Upload Qwen3-4B-Code-Analyzer-Base model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

args.json

@@ -0,0 +1,339 @@
+{
+  "output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/v0-20260215-024038",
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "gradient_accumulation_steps": 16,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 2e-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": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.03,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 200.0,
+  "save_total_limit": 3,
+  "enable_jit_checkpoint": false,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "use_cpu": false,
+  "seed": 42,
+  "data_seed": 42,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": -1,
+  "ddp_backend": null,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 200.0,
+  "dataloader_num_workers": 8,
+  "dataloader_prefetch_factor": null,
+  "run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/v0-20260215-024038",
+  "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": [],
+  "fsdp_config": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "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,
+  "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": "{\"use_reentrant\": false}",
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "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,
+  "use_cache": false,
+  "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": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "eval_metric": null,
+  "callbacks": [],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "full",
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "Qwen/Qwen3-4B-Instruct-2507",
+  "model_type": "qwen3",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "experts_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen3_nothinking",
+  "system": null,
+  "max_length": 32768,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/home/ubuntu/ms-swift/data/msswift-tooluse-2026-02-14-train.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "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,
+  "structured_outputs_regex": null,
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "use_hf": true,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "swift_version": "4.0.0.dev0",
+  "ckpt_dir": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen3-4B-Instruct-2507",
+  "model_info": "ModelInfo(model_type='qwen3', model_dir='/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'rope_theta': 5000000, 'rope_type': 'default'}, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3Guard-Gen-0.6B', hf_model_id='Qwen/Qwen3Guard-Gen-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-4B', hf_model_id='Qwen/Qwen3Guard-Gen-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-8B', hf_model_id='Qwen/Qwen3Guard-Gen-8B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_guard', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507', hf_model_id='Qwen/Qwen3-4B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template='qwen3_nothinking', model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
+  "template_meta": "QwenTemplateMeta(template_type='qwen3_nothinking', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.base.Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
+  "_val_dataset_exists": false,
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/v0-20260215-024038', do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-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=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0.03, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=200, save_total_limit=3, enable_jit_checkpoint=False, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, use_cpu=False, seed=42, data_seed=42, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=-1, ddp_backend=None, debug=[], dataloader_drop_last=False, eval_steps=200.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-tooluse-h100sxm/v0-20260215-024038', 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_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 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, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, 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={'use_reentrant': False}, include_for_metrics=[], eval_do_concat_batches=True, auto_find_batch_size=False, full_determinism=False, ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, use_cache=False, 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=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
