Upload folder using huggingface_hub

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker.model.*\\.(o_proj|k_proj|gate_proj|down_proj|v_proj|up_proj|q_proj)|thinker.audio_tower.proj|thinker.visual.merger.*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfbacf2981f3c2abe6ad7e2e648c659252392cdae3e51b3fd9c383d6a09704b
+size 81557840

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c014c517b6ff386814a4eaa791788b448d99ef758b1a0f0af2d05076e30b6f
+size 163345037

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87c63b89cfbf114f156e5890b38a355cedd43c7e862789cccd5748ec62cc78a
+size 14645

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8e2e4cc1ef1e53c969effff41dcad0107cf64a1b1018212d5b61170db41e00
+size 1465

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/trainer_state.json

@@ -0,0 +1,1038 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 0.12971985,
+  "best_model_checkpoint": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200",
+  "epoch": 0.7111111111111111,
+  "eval_steps": 300,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005925925925925926,
+      "grad_norm": 1.32502019405365,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.38409245014190674,
+      "step": 1,
+      "token_acc": 0.9151943462897526
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 1.348962426185608,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.4804305500454373,
+      "step": 10,
+      "token_acc": 0.8925214548426645
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 1.474541187286377,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 0.4860693454742432,
+      "step": 20,
+      "token_acc": 0.8906647293861242
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5195010900497437,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.4820727348327637,
+      "step": 30,
+      "token_acc": 0.8872207982424021
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 1.5887762308120728,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.4436625957489014,
+      "step": 40,
+      "token_acc": 0.8992023205221175
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 1.7676503658294678,
+      "learning_rate": 5.91715976331361e-06,
+      "loss": 0.473007869720459,
+      "step": 50,
+      "token_acc": 0.8852583586626139
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.005035161972046,
+      "learning_rate": 7.100591715976332e-06,
+      "loss": 0.4192169666290283,
+      "step": 60,
+      "token_acc": 0.8907309721175584
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 1.361005187034607,
+      "learning_rate": 8.284023668639054e-06,
+      "loss": 0.3096126079559326,
+      "step": 70,
+      "token_acc": 0.91939457937346
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 1.3007423877716064,
+      "learning_rate": 9.467455621301776e-06,
+      "loss": 0.28482446670532224,
+      "step": 80,
+      "token_acc": 0.9255202628696605
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7848371863365173,
+      "learning_rate": 1.0650887573964498e-05,
+      "loss": 0.24792802333831787,
+      "step": 90,
+      "token_acc": 0.9363215937388829
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.5432378649711609,
+      "learning_rate": 1.183431952662722e-05,
+      "loss": 0.21306073665618896,
+      "step": 100,
+      "token_acc": 0.9468995010691376
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 0.64493727684021,
+      "learning_rate": 1.3017751479289941e-05,
+      "loss": 0.20164842605590821,
+      "step": 110,
+      "token_acc": 0.9505376344086022
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9089162349700928,
+      "learning_rate": 1.4201183431952663e-05,
+      "loss": 0.22527461051940917,
+      "step": 120,
+      "token_acc": 0.9423220973782771
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 0.9455512762069702,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1824732780456543,
+      "step": 130,
+      "token_acc": 0.9536231884057971
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 0.6021348237991333,
+      "learning_rate": 1.6568047337278108e-05,
+      "loss": 0.18543678522109985,
+      "step": 140,
+      "token_acc": 0.9523099850968704
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8500062227249146,
+      "learning_rate": 1.7751479289940828e-05,
+      "loss": 0.18889259099960326,
+      "step": 150,
+      "token_acc": 0.9432362698120162
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 1.0183658599853516,
+      "learning_rate": 1.8934911242603552e-05,
+      "loss": 0.1937463402748108,
+      "step": 160,
+      "token_acc": 0.9425625920471281
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 0.5574401021003723,
+      "learning_rate": 1.9999978612794268e-05,
+      "loss": 0.16474100351333618,
+      "step": 170,
+      "token_acc": 0.9523260284505959
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7811685800552368,
+      "learning_rate": 1.9997412258797892e-05,
+      "loss": 0.14637688398361207,
+      "step": 180,
+      "token_acc": 0.9594446474241871
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 0.671356737613678,
+      "learning_rate": 1.9990569721450324e-05,
+      "loss": 0.12380313873291016,
+      "step": 190,
+      "token_acc": 0.9659009332376166
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.7796847224235535,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.2040093183517456,
+      "step": 200,
+      "token_acc": 0.9489942528735632
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.0088781118392944,
+      "learning_rate": 1.9964069631504664e-05,
+      "loss": 0.1916598677635193,
+      "step": 210,
+      "token_acc": 0.9477272727272728
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 1.3728845119476318,
+      "learning_rate": 1.994442341376408e-05,
+      "loss": 0.13621771335601807,
+      "step": 220,
+      "token_acc": 0.9564245810055866
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 0.8439155220985413,
+      "learning_rate": 1.9920523677539076e-05,
+      "loss": 0.1574079394340515,
+      "step": 230,
+      "token_acc": 0.9541870071348104
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.2579078674316406,
+      "learning_rate": 1.9892380645440422e-05,
+      "loss": 0.13396313190460205,
+      "step": 240,
+      "token_acc": 0.9584548104956269
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9577816724777222,
+      "learning_rate": 1.9860006355059656e-05,
+      "loss": 0.14859610795974731,
+      "step": 250,
+      "token_acc": 0.9541044776119403
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 1.2375385761260986,
+      "learning_rate": 1.982341465382029e-05,
+      "loss": 0.1562924861907959,
+      "step": 260,
+      "token_acc": 0.9559248554913294
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.978262119305485e-05,
+      "loss": 0.12399486303329468,
+      "step": 270,
+      "token_acc": 0.9662838088180807
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 1.176658272743225,
+      "learning_rate": 1.9737643421310346e-05,
+      "loss": 0.14870967864990234,
+      "step": 280,
+      "token_acc": 0.9565873914684787
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 1.807876706123352,
+      "learning_rate": 1.9688500576885012e-05,
+      "loss": 0.11581240892410279,
+      "step": 290,
+      "token_acc": 0.9647544056992876
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1867674589157104,
+      "learning_rate": 1.9635213679599562e-05,
+      "loss": 0.1393712043762207,
+      "step": 300,
+      "token_acc": 0.9596832253419726
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.1630009412765503,
+      "eval_runtime": 239.7168,
+      "eval_samples_per_second": 6.257,
+      "eval_steps_per_second": 6.257,
+      "eval_token_acc": 0.9527580557072638,
+      "step": 300
+    },
+    {
+      "epoch": 0.1837037037037037,
+      "grad_norm": 1.2620875835418701,
+      "learning_rate": 1.9577805521806358e-05,
+      "loss": 0.1300894260406494,
+      "step": 310,
+      "token_acc": 0.960536398467433
+    },
+    {
+      "epoch": 0.18962962962962962,
+      "grad_norm": 1.1361067295074463,
+      "learning_rate": 1.95163006586405e-05,
+      "loss": 0.16317719221115112,
+      "step": 320,
+      "token_acc": 0.9544095665171899
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.8173150420188904,
+      "learning_rate": 1.945072539751685e-05,
+      "loss": 0.17428743839263916,
+      "step": 330,
+      "token_acc": 0.94750656167979
+    },
+    {
+      "epoch": 0.20148148148148148,
+      "grad_norm": 0.8849798440933228,
+      "learning_rate": 1.93811077868776e-05,
+      "loss": 0.12995322942733764,
+      "step": 340,
+      "token_acc": 0.9658246656760773
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.6326722502708435,
+      "learning_rate": 1.9307477604195162e-05,
+      "loss": 0.1278319001197815,
+      "step": 350,
+      "token_acc": 0.9639468690702088
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.1027580499649048,
+      "learning_rate": 1.9229866343235427e-05,
+      "loss": 0.12902997732162474,
+      "step": 360,
+      "token_acc": 0.9652777777777778
+    },
+    {
+      "epoch": 0.21925925925925926,
+      "grad_norm": 0.7148353457450867,
+      "learning_rate": 1.914830720058701e-05,
+      "loss": 0.14380792379379273,
+      "step": 370,
+      "token_acc": 0.9572490706319703
+    },
+    {
+      "epoch": 0.22518518518518518,
+      "grad_norm": 1.1909170150756836,
+      "learning_rate": 1.9062835061462105e-05,
+      "loss": 0.15708266496658324,
+      "step": 380,
+      "token_acc": 0.9598788796366389
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.7275416254997253,
+      "learning_rate": 1.8973486484775037e-05,
+      "loss": 0.15604959726333617,
+      "step": 390,
+      "token_acc": 0.9558498896247241
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.9419987201690674,
+      "learning_rate": 1.888029968750498e-05,
+      "loss": 0.1431185483932495,
+      "step": 400,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.24296296296296296,
+      "grad_norm": 0.6928850412368774,
+      "learning_rate": 1.878331452834944e-05,
+      "loss": 0.15362846851348877,
+      "step": 410,
+      "token_acc": 0.9517941283073578
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.6290676593780518,
+      "learning_rate": 1.8682572490675524e-05,
+      "loss": 0.12896524667739867,
+      "step": 420,
+      "token_acc": 0.9619504987070557
+    },
+    {
+      "epoch": 0.2548148148148148,
+      "grad_norm": 0.7995588779449463,
+      "learning_rate": 1.8578116664776314e-05,
+      "loss": 0.14157743453979493,
+      "step": 430,
+      "token_acc": 0.9562071591774562
+    },
+    {
+      "epoch": 0.2607407407407407,
+      "grad_norm": 0.780008852481842,
+      "learning_rate": 1.8469991729439888e-05,
+      "loss": 0.16496583223342895,
+      "step": 440,
+      "token_acc": 0.9543109801031687
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8067275881767273,
+      "learning_rate": 1.8358243932838914e-05,
+      "loss": 0.14944461584091187,
+      "step": 450,
+      "token_acc": 0.9509394572025052
+    },
+    {
+      "epoch": 0.2725925925925926,
+      "grad_norm": 0.8212175369262695,
+      "learning_rate": 1.8242921072748948e-05,
+      "loss": 0.12261044979095459,
+      "step": 460,
+      "token_acc": 0.9617764834364761
+    },
+    {
+      "epoch": 0.2785185185185185,
+      "grad_norm": 0.688872754573822,
+      "learning_rate": 1.8124072476103957e-05,
+      "loss": 0.12651515007019043,
+      "step": 470,
+      "token_acc": 0.9594694178334562
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.0954047441482544,
+      "learning_rate": 1.8001748977897754e-05,
+      "loss": 0.11215313673019409,
+      "step": 480,
+      "token_acc": 0.9634851771511207
+    },
+    {
+      "epoch": 0.2903703703703704,
+      "grad_norm": 0.8077743649482727,
+      "learning_rate": 1.787600289944039e-05,
+      "loss": 0.1215265154838562,
+      "step": 490,
+      "token_acc": 0.9642989959092599
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.9279748797416687,
+      "learning_rate": 1.7746888025978807e-05,
+      "loss": 0.11017097234725952,
+      "step": 500,
+      "token_acc": 0.9696060037523452
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.2479947805404663,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.1296389102935791,
+      "step": 510,
+      "token_acc": 0.9566453447050463
+    },
+    {
+      "epoch": 0.30814814814814817,
+      "grad_norm": 1.1002650260925293,
+      "learning_rate": 1.7478774216065882e-05,
+      "loss": 0.13492013216018678,
+      "step": 520,
+      "token_acc": 0.9590994371482177
+    },
+    {
+      "epoch": 0.31407407407407406,
+      "grad_norm": 1.108170747756958,
+      "learning_rate": 1.733988995967179e-05,
+      "loss": 0.14083080291748046,
+      "step": 530,
+      "token_acc": 0.9592061742006616
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8783969879150391,
+      "learning_rate": 1.719786621933599e-05,
+      "loss": 0.12698700428009033,
+      "step": 540,
+      "token_acc": 0.9617927994121969
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.6896427273750305,
+      "learning_rate": 1.70527637427338e-05,
+      "loss": 0.11144465208053589,
+      "step": 550,
+      "token_acc": 0.9692820133234641
+    },
+    {
+      "epoch": 0.33185185185185184,
+      "grad_norm": 1.067499041557312,
+      "learning_rate": 1.690464459440538e-05,
+      "loss": 0.13314462900161744,
+      "step": 560,
+      "token_acc": 0.9597096188747731
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.6953498721122742,
+      "learning_rate": 1.6753572129208935e-05,
+      "loss": 0.11334860324859619,
+      "step": 570,
+      "token_acc": 0.9676190476190476
+    },
+    {
+      "epoch": 0.3437037037037037,
+      "grad_norm": 1.197219967842102,
+      "learning_rate": 1.6599610965222002e-05,
+      "loss": 0.1281804084777832,
+      "step": 580,
+      "token_acc": 0.9607272727272728
+    },
+    {
+      "epoch": 0.3496296296296296,
+      "grad_norm": 0.6708402633666992,
+      "learning_rate": 1.6442826956102424e-05,
+      "loss": 0.12322006225585938,
+      "step": 590,
+      "token_acc": 0.9628704034273474
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.0634019374847412,
+      "learning_rate": 1.628328716292082e-05,
