FutureMa commited on
Commit
d5c31eb
·
verified ·
1 Parent(s): 353f413

Upload Eva-4B-Label-Only fine-tuned model

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 +1,354 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v2-20260116-230845",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 8,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 2e-05,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.03,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 500.0,
39
+ "save_total_limit": 3,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 500.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v2-20260116-230845",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": null,
84
+ "label_smoothing_factor": 0.0,
85
+ "optim": "adamw_torch_fused",
86
+ "optim_args": null,
87
+ "adafactor": false,
88
+ "group_by_length": false,
89
+ "length_column_name": "length",
90
+ "report_to": [
91
+ "tensorboard"
92
+ ],
93
+ "project": "huggingface",
94
+ "trackio_space_id": "trackio",
95
+ "ddp_find_unused_parameters": null,
96
+ "ddp_bucket_cap_mb": null,
97
+ "ddp_broadcast_buffers": null,
98
+ "dataloader_pin_memory": true,
99
+ "dataloader_persistent_workers": false,
100
+ "skip_memory_metrics": true,
101
+ "use_legacy_prediction_loop": false,
102
+ "push_to_hub": false,
103
+ "resume_from_checkpoint": null,
104
+ "hub_model_id": null,
105
+ "hub_strategy": "every_save",
106
+ "hub_token": null,
107
+ "hub_private_repo": null,
108
+ "hub_always_push": false,
109
+ "hub_revision": null,
110
+ "gradient_checkpointing": true,
111
+ "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
112
+ "include_inputs_for_metrics": false,
113
+ "include_for_metrics": [],
114
+ "eval_do_concat_batches": true,
115
+ "fp16_backend": "auto",
116
+ "push_to_hub_model_id": null,
117
+ "push_to_hub_organization": null,
118
+ "push_to_hub_token": null,
119
+ "mp_parameters": "",
120
+ "auto_find_batch_size": false,
121
+ "full_determinism": false,
122
+ "torchdynamo": null,
123
+ "ray_scope": "last",
124
+ "ddp_timeout": 18000000,
125
+ "torch_compile": false,
126
+ "torch_compile_backend": null,
127
+ "torch_compile_mode": null,
128
+ "include_tokens_per_second": false,
129
+ "include_num_input_tokens_seen": false,
130
+ "neftune_noise_alpha": null,
131
+ "optim_target_modules": null,
132
+ "batch_eval_metrics": false,
133
+ "eval_on_start": false,
134
+ "use_liger_kernel": false,
135
+ "liger_kernel_config": null,
136
+ "eval_use_gather_object": false,
137
+ "average_tokens_across_devices": true,
138
+ "sortish_sampler": false,
139
+ "predict_with_generate": false,
140
+ "generation_max_length": null,
141
+ "generation_num_beams": null,
142
+ "generation_config": null,
143
+ "tuner_backend": "peft",
144
+ "vit_gradient_checkpointing": null,
145
+ "router_aux_loss_coef": 0.0,
146
+ "enable_dft_loss": false,
147
+ "enable_channel_loss": false,
148
+ "check_model": true,
149
+ "acc_strategy": "token",
150
+ "train_dataloader_shuffle": true,
151
+ "max_epochs": null,
152
+ "aligner_lr": null,
153
+ "vit_lr": null,
154
+ "use_logits_to_keep": null,
155
+ "ds3_gather_for_generation": true,
156
+ "resume_only_model": false,
157
+ "optimizer": null,
158
+ "loss_type": null,
159
+ "metric": null,
160
+ "eval_use_evalscope": false,
161
+ "eval_dataset": [],
162
+ "eval_dataset_args": null,
163
+ "eval_limit": null,
164
+ "eval_generation_config": null,
165
+ "extra_eval_args": null,
166
+ "use_flash_ckpt": false,
167
+ "use_ray": false,
168
+ "ray_exp_name": null,
169
+ "device_groups": null,
170
+ "model": "FutureMa/Qwen3-4B-Evasion-Exp",
171
+ "model_type": "qwen3",
172
+ "model_revision": null,
173
+ "task_type": "causal_lm",
174
+ "torch_dtype": "bfloat16",
175
+ "attn_impl": null,
176
+ "new_special_tokens": [],
177
+ "num_labels": null,
178
+ "problem_type": null,
179
+ "rope_scaling": null,
180
+ "device_map": null,
181
+ "max_memory": {},
182
+ "max_model_len": null,
183
+ "local_repo_path": null,
184
+ "init_strategy": null,
185
+ "template": "qwen3_nothinking",
186
+ "system": null,
187
+ "max_length": 2048,
188
+ "truncation_strategy": "delete",
189
+ "max_pixels": null,
190
+ "agent_template": null,
191
+ "norm_bbox": null,
192
+ "use_chat_template": true,
193
+ "padding_side": "right",
194
+ "padding_free": false,
195
+ "loss_scale": "default",
196
+ "sequence_parallel_size": 1,
197
+ "template_backend": "swift",
198
+ "response_prefix": null,
199
+ "enable_thinking": null,
200
+ "add_non_thinking_prefix": true,
201
+ "dataset": [
202
+ "/home/ubuntu/ms-swift/data/balanced_30k_label_only_msswift.jsonl"
203
+ ],
204
+ "val_dataset": [],
205
+ "cached_dataset": [],
206
+ "cached_val_dataset": [],
207
+ "split_dataset_ratio": 0.0,
208
+ "dataset_num_proc": 1,
209
+ "load_from_cache_file": false,
210
+ "dataset_shuffle": true,
211
+ "val_dataset_shuffle": false,
212
+ "streaming": false,
213
+ "interleave_prob": null,
214
+ "stopping_strategy": "first_exhausted",
215
+ "shuffle_buffer_size": 1000,
216
+ "download_mode": "reuse_dataset_if_exists",
217
+ "columns": {},
218
+ "strict": false,
219
+ "model_name": null,
220
+ "model_author": null,
221
+ "custom_dataset_info": [],
222
+ "quant_method": null,
223
+ "quant_bits": null,
224
+ "hqq_axis": null,
225
+ "bnb_4bit_compute_dtype": "bfloat16",
226
+ "bnb_4bit_quant_type": "nf4",
227
+ "bnb_4bit_use_double_quant": true,
228
+ "bnb_4bit_quant_storage": null,
229
+ "max_new_tokens": 64,
230
+ "temperature": 0.0,
231
+ "top_k": null,
232
+ "top_p": null,
233
+ "repetition_penalty": null,
234
+ "num_beams": 1,
235
+ "stream": false,
236
+ "stop_words": [],
237
+ "logprobs": false,
238
+ "top_logprobs": null,
239
+ "structured_outputs_regex": null,
240
+ "ckpt_dir": null,
241
+ "lora_modules": [],
242
+ "train_type": "full",
243
+ "adapters": [],
244
+ "external_plugins": [],
245
+ "custom_register_path": [],
246
+ "model_kwargs": {},
247
+ "load_args": false,
248
+ "load_data_args": false,
249
+ "packing": false,
250
+ "packing_length": null,
251
+ "packing_num_proc": 1,
252
+ "lazy_tokenize": false,
253
+ "use_hf": true,
254
+ "ignore_args_error": false,
255
+ "use_swift_lora": false,
256
+ "freeze_parameters": [],
257
+ "freeze_parameters_regex": null,
258
+ "freeze_parameters_ratio": 0.0,
259
+ "trainable_parameters": [],
260
+ "trainable_parameters_regex": null,
261
+ "freeze_llm": false,
262
+ "freeze_vit": true,
263
+ "freeze_aligner": true,
264
+ "target_modules": [
265
+ "all-linear"
266
+ ],
267
+ "target_regex": null,
268
+ "target_parameters": null,
269
+ "modules_to_save": [],
270
+ "lora_rank": 8,
271
+ "lora_alpha": 32,
272
+ "lora_dropout": 0.05,
273
+ "lora_bias": "none",
274
+ "lora_dtype": null,
275