+}

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.1.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39dbbd32a512203b8371d3975db535144a3969d1d7ee277f9f0bbc3ccb9fbcc
+size 8044982080

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3351f17380c8be1911a906a34739ec1e233b4f22c4ff1cab6f111af178e6a783
+size 16090225449

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb1878d877a42ce7669e65b702bc4162c15e435a8917656ff78ed4ac40da867
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,666 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200.0,
+  "global_step": 394,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005097164702134438,
+      "grad_norm": 12.5,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7101277709007263,
+      "step": 1,
+      "token_acc": 0.8745318352059925
+    },
+    {
+      "epoch": 0.02548582351067219,
+      "grad_norm": 12.1875,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8278377652168274,
+      "step": 5,
+      "token_acc": 0.8552833964573375
+    },
+    {
+      "epoch": 0.05097164702134438,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5761711120605468,
+      "step": 10,
+      "token_acc": 0.8653274252066853
+    },
+    {
+      "epoch": 0.07645747053201657,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.9996956568698325e-05,
+      "loss": 0.39079511165618896,
+      "step": 15,
+      "token_acc": 0.8887680715510904
+    },
+    {
+      "epoch": 0.10194329404268876,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.9978364530054465e-05,
+      "loss": 0.34750330448150635,
+      "step": 20,
+      "token_acc": 0.8949520766773162
+    },
+    {
+      "epoch": 0.12742911755336095,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.9942902642308737e-05,
+      "loss": 0.26970508098602297,
+      "step": 25,
+      "token_acc": 0.9119090968203394
+    },
+    {
+      "epoch": 0.15291494106403314,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.9890630858842614e-05,
+      "loss": 0.31259732246398925,
+      "step": 30,
+      "token_acc": 0.8999557705203384
+    },
+    {
+      "epoch": 0.17840076457470533,
+      "grad_norm": 1.625,
+      "learning_rate": 1.9821637552564973e-05,
+      "loss": 0.2847127437591553,
+      "step": 35,
+      "token_acc": 0.9077454674132511
+    },
+    {
+      "epoch": 0.20388658808537752,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.9736039366505087e-05,
+      "loss": 0.26165449619293213,
+      "step": 40,
+      "token_acc": 0.913668239925095
+    },
+    {
+      "epoch": 0.2293724115960497,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.9633981016610926e-05,
+      "loss": 0.24728527069091796,
+      "step": 45,
+      "token_acc": 0.9214681226749867
+    },
+    {
+      "epoch": 0.2548582351067219,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.951563504708622e-05,
+      "loss": 0.21780962944030763,
+      "step": 50,
+      "token_acc": 0.9288334437567668
+    },
+    {
+      "epoch": 0.2803440586173941,
+      "grad_norm": 2.25,
+      "learning_rate": 1.938120153867983e-05,
+      "loss": 0.24094951152801514,
+      "step": 55,
+      "token_acc": 0.9214724125087046
+    },
+    {
+      "epoch": 0.3058298821280663,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.9230907770420737e-05,
+      "loss": 0.2268754005432129,
+      "step": 60,
+      "token_acc": 0.9281276558333089
+    },
+    {
+      "epoch": 0.33131570563873847,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.9065007835370358e-05,
+      "loss": 0.22875683307647704,
+      "step": 65,
+      "token_acc": 0.9230186030186031
+    },
+    {
+      "epoch": 0.35680152914941066,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.888378221104201e-05,
+      "loss": 0.239988374710083,
+      "step": 70,
+      "token_acc": 0.9226348493246594
+    },
+    {
+      "epoch": 0.38228735266008285,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.8687537285213627e-05,
+      "loss": 0.1711668848991394,
+      "step": 75,
+      "token_acc": 0.9440668926242624
+    },
+    {
+      "epoch": 0.40777317617075504,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.8476604837935515e-05,
+      "loss": 0.2378025770187378,
+      "step": 80,
+      "token_acc": 0.9246084180832901
+    },
+    {
+      "epoch": 0.4332589996814272,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8251341480608823e-05,
+      "loss": 0.18637551069259645,
+      "step": 85,
+      "token_acc": 0.9384391968682915
+    },
+    {
