Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

args.json

@@ -0,0 +1,386 @@
+{
+  "output_dir": "/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 4,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "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": 3.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": 3,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": true,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 8,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620",
+  "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_min_num_params": 0,
+  "fsdp_config": null,
+  "tp_size": 0,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 3,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "offload_param": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "overlap_comm": false,
+      "contiguous_gradients": true,
+      "sub_group_size": 1000000000.0,
+      "reduce_bucket_size": "auto",
+      "zero_quantized_weights": false,
+      "zero_quantized_gradients": false,
+      "stage3_prefetch_bucket_size": "auto",
+      "stage3_param_persistence_threshold": "auto",
+      "stage3_max_live_parameters": 1000000000.0,
+      "stage3_max_reuse_distance": 1000000000.0,
+      "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "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,
+  "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": true,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": 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,
+  "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,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/Qwen3-4B-Instruct-2507",
+  "model_type": "qwen3_nothinking",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "flash_attn",
+  "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": 24576,
+  "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": [
+    "/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/benchmark/DABStep/train_data/generate/generate_prm_traj/prm_train_data_no_indentation_error_v2.json"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 8,
+  "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": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "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": 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,
+  "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": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen3-4B-Instruct-2507",
+  "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/Qwen3-4B-Instruct-2507', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f29009a9240>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/Qwen3-4B-Instruct-2507",
+  "_val_dataset_exists": [],
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=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=None, dataloader_num_workers=8, dataloader_prefetch_factor=10, past_index=-1, run_name='/gruntdata/event_graph/weike.zyq2/qzs/DataPRM/model/qwen3-4b-prm_deepseek_v3_2_no_indentation_error_v2/v4-20251226-013620', 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}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=True, 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=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, 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='full', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm', problem_type=None)"
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "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": "4.51.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8e902d5d73177b34f4361bcb35763b2da45f9a952ff3c379f6e109e2e00092
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b1ea465f1f4e92bfe099ed3d89678a1a551cf423db46ae820c44e36c053799
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2890 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9816849816849818,
+  "eval_steps": 500,
+  "global_step": 408,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007326007326007326,
+      "grad_norm": 30.21496593413568,
+      "learning_rate": 4.7619047619047623e-07,
+      "loss": 1.0635175704956055,
+      "step": 1
+    },
+    {
+      "epoch": 0.014652014652014652,
+      "grad_norm": 27.043345585334517,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 1.0006253719329834,
+      "step": 2
+    },
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 21.646848717902948,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.9898864030838013,
+      "step": 3
+    },
+    {
+      "epoch": 0.029304029304029304,
+      "grad_norm": 22.348396709879044,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.988436758518219,
+      "step": 4
+    },
+    {
+      "epoch": 0.03663003663003663,
+      "grad_norm": 19.157410690764603,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 0.9326452016830444,
+      "step": 5
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 18.08116663695173,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.8227804899215698,
+      "step": 6
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 16.123821453273436,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.816413938999176,
+      "step": 7
+    },
+    {
+      "epoch": 0.05860805860805861,
+      "grad_norm": 10.059553232587936,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.6918408274650574,
+      "step": 8
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 10.100146604450146,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.709736704826355,
+      "step": 9
+    },
+    {
+      "epoch": 0.07326007326007326,
+      "grad_norm": 3.6849384254746336,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.5924822688102722,
+      "step": 10
+    },
+    {
+      "epoch": 0.08058608058608059,
+      "grad_norm": 2.515001245028391,
+      "learning_rate": 5.2380952380952384e-06,
+      "loss": 0.5829637050628662,
+      "step": 11
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 2.7142652174838964,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.5520739555358887,
+      "step": 12
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 2.396783666272162,
+      "learning_rate": 6.1904761904761914e-06,
+      "loss": 0.5408250689506531,
+      "step": 13
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 2.613664759900683,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5364675521850586,
+      "step": 14
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 2.140953850448383,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.5406008958816528,
+      "step": 15
+    },
+    {
+      "epoch": 0.11721611721611722,
+      "grad_norm": 2.1637811311224513,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 0.5351678133010864,
+      "step": 16
+    },
+    {
+      "epoch": 0.12454212454212454,
+      "grad_norm": 1.889685988846562,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 0.5272159576416016,
+      "step": 17
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 1.610391433650919,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.4894131124019623,
+      "step": 18
+    },
+    {
+      "epoch": 0.1391941391941392,
+      "grad_norm": 1.5780714267255904,
+      "learning_rate": 9.047619047619049e-06,
+      "loss": 0.4680541753768921,
+      "step": 19
+    },
+    {
+      "epoch": 0.14652014652014653,
+      "grad_norm": 1.3826646451572844,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.41832777857780457,
+      "step": 20
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.9876445386481647,
+      "learning_rate": 1e-05,
+      "loss": 0.5307973623275757,
+      "step": 21
+    },
+    {
+      "epoch": 0.16117216117216118,
+      "grad_norm": 1.989790222306354,
+      "learning_rate": 9.999835253787472e-06,
+      "loss": 0.4524080753326416,
+      "step": 22
+    },
+    {
+      "epoch": 0.1684981684981685,
+      "grad_norm": 1.7132167306761634,
+      "learning_rate": 9.99934102600642e-06,
+      "loss": 0.4481462240219116,
+      "step": 23
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 1.675845803554774,
+      "learning_rate": 9.998517349225698e-06,
+      "loss": 0.470619797706604,
+      "step": 24
+    },
+    {
+      "epoch": 0.18315018315018314,
+      "grad_norm": 1.8889444953942198,
+      "learning_rate": 9.997364277724362e-06,
+      "loss": 0.4533703625202179,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.2961235388879089,
+      "learning_rate": 9.99588188748808e-06,
+      "loss": 0.4506123661994934,
+      "step": 26
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 1.3960705328975553,
+      "learning_rate": 9.994070276204115e-06,
+      "loss": 0.5040400624275208,
+      "step": 27
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 1.42158083553959,
+      "learning_rate": 9.991929563254913e-06,
+      "loss": 0.4825146794319153,
+      "step": 28
+    },
+    {
+      "epoch": 0.21245421245421245,
+      "grad_norm": 1.1661369187587884,
+      "learning_rate": 9.989459889710214e-06,
+      "loss": 0.4361911714076996,
+      "step": 29
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 1.2574093229638947,
+      "learning_rate": 9.986661418317759e-06,
+      "loss": 0.45438122749328613,
+      "step": 30
+    },
+    {
+      "epoch": 0.2271062271062271,
+      "grad_norm": 1.3348666437119017,
+      "learning_rate": 9.983534333492575e-06,
+      "loss": 0.4379500448703766,
+      "step": 31
+    },
+    {
+      "epoch": 0.23443223443223443,
+      "grad_norm": 1.246184387917552,
+      "learning_rate": 9.980078841304817e-06,
+      "loss": 0.4118569791316986,
+      "step": 32
+    },
+    {
+      "epoch": 0.24175824175824176,
+      "grad_norm": 1.179330565300909,
+      "learning_rate": 9.97629516946618e-06,
+      "loss": 0.4063628315925598,
+      "step": 33
+    },
+    {
+      "epoch": 0.2490842490842491,
+      "grad_norm": 1.1385770353147593,
+      "learning_rate": 9.97218356731491e-06,
+      "loss": 0.4152410626411438,
+      "step": 34
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 1.6513827173956053,
