consultantQ commited on
Commit
bea6243
·
verified ·
1 Parent(s): 622ada9

Upload folder using huggingface_hub

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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
args.json ADDED
@@ -0,0 +1,389 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": 3,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": null,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": null,
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "tensorboard"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": null,
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": true,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": null,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "check_model": true,
189
+ "acc_strategy": "token",
190
+ "train_dataloader_shuffle": true,
191
+ "max_epochs": null,
192
+ "aligner_lr": null,
193
+ "vit_lr": null,
194
+ "use_logits_to_keep": null,
195
+ "ds3_gather_for_generation": true,
196
+ "resume_only_model": false,
197
+ "optimizer": null,
198
+ "loss_type": null,
199
+ "metric": null,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "extra_eval_args": null,
206
+ "use_flash_ckpt": false,
207
+ "use_ray": false,
208
+ "ray_exp_name": null,
209
+ "device_groups": null,
210
+ "model": "/data2/PLMs/Qwen3-4B-Instruct-2507",
211
+ "model_type": "qwen3_nothinking",
212
+ "model_revision": null,
213
+ "task_type": "causal_lm",
214
+ "torch_dtype": "bfloat16",
215
+ "attn_impl": "flash_attn",
216
+ "new_special_tokens": [],
217
+ "num_labels": null,
218
+ "problem_type": null,
219
+ "rope_scaling": null,
220
+ "device_map": null,
221
+ "max_memory": {},
222
+ "max_model_len": null,
223
+ "local_repo_path": null,
224
+ "init_strategy": null,
225
+ "template": "qwen3_nothinking",
226
+ "system": null,
227
+ "max_length": 24576,
228
+ "truncation_strategy": "delete",
229
+ "max_pixels": null,
230
+ "agent_template": null,
231
+ "norm_bbox": null,
232
+ "use_chat_template": true,
233
+ "padding_free": false,
234
+ "padding_side": "right",
235
+ "loss_scale": "default",
236
+ "sequence_parallel_size": 1,
237
+ "response_prefix": null,
238
+ "template_backend": "swift",
239
+ "dataset": [
240
+ "/data/qzs/AutoSDT-main/datasets/generate_prm_traj/format_train_data_total_no_indentation_error.json"
241
+ ],
242
+ "val_dataset": [],
243
+ "cached_dataset": [],
244
+ "cached_val_dataset": [],
245
+ "split_dataset_ratio": 0.0,
246
+ "dataset_num_proc": 8,
247
+ "load_from_cache_file": false,
248
+ "dataset_shuffle": true,
249
+ "val_dataset_shuffle": false,
250
+ "streaming": false,
251
+ "interleave_prob": null,
252
+ "stopping_strategy": "first_exhausted",
253
+ "shuffle_buffer_size": 1000,
254
+ "download_mode": "reuse_dataset_if_exists",
255
+ "columns": {},
256
+ "strict": false,
257
+ "model_name": null,
258
+ "model_author": null,
259
+ "custom_dataset_info": [],
260
+ "quant_method": null,
261
+ "quant_bits": null,
262
+ "hqq_axis": null,
263
+ "bnb_4bit_compute_dtype": "bfloat16",
264
+ "bnb_4bit_quant_type": "nf4",
265
+ "bnb_4bit_use_double_quant": true,
266
+ "bnb_4bit_quant_storage": null,
267
+ "max_new_tokens": 64,
268
+ "temperature": 0.0,
269
+ "top_k": null,
270
+ "top_p": null,
271
+ "repetition_penalty": null,
272
+ "num_beams": 1,
273
+ "stream": false,
274
+ "stop_words": [],
275
+ "logprobs": false,
276
+ "top_logprobs": null,
277
+ "ckpt_dir": null,
278
+ "lora_modules": [],
279
+ "train_type": "full",
280
+ "adapters": [],
281
+ "external_plugins": [],
282
+ "model_kwargs": {},
283
+ "load_args": false,
284
+ "load_data_args": false,
285
+ "packing": false,
286
+ "packing_length": null,
287
+ "packing_num_proc": 1,
288
+ "lazy_tokenize": false,
289
+ "custom_register_path": [],
290
+ "use_hf": false,
291
+ "ignore_args_error": false,
292
+ "use_swift_lora": false,
293
+ "freeze_parameters": [],
294
+ "freeze_parameters_regex": null,
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "trainable_parameters_regex": null,
298
+ "freeze_llm": false,
299
+ "freeze_vit": true,
300
+ "freeze_aligner": true,
301
+ "target_modules": [
302
+ "all-linear"
303
+ ],
304
+ "target_regex": null,
305
+ "target_parameters": null,
306
+ "modules_to_save": [],
307
+ "lora_rank": 8,
308
+ "lora_alpha": 32,
309
+ "lora_dropout": 0.05,
310
+ "lora_bias": "none",
311
+ "lora_dtype": null,
312
+ "lorap_lr_ratio": null,
313
+ "use_rslora": false,
314
+ "use_dora": false,
315
+ "lora_ga_batch_size": 2,
316
+ "lora_ga_iters": 2,
317
+ "lora_ga_max_length": 1024,
318
+ "lora_ga_direction": "ArB2r",
319
+ "lora_ga_scale": "stable",
320
+ "lora_ga_stable_gamma": 16,
321
+ "init_weights": true,
322
+ "fourier_n_frequency": 2000,
323
+ "fourier_scaling": 300.0,
324
+ "boft_block_size": 4,
325
+ "boft_block_num": 0,
326
+ "boft_n_butterfly_factor": 1,
327
+ "boft_dropout": 0.0,
328
+ "vera_rank": 256,
329
+ "vera_projection_prng_key": 0,
330
+ "vera_dropout": 0.0,
331
+ "vera_d_initial": 0.1,
332
+ "adapter_act": "gelu",
333
+ "adapter_length": 128,
334
+ "use_galore": false,
335
+ "galore_target_modules": null,
336
+ "galore_rank": 128,
337
+ "galore_update_proj_gap": 50,
338
+ "galore_scale": 1.0,
339
+ "galore_proj_type": "std",
340
+ "galore_optim_per_parameter": false,
341
+ "galore_with_embedding": false,
342
+ "galore_quantization": false,
343
+ "galore_proj_quant": false,
344
+ "galore_proj_bits": 4,
345
+ "galore_proj_group_size": 256,
346
+ "galore_cos_threshold": 0.4,
347
+ "galore_gamma_proj": 2,
348
+ "galore_queue_size": 5,
349
+ "adalora_target_r": 8,
350
+ "adalora_init_r": 12,
351
+ "adalora_tinit": 0,
352
+ "adalora_tfinal": 0,
353
+ "adalora_deltaT": 1,
354
+ "adalora_beta1": 0.85,
355
+ "adalora_beta2": 0.85,
356
+ "adalora_orth_reg_weight": 0.5,
357
+ "llamapro_num_new_blocks": 4,
358
+ "llamapro_num_groups": null,
359
+ "lisa_activated_layers": 0,
360
+ "lisa_step_interval": 20,
361
+ "reft_layer_key": null,
362
+ "reft_layers": null,
363
+ "reft_rank": 4,
364
+ "reft_intervention_type": "LoreftIntervention",
365
+ "reft_args": null,
366
+ "swanlab_token": null,
367
+ "swanlab_project": null,
368
+ "swanlab_workspace": null,
369
+ "swanlab_exp_name": null,
370
+ "swanlab_lark_webhook_url": null,
371
+ "swanlab_lark_secret": null,
372
+ "swanlab_mode": "cloud",
373
+ "add_version": true,
374
+ "create_checkpoint_symlink": false,
375
+ "zero_hpz_partition_size": null,
376
+ "deepspeed_autotp_size": null,
377
+ "early_stop_interval": null,
378
+ "rank": 0,
379
+ "global_world_size": 4,
380
+ "local_world_size": 4,
381
+ "model_suffix": "Qwen3-4B-Instruct-2507",
382
+ "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/data2/PLMs/Qwen3-4B-Instruct-2507', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
383
+ "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fa74f263880>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
384
+ "model_dir": "/data2/PLMs/Qwen3-4B-Instruct-2507",
385
+ "_val_dataset_exists": [],
386
+ "hub": "<class 'swift.hub.hub.MSHub'>",
387
+ "evaluation_strategy": "epoch",
388
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, 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=None, dataloader_num_workers=8, dataloader_prefetch_factor=10, past_index=-1, run_name='/data/qzs/DataPRM/models/qwen3-4b-prm_deepseek_v3_2_autosdt_v2_no_indentation/v0-20260107-014603', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=True, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
389
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 262144,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151643,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 5000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.3",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411cd775b13eca4c2c08d114c08c955887b67e8451ccafb546668ba8d9160220
3
+ size 4967215360
