Hugging Face's logo

zjunlp
/
LightThinker-Plus-Llama

Safetensors
llama
Model card Files
xet
 Community
Yukirsh commited on
Commit
b996f58
·
verified ·
1 Parent(s): ca09bc6

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. args.json +387 -0
  3. chat_template.jinja +1 -0
  4. config.json +36 -0
  5. generation_config.json +9 -0
  6. model-00001-of-00004.safetensors +3 -0
  7. model-00002-of-00004.safetensors +3 -0
  8. model-00003-of-00004.safetensors +3 -0
  9. model-00004-of-00004.safetensors +3 -0
  10. model.safetensors.index.json +299 -0
  11. special_tokens_map.json +23 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +2066 -0
  14. trainer_state.json +1954 -0
  15. training_args.bin +3 -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
args.json ADDED
@@ -0,0 +1,387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "LightThinker-Plus-Llama",
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": 4,
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": 5.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "LightThinker-Plus-Llama/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": 3,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
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": null,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "LightThinker-Plus-Llama",
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": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "tensorboard"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": true,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": true,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": null,
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "use_ray": false,
206
+ "ray_exp_name": null,
207
+ "device_groups": null,
208
+ "model": "/MODELS/DeepSeek-R1-Distill-Llama-8B",
209
+ "model_type": "deepseek_r1_distill",
210
+ "model_revision": null,
211
+ "task_type": "causal_lm",
212
+ "torch_dtype": "bfloat16",
213
+ "attn_impl": "flash_attn",
214
+ "new_special_tokens": [],
215
+ "num_labels": null,
216
+ "problem_type": null,
217
+ "rope_scaling": null,
218
+ "device_map": null,
219
+ "max_memory": {},
220
+ "max_model_len": null,
221
+ "local_repo_path": null,
222
+ "init_strategy": null,
223
+ "template": "deepseek_r1",
224
+ "system": null,
225
+ "max_length": 16384,
226
+ "truncation_strategy": "delete",
227
+ "max_pixels": null,
228
+ "agent_template": null,
229
+ "norm_bbox": null,
230
+ "use_chat_template": true,
231
+ "padding_free": true,
232
+ "padding_side": "right",
233
+ "loss_scale": "default",
234
+ "sequence_parallel_size": 1,
235
+ "response_prefix": null,
236
+ "template_backend": "swift",
237
+ "dataset": [
238
+ "train_ltthinker.json"
239
+ ],
240
+ "val_dataset": [],
241
+ "cached_dataset": [],
242
+ "cached_val_dataset": [],
243
+ "split_dataset_ratio": 0.0,
244
+ "dataset_num_proc": 8,
245
+ "load_from_cache_file": false,
246
+ "dataset_shuffle": true,
247
+ "val_dataset_shuffle": false,
248
+ "streaming": false,
249
+ "interleave_prob": null,
250
+ "stopping_strategy": "first_exhausted",
251
+ "shuffle_buffer_size": 1000,
252
+ "download_mode": "reuse_dataset_if_exists",
253
+ "columns": {},
254
+ "strict": false,
255
+ "model_name": null,
256
+ "model_author": null,
257
+ "custom_dataset_info": [],
258
+ "quant_method": null,
259
+ "quant_bits": null,
260
+ "hqq_axis": null,
261
+ "bnb_4bit_compute_dtype": "bfloat16",
262
+ "bnb_4bit_quant_type": "nf4",
263
+ "bnb_4bit_use_double_quant": true,
264
+ "bnb_4bit_quant_storage": null,
265
+ "max_new_tokens": 64,
266
+ "temperature": 0.0,
267
+ "top_k": null,
268
+ "top_p": null,
269
+ "repetition_penalty": null,
270
+ "num_beams": 1,
271
+ "stream": false,
272
+ "stop_words": [],
273
+ "logprobs": false,
274
+ "top_logprobs": null,
275
+ "ckpt_dir": null,
276
+ "lora_modules": [],
277
+ "train_type": "full",
278
+ "adapters": [],
279
+ "external_plugins": [],
280
+ "model_kwargs": {},
281
+ "load_args": false,
282
+ "load_data_args": false,
283
+ "packing": true,
284
+ "packing_length": 16384,
285
+ "packing_num_proc": 1,
286
+ "lazy_tokenize": false,
287
+ "custom_register_path": [],
288
+ "use_hf": false,
289
+ "ignore_args_error": false,
290
+ "use_swift_lora": false,
291
+ "freeze_parameters": [],
292
+ "freeze_parameters_regex": null,
293
+ "freeze_parameters_ratio": 0.0,
294
+ "trainable_parameters": [],
295
+ "trainable_parameters_regex": null,
296
+ "freeze_llm": false,
297
+ "freeze_vit": true,
298
+ "freeze_aligner": true,
299
+ "target_modules": [
300
+ "all-linear"
301
+ ],
302
+ "target_regex": null,
303
+ "target_parameters": null,
304
+ "modules_to_save": [],
305
+ "lora_rank": 8,
306
+ "lora_alpha": 32,
307
+ "lora_dropout": 0.05,
308
+ "lora_bias": "none",
309
+ "lora_dtype": null,
310
+ "lorap_lr_ratio": null,
311
+ "use_rslora": false,
312
+ "use_dora": false,
313
+ "lora_ga_batch_size": 2,
314
+ "lora_ga_iters": 2,
315
+ "lora_ga_max_length": 1024,
316
+ "lora_ga_direction": "ArB2r",
317
+ "lora_ga_scale": "stable",
318
+ "lora_ga_stable_gamma": 16,
319
+ "init_weights": true,
320
+ "fourier_n_frequency": 2000,
321
+ "fourier_scaling": 300.0,
322
+ "boft_block_size": 4,
323
+ "boft_block_num": 0,
324
+ "boft_n_butterfly_factor": 1,
325
+ "boft_dropout": 0.0,
326
+ "vera_rank": 256,
327
+ "vera_projection_prng_key": 0,
328
+ "vera_dropout": 0.0,
329
+ "vera_d_initial": 0.1,
330
+ "adapter_act": "gelu",
331
+ "adapter_length": 128,
332
+ "use_galore": false,
333
+ "galore_target_modules": null,
334
+ "galore_rank": 128,
335
+ "galore_update_proj_gap": 50,
336
+ "galore_scale": 1.0,
337
+ "galore_proj_type": "std",
338
+ "galore_optim_per_parameter": false,
339
+ "galore_with_embedding": false,
340
+ "galore_quantization": false,
341
+ "galore_proj_quant": false,
342
+ "galore_proj_bits": 4,
343
+ "galore_proj_group_size": 256,
344
+ "galore_cos_threshold": 0.4,
345
+ "galore_gamma_proj": 2,
346
+ "galore_queue_size": 5,
347
+ "adalora_target_r": 8,
348
+ "adalora_init_r": 12,
349
+ "adalora_tinit": 0,
350
+ "adalora_tfinal": 0,
351
+ "adalora_deltaT": 1,
352
+ "adalora_beta1": 0.85,
353
+ "adalora_beta2": 0.85,
354
+ "adalora_orth_reg_weight": 0.5,
355
+ "llamapro_num_new_blocks": 4,
356
+ "llamapro_num_groups": null,
357
+ "lisa_activated_layers": 0,
358
+ "lisa_step_interval": 20,
359
+ "reft_layer_key": null,
360
+ "reft_layers": null,
361
+ "reft_rank": 4,
362
+ "reft_intervention_type": "LoreftIntervention",
363
+ "reft_args": null,
364
+ "swanlab_token": null,
365
+ "swanlab_project": null,
366
+ "swanlab_workspace": null,
367
+ "swanlab_exp_name": null,
368
+ "swanlab_lark_webhook_url": null,
369
+ "swanlab_lark_secret": null,
370
+ "swanlab_mode": "cloud",
371
+ "add_version": true,
372
+ "create_checkpoint_symlink": false,
373
+ "zero_hpz_partition_size": null,
374
+ "deepspeed_autotp_size": null,
375
+ "early_stop_interval": null,
376
+ "rank": 0,
377
+ "global_world_size": 8,
378
+ "local_world_size": 8,
379
+ "model_suffix": "DeepSeek-R1-Distill-Llama-8B",
380
+ "model_info": "ModelInfo(model_type='deepseek_r1_distill', model_dir='/MODELS/DeepSeek-R1-Distill-Llama-8B', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling={'factor': 8.0, 'low_freq_factor': 1.0, 'high_freq_factor': 4.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
381
+ "model_meta": "ModelMeta(model_type='deepseek_r1_distill', model_groups=[ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='iic/QwenLong-L1-32B', hf_model_id='Tongyi-Zhiwen/QwenLong-L1-32B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=['transformers>=4.37'], tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', model_path=None, ms_revision=None, hf_revision=None)], 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)], ignore_patterns=None, requires=None, tags=[])], template='deepseek_r1', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fdfb74bb250>, 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=['Qwen2ForCausalLM', 'LlamaForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
382
+ "model_dir": "/MODELS/DeepSeek-R1-Distill-Llama-8B",
383
+ "_val_dataset_exists": [],
384
+ "hub": "<class 'swift.hub.hub.MSHub'>",
385
+ "evaluation_strategy": "epoch",
386
+ "training_args": "xxxx"
387
+ }
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128001,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "4.57.0.dev0",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.57.0.dev0"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076ffec7c6def517ad77046ec3fce0508f5975a22ea53e391091515fad128f04
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f9a64aa4e64fdeb7cf64ec496c73f36fdee6166513609d68fceed0330e8d08
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6addd36d571b7996d70d5069408c74f4ceecc0c1d2c0b4a111d993e5a2f7df7d
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9a426cb1ed0203b0a4a966b96df63de3d6d46ae0b97b56f011824795c91e1a
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 266240,
4
+ "total_size": 16060522496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.norm.weight": "model-00004-of-00004.safetensors"
298
+ }
299
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "128000": {
7
+ "content": "<｜begin▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "128001": {
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "128002": {
23
+ "content": "<|reserved_special_token_0|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "128003": {
31
+ "content": "<|reserved_special_token_1|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "128004": {
39
+ "content": "<|finetune_right_pad_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "128005": {
47
+ "content": "<|reserved_special_token_2|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "128006": {
55
+ "content": "<|start_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "128007": {
63
+ "content": "<|end_header_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "128008": {
71
+ "content": "<|eom_id|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "128009": {
79
+ "content": "<|eot_id|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "128010": {
87
+ "content": "<|python_tag|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "128011": {
95
+ "content": "<｜User｜>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "128012": {
103
+ "content": "<｜Assistant｜>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "128013": {
111
+ "content": "<think>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "128014": {
119
+ "content": "</think>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "128015": {
127
+ "content": "<｜▁pad▁｜>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "128016": {
135
+ "content": "<|reserved_special_token_8|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "128017": {
143
+ "content": "<|reserved_special_token_9|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "128018": {
151
+ "content": "<|reserved_special_token_10|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "128019": {
159
+ "content": "<|reserved_special_token_11|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "128020": {
167
+ "content": "<|reserved_special_token_12|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "128021": {
175
+ "content": "<|reserved_special_token_13|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "128022": {
183
+ "content": "<|reserved_special_token_14|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "128023": {
191
+ "content": "<|reserved_special_token_15|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "128024": {
199
+ "content": "<|reserved_special_token_16|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "128025": {
207
+ "content": "<|reserved_special_token_17|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "128026": {
215
+ "content": "<|reserved_special_token_18|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "128027": {
223
+ "content": "<|reserved_special_token_19|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "128028": {
231
+ "content": "<|reserved_special_token_20|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "128029": {
239
+ "content": "<|reserved_special_token_21|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "128030": {
247
+ "content": "<|reserved_special_token_22|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "128031": {
255
+ "content": "<|reserved_special_token_23|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "128032": {
263
+ "content": "<|reserved_special_token_24|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "128033": {
271
+ "content": "<|reserved_special_token_25|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "128034": {
279
+ "content": "<|reserved_special_token_26|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "128035": {
