| | config: {'text_model_name': '/oss/wangyujia/BIO/construction_finetuning/alpaca/v1-20250609-141541/checkpoint-50-merged', 'protein_model_name': '/nas/shared/kilab/wangyujia/ProtT3/plm_model/esm2-150m', 'qformer_model_name': '/nas/shared/kilab/wangyujia/ProtT3/plm_model/microsoft', 'cache_dir': '/model-weights', 'num_query_tokens': 8, 'train_dataset': '/nas/shared/kilab/wangyujia/ProtT3/data/SwissProtV3/train_set.jsonl', 'valid_dataset': '/nas/shared/kilab/wangyujia/ProtT3/data/SwissProtV3/valid_set.jsonl', 'eval_dataset': True, 'output_dir': './contrastive_outputs', 'num_epochs': 10, 'batch_size': 8, 'learning_rate': 0.0001, 'weight_decay': 0.01, 'warmup_steps': 1000, 'gradient_accumulation_steps': 1, 'temperature': 0.07, 'freeze_protein_model': True, 'freeze_text_model': True, 'protein_weight': 1.0, 'text_weight': 1.0, 'enable_ptm': True, 'ptm_weight': 1.0, 'max_length_protein': 1024, 'max_length_text': 512, 'num_workers': 8, 'logging_steps': 100, 'eval_steps': 500, 'save_steps': 1000, 'save_total_limit': 3, 'fp16': False, 'bf16': False, 'seed': 42, 'use_wandb': True, 'wandb_project': 'protein-llm-contrastive', 'wandb_entity': None, '_wandb': {}} |
| | 2025-08-13 15:33:36,032 INFO MainThread:13510 [wandb_run.py:_config_callback():1380] config_cb None None {'output_dir': './contrastive_outputs', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0001, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './contrastive_outputs/runs/Aug13_15-33-30_dsw-265304-585cc9d768-ckfd7', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 8, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'eval_avg_recall_at_1', 'greater_is_better': True, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'temperature': 0.07, 'freeze_protein_model': True, 'freeze_text_model': True, 'protein_weight': 1.0, 'text_weight': 1.0, 'max_length_protein': 1024, 'max_length_text': 512, 'enable_ptm': True, 'ptm_weight': 1.0} |