+      "loss": 0.13818006515502929,
+      "step": 600,
+      "token_acc": 0.9580494801003944
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.14249637722969055,
+      "eval_runtime": 229.7535,
+      "eval_samples_per_second": 6.529,
+      "eval_steps_per_second": 6.529,
+      "eval_token_acc": 0.9576734025122884,
+      "step": 600
+    },
+    {
+      "epoch": 0.36148148148148146,
+      "grad_norm": 0.7200868129730225,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.13777921199798585,
+      "step": 610,
+      "token_acc": 0.9565537555228277
+    },
+    {
+      "epoch": 0.3674074074074074,
+      "grad_norm": 1.610889196395874,
+      "learning_rate": 1.595621433310997e-05,
+      "loss": 0.12660154104232788,
+      "step": 620,
+      "token_acc": 0.9658464928387808
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7054650783538818,
+      "learning_rate": 1.5788821195021792e-05,
+      "loss": 0.13561646938323973,
+      "step": 630,
+      "token_acc": 0.9558277654046028
+    },
+    {
+      "epoch": 0.37925925925925924,
+      "grad_norm": 1.4907517433166504,
+      "learning_rate": 1.5618952010115057e-05,
+      "loss": 0.12502728700637816,
+      "step": 640,
+      "token_acc": 0.9623144271031595
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 1.1567004919052124,
+      "learning_rate": 1.544667943636981e-05,
+      "loss": 0.1149907112121582,
+      "step": 650,
+      "token_acc": 0.9643255295429208
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.0321091413497925,
+      "learning_rate": 1.527207715976525e-05,
+      "loss": 0.14286714792251587,
+      "step": 660,
+      "token_acc": 0.9604221635883905
+    },
+    {
+      "epoch": 0.397037037037037,
+      "grad_norm": 1.4016674757003784,
+      "learning_rate": 1.5095219862762091e-05,
+      "loss": 0.13563259840011596,
+      "step": 670,
+      "token_acc": 0.9618029029793735
+    },
+    {
+      "epoch": 0.40296296296296297,
+      "grad_norm": 1.089959979057312,
+      "learning_rate": 1.4916183192358717e-05,
+      "loss": 0.1207580804824829,
+      "step": 680,
+      "token_acc": 0.9630141721396475
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.045990228652954,
+      "learning_rate": 1.4735043727734762e-05,
+      "loss": 0.11743853092193604,
+      "step": 690,
+      "token_acc": 0.9632217727105553
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 1.4252482652664185,
+      "learning_rate": 1.455187894749597e-05,
+      "loss": 0.0928974449634552,
+      "step": 700,
+      "token_acc": 0.9683257918552036
+    },
+    {
+      "epoch": 0.42074074074074075,
+      "grad_norm": 1.1641786098480225,
+      "learning_rate": 1.436676719653435e-05,
+      "loss": 0.12940033674240112,
+      "step": 710,
+      "token_acc": 0.9638252148997135
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.7832347750663757,
+      "learning_rate": 1.4179787652517791e-05,
+      "loss": 0.12433557510375977,
+      "step": 720,
+      "token_acc": 0.9617952522255193
+    },
+    {
+      "epoch": 0.4325925925925926,
+      "grad_norm": 1.1413239240646362,
+      "learning_rate": 1.3991020292023474e-05,
+      "loss": 0.09806026816368103,
+      "step": 730,
+      "token_acc": 0.9669064748201439
+    },
+    {
+      "epoch": 0.43851851851851853,
+      "grad_norm": 0.8681485056877136,
+      "learning_rate": 1.3800545856329572e-05,
+      "loss": 0.14417175054550171,
+      "step": 740,
+      "token_acc": 0.9569114098586694
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.9045178294181824,
+      "learning_rate": 1.3608445816879865e-05,
+      "loss": 0.10493698120117187,
+      "step": 750,
+      "token_acc": 0.9662880175888604
+    },
+    {
+      "epoch": 0.45037037037037037,
+      "grad_norm": 1.1523085832595825,
+      "learning_rate": 1.3414802340436022e-05,
+      "loss": 0.12941417694091797,
+      "step": 760,
+      "token_acc": 0.9683060109289617
+    },
+    {
+      "epoch": 0.4562962962962963,
+      "grad_norm": 0.9145503640174866,
+      "learning_rate": 1.3219698253932518e-05,
+      "loss": 0.12189668416976929,
+      "step": 770,
+      "token_acc": 0.9584711503123852
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.0088993310928345,
+      "learning_rate": 1.3023217009049133e-05,
+      "loss": 0.10943882465362549,
+      "step": 780,
+      "token_acc": 0.9680624556422995
+    },
+    {
+      "epoch": 0.46814814814814815,
+      "grad_norm": 1.376142978668213,
+      "learning_rate": 1.2825442646516253e-05,
+      "loss": 0.10388659238815308,
+      "step": 790,
+      "token_acc": 0.9674435812060673
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.3877886533737183,
+      "learning_rate": 1.262645976016821e-05,
+      "loss": 0.1380447506904602,
+      "step": 800,
+      "token_acc": 0.9608202123764189
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8192164301872253,
+      "learning_rate": 1.2426353460760036e-05,
+      "loss": 0.11965352296829224,
+      "step": 810,
+      "token_acc": 0.9655172413793104
+    },
+    {
+      "epoch": 0.48592592592592593,
+      "grad_norm": 0.8384001851081848,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.09073964357376099,
+      "step": 820,
+      "token_acc": 0.9659477866061293
+    },
+    {
+      "epoch": 0.4918518518518519,
+      "grad_norm": 1.1015766859054565,
+      "learning_rate": 1.2023113431755435e-05,
+      "loss": 0.10787882804870605,
+      "step": 830,
+      "token_acc": 0.9649122807017544
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.042965292930603,
+      "learning_rate": 1.1820152179621564e-05,
+      "loss": 0.13076914548873902,
+      "step": 840,
+      "token_acc": 0.960755275823769
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.8400379419326782,
+      "learning_rate": 1.161641239557907e-05,
+      "loss": 0.13471759557724,
+      "step": 850,
+      "token_acc": 0.9608513873052071
+    },
+    {
+      "epoch": 0.5096296296296297,
+      "grad_norm": 1.0256035327911377,
+      "learning_rate": 1.141198122504618e-05,
+      "loss": 0.11886721849441528,
+      "step": 860,
+      "token_acc": 0.9659887798036466
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.1291937828063965,
+      "learning_rate": 1.1206946109167189e-05,
+      "loss": 0.13678861856460572,
+      "step": 870,
+      "token_acc": 0.961859789320741
+    },
+    {
+      "epoch": 0.5214814814814814,
+      "grad_norm": 1.4508821964263916,
+      "learning_rate": 1.1001394747411347e-05,
+      "loss": 0.13137236833572388,
+      "step": 880,
+      "token_acc": 0.9597744360902256
+    },
+    {
+      "epoch": 0.5274074074074074,
+      "grad_norm": 0.6653353571891785,
+      "learning_rate": 1.0795415060061242e-05,
+      "loss": 0.11796672344207763,
+      "step": 890,
+      "token_acc": 0.9627539503386005
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7665302753448486,
+      "learning_rate": 1.0589095150606747e-05,
+      "loss": 0.14120289087295532,
+      "step": 900,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.1341869980096817,
+      "eval_runtime": 228.3025,
+      "eval_samples_per_second": 6.57,
+      "eval_steps_per_second": 6.57,
+      "eval_token_acc": 0.9593898728251541,
+      "step": 900
+    },
+    {
+      "epoch": 0.5392592592592592,
+      "grad_norm": 1.1279549598693848,
+      "learning_rate": 1.0382523268060612e-05,
+      "loss": 0.11883513927459717,
+      "step": 910,
+      "token_acc": 0.9647756766777902
+    },
+    {
+      "epoch": 0.5451851851851852,
+      "grad_norm": 1.0214804410934448,
+      "learning_rate": 1.0175787769211778e-05,
+      "loss": 0.11933118104934692,
+      "step": 920,
+      "token_acc": 0.959910078681154
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.8586761951446533,
+      "learning_rate": 9.968977080832633e-06,
+      "loss": 0.11430730819702148,
+      "step": 930,
+      "token_acc": 0.9654676258992806
+    },
+    {
+      "epoch": 0.557037037037037,
+      "grad_norm": 0.7968057990074158,
+      "learning_rate": 9.762179661856312e-06,
+      "loss": 0.13973416090011598,
+      "step": 940,
+      "token_acc": 0.9573529411764706
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 1.0118746757507324,
+      "learning_rate": 9.555483965540238e-06,
+      "loss": 0.12812395095825196,
+      "step": 950,
+      "token_acc": 0.9614254224834681
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.1432191133499146,
+      "learning_rate": 9.348978401632101e-06,
+      "loss": 0.1379111647605896,
+      "step": 960,
+      "token_acc": 0.9561209439528023
+    },
+    {
+      "epoch": 0.5748148148148148,
+      "grad_norm": 0.7802894115447998,
+      "learning_rate": 9.142751298554436e-06,
+      "loss": 0.14111405611038208,
+      "step": 970,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5807407407407408,
+      "grad_norm": 0.741787314414978,
+      "learning_rate": 8.936890865624014e-06,
+      "loss": 0.10649667978286743,
+      "step": 980,
+      "token_acc": 0.9672929714683368
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.7642576694488525,
+      "learning_rate": 8.731485155322134e-06,
+      "loss": 0.10067906379699706,
+      "step": 990,
+      "token_acc": 0.9700443786982249
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 1.0362651348114014,
+      "learning_rate": 8.52662202563203e-06,
+      "loss": 0.12069357633590698,
+      "step": 1000,
+      "token_acc": 0.9607771260997068
+    },
+    {
+      "epoch": 0.5985185185185186,
+      "grad_norm": 0.7719289064407349,
+      "learning_rate": 8.322389102459458e-06,
+      "loss": 0.11699739694595337,
+      "step": 1010,
+      "token_acc": 0.9636767976278725
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.143441081047058,
+      "learning_rate": 8.118873742152574e-06,
+      "loss": 0.12428475618362426,
+      "step": 1020,
+      "token_acc": 0.9612553273924835
+    },
+    {
+      "epoch": 0.6103703703703703,
+      "grad_norm": 0.7593462467193604,
+      "learning_rate": 7.916162994137056e-06,
+      "loss": 0.114216148853302,
+      "step": 1030,
+      "token_acc": 0.9674105561459441
+    },
+    {
+      "epoch": 0.6162962962962963,
+      "grad_norm": 0.9898127317428589,
+      "learning_rate": 7.714343563682565e-06,
+      "loss": 0.12711145877838134,
+      "step": 1040,
+      "token_acc": 0.9625998547567175
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.3860629796981812,
+      "learning_rate": 7.513501774816362e-06,
+      "loss": 0.14218902587890625,
+      "step": 1050,
+      "token_acc": 0.9609863820390137
+    },
+    {
+      "epoch": 0.6281481481481481,
+      "grad_norm": 0.7516865134239197,
+      "learning_rate": 7.313723533400047e-06,
+      "loss": 0.1154281735420227,
+      "step": 1060,
+      "token_acc": 0.965135769359705
+    },
+    {
+      "epoch": 0.6340740740740741,
+      "grad_norm": 1.0139286518096924,
+      "learning_rate": 7.115094290385103e-06,
+      "loss": 0.12470541000366211,
+      "step": 1070,
+      "token_acc": 0.9648382559774965
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0060116052627563,
+      "learning_rate": 6.9176990052630465e-06,
+      "loss": 0.1165156364440918,
+      "step": 1080,
+      "token_acc": 0.9641779788838613
+    },
+    {
+      "epoch": 0.6459259259259259,
+      "grad_norm": 1.437506079673767,
+      "learning_rate": 6.721622109725799e-06,
+      "loss": 0.128699791431427,
+      "step": 1090,
+      "token_acc": 0.9611650485436893
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 1.0488654375076294,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.14162105321884155,
+      "step": 1100,
+      "token_acc": 0.9533483822422875
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.9438616633415222,
+      "learning_rate": 6.333758358733313e-06,
+      "loss": 0.14174394607543944,
+      "step": 1110,
+      "token_acc": 0.9583492548719909
+    },
+    {
+      "epoch": 0.6637037037037037,
+      "grad_norm": 1.2012673616409302,
+      "learning_rate": 6.142137403860301e-06,
+      "loss": 0.14388898611068726,
+      "step": 1120,
+      "token_acc": 0.9564558879212419
+    },
+    {
+      "epoch": 0.6696296296296296,
+      "grad_norm": 1.1282634735107422,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.11517893075942993,
+      "step": 1130,
+      "token_acc": 0.9685185185185186
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.8449248671531677,
+      "learning_rate": 5.763927109519784e-06,
+      "loss": 0.08853521943092346,
+      "step": 1140,
+      "token_acc": 0.9759211966435607
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.9580397009849548,
+      "learning_rate": 5.577499541570954e-06,
+      "loss": 0.14078164100646973,
+      "step": 1150,
+      "token_acc": 0.9634651600753296
+    },
+    {
+      "epoch": 0.6874074074074074,
+      "grad_norm": 0.7772520184516907,
+      "learning_rate": 5.3929636054105745e-06,
+      "loss": 0.10377205610275268,
+      "step": 1160,
+      "token_acc": 0.9701709712622771
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.3566169738769531,
+      "learning_rate": 5.210398232413824e-06,
+      "loss": 0.1568630576133728,
+      "step": 1170,
+      "token_acc": 0.9556422995031938
+    },
+    {
+      "epoch": 0.6992592592592592,
+      "grad_norm": 0.9245796203613281,
+      "learning_rate": 5.0298815110888566e-06,
+      "loss": 0.14888057708740235,
+      "step": 1180,
+      "token_acc": 0.9563852058618283
+    },
+    {
+      "epoch": 0.7051851851851851,
+      "grad_norm": 1.0345977544784546,
+      "learning_rate": 4.851490653676019e-06,
+      "loss": 0.1214102029800415,
+      "step": 1190,
+      "token_acc": 0.9646017699115044
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.1635781526565552,
+      "learning_rate": 4.675301963121998e-06,
+      "loss": 0.12966567277908325,
+      "step": 1200,
+      "token_acc": 0.9577946768060837
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.12971985340118408,
+      "eval_runtime": 229.3094,
+      "eval_samples_per_second": 6.541,
+      "eval_steps_per_second": 6.541,
+      "eval_token_acc": 0.9621596317390965,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.082426367157522e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373517452fe5b4afd611e83a428a73a2e60bfea34aa4e86fa640ece3038da43d
+size 7185

