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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,366 @@
+{
+  "model": "/data/yubo/models/Qwen2.5-Math-1.5B",
+  "model_type": "qwen2_5_math",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "flash_attn",
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "local_repo_path": null,
+  "template": "qwen2_5_math",
+  "system": null,
+  "max_length": null,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "response_prefix": null,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "use_chat_template": true,
+  "template_backend": "swift",
+  "dataset": [
+    "/data/yubo/CriticCoT/dsr_scripts_0514/dsr_one-shot_train_data_0514_p0.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "data_seed": 42,
+  "dataset_num_proc": 4,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "enable_cache": false,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "remove_unused_columns": false,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    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,
+  "load_dataset_config": null,
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "use_hf": true,
+  "hub_token": null,
+  "custom_register_path": [],
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "output_dir": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 128,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-06,
+  "weight_decay": 0.05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 200.0,
+  "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": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 2.0,
+  "save_total_limit": null,
+  "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,
+  "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": "nccl",
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2.0,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201",
+  "disable_tqdm": null,
+  "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": [
+    "none"
+  ],
+  "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_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": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "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,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "acc_steps": 1,
+  "eval_use_evalscope": false,
+  "eval_datasets": [],
+  "eval_limit": null,
+  "eval_datasets_args": null,
+  "eval_generation_config": null,
+  "freeze_parameters": [],
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "freeze_llm": false,
+  "freeze_vit": false,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": 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_mode": "cloud",
+  "add_version": true,
+  "resume_only_model": false,
+  "create_checkpoint_symlink": false,
+  "packing": false,
+  "lazy_tokenize": false,
+  "loss_type": null,
+  "optimizer": null,
+  "metric": null,
+  "zero_hpz_partition_size": null,
+  "rank": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen2.5-Math-1.5B",
+  "model_info": "ModelInfo(model_type='qwen2_5_math', model_dir='/data/yubo/models/Qwen2.5-Math-1.5B', torch_dtype=torch.bfloat16, max_model_len=4096, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_math', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Math-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Math-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Math-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Math-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Math-72B-Instruct', hf_model_id='Qwen/Qwen2.5-Math-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Math-1.5B', hf_model_id='Qwen/Qwen2.5-Math-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Math-7B', hf_model_id='Qwen/Qwen2.5-Math-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Math-72B', hf_model_id='Qwen/Qwen2.5-Math-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['math'])], template='qwen2_5_math', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ea56d429fc0>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=['math'])",
+  "model_dir": "/data/yubo/models/Qwen2.5-Math-1.5B",
