FutureMa commited on
Commit
d71de19
·
verified ·
1 Parent(s): 42418b3

Upload Qwen3-4B-Code-Analyzer-Step2000 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 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215",
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": 2,
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": 4,
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": 1.0,
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/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215/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": 32,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/home/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": null,
84
+ "label_smoothing_factor": 0.0,
85
+ "optim": "adamw_torch_fused",
86
+ "optim_args": null,
87
+ "adafactor": false,
88
+ "group_by_length": false,
89
+ "length_column_name": "length",
90
+ "report_to": [
91
+ "tensorboard"
92
+ ],
93
+ "project": "huggingface",
94
+ "trackio_space_id": "trackio",
95
+ "ddp_find_unused_parameters": null,
96
+ "ddp_bucket_cap_mb": null,
97
+ "ddp_broadcast_buffers": null,
98
+ "dataloader_pin_memory": true,
99
+ "dataloader_persistent_workers": false,
100
+ "skip_memory_metrics": true,
101
+ "use_legacy_prediction_loop": false,
102
+ "push_to_hub": false,
103
+ "resume_from_checkpoint": null,
104
+ "hub_model_id": null,
105
+ "hub_strategy": "every_save",
106
+ "hub_token": null,
107
+ "hub_private_repo": null,
108
+ "hub_always_push": false,
109
+ "hub_revision": null,
110
+ "gradient_checkpointing": true,
111
+ "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
112
+ "include_inputs_for_metrics": false,
113
+ "include_for_metrics": [],
114
+ "eval_do_concat_batches": true,
115
+ "fp16_backend": "auto",
116
+ "push_to_hub_model_id": null,
117
+ "push_to_hub_organization": null,
118
+ "push_to_hub_token": null,
119
+ "mp_parameters": "",
120
+ "auto_find_batch_size": false,
121
+ "full_determinism": false,
122
+ "torchdynamo": null,
123
+ "ray_scope": "last",
124
+ "ddp_timeout": 18000000,
125
+ "torch_compile": false,
126
+ "torch_compile_backend": null,
127
+ "torch_compile_mode": null,
128
+ "include_tokens_per_second": false,
129
+ "include_num_input_tokens_seen": false,
130
+ "neftune_noise_alpha": null,
131
+ "optim_target_modules": null,
132
+ "batch_eval_metrics": false,
133
+ "eval_on_start": false,
134
+ "use_liger_kernel": false,
135
+ "liger_kernel_config": null,
136
+ "eval_use_gather_object": false,
137
+ "average_tokens_across_devices": true,
138
+ "sortish_sampler": false,
139
+ "predict_with_generate": false,
140
+ "generation_max_length": null,
141
+ "generation_num_beams": null,
142
+ "generation_config": null,
143
+ "tuner_backend": "peft",
144
+ "vit_gradient_checkpointing": null,
145
+ "router_aux_loss_coef": 0.0,
146
+ "enable_dft_loss": false,
147
+ "enable_channel_loss": false,
148
+ "check_model": true,
149
+ "acc_strategy": "token",
150
+ "train_dataloader_shuffle": true,
151
+ "max_epochs": null,
152
+ "aligner_lr": null,
153
+ "vit_lr": null,
154
+ "use_logits_to_keep": null,
155
+ "ds3_gather_for_generation": true,
156
+ "resume_only_model": false,
157
+ "optimizer": null,
158
+ "loss_type": null,
159
+ "eval_metric": null,
160
+ "callbacks": [],
161
+ "early_stop_interval": null,
162
+ "eval_use_evalscope": false,
163
+ "eval_dataset": [],
164
+ "eval_dataset_args": null,
165
+ "eval_limit": null,
166
+ "eval_generation_config": null,
167
+ "extra_eval_args": null,
168
+ "tuner_type": "full",
169
+ "use_galore": false,
170
+ "galore_target_modules": null,
171
+ "galore_rank": 128,
172
+ "galore_update_proj_gap": 50,
173
+ "galore_scale": 1.0,
174
+ "galore_proj_type": "std",
175
+ "galore_optim_per_parameter": false,
176
+ "galore_with_embedding": false,
177
+ "galore_quantization": false,
178
+ "galore_proj_quant": false,
179
+ "galore_proj_bits": 4,
180
+ "galore_proj_group_size": 256,
181
+ "galore_cos_threshold": 0.4,
182
+ "galore_gamma_proj": 2,
183
+ "galore_queue_size": 5,
184
+ "lisa_activated_layers": 0,
185
+ "lisa_step_interval": 20,
186
+ "use_flash_ckpt": false,
187
+ "use_ray": false,
188
+ "ray_exp_name": null,
189
+ "device_groups": null,
190
+ "model": "Qwen/Qwen3-4B-Instruct-2507",
191
+ "model_type": "qwen3",
192
+ "model_revision": null,
193
+ "task_type": "causal_lm",
194
+ "torch_dtype": "bfloat16",
195
+ "attn_impl": null,
196
+ "experts_impl": null,
197
+ "new_special_tokens": [],
198
+ "num_labels": null,
199
+ "problem_type": null,
200
+ "rope_scaling": null,
201
+ "device_map": null,
202
+ "max_memory": {},
203
+ "max_model_len": null,
204
+ "local_repo_path": null,
205