+      "learning_rate": 9.967744305799358e-06,
+      "loss": 0.4543665647506714,
+      "step": 35
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 1.1284245393981716,
+      "learning_rate": 9.962977677460132e-06,
+      "loss": 0.42496830224990845,
+      "step": 36
+    },
+    {
+      "epoch": 0.27106227106227104,
+      "grad_norm": 1.0753146429921163,
+      "learning_rate": 9.957883996410821e-06,
+      "loss": 0.42909127473831177,
+      "step": 37
+    },
+    {
+      "epoch": 0.2783882783882784,
+      "grad_norm": 1.295900042465006,
+      "learning_rate": 9.952463598317286e-06,
+      "loss": 0.3935036063194275,
+      "step": 38
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.134829504686702,
+      "learning_rate": 9.946716840375552e-06,
+      "loss": 0.44124358892440796,
+      "step": 39
+    },
+    {
+      "epoch": 0.29304029304029305,
+      "grad_norm": 1.1702725203395377,
+      "learning_rate": 9.940644101288259e-06,
+      "loss": 0.4439253509044647,
+      "step": 40
+    },
+    {
+      "epoch": 0.30036630036630035,
+      "grad_norm": 1.256616648991797,
+      "learning_rate": 9.934245781239714e-06,
+      "loss": 0.3892786502838135,
+      "step": 41
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.1589721621440654,
+      "learning_rate": 9.927522301869515e-06,
+      "loss": 0.36586904525756836,
+      "step": 42
+    },
+    {
+      "epoch": 0.315018315018315,
+      "grad_norm": 1.2097406758159928,
+      "learning_rate": 9.920474106244764e-06,
+      "loss": 0.3926905393600464,
+      "step": 43
+    },
+    {
+      "epoch": 0.32234432234432236,
+      "grad_norm": 1.1180887734407854,
+      "learning_rate": 9.913101658830879e-06,
+      "loss": 0.39513468742370605,
+      "step": 44
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 1.489392826555109,
+      "learning_rate": 9.905405445460972e-06,
+      "loss": 0.4130535125732422,
+      "step": 45
+    },
+    {
+      "epoch": 0.336996336996337,
+      "grad_norm": 1.154514234942715,
+      "learning_rate": 9.897385973303845e-06,
+      "loss": 0.4013521373271942,
+      "step": 46
+    },
+    {
+      "epoch": 0.3443223443223443,
+      "grad_norm": 1.1719627644397432,
+      "learning_rate": 9.889043770830566e-06,
+      "loss": 0.4277796745300293,
+      "step": 47
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 1.5740413108726932,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.38313156366348267,
+      "step": 48
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 1.1734369672836624,
+      "learning_rate": 9.871393395120774e-06,
+      "loss": 0.4053453803062439,
+      "step": 49
+    },
+    {
+      "epoch": 0.3663003663003663,
+      "grad_norm": 1.4855170661495627,
+      "learning_rate": 9.862086385017283e-06,
+      "loss": 0.37065786123275757,
+      "step": 50
+    },
+    {
+      "epoch": 0.37362637362637363,
+      "grad_norm": 1.2470491770738514,
+      "learning_rate": 9.852458970787027e-06,
+      "loss": 0.3932054042816162,
+      "step": 51
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.1200733413865462,
+      "learning_rate": 9.842511786862018e-06,
+      "loss": 0.3844960331916809,
+      "step": 52
+    },
+    {
+      "epoch": 0.3882783882783883,
+      "grad_norm": 1.2353594939698733,
+      "learning_rate": 9.832245488746612e-06,
+      "loss": 0.4030640125274658,
+      "step": 53
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 1.2526400425035524,
+      "learning_rate": 9.821660752974294e-06,
+      "loss": 0.41372472047805786,
+      "step": 54
+    },
+    {
+      "epoch": 0.40293040293040294,
+      "grad_norm": 1.1578568131070235,
+      "learning_rate": 9.81075827706312e-06,
+      "loss": 0.38878971338272095,
+      "step": 55
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 1.1789063859126412,
+      "learning_rate": 9.799538779469734e-06,
+      "loss": 0.3679278492927551,
+      "step": 56
+    },
+    {
+      "epoch": 0.4175824175824176,
+      "grad_norm": 1.0793218213230338,
+      "learning_rate": 9.78800299954203e-06,
+      "loss": 0.35747843980789185,
+      "step": 57
+    },
+    {
+      "epoch": 0.4249084249084249,
+      "grad_norm": 1.4979207988768952,
+      "learning_rate": 9.776151697470431e-06,
+      "loss": 0.38858622312545776,
+      "step": 58
+    },
+    {
+      "epoch": 0.43223443223443225,
+      "grad_norm": 1.5776030032036932,
+      "learning_rate": 9.763985654237785e-06,
+      "loss": 0.410378634929657,
+      "step": 59
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 1.1687321357395992,
+      "learning_rate": 9.751505671567914e-06,
+      "loss": 0.3829571008682251,
+      "step": 60
+    },
+    {
+      "epoch": 0.4468864468864469,
+      "grad_norm": 1.1022315738152733,
+      "learning_rate": 9.738712571872765e-06,
+      "loss": 0.38535329699516296,
+      "step": 61
+    },
+    {
+      "epoch": 0.4542124542124542,
+      "grad_norm": 1.031148812173931,
+      "learning_rate": 9.725607198198227e-06,
+      "loss": 0.37591585516929626,
+      "step": 62
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.1465009384770484,
+      "learning_rate": 9.712190414168573e-06,
+      "loss": 0.43732309341430664,
+      "step": 63
+    },
+    {
+      "epoch": 0.46886446886446886,
+      "grad_norm": 3.901087295216021,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.35739046335220337,
+      "step": 64
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.1832020160855363,
+      "learning_rate": 9.684426172090084e-06,
+      "loss": 0.39645135402679443,
+      "step": 65
+    },
+    {
+      "epoch": 0.4835164835164835,
+      "grad_norm": 1.1501088941718765,
+      "learning_rate": 9.670080543662742e-06,
+      "loss": 0.3675802946090698,
+      "step": 66
+    },
+    {
+      "epoch": 0.4908424908424908,
+      "grad_norm": 1.2208405532006774,
+      "learning_rate": 9.655427164002692e-06,
+      "loss": 0.39301833510398865,
+      "step": 67
+    },
+    {
+      "epoch": 0.4981684981684982,
+      "grad_norm": 1.1252142850079323,
+      "learning_rate": 9.640466998745456e-06,
+      "loss": 0.4137623906135559,
+      "step": 68
+    },
+    {
+      "epoch": 0.5054945054945055,
+      "grad_norm": 1.0526557640749403,
+      "learning_rate": 9.625201033743262e-06,
+      "loss": 0.3448682129383087,
+      "step": 69
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 1.147790880025079,
+      "learning_rate": 9.609630275000072e-06,
+      "loss": 0.4187518358230591,
+      "step": 70
+    },
+    {
+      "epoch": 0.5201465201465202,
+      "grad_norm": 1.1265458933551666,
+      "learning_rate": 9.5937557486053e-06,
+      "loss": 0.3735639452934265,
+      "step": 71
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 1.1089149618339371,
+      "learning_rate": 9.577578500666187e-06,
+      "loss": 0.40197598934173584,
+      "step": 72
+    },
+    {
+      "epoch": 0.5347985347985348,
+      "grad_norm": 1.3993390218741097,
+      "learning_rate": 9.561099597238862e-06,
+      "loss": 0.40231800079345703,
+      "step": 73
+    },
+    {
+      "epoch": 0.5421245421245421,
+      "grad_norm": 1.1143458075824666,
+      "learning_rate": 9.544320124258093e-06,
+      "loss": 0.3674388527870178,
+      "step": 74
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 1.0051401204214154,
+      "learning_rate": 9.527241187465735e-06,
+      "loss": 0.40350422263145447,
+      "step": 75
+    },
+    {
+      "epoch": 0.5567765567765568,
+      "grad_norm": 1.1152468221193563,
+      "learning_rate": 9.509863912337843e-06,
+      "loss": 0.4011390507221222,
+      "step": 76
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 1.259123019280062,
+      "learning_rate": 9.492189444010522e-06,
+      "loss": 0.3963205814361572,
+      "step": 77
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.0882181942002715,
+      "learning_rate": 9.47421894720446e-06,
+      "loss": 0.3761591613292694,
+      "step": 78
+    },
+    {
+      "epoch": 0.5787545787545788,
+      "grad_norm": 1.3171244527835357,
+      "learning_rate": 9.455953606148172e-06,
+      "loss": 0.37985581159591675,
+      "step": 79
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "grad_norm": 1.1576335484597036,
+      "learning_rate": 9.437394624499957e-06,
+      "loss": 0.38125094771385193,
+      "step": 80
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 1.340371799783884,
+      "learning_rate": 9.418543225268598e-06,
+      "loss": 0.38609158992767334,
+      "step": 81
+    },
+    {
+      "epoch": 0.6007326007326007,
+      "grad_norm": 1.062259591126727,
+      "learning_rate": 9.399400650732735e-06,
+      "loss": 0.36670905351638794,
+      "step": 82
+    },
+    {
+      "epoch": 0.608058608058608,
+      "grad_norm": 1.2435607193732192,
+      "learning_rate": 9.379968162359034e-06,
+      "loss": 0.39242708683013916,
+      "step": 83
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.0441743485299124,
+      "learning_rate": 9.36024704071904e-06,
+      "loss": 0.3625451326370239,
+      "step": 84
+    },
+    {
+      "epoch": 0.6227106227106227,
+      "grad_norm": 1.1226141976759751,
+      "learning_rate": 9.340238585404787e-06,
+      "loss": 0.3682897090911865,
+      "step": 85
+    },
+    {
+      "epoch": 0.63003663003663,
+      "grad_norm": 1.1834442757500532,
+      "learning_rate": 9.319944114943171e-06,
+      "loss": 0.3925570845603943,
+      "step": 86
+    },
+    {
+      "epoch": 0.6373626373626373,
+      "grad_norm": 1.2543334036025904,
+      "learning_rate": 9.299364966709051e-06,
+      "loss": 0.40064454078674316,
+      "step": 87
+    },
+    {
+      "epoch": 0.6446886446886447,
+      "grad_norm": 1.1281264939516502,
+      "learning_rate": 9.278502496837116e-06,
+      "loss": 0.350555956363678,
+      "step": 88
+    },
+    {
+      "epoch": 0.652014652014652,
+      "grad_norm": 0.9918889297129596,
+      "learning_rate": 9.257358080132524e-06,
