Add files using upload-large-folder tool

.gitattributes

@@ -42,3 +42,4 @@ qwen2.5vl-7b-thinking_v2_full_cls_grpo/v0-20250912-102404/completions.jsonl filt
 qwen2.5vl-7b-thinking_v2_full_cls_grpo/v0-20250912-102404/checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/completions.jsonl filter=lfs diff=lfs merge=lfs -text
 qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/args.json

@@ -0,0 +1,375 @@
+{
+  "output_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 2,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 2e-06,
+  "weight_decay": 0.0001,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 5.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.1,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": 5,
+  "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,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "tp_size": 0,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "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": "auto",
+      "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": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "swanlab"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "vit_gradient_checkpointing": null,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "optimizer": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "acc_steps": 1,
+  "eval_use_evalscope": false,
+  "eval_datasets": [],
+  "eval_limit": null,
+  "eval_datasets_args": null,
+  "eval_generation_config": null,
+  "model": "/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct",
+  "model_type": "qwen2_5_vl",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5_vl",
+  "system": null,
+  "max_length": 32768,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/ambi_normal_train_thinking_772.json",
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/mma_train_thinking_126.json",
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/sp_train_thinking_102.json"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.1,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_cache": null,
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [
+    "visual",
+    "visual.merger"
+  ],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "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,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "resume_only_model": false,
+  "create_checkpoint_symlink": false,
+  "lazy_tokenize": true,
+  "loss_type": null,
+  "metric": null,
+  "zero_hpz_partition_size": null,
+  "rank": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen2.5-VL-7B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7f8d901c8700>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
+  "model_dir": "/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-06, weight_decay=0.0001, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=5, 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, 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=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=True, metric_for_best_model='eval_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}, tp_size=0, 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), 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': 'auto', '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: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['swanlab'], 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, 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, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', local_repo_path=None, galore_config=None)"
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/args.json

@@ -0,0 +1,375 @@
+{
+  "output_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 2,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 2e-06,
+  "weight_decay": 0.0001,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 5.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.1,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": 5,
+  "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,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "tp_size": 0,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "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": "auto",
+      "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": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "swanlab"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "vit_gradient_checkpointing": null,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "optimizer": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "acc_steps": 1,
+  "eval_use_evalscope": false,
+  "eval_datasets": [],
+  "eval_limit": null,
+  "eval_datasets_args": null,
+  "eval_generation_config": null,
+  "model": "/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct",
+  "model_type": "qwen2_5_vl",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5_vl",
+  "system": null,
+  "max_length": 32768,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/ambi_normal_train_thinking_772.json",
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/mma_train_thinking_126.json",
+    "/mnt/data/users/liamding/data/3AM_Plus/final/training/thinking_v2/sp_train_thinking_102.json"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.1,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_cache": null,
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [
+    "visual",
+    "visual.merger"
+  ],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "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,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "resume_only_model": false,
+  "create_checkpoint_symlink": false,
+  "lazy_tokenize": true,
+  "loss_type": null,
+  "metric": null,
+  "zero_hpz_partition_size": null,
+  "rank": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen2.5-VL-7B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7f8d901c8700>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
+  "model_dir": "/mnt/data/users/liamding/data/models/Qwen2.5-VL-7B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-06, weight_decay=0.0001, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=5, 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, 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=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=True, metric_for_best_model='eval_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}, tp_size=0, 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), 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': 'auto', '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: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['swanlab'], 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, 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, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', local_repo_path=None, galore_config=None)"
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.3"
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/latest

@@ -0,0 +1 @@
+global_step278

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9097d8940842635d7805474309c93e3287cd50c59eebef340e878314cf85a238
+size 4968243304

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe3ae4f81eeaada293ebaccb43c8d83f25c2feb65aee3bfe10295054bc6ac50
+size 4991495816

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5184669f8de999a2865dc374810064148ad1bbef2a8d3bbc184dfd0ccc1a1d
+size 4932751040

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2689341e2dd057530520b0b150bf21df4ff3d64186933ba303777c0ac7662a14
+size 1691924384

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d4ec11f6f0c4379a450e016e2475ddcdb9f98c890cea685430f774510e454c
+size 15365

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ea0f5e1c543bb6e7297ddedb0c2b9f30373216d289e72c7be8799b46ac0a9e
+size 15365

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8b328f7d4f2bb6648f1f263cde446be2b7d71b86a2fe59e904e9c80bd58c4d
+size 15365

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449e8d845f7cbbc2f810921abc3f37f01338b84751e2dcde9f14a53ca2fc564b
+size 15365

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e992dd0fee4e3c06035652b6a642918796d13de583f52aec0ec1a30e35cd2c22
+size 1465

