ASLP-lab/CN-MultiDialect-ASR

1{2  "output_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534",3  "overwrite_output_dir": false,4  "do_train": false,5  "do_eval": false,6  "do_predict": false,7  "eval_strategy": "steps",8  "prediction_loss_only": false,9  "per_device_train_batch_size": 96,10  "per_device_eval_batch_size": 96,11  "per_gpu_train_batch_size": null,12  "per_gpu_eval_batch_size": null,13  "gradient_accumulation_steps": 2,14  "eval_accumulation_steps": null,15  "eval_delay": 0,16  "torch_empty_cache_steps": null,17  "learning_rate": 1e-05,18  "weight_decay": 0.1,19  "adam_beta1": 0.9,20  "adam_beta2": 0.95,21  "adam_epsilon": 1e-08,22  "max_grad_norm": 1.0,23  "num_train_epochs": 1.0,24  "max_steps": -1,25  "lr_scheduler_type": "cosine",26  "lr_scheduler_kwargs": null,27  "warmup_ratio": 0.05,28  "warmup_steps": 0,29  "log_level": "passive",30  "log_level_replica": "warning",31  "log_on_each_node": true,32  "logging_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534/runs",33  "logging_strategy": "steps",34  "logging_first_step": true,35  "logging_steps": 5,36  "logging_nan_inf_filter": true,37  "save_strategy": "steps",38  "save_steps": 500.0,39  "save_total_limit": null,40  "save_safetensors": true,41  "save_on_each_node": false,42  "save_only_model": false,43  "restore_callback_states_from_checkpoint": false,44  "no_cuda": false,45  "use_cpu": false,46  "use_mps_device": false,47  "seed": 42,48  "data_seed": 42,49  "jit_mode_eval": false,50  "bf16": true,51  "fp16": false,52  "fp16_opt_level": "O1",53  "half_precision_backend": "auto",54  "bf16_full_eval": false,55  "fp16_full_eval": false,56  "tf32": null,57  "local_rank": 0,58  "ddp_backend": null,59  "tpu_num_cores": null,60  "tpu_metrics_debug": false,61  "debug": null,62  "dataloader_drop_last": false,63  "eval_steps": 500.0,64  "dataloader_num_workers": 16,65  "dataloader_prefetch_factor": null,66  "past_index": -1,67  "run_name": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534",68  "disable_tqdm": null,69  "remove_unused_columns": true,70  "label_names": null,71  "load_best_model_at_end": false,72  "metric_for_best_model": "loss",73  "greater_is_better": false,74  "ignore_data_skip": false,75  "fsdp": [],76  "fsdp_min_num_params": 0,77  "fsdp_config": null,78  "fsdp_transformer_layer_cls_to_wrap": null,79  "accelerator_config": {80    "dispatch_batches": false81  },82  "parallelism_config": null,83  "deepspeed": {84    "fp16": {85      "enabled": "auto",86      "loss_scale": 0,87      "loss_scale_window": 1000,88      "initial_scale_power": 16,89      "hysteresis": 2,90      "min_loss_scale": 191    },92    "bf16": {93      "enabled": "auto"94    },95    "zero_optimization": {96      "stage": 2,97      "offload_optimizer": {98        "device": "none",99        "pin_memory": true100      },101      "allgather_partitions": true,102      "allgather_bucket_size": 200000000.0,103      "overlap_comm": false,104      "reduce_scatter": true,105      "reduce_bucket_size": 200000000.0,106      "contiguous_gradients": true107    },108    "gradient_accumulation_steps": "auto",109    "gradient_clipping": "auto",110    "steps_per_print": 2000,111    "train_batch_size": "auto",112    "train_micro_batch_size_per_gpu": "auto",113    "wall_clock_breakdown": false114  },115  "label_smoothing_factor": 0.0,116  "optim": "adamw_torch_fused",117  "optim_args": null,118  "adafactor": false,119  "group_by_length": false,120  "length_column_name": "length",121  "report_to": [122    "tensorboard"123  ],124  "project": "huggingface",125  "trackio_space_id": "trackio",126  "ddp_find_unused_parameters": null,127  "ddp_bucket_cap_mb": null,128  "ddp_broadcast_buffers": null,129  "dataloader_pin_memory": true,130  "dataloader_persistent_workers": false,131  "skip_memory_metrics": true,132  "use_legacy_prediction_loop": false,133  "push_to_hub": false,134  "resume_from_checkpoint": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v6-20260707-132425/checkpoint-8500",135  "hub_model_id": null,136  "hub_strategy": "every_save",137  "hub_token": null,138  "hub_private_repo": null,139  "hub_always_push": false,140  "hub_revision": null,141  "gradient_checkpointing": true,142  "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",143  "include_inputs_for_metrics": false,144  "include_for_metrics": [],145  "eval_do_concat_batches": true,146  "fp16_backend": "auto",147  "push_to_hub_model_id": null,148  "push_to_hub_organization": null,149  "push_to_hub_token": null,150  "mp_parameters": "",151  "auto_find_batch_size": false,152  "full_determinism": false,153  "torchdynamo": null,154  "ray_scope": "last",155  "ddp_timeout": 18000000,156  "torch_compile": false,157  "torch_compile_backend": null,158  "torch_compile_mode": null,159  "include_tokens_per_second": false,160  "include_num_input_tokens_seen": false,161  "neftune_noise_alpha": null,162  "optim_target_modules": null,163  "batch_eval_metrics": false,164  "eval_on_start": false,165  "use_liger_kernel": false,166  "liger_kernel_config": null,167  "eval_use_gather_object": false,168  "average_tokens_across_devices": true,169  "sortish_sampler": false,170  "predict_with_generate": false,171  "generation_max_length": null,172  "generation_num_beams": null,173  "generation_config": null,174  "tuner_backend": "peft",175  "vit_gradient_checkpointing": true,176  "router_aux_loss_coef": 0.0,177  "enable_dft_loss": false,178  "enable_channel_loss": false,179  "safe_serialization": true,180  "max_shard_size": "5GB",181  "check_model": false,182  "acc_strategy": "token",183  "train_dataloader_shuffle": true,184  "max_epochs": null,185  "aligner_lr": null,186  "vit_lr": null,187  "use_logits_to_keep": null,188  "ds3_gather_for_generation": true,189  "resume_only_model": false,190  "optimizer": null,191  "loss_type": null,192  "eval_metric": null,193  "callbacks": [],194  "early_stop_interval": null,195  "eval_use_evalscope": false,196  "eval_dataset": [],197  "eval_dataset_args": null,198  "eval_limit": null,199  "eval_generation_config": null,200  "extra_eval_args": null,201  "tuner_type": "full",202  "use_galore": false,203  "galore_target_modules": null,204  "galore_rank": 128,205  "galore_update_proj_gap": 50,206  "galore_scale": 1.0,207  "galore_proj_type": "std",208  "galore_optim_per_parameter": false,209  "galore_with_embedding": false,210  "galore_quantization": false,211  "galore_proj_quant": false,212  "galore_proj_bits": 4,213  "galore_proj_group_size": 256,214  "galore_cos_threshold": 0.4,215  "galore_gamma_proj": 2,216  "galore_queue_size": 5,217  "lisa_activated_layers": 0,218  "lisa_step_interval": 20,219  "use_flash_ckpt": false,220  "use_ray": false,221  "ray_exp_name": null,222  "device_groups": null,223  "model": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",224  "model_type": "qwen3_asr",225  "model_revision": null,226  "task_type": "causal_lm",227  "torch_dtype": "bfloat16",228  "attn_impl": "flash_attention_2",229  "experts_impl": null,230  "new_special_tokens": [],231  "num_labels": null,232  "problem_type": null,233  "rope_scaling": null,234  "device_map": null,235  "max_memory": {},236  "max_model_len": null,237  "local_repo_path": null,238  "init_strategy": null,239  "template": "qwen3_asr",240  "system": null,241  "max_length": 1024,242  "truncation_strategy": "delete",243  "max_pixels": null,244  "agent_template": null,245  "norm_bbox": null,246  "use_chat_template": true,247  "padding_side": "right",248  "padding_free": true,249  "loss_scale": "default",250  "sequence_parallel_size": 1,251  "is_binary_loss_scale": null,252  "template_backend": "swift",253  "response_prefix": null,254  "enable_thinking": null,255  "preserve_thinking": null,256  "add_non_thinking_prefix": true,257  "disable_ignore_empty_think": false,258  "dataset": [259    "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/data/train_v8_processed/train_new.jsonl"260  ],261  "val_dataset": [262    "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/data/train_v8_processed/dev.jsonl"263  ],264  "cached_dataset": [],265  "cached_val_dataset": [],266  "split_dataset_ratio": 0.0,267  "dataset_num_proc": 8,268  "load_from_cache_file": true,269  "dataset_shuffle": true,270  "val_dataset_shuffle": false,271  "streaming": false,272  "interleave_prob": null,273  "stopping_strategy": "first_exhausted",274  "shuffle_buffer_size": 1000,275  "download_mode": "reuse_dataset_if_exists",276  "columns": {},277  "strict": false,278  "disable_auto_column_mapping": false,279  "model_name": null,280  "model_author": null,281  "custom_dataset_info": [],282  "quant_method": null,283  "quant_bits": null,284  "hqq_axis": null,285  "bnb_4bit_compute_dtype": "bfloat16",286  "bnb_4bit_quant_type": "nf4",287  "bnb_4bit_use_double_quant": true,288  "bnb_4bit_quant_storage": null,289  "max_new_tokens": 64,290  "temperature": 0.0,291  "top_k": null,292  "top_p": null,293  "repetition_penalty": null,294  "num_beams": 1,295  "stream": false,296  "stop_words": [],297  "logprobs": false,298  "top_logprobs": null,299  "structured_outputs_regex": null,300  "adapters": [],301  "external_plugins": [],302  "custom_register_path": [],303  "model_kwargs": {},304  "enable_npu_model_patch": true,305  "load_args": false,306  "load_data_args": false,307  "packing": false,308  "packing_length": null,309  "packing_num_proc": 1,310  "lazy_tokenize": true,311  "use_hf": false,312  "ignore_args_error": false,313  "use_swift_lora": false,314  "freeze_parameters": [],315  "freeze_parameters_regex": null,316  "freeze_parameters_ratio": 0.0,317  "trainable_parameters": [318    "thinker.audio_tower.proj1",319    "thinker.audio_tower.proj2"320  ],321  "trainable_parameters_regex": null,322  "freeze_llm": false,323  "freeze_vit": false,324  "freeze_aligner": false,325  "target_modules": [326    "all-linear"327  ],328  "target_regex": null,329  "target_parameters": null,330  "modules_to_save": [],331  "lora_rank": 8,332  "lora_alpha": 32,333  "lora_dropout": 0.05,334  "lora_bias": "none",335  "lora_dtype": null,336  "lorap_lr_ratio": null,337  "use_rslora": false,338  "use_dora": false,339  "lora_ga_batch_size": 2,340  "lora_ga_iters": 2,341  "lora_ga_max_length": 1024,342  "lora_ga_direction": "ArB2r",343  "lora_ga_scale": "stable",344  "lora_ga_stable_gamma": 16,345  "init_weights": true,346  "fourier_n_frequency": 2000,347  "fourier_scaling": 300.0,348  "boft_block_size": 4,349  "boft_block_num": 0,350  "boft_n_butterfly_factor": 1,351  "boft_dropout": 0.0,352  "vera_rank": 256,353  "vera_projection_prng_key": 0,354  "vera_dropout": 0.0,355  "vera_d_initial": 0.1,356  "adapter_act": "gelu",357  "adapter_length": 128,358  "adalora_target_r": 8,359  "adalora_init_r": 12,360  "adalora_tinit": 0,361  "adalora_tfinal": 0,362  "adalora_deltaT": 1,363  "adalora_beta1": 0.85,364  "adalora_beta2": 0.85,365  "adalora_orth_reg_weight": 0.5,366  "llamapro_num_new_blocks": 4,367  "llamapro_num_groups": null,368  "reft_layer_key": null,369  "reft_layers": null,370  "reft_rank": 4,371  "reft_intervention_type": "LoreftIntervention",372  "reft_args": null,373  "swanlab_token": null,374  "swanlab_project": "ms-swift",375  "swanlab_workspace": null,376  "swanlab_exp_name": null,377  "swanlab_notification_method": null,378  "swanlab_webhook_url": null,379  "swanlab_secret": null,380  "swanlab_sender_email": null,381  "swanlab_receiver_email": null,382  "swanlab_smtp_server": null,383  "swanlab_smtp_port": null,384  "swanlab_email_language": "zh",385  "swanlab_mode": "cloud",386  "add_version": true,387  "create_checkpoint_symlink": false,388  "zero_hpz_partition_size": null,389  "deepspeed_autotp_size": null,390  "swift_version": "4.3.1",391  "ckpt_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",392  "rank": 0,393  "global_world_size": 8,394  "local_world_size": 8,395  "model_suffix": "checkpoint-10000-merged",396  "model_info": "ModelInfo(model_type='qwen3_asr', model_dir='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged', torch_dtype=torch.bfloat16, max_model_len=65536, quant_method=None, quant_bits=None, rope_scaling={'interleaved': True, 'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",397  "model_meta": "ModelMeta(model_type='qwen3_asr', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-ASR-1.7B', hf_model_id='Qwen/Qwen3-ASR-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-ASR-0.6B', hf_model_id='Qwen/Qwen3-ASR-0.6B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_asr', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3ASRLoader'>, template=None, model_arch=MultiModelKeys(arch_name='qwen3_asr', 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.proj1', 'thinker.audio_tower.proj2'], vision_tower=['thinker.audio_tower'], generator=[]), mcore_model_type=None, architectures=['Qwen3ASRForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['qwen-asr', 'transformers==4.57.6'], tags=['audio'])",398  "model_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",399  "template_meta": "QwenTemplateMeta(template_type='qwen3_asr', prefix=['<|im_start|>system\\n<|im_end|>\\n'], 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.Qwen3ASRTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",400  "_val_dataset_exists": true,401  "hub": "<class 'swift.hub.hub.MSHub'>",402  "evaluation_strategy": "steps",403  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534', 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=96, per_device_eval_batch_size=96, 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=1e-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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534/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=500, 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=False, eval_steps=500, dataloader_num_workers=16, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534', 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}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v6-20260707-132425/checkpoint-8500', 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={'use_reentrant': False}, 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, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=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=False, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"404}