| SYSTEM = '' | |
| accumulative_counts = 1 | |
| batch_size = 16 | |
| betas = ( | |
| 0.9, | |
| 0.999, | |
| ) | |
| custom_hooks = [ | |
| dict( | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.engine.DatasetInfoHook'), | |
| dict( | |
| evaluation_images='https://llava-vl.github.io/static/images/view.jpg', | |
| evaluation_inputs=[ | |
| '请描述一下这张照片', | |
| 'Please describe this picture', | |
| ], | |
| every_n_iters=500, | |
| image_processor=dict( | |
| pretrained_model_name_or_path='openai/clip-vit-large-patch14-336', | |
| trust_remote_code=True, | |
| type='transformers.CLIPImageProcessor.from_pretrained'), | |
| prompt_template='xtuner.utils.PROMPT_TEMPLATE.vicuna', | |
| system='', | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.engine.EvaluateChatHook'), | |
| ] | |
| data_path = './data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json' | |
| dataloader_num_workers = 0 | |
| default_hooks = dict( | |
| checkpoint=dict(interval=1, type='mmengine.hooks.CheckpointHook'), | |
| logger=dict(interval=10, type='mmengine.hooks.LoggerHook'), | |
| param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'), | |
| sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'), | |
| timer=dict(type='mmengine.hooks.IterTimerHook')) | |
| env_cfg = dict( | |
| cudnn_benchmark=False, | |
| dist_cfg=dict(backend='nccl'), | |
| mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) | |
| evaluation_freq = 500 | |
| evaluation_images = 'https://llava-vl.github.io/static/images/view.jpg' | |
| evaluation_inputs = [ | |
| '请描述一下这张照片', | |
| 'Please describe this picture', | |
| ] | |
| image_folder = './data/llava_data/llava_images' | |
| launcher = 'pytorch' | |
| llava_data_root = './data/llava_data/' | |
| llava_dataset = dict( | |
| data_path='./data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json', | |
| dataset_map_fn='xtuner.dataset.map_fns.llava_map_fn', | |
| image_folder='./data/llava_data/llava_images', | |
| max_length=1472, | |
| pad_image_to_square=True, | |
| image_processor=dict( | |
| pretrained_model_name_or_path='openai/clip-vit-large-patch14-336', | |
| trust_remote_code=True, | |
| type='transformers.CLIPImageProcessor.from_pretrained'), | |
| template_map_fn=dict( | |
| template='xtuner.utils.PROMPT_TEMPLATE.vicuna', | |
| type='xtuner.dataset.map_fns.template_map_fn_factory'), | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.dataset.LLaVADataset') | |
| llm_name_or_path = 'lmsys/vicuna-7b-v1.5' | |
| load_from = None | |
| log_level = 'INFO' | |
| lr = 0.0002 | |
| max_epochs = 1 | |
| max_length = 1472 | |
| max_norm = 1 | |
| model = dict( | |
| freeze_llm=True, | |
| freeze_visual_encoder=True, | |
| llm=dict( | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| quantization_config=dict( | |
| bnb_4bit_compute_dtype='torch.float16', | |
| bnb_4bit_quant_type='nf4', | |
| bnb_4bit_use_double_quant=True, | |
| llm_int8_has_fp16_weight=False, | |
| llm_int8_threshold=6.0, | |
| load_in_4bit=True, | |
| load_in_8bit=False, | |
| type='transformers.BitsAndBytesConfig'), | |
| torch_dtype='torch.float16', | |
| trust_remote_code=True, | |
| type='transformers.AutoModelForCausalLM.from_pretrained'), | |
| llm_lora=dict( | |
| bias='none', | |
| lora_alpha=256, | |
| lora_dropout=0.05, | |
| r=512, | |
| task_type='CAUSAL_LM', | |
| type='peft.LoraConfig'), | |
| pretrained_pth= | |
| './work_dirs/llava_vicuna_7b_v15_clip_vit_large_p14_336_e1_gpu8_pretrain/epoch_1.pth', | |
