Yugong09/GeoGuess

1{2  "output_dir": "/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331",3  "overwrite_output_dir": false,4  "do_train": false,5  "do_eval": false,6  "do_predict": false,7  "eval_strategy": "no",8  "prediction_loss_only": false,9  "per_device_train_batch_size": 1,10  "per_device_eval_batch_size": 1,11  "per_gpu_train_batch_size": null,12  "per_gpu_eval_batch_size": null,13  "gradient_accumulation_steps": 8,14  "eval_accumulation_steps": null,15  "eval_delay": 0,16  "torch_empty_cache_steps": null,17  "learning_rate": 1e-06,18  "weight_decay": 0.1,19  "adam_beta1": 0.9,20  "adam_beta2": 0.95,21  "adam_epsilon": 1e-08,22  "max_grad_norm": 1.0,23  "num_train_epochs": 1.0,24  "max_steps": -1,25  "lr_scheduler_type": "cosine",26  "lr_scheduler_kwargs": null,27  "warmup_ratio": 0.0,28  "warmup_steps": 0,29  "log_level": "passive",30  "log_level_replica": "warning",31  "log_on_each_node": true,32  "logging_dir": "/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331/runs",33  "logging_strategy": "steps",34  "logging_first_step": true,35  "logging_steps": 1,36  "logging_nan_inf_filter": true,37  "save_strategy": "steps",38  "save_steps": 30.0,39  "save_total_limit": 3,40  "save_safetensors": true,41  "save_on_each_node": false,42  "save_only_model": false,43  "restore_callback_states_from_checkpoint": false,44  "no_cuda": false,45  "use_cpu": false,46  "use_mps_device": false,47  "seed": 42,48  "data_seed": 42,49  "jit_mode_eval": false,50  "bf16": true,51  "fp16": false,52  "fp16_opt_level": "O1",53  "half_precision_backend": "auto",54  "bf16_full_eval": false,55  "fp16_full_eval": false,56  "tf32": null,57  "local_rank": 0,58  "ddp_backend": null,59  "tpu_num_cores": null,60  "tpu_metrics_debug": false,61  "debug": null,62  "dataloader_drop_last": false,63  "eval_steps": 30.0,64  "dataloader_num_workers": 4,65  "dataloader_prefetch_factor": null,66  "past_index": -1,67  "run_name": "/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331",68  "disable_tqdm": null,69  "remove_unused_columns": false,70  "label_names": null,71  "load_best_model_at_end": false,72  "metric_for_best_model": "loss",73  "greater_is_better": false,74  "ignore_data_skip": false,75  "fsdp": [],76  "fsdp_min_num_params": 0,77  "fsdp_config": null,78  "fsdp_transformer_layer_cls_to_wrap": null,79  "accelerator_config": {80    "dispatch_batches": false81  },82  "parallelism_config": null,83  "deepspeed": {84    "fp16": {85      "enabled": "auto",86      "loss_scale": 0,87      "loss_scale_window": 1000,88      "initial_scale_power": 16,89      "hysteresis": 2,90      "min_loss_scale": 191    },92    "bf16": {93      "enabled": "auto"94    },95    "zero_optimization": {96      "stage": 3,97      "offload_optimizer": {98        "device": "none",99        "pin_memory": true100      },101      "offload_param": {102        "device": "none",103        "pin_memory": true104      },105      "overlap_comm": false,106      "contiguous_gradients": true,107      "sub_group_size": 1000000000.0,108      "reduce_bucket_size": "auto",109      "zero_quantized_weights": false,110      "zero_quantized_gradients": false,111      "stage3_prefetch_bucket_size": "auto",112      "stage3_param_persistence_threshold": "auto",113      "stage3_max_live_parameters": 1000000000.0,114      "stage3_max_reuse_distance": 1000000000.0,115      "stage3_gather_16bit_weights_on_model_save": true116    },117    "gradient_accumulation_steps": "auto",118    "gradient_clipping": "auto",119    "steps_per_print": 2000,120    "train_batch_size": "auto",121    "train_micro_batch_size_per_gpu": "auto",122    "wall_clock_breakdown": false123  },124  "label_smoothing_factor": 0.0,125  "optim": "adamw_torch_fused",126  "optim_args": null,127  "adafactor": false,128  "group_by_length": false,129  "length_column_name": "length",130  "report_to": [131    "tensorboard"132  ],133  "project": "huggingface",134  "trackio_space_id": "trackio",135  "ddp_find_unused_parameters": null,136  "ddp_bucket_cap_mb": null,137  "ddp_broadcast_buffers": null,138  "dataloader_pin_memory": true,139  "dataloader_persistent_workers": false,140  "skip_memory_metrics": true,141  "use_legacy_prediction_loop": false,142  "push_to_hub": false,143  "resume_from_checkpoint": "/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v2-20260408-131844/checkpoint-1230",144  "hub_model_id": null,145  "hub_strategy": "every_save",146  "hub_token": null,147  "hub_private_repo": null,148  "hub_always_push": false,149  "hub_revision": null,150  "gradient_checkpointing": true,151  "gradient_checkpointing_kwargs": null,152  "include_inputs_for_metrics": false,153  "include_for_metrics": [],154  "eval_do_concat_batches": true,155  "fp16_backend": "auto",156  "push_to_hub_model_id": null,157  "push_to_hub_organization": null,158  "push_to_hub_token": null,159  "mp_parameters": "",160  "auto_find_batch_size": false,161  "full_determinism": false,162  "torchdynamo": null,163  "ray_scope": "last",164  "ddp_timeout": 18000000,165  "torch_compile": false,166  "torch_compile_backend": null,167  "torch_compile_mode": null,168  "include_tokens_per_second": false,169  "include_num_input_tokens_seen": false,170  "neftune_noise_alpha": null,171  "optim_target_modules": null,172  "batch_eval_metrics": false,173  "eval_on_start": false,174  "use_liger_kernel": false,175  "liger_kernel_config": null,176  "eval_use_gather_object": false,177  "average_tokens_across_devices": true,178  "sortish_sampler": false,179  "predict_with_generate": false,180  "generation_max_length": null,181  "generation_num_beams": null,182  "generation_config": null,183  "tuner_backend": "peft",184  "vit_gradient_checkpointing": null,185  "router_aux_loss_coef": 0.0,186  "enable_dft_loss": false,187  "enable_channel_loss": false,188  "safe_serialization": true,189  "max_shard_size": "5GB",190  "check_model": true,191  "acc_strategy": "token",192  "train_dataloader_shuffle": true,193  "max_epochs": null,194  "aligner_lr": null,195  "vit_lr": null,196  "use_logits_to_keep": null,197  "ds3_gather_for_generation": true,198  "resume_only_model": false,199  "optimizer": null,200  "loss_type": "grpo",201  "eval_metric": null,202  "callbacks": [],203  "early_stop_interval": null,204  "eval_use_evalscope": false,205  "eval_dataset": [],206  "eval_dataset_args": null,207  "eval_limit": null,208  "eval_generation_config": null,209  "extra_eval_args": null,210  "tuner_type": "full",211  "use_galore": false,212  "galore_target_modules": null,213  "galore_rank": 128,214  "galore_update_proj_gap": 50,215  "galore_scale": 1.0,216  "galore_proj_type": "std",217  "galore_optim_per_parameter": false,218  "galore_with_embedding": false,219  "galore_quantization": false,220  "galore_proj_quant": false,221  "galore_proj_bits": 4,222  "galore_proj_group_size": 256,223  "galore_cos_threshold": 0.4,224  "galore_gamma_proj": 2,225  "galore_queue_size": 5,226  "lisa_activated_layers": 0,227  "lisa_step_interval": 20,228  "use_flash_ckpt": false,229  "use_ray": false,230  "ray_exp_name": null,231  "device_groups": null,232  "model": "/work/nvme/beqq/ytao4/hf_cache/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",233  "model_type": "qwen3_vl",234  "model_revision": null,235  "task_type": "causal_lm",236  "torch_dtype": "bfloat16",237  "attn_impl": null,238  "experts_impl": null,239  "new_special_tokens": [],240  "num_labels": null,241  "problem_type": null,242  "rope_scaling": null,243  "device_map": null,244  "max_memory": {},245  "max_model_len": null,246  "local_repo_path": null,247  "init_strategy": null,248  "template": "qwen3_vl",249  "system": null,250  "max_length": 2048,251  "truncation_strategy": "left",252  "max_pixels": null,253  "agent_template": null,254  "norm_bbox": null,255  "use_chat_template": true,256  "padding_side": "right",257  "padding_free": false,258  "loss_scale": "last_round",259  "sequence_parallel_size": 1,260  "template_backend": "swift",261  "response_prefix": null,262  "enable_thinking": null,263  "add_non_thinking_prefix": true,264  "dataset": [265    "/u/ytao4/geolocation-dev/method/data/mp16-eval-geoclip.jsonl"266  ],267  "val_dataset": [],268  "cached_dataset": [],269  "cached_val_dataset": [],270  "split_dataset_ratio": 0.0,271  "dataset_num_proc": 1,272  "load_from_cache_file": true,273  "dataset_shuffle": true,274  "val_dataset_shuffle": false,275  "streaming": false,276  "interleave_prob": null,277  "stopping_strategy": "first_exhausted",278  "shuffle_buffer_size": 1000,279  "download_mode": "reuse_dataset_if_exists",280  "columns": {},281  "strict": false,282  "model_name": null,283  "model_author": null,284  "custom_dataset_info": [],285  "quant_method": null,286  "quant_bits": null,287  "hqq_axis": null,288  "bnb_4bit_compute_dtype": "bfloat16",289  "bnb_4bit_quant_type": "nf4",290  "bnb_4bit_use_double_quant": true,291  "bnb_4bit_quant_storage": null,292  "max_new_tokens": 2048,293  "temperature": 1.0,294  "top_k": -1,295  "top_p": 1.0,296  "repetition_penalty": 1.0,297  "num_beams": 1,298  "stream": false,299  "stop_words": [],300  "logprobs": false,301  "top_logprobs": null,302  "structured_outputs_regex": null,303  "train_type": null,304  "adapters": [],305  "external_plugins": [306    "/u/ytao4/geolocation-dev/method/geo_reward.py"307  ],308  "custom_register_path": [],309  "model_kwargs": {},310  "load_args": false,311  "load_data_args": false,312  "packing": false,313  "packing_length": null,314  "packing_num_proc": 1,315  "lazy_tokenize": true,316  "use_hf": true,317  "ignore_args_error": false,318  "use_swift_lora": false,319  "freeze_parameters": [320    "model.visual",321    "model.visual.merger",322    "model.visual.deepstack_merger_list"323  ],324  "freeze_parameters_regex": null,325  "freeze_parameters_ratio": 0.0,326  "trainable_parameters": [],327  "trainable_parameters_regex": null,328  "freeze_llm": false,329  "freeze_vit": true,330  "freeze_aligner": true,331  "target_modules": [332    "all-linear"333  ],334  "target_regex": null,335  "target_parameters": null,336  "modules_to_save": [],337  "lora_rank": 8,338  "lora_alpha": 32,339  "lora_dropout": 0.05,340  "lora_bias": "none",341  "lora_dtype": null,342  "lorap_lr_ratio": null,343  "use_rslora": false,344  "use_dora": false,345  "lora_ga_batch_size": 2,346  "lora_ga_iters": 2,347  "lora_ga_max_length": 1024,348  "lora_ga_direction": "ArB2r",349  "lora_ga_scale": "stable",350  "lora_ga_stable_gamma": 16,351  "init_weights": true,352  "fourier_n_frequency": 2000,353  "fourier_scaling": 300.0,354  "boft_block_size": 4,355  "boft_block_num": 0,356  "boft_n_butterfly_factor": 1,357  "boft_dropout": 0.0,358  "vera_rank": 256,359  "vera_projection_prng_key": 0,360  "vera_dropout": 0.0,361  "vera_d_initial": 0.1,362  "adapter_act": "gelu",363  "adapter_length": 128,364  "adalora_target_r": 8,365  "adalora_init_r": 12,366  "adalora_tinit": 0,367  "adalora_tfinal": 0,368  "adalora_deltaT": 1,369  "adalora_beta1": 0.85,370  "adalora_beta2": 0.85,371  "adalora_orth_reg_weight": 0.5,372  "llamapro_num_new_blocks": 4,373  "llamapro_num_groups": null,374  "reft_layer_key": null,375  "reft_layers": null,376  "reft_rank": 4,377  "reft_intervention_type": "LoreftIntervention",378  "reft_args": null,379  "swanlab_token": null,380  "swanlab_project": "ms-swift",381  "swanlab_workspace": null,382  "swanlab_exp_name": null,383  "swanlab_notification_method": null,384  "swanlab_webhook_url": null,385  "swanlab_secret": null,386  "swanlab_sender_email": null,387  "swanlab_receiver_email": null,388  "swanlab_smtp_server": null,389  "swanlab_smtp_port": null,390  "swanlab_email_language": "zh",391  "swanlab_mode": "cloud",392  "add_version": true,393  "create_checkpoint_symlink": false,394  "zero_hpz_partition_size": null,395  "deepspeed_autotp_size": null,396  "reward_model": null,397  "reward_adapters": [],398  "reward_model_type": null,399  "reward_model_revision": null,400  "reward_template": null,401  "num_ppo_epochs": 4,402  "whiten_rewards": false,403  "kl_coef": 0.05,404  "cliprange": 0.2,405  "vf_coef": 0.1,406  "cliprange_value": 0.2,407  "gamma": 1.0,408  "lam": 0.95,409  "num_mini_batches": 1,410  "local_rollout_forward_batch_size": 64,411  "num_sample_generations": 10,412  "response_length": 2048,413  "missing_eos_penalty": null,414  "vllm_gpu_memory_utilization": 0.2,415  "vllm_tensor_parallel_size": 4,416  "vllm_pipeline_parallel_size": 1,417  "vllm_enable_expert_parallel": false,418  "vllm_max_num_seqs": null,419  "vllm_max_model_len": 4096,420  "vllm_disable_custom_all_reduce": true,421  "vllm_enforce_eager": false,422  "vllm_limit_mm_per_prompt": null,423  "vllm_max_lora_rank": 16,424  "vllm_enable_prefix_caching": false,425  "vllm_use_async_engine": null,426  "vllm_quantization": null,427  "vllm_reasoning_parser": null,428  "vllm_disable_cascade_attn": false,429  "vllm_mm_processor_cache_gb": 0.0,430  "vllm_speculative_config": null,431  "vllm_engine_kwargs": {},432  "vllm_data_parallel_size": 1,433  "use_vllm": true,434  "vllm_mode": "colocate",435  "vllm_enable_lora": false,436  "vllm_server_base_url": null,437  "vllm_server_host": null,438  "vllm_server_port": [439    8000440  ],441  "vllm_server_timeout": 240.0,442  "vllm_server_group_port": null,443  "enable_flattened_weight_sync": true,444  "async_generate": false,445  "sleep_level": 1,446  "move_model_batches": null,447  "offload_optimizer": false,448  "offload_model": false,449  "wandb_log_unique_prompts": null,450  "epsilon": 0.2,451  "epsilon_high": 0.28,452  "delta": null,453  "cosine_min_len_value_wrong": -0.5,454  "cosine_max_len_value_wrong": 0.0,455  "cosine_min_len_value_correct": 1.0,456  "cosine_max_len_value_correct": 0.5,457  "cosine_max_len": null,458  "repetition_n_grams": 3,459  "repetition_max_penalty": -1.0,460  "reward_model_plugin": null,461  "chord_sft_dataset": [],462  "chord_sft_per_device_train_batch_size": null,463  "chord_enable_phi_function": false,464  "chord_mu_warmup_steps": null,465  "chord_mu_decay_steps": null,466  "chord_mu_peak": null,467  "chord_mu_valley": null,468  "sync_ref_model": false,469  "ref_model_sync_steps": 512,470  "ref_model_mixup_alpha": 0.6,471  "multi_turn_scheduler": null,472  "max_turns": null,473  "completion_length_limit_scope": "per_round",474  "vllm_server_pass_dataset": false,475  "dynamic_sample": false,476  "max_resample_times": 3,477  "overlong_filter": false,478  "soft_max_length": null,479  "soft_cache_length": null,480  "scale_rewards": "none",481  "log_entropy": false,482  "top_entropy_quantile": 1.0,483  "importance_sampling_level": "token",484  "tau_pos": 1.0,485  "tau_neg": 1.05,486  "advantage_estimator": "grpo",487  "kl_in_reward": false,488  "generation_batch_size": null,489  "steps_per_generation": null,490  "num_generations_eval": null,491  "rollout_importance_sampling_mode": null,492  "rollout_importance_sampling_threshold": 2.0,493  "log_rollout_offpolicy_metrics": false,494  "off_policy_sequence_mask_delta": null,495  "num_generations": 4,496  "reward_funcs": [497    "geo_format_acc",498    "geo_distance_acc"499  ],500  "reward_weights": null,501  "log_completions": true,502  "num_iterations": 1,503  "teacher_model": null,504  "teacher_adapters": [],505  "teacher_model_type": null,506  "teacher_model_revision": null,507  "teacher_deepspeed": null,508  "teacher_model_server": null,509  "rlhf_type": "grpo",510  "ref_model": "/work/nvme/beqq/ytao4/hf_cache/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",511  "ref_adapters": [],512  "ref_model_type": "qwen3_vl",513  "ref_model_revision": null,514  "beta": 0.04,515  "label_smoothing": 0,516  "max_completion_length": 2048,517  "rpo_alpha": null,518  "ld_alpha": null,519  "discopop_tau": 0.05,520  "loss_weights": null,521  "cpo_alpha": 1.0,522  "simpo_gamma": 1,523  "desirable_weight": 1.0,524  "undesirable_weight": 1.0,525  "center_rewards_coefficient": null,526  "sft_alpha": 0,527  "lmbda": 0.5,528  "seq_kd": false,529  "gkd_logits_topk": null,530  "offload_teacher_model": false,531  "swift_version": "4.0.4",532  "ckpt_dir": null,533  "rank": 0,534  "global_world_size": 4,535  "local_world_size": 4,536  "model_suffix": "Qwen3-VL-4B-Instruct",537  "model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/work/nvme/beqq/ytao4/hf_cache/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",538  "model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3VLLoader'>, template='qwen3_vl', model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",539  "model_dir": "/work/nvme/beqq/ytao4/hf_cache/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",540  "template_meta": "QwenTemplateMeta(template_type='qwen3_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')",541  "_val_dataset_exists": false,542  "hub": "<class 'swift.hub.hub.HFHub'>",543  "evaluation_strategy": "steps",544  "training_args": "GRPOConfig(output_dir='/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=30, 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=42, jit_mode_eval=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=True, eval_steps=30.0, dataloader_num_workers=4, dataloader_prefetch_factor=2, past_index=-1, run_name='/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v3-20260412-185331', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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='/u/ytao4/geolocation-dev/method/output/qwen3-vl-4b-geolocation-rl/v2-20260408-131844/checkpoint-1230', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, 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=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, 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=None, model_init_kwargs=None, disable_dropout=False, cast_lm_head_to_fp32=False, num_generations=4, num_generations_eval=None, max_completion_length=2048, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=32, steps_per_generation=8, temperature=1.0, top_p=1.0, top_k=-1, min_p=None, generation_kwargs=None, chat_template_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='colocate', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_structured_outputs_regex=None, vllm_server_base_url=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_group_port=51216, vllm_gpu_memory_utilization=0.2, vllm_max_model_length=None, vllm_tensor_parallel_size=4, beta=0.04, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=0.28, sapo_temperature_neg=1.05, sapo_temperature_pos=1.0, importance_sampling_level='token', reward_weights=None, multi_objective_aggregation='sum_then_normalize', scale_rewards='none', loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, max_tool_calling_iterations=None, vllm_importance_sampling_correction=True, vllm_importance_sampling_mode='sequence_mask', vllm_importance_sampling_cap=3.0, off_policy_mask_threshold=None, use_bias_correction_kl=False, log_completions=True, num_completions_to_print=None, log_unique_prompts=False, log_completions_hub_repo=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=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='full', 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, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=4096, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=16, vllm_enable_prefix_caching=False, vllm_use_async_engine=None, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=0.0, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=None, enable_flattened_weight_sync=True, async_generate=False, structured_outputs_regex=None, sleep_level=1, move_model_batches=None, offload_optimizer=False, offload_model=False, wandb_log_unique_prompts=None, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=2048, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, dataset_shuffle=True, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=False, off_policy_sequence_mask_delta=None)"545}