 94.064 loss 1.083
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 78.03%
Epoch: [262]  [  0/312]  eta: 1:02:46  lr: 0.000180  min_lr: 0.000180  loss: 2.9073 (2.9073)  weight_decay: 0.0500 (0.0500)  time: 12.0728  data: 8.8295  max mem: 31830
Epoch: [262]  [ 10/312]  eta: 0:08:32  lr: 0.000180  min_lr: 0.000180  loss: 3.2180 (3.0272)  weight_decay: 0.0500 (0.0500)  time: 1.6962  data: 1.0323  max mem: 31830
Epoch: [262]  [ 20/312]  eta: 0:05:39  lr: 0.000179  min_lr: 0.000179  loss: 3.2180 (3.0383)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.1622  max mem: 31830
Epoch: [262]  [ 30/312]  eta: 0:04:18  lr: 0.000179  min_lr: 0.000179  loss: 3.2518 (3.1159)  weight_decay: 0.0500 (0.0500)  time: 0.4868  data: 0.0364  max mem: 31830
Epoch: [262]  [ 40/312]  eta: 0:03:34  lr: 0.000179  min_lr: 0.000179  loss: 3.3403 (3.1321)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0008  max mem: 31830
Epoch: [262]  [ 50/312]  eta: 0:03:08  lr: 0.000179  min_lr: 0.000179  loss: 3.3698 (3.1601)  weight_decay: 0.0500 (0.0500)  time: 0.4150  data: 0.0008  max mem: 31830
Epoch: [262]  [ 60/312]  eta: 0:02:47  lr: 0.000178  min_lr: 0.000178  loss: 3.4597 (3.1887)  weight_decay: 0.0500 (0.0500)  time: 0.4137  data: 0.0008  max mem: 31830
Epoch: [262]  [ 70/312]  eta: 0:02:37  lr: 0.000178  min_lr: 0.000178  loss: 3.4597 (3.2105)  weight_decay: 0.0500 (0.0500)  time: 0.4721  data: 0.0010  max mem: 31830
Epoch: [262]  [ 80/312]  eta: 0:02:29  lr: 0.000178  min_lr: 0.000178  loss: 3.3496 (3.2086)  weight_decay: 0.0500 (0.0500)  time: 0.5715  data: 0.0010  max mem: 31830
Epoch: [262]  [ 90/312]  eta: 0:02:18  lr: 0.000177  min_lr: 0.000177  loss: 3.3203 (3.2058)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0148  max mem: 31830
Epoch: [262]  [100/312]  eta: 0:02:12  lr: 0.000177  min_lr: 0.000177  loss: 3.2519 (3.2115)  weight_decay: 0.0500 (0.0500)  time: 0.5633  data: 0.0151  max mem: 31830
Epoch: [262]  [110/312]  eta: 0:02:02  lr: 0.000177  min_lr: 0.000177  loss: 3.4117 (3.2224)  weight_decay: 0.0500 (0.0500)  time: 0.5342  data: 0.0017  max mem: 31830
Epoch: [262]  [120/312]  eta: 0:01:55  lr: 0.000176  min_lr: 0.000176  loss: 3.4117 (3.2257)  weight_decay: 0.0500 (0.0500)  time: 0.4834  data: 0.0080  max mem: 31830
Epoch: [262]  [130/312]  eta: 0:01:49  lr: 0.000176  min_lr: 0.000176  loss: 3.2984 (3.2297)  weight_decay: 0.0500 (0.0500)  time: 0.5848  data: 0.0283  max mem: 31830
Epoch: [262]  [140/312]  eta: 0:01:41  lr: 0.000176  min_lr: 0.000176  loss: 3.1035 (3.2144)  weight_decay: 0.0500 (0.0500)  time: 0.4983  data: 0.0216  max mem: 31830
Epoch: [262]  [150/312]  eta: 0:01:36  lr: 0.000176  min_lr: 0.000176  loss: 3.1035 (3.2076)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0221  max mem: 31830
Epoch: [262]  [160/312]  eta: 0:01:30  lr: 0.000175  min_lr: 0.000175  loss: 3.4081 (3.2270)  weight_decay: 0.0500 (0.0500)  time: 0.6284  data: 0.0221  max mem: 31830
Epoch: [262]  [170/312]  eta: 0:01:22  lr: 0.000175  min_lr: 0.000175  loss: 3.5155 (3.2226)  weight_decay: 0.0500 (0.0500)  time: 0.5053  data: 0.0157  max mem: 31830
Epoch: [262]  [180/312]  eta: 0:01:17  lr: 0.000175  min_lr: 0.000175  loss: 3.2021 (3.2130)  weight_decay: 0.0500 (0.0500)  time: 0.5281  data: 0.0158  max mem: 31830
Epoch: [262]  [190/312]  eta: 0:01:10  lr: 0.000174  min_lr: 0.000174  loss: 3.3314 (3.2205)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0008  max mem: 31830
Epoch: [262]  [200/312]  eta: 0:01:04  lr: 0.000174  min_lr: 0.000174  loss: 3.3314 (3.2160)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0008  max mem: 31830
Epoch: [262]  [210/312]  eta: 0:00:59  lr: 0.000174  min_lr: 0.000174  loss: 3.3243 (3.2201)  weight_decay: 0.0500 (0.0500)  time: 0.6371  data: 0.0322  max mem: 31830
Epoch: [262]  [220/312]  eta: 0:00:52  lr: 0.000174  min_lr: 0.000174  loss: 3.3883 (3.2208)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0327  max mem: 31830
Epoch: [262]  [230/312]  eta: 0:00:47  lr: 0.000173  min_lr: 0.000173  loss: 3.5287 (3.2283)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0078  max mem: 31830
Epoch: [262]  [240/312]  eta: 0:00:41  lr: 0.000173  min_lr: 0.000173  loss: 3.3320 (3.2334)  weight_decay: 0.0500 (0.0500)  time: 0.5942  data: 0.0072  max mem: 31830
Epoch: [262]  [250/312]  eta: 0:00:35  lr: 0.000173  min_lr: 0.000173  loss: 3.4635 (3.2441)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0085  max mem: 31830
Epoch: [262]  [260/312]  eta: 0:00:29  lr: 0.000172  min_lr: 0.000172  loss: 3.4839 (3.2468)  weight_decay: 0.0500 (0.0500)  time: 0.5785  data: 0.0087  max mem: 31830
Epoch: [262]  [270/312]  eta: 0:00:23  lr: 0.000172  min_lr: 0.000172  loss: 3.4120 (3.2439)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0010  max mem: 31830
Epoch: [262]  [280/312]  eta: 0:00:18  lr: 0.000172  min_lr: 0.000172  loss: 3.4450 (3.2524)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0122  max mem: 31830
Epoch: [262]  [290/312]  eta: 0:00:12  lr: 0.000171  min_lr: 0.000171  loss: 3.3691 (3.2509)  weight_decay: 0.0500 (0.0500)  time: 0.5379  data: 0.0121  max mem: 31830
Epoch: [262]  [300/312]  eta: 0:00:06  lr: 0.000171  min_lr: 0.000171  loss: 3.2800 (3.2521)  weight_decay: 0.0500 (0.0500)  time: 0.4528  data: 0.0155  max mem: 31830
Epoch: [262]  [310/312]  eta: 0:00:01  lr: 0.000171  min_lr: 0.000171  loss: 3.4593 (3.2571)  weight_decay: 0.0500 (0.0500)  time: 0.4120  data: 0.0153  max mem: 31830
Epoch: [262]  [311/312]  eta: 0:00:00  lr: 0.000171  min_lr: 0.000171  loss: 3.4593 (3.2571)  weight_decay: 0.0500 (0.0500)  time: 0.3965  data: 0.0001  max mem: 31830
Epoch: [262] Total time: 0:02:54 (0.5607 s / it)
Averaged stats: lr: 0.000171  min_lr: 0.000171  loss: 3.4593 (3.2064)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.9681 (0.9681)  acc1: 85.0260 (85.0260)  acc5: 96.8750 (96.8750)  time: 8.1202  data: 7.9533  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2627 (1.1822)  acc1: 77.7344 (77.8080)  acc5: 94.6615 (94.4800)  time: 1.0191  data: 0.8838  max mem: 31830
Test: Total time: 0:00:09 (1.0298 s / it)
* Acc@1 78.076 Acc@5 94.252 loss 1.182
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.08%
Epoch: [263]  [  0/312]  eta: 0:58:57  lr: 0.000171  min_lr: 0.000171  loss: 2.9502 (2.9502)  weight_decay: 0.0500 (0.0500)  time: 11.3376  data: 8.4177  max mem: 31830
Epoch: [263]  [ 10/312]  eta: 0:08:47  lr: 0.000171  min_lr: 0.000171  loss: 3.3538 (3.2698)  weight_decay: 0.0500 (0.0500)  time: 1.7475  data: 0.9135  max mem: 31830
Epoch: [263]  [ 20/312]  eta: 0:05:21  lr: 0.000170  min_lr: 0.000170  loss: 3.3196 (3.2906)  weight_decay: 0.0500 (0.0500)  time: 0.5909  data: 0.0819  max mem: 31830
Epoch: [263]  [ 30/312]  eta: 0:04:12  lr: 0.000170  min_lr: 0.000170  loss: 3.5391 (3.3868)  weight_decay: 0.0500 (0.0500)  time: 0.4242  data: 0.0305  max mem: 31830
Epoch: [263]  [ 40/312]  eta: 0:03:30  lr: 0.000170  min_lr: 0.000170  loss: 3.5391 (3.3315)  weight_decay: 0.0500 (0.0500)  time: 0.4274  data: 0.0306  max mem: 31830
Epoch: [263]  [ 50/312]  eta: 0:03:03  lr: 0.000169  min_lr: 0.000169  loss: 3.2222 (3.3386)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [263]  [ 60/312]  eta: 0:02:44  lr: 0.000169  min_lr: 0.000169  loss: 3.1703 (3.2721)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0009  max mem: 31830
Epoch: [263]  [ 70/312]  eta: 0:02:30  lr: 0.000169  min_lr: 0.000169  loss: 3.3085 (3.3111)  weight_decay: 0.0500 (0.0500)  time: 0.4227  data: 0.0011  max mem: 31830
Epoch: [263]  [ 80/312]  eta: 0:02:22  lr: 0.000169  min_lr: 0.000169  loss: 3.4411 (3.2656)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0437  max mem: 31830
Epoch: [263]  [ 90/312]  eta: 0:02:11  lr: 0.000168  min_lr: 0.000168  loss: 3.2551 (3.2754)  weight_decay: 0.0500 (0.0500)  time: 0.4925  data: 0.0582  max mem: 31830
Epoch: [263]  [100/312]  eta: 0:02:06  lr: 0.000168  min_lr: 0.000168  loss: 3.1552 (3.2368)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0442  max mem: 31830
Epoch: [263]  [110/312]  eta: 0:01:57  lr: 0.000168  min_lr: 0.000168  loss: 3.1285 (3.2380)  weight_decay: 0.0500 (0.0500)  time: 0.5241  data: 0.0349  max mem: 31830
Epoch: [263]  [120/312]  eta: 0:01:51  lr: 0.000167  min_lr: 0.000167  loss: 3.3539 (3.2376)  weight_decay: 0.0500 (0.0500)  time: 0.5165  data: 0.0614  max mem: 31830
Epoch: [263]  [130/312]  eta: 0:01:47  lr: 0.000167  min_lr: 0.000167  loss: 3.1914 (3.2303)  weight_decay: 0.0500 (0.0500)  time: 0.6280  data: 0.0848  max mem: 31830
Epoch: [263]  [140/312]  eta: 0:01:39  lr: 0.000167  min_lr: 0.000167  loss: 3.1914 (3.2357)  weight_decay: 0.0500 (0.0500)  time: 0.5437  data: 0.0298  max mem: 31830
Epoch: [263]  [150/312]  eta: 0:01:34  lr: 0.000167  min_lr: 0.000167  loss: 3.3491 (3.2347)  weight_decay: 0.0500 (0.0500)  time: 0.5390  data: 0.0253  max mem: 31830
Epoch: [263]  [160/312]  eta: 0:01:27  lr: 0.000166  min_lr: 0.000166  loss: 3.2766 (3.2282)  weight_decay: 0.0500 (0.0500)  time: 0.5852  data: 0.0359  max mem: 31830
Epoch: [263]  [170/312]  eta: 0:01:21  lr: 0.000166  min_lr: 0.000166  loss: 3.1770 (3.2256)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0255  max mem: 31830
Epoch: [263]  [180/312]  eta: 0:01:15  lr: 0.000166  min_lr: 0.000166  loss: 3.3246 (3.2333)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0238  max mem: 31830
Epoch: [263]  [190/312]  eta: 0:01:09  lr: 0.000165  min_lr: 0.000165  loss: 3.2920 (3.2231)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0275  max mem: 31830
Epoch: [263]  [200/312]  eta: 0:01:03  lr: 0.000165  min_lr: 0.000165  loss: 3.1735 (3.2198)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0237  max mem: 31830
Epoch: [263]  [210/312]  eta: 0:00:58  lr: 0.000165  min_lr: 0.000165  loss: 3.3027 (3.2226)  weight_decay: 0.0500 (0.0500)  time: 0.6071  data: 0.0129  max mem: 31830
Epoch: [263]  [220/312]  eta: 0:00:51  lr: 0.000165  min_lr: 0.000165  loss: 3.3027 (3.2143)  weight_decay: 0.0500 (0.0500)  time: 0.5579  data: 0.0079  max mem: 31830
Epoch: [263]  [230/312]  eta: 0:00:46  lr: 0.000164  min_lr: 0.000164  loss: 3.2260 (3.2085)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0073  max mem: 31830
Epoch: [263]  [240/312]  eta: 0:00:40  lr: 0.000164  min_lr: 0.000164  loss: 3.4302 (3.2196)  weight_decay: 0.0500 (0.0500)  time: 0.5880  data: 0.0187  max mem: 31830
Epoch: [263]  [250/312]  eta: 0:00:34  lr: 0.000164  min_lr: 0.000164  loss: 3.4796 (3.2211)  weight_decay: 0.0500 (0.0500)  time: 0.5700  data: 0.0290  max mem: 31830
Epoch: [263]  [260/312]  eta: 0:00:29  lr: 0.000163  min_lr: 0.000163  loss: 3.3121 (3.2194)  weight_decay: 0.0500 (0.0500)  time: 0.5215  data: 0.0458  max mem: 31830
Epoch: [263]  [270/312]  eta: 0:00:23  lr: 0.000163  min_lr: 0.000163  loss: 3.2564 (3.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.0291  max mem: 31830
Epoch: [263]  [280/312]  eta: 0:00:17  lr: 0.000163  min_lr: 0.000163  loss: 3.1484 (3.2091)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0218  max mem: 31830
Epoch: [263]  [290/312]  eta: 0:00:12  lr: 0.000163  min_lr: 0.000163  loss: 3.1584 (3.2100)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.0408  max mem: 31830
Epoch: [263]  [300/312]  eta: 0:00:06  lr: 0.000162  min_lr: 0.000162  loss: 3.1784 (3.2064)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0195  max mem: 31830
Epoch: [263]  [310/312]  eta: 0:00:01  lr: 0.000162  min_lr: 0.000162  loss: 3.3684 (3.2092)  weight_decay: 0.0500 (0.0500)  time: 0.4080  data: 0.0002  max mem: 31830
Epoch: [263]  [311/312]  eta: 0:00:00  lr: 0.000162  min_lr: 0.000162  loss: 3.3106 (3.2081)  weight_decay: 0.0500 (0.0500)  time: 0.4078  data: 0.0002  max mem: 31830
Epoch: [263] Total time: 0:02:53 (0.5556 s / it)
Averaged stats: lr: 0.000162  min_lr: 0.000162  loss: 3.3106 (3.2112)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8986 (0.8986)  acc1: 84.5052 (84.5052)  acc5: 96.8750 (96.8750)  time: 8.9321  data: 8.7648  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1848 (1.1061)  acc1: 78.7760 (77.7760)  acc5: 94.4010 (94.0480)  time: 1.1087  data: 0.9739  max mem: 31830
Test: Total time: 0:00:10 (1.1200 s / it)
* Acc@1 77.924 Acc@5 94.086 loss 1.100
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 78.08%
Epoch: [264]  [  0/312]  eta: 1:04:34  lr: 0.000162  min_lr: 0.000162  loss: 2.7765 (2.7765)  weight_decay: 0.0500 (0.0500)  time: 12.4184  data: 10.6306  max mem: 31830
Epoch: [264]  [ 10/312]  eta: 0:09:00  lr: 0.000162  min_lr: 0.000162  loss: 3.2076 (3.1494)  weight_decay: 0.0500 (0.0500)  time: 1.7894  data: 0.9670  max mem: 31830
Epoch: [264]  [ 20/312]  eta: 0:05:28  lr: 0.000161  min_lr: 0.000161  loss: 3.3461 (3.2425)  weight_decay: 0.0500 (0.0500)  time: 0.5594  data: 0.0007  max mem: 31830
Epoch: [264]  [ 30/312]  eta: 0:04:11  lr: 0.000161  min_lr: 0.000161  loss: 3.3461 (3.0807)  weight_decay: 0.0500 (0.0500)  time: 0.3962  data: 0.0008  max mem: 31830
Epoch: [264]  [ 40/312]  eta: 0:03:29  lr: 0.000161  min_lr: 0.000161  loss: 3.0948 (3.1172)  weight_decay: 0.0500 (0.0500)  time: 0.4000  data: 0.0008  max mem: 31830
Epoch: [264]  [ 50/312]  eta: 0:03:02  lr: 0.000160  min_lr: 0.000160  loss: 3.3997 (3.1882)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0011  max mem: 31830
Epoch: [264]  [ 60/312]  eta: 0:02:43  lr: 0.000160  min_lr: 0.000160  loss: 3.4955 (3.2080)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0012  max mem: 31830
Epoch: [264]  [ 70/312]  eta: 0:02:30  lr: 0.000160  min_lr: 0.000160  loss: 3.4433 (3.2079)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0015  max mem: 31830
Epoch: [264]  [ 80/312]  eta: 0:02:23  lr: 0.000160  min_lr: 0.000160  loss: 3.4433 (3.2156)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.0284  max mem: 31830
Epoch: [264]  [ 90/312]  eta: 0:02:15  lr: 0.000159  min_lr: 0.000159  loss: 3.4701 (3.2316)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.0508  max mem: 31830
Epoch: [264]  [100/312]  eta: 0:02:07  lr: 0.000159  min_lr: 0.000159  loss: 3.3406 (3.2206)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0389  max mem: 31830
Epoch: [264]  [110/312]  eta: 0:02:00  lr: 0.000159  min_lr: 0.000159  loss: 3.3437 (3.2253)  weight_decay: 0.0500 (0.0500)  time: 0.5389  data: 0.0522  max mem: 31830
Epoch: [264]  [120/312]  eta: 0:01:51  lr: 0.000159  min_lr: 0.000159  loss: 3.0452 (3.2122)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0370  max mem: 31830
Epoch: [264]  [130/312]  eta: 0:01:46  lr: 0.000158  min_lr: 0.000158  loss: 3.1365 (3.2244)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0340  max mem: 31830
Epoch: [264]  [140/312]  eta: 0:01:39  lr: 0.000158  min_lr: 0.000158  loss: 3.4744 (3.2375)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0487  max mem: 31830
Epoch: [264]  [150/312]  eta: 0:01:33  lr: 0.000158  min_lr: 0.000158  loss: 3.3795 (3.2371)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0354  max mem: 31830
Epoch: [264]  [160/312]  eta: 0:01:28  lr: 0.000157  min_lr: 0.000157  loss: 3.2125 (3.2314)  weight_decay: 0.0500 (0.0500)  time: 0.5879  data: 0.0344  max mem: 31830
Epoch: [264]  [170/312]  eta: 0:01:21  lr: 0.000157  min_lr: 0.000157  loss: 3.4675 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0357  max mem: 31830
Epoch: [264]  [180/312]  eta: 0:01:15  lr: 0.000157  min_lr: 0.000157  loss: 3.5382 (3.2557)  weight_decay: 0.0500 (0.0500)  time: 0.5066  data: 0.0223  max mem: 31830
Epoch: [264]  [190/312]  eta: 0:01:09  lr: 0.000157  min_lr: 0.000157  loss: 3.4643 (3.2536)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0192  max mem: 31830
Epoch: [264]  [200/312]  eta: 0:01:03  lr: 0.000156  min_lr: 0.000156  loss: 3.2201 (3.2461)  weight_decay: 0.0500 (0.0500)  time: 0.5438  data: 0.0190  max mem: 31830
Epoch: [264]  [210/312]  eta: 0:00:58  lr: 0.000156  min_lr: 0.000156  loss: 3.3518 (3.2460)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0206  max mem: 31830
Epoch: [264]  [220/312]  eta: 0:00:52  lr: 0.000156  min_lr: 0.000156  loss: 3.4624 (3.2500)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0414  max mem: 31830
Epoch: [264]  [230/312]  eta: 0:00:46  lr: 0.000155  min_lr: 0.000155  loss: 3.4624 (3.2517)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0216  max mem: 31830
Epoch: [264]  [240/312]  eta: 0:00:40  lr: 0.000155  min_lr: 0.000155  loss: 3.4285 (3.2543)  weight_decay: 0.0500 (0.0500)  time: 0.5812  data: 0.0129  max mem: 31830
Epoch: [264]  [250/312]  eta: 0:00:34  lr: 0.000155  min_lr: 0.000155  loss: 3.5030 (3.2640)  weight_decay: 0.0500 (0.0500)  time: 0.5598  data: 0.0427  max mem: 31830
Epoch: [264]  [260/312]  eta: 0:00:29  lr: 0.000155  min_lr: 0.000155  loss: 3.4826 (3.2643)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0361  max mem: 31830
Epoch: [264]  [270/312]  eta: 0:00:23  lr: 0.000154  min_lr: 0.000154  loss: 3.1888 (3.2537)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0411  max mem: 31830
Epoch: [264]  [280/312]  eta: 0:00:17  lr: 0.000154  min_lr: 0.000154  loss: 3.1888 (3.2556)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0365  max mem: 31830
Epoch: [264]  [290/312]  eta: 0:00:12  lr: 0.000154  min_lr: 0.000154  loss: 3.3555 (3.2503)  weight_decay: 0.0500 (0.0500)  time: 0.5650  data: 0.0294  max mem: 31830
Epoch: [264]  [300/312]  eta: 0:00:06  lr: 0.000154  min_lr: 0.000154  loss: 3.0780 (3.2338)  weight_decay: 0.0500 (0.0500)  time: 0.5363  data: 0.0332  max mem: 31830
Epoch: [264]  [310/312]  eta: 0:00:01  lr: 0.000153  min_lr: 0.000153  loss: 3.3121 (3.2406)  weight_decay: 0.0500 (0.0500)  time: 0.4183  data: 0.0053  max mem: 31830
Epoch: [264]  [311/312]  eta: 0:00:00  lr: 0.000153  min_lr: 0.000153  loss: 3.3298 (3.2413)  weight_decay: 0.0500 (0.0500)  time: 0.4176  data: 0.0053  max mem: 31830
Epoch: [264] Total time: 0:02:53 (0.5549 s / it)
Averaged stats: lr: 0.000153  min_lr: 0.000153  loss: 3.3298 (3.1980)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9437 (0.9437)  acc1: 85.0260 (85.0260)  acc5: 96.7448 (96.7448)  time: 8.8674  data: 8.7001  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2386 (1.1559)  acc1: 77.9948 (77.7440)  acc5: 93.8802 (94.3520)  time: 1.1026  data: 0.9668  max mem: 31830
Test: Total time: 0:00:10 (1.1315 s / it)
* Acc@1 78.070 Acc@5 94.280 loss 1.150
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.08%
Epoch: [265]  [  0/312]  eta: 1:04:03  lr: 0.000153  min_lr: 0.000153  loss: 3.7428 (3.7428)  weight_decay: 0.0500 (0.0500)  time: 12.3194  data: 11.9169  max mem: 31830
Epoch: [265]  [ 10/312]  eta: 0:08:36  lr: 0.000153  min_lr: 0.000153  loss: 3.4611 (3.2109)  weight_decay: 0.0500 (0.0500)  time: 1.7090  data: 1.0841  max mem: 31830
Epoch: [265]  [ 20/312]  eta: 0:05:25  lr: 0.000153  min_lr: 0.000153  loss: 3.4611 (3.2773)  weight_decay: 0.0500 (0.0500)  time: 0.5528  data: 0.0255  max mem: 31830
Epoch: [265]  [ 30/312]  eta: 0:04:08  lr: 0.000152  min_lr: 0.000152  loss: 3.3111 (3.2707)  weight_decay: 0.0500 (0.0500)  time: 0.4282  data: 0.0256  max mem: 31830
Epoch: [265]  [ 40/312]  eta: 0:03:27  lr: 0.000152  min_lr: 0.000152  loss: 3.3111 (3.2681)  weight_decay: 0.0500 (0.0500)  time: 0.3989  data: 0.0011  max mem: 31830
Epoch: [265]  [ 50/312]  eta: 0:03:06  lr: 0.000152  min_lr: 0.000152  loss: 3.2400 (3.2404)  weight_decay: 0.0500 (0.0500)  time: 0.4456  data: 0.0012  max mem: 31830
Epoch: [265]  [ 60/312]  eta: 0:02:46  lr: 0.000152  min_lr: 0.000152  loss: 3.1763 (3.2096)  weight_decay: 0.0500 (0.0500)  time: 0.4419  data: 0.0010  max mem: 31830
Epoch: [265]  [ 70/312]  eta: 0:02:37  lr: 0.000151  min_lr: 0.000151  loss: 3.0926 (3.1877)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0016  max mem: 31830
Epoch: [265]  [ 80/312]  eta: 0:02:29  lr: 0.000151  min_lr: 0.000151  loss: 3.3077 (3.2382)  weight_decay: 0.0500 (0.0500)  time: 0.5972  data: 0.0015  max mem: 31830
Epoch: [265]  [ 90/312]  eta: 0:02:18  lr: 0.000151  min_lr: 0.000151  loss: 3.4579 (3.2367)  weight_decay: 0.0500 (0.0500)  time: 0.5372  data: 0.0007  max mem: 31830
Epoch: [265]  [100/312]  eta: 0:02:11  lr: 0.000150  min_lr: 0.000150  loss: 3.3668 (3.2164)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0014  max mem: 31830
Epoch: [265]  [110/312]  eta: 0:02:01  lr: 0.000150  min_lr: 0.000150  loss: 3.3823 (3.2187)  weight_decay: 0.0500 (0.0500)  time: 0.4897  data: 0.0021  max mem: 31830
Epoch: [265]  [120/312]  eta: 0:01:55  lr: 0.000150  min_lr: 0.000150  loss: 3.3776 (3.2096)  weight_decay: 0.0500 (0.0500)  time: 0.5021  data: 0.0014  max mem: 31830
Epoch: [265]  [130/312]  eta: 0:01:51  lr: 0.000150  min_lr: 0.000150  loss: 3.4435 (3.2111)  weight_decay: 0.0500 (0.0500)  time: 0.6611  data: 0.0010  max mem: 31830
Epoch: [265]  [140/312]  eta: 0:01:42  lr: 0.000149  min_lr: 0.000149  loss: 3.3238 (3.1880)  weight_decay: 0.0500 (0.0500)  time: 0.5554  data: 0.0014  max mem: 31830
Epoch: [265]  [150/312]  eta: 0:01:35  lr: 0.000149  min_lr: 0.000149  loss: 3.3238 (3.2047)  weight_decay: 0.0500 (0.0500)  time: 0.4639  data: 0.0015  max mem: 31830
Epoch: [265]  [160/312]  eta: 0:01:30  lr: 0.000149  min_lr: 0.000149  loss: 3.3811 (3.2030)  weight_decay: 0.0500 (0.0500)  time: 0.6073  data: 0.0012  max mem: 31830
Epoch: [265]  [170/312]  eta: 0:01:23  lr: 0.000149  min_lr: 0.000149  loss: 3.3811 (3.2156)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0009  max mem: 31830
Epoch: [265]  [180/312]  eta: 0:01:17  lr: 0.000148  min_lr: 0.000148  loss: 3.3078 (3.2206)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0011  max mem: 31830
Epoch: [265]  [190/312]  eta: 0:01:10  lr: 0.000148  min_lr: 0.000148  loss: 3.3067 (3.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0015  max mem: 31830
Epoch: [265]  [200/312]  eta: 0:01:05  lr: 0.000148  min_lr: 0.000148  loss: 3.3845 (3.2181)  weight_decay: 0.0500 (0.0500)  time: 0.5255  data: 0.0060  max mem: 31830
Epoch: [265]  [210/312]  eta: 0:00:59  lr: 0.000147  min_lr: 0.000147  loss: 3.2826 (3.2086)  weight_decay: 0.0500 (0.0500)  time: 0.6392  data: 0.0057  max mem: 31830
Epoch: [265]  [220/312]  eta: 0:00:53  lr: 0.000147  min_lr: 0.000147  loss: 3.2616 (3.2162)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0009  max mem: 31830
Epoch: [265]  [230/312]  eta: 0:00:47  lr: 0.000147  min_lr: 0.000147  loss: 3.3955 (3.2220)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0412  max mem: 31830
Epoch: [265]  [240/312]  eta: 0:00:41  lr: 0.000147  min_lr: 0.000147  loss: 3.0657 (3.2094)  weight_decay: 0.0500 (0.0500)  time: 0.6378  data: 0.0413  max mem: 31830
Epoch: [265]  [250/312]  eta: 0:00:35  lr: 0.000146  min_lr: 0.000146  loss: 3.4159 (3.2190)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0009  max mem: 31830
Epoch: [265]  [260/312]  eta: 0:00:30  lr: 0.000146  min_lr: 0.000146  loss: 3.4504 (3.2258)  weight_decay: 0.0500 (0.0500)  time: 0.5238  data: 0.0009  max mem: 31830
Epoch: [265]  [270/312]  eta: 0:00:24  lr: 0.000146  min_lr: 0.000146  loss: 3.3453 (3.2250)  weight_decay: 0.0500 (0.0500)  time: 0.5239  data: 0.0013  max mem: 31830
Epoch: [265]  [280/312]  eta: 0:00:18  lr: 0.000146  min_lr: 0.000146  loss: 3.3091 (3.2203)  weight_decay: 0.0500 (0.0500)  time: 0.5228  data: 0.0027  max mem: 31830
Epoch: [265]  [290/312]  eta: 0:00:12  lr: 0.000145  min_lr: 0.000145  loss: 3.2566 (3.2202)  weight_decay: 0.0500 (0.0500)  time: 0.5776  data: 0.0055  max mem: 31830
Epoch: [265]  [300/312]  eta: 0:00:06  lr: 0.000145  min_lr: 0.000145  loss: 3.2566 (3.2174)  weight_decay: 0.0500 (0.0500)  time: 0.4451  data: 0.0038  max mem: 31830
Epoch: [265]  [310/312]  eta: 0:00:01  lr: 0.000145  min_lr: 0.000145  loss: 3.2485 (3.2156)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [265]  [311/312]  eta: 0:00:00  lr: 0.000145  min_lr: 0.000145  loss: 3.1343 (3.2146)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [265] Total time: 0:02:55 (0.5631 s / it)
Averaged stats: lr: 0.000145  min_lr: 0.000145  loss: 3.1343 (3.2077)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.8395 (0.8395)  acc1: 84.7656 (84.7656)  acc5: 97.1354 (97.1354)  time: 9.1481  data: 8.9803  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1632 (1.0768)  acc1: 78.3854 (77.8400)  acc5: 94.1406 (94.0320)  time: 1.1333  data: 0.9979  max mem: 31830
Test: Total time: 0:00:10 (1.1568 s / it)
* Acc@1 78.066 Acc@5 94.160 loss 1.072
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.08%
Epoch: [266]  [  0/312]  eta: 1:05:07  lr: 0.000145  min_lr: 0.000145  loss: 3.5331 (3.5331)  weight_decay: 0.0500 (0.0500)  time: 12.5232  data: 8.7719  max mem: 31830
Epoch: [266]  [ 10/312]  eta: 0:08:50  lr: 0.000144  min_lr: 0.000144  loss: 3.4061 (3.3298)  weight_decay: 0.0500 (0.0500)  time: 1.7561  data: 1.0658  max mem: 31830
Epoch: [266]  [ 20/312]  eta: 0:05:37  lr: 0.000144  min_lr: 0.000144  loss: 3.2020 (3.1920)  weight_decay: 0.0500 (0.0500)  time: 0.5862  data: 0.1872  max mem: 31830
Epoch: [266]  [ 30/312]  eta: 0:04:16  lr: 0.000144  min_lr: 0.000144  loss: 3.1813 (3.1851)  weight_decay: 0.0500 (0.0500)  time: 0.4439  data: 0.0399  max mem: 31830
Epoch: [266]  [ 40/312]  eta: 0:03:33  lr: 0.000144  min_lr: 0.000144  loss: 3.3071 (3.1745)  weight_decay: 0.0500 (0.0500)  time: 0.3942  data: 0.0007  max mem: 31830
Epoch: [266]  [ 50/312]  eta: 0:03:05  lr: 0.000143  min_lr: 0.000143  loss: 3.3449 (3.1780)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0008  max mem: 31830
Epoch: [266]  [ 60/312]  eta: 0:02:45  lr: 0.000143  min_lr: 0.000143  loss: 3.1246 (3.1521)  weight_decay: 0.0500 (0.0500)  time: 0.3978  data: 0.0008  max mem: 31830
Epoch: [266]  [ 70/312]  eta: 0:02:32  lr: 0.000143  min_lr: 0.000143  loss: 3.1092 (3.1081)  weight_decay: 0.0500 (0.0500)  time: 0.4305  data: 0.0059  max mem: 31830
Epoch: [266]  [ 80/312]  eta: 0:02:24  lr: 0.000143  min_lr: 0.000143  loss: 3.3299 (3.1486)  weight_decay: 0.0500 (0.0500)  time: 0.5269  data: 0.0060  max mem: 31830
Epoch: [266]  [ 90/312]  eta: 0:02:15  lr: 0.000142  min_lr: 0.000142  loss: 3.4199 (3.1660)  weight_decay: 0.0500 (0.0500)  time: 0.5390  data: 0.0467  max mem: 31830
Epoch: [266]  [100/312]  eta: 0:02:07  lr: 0.000142  min_lr: 0.000142  loss: 3.3406 (3.1789)  weight_decay: 0.0500 (0.0500)  time: 0.5133  data: 0.0467  max mem: 31830
Epoch: [266]  [110/312]  eta: 0:02:00  lr: 0.000142  min_lr: 0.000142  loss: 3.3406 (3.1669)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0153  max mem: 31830
Epoch: [266]  [120/312]  eta: 0:01:53  lr: 0.000142  min_lr: 0.000142  loss: 3.2811 (3.1647)  weight_decay: 0.0500 (0.0500)  time: 0.5414  data: 0.0396  max mem: 31830
Epoch: [266]  [130/312]  eta: 0:01:47  lr: 0.000141  min_lr: 0.000141  loss: 3.2898 (3.1771)  weight_decay: 0.0500 (0.0500)  time: 0.5771  data: 0.0312  max mem: 31830
Epoch: [266]  [140/312]  eta: 0:01:41  lr: 0.000141  min_lr: 0.000141  loss: 3.4537 (3.1851)  weight_decay: 0.0500 (0.0500)  time: 0.5602  data: 0.0069  max mem: 31830
Epoch: [266]  [150/312]  eta: 0:01:34  lr: 0.000141  min_lr: 0.000141  loss: 3.3275 (3.1912)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0070  max mem: 31830
Epoch: [266]  [160/312]  eta: 0:01:29  lr: 0.000140  min_lr: 0.000140  loss: 3.3555 (3.1976)  weight_decay: 0.0500 (0.0500)  time: 0.5719  data: 0.0068  max mem: 31830
Epoch: [266]  [170/312]  eta: 0:01:21  lr: 0.000140  min_lr: 0.000140  loss: 3.3734 (3.1954)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0008  max mem: 31830
Epoch: [266]  [180/312]  eta: 0:01:16  lr: 0.000140  min_lr: 0.000140  loss: 3.3734 (3.2081)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0012  max mem: 31830
Epoch: [266]  [190/312]  eta: 0:01:10  lr: 0.000140  min_lr: 0.000140  loss: 3.1878 (3.1896)  weight_decay: 0.0500 (0.0500)  time: 0.5914  data: 0.0012  max mem: 31830
Epoch: [266]  [200/312]  eta: 0:01:04  lr: 0.000139  min_lr: 0.000139  loss: 3.1878 (3.1976)  weight_decay: 0.0500 (0.0500)  time: 0.5378  data: 0.0009  max mem: 31830
Epoch: [266]  [210/312]  eta: 0:00:58  lr: 0.000139  min_lr: 0.000139  loss: 3.4401 (3.2002)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.0073  max mem: 31830
Epoch: [266]  [220/312]  eta: 0:00:53  lr: 0.000139  min_lr: 0.000139  loss: 3.4490 (3.2092)  weight_decay: 0.0500 (0.0500)  time: 0.5954  data: 0.0076  max mem: 31830
Epoch: [266]  [230/312]  eta: 0:00:46  lr: 0.000139  min_lr: 0.000139  loss: 3.4587 (3.2161)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0064  max mem: 31830
Epoch: [266]  [240/312]  eta: 0:00:41  lr: 0.000138  min_lr: 0.000138  loss: 3.3171 (3.2154)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0061  max mem: 31830
Epoch: [266]  [250/312]  eta: 0:00:35  lr: 0.000138  min_lr: 0.000138  loss: 3.3527 (3.2158)  weight_decay: 0.0500 (0.0500)  time: 0.4848  data: 0.0075  max mem: 31830
Epoch: [266]  [260/312]  eta: 0:00:29  lr: 0.000138  min_lr: 0.000138  loss: 3.0803 (3.2032)  weight_decay: 0.0500 (0.0500)  time: 0.5591  data: 0.0255  max mem: 31830