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cda2b083b942283a3521a4439c607dc93cd75f4dd5c3f17cdd5d71420c7a8b8
3
+ size 3077766632
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 196096,
4
+ "total_size": 8044936192
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.norm.weight": "model-00002-of-00002.safetensors"
405
+ }
406
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,1987 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 279,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.010752688172043012,
14
+ "grad_norm": 19.659445278083677,
15
+ "learning_rate": 7.142857142857143e-07,
16
+ "loss": 0.8801538944244385,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.021505376344086023,
21
+ "grad_norm": 21.183622990197563,
22
+ "learning_rate": 1.4285714285714286e-06,
23
+ "loss": 0.9106118679046631,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.03225806451612903,
28
+ "grad_norm": 9.680562864297194,
29
+ "learning_rate": 2.1428571428571427e-06,
30
+ "loss": 0.89518141746521,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.043010752688172046,
35
+ "grad_norm": 8.463557758001873,
36
+ "learning_rate": 2.8571428571428573e-06,
37
+ "loss": 0.8813375234603882,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.053763440860215055,
42
+ "grad_norm": 8.000585049846563,
43
+ "learning_rate": 3.5714285714285718e-06,
44
+ "loss": 0.8478757739067078,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.06451612903225806,
49
+ "grad_norm": 6.392760393586216,
50
+ "learning_rate": 4.2857142857142855e-06,
51
+ "loss": 0.7342901825904846,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.07526881720430108,
56
+ "grad_norm": 4.291231505071156,
57
+ "learning_rate": 5e-06,
58
+ "loss": 0.6894474029541016,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.08602150537634409,
63
+ "grad_norm": 3.3545639671049603,
64
+ "learning_rate": 5.7142857142857145e-06,
65
+ "loss": 0.6144750118255615,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0967741935483871,
70
+ "grad_norm": 1.3577798099653526,
71
+ "learning_rate": 6.4285714285714295e-06,
72
+ "loss": 0.5370485186576843,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.10752688172043011,
77
+ "grad_norm": 1.2774532761940443,
78
+ "learning_rate": 7.1428571428571436e-06,
79
+ "loss": 0.5807953476905823,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.11827956989247312,
84
+ "grad_norm": 1.0447472651159857,
85
+ "learning_rate": 7.857142857142858e-06,
86
+ "loss": 0.5280188918113708,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.12903225806451613,
91
+ "grad_norm": 1.3301070676426008,
92
+ "learning_rate": 8.571428571428571e-06,
93
+ "loss": 0.5441749691963196,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.13978494623655913,
98
+ "grad_norm": 1.0565188353675214,
99
+ "learning_rate": 9.285714285714288e-06,
100
+ "loss": 0.5112073421478271,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.15053763440860216,
105
+ "grad_norm": 1.0753192556611026,
106
+ "learning_rate": 1e-05,
107
+ "loss": 0.5184136629104614,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.16129032258064516,
112
+ "grad_norm": 0.8209457367101312,
113
+ "learning_rate": 9.999648647603774e-06,
114
+ "loss": 0.5023149251937866,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.17204301075268819,
119
+ "grad_norm": 0.7282985426170734,
120
+ "learning_rate": 9.998594639794502e-06,
121
+ "loss": 0.48974722623825073,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.1827956989247312,
126
+ "grad_norm": 0.7177574512039909,
127
+ "learning_rate": 9.996838124703448e-06,
128
+ "loss": 0.47443556785583496,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.1935483870967742,
133
+ "grad_norm": 0.7867041042254088,
134
+ "learning_rate": 9.994379349192927e-06,
135
+ "loss": 0.48248669505119324,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.20430107526881722,
140
+ "grad_norm": 0.7192865433337082,
141
+ "learning_rate": 9.991218658821609e-06,
142
+ "loss": 0.46316730976104736,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.21505376344086022,
147
+ "grad_norm": 0.8279557032400371,
148
+ "learning_rate": 9.987356497795944e-06,
149
+ "loss": 0.5312884449958801,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.22580645161290322,
154
+ "grad_norm": 0.7907337063911983,
155
+ "learning_rate": 9.982793408907747e-06,
156
+ "loss": 0.48629915714263916,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.23655913978494625,
161
+ "grad_norm": 0.634234358721607,
162
+ "learning_rate": 9.977530033457906e-06,
163
+ "loss": 0.47711604833602905,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.24731182795698925,
168
+ "grad_norm": 0.7748372497671804,
169
+ "learning_rate": 9.971567111166246e-06,
170
+ "loss": 0.4741020202636719,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.25806451612903225,
175
+ "grad_norm": 0.6968307669517513,
176
+ "learning_rate": 9.964905480067585e-06,
177
+ "loss": 0.48086652159690857,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.26881720430107525,
182
+ "grad_norm": 0.6205197336090342,
183
+ "learning_rate": 9.957546076393944e-06,
184
+ "loss": 0.45759013295173645,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.27956989247311825,
189
+ "grad_norm": 0.5942106287222008,
190
+ "learning_rate": 9.949489934442966e-06,
191
+ "loss": 0.454744428396225,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.2903225806451613,
196
+ "grad_norm": 0.6374339549026193,
197
+ "learning_rate": 9.940738186432565e-06,
198
+ "loss": 0.4751560091972351,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.3010752688172043,
203
+ "grad_norm": 0.5187971760627564,
204
+ "learning_rate": 9.931292062341793e-06,
205
+ "loss": 0.39658498764038086,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.3118279569892473,
210
+ "grad_norm": 0.5360240389517962,
211
+ "learning_rate": 9.921152889737985e-06,
212
+ "loss": 0.46163371205329895,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.3225806451612903,
217
+ "grad_norm": 0.5585203893563241,
218
+ "learning_rate": 9.910322093590177e-06,
219
+ "loss": 0.46062612533569336,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.3333333333333333,
224
+ "grad_norm": 0.5610561072744311,
225
+ "learning_rate": 9.898801196068839e-06,
226
+ "loss": 0.4484734833240509,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.34408602150537637,
231
+ "grad_norm": 0.5533641378752504,
232
+ "learning_rate": 9.886591816331953e-06,
233
+ "loss": 0.41486942768096924,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.3548387096774194,
238
+ "grad_norm": 0.5365723882895206,
239
+ "learning_rate": 9.87369567029745e-06,
240
+ "loss": 0.43502286076545715,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.3655913978494624,
245
+ "grad_norm": 0.5536007189636761,
246
+ "learning_rate": 9.860114570402055e-06,
247
+ "loss": 0.4295029640197754,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.3763440860215054,
252
+ "grad_norm": 0.537839879636324,
253
+ "learning_rate": 9.845850425346563e-06,
254
+ "loss": 0.45029592514038086,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.3870967741935484,
259
+ "grad_norm": 0.5299693550104672,
260
+ "learning_rate": 9.830905239827592e-06,
261
+ "loss": 0.38297146558761597,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.3978494623655914,
266
+ "grad_norm": 0.5451092272235792,
267
+ "learning_rate": 9.815281114255841e-06,
268
+ "loss": 0.4300140142440796,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.40860215053763443,
273
+ "grad_norm": 0.6192689983212899,
274
+ "learning_rate": 9.798980244460892e-06,
275
+ "loss": 0.47214269638061523,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.41935483870967744,
280
+ "grad_norm": 0.5870329353069306,
281
+ "learning_rate": 9.782004921382612e-06,
282
+ "loss": 0.43783068656921387,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.43010752688172044,
