Upload Eva-4B-Label-Only-Consensus fine-tuned model
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- args.json +356 -0
- chat_template.jinja +61 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +406 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +3042 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260125-022436",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 8,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 2,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 2e-05,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 2.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.03,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 10,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 500.0,
|
| 39 |
+
"save_total_limit": 3,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"bf16": true,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 0,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": null,
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 500.0,
|
| 64 |
+
"dataloader_num_workers": 8,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260125-022436",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": true,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": null,
|
| 84 |
+
"label_smoothing_factor": 0.0,
|
| 85 |
+
"optim": "adamw_torch_fused",
|
| 86 |
+
"optim_args": null,
|
| 87 |
+
"adafactor": false,
|
| 88 |
+
"group_by_length": false,
|
| 89 |
+
"length_column_name": "length",
|
| 90 |
+
"report_to": [
|
| 91 |
+
"tensorboard"
|
| 92 |
+
],
|
| 93 |
+
"project": "huggingface",
|
| 94 |
+
"trackio_space_id": "trackio",
|
| 95 |
+
"ddp_find_unused_parameters": null,
|
| 96 |
+
"ddp_bucket_cap_mb": null,
|
| 97 |
+
"ddp_broadcast_buffers": null,
|
| 98 |
+
"dataloader_pin_memory": true,
|
| 99 |
+
"dataloader_persistent_workers": false,
|
| 100 |
+
"skip_memory_metrics": true,
|
| 101 |
+
"use_legacy_prediction_loop": false,
|
| 102 |
+
"push_to_hub": false,
|
| 103 |
+
"resume_from_checkpoint": null,
|
| 104 |
+
"hub_model_id": null,
|
| 105 |
+
"hub_strategy": "every_save",
|
| 106 |
+
"hub_token": null,
|
| 107 |
+
"hub_private_repo": null,
|
| 108 |
+
"hub_always_push": false,
|
| 109 |
+
"hub_revision": null,
|
| 110 |
+
"gradient_checkpointing": true,
|
| 111 |
+
"gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
|
| 112 |
+
"include_inputs_for_metrics": false,
|
| 113 |
+
"include_for_metrics": [],
|
| 114 |
+
"eval_do_concat_batches": true,
|
| 115 |
+
"fp16_backend": "auto",
|
| 116 |
+
"push_to_hub_model_id": null,
|
| 117 |
+
"push_to_hub_organization": null,
|
| 118 |
+
"push_to_hub_token": null,
|
| 119 |
+
"mp_parameters": "",
|
| 120 |
+
"auto_find_batch_size": false,
|
| 121 |
+
"full_determinism": false,
|
| 122 |
+
"torchdynamo": null,
|
| 123 |
+
"ray_scope": "last",
|
| 124 |
+
"ddp_timeout": 18000000,
|
| 125 |
+
"torch_compile": false,
|
| 126 |
+
"torch_compile_backend": null,
|
| 127 |
+
"torch_compile_mode": null,
|
| 128 |
+
"include_tokens_per_second": false,
|
| 129 |
+
"include_num_input_tokens_seen": false,
|
| 130 |
+
"neftune_noise_alpha": null,
|
| 131 |
+
"optim_target_modules": null,
|
| 132 |
+
"batch_eval_metrics": false,
|
| 133 |
+
"eval_on_start": false,
|
| 134 |
+
"use_liger_kernel": false,
|
| 135 |
+
"liger_kernel_config": null,
|
| 136 |
+
"eval_use_gather_object": false,
|
| 137 |
+
"average_tokens_across_devices": true,
|
| 138 |
+
"sortish_sampler": false,
|
| 139 |
+
"predict_with_generate": false,
|
| 140 |
+
"generation_max_length": null,
|
| 141 |
+
"generation_num_beams": null,
|
| 142 |
+
"generation_config": null,
|
| 143 |
+
"tuner_backend": "peft",
|
| 144 |
+
"vit_gradient_checkpointing": null,
|
| 145 |
+
"router_aux_loss_coef": 0.0,
|
| 146 |
+
"enable_dft_loss": false,
|
| 147 |
+
"enable_channel_loss": false,
|
| 148 |
+
"check_model": true,
|
| 149 |
+
"acc_strategy": "token",
|
| 150 |
+
"train_dataloader_shuffle": true,
|
| 151 |
+
"max_epochs": null,
|
| 152 |
+
"aligner_lr": null,
|
| 153 |
+
"vit_lr": null,
|
| 154 |
+
"use_logits_to_keep": null,
|
| 155 |
+
"ds3_gather_for_generation": true,
|
| 156 |
+
"resume_only_model": false,
|
| 157 |
+
"optimizer": null,
|
| 158 |
+
"loss_type": null,
|
| 159 |
+
"eval_metric": null,
|
| 160 |
+
"callbacks": [],
|
| 161 |
+
"early_stop_interval": null,
|
| 162 |
+
"eval_use_evalscope": false,
|
| 163 |
+
"eval_dataset": [],
|
| 164 |
+
"eval_dataset_args": null,
|
| 165 |
+
"eval_limit": null,
|
| 166 |
+
"eval_generation_config": null,
|
| 167 |
+
"extra_eval_args": null,
|
| 168 |
+
"tuner_type": "full",
|
| 169 |
+
"use_galore": false,
|
| 170 |
+
"galore_target_modules": null,
|
| 171 |
+
"galore_rank": 128,
|
| 172 |
+
"galore_update_proj_gap": 50,
|
| 173 |
+
"galore_scale": 1.0,
|
| 174 |
+
"galore_proj_type": "std",
|
| 175 |
+
"galore_optim_per_parameter": false,
|
| 176 |
+
"galore_with_embedding": false,
|
| 177 |
+
"galore_quantization": false,
|
| 178 |
+
"galore_proj_quant": false,
|
| 179 |
+
"galore_proj_bits": 4,
|
| 180 |
+
"galore_proj_group_size": 256,
|
| 181 |
+
"galore_cos_threshold": 0.4,
|
| 182 |
+
"galore_gamma_proj": 2,
|
| 183 |
+
"galore_queue_size": 5,
|
| 184 |
+
"lisa_activated_layers": 0,
|
| 185 |
+
"lisa_step_interval": 20,
|
| 186 |
+
"use_flash_ckpt": false,
|
| 187 |
+
"use_ray": false,
|
| 188 |
+
"ray_exp_name": null,
|
| 189 |
+
"device_groups": null,
|
| 190 |
+
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
| 191 |
+
"model_type": "qwen3",
|
| 192 |
+
"model_revision": null,
|
| 193 |
+
"task_type": "causal_lm",
|
| 194 |
+
"torch_dtype": "bfloat16",
|
| 195 |
+
"attn_impl": null,
|
| 196 |
+
"experts_impl": null,
|
| 197 |
+
"new_special_tokens": [],
|
| 198 |
+
"num_labels": null,
|
| 199 |
+
"problem_type": null,
|
| 200 |
+
"rope_scaling": null,
|
| 201 |
+
"device_map": null,
|
| 202 |
+
"max_memory": {},
|
| 203 |
+
"max_model_len": null,
|
| 204 |
+
"local_repo_path": null,
|
| 205 |
+
"init_strategy": null,
|
| 206 |
+
"template": "qwen3_nothinking",
|
| 207 |
+
"system": null,
|
| 208 |
+
"max_length": 2048,
|
| 209 |
+
"truncation_strategy": "delete",
|
| 210 |
+
"max_pixels": null,
|
| 211 |
+
"agent_template": null,
|
| 212 |
+
"norm_bbox": null,
|
| 213 |
+
"use_chat_template": true,
|
| 214 |
+
"padding_side": "right",
|
| 215 |
+
"padding_free": false,
|
| 216 |
+
"loss_scale": "default",
|
| 217 |
+
"sequence_parallel_size": 1,
|
| 218 |
+
"template_backend": "swift",
|
| 219 |
+
"response_prefix": null,
|
| 220 |
+
"enable_thinking": null,
|
| 221 |
+
"add_non_thinking_prefix": true,
|
| 222 |
+
"dataset": [
|
| 223 |
+
"/home/ubuntu/ms-swift/data/balanced_60k_msswift_label_only.jsonl"
|
| 224 |
+
],
|
| 225 |
+
"val_dataset": [],
|
| 226 |
+
"cached_dataset": [],
|
| 227 |
+
"cached_val_dataset": [],
|
| 228 |
+
"split_dataset_ratio": 0.0,
|
| 229 |
+
"dataset_num_proc": 1,
|
| 230 |
+
"load_from_cache_file": false,
|
| 231 |
+
"dataset_shuffle": true,
|
| 232 |
+
"val_dataset_shuffle": false,
|
| 233 |
+
"streaming": false,
|
| 234 |
+
"interleave_prob": null,
|
| 235 |
+
"stopping_strategy": "first_exhausted",
|
| 236 |
+
"shuffle_buffer_size": 1000,
|
| 237 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 238 |
+
"columns": {},
|
| 239 |
+
"strict": false,
|
| 240 |
+
"model_name": null,
|
| 241 |
+
"model_author": null,
|
| 242 |
+
"custom_dataset_info": [],
|
| 243 |
+
"quant_method": null,
|
| 244 |
+
"quant_bits": null,
|
| 245 |
+
"hqq_axis": null,
|
| 246 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 247 |
+
"bnb_4bit_quant_type": "nf4",
|
| 248 |
+
"bnb_4bit_use_double_quant": true,
|
| 249 |
+
"bnb_4bit_quant_storage": null,
|
| 250 |
+
"max_new_tokens": 64,
|
| 251 |
+
"temperature": 0.0,
|
| 252 |
+
"top_k": null,
|
| 253 |
+
"top_p": null,
|
| 254 |
+
"repetition_penalty": null,
|
| 255 |
+
"num_beams": 1,
|
| 256 |
+
"stream": false,
|
| 257 |
+
"stop_words": [],
|
| 258 |
+
"logprobs": false,
|
| 259 |
+
"top_logprobs": null,
|
| 260 |
+
"structured_outputs_regex": null,
|
| 261 |
+
"train_type": "full",
|
| 262 |
+
"adapters": [],
|
| 263 |
+
"external_plugins": [],
|
| 264 |
+
"custom_register_path": [],
|
| 265 |
+
"model_kwargs": {},
|
| 266 |
+
"load_args": false,
|
| 267 |
+
"load_data_args": false,
|
| 268 |
+
"packing": false,
|
| 269 |
+
"packing_length": null,
|
| 270 |
+
"packing_num_proc": 1,
|
| 271 |
+
"lazy_tokenize": false,
|
| 272 |
+
"use_hf": true,
|
| 273 |
+
"ignore_args_error": false,
|
| 274 |
+
"use_swift_lora": false,
|
| 275 |
+
"freeze_parameters": [],
|
| 276 |
+
"freeze_parameters_regex": null,
|
| 277 |
+
"freeze_parameters_ratio": 0.0,
|
| 278 |
+
"trainable_parameters": [],
|
| 279 |
+
"trainable_parameters_regex": null,
|
| 280 |
+
"freeze_llm": false,
|
| 281 |
+
"freeze_vit": true,
|
| 282 |
+
"freeze_aligner": true,
|
| 283 |
+
"target_modules": [
|
| 284 |
+
"all-linear"
|
| 285 |
+
],
|
| 286 |
+
"target_regex": null,
|
| 287 |
+
"target_parameters": null,
|
| 288 |
+
"modules_to_save": [],
|
| 289 |
+
"lora_rank": 8,
|
| 290 |
+
"lora_alpha": 32,
|
| 291 |
+
"lora_dropout": 0.05,
|
| 292 |
+
"lora_bias": "none",
|
| 293 |
+
"lora_dtype": null,
|
| 294 |
+
"lorap_lr_ratio": null,
|
| 295 |
+
"use_rslora": false,
|
| 296 |
+
"use_dora": false,
|
| 297 |
+
"lora_ga_batch_size": 2,
|
| 298 |
+
"lora_ga_iters": 2,
|
| 299 |
+
"lora_ga_max_length": 1024,
|
| 300 |
+
"lora_ga_direction": "ArB2r",
|
| 301 |
+
"lora_ga_scale": "stable",
|
| 302 |
+
"lora_ga_stable_gamma": 16,
|
| 303 |
+
"init_weights": true,
|
| 304 |
+
"fourier_n_frequency": 2000,
|
| 305 |
+
"fourier_scaling": 300.0,
|
| 306 |
+
"boft_block_size": 4,
|
| 307 |
+
"boft_block_num": 0,
|
| 308 |
+
"boft_n_butterfly_factor": 1,
|
| 309 |
+
"boft_dropout": 0.0,
|
| 310 |
+
"vera_rank": 256,
|
| 311 |
+
"vera_projection_prng_key": 0,
|
| 312 |
+
"vera_dropout": 0.0,
|
| 313 |
+
"vera_d_initial": 0.1,
|
| 314 |
+
"adapter_act": "gelu",
|
| 315 |
+
"adapter_length": 128,
|
| 316 |
+
"adalora_target_r": 8,
|
| 317 |
+
"adalora_init_r": 12,
|
| 318 |
+
"adalora_tinit": 0,
|
| 319 |
+
"adalora_tfinal": 0,
|
| 320 |
+
"adalora_deltaT": 1,
|
| 321 |
+
"adalora_beta1": 0.85,
|
| 322 |
+
"adalora_beta2": 0.85,
|
| 323 |
+
"adalora_orth_reg_weight": 0.5,
|
| 324 |
+
"llamapro_num_new_blocks": 4,
|
| 325 |
+
"llamapro_num_groups": null,
|
| 326 |
+
"reft_layer_key": null,
|
| 327 |
+
"reft_layers": null,
|
| 328 |
+
"reft_rank": 4,
|
| 329 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 330 |
+
"reft_args": null,
|
| 331 |
+
"swanlab_token": null,
|
| 332 |
+
"swanlab_project": "ms-swift",
|
| 333 |
+
"swanlab_workspace": null,
|
| 334 |
+
"swanlab_exp_name": null,
|
| 335 |
+
"swanlab_notification_method": null,
|
| 336 |
+
"swanlab_webhook_url": null,
|
| 337 |
+
"swanlab_secret": null,
|
| 338 |
+
"swanlab_mode": "cloud",
|
| 339 |
+
"add_version": true,
|
| 340 |
+
"create_checkpoint_symlink": false,
|
| 341 |
+
"zero_hpz_partition_size": null,
|
| 342 |
+
"deepspeed_autotp_size": null,
|
| 343 |
+
"swift_version": "4.0.0.dev0",
|
| 344 |
+
"ckpt_dir": null,
|
| 345 |
+
"rank": 0,
|
| 346 |
+
"global_world_size": 2,
|
| 347 |
+
"local_world_size": 2,
|
| 348 |
+
"model_suffix": "Qwen3-4B-Instruct-2507",
|
| 349 |
+
"model_info": "ModelInfo(model_type='qwen3', model_dir='/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
|
| 350 |
+
"model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3Guard-Gen-0.6B', hf_model_id='Qwen/Qwen3Guard-Gen-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-4B', hf_model_id='Qwen/Qwen3Guard-Gen-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-8B', hf_model_id='Qwen/Qwen3Guard-Gen-8B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_guard', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507', hf_model_id='Qwen/Qwen3-4B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template='qwen3_nothinking', model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
|
| 351 |
+
"model_dir": "/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
|
| 352 |
+
"_val_dataset_exists": [],
|
| 353 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 354 |
+
"evaluation_strategy": "steps",
|
| 355 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260125-022436', 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=8, 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=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260125-022436', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
|
| 356 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 262144,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 5000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": true,
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.6"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5be3fc26dd599a270cae7fb8aa1456e52aff0cf38de0d93b80234ef94e450d64
|
| 3 |
+
size 4967215360
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d5e5dbb911ac53da6ba4b1472ec4bc6a281bc27d2f892df6aa400a39469abb5
|
| 3 |
+
size 3077766632
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4022468096,
|
| 4 |
+
"total_size": 8044936192
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
+
}
|
| 406 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34c4bd422a1f57b75cfeec7c413a6893d99d0c4df1aa5e06c3aadbc2d541c74c
|
| 3 |
+
size 16090225449
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
|
| 3 |
+
size 14917
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
|
| 3 |
+
size 14917
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29c735055c8d99c9d27f8079227e4e096e9d24b754120d1c164915116f03f465
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3042 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500.0,
|
| 7 |
+
"global_step": 3750,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0005333333333333334,
|
| 14 |
+
"grad_norm": 60.0,
|
| 15 |
+
"learning_rate": 1.7699115044247788e-07,
|
| 16 |
+
"loss": 0.48311638832092285,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.9515738498789347
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.005333333333333333,
|
| 22 |
+
"grad_norm": 49.5,
|
| 23 |
+
"learning_rate": 1.769911504424779e-06,
|
| 24 |
+
"loss": 0.411925474802653,
|
| 25 |
+
"step": 10,
|
| 26 |
+
"token_acc": 0.9584996009577015
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.010666666666666666,
|
| 30 |
+
"grad_norm": 27.125,
|
| 31 |
+
"learning_rate": 3.539823008849558e-06,
|
| 32 |
+
"loss": 0.21190166473388672,
|
| 33 |
+
"step": 20,
|
| 34 |
+
"token_acc": 0.9635054021608643
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.016,
|
| 38 |
+
