| 2026-04-14 11:15:52,796 INFO MainThread:2159522 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': '^(model\\.language_model(?=\\.).*\\.(up_proj|q_proj|v_proj|o_proj|k_proj|gate_proj|down_proj)|(?!(model.visual.merger|model.visual.deepstack_merger_list))model\\.visual(?=\\.).*\\.(qkv|linear_fc1|linear_fc2|attn.proj)|model\\.visual\\.merger(?=\\.).*\\.(linear_fc1|linear_fc2)|model\\.visual\\.deepstack_merger_list(?=\\.).*\\.(linear_fc1|linear_fc2))$', 'exclude_modules': None, 'lora_alpha': 32, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': [], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False, 'lora_dtype': None, 'lorap_lr_ratio': None, 'lorap_emb_lr': 1e-06}}, 'vision_config': {'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '', 'model_type': 'qwen3_vl', 'depth': 24, 'hidden_size': 1024, 'hidden_act': 'gelu_pytorch_tanh', 'intermediate_size': 4096, 'num_heads': 16, 'in_channels': 3, 'patch_size': 16, 'spatial_merge_size': 2, 'temporal_patch_size': 2, 'out_hidden_size': 2560, 'num_position_embeddings': 2304, 'initializer_range': 0.02, 'deepstack_visual_indexes': [5, 11, 17], 'output_attentions': False}, 'text_config': {'vocab_size': 151936, 'max_position_embeddings': 262144, 'hidden_size': 2560, 'intermediate_size': 9728, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'rope_parameters': {'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default', 'rope_theta': 5000000}, 'pad_token_id': 151643, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '', 'bos_token_id': 151643, 'eos_token_id': 151645, 'model_type': 'qwen3_vl_text', 'tie_word_embeddings': True, 'output_attentions': False}, 'image_token_id': 151655, 'video_token_id': 151656, 'vision_start_token_id': 151652, 'vision_end_token_id': 151653, 'tie_word_embeddings': True, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3VLForConditionalGeneration'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct', 'transformers_version': '5.3.0', 'model_type': 'qwen3_vl', 'hidden_size': 2560, 'use_cache': False, 'eos_token_id': 151645, 'bos_token_id': None, 'pad_token_id': 151643, 'output_attentions': False, 'output_dir': '/mnt/data/fangyu/RewardModel/outputs/weights/ar-w3-20260414-111508/v0-20260414-111525', 'per_device_train_batch_size': 16, 'num_train_epochs': 5.0, 'max_steps': -1, 'learning_rate': 1e-05, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_steps': 0.05, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 2, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 5, 'logging_first_step': True, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': '/mnt/data/fangyu/RewardModel/outputs/weights/ar-w3-20260414-111508/v0-20260414-111525', 'project': 'huggingface', 'trackio_space_id': 'trackio', 'eval_strategy': 'steps', 'eval_steps': 2500, 'eval_delay': 0, 'per_device_eval_batch_size': 1, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': 99, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 4, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': 2, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_backend': None, 'ddp_timeout': 18000000, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'warmup_ratio': 0.05, 'logging_dir': '/mnt/data/fangyu/RewardModel/outputs/weights/ar-w3-20260414-111508/v0-20260414-111525/runs', 'local_rank': 0, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None, 'tuner_backend': 'peft', 'vit_gradient_checkpointing': True, 'router_aux_loss_coef': 0.0, 'enable_dft_loss': False, 'enable_channel_loss': False, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'group_by_length': False, 'max_epochs': None, 'aligner_lr': None, 'vit_lr': None, 'use_logits_to_keep': None, 'ds3_gather_for_generation': True, 'resume_only_model': False, 'optimizer': None, 'loss_type': None, 'eval_metric': None, 'callbacks': [], 'early_stop_interval': None, 'eval_use_evalscope': False, 'eval_dataset': [], 'eval_dataset_args': None, 'eval_limit': None, 'eval_generation_config': None, 'extra_eval_args': None, 'tuner_type': 'lora', 'use_galore': False, 'galore_target_modules': None, 'galore_rank': 128, 'galore_update_proj_gap': 50, 'galore_scale': 1.0, 'galore_proj_type': 'std', 'galore_optim_per_parameter': False, 'galore_with_embedding': False, 'galore_quantization': False, 'galore_proj_quant': False, 'galore_proj_bits': 4, 'galore_proj_group_size': 256, 'galore_cos_threshold': 0.4, 'galore_gamma_proj': 2, 'galore_queue_size': 5, 'lisa_activated_layers': 0, 'lisa_step_interval': 20, 'use_flash_ckpt': False} |
