Upload folder using huggingface_hub
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
- rng_state_2.pth +3 -0
- rng_state_3.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 +1242 -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/eva-4b-balanced24k-full/v0-20260125-094752",
|
| 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": 1,
|
| 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/eva-4b-balanced24k-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/eva-4b-balanced24k-full/v0-20260125-094752",
|
| 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": "FutureMa/Eva-4B-Label-Only-Consensus",
|
| 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_24k_training_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": 4,
|
| 347 |
+
"local_world_size": 4,
|
| 348 |
+
"model_suffix": "Eva-4B-Label-Only-Consensus",
|
| 349 |
+
"model_info": "ModelInfo(model_type='qwen3', model_dir='/home/ubuntu/.cache/huggingface/hub/models--FutureMa--Eva-4B-Label-Only-Consensus/snapshots/0a9a8f028410f178ae8774d62187346ce43356a1', 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=None, 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--FutureMa--Eva-4B-Label-Only-Consensus/snapshots/0a9a8f028410f178ae8774d62187346ce43356a1",
|
| 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/eva-4b-balanced24k-full/v0-20260125-094752', 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=1, 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/eva-4b-balanced24k-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/eva-4b-balanced24k-full/v0-20260125-094752', 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:bafff46d2ccda3b0d5da553d01822290d1e79431f13781a5e0f0c6c19b812b4e
|
| 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:cfb0b6df3823bed58d476d1f4fccd8b187045562cb27035d1f7e2122ec114614
|
| 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 sha256:4382fc771627d76c912c6df506883d17ae060f8de249e9f5d4ff637fc5ec6411
|
| 3 |
+
size 16090225449
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fe6b873f1da64bb980afe982fc1c6b6bc461ad8c33073d856804323f64b26d9
|
| 3 |
+
size 15429
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13db4dd10b22b5464f5ef0b539152b46390eae6a827b355108cb54b1af2eb830
|
| 3 |
+
size 15429
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06e293f13fb6e873e8081636b6b07115410b397c55f1ed08b8772b059c8eb74e
|
| 3 |
+
size 15429
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c595c077664f94b7f91088561951be20e39483e01865774a83bc46f3971a3152
|
| 3 |
+
size 15429
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26d2a2bf2d7b13984f8efee440ac376dc9aec135d539034d0f6ff7509ce14c7c
|
| 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 +1,1242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0013333333333333333,
|
| 14 |
+
"grad_norm": 4.90625,
|
| 15 |
+
"learning_rate": 4.444444444444445e-07,
|
| 16 |
+
"loss": 0.027944788336753845,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.9901477832512315
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.013333333333333334,
|
| 22 |
+
"grad_norm": 4.90625,
|
| 23 |
+
"learning_rate": 4.444444444444444e-06,
|
| 24 |
+
"loss": 0.05075684520933363,
|
| 25 |
+
"step": 10,
|
| 26 |
+
"token_acc": 0.9901595744680851
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02666666666666667,
|
| 30 |
+
"grad_norm": 2.578125,
|
| 31 |
+
"learning_rate": 8.888888888888888e-06,
|
| 32 |
+
"loss": 0.04696210622787476,
|
| 33 |
+
"step": 20,
|
| 34 |
+
"token_acc": 0.9893488259501332
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.04,
|
| 38 |
+
"grad_norm": 2.5625,
|
| 39 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 40 |
+
"loss": 0.05452235341072083,
|
| 41 |
+
"step": 30,
|
| 42 |
+
"token_acc": 0.9853012048192771
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.05333333333333334,
|
| 46 |
+
"grad_norm": 2.0625,
|
| 47 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 48 |
+
"loss": 0.03315775990486145,
|
| 49 |
+
"step": 40,
|
| 50 |
+
"token_acc": 0.9846264712947393
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06666666666666667,
|
| 54 |
+
"grad_norm": 1.046875,
|
| 55 |
+
"learning_rate": 1.9999417253661235e-05,
|
| 56 |
+
"loss": 0.028552538156509398,
|
| 57 |
+
"step": 50,
|
| 58 |
+
"token_acc": 0.9908411665461557
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08,
|
| 62 |
+
"grad_norm": 1.765625,
|
| 63 |
+
"learning_rate": 1.9994755690455154e-05,
|
| 64 |
+
"loss": 0.04210628271102905,
|
| 65 |
+
"step": 60,
|
| 66 |
+
"token_acc": 0.9860944617597699
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09333333333333334,
|
| 70 |
+
"grad_norm": 1.5859375,
|
| 71 |
+
"learning_rate": 1.998543473718677e-05,
|
| 72 |
+
"loss": 0.03467268347740173,
|
| 73 |
+
"step": 70,
|
| 74 |
+
"token_acc": 0.9840695148443157
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.10666666666666667,
|
| 78 |
+
"grad_norm": 1.03125,
|
| 79 |
+
"learning_rate": 1.9971458739130598e-05,
|
| 80 |
+
"loss": 0.03366573452949524,
|
| 81 |
+
"step": 80,
|
| 82 |
+
"token_acc": 0.986271676300578
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.12,
|
| 86 |
+
"grad_norm": 2.109375,
|
| 87 |
+
"learning_rate": 1.995283421166614e-05,
|
| 88 |
+
"loss": 0.03945094347000122,
|
| 89 |
+
"step": 90,
|
| 90 |
+
"token_acc": 0.9827420901246404
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.13333333333333333,
|
| 94 |
+
"grad_norm": 2.171875,
|
| 95 |
+
"learning_rate": 1.9929569837240567e-05,