"grad_norm": 12.0,
|
| 39 |
+
"learning_rate": 5.309734513274337e-06,
|
| 40 |
+
"loss": 0.09306760430335999,
|
| 41 |
+
"step": 30,
|
| 42 |
+
"token_acc": 0.9690127312034591
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.021333333333333333,
|
| 46 |
+
"grad_norm": 3.703125,
|
| 47 |
+
"learning_rate": 7.079646017699116e-06,
|
| 48 |
+
"loss": 0.05371033549308777,
|
| 49 |
+
"step": 40,
|
| 50 |
+
"token_acc": 0.9756919374247894
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.02666666666666667,
|
| 54 |
+
"grad_norm": 4.875,
|
| 55 |
+
"learning_rate": 8.849557522123895e-06,
|
| 56 |
+
"loss": 0.04967069625854492,
|
| 57 |
+
"step": 50,
|
| 58 |
+
"token_acc": 0.9762884103556738
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032,
|
| 62 |
+
"grad_norm": 9.0,
|
| 63 |
+
"learning_rate": 1.0619469026548675e-05,
|
| 64 |
+
"loss": 0.043303996324539185,
|
| 65 |
+
"step": 60,
|
| 66 |
+
"token_acc": 0.9821471652593486
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.037333333333333336,
|
| 70 |
+
"grad_norm": 4.34375,
|
| 71 |
+
"learning_rate": 1.2389380530973452e-05,
|
| 72 |
+
"loss": 0.05136480927467346,
|
| 73 |
+
"step": 70,
|
| 74 |
+
"token_acc": 0.9824687800192123
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.042666666666666665,
|
| 78 |
+
"grad_norm": 2.515625,
|
| 79 |
+
"learning_rate": 1.4159292035398232e-05,
|
| 80 |
+
"loss": 0.040071535110473636,
|
| 81 |
+
"step": 80,
|
| 82 |
+
"token_acc": 0.9839212862970962
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.048,
|
| 86 |
+
"grad_norm": 6.9375,
|
| 87 |
+
"learning_rate": 1.592920353982301e-05,
|
| 88 |
+
"loss": 0.04163743853569031,
|
| 89 |
+
"step": 90,
|
| 90 |
+
"token_acc": 0.982388419782871
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05333333333333334,
|
| 94 |
+
"grad_norm": 3.40625,
|
| 95 |
+
"learning_rate": 1.769911504424779e-05,
|
| 96 |
+
"loss": 0.04012444615364075,
|
| 97 |
+
"step": 100,
|
| 98 |
+
"token_acc": 0.984115523465704
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.058666666666666666,
|
| 102 |
+
"grad_norm": 5.65625,
|
| 103 |
+
"learning_rate": 1.946902654867257e-05,
|
| 104 |
+
"loss": 0.03385461866855621,
|
| 105 |
+
"step": 110,
|
| 106 |
+
"token_acc": 0.986376673040153
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.064,
|
| 110 |
+
"grad_norm": 3.09375,
|
| 111 |
+
"learning_rate": 1.9999817199278942e-05,
|
| 112 |
+
"loss": 0.03304356336593628,
|
| 113 |
+
"step": 120,
|
| 114 |
+
"token_acc": 0.9869596715769138
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06933333333333333,
|
| 118 |
+
"grad_norm": 5.5625,
|
| 119 |
+
"learning_rate": 1.9998921864897123e-05,
|
| 120 |
+
"loss": 0.044121870398521425,
|
| 121 |
+
"step": 130,
|
| 122 |
+
"token_acc": 0.984873949579832
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07466666666666667,
|
| 126 |
+
"grad_norm": 4.53125,
|
| 127 |
+
"learning_rate": 1.9997280487931355e-05,
|
| 128 |
+
"loss": 0.03417717218399048,
|
| 129 |
+
"step": 140,
|
| 130 |
+
"token_acc": 0.9848884624610218
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.08,
|
| 134 |
+
"grad_norm": 3.0,
|
| 135 |
+
"learning_rate": 1.9994893190848556e-05,
|
| 136 |
+
"loss": 0.029238414764404298,
|
| 137 |
+
"step": 150,
|
| 138 |
+
"token_acc": 0.987954709708504
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.08533333333333333,
|
| 142 |
+
"grad_norm": 3.546875,
|
| 143 |
+
"learning_rate": 1.999176015177046e-05,
|
| 144 |
+
"loss": 0.022293809056282043,
|
| 145 |
+
"step": 160,
|
| 146 |
+
"token_acc": 0.9906385021603457
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.09066666666666667,
|
| 150 |
+
"grad_norm": 5.4375,
|
| 151 |
+
"learning_rate": 1.998788160446032e-05,
|
| 152 |
+
"loss": 0.02923697829246521,
|
| 153 |
+
"step": 170,
|
| 154 |
+
"token_acc": 0.9894862604540023
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.096,
|
| 158 |
+
"grad_norm": 2.34375,
|
| 159 |
+
"learning_rate": 1.9983257838305487e-05,
|
| 160 |
+
"loss": 0.03760753273963928,
|
| 161 |
+
"step": 180,
|
| 162 |
+
"token_acc": 0.9840425531914894
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.10133333333333333,
|
| 166 |
+
"grad_norm": 2.90625,
|
| 167 |
+
"learning_rate": 1.9977889198295794e-05,
|
| 168 |
+
"loss": 0.03487681448459625,
|
| 169 |
+
"step": 190,
|
| 170 |
+
"token_acc": 0.9852380952380952
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.10666666666666667,
|
| 174 |
+
"grad_norm": 3.28125,
|
| 175 |
+
"learning_rate": 1.9971776084997844e-05,
|
| 176 |
+
"loss": 0.023173870146274568,
|
| 177 |
+
"step": 200,
|
| 178 |
+
"token_acc": 0.9909069155300311
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.112,
|
| 182 |
+
"grad_norm": 1.953125,
|
| 183 |
+
"learning_rate": 1.9964918954525086e-05,
|
| 184 |
+
"loss": 0.030919164419174194,
|
| 185 |
+
"step": 210,
|
| 186 |
+
"token_acc": 0.9863178108497359
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.11733333333333333,
|
| 190 |
+
"grad_norm": 4.09375,
|
| 191 |
+
"learning_rate": 1.995731831850382e-05,
|
| 192 |
+
"loss": 0.03021637201309204,
|
| 193 |
+
"step": 220,
|
| 194 |
+
"token_acc": 0.9885112494016276
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.12266666666666666,
|
| 198 |
+
"grad_norm": 1.4375,
|
| 199 |
+
"learning_rate": 1.9948974744035002e-05,
|
| 200 |
+
"loss": 0.028303766250610353,
|
| 201 |
+
"step": 230,
|
| 202 |
+
"token_acc": 0.9881785283474065
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.128,
|
| 206 |
+
"grad_norm": 2.890625,
|
| 207 |
+
"learning_rate": 1.9939888853651933e-05,
|
| 208 |
+
"loss": 0.02691739797592163,
|
| 209 |
+
"step": 240,
|
| 210 |
+
"token_acc": 0.9875598086124402
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.13333333333333333,
|
| 214 |
+
"grad_norm": 2.609375,
|
| 215 |
+
"learning_rate": 1.9930061325273812e-05,
|
| 216 |
+
"loss": 0.021169370412826537,
|
| 217 |
+
"step": 250,
|
| 218 |
+
"token_acc": 0.9908521906596052
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.13866666666666666,
|
| 222 |
+
"grad_norm": 2.703125,
|
| 223 |
+
"learning_rate": 1.9919492892155164e-05,
|
| 224 |
+
"loss": 0.028641647100448607,
|
| 225 |
+
"step": 260,
|
| 226 |
+
"token_acc": 0.9887344199424737
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.144,
|
| 230 |
+
"grad_norm": 2.28125,
|
| 231 |
+
"learning_rate": 1.990818434283112e-05,
|
| 232 |
+
"loss": 0.018036679923534395,
|
| 233 |
+
"step": 270,
|
| 234 |
+
"token_acc": 0.9930271699927867
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.14933333333333335,
|
| 238 |
+
"grad_norm": 2.78125,
|
| 239 |
+
"learning_rate": 1.989613652105858e-05,
|
| 240 |
+
"loss": 0.042414110898971555,
|
| 241 |
+
"step": 280,
|
| 242 |
+
"token_acc": 0.9865707434052757
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.15466666666666667,
|
| 246 |
+
"grad_norm": 1.671875,
|
| 247 |
+
"learning_rate": 1.9883350325753276e-05,
|
| 248 |
+
"loss": 0.02896667718887329,
|
| 249 |
+
"step": 290,
|
| 250 |
+
"token_acc": 0.9865255052935515
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.16,
|
| 254 |
+
"grad_norm": 4.46875,
|
| 255 |
+
"learning_rate": 1.9869826710922676e-05,
|
| 256 |
+
"loss": 0.024548523128032684,
|
| 257 |
+
"step": 300,
|
| 258 |
+
"token_acc": 0.9903869262196587
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.16533333333333333,
|
| 262 |
+
"grad_norm": 1.5546875,
|
| 263 |
+
"learning_rate": 1.9855566685594817e-05,
|
| 264 |
+
"loss": 0.02712039351463318,
|
| 265 |
+
"step": 310,
|
| 266 |
+
"token_acc": 0.9897129186602871
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.17066666666666666,
|
| 270 |
+
"grad_norm": 2.015625,
|
| 271 |
+
"learning_rate": 1.984057131374303e-05,
|
| 272 |
+
"loss": 0.028550270199775695,
|
| 273 |
+
"step": 320,
|
| 274 |
+
"token_acc": 0.9891487822522306
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.176,
|
| 278 |
+
"grad_norm": 2.203125,
|
| 279 |
+
"learning_rate": 1.982484171420654e-05,
|
| 280 |
+
"loss": 0.02943946123123169,
|
| 281 |
+
"step": 330,
|
| 282 |
+
"token_acc": 0.9891618497109826
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18133333333333335,
|
| 286 |
+
"grad_norm": 1.65625,
|
| 287 |
+
"learning_rate": 1.980837906060698e-05,
|
| 288 |
+
"loss": 0.026945659518241884,
|
| 289 |
+
"step": 340,
|
| 290 |
+
"token_acc": 0.9886992065400336
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.18666666666666668,
|
| 294 |
+
"grad_norm": 2.84375,
|
| 295 |
+
"learning_rate": 1.979118458126085e-05,
|
| 296 |
+
"loss": 0.030513125658035278,
|
| 297 |
+
"step": 350,
|
| 298 |
+
"token_acc": 0.9872350674373795
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.192,
|
| 302 |
+
"grad_norm": 3.15625,
|
| 303 |
+
"learning_rate": 1.9773259559087838e-05,
|
| 304 |
+
"loss": 0.02490377426147461,
|
| 305 |
+
"step": 360,
|
| 306 |
+
"token_acc": 0.9895038167938931
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.19733333333333333,
|
| 310 |
+
"grad_norm": 1.34375,
|
| 311 |
+
"learning_rate": 1.975460533151513e-05,
|
| 312 |
+
"loss": 0.025952666997909546,
|
| 313 |
+
"step": 370,
|
| 314 |
+
"token_acc": 0.9888996138996139
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.20266666666666666,
|
| 318 |
+
"grad_norm": 2.25,
|
| 319 |
+
"learning_rate": 1.9735223290377595e-05,
|
| 320 |
+
"loss": 0.016641640663146974,
|
| 321 |
+
"step": 380,
|
| 322 |
+
"token_acc": 0.9939686369119421
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.208,
|
| 326 |
+
"grad_norm": 1.09375,
|
| 327 |
+
"learning_rate": 1.971511488181395e-05,
|
| 328 |
+
"loss": 0.034984779357910153,
|
| 329 |
+
"step": 390,
|
| 330 |
+
"token_acc": 0.9870067372473532
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.21333333333333335,
|
| 334 |
+
"grad_norm": 1.6015625,
|
| 335 |
+
"learning_rate": 1.9694281606158864e-05,
|
| 336 |
+
"loss": 0.026276156306266785,
|
| 337 |
+
"step": 400,
|
| 338 |
+
"token_acc": 0.9906204906204906
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.21866666666666668,
|
| 342 |
+
"grad_norm": 2.015625,
|
| 343 |
+
"learning_rate": 1.9672725017831003e-05,
|
| 344 |
+
"loss": 0.020120564103126525,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"token_acc": 0.9908499879605105
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.224,
|
| 350 |
+
"grad_norm": 1.6875,
|
| 351 |
+
"learning_rate": 1.9650446725217056e-05,
|
| 352 |
+
"loss": 0.018248651921749116,
|
| 353 |
+
"step": 420,
|
| 354 |
+
"token_acc": 0.9915743861338469
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.22933333333333333,
|
| 358 |
+
"grad_norm": 1.5546875,
|
| 359 |
+
"learning_rate": 1.9627448390551736e-05,
|
| 360 |
+
"loss": 0.027030360698699952,
|
| 361 |
+
"step": 430,
|
| 362 |
+
"token_acc": 0.9883805374001452
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.23466666666666666,
|
| 366 |
+
"grad_norm": 1.7109375,
|
| 367 |
+
"learning_rate": 1.9603731729793746e-05,
|
| 368 |
+
"loss": 0.01883748471736908,
|
| 369 |
+
"step": 440,
|
| 370 |
+
"token_acc": 0.992797118847539
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.24,
|
| 374 |
+
"grad_norm": 1.1328125,
|
| 375 |
+
"learning_rate": 1.9579298512497758e-05,
|
| 376 |
+
"loss": 0.02055278718471527,
|
| 377 |
+
"step": 450,
|
| 378 |
+
"token_acc": 0.992283578490475
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.24533333333333332,
|
| 382 |
+
"grad_norm": 2.640625,
|
| 383 |
+
"learning_rate": 1.9554150561682374e-05,
|
| 384 |
+
"loss": 0.01704043596982956,
|
| 385 |
+
"step": 460,
|
| 386 |
+
"token_acc": 0.9932692307692308
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.25066666666666665,
|
| 390 |
+
"grad_norm": 2.453125,
|
| 391 |
+
"learning_rate": 1.9528289753694108e-05,
|
| 392 |
+
"loss": 0.02123623788356781,
|
| 393 |
+
"step": 470,
|
| 394 |
+
"token_acc": 0.9913689762646847
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.256,
|
| 398 |
+
"grad_norm": 1.7578125,
|
| 399 |
+
"learning_rate": 1.9501718018067395e-05,
|
| 400 |
+
"loss": 0.019534851610660552,
|
| 401 |
+
"step": 480,
|
| 402 |
+
"token_acc": 0.9918229918229918
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2613333333333333,
|
| 406 |
+
"grad_norm": 1.03125,
|
| 407 |
+
"learning_rate": 1.9474437337380608e-05,
|
| 408 |
+
"loss": 0.021141186356544495,
|
| 409 |
+
"step": 490,
|
| 410 |
+
"token_acc": 0.9910950661853188
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.26666666666666666,
|
| 414 |
+
"grad_norm": 1.4453125,
|
| 415 |
+
"learning_rate": 1.944644974710816e-05,
|
| 416 |
+
"loss": 0.020709624886512755,
|
| 417 |
+
"step": 500,
|
| 418 |
+
"token_acc": 0.991608726923999
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.272,
|
| 422 |
+
"grad_norm": 1.8828125,
|
| 423 |
+
"learning_rate": 1.9417757335468596e-05,
|
| 424 |
+
"loss": 0.023134306073188782,
|
| 425 |
+
"step": 510,
|
| 426 |
+
"token_acc": 0.9908543922984356
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.2773333333333333,
|
| 430 |
+
"grad_norm": 1.7890625,
|
| 431 |
+
"learning_rate": 1.9388362243268823e-05,
|
| 432 |
+
"loss": 0.026473182439804076,
|
| 433 |
+
"step": 520,
|
| 434 |
+
"token_acc": 0.9901465993751501
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.2826666666666667,
|
| 438 |
+
"grad_norm": 1.9765625,
|
| 439 |
+
"learning_rate": 1.935826666374435e-05,
|
| 440 |
+
"loss": 0.022518408298492432,
|
| 441 |
+
"step": 530,
|
| 442 |
+
"token_acc": 0.9892267177400048
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.288,
|
| 446 |
+
"grad_norm": 1.4296875,
|
| 447 |
+
"learning_rate": 1.9327472842395666e-05,
|
| 448 |
+
"loss": 0.019042176008224488,
|
| 449 |
+
"step": 540,
|
| 450 |
+
"token_acc": 0.9918796274181992
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.29333333333333333,
|
| 454 |
+
"grad_norm": 3.078125,
|
| 455 |
+
"learning_rate": 1.9295983076820687e-05,
|
| 456 |
+
"loss": 0.024749264121055603,
|
| 457 |
+
"step": 550,
|
| 458 |
+
"token_acc": 0.9903707270101108
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2986666666666667,
|
| 462 |
+
"grad_norm": 2.296875,
|
| 463 |
+
"learning_rate": 1.9263799716543335e-05,
|
| 464 |
+
"loss": 0.02081143856048584,
|
| 465 |
+
"step": 560,
|
| 466 |
+
"token_acc": 0.9911820781696854
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.304,
|
| 470 |
+
"grad_norm": 4.25,
|
| 471 |
+
"learning_rate": 1.9230925162838223e-05,
|
| 472 |
+
"loss": 0.02844887673854828,
|
| 473 |
+
"step": 570,
|
| 474 |
+
"token_acc": 0.9888942539835828
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.30933333333333335,