Epoch: [266]  [270/312]  eta: 0:00:24  lr: 0.000138  min_lr: 0.000138  loss: 3.2133 (3.2138)  weight_decay: 0.0500 (0.0500)  time: 0.6526  data: 0.0188  max mem: 31830
Epoch: [266]  [280/312]  eta: 0:00:18  lr: 0.000137  min_lr: 0.000137  loss: 3.4429 (3.2141)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0038  max mem: 31830
Epoch: [266]  [290/312]  eta: 0:00:12  lr: 0.000137  min_lr: 0.000137  loss: 3.3776 (3.2192)  weight_decay: 0.0500 (0.0500)  time: 0.5104  data: 0.0036  max mem: 31830
Epoch: [266]  [300/312]  eta: 0:00:06  lr: 0.000137  min_lr: 0.000137  loss: 3.3628 (3.2134)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0002  max mem: 31830
Epoch: [266]  [310/312]  eta: 0:00:01  lr: 0.000137  min_lr: 0.000137  loss: 3.1196 (3.2128)  weight_decay: 0.0500 (0.0500)  time: 0.4069  data: 0.0001  max mem: 31830
Epoch: [266]  [311/312]  eta: 0:00:00  lr: 0.000137  min_lr: 0.000137  loss: 3.1348 (3.2130)  weight_decay: 0.0500 (0.0500)  time: 0.4068  data: 0.0001  max mem: 31830
Epoch: [266] Total time: 0:02:54 (0.5605 s / it)
Averaged stats: lr: 0.000137  min_lr: 0.000137  loss: 3.1348 (3.2029)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8987 (0.8987)  acc1: 85.1562 (85.1562)  acc5: 96.8750 (96.8750)  time: 8.3898  data: 8.2224  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1856 (1.1154)  acc1: 78.7760 (77.9040)  acc5: 94.6615 (94.3520)  time: 1.0591  data: 0.9225  max mem: 31830
Test: Total time: 0:00:09 (1.0748 s / it)
* Acc@1 78.100 Acc@5 94.184 loss 1.114
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.10%
Epoch: [267]  [  0/312]  eta: 0:58:33  lr: 0.000136  min_lr: 0.000136  loss: 3.4520 (3.4520)  weight_decay: 0.0500 (0.0500)  time: 11.2613  data: 10.0400  max mem: 31830
Epoch: [267]  [ 10/312]  eta: 0:08:45  lr: 0.000136  min_lr: 0.000136  loss: 3.3587 (3.2926)  weight_decay: 0.0500 (0.0500)  time: 1.7412  data: 1.0274  max mem: 31830
Epoch: [267]  [ 20/312]  eta: 0:05:23  lr: 0.000136  min_lr: 0.000136  loss: 3.3587 (3.2541)  weight_decay: 0.0500 (0.0500)  time: 0.6015  data: 0.0634  max mem: 31830
Epoch: [267]  [ 30/312]  eta: 0:04:07  lr: 0.000136  min_lr: 0.000136  loss: 3.2209 (3.1311)  weight_decay: 0.0500 (0.0500)  time: 0.4042  data: 0.0008  max mem: 31830
Epoch: [267]  [ 40/312]  eta: 0:03:27  lr: 0.000135  min_lr: 0.000135  loss: 3.0027 (3.1501)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0009  max mem: 31830
Epoch: [267]  [ 50/312]  eta: 0:03:01  lr: 0.000135  min_lr: 0.000135  loss: 3.1157 (3.1536)  weight_decay: 0.0500 (0.0500)  time: 0.4008  data: 0.0013  max mem: 31830
Epoch: [267]  [ 60/312]  eta: 0:02:42  lr: 0.000135  min_lr: 0.000135  loss: 3.0791 (3.1316)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0015  max mem: 31830
Epoch: [267]  [ 70/312]  eta: 0:02:31  lr: 0.000135  min_lr: 0.000135  loss: 3.1561 (3.1346)  weight_decay: 0.0500 (0.0500)  time: 0.4538  data: 0.0261  max mem: 31830
Epoch: [267]  [ 80/312]  eta: 0:02:25  lr: 0.000134  min_lr: 0.000134  loss: 3.1739 (3.1118)  weight_decay: 0.0500 (0.0500)  time: 0.5730  data: 0.0385  max mem: 31830
Epoch: [267]  [ 90/312]  eta: 0:02:14  lr: 0.000134  min_lr: 0.000134  loss: 3.2873 (3.1300)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0417  max mem: 31830
Epoch: [267]  [100/312]  eta: 0:02:07  lr: 0.000134  min_lr: 0.000134  loss: 3.3602 (3.1292)  weight_decay: 0.0500 (0.0500)  time: 0.4978  data: 0.0836  max mem: 31830
Epoch: [267]  [110/312]  eta: 0:01:58  lr: 0.000134  min_lr: 0.000134  loss: 3.3164 (3.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0554  max mem: 31830
Epoch: [267]  [120/312]  eta: 0:01:52  lr: 0.000133  min_lr: 0.000133  loss: 3.3164 (3.1568)  weight_decay: 0.0500 (0.0500)  time: 0.4988  data: 0.0641  max mem: 31830
Epoch: [267]  [130/312]  eta: 0:01:47  lr: 0.000133  min_lr: 0.000133  loss: 3.2375 (3.1469)  weight_decay: 0.0500 (0.0500)  time: 0.6028  data: 0.1364  max mem: 31830
Epoch: [267]  [140/312]  eta: 0:01:39  lr: 0.000133  min_lr: 0.000133  loss: 2.8417 (3.1408)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0967  max mem: 31830
Epoch: [267]  [150/312]  eta: 0:01:33  lr: 0.000133  min_lr: 0.000133  loss: 3.1038 (3.1477)  weight_decay: 0.0500 (0.0500)  time: 0.5116  data: 0.1088  max mem: 31830
Epoch: [267]  [160/312]  eta: 0:01:28  lr: 0.000132  min_lr: 0.000132  loss: 3.4881 (3.1744)  weight_decay: 0.0500 (0.0500)  time: 0.6121  data: 0.1903  max mem: 31830
Epoch: [267]  [170/312]  eta: 0:01:21  lr: 0.000132  min_lr: 0.000132  loss: 3.4881 (3.1776)  weight_decay: 0.0500 (0.0500)  time: 0.5405  data: 0.1111  max mem: 31830
Epoch: [267]  [180/312]  eta: 0:01:15  lr: 0.000132  min_lr: 0.000132  loss: 3.3806 (3.1846)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0799  max mem: 31830
Epoch: [267]  [190/312]  eta: 0:01:09  lr: 0.000132  min_lr: 0.000132  loss: 3.2002 (3.1790)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.0890  max mem: 31830
Epoch: [267]  [200/312]  eta: 0:01:03  lr: 0.000131  min_lr: 0.000131  loss: 3.3656 (3.1902)  weight_decay: 0.0500 (0.0500)  time: 0.5215  data: 0.1158  max mem: 31830
Epoch: [267]  [210/312]  eta: 0:00:58  lr: 0.000131  min_lr: 0.000131  loss: 3.3444 (3.1823)  weight_decay: 0.0500 (0.0500)  time: 0.5966  data: 0.1724  max mem: 31830
Epoch: [267]  [220/312]  eta: 0:00:52  lr: 0.000131  min_lr: 0.000131  loss: 2.9290 (3.1742)  weight_decay: 0.0500 (0.0500)  time: 0.5168  data: 0.0992  max mem: 31830
Epoch: [267]  [230/312]  eta: 0:00:46  lr: 0.000131  min_lr: 0.000131  loss: 3.2779 (3.1795)  weight_decay: 0.0500 (0.0500)  time: 0.5256  data: 0.0886  max mem: 31830
Epoch: [267]  [240/312]  eta: 0:00:40  lr: 0.000130  min_lr: 0.000130  loss: 3.2779 (3.1729)  weight_decay: 0.0500 (0.0500)  time: 0.6014  data: 0.1299  max mem: 31830
Epoch: [267]  [250/312]  eta: 0:00:34  lr: 0.000130  min_lr: 0.000130  loss: 3.2354 (3.1751)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0830  max mem: 31830
Epoch: [267]  [260/312]  eta: 0:00:29  lr: 0.000130  min_lr: 0.000130  loss: 3.3693 (3.1821)  weight_decay: 0.0500 (0.0500)  time: 0.5154  data: 0.0892  max mem: 31830
Epoch: [267]  [270/312]  eta: 0:00:23  lr: 0.000130  min_lr: 0.000130  loss: 3.5010 (3.1850)  weight_decay: 0.0500 (0.0500)  time: 0.5517  data: 0.0907  max mem: 31830
Epoch: [267]  [280/312]  eta: 0:00:18  lr: 0.000129  min_lr: 0.000129  loss: 3.4274 (3.1871)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.1131  max mem: 31830
Epoch: [267]  [290/312]  eta: 0:00:12  lr: 0.000129  min_lr: 0.000129  loss: 3.3937 (3.1972)  weight_decay: 0.0500 (0.0500)  time: 0.5960  data: 0.1792  max mem: 31830
Epoch: [267]  [300/312]  eta: 0:00:06  lr: 0.000129  min_lr: 0.000129  loss: 3.3505 (3.1942)  weight_decay: 0.0500 (0.0500)  time: 0.4845  data: 0.0816  max mem: 31830
Epoch: [267]  [310/312]  eta: 0:00:01  lr: 0.000129  min_lr: 0.000129  loss: 3.4570 (3.2000)  weight_decay: 0.0500 (0.0500)  time: 0.3817  data: 0.0001  max mem: 31830
Epoch: [267]  [311/312]  eta: 0:00:00  lr: 0.000129  min_lr: 0.000129  loss: 3.4570 (3.2011)  weight_decay: 0.0500 (0.0500)  time: 0.3815  data: 0.0001  max mem: 31830
Epoch: [267] Total time: 0:02:53 (0.5562 s / it)
Averaged stats: lr: 0.000129  min_lr: 0.000129  loss: 3.4570 (3.1923)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.9148 (0.9148)  acc1: 85.1562 (85.1562)  acc5: 96.8750 (96.8750)  time: 8.0938  data: 7.9342  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2401 (1.1604)  acc1: 78.6458 (78.1600)  acc5: 94.7917 (94.3840)  time: 1.0836  data: 0.9495  max mem: 31830
Test: Total time: 0:00:09 (1.0933 s / it)
* Acc@1 78.090 Acc@5 94.268 loss 1.160
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.10%
Epoch: [268]  [  0/312]  eta: 1:05:19  lr: 0.000128  min_lr: 0.000128  loss: 2.8934 (2.8934)  weight_decay: 0.0500 (0.0500)  time: 12.5625  data: 12.1668  max mem: 31830
Epoch: [268]  [ 10/312]  eta: 0:09:11  lr: 0.000128  min_lr: 0.000128  loss: 3.4132 (3.3458)  weight_decay: 0.0500 (0.0500)  time: 1.8262  data: 1.1065  max mem: 31830
Epoch: [268]  [ 20/312]  eta: 0:05:41  lr: 0.000128  min_lr: 0.000128  loss: 3.3746 (3.2365)  weight_decay: 0.0500 (0.0500)  time: 0.6002  data: 0.0301  max mem: 31830
Epoch: [268]  [ 30/312]  eta: 0:04:19  lr: 0.000128  min_lr: 0.000128  loss: 3.1077 (3.1883)  weight_decay: 0.0500 (0.0500)  time: 0.4230  data: 0.0302  max mem: 31830
Epoch: [268]  [ 40/312]  eta: 0:03:35  lr: 0.000127  min_lr: 0.000127  loss: 3.1077 (3.1826)  weight_decay: 0.0500 (0.0500)  time: 0.3988  data: 0.0008  max mem: 31830
Epoch: [268]  [ 50/312]  eta: 0:03:07  lr: 0.000127  min_lr: 0.000127  loss: 3.4024 (3.2204)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0008  max mem: 31830
Epoch: [268]  [ 60/312]  eta: 0:02:47  lr: 0.000127  min_lr: 0.000127  loss: 3.4305 (3.2525)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0011  max mem: 31830
Epoch: [268]  [ 70/312]  eta: 0:02:31  lr: 0.000127  min_lr: 0.000127  loss: 3.3232 (3.2500)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0010  max mem: 31830
Epoch: [268]  [ 80/312]  eta: 0:02:26  lr: 0.000126  min_lr: 0.000126  loss: 3.3264 (3.2592)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0320  max mem: 31830
Epoch: [268]  [ 90/312]  eta: 0:02:14  lr: 0.000126  min_lr: 0.000126  loss: 3.3301 (3.2310)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0390  max mem: 31830
Epoch: [268]  [100/312]  eta: 0:02:09  lr: 0.000126  min_lr: 0.000126  loss: 3.1379 (3.2194)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0412  max mem: 31830
Epoch: [268]  [110/312]  eta: 0:02:02  lr: 0.000126  min_lr: 0.000126  loss: 3.1379 (3.2074)  weight_decay: 0.0500 (0.0500)  time: 0.6088  data: 0.0347  max mem: 31830
Epoch: [268]  [120/312]  eta: 0:01:53  lr: 0.000125  min_lr: 0.000125  loss: 3.1142 (3.1995)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0355  max mem: 31830
Epoch: [268]  [130/312]  eta: 0:01:48  lr: 0.000125  min_lr: 0.000125  loss: 3.1299 (3.2125)  weight_decay: 0.0500 (0.0500)  time: 0.5506  data: 0.0674  max mem: 31830
Epoch: [268]  [140/312]  eta: 0:01:40  lr: 0.000125  min_lr: 0.000125  loss: 3.4000 (3.2190)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0395  max mem: 31830
Epoch: [268]  [150/312]  eta: 0:01:35  lr: 0.000125  min_lr: 0.000125  loss: 3.3602 (3.2167)  weight_decay: 0.0500 (0.0500)  time: 0.5169  data: 0.0306  max mem: 31830
Epoch: [268]  [160/312]  eta: 0:01:29  lr: 0.000124  min_lr: 0.000124  loss: 3.2968 (3.2195)  weight_decay: 0.0500 (0.0500)  time: 0.6125  data: 0.0327  max mem: 31830
Epoch: [268]  [170/312]  eta: 0:01:22  lr: 0.000124  min_lr: 0.000124  loss: 3.2771 (3.2248)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0361  max mem: 31830
Epoch: [268]  [180/312]  eta: 0:01:16  lr: 0.000124  min_lr: 0.000124  loss: 3.1627 (3.2188)  weight_decay: 0.0500 (0.0500)  time: 0.5383  data: 0.0430  max mem: 31830
Epoch: [268]  [190/312]  eta: 0:01:11  lr: 0.000124  min_lr: 0.000124  loss: 3.4088 (3.2228)  weight_decay: 0.0500 (0.0500)  time: 0.6172  data: 0.0238  max mem: 31830
Epoch: [268]  [200/312]  eta: 0:01:04  lr: 0.000123  min_lr: 0.000123  loss: 3.5108 (3.2358)  weight_decay: 0.0500 (0.0500)  time: 0.5288  data: 0.0382  max mem: 31830
Epoch: [268]  [210/312]  eta: 0:00:59  lr: 0.000123  min_lr: 0.000123  loss: 3.4359 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 0.5620  data: 0.0712  max mem: 31830
Epoch: [268]  [220/312]  eta: 0:00:52  lr: 0.000123  min_lr: 0.000123  loss: 3.1259 (3.2219)  weight_decay: 0.0500 (0.0500)  time: 0.5345  data: 0.0419  max mem: 31830
Epoch: [268]  [230/312]  eta: 0:00:47  lr: 0.000123  min_lr: 0.000123  loss: 3.1045 (3.2269)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0384  max mem: 31830
Epoch: [268]  [240/312]  eta: 0:00:41  lr: 0.000123  min_lr: 0.000123  loss: 3.3674 (3.2197)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.0380  max mem: 31830
Epoch: [268]  [250/312]  eta: 0:00:35  lr: 0.000122  min_lr: 0.000122  loss: 3.3256 (3.2135)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.0446  max mem: 31830
Epoch: [268]  [260/312]  eta: 0:00:29  lr: 0.000122  min_lr: 0.000122  loss: 3.3882 (3.2194)  weight_decay: 0.0500 (0.0500)  time: 0.5674  data: 0.0907  max mem: 31830
Epoch: [268]  [270/312]  eta: 0:00:24  lr: 0.000122  min_lr: 0.000122  loss: 3.4593 (3.2237)  weight_decay: 0.0500 (0.0500)  time: 0.5945  data: 0.0468  max mem: 31830
Epoch: [268]  [280/312]  eta: 0:00:18  lr: 0.000122  min_lr: 0.000122  loss: 3.3139 (3.2234)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0480  max mem: 31830
Epoch: [268]  [290/312]  eta: 0:00:12  lr: 0.000121  min_lr: 0.000121  loss: 3.0889 (3.2126)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.0805  max mem: 31830
Epoch: [268]  [300/312]  eta: 0:00:06  lr: 0.000121  min_lr: 0.000121  loss: 2.9456 (3.2049)  weight_decay: 0.0500 (0.0500)  time: 0.5023  data: 0.0329  max mem: 31830
Epoch: [268]  [310/312]  eta: 0:00:01  lr: 0.000121  min_lr: 0.000121  loss: 3.0677 (3.2027)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [268]  [311/312]  eta: 0:00:00  lr: 0.000121  min_lr: 0.000121  loss: 3.0677 (3.2036)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [268] Total time: 0:02:55 (0.5621 s / it)
Averaged stats: lr: 0.000121  min_lr: 0.000121  loss: 3.0677 (3.1892)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.8612 (0.8612)  acc1: 84.5052 (84.5052)  acc5: 97.1354 (97.1354)  time: 8.0304  data: 7.8634  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1413 (1.0641)  acc1: 78.2552 (78.1120)  acc5: 94.4010 (94.3200)  time: 1.1053  data: 0.9675  max mem: 31830
Test: Total time: 0:00:10 (1.1206 s / it)
* Acc@1 78.246 Acc@5 94.234 loss 1.060
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.25%
Epoch: [269]  [  0/312]  eta: 1:01:14  lr: 0.000121  min_lr: 0.000121  loss: 3.3169 (3.3169)  weight_decay: 0.0500 (0.0500)  time: 11.7762  data: 11.3212  max mem: 31830
Epoch: [269]  [ 10/312]  eta: 0:08:06  lr: 0.000120  min_lr: 0.000120  loss: 3.4249 (3.3418)  weight_decay: 0.0500 (0.0500)  time: 1.6120  data: 1.0302  max mem: 31830
Epoch: [269]  [ 20/312]  eta: 0:05:27  lr: 0.000120  min_lr: 0.000120  loss: 3.2684 (3.1403)  weight_decay: 0.0500 (0.0500)  time: 0.5881  data: 0.0943  max mem: 31830
Epoch: [269]  [ 30/312]  eta: 0:04:09  lr: 0.000120  min_lr: 0.000120  loss: 3.0868 (3.1202)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0942  max mem: 31830
Epoch: [269]  [ 40/312]  eta: 0:03:30  lr: 0.000120  min_lr: 0.000120  loss: 3.2084 (3.1132)  weight_decay: 0.0500 (0.0500)  time: 0.4063  data: 0.0161  max mem: 31830
Epoch: [269]  [ 50/312]  eta: 0:03:08  lr: 0.000120  min_lr: 0.000120  loss: 3.2406 (3.1010)  weight_decay: 0.0500 (0.0500)  time: 0.4655  data: 0.0722  max mem: 31830
Epoch: [269]  [ 60/312]  eta: 0:02:47  lr: 0.000119  min_lr: 0.000119  loss: 3.1643 (3.1155)  weight_decay: 0.0500 (0.0500)  time: 0.4501  data: 0.0571  max mem: 31830
Epoch: [269]  [ 70/312]  eta: 0:02:37  lr: 0.000119  min_lr: 0.000119  loss: 3.2294 (3.1380)  weight_decay: 0.0500 (0.0500)  time: 0.4761  data: 0.0855  max mem: 31830
Epoch: [269]  [ 80/312]  eta: 0:02:30  lr: 0.000119  min_lr: 0.000119  loss: 3.2473 (3.1450)  weight_decay: 0.0500 (0.0500)  time: 0.6006  data: 0.2087  max mem: 31830
Epoch: [269]  [ 90/312]  eta: 0:02:18  lr: 0.000119  min_lr: 0.000119  loss: 3.4789 (3.1818)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.1244  max mem: 31830
Epoch: [269]  [100/312]  eta: 0:02:10  lr: 0.000118  min_lr: 0.000118  loss: 3.3867 (3.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4843  data: 0.0865  max mem: 31830
Epoch: [269]  [110/312]  eta: 0:02:00  lr: 0.000118  min_lr: 0.000118  loss: 3.3339 (3.1770)  weight_decay: 0.0500 (0.0500)  time: 0.4826  data: 0.0865  max mem: 31830
Epoch: [269]  [120/312]  eta: 0:01:55  lr: 0.000118  min_lr: 0.000118  loss: 3.4585 (3.1912)  weight_decay: 0.0500 (0.0500)  time: 0.5100  data: 0.1171  max mem: 31830
Epoch: [269]  [130/312]  eta: 0:01:50  lr: 0.000118  min_lr: 0.000118  loss: 3.2234 (3.1859)  weight_decay: 0.0500 (0.0500)  time: 0.6722  data: 0.2805  max mem: 31830
Epoch: [269]  [140/312]  eta: 0:01:42  lr: 0.000117  min_lr: 0.000117  loss: 3.2234 (3.1756)  weight_decay: 0.0500 (0.0500)  time: 0.5594  data: 0.1644  max mem: 31830
Epoch: [269]  [150/312]  eta: 0:01:36  lr: 0.000117  min_lr: 0.000117  loss: 3.2091 (3.1817)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.1290  max mem: 31830
Epoch: [269]  [160/312]  eta: 0:01:31  lr: 0.000117  min_lr: 0.000117  loss: 3.4687 (3.1935)  weight_decay: 0.0500 (0.0500)  time: 0.6406  data: 0.2449  max mem: 31830
Epoch: [269]  [170/312]  eta: 0:01:23  lr: 0.000117  min_lr: 0.000117  loss: 3.4722 (3.2107)  weight_decay: 0.0500 (0.0500)  time: 0.5142  data: 0.1168  max mem: 31830
Epoch: [269]  [180/312]  eta: 0:01:17  lr: 0.000116  min_lr: 0.000116  loss: 3.2306 (3.2049)  weight_decay: 0.0500 (0.0500)  time: 0.4717  data: 0.0761  max mem: 31830
Epoch: [269]  [190/312]  eta: 0:01:10  lr: 0.000116  min_lr: 0.000116  loss: 3.0707 (3.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4853  data: 0.0761  max mem: 31830
Epoch: [269]  [200/312]  eta: 0:01:04  lr: 0.000116  min_lr: 0.000116  loss: 3.4328 (3.2054)  weight_decay: 0.0500 (0.0500)  time: 0.4971  data: 0.0887  max mem: 31830
Epoch: [269]  [210/312]  eta: 0:00:59  lr: 0.000116  min_lr: 0.000116  loss: 3.3010 (3.2016)  weight_decay: 0.0500 (0.0500)  time: 0.6149  data: 0.1697  max mem: 31830
Epoch: [269]  [220/312]  eta: 0:00:53  lr: 0.000115  min_lr: 0.000115  loss: 3.2532 (3.2009)  weight_decay: 0.0500 (0.0500)  time: 0.5732  data: 0.0817  max mem: 31830
Epoch: [269]  [230/312]  eta: 0:00:47  lr: 0.000115  min_lr: 0.000115  loss: 3.2378 (3.2032)  weight_decay: 0.0500 (0.0500)  time: 0.5089  data: 0.0697  max mem: 31830
Epoch: [269]  [240/312]  eta: 0:00:41  lr: 0.000115  min_lr: 0.000115  loss: 3.2378 (3.1994)  weight_decay: 0.0500 (0.0500)  time: 0.5802  data: 0.1371  max mem: 31830
Epoch: [269]  [250/312]  eta: 0:00:35  lr: 0.000115  min_lr: 0.000115  loss: 3.2994 (3.2063)  weight_decay: 0.0500 (0.0500)  time: 0.5106  data: 0.0681  max mem: 31830
Epoch: [269]  [260/312]  eta: 0:00:29  lr: 0.000114  min_lr: 0.000114  loss: 3.3814 (3.2065)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0468  max mem: 31830
Epoch: [269]  [270/312]  eta: 0:00:23  lr: 0.000114  min_lr: 0.000114  loss: 3.1344 (3.2034)  weight_decay: 0.0500 (0.0500)  time: 0.5875  data: 0.0468  max mem: 31830
Epoch: [269]  [280/312]  eta: 0:00:18  lr: 0.000114  min_lr: 0.000114  loss: 3.3336 (3.2092)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0577  max mem: 31830
Epoch: [269]  [290/312]  eta: 0:00:12  lr: 0.000114  min_lr: 0.000114  loss: 3.2173 (3.1980)  weight_decay: 0.0500 (0.0500)  time: 0.5453  data: 0.0835  max mem: 31830
Epoch: [269]  [300/312]  eta: 0:00:06  lr: 0.000113  min_lr: 0.000113  loss: 3.1580 (3.2029)  weight_decay: 0.0500 (0.0500)  time: 0.4847  data: 0.0262  max mem: 31830
Epoch: [269]  [310/312]  eta: 0:00:01  lr: 0.000113  min_lr: 0.000113  loss: 3.4159 (3.2052)  weight_decay: 0.0500 (0.0500)  time: 0.3821  data: 0.0001  max mem: 31830
Epoch: [269]  [311/312]  eta: 0:00:00  lr: 0.000113  min_lr: 0.000113  loss: 3.4159 (3.2077)  weight_decay: 0.0500 (0.0500)  time: 0.3821  data: 0.0001  max mem: 31830
Epoch: [269] Total time: 0:02:54 (0.5601 s / it)
Averaged stats: lr: 0.000113  min_lr: 0.000113  loss: 3.4159 (3.1950)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.9401 (0.9401)  acc1: 84.6354 (84.6354)  acc5: 97.1354 (97.1354)  time: 8.6667  data: 8.5066  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2317 (1.1621)  acc1: 79.1667 (78.2720)  acc5: 94.5312 (94.4000)  time: 1.0848  data: 0.9453  max mem: 31830
Test: Total time: 0:00:09 (1.0959 s / it)
* Acc@1 78.228 Acc@5 94.296 loss 1.162
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.25%
Epoch: [270]  [  0/312]  eta: 0:59:18  lr: 0.000113  min_lr: 0.000113  loss: 3.4103 (3.4103)  weight_decay: 0.0500 (0.0500)  time: 11.4042  data: 11.0040  max mem: 31830
Epoch: [270]  [ 10/312]  eta: 0:08:02  lr: 0.000113  min_lr: 0.000113  loss: 3.1872 (3.1867)  weight_decay: 0.0500 (0.0500)  time: 1.5993  data: 1.0014  max mem: 31830
Epoch: [270]  [ 20/312]  eta: 0:05:21  lr: 0.000113  min_lr: 0.000113  loss: 3.1597 (3.1153)  weight_decay: 0.0500 (0.0500)  time: 0.5856  data: 0.0827  max mem: 31830
Epoch: [270]  [ 30/312]  eta: 0:04:06  lr: 0.000112  min_lr: 0.000112  loss: 3.1597 (3.1365)  weight_decay: 0.0500 (0.0500)  time: 0.4741  data: 0.0825  max mem: 31830
Epoch: [270]  [ 40/312]  eta: 0:03:26  lr: 0.000112  min_lr: 0.000112  loss: 3.2800 (3.1648)  weight_decay: 0.0500 (0.0500)  time: 0.3978  data: 0.0015  max mem: 31830
Epoch: [270]  [ 50/312]  eta: 0:03:15  lr: 0.000112  min_lr: 0.000112  loss: 3.3842 (3.1839)  weight_decay: 0.0500 (0.0500)  time: 0.5508  data: 0.0371  max mem: 31830
Epoch: [270]  [ 60/312]  eta: 0:02:53  lr: 0.000112  min_lr: 0.000112  loss: 3.3514 (3.1687)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0367  max mem: 31830
Epoch: [270]  [ 70/312]  eta: 0:02:43  lr: 0.000112  min_lr: 0.000112  loss: 3.1490 (3.1914)  weight_decay: 0.0500 (0.0500)  time: 0.4937  data: 0.0141  max mem: 31830
Epoch: [270]  [ 80/312]  eta: 0:02:32  lr: 0.000111  min_lr: 0.000111  loss: 3.2992 (3.1930)  weight_decay: 0.0500 (0.0500)  time: 0.5604  data: 0.0351  max mem: 31830
Epoch: [270]  [ 90/312]  eta: 0:02:21  lr: 0.000111  min_lr: 0.000111  loss: 3.3840 (3.2372)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0220  max mem: 31830
Epoch: [270]  [100/312]  eta: 0:02:13  lr: 0.000111  min_lr: 0.000111  loss: 3.3887 (3.2300)  weight_decay: 0.0500 (0.0500)  time: 0.5217  data: 0.0068  max mem: 31830
Epoch: [270]  [110/312]  eta: 0:02:03  lr: 0.000111  min_lr: 0.000111  loss: 3.2813 (3.2176)  weight_decay: 0.0500 (0.0500)  time: 0.4771  data: 0.0068  max mem: 31830
Epoch: [270]  [120/312]  eta: 0:01:56  lr: 0.000110  min_lr: 0.000110  loss: 3.2117 (3.2199)  weight_decay: 0.0500 (0.0500)  time: 0.4774  data: 0.0643  max mem: 31830
Epoch: [270]  [130/312]  eta: 0:01:51  lr: 0.000110  min_lr: 0.000110  loss: 3.2783 (3.2229)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.1129  max mem: 31830
Epoch: [270]  [140/312]  eta: 0:01:42  lr: 0.000110  min_lr: 0.000110  loss: 3.3150 (3.2047)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0497  max mem: 31830
Epoch: [270]  [150/312]  eta: 0:01:37  lr: 0.000110  min_lr: 0.000110  loss: 3.3501 (3.2111)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0307  max mem: 31830
Epoch: [270]  [160/312]  eta: 0:01:30  lr: 0.000109  min_lr: 0.000109  loss: 3.3466 (3.2049)  weight_decay: 0.0500 (0.0500)  time: 0.5814  data: 0.0516  max mem: 31830
Epoch: [270]  [170/312]  eta: 0:01:23  lr: 0.000109  min_lr: 0.000109  loss: 3.0935 (3.2049)  weight_decay: 0.0500 (0.0500)  time: 0.5209  data: 0.0228  max mem: 31830
Epoch: [270]  [180/312]  eta: 0:01:18  lr: 0.000109  min_lr: 0.000109  loss: 3.4630 (3.2200)  weight_decay: 0.0500 (0.0500)  time: 0.5730  data: 0.0096  max mem: 31830
Epoch: [270]  [190/312]  eta: 0:01:10  lr: 0.000109  min_lr: 0.000109  loss: 3.3870 (3.2053)  weight_decay: 0.0500 (0.0500)  time: 0.5036  data: 0.0089  max mem: 31830
Epoch: [270]  [200/312]  eta: 0:01:04  lr: 0.000109  min_lr: 0.000109  loss: 3.1469 (3.1989)  weight_decay: 0.0500 (0.0500)  time: 0.4700  data: 0.0376  max mem: 31830
Epoch: [270]  [210/312]  eta: 0:00:59  lr: 0.000108  min_lr: 0.000108  loss: 3.2336 (3.1905)  weight_decay: 0.0500 (0.0500)  time: 0.6252  data: 0.0651  max mem: 31830
Epoch: [270]  [220/312]  eta: 0:00:53  lr: 0.000108  min_lr: 0.000108  loss: 3.2376 (3.1921)  weight_decay: 0.0500 (0.0500)  time: 0.5545  data: 0.0284  max mem: 31830
Epoch: [270]  [230/312]  eta: 0:00:47  lr: 0.000108  min_lr: 0.000108  loss: 3.3117 (3.1944)  weight_decay: 0.0500 (0.0500)  time: 0.4991  data: 0.0287  max mem: 31830
Epoch: [270]  [240/312]  eta: 0:00:41  lr: 0.000108  min_lr: 0.000108  loss: 3.4053 (3.1952)  weight_decay: 0.0500 (0.0500)  time: 0.5313  data: 0.0648  max mem: 31830
Epoch: [270]  [250/312]  eta: 0:00:35  lr: 0.000107  min_lr: 0.000107  loss: 3.2403 (3.1937)  weight_decay: 0.0500 (0.0500)  time: 0.4825  data: 0.0369  max mem: 31830
Epoch: [270]  [260/312]  eta: 0:00:29  lr: 0.000107  min_lr: 0.000107  loss: 3.4240 (3.2071)  weight_decay: 0.0500 (0.0500)  time: 0.5438  data: 0.0419  max mem: 31830
Epoch: [270]  [270/312]  eta: 0:00:23  lr: 0.000107  min_lr: 0.000107  loss: 3.5000 (3.2110)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0420  max mem: 31830
Epoch: [270]  [280/312]  eta: 0:00:18  lr: 0.000107  min_lr: 0.000107  loss: 3.0714 (3.1942)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0673  max mem: 31830
Epoch: [270]  [290/312]  eta: 0:00:12  lr: 0.000106  min_lr: 0.000106  loss: 3.0124 (3.1986)  weight_decay: 0.0500 (0.0500)  time: 0.6055  data: 0.0719  max mem: 31830
Epoch: [270]  [300/312]  eta: 0:00:06  lr: 0.000106  min_lr: 0.000106  loss: 3.2256 (3.1923)  weight_decay: 0.0500 (0.0500)  time: 0.4740  data: 0.0051  max mem: 31830
Epoch: [270]  [310/312]  eta: 0:00:01  lr: 0.000106  min_lr: 0.000106  loss: 3.2216 (3.1908)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [270]  [311/312]  eta: 0:00:00  lr: 0.000106  min_lr: 0.000106  loss: 3.0758 (3.1904)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [270] Total time: 0:02:54 (0.5591 s / it)
Averaged stats: lr: 0.000106  min_lr: 0.000106  loss: 3.0758 (3.1877)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8537 (0.8537)  acc1: 85.1562 (85.1562)  acc5: 97.3958 (97.3958)  time: 8.4491  data: 8.2816  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1521 (1.0906)  acc1: 78.3854 (78.3520)  acc5: 94.6615 (94.4160)  time: 1.0817  data: 0.9466  max mem: 31830
Test: Total time: 0:00:09 (1.0916 s / it)
* Acc@1 78.282 Acc@5 94.338 loss 1.089
Accuracy of the model on the 50000 test images: 78.3%
Max accuracy: 78.28%
Epoch: [271]  [  0/312]  eta: 1:00:50  lr: 0.000106  min_lr: 0.000106  loss: 2.6496 (2.6496)  weight_decay: 0.0500 (0.0500)  time: 11.7010  data: 11.3021  max mem: 31830
Epoch: [271]  [ 10/312]  eta: 0:08:00  lr: 0.000106  min_lr: 0.000106  loss: 3.0717 (3.1112)  weight_decay: 0.0500 (0.0500)  time: 1.5926  data: 1.0807  max mem: 31830
Epoch: [271]  [ 20/312]  eta: 0:05:25  lr: 0.000105  min_lr: 0.000105  loss: 3.3824 (3.1397)  weight_decay: 0.0500 (0.0500)  time: 0.5842  data: 0.1178  max mem: 31830
Epoch: [271]  [ 30/312]  eta: 0:04:08  lr: 0.000105  min_lr: 0.000105  loss: 3.4101 (3.1434)  weight_decay: 0.0500 (0.0500)  time: 0.4909  data: 0.0889  max mem: 31830
Epoch: [271]  [ 40/312]  eta: 0:03:27  lr: 0.000105  min_lr: 0.000105  loss: 3.3886 (3.1640)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0008  max mem: 31830
Epoch: [271]  [ 50/312]  eta: 0:03:06  lr: 0.000105  min_lr: 0.000105  loss: 3.3119 (3.1954)  weight_decay: 0.0500 (0.0500)  time: 0.4497  data: 0.0490  max mem: 31830
Epoch: [271]  [ 60/312]  eta: 0:02:46  lr: 0.000105  min_lr: 0.000105  loss: 3.2296 (3.1891)  weight_decay: 0.0500 (0.0500)  time: 0.4475  data: 0.0490  max mem: 31830
Epoch: [271]  [ 70/312]  eta: 0:02:36  lr: 0.000104  min_lr: 0.000104  loss: 3.0548 (3.1557)  weight_decay: 0.0500 (0.0500)  time: 0.4797  data: 0.0790  max mem: 31830
Epoch: [271]  [ 80/312]  eta: 0:02:28  lr: 0.000104  min_lr: 0.000104  loss: 3.3108 (3.1752)  weight_decay: 0.0500 (0.0500)  time: 0.5779  data: 0.1433  max mem: 31830
Epoch: [271]  [ 90/312]  eta: 0:02:16  lr: 0.000104  min_lr: 0.000104  loss: 3.4386 (3.1895)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0804  max mem: 31830
Epoch: [271]  [100/312]  eta: 0:02:11  lr: 0.000104  min_lr: 0.000104  loss: 3.3913 (3.1776)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.1225  max mem: 31830
Epoch: [271]  [110/312]  eta: 0:02:00  lr: 0.000103  min_lr: 0.000103  loss: 3.3392 (3.1888)  weight_decay: 0.0500 (0.0500)  time: 0.5153  data: 0.1073  max mem: 31830
Epoch: [271]  [120/312]  eta: 0:01:56  lr: 0.000103  min_lr: 0.000103  loss: 3.4378 (3.2026)  weight_decay: 0.0500 (0.0500)  time: 0.5450  data: 0.1078  max mem: 31830
Epoch: [271]  [130/312]  eta: 0:01:49  lr: 0.000103  min_lr: 0.000103  loss: 3.4642 (3.2354)  weight_decay: 0.0500 (0.0500)  time: 0.6241  data: 0.1305  max mem: 31830
Epoch: [271]  [140/312]  eta: 0:01:41  lr: 0.000103  min_lr: 0.000103  loss: 3.5847 (3.2410)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.0522  max mem: 31830
Epoch: [271]  [150/312]  eta: 0:01:36  lr: 0.000102  min_lr: 0.000102  loss: 3.3396 (3.2387)  weight_decay: 0.0500 (0.0500)  time: 0.5409  data: 0.0902  max mem: 31830
Epoch: [271]  [160/312]  eta: 0:01:29  lr: 0.000102  min_lr: 0.000102  loss: 3.3587 (3.2427)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0615  max mem: 31830
Epoch: [271]  [170/312]  eta: 0:01:22  lr: 0.000102  min_lr: 0.000102  loss: 3.5025 (3.2513)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0559  max mem: 31830