|
| 96 |
+
"loss": 0.03638350963592529,
|
| 97 |
+
"step": 100,
|
| 98 |
+
"token_acc": 0.9838981014179283
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.14666666666666667,
|
| 102 |
+
"grad_norm": 1.0234375,
|
| 103 |
+
"learning_rate": 1.990167646132107e-05,
|
| 104 |
+
"loss": 0.027288395166397094,
|
| 105 |
+
"step": 110,
|
| 106 |
+
"token_acc": 0.9886555636012552
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.16,
|
| 110 |
+
"grad_norm": 1.375,
|
| 111 |
+
"learning_rate": 1.9869167087338908e-05,
|
| 112 |
+
"loss": 0.03376817405223846,
|
| 113 |
+
"step": 120,
|
| 114 |
+
"token_acc": 0.987075155576831
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17333333333333334,
|
| 118 |
+
"grad_norm": 1.7265625,
|
| 119 |
+
"learning_rate": 1.983205687062742e-05,
|
| 120 |
+
"loss": 0.03553054332733154,
|
| 121 |
+
"step": 130,
|
| 122 |
+
"token_acc": 0.9824687800192123
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.18666666666666668,
|
| 126 |
+
"grad_norm": 1.59375,
|
| 127 |
+
"learning_rate": 1.9790363111356838e-05,
|
| 128 |
+
"loss": 0.033854860067367556,
|
| 129 |
+
"step": 140,
|
| 130 |
+
"token_acc": 0.9848812095032398
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2,
|
| 134 |
+
"grad_norm": 1.53125,
|
| 135 |
+
"learning_rate": 1.9744105246469264e-05,
|
| 136 |
+
"loss": 0.02748125195503235,
|
| 137 |
+
"step": 150,
|
| 138 |
+
"token_acc": 0.9879459980713597
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.21333333333333335,
|
| 142 |
+
"grad_norm": 2.59375,
|
| 143 |
+
"learning_rate": 1.9693304840617456e-05,
|
| 144 |
+
"loss": 0.03520364165306091,
|
| 145 |
+
"step": 160,
|
| 146 |
+
"token_acc": 0.9846042819340871
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.22666666666666666,
|
| 150 |
+
"grad_norm": 1.6171875,
|
| 151 |
+
"learning_rate": 1.963798557611178e-05,
|
| 152 |
+
"loss": 0.03284199237823486,
|
| 153 |
+
"step": 170,
|
| 154 |
+
"token_acc": 0.9877902801053388
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.24,
|
| 158 |
+
"grad_norm": 0.96484375,
|
| 159 |
+
"learning_rate": 1.957817324187987e-05,
|
| 160 |
+
"loss": 0.03556506037712097,
|
| 161 |
+
"step": 180,
|
| 162 |
+
"token_acc": 0.98562874251497
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.25333333333333335,
|
| 166 |
+
"grad_norm": 1.15625,
|
| 167 |
+
"learning_rate": 1.9513895721444286e-05,
|
| 168 |
+
"loss": 0.030231645703315733,
|
| 169 |
+
"step": 190,
|
| 170 |
+
"token_acc": 0.9858275282248379
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.26666666666666666,
|
| 174 |
+
"grad_norm": 2.515625,
|
| 175 |
+
"learning_rate": 1.9445182979923657e-05,
|
| 176 |
+
"loss": 0.03149127662181854,
|
| 177 |
+
"step": 200,
|
| 178 |
+
"token_acc": 0.9862085652068715
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.28,
|
| 182 |
+
"grad_norm": 1.0234375,
|
| 183 |
+
"learning_rate": 1.937206705006344e-05,
|
| 184 |
+
"loss": 0.03637541532516479,
|
| 185 |
+
"step": 210,
|
| 186 |
+
"token_acc": 0.9851211903047756
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.29333333333333333,
|
| 190 |
+
"grad_norm": 1.34375,
|
| 191 |
+
"learning_rate": 1.9294582017302797e-05,
|
| 192 |
+
"loss": 0.03209535479545593,
|
| 193 |
+
"step": 220,
|
| 194 |
+
"token_acc": 0.9861542134160898
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.30666666666666664,
|
| 198 |
+
"grad_norm": 1.6015625,
|
| 199 |
+
"learning_rate": 1.921276400388451e-05,
|
| 200 |
+
"loss": 0.031918269395828244,
|
| 201 |
+
"step": 230,
|
| 202 |
+
"token_acc": 0.986810551558753
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.32,
|
| 206 |
+
"grad_norm": 1.9921875,
|
| 207 |
+
"learning_rate": 1.9126651152015404e-05,
|
| 208 |
+
"loss": 0.03563873469829559,
|
| 209 |
+
"step": 240,
|
| 210 |
+
"token_acc": 0.983626294245124
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.3333333333333333,
|
| 214 |
+
"grad_norm": 1.5234375,
|
| 215 |
+
"learning_rate": 1.9036283606085057e-05,
|
| 216 |
+
"loss": 0.03571958541870117,
|
| 217 |
+
"step": 250,
|
| 218 |
+
"token_acc": 0.9839019702066314
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.3466666666666667,
|
| 222 |
+
"grad_norm": 2.1875,
|
| 223 |
+
"learning_rate": 1.8941703493951163e-05,
|
| 224 |
+
"loss": 0.030891618132591246,
|
| 225 |
+
"step": 260,
|
| 226 |
+
"token_acc": 0.9862881885975463
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.36,
|
| 230 |
+
"grad_norm": 1.78125,
|
| 231 |
+
"learning_rate": 1.8842954907300236e-05,
|
| 232 |
+
"loss": 0.03673713207244873,
|
| 233 |
+
"step": 270,
|
| 234 |
+
"token_acc": 0.9827006246996636
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.37333333333333335,
|
| 238 |
+
"grad_norm": 2.015625,
|
| 239 |
+
"learning_rate": 1.874008388109276e-05,
|
| 240 |
+
"loss": 0.033187645673751834,
|
| 241 |
+
"step": 280,
|
| 242 |
+
"token_acc": 0.9853752097818269
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.38666666666666666,
|
| 246 |
+
"grad_norm": 1.21875,
|
| 247 |
+
"learning_rate": 1.863313837210247e-05,
|
| 248 |
+
"loss": 0.03002692461013794,
|
| 249 |
+
"step": 290,
|
| 250 |
+
"token_acc": 0.9861011262880421
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.4,
|
| 254 |
+
"grad_norm": 1.9921875,
|
| 255 |
+
"learning_rate": 1.8522168236559693e-05,
|
| 256 |
+
"loss": 0.03252564668655396,
|
| 257 |
+
"step": 300,
|
| 258 |
+
"token_acc": 0.9860409145607701
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.41333333333333333,