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=128, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=200.0, 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='/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2, save_total_limit=None, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data/yubo/CriticCoT/ms-swift/output_models_dsr_1.5b_base_of_0517_p0/v0-20250517-184201', 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=[], 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5e7653281224ada57814015c3d6e567d37b4398cf2b7f13d8f617846dcbd9b
+size 3087467144

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": "<|endoftext|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.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 %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,954 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 91.78527607361963,
+  "eval_steps": 2,
+  "global_step": 92,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7852760736196319,
+      "grad_norm": 2.828015891236112,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.7344894409179688,
+      "memory(GiB)": 33.35,
+      "step": 1,
+      "token_acc": 0.8210270474011879,
+      "train_speed(iter/s)": 0.01508
+    },
+    {
+      "epoch": 1.7852760736196318,
+      "grad_norm": 5.560922634626607,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.4670829772949219,
+      "memory(GiB)": 39.33,
+      "step": 2,
+      "token_acc": 0.8254568857425018,
+      "train_speed(iter/s)": 0.015066
+    },
+    {
+      "epoch": 2.785276073619632,
+      "grad_norm": 5.459222412898219,
+      "learning_rate": 1.5e-06,
+      "loss": 1.452088713645935,
+      "memory(GiB)": 39.33,
+      "step": 3,
+      "token_acc": 0.8195757791207489,
+      "train_speed(iter/s)": 0.014624
+    },
+    {
+      "epoch": 3.785276073619632,
+      "grad_norm": 5.463168612488766,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4775556325912476,
+      "memory(GiB)": 39.33,
+      "step": 4,
+      "token_acc": 0.823338222352596,
+      "train_speed(iter/s)": 0.014761
+    },
+    {
+      "epoch": 4.785276073619632,
+      "grad_norm": 5.608488489325384,
+      "learning_rate": 2.5e-06,
+      "loss": 1.4884722232818604,
+      "memory(GiB)": 39.33,
+      "step": 5,
+      "token_acc": 0.8191892680081656,
+      "train_speed(iter/s)": 0.014538
+    },
+    {
+      "epoch": 5.785276073619632,
+      "grad_norm": 5.119511687917419,
+      "learning_rate": 3e-06,
+      "loss": 1.4214377403259277,
+      "memory(GiB)": 39.33,
+      "step": 6,
+      "token_acc": 0.8322302158273381,
+      "train_speed(iter/s)": 0.014634
+    },
+    {
+      "epoch": 6.785276073619632,
+      "grad_norm": 5.315421901389787,
+      "learning_rate": 3.5e-06,
+      "loss": 1.4595433473587036,
+      "memory(GiB)": 39.33,
+      "step": 7,
+      "token_acc": 0.8237858651099242,
+      "train_speed(iter/s)": 0.014497
+    },
+    {
+      "epoch": 7.785276073619632,
+      "grad_norm": 4.5538985334897495,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4617054462432861,
+      "memory(GiB)": 39.33,
+      "step": 8,
+      "token_acc": 0.8285934756595355,
+      "train_speed(iter/s)": 0.014575
+    },
+    {
+      "epoch": 8.785276073619633,
+      "grad_norm": 4.50876794473483,
+      "learning_rate": 4.5e-06,
+      "loss": 1.3948967456817627,
+      "memory(GiB)": 39.33,
+      "step": 9,
+      "token_acc": 0.8302743891270103,
+      "train_speed(iter/s)": 0.01447
+    },
+    {
+      "epoch": 9.785276073619633,
+      "grad_norm": 3.214342485444024,
+      "learning_rate": 5e-06,
+      "loss": 1.2821123600006104,
+      "memory(GiB)": 39.33,
+      "step": 10,
+      "token_acc": 0.8313403718154694,
+      "train_speed(iter/s)": 0.014524
+    },
+    {
+      "epoch": 10.785276073619633,
+      "grad_norm": 2.8792276792731872,
+      "learning_rate": 4.999658262481173e-06,
+      "loss": 1.275630235671997,
+      "memory(GiB)": 39.33,
+      "step": 11,
+      "token_acc": 0.8285017000556812,