287
+ "grad_norm": 0.5903637860392952,
288
+ "learning_rate": 9.764357530749178e-06,
289
+ "loss": 0.4084509611129761,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.44086021505376344,
294
+ "grad_norm": 0.61705449873411,
295
+ "learning_rate": 9.74604055274178e-06,
296
+ "loss": 0.42812418937683105,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.45161290322580644,
301
+ "grad_norm": 1.156325694795339,
302
+ "learning_rate": 9.727056561646067e-06,
303
+ "loss": 0.4196915626525879,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.46236559139784944,
308
+ "grad_norm": 0.580641483078281,
309
+ "learning_rate": 9.707408225490343e-06,
310
+ "loss": 0.4251587986946106,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.4731182795698925,
315
+ "grad_norm": 0.5510691280763641,
316
+ "learning_rate": 9.687098305670606e-06,
317
+ "loss": 0.4205142855644226,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.4838709677419355,
322
+ "grad_norm": 0.5225683335691166,
323
+ "learning_rate": 9.66612965656245e-06,
324
+ "loss": 0.37856176495552063,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.4946236559139785,
329
+ "grad_norm": 0.5740926054795668,
330
+ "learning_rate": 9.644505225119922e-06,
331
+ "loss": 0.4447917342185974,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.5053763440860215,
336
+ "grad_norm": 0.5873250280785997,
337
+ "learning_rate": 9.622228050461345e-06,
338
+ "loss": 0.3922080397605896,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.5161290322580645,
343
+ "grad_norm": 0.6219913849412524,
344
+ "learning_rate": 9.599301263442194e-06,
345
+ "loss": 0.43804931640625,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.5268817204301075,
350
+ "grad_norm": 0.5613998719760911,
351
+ "learning_rate": 9.575728086215093e-06,
352
+ "loss": 0.39639532566070557,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.5376344086021505,
357
+ "grad_norm": 0.5892845271021349,
358
+ "learning_rate": 9.551511831776966e-06,
359
+ "loss": 0.4323637783527374,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.5483870967741935,
364
+ "grad_norm": 0.6452327069861976,
365
+ "learning_rate": 9.526655903503423e-06,
366
+ "loss": 0.4111916422843933,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.5591397849462365,
371
+ "grad_norm": 0.6139840452181067,
372
+ "learning_rate": 9.501163794670445e-06,
373
+ "loss": 0.41024255752563477,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.5698924731182796,
378
+ "grad_norm": 0.5311229042653062,
379
+ "learning_rate": 9.475039087963443e-06,
380
+ "loss": 0.39047467708587646,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.5806451612903226,
385
+ "grad_norm": 0.5686779350086011,
386
+ "learning_rate": 9.448285454973739e-06,
387
+ "loss": 0.4083505868911743,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.5913978494623656,
392
+ "grad_norm": 0.5795028580373828,
393
+ "learning_rate": 9.420906655682553e-06,
394
+ "loss": 0.41430288553237915,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.6021505376344086,
399
+ "grad_norm": 0.5426200748349074,
400
+ "learning_rate": 9.392906537932582e-06,
401
+ "loss": 0.39692986011505127,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.6129032258064516,
406
+ "grad_norm": 0.5096666206067523,
407
+ "learning_rate": 9.364289036887214e-06,
408
+ "loss": 0.39456355571746826,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.6236559139784946,
413
+ "grad_norm": 0.6214693543974321,
414
+ "learning_rate": 9.335058174477472e-06,
415
+ "loss": 0.43065640330314636,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.6344086021505376,
420
+ "grad_norm": 0.6080775052566749,
421
+ "learning_rate": 9.305218058836778e-06,
422
+ "loss": 0.4233320653438568,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.6451612903225806,
427
+ "grad_norm": 0.5891380183146641,
428
+ "learning_rate": 9.274772883723587e-06,
429
+ "loss": 0.44017481803894043,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.6559139784946236,
434
+ "grad_norm": 0.5317932432917034,
435
+ "learning_rate": 9.24372692793199e-06,
436
+ "loss": 0.39426931738853455,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.6666666666666666,
441
+ "grad_norm": 0.6464375491620328,
442
+ "learning_rate": 9.21208455469037e-06,
443
+ "loss": 0.4302670657634735,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.6774193548387096,
448
+ "grad_norm": 0.6191245668003084,
449
+ "learning_rate": 9.179850211048193e-06,
450
+ "loss": 0.3996105492115021,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.6881720430107527,
455
+ "grad_norm": 0.5209850545783036,
456
+ "learning_rate": 9.14702842725101e-06,
457
+ "loss": 0.3926236629486084,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.6989247311827957,
462
+ "grad_norm": 0.5469602060829455,
463
+ "learning_rate": 9.113623816103775e-06,
464
+ "loss": 0.4129854142665863,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.7096774193548387,
469
+ "grad_norm": 0.6436176685575749,
470
+ "learning_rate": 9.079641072322555e-06,
471
+ "loss": 0.4262722432613373,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.7204301075268817,
476
+ "grad_norm": 0.6241121753870925,
477
+ "learning_rate": 9.045084971874738e-06,
478
+ "loss": 0.4259442687034607,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.7311827956989247,
483
+ "grad_norm": 0.520706057326722,
484
+ "learning_rate": 9.009960371307798e-06,
485
+ "loss": 0.40881264209747314,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.7419354838709677,
490
+ "grad_norm": 0.5406305590251429,
491
+ "learning_rate": 8.974272207066767e-06,
492
+ "loss": 0.4136165976524353,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.7526881720430108,
497
+ "grad_norm": 0.5589669382622552,
498
+ "learning_rate": 8.938025494800454e-06,
499
+ "loss": 0.3692484498023987,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.7634408602150538,
504
+ "grad_norm": 0.5484586018961858,
505
+ "learning_rate": 8.901225328656543e-06,
506
+ "loss": 0.392721563577652,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.7741935483870968,
511
+ "grad_norm": 0.5720189126246105,
512
+ "learning_rate": 8.863876880565656e-06,
513
+ "loss": 0.4131432771682739,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.7849462365591398,
518
+ "grad_norm": 0.5475650690180592,
519
+ "learning_rate": 8.825985399514488e-06,
520
+ "loss": 0.39399850368499756,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.7956989247311828,
525
+ "grad_norm": 0.571446157132029,
526
+ "learning_rate": 8.787556210808101e-06,
527
+ "loss": 0.3765556216239929,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.8064516129032258,
532
+ "grad_norm": 0.5096610649520538,
533
+ "learning_rate": 8.748594715321512e-06,
534
+ "loss": 0.38086819648742676,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.8172043010752689,
539
+ "grad_norm": 0.5696584948279285,
540
+ "learning_rate": 8.70910638874064e-06,
541
+ "loss": 0.40993741154670715,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.8279569892473119,
546
+ "grad_norm": 0.5448260281274895,
547
+ "learning_rate": 8.669096780792754e-06,
548
+ "loss": 0.3912901282310486,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.8387096774193549,
553
+ "grad_norm": 0.584810442023009,
554
+ "learning_rate": 8.628571514466502e-06,
555
+ "loss": 0.39722931385040283,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.8494623655913979,
560
+ "grad_norm": 0.5590387314291252,
561
+ "learning_rate": 8.587536285221656e-06,
562
+ "loss": 0.38008394837379456,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.8602150537634409,
567
+ "grad_norm": 0.5199976478034525,
568
+ "learning_rate": 8.545996860188668e-06,
569
+ "loss": 0.3779188394546509,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.8709677419354839,
574
+ "grad_norm": 0.6237910452530793,
575