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker.model.*\\.(o_proj|k_proj|gate_proj|down_proj|v_proj|up_proj|q_proj)|thinker.audio_tower.proj|thinker.visual.merger.*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662fb11b5e93ff923e74a6b426500a21b913bfef8b8354e21f4b73dc42cd4eea
+size 81557840

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fbaee92c5609589b2907bccf446872d750360ce8839e253f8799f09784684a
+size 163345037

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3459f36f23608cbd4d222126bf4d6a03bc7cf6c67a017764ca2382c5b4866ba0
+size 14645

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321c72446eee54ca44622234aad979f81b307ef134c6dfe0b9cf09bacabd7b7a
+size 1465

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/trainer_state.json

@@ -0,0 +1,1287 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.12762739,
+  "best_model_checkpoint": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500",
+  "epoch": 0.8888888888888888,
+  "eval_steps": 300,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005925925925925926,
+      "grad_norm": 1.32502019405365,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.38409245014190674,
+      "step": 1,
+      "token_acc": 0.9151943462897526
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 1.348962426185608,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.4804305500454373,
+      "step": 10,
+      "token_acc": 0.8925214548426645
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 1.474541187286377,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 0.4860693454742432,
+      "step": 20,
+      "token_acc": 0.8906647293861242
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5195010900497437,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.4820727348327637,
+      "step": 30,
+      "token_acc": 0.8872207982424021
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 1.5887762308120728,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.4436625957489014,
+      "step": 40,
+      "token_acc": 0.8992023205221175
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 1.7676503658294678,
+      "learning_rate": 5.91715976331361e-06,
+      "loss": 0.473007869720459,
+      "step": 50,
+      "token_acc": 0.8852583586626139
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.005035161972046,
+      "learning_rate": 7.100591715976332e-06,
+      "loss": 0.4192169666290283,
+      "step": 60,
+      "token_acc": 0.8907309721175584
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 1.361005187034607,
+      "learning_rate": 8.284023668639054e-06,
+      "loss": 0.3096126079559326,
+      "step": 70,
+      "token_acc": 0.91939457937346
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 1.3007423877716064,
+      "learning_rate": 9.467455621301776e-06,
+      "loss": 0.28482446670532224,
+      "step": 80,
+      "token_acc": 0.9255202628696605
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7848371863365173,
+      "learning_rate": 1.0650887573964498e-05,
+      "loss": 0.24792802333831787,
+      "step": 90,
+      "token_acc": 0.9363215937388829
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.5432378649711609,
+      "learning_rate": 1.183431952662722e-05,
+      "loss": 0.21306073665618896,
+      "step": 100,
+      "token_acc": 0.9468995010691376
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 0.64493727684021,
+      "learning_rate": 1.3017751479289941e-05,
+      "loss": 0.20164842605590821,
+      "step": 110,
+      "token_acc": 0.9505376344086022
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9089162349700928,
+      "learning_rate": 1.4201183431952663e-05,
+      "loss": 0.22527461051940917,
+      "step": 120,
+      "token_acc": 0.9423220973782771
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 0.9455512762069702,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1824732780456543,
+      "step": 130,
+      "token_acc": 0.9536231884057971
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 0.6021348237991333,
+      "learning_rate": 1.6568047337278108e-05,
+      "loss": 0.18543678522109985,
+      "step": 140,
+      "token_acc": 0.9523099850968704
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8500062227249146,
+      "learning_rate": 1.7751479289940828e-05,
+      "loss": 0.18889259099960326,
+      "step": 150,
+      "token_acc": 0.9432362698120162
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 1.0183658599853516,
+      "learning_rate": 1.8934911242603552e-05,
+      "loss": 0.1937463402748108,
+      "step": 160,
+      "token_acc": 0.9425625920471281
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 0.5574401021003723,
+      "learning_rate": 1.9999978612794268e-05,
+      "loss": 0.16474100351333618,
+      "step": 170,
+      "token_acc": 0.9523260284505959
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7811685800552368,
+      "learning_rate": 1.9997412258797892e-05,
+      "loss": 0.14637688398361207,
+      "step": 180,
+      "token_acc": 0.9594446474241871
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 0.671356737613678,
+      "learning_rate": 1.9990569721450324e-05,
+      "loss": 0.12380313873291016,
+      "step": 190,
+      "token_acc": 0.9659009332376166
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.7796847224235535,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.2040093183517456,
+      "step": 200,
+      "token_acc": 0.9489942528735632
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.0088781118392944,
+      "learning_rate": 1.9964069631504664e-05,
+      "loss": 0.1916598677635193,
+      "step": 210,
+      "token_acc": 0.9477272727272728
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 1.3728845119476318,
+      "learning_rate": 1.994442341376408e-05,
+      "loss": 0.13621771335601807,
+      "step": 220,
+      "token_acc": 0.9564245810055866
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 0.8439155220985413,
+      "learning_rate": 1.9920523677539076e-05,
+      "loss": 0.1574079394340515,
+      "step": 230,
+      "token_acc": 0.9541870071348104
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.2579078674316406,
+      "learning_rate": 1.9892380645440422e-05,
+      "loss": 0.13396313190460205,
+      "step": 240,
+      "token_acc": 0.9584548104956269
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9577816724777222,
+      "learning_rate": 1.9860006355059656e-05,
+      "loss": 0.14859610795974731,
+      "step": 250,
+      "token_acc": 0.9541044776119403
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 1.2375385761260986,
+      "learning_rate": 1.982341465382029e-05,
+      "loss": 0.1562924861907959,
+      "step": 260,
+      "token_acc": 0.9559248554913294
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.978262119305485e-05,
+      "loss": 0.12399486303329468,
+      "step": 270,
+      "token_acc": 0.9662838088180807
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 1.176658272743225,
+      "learning_rate": 1.9737643421310346e-05,
+      "loss": 0.14870967864990234,
+      "step": 280,
+      "token_acc": 0.9565873914684787
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 1.807876706123352,
+      "learning_rate": 1.9688500576885012e-05,
+      "loss": 0.11581240892410279,
+      "step": 290,
+      "token_acc": 0.9647544056992876
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1867674589157104,
+      "learning_rate": 1.9635213679599562e-05,
+      "loss": 0.1393712043762207,
+      "step": 300,
+      "token_acc": 0.9596832253419726
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.1630009412765503,
+      "eval_runtime": 239.7168,
+      "eval_samples_per_second": 6.257,
+      "eval_steps_per_second": 6.257,
+      "eval_token_acc": 0.9527580557072638,
+      "step": 300
+    },
+    {
+      "epoch": 0.1837037037037037,
+      "grad_norm": 1.2620875835418701,
+      "learning_rate": 1.9577805521806358e-05,
+      "loss": 0.1300894260406494,
+      "step": 310,
+      "token_acc": 0.960536398467433
+    },
+    {
+      "epoch": 0.18962962962962962,
+      "grad_norm": 1.1361067295074463,
+      "learning_rate": 1.95163006586405e-05,
+      "loss": 0.16317719221115112,
+      "step": 320,
+      "token_acc": 0.9544095665171899
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.8173150420188904,
+      "learning_rate": 1.945072539751685e-05,
+      "loss": 0.17428743839263916,
+      "step": 330,
+      "token_acc": 0.94750656167979
+    },
+    {
+      "epoch": 0.20148148148148148,
+      "grad_norm": 0.8849798440933228,
+      "learning_rate": 1.93811077868776e-05,
+      "loss": 0.12995322942733764,
+      "step": 340,
+      "token_acc": 0.9658246656760773
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.6326722502708435,
+      "learning_rate": 1.9307477604195162e-05,
+      "loss": 0.1278319001197815,
+      "step": 350,
+      "token_acc": 0.9639468690702088
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.1027580499649048,
+      "learning_rate": 1.9229866343235427e-05,
+      "loss": 0.12902997732162474,
+      "step": 360,
+      "token_acc": 0.9652777777777778
+    },
+    {
+      "epoch": 0.21925925925925926,
+      "grad_norm": 0.7148353457450867,
+      "learning_rate": 1.914830720058701e-05,
+      "loss": 0.14380792379379273,
+      "step": 370,
+      "token_acc": 0.9572490706319703
+    },
+    {
+      "epoch": 0.22518518518518518,
+      "grad_norm": 1.1909170150756836,
+      "learning_rate": 1.9062835061462105e-05,
+      "loss": 0.15708266496658324,
+      "step": 380,
+      "token_acc": 0.9598788796366389
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.7275416254997253,
+      "learning_rate": 1.8973486484775037e-05,
+      "loss": 0.15604959726333617,
+      "step": 390,
+      "token_acc": 0.9558498896247241
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.9419987201690674,
+      "learning_rate": 1.888029968750498e-05,
+      "loss": 0.1431185483932495,
+      "step": 400,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.24296296296296296,
+      "grad_norm": 0.6928850412368774,
+      "learning_rate": 1.878331452834944e-05,
+      "loss": 0.15362846851348877,
+      "step": 410,
+      "token_acc": 0.9517941283073578
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.6290676593780518,
+      "learning_rate": 1.8682572490675524e-05,
+      "loss": 0.12896524667739867,
+      "step": 420,
+      "token_acc": 0.9619504987070557
+    },
+    {
+      "epoch": 0.2548148148148148,
+      "grad_norm": 0.7995588779449463,
+      "learning_rate": 1.8578116664776314e-05,
+      "loss": 0.14157743453979493,
+      "step": 430,
+      "token_acc": 0.9562071591774562
+    },
+    {
+      "epoch": 0.2607407407407407,
+      "grad_norm": 0.780008852481842,
+      "learning_rate": 1.8469991729439888e-05,
+      "loss": 0.16496583223342895,
+      "step": 440,
+      "token_acc": 0.9543109801031687
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8067275881767273,
+      "learning_rate": 1.8358243932838914e-05,
+      "loss": 0.14944461584091187,
+      "step": 450,
+      "token_acc": 0.9509394572025052
+    },
+    {
+      "epoch": 0.2725925925925926,
+      "grad_norm": 0.8212175369262695,
+      "learning_rate": 1.8242921072748948e-05,
+      "loss": 0.12261044979095459,
+      "step": 460,
+      "token_acc": 0.9617764834364761
+    },
+    {
+      "epoch": 0.2785185185185185,
+      "grad_norm": 0.688872754573822,
+      "learning_rate": 1.8124072476103957e-05,
+      "loss": 0.12651515007019043,
+      "step": 470,
+      "token_acc": 0.9594694178334562
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.0954047441482544,
+      "learning_rate": 1.8001748977897754e-05,
+      "loss": 0.11215313673019409,
+      "step": 480,
+      "token_acc": 0.9634851771511207
+    },
+    {
+      "epoch": 0.2903703703703704,
+      "grad_norm": 0.8077743649482727,
+      "learning_rate": 1.787600289944039e-05,
+      "loss": 0.1215265154838562,
+      "step": 490,
+      "token_acc": 0.9642989959092599
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.9279748797416687,
+      "learning_rate": 1.7746888025978807e-05,
+      "loss": 0.11017097234725952,
+      "step": 500,
+      "token_acc": 0.9696060037523452
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.2479947805404663,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.1296389102935791,
+      "step": 510,
+      "token_acc": 0.9566453447050463
+    },
+    {
+      "epoch": 0.30814814814814817,
+      "grad_norm": 1.1002650260925293,
+      "learning_rate": 1.7478774216065882e-05,
+      "loss": 0.13492013216018678,
+      "step": 520,
+      "token_acc": 0.9590994371482177
+    },
+    {
+      "epoch": 0.31407407407407406,
+      "grad_norm": 1.108170747756958,
+      "learning_rate": 1.733988995967179e-05,
+      "loss": 0.14083080291748046,
+      "step": 530,
+      "token_acc": 0.9592061742006616
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8783969879150391,
+      "learning_rate": 1.719786621933599e-05,
+      "loss": 0.12698700428009033,
+      "step": 540,
+      "token_acc": 0.9617927994121969
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.6896427273750305,
+      "learning_rate": 1.70527637427338e-05,
+      "loss": 0.11144465208053589,
+      "step": 550,
+      "token_acc": 0.9692820133234641
+    },
+    {
+      "epoch": 0.33185185185185184,
+      "grad_norm": 1.067499041557312,
+      "learning_rate": 1.690464459440538e-05,
+      "loss": 0.13314462900161744,
+      "step": 560,
+      "token_acc": 0.9597096188747731
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.6953498721122742,
+      "learning_rate": 1.6753572129208935e-05,
+      "loss": 0.11334860324859619,
+      "step": 570,
+      "token_acc": 0.9676190476190476
+    },
+    {
+      "epoch": 0.3437037037037037,
+      "grad_norm": 1.197219967842102,
+      "learning_rate": 1.6599610965222002e-05,
+      "loss": 0.1281804084777832,
+      "step": 580,
+      "token_acc": 0.9607272727272728
+    },
+    {
+      "epoch": 0.3496296296296296,
+      "grad_norm": 0.6708402633666992,
+      "learning_rate": 1.6442826956102424e-05,
+      "loss": 0.12322006225585938,
+      "step": 590,
+      "token_acc": 0.9628704034273474
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.0634019374847412,
+      "learning_rate": 1.628328716292082e-05,
+      "loss": 0.13818006515502929,
+      "step": 600,
+      "token_acc": 0.9580494801003944
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.14249637722969055,
+      "eval_runtime": 229.7535,
+      "eval_samples_per_second": 6.529,
+      "eval_steps_per_second": 6.529,
+      "eval_token_acc": 0.9576734025122884,
+      "step": 600
+    },
+    {
+      "epoch": 0.36148148148148146,
+      "grad_norm": 0.7200868129730225,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.13777921199798585,
+      "step": 610,
+      "token_acc": 0.9565537555228277
+    },
+    {
+      "epoch": 0.3674074074074074,
+      "grad_norm": 1.610889196395874,
+      "learning_rate": 1.595621433310997e-05,
+      "loss": 0.12660154104232788,
+      "step": 620,
+      "token_acc": 0.9658464928387808
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7054650783538818,
+      "learning_rate": 1.5788821195021792e-05,
+      "loss": 0.13561646938323973,
+      "step": 630,
+      "token_acc": 0.9558277654046028
+    },
+    {
+      "epoch": 0.37925925925925924,
+      "grad_norm": 1.4907517433166504,
+      "learning_rate": 1.5618952010115057e-05,
+      "loss": 0.12502728700637816,
+      "step": 640,
+      "token_acc": 0.9623144271031595
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 1.1567004919052124,
+      "learning_rate": 1.544667943636981e-05,
+      "loss": 0.1149907112121582,
+      "step": 650,
+      "token_acc": 0.9643255295429208
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.0321091413497925,
+      "learning_rate": 1.527207715976525e-05,
+      "loss": 0.14286714792251587,
+      "step": 660,
+      "token_acc": 0.9604221635883905
+    },
+    {
+      "epoch": 0.397037037037037,
+      "grad_norm": 1.4016674757003784,
+      "learning_rate": 1.5095219862762091e-05,
+      "loss": 0.13563259840011596,
+      "step": 670,
+      "token_acc": 0.9618029029793735
+    },
+    {
+      "epoch": 0.40296296296296297,
+      "grad_norm": 1.089959979057312,
+      "learning_rate": 1.4916183192358717e-05,
+      "loss": 0.1207580804824829,
+      "step": 680,
+      "token_acc": 0.9630141721396475
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.045990228652954,
+      "learning_rate": 1.4735043727734762e-05,
+      "loss": 0.11743853092193604,
+      "step": 690,
+      "token_acc": 0.9632217727105553
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 1.4252482652664185,
+      "learning_rate": 1.455187894749597e-05,
+      "loss": 0.0928974449634552,
+      "step": 700,
+      "token_acc": 0.9683257918552036
+    },
+    {
+      "epoch": 0.42074074074074075,
+      "grad_norm": 1.1641786098480225,
+      "learning_rate": 1.436676719653435e-05,
+      "loss": 0.12940033674240112,
+      "step": 710,
+      "token_acc": 0.9638252148997135
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.7832347750663757,
+      "learning_rate": 1.4179787652517791e-05,
+      "loss": 0.12433557510375977,
+      "step": 720,
+      "token_acc": 0.9617952522255193
+    },
+    {
+      "epoch": 0.4325925925925926,
+      "grad_norm": 1.1413239240646362,
+      "learning_rate": 1.3991020292023474e-05,
+      "loss": 0.09806026816368103,
+      "step": 730,
+      "token_acc": 0.9669064748201439
+    },
+    {
+      "epoch": 0.43851851851851853,
+      "grad_norm": 0.8681485056877136,
+      "learning_rate": 1.3800545856329572e-05,
+      "loss": 0.14417175054550171,
+      "step": 740,
+      "token_acc": 0.9569114098586694
