tejeshbhalla commited on
Commit
90e887f
·
verified ·
1 Parent(s): 329e0a4

Training in progress, step 100

Browse files
.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
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/highspeedstorage/ft-volume/llama",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": [],
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "k_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": true
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0ba879241d961eb8e67dc6251fc9367217c80e78cf3940807d84e4c56d82af
3
+ size 6627156248
args.json ADDED
@@ -0,0 +1,345 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/root/highspeedstorage/ft-volume/llama",
3
+ "model_type": "llama3_2",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "rope_scaling": null,
10
+ "device_map": null,
11
+ "local_repo_path": null,
12
+ "template": "llama3_2",
13
+ "system": "",
14
+ "max_length": 22000,
15
+ "truncation_strategy": "left",
16
+ "max_pixels": null,
17
+ "tools_prompt": "react_en",
18
+ "padding_side": "right",
19
+ "loss_scale": "default",
20
+ "sequence_parallel_size": 1,
21
+ "use_chat_template": true,
22
+ "template_backend": "swift",
23
+ "dataset": [
24
+ "llama_data.jsonl"
25
+ ],
26
+ "val_dataset": [],
27
+ "split_dataset_ratio": 0.01,
28
+ "data_seed": 42,
29
+ "dataset_num_proc": 1,
30
+ "streaming": false,
31
+ "enable_cache": false,
32
+ "download_mode": "reuse_dataset_if_exists",
33
+ "strict": false,
34
+ "model_name": [
35
+ null,
36
+ null
37
+ ],
38
+ "model_author": [
39
+ null,
40
+ null
41
+ ],
42
+ "custom_dataset_info": [],
43
+ "quant_method": null,
44
+ "quant_bits": null,
45
+ "hqq_axis": null,
46
+ "bnb_4bit_compute_dtype": "bfloat16",
47
+ "bnb_4bit_quant_type": "nf4",
48
+ "bnb_4bit_use_double_quant": true,
49
+ "bnb_4bit_quant_storage": null,
50
+ "max_new_tokens": 64,
51
+ "temperature": 0.0,
52
+ "top_k": null,
53
+ "top_p": null,
54
+ "repetition_penalty": null,
55
+ "num_beams": 1,
56
+ "stream": false,
57
+ "stop_words": [],
58
+ "logprobs": false,
59
+ "top_logprobs": null,
60
+ "ckpt_dir": null,
61
+ "load_dataset_config": null,
62
+ "lora_modules": [],
63
+ "tuner_backend": "peft",
64
+ "train_type": "lora",
65
+ "adapters": [],
66
+ "seed": 42,
67
+ "model_kwargs": {},
68
+ "load_args": true,
69
+ "load_data_args": false,
70
+ "use_hf": true,
71
+ "hub_token": null,
72
+ "custom_register_path": [],
73
+ "ignore_args_error": false,
74
+ "use_swift_lora": false,
75
+ "output_dir": "/root/dataDisk/llama-new/output/v3-20250124-205715",
76
+ "overwrite_output_dir": false,
77
+ "do_train": false,
78
+ "do_eval": false,
79
+ "do_predict": false,
80
+ "eval_strategy": "steps",
81
+ "prediction_loss_only": false,
82
+ "per_device_train_batch_size": 1,
83
+ "per_device_eval_batch_size": 1,
84
+ "per_gpu_train_batch_size": null,
85
+ "per_gpu_eval_batch_size": null,
86
+ "gradient_accumulation_steps": 16,
87
+ "eval_accumulation_steps": null,
88
+ "eval_delay": 0,
89
+ "torch_empty_cache_steps": null,
90
+ "learning_rate": 5e-05,
91
+ "weight_decay": 0.01,
92
+ "adam_beta1": 0.9,
93
+ "adam_beta2": 0.999,
94
+ "adam_epsilon": 1e-08,
95
+ "max_grad_norm": 1.0,
96
+ "num_train_epochs": 3.0,
97
+ "max_steps": -1,
98
+ "lr_scheduler_type": "linear",
99
+ "lr_scheduler_kwargs": null,
100
+ "warmup_ratio": 0.1,
101
+ "warmup_steps": 0,
102
+ "log_level": "passive",
103
+ "log_level_replica": "warning",
104
+ "log_on_each_node": true,
105
+ "logging_dir": "/root/dataDisk/llama-new/output/v3-20250124-205715/runs",
106
+ "logging_strategy": "steps",
107
+ "logging_first_step": true,
108
+ "logging_steps": 1,
109
+ "logging_nan_inf_filter": true,
110
+ "save_strategy": "steps",
111
+ "save_steps": 100.0,
112
+ "save_total_limit": 2,
113
+ "save_safetensors": true,
114
+ "save_on_each_node": false,
115
+ "save_only_model": false,
116
+ "restore_callback_states_from_checkpoint": false,
117
+ "no_cuda": false,
118
+ "use_cpu": false,
119
+ "use_mps_device": false,
120
+ "jit_mode_eval": false,
121
+ "use_ipex": false,
122
+ "bf16": true,
123
+ "fp16": false,
124
+ "fp16_opt_level": "O1",
125
+ "half_precision_backend": "auto",
126
+ "bf16_full_eval": false,
127
+ "fp16_full_eval": false,
128
+ "tf32": null,
129
+ "local_rank": 0,
130
+ "ddp_backend": null,
131
+ "tpu_num_cores": null,
132
+ "tpu_metrics_debug": false,
133
+ "debug": null,
134
+ "dataloader_drop_last": false,
135
+ "eval_steps": 100.0,
136
+ "dataloader_num_workers": 0,
137
+ "dataloader_prefetch_factor": null,
138
+ "past_index": -1,
139
+ "run_name": null,
140
+ "disable_tqdm": null,
141
+ "remove_unused_columns": false,
142
+ "label_names": null,
143
+ "load_best_model_at_end": false,
144
+ "metric_for_best_model": "loss",
145
+ "greater_is_better": false,
146
+ "ignore_data_skip": false,
147
+ "fsdp": "",
148
+ "fsdp_min_num_params": 0,
149
+ "fsdp_config": null,
150
+ "fsdp_transformer_layer_cls_to_wrap": null,
151
+ "accelerator_config": {
152
+ "dispatch_batches": false
153
+ },
154
+ "deepspeed": {
155
+ "fp16": {
156
+ "enabled": "auto",
157
+ "loss_scale": 0,
158
+ "loss_scale_window": 1000,
159
+ "initial_scale_power": 16,
160
+ "hysteresis": 2,
161
+ "min_loss_scale": 1
162
+ },
163
+ "bf16": {
164
+ "enabled": "auto"
165
+ },
166
+ "zero_optimization": {
167
+ "stage": 3,
168
+ "offload_optimizer": {
169
+ "device": "cpu",
170
+ "pin_memory": true
171
+ },
172
+ "offload_param": {
173
+ "device": "cpu",
174
+ "pin_memory": true