+      "epoch": 0.4587448231920994,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.8012128053083097e-05,
+      "loss": 0.1798395037651062,
+      "step": 90,
+      "token_acc": 0.9428771275355561
+    },
+    {
+      "epoch": 0.4842306467027716,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.7759368979792145e-05,
+      "loss": 0.19358837604522705,
+      "step": 95,
+      "token_acc": 0.9375457743950599
+    },
+    {
+      "epoch": 0.5097164702134438,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.749349158601686e-05,
+      "loss": 0.18399842977523803,
+      "step": 100,
+      "token_acc": 0.9422957113270134
+    },
+    {
+      "epoch": 0.535202293724116,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.7214945375430816e-05,
+      "loss": 0.17546424865722657,
+      "step": 105,
+      "token_acc": 0.9426513393021628
+    },
+    {
+      "epoch": 0.5606881172347882,
+      "grad_norm": 1.625,
+      "learning_rate": 1.6924201270150194e-05,
+      "loss": 0.15674128532409667,
+      "step": 110,
+      "token_acc": 0.948707565634069
+    },
+    {
+      "epoch": 0.5861739407454604,
+      "grad_norm": 2.375,
+      "learning_rate": 1.6621750814572728e-05,
+      "loss": 0.17290754318237306,
+      "step": 115,
+      "token_acc": 0.9423056713490034
+    },
+    {
+      "epoch": 0.6116597642561326,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.6308105344351776e-05,
+      "loss": 0.1858464241027832,
+      "step": 120,
+      "token_acc": 0.9447680047665152
+    },
+    {
+      "epoch": 0.6371455877668047,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.598379512191042e-05,
+      "loss": 0.13930436372756957,
+      "step": 125,
+      "token_acc": 0.9549336664078587
+    },
+    {
+      "epoch": 0.6626314112774769,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.5649368439957182e-05,
+      "loss": 0.1962134599685669,
+      "step": 130,
+      "token_acc": 0.9364768586501332
+    },
+    {
+      "epoch": 0.6881172347881491,
+      "grad_norm": 2.0,
+      "learning_rate": 1.5305390694518953e-05,
+      "loss": 0.17399163246154786,
+      "step": 135,
+      "token_acc": 0.9454186101668116
+    },
+    {
+      "epoch": 0.7136030582988213,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.4952443429058334e-05,
+      "loss": 0.116390061378479,
+      "step": 140,
+      "token_acc": 0.9623854999025531
+    },
+    {
+      "epoch": 0.7390888818094935,
+      "grad_norm": 2.125,
+      "learning_rate": 1.459112335129144e-05,
+      "loss": 0.20297460556030272,
+      "step": 145,
+      "token_acc": 0.9371412765368923
+    },
+    {
+      "epoch": 0.7645747053201657,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.4222041324368347e-05,
+      "loss": 0.14657198190689086,
+      "step": 150,
+      "token_acc": 0.9517101943288719
+    },
+    {
+      "epoch": 0.7900605288308379,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.3845821334121763e-05,
+      "loss": 0.1491287589073181,
+      "step": 155,
+      "token_acc": 0.9500473678670425
+    },
+    {
+      "epoch": 0.8155463523415101,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.346309943412995e-05,
+      "loss": 0.10045711994171143,
+      "step": 160,
+      "token_acc": 0.9683162116626162
+    },
+    {
+      "epoch": 0.8410321758521823,
+      "grad_norm": 2.125,
+      "learning_rate": 1.3074522670377392e-05,
+      "loss": 0.12388412952423096,
+      "step": 165,
+      "token_acc": 0.9603866049550775
+    },
+    {
+      "epoch": 0.8665179993628545,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.2680747987331215e-05,
+      "loss": 0.11760580539703369,
+      "step": 170,
+      "token_acc": 0.9641480008911587
+    },
+    {
+      "epoch": 0.8920038228735266,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.2282441117282831e-05,
+      "loss": 0.09457792043685913,
+      "step": 175,
+      "token_acc": 0.9685485409116917
+    },
+    {
+      "epoch": 0.9174896463841988,
+      "grad_norm": 2.125,
+      "learning_rate": 1.1880275454832493e-05,
+      "loss": 0.1546500325202942,
+      "step": 180,
+      "token_acc": 0.9522128782763489
+    },
+    {
+      "epoch": 0.942975469894871,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.147493091841965e-05,
+      "loss": 0.17746270895004274,
+      "step": 185,
+      "token_acc": 0.9467413034786085
+    },
+    {
+      "epoch": 0.9684612934055432,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.1067092800823798e-05,
+      "loss": 0.17491767406463624,
+      "step": 190,