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.9045178294181824,
+      "learning_rate": 1.3608445816879865e-05,
+      "loss": 0.10493698120117187,
+      "step": 750,
+      "token_acc": 0.9662880175888604
+    },
+    {
+      "epoch": 0.45037037037037037,
+      "grad_norm": 1.1523085832595825,
+      "learning_rate": 1.3414802340436022e-05,
+      "loss": 0.12941417694091797,
+      "step": 760,
+      "token_acc": 0.9683060109289617
+    },
+    {
+      "epoch": 0.4562962962962963,
+      "grad_norm": 0.9145503640174866,
+      "learning_rate": 1.3219698253932518e-05,
+      "loss": 0.12189668416976929,
+      "step": 770,
+      "token_acc": 0.9584711503123852
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.0088993310928345,
+      "learning_rate": 1.3023217009049133e-05,
+      "loss": 0.10943882465362549,
+      "step": 780,
+      "token_acc": 0.9680624556422995
+    },
+    {
+      "epoch": 0.46814814814814815,
+      "grad_norm": 1.376142978668213,
+      "learning_rate": 1.2825442646516253e-05,
+      "loss": 0.10388659238815308,
+      "step": 790,
+      "token_acc": 0.9674435812060673
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.3877886533737183,
+      "learning_rate": 1.262645976016821e-05,
+      "loss": 0.1380447506904602,
+      "step": 800,
+      "token_acc": 0.9608202123764189
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8192164301872253,
+      "learning_rate": 1.2426353460760036e-05,
+      "loss": 0.11965352296829224,
+      "step": 810,
+      "token_acc": 0.9655172413793104
+    },
+    {
+      "epoch": 0.48592592592592593,
+      "grad_norm": 0.8384001851081848,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.09073964357376099,
+      "step": 820,
+      "token_acc": 0.9659477866061293
+    },
+    {
+      "epoch": 0.4918518518518519,
+      "grad_norm": 1.1015766859054565,
+      "learning_rate": 1.2023113431755435e-05,
+      "loss": 0.10787882804870605,
+      "step": 830,
+      "token_acc": 0.9649122807017544
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.042965292930603,
+      "learning_rate": 1.1820152179621564e-05,
+      "loss": 0.13076914548873902,
+      "step": 840,
+      "token_acc": 0.960755275823769
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.8400379419326782,
+      "learning_rate": 1.161641239557907e-05,
+      "loss": 0.13471759557724,
+      "step": 850,
+      "token_acc": 0.9608513873052071
+    },
+    {
+      "epoch": 0.5096296296296297,
+      "grad_norm": 1.0256035327911377,
+      "learning_rate": 1.141198122504618e-05,
+      "loss": 0.11886721849441528,
+      "step": 860,
+      "token_acc": 0.9659887798036466
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.1291937828063965,
+      "learning_rate": 1.1206946109167189e-05,
+      "loss": 0.13678861856460572,
+      "step": 870,
+      "token_acc": 0.961859789320741
+    },
+    {
+      "epoch": 0.5214814814814814,
+      "grad_norm": 1.4508821964263916,
+      "learning_rate": 1.1001394747411347e-05,
+      "loss": 0.13137236833572388,
+      "step": 880,
+      "token_acc": 0.9597744360902256
+    },
+    {
+      "epoch": 0.5274074074074074,
+      "grad_norm": 0.6653353571891785,
+      "learning_rate": 1.0795415060061242e-05,
+      "loss": 0.11796672344207763,
+      "step": 890,
+      "token_acc": 0.9627539503386005
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7665302753448486,
+      "learning_rate": 1.0589095150606747e-05,
+      "loss": 0.14120289087295532,
+      "step": 900,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.1341869980096817,
+      "eval_runtime": 228.3025,
+      "eval_samples_per_second": 6.57,
+      "eval_steps_per_second": 6.57,
+      "eval_token_acc": 0.9593898728251541,
+      "step": 900
+    },
+    {
+      "epoch": 0.5392592592592592,
+      "grad_norm": 1.1279549598693848,
+      "learning_rate": 1.0382523268060612e-05,
+      "loss": 0.11883513927459717,
+      "step": 910,
+      "token_acc": 0.9647756766777902
+    },
+    {
+      "epoch": 0.5451851851851852,
+      "grad_norm": 1.0214804410934448,
+      "learning_rate": 1.0175787769211778e-05,
+      "loss": 0.11933118104934692,
+      "step": 920,
+      "token_acc": 0.959910078681154
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.8586761951446533,
+      "learning_rate": 9.968977080832633e-06,
+      "loss": 0.11430730819702148,
+      "step": 930,
+      "token_acc": 0.9654676258992806
+    },
+    {
+      "epoch": 0.557037037037037,
+      "grad_norm": 0.7968057990074158,
+      "learning_rate": 9.762179661856312e-06,
+      "loss": 0.13973416090011598,
+      "step": 940,
+      "token_acc": 0.9573529411764706
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 1.0118746757507324,
+      "learning_rate": 9.555483965540238e-06,
+      "loss": 0.12812395095825196,
+      "step": 950,
+      "token_acc": 0.9614254224834681
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.1432191133499146,
+      "learning_rate": 9.348978401632101e-06,
+      "loss": 0.1379111647605896,
+      "step": 960,
+      "token_acc": 0.9561209439528023
+    },
+    {
+      "epoch": 0.5748148148148148,
+      "grad_norm": 0.7802894115447998,
+      "learning_rate": 9.142751298554436e-06,
+      "loss": 0.14111405611038208,
+      "step": 970,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5807407407407408,
+      "grad_norm": 0.741787314414978,
+      "learning_rate": 8.936890865624014e-06,
+      "loss": 0.10649667978286743,
+      "step": 980,
+      "token_acc": 0.9672929714683368
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.7642576694488525,
+      "learning_rate": 8.731485155322134e-06,
+      "loss": 0.10067906379699706,
+      "step": 990,
+      "token_acc": 0.9700443786982249
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 1.0362651348114014,
+      "learning_rate": 8.52662202563203e-06,
+      "loss": 0.12069357633590698,
+      "step": 1000,
+      "token_acc": 0.9607771260997068
+    },
+    {
+      "epoch": 0.5985185185185186,
+      "grad_norm": 0.7719289064407349,
+      "learning_rate": 8.322389102459458e-06,
+      "loss": 0.11699739694595337,
+      "step": 1010,
+      "token_acc": 0.9636767976278725
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.143441081047058,
+      "learning_rate": 8.118873742152574e-06,
+      "loss": 0.12428475618362426,
+      "step": 1020,
+      "token_acc": 0.9612553273924835
+    },
+    {
+      "epoch": 0.6103703703703703,
+      "grad_norm": 0.7593462467193604,
+      "learning_rate": 7.916162994137056e-06,
+      "loss": 0.114216148853302,
+      "step": 1030,
+      "token_acc": 0.9674105561459441
+    },
+    {
+      "epoch": 0.6162962962962963,
+      "grad_norm": 0.9898127317428589,
+      "learning_rate": 7.714343563682565e-06,
+      "loss": 0.12711145877838134,
+      "step": 1040,
+      "token_acc": 0.9625998547567175
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.3860629796981812,
+      "learning_rate": 7.513501774816362e-06,
+      "loss": 0.14218902587890625,
+      "step": 1050,
+      "token_acc": 0.9609863820390137
+    },
+    {
+      "epoch": 0.6281481481481481,
+      "grad_norm": 0.7516865134239197,
+      "learning_rate": 7.313723533400047e-06,
+      "loss": 0.1154281735420227,
+      "step": 1060,
+      "token_acc": 0.965135769359705
+    },
+    {
+      "epoch": 0.6340740740740741,
+      "grad_norm": 1.0139286518096924,
+      "learning_rate": 7.115094290385103e-06,
+      "loss": 0.12470541000366211,
+      "step": 1070,
+      "token_acc": 0.9648382559774965
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0060116052627563,
+      "learning_rate": 6.9176990052630465e-06,
+      "loss": 0.1165156364440918,
+      "step": 1080,
+      "token_acc": 0.9641779788838613
+    },
+    {
+      "epoch": 0.6459259259259259,
+      "grad_norm": 1.437506079673767,
+      "learning_rate": 6.721622109725799e-06,
+      "loss": 0.128699791431427,
+      "step": 1090,
+      "token_acc": 0.9611650485436893
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 1.0488654375076294,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.14162105321884155,
+      "step": 1100,
+      "token_acc": 0.9533483822422875
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.9438616633415222,
+      "learning_rate": 6.333758358733313e-06,
+      "loss": 0.14174394607543944,
+      "step": 1110,
+      "token_acc": 0.9583492548719909
+    },
+    {
+      "epoch": 0.6637037037037037,
+      "grad_norm": 1.2012673616409302,
+      "learning_rate": 6.142137403860301e-06,
+      "loss": 0.14388898611068726,
+      "step": 1120,
+      "token_acc": 0.9564558879212419
+    },
+    {
+      "epoch": 0.6696296296296296,
+      "grad_norm": 1.1282634735107422,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.11517893075942993,
+      "step": 1130,
+      "token_acc": 0.9685185185185186
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.8449248671531677,
+      "learning_rate": 5.763927109519784e-06,
+      "loss": 0.08853521943092346,
+      "step": 1140,
+      "token_acc": 0.9759211966435607
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.9580397009849548,
+      "learning_rate": 5.577499541570954e-06,
+      "loss": 0.14078164100646973,
+      "step": 1150,
+      "token_acc": 0.9634651600753296
+    },
+    {
+      "epoch": 0.6874074074074074,
+      "grad_norm": 0.7772520184516907,
+      "learning_rate": 5.3929636054105745e-06,
+      "loss": 0.10377205610275268,
+      "step": 1160,
+      "token_acc": 0.9701709712622771
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.3566169738769531,
+      "learning_rate": 5.210398232413824e-06,
+      "loss": 0.1568630576133728,
+      "step": 1170,
+      "token_acc": 0.9556422995031938
+    },
+    {
+      "epoch": 0.6992592592592592,
+      "grad_norm": 0.9245796203613281,
+      "learning_rate": 5.0298815110888566e-06,
+      "loss": 0.14888057708740235,
+      "step": 1180,
+      "token_acc": 0.9563852058618283
+    },
+    {
+      "epoch": 0.7051851851851851,
+      "grad_norm": 1.0345977544784546,
+      "learning_rate": 4.851490653676019e-06,
+      "loss": 0.1214102029800415,
+      "step": 1190,
+      "token_acc": 0.9646017699115044
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.1635781526565552,
+      "learning_rate": 4.675301963121998e-06,
+      "loss": 0.12966567277908325,
+      "step": 1200,
+      "token_acc": 0.9577946768060837
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.12971985340118408,
+      "eval_runtime": 229.3094,
+      "eval_samples_per_second": 6.541,
+      "eval_steps_per_second": 6.541,
+      "eval_token_acc": 0.9621596317390965,
+      "step": 1200
+    },
+    {
+      "epoch": 0.717037037037037,
+      "grad_norm": 0.6507232785224915,
+      "learning_rate": 4.501390800442783e-06,
+      "loss": 0.12880181074142455,
+      "step": 1210,
+      "token_acc": 0.9664481295796374
+    },
+    {
+      "epoch": 0.7229629629629629,
+      "grad_norm": 0.9675179123878479,
+      "learning_rate": 4.329831552489626e-06,
+      "loss": 0.12247174978256226,
+      "step": 1220,
+      "token_acc": 0.9622926093514329
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.9841185808181763,
+      "learning_rate": 4.160697600131568e-06,
+      "loss": 0.12777591943740846,
+      "step": 1230,
+      "token_acc": 0.9612147822905233
+    },
+    {
+      "epoch": 0.7348148148148148,
+      "grad_norm": 1.4565831422805786,
+      "learning_rate": 3.994061286868361e-06,
+      "loss": 0.13893853425979613,
+      "step": 1240,
+      "token_acc": 0.9622920517560074
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.1277369260787964,
+      "learning_rate": 3.8299938878870215e-06,
+      "loss": 0.09945087432861328,
+      "step": 1250,
+      "token_acc": 0.965828013518588
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.1658375263214111,
+      "learning_rate": 3.6685655795753836e-06,
+      "loss": 0.08901865482330322,
+      "step": 1260,
+      "token_acc": 0.9718995878606219
+    },
+    {
+      "epoch": 0.7525925925925926,
+      "grad_norm": 1.2467801570892334,
+      "learning_rate": 3.50984540950562e-06,
+      "loss": 0.12474504709243775,
+      "step": 1270,
+      "token_acc": 0.9593131765584173
+    },
+    {
+      "epoch": 0.7585185185185185,
+      "grad_norm": 1.2965892553329468,
+      "learning_rate": 3.3539012669005653e-06,
+      "loss": 0.12159136533737183,
+      "step": 1280,
+      "token_acc": 0.961352657004831
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.1689339876174927,
+      "learning_rate": 3.2007998535955774e-06,
+      "loss": 0.1344360113143921,
+      "step": 1290,
+      "token_acc": 0.9594349873234336
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.7894589304924011,
+      "learning_rate": 3.0506066555081683e-06,
+      "loss": 0.12788604497909545,
+      "step": 1300,
+      "token_acc": 0.963855421686747
+    },
+    {
+      "epoch": 0.7762962962962963,
+      "grad_norm": 1.2829697132110596,
+      "learning_rate": 2.90338591462782e-06,
+      "loss": 0.11962369680404664,
+      "step": 1310,
+      "token_acc": 0.9604395604395605
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.1379469633102417,
+      "learning_rate": 2.7592006015377937e-06,
+      "loss": 0.11098712682723999,
+      "step": 1320,
+      "token_acc": 0.9649507119386638
+    },
+    {
+      "epoch": 0.7881481481481482,
+      "grad_norm": 1.723992109298706,
+      "learning_rate": 2.6181123884808056e-06,
+      "loss": 0.13792314529418945,
+      "step": 1330,
+      "token_acc": 0.9560761346998536
+    },
+    {
+      "epoch": 0.794074074074074,
+      "grad_norm": 1.1304504871368408,
+      "learning_rate": 2.480181622980009e-06,
+      "loss": 0.10700693130493164,
+      "step": 1340,
+      "token_acc": 0.9640314724615962
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3609181642532349,
+      "learning_rate": 2.3454673020265973e-06,
+      "loss": 0.11214718818664551,
+      "step": 1350,
+      "token_acc": 0.967559411542814
+    },
+    {
+      "epoch": 0.8059259259259259,
+      "grad_norm": 0.7761492133140564,
+      "learning_rate": 2.2140270468450966e-06,
+      "loss": 0.09663894772529602,
+      "step": 1360,
+      "token_acc": 0.9720812182741116
+    },
+    {
+      "epoch": 0.8118518518518518,
+      "grad_norm": 1.143888235092163,
+      "learning_rate": 2.0859170782470873e-06,
+      "loss": 0.1209203839302063,
+      "step": 1370,
+      "token_acc": 0.9637912673056444
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.0649224519729614,
+      "learning_rate": 1.961192192583934e-06,
+      "loss": 0.14124363660812378,
+      "step": 1380,
+      "token_acc": 0.9554285714285714
+    },
+    {
+      "epoch": 0.8237037037037037,
+      "grad_norm": 1.3557066917419434,
+      "learning_rate": 1.8399057383087859e-06,
+      "loss": 0.11149574518203735,
+      "step": 1390,
+      "token_acc": 0.9653537563822028
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 1.064666748046875,
+      "learning_rate": 1.7221095931579091e-06,
+      "loss": 0.1278609037399292,
+      "step": 1400,
+      "token_acc": 0.9580903790087464
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.6276605129241943,
+      "learning_rate": 1.6078541419610716e-06,
+      "loss": 0.1316068649291992,
+      "step": 1410,
+      "token_acc": 0.961738484398217
+    },
+    {
+      "epoch": 0.8414814814814815,
+      "grad_norm": 1.0021592378616333,
+      "learning_rate": 1.4971882550904725e-06,
+      "loss": 0.12551895380020142,
+      "step": 1420,
+      "token_acc": 0.9635036496350365
+    },
+    {
+      "epoch": 0.8474074074074074,
+      "grad_norm": 1.2714834213256836,
+      "learning_rate": 1.3901592675574915e-06,
+      "loss": 0.11337714195251465,
+      "step": 1430,
+      "token_acc": 0.9627518053971874
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.2086464166641235,
+      "learning_rate": 1.286812958766106e-06,
+      "loss": 0.1030318260192871,
+      "step": 1440,
+      "token_acc": 0.9690611664295875
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 1.4665285348892212,
+      "learning_rate": 1.1871935329317363e-06,
+      "loss": 0.1136628270149231,
+      "step": 1450,
+      "token_acc": 0.9621955652490004
+    },
+    {
+      "epoch": 0.8651851851851852,
+      "grad_norm": 1.4833930730819702,
+      "learning_rate": 1.0913436001737953e-06,
+      "loss": 0.14109413623809813,
+      "step": 1460,
+      "token_acc": 0.9591619318181818
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.6605064868927002,
+      "learning_rate": 9.993041582901208e-07,
+      "loss": 0.13869184255599976,
+      "step": 1470,
+      "token_acc": 0.9622367465504721
+    },
+    {
+      "epoch": 0.8770370370370371,
+      "grad_norm": 1.142251968383789,
+      "learning_rate": 9.111145752210171e-07,
+      "loss": 0.15464030504226683,
+      "step": 1480,
+      "token_acc": 0.9590840840840841
+    },
+    {
+      "epoch": 0.882962962962963,
+      "grad_norm": 1.4246073961257935,
+      "learning_rate": 8.268125722104569e-07,
+      "loss": 0.137708580493927,
+      "step": 1490,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4238859415054321,
+      "learning_rate": 7.46434207671598e-07,
+      "loss": 0.08925541639328002,
+      "step": 1500,
+      "token_acc": 0.9747899159663865
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.1276273876428604,
+      "eval_runtime": 229.1217,
+      "eval_samples_per_second": 6.547,
+      "eval_steps_per_second": 6.547,
+      "eval_token_acc": 0.9623546851837403,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6017818173586662e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373517452fe5b4afd611e83a428a73a2e60bfea34aa4e86fa640ece3038da43d
+size 7185