+ "learning_rate": 8.503959077358143e-06,
576
+ "loss": 0.40831005573272705,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.8817204301075269,
581
+ "grad_norm": 0.5103230716146216,
582
+ "learning_rate": 8.46142884476038e-06,
583
+ "loss": 0.3830574154853821,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.8924731182795699,
588
+ "grad_norm": 0.6022470754794768,
589
+ "learning_rate": 8.418412139635026e-06,
590
+ "loss": 0.3760561943054199,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.9032258064516129,
595
+ "grad_norm": 0.5676501864622416,
596
+ "learning_rate": 8.374915007591053e-06,
597
+ "loss": 0.3981160521507263,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.9139784946236559,
602
+ "grad_norm": 0.62733814659435,
603
+ "learning_rate": 8.330943561757092e-06,
604
+ "loss": 0.38736072182655334,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.9247311827956989,
609
+ "grad_norm": 0.581917413328386,
610
+ "learning_rate": 8.286503981922284e-06,
611
+ "loss": 0.40054696798324585,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.9354838709677419,
616
+ "grad_norm": 0.5069721523225358,
617
+ "learning_rate": 8.241602513667775e-06,
618
+ "loss": 0.36416178941726685,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.946236559139785,
623
+ "grad_norm": 0.6484709424945745,
624
+ "learning_rate": 8.19624546748895e-06,
625
+ "loss": 0.3703634738922119,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.956989247311828,
630
+ "grad_norm": 0.5102251649420729,
631
+ "learning_rate": 8.150439217908557e-06,
632
+ "loss": 0.39143842458724976,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.967741935483871,
637
+ "grad_norm": 0.5485517368687335,
638
+ "learning_rate": 8.104190202580811e-06,
639
+ "loss": 0.3922935128211975,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.978494623655914,
644
+ "grad_norm": 0.5680193851368315,
645
+ "learning_rate": 8.057504921386661e-06,
646
+ "loss": 0.3872210383415222,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.989247311827957,
651
+ "grad_norm": 0.5405961708214808,
652
+ "learning_rate": 8.010389935520269e-06,
653
+ "loss": 0.4088854193687439,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.0,
658
+ "grad_norm": 0.5234958056904553,
659
+ "learning_rate": 7.962851866566912e-06,
660
+ "loss": 0.3855600953102112,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.010752688172043,
665
+ "grad_norm": 0.5751268630788401,
666
+ "learning_rate": 7.914897395572362e-06,
667
+ "loss": 0.32572415471076965,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.021505376344086,
672
+ "grad_norm": 0.5181295042077261,
673
+ "learning_rate": 7.866533262103937e-06,
674
+ "loss": 0.3046826720237732,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.032258064516129,
679
+ "grad_norm": 0.5508917328926465,
680
+ "learning_rate": 7.817766263303312e-06,
681
+ "loss": 0.29789605736732483,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.043010752688172,
686
+ "grad_norm": 0.5870437887252276,
687
+ "learning_rate": 7.768603252931243e-06,
688
+ "loss": 0.3265905976295471,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.053763440860215,
693
+ "grad_norm": 0.5133318653975599,
694
+ "learning_rate": 7.719051140404327e-06,
695
+ "loss": 0.31667008996009827,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.064516129032258,
700
+ "grad_norm": 0.5679147172610466,
701
+ "learning_rate": 7.669116889823955e-06,
702
+ "loss": 0.2714020311832428,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 1.075268817204301,
707
+ "grad_norm": 0.6225396396665326,
708
+ "learning_rate": 7.6188075189975644e-06,
709
+ "loss": 0.3139406740665436,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 1.086021505376344,
714
+ "grad_norm": 0.714553736071244,
715
+ "learning_rate": 7.568130098452352e-06,
716
+ "loss": 0.2961091995239258,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 1.096774193548387,
721
+ "grad_norm": 0.523889168005371,
722
+ "learning_rate": 7.517091750441576e-06,
723
+ "loss": 0.27245283126831055,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 1.10752688172043,
728
+ "grad_norm": 0.639295771779283,
729
+ "learning_rate": 7.465699647943586e-06,
730
+ "loss": 0.29422637820243835,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 1.118279569892473,
735
+ "grad_norm": 0.6150692376811179,
736
+ "learning_rate": 7.413961013653725e-06,
737
+ "loss": 0.29594993591308594,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 1.129032258064516,
742
+ "grad_norm": 0.6901790920161586,
743
+ "learning_rate": 7.361883118969248e-06,
744
+ "loss": 0.3163909912109375,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 1.139784946236559,
749
+ "grad_norm": 0.5947317629259291,
750
+ "learning_rate": 7.309473282967387e-06,
751
+ "loss": 0.2941242456436157,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 1.1505376344086022,
756
+ "grad_norm": 0.5873657820382887,
757
+ "learning_rate": 7.256738871376733e-06,
758
+ "loss": 0.29748812317848206,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 1.1612903225806452,
763
+ "grad_norm": 0.5914901548215277,
764
+ "learning_rate": 7.203687295542032e-06,
765
+ "loss": 0.3174619972705841,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 1.1720430107526882,
770
+ "grad_norm": 0.5757880846821776,
771
+ "learning_rate": 7.1503260113826035e-06,
772
+ "loss": 0.31319767236709595,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 1.1827956989247312,
777
+ "grad_norm": 0.7019483863871168,
778
+ "learning_rate": 7.09666251834447e-06,
779
+ "loss": 0.3302695155143738,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 1.1935483870967742,
784
+ "grad_norm": 0.5613831627968954,
785
+ "learning_rate": 7.042704358346375e-06,
786
+ "loss": 0.30153942108154297,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 1.2043010752688172,
791
+ "grad_norm": 0.5906296533769152,
792
+ "learning_rate": 6.988459114719849e-06,
793
+ "loss": 0.3321286141872406,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 1.2150537634408602,
798
+ "grad_norm": 0.6185930436417313,
799
+ "learning_rate": 6.933934411143419e-06,
800
+ "loss": 0.3183019161224365,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 1.2258064516129032,
805
+ "grad_norm": 0.5223193968800454,
806
+ "learning_rate": 6.879137910571191e-06,
807
+ "loss": 0.28522804379463196,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 1.2365591397849462,
812
+ "grad_norm": 0.5306097120719284,
813
+ "learning_rate": 6.824077314155877e-06,
814
+ "loss": 0.27248305082321167,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 1.2473118279569892,
819
+ "grad_norm": 0.5410094711890291,
820
+ "learning_rate": 6.768760360166471e-06,
821
+ "loss": 0.29798364639282227,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 1.2580645161290323,
826
+ "grad_norm": 0.594316663926518,
827
+ "learning_rate": 6.713194822900707e-06,
828
+ "loss": 0.27839338779449463,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 1.2688172043010753,
833
+ "grad_norm": 0.6110653082771621,
834
+ "learning_rate": 6.657388511592453e-06,
835
+ "loss": 0.30802613496780396,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 1.2795698924731183,
840
+ "grad_norm": 0.5260300979877027,
841
+ "learning_rate": 6.601349269314188e-06,
842
+ "loss": 0.29552769660949707,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 1.2903225806451613,
847
+ "grad_norm": 0.541255561766811,
848
+ "learning_rate": 6.545084971874738e-06,
849
+ "loss": 0.28333544731140137,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 1.3010752688172043,
854
+ "grad_norm": 0.5631658544435217,
855
+ "learning_rate": 6.488603526712391e-06,
856
+ "loss": 0.3072783946990967,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 1.3118279569892473,
861
+ "grad_norm": 0.5999697642319023,
862
+ "learning_rate": 6.431912871783587e-06,