Epoch: [271]  [180/312]  eta: 0:01:18  lr: 0.000102  min_lr: 0.000102  loss: 3.0122 (3.2292)  weight_decay: 0.0500 (0.0500)  time: 0.6278  data: 0.1013  max mem: 31830
Epoch: [271]  [190/312]  eta: 0:01:10  lr: 0.000102  min_lr: 0.000102  loss: 3.0773 (3.2386)  weight_decay: 0.0500 (0.0500)  time: 0.5693  data: 0.0462  max mem: 31830
Epoch: [271]  [200/312]  eta: 0:01:04  lr: 0.000101  min_lr: 0.000101  loss: 3.3235 (3.2363)  weight_decay: 0.0500 (0.0500)  time: 0.4564  data: 0.0160  max mem: 31830
Epoch: [271]  [210/312]  eta: 0:00:59  lr: 0.000101  min_lr: 0.000101  loss: 3.2022 (3.2282)  weight_decay: 0.0500 (0.0500)  time: 0.5623  data: 0.0685  max mem: 31830
Epoch: [271]  [220/312]  eta: 0:00:52  lr: 0.000101  min_lr: 0.000101  loss: 3.0463 (3.2235)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0539  max mem: 31830
Epoch: [271]  [230/312]  eta: 0:00:47  lr: 0.000101  min_lr: 0.000101  loss: 3.2730 (3.2172)  weight_decay: 0.0500 (0.0500)  time: 0.5085  data: 0.0675  max mem: 31830
Epoch: [271]  [240/312]  eta: 0:00:40  lr: 0.000100  min_lr: 0.000100  loss: 3.2965 (3.2172)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0819  max mem: 31830
Epoch: [271]  [250/312]  eta: 0:00:35  lr: 0.000100  min_lr: 0.000100  loss: 3.4462 (3.2202)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.0618  max mem: 31830
Epoch: [271]  [260/312]  eta: 0:00:29  lr: 0.000100  min_lr: 0.000100  loss: 3.4839 (3.2239)  weight_decay: 0.0500 (0.0500)  time: 0.6246  data: 0.0839  max mem: 31830
Epoch: [271]  [270/312]  eta: 0:00:23  lr: 0.000100  min_lr: 0.000100  loss: 3.5019 (3.2237)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0379  max mem: 31830
Epoch: [271]  [280/312]  eta: 0:00:18  lr: 0.000100  min_lr: 0.000100  loss: 3.4015 (3.2214)  weight_decay: 0.0500 (0.0500)  time: 0.4777  data: 0.0339  max mem: 31830
Epoch: [271]  [290/312]  eta: 0:00:12  lr: 0.000099  min_lr: 0.000099  loss: 3.4068 (3.2285)  weight_decay: 0.0500 (0.0500)  time: 0.5581  data: 0.1199  max mem: 31830
Epoch: [271]  [300/312]  eta: 0:00:06  lr: 0.000099  min_lr: 0.000099  loss: 3.4504 (3.2307)  weight_decay: 0.0500 (0.0500)  time: 0.4710  data: 0.0865  max mem: 31830
Epoch: [271]  [310/312]  eta: 0:00:01  lr: 0.000099  min_lr: 0.000099  loss: 3.3288 (3.2332)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [271]  [311/312]  eta: 0:00:00  lr: 0.000099  min_lr: 0.000099  loss: 3.3288 (3.2341)  weight_decay: 0.0500 (0.0500)  time: 0.3808  data: 0.0001  max mem: 31830
Epoch: [271] Total time: 0:02:53 (0.5574 s / it)
Averaged stats: lr: 0.000099  min_lr: 0.000099  loss: 3.3288 (3.2007)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.9195 (0.9195)  acc1: 85.2865 (85.2865)  acc5: 97.1354 (97.1354)  time: 8.4322  data: 8.2645  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2307 (1.1464)  acc1: 78.1250 (78.1120)  acc5: 95.0521 (94.4960)  time: 1.0759  data: 0.9409  max mem: 31830
Test: Total time: 0:00:09 (1.0914 s / it)
* Acc@1 78.392 Acc@5 94.306 loss 1.146
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.39%
Epoch: [272]  [  0/312]  eta: 1:01:51  lr: 0.000099  min_lr: 0.000099  loss: 3.1276 (3.1276)  weight_decay: 0.0500 (0.0500)  time: 11.8962  data: 11.4800  max mem: 31830
Epoch: [272]  [ 10/312]  eta: 0:07:58  lr: 0.000099  min_lr: 0.000099  loss: 2.8999 (2.8840)  weight_decay: 0.0500 (0.0500)  time: 1.5853  data: 1.0442  max mem: 31830
Epoch: [272]  [ 20/312]  eta: 0:05:12  lr: 0.000098  min_lr: 0.000098  loss: 3.0147 (3.0810)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0434  max mem: 31830
Epoch: [272]  [ 30/312]  eta: 0:04:00  lr: 0.000098  min_lr: 0.000098  loss: 3.3161 (3.1339)  weight_decay: 0.0500 (0.0500)  time: 0.4521  data: 0.0436  max mem: 31830
Epoch: [272]  [ 40/312]  eta: 0:03:23  lr: 0.000098  min_lr: 0.000098  loss: 3.2018 (3.1030)  weight_decay: 0.0500 (0.0500)  time: 0.4111  data: 0.0146  max mem: 31830
Epoch: [272]  [ 50/312]  eta: 0:03:09  lr: 0.000098  min_lr: 0.000098  loss: 3.2352 (3.1682)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0782  max mem: 31830
Epoch: [272]  [ 60/312]  eta: 0:02:50  lr: 0.000098  min_lr: 0.000098  loss: 3.4422 (3.2030)  weight_decay: 0.0500 (0.0500)  time: 0.5284  data: 0.0828  max mem: 31830
Epoch: [272]  [ 70/312]  eta: 0:02:41  lr: 0.000097  min_lr: 0.000097  loss: 3.3705 (3.2118)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0702  max mem: 31830
Epoch: [272]  [ 80/312]  eta: 0:02:30  lr: 0.000097  min_lr: 0.000097  loss: 3.3565 (3.2177)  weight_decay: 0.0500 (0.0500)  time: 0.5619  data: 0.0725  max mem: 31830
Epoch: [272]  [ 90/312]  eta: 0:02:22  lr: 0.000097  min_lr: 0.000097  loss: 3.3791 (3.2238)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0833  max mem: 31830
Epoch: [272]  [100/312]  eta: 0:02:15  lr: 0.000097  min_lr: 0.000097  loss: 3.3791 (3.2161)  weight_decay: 0.0500 (0.0500)  time: 0.6077  data: 0.1151  max mem: 31830
Epoch: [272]  [110/312]  eta: 0:02:04  lr: 0.000096  min_lr: 0.000096  loss: 3.2767 (3.2207)  weight_decay: 0.0500 (0.0500)  time: 0.5224  data: 0.0533  max mem: 31830
Epoch: [272]  [120/312]  eta: 0:01:58  lr: 0.000096  min_lr: 0.000096  loss: 3.2603 (3.2173)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0485  max mem: 31830
Epoch: [272]  [130/312]  eta: 0:01:51  lr: 0.000096  min_lr: 0.000096  loss: 3.1229 (3.1995)  weight_decay: 0.0500 (0.0500)  time: 0.5647  data: 0.0622  max mem: 31830
Epoch: [272]  [140/312]  eta: 0:01:43  lr: 0.000096  min_lr: 0.000096  loss: 3.2172 (3.2096)  weight_decay: 0.0500 (0.0500)  time: 0.4924  data: 0.0535  max mem: 31830
Epoch: [272]  [150/312]  eta: 0:01:36  lr: 0.000096  min_lr: 0.000096  loss: 3.2629 (3.1912)  weight_decay: 0.0500 (0.0500)  time: 0.5102  data: 0.1168  max mem: 31830
Epoch: [272]  [160/312]  eta: 0:01:30  lr: 0.000095  min_lr: 0.000095  loss: 3.1444 (3.1928)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.1682  max mem: 31830
Epoch: [272]  [170/312]  eta: 0:01:23  lr: 0.000095  min_lr: 0.000095  loss: 3.2827 (3.1921)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0993  max mem: 31830
Epoch: [272]  [180/312]  eta: 0:01:17  lr: 0.000095  min_lr: 0.000095  loss: 3.3357 (3.1990)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.1376  max mem: 31830
Epoch: [272]  [190/312]  eta: 0:01:10  lr: 0.000095  min_lr: 0.000095  loss: 3.2156 (3.1889)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.1294  max mem: 31830
Epoch: [272]  [200/312]  eta: 0:01:05  lr: 0.000094  min_lr: 0.000094  loss: 3.1030 (3.1794)  weight_decay: 0.0500 (0.0500)  time: 0.5190  data: 0.1279  max mem: 31830
Epoch: [272]  [210/312]  eta: 0:00:58  lr: 0.000094  min_lr: 0.000094  loss: 3.2713 (3.1836)  weight_decay: 0.0500 (0.0500)  time: 0.5715  data: 0.1764  max mem: 31830
Epoch: [272]  [220/312]  eta: 0:00:53  lr: 0.000094  min_lr: 0.000094  loss: 3.2398 (3.1723)  weight_decay: 0.0500 (0.0500)  time: 0.5230  data: 0.1271  max mem: 31830
Epoch: [272]  [230/312]  eta: 0:00:47  lr: 0.000094  min_lr: 0.000094  loss: 3.0988 (3.1674)  weight_decay: 0.0500 (0.0500)  time: 0.5854  data: 0.1565  max mem: 31830
Epoch: [272]  [240/312]  eta: 0:00:41  lr: 0.000094  min_lr: 0.000094  loss: 3.3138 (3.1842)  weight_decay: 0.0500 (0.0500)  time: 0.5581  data: 0.1063  max mem: 31830
Epoch: [272]  [250/312]  eta: 0:00:35  lr: 0.000093  min_lr: 0.000093  loss: 3.4546 (3.1878)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0663  max mem: 31830
Epoch: [272]  [260/312]  eta: 0:00:29  lr: 0.000093  min_lr: 0.000093  loss: 3.2002 (3.1759)  weight_decay: 0.0500 (0.0500)  time: 0.5912  data: 0.0829  max mem: 31830
Epoch: [272]  [270/312]  eta: 0:00:23  lr: 0.000093  min_lr: 0.000093  loss: 3.2370 (3.1822)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0450  max mem: 31830
Epoch: [272]  [280/312]  eta: 0:00:18  lr: 0.000093  min_lr: 0.000093  loss: 3.3892 (3.1924)  weight_decay: 0.0500 (0.0500)  time: 0.5132  data: 0.1133  max mem: 31830
Epoch: [272]  [290/312]  eta: 0:00:12  lr: 0.000093  min_lr: 0.000093  loss: 3.2726 (3.1882)  weight_decay: 0.0500 (0.0500)  time: 0.5453  data: 0.1498  max mem: 31830
Epoch: [272]  [300/312]  eta: 0:00:06  lr: 0.000092  min_lr: 0.000092  loss: 3.3104 (3.1981)  weight_decay: 0.0500 (0.0500)  time: 0.4267  data: 0.0435  max mem: 31830
Epoch: [272]  [310/312]  eta: 0:00:01  lr: 0.000092  min_lr: 0.000092  loss: 3.4251 (3.1984)  weight_decay: 0.0500 (0.0500)  time: 0.3869  data: 0.0067  max mem: 31830
Epoch: [272]  [311/312]  eta: 0:00:00  lr: 0.000092  min_lr: 0.000092  loss: 3.4251 (3.2004)  weight_decay: 0.0500 (0.0500)  time: 0.3867  data: 0.0067  max mem: 31830
Epoch: [272] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.000092  min_lr: 0.000092  loss: 3.4251 (3.1816)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9462 (0.9462)  acc1: 83.9844 (83.9844)  acc5: 97.3958 (97.3958)  time: 8.5462  data: 8.3785  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2210 (1.1529)  acc1: 79.0365 (78.0640)  acc5: 94.6615 (94.4320)  time: 1.0712  data: 0.9355  max mem: 31830
Test: Total time: 0:00:09 (1.0812 s / it)
* Acc@1 78.162 Acc@5 94.290 loss 1.150
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.39%
Epoch: [273]  [  0/312]  eta: 0:59:20  lr: 0.000092  min_lr: 0.000092  loss: 3.3998 (3.3998)  weight_decay: 0.0500 (0.0500)  time: 11.4106  data: 10.2254  max mem: 31830
Epoch: [273]  [ 10/312]  eta: 0:08:51  lr: 0.000092  min_lr: 0.000092  loss: 3.1673 (3.1751)  weight_decay: 0.0500 (0.0500)  time: 1.7611  data: 0.9652  max mem: 31830
Epoch: [273]  [ 20/312]  eta: 0:05:30  lr: 0.000092  min_lr: 0.000092  loss: 3.0907 (3.0549)  weight_decay: 0.0500 (0.0500)  time: 0.6195  data: 0.0206  max mem: 31830
Epoch: [273]  [ 30/312]  eta: 0:04:14  lr: 0.000091  min_lr: 0.000091  loss: 3.1131 (3.0764)  weight_decay: 0.0500 (0.0500)  time: 0.4312  data: 0.0157  max mem: 31830
Epoch: [273]  [ 40/312]  eta: 0:03:32  lr: 0.000091  min_lr: 0.000091  loss: 3.4009 (3.1252)  weight_decay: 0.0500 (0.0500)  time: 0.4097  data: 0.0153  max mem: 31830
Epoch: [273]  [ 50/312]  eta: 0:03:04  lr: 0.000091  min_lr: 0.000091  loss: 3.4009 (3.1809)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0010  max mem: 31830
Epoch: [273]  [ 60/312]  eta: 0:02:44  lr: 0.000091  min_lr: 0.000091  loss: 3.3511 (3.1788)  weight_decay: 0.0500 (0.0500)  time: 0.3967  data: 0.0008  max mem: 31830
Epoch: [273]  [ 70/312]  eta: 0:02:30  lr: 0.000091  min_lr: 0.000091  loss: 3.2322 (3.1748)  weight_decay: 0.0500 (0.0500)  time: 0.4143  data: 0.0197  max mem: 31830
Epoch: [273]  [ 80/312]  eta: 0:02:23  lr: 0.000090  min_lr: 0.000090  loss: 3.2153 (3.1564)  weight_decay: 0.0500 (0.0500)  time: 0.5151  data: 0.1202  max mem: 31830
Epoch: [273]  [ 90/312]  eta: 0:02:14  lr: 0.000090  min_lr: 0.000090  loss: 3.2153 (3.1508)  weight_decay: 0.0500 (0.0500)  time: 0.5352  data: 0.1418  max mem: 31830
Epoch: [273]  [100/312]  eta: 0:02:06  lr: 0.000090  min_lr: 0.000090  loss: 3.2392 (3.1365)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0932  max mem: 31830
Epoch: [273]  [110/312]  eta: 0:01:58  lr: 0.000090  min_lr: 0.000090  loss: 3.2290 (3.1279)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0964  max mem: 31830
Epoch: [273]  [120/312]  eta: 0:01:52  lr: 0.000089  min_lr: 0.000089  loss: 3.1724 (3.1320)  weight_decay: 0.0500 (0.0500)  time: 0.5306  data: 0.1034  max mem: 31830
Epoch: [273]  [130/312]  eta: 0:01:48  lr: 0.000089  min_lr: 0.000089  loss: 3.1190 (3.1137)  weight_decay: 0.0500 (0.0500)  time: 0.6426  data: 0.1406  max mem: 31830
Epoch: [273]  [140/312]  eta: 0:01:41  lr: 0.000089  min_lr: 0.000089  loss: 3.1387 (3.1282)  weight_decay: 0.0500 (0.0500)  time: 0.6067  data: 0.1376  max mem: 31830
Epoch: [273]  [150/312]  eta: 0:01:35  lr: 0.000089  min_lr: 0.000089  loss: 3.2908 (3.1333)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0568  max mem: 31830
Epoch: [273]  [160/312]  eta: 0:01:28  lr: 0.000089  min_lr: 0.000089  loss: 3.2553 (3.1409)  weight_decay: 0.0500 (0.0500)  time: 0.5188  data: 0.0456  max mem: 31830
Epoch: [273]  [170/312]  eta: 0:01:22  lr: 0.000088  min_lr: 0.000088  loss: 3.2159 (3.1384)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0884  max mem: 31830
Epoch: [273]  [180/312]  eta: 0:01:16  lr: 0.000088  min_lr: 0.000088  loss: 3.3310 (3.1472)  weight_decay: 0.0500 (0.0500)  time: 0.5581  data: 0.0438  max mem: 31830
Epoch: [273]  [190/312]  eta: 0:01:10  lr: 0.000088  min_lr: 0.000088  loss: 3.3310 (3.1562)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0622  max mem: 31830
Epoch: [273]  [200/312]  eta: 0:01:03  lr: 0.000088  min_lr: 0.000088  loss: 3.2153 (3.1476)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0626  max mem: 31830
Epoch: [273]  [210/312]  eta: 0:00:58  lr: 0.000088  min_lr: 0.000088  loss: 2.9087 (3.1480)  weight_decay: 0.0500 (0.0500)  time: 0.5749  data: 0.0728  max mem: 31830
Epoch: [273]  [220/312]  eta: 0:00:52  lr: 0.000087  min_lr: 0.000087  loss: 3.2369 (3.1472)  weight_decay: 0.0500 (0.0500)  time: 0.5746  data: 0.1188  max mem: 31830
Epoch: [273]  [230/312]  eta: 0:00:46  lr: 0.000087  min_lr: 0.000087  loss: 3.2386 (3.1542)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0488  max mem: 31830
Epoch: [273]  [240/312]  eta: 0:00:40  lr: 0.000087  min_lr: 0.000087  loss: 3.1695 (3.1473)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0755  max mem: 31830
Epoch: [273]  [250/312]  eta: 0:00:35  lr: 0.000087  min_lr: 0.000087  loss: 3.1695 (3.1492)  weight_decay: 0.0500 (0.0500)  time: 0.5858  data: 0.1440  max mem: 31830
Epoch: [273]  [260/312]  eta: 0:00:29  lr: 0.000087  min_lr: 0.000087  loss: 3.4702 (3.1593)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0706  max mem: 31830
Epoch: [273]  [270/312]  eta: 0:00:23  lr: 0.000086  min_lr: 0.000086  loss: 3.6862 (3.1656)  weight_decay: 0.0500 (0.0500)  time: 0.5312  data: 0.1145  max mem: 31830
Epoch: [273]  [280/312]  eta: 0:00:18  lr: 0.000086  min_lr: 0.000086  loss: 3.3441 (3.1701)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.1158  max mem: 31830
Epoch: [273]  [290/312]  eta: 0:00:12  lr: 0.000086  min_lr: 0.000086  loss: 3.3813 (3.1713)  weight_decay: 0.0500 (0.0500)  time: 0.5801  data: 0.1856  max mem: 31830
Epoch: [273]  [300/312]  eta: 0:00:06  lr: 0.000086  min_lr: 0.000086  loss: 3.3022 (3.1720)  weight_decay: 0.0500 (0.0500)  time: 0.5803  data: 0.1965  max mem: 31830
Epoch: [273]  [310/312]  eta: 0:00:01  lr: 0.000086  min_lr: 0.000086  loss: 3.2146 (3.1697)  weight_decay: 0.0500 (0.0500)  time: 0.3928  data: 0.0126  max mem: 31830
Epoch: [273]  [311/312]  eta: 0:00:00  lr: 0.000085  min_lr: 0.000085  loss: 3.2605 (3.1700)  weight_decay: 0.0500 (0.0500)  time: 0.3927  data: 0.0126  max mem: 31830
Epoch: [273] Total time: 0:02:55 (0.5610 s / it)
Averaged stats: lr: 0.000085  min_lr: 0.000085  loss: 3.2605 (3.1860)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.9088 (0.9088)  acc1: 84.6354 (84.6354)  acc5: 97.1354 (97.1354)  time: 8.7370  data: 8.5749  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1863 (1.1145)  acc1: 78.2552 (78.2880)  acc5: 95.0521 (94.4640)  time: 1.0898  data: 0.9529  max mem: 31830
Test: Total time: 0:00:09 (1.1037 s / it)
* Acc@1 78.444 Acc@5 94.342 loss 1.112
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.44%
Epoch: [274]  [  0/312]  eta: 1:04:33  lr: 0.000085  min_lr: 0.000085  loss: 3.5871 (3.5871)  weight_decay: 0.0500 (0.0500)  time: 12.4150  data: 8.4948  max mem: 31830
Epoch: [274]  [ 10/312]  eta: 0:09:12  lr: 0.000085  min_lr: 0.000085  loss: 3.4336 (3.1897)  weight_decay: 0.0500 (0.0500)  time: 1.8289  data: 1.0024  max mem: 31830
Epoch: [274]  [ 20/312]  eta: 0:05:34  lr: 0.000085  min_lr: 0.000085  loss: 3.3042 (3.0624)  weight_decay: 0.0500 (0.0500)  time: 0.5815  data: 0.1270  max mem: 31830
Epoch: [274]  [ 30/312]  eta: 0:04:14  lr: 0.000085  min_lr: 0.000085  loss: 3.1064 (3.0754)  weight_decay: 0.0500 (0.0500)  time: 0.3942  data: 0.0008  max mem: 31830
Epoch: [274]  [ 40/312]  eta: 0:03:31  lr: 0.000085  min_lr: 0.000085  loss: 3.3802 (3.1391)  weight_decay: 0.0500 (0.0500)  time: 0.3951  data: 0.0010  max mem: 31830
Epoch: [274]  [ 50/312]  eta: 0:03:04  lr: 0.000084  min_lr: 0.000084  loss: 3.4345 (3.1363)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [274]  [ 60/312]  eta: 0:02:45  lr: 0.000084  min_lr: 0.000084  loss: 3.4345 (3.1608)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [274]  [ 70/312]  eta: 0:02:32  lr: 0.000084  min_lr: 0.000084  loss: 3.4411 (3.1927)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0012  max mem: 31830
Epoch: [274]  [ 80/312]  eta: 0:02:25  lr: 0.000084  min_lr: 0.000084  loss: 3.4730 (3.2231)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0425  max mem: 31830
Epoch: [274]  [ 90/312]  eta: 0:02:13  lr: 0.000084  min_lr: 0.000084  loss: 3.5040 (3.2273)  weight_decay: 0.0500 (0.0500)  time: 0.5023  data: 0.0424  max mem: 31830
Epoch: [274]  [100/312]  eta: 0:02:08  lr: 0.000083  min_lr: 0.000083  loss: 3.3333 (3.2299)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0153  max mem: 31830
Epoch: [274]  [110/312]  eta: 0:01:59  lr: 0.000083  min_lr: 0.000083  loss: 3.2646 (3.2299)  weight_decay: 0.0500 (0.0500)  time: 0.5487  data: 0.0266  max mem: 31830
Epoch: [274]  [120/312]  eta: 0:01:53  lr: 0.000083  min_lr: 0.000083  loss: 3.2646 (3.2177)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.0259  max mem: 31830
Epoch: [274]  [130/312]  eta: 0:01:47  lr: 0.000083  min_lr: 0.000083  loss: 3.1655 (3.2024)  weight_decay: 0.0500 (0.0500)  time: 0.5944  data: 0.0215  max mem: 31830
Epoch: [274]  [140/312]  eta: 0:01:40  lr: 0.000083  min_lr: 0.000083  loss: 3.3848 (3.2155)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0130  max mem: 31830
Epoch: [274]  [150/312]  eta: 0:01:35  lr: 0.000082  min_lr: 0.000082  loss: 3.3658 (3.2107)  weight_decay: 0.0500 (0.0500)  time: 0.5535  data: 0.0123  max mem: 31830
Epoch: [274]  [160/312]  eta: 0:01:28  lr: 0.000082  min_lr: 0.000082  loss: 3.2870 (3.2115)  weight_decay: 0.0500 (0.0500)  time: 0.5975  data: 0.0072  max mem: 31830
Epoch: [274]  [170/312]  eta: 0:01:22  lr: 0.000082  min_lr: 0.000082  loss: 3.3510 (3.2140)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.0260  max mem: 31830
Epoch: [274]  [180/312]  eta: 0:01:16  lr: 0.000082  min_lr: 0.000082  loss: 3.3016 (3.2034)  weight_decay: 0.0500 (0.0500)  time: 0.5595  data: 0.0264  max mem: 31830
Epoch: [274]  [190/312]  eta: 0:01:09  lr: 0.000082  min_lr: 0.000082  loss: 3.0886 (3.1934)  weight_decay: 0.0500 (0.0500)  time: 0.5367  data: 0.0021  max mem: 31830
Epoch: [274]  [200/312]  eta: 0:01:04  lr: 0.000081  min_lr: 0.000081  loss: 3.0886 (3.1942)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0017  max mem: 31830
Epoch: [274]  [210/312]  eta: 0:00:58  lr: 0.000081  min_lr: 0.000081  loss: 3.3861 (3.2008)  weight_decay: 0.0500 (0.0500)  time: 0.5896  data: 0.0010  max mem: 31830
Epoch: [274]  [220/312]  eta: 0:00:52  lr: 0.000081  min_lr: 0.000081  loss: 3.3861 (3.1988)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0273  max mem: 31830
Epoch: [274]  [230/312]  eta: 0:00:47  lr: 0.000081  min_lr: 0.000081  loss: 3.4290 (3.2053)  weight_decay: 0.0500 (0.0500)  time: 0.5776  data: 0.0351  max mem: 31830
Epoch: [274]  [240/312]  eta: 0:00:41  lr: 0.000081  min_lr: 0.000081  loss: 3.3812 (3.2054)  weight_decay: 0.0500 (0.0500)  time: 0.6351  data: 0.0093  max mem: 31830
Epoch: [274]  [250/312]  eta: 0:00:35  lr: 0.000080  min_lr: 0.000080  loss: 3.2820 (3.2015)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0015  max mem: 31830
Epoch: [274]  [260/312]  eta: 0:00:29  lr: 0.000080  min_lr: 0.000080  loss: 3.4016 (3.2046)  weight_decay: 0.0500 (0.0500)  time: 0.5294  data: 0.0098  max mem: 31830
Epoch: [274]  [270/312]  eta: 0:00:23  lr: 0.000080  min_lr: 0.000080  loss: 3.4597 (3.2095)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0098  max mem: 31830
Epoch: [274]  [280/312]  eta: 0:00:18  lr: 0.000080  min_lr: 0.000080  loss: 3.3915 (3.2107)  weight_decay: 0.0500 (0.0500)  time: 0.5404  data: 0.0292  max mem: 31830
Epoch: [274]  [290/312]  eta: 0:00:12  lr: 0.000080  min_lr: 0.000080  loss: 3.3915 (3.2109)  weight_decay: 0.0500 (0.0500)  time: 0.6058  data: 0.0289  max mem: 31830
Epoch: [274]  [300/312]  eta: 0:00:06  lr: 0.000079  min_lr: 0.000079  loss: 3.4001 (3.2076)  weight_decay: 0.0500 (0.0500)  time: 0.4854  data: 0.0053  max mem: 31830
Epoch: [274]  [310/312]  eta: 0:00:01  lr: 0.000079  min_lr: 0.000079  loss: 3.1385 (3.2031)  weight_decay: 0.0500 (0.0500)  time: 0.4103  data: 0.0052  max mem: 31830
Epoch: [274]  [311/312]  eta: 0:00:00  lr: 0.000079  min_lr: 0.000079  loss: 3.1385 (3.2038)  weight_decay: 0.0500 (0.0500)  time: 0.4058  data: 0.0001  max mem: 31830
Epoch: [274] Total time: 0:02:55 (0.5634 s / it)
Averaged stats: lr: 0.000079  min_lr: 0.000079  loss: 3.1385 (3.1844)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8523 (0.8523)  acc1: 84.5052 (84.5052)  acc5: 97.3958 (97.3958)  time: 8.6991  data: 8.5317  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1655 (1.0763)  acc1: 78.6458 (78.1280)  acc5: 94.5312 (94.4960)  time: 1.0836  data: 0.9480  max mem: 31830
Test: Total time: 0:00:10 (1.1159 s / it)
* Acc@1 78.370 Acc@5 94.412 loss 1.073
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.44%
Epoch: [275]  [  0/312]  eta: 1:01:39  lr: 0.000079  min_lr: 0.000079  loss: 2.2872 (2.2872)  weight_decay: 0.0500 (0.0500)  time: 11.8585  data: 9.9410  max mem: 31830
Epoch: [275]  [ 10/312]  eta: 0:08:16  lr: 0.000079  min_lr: 0.000079  loss: 2.8314 (2.8579)  weight_decay: 0.0500 (0.0500)  time: 1.6447  data: 1.1149  max mem: 31830
Epoch: [275]  [ 20/312]  eta: 0:05:38  lr: 0.000079  min_lr: 0.000079  loss: 3.3471 (3.1045)  weight_decay: 0.0500 (0.0500)  time: 0.6250  data: 0.1631  max mem: 31830
Epoch: [275]  [ 30/312]  eta: 0:04:17  lr: 0.000079  min_lr: 0.000079  loss: 3.3875 (3.1407)  weight_decay: 0.0500 (0.0500)  time: 0.5109  data: 0.0473  max mem: 31830
Epoch: [275]  [ 40/312]  eta: 0:03:34  lr: 0.000078  min_lr: 0.000078  loss: 3.3327 (3.1254)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0008  max mem: 31830
Epoch: [275]  [ 50/312]  eta: 0:03:06  lr: 0.000078  min_lr: 0.000078  loss: 3.3491 (3.2038)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0017  max mem: 31830
Epoch: [275]  [ 60/312]  eta: 0:02:46  lr: 0.000078  min_lr: 0.000078  loss: 3.4825 (3.2331)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0017  max mem: 31830
Epoch: [275]  [ 70/312]  eta: 0:02:34  lr: 0.000078  min_lr: 0.000078  loss: 3.4228 (3.2293)  weight_decay: 0.0500 (0.0500)  time: 0.4458  data: 0.0012  max mem: 31830
Epoch: [275]  [ 80/312]  eta: 0:02:28  lr: 0.000078  min_lr: 0.000078  loss: 3.2819 (3.2172)  weight_decay: 0.0500 (0.0500)  time: 0.5701  data: 0.0011  max mem: 31830
Epoch: [275]  [ 90/312]  eta: 0:02:17  lr: 0.000077  min_lr: 0.000077  loss: 3.0036 (3.1889)  weight_decay: 0.0500 (0.0500)  time: 0.5670  data: 0.0484  max mem: 31830
Epoch: [275]  [100/312]  eta: 0:02:11  lr: 0.000077  min_lr: 0.000077  loss: 2.9912 (3.1739)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0541  max mem: 31830
Epoch: [275]  [110/312]  eta: 0:02:00  lr: 0.000077  min_lr: 0.000077  loss: 3.1788 (3.1787)  weight_decay: 0.0500 (0.0500)  time: 0.4954  data: 0.0066  max mem: 31830
Epoch: [275]  [120/312]  eta: 0:01:55  lr: 0.000077  min_lr: 0.000077  loss: 3.1788 (3.1735)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0213  max mem: 31830
Epoch: [275]  [130/312]  eta: 0:01:49  lr: 0.000077  min_lr: 0.000077  loss: 3.0634 (3.1565)  weight_decay: 0.0500 (0.0500)  time: 0.6242  data: 0.0373  max mem: 31830
Epoch: [275]  [140/312]  eta: 0:01:41  lr: 0.000076  min_lr: 0.000076  loss: 3.1694 (3.1579)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0170  max mem: 31830
Epoch: [275]  [150/312]  eta: 0:01:35  lr: 0.000076  min_lr: 0.000076  loss: 3.4516 (3.1674)  weight_decay: 0.0500 (0.0500)  time: 0.4980  data: 0.0198  max mem: 31830
Epoch: [275]  [160/312]  eta: 0:01:29  lr: 0.000076  min_lr: 0.000076  loss: 3.4102 (3.1739)  weight_decay: 0.0500 (0.0500)  time: 0.6153  data: 0.0197  max mem: 31830
Epoch: [275]  [170/312]  eta: 0:01:22  lr: 0.000076  min_lr: 0.000076  loss: 3.0234 (3.1698)  weight_decay: 0.0500 (0.0500)  time: 0.5419  data: 0.0294  max mem: 31830
Epoch: [275]  [180/312]  eta: 0:01:16  lr: 0.000076  min_lr: 0.000076  loss: 3.1795 (3.1787)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0347  max mem: 31830
Epoch: [275]  [190/312]  eta: 0:01:09  lr: 0.000075  min_lr: 0.000075  loss: 3.4316 (3.1804)  weight_decay: 0.0500 (0.0500)  time: 0.4799  data: 0.0061  max mem: 31830
Epoch: [275]  [200/312]  eta: 0:01:04  lr: 0.000075  min_lr: 0.000075  loss: 3.4169 (3.1796)  weight_decay: 0.0500 (0.0500)  time: 0.5264  data: 0.0416  max mem: 31830
Epoch: [275]  [210/312]  eta: 0:00:58  lr: 0.000075  min_lr: 0.000075  loss: 3.4016 (3.1844)  weight_decay: 0.0500 (0.0500)  time: 0.6147  data: 0.0559  max mem: 31830
Epoch: [275]  [220/312]  eta: 0:00:52  lr: 0.000075  min_lr: 0.000075  loss: 3.3317 (3.1859)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0329  max mem: 31830
Epoch: [275]  [230/312]  eta: 0:00:46  lr: 0.000075  min_lr: 0.000075  loss: 3.2553 (3.1791)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0247  max mem: 31830
Epoch: [275]  [240/312]  eta: 0:00:41  lr: 0.000074  min_lr: 0.000074  loss: 3.3296 (3.1780)  weight_decay: 0.0500 (0.0500)  time: 0.6203  data: 0.0220  max mem: 31830
Epoch: [275]  [250/312]  eta: 0:00:35  lr: 0.000074  min_lr: 0.000074  loss: 3.0955 (3.1608)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0284  max mem: 31830
Epoch: [275]  [260/312]  eta: 0:00:29  lr: 0.000074  min_lr: 0.000074  loss: 3.0955 (3.1592)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0134  max mem: 31830
Epoch: [275]  [270/312]  eta: 0:00:23  lr: 0.000074  min_lr: 0.000074  loss: 3.3380 (3.1608)  weight_decay: 0.0500 (0.0500)  time: 0.4992  data: 0.0076  max mem: 31830
Epoch: [275]  [280/312]  eta: 0:00:18  lr: 0.000074  min_lr: 0.000074  loss: 3.1863 (3.1577)  weight_decay: 0.0500 (0.0500)  time: 0.5302  data: 0.0286  max mem: 31830
Epoch: [275]  [290/312]  eta: 0:00:12  lr: 0.000073  min_lr: 0.000073  loss: 3.1389 (3.1581)  weight_decay: 0.0500 (0.0500)  time: 0.6009  data: 0.0391  max mem: 31830
Epoch: [275]  [300/312]  eta: 0:00:06  lr: 0.000073  min_lr: 0.000073  loss: 3.1389 (3.1594)  weight_decay: 0.0500 (0.0500)  time: 0.4673  data: 0.0176  max mem: 31830
Epoch: [275]  [310/312]  eta: 0:00:01  lr: 0.000073  min_lr: 0.000073  loss: 3.3306 (3.1582)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [275]  [311/312]  eta: 0:00:00  lr: 0.000073  min_lr: 0.000073  loss: 3.3192 (3.1562)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [275] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.000073  min_lr: 0.000073  loss: 3.3192 (3.1633)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8063 (0.8063)  acc1: 85.1562 (85.1562)  acc5: 97.5260 (97.5260)  time: 8.6825  data: 8.5155  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1001 (1.0330)  acc1: 79.6875 (78.3360)  acc5: 94.4010 (94.4320)  time: 1.0815  data: 0.9463  max mem: 31830
Test: Total time: 0:00:09 (1.0996 s / it)
* Acc@1 78.560 Acc@5 94.414 loss 1.031
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.56%
Epoch: [276]  [  0/312]  eta: 0:59:55  lr: 0.000073  min_lr: 0.000073  loss: 3.6340 (3.6340)  weight_decay: 0.0500 (0.0500)  time: 11.5234  data: 8.6058  max mem: 31830
Epoch: [276]  [ 10/312]  eta: 0:08:33  lr: 0.000073  min_lr: 0.000073  loss: 3.3540 (3.2762)  weight_decay: 0.0500 (0.0500)  time: 1.7011  data: 1.0849  max mem: 31830
Epoch: [276]  [ 20/312]  eta: 0:05:23  lr: 0.000073  min_lr: 0.000073  loss: 3.2034 (3.2297)  weight_decay: 0.0500 (0.0500)  time: 0.5862  data: 0.1834  max mem: 31830
Epoch: [276]  [ 30/312]  eta: 0:04:07  lr: 0.000072  min_lr: 0.000072  loss: 3.0281 (3.1769)  weight_decay: 0.0500 (0.0500)  time: 0.4262  data: 0.0176  max mem: 31830
Epoch: [276]  [ 40/312]  eta: 0:03:27  lr: 0.000072  min_lr: 0.000072  loss: 3.0802 (3.1690)  weight_decay: 0.0500 (0.0500)  time: 0.3986  data: 0.0010  max mem: 31830
Epoch: [276]  [ 50/312]  eta: 0:03:00  lr: 0.000072  min_lr: 0.000072  loss: 3.4197 (3.1586)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0013  max mem: 31830
Epoch: [276]  [ 60/312]  eta: 0:02:41  lr: 0.000072  min_lr: 0.000072  loss: 2.8672 (3.1061)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0013  max mem: 31830
Epoch: [276]  [ 70/312]  eta: 0:02:32  lr: 0.000072  min_lr: 0.000072  loss: 3.1782 (3.1389)  weight_decay: 0.0500 (0.0500)  time: 0.4800  data: 0.0497  max mem: 31830
Epoch: [276]  [ 80/312]  eta: 0:02:24  lr: 0.000072  min_lr: 0.000072  loss: 3.3866 (3.1340)  weight_decay: 0.0500 (0.0500)  time: 0.5696  data: 0.0826  max mem: 31830
Epoch: [276]  [ 90/312]  eta: 0:02:14  lr: 0.000071  min_lr: 0.000071  loss: 3.2394 (3.1609)  weight_decay: 0.0500 (0.0500)  time: 0.5117  data: 0.0620  max mem: 31830