+ "lorap_lr_ratio": null,
276
+ "use_rslora": false,
277
+ "use_dora": false,
278
+ "lora_ga_batch_size": 2,
279
+ "lora_ga_iters": 2,
280
+ "lora_ga_max_length": 1024,
281
+ "lora_ga_direction": "ArB2r",
282
+ "lora_ga_scale": "stable",
283
+ "lora_ga_stable_gamma": 16,
284
+ "init_weights": true,
285
+ "fourier_n_frequency": 2000,
286
+ "fourier_scaling": 300.0,
287
+ "boft_block_size": 4,
288
+ "boft_block_num": 0,
289
+ "boft_n_butterfly_factor": 1,
290
+ "boft_dropout": 0.0,
291
+ "vera_rank": 256,
292
+ "vera_projection_prng_key": 0,
293
+ "vera_dropout": 0.0,
294
+ "vera_d_initial": 0.1,
295
+ "adapter_act": "gelu",
296
+ "adapter_length": 128,
297
+ "use_galore": false,
298
+ "galore_target_modules": null,
299
+ "galore_rank": 128,
300
+ "galore_update_proj_gap": 50,
301
+ "galore_scale": 1.0,
302
+ "galore_proj_type": "std",
303
+ "galore_optim_per_parameter": false,
304
+ "galore_with_embedding": false,
305
+ "galore_quantization": false,
306
+ "galore_proj_quant": false,
307
+ "galore_proj_bits": 4,
308
+ "galore_proj_group_size": 256,
309
+ "galore_cos_threshold": 0.4,
310
+ "galore_gamma_proj": 2,
311
+ "galore_queue_size": 5,
312
+ "adalora_target_r": 8,
313
+ "adalora_init_r": 12,
314
+ "adalora_tinit": 0,
315
+ "adalora_tfinal": 0,
316
+ "adalora_deltaT": 1,
317
+ "adalora_beta1": 0.85,
318
+ "adalora_beta2": 0.85,
319
+ "adalora_orth_reg_weight": 0.5,
320
+ "llamapro_num_new_blocks": 4,
321
+ "llamapro_num_groups": null,
322
+ "lisa_activated_layers": 0,
323
+ "lisa_step_interval": 20,
324
+ "reft_layer_key": null,
325
+ "reft_layers": null,
326
+ "reft_rank": 4,
327
+ "reft_intervention_type": "LoreftIntervention",
328
+ "reft_args": null,
329
+ "swanlab_token": null,
330
+ "swanlab_project": "ms-swift",
331
+ "swanlab_workspace": null,
332
+ "swanlab_exp_name": null,
333
+ "swanlab_notification_method": null,
334
+ "swanlab_webhook_url": null,
335
+ "swanlab_secret": null,
336
+ "swanlab_mode": "cloud",
337
+ "add_version": true,
338
+ "create_checkpoint_symlink": false,
339
+ "zero_hpz_partition_size": null,
340
+ "deepspeed_autotp_size": null,
341
+ "early_stop_interval": null,
342
+ "swift_version": "4.0.0.dev0",
343
+ "rank": 0,
344
+ "global_world_size": 2,
345
+ "local_world_size": 2,
346
+ "model_suffix": "Qwen3-4B-Evasion-Exp",
347
+ "model_info": "ModelInfo(model_type='qwen3', model_dir='/home/ubuntu/.cache/huggingface/hub/models--FutureMa--Qwen3-4B-Evasion-Exp/snapshots/a95696b6d485a93ec11814d2976c056d8f567b36', 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)",
348
+ "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3Guard-Gen-0.6B', hf_model_id='Qwen/Qwen3Guard-Gen-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-4B', hf_model_id='Qwen/Qwen3Guard-Gen-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-8B', hf_model_id='Qwen/Qwen3Guard-Gen-8B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_guard', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507', hf_model_id='Qwen/Qwen3-4B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template=None, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
349
+ "model_dir": "/home/ubuntu/.cache/huggingface/hub/models--FutureMa--Qwen3-4B-Evasion-Exp/snapshots/a95696b6d485a93ec11814d2976c056d8f567b36",
350
+ "_val_dataset_exists": [],
351
+ "hub": "<class 'swift.hub.hub.HFHub'>",
352
+ "evaluation_strategy": "steps",
353
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v2-20260116-230845', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v2-20260116-230845', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, 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, task_type='causal_lm', problem_type=None)"
354
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 262144,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151643,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 5000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.6",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87da5836cd683e893c2335c24b68e96c8fe5806230e8125283acf3739e6ca122
3
+ size 4967215360
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c1e5faa3c8f21a8f642092b10d3f6fa847c8df669106400100f8153555126b
3
+ size 3077766632
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 8044936192
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.norm.weight": "model-00002-of-00002.safetensors"
405
+ }
406
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940892b3207f7fc0255fb1a73629eb159f0c636b0ffb4a7f91e05492d51c7c04
3
+ size 16090225449
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
3
+ size 14917
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9a51605f7783f6fc367ac7fc787e622e534a895c2dd8db5311e2d94bf71471
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,1538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500.0,
7
+ "global_step": 1876,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0010666666666666667,
14
+ "grad_norm": 9.75,
15
+ "learning_rate": 3.5087719298245616e-07,
16
+ "loss": 0.06797242164611816,
17
+ "step": 1,
18
+ "token_acc": 0.970873786407767
19
+ },
20
+ {
21
+ "epoch": 0.010666666666666666,
22
+ "grad_norm": 3.375,
23
+ "learning_rate": 3.5087719298245615e-06,
24
+ "loss": 0.04619172546598646,
25
+ "step": 10,
26
+ "token_acc": 0.9840170484816196
27
+ },
28
+ {
29
+ "epoch": 0.021333333333333333,
30
+ "grad_norm": 1.3515625,
31
+ "learning_rate": 7.017543859649123e-06,
32
+ "loss": 0.03136685192584991,
33
+ "step": 20,
34
+ "token_acc": 0.9862650602409638
35
+ },
36
+ {
37
+ "epoch": 0.032,
38
+ "grad_norm": 2.234375,
39
+ "learning_rate": 1.0526315789473684e-05,
40
+ "loss": 0.035260409116744995,
41
+ "step": 30,
42
+ "token_acc": 0.9865771812080537
43
+ },
44
+ {
45
+ "epoch": 0.042666666666666665,
46
+ "grad_norm": 2.90625,
47
+ "learning_rate": 1.4035087719298246e-05,
48
+ "loss": 0.03275148570537567,
49
+ "step": 40,
50
+ "token_acc": 0.985594237695078
51
+ },
52
+ {
53
+ "epoch": 0.05333333333333334,
54
+ "grad_norm": 2.296875,
55
+ "learning_rate": 1.754385964912281e-05,
56
+ "loss": 0.02667125463485718,
57
+ "step": 50,
58
+ "token_acc": 0.9887181949111858
59
+ },
60
+ {
61
+ "epoch": 0.064,
62
+ "grad_norm": 1.8203125,
63
+ "learning_rate": 1.9999865771143805e-05,
64
+ "loss": 0.042026185989379884,
65
+ "step": 60,
66
+ "token_acc": 0.9822286263208453
67
+ },
68
+ {
69
+ "epoch": 0.07466666666666667,
70
+ "grad_norm": 3.046875,
71
+ "learning_rate": 1.9997479580610527e-05,
72
+ "loss": 0.041328877210617065,
73
+ "step": 70,
74
+ "token_acc": 0.9809270883631096
75
+ },
76
+ {
77
+ "epoch": 0.08533333333333333,
78
+ "grad_norm": 2.140625,
79
+ "learning_rate": 1.9992111345867986e-05,
80
+ "loss": 0.03837056159973144,
81