175
+ },
176
+ "overlap_comm": true,
177
+ "contiguous_gradients": true,
178
+ "sub_group_size": 1000000000.0,
179
+ "reduce_bucket_size": "auto",
180
+ "stage3_prefetch_bucket_size": "auto",
181
+ "stage3_param_persistence_threshold": "auto",
182
+ "stage3_max_live_parameters": 1000000000.0,
183
+ "stage3_max_reuse_distance": 1000000000.0,
184
+ "stage3_gather_16bit_weights_on_model_save": true
185
+ },
186
+ "gradient_accumulation_steps": "auto",
187
+ "gradient_clipping": "auto",
188
+ "steps_per_print": 2000,
189
+ "train_batch_size": "auto",
190
+ "train_micro_batch_size_per_gpu": "auto",
191
+ "wall_clock_breakdown": false
192
+ },
193
+ "label_smoothing_factor": 0.0,
194
+ "optim": "adamw_torch",
195
+ "optim_args": null,
196
+ "adafactor": false,
197
+ "group_by_length": false,
198
+ "length_column_name": "length",
199
+ "report_to": [
200
+ "wandb"
201
+ ],
202
+ "ddp_find_unused_parameters": null,
203
+ "ddp_bucket_cap_mb": null,
204
+ "ddp_broadcast_buffers": null,
205
+ "dataloader_pin_memory": true,
206
+ "dataloader_persistent_workers": false,
207
+ "skip_memory_metrics": true,
208
+ "use_legacy_prediction_loop": false,
209
+ "push_to_hub": true,
210
+ "resume_from_checkpoint": null,
211
+ "hub_model_id": "TheAgenticAI/LLAMA-3.3-70B-Reasoning",
212
+ "hub_strategy": "every_save",
213
+ "hub_private_repo": true,
214
+ "hub_always_push": false,
215
+ "gradient_checkpointing": true,
216
+ "gradient_checkpointing_kwargs": {
217
+ "use_reentrant": true
218
+ },
219
+ "include_inputs_for_metrics": false,
220
+ "include_for_metrics": [],
221
+ "eval_do_concat_batches": true,
222
+ "fp16_backend": "auto",
223
+ "evaluation_strategy": "steps",
224
+ "push_to_hub_model_id": null,
225
+ "push_to_hub_organization": null,
226
+ "push_to_hub_token": null,
227
+ "mp_parameters": "",
228
+ "auto_find_batch_size": false,
229
+ "full_determinism": false,
230
+ "torchdynamo": null,
231
+ "ray_scope": "last",
232
+ "ddp_timeout": 1800,
233
+ "torch_compile": false,
234
+ "torch_compile_backend": null,
235
+ "torch_compile_mode": null,
236
+ "dispatch_batches": null,
237
+ "split_batches": null,
238
+ "include_tokens_per_second": false,
239
+ "include_num_input_tokens_seen": false,
240
+ "neftune_noise_alpha": null,
241
+ "optim_target_modules": null,
242
+ "batch_eval_metrics": false,
243
+ "eval_on_start": false,
244
+ "use_liger_kernel": false,
245
+ "eval_use_gather_object": false,
246
+ "average_tokens_across_devices": false,
247
+ "sortish_sampler": false,
248
+ "predict_with_generate": false,
249
+ "generation_max_length": null,
250
+ "generation_num_beams": null,
251
+ "generation_config": null,
252
+ "freeze_parameters": [],
253
+ "freeze_parameters_ratio": 0.0,
254
+ "trainable_parameters": [],
255
+ "freeze_llm": false,
256
+ "freeze_vit": true,
257
+ "freeze_aligner": true,
258
+ "target_modules": [
259
+ "all-linear"
260
+ ],
261
+ "target_regex": null,
262
+ "modules_to_save": [],
263
+ "lora_rank": 256,
264
+ "lora_alpha": 64,
265
+ "lora_dropout": 0.05,
266
+ "lora_bias": "none",
267
+ "lora_dtype": null,
268
+ "lorap_lr_ratio": null,
269
+ "use_rslora": true,
270
+ "use_dora": false,
271
+ "lora_ga_batch_size": 2,
272
+ "lora_ga_iters": 2,
273
+ "lora_ga_max_length": 1024,
274
+ "lora_ga_direction": "ArB2r",
275
+ "lora_ga_scale": "stable",
276
+ "lora_ga_stable_gamma": 16,
277
+ "init_weights": true,
278
+ "fourier_n_frequency": 2000,
279
+ "fourier_scaling": 300.0,
280
+ "boft_block_size": 4,
281
+ "boft_block_num": 0,
282
+ "boft_n_butterfly_factor": 1,
283
+ "boft_dropout": 0.0,
284
+ "vera_rank": 256,
285
+ "vera_projection_prng_key": 0,
286
+ "vera_dropout": 0.0,
287
+ "vera_d_initial": 0.1,
288
+ "adapter_act": "gelu",
289
+ "adapter_length": 128,
290
+ "use_galore": false,
291
+ "galore_target_modules": null,
292
+ "galore_rank": 128,
293
+ "galore_update_proj_gap": 50,
294
+ "galore_scale": 1.0,
295
+ "galore_proj_type": "std",
296
+ "galore_optim_per_parameter": false,
297
+ "galore_with_embedding": false,
298
+ "galore_quantization": false,
299
+ "galore_proj_quant": false,
300
+ "galore_proj_bits": 4,
301
+ "galore_proj_group_size": 256,
302
+ "galore_cos_threshold": 0.4,
303
+ "galore_gamma_proj": 2,
304
+ "galore_queue_size": 5,
305
+ "adalora_target_r": 8,
306
+ "adalora_init_r": 12,
307
+ "adalora_tinit": 0,
308
+ "adalora_tfinal": 0,
309
+ "adalora_deltaT": 1,
310
+ "adalora_beta1": 0.85,
311
+ "adalora_beta2": 0.85,
312
+ "adalora_orth_reg_weight": 0.5,
313
+ "llamapro_num_new_blocks": 4,
314
+ "llamapro_num_groups": null,
315
+ "lisa_activated_layers": 0,
316
+ "lisa_step_interval": 20,
317
+ "reft_layer_key": null,
318
+ "reft_layers": null,
319
+ "reft_rank": 4,
320
+ "reft_intervention_type": "LoreftIntervention",
321
+ "reft_args": null,
322
+ "use_liger": false,
323
+ "model_layer_cls_name": null,
324
+ "metric_warmup_step": 0,
325
+ "fsdp_num": 1,
326
+ "acc_steps": 1,
327
+ "add_version": true,
328
+ "resume_only_model": false,
329
+ "check_model": true,
330
+ "packing": false,
331
+ "lazy_tokenize": false,
332
+ "loss_type": null,
333
+ "optimizer": null,
334
+ "metric": null,
335
+ "acc_strategy": "token",
336
+ "rank": 0,
337
+ "global_world_size": 8,
338
+ "local_world_size": 8,
339
+ "model_suffix": "llama",
340
+ "model_info": "ModelInfo(model_type='llama3_2', model_dir='/root/highspeedstorage/ft-volume/llama', torch_dtype=torch.bfloat16, max_model_len=8192, quant_method=None, quant_bits=None, config=None, task_type='causal_lm', num_labels=None)",