|
| 478 |
+
"grad_norm": 1.7890625,
|
| 479 |
+
"learning_rate": 1.9197361868551498e-05,
|
| 480 |
+
"loss": 0.02411177456378937,
|
| 481 |
+
"step": 580,
|
| 482 |
+
"token_acc": 0.9910778876296118
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.31466666666666665,
|
| 486 |
+
"grad_norm": 2.484375,
|
| 487 |
+
"learning_rate": 1.916311233791783e-05,
|
| 488 |
+
"loss": 0.026547589898109437,
|
| 489 |
+
"step": 590,
|
| 490 |
+
"token_acc": 0.9884253677357125
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.32,
|
| 494 |
+
"grad_norm": 1.7578125,
|
| 495 |
+
"learning_rate": 1.912817912637357e-05,
|
| 496 |
+
"loss": 0.021162503957748414,
|
| 497 |
+
"step": 600,
|
| 498 |
+
"token_acc": 0.9920270596762503
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.3253333333333333,
|
| 502 |
+
"grad_norm": 2.25,
|
| 503 |
+
"learning_rate": 1.909256484036606e-05,
|
| 504 |
+
"loss": 0.018523281812667845,
|
| 505 |
+
"step": 610,
|
| 506 |
+
"token_acc": 0.9920386007237636
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.33066666666666666,
|
| 510 |
+
"grad_norm": 2.21875,
|
| 511 |
+
"learning_rate": 1.9056272137159187e-05,
|
| 512 |
+
"loss": 0.019353365898132323,
|
| 513 |
+
"step": 620,
|
| 514 |
+
"token_acc": 0.9906001446131598
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.336,
|
| 518 |
+
"grad_norm": 1.1171875,
|
| 519 |
+
"learning_rate": 1.901930372463511e-05,
|
| 520 |
+
"loss": 0.016073083877563475,
|
| 521 |
+
"step": 630,
|
| 522 |
+
"token_acc": 0.9935236267690094
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3413333333333333,
|
| 526 |
+
"grad_norm": 1.2578125,
|
| 527 |
+
"learning_rate": 1.8981662361092206e-05,
|
| 528 |
+
"loss": 0.023251956701278685,
|
| 529 |
+
"step": 640,
|
| 530 |
+
"token_acc": 0.9899159663865547
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.3466666666666667,
|
| 534 |
+
"grad_norm": 1.1015625,
|
| 535 |
+
"learning_rate": 1.8943350855039288e-05,
|
| 536 |
+
"loss": 0.020946937799453735,
|
| 537 |
+
"step": 650,
|
| 538 |
+
"token_acc": 0.9917914051183003
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.352,
|
| 542 |
+
"grad_norm": 1.3828125,
|
| 543 |
+
"learning_rate": 1.8904372064986033e-05,
|
| 544 |
+
"loss": 0.026175621151924133,
|
| 545 |
+
"step": 660,
|
| 546 |
+
"token_acc": 0.9892267177400048
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.35733333333333334,
|
| 550 |
+
"grad_norm": 1.546875,
|
| 551 |
+
"learning_rate": 1.886472889922972e-05,
|
| 552 |
+
"loss": 0.021933737397193908,
|
| 553 |
+
"step": 670,
|
| 554 |
+
"token_acc": 0.9913190258017844
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.3626666666666667,
|
| 558 |
+
"grad_norm": 2.15625,
|
| 559 |
+
"learning_rate": 1.8824424315638233e-05,
|
| 560 |
+
"loss": 0.024211180210113526,
|
| 561 |
+
"step": 680,
|
| 562 |
+
"token_acc": 0.9887694145758662
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.368,
|
| 566 |
+
"grad_norm": 2.171875,
|
| 567 |
+
"learning_rate": 1.8783461321429356e-05,
|
| 568 |
+
"loss": 0.02285428047180176,
|
| 569 |
+
"step": 690,
|
| 570 |
+
"token_acc": 0.9899183869419107
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.37333333333333335,
|
| 574 |
+
"grad_norm": 2.875,
|
| 575 |
+
"learning_rate": 1.874184297294641e-05,
|
| 576 |
+
"loss": 0.017681846022605897,
|
| 577 |
+
"step": 700,
|
| 578 |
+
"token_acc": 0.9925319200192725
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.37866666666666665,
|
| 582 |
+
"grad_norm": 2.890625,
|
| 583 |
+
"learning_rate": 1.8699572375430206e-05,
|
| 584 |
+
"loss": 0.024342547357082366,
|
| 585 |
+
"step": 710,
|
| 586 |
+
"token_acc": 0.9891956782713085
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.384,
|
| 590 |
+
"grad_norm": 1.5546875,
|
| 591 |
+
"learning_rate": 1.8656652682787356e-05,
|
| 592 |
+
"loss": 0.019416600465774536,
|
| 593 |
+
"step": 720,
|
| 594 |
+
"token_acc": 0.9918111753371869
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.3893333333333333,
|
| 598 |
+
"grad_norm": 1.9921875,
|
| 599 |
+
"learning_rate": 1.861308709735496e-05,
|
| 600 |
+
"loss": 0.021490809321403504,
|
| 601 |
+
"step": 730,
|
| 602 |
+
"token_acc": 0.9920673076923077
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.39466666666666667,
|
| 606 |
+
"grad_norm": 1.359375,
|
| 607 |
+
"learning_rate": 1.856887886966166e-05,
|
| 608 |
+
"loss": 0.022315359115600585,
|
| 609 |
+
"step": 740,
|
| 610 |
+
"token_acc": 0.9910800385728061
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.4,
|
| 614 |
+
"grad_norm": 2.125,
|
| 615 |
+
"learning_rate": 1.8524031298185114e-05,
|
| 616 |
+
"loss": 0.02025478482246399,
|
| 617 |
+
"step": 750,
|
| 618 |
+
"token_acc": 0.9923076923076923
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4053333333333333,
|
| 622 |
+
"grad_norm": 0.59765625,
|
| 623 |
+
"learning_rate": 1.8478547729105898e-05,
|
| 624 |
+
"loss": 0.01826128214597702,
|
| 625 |
+
"step": 760,
|
| 626 |
+
"token_acc": 0.9928005759539237
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4106666666666667,
|
| 630 |
+
"grad_norm": 2.34375,
|
| 631 |
+
"learning_rate": 1.8432431556057832e-05,
|
| 632 |
+
"loss": 0.018927228450775147,
|
| 633 |
+
"step": 770,
|
| 634 |
+
"token_acc": 0.9920501084076127
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.416,
|
| 638 |
+
"grad_norm": 1.6796875,
|
| 639 |
+
"learning_rate": 1.838568621987478e-05,
|
| 640 |
+
"loss": 0.019689281284809113,
|
| 641 |
+
"step": 780,
|
| 642 |
+
"token_acc": 0.9923187710033605
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.42133333333333334,
|
| 646 |
+
"grad_norm": 1.0390625,
|
| 647 |
+
"learning_rate": 1.8338315208333904e-05,
|
| 648 |
+
"loss": 0.019245265424251555,
|
| 649 |
+
"step": 790,
|
| 650 |
+
"token_acc": 0.9921109251733206
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.4266666666666667,
|
| 654 |
+
"grad_norm": 3.15625,
|
| 655 |
+
"learning_rate": 1.8290322055895454e-05,
|
| 656 |
+
"loss": 0.029564368724822997,
|
| 657 |
+
"step": 800,
|
| 658 |
+
"token_acc": 0.9883692755027865
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.432,
|
| 662 |
+
"grad_norm": 1.8203125,
|
| 663 |
+
"learning_rate": 1.8241710343439042e-05,
|
| 664 |
+
"loss": 0.019276759028434752,
|
| 665 |
+
"step": 810,
|
| 666 |
+
"token_acc": 0.9908960229995208
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.43733333333333335,
|
| 670 |
+
"grad_norm": 1.8671875,
|
| 671 |
+
"learning_rate": 1.8192483697996473e-05,
|
| 672 |
+
"loss": 0.02783963978290558,
|
| 673 |
+
"step": 820,
|
| 674 |
+
"token_acc": 0.9889103182256509
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44266666666666665,
|
| 678 |
+
"grad_norm": 1.109375,
|
| 679 |
+
"learning_rate": 1.814264579248111e-05,
|
| 680 |
+
"loss": 0.021492433547973634,
|
| 681 |
+
"step": 830,
|
| 682 |
+
"token_acc": 0.9923408329344183
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.448,
|
| 686 |
+
"grad_norm": 1.90625,
|
| 687 |
+
"learning_rate": 1.809220034541384e-05,
|
| 688 |
+
"loss": 0.018139883875846863,
|
| 689 |
+
"step": 840,
|
| 690 |
+
"token_acc": 0.9913565426170469
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.4533333333333333,
|
| 694 |
+
"grad_norm": 1.9765625,
|
| 695 |
+
"learning_rate": 1.8041151120645622e-05,
|
| 696 |
+
"loss": 0.01825737953186035,
|
| 697 |
+
"step": 850,
|
| 698 |
+
"token_acc": 0.9932789246279404
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.45866666666666667,
|
| 702 |
+
"grad_norm": 1.0078125,
|
| 703 |
+
"learning_rate": 1.7989501927076663e-05,
|
| 704 |
+
"loss": 0.019094854593276978,
|
| 705 |
+
"step": 860,
|
| 706 |
+
"token_acc": 0.9921109251733206
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.464,
|
| 710 |
+
"grad_norm": 2.4375,
|
| 711 |
+
"learning_rate": 1.793725661837223e-05,
|
| 712 |
+
"loss": 0.016404467821121215,
|
| 713 |
+
"step": 870,
|
| 714 |
+
"token_acc": 0.9937649880095923
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4693333333333333,
|
| 718 |
+
"grad_norm": 0.625,
|
| 719 |
+
"learning_rate": 1.7884419092675104e-05,
|
| 720 |
+
"loss": 0.01613576114177704,
|
| 721 |
+
"step": 880,
|
| 722 |
+
"token_acc": 0.9940033581194531
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.4746666666666667,
|
| 726 |
+
"grad_norm": 1.15625,
|
| 727 |
+
"learning_rate": 1.7830993292314736e-05,
|
| 728 |
+
"loss": 0.02038634419441223,
|
| 729 |
+
"step": 890,
|
| 730 |
+
"token_acc": 0.9923518164435946
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.48,
|
| 734 |
+
"grad_norm": 2.78125,
|
| 735 |
+
"learning_rate": 1.7776983203513113e-05,
|
| 736 |
+
"loss": 0.022456066310405733,
|
| 737 |
+
"step": 900,
|
| 738 |
+
"token_acc": 0.9901014002897152
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.48533333333333334,
|
| 742 |
+
"grad_norm": 1.640625,
|
| 743 |
+
"learning_rate": 1.7722392856087326e-05,
|
| 744 |
+
"loss": 0.020150689780712126,
|
| 745 |
+
"step": 910,
|
| 746 |
+
"token_acc": 0.9925748502994012
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.49066666666666664,
|
| 750 |
+
"grad_norm": 0.78515625,
|
| 751 |
+
"learning_rate": 1.7667226323148894e-05,
|
| 752 |
+
"loss": 0.020665311813354494,
|
| 753 |
+
"step": 920,
|
| 754 |
+
"token_acc": 0.9916167664670659
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.496,
|
| 758 |
+
"grad_norm": 1.9140625,
|
| 759 |
+
"learning_rate": 1.7611487720799868e-05,
|
| 760 |
+
"loss": 0.02016124427318573,
|
| 761 |
+
"step": 930,
|
| 762 |
+
"token_acc": 0.9916267942583732
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.5013333333333333,
|
| 766 |
+
"grad_norm": 2.21875,
|
| 767 |
+
"learning_rate": 1.7555181207825712e-05,
|
| 768 |
+
"loss": 0.02833055853843689,
|
| 769 |
+
"step": 940,
|
| 770 |
+
"token_acc": 0.9886801541425819
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5066666666666667,
|
| 774 |
+
"grad_norm": 0.91015625,
|
| 775 |
+
"learning_rate": 1.749831098538501e-05,
|
| 776 |
+
"loss": 0.01865219920873642,
|
| 777 |
+
"step": 950,
|
| 778 |
+
"token_acc": 0.9929816069699903
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.512,
|
| 782 |
+
"grad_norm": 1.4765625,
|
| 783 |
+
"learning_rate": 1.744088129669601e-05,
|
| 784 |
+
"loss": 0.015682655572891235,
|
| 785 |
+
"step": 960,
|
| 786 |
+
"token_acc": 0.9940334128878282
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5173333333333333,
|
| 790 |
+
"grad_norm": 2.171875,
|
| 791 |
+
"learning_rate": 1.7382896426720025e-05,
|
| 792 |
+
"loss": 0.01739872097969055,
|
| 793 |
+
"step": 970,
|
| 794 |
+
"token_acc": 0.9930238152513832
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5226666666666666,
|
| 798 |
+
"grad_norm": 2.328125,
|
| 799 |
+
"learning_rate": 1.732436070184172e-05,
|
| 800 |
+
"loss": 0.021472826600074768,
|
| 801 |
+
"step": 980,
|
| 802 |
+
"token_acc": 0.9922965816080885
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.528,
|
| 806 |
+
"grad_norm": 1.40625,
|
| 807 |
+
"learning_rate": 1.726527848954631e-05,
|
| 808 |
+
"loss": 0.02006145417690277,
|
| 809 |
+
"step": 990,
|
| 810 |
+
"token_acc": 0.9905910735826297
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.5333333333333333,
|
| 814 |
+
"grad_norm": 1.140625,
|
| 815 |
+
"learning_rate": 1.72056541980937e-05,
|
| 816 |
+
"loss": 0.01847991794347763,
|
| 817 |
+
"step": 1000,
|
| 818 |
+
"token_acc": 0.9911462072266093
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.5386666666666666,
|
| 822 |
+
"grad_norm": 1.3515625,
|
| 823 |
+
"learning_rate": 1.7145492276189565e-05,
|
| 824 |
+
"loss": 0.01983983814716339,
|
| 825 |
+
"step": 1010,
|
| 826 |
+
"token_acc": 0.9906295050456512
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.544,
|
| 830 |
+
"grad_norm": 2.25,
|
| 831 |
+
"learning_rate": 1.7084797212653427e-05,
|
| 832 |
+
"loss": 0.020782938599586485,
|
| 833 |
+
"step": 1020,
|
| 834 |
+
"token_acc": 0.9922928709055877
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5493333333333333,
|
| 838 |
+
"grad_norm": 2.40625,
|
| 839 |
+
"learning_rate": 1.7023573536083734e-05,
|
| 840 |
+
"loss": 0.017258843779563902,
|
| 841 |
+
"step": 1030,
|
| 842 |
+
"token_acc": 0.9934545454545455
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5546666666666666,
|
| 846 |
+
"grad_norm": 1.3046875,
|
| 847 |
+
"learning_rate": 1.6961825814519976e-05,
|
| 848 |
+
"loss": 0.020492631196975707,
|
| 849 |
+
"step": 1040,
|
| 850 |
+
"token_acc": 0.9898477157360406
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.56,
|
| 854 |
+
"grad_norm": 0.9296875,
|
| 855 |
+
"learning_rate": 1.6899558655101832e-05,
|
| 856 |
+
"loss": 0.018405696749687193,
|
| 857 |
+
"step": 1050,
|
| 858 |
+
"token_acc": 0.9937694704049844
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.5653333333333334,
|
| 862 |
+
"grad_norm": 1.1953125,
|
| 863 |
+
"learning_rate": 1.683677670372544e-05,
|
| 864 |
+
"loss": 0.02100014090538025,
|
| 865 |
+
"step": 1060,
|
| 866 |
+
"token_acc": 0.9916347992351816
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5706666666666667,
|
| 870 |
+
"grad_norm": 1.671875,
|
| 871 |
+
"learning_rate": 1.6773484644696764e-05,
|
| 872 |
+
"loss": 0.01713407039642334,
|
| 873 |
+
"step": 1070,
|
| 874 |
+
"token_acc": 0.9932708483537611
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.576,
|
| 878 |
+
"grad_norm": 2.390625,
|
| 879 |
+
"learning_rate": 1.6709687200382057e-05,
|
| 880 |
+
"loss": 0.018759623169898987,
|
| 881 |
+
"step": 1080,
|
| 882 |
+
"token_acc": 0.9932659932659933
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.5813333333333334,
|
| 886 |
+
"grad_norm": 1.4921875,
|
| 887 |
+
"learning_rate": 1.6645389130855547e-05,
|
| 888 |
+
"loss": 0.02089170664548874,
|
| 889 |
+
"step": 1090,
|
| 890 |
+
"token_acc": 0.9915905814512254
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.5866666666666667,
|
| 894 |
+
"grad_norm": 1.6796875,
|
| 895 |
+
"learning_rate": 1.658059523354425e-05,
|
| 896 |
+
"loss": 0.023786291480064392,
|
| 897 |
+
"step": 1100,
|
| 898 |
+
"token_acc": 0.9910735826296743
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.592,
|
| 902 |
+
"grad_norm": 2.328125,
|
| 903 |
+
"learning_rate": 1.6515310342870038e-05,
|
| 904 |
+
"loss": 0.02250564396381378,
|
| 905 |
+
"step": 1110,
|
| 906 |
+
"token_acc": 0.9894179894179894
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5973333333333334,
|
| 910 |
+
"grad_norm": 1.03125,
|
| 911 |
+
"learning_rate": 1.6449539329888934e-05,
|
| 912 |
+
"loss": 0.018116173148155213,
|
| 913 |
+
"step": 1120,
|
| 914 |
+