+ "init_strategy": null,
206
+ "template": "qwen3_nothinking",
207
+ "system": null,
208
+ "max_length": 16384,
209
+ "truncation_strategy": "delete",
210
+ "max_pixels": null,
211
+ "agent_template": null,
212
+ "norm_bbox": null,
213
+ "use_chat_template": true,
214
+ "padding_side": "right",
215
+ "padding_free": false,
216
+ "loss_scale": "default",
217
+ "sequence_parallel_size": 1,
218
+ "template_backend": "swift",
219
+ "response_prefix": null,
220
+ "enable_thinking": null,
221
+ "add_non_thinking_prefix": true,
222
+ "dataset": [
223
+ "/home/shadeform/ms-swift/data/cc/msswift-codebase-projects-train.jsonl"
224
+ ],
225
+ "val_dataset": [],
226
+ "cached_dataset": [],
227
+ "cached_val_dataset": [],
228
+ "split_dataset_ratio": 0.0,
229
+ "dataset_num_proc": 64,
230
+ "load_from_cache_file": false,
231
+ "dataset_shuffle": true,
232
+ "val_dataset_shuffle": false,
233
+ "streaming": false,
234
+ "interleave_prob": null,
235
+ "stopping_strategy": "first_exhausted",
236
+ "shuffle_buffer_size": 1000,
237
+ "download_mode": "reuse_dataset_if_exists",
238
+ "columns": {},
239
+ "strict": false,
240
+ "model_name": null,
241
+ "model_author": null,
242
+ "custom_dataset_info": [],
243
+ "quant_method": null,
244
+ "quant_bits": null,
245
+ "hqq_axis": null,
246
+ "bnb_4bit_compute_dtype": "bfloat16",
247
+ "bnb_4bit_quant_type": "nf4",
248
+ "bnb_4bit_use_double_quant": true,
249
+ "bnb_4bit_quant_storage": null,
250
+ "max_new_tokens": 64,
251
+ "temperature": 0.0,
252
+ "top_k": null,
253
+ "top_p": null,
254
+ "repetition_penalty": null,
255
+ "num_beams": 1,
256
+ "stream": false,
257
+ "stop_words": [],
258
+ "logprobs": false,
259
+ "top_logprobs": null,
260
+ "structured_outputs_regex": null,
261
+ "train_type": null,
262
+ "adapters": [],
263
+ "external_plugins": [],
264
+ "custom_register_path": [],
265
+ "model_kwargs": {},
266
+ "load_args": false,
267
+ "load_data_args": false,
268
+ "packing": false,
269
+ "packing_length": null,
270
+ "packing_num_proc": 1,
271
+ "lazy_tokenize": false,
272
+ "use_hf": true,
273
+ "ignore_args_error": false,
274
+ "use_swift_lora": false,
275
+ "freeze_parameters": [],
276
+ "freeze_parameters_regex": null,
277
+ "freeze_parameters_ratio": 0.0,
278
+ "trainable_parameters": [],
279
+ "trainable_parameters_regex": null,
280
+ "freeze_llm": false,
281
+ "freeze_vit": true,
282
+ "freeze_aligner": true,
283
+ "target_modules": [
284
+ "all-linear"
285
+ ],
286
+ "target_regex": null,
287
+ "target_parameters": null,
288
+ "modules_to_save": [],
289
+ "lora_rank": 8,
290
+ "lora_alpha": 32,
291
+ "lora_dropout": 0.05,
292
+ "lora_bias": "none",
293
+ "lora_dtype": null,
294
+ "lorap_lr_ratio": null,
295
+ "use_rslora": false,
296
+ "use_dora": false,
297
+ "lora_ga_batch_size": 2,
298
+ "lora_ga_iters": 2,
299
+ "lora_ga_max_length": 1024,
300
+ "lora_ga_direction": "ArB2r",
301
+ "lora_ga_scale": "stable",
302
+ "lora_ga_stable_gamma": 16,
303
+ "init_weights": true,
304
+ "fourier_n_frequency": 2000,
305
+ "fourier_scaling": 300.0,
306
+ "boft_block_size": 4,
307
+ "boft_block_num": 0,
308
+ "boft_n_butterfly_factor": 1,
309
+ "boft_dropout": 0.0,
310
+ "vera_rank": 256,
311
+ "vera_projection_prng_key": 0,
312
+ "vera_dropout": 0.0,
313
+ "vera_d_initial": 0.1,
314
+ "adapter_act": "gelu",
315
+ "adapter_length": 128,
316
+ "adalora_target_r": 8,
317
+ "adalora_init_r": 12,
318
+ "adalora_tinit": 0,
319
+ "adalora_tfinal": 0,
320
+ "adalora_deltaT": 1,
321
+ "adalora_beta1": 0.85,
322
+ "adalora_beta2": 0.85,
323
+ "adalora_orth_reg_weight": 0.5,
324
+ "llamapro_num_new_blocks": 4,
325
+ "llamapro_num_groups": null,
326
+ "reft_layer_key": null,
327
+ "reft_layers": null,
328
+ "reft_rank": 4,
329
+ "reft_intervention_type": "LoreftIntervention",
330
+ "reft_args": null,
331
+ "swanlab_token": null,
332
+ "swanlab_project": "ms-swift",
333
+ "swanlab_workspace": null,
334
+ "swanlab_exp_name": null,
335
+ "swanlab_notification_method": null,
336
+ "swanlab_webhook_url": null,
337
+ "swanlab_secret": null,
338
+ "swanlab_sender_email": null,
339
+ "swanlab_receiver_email": null,
340
+ "swanlab_smtp_server": null,
341
+ "swanlab_smtp_port": null,
342
+ "swanlab_email_language": "zh",
343
+ "swanlab_mode": "cloud",
344
+ "add_version": true,
345
+ "create_checkpoint_symlink": false,
346
+ "zero_hpz_partition_size": null,
347
+ "deepspeed_autotp_size": null,
348
+ "swift_version": "4.0.0.dev0",
349
+ "ckpt_dir": null,
350
+ "rank": 0,
351
+ "global_world_size": 4,
352
+ "local_world_size": 4,
353
+ "model_suffix": "Qwen3-4B-Instruct-2507",
354