+ "step": 80,
82
+ "token_acc": 0.9831162566328991
83
+ },
84
+ {
85
+ "epoch": 0.096,
86
+ "grad_norm": 1.59375,
87
+ "learning_rate": 1.9983762668151084e-05,
88
+ "loss": 0.032483524084091185,
89
+ "step": 90,
90
+ "token_acc": 0.9863896848137536
91
+ },
92
+ {
93
+ "epoch": 0.10666666666666667,
94
+ "grad_norm": 1.8671875,
95
+ "learning_rate": 1.9972436037700082e-05,
96
+ "loss": 0.03307614922523498,
97
+ "step": 100,
98
+ "token_acc": 0.9855560905151661
99
+ },
100
+ {
101
+ "epoch": 0.11733333333333333,
102
+ "grad_norm": 1.734375,
103
+ "learning_rate": 1.9958134833017768e-05,
104
+ "loss": 0.0380557119846344,
105
+ "step": 110,
106
+ "token_acc": 0.98277117204562
107
+ },
108
+ {
109
+ "epoch": 0.128,
110
+ "grad_norm": 3.53125,
111
+ "learning_rate": 1.9940863319861758e-05,
112
+ "loss": 0.047079157829284665,
113
+ "step": 120,
114
+ "token_acc": 0.9812545061283345
115
+ },
116
+ {
117
+ "epoch": 0.13866666666666666,
118
+ "grad_norm": 2.625,
119
+ "learning_rate": 1.992062664997209e-05,
120
+ "loss": 0.039805743098258975,
121
+ "step": 130,
122
+ "token_acc": 0.9844460397224216
123
+ },
124
+ {
125
+ "epoch": 0.14933333333333335,
126
+ "grad_norm": 3.03125,
127
+ "learning_rate": 1.9897430859534553e-05,
128
+ "loss": 0.029691782593727113,
129
+ "step": 140,
130
+ "token_acc": 0.9876781831360232
131
+ },
132
+ {
133
+ "epoch": 0.16,
134
+ "grad_norm": 2.203125,
135
+ "learning_rate": 1.9871282867380245e-05,
136
+ "loss": 0.03704167008399963,
137
+ "step": 150,
138
+ "token_acc": 0.9851104707012488
139
+ },
140
+ {
141
+ "epoch": 0.17066666666666666,
142
+ "grad_norm": 2.828125,
143
+ "learning_rate": 1.9842190472921802e-05,
144
+ "loss": 0.03181208968162537,
145
+ "step": 160,
146
+ "token_acc": 0.9877049180327869
147
+ },
148
+ {
149
+ "epoch": 0.18133333333333335,
150
+ "grad_norm": 2.0,
151
+ "learning_rate": 1.9810162353827e-05,
152
+ "loss": 0.03544786870479584,
153
+ "step": 170,
154
+ "token_acc": 0.9834333733493398
155
+ },
156
+ {
157
+ "epoch": 0.192,
158
+ "grad_norm": 2.453125,
159
+ "learning_rate": 1.977520806343039e-05,
160
+ "loss": 0.02816782593727112,
161
+ "step": 180,
162
+ "token_acc": 0.9887935145445875
163
+ },
164
+ {
165
+ "epoch": 0.20266666666666666,
166
+ "grad_norm": 2.140625,
167
+ "learning_rate": 1.9737338027883727e-05,
168
+ "loss": 0.033563745021820066,
169
+ "step": 190,
170
+ "token_acc": 0.9869910864851843
171
+ },
172
+ {
173
+ "epoch": 0.21333333333333335,
174
+ "grad_norm": 1.1015625,
175
+ "learning_rate": 1.969656354304606e-05,
176
+ "loss": 0.037265950441360475,
177
+ "step": 200,
178
+ "token_acc": 0.983140655105973
179
+ },
180
+ {
181
+ "epoch": 0.224,
182
+ "grad_norm": 2.1875,
183
+ "learning_rate": 1.9652896771114416e-05,
184
+ "loss": 0.03406996726989746,
185
+ "step": 210,
186
+ "token_acc": 0.9867565615217915
187
+ },
188
+ {
189
+ "epoch": 0.23466666666666666,
190
+ "grad_norm": 1.875,
191
+ "learning_rate": 1.960635073699605e-05,
192
+ "loss": 0.036304399371147156,
193
+ "step": 220,
194
+ "token_acc": 0.9850169163847269
195
+ },
196
+ {
197
+ "epoch": 0.24533333333333332,
198
+ "grad_norm": 2.0625,
199
+ "learning_rate": 1.95569393244234e-05,
200
+ "loss": 0.03020932674407959,
201
+ "step": 230,
202
+ "token_acc": 0.9867437936852254
203
+ },
204
+ {
205
+ "epoch": 0.256,
206
+ "grad_norm": 3.046875,
207
+ "learning_rate": 1.950467727181284e-05,
208
+ "loss": 0.03292643427848816,
209
+ "step": 240,
210
+ "token_acc": 0.986077772443591
211
+ },
212
+ {
213
+ "epoch": 0.26666666666666666,
214
+ "grad_norm": 1.28125,
215
+ "learning_rate": 1.9449580167868506e-05,
216
+ "loss": 0.03676349222660065,
217
+ "step": 250,
218
+ "token_acc": 0.983389504092441
219
+ },
220
+ {
221
+ "epoch": 0.2773333333333333,
222
+ "grad_norm": 1.2421875,
223
+ "learning_rate": 1.939166444693252e-05,
224
+ "loss": 0.03957515358924866,
225
+ "step": 260,
226
+ "token_acc": 0.982388419782871
227
+ },
228
+ {
229
+ "epoch": 0.288,
230
+ "grad_norm": 1.875,
231
+ "learning_rate": 1.9330947384082957e-05,
232
+ "loss": 0.03727341294288635,
233
+ "step": 270,
234
+ "token_acc": 0.9828998073217726
235
+ },
236
+ {
237
+ "epoch": 0.2986666666666667,
238
+ "grad_norm": 1.0,
239
+ "learning_rate": 1.9267447089981018e-05,
240
+ "loss": 0.04420234560966492,
241
+ "step": 280,
242
+ "token_acc": 0.9821299203091041
243
+ },
244
+ {
245
+ "epoch": 0.30933333333333335,
246
+ "grad_norm": 2.046875,
247
+ "learning_rate": 1.9201182505469035e-05,
248
+ "loss": 0.03257325291633606,
249
+ "step": 290,
250
+ "token_acc": 0.986077772443591
251
+ },
252
+ {
253
+ "epoch": 0.32,
254
+ "grad_norm": 2.265625,
255
+ "learning_rate": 1.9132173395920756e-05,
256
+ "loss": 0.04046020805835724,
257
+ "step": 300,
258
+ "token_acc": 0.9863243761996161
259
+ },
260
+ {
261
+ "epoch": 0.33066666666666666,
262
+ "grad_norm": 1.6640625,
263
+ "learning_rate": 1.9060440345345762e-05,
264
+ "loss": 0.0318397045135498,
265
+ "step": 310,
266
+ "token_acc": 0.9875
267
+ },
268
+ {
269
+ "epoch": 0.3413333333333333,
270
+ "grad_norm": 2.4375,
271
+ "learning_rate": 1.8986004750249687e-05,
272
+ "loss": 0.030359810590744017,
273
+ "step": 320,
274
+ "token_acc": 0.9879576107899807
275
+ },
276
+ {
277
+ "epoch": 0.352,
278
+ "grad_norm": 2.59375,
279
+ "learning_rate": 1.890888881325205e-05,
280
+ "loss": 0.03387542963027954,
281
+ "step": 330,
282
+ "token_acc": 0.9860710854947167
283
+ },
284
+ {
285
+ "epoch": 0.3626666666666667,
286
+ "grad_norm": 1.2109375,
287
+ "learning_rate": 1.8829115536463682e-05,
288
+ "loss": 0.02995218336582184,
289
+ "step": 340,
290
+ "token_acc": 0.9878048780487805
291
+ },
292
+ {
293
+ "epoch": 0.37333333333333335,
294
+ "grad_norm": 1.5546875,
295
+ "learning_rate": 1.8746708714625668e-05,
296
+ "loss": 0.03572494685649872,
297
+ "step": 350,
298
+ "token_acc": 0.9858173076923077
299
+ },
300
+ {
301
+ "epoch": 0.384,
302
+ "grad_norm": 1.796875,
303
+ "learning_rate": 1.8661692928011858e-05,
304
+ "loss": 0.027254277467727663,
305
+ "step": 360,
306
+ "token_acc": 0.987460815047022
307
+ },
308
+ {
309
+ "epoch": 0.39466666666666667,
310
+ "grad_norm": 2.640625,
311
+ "learning_rate": 1.8574093535097062e-05,
312
+ "loss": 0.03353258669376373,
313
+ "step": 370,
314
+ "token_acc": 0.984844840028867
315
+ },
316
+ {
317
+ "epoch": 0.4053333333333333,
318
+ "grad_norm": 1.6484375,
319
+ "learning_rate": 1.8483936664993152e-05,
320
+ "loss": 0.03917534947395325,
321
+ "step": 380,
322
+ "token_acc": 0.9830917874396136
323
+ },
324
+ {
325
+ "epoch": 0.416,
326
+ "grad_norm": 1.5703125,
327
+ "learning_rate": 1.839124920965527e-05,
328
+ "loss": 0.03518342077732086,
329
+ "step": 390,
330
+ "token_acc": 0.9841346153846153
331
+ },