+      "loss": 0.3880164623260498,
+      "step": 89
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 1.2461108393741742,
+      "learning_rate": 9.235933109980302e-06,
+      "loss": 0.36218661069869995,
+      "step": 90
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.1159489708058996,
+      "learning_rate": 9.214228998253526e-06,
+      "loss": 0.39029616117477417,
+      "step": 91
+    },
+    {
+      "epoch": 0.673992673992674,
+      "grad_norm": 1.1373218288826976,
+      "learning_rate": 9.192247175220276e-06,
+      "loss": 0.3715818524360657,
+      "step": 92
+    },
+    {
+      "epoch": 0.6813186813186813,
+      "grad_norm": 1.1336385214393307,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.3895593285560608,
+      "step": 93
+    },
+    {
+      "epoch": 0.6886446886446886,
+      "grad_norm": 1.2322915227119142,
+      "learning_rate": 9.147456207714998e-06,
+      "loss": 0.3933688700199127,
+      "step": 94
+    },
+    {
+      "epoch": 0.6959706959706959,
+      "grad_norm": 1.110226455606631,
+      "learning_rate": 9.124650014899868e-06,
+      "loss": 0.37298864126205444,
+      "step": 95
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 1.0929399186170907,
+      "learning_rate": 9.101572013897555e-06,
+      "loss": 0.35858720541000366,
+      "step": 96
+    },
+    {
+      "epoch": 0.7106227106227107,
+      "grad_norm": 1.1200942735792472,
+      "learning_rate": 9.078223725513366e-06,
+      "loss": 0.35287725925445557,
+      "step": 97
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 1.107219943504411,
+      "learning_rate": 9.05460668836413e-06,
+      "loss": 0.3863588869571686,
+      "step": 98
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 1.0734987755886534,
+      "learning_rate": 9.030722458776815e-06,
+      "loss": 0.35608792304992676,
+      "step": 99
+    },
+    {
+      "epoch": 0.7326007326007326,
+      "grad_norm": 0.9382920838540864,
+      "learning_rate": 9.006572610685969e-06,
+      "loss": 0.3744190037250519,
+      "step": 100
+    },
+    {
+      "epoch": 0.73992673992674,
+      "grad_norm": 1.2299021078001484,
+      "learning_rate": 8.982158735529991e-06,
+      "loss": 0.38028016686439514,
+      "step": 101
+    },
+    {
+      "epoch": 0.7472527472527473,
+      "grad_norm": 1.0711983498848636,
+      "learning_rate": 8.957482442146271e-06,
+      "loss": 0.35936033725738525,
+      "step": 102
+    },
+    {
+      "epoch": 0.7545787545787546,
+      "grad_norm": 1.0380773275659636,
+      "learning_rate": 8.932545356665157e-06,
+      "loss": 0.3793637454509735,
+      "step": 103
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.1144376402102996,
+      "learning_rate": 8.907349122402803e-06,
+      "loss": 0.3640226721763611,
+      "step": 104
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.1640128905082725,
+      "learning_rate": 8.881895399752873e-06,
+      "loss": 0.3372342586517334,
+      "step": 105
+    },
+    {
+      "epoch": 0.7765567765567766,
+      "grad_norm": 1.199009223038314,
+      "learning_rate": 8.85618586607713e-06,
+      "loss": 0.37812405824661255,
+      "step": 106
+    },
+    {
+      "epoch": 0.7838827838827839,
+      "grad_norm": 1.0273110860584846,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.35580265522003174,
+      "step": 107
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 1.0516706336456754,
+      "learning_rate": 8.80400615927139e-06,
+      "loss": 0.3262220025062561,
+      "step": 108
+    },
+    {
+      "epoch": 0.7985347985347986,
+      "grad_norm": 1.0704201377081104,
+      "learning_rate": 8.777539424705022e-06,
+      "loss": 0.3796083927154541,
+      "step": 109
+    },
+    {
+      "epoch": 0.8058608058608059,
+      "grad_norm": 1.1209202523652468,
+      "learning_rate": 8.750823756013498e-06,
+      "loss": 0.3779366612434387,
+      "step": 110
+    },
+    {
+      "epoch": 0.8131868131868132,
+      "grad_norm": 1.0413754375402127,
+      "learning_rate": 8.72386091371891e-06,
+      "loss": 0.34237805008888245,
+      "step": 111
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 1.1829628343503562,
+      "learning_rate": 8.696652674631716e-06,
+      "loss": 0.3707228899002075,
+      "step": 112
+    },
+    {
+      "epoch": 0.8278388278388278,
+      "grad_norm": 1.0593662409475815,
+      "learning_rate": 8.669200831733655e-06,
+      "loss": 0.3644367456436157,
+      "step": 113
+    },
+    {
+      "epoch": 0.8351648351648352,
+      "grad_norm": 0.9884645087059205,
+      "learning_rate": 8.64150719405958e-06,
+      "loss": 0.354566752910614,
+      "step": 114
+    },
+    {
+      "epoch": 0.8424908424908425,
+      "grad_norm": 1.1284969366067186,
+      "learning_rate": 8.613573586578262e-06,
+      "loss": 0.34911516308784485,
+      "step": 115
+    },
+    {
+      "epoch": 0.8498168498168498,
+      "grad_norm": 1.0401559892838286,
+      "learning_rate": 8.585401850072114e-06,
+      "loss": 0.3552972078323364,
+      "step": 116
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.096500663411754,
+      "learning_rate": 8.55699384101589e-06,
+      "loss": 0.3714224100112915,
+      "step": 117
+    },
+    {
+      "epoch": 0.8644688644688645,
+      "grad_norm": 0.9686738471210327,
+      "learning_rate": 8.528351431454352e-06,
+      "loss": 0.3586280941963196,
+      "step": 118
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 1.1418772784157138,
+      "learning_rate": 8.499476508878894e-06,
+      "loss": 0.37895333766937256,
+      "step": 119
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 1.102623279686654,
+      "learning_rate": 8.470370976103171e-06,
+      "loss": 0.33410561084747314,
+      "step": 120
+    },
+    {
+      "epoch": 0.8864468864468864,
+      "grad_norm": 1.2084381697438025,
+      "learning_rate": 8.441036751137697e-06,
+      "loss": 0.34863168001174927,
+      "step": 121
+    },
+    {
+      "epoch": 0.8937728937728938,
+      "grad_norm": 1.0221326248807063,
+      "learning_rate": 8.411475767063454e-06,
+      "loss": 0.36963531374931335,
+      "step": 122
+    },
+    {
+      "epoch": 0.9010989010989011,
+      "grad_norm": 0.9696301679675473,
+      "learning_rate": 8.381689971904514e-06,
+      "loss": 0.382631778717041,
+      "step": 123
+    },
+    {
+      "epoch": 0.9084249084249084,
+      "grad_norm": 1.138279150305765,
+      "learning_rate": 8.35168132849965e-06,
+      "loss": 0.3976040780544281,
+      "step": 124
+    },
+    {
+      "epoch": 0.9157509157509157,
+      "grad_norm": 1.0494402894524364,
+      "learning_rate": 8.321451814372998e-06,
+      "loss": 0.37572136521339417,
+      "step": 125
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.0892258482751453,
+      "learning_rate": 8.29100342160374e-06,
+      "loss": 0.3367949426174164,
+      "step": 126
+    },
+    {
+      "epoch": 0.9304029304029304,
+      "grad_norm": 1.5742935797211806,
+      "learning_rate": 8.260338156694836e-06,
+      "loss": 0.3577330410480499,
+      "step": 127
+    },
+    {
+      "epoch": 0.9377289377289377,
+      "grad_norm": 1.0337951916800752,
+      "learning_rate": 8.229458040440783e-06,
+      "loss": 0.38907700777053833,
+      "step": 128
+    },
+    {
+      "epoch": 0.945054945054945,
+      "grad_norm": 1.0463672741030141,
+      "learning_rate": 8.198365107794457e-06,
+      "loss": 0.35719990730285645,
+      "step": 129
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.150609447800333,
+      "learning_rate": 8.167061407733018e-06,
+      "loss": 0.3516216278076172,
+      "step": 130
+    },
+    {
+      "epoch": 0.9597069597069597,
+      "grad_norm": 1.0134109975745493,
+      "learning_rate": 8.135549003122871e-06,
+      "loss": 0.37219393253326416,
+      "step": 131
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 1.1888953837381901,
+      "learning_rate": 8.103829970583742e-06,
+      "loss": 0.3526732325553894,
+      "step": 132
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 0.9504435010655483,
+      "learning_rate": 8.071906400351823e-06,
+      "loss": 0.3242747187614441,
+      "step": 133
+    },
+    {
+      "epoch": 0.9816849816849816,
+      "grad_norm": 1.1620841266168631,
+      "learning_rate": 8.039780396142023e-06,
+      "loss": 0.3983690142631531,
+      "step": 134
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 1.080002653239463,
+      "learning_rate": 8.007454075009352e-06,
+      "loss": 0.3187519907951355,
+      "step": 135
+    },
+    {
+      "epoch": 0.9963369963369964,
+      "grad_norm": 1.0777271233101429,
+      "learning_rate": 7.974929567209399e-06,
+      "loss": 0.33882084488868713,
+      "step": 136
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.182267386409593,
+      "learning_rate": 7.942209016057954e-06,
+      "loss": 0.36792832612991333,
+      "step": 137
+    },
+    {
+      "epoch": 1.0073260073260073,
+      "grad_norm": 1.0686033471580987,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.2894274592399597,
+      "step": 138
+    },
+    {
+      "epoch": 1.0146520146520146,
+      "grad_norm": 1.0153401594780536,
+      "learning_rate": 7.87618842141645e-06,
+      "loss": 0.30820950865745544,
+      "step": 139
+    },
+    {
+      "epoch": 1.021978021978022,
+      "grad_norm": 1.0573547123823617,
+      "learning_rate": 7.842892728583557e-06,
+      "loss": 0.2707104980945587,
+      "step": 140
+    },
+    {
+      "epoch": 1.0293040293040292,
+      "grad_norm": 1.068424976718832,
+      "learning_rate": 7.809409693426803e-06,
+      "loss": 0.2870473861694336,
+      "step": 141
+    },
+    {
+      "epoch": 1.0366300366300367,
+      "grad_norm": 1.108505986461051,
+      "learning_rate": 7.775741522427477e-06,
+      "loss": 0.27766191959381104,
+      "step": 142
+    },
+    {
+      "epoch": 1.043956043956044,
+      "grad_norm": 1.0788011444539796,
+      "learning_rate": 7.741890434267043e-06,
+      "loss": 0.2834435999393463,
+      "step": 143
