huawei-ai4math/Mathesis-Autoformalizer-HPO

1{2  "model": "/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/models/Kimina-Autoformalizer-7B-RL-0506",3  "model_type": "qwen2",4  "model_revision": null,5  "task_type": "causal_lm",6  "torch_dtype": "float16",7  "attn_impl": null,8  "num_labels": null,9  "rope_scaling": null,10  "device_map": null,11  "local_repo_path": null,12  "template": "qwen",13  "system": "",14  "max_length": 2048,15  "truncation_strategy": "delete",16  "max_pixels": null,17  "tools_prompt": "react_en",18  "norm_bbox": null,19  "padding_side": "right",20  "loss_scale": "last_round",21  "sequence_parallel_size": 1,22  "use_chat_template": true,23  "template_backend": "swift",24  "dataset": [25    "0604_train_clean1972.jsonl"26  ],27  "val_dataset": [],28  "split_dataset_ratio": 0.01,29  "data_seed": 42,30  "dataset_num_proc": 4,31  "streaming": false,32  "enable_cache": false,33  "download_mode": "reuse_dataset_if_exists",34  "columns": {},35  "strict": false,36  "remove_unused_columns": true,37  "model_name": [38    null,39    null40  ],41  "model_author": [42    null,43    null44  ],45  "custom_dataset_info": [],46  "quant_method": null,47  "quant_bits": null,48  "hqq_axis": null,49  "bnb_4bit_compute_dtype": "float32",50  "bnb_4bit_quant_type": "nf4",51  "bnb_4bit_use_double_quant": true,52  "bnb_4bit_quant_storage": null,53  "max_new_tokens": 64,54  "temperature": 0.9,55  "top_k": null,56  "top_p": null,57  "repetition_penalty": null,58  "num_beams": 1,59  "stream": false,60  "stop_words": [],61  "logprobs": false,62  "top_logprobs": null,63  "ckpt_dir": null,64  "load_dataset_config": null,65  "lora_modules": [],66  "tuner_backend": "peft",67  "train_type": "full",68  "adapters": [],69  "seed": 42,70  "model_kwargs": {},71  "load_args": true,72  "load_data_args": false,73  "use_hf": false,74  "hub_token": null,75  "custom_register_path": [],76  "ignore_args_error": false,77  "use_swift_lora": false,78  "output_dir": "/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/outputs/dpo_output/v5-20250701-170604",79  "overwrite_output_dir": false,80  "do_train": false,81  "do_eval": false,82  "do_predict": false,83  "eval_strategy": "steps",84  "prediction_loss_only": false,85  "per_device_train_batch_size": 1,86  "per_device_eval_batch_size": 1,87  "per_gpu_train_batch_size": null,88  "per_gpu_eval_batch_size": null,89  "gradient_accumulation_steps": 8,90  "eval_accumulation_steps": null,91  "eval_delay": 0,92  "torch_empty_cache_steps": null,93  "learning_rate": 1e-05,94  "weight_decay": 0.1,95  "adam_beta1": 0.9,96  "adam_beta2": 0.999,97  "adam_epsilon": 1e-08,98  "max_grad_norm": 1.0,99  "num_train_epochs": 1.0,100  "max_steps": -1,101  "lr_scheduler_type": "cosine",102  "lr_scheduler_kwargs": null,103  "warmup_ratio": 0.05,104  "warmup_steps": 0,105  "log_level": "passive",106  "log_level_replica": "warning",107  "log_on_each_node": true,108  "logging_dir": "/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/outputs/dpo_output/v5-20250701-170604/runs",109  "logging_strategy": "steps",110  "logging_first_step": true,111  "logging_steps": 5,112  "logging_nan_inf_filter": true,113  "save_strategy": "steps",114  "save_steps": 10.0,115  "save_total_limit": 3,116  "save_safetensors": true,117  "save_on_each_node": false,118  "save_only_model": false,119  "restore_callback_states_from_checkpoint": false,120  "no_cuda": false,121  "use_cpu": false,122  "use_mps_device": false,123  "jit_mode_eval": false,124  "use_ipex": false,125  "bf16": false,126  "fp16": true,127  "fp16_opt_level": "O1",128  "half_precision_backend": "auto",129  "bf16_full_eval": false,130  "fp16_full_eval": false,131  "tf32": null,132  "local_rank": 0,133  "ddp_backend": null,134  "tpu_num_cores": null,135  "tpu_metrics_debug": false,136  "debug": null,137  "dataloader_drop_last": false,138  "eval_steps": 10.0,139  "dataloader_num_workers": 4,140  "dataloader_prefetch_factor": null,141  "past_index": -1,142  "run_name": null,143  "disable_tqdm": null,144  "label_names": null,145  "load_best_model_at_end": false,146  "metric_for_best_model": "loss",147  "greater_is_better": false,148  "ignore_data_skip": false,149  "fsdp": "",150  "fsdp_min_num_params": 0,151  "fsdp_config": null,152  "fsdp_transformer_layer_cls_to_wrap": null,153  "accelerator_config": {154    "dispatch_batches": false155  },156  "deepspeed": {157    "fp16": {158      "enabled": "auto",159      "loss_scale": 0,160      "loss_scale_window": 1000,161      "initial_scale_power": 16,162      "hysteresis": 2,163      "min_loss_scale": 1164    },165    "bf16": {166      "enabled": "auto"167    },168    "zero_optimization": {169      "stage": 3,170      "offload_optimizer": {171        "device": "cpu",172        "pin_memory": true173      },174      "offload_param": {175        "device": "cpu",176        "pin_memory": true177      },178      "overlap_comm": true,179      "contiguous_gradients": true,180      "sub_group_size": 1000000000.0,181      "reduce_bucket_size": "auto",182      "stage3_prefetch_bucket_size": "auto",183      "stage3_param_persistence_threshold": "auto",184      "stage3_max_live_parameters": 1000000000.0,185      "stage3_max_reuse_distance": 1000000000.0,186      "stage3_gather_16bit_weights_on_model_save": true187    },188    "gradient_accumulation_steps": "auto",189    "gradient_clipping": "auto",190    "steps_per_print": 2000,191    "train_batch_size": "auto",192    "train_micro_batch_size_per_gpu": "auto",193    "wall_clock_breakdown": false194  },195  "label_smoothing_factor": 0.0,196  "optim": "adamw_torch",197  "optim_args": null,198  "adafactor": false,199  "group_by_length": false,200  "length_column_name": "length",201  "report_to": [202    "tensorboard"203  ],204  "ddp_find_unused_parameters": null,205  "ddp_bucket_cap_mb": null,206  "ddp_broadcast_buffers": null,207  "dataloader_pin_memory": true,208  "dataloader_persistent_workers": false,209  "skip_memory_metrics": true,210  "use_legacy_prediction_loop": false,211  "push_to_hub": false,212  "resume_from_checkpoint": null,213  "hub_model_id": null,214  "hub_strategy": "every_save",215  "hub_private_repo": null,216  "hub_always_push": false,217  "gradient_checkpointing": true,218  "gradient_checkpointing_kwargs": null,219  "include_inputs_for_metrics": false,220  "include_for_metrics": [],221  "eval_do_concat_batches": true,222  "fp16_backend": "auto",223  "evaluation_strategy": "steps",224  "push_to_hub_model_id": null,225  "push_to_hub_organization": null,226  "push_to_hub_token": null,227  "mp_parameters": "",228  "auto_find_batch_size": false,229  "full_determinism": false,230  "torchdynamo": null,231  "ray_scope": "last",232  "ddp_timeout": 1800,233  "torch_compile": false,234  "torch_compile_backend": null,235  "torch_compile_mode": null,236  "dispatch_batches": null,237  "split_batches": null,238  "include_tokens_per_second": false,239  "include_num_input_tokens_seen": false,240  "neftune_noise_alpha": null,241  "optim_target_modules": null,242  "batch_eval_metrics": false,243  "eval_on_start": false,244  "use_liger_kernel": false,245  "eval_use_gather_object": false,246  "average_tokens_across_devices": false,247  "sortish_sampler": false,248  "predict_with_generate": false,249  "generation_max_length": null,250  "generation_num_beams": null,251  "generation_config": null,252  "freeze_parameters": [],253  "freeze_parameters_ratio": 0.0,254  "trainable_parameters": [],255  "freeze_llm": false,256  "freeze_vit": true,257  "freeze_aligner": true,258  "target_modules": [259    "all-linear"260  ],261  "target_regex": null,262  "modules_to_save": [],263  "lora_rank": 8,264  "lora_alpha": 32,265  "lora_dropout": 0.05,266  "lora_bias": "none",267  "lora_dtype": null,268  "lorap_lr_ratio": null,269  "use_rslora": false,270  "use_dora": false,271  "lora_ga_batch_size": 2,272  "lora_ga_iters": 2,273  "lora_ga_max_length": 1024,274  "lora_ga_direction": "ArB2r",275  "lora_ga_scale": "stable",276  "lora_ga_stable_gamma": 16,277  "init_weights": true,278  "fourier_n_frequency": 2000,279  "fourier_scaling": 300.0,280  "boft_block_size": 4,281  "boft_block_num": 0,282  "boft_n_butterfly_factor": 1,283  "boft_dropout": 0.0,284  "vera_rank": 256,285  "vera_projection_prng_key": 0,286  "vera_dropout": 0.0,287  "vera_d_initial": 0.1,288  "adapter_act": "gelu",289  "adapter_length": 128,290  "use_galore": false,291  "galore_target_modules": null,292  "galore_rank": 128,293  "galore_update_proj_gap": 50,294  "galore_scale": 1.0,295  "galore_proj_type": "std",296  "galore_optim_per_parameter": false,297  "galore_with_embedding": false,298  "galore_quantization": false,299  "galore_proj_quant": false,300  "galore_proj_bits": 4,301  "galore_proj_group_size": 256,302  "galore_cos_threshold": 0.4,303  "galore_gamma_proj": 2,304  "galore_queue_size": 5,305  "adalora_target_r": 8,306  "adalora_init_r": 12,307  "adalora_tinit": 0,308  "adalora_tfinal": 