332
+ {
333
+ "epoch": 0.4266666666666667,
334
+ "grad_norm": 1.7890625,
335
+ "learning_rate": 1.829605881586051e-05,
336
+ "loss": 0.03069465160369873,
337
+ "step": 400,
338
+ "token_acc": 0.9872504209766658
339
+ },
340
+ {
341
+ "epoch": 0.43733333333333335,
342
+ "grad_norm": 1.5546875,
343
+ "learning_rate": 1.8198393876961446e-05,
344
+ "loss": 0.02751390039920807,
345
+ "step": 410,
346
+ "token_acc": 0.9887613582018173
347
+ },
348
+ {
349
+ "epoch": 0.448,
350
+ "grad_norm": 1.6640625,
351
+ "learning_rate": 1.8098283524416982e-05,
352
+ "loss": 0.026150995492935182,
353
+ "step": 420,
354
+ "token_acc": 0.9882606612362242
355
+ },
356
+ {
357
+ "epoch": 0.45866666666666667,
358
+ "grad_norm": 1.828125,
359
+ "learning_rate": 1.7995757619103012e-05,
360
+ "loss": 0.03289719820022583,
361
+ "step": 430,
362
+ "token_acc": 0.9862617498192335
363
+ },
364
+ {
365
+ "epoch": 0.4693333333333333,
366
+ "grad_norm": 1.921875,
367
+ "learning_rate": 1.7890846742405558e-05,
368
+ "loss": 0.035283339023590085,
369
+ "step": 440,
370
+ "token_acc": 0.98579340235974
371
+ },
372
+ {
373
+ "epoch": 0.48,
374
+ "grad_norm": 2.203125,
375
+ "learning_rate": 1.7783582187098944e-05,
376
+ "loss": 0.03278760313987732,
377
+ "step": 450,
378
+ "token_acc": 0.9858716475095786
379
+ },
380
+ {
381
+ "epoch": 0.49066666666666664,
382
+ "grad_norm": 1.6796875,
383
+ "learning_rate": 1.7673995948011807e-05,
384
+ "loss": 0.030364534258842467,
385
+ "step": 460,
386
+ "token_acc": 0.9877873563218391
387
+ },
388
+ {
389
+ "epoch": 0.5013333333333333,
390
+ "grad_norm": 1.40625,
391
+ "learning_rate": 1.75621207124837e-05,
392
+ "loss": 0.02944081127643585,
393
+ "step": 470,
394
+ "token_acc": 0.9857522337599613
395
+ },
396
+ {
397
+ "epoch": 0.512,
398
+ "grad_norm": 2.359375,
399
+ "learning_rate": 1.7447989850615114e-05,
400
+ "loss": 0.03358876705169678,
401
+ "step": 480,
402
+ "token_acc": 0.9858343337334934
403
+ },
404
+ {
405
+ "epoch": 0.5226666666666666,
406
+ "grad_norm": 1.9609375,
407
+ "learning_rate": 1.733163740531386e-05,
408
+ "loss": 0.03116101920604706,
409
+ "step": 490,
410
+ "token_acc": 0.9863603732950467
411
+ },
412
+ {
413
+ "epoch": 0.5333333333333333,
414
+ "grad_norm": 0.91015625,
415
+ "learning_rate": 1.7213098082140774e-05,
416
+ "loss": 0.030902951955795288,
417
+ "step": 500,
418
+ "token_acc": 0.9863276565123531
419
+ },
420
+ {
421
+ "epoch": 0.544,
422
+ "grad_norm": 1.1953125,
423
+ "learning_rate": 1.7092407238957737e-05,
424
+ "loss": 0.03449364304542542,
425
+ "step": 510,
426
+ "token_acc": 0.988502994011976
427
+ },
428
+ {
429
+ "epoch": 0.5546666666666666,
430
+ "grad_norm": 1.1875,
431
+ "learning_rate": 1.6969600875381172e-05,
432
+ "loss": 0.0299816370010376,
433
+ "step": 520,
434
+ "token_acc": 0.9869109947643979
435
+ },
436
+ {
437
+ "epoch": 0.5653333333333334,
438
+ "grad_norm": 1.2265625,
439
+ "learning_rate": 1.684471562204407e-05,
440
+ "loss": 0.033460429310798644,
441
+ "step": 530,
442
+ "token_acc": 0.9860744297719087
443
+ },
444
+ {
445
+ "epoch": 0.576,
446
+ "grad_norm": 1.6875,
447
+ "learning_rate": 1.6717788729669822e-05,
448
+ "loss": 0.029380664229393005,
449
+ "step": 540,
450
+ "token_acc": 0.9881756756756757
451
+ },
452
+ {
453
+ "epoch": 0.5866666666666667,
454
+ "grad_norm": 2.21875,
455
+ "learning_rate": 1.658885805796111e-05,
456
+ "loss": 0.0348785400390625,
457
+ "step": 550,
458
+ "token_acc": 0.9853047458443749
459
+ },
460
+ {
461
+ "epoch": 0.5973333333333334,
462
+ "grad_norm": 1.1015625,
463
+ "learning_rate": 1.6457962064307104e-05,
464
+ "loss": 0.025776177644729614,
465
+ "step": 560,
466
+ "token_acc": 0.9886883273164861
467
+ },
468
+ {
469
+ "epoch": 0.608,
470
+ "grad_norm": 2.453125,
471
+ "learning_rate": 1.6325139792312414e-05,
472
+ "loss": 0.03230432271957397,
473
+ "step": 570,
474
+ "token_acc": 0.9868641031764986
475
+ },
476
+ {
477
+ "epoch": 0.6186666666666667,
478
+ "grad_norm": 2.265625,
479
+ "learning_rate": 1.6190430860151196e-05,
480
+ "loss": 0.031005895137786864,
481
+ "step": 580,
482
+ "token_acc": 0.9841612670986322
483
+ },
484
+ {
485
+ "epoch": 0.6293333333333333,
486
+ "grad_norm": 2.546875,
487
+ "learning_rate": 1.605387544874983e-05,
488
+ "loss": 0.03286699056625366,
489
+ "step": 590,
490
+ "token_acc": 0.9843033083796184
491
+ },
492
+ {
493
+ "epoch": 0.64,
494
+ "grad_norm": 1.515625,
495
+ "learning_rate": 1.591551428980179e-05,
496
+ "loss": 0.032039952278137204,
497
+ "step": 600,
498
+ "token_acc": 0.9858648778150455
499
+ },
500
+ {
501
+ "epoch": 0.6506666666666666,
502
+ "grad_norm": 1.3515625,
503
+ "learning_rate": 1.5775388653618217e-05,
504
+ "loss": 0.03594903945922852,
505
+ "step": 610,
506
+ "token_acc": 0.9849318344893566
507
+ },
508
+ {
509
+ "epoch": 0.6613333333333333,
510
+ "grad_norm": 2.625,
511
+ "learning_rate": 1.5633540336817804e-05,
512
+ "loss": 0.027490669488906862,
513
+ "step": 620,
514
+ "token_acc": 0.985925572519084
515
+ },
516
+ {
517
+ "epoch": 0.672,
518
+ "grad_norm": 1.75,
519
+ "learning_rate": 1.549001164985973e-05,
520
+ "loss": 0.03038315773010254,
521
+ "step": 630,
522
+ "token_acc": 0.9857865574560347
523
+ },
524
+ {
525
+ "epoch": 0.6826666666666666,
526
+ "grad_norm": 2.109375,
527
+ "learning_rate": 1.5344845404423313e-05,
528
+ "loss": 0.0375783383846283,
529
+ "step": 640,
530
+ "token_acc": 0.981414433985035
531
+ },
532
+ {
533
+ "epoch": 0.6933333333333334,
534
+ "grad_norm": 1.3515625,
535
+ "learning_rate": 1.5198084900638161e-05,
536
+ "loss": 0.03005017340183258,
537
+ "step": 650,
538
+ "token_acc": 0.9848082951531227
539
+ },
540
+ {
541
+ "epoch": 0.704,
542
+ "grad_norm": 0.7265625,
543
+ "learning_rate": 1.5049773914168629e-05,
544
+ "loss": 0.031009536981582642,
545
+ "step": 660,
546
+ "token_acc": 0.9857899807321773
547
+ },
548
+ {
549
+ "epoch": 0.7146666666666667,
550
+ "grad_norm": 2.34375,
551
+ "learning_rate": 1.4899956683156413e-05,
552
+ "loss": 0.033309900760650636,
553
+ "step": 670,
554
+ "token_acc": 0.98503861003861
555
+ },
556
+ {
557
+ "epoch": 0.7253333333333334,
558
+ "grad_norm": 1.9921875,
559
+ "learning_rate": 1.4748677895025243e-05,
560
+ "loss": 0.03143962621688843,
561
+ "step": 680,
562
+ "token_acc": 0.9863013698630136
563
+ },
564
+ {
565
+ "epoch": 0.736,
566
+ "grad_norm": 1.5703125,
567
+ "learning_rate": 1.4595982673151511e-05,
568
+ "loss": 0.028191816806793214,
569
+ "step": 690,
570
+ "token_acc": 0.9877785765636233
571
+ },
572
+ {
573
+ "epoch": 0.7466666666666667,
574
+ "grad_norm": 1.9921875,
575
+ "learning_rate": 1.444191656340491e-05,
576
+ "loss": 0.02878325283527374,
577
+ "step": 700,
578
+ "token_acc": 0.9867437936852254
579