287
+ "content": "<|reserved_special_token_27|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "128036": {
295
+ "content": "<|reserved_special_token_28|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "128037": {
303
+ "content": "<|reserved_special_token_29|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "128038": {
311
+ "content": "<|reserved_special_token_30|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "128039": {
319
+ "content": "<|reserved_special_token_31|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "128040": {
327
+ "content": "<|reserved_special_token_32|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "128041": {
335
+ "content": "<|reserved_special_token_33|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "128042": {
343
+ "content": "<|reserved_special_token_34|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "128043": {
351
+ "content": "<|reserved_special_token_35|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "128044": {
359
+ "content": "<|reserved_special_token_36|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "128045": {
367
+ "content": "<|reserved_special_token_37|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "128046": {
375
+ "content": "<|reserved_special_token_38|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "128047": {
383
+ "content": "<|reserved_special_token_39|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "128048": {
391
+ "content": "<|reserved_special_token_40|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "128049": {
399
+ "content": "<|reserved_special_token_41|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "128050": {
407
+ "content": "<|reserved_special_token_42|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "128051": {
415
+ "content": "<|reserved_special_token_43|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "128052": {
423
+ "content": "<|reserved_special_token_44|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "128053": {
431
+ "content": "<|reserved_special_token_45|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "128054": {
439
+ "content": "<|reserved_special_token_46|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "128055": {
447
+ "content": "<|reserved_special_token_47|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "128056": {
455
+ "content": "<|reserved_special_token_48|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "128057": {
463
+ "content": "<|reserved_special_token_49|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "128058": {
471
+ "content": "<|reserved_special_token_50|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "128059": {
479
+ "content": "<|reserved_special_token_51|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "128060": {
487
+ "content": "<|reserved_special_token_52|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "128061": {
495
+ "content": "<|reserved_special_token_53|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "128062": {
503
+ "content": "<|reserved_special_token_54|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "128063": {
511
+ "content": "<|reserved_special_token_55|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "128064": {
519
+ "content": "<|reserved_special_token_56|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "128065": {
527
+ "content": "<|reserved_special_token_57|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "128066": {
535
+ "content": "<|reserved_special_token_58|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "128067": {
543
+ "content": "<|reserved_special_token_59|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "128068": {
551
+ "content": "<|reserved_special_token_60|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "128069": {
559
+ "content": "<|reserved_special_token_61|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "128070": {
567
+ "content": "<|reserved_special_token_62|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "128071": {
575
+ "content": "<|reserved_special_token_63|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "128072": {
583
+ "content": "<|reserved_special_token_64|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "128073": {
591
+ "content": "<|reserved_special_token_65|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "128074": {
599
+ "content": "<|reserved_special_token_66|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "128075": {
607
+ "content": "<|reserved_special_token_67|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "128076": {
615
+ "content": "<|reserved_special_token_68|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "128077": {
623
+ "content": "<|reserved_special_token_69|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "128078": {
631
+ "content": "<|reserved_special_token_70|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "128079": {
639
+ "content": "<|reserved_special_token_71|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "128080": {
647
+ "content": "<|reserved_special_token_72|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "128081": {
655
+ "content": "<|reserved_special_token_73|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "128082": {
663
+ "content": "<|reserved_special_token_74|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "128083": {
671
+ "content": "<|reserved_special_token_75|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "128084": {
679
+ "content": "<|reserved_special_token_76|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "128085": {
687
+ "content": "<|reserved_special_token_77|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "128086": {
695
+ "content": "<|reserved_special_token_78|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "128087": {
703
+ "content": "<|reserved_special_token_79|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "128088": {
711
+ "content": "<|reserved_special_token_80|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "128089": {
719
+ "content": "<|reserved_special_token_81|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "128090": {
727
+ "content": "<|reserved_special_token_82|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "128091": {
735
+ "content": "<|reserved_special_token_83|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "128092": {
743
+ "content": "<|reserved_special_token_84|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "128093": {
751
+ "content": "<|reserved_special_token_85|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "128094": {
759
+ "content": "<|reserved_special_token_86|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "128095": {
767
+ "content": "<|reserved_special_token_87|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "128096": {
775
+ "content": "<|reserved_special_token_88|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "128097": {
783
+ "content": "<|reserved_special_token_89|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "128098": {
791
+ "content": "<|reserved_special_token_90|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "128099": {
799
+ "content": "<|reserved_special_token_91|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "128100": {
807
+ "content": "<|reserved_special_token_92|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "128101": {
815
+ "content": "<|reserved_special_token_93|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "128102": {
823
+ "content": "<|reserved_special_token_94|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "128103": {
831
+ "content": "<|reserved_special_token_95|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "128104": {
839
+ "content": "<|reserved_special_token_96|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "128105": {
847
+ "content": "<|reserved_special_token_97|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "128106": {
855
+ "content": "<|reserved_special_token_98|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "128107": {
863
+ "content": "<|reserved_special_token_99|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "128108": {
871
+ "content": "<|reserved_special_token_100|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "128109": {
879
+ "content": "<|reserved_special_token_101|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "128110": {
887
+ "content": "<|reserved_special_token_102|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "128111": {
895
+ "content": "<|reserved_special_token_103|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "128112": {
903
+ "content": "<|reserved_special_token_104|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "128113": {
911
+ "content": "<|reserved_special_token_105|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "128114": {
919
+ "content": "<|reserved_special_token_106|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "128115": {
927
+ "content": "<|reserved_special_token_107|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "128116": {
935
+ "content": "<|reserved_special_token_108|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "128117": {
943
+ "content": "<|reserved_special_token_109|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "128118": {
951
+ "content": "<|reserved_special_token_110|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "128119": {
959
+ "content": "<|reserved_special_token_111|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "128120": {
967
+ "content": "<|reserved_special_token_112|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "128121": {
975
+ "content": "<|reserved_special_token_113|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "128122": {
983
+ "content": "<|reserved_special_token_114|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "128123": {
991
+ "content": "<|reserved_special_token_115|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "128124": {
999
+ "content": "<|reserved_special_token_116|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "128125": {
1007
+ "content": "<|reserved_special_token_117|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "128126": {
1015
+ "content": "<|reserved_special_token_118|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "128127": {
1023
+ "content": "<|reserved_special_token_119|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "128128": {
1031
+ "content": "<|reserved_special_token_120|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "128129": {
1039
+ "content": "<|reserved_special_token_121|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "128130": {
1047
+ "content": "<|reserved_special_token_122|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ },
1054
+ "128131": {
1055
+ "content": "<|reserved_special_token_123|>",
1056
+ "lstrip": false,
1057
+ "normalized": false,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": true
1061
+ },
1062
+ "128132": {
1063
+ "content": "<|reserved_special_token_124|>",
1064
+ "lstrip": false,
1065
+ "normalized": false,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": true
1069
+ },
1070
+ "128133": {
1071
+ "content": "<|reserved_special_token_125|>",
1072
+ "lstrip": false,
1073
+ "normalized": false,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": true
1077
+ },
1078
+ "128134": {
1079
+ "content": "<|reserved_special_token_126|>",
1080
+ "lstrip": false,
1081
+ "normalized": false,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": true
1085
+ },
1086
+ "128135": {
1087
+ "content": "<|reserved_special_token_127|>",
1088
+ "lstrip": false,
1089
+ "normalized": false,
1090
+ "rstrip": false,
1091
+ "single_word": false,
1092
+ "special": true
1093
+ },
1094
+ "128136": {
1095
+ "content": "<|reserved_special_token_128|>",
1096
+ "lstrip": false,
1097
+ "normalized": false,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": true
1101
+ },
1102
+ "128137": {
1103
+ "content": "<|reserved_special_token_129|>",
1104
+ "lstrip": false,
1105
+ "normalized": false,
1106
+ "rstrip": false,
1107
+ "single_word": false,
1108
+ "special": true
1109
+ },
1110
+ "128138": {
1111
+ "content": "<|reserved_special_token_130|>",
1112
+ "lstrip": false,
1113
+ "normalized": false,
1114
+ "rstrip": false,
1115
+ "single_word": false,
1116
+ "special": true
1117
+ },
1118
+ "128139": {
1119
+ "content": "<|reserved_special_token_131|>",
1120
+ "lstrip": false,
1121
+ "normalized": false,
1122
+ "rstrip": false,
1123
+ "single_word": false,
1124
+ "special": true
1125
+ },
1126
+ "128140": {
1127
+ "content": "<|reserved_special_token_132|>",
1128
+ "lstrip": false,
1129
+ "normalized": false,
1130
+ "rstrip": false,
1131
+ "single_word": false,
1132