+    },
+    {
+      "epoch": 1.0512820512820513,
+      "grad_norm": 1.2267316092589455,
+      "learning_rate": 7.707858659680924e-06,
+      "loss": 0.2835862338542938,
+      "step": 144
+    },
+    {
+      "epoch": 1.0586080586080586,
+      "grad_norm": 1.3229066354461252,
+      "learning_rate": 7.67364844131151e-06,
+      "loss": 0.27477383613586426,
+      "step": 145
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 1.2384024803974207,
+      "learning_rate": 7.63926203356036e-06,
+      "loss": 0.2960669994354248,
+      "step": 146
+    },
+    {
+      "epoch": 1.0732600732600732,
+      "grad_norm": 1.18044187380908,
+      "learning_rate": 7.604701702439652e-06,
+      "loss": 0.2972232699394226,
+      "step": 147
+    },
+    {
+      "epoch": 1.0805860805860805,
+      "grad_norm": 1.2009282809760102,
+      "learning_rate": 7.5699697254228496e-06,
+      "loss": 0.2825266420841217,
+      "step": 148
+    },
+    {
+      "epoch": 1.0879120879120878,
+      "grad_norm": 1.019088056663372,
+      "learning_rate": 7.535068391294618e-06,
+      "loss": 0.29965272545814514,
+      "step": 149
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 1.1839639402543083,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.29271137714385986,
+      "step": 150
+    },
+    {
+      "epoch": 1.1025641025641026,
+      "grad_norm": 1.0809429287242711,
+      "learning_rate": 7.464766862492856e-06,
+      "loss": 0.2796112298965454,
+      "step": 151
+    },
+    {
+      "epoch": 1.10989010989011,
+      "grad_norm": 1.1992697090491269,
+      "learning_rate": 7.42937130058357e-06,
+      "loss": 0.28620994091033936,
+      "step": 152
+    },
+    {
+      "epoch": 1.1172161172161172,
+      "grad_norm": 1.1027252290575018,
+      "learning_rate": 7.393815646786047e-06,
+      "loss": 0.2959006428718567,
+      "step": 153
+    },
+    {
+      "epoch": 1.1245421245421245,
+      "grad_norm": 1.0120783087707164,
+      "learning_rate": 7.358102244164003e-06,
+      "loss": 0.29200655221939087,
+      "step": 154
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 1.1552817802815585,
+      "learning_rate": 7.322233446176571e-06,
+      "loss": 0.29077982902526855,
+      "step": 155
+    },
+    {
+      "epoch": 1.1391941391941391,
+      "grad_norm": 1.1540271695101154,
+      "learning_rate": 7.286211616523193e-06,
+      "loss": 0.29103994369506836,
+      "step": 156
+    },
+    {
+      "epoch": 1.1465201465201464,
+      "grad_norm": 1.0723601056663603,
+      "learning_rate": 7.250039128987874e-06,
+      "loss": 0.2747235894203186,
+      "step": 157
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.1487058706441489,
+      "learning_rate": 7.213718367282737e-06,
+      "loss": 0.30069500207901,
+      "step": 158
+    },
+    {
+      "epoch": 1.1611721611721613,
+      "grad_norm": 1.3318093229671866,
+      "learning_rate": 7.177251724890957e-06,
+      "loss": 0.3071703314781189,
+      "step": 159
+    },
+    {
+      "epoch": 1.1684981684981686,
+      "grad_norm": 1.1534532452958286,
+      "learning_rate": 7.14064160490902e-06,
+      "loss": 0.28914874792099,
+      "step": 160
+    },
+    {
+      "epoch": 1.1758241758241759,
+      "grad_norm": 1.1547701660303746,
+      "learning_rate": 7.103890419888367e-06,
+      "loss": 0.3017809987068176,
+      "step": 161
+    },
+    {
+      "epoch": 1.1831501831501832,
+      "grad_norm": 1.2947227089667261,
+      "learning_rate": 7.067000591676416e-06,
+      "loss": 0.3369286060333252,
+      "step": 162
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 1.1140895594029996,
+      "learning_rate": 7.029974551256957e-06,
+      "loss": 0.27125978469848633,
+      "step": 163
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 1.0122537303440942,
+      "learning_rate": 6.992814738589958e-06,
+      "loss": 0.28907060623168945,
+      "step": 164
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 1.025657300579659,
+      "learning_rate": 6.95552360245078e-06,
+      "loss": 0.2677385210990906,
+      "step": 165
+    },
+    {
+      "epoch": 1.2124542124542124,
+      "grad_norm": 1.0823638919225964,
+      "learning_rate": 6.9181036002687985e-06,
+      "loss": 0.27675288915634155,
+      "step": 166
+    },
+    {
+      "epoch": 1.2197802197802199,
+      "grad_norm": 1.0413163959584528,
+      "learning_rate": 6.880557197965465e-06,
+      "loss": 0.3112404942512512,
+      "step": 167
+    },
+    {
+      "epoch": 1.2271062271062272,
+      "grad_norm": 1.0645554729563804,
+      "learning_rate": 6.84288686979181e-06,
+      "loss": 0.2850072383880615,
+      "step": 168
+    },
+    {
+      "epoch": 1.2344322344322345,
+      "grad_norm": 0.8982420186922085,
+      "learning_rate": 6.805095098165388e-06,
+      "loss": 0.26976898312568665,
+      "step": 169
+    },
+    {
+      "epoch": 1.2417582417582418,
+      "grad_norm": 1.1333676300011672,
+      "learning_rate": 6.767184373506698e-06,
+      "loss": 0.2745368480682373,
+      "step": 170
+    },
+    {
+      "epoch": 1.249084249084249,
+      "grad_norm": 1.0709277161683297,
+      "learning_rate": 6.7291571940750575e-06,
+      "loss": 0.2779650390148163,
+      "step": 171
+    },
+    {
+      "epoch": 1.2564102564102564,
+      "grad_norm": 1.0868456188418263,
+      "learning_rate": 6.6910160658039835e-06,
+      "loss": 0.3108050227165222,
+      "step": 172
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 1.1874804808558082,
+      "learning_rate": 6.652763502136044e-06,
+      "loss": 0.27616167068481445,
+      "step": 173
+    },
+    {
+      "epoch": 1.271062271062271,
+      "grad_norm": 1.0270742547414067,
+      "learning_rate": 6.614402023857231e-06,
+      "loss": 0.26505476236343384,
+      "step": 174
+    },
+    {
+      "epoch": 1.2783882783882783,
+      "grad_norm": 0.9281377603059646,
+      "learning_rate": 6.57593415893085e-06,
+      "loss": 0.26481738686561584,
+      "step": 175
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.0894098307492133,
+      "learning_rate": 6.5373624423309165e-06,
+      "loss": 0.27870288491249084,
+      "step": 176
+    },
+    {
+      "epoch": 1.293040293040293,
+      "grad_norm": 1.074181253190212,
+      "learning_rate": 6.498689415875121e-06,
+      "loss": 0.29720550775527954,
+      "step": 177
+    },
+    {
+      "epoch": 1.3003663003663004,
+      "grad_norm": 1.0913740336999906,
+      "learning_rate": 6.459917628057319e-06,
+      "loss": 0.2793238162994385,
+      "step": 178
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 1.1164998009762015,
+      "learning_rate": 6.421049633879588e-06,
+      "loss": 0.3088657855987549,
+      "step": 179
+    },
+    {
+      "epoch": 1.315018315018315,
+      "grad_norm": 0.9299860686646102,
+      "learning_rate": 6.3820879946838585e-06,
+      "loss": 0.2543247938156128,
+      "step": 180
+    },
+    {
+      "epoch": 1.3223443223443223,
+      "grad_norm": 1.1571048592937423,
+      "learning_rate": 6.3430352779831275e-06,
+      "loss": 0.2909772992134094,
+      "step": 181
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 1.094026131808152,
+      "learning_rate": 6.303894057292261e-06,
+      "loss": 0.2640184164047241,
+      "step": 182
+    },
+    {
+      "epoch": 1.3369963369963371,
+      "grad_norm": 0.9363985633369026,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.2943224012851715,
+      "step": 183
+    },
+    {
+      "epoch": 1.3443223443223444,
+      "grad_norm": 1.0969037309510354,
+      "learning_rate": 6.225356426991007e-06,
+      "loss": 0.24726328253746033,
+      "step": 184
+    },
+    {
+      "epoch": 1.3516483516483517,
+      "grad_norm": 1.0885385789514508,
+      "learning_rate": 6.185965192891472e-06,
+      "loss": 0.2971659302711487,
+      "step": 185
+    },
+    {
+      "epoch": 1.358974358974359,
+      "grad_norm": 1.0158089498674099,
+      "learning_rate": 6.146495805482451e-06,
+      "loss": 0.29360431432724,
+      "step": 186
+    },
+    {
+      "epoch": 1.3663003663003663,
+      "grad_norm": 1.3591604878047607,
+      "learning_rate": 6.106950865736777e-06,
+      "loss": 0.2744835615158081,
+      "step": 187
+    },
+    {
+      "epoch": 1.3736263736263736,
+      "grad_norm": 1.0213784235417054,
+      "learning_rate": 6.067332979606069e-06,
+      "loss": 0.2648021876811981,
+      "step": 188
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 1.0816098136800893,
+      "learning_rate": 6.027644757849004e-06,
+      "loss": 0.32366281747817993,
+      "step": 189
+    },
+    {
+      "epoch": 1.3882783882783882,
+      "grad_norm": 1.0884347912067143,
+      "learning_rate": 5.987888815859266e-06,
+      "loss": 0.2866742014884949,
+      "step": 190
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.915669390965943,
+      "learning_rate": 5.948067773493205e-06,
+      "loss": 0.30587273836135864,
+      "step": 191
+    },
+    {
+      "epoch": 1.4029304029304028,
+      "grad_norm": 1.0927318653030724,
+      "learning_rate": 5.908184254897183e-06,
+      "loss": 0.314590185880661,
+      "step": 192
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 1.1120641499678694,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.30427268147468567,
+      "step": 193
+    },
+    {
+      "epoch": 1.4175824175824177,
+      "grad_norm": 1.004808225175699,
+      "learning_rate": 5.828240306012957e-06,
+      "loss": 0.26962751150131226,
+      "step": 194
+    },
+    {
+      "epoch": 1.424908424908425,
+      "grad_norm": 1.1800129602480383,
+      "learning_rate": 5.788185143909868e-06,
+      "loss": 0.3093605637550354,
+      "step": 195
+    },
+    {
+      "epoch": 1.4322344322344323,
+      "grad_norm": 1.1081211032827851,
+      "learning_rate": 5.74807804159989e-06,
+      "loss": 0.2661038935184479,
+      "step": 196
+    },
+    {
+      "epoch": 1.4395604395604396,
+      "grad_norm": 1.0397696208232112,
+      "learning_rate": 5.7079216420803e-06,