|
| 262 |
+
"grad_norm": 1.1484375,
|
| 263 |
+
"learning_rate": 1.840722520690921e-05,
|
| 264 |
+
"loss": 0.034389343857765195,
|
| 265 |
+
"step": 310,
|
| 266 |
+
"token_acc": 0.9862683690676946
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.4266666666666667,
|
| 270 |
+
"grad_norm": 2.046875,
|
| 271 |
+
"learning_rate": 1.8288362867693414e-05,
|
| 272 |
+
"loss": 0.030599406361579894,
|
| 273 |
+
"step": 320,
|
| 274 |
+
"token_acc": 0.9861011262880421
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.44,
|
| 278 |
+
"grad_norm": 0.9453125,
|
| 279 |
+
"learning_rate": 1.816563663057211e-05,
|
| 280 |
+
"loss": 0.029587957262992858,
|
| 281 |
+
"step": 330,
|
| 282 |
+
"token_acc": 0.9865513928914506
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4533333333333333,
|
| 286 |
+
"grad_norm": 1.5390625,
|
| 287 |
+
"learning_rate": 1.8039103708490503e-05,
|
| 288 |
+
"loss": 0.03238507807254791,
|
| 289 |
+
"step": 340,
|
| 290 |
+
"token_acc": 0.985875029925784
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.4666666666666667,
|
| 294 |
+
"grad_norm": 0.77734375,
|
| 295 |
+
"learning_rate": 1.790882308900746e-05,
|
| 296 |
+
"loss": 0.03101579546928406,
|
| 297 |
+
"step": 350,
|
| 298 |
+
"token_acc": 0.9872962607861937
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.48,
|
| 302 |
+
"grad_norm": 1.53125,
|
| 303 |
+
"learning_rate": 1.7774855506796497e-05,
|
| 304 |
+
"loss": 0.031994479894638064,
|
| 305 |
+
"step": 360,
|
| 306 |
+
"token_acc": 0.9857350096711799
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.49333333333333335,
|
| 310 |
+
"grad_norm": 1.2421875,
|
| 311 |
+
"learning_rate": 1.7637263415332272e-05,
|
| 312 |
+
"loss": 0.028815871477127074,
|
| 313 |
+
"step": 370,
|
| 314 |
+
"token_acc": 0.9896110171539019
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.5066666666666667,
|
| 318 |
+
"grad_norm": 1.515625,
|
| 319 |
+
"learning_rate": 1.749611095777581e-05,
|
| 320 |
+
"loss": 0.03330559730529785,
|
| 321 |
+
"step": 380,
|
| 322 |
+
"token_acc": 0.9864734299516909
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.52,
|
| 326 |
+
"grad_norm": 1.4453125,
|
| 327 |
+
"learning_rate": 1.7351463937072008e-05,
|
| 328 |
+
"loss": 0.024368155002593993,
|
| 329 |
+
"step": 390,
|
| 330 |
+
"token_acc": 0.9897202964379632
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.5333333333333333,
|
| 334 |
+
"grad_norm": 2.140625,
|
| 335 |
+
"learning_rate": 1.7203389785273402e-05,
|
| 336 |
+
"loss": 0.0315426915884018,
|
| 337 |
+
"step": 400,
|
| 338 |
+
"token_acc": 0.9867501806793544
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5466666666666666,
|
| 342 |
+
"grad_norm": 0.99609375,
|
| 343 |
+
"learning_rate": 1.705195753210446e-05,
|
| 344 |
+
"loss": 0.027628937363624574,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"token_acc": 0.9856699307379986
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.56,
|
| 350 |
+
"grad_norm": 1.5078125,
|
| 351 |
+
"learning_rate": 1.6897237772781046e-05,
|
| 352 |
+
"loss": 0.031161597371101378,
|
| 353 |
+
"step": 420,
|
| 354 |
+
"token_acc": 0.9867756672276989
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.5733333333333334,
|
| 358 |
+
"grad_norm": 2.046875,
|
| 359 |
+
"learning_rate": 1.673930263510011e-05,
|
| 360 |
+
"loss": 0.030777221918106078,
|
| 361 |
+
"step": 430,
|
| 362 |
+
"token_acc": 0.9867851994233542
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.5866666666666667,
|
| 366 |
+
"grad_norm": 1.9609375,
|
| 367 |
+
"learning_rate": 1.6578225745814907e-05,
|
| 368 |
+
"loss": 0.030515575408935548,
|
| 369 |
+
"step": 440,
|
| 370 |
+
"token_acc": 0.9867947178871549
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.6,
|
| 374 |
+
"grad_norm": 2.65625,
|
| 375 |
+
"learning_rate": 1.6414082196311402e-05,
|
| 376 |
+
"loss": 0.031556323170661926,
|
| 377 |
+
"step": 450,
|
| 378 |
+
"token_acc": 0.9853471054527985
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.6133333333333333,
|
| 382 |
+
"grad_norm": 2.859375,
|
| 383 |
+
"learning_rate": 1.6246948507601915e-05,
|
| 384 |
+
"loss": 0.028740781545639037,
|
| 385 |
+
"step": 460,
|
| 386 |
+
"token_acc": 0.9858173076923077
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.6266666666666667,
|
| 390 |
+
"grad_norm": 3.296875,
|
| 391 |
+
"learning_rate": 1.607690259465229e-05,
|
| 392 |
+
"loss": 0.031500387191772464,
|
| 393 |
+
"step": 470,
|
| 394 |
+
"token_acc": 0.9882522176935986
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.64,
|
| 398 |
+
"grad_norm": 2.25,
|
| 399 |
+
"learning_rate": 1.5904023730059227e-05,
|
| 400 |
+
"loss": 0.03357301354408264,
|
| 401 |
+
"step": 480,
|
| 402 |
+
"token_acc": 0.9862914862914863
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6533333333333333,
|
| 406 |
+
"grad_norm": 2.015625,
|
| 407 |
+
"learning_rate": 1.57283925070947e-05,
|
| 408 |
+
"loss": 0.03677979111671448,
|
| 409 |
+
"step": 490,
|
| 410 |
+
"token_acc": 0.982924482924483
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.6666666666666666,
|
| 414 |
+
"grad_norm": 1.1171875,
|
| 415 |
+
"learning_rate": 1.55500908021347e-05,
|
| 416 |
+
"loss": 0.03298424780368805,
|
| 417 |
+
"step": 500,
|
| 418 |
+
"token_acc": 0.9850169163847269
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.68,
|
| 422 |
+
"grad_norm": 2.6875,
|
| 423 |
+
"learning_rate": 1.536920173648984e-05,
|
| 424 |
+
"loss": 0.035187387466430665,
|
| 425 |
+
"step": 510,
|
| 426 |
+