+ "model_info": "ModelInfo(model_type='qwen3', model_dir='/home/shadeform/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554', 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)",
355
+ "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='qwen3_nothinking', 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=[])",
356
+ "model_dir": "/home/shadeform/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
357
+ "template_meta": "QwenTemplateMeta(template_type='qwen3_nothinking', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.base.Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
358
+ "_val_dataset_exists": false,
359
+ "hub": "<class 'swift.hub.hub.HFHub'>",
360
+ "evaluation_strategy": "steps",
361
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215', 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=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, 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=1.0, 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/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215/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=32, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/shadeform/ms-swift/output/qwen3-4b-codebase-4xh200/v12-20260218-070215', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
362
+ }
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": "4.57.0",
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": "4.57.0"
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:f6b746cd08b9691da351af44e03cd5e83289f992ec7d5912a572b203830052a8
3
+ size 4967215360
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61830f45a634961994dc25ae744e29360a675a06633d564b84319fcf0430b0ed
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:f1a2e668047a797a7925b168124e3c17a6ee306923d08da00ae060e00a778e00
3
+ size 16090225449
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dab20227f2e733fb86e5fea2c37af9a6c1ce0d589c390c85ef5c734f1323c6c
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 +1,1642 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.79247152055473,
6
+ "eval_steps": 500.0,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00039623576027736503,
14
+ "grad_norm": 23.5,
15
+ "learning_rate": 2.6315789473684213e-07,
16
+ "loss": 1.1837007999420166,
17
+ "step": 1,
18
+ "token_acc": 0.8159329621764334
19
+ },
20
+ {
21
+ "epoch": 0.00396235760277365,
22
+ "grad_norm": 21.375,
23
+ "learning_rate": 2.631578947368421e-06,
24
+ "loss": 1.123257319132487,
25
+ "step": 10,
26
+ "token_acc": 0.8210087927828165
27
+ },
28
+ {
29
+ "epoch": 0.0079247152055473,
30
+ "grad_norm": 7.09375,
31
+ "learning_rate": 5.263157894736842e-06,
32
+ "loss": 0.9101140975952149,
33
+ "step": 20,
34
+ "token_acc": 0.8285831313786395
35
+ },
36
+ {
37
+ "epoch": 0.01188707280832095,
38
+ "grad_norm": 2.8125,
39
+ "learning_rate": 7.894736842105265e-06,
40
+ "loss": 0.5795128822326661,
41
+ "step": 30,
42
+ "token_acc": 0.8505745886743207
43
+ },
44
+ {
45
+ "epoch": 0.0158494304110946,
46
+ "grad_norm": 1.7578125,
47
+ "learning_rate": 1.0526315789473684e-05,
48
+ "loss": 0.42301692962646487,
49
+ "step": 40,
50
+ "token_acc": 0.8767900103104593
51
+ },
52
+ {
53
+ "epoch": 0.01981178801386825,
54
+ "grad_norm": 1.4921875,
55
+ "learning_rate": 1.3157894736842108e-05,
56
+ "loss": 0.35302650928497314,
57
+ "step": 50,
58
+ "token_acc": 0.8897820845537251
59
+ },
60
+ {
61
+ "epoch": 0.0237741456166419,
62
+ "grad_norm": 1.375,
63
+ "learning_rate": 1.578947368421053e-05,
64
+ "loss": 0.33079302310943604,
65
+ "step": 60,
66
+ "token_acc": 0.8967102736745091
67
+ },
68
+ {
69
+ "epoch": 0.02773650321941555,
70
+ "grad_norm": 1.25,
71
+ "learning_rate": 1.8421052631578947e-05,
72
+ "loss": 0.31292335987091063,
73
+ "step": 70,
74
+ "token_acc": 0.9010626512129326
75
+ },
76
+ {
77
+ "epoch": 0.0316988608221892,
78
+ "grad_norm": 1.109375,
79
+ "learning_rate": 1.999986824534997e-05,
80
+ "loss": 0.3141467094421387,
81
+ "step": 80,
82
+ "token_acc": 0.9005368650633087
83
+ },
84
+ {
85
+ "epoch": 0.03566121842496285,
86
+ "grad_norm": 1.296875,
87
+ "learning_rate": 1.9998386045408938e-05,
88
+ "loss": 0.29496400356292723,
89
+ "step": 90,
90
+ "token_acc": 0.9055861965123218
91
+ },
92
+ {
93
+ "epoch": 0.0396235760277365,
94
+ "grad_norm": 1.28125,
95
+ "learning_rate": 1.999525719713366e-05,
96
+ "loss": 0.2913074970245361,
97
+ "step": 100,
98
+ "token_acc": 0.9076149509114921
99
+ },
100
+ {
101
+ "epoch": 0.04358593363051015,
102
+ "grad_norm": 1.6015625,
103
+ "learning_rate": 1.999048221581858e-05,
104
+ "loss": 0.2880474805831909,
105
+ "step": 110,
106
+ "token_acc": 0.9073922051522615
107
+ },
108
+ {
109
+ "epoch": 0.0475482912332838,