+      "train_speed(iter/s)": 0.014445
+    },
+    {
+      "epoch": 11.785276073619633,
+      "grad_norm": 3.0281873560029338,
+      "learning_rate": 4.998633143352315e-06,
+      "loss": 1.2036690711975098,
+      "memory(GiB)": 39.33,
+      "step": 12,
+      "token_acc": 0.8379109677897624,
+      "train_speed(iter/s)": 0.014493
+    },
+    {
+      "epoch": 12.785276073619633,
+      "grad_norm": 3.0371512203857205,
+      "learning_rate": 4.9969249228707625e-06,
+      "loss": 1.2084441184997559,
+      "memory(GiB)": 39.33,
+      "step": 13,
+      "token_acc": 0.8384220321813085,
+      "train_speed(iter/s)": 0.014427
+    },
+    {
+      "epoch": 13.785276073619633,
+      "grad_norm": 2.6387426090200363,
+      "learning_rate": 4.994534068046936e-06,
+      "loss": 1.1901323795318604,
+      "memory(GiB)": 39.33,
+      "step": 14,
+      "token_acc": 0.8441223334680967,
+      "train_speed(iter/s)": 0.014476
+    },
+    {
+      "epoch": 14.785276073619633,
+      "grad_norm": 2.3160115440855873,
+      "learning_rate": 4.991461232516675e-06,
+      "loss": 1.141261100769043,
+      "memory(GiB)": 39.33,
+      "step": 15,
+      "token_acc": 0.8443658849034292,
+      "train_speed(iter/s)": 0.014426
+    },
+    {
+      "epoch": 15.785276073619633,
+      "grad_norm": 2.083813179452864,
+      "learning_rate": 4.987707256362529e-06,
+      "loss": 1.084287166595459,
+      "memory(GiB)": 39.33,
+      "step": 16,
+      "token_acc": 0.8477599213633511,
+      "train_speed(iter/s)": 0.014468
+    },
+    {
+      "epoch": 16.78527607361963,
+      "grad_norm": 1.9692176113541133,
+      "learning_rate": 4.983273165884096e-06,
+      "loss": 1.0419270992279053,
+      "memory(GiB)": 39.33,
+      "step": 17,
+      "token_acc": 0.8630328525162231,
+      "train_speed(iter/s)": 0.014414
+    },
+    {
+      "epoch": 17.78527607361963,
+      "grad_norm": 1.7151316178388507,
+      "learning_rate": 4.978160173317439e-06,
+      "loss": 0.9549746513366699,
+      "memory(GiB)": 39.33,
+      "step": 18,
+      "token_acc": 0.8722866869211904,
+      "train_speed(iter/s)": 0.01445
+    },
+    {
+      "epoch": 18.78527607361963,
+      "grad_norm": 1.549137117164761,
+      "learning_rate": 4.972369676503672e-06,
+      "loss": 0.9502382278442383,
+      "memory(GiB)": 39.33,
+      "step": 19,
+      "token_acc": 0.8675967359831535,
+      "train_speed(iter/s)": 0.014405
+    },
+    {
+      "epoch": 19.78527607361963,
+      "grad_norm": 1.1953412837491808,
+      "learning_rate": 4.965903258506806e-06,
+      "loss": 0.893640398979187,
+      "memory(GiB)": 39.33,
+      "step": 20,
+      "token_acc": 0.870425555791075,
+      "train_speed(iter/s)": 0.014441
+    },
+    {
+      "epoch": 20.78527607361963,
+      "grad_norm": 1.2537339963447596,
+      "learning_rate": 4.9587626871809564e-06,
+      "loss": 0.860186755657196,
+      "memory(GiB)": 39.33,
+      "step": 21,
+      "token_acc": 0.8714236257078563,
+      "train_speed(iter/s)": 0.014406
+    },
+    {
+      "epoch": 21.78527607361963,
+      "grad_norm": 1.1827204340282138,
+      "learning_rate": 4.950949914687024e-06,
+      "loss": 0.8294661641120911,
+      "memory(GiB)": 39.34,
+      "step": 22,
+      "token_acc": 0.8780051945745555,
+      "train_speed(iter/s)": 0.014437
+    },
+    {
+      "epoch": 22.78527607361963,
+      "grad_norm": 1.074496322059685,
+      "learning_rate": 4.942467076958999e-06,
+      "loss": 0.826668381690979,
+      "memory(GiB)": 39.34,
+      "step": 23,
+      "token_acc": 0.8780265115649939,
+      "train_speed(iter/s)": 0.014396
+    },
+    {
+      "epoch": 23.78527607361963,
+      "grad_norm": 0.9237880545379076,
+      "learning_rate": 4.933316493120015e-06,
+      "loss": 0.8319023847579956,
+      "memory(GiB)": 39.34,
+      "step": 24,
+      "token_acc": 0.8776226135060379,
+      "train_speed(iter/s)": 0.014423
+    },
+    {
+      "epoch": 24.78527607361963,
+      "grad_norm": 0.8450828330230173,
+      "learning_rate": 4.923500664848327e-06,
+      "loss": 0.7946324348449707,