341
+ "model_meta": "ModelMeta(model_type='llama3_2', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.2-1B', hf_model_id='meta-llama/Llama-3.2-1B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B', hf_model_id='meta-llama/Llama-3.2-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-1B-Instruct', hf_model_id='meta-llama/Llama-3.2-1B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B-Instruct', hf_model_id='meta-llama/Llama-3.2-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.3-70B-Instruct', hf_model_id='meta-llama/Llama-3.3-70B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', hf_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='llama3_2', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f5a1d2fb2e0>, model_arch='llama', architectures=['LlamaForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.45'], tags=[])",
342
+ "model_dir": "/root/highspeedstorage/ft-volume/llama",
343
+ "hub": "<class 'swift.hub.hub.HFHub'>",
344
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/llama-new/output/v3-20250124-205715', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-05, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/llama-new/output/v3-20250124-205715/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/llama-new/output/v3-20250124-205715', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id='TheAgenticAI/LLAMA-3.3-70B-Reasoning', hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, galore_config=None)"
345
+ }
logging.jsonl ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"loss": 0.74616313, "token_acc": 0.84351861, "grad_norm": 0.09043229, "learning_rate": 1.72e-06, "memory(GiB)": 75.89, "train_speed(iter/s)": 0.003054, "epoch": 0.01032258, "global_step/max_steps": "1/288", "percentage": "0.35%", "elapsed_time": "5m 11s", "remaining_time": "1d 0h 50m 2s"}
2
+ {"loss": 0.78952539, "token_acc": 0.78098911, "grad_norm": 0.10398929, "learning_rate": 3.45e-06, "memory(GiB)": 75.89, "train_speed(iter/s)": 0.003215, "epoch": 0.02064516, "global_step/max_steps": "2/288", "percentage": "0.69%", "elapsed_time": "10m 6s", "remaining_time": "1d 0h 4m 37s"}
3
+ {"loss": 0.82183272, "token_acc": 0.79650972, "grad_norm": 0.11484293, "learning_rate": 5.17e-06, "memory(GiB)": 75.89, "train_speed(iter/s)": 0.003281, "epoch": 0.03096774, "global_step/max_steps": "3/288", "percentage": "1.04%", "elapsed_time": "14m 58s", "remaining_time": "23h 42m 19s"}
4
+ {"loss": 0.89525408, "token_acc": 0.79723175, "grad_norm": 0.15229513, "learning_rate": 6.9e-06, "memory(GiB)": 75.89, "train_speed(iter/s)": 0.003227, "epoch": 0.04129032, "global_step/max_steps": "4/288", "percentage": "1.39%", "elapsed_time": "20m 23s", "remaining_time": "1d 0h 7m 51s"}
5
+ {"loss": 0.87880141, "token_acc": 0.83182664, "grad_norm": 0.10113768, "learning_rate": 8.62e-06, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.003425, "epoch": 0.0516129, "global_step/max_steps": "5/288", "percentage": "1.74%", "elapsed_time": "24m 3s", "remaining_time": "22h 41m 53s"}
6
+ {"loss": 0.78032863, "token_acc": 0.78393572, "grad_norm": 0.07195292, "learning_rate": 1.034e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.00377, "epoch": 0.06193548, "global_step/max_steps": "6/288", "percentage": "2.08%", "elapsed_time": "26m 15s", "remaining_time": "20h 34m 2s"}
7
+ {"loss": 0.81582403, "token_acc": 0.80598127, "grad_norm": 0.03998778, "learning_rate": 1.207e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004052, "epoch": 0.07225806, "global_step/max_steps": "7/288", "percentage": "2.43%", "elapsed_time": "28m 31s", "remaining_time": "19h 5m 13s"}
8
+ {"loss": 0.70669603, "token_acc": 0.8440445, "grad_norm": 0.0443429, "learning_rate": 1.379e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004283, "epoch": 0.08258065, "global_step/max_steps": "8/288", "percentage": "2.78%", "elapsed_time": "30m 52s", "remaining_time": "18h 0m 22s"}
9
+ {"loss": 0.7262044, "token_acc": 0.81845238, "grad_norm": 0.04136974, "learning_rate": 1.552e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004467, "epoch": 0.09290323, "global_step/max_steps": "9/288", "percentage": "3.12%", "elapsed_time": "33m 18s", "remaining_time": "17h 12m 39s"}
10
+ {"loss": 0.87036347, "token_acc": 0.84759051, "grad_norm": 0.05472838, "learning_rate": 1.724e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004617, "epoch": 0.10322581, "global_step/max_steps": "10/288", "percentage": "3.47%", "elapsed_time": "35m 49s", "remaining_time": "16h 36m 4s"}
11
+ {"loss": 0.60506105, "token_acc": 0.84473466, "grad_norm": 0.03589521, "learning_rate": 1.897e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004782, "epoch": 0.11354839, "global_step/max_steps": "11/288", "percentage": "3.82%", "elapsed_time": "38m 4s", "remaining_time": "15h 58m 48s"}
12
+ {"loss": 0.83035898, "token_acc": 0.84033392, "grad_norm": 0.03401323, "learning_rate": 2.069e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.004884, "epoch": 0.12387097, "global_step/max_steps": "12/288", "percentage": "4.17%", "elapsed_time": "40m 40s", "remaining_time": "15h 35m 38s"}
13
+ {"loss": 0.56105936, "token_acc": 0.83656801, "grad_norm": 0.02542925, "learning_rate": 2.241e-05, "memory(GiB)": 100.51, "train_speed(iter/s)": 0.005025, "epoch": 0.13419355, "global_step/max_steps": "13/288", "percentage": "4.51%", "elapsed_time": "42m 51s", "remaining_time": "15h 6m 27s"}
14