"token_acc": 0.9922761284093652
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6026666666666667,
|
| 918 |
+
"grad_norm": 1.984375,
|
| 919 |
+
"learning_rate": 1.638328710192766e-05,
|
| 920 |
+
"loss": 0.015691110491752626,
|
| 921 |
+
"step": 1130,
|
| 922 |
+
"token_acc": 0.9942501197891711
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.608,
|
| 926 |
+
"grad_norm": 1.953125,
|
| 927 |
+
"learning_rate": 1.63165586022175e-05,
|
| 928 |
+
"loss": 0.020994681119918823,
|
| 929 |
+
"step": 1140,
|
| 930 |
+
"token_acc": 0.9935158501440923
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.6133333333333333,
|
| 934 |
+
"grad_norm": 1.9296875,
|
| 935 |
+
"learning_rate": 1.6249358809525457e-05,
|
| 936 |
+
"loss": 0.021514520049095154,
|
| 937 |
+
"step": 1150,
|
| 938 |
+
"token_acc": 0.9916187739463601
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.6186666666666667,
|
| 942 |
+
"grad_norm": 1.078125,
|
| 943 |
+
"learning_rate": 1.6181692737782806e-05,
|
| 944 |
+
"loss": 0.019446739554405214,
|
| 945 |
+
"step": 1160,
|
| 946 |
+
"token_acc": 0.9911462072266093
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.624,
|
| 950 |
+
"grad_norm": 25.875,
|
| 951 |
+
"learning_rate": 1.6113565435710975e-05,
|
| 952 |
+
"loss": 0.02417919337749481,
|
| 953 |
+
"step": 1170,
|
| 954 |
+
"token_acc": 0.9889049686444766
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6293333333333333,
|
| 958 |
+
"grad_norm": 1.203125,
|
| 959 |
+
"learning_rate": 1.6044981986444827e-05,
|
| 960 |
+
"loss": 0.016394074261188506,
|
| 961 |
+
"step": 1180,
|
| 962 |
+
"token_acc": 0.9947077219148425
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6346666666666667,
|
| 966 |
+
"grad_norm": 1.765625,
|
| 967 |
+
"learning_rate": 1.597594750715344e-05,
|
| 968 |
+
"loss": 0.025788456201553345,
|
| 969 |
+
"step": 1190,
|
| 970 |
+
"token_acc": 0.9900918318028032
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.64,
|
| 974 |
+
"grad_norm": 1.5390625,
|
| 975 |
+
"learning_rate": 1.590646714865828e-05,
|
| 976 |
+
"loss": 0.02058074176311493,
|
| 977 |
+
"step": 1200,
|
| 978 |
+
"token_acc": 0.9913419913419913
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6453333333333333,
|
| 982 |
+
"grad_norm": 1.2109375,
|
| 983 |
+
"learning_rate": 1.5836546095048873e-05,
|
| 984 |
+
"loss": 0.02075360417366028,
|
| 985 |
+
"step": 1210,
|
| 986 |
+
"token_acc": 0.9903614457831326
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.6506666666666666,
|
| 990 |
+
"grad_norm": 2.15625,
|
| 991 |
+
"learning_rate": 1.5766189563296027e-05,
|
| 992 |
+
"loss": 0.01986580789089203,
|
| 993 |
+
"step": 1220,
|
| 994 |
+
"token_acc": 0.991866028708134
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.656,
|
| 998 |
+
"grad_norm": 1.0390625,
|
| 999 |
+
"learning_rate": 1.5695402802862586e-05,
|
| 1000 |
+
"loss": 0.020870494842529296,
|
| 1001 |
+
"step": 1230,
|
| 1002 |
+
"token_acc": 0.9921052631578947
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.6613333333333333,
|
| 1006 |
+
"grad_norm": 0.98828125,
|
| 1007 |
+
"learning_rate": 1.5624191095311736e-05,
|
| 1008 |
+
"loss": 0.01600797474384308,
|
| 1009 |
+
"step": 1240,
|
| 1010 |
+
"token_acc": 0.9934593023255814
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6666666666666666,
|
| 1014 |
+
"grad_norm": 1.828125,
|
| 1015 |
+
"learning_rate": 1.5552559753912952e-05,
|
| 1016 |
+
"loss": 0.018866974115371703,
|
| 1017 |
+
"step": 1250,
|
| 1018 |
+
"token_acc": 0.9932853717026379
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.672,
|
| 1022 |
+
"grad_norm": 1.203125,
|
| 1023 |
+
"learning_rate": 1.5480514123245557e-05,
|
| 1024 |
+
"loss": 0.014872387051582336,
|
| 1025 |
+
"step": 1260,
|
| 1026 |
+
"token_acc": 0.9934782608695653
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.6773333333333333,
|
| 1030 |
+
"grad_norm": 1.3515625,
|
| 1031 |
+
"learning_rate": 1.540805957879994e-05,
|
| 1032 |
+
"loss": 0.01863376349210739,
|
| 1033 |
+
"step": 1270,
|
| 1034 |
+
"token_acc": 0.9929799080125877
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6826666666666666,
|
| 1038 |
+
"grad_norm": 1.234375,
|
| 1039 |
+
"learning_rate": 1.5335201526576505e-05,
|
| 1040 |
+
"loss": 0.017441746592521668,
|
| 1041 |
+
"step": 1280,
|
| 1042 |
+
"token_acc": 0.9937469937469937
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.688,
|
| 1046 |
+
"grad_norm": 0.7890625,
|
| 1047 |
+
"learning_rate": 1.5261945402682292e-05,
|
| 1048 |
+
"loss": 0.015908092260360718,
|
| 1049 |
+
"step": 1290,
|
| 1050 |
+
"token_acc": 0.9935189630340855
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.6933333333333334,
|
| 1054 |
+
"grad_norm": 1.4296875,
|
| 1055 |
+
"learning_rate": 1.5188296672925378e-05,
|
| 1056 |
+
"loss": 0.01847825348377228,
|
| 1057 |
+
"step": 1300,
|
| 1058 |
+
"token_acc": 0.9921033740129217
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.6986666666666667,
|
| 1062 |
+
"grad_norm": 1.3125,
|
| 1063 |
+
"learning_rate": 1.511426083240708e-05,
|
| 1064 |
+
"loss": 0.020309022068977355,
|
| 1065 |
+
"step": 1310,
|
| 1066 |
+
"token_acc": 0.9918776875298615
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.704,
|
| 1070 |
+
"grad_norm": 1.109375,
|
| 1071 |
+
"learning_rate": 1.503984340511193e-05,
|
| 1072 |
+
"loss": 0.015028844773769378,
|
| 1073 |
+
"step": 1320,
|
| 1074 |
+
"token_acc": 0.9934687953555879
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7093333333333334,
|
| 1078 |
+
"grad_norm": 1.6640625,
|
| 1079 |
+
"learning_rate": 1.496504994349554e-05,
|
| 1080 |
+
"loss": 0.020722246170043944,
|
| 1081 |
+
"step": 1330,
|
| 1082 |
+
"token_acc": 0.9917993246502653
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.7146666666666667,
|
| 1086 |
+
"grad_norm": 2.765625,
|
| 1087 |
+
"learning_rate": 1.4889886028070295e-05,
|
| 1088 |
+
"loss": 0.01873396784067154,
|
| 1089 |
+
"step": 1340,
|
| 1090 |
+
"token_acc": 0.9920787325972156
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.72,
|
| 1094 |
+
"grad_norm": 2.828125,
|
| 1095 |
+
"learning_rate": 1.4814357266989e-05,
|
| 1096 |
+
"loss": 0.015888297557830812,
|
| 1097 |
+
"step": 1350,
|
| 1098 |
+
"token_acc": 0.9925801819052178
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.7253333333333334,
|
| 1102 |
+
"grad_norm": 1.6015625,
|
| 1103 |
+
"learning_rate": 1.4738469295626435e-05,
|
| 1104 |
+
"loss": 0.021275366842746734,
|
| 1105 |
+
"step": 1360,
|
| 1106 |
+
"token_acc": 0.9901299951853635
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.7306666666666667,
|
| 1110 |
+
"grad_norm": 2.359375,
|
| 1111 |
+
"learning_rate": 1.4662227776158877e-05,
|
| 1112 |
+
"loss": 0.019410797953605653,
|
| 1113 |
+
"step": 1370,
|
| 1114 |
+
"token_acc": 0.991321118611379
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.736,
|
| 1118 |
+
"grad_norm": 1.625,
|
| 1119 |
+
"learning_rate": 1.4585638397141657e-05,
|
| 1120 |
+
"loss": 0.01648997813463211,
|
| 1121 |
+
"step": 1380,
|
| 1122 |
+
"token_acc": 0.9937769267592149
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7413333333333333,
|
| 1126 |
+
"grad_norm": 2.015625,
|
| 1127 |
+
"learning_rate": 1.4508706873084691e-05,
|
| 1128 |
+
"loss": 0.016959480941295624,
|
| 1129 |
+
"step": 1390,
|
| 1130 |
+
"token_acc": 0.9930572180991142
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7466666666666667,
|
| 1134 |
+
"grad_norm": 2.609375,
|
| 1135 |
+
"learning_rate": 1.4431438944026135e-05,
|
| 1136 |
+
"loss": 0.0224549800157547,
|
| 1137 |
+
"step": 1400,
|
| 1138 |
+
"token_acc": 0.9907990314769975
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.752,
|
| 1142 |
+
"grad_norm": 0.8671875,
|
| 1143 |
+
"learning_rate": 1.4353840375104093e-05,
|
| 1144 |
+
"loss": 0.020980487763881683,
|
| 1145 |
+
"step": 1410,
|
| 1146 |
+
"token_acc": 0.9906429942418427
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.7573333333333333,
|
| 1150 |
+
"grad_norm": 1.46875,
|
| 1151 |
+
"learning_rate": 1.4275916956126475e-05,
|
| 1152 |
+
"loss": 0.018121670186519622,
|
| 1153 |
+
"step": 1420,
|
| 1154 |
+
"token_acc": 0.9928281137939278
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.7626666666666667,
|
| 1158 |
+
"grad_norm": 1.453125,
|
| 1159 |
+
"learning_rate": 1.4197674501138993e-05,
|
| 1160 |
+
"loss": 0.01867426037788391,
|
| 1161 |
+
"step": 1430,
|
| 1162 |
+
"token_acc": 0.9937634924442312
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.768,
|
| 1166 |
+
"grad_norm": 1.1484375,
|
| 1167 |
+
"learning_rate": 1.411911884799138e-05,
|
| 1168 |
+
"loss": 0.02212289273738861,
|
| 1169 |
+
"step": 1440,
|
| 1170 |
+
"token_acc": 0.9910972088546679
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.7733333333333333,
|
| 1174 |
+
"grad_norm": 1.125,
|
| 1175 |
+
"learning_rate": 1.4040255857901797e-05,
|
| 1176 |
+
"loss": 0.0170156791806221,
|
| 1177 |
+
"step": 1450,
|
| 1178 |
+
"token_acc": 0.9925641640681219
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7786666666666666,
|
| 1182 |
+
"grad_norm": 2.453125,
|
| 1183 |
+
"learning_rate": 1.3961091415019525e-05,
|
| 1184 |
+
"loss": 0.01638861894607544,
|
| 1185 |
+
"step": 1460,
|
| 1186 |
+
"token_acc": 0.992320614350852
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.784,
|
| 1190 |
+
"grad_norm": 1.921875,
|
| 1191 |
+
"learning_rate": 1.3881631425985935e-05,
|
| 1192 |
+
"loss": 0.01728953719139099,
|
| 1193 |
+
"step": 1470,
|
| 1194 |
+
"token_acc": 0.993993272465161
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.7893333333333333,
|
| 1198 |
+
"grad_norm": 3.0625,
|
| 1199 |
+
"learning_rate": 1.3801881819493772e-05,
|
| 1200 |
+
"loss": 0.01775331199169159,
|
| 1201 |
+
"step": 1480,
|
| 1202 |
+
"token_acc": 0.9929900894367899
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.7946666666666666,
|
| 1206 |
+
"grad_norm": 1.2265625,
|
| 1207 |
+
"learning_rate": 1.3721848545844812e-05,
|
| 1208 |
+
"loss": 0.01741935908794403,
|
| 1209 |
+
"step": 1490,
|
| 1210 |
+
"token_acc": 0.9929934766851897
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.8,
|
| 1214 |
+
"grad_norm": 2.46875,
|
| 1215 |
+
"learning_rate": 1.3641537576505882e-05,
|
| 1216 |
+
"loss": 0.015620550513267517,
|
| 1217 |
+
"step": 1500,
|
| 1218 |
+
"token_acc": 0.9935205183585313
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.8053333333333333,
|
| 1222 |
+
"grad_norm": 1.5546875,
|
| 1223 |
+
"learning_rate": 1.3560954903663333e-05,
|
| 1224 |
+
"loss": 0.01380889117717743,
|
| 1225 |
+
"step": 1510,
|
| 1226 |
+
"token_acc": 0.9932595089070775
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.8106666666666666,
|
| 1230 |
+
"grad_norm": 1.359375,
|
| 1231 |
+
"learning_rate": 1.3480106539775935e-05,
|
| 1232 |
+
"loss": 0.015630985796451568,
|
| 1233 |
+
"step": 1520,
|
| 1234 |
+
"token_acc": 0.9935018050541516
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.816,
|
| 1238 |
+
"grad_norm": 1.6484375,
|
| 1239 |
+
"learning_rate": 1.3398998517126275e-05,
|
| 1240 |
+
"loss": 0.02101683020591736,
|
| 1241 |
+
"step": 1530,
|
| 1242 |
+
"token_acc": 0.9911100432484382
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8213333333333334,
|
| 1246 |
+
"grad_norm": 1.3125,
|
| 1247 |
+
"learning_rate": 1.3317636887370695e-05,
|
| 1248 |
+
"loss": 0.016578157246112824,
|
| 1249 |
+
"step": 1540,
|
| 1250 |
+
"token_acc": 0.9917775090689238
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.8266666666666667,
|
| 1254 |
+
"grad_norm": 2.015625,
|
| 1255 |
+
"learning_rate": 1.3236027721087724e-05,
|
| 1256 |
+
"loss": 0.020927420258522032,
|
| 1257 |
+
"step": 1550,
|
| 1258 |
+
"token_acc": 0.990118100747168
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.832,
|
| 1262 |
+
"grad_norm": 1.6484375,
|
| 1263 |
+
"learning_rate": 1.3154177107325174e-05,
|
| 1264 |
+
"loss": 0.016280189156532288,
|
| 1265 |
+
"step": 1560,
|
| 1266 |
+
"token_acc": 0.9930388862217955
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.8373333333333334,
|
| 1270 |
+
"grad_norm": 1.5390625,
|
| 1271 |
+
"learning_rate": 1.307209115314581e-05,
|
| 1272 |
+
"loss": 0.01498023122549057,
|
| 1273 |
+
"step": 1570,
|
| 1274 |
+
"token_acc": 0.9932676124068286
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.8426666666666667,
|
| 1278 |
+
"grad_norm": 1.203125,
|
| 1279 |
+
"learning_rate": 1.2989775983171688e-05,
|
| 1280 |
+
"loss": 0.01635483354330063,
|
| 1281 |
+
"step": 1580,
|
| 1282 |
+
"token_acc": 0.9932448733413751
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.848,
|
| 1286 |
+
"grad_norm": 1.328125,
|
| 1287 |
+
"learning_rate": 1.2907237739127174e-05,
|
| 1288 |
+
"loss": 0.01580911874771118,
|
| 1289 |
+
"step": 1590,
|
| 1290 |
+
"token_acc": 0.9927606177606177
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8533333333333334,
|
| 1294 |
+
"grad_norm": 2.703125,
|
| 1295 |
+
"learning_rate": 1.2824482579380715e-05,
|
| 1296 |
+
"loss": 0.017236483097076417,
|
| 1297 |
+
"step": 1600,
|
| 1298 |
+
"token_acc": 0.9939990398463754
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8586666666666667,
|
| 1302 |
+
"grad_norm": 1.234375,
|
| 1303 |
+
"learning_rate": 1.274151667848533e-05,
|
| 1304 |
+
"loss": 0.013278999924659729,
|
| 1305 |
+
"step": 1610,
|
| 1306 |
+
"token_acc": 0.9952164553934465
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.864,
|
| 1310 |
+
"grad_norm": 0.78515625,
|
| 1311 |
+
"learning_rate": 1.2658346226717917e-05,
|
| 1312 |
+
"loss": 0.01357889622449875,
|
| 1313 |
+
"step": 1620,
|
| 1314 |
+
"token_acc": 0.9937439846005774
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.8693333333333333,
|
| 1318 |
+
"grad_norm": 1.4453125,
|
| 1319 |
+
"learning_rate": 1.25749774296174e-05,
|
| 1320 |
+
"loss": 0.019012153148651123,
|
| 1321 |
+
"step": 1630,
|
| 1322 |
+
"token_acc": 0.992816091954023
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.8746666666666667,
|
| 1326 |
+
"grad_norm": 1.9296875,
|
| 1327 |
+
"learning_rate": 1.2491416507521692e-05,
|
| 1328 |
+
"loss": 0.01692788451910019,
|
| 1329 |
+
"step": 1640,
|
| 1330 |
+
"token_acc": 0.993006993006993
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.88,
|
| 1334 |
+
"grad_norm": 1.5625,
|
| 1335 |
+
"learning_rate": 1.2407669695103602e-05,
|
| 1336 |
+
"loss": 0.01657618284225464,
|
| 1337 |
+
"step": 1650,
|
| 1338 |
+
"token_acc": 0.9930622009569378
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.8853333333333333,
|
| 1342 |
+
"grad_norm": 1.25,
|
| 1343 |
+
"learning_rate": 1.2323743240905634e-05,
|
| 1344 |
+
"loss": 0.014970755577087403,
|
| 1345 |