+ },
580
+ {
581
+ "epoch": 0.7573333333333333,
582
+ "grad_norm": 0.875,
583
+ "learning_rate": 1.4286525520563003e-05,
584
+ "loss": 0.028445839881896973,
585
+ "step": 710,
586
+ "token_acc": 0.9870192307692308
587
+ },
588
+ {
589
+ "epoch": 0.768,
590
+ "grad_norm": 1.921875,
591
+ "learning_rate": 1.4129855894603885e-05,
592
+ "loss": 0.02481076419353485,
593
+ "step": 720,
594
+ "token_acc": 0.9894636015325671
595
+ },
596
+ {
597
+ "epoch": 0.7786666666666666,
598
+ "grad_norm": 1.703125,
599
+ "learning_rate": 1.3971954416880897e-05,
600
+ "loss": 0.032581061124801636,
601
+ "step": 730,
602
+ "token_acc": 0.9865222623345367
603
+ },
604
+ {
605
+ "epoch": 0.7893333333333333,
606
+ "grad_norm": 1.28125,
607
+ "learning_rate": 1.3812868186183641e-05,
608
+ "loss": 0.03237102627754211,
609
+ "step": 740,
610
+ "token_acc": 0.9857865574560347
611
+ },
612
+ {
613
+ "epoch": 0.8,
614
+ "grad_norm": 0.83984375,
615
+ "learning_rate": 1.3652644654689355e-05,
616
+ "loss": 0.027326399087905885,
617
+ "step": 750,
618
+ "token_acc": 0.9896634615384615
619
+ },
620
+ {
621
+ "epoch": 0.8106666666666666,
622
+ "grad_norm": 2.59375,
623
+ "learning_rate": 1.3491331613808909e-05,
624
+ "loss": 0.032716572284698486,
625
+ "step": 760,
626
+ "token_acc": 0.9857831325301205
627
+ },
628
+ {
629
+ "epoch": 0.8213333333333334,
630
+ "grad_norm": 2.171875,
631
+ "learning_rate": 1.3328977179931595e-05,
632
+ "loss": 0.03095829486846924,
633
+ "step": 770,
634
+ "token_acc": 0.9869848156182213
635
+ },
636
+ {
637
+ "epoch": 0.832,
638
+ "grad_norm": 1.0625,
639
+ "learning_rate": 1.3165629780072991e-05,
640
+ "loss": 0.029185777902603148,
641
+ "step": 780,
642
+ "token_acc": 0.9876960193003619
643
+ },
644
+ {
645
+ "epoch": 0.8426666666666667,
646
+ "grad_norm": 1.1328125,
647
+ "learning_rate": 1.3001338137430163e-05,
648
+ "loss": 0.024865221977233887,
649
+ "step": 790,
650
+ "token_acc": 0.9870720612880057
651
+ },
652
+ {
653
+ "epoch": 0.8533333333333334,
654
+ "grad_norm": 1.15625,
655
+ "learning_rate": 1.2836151256848562e-05,
656
+ "loss": 0.029257166385650634,
657
+ "step": 800,
658
+ "token_acc": 0.9872779644743159
659
+ },
660
+ {
661
+ "epoch": 0.864,
662
+ "grad_norm": 3.296875,
663
+ "learning_rate": 1.2670118410204819e-05,
664
+ "loss": 0.031032463908195494,
665
+ "step": 810,
666
+ "token_acc": 0.9853153586904189
667
+ },
668
+ {
669
+ "epoch": 0.8746666666666667,
670
+ "grad_norm": 1.5234375,
671
+ "learning_rate": 1.250328912171001e-05,
672
+ "loss": 0.027763417363166808,
673
+ "step": 820,
674
+ "token_acc": 0.9882719004308281
675
+ },
676
+ {
677
+ "epoch": 0.8853333333333333,
678
+ "grad_norm": 1.40625,
679
+ "learning_rate": 1.2335713153137551e-05,
680
+ "loss": 0.03198724389076233,
681
+ "step": 830,
682
+ "token_acc": 0.9862947823996153
683
+ },
684
+ {
685
+ "epoch": 0.896,
686
+ "grad_norm": 1.4453125,
687
+ "learning_rate": 1.2167440488980309e-05,
688
+ "loss": 0.02678609490394592,
689
+ "step": 840,
690
+ "token_acc": 0.9867053420352913
691
+ },
692
+ {
693
+ "epoch": 0.9066666666666666,
694
+ "grad_norm": 2.390625,
695
+ "learning_rate": 1.1998521321541214e-05,
696
+ "loss": 0.028643500804901124,
697
+ "step": 850,
698
+ "token_acc": 0.9868483978957436
699
+ },
700
+ {
701
+ "epoch": 0.9173333333333333,
702
+ "grad_norm": 0.8203125,
703
+ "learning_rate": 1.1829006035961947e-05,
704
+ "loss": 0.033641707897186277,
705
+ "step": 860,
706
+ "token_acc": 0.983855421686747
707
+ },
708
+ {
709
+ "epoch": 0.928,
710
+ "grad_norm": 0.75390625,
711
+ "learning_rate": 1.165894519519407e-05,
712
+ "loss": 0.02538594901561737,
713
+ "step": 870,
714
+ "token_acc": 0.9887290167865708
715
+ },
716
+ {
717
+ "epoch": 0.9386666666666666,
718
+ "grad_norm": 0.92578125,
719
+ "learning_rate": 1.148838952491712e-05,
720
+ "loss": 0.029299235343933104,
721
+ "step": 880,
722
+ "token_acc": 0.9872350674373795
723
+ },
724
+ {
725
+ "epoch": 0.9493333333333334,
726
+ "grad_norm": 1.4296875,
727
+ "learning_rate": 1.1317389898408188e-05,
728
+ "loss": 0.027896964550018312,
729
+ "step": 890,
730
+ "token_acc": 0.9877668505636843
731
+ },
732
+ {
733
+ "epoch": 0.96,
734
+ "grad_norm": 1.1796875,
735
+ "learning_rate": 1.1145997321367454e-05,
736
+ "loss": 0.02889745831489563,
737
+ "step": 900,
738
+ "token_acc": 0.9889316650625601
739
+ },
740
+ {
741
+ "epoch": 0.9706666666666667,
742
+ "grad_norm": 2.203125,
743
+ "learning_rate": 1.0974262916704223e-05,
744
+ "loss": 0.030401945114135742,
745
+ "step": 910,
746
+ "token_acc": 0.986557849255881
747
+ },
748
+ {
749
+ "epoch": 0.9813333333333333,
750
+ "grad_norm": 1.9375,
751
+ "learning_rate": 1.0802237909288005e-05,
752
+ "loss": 0.029643896222114562,
753
+ "step": 920,
754
+ "token_acc": 0.9869942196531792
755
+ },
756
+ {
757
+ "epoch": 0.992,
758
+ "grad_norm": 2.90625,
759
+ "learning_rate": 1.062997361066918e-05,
760
+ "loss": 0.02902018129825592,
761
+ "step": 930,
762
+ "token_acc": 0.9874396135265701
763
+ },
764
+ {
765
+ "epoch": 1.0021333333333333,
766
+ "grad_norm": 1.0234375,
767
+ "learning_rate": 1.0457521403773823e-05,
768
+ "loss": 0.02213967442512512,
769
+ "step": 940,
770
+ "token_acc": 0.9900153609831029
771
+ },
772
+ {
773
+ "epoch": 1.0128,
774
+ "grad_norm": 1.3125,
775
+ "learning_rate": 1.0284932727577203e-05,
776
+ "loss": 0.010565431416034698,
777
+ "step": 950,
778
+ "token_acc": 0.9968839884947267
779
+ },
780
+ {
781
+ "epoch": 1.0234666666666667,
782
+ "grad_norm": 1.1640625,
783
+ "learning_rate": 1.0112259061760605e-05,
784
+ "loss": 0.01075158715248108,
785
+ "step": 960,
786
+ "token_acc": 0.9956741167988464
787
+ },
788
+ {
789
+ "epoch": 1.0341333333333333,
790
+ "grad_norm": 2.484375,
791
+ "learning_rate": 9.939551911355979e-06,
792
+ "loss": 0.016012924909591674,
793
+ "step": 970,
794
+ "token_acc": 0.9942335415665545
795
+ },
796
+ {
797
+ "epoch": 1.0448,
798
+ "grad_norm": 1.578125,
799
+ "learning_rate": 9.766862791383054e-06,
800
+ "loss": 0.012686330080032348,
801
+ "step": 980,
802
+ "token_acc": 0.995164410058027
803
+ },
804
+ {
805
+ "epoch": 1.0554666666666668,
806
+ "grad_norm": 0.9609375,
807
+ "learning_rate": 9.59424321148343e-06,
808
+ "loss": 0.006662490963935852,
809
+ "step": 990,
810
+ "token_acc": 0.9975984630163305
811
+ },
812
+ {
813
+ "epoch": 1.0661333333333334,
814
+ "grad_norm": 0.765625,
815
+ "learning_rate": 9.42174466055634e-06,
816
+ "loss": 0.0062740519642829895,
817
+ "step": 1000,
818
+ "token_acc": 0.9980694980694981
819
+ },
820
+ {
821
+ "epoch": 1.0768,
822
+ "grad_norm": 2.515625,
823
+ "learning_rate": 9.249418591400539e-06,
824
+ "loss": 0.011450471729040146,
825
+ "step": 1010,
826
+ "token_acc": 0.9964046021093