+ {"loss": 0.69628751, "token_acc": 0.85242543, "grad_norm": 0.02137301, "learning_rate": 2.414e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005121, "epoch": 0.14451613, "global_step/max_steps": "14/288", "percentage": "4.86%", "elapsed_time": "45m 17s", "remaining_time": "14h 46m 28s"}
15
+ {"loss": 0.5410732, "token_acc": 0.834718, "grad_norm": 0.02185575, "learning_rate": 2.586e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005231, "epoch": 0.15483871, "global_step/max_steps": "15/288", "percentage": "5.21%", "elapsed_time": "47m 31s", "remaining_time": "14h 24m 54s"}
16
+ {"loss": 0.57584238, "token_acc": 0.83049947, "grad_norm": 0.01980691, "learning_rate": 2.759e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005352, "epoch": 0.16516129, "global_step/max_steps": "16/288", "percentage": "5.56%", "elapsed_time": "49m 33s", "remaining_time": "14h 2m 27s"}
17
+ {"loss": 0.56113476, "token_acc": 0.84900414, "grad_norm": 0.02572861, "learning_rate": 2.931e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005441, "epoch": 0.17548387, "global_step/max_steps": "17/288", "percentage": "5.90%", "elapsed_time": "51m 48s", "remaining_time": "13h 45m 52s"}
18
+ {"loss": 0.51780677, "token_acc": 0.86407566, "grad_norm": 0.01697748, "learning_rate": 3.103e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005525, "epoch": 0.18580645, "global_step/max_steps": "18/288", "percentage": "6.25%", "elapsed_time": "54m 1s", "remaining_time": "13h 30m 25s"}
19
+ {"loss": 0.5272339, "token_acc": 0.84709974, "grad_norm": 0.02022088, "learning_rate": 3.276e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005605, "epoch": 0.19612903, "global_step/max_steps": "19/288", "percentage": "6.60%", "elapsed_time": "56m 14s", "remaining_time": "13h 16m 10s"}
20
+ {"loss": 0.50596046, "token_acc": 0.82722892, "grad_norm": 0.01607172, "learning_rate": 3.448e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005684, "epoch": 0.20645161, "global_step/max_steps": "20/288", "percentage": "6.94%", "elapsed_time": "58m 22s", "remaining_time": "13h 2m 11s"}
21
+ {"loss": 0.49655235, "token_acc": 0.8496895, "grad_norm": 0.01419209, "learning_rate": 3.621e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.00576, "epoch": 0.21677419, "global_step/max_steps": "21/288", "percentage": "7.29%", "elapsed_time": "1h 0m 29s", "remaining_time": "12h 49m 9s"}
22
+ {"loss": 0.63461268, "token_acc": 0.86161907, "grad_norm": 0.02277333, "learning_rate": 3.793e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005796, "epoch": 0.22709677, "global_step/max_steps": "22/288", "percentage": "7.64%", "elapsed_time": "1h 2m 59s", "remaining_time": "12h 41m 42s"}
23
+ {"loss": 0.49595475, "token_acc": 0.84451534, "grad_norm": 0.01650185, "learning_rate": 3.966e-05, "memory(GiB)": 113.25, "train_speed(iter/s)": 0.005856, "epoch": 0.23741935, "global_step/max_steps": "23/288", "percentage": "7.99%", "elapsed_time": "1h 5m 11s", "remaining_time": "12h 31m 7s"}
24
+ {"loss": 0.58476871, "token_acc": 0.86130925, "grad_norm": 0.02474417, "learning_rate": 4.138e-05, "memory(GiB)": 128.5, "train_speed(iter/s)": 0.005889, "epoch": 0.24774194, "global_step/max_steps": "24/288", "percentage": "8.33%", "elapsed_time": "1h 7m 39s", "remaining_time": "12h 24m 14s"}
25
+ {"loss": 0.46254018, "token_acc": 0.87392386, "grad_norm": 0.01164004, "learning_rate": 4.31e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.005934, "epoch": 0.25806452, "global_step/max_steps": "25/288", "percentage": "8.68%", "elapsed_time": "1h 9m 57s", "remaining_time": "12h 15m 54s"}
26
+ {"loss": 0.4681581, "token_acc": 0.85397297, "grad_norm": 0.01212974, "learning_rate": 4.483e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.005981, "epoch": 0.2683871, "global_step/max_steps": "26/288", "percentage": "9.03%", "elapsed_time": "1h 12m 11s", "remaining_time": "12h 7m 25s"}
27
+ {"loss": 0.47845387, "token_acc": 0.84917576, "grad_norm": 0.01104543, "learning_rate": 4.655e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006041, "epoch": 0.27870968, "global_step/max_steps": "27/288", "percentage": "9.38%", "elapsed_time": "1h 14m 13s", "remaining_time": "11h 57m 31s"}
28
+ {"loss": 0.47385406, "token_acc": 0.86413749, "grad_norm": 0.01086575, "learning_rate": 4.828e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006094, "epoch": 0.28903226, "global_step/max_steps": "28/288", "percentage": "9.72%", "elapsed_time": "1h 16m 18s", "remaining_time": "11h 48m 38s"}
29
+ {"loss": 0.47718155, "token_acc": 0.8669849, "grad_norm": 0.01727354, "learning_rate": 5e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006098, "epoch": 0.29935484, "global_step/max_steps": "29/288", "percentage": "10.07%", "elapsed_time": "1h 18m 59s", "remaining_time": "11h 45m 32s"}
30
+ {"loss": 0.45292401, "token_acc": 0.84559537, "grad_norm": 0.04902146, "learning_rate": 4.981e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00614, "epoch": 0.30967742, "global_step/max_steps": "30/288", "percentage": "10.42%", "elapsed_time": "1h 21m 10s", "remaining_time": "11h 38m 3s"}
31
+ {"loss": 0.43841478, "token_acc": 0.86037951, "grad_norm": 0.01185949, "learning_rate": 4.961e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006182, "epoch": 0.32, "global_step/max_steps": "31/288", "percentage": "10.76%", "elapsed_time": "1h 23m 18s", "remaining_time": "11h 30m 42s"}
32