"token_acc": 0.9867597496389022
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6933333333333334,
|
| 430 |
+
"grad_norm": 1.546875,
|
| 431 |
+
"learning_rate": 1.5185809637655548e-05,
|
| 432 |
+
"loss": 0.02551887333393097,
|
| 433 |
+
"step": 520,
|
| 434 |
+
"token_acc": 0.990148966842864
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.7066666666666667,
|
| 438 |
+
"grad_norm": 1.375,
|
| 439 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 440 |
+
"loss": 0.029168868064880372,
|
| 441 |
+
"step": 530,
|
| 442 |
+
"token_acc": 0.9879489033502049
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.72,
|
| 446 |
+
"grad_norm": 1.8203125,
|
| 447 |
+
"learning_rate": 1.4811859444908053e-05,
|
| 448 |
+
"loss": 0.02838689088821411,
|
| 449 |
+
"step": 540,
|
| 450 |
+
"token_acc": 0.9872442839951865
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7333333333333333,
|
| 454 |
+
"grad_norm": 1.6875,
|
| 455 |
+
"learning_rate": 1.4621475680399771e-05,
|
| 456 |
+
"loss": 0.027503234148025513,
|
| 457 |
+
"step": 550,
|
| 458 |
+
"token_acc": 0.9870285851549363
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7466666666666667,
|
| 462 |
+
"grad_norm": 0.9296875,
|
| 463 |
+
"learning_rate": 1.4428937460242417e-05,
|
| 464 |
+
"loss": 0.03381537199020386,
|
| 465 |
+
"step": 560,
|
| 466 |
+
"token_acc": 0.9860744297719087
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.76,
|
| 470 |
+
"grad_norm": 1.296875,
|
| 471 |
+
"learning_rate": 1.4234334542574906e-05,
|
| 472 |
+
"loss": 0.028558316826820373,
|
| 473 |
+
"step": 570,
|
| 474 |
+
"token_acc": 0.9874909790714458
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.7733333333333333,
|
| 478 |
+
"grad_norm": 1.4921875,
|
| 479 |
+
"learning_rate": 1.4037757648064019e-05,
|
| 480 |
+
"loss": 0.029447346925735474,
|
| 481 |
+
"step": 580,
|
| 482 |
+
"token_acc": 0.9868609651218346
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.7866666666666666,
|
| 486 |
+
"grad_norm": 2.453125,
|
| 487 |
+
"learning_rate": 1.3839298417611964e-05,
|
| 488 |
+
"loss": 0.02759793698787689,
|
| 489 |
+
"step": 590,
|
| 490 |
+
"token_acc": 0.9877285851780558
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.8,
|
| 494 |
+
"grad_norm": 1.8671875,
|
| 495 |
+
"learning_rate": 1.3639049369634878e-05,
|
| 496 |
+
"loss": 0.030391490459442137,
|
| 497 |
+
"step": 600,
|
| 498 |
+
"token_acc": 0.9863505747126436
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.8133333333333334,
|
| 502 |
+
"grad_norm": 1.5390625,
|
| 503 |
+
"learning_rate": 1.3437103856932266e-05,
|
| 504 |
+
"loss": 0.028662437200546266,
|
| 505 |
+
"step": 610,
|
| 506 |
+
"token_acc": 0.9881470730527334
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8266666666666667,
|
| 510 |
+
"grad_norm": 1.453125,
|
| 511 |
+
"learning_rate": 1.3233556023167487e-05,
|
| 512 |
+
"loss": 0.02797028422355652,
|
| 513 |
+
"step": 620,
|
| 514 |
+
"token_acc": 0.9882211538461538
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.84,
|
| 518 |
+
"grad_norm": 1.59375,
|
| 519 |
+
"learning_rate": 1.3028500758979507e-05,
|
| 520 |
+
"loss": 0.02865118682384491,
|
| 521 |
+
"step": 630,
|
| 522 |
+
"token_acc": 0.9860911270983214
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.8533333333333334,
|
| 526 |
+
"grad_norm": 1.234375,
|
| 527 |
+
"learning_rate": 1.2822033657746478e-05,
|
| 528 |
+
"loss": 0.026763680577278137,
|
| 529 |
+
"step": 640,
|
| 530 |
+
"token_acc": 0.9887127761767531
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.8666666666666667,
|
| 534 |
+
"grad_norm": 2.078125,
|
| 535 |
+
"learning_rate": 1.2614250971021658e-05,
|
| 536 |
+
"loss": 0.03335306942462921,
|
| 537 |
+
"step": 650,
|
| 538 |
+
"token_acc": 0.9831568816169394
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.88,
|
| 542 |
+
"grad_norm": 1.765625,
|
| 543 |
+
"learning_rate": 1.2405249563662539e-05,
|
| 544 |
+
"loss": 0.02619180679321289,
|
| 545 |
+
"step": 660,
|
| 546 |
+
"token_acc": 0.9882465819141281
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.8933333333333333,
|
| 550 |
+
"grad_norm": 1.2890625,
|
| 551 |
+
"learning_rate": 1.2195126868674052e-05,
|
| 552 |
+
"loss": 0.028585124015808105,
|
| 553 |
+
"step": 670,
|
| 554 |
+
"token_acc": 0.9881984585741811
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.9066666666666666,
|
| 558 |
+
"grad_norm": 1.15625,
|
| 559 |
+
"learning_rate": 1.1983980841786899e-05,
|
| 560 |
+
"loss": 0.02787652611732483,
|
| 561 |
+
"step": 680,
|
| 562 |
+
"token_acc": 0.9889290012033695
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.92,
|
| 566 |
+
"grad_norm": 1.796875,
|
| 567 |
+
"learning_rate": 1.177190991579223e-05,
|
| 568 |
+
"loss": 0.0291363924741745,
|
| 569 |
+
"step": 690,
|
| 570 |
+
"token_acc": 0.9864897466827504
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9333333333333333,
|
| 574 |
+
"grad_norm": 1.21875,
|
| 575 |
+
"learning_rate": 1.1559012954653865e-05,
|
| 576 |
+
"loss": 0.03034358024597168,
|
| 577 |
+
"step": 700,
|
| 578 |
+
"token_acc": 0.9869407496977025
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.9466666666666667,
|
| 582 |
+
"grad_norm": 1.34375,
|
| 583 |
+
"learning_rate": 1.1345389207419588e-05,
|
| 584 |
+
"loss": 0.027029412984848022,
|
| 585 |
+
"step": 710,
|
| 586 |
+
"token_acc": 0.9873084291187739
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.96,
|
| 590 |
+
"grad_norm": 2.125,
|
| 591 |
+
"learning_rate": 1.1131138261952845e-05,
