| { |
| "output_dir": "/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131", |
| "overwrite_output_dir": false, |
| "do_train": false, |
| "do_eval": false, |
| "do_predict": false, |
| "eval_strategy": "steps", |
| "prediction_loss_only": false, |
| "per_device_train_batch_size": 1, |
| "per_device_eval_batch_size": 8, |
| "per_gpu_train_batch_size": null, |
| "per_gpu_eval_batch_size": null, |
| "gradient_accumulation_steps": 16, |
| "eval_accumulation_steps": null, |
| "eval_delay": 0, |
| "torch_empty_cache_steps": null, |
| "learning_rate": 5e-05, |
| "weight_decay": 0.1, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.95, |
| "adam_epsilon": 1e-08, |
| "max_grad_norm": 1.0, |
| "num_train_epochs": 1.0, |
| "max_steps": -1, |
| "lr_scheduler_type": "cosine", |
| "lr_scheduler_kwargs": null, |
| "warmup_ratio": 0.0, |
| "warmup_steps": 0, |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": true, |
| "logging_dir": "/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131/runs", |
| "logging_strategy": "steps", |
| "logging_first_step": true, |
| "logging_steps": 5, |
| "logging_nan_inf_filter": true, |
| "save_strategy": "steps", |
| "save_steps": 50.0, |
| "save_total_limit": null, |
| "save_safetensors": true, |
| "save_on_each_node": false, |
| "save_only_model": false, |
| "restore_callback_states_from_checkpoint": false, |
| "no_cuda": false, |
| "use_cpu": false, |
| "use_mps_device": false, |
| "seed": 42, |
| "data_seed": 42, |
| "jit_mode_eval": false, |
| "bf16": true, |
| "fp16": false, |
| "fp16_opt_level": "O1", |
| "half_precision_backend": "auto", |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "local_rank": 0, |
| "ddp_backend": null, |
| "tpu_num_cores": null, |
| "tpu_metrics_debug": false, |
| "debug": null, |
| "dataloader_drop_last": false, |
| "eval_steps": 50.0, |
| "dataloader_num_workers": 2, |
| "dataloader_prefetch_factor": null, |
| "past_index": -1, |
| "run_name": "/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131", |
| "disable_tqdm": null, |
| "remove_unused_columns": false, |
| "label_names": null, |
| "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": null, |
| "fsdp_transformer_layer_cls_to_wrap": null, |
| "accelerator_config": { |
| "dispatch_batches": false |
| }, |
| "parallelism_config": null, |
| "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": 2, |
| "offload_optimizer": { |
| "device": "none", |
| "pin_memory": true |
| }, |
| "allgather_partitions": true, |
| "allgather_bucket_size": 200000000.0, |
| "overlap_comm": false, |
| "reduce_scatter": true, |
| "reduce_bucket_size": 200000000.0, |
| "contiguous_gradients": 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, |
| "scheduler": { |
| "type": "WarmupDecayLR", |
| "params": { |
| "warmup_min_lr": "auto", |
| "warmup_max_lr": "auto", |
| "warmup_num_steps": "auto", |
| "total_num_steps": "auto" |
| } |
| } |
| }, |
| "label_smoothing_factor": 0.0, |
| "optim": "adamw_torch_fused", |
| "optim_args": null, |
| "adafactor": false, |
| "group_by_length": false, |
| "length_column_name": "length", |
| "report_to": [ |
| "none" |
| ], |
| "project": "huggingface", |
| "trackio_space_id": "trackio", |
| "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, |
| "hub_revision": null, |
| "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, |
| "liger_kernel_config": null, |
| "eval_use_gather_object": false, |
| "average_tokens_across_devices": true, |
| "sortish_sampler": false, |
| "predict_with_generate": false, |
| "generation_max_length": null, |
| "generation_num_beams": null, |
| "generation_config": null, |
| "tuner_backend": "peft", |
| "vit_gradient_checkpointing": null, |
| "router_aux_loss_coef": 0.0, |
| "enable_dft_loss": false, |
| "enable_channel_loss": false, |
| "safe_serialization": true, |
| "max_shard_size": "5GB", |
| "check_model": true, |
| "acc_strategy": "token", |
| "train_dataloader_shuffle": true, |
| "max_epochs": null, |
| "aligner_lr": null, |
| "vit_lr": null, |
| "use_logits_to_keep": null, |
