Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "chicken",
+    "1": "duck",
+    "2": "plant"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "chicken": 0,
+    "duck": 1,
+    "plant": 2
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa596dc538cac5054659c056eeee0c2a30cd447ef327a1011f1e70fecb90f06
+size 166496880

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a50721b779268ab210dcbe5644f085fcef64f98b6d9d1ef22e58b6d63b5f99
+size 330495866

last-checkpoint/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": {
+    "height": 480,
+    "width": 480
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 480,
+    "width": 480
+  }
+}

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc4ee78cd7759ec8ff9674d33f1647ad740f9312009ce8839eba48be5854ab5
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f85bfd04697e193837621bcee517ef411ceb3ff41be8f3db66d9050b657471
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,290 @@
+{
+  "best_metric": 1.0389255285263062,
+  "best_model_checkpoint": "chickens-composite-403232323232-150-epochs-wo-transform-metrics-test/checkpoint-1000",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 66.56904602050781,
+      "learning_rate": 9.999999013039593e-06,
+      "loss": 2.4268,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 112.98941040039062,
+      "learning_rate": 9.99999605215876e-06,
+      "loss": 2.0773,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 557.6592407226562,
+      "learning_rate": 9.99999111735867e-06,
+      "loss": 1.9853,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 98.06645202636719,
+      "learning_rate": 9.999984208641271e-06,
+      "loss": 1.9418,
+      "step": 120
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 48.38751220703125,
+      "learning_rate": 9.999975326009292e-06,
+      "loss": 1.7765,
+      "step": 150
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 149.62818908691406,
+      "learning_rate": 9.999964469466236e-06,
+      "loss": 1.7082,
+      "step": 180
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 52.00157928466797,
+      "learning_rate": 9.999951639016396e-06,
+      "loss": 1.5909,
+      "step": 210
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 84.25818634033203,
+      "learning_rate": 9.99993683466483e-06,
+      "loss": 1.6516,
+      "step": 240
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 74.45547485351562,
+      "learning_rate": 9.999920056417385e-06,
+      "loss": 1.5917,
+      "step": 270
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 76.79074096679688,
+      "learning_rate": 9.999901304280686e-06,
+      "loss": 1.5963,
+      "step": 300
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 75.8291244506836,
+      "learning_rate": 9.999880578262135e-06,
+      "loss": 1.5818,
+      "step": 330
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 100.18952178955078,
+      "learning_rate": 9.999857878369917e-06,
+      "loss": 1.5162,
+      "step": 360
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 46.70471954345703,
+      "learning_rate": 9.999833204612988e-06,
+      "loss": 1.5214,
+      "step": 390
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 32.750648498535156,
+      "learning_rate": 9.999806557001092e-06,
+      "loss": 1.4932,
+      "step": 420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 127.58596801757812,
+      "learning_rate": 9.99977793554475e-06,
+      "loss": 1.4611,
+      "step": 450
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 121.99650573730469,
+      "learning_rate": 9.99974734025526e-06,
+      "loss": 1.3418,
+      "step": 480
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 275.6409606933594,
+      "learning_rate": 9.9997147711447e-06,
+      "loss": 1.3033,
+      "step": 510
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 95.28325653076172,
+      "learning_rate": 9.99968022822593e-06,
+      "loss": 1.3253,
+      "step": 540
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 45.146759033203125,
+      "learning_rate": 9.999643711512586e-06,
+      "loss": 1.2676,
+      "step": 570
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 53.740474700927734,
+      "learning_rate": 9.999605221019082e-06,
+      "loss": 1.3089,
+      "step": 600
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 49.25059127807617,
+      "learning_rate": 9.999564756760616e-06,
+      "loss": 1.2178,
+      "step": 630
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 64.69489288330078,
+      "learning_rate": 9.99952231875316e-06,
+      "loss": 1.1728,
+      "step": 660
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 75.14103698730469,
+      "learning_rate": 9.999477907013473e-06,
+      "loss": 1.2076,
+      "step": 690
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 62.69426345825195,
+      "learning_rate": 9.999431521559081e-06,
+      "loss": 1.2195,
+      "step": 720
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 74.42636108398438,
+      "learning_rate": 9.999383162408303e-06,
+      "loss": 1.1816,
+      "step": 750
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 71.95822143554688,
+      "learning_rate": 9.999332829580227e-06,
+      "loss": 1.1643,
+      "step": 780
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 52.83081817626953,
+      "learning_rate": 9.999280523094724e-06,
+      "loss": 1.2048,
+      "step": 810
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 100.67701721191406,
+      "learning_rate": 9.999226242972445e-06,
+      "loss": 1.0853,
+      "step": 840
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 60.53106689453125,
+      "learning_rate": 9.999169989234815e-06,
+      "loss": 1.1435,
+      "step": 870
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 60.462501525878906,
+      "learning_rate": 9.999111761904046e-06,
+      "loss": 1.1131,
+      "step": 900
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 57.989688873291016,
+      "learning_rate": 9.999051561003124e-06,
+      "loss": 1.1354,
+      "step": 930
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 72.74979400634766,
+      "learning_rate": 9.998989386555815e-06,
+      "loss": 1.0673,
+      "step": 960
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 49.00534439086914,
+      "learning_rate": 9.998925238586666e-06,
+      "loss": 1.0777,
+      "step": 990
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0389255285263062,
+      "eval_map": 0.2068,
+      "eval_map_50": 0.2913,
+      "eval_map_75": 0.2391,
+      "eval_map_chicken": 0.0635,
+      "eval_map_duck": 0.0,
+      "eval_map_large": 0.2388,
+      "eval_map_medium": 0.1388,
+      "eval_map_plant": 0.5568,
+      "eval_map_small": 0.013,
+      "eval_mar_1": 0.0854,
+      "eval_mar_10": 0.2648,
+      "eval_mar_100": 0.2788,
+      "eval_mar_100_chicken": 0.1076,
+      "eval_mar_100_duck": 0.0,
+      "eval_mar_100_plant": 0.7287,
+      "eval_mar_large": 0.2929,
+      "eval_mar_medium": 0.2419,
+      "eval_mar_small": 0.0549,
+      "eval_runtime": 13.4063,
+      "eval_samples_per_second": 14.918,
+      "eval_steps_per_second": 1.865,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 150000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.440231129088e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bef9e1b255cd9de9fc9f57b89c3a6bc4022047f529599034965134990e7809
+size 5368