|
| 592 |
+
"loss": 0.029054158926010133,
|
| 593 |
+
"step": 720,
|
| 594 |
+
"token_acc": 0.9872657376261412
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.9733333333333334,
|
| 598 |
+
"grad_norm": 1.28125,
|
| 599 |
+
"learning_rate": 1.0916359998506549e-05,
|
| 600 |
+
"loss": 0.030344563722610473,
|
| 601 |
+
"step": 730,
|
| 602 |
+
"token_acc": 0.987710843373494
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.9866666666666667,
|
| 606 |
+
"grad_norm": 1.2421875,
|
| 607 |
+
"learning_rate": 1.070115454316054e-05,
|
| 608 |
+
"loss": 0.028968954086303712,
|
| 609 |
+
"step": 740,
|
| 610 |
+
"token_acc": 0.986003861003861
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.0,
|
| 614 |
+
"grad_norm": 1.5546875,
|
| 615 |
+
"learning_rate": 1.0485622221144485e-05,
|
| 616 |
+
"loss": 0.027395570278167726,
|
| 617 |
+
"step": 750,
|
| 618 |
+
"token_acc": 0.9886005335920446
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0133333333333334,
|
| 622 |
+
"grad_norm": 0.796875,
|
| 623 |
+
"learning_rate": 1.0269863510067872e-05,
|
| 624 |
+
"loss": 0.013629350066184997,
|
| 625 |
+
"step": 760,
|
| 626 |
+
"token_acc": 0.9968712394705175
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0266666666666666,
|
| 630 |
+
"grad_norm": 0.79296875,
|
| 631 |
+
"learning_rate": 1.0053978993079046e-05,
|
| 632 |
+
"loss": 0.012067935615777969,
|
| 633 |
+
"step": 770,
|
| 634 |
+
"token_acc": 0.9961749940234281
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.04,
|
| 638 |
+
"grad_norm": 2.203125,
|
| 639 |
+
"learning_rate": 9.838069311974986e-06,
|
| 640 |
+
"loss": 0.011612998694181443,
|
| 641 |
+
"step": 780,
|
| 642 |
+
"token_acc": 0.9954348870735223
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.0533333333333332,
|
| 646 |
+
"grad_norm": 0.5,
|
| 647 |
+
"learning_rate": 9.622235120283769e-06,
|
| 648 |
+
"loss": 0.0077203229069709774,
|
| 649 |
+
"step": 790,
|
| 650 |
+
"token_acc": 0.9971271247306679
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.0666666666666667,
|
| 654 |
+
"grad_norm": 0.45703125,
|
| 655 |
+
"learning_rate": 9.406577036341548e-06,
|
| 656 |
+
"loss": 0.011040687561035156,
|
| 657 |
+
"step": 800,
|
| 658 |
+
"token_acc": 0.9956772334293948
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.08,
|
| 662 |
+
"grad_norm": 0.5859375,
|
| 663 |
+
"learning_rate": 9.19119559638596e-06,
|
| 664 |
+
"loss": 0.008952221274375916,
|
| 665 |
+
"step": 810,
|
| 666 |
+
"token_acc": 0.9966450994488377
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.0933333333333333,
|
| 670 |
+
"grad_norm": 1.8515625,
|
| 671 |
+
"learning_rate": 8.976191207687775e-06,
|
| 672 |
+
"loss": 0.010079852491617202,
|
| 673 |
+
"step": 820,
|
| 674 |
+
"token_acc": 0.9959310674964098
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.1066666666666667,
|
| 678 |
+
"grad_norm": 1.625,
|
| 679 |
+
"learning_rate": 8.7616641017427e-06,
|
| 680 |
+
"loss": 0.01139761358499527,
|
| 681 |
+
"step": 830,
|
| 682 |
+
"token_acc": 0.9963916285783017
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.12,
|
| 686 |
+
"grad_norm": 1.609375,
|
| 687 |
+
"learning_rate": 8.5477142875451e-06,
|
| 688 |
+
"loss": 0.010524387657642364,
|
| 689 |
+
"step": 840,
|
| 690 |
+
"token_acc": 0.9961361989857522
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.1333333333333333,
|
| 694 |
+
"grad_norm": 0.84375,
|
| 695 |
+
"learning_rate": 8.334441504965456e-06,
|
| 696 |
+
"loss": 0.011410476267337799,
|
| 697 |
+
"step": 850,
|
| 698 |
+
"token_acc": 0.9956490210297317
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.1466666666666667,
|
| 702 |
+
"grad_norm": 1.90625,
|
| 703 |
+
"learning_rate": 8.1219451782533e-06,
|
| 704 |
+
"loss": 0.009808246791362763,
|
| 705 |
+
"step": 860,
|
| 706 |
+
"token_acc": 0.9964020148716719
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.16,
|
| 710 |
+
"grad_norm": 1.28125,
|
| 711 |
+
"learning_rate": 7.91032436968725e-06,
|
| 712 |
+
"loss": 0.008106120675802232,
|
| 713 |
+
"step": 870,
|
| 714 |
+
"token_acc": 0.9964054636951833
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.1733333333333333,
|
| 718 |
+
"grad_norm": 1.0859375,
|
| 719 |
+
"learning_rate": 7.699677733393827e-06,
|
| 720 |
+
"loss": 0.005388218909502029,
|
| 721 |
+
"step": 880,
|
| 722 |
+
"token_acc": 0.9978515158749105
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.1866666666666668,
|
| 726 |
+
"grad_norm": 1.96875,
|
| 727 |
+
"learning_rate": 7.490103469356513e-06,
|
| 728 |
+
"loss": 0.016499459743499756,
|
| 729 |
+
"step": 890,
|
| 730 |
+
"token_acc": 0.9947000722717417
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.2,
|
| 734 |
+
"grad_norm": 1.75,
|
| 735 |
+
"learning_rate": 7.2816992776365714e-06,
|
| 736 |
+
"loss": 0.008301901072263718,
|
| 737 |
+
"step": 900,
|
| 738 |
+
"token_acc": 0.9966418805468937
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.2133333333333334,
|
| 742 |
+
"grad_norm": 1.1328125,
|
| 743 |
+
"learning_rate": 7.0745623128268605e-06,
|
| 744 |
+
"loss": 0.010182877629995346,
|
| 745 |
+
"step": 910,
|
| 746 |
+
"token_acc": 0.9963968292097045
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.2266666666666666,
|
| 750 |
+
"grad_norm": 0.44921875,
|
| 751 |
+
"learning_rate": 6.868789138759977e-06,
|
| 752 |
+
"loss": 0.007760406285524368,
|
| 753 |
+
"step": 920,
|
| 754 |
+
"token_acc": 0.9971278123504069
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.24,
|
| 758 |