0,309  "adalora_deltaT": 1,310  "adalora_beta1": 0.85,311  "adalora_beta2": 0.85,312  "adalora_orth_reg_weight": 0.5,313  "llamapro_num_new_blocks": 4,314  "llamapro_num_groups": null,315  "lisa_activated_layers": 0,316  "lisa_step_interval": 20,317  "reft_layer_key": null,318  "reft_layers": null,319  "reft_rank": 4,320  "reft_intervention_type": "LoreftIntervention",321  "reft_args": null,322  "use_liger": false,323  "model_layer_cls_name": null,324  "metric_warmup_step": 0,325  "fsdp_num": 1,326  "acc_steps": 1,327  "swanlab_token": null,328  "swanlab_project": null,329  "swanlab_workspace": null,330  "swanlab_exp_name": null,331  "swanlab_mode": "cloud",332  "add_version": true,333  "resume_only_model": false,334  "check_model": true,335  "create_checkpoint_symlink": false,336  "packing": false,337  "lazy_tokenize": false,338  "external_plugins": [],339  "loss_type": "sigmoid",340  "optimizer": null,341  "metric": null,342  "acc_strategy": "token",343  "reward_model": null,344  "reward_adapters": [],345  "reward_model_type": null,346  "reward_model_revision": null,347  "num_ppo_epochs": 4,348  "whiten_rewards": false,349  "kl_coef": 0.05,350  "cliprange": 0.2,351  "vf_coef": 0.1,352  "cliprange_value": 0.2,353  "gamma": 1.0,354  "lam": 0.95,355  "num_mini_batches": 1,356  "local_rollout_forward_batch_size": 64,357  "num_sample_generations": 10,358  "response_length": 512,359  "missing_eos_penalty": null,360  "vllm_max_num_seqs": 256,361  "vllm_enforce_eager": false,362  "vllm_limit_mm_per_prompt": null,363  "vllm_enable_prefix_caching": true,364  "cosine_min_len_value_wrong": 0.0,365  "cosine_max_len_value_wrong": -0.5,366  "cosine_min_len_value_correct": 1.0,367  "cosine_max_len_value_correct": 0.5,368  "cosine_max_len": null,369  "repetition_n_grams": 3,370  "repetition_max_penalty": -1.0,371  "use_lmdeploy": false,372  "lmdeploy_device": "auto",373  "lmdeploy_session_len": null,374  "lmdeploy_cache_max_entry_count": 0.8,375  "num_generations": 8,376  "max_completion_length": 512,377  "ds3_gather_for_generation": true,378  "reward_funcs": [],379  "reward_weights": null,380  "log_completions": false,381  "use_vllm": false,382  "vllm_device": "auto",383  "vllm_gpu_memory_utilization": 0.9,384  "vllm_max_model_len": null,385  "rlhf_type": "dpo",386  "ref_model": "/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/models/Kimina-Autoformalizer-7B-RL-0506",387  "ref_model_type": "qwen2",388  "ref_model_revision": null,389  "beta": 0.1,390  "label_smoothing": 0,391  "rpo_alpha": 1.0,392  "cpo_alpha": 1.0,393  "simpo_gamma": 1,394  "desirable_weight": 1.0,395  "undesirable_weight": 1.0,396  "rank": 0,397  "global_world_size": 8,398  "local_world_size": 8,399  "model_suffix": "Kimina-Autoformalizer-7B-RL-0506",400  "model_info": "ModelInfo(model_type='qwen2', model_dir='/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/models/Kimina-Autoformalizer-7B-RL-0506', torch_dtype=torch.float16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",401  "model_meta": "ModelMeta(model_type='qwen2', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat', hf_model_id='Qwen/Qwen1.5-0.5B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat', hf_model_id='Qwen/Qwen1.5-1.8B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat', hf_model_id='Qwen/Qwen1.5-4B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat', hf_model_id='Qwen/Qwen1.5-7B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat', hf_model_id='Qwen/Qwen1.5-14B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat', hf_model_id='Qwen/Qwen1.5-32B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat', hf_model_id='Qwen/Qwen1.5-72B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat', hf_model_id='Qwen/Qwen1.5-110B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B', hf_model_id='Qwen/Qwen1.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B', hf_model_id='Qwen/Qwen1.5-1.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B', hf_model_id='Qwen/Qwen1.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B', hf_model_id='Qwen/Qwen1.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B', hf_model_id='Qwen/Qwen1.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B', hf_model_id='Qwen/Qwen1.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B', hf_model_id='Qwen/Qwen1.