+ {"loss": 0.51614481, "token_acc": 0.86514002, "grad_norm": 0.03404158, "learning_rate": 4.942e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006206, "epoch": 0.33032258, "global_step/max_steps": "32/288", "percentage": "11.11%", "elapsed_time": "1h 25m 40s", "remaining_time": "11h 25m 24s"}
33
+ {"loss": 0.4681246, "token_acc": 0.82303734, "grad_norm": 0.01642565, "learning_rate": 4.923e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006237, "epoch": 0.34064516, "global_step/max_steps": "33/288", "percentage": "11.46%", "elapsed_time": "1h 27m 54s", "remaining_time": "11h 19m 21s"}
34
+ {"loss": 0.42925426, "token_acc": 0.87939367, "grad_norm": 0.00986654, "learning_rate": 4.903e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006271, "epoch": 0.35096774, "global_step/max_steps": "34/288", "percentage": "11.81%", "elapsed_time": "1h 30m 5s", "remaining_time": "11h 13m 5s"}
35
+ {"loss": 0.61444378, "token_acc": 0.80021854, "grad_norm": 0.0488668, "learning_rate": 4.884e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00628, "epoch": 0.36129032, "global_step/max_steps": "35/288", "percentage": "12.15%", "elapsed_time": "1h 32m 37s", "remaining_time": "11h 9m 32s"}
36
+ {"loss": 0.49848884, "token_acc": 0.87356891, "grad_norm": 0.02112174, "learning_rate": 4.865e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00629, "epoch": 0.3716129, "global_step/max_steps": "36/288", "percentage": "12.50%", "elapsed_time": "1h 35m 7s", "remaining_time": "11h 5m 52s"}
37
+ {"loss": 0.44967794, "token_acc": 0.86236844, "grad_norm": 0.00945088, "learning_rate": 4.846e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006325, "epoch": 0.38193548, "global_step/max_steps": "37/288", "percentage": "12.85%", "elapsed_time": "1h 37m 13s", "remaining_time": "10h 59m 36s"}
38
+ {"loss": 0.42617065, "token_acc": 0.87972228, "grad_norm": 0.00959377, "learning_rate": 4.826e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006351, "epoch": 0.39225806, "global_step/max_steps": "38/288", "percentage": "13.19%", "elapsed_time": "1h 39m 27s", "remaining_time": "10h 54m 16s"}
39
+ {"loss": 0.4227379, "token_acc": 0.88012363, "grad_norm": 0.01300816, "learning_rate": 4.807e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006377, "epoch": 0.40258065, "global_step/max_steps": "39/288", "percentage": "13.54%", "elapsed_time": "1h 41m 39s", "remaining_time": "10h 49m 2s"}
40
+ {"loss": 0.41896996, "token_acc": 0.84762152, "grad_norm": 0.01550369, "learning_rate": 4.788e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006409, "epoch": 0.41290323, "global_step/max_steps": "40/288", "percentage": "13.89%", "elapsed_time": "1h 43m 45s", "remaining_time": "10h 43m 17s"}
41
+ {"loss": 0.44419405, "token_acc": 0.81527302, "grad_norm": 0.01633696, "learning_rate": 4.768e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00643, "epoch": 0.42322581, "global_step/max_steps": "41/288", "percentage": "14.24%", "elapsed_time": "1h 46m 0s", "remaining_time": "10h 38m 37s"}
42
+ {"loss": 0.4448446, "token_acc": 0.84361949, "grad_norm": 0.00948541, "learning_rate": 4.749e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006465, "epoch": 0.43354839, "global_step/max_steps": "42/288", "percentage": "14.58%", "elapsed_time": "1h 48m 0s", "remaining_time": "10h 32m 36s"}
43
+ {"loss": 0.4308551, "token_acc": 0.85782495, "grad_norm": 0.12180801, "learning_rate": 4.73e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006475, "epoch": 0.44387097, "global_step/max_steps": "43/288", "percentage": "14.93%", "elapsed_time": "1h 50m 24s", "remaining_time": "10h 29m 5s"}
44
+ {"loss": 0.43652752, "token_acc": 0.84613588, "grad_norm": 0.00945682, "learning_rate": 4.71e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006501, "epoch": 0.45419355, "global_step/max_steps": "44/288", "percentage": "15.28%", "elapsed_time": "1h 52m 32s", "remaining_time": "10h 24m 4s"}
45
+ {"loss": 0.42303067, "token_acc": 0.88438384, "grad_norm": 0.00908574, "learning_rate": 4.691e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00652, "epoch": 0.46451613, "global_step/max_steps": "45/288", "percentage": "15.62%", "elapsed_time": "1h 54m 46s", "remaining_time": "10h 19m 46s"}
46
+ {"loss": 0.40082443, "token_acc": 0.87893522, "grad_norm": 0.01320151, "learning_rate": 4.672e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006535, "epoch": 0.47483871, "global_step/max_steps": "46/288", "percentage": "15.97%", "elapsed_time": "1h 57m 2s", "remaining_time": "10h 15m 44s"}
47
+ {"loss": 0.39771432, "token_acc": 0.87401729, "grad_norm": 0.01309315, "learning_rate": 4.653e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00655, "epoch": 0.48516129, "global_step/max_steps": "47/288", "percentage": "16.32%", "elapsed_time": "1h 59m 19s", "remaining_time": "10h 11m 50s"}
48
+ {"loss": 0.43932644, "token_acc": 0.86438174, "grad_norm": 0.01308558, "learning_rate": 4.633e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006571, "epoch": 0.49548387, "global_step/max_steps": "48/288", "percentage": "16.67%", "elapsed_time": "2h 1m 29s", "remaining_time": "10h 7m 25s"}
49
+ {"loss": 0.40402907, "token_acc": 0.87178259, "grad_norm": 0.01584367, "learning_rate": 4.614e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006585, "epoch": 0.50580645, "global_step/max_steps": "49/288", "percentage": "17.01%", "elapsed_time": "2h 3m 44s", "remaining_time": "10h 3m 34s"}
50