Epoch: [276]  [100/312]  eta: 0:02:08  lr: 0.000071  min_lr: 0.000071  loss: 3.2394 (3.1576)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0698  max mem: 31830
Epoch: [276]  [110/312]  eta: 0:01:58  lr: 0.000071  min_lr: 0.000071  loss: 3.1782 (3.1438)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.0415  max mem: 31830
Epoch: [276]  [120/312]  eta: 0:01:53  lr: 0.000071  min_lr: 0.000071  loss: 3.0152 (3.1287)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0346  max mem: 31830
Epoch: [276]  [130/312]  eta: 0:01:47  lr: 0.000071  min_lr: 0.000071  loss: 3.0987 (3.1274)  weight_decay: 0.0500 (0.0500)  time: 0.6172  data: 0.0626  max mem: 31830
Epoch: [276]  [140/312]  eta: 0:01:40  lr: 0.000070  min_lr: 0.000070  loss: 3.0987 (3.1174)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0288  max mem: 31830
Epoch: [276]  [150/312]  eta: 0:01:33  lr: 0.000070  min_lr: 0.000070  loss: 3.2882 (3.1385)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0173  max mem: 31830
Epoch: [276]  [160/312]  eta: 0:01:28  lr: 0.000070  min_lr: 0.000070  loss: 3.3419 (3.1179)  weight_decay: 0.0500 (0.0500)  time: 0.5798  data: 0.0183  max mem: 31830
Epoch: [276]  [170/312]  eta: 0:01:22  lr: 0.000070  min_lr: 0.000070  loss: 2.8304 (3.1100)  weight_decay: 0.0500 (0.0500)  time: 0.5586  data: 0.0320  max mem: 31830
Epoch: [276]  [180/312]  eta: 0:01:15  lr: 0.000070  min_lr: 0.000070  loss: 3.2380 (3.1115)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0607  max mem: 31830
Epoch: [276]  [190/312]  eta: 0:01:09  lr: 0.000069  min_lr: 0.000069  loss: 3.3071 (3.1195)  weight_decay: 0.0500 (0.0500)  time: 0.5119  data: 0.0320  max mem: 31830
Epoch: [276]  [200/312]  eta: 0:01:03  lr: 0.000069  min_lr: 0.000069  loss: 3.3834 (3.1355)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0338  max mem: 31830
Epoch: [276]  [210/312]  eta: 0:00:58  lr: 0.000069  min_lr: 0.000069  loss: 3.4386 (3.1408)  weight_decay: 0.0500 (0.0500)  time: 0.6007  data: 0.0536  max mem: 31830
Epoch: [276]  [220/312]  eta: 0:00:52  lr: 0.000069  min_lr: 0.000069  loss: 3.3440 (3.1440)  weight_decay: 0.0500 (0.0500)  time: 0.5526  data: 0.0328  max mem: 31830
Epoch: [276]  [230/312]  eta: 0:00:46  lr: 0.000069  min_lr: 0.000069  loss: 3.3440 (3.1501)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0477  max mem: 31830
Epoch: [276]  [240/312]  eta: 0:00:40  lr: 0.000069  min_lr: 0.000069  loss: 3.3010 (3.1565)  weight_decay: 0.0500 (0.0500)  time: 0.5469  data: 0.0379  max mem: 31830
Epoch: [276]  [250/312]  eta: 0:00:35  lr: 0.000068  min_lr: 0.000068  loss: 3.0639 (3.1435)  weight_decay: 0.0500 (0.0500)  time: 0.5572  data: 0.0472  max mem: 31830
Epoch: [276]  [260/312]  eta: 0:00:29  lr: 0.000068  min_lr: 0.000068  loss: 3.1080 (3.1471)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0766  max mem: 31830
Epoch: [276]  [270/312]  eta: 0:00:23  lr: 0.000068  min_lr: 0.000068  loss: 3.3470 (3.1471)  weight_decay: 0.0500 (0.0500)  time: 0.5260  data: 0.0623  max mem: 31830
Epoch: [276]  [280/312]  eta: 0:00:18  lr: 0.000068  min_lr: 0.000068  loss: 3.3921 (3.1516)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.1046  max mem: 31830
Epoch: [276]  [290/312]  eta: 0:00:12  lr: 0.000068  min_lr: 0.000068  loss: 3.3054 (3.1487)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0732  max mem: 31830
Epoch: [276]  [300/312]  eta: 0:00:06  lr: 0.000067  min_lr: 0.000067  loss: 3.1017 (3.1468)  weight_decay: 0.0500 (0.0500)  time: 0.4693  data: 0.0247  max mem: 31830
Epoch: [276]  [310/312]  eta: 0:00:01  lr: 0.000067  min_lr: 0.000067  loss: 3.2687 (3.1540)  weight_decay: 0.0500 (0.0500)  time: 0.4054  data: 0.0246  max mem: 31830
Epoch: [276]  [311/312]  eta: 0:00:00  lr: 0.000067  min_lr: 0.000067  loss: 3.3201 (3.1554)  weight_decay: 0.0500 (0.0500)  time: 0.4052  data: 0.0246  max mem: 31830
Epoch: [276] Total time: 0:02:53 (0.5565 s / it)
Averaged stats: lr: 0.000067  min_lr: 0.000067  loss: 3.3201 (3.1936)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9378 (0.9378)  acc1: 84.2448 (84.2448)  acc5: 97.0052 (97.0052)  time: 8.7788  data: 8.6115  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2308 (1.1637)  acc1: 79.4271 (78.2560)  acc5: 95.1823 (94.7040)  time: 1.0924  data: 0.9569  max mem: 31830
Test: Total time: 0:00:09 (1.1102 s / it)
* Acc@1 78.486 Acc@5 94.480 loss 1.162
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.56%
Epoch: [277]  [  0/312]  eta: 1:05:51  lr: 0.000067  min_lr: 0.000067  loss: 3.4478 (3.4478)  weight_decay: 0.0500 (0.0500)  time: 12.6637  data: 12.2694  max mem: 31830
Epoch: [277]  [ 10/312]  eta: 0:08:45  lr: 0.000067  min_lr: 0.000067  loss: 3.1033 (3.1603)  weight_decay: 0.0500 (0.0500)  time: 1.7387  data: 1.1160  max mem: 31830
Epoch: [277]  [ 20/312]  eta: 0:05:34  lr: 0.000067  min_lr: 0.000067  loss: 3.3205 (3.3009)  weight_decay: 0.0500 (0.0500)  time: 0.5688  data: 0.0008  max mem: 31830
Epoch: [277]  [ 30/312]  eta: 0:04:15  lr: 0.000067  min_lr: 0.000067  loss: 3.4698 (3.2364)  weight_decay: 0.0500 (0.0500)  time: 0.4454  data: 0.0010  max mem: 31830
Epoch: [277]  [ 40/312]  eta: 0:03:32  lr: 0.000066  min_lr: 0.000066  loss: 3.2405 (3.2349)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0010  max mem: 31830
Epoch: [277]  [ 50/312]  eta: 0:03:05  lr: 0.000066  min_lr: 0.000066  loss: 3.1458 (3.1936)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0009  max mem: 31830
Epoch: [277]  [ 60/312]  eta: 0:02:45  lr: 0.000066  min_lr: 0.000066  loss: 3.1458 (3.1971)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0008  max mem: 31830
Epoch: [277]  [ 70/312]  eta: 0:02:32  lr: 0.000066  min_lr: 0.000066  loss: 3.0830 (3.1454)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0071  max mem: 31830
Epoch: [277]  [ 80/312]  eta: 0:02:24  lr: 0.000066  min_lr: 0.000066  loss: 2.7479 (3.1058)  weight_decay: 0.0500 (0.0500)  time: 0.5248  data: 0.0777  max mem: 31830
Epoch: [277]  [ 90/312]  eta: 0:02:13  lr: 0.000066  min_lr: 0.000066  loss: 3.1305 (3.1163)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0714  max mem: 31830
Epoch: [277]  [100/312]  eta: 0:02:06  lr: 0.000065  min_lr: 0.000065  loss: 3.3006 (3.1180)  weight_decay: 0.0500 (0.0500)  time: 0.4947  data: 0.0513  max mem: 31830
Epoch: [277]  [110/312]  eta: 0:01:58  lr: 0.000065  min_lr: 0.000065  loss: 3.2171 (3.1091)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0696  max mem: 31830
Epoch: [277]  [120/312]  eta: 0:01:52  lr: 0.000065  min_lr: 0.000065  loss: 3.3812 (3.1341)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0785  max mem: 31830
Epoch: [277]  [130/312]  eta: 0:01:46  lr: 0.000065  min_lr: 0.000065  loss: 3.3812 (3.1149)  weight_decay: 0.0500 (0.0500)  time: 0.5768  data: 0.1109  max mem: 31830
Epoch: [277]  [140/312]  eta: 0:01:39  lr: 0.000065  min_lr: 0.000065  loss: 3.1024 (3.1080)  weight_decay: 0.0500 (0.0500)  time: 0.5451  data: 0.0774  max mem: 31830
Epoch: [277]  [150/312]  eta: 0:01:33  lr: 0.000064  min_lr: 0.000064  loss: 3.1527 (3.1119)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0475  max mem: 31830
Epoch: [277]  [160/312]  eta: 0:01:27  lr: 0.000064  min_lr: 0.000064  loss: 3.2890 (3.1226)  weight_decay: 0.0500 (0.0500)  time: 0.5546  data: 0.0656  max mem: 31830
Epoch: [277]  [170/312]  eta: 0:01:21  lr: 0.000064  min_lr: 0.000064  loss: 3.2483 (3.1153)  weight_decay: 0.0500 (0.0500)  time: 0.5475  data: 0.0447  max mem: 31830
Epoch: [277]  [180/312]  eta: 0:01:15  lr: 0.000064  min_lr: 0.000064  loss: 3.2236 (3.1205)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0285  max mem: 31830
Epoch: [277]  [190/312]  eta: 0:01:09  lr: 0.000064  min_lr: 0.000064  loss: 3.4144 (3.1212)  weight_decay: 0.0500 (0.0500)  time: 0.5038  data: 0.0293  max mem: 31830
Epoch: [277]  [200/312]  eta: 0:01:03  lr: 0.000064  min_lr: 0.000064  loss: 3.3245 (3.1268)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0517  max mem: 31830
Epoch: [277]  [210/312]  eta: 0:00:58  lr: 0.000063  min_lr: 0.000063  loss: 3.2831 (3.1192)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.0635  max mem: 31830
Epoch: [277]  [220/312]  eta: 0:00:51  lr: 0.000063  min_lr: 0.000063  loss: 3.3666 (3.1374)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0469  max mem: 31830
Epoch: [277]  [230/312]  eta: 0:00:46  lr: 0.000063  min_lr: 0.000063  loss: 3.3632 (3.1239)  weight_decay: 0.0500 (0.0500)  time: 0.5527  data: 0.0784  max mem: 31830
Epoch: [277]  [240/312]  eta: 0:00:40  lr: 0.000063  min_lr: 0.000063  loss: 2.9683 (3.1257)  weight_decay: 0.0500 (0.0500)  time: 0.5756  data: 0.0449  max mem: 31830
Epoch: [277]  [250/312]  eta: 0:00:35  lr: 0.000063  min_lr: 0.000063  loss: 3.2036 (3.1244)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0261  max mem: 31830
Epoch: [277]  [260/312]  eta: 0:00:29  lr: 0.000063  min_lr: 0.000063  loss: 3.2036 (3.1260)  weight_decay: 0.0500 (0.0500)  time: 0.5575  data: 0.0334  max mem: 31830
Epoch: [277]  [270/312]  eta: 0:00:23  lr: 0.000062  min_lr: 0.000062  loss: 2.9951 (3.1185)  weight_decay: 0.0500 (0.0500)  time: 0.4958  data: 0.0177  max mem: 31830
Epoch: [277]  [280/312]  eta: 0:00:18  lr: 0.000062  min_lr: 0.000062  loss: 2.9951 (3.1169)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0518  max mem: 31830
Epoch: [277]  [290/312]  eta: 0:00:12  lr: 0.000062  min_lr: 0.000062  loss: 3.0764 (3.1227)  weight_decay: 0.0500 (0.0500)  time: 0.5935  data: 0.0481  max mem: 31830
Epoch: [277]  [300/312]  eta: 0:00:06  lr: 0.000062  min_lr: 0.000062  loss: 3.3319 (3.1216)  weight_decay: 0.0500 (0.0500)  time: 0.4787  data: 0.0217  max mem: 31830
Epoch: [277]  [310/312]  eta: 0:00:01  lr: 0.000062  min_lr: 0.000062  loss: 3.3215 (3.1267)  weight_decay: 0.0500 (0.0500)  time: 0.4005  data: 0.0155  max mem: 31830
Epoch: [277]  [311/312]  eta: 0:00:00  lr: 0.000062  min_lr: 0.000062  loss: 3.2116 (3.1248)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0155  max mem: 31830
Epoch: [277] Total time: 0:02:53 (0.5550 s / it)
Averaged stats: lr: 0.000062  min_lr: 0.000062  loss: 3.2116 (3.1798)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8824 (0.8824)  acc1: 83.9844 (83.9844)  acc5: 97.0052 (97.0052)  time: 8.2515  data: 8.0844  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1549 (1.0888)  acc1: 79.4271 (77.9840)  acc5: 94.9219 (94.4960)  time: 1.0333  data: 0.8984  max mem: 31830
Test: Total time: 0:00:09 (1.0427 s / it)
* Acc@1 78.470 Acc@5 94.448 loss 1.087
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.56%
Epoch: [278]  [  0/312]  eta: 1:03:34  lr: 0.000062  min_lr: 0.000062  loss: 2.0489 (2.0489)  weight_decay: 0.0500 (0.0500)  time: 12.2269  data: 8.7436  max mem: 31830
Epoch: [278]  [ 10/312]  eta: 0:08:48  lr: 0.000061  min_lr: 0.000061  loss: 3.4255 (3.1343)  weight_decay: 0.0500 (0.0500)  time: 1.7506  data: 1.0569  max mem: 31830
Epoch: [278]  [ 20/312]  eta: 0:05:34  lr: 0.000061  min_lr: 0.000061  loss: 3.2781 (3.0896)  weight_decay: 0.0500 (0.0500)  time: 0.5898  data: 0.1758  max mem: 31830
Epoch: [278]  [ 30/312]  eta: 0:04:14  lr: 0.000061  min_lr: 0.000061  loss: 3.0306 (3.0989)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0320  max mem: 31830
Epoch: [278]  [ 40/312]  eta: 0:03:32  lr: 0.000061  min_lr: 0.000061  loss: 3.0306 (3.0589)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0015  max mem: 31830
Epoch: [278]  [ 50/312]  eta: 0:03:04  lr: 0.000061  min_lr: 0.000061  loss: 3.3177 (3.1085)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0016  max mem: 31830
Epoch: [278]  [ 60/312]  eta: 0:02:45  lr: 0.000061  min_lr: 0.000061  loss: 3.4213 (3.1427)  weight_decay: 0.0500 (0.0500)  time: 0.3984  data: 0.0008  max mem: 31830
Epoch: [278]  [ 70/312]  eta: 0:02:31  lr: 0.000060  min_lr: 0.000060  loss: 3.1002 (3.0921)  weight_decay: 0.0500 (0.0500)  time: 0.4288  data: 0.0007  max mem: 31830
Epoch: [278]  [ 80/312]  eta: 0:02:24  lr: 0.000060  min_lr: 0.000060  loss: 3.1149 (3.1220)  weight_decay: 0.0500 (0.0500)  time: 0.5296  data: 0.0356  max mem: 31830
Epoch: [278]  [ 90/312]  eta: 0:02:14  lr: 0.000060  min_lr: 0.000060  loss: 3.3184 (3.1364)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.0463  max mem: 31830
Epoch: [278]  [100/312]  eta: 0:02:10  lr: 0.000060  min_lr: 0.000060  loss: 3.3251 (3.1497)  weight_decay: 0.0500 (0.0500)  time: 0.5693  data: 0.0325  max mem: 31830
Epoch: [278]  [110/312]  eta: 0:02:00  lr: 0.000060  min_lr: 0.000060  loss: 3.3817 (3.1641)  weight_decay: 0.0500 (0.0500)  time: 0.5539  data: 0.0415  max mem: 31830
Epoch: [278]  [120/312]  eta: 0:01:54  lr: 0.000060  min_lr: 0.000060  loss: 3.0964 (3.1360)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0208  max mem: 31830
Epoch: [278]  [130/312]  eta: 0:01:49  lr: 0.000059  min_lr: 0.000059  loss: 3.0391 (3.1399)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.0134  max mem: 31830
Epoch: [278]  [140/312]  eta: 0:01:41  lr: 0.000059  min_lr: 0.000059  loss: 3.3922 (3.1433)  weight_decay: 0.0500 (0.0500)  time: 0.5510  data: 0.0135  max mem: 31830
Epoch: [278]  [150/312]  eta: 0:01:36  lr: 0.000059  min_lr: 0.000059  loss: 3.2941 (3.1489)  weight_decay: 0.0500 (0.0500)  time: 0.5767  data: 0.0067  max mem: 31830
Epoch: [278]  [160/312]  eta: 0:01:29  lr: 0.000059  min_lr: 0.000059  loss: 3.3070 (3.1600)  weight_decay: 0.0500 (0.0500)  time: 0.5724  data: 0.0198  max mem: 31830
Epoch: [278]  [170/312]  eta: 0:01:23  lr: 0.000059  min_lr: 0.000059  loss: 3.4211 (3.1745)  weight_decay: 0.0500 (0.0500)  time: 0.5376  data: 0.0144  max mem: 31830
Epoch: [278]  [180/312]  eta: 0:01:18  lr: 0.000058  min_lr: 0.000058  loss: 3.3731 (3.1811)  weight_decay: 0.0500 (0.0500)  time: 0.6479  data: 0.0014  max mem: 31830
Epoch: [278]  [190/312]  eta: 0:01:11  lr: 0.000058  min_lr: 0.000058  loss: 3.4070 (3.1903)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0015  max mem: 31830
Epoch: [278]  [200/312]  eta: 0:01:06  lr: 0.000058  min_lr: 0.000058  loss: 3.4418 (3.1998)  weight_decay: 0.0500 (0.0500)  time: 0.5585  data: 0.0011  max mem: 31830
Epoch: [278]  [210/312]  eta: 0:00:59  lr: 0.000058  min_lr: 0.000058  loss: 3.3572 (3.1963)  weight_decay: 0.0500 (0.0500)  time: 0.5725  data: 0.0012  max mem: 31830
Epoch: [278]  [220/312]  eta: 0:00:53  lr: 0.000058  min_lr: 0.000058  loss: 2.9199 (3.1854)  weight_decay: 0.0500 (0.0500)  time: 0.5177  data: 0.0010  max mem: 31830
Epoch: [278]  [230/312]  eta: 0:00:47  lr: 0.000058  min_lr: 0.000058  loss: 3.0424 (3.1794)  weight_decay: 0.0500 (0.0500)  time: 0.5971  data: 0.0207  max mem: 31830
Epoch: [278]  [240/312]  eta: 0:00:41  lr: 0.000057  min_lr: 0.000057  loss: 3.3418 (3.1894)  weight_decay: 0.0500 (0.0500)  time: 0.4918  data: 0.0207  max mem: 31830
Epoch: [278]  [250/312]  eta: 0:00:35  lr: 0.000057  min_lr: 0.000057  loss: 3.3793 (3.1975)  weight_decay: 0.0500 (0.0500)  time: 0.5244  data: 0.0009  max mem: 31830
Epoch: [278]  [260/312]  eta: 0:00:30  lr: 0.000057  min_lr: 0.000057  loss: 3.4614 (3.1981)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0094  max mem: 31830
Epoch: [278]  [270/312]  eta: 0:00:24  lr: 0.000057  min_lr: 0.000057  loss: 3.1780 (3.1922)  weight_decay: 0.0500 (0.0500)  time: 0.4901  data: 0.0094  max mem: 31830
Epoch: [278]  [280/312]  eta: 0:00:18  lr: 0.000057  min_lr: 0.000057  loss: 2.9621 (3.1795)  weight_decay: 0.0500 (0.0500)  time: 0.5128  data: 0.0049  max mem: 31830
Epoch: [278]  [290/312]  eta: 0:00:12  lr: 0.000057  min_lr: 0.000057  loss: 3.0042 (3.1754)  weight_decay: 0.0500 (0.0500)  time: 0.5202  data: 0.0045  max mem: 31830
Epoch: [278]  [300/312]  eta: 0:00:06  lr: 0.000056  min_lr: 0.000056  loss: 3.2828 (3.1823)  weight_decay: 0.0500 (0.0500)  time: 0.4141  data: 0.0002  max mem: 31830
Epoch: [278]  [310/312]  eta: 0:00:01  lr: 0.000056  min_lr: 0.000056  loss: 3.3333 (3.1828)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0001  max mem: 31830
Epoch: [278]  [311/312]  eta: 0:00:00  lr: 0.000056  min_lr: 0.000056  loss: 3.3333 (3.1839)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0001  max mem: 31830
Epoch: [278] Total time: 0:02:55 (0.5617 s / it)
Averaged stats: lr: 0.000056  min_lr: 0.000056  loss: 3.3333 (3.1873)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.9066 (0.9066)  acc1: 84.3750 (84.3750)  acc5: 97.1354 (97.1354)  time: 8.6479  data: 8.4803  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2021 (1.1316)  acc1: 78.7760 (78.0800)  acc5: 94.5312 (94.4160)  time: 1.0803  data: 0.9452  max mem: 31830
Test: Total time: 0:00:09 (1.0948 s / it)
* Acc@1 78.380 Acc@5 94.386 loss 1.131
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.56%
Epoch: [279]  [  0/312]  eta: 1:05:15  lr: 0.000056  min_lr: 0.000056  loss: 2.8728 (2.8728)  weight_decay: 0.0500 (0.0500)  time: 12.5508  data: 8.0885  max mem: 31830
Epoch: [279]  [ 10/312]  eta: 0:09:33  lr: 0.000056  min_lr: 0.000056  loss: 2.8728 (2.8639)  weight_decay: 0.0500 (0.0500)  time: 1.8993  data: 1.0306  max mem: 31830
Epoch: [279]  [ 20/312]  eta: 0:05:43  lr: 0.000056  min_lr: 0.000056  loss: 3.2203 (3.0786)  weight_decay: 0.0500 (0.0500)  time: 0.6094  data: 0.1627  max mem: 31830
Epoch: [279]  [ 30/312]  eta: 0:04:21  lr: 0.000056  min_lr: 0.000056  loss: 3.2221 (3.0814)  weight_decay: 0.0500 (0.0500)  time: 0.3918  data: 0.0007  max mem: 31830
Epoch: [279]  [ 40/312]  eta: 0:03:37  lr: 0.000056  min_lr: 0.000056  loss: 3.0369 (3.0732)  weight_decay: 0.0500 (0.0500)  time: 0.4044  data: 0.0040  max mem: 31830
Epoch: [279]  [ 50/312]  eta: 0:03:09  lr: 0.000055  min_lr: 0.000055  loss: 3.1305 (3.0790)  weight_decay: 0.0500 (0.0500)  time: 0.4075  data: 0.0041  max mem: 31830
Epoch: [279]  [ 60/312]  eta: 0:02:48  lr: 0.000055  min_lr: 0.000055  loss: 3.1332 (3.0809)  weight_decay: 0.0500 (0.0500)  time: 0.4025  data: 0.0023  max mem: 31830
Epoch: [279]  [ 70/312]  eta: 0:02:32  lr: 0.000055  min_lr: 0.000055  loss: 3.3394 (3.1229)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0023  max mem: 31830
Epoch: [279]  [ 80/312]  eta: 0:02:24  lr: 0.000055  min_lr: 0.000055  loss: 3.5051 (3.1372)  weight_decay: 0.0500 (0.0500)  time: 0.4730  data: 0.0148  max mem: 31830
Epoch: [279]  [ 90/312]  eta: 0:02:17  lr: 0.000055  min_lr: 0.000055  loss: 3.1655 (3.1107)  weight_decay: 0.0500 (0.0500)  time: 0.5847  data: 0.0414  max mem: 31830
Epoch: [279]  [100/312]  eta: 0:02:07  lr: 0.000055  min_lr: 0.000055  loss: 3.1091 (3.1137)  weight_decay: 0.0500 (0.0500)  time: 0.5289  data: 0.0275  max mem: 31830
Epoch: [279]  [110/312]  eta: 0:02:02  lr: 0.000054  min_lr: 0.000054  loss: 3.1242 (3.1131)  weight_decay: 0.0500 (0.0500)  time: 0.5348  data: 0.0011  max mem: 31830
Epoch: [279]  [120/312]  eta: 0:01:56  lr: 0.000054  min_lr: 0.000054  loss: 3.1652 (3.1094)  weight_decay: 0.0500 (0.0500)  time: 0.6253  data: 0.0073  max mem: 31830
Epoch: [279]  [130/312]  eta: 0:01:48  lr: 0.000054  min_lr: 0.000054  loss: 3.3285 (3.1244)  weight_decay: 0.0500 (0.0500)  time: 0.5396  data: 0.0071  max mem: 31830
Epoch: [279]  [140/312]  eta: 0:01:42  lr: 0.000054  min_lr: 0.000054  loss: 3.3494 (3.1460)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0009  max mem: 31830
Epoch: [279]  [150/312]  eta: 0:01:34  lr: 0.000054  min_lr: 0.000054  loss: 3.4354 (3.1544)  weight_decay: 0.0500 (0.0500)  time: 0.5028  data: 0.0065  max mem: 31830
Epoch: [279]  [160/312]  eta: 0:01:28  lr: 0.000054  min_lr: 0.000054  loss: 3.0941 (3.1424)  weight_decay: 0.0500 (0.0500)  time: 0.5268  data: 0.0066  max mem: 31830
Epoch: [279]  [170/312]  eta: 0:01:23  lr: 0.000053  min_lr: 0.000053  loss: 2.9113 (3.1399)  weight_decay: 0.0500 (0.0500)  time: 0.6097  data: 0.0059  max mem: 31830
Epoch: [279]  [180/312]  eta: 0:01:16  lr: 0.000053  min_lr: 0.000053  loss: 3.1598 (3.1425)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0115  max mem: 31830
Epoch: [279]  [190/312]  eta: 0:01:10  lr: 0.000053  min_lr: 0.000053  loss: 3.2479 (3.1511)  weight_decay: 0.0500 (0.0500)  time: 0.5221  data: 0.0066  max mem: 31830
Epoch: [279]  [200/312]  eta: 0:01:04  lr: 0.000053  min_lr: 0.000053  loss: 3.4759 (3.1604)  weight_decay: 0.0500 (0.0500)  time: 0.5954  data: 0.0009  max mem: 31830
Epoch: [279]  [210/312]  eta: 0:00:58  lr: 0.000053  min_lr: 0.000053  loss: 3.4759 (3.1691)  weight_decay: 0.0500 (0.0500)  time: 0.5448  data: 0.0009  max mem: 31830
Epoch: [279]  [220/312]  eta: 0:00:52  lr: 0.000053  min_lr: 0.000053  loss: 3.5230 (3.1806)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0075  max mem: 31830
Epoch: [279]  [230/312]  eta: 0:00:46  lr: 0.000052  min_lr: 0.000052  loss: 3.4346 (3.1714)  weight_decay: 0.0500 (0.0500)  time: 0.4699  data: 0.0157  max mem: 31830
Epoch: [279]  [240/312]  eta: 0:00:41  lr: 0.000052  min_lr: 0.000052  loss: 3.4346 (3.1734)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0096  max mem: 31830
Epoch: [279]  [250/312]  eta: 0:00:35  lr: 0.000052  min_lr: 0.000052  loss: 3.2856 (3.1696)  weight_decay: 0.0500 (0.0500)  time: 0.6118  data: 0.0075  max mem: 31830
Epoch: [279]  [260/312]  eta: 0:00:29  lr: 0.000052  min_lr: 0.000052  loss: 3.2673 (3.1758)  weight_decay: 0.0500 (0.0500)  time: 0.4865  data: 0.0120  max mem: 31830
Epoch: [279]  [270/312]  eta: 0:00:23  lr: 0.000052  min_lr: 0.000052  loss: 3.3506 (3.1781)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0058  max mem: 31830
Epoch: [279]  [280/312]  eta: 0:00:18  lr: 0.000052  min_lr: 0.000052  loss: 3.1511 (3.1801)  weight_decay: 0.0500 (0.0500)  time: 0.5952  data: 0.0217  max mem: 31830
Epoch: [279]  [290/312]  eta: 0:00:12  lr: 0.000051  min_lr: 0.000051  loss: 3.2822 (3.1832)  weight_decay: 0.0500 (0.0500)  time: 0.5354  data: 0.0271  max mem: 31830
Epoch: [279]  [300/312]  eta: 0:00:06  lr: 0.000051  min_lr: 0.000051  loss: 3.3319 (3.1797)  weight_decay: 0.0500 (0.0500)  time: 0.4813  data: 0.0059  max mem: 31830
Epoch: [279]  [310/312]  eta: 0:00:01  lr: 0.000051  min_lr: 0.000051  loss: 3.2554 (3.1850)  weight_decay: 0.0500 (0.0500)  time: 0.4217  data: 0.0001  max mem: 31830
Epoch: [279]  [311/312]  eta: 0:00:00  lr: 0.000051  min_lr: 0.000051  loss: 3.2554 (3.1833)  weight_decay: 0.0500 (0.0500)  time: 0.4214  data: 0.0001  max mem: 31830
Epoch: [279] Total time: 0:02:54 (0.5595 s / it)
Averaged stats: lr: 0.000051  min_lr: 0.000051  loss: 3.2554 (3.1814)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.9044 (0.9044)  acc1: 84.3750 (84.3750)  acc5: 97.1354 (97.1354)  time: 8.2767  data: 8.1066  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1940 (1.1088)  acc1: 79.0365 (78.0960)  acc5: 94.6615 (94.4320)  time: 1.0577  data: 0.9211  max mem: 31830
Test: Total time: 0:00:09 (1.0804 s / it)
* Acc@1 78.486 Acc@5 94.432 loss 1.106
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.56%
Epoch: [280]  [  0/312]  eta: 0:58:53  lr: 0.000051  min_lr: 0.000051  loss: 3.8510 (3.8510)  weight_decay: 0.0500 (0.0500)  time: 11.3261  data: 10.3702  max mem: 31830
Epoch: [280]  [ 10/312]  eta: 0:09:06  lr: 0.000051  min_lr: 0.000051  loss: 3.5709 (3.3755)  weight_decay: 0.0500 (0.0500)  time: 1.8099  data: 1.1044  max mem: 31830
Epoch: [280]  [ 20/312]  eta: 0:05:31  lr: 0.000051  min_lr: 0.000051  loss: 3.2400 (3.2436)  weight_decay: 0.0500 (0.0500)  time: 0.6272  data: 0.0894  max mem: 31830
Epoch: [280]  [ 30/312]  eta: 0:04:13  lr: 0.000051  min_lr: 0.000051  loss: 3.2400 (3.2300)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0009  max mem: 31830
Epoch: [280]  [ 40/312]  eta: 0:03:31  lr: 0.000050  min_lr: 0.000050  loss: 3.1909 (3.1905)  weight_decay: 0.0500 (0.0500)  time: 0.4004  data: 0.0010  max mem: 31830
Epoch: [280]  [ 50/312]  eta: 0:03:04  lr: 0.000050  min_lr: 0.000050  loss: 3.1731 (3.1638)  weight_decay: 0.0500 (0.0500)  time: 0.3975  data: 0.0010  max mem: 31830
Epoch: [280]  [ 60/312]  eta: 0:02:44  lr: 0.000050  min_lr: 0.000050  loss: 3.2090 (3.1664)  weight_decay: 0.0500 (0.0500)  time: 0.3957  data: 0.0015  max mem: 31830
Epoch: [280]  [ 70/312]  eta: 0:02:33  lr: 0.000050  min_lr: 0.000050  loss: 3.2769 (3.1672)  weight_decay: 0.0500 (0.0500)  time: 0.4581  data: 0.0145  max mem: 31830
Epoch: [280]  [ 80/312]  eta: 0:02:22  lr: 0.000050  min_lr: 0.000050  loss: 3.3533 (3.1388)  weight_decay: 0.0500 (0.0500)  time: 0.4900  data: 0.0353  max mem: 31830
Epoch: [280]  [ 90/312]  eta: 0:02:14  lr: 0.000050  min_lr: 0.000050  loss: 3.2824 (3.1605)  weight_decay: 0.0500 (0.0500)  time: 0.5143  data: 0.0600  max mem: 31830
Epoch: [280]  [100/312]  eta: 0:02:06  lr: 0.000050  min_lr: 0.000050  loss: 3.3722 (3.1709)  weight_decay: 0.0500 (0.0500)  time: 0.5432  data: 0.0853  max mem: 31830
Epoch: [280]  [110/312]  eta: 0:02:00  lr: 0.000049  min_lr: 0.000049  loss: 3.1518 (3.1516)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0673  max mem: 31830
Epoch: [280]  [120/312]  eta: 0:01:54  lr: 0.000049  min_lr: 0.000049  loss: 3.0285 (3.1438)  weight_decay: 0.0500 (0.0500)  time: 0.5999  data: 0.0465  max mem: 31830
Epoch: [280]  [130/312]  eta: 0:01:47  lr: 0.000049  min_lr: 0.000049  loss: 3.3069 (3.1571)  weight_decay: 0.0500 (0.0500)  time: 0.5413  data: 0.0541  max mem: 31830
Epoch: [280]  [140/312]  eta: 0:01:41  lr: 0.000049  min_lr: 0.000049  loss: 3.4477 (3.1661)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0336  max mem: 31830
Epoch: [280]  [150/312]  eta: 0:01:35  lr: 0.000049  min_lr: 0.000049  loss: 3.0426 (3.1399)  weight_decay: 0.0500 (0.0500)  time: 0.6084  data: 0.0208  max mem: 31830
Epoch: [280]  [160/312]  eta: 0:01:27  lr: 0.000049  min_lr: 0.000049  loss: 2.9708 (3.1391)  weight_decay: 0.0500 (0.0500)  time: 0.4867  data: 0.0158  max mem: 31830
Epoch: [280]  [170/312]  eta: 0:01:23  lr: 0.000048  min_lr: 0.000048  loss: 3.3897 (3.1557)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0013  max mem: 31830
Epoch: [280]  [180/312]  eta: 0:01:16  lr: 0.000048  min_lr: 0.000048  loss: 3.3897 (3.1547)  weight_decay: 0.0500 (0.0500)  time: 0.5579  data: 0.0010  max mem: 31830
Epoch: [280]  [190/312]  eta: 0:01:10  lr: 0.000048  min_lr: 0.000048  loss: 3.2658 (3.1578)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.0011  max mem: 31830
Epoch: [280]  [200/312]  eta: 0:01:04  lr: 0.000048  min_lr: 0.000048  loss: 3.1639 (3.1571)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0217  max mem: 31830
Epoch: [280]  [210/312]  eta: 0:00:58  lr: 0.000048  min_lr: 0.000048  loss: 3.2201 (3.1647)  weight_decay: 0.0500 (0.0500)  time: 0.5281  data: 0.0279  max mem: 31830
Epoch: [280]  [220/312]  eta: 0:00:52  lr: 0.000048  min_lr: 0.000048  loss: 3.4206 (3.1753)  weight_decay: 0.0500 (0.0500)  time: 0.5567  data: 0.0071  max mem: 31830
Epoch: [280]  [230/312]  eta: 0:00:46  lr: 0.000048  min_lr: 0.000048  loss: 3.4161 (3.1722)  weight_decay: 0.0500 (0.0500)  time: 0.5727  data: 0.0124  max mem: 31830
Epoch: [280]  [240/312]  eta: 0:00:40  lr: 0.000047  min_lr: 0.000047  loss: 3.2208 (3.1689)  weight_decay: 0.0500 (0.0500)  time: 0.5134  data: 0.0146  max mem: 31830
Epoch: [280]  [250/312]  eta: 0:00:35  lr: 0.000047  min_lr: 0.000047  loss: 3.3732 (3.1761)  weight_decay: 0.0500 (0.0500)  time: 0.5758  data: 0.0082  max mem: 31830
Epoch: [280]  [260/312]  eta: 0:00:29  lr: 0.000047  min_lr: 0.000047  loss: 3.3439 (3.1669)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0060  max mem: 31830
Epoch: [280]  [270/312]  eta: 0:00:23  lr: 0.000047  min_lr: 0.000047  loss: 3.3427 (3.1753)  weight_decay: 0.0500 (0.0500)  time: 0.5273  data: 0.0011  max mem: 31830
Epoch: [280]  [280/312]  eta: 0:00:18  lr: 0.000047  min_lr: 0.000047  loss: 3.3058 (3.1691)  weight_decay: 0.0500 (0.0500)  time: 0.6348  data: 0.0029  max mem: 31830
Epoch: [280]  [290/312]  eta: 0:00:12  lr: 0.000047  min_lr: 0.000047  loss: 3.0566 (3.1661)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0023  max mem: 31830
Epoch: [280]  [300/312]  eta: 0:00:06  lr: 0.000046  min_lr: 0.000046  loss: 3.2795 (3.1669)  weight_decay: 0.0500 (0.0500)  time: 0.4582  data: 0.0002  max mem: 31830
Epoch: [280]  [310/312]  eta: 0:00:01  lr: 0.000046  min_lr: 0.000046  loss: 3.2795 (3.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0002  max mem: 31830
Epoch: [280]  [311/312]  eta: 0:00:00  lr: 0.000046  min_lr: 0.000046  loss: 3.2795 (3.1649)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0002  max mem: 31830
Epoch: [280] Total time: 0:02:54 (0.5602 s / it)
Averaged stats: lr: 0.000046  min_lr: 0.000046  loss: 3.2795 (3.1819)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8375 (0.8375)  acc1: 85.2865 (85.2865)  acc5: 97.1354 (97.1354)  time: 8.3139  data: 8.1464  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1329 (1.0579)  acc1: 79.6875 (78.4480)  acc5: 94.6615 (94.3840)  time: 1.0416  data: 0.9052  max mem: 31830
Test: Total time: 0:00:09 (1.0541 s / it)
* Acc@1 78.548 Acc@5 94.448 loss 1.054
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.56%