+      "memory(GiB)": 39.34,
+      "step": 25,
+      "token_acc": 0.8774449657163479,
+      "train_speed(iter/s)": 0.01434
+    },
+    {
+      "epoch": 25.78527607361963,
+      "grad_norm": 0.8084371406940016,
+      "learning_rate": 4.913022275693372e-06,
+      "loss": 0.7982379198074341,
+      "memory(GiB)": 39.34,
+      "step": 26,
+      "token_acc": 0.8835678461967121,
+      "train_speed(iter/s)": 0.014197
+    },
+    {
+      "epoch": 26.78527607361963,
+      "grad_norm": 0.8064722550105239,
+      "learning_rate": 4.901884190342121e-06,
+      "loss": 0.7379294633865356,
+      "memory(GiB)": 39.34,
+      "step": 27,
+      "token_acc": 0.8820249380108911,
+      "train_speed(iter/s)": 0.014015
+    },
+    {
+      "epoch": 27.78527607361963,
+      "grad_norm": 0.7505443142537965,
+      "learning_rate": 4.890089453835894e-06,
+      "loss": 0.8055274486541748,
+      "memory(GiB)": 39.34,
+      "step": 28,
+      "token_acc": 0.8885918287235961,
+      "train_speed(iter/s)": 0.013867
+    },
+    {
+      "epoch": 28.78527607361963,
+      "grad_norm": 0.6119739730959108,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.7476144433021545,
+      "memory(GiB)": 39.34,
+      "step": 29,
+      "token_acc": 0.8924232543535493,
+      "train_speed(iter/s)": 0.013849
+    },
+    {
+      "epoch": 29.78527607361963,
+      "grad_norm": 0.7681036255940338,
+      "learning_rate": 4.864543104251587e-06,
+      "loss": 0.7009764909744263,
+      "memory(GiB)": 39.34,
+      "step": 30,
+      "token_acc": 0.8919646242859415,
+      "train_speed(iter/s)": 0.013827
+    },
+    {
+      "epoch": 30.78527607361963,
+      "grad_norm": 0.7104586578934021,
+      "learning_rate": 4.850798475290403e-06,
+      "loss": 0.6857994198799133,
+      "memory(GiB)": 39.34,
+      "step": 31,
+      "token_acc": 0.8883618146266964,
+      "train_speed(iter/s)": 0.013775
+    },
+    {
+      "epoch": 31.78527607361963,
+      "grad_norm": 0.6784594125219264,
+      "learning_rate": 4.836411161498653e-06,
+      "loss": 0.6878491044044495,
+      "memory(GiB)": 39.34,
+      "step": 32,
+      "token_acc": 0.8874739614039225,
+      "train_speed(iter/s)": 0.013774
+    },
+    {
+      "epoch": 32.785276073619634,
+      "grad_norm": 0.6524486859004722,
+      "learning_rate": 4.821385096224268e-06,
+      "loss": 0.6495063900947571,
+      "memory(GiB)": 39.34,
+      "step": 33,
+      "token_acc": 0.8972710558886793,
+      "train_speed(iter/s)": 0.013745
+    },
+    {
+      "epoch": 33.785276073619634,
+      "grad_norm": 0.6437780661180932,
+      "learning_rate": 4.8057243874434625e-06,
+      "loss": 0.6780753135681152,
+      "memory(GiB)": 39.34,
+      "step": 34,
+      "token_acc": 0.8965800092610968,
+      "train_speed(iter/s)": 0.013776
+    },
+    {
+      "epoch": 34.785276073619634,
+      "grad_norm": 0.6012280443982766,
+      "learning_rate": 4.789433316637644e-06,
+      "loss": 0.6937360763549805,
+      "memory(GiB)": 39.34,
+      "step": 35,
+      "token_acc": 0.8985454504099806,
+      "train_speed(iter/s)": 0.01377
+    },
+    {
+      "epoch": 35.785276073619634,
+      "grad_norm": 0.602538629390956,
+      "learning_rate": 4.772516337622907e-06,
+      "loss": 0.6754523515701294,
+      "memory(GiB)": 39.34,
+      "step": 36,
+      "token_acc": 0.8950226959644091,
+      "train_speed(iter/s)": 0.013804
+    },
+    {
+      "epoch": 36.785276073619634,
+      "grad_norm": 0.5846158635967554,
+      "learning_rate": 4.754978075332398e-06,
+      "loss": 0.6398173570632935,
+      "memory(GiB)": 39.34,
+      "step": 37,
+      "token_acc": 0.898102863215351,
+      "train_speed(iter/s)": 0.013765
+    },
+    {
+      "epoch": 37.785276073619634,
+      "grad_norm": 0.44752405527595507,
+      "learning_rate": 4.736823324551909e-06,
+      "loss": 0.6178634166717529,
+      "memory(GiB)": 39.34,
+      "step": 38,
+      "token_acc": 0.8983179005164953,
+      "train_speed(iter/s)": 0.013757
+    },
+    {
+      "epoch": 38.785276073619634,