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/trainer_state.json

@@ -0,0 +1,658 @@
+{
+  "best_global_step": 114,
+  "best_metric": 0.7607758,
+  "best_model_checkpoint": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/checkpoint-114",
+  "epoch": 4.920353982300885,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017699115044247787,
+      "grad_norm": 14.321202142330474,
+      "learning_rate": 7.142857142857142e-08,
+      "loss": 1.5010039806365967,
+      "memory(GiB)": 47.49,
+      "step": 1,
+      "token_acc": 0.6500470366886171,
+      "train_speed(iter/s)": 0.038953
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 13.850137512340337,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 1.4922606945037842,
+      "memory(GiB)": 51.25,
+      "step": 5,
+      "token_acc": 0.655378858746492,
+      "train_speed(iter/s)": 0.116713
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 11.085608181041955,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 1.5185029983520508,
+      "memory(GiB)": 51.25,
+      "step": 10,
+      "token_acc": 0.6421171900291356,
+      "train_speed(iter/s)": 0.158895
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 10.099767650091824,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 1.418886947631836,
+      "memory(GiB)": 51.25,
+      "step": 15,
+      "token_acc": 0.6515497553017945,
+      "train_speed(iter/s)": 0.180462
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 7.208261462804431,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.262962818145752,
+      "memory(GiB)": 51.25,
+      "step": 20,
+      "token_acc": 0.68983785519345,
+      "train_speed(iter/s)": 0.194584
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 5.173732261381882,
+      "learning_rate": 1.7857142857142857e-06,
+      "loss": 1.073284912109375,
+      "memory(GiB)": 51.25,
+      "step": 25,
+      "token_acc": 0.7166123778501629,
+      "train_speed(iter/s)": 0.201382
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 4.220378201838244,
+      "learning_rate": 1.999689182000816e-06,
+      "loss": 0.9412189483642578,
+      "memory(GiB)": 51.25,
+      "step": 30,
+      "token_acc": 0.7448033258714423,
+      "train_speed(iter/s)": 0.207482
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 3.7848410629789915,
+      "learning_rate": 1.9961946980917456e-06,
+      "loss": 0.8547769546508789,
+      "memory(GiB)": 51.25,
+      "step": 35,
+      "token_acc": 0.7673329731676571,
+      "train_speed(iter/s)": 0.211653
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 3.162551995799436,
+      "learning_rate": 1.9888308262251284e-06,
+      "loss": 0.8335395812988281,
+      "memory(GiB)": 51.25,
+      "step": 40,
+      "token_acc": 0.7791298549758293,
+      "train_speed(iter/s)": 0.215364
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 3.122148888252451,
+      "learning_rate": 1.9776261689193047e-06,
+      "loss": 0.7813321113586426,
+      "memory(GiB)": 51.25,
+      "step": 45,
+      "token_acc": 0.7778324315461551,
+      "train_speed(iter/s)": 0.217595
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 3.169430208625158,
+      "learning_rate": 1.962624246950012e-06,
+      "loss": 0.8174391746520996,
+      "memory(GiB)": 51.25,
+      "step": 50,
+      "token_acc": 0.7664670658682635,
+      "train_speed(iter/s)": 0.219573
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 3.058314649810024,
+      "learning_rate": 1.9438833303083674e-06,
+      "loss": 0.8344223022460937,
+      "memory(GiB)": 51.25,
+      "step": 55,
+      "token_acc": 0.7612990122717749,
+      "train_speed(iter/s)": 0.220839
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7927725911140442,
+      "eval_runtime": 8.7412,
+      "eval_samples_per_second": 11.326,
+      "eval_steps_per_second": 1.487,
+      "eval_token_acc": 0.7761843225013395,
+      "step": 57
+    },
+    {
+      "epoch": 1.0530973451327434,
+      "grad_norm": 2.9473755467255063,
+      "learning_rate": 1.9214762118704076e-06,
+      "loss": 0.7690113067626954,
+      "memory(GiB)": 51.26,
+      "step": 60,
+      "token_acc": 0.7867647058823529,
+      "train_speed(iter/s)": 0.159233
+    },
+    {
+      "epoch": 1.1415929203539823,
+      "grad_norm": 3.1393710481627326,
+      "learning_rate": 1.895489924657301e-06,
+      "loss": 0.7590018749237061,
+      "memory(GiB)": 51.26,
+      "step": 65,
+      "token_acc": 0.7902051621442753,
+      "train_speed(iter/s)": 0.163536
+    },
+    {
+      "epoch": 1.2300884955752212,
+      "grad_norm": 3.0882270401966663,
+      "learning_rate": 1.8660254037844386e-06,
+      "loss": 0.7359669208526611,
+      "memory(GiB)": 51.26,
+      "step": 70,
+      "token_acc": 0.7988264878457669,
+      "train_speed(iter/s)": 0.166998
+    },
+    {
+      "epoch": 1.3185840707964602,
+      "grad_norm": 3.1483230946693497,
+      "learning_rate": 1.8331970944124488e-06,
+      "loss": 0.7367212295532226,
+      "memory(GiB)": 51.26,
+      "step": 75,
+      "token_acc": 0.7894736842105263,
+      "train_speed(iter/s)": 0.170759
+    },
+    {
+      "epoch": 1.407079646017699,
+      "grad_norm": 2.8606263132357057,
+      "learning_rate": 1.7971325072229223e-06,
+      "loss": 0.7444428443908692,
+      "memory(GiB)": 51.26,
+      "step": 80,
+      "token_acc": 0.7793186614410612,
+      "train_speed(iter/s)": 0.173935
+    },
+    {
+      "epoch": 1.495575221238938,
+      "grad_norm": 3.0859567998343356,
+      "learning_rate": 1.7579717231454529e-06,
+      "loss": 0.7384658336639405,
+      "memory(GiB)": 51.26,
+      "step": 85,
+      "token_acc": 0.7813609010955099,
+      "train_speed(iter/s)": 0.176791
+    },
+    {
+      "epoch": 1.584070796460177,
+      "grad_norm": 3.0792939871724494,
+      "learning_rate": 1.7158668492597184e-06,
+      "loss": 0.7257696151733398,
+      "memory(GiB)": 51.26,
+      "step": 90,
+      "token_acc": 0.7866149369544132,
+      "train_speed(iter/s)": 0.179515
+    },
+    {
+      "epoch": 1.672566371681416,
+      "grad_norm": 3.1625331048332748,
+      "learning_rate": 1.67098142798597e-06,
+      "loss": 0.7048945426940918,
+      "memory(GiB)": 51.26,
+      "step": 95,
+      "token_acc": 0.7972108285479902,
