2026-02-25 11:15:18,028 INFO    MainThread:121696 [wandb_setup.py:_flush():81] Current SDK version is 0.22.3
2026-02-25 11:15:18,030 INFO    MainThread:121696 [wandb_setup.py:_flush():81] Configure stats pid to 121696
2026-02-25 11:15:18,031 INFO    MainThread:121696 [wandb_setup.py:_flush():81] Loading settings from /mnt/petrelfs/wangmaonan/.config/wandb/settings
2026-02-25 11:15:18,031 INFO    MainThread:121696 [wandb_setup.py:_flush():81] Loading settings from /mnt/petrelfs/wangmaonan/yuxin/CL_CoTNav/InternVL_cleaned/internvl_chat/wandb/settings
2026-02-25 11:15:18,032 INFO    MainThread:121696 [wandb_setup.py:_flush():81] Loading settings from environment variables
2026-02-25 11:15:18,032 INFO    MainThread:121696 [wandb_init.py:setup_run_log_directory():706] Logging user logs to /mnt/petrelfs/wangmaonan/yuxin/CL_CoTNav/all_log/experiments/a100_dualvit_llm-64_mlp-train-patch-32768-acc1_BEVftFOV_FrontierRGB_PosB__FRONTIER_PIXEL_NUMBER_ONLY/wandb/run-20260225_111518-pg2w7c3p/logs/debug.log
2026-02-25 11:15:18,033 INFO    MainThread:121696 [wandb_init.py:setup_run_log_directory():707] Logging internal logs to /mnt/petrelfs/wangmaonan/yuxin/CL_CoTNav/all_log/experiments/a100_dualvit_llm-64_mlp-train-patch-32768-acc1_BEVftFOV_FrontierRGB_PosB__FRONTIER_PIXEL_NUMBER_ONLY/wandb/run-20260225_111518-pg2w7c3p/logs/debug-internal.log
2026-02-25 11:15:18,034 INFO    MainThread:121696 [wandb_init.py:init():833] calling init triggers
2026-02-25 11:15:18,034 INFO    MainThread:121696 [wandb_init.py:init():838] wandb.init called with sweep_config: {}
config: {'_wandb': {}}
2026-02-25 11:15:18,035 INFO    MainThread:121696 [wandb_init.py:init():881] starting backend
2026-02-25 11:15:18,255 INFO    MainThread:121696 [wandb_init.py:init():884] sending inform_init request
2026-02-25 11:15:18,261 INFO    MainThread:121696 [wandb_init.py:init():892] backend started and connected
2026-02-25 11:15:18,263 INFO    MainThread:121696 [wandb_init.py:init():962] updated telemetry
2026-02-25 11:15:18,290 INFO    MainThread:121696 [wandb_init.py:init():986] communicating run to backend with 90.0 second timeout
2026-02-25 11:15:28,713 INFO    MainThread:121696 [wandb_init.py:init():1033] starting run threads in backend
2026-02-25 11:15:28,992 INFO    MainThread:121696 [wandb_run.py:_console_start():2506] atexit reg
2026-02-25 11:15:28,993 INFO    MainThread:121696 [wandb_run.py:_redirect():2354] redirect: wrap_raw
2026-02-25 11:15:28,993 INFO    MainThread:121696 [wandb_run.py:_redirect():2423] Wrapping output streams.
2026-02-25 11:15:28,994 INFO    MainThread:121696 [wandb_run.py:_redirect():2446] Redirects installed.