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker.model.*\\.(o_proj|k_proj|gate_proj|down_proj|v_proj|up_proj|q_proj)|thinker.audio_tower.proj|thinker.visual.merger.*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1afa8ea4b593f75e66d3a82957fad91222dba43a0f89fc2ee057a3ee4bfc09
+size 81557840

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b7fcbf513203fcbab0d1e8f4b311b6b70369475e9046b63e978c48bac3b881
+size 163345037

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6239986128c5b3633dc0424948128e9f5ea5b332ee9e585be64c0a958313cdc
+size 14645

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceef23c3406c5c7cabde148af9d5d6d9cedd33c1aeefb523c9db929ff154b250
+size 1465

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/trainer_state.json

@@ -0,0 +1,1440 @@
+{
+  "best_global_step": 1688,
+  "best_metric": 0.12758993,
+  "best_model_checkpoint": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688",
+  "epoch": 1.0,
+  "eval_steps": 300,
+  "global_step": 1688,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005925925925925926,
+      "grad_norm": 1.32502019405365,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.38409245014190674,
+      "step": 1,
+      "token_acc": 0.9151943462897526
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 1.348962426185608,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.4804305500454373,
+      "step": 10,
+      "token_acc": 0.8925214548426645
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 1.474541187286377,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 0.4860693454742432,
+      "step": 20,
+      "token_acc": 0.8906647293861242
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5195010900497437,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.4820727348327637,
+      "step": 30,
+      "token_acc": 0.8872207982424021
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 1.5887762308120728,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.4436625957489014,
+      "step": 40,
+      "token_acc": 0.8992023205221175
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 1.7676503658294678,
+      "learning_rate": 5.91715976331361e-06,
+      "loss": 0.473007869720459,
+      "step": 50,
+      "token_acc": 0.8852583586626139
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.005035161972046,
+      "learning_rate": 7.100591715976332e-06,
+      "loss": 0.4192169666290283,
+      "step": 60,
+      "token_acc": 0.8907309721175584
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 1.361005187034607,
+      "learning_rate": 8.284023668639054e-06,
+      "loss": 0.3096126079559326,
+      "step": 70,
+      "token_acc": 0.91939457937346
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 1.3007423877716064,
+      "learning_rate": 9.467455621301776e-06,
+      "loss": 0.28482446670532224,
+      "step": 80,
+      "token_acc": 0.9255202628696605
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7848371863365173,
+      "learning_rate": 1.0650887573964498e-05,
+      "loss": 0.24792802333831787,
+      "step": 90,
+      "token_acc": 0.9363215937388829
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.5432378649711609,
+      "learning_rate": 1.183431952662722e-05,
+      "loss": 0.21306073665618896,
+      "step": 100,
+      "token_acc": 0.9468995010691376
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 0.64493727684021,
+      "learning_rate": 1.3017751479289941e-05,
+      "loss": 0.20164842605590821,
+      "step": 110,
+      "token_acc": 0.9505376344086022
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9089162349700928,
+      "learning_rate": 1.4201183431952663e-05,
+      "loss": 0.22527461051940917,
+      "step": 120,
+      "token_acc": 0.9423220973782771
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 0.9455512762069702,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1824732780456543,
+      "step": 130,
+      "token_acc": 0.9536231884057971
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 0.6021348237991333,
+      "learning_rate": 1.6568047337278108e-05,
+      "loss": 0.18543678522109985,
+      "step": 140,
+      "token_acc": 0.9523099850968704
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8500062227249146,
+      "learning_rate": 1.7751479289940828e-05,
+      "loss": 0.18889259099960326,
+      "step": 150,
+      "token_acc": 0.9432362698120162
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 1.0183658599853516,
+      "learning_rate": 1.8934911242603552e-05,
+      "loss": 0.1937463402748108,
+      "step": 160,
+      "token_acc": 0.9425625920471281
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 0.5574401021003723,
+      "learning_rate": 1.9999978612794268e-05,
+      "loss": 0.16474100351333618,
+      "step": 170,
+      "token_acc": 0.9523260284505959
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7811685800552368,
+      "learning_rate": 1.9997412258797892e-05,
+      "loss": 0.14637688398361207,
+      "step": 180,
+      "token_acc": 0.9594446474241871
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 0.671356737613678,
+      "learning_rate": 1.9990569721450324e-05,
+      "loss": 0.12380313873291016,
+      "step": 190,
+      "token_acc": 0.9659009332376166
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.7796847224235535,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.2040093183517456,
+      "step": 200,
+      "token_acc": 0.9489942528735632
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.0088781118392944,
+      "learning_rate": 1.9964069631504664e-05,
+      "loss": 0.1916598677635193,
+      "step": 210,
+      "token_acc": 0.9477272727272728
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 1.3728845119476318,
+      "learning_rate": 1.994442341376408e-05,
+      "loss": 0.13621771335601807,
+      "step": 220,
+      "token_acc": 0.9564245810055866
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 0.8439155220985413,
+      "learning_rate": 1.9920523677539076e-05,
+      "loss": 0.1574079394340515,
+      "step": 230,
+      "token_acc": 0.9541870071348104
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.2579078674316406,
+      "learning_rate": 1.9892380645440422e-05,
+      "loss": 0.13396313190460205,
+      "step": 240,
+      "token_acc": 0.9584548104956269
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9577816724777222,
+      "learning_rate": 1.9860006355059656e-05,
+      "loss": 0.14859610795974731,
+      "step": 250,
+      "token_acc": 0.9541044776119403
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 1.2375385761260986,
+      "learning_rate": 1.982341465382029e-05,
+      "loss": 0.1562924861907959,
+      "step": 260,
+      "token_acc": 0.9559248554913294
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.978262119305485e-05,
+      "loss": 0.12399486303329468,
+      "step": 270,
+      "token_acc": 0.9662838088180807
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 1.176658272743225,
+      "learning_rate": 1.9737643421310346e-05,
+      "loss": 0.14870967864990234,
+      "step": 280,
+      "token_acc": 0.9565873914684787
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 1.807876706123352,
+      "learning_rate": 1.9688500576885012e-05,
+      "loss": 0.11581240892410279,
+      "step": 290,
+      "token_acc": 0.9647544056992876
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1867674589157104,
+      "learning_rate": 1.9635213679599562e-05,
+      "loss": 0.1393712043762207,
+      "step": 300,
+      "token_acc": 0.9596832253419726
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.1630009412765503,
+      "eval_runtime": 239.7168,
+      "eval_samples_per_second": 6.257,
+      "eval_steps_per_second": 6.257,
+      "eval_token_acc": 0.9527580557072638,
+      "step": 300
+    },
+    {
+      "epoch": 0.1837037037037037,
+      "grad_norm": 1.2620875835418701,
+      "learning_rate": 1.9577805521806358e-05,
+      "loss": 0.1300894260406494,
+      "step": 310,
+      "token_acc": 0.960536398467433
+    },
+    {
+      "epoch": 0.18962962962962962,
+      "grad_norm": 1.1361067295074463,
+      "learning_rate": 1.95163006586405e-05,
+      "loss": 0.16317719221115112,
+      "step": 320,
+      "token_acc": 0.9544095665171899
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.8173150420188904,
+      "learning_rate": 1.945072539751685e-05,
+      "loss": 0.17428743839263916,
+      "step": 330,
+      "token_acc": 0.94750656167979
+    },
+    {
+      "epoch": 0.20148148148148148,
+      "grad_norm": 0.8849798440933228,
+      "learning_rate": 1.93811077868776e-05,
+      "loss": 0.12995322942733764,
+      "step": 340,
+      "token_acc": 0.9658246656760773
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.6326722502708435,
+      "learning_rate": 1.9307477604195162e-05,
+      "loss": 0.1278319001197815,
+      "step": 350,
+      "token_acc": 0.9639468690702088
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.1027580499649048,
+      "learning_rate": 1.9229866343235427e-05,
+      "loss": 0.12902997732162474,
+      "step": 360,
+      "token_acc": 0.9652777777777778
+    },
+    {
+      "epoch": 0.21925925925925926,
+      "grad_norm": 0.7148353457450867,
+      "learning_rate": 1.914830720058701e-05,
+      "loss": 0.14380792379379273,
+      "step": 370,
+      "token_acc": 0.9572490706319703
+    },
+    {
+      "epoch": 0.22518518518518518,
+      "grad_norm": 1.1909170150756836,
+      "learning_rate": 1.9062835061462105e-05,
+      "loss": 0.15708266496658324,
+      "step": 380,
+      "token_acc": 0.9598788796366389
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.7275416254997253,
+      "learning_rate": 1.8973486484775037e-05,
+      "loss": 0.15604959726333617,
+      "step": 390,
+      "token_acc": 0.9558498896247241
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.9419987201690674,
+      "learning_rate": 1.888029968750498e-05,
+      "loss": 0.1431185483932495,
+      "step": 400,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.24296296296296296,
+      "grad_norm": 0.6928850412368774,
+      "learning_rate": 1.878331452834944e-05,
+      "loss": 0.15362846851348877,
+      "step": 410,
+      "token_acc": 0.9517941283073578
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.6290676593780518,
+      "learning_rate": 1.8682572490675524e-05,
+      "loss": 0.12896524667739867,
+      "step": 420,
+      "token_acc": 0.9619504987070557
+    },
+    {
+      "epoch": 0.2548148148148148,
+      "grad_norm": 0.7995588779449463,
+      "learning_rate": 1.8578116664776314e-05,
+      "loss": 0.14157743453979493,
+      "step": 430,
+      "token_acc": 0.9562071591774562
+    },
+    {
+      "epoch": 0.2607407407407407,
+      "grad_norm": 0.780008852481842,
+      "learning_rate": 1.8469991729439888e-05,
+      "loss": 0.16496583223342895,
+      "step": 440,
+      "token_acc": 0.9543109801031687
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8067275881767273,
+      "learning_rate": 1.8358243932838914e-05,
+      "loss": 0.14944461584091187,
+      "step": 450,
+      "token_acc": 0.9509394572025052
+    },
+    {
+      "epoch": 0.2725925925925926,
+      "grad_norm": 0.8212175369262695,
+      "learning_rate": 1.8242921072748948e-05,
+      "loss": 0.12261044979095459,
+      "step": 460,
+      "token_acc": 0.9617764834364761
+    },
+    {
+      "epoch": 0.2785185185185185,
+      "grad_norm": 0.688872754573822,
+      "learning_rate": 1.8124072476103957e-05,
+      "loss": 0.12651515007019043,
+      "step": 470,
+      "token_acc": 0.9594694178334562
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.0954047441482544,
+      "learning_rate": 1.8001748977897754e-05,
+      "loss": 0.11215313673019409,
+      "step": 480,
+      "token_acc": 0.9634851771511207
+    },
+    {
+      "epoch": 0.2903703703703704,
+      "grad_norm": 0.8077743649482727,
+      "learning_rate": 1.787600289944039e-05,
+      "loss": 0.1215265154838562,
+      "step": 490,
+      "token_acc": 0.9642989959092599
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.9279748797416687,
+      "learning_rate": 1.7746888025978807e-05,
+      "loss": 0.11017097234725952,
+      "step": 500,
+      "token_acc": 0.9696060037523452
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.2479947805404663,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.1296389102935791,
+      "step": 510,
+      "token_acc": 0.9566453447050463
+    },
+    {
+      "epoch": 0.30814814814814817,
+      "grad_norm": 1.1002650260925293,
+      "learning_rate": 1.7478774216065882e-05,
+      "loss": 0.13492013216018678,
+      "step": 520,
+      "token_acc": 0.9590994371482177
+    },
+    {
+      "epoch": 0.31407407407407406,
+      "grad_norm": 1.108170747756958,
+      "learning_rate": 1.733988995967179e-05,
+      "loss": 0.14083080291748046,
+      "step": 530,
+      "token_acc": 0.9592061742006616
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8783969879150391,
+      "learning_rate": 1.719786621933599e-05,
+      "loss": 0.12698700428009033,
+      "step": 540,
+      "token_acc": 0.9617927994121969
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.6896427273750305,
+      "learning_rate": 1.70527637427338e-05,
+      "loss": 0.11144465208053589,
+      "step": 550,
+      "token_acc": 0.9692820133234641
+    },
+    {
+      "epoch": 0.33185185185185184,
+      "grad_norm": 1.067499041557312,
+      "learning_rate": 1.690464459440538e-05,
+      "loss": 0.13314462900161744,
+      "step": 560,
+      "token_acc": 0.9597096188747731
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.6953498721122742,
+      "learning_rate": 1.6753572129208935e-05,
+      "loss": 0.11334860324859619,
+      "step": 570,
+      "token_acc": 0.9676190476190476
+    },
+    {
+      "epoch": 0.3437037037037037,
+      "grad_norm": 1.197219967842102,
+      "learning_rate": 1.6599610965222002e-05,
+      "loss": 0.1281804084777832,
+      "step": 580,
+      "token_acc": 0.9607272727272728
+    },
+    {
+      "epoch": 0.3496296296296296,
+      "grad_norm": 0.6708402633666992,
+      "learning_rate": 1.6442826956102424e-05,
+      "loss": 0.12322006225585938,
+      "step": 590,
+      "token_acc": 0.9628704034273474
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.0634019374847412,
+      "learning_rate": 1.628328716292082e-05,
+      "loss": 0.13818006515502929,
+      "step": 600,
+      "token_acc": 0.9580494801003944
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.14249637722969055,
+      "eval_runtime": 229.7535,
+      "eval_samples_per_second": 6.529,
+      "eval_steps_per_second": 6.529,
+      "eval_token_acc": 0.9576734025122884,
+      "step": 600
+    },
+    {
+      "epoch": 0.36148148148148146,
+      "grad_norm": 0.7200868129730225,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.13777921199798585,
+      "step": 610,
+      "token_acc": 0.9565537555228277
+    },
+    {
+      "epoch": 0.3674074074074074,
+      "grad_norm": 1.610889196395874,
+      "learning_rate": 1.595621433310997e-05,
+      "loss": 0.12660154104232788,
+      "step": 620,
+      "token_acc": 0.9658464928387808
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7054650783538818,
+      "learning_rate": 1.5788821195021792e-05,
+      "loss": 0.13561646938323973,
+      "step": 630,
+      "token_acc": 0.9558277654046028
+    },
+    {
+      "epoch": 0.37925925925925924,
+      "grad_norm": 1.4907517433166504,
+      "learning_rate": 1.5618952010115057e-05,
+      "loss": 0.12502728700637816,
+      "step": 640,
+      "token_acc": 0.9623144271031595
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 1.1567004919052124,
+      "learning_rate": 1.544667943636981e-05,
+      "loss": 0.1149907112121582,
+      "step": 650,
+      "token_acc": 0.9643255295429208
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.0321091413497925,
+      "learning_rate": 1.527207715976525e-05,
+      "loss": 0.14286714792251587,
+      "step": 660,
+      "token_acc": 0.9604221635883905
+    },
+    {
+      "epoch": 0.397037037037037,
+      "grad_norm": 1.4016674757003784,
+      "learning_rate": 1.5095219862762091e-05,
+      "loss": 0.13563259840011596,
+      "step": 670,
+      "token_acc": 0.9618029029793735
+    },
+    {
+      "epoch": 0.40296296296296297,
+      "grad_norm": 1.089959979057312,
+      "learning_rate": 1.4916183192358717e-05,
+      "loss": 0.1207580804824829,
+      "step": 680,
+      "token_acc": 0.9630141721396475
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.045990228652954,
+      "learning_rate": 1.4735043727734762e-05,
+      "loss": 0.11743853092193604,
+      "step": 690,
+      "token_acc": 0.9632217727105553
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 1.4252482652664185,
+      "learning_rate": 1.455187894749597e-05,
+      "loss": 0.0928974449634552,
+      "step": 700,
+      "token_acc": 0.9683257918552036
+    },
+    {
+      "epoch": 0.42074074074074075,
+      "grad_norm": 1.1641786098480225,
+      "learning_rate": 1.436676719653435e-05,
+      "loss": 0.12940033674240112,
+      "step": 710,
+      "token_acc": 0.9638252148997135
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.7832347750663757,
+      "learning_rate": 1.4179787652517791e-05,
+      "loss": 0.12433557510375977,
+      "step": 720,
+      "token_acc": 0.9617952522255193
+    },
+    {
+      "epoch": 0.4325925925925926,
+      "grad_norm": 1.1413239240646362,
+      "learning_rate": 1.3991020292023474e-05,
+      "loss": 0.09806026816368103,
+      "step": 730,
+      "token_acc": 0.9669064748201439
+    },
+    {
+      "epoch": 0.43851851851851853,
+      "grad_norm": 0.8681485056877136,
+      "learning_rate": 1.3800545856329572e-05,
+      "loss": 0.14417175054550171,
+      "step": 740,
+      "token_acc": 0.9569114098586694
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.9045178294181824,
+      "learning_rate": 1.3608445816879865e-05,
+      "loss": 0.10493698120117187,
+      "step": 750,
+      "token_acc": 0.9662880175888604
+    },
+    {
+      "epoch": 0.45037037037037037,
+      "grad_norm": 1.1523085832595825,
+      "learning_rate": 1.3414802340436022e-05,
+      "loss": 0.12941417694091797,
+      "step": 760,
+      "token_acc": 0.9683060109289617
+    },
+    {
+      "epoch": 0.4562962962962963,
+      "grad_norm": 0.9145503640174866,
+      "learning_rate": 1.3219698253932518e-05,
+      "loss": 0.12189668416976929,
+      "step": 770,
+      "token_acc": 0.9584711503123852
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.0088993310928345,
+      "learning_rate": 1.3023217009049133e-05,
+      "loss": 0.10943882465362549,
+      "step": 780,
+      "token_acc": 0.9680624556422995
+    },
+    {
+      "epoch": 0.46814814814814815,
+      "grad_norm": 1.376142978668213,
+      "learning_rate": 1.2825442646516253e-05,
+      "loss": 0.10388659238815308,
+      "step": 790,
+      "token_acc": 0.9674435812060673
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.3877886533737183,
+      "learning_rate": 1.262645976016821e-05,
+      "loss": 0.1380447506904602,
+      "step": 800,
+      "token_acc": 0.9608202123764189
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8192164301872253,
+      "learning_rate": 1.2426353460760036e-05,
+      "loss": 0.11965352296829224,
+      "step": 810,
+      "token_acc": 0.9655172413793104
+    },
+    {
+      "epoch": 0.48592592592592593,
+      "grad_norm": 0.8384001851081848,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.09073964357376099,
+      "step": 820,
+      "token_acc": 0.9659477866061293
+    },
+    {
+      "epoch": 0.4918518518518519,
+      "grad_norm": 1.1015766859054565,
+      "learning_rate": 1.2023113431755435e-05,
+      "loss": 0.10787882804870605,
+      "step": 830,
+      "token_acc": 0.9649122807017544
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.042965292930603,
+      "learning_rate": 1.1820152179621564e-05,
+      "loss": 0.13076914548873902,
+      "step": 840,