| type='xtuner.model.LLaVAModel', | |
| visual_encoder=dict( | |
| pretrained_model_name_or_path='openai/clip-vit-large-patch14-336', | |
| type='transformers.CLIPVisionModel.from_pretrained'), | |
| visual_encoder_lora=dict( | |
| bias='none', | |
| lora_alpha=16, | |
| lora_dropout=0.05, | |
| r=64, | |
| type='peft.LoraConfig')) | |
| optim_type = 'torch.optim.AdamW' | |
| optim_wrapper = dict( | |
| optimizer=dict( | |
| betas=( | |
| 0.9, | |
| 0.999, | |
| ), | |
| lr=0.0002, | |
| type='torch.optim.AdamW', | |
| weight_decay=0), | |
| type='DeepSpeedOptimWrapper') | |
| param_scheduler = [ | |
| dict( | |
| begin=0, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=0.03, | |
| start_factor=1e-05, | |
| type='mmengine.optim.LinearLR'), | |
| dict( | |
| T_max=1, | |
| begin=0.03, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| eta_min=0.0, | |
| type='mmengine.optim.CosineAnnealingLR'), | |
| ] | |
| pretrained_pth = './work_dirs/llava_vicuna_7b_v15_clip_vit_large_p14_336_e1_gpu8_pretrain/epoch_1.pth' | |
| image_processor = dict( | |
| pretrained_model_name_or_path='openai/clip-vit-large-patch14-336', | |
| trust_remote_code=True, | |
| type='transformers.CLIPImageProcessor.from_pretrained') | |
| prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.vicuna' | |
| randomness = dict(deterministic=False, seed=None) | |
| resume = False | |
| runner_type = 'FlexibleRunner' | |
| strategy = dict( | |
| config=dict( | |
| bf16=dict(enabled=True), | |
| fp16=dict(enabled=False, initial_scale_power=16), | |
| gradient_accumulation_steps='auto', | |
| gradient_clipping='auto', | |
| train_micro_batch_size_per_gpu='auto', | |
| zero_allow_untested_optimizer=True, | |
| zero_force_ds_cpu_optimizer=False, | |
| zero_optimization=dict(overlap_comm=True, stage=2)), | |
| exclude_frozen_parameters=True, | |
| gradient_accumulation_steps=1, | |
| gradient_clipping=1, | |
| train_micro_batch_size_per_gpu=16, | |
| type='xtuner.engine.DeepSpeedStrategy') | |
| tokenizer = dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained') | |
| train_cfg = dict(by_epoch=True, max_epochs=1, val_interval=1) | |
| train_dataloader = dict( | |
| batch_size=16, | |
| collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'), | |
| dataset=dict( | |
| data_path= | |
| './data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json', | |
| dataset_map_fn='xtuner.dataset.map_fns.llava_map_fn', | |
| image_folder='./data/llava_data/llava_images', | |
| max_length=1472, | |
| pad_image_to_square=True, | |
| image_processor=dict( | |
| pretrained_model_name_or_path='openai/clip-vit-large-patch14-336', | |
| trust_remote_code=True, | |
| type='transformers.CLIPImageProcessor.from_pretrained'), | |
| template_map_fn=dict( | |
| template='xtuner.utils.PROMPT_TEMPLATE.vicuna', | |
| type='xtuner.dataset.map_fns.template_map_fn_factory'), | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path='lmsys/vicuna-7b-v1.5', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.dataset.LLaVADataset'), | |
| num_workers=0, | |
| sampler=dict( | |
| length_property='modality_length', | |
| per_device_batch_size=16, | |
| type='xtuner.dataset.samplers.LengthGroupedSampler')) | |
| visual_encoder_name_or_path = 'openai/clip-vit-large-patch14-336' | |
| visualizer = None | |
| warmup_ratio = 0.03 | |
| weight_decay = 0 | |
| work_dir = './work_dirs/llava_vicuna_7b_v15_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune' | |