+      "token_acc": 0.9474711941210667
+    },
+    {
+      "epoch": 0.9939471169162154,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.0657450610579225e-05,
+      "loss": 0.10773472785949707,
+      "step": 195,
+      "token_acc": 0.9669074948340096
+    },
+    {
+      "epoch": 1.0152914941064033,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.0246696906262484e-05,
+      "loss": 0.1128343939781189,
+      "step": 200,
+      "token_acc": 0.9617505882352941
+    },
+    {
+      "epoch": 1.0407773176170756,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.835526125623262e-06,
+      "loss": 0.08277679681777954,
+      "step": 205,
+      "token_acc": 0.9738211210471551
+    },
+    {
+      "epoch": 1.0662631411277477,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.424633411538289e-06,
+      "loss": 0.08777509927749634,
+      "step": 210,
+      "token_acc": 0.9702302847395355
+    },
+    {
+      "epoch": 1.09174896463842,
+      "grad_norm": 2.078125,
+      "learning_rate": 9.014713436773114e-06,
+      "loss": 0.1303470253944397,
+      "step": 215,
+      "token_acc": 0.958813470139437
+    },
+    {
+      "epoch": 1.117234788149092,
+      "grad_norm": 2.234375,
+      "learning_rate": 8.606459229538645e-06,
+      "loss": 0.12297415733337402,
+      "step": 220,
+      "token_acc": 0.9640833060584658
+    },
+    {
+      "epoch": 1.1427206116597644,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.200561001828093e-06,
+      "loss": 0.11149228811264038,
+      "step": 225,
+      "token_acc": 0.9653502592232877
+    },
+    {
+      "epoch": 1.1682064351704364,
+      "grad_norm": 2.484375,
+      "learning_rate": 7.797704982515094e-06,
+      "loss": 0.13481587171554565,
+      "step": 230,
+      "token_acc": 0.954266376601402
+    },
+    {
+      "epoch": 1.1936922586811085,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.398572257185879e-06,
+      "loss": 0.08835281133651733,
+      "step": 235,
+      "token_acc": 0.9707970452128424
+    },
+    {
+      "epoch": 1.2191780821917808,
+      "grad_norm": 1.8046875,
+      "learning_rate": 7.003837616666906e-06,
+      "loss": 0.10161161422729492,
+      "step": 240,
+      "token_acc": 0.9656063115927788
+    },
+    {
+      "epoch": 1.244663905702453,
+      "grad_norm": 2.34375,
+      "learning_rate": 6.614168416194674e-06,
+      "loss": 0.07140190601348877,
+      "step": 245,
+      "token_acc": 0.9799972242462094
+    },
+    {
+      "epoch": 1.2701497292131252,
+      "grad_norm": 2.953125,
+      "learning_rate": 6.230223447156469e-06,
+      "loss": 0.11119414567947387,
+      "step": 250,
+      "token_acc": 0.9668460399436599
+    },
+    {
+      "epoch": 1.2956355527237973,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.852651823309521e-06,
+      "loss": 0.1017767071723938,
+      "step": 255,
+      "token_acc": 0.9658570417142279
+    },
+    {
+      "epoch": 1.3211213762344696,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.482091883361571e-06,
+      "loss": 0.12420098781585694,
+      "step": 260,
+      "token_acc": 0.9606861625830626
+    },
+    {
+      "epoch": 1.3466071997451419,
+      "grad_norm": 2.953125,
+      "learning_rate": 5.1191701117681815e-06,
+      "loss": 0.08732576370239258,
+      "step": 265,
+      "token_acc": 0.9742369029426746
+    },
+    {
+      "epoch": 1.372093023255814,
+      "grad_norm": 3.0625,
+      "learning_rate": 4.764500079571403e-06,
+      "loss": 0.08145667314529419,
+      "step": 270,
+      "token_acc": 0.9741474896414886
+    },
+    {
+      "epoch": 1.397578846766486,
+      "grad_norm": 1.65625,
+      "learning_rate": 4.418681407070339e-06,
+      "loss": 0.07903674840927125,
+      "step": 275,
+      "token_acc": 0.9746860907612613
+    },
+    {
+      "epoch": 1.4230646702771583,
+      "grad_norm": 2.34375,
+      "learning_rate": 4.082298750077485e-06,
+      "loss": 0.10514881610870361,
+      "step": 280,
+      "token_acc": 0.9671857823378527
+    },
+    {
+      "epoch": 1.4485504937878306,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.755920811474647e-06,
+      "loss": 0.06307402849197388,
+      "step": 285,
+      "token_acc": 0.978928398142372
+    },
+    {
+      "epoch": 1.4740363172985027,
+      "grad_norm": 2.671875,
+      "learning_rate": 3.4400993797395664e-06,
+      "loss": 0.10954618453979492,
+      "step": 290,
+      "token_acc": 0.9647058823529412
+    },
+    {
+      "epoch": 1.4995221408091748,
+      "grad_norm": 1.359375,
+      "learning_rate": 3.135368396068771e-06,