Epoch: [281]  [  0/312]  eta: 1:01:17  lr: 0.000046  min_lr: 0.000046  loss: 3.2203 (3.2203)  weight_decay: 0.0500 (0.0500)  time: 11.7882  data: 10.4368  max mem: 31830
Epoch: [281]  [ 10/312]  eta: 0:08:49  lr: 0.000046  min_lr: 0.000046  loss: 2.9778 (3.0102)  weight_decay: 0.0500 (0.0500)  time: 1.7548  data: 0.9493  max mem: 31830
Epoch: [281]  [ 20/312]  eta: 0:05:35  lr: 0.000046  min_lr: 0.000046  loss: 3.0835 (3.0735)  weight_decay: 0.0500 (0.0500)  time: 0.6175  data: 0.0471  max mem: 31830
Epoch: [281]  [ 30/312]  eta: 0:04:15  lr: 0.000046  min_lr: 0.000046  loss: 3.2958 (3.1453)  weight_decay: 0.0500 (0.0500)  time: 0.4410  data: 0.0472  max mem: 31830
Epoch: [281]  [ 40/312]  eta: 0:03:33  lr: 0.000046  min_lr: 0.000046  loss: 3.4019 (3.1359)  weight_decay: 0.0500 (0.0500)  time: 0.3990  data: 0.0010  max mem: 31830
Epoch: [281]  [ 50/312]  eta: 0:03:05  lr: 0.000046  min_lr: 0.000046  loss: 3.3950 (3.1457)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0012  max mem: 31830
Epoch: [281]  [ 60/312]  eta: 0:02:45  lr: 0.000045  min_lr: 0.000045  loss: 3.2645 (3.1482)  weight_decay: 0.0500 (0.0500)  time: 0.3994  data: 0.0011  max mem: 31830
Epoch: [281]  [ 70/312]  eta: 0:02:34  lr: 0.000045  min_lr: 0.000045  loss: 2.9882 (3.1339)  weight_decay: 0.0500 (0.0500)  time: 0.4545  data: 0.0312  max mem: 31830
Epoch: [281]  [ 80/312]  eta: 0:02:24  lr: 0.000045  min_lr: 0.000045  loss: 3.1290 (3.1544)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0849  max mem: 31830
Epoch: [281]  [ 90/312]  eta: 0:02:15  lr: 0.000045  min_lr: 0.000045  loss: 3.4448 (3.1778)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0545  max mem: 31830
Epoch: [281]  [100/312]  eta: 0:02:09  lr: 0.000045  min_lr: 0.000045  loss: 3.4525 (3.1798)  weight_decay: 0.0500 (0.0500)  time: 0.5669  data: 0.0389  max mem: 31830
Epoch: [281]  [110/312]  eta: 0:02:00  lr: 0.000045  min_lr: 0.000045  loss: 3.2231 (3.1737)  weight_decay: 0.0500 (0.0500)  time: 0.5222  data: 0.0391  max mem: 31830
Epoch: [281]  [120/312]  eta: 0:01:54  lr: 0.000044  min_lr: 0.000044  loss: 3.4472 (3.1755)  weight_decay: 0.0500 (0.0500)  time: 0.5108  data: 0.0504  max mem: 31830
Epoch: [281]  [130/312]  eta: 0:01:46  lr: 0.000044  min_lr: 0.000044  loss: 3.3266 (3.1821)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0796  max mem: 31830
Epoch: [281]  [140/312]  eta: 0:01:41  lr: 0.000044  min_lr: 0.000044  loss: 3.2229 (3.1837)  weight_decay: 0.0500 (0.0500)  time: 0.5476  data: 0.0310  max mem: 31830
Epoch: [281]  [150/312]  eta: 0:01:35  lr: 0.000044  min_lr: 0.000044  loss: 3.1237 (3.1699)  weight_decay: 0.0500 (0.0500)  time: 0.6067  data: 0.0181  max mem: 31830
Epoch: [281]  [160/312]  eta: 0:01:28  lr: 0.000044  min_lr: 0.000044  loss: 3.1653 (3.1718)  weight_decay: 0.0500 (0.0500)  time: 0.5254  data: 0.0174  max mem: 31830
Epoch: [281]  [170/312]  eta: 0:01:22  lr: 0.000044  min_lr: 0.000044  loss: 3.1653 (3.1616)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0016  max mem: 31830
Epoch: [281]  [180/312]  eta: 0:01:17  lr: 0.000044  min_lr: 0.000044  loss: 3.2116 (3.1651)  weight_decay: 0.0500 (0.0500)  time: 0.6198  data: 0.0016  max mem: 31830
Epoch: [281]  [190/312]  eta: 0:01:10  lr: 0.000043  min_lr: 0.000043  loss: 3.2116 (3.1615)  weight_decay: 0.0500 (0.0500)  time: 0.5247  data: 0.0010  max mem: 31830
Epoch: [281]  [200/312]  eta: 0:01:04  lr: 0.000043  min_lr: 0.000043  loss: 3.2466 (3.1664)  weight_decay: 0.0500 (0.0500)  time: 0.5250  data: 0.0009  max mem: 31830
Epoch: [281]  [210/312]  eta: 0:00:58  lr: 0.000043  min_lr: 0.000043  loss: 3.4439 (3.1754)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0008  max mem: 31830
Epoch: [281]  [220/312]  eta: 0:00:52  lr: 0.000043  min_lr: 0.000043  loss: 3.4985 (3.1810)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.0008  max mem: 31830
Epoch: [281]  [230/312]  eta: 0:00:47  lr: 0.000043  min_lr: 0.000043  loss: 3.4585 (3.1775)  weight_decay: 0.0500 (0.0500)  time: 0.6275  data: 0.0010  max mem: 31830
Epoch: [281]  [240/312]  eta: 0:00:40  lr: 0.000043  min_lr: 0.000043  loss: 2.9589 (3.1624)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0010  max mem: 31830
Epoch: [281]  [250/312]  eta: 0:00:35  lr: 0.000043  min_lr: 0.000043  loss: 2.9966 (3.1638)  weight_decay: 0.0500 (0.0500)  time: 0.5186  data: 0.0020  max mem: 31830
Epoch: [281]  [260/312]  eta: 0:00:29  lr: 0.000042  min_lr: 0.000042  loss: 3.2810 (3.1658)  weight_decay: 0.0500 (0.0500)  time: 0.5958  data: 0.0028  max mem: 31830
Epoch: [281]  [270/312]  eta: 0:00:23  lr: 0.000042  min_lr: 0.000042  loss: 3.2717 (3.1610)  weight_decay: 0.0500 (0.0500)  time: 0.5091  data: 0.0017  max mem: 31830
Epoch: [281]  [280/312]  eta: 0:00:18  lr: 0.000042  min_lr: 0.000042  loss: 3.1896 (3.1642)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0033  max mem: 31830
Epoch: [281]  [290/312]  eta: 0:00:12  lr: 0.000042  min_lr: 0.000042  loss: 3.3789 (3.1722)  weight_decay: 0.0500 (0.0500)  time: 0.5666  data: 0.0318  max mem: 31830
Epoch: [281]  [300/312]  eta: 0:00:06  lr: 0.000042  min_lr: 0.000042  loss: 3.3307 (3.1624)  weight_decay: 0.0500 (0.0500)  time: 0.4729  data: 0.0290  max mem: 31830
Epoch: [281]  [310/312]  eta: 0:00:01  lr: 0.000042  min_lr: 0.000042  loss: 3.3766 (3.1743)  weight_decay: 0.0500 (0.0500)  time: 0.4235  data: 0.0002  max mem: 31830
Epoch: [281]  [311/312]  eta: 0:00:00  lr: 0.000042  min_lr: 0.000042  loss: 3.4079 (3.1754)  weight_decay: 0.0500 (0.0500)  time: 0.3817  data: 0.0002  max mem: 31830
Epoch: [281] Total time: 0:02:54 (0.5600 s / it)
Averaged stats: lr: 0.000042  min_lr: 0.000042  loss: 3.4079 (3.1661)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9602 (0.9602)  acc1: 84.5052 (84.5052)  acc5: 97.1354 (97.1354)  time: 8.8753  data: 8.7133  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2599 (1.1814)  acc1: 79.0365 (78.0480)  acc5: 94.6615 (94.3520)  time: 1.1039  data: 0.9682  max mem: 31830
Test: Total time: 0:00:10 (1.1264 s / it)
* Acc@1 78.460 Acc@5 94.446 loss 1.177
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.56%
Epoch: [282]  [  0/312]  eta: 1:04:26  lr: 0.000042  min_lr: 0.000042  loss: 3.4801 (3.4801)  weight_decay: 0.0500 (0.0500)  time: 12.3920  data: 9.7372  max mem: 31830
Epoch: [282]  [ 10/312]  eta: 0:08:40  lr: 0.000041  min_lr: 0.000041  loss: 3.3772 (3.2729)  weight_decay: 0.0500 (0.0500)  time: 1.7233  data: 0.9440  max mem: 31830
Epoch: [282]  [ 20/312]  eta: 0:05:41  lr: 0.000041  min_lr: 0.000041  loss: 3.2907 (3.1434)  weight_decay: 0.0500 (0.0500)  time: 0.6096  data: 0.0959  max mem: 31830
Epoch: [282]  [ 30/312]  eta: 0:04:19  lr: 0.000041  min_lr: 0.000041  loss: 3.2269 (3.1393)  weight_decay: 0.0500 (0.0500)  time: 0.4765  data: 0.0639  max mem: 31830
Epoch: [282]  [ 40/312]  eta: 0:03:35  lr: 0.000041  min_lr: 0.000041  loss: 3.2269 (3.0773)  weight_decay: 0.0500 (0.0500)  time: 0.3972  data: 0.0038  max mem: 31830
Epoch: [282]  [ 50/312]  eta: 0:03:07  lr: 0.000041  min_lr: 0.000041  loss: 3.0317 (3.0611)  weight_decay: 0.0500 (0.0500)  time: 0.3987  data: 0.0039  max mem: 31830
Epoch: [282]  [ 60/312]  eta: 0:02:46  lr: 0.000041  min_lr: 0.000041  loss: 3.1861 (3.0906)  weight_decay: 0.0500 (0.0500)  time: 0.3934  data: 0.0010  max mem: 31830
Epoch: [282]  [ 70/312]  eta: 0:02:34  lr: 0.000041  min_lr: 0.000041  loss: 3.1861 (3.0864)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0022  max mem: 31830
Epoch: [282]  [ 80/312]  eta: 0:02:26  lr: 0.000040  min_lr: 0.000040  loss: 3.1121 (3.0846)  weight_decay: 0.0500 (0.0500)  time: 0.5373  data: 0.0021  max mem: 31830
Epoch: [282]  [ 90/312]  eta: 0:02:15  lr: 0.000040  min_lr: 0.000040  loss: 3.3379 (3.1094)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0337  max mem: 31830
Epoch: [282]  [100/312]  eta: 0:02:08  lr: 0.000040  min_lr: 0.000040  loss: 3.2649 (3.0889)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0401  max mem: 31830
Epoch: [282]  [110/312]  eta: 0:01:59  lr: 0.000040  min_lr: 0.000040  loss: 3.0304 (3.0990)  weight_decay: 0.0500 (0.0500)  time: 0.4907  data: 0.0203  max mem: 31830
Epoch: [282]  [120/312]  eta: 0:01:54  lr: 0.000040  min_lr: 0.000040  loss: 3.1325 (3.0957)  weight_decay: 0.0500 (0.0500)  time: 0.5305  data: 0.0295  max mem: 31830
Epoch: [282]  [130/312]  eta: 0:01:48  lr: 0.000040  min_lr: 0.000040  loss: 3.2369 (3.1055)  weight_decay: 0.0500 (0.0500)  time: 0.6211  data: 0.0219  max mem: 31830
Epoch: [282]  [140/312]  eta: 0:01:40  lr: 0.000040  min_lr: 0.000040  loss: 3.2369 (3.1030)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0446  max mem: 31830
Epoch: [282]  [150/312]  eta: 0:01:34  lr: 0.000040  min_lr: 0.000040  loss: 2.9985 (3.0934)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0391  max mem: 31830
Epoch: [282]  [160/312]  eta: 0:01:29  lr: 0.000039  min_lr: 0.000039  loss: 2.9985 (3.0885)  weight_decay: 0.0500 (0.0500)  time: 0.6226  data: 0.0068  max mem: 31830
Epoch: [282]  [170/312]  eta: 0:01:22  lr: 0.000039  min_lr: 0.000039  loss: 3.3703 (3.1011)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.0192  max mem: 31830
Epoch: [282]  [180/312]  eta: 0:01:16  lr: 0.000039  min_lr: 0.000039  loss: 3.1277 (3.0932)  weight_decay: 0.0500 (0.0500)  time: 0.4945  data: 0.0133  max mem: 31830
Epoch: [282]  [190/312]  eta: 0:01:09  lr: 0.000039  min_lr: 0.000039  loss: 3.3761 (3.1084)  weight_decay: 0.0500 (0.0500)  time: 0.4842  data: 0.0010  max mem: 31830
Epoch: [282]  [200/312]  eta: 0:01:04  lr: 0.000039  min_lr: 0.000039  loss: 3.4052 (3.1101)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0010  max mem: 31830
Epoch: [282]  [210/312]  eta: 0:00:58  lr: 0.000039  min_lr: 0.000039  loss: 3.3842 (3.1231)  weight_decay: 0.0500 (0.0500)  time: 0.6539  data: 0.0010  max mem: 31830
Epoch: [282]  [220/312]  eta: 0:00:52  lr: 0.000039  min_lr: 0.000039  loss: 3.3733 (3.1240)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0049  max mem: 31830
Epoch: [282]  [230/312]  eta: 0:00:46  lr: 0.000038  min_lr: 0.000038  loss: 3.0768 (3.1172)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0048  max mem: 31830
Epoch: [282]  [240/312]  eta: 0:00:41  lr: 0.000038  min_lr: 0.000038  loss: 2.9378 (3.1127)  weight_decay: 0.0500 (0.0500)  time: 0.5944  data: 0.0058  max mem: 31830
Epoch: [282]  [250/312]  eta: 0:00:35  lr: 0.000038  min_lr: 0.000038  loss: 3.1145 (3.1048)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0102  max mem: 31830
Epoch: [282]  [260/312]  eta: 0:00:29  lr: 0.000038  min_lr: 0.000038  loss: 3.1145 (3.1097)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0057  max mem: 31830
Epoch: [282]  [270/312]  eta: 0:00:23  lr: 0.000038  min_lr: 0.000038  loss: 3.0319 (3.1100)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.0072  max mem: 31830
Epoch: [282]  [280/312]  eta: 0:00:18  lr: 0.000038  min_lr: 0.000038  loss: 3.2106 (3.1126)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0079  max mem: 31830
Epoch: [282]  [290/312]  eta: 0:00:12  lr: 0.000038  min_lr: 0.000038  loss: 3.3765 (3.1206)  weight_decay: 0.0500 (0.0500)  time: 0.6338  data: 0.0017  max mem: 31830
Epoch: [282]  [300/312]  eta: 0:00:06  lr: 0.000037  min_lr: 0.000037  loss: 3.4072 (3.1274)  weight_decay: 0.0500 (0.0500)  time: 0.5023  data: 0.0002  max mem: 31830
Epoch: [282]  [310/312]  eta: 0:00:01  lr: 0.000037  min_lr: 0.000037  loss: 3.2862 (3.1281)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [282]  [311/312]  eta: 0:00:00  lr: 0.000037  min_lr: 0.000037  loss: 3.2719 (3.1252)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [282] Total time: 0:02:54 (0.5579 s / it)
Averaged stats: lr: 0.000037  min_lr: 0.000037  loss: 3.2719 (3.1614)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8458 (0.8458)  acc1: 85.0260 (85.0260)  acc5: 97.1354 (97.1354)  time: 8.5093  data: 8.3499  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1314 (1.0638)  acc1: 79.6875 (78.2720)  acc5: 94.9219 (94.5120)  time: 1.0704  data: 0.9363  max mem: 31830
Test: Total time: 0:00:09 (1.0854 s / it)
* Acc@1 78.620 Acc@5 94.442 loss 1.062
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.62%
Epoch: [283]  [  0/312]  eta: 1:01:55  lr: 0.000037  min_lr: 0.000037  loss: 2.2747 (2.2747)  weight_decay: 0.0500 (0.0500)  time: 11.9094  data: 8.7488  max mem: 31830
Epoch: [283]  [ 10/312]  eta: 0:08:31  lr: 0.000037  min_lr: 0.000037  loss: 3.2082 (3.1201)  weight_decay: 0.0500 (0.0500)  time: 1.6942  data: 0.9295  max mem: 31830
Epoch: [283]  [ 20/312]  eta: 0:05:27  lr: 0.000037  min_lr: 0.000037  loss: 3.2082 (3.0815)  weight_decay: 0.0500 (0.0500)  time: 0.5839  data: 0.0742  max mem: 31830
Epoch: [283]  [ 30/312]  eta: 0:04:10  lr: 0.000037  min_lr: 0.000037  loss: 3.3723 (3.1809)  weight_decay: 0.0500 (0.0500)  time: 0.4475  data: 0.0013  max mem: 31830
Epoch: [283]  [ 40/312]  eta: 0:03:29  lr: 0.000037  min_lr: 0.000037  loss: 3.1759 (3.1105)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0016  max mem: 31830
Epoch: [283]  [ 50/312]  eta: 0:03:02  lr: 0.000037  min_lr: 0.000037  loss: 2.9767 (3.0869)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0012  max mem: 31830
Epoch: [283]  [ 60/312]  eta: 0:02:43  lr: 0.000036  min_lr: 0.000036  loss: 3.3332 (3.1313)  weight_decay: 0.0500 (0.0500)  time: 0.3993  data: 0.0009  max mem: 31830
Epoch: [283]  [ 70/312]  eta: 0:02:31  lr: 0.000036  min_lr: 0.000036  loss: 3.4408 (3.1626)  weight_decay: 0.0500 (0.0500)  time: 0.4499  data: 0.0521  max mem: 31830
Epoch: [283]  [ 80/312]  eta: 0:02:25  lr: 0.000036  min_lr: 0.000036  loss: 3.2419 (3.1762)  weight_decay: 0.0500 (0.0500)  time: 0.5556  data: 0.1136  max mem: 31830
Epoch: [283]  [ 90/312]  eta: 0:02:15  lr: 0.000036  min_lr: 0.000036  loss: 3.3673 (3.2038)  weight_decay: 0.0500 (0.0500)  time: 0.5491  data: 0.0909  max mem: 31830
Epoch: [283]  [100/312]  eta: 0:02:09  lr: 0.000036  min_lr: 0.000036  loss: 3.3518 (3.1973)  weight_decay: 0.0500 (0.0500)  time: 0.5488  data: 0.0860  max mem: 31830
Epoch: [283]  [110/312]  eta: 0:01:59  lr: 0.000036  min_lr: 0.000036  loss: 3.3855 (3.2139)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0574  max mem: 31830
Epoch: [283]  [120/312]  eta: 0:01:55  lr: 0.000036  min_lr: 0.000036  loss: 3.3284 (3.1976)  weight_decay: 0.0500 (0.0500)  time: 0.5453  data: 0.0634  max mem: 31830
Epoch: [283]  [130/312]  eta: 0:01:49  lr: 0.000036  min_lr: 0.000036  loss: 3.0546 (3.1940)  weight_decay: 0.0500 (0.0500)  time: 0.6523  data: 0.0924  max mem: 31830
Epoch: [283]  [140/312]  eta: 0:01:40  lr: 0.000035  min_lr: 0.000035  loss: 3.4489 (3.2098)  weight_decay: 0.0500 (0.0500)  time: 0.5078  data: 0.0357  max mem: 31830
Epoch: [283]  [150/312]  eta: 0:01:35  lr: 0.000035  min_lr: 0.000035  loss: 3.3253 (3.2054)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0748  max mem: 31830
Epoch: [283]  [160/312]  eta: 0:01:28  lr: 0.000035  min_lr: 0.000035  loss: 3.2828 (3.2165)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.0689  max mem: 31830
Epoch: [283]  [170/312]  eta: 0:01:21  lr: 0.000035  min_lr: 0.000035  loss: 3.2903 (3.2113)  weight_decay: 0.0500 (0.0500)  time: 0.4743  data: 0.0356  max mem: 31830
Epoch: [283]  [180/312]  eta: 0:01:16  lr: 0.000035  min_lr: 0.000035  loss: 3.2903 (3.2197)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0919  max mem: 31830
Epoch: [283]  [190/312]  eta: 0:01:09  lr: 0.000035  min_lr: 0.000035  loss: 3.2883 (3.2188)  weight_decay: 0.0500 (0.0500)  time: 0.5201  data: 0.0572  max mem: 31830
Epoch: [283]  [200/312]  eta: 0:01:04  lr: 0.000035  min_lr: 0.000035  loss: 3.2594 (3.2083)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0438  max mem: 31830
Epoch: [283]  [210/312]  eta: 0:00:58  lr: 0.000034  min_lr: 0.000034  loss: 3.3076 (3.2158)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0739  max mem: 31830
Epoch: [283]  [220/312]  eta: 0:00:52  lr: 0.000034  min_lr: 0.000034  loss: 3.3083 (3.2153)  weight_decay: 0.0500 (0.0500)  time: 0.4994  data: 0.0497  max mem: 31830
Epoch: [283]  [230/312]  eta: 0:00:46  lr: 0.000034  min_lr: 0.000034  loss: 3.2792 (3.2145)  weight_decay: 0.0500 (0.0500)  time: 0.5148  data: 0.0815  max mem: 31830
Epoch: [283]  [240/312]  eta: 0:00:40  lr: 0.000034  min_lr: 0.000034  loss: 3.2892 (3.2083)  weight_decay: 0.0500 (0.0500)  time: 0.5537  data: 0.0635  max mem: 31830
Epoch: [283]  [250/312]  eta: 0:00:34  lr: 0.000034  min_lr: 0.000034  loss: 3.3976 (3.2099)  weight_decay: 0.0500 (0.0500)  time: 0.5120  data: 0.0582  max mem: 31830
Epoch: [283]  [260/312]  eta: 0:00:29  lr: 0.000034  min_lr: 0.000034  loss: 3.3976 (3.2108)  weight_decay: 0.0500 (0.0500)  time: 0.6236  data: 0.1327  max mem: 31830
Epoch: [283]  [270/312]  eta: 0:00:23  lr: 0.000034  min_lr: 0.000034  loss: 3.0869 (3.2004)  weight_decay: 0.0500 (0.0500)  time: 0.5788  data: 0.0761  max mem: 31830
Epoch: [283]  [280/312]  eta: 0:00:18  lr: 0.000034  min_lr: 0.000034  loss: 3.1720 (3.2045)  weight_decay: 0.0500 (0.0500)  time: 0.4885  data: 0.0327  max mem: 31830
Epoch: [283]  [290/312]  eta: 0:00:12  lr: 0.000033  min_lr: 0.000033  loss: 3.2516 (3.2008)  weight_decay: 0.0500 (0.0500)  time: 0.6051  data: 0.0671  max mem: 31830
Epoch: [283]  [300/312]  eta: 0:00:06  lr: 0.000033  min_lr: 0.000033  loss: 3.4295 (3.2062)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0348  max mem: 31830
Epoch: [283]  [310/312]  eta: 0:00:01  lr: 0.000033  min_lr: 0.000033  loss: 3.4303 (3.2056)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0002  max mem: 31830
Epoch: [283]  [311/312]  eta: 0:00:00  lr: 0.000033  min_lr: 0.000033  loss: 3.4303 (3.2051)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [283] Total time: 0:02:54 (0.5589 s / it)
Averaged stats: lr: 0.000033  min_lr: 0.000033  loss: 3.4303 (3.1548)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.8792 (0.8792)  acc1: 85.0260 (85.0260)  acc5: 97.2656 (97.2656)  time: 9.1112  data: 8.9440  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1561 (1.0885)  acc1: 79.5573 (78.2240)  acc5: 95.1823 (94.4640)  time: 1.1294  data: 0.9939  max mem: 31830
Test: Total time: 0:00:10 (1.1412 s / it)
* Acc@1 78.508 Acc@5 94.448 loss 1.085
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.62%
Epoch: [284]  [  0/312]  eta: 1:01:46  lr: 0.000033  min_lr: 0.000033  loss: 3.2000 (3.2000)  weight_decay: 0.0500 (0.0500)  time: 11.8796  data: 8.2594  max mem: 31830
Epoch: [284]  [ 10/312]  eta: 0:08:50  lr: 0.000033  min_lr: 0.000033  loss: 3.3904 (3.3825)  weight_decay: 0.0500 (0.0500)  time: 1.7578  data: 1.0787  max mem: 31830
Epoch: [284]  [ 20/312]  eta: 0:05:34  lr: 0.000033  min_lr: 0.000033  loss: 3.3701 (3.3591)  weight_decay: 0.0500 (0.0500)  time: 0.6094  data: 0.1870  max mem: 31830
Epoch: [284]  [ 30/312]  eta: 0:04:15  lr: 0.000033  min_lr: 0.000033  loss: 3.3646 (3.3160)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0070  max mem: 31830
Epoch: [284]  [ 40/312]  eta: 0:03:32  lr: 0.000033  min_lr: 0.000033  loss: 3.4060 (3.2757)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0008  max mem: 31830
Epoch: [284]  [ 50/312]  eta: 0:03:04  lr: 0.000032  min_lr: 0.000032  loss: 3.4060 (3.2801)  weight_decay: 0.0500 (0.0500)  time: 0.3955  data: 0.0008  max mem: 31830
Epoch: [284]  [ 60/312]  eta: 0:02:45  lr: 0.000032  min_lr: 0.000032  loss: 3.3639 (3.2541)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0010  max mem: 31830
Epoch: [284]  [ 70/312]  eta: 0:02:29  lr: 0.000032  min_lr: 0.000032  loss: 3.3255 (3.2545)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0011  max mem: 31830
Epoch: [284]  [ 80/312]  eta: 0:02:20  lr: 0.000032  min_lr: 0.000032  loss: 3.2787 (3.2407)  weight_decay: 0.0500 (0.0500)  time: 0.4578  data: 0.0328  max mem: 31830
Epoch: [284]  [ 90/312]  eta: 0:02:12  lr: 0.000032  min_lr: 0.000032  loss: 3.3537 (3.2646)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0487  max mem: 31830
Epoch: [284]  [100/312]  eta: 0:02:08  lr: 0.000032  min_lr: 0.000032  loss: 3.3537 (3.2320)  weight_decay: 0.0500 (0.0500)  time: 0.5940  data: 0.0519  max mem: 31830
Epoch: [284]  [110/312]  eta: 0:01:58  lr: 0.000032  min_lr: 0.000032  loss: 3.2133 (3.2294)  weight_decay: 0.0500 (0.0500)  time: 0.5374  data: 0.0360  max mem: 31830
Epoch: [284]  [120/312]  eta: 0:01:52  lr: 0.000032  min_lr: 0.000032  loss: 3.4134 (3.2315)  weight_decay: 0.0500 (0.0500)  time: 0.4872  data: 0.0572  max mem: 31830
Epoch: [284]  [130/312]  eta: 0:01:46  lr: 0.000031  min_lr: 0.000031  loss: 3.2568 (3.2081)  weight_decay: 0.0500 (0.0500)  time: 0.5751  data: 0.1411  max mem: 31830
Epoch: [284]  [140/312]  eta: 0:01:38  lr: 0.000031  min_lr: 0.000031  loss: 3.0807 (3.2004)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0902  max mem: 31830
Epoch: [284]  [150/312]  eta: 0:01:33  lr: 0.000031  min_lr: 0.000031  loss: 3.2357 (3.1998)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0800  max mem: 31830
Epoch: [284]  [160/312]  eta: 0:01:27  lr: 0.000031  min_lr: 0.000031  loss: 3.2320 (3.1999)  weight_decay: 0.0500 (0.0500)  time: 0.5990  data: 0.1360  max mem: 31830
Epoch: [284]  [170/312]  eta: 0:01:21  lr: 0.000031  min_lr: 0.000031  loss: 3.0521 (3.1808)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0928  max mem: 31830
Epoch: [284]  [180/312]  eta: 0:01:16  lr: 0.000031  min_lr: 0.000031  loss: 3.0135 (3.1769)  weight_decay: 0.0500 (0.0500)  time: 0.5800  data: 0.1518  max mem: 31830
Epoch: [284]  [190/312]  eta: 0:01:09  lr: 0.000031  min_lr: 0.000031  loss: 3.2440 (3.1765)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.1209  max mem: 31830
Epoch: [284]  [200/312]  eta: 0:01:03  lr: 0.000031  min_lr: 0.000031  loss: 3.2440 (3.1703)  weight_decay: 0.0500 (0.0500)  time: 0.4871  data: 0.0653  max mem: 31830
Epoch: [284]  [210/312]  eta: 0:00:58  lr: 0.000030  min_lr: 0.000030  loss: 3.2869 (3.1663)  weight_decay: 0.0500 (0.0500)  time: 0.5981  data: 0.1467  max mem: 31830
Epoch: [284]  [220/312]  eta: 0:00:51  lr: 0.000030  min_lr: 0.000030  loss: 3.3316 (3.1690)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0829  max mem: 31830
Epoch: [284]  [230/312]  eta: 0:00:46  lr: 0.000030  min_lr: 0.000030  loss: 3.4181 (3.1765)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.0879  max mem: 31830
Epoch: [284]  [240/312]  eta: 0:00:40  lr: 0.000030  min_lr: 0.000030  loss: 3.1459 (3.1654)  weight_decay: 0.0500 (0.0500)  time: 0.6013  data: 0.1228  max mem: 31830
Epoch: [284]  [250/312]  eta: 0:00:34  lr: 0.000030  min_lr: 0.000030  loss: 3.1017 (3.1679)  weight_decay: 0.0500 (0.0500)  time: 0.4923  data: 0.0771  max mem: 31830
Epoch: [284]  [260/312]  eta: 0:00:29  lr: 0.000030  min_lr: 0.000030  loss: 3.1680 (3.1687)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.1337  max mem: 31830
Epoch: [284]  [270/312]  eta: 0:00:23  lr: 0.000030  min_lr: 0.000030  loss: 3.1680 (3.1737)  weight_decay: 0.0500 (0.0500)  time: 0.5115  data: 0.0931  max mem: 31830
Epoch: [284]  [280/312]  eta: 0:00:18  lr: 0.000030  min_lr: 0.000030  loss: 3.2397 (3.1763)  weight_decay: 0.0500 (0.0500)  time: 0.5521  data: 0.1545  max mem: 31830
Epoch: [284]  [290/312]  eta: 0:00:12  lr: 0.000030  min_lr: 0.000030  loss: 3.1135 (3.1698)  weight_decay: 0.0500 (0.0500)  time: 0.6314  data: 0.2363  max mem: 31830
Epoch: [284]  [300/312]  eta: 0:00:06  lr: 0.000029  min_lr: 0.000029  loss: 3.1548 (3.1760)  weight_decay: 0.0500 (0.0500)  time: 0.4673  data: 0.0822  max mem: 31830
Epoch: [284]  [310/312]  eta: 0:00:01  lr: 0.000029  min_lr: 0.000029  loss: 3.3533 (3.1751)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0002  max mem: 31830
Epoch: [284]  [311/312]  eta: 0:00:00  lr: 0.000029  min_lr: 0.000029  loss: 3.2469 (3.1716)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0001  max mem: 31830
Epoch: [284] Total time: 0:02:53 (0.5558 s / it)
Averaged stats: lr: 0.000029  min_lr: 0.000029  loss: 3.2469 (3.1665)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8615 (0.8615)  acc1: 84.7656 (84.7656)  acc5: 97.2656 (97.2656)  time: 8.6039  data: 8.4365  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1580 (1.0814)  acc1: 79.4271 (78.3200)  acc5: 94.9219 (94.5280)  time: 1.0789  data: 0.9421  max mem: 31830
Test: Total time: 0:00:09 (1.1047 s / it)
* Acc@1 78.562 Acc@5 94.450 loss 1.078
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.62%
Epoch: [285]  [  0/312]  eta: 1:05:56  lr: 0.000029  min_lr: 0.000029  loss: 2.5974 (2.5974)  weight_decay: 0.0500 (0.0500)  time: 12.6801  data: 8.8137  max mem: 31830
Epoch: [285]  [ 10/312]  eta: 0:08:42  lr: 0.000029  min_lr: 0.000029  loss: 3.4070 (3.2392)  weight_decay: 0.0500 (0.0500)  time: 1.7291  data: 1.0226  max mem: 31830
Epoch: [285]  [ 20/312]  eta: 0:05:35  lr: 0.000029  min_lr: 0.000029  loss: 3.2506 (3.2204)  weight_decay: 0.0500 (0.0500)  time: 0.5716  data: 0.1598  max mem: 31830
Epoch: [285]  [ 30/312]  eta: 0:04:15  lr: 0.000029  min_lr: 0.000029  loss: 3.1778 (3.1568)  weight_decay: 0.0500 (0.0500)  time: 0.4527  data: 0.0386  max mem: 31830
Epoch: [285]  [ 40/312]  eta: 0:03:32  lr: 0.000029  min_lr: 0.000029  loss: 3.1778 (3.1497)  weight_decay: 0.0500 (0.0500)  time: 0.3958  data: 0.0010  max mem: 31830
Epoch: [285]  [ 50/312]  eta: 0:03:04  lr: 0.000029  min_lr: 0.000029  loss: 3.1916 (3.1635)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0014  max mem: 31830
Epoch: [285]  [ 60/312]  eta: 0:02:45  lr: 0.000029  min_lr: 0.000029  loss: 3.2407 (3.1676)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0016  max mem: 31830
Epoch: [285]  [ 70/312]  eta: 0:02:34  lr: 0.000028  min_lr: 0.000028  loss: 3.3082 (3.1715)  weight_decay: 0.0500 (0.0500)  time: 0.4707  data: 0.0206  max mem: 31830
Epoch: [285]  [ 80/312]  eta: 0:02:27  lr: 0.000028  min_lr: 0.000028  loss: 3.3761 (3.1940)  weight_decay: 0.0500 (0.0500)  time: 0.5755  data: 0.0202  max mem: 31830
Epoch: [285]  [ 90/312]  eta: 0:02:16  lr: 0.000028  min_lr: 0.000028  loss: 3.3693 (3.1789)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0060  max mem: 31830
Epoch: [285]  [100/312]  eta: 0:02:10  lr: 0.000028  min_lr: 0.000028  loss: 3.0899 (3.1347)  weight_decay: 0.0500 (0.0500)  time: 0.5293  data: 0.0264  max mem: 31830
Epoch: [285]  [110/312]  eta: 0:02:00  lr: 0.000028  min_lr: 0.000028  loss: 3.0899 (3.1447)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.0214  max mem: 31830
Epoch: [285]  [120/312]  eta: 0:01:54  lr: 0.000028  min_lr: 0.000028  loss: 3.3533 (3.1465)  weight_decay: 0.0500 (0.0500)  time: 0.5192  data: 0.0075  max mem: 31830
Epoch: [285]  [130/312]  eta: 0:01:48  lr: 0.000028  min_lr: 0.000028  loss: 3.2013 (3.1294)  weight_decay: 0.0500 (0.0500)  time: 0.6122  data: 0.0074  max mem: 31830
Epoch: [285]  [140/312]  eta: 0:01:41  lr: 0.000028  min_lr: 0.000028  loss: 3.2013 (3.1435)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0159  max mem: 31830
Epoch: [285]  [150/312]  eta: 0:01:35  lr: 0.000027  min_lr: 0.000027  loss: 3.1997 (3.1245)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0214  max mem: 31830
Epoch: [285]  [160/312]  eta: 0:01:28  lr: 0.000027  min_lr: 0.000027  loss: 3.0684 (3.1298)  weight_decay: 0.0500 (0.0500)  time: 0.5506  data: 0.0066  max mem: 31830
Epoch: [285]  [170/312]  eta: 0:01:21  lr: 0.000027  min_lr: 0.000027  loss: 3.3566 (3.1289)  weight_decay: 0.0500 (0.0500)  time: 0.4973  data: 0.0080  max mem: 31830
Epoch: [285]  [180/312]  eta: 0:01:16  lr: 0.000027  min_lr: 0.000027  loss: 2.9480 (3.1186)  weight_decay: 0.0500 (0.0500)  time: 0.5389  data: 0.0263  max mem: 31830
Epoch: [285]  [190/312]  eta: 0:01:09  lr: 0.000027  min_lr: 0.000027  loss: 2.8731 (3.1208)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0243  max mem: 31830
Epoch: [285]  [200/312]  eta: 0:01:05  lr: 0.000027  min_lr: 0.000027  loss: 3.1613 (3.1170)  weight_decay: 0.0500 (0.0500)  time: 0.5998  data: 0.0486  max mem: 31830
Epoch: [285]  [210/312]  eta: 0:00:58  lr: 0.000027  min_lr: 0.000027  loss: 3.3076 (3.1263)  weight_decay: 0.0500 (0.0500)  time: 0.6174  data: 0.0437  max mem: 31830
Epoch: [285]  [220/312]  eta: 0:00:52  lr: 0.000027  min_lr: 0.000027  loss: 3.4070 (3.1286)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0144  max mem: 31830
Epoch: [285]  [230/312]  eta: 0:00:47  lr: 0.000027  min_lr: 0.000027  loss: 3.2108 (3.1275)  weight_decay: 0.0500 (0.0500)  time: 0.5633  data: 0.0298  max mem: 31830
Epoch: [285]  [240/312]  eta: 0:00:41  lr: 0.000026  min_lr: 0.000026  loss: 3.0962 (3.1274)  weight_decay: 0.0500 (0.0500)  time: 0.5934  data: 0.0332  max mem: 31830
Epoch: [285]  [250/312]  eta: 0:00:35  lr: 0.000026  min_lr: 0.000026  loss: 2.9962 (3.1111)  weight_decay: 0.0500 (0.0500)  time: 0.4936  data: 0.0374  max mem: 31830
Epoch: [285]  [260/312]  eta: 0:00:29  lr: 0.000026  min_lr: 0.000026  loss: 2.8183 (3.1106)  weight_decay: 0.0500 (0.0500)  time: 0.5593  data: 0.0207  max mem: 31830
Epoch: [285]  [270/312]  eta: 0:00:23  lr: 0.000026  min_lr: 0.000026  loss: 3.2986 (3.1105)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0188  max mem: 31830