+ {"loss": 0.42721552, "token_acc": 0.87538548, "grad_norm": 0.01127676, "learning_rate": 4.595e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006605, "epoch": 0.51612903, "global_step/max_steps": "50/288", "percentage": "17.36%", "elapsed_time": "2h 5m 54s", "remaining_time": "9h 59m 17s"}
51
+ {"loss": 0.54179633, "token_acc": 0.84423901, "grad_norm": 0.03042504, "learning_rate": 4.575e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.0066, "epoch": 0.52645161, "global_step/max_steps": "51/288", "percentage": "17.71%", "elapsed_time": "2h 8m 31s", "remaining_time": "9h 57m 16s"}
52
+ {"loss": 0.40824139, "token_acc": 0.85981165, "grad_norm": 0.01089707, "learning_rate": 4.556e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006621, "epoch": 0.53677419, "global_step/max_steps": "52/288", "percentage": "18.06%", "elapsed_time": "2h 10m 38s", "remaining_time": "9h 52m 52s"}
53
+ {"loss": 0.5188899, "token_acc": 0.86626307, "grad_norm": 0.02277813, "learning_rate": 4.537e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006632, "epoch": 0.54709677, "global_step/max_steps": "53/288", "percentage": "18.40%", "elapsed_time": "2h 12m 55s", "remaining_time": "9h 49m 21s"}
54
+ {"loss": 0.49796051, "token_acc": 0.87458007, "grad_norm": 0.10761227, "learning_rate": 4.517e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00665, "epoch": 0.55741935, "global_step/max_steps": "54/288", "percentage": "18.75%", "elapsed_time": "2h 15m 4s", "remaining_time": "9h 45m 18s"}
55
+ {"loss": 0.55097961, "token_acc": 0.7219632, "grad_norm": 0.0301041, "learning_rate": 4.498e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006655, "epoch": 0.56774194, "global_step/max_steps": "55/288", "percentage": "19.10%", "elapsed_time": "2h 17m 28s", "remaining_time": "9h 42m 22s"}
56
+ {"loss": 0.40282875, "token_acc": 0.88147197, "grad_norm": 0.02567812, "learning_rate": 4.479e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006667, "epoch": 0.57806452, "global_step/max_steps": "56/288", "percentage": "19.44%", "elapsed_time": "2h 19m 43s", "remaining_time": "9h 38m 53s"}
57
+ {"loss": 0.4145909, "token_acc": 0.86279797, "grad_norm": 0.09259639, "learning_rate": 4.459e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006681, "epoch": 0.5883871, "global_step/max_steps": "57/288", "percentage": "19.79%", "elapsed_time": "2h 21m 56s", "remaining_time": "9h 35m 13s"}
58
+ {"loss": 0.49579778, "token_acc": 0.86323816, "grad_norm": 0.2940706, "learning_rate": 4.44e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006688, "epoch": 0.59870968, "global_step/max_steps": "58/288", "percentage": "20.14%", "elapsed_time": "2h 24m 16s", "remaining_time": "9h 32m 7s"}
59
+ {"loss": 0.40309823, "token_acc": 0.88168864, "grad_norm": 0.35733849, "learning_rate": 4.421e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006701, "epoch": 0.60903226, "global_step/max_steps": "59/288", "percentage": "20.49%", "elapsed_time": "2h 26m 28s", "remaining_time": "9h 28m 31s"}
60
+ {"loss": 0.42548287, "token_acc": 0.85303217, "grad_norm": 0.971573, "learning_rate": 4.402e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006715, "epoch": 0.61935484, "global_step/max_steps": "60/288", "percentage": "20.83%", "elapsed_time": "2h 28m 38s", "remaining_time": "9h 24m 50s"}
61
+ {"loss": 0.43157196, "token_acc": 0.86270378, "grad_norm": 0.97569734, "learning_rate": 4.382e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006734, "epoch": 0.62967742, "global_step/max_steps": "61/288", "percentage": "21.18%", "elapsed_time": "2h 30m 42s", "remaining_time": "9h 20m 48s"}
62
+ {"loss": 0.40518153, "token_acc": 0.88739643, "grad_norm": 0.02967451, "learning_rate": 4.363e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006748, "epoch": 0.64, "global_step/max_steps": "62/288", "percentage": "21.53%", "elapsed_time": "2h 32m 52s", "remaining_time": "9h 17m 15s"}
63
+ {"loss": 0.4438884, "token_acc": 0.87470964, "grad_norm": 0.01226234, "learning_rate": 4.344e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006765, "epoch": 0.65032258, "global_step/max_steps": "63/288", "percentage": "21.88%", "elapsed_time": "2h 34m 57s", "remaining_time": "9h 13m 23s"}
64
+ {"loss": 0.39373183, "token_acc": 0.88465558, "grad_norm": 0.05350703, "learning_rate": 4.324e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006778, "epoch": 0.66064516, "global_step/max_steps": "64/288", "percentage": "22.22%", "elapsed_time": "2h 37m 6s", "remaining_time": "9h 9m 53s"}
65
+ {"loss": 0.44090027, "token_acc": 0.87650124, "grad_norm": 0.06398247, "learning_rate": 4.305e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006791, "epoch": 0.67096774, "global_step/max_steps": "65/288", "percentage": "22.57%", "elapsed_time": "2h 39m 15s", "remaining_time": "9h 6m 23s"}
66
+ {"loss": 0.47568282, "token_acc": 0.88244228, "grad_norm": 0.07284541, "learning_rate": 4.286e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006791, "epoch": 0.68129032, "global_step/max_steps": "66/288", "percentage": "22.92%", "elapsed_time": "2h 41m 42s", "remaining_time": "9h 3m 54s"}
67
+ {"loss": 0.40231276, "token_acc": 0.859897, "grad_norm": 0.02990863, "learning_rate": 4.266e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006801, "epoch": 0.6916129, "global_step/max_steps": "67/288", "percentage": "23.26%", "elapsed_time": "2h 43m 55s", "remaining_time": "9h 0m 43s"}
68