+ "special": true
1133
+ },
1134
+ "128141": {
1135
+ "content": "<|reserved_special_token_133|>",
1136
+ "lstrip": false,
1137
+ "normalized": false,
1138
+ "rstrip": false,
1139
+ "single_word": false,
1140
+ "special": true
1141
+ },
1142
+ "128142": {
1143
+ "content": "<|reserved_special_token_134|>",
1144
+ "lstrip": false,
1145
+ "normalized": false,
1146
+ "rstrip": false,
1147
+ "single_word": false,
1148
+ "special": true
1149
+ },
1150
+ "128143": {
1151
+ "content": "<|reserved_special_token_135|>",
1152
+ "lstrip": false,
1153
+ "normalized": false,
1154
+ "rstrip": false,
1155
+ "single_word": false,
1156
+ "special": true
1157
+ },
1158
+ "128144": {
1159
+ "content": "<|reserved_special_token_136|>",
1160
+ "lstrip": false,
1161
+ "normalized": false,
1162
+ "rstrip": false,
1163
+ "single_word": false,
1164
+ "special": true
1165
+ },
1166
+ "128145": {
1167
+ "content": "<|reserved_special_token_137|>",
1168
+ "lstrip": false,
1169
+ "normalized": false,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": true
1173
+ },
1174
+ "128146": {
1175
+ "content": "<|reserved_special_token_138|>",
1176
+ "lstrip": false,
1177
+ "normalized": false,
1178
+ "rstrip": false,
1179
+ "single_word": false,
1180
+ "special": true
1181
+ },
1182
+ "128147": {
1183
+ "content": "<|reserved_special_token_139|>",
1184
+ "lstrip": false,
1185
+ "normalized": false,
1186
+ "rstrip": false,
1187
+ "single_word": false,
1188
+ "special": true
1189
+ },
1190
+ "128148": {
1191
+ "content": "<|reserved_special_token_140|>",
1192
+ "lstrip": false,
1193
+ "normalized": false,
1194
+ "rstrip": false,
1195
+ "single_word": false,
1196
+ "special": true
1197
+ },
1198
+ "128149": {
1199
+ "content": "<|reserved_special_token_141|>",
1200
+ "lstrip": false,
1201
+ "normalized": false,
1202
+ "rstrip": false,
1203
+ "single_word": false,
1204
+ "special": true
1205
+ },
1206
+ "128150": {
1207
+ "content": "<|reserved_special_token_142|>",
1208
+ "lstrip": false,
1209
+ "normalized": false,
1210
+ "rstrip": false,
1211
+ "single_word": false,
1212
+ "special": true
1213
+ },
1214
+ "128151": {
1215
+ "content": "<|reserved_special_token_143|>",
1216
+ "lstrip": false,
1217
+ "normalized": false,
1218
+ "rstrip": false,
1219
+ "single_word": false,
1220
+ "special": true
1221
+ },
1222
+ "128152": {
1223
+ "content": "<|reserved_special_token_144|>",
1224
+ "lstrip": false,
1225
+ "normalized": false,
1226
+ "rstrip": false,
1227
+ "single_word": false,
1228
+ "special": true
1229
+ },
1230
+ "128153": {
1231
+ "content": "<|reserved_special_token_145|>",
1232
+ "lstrip": false,
1233
+ "normalized": false,
1234
+ "rstrip": false,
1235
+ "single_word": false,
1236
+ "special": true
1237
+ },
1238
+ "128154": {
1239
+ "content": "<|reserved_special_token_146|>",
1240
+ "lstrip": false,
1241
+ "normalized": false,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": true
1245
+ },
1246
+ "128155": {
1247
+ "content": "<|reserved_special_token_147|>",
1248
+ "lstrip": false,
1249
+ "normalized": false,
1250
+ "rstrip": false,
1251
+ "single_word": false,
1252
+ "special": true
1253
+ },
1254
+ "128156": {
1255
+ "content": "<|reserved_special_token_148|>",
1256
+ "lstrip": false,
1257
+ "normalized": false,
1258
+ "rstrip": false,
1259
+ "single_word": false,
1260
+ "special": true
1261
+ },
1262
+ "128157": {
1263
+ "content": "<|reserved_special_token_149|>",
1264
+ "lstrip": false,
1265
+ "normalized": false,
1266
+ "rstrip": false,
1267
+ "single_word": false,
1268
+ "special": true
1269
+ },
1270
+ "128158": {
1271
+ "content": "<|reserved_special_token_150|>",
1272
+ "lstrip": false,
1273
+ "normalized": false,
1274
+ "rstrip": false,
1275
+ "single_word": false,
1276
+ "special": true
1277
+ },
1278
+ "128159": {
1279
+ "content": "<|reserved_special_token_151|>",
1280
+ "lstrip": false,
1281
+ "normalized": false,
1282
+ "rstrip": false,
1283
+ "single_word": false,
1284
+ "special": true
1285
+ },
1286
+ "128160": {
1287
+ "content": "<|reserved_special_token_152|>",
1288
+ "lstrip": false,
1289
+ "normalized": false,
1290
+ "rstrip": false,
1291
+ "single_word": false,
1292
+ "special": true
1293
+ },
1294
+ "128161": {
1295
+ "content": "<|reserved_special_token_153|>",
1296
+ "lstrip": false,
1297
+ "normalized": false,
1298
+ "rstrip": false,
1299
+ "single_word": false,
1300
+ "special": true
1301
+ },
1302
+ "128162": {
1303
+ "content": "<|reserved_special_token_154|>",
1304
+ "lstrip": false,
1305
+ "normalized": false,
1306
+ "rstrip": false,
1307
+ "single_word": false,
1308
+ "special": true
1309
+ },
1310
+ "128163": {
1311
+ "content": "<|reserved_special_token_155|>",
1312
+ "lstrip": false,
1313
+ "normalized": false,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": true
1317
+ },
1318
+ "128164": {
1319
+ "content": "<|reserved_special_token_156|>",
1320
+ "lstrip": false,
1321
+ "normalized": false,
1322
+ "rstrip": false,
1323
+ "single_word": false,
1324
+ "special": true
1325
+ },
1326
+ "128165": {
1327
+ "content": "<|reserved_special_token_157|>",
1328
+ "lstrip": false,
1329
+ "normalized": false,
1330
+ "rstrip": false,
1331
+ "single_word": false,
1332
+ "special": true
1333
+ },
1334
+ "128166": {
1335
+ "content": "<|reserved_special_token_158|>",
1336
+ "lstrip": false,
1337
+ "normalized": false,
1338
+ "rstrip": false,
1339
+ "single_word": false,
1340
+ "special": true
1341
+ },
1342
+ "128167": {
1343
+ "content": "<|reserved_special_token_159|>",
1344
+ "lstrip": false,
1345
+ "normalized": false,
1346
+ "rstrip": false,
1347
+ "single_word": false,
1348
+ "special": true
1349
+ },
1350
+ "128168": {
1351
+ "content": "<|reserved_special_token_160|>",
1352
+ "lstrip": false,
1353
+ "normalized": false,
1354
+ "rstrip": false,
1355
+ "single_word": false,
1356
+ "special": true
1357
+ },
1358
+ "128169": {
1359
+ "content": "<|reserved_special_token_161|>",
1360
+ "lstrip": false,
1361
+ "normalized": false,
1362
+ "rstrip": false,
1363
+ "single_word": false,
1364
+ "special": true
1365
+ },
1366
+ "128170": {
1367
+ "content": "<|reserved_special_token_162|>",
1368
+ "lstrip": false,
1369
+ "normalized": false,
1370
+ "rstrip": false,
1371
+ "single_word": false,
1372
+ "special": true
1373
+ },
1374
+ "128171": {
1375
+ "content": "<|reserved_special_token_163|>",
1376
+ "lstrip": false,
1377
+ "normalized": false,
1378
+ "rstrip": false,
1379
+ "single_word": false,
1380
+ "special": true
1381
+ },
1382
+ "128172": {
1383
+ "content": "<|reserved_special_token_164|>",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": true
1389
+ },
1390
+ "128173": {
1391
+ "content": "<|reserved_special_token_165|>",
1392
+ "lstrip": false,
1393
+ "normalized": false,
1394
+ "rstrip": false,
1395
+ "single_word": false,
1396
+ "special": true
1397
+ },
1398
+ "128174": {
1399
+ "content": "<|reserved_special_token_166|>",
1400
+ "lstrip": false,
1401
+ "normalized": false,
1402
+ "rstrip": false,
1403
+ "single_word": false,
1404
+ "special": true
1405
+ },
1406
+ "128175": {
1407
+ "content": "<|reserved_special_token_167|>",
1408
+ "lstrip": false,
1409
+ "normalized": false,
1410
+ "rstrip": false,
1411
+ "single_word": false,
1412
+ "special": true
1413
+ },
1414
+ "128176": {
1415
+ "content": "<|reserved_special_token_168|>",
1416
+ "lstrip": false,
1417
+ "normalized": false,
1418
+ "rstrip": false,
1419
+ "single_word": false,
1420
+ "special": true
1421
+ },
1422
+ "128177": {
1423
+ "content": "<|reserved_special_token_169|>",
1424
+ "lstrip": false,
1425
+ "normalized": false,
1426
+ "rstrip": false,
1427
+ "single_word": false,
1428
+ "special": true
1429
+ },
1430
+ "128178": {
1431
+ "content": "<|reserved_special_token_170|>",
1432
+ "lstrip": false,
1433
+ "normalized": false,
1434
+ "rstrip": false,
1435
+ "single_word": false,
1436
+ "special": true
1437
+ },
1438
+ "128179": {
1439
+ "content": "<|reserved_special_token_171|>",
1440
+ "lstrip": false,
1441
+ "normalized": false,
1442
+ "rstrip": false,
1443
+ "single_word": false,
1444
+ "special": true
1445
+ },
1446
+ "128180": {
1447
+ "content": "<|reserved_special_token_172|>",
1448
+ "lstrip": false,
1449
+ "normalized": false,
1450
+ "rstrip": false,
1451
+ "single_word": false,
1452
+ "special": true
1453
+ },
1454
+ "128181": {
1455
+ "content": "<|reserved_special_token_173|>",
1456
+ "lstrip": false,
1457
+ "normalized": false,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": true
1461
+ },
1462
+ "128182": {
1463
+ "content": "<|reserved_special_token_174|>",
1464
+ "lstrip": false,
1465
+ "normalized": false,
1466
+ "rstrip": false,
1467
+ "single_word": false,
1468
+ "special": true
1469
+ },
1470
+ "128183": {
1471
+ "content": "<|reserved_special_token_175|>",
1472
+ "lstrip": false,
1473
+ "normalized": false,
1474
+ "rstrip": false,
1475
+ "single_word": false,
1476
+ "special": true
1477
+ },
1478
+ "128184": {
1479
+ "content": "<|reserved_special_token_176|>",
1480
+ "lstrip": false,
1481
+ "normalized": false,
1482
+ "rstrip": false,
1483
+ "single_word": false,
1484
+ "special": true
1485
+ },
1486
+ "128185": {
1487
+ "content": "<|reserved_special_token_177|>",
1488
+ "lstrip": false,
1489
+ "normalized": false,
1490
+ "rstrip": false,
1491
+ "single_word": false,
1492
+ "special": true
1493
+ },
1494
+ "128186": {
1495
+ "content": "<|reserved_special_token_178|>",
1496
+ "lstrip": false,
1497
+ "normalized": false,
1498
+ "rstrip": false,
1499
+ "single_word": false,
1500
+ "special": true
1501
+ },
1502
+ "128187": {
1503
+ "content": "<|reserved_special_token_179|>",
1504
+ "lstrip": false,
1505
+ "normalized": false,
1506
+ "rstrip": false,
1507
+ "single_word": false,
1508
+ "special": true
1509
+ },
1510
+ "128188": {
1511
+ "content": "<|reserved_special_token_180|>",
1512
+ "lstrip": false,
1513
+ "normalized": false,
1514
+ "rstrip": false,
1515
+ "single_word": false,
1516
+ "special": true
1517
+ },
1518
+ "128189": {
1519
+ "content": "<|reserved_special_token_181|>",
1520
+ "lstrip": false,
1521
+ "normalized": false,
1522
+ "rstrip": false,
1523
+ "single_word": false,
1524
+ "special": true
1525
+ },
1526
+ "128190": {
1527
+ "content": "<|reserved_special_token_182|>",
1528
+ "lstrip": false,
1529
+ "normalized": false,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": true
1533
+ },
1534
+ "128191": {
1535
+ "content": "<|reserved_special_token_183|>",
1536
+ "lstrip": false,
1537
+ "normalized": false,
1538
+ "rstrip": false,
1539
+ "single_word": false,
1540
+ "special": true
1541
+ },
1542
+ "128192": {
1543
+ "content": "<|reserved_special_token_184|>",
1544
+ "lstrip": false,
1545
+ "normalized": false,
1546
+ "rstrip": false,
1547
+ "single_word": false,
1548
+ "special": true
1549
+ },
1550
+ "128193": {
1551
+ "content": "<|reserved_special_token_185|>",
1552
+ "lstrip": false,
1553
+ "normalized": false,
1554
+ "rstrip": false,
1555
+ "single_word": false,
1556
+ "special": true
1557
+ },
1558
+ "128194": {
1559
+ "content": "<|reserved_special_token_186|>",
1560
+ "lstrip": false,
1561
+ "normalized": false,
1562
+ "rstrip": false,
1563
+ "single_word": false,
1564
+ "special": true
1565
+ },
1566
+ "128195": {
1567
+ "content": "<|reserved_special_token_187|>",
1568
+ "lstrip": false,
1569
+ "normalized": false,
1570
+ "rstrip": false,
1571
+ "single_word": false,
1572
+ "special": true
1573
+ },
1574
+ "128196": {
1575
+ "content": "<|reserved_special_token_188|>",
1576
+ "lstrip": false,
1577
+ "normalized": false,
1578
+ "rstrip": false,
1579
+ "single_word": false,
1580
+ "special": true
1581
+ },
1582
+ "128197": {
1583
+ "content": "<|reserved_special_token_189|>",
1584
+ "lstrip": false,
1585
+ "normalized": false,
1586
+ "rstrip": false,
1587
+ "single_word": false,
1588
+ "special": true
1589
+ },
1590
+ "128198": {
1591
+ "content": "<|reserved_special_token_190|>",
1592
+ "lstrip": false,
1593
+ "normalized": false,
1594
+ "rstrip": false,
1595
+ "single_word": false,
1596
+ "special": true
1597
+ },
1598
+ "128199": {
1599
+ "content": "<|reserved_special_token_191|>",
1600
+ "lstrip": false,
1601
+ "normalized": false,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": true
1605
+ },
1606
+ "128200": {
1607
+ "content": "<|reserved_special_token_192|>",
1608
+ "lstrip": false,
1609
+ "normalized": false,
1610
+ "rstrip": false,
1611
+ "single_word": false,
1612
+ "special": true
1613
+ },
1614
+ "128201": {
1615
+ "content": "<|reserved_special_token_193|>",
1616
+ "lstrip": false,
1617
+ "normalized": false,
1618
+ "rstrip": false,
1619
+ "single_word": false,
1620
+ "special": true
1621
+ },
1622
+ "128202": {
1623
+ "content": "<|reserved_special_token_194|>",
1624
+ "lstrip": false,
1625