+      "token_acc": 0.960755275823769
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.8400379419326782,
+      "learning_rate": 1.161641239557907e-05,
+      "loss": 0.13471759557724,
+      "step": 850,
+      "token_acc": 0.9608513873052071
+    },
+    {
+      "epoch": 0.5096296296296297,
+      "grad_norm": 1.0256035327911377,
+      "learning_rate": 1.141198122504618e-05,
+      "loss": 0.11886721849441528,
+      "step": 860,
+      "token_acc": 0.9659887798036466
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.1291937828063965,
+      "learning_rate": 1.1206946109167189e-05,
+      "loss": 0.13678861856460572,
+      "step": 870,
+      "token_acc": 0.961859789320741
+    },
+    {
+      "epoch": 0.5214814814814814,
+      "grad_norm": 1.4508821964263916,
+      "learning_rate": 1.1001394747411347e-05,
+      "loss": 0.13137236833572388,
+      "step": 880,
+      "token_acc": 0.9597744360902256
+    },
+    {
+      "epoch": 0.5274074074074074,
+      "grad_norm": 0.6653353571891785,
+      "learning_rate": 1.0795415060061242e-05,
+      "loss": 0.11796672344207763,
+      "step": 890,
+      "token_acc": 0.9627539503386005
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7665302753448486,
+      "learning_rate": 1.0589095150606747e-05,
+      "loss": 0.14120289087295532,
+      "step": 900,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.1341869980096817,
+      "eval_runtime": 228.3025,
+      "eval_samples_per_second": 6.57,
+      "eval_steps_per_second": 6.57,
+      "eval_token_acc": 0.9593898728251541,
+      "step": 900
+    },
+    {
+      "epoch": 0.5392592592592592,
+      "grad_norm": 1.1279549598693848,
+      "learning_rate": 1.0382523268060612e-05,
+      "loss": 0.11883513927459717,
+      "step": 910,
+      "token_acc": 0.9647756766777902
+    },
+    {
+      "epoch": 0.5451851851851852,
+      "grad_norm": 1.0214804410934448,
+      "learning_rate": 1.0175787769211778e-05,
+      "loss": 0.11933118104934692,
+      "step": 920,
+      "token_acc": 0.959910078681154
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.8586761951446533,
+      "learning_rate": 9.968977080832633e-06,
+      "loss": 0.11430730819702148,
+      "step": 930,
+      "token_acc": 0.9654676258992806
+    },
+    {
+      "epoch": 0.557037037037037,
+      "grad_norm": 0.7968057990074158,
+      "learning_rate": 9.762179661856312e-06,
+      "loss": 0.13973416090011598,
+      "step": 940,
+      "token_acc": 0.9573529411764706
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 1.0118746757507324,
+      "learning_rate": 9.555483965540238e-06,
+      "loss": 0.12812395095825196,
+      "step": 950,
+      "token_acc": 0.9614254224834681
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.1432191133499146,
+      "learning_rate": 9.348978401632101e-06,
+      "loss": 0.1379111647605896,
+      "step": 960,
+      "token_acc": 0.9561209439528023
+    },
+    {
+      "epoch": 0.5748148148148148,
+      "grad_norm": 0.7802894115447998,
+      "learning_rate": 9.142751298554436e-06,
+      "loss": 0.14111405611038208,
+      "step": 970,
+      "token_acc": 0.9607002500893176
+    },
+    {
+      "epoch": 0.5807407407407408,
+      "grad_norm": 0.741787314414978,
+      "learning_rate": 8.936890865624014e-06,
+      "loss": 0.10649667978286743,
+      "step": 980,
+      "token_acc": 0.9672929714683368
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.7642576694488525,
+      "learning_rate": 8.731485155322134e-06,
+      "loss": 0.10067906379699706,
+      "step": 990,
+      "token_acc": 0.9700443786982249
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 1.0362651348114014,
+      "learning_rate": 8.52662202563203e-06,
+      "loss": 0.12069357633590698,
+      "step": 1000,
+      "token_acc": 0.9607771260997068
+    },
+    {
+      "epoch": 0.5985185185185186,
+      "grad_norm": 0.7719289064407349,
+      "learning_rate": 8.322389102459458e-06,
+      "loss": 0.11699739694595337,
+      "step": 1010,
+      "token_acc": 0.9636767976278725
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.143441081047058,
+      "learning_rate": 8.118873742152574e-06,
+      "loss": 0.12428475618362426,
+      "step": 1020,
+      "token_acc": 0.9612553273924835
+    },
+    {
+      "epoch": 0.6103703703703703,
+      "grad_norm": 0.7593462467193604,
+      "learning_rate": 7.916162994137056e-06,
+      "loss": 0.114216148853302,
+      "step": 1030,
+      "token_acc": 0.9674105561459441
+    },
+    {
+      "epoch": 0.6162962962962963,
+      "grad_norm": 0.9898127317428589,
+      "learning_rate": 7.714343563682565e-06,
+      "loss": 0.12711145877838134,
+      "step": 1040,
+      "token_acc": 0.9625998547567175
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.3860629796981812,
+      "learning_rate": 7.513501774816362e-06,
+      "loss": 0.14218902587890625,
+      "step": 1050,
+      "token_acc": 0.9609863820390137
+    },
+    {
+      "epoch": 0.6281481481481481,
+      "grad_norm": 0.7516865134239197,
+      "learning_rate": 7.313723533400047e-06,
+      "loss": 0.1154281735420227,
+      "step": 1060,
+      "token_acc": 0.965135769359705
+    },
+    {
+      "epoch": 0.6340740740740741,
+      "grad_norm": 1.0139286518096924,
+      "learning_rate": 7.115094290385103e-06,
+      "loss": 0.12470541000366211,
+      "step": 1070,
+      "token_acc": 0.9648382559774965
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0060116052627563,
+      "learning_rate": 6.9176990052630465e-06,
+      "loss": 0.1165156364440918,
+      "step": 1080,
+      "token_acc": 0.9641779788838613
+    },
+    {
+      "epoch": 0.6459259259259259,
+      "grad_norm": 1.437506079673767,
+      "learning_rate": 6.721622109725799e-06,
+      "loss": 0.128699791431427,
+      "step": 1090,
+      "token_acc": 0.9611650485436893
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 1.0488654375076294,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.14162105321884155,
+      "step": 1100,
+      "token_acc": 0.9533483822422875
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.9438616633415222,
+      "learning_rate": 6.333758358733313e-06,
+      "loss": 0.14174394607543944,
+      "step": 1110,
+      "token_acc": 0.9583492548719909
+    },
+    {
+      "epoch": 0.6637037037037037,
+      "grad_norm": 1.2012673616409302,
+      "learning_rate": 6.142137403860301e-06,
+      "loss": 0.14388898611068726,
+      "step": 1120,
+      "token_acc": 0.9564558879212419
+    },
+    {
+      "epoch": 0.6696296296296296,
+      "grad_norm": 1.1282634735107422,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.11517893075942993,
+      "step": 1130,
+      "token_acc": 0.9685185185185186
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.8449248671531677,
+      "learning_rate": 5.763927109519784e-06,
+      "loss": 0.08853521943092346,
+      "step": 1140,
+      "token_acc": 0.9759211966435607
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.9580397009849548,
+      "learning_rate": 5.577499541570954e-06,
+      "loss": 0.14078164100646973,
+      "step": 1150,
+      "token_acc": 0.9634651600753296
+    },
+    {
+      "epoch": 0.6874074074074074,
+      "grad_norm": 0.7772520184516907,
+      "learning_rate": 5.3929636054105745e-06,
+      "loss": 0.10377205610275268,
+      "step": 1160,
+      "token_acc": 0.9701709712622771
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.3566169738769531,
+      "learning_rate": 5.210398232413824e-06,
+      "loss": 0.1568630576133728,
+      "step": 1170,
+      "token_acc": 0.9556422995031938
+    },
+    {
+      "epoch": 0.6992592592592592,
+      "grad_norm": 0.9245796203613281,
+      "learning_rate": 5.0298815110888566e-06,
+      "loss": 0.14888057708740235,
+      "step": 1180,
+      "token_acc": 0.9563852058618283
+    },
+    {
+      "epoch": 0.7051851851851851,
+      "grad_norm": 1.0345977544784546,
+      "learning_rate": 4.851490653676019e-06,
+      "loss": 0.1214102029800415,
+      "step": 1190,
+      "token_acc": 0.9646017699115044
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.1635781526565552,
+      "learning_rate": 4.675301963121998e-06,
+      "loss": 0.12966567277908325,
+      "step": 1200,
+      "token_acc": 0.9577946768060837
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.12971985340118408,
+      "eval_runtime": 229.3094,
+      "eval_samples_per_second": 6.541,
+      "eval_steps_per_second": 6.541,
+      "eval_token_acc": 0.9621596317390965,
+      "step": 1200
+    },
+    {
+      "epoch": 0.717037037037037,
+      "grad_norm": 0.6507232785224915,
+      "learning_rate": 4.501390800442783e-06,
+      "loss": 0.12880181074142455,
+      "step": 1210,
+      "token_acc": 0.9664481295796374
+    },
+    {
+      "epoch": 0.7229629629629629,
+      "grad_norm": 0.9675179123878479,
+      "learning_rate": 4.329831552489626e-06,
+      "loss": 0.12247174978256226,
+      "step": 1220,
+      "token_acc": 0.9622926093514329
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.9841185808181763,
+      "learning_rate": 4.160697600131568e-06,
+      "loss": 0.12777591943740846,
+      "step": 1230,
+      "token_acc": 0.9612147822905233
+    },
+    {
+      "epoch": 0.7348148148148148,
+      "grad_norm": 1.4565831422805786,
+      "learning_rate": 3.994061286868361e-06,
+      "loss": 0.13893853425979613,
+      "step": 1240,
+      "token_acc": 0.9622920517560074
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.1277369260787964,
+      "learning_rate": 3.8299938878870215e-06,
+      "loss": 0.09945087432861328,
+      "step": 1250,
+      "token_acc": 0.965828013518588
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.1658375263214111,
+      "learning_rate": 3.6685655795753836e-06,
+      "loss": 0.08901865482330322,
+      "step": 1260,
+      "token_acc": 0.9718995878606219
+    },
+    {
+      "epoch": 0.7525925925925926,
+      "grad_norm": 1.2467801570892334,
+      "learning_rate": 3.50984540950562e-06,
+      "loss": 0.12474504709243775,
+      "step": 1270,
+      "token_acc": 0.9593131765584173
+    },
+    {
+      "epoch": 0.7585185185185185,
+      "grad_norm": 1.2965892553329468,
+      "learning_rate": 3.3539012669005653e-06,
+      "loss": 0.12159136533737183,
+      "step": 1280,
+      "token_acc": 0.961352657004831
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.1689339876174927,
+      "learning_rate": 3.2007998535955774e-06,
+      "loss": 0.1344360113143921,
+      "step": 1290,
+      "token_acc": 0.9594349873234336
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.7894589304924011,
+      "learning_rate": 3.0506066555081683e-06,
+      "loss": 0.12788604497909545,
+      "step": 1300,
+      "token_acc": 0.963855421686747
+    },
+    {
+      "epoch": 0.7762962962962963,
+      "grad_norm": 1.2829697132110596,
+      "learning_rate": 2.90338591462782e-06,
+      "loss": 0.11962369680404664,
+      "step": 1310,
+      "token_acc": 0.9604395604395605
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.1379469633102417,
+      "learning_rate": 2.7592006015377937e-06,
+      "loss": 0.11098712682723999,
+      "step": 1320,
+      "token_acc": 0.9649507119386638
+    },
+    {
+      "epoch": 0.7881481481481482,
+      "grad_norm": 1.723992109298706,
+      "learning_rate": 2.6181123884808056e-06,
+      "loss": 0.13792314529418945,
+      "step": 1330,
+      "token_acc": 0.9560761346998536
+    },
+    {
+      "epoch": 0.794074074074074,
+      "grad_norm": 1.1304504871368408,
+      "learning_rate": 2.480181622980009e-06,
+      "loss": 0.10700693130493164,
+      "step": 1340,
+      "token_acc": 0.9640314724615962
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3609181642532349,
+      "learning_rate": 2.3454673020265973e-06,
+      "loss": 0.11214718818664551,
+      "step": 1350,
+      "token_acc": 0.967559411542814
+    },
+    {
+      "epoch": 0.8059259259259259,
+      "grad_norm": 0.7761492133140564,
+      "learning_rate": 2.2140270468450966e-06,
+      "loss": 0.09663894772529602,
+      "step": 1360,
+      "token_acc": 0.9720812182741116
+    },
+    {
+      "epoch": 0.8118518518518518,
+      "grad_norm": 1.143888235092163,
+      "learning_rate": 2.0859170782470873e-06,
+      "loss": 0.1209203839302063,
+      "step": 1370,
+      "token_acc": 0.9637912673056444
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.0649224519729614,
+      "learning_rate": 1.961192192583934e-06,
+      "loss": 0.14124363660812378,
+      "step": 1380,
+      "token_acc": 0.9554285714285714
+    },
+    {
+      "epoch": 0.8237037037037037,
+      "grad_norm": 1.3557066917419434,
+      "learning_rate": 1.8399057383087859e-06,
+      "loss": 0.11149574518203735,
+      "step": 1390,
+      "token_acc": 0.9653537563822028
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 1.064666748046875,
+      "learning_rate": 1.7221095931579091e-06,
+      "loss": 0.1278609037399292,
+      "step": 1400,
+      "token_acc": 0.9580903790087464
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.6276605129241943,
+      "learning_rate": 1.6078541419610716e-06,
+      "loss": 0.1316068649291992,
+      "step": 1410,
+      "token_acc": 0.961738484398217
+    },
+    {
+      "epoch": 0.8414814814814815,
+      "grad_norm": 1.0021592378616333,
+      "learning_rate": 1.4971882550904725e-06,
+      "loss": 0.12551895380020142,
+      "step": 1420,
+      "token_acc": 0.9635036496350365
+    },
+    {
+      "epoch": 0.8474074074074074,
+      "grad_norm": 1.2714834213256836,
+      "learning_rate": 1.3901592675574915e-06,
+      "loss": 0.11337714195251465,
+      "step": 1430,
+      "token_acc": 0.9627518053971874
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.2086464166641235,
+      "learning_rate": 1.286812958766106e-06,
+      "loss": 0.1030318260192871,
+      "step": 1440,
+      "token_acc": 0.9690611664295875
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 1.4665285348892212,
+      "learning_rate": 1.1871935329317363e-06,
+      "loss": 0.1136628270149231,
+      "step": 1450,
+      "token_acc": 0.9621955652490004
+    },
+    {
+      "epoch": 0.8651851851851852,
+      "grad_norm": 1.4833930730819702,
+      "learning_rate": 1.0913436001737953e-06,
+      "loss": 0.14109413623809813,
+      "step": 1460,
+      "token_acc": 0.9591619318181818
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.6605064868927002,
+      "learning_rate": 9.993041582901208e-07,
+      "loss": 0.13869184255599976,
+      "step": 1470,
+      "token_acc": 0.9622367465504721
+    },
+    {
+      "epoch": 0.8770370370370371,
+      "grad_norm": 1.142251968383789,
+      "learning_rate": 9.111145752210171e-07,
+      "loss": 0.15464030504226683,
+      "step": 1480,
+      "token_acc": 0.9590840840840841
+    },
+    {
+      "epoch": 0.882962962962963,
+      "grad_norm": 1.4246073961257935,
+      "learning_rate": 8.268125722104569e-07,
+      "loss": 0.137708580493927,
+      "step": 1490,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4238859415054321,
+      "learning_rate": 7.46434207671598e-07,
+      "loss": 0.08925541639328002,
+      "step": 1500,
+      "token_acc": 0.9747899159663865
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.1276273876428604,
+      "eval_runtime": 229.1217,
+      "eval_samples_per_second": 6.547,
+      "eval_steps_per_second": 6.547,
+      "eval_token_acc": 0.9623546851837403,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8948148148148148,
+      "grad_norm": 1.1456782817840576,
+      "learning_rate": 6.700138617635577e-07,
+      "loss": 0.12536653280258178,
+      "step": 1510,
+      "token_acc": 0.9648377125193199
+    },
+    {
+      "epoch": 0.9007407407407407,
+      "grad_norm": 0.5869998931884766,
+      "learning_rate": 5.975842216860239e-07,
+      "loss": 0.11909486055374145,
+      "step": 1520,
+      "token_acc": 0.9651647103369936
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.8277629613876343,
+      "learning_rate": 5.291762676979917e-07,
+      "loss": 0.10322866439819336,
+      "step": 1530,
+      "token_acc": 0.9698861549761293
+    },
+    {
+      "epoch": 0.9125925925925926,
+      "grad_norm": 1.0630172491073608,
+      "learning_rate": 4.648192598666013e-07,
+      "loss": 0.1228654146194458,
+      "step": 1540,
+      "token_acc": 0.9670886075949368
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 0.8849966526031494,
+      "learning_rate": 4.0454072555176195e-07,
+      "loss": 0.08263896107673645,
+      "step": 1550,
+      "token_acc": 0.9724354501046755
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.4644533395767212,
+      "learning_rate": 3.4836644763190264e-07,
+      "loss": 0.10929735898971557,
+      "step": 1560,
+      "token_acc": 0.9660516605166052
+    },
+    {
+      "epoch": 0.9303703703703704,
+      "grad_norm": 1.3451666831970215,
+      "learning_rate": 2.9632045347588566e-07,
+      "loss": 0.0930831789970398,
+      "step": 1570,
+      "token_acc": 0.967948717948718
+    },
+    {
+      "epoch": 0.9362962962962963,
+      "grad_norm": 0.6276125907897949,
+      "learning_rate": 2.484250046658054e-07,
+      "loss": 0.0964022159576416,
+      "step": 1580,
+      "token_acc": 0.9702295552367288
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.964272141456604,
+      "learning_rate": 2.0470058747505516e-07,
+      "loss": 0.12160607576370239,
+      "step": 1590,
+      "token_acc": 0.961283571677712
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 1.202038049697876,
+      "learning_rate": 1.6516590410576628e-07,
+      "loss": 0.11407674551010132,
+      "step": 1600,
+      "token_acc": 0.9619465788510794
+    },
+    {
+      "epoch": 0.9540740740740741,
+      "grad_norm": 1.0892561674118042,
+      "learning_rate": 1.2983786468932503e-07,
+      "loss": 0.12073925733566285,
+      "step": 1610,
+      "token_acc": 0.962109955423477
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3103691339492798,
+      "learning_rate": 9.873158005341943e-08,
+      "loss": 0.10570030212402344,
+      "step": 1620,
+      "token_acc": 0.9626497533474278
+    },
+    {
+      "epoch": 0.965925925925926,
+      "grad_norm": 0.9008719325065613,
+      "learning_rate": 7.186035525870272e-08,
+      "loss": 0.1048168420791626,
+      "step": 1630,
+      "token_acc": 0.9678002894356006
+    },
+    {
+      "epoch": 0.9718518518518519,
+      "grad_norm": 1.2709956169128418,
+      "learning_rate": 4.9235683907833396e-08,
+      "loss": 0.16029913425445558,
+      "step": 1640,
+      "token_acc": 0.956964892412231
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.142215371131897,
+      "learning_rate": 3.086724322932111e-08,
+      "loss": 0.10578294992446899,
+      "step": 1650,
+      "token_acc": 0.9671545876472688
+    },
+    {
+      "epoch": 0.9837037037037037,
+      "grad_norm": 1.015450119972229,
+      "learning_rate": 1.6762889938303216e-08,
+      "loss": 0.1220880389213562,
+      "step": 1660,
+      "token_acc": 0.9671361502347418
+    },
+    {
+      "epoch": 0.9896296296296296,
+      "grad_norm": 1.1465100049972534,
+      "learning_rate": 6.928656875994089e-09,
+      "loss": 0.12359803915023804,
+      "step": 1670,
+      "token_acc": 0.963089802130898
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.6673016548156738,
+      "learning_rate": 1.3687504292692055e-09,
+      "loss": 0.10396100282669067,
+      "step": 1680,
+      "token_acc": 0.9718817591925017
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.12758992612361908,
+      "eval_runtime": 231.1684,
+      "eval_samples_per_second": 6.489,
+      "eval_steps_per_second": 6.489,
+      "eval_token_acc": 0.9622766638058828,
+      "step": 1688
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.929447543828032e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-1688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373517452fe5b4afd611e83a428a73a2e60bfea34aa4e86fa640ece3038da43d
+size 7185