+
"step": 1660,
|
| 1346 |
+
"token_acc": 0.9937243543326092
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8906666666666667,
|
| 1350 |
+
"grad_norm": 1.03125,
|
| 1351 |
+
"learning_rate": 1.223964340687379e-05,
|
| 1352 |
+
"loss": 0.015818938612937927,
|
| 1353 |
+
"step": 1670,
|
| 1354 |
+
"token_acc": 0.9932692307692308
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.896,
|
| 1358 |
+
"grad_norm": 0.96875,
|
| 1359 |
+
"learning_rate": 1.2155376467890341e-05,
|
| 1360 |
+
"loss": 0.02039675712585449,
|
| 1361 |
+
"step": 1680,
|
| 1362 |
+
"token_acc": 0.9917874396135266
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.9013333333333333,
|
| 1366 |
+
"grad_norm": 0.91015625,
|
| 1367 |
+
"learning_rate": 1.207094871130563e-05,
|
| 1368 |
+
"loss": 0.016360247135162355,
|
| 1369 |
+
"step": 1690,
|
| 1370 |
+
"token_acc": 0.991813147122562
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.9066666666666666,
|
| 1374 |
+
"grad_norm": 1.0078125,
|
| 1375 |
+
"learning_rate": 1.1986366436468986e-05,
|
| 1376 |
+
"loss": 0.017489761114120483,
|
| 1377 |
+
"step": 1700,
|
| 1378 |
+
"token_acc": 0.992519305019305
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.912,
|
| 1382 |
+
"grad_norm": 1.8203125,
|
| 1383 |
+
"learning_rate": 1.1901635954258688e-05,
|
| 1384 |
+
"loss": 0.02098821699619293,
|
| 1385 |
+
"step": 1710,
|
| 1386 |
+
"token_acc": 0.9916127486220944
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.9173333333333333,
|
| 1390 |
+
"grad_norm": 1.578125,
|
| 1391 |
+
"learning_rate": 1.1816763586611121e-05,
|
| 1392 |
+
"loss": 0.015266384184360503,
|
| 1393 |
+
"step": 1720,
|
| 1394 |
+
"token_acc": 0.9927884615384616
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.9226666666666666,
|
| 1398 |
+
"grad_norm": 1.578125,
|
| 1399 |
+
"learning_rate": 1.1731755666049058e-05,
|
| 1400 |
+
"loss": 0.017502057552337646,
|
| 1401 |
+
"step": 1730,
|
| 1402 |
+
"token_acc": 0.994256999282125
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.928,
|
| 1406 |
+
"grad_norm": 1.6640625,
|
| 1407 |
+
"learning_rate": 1.16466185352092e-05,
|
| 1408 |
+
"loss": 0.01726265549659729,
|
| 1409 |
+
"step": 1740,
|
| 1410 |
+
"token_acc": 0.9923169267707083
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9333333333333333,
|
| 1414 |
+
"grad_norm": 2.078125,
|
| 1415 |
+
"learning_rate": 1.1561358546368907e-05,
|
| 1416 |
+
"loss": 0.015200915932655334,
|
| 1417 |
+
"step": 1750,
|
| 1418 |
+
"token_acc": 0.9925211097708082
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.9386666666666666,
|
| 1422 |
+
"grad_norm": 0.77734375,
|
| 1423 |
+
"learning_rate": 1.1475982060972273e-05,
|
| 1424 |
+
"loss": 0.019084087014198302,
|
| 1425 |
+
"step": 1760,
|
| 1426 |
+
"token_acc": 0.9923132356473697
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.944,
|
| 1430 |
+
"grad_norm": 1.0546875,
|
| 1431 |
+
"learning_rate": 1.1390495449155461e-05,
|
| 1432 |
+
"loss": 0.019373241066932678,
|
| 1433 |
+
"step": 1770,
|
| 1434 |
+
"token_acc": 0.9918288872867099
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.9493333333333334,
|
| 1438 |
+
"grad_norm": 1.3046875,
|
| 1439 |
+
"learning_rate": 1.1304905089271419e-05,
|
| 1440 |
+
"loss": 0.019359979033470153,
|
| 1441 |
+
"step": 1780,
|
| 1442 |
+
"token_acc": 0.9923150816522575
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.9546666666666667,
|
| 1446 |
+
"grad_norm": 1.2265625,
|
| 1447 |
+
"learning_rate": 1.1219217367413979e-05,
|
| 1448 |
+
"loss": 0.01616174578666687,
|
| 1449 |
+
"step": 1790,
|
| 1450 |
+
"token_acc": 0.9928143712574851
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.96,
|
| 1454 |
+
"grad_norm": 0.98828125,
|
| 1455 |
+
"learning_rate": 1.1133438676941376e-05,
|
| 1456 |
+
"loss": 0.016984623670578004,
|
| 1457 |
+
"step": 1800,
|
| 1458 |
+
"token_acc": 0.9930271699927867
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9653333333333334,
|
| 1462 |
+
"grad_norm": 1.0703125,
|
| 1463 |
+
"learning_rate": 1.1047575417999222e-05,
|
| 1464 |
+
"loss": 0.01455014944076538,
|
| 1465 |
+
"step": 1810,
|
| 1466 |
+
"token_acc": 0.9932627526467758
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.9706666666666667,
|
| 1470 |
+
"grad_norm": 1.5625,
|
| 1471 |
+
"learning_rate": 1.0961633997042972e-05,
|
| 1472 |
+
"loss": 0.013113033771514893,
|
| 1473 |
+
"step": 1820,
|
| 1474 |
+
"token_acc": 0.9945094294581046
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.976,
|
| 1478 |
+
"grad_norm": 0.60546875,
|
| 1479 |
+
"learning_rate": 1.0875620826359939e-05,
|
| 1480 |
+
"loss": 0.014685747027397156,
|
| 1481 |
+
"step": 1830,
|
| 1482 |
+
"token_acc": 0.9929679922405431
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.9813333333333333,
|
| 1486 |
+
"grad_norm": 2.578125,
|
| 1487 |
+
"learning_rate": 1.0789542323590839e-05,
|
| 1488 |
+
"loss": 0.017240770161151886,
|
| 1489 |
+
"step": 1840,
|
| 1490 |
+
"token_acc": 0.9937590014402304
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.9866666666666667,
|
| 1494 |
+
"grad_norm": 2.703125,
|
| 1495 |
+
"learning_rate": 1.0703404911250963e-05,
|
| 1496 |
+
"loss": 0.01656486988067627,
|
| 1497 |
+
"step": 1850,
|
| 1498 |
+
"token_acc": 0.9937530033637674
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.992,
|
| 1502 |
+
"grad_norm": 1.703125,
|
| 1503 |
+
"learning_rate": 1.0617215016250996e-05,
|
| 1504 |
+
"loss": 0.01589758098125458,
|
| 1505 |
+
"step": 1860,
|
| 1506 |
+
"token_acc": 0.9944524843222383
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.9973333333333333,
|
| 1510 |
+
"grad_norm": 2.734375,
|
| 1511 |
+
"learning_rate": 1.0530979069417463e-05,
|
| 1512 |
+
"loss": 0.015091650187969208,
|
| 1513 |
+
"step": 1870,
|
| 1514 |
+
"token_acc": 0.9942252165543792
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.0026666666666666,
|
| 1518 |
+
"grad_norm": 0.71484375,
|
| 1519 |
+
"learning_rate": 1.044470350501292e-05,
|
| 1520 |
+
"loss": 0.00926424264907837,
|
| 1521 |
+
"step": 1880,
|
| 1522 |
+
"token_acc": 0.9962396590624216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.008,
|
| 1526 |
+
"grad_norm": 1.46875,
|
| 1527 |
+
"learning_rate": 1.0358394760255891e-05,
|
| 1528 |
+
"loss": 0.004853641241788864,
|
| 1529 |
+
"step": 1890,
|
| 1530 |
+
"token_acc": 0.9983091787439613
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.0133333333333334,
|
| 1534 |
+
"grad_norm": 0.2578125,
|
| 1535 |
+
"learning_rate": 1.0272059274840555e-05,
|
| 1536 |
+
"loss": 0.006672994792461395,
|
| 1537 |
+
"step": 1900,
|
| 1538 |
+
"token_acc": 0.9980852082336046
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.0186666666666666,
|
| 1542 |
+
"grad_norm": 1.0,
|
| 1543 |
+
"learning_rate": 1.0185703490456281e-05,
|
| 1544 |
+
"loss": 0.00521823950111866,
|
| 1545 |
+
"step": 1910,
|
| 1546 |
+
"token_acc": 0.998324958123953
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.024,
|
| 1550 |
+
"grad_norm": 0.11767578125,
|
| 1551 |
+
"learning_rate": 1.0099333850306979e-05,
|
| 1552 |
+
"loss": 0.0029520409181714056,
|
| 1553 |
+
"step": 1920,
|
| 1554 |
+
"token_acc": 0.9992800575953924
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.0293333333333334,
|
| 1558 |
+
"grad_norm": 0.50390625,
|
| 1559 |
+
"learning_rate": 1.001295679863038e-05,
|
| 1560 |
+
"loss": 0.005888096615672111,
|
| 1561 |
+
"step": 1930,
|
| 1562 |
+
"token_acc": 0.9980838323353294
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.0346666666666666,
|
| 1566 |
+
"grad_norm": 1.1328125,
|
| 1567 |
+
"learning_rate": 9.926578780217198e-06,
|
| 1568 |
+
"loss": 0.006349328905344009,
|
| 1569 |
+
"step": 1940,
|
| 1570 |
+
"token_acc": 0.9990412272291467
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.04,
|
| 1574 |
+
"grad_norm": 4.59375,
|
| 1575 |
+
"learning_rate": 9.840206239930286e-06,
|
| 1576 |
+
"loss": 0.007245439291000366,
|
| 1577 |
+
"step": 1950,
|
| 1578 |
+
"token_acc": 0.99712368168744
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.0453333333333332,
|
| 1582 |
+
"grad_norm": 0.1767578125,
|
| 1583 |
+
"learning_rate": 9.753845622223758e-06,
|
| 1584 |
+
"loss": 0.005397027730941773,
|
| 1585 |
+
"step": 1960,
|
| 1586 |
+
"token_acc": 0.9983164983164983
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.0506666666666666,
|
| 1590 |
+
"grad_norm": 0.130859375,
|
| 1591 |
+
"learning_rate": 9.66750337066215e-06,
|
| 1592 |
+
"loss": 0.008311130106449127,
|
| 1593 |
+
"step": 1970,
|
| 1594 |
+
"token_acc": 0.9961547704878635
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.056,
|
| 1598 |
+
"grad_norm": 0.92578125,
|
| 1599 |
+
"learning_rate": 9.581185927439665e-06,
|
| 1600 |
+
"loss": 0.0037665631622076034,
|
| 1601 |
+
"step": 1980,
|
| 1602 |
+
"token_acc": 0.9987992315081652
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.0613333333333332,
|
| 1606 |
+
"grad_norm": 3.171875,
|
| 1607 |
+
"learning_rate": 9.4948997328995e-06,
|
| 1608 |
+
"loss": 0.005160611867904663,
|
| 1609 |
+
"step": 1990,
|
| 1610 |
+
"token_acc": 0.9975822050290135
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.0666666666666667,
|
| 1614 |
+
"grad_norm": 3.0,
|
| 1615 |
+
"learning_rate": 9.408651225053313e-06,
|
| 1616 |
+
"loss": 0.008499051630496978,
|
| 1617 |
+
"step": 2000,
|
| 1618 |
+
"token_acc": 0.9978354978354979
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.072,
|
| 1622 |
+
"grad_norm": 0.44140625,
|
| 1623 |
+
"learning_rate": 9.32244683910087e-06,
|
| 1624 |
+
"loss": 0.0035781636834144592,
|
| 1625 |
+
"step": 2010,
|
| 1626 |
+
"token_acc": 0.9983136593591906
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.0773333333333333,
|
| 1630 |
+
"grad_norm": 1.890625,
|
| 1631 |
+
"learning_rate": 9.236293006949901e-06,
|
| 1632 |
+
"loss": 0.0061306580901145935,
|
| 1633 |
+
"step": 2020,
|
| 1634 |
+
"token_acc": 0.9968884633796075
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.0826666666666667,
|
| 1638 |
+
"grad_norm": 1.7265625,
|
| 1639 |
+
"learning_rate": 9.150196156736205e-06,
|
| 1640 |
+
"loss": 0.006732334196567535,
|
| 1641 |
+
"step": 2030,
|
| 1642 |
+
"token_acc": 0.9980750721847931
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.088,
|
| 1646 |
+
"grad_norm": 1.8046875,
|
| 1647 |
+
"learning_rate": 9.064162712344015e-06,
|
| 1648 |
+
"loss": 0.005464298278093338,
|
| 1649 |
+
"step": 2040,
|
| 1650 |
+
"token_acc": 0.9968576262992507
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.0933333333333333,
|
| 1654 |
+
"grad_norm": 3.546875,
|
| 1655 |
+
"learning_rate": 8.978199092926726e-06,
|
| 1656 |
+
"loss": 0.007541795819997787,
|
| 1657 |
+
"step": 2050,
|
| 1658 |
+
"token_acc": 0.9976133651551312
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.0986666666666667,
|
| 1662 |
+
"grad_norm": 1.609375,
|
| 1663 |
+
"learning_rate": 8.892311712427924e-06,
|
| 1664 |
+
"loss": 0.004805643856525421,
|
| 1665 |
+
"step": 2060,
|
| 1666 |
+
"token_acc": 0.9985594237695078
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.104,
|
| 1670 |
+
"grad_norm": 1.6875,
|
| 1671 |
+
"learning_rate": 8.806506979102834e-06,
|
| 1672 |
+
"loss": 0.0038967303931713103,
|
| 1673 |
+
"step": 2070,
|
| 1674 |
+
"token_acc": 0.9983177120884402
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.1093333333333333,
|
| 1678 |
+
"grad_norm": 2.40625,
|
| 1679 |
+
"learning_rate": 8.720791295040175e-06,
|
| 1680 |
+
"loss": 0.006791643053293228,
|
| 1681 |
+
"step": 2080,
|
| 1682 |
+
"token_acc": 0.9973627427475426
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.1146666666666667,
|
| 1686 |
+
"grad_norm": 0.03466796875,
|
| 1687 |
+
"learning_rate": 8.63517105568451e-06,
|
| 1688 |
+
"loss": 0.010593726485967635,
|
| 1689 |
+
"step": 2090,
|
| 1690 |
+
"token_acc": 0.9963968292097045
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.12,
|
| 1694 |
+
"grad_norm": 0.61328125,
|
| 1695 |
+
"learning_rate": 8.549652649359053e-06,
|
| 1696 |
+
"loss": 0.008941850066184998,
|
| 1697 |
+
"step": 2100,
|
| 1698 |
+
"token_acc": 0.9973551334455398
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.1253333333333333,
|
| 1702 |
+
"grad_norm": 0.52734375,
|
| 1703 |
+
"learning_rate": 8.46424245678901e-06,
|
| 1704 |
+
"loss": 0.002381850406527519,
|
| 1705 |
+
"step": 2110,
|
| 1706 |
+
"token_acc": 0.9997611084567606
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.1306666666666667,
|
| 1710 |
+
"grad_norm": 1.078125,
|
| 1711 |
+
"learning_rate": 8.37894685062551e-06,
|
| 1712 |
+
"loss": 0.004864877089858055,
|
| 1713 |
+
"step": 2120,
|
| 1714 |
+
"token_acc": 0.9978380975258228
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.1360000000000001,
|
| 1718 |
+
"grad_norm": 1.5859375,
|
| 1719 |
+
"learning_rate": 8.293772194970137e-06,
|
| 1720 |
+
"loss": 0.006302349269390106,
|
| 1721 |
+
"step": 2130,
|
| 1722 |
+
"token_acc": 0.9971167707832773
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.1413333333333333,
|
| 1726 |
+
"grad_norm": 1.03125,
|
| 1727 |
+
"learning_rate": 8.208724844900078e-06,
|
| 1728 |
+
"loss": 0.006415116786956787,
|
| 1729 |
+
"step": 2140,
|
| 1730 |
+
"token_acc": 0.9975996159385502
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.1466666666666667,
|
| 1734 |
+
"grad_norm": 0.333984375,
|
| 1735 |
+
"learning_rate": 8.123811145993943e-06,
|
| 1736 |
+
"loss": 0.004534322023391724,
|
| 1737 |
+
"step": 2150,
|
| 1738 |
+
"token_acc": 0.9985569985569985
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.152,
|
| 1742 |
+
"grad_norm": 0.81640625,
|
| 1743 |
+
"learning_rate": 8.039037433858334e-06,
|
| 1744 |
+
"loss": 0.0036215364933013918,
|
| 1745 |
+
"step": 2160,
|
| 1746 |
+
"token_acc": 0.9985611510791367
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.1573333333333333,
|
| 1750 |
+
"grad_norm": 2.53125,
|
| 1751 |
+
"learning_rate": 7.95441003365512e-06,
|
| 1752 |
+
"loss": 0.0054457664489746095,
|
| 1753 |
+
"step": 2170,
|
| 1754 |
+
"token_acc": 0.9983189241114313
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.1626666666666667,
|
| 1758 |
+
"grad_norm": 1.21875,
|
| 1759 |
+
"learning_rate": 7.869935259629486e-06,
|
| 1760 |
+
"loss": 0.002699613384902477,
|
| 1761 |
+
"step": 2180,
|
| 1762 |
+
"token_acc": 0.9987931450639633
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.168,
|
| 1766 |
+
"grad_norm": 0.427734375,
|
| 1767 |
+
"learning_rate": 7.785619414638836e-06,
|
| 1768 |
+
"loss": 0.0033791519701480864,
|
| 1769 |
+
"step": 2190,
|
| 1770 |
+
"token_acc": 0.9985538684020245
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.1733333333333333,