+ "normalized": false,
1626
+ "rstrip": false,
1627
+ "single_word": false,
1628
+ "special": true
1629
+ },
1630
+ "128203": {
1631
+ "content": "<|reserved_special_token_195|>",
1632
+ "lstrip": false,
1633
+ "normalized": false,
1634
+ "rstrip": false,
1635
+ "single_word": false,
1636
+ "special": true
1637
+ },
1638
+ "128204": {
1639
+ "content": "<|reserved_special_token_196|>",
1640
+ "lstrip": false,
1641
+ "normalized": false,
1642
+ "rstrip": false,
1643
+ "single_word": false,
1644
+ "special": true
1645
+ },
1646
+ "128205": {
1647
+ "content": "<|reserved_special_token_197|>",
1648
+ "lstrip": false,
1649
+ "normalized": false,
1650
+ "rstrip": false,
1651
+ "single_word": false,
1652
+ "special": true
1653
+ },
1654
+ "128206": {
1655
+ "content": "<|reserved_special_token_198|>",
1656
+ "lstrip": false,
1657
+ "normalized": false,
1658
+ "rstrip": false,
1659
+ "single_word": false,
1660
+ "special": true
1661
+ },
1662
+ "128207": {
1663
+ "content": "<|reserved_special_token_199|>",
1664
+ "lstrip": false,
1665
+ "normalized": false,
1666
+ "rstrip": false,
1667
+ "single_word": false,
1668
+ "special": true
1669
+ },
1670
+ "128208": {
1671
+ "content": "<|reserved_special_token_200|>",
1672
+ "lstrip": false,
1673
+ "normalized": false,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": true
1677
+ },
1678
+ "128209": {
1679
+ "content": "<|reserved_special_token_201|>",
1680
+ "lstrip": false,
1681
+ "normalized": false,
1682
+ "rstrip": false,
1683
+ "single_word": false,
1684
+ "special": true
1685
+ },
1686
+ "128210": {
1687
+ "content": "<|reserved_special_token_202|>",
1688
+ "lstrip": false,
1689
+ "normalized": false,
1690
+ "rstrip": false,
1691
+ "single_word": false,
1692
+ "special": true
1693
+ },
1694
+ "128211": {
1695
+ "content": "<|reserved_special_token_203|>",
1696
+ "lstrip": false,
1697
+ "normalized": false,
1698
+ "rstrip": false,
1699
+ "single_word": false,
1700
+ "special": true
1701
+ },
1702
+ "128212": {
1703
+ "content": "<|reserved_special_token_204|>",
1704
+ "lstrip": false,
1705
+ "normalized": false,
1706
+ "rstrip": false,
1707
+ "single_word": false,
1708
+ "special": true
1709
+ },
1710
+ "128213": {
1711
+ "content": "<|reserved_special_token_205|>",
1712
+ "lstrip": false,
1713
+ "normalized": false,
1714
+ "rstrip": false,
1715
+ "single_word": false,
1716
+ "special": true
1717
+ },
1718
+ "128214": {
1719
+ "content": "<|reserved_special_token_206|>",
1720
+ "lstrip": false,
1721
+ "normalized": false,
1722
+ "rstrip": false,
1723
+ "single_word": false,
1724
+ "special": true
1725
+ },
1726
+ "128215": {
1727
+ "content": "<|reserved_special_token_207|>",
1728
+ "lstrip": false,
1729
+ "normalized": false,
1730
+ "rstrip": false,
1731
+ "single_word": false,
1732
+ "special": true
1733
+ },
1734
+ "128216": {
1735
+ "content": "<|reserved_special_token_208|>",
1736
+ "lstrip": false,
1737
+ "normalized": false,
1738
+ "rstrip": false,
1739
+ "single_word": false,
1740
+ "special": true
1741
+ },
1742
+ "128217": {
1743
+ "content": "<|reserved_special_token_209|>",
1744
+ "lstrip": false,
1745
+ "normalized": false,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": true
1749
+ },
1750
+ "128218": {
1751
+ "content": "<|reserved_special_token_210|>",
1752
+ "lstrip": false,
1753
+ "normalized": false,
1754
+ "rstrip": false,
1755
+ "single_word": false,
1756
+ "special": true
1757
+ },
1758
+ "128219": {
1759
+ "content": "<|reserved_special_token_211|>",
1760
+ "lstrip": false,
1761
+ "normalized": false,
1762
+ "rstrip": false,
1763
+ "single_word": false,
1764
+ "special": true
1765
+ },
1766
+ "128220": {
1767
+ "content": "<|reserved_special_token_212|>",
1768
+ "lstrip": false,
1769
+ "normalized": false,
1770
+ "rstrip": false,
1771
+ "single_word": false,
1772
+ "special": true
1773
+ },
1774
+ "128221": {
1775
+ "content": "<|reserved_special_token_213|>",
1776
+ "lstrip": false,
1777
+ "normalized": false,
1778
+ "rstrip": false,
1779
+ "single_word": false,
1780
+ "special": true
1781
+ },
1782
+ "128222": {
1783
+ "content": "<|reserved_special_token_214|>",
1784
+ "lstrip": false,
1785
+ "normalized": false,
1786
+ "rstrip": false,
1787
+ "single_word": false,
1788
+ "special": true
1789
+ },
1790
+ "128223": {
1791
+ "content": "<|reserved_special_token_215|>",
1792
+ "lstrip": false,
1793
+ "normalized": false,
1794
+ "rstrip": false,
1795
+ "single_word": false,
1796
+ "special": true
1797
+ },
1798
+ "128224": {
1799
+ "content": "<|reserved_special_token_216|>",
1800
+ "lstrip": false,
1801
+ "normalized": false,
1802
+ "rstrip": false,
1803
+ "single_word": false,
1804
+ "special": true
1805
+ },
1806
+ "128225": {
1807
+ "content": "<|reserved_special_token_217|>",
1808
+ "lstrip": false,
1809
+ "normalized": false,
1810
+ "rstrip": false,
1811
+ "single_word": false,
1812
+ "special": true
1813
+ },
1814
+ "128226": {
1815
+ "content": "<|reserved_special_token_218|>",
1816
+ "lstrip": false,
1817
+ "normalized": false,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": true
1821
+ },
1822
+ "128227": {
1823
+ "content": "<|reserved_special_token_219|>",
1824
+ "lstrip": false,
1825
+ "normalized": false,
1826
+ "rstrip": false,
1827
+ "single_word": false,
1828
+ "special": true
1829
+ },
1830
+ "128228": {
1831
+ "content": "<|reserved_special_token_220|>",
1832
+ "lstrip": false,
1833
+ "normalized": false,
1834
+ "rstrip": false,
1835
+ "single_word": false,
1836
+ "special": true
1837
+ },
1838
+ "128229": {
1839
+ "content": "<|reserved_special_token_221|>",
1840
+ "lstrip": false,
1841
+ "normalized": false,
1842
+ "rstrip": false,
1843
+ "single_word": false,
1844
+ "special": true
1845
+ },
1846
+ "128230": {
1847
+ "content": "<|reserved_special_token_222|>",
1848
+ "lstrip": false,
1849
+ "normalized": false,
1850
+ "rstrip": false,
1851
+ "single_word": false,
1852
+ "special": true
1853
+ },
1854
+ "128231": {
1855
+ "content": "<|reserved_special_token_223|>",
1856
+ "lstrip": false,
1857
+ "normalized": false,
1858
+ "rstrip": false,
1859
+ "single_word": false,
1860
+ "special": true
1861
+ },
1862
+ "128232": {
1863
+ "content": "<|reserved_special_token_224|>",
1864
+ "lstrip": false,
1865
+ "normalized": false,
1866
+ "rstrip": false,
1867
+ "single_word": false,
1868
+ "special": true
1869
+ },
1870
+ "128233": {
1871
+ "content": "<|reserved_special_token_225|>",
1872
+ "lstrip": false,
1873
+ "normalized": false,
1874
+ "rstrip": false,
1875
+ "single_word": false,
1876
+ "special": true
1877
+ },
1878
+ "128234": {
1879
+ "content": "<|reserved_special_token_226|>",
1880
+ "lstrip": false,
1881
+ "normalized": false,
1882
+ "rstrip": false,
1883
+ "single_word": false,
1884
+ "special": true
1885
+ },
1886
+ "128235": {
1887
+ "content": "<|reserved_special_token_227|>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": true
1893
+ },
1894
+ "128236": {
1895
+ "content": "<|reserved_special_token_228|>",
1896
+ "lstrip": false,
1897
+ "normalized": false,
1898
+ "rstrip": false,
1899
+ "single_word": false,
1900
+ "special": true
1901
+ },
1902
+ "128237": {
1903
+ "content": "<|reserved_special_token_229|>",
1904
+ "lstrip": false,
1905
+ "normalized": false,
1906
+ "rstrip": false,
1907
+ "single_word": false,
1908
+ "special": true
1909
+ },
1910
+ "128238": {
1911
+ "content": "<|reserved_special_token_230|>",
1912
+ "lstrip": false,
1913
+ "normalized": false,
1914
+ "rstrip": false,
1915
+ "single_word": false,
1916
+ "special": true
1917
+ },
1918
+ "128239": {
1919
+ "content": "<|reserved_special_token_231|>",
1920
+ "lstrip": false,
1921
+ "normalized": false,
1922
+ "rstrip": false,
1923
+ "single_word": false,
1924
+ "special": true
1925
+ },
1926
+ "128240": {
1927
+ "content": "<|reserved_special_token_232|>",
1928
+ "lstrip": false,
1929
+ "normalized": false,
1930
+ "rstrip": false,
1931
+ "single_word": false,
1932
+ "special": true
1933
+ },
1934
+ "128241": {
1935
+ "content": "<|reserved_special_token_233|>",
1936
+ "lstrip": false,
1937
+ "normalized": false,
1938
+ "rstrip": false,
1939
+ "single_word": false,
1940
+ "special": true
1941
+ },
1942
+ "128242": {
1943
+ "content": "<|reserved_special_token_234|>",
1944
+ "lstrip": false,
1945
+ "normalized": false,
1946
+ "rstrip": false,
1947
+ "single_word": false,
1948
+ "special": true
1949
+ },
1950
+ "128243": {
1951
+ "content": "<|reserved_special_token_235|>",
1952
+ "lstrip": false,
1953
+ "normalized": false,
1954
+ "rstrip": false,
1955
+ "single_word": false,
1956
+ "special": true
1957
+ },
1958
+ "128244": {
1959
+ "content": "<|reserved_special_token_236|>",
1960
+ "lstrip": false,
1961
+ "normalized": false,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": true
1965
+ },
1966
+ "128245": {
1967
+ "content": "<|reserved_special_token_237|>",
1968
+ "lstrip": false,
1969
+ "normalized": false,
1970
+ "rstrip": false,
1971
+ "single_word": false,
1972
+ "special": true
1973
+ },
1974
+ "128246": {
1975
+ "content": "<|reserved_special_token_238|>",
1976
+ "lstrip": false,
1977
+ "normalized": false,
1978
+ "rstrip": false,
1979
+ "single_word": false,
1980
+ "special": true
1981
+ },
1982
+ "128247": {
1983
+ "content": "<|reserved_special_token_239|>",
1984
+ "lstrip": false,
1985
+ "normalized": false,
1986
+ "rstrip": false,
1987
+ "single_word": false,
1988
+ "special": true
1989
+ },
1990
+ "128248": {
1991
+ "content": "<|reserved_special_token_240|>",
1992
+ "lstrip": false,
1993
+ "normalized": false,
1994
+ "rstrip": false,
1995
+ "single_word": false,
1996
+ "special": true
1997
+ },
1998
+ "128249": {
1999
+ "content": "<|reserved_special_token_241|>",
2000
+ "lstrip": false,
2001
+ "normalized": false,
2002
+ "rstrip": false,
2003
+ "single_word": false,
2004
+ "special": true
2005
+ },
2006
+ "128250": {
2007
+ "content": "<|reserved_special_token_242|>",
2008
+ "lstrip": false,
2009
+ "normalized": false,
2010
+ "rstrip": false,
2011
+ "single_word": false,
2012
+ "special": true
2013
+ },
2014
+ "128251": {
2015
+ "content": "<|reserved_special_token_243|>",
2016
+ "lstrip": false,
2017
+ "normalized": false,
2018
+ "rstrip": false,
2019
+ "single_word": false,
2020
+ "special": true
2021
+ },
2022
+ "128252": {
2023
+ "content": "<|reserved_special_token_244|>",
2024
+ "lstrip": false,
2025
+ "normalized": false,
2026
+ "rstrip": false,
2027
+ "single_word": false,
2028
+ "special": true
2029
+ },
2030
+ "128253": {
2031
+ "content": "<|reserved_special_token_245|>",
2032
+ "lstrip": false,
2033
+ "normalized": false,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": true
2037
+ },
2038
+ "128254": {
2039
+ "content": "<|reserved_special_token_246|>",
2040
+ "lstrip": false,
2041
+ "normalized": false,
2042
+ "rstrip": false,
2043
+ "single_word": false,
2044
+ "special": true
2045
+ },
2046
+ "128255": {
2047
+ "content": "<|reserved_special_token_247|>",
2048
+ "lstrip": false,
2049
+ "normalized": false,
2050
+ "rstrip": false,
2051
+ "single_word": false,
2052
+ "special": true
2053
+ }
2054
+ },
2055
+ "bos_token": "<｜begin▁of▁sentence｜>",
2056
+ "clean_up_tokenization_spaces": false,
2057
+ "eos_token": "<｜end▁of▁sentence｜>",
2058
+ "extra_special_tokens": {},
2059
+ "legacy": true,
2060
+ "model_max_length": 16384,
2061
+ "pad_token": "<｜end▁of▁sentence｜>",
2062
+ "sp_model_kwargs": {},
2063
+ "tokenizer_class": "LlamaTokenizerFast",
2064
+ "unk_token": null,
2065
+ "use_default_system_prompt": false
2066
+ }
trainer_state.json ADDED
@@ -0,0 +1,1954 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 240,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0125,
14
+ "grad_norm": 10.18331757027076,
15
+ "learning_rate": 1.0000000000000002e-06,
16
+ "loss": 0.8960644006729126,
17
+ "num_input_tokens_seen": 0,
18
+ "step": 1
19
+ },
20
+ {
21
+ "epoch": 0.025,
22
+ "grad_norm": 9.16263025394979,
23
+ "learning_rate": 2.0000000000000003e-06,
24
+ "loss": 0.8488595485687256,
25
+ "num_input_tokens_seen": 0,
26
+ "step": 2
27
+ },
28
+ {
29
+ "epoch": 0.0375,
30
+ "grad_norm": 8.92834992115862,
31
+ "learning_rate": 3e-06,
32
+ "loss": 0.8538516759872437,
33
+ "num_input_tokens_seen": 0,
34
+ "step": 3
35
+ },
36
+ {
37
+ "epoch": 0.05,
38
+ "grad_norm": 9.282181600009132,
39
+ "learning_rate": 4.000000000000001e-06,
40
+ "loss": 0.856260359287262,
41
+ "num_input_tokens_seen": 0,
42
+ "step": 4
43
+ },
44
+ {
45
+ "epoch": 0.0625,
46
+ "grad_norm": 5.998755609205955,
47
+ "learning_rate": 5e-06,
48
+ "loss": 0.7300517559051514,
49
+ "num_input_tokens_seen": 0,
50
+ "step": 5
51
+ },
52
+ {
53
+ "epoch": 0.075,
54
+ "grad_norm": 4.585755656488519,
55
+ "learning_rate": 6e-06,
56
+ "loss": 0.6810914278030396,
57
+ "num_input_tokens_seen": 0,