+
"grad_norm": 1.3828125,
|
| 759 |
+
"learning_rate": 6.664475683491797e-06,
|
| 760 |
+
"loss": 0.007416041195392608,
|
| 761 |
+
"step": 930,
|
| 762 |
+
"token_acc": 0.997346840328027
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.2533333333333334,
|
| 766 |
+
"grad_norm": 1.6484375,
|
| 767 |
+
"learning_rate": 6.461717194581394e-06,
|
| 768 |
+
"loss": 0.012545964121818543,
|
| 769 |
+
"step": 940,
|
| 770 |
+
"token_acc": 0.9954260953298026
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.2666666666666666,
|
| 774 |
+
"grad_norm": 2.625,
|
| 775 |
+
"learning_rate": 6.260608194688207e-06,
|
| 776 |
+
"loss": 0.009528040885925293,
|
| 777 |
+
"step": 950,
|
| 778 |
+
"token_acc": 0.9964011516314779
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.28,
|
| 782 |
+
"grad_norm": 1.109375,
|
| 783 |
+
"learning_rate": 6.061242437507131e-06,
|
| 784 |
+
"loss": 0.010063067823648453,
|
| 785 |
+
"step": 960,
|
| 786 |
+
"token_acc": 0.9958907420836355
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.2933333333333334,
|
| 790 |
+
"grad_norm": 2.03125,
|
| 791 |
+
"learning_rate": 5.863712864062089e-06,
|
| 792 |
+
"loss": 0.016041702032089232,
|
| 793 |
+
"step": 970,
|
| 794 |
+
"token_acc": 0.9954326923076923
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.3066666666666666,
|
| 798 |
+
"grad_norm": 1.859375,
|
| 799 |
+
"learning_rate": 5.6681115593784705e-06,
|
| 800 |
+
"loss": 0.010919718444347382,
|
| 801 |
+
"step": 980,
|
| 802 |
+
"token_acc": 0.9959124789612888
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.32,
|
| 806 |
+
"grad_norm": 0.421875,
|
| 807 |
+
"learning_rate": 5.4745297095546125e-06,
|
| 808 |
+
"loss": 0.011771070957183837,
|
| 809 |
+
"step": 990,
|
| 810 |
+
"token_acc": 0.9963933637893725
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.3333333333333333,
|
| 814 |
+
"grad_norm": 0.21484375,
|
| 815 |
+
"learning_rate": 5.2830575592523415e-06,
|
| 816 |
+
"loss": 0.011084750294685364,
|
| 817 |
+
"step": 1000,
|
| 818 |
+
"token_acc": 0.996135265700483
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.3466666666666667,
|
| 822 |
+
"grad_norm": 1.3828125,
|
| 823 |
+
"learning_rate": 5.093784369626397e-06,
|
| 824 |
+
"loss": 0.007512730360031128,
|
| 825 |
+
"step": 1010,
|
| 826 |
+
"token_acc": 0.9968772519817439
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.3599999999999999,
|
| 830 |
+
"grad_norm": 0.85546875,
|
| 831 |
+
"learning_rate": 4.9067983767123736e-06,
|
| 832 |
+
"loss": 0.010888008773326874,
|
| 833 |
+
"step": 1020,
|
| 834 |
+
"token_acc": 0.9963985594237695
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.3733333333333333,
|
| 838 |
+
"grad_norm": 1.3828125,
|
| 839 |
+
"learning_rate": 4.722186750292511e-06,
|
| 840 |
+
"loss": 0.01149669587612152,
|
| 841 |
+
"step": 1030,
|
| 842 |
+
"token_acc": 0.9964054636951833
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.3866666666666667,
|
| 846 |
+
"grad_norm": 1.890625,
|
| 847 |
+
"learning_rate": 4.54003555325862e-06,
|
| 848 |
+
"loss": 0.009606964886188507,
|
| 849 |
+
"step": 1040,
|
| 850 |
+
"token_acc": 0.9970937272947444
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.4,
|
| 854 |
+
"grad_norm": 2.484375,
|
| 855 |
+
"learning_rate": 4.360429701490935e-06,
|
| 856 |
+
"loss": 0.011592777073383331,
|
| 857 |
+
"step": 1050,
|
| 858 |
+
"token_acc": 0.9959222835212281
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.4133333333333333,
|
| 862 |
+
"grad_norm": 0.625,
|
| 863 |
+
"learning_rate": 4.183452924271776e-06,
|
| 864 |
+
"loss": 0.008268815279006959,
|
| 865 |
+
"step": 1060,
|
| 866 |
+
"token_acc": 0.9963924963924964
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.4266666666666667,
|
| 870 |
+
"grad_norm": 1.0859375,
|
| 871 |
+
"learning_rate": 4.009187725252309e-06,
|
| 872 |
+
"loss": 0.008235112577676774,
|
| 873 |
+
"step": 1070,
|
| 874 |
+
"token_acc": 0.996875
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.44,
|
| 878 |
+
"grad_norm": 1.6953125,
|
| 879 |
+
"learning_rate": 3.837715343990727e-06,
|
| 880 |
+
"loss": 0.010764123499393463,
|
| 881 |
+
"step": 1080,
|
| 882 |
+
"token_acc": 0.9963645176926805
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.4533333333333334,
|
| 886 |
+
"grad_norm": 2.421875,
|
| 887 |
+
"learning_rate": 3.669115718079702e-06,
|
| 888 |
+
"loss": 0.01102955937385559,
|
| 889 |
+
"step": 1090,
|
| 890 |
+
"token_acc": 0.9954425521707844
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.4666666666666668,
|
| 894 |
+
"grad_norm": 0.453125,
|
| 895 |
+
"learning_rate": 3.5034674458807893e-06,
|
| 896 |
+
"loss": 0.01023436188697815,
|
| 897 |
+
"step": 1100,
|
| 898 |
+
"token_acc": 0.9963750604156597
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.48,
|
| 902 |
+
"grad_norm": 1.8125,
|
| 903 |
+
"learning_rate": 3.3408477498831917e-06,
|
| 904 |
+
"loss": 0.008587966859340667,
|
| 905 |
+
"step": 1110,
|
| 906 |
+
"token_acc": 0.9961676646706586
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4933333333333334,
|
| 910 |
+
"grad_norm": 1.59375,
|
| 911 |
+
"learning_rate": 3.1813324407038826e-06,
|
| 912 |
+
"loss": 0.007490788400173187,
|
| 913 |
+
"step": 1120,
|
| 914 |
+
"token_acc": 0.9971056439942113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.5066666666666668,
|
| 918 |
+
"grad_norm": 0.88671875,
|
| 919 |
+
"learning_rate": 3.024995881745972e-06,
|
| 920 |
+
"loss": 0.00892709642648697,
|
| 921 |
+
"step": 1130,
|
| 922 |