+      "train_speed(iter/s)": 0.182183
+    },
+    {
+      "epoch": 1.7610619469026547,
+      "grad_norm": 2.9509799947159148,
+      "learning_rate": 1.6234898018587336e-06,
+      "loss": 0.7338976860046387,
+      "memory(GiB)": 51.26,
+      "step": 100,
+      "token_acc": 0.7879187984815976,
+      "train_speed(iter/s)": 0.184597
+    },
+    {
+      "epoch": 1.8495575221238938,
+      "grad_norm": 2.8751581715716807,
+      "learning_rate": 1.573576436351046e-06,
+      "loss": 0.7140029907226563,
+      "memory(GiB)": 51.26,
+      "step": 105,
+      "token_acc": 0.8070087189805499,
+      "train_speed(iter/s)": 0.186539
+    },
+    {
+      "epoch": 1.9380530973451329,
+      "grad_norm": 3.150290625878061,
+      "learning_rate": 1.521435203379498e-06,
+      "loss": 0.7308782577514649,
+      "memory(GiB)": 51.26,
+      "step": 110,
+      "token_acc": 0.7966826265389877,
+      "train_speed(iter/s)": 0.188659
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7607758045196533,
+      "eval_runtime": 9.1575,
+      "eval_samples_per_second": 10.811,
+      "eval_steps_per_second": 1.42,
+      "eval_token_acc": 0.7803763356132001,
+      "step": 114
+    },
+    {
+      "epoch": 2.017699115044248,
+      "grad_norm": 3.0635721715867654,
+      "learning_rate": 1.467268628273062e-06,
+      "loss": 0.7074690818786621,
+      "memory(GiB)": 51.26,
+      "step": 115,
+      "token_acc": 0.8036342321219226,
+      "train_speed(iter/s)": 0.162244
+    },
+    {
+      "epoch": 2.106194690265487,
+      "grad_norm": 2.7588304088961544,
+      "learning_rate": 1.4112871031306117e-06,
+      "loss": 0.6462282180786133,
+      "memory(GiB)": 51.26,
+      "step": 120,
+      "token_acc": 0.8059470342264209,
+      "train_speed(iter/s)": 0.164096
+    },
+    {
+      "epoch": 2.1946902654867255,
+      "grad_norm": 2.950192232635502,
+      "learning_rate": 1.3537080696225813e-06,
+      "loss": 0.6533058166503907,
+      "memory(GiB)": 51.26,
+      "step": 125,
+      "token_acc": 0.8170256062404613,
+      "train_speed(iter/s)": 0.166413
+    },
+    {
+      "epoch": 2.2831858407079646,
+      "grad_norm": 3.0591807660314214,
+      "learning_rate": 1.2947551744109043e-06,
+      "loss": 0.6744392871856689,
+      "memory(GiB)": 51.26,
+      "step": 130,
+      "token_acc": 0.8004509582863585,
+      "train_speed(iter/s)": 0.168338
+    },
+    {
+      "epoch": 2.3716814159292037,
+      "grad_norm": 2.8695003359447453,
+      "learning_rate": 1.2346574004677154e-06,
+      "loss": 0.6608050346374512,
+      "memory(GiB)": 51.26,
+      "step": 135,
+      "token_acc": 0.7993735575337949,
+      "train_speed(iter/s)": 0.170109
+    },
+    {
+      "epoch": 2.4601769911504423,
+      "grad_norm": 2.9238312592074687,
+      "learning_rate": 1.1736481776669305e-06,
+      "loss": 0.6362295150756836,
+      "memory(GiB)": 51.26,
+      "step": 140,
+      "token_acc": 0.7953693135496495,
+      "train_speed(iter/s)": 0.171946
+    },
+    {
+      "epoch": 2.5486725663716814,
+      "grad_norm": 3.074846193112176,
+      "learning_rate": 1.1119644761033077e-06,
+      "loss": 0.6545632362365723,
+      "memory(GiB)": 51.26,
+      "step": 145,
+      "token_acc": 0.8076585280168628,
+      "train_speed(iter/s)": 0.173839
+    },
+    {
+      "epoch": 2.6371681415929205,
+      "grad_norm": 2.813724457337761,
+      "learning_rate": 1.0498458856606971e-06,
+      "loss": 0.6306678771972656,
+      "memory(GiB)": 51.26,
+      "step": 150,
+      "token_acc": 0.8082706766917294,
+      "train_speed(iter/s)": 0.175219
+    },
+    {
+      "epoch": 2.725663716814159,
+      "grad_norm": 3.0959475475956024,
+      "learning_rate": 9.875336854045848e-07,
+      "loss": 0.6193599700927734,
+      "memory(GiB)": 51.26,
+      "step": 155,
+      "token_acc": 0.8187106156083374,
+      "train_speed(iter/s)": 0.176829
+    },
+    {
+      "epoch": 2.814159292035398,
+      "grad_norm": 2.9772113141147374,
+      "learning_rate": 9.252699064135758e-07,
+      "loss": 0.6314750194549561,
+      "memory(GiB)": 51.26,
+      "step": 160,
+      "token_acc": 0.8097835068583705,
+      "train_speed(iter/s)": 0.178438
+    },
+    {
+      "epoch": 2.9026548672566372,
+      "grad_norm": 3.0510489009674364,
+      "learning_rate": 8.632963916899268e-07,
+      "loss": 0.6404808044433594,
+      "memory(GiB)": 51.26,
+      "step": 165,
+      "token_acc": 0.8075413751919468,
+      "train_speed(iter/s)": 0.180152
+    },
+    {
+      "epoch": 2.991150442477876,
+      "grad_norm": 2.9648920829040413,
+      "learning_rate": 8.018538568006025e-07,
+      "loss": 0.624687385559082,
+      "memory(GiB)": 51.26,
+      "step": 170,
+      "token_acc": 0.8113074204946996,
+      "train_speed(iter/s)": 0.181543
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7611194252967834,
+      "eval_runtime": 9.2927,
+      "eval_samples_per_second": 10.654,
+      "eval_steps_per_second": 1.399,
+      "eval_token_acc": 0.7798720332839537,
+      "step": 171
+    },
+    {
+      "epoch": 3.0707964601769913,
+      "grad_norm": 2.8610192045624814,
+      "learning_rate": 7.411809548974791e-07,
+      "loss": 0.6192464828491211,
+      "memory(GiB)": 51.26,
+      "step": 175,
+      "token_acc": 0.8229145728643216,
+      "train_speed(iter/s)": 0.162599
+    },
+    {
+      "epoch": 3.15929203539823,
+      "grad_norm": 2.8439605626589968,
+      "learning_rate": 6.815133497483157e-07,
+      "loss": 0.5926939964294433,
+      "memory(GiB)": 51.26,
+      "step": 180,
+      "token_acc": 0.8105864037363778,
+      "train_speed(iter/s)": 0.16401
+    },
+    {
+      "epoch": 3.247787610619469,
+      "grad_norm": 2.7882800524381373,
+      "learning_rate": 6.230828003789947e-07,
+      "loss": 0.5760529518127442,
+      "memory(GiB)": 51.26,
+      "step": 185,
+      "token_acc": 0.8256435974590438,
+      "train_speed(iter/s)": 0.165376
+    },
+    {
+      "epoch": 3.336283185840708,
+      "grad_norm": 2.8647820161040913,
+      "learning_rate": 5.661162608824419e-07,
+      "loss": 0.5923486232757569,
+      "memory(GiB)": 51.26,
+      "step": 190,
+      "token_acc": 0.8314030443414957,
+      "train_speed(iter/s)": 0.166681
+    },
+    {
+      "epoch": 3.4247787610619467,