58
+ "step": 6
59
+ },
60
+ {
61
+ "epoch": 0.0875,
62
+ "grad_norm": 3.5581298112309763,
63
+ "learning_rate": 7e-06,
64
+ "loss": 0.6221330761909485,
65
+ "num_input_tokens_seen": 0,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.1,
70
+ "grad_norm": 4.186415400005925,
71
+ "learning_rate": 8.000000000000001e-06,
72
+ "loss": 0.5942986011505127,
73
+ "num_input_tokens_seen": 0,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.1125,
78
+ "grad_norm": 2.0815923930377633,
79
+ "learning_rate": 9e-06,
80
+ "loss": 0.5573145151138306,
81
+ "num_input_tokens_seen": 0,
82
+ "step": 9
83
+ },
84
+ {
85
+ "epoch": 0.125,
86
+ "grad_norm": 1.538737138740704,
87
+ "learning_rate": 1e-05,
88
+ "loss": 0.5063657164573669,
89
+ "num_input_tokens_seen": 0,
90
+ "step": 10
91
+ },
92
+ {
93
+ "epoch": 0.1375,
94
+ "grad_norm": 1.3167709252541377,
95
+ "learning_rate": 1.1000000000000001e-05,
96
+ "loss": 0.5080946087837219,
97
+ "num_input_tokens_seen": 0,
98
+ "step": 11
99
+ },
100
+ {
101
+ "epoch": 0.15,
102
+ "grad_norm": 1.0093046488935542,
103
+ "learning_rate": 1.2e-05,
104
+ "loss": 0.5118667483329773,
105
+ "num_input_tokens_seen": 0,
106
+ "step": 12
107
+ },
108
+ {
109
+ "epoch": 0.1625,
110
+ "grad_norm": 1.0176825029370344,
111
+ "learning_rate": 1.3000000000000001e-05,
112
+ "loss": 0.4826335608959198,
113
+ "num_input_tokens_seen": 0,
114
+ "step": 13
115
+ },
116
+ {
117
+ "epoch": 0.175,
118
+ "grad_norm": 0.868692377639643,
119
+ "learning_rate": 1.4e-05,
120
+ "loss": 0.4561425447463989,
121
+ "num_input_tokens_seen": 0,
122
+ "step": 14
123
+ },
124
+ {
125
+ "epoch": 0.1875,
126
+ "grad_norm": 0.7576207830400876,
127
+ "learning_rate": 1.5000000000000002e-05,
128
+ "loss": 0.46192091703414917,
129
+ "num_input_tokens_seen": 0,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.2,
134
+ "grad_norm": 0.6607030167581055,
135
+ "learning_rate": 1.6000000000000003e-05,
136
+ "loss": 0.436120867729187,
137
+ "num_input_tokens_seen": 0,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.2125,
142
+ "grad_norm": 0.6388324060478595,
143
+ "learning_rate": 1.7e-05,
144
+ "loss": 0.43788450956344604,
145
+ "num_input_tokens_seen": 0,
146
+ "step": 17
147
+ },
148
+ {
149
+ "epoch": 0.225,
150
+ "grad_norm": 0.6522444786796912,
151
+ "learning_rate": 1.8e-05,
152
+ "loss": 0.42514723539352417,
153
+ "num_input_tokens_seen": 0,
154
+ "step": 18
155
+ },
156
+ {
157
+ "epoch": 0.2375,
158
+ "grad_norm": 0.5939148285210124,
159
+ "learning_rate": 1.9e-05,
160
+ "loss": 0.41062527894973755,
161
+ "num_input_tokens_seen": 0,
162
+ "step": 19
163
+ },
164
+ {
165
+ "epoch": 0.25,
166
+ "grad_norm": 0.6228429094034043,
167
+ "learning_rate": 2e-05,
168
+ "loss": 0.3994959890842438,
169
+ "num_input_tokens_seen": 0,
170
+ "step": 20
171
+ },
172
+ {
173
+ "epoch": 0.2625,
174
+ "grad_norm": 0.5940088612229671,
175
+ "learning_rate": 1.9999658256641746e-05,
176
+ "loss": 0.41216734051704407,
177
+ "num_input_tokens_seen": 0,
178
+ "step": 21
179
+ },
180
+ {
181
+ "epoch": 0.275,
182
+ "grad_norm": 0.5920054647245636,
183
+ "learning_rate": 1.9998633049924693e-05,
184
+ "loss": 0.41810792684555054,
185
+ "num_input_tokens_seen": 0,
186
+ "step": 22
187
+ },
188
+ {
189
+ "epoch": 0.2875,
190
+ "grad_norm": 0.5480649368192407,
191
+ "learning_rate": 1.999692444992035e-05,
192
+ "loss": 0.4036347568035126,
193
+ "num_input_tokens_seen": 0,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.3,
198
+ "grad_norm": 0.5565757348287612,
199
+ "learning_rate": 1.999453257340926e-05,
200
+ "loss": 0.419705331325531,
201
+ "num_input_tokens_seen": 0,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.3125,
206
+ "grad_norm": 0.5548087155409337,
207
+ "learning_rate": 1.999145758387301e-05,
208
+ "loss": 0.40048182010650635,
209
+ "num_input_tokens_seen": 0,
210
+ "step": 25
211
+ },
212
+ {
213
+ "epoch": 0.325,
214
+ "grad_norm": 0.5338888290743757,
215
+ "learning_rate": 1.998769969148305e-05,
216
+ "loss": 0.40444415807724,
217
+ "num_input_tokens_seen": 0,
218
+ "step": 26
219
+ },
220
+ {
221
+ "epoch": 0.3375,
222
+ "grad_norm": 0.5018287159150987,
223
+ "learning_rate": 1.9983259153086328e-05,
224
+ "loss": 0.3908202052116394,
225
+ "num_input_tokens_seen": 0,
226
+ "step": 27
227
+ },
228
+ {
229
+ "epoch": 0.35,
230
+ "grad_norm": 0.5666363779267786,
231
+ "learning_rate": 1.9978136272187745e-05,
232
+ "loss": 0.3917597532272339,
233
+ "num_input_tokens_seen": 0,
234
+ "step": 28
235
+ },
236
+ {
237
+ "epoch": 0.3625,
238
+ "grad_norm": 0.5311731782089377,
239
+ "learning_rate": 1.997233139892941e-05,
240
+ "loss": 0.38186532258987427,
241
+ "num_input_tokens_seen": 0,
242
+ "step": 29
243
+ },
244
+ {
245
+ "epoch": 0.375,
246
+ "grad_norm": 0.5017076164418427,
247
+ "learning_rate": 1.99658449300667e-05,
248
+ "loss": 0.3953409492969513,
249
+ "num_input_tokens_seen": 0,
250
+ "step": 30
251
+ },
252
+ {
253
+ "epoch": 0.3875,
254
+ "grad_norm": 0.5191236527322374,
255
+ "learning_rate": 1.995867730894114e-05,
256
+ "loss": 0.3810531198978424,
257
+ "num_input_tokens_seen": 0,
258
+ "step": 31
259
+ },
260
+ {
261
+ "epoch": 0.4,
262
+ "grad_norm": 0.479389601325034,
263
+ "learning_rate": 1.9950829025450116e-05,
264
+ "loss": 0.3787350058555603,
265
+ "num_input_tokens_seen": 0,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 0.4125,
270
+ "grad_norm": 0.5052682473625102,
271
+ "learning_rate": 1.9942300616013378e-05,
272
+ "loss": 0.3784908056259155,
273
+ "num_input_tokens_seen": 0,
274
+ "step": 33
275
+ },
276
+ {
277
+ "epoch": 0.425,
278
+ "grad_norm": 0.5093747529791427,
279
+ "learning_rate": 1.9933092663536384e-05,
280
+ "loss": 0.377264142036438,
281
+ "num_input_tokens_seen": 0,
282
+ "step": 34
283
+ },
284
+ {
285
+ "epoch": 0.4375,
286
+ "grad_norm": 0.5496127833092357,
287
+ "learning_rate": 1.992320579737045e-05,
288
+ "loss": 0.4013134837150574,
289
+ "num_input_tokens_seen": 0,
290
+ "step": 35
291
+ },
292
+ {
293
+ "epoch": 0.45,
294
+ "grad_norm": 0.5194182976027281,
295
+ "learning_rate": 1.9912640693269754e-05,
296
+ "loss": 0.3868390917778015,
297
+ "num_input_tokens_seen": 0,
298
+ "step": 36
299
+ },
300
+ {
301
+ "epoch": 0.4625,
302
+ "grad_norm": 0.4772201831075947,
303
+ "learning_rate": 1.990139807334512e-05,
304
+ "loss": 0.3554729223251343,
305
+ "num_input_tokens_seen": 0,
306
+ "step": 37
307
+ },
308
+ {
309
+ "epoch": 0.475,
310
+ "grad_norm": 0.5411145901050805,
311
+ "learning_rate": 1.9889478706014687e-05,
312
+ "loss": 0.3768259882926941,
313
+ "num_input_tokens_seen": 0,
314
+ "step": 38
315
+ },
316
+ {
317
+ "epoch": 0.4875,
318
+ "grad_norm": 0.47151248168784593,
319
+ "learning_rate": 1.9876883405951378e-05,
320
+ "loss": 0.3637596368789673,
321
+ "num_input_tokens_seen": 0,
322
+ "step": 39
323
+ },
324
+ {
325
+ "epoch": 0.5,
326
+ "grad_norm": 0.4900043722490537,
327
+ "learning_rate": 1.9863613034027224e-05,
328
+ "loss": 0.3731005787849426,
329
+ "num_input_tokens_seen": 0,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 0.5125,
334
+ "grad_norm": 0.4740418320125202,
335
+ "learning_rate": 1.984966849725452e-05,
336
+ "loss": 0.36029529571533203,
337
+ "num_input_tokens_seen": 0,
338
+ "step": 41
339
+ },
340
+ {
341
+ "epoch": 0.525,
342
+ "grad_norm": 0.5282467622205699,
343
+ "learning_rate": 1.9835050748723826e-05,
344
+ "loss": 0.371197909116745,
345
+ "num_input_tokens_seen": 0,
346
+ "step": 42
347
+ },
348
+ {
349
+ "epoch": 0.5375,
350
+ "grad_norm": 0.4755646348335201,
351
+ "learning_rate": 1.981976078753884e-05,
352
+ "loss": 0.34178704023361206,
353
+ "num_input_tokens_seen": 0,
354
+ "step": 43
355
+ },
356
+ {
357
+ "epoch": 0.55,
358
+ "grad_norm": 0.507685264776996,
359
+ "learning_rate": 1.9803799658748096e-05,
360
+ "loss": 0.3663065731525421,
361
+ "num_input_tokens_seen": 0,
362
+ "step": 44
363
+ },
364
+ {
365
+ "epoch": 0.5625,
366
+ "grad_norm": 0.5265705406067266,
367
+ "learning_rate": 1.9787168453273546e-05,
368
+ "loss": 0.3737153708934784,
369
+ "num_input_tokens_seen": 0,
370
+ "step": 45
371
+ },
372
+ {
373
+ "epoch": 0.575,
374
+ "grad_norm": 0.5571656899248943,
375
+ "learning_rate": 1.9769868307835996e-05,
376
+ "loss": 0.3628424406051636,
377
+ "num_input_tokens_seen": 0,
378
+ "step": 46
379
+ },
380
+ {
381
+ "epoch": 0.5875,
382
+ "grad_norm": 0.569279834268425,
383
+ "learning_rate": 1.97519004048774e-05,
384
+ "loss": 0.37988948822021484,
385
+ "num_input_tokens_seen": 0,
386
+ "step": 47
387
+ },
388
+ {
389
+ "epoch": 0.6,
390
+ "grad_norm": 0.4969114483932452,
391
+ "learning_rate": 1.973326597248006e-05,
392
+ "loss": 0.3636181950569153,
393
+ "num_input_tokens_seen": 0,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 0.6125,
398
+ "grad_norm": 0.5439018148028109,
399
+ "learning_rate": 1.9713966284282677e-05,
400
+ "loss": 0.3687742352485657,
401
+ "num_input_tokens_seen": 0,
402
+ "step": 49
403
+ },
404
+ {
405
+ "epoch": 0.625,
406
+ "grad_norm": 0.47096960108233016,
407
+ "learning_rate": 1.9694002659393306e-05,
408
+ "loss": 0.3656526207923889,
409
+ "num_input_tokens_seen": 0,
410
+ "step": 50
411
+ },
412
+ {
413
+ "epoch": 0.6375,
414
+ "grad_norm": 0.49069042740477836,
415
+ "learning_rate": 1.9673376462299186e-05,
416
+ "loss": 0.3719867467880249,
417
+ "num_input_tokens_seen": 0,
418
+ "step": 51
419
+ },
420
+ {
421
+ "epoch": 0.65,
422
+ "grad_norm": 0.5230240054949966,
423
+ "learning_rate": 1.9652089102773487e-05,
424
+ "loss": 0.3670026361942291,
425
+ "num_input_tokens_seen": 0,
426
+ "step": 52
427
+ },
428
+ {
429
+ "epoch": 0.6625,
430
+ "grad_norm": 0.539667408085974,
431
+ "learning_rate": 1.963014203577896e-05,
432
+ "loss": 0.3777502775192261,
433
+ "num_input_tokens_seen": 0,
434
+ "step": 53
435
+ },
436
+ {
437
+ "epoch": 0.675,
438
+ "grad_norm": 0.5303927925423055,
439
+ "learning_rate": 1.9607536761368484e-05,
440
+ "loss": 0.360956609249115,
441
+ "num_input_tokens_seen": 0,
442
+ "step": 54
443
+ },
444
+ {
445
+ "epoch": 0.6875,
446
+ "grad_norm": 0.5669762895801259,
447
+ "learning_rate": 1.958427482458253e-05,
448
+ "loss": 0.3712082505226135,
449
+ "num_input_tokens_seen": 0,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.7,
454
+ "grad_norm": 0.4924233132486405,
455
+ "learning_rate": 1.9560357815343577e-05,
456
+ "loss": 0.34069931507110596,
457
+ "num_input_tokens_seen": 0,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 0.7125,
462
+ "grad_norm": 0.4939181685825231,
463
+ "learning_rate": 1.9535787368347444e-05,
464
+ "loss": 0.3445311188697815,
465
+ "num_input_tokens_seen": 0,
466
+ "step": 57
467
+ },
468
+ {
469
+ "epoch": 0.725,
470
+ "grad_norm": 0.5132891832051437,
471
+ "learning_rate": 1.9510565162951538e-05,
472
+ "loss": 0.352506160736084,
473
+ "num_input_tokens_seen": 0,
474
+ "step": 58
475
+ },
476
+ {
477
+ "epoch": 0.7375,
478
+ "grad_norm": 0.5228074950046403,
479
+ "learning_rate": 1.9484692923060095e-05,
480
+ "loss": 0.352910578250885,
481
+ "num_input_tokens_seen": 0,
482
+ "step": 59
483
+ },
484
+ {
485
+ "epoch": 0.75,
486
+ "grad_norm": 0.48331453046149664,
487
+ "learning_rate": 1.9458172417006347e-05,
488
+ "loss": 0.3518715500831604,
489
+ "num_input_tokens_seen": 0,
490
+ "step": 60
491
+ },
492
+ {
493
+ "epoch": 0.7625,
494
+ "grad_norm": 0.4971643896288794,
495
+ "learning_rate": 1.9431005457431654e-05,
496
+ "loss": 0.3532984256744385,
497
+ "num_input_tokens_seen": 0,
498
+ "step": 61
499
+ },
500
+ {
501
+ "epoch": 0.775,
502
+ "grad_norm": 0.5331008024051833,
503
+ "learning_rate": 1.9403193901161614e-05,
504
+ "loss": 0.3648609220981598,
505
+ "num_input_tokens_seen": 0,
506
+ "step": 62
507
+ },
508
+ {
509
+ "epoch": 0.7875,
510
+ "grad_norm": 1.2839239169737044,
511
+ "learning_rate": 1.9374739649079155e-05,
512
+ "loss": 0.3517247438430786,
513
+ "num_input_tokens_seen": 0,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.8,
518
+ "grad_norm": 0.5877379242744403,
519
+ "learning_rate": 1.934564464599461e-05,
520
+ "loss": 0.3657301962375641,
521
+ "num_input_tokens_seen": 0,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 0.8125,
526
+ "grad_norm": 0.4867340909281986,
527
+ "learning_rate": 1.9315910880512792e-05,
528
+ "loss": 0.36049771308898926,
529
+ "num_input_tokens_seen": 0,
530
+ "step": 65
531
+ },
532
+ {
533
+ "epoch": 0.825,
534
+ "grad_norm": 0.49356286585265735,
535
+ "learning_rate": 1.9285540384897073e-05,
536
+ "loss": 0.34778010845184326,
537
+ "num_input_tokens_seen": 0,
538
+ "step": 66
539
+ },
540
+ {
541
+ "epoch": 0.8375,
542
+ "grad_norm": 0.5535250380039742,
543
+ "learning_rate": 1.9254535234930486e-05,
544
+ "loss": 0.36141228675842285,
545
+ "num_input_tokens_seen": 0,
546
+ "step": 67
547
+ },
548
+ {
549