+
"token_acc": 0.9952049868137137
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.52,
|
| 926 |
+
"grad_norm": 0.625,
|
| 927 |
+
"learning_rate": 2.8719109545317102e-06,
|
| 928 |
+
"loss": 0.010660454630851746,
|
| 929 |
+
"step": 1140,
|
| 930 |
+
"token_acc": 0.9963715529753265
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.5333333333333332,
|
| 934 |
+
"grad_norm": 0.921875,
|
| 935 |
+
"learning_rate": 2.722149024726307e-06,
|
| 936 |
+
"loss": 0.008663681149482728,
|
| 937 |
+
"step": 1150,
|
| 938 |
+
"token_acc": 0.9968892079444843
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.5466666666666666,
|
| 942 |
+
"grad_norm": 1.1796875,
|
| 943 |
+
"learning_rate": 2.5757799088684654e-06,
|
| 944 |
+
"loss": 0.011409056186676026,
|
| 945 |
+
"step": 1160,
|
| 946 |
+
"token_acc": 0.9959193470955353
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.56,
|
| 950 |
+
"grad_norm": 1.8046875,
|
| 951 |
+
"learning_rate": 2.432871841823047e-06,
|
| 952 |
+
"loss": 0.008858834207057954,
|
| 953 |
+
"step": 1170,
|
| 954 |
+
"token_acc": 0.9973513123043583
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.5733333333333333,
|
| 958 |
+
"grad_norm": 0.1435546875,
|
| 959 |
+
"learning_rate": 2.293491444971109e-06,
|
| 960 |
+
"loss": 0.005919945612549782,
|
| 961 |
+
"step": 1180,
|
| 962 |
+
"token_acc": 0.9971133028626413
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.5866666666666667,
|
| 966 |
+
"grad_norm": 1.5546875,
|
| 967 |
+
"learning_rate": 2.157703695152109e-06,
|
| 968 |
+
"loss": 0.011429443210363387,
|
| 969 |
+
"step": 1190,
|
| 970 |
+
"token_acc": 0.9944724825763037
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.6,
|
| 974 |
+
"grad_norm": 0.96484375,
|
| 975 |
+
"learning_rate": 2.025571894372794e-06,
|
| 976 |
+
"loss": 0.008558385819196702,
|
| 977 |
+
"step": 1200,
|
| 978 |
+
"token_acc": 0.9966159052453468
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.6133333333333333,
|
| 982 |
+
"grad_norm": 1.9921875,
|
| 983 |
+
"learning_rate": 1.897157640296825e-06,
|
| 984 |
+
"loss": 0.012137772142887115,
|
| 985 |
+
"step": 1210,
|
| 986 |
+
"token_acc": 0.9954282964388835
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.6266666666666667,
|
| 990 |
+
"grad_norm": 2.03125,
|
| 991 |
+
"learning_rate": 1.7725207975289883e-06,
|
| 992 |
+
"loss": 0.008094522356986999,
|
| 993 |
+
"step": 1220,
|
| 994 |
+
"token_acc": 0.9976019184652278
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.6400000000000001,
|
| 998 |
+
"grad_norm": 1.2890625,
|
| 999 |
+
"learning_rate": 1.6517194697072903e-06,
|
| 1000 |
+
"loss": 0.01032220721244812,
|
| 1001 |
+
"step": 1230,
|
| 1002 |
+
"token_acc": 0.9975984630163305
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.6533333333333333,
|
| 1006 |
+
"grad_norm": 1.4765625,
|
| 1007 |
+
"learning_rate": 1.534809972415998e-06,
|
| 1008 |
+
"loss": 0.006939056515693665,
|
| 1009 |
+
"step": 1240,
|
| 1010 |
+
"token_acc": 0.996868978805395
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.6666666666666665,
|
| 1014 |
+
"grad_norm": 2.53125,
|
| 1015 |
+
"learning_rate": 1.4218468069322576e-06,
|
| 1016 |
+
"loss": 0.015096238255500794,
|
| 1017 |
+
"step": 1250,
|
| 1018 |
+
"token_acc": 0.9951853635050554
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6800000000000002,
|
| 1022 |
+
"grad_norm": 1.6875,
|
| 1023 |
+
"learning_rate": 1.3128826348184886e-06,
|
| 1024 |
+
"loss": 0.010143952071666717,
|
| 1025 |
+
"step": 1260,
|
| 1026 |
+
"token_acc": 0.9961482908040443
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.6933333333333334,
|
| 1030 |
+
"grad_norm": 0.62109375,
|
| 1031 |
+
"learning_rate": 1.207968253372438e-06,
|
| 1032 |
+
"loss": 0.009067404270172118,
|
| 1033 |
+
"step": 1270,
|
| 1034 |
+
"token_acc": 0.995906573561281
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.7066666666666666,
|
| 1038 |
+
"grad_norm": 1.5078125,
|
| 1039 |
+
"learning_rate": 1.1071525719463094e-06,
|
| 1040 |
+
"loss": 0.011023186147212982,
|
| 1041 |
+
"step": 1280,
|
| 1042 |
+
"token_acc": 0.9954447374730281
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.72,
|
| 1046 |
+
"grad_norm": 1.0625,
|
| 1047 |
+
"learning_rate": 1.010482589146048e-06,
|
| 1048 |
+
"loss": 0.009403180330991745,
|
| 1049 |
+
"step": 1290,
|
| 1050 |
+
"token_acc": 0.9964251668255482
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.7333333333333334,
|
| 1054 |
+
"grad_norm": 1.3359375,
|
| 1055 |
+
"learning_rate": 9.180033709213454e-07,
|
| 1056 |
+
"loss": 0.010034725069999695,
|
| 1057 |
+
"step": 1300,
|
| 1058 |
+
"token_acc": 0.997114691031498
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.7466666666666666,
|
| 1062 |
+
"grad_norm": 1.3671875,
|
| 1063 |
+
"learning_rate": 8.297580295566576e-07,
|
| 1064 |
+
"loss": 0.009973371028900146,
|
| 1065 |
+
"step": 1310,
|
| 1066 |
+
"token_acc": 0.9968772519817439
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.76,
|
| 1070 |
+
"grad_norm": 0.359375,
|
| 1071 |
+
"learning_rate": 7.457877035729588e-07,
|
| 1072 |
+
"loss": 0.0062577612698078156,
|
| 1073 |
+
"step": 1320,
|
| 1074 |
+
"token_acc": 0.9978406909788867
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.7733333333333334,
|
| 1078 |
+
"grad_norm": 1.296875,
|
| 1079 |
+
"learning_rate": 6.661315385496426e-07,
|
| 1080 |
+
"loss": 0.010465647280216216,
|
| 1081 |
+
"step": 1330,
|
| 1082 |
+
"token_acc": 0.9971133028626413