863
+ "loss": 0.2956047058105469,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 1.3225806451612903,
868
+ "grad_norm": 0.5550402984265157,
869
+ "learning_rate": 6.3750209744473105e-06,
870
+ "loss": 0.3064526319503784,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 1.3333333333333333,
875
+ "grad_norm": 0.6418624402271341,
876
+ "learning_rate": 6.3179358303453386e-06,
877
+ "loss": 0.30682218074798584,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.3440860215053765,
882
+ "grad_norm": 0.5305043074037712,
883
+ "learning_rate": 6.260665462278544e-06,
884
+ "loss": 0.3036462068557739,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 1.3548387096774195,
889
+ "grad_norm": 0.5732839993822031,
890
+ "learning_rate": 6.203217919079343e-06,
891
+ "loss": 0.32605141401290894,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 1.3655913978494625,
896
+ "grad_norm": 0.5272514261375651,
897
+ "learning_rate": 6.145601274480521e-06,
898
+ "loss": 0.2800780236721039,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 1.3763440860215055,
903
+ "grad_norm": 0.5383888711112677,
904
+ "learning_rate": 6.08782362598054e-06,
905
+ "loss": 0.29685452580451965,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 1.3870967741935485,
910
+ "grad_norm": 0.5260069329849035,
911
+ "learning_rate": 6.029893093705492e-06,
912
+ "loss": 0.30100512504577637,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 1.3978494623655915,
917
+ "grad_norm": 0.5194176965790988,
918
+ "learning_rate": 5.971817819267914e-06,
919
+ "loss": 0.28969407081604004,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 1.4086021505376345,
924
+ "grad_norm": 0.5795379145956892,
925
+ "learning_rate": 5.9136059646225375e-06,
926
+ "loss": 0.3088012635707855,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 1.4193548387096775,
931
+ "grad_norm": 0.5605938731509191,
932
+ "learning_rate": 5.855265710919211e-06,
933
+ "loss": 0.2954477369785309,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 1.4301075268817205,
938
+ "grad_norm": 0.5513949309182947,
939
+ "learning_rate": 5.796805257353109e-06,
940
+ "loss": 0.31166109442710876,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 1.4408602150537635,
945
+ "grad_norm": 0.6271394444282732,
946
+ "learning_rate": 5.738232820012407e-06,
947
+ "loss": 0.33265459537506104,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 1.4516129032258065,
952
+ "grad_norm": 0.5513926189063966,
953
+ "learning_rate": 5.679556630723592e-06,
954
+ "loss": 0.271618515253067,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 1.4623655913978495,
959
+ "grad_norm": 0.5799088021416959,
960
+ "learning_rate": 5.620784935894548e-06,
961
+ "loss": 0.2902123034000397,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 1.4731182795698925,
966
+ "grad_norm": 0.5662089313253346,
967
+ "learning_rate": 5.561925995355595e-06,
968
+ "loss": 0.2844197154045105,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 1.4838709677419355,
973
+ "grad_norm": 0.9937555515678825,
974
+ "learning_rate": 5.5029880811986546e-06,
975
+ "loss": 0.2922922372817993,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 1.4946236559139785,
980
+ "grad_norm": 0.591368004900944,
981
+ "learning_rate": 5.443979476614674e-06,
982
+ "loss": 0.28497251868247986,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 1.5053763440860215,
987
+ "grad_norm": 0.6076112891374724,
988
+ "learning_rate": 5.384908474729501e-06,
989
+ "loss": 0.31142377853393555,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 1.5161290322580645,
994
+ "grad_norm": 0.5765965412966652,
995
+ "learning_rate": 5.325783377438357e-06,
996
+ "loss": 0.3015650510787964,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 1.5268817204301075,
1001
+ "grad_norm": 0.5232918774810716,
1002
+ "learning_rate": 5.266612494239088e-06,
1003
+ "loss": 0.275716096162796,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 1.5376344086021505,
1008
+ "grad_norm": 0.5680197113944581,
1009
+ "learning_rate": 5.207404141064334e-06,
1010
+ "loss": 0.2873622179031372,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 1.5483870967741935,
1015
+ "grad_norm": 0.49399262225350316,
1016
+ "learning_rate": 5.148166639112799e-06,
1017
+ "loss": 0.26688140630722046,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 1.5591397849462365,
1022
+ "grad_norm": 0.5949244178581083,
1023
+ "learning_rate": 5.088908313679788e-06,
1024
+ "loss": 0.29102981090545654,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 1.5698924731182795,
1029
+ "grad_norm": 0.6289302836737687,
1030
+ "learning_rate": 5.029637492987153e-06,
1031
+ "loss": 0.2931191027164459,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 1.5806451612903225,
1036
+ "grad_norm": 0.6088833365757095,
1037
+ "learning_rate": 4.970362507012848e-06,
1038
+ "loss": 0.2844638228416443,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 1.5913978494623655,
1043
+ "grad_norm": 0.6971118150263104,
1044
+ "learning_rate": 4.911091686320213e-06,
1045
+ "loss": 0.3226025104522705,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 1.6021505376344085,
1050
+ "grad_norm": 0.5612811561354285,
1051
+ "learning_rate": 4.8518333608872015e-06,
1052
+ "loss": 0.28764593601226807,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 1.6129032258064515,
1057
+ "grad_norm": 0.6065928167636621,
1058
+ "learning_rate": 4.792595858935668e-06,
1059
+ "loss": 0.3277990221977234,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 1.6236559139784945,
1064
+ "grad_norm": 0.5135483316527438,
1065
+ "learning_rate": 4.733387505760913e-06,
1066
+ "loss": 0.2962847948074341,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 1.6344086021505375,
1071
+ "grad_norm": 0.6160906809336857,
1072
+ "learning_rate": 4.674216622561645e-06,
1073
+ "loss": 0.294375479221344,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 1.6451612903225805,
1078
+ "grad_norm": 0.6058840168616271,
1079
+ "learning_rate": 4.6150915252705005e-06,
1080
+ "loss": 0.3054540157318115,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 1.6559139784946235,
1085
+ "grad_norm": 0.5298336251451402,
1086
+ "learning_rate": 4.556020523385326e-06,
1087
+ "loss": 0.30477648973464966,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 1.6666666666666665,
1092
+ "grad_norm": 0.5241054596736249,
1093
+ "learning_rate": 4.497011918801347e-06,
1094
+ "loss": 0.2855217456817627,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 1.6774193548387095,
1099
+ "grad_norm": 0.48994778885097257,
1100
+ "learning_rate": 4.438074004644407e-06,
1101
+ "loss": 0.30031388998031616,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 1.6881720430107527,
1106
+ "grad_norm": 0.6034882888193746,
1107
+ "learning_rate": 4.379215064105454e-06,
1108
+ "loss": 0.3072971999645233,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 1.6989247311827957,
1113
+ "grad_norm": 0.5057395078651564,
1114
+ "learning_rate": 4.32044336927641e-06,
1115
+ "loss": 0.27074217796325684,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 1.7096774193548387,
1120
+ "grad_norm": 0.548027010828449,
1121
+ "learning_rate": 4.261767179987595e-06,
1122
+ "loss": 0.28892627358436584,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 1.7204301075268817,
1127
+ "grad_norm": 0.5949799690870136,
1128
+ "learning_rate": 4.203194742646893e-06,
1129
+ "loss": 0.31755733489990234,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 1.7311827956989247,
1134
+ "grad_norm": 0.5988557766268561,
1135
+ "learning_rate": 4.1447342890807905e-06,
1136
+ "loss": 0.28983038663864136,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 1.7419354838709677,
1141
+ "grad_norm": 0.5153375977084437,
1142
+ "learning_rate": 4.086394035377463e-06,
1143
+ "loss": 0.2821354269981384,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 1.7526881720430108,