+      "grad_norm": 2.963477233323649,
+      "learning_rate": 5.10834998890711e-07,
+      "loss": 0.5733409881591797,
+      "memory(GiB)": 51.26,
+      "step": 195,
+      "token_acc": 0.8251090970124203,
+      "train_speed(iter/s)": 0.168077
+    },
+    {
+      "epoch": 3.5132743362831858,
+      "grad_norm": 2.7638694364057983,
+      "learning_rate": 4.5745373613424065e-07,
+      "loss": 0.5825803756713868,
+      "memory(GiB)": 51.26,
+      "step": 200,
+      "token_acc": 0.8090937896070975,
+      "train_speed(iter/s)": 0.169486
+    },
+    {
+      "epoch": 3.601769911504425,
+      "grad_norm": 2.807684977402112,
+      "learning_rate": 4.061798144264985e-07,
+      "loss": 0.5774609565734863,
+      "memory(GiB)": 51.26,
+      "step": 205,
+      "token_acc": 0.830702515177797,
+      "train_speed(iter/s)": 0.170811
+    },
+    {
+      "epoch": 3.6902654867256635,
+      "grad_norm": 2.856686809322862,
+      "learning_rate": 3.5721239031346063e-07,
+      "loss": 0.582278060913086,
+      "memory(GiB)": 51.26,
+      "step": 210,
+      "token_acc": 0.8154953299647834,
+      "train_speed(iter/s)": 0.171798
+    },
+    {
+      "epoch": 3.7787610619469025,
+      "grad_norm": 3.0310016237521586,
+      "learning_rate": 3.1074166151605295e-07,
+      "loss": 0.5766501426696777,
+      "memory(GiB)": 51.26,
+      "step": 215,
+      "token_acc": 0.8216650898770104,
+      "train_speed(iter/s)": 0.17292
+    },
+    {
+      "epoch": 3.8672566371681416,
+      "grad_norm": 2.9950968583230315,
+      "learning_rate": 2.6694812817017387e-07,
+      "loss": 0.5743735313415528,
+      "memory(GiB)": 51.26,
+      "step": 220,
+      "token_acc": 0.8158730158730159,
+      "train_speed(iter/s)": 0.174021
+    },
+    {
+      "epoch": 3.9557522123893807,
+      "grad_norm": 2.758062569924176,
+      "learning_rate": 2.260018917337726e-07,
+      "loss": 0.5766110897064209,
+      "memory(GiB)": 51.26,
+      "step": 225,
+      "token_acc": 0.8224971231300345,
+      "train_speed(iter/s)": 0.17495
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7725582122802734,
+      "eval_runtime": 9.5623,
+      "eval_samples_per_second": 10.353,
+      "eval_steps_per_second": 1.36,
+      "eval_token_acc": 0.778548239669682,
+      "step": 228
+    },
+    {
+      "epoch": 4.035398230088496,
+      "grad_norm": 2.8617766742884445,
+      "learning_rate": 1.880619942841435e-07,
+      "loss": 0.5654587268829345,
+      "memory(GiB)": 51.26,
+      "step": 230,
+      "token_acc": 0.816607634789453,
+      "train_speed(iter/s)": 0.162409
+    },
+    {
+      "epoch": 4.123893805309734,
+      "grad_norm": 2.905182934145488,
+      "learning_rate": 1.5327580077171588e-07,
+      "loss": 0.542338752746582,
+      "memory(GiB)": 51.26,
+      "step": 235,
+      "token_acc": 0.8262200032211306,
+      "train_speed(iter/s)": 0.163561
+    },
+    {
+      "epoch": 4.212389380530974,
+      "grad_norm": 2.924689122435952,
+      "learning_rate": 1.2177842662977133e-07,
+      "loss": 0.5480621337890625,
+      "memory(GiB)": 51.26,
+      "step": 240,
+      "token_acc": 0.8320841970977516,
+      "train_speed(iter/s)": 0.164615
+    },
+    {
+      "epoch": 4.300884955752212,
+      "grad_norm": 2.732849650640299,
+      "learning_rate": 9.369221296335006e-08,
+      "loss": 0.5505722999572754,
+      "memory(GiB)": 51.26,
+      "step": 245,
+      "token_acc": 0.8314749920356802,
+      "train_speed(iter/s)": 0.165798
+    },
+    {
+      "epoch": 4.389380530973451,
+      "grad_norm": 2.854471931540614,
+      "learning_rate": 6.912625135579586e-08,
+      "loss": 0.5473582744598389,
+      "memory(GiB)": 51.26,
+      "step": 250,
+      "token_acc": 0.8420708802874408,
+      "train_speed(iter/s)": 0.166841
+    },
+    {
+      "epoch": 4.477876106194691,
+      "grad_norm": 2.9934648918607416,
+      "learning_rate": 4.817596013867764e-08,
+      "loss": 0.5528162002563477,
+      "memory(GiB)": 51.26,
+      "step": 255,
+      "token_acc": 0.8263268949845805,
+      "train_speed(iter/s)": 0.167786
+    },
+    {
+      "epoch": 4.566371681415929,
+      "grad_norm": 2.8370169229269533,
+      "learning_rate": 3.092271377092215e-08,
+      "loss": 0.5519961833953857,
+      "memory(GiB)": 51.26,
+      "step": 260,
+      "token_acc": 0.8237665269267979,
+      "train_speed(iter/s)": 0.168766
+    },
+    {
+      "epoch": 4.654867256637168,
+      "grad_norm": 2.9449232066148374,
+      "learning_rate": 1.7433526766711725e-08,
+      "loss": 0.5393988609313964,
+      "memory(GiB)": 51.26,
+      "step": 265,
+      "token_acc": 0.8207667731629393,
+      "train_speed(iter/s)": 0.169653
+    },
+    {
+      "epoch": 4.743362831858407,
+      "grad_norm": 3.005898852586366,
+      "learning_rate": 7.760793399827936e-09,
+      "loss": 0.573880958557129,
+      "memory(GiB)": 51.26,
+      "step": 270,
+      "token_acc": 0.8175997373173535,
+      "train_speed(iter/s)": 0.17056
+    },
+    {
+      "epoch": 4.831858407079646,
+      "grad_norm": 2.8671280726864454,
+      "learning_rate": 1.942084195468152e-09,
+      "loss": 0.5792054176330567,
+      "memory(GiB)": 51.26,
+      "step": 275,
+      "token_acc": 0.8213772168077967,
+      "train_speed(iter/s)": 0.171452
+    },
+    {
+      "epoch": 4.920353982300885,
+      "grad_norm": 2.9597071657306118,
+      "learning_rate": 0.0,
+      "loss": 0.571114444732666,
+      "memory(GiB)": 51.26,
+      "step": 280,
+      "token_acc": 0.8273170731707317,
+      "train_speed(iter/s)": 0.172362
+    },
+    {
+      "epoch": 4.920353982300885,
+      "eval_loss": 0.7800883054733276,
+      "eval_runtime": 10.3882,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.251,
+      "eval_token_acc": 0.7776972294890787,
+      "step": 280
+    },
+    {
+      "epoch": 4.920353982300885,
+      "eval_loss": 0.7800883054733276,
+      "eval_runtime": 10.1584,
+      "eval_samples_per_second": 9.746,
+      "eval_steps_per_second": 1.28,
+      "eval_token_acc": 0.7776972294890787,
+      "step": 280
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 43238058737664.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87eb5c72cd096b0464d17098890b1f6a52cab0444cc28284707e33f35fcf8ff9
+size 8849