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.7866666666666666,
|
| 1086 |
+
"grad_norm": 2.96875,
|
| 1087 |
+
"learning_rate": 5.908266688755049e-07,
|
| 1088 |
+
"loss": 0.012356024980545045,
|
| 1089 |
+
"step": 1340,
|
| 1090 |
+
"token_acc": 0.9951737451737451
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.8,
|
| 1094 |
+
"grad_norm": 0.98046875,
|
| 1095 |
+
"learning_rate": 5.199082004372958e-07,
|
| 1096 |
+
"loss": 0.009671059250831605,
|
| 1097 |
+
"step": 1350,
|
| 1098 |
+
"token_acc": 0.9966378482228626
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.8133333333333335,
|
| 1102 |
+
"grad_norm": 2.078125,
|
| 1103 |
+
"learning_rate": 4.534091942539476e-07,
|
| 1104 |
+
"loss": 0.008851684629917145,
|
| 1105 |
+
"step": 1360,
|
| 1106 |
+
"token_acc": 0.9968802495800336
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.8266666666666667,
|
| 1110 |
+
"grad_norm": 1.5625,
|
| 1111 |
+
"learning_rate": 3.913606510640644e-07,
|
| 1112 |
+
"loss": 0.008533693850040436,
|
| 1113 |
+
"step": 1370,
|
| 1114 |
+
"token_acc": 0.9966232513265798
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.8399999999999999,
|
| 1118 |
+
"grad_norm": 0.81640625,
|
| 1119 |
+
"learning_rate": 3.3379149687388866e-07,
|
| 1120 |
+
"loss": 0.010838476568460464,
|
| 1121 |
+
"step": 1380,
|
| 1122 |
+
"token_acc": 0.9959193470955353
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.8533333333333335,
|
| 1126 |
+
"grad_norm": 0.3515625,
|
| 1127 |
+
"learning_rate": 2.807285694724804e-07,
|
| 1128 |
+
"loss": 0.0096530020236969,
|
| 1129 |
+
"step": 1390,
|
| 1130 |
+
"token_acc": 0.9966442953020134
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.8666666666666667,
|
| 1134 |
+
"grad_norm": 1.9609375,
|
| 1135 |
+
"learning_rate": 2.3219660592038285e-07,
|
| 1136 |
+
"loss": 0.01174573004245758,
|
| 1137 |
+
"step": 1400,
|
| 1138 |
+
"token_acc": 0.9966346153846154
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.88,
|
| 1142 |
+
"grad_norm": 2.171875,
|
| 1143 |
+
"learning_rate": 1.8821823101760949e-07,
|
| 1144 |
+
"loss": 0.012217908352613448,
|
| 1145 |
+
"step": 1410,
|
| 1146 |
+
"token_acc": 0.9949555608935864
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.8933333333333333,
|
| 1150 |
+
"grad_norm": 0.4375,
|
| 1151 |
+
"learning_rate": 1.4881394675633543e-07,
|
| 1152 |
+
"loss": 0.007538451254367829,
|
| 1153 |
+
"step": 1420,
|
| 1154 |
+
"token_acc": 0.9978354978354979
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.9066666666666667,
|
| 1158 |
+
"grad_norm": 0.251953125,
|
| 1159 |
+
"learning_rate": 1.1400212276321377e-07,
|
| 1160 |
+
"loss": 0.005265282094478607,
|
| 1161 |
+
"step": 1430,
|
| 1162 |
+
"token_acc": 0.9976065102920058
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.92,
|
| 1166 |
+
"grad_norm": 2.34375,
|
| 1167 |
+
"learning_rate": 8.379898773574924e-08,
|
| 1168 |
+
"loss": 0.009292224794626236,
|
| 1169 |
+
"step": 1440,
|
| 1170 |
+
"token_acc": 0.9964046021093
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.9333333333333333,
|
| 1174 |
+
"grad_norm": 1.390625,
|
| 1175 |
+
"learning_rate": 5.821862187675775e-08,
|
| 1176 |
+
"loss": 0.009811708331108093,
|
| 1177 |
+
"step": 1450,
|
| 1178 |
+
"token_acc": 0.9966450994488377
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.9466666666666668,
|
| 1182 |
+
"grad_norm": 2.265625,
|
| 1183 |
+
"learning_rate": 3.727295033040035e-08,
|
| 1184 |
+
"loss": 0.00994875207543373,
|
| 1185 |
+
"step": 1460,
|
| 1186 |
+
"token_acc": 0.9966329966329966
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.96,
|
| 1190 |
+
"grad_norm": 2.734375,
|
| 1191 |
+
"learning_rate": 2.0971737622883515e-08,
|
| 1192 |
+
"loss": 0.009690174460411071,
|
| 1193 |
+
"step": 1470,
|
| 1194 |
+
"token_acc": 0.9963776865491427
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.9733333333333334,
|
| 1198 |
+
"grad_norm": 1.671875,
|
| 1199 |
+
"learning_rate": 9.322583110392692e-09,
|
| 1200 |
+
"loss": 0.00724238008260727,
|
| 1201 |
+
"step": 1480,
|
| 1202 |
+
"token_acc": 0.9978380975258228
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.9866666666666668,
|
| 1206 |
+
"grad_norm": 1.0234375,
|
| 1207 |
+
"learning_rate": 2.330917436402791e-09,
|
| 1208 |
+
"loss": 0.008754293620586395,
|
| 1209 |
+
"step": 1490,
|
| 1210 |
+
"token_acc": 0.9961492178098676
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.0,
|
| 1214 |
+
"grad_norm": 1.84375,
|
| 1215 |
+
"learning_rate": 0.0,
|
| 1216 |
+
"loss": 0.007110082358121872,
|
| 1217 |
+
"step": 1500,
|
| 1218 |
+
"token_acc": 0.997303260603089
|
| 1219 |
+
}
|
| 1220 |
+
],
|
| 1221 |
+
"logging_steps": 10,
|
| 1222 |
+
"max_steps": 1500,
|
| 1223 |
+
"num_input_tokens_seen": 0,
|
| 1224 |
+
"num_train_epochs": 2,
|
| 1225 |
+
"save_steps": 500,
|
| 1226 |
+
"stateful_callbacks": {
|
| 1227 |
+
"TrainerControl": {
|
| 1228 |
+
"args": {
|
| 1229 |
+
"should_epoch_stop": false,
|
| 1230 |
+
"should_evaluate": false,
|
| 1231 |
+
"should_log": false,
|
| 1232 |
+
"should_save": true,
|
| 1233 |
+
"should_training_stop": true
|
| 1234 |
+
},
|
| 1235 |
+
"attributes": {}
|
| 1236 |
+
}
|
| 1237 |
+
},
|
| 1238 |
+
"total_flos": 6.111061190492815e+17,
|
| 1239 |
+
"train_batch_size": 8,
|
| 1240 |
+
"trial_name": null,
|
| 1241 |
+
"trial_params": null
|
| 1242 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06ce2aa39746d0e81f2d1ef996d3c279d6be89ddc99cd768fd9388df5406db7a
|
| 3 |
+
size 7313
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|