1148
+ "grad_norm": 0.5758453410329892,
1149
+ "learning_rate": 4.028182180732088e-06,
1150
+ "loss": 0.26659733057022095,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 1.7634408602150538,
1155
+ "grad_norm": 0.5515188533069812,
1156
+ "learning_rate": 3.970106906294509e-06,
1157
+ "loss": 0.29241591691970825,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 1.7741935483870968,
1162
+ "grad_norm": 0.5465960078319545,
1163
+ "learning_rate": 3.912176374019462e-06,
1164
+ "loss": 0.28333449363708496,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 1.7849462365591398,
1169
+ "grad_norm": 0.5696267902501757,
1170
+ "learning_rate": 3.85439872551948e-06,
1171
+ "loss": 0.28454482555389404,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 1.7956989247311828,
1176
+ "grad_norm": 0.5537225691065368,
1177
+ "learning_rate": 3.796782080920659e-06,
1178
+ "loss": 0.29573291540145874,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 1.8064516129032258,
1183
+ "grad_norm": 0.5317821119388748,
1184
+ "learning_rate": 3.7393345377214584e-06,
1185
+ "loss": 0.3006817400455475,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 1.817204301075269,
1190
+ "grad_norm": 0.5193143293546626,
1191
+ "learning_rate": 3.682064169654663e-06,
1192
+ "loss": 0.28759250044822693,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 1.827956989247312,
1197
+ "grad_norm": 0.5024936169709733,
1198
+ "learning_rate": 3.6249790255526916e-06,
1199
+ "loss": 0.279812753200531,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 1.838709677419355,
1204
+ "grad_norm": 0.522744432939167,
1205
+ "learning_rate": 3.568087128216414e-06,
1206
+ "loss": 0.2699696123600006,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 1.849462365591398,
1211
+ "grad_norm": 0.6740080747223203,
1212
+ "learning_rate": 3.511396473287611e-06,
1213
+ "loss": 0.3212928771972656,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 1.860215053763441,
1218
+ "grad_norm": 0.5393424030521861,
1219
+ "learning_rate": 3.4549150281252635e-06,
1220
+ "loss": 0.28264331817626953,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 1.870967741935484,
1225
+ "grad_norm": 0.5389635395816308,
1226
+ "learning_rate": 3.398650730685813e-06,
1227
+ "loss": 0.2982739508152008,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 1.881720430107527,
1232
+ "grad_norm": 0.5527956538218779,
1233
+ "learning_rate": 3.3426114884075488e-06,
1234
+ "loss": 0.2892792820930481,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 1.89247311827957,
1239
+ "grad_norm": 0.5783362380337232,
1240
+ "learning_rate": 3.2868051770992935e-06,
1241
+ "loss": 0.2867039442062378,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 1.903225806451613,
1246
+ "grad_norm": 0.4505107682619091,
1247
+ "learning_rate": 3.2312396398335312e-06,
1248
+ "loss": 0.2998119592666626,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 1.913978494623656,
1253
+ "grad_norm": 0.544159970587014,
1254
+ "learning_rate": 3.175922685844125e-06,
1255
+ "loss": 0.2946498394012451,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 1.924731182795699,
1260
+ "grad_norm": 0.5601933382330992,
1261
+ "learning_rate": 3.1208620894288105e-06,
1262
+ "loss": 0.30848872661590576,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 1.935483870967742,
1267
+ "grad_norm": 0.5692086999688832,
1268
+ "learning_rate": 3.0660655888565827e-06,
1269
+ "loss": 0.30292433500289917,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 1.946236559139785,
1274
+ "grad_norm": 0.5204759182695003,
1275
+ "learning_rate": 3.0115408852801535e-06,
1276
+ "loss": 0.2992181181907654,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 1.956989247311828,
1281
+ "grad_norm": 0.547974934732699,
1282
+ "learning_rate": 2.9572956416536267e-06,
1283
+ "loss": 0.3052282929420471,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 1.967741935483871,
1288
+ "grad_norm": 0.5036888640423901,
1289
+ "learning_rate": 2.9033374816555338e-06,
1290
+ "loss": 0.27619490027427673,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 1.978494623655914,
1295
+ "grad_norm": 0.5857097319940581,
1296
+ "learning_rate": 2.8496739886173994e-06,
1297
+ "loss": 0.2969588041305542,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 1.989247311827957,
1302
+ "grad_norm": 0.5125923920870736,
1303
+ "learning_rate": 2.7963127044579697e-06,
1304
+ "loss": 0.28236857056617737,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 2.0,
1309
+ "grad_norm": 0.5460296926482203,
1310
+ "learning_rate": 2.743261128623269e-06,
1311
+ "loss": 0.2802872657775879,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 2.010752688172043,
1316
+ "grad_norm": 0.5627765344162555,
1317
+ "learning_rate": 2.6905267170326143e-06,
1318
+ "loss": 0.2465861439704895,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 2.021505376344086,
1323
+ "grad_norm": 0.5241819547135816,
1324
+ "learning_rate": 2.6381168810307536e-06,
1325
+ "loss": 0.2593002915382385,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 2.032258064516129,
1330
+ "grad_norm": 0.5146155536713976,
1331
+ "learning_rate": 2.5860389863462765e-06,
1332
+ "loss": 0.22058740258216858,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 2.043010752688172,
1337
+ "grad_norm": 0.527929699946712,
1338
+ "learning_rate": 2.534300352056416e-06,
1339
+ "loss": 0.24380052089691162,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 2.053763440860215,
1344
+ "grad_norm": 0.5680981651809573,
1345
+ "learning_rate": 2.4829082495584244e-06,
1346
+ "loss": 0.2181762158870697,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 2.064516129032258,
1351
+ "grad_norm": 0.5210266779766828,
1352
+ "learning_rate": 2.4318699015476495e-06,
1353
+ "loss": 0.21483556926250458,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 2.075268817204301,
1358
+ "grad_norm": 0.5228849523676178,
1359
+ "learning_rate": 2.3811924810024385e-06,
1360
+ "loss": 0.2233523428440094,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 2.086021505376344,
1365
+ "grad_norm": 1.2592287942902403,
1366
+ "learning_rate": 2.330883110176049e-06,
1367
+ "loss": 0.21375712752342224,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 2.096774193548387,
1372
+ "grad_norm": 0.5541159570889329,
1373
+ "learning_rate": 2.2809488595956746e-06,
1374
+ "loss": 0.22336843609809875,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 2.10752688172043,
1379
+ "grad_norm": 0.6275490404272853,
1380
+ "learning_rate": 2.2313967470687593e-06,
1381
+ "loss": 0.23877255618572235,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 2.118279569892473,
1386
+ "grad_norm": 0.5287134027247969,
1387
+ "learning_rate": 2.18223373669669e-06,
1388
+ "loss": 0.23572032153606415,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 2.129032258064516,
1393
+ "grad_norm": 0.6005092115812523,
1394
+ "learning_rate": 2.1334667378960642e-06,
1395
+ "loss": 0.25271525979042053,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 2.139784946236559,
1400
+ "grad_norm": 0.5729023596023511,
1401
+ "learning_rate": 2.0851026044276405e-06,
1402
+ "loss": 0.2403365820646286,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 2.150537634408602,
1407
+ "grad_norm": 0.502960648659189,
1408
+ "learning_rate": 2.0371481334330913e-06,
1409
+ "loss": 0.22194445133209229,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 2.161290322580645,
1414
+ "grad_norm": 1.0792975178234447,
1415
+ "learning_rate": 1.9896100644797316e-06,
1416
+ "loss": 0.20418012142181396,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 2.172043010752688,
1421
+ "grad_norm": 0.563900355756192,
1422
+ "learning_rate": 1.9424950786133414e-06,
1423
+ "loss": 0.2197030484676361,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 2.182795698924731,
1428
+ "grad_norm": 0.6049813205320395,
1429