| "ds3_gather_for_generation": true, |
| "resume_only_model": false, |
| "optimizer": null, |
| "loss_type": "grpo", |
| "eval_metric": null, |
| "callbacks": [], |
| "early_stop_interval": null, |
| "eval_use_evalscope": false, |
| "eval_dataset": [], |
| "eval_dataset_args": null, |
| "eval_limit": null, |
| "eval_generation_config": null, |
| "extra_eval_args": null, |
| "tuner_type": "lora", |
| "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, |
| "lisa_activated_layers": 0, |
| "lisa_step_interval": 20, |
| "use_flash_ckpt": false, |
| "use_ray": false, |
| "ray_exp_name": null, |
| "device_groups": null, |
| "model": "Qwen/Qwen2.5-Omni-7B", |
| "model_type": "qwen2_5_omni", |
| "model_revision": null, |
| "task_type": "causal_lm", |
| "torch_dtype": "bfloat16", |
| "attn_impl": null, |
| "experts_impl": null, |
| "new_special_tokens": [], |
| "num_labels": null, |
| "problem_type": null, |
| "rope_scaling": null, |
| "device_map": null, |
| "max_memory": {}, |
| "max_model_len": null, |
| "local_repo_path": null, |
| "init_strategy": null, |
| "template": "qwen2_5_omni", |
| "system": null, |
| "max_length": 32768, |
| "truncation_strategy": "left", |
| "max_pixels": null, |
| "agent_template": null, |
| "norm_bbox": null, |
| "use_chat_template": true, |
| "padding_side": "right", |
| "padding_free": false, |
| "loss_scale": "last_round", |
| "sequence_parallel_size": 1, |
| "template_backend": "swift", |
| "response_prefix": null, |
| "enable_thinking": null, |
| "add_non_thinking_prefix": true, |
| "dataset": [ |
| "/tmp/haolong2/qwen25omni-grpo-ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1.head2000.grpo.jsonl" |
| ], |
| "val_dataset": [], |
| "cached_dataset": [], |
| "cached_val_dataset": [], |
| "split_dataset_ratio": 0.025, |
| "dataset_num_proc": 1, |
| "load_from_cache_file": false, |
| "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": 512, |
| "temperature": 1.0, |
| "top_k": -1, |
| "top_p": 1.0, |
| "repetition_penalty": 1.0, |
| "num_beams": 1, |
| "stream": false, |
| "stop_words": [], |
| "logprobs": false, |
| "top_logprobs": null, |
| "structured_outputs_regex": null, |
| "train_type": "lora", |
| "adapters": [], |
| "external_plugins": [ |
| "src/plugin/plugin.py" |
| ], |
| "custom_register_path": [], |
| "model_kwargs": {}, |
| "load_args": false, |
| "load_data_args": false, |
| "packing": false, |
| "packing_length": null, |
| "packing_num_proc": 1, |
| "lazy_tokenize": true, |
| "use_hf": true, |
| "ignore_args_error": false, |
| "use_swift_lora": false, |
| "freeze_parameters": [], |
| "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, |
| "target_parameters": 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, |
| "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, |
| "reft_layer_key": null, |
| "reft_layers": null, |
| "reft_rank": 4, |
| "reft_intervention_type": "LoreftIntervention", |
| "reft_args": null, |
| "swanlab_token": null, |
| "swanlab_project": "ms-swift", |
| "swanlab_workspace": null, |
| "swanlab_exp_name": null, |
| "swanlab_notification_method": null, |
| "swanlab_webhook_url": null, |
| "swanlab_secret": null, |
| "swanlab_sender_email": null, |
| "swanlab_receiver_email": null, |
| "swanlab_smtp_server": null, |
| "swanlab_smtp_port": null, |
| "swanlab_email_language": "zh", |
| "swanlab_mode": "cloud", |
| "add_version": true, |
| "create_checkpoint_symlink": false, |
| "zero_hpz_partition_size": null, |
| "deepspeed_autotp_size": null, |
| "reward_model": null, |
| "reward_adapters": [], |
| "reward_model_type": null, |
| "reward_model_revision": null, |
| "reward_template": null, |
| "num_ppo_epochs": 4, |
| "whiten_rewards": false, |
| "kl_coef": 0.05, |
| "cliprange": 0.2, |
| "vf_coef": 0.1, |
| "cliprange_value": 0.2, |
| "gamma": 1.0, |
| "lam": 0.95, |
| "num_mini_batches": 1, |
| "local_rollout_forward_batch_size": 64, |
| "num_sample_generations": 10, |
| "response_length": 512, |
| "missing_eos_penalty": null, |
| "vllm_gpu_memory_utilization": 0.9, |