110
+ "grad_norm": 1.390625,
111
+ "learning_rate": 1.9984061887862118e-05,
112
+ "loss": 0.27746291160583497,
113
+ "step": 120,
114
+ "token_acc": 0.9101783276777932
115
+ },
116
+ {
117
+ "epoch": 0.05151064883605745,
118
+ "grad_norm": 1.171875,
119
+ "learning_rate": 1.9975997270637172e-05,
120
+ "loss": 0.273817777633667,
121
+ "step": 130,
122
+ "token_acc": 0.909736600422787
123
+ },
124
+ {
125
+ "epoch": 0.0554730064388311,
126
+ "grad_norm": 1.2578125,
127
+ "learning_rate": 1.9966289692316944e-05,
128
+ "loss": 0.2767889976501465,
129
+ "step": 140,
130
+ "token_acc": 0.9082912026144594
131
+ },
132
+ {
133
+ "epoch": 0.05943536404160475,
134
+ "grad_norm": 1.4921875,
135
+ "learning_rate": 1.9954940751656245e-05,
136
+ "loss": 0.27089781761169435,
137
+ "step": 150,
138
+ "token_acc": 0.9099060425408418
139
+ },
140
+ {
141
+ "epoch": 0.0633977216443784,
142
+ "grad_norm": 1.171875,
143
+ "learning_rate": 1.994195231772815e-05,
144
+ "loss": 0.25421991348266604,
145
+ "step": 160,
146
+ "token_acc": 0.9162766481231006
147
+ },
148
+ {
149
+ "epoch": 0.06736007924715205,
150
+ "grad_norm": 1.359375,
151
+ "learning_rate": 1.9927326529616203e-05,
152
+ "loss": 0.2611961841583252,
153
+ "step": 170,
154
+ "token_acc": 0.9147679722152482
155
+ },
156
+ {
157
+ "epoch": 0.0713224368499257,
158
+ "grad_norm": 1.4296875,
159
+ "learning_rate": 1.9911065796062137e-05,
160
+ "loss": 0.264358377456665,
161
+ "step": 180,
162
+ "token_acc": 0.9137104702605277
163
+ },
164
+ {
165
+ "epoch": 0.07528479445269935,
166
+ "grad_norm": 1.2265625,
167
+ "learning_rate": 1.9893172795069144e-05,
168
+ "loss": 0.27645695209503174,
169
+ "step": 190,
170
+ "token_acc": 0.9085774438661551
171
+ },
172
+ {
173
+ "epoch": 0.079247152055473,
174
+ "grad_norm": 1.3125,
175
+ "learning_rate": 1.9873650473460862e-05,
176
+ "loss": 0.2564415693283081,
177
+ "step": 200,
178
+ "token_acc": 0.9148068228524455
179
+ },
180
+ {
181
+ "epoch": 0.08320950965824665,
182
+ "grad_norm": 1.2265625,
183
+ "learning_rate": 1.9852502046396035e-05,
184
+ "loss": 0.2584503650665283,
185
+ "step": 210,
186
+ "token_acc": 0.9148747112137906
187
+ },
188
+ {
189
+ "epoch": 0.0871718672610203,
190
+ "grad_norm": 1.1171875,
191
+ "learning_rate": 1.982973099683902e-05,
192
+ "loss": 0.25623598098754885,
193
+ "step": 220,
194
+ "token_acc": 0.916684382955295
195
+ },
196
+ {
197
+ "epoch": 0.09113422486379395,
198
+ "grad_norm": 1.4296875,
199
+ "learning_rate": 1.980534107498616e-05,
200
+ "loss": 0.2456662178039551,
201
+ "step": 230,
202
+ "token_acc": 0.9188118082346068
203
+ },
204
+ {
205
+ "epoch": 0.0950965824665676,
206
+ "grad_norm": 1.4609375,
207
+ "learning_rate": 1.977933629764817e-05,
208
+ "loss": 0.2530802249908447,
209
+ "step": 240,
210
+ "token_acc": 0.9152495545682131
211
+ },
212
+ {
213
+ "epoch": 0.09905894006934125,
214
+ "grad_norm": 1.3203125,
215
+ "learning_rate": 1.9751720947588603e-05,
216
+ "loss": 0.24223690032958983,
217
+ "step": 250,
218
+ "token_acc": 0.9186887231706855
219
+ },
220
+ {
221
+ "epoch": 0.1030212976721149,
222
+ "grad_norm": 1.21875,
223
+ "learning_rate": 1.9722499572818496e-05,
224
+ "loss": 0.23485193252563477,
225
+ "step": 260,
226
+ "token_acc": 0.9216265054055996
227
+ },
228
+ {
229
+ "epoch": 0.10698365527488855,
230
+ "grad_norm": 1.5,
231
+ "learning_rate": 1.969167698584738e-05,
232
+ "loss": 0.24744803905487062,
233
+ "step": 270,
234
+ "token_acc": 0.9177383756974582
235
+ },
236
+ {
237
+ "epoch": 0.1109460128776622,
238
+ "grad_norm": 1.234375,
239
+ "learning_rate": 1.9659258262890683e-05,
240
+ "loss": 0.25014376640319824,
241
+ "step": 280,
242
+ "token_acc": 0.9170167948905685
243
+ },
244
+ {
245
+ "epoch": 0.11490837048043585,
246
+ "grad_norm": 1.5078125,
247
+ "learning_rate": 1.9625248743033725e-05,
248
+ "loss": 0.23340215682983398,
249
+ "step": 290,
250
+ "token_acc": 0.9214856049225197
251
+ },
252
+ {
253
+ "epoch": 0.1188707280832095,
254
+ "grad_norm": 1.171875,
255
+ "learning_rate": 1.9589654027352412e-05,
256
+ "loss": 0.24289028644561766,
257
+ "step": 300,
258
+ "token_acc": 0.9185406963850078
259
+ },
260
+ {
261
+ "epoch": 0.12283308568598315,
262
+ "grad_norm": 1.0625,
263
+ "learning_rate": 1.9552479977990802e-05,
264
+ "loss": 0.24520406723022461,
265
+ "step": 310,
266
+ "token_acc": 0.9184403422069023
267
+ },
268
+ {
269
+ "epoch": 0.1267954432887568,
270
+ "grad_norm": 1.359375,
271
+ "learning_rate": 1.9513732717195638e-05,
272
+ "loss": 0.2427917242050171,
273
+ "step": 320,
274
+ "token_acc": 0.9178514285714285
275
+ },
276
+ {
277
+ "epoch": 0.13075780089153047,
278
+ "grad_norm": 0.9609375,