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker.model.*\\.(o_proj|k_proj|gate_proj|down_proj|v_proj|up_proj|q_proj)|thinker.audio_tower.proj|thinker.visual.merger.*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf5a48e521068993dd9da41d132a20974d5753e5313eee444319810f5f61757
+size 81557840

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68b18e5461252104174f929b4449a4f5b8945111bfda257b87b0dd186045418
+size 163345037

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842daffb645025b02820ebabb2155b6b142a63dc5f33939702b9b825dcf03589
+size 14645

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389f1187d2ea46f74eb31cb122f8387456383583ccc859272cc9a99b01de23c3
+size 1465

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_global_step": 300,
+  "best_metric": 0.16300094,
+  "best_model_checkpoint": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300",
+  "epoch": 0.17777777777777778,
+  "eval_steps": 300,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005925925925925926,
+      "grad_norm": 1.32502019405365,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.38409245014190674,
+      "step": 1,
+      "token_acc": 0.9151943462897526
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 1.348962426185608,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.4804305500454373,
+      "step": 10,
+      "token_acc": 0.8925214548426645
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 1.474541187286377,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 0.4860693454742432,
+      "step": 20,
+      "token_acc": 0.8906647293861242
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5195010900497437,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.4820727348327637,
+      "step": 30,
+      "token_acc": 0.8872207982424021
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 1.5887762308120728,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.4436625957489014,
+      "step": 40,
+      "token_acc": 0.8992023205221175
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 1.7676503658294678,
+      "learning_rate": 5.91715976331361e-06,
+      "loss": 0.473007869720459,
+      "step": 50,
+      "token_acc": 0.8852583586626139
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.005035161972046,
+      "learning_rate": 7.100591715976332e-06,
+      "loss": 0.4192169666290283,
+      "step": 60,
+      "token_acc": 0.8907309721175584
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 1.361005187034607,
+      "learning_rate": 8.284023668639054e-06,
+      "loss": 0.3096126079559326,
+      "step": 70,
+      "token_acc": 0.91939457937346
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 1.3007423877716064,
+      "learning_rate": 9.467455621301776e-06,
+      "loss": 0.28482446670532224,
+      "step": 80,
+      "token_acc": 0.9255202628696605
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7848371863365173,
+      "learning_rate": 1.0650887573964498e-05,
+      "loss": 0.24792802333831787,
+      "step": 90,
+      "token_acc": 0.9363215937388829
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.5432378649711609,
+      "learning_rate": 1.183431952662722e-05,
+      "loss": 0.21306073665618896,
+      "step": 100,
+      "token_acc": 0.9468995010691376
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 0.64493727684021,
+      "learning_rate": 1.3017751479289941e-05,
+      "loss": 0.20164842605590821,
+      "step": 110,
+      "token_acc": 0.9505376344086022
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9089162349700928,
+      "learning_rate": 1.4201183431952663e-05,
+      "loss": 0.22527461051940917,
+      "step": 120,
+      "token_acc": 0.9423220973782771
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 0.9455512762069702,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1824732780456543,
+      "step": 130,
+      "token_acc": 0.9536231884057971
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 0.6021348237991333,
+      "learning_rate": 1.6568047337278108e-05,
+      "loss": 0.18543678522109985,
+      "step": 140,
+      "token_acc": 0.9523099850968704
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8500062227249146,
+      "learning_rate": 1.7751479289940828e-05,
+      "loss": 0.18889259099960326,
+      "step": 150,
+      "token_acc": 0.9432362698120162
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 1.0183658599853516,
+      "learning_rate": 1.8934911242603552e-05,
+      "loss": 0.1937463402748108,
+      "step": 160,
+      "token_acc": 0.9425625920471281
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 0.5574401021003723,
+      "learning_rate": 1.9999978612794268e-05,
+      "loss": 0.16474100351333618,
+      "step": 170,
+      "token_acc": 0.9523260284505959
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7811685800552368,
+      "learning_rate": 1.9997412258797892e-05,
+      "loss": 0.14637688398361207,
+      "step": 180,
+      "token_acc": 0.9594446474241871
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 0.671356737613678,
+      "learning_rate": 1.9990569721450324e-05,
+      "loss": 0.12380313873291016,
+      "step": 190,
+      "token_acc": 0.9659009332376166
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.7796847224235535,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.2040093183517456,
+      "step": 200,
+      "token_acc": 0.9489942528735632
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.0088781118392944,
+      "learning_rate": 1.9964069631504664e-05,
+      "loss": 0.1916598677635193,
+      "step": 210,
+      "token_acc": 0.9477272727272728
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 1.3728845119476318,
+      "learning_rate": 1.994442341376408e-05,
+      "loss": 0.13621771335601807,
+      "step": 220,
+      "token_acc": 0.9564245810055866
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 0.8439155220985413,
+      "learning_rate": 1.9920523677539076e-05,
+      "loss": 0.1574079394340515,
+      "step": 230,
+      "token_acc": 0.9541870071348104
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.2579078674316406,
+      "learning_rate": 1.9892380645440422e-05,
+      "loss": 0.13396313190460205,
+      "step": 240,
+      "token_acc": 0.9584548104956269
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9577816724777222,
+      "learning_rate": 1.9860006355059656e-05,
+      "loss": 0.14859610795974731,
+      "step": 250,
+      "token_acc": 0.9541044776119403
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 1.2375385761260986,
+      "learning_rate": 1.982341465382029e-05,
+      "loss": 0.1562924861907959,
+      "step": 260,
+      "token_acc": 0.9559248554913294
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.978262119305485e-05,
+      "loss": 0.12399486303329468,
+      "step": 270,
+      "token_acc": 0.9662838088180807
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 1.176658272743225,
+      "learning_rate": 1.9737643421310346e-05,
+      "loss": 0.14870967864990234,
+      "step": 280,
+      "token_acc": 0.9565873914684787
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 1.807876706123352,
+      "learning_rate": 1.9688500576885012e-05,
+      "loss": 0.11581240892410279,
+      "step": 290,
+      "token_acc": 0.9647544056992876
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1867674589157104,
+      "learning_rate": 1.9635213679599562e-05,
+      "loss": 0.1393712043762207,
+      "step": 300,
+      "token_acc": 0.9596832253419726
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.1630009412765503,
+      "eval_runtime": 239.7168,
+      "eval_samples_per_second": 6.257,
+      "eval_steps_per_second": 6.257,
+      "eval_token_acc": 0.9527580557072638,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.192901387485568e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373517452fe5b4afd611e83a428a73a2e60bfea34aa4e86fa640ece3038da43d
+size 7185