| "vllm_tensor_parallel_size": 1, |
| "vllm_pipeline_parallel_size": 1, |
| "vllm_enable_expert_parallel": false, |
| "vllm_max_num_seqs": null, |
| "vllm_max_model_len": null, |
| "vllm_disable_custom_all_reduce": true, |
| "vllm_enforce_eager": false, |
| "vllm_limit_mm_per_prompt": null, |
| "vllm_max_lora_rank": 8, |
| "vllm_enable_prefix_caching": true, |
| "vllm_use_async_engine": null, |
| "vllm_quantization": null, |
| "vllm_reasoning_parser": null, |
| "vllm_disable_cascade_attn": false, |
| "vllm_mm_processor_cache_gb": 1.0, |
| "vllm_speculative_config": null, |
| "vllm_engine_kwargs": {}, |
| "vllm_data_parallel_size": 1, |
| "use_vllm": true, |
| "vllm_mode": "server", |
| "vllm_enable_lora": false, |
| "vllm_server_base_url": null, |
| "vllm_server_host": [ |
| "127.0.0.1" |
| ], |
| "vllm_server_port": [ |
| 26799 |
| ], |
| "vllm_server_timeout": 240.0, |
| "vllm_server_group_port": [ |
| 27799 |
| ], |
| "enable_flattened_weight_sync": true, |
| "async_generate": false, |
| "sleep_level": 0, |
| "move_model_batches": null, |
| "offload_optimizer": false, |
| "offload_model": false, |
| "wandb_log_unique_prompts": null, |
| "epsilon": 0.2, |
| "epsilon_high": null, |
| "delta": null, |
| "cosine_min_len_value_wrong": -0.5, |
| "cosine_max_len_value_wrong": 0.0, |
| "cosine_min_len_value_correct": 1.0, |
| "cosine_max_len_value_correct": 0.5, |
| "cosine_max_len": null, |
| "repetition_n_grams": 3, |
| "repetition_max_penalty": -1.0, |
| "reward_model_plugin": null, |
| "chord_sft_dataset": [], |
| "chord_sft_per_device_train_batch_size": null, |
| "chord_enable_phi_function": false, |
| "chord_mu_warmup_steps": null, |
| "chord_mu_decay_steps": null, |
| "chord_mu_peak": null, |
| "chord_mu_valley": null, |
| "sync_ref_model": false, |
| "ref_model_sync_steps": 512, |
| "ref_model_mixup_alpha": 0.6, |
| "multi_turn_scheduler": null, |
| "max_turns": null, |
| "completion_length_limit_scope": "per_round", |
| "vllm_server_pass_dataset": false, |
| "dynamic_sample": false, |
| "max_resample_times": 3, |
| "overlong_filter": true, |
| "soft_max_length": null, |
| "soft_cache_length": null, |
| "scale_rewards": "group", |
| "log_entropy": true, |
| "top_entropy_quantile": 1.0, |
| "importance_sampling_level": "token", |
| "tau_pos": 1.0, |
| "tau_neg": 1.05, |
| "advantage_estimator": "grpo", |
| "kl_in_reward": false, |
| "generation_batch_size": null, |
| "steps_per_generation": null, |
| "num_generations_eval": null, |
| "rollout_importance_sampling_mode": null, |
| "rollout_importance_sampling_threshold": 2.0, |
| "log_rollout_offpolicy_metrics": true, |
| "off_policy_sequence_mask_delta": null, |
| "num_generations": 8, |
| "reward_funcs": [ |
| "sicl_reward", |
| "sicl_ice_embedding_reward" |
| ], |
| "reward_weights": [ |
| 1.0, |
| 0.04 |
| ], |
| "log_completions": true, |
| "num_iterations": 1, |
| "teacher_model": null, |
| "teacher_adapters": [], |
| "teacher_model_type": null, |
| "teacher_model_revision": null, |
| "teacher_deepspeed": null, |
| "teacher_model_server": null, |
| "rlhf_type": "grpo", |
| "ref_model": null, |
| "ref_adapters": [], |
| "ref_model_type": null, |
| "ref_model_revision": null, |
| "beta": 0.001, |
| "label_smoothing": 0, |
| "max_completion_length": 512, |
| "rpo_alpha": null, |
| "ld_alpha": null, |
| "discopop_tau": 0.05, |
| "loss_weights": null, |
| "cpo_alpha": 1.0, |
| "simpo_gamma": 1, |
| "desirable_weight": 1.0, |
| "undesirable_weight": 1.0, |
| "center_rewards_coefficient": null, |
| "sft_alpha": 0, |
| "lmbda": 0.5, |
| "seq_kd": false, |
| "gkd_logits_topk": null, |
| "offload_teacher_model": false, |
| "vllm_client": "<swift.rlhf_trainers.vllm_client.VLLMClient object at 0x7f3ea9e2e690>", |
| "swift_version": "4.0.4", |
| "ckpt_dir": null, |
| "rank": 0, |
| "global_world_size": 1, |
| "local_world_size": 1, |
| "model_suffix": "Qwen2.5-Omni-7B", |
| "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/work/hdd/beiq/huggingface/hub/models--Qwen--Qwen2.5-Omni-7B/snapshots/ae9e1690543ffd5c0221dc27f79834d0294cba00', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", |