+ "epoch": 0.85,
550
+ "grad_norm": 0.5243933357988406,
551
+ "learning_rate": 1.922289754977385e-05,
552
+ "loss": 0.3524037301540375,
553
+ "num_input_tokens_seen": 0,
554
+ "step": 68
555
+ },
556
+ {
557
+ "epoch": 0.8625,
558
+ "grad_norm": 0.5324496372479985,
559
+ "learning_rate": 1.919062949182091e-05,
560
+ "loss": 0.36538389325141907,
561
+ "num_input_tokens_seen": 0,
562
+ "step": 69
563
+ },
564
+ {
565
+ "epoch": 0.875,
566
+ "grad_norm": 0.49491533066436794,
567
+ "learning_rate": 1.9157733266550577e-05,
568
+ "loss": 0.35084018111228943,
569
+ "num_input_tokens_seen": 0,
570
+ "step": 70
571
+ },
572
+ {
573
+ "epoch": 0.8875,
574
+ "grad_norm": 0.5287693804586798,
575
+ "learning_rate": 1.9124211122376138e-05,
576
+ "loss": 0.3459678292274475,
577
+ "num_input_tokens_seen": 0,
578
+ "step": 71
579
+ },
580
+ {
581
+ "epoch": 0.9,
582
+ "grad_norm": 0.4675049739386483,
583
+ "learning_rate": 1.909006535049163e-05,
584
+ "loss": 0.34027597308158875,
585
+ "num_input_tokens_seen": 0,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 0.9125,
590
+ "grad_norm": 0.5068359141834208,
591
+ "learning_rate": 1.9055298284715192e-05,
592
+ "loss": 0.34234559535980225,
593
+ "num_input_tokens_seen": 0,
594
+ "step": 73
595
+ },
596
+ {
597
+ "epoch": 0.925,
598
+ "grad_norm": 0.5454693950983837,
599
+ "learning_rate": 1.9019912301329593e-05,
600
+ "loss": 0.3697267770767212,
601
+ "num_input_tokens_seen": 0,
602
+ "step": 74
603
+ },
604
+ {
605
+ "epoch": 0.9375,
606
+ "grad_norm": 0.48781498197167644,
607
+ "learning_rate": 1.898390981891979e-05,
608
+ "loss": 0.3399868607521057,
609
+ "num_input_tokens_seen": 0,
610
+ "step": 75
611
+ },
612
+ {
613
+ "epoch": 0.95,
614
+ "grad_norm": 0.467529345150941,
615
+ "learning_rate": 1.8947293298207637e-05,
616
+ "loss": 0.3481365442276001,
617
+ "num_input_tokens_seen": 0,
618
+ "step": 76
619
+ },
620
+ {
621
+ "epoch": 0.9625,
622
+ "grad_norm": 0.5173617613436983,
623
+ "learning_rate": 1.891006524188368e-05,
624
+ "loss": 0.35163643956184387,
625
+ "num_input_tokens_seen": 0,
626
+ "step": 77
627
+ },
628
+ {
629
+ "epoch": 0.975,
630
+ "grad_norm": 0.4964553718237553,
631
+ "learning_rate": 1.887222819443612e-05,
632
+ "loss": 0.3495897650718689,
633
+ "num_input_tokens_seen": 0,
634
+ "step": 78
635
+ },
636
+ {
637
+ "epoch": 0.9875,
638
+ "grad_norm": 0.5266061782006969,
639
+ "learning_rate": 1.883378474197689e-05,
640
+ "loss": 0.3525278568267822,
641
+ "num_input_tokens_seen": 0,
642
+ "step": 79
643
+ },
644
+ {
645
+ "epoch": 1.0,
646
+ "grad_norm": 0.48903026352892565,
647
+ "learning_rate": 1.879473751206489e-05,
648
+ "loss": 0.3540067672729492,
649
+ "num_input_tokens_seen": 0,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 1.0125,
654
+ "grad_norm": 0.8791291129207356,
655
+ "learning_rate": 1.875508917352643e-05,
656
+ "loss": 0.26043254137039185,
657
+ "num_input_tokens_seen": 0,
658
+ "step": 81
659
+ },
660
+ {
661
+ "epoch": 1.025,
662
+ "grad_norm": 0.6487054540761681,
663
+ "learning_rate": 1.8714842436272774e-05,
664
+ "loss": 0.2440587878227234,
665
+ "num_input_tokens_seen": 0,
666
+ "step": 82
667
+ },
668
+ {
669
+ "epoch": 1.0375,
670
+ "grad_norm": 0.6795282145993521,
671
+ "learning_rate": 1.8674000051114953e-05,
672
+ "loss": 0.2597944140434265,
673
+ "num_input_tokens_seen": 0,
674
+ "step": 83
675
+ },
676
+ {
677
+ "epoch": 1.05,
678
+ "grad_norm": 0.6670449632773737,
679
+ "learning_rate": 1.863256480957574e-05,
680
+ "loss": 0.23764365911483765,
681
+ "num_input_tokens_seen": 0,
682
+ "step": 84
683
+ },
684
+ {
685
+ "epoch": 1.0625,
686
+ "grad_norm": 0.8445000033015495,
687
+ "learning_rate": 1.8590539543698852e-05,
688
+ "loss": 0.22128596901893616,
689
+ "num_input_tokens_seen": 0,
690
+ "step": 85
691
+ },
692
+ {
693
+ "epoch": 1.075,
694
+ "grad_norm": 0.7319387611539306,
695
+ "learning_rate": 1.854792712585539e-05,
696
+ "loss": 0.22451584041118622,
697
+ "num_input_tokens_seen": 0,
698
+ "step": 86
699
+ },
700
+ {
701
+ "epoch": 1.0875,
702
+ "grad_norm": 0.7347266658746741,
703
+ "learning_rate": 1.8504730468547508e-05,
704
+ "loss": 0.23484283685684204,
705
+ "num_input_tokens_seen": 0,
706
+ "step": 87
707
+ },
708
+ {
709
+ "epoch": 1.1,
710
+ "grad_norm": 0.684429737748084,
711
+ "learning_rate": 1.8460952524209355e-05,
712
+ "loss": 0.22682486474514008,
713
+ "num_input_tokens_seen": 0,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 1.1125,
718
+ "grad_norm": 0.6253196189027981,
719
+ "learning_rate": 1.8416596285005274e-05,
720
+ "loss": 0.23638179898262024,
721
+ "num_input_tokens_seen": 0,
722
+ "step": 89
723
+ },
724
+ {
725
+ "epoch": 1.125,
726
+ "grad_norm": 0.7140008070317728,
727
+ "learning_rate": 1.8371664782625287e-05,
728
+ "loss": 0.22379158437252045,
729
+ "num_input_tokens_seen": 0,
730
+ "step": 90
731
+ },
732
+ {
733
+ "epoch": 1.1375,
734
+ "grad_norm": 0.5609948172492557,
735
+ "learning_rate": 1.8326161088077905e-05,
736
+ "loss": 0.23043715953826904,
737
+ "num_input_tokens_seen": 0,
738
+ "step": 91
739
+ },
740
+ {
741
+ "epoch": 1.15,
742
+ "grad_norm": 0.5762843622395748,
743
+ "learning_rate": 1.8280088311480203e-05,
744
+ "loss": 0.22419373691082,
745
+ "num_input_tokens_seen": 0,
746
+ "step": 92
747
+ },
748
+ {
749
+ "epoch": 1.1625,
750
+ "grad_norm": 0.7331777727867734,
751
+ "learning_rate": 1.823344960184526e-05,
752
+ "loss": 0.22210514545440674,
753
+ "num_input_tokens_seen": 0,
754
+ "step": 93
755
+ },
756
+ {
757
+ "epoch": 1.175,
758
+ "grad_norm": 0.6205497447918622,
759
+ "learning_rate": 1.8186248146866928e-05,
760
+ "loss": 0.23843634128570557,
761
+ "num_input_tokens_seen": 0,
762
+ "step": 94
763
+ },
764
+ {
765
+ "epoch": 1.1875,
766
+ "grad_norm": 0.645067422698941,
767
+ "learning_rate": 1.813848717270195e-05,
768
+ "loss": 0.22561757266521454,
769
+ "num_input_tokens_seen": 0,
770
+ "step": 95
771
+ },
772
+ {
773
+ "epoch": 1.2,
774
+ "grad_norm": 0.5305489735340998,
775
+ "learning_rate": 1.8090169943749477e-05,
776
+ "loss": 0.23090419173240662,
777
+ "num_input_tokens_seen": 0,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 1.2125,
782
+ "grad_norm": 0.652421080289407,
783
+ "learning_rate": 1.804129976242792e-05,
784
+ "loss": 0.21994651854038239,
785
+ "num_input_tokens_seen": 0,
786
+ "step": 97
787
+ },
788
+ {
789
+ "epoch": 1.225,
790
+ "grad_norm": 0.546464902083412,
791
+ "learning_rate": 1.7991879968949248e-05,
792
+ "loss": 0.2290341556072235,
793
+ "num_input_tokens_seen": 0,
794
+ "step": 98
795
+ },
796
+ {
797
+ "epoch": 1.2375,
798
+ "grad_norm": 0.6476920457708351,
799
+ "learning_rate": 1.7941913941090712e-05,
800
+ "loss": 0.24561816453933716,
801
+ "num_input_tokens_seen": 0,
802
+ "step": 99
803
+ },
804
+ {
805
+ "epoch": 1.25,
806
+ "grad_norm": 0.5782245623531915,
807
+ "learning_rate": 1.789140509396394e-05,
808
+ "loss": 0.23482097685337067,
809
+ "num_input_tokens_seen": 0,
810
+ "step": 100
811
+ },
812
+ {
813
+ "epoch": 1.2625,
814
+ "grad_norm": 0.6348611730944753,
815
+ "learning_rate": 1.784035687978153e-05,
816
+ "loss": 0.21998700499534607,
817
+ "num_input_tokens_seen": 0,
818
+ "step": 101
819
+ },
820
+ {
821
+ "epoch": 1.275,
822
+ "grad_norm": 0.5855684501933186,
823
+ "learning_rate": 1.7788772787621126e-05,
824
+ "loss": 0.22731050848960876,
825
+ "num_input_tokens_seen": 0,
826
+ "step": 102
827
+ },
828
+ {
829
+ "epoch": 1.2875,
830
+ "grad_norm": 0.5849783819104052,
831
+ "learning_rate": 1.7736656343186897e-05,
832
+ "loss": 0.21847045421600342,
833
+ "num_input_tokens_seen": 0,
834
+ "step": 103
835
+ },
836
+ {
837
+ "epoch": 1.3,
838
+ "grad_norm": 0.6468451663174432,
839
+ "learning_rate": 1.7684011108568593e-05,
840
+ "loss": 0.23889131844043732,
841
+ "num_input_tokens_seen": 0,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 1.3125,
846
+ "grad_norm": 0.5379228455435396,
847
+ "learning_rate": 1.7630840681998068e-05,
848
+ "loss": 0.22917379438877106,
849
+ "num_input_tokens_seen": 0,
850
+ "step": 105
851
+ },
852
+ {
853
+ "epoch": 1.325,
854
+ "grad_norm": 0.6386415797352409,
855
+ "learning_rate": 1.757714869760335e-05,
856
+ "loss": 0.22476345300674438,
857
+ "num_input_tokens_seen": 0,
858
+ "step": 106
859
+ },
860
+ {
861
+ "epoch": 1.3375,
862
+ "grad_norm": 0.5432607518100792,
863
+ "learning_rate": 1.752293882516025e-05,
864
+ "loss": 0.23026630282402039,
865
+ "num_input_tokens_seen": 0,
866
+ "step": 107
867
+ },
868
+ {
869
+ "epoch": 1.35,
870
+ "grad_norm": 0.6251676560462321,
871
+ "learning_rate": 1.7468214769841542e-05,
872
+ "loss": 0.22793394327163696,
873
+ "num_input_tokens_seen": 0,
874
+ "step": 108
875
+ },
876
+ {
877
+ "epoch": 1.3625,
878
+ "grad_norm": 0.5786323989132912,
879
+ "learning_rate": 1.7412980271963712e-05,
880
+ "loss": 0.24610519409179688,
881
+ "num_input_tokens_seen": 0,
882
+ "step": 109
883
+ },
884
+ {
885
+ "epoch": 1.375,
886
+ "grad_norm": 0.5735661628137917,
887
+ "learning_rate": 1.735723910673132e-05,
888
+ "loss": 0.21196551620960236,
889
+ "num_input_tokens_seen": 0,
890
+ "step": 110
891
+ },
892
+ {
893
+ "epoch": 1.3875,
894
+ "grad_norm": 0.5881031218701362,
895
+ "learning_rate": 1.7300995083978965e-05,
896
+ "loss": 0.22360339760780334,
897
+ "num_input_tokens_seen": 0,
898
+ "step": 111
899
+ },
900
+ {
901
+ "epoch": 1.4,
902
+ "grad_norm": 0.5603841737931269,
903
+ "learning_rate": 1.7244252047910893e-05,
904
+ "loss": 0.22254161536693573,
905
+ "num_input_tokens_seen": 0,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 1.4125,
910
+ "grad_norm": 0.566304468507664,
911
+ "learning_rate": 1.718701387683824e-05,
912
+ "loss": 0.21939656138420105,
913
+ "num_input_tokens_seen": 0,
914
+ "step": 113
915
+ },
916
+ {
917
+ "epoch": 1.425,
918
+ "grad_norm": 0.532198517126917,
919
+ "learning_rate": 1.7129284482913973e-05,
920
+ "loss": 0.2217104434967041,
921
+ "num_input_tokens_seen": 0,
922
+ "step": 114
923
+ },
924
+ {
925
+ "epoch": 1.4375,
926
+ "grad_norm": 0.5486267196897048,
927
+ "learning_rate": 1.7071067811865477e-05,
928
+ "loss": 0.22763556241989136,
929
+ "num_input_tokens_seen": 0,
930
+ "step": 115
931
+ },
932
+ {
933
+ "epoch": 1.45,
934
+ "grad_norm": 0.5318598905653756,
935
+ "learning_rate": 1.7012367842724887e-05,
936
+ "loss": 0.22226908802986145,
937
+ "num_input_tokens_seen": 0,
938
+ "step": 116
939
+ },
940
+ {
941
+ "epoch": 1.4625,
942
+ "grad_norm": 0.5219241851069808,
943
+ "learning_rate": 1.6953188587557122e-05,
944
+ "loss": 0.2251712530851364,
945
+ "num_input_tokens_seen": 0,
946
+ "step": 117
947
+ },
948
+ {
949
+ "epoch": 1.475,
950
+ "grad_norm": 0.5576204648175208,
951
+ "learning_rate": 1.6893534091185658e-05,
952
+ "loss": 0.2300577610731125,
953
+ "num_input_tokens_seen": 0,
954
+ "step": 118
955
+ },
956
+ {
957
+ "epoch": 1.4875,
958
+ "grad_norm": 0.5157156531813916,
959
+ "learning_rate": 1.6833408430916085e-05,
960
+ "loss": 0.23422931134700775,
961
+ "num_input_tokens_seen": 0,
962
+ "step": 119
963
+ },
964
+ {
965
+ "epoch": 1.5,
966
+ "grad_norm": 0.5525368224210166,
967
+ "learning_rate": 1.6772815716257414e-05,
968
+ "loss": 0.23097172379493713,
969
+ "num_input_tokens_seen": 0,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 1.5125,
974
+ "grad_norm": 0.5671209735467264,
975
+ "learning_rate": 1.6711760088641197e-05,
976
+ "loss": 0.22700801491737366,
977
+ "num_input_tokens_seen": 0,
978
+ "step": 121
979
+ },
980
+ {
981
+ "epoch": 1.525,
982
+ "grad_norm": 0.49340662518168044,
983
+ "learning_rate": 1.6650245721138483e-05,
984
+ "loss": 0.21679332852363586,
985
+ "num_input_tokens_seen": 0,
986
+ "step": 122
987
+ },
988
+ {
989
+ "epoch": 1.5375,
990
+ "grad_norm": 0.5241279113240838,
991
+ "learning_rate": 1.658827681817458e-05,
992
+ "loss": 0.23128211498260498,
993
+ "num_input_tokens_seen": 0,
994
+ "step": 123
995
+ },
996
+ {
997
+ "epoch": 1.55,
998
+ "grad_norm": 0.5605937616757047,
999
+ "learning_rate": 1.6525857615241686e-05,
1000
+ "loss": 0.2341003566980362,
1001
+ "num_input_tokens_seen": 0,
1002
+ "step": 124
1003
+ },
1004
+ {
1005
+ "epoch": 1.5625,
1006
+ "grad_norm": 0.5731377051701606,
1007
+ "learning_rate": 1.646299237860941e-05,
1008
+ "loss": 0.24362272024154663,
1009
+ "num_input_tokens_seen": 0,
1010
+ "step": 125
1011
+ },
1012
+ {
1013
+ "epoch": 1.575,
1014
+ "grad_norm": 0.4973323542505726,
1015
+ "learning_rate": 1.6399685405033168e-05,
1016
+ "loss": 0.21342068910598755,
1017
+ "num_input_tokens_seen": 0,
1018
+ "step": 126
1019
+ },
1020
+ {
1021
+ "epoch": 1.5875,
1022
+ "grad_norm": 0.5599176772369371,
1023
+ "learning_rate": 1.6335941021460507e-05,
1024
+ "loss": 0.2271297574043274,
1025
+ "num_input_tokens_seen": 0,
1026
+ "step": 127
1027
+ },
1028
+ {
1029
+ "epoch": 1.6,