+      "grad_norm": 0.5759115585585194,
+      "learning_rate": 4.71805704860903e-06,
+      "loss": 0.6596415638923645,
+      "memory(GiB)": 39.34,
+      "step": 39,
+      "token_acc": 0.9043605764785142,
+      "train_speed(iter/s)": 0.013748
+    },
+    {
+      "epoch": 39.785276073619634,
+      "grad_norm": 0.5251913319753604,
+      "learning_rate": 4.698684378016223e-06,
+      "loss": 0.6197866797447205,
+      "memory(GiB)": 39.34,
+      "step": 40,
+      "token_acc": 0.9019051278555227,
+      "train_speed(iter/s)": 0.013779
+    },
+    {
+      "epoch": 40.785276073619634,
+      "grad_norm": 0.5556487937376285,
+      "learning_rate": 4.678710609068193e-06,
+      "loss": 0.6387439370155334,
+      "memory(GiB)": 39.34,
+      "step": 41,
+      "token_acc": 0.8996385106639354,
+      "train_speed(iter/s)": 0.013774
+    },
+    {
+      "epoch": 41.785276073619634,
+      "grad_norm": 0.5595033551514544,
+      "learning_rate": 4.658141202393935e-06,
+      "loss": 0.5881360769271851,
+      "memory(GiB)": 39.34,
+      "step": 42,
+      "token_acc": 0.902147025625015,
+      "train_speed(iter/s)": 0.013803
+    },
+    {
+      "epoch": 42.785276073619634,
+      "grad_norm": 0.592912316638698,
+      "learning_rate": 4.636981781463848e-06,
+      "loss": 0.6058595776557922,
+      "memory(GiB)": 39.34,
+      "step": 43,
+      "token_acc": 0.8997946249700757,
+      "train_speed(iter/s)": 0.013801
+    },
+    {
+      "epoch": 43.785276073619634,
+      "grad_norm": 0.5474462324998715,
+      "learning_rate": 4.615238131052339e-06,
+      "loss": 0.5743303894996643,
+      "memory(GiB)": 39.34,
+      "step": 44,
+      "token_acc": 0.9094863701578192,
+      "train_speed(iter/s)": 0.013828
+    },
+    {
+      "epoch": 44.785276073619634,
+      "grad_norm": 0.6003410732076991,
+      "learning_rate": 4.592916195656322e-06,
+      "loss": 0.612324059009552,
+      "memory(GiB)": 39.34,
+      "step": 45,
+      "token_acc": 0.9116981475374416,
+      "train_speed(iter/s)": 0.013823
+    },
+    {
+      "epoch": 45.785276073619634,
+      "grad_norm": 0.5803467871688905,
+      "learning_rate": 4.570022077870051e-06,
+      "loss": 0.540604829788208,
+      "memory(GiB)": 39.34,
+      "step": 46,
+      "token_acc": 0.9066389293058044,
+      "train_speed(iter/s)": 0.013844
+    },
+    {
+      "epoch": 46.785276073619634,
+      "grad_norm": 0.31746472746367554,
+      "learning_rate": 4.546562036716732e-06,
+      "loss": 0.5575750470161438,
+      "memory(GiB)": 39.34,
+      "step": 47,
+      "token_acc": 0.911935911474843,
+      "train_speed(iter/s)": 0.013831
+    },
+    {
+      "epoch": 47.785276073619634,
+      "grad_norm": 0.547728341912002,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.5444112420082092,
+      "memory(GiB)": 39.34,
+      "step": 48,
+      "token_acc": 0.9140458085414321,
+      "train_speed(iter/s)": 0.013854
+    },
+    {
+      "epoch": 48.785276073619634,
+      "grad_norm": 0.5196821422871499,
+      "learning_rate": 4.497969992237312e-06,
+      "loss": 0.5895761847496033,
+      "memory(GiB)": 39.34,
+      "step": 49,
+      "token_acc": 0.9174603967193878,
+      "train_speed(iter/s)": 0.01385
+    },
+    {
+      "epoch": 49.785276073619634,
+      "grad_norm": 0.5165933268106758,
+      "learning_rate": 4.472851273490985e-06,
+      "loss": 0.5617235898971558,
+      "memory(GiB)": 39.34,
+      "step": 50,
+      "token_acc": 0.9105760761054671,
+      "train_speed(iter/s)": 0.013873
+    },
+    {
+      "epoch": 50.785276073619634,
+      "grad_norm": 0.5491429792142556,
+      "learning_rate": 4.4471931969052816e-06,
+      "loss": 0.5617798566818237,
+      "memory(GiB)": 39.34,
+      "step": 51,
+      "token_acc": 0.914954423407124,
+      "train_speed(iter/s)": 0.013865
+    },
+    {
+      "epoch": 51.785276073619634,
+      "grad_norm": 0.47279597803824047,
+      "learning_rate": 4.421002777142148e-06,
+      "loss": 0.5274189710617065,
+      "memory(GiB)": 39.34,
+      "step": 52,
+      "token_acc": 0.9109212369606242,