+ "learning_rate": 1.8958097974191909e-06,
1430
+ "loss": 0.23065771162509918,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 2.193548387096774,
1435
+ "grad_norm": 0.5693258359321052,
1436
+ "learning_rate": 1.8495607820914451e-06,
1437
+ "loss": 0.22469733655452728,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 2.204301075268817,
1442
+ "grad_norm": 0.49687778546847566,
1443
+ "learning_rate": 1.8037545325110506e-06,
1444
+ "loss": 0.22447475790977478,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 2.21505376344086,
1449
+ "grad_norm": 0.6870685608162285,
1450
+ "learning_rate": 1.7583974863322272e-06,
1451
+ "loss": 0.2232748568058014,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 2.225806451612903,
1456
+ "grad_norm": 0.5587791759635568,
1457
+ "learning_rate": 1.7134960180777171e-06,
1458
+ "loss": 0.21617698669433594,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 2.236559139784946,
1463
+ "grad_norm": 0.5406726897347297,
1464
+ "learning_rate": 1.6690564382429104e-06,
1465
+ "loss": 0.22749440371990204,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 2.247311827956989,
1470
+ "grad_norm": 0.6059659457413509,
1471
+ "learning_rate": 1.6250849924089485e-06,
1472
+ "loss": 0.24092203378677368,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 2.258064516129032,
1477
+ "grad_norm": 0.5440152722934113,
1478
+ "learning_rate": 1.581587860364977e-06,
1479
+ "loss": 0.20948372781276703,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 2.268817204301075,
1484
+ "grad_norm": 0.48547134095880384,
1485
+ "learning_rate": 1.5385711552396227e-06,
1486
+ "loss": 0.21325388550758362,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 2.279569892473118,
1491
+ "grad_norm": 0.6324122951694761,
1492
+ "learning_rate": 1.4960409226418576e-06,
1493
+ "loss": 0.22965453565120697,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 2.2903225806451615,
1498
+ "grad_norm": 0.5469586332098659,
1499
+ "learning_rate": 1.4540031398113335e-06,
1500
+ "loss": 0.22315660119056702,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 2.3010752688172045,
1505
+ "grad_norm": 0.7520121411441703,
1506
+ "learning_rate": 1.4124637147783431e-06,
1507
+ "loss": 0.23476293683052063,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 2.3118279569892475,
1512
+ "grad_norm": 0.535533468892341,
1513
+ "learning_rate": 1.371428485533498e-06,
1514
+ "loss": 0.21404291689395905,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 2.3225806451612905,
1519
+ "grad_norm": 0.5561238179269572,
1520
+ "learning_rate": 1.3309032192072463e-06,
1521
+ "loss": 0.23378810286521912,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 2.3333333333333335,
1526
+ "grad_norm": 0.5663331713554731,
1527
+ "learning_rate": 1.29089361125936e-06,
1528
+ "loss": 0.2105513960123062,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 2.3440860215053765,
1533
+ "grad_norm": 0.5851084790781899,
1534
+ "learning_rate": 1.251405284678488e-06,
1535
+ "loss": 0.22501936554908752,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 2.3548387096774195,
1540
+ "grad_norm": 0.5546173616985522,
1541
+ "learning_rate": 1.2124437891918995e-06,
1542
+ "loss": 0.21492747962474823,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 2.3655913978494625,
1547
+ "grad_norm": 0.5542629930888266,
1548
+ "learning_rate": 1.1740146004855141e-06,
1549
+ "loss": 0.22757509350776672,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 2.3763440860215055,
1554
+ "grad_norm": 0.5368948762143404,
1555
+ "learning_rate": 1.1361231194343436e-06,
1556
+ "loss": 0.20776845514774323,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 2.3870967741935485,
1561
+ "grad_norm": 0.5362067849303692,
1562
+ "learning_rate": 1.0987746713434578e-06,
1563
+ "loss": 0.21643775701522827,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 2.3978494623655915,
1568
+ "grad_norm": 0.7478981160056104,
1569
+ "learning_rate": 1.0619745051995473e-06,
1570
+ "loss": 0.2321006953716278,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 2.4086021505376345,
1575
+ "grad_norm": 0.5589077284378241,
1576
+ "learning_rate": 1.0257277929332332e-06,
1577
+ "loss": 0.2335091233253479,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 2.4193548387096775,
1582
+ "grad_norm": 0.5449990060855128,
1583
+ "learning_rate": 9.900396286922025e-07,
1584
+ "loss": 0.22067061066627502,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 2.4301075268817205,
1589
+ "grad_norm": 0.545790815861183,
1590
+ "learning_rate": 9.549150281252633e-07,
1591
+ "loss": 0.24003136157989502,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 2.4408602150537635,
1596
+ "grad_norm": 0.5197037503280709,
1597
+ "learning_rate": 9.203589276774438e-07,
1598
+ "loss": 0.2232522964477539,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 2.4516129032258065,
1603
+ "grad_norm": 0.5783224759821376,
1604
+ "learning_rate": 8.86376183896226e-07,
1605
+ "loss": 0.2168661653995514,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 2.4623655913978495,
1610
+ "grad_norm": 0.5772298663365216,
1611
+ "learning_rate": 8.529715727489912e-07,
1612
+ "loss": 0.22855976223945618,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 2.4731182795698925,
1617
+ "grad_norm": 0.5901747678986362,
1618
+ "learning_rate": 8.201497889518073e-07,
1619
+ "loss": 0.23543155193328857,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 2.4838709677419355,
1624
+ "grad_norm": 0.4859350321815666,
1625
+ "learning_rate": 7.879154453096305e-07,
1626
+ "loss": 0.20444487035274506,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 2.4946236559139785,
1631
+ "grad_norm": 0.5733816209081586,
1632
+ "learning_rate": 7.562730720680111e-07,
1633
+ "loss": 0.22317257523536682,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 2.5053763440860215,
1638
+ "grad_norm": 0.6158850373560834,
1639
+ "learning_rate": 7.25227116276413e-07,
1640
+ "loss": 0.21304547786712646,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 2.5161290322580645,
1645
+ "grad_norm": 0.5303929149495401,
1646
+ "learning_rate": 6.947819411632223e-07,
1647
+ "loss": 0.22398605942726135,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 2.5268817204301075,
1652
+ "grad_norm": 0.5807287890882401,
1653
+ "learning_rate": 6.649418255225298e-07,
1654
+ "loss": 0.22487413883209229,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 2.5376344086021505,
1659
+ "grad_norm": 0.5151341689499322,
1660
+ "learning_rate": 6.357109631127889e-07,
1661
+ "loss": 0.20791815221309662,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 2.5483870967741935,
1666
+ "grad_norm": 0.5723989318815612,
1667
+ "learning_rate": 6.07093462067419e-07,
1668
+ "loss": 0.22853252291679382,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 2.5591397849462365,
1673
+ "grad_norm": 0.5151529413040788,
1674
+ "learning_rate": 5.79093344317449e-07,
1675
+ "loss": 0.23513737320899963,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 2.5698924731182795,
1680
+ "grad_norm": 0.6125760680997326,
1681
+ "learning_rate": 5.517145450262639e-07,
1682
+ "loss": 0.23416566848754883,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 2.5806451612903225,
1687
+ "grad_norm": 0.5169337829356161,
1688
+ "learning_rate": 5.249609120365579e-07,
1689
+ "loss": 0.2236918807029724,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 2.5913978494623655,
1694
+ "grad_norm": 0.5150874552544314,
1695
+ "learning_rate": 4.988362053295564e-07,
1696
+ "loss": 0.22128576040267944,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 2.6021505376344085,
1701
+ "grad_norm": 0.6254184464054292,
1702
+ "learning_rate": 4.733440964965791e-07,
1703
+ "loss": 0.23455382883548737,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 2.6129032258064515,
1708
+ "grad_norm": 0.5612944471466359,
1709