+ {"loss": 0.45850387, "token_acc": 0.86981746, "grad_norm": 0.07461943, "learning_rate": 4.247e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006808, "epoch": 0.70193548, "global_step/max_steps": "68/288", "percentage": "23.61%", "elapsed_time": "2h 46m 12s", "remaining_time": "8h 57m 43s"}
69
+ {"loss": 0.42772788, "token_acc": 0.86058025, "grad_norm": 0.01338425, "learning_rate": 4.228e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00682, "epoch": 0.71225806, "global_step/max_steps": "69/288", "percentage": "23.96%", "elapsed_time": "2h 48m 20s", "remaining_time": "8h 54m 18s"}
70
+ {"loss": 0.50105357, "token_acc": 0.88452936, "grad_norm": 0.08125398, "learning_rate": 4.208e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006823, "epoch": 0.72258065, "global_step/max_steps": "70/288", "percentage": "24.31%", "elapsed_time": "2h 50m 42s", "remaining_time": "8h 51m 38s"}
71
+ {"loss": 0.38152462, "token_acc": 0.8830297, "grad_norm": 0.01115579, "learning_rate": 4.189e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006831, "epoch": 0.73290323, "global_step/max_steps": "71/288", "percentage": "24.65%", "elapsed_time": "2h 52m 57s", "remaining_time": "8h 48m 37s"}
72
+ {"loss": 0.39672104, "token_acc": 0.88033904, "grad_norm": 0.01423557, "learning_rate": 4.17e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006843, "epoch": 0.74322581, "global_step/max_steps": "72/288", "percentage": "25.00%", "elapsed_time": "2h 55m 6s", "remaining_time": "8h 45m 18s"}
73
+ {"loss": 0.43814272, "token_acc": 0.88551196, "grad_norm": 0.14627557, "learning_rate": 4.151e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006843, "epoch": 0.75354839, "global_step/max_steps": "73/288", "percentage": "25.35%", "elapsed_time": "2h 57m 32s", "remaining_time": "8h 42m 53s"}
74
+ {"loss": 0.3858158, "token_acc": 0.86370734, "grad_norm": 0.05014987, "learning_rate": 4.131e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006845, "epoch": 0.76387097, "global_step/max_steps": "74/288", "percentage": "25.69%", "elapsed_time": "2h 59m 55s", "remaining_time": "8h 40m 18s"}
75
+ {"loss": 0.37708718, "token_acc": 0.89819705, "grad_norm": 0.08282039, "learning_rate": 4.112e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006855, "epoch": 0.77419355, "global_step/max_steps": "75/288", "percentage": "26.04%", "elapsed_time": "3h 2m 5s", "remaining_time": "8h 37m 8s"}
76
+ {"loss": 0.40146717, "token_acc": 0.87541194, "grad_norm": 0.03130351, "learning_rate": 4.093e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00686, "epoch": 0.78451613, "global_step/max_steps": "76/288", "percentage": "26.39%", "elapsed_time": "3h 4m 23s", "remaining_time": "8h 34m 20s"}
77
+ {"loss": 0.45210558, "token_acc": 0.86619006, "grad_norm": 0.24303684, "learning_rate": 4.073e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006858, "epoch": 0.79483871, "global_step/max_steps": "77/288", "percentage": "26.74%", "elapsed_time": "3h 6m 52s", "remaining_time": "8h 32m 4s"}
78
+ {"loss": 0.42958081, "token_acc": 0.85775103, "grad_norm": 0.01276872, "learning_rate": 4.054e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006869, "epoch": 0.80516129, "global_step/max_steps": "78/288", "percentage": "27.08%", "elapsed_time": "3h 8m 59s", "remaining_time": "8h 28m 50s"}
79
+ {"loss": 0.40100986, "token_acc": 0.8705993, "grad_norm": 0.0461642, "learning_rate": 4.035e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006862, "epoch": 0.81548387, "global_step/max_steps": "79/288", "percentage": "27.43%", "elapsed_time": "3h 11m 36s", "remaining_time": "8h 26m 53s"}
80
+ {"loss": 0.38652623, "token_acc": 0.89047065, "grad_norm": 0.07440139, "learning_rate": 4.015e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006869, "epoch": 0.82580645, "global_step/max_steps": "80/288", "percentage": "27.78%", "elapsed_time": "3h 13m 49s", "remaining_time": "8h 23m 57s"}
81
+ {"loss": 0.38682115, "token_acc": 0.87585879, "grad_norm": 0.01817736, "learning_rate": 3.996e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006875, "epoch": 0.83612903, "global_step/max_steps": "81/288", "percentage": "28.12%", "elapsed_time": "3h 16m 6s", "remaining_time": "8h 21m 10s"}
82
+ {"loss": 0.41781539, "token_acc": 0.85694046, "grad_norm": 0.02927447, "learning_rate": 3.977e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.00688, "epoch": 0.84645161, "global_step/max_steps": "82/288", "percentage": "28.47%", "elapsed_time": "3h 18m 22s", "remaining_time": "8h 18m 20s"}
83
+ {"loss": 0.39182213, "token_acc": 0.89268926, "grad_norm": 0.06937289, "learning_rate": 3.958e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006885, "epoch": 0.85677419, "global_step/max_steps": "83/288", "percentage": "28.82%", "elapsed_time": "3h 20m 38s", "remaining_time": "8h 15m 34s"}
84
+ {"loss": 0.37565386, "token_acc": 0.88184552, "grad_norm": 0.05194683, "learning_rate": 3.938e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006893, "epoch": 0.86709677, "global_step/max_steps": "84/288", "percentage": "29.17%", "elapsed_time": "3h 22m 49s", "remaining_time": "8h 12m 34s"}
85
+ {"loss": 0.45567641, "token_acc": 0.86954447, "grad_norm": 0.05576006, "learning_rate": 3.919e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006891, "epoch": 0.87741935, "global_step/max_steps": "85/288", "percentage": "29.51%", "elapsed_time": "3h 25m 18s", "remaining_time": "8h 10m 19s"}
86
+ {"loss": 0.37166446, "token_acc": 0.89650233, "grad_norm": 0.03371212, "learning_rate": 3.9e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006895, "epoch": 0.88774194, "global_step/max_steps": "86/288", "percentage": "29.86%", "elapsed_time": "3h 27m 36s", "remaining_time": "8h 7m 39s"}