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/logging.jsonl

@@ -0,0 +1,65 @@
+{"loss": 1.50100398, "token_acc": 0.65004704, "grad_norm": 14.32120214, "learning_rate": 7e-08, "memory(GiB)": 47.49, "train_speed(iter/s)": 0.038953, "epoch": 0.01769912, "global_step/max_steps": "1/280", "percentage": "0.36%", "elapsed_time": "12s", "remaining_time": "56m 24s"}
+{"loss": 1.49226069, "token_acc": 0.65537886, "grad_norm": 13.85013751, "learning_rate": 3.6e-07, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.116713, "epoch": 0.08849558, "global_step/max_steps": "5/280", "percentage": "1.79%", "elapsed_time": "29s", "remaining_time": "26m 51s"}
+{"loss": 1.518503, "token_acc": 0.64211719, "grad_norm": 11.08560818, "learning_rate": 7.1e-07, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.158895, "epoch": 0.17699115, "global_step/max_steps": "10/280", "percentage": "3.57%", "elapsed_time": "49s", "remaining_time": "22m 13s"}
+{"loss": 1.41888695, "token_acc": 0.65154976, "grad_norm": 10.09976765, "learning_rate": 1.07e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.180462, "epoch": 0.26548673, "global_step/max_steps": "15/280", "percentage": "5.36%", "elapsed_time": "1m 9s", "remaining_time": "20m 29s"}
+{"loss": 1.26296282, "token_acc": 0.68983786, "grad_norm": 7.20826146, "learning_rate": 1.43e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.194584, "epoch": 0.3539823, "global_step/max_steps": "20/280", "percentage": "7.14%", "elapsed_time": "1m 29s", "remaining_time": "19m 20s"}
+{"loss": 1.07328491, "token_acc": 0.71661238, "grad_norm": 5.17373226, "learning_rate": 1.79e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.201382, "epoch": 0.44247788, "global_step/max_steps": "25/280", "percentage": "8.93%", "elapsed_time": "1m 50s", "remaining_time": "18m 48s"}
+{"loss": 0.94121895, "token_acc": 0.74480333, "grad_norm": 4.2203782, "learning_rate": 2e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.207482, "epoch": 0.53097345, "global_step/max_steps": "30/280", "percentage": "10.71%", "elapsed_time": "2m 11s", "remaining_time": "18m 12s"}
+{"loss": 0.85477695, "token_acc": 0.76733297, "grad_norm": 3.78484106, "learning_rate": 2e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.211653, "epoch": 0.61946903, "global_step/max_steps": "35/280", "percentage": "12.50%", "elapsed_time": "2m 31s", "remaining_time": "17m 42s"}
+{"loss": 0.83353958, "token_acc": 0.77912985, "grad_norm": 3.162552, "learning_rate": 1.99e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.215364, "epoch": 0.7079646, "global_step/max_steps": "40/280", "percentage": "14.29%", "elapsed_time": "2m 52s", "remaining_time": "17m 13s"}
+{"loss": 0.78133211, "token_acc": 0.77783243, "grad_norm": 3.12214889, "learning_rate": 1.98e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.217595, "epoch": 0.79646018, "global_step/max_steps": "45/280", "percentage": "16.07%", "elapsed_time": "3m 13s", "remaining_time": "16m 49s"}
+{"loss": 0.81743917, "token_acc": 0.76646707, "grad_norm": 3.16943021, "learning_rate": 1.96e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.219573, "epoch": 0.88495575, "global_step/max_steps": "50/280", "percentage": "17.86%", "elapsed_time": "3m 34s", "remaining_time": "16m 25s"}
+{"loss": 0.8344223, "token_acc": 0.76129901, "grad_norm": 3.05831465, "learning_rate": 1.94e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.220839, "epoch": 0.97345133, "global_step/max_steps": "55/280", "percentage": "19.64%", "elapsed_time": "3m 55s", "remaining_time": "16m 3s"}
+{"eval_loss": 0.79277259, "eval_token_acc": 0.77618432, "eval_runtime": 8.7412, "eval_samples_per_second": 11.326, "eval_steps_per_second": 1.487, "epoch": 1.0, "global_step/max_steps": "57/280", "percentage": "20.36%", "elapsed_time": "4m 9s", "remaining_time": "16m 17s"}
+{"loss": 0.76901131, "token_acc": 0.78676471, "grad_norm": 2.94737555, "learning_rate": 1.92e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.159233, "epoch": 1.05309735, "global_step/max_steps": "60/280", "percentage": "21.43%", "elapsed_time": "6m 3s", "remaining_time": "22m 11s"}
+{"loss": 0.75900187, "token_acc": 0.79020516, "grad_norm": 3.13937105, "learning_rate": 1.9e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.163536, "epoch": 1.14159292, "global_step/max_steps": "65/280", "percentage": "23.21%", "elapsed_time": "6m 23s", "remaining_time": "21m 9s"}
+{"loss": 0.73596692, "token_acc": 0.79882649, "grad_norm": 3.08822704, "learning_rate": 1.87e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166998, "epoch": 1.2300885, "global_step/max_steps": "70/280", "percentage": "25.00%", "elapsed_time": "6m 45s", "remaining_time": "20m 16s"}
+{"loss": 0.73672123, "token_acc": 0.78947368, "grad_norm": 3.14832309, "learning_rate": 1.83e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170759, "epoch": 1.31858407, "global_step/max_steps": "75/280", "percentage": "26.79%", "elapsed_time": "7m 5s", "remaining_time": "19m 23s"}
+{"loss": 0.74444284, "token_acc": 0.77931866, "grad_norm": 2.86062631, "learning_rate": 1.8e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.173935, "epoch": 1.40707965, "global_step/max_steps": "80/280", "percentage": "28.57%", "elapsed_time": "7m 26s", "remaining_time": "18m 36s"}
+{"loss": 0.73846583, "token_acc": 0.7813609, "grad_norm": 3.0859568, "learning_rate": 1.76e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.176791, "epoch": 1.49557522, "global_step/max_steps": "85/280", "percentage": "30.36%", "elapsed_time": "7m 47s", "remaining_time": "17m 51s"}
+{"loss": 0.72576962, "token_acc": 0.78661494, "grad_norm": 3.07929399, "learning_rate": 1.72e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.179515, "epoch": 1.5840708, "global_step/max_steps": "90/280", "percentage": "32.14%", "elapsed_time": "8m 7s", "remaining_time": "17m 9s"}
+{"loss": 0.70489454, "token_acc": 0.79721083, "grad_norm": 3.1625331, "learning_rate": 1.67e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.182183, "epoch": 1.67256637, "global_step/max_steps": "95/280", "percentage": "33.93%", "elapsed_time": "8m 27s", "remaining_time": "16m 29s"}
+{"loss": 0.73389769, "token_acc": 0.7879188, "grad_norm": 2.95097999, "learning_rate": 1.62e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.184597, "epoch": 1.76106195, "global_step/max_steps": "100/280", "percentage": "35.71%", "elapsed_time": "8m 48s", "remaining_time": "15m 50s"}
+{"loss": 0.71400299, "token_acc": 0.80700872, "grad_norm": 2.87515817, "learning_rate": 1.57e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.186539, "epoch": 1.84955752, "global_step/max_steps": "105/280", "percentage": "37.50%", "elapsed_time": "9m 9s", "remaining_time": "15m 15s"}
+{"loss": 0.73087826, "token_acc": 0.79668263, "grad_norm": 3.15029063, "learning_rate": 1.52e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.188659, "epoch": 1.9380531, "global_step/max_steps": "110/280", "percentage": "39.29%", "elapsed_time": "9m 29s", "remaining_time": "14m 40s"}
+{"eval_loss": 0.7607758, "eval_token_acc": 0.78037634, "eval_runtime": 9.1575, "eval_samples_per_second": 10.811, "eval_steps_per_second": 1.42, "epoch": 2.0, "global_step/max_steps": "114/280", "percentage": "40.71%", "elapsed_time": "9m 52s", "remaining_time": "14m 23s"}
+{"loss": 0.70746908, "token_acc": 0.80363423, "grad_norm": 3.06357217, "learning_rate": 1.47e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162244, "epoch": 2.01769912, "global_step/max_steps": "115/280", "percentage": "41.07%", "elapsed_time": "11m 35s", "remaining_time": "16m 37s"}
+{"loss": 0.64622822, "token_acc": 0.80594703, "grad_norm": 2.75883041, "learning_rate": 1.41e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.164096, "epoch": 2.10619469, "global_step/max_steps": "120/280", "percentage": "42.86%", "elapsed_time": "11m 57s", "remaining_time": "15m 56s"}
+{"loss": 0.65330582, "token_acc": 0.81702561, "grad_norm": 2.95019223, "learning_rate": 1.35e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166413, "epoch": 2.19469027, "global_step/max_steps": "125/280", "percentage": "44.64%", "elapsed_time": "12m 17s", "remaining_time": "15m 14s"}
+{"loss": 0.67443929, "token_acc": 0.80045096, "grad_norm": 3.05918077, "learning_rate": 1.29e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168338, "epoch": 2.28318584, "global_step/max_steps": "130/280", "percentage": "46.43%", "elapsed_time": "12m 38s", "remaining_time": "14m 35s"}