|
| 1774 |
+
"grad_norm": 0.384765625,
|
| 1775 |
+
"learning_rate": 7.701468789682511e-06,
|
| 1776 |
+
"loss": 0.006151729822158813,
|
| 1777 |
+
"step": 2200,
|
| 1778 |
+
"token_acc": 0.9975874547647768
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.1786666666666668,
|
| 1782 |
+
"grad_norm": 1.34375,
|
| 1783 |
+
"learning_rate": 7.6174896634324135e-06,
|
| 1784 |
+
"loss": 0.0063545525074005125,
|
| 1785 |
+
"step": 2210,
|
| 1786 |
+
"token_acc": 0.9973690504663956
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.184,
|
| 1790 |
+
"grad_norm": 2.53125,
|
| 1791 |
+
"learning_rate": 7.533688301764511e-06,
|
| 1792 |
+
"loss": 0.007921293377876282,
|
| 1793 |
+
"step": 2220,
|
| 1794 |
+
"token_acc": 0.9976070830342187
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.1893333333333334,
|
| 1798 |
+
"grad_norm": 0.01483154296875,
|
| 1799 |
+
"learning_rate": 7.450070957291366e-06,
|
| 1800 |
+
"loss": 0.002941630594432354,
|
| 1801 |
+
"step": 2230,
|
| 1802 |
+
"token_acc": 0.9990403071017274
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.1946666666666665,
|
| 1806 |
+
"grad_norm": 1.6796875,
|
| 1807 |
+
"learning_rate": 7.3666438688955885e-06,
|
| 1808 |
+
"loss": 0.003889225795865059,
|
| 1809 |
+
"step": 2240,
|
| 1810 |
+
"token_acc": 0.9983265598852499
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.2,
|
| 1814 |
+
"grad_norm": 2.4375,
|
| 1815 |
+
"learning_rate": 7.283413261264341e-06,
|
| 1816 |
+
"loss": 0.009336037933826447,
|
| 1817 |
+
"step": 2250,
|
| 1818 |
+
"token_acc": 0.9964037401102853
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.2053333333333334,
|
| 1822 |
+
"grad_norm": 0.1552734375,
|
| 1823 |
+
"learning_rate": 7.200385344424908e-06,
|
| 1824 |
+
"loss": 0.0049955971539020535,
|
| 1825 |
+
"step": 2260,
|
| 1826 |
+
"token_acc": 0.9978271366489618
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.2106666666666666,
|
| 1830 |
+
"grad_norm": 0.96875,
|
| 1831 |
+
"learning_rate": 7.117566313281346e-06,
|
| 1832 |
+
"loss": 0.006457388401031494,
|
| 1833 |
+
"step": 2270,
|
| 1834 |
+
"token_acc": 0.9973532242540905
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.216,
|
| 1838 |
+
"grad_norm": 0.5078125,
|
| 1839 |
+
"learning_rate": 7.03496234715227e-06,
|
| 1840 |
+
"loss": 0.00416189506649971,
|
| 1841 |
+
"step": 2280,
|
| 1842 |
+
"token_acc": 0.9980755352417608
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.2213333333333334,
|
| 1846 |
+
"grad_norm": 0.197265625,
|
| 1847 |
+
"learning_rate": 6.952579609309793e-06,
|
| 1848 |
+
"loss": 0.002200193703174591,
|
| 1849 |
+
"step": 2290,
|
| 1850 |
+
"token_acc": 0.9990400767938565
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.2266666666666666,
|
| 1854 |
+
"grad_norm": 0.1416015625,
|
| 1855 |
+
"learning_rate": 6.870424246519682e-06,
|
| 1856 |
+
"loss": 0.002812638506293297,
|
| 1857 |
+
"step": 2300,
|
| 1858 |
+
"token_acc": 0.9992804029743344
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.232,
|
| 1862 |
+
"grad_norm": 0.1015625,
|
| 1863 |
+
"learning_rate": 6.788502388582727e-06,
|
| 1864 |
+
"loss": 0.004387106746435165,
|
| 1865 |
+
"step": 2310,
|
| 1866 |
+
"token_acc": 0.9983169031017072
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.2373333333333334,
|
| 1870 |
+
"grad_norm": 2.34375,
|
| 1871 |
+
"learning_rate": 6.706820147877388e-06,
|
| 1872 |
+
"loss": 0.0042403869330883024,
|
| 1873 |
+
"step": 2320,
|
| 1874 |
+
"token_acc": 0.9983156881616939
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.2426666666666666,
|
| 1878 |
+
"grad_norm": 1.2734375,
|
| 1879 |
+
"learning_rate": 6.625383618903718e-06,
|
| 1880 |
+
"loss": 0.003984439373016358,
|
| 1881 |
+
"step": 2330,
|
| 1882 |
+
"token_acc": 0.9983104030895487
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.248,
|
| 1886 |
+
"grad_norm": 4.40625,
|
| 1887 |
+
"learning_rate": 6.5441988778286625e-06,
|
| 1888 |
+
"loss": 0.011166787147521973,
|
| 1889 |
+
"step": 2340,
|
| 1890 |
+
"token_acc": 0.9971139971139971
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.2533333333333334,
|
| 1894 |
+
"grad_norm": 0.88671875,
|
| 1895 |
+
"learning_rate": 6.463271982032695e-06,
|
| 1896 |
+
"loss": 0.005804238468408584,
|
| 1897 |
+
"step": 2350,
|
| 1898 |
+
"token_acc": 0.9983148772267694
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.2586666666666666,
|
| 1902 |
+
"grad_norm": 0.64453125,
|
| 1903 |
+
"learning_rate": 6.382608969657847e-06,
|
| 1904 |
+
"loss": 0.009684956073760987,
|
| 1905 |
+
"step": 2360,
|
| 1906 |
+
"token_acc": 0.9968929254302104
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.264,
|
| 1910 |
+
"grad_norm": 2.75,
|
| 1911 |
+
"learning_rate": 6.302215859157208e-06,
|
| 1912 |
+
"loss": 0.005170706287026405,
|
| 1913 |
+
"step": 2370,
|
| 1914 |
+
"token_acc": 0.9980727535533607
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.2693333333333334,
|
| 1918 |
+
"grad_norm": 0.65625,
|
| 1919 |
+
"learning_rate": 6.22209864884587e-06,
|
| 1920 |
+
"loss": 0.005149983614683151,
|
| 1921 |
+
"step": 2380,
|
| 1922 |
+
"token_acc": 0.9976065102920058
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.2746666666666666,
|
| 1926 |
+
"grad_norm": 1.0546875,
|
| 1927 |
+
"learning_rate": 6.142263316453376e-06,
|
| 1928 |
+
"loss": 0.004198073223233223,
|
| 1929 |
+
"step": 2390,
|
| 1930 |
+
"token_acc": 0.9985583853916387
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.28,
|
| 1934 |
+
"grad_norm": 2.734375,
|
| 1935 |
+
"learning_rate": 6.062715818677696e-06,
|
| 1936 |
+
"loss": 0.00775875523686409,
|
| 1937 |
+
"step": 2400,
|
| 1938 |
+
"token_acc": 0.9971098265895953
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.2853333333333334,
|
| 1942 |
+
"grad_norm": 0.83203125,
|
| 1943 |
+
"learning_rate": 5.983462090740811e-06,
|
| 1944 |
+
"loss": 0.0033920254558324815,
|
| 1945 |
+
"step": 2410,
|
| 1946 |
+
"token_acc": 0.999279711884754
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.2906666666666666,
|
| 1950 |
+
"grad_norm": 0.7421875,
|
| 1951 |
+
"learning_rate": 5.904508045945854e-06,
|
| 1952 |
+
"loss": 0.005340686440467835,
|
| 1953 |
+
"step": 2420,
|
| 1954 |
+
"token_acc": 0.9971284996410624
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.296,
|
| 1958 |
+
"grad_norm": 1.0546875,
|
| 1959 |
+
"learning_rate": 5.825859575235904e-06,
|
| 1960 |
+
"loss": 0.004911442846059799,
|
| 1961 |
+
"step": 2430,
|
| 1962 |
+
"token_acc": 0.9983112183353438
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.3013333333333335,
|
| 1966 |
+
"grad_norm": 1.046875,
|
| 1967 |
+
"learning_rate": 5.747522546754456e-06,
|
| 1968 |
+
"loss": 0.004845966398715973,
|
| 1969 |
+
"step": 2440,
|
| 1970 |
+
"token_acc": 0.9973519499277804
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.3066666666666666,
|
| 1974 |
+
"grad_norm": 2.0,
|
| 1975 |
+
"learning_rate": 5.669502805407592e-06,
|
| 1976 |
+
"loss": 0.004123274236917496,
|
| 1977 |
+
"step": 2450,
|
| 1978 |
+
"token_acc": 0.9985576923076923
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.312,
|
| 1982 |
+
"grad_norm": 1.6484375,
|
| 1983 |
+
"learning_rate": 5.591806172427858e-06,
|
| 1984 |
+
"loss": 0.0051461681723594666,
|
| 1985 |
+
"step": 2460,
|
| 1986 |
+
"token_acc": 0.9985652797704447
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.3173333333333335,
|
| 1990 |
+
"grad_norm": 0.421875,
|
| 1991 |
+
"learning_rate": 5.514438444939947e-06,
|
| 1992 |
+
"loss": 0.004213321581482887,
|
| 1993 |
+
"step": 2470,
|
| 1994 |
+
"token_acc": 0.9985524728588661
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.3226666666666667,
|
| 1998 |
+
"grad_norm": 0.5625,
|
| 1999 |
+
"learning_rate": 5.437405395528148e-06,
|
| 2000 |
+
"loss": 0.002550625242292881,
|
| 2001 |
+
"step": 2480,
|
| 2002 |
+
"token_acc": 0.9990379990379991
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.328,
|
| 2006 |
+
"grad_norm": 1.9921875,
|
| 2007 |
+
"learning_rate": 5.36071277180567e-06,
|
| 2008 |
+
"loss": 0.0048110231757164,
|
| 2009 |
+
"step": 2490,
|
| 2010 |
+
"token_acc": 0.9975973089860644
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.3333333333333333,
|
| 2014 |
+
"grad_norm": 1.59375,
|
| 2015 |
+
"learning_rate": 5.284366295985741e-06,
|
| 2016 |
+
"loss": 0.0039034508168697356,
|
| 2017 |
+
"step": 2500,
|
| 2018 |
+
"token_acc": 0.9985604606525912
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.3386666666666667,
|
| 2022 |
+
"grad_norm": 0.5703125,
|
| 2023 |
+
"learning_rate": 5.208371664454737e-06,
|
| 2024 |
+
"loss": 0.006703800708055496,
|
| 2025 |
+
"step": 2510,
|
| 2026 |
+
"token_acc": 0.9980833732630571
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.3439999999999999,
|
| 2030 |
+
"grad_norm": 0.1630859375,
|
| 2031 |
+
"learning_rate": 5.132734547347088e-06,
|
| 2032 |
+
"loss": 0.004545541480183601,
|
| 2033 |
+
"step": 2520,
|
| 2034 |
+
"token_acc": 0.998081074598225
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.3493333333333333,
|
| 2038 |
+
"grad_norm": 2.265625,
|
| 2039 |
+
"learning_rate": 5.057460588122276e-06,
|
| 2040 |
+
"loss": 0.006165074557065964,
|
| 2041 |
+
"step": 2530,
|
| 2042 |
+
"token_acc": 0.997837578087458
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 1.3546666666666667,
|
| 2046 |
+
"grad_norm": 0.41015625,
|
| 2047 |
+
"learning_rate": 4.98255540314372e-06,
|
| 2048 |
+
"loss": 0.0034597426652908324,
|
| 2049 |
+
"step": 2540,
|
| 2050 |
+
"token_acc": 0.9987966305655837
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.3599999999999999,
|
| 2054 |
+
"grad_norm": 4.46875,
|
| 2055 |
+
"learning_rate": 4.908024581259744e-06,
|
| 2056 |
+
"loss": 0.008379907160997391,
|
| 2057 |
+
"step": 2550,
|
| 2058 |
+
"token_acc": 0.997597886139803
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.3653333333333333,
|
| 2062 |
+
"grad_norm": 2.265625,
|
| 2063 |
+
"learning_rate": 4.833873683386596e-06,
|
| 2064 |
+
"loss": 0.004962638020515442,
|
| 2065 |
+
"step": 2560,
|
| 2066 |
+
"token_acc": 0.9980759980759981
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.3706666666666667,
|
| 2070 |
+
"grad_norm": 1.6875,
|
| 2071 |
+
"learning_rate": 4.760108242093493e-06,
|
| 2072 |
+
"loss": 0.004094836115837097,
|
| 2073 |
+
"step": 2570,
|
| 2074 |
+
"token_acc": 0.9988023952095808
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.376,
|
| 2078 |
+
"grad_norm": 0.201171875,
|
| 2079 |
+
"learning_rate": 4.686733761189872e-06,
|
| 2080 |
+
"loss": 0.003802131861448288,
|
| 2081 |
+
"step": 2580,
|
| 2082 |
+
"token_acc": 0.9985524728588661
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.3813333333333333,
|
| 2086 |
+
"grad_norm": 0.30078125,
|
| 2087 |
+
"learning_rate": 4.613755715314701e-06,
|
| 2088 |
+
"loss": 0.004577885195612907,
|
| 2089 |
+
"step": 2590,
|
| 2090 |
+
"token_acc": 0.9983213429256594
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.3866666666666667,
|
| 2094 |
+
"grad_norm": 0.71484375,
|
| 2095 |
+
"learning_rate": 4.541179549528032e-06,
|
| 2096 |
+
"loss": 0.006140761077404022,
|
| 2097 |
+
"step": 2600,
|
| 2098 |
+
"token_acc": 0.9978417266187051
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 1.392,
|
| 2102 |
+
"grad_norm": 1.15625,
|
| 2103 |
+
"learning_rate": 4.469010678904694e-06,
|
| 2104 |
+
"loss": 0.005562315881252289,
|
| 2105 |
+
"step": 2610,
|
| 2106 |
+
"token_acc": 0.9968629343629344
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 1.3973333333333333,
|
| 2110 |
+
"grad_norm": 0.08203125,
|
| 2111 |
+
"learning_rate": 4.397254488130313e-06,
|
| 2112 |
+
"loss": 0.006752446293830872,
|
| 2113 |
+
"step": 2620,
|
| 2114 |
+
"token_acc": 0.9976036424634556
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.4026666666666667,
|
| 2118 |
+
"grad_norm": 0.48828125,
|
| 2119 |
+
"learning_rate": 4.3259163310995e-06,
|
| 2120 |
+
"loss": 0.004103198274970054,
|
| 2121 |
+
"step": 2630,
|
| 2122 |
+
"token_acc": 0.9985514244326412
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.408,
|
| 2126 |
+
"grad_norm": 0.61328125,
|
| 2127 |
+
"learning_rate": 4.255001530516425e-06,
|
| 2128 |
+
"loss": 0.003177974745631218,
|
| 2129 |
+
"step": 2640,
|
| 2130 |
+
"token_acc": 0.9988035415171094
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.4133333333333333,
|
| 2134 |
+
"grad_norm": 0.3671875,
|
| 2135 |
+
"learning_rate": 4.184515377497643e-06,
|
| 2136 |
+
"loss": 0.0040819644927978516,
|
| 2137 |
+
"step": 2650,
|
| 2138 |
+
"token_acc": 0.9988012467034284
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.4186666666666667,
|
| 2142 |
+
"grad_norm": 1.15625,
|
| 2143 |
+
"learning_rate": 4.11446313117733e-06,
|
| 2144 |
+
"loss": 0.006515056639909744,
|
| 2145 |
+
"step": 2660,
|
| 2146 |
+
"token_acc": 0.9985507246376811
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.424,
|
| 2150 |
+
"grad_norm": 2.296875,
|
| 2151 |
+
"learning_rate": 4.044850018314896e-06,
|
| 2152 |
+
"loss": 0.008263874053955077,
|
| 2153 |
+
"step": 2670,
|
| 2154 |
+
"token_acc": 0.9973696795791487
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.4293333333333333,
|
| 2158 |
+
"grad_norm": 0.228515625,
|
| 2159 |
+
"learning_rate": 3.975681232904971e-06,
|
| 2160 |
+
"loss": 0.004042870551347733,
|
| 2161 |
+
"step": 2680,
|
| 2162 |
+
"token_acc": 0.9985587316838818
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 1.4346666666666668,
|
| 2166 |
+
"grad_norm": 1.015625,
|
| 2167 |
+
"learning_rate": 3.906961935789914e-06,
|
| 2168 |
+
"loss": 0.0033185966312885284,
|
| 2169 |
+
"step": 2690,
|
| 2170 |
+
"token_acc": 0.9992764109985528
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 1.44,
|
| 2174 |
+
"grad_norm": 0.37109375,
|
| 2175 |
+
"learning_rate": 3.838697254274708e-06,
|
| 2176 |
+
"loss": 0.005210072547197342,
|
| 2177 |
+
"step": 2700,
|
| 2178 |
+
"token_acc": 0.9978297564504461
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 1.4453333333333334,
|
| 2182 |
+
"grad_norm": 0.8984375,
|
| 2183 |
+
"learning_rate": 3.7708922817444382e-06,
|
| 2184 |
+
"loss": 0.004422234743833542,
|
| 2185 |
+
"step": 2710,
|
| 2186 |
+
"token_acc": 0.9980764606876653
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.4506666666666668,
|
| 2190 |
+
"grad_norm": 1.3515625,
|
| 2191 |
+
"learning_rate": 3.7035520772842216e-06,
|
| 2192 |
+
"loss": 0.003228164464235306,
|
| 2193 |
+
"step": 2720,
|
| 2194 |
+
"token_acc": 0.9987974987974988
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.456,
|
| 2198 |
+
"grad_norm": 0.85546875,
|
| 2199 |
+