Epoch: [285]  [280/312]  eta: 0:00:18  lr: 0.000026  min_lr: 0.000026  loss: 3.3112 (3.1103)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0343  max mem: 31830
Epoch: [285]  [290/312]  eta: 0:00:12  lr: 0.000026  min_lr: 0.000026  loss: 3.3112 (3.1138)  weight_decay: 0.0500 (0.0500)  time: 0.5468  data: 0.0162  max mem: 31830
Epoch: [285]  [300/312]  eta: 0:00:06  lr: 0.000026  min_lr: 0.000026  loss: 3.0922 (3.1103)  weight_decay: 0.0500 (0.0500)  time: 0.4438  data: 0.0002  max mem: 31830
Epoch: [285]  [310/312]  eta: 0:00:01  lr: 0.000026  min_lr: 0.000026  loss: 2.9544 (3.1077)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0002  max mem: 31830
Epoch: [285]  [311/312]  eta: 0:00:00  lr: 0.000026  min_lr: 0.000026  loss: 2.9137 (3.1064)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0001  max mem: 31830
Epoch: [285] Total time: 0:02:53 (0.5557 s / it)
Averaged stats: lr: 0.000026  min_lr: 0.000026  loss: 2.9137 (3.1542)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.8339 (0.8339)  acc1: 85.5469 (85.5469)  acc5: 97.3958 (97.3958)  time: 8.7130  data: 8.5454  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1250 (1.0519)  acc1: 79.1667 (78.4000)  acc5: 94.4010 (94.4800)  time: 1.0845  data: 0.9496  max mem: 31830
Test: Total time: 0:00:09 (1.0979 s / it)
* Acc@1 78.638 Acc@5 94.484 loss 1.048
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.64%
Epoch: [286]  [  0/312]  eta: 1:01:08  lr: 0.000026  min_lr: 0.000026  loss: 2.5099 (2.5099)  weight_decay: 0.0500 (0.0500)  time: 11.7578  data: 8.9261  max mem: 31830
Epoch: [286]  [ 10/312]  eta: 0:08:53  lr: 0.000026  min_lr: 0.000026  loss: 3.1829 (3.0406)  weight_decay: 0.0500 (0.0500)  time: 1.7652  data: 0.9293  max mem: 31830
Epoch: [286]  [ 20/312]  eta: 0:05:24  lr: 0.000025  min_lr: 0.000025  loss: 3.2134 (3.0382)  weight_decay: 0.0500 (0.0500)  time: 0.5781  data: 0.0652  max mem: 31830
Epoch: [286]  [ 30/312]  eta: 0:04:08  lr: 0.000025  min_lr: 0.000025  loss: 3.2134 (3.0663)  weight_decay: 0.0500 (0.0500)  time: 0.3950  data: 0.0008  max mem: 31830
Epoch: [286]  [ 40/312]  eta: 0:03:27  lr: 0.000025  min_lr: 0.000025  loss: 3.3212 (3.0996)  weight_decay: 0.0500 (0.0500)  time: 0.4001  data: 0.0010  max mem: 31830
Epoch: [286]  [ 50/312]  eta: 0:03:01  lr: 0.000025  min_lr: 0.000025  loss: 3.3444 (3.1526)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0014  max mem: 31830
Epoch: [286]  [ 60/312]  eta: 0:02:42  lr: 0.000025  min_lr: 0.000025  loss: 3.3986 (3.1743)  weight_decay: 0.0500 (0.0500)  time: 0.3996  data: 0.0015  max mem: 31830
Epoch: [286]  [ 70/312]  eta: 0:02:29  lr: 0.000025  min_lr: 0.000025  loss: 3.2759 (3.1789)  weight_decay: 0.0500 (0.0500)  time: 0.4275  data: 0.0017  max mem: 31830
Epoch: [286]  [ 80/312]  eta: 0:02:23  lr: 0.000025  min_lr: 0.000025  loss: 3.2759 (3.1829)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0614  max mem: 31830
Epoch: [286]  [ 90/312]  eta: 0:02:13  lr: 0.000025  min_lr: 0.000025  loss: 3.1450 (3.1682)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0608  max mem: 31830
Epoch: [286]  [100/312]  eta: 0:02:06  lr: 0.000025  min_lr: 0.000025  loss: 3.0771 (3.1631)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0479  max mem: 31830
Epoch: [286]  [110/312]  eta: 0:01:59  lr: 0.000024  min_lr: 0.000024  loss: 3.2323 (3.1842)  weight_decay: 0.0500 (0.0500)  time: 0.5518  data: 0.0737  max mem: 31830
Epoch: [286]  [120/312]  eta: 0:01:52  lr: 0.000024  min_lr: 0.000024  loss: 3.1680 (3.1624)  weight_decay: 0.0500 (0.0500)  time: 0.5473  data: 0.0398  max mem: 31830
Epoch: [286]  [130/312]  eta: 0:01:47  lr: 0.000024  min_lr: 0.000024  loss: 2.9879 (3.1565)  weight_decay: 0.0500 (0.0500)  time: 0.5750  data: 0.0269  max mem: 31830
Epoch: [286]  [140/312]  eta: 0:01:39  lr: 0.000024  min_lr: 0.000024  loss: 3.2611 (3.1483)  weight_decay: 0.0500 (0.0500)  time: 0.5381  data: 0.0138  max mem: 31830
Epoch: [286]  [150/312]  eta: 0:01:34  lr: 0.000024  min_lr: 0.000024  loss: 3.2947 (3.1537)  weight_decay: 0.0500 (0.0500)  time: 0.5461  data: 0.0066  max mem: 31830
Epoch: [286]  [160/312]  eta: 0:01:28  lr: 0.000024  min_lr: 0.000024  loss: 3.3006 (3.1611)  weight_decay: 0.0500 (0.0500)  time: 0.5964  data: 0.0257  max mem: 31830
Epoch: [286]  [170/312]  eta: 0:01:21  lr: 0.000024  min_lr: 0.000024  loss: 3.0993 (3.1415)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.0199  max mem: 31830
Epoch: [286]  [180/312]  eta: 0:01:16  lr: 0.000024  min_lr: 0.000024  loss: 3.1975 (3.1541)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0067  max mem: 31830
Epoch: [286]  [190/312]  eta: 0:01:09  lr: 0.000024  min_lr: 0.000024  loss: 3.3518 (3.1522)  weight_decay: 0.0500 (0.0500)  time: 0.5646  data: 0.0068  max mem: 31830
Epoch: [286]  [200/312]  eta: 0:01:03  lr: 0.000023  min_lr: 0.000023  loss: 3.3600 (3.1683)  weight_decay: 0.0500 (0.0500)  time: 0.5124  data: 0.0063  max mem: 31830
Epoch: [286]  [210/312]  eta: 0:00:58  lr: 0.000023  min_lr: 0.000023  loss: 3.3470 (3.1701)  weight_decay: 0.0500 (0.0500)  time: 0.5886  data: 0.0305  max mem: 31830
Epoch: [286]  [220/312]  eta: 0:00:52  lr: 0.000023  min_lr: 0.000023  loss: 3.2635 (3.1750)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0250  max mem: 31830
Epoch: [286]  [230/312]  eta: 0:00:46  lr: 0.000023  min_lr: 0.000023  loss: 3.3756 (3.1696)  weight_decay: 0.0500 (0.0500)  time: 0.5123  data: 0.0072  max mem: 31830
Epoch: [286]  [240/312]  eta: 0:00:41  lr: 0.000023  min_lr: 0.000023  loss: 3.3847 (3.1740)  weight_decay: 0.0500 (0.0500)  time: 0.5927  data: 0.0072  max mem: 31830
Epoch: [286]  [250/312]  eta: 0:00:35  lr: 0.000023  min_lr: 0.000023  loss: 3.4332 (3.1740)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0070  max mem: 31830
Epoch: [286]  [260/312]  eta: 0:00:29  lr: 0.000023  min_lr: 0.000023  loss: 3.2054 (3.1753)  weight_decay: 0.0500 (0.0500)  time: 0.4961  data: 0.0110  max mem: 31830
Epoch: [286]  [270/312]  eta: 0:00:23  lr: 0.000023  min_lr: 0.000023  loss: 3.0647 (3.1776)  weight_decay: 0.0500 (0.0500)  time: 0.5608  data: 0.0049  max mem: 31830
Epoch: [286]  [280/312]  eta: 0:00:18  lr: 0.000023  min_lr: 0.000023  loss: 3.3551 (3.1837)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0190  max mem: 31830
Epoch: [286]  [290/312]  eta: 0:00:12  lr: 0.000022  min_lr: 0.000022  loss: 3.3551 (3.1788)  weight_decay: 0.0500 (0.0500)  time: 0.5710  data: 0.0540  max mem: 31830
Epoch: [286]  [300/312]  eta: 0:00:06  lr: 0.000022  min_lr: 0.000022  loss: 2.9233 (3.1700)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0355  max mem: 31830
Epoch: [286]  [310/312]  eta: 0:00:01  lr: 0.000022  min_lr: 0.000022  loss: 3.1561 (3.1703)  weight_decay: 0.0500 (0.0500)  time: 0.3819  data: 0.0001  max mem: 31830
Epoch: [286]  [311/312]  eta: 0:00:00  lr: 0.000022  min_lr: 0.000022  loss: 3.1484 (3.1699)  weight_decay: 0.0500 (0.0500)  time: 0.3816  data: 0.0001  max mem: 31830
Epoch: [286] Total time: 0:02:53 (0.5572 s / it)
Averaged stats: lr: 0.000022  min_lr: 0.000022  loss: 3.1484 (3.1637)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8506 (0.8506)  acc1: 85.0260 (85.0260)  acc5: 97.5260 (97.5260)  time: 8.9221  data: 8.7547  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1376 (1.0626)  acc1: 79.4271 (78.3520)  acc5: 94.7917 (94.5440)  time: 1.1092  data: 0.9728  max mem: 31830
Test: Total time: 0:00:10 (1.1232 s / it)
* Acc@1 78.676 Acc@5 94.490 loss 1.059
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.68%
Epoch: [287]  [  0/312]  eta: 0:56:41  lr: 0.000022  min_lr: 0.000022  loss: 3.2280 (3.2280)  weight_decay: 0.0500 (0.0500)  time: 10.9011  data: 9.3025  max mem: 31830
Epoch: [287]  [ 10/312]  eta: 0:07:59  lr: 0.000022  min_lr: 0.000022  loss: 3.2721 (3.2706)  weight_decay: 0.0500 (0.0500)  time: 1.5865  data: 1.0578  max mem: 31830
Epoch: [287]  [ 20/312]  eta: 0:05:25  lr: 0.000022  min_lr: 0.000022  loss: 3.1942 (3.2087)  weight_decay: 0.0500 (0.0500)  time: 0.6239  data: 0.1800  max mem: 31830
Epoch: [287]  [ 30/312]  eta: 0:04:08  lr: 0.000022  min_lr: 0.000022  loss: 3.0661 (3.1744)  weight_decay: 0.0500 (0.0500)  time: 0.4937  data: 0.0638  max mem: 31830
Epoch: [287]  [ 40/312]  eta: 0:03:27  lr: 0.000022  min_lr: 0.000022  loss: 3.1884 (3.1795)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0010  max mem: 31830
Epoch: [287]  [ 50/312]  eta: 0:03:09  lr: 0.000022  min_lr: 0.000022  loss: 3.3815 (3.2380)  weight_decay: 0.0500 (0.0500)  time: 0.4747  data: 0.0069  max mem: 31830
Epoch: [287]  [ 60/312]  eta: 0:02:49  lr: 0.000022  min_lr: 0.000022  loss: 3.4029 (3.2403)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0204  max mem: 31830
Epoch: [287]  [ 70/312]  eta: 0:02:39  lr: 0.000022  min_lr: 0.000022  loss: 3.3808 (3.2564)  weight_decay: 0.0500 (0.0500)  time: 0.5025  data: 0.0592  max mem: 31830
Epoch: [287]  [ 80/312]  eta: 0:02:28  lr: 0.000021  min_lr: 0.000021  loss: 3.4220 (3.2682)  weight_decay: 0.0500 (0.0500)  time: 0.5499  data: 0.0456  max mem: 31830
Epoch: [287]  [ 90/312]  eta: 0:02:19  lr: 0.000021  min_lr: 0.000021  loss: 3.0741 (3.2141)  weight_decay: 0.0500 (0.0500)  time: 0.5106  data: 0.0590  max mem: 31830
Epoch: [287]  [100/312]  eta: 0:02:11  lr: 0.000021  min_lr: 0.000021  loss: 3.0741 (3.2223)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0985  max mem: 31830
Epoch: [287]  [110/312]  eta: 0:02:00  lr: 0.000021  min_lr: 0.000021  loss: 3.3848 (3.2382)  weight_decay: 0.0500 (0.0500)  time: 0.4654  data: 0.0412  max mem: 31830
Epoch: [287]  [120/312]  eta: 0:01:55  lr: 0.000021  min_lr: 0.000021  loss: 3.3881 (3.2375)  weight_decay: 0.0500 (0.0500)  time: 0.5170  data: 0.0659  max mem: 31830
Epoch: [287]  [130/312]  eta: 0:01:50  lr: 0.000021  min_lr: 0.000021  loss: 3.2007 (3.2315)  weight_decay: 0.0500 (0.0500)  time: 0.6422  data: 0.1094  max mem: 31830
Epoch: [287]  [140/312]  eta: 0:01:41  lr: 0.000021  min_lr: 0.000021  loss: 3.1925 (3.2218)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0449  max mem: 31830
Epoch: [287]  [150/312]  eta: 0:01:35  lr: 0.000021  min_lr: 0.000021  loss: 3.1251 (3.2038)  weight_decay: 0.0500 (0.0500)  time: 0.5003  data: 0.0809  max mem: 31830
Epoch: [287]  [160/312]  eta: 0:01:28  lr: 0.000021  min_lr: 0.000021  loss: 3.2295 (3.2077)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0810  max mem: 31830
Epoch: [287]  [170/312]  eta: 0:01:22  lr: 0.000020  min_lr: 0.000020  loss: 3.1316 (3.1865)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0928  max mem: 31830
Epoch: [287]  [180/312]  eta: 0:01:17  lr: 0.000020  min_lr: 0.000020  loss: 3.2384 (3.1923)  weight_decay: 0.0500 (0.0500)  time: 0.5865  data: 0.1081  max mem: 31830
Epoch: [287]  [190/312]  eta: 0:01:10  lr: 0.000020  min_lr: 0.000020  loss: 3.2896 (3.1700)  weight_decay: 0.0500 (0.0500)  time: 0.5561  data: 0.0765  max mem: 31830
Epoch: [287]  [200/312]  eta: 0:01:04  lr: 0.000020  min_lr: 0.000020  loss: 3.2537 (3.1755)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.1101  max mem: 31830
Epoch: [287]  [210/312]  eta: 0:00:58  lr: 0.000020  min_lr: 0.000020  loss: 3.3216 (3.1741)  weight_decay: 0.0500 (0.0500)  time: 0.5159  data: 0.0497  max mem: 31830
Epoch: [287]  [220/312]  eta: 0:00:52  lr: 0.000020  min_lr: 0.000020  loss: 3.4015 (3.1789)  weight_decay: 0.0500 (0.0500)  time: 0.5034  data: 0.0715  max mem: 31830
Epoch: [287]  [230/312]  eta: 0:00:47  lr: 0.000020  min_lr: 0.000020  loss: 3.4780 (3.1820)  weight_decay: 0.0500 (0.0500)  time: 0.5718  data: 0.1257  max mem: 31830
Epoch: [287]  [240/312]  eta: 0:00:40  lr: 0.000020  min_lr: 0.000020  loss: 3.4780 (3.1868)  weight_decay: 0.0500 (0.0500)  time: 0.5213  data: 0.0550  max mem: 31830
Epoch: [287]  [250/312]  eta: 0:00:35  lr: 0.000020  min_lr: 0.000020  loss: 3.4415 (3.1871)  weight_decay: 0.0500 (0.0500)  time: 0.5136  data: 0.0582  max mem: 31830
Epoch: [287]  [260/312]  eta: 0:00:29  lr: 0.000020  min_lr: 0.000020  loss: 3.4415 (3.1885)  weight_decay: 0.0500 (0.0500)  time: 0.5615  data: 0.0583  max mem: 31830
Epoch: [287]  [270/312]  eta: 0:00:23  lr: 0.000020  min_lr: 0.000020  loss: 3.4119 (3.1925)  weight_decay: 0.0500 (0.0500)  time: 0.5055  data: 0.0480  max mem: 31830
Epoch: [287]  [280/312]  eta: 0:00:18  lr: 0.000019  min_lr: 0.000019  loss: 3.2245 (3.1886)  weight_decay: 0.0500 (0.0500)  time: 0.5847  data: 0.1023  max mem: 31830
Epoch: [287]  [290/312]  eta: 0:00:12  lr: 0.000019  min_lr: 0.000019  loss: 3.2245 (3.1879)  weight_decay: 0.0500 (0.0500)  time: 0.5816  data: 0.0548  max mem: 31830
Epoch: [287]  [300/312]  eta: 0:00:06  lr: 0.000019  min_lr: 0.000019  loss: 3.3560 (3.1905)  weight_decay: 0.0500 (0.0500)  time: 0.4614  data: 0.0211  max mem: 31830
Epoch: [287]  [310/312]  eta: 0:00:01  lr: 0.000019  min_lr: 0.000019  loss: 3.1496 (3.1853)  weight_decay: 0.0500 (0.0500)  time: 0.4103  data: 0.0211  max mem: 31830
Epoch: [287]  [311/312]  eta: 0:00:00  lr: 0.000019  min_lr: 0.000019  loss: 3.1496 (3.1861)  weight_decay: 0.0500 (0.0500)  time: 0.4101  data: 0.0210  max mem: 31830
Epoch: [287] Total time: 0:02:54 (0.5594 s / it)
Averaged stats: lr: 0.000019  min_lr: 0.000019  loss: 3.1496 (3.1560)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8578 (0.8578)  acc1: 85.4167 (85.4167)  acc5: 97.2656 (97.2656)  time: 8.5694  data: 8.4023  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1523 (1.0754)  acc1: 79.0365 (78.4320)  acc5: 95.0521 (94.5440)  time: 1.0694  data: 0.9337  max mem: 31830
Test: Total time: 0:00:09 (1.0828 s / it)
* Acc@1 78.628 Acc@5 94.536 loss 1.072
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.68%
Epoch: [288]  [  0/312]  eta: 1:02:01  lr: 0.000019  min_lr: 0.000019  loss: 1.9642 (1.9642)  weight_decay: 0.0500 (0.0500)  time: 11.9277  data: 8.3397  max mem: 31830
Epoch: [288]  [ 10/312]  eta: 0:09:13  lr: 0.000019  min_lr: 0.000019  loss: 3.0530 (2.8850)  weight_decay: 0.0500 (0.0500)  time: 1.8326  data: 1.0282  max mem: 31830
Epoch: [288]  [ 20/312]  eta: 0:05:35  lr: 0.000019  min_lr: 0.000019  loss: 3.2408 (3.0378)  weight_decay: 0.0500 (0.0500)  time: 0.6097  data: 0.1488  max mem: 31830
Epoch: [288]  [ 30/312]  eta: 0:04:15  lr: 0.000019  min_lr: 0.000019  loss: 3.1537 (3.0223)  weight_decay: 0.0500 (0.0500)  time: 0.3981  data: 0.0008  max mem: 31830
Epoch: [288]  [ 40/312]  eta: 0:03:33  lr: 0.000019  min_lr: 0.000019  loss: 3.1307 (3.0893)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0011  max mem: 31830
Epoch: [288]  [ 50/312]  eta: 0:03:05  lr: 0.000019  min_lr: 0.000019  loss: 3.5068 (3.1181)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0017  max mem: 31830
Epoch: [288]  [ 60/312]  eta: 0:02:45  lr: 0.000019  min_lr: 0.000019  loss: 3.4309 (3.1400)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0017  max mem: 31830
Epoch: [288]  [ 70/312]  eta: 0:02:30  lr: 0.000018  min_lr: 0.000018  loss: 3.3158 (3.1334)  weight_decay: 0.0500 (0.0500)  time: 0.4002  data: 0.0010  max mem: 31830
Epoch: [288]  [ 80/312]  eta: 0:02:21  lr: 0.000018  min_lr: 0.000018  loss: 3.0763 (3.0997)  weight_decay: 0.0500 (0.0500)  time: 0.4725  data: 0.0067  max mem: 31830
Epoch: [288]  [ 90/312]  eta: 0:02:13  lr: 0.000018  min_lr: 0.000018  loss: 3.1826 (3.1231)  weight_decay: 0.0500 (0.0500)  time: 0.5346  data: 0.0257  max mem: 31830
Epoch: [288]  [100/312]  eta: 0:02:07  lr: 0.000018  min_lr: 0.000018  loss: 3.3278 (3.1220)  weight_decay: 0.0500 (0.0500)  time: 0.5537  data: 0.0466  max mem: 31830
Epoch: [288]  [110/312]  eta: 0:02:00  lr: 0.000018  min_lr: 0.000018  loss: 3.2911 (3.1420)  weight_decay: 0.0500 (0.0500)  time: 0.5737  data: 0.0535  max mem: 31830
Epoch: [288]  [120/312]  eta: 0:01:53  lr: 0.000018  min_lr: 0.000018  loss: 3.3993 (3.1643)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0572  max mem: 31830
Epoch: [288]  [130/312]  eta: 0:01:47  lr: 0.000018  min_lr: 0.000018  loss: 3.2263 (3.1415)  weight_decay: 0.0500 (0.0500)  time: 0.5445  data: 0.0456  max mem: 31830
Epoch: [288]  [140/312]  eta: 0:01:40  lr: 0.000018  min_lr: 0.000018  loss: 2.7933 (3.1335)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0454  max mem: 31830
Epoch: [288]  [150/312]  eta: 0:01:33  lr: 0.000018  min_lr: 0.000018  loss: 2.8588 (3.1284)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0653  max mem: 31830
Epoch: [288]  [160/312]  eta: 0:01:28  lr: 0.000018  min_lr: 0.000018  loss: 3.0388 (3.1104)  weight_decay: 0.0500 (0.0500)  time: 0.5618  data: 0.0672  max mem: 31830
Epoch: [288]  [170/312]  eta: 0:01:21  lr: 0.000017  min_lr: 0.000017  loss: 3.3207 (3.1148)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0590  max mem: 31830
Epoch: [288]  [180/312]  eta: 0:01:16  lr: 0.000017  min_lr: 0.000017  loss: 3.1665 (3.1034)  weight_decay: 0.0500 (0.0500)  time: 0.5621  data: 0.0553  max mem: 31830
Epoch: [288]  [190/312]  eta: 0:01:10  lr: 0.000017  min_lr: 0.000017  loss: 3.1665 (3.1075)  weight_decay: 0.0500 (0.0500)  time: 0.5603  data: 0.0292  max mem: 31830
Epoch: [288]  [200/312]  eta: 0:01:03  lr: 0.000017  min_lr: 0.000017  loss: 3.3718 (3.1035)  weight_decay: 0.0500 (0.0500)  time: 0.5045  data: 0.0061  max mem: 31830
Epoch: [288]  [210/312]  eta: 0:00:58  lr: 0.000017  min_lr: 0.000017  loss: 3.2712 (3.1059)  weight_decay: 0.0500 (0.0500)  time: 0.5392  data: 0.0062  max mem: 31830
Epoch: [288]  [220/312]  eta: 0:00:52  lr: 0.000017  min_lr: 0.000017  loss: 3.2404 (3.1061)  weight_decay: 0.0500 (0.0500)  time: 0.5687  data: 0.0142  max mem: 31830
Epoch: [288]  [230/312]  eta: 0:00:46  lr: 0.000017  min_lr: 0.000017  loss: 3.2404 (3.1118)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.0200  max mem: 31830
Epoch: [288]  [240/312]  eta: 0:00:41  lr: 0.000017  min_lr: 0.000017  loss: 3.2741 (3.1054)  weight_decay: 0.0500 (0.0500)  time: 0.5839  data: 0.0069  max mem: 31830
Epoch: [288]  [250/312]  eta: 0:00:35  lr: 0.000017  min_lr: 0.000017  loss: 3.3747 (3.1186)  weight_decay: 0.0500 (0.0500)  time: 0.5395  data: 0.0015  max mem: 31830
Epoch: [288]  [260/312]  eta: 0:00:29  lr: 0.000017  min_lr: 0.000017  loss: 3.3290 (3.1228)  weight_decay: 0.0500 (0.0500)  time: 0.5548  data: 0.0076  max mem: 31830
Epoch: [288]  [270/312]  eta: 0:00:23  lr: 0.000017  min_lr: 0.000017  loss: 3.1882 (3.1236)  weight_decay: 0.0500 (0.0500)  time: 0.6228  data: 0.0071  max mem: 31830
Epoch: [288]  [280/312]  eta: 0:00:18  lr: 0.000016  min_lr: 0.000016  loss: 3.2881 (3.1294)  weight_decay: 0.0500 (0.0500)  time: 0.4904  data: 0.0032  max mem: 31830
Epoch: [288]  [290/312]  eta: 0:00:12  lr: 0.000016  min_lr: 0.000016  loss: 3.1986 (3.1227)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0029  max mem: 31830
Epoch: [288]  [300/312]  eta: 0:00:06  lr: 0.000016  min_lr: 0.000016  loss: 3.1305 (3.1169)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0046  max mem: 31830
Epoch: [288]  [310/312]  eta: 0:00:01  lr: 0.000016  min_lr: 0.000016  loss: 3.0083 (3.1094)  weight_decay: 0.0500 (0.0500)  time: 0.4046  data: 0.0045  max mem: 31830
Epoch: [288]  [311/312]  eta: 0:00:00  lr: 0.000016  min_lr: 0.000016  loss: 3.0055 (3.1091)  weight_decay: 0.0500 (0.0500)  time: 0.4008  data: 0.0001  max mem: 31830
Epoch: [288] Total time: 0:02:54 (0.5592 s / it)
Averaged stats: lr: 0.000016  min_lr: 0.000016  loss: 3.0055 (3.1668)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8040 (0.8040)  acc1: 85.2865 (85.2865)  acc5: 97.1354 (97.1354)  time: 8.2921  data: 8.1338  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.0897 (1.0163)  acc1: 79.6875 (78.6400)  acc5: 94.7917 (94.4480)  time: 1.0443  data: 0.9038  max mem: 31830
Test: Total time: 0:00:09 (1.0553 s / it)
* Acc@1 78.632 Acc@5 94.482 loss 1.014
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.68%
Epoch: [289]  [  0/312]  eta: 1:04:19  lr: 0.000016  min_lr: 0.000016  loss: 3.5259 (3.5259)  weight_decay: 0.0500 (0.0500)  time: 12.3717  data: 11.6315  max mem: 31830
Epoch: [289]  [ 10/312]  eta: 0:08:29  lr: 0.000016  min_lr: 0.000016  loss: 3.4183 (3.3092)  weight_decay: 0.0500 (0.0500)  time: 1.6857  data: 1.0582  max mem: 31830
Epoch: [289]  [ 20/312]  eta: 0:05:28  lr: 0.000016  min_lr: 0.000016  loss: 3.3349 (3.2431)  weight_decay: 0.0500 (0.0500)  time: 0.5622  data: 0.0531  max mem: 31830
Epoch: [289]  [ 30/312]  eta: 0:04:11  lr: 0.000016  min_lr: 0.000016  loss: 3.3764 (3.2453)  weight_decay: 0.0500 (0.0500)  time: 0.4539  data: 0.0535  max mem: 31830
Epoch: [289]  [ 40/312]  eta: 0:03:29  lr: 0.000016  min_lr: 0.000016  loss: 3.3084 (3.2117)  weight_decay: 0.0500 (0.0500)  time: 0.3995  data: 0.0013  max mem: 31830
Epoch: [289]  [ 50/312]  eta: 0:03:04  lr: 0.000016  min_lr: 0.000016  loss: 3.1157 (3.1669)  weight_decay: 0.0500 (0.0500)  time: 0.4111  data: 0.0009  max mem: 31830
Epoch: [289]  [ 60/312]  eta: 0:02:44  lr: 0.000016  min_lr: 0.000016  loss: 2.9248 (3.1501)  weight_decay: 0.0500 (0.0500)  time: 0.4099  data: 0.0009  max mem: 31830
Epoch: [289]  [ 70/312]  eta: 0:02:34  lr: 0.000016  min_lr: 0.000016  loss: 3.3401 (3.1619)  weight_decay: 0.0500 (0.0500)  time: 0.4808  data: 0.0707  max mem: 31830
Epoch: [289]  [ 80/312]  eta: 0:02:27  lr: 0.000016  min_lr: 0.000016  loss: 3.3575 (3.1729)  weight_decay: 0.0500 (0.0500)  time: 0.5934  data: 0.1668  max mem: 31830
Epoch: [289]  [ 90/312]  eta: 0:02:15  lr: 0.000015  min_lr: 0.000015  loss: 3.3575 (3.1706)  weight_decay: 0.0500 (0.0500)  time: 0.5087  data: 0.0969  max mem: 31830
Epoch: [289]  [100/312]  eta: 0:02:09  lr: 0.000015  min_lr: 0.000015  loss: 3.2727 (3.1600)  weight_decay: 0.0500 (0.0500)  time: 0.5054  data: 0.0953  max mem: 31830
Epoch: [289]  [110/312]  eta: 0:01:59  lr: 0.000015  min_lr: 0.000015  loss: 3.2757 (3.1759)  weight_decay: 0.0500 (0.0500)  time: 0.5049  data: 0.0952  max mem: 31830
Epoch: [289]  [120/312]  eta: 0:01:54  lr: 0.000015  min_lr: 0.000015  loss: 3.3495 (3.1842)  weight_decay: 0.0500 (0.0500)  time: 0.5147  data: 0.1058  max mem: 31830
Epoch: [289]  [130/312]  eta: 0:01:48  lr: 0.000015  min_lr: 0.000015  loss: 3.0150 (3.1640)  weight_decay: 0.0500 (0.0500)  time: 0.6200  data: 0.2070  max mem: 31830
Epoch: [289]  [140/312]  eta: 0:01:40  lr: 0.000015  min_lr: 0.000015  loss: 2.9727 (3.1451)  weight_decay: 0.0500 (0.0500)  time: 0.5003  data: 0.1026  max mem: 31830
Epoch: [289]  [150/312]  eta: 0:01:34  lr: 0.000015  min_lr: 0.000015  loss: 3.3949 (3.1602)  weight_decay: 0.0500 (0.0500)  time: 0.5203  data: 0.1131  max mem: 31830
Epoch: [289]  [160/312]  eta: 0:01:29  lr: 0.000015  min_lr: 0.000015  loss: 3.3193 (3.1437)  weight_decay: 0.0500 (0.0500)  time: 0.6294  data: 0.1909  max mem: 31830
Epoch: [289]  [170/312]  eta: 0:01:21  lr: 0.000015  min_lr: 0.000015  loss: 2.9311 (3.1344)  weight_decay: 0.0500 (0.0500)  time: 0.5062  data: 0.0796  max mem: 31830
Epoch: [289]  [180/312]  eta: 0:01:16  lr: 0.000015  min_lr: 0.000015  loss: 3.4517 (3.1483)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.1063  max mem: 31830
Epoch: [289]  [190/312]  eta: 0:01:09  lr: 0.000015  min_lr: 0.000015  loss: 3.4343 (3.1392)  weight_decay: 0.0500 (0.0500)  time: 0.5014  data: 0.1060  max mem: 31830
Epoch: [289]  [200/312]  eta: 0:01:04  lr: 0.000014  min_lr: 0.000014  loss: 3.0013 (3.1377)  weight_decay: 0.0500 (0.0500)  time: 0.5191  data: 0.1250  max mem: 31830
Epoch: [289]  [210/312]  eta: 0:00:58  lr: 0.000014  min_lr: 0.000014  loss: 3.3638 (3.1431)  weight_decay: 0.0500 (0.0500)  time: 0.6352  data: 0.2398  max mem: 31830
Epoch: [289]  [220/312]  eta: 0:00:52  lr: 0.000014  min_lr: 0.000014  loss: 3.3638 (3.1420)  weight_decay: 0.0500 (0.0500)  time: 0.5082  data: 0.1155  max mem: 31830
Epoch: [289]  [230/312]  eta: 0:00:46  lr: 0.000014  min_lr: 0.000014  loss: 3.1131 (3.1340)  weight_decay: 0.0500 (0.0500)  time: 0.5048  data: 0.1112  max mem: 31830
Epoch: [289]  [240/312]  eta: 0:00:40  lr: 0.000014  min_lr: 0.000014  loss: 3.3191 (3.1480)  weight_decay: 0.0500 (0.0500)  time: 0.5956  data: 0.2009  max mem: 31830
Epoch: [289]  [250/312]  eta: 0:00:34  lr: 0.000014  min_lr: 0.000014  loss: 3.3729 (3.1546)  weight_decay: 0.0500 (0.0500)  time: 0.4965  data: 0.0904  max mem: 31830
Epoch: [289]  [260/312]  eta: 0:00:29  lr: 0.000014  min_lr: 0.000014  loss: 3.3729 (3.1594)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.1051  max mem: 31830
Epoch: [289]  [270/312]  eta: 0:00:23  lr: 0.000014  min_lr: 0.000014  loss: 3.4228 (3.1599)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.1051  max mem: 31830
Epoch: [289]  [280/312]  eta: 0:00:17  lr: 0.000014  min_lr: 0.000014  loss: 3.4571 (3.1657)  weight_decay: 0.0500 (0.0500)  time: 0.5093  data: 0.0991  max mem: 31830
Epoch: [289]  [290/312]  eta: 0:00:12  lr: 0.000014  min_lr: 0.000014  loss: 2.9886 (3.1555)  weight_decay: 0.0500 (0.0500)  time: 0.6052  data: 0.1813  max mem: 31830
Epoch: [289]  [300/312]  eta: 0:00:06  lr: 0.000014  min_lr: 0.000014  loss: 2.9886 (3.1571)  weight_decay: 0.0500 (0.0500)  time: 0.4855  data: 0.0826  max mem: 31830
Epoch: [289]  [310/312]  eta: 0:00:01  lr: 0.000014  min_lr: 0.000014  loss: 3.3311 (3.1603)  weight_decay: 0.0500 (0.0500)  time: 0.3811  data: 0.0001  max mem: 31830
Epoch: [289]  [311/312]  eta: 0:00:00  lr: 0.000014  min_lr: 0.000014  loss: 3.3558 (3.1614)  weight_decay: 0.0500 (0.0500)  time: 0.3809  data: 0.0001  max mem: 31830
Epoch: [289] Total time: 0:02:53 (0.5549 s / it)
Averaged stats: lr: 0.000014  min_lr: 0.000014  loss: 3.3558 (3.1668)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.9062 (0.9062)  acc1: 85.2865 (85.2865)  acc5: 97.2656 (97.2656)  time: 8.6367  data: 8.4692  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2001 (1.1263)  acc1: 79.1667 (78.3680)  acc5: 94.7917 (94.4960)  time: 1.0773  data: 0.9411  max mem: 31830
Test: Total time: 0:00:09 (1.0928 s / it)
* Acc@1 78.574 Acc@5 94.464 loss 1.124
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.68%
Epoch: [290]  [  0/312]  eta: 1:06:37  lr: 0.000014  min_lr: 0.000014  loss: 3.5000 (3.5000)  weight_decay: 0.0500 (0.0500)  time: 12.8134  data: 12.4123  max mem: 31830
Epoch: [290]  [ 10/312]  eta: 0:08:37  lr: 0.000013  min_lr: 0.000013  loss: 3.3724 (3.1301)  weight_decay: 0.0500 (0.0500)  time: 1.7133  data: 1.1288  max mem: 31830
Epoch: [290]  [ 20/312]  eta: 0:05:38  lr: 0.000013  min_lr: 0.000013  loss: 3.2464 (3.1648)  weight_decay: 0.0500 (0.0500)  time: 0.5768  data: 0.0155  max mem: 31830
Epoch: [290]  [ 30/312]  eta: 0:04:17  lr: 0.000013  min_lr: 0.000013  loss: 3.2877 (3.1293)  weight_decay: 0.0500 (0.0500)  time: 0.4744  data: 0.0158  max mem: 31830
Epoch: [290]  [ 40/312]  eta: 0:03:34  lr: 0.000013  min_lr: 0.000013  loss: 3.1292 (3.0856)  weight_decay: 0.0500 (0.0500)  time: 0.3976  data: 0.0010  max mem: 31830
Epoch: [290]  [ 50/312]  eta: 0:03:06  lr: 0.000013  min_lr: 0.000013  loss: 3.3527 (3.1302)  weight_decay: 0.0500 (0.0500)  time: 0.3960  data: 0.0009  max mem: 31830
Epoch: [290]  [ 60/312]  eta: 0:02:46  lr: 0.000013  min_lr: 0.000013  loss: 3.3527 (3.1443)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0019  max mem: 31830
Epoch: [290]  [ 70/312]  eta: 0:02:32  lr: 0.000013  min_lr: 0.000013  loss: 3.3121 (3.1687)  weight_decay: 0.0500 (0.0500)  time: 0.4274  data: 0.0169  max mem: 31830
Epoch: [290]  [ 80/312]  eta: 0:02:23  lr: 0.000013  min_lr: 0.000013  loss: 3.3840 (3.1755)  weight_decay: 0.0500 (0.0500)  time: 0.5030  data: 0.0717  max mem: 31830
Epoch: [290]  [ 90/312]  eta: 0:02:13  lr: 0.000013  min_lr: 0.000013  loss: 3.1152 (3.1503)  weight_decay: 0.0500 (0.0500)  time: 0.4909  data: 0.0567  max mem: 31830
Epoch: [290]  [100/312]  eta: 0:02:07  lr: 0.000013  min_lr: 0.000013  loss: 2.8344 (3.1202)  weight_decay: 0.0500 (0.0500)  time: 0.5193  data: 0.0725  max mem: 31830
Epoch: [290]  [110/312]  eta: 0:01:57  lr: 0.000013  min_lr: 0.000013  loss: 3.0052 (3.1196)  weight_decay: 0.0500 (0.0500)  time: 0.4985  data: 0.0725  max mem: 31830
Epoch: [290]  [120/312]  eta: 0:01:52  lr: 0.000013  min_lr: 0.000013  loss: 3.2332 (3.1198)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.1104  max mem: 31830
Epoch: [290]  [130/312]  eta: 0:01:46  lr: 0.000013  min_lr: 0.000013  loss: 3.2332 (3.1209)  weight_decay: 0.0500 (0.0500)  time: 0.6098  data: 0.2056  max mem: 31830
Epoch: [290]  [140/312]  eta: 0:01:38  lr: 0.000012  min_lr: 0.000012  loss: 3.1421 (3.1110)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0962  max mem: 31830
Epoch: [290]  [150/312]  eta: 0:01:33  lr: 0.000012  min_lr: 0.000012  loss: 3.2075 (3.1199)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.1091  max mem: 31830
Epoch: [290]  [160/312]  eta: 0:01:27  lr: 0.000012  min_lr: 0.000012  loss: 3.2832 (3.1115)  weight_decay: 0.0500 (0.0500)  time: 0.5987  data: 0.1762  max mem: 31830
Epoch: [290]  [170/312]  eta: 0:01:21  lr: 0.000012  min_lr: 0.000012  loss: 3.1395 (3.1151)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0688  max mem: 31830