+{"loss": 0.66080503, "token_acc": 0.79937356, "grad_norm": 2.86950034, "learning_rate": 1.23e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170109, "epoch": 2.37168142, "global_step/max_steps": "135/280", "percentage": "48.21%", "elapsed_time": "13m 0s", "remaining_time": "13m 57s"}
+{"loss": 0.63622952, "token_acc": 0.79536931, "grad_norm": 2.92383126, "learning_rate": 1.17e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171946, "epoch": 2.46017699, "global_step/max_steps": "140/280", "percentage": "50.00%", "elapsed_time": "13m 20s", "remaining_time": "13m 20s"}
+{"loss": 0.65456324, "token_acc": 0.80765853, "grad_norm": 3.07484619, "learning_rate": 1.11e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.173839, "epoch": 2.54867257, "global_step/max_steps": "145/280", "percentage": "51.79%", "elapsed_time": "13m 40s", "remaining_time": "12m 43s"}
+{"loss": 0.63066788, "token_acc": 0.80827068, "grad_norm": 2.81372446, "learning_rate": 1.05e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.175219, "epoch": 2.63716814, "global_step/max_steps": "150/280", "percentage": "53.57%", "elapsed_time": "14m 2s", "remaining_time": "12m 10s"}
+{"loss": 0.61935997, "token_acc": 0.81871062, "grad_norm": 3.09594755, "learning_rate": 9.9e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.176829, "epoch": 2.72566372, "global_step/max_steps": "155/280", "percentage": "55.36%", "elapsed_time": "14m 23s", "remaining_time": "11m 35s"}
+{"loss": 0.63147502, "token_acc": 0.80978351, "grad_norm": 2.97721131, "learning_rate": 9.3e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.178438, "epoch": 2.81415929, "global_step/max_steps": "160/280", "percentage": "57.14%", "elapsed_time": "14m 43s", "remaining_time": "11m 2s"}
+{"loss": 0.6404808, "token_acc": 0.80754138, "grad_norm": 3.0510489, "learning_rate": 8.6e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.180152, "epoch": 2.90265487, "global_step/max_steps": "165/280", "percentage": "58.93%", "elapsed_time": "15m 2s", "remaining_time": "10m 28s"}
+{"loss": 0.62468739, "token_acc": 0.81130742, "grad_norm": 2.96489208, "learning_rate": 8e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.181543, "epoch": 2.99115044, "global_step/max_steps": "170/280", "percentage": "60.71%", "elapsed_time": "15m 22s", "remaining_time": "9m 57s"}
+{"eval_loss": 0.76111943, "eval_token_acc": 0.77987203, "eval_runtime": 9.2927, "eval_samples_per_second": 10.654, "eval_steps_per_second": 1.399, "epoch": 3.0, "global_step/max_steps": "171/280", "percentage": "61.07%", "elapsed_time": "15m 33s", "remaining_time": "9m 55s"}
+{"loss": 0.61924648, "token_acc": 0.82291457, "grad_norm": 2.8610192, "learning_rate": 7.4e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162599, "epoch": 3.07079646, "global_step/max_steps": "175/280", "percentage": "62.50%", "elapsed_time": "17m 42s", "remaining_time": "10m 37s"}
+{"loss": 0.592694, "token_acc": 0.8105864, "grad_norm": 2.84396056, "learning_rate": 6.8e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.16401, "epoch": 3.15929204, "global_step/max_steps": "180/280", "percentage": "64.29%", "elapsed_time": "18m 3s", "remaining_time": "10m 2s"}
+{"loss": 0.57605295, "token_acc": 0.8256436, "grad_norm": 2.78828005, "learning_rate": 6.2e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.165376, "epoch": 3.24778761, "global_step/max_steps": "185/280", "percentage": "66.07%", "elapsed_time": "18m 25s", "remaining_time": "9m 27s"}
+{"loss": 0.59234862, "token_acc": 0.83140304, "grad_norm": 2.86478202, "learning_rate": 5.7e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166681, "epoch": 3.33628319, "global_step/max_steps": "190/280", "percentage": "67.86%", "elapsed_time": "18m 46s", "remaining_time": "8m 53s"}
+{"loss": 0.57334099, "token_acc": 0.8251091, "grad_norm": 2.96347723, "learning_rate": 5.1e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168077, "epoch": 3.42477876, "global_step/max_steps": "195/280", "percentage": "69.64%", "elapsed_time": "19m 6s", "remaining_time": "8m 19s"}
+{"loss": 0.58258038, "token_acc": 0.80909379, "grad_norm": 2.76386944, "learning_rate": 4.6e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.169486, "epoch": 3.51327434, "global_step/max_steps": "200/280", "percentage": "71.43%", "elapsed_time": "19m 26s", "remaining_time": "7m 46s"}
+{"loss": 0.57746096, "token_acc": 0.83070252, "grad_norm": 2.80768498, "learning_rate": 4.1e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170811, "epoch": 3.60176991, "global_step/max_steps": "205/280", "percentage": "73.21%", "elapsed_time": "19m 46s", "remaining_time": "7m 14s"}
+{"loss": 0.58227806, "token_acc": 0.81549533, "grad_norm": 2.85668681, "learning_rate": 3.6e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171798, "epoch": 3.69026549, "global_step/max_steps": "210/280", "percentage": "75.00%", "elapsed_time": "20m 8s", "remaining_time": "6m 42s"}
+{"loss": 0.57665014, "token_acc": 0.82166509, "grad_norm": 3.03100162, "learning_rate": 3.1e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17292, "epoch": 3.77876106, "global_step/max_steps": "215/280", "percentage": "76.79%", "elapsed_time": "20m 29s", "remaining_time": "6m 11s"}
+{"loss": 0.57437353, "token_acc": 0.81587302, "grad_norm": 2.99509686, "learning_rate": 2.7e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.174021, "epoch": 3.86725664, "global_step/max_steps": "220/280", "percentage": "78.57%", "elapsed_time": "20m 50s", "remaining_time": "5m 41s"}
+{"loss": 0.57661109, "token_acc": 0.82249712, "grad_norm": 2.75806257, "learning_rate": 2.3e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17495, "epoch": 3.95575221, "global_step/max_steps": "225/280", "percentage": "80.36%", "elapsed_time": "21m 12s", "remaining_time": "5m 11s"}
+{"eval_loss": 0.77255821, "eval_token_acc": 0.77854824, "eval_runtime": 9.5623, "eval_samples_per_second": 10.353, "eval_steps_per_second": 1.36, "epoch": 4.0, "global_step/max_steps": "228/280", "percentage": "81.43%", "elapsed_time": "21m 31s", "remaining_time": "4m 54s"}
+{"loss": 0.56545873, "token_acc": 0.81660763, "grad_norm": 2.86177667, "learning_rate": 1.9e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162409, "epoch": 4.03539823, "global_step/max_steps": "230/280", "percentage": "82.14%", "elapsed_time": "23m 22s", "remaining_time": "5m 4s"}
+{"loss": 0.54233875, "token_acc": 0.82622, "grad_norm": 2.90518293, "learning_rate": 1.5e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.163561, "epoch": 4.12389381, "global_step/max_steps": "235/280", "percentage": "83.93%", "elapsed_time": "23m 43s", "remaining_time": "4m 32s"}
+{"loss": 0.54806213, "token_acc": 0.8320842, "grad_norm": 2.92468912, "learning_rate": 1.2e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.164615, "epoch": 4.21238938, "global_step/max_steps": "240/280", "percentage": "85.71%", "elapsed_time": "24m 4s", "remaining_time": "4m 0s"}
+{"loss": 0.5505723, "token_acc": 0.83147499, "grad_norm": 2.73284965, "learning_rate": 9e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.165798, "epoch": 4.30088496, "global_step/max_steps": "245/280", "percentage": "87.50%", "elapsed_time": "24m 24s", "remaining_time": "3m 29s"}
+{"loss": 0.54735827, "token_acc": 0.84207088, "grad_norm": 2.85447193, "learning_rate": 7e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166841, "epoch": 4.38938053, "global_step/max_steps": "250/280", "percentage": "89.29%", "elapsed_time": "24m 44s", "remaining_time": "2m 58s"}
+{"loss": 0.5528162, "token_acc": 0.82632689, "grad_norm": 2.99346489, "learning_rate": 5e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.167786, "epoch": 4.47787611, "global_step/max_steps": "255/280", "percentage": "91.07%", "elapsed_time": "25m 6s", "remaining_time": "2m 27s"}
+{"loss": 0.55199618, "token_acc": 0.82376653, "grad_norm": 2.83701692, "learning_rate": 3e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168766, "epoch": 4.56637168, "global_step/max_steps": "260/280", "percentage": "92.86%", "elapsed_time": "25m 27s", "remaining_time": "1m 57s"}
+{"loss": 0.53939886, "token_acc": 0.82076677, "grad_norm": 2.94492321, "learning_rate": 2e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.169653, "epoch": 4.65486726, "global_step/max_steps": "265/280", "percentage": "94.64%", "elapsed_time": "25m 48s", "remaining_time": "1m 27s"}