+      "train_speed(iter/s)": 0.013856
+    },
+    {
+      "epoch": 52.785276073619634,
+      "grad_norm": 0.5331682466669002,
+      "learning_rate": 4.394287174400838e-06,
+      "loss": 0.5500538945198059,
+      "memory(GiB)": 39.34,
+      "step": 53,
+      "token_acc": 0.9179731638418079,
+      "train_speed(iter/s)": 0.013816
+    },
+    {
+      "epoch": 53.785276073619634,
+      "grad_norm": 0.5015412639019045,
+      "learning_rate": 4.3670536924603855e-06,
+      "loss": 0.5379254817962646,
+      "memory(GiB)": 39.34,
+      "step": 54,
+      "token_acc": 0.91340303696508,
+      "train_speed(iter/s)": 0.013806
+    },
+    {
+      "epoch": 54.785276073619634,
+      "grad_norm": 0.5012274856872988,
+      "learning_rate": 4.33930977668283e-06,
+      "loss": 0.5354421138763428,
+      "memory(GiB)": 39.34,
+      "step": 55,
+      "token_acc": 0.9172959682882159,
+      "train_speed(iter/s)": 0.013802
+    },
+    {
+      "epoch": 55.785276073619634,
+      "grad_norm": 0.2803188316237382,
+      "learning_rate": 4.311063011977723e-06,
+      "loss": 0.5273925065994263,
+      "memory(GiB)": 39.34,
+      "step": 56,
+      "token_acc": 0.9197245144878079,
+      "train_speed(iter/s)": 0.013823
+    },
+    {
+      "epoch": 56.785276073619634,
+      "grad_norm": 0.5225252350052656,
+      "learning_rate": 4.282321120728493e-06,
+      "loss": 0.49844077229499817,
+      "memory(GiB)": 39.34,
+      "step": 57,
+      "token_acc": 0.9147932040501116,
+      "train_speed(iter/s)": 0.01382
+    },
+    {
+      "epoch": 57.785276073619634,
+      "grad_norm": 0.5016830591757713,
+      "learning_rate": 4.253091960681222e-06,
+      "loss": 0.514026939868927,
+      "memory(GiB)": 39.34,
+      "step": 58,
+      "token_acc": 0.914426587542329,
+      "train_speed(iter/s)": 0.01384
+    },
+    {
+      "epoch": 58.785276073619634,
+      "grad_norm": 0.5162114438500172,
+      "learning_rate": 4.2233835227964145e-06,
+      "loss": 0.5164660215377808,
+      "memory(GiB)": 39.34,
+      "step": 59,
+      "token_acc": 0.9154462464242161,
+      "train_speed(iter/s)": 0.013838
+    },
+    {
+      "epoch": 59.785276073619634,
+      "grad_norm": 0.5003508758002871,
+      "learning_rate": 4.1932039290643534e-06,
+      "loss": 0.5167316198348999,
+      "memory(GiB)": 39.34,
+      "step": 60,
+      "token_acc": 0.9177114825166848,
+      "train_speed(iter/s)": 0.013857
+    },
+    {
+      "epoch": 60.785276073619634,
+      "grad_norm": 0.5370771821941825,
+      "learning_rate": 4.162561430284621e-06,
+      "loss": 0.4968717098236084,
+      "memory(GiB)": 39.34,
+      "step": 61,
+      "token_acc": 0.9180080667900795,
+      "train_speed(iter/s)": 0.013854
+    },
+    {
+      "epoch": 61.785276073619634,
+      "grad_norm": 0.4703998846973088,
+      "learning_rate": 4.1314644038104215e-06,
+      "loss": 0.48470860719680786,
+      "memory(GiB)": 39.34,
+      "step": 62,
+      "token_acc": 0.9172036041531638,
+      "train_speed(iter/s)": 0.01387
+    },
+    {
+      "epoch": 62.785276073619634,
+      "grad_norm": 0.5732521467141994,
+      "learning_rate": 4.099921351258292e-06,
+      "loss": 0.4761297106742859,
+      "memory(GiB)": 39.34,
+      "step": 63,
+      "token_acc": 0.9202728996822739,
+      "train_speed(iter/s)": 0.013866
+    },
+    {
+      "epoch": 63.785276073619634,
+      "grad_norm": 0.566487845334896,
+      "learning_rate": 4.067940896183843e-06,
+      "loss": 0.4775853157043457,
+      "memory(GiB)": 39.34,
+      "step": 64,
+      "token_acc": 0.9162934345333743,
+      "train_speed(iter/s)": 0.013883
+    },
+    {
+      "epoch": 64.78527607361963,
+      "grad_norm": 0.31449277119414887,
+      "learning_rate": 4.0355317817241705e-06,
+      "loss": 0.4875542223453522,
+      "memory(GiB)": 39.34,
+      "step": 65,
+      "token_acc": 0.9208928240311515,
+      "train_speed(iter/s)": 0.013874
+    },
+    {
+      "epoch": 65.78527607361963,
+      "grad_norm": 0.7863716510843305,
+      "learning_rate": 4.002702868207563e-06,