279
+ "learning_rate": 1.9473418626308086e-05,
280
+ "loss": 0.21972455978393554,
281
+ "step": 330,
282
+ "token_acc": 0.9259012550960103
283
+ },
284
+ {
285
+ "epoch": 0.1347201584943041,
286
+ "grad_norm": 1.3984375,
287
+ "learning_rate": 1.9431544344712776e-05,
288
+ "loss": 0.2463603973388672,
289
+ "step": 340,
290
+ "token_acc": 0.9171354320865818
291
+ },
292
+ {
293
+ "epoch": 0.13868251609707777,
294
+ "grad_norm": 1.25,
295
+ "learning_rate": 1.9388116768744344e-05,
296
+ "loss": 0.23121447563171388,
297
+ "step": 350,
298
+ "token_acc": 0.9208610209876757
299
+ },
300
+ {
301
+ "epoch": 0.1426448736998514,
302
+ "grad_norm": 1.0546875,
303
+ "learning_rate": 1.9343143050551684e-05,
304
+ "loss": 0.2372572898864746,
305
+ "step": 360,
306
+ "token_acc": 0.9205740491816241
307
+ },
308
+ {
309
+ "epoch": 0.14660723130262507,
310
+ "grad_norm": 1.6328125,
311
+ "learning_rate": 1.929663059692002e-05,
312
+ "loss": 0.23370888233184814,
313
+ "step": 370,
314
+ "token_acc": 0.9218769547078884
315
+ },
316
+ {
317
+ "epoch": 0.1505695889053987,
318
+ "grad_norm": 1.3515625,
319
+ "learning_rate": 1.924858706805112e-05,
320
+ "loss": 0.22563014030456544,
321
+ "step": 380,
322
+ "token_acc": 0.9239206109486627
323
+ },
324
+ {
325
+ "epoch": 0.15453194650817237,
326
+ "grad_norm": 1.2890625,
327
+ "learning_rate": 1.9199020376301666e-05,
328
+ "loss": 0.22754812240600586,
329
+ "step": 390,
330
+ "token_acc": 0.923770752222635
331
+ },
332
+ {
333
+ "epoch": 0.158494304110946,
334
+ "grad_norm": 1.2109375,
335
+ "learning_rate": 1.9147938684880213e-05,
336
+ "loss": 0.233451247215271,
337
+ "step": 400,
338
+ "token_acc": 0.9208578517882449
339
+ },
340
+ {
341
+ "epoch": 0.16245666171371967,
342
+ "grad_norm": 1.359375,
343
+ "learning_rate": 1.9095350406502736e-05,
344
+ "loss": 0.22117164134979247,
345
+ "step": 410,
346
+ "token_acc": 0.9251948698253339
347
+ },
348
+ {
349
+ "epoch": 0.1664190193164933,
350
+ "grad_norm": 1.265625,
351
+ "learning_rate": 1.9041264202007158e-05,
352
+ "loss": 0.23051214218139648,
353
+ "step": 420,
354
+ "token_acc": 0.9227009356565836
355
+ },
356
+ {
357
+ "epoch": 0.17038137691926697,
358
+ "grad_norm": 1.296875,
359
+ "learning_rate": 1.8985688978926972e-05,
360
+ "loss": 0.22384767532348632,
361
+ "step": 430,
362
+ "token_acc": 0.9254292644524351
363
+ },
364
+ {
365
+ "epoch": 0.1743437345220406,
366
+ "grad_norm": 0.96484375,
367
+ "learning_rate": 1.892863389002424e-05,
368
+ "loss": 0.22796776294708251,
369
+ "step": 440,
370
+ "token_acc": 0.9236655948553054
371
+ },
372
+ {
373
+ "epoch": 0.17830609212481427,
374
+ "grad_norm": 1.1015625,
375
+ "learning_rate": 1.887010833178222e-05,
376
+ "loss": 0.2255650520324707,
377
+ "step": 450,
378
+ "token_acc": 0.9233627684120709
379
+ },
380
+ {
381
+ "epoch": 0.1822684497275879,
382
+ "grad_norm": 1.3828125,
383
+ "learning_rate": 1.8810121942857848e-05,
384
+ "loss": 0.21253745555877684,
385
+ "step": 460,
386
+ "token_acc": 0.9272634714542769
387
+ },
388
+ {
389
+ "epoch": 0.18623080733036157,
390
+ "grad_norm": 1.171875,
391
+ "learning_rate": 1.8748684602494327e-05,
392
+ "loss": 0.22184033393859864,
393
+ "step": 470,
394
+ "token_acc": 0.9256473357586134
395
+ },
396
+ {
397
+ "epoch": 0.1901931649331352,
398
+ "grad_norm": 1.046875,
399
+ "learning_rate": 1.8685806428894113e-05,
400
+ "loss": 0.2163544178009033,
401
+ "step": 480,
402
+ "token_acc": 0.92641120988206
403
+ },
404
+ {
405
+ "epoch": 0.19415552253590887,
406
+ "grad_norm": 1.234375,
407
+ "learning_rate": 1.8621497777552508e-05,
408
+ "loss": 0.2326265335083008,
409
+ "step": 490,
410
+ "token_acc": 0.9219484631704639
411
+ },
412
+ {
413
+ "epoch": 0.1981178801386825,
414
+ "grad_norm": 1.1328125,
415
+ "learning_rate": 1.8555769239552232e-05,
416
+ "loss": 0.21914072036743165,
417
+ "step": 500,
418
+ "token_acc": 0.9266210447862321
419
+ },
420
+ {
421
+ "epoch": 0.20208023774145617,
422
+ "grad_norm": 1.546875,
423
+ "learning_rate": 1.848863163981914e-05,
424
+ "loss": 0.22959327697753906,
425
+ "step": 510,
426
+ "token_acc": 0.9215090641842234
427
+ },
428
+ {
429
+ "epoch": 0.2060425953442298,
430
+ "grad_norm": 1.109375,
431
+ "learning_rate": 1.8420096035339454e-05,
432
+ "loss": 0.21052975654602052,
433
+ "step": 520,
434
+ "token_acc": 0.9286930380232219
435
+ },
436
+ {
437
+ "epoch": 0.21000495294700347,
438
+ "grad_norm": 1.0703125,
439
+ "learning_rate": 1.8350173713338777e-05,
440
+ "loss": 0.22955830097198487,
441
+ "step": 530,
442
+ "token_acc": 0.9225931053342221
443
+ },
444
+ {
445
+ "epoch": 0.2139673105497771,
446
+ "grad_norm": 1.2890625,
447