Epoch: [290]  [180/312]  eta: 0:01:15  lr: 0.000012  min_lr: 0.000012  loss: 3.3078 (3.1094)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.0866  max mem: 31830
Epoch: [290]  [190/312]  eta: 0:01:09  lr: 0.000012  min_lr: 0.000012  loss: 2.9824 (3.0922)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0859  max mem: 31830
Epoch: [290]  [200/312]  eta: 0:01:03  lr: 0.000012  min_lr: 0.000012  loss: 3.0713 (3.0951)  weight_decay: 0.0500 (0.0500)  time: 0.5096  data: 0.0743  max mem: 31830
Epoch: [290]  [210/312]  eta: 0:00:57  lr: 0.000012  min_lr: 0.000012  loss: 3.0903 (3.0950)  weight_decay: 0.0500 (0.0500)  time: 0.5824  data: 0.1283  max mem: 31830
Epoch: [290]  [220/312]  eta: 0:00:52  lr: 0.000012  min_lr: 0.000012  loss: 3.3688 (3.1142)  weight_decay: 0.0500 (0.0500)  time: 0.5672  data: 0.0608  max mem: 31830
Epoch: [290]  [230/312]  eta: 0:00:46  lr: 0.000012  min_lr: 0.000012  loss: 3.4601 (3.1242)  weight_decay: 0.0500 (0.0500)  time: 0.5079  data: 0.0502  max mem: 31830
Epoch: [290]  [240/312]  eta: 0:00:40  lr: 0.000012  min_lr: 0.000012  loss: 3.4601 (3.1344)  weight_decay: 0.0500 (0.0500)  time: 0.5324  data: 0.0958  max mem: 31830
Epoch: [290]  [250/312]  eta: 0:00:34  lr: 0.000012  min_lr: 0.000012  loss: 3.4054 (3.1392)  weight_decay: 0.0500 (0.0500)  time: 0.5536  data: 0.0839  max mem: 31830
Epoch: [290]  [260/312]  eta: 0:00:29  lr: 0.000012  min_lr: 0.000012  loss: 3.1805 (3.1296)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0980  max mem: 31830
Epoch: [290]  [270/312]  eta: 0:00:23  lr: 0.000011  min_lr: 0.000011  loss: 3.0261 (3.1291)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.0665  max mem: 31830
Epoch: [290]  [280/312]  eta: 0:00:18  lr: 0.000011  min_lr: 0.000011  loss: 3.2653 (3.1288)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.0785  max mem: 31830
Epoch: [290]  [290/312]  eta: 0:00:12  lr: 0.000011  min_lr: 0.000011  loss: 3.1996 (3.1284)  weight_decay: 0.0500 (0.0500)  time: 0.6725  data: 0.1320  max mem: 31830
Epoch: [290]  [300/312]  eta: 0:00:06  lr: 0.000011  min_lr: 0.000011  loss: 3.3194 (3.1329)  weight_decay: 0.0500 (0.0500)  time: 0.5204  data: 0.0540  max mem: 31830
Epoch: [290]  [310/312]  eta: 0:00:01  lr: 0.000011  min_lr: 0.000011  loss: 3.4326 (3.1402)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [290]  [311/312]  eta: 0:00:00  lr: 0.000011  min_lr: 0.000011  loss: 3.4326 (3.1421)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [290] Total time: 0:02:53 (0.5577 s / it)
Averaged stats: lr: 0.000011  min_lr: 0.000011  loss: 3.4326 (3.1573)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.9172 (0.9172)  acc1: 84.5052 (84.5052)  acc5: 97.0052 (97.0052)  time: 7.7576  data: 7.5931  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.2046 (1.1304)  acc1: 79.2969 (78.2880)  acc5: 94.9219 (94.5280)  time: 1.0223  data: 0.8878  max mem: 31830
Test: Total time: 0:00:09 (1.0312 s / it)
* Acc@1 78.406 Acc@5 94.384 loss 1.130
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.68%
Epoch: [291]  [  0/312]  eta: 1:03:54  lr: 0.000011  min_lr: 0.000011  loss: 3.1547 (3.1547)  weight_decay: 0.0500 (0.0500)  time: 12.2896  data: 9.7798  max mem: 31830
Epoch: [291]  [ 10/312]  eta: 0:08:30  lr: 0.000011  min_lr: 0.000011  loss: 3.0560 (2.9866)  weight_decay: 0.0500 (0.0500)  time: 1.6904  data: 0.9887  max mem: 31830
Epoch: [291]  [ 20/312]  eta: 0:05:35  lr: 0.000011  min_lr: 0.000011  loss: 3.2023 (3.0401)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0558  max mem: 31830
Epoch: [291]  [ 30/312]  eta: 0:04:15  lr: 0.000011  min_lr: 0.000011  loss: 3.2982 (3.0699)  weight_decay: 0.0500 (0.0500)  time: 0.4726  data: 0.0014  max mem: 31830
Epoch: [291]  [ 40/312]  eta: 0:03:32  lr: 0.000011  min_lr: 0.000011  loss: 3.3254 (3.1176)  weight_decay: 0.0500 (0.0500)  time: 0.3912  data: 0.0008  max mem: 31830
Epoch: [291]  [ 50/312]  eta: 0:03:06  lr: 0.000011  min_lr: 0.000011  loss: 3.3590 (3.0953)  weight_decay: 0.0500 (0.0500)  time: 0.4156  data: 0.0016  max mem: 31830
Epoch: [291]  [ 60/312]  eta: 0:02:46  lr: 0.000011  min_lr: 0.000011  loss: 3.3590 (3.1067)  weight_decay: 0.0500 (0.0500)  time: 0.4167  data: 0.0019  max mem: 31830
Epoch: [291]  [ 70/312]  eta: 0:02:41  lr: 0.000011  min_lr: 0.000011  loss: 3.4797 (3.1604)  weight_decay: 0.0500 (0.0500)  time: 0.5490  data: 0.0014  max mem: 31830
Epoch: [291]  [ 80/312]  eta: 0:02:32  lr: 0.000011  min_lr: 0.000011  loss: 3.4933 (3.1784)  weight_decay: 0.0500 (0.0500)  time: 0.6548  data: 0.0012  max mem: 31830
Epoch: [291]  [ 90/312]  eta: 0:02:20  lr: 0.000011  min_lr: 0.000011  loss: 3.3786 (3.1999)  weight_decay: 0.0500 (0.0500)  time: 0.5027  data: 0.0009  max mem: 31830
Epoch: [291]  [100/312]  eta: 0:02:13  lr: 0.000010  min_lr: 0.000010  loss: 3.3957 (3.1995)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0009  max mem: 31830
Epoch: [291]  [110/312]  eta: 0:02:03  lr: 0.000010  min_lr: 0.000010  loss: 3.3957 (3.2022)  weight_decay: 0.0500 (0.0500)  time: 0.5188  data: 0.0059  max mem: 31830
Epoch: [291]  [120/312]  eta: 0:01:58  lr: 0.000010  min_lr: 0.000010  loss: 3.1882 (3.1780)  weight_decay: 0.0500 (0.0500)  time: 0.5352  data: 0.0062  max mem: 31830
Epoch: [291]  [130/312]  eta: 0:01:52  lr: 0.000010  min_lr: 0.000010  loss: 3.3579 (3.1870)  weight_decay: 0.0500 (0.0500)  time: 0.6559  data: 0.0121  max mem: 31830
Epoch: [291]  [140/312]  eta: 0:01:44  lr: 0.000010  min_lr: 0.000010  loss: 3.3843 (3.1942)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.0473  max mem: 31830
Epoch: [291]  [150/312]  eta: 0:01:37  lr: 0.000010  min_lr: 0.000010  loss: 3.1547 (3.1907)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0367  max mem: 31830
Epoch: [291]  [160/312]  eta: 0:01:31  lr: 0.000010  min_lr: 0.000010  loss: 3.3212 (3.1876)  weight_decay: 0.0500 (0.0500)  time: 0.5916  data: 0.0112  max mem: 31830
Epoch: [291]  [170/312]  eta: 0:01:24  lr: 0.000010  min_lr: 0.000010  loss: 3.2096 (3.1875)  weight_decay: 0.0500 (0.0500)  time: 0.5233  data: 0.0215  max mem: 31830
Epoch: [291]  [180/312]  eta: 0:01:18  lr: 0.000010  min_lr: 0.000010  loss: 3.2096 (3.1841)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0215  max mem: 31830
Epoch: [291]  [190/312]  eta: 0:01:11  lr: 0.000010  min_lr: 0.000010  loss: 3.2310 (3.1803)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.0437  max mem: 31830
Epoch: [291]  [200/312]  eta: 0:01:05  lr: 0.000010  min_lr: 0.000010  loss: 3.2310 (3.1809)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0580  max mem: 31830
Epoch: [291]  [210/312]  eta: 0:00:59  lr: 0.000010  min_lr: 0.000010  loss: 3.1892 (3.1713)  weight_decay: 0.0500 (0.0500)  time: 0.5844  data: 0.0251  max mem: 31830
Epoch: [291]  [220/312]  eta: 0:00:53  lr: 0.000010  min_lr: 0.000010  loss: 2.9685 (3.1611)  weight_decay: 0.0500 (0.0500)  time: 0.4881  data: 0.0008  max mem: 31830
Epoch: [291]  [230/312]  eta: 0:00:47  lr: 0.000010  min_lr: 0.000010  loss: 2.8716 (3.1497)  weight_decay: 0.0500 (0.0500)  time: 0.5024  data: 0.0010  max mem: 31830
Epoch: [291]  [240/312]  eta: 0:00:41  lr: 0.000010  min_lr: 0.000010  loss: 3.0172 (3.1505)  weight_decay: 0.0500 (0.0500)  time: 0.6089  data: 0.0242  max mem: 31830
Epoch: [291]  [250/312]  eta: 0:00:35  lr: 0.000009  min_lr: 0.000009  loss: 3.3140 (3.1520)  weight_decay: 0.0500 (0.0500)  time: 0.5427  data: 0.0604  max mem: 31830
Epoch: [291]  [260/312]  eta: 0:00:29  lr: 0.000009  min_lr: 0.000009  loss: 3.3140 (3.1569)  weight_decay: 0.0500 (0.0500)  time: 0.5097  data: 0.0376  max mem: 31830
Epoch: [291]  [270/312]  eta: 0:00:23  lr: 0.000009  min_lr: 0.000009  loss: 3.3059 (3.1556)  weight_decay: 0.0500 (0.0500)  time: 0.4742  data: 0.0013  max mem: 31830
Epoch: [291]  [280/312]  eta: 0:00:18  lr: 0.000009  min_lr: 0.000009  loss: 3.3059 (3.1563)  weight_decay: 0.0500 (0.0500)  time: 0.5604  data: 0.0369  max mem: 31830
Epoch: [291]  [290/312]  eta: 0:00:12  lr: 0.000009  min_lr: 0.000009  loss: 3.3884 (3.1607)  weight_decay: 0.0500 (0.0500)  time: 0.6045  data: 0.0370  max mem: 31830
Epoch: [291]  [300/312]  eta: 0:00:06  lr: 0.000009  min_lr: 0.000009  loss: 3.4013 (3.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0008  max mem: 31830
Epoch: [291]  [310/312]  eta: 0:00:01  lr: 0.000009  min_lr: 0.000009  loss: 3.2326 (3.1561)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [291]  [311/312]  eta: 0:00:00  lr: 0.000009  min_lr: 0.000009  loss: 3.2326 (3.1580)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [291] Total time: 0:02:55 (0.5623 s / it)
Averaged stats: lr: 0.000009  min_lr: 0.000009  loss: 3.2326 (3.1542)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8614 (0.8614)  acc1: 85.6771 (85.6771)  acc5: 97.2656 (97.2656)  time: 8.4350  data: 8.2763  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1448 (1.0719)  acc1: 79.8177 (78.4800)  acc5: 94.7917 (94.5440)  time: 1.0551  data: 0.9197  max mem: 31830
Test: Total time: 0:00:09 (1.0649 s / it)
* Acc@1 78.652 Acc@5 94.490 loss 1.070
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.68%
Epoch: [292]  [  0/312]  eta: 1:05:43  lr: 0.000009  min_lr: 0.000009  loss: 3.8237 (3.8237)  weight_decay: 0.0500 (0.0500)  time: 12.6398  data: 8.4098  max mem: 31830
Epoch: [292]  [ 10/312]  eta: 0:09:20  lr: 0.000009  min_lr: 0.000009  loss: 3.1457 (3.0888)  weight_decay: 0.0500 (0.0500)  time: 1.8558  data: 0.9304  max mem: 31830
Epoch: [292]  [ 20/312]  eta: 0:05:37  lr: 0.000009  min_lr: 0.000009  loss: 3.0340 (3.0424)  weight_decay: 0.0500 (0.0500)  time: 0.5830  data: 0.0915  max mem: 31830
Epoch: [292]  [ 30/312]  eta: 0:04:17  lr: 0.000009  min_lr: 0.000009  loss: 3.2700 (3.1224)  weight_decay: 0.0500 (0.0500)  time: 0.3930  data: 0.0012  max mem: 31830
Epoch: [292]  [ 40/312]  eta: 0:03:33  lr: 0.000009  min_lr: 0.000009  loss: 3.3841 (3.2082)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0012  max mem: 31830
Epoch: [292]  [ 50/312]  eta: 0:03:05  lr: 0.000009  min_lr: 0.000009  loss: 3.3841 (3.2363)  weight_decay: 0.0500 (0.0500)  time: 0.3953  data: 0.0008  max mem: 31830
Epoch: [292]  [ 60/312]  eta: 0:02:45  lr: 0.000009  min_lr: 0.000009  loss: 3.3859 (3.2378)  weight_decay: 0.0500 (0.0500)  time: 0.3973  data: 0.0014  max mem: 31830
Epoch: [292]  [ 70/312]  eta: 0:02:31  lr: 0.000009  min_lr: 0.000009  loss: 3.3966 (3.2524)  weight_decay: 0.0500 (0.0500)  time: 0.4068  data: 0.0014  max mem: 31830
Epoch: [292]  [ 80/312]  eta: 0:02:22  lr: 0.000009  min_lr: 0.000009  loss: 3.3108 (3.2091)  weight_decay: 0.0500 (0.0500)  time: 0.4798  data: 0.0159  max mem: 31830
Epoch: [292]  [ 90/312]  eta: 0:02:16  lr: 0.000008  min_lr: 0.000008  loss: 3.0359 (3.1802)  weight_decay: 0.0500 (0.0500)  time: 0.5897  data: 0.0446  max mem: 31830
Epoch: [292]  [100/312]  eta: 0:02:07  lr: 0.000008  min_lr: 0.000008  loss: 3.0706 (3.1901)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0296  max mem: 31830
Epoch: [292]  [110/312]  eta: 0:02:02  lr: 0.000008  min_lr: 0.000008  loss: 3.2889 (3.1767)  weight_decay: 0.0500 (0.0500)  time: 0.5601  data: 0.0273  max mem: 31830
Epoch: [292]  [120/312]  eta: 0:01:53  lr: 0.000008  min_lr: 0.000008  loss: 3.0934 (3.1548)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0413  max mem: 31830
Epoch: [292]  [130/312]  eta: 0:01:49  lr: 0.000008  min_lr: 0.000008  loss: 3.2178 (3.1549)  weight_decay: 0.0500 (0.0500)  time: 0.5644  data: 0.0436  max mem: 31830
Epoch: [292]  [140/312]  eta: 0:01:43  lr: 0.000008  min_lr: 0.000008  loss: 3.3631 (3.1502)  weight_decay: 0.0500 (0.0500)  time: 0.6697  data: 0.0345  max mem: 31830
Epoch: [292]  [150/312]  eta: 0:01:36  lr: 0.000008  min_lr: 0.000008  loss: 3.3631 (3.1481)  weight_decay: 0.0500 (0.0500)  time: 0.5625  data: 0.0059  max mem: 31830
Epoch: [292]  [160/312]  eta: 0:01:30  lr: 0.000008  min_lr: 0.000008  loss: 3.2768 (3.1568)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0158  max mem: 31830
Epoch: [292]  [170/312]  eta: 0:01:24  lr: 0.000008  min_lr: 0.000008  loss: 3.2768 (3.1633)  weight_decay: 0.0500 (0.0500)  time: 0.6051  data: 0.0158  max mem: 31830
Epoch: [292]  [180/312]  eta: 0:01:17  lr: 0.000008  min_lr: 0.000008  loss: 3.2545 (3.1551)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0068  max mem: 31830
Epoch: [292]  [190/312]  eta: 0:01:12  lr: 0.000008  min_lr: 0.000008  loss: 3.1800 (3.1516)  weight_decay: 0.0500 (0.0500)  time: 0.5763  data: 0.0076  max mem: 31830
Epoch: [292]  [200/312]  eta: 0:01:05  lr: 0.000008  min_lr: 0.000008  loss: 3.3375 (3.1678)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.0017  max mem: 31830
Epoch: [292]  [210/312]  eta: 0:00:59  lr: 0.000008  min_lr: 0.000008  loss: 3.3557 (3.1657)  weight_decay: 0.0500 (0.0500)  time: 0.5077  data: 0.0050  max mem: 31830
Epoch: [292]  [220/312]  eta: 0:00:54  lr: 0.000008  min_lr: 0.000008  loss: 3.3557 (3.1703)  weight_decay: 0.0500 (0.0500)  time: 0.6201  data: 0.0111  max mem: 31830
Epoch: [292]  [230/312]  eta: 0:00:47  lr: 0.000008  min_lr: 0.000008  loss: 3.0760 (3.1520)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0070  max mem: 31830
Epoch: [292]  [240/312]  eta: 0:00:42  lr: 0.000008  min_lr: 0.000008  loss: 3.0760 (3.1561)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0083  max mem: 31830
Epoch: [292]  [250/312]  eta: 0:00:36  lr: 0.000008  min_lr: 0.000008  loss: 2.9289 (3.1392)  weight_decay: 0.0500 (0.0500)  time: 0.6217  data: 0.0082  max mem: 31830
Epoch: [292]  [260/312]  eta: 0:00:30  lr: 0.000007  min_lr: 0.000007  loss: 2.7575 (3.1292)  weight_decay: 0.0500 (0.0500)  time: 0.5420  data: 0.0114  max mem: 31830
Epoch: [292]  [270/312]  eta: 0:00:24  lr: 0.000007  min_lr: 0.000007  loss: 3.1972 (3.1362)  weight_decay: 0.0500 (0.0500)  time: 0.5731  data: 0.0350  max mem: 31830
Epoch: [292]  [280/312]  eta: 0:00:18  lr: 0.000007  min_lr: 0.000007  loss: 3.3772 (3.1351)  weight_decay: 0.0500 (0.0500)  time: 0.5433  data: 0.0256  max mem: 31830
Epoch: [292]  [290/312]  eta: 0:00:12  lr: 0.000007  min_lr: 0.000007  loss: 3.0195 (3.1318)  weight_decay: 0.0500 (0.0500)  time: 0.5103  data: 0.0089  max mem: 31830
Epoch: [292]  [300/312]  eta: 0:00:06  lr: 0.000007  min_lr: 0.000007  loss: 3.2955 (3.1328)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0074  max mem: 31830
Epoch: [292]  [310/312]  eta: 0:00:01  lr: 0.000007  min_lr: 0.000007  loss: 3.2543 (3.1320)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [292]  [311/312]  eta: 0:00:00  lr: 0.000007  min_lr: 0.000007  loss: 3.3181 (3.1328)  weight_decay: 0.0500 (0.0500)  time: 0.3805  data: 0.0001  max mem: 31830
Epoch: [292] Total time: 0:02:57 (0.5695 s / it)
Averaged stats: lr: 0.000007  min_lr: 0.000007  loss: 3.3181 (3.1744)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.8642 (0.8642)  acc1: 85.6771 (85.6771)  acc5: 97.2656 (97.2656)  time: 7.9292  data: 7.7685  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1590 (1.0840)  acc1: 79.4271 (78.6080)  acc5: 94.9219 (94.5440)  time: 1.0634  data: 0.9283  max mem: 31830
Test: Total time: 0:00:09 (1.0729 s / it)
* Acc@1 78.704 Acc@5 94.524 loss 1.081
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.70%
Epoch: [293]  [  0/312]  eta: 0:56:06  lr: 0.000007  min_lr: 0.000007  loss: 2.6316 (2.6316)  weight_decay: 0.0500 (0.0500)  time: 10.7893  data: 8.4178  max mem: 31830
Epoch: [293]  [ 10/312]  eta: 0:08:34  lr: 0.000007  min_lr: 0.000007  loss: 2.8972 (3.0002)  weight_decay: 0.0500 (0.0500)  time: 1.7024  data: 1.0231  max mem: 31830
Epoch: [293]  [ 20/312]  eta: 0:05:16  lr: 0.000007  min_lr: 0.000007  loss: 3.1205 (3.0791)  weight_decay: 0.0500 (0.0500)  time: 0.5997  data: 0.1422  max mem: 31830
Epoch: [293]  [ 30/312]  eta: 0:04:03  lr: 0.000007  min_lr: 0.000007  loss: 3.1923 (3.1093)  weight_decay: 0.0500 (0.0500)  time: 0.4026  data: 0.0009  max mem: 31830
Epoch: [293]  [ 40/312]  eta: 0:03:24  lr: 0.000007  min_lr: 0.000007  loss: 3.4282 (3.1626)  weight_decay: 0.0500 (0.0500)  time: 0.3991  data: 0.0009  max mem: 31830
Epoch: [293]  [ 50/312]  eta: 0:03:02  lr: 0.000007  min_lr: 0.000007  loss: 3.4165 (3.1824)  weight_decay: 0.0500 (0.0500)  time: 0.4400  data: 0.0008  max mem: 31830
Epoch: [293]  [ 60/312]  eta: 0:02:43  lr: 0.000007  min_lr: 0.000007  loss: 3.3857 (3.1734)  weight_decay: 0.0500 (0.0500)  time: 0.4403  data: 0.0010  max mem: 31830
Epoch: [293]  [ 70/312]  eta: 0:02:35  lr: 0.000007  min_lr: 0.000007  loss: 3.2357 (3.1609)  weight_decay: 0.0500 (0.0500)  time: 0.5046  data: 0.0296  max mem: 31830
Epoch: [293]  [ 80/312]  eta: 0:02:27  lr: 0.000007  min_lr: 0.000007  loss: 3.1535 (3.1582)  weight_decay: 0.0500 (0.0500)  time: 0.5977  data: 0.0365  max mem: 31830
Epoch: [293]  [ 90/312]  eta: 0:02:17  lr: 0.000007  min_lr: 0.000007  loss: 2.9689 (3.1321)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0145  max mem: 31830
Epoch: [293]  [100/312]  eta: 0:02:11  lr: 0.000007  min_lr: 0.000007  loss: 3.0851 (3.1343)  weight_decay: 0.0500 (0.0500)  time: 0.5454  data: 0.0431  max mem: 31830
Epoch: [293]  [110/312]  eta: 0:02:00  lr: 0.000007  min_lr: 0.000007  loss: 3.2856 (3.1402)  weight_decay: 0.0500 (0.0500)  time: 0.5070  data: 0.0367  max mem: 31830
Epoch: [293]  [120/312]  eta: 0:01:55  lr: 0.000007  min_lr: 0.000007  loss: 3.3550 (3.1492)  weight_decay: 0.0500 (0.0500)  time: 0.5040  data: 0.0235  max mem: 31830
Epoch: [293]  [130/312]  eta: 0:01:49  lr: 0.000006  min_lr: 0.000006  loss: 3.3389 (3.1631)  weight_decay: 0.0500 (0.0500)  time: 0.6100  data: 0.0486  max mem: 31830
Epoch: [293]  [140/312]  eta: 0:01:41  lr: 0.000006  min_lr: 0.000006  loss: 3.2582 (3.1500)  weight_decay: 0.0500 (0.0500)  time: 0.5164  data: 0.0261  max mem: 31830
Epoch: [293]  [150/312]  eta: 0:01:35  lr: 0.000006  min_lr: 0.000006  loss: 3.2582 (3.1591)  weight_decay: 0.0500 (0.0500)  time: 0.5212  data: 0.0180  max mem: 31830
Epoch: [293]  [160/312]  eta: 0:01:29  lr: 0.000006  min_lr: 0.000006  loss: 3.4549 (3.1711)  weight_decay: 0.0500 (0.0500)  time: 0.6062  data: 0.0179  max mem: 31830
Epoch: [293]  [170/312]  eta: 0:01:22  lr: 0.000006  min_lr: 0.000006  loss: 3.4116 (3.1661)  weight_decay: 0.0500 (0.0500)  time: 0.5385  data: 0.0137  max mem: 31830
Epoch: [293]  [180/312]  eta: 0:01:17  lr: 0.000006  min_lr: 0.000006  loss: 3.3463 (3.1723)  weight_decay: 0.0500 (0.0500)  time: 0.5516  data: 0.0137  max mem: 31830
Epoch: [293]  [190/312]  eta: 0:01:10  lr: 0.000006  min_lr: 0.000006  loss: 3.2133 (3.1577)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0015  max mem: 31830
Epoch: [293]  [200/312]  eta: 0:01:04  lr: 0.000006  min_lr: 0.000006  loss: 3.1285 (3.1666)  weight_decay: 0.0500 (0.0500)  time: 0.5326  data: 0.0036  max mem: 31830
Epoch: [293]  [210/312]  eta: 0:00:59  lr: 0.000006  min_lr: 0.000006  loss: 3.1285 (3.1612)  weight_decay: 0.0500 (0.0500)  time: 0.5850  data: 0.0083  max mem: 31830
Epoch: [293]  [220/312]  eta: 0:00:52  lr: 0.000006  min_lr: 0.000006  loss: 3.0707 (3.1646)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0063  max mem: 31830
Epoch: [293]  [230/312]  eta: 0:00:47  lr: 0.000006  min_lr: 0.000006  loss: 3.1143 (3.1560)  weight_decay: 0.0500 (0.0500)  time: 0.6049  data: 0.0267  max mem: 31830
Epoch: [293]  [240/312]  eta: 0:00:41  lr: 0.000006  min_lr: 0.000006  loss: 3.4051 (3.1627)  weight_decay: 0.0500 (0.0500)  time: 0.5802  data: 0.0275  max mem: 31830
Epoch: [293]  [250/312]  eta: 0:00:35  lr: 0.000006  min_lr: 0.000006  loss: 3.3774 (3.1608)  weight_decay: 0.0500 (0.0500)  time: 0.5140  data: 0.0017  max mem: 31830
Epoch: [293]  [260/312]  eta: 0:00:30  lr: 0.000006  min_lr: 0.000006  loss: 3.1719 (3.1569)  weight_decay: 0.0500 (0.0500)  time: 0.6012  data: 0.0073  max mem: 31830
Epoch: [293]  [270/312]  eta: 0:00:24  lr: 0.000006  min_lr: 0.000006  loss: 3.2450 (3.1614)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0073  max mem: 31830
Epoch: [293]  [280/312]  eta: 0:00:18  lr: 0.000006  min_lr: 0.000006  loss: 3.3779 (3.1554)  weight_decay: 0.0500 (0.0500)  time: 0.5393  data: 0.0077  max mem: 31830
Epoch: [293]  [290/312]  eta: 0:00:12  lr: 0.000006  min_lr: 0.000006  loss: 3.2497 (3.1570)  weight_decay: 0.0500 (0.0500)  time: 0.5303  data: 0.0144  max mem: 31830
Epoch: [293]  [300/312]  eta: 0:00:06  lr: 0.000006  min_lr: 0.000006  loss: 3.3699 (3.1606)  weight_decay: 0.0500 (0.0500)  time: 0.4162  data: 0.0072  max mem: 31830
Epoch: [293]  [310/312]  eta: 0:00:01  lr: 0.000006  min_lr: 0.000006  loss: 3.0633 (3.1519)  weight_decay: 0.0500 (0.0500)  time: 0.4010  data: 0.0001  max mem: 31830
Epoch: [293]  [311/312]  eta: 0:00:00  lr: 0.000006  min_lr: 0.000006  loss: 3.0633 (3.1536)  weight_decay: 0.0500 (0.0500)  time: 0.4009  data: 0.0001  max mem: 31830
Epoch: [293] Total time: 0:02:55 (0.5616 s / it)
Averaged stats: lr: 0.000006  min_lr: 0.000006  loss: 3.0633 (3.1524)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8487 (0.8487)  acc1: 85.1562 (85.1562)  acc5: 97.2656 (97.2656)  time: 8.3903  data: 8.2227  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1344 (1.0608)  acc1: 79.0365 (78.4160)  acc5: 94.9219 (94.5760)  time: 1.0600  data: 0.9248  max mem: 31830
Test: Total time: 0:00:09 (1.0760 s / it)
* Acc@1 78.702 Acc@5 94.538 loss 1.057
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.70%
Epoch: [294]  [  0/312]  eta: 1:02:15  lr: 0.000006  min_lr: 0.000006  loss: 3.4512 (3.4512)  weight_decay: 0.0500 (0.0500)  time: 11.9721  data: 11.5712  max mem: 31830
Epoch: [294]  [ 10/312]  eta: 0:08:22  lr: 0.000005  min_lr: 0.000005  loss: 3.2957 (3.1182)  weight_decay: 0.0500 (0.0500)  time: 1.6643  data: 1.0526  max mem: 31830
Epoch: [294]  [ 20/312]  eta: 0:05:18  lr: 0.000005  min_lr: 0.000005  loss: 2.8804 (3.0011)  weight_decay: 0.0500 (0.0500)  time: 0.5483  data: 0.0008  max mem: 31830
Epoch: [294]  [ 30/312]  eta: 0:04:05  lr: 0.000005  min_lr: 0.000005  loss: 3.2598 (3.0649)  weight_decay: 0.0500 (0.0500)  time: 0.4318  data: 0.0009  max mem: 31830
Epoch: [294]  [ 40/312]  eta: 0:03:24  lr: 0.000005  min_lr: 0.000005  loss: 3.1803 (3.0378)  weight_decay: 0.0500 (0.0500)  time: 0.3966  data: 0.0008  max mem: 31830
Epoch: [294]  [ 50/312]  eta: 0:03:03  lr: 0.000005  min_lr: 0.000005  loss: 2.9388 (3.0446)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0511  max mem: 31830
Epoch: [294]  [ 60/312]  eta: 0:02:44  lr: 0.000005  min_lr: 0.000005  loss: 3.1938 (3.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4444  data: 0.0511  max mem: 31830
Epoch: [294]  [ 70/312]  eta: 0:02:38  lr: 0.000005  min_lr: 0.000005  loss: 3.2545 (3.0580)  weight_decay: 0.0500 (0.0500)  time: 0.5301  data: 0.1348  max mem: 31830
Epoch: [294]  [ 80/312]  eta: 0:02:30  lr: 0.000005  min_lr: 0.000005  loss: 3.3024 (3.0463)  weight_decay: 0.0500 (0.0500)  time: 0.6360  data: 0.2399  max mem: 31830
Epoch: [294]  [ 90/312]  eta: 0:02:17  lr: 0.000005  min_lr: 0.000005  loss: 2.9546 (3.0472)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.1065  max mem: 31830
Epoch: [294]  [100/312]  eta: 0:02:11  lr: 0.000005  min_lr: 0.000005  loss: 3.1030 (3.0417)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.1119  max mem: 31830
Epoch: [294]  [110/312]  eta: 0:02:01  lr: 0.000005  min_lr: 0.000005  loss: 3.2481 (3.0525)  weight_decay: 0.0500 (0.0500)  time: 0.5069  data: 0.1116  max mem: 31830
Epoch: [294]  [120/312]  eta: 0:01:55  lr: 0.000005  min_lr: 0.000005  loss: 3.2481 (3.0452)  weight_decay: 0.0500 (0.0500)  time: 0.5083  data: 0.1155  max mem: 31830
Epoch: [294]  [130/312]  eta: 0:01:49  lr: 0.000005  min_lr: 0.000005  loss: 2.8655 (3.0285)  weight_decay: 0.0500 (0.0500)  time: 0.5928  data: 0.1987  max mem: 31830
Epoch: [294]  [140/312]  eta: 0:01:40  lr: 0.000005  min_lr: 0.000005  loss: 2.8569 (3.0283)  weight_decay: 0.0500 (0.0500)  time: 0.4849  data: 0.0918  max mem: 31830
Epoch: [294]  [150/312]  eta: 0:01:35  lr: 0.000005  min_lr: 0.000005  loss: 3.1436 (3.0297)  weight_decay: 0.0500 (0.0500)  time: 0.5311  data: 0.1408  max mem: 31830
Epoch: [294]  [160/312]  eta: 0:01:29  lr: 0.000005  min_lr: 0.000005  loss: 3.1747 (3.0330)  weight_decay: 0.0500 (0.0500)  time: 0.6063  data: 0.2148  max mem: 31830
Epoch: [294]  [170/312]  eta: 0:01:21  lr: 0.000005  min_lr: 0.000005  loss: 3.2348 (3.0425)  weight_decay: 0.0500 (0.0500)  time: 0.4785  data: 0.0823  max mem: 31830
Epoch: [294]  [180/312]  eta: 0:01:16  lr: 0.000005  min_lr: 0.000005  loss: 3.2309 (3.0433)  weight_decay: 0.0500 (0.0500)  time: 0.5061  data: 0.0918  max mem: 31830
Epoch: [294]  [190/312]  eta: 0:01:09  lr: 0.000005  min_lr: 0.000005  loss: 3.1271 (3.0490)  weight_decay: 0.0500 (0.0500)  time: 0.5050  data: 0.0917  max mem: 31830
Epoch: [294]  [200/312]  eta: 0:01:04  lr: 0.000005  min_lr: 0.000005  loss: 3.0380 (3.0492)  weight_decay: 0.0500 (0.0500)  time: 0.5287  data: 0.1313  max mem: 31830
Epoch: [294]  [210/312]  eta: 0:00:58  lr: 0.000005  min_lr: 0.000005  loss: 3.0380 (3.0560)  weight_decay: 0.0500 (0.0500)  time: 0.6223  data: 0.2251  max mem: 31830
Epoch: [294]  [220/312]  eta: 0:00:52  lr: 0.000005  min_lr: 0.000005  loss: 3.2450 (3.0598)  weight_decay: 0.0500 (0.0500)  time: 0.5095  data: 0.0949  max mem: 31830
Epoch: [294]  [230/312]  eta: 0:00:46  lr: 0.000004  min_lr: 0.000004  loss: 3.0529 (3.0633)  weight_decay: 0.0500 (0.0500)  time: 0.5320  data: 0.1131  max mem: 31830
Epoch: [294]  [240/312]  eta: 0:00:41  lr: 0.000004  min_lr: 0.000004  loss: 3.1608 (3.0681)  weight_decay: 0.0500 (0.0500)  time: 0.6230  data: 0.2104  max mem: 31830
Epoch: [294]  [250/312]  eta: 0:00:35  lr: 0.000004  min_lr: 0.000004  loss: 3.1839 (3.0719)  weight_decay: 0.0500 (0.0500)  time: 0.5195  data: 0.0984  max mem: 31830
Epoch: [294]  [260/312]  eta: 0:00:29  lr: 0.000004  min_lr: 0.000004  loss: 3.3958 (3.0776)  weight_decay: 0.0500 (0.0500)  time: 0.5067  data: 0.0969  max mem: 31830
Epoch: [294]  [270/312]  eta: 0:00:23  lr: 0.000004  min_lr: 0.000004  loss: 3.4246 (3.0817)  weight_decay: 0.0500 (0.0500)  time: 0.4952  data: 0.0972  max mem: 31830
Epoch: [294]  [280/312]  eta: 0:00:18  lr: 0.000004  min_lr: 0.000004  loss: 3.3702 (3.0873)  weight_decay: 0.0500 (0.0500)  time: 0.5232  data: 0.1260  max mem: 31830
Epoch: [294]  [290/312]  eta: 0:00:12  lr: 0.000004  min_lr: 0.000004  loss: 3.3702 (3.0916)  weight_decay: 0.0500 (0.0500)  time: 0.6131  data: 0.2180  max mem: 31830
Epoch: [294]  [300/312]  eta: 0:00:06  lr: 0.000004  min_lr: 0.000004  loss: 2.9101 (3.0803)  weight_decay: 0.0500 (0.0500)  time: 0.4807  data: 0.0928  max mem: 31830
Epoch: [294]  [310/312]  eta: 0:00:01  lr: 0.000004  min_lr: 0.000004  loss: 3.0818 (3.0785)  weight_decay: 0.0500 (0.0500)  time: 0.3812  data: 0.0001  max mem: 31830
Epoch: [294]  [311/312]  eta: 0:00:00  lr: 0.000004  min_lr: 0.000004  loss: 3.0818 (3.0809)  weight_decay: 0.0500 (0.0500)  time: 0.3810  data: 0.0001  max mem: 31830
Epoch: [294] Total time: 0:02:53 (0.5564 s / it)
Averaged stats: lr: 0.000004  min_lr: 0.000004  loss: 3.0818 (3.1422)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8348 (0.8348)  acc1: 85.6771 (85.6771)  acc5: 97.2656 (97.2656)  time: 8.4927  data: 8.3250  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1277 (1.0519)  acc1: 79.1667 (78.4640)  acc5: 94.7917 (94.4800)  time: 1.0717  data: 0.9251  max mem: 31830
Test: Total time: 0:00:09 (1.0824 s / it)
* Acc@1 78.772 Acc@5 94.474 loss 1.048
Accuracy of the model on the 50000 test images: 78.8%
Max accuracy: 78.77%
Epoch: [295]  [  0/312]  eta: 1:01:56  lr: 0.000004  min_lr: 0.000004  loss: 3.4103 (3.4103)  weight_decay: 0.0500 (0.0500)  time: 11.9106  data: 9.6972  max mem: 31830
Epoch: [295]  [ 10/312]  eta: 0:09:14  lr: 0.000004  min_lr: 0.000004  loss: 3.2619 (3.1329)  weight_decay: 0.0500 (0.0500)  time: 1.8346  data: 1.0573  max mem: 31830
Epoch: [295]  [ 20/312]  eta: 0:05:42  lr: 0.000004  min_lr: 0.000004  loss: 3.0581 (3.1137)  weight_decay: 0.0500 (0.0500)  time: 0.6359  data: 0.1221  max mem: 31830
Epoch: [295]  [ 30/312]  eta: 0:04:19  lr: 0.000004  min_lr: 0.000004  loss: 3.1412 (3.1594)  weight_decay: 0.0500 (0.0500)  time: 0.4199  data: 0.0258  max mem: 31830
Epoch: [295]  [ 40/312]  eta: 0:03:35  lr: 0.000004  min_lr: 0.000004  loss: 3.1655 (3.1618)  weight_decay: 0.0500 (0.0500)  time: 0.3949  data: 0.0017  max mem: 31830
Epoch: [295]  [ 50/312]  eta: 0:03:07  lr: 0.000004  min_lr: 0.000004  loss: 3.1904 (3.1696)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0018  max mem: 31830
Epoch: [295]  [ 60/312]  eta: 0:02:47  lr: 0.000004  min_lr: 0.000004  loss: 3.3326 (3.1470)  weight_decay: 0.0500 (0.0500)  time: 0.3997  data: 0.0008  max mem: 31830
Epoch: [295]  [ 70/312]  eta: 0:02:31  lr: 0.000004  min_lr: 0.000004  loss: 2.9756 (3.1073)  weight_decay: 0.0500 (0.0500)  time: 0.3992  data: 0.0008  max mem: 31830
Epoch: [295]  [ 80/312]  eta: 0:02:21  lr: 0.000004  min_lr: 0.000004  loss: 3.0651 (3.1140)  weight_decay: 0.0500 (0.0500)  time: 0.4468  data: 0.0009  max mem: 31830
Epoch: [295]  [ 90/312]  eta: 0:02:13  lr: 0.000004  min_lr: 0.000004  loss: 3.1688 (3.1158)  weight_decay: 0.0500 (0.0500)  time: 0.5012  data: 0.0073  max mem: 31830