+      "loss": 0.4927229881286621,
+      "memory(GiB)": 39.34,
+      "step": 66,
+      "token_acc": 0.9251339373531896,
+      "train_speed(iter/s)": 0.01389
+    },
+    {
+      "epoch": 66.78527607361963,
+      "grad_norm": 0.6581549893568186,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.4890143871307373,
+      "memory(GiB)": 39.34,
+      "step": 67,
+      "token_acc": 0.9183355219960604,
+      "train_speed(iter/s)": 0.013878
+    },
+    {
+      "epoch": 67.78527607361963,
+      "grad_norm": 0.5900053583989073,
+      "learning_rate": 3.935821656707359e-06,
+      "loss": 0.48031631112098694,
+      "memory(GiB)": 39.34,
+      "step": 68,
+      "token_acc": 0.9213672888828442,
+      "train_speed(iter/s)": 0.01389
+    },
+    {
+      "epoch": 68.78527607361963,
+      "grad_norm": 0.6132529596085236,
+      "learning_rate": 3.901787643379183e-06,
+      "loss": 0.45974451303482056,
+      "memory(GiB)": 39.34,
+      "step": 69,
+      "token_acc": 0.9189587008089533,
+      "train_speed(iter/s)": 0.013882
+    },
+    {
+      "epoch": 69.78527607361963,
+      "grad_norm": 0.7256621524580472,
+      "learning_rate": 3.8673703953060685e-06,
+      "loss": 0.45002666115760803,
+      "memory(GiB)": 39.34,
+      "step": 70,
+      "token_acc": 0.9235120083536373,
+      "train_speed(iter/s)": 0.013876
+    },
+    {
+      "epoch": 70.78527607361963,
+      "grad_norm": 0.6572360898351522,
+      "learning_rate": 3.832579321819985e-06,
+      "loss": 0.44984108209609985,
+      "memory(GiB)": 39.34,
+      "step": 71,
+      "token_acc": 0.9278641983998498,
+      "train_speed(iter/s)": 0.013872
+    },
+    {
+      "epoch": 71.78527607361963,
+      "grad_norm": 0.6788420593989611,
+      "learning_rate": 3.797423934453038e-06,
+      "loss": 0.46496278047561646,
+      "memory(GiB)": 39.34,
+      "step": 72,
+      "token_acc": 0.9247173628466024,
+      "train_speed(iter/s)": 0.013887
+    },
+    {
+      "epoch": 72.78527607361963,
+      "grad_norm": 0.6073327829268869,
+      "learning_rate": 3.76191384433711e-06,
+      "loss": 0.43901190161705017,
+      "memory(GiB)": 39.34,
+      "step": 73,
+      "token_acc": 0.9269318854378426,
+      "train_speed(iter/s)": 0.013872
+    },
+    {
+      "epoch": 73.78527607361963,
+      "grad_norm": 0.4952804216866532,
+      "learning_rate": 3.726058759576271e-06,
+      "loss": 0.4391399025917053,
+      "memory(GiB)": 39.34,
+      "step": 74,
+      "token_acc": 0.9251885591145068,
+      "train_speed(iter/s)": 0.01388
+    },
+    {
+      "epoch": 74.78527607361963,
+      "grad_norm": 0.7195321191248989,
+      "learning_rate": 3.6898684825926845e-06,
+      "loss": 0.440918892621994,
+      "memory(GiB)": 39.34,
+      "step": 75,
+      "token_acc": 0.9259756638718266,
+      "train_speed(iter/s)": 0.013868
+    },
+    {
+      "epoch": 75.78527607361963,
+      "grad_norm": 0.5356189516143581,
+      "learning_rate": 3.65335290744672e-06,
+      "loss": 0.44449836015701294,
+      "memory(GiB)": 39.34,
+      "step": 76,
+      "token_acc": 0.9235405737247461,
+      "train_speed(iter/s)": 0.013861
+    },
+    {
+      "epoch": 76.78527607361963,
+      "grad_norm": 0.7790146643095753,
+      "learning_rate": 3.616522017132017e-06,
+      "loss": 0.4214305877685547,
+      "memory(GiB)": 39.34,
+      "step": 77,
+      "token_acc": 0.935737818195279,
+      "train_speed(iter/s)": 0.013851
+    },
+    {
+      "epoch": 77.78527607361963,
+      "grad_norm": 0.640555014306015,
+      "learning_rate": 3.579385880846232e-06,
+      "loss": 0.41491076350212097,
+      "memory(GiB)": 39.34,
+      "step": 78,
+      "token_acc": 0.9254948760620128,
+      "train_speed(iter/s)": 0.013865
+    },
+    {
+      "epoch": 78.78527607361963,
+      "grad_norm": 0.7225957987793631,
+      "learning_rate": 3.5419546512382264e-06,
+      "loss": 0.4449855089187622,
+      "memory(GiB)": 39.34,
+      "step": 79,
+      "token_acc": 0.92669304165697,
+      "train_speed(iter/s)": 0.013861
+    },
+    {
+      "epoch": 79.78527607361963,