1030
+ "grad_norm": 0.5203662408979232,
1031
+ "learning_rate": 1.6271763584735373e-05,
1032
+ "loss": 0.22479626536369324,
1033
+ "num_input_tokens_seen": 0,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 1.6125,
1038
+ "grad_norm": 0.5095863344896252,
1039
+ "learning_rate": 1.6207157481300315e-05,
1040
+ "loss": 0.22810155153274536,
1041
+ "num_input_tokens_seen": 0,
1042
+ "step": 129
1043
+ },
1044
+ {
1045
+ "epoch": 1.625,
1046
+ "grad_norm": 0.5317196453792732,
1047
+ "learning_rate": 1.6142127126896682e-05,
1048
+ "loss": 0.21053889393806458,
1049
+ "num_input_tokens_seen": 0,
1050
+ "step": 130
1051
+ },
1052
+ {
1053
+ "epoch": 1.6375,
1054
+ "grad_norm": 0.5425148287230596,
1055
+ "learning_rate": 1.6076676966262815e-05,
1056
+ "loss": 0.23062941431999207,
1057
+ "num_input_tokens_seen": 0,
1058
+ "step": 131
1059
+ },
1060
+ {
1061
+ "epoch": 1.65,
1062
+ "grad_norm": 0.6023208751142557,
1063
+ "learning_rate": 1.6010811472830253e-05,
1064
+ "loss": 0.2463783472776413,
1065
+ "num_input_tokens_seen": 0,
1066
+ "step": 132
1067
+ },
1068
+ {
1069
+ "epoch": 1.6625,
1070
+ "grad_norm": 0.5550292129482939,
1071
+ "learning_rate": 1.5944535148417982e-05,
1072
+ "loss": 0.23075446486473083,
1073
+ "num_input_tokens_seen": 0,
1074
+ "step": 133
1075
+ },
1076
+ {
1077
+ "epoch": 1.675,
1078
+ "grad_norm": 0.5643030708792179,
1079
+ "learning_rate": 1.5877852522924733e-05,
1080
+ "loss": 0.22998251020908356,
1081
+ "num_input_tokens_seen": 0,
1082
+ "step": 134
1083
+ },
1084
+ {
1085
+ "epoch": 1.6875,
1086
+ "grad_norm": 0.6739206936197925,
1087
+ "learning_rate": 1.5810768154019386e-05,
1088
+ "loss": 0.23184943199157715,
1089
+ "num_input_tokens_seen": 0,
1090
+ "step": 135
1091
+ },
1092
+ {
1093
+ "epoch": 1.7,
1094
+ "grad_norm": 0.5322077543412791,
1095
+ "learning_rate": 1.5743286626829437e-05,
1096
+ "loss": 0.24749401211738586,
1097
+ "num_input_tokens_seen": 0,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 1.7125,
1102
+ "grad_norm": 0.6117204460062114,
1103
+ "learning_rate": 1.5675412553627638e-05,
1104
+ "loss": 0.22619368135929108,
1105
+ "num_input_tokens_seen": 0,
1106
+ "step": 137
1107
+ },
1108
+ {
1109
+ "epoch": 1.725,
1110
+ "grad_norm": 0.5683821158495919,
1111
+ "learning_rate": 1.560715057351673e-05,
1112
+ "loss": 0.2415420114994049,
1113
+ "num_input_tokens_seen": 0,
1114
+ "step": 138
1115
+ },
1116
+ {
1117
+ "epoch": 1.7375,
1118
+ "grad_norm": 0.5531774081547891,
1119
+ "learning_rate": 1.5538505352112373e-05,
1120
+ "loss": 0.23251904547214508,
1121
+ "num_input_tokens_seen": 0,
1122
+ "step": 139
1123
+ },
1124
+ {
1125
+ "epoch": 1.75,
1126
+ "grad_norm": 0.5656996064712688,
1127
+ "learning_rate": 1.5469481581224274e-05,
1128
+ "loss": 0.2148549109697342,
1129
+ "num_input_tokens_seen": 0,
1130
+ "step": 140
1131
+ },
1132
+ {
1133
+ "epoch": 1.7625,
1134
+ "grad_norm": 0.5342290575425301,
1135
+ "learning_rate": 1.5400083978535475e-05,
1136
+ "loss": 0.221043199300766,
1137
+ "num_input_tokens_seen": 0,
1138
+ "step": 141
1139
+ },
1140
+ {
1141
+ "epoch": 1.775,
1142
+ "grad_norm": 0.5312824045538664,
1143
+ "learning_rate": 1.533031728727994e-05,
1144
+ "loss": 0.22295251488685608,
1145
+ "num_input_tokens_seen": 0,
1146
+ "step": 142
1147
+ },
1148
+ {
1149
+ "epoch": 1.7875,
1150
+ "grad_norm": 0.5532281742783289,
1151
+ "learning_rate": 1.526018627591834e-05,
1152
+ "loss": 0.23230503499507904,
1153
+ "num_input_tokens_seen": 0,
1154
+ "step": 143
1155
+ },
1156
+ {
1157
+ "epoch": 1.8,
1158
+ "grad_norm": 0.5486342376292719,
1159
+ "learning_rate": 1.5189695737812153e-05,
1160
+ "loss": 0.22794640064239502,
1161
+ "num_input_tokens_seen": 0,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 1.8125,
1166
+ "grad_norm": 0.5282686765938053,
1167
+ "learning_rate": 1.5118850490896012e-05,
1168
+ "loss": 0.23277482390403748,
1169
+ "num_input_tokens_seen": 0,
1170
+ "step": 145
1171
+ },
1172
+ {
1173
+ "epoch": 1.825,
1174
+ "grad_norm": 0.5221771559817829,
1175
+ "learning_rate": 1.504765537734844e-05,
1176
+ "loss": 0.23067018389701843,
1177
+ "num_input_tokens_seen": 0,
1178
+ "step": 146
1179
+ },
1180
+ {
1181
+ "epoch": 1.8375,
1182
+ "grad_norm": 0.5641718599884086,
1183
+ "learning_rate": 1.4976115263260876e-05,
1184
+ "loss": 0.21835649013519287,
1185
+ "num_input_tokens_seen": 0,
1186
+ "step": 147
1187
+ },
1188
+ {
1189
+ "epoch": 1.85,
1190
+ "grad_norm": 0.5505224831003699,
1191
+ "learning_rate": 1.4904235038305084e-05,
1192
+ "loss": 0.2256629765033722,
1193
+ "num_input_tokens_seen": 0,
1194
+ "step": 148
1195
+ },
1196
+ {
1197
+ "epoch": 1.8625,
1198
+ "grad_norm": 0.5686783195373294,
1199
+ "learning_rate": 1.4832019615398962e-05,
1200
+ "loss": 0.215658038854599,
1201
+ "num_input_tokens_seen": 0,
1202
+ "step": 149
1203
+ },
1204
+ {
1205
+ "epoch": 1.875,
1206
+ "grad_norm": 0.5570580083339357,
1207
+ "learning_rate": 1.4759473930370738e-05,
1208
+ "loss": 0.23637929558753967,
1209
+ "num_input_tokens_seen": 0,
1210
+ "step": 150
1211
+ },
1212
+ {
1213
+ "epoch": 1.8875,
1214
+ "grad_norm": 0.5613938118868574,
1215
+ "learning_rate": 1.4686602941621618e-05,
1216
+ "loss": 0.2198466658592224,
1217
+ "num_input_tokens_seen": 0,
1218
+ "step": 151
1219
+ },
1220
+ {
1221
+ "epoch": 1.9,
1222
+ "grad_norm": 0.5554584703399501,
1223
+ "learning_rate": 1.461341162978688e-05,
1224
+ "loss": 0.2246859222650528,
1225
+ "num_input_tokens_seen": 0,
1226
+ "step": 152
1227
+ },
1228
+ {
1229
+ "epoch": 1.9125,
1230
+ "grad_norm": 0.5909451217927424,
1231
+ "learning_rate": 1.4539904997395468e-05,
1232
+ "loss": 0.24911729991436005,
1233
+ "num_input_tokens_seen": 0,
1234
+ "step": 153
1235
+ },
1236
+ {
1237
+ "epoch": 1.925,
1238
+ "grad_norm": 0.5842777476606686,
1239
+ "learning_rate": 1.4466088068528068e-05,
1240
+ "loss": 0.23788337409496307,
1241
+ "num_input_tokens_seen": 0,
1242
+ "step": 154
1243
+ },
1244
+ {
1245
+ "epoch": 1.9375,
1246
+ "grad_norm": 0.4981326579110442,
1247
+ "learning_rate": 1.4391965888473705e-05,
1248
+ "loss": 0.2209474742412567,
1249
+ "num_input_tokens_seen": 0,
1250
+ "step": 155
1251
+ },
1252
+ {
1253
+ "epoch": 1.95,
1254
+ "grad_norm": 0.5397167568674605,
1255
+ "learning_rate": 1.4317543523384928e-05,
1256
+ "loss": 0.23926502466201782,
1257
+ "num_input_tokens_seen": 0,
1258
+ "step": 156
1259
+ },
1260
+ {
1261
+ "epoch": 1.9625,
1262
+ "grad_norm": 0.5359703981598113,
1263
+ "learning_rate": 1.4242826059931538e-05,
1264
+ "loss": 0.2312660813331604,
1265
+ "num_input_tokens_seen": 0,
1266
+ "step": 157
1267
+ },
1268
+ {
1269
+ "epoch": 1.975,
1270
+ "grad_norm": 0.5386500827778109,
1271
+ "learning_rate": 1.4167818604952906e-05,
1272
+ "loss": 0.2199496328830719,
1273
+ "num_input_tokens_seen": 0,
1274
+ "step": 158
1275
+ },
1276
+ {
1277
+ "epoch": 1.9875,
1278
+ "grad_norm": 0.5538059936709024,
1279
+ "learning_rate": 1.409252628510894e-05,
1280
+ "loss": 0.23412078619003296,
1281
+ "num_input_tokens_seen": 0,
1282
+ "step": 159
1283
+ },
1284
+ {
1285
+ "epoch": 2.0,
1286
+ "grad_norm": 0.540376667893175,
1287
+ "learning_rate": 1.4016954246529697e-05,
1288
+ "loss": 0.2249927967786789,
1289
+ "num_input_tokens_seen": 0,
1290
+ "step": 160
1291
+ },
1292
+ {
1293
+ "epoch": 2.0125,
1294
+ "grad_norm": 1.0198244871776765,
1295
+ "learning_rate": 1.3941107654463619e-05,
1296
+ "loss": 0.12236860394477844,
1297
+ "num_input_tokens_seen": 0,
1298
+ "step": 161
1299
+ },
1300
+ {
1301
+ "epoch": 2.025,
1302
+ "grad_norm": 0.8629260127173042,
1303
+ "learning_rate": 1.3864991692924524e-05,
1304
+ "loss": 0.11816570162773132,
1305
+ "num_input_tokens_seen": 0,
1306
+ "step": 162
1307
+ },
1308
+ {
1309
+ "epoch": 2.0375,
1310
+ "grad_norm": 0.6404376890511378,
1311
+ "learning_rate": 1.3788611564337277e-05,
1312
+ "loss": 0.10550174862146378,
1313
+ "num_input_tokens_seen": 0,
1314
+ "step": 163
1315
+ },
1316
+ {
1317
+ "epoch": 2.05,
1318
+ "grad_norm": 1.140833870667296,
1319
+ "learning_rate": 1.3711972489182208e-05,
1320
+ "loss": 0.10521072149276733,
1321
+ "num_input_tokens_seen": 0,
1322
+ "step": 164
1323
+ },
1324
+ {
1325
+ "epoch": 2.0625,
1326
+ "grad_norm": 1.004887415099318,
1327
+ "learning_rate": 1.3635079705638298e-05,
1328
+ "loss": 0.10304014384746552,
1329
+ "num_input_tokens_seen": 0,
1330
+ "step": 165
1331
+ },
1332
+ {
1333
+ "epoch": 2.075,
1334
+ "grad_norm": 0.7658325943968483,
1335
+ "learning_rate": 1.3557938469225167e-05,
1336
+ "loss": 0.10292299091815948,
1337
+ "num_input_tokens_seen": 0,
1338
+ "step": 166
1339
+ },
1340
+ {
1341
+ "epoch": 2.0875,
1342
+ "grad_norm": 0.7338849003327649,
1343
+ "learning_rate": 1.3480554052443847e-05,
1344
+ "loss": 0.10219870507717133,
1345
+ "num_input_tokens_seen": 0,
1346
+ "step": 167
1347
+ },
1348
+ {
1349
+ "epoch": 2.1,
1350
+ "grad_norm": 0.7745676732651274,
1351
+ "learning_rate": 1.3402931744416432e-05,
1352
+ "loss": 0.10130374133586884,
1353
+ "num_input_tokens_seen": 0,
1354
+ "step": 168
1355
+ },
1356
+ {
1357
+ "epoch": 2.1125,
1358
+ "grad_norm": 0.6584333483269132,
1359
+ "learning_rate": 1.332507685052457e-05,
1360
+ "loss": 0.10410261154174805,
1361
+ "num_input_tokens_seen": 0,
1362
+ "step": 169
1363
+ },
1364
+ {
1365
+ "epoch": 2.125,
1366
+ "grad_norm": 0.6821199419154345,
1367
+ "learning_rate": 1.3246994692046837e-05,
1368
+ "loss": 0.09977763891220093,
1369
+ "num_input_tokens_seen": 0,
1370
+ "step": 170
1371
+ },
1372
+ {
1373
+ "epoch": 2.1375,
1374
+ "grad_norm": 0.6358679555892452,
1375
+ "learning_rate": 1.3168690605795044e-05,
1376
+ "loss": 0.09835107624530792,
1377
+ "num_input_tokens_seen": 0,
1378
+ "step": 171
1379
+ },
1380
+ {
1381
+ "epoch": 2.15,
1382
+ "grad_norm": 0.6632837484026789,
1383
+ "learning_rate": 1.3090169943749475e-05,
1384
+ "loss": 0.09917747974395752,
1385
+ "num_input_tokens_seen": 0,
1386
+ "step": 172
1387
+ },
1388
+ {
1389
+ "epoch": 2.1625,
1390
+ "grad_norm": 0.6342553931938368,
1391
+ "learning_rate": 1.3011438072693077e-05,
1392
+ "loss": 0.09428848326206207,
1393
+ "num_input_tokens_seen": 0,
1394
+ "step": 173
1395
+ },
1396
+ {
1397
+ "epoch": 2.175,
1398
+ "grad_norm": 0.6387577881812592,
1399
+ "learning_rate": 1.293250037384465e-05,
1400
+ "loss": 0.0958920419216156,
1401
+ "num_input_tokens_seen": 0,
1402
+ "step": 174
1403
+ },
1404
+ {
1405
+ "epoch": 2.1875,
1406
+ "grad_norm": 0.6954184373882712,
1407
+ "learning_rate": 1.2853362242491054e-05,
1408
+ "loss": 0.09917563199996948,
1409
+ "num_input_tokens_seen": 0,
1410
+ "step": 175
1411
+ },
1412
+ {
1413
+ "epoch": 2.2,
1414
+ "grad_norm": 0.5974385656105545,
1415
+ "learning_rate": 1.2774029087618448e-05,
1416
+ "loss": 0.09344319999217987,
1417
+ "num_input_tokens_seen": 0,
1418
+ "step": 176
1419
+ },
1420
+ {
1421
+ "epoch": 2.2125,
1422
+ "grad_norm": 0.6472498757039972,
1423
+ "learning_rate": 1.269450633154258e-05,
1424
+ "loss": 0.10768131911754608,
1425
+ "num_input_tokens_seen": 0,
1426
+ "step": 177
1427
+ },
1428
+ {
1429
+ "epoch": 2.225,
1430
+ "grad_norm": 0.6685276002639324,
1431
+ "learning_rate": 1.26147994095382e-05,
1432
+ "loss": 0.10777394473552704,
1433
+ "num_input_tokens_seen": 0,
1434
+ "step": 178
1435
+ },
1436
+ {
1437
+ "epoch": 2.2375,
1438
+ "grad_norm": 0.6340976446307695,
1439
+ "learning_rate": 1.253491376946754e-05,
1440
+ "loss": 0.10363772511482239,
1441
+ "num_input_tokens_seen": 0,
1442
+ "step": 179
1443
+ },
1444
+ {
1445
+ "epoch": 2.25,
1446
+ "grad_norm": 0.5829966761174877,
1447
+ "learning_rate": 1.2454854871407993e-05,
1448
+ "loss": 0.09860391169786453,
1449
+ "num_input_tokens_seen": 0,
1450
+ "step": 180
1451
+ },
1452
+ {
1453
+ "epoch": 2.2625,
1454
+ "grad_norm": 0.6211718617191284,
1455
+ "learning_rate": 1.2374628187278888e-05,
1456
+ "loss": 0.09785199165344238,
1457
+ "num_input_tokens_seen": 0,
1458
+ "step": 181
1459
+ },
1460
+ {
1461
+ "epoch": 2.275,
1462
+ "grad_norm": 0.5692692956767395,
1463
+ "learning_rate": 1.2294239200467516e-05,
1464
+ "loss": 0.09915725886821747,
1465
+ "num_input_tokens_seen": 0,
1466
+ "step": 182
1467
+ },
1468
+ {
1469
+ "epoch": 2.2875,
1470
+ "grad_norm": 0.6193608649665566,
1471
+ "learning_rate": 1.2213693405454345e-05,
1472
+ "loss": 0.09728467464447021,
1473
+ "num_input_tokens_seen": 0,
1474
+ "step": 183
1475
+ },
1476
+ {
1477
+ "epoch": 2.3,
1478
+ "grad_norm": 0.6644514294612655,
1479
+ "learning_rate": 1.213299630743747e-05,
1480
+ "loss": 0.10535012185573578,
1481
+ "num_input_tokens_seen": 0,
1482
+ "step": 184
1483
+ },
1484
+ {
1485
+ "epoch": 2.3125,
1486
+ "grad_norm": 0.5826634498573604,
1487
+ "learning_rate": 1.2052153421956343e-05,
1488
+ "loss": 0.09781628847122192,
1489
+ "num_input_tokens_seen": 0,
1490
+ "step": 185
1491
+ },
1492
+ {