"learning_rate": 3.636681665301779e-06,
|
| 2200 |
+
"loss": 0.00462164580821991,
|
| 2201 |
+
"step": 2730,
|
| 2202 |
+
"token_acc": 0.9980648282535075
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.4613333333333334,
|
| 2206 |
+
"grad_norm": 1.4453125,
|
| 2207 |
+
"learning_rate": 3.5702860351525216e-06,
|
| 2208 |
+
"loss": 0.004252329096198082,
|
| 2209 |
+
"step": 2740,
|
| 2210 |
+
"token_acc": 0.9988026819923371
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 1.4666666666666668,
|
| 2214 |
+
"grad_norm": 2.25,
|
| 2215 |
+
"learning_rate": 3.504370140767297e-06,
|
| 2216 |
+
"loss": 0.0034693241119384765,
|
| 2217 |
+
"step": 2750,
|
| 2218 |
+
"token_acc": 0.9987896393125151
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 1.472,
|
| 2222 |
+
"grad_norm": 1.3671875,
|
| 2223 |
+
"learning_rate": 3.438938900282768e-06,
|
| 2224 |
+
"loss": 0.005826358124613762,
|
| 2225 |
+
"step": 2760,
|
| 2226 |
+
"token_acc": 0.9983144714664098
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.4773333333333334,
|
| 2230 |
+
"grad_norm": 0.1552734375,
|
| 2231 |
+
"learning_rate": 3.3739971956744444e-06,
|
| 2232 |
+
"loss": 0.006960628926753998,
|
| 2233 |
+
"step": 2770,
|
| 2234 |
+
"token_acc": 0.9975944190522011
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 1.4826666666666668,
|
| 2238 |
+
"grad_norm": 0.5625,
|
| 2239 |
+
"learning_rate": 3.3095498723924514e-06,
|
| 2240 |
+
"loss": 0.0032369595021009443,
|
| 2241 |
+
"step": 2780,
|
| 2242 |
+
"token_acc": 0.9985552612569227
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.488,
|
| 2246 |
+
"grad_norm": 2.0,
|
| 2247 |
+
"learning_rate": 3.245601738999964e-06,
|
| 2248 |
+
"loss": 0.00596727654337883,
|
| 2249 |
+
"step": 2790,
|
| 2250 |
+
"token_acc": 0.9980787704130644
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.4933333333333334,
|
| 2254 |
+
"grad_norm": 2.296875,
|
| 2255 |
+
"learning_rate": 3.182157566814471e-06,
|
| 2256 |
+
"loss": 0.0037505336105823515,
|
| 2257 |
+
"step": 2800,
|
| 2258 |
+
"token_acc": 0.9990407673860912
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.4986666666666666,
|
| 2262 |
+
"grad_norm": 0.32421875,
|
| 2263 |
+
"learning_rate": 3.1192220895517434e-06,
|
| 2264 |
+
"loss": 0.005509653314948082,
|
| 2265 |
+
"step": 2810,
|
| 2266 |
+
"token_acc": 0.9983095870562666
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.504,
|
| 2270 |
+
"grad_norm": 3.09375,
|
| 2271 |
+
"learning_rate": 3.056800002972655e-06,
|
| 2272 |
+
"loss": 0.005837666988372803,
|
| 2273 |
+
"step": 2820,
|
| 2274 |
+
"token_acc": 0.9978323699421965
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.5093333333333332,
|
| 2278 |
+
"grad_norm": 2.78125,
|
| 2279 |
+
"learning_rate": 2.994895964532818e-06,
|
| 2280 |
+
"loss": 0.005459493398666382,
|
| 2281 |
+
"step": 2830,
|
| 2282 |
+
"token_acc": 0.9983253588516746
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 1.5146666666666668,
|
| 2286 |
+
"grad_norm": 1.3125,
|
| 2287 |
+
"learning_rate": 2.9335145930350852e-06,
|
| 2288 |
+
"loss": 0.001859320141375065,
|
| 2289 |
+
"step": 2840,
|
| 2290 |
+
"token_acc": 0.9990300678952473
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 1.52,
|
| 2294 |
+
"grad_norm": 0.2216796875,
|
| 2295 |
+
"learning_rate": 2.8726604682849192e-06,
|
| 2296 |
+
"loss": 0.003423035144805908,
|
| 2297 |
+
"step": 2850,
|
| 2298 |
+
"token_acc": 0.9978380975258228
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.5253333333333332,
|
| 2302 |
+
"grad_norm": 2.5,
|
| 2303 |
+
"learning_rate": 2.8123381307486875e-06,
|
| 2304 |
+
"loss": 0.007793290168046951,
|
| 2305 |
+
"step": 2860,
|
| 2306 |
+
"token_acc": 0.9968824940047961
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.5306666666666666,
|
| 2310 |
+
"grad_norm": 1.09375,
|
| 2311 |
+
"learning_rate": 2.752552081214899e-06,
|
| 2312 |
+
"loss": 0.0038124389946460726,
|
| 2313 |
+
"step": 2870,
|
| 2314 |
+
"token_acc": 0.9985601151907847
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.536,
|
| 2318 |
+
"grad_norm": 1.65625,
|
| 2319 |
+
"learning_rate": 2.693306780458369e-06,
|
| 2320 |
+
"loss": 0.0020717747509479524,
|
| 2321 |
+
"step": 2880,
|
| 2322 |
+
"token_acc": 0.9987951807228915
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 1.5413333333333332,
|
| 2326 |
+
"grad_norm": 0.1474609375,
|
| 2327 |
+
"learning_rate": 2.6346066489074083e-06,
|
| 2328 |
+
"loss": 0.0018467091023921967,
|
| 2329 |
+
"step": 2890,
|
| 2330 |
+
"token_acc": 0.9995200383969283
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 1.5466666666666666,
|
| 2334 |
+
"grad_norm": 0.279296875,
|
| 2335 |
+
"learning_rate": 2.576456066313989e-06,
|
| 2336 |
+
"loss": 0.005197260528802872,
|
| 2337 |
+
"step": 2900,
|
| 2338 |
+
"token_acc": 0.9973715651135006
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.552,
|
| 2342 |
+
"grad_norm": 0.451171875,
|
| 2343 |
+
"learning_rate": 2.518859371426985e-06,
|
| 2344 |
+
"loss": 0.0031303077936172484,
|
| 2345 |
+
"step": 2910,
|
| 2346 |
+
"token_acc": 0.9988012467034284
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 1.5573333333333332,
|
| 2350 |
+
"grad_norm": 0.88671875,
|
| 2351 |
+
"learning_rate": 2.4618208616684213e-06,
|
| 2352 |
+
"loss": 0.0031688179820775985,
|
| 2353 |
+
"step": 2920,
|
| 2354 |
+
"token_acc": 0.9990426041168023
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.5626666666666666,
|
| 2358 |
+
"grad_norm": 1.1328125,
|
| 2359 |
+
"learning_rate": 2.405344792812847e-06,
|
| 2360 |
+
"loss": 0.004901519417762757,
|
| 2361 |
+
"step": 2930,
|
| 2362 |
+
"token_acc": 0.9985535197685632
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.568,
|
| 2366 |
+
"grad_norm": 1.7109375,
|
| 2367 |
+
"learning_rate": 2.3494353786698e-06,
|
| 2368 |
+
"loss": 0.003883931040763855,
|
| 2369 |
+
"step": 2940,
|
| 2370 |
+
"token_acc": 0.9985576923076923
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.5733333333333333,
|
| 2374 |
+
"grad_norm": 0.78515625,
|
| 2375 |
+
"learning_rate": 2.294096790769411e-06,
|
| 2376 |
+
"loss": 0.002903797477483749,
|
| 2377 |
+
"step": 2950,
|
| 2378 |
+
"token_acc": 0.9988000959923207
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.5786666666666667,
|
| 2382 |
+
"grad_norm": 0.72265625,
|
| 2383 |
+
"learning_rate": 2.239333158051147e-06,
|
| 2384 |
+
"loss": 0.0052621312439441684,
|
| 2385 |
+
"step": 2960,
|
| 2386 |
+
"token_acc": 0.9980796927508402
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 1.584,
|
| 2390 |
+
"grad_norm": 2.0625,
|
| 2391 |
+
"learning_rate": 2.185148566555738e-06,
|
| 2392 |
+
"loss": 0.0045540638267993925,
|
| 2393 |
+
"step": 2970,
|
| 2394 |
+
"token_acc": 0.9983173076923076
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 1.5893333333333333,
|
| 2398 |
+
"grad_norm": 2.671875,
|
| 2399 |
+
"learning_rate": 2.131547059120329e-06,
|
| 2400 |
+
"loss": 0.0034696806222200395,
|
| 2401 |
+
"step": 2980,
|
| 2402 |
+
"token_acc": 0.9980680994928761
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.5946666666666667,
|
| 2406 |
+
"grad_norm": 0.375,
|
| 2407 |
+
"learning_rate": 2.0785326350768085e-06,
|
| 2408 |
+
"loss": 0.005480880290269852,
|
| 2409 |
+
"step": 2990,
|
| 2410 |
+
"token_acc": 0.9980847498204453
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.6,
|
| 2414 |
+
"grad_norm": 0.1865234375,
|
| 2415 |
+
"learning_rate": 2.0261092499534287e-06,
|
| 2416 |
+
"loss": 0.0024819549173116682,
|
| 2417 |
+
"step": 3000,
|
| 2418 |
+
"token_acc": 0.9992753623188406
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.6053333333333333,
|
| 2422 |
+
"grad_norm": 0.126953125,
|
| 2423 |
+
"learning_rate": 1.974280815179659e-06,
|
| 2424 |
+
"loss": 0.005214349180459976,
|
| 2425 |
+
"step": 3010,
|
| 2426 |
+
"token_acc": 0.9987992315081652
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 1.6106666666666667,
|
| 2430 |
+
"grad_norm": 2.03125,
|
| 2431 |
+
"learning_rate": 1.9230511977943646e-06,
|
| 2432 |
+
"loss": 0.0028021618723869323,
|
| 2433 |
+
"step": 3020,
|
| 2434 |
+
"token_acc": 0.9987974987974988
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.616,
|
| 2438 |
+
"grad_norm": 0.8828125,
|
| 2439 |
+
"learning_rate": 1.8724242201572585e-06,
|
| 2440 |
+
"loss": 0.002719448506832123,
|
| 2441 |
+
"step": 3030,
|
| 2442 |
+
"token_acc": 0.9985563041385948
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 1.6213333333333333,
|
| 2446 |
+
"grad_norm": 1.3671875,
|
| 2447 |
+
"learning_rate": 1.822403659663715e-06,
|
| 2448 |
+
"loss": 0.001963297836482525,
|
| 2449 |
+
"step": 3040,
|
| 2450 |
+
"token_acc": 0.9995184204189742
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 1.6266666666666667,
|
| 2454 |
+
"grad_norm": 1.1171875,
|
| 2455 |
+
"learning_rate": 1.7729932484629298e-06,
|
| 2456 |
+
"loss": 0.007073329389095306,
|
| 2457 |
+
"step": 3050,
|
| 2458 |
+
"token_acc": 0.9973513123043583
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 1.6320000000000001,
|
| 2462 |
+
"grad_norm": 2.765625,
|
| 2463 |
+
"learning_rate": 1.724196673179458e-06,
|
| 2464 |
+
"loss": 0.006209851428866387,
|
| 2465 |
+
"step": 3060,
|
| 2466 |
+
"token_acc": 0.9978391356542617
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.6373333333333333,
|
| 2470 |
+
"grad_norm": 0.96875,
|
| 2471 |
+
"learning_rate": 1.6760175746381402e-06,
|
| 2472 |
+
"loss": 0.0023255087435245514,
|
| 2473 |
+
"step": 3070,
|
| 2474 |
+
"token_acc": 0.9995188838104402
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.6426666666666667,
|
| 2478 |
+
"grad_norm": 0.5234375,
|
| 2479 |
+
"learning_rate": 1.6284595475924547e-06,
|
| 2480 |
+
"loss": 0.005354274809360504,
|
| 2481 |
+
"step": 3080,
|
| 2482 |
+
"token_acc": 0.9985576923076923
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 1.6480000000000001,
|
| 2486 |
+
"grad_norm": 0.162109375,
|
| 2487 |
+
"learning_rate": 1.5815261404563066e-06,
|
| 2488 |
+
"loss": 0.00551719069480896,
|
| 2489 |
+
"step": 3090,
|
| 2490 |
+
"token_acc": 0.998088867654085
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 1.6533333333333333,
|
| 2494 |
+
"grad_norm": 3.015625,
|
| 2495 |
+
"learning_rate": 1.5352208550392745e-06,
|
| 2496 |
+
"loss": 0.003801211714744568,
|
| 2497 |
+
"step": 3100,
|
| 2498 |
+
"token_acc": 0.9980764606876653
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 1.6586666666666665,
|
| 2502 |
+
"grad_norm": 0.40234375,
|
| 2503 |
+
"learning_rate": 1.489547146285325e-06,
|
| 2504 |
+
"loss": 0.0029349761083722115,
|
| 2505 |
+
"step": 3110,
|
| 2506 |
+
"token_acc": 0.9985535197685632
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 1.6640000000000001,
|
| 2510 |
+
"grad_norm": 2.421875,
|
| 2511 |
+
"learning_rate": 1.4445084220150341e-06,
|
| 2512 |
+
"loss": 0.005994468182325363,
|
| 2513 |
+
"step": 3120,
|
| 2514 |
+
"token_acc": 0.9975816203143894
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 1.6693333333333333,
|
| 2518 |
+
"grad_norm": 3.421875,
|
| 2519 |
+
"learning_rate": 1.4001080426713332e-06,
|
| 2520 |
+
"loss": 0.004013296961784363,
|
| 2521 |
+
"step": 3130,
|
| 2522 |
+
"token_acc": 0.9985608059486687
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.6746666666666665,
|
| 2526 |
+
"grad_norm": 2.703125,
|
| 2527 |
+
"learning_rate": 1.3563493210687527e-06,
|
| 2528 |
+
"loss": 0.005458477884531021,
|
| 2529 |
+
"step": 3140,
|
| 2530 |
+
"token_acc": 0.9983201343892488
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.6800000000000002,
|
| 2534 |
+
"grad_norm": 0.88671875,
|
| 2535 |
+
"learning_rate": 1.3132355221462778e-06,
|
| 2536 |
+
"loss": 0.004872192442417145,
|
| 2537 |
+
"step": 3150,
|
| 2538 |
+
"token_acc": 0.9980755352417608
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 1.6853333333333333,
|
| 2542 |
+
"grad_norm": 3.234375,
|
| 2543 |
+
"learning_rate": 1.2707698627237152e-06,
|
| 2544 |
+
"loss": 0.0033847920596599577,
|
| 2545 |
+
"step": 3160,
|
| 2546 |
+
"token_acc": 0.998795761078998
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 1.6906666666666665,
|
| 2550 |
+
"grad_norm": 1.640625,
|
| 2551 |
+
"learning_rate": 1.2289555112617024e-06,
|
| 2552 |
+
"loss": 0.0032213889062404633,
|
| 2553 |
+
"step": 3170,
|
| 2554 |
+
"token_acc": 0.999277108433735
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 1.696,
|
| 2558 |
+
"grad_norm": 2.3125,
|
| 2559 |
+
"learning_rate": 1.1877955876252779e-06,
|
| 2560 |
+
"loss": 0.004248654469847679,
|
| 2561 |
+
"step": 3180,
|
| 2562 |
+
"token_acc": 0.9983156881616939
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 1.7013333333333334,
|
| 2566 |
+
"grad_norm": 1.390625,
|
| 2567 |
+
"learning_rate": 1.147293162851123e-06,
|
| 2568 |
+
"loss": 0.008833888173103332,
|
| 2569 |
+
"step": 3190,
|
| 2570 |
+
"token_acc": 0.996867469879518
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 1.7066666666666666,
|
| 2574 |
+
"grad_norm": 1.0390625,
|
| 2575 |
+
"learning_rate": 1.1074512589184105e-06,
|
| 2576 |
+
"loss": 0.004553095623850823,
|
| 2577 |
+
"step": 3200,
|
| 2578 |
+
"token_acc": 0.9978234582829504
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 1.712,
|
| 2582 |
+
"grad_norm": 1.546875,
|
| 2583 |
+
"learning_rate": 1.0682728485233306e-06,
|
| 2584 |
+
"loss": 0.0025400497019290925,
|
| 2585 |
+
"step": 3210,
|
| 2586 |
+
"token_acc": 0.9990396158463385
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.7173333333333334,
|
| 2590 |
+
"grad_norm": 0.435546875,
|
| 2591 |
+
"learning_rate": 1.0297608548573002e-06,
|
| 2592 |
+
"loss": 0.00552871935069561,
|
| 2593 |
+
"step": 3220,
|
| 2594 |
+
"token_acc": 0.9985510746196571
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 1.7226666666666666,
|
| 2598 |
+
"grad_norm": 1.609375,
|
| 2599 |
+
"learning_rate": 9.91918151388841e-07,
|
| 2600 |
+
"loss": 0.007216790318489074,
|
| 2601 |
+
"step": 3230,
|
| 2602 |
+
"token_acc": 0.997834977146981
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 1.728,
|
| 2606 |
+
"grad_norm": 1.7265625,
|
| 2607 |
+
"learning_rate": 9.547475616492008e-07,
|
| 2608 |
+
"loss": 0.003866948187351227,
|
| 2609 |
+
"step": 3240,
|
| 2610 |
+
"token_acc": 0.9987974987974988
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 1.7333333333333334,
|
| 2614 |
+
"grad_norm": 2.21875,
|
| 2615 |
+
"learning_rate": 9.182518590216616e-07,
|
| 2616 |
+
"loss": 0.004370670020580292,
|
| 2617 |
+
"step": 3250,
|
| 2618 |
+
"token_acc": 0.9988083889418494
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 1.7386666666666666,
|
| 2622 |
+
"grad_norm": 1.7890625,
|
| 2623 |
+