87
+ {"loss": 0.41649836, "token_acc": 0.87910183, "grad_norm": 0.01462127, "learning_rate": 3.88e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006898, "epoch": 0.89806452, "global_step/max_steps": "87/288", "percentage": "30.21%", "elapsed_time": "3h 29m 56s", "remaining_time": "8h 5m 3s"}
88
+ {"loss": 0.41595942, "token_acc": 0.85043611, "grad_norm": 0.01152844, "learning_rate": 3.861e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006908, "epoch": 0.9083871, "global_step/max_steps": "88/288", "percentage": "30.56%", "elapsed_time": "3h 32m 3s", "remaining_time": "8h 1m 56s"}
89
+ {"loss": 0.38049665, "token_acc": 0.88799895, "grad_norm": 0.00966426, "learning_rate": 3.842e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006917, "epoch": 0.91870968, "global_step/max_steps": "89/288", "percentage": "30.90%", "elapsed_time": "3h 34m 10s", "remaining_time": "7h 58m 53s"}
90
+ {"loss": 0.40713, "token_acc": 0.8783668, "grad_norm": 0.01316505, "learning_rate": 3.822e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006923, "epoch": 0.92903226, "global_step/max_steps": "90/288", "percentage": "31.25%", "elapsed_time": "3h 36m 25s", "remaining_time": "7h 56m 7s"}
91
+ {"loss": 0.4486534, "token_acc": 0.85522959, "grad_norm": 0.04914835, "learning_rate": 3.803e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006923, "epoch": 0.93935484, "global_step/max_steps": "91/288", "percentage": "31.60%", "elapsed_time": "3h 38m 49s", "remaining_time": "7h 53m 43s"}
92
+ {"loss": 0.37252715, "token_acc": 0.8659446, "grad_norm": 0.00998468, "learning_rate": 3.784e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006929, "epoch": 0.94967742, "global_step/max_steps": "92/288", "percentage": "31.94%", "elapsed_time": "3h 41m 0s", "remaining_time": "7h 50m 51s"}
93
+ {"loss": 0.39902872, "token_acc": 0.87282829, "grad_norm": 0.01568112, "learning_rate": 3.764e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006928, "epoch": 0.96, "global_step/max_steps": "93/288", "percentage": "32.29%", "elapsed_time": "3h 43m 28s", "remaining_time": "7h 48m 33s"}
94
+ {"loss": 0.36277354, "token_acc": 0.88438775, "grad_norm": 0.0237332, "learning_rate": 3.745e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006933, "epoch": 0.97032258, "global_step/max_steps": "94/288", "percentage": "32.64%", "elapsed_time": "3h 45m 42s", "remaining_time": "7h 45m 48s"}
95
+ {"loss": 0.38434136, "token_acc": 0.8888924, "grad_norm": 0.00939997, "learning_rate": 3.726e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006939, "epoch": 0.98064516, "global_step/max_steps": "95/288", "percentage": "32.99%", "elapsed_time": "3h 47m 54s", "remaining_time": "7h 43m 0s"}
96
+ {"loss": 0.36436903, "token_acc": 0.89673349, "grad_norm": 0.01110194, "learning_rate": 3.707e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006944, "epoch": 0.99096774, "global_step/max_steps": "96/288", "percentage": "33.33%", "elapsed_time": "3h 50m 8s", "remaining_time": "7h 40m 16s"}
97
+ {"loss": 0.78716338, "token_acc": 0.87718253, "grad_norm": 0.01389996, "learning_rate": 3.687e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006908, "epoch": 1.01032258, "global_step/max_steps": "97/288", "percentage": "33.68%", "elapsed_time": "3h 53m 45s", "remaining_time": "7h 40m 16s"}
98
+ {"loss": 0.40994811, "token_acc": 0.82488286, "grad_norm": 0.18944687, "learning_rate": 3.668e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006908, "epoch": 1.02064516, "global_step/max_steps": "98/288", "percentage": "34.03%", "elapsed_time": "3h 56m 9s", "remaining_time": "7h 37m 51s"}
99
+ {"loss": 0.36000898, "token_acc": 0.90903877, "grad_norm": 0.0123647, "learning_rate": 3.649e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006912, "epoch": 1.03096774, "global_step/max_steps": "99/288", "percentage": "34.38%", "elapsed_time": "3h 58m 26s", "remaining_time": "7h 35m 11s"}
100
+ {"loss": 0.38061467, "token_acc": 0.89940414, "grad_norm": 0.01069106, "learning_rate": 3.629e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006917, "epoch": 1.04129032, "global_step/max_steps": "100/288", "percentage": "34.72%", "elapsed_time": "4h 0m 42s", "remaining_time": "7h 32m 31s"}
101
+ {"eval_loss": 0.39166829, "eval_token_acc": 0.88091295, "eval_runtime": 48.768, "eval_samples_per_second": 2.563, "eval_steps_per_second": 0.328, "epoch": 1.04129032, "global_step/max_steps": "100/288", "percentage": "34.72%", "elapsed_time": "4h 1m 30s", "remaining_time": "7h 34m 2s"}
102
+ {"loss": 0.37255841, "token_acc": 0.88312756, "grad_norm": 0.01173662, "learning_rate": 3.61e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006886, "epoch": 1.0516129, "global_step/max_steps": "101/288", "percentage": "35.07%", "elapsed_time": "4h 4m 10s", "remaining_time": "7h 32m 5s"}
103
+ {"loss": 0.36340833, "token_acc": 0.87858518, "grad_norm": 0.01821016, "learning_rate": 3.591e-05, "memory(GiB)": 130.45, "train_speed(iter/s)": 0.006891, "epoch": 1.06193548, "global_step/max_steps": "102/288", "percentage": "35.42%", "elapsed_time": "4h 6m 25s", "remaining_time": "7h 29m 21s"}
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 1000000000000000019884624838656,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62aec4a16ad7784426afd2d42eaebf68758b687450726ad42691b8511c06d4e7
3
+ size 8184