827
+ },
828
+ {
829
+ "epoch": 1.0874666666666666,
830
+ "grad_norm": 2.75,
831
+ "learning_rate": 9.07731640536698e-06,
832
+ "loss": 0.014336982369422912,
833
+ "step": 1020,
834
+ "token_acc": 0.9954172696575012
835
+ },
836
+ {
837
+ "epoch": 1.0981333333333334,
838
+ "grad_norm": 0.77734375,
839
+ "learning_rate": 8.90548943702686e-06,
840
+ "loss": 0.009051916003227235,
841
+ "step": 1030,
842
+ "token_acc": 0.9963820549927641
843
+ },
844
+ {
845
+ "epoch": 1.1088,
846
+ "grad_norm": 3.40625,
847
+ "learning_rate": 8.733988938859545e-06,
848
+ "loss": 0.014770987629890441,
849
+ "step": 1040,
850
+ "token_acc": 0.9946962391513983
851
+ },
852
+ {
853
+ "epoch": 1.1194666666666666,
854
+ "grad_norm": 0.40625,
855
+ "learning_rate": 8.562866065965013e-06,
856
+ "loss": 0.0071306928992271425,
857
+ "step": 1050,
858
+ "token_acc": 0.9971112181030333
859
+ },
860
+ {
861
+ "epoch": 1.1301333333333332,
862
+ "grad_norm": 1.5703125,
863
+ "learning_rate": 8.39217186080532e-06,
864
+ "loss": 0.010715489089488984,
865
+ "step": 1060,
866
+ "token_acc": 0.9963916285783017
867
+ },
868
+ {
869
+ "epoch": 1.1408,
870
+ "grad_norm": 0.8125,
871
+ "learning_rate": 8.221957237979686e-06,
872
+ "loss": 0.011085398495197296,
873
+ "step": 1070,
874
+ "token_acc": 0.9956374212312167
875
+ },
876
+ {
877
+ "epoch": 1.1514666666666666,
878
+ "grad_norm": 1.859375,
879
+ "learning_rate": 8.052272969037702e-06,
880
+ "loss": 0.011836430430412293,
881
+ "step": 1080,
882
+ "token_acc": 0.9942154736080984
883
+ },
884
+ {
885
+ "epoch": 1.1621333333333332,
886
+ "grad_norm": 2.5625,
887
+ "learning_rate": 7.88316966733522e-06,
888
+ "loss": 0.00989045649766922,
889
+ "step": 1090,
890
+ "token_acc": 0.9959281437125749
891
+ },
892
+ {
893
+ "epoch": 1.1728,
894
+ "grad_norm": 2.25,
895
+ "learning_rate": 7.71469777293741e-06,
896
+ "loss": 0.012199420481920242,
897
+ "step": 1100,
898
+ "token_acc": 0.995438175270108
899
+ },
900
+ {
901
+ "epoch": 1.1834666666666667,
902
+ "grad_norm": 1.4765625,
903
+ "learning_rate": 7.546907537573529e-06,
904
+ "loss": 0.01276719719171524,
905
+ "step": 1110,
906
+ "token_acc": 0.9954216867469879
907
+ },
908
+ {
909
+ "epoch": 1.1941333333333333,
910
+ "grad_norm": 1.171875,
911
+ "learning_rate": 7.379849009647848e-06,
912
+ "loss": 0.008200515061616898,
913
+ "step": 1120,
914
+ "token_acc": 0.9975851243660951
915
+ },
916
+ {
917
+ "epoch": 1.2048,
918
+ "grad_norm": 1.7734375,
919
+ "learning_rate": 7.213572019311235e-06,
920
+ "loss": 0.010789988934993744,
921
+ "step": 1130,
922
+ "token_acc": 0.9956751561749159
923
+ },
924
+ {
925
+ "epoch": 1.2154666666666667,
926
+ "grad_norm": 2.390625,
927
+ "learning_rate": 7.04812616359784e-06,
928
+ "loss": 0.00852215737104416,
929
+ "step": 1140,
930
+ "token_acc": 0.9968958930276982
931
+ },
932
+ {
933
+ "epoch": 1.2261333333333333,
934
+ "grad_norm": 2.375,
935
+ "learning_rate": 6.883560791631307e-06,
936
+ "loss": 0.010482875257730484,
937
+ "step": 1150,
938
+ "token_acc": 0.9961371318203767
939
+ },
940
+ {
941
+ "epoch": 1.2368000000000001,
942
+ "grad_norm": 0.95703125,
943
+ "learning_rate": 6.7199249899049435e-06,
944
+ "loss": 0.012379509210586549,
945
+ "step": 1160,
946
+ "token_acc": 0.9954249939802552
947
+ },
948
+ {
949
+ "epoch": 1.2474666666666667,
950
+ "grad_norm": 2.953125,
951
+ "learning_rate": 6.557267567640217e-06,
952
+ "loss": 0.010692089051008224,
953
+ "step": 1170,
954
+ "token_acc": 0.9959271681839962
955
+ },
956
+ {
957
+ "epoch": 1.2581333333333333,
958
+ "grad_norm": 0.65234375,
959
+ "learning_rate": 6.3956370422279625e-06,
960
+ "loss": 0.0074609115719795225,
961
+ "step": 1180,
962
+ "token_acc": 0.997589780670041
963
+ },
964
+ {
965
+ "epoch": 1.2688,
966
+ "grad_norm": 2.9375,
967
+ "learning_rate": 6.235081624756629e-06,
968
+ "loss": 0.009892877936363221,
969
+ "step": 1190,
970
+ "token_acc": 0.9968636911942099
971
+ },
972
+ {
973
+ "epoch": 1.2794666666666665,
974
+ "grad_norm": 1.765625,
975
+ "learning_rate": 6.075649205631904e-06,
976
+ "loss": 0.011288212984800339,
977
+ "step": 1200,
978
+ "token_acc": 0.9954414587332053
979
+ },
980
+ {
981
+ "epoch": 1.2901333333333334,
982
+ "grad_norm": 2.421875,
983
+ "learning_rate": 5.917387340291969e-06,
984
+ "loss": 0.009337464720010758,
985
+ "step": 1210,
986
+ "token_acc": 0.9973595775324052
987
+ },
988
+ {
989
+ "epoch": 1.3008,
990
+ "grad_norm": 3.578125,
991
+ "learning_rate": 5.760343235022703e-06,
992
+ "loss": 0.017143648862838746,
993
+ "step": 1220,
994
+ "token_acc": 0.9942321557317952
995
+ },
996
+ {
997
+ "epoch": 1.3114666666666666,
998
+ "grad_norm": 2.15625,
999
+ "learning_rate": 5.604563732876989e-06,
1000
+ "loss": 0.013416722416877747,
1001
+ "step": 1230,
1002
+ "token_acc": 0.9958887545344619
1003
+ },
1004
+ {
1005
+ "epoch": 1.3221333333333334,
1006
+ "grad_norm": 3.375,
1007
+ "learning_rate": 5.450095299702392e-06,
1008
+ "loss": 0.017079284787178038,
1009
+ "step": 1240,
1010
+ "token_acc": 0.9930238152513832
1011
+ },
1012
+ {
1013
+ "epoch": 1.3328,
1014
+ "grad_norm": 1.8515625,
1015
+ "learning_rate": 5.296984010281367e-06,
1016
+ "loss": 0.009312470257282258,
1017
+ "step": 1250,
1018
+ "token_acc": 0.9961722488038277
1019
+ },
1020
+ {
1021
+ "epoch": 1.3434666666666666,
1022
+ "grad_norm": 1.8828125,
1023
+ "learning_rate": 5.145275534588053e-06,
1024
+ "loss": 0.012822112441062928,
1025
+ "step": 1260,
1026
+ "token_acc": 0.995438175270108
1027
+ },
1028
+ {
1029
+ "epoch": 1.3541333333333334,
1030
+ "grad_norm": 0.92578125,
1031
+ "learning_rate": 4.995015124165883e-06,
1032
+ "loss": 0.0064118683338165285,
1033
+ "step": 1270,
1034
+ "token_acc": 0.9976047904191617
1035
+ },
1036
+ {
1037
+ "epoch": 1.3648,
1038
+ "grad_norm": 0.7265625,
1039
+ "learning_rate": 4.8462475986299625e-06,
1040
+ "loss": 0.015998595952987672,
1041
+ "step": 1280,
1042
+ "token_acc": 0.9946898382814385
1043
+ },
1044
+ {
1045
+ "epoch": 1.3754666666666666,
1046
+ "grad_norm": 1.2109375,
1047
+ "learning_rate": 4.69901733229828e-06,
1048
+ "loss": 0.011354514211416245,
1049
+ "step": 1290,
1050
+ "token_acc": 0.9952049868137137
1051
+ },
1052
+ {
1053
+ "epoch": 1.3861333333333334,
1054
+ "grad_norm": 1.421875,
1055
+ "learning_rate": 4.5533682409557745e-06,
1056
+ "loss": 0.01483256220817566,
1057
+ "step": 1300,
1058
+ "token_acc": 0.995706106870229
1059
+ },
1060
+ {
1061
+ "epoch": 1.3968,
1062
+ "grad_norm": 3.078125,
1063
+ "learning_rate": 4.409343768755135e-06,
1064
+ "loss": 0.009935888648033141,
1065
+ "step": 1310,
1066
+ "token_acc": 0.99592032637389
1067
+ },
1068
+ {
1069
+ "epoch": 1.4074666666666666,
1070
+ "grad_norm": 1.2578125,
1071