+ "learning_rate": 1.827887618942318e-05,
448
+ "loss": 0.21942346096038817,
449
+ "step": 540,
450
+ "token_acc": 0.9257000477242205
451
+ },
452
+ {
453
+ "epoch": 0.21792966815255077,
454
+ "grad_norm": 1.234375,
455
+ "learning_rate": 1.8206215205682683e-05,
456
+ "loss": 0.21607930660247804,
457
+ "step": 550,
458
+ "token_acc": 0.9265396164644921
459
+ },
460
+ {
461
+ "epoch": 0.2218920257553244,
462
+ "grad_norm": 1.359375,
463
+ "learning_rate": 1.8132202728757428e-05,
464
+ "loss": 0.21843266487121582,
465
+ "step": 560,
466
+ "token_acc": 0.9258849850056328
467
+ },
468
+ {
469
+ "epoch": 0.22585438335809807,
470
+ "grad_norm": 1.3671875,
471
+ "learning_rate": 1.805685094786689e-05,
472
+ "loss": 0.21874871253967285,
473
+ "step": 570,
474
+ "token_acc": 0.9250736338016231
475
+ },
476
+ {
477
+ "epoch": 0.2298167409608717,
478
+ "grad_norm": 1.1640625,
479
+ "learning_rate": 1.7980172272802398e-05,
480
+ "loss": 0.22817540168762207,
481
+ "step": 580,
482
+ "token_acc": 0.9221536778365731
483
+ },
484
+ {
485
+ "epoch": 0.23377909856364537,
486
+ "grad_norm": 1.3671875,
487
+ "learning_rate": 1.790217933188336e-05,
488
+ "loss": 0.20628876686096193,
489
+ "step": 590,
490
+ "token_acc": 0.9291559217209775
491
+ },
492
+ {
493
+ "epoch": 0.237741456166419,
494
+ "grad_norm": 1.2265625,
495
+ "learning_rate": 1.7822884969877493e-05,
496
+ "loss": 0.22458946704864502,
497
+ "step": 600,
498
+ "token_acc": 0.9231406464867372
499
+ },
500
+ {
501
+ "epoch": 0.24170381376919267,
502
+ "grad_norm": 1.3046875,
503
+ "learning_rate": 1.7742302245885384e-05,
504
+ "loss": 0.20527830123901367,
505
+ "step": 610,
506
+ "token_acc": 0.9306424304540271
507
+ },
508
+ {
509
+ "epoch": 0.2456661713719663,
510
+ "grad_norm": 1.1171875,
511
+ "learning_rate": 1.766044443118978e-05,
512
+ "loss": 0.2055346965789795,
513
+ "step": 620,
514
+ "token_acc": 0.9294153185205075
515
+ },
516
+ {
517
+ "epoch": 0.24962852897473997,
518
+ "grad_norm": 1.1640625,
519
+ "learning_rate": 1.7577325007069927e-05,
520
+ "loss": 0.21000022888183595,
521
+ "step": 630,
522
+ "token_acc": 0.9276756514760238
523
+ },
524
+ {
525
+ "epoch": 0.2535908865775136,
526
+ "grad_norm": 1.2265625,
527
+ "learning_rate": 1.7492957662581297e-05,
528
+ "loss": 0.20726590156555175,
529
+ "step": 640,
530
+ "token_acc": 0.9288681287625508
531
+ },
532
+ {
533
+ "epoch": 0.25755324418028724,
534
+ "grad_norm": 1.1328125,
535
+ "learning_rate": 1.7407356292301134e-05,
536
+ "loss": 0.20893335342407227,
537
+ "step": 650,
538
+ "token_acc": 0.9287459199802928
539
+ },
540
+ {
541
+ "epoch": 0.26151560178306094,
542
+ "grad_norm": 1.46875,
543
+ "learning_rate": 1.7320534994040148e-05,
544
+ "loss": 0.2122333526611328,
545
+ "step": 660,
546
+ "token_acc": 0.9268251113697004
547
+ },
548
+ {
549
+ "epoch": 0.26547795938583457,
550
+ "grad_norm": 2.21875,
551
+ "learning_rate": 1.7232508066520702e-05,
552
+ "loss": 0.2119227170944214,
553
+ "step": 670,
554
+ "token_acc": 0.9272324174995067
555
+ },
556
+ {
557
+ "epoch": 0.2694403169886082,
558
+ "grad_norm": 1.2890625,
559
+ "learning_rate": 1.7143290007021942e-05,
560
+ "loss": 0.2144456148147583,
561
+ "step": 680,
562
+ "token_acc": 0.9266572858854115
563
+ },
564
+ {
565
+ "epoch": 0.27340267459138184,
566
+ "grad_norm": 1.3515625,
567
+ "learning_rate": 1.7052895508992236e-05,
568
+ "loss": 0.20908637046813966,
569
+ "step": 690,
570
+ "token_acc": 0.9279253384640653
571
+ },
572
+ {
573
+ "epoch": 0.27736503219415554,
574
+ "grad_norm": 1.2734375,
575
+ "learning_rate": 1.696133945962927e-05,
576
+ "loss": 0.21407780647277833,
577
+ "step": 700,
578
+ "token_acc": 0.9275297697109584
579
+ },
580
+ {
581
+ "epoch": 0.2813273897969292,
582
+ "grad_norm": 1.3984375,
583
+ "learning_rate": 1.6868636937428254e-05,
584
+ "loss": 0.20272161960601806,
585
+ "step": 710,
586
+ "token_acc": 0.9313989228518674
587
+ },
588
+ {
589
+ "epoch": 0.2852897473997028,
590
+ "grad_norm": 1.359375,
591
+ "learning_rate": 1.677480320969865e-05,
592
+ "loss": 0.20830063819885253,
593
+ "step": 720,
594
+ "token_acc": 0.9284670505715276
595
+ },
596
+ {
597
+ "epoch": 0.2892521050024765,
598
+ "grad_norm": 1.3046875,
599
+ "learning_rate": 1.6679853730049743e-05,
600
+ "loss": 0.20571448802947997,
601
+ "step": 730,
602
+ "token_acc": 0.9288137503522119
603
+ },
604
+ {
605
+ "epoch": 0.29321446260525014,
606
+ "grad_norm": 1.4375,
607
+ "learning_rate": 1.6583804135845582e-05,
608
+ "loss": 0.207275128364563,
609
+ "step": 740,
610
+ "token_acc": 0.9295052506473598
611
+ },
612
+ {
613
+ "epoch": 0.2971768202080238,
614
+ "grad_norm": 1.1640625,
615