| "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen2_5_omni', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen2_5OmniLoader'>, template='qwen2_5_omni', model_arch=MultiModelKeys(arch_name='qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model', 'thinker.lm_head'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=['*.bin', '*.safetensors'], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=[])", |
| "model_dir": "/work/hdd/beiq/huggingface/hub/models--Qwen--Qwen2.5-Omni-7B/snapshots/ae9e1690543ffd5c0221dc27f79834d0294cba00", |
| "template_meta": "QwenTemplateMeta(template_type='qwen2_5_omni', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen2_5OmniTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system='You are a helpful assistant.', auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')", |
| "_val_dataset_exists": true, |
| "hub": "<class 'swift.hub.hub.HFHub'>", |
| "evaluation_strategy": "steps", |
| "training_args": "GRPOConfig(output_dir='/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131', 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=8, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131/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=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=50, dataloader_num_workers=2, dataloader_prefetch_factor=2, past_index=-1, run_name='/work/hdd/beiq/haolong2/SICL-GRPO/checkpoint/Qwen2.5-Omni-7B/lora_grpo_ctx_good_perf_bad_2k_s42_ctx0p6_wer0p1_ice_soft_w004/18288799/v0-20260516-181131', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': 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, 'scheduler': {'type': 'WarmupDecayLR', 'params': {'warmup_min_lr': 'auto', 'warmup_max_lr': 'auto', 'warmup_num_steps': 'auto', 'total_num_steps': 'auto'}}}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, cast_lm_head_to_fp32=False, num_generations=8, num_generations_eval=None, max_completion_length=512, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=16, steps_per_generation=16, temperature=1.0, top_p=1.0, top_k=-1, min_p=None, generation_kwargs=None, chat_template_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='server', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_structured_outputs_regex=None, vllm_server_base_url=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[26799], vllm_server_timeout=240.0, vllm_group_port=51216, vllm_gpu_memory_utilization=0.9, vllm_max_model_length=None, vllm_tensor_parallel_size=1, beta=0.001, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, sapo_temperature_neg=1.05, sapo_temperature_pos=1.0, importance_sampling_level='token', reward_weights=[1.0, 0.04], multi_objective_aggregation='sum_then_normalize', scale_rewards='group', loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, max_tool_calling_iterations=None, vllm_importance_sampling_correction=True, vllm_importance_sampling_mode='sequence_mask', vllm_importance_sampling_cap=3.0, off_policy_mask_threshold=None, use_bias_correction_kl=False, log_completions=True, num_completions_to_print=None, log_unique_prompts=False, log_completions_hub_repo=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='lora', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=8, vllm_enable_prefix_caching=True, vllm_use_async_engine=None, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=1.0, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=[27799], enable_flattened_weight_sync=True, async_generate=False, structured_outputs_regex=None, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, wandb_log_unique_prompts=None, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=512, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=True, soft_max_length=None, soft_cache_length=None, log_entropy=True, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, dataset_shuffle=True, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=True, off_policy_sequence_mask_delta=None)" |
| } |