Epoch: [295]  [100/312]  eta: 0:02:07  lr: 0.000004  min_lr: 0.000004  loss: 3.1783 (3.1204)  weight_decay: 0.0500 (0.0500)  time: 0.5533  data: 0.0074  max mem: 31830
Epoch: [295]  [110/312]  eta: 0:02:00  lr: 0.000004  min_lr: 0.000004  loss: 3.3912 (3.1281)  weight_decay: 0.0500 (0.0500)  time: 0.5765  data: 0.0072  max mem: 31830
Epoch: [295]  [120/312]  eta: 0:01:52  lr: 0.000004  min_lr: 0.000004  loss: 3.3245 (3.1332)  weight_decay: 0.0500 (0.0500)  time: 0.5234  data: 0.0129  max mem: 31830
Epoch: [295]  [130/312]  eta: 0:01:45  lr: 0.000004  min_lr: 0.000004  loss: 3.3849 (3.1544)  weight_decay: 0.0500 (0.0500)  time: 0.5113  data: 0.0258  max mem: 31830
Epoch: [295]  [140/312]  eta: 0:01:40  lr: 0.000004  min_lr: 0.000004  loss: 3.3516 (3.1507)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0548  max mem: 31830
Epoch: [295]  [150/312]  eta: 0:01:34  lr: 0.000004  min_lr: 0.000004  loss: 3.1428 (3.1465)  weight_decay: 0.0500 (0.0500)  time: 0.5727  data: 0.0358  max mem: 31830
Epoch: [295]  [160/312]  eta: 0:01:27  lr: 0.000004  min_lr: 0.000004  loss: 3.2368 (3.1531)  weight_decay: 0.0500 (0.0500)  time: 0.5377  data: 0.0286  max mem: 31830
Epoch: [295]  [170/312]  eta: 0:01:21  lr: 0.000003  min_lr: 0.000003  loss: 3.3384 (3.1610)  weight_decay: 0.0500 (0.0500)  time: 0.5356  data: 0.0285  max mem: 31830
Epoch: [295]  [180/312]  eta: 0:01:16  lr: 0.000003  min_lr: 0.000003  loss: 3.3098 (3.1656)  weight_decay: 0.0500 (0.0500)  time: 0.5773  data: 0.0016  max mem: 31830
Epoch: [295]  [190/312]  eta: 0:01:10  lr: 0.000003  min_lr: 0.000003  loss: 3.3098 (3.1642)  weight_decay: 0.0500 (0.0500)  time: 0.5663  data: 0.0082  max mem: 31830
Epoch: [295]  [200/312]  eta: 0:01:03  lr: 0.000003  min_lr: 0.000003  loss: 3.4068 (3.1677)  weight_decay: 0.0500 (0.0500)  time: 0.5172  data: 0.0077  max mem: 31830
Epoch: [295]  [210/312]  eta: 0:00:57  lr: 0.000003  min_lr: 0.000003  loss: 3.3087 (3.1652)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0015  max mem: 31830
Epoch: [295]  [220/312]  eta: 0:00:52  lr: 0.000003  min_lr: 0.000003  loss: 3.3087 (3.1667)  weight_decay: 0.0500 (0.0500)  time: 0.5871  data: 0.0167  max mem: 31830
Epoch: [295]  [230/312]  eta: 0:00:46  lr: 0.000003  min_lr: 0.000003  loss: 3.4330 (3.1775)  weight_decay: 0.0500 (0.0500)  time: 0.5925  data: 0.0174  max mem: 31830
Epoch: [295]  [240/312]  eta: 0:00:40  lr: 0.000003  min_lr: 0.000003  loss: 3.3797 (3.1755)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0073  max mem: 31830
Epoch: [295]  [250/312]  eta: 0:00:35  lr: 0.000003  min_lr: 0.000003  loss: 2.9492 (3.1588)  weight_decay: 0.0500 (0.0500)  time: 0.5260  data: 0.0064  max mem: 31830
Epoch: [295]  [260/312]  eta: 0:00:29  lr: 0.000003  min_lr: 0.000003  loss: 2.8359 (3.1489)  weight_decay: 0.0500 (0.0500)  time: 0.5386  data: 0.0058  max mem: 31830
Epoch: [295]  [270/312]  eta: 0:00:23  lr: 0.000003  min_lr: 0.000003  loss: 3.1846 (3.1489)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0111  max mem: 31830
Epoch: [295]  [280/312]  eta: 0:00:18  lr: 0.000003  min_lr: 0.000003  loss: 3.2836 (3.1574)  weight_decay: 0.0500 (0.0500)  time: 0.5290  data: 0.0075  max mem: 31830
Epoch: [295]  [290/312]  eta: 0:00:12  lr: 0.000003  min_lr: 0.000003  loss: 3.2495 (3.1540)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0068  max mem: 31830
Epoch: [295]  [300/312]  eta: 0:00:06  lr: 0.000003  min_lr: 0.000003  loss: 3.1743 (3.1546)  weight_decay: 0.0500 (0.0500)  time: 0.5220  data: 0.0053  max mem: 31830
Epoch: [295]  [310/312]  eta: 0:00:01  lr: 0.000003  min_lr: 0.000003  loss: 3.2059 (3.1573)  weight_decay: 0.0500 (0.0500)  time: 0.4110  data: 0.0001  max mem: 31830
Epoch: [295]  [311/312]  eta: 0:00:00  lr: 0.000003  min_lr: 0.000003  loss: 3.2059 (3.1586)  weight_decay: 0.0500 (0.0500)  time: 0.4101  data: 0.0001  max mem: 31830
Epoch: [295] Total time: 0:02:54 (0.5578 s / it)
Averaged stats: lr: 0.000003  min_lr: 0.000003  loss: 3.2059 (3.1571)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8993 (0.8993)  acc1: 85.2865 (85.2865)  acc5: 97.2656 (97.2656)  time: 8.8946  data: 8.7272  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1925 (1.1185)  acc1: 79.2969 (78.4640)  acc5: 95.0521 (94.5120)  time: 1.1058  data: 0.9698  max mem: 31830
Test: Total time: 0:00:10 (1.1173 s / it)
* Acc@1 78.616 Acc@5 94.476 loss 1.115
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.77%
Epoch: [296]  [  0/312]  eta: 1:05:45  lr: 0.000003  min_lr: 0.000003  loss: 2.4214 (2.4214)  weight_decay: 0.0500 (0.0500)  time: 12.6466  data: 10.8198  max mem: 31830
Epoch: [296]  [ 10/312]  eta: 0:08:46  lr: 0.000003  min_lr: 0.000003  loss: 3.2657 (3.1480)  weight_decay: 0.0500 (0.0500)  time: 1.7420  data: 1.0834  max mem: 31830
Epoch: [296]  [ 20/312]  eta: 0:05:35  lr: 0.000003  min_lr: 0.000003  loss: 3.0410 (2.9742)  weight_decay: 0.0500 (0.0500)  time: 0.5731  data: 0.0825  max mem: 31830
Epoch: [296]  [ 30/312]  eta: 0:04:15  lr: 0.000003  min_lr: 0.000003  loss: 2.9492 (3.0510)  weight_decay: 0.0500 (0.0500)  time: 0.4471  data: 0.0279  max mem: 31830
Epoch: [296]  [ 40/312]  eta: 0:03:32  lr: 0.000003  min_lr: 0.000003  loss: 3.3120 (3.0758)  weight_decay: 0.0500 (0.0500)  time: 0.3970  data: 0.0008  max mem: 31830
Epoch: [296]  [ 50/312]  eta: 0:03:06  lr: 0.000003  min_lr: 0.000003  loss: 3.1607 (3.0860)  weight_decay: 0.0500 (0.0500)  time: 0.4126  data: 0.0080  max mem: 31830
Epoch: [296]  [ 60/312]  eta: 0:02:46  lr: 0.000003  min_lr: 0.000003  loss: 3.0988 (3.1048)  weight_decay: 0.0500 (0.0500)  time: 0.4139  data: 0.0079  max mem: 31830
Epoch: [296]  [ 70/312]  eta: 0:02:37  lr: 0.000003  min_lr: 0.000003  loss: 2.9044 (3.0383)  weight_decay: 0.0500 (0.0500)  time: 0.4942  data: 0.0985  max mem: 31830
Epoch: [296]  [ 80/312]  eta: 0:02:30  lr: 0.000003  min_lr: 0.000003  loss: 2.7577 (3.0330)  weight_decay: 0.0500 (0.0500)  time: 0.6058  data: 0.2086  max mem: 31830
Epoch: [296]  [ 90/312]  eta: 0:02:17  lr: 0.000003  min_lr: 0.000003  loss: 3.2273 (3.0494)  weight_decay: 0.0500 (0.0500)  time: 0.5075  data: 0.1109  max mem: 31830
Epoch: [296]  [100/312]  eta: 0:02:10  lr: 0.000003  min_lr: 0.000003  loss: 3.2267 (3.0577)  weight_decay: 0.0500 (0.0500)  time: 0.4954  data: 0.1033  max mem: 31830
Epoch: [296]  [110/312]  eta: 0:02:00  lr: 0.000003  min_lr: 0.000003  loss: 3.4452 (3.0948)  weight_decay: 0.0500 (0.0500)  time: 0.4949  data: 0.1032  max mem: 31830
Epoch: [296]  [120/312]  eta: 0:01:55  lr: 0.000003  min_lr: 0.000003  loss: 3.3329 (3.0885)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.1171  max mem: 31830
Epoch: [296]  [130/312]  eta: 0:01:49  lr: 0.000003  min_lr: 0.000003  loss: 2.9752 (3.0821)  weight_decay: 0.0500 (0.0500)  time: 0.6298  data: 0.2348  max mem: 31830
Epoch: [296]  [140/312]  eta: 0:01:41  lr: 0.000003  min_lr: 0.000003  loss: 3.2701 (3.0817)  weight_decay: 0.0500 (0.0500)  time: 0.5122  data: 0.1200  max mem: 31830
Epoch: [296]  [150/312]  eta: 0:01:35  lr: 0.000003  min_lr: 0.000003  loss: 3.2748 (3.0819)  weight_decay: 0.0500 (0.0500)  time: 0.5199  data: 0.1260  max mem: 31830
Epoch: [296]  [160/312]  eta: 0:01:29  lr: 0.000003  min_lr: 0.000003  loss: 3.1233 (3.0838)  weight_decay: 0.0500 (0.0500)  time: 0.6248  data: 0.2303  max mem: 31830
Epoch: [296]  [170/312]  eta: 0:01:22  lr: 0.000003  min_lr: 0.000003  loss: 3.1352 (3.0812)  weight_decay: 0.0500 (0.0500)  time: 0.5020  data: 0.1066  max mem: 31830
Epoch: [296]  [180/312]  eta: 0:01:16  lr: 0.000002  min_lr: 0.000002  loss: 3.2239 (3.0867)  weight_decay: 0.0500 (0.0500)  time: 0.5125  data: 0.1136  max mem: 31830
Epoch: [296]  [190/312]  eta: 0:01:09  lr: 0.000002  min_lr: 0.000002  loss: 3.1389 (3.0758)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.1135  max mem: 31830
Epoch: [296]  [200/312]  eta: 0:01:04  lr: 0.000002  min_lr: 0.000002  loss: 3.2114 (3.0878)  weight_decay: 0.0500 (0.0500)  time: 0.5183  data: 0.1239  max mem: 31830
Epoch: [296]  [210/312]  eta: 0:00:58  lr: 0.000002  min_lr: 0.000002  loss: 3.3084 (3.0927)  weight_decay: 0.0500 (0.0500)  time: 0.5849  data: 0.1896  max mem: 31830
Epoch: [296]  [220/312]  eta: 0:00:52  lr: 0.000002  min_lr: 0.000002  loss: 3.2323 (3.0946)  weight_decay: 0.0500 (0.0500)  time: 0.4617  data: 0.0665  max mem: 31830
Epoch: [296]  [230/312]  eta: 0:00:46  lr: 0.000002  min_lr: 0.000002  loss: 3.2323 (3.0973)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.1137  max mem: 31830
Epoch: [296]  [240/312]  eta: 0:00:41  lr: 0.000002  min_lr: 0.000002  loss: 3.1528 (3.0922)  weight_decay: 0.0500 (0.0500)  time: 0.6055  data: 0.2076  max mem: 31830
Epoch: [296]  [250/312]  eta: 0:00:35  lr: 0.000002  min_lr: 0.000002  loss: 2.8015 (3.0771)  weight_decay: 0.0500 (0.0500)  time: 0.5267  data: 0.0949  max mem: 31830
Epoch: [296]  [260/312]  eta: 0:00:29  lr: 0.000002  min_lr: 0.000002  loss: 2.6982 (3.0797)  weight_decay: 0.0500 (0.0500)  time: 0.5461  data: 0.0652  max mem: 31830
Epoch: [296]  [270/312]  eta: 0:00:23  lr: 0.000002  min_lr: 0.000002  loss: 3.3266 (3.0875)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0652  max mem: 31830
Epoch: [296]  [280/312]  eta: 0:00:18  lr: 0.000002  min_lr: 0.000002  loss: 3.2604 (3.0905)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0938  max mem: 31830
Epoch: [296]  [290/312]  eta: 0:00:12  lr: 0.000002  min_lr: 0.000002  loss: 3.3058 (3.0984)  weight_decay: 0.0500 (0.0500)  time: 0.6168  data: 0.1856  max mem: 31830
Epoch: [296]  [300/312]  eta: 0:00:06  lr: 0.000002  min_lr: 0.000002  loss: 3.2891 (3.0960)  weight_decay: 0.0500 (0.0500)  time: 0.4890  data: 0.0925  max mem: 31830
Epoch: [296]  [310/312]  eta: 0:00:01  lr: 0.000002  min_lr: 0.000002  loss: 3.2613 (3.0986)  weight_decay: 0.0500 (0.0500)  time: 0.3814  data: 0.0002  max mem: 31830
Epoch: [296]  [311/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 3.2613 (3.0990)  weight_decay: 0.0500 (0.0500)  time: 0.3813  data: 0.0002  max mem: 31830
Epoch: [296] Total time: 0:02:53 (0.5569 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 3.2613 (3.1591)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.9051 (0.9051)  acc1: 85.6771 (85.6771)  acc5: 97.2656 (97.2656)  time: 8.7873  data: 8.6262  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1938 (1.1206)  acc1: 79.1667 (78.5600)  acc5: 94.9219 (94.5120)  time: 1.0959  data: 0.9586  max mem: 31830
Test: Total time: 0:00:10 (1.1209 s / it)
* Acc@1 78.642 Acc@5 94.488 loss 1.118
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.77%
Epoch: [297]  [  0/312]  eta: 0:57:34  lr: 0.000002  min_lr: 0.000002  loss: 3.7246 (3.7246)  weight_decay: 0.0500 (0.0500)  time: 11.0712  data: 8.3931  max mem: 31830
Epoch: [297]  [ 10/312]  eta: 0:08:37  lr: 0.000002  min_lr: 0.000002  loss: 3.5181 (3.4661)  weight_decay: 0.0500 (0.0500)  time: 1.7125  data: 1.0149  max mem: 31830
Epoch: [297]  [ 20/312]  eta: 0:05:16  lr: 0.000002  min_lr: 0.000002  loss: 3.2822 (3.2036)  weight_decay: 0.0500 (0.0500)  time: 0.5851  data: 0.1390  max mem: 31830
Epoch: [297]  [ 30/312]  eta: 0:04:03  lr: 0.000002  min_lr: 0.000002  loss: 3.1632 (3.2148)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0010  max mem: 31830
Epoch: [297]  [ 40/312]  eta: 0:03:24  lr: 0.000002  min_lr: 0.000002  loss: 3.2482 (3.2060)  weight_decay: 0.0500 (0.0500)  time: 0.3999  data: 0.0011  max mem: 31830
Epoch: [297]  [ 50/312]  eta: 0:02:59  lr: 0.000002  min_lr: 0.000002  loss: 3.1829 (3.2164)  weight_decay: 0.0500 (0.0500)  time: 0.4053  data: 0.0010  max mem: 31830
Epoch: [297]  [ 60/312]  eta: 0:02:40  lr: 0.000002  min_lr: 0.000002  loss: 3.3111 (3.2293)  weight_decay: 0.0500 (0.0500)  time: 0.4049  data: 0.0009  max mem: 31830
Epoch: [297]  [ 70/312]  eta: 0:02:33  lr: 0.000002  min_lr: 0.000002  loss: 3.3111 (3.2274)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0634  max mem: 31830
Epoch: [297]  [ 80/312]  eta: 0:02:24  lr: 0.000002  min_lr: 0.000002  loss: 3.3449 (3.2100)  weight_decay: 0.0500 (0.0500)  time: 0.5729  data: 0.0703  max mem: 31830
Epoch: [297]  [ 90/312]  eta: 0:02:14  lr: 0.000002  min_lr: 0.000002  loss: 3.1575 (3.2043)  weight_decay: 0.0500 (0.0500)  time: 0.5071  data: 0.0553  max mem: 31830
Epoch: [297]  [100/312]  eta: 0:02:08  lr: 0.000002  min_lr: 0.000002  loss: 3.1575 (3.2029)  weight_decay: 0.0500 (0.0500)  time: 0.5444  data: 0.1006  max mem: 31830
Epoch: [297]  [110/312]  eta: 0:01:58  lr: 0.000002  min_lr: 0.000002  loss: 3.2672 (3.1962)  weight_decay: 0.0500 (0.0500)  time: 0.4969  data: 0.0529  max mem: 31830
Epoch: [297]  [120/312]  eta: 0:01:52  lr: 0.000002  min_lr: 0.000002  loss: 3.2474 (3.1729)  weight_decay: 0.0500 (0.0500)  time: 0.4922  data: 0.0567  max mem: 31830
Epoch: [297]  [130/312]  eta: 0:01:47  lr: 0.000002  min_lr: 0.000002  loss: 2.9428 (3.1565)  weight_decay: 0.0500 (0.0500)  time: 0.6004  data: 0.1062  max mem: 31830
Epoch: [297]  [140/312]  eta: 0:01:39  lr: 0.000002  min_lr: 0.000002  loss: 3.1835 (3.1613)  weight_decay: 0.0500 (0.0500)  time: 0.5197  data: 0.0641  max mem: 31830
Epoch: [297]  [150/312]  eta: 0:01:34  lr: 0.000002  min_lr: 0.000002  loss: 3.1835 (3.1495)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0669  max mem: 31830
Epoch: [297]  [160/312]  eta: 0:01:28  lr: 0.000002  min_lr: 0.000002  loss: 3.1202 (3.1363)  weight_decay: 0.0500 (0.0500)  time: 0.6073  data: 0.0580  max mem: 31830
Epoch: [297]  [170/312]  eta: 0:01:21  lr: 0.000002  min_lr: 0.000002  loss: 3.1665 (3.1427)  weight_decay: 0.0500 (0.0500)  time: 0.5044  data: 0.0385  max mem: 31830
Epoch: [297]  [180/312]  eta: 0:01:16  lr: 0.000002  min_lr: 0.000002  loss: 3.2867 (3.1413)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0629  max mem: 31830
Epoch: [297]  [190/312]  eta: 0:01:09  lr: 0.000002  min_lr: 0.000002  loss: 3.1930 (3.1388)  weight_decay: 0.0500 (0.0500)  time: 0.5099  data: 0.0303  max mem: 31830
Epoch: [297]  [200/312]  eta: 0:01:03  lr: 0.000002  min_lr: 0.000002  loss: 3.1975 (3.1340)  weight_decay: 0.0500 (0.0500)  time: 0.4944  data: 0.0316  max mem: 31830
Epoch: [297]  [210/312]  eta: 0:00:58  lr: 0.000002  min_lr: 0.000002  loss: 3.2700 (3.1264)  weight_decay: 0.0500 (0.0500)  time: 0.5924  data: 0.0619  max mem: 31830
Epoch: [297]  [220/312]  eta: 0:00:51  lr: 0.000002  min_lr: 0.000002  loss: 3.2276 (3.1247)  weight_decay: 0.0500 (0.0500)  time: 0.5116  data: 0.0312  max mem: 31830
Epoch: [297]  [230/312]  eta: 0:00:46  lr: 0.000002  min_lr: 0.000002  loss: 3.3320 (3.1292)  weight_decay: 0.0500 (0.0500)  time: 0.5321  data: 0.0377  max mem: 31830
Epoch: [297]  [240/312]  eta: 0:00:40  lr: 0.000002  min_lr: 0.000002  loss: 3.3022 (3.1273)  weight_decay: 0.0500 (0.0500)  time: 0.6113  data: 0.0378  max mem: 31830
Epoch: [297]  [250/312]  eta: 0:00:34  lr: 0.000002  min_lr: 0.000002  loss: 3.0847 (3.1234)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0171  max mem: 31830
Epoch: [297]  [260/312]  eta: 0:00:29  lr: 0.000002  min_lr: 0.000002  loss: 3.2736 (3.1309)  weight_decay: 0.0500 (0.0500)  time: 0.5015  data: 0.0360  max mem: 31830
Epoch: [297]  [270/312]  eta: 0:00:23  lr: 0.000002  min_lr: 0.000002  loss: 3.0832 (3.1294)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0199  max mem: 31830
Epoch: [297]  [280/312]  eta: 0:00:17  lr: 0.000002  min_lr: 0.000002  loss: 3.3984 (3.1426)  weight_decay: 0.0500 (0.0500)  time: 0.4972  data: 0.0175  max mem: 31830
Epoch: [297]  [290/312]  eta: 0:00:12  lr: 0.000002  min_lr: 0.000002  loss: 3.4341 (3.1509)  weight_decay: 0.0500 (0.0500)  time: 0.6013  data: 0.0514  max mem: 31830
Epoch: [297]  [300/312]  eta: 0:00:06  lr: 0.000002  min_lr: 0.000002  loss: 3.3889 (3.1607)  weight_decay: 0.0500 (0.0500)  time: 0.5298  data: 0.0344  max mem: 31830
Epoch: [297]  [310/312]  eta: 0:00:01  lr: 0.000002  min_lr: 0.000002  loss: 3.3192 (3.1547)  weight_decay: 0.0500 (0.0500)  time: 0.3961  data: 0.0002  max mem: 31830
Epoch: [297]  [311/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 3.3273 (3.1555)  weight_decay: 0.0500 (0.0500)  time: 0.3960  data: 0.0002  max mem: 31830
Epoch: [297] Total time: 0:02:52 (0.5536 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 3.3273 (3.1624)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8750 (0.8750)  acc1: 85.0260 (85.0260)  acc5: 97.2656 (97.2656)  time: 8.9794  data: 8.8122  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1662 (1.0902)  acc1: 78.9062 (78.4320)  acc5: 94.5312 (94.4960)  time: 1.1149  data: 0.9792  max mem: 31830
Test: Total time: 0:00:10 (1.1302 s / it)
* Acc@1 78.694 Acc@5 94.492 loss 1.088
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.77%
Epoch: [298]  [  0/312]  eta: 0:56:35  lr: 0.000002  min_lr: 0.000002  loss: 3.3222 (3.3222)  weight_decay: 0.0500 (0.0500)  time: 10.8845  data: 10.1904  max mem: 31830
Epoch: [298]  [ 10/312]  eta: 0:07:52  lr: 0.000001  min_lr: 0.000001  loss: 3.3226 (3.2849)  weight_decay: 0.0500 (0.0500)  time: 1.5634  data: 1.1174  max mem: 31830
Epoch: [298]  [ 20/312]  eta: 0:05:28  lr: 0.000001  min_lr: 0.000001  loss: 3.2833 (3.1624)  weight_decay: 0.0500 (0.0500)  time: 0.6367  data: 0.1977  max mem: 31830
Epoch: [298]  [ 30/312]  eta: 0:04:11  lr: 0.000001  min_lr: 0.000001  loss: 3.2336 (3.1791)  weight_decay: 0.0500 (0.0500)  time: 0.5200  data: 0.0931  max mem: 31830
Epoch: [298]  [ 40/312]  eta: 0:03:33  lr: 0.000001  min_lr: 0.000001  loss: 3.2972 (3.2204)  weight_decay: 0.0500 (0.0500)  time: 0.4288  data: 0.0110  max mem: 31830
Epoch: [298]  [ 50/312]  eta: 0:03:13  lr: 0.000001  min_lr: 0.000001  loss: 3.4508 (3.2470)  weight_decay: 0.0500 (0.0500)  time: 0.4998  data: 0.0607  max mem: 31830
Epoch: [298]  [ 60/312]  eta: 0:02:51  lr: 0.000001  min_lr: 0.000001  loss: 3.4485 (3.2129)  weight_decay: 0.0500 (0.0500)  time: 0.4698  data: 0.0508  max mem: 31830
Epoch: [298]  [ 70/312]  eta: 0:02:40  lr: 0.000001  min_lr: 0.000001  loss: 3.1702 (3.1945)  weight_decay: 0.0500 (0.0500)  time: 0.4811  data: 0.0651  max mem: 31830
Epoch: [298]  [ 80/312]  eta: 0:02:30  lr: 0.000001  min_lr: 0.000001  loss: 2.9794 (3.1807)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.1189  max mem: 31830
Epoch: [298]  [ 90/312]  eta: 0:02:20  lr: 0.000001  min_lr: 0.000001  loss: 2.9794 (3.1593)  weight_decay: 0.0500 (0.0500)  time: 0.5130  data: 0.0855  max mem: 31830
Epoch: [298]  [100/312]  eta: 0:02:16  lr: 0.000001  min_lr: 0.000001  loss: 2.8585 (3.1456)  weight_decay: 0.0500 (0.0500)  time: 0.6348  data: 0.1531  max mem: 31830
Epoch: [298]  [110/312]  eta: 0:02:05  lr: 0.000001  min_lr: 0.000001  loss: 2.8806 (3.1412)  weight_decay: 0.0500 (0.0500)  time: 0.5780  data: 0.1224  max mem: 31830
Epoch: [298]  [120/312]  eta: 0:01:58  lr: 0.000001  min_lr: 0.000001  loss: 3.2655 (3.1570)  weight_decay: 0.0500 (0.0500)  time: 0.4864  data: 0.0634  max mem: 31830
Epoch: [298]  [130/312]  eta: 0:01:53  lr: 0.000001  min_lr: 0.000001  loss: 3.4344 (3.1680)  weight_decay: 0.0500 (0.0500)  time: 0.6247  data: 0.1550  max mem: 31830
Epoch: [298]  [140/312]  eta: 0:01:44  lr: 0.000001  min_lr: 0.000001  loss: 3.4327 (3.1793)  weight_decay: 0.0500 (0.0500)  time: 0.5332  data: 0.0923  max mem: 31830
Epoch: [298]  [150/312]  eta: 0:01:37  lr: 0.000001  min_lr: 0.000001  loss: 3.3790 (3.1913)  weight_decay: 0.0500 (0.0500)  time: 0.4870  data: 0.0665  max mem: 31830
Epoch: [298]  [160/312]  eta: 0:01:30  lr: 0.000001  min_lr: 0.000001  loss: 3.3373 (3.1918)  weight_decay: 0.0500 (0.0500)  time: 0.5453  data: 0.0666  max mem: 31830
Epoch: [298]  [170/312]  eta: 0:01:24  lr: 0.000001  min_lr: 0.000001  loss: 3.3084 (3.1899)  weight_decay: 0.0500 (0.0500)  time: 0.5249  data: 0.0751  max mem: 31830
Epoch: [298]  [180/312]  eta: 0:01:18  lr: 0.000001  min_lr: 0.000001  loss: 3.2651 (3.1959)  weight_decay: 0.0500 (0.0500)  time: 0.5797  data: 0.1494  max mem: 31830
Epoch: [298]  [190/312]  eta: 0:01:11  lr: 0.000001  min_lr: 0.000001  loss: 3.3130 (3.1798)  weight_decay: 0.0500 (0.0500)  time: 0.5098  data: 0.0753  max mem: 31830
Epoch: [298]  [200/312]  eta: 0:01:05  lr: 0.000001  min_lr: 0.000001  loss: 3.1693 (3.1743)  weight_decay: 0.0500 (0.0500)  time: 0.5047  data: 0.0667  max mem: 31830
Epoch: [298]  [210/312]  eta: 0:01:00  lr: 0.000001  min_lr: 0.000001  loss: 3.1823 (3.1751)  weight_decay: 0.0500 (0.0500)  time: 0.6403  data: 0.1316  max mem: 31830
Epoch: [298]  [220/312]  eta: 0:00:53  lr: 0.000001  min_lr: 0.000001  loss: 3.1470 (3.1619)  weight_decay: 0.0500 (0.0500)  time: 0.5354  data: 0.0657  max mem: 31830
Epoch: [298]  [230/312]  eta: 0:00:47  lr: 0.000001  min_lr: 0.000001  loss: 3.2071 (3.1615)  weight_decay: 0.0500 (0.0500)  time: 0.4692  data: 0.0354  max mem: 31830
Epoch: [298]  [240/312]  eta: 0:00:41  lr: 0.000001  min_lr: 0.000001  loss: 3.2602 (3.1593)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.0353  max mem: 31830
Epoch: [298]  [250/312]  eta: 0:00:35  lr: 0.000001  min_lr: 0.000001  loss: 2.8900 (3.1460)  weight_decay: 0.0500 (0.0500)  time: 0.5297  data: 0.0688  max mem: 31830
Epoch: [298]  [260/312]  eta: 0:00:30  lr: 0.000001  min_lr: 0.000001  loss: 3.0434 (3.1428)  weight_decay: 0.0500 (0.0500)  time: 0.5831  data: 0.1340  max mem: 31830
Epoch: [298]  [270/312]  eta: 0:00:24  lr: 0.000001  min_lr: 0.000001  loss: 3.3066 (3.1346)  weight_decay: 0.0500 (0.0500)  time: 0.5198  data: 0.0660  max mem: 31830
Epoch: [298]  [280/312]  eta: 0:00:18  lr: 0.000001  min_lr: 0.000001  loss: 3.2753 (3.1391)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0701  max mem: 31830
Epoch: [298]  [290/312]  eta: 0:00:12  lr: 0.000001  min_lr: 0.000001  loss: 3.4056 (3.1430)  weight_decay: 0.0500 (0.0500)  time: 0.5787  data: 0.1119  max mem: 31830
Epoch: [298]  [300/312]  eta: 0:00:06  lr: 0.000001  min_lr: 0.000001  loss: 3.3726 (3.1422)  weight_decay: 0.0500 (0.0500)  time: 0.4565  data: 0.0422  max mem: 31830
Epoch: [298]  [310/312]  eta: 0:00:01  lr: 0.000001  min_lr: 0.000001  loss: 3.1754 (3.1410)  weight_decay: 0.0500 (0.0500)  time: 0.3807  data: 0.0001  max mem: 31830
Epoch: [298]  [311/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 3.1754 (3.1426)  weight_decay: 0.0500 (0.0500)  time: 0.3806  data: 0.0001  max mem: 31830
Epoch: [298] Total time: 0:02:55 (0.5638 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 3.1754 (3.1640)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.8839 (0.8839)  acc1: 85.1562 (85.1562)  acc5: 97.2656 (97.2656)  time: 9.0243  data: 8.8653  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1693 (1.0994)  acc1: 79.1667 (78.3040)  acc5: 95.1823 (94.4960)  time: 1.1243  data: 0.9851  max mem: 31830
Test: Total time: 0:00:10 (1.1592 s / it)
* Acc@1 78.558 Acc@5 94.460 loss 1.097
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.77%
Epoch: [299]  [  0/312]  eta: 1:03:35  lr: 0.000001  min_lr: 0.000001  loss: 3.8244 (3.8244)  weight_decay: 0.0500 (0.0500)  time: 12.2276  data: 10.6378  max mem: 31830
Epoch: [299]  [ 10/312]  eta: 0:08:59  lr: 0.000001  min_lr: 0.000001  loss: 2.8357 (2.8314)  weight_decay: 0.0500 (0.0500)  time: 1.7858  data: 1.0173  max mem: 31830
Epoch: [299]  [ 20/312]  eta: 0:05:30  lr: 0.000001  min_lr: 0.000001  loss: 2.8357 (2.8947)  weight_decay: 0.0500 (0.0500)  time: 0.5783  data: 0.0425  max mem: 31830
Epoch: [299]  [ 30/312]  eta: 0:04:12  lr: 0.000001  min_lr: 0.000001  loss: 3.2879 (2.9666)  weight_decay: 0.0500 (0.0500)  time: 0.4067  data: 0.0152  max mem: 31830
Epoch: [299]  [ 40/312]  eta: 0:03:30  lr: 0.000001  min_lr: 0.000001  loss: 3.2879 (3.0172)  weight_decay: 0.0500 (0.0500)  time: 0.3998  data: 0.0014  max mem: 31830
Epoch: [299]  [ 50/312]  eta: 0:03:03  lr: 0.000001  min_lr: 0.000001  loss: 3.1849 (3.0782)  weight_decay: 0.0500 (0.0500)  time: 0.3983  data: 0.0014  max mem: 31830
Epoch: [299]  [ 60/312]  eta: 0:02:44  lr: 0.000001  min_lr: 0.000001  loss: 3.2322 (3.0899)  weight_decay: 0.0500 (0.0500)  time: 0.3971  data: 0.0009  max mem: 31830
Epoch: [299]  [ 70/312]  eta: 0:02:31  lr: 0.000001  min_lr: 0.000001  loss: 3.2068 (3.1071)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0063  max mem: 31830
Epoch: [299]  [ 80/312]  eta: 0:02:23  lr: 0.000001  min_lr: 0.000001  loss: 3.1821 (3.0977)  weight_decay: 0.0500 (0.0500)  time: 0.5179  data: 0.0115  max mem: 31830
Epoch: [299]  [ 90/312]  eta: 0:02:14  lr: 0.000001  min_lr: 0.000001  loss: 3.0169 (3.0935)  weight_decay: 0.0500 (0.0500)  time: 0.5302  data: 0.0259  max mem: 31830
Epoch: [299]  [100/312]  eta: 0:02:09  lr: 0.000001  min_lr: 0.000001  loss: 3.2413 (3.0996)  weight_decay: 0.0500 (0.0500)  time: 0.5695  data: 0.0497  max mem: 31830
Epoch: [299]  [110/312]  eta: 0:01:59  lr: 0.000001  min_lr: 0.000001  loss: 3.1865 (3.0807)  weight_decay: 0.0500 (0.0500)  time: 0.5418  data: 0.0439  max mem: 31830
Epoch: [299]  [120/312]  eta: 0:01:54  lr: 0.000001  min_lr: 0.000001  loss: 2.9674 (3.0683)  weight_decay: 0.0500 (0.0500)  time: 0.5246  data: 0.0150  max mem: 31830
Epoch: [299]  [130/312]  eta: 0:01:48  lr: 0.000001  min_lr: 0.000001  loss: 3.1583 (3.0841)  weight_decay: 0.0500 (0.0500)  time: 0.5950  data: 0.0166  max mem: 31830
Epoch: [299]  [140/312]  eta: 0:01:40  lr: 0.000001  min_lr: 0.000001  loss: 3.2332 (3.0796)  weight_decay: 0.0500 (0.0500)  time: 0.5121  data: 0.0330  max mem: 31830
Epoch: [299]  [150/312]  eta: 0:01:34  lr: 0.000001  min_lr: 0.000001  loss: 3.3211 (3.1034)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0243  max mem: 31830
Epoch: [299]  [160/312]  eta: 0:01:29  lr: 0.000001  min_lr: 0.000001  loss: 3.4444 (3.1185)  weight_decay: 0.0500 (0.0500)  time: 0.6034  data: 0.0140  max mem: 31830
Epoch: [299]  [170/312]  eta: 0:01:22  lr: 0.000001  min_lr: 0.000001  loss: 3.4262 (3.1396)  weight_decay: 0.0500 (0.0500)  time: 0.5264  data: 0.0132  max mem: 31830
Epoch: [299]  [180/312]  eta: 0:01:16  lr: 0.000001  min_lr: 0.000001  loss: 3.3876 (3.1382)  weight_decay: 0.0500 (0.0500)  time: 0.5307  data: 0.0070  max mem: 31830
Epoch: [299]  [190/312]  eta: 0:01:09  lr: 0.000001  min_lr: 0.000001  loss: 3.3876 (3.1498)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0074  max mem: 31830
Epoch: [299]  [200/312]  eta: 0:01:04  lr: 0.000001  min_lr: 0.000001  loss: 3.5369 (3.1560)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0073  max mem: 31830
Epoch: [299]  [210/312]  eta: 0:00:59  lr: 0.000001  min_lr: 0.000001  loss: 3.3598 (3.1575)  weight_decay: 0.0500 (0.0500)  time: 0.6359  data: 0.0073  max mem: 31830
Epoch: [299]  [220/312]  eta: 0:00:52  lr: 0.000001  min_lr: 0.000001  loss: 3.0498 (3.1564)  weight_decay: 0.0500 (0.0500)  time: 0.5497  data: 0.0268  max mem: 31830
Epoch: [299]  [230/312]  eta: 0:00:46  lr: 0.000001  min_lr: 0.000001  loss: 3.2267 (3.1568)  weight_decay: 0.0500 (0.0500)  time: 0.4935  data: 0.0204  max mem: 31830
Epoch: [299]  [240/312]  eta: 0:00:41  lr: 0.000001  min_lr: 0.000001  loss: 3.2267 (3.1602)  weight_decay: 0.0500 (0.0500)  time: 0.5799  data: 0.0203  max mem: 31830
Epoch: [299]  [250/312]  eta: 0:00:35  lr: 0.000001  min_lr: 0.000001  loss: 3.2062 (3.1613)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0334  max mem: 31830
Epoch: [299]  [260/312]  eta: 0:00:29  lr: 0.000001  min_lr: 0.000001  loss: 3.1227 (3.1567)  weight_decay: 0.0500 (0.0500)  time: 0.5271  data: 0.0140  max mem: 31830
Epoch: [299]  [270/312]  eta: 0:00:23  lr: 0.000001  min_lr: 0.000001  loss: 2.9586 (3.1512)  weight_decay: 0.0500 (0.0500)  time: 0.5347  data: 0.0155  max mem: 31830
Epoch: [299]  [280/312]  eta: 0:00:18  lr: 0.000001  min_lr: 0.000001  loss: 2.9637 (3.1509)  weight_decay: 0.0500 (0.0500)  time: 0.5554  data: 0.0186  max mem: 31830
Epoch: [299]  [290/312]  eta: 0:00:12  lr: 0.000001  min_lr: 0.000001  loss: 3.1386 (3.1504)  weight_decay: 0.0500 (0.0500)  time: 0.6054  data: 0.0087  max mem: 31830
Epoch: [299]  [300/312]  eta: 0:00:06  lr: 0.000001  min_lr: 0.000001  loss: 3.1117 (3.1445)  weight_decay: 0.0500 (0.0500)  time: 0.4842  data: 0.0052  max mem: 31830
Epoch: [299]  [310/312]  eta: 0:00:01  lr: 0.000001  min_lr: 0.000001  loss: 3.0298 (3.1405)  weight_decay: 0.0500 (0.0500)  time: 0.3919  data: 0.0002  max mem: 31830
Epoch: [299]  [311/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 3.0298 (3.1413)  weight_decay: 0.0500 (0.0500)  time: 0.3917  data: 0.0001  max mem: 31830
Epoch: [299] Total time: 0:02:54 (0.5599 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 3.0298 (3.1472)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.8117 (0.8117)  acc1: 85.1562 (85.1562)  acc5: 97.3958 (97.3958)  time: 8.9913  data: 8.8283  max mem: 31830
Test:  [8/9]  eta: 0:00:01  loss: 1.1059 (1.0284)  acc1: 78.9062 (78.5760)  acc5: 94.6615 (94.5600)  time: 1.1171  data: 0.9810  max mem: 31830
Test: Total time: 0:00:10 (1.1295 s / it)
* Acc@1 78.794 Acc@5 94.532 loss 1.025
Accuracy of the model on the 50000 test images: 78.8%
Max accuracy: 78.79%
Training time 15:24:51