+ "learning_rate": 1.648667024562963e-05,
616
+ "loss": 0.2059840202331543,
617
+ "step": 750,
618
+ "token_acc": 0.9303702716282313
619
+ },
620
+ {
621
+ "epoch": 0.3011391778107974,
622
+ "grad_norm": 1.4296875,
623
+ "learning_rate": 1.638846805651961e-05,
624
+ "loss": 0.20929555892944335,
625
+ "step": 760,
626
+ "token_acc": 0.9285013576720667
627
+ },
628
+ {
629
+ "epoch": 0.3051015354135711,
630
+ "grad_norm": 1.2265625,
631
+ "learning_rate": 1.62892137415729e-05,
632
+ "loss": 0.2164773464202881,
633
+ "step": 770,
634
+ "token_acc": 0.9268445872201972
635
+ },
636
+ {
637
+ "epoch": 0.30906389301634474,
638
+ "grad_norm": 1.078125,
639
+ "learning_rate": 1.6188923647122946e-05,
640
+ "loss": 0.20146725177764893,
641
+ "step": 780,
642
+ "token_acc": 0.9308608962964089
643
+ },
644
+ {
645
+ "epoch": 0.3130262506191184,
646
+ "grad_norm": 1.1796875,
647
+ "learning_rate": 1.608761429008721e-05,
648
+ "loss": 0.19116392135620117,
649
+ "step": 790,
650
+ "token_acc": 0.9360810066351728
651
+ },
652
+ {
653
+ "epoch": 0.316988608221892,
654
+ "grad_norm": 1.40625,
655
+ "learning_rate": 1.5985302355246932e-05,
656
+ "loss": 0.19471538066864014,
657
+ "step": 800,
658
+ "token_acc": 0.9334035945789697
659
+ },
660
+ {
661
+ "epoch": 0.3209509658246657,
662
+ "grad_norm": 1.3984375,
663
+ "learning_rate": 1.5882004692499324e-05,
664
+ "loss": 0.20449495315551758,
665
+ "step": 810,
666
+ "token_acc": 0.9296946281131374
667
+ },
668
+ {
669
+ "epoch": 0.32491332342743934,
670
+ "grad_norm": 1.4140625,
671
+ "learning_rate": 1.5777738314082514e-05,
672
+ "loss": 0.2058267116546631,
673
+ "step": 820,
674
+ "token_acc": 0.930226312581988
675
+ },
676
+ {
677
+ "epoch": 0.328875681030213,
678
+ "grad_norm": 1.4296875,
679
+ "learning_rate": 1.567252039177378e-05,
680
+ "loss": 0.19794673919677735,
681
+ "step": 830,
682
+ "token_acc": 0.931884692988862
683
+ },
684
+ {
685
+ "epoch": 0.3328380386329866,
686
+ "grad_norm": 1.390625,
687
+ "learning_rate": 1.5566368254061505e-05,
688
+ "loss": 0.20482149124145507,
689
+ "step": 840,
690
+ "token_acc": 0.9305290785274152
691
+ },
692
+ {
693
+ "epoch": 0.3368003962357603,
694
+ "grad_norm": 1.53125,
695
+ "learning_rate": 1.5459299383291347e-05,
696
+ "loss": 0.19639644622802735,
697
+ "step": 850,
698
+ "token_acc": 0.9322417158382036
699
+ },
700
+ {
701
+ "epoch": 0.34076275383853394,
702
+ "grad_norm": 1.4375,
703
+ "learning_rate": 1.5351331412787004e-05,
704
+ "loss": 0.2021495819091797,
705
+ "step": 860,
706
+ "token_acc": 0.9298179216523921
707
+ },
708
+ {
709
+ "epoch": 0.3447251114413076,
710
+ "grad_norm": 1.1875,
711
+ "learning_rate": 1.52424821239462e-05,
712
+ "loss": 0.20063307285308837,
713
+ "step": 870,
714
+ "token_acc": 0.9313979538110527
715
+ },
716
+ {
717
+ "epoch": 0.3486874690440812,
718
+ "grad_norm": 1.6328125,
719
+ "learning_rate": 1.5132769443312207e-05,
720
+ "loss": 0.20427477359771729,
721
+ "step": 880,
722
+ "token_acc": 0.9299313715863092
723
+ },
724
+ {
725
+ "epoch": 0.3526498266468549,
726
+ "grad_norm": 1.4609375,
727
+ "learning_rate": 1.5022211439621521e-05,
728
+ "loss": 0.20063276290893556,
729
+ "step": 890,
730
+ "token_acc": 0.9309864789183134
731
+ },
732
+ {
733
+ "epoch": 0.35661218424962854,
734
+ "grad_norm": 1.328125,
735
+ "learning_rate": 1.4910826320828085e-05,
736
+ "loss": 0.19403212070465087,
737
+ "step": 900,
738
+ "token_acc": 0.9340383217142124
739
+ },
740
+ {
741
+ "epoch": 0.3605745418524022,
742
+ "grad_norm": 1.21875,
743
+ "learning_rate": 1.4798632431104591e-05,
744
+ "loss": 0.1897117853164673,
745
+ "step": 910,
746
+ "token_acc": 0.9360307874252368
747
+ },
748
+ {
749
+ "epoch": 0.3645368994551758,
750
+ "grad_norm": 1.4296875,
751
+ "learning_rate": 1.4685648247821376e-05,
752
+ "loss": 0.19313969612121581,
753
+ "step": 920,
754
+ "token_acc": 0.9329953036961753
755
+ },
756
+ {
757
+ "epoch": 0.3684992570579495,
758
+ "grad_norm": 1.0859375,
759
+ "learning_rate": 1.457189237850332e-05,
760
+ "loss": 0.203882098197937,
761
+ "step": 930,
762
+ "token_acc": 0.9312272344443193
763
+ },
764
+ {
765
+ "epoch": 0.37246161466072314,
766
+ "grad_norm": 0.875,
767
+ "learning_rate": 1.4457383557765385e-05,
768
+ "loss": 0.1886841893196106,
769
+ "step": 940,
770
+ "token_acc": 0.9355444372139664
771
+ },
772
+ {
773
+ "epoch": 0.3764239722634968,
774
+ "grad_norm": 1.359375,
775
+ "learning_rate": 1.4342140644227151e-05,
776
+ "loss": 0.1905367612838745,
777
+ "step": 950,
778
+ "token_acc": 0.9352085303078055
779
+ },
780
+ {
781
+ "epoch": 0.3803863298662704,
782
+ "grad_norm": 1.140625,
783
+ "learning_rate": 1.4226182617406996e-05,
784