+ "learning_rate": 4.266986875258299e-06,
1072
+ "loss": 0.013563062250614166,
1073
+ "step": 1320,
1074
+ "token_acc": 0.9956730769230769
1075
+ },
1076
+ {
1077
+ "epoch": 1.4181333333333335,
1078
+ "grad_norm": 1.203125,
1079
+ "learning_rate": 4.126340022622506e-06,
1080
+ "loss": 0.011859767884016038,
1081
+ "step": 1330,
1082
+ "token_acc": 0.9961713328547499
1083
+ },
1084
+ {
1085
+ "epoch": 1.4288,
1086
+ "grad_norm": 0.73046875,
1087
+ "learning_rate": 3.987445162934689e-06,
1088
+ "loss": 0.007380545139312744,
1089
+ "step": 1340,
1090
+ "token_acc": 0.9973627427475426
1091
+ },
1092
+ {
1093
+ "epoch": 1.4394666666666667,
1094
+ "grad_norm": 1.359375,
1095
+ "learning_rate": 3.850343725698018e-06,
1096
+ "loss": 0.011476223170757294,
1097
+ "step": 1350,
1098
+ "token_acc": 0.9949640287769784
1099
+ },
1100
+ {
1101
+ "epoch": 1.4501333333333333,
1102
+ "grad_norm": 1.3046875,
1103
+ "learning_rate": 3.7150766054743393e-06,
1104
+ "loss": 0.008989098668098449,
1105
+ "step": 1360,
1106
+ "token_acc": 0.9966370405957242
1107
+ },
1108
+ {
1109
+ "epoch": 1.4607999999999999,
1110
+ "grad_norm": 1.1171875,
1111
+ "learning_rate": 3.5816841496861563e-06,
1112
+ "loss": 0.008315403014421463,
1113
+ "step": 1370,
1114
+ "token_acc": 0.9968772519817439
1115
+ },
1116
+ {
1117
+ "epoch": 1.4714666666666667,
1118
+ "grad_norm": 1.3203125,
1119
+ "learning_rate": 3.4502061465818024e-06,
1120
+ "loss": 0.012508057057857513,
1121
+ "step": 1380,
1122
+ "token_acc": 0.9963776865491427
1123
+ },
1124
+ {
1125
+ "epoch": 1.4821333333333333,
1126
+ "grad_norm": 1.9453125,
1127
+ "learning_rate": 3.3206818133674478e-06,
1128
+ "loss": 0.013706037402153015,
1129
+ "step": 1390,
1130
+ "token_acc": 0.9961436490720655
1131
+ },
1132
+ {
1133
+ "epoch": 1.4928,
1134
+ "grad_norm": 2.171875,
1135
+ "learning_rate": 3.1931497845093753e-06,
1136
+ "loss": 0.010326726734638214,
1137
+ "step": 1400,
1138
+ "token_acc": 0.9968936678614098
1139
+ },
1140
+ {
1141
+ "epoch": 1.5034666666666667,
1142
+ "grad_norm": 0.4296875,
1143
+ "learning_rate": 3.0676481002101223e-06,
1144
+ "loss": 0.00966293215751648,
1145
+ "step": 1410,
1146
+ "token_acc": 0.9968697327233326
1147
+ },
1148
+ {
1149
+ "epoch": 1.5141333333333333,
1150
+ "grad_norm": 1.71875,
1151
+ "learning_rate": 2.9442141950618762e-06,
1152
+ "loss": 0.010416048765182494,
1153
+ "step": 1420,
1154
+ "token_acc": 0.9968862275449102
1155
+ },
1156
+ {
1157
+ "epoch": 1.5248,
1158
+ "grad_norm": 1.7578125,
1159
+ "learning_rate": 2.8228848868804714e-06,
1160
+ "loss": 0.010529063642024994,
1161
+ "step": 1430,
1162
+ "token_acc": 0.9954337899543378
1163
+ },
1164
+ {
1165
+ "epoch": 1.5354666666666668,
1166
+ "grad_norm": 1.078125,
1167
+ "learning_rate": 2.7036963657234105e-06,
1168
+ "loss": 0.009810931980609894,
1169
+ "step": 1440,
1170
+ "token_acc": 0.9966208061790973
1171
+ },
1172
+ {
1173
+ "epoch": 1.5461333333333334,
1174
+ "grad_norm": 1.9609375,
1175
+ "learning_rate": 2.5866841830950994e-06,
1176
+ "loss": 0.010760371387004853,
1177
+ "step": 1450,
1178
+ "token_acc": 0.9954501915708812
1179
+ },
1180
+ {
1181
+ "epoch": 1.5568,
1182
+ "grad_norm": 1.0625,
1183
+ "learning_rate": 2.47188324134255e-06,
1184
+ "loss": 0.011224661022424698,
1185
+ "step": 1460,
1186
+ "token_acc": 0.9966434907695996
1187
+ },
1188
+ {
1189
+ "epoch": 1.5674666666666668,
1190
+ "grad_norm": 1.03125,
1191
+ "learning_rate": 2.3593277832447405e-06,
1192
+ "loss": 0.01038598120212555,
1193
+ "step": 1470,
1194
+ "token_acc": 0.9959552700452058
1195
+ },
1196
+ {
1197
+ "epoch": 1.5781333333333334,
1198
+ "grad_norm": 0.80078125,
1199
+ "learning_rate": 2.2490513817986757e-06,
1200
+ "loss": 0.010531876236200333,
1201
+ "step": 1480,
1202
+ "token_acc": 0.9968734968734969
1203
+ },
1204
+ {
1205
+ "epoch": 1.5888,
1206
+ "grad_norm": 1.8515625,
1207
+ "learning_rate": 2.141086930205255e-06,
1208
+ "loss": 0.010695824027061462,
1209
+ "step": 1490,
1210
+ "token_acc": 0.9956782713085234
1211
+ },
1212
+ {
1213
+ "epoch": 1.5994666666666668,
1214
+ "grad_norm": 1.5703125,
1215
+ "learning_rate": 2.035466632057905e-06,
1216
+ "loss": 0.007252989709377289,
1217
+ "step": 1500,
1218
+ "token_acc": 0.9966483121857793
1219
+ },
1220
+ {
1221
+ "epoch": 1.6101333333333332,
1222
+ "grad_norm": 0.18359375,
1223
+ "learning_rate": 1.9322219917369e-06,
1224
+ "loss": 0.007471411675214768,
1225
+ "step": 1510,
1226
+ "token_acc": 0.9971133028626413
1227
+ },
1228
+ {
1229
+ "epoch": 1.6208,
1230
+ "grad_norm": 2.15625,
1231
+ "learning_rate": 1.8313838050122423e-06,
1232
+ "loss": 0.015065881609916686,
1233
+ "step": 1520,
1234
+ "token_acc": 0.9946885562530179
1235
+ },
1236
+ {
1237
+ "epoch": 1.6314666666666666,
1238
+ "grad_norm": 2.46875,
1239
+ "learning_rate": 1.7329821498579257e-06,
1240
+ "loss": 0.013307811319828033,
1241
+ "step": 1530,
1242
+ "token_acc": 0.9947000722717417
1243
+ },
1244
+ {
1245
+ "epoch": 1.6421333333333332,
1246
+ "grad_norm": 1.375,
1247
+ "learning_rate": 1.6370463774802759e-06,
1248
+ "loss": 0.008927606046199799,
1249
+ "step": 1540,
1250
+ "token_acc": 0.9973513123043583
1251
+ },
1252
+ {
1253
+ "epoch": 1.6528,
1254
+ "grad_norm": 2.296875,
1255
+ "learning_rate": 1.5436051035630962e-06,
1256
+ "loss": 0.010501272231340408,
1257
+ "step": 1550,
1258
+ "token_acc": 0.9963820549927641
1259
+ },
1260
+ {
1261
+ "epoch": 1.6634666666666666,
1262
+ "grad_norm": 1.8046875,
1263
+ "learning_rate": 1.4526861997321794e-06,
1264
+ "loss": 0.013346484303474427,
1265
+ "step": 1560,
1266
+ "token_acc": 0.9951969260326609
1267
+ },
1268
+ {
1269
+ "epoch": 1.6741333333333333,
1270
+ "grad_norm": 1.1015625,
1271
+ "learning_rate": 1.3643167852417894e-06,
1272
+ "loss": 0.011042323708534241,
1273
+ "step": 1570,
1274
+ "token_acc": 0.9959359311498924
1275
+ },
1276
+ {
1277
+ "epoch": 1.6848,
1278
+ "grad_norm": 1.6953125,
1279
+ "learning_rate": 1.278523218885518e-06,
1280
+ "loss": 0.008789537847042084,
1281
+ "step": 1580,
1282
+ "token_acc": 0.9968877184582237
1283
+ },
1284
+ {
1285
+ "epoch": 1.6954666666666667,
1286
+ "grad_norm": 1.5546875,
1287
+ "learning_rate": 1.1953310911340165e-06,
1288
+ "loss": 0.009821423888206482,
1289
+ "step": 1590,
1290
+ "token_acc": 0.9949507093051214
1291
+ },
1292
+ {
1293
+ "epoch": 1.7061333333333333,
1294
+ "grad_norm": 2.09375,
1295
+ "learning_rate": 1.1147652165018597e-06,
1296
+ "loss": 0.009412066638469696,
1297
+ "step": 1600,
1298
+ "token_acc": 0.9966378482228626
1299
+ },
1300
+ {
1301
+ "epoch": 1.7168,
1302
+ "grad_norm": 0.703125,
1303
+ "learning_rate": 1.0368496261459004e-06,
1304
+ "loss": 0.011984483152627946,
1305
+ "step": 1610,
1306
+ "token_acc": 0.995906573561281
1307