+{"loss": 0.57388096, "token_acc": 0.81759974, "grad_norm": 3.00589885, "learning_rate": 1e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17056, "epoch": 4.74336283, "global_step/max_steps": "270/280", "percentage": "96.43%", "elapsed_time": "26m 9s", "remaining_time": "58s"}
+{"loss": 0.57920542, "token_acc": 0.82137722, "grad_norm": 2.86712807, "learning_rate": 0.0, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171452, "epoch": 4.83185841, "global_step/max_steps": "275/280", "percentage": "98.21%", "elapsed_time": "26m 30s", "remaining_time": "28s"}
+{"loss": 0.57111444, "token_acc": 0.82731707, "grad_norm": 2.95970717, "learning_rate": 0.0, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.172362, "epoch": 4.92035398, "global_step/max_steps": "280/280", "percentage": "100.00%", "elapsed_time": "26m 50s", "remaining_time": "0s"}
+{"eval_loss": 0.78008831, "eval_token_acc": 0.77769723, "eval_runtime": 10.3882, "eval_samples_per_second": 9.53, "eval_steps_per_second": 1.251, "epoch": 4.92035398, "global_step/max_steps": "280/280", "percentage": "100.00%", "elapsed_time": "27m 1s", "remaining_time": "0s"}
+{"eval_loss": 0.78008831, "eval_token_acc": 0.77769723, "eval_runtime": 10.1584, "eval_samples_per_second": 9.746, "eval_steps_per_second": 1.28, "epoch": 4.92035398, "global_step/max_steps": "280/280", "percentage": "100.00%", "elapsed_time": "28m 55s", "remaining_time": "0s"}
+{"train_runtime": 1921.6184, "train_samples_per_second": 2.344, "train_steps_per_second": 0.146, "total_flos": 43238058737664.0, "train_loss": 0.71873178, "epoch": 4.92035398, "global_step/max_steps": "280/280", "percentage": "100.00%", "elapsed_time": "31m 54s", "remaining_time": "0s"}
+{"model_parameter_info": "Qwen2_5_VLForConditionalGeneration: 8292.1667M Params (7615.6165M Trainable [91.8411%]), 0.0019M Buffers.", "last_model_checkpoint": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/checkpoint-280", "best_model_checkpoint": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_full_v2/v0-20250813-193210/checkpoint-114", "best_metric": 0.7607758, "global_step": 280, "log_history": [{"loss": 1.5010039806365967, "token_acc": 0.6500470366886171, "grad_norm": 14.321202142330474, "learning_rate": 7.142857142857142e-08, "memory(GiB)": 47.49, "train_speed(iter/s)": 0.038953, "epoch": 0.017699115044247787, "step": 1}, {"loss": 1.4922606945037842, "token_acc": 0.655378858746492, "grad_norm": 13.850137512340337, "learning_rate": 3.5714285714285716e-07, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.116713, "epoch": 0.08849557522123894, "step": 5}, {"loss": 1.5185029983520508, "token_acc": 0.6421171900291356, "grad_norm": 11.085608181041955, "learning_rate": 7.142857142857143e-07, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.158895, "epoch": 0.17699115044247787, "step": 10}, {"loss": 1.418886947631836, "token_acc": 0.6515497553017945, "grad_norm": 10.099767650091824, "learning_rate": 1.0714285714285714e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.180462, "epoch": 0.26548672566371684, "step": 15}, {"loss": 1.262962818145752, "token_acc": 0.68983785519345, "grad_norm": 7.208261462804431, "learning_rate": 1.4285714285714286e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.194584, "epoch": 0.35398230088495575, "step": 20}, {"loss": 1.073284912109375, "token_acc": 0.7166123778501629, "grad_norm": 5.173732261381882, "learning_rate": 1.7857142857142857e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.201382, "epoch": 0.4424778761061947, "step": 25}, {"loss": 0.9412189483642578, "token_acc": 0.7448033258714423, "grad_norm": 4.220378201838244, "learning_rate": 1.999689182000816e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.207482, "epoch": 0.5309734513274337, "step": 30}, {"loss": 0.8547769546508789, "token_acc": 0.7673329731676571, "grad_norm": 3.7848410629789915, "learning_rate": 1.9961946980917456e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.211653, "epoch": 0.6194690265486725, "step": 35}, {"loss": 0.8335395812988281, "token_acc": 0.7791298549758293, "grad_norm": 3.162551995799436, "learning_rate": 1.9888308262251284e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.215364, "epoch": 0.7079646017699115, "step": 40}, {"loss": 0.7813321113586426, "token_acc": 0.7778324315461551, "grad_norm": 3.122148888252451, "learning_rate": 1.9776261689193047e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.217595, "epoch": 0.7964601769911505, "step": 45}, {"loss": 0.8174391746520996, "token_acc": 0.7664670658682635, "grad_norm": 3.169430208625158, "learning_rate": 1.962624246950012e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.219573, "epoch": 0.8849557522123894, "step": 50}, {"loss": 0.8344223022460937, "token_acc": 0.7612990122717749, "grad_norm": 3.058314649810024, "learning_rate": 1.9438833303083674e-06, "memory(GiB)": 51.25, "train_speed(iter/s)": 0.220839, "epoch": 0.9734513274336283, "step": 55}, {"eval_loss": 0.7927725911140442, "eval_token_acc": 0.7761843225013395, "eval_runtime": 8.7412, "eval_samples_per_second": 11.326, "eval_steps_per_second": 1.487, "epoch": 1.0, "step": 57}, {"loss": 0.7690113067626954, "token_acc": 0.7867647058823529, "grad_norm": 2.9473755467255063, "learning_rate": 1.9214762118704076e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.159233, "epoch": 1.0530973451327434, "step": 60}, {"loss": 0.7590018749237061, "token_acc": 0.7902051621442753, "grad_norm": 3.1393710481627326, "learning_rate": 1.895489924657301e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.163536, "epoch": 1.1415929203539823, "step": 65}, {"loss": 0.7359669208526611, "token_acc": 0.7988264878457669, "grad_norm": 3.0882270401966663, "learning_rate": 1.8660254037844386e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166998, "epoch": 1.2300884955752212, "step": 70}, {"loss": 0.7367212295532226, "token_acc": 0.7894736842105263, "grad_norm": 3.1483230946693497, "learning_rate": 1.8331970944124488e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170759, "epoch": 1.3185840707964602, "step": 75}, {"loss": 0.7444428443908692, "token_acc": 0.7793186614410612, "grad_norm": 2.8606263132357057, "learning_rate": 1.7971325072229223e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.173935, "epoch": 1.407079646017699, "step": 80}, {"loss": 0.7384658336639405, "token_acc": 0.7813609010955099, "grad_norm": 3.0859567998343356, "learning_rate": 1.7579717231454529e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.176791, "epoch": 1.495575221238938, "step": 85}, {"loss": 0.7257696151733398, "token_acc": 0.7866149369544132, "grad_norm": 3.0792939871724494, "learning_rate": 1.7158668492597184e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.179515, "epoch": 1.584070796460177, "step": 90}, {"loss": 0.7048945426940918, "token_acc": 0.7972108285479902, "grad_norm": 3.1625331048332748, "learning_rate": 1.67098142798597e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.182183, "epoch": 1.672566371681416, "step": 95}, {"loss": 0.7338976860046387, "token_acc": 0.7879187984815976, "grad_norm": 2.9509799947159148, "learning_rate": 1.6234898018587336e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.184597, "epoch": 1.7610619469026547, "step": 100}, {"loss": 0.7140029907226563, "token_acc": 0.8070087189805499, "grad_norm": 2.8751581715716807, "learning_rate": 1.573576436351046e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.186539, "epoch": 1.8495575221238938, "step": 105}, {"loss": 0.7308782577514649, "token_acc": 0.7966826265389877, "grad_norm": 3.150290625878061, "learning_rate": 1.521435203379498e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.188659, "epoch": 1.9380530973451329, "step": 110}, {"eval_loss": 0.7607758045196533, "eval_token_acc": 0.7803763356132001, "eval_runtime": 9.1575, "eval_samples_per_second": 10.811, "eval_steps_per_second": 1.42, "epoch": 2.0, "step": 114}, {"loss": 0.7074690818786621, "token_acc": 0.8036342321219226, "grad_norm": 3.0635721715867654, "learning_rate": 1.467268628273062e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162244, "epoch": 2.017699115044248, "step": 115}, {"loss": 0.6462282180786133, "token_acc": 0.8059470342264209, "grad_norm": 2.7588304088961544, "learning_rate": 1.4112871031306117e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.164096, "epoch": 2.106194690265487, "step": 120}, {"loss": 0.6533058166503907, "token_acc": 0.8170256062404613, "grad_norm": 