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker.model.*\\.(o_proj|k_proj|gate_proj|down_proj|v_proj|up_proj|q_proj)|thinker.audio_tower.proj|thinker.visual.merger.*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47a3eb420fb0eaa8ddb10cb1fd3a2d83a1295e18530d83c3cee18d57759a567
+size 81557840

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/args.json

@@ -0,0 +1,345 @@
+{
+  "output_dir": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639",
+  "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": 1,
+  "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": 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": "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": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 300.0,
+  "save_total_limit": 20,
+  "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": -1,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": null,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": null,
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": 2e-05,
+  "vit_lr": 1e-05,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-Omni-7B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "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": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_train90.jsonl"
+  ],
+  "val_dataset": [
+    "/workspace/intern/pangkaiyu/dg/out_scenes/far_field_val5.jsonl"
+  ],
+  "split_dataset_ratio": 0.0,
+  "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": 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": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "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": false,
+  "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,
+  "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": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen2.5-Omni-7B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B', 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, 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fafd355e830>, 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'], 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=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-Omni-7B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639', 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=16, 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=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=20, 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=300, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1', 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=None, 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=['wandb'], 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=2e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, 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, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm')"
+}

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971b96994930a38e0dd79cfc4d1052170ff709d9c16e5862eda4d7aed978f207
+size 163345037

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc843956e5df2dfce2e865b93d72500f141c62d6949cb4b4f897ca2fd8826c50
+size 14645

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7628f6a28d4d606e1b4a4bc8623e5399d9a39373321dfb196f921da21d6070b7
+size 1465

output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600/trainer_state.json

@@ -0,0 +1,540 @@
+{
+  "best_global_step": 600,
+  "best_metric": 0.14249638,
+  "best_model_checkpoint": "/workspace/intern/pangkaiyu/dg/output_omni7B-LLM-aligner-ff-lora-1gpu-save300_linear1/v0-20251213-110639/checkpoint-600",
+  "epoch": 0.35555555555555557,
+  "eval_steps": 300,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005925925925925926,
+      "grad_norm": 1.32502019405365,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.38409245014190674,
+      "step": 1,
+      "token_acc": 0.9151943462897526
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 1.348962426185608,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.4804305500454373,
+      "step": 10,
+      "token_acc": 0.8925214548426645
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 1.474541187286377,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 0.4860693454742432,
+      "step": 20,
+      "token_acc": 0.8906647293861242
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5195010900497437,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.4820727348327637,
+      "step": 30,
+      "token_acc": 0.8872207982424021
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 1.5887762308120728,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.4436625957489014,
+      "step": 40,
+      "token_acc": 0.8992023205221175
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 1.7676503658294678,
+      "learning_rate": 5.91715976331361e-06,
+      "loss": 0.473007869720459,
+      "step": 50,
+      "token_acc": 0.8852583586626139
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.005035161972046,
+      "learning_rate": 7.100591715976332e-06,
+      "loss": 0.4192169666290283,
+      "step": 60,
+      "token_acc": 0.8907309721175584
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 1.361005187034607,
+      "learning_rate": 8.284023668639054e-06,
+      "loss": 0.3096126079559326,
+      "step": 70,
+      "token_acc": 0.91939457937346
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 1.3007423877716064,
+      "learning_rate": 9.467455621301776e-06,
+      "loss": 0.28482446670532224,
+      "step": 80,
+      "token_acc": 0.9255202628696605
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7848371863365173,
+      "learning_rate": 1.0650887573964498e-05,
+      "loss": 0.24792802333831787,
+      "step": 90,
+      "token_acc": 0.9363215937388829
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.5432378649711609,
+      "learning_rate": 1.183431952662722e-05,
+      "loss": 0.21306073665618896,
+      "step": 100,
+      "token_acc": 0.9468995010691376
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 0.64493727684021,
+      "learning_rate": 1.3017751479289941e-05,
+      "loss": 0.20164842605590821,
+      "step": 110,
+      "token_acc": 0.9505376344086022
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9089162349700928,
+      "learning_rate": 1.4201183431952663e-05,
+      "loss": 0.22527461051940917,
+      "step": 120,
+      "token_acc": 0.9423220973782771
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 0.9455512762069702,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1824732780456543,
+      "step": 130,
+      "token_acc": 0.9536231884057971
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 0.6021348237991333,
+      "learning_rate": 1.6568047337278108e-05,
+      "loss": 0.18543678522109985,
+      "step": 140,
+      "token_acc": 0.9523099850968704
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8500062227249146,
+      "learning_rate": 1.7751479289940828e-05,
+      "loss": 0.18889259099960326,
+      "step": 150,
+      "token_acc": 0.9432362698120162
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 1.0183658599853516,
+      "learning_rate": 1.8934911242603552e-05,
+      "loss": 0.1937463402748108,
+      "step": 160,
+      "token_acc": 0.9425625920471281
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 0.5574401021003723,
+      "learning_rate": 1.9999978612794268e-05,
+      "loss": 0.16474100351333618,
+      "step": 170,
+      "token_acc": 0.9523260284505959
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7811685800552368,
+      "learning_rate": 1.9997412258797892e-05,
+      "loss": 0.14637688398361207,
+      "step": 180,
+      "token_acc": 0.9594446474241871
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 0.671356737613678,
+      "learning_rate": 1.9990569721450324e-05,
+      "loss": 0.12380313873291016,
+      "step": 190,
+      "token_acc": 0.9659009332376166
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.7796847224235535,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.2040093183517456,
+      "step": 200,
+      "token_acc": 0.9489942528735632
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.0088781118392944,
+      "learning_rate": 1.9964069631504664e-05,
+      "loss": 0.1916598677635193,
+      "step": 210,
+      "token_acc": 0.9477272727272728
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 1.3728845119476318,
+      "learning_rate": 1.994442341376408e-05,
+      "loss": 0.13621771335601807,
+      "step": 220,
+      "token_acc": 0.9564245810055866
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 0.8439155220985413,
+      "learning_rate": 1.9920523677539076e-05,
+      "loss": 0.1574079394340515,
+      "step": 230,
+      "token_acc": 0.9541870071348104
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.2579078674316406,
+      "learning_rate": 1.9892380645440422e-05,
+      "loss": 0.13396313190460205,
+      "step": 240,
+      "token_acc": 0.9584548104956269
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9577816724777222,
+      "learning_rate": 1.9860006355059656e-05,
+      "loss": 0.14859610795974731,
+      "step": 250,
+      "token_acc": 0.9541044776119403
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 1.2375385761260986,
+      "learning_rate": 1.982341465382029e-05,
+      "loss": 0.1562924861907959,
+      "step": 260,
+      "token_acc": 0.9559248554913294
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.978262119305485e-05,
+      "loss": 0.12399486303329468,
+      "step": 270,
+      "token_acc": 0.9662838088180807
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 1.176658272743225,
+      "learning_rate": 1.9737643421310346e-05,
+      "loss": 0.14870967864990234,
+      "step": 280,
+      "token_acc": 0.9565873914684787
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 1.807876706123352,
+      "learning_rate": 1.9688500576885012e-05,
+      "loss": 0.11581240892410279,
+      "step": 290,
+      "token_acc": 0.9647544056992876
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1867674589157104,
+      "learning_rate": 1.9635213679599562e-05,
+      "loss": 0.1393712043762207,
+      "step": 300,
+      "token_acc": 0.9596832253419726
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.1630009412765503,
+      "eval_runtime": 239.7168,
+      "eval_samples_per_second": 6.257,
+      "eval_steps_per_second": 6.257,
+      "eval_token_acc": 0.9527580557072638,
+      "step": 300
+    },
+    {
+      "epoch": 0.1837037037037037,
+      "grad_norm": 1.2620875835418701,
+      "learning_rate": 1.9577805521806358e-05,
+      "loss": 0.1300894260406494,
+      "step": 310,
+      "token_acc": 0.960536398467433
+    },
+    {
+      "epoch": 0.18962962962962962,
+      "grad_norm": 1.1361067295074463,
+      "learning_rate": 1.95163006586405e-05,
+      "loss": 0.16317719221115112,
+      "step": 320,
+      "token_acc": 0.9544095665171899
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.8173150420188904,
+      "learning_rate": 1.945072539751685e-05,
+      "loss": 0.17428743839263916,
+      "step": 330,
+      "token_acc": 0.94750656167979
+    },
+    {
+      "epoch": 0.20148148148148148,
+      "grad_norm": 0.8849798440933228,
+      "learning_rate": 1.93811077868776e-05,
+      "loss": 0.12995322942733764,
+      "step": 340,
+      "token_acc": 0.9658246656760773
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.6326722502708435,
+      "learning_rate": 1.9307477604195162e-05,
+      "loss": 0.1278319001197815,
+      "step": 350,
+      "token_acc": 0.9639468690702088
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.1027580499649048,
+      "learning_rate": 1.9229866343235427e-05,
+      "loss": 0.12902997732162474,
+      "step": 360,
+      "token_acc": 0.9652777777777778
+    },
+    {
+      "epoch": 0.21925925925925926,
+      "grad_norm": 0.7148353457450867,
+      "learning_rate": 1.914830720058701e-05,
+      "loss": 0.14380792379379273,
+      "step": 370,
+      "token_acc": 0.9572490706319703
+    },
+    {
+      "epoch": 0.22518518518518518,
+      "grad_norm": 1.1909170150756836,
+      "learning_rate": 1.9062835061462105e-05,
+      "loss": 0.15708266496658324,
+      "step": 380,
+      "token_acc": 0.9598788796366389
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.7275416254997253,
+      "learning_rate": 1.8973486484775037e-05,
+      "loss": 0.15604959726333617,
+      "step": 390,
+      "token_acc": 0.9558498896247241
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.9419987201690674,
+      "learning_rate": 1.888029968750498e-05,
+      "loss": 0.1431185483932495,
+      "step": 400,
+      "token_acc": 0.9590773809523809
+    },
+    {
+      "epoch": 0.24296296296296296,
+      "grad_norm": 0.6928850412368774,
+      "learning_rate": 1.878331452834944e-05,
+      "loss": 0.15362846851348877,
+      "step": 410,
+      "token_acc": 0.9517941283073578
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.6290676593780518,
+      "learning_rate": 1.8682572490675524e-05,
+      "loss": 0.12896524667739867,
+      "step": 420,
+      "token_acc": 0.9619504987070557
+    },
+    {
+      "epoch": 0.2548148148148148,
+      "grad_norm": 0.7995588779449463,
+      "learning_rate": 1.8578116664776314e-05,
+      "loss": 0.14157743453979493,
+      "step": 430,
+      "token_acc": 0.9562071591774562
+    },
+    {
+      "epoch": 0.2607407407407407,
+      "grad_norm": 0.780008852481842,
+      "learning_rate": 1.8469991729439888e-05,
+      "loss": 0.16496583223342895,
+      "step": 440,
+      "token_acc": 0.9543109801031687
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8067275881767273,
+      "learning_rate": 1.8358243932838914e-05,
+      "loss": 0.14944461584091187,
+      "step": 450,
+      "token_acc": 0.9509394572025052
+    },
+    {
+      "epoch": 0.2725925925925926,
+      "grad_norm": 0.8212175369262695,
+      "learning_rate": 1.8242921072748948e-05,
+      "loss": 0.12261044979095459,
+      "step": 460,
+      "token_acc": 0.9617764834364761
+    },
+    {
+      "epoch": 0.2785185185185185,
+      "grad_norm": 0.688872754573822,
+      "learning_rate": 1.8124072476103957e-05,
+      "loss": 0.12651515007019043,
+      "step": 470,
+      "token_acc": 0.9594694178334562
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.0954047441482544,
+      "learning_rate": 1.8001748977897754e-05,
+      "loss": 0.11215313673019409,
+      "step": 480,
+      "token_acc": 0.9634851771511207
+    },
+    {
+      "epoch": 0.2903703703703704,
+      "grad_norm": 0.8077743649482727,
+      "learning_rate": 1.787600289944039e-05,
+      "loss": 0.1215265154838562,
+      "step": 490,
+      "token_acc": 0.9642989959092599
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.9279748797416687,
+      "learning_rate": 1.7746888025978807e-05,
+      "loss": 0.11017097234725952,
+      "step": 500,
+      "token_acc": 0.9696060037523452
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.2479947805404663,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.1296389102935791,
+      "step": 510,
+      "token_acc": 0.9566453447050463
+    },
+    {
+      "epoch": 0.30814814814814817,
+      "grad_norm": 1.1002650260925293,
+      "learning_rate": 1.7478774216065882e-05,
+      "loss": 0.13492013216018678,
+      "step": 520,
+      "token_acc": 0.9590994371482177
+    },
+    {
+      "epoch": 0.31407407407407406,
+      "grad_norm": 1.108170747756958,
+      "learning_rate": 1.733988995967179e-05,
+      "loss": 0.14083080291748046,
+      "step": 530,
+      "token_acc": 0.9592061742006616
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8783969879150391,
+      "learning_rate": 1.719786621933599e-05,
+      "loss": 0.12698700428009033,
+      "step": 540,
+      "token_acc": 0.9617927994121969
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.6896427273750305,
+      "learning_rate": 1.70527637427338e-05,
+      "loss": 0.11144465208053589,
+      "step": 550,
+      "token_acc": 0.9692820133234641
+    },
+    {
+      "epoch": 0.33185185185185184,
+      "grad_norm": 1.067499041557312,
+      "learning_rate": 1.690464459440538e-05,
+      "loss": 0.13314462900161744,
+      "step": 560,
+      "token_acc": 0.9597096188747731
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.6953498721122742,
+      "learning_rate": 1.6753572129208935e-05,
+      "loss": 0.11334860324859619,
+      "step": 570,
+      "token_acc": 0.9676190476190476
+    },
+    {
+      "epoch": 0.3437037037037037,
+      "grad_norm": 1.197219967842102,
+      "learning_rate": 1.6599610965222002e-05,
+      "loss": 0.1281804084777832,
+      "step": 580,
+      "token_acc": 0.9607272727272728
+    },
+    {
+      "epoch": 0.3496296296296296,
+      "grad_norm": 0.6708402633666992,
+      "learning_rate": 1.6442826956102424e-05,
+      "loss": 0.12322006225585938,
+      "step": 590,
+      "token_acc": 0.9628704034273474
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.0634019374847412,
+      "learning_rate": 1.628328716292082e-05,
+      "loss": 0.13818006515502929,
+      "step": 600,
+      "token_acc": 0.9580494801003944
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.14249637722969055,
+      "eval_runtime": 229.7535,
+      "eval_samples_per_second": 6.529,
+      "eval_steps_per_second": 6.529,
+      "eval_token_acc": 0.9576734025122884,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0364707786172774e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}