+      "loss": 0.07190140485763549,
+      "step": 295,
+      "token_acc": 0.975735236452043
+    },
+    {
+      "epoch": 1.525007964319847,
+      "grad_norm": 1.640625,
+      "learning_rate": 2.8422430516737733e-06,
+      "loss": 0.08197641372680664,
+      "step": 300,
+      "token_acc": 0.9747953097358987
+    },
+    {
+      "epoch": 1.5504937878305194,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.561218916776823e-06,
+      "loss": 0.0815430760383606,
+      "step": 305,
+      "token_acc": 0.9747565568486412
+    },
+    {
+      "epoch": 1.5759796113411915,
+      "grad_norm": 2.125,
+      "learning_rate": 2.292771102778739e-06,
+      "loss": 0.09041160345077515,
+      "step": 310,
+      "token_acc": 0.9739717810291317
+    },
+    {
+      "epoch": 1.6014654348518635,
+      "grad_norm": 2.515625,
+      "learning_rate": 2.037353459015272e-06,
+      "loss": 0.07603458166122437,
+      "step": 315,
+      "token_acc": 0.9746314985454959
+    },
+    {
+      "epoch": 1.6269512583625358,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.795397805460053e-06,
+      "loss": 0.09144850373268128,
+      "step": 320,
+      "token_acc": 0.9713049218807306
+    },
+    {
+      "epoch": 1.6524370818732081,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.5673132026713046e-06,
+      "loss": 0.08237828016281128,
+      "step": 325,
+      "token_acc": 0.9731688670646006
+    },
+    {
+      "epoch": 1.6779229053838802,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1.353485260216596e-06,
+      "loss": 0.07584392428398132,
+      "step": 330,
+      "token_acc": 0.9767055819044145
+    },
+    {
+      "epoch": 1.7034087288945523,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.1542754847448544e-06,
+      "loss": 0.05938386917114258,
+      "step": 335,
+      "token_acc": 0.9827799662352279
+    },
+    {
+      "epoch": 1.7288945524052246,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.700206688077707e-07,
+      "loss": 0.08313992023468017,
+      "step": 340,
+      "token_acc": 0.9746641292924703
+    },
+    {
+      "epoch": 1.754380375915897,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.010323214639492e-07,
+      "loss": 0.10048294067382812,
+      "step": 345,
+      "token_acc": 0.9692962175159531
+    },
+    {
+      "epoch": 1.779866199426569,
+      "grad_norm": 2.265625,
+      "learning_rate": 6.475961416283838e-07,
+      "loss": 0.07593317031860351,
+      "step": 350,
+      "token_acc": 0.9778483525208416
+    },
+    {
+      "epoch": 1.805352022937241,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.099715350576817e-07,
+      "loss": 0.09315924048423767,
+      "step": 355,
+      "token_acc": 0.9696224141393854
+    },
+    {
+      "epoch": 1.8308378464479134,
+      "grad_norm": 2.0625,
+      "learning_rate": 3.883911757876058e-07,
+      "loss": 0.08427355885505676,
+      "step": 360,
+      "token_acc": 0.9726720482046076
+    },
+    {
+      "epoch": 1.8563236699585857,
+      "grad_norm": 2.453125,
+      "learning_rate": 2.8306061276442753e-07,
+      "loss": 0.09181307554244995,
+      "step": 365,
+      "token_acc": 0.97152072887367
+    },
+    {
+      "epoch": 1.8818094934692577,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.941579223350898e-07,
+      "loss": 0.08087407350540161,
+      "step": 370,
+      "token_acc": 0.9741133571604277
+    },
+    {
+      "epoch": 1.9072953169799298,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.218334071837468e-07,
+      "loss": 0.10078444480895996,
+      "step": 375,
+      "token_acc": 0.9704466920176089
+    },
+    {
+      "epoch": 1.9327811404906021,
+      "grad_norm": 1.9609375,
+      "learning_rate": 6.62093422236132e-08,
+      "loss": 0.09156302809715271,
+      "step": 380,
+      "token_acc": 0.9694673981909602
+    },
+    {
+      "epoch": 1.9582669640012744,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.73797678737886e-08,
+      "loss": 0.07732056379318238,
+      "step": 385,
+      "token_acc": 0.9762223117196939
+    },
+    {
+      "epoch": 1.9837527875119465,
+      "grad_norm": 1.953125,
+      "learning_rate": 5.410331070498931e-09,
+      "loss": 0.07045769095420837,
+      "step": 390,
+      "token_acc": 0.9786481253300475
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 394,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8765180828971213e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b47478f5c544f57e741026063816c079ad979eedbdb66df415545330f106519
+size 6673