+      "loss": 0.26260125637054443,
+      "step": 197
+    },
+    {
+      "epoch": 1.4468864468864469,
+      "grad_norm": 1.0675565712457995,
+      "learning_rate": 5.66771859159699e-06,
+      "loss": 0.30148035287857056,
+      "step": 198
+    },
+    {
+      "epoch": 1.4542124542124542,
+      "grad_norm": 1.0592600391219584,
+      "learning_rate": 5.6274715394700805e-06,
+      "loss": 0.2963045537471771,
+      "step": 199
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 1.1774403611908744,
+      "learning_rate": 5.587183137919332e-06,
+      "loss": 0.3152458071708679,
+      "step": 200
+    },
+    {
+      "epoch": 1.468864468864469,
+      "grad_norm": 1.0787649372567354,
+      "learning_rate": 5.546856041889374e-06,
+      "loss": 0.27110299468040466,
+      "step": 201
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.9830650827059149,
+      "learning_rate": 5.5064929088747324e-06,
+      "loss": 0.28375378251075745,
+      "step": 202
+    },
+    {
+      "epoch": 1.4835164835164836,
+      "grad_norm": 1.134296905235914,
+      "learning_rate": 5.46609639874473e-06,
+      "loss": 0.29090097546577454,
+      "step": 203
+    },
+    {
+      "epoch": 1.4908424908424909,
+      "grad_norm": 1.282298463772494,
+      "learning_rate": 5.425669173568179e-06,
+      "loss": 0.3167083263397217,
+      "step": 204
+    },
+    {
+      "epoch": 1.4981684981684982,
+      "grad_norm": 1.0742616101894822,
+      "learning_rate": 5.385213897437975e-06,
+      "loss": 0.25165435671806335,
+      "step": 205
+    },
+    {
+      "epoch": 1.5054945054945055,
+      "grad_norm": 1.1328142095892046,
+      "learning_rate": 5.344733236295525e-06,
+      "loss": 0.27617213129997253,
+      "step": 206
+    },
+    {
+      "epoch": 1.5128205128205128,
+      "grad_norm": 1.0219367549951983,
+      "learning_rate": 5.30422985775507e-06,
+      "loss": 0.25958195328712463,
+      "step": 207
+    },
+    {
+      "epoch": 1.52014652014652,
+      "grad_norm": 1.0847411482729885,
+      "learning_rate": 5.263706430927895e-06,
+      "loss": 0.2788093686103821,
+      "step": 208
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 1.2394999596242242,
+      "learning_rate": 5.223165626246432e-06,
+      "loss": 0.30942243337631226,
+      "step": 209
+    },
+    {
+      "epoch": 1.5347985347985347,
+      "grad_norm": 1.0406322641722239,
+      "learning_rate": 5.182610115288296e-06,
+      "loss": 0.3002859950065613,
+      "step": 210
+    },
+    {
+      "epoch": 1.542124542124542,
+      "grad_norm": 1.0478051687617,
+      "learning_rate": 5.142042570600212e-06,
+      "loss": 0.2850934565067291,
+      "step": 211
+    },
+    {
+      "epoch": 1.5494505494505495,
+      "grad_norm": 1.082184087642848,
+      "learning_rate": 5.101465665521919e-06,
+      "loss": 0.29597795009613037,
+      "step": 212
+    },
+    {
+      "epoch": 1.5567765567765568,
+      "grad_norm": 1.1107024805480228,
+      "learning_rate": 5.060882074009988e-06,
+      "loss": 0.3078245520591736,
+      "step": 213
+    },
+    {
+      "epoch": 1.564102564102564,
+      "grad_norm": 1.0296929677102222,
+      "learning_rate": 5.020294470461615e-06,
+      "loss": 0.2921220064163208,
+      "step": 214
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 1.0540827764915854,
+      "learning_rate": 4.979705529538385e-06,
+      "loss": 0.2733391523361206,
+      "step": 215
+    },
+    {
+      "epoch": 1.578754578754579,
+      "grad_norm": 0.9652888358034895,
+      "learning_rate": 4.939117925990013e-06,
+      "loss": 0.2933793365955353,
+      "step": 216
+    },
+    {
+      "epoch": 1.5860805860805862,
+      "grad_norm": 1.1196595116135142,
+      "learning_rate": 4.8985343344780815e-06,
+      "loss": 0.31104928255081177,
+      "step": 217
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 1.0078579598513866,
+      "learning_rate": 4.857957429399788e-06,
+      "loss": 0.2975787818431854,
+      "step": 218
+    },
+    {
+      "epoch": 1.6007326007326008,
+      "grad_norm": 1.003543299759328,
+      "learning_rate": 4.817389884711706e-06,
+      "loss": 0.2911156117916107,
+      "step": 219
+    },
+    {
+      "epoch": 1.6080586080586081,
+      "grad_norm": 1.117174701168215,
+      "learning_rate": 4.7768343737535694e-06,
+      "loss": 0.28502243757247925,
+      "step": 220
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 1.2387468209978119,
+      "learning_rate": 4.736293569072108e-06,
+      "loss": 0.3383062779903412,
+      "step": 221
+    },
+    {
+      "epoch": 1.6227106227106227,
+      "grad_norm": 0.9751319932294236,
+      "learning_rate": 4.695770142244931e-06,
+      "loss": 0.26932916045188904,
+      "step": 222
+    },
+    {
+      "epoch": 1.63003663003663,
+      "grad_norm": 1.0756446276168852,
+      "learning_rate": 4.655266763704476e-06,
+      "loss": 0.2709274888038635,
+      "step": 223
+    },
+    {
+      "epoch": 1.6373626373626373,
+      "grad_norm": 1.0873882111356061,
+      "learning_rate": 4.614786102562026e-06,
+      "loss": 0.30510762333869934,
+      "step": 224
+    },
+    {
+      "epoch": 1.6446886446886446,
+      "grad_norm": 0.9991578718833676,
+      "learning_rate": 4.574330826431822e-06,
+      "loss": 0.271587610244751,
+      "step": 225
+    },
+    {
+      "epoch": 1.652014652014652,
+      "grad_norm": 0.9959466132377315,
+      "learning_rate": 4.533903601255272e-06,
+      "loss": 0.27231907844543457,
+      "step": 226
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 1.1774838310535634,
+      "learning_rate": 4.493507091125269e-06,
+      "loss": 0.2669839560985565,
+      "step": 227
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.0881926934718549,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.2904966175556183,
+      "step": 228
+    },
+    {
+      "epoch": 1.673992673992674,
+      "grad_norm": 1.1146102161723215,
+      "learning_rate": 4.412816862080668e-06,
+      "loss": 0.2829638123512268,
+      "step": 229
+    },
+    {
+      "epoch": 1.6813186813186813,
+      "grad_norm": 1.1410084762917667,
+      "learning_rate": 4.37252846052992e-06,
+      "loss": 0.31257230043411255,
+      "step": 230
+    },
+    {
+      "epoch": 1.6886446886446886,
+      "grad_norm": 1.1796551533789368,
+      "learning_rate": 4.332281408403011e-06,
+      "loss": 0.2940324544906616,
+      "step": 231
+    },
+    {
+      "epoch": 1.695970695970696,
+      "grad_norm": 0.9380068545214617,
+      "learning_rate": 4.292078357919701e-06,
+      "loss": 0.27315038442611694,
+      "step": 232
+    },
+    {
+      "epoch": 1.7032967032967035,
+      "grad_norm": 1.1309971396055292,
+      "learning_rate": 4.2519219584001106e-06,
+      "loss": 0.31711578369140625,
+      "step": 233
+    },
+    {
+      "epoch": 1.7106227106227108,
+      "grad_norm": 1.0898708429146375,
+      "learning_rate": 4.2118148560901325e-06,
+      "loss": 0.27645236253738403,
+      "step": 234
+    },
+    {
+      "epoch": 1.717948717948718,
+      "grad_norm": 0.9890674690676207,
+      "learning_rate": 4.171759693987046e-06,
+      "loss": 0.2982947528362274,
+      "step": 235
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 1.0308735193031042,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.27972856163978577,
+      "step": 236
+    },
+    {
+      "epoch": 1.7326007326007327,
+      "grad_norm": 0.9974962409078789,
+      "learning_rate": 4.091815745102818e-06,
+      "loss": 0.2757408916950226,
+      "step": 237
+    },
+    {
+      "epoch": 1.73992673992674,
+      "grad_norm": 1.040632796534077,
+      "learning_rate": 4.051932226506797e-06,
+      "loss": 0.2961726784706116,
+      "step": 238
+    },
+    {
+      "epoch": 1.7472527472527473,
+      "grad_norm": 1.0688391666784938,
+      "learning_rate": 4.0121111841407345e-06,
+      "loss": 0.2576867938041687,
+      "step": 239
+    },
+    {
+      "epoch": 1.7545787545787546,
+      "grad_norm": 1.044156456246768,
+      "learning_rate": 3.9723552421509975e-06,
+      "loss": 0.27895694971084595,
+      "step": 240
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.9743851064122274,
+      "learning_rate": 3.932667020393933e-06,
+      "loss": 0.2776602804660797,
+      "step": 241
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.9129387125371341,
+      "learning_rate": 3.8930491342632235e-06,
+      "loss": 0.2480865716934204,
+      "step": 242
+    },
+    {
+      "epoch": 1.7765567765567765,
+      "grad_norm": 1.0565234983933456,
+      "learning_rate": 3.853504194517551e-06,
+      "loss": 0.290374755859375,
+      "step": 243
+    },
+    {
+      "epoch": 1.7838827838827838,
+      "grad_norm": 1.0245173104357006,
+      "learning_rate": 3.814034807108529e-06,
+      "loss": 0.27799317240715027,
+      "step": 244
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 1.1247482481535258,
+      "learning_rate": 3.774643573008995e-06,
+      "loss": 0.287639319896698,
+      "step": 245
+    },
+    {
+      "epoch": 1.7985347985347986,
+      "grad_norm": 1.2831629362435393,
+      "learning_rate": 3.7353330880415963e-06,
+      "loss": 0.2996615171432495,
+      "step": 246
+    },
+    {
+      "epoch": 1.8058608058608059,
+      "grad_norm": 0.9631002049148443,
+      "learning_rate": 3.6961059427077407e-06,
+      "loss": 0.2891607880592346,
+      "step": 247
+    },
+    {
+      "epoch": 1.8131868131868132,
+      "grad_norm": 1.0326234643935235,
+      "learning_rate": 3.656964722016875e-06,
+      "loss": 0.2577850818634033,
+      "step": 248
+    },
+    {
+      "epoch": 1.8205128205128205,
+      "grad_norm": 0.9666099123254006,
+      "learning_rate": 3.617912005316142e-06,
+      "loss": 0.25415879487991333,
+      "step": 249
+    },
+    {
+      "epoch": 1.8278388278388278,
+      "grad_norm": 0.9577101943470598,
+      "learning_rate": 3.578950366120414e-06,
+      "loss": 0.2674415111541748,
+      "step": 250
+    },
+    {