1493
+ "epoch": 2.325,
1494
+ "grad_norm": 0.6951420866310761,
1495
+ "learning_rate": 1.1971170274514802e-05,
1496
+ "loss": 0.09797348082065582,
1497
+ "num_input_tokens_seen": 0,
1498
+ "step": 186
1499
+ },
1500
+ {
1501
+ "epoch": 2.3375,
1502
+ "grad_norm": 0.6449424096000549,
1503
+ "learning_rate": 1.1890052400203405e-05,
1504
+ "loss": 0.11403355002403259,
1505
+ "num_input_tokens_seen": 0,
1506
+ "step": 187
1507
+ },
1508
+ {
1509
+ "epoch": 2.35,
1510
+ "grad_norm": 0.6977055112415091,
1511
+ "learning_rate": 1.1808805343321102e-05,
1512
+ "loss": 0.09498105198144913,
1513
+ "num_input_tokens_seen": 0,
1514
+ "step": 188
1515
+ },
1516
+ {
1517
+ "epoch": 2.3625,
1518
+ "grad_norm": 0.6309628403695112,
1519
+ "learning_rate": 1.1727434656996306e-05,
1520
+ "loss": 0.0992412120103836,
1521
+ "num_input_tokens_seen": 0,
1522
+ "step": 189
1523
+ },
1524
+ {
1525
+ "epoch": 2.375,
1526
+ "grad_norm": 0.6731776940075981,
1527
+ "learning_rate": 1.164594590280734e-05,
1528
+ "loss": 0.11293548345565796,
1529
+ "num_input_tokens_seen": 0,
1530
+ "step": 190
1531
+ },
1532
+ {
1533
+ "epoch": 2.3875,
1534
+ "grad_norm": 0.6741092344709629,
1535
+ "learning_rate": 1.156434465040231e-05,
1536
+ "loss": 0.094619981944561,
1537
+ "num_input_tokens_seen": 0,
1538
+ "step": 191
1539
+ },
1540
+ {
1541
+ "epoch": 2.4,
1542
+ "grad_norm": 0.5967386003242268,
1543
+ "learning_rate": 1.148263647711842e-05,
1544
+ "loss": 0.09347110986709595,
1545
+ "num_input_tokens_seen": 0,
1546
+ "step": 192
1547
+ },
1548
+ {
1549
+ "epoch": 2.4125,
1550
+ "grad_norm": 0.7159915413192838,
1551
+ "learning_rate": 1.140082696760078e-05,
1552
+ "loss": 0.10074266791343689,
1553
+ "num_input_tokens_seen": 0,
1554
+ "step": 193
1555
+ },
1556
+ {
1557
+ "epoch": 2.425,
1558
+ "grad_norm": 0.5968881913694516,
1559
+ "learning_rate": 1.1318921713420691e-05,
1560
+ "loss": 0.10465800762176514,
1561
+ "num_input_tokens_seen": 0,
1562
+ "step": 194
1563
+ },
1564
+ {
1565
+ "epoch": 2.4375,
1566
+ "grad_norm": 0.6589415029348668,
1567
+ "learning_rate": 1.123692631269348e-05,
1568
+ "loss": 0.10594508051872253,
1569
+ "num_input_tokens_seen": 0,
1570
+ "step": 195
1571
+ },
1572
+ {
1573
+ "epoch": 2.45,
1574
+ "grad_norm": 0.663988394877507,
1575
+ "learning_rate": 1.1154846369695864e-05,
1576
+ "loss": 0.09538954496383667,
1577
+ "num_input_tokens_seen": 0,
1578
+ "step": 196
1579
+ },
1580
+ {
1581
+ "epoch": 2.4625,
1582
+ "grad_norm": 0.6228831383495524,
1583
+ "learning_rate": 1.107268749448292e-05,
1584
+ "loss": 0.09765101969242096,
1585
+ "num_input_tokens_seen": 0,
1586
+ "step": 197
1587
+ },
1588
+ {
1589
+ "epoch": 2.475,
1590
+ "grad_norm": 0.61772733625651,
1591
+ "learning_rate": 1.099045530250463e-05,
1592
+ "loss": 0.09396866708993912,
1593
+ "num_input_tokens_seen": 0,
1594
+ "step": 198
1595
+ },
1596
+ {
1597
+ "epoch": 2.4875,
1598
+ "grad_norm": 0.5929697542542042,
1599
+ "learning_rate": 1.0908155414222083e-05,
1600
+ "loss": 0.09863300621509552,
1601
+ "num_input_tokens_seen": 0,
1602
+ "step": 199
1603
+ },
1604
+ {
1605
+ "epoch": 2.5,
1606
+ "grad_norm": 0.6899961462901135,
1607
+ "learning_rate": 1.0825793454723325e-05,
1608
+ "loss": 0.09633656591176987,
1609
+ "num_input_tokens_seen": 0,
1610
+ "step": 200
1611
+ },
1612
+ {
1613
+ "epoch": 2.5125,
1614
+ "grad_norm": 0.5997938148312979,
1615
+ "learning_rate": 1.0743375053338879e-05,
1616
+ "loss": 0.10011985152959824,
1617
+ "num_input_tokens_seen": 0,
1618
+ "step": 201
1619
+ },
1620
+ {
1621
+ "epoch": 2.525,
1622
+ "grad_norm": 0.6332752356735514,
1623
+ "learning_rate": 1.0660905843256995e-05,
1624
+ "loss": 0.09651218354701996,
1625
+ "num_input_tokens_seen": 0,
1626
+ "step": 202
1627
+ },
1628
+ {
1629
+ "epoch": 2.5375,
1630
+ "grad_norm": 0.6204192543359215,
1631
+ "learning_rate": 1.0578391461138642e-05,
1632
+ "loss": 0.0994209498167038,
1633
+ "num_input_tokens_seen": 0,
1634
+ "step": 203
1635
+ },
1636
+ {
1637
+ "epoch": 2.55,
1638
+ "grad_norm": 0.6132942561027718,
1639
+ "learning_rate": 1.0495837546732224e-05,
1640
+ "loss": 0.10166719555854797,
1641
+ "num_input_tokens_seen": 0,
1642
+ "step": 204
1643
+ },
1644
+ {
1645
+ "epoch": 2.5625,
1646
+ "grad_norm": 0.5964143279459994,
1647
+ "learning_rate": 1.0413249742488132e-05,
1648
+ "loss": 0.10079332441091537,
1649
+ "num_input_tokens_seen": 0,
1650
+ "step": 205
1651
+ },
1652
+ {
1653
+ "epoch": 2.575,
1654
+ "grad_norm": 0.6090535510158961,
1655
+ "learning_rate": 1.0330633693173083e-05,
1656
+ "loss": 0.10682345926761627,
1657
+ "num_input_tokens_seen": 0,
1658
+ "step": 206
1659
+ },
1660
+ {
1661
+ "epoch": 2.5875,
1662
+ "grad_norm": 0.5757143060836244,
1663
+ "learning_rate": 1.0247995045484303e-05,
1664
+ "loss": 0.10448747873306274,
1665
+ "num_input_tokens_seen": 0,
1666
+ "step": 207
1667
+ },
1668
+ {
1669
+ "epoch": 2.6,
1670
+ "grad_norm": 0.5318320587544387,
1671
+ "learning_rate": 1.0165339447663586e-05,
1672
+ "loss": 0.09677817672491074,
1673
+ "num_input_tokens_seen": 0,
1674
+ "step": 208
1675
+ },
1676
+ {
1677
+ "epoch": 2.6125,
1678
+ "grad_norm": 0.5653047610868341,
1679
+ "learning_rate": 1.008267254911125e-05,
1680
+ "loss": 0.10041716694831848,
1681
+ "num_input_tokens_seen": 0,
1682
+ "step": 209
1683
+ },
1684
+ {
1685
+ "epoch": 2.625,
1686
+ "grad_norm": 0.6709564219802151,
1687
+ "learning_rate": 1e-05,
1688
+ "loss": 0.11834404617547989,
1689
+ "num_input_tokens_seen": 0,
1690
+ "step": 210
1691
+ },
1692
+ {
1693
+ "epoch": 2.6375,
1694
+ "grad_norm": 0.59364936824183,
1695
+ "learning_rate": 9.917327450888751e-06,
1696
+ "loss": 0.10398055613040924,
1697
+ "num_input_tokens_seen": 0,
1698
+ "step": 211
1699
+ },
1700
+ {
1701
+ "epoch": 2.65,
1702
+ "grad_norm": 0.6135322123850998,
1703
+ "learning_rate": 9.834660552336415e-06,
1704
+ "loss": 0.09955007582902908,
1705
+ "num_input_tokens_seen": 0,
1706
+ "step": 212
1707
+ },
1708
+ {
1709
+ "epoch": 2.6625,
1710
+ "grad_norm": 0.5771675846362164,
1711
+ "learning_rate": 9.7520049545157e-06,
1712
+ "loss": 0.09840433299541473,
1713
+ "num_input_tokens_seen": 0,
1714
+ "step": 213
1715
+ },
1716
+ {
1717
+ "epoch": 2.675,
1718
+ "grad_norm": 0.6231353540589576,
1719
+ "learning_rate": 9.669366306826919e-06,
1720
+ "loss": 0.10380570590496063,
1721
+ "num_input_tokens_seen": 0,
1722
+ "step": 214
1723
+ },
1724
+ {
1725
+ "epoch": 2.6875,
1726
+ "grad_norm": 0.5948673639371316,
1727
+ "learning_rate": 9.586750257511868e-06,
1728
+ "loss": 0.0970538780093193,
1729
+ "num_input_tokens_seen": 0,
1730
+ "step": 215
1731
+ },
1732
+ {
1733
+ "epoch": 2.7,
1734
+ "grad_norm": 0.6060511739998478,
1735
+ "learning_rate": 9.504162453267776e-06,
1736
+ "loss": 0.10509540140628815,
1737
+ "num_input_tokens_seen": 0,
1738
+ "step": 216
1739
+ },
1740
+ {
1741
+ "epoch": 2.7125,
1742
+ "grad_norm": 0.5510731357722317,
1743
+ "learning_rate": 9.421608538861361e-06,
1744
+ "loss": 0.09432905912399292,
1745
+ "num_input_tokens_seen": 0,
1746
+ "step": 217
1747
+ },
1748
+ {
1749
+ "epoch": 2.725,
1750
+ "grad_norm": 0.6639639280503086,
1751
+ "learning_rate": 9.339094156743007e-06,
1752
+ "loss": 0.09837593883275986,
1753
+ "num_input_tokens_seen": 0,
1754
+ "step": 218
1755
+ },
1756
+ {
1757
+ "epoch": 2.7375,
1758
+ "grad_norm": 0.6270361275419634,
1759
+ "learning_rate": 9.256624946661126e-06,
1760
+ "loss": 0.10134841501712799,
1761
+ "num_input_tokens_seen": 0,
1762
+ "step": 219
1763
+ },
1764
+ {
1765
+ "epoch": 2.75,
1766
+ "grad_norm": 0.6771440915713338,
1767
+ "learning_rate": 9.174206545276678e-06,
1768
+ "loss": 0.11078701913356781,
1769
+ "num_input_tokens_seen": 0,
1770
+ "step": 220
1771
+ },
1772
+ {
1773
+ "epoch": 2.7625,
1774
+ "grad_norm": 0.705959945496674,
1775
+ "learning_rate": 9.091844585777919e-06,
1776
+ "loss": 0.1001749038696289,
1777
+ "num_input_tokens_seen": 0,
1778
+ "step": 221
1779
+ },
1780
+ {
1781
+ "epoch": 2.775,
1782
+ "grad_norm": 0.60937291192483,
1783
+ "learning_rate": 9.009544697495373e-06,
1784
+ "loss": 0.10557325184345245,
1785
+ "num_input_tokens_seen": 0,
1786
+ "step": 222
1787
+ },
1788
+ {
1789
+ "epoch": 2.7875,
1790
+ "grad_norm": 0.5893171675572725,
1791
+ "learning_rate": 8.927312505517086e-06,
1792
+ "loss": 0.10320694744586945,
1793
+ "num_input_tokens_seen": 0,
1794
+ "step": 223
1795
+ },
1796
+ {
1797
+ "epoch": 2.8,
1798
+ "grad_norm": 0.6133977099413181,
1799
+ "learning_rate": 8.84515363030414e-06,
1800
+ "loss": 0.09662497788667679,
1801
+ "num_input_tokens_seen": 0,
1802
+ "step": 224
1803
+ },
1804
+ {
1805
+ "epoch": 2.8125,
1806
+ "grad_norm": 0.6010610432879008,
1807
+ "learning_rate": 8.763073687306523e-06,
1808
+ "loss": 0.10481660068035126,
1809
+ "num_input_tokens_seen": 0,
1810
+ "step": 225
1811
+ },
1812
+ {
1813
+ "epoch": 2.825,
1814
+ "grad_norm": 0.6248420832412895,
1815
+ "learning_rate": 8.68107828657931e-06,
1816
+ "loss": 0.10239937901496887,
1817
+ "num_input_tokens_seen": 0,
1818
+ "step": 226
1819
+ },
1820
+ {
1821
+ "epoch": 2.8375,
1822
+ "grad_norm": 0.5868088627329976,
1823
+ "learning_rate": 8.599173032399222e-06,
1824
+ "loss": 0.10687953978776932,
1825
+ "num_input_tokens_seen": 0,
1826
+ "step": 227
1827
+ },
1828
+ {
1829
+ "epoch": 2.85,
1830
+ "grad_norm": 0.6268898716250957,
1831
+ "learning_rate": 8.51736352288158e-06,
1832
+ "loss": 0.10268527269363403,
1833
+ "num_input_tokens_seen": 0,
1834
+ "step": 228
1835
+ },
1836
+ {
1837
+ "epoch": 2.8625,
1838
+ "grad_norm": 0.6191681347772287,
1839
+ "learning_rate": 8.43565534959769e-06,
1840
+ "loss": 0.10145796835422516,
1841
+ "num_input_tokens_seen": 0,
1842
+ "step": 229
1843
+ },
1844
+ {
1845
+ "epoch": 2.875,
1846
+ "grad_norm": 0.6058846171541453,
1847
+ "learning_rate": 8.35405409719266e-06,
1848
+ "loss": 0.104601189494133,
1849
+ "num_input_tokens_seen": 0,
1850
+ "step": 230
1851
+ },
1852
+ {
1853
+ "epoch": 2.8875,
1854
+ "grad_norm": 0.5661519092091898,
1855
+ "learning_rate": 8.2725653430037e-06,
1856
+ "loss": 0.09631498157978058,
1857
+ "num_input_tokens_seen": 0,
1858
+ "step": 231
1859
+ },
1860
+ {
1861
+ "epoch": 2.9,
1862
+ "grad_norm": 0.5902711791447997,
1863
+ "learning_rate": 8.191194656678905e-06,
1864
+ "loss": 0.0936303585767746,
1865
+ "num_input_tokens_seen": 0,
1866
+ "step": 232
1867
+ },
1868
+ {
1869
+ "epoch": 2.9125,
1870
+ "grad_norm": 0.5638822103591541,
1871
+ "learning_rate": 8.109947599796599e-06,
1872
+ "loss": 0.1050085574388504,
1873
+ "num_input_tokens_seen": 0,
1874
+ "step": 233
1875
+ },
1876
+ {
1877
+ "epoch": 2.925,
1878
+ "grad_norm": 0.5703156532416298,
1879
+ "learning_rate": 8.0288297254852e-06,
1880
+ "loss": 0.09568509459495544,
1881
+ "num_input_tokens_seen": 0,
1882
+ "step": 234
1883
+ },
1884
+ {
1885
+ "epoch": 2.9375,
1886
+ "grad_norm": 0.6177421968590858,
1887
+ "learning_rate": 7.947846578043658e-06,
1888
+ "loss": 0.10282063484191895,
1889
+ "num_input_tokens_seen": 0,
1890
+ "step": 235
1891
+ },
1892
+ {
1893
+ "epoch": 2.95,
1894
+ "grad_norm": 0.5724279751966526,
1895
+ "learning_rate": 7.867003692562533e-06,
1896
+ "loss": 0.10039152950048447,
1897
+ "num_input_tokens_seen": 0,
1898
+ "step": 236
1899
+ },
1900
+ {
1901
+ "epoch": 2.9625,
1902
+ "grad_norm": 0.665494938328959,
1903
+ "learning_rate": 7.786306594545658e-06,
1904
+ "loss": 0.09484650194644928,
1905
+ "num_input_tokens_seen": 0,
1906
+ "step": 237
1907
+ },
1908
+ {
1909
+ "epoch": 2.975,
1910
+ "grad_norm": 0.5909403346328018,
1911
+ "learning_rate": 7.705760799532485e-06,
1912
+ "loss": 0.0970713198184967,
1913
+ "num_input_tokens_seen": 0,
1914
+ "step": 238
1915
+ },
1916
+ {
1917
+ "epoch": 2.9875,
1918
+ "grad_norm": 0.5930301687493515,
1919
+ "learning_rate": 7.625371812721115e-06,
1920
+ "loss": 0.1040472462773323,
1921
+ "num_input_tokens_seen": 0,
1922
+ "step": 239
1923
+ },
1924
+ {
1925
+ "epoch": 3.0,
1926
+ "grad_norm": 0.5975944410229318,
1927
+ "learning_rate": 7.545145128592009e-06,
1928
+ "loss": 0.10229268670082092,
1929
+ "num_input_tokens_seen": 0,
1930
+ "step": 240
1931
+ }
1932
+ ],
1933
+ "logging_steps": 1,
1934
+ "max_steps": 400,
1935
+ "num_input_tokens_seen": 0,
1936
+ "num_train_epochs": 5,
1937
+ "save_steps": 500,
1938
+ "stateful_callbacks": {
1939
+ "TrainerControl": {
1940
+ "args": {
1941
+ "should_epoch_stop": false,
1942
+ "should_evaluate": false,
1943
+ "should_log": false,
1944
+ "should_save": true,
1945
+ "should_training_stop": false
1946
+ },
1947
+ "attributes": {}
1948
+ }
1949
+ },
1950
+ "total_flos": 200924346515456.0,
1951
+ "train_batch_size": 4,
1952
+ "trial_name": null,
1953
+ "trial_params": null
1954
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069c746252d0631bff6d171f300fcef1b020cf21658ce399cf21202a7be231b3
3
+ size 9617