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B', hf_model_id='Qwen/Qwen1.5-110B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-32B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-110B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-4B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-7B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-14B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-32B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-72B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-110B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/CodeQwen1.5-7B', hf_model_id='Qwen/CodeQwen1.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/CodeQwen1.5-7B-Chat', hf_model_id='Qwen/CodeQwen1.5-7B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/CodeQwen1.5-7B-Chat-AWQ', hf_model_id='Qwen/CodeQwen1.5-7B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct', hf_model_id='Qwen/Qwen2-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct', hf_model_id='Qwen/Qwen2-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct', hf_model_id='Qwen/Qwen2-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct', hf_model_id='Qwen/Qwen2-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B', hf_model_id='Qwen/Qwen2-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B', hf_model_id='Qwen/Qwen2-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B', hf_model_id='Qwen/Qwen2-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B', hf_model_id='Qwen/Qwen2-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-Math-1.5B-Instruct', hf_model_id='Qwen/Qwen2-Math-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-7B-Instruct', hf_model_id='Qwen/Qwen2-Math-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-72B-Instruct', hf_model_id='Qwen/Qwen2-Math-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-1.5B', hf_model_id='Qwen/Qwen2-Math-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-7B', hf_model_id='Qwen/Qwen2-Math-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-72B', hf_model_id='Qwen/Qwen2-Math-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['math']), ModelGroup(models=[Model(ms_model_id='PowerInfer/SmallThinker-3B-Preview', hf_model_id='PowerInfer/SmallThinker-3B-Preview', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-1M', hf_model_id='Qwen/Qwen2.5-7B-Instruct-1M', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-1M', hf_model_id='Qwen/Qwen2.5-14B-Instruct-1M', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen', get_function=<function get_model_tokenizer_with_flash_attn at 0x15547c7eb5b0>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.37'], tags=[])",402  "model_dir": "/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/models/Kimina-Autoformalizer-7B-RL-0506",403  "hub": "<class 'swift.hub.hub.MSHub'>",404  "training_args": "DPOConfig(output_dir='/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/outputs/dpo_output/v5-20250701-170604', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/outputs/dpo_output/v5-20250701-170604/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=False, fp16=True, 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=10, dataloader_num_workers=4, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/ndfl4zki/ndfl4zkiuser07/zjfeng/work/reason_math/lean/DPO20250604_code_data/outputs/dpo_output/v5-20250701-170604', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), 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': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', '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=['tensorboard'], 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', evaluation_strategy='steps', 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=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, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, force_use_ref_model=False, disable_dropout=True, use_logits_to_keep=False, dataset_num_proc=4, padding_value=None, label_pad_token_id=None, max_prompt_length=512, max_completion_length=512, max_length=2048, truncation_mode='keep_end', padding_free=False, precompute_ref_log_probs=False, precompute_ref_batch_size=None, tools=None, loss_type='sigmoid', beta=0.1, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, reference_free=False, label_smoothing=0, use_weighting=False, rpo_alpha=1.0, discopop_tau=0.05, sync_ref_model=False, ref_model_mixup_alpha=0.9, ref_model_sync_steps=64, generate_during_eval=False, use_num_logits_to_keep=False, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='full', optimizer=None, galore_config=None)"405}