+      "epoch": 1.8351648351648353,
+      "grad_norm": 1.2104620184418453,
+      "learning_rate": 3.540082371942682e-06,
+      "loss": 0.29486364126205444,
+      "step": 251
+    },
+    {
+      "epoch": 1.8424908424908426,
+      "grad_norm": 1.1130183230560342,
+      "learning_rate": 3.5013105841248794e-06,
+      "loss": 0.28867706656455994,
+      "step": 252
+    },
+    {
+      "epoch": 1.84981684981685,
+      "grad_norm": 0.960795493916683,
+      "learning_rate": 3.462637557669084e-06,
+      "loss": 0.27347224950790405,
+      "step": 253
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 1.053963606829607,
+      "learning_rate": 3.424065841069152e-06,
+      "loss": 0.27742648124694824,
+      "step": 254
+    },
+    {
+      "epoch": 1.8644688644688645,
+      "grad_norm": 1.073637011494531,
+      "learning_rate": 3.3855979761427705e-06,
+      "loss": 0.30111193656921387,
+      "step": 255
+    },
+    {
+      "epoch": 1.8717948717948718,
+      "grad_norm": 1.006804490181391,
+      "learning_rate": 3.347236497863957e-06,
+      "loss": 0.2510993182659149,
+      "step": 256
+    },
+    {
+      "epoch": 1.879120879120879,
+      "grad_norm": 0.9797151960888058,
+      "learning_rate": 3.308983934196018e-06,
+      "loss": 0.2800617218017578,
+      "step": 257
+    },
+    {
+      "epoch": 1.8864468864468864,
+      "grad_norm": 1.1964125842584994,
+      "learning_rate": 3.2708428059249437e-06,
+      "loss": 0.28070536255836487,
+      "step": 258
+    },
+    {
+      "epoch": 1.8937728937728937,
+      "grad_norm": 1.0143522113609016,
+      "learning_rate": 3.2328156264933043e-06,
+      "loss": 0.28813984990119934,
+      "step": 259
+    },
+    {
+      "epoch": 1.901098901098901,
+      "grad_norm": 1.0887942458637438,
+      "learning_rate": 3.194904901834613e-06,
+      "loss": 0.27424943447113037,
+      "step": 260
+    },
+    {
+      "epoch": 1.9084249084249083,
+      "grad_norm": 0.9073919323524343,
+      "learning_rate": 3.1571131302081916e-06,
+      "loss": 0.2768292725086212,
+      "step": 261
+    },
+    {
+      "epoch": 1.9157509157509156,
+      "grad_norm": 0.9850360881093612,
+      "learning_rate": 3.1194428020345375e-06,
+      "loss": 0.318487286567688,
+      "step": 262
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.0090745199197444,
+      "learning_rate": 3.081896399731202e-06,
+      "loss": 0.2533684968948364,
+      "step": 263
+    },
+    {
+      "epoch": 1.9304029304029304,
+      "grad_norm": 1.1058329729628358,
+      "learning_rate": 3.044476397549221e-06,
+      "loss": 0.27426987886428833,
+      "step": 264
+    },
+    {
+      "epoch": 1.9377289377289377,
+      "grad_norm": 1.0176581083684877,
+      "learning_rate": 3.0071852614100427e-06,
+      "loss": 0.27716314792633057,
+      "step": 265
+    },
+    {
+      "epoch": 1.945054945054945,
+      "grad_norm": 1.0536498699210162,
+      "learning_rate": 2.9700254487430448e-06,
+      "loss": 0.2791192829608917,
+      "step": 266
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 1.1327721722858968,
+      "learning_rate": 2.9329994083235857e-06,
+      "loss": 0.2645677626132965,
+      "step": 267
+    },
+    {
+      "epoch": 1.9597069597069599,
+      "grad_norm": 1.078652769506114,
+      "learning_rate": 2.896109580111634e-06,
+      "loss": 0.27191221714019775,
+      "step": 268
+    },
+    {
+      "epoch": 1.9670329670329672,
+      "grad_norm": 1.1837421082764947,
+      "learning_rate": 2.8593583950909833e-06,
+      "loss": 0.2969869375228882,
+      "step": 269
+    },
+    {
+      "epoch": 1.9743589743589745,
+      "grad_norm": 0.9930141875119173,
+      "learning_rate": 2.8227482751090445e-06,
+      "loss": 0.25214335322380066,
+      "step": 270
+    },
+    {
+      "epoch": 1.9816849816849818,
+      "grad_norm": 1.0475298808452358,
+      "learning_rate": 2.786281632717264e-06,
+      "loss": 0.29422906041145325,
+      "step": 271
+    },
+    {
+      "epoch": 1.989010989010989,
+      "grad_norm": 1.0442095186311762,
+      "learning_rate": 2.749960871012129e-06,
+      "loss": 0.30069488286972046,
+      "step": 272
+    },
+    {
+      "epoch": 1.9963369963369964,
+      "grad_norm": 0.9446344835083768,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.29935750365257263,
+      "step": 273
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8903335357771034,
+      "learning_rate": 2.6777665538234292e-06,
+      "loss": 0.26212257146835327,
+      "step": 274
+    },
+    {
+      "epoch": 2.0073260073260073,
+      "grad_norm": 1.0872778312217004,
+      "learning_rate": 2.641897755835997e-06,
+      "loss": 0.2080368995666504,
+      "step": 275
+    },
+    {
+      "epoch": 2.0146520146520146,
+      "grad_norm": 1.153142895526473,
+      "learning_rate": 2.6061843532139563e-06,
+      "loss": 0.22341328859329224,
+      "step": 276
+    },
+    {
+      "epoch": 2.021978021978022,
+      "grad_norm": 0.9779095973602308,
+      "learning_rate": 2.5706286994164315e-06,
+      "loss": 0.22445546090602875,
+      "step": 277
+    },
+    {
+      "epoch": 2.029304029304029,
+      "grad_norm": 1.1817760186238315,
+      "learning_rate": 2.5352331375071437e-06,
+      "loss": 0.23708981275558472,
+      "step": 278
+    },
+    {
+      "epoch": 2.0366300366300365,
+      "grad_norm": 1.023239338905551,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.22113129496574402,
+      "step": 279
+    },
+    {
+      "epoch": 2.043956043956044,
+      "grad_norm": 1.1289343692866138,
+      "learning_rate": 2.464931608705384e-06,
+      "loss": 0.24936091899871826,
+      "step": 280
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 1.0298366936737875,
+      "learning_rate": 2.430030274577151e-06,
+      "loss": 0.22182141244411469,
+      "step": 281
+    },
+    {
+      "epoch": 2.0586080586080584,
+      "grad_norm": 0.9322342047480516,
+      "learning_rate": 2.3952982975603494e-06,
+      "loss": 0.24618740379810333,
+      "step": 282
+    },
+    {
+      "epoch": 2.065934065934066,
+      "grad_norm": 1.301143268306206,
+      "learning_rate": 2.3607379664396414e-06,
+      "loss": 0.22918632626533508,
+      "step": 283
+    },
+    {
+      "epoch": 2.0732600732600734,
+      "grad_norm": 1.0677424151131676,
+      "learning_rate": 2.3263515586884935e-06,
+      "loss": 0.2351371943950653,
+      "step": 284
+    },
+    {
+      "epoch": 2.0805860805860807,
+      "grad_norm": 1.122503313580565,
+      "learning_rate": 2.2921413403190774e-06,
+      "loss": 0.23036789894104004,
+      "step": 285
+    },
+    {
+      "epoch": 2.087912087912088,
+      "grad_norm": 1.0871719769548138,
+      "learning_rate": 2.25810956573296e-06,
+      "loss": 0.24664072692394257,
+      "step": 286
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 1.072946930604994,
+      "learning_rate": 2.224258477572524e-06,
+      "loss": 0.2169453501701355,
+      "step": 287
+    },
+    {
+      "epoch": 2.1025641025641026,
+      "grad_norm": 1.1552824570087117,
+      "learning_rate": 2.190590306573198e-06,
+      "loss": 0.23637241125106812,
+      "step": 288
+    },
+    {
+      "epoch": 2.10989010989011,
+      "grad_norm": 1.0605290517940913,
+      "learning_rate": 2.1571072714164445e-06,
+      "loss": 0.22414323687553406,
+      "step": 289
+    },
+    {
+      "epoch": 2.1172161172161172,
+      "grad_norm": 1.043154934258016,
+      "learning_rate": 2.1238115785835512e-06,
+      "loss": 0.22473719716072083,
+      "step": 290
+    },
+    {
+      "epoch": 2.1245421245421245,
+      "grad_norm": 1.2211410010717425,
+      "learning_rate": 2.0907054222102367e-06,
+      "loss": 0.21707648038864136,
+      "step": 291
+    },
+    {
+      "epoch": 2.131868131868132,
+      "grad_norm": 1.0642724049563004,
+      "learning_rate": 2.0577909839420468e-06,
+      "loss": 0.21333038806915283,
+      "step": 292
+    },
+    {
+      "epoch": 2.139194139194139,
+      "grad_norm": 1.0298997037587465,
+      "learning_rate": 2.0250704327906025e-06,
+      "loss": 0.23482055962085724,
+      "step": 293
+    },
+    {
+      "epoch": 2.1465201465201464,
+      "grad_norm": 1.2521151418866294,
+      "learning_rate": 1.9925459249906488e-06,
+      "loss": 0.24669216573238373,
+      "step": 294
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.0015347552107015,
+      "learning_rate": 1.9602196038579774e-06,
+      "loss": 0.21570074558258057,
+      "step": 295
+    },
+    {
+      "epoch": 2.161172161172161,
+      "grad_norm": 1.1363173380860716,
+      "learning_rate": 1.9280935996481792e-06,
+      "loss": 0.21716558933258057,
+      "step": 296
+    },
+    {
+      "epoch": 2.1684981684981683,
+      "grad_norm": 1.1171710714186258,
+      "learning_rate": 1.8961700294162578e-06,
+      "loss": 0.2021581530570984,
+      "step": 297
+    },
+    {
+      "epoch": 2.1758241758241756,
+      "grad_norm": 1.0929444504935302,
+      "learning_rate": 1.8644509968771302e-06,
+      "loss": 0.2062225341796875,
+      "step": 298
+    },
+    {
+      "epoch": 2.183150183150183,
+      "grad_norm": 1.041045504034978,
+      "learning_rate": 1.832938592266984e-06,
+      "loss": 0.2139657437801361,
+      "step": 299
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 1.057190385371437,
+      "learning_rate": 1.8016348922055448e-06,
+      "loss": 0.1996728926897049,
+      "step": 300
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 1.1946122105787467,
+      "learning_rate": 1.7705419595592193e-06,
+      "loss": 0.25132063031196594,
+      "step": 301
+    },
+    {
+      "epoch": 2.2051282051282053,
+      "grad_norm": 0.9259953268131886,
+      "learning_rate": 1.7396618433051648e-06,
+      "loss": 0.21299096941947937,
+      "step": 302
+    },
+    {
+      "epoch": 2.2124542124542126,
+      "grad_norm": 1.213328353826304,
+      "learning_rate": 1.7089965783962608e-06,
+      "loss": 0.2140902727842331,
+      "step": 303
+    },
+    {