+      "grad_norm": 0.71186832956713,
+      "learning_rate": 3.5042385616324243e-06,
+      "loss": 0.4115943908691406,
+      "memory(GiB)": 39.34,
+      "step": 80,
+      "token_acc": 0.9300436681222708,
+      "train_speed(iter/s)": 0.013871
+    },
+    {
+      "epoch": 80.78527607361963,
+      "grad_norm": 0.5344801517675843,
+      "learning_rate": 3.466247923231131e-06,
+      "loss": 0.4183962047100067,
+      "memory(GiB)": 39.34,
+      "step": 81,
+      "token_acc": 0.9238792981795946,
+      "train_speed(iter/s)": 0.013858
+    },
+    {
+      "epoch": 81.78527607361963,
+      "grad_norm": 0.7110303531981544,
+      "learning_rate": 3.427993122295552e-06,
+      "loss": 0.43044573068618774,
+      "memory(GiB)": 39.34,
+      "step": 82,
+      "token_acc": 0.9315566699353302,
+      "train_speed(iter/s)": 0.013848
+    },
+    {
+      "epoch": 82.78527607361963,
+      "grad_norm": 0.6054164665729541,
+      "learning_rate": 3.3894846173062917e-06,
+      "loss": 0.391621857881546,
+      "memory(GiB)": 39.34,
+      "step": 83,
+      "token_acc": 0.9380456974067156,
+      "train_speed(iter/s)": 0.013842
+    },
+    {
+      "epoch": 83.78527607361963,
+      "grad_norm": 0.659034943496206,
+      "learning_rate": 3.350732936104108e-06,
+      "loss": 0.40062740445137024,
+      "memory(GiB)": 39.34,
+      "step": 84,
+      "token_acc": 0.9351094518920754,
+      "train_speed(iter/s)": 0.013855
+    },
+    {
+      "epoch": 84.78527607361963,
+      "grad_norm": 0.6757156967804352,
+      "learning_rate": 3.3117486730117092e-06,
+      "loss": 0.42082643508911133,
+      "memory(GiB)": 39.34,
+      "step": 85,
+      "token_acc": 0.9334060495173756,
+      "train_speed(iter/s)": 0.01385
+    },
+    {
+      "epoch": 85.78527607361963,
+      "grad_norm": 0.6462108938520096,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.4044734239578247,
+      "memory(GiB)": 39.34,
+      "step": 86,
+      "token_acc": 0.937454412837345,
+      "train_speed(iter/s)": 0.013858
+    },
+    {
+      "epoch": 86.78527607361963,
+      "grad_norm": 0.6658216806148752,
+      "learning_rate": 3.2331250934611623e-06,
+      "loss": 0.4085301458835602,
+      "memory(GiB)": 39.34,
+      "step": 87,
+      "token_acc": 0.9344952439398588,
+      "train_speed(iter/s)": 0.013849
+    },
+    {
+      "epoch": 87.78527607361963,
+      "grad_norm": 0.5859038575973,
+      "learning_rate": 3.193507271904612e-06,
+      "loss": 0.4107922613620758,
+      "memory(GiB)": 39.34,
+      "step": 88,
+      "token_acc": 0.9370524843896911,
+      "train_speed(iter/s)": 0.013851
+    },
+    {
+      "epoch": 88.78527607361963,
+      "grad_norm": 0.6618470555633296,
+      "learning_rate": 3.15369985238455e-06,
+      "loss": 0.374958336353302,
+      "memory(GiB)": 39.34,
+      "step": 89,
+      "token_acc": 0.9345464787352592,
+      "train_speed(iter/s)": 0.013831
+    },
+    {
+      "epoch": 89.78527607361963,
+      "grad_norm": 0.8076141889252606,
+      "learning_rate": 3.1137137178519983e-06,
+      "loss": 0.40027111768722534,
+      "memory(GiB)": 39.34,
+      "step": 90,
+      "token_acc": 0.9367903505358848,
+      "train_speed(iter/s)": 0.013844
+    },
+    {
+      "epoch": 90.78527607361963,
+      "grad_norm": 0.591801688114359,
+      "learning_rate": 3.073559800116879e-06,
+      "loss": 0.3753508925437927,
+      "memory(GiB)": 39.34,
+      "step": 91,
+      "token_acc": 0.9328512619350389,
+      "train_speed(iter/s)": 0.013839
+    },
+    {
+      "epoch": 91.78527607361963,
+      "grad_norm": 0.7666418774168722,
+      "learning_rate": 3.0332490768593676e-06,
+      "loss": 0.39489710330963135,
+      "memory(GiB)": 39.34,
+      "step": 92,
+      "token_acc": 0.9387719407833094,
+      "train_speed(iter/s)": 0.013851
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 200,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 63696844357632.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c2c5571878a4a4b8d670308a0a830227c68334200992d3d9b67592c07918e4
+size 8312