+ "learning_rate": 4.484881682230341e-07,
1710
+ "loss": 0.22176575660705566,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 2.6236559139784945,
1715
+ "grad_norm": 0.5178079276744024,
1716
+ "learning_rate": 4.242719137849077e-07,
1717
+ "loss": 0.21548646688461304,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 2.6344086021505375,
1722
+ "grad_norm": 0.5659047109155118,
1723
+ "learning_rate": 4.00698736557808e-07,
1724
+ "loss": 0.23057113587856293,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 2.6451612903225805,
1729
+ "grad_norm": 0.5098023427109231,
1730
+ "learning_rate": 3.777719495386567e-07,
1731
+ "loss": 0.2156354784965515,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 2.6559139784946235,
1736
+ "grad_norm": 0.49515330466811,
1737
+ "learning_rate": 3.5549477488007853e-07,
1738
+ "loss": 0.19704020023345947,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 2.6666666666666665,
1743
+ "grad_norm": 0.5297791040512543,
1744
+ "learning_rate": 3.3387034343755063e-07,
1745
+ "loss": 0.21541355550289154,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 2.6774193548387095,
1750
+ "grad_norm": 0.5134148705186912,
1751
+ "learning_rate": 3.1290169432939556e-07,
1752
+ "loss": 0.20781481266021729,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 2.688172043010753,
1757
+ "grad_norm": 0.6591675869543023,
1758
+ "learning_rate": 2.925917745096568e-07,
1759
+ "loss": 0.23452350497245789,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 2.698924731182796,
1764
+ "grad_norm": 0.5940779586998381,
1765
+ "learning_rate": 2.7294343835393366e-07,
1766
+ "loss": 0.23721283674240112,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 2.709677419354839,
1771
+ "grad_norm": 0.6904575634426214,
1772
+ "learning_rate": 2.539594472582213e-07,
1773
+ "loss": 0.23339498043060303,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 2.720430107526882,
1778
+ "grad_norm": 0.549700857643845,
1779
+ "learning_rate": 2.3564246925082358e-07,
1780
+ "loss": 0.2422715723514557,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 2.731182795698925,
1785
+ "grad_norm": 0.551951066945312,
1786
+ "learning_rate": 2.179950786173879e-07,
1787
+ "loss": 0.22343403100967407,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 2.741935483870968,
1792
+ "grad_norm": 0.5112230065122543,
1793
+ "learning_rate": 2.01019755539108e-07,
1794
+ "loss": 0.2022184431552887,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 2.752688172043011,
1799
+ "grad_norm": 0.6011326795775324,
1800
+ "learning_rate": 1.8471888574415953e-07,
1801
+ "loss": 0.21843938529491425,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 2.763440860215054,
1806
+ "grad_norm": 0.5598013580182175,
1807
+ "learning_rate": 1.690947601724091e-07,
1808
+ "loss": 0.2313247174024582,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 2.774193548387097,
1813
+ "grad_norm": 0.579260801737671,
1814
+ "learning_rate": 1.5414957465343883e-07,
1815
+ "loss": 0.23432737588882446,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 2.78494623655914,
1820
+ "grad_norm": 0.6080486926763811,
1821
+ "learning_rate": 1.3988542959794627e-07,
1822
+ "loss": 0.2501685619354248,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 2.795698924731183,
1827
+ "grad_norm": 0.6231912247704571,
1828
+ "learning_rate": 1.2630432970255014e-07,
1829
+ "loss": 0.22736617922782898,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 2.806451612903226,
1834
+ "grad_norm": 0.6526633675286432,
1835
+ "learning_rate": 1.1340818366804728e-07,
1836
+ "loss": 0.2217504233121872,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 2.817204301075269,
1841
+ "grad_norm": 0.5774442194442434,
1842
+ "learning_rate": 1.0119880393116177e-07,
1843
+ "loss": 0.21880705654621124,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 2.827956989247312,
1848
+ "grad_norm": 0.5510924764674725,
1849
+ "learning_rate": 8.967790640982466e-08,
1850
+ "loss": 0.23220205307006836,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 2.838709677419355,
1855
+ "grad_norm": 0.5940155308333281,
1856
+ "learning_rate": 7.884711026201586e-08,
1857
+ "loss": 0.22368629276752472,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 2.849462365591398,
1862
+ "grad_norm": 0.48018958702032566,
1863
+ "learning_rate": 6.870793765820783e-08,
1864
+ "loss": 0.2191024124622345,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 2.860215053763441,
1869
+ "grad_norm": 0.5348968055346366,
1870
+ "learning_rate": 5.92618135674361e-08,
1871
+ "loss": 0.2141711413860321,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 2.870967741935484,
1876
+ "grad_norm": 0.5058952998875674,
1877
+ "learning_rate": 5.0510065557034526e-08,
1878
+ "loss": 0.21273520588874817,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 2.881720430107527,
1883
+ "grad_norm": 0.5748923929140294,
1884
+ "learning_rate": 4.245392360605727e-08,
1885
+ "loss": 0.2339775264263153,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 2.89247311827957,
1890
+ "grad_norm": 0.543587597117276,
1891
+ "learning_rate": 3.5094519932415417e-08,
1892
+ "loss": 0.22123411297798157,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 2.903225806451613,
1897
+ "grad_norm": 0.5451715623802244,
1898
+ "learning_rate": 2.843288883375539e-08,
1899
+ "loss": 0.22225311398506165,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 2.913978494623656,
1904
+ "grad_norm": 0.5639808086322913,
1905
+ "learning_rate": 2.2469966542096323e-08,
1906
+ "loss": 0.220473051071167,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 2.924731182795699,
1911
+ "grad_norm": 0.5603998497829358,
1912
+ "learning_rate": 1.7206591092253642e-08,
1913
+ "loss": 0.22855965793132782,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 2.935483870967742,
1918
+ "grad_norm": 0.5700123425140283,
1919
+ "learning_rate": 1.264350220405719e-08,
1920
+ "loss": 0.226323202252388,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 2.946236559139785,
1925
+ "grad_norm": 0.5193108167577539,
1926
+ "learning_rate": 8.781341178393244e-09,
1927
+ "loss": 0.21938025951385498,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 2.956989247311828,
1932
+ "grad_norm": 0.6419513279403505,
1933
+ "learning_rate": 5.620650807073857e-09,
1934
+ "loss": 0.24610912799835205,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 2.967741935483871,
1939
+ "grad_norm": 0.6308682159730912,
1940
+ "learning_rate": 3.1618752965534295e-09,
1941
+ "loss": 0.22690746188163757,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 2.978494623655914,
1946
+ "grad_norm": 0.5263395659056124,
1947
+ "learning_rate": 1.4053602054991954e-09,
1948
+ "loss": 0.20472858846187592,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 2.989247311827957,
1953
+ "grad_norm": 0.5329091838420249,
1954
+ "learning_rate": 3.513523962256349e-10,
1955
+ "loss": 0.2296607792377472,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 3.0,
1960
+ "grad_norm": 0.6481688008102051,
1961
+ "learning_rate": 0.0,
1962
+ "loss": 0.22974838316440582,
1963
+ "step": 279
1964
+ }
1965
+ ],
1966
+ "logging_steps": 1,
1967
+ "max_steps": 279,
1968
+ "num_input_tokens_seen": 0,
1969
+ "num_train_epochs": 3,
1970
+ "save_steps": 500,
1971
+ "stateful_callbacks": {
1972
+ "TrainerControl": {
1973
+ "args": {
1974
+ "should_epoch_stop": false,
1975
+ "should_evaluate": false,
1976
+ "should_log": false,
1977
+ "should_save": true,
1978
+ "should_training_stop": true
1979
+ },
1980
+ "attributes": {}
1981
+ }
1982
+ },
1983
+ "total_flos": 142925655572480.0,
1984
+ "train_batch_size": 4,
1985
+ "trial_name": null,
1986
+ "trial_params": null
1987
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1fc808c886b17b8e30d33921efac468e75b7e1c8cdd35cf4981c08f18ebafa
3
+ size 9553
vocab.json ADDED
The diff for this file is too large to render. See raw diff