+      "epoch": 2.21978021978022,
+      "grad_norm": 0.9761515672225444,
+      "learning_rate": 1.6785481856270042e-06,
+      "loss": 0.22363431751728058,
+      "step": 304
+    },
+    {
+      "epoch": 2.227106227106227,
+      "grad_norm": 1.155337550086334,
+      "learning_rate": 1.6483186715003523e-06,
+      "loss": 0.23464494943618774,
+      "step": 305
+    },
+    {
+      "epoch": 2.2344322344322345,
+      "grad_norm": 1.1140172781174638,
+      "learning_rate": 1.618310028095486e-06,
+      "loss": 0.21518093347549438,
+      "step": 306
+    },
+    {
+      "epoch": 2.241758241758242,
+      "grad_norm": 1.2179937873095439,
+      "learning_rate": 1.5885242329365448e-06,
+      "loss": 0.2589687705039978,
+      "step": 307
+    },
+    {
+      "epoch": 2.249084249084249,
+      "grad_norm": 1.083087208307822,
+      "learning_rate": 1.5589632488623053e-06,
+      "loss": 0.2202206552028656,
+      "step": 308
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 1.1247253618959971,
+      "learning_rate": 1.5296290238968303e-06,
+      "loss": 0.2516007423400879,
+      "step": 309
+    },
+    {
+      "epoch": 2.2637362637362637,
+      "grad_norm": 1.029732329010538,
+      "learning_rate": 1.500523491121108e-06,
+      "loss": 0.21486574411392212,
+      "step": 310
+    },
+    {
+      "epoch": 2.271062271062271,
+      "grad_norm": 1.522644892476846,
+      "learning_rate": 1.47164856854565e-06,
+      "loss": 0.22302576899528503,
+      "step": 311
+    },
+    {
+      "epoch": 2.2783882783882783,
+      "grad_norm": 1.0835410135357464,
+      "learning_rate": 1.4430061589841122e-06,
+      "loss": 0.2299138456583023,
+      "step": 312
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.1608076314086253,
+      "learning_rate": 1.4145981499278877e-06,
+      "loss": 0.2284044623374939,
+      "step": 313
+    },
+    {
+      "epoch": 2.293040293040293,
+      "grad_norm": 1.007806828890649,
+      "learning_rate": 1.386426413421738e-06,
+      "loss": 0.21568208932876587,
+      "step": 314
+    },
+    {
+      "epoch": 2.3003663003663,
+      "grad_norm": 1.110614593649845,
+      "learning_rate": 1.3584928059404207e-06,
+      "loss": 0.21330109238624573,
+      "step": 315
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.9269591001624151,
+      "learning_rate": 1.3307991682663463e-06,
+      "loss": 0.2049589455127716,
+      "step": 316
+    },
+    {
+      "epoch": 2.315018315018315,
+      "grad_norm": 1.030660764247251,
+      "learning_rate": 1.303347325368285e-06,
+      "loss": 0.23808613419532776,
+      "step": 317
+    },
+    {
+      "epoch": 2.3223443223443225,
+      "grad_norm": 1.0741881929381032,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.2274160087108612,
+      "step": 318
+    },
+    {
+      "epoch": 2.32967032967033,
+      "grad_norm": 1.23151478025897,
+      "learning_rate": 1.2491762439865034e-06,
+      "loss": 0.22255614399909973,
+      "step": 319
+    },
+    {
+      "epoch": 2.336996336996337,
+      "grad_norm": 1.120344003470698,
+      "learning_rate": 1.2224605752949786e-06,
+      "loss": 0.2374870479106903,
+      "step": 320
+    },
+    {
+      "epoch": 2.3443223443223444,
+      "grad_norm": 1.5560919363814774,
+      "learning_rate": 1.1959938407286099e-06,
+      "loss": 0.2206483781337738,
+      "step": 321
+    },
+    {
+      "epoch": 2.3516483516483517,
+      "grad_norm": 0.9655470657059726,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.20176303386688232,
+      "step": 322
+    },
+    {
+      "epoch": 2.358974358974359,
+      "grad_norm": 1.096436902395159,
+      "learning_rate": 1.143814133922872e-06,
+      "loss": 0.22084000706672668,
+      "step": 323
+    },
+    {
+      "epoch": 2.3663003663003663,
+      "grad_norm": 1.065227284623936,
+      "learning_rate": 1.1181046002471292e-06,
+      "loss": 0.20460768043994904,
+      "step": 324
+    },
+    {
+      "epoch": 2.3736263736263736,
+      "grad_norm": 1.0697198399954104,
+      "learning_rate": 1.0926508775971995e-06,
+      "loss": 0.21005329489707947,
+      "step": 325
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 1.119132681089307,
+      "learning_rate": 1.0674546433348453e-06,
+      "loss": 0.23384399712085724,
+      "step": 326
+    },
+    {
+      "epoch": 2.3882783882783882,
+      "grad_norm": 1.0612726585808296,
+      "learning_rate": 1.04251755785373e-06,
+      "loss": 0.2149549424648285,
+      "step": 327
+    },
+    {
+      "epoch": 2.3956043956043955,
+      "grad_norm": 1.1103936104585082,
+      "learning_rate": 1.0178412644700093e-06,
+      "loss": 0.23808100819587708,
+      "step": 328
+    },
+    {
+      "epoch": 2.402930402930403,
+      "grad_norm": 1.1803986673849467,
+      "learning_rate": 9.934273893140335e-07,
+      "loss": 0.21827144920825958,
+      "step": 329
+    },
+    {
+      "epoch": 2.41025641025641,
+      "grad_norm": 1.7607496045758002,
+      "learning_rate": 9.692775412231863e-07,
+      "loss": 0.2156897485256195,
+      "step": 330
+    },
+    {
+      "epoch": 2.4175824175824174,
+      "grad_norm": 1.0855693076540742,
+      "learning_rate": 9.453933116358715e-07,
+      "loss": 0.22576552629470825,
+      "step": 331
+    },
+    {
+      "epoch": 2.4249084249084247,
+      "grad_norm": 1.0458722036651498,
+      "learning_rate": 9.21776274486636e-07,
+      "loss": 0.2029896229505539,
+      "step": 332
+    },
+    {
+      "epoch": 2.4322344322344325,
+      "grad_norm": 1.0316218724135404,
+      "learning_rate": 8.984279861024453e-07,
+      "loss": 0.21579168736934662,
+      "step": 333
+    },
+    {
+      "epoch": 2.4395604395604398,
+      "grad_norm": 1.0481067715510672,
+      "learning_rate": 8.753499851001341e-07,
+      "loss": 0.2032783031463623,
+      "step": 334
+    },
+    {
+      "epoch": 2.446886446886447,
+      "grad_norm": 1.0255499821271086,
+      "learning_rate": 8.525437922850033e-07,
+      "loss": 0.21618527173995972,
+      "step": 335
+    },
+    {
+      "epoch": 2.4542124542124544,
+      "grad_norm": 1.2612515831683861,
+      "learning_rate": 8.30010910550611e-07,
+      "loss": 0.22778677940368652,
+      "step": 336
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.0389223185126732,
+      "learning_rate": 8.077528247797234e-07,
+      "loss": 0.21174968779087067,
+      "step": 337
+    },
+    {
+      "epoch": 2.468864468864469,
+      "grad_norm": 1.056290930403573,
+      "learning_rate": 7.857710017464737e-07,
+      "loss": 0.2388148009777069,
+      "step": 338
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 1.069550154228755,
+      "learning_rate": 7.640668900196985e-07,
+      "loss": 0.22967322170734406,
+      "step": 339
+    },
+    {
+      "epoch": 2.4835164835164836,
+      "grad_norm": 1.1293770611150251,
+      "learning_rate": 7.426419198674773e-07,
+      "loss": 0.22522856295108795,
+      "step": 340
+    },
+    {
+      "epoch": 2.490842490842491,
+      "grad_norm": 1.044662314903284,
+      "learning_rate": 7.214975031628856e-07,
+      "loss": 0.22356775403022766,
+      "step": 341
+    },
+    {
+      "epoch": 2.498168498168498,
+      "grad_norm": 1.8203551388983328,
+      "learning_rate": 7.006350332909495e-07,
+      "loss": 0.23231935501098633,
+      "step": 342
+    },
+    {
+      "epoch": 2.5054945054945055,
+      "grad_norm": 1.3212997188494113,
+      "learning_rate": 6.800558850568295e-07,
+      "loss": 0.2266559600830078,
+      "step": 343
+    },
+    {
+      "epoch": 2.5128205128205128,
+      "grad_norm": 0.9853631772097284,
+      "learning_rate": 6.597614145952136e-07,
+      "loss": 0.22157558798789978,
+      "step": 344
+    },
+    {
+      "epoch": 2.52014652014652,
+      "grad_norm": 0.9528136427940737,
+      "learning_rate": 6.397529592809615e-07,
+      "loss": 0.21530809998512268,
+      "step": 345
+    },
+    {
+      "epoch": 2.5274725274725274,
+      "grad_norm": 0.973961814473209,
+      "learning_rate": 6.20031837640967e-07,
+      "loss": 0.21502554416656494,
+      "step": 346
+    },
+    {
+      "epoch": 2.5347985347985347,
+      "grad_norm": 0.9865830937894688,
+      "learning_rate": 6.005993492672657e-07,
+      "loss": 0.23088479042053223,
+      "step": 347
+    },
+    {
+      "epoch": 2.542124542124542,
+      "grad_norm": 1.031234686449057,
+      "learning_rate": 5.814567747314049e-07,
+      "loss": 0.2098679542541504,
+      "step": 348
+    },
+    {
+      "epoch": 2.5494505494505493,
+      "grad_norm": 1.056068279344729,
+      "learning_rate": 5.626053755000421e-07,
+      "loss": 0.21406947076320648,
+      "step": 349
+    },
+    {
+      "epoch": 2.5567765567765566,
+      "grad_norm": 0.9374826580586869,
+      "learning_rate": 5.440463938518304e-07,
+      "loss": 0.21536314487457275,
+      "step": 350
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 1.2706543007223374,
+      "learning_rate": 5.25781052795541e-07,
+      "loss": 0.21673786640167236,
+      "step": 351
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0671257757787735,
+      "learning_rate": 5.078105559894791e-07,
+      "loss": 0.21061310172080994,
+      "step": 352
+    },
+    {
+      "epoch": 2.578754578754579,
+      "grad_norm": 0.9344178285162987,
+      "learning_rate": 4.901360876621597e-07,
+      "loss": 0.20954422652721405,
+      "step": 353
+    },
+    {
+      "epoch": 2.586080586080586,
+      "grad_norm": 0.9853291224784689,
+      "learning_rate": 4.727588125342669e-07,
+      "loss": 0.2262524664402008,
+      "step": 354
+    },
+    {
+      "epoch": 2.5934065934065935,
+      "grad_norm": 1.1287752995473084,
+      "learning_rate": 4.5567987574190677e-07,
+      "loss": 0.2586604356765747,
+      "step": 355
+    },
+    {
+      "epoch": 2.600732600732601,
+      "grad_norm": 1.0263217600262091,
+      "learning_rate": 4.3890040276114044e-07,
+      "loss": 0.21056286990642548,
+      "step": 356
+    },
+    {
+      "epoch": 2.608058608058608,