+ },
1308
+ {
1309
+ "epoch": 1.7274666666666667,
1310
+ "grad_norm": 1.1875,
1311
+ "learning_rate": 9.616075606972597e-07,
1312
+ "loss": 0.007756148278713226,
1313
+ "step": 1620,
1314
+ "token_acc": 0.9971181556195965
1315
+ },
1316
+ {
1317
+ "epoch": 1.7381333333333333,
1318
+ "grad_norm": 2.046875,
1319
+ "learning_rate": 8.890614633291095e-07,
1320
+ "loss": 0.00872180163860321,
1321
+ "step": 1630,
1322
+ "token_acc": 0.9966313763233878
1323
+ },
1324
+ {
1325
+ "epoch": 1.7488000000000001,
1326
+ "grad_norm": 2.546875,
1327
+ "learning_rate": 8.192329730623471e-07,
1328
+ "loss": 0.011189891397953034,
1329
+ "step": 1640,
1330
+ "token_acc": 0.9973765800143095
1331
+ },
1332
+ {
1333
+ "epoch": 1.7594666666666665,
1334
+ "grad_norm": 1.3671875,
1335
+ "learning_rate": 7.521429183111139e-07,
1336
+ "loss": 0.011723892390727996,
1337
+ "step": 1650,
1338
+ "token_acc": 0.9959036144578314
1339
+ },
1340
+ {
1341
+ "epoch": 1.7701333333333333,
1342
+ "grad_norm": 2.3125,
1343
+ "learning_rate": 6.878113106700946e-07,
1344
+ "loss": 0.007294324040412903,
1345
+ "step": 1660,
1346
+ "token_acc": 0.9973493975903615
1347
+ },
1348
+ {
1349
+ "epoch": 1.7808000000000002,
1350
+ "grad_norm": 0.42578125,
1351
+ "learning_rate": 6.262573389454773e-07,
1352
+ "loss": 0.008933399617671967,
1353
+ "step": 1670,
1354
+ "token_acc": 0.9963741841914431
1355
+ },
1356
+ {
1357
+ "epoch": 1.7914666666666665,
1358
+ "grad_norm": 1.1796875,
1359
+ "learning_rate": 5.674993634313242e-07,
1360
+ "loss": 0.012564325332641601,
1361
+ "step": 1680,
1362
+ "token_acc": 0.9956720365472469
1363
+ },
1364
+ {
1365
+ "epoch": 1.8021333333333334,
1366
+ "grad_norm": 0.5625,
1367
+ "learning_rate": 5.115549104330575e-07,
1368
+ "loss": 0.00787913054227829,
1369
+ "step": 1690,
1370
+ "token_acc": 0.9976082276967233
1371
+ },
1372
+ {
1373
+ "epoch": 1.8128,
1374
+ "grad_norm": 1.1875,
1375
+ "learning_rate": 4.5844066703973676e-07,
1376
+ "loss": 0.007952670753002166,
1377
+ "step": 1700,
1378
+ "token_acc": 0.9973583093179635
1379
+ },
1380
+ {
1381
+ "epoch": 1.8234666666666666,
1382
+ "grad_norm": 1.0546875,
1383
+ "learning_rate": 4.081724761466288e-07,
1384
+ "loss": 0.013583377003669739,
1385
+ "step": 1710,
1386
+ "token_acc": 0.9946898382814385
1387
+ },
1388
+ {
1389
+ "epoch": 1.8341333333333334,
1390
+ "grad_norm": 0.9609375,
1391
+ "learning_rate": 3.6076533172959895e-07,
1392
+ "loss": 0.008094549179077148,
1393
+ "step": 1720,
1394
+ "token_acc": 0.9973519499277804
1395
+ },
1396
+ {
1397
+ "epoch": 1.8448,
1398
+ "grad_norm": 1.3046875,
1399
+ "learning_rate": 3.1623337437272084e-07,
1400
+ "loss": 0.010456332564353943,
1401
+ "step": 1730,
1402
+ "token_acc": 0.9963864129125511
1403
+ },
1404
+ {
1405
+ "epoch": 1.8554666666666666,
1406
+ "grad_norm": 1.375,
1407
+ "learning_rate": 2.745898870504116e-07,
1408
+ "loss": 0.009122979640960694,
1409
+ "step": 1740,
1410
+ "token_acc": 0.9980750721847931
1411
+ },
1412
+ {
1413
+ "epoch": 1.8661333333333334,
1414
+ "grad_norm": 2.0625,
1415
+ "learning_rate": 2.3584729116541305e-07,
1416
+ "loss": 0.010391271114349366,
1417
+ "step": 1750,
1418
+ "token_acc": 0.9958986731001206
1419
+ },
1420
+ {
1421
+ "epoch": 1.8768,
1422
+ "grad_norm": 1.171875,
1423
+ "learning_rate": 2.0001714284372253e-07,
1424
+ "loss": 0.009891322255134583,
1425
+ "step": 1760,
1426
+ "token_acc": 0.9959193470955353
1427
+ },
1428
+ {
1429
+ "epoch": 1.8874666666666666,
1430
+ "grad_norm": 1.359375,
1431
+ "learning_rate": 1.6711012948764426e-07,
1432
+ "loss": 0.010584476590156554,
1433
+ "step": 1770,
1434
+ "token_acc": 0.9956948098541019
1435
+ },
1436
+ {
1437
+ "epoch": 1.8981333333333335,
1438
+ "grad_norm": 2.65625,
1439
+ "learning_rate": 1.371360665879584e-07,
1440
+ "loss": 0.006497502326965332,
1441
+ "step": 1780,
1442
+ "token_acc": 0.9978401727861771
1443
+ },
1444
+ {
1445
+ "epoch": 1.9088,
1446
+ "grad_norm": 1.265625,
1447
+ "learning_rate": 1.1010389479615302e-07,
1448
+ "loss": 0.011741268634796142,
1449
+ "step": 1790,
1450
+ "token_acc": 0.9944698244770378
1451
+ },
1452
+ {
1453
+ "epoch": 1.9194666666666667,
1454
+ "grad_norm": 2.234375,
1455
+ "learning_rate": 8.60216772576139e-08,
1456
+ "loss": 0.010211998224258423,
1457
+ "step": 1800,
1458
+ "token_acc": 0.9961566178236848
1459
+ },
1460
+ {
1461
+ "epoch": 1.9301333333333335,
1462
+ "grad_norm": 1.5546875,
1463
+ "learning_rate": 6.489659720655295e-08,
1464
+ "loss": 0.008484911918640137,
1465
+ "step": 1810,
1466
+ "token_acc": 0.9968712394705175
1467
+ },
1468
+ {
1469
+ "epoch": 1.9407999999999999,
1470
+ "grad_norm": 2.0,
1471
+ "learning_rate": 4.673495582339649e-08,
1472
+ "loss": 0.011189290881156921,
1473
+ "step": 1820,
1474
+ "token_acc": 0.9954050785973397
1475
+ },
1476
+ {
1477
+ "epoch": 1.9514666666666667,
1478
+ "grad_norm": 1.5,
1479
+ "learning_rate": 3.154217035526874e-08,
1480
+ "loss": 0.012943205237388612,
1481
+ "step": 1830,
1482
+ "token_acc": 0.9949604031677466
1483
+ },
1484
+ {
1485
+ "epoch": 1.9621333333333333,
1486
+ "grad_norm": 2.078125,
1487
+ "learning_rate": 1.932277250014214e-08,
1488
+ "loss": 0.014319291710853577,
1489
+ "step": 1840,
1490
+ "token_acc": 0.9944883776659478
1491
+ },
1492
+ {
1493
+ "epoch": 1.9727999999999999,
1494
+ "grad_norm": 1.1640625,
1495
+ "learning_rate": 1.008040705511748e-08,
1496
+ "loss": 0.0120982825756073,
1497
+ "step": 1850,
1498
+ "token_acc": 0.9949016751638747
1499
+ },
1500
+ {
1501
+ "epoch": 1.9834666666666667,
1502
+ "grad_norm": 1.4609375,
1503
+ "learning_rate": 3.8178308292624585e-09,
1504
+ "loss": 0.00735490694642067,
1505
+ "step": 1860,
1506
+ "token_acc": 0.997832891885384
1507
+ },
1508
+ {
1509
+ "epoch": 1.9941333333333333,
1510
+ "grad_norm": 1.859375,
1511
+ "learning_rate": 5.369118213094382e-10,
1512
+ "loss": 0.009274058043956757,
1513
+ "step": 1870,
1514
+ "token_acc": 0.9959075589792971
1515
+ }
1516
+ ],
1517
+ "logging_steps": 10,
1518
+ "max_steps": 1876,
1519
+ "num_input_tokens_seen": 0,
1520
+ "num_train_epochs": 2,
1521
+ "save_steps": 500,
1522
+ "stateful_callbacks": {
1523
+ "TrainerControl": {
1524
+ "args": {
1525
+ "should_epoch_stop": false,
1526
+ "should_evaluate": false,
1527
+ "should_log": false,
1528
+ "should_save": true,
1529
+ "should_training_stop": true
1530
+ },
1531
+ "attributes": {}
1532
+ }
1533
+ },
1534
+ "total_flos": 7.528224876952289e+17,
1535
+ "train_batch_size": 8,
1536
+ "trial_name": null,
1537
+ "trial_params": null
1538
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804fca9f77655d0b37aef816a7c0bd6c39a6554afb15a7051564e2b54b0386e9
3
+ size 6993
vocab.json ADDED
The diff for this file is too large to render. See raw diff