"learning_rate": 8.824337665346372e-07,
|
| 2624 |
+
"loss": 0.004827927052974701,
|
| 2625 |
+
"step": 3260,
|
| 2626 |
+
"token_acc": 0.9990400767938565
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 1.744,
|
| 2630 |
+
"grad_norm": 1.1875,
|
| 2631 |
+
"learning_rate": 8.472959566584804e-07,
|
| 2632 |
+
"loss": 0.004777887836098671,
|
| 2633 |
+
"step": 3270,
|
| 2634 |
+
"token_acc": 0.9980815347721822
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 1.7493333333333334,
|
| 2638 |
+
"grad_norm": 0.578125,
|
| 2639 |
+
"learning_rate": 8.128410511061002e-07,
|
| 2640 |
+
"loss": 0.0018575575202703476,
|
| 2641 |
+
"step": 3280,
|
| 2642 |
+
"token_acc": 0.9995191151719163
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.7546666666666666,
|
| 2646 |
+
"grad_norm": 0.296875,
|
| 2647 |
+
"learning_rate": 7.790716206373283e-07,
|
| 2648 |
+
"loss": 0.00343349426984787,
|
| 2649 |
+
"step": 3290,
|
| 2650 |
+
"token_acc": 0.9987977879297908
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 1.76,
|
| 2654 |
+
"grad_norm": 4.40625,
|
| 2655 |
+
"learning_rate": 7.459901848671347e-07,
|
| 2656 |
+
"loss": 0.004643554985523224,
|
| 2657 |
+
"step": 3300,
|
| 2658 |
+
"token_acc": 0.9980750721847931
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 1.7653333333333334,
|
| 2662 |
+
"grad_norm": 2.375,
|
| 2663 |
+
"learning_rate": 7.135992120776159e-07,
|
| 2664 |
+
"loss": 0.006345170736312866,
|
| 2665 |
+
"step": 3310,
|
| 2666 |
+
"token_acc": 0.9973614775725593
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 1.7706666666666666,
|
| 2670 |
+
"grad_norm": 0.1708984375,
|
| 2671 |
+
"learning_rate": 6.819011190338309e-07,
|
| 2672 |
+
"loss": 0.004708114266395569,
|
| 2673 |
+
"step": 3320,
|
| 2674 |
+
"token_acc": 0.9971243709561467
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 1.776,
|
| 2678 |
+
"grad_norm": 1.6328125,
|
| 2679 |
+
"learning_rate": 6.508982708034962e-07,
|
| 2680 |
+
"loss": 0.005871200561523437,
|
| 2681 |
+
"step": 3330,
|
| 2682 |
+
"token_acc": 0.9975868725868726
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 1.7813333333333334,
|
| 2686 |
+
"grad_norm": 0.068359375,
|
| 2687 |
+
"learning_rate": 6.205929805805e-07,
|
| 2688 |
+
"loss": 0.004391339421272278,
|
| 2689 |
+
"step": 3340,
|
| 2690 |
+
"token_acc": 0.9983169031017072
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 1.7866666666666666,
|
| 2694 |
+
"grad_norm": 1.90625,
|
| 2695 |
+
"learning_rate": 5.90987509512333e-07,
|
| 2696 |
+
"loss": 0.0028297567740082743,
|
| 2697 |
+
"step": 3350,
|
| 2698 |
+
"token_acc": 0.9987948903350204
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.792,
|
| 2702 |
+
"grad_norm": 1.5078125,
|
| 2703 |
+
"learning_rate": 5.620840665313554e-07,
|
| 2704 |
+
"loss": 0.0036468330770730974,
|
| 2705 |
+
"step": 3360,
|
| 2706 |
+
"token_acc": 0.9983116256632899
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 1.7973333333333334,
|
| 2710 |
+
"grad_norm": 1.2109375,
|
| 2711 |
+
"learning_rate": 5.338848081900062e-07,
|
| 2712 |
+
"loss": 0.005594483017921448,
|
| 2713 |
+
"step": 3370,
|
| 2714 |
+
"token_acc": 0.998563562365334
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 1.8026666666666666,
|
| 2718 |
+
"grad_norm": 0.1962890625,
|
| 2719 |
+
"learning_rate": 5.063918384998801e-07,
|
| 2720 |
+
"loss": 0.002733568102121353,
|
| 2721 |
+
"step": 3380,
|
| 2722 |
+
"token_acc": 0.9990377676208805
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 1.808,
|
| 2726 |
+
"grad_norm": 1.625,
|
| 2727 |
+
"learning_rate": 4.796072087747506e-07,
|
| 2728 |
+
"loss": 0.00883147269487381,
|
| 2729 |
+
"step": 3390,
|
| 2730 |
+
"token_acc": 0.9975862901279267
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 1.8133333333333335,
|
| 2734 |
+
"grad_norm": 0.166015625,
|
| 2735 |
+
"learning_rate": 4.5353291747751605e-07,
|
| 2736 |
+
"loss": 0.005349083244800568,
|
| 2737 |
+
"step": 3400,
|
| 2738 |
+
"token_acc": 0.9985621854780733
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 1.8186666666666667,
|
| 2742 |
+
"grad_norm": 1.859375,
|
| 2743 |
+
"learning_rate": 4.281709100710907e-07,
|
| 2744 |
+
"loss": 0.004085775464773178,
|
| 2745 |
+
"step": 3410,
|
| 2746 |
+
"token_acc": 0.9985601151907847
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 1.8239999999999998,
|
| 2750 |
+
"grad_norm": 1.625,
|
| 2751 |
+
"learning_rate": 4.035230788732447e-07,
|
| 2752 |
+
"loss": 0.003792187198996544,
|
| 2753 |
+
"step": 3420,
|
| 2754 |
+
"token_acc": 0.9987843423292001
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.8293333333333335,
|
| 2758 |
+
"grad_norm": 0.90234375,
|
| 2759 |
+
"learning_rate": 3.7959126291541635e-07,
|
| 2760 |
+
"loss": 0.004388328641653061,
|
| 2761 |
+
"step": 3430,
|
| 2762 |
+
"token_acc": 0.9980718245360328
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 1.8346666666666667,
|
| 2766 |
+
"grad_norm": 1.8359375,
|
| 2767 |
+
"learning_rate": 3.5637724780550386e-07,
|
| 2768 |
+
"loss": 0.004762783646583557,
|
| 2769 |
+
"step": 3440,
|
| 2770 |
+
"token_acc": 0.9980806142034548
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 1.8399999999999999,
|
| 2774 |
+
"grad_norm": 0.984375,
|
| 2775 |
+
"learning_rate": 3.338827655946253e-07,
|
| 2776 |
+
"loss": 0.004710916429758072,
|
| 2777 |
+
"step": 3450,
|
| 2778 |
+
"token_acc": 0.998324557204404
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 1.8453333333333335,
|
| 2782 |
+
"grad_norm": 0.1845703125,
|
| 2783 |
+
"learning_rate": 3.121094946478942e-07,
|
| 2784 |
+
"loss": 0.00310780368745327,
|
| 2785 |
+
"step": 3460,
|
| 2786 |
+
"token_acc": 0.9987977879297908
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 1.8506666666666667,
|
| 2790 |
+
"grad_norm": 0.05908203125,
|
| 2791 |
+
"learning_rate": 2.910590595191898e-07,
|
| 2792 |
+
"loss": 0.003157524764537811,
|
| 2793 |
+
"step": 3470,
|
| 2794 |
+
"token_acc": 0.9983185202978622
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 1.8559999999999999,
|
| 2798 |
+
"grad_norm": 0.474609375,
|
| 2799 |
+
"learning_rate": 2.707330308299516e-07,
|
| 2800 |
+
"loss": 0.00519019179046154,
|
| 2801 |
+
"step": 3480,
|
| 2802 |
+
"token_acc": 0.9985538684020245
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 1.8613333333333333,
|
| 2806 |
+
"grad_norm": 2.875,
|
| 2807 |
+
"learning_rate": 2.5113292515198007e-07,
|
| 2808 |
+
"loss": 0.004100662097334862,
|
| 2809 |
+
"step": 3490,
|
| 2810 |
+
"token_acc": 0.9987995198079231
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.8666666666666667,
|
| 2814 |
+
"grad_norm": 1.671875,
|
| 2815 |
+
"learning_rate": 2.3226020489429235e-07,
|
| 2816 |
+
"loss": 0.00834677368402481,
|
| 2817 |
+
"step": 3500,
|
| 2818 |
+
"token_acc": 0.9971333014811276
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 1.8719999999999999,
|
| 2822 |
+
"grad_norm": 0.59375,
|
| 2823 |
+
"learning_rate": 2.1411627819400317e-07,
|
| 2824 |
+
"loss": 0.005914821475744248,
|
| 2825 |
+
"step": 3510,
|
| 2826 |
+
"token_acc": 0.9978281853281853
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 1.8773333333333333,
|
| 2830 |
+
"grad_norm": 1.71875,
|
| 2831 |
+
"learning_rate": 1.9670249881126202e-07,
|
| 2832 |
+
"loss": 0.004040413722395897,
|
| 2833 |
+
"step": 3520,
|
| 2834 |
+
"token_acc": 0.9983177120884402
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 1.8826666666666667,
|
| 2838 |
+
"grad_norm": 0.8359375,
|
| 2839 |
+
"learning_rate": 1.8002016602824634e-07,
|
| 2840 |
+
"loss": 0.003570510447025299,
|
| 2841 |
+
"step": 3530,
|
| 2842 |
+
"token_acc": 0.9985594237695078
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 1.888,
|
| 2846 |
+
"grad_norm": 2.0625,
|
| 2847 |
+
"learning_rate": 1.6407052455221562e-07,
|
| 2848 |
+
"loss": 0.006800946593284607,
|
| 2849 |
+
"step": 3540,
|
| 2850 |
+
"token_acc": 0.9973576747537833
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 1.8933333333333333,
|
| 2854 |
+
"grad_norm": 1.3984375,
|
| 2855 |
+
"learning_rate": 1.4885476442264902e-07,
|
| 2856 |
+
"loss": 0.005493031442165374,
|
| 2857 |
+
"step": 3550,
|
| 2858 |
+
"token_acc": 0.9983225497244189
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 1.8986666666666667,
|
| 2862 |
+
"grad_norm": 1.1796875,
|
| 2863 |
+
"learning_rate": 1.3437402092244533e-07,
|
| 2864 |
+
"loss": 0.004691895842552185,
|
| 2865 |
+
"step": 3560,
|
| 2866 |
+
"token_acc": 0.9983185202978622
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.904,
|
| 2870 |
+
"grad_norm": 0.03857421875,
|
| 2871 |
+
"learning_rate": 1.2062937449321854e-07,
|
| 2872 |
+
"loss": 0.002638164907693863,
|
| 2873 |
+
"step": 3570,
|
| 2874 |
+
"token_acc": 0.9985621854780733
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 1.9093333333333333,
|
| 2878 |
+
"grad_norm": 1.0859375,
|
| 2879 |
+
"learning_rate": 1.0762185065468889e-07,
|
| 2880 |
+
"loss": 0.0054055720567703245,
|
| 2881 |
+
"step": 3580,
|
| 2882 |
+
"token_acc": 0.9973627427475426
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 1.9146666666666667,
|
| 2886 |
+
"grad_norm": 2.40625,
|
| 2887 |
+
"learning_rate": 9.535241992816191e-08,
|
| 2888 |
+
"loss": 0.009028273820877075,
|
| 2889 |
+
"step": 3590,
|
| 2890 |
+
"token_acc": 0.997114691031498
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 1.92,
|
| 2894 |
+
"grad_norm": 1.78125,
|
| 2895 |
+
"learning_rate": 8.382199776411526e-08,
|
| 2896 |
+
"loss": 0.00407477468252182,
|
| 2897 |
+
"step": 3600,
|
| 2898 |
+
"token_acc": 0.9980792316926771
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"epoch": 1.9253333333333333,
|
| 2902 |
+
"grad_norm": 1.421875,
|
| 2903 |
+
"learning_rate": 7.303144447389554e-08,
|
| 2904 |
+
"loss": 0.003363639488816261,
|
| 2905 |
+
"step": 3610,
|
| 2906 |
+
"token_acc": 0.9987925621830476
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 1.9306666666666668,
|
| 2910 |
+
"grad_norm": 2.734375,
|
| 2911 |
+
"learning_rate": 6.298156516552966e-08,
|
| 2912 |
+
"loss": 0.002769722230732441,
|
| 2913 |
+
"step": 3620,
|
| 2914 |
+
"token_acc": 0.9990363767766803
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 1.936,
|
| 2918 |
+
"grad_norm": 0.53515625,
|
| 2919 |
+
"learning_rate": 5.3673109683656245e-08,
|
| 2920 |
+
"loss": 0.0032248608767986298,
|
| 2921 |
+
"step": 3630,
|
| 2922 |
+
"token_acc": 0.999275887038378
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 1.9413333333333334,
|
| 2926 |
+
"grad_norm": 1.484375,
|
| 2927 |
+
"learning_rate": 4.510677255357143e-08,
|
| 2928 |
+
"loss": 0.002857924811542034,
|
| 2929 |
+
"step": 3640,
|
| 2930 |
+
"token_acc": 0.999273607748184
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 1.9466666666666668,
|
| 2934 |
+
"grad_norm": 1.0625,
|
| 2935 |
+
"learning_rate": 3.7283192929412624e-08,
|
| 2936 |
+
"loss": 0.003569948300719261,
|
| 2937 |
+
"step": 3650,
|
| 2938 |
+
"token_acc": 0.9983173076923076
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 1.952,
|
| 2942 |
+
"grad_norm": 1.1796875,
|
| 2943 |
+
"learning_rate": 3.020295454647104e-08,
|
| 2944 |
+
"loss": 0.0055261336266994475,
|
| 2945 |
+
"step": 3660,
|
| 2946 |
+
"token_acc": 0.9983213429256594
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 1.9573333333333334,
|
| 2950 |
+
"grad_norm": 2.015625,
|
| 2951 |
+
"learning_rate": 2.3866585677635445e-08,
|
| 2952 |
+
"loss": 0.00529012456536293,
|
| 2953 |
+
"step": 3670,
|
| 2954 |
+
"token_acc": 0.9983156881616939
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 1.9626666666666668,
|
| 2958 |
+
"grad_norm": 0.71484375,
|
| 2959 |
+
"learning_rate": 1.827455909397813e-08,
|
| 2960 |
+
"loss": 0.0030386311933398246,
|
| 2961 |
+
"step": 3680,
|
| 2962 |
+
"token_acc": 0.9990391544559212
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 1.968,
|
| 2966 |
+
"grad_norm": 0.47265625,
|
| 2967 |
+
"learning_rate": 1.3427292029476458e-08,
|
| 2968 |
+
"loss": 0.004317119717597961,
|
| 2969 |
+
"step": 3690,
|
| 2970 |
+
"token_acc": 0.9987916868052199
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 1.9733333333333334,
|
| 2974 |
+
"grad_norm": 1.2421875,
|
| 2975 |
+
"learning_rate": 9.325146149888887e-09,
|
| 2976 |
+
"loss": 0.0020676439628005026,
|
| 2977 |
+
"step": 3700,
|
| 2978 |
+
"token_acc": 0.9992704280155642
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 1.9786666666666668,
|
| 2982 |
+
"grad_norm": 0.33203125,
|
| 2983 |
+
"learning_rate": 5.96842752576543e-09,
|
| 2984 |
+
"loss": 0.00551963597536087,
|
| 2985 |
+
"step": 3710,
|
| 2986 |
+
"token_acc": 0.9971291866028709
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 1.984,
|
| 2990 |
+
"grad_norm": 1.7578125,
|
| 2991 |
+
"learning_rate": 3.3573866096114903e-09,
|
| 2992 |
+
"loss": 0.00279228575527668,
|
| 2993 |
+
"step": 3720,
|
| 2994 |
+
"token_acc": 0.9985639061752034
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 1.9893333333333332,
|
| 2998 |
+
"grad_norm": 1.6875,
|
| 2999 |
+
"learning_rate": 1.4922182172016908e-09,
|
| 3000 |
+
"loss": 0.005330391228199005,
|
| 3001 |
+
"step": 3730,
|
| 3002 |
+
"token_acc": 0.9980741454020221
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 1.9946666666666668,
|
| 3006 |
+
"grad_norm": 1.734375,
|
| 3007 |
+
"learning_rate": 3.7306151304483675e-10,
|
| 3008 |
+
"loss": 0.004098391160368919,
|
| 3009 |
+
"step": 3740,
|
| 3010 |
+
"token_acc": 0.9987937273823885
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"epoch": 2.0,
|
| 3014 |
+
"grad_norm": 0.045654296875,
|
| 3015 |
+
"learning_rate": 0.0,
|
| 3016 |
+
"loss": 0.006149080768227577,
|
| 3017 |
+
"step": 3750,
|
| 3018 |
+
"token_acc": 0.9972527472527473
|
| 3019 |
+
}
|
| 3020 |
+
],
|
| 3021 |
+
"logging_steps": 10,
|
| 3022 |
+
"max_steps": 3750,
|
| 3023 |
+
"num_input_tokens_seen": 0,
|
| 3024 |
+
"num_train_epochs": 2,
|
| 3025 |
+
"save_steps": 500,
|
| 3026 |
+
"stateful_callbacks": {
|
| 3027 |
+
"TrainerControl": {
|
| 3028 |
+
"args": {
|
| 3029 |
+
"should_epoch_stop": false,
|
| 3030 |
+
"should_evaluate": false,
|
| 3031 |
+
"should_log": false,
|
| 3032 |
+
"should_save": true,
|
| 3033 |
+
"should_training_stop": true
|
| 3034 |
+
},
|
| 3035 |
+
"attributes": {}
|
| 3036 |
+
}
|
| 3037 |
+
},
|
| 3038 |
+
"total_flos": 1.6689320719024128e+18,
|
| 3039 |
+
"train_batch_size": 8,
|
| 3040 |
+
"trial_name": null,
|
| 3041 |
+
"trial_params": null
|
| 3042 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b000a09eb9b90b384d59753f090056f7dd40fd111481f613301c13df94148aae
|
| 3 |
+
size 7249
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|