2.950192232635502, "learning_rate": 1.3537080696225813e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166413, "epoch": 2.1946902654867255, "step": 125}, {"loss": 0.6744392871856689, "token_acc": 0.8004509582863585, "grad_norm": 3.0591807660314214, "learning_rate": 1.2947551744109043e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168338, "epoch": 2.2831858407079646, "step": 130}, {"loss": 0.6608050346374512, "token_acc": 0.7993735575337949, "grad_norm": 2.8695003359447453, "learning_rate": 1.2346574004677154e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170109, "epoch": 2.3716814159292037, "step": 135}, {"loss": 0.6362295150756836, "token_acc": 0.7953693135496495, "grad_norm": 2.9238312592074687, "learning_rate": 1.1736481776669305e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171946, "epoch": 2.4601769911504423, "step": 140}, {"loss": 0.6545632362365723, "token_acc": 0.8076585280168628, "grad_norm": 3.074846193112176, "learning_rate": 1.1119644761033077e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.173839, "epoch": 2.5486725663716814, "step": 145}, {"loss": 0.6306678771972656, "token_acc": 0.8082706766917294, "grad_norm": 2.813724457337761, "learning_rate": 1.0498458856606971e-06, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.175219, "epoch": 2.6371681415929205, "step": 150}, {"loss": 0.6193599700927734, "token_acc": 0.8187106156083374, "grad_norm": 3.0959475475956024, "learning_rate": 9.875336854045848e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.176829, "epoch": 2.725663716814159, "step": 155}, {"loss": 0.6314750194549561, "token_acc": 0.8097835068583705, "grad_norm": 2.9772113141147374, "learning_rate": 9.252699064135758e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.178438, "epoch": 2.814159292035398, "step": 160}, {"loss": 0.6404808044433594, "token_acc": 0.8075413751919468, "grad_norm": 3.0510489009674364, "learning_rate": 8.632963916899268e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.180152, "epoch": 2.9026548672566372, "step": 165}, {"loss": 0.624687385559082, "token_acc": 0.8113074204946996, "grad_norm": 2.9648920829040413, "learning_rate": 8.018538568006025e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.181543, "epoch": 2.991150442477876, "step": 170}, {"eval_loss": 0.7611194252967834, "eval_token_acc": 0.7798720332839537, "eval_runtime": 9.2927, "eval_samples_per_second": 10.654, "eval_steps_per_second": 1.399, "epoch": 3.0, "step": 171}, {"loss": 0.6192464828491211, "token_acc": 0.8229145728643216, "grad_norm": 2.8610192045624814, "learning_rate": 7.411809548974791e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162599, "epoch": 3.0707964601769913, "step": 175}, {"loss": 0.5926939964294433, "token_acc": 0.8105864037363778, "grad_norm": 2.8439605626589968, "learning_rate": 6.815133497483157e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.16401, "epoch": 3.15929203539823, "step": 180}, {"loss": 0.5760529518127442, "token_acc": 0.8256435974590438, "grad_norm": 2.7882800524381373, "learning_rate": 6.230828003789947e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.165376, "epoch": 3.247787610619469, "step": 185}, {"loss": 0.5923486232757569, "token_acc": 0.8314030443414957, "grad_norm": 2.8647820161040913, "learning_rate": 5.661162608824419e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166681, "epoch": 3.336283185840708, "step": 190}, {"loss": 0.5733409881591797, "token_acc": 0.8251090970124203, "grad_norm": 2.963477233323649, "learning_rate": 5.10834998890711e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168077, "epoch": 3.4247787610619467, "step": 195}, {"loss": 0.5825803756713868, "token_acc": 0.8090937896070975, "grad_norm": 2.7638694364057983, "learning_rate": 4.5745373613424065e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.169486, "epoch": 3.5132743362831858, "step": 200}, {"loss": 0.5774609565734863, "token_acc": 0.830702515177797, "grad_norm": 2.807684977402112, "learning_rate": 4.061798144264985e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.170811, "epoch": 3.601769911504425, "step": 205}, {"loss": 0.582278060913086, "token_acc": 0.8154953299647834, "grad_norm": 2.856686809322862, "learning_rate": 3.5721239031346063e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171798, "epoch": 3.6902654867256635, "step": 210}, {"loss": 0.5766501426696777, "token_acc": 0.8216650898770104, "grad_norm": 3.0310016237521586, "learning_rate": 3.1074166151605295e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17292, "epoch": 3.7787610619469025, "step": 215}, {"loss": 0.5743735313415528, "token_acc": 0.8158730158730159, "grad_norm": 2.9950968583230315, "learning_rate": 2.6694812817017387e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.174021, "epoch": 3.8672566371681416, "step": 220}, {"loss": 0.5766110897064209, "token_acc": 0.8224971231300345, "grad_norm": 2.758062569924176, "learning_rate": 2.260018917337726e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17495, "epoch": 3.9557522123893807, "step": 225}, {"eval_loss": 0.7725582122802734, "eval_token_acc": 0.778548239669682, "eval_runtime": 9.5623, "eval_samples_per_second": 10.353, "eval_steps_per_second": 1.36, "epoch": 4.0, "step": 228}, {"loss": 0.5654587268829345, "token_acc": 0.816607634789453, "grad_norm": 2.8617766742884445, "learning_rate": 1.880619942841435e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.162409, "epoch": 4.035398230088496, "step": 230}, {"loss": 0.542338752746582, "token_acc": 0.8262200032211306, "grad_norm": 2.905182934145488, "learning_rate": 1.5327580077171588e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.163561, "epoch": 4.123893805309734, "step": 235}, {"loss": 0.5480621337890625, "token_acc": 0.8320841970977516, "grad_norm": 2.924689122435952, "learning_rate": 1.2177842662977133e-07, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.164615, "epoch": 4.212389380530974, "step": 240}, {"loss": 0.5505722999572754, "token_acc": 0.8314749920356802, "grad_norm": 2.732849650640299, "learning_rate": 9.369221296335006e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.165798, "epoch": 4.300884955752212, "step": 245}, {"loss": 0.5473582744598389, "token_acc": 0.8420708802874408, "grad_norm": 2.854471931540614, "learning_rate": 6.912625135579586e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.166841, "epoch": 4.389380530973451, "step": 250}, {"loss": 0.5528162002563477, "token_acc": 0.8263268949845805, "grad_norm": 2.9934648918607416, "learning_rate": 4.817596013867764e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.167786, "epoch": 4.477876106194691, "step": 255}, {"loss": 0.5519961833953857, "token_acc": 0.8237665269267979, "grad_norm": 2.8370169229269533, "learning_rate": 3.092271377092215e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.168766, "epoch": 4.566371681415929, "step": 260}, {"loss": 0.5393988609313964, "token_acc": 0.8207667731629393, "grad_norm": 2.9449232066148374, "learning_rate": 1.7433526766711725e-08, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.169653, "epoch": 4.654867256637168, "step": 265}, {"loss": 0.573880958557129, "token_acc": 0.8175997373173535, "grad_norm": 3.005898852586366, "learning_rate": 7.760793399827936e-09, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.17056, "epoch": 4.743362831858407, "step": 270}, {"loss": 0.5792054176330567, "token_acc": 0.8213772168077967, "grad_norm": 2.8671280726864454, "learning_rate": 1.942084195468152e-09, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.171452, "epoch": 4.831858407079646, "step": 275}, {"loss": 0.571114444732666, "token_acc": 0.8273170731707317, "grad_norm": 2.9597071657306118, "learning_rate": 0.0, "memory(GiB)": 51.26, "train_speed(iter/s)": 0.172362, "epoch": 4.920353982300885, "step": 280}, {"eval_loss": 0.7800883054733276, "eval_token_acc": 0.7776972294890787, "eval_runtime": 10.3882, "eval_samples_per_second": 9.53, "eval_steps_per_second": 1.251, "epoch": 4.920353982300885, "step": 280}, {"eval_loss": 0.7800883054733276, "eval_token_acc": 0.7776972294890787, "eval_runtime": 10.1584, "eval_samples_per_second": 9.746, "eval_steps_per_second": 1.28, "epoch": 4.920353982300885, "step": 280}, {"train_runtime": 1921.6184, "train_samples_per_second": 2.344, "train_steps_per_second": 0.146, "total_flos": 43238058737664.0, "train_loss": 0.7187317839690617, "epoch": 4.920353982300885, "step": 280}], "memory": 51.255859375}