2026-02-25 11:15:28,999 INFO    MainThread:121696 [wandb_init.py:init():1073] run started, returning control to user process
2026-02-25 11:15:29,002 INFO    MainThread:121696 [wandb_run.py:_config_callback():1390] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['InternVLChatModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '../pretrained/InternVL3-2B', '_commit_hash': None, '_attn_implementation_internal': None, 'transformers_version': None, 'auto_map': {'AutoConfig': 'configuration_internvl_chat.InternVLChatConfig', 'AutoModel': 'modeling_internvl_chat.InternVLChatModel', 'AutoModelForCausalLM': 'modeling_internvl_chat.InternVLChatModel'}, 'hidden_size': 1536, 'image_fold': None, 'model_type': 'internvl_chat', 'system_message': 'You are an autonomous navigation agent operating in indoor environments. You receive spatial information through position embeddings injected into visual features and text tokens. Use the BEV map, position embeddings, and semantic information to make navigation decisions. When the target object is detected (<target> marker), navigate directly to it. Otherwise, explore frontiers strategically to find the goal object.', 'vision_config': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': True, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['InternVisionModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'OpenGVLab/InternViT-6B-448px-V1-5', 'transformers_version': '4.37.2', '_attn_implementation_autoset': True, 'auto_map': {'AutoConfig': 'configuration_intern_vit.InternVisionConfig', 'AutoModel': 'modeling_intern_vit.InternVisionModel'}, 'capacity_factor': 1.2, 'eval_capacity_factor': 1.4, 'laux_allreduce': 'all_nodes', 'model_type': 'intern_vit_6b', 'moe_coeff_ratio': 0.5, 'moe_intermediate_size': 768, 'moe_output_scale': 4.0, 'noisy_gate_policy': 'RSample_before', 'num_experts': 8, 'num_routed_experts': 4, 'num_shared_experts': 4, 'shared_expert_intermediate_size': 3072, 'use_moe': False, 'use_residual': True, 'use_rts': False, 'use_weighted_residual': False, 'hidden_size': 1024, 'intermediate_size': 4096, 'dropout': 0.0, 'drop_path_rate': 0.0, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'num_channels': 3, 'patch_size': 14, 'image_size': 448, 'initializer_range': 1e-10, 'initializer_factor': 0.1, 'attention_dropout': 0.0, 'layer_norm_eps': 1e-06, 'hidden_act': 'gelu', 'norm_type': 'layer_norm', 'qkv_bias': True, 'qk_normalization': False, 'use_flash_attn': True}, 'llm_config': {'vocab_size': 151677, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 70, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': True, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './pretrained/Qwen2.5-32B-Instruct', 'transformers_version': '4.37.2', '_attn_implementation_autoset': True, 'model_type': 'qwen2', 'moe_config': None, 'rope_scaling': {'factor': 2.0, 'rope_type': 'dynamic', 'type': 'dynamic'}, 'attn_implementation': 'flash_attention_2'}, 'use_backbone_lora': 0, 'use_llm_lora': 64, 'pad2square': False, 'select_layer': -1, 'force_image_size': 448, 'downsample_ratio': 0.5, 'template': 'internvl2_5_nav', 'dynamic_image_size': False, 'use_thumbnail': True, 'ps_version': 'v2', 'min_dynamic_patch': 1, 'max_dynamic_patch': 12, 'num_image_token_bev': 256, 'num_image_token_ego': 32, 'use_pairwise_spatial_encoder': False, 'use_position_embeddings': True, 'dual_text_pos_injection': True, 'bev_image_size': 448, 'vit_bev_freeze': True, 'vit_bev_use_lora': True, 'vit_bev_lora_rank': 64, 'vit_rgb_freeze': True, 'vit_rgb_use_lora': True, 'vit_rgb_lora_rank': 16, 'output_dir': '/mnt/petrelfs/wangmaonan/yuxin/CL_CoTNav/all_log/experiments/a100_dualvit_llm-64_mlp-train-patch-32768-acc1_BEVftFOV_FrontierRGB_PosB__FRONTIER_PIXEL_NUMBER_ONLY', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, '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, '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': 1, 'max_steps': 9300, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'runs/Feb25_11-14-26_SH-IDC1-10-140-37-90', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 0.5, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, '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': None, 'dataloader_num_workers': 2, 'past_index': -1, 'run_name': 'a100_dualvit_llm-64_mlp-train-patch-32768-acc1_BEVftFOV_FrontierRGB_PosB__FRONTIER_PIXEL_NUMBER_ONLY_steps9300_gpus4_acc1', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': 'zero_stage2_config_acc1.json', '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': None, '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': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, '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, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
2026-02-26 19:46:56,115 INFO    wandb-AsyncioManager-main:121696 [service_client.py:_forward_responses():80] Reached EOF.
2026-02-26 19:46:56,116 INFO    wandb-AsyncioManager-main:121696 [mailbox.py:close():137] Closing mailbox, abandoning 1 handles.