+      "grad_norm": 1.059496022645036,
+      "learning_rate": 4.224214993338149e-07,
+      "loss": 0.2316097766160965,
+      "step": 357
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 1.0445066802035055,
+      "learning_rate": 4.062442513947007e-07,
+      "loss": 0.2548368275165558,
+      "step": 358
+    },
+    {
+      "epoch": 2.6227106227106227,
+      "grad_norm": 1.0677332887683673,
+      "learning_rate": 3.903697249999289e-07,
+      "loss": 0.21376073360443115,
+      "step": 359
+    },
+    {
+      "epoch": 2.63003663003663,
+      "grad_norm": 1.0466606342655096,
+      "learning_rate": 3.747989662567403e-07,
+      "loss": 0.24471336603164673,
+      "step": 360
+    },
+    {
+      "epoch": 2.6373626373626373,
+      "grad_norm": 1.120513746514606,
+      "learning_rate": 3.595330012545445e-07,
+      "loss": 0.23034799098968506,
+      "step": 361
+    },
+    {
+      "epoch": 2.6446886446886446,
+      "grad_norm": 1.0798320309567475,
+      "learning_rate": 3.445728359973094e-07,
+      "loss": 0.20568513870239258,
+      "step": 362
+    },
+    {
+      "epoch": 2.652014652014652,
+      "grad_norm": 1.103445307324226,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.24212944507598877,
+      "step": 363
+    },
+    {
+      "epoch": 2.659340659340659,
+      "grad_norm": 1.0111358189326647,
+      "learning_rate": 3.1557382790991686e-07,
+      "loss": 0.216970294713974,
+      "step": 364
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.0318010970274858,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.23717445135116577,
+      "step": 365
+    },
+    {
+      "epoch": 2.6739926739926743,
+      "grad_norm": 1.1278229722297761,
+      "learning_rate": 2.878095858314278e-07,
+      "loss": 0.21703487634658813,
+      "step": 366
+    },
+    {
+      "epoch": 2.6813186813186816,
+      "grad_norm": 1.0063580032703539,
+      "learning_rate": 2.743928018017744e-07,
+      "loss": 0.19310849905014038,
+      "step": 367
+    },
+    {
+      "epoch": 2.688644688644689,
+      "grad_norm": 1.0725897334713086,
+      "learning_rate": 2.612874281272371e-07,
+      "loss": 0.21045850217342377,
+      "step": 368
+    },
+    {
+      "epoch": 2.695970695970696,
+      "grad_norm": 1.1432574967176703,
+      "learning_rate": 2.4849432843208786e-07,
+      "loss": 0.23722723126411438,
+      "step": 369
+    },
+    {
+      "epoch": 2.7032967032967035,
+      "grad_norm": 1.1944305105743942,
+      "learning_rate": 2.3601434576221548e-07,
+      "loss": 0.23865890502929688,
+      "step": 370
+    },
+    {
+      "epoch": 2.7106227106227108,
+      "grad_norm": 1.0134760129247256,
+      "learning_rate": 2.2384830252957068e-07,
+      "loss": 0.22348350286483765,
+      "step": 371
+    },
+    {
+      "epoch": 2.717948717948718,
+      "grad_norm": 0.9433770405793843,
+      "learning_rate": 2.1199700045797077e-07,
+      "loss": 0.2057940810918808,
+      "step": 372
+    },
+    {
+      "epoch": 2.7252747252747254,
+      "grad_norm": 1.101087652221433,
+      "learning_rate": 2.0046122053026697e-07,
+      "loss": 0.21743959188461304,
+      "step": 373
+    },
+    {
+      "epoch": 2.7326007326007327,
+      "grad_norm": 1.025514441353977,
+      "learning_rate": 1.8924172293688148e-07,
+      "loss": 0.21851155161857605,
+      "step": 374
+    },
+    {
+      "epoch": 2.73992673992674,
+      "grad_norm": 1.0627298559202316,
+      "learning_rate": 1.7833924702570725e-07,
+      "loss": 0.2246307134628296,
+      "step": 375
+    },
+    {
+      "epoch": 2.7472527472527473,
+      "grad_norm": 1.0363820350724882,
+      "learning_rate": 1.677545112533896e-07,
+      "loss": 0.20863071084022522,
+      "step": 376
+    },
+    {
+      "epoch": 2.7545787545787546,
+      "grad_norm": 0.9833790666928801,
+      "learning_rate": 1.5748821313798124e-07,
+      "loss": 0.2220936417579651,
+      "step": 377
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 1.1353105880296717,
+      "learning_rate": 1.4754102921297363e-07,
+      "loss": 0.22596627473831177,
+      "step": 378
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 1.098762154582319,
+      "learning_rate": 1.3791361498271704e-07,
+      "loss": 0.23951691389083862,
+      "step": 379
+    },
+    {
+      "epoch": 2.7765567765567765,
+      "grad_norm": 1.0516458633934982,
+      "learning_rate": 1.2860660487922616e-07,
+      "loss": 0.22323718667030334,
+      "step": 380
+    },
+    {
+      "epoch": 2.7838827838827838,
+      "grad_norm": 1.0766560868652186,
+      "learning_rate": 1.196206122203647e-07,
+      "loss": 0.2271801382303238,
+      "step": 381
+    },
+    {
+      "epoch": 2.791208791208791,
+      "grad_norm": 1.012988527675345,
+      "learning_rate": 1.1095622916943494e-07,
+      "loss": 0.2283664345741272,
+      "step": 382
+    },
+    {
+      "epoch": 2.7985347985347984,
+      "grad_norm": 1.0479928682412392,
+      "learning_rate": 1.0261402669615505e-07,
+      "loss": 0.24376513063907623,
+      "step": 383
+    },
+    {
+      "epoch": 2.8058608058608057,
+      "grad_norm": 1.0034449700163197,
+      "learning_rate": 9.459455453902866e-08,
+      "loss": 0.223099946975708,
+      "step": 384
+    },
+    {
+      "epoch": 2.813186813186813,
+      "grad_norm": 0.909745107199666,
+      "learning_rate": 8.68983411691221e-08,
+      "loss": 0.20832499861717224,
+      "step": 385
+    },
+    {
+      "epoch": 2.8205128205128203,
+      "grad_norm": 0.9952167120384509,
+      "learning_rate": 7.952589375523567e-08,
+      "loss": 0.21737533807754517,
+      "step": 386
+    },
+    {
+      "epoch": 2.8278388278388276,
+      "grad_norm": 0.9659352926198512,
+      "learning_rate": 7.247769813048644e-08,
+      "loss": 0.22568273544311523,
+      "step": 387
+    },
+    {
+      "epoch": 2.8351648351648353,
+      "grad_norm": 1.048929026784002,
+      "learning_rate": 6.575421876028721e-08,
+      "loss": 0.22502297163009644,
+      "step": 388
+    },
+    {
+      "epoch": 2.8424908424908426,
+      "grad_norm": 1.0019261712810552,
+      "learning_rate": 5.935589871174208e-08,
+      "loss": 0.21102303266525269,
+      "step": 389
+    },
+    {
+      "epoch": 2.84981684981685,
+      "grad_norm": 1.1048123277921031,
+      "learning_rate": 5.3283159624448745e-08,
+      "loss": 0.2348283976316452,
+      "step": 390
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.0414285166534145,
+      "learning_rate": 4.753640168271456e-08,
+      "loss": 0.22936861217021942,
+      "step": 391
+    },
+    {
+      "epoch": 2.8644688644688645,
+      "grad_norm": 1.2429631645211932,
+      "learning_rate": 4.211600358917989e-08,
+      "loss": 0.24630418419837952,
+      "step": 392
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 0.9924039773066393,
+      "learning_rate": 3.702232253986804e-08,
+      "loss": 0.22691383957862854,
+      "step": 393
+    },
+    {
+      "epoch": 2.879120879120879,
+      "grad_norm": 1.0577599551717047,
+      "learning_rate": 3.2255694200643003e-08,
+      "loss": 0.22667211294174194,
+      "step": 394
+    },
+    {
+      "epoch": 2.8864468864468864,
+      "grad_norm": 1.1382843631032735,
+      "learning_rate": 2.7816432685091598e-08,
+      "loss": 0.20482704043388367,
+      "step": 395
+    },
+    {
+      "epoch": 2.8937728937728937,
+      "grad_norm": 1.0580508429061475,
+      "learning_rate": 2.370483053382111e-08,
+      "loss": 0.23122745752334595,
+      "step": 396
+    },
+    {
+      "epoch": 2.901098901098901,
+      "grad_norm": 1.0549784779989113,
+      "learning_rate": 1.992115869518474e-08,
+      "loss": 0.23232720792293549,
+      "step": 397
+    },
+    {
+      "epoch": 2.9084249084249083,
+      "grad_norm": 1.0136739757000526,
+      "learning_rate": 1.6465666507425314e-08,
+      "loss": 0.24128326773643494,
+      "step": 398
+    },
+    {
+      "epoch": 2.9157509157509156,
+      "grad_norm": 1.1068489652877105,
+      "learning_rate": 1.333858168224178e-08,
+      "loss": 0.24579691886901855,
+      "step": 399
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.0482106591579268,
+      "learning_rate": 1.0540110289786742e-08,
+      "loss": 0.19634608924388885,
+      "step": 400
+    },
+    {
+      "epoch": 2.9304029304029307,
+      "grad_norm": 0.9986056076887907,
+      "learning_rate": 8.07043674508623e-09,
+      "loss": 0.2212928682565689,
+      "step": 401
+    },
+    {
+      "epoch": 2.937728937728938,
+      "grad_norm": 1.0118052358258176,
+      "learning_rate": 5.929723795884967e-09,
+      "loss": 0.21850597858428955,
+      "step": 402
+    },
+    {
+      "epoch": 2.9450549450549453,
+      "grad_norm": 0.9704495600656273,
+      "learning_rate": 4.1181125119221785e-09,
+      "loss": 0.21226581931114197,
+      "step": 403
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.966690163811677,
+      "learning_rate": 2.635722275638464e-09,
+      "loss": 0.21004317700862885,
+      "step": 404
+    },
+    {
+      "epoch": 2.95970695970696,
+      "grad_norm": 1.6033220723893016,
+      "learning_rate": 1.4826507743032071e-09,
+      "loss": 0.20844367146492004,
+      "step": 405
+    },
+    {
+      "epoch": 2.967032967032967,
+      "grad_norm": 1.076763214226366,
+      "learning_rate": 6.589739935819461e-10,
+      "loss": 0.21316523849964142,
+      "step": 406
+    },
+    {
+      "epoch": 2.9743589743589745,
+      "grad_norm": 1.1351171984487796,
+      "learning_rate": 1.6474621252704494e-10,
+      "loss": 0.21295702457427979,
+      "step": 407
+    },
+    {
+      "epoch": 2.9816849816849818,
+      "grad_norm": 0.9892972289109477,
+      "learning_rate": 0.0,
+      "loss": 0.19279634952545166,
+      "step": 408
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 408,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 179589737414656.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84534c17027eca94cf096c295d3c81798dbd6ac0aa984e4634f1116128bacbd3
+size 9080