+ "loss": 0.19780998229980468,
785
+ "step": 960,
786
+ "token_acc": 0.9324879595849204
787
+ },
788
+ {
789
+ "epoch": 0.3843486874690441,
790
+ "grad_norm": 1.3203125,
791
+ "learning_rate": 1.41095285745963e-05,
792
+ "loss": 0.19177125692367553,
793
+ "step": 970,
794
+ "token_acc": 0.9343932834841926
795
+ },
796
+ {
797
+ "epoch": 0.38831104507181774,
798
+ "grad_norm": 1.7578125,
799
+ "learning_rate": 1.399219772771431e-05,
800
+ "loss": 0.1960275650024414,
801
+ "step": 980,
802
+ "token_acc": 0.9329073312723757
803
+ },
804
+ {
805
+ "epoch": 0.3922734026745914,
806
+ "grad_norm": 1.34375,
807
+ "learning_rate": 1.3874209400144092e-05,
808
+ "loss": 0.18507509231567382,
809
+ "step": 990,
810
+ "token_acc": 0.9359859759133133
811
+ },
812
+ {
813
+ "epoch": 0.396235760277365,
814
+ "grad_norm": 1.2734375,
815
+ "learning_rate": 1.3755583023550128e-05,
816
+ "loss": 0.1876603364944458,
817
+ "step": 1000,
818
+ "token_acc": 0.9350970511384845
819
+ },
820
+ {
821
+ "epoch": 0.4001981178801387,
822
+ "grad_norm": 1.28125,
823
+ "learning_rate": 1.3636338134678104e-05,
824
+ "loss": 0.17850277423858643,
825
+ "step": 1010,
826
+ "token_acc": 0.9377877376733048
827
+ },
828
+ {
829
+ "epoch": 0.40416047548291234,
830
+ "grad_norm": 1.234375,
831
+ "learning_rate": 1.3516494372137368e-05,
832
+ "loss": 0.1958215355873108,
833
+ "step": 1020,
834
+ "token_acc": 0.9318651647470785
835
+ },
836
+ {
837
+ "epoch": 0.408122833085686,
838
+ "grad_norm": 1.6640625,
839
+ "learning_rate": 1.3396071473166614e-05,
840
+ "loss": 0.18602523803710938,
841
+ "step": 1030,
842
+ "token_acc": 0.9359838557500786
843
+ },
844
+ {
845
+ "epoch": 0.4120851906884596,
846
+ "grad_norm": 1.2109375,
847
+ "learning_rate": 1.327508927038334e-05,
848
+ "loss": 0.18929693698883057,
849
+ "step": 1040,
850
+ "token_acc": 0.9350099237438629
851
+ },
852
+ {
853
+ "epoch": 0.4160475482912333,
854
+ "grad_norm": 1.03125,
855
+ "learning_rate": 1.3153567688517567e-05,
856
+ "loss": 0.18981436491012574,
857
+ "step": 1050,
858
+ "token_acc": 0.934143741104814
859
+ },
860
+ {
861
+ "epoch": 0.42000990589400694,
862
+ "grad_norm": 1.3359375,
863
+ "learning_rate": 1.3031526741130435e-05,
864
+ "loss": 0.1816575288772583,
865
+ "step": 1060,
866
+ "token_acc": 0.9370538611291369
867
+ },
868
+ {
869
+ "epoch": 0.4239722634967806,
870
+ "grad_norm": 1.3203125,
871
+ "learning_rate": 1.2908986527318121e-05,
872
+ "loss": 0.19676063060760499,
873
+ "step": 1070,
874
+ "token_acc": 0.932801285003426
875
+ },
876
+ {
877
+ "epoch": 0.4279346210995542,
878
+ "grad_norm": 1.2734375,
879
+ "learning_rate": 1.2785967228401688e-05,
880
+ "loss": 0.19254275560379028,
881
+ "step": 1080,
882
+ "token_acc": 0.9333315147712704
883
+ },
884
+ {
885
+ "epoch": 0.4318969787023279,
886
+ "grad_norm": 1.5078125,
887
+ "learning_rate": 1.266248910460341e-05,
888
+ "loss": 0.18717528581619264,
889
+ "step": 1090,
890
+ "token_acc": 0.9360305301291446
891
+ },
892
+ {
893
+ "epoch": 0.43585933630510154,
894
+ "grad_norm": 1.734375,
895
+ "learning_rate": 1.2538572491710079e-05,
896
+ "loss": 0.1824967622756958,
897
+ "step": 1100,
898
+ "token_acc": 0.9372006812944594
899
+ },
900
+ {
901
+ "epoch": 0.4398216939078752,
902
+ "grad_norm": 1.0078125,
903
+ "learning_rate": 1.2414237797723876e-05,
904
+ "loss": 0.17919249534606935,
905
+ "step": 1110,
906
+ "token_acc": 0.9387596071733562
907
+ },
908
+ {
909
+ "epoch": 0.4437840515106488,
910
+ "grad_norm": 1.296875,
911
+ "learning_rate": 1.2289505499501341e-05,
912
+ "loss": 0.18926095962524414,
913
+ "step": 1120,
914
+ "token_acc": 0.9342525248667318
915
+ },
916
+ {
917
+ "epoch": 0.4477464091134225,
918
+ "grad_norm": 1.28125,
919
+ "learning_rate": 1.2164396139381029e-05,
920
+ "loss": 0.20064361095428468,
921
+ "step": 1130,
922
+ "token_acc": 0.9315847075431296
923
+ },
924
+ {
925
+ "epoch": 0.45170876671619614,
926
+ "grad_norm": 1.484375,
927
+ "learning_rate": 1.2038930321800346e-05,
928
+ "loss": 0.1895804524421692,
929
+ "step": 1140,
930
+ "token_acc": 0.9349271790531848
931
+ },
932
+ {
933
+ "epoch": 0.4556711243189698,
934
+ "grad_norm": 1.5703125,
935
+ "learning_rate": 1.1913128709902182e-05,
936
+ "loss": 0.1807018995285034,
937
+ "step": 1150,
938
+ "token_acc": 0.9369057628872647
939
+ },
940
+ {
941
+ "epoch": 0.4596334819217434,
942
+ "grad_norm": 1.4140625,
943
+ "learning_rate": 1.1787012022131863e-05,
944
+ "loss": 0.1842559814453125,
945
+ "step": 1160,
946
+ "token_acc": 0.9362108645620739
947
+ },
948
+ {
949
+ "epoch": 0.4635958395245171,
950
+ "grad_norm": 1.3203125,
951
+ "learning_rate": 1.1660601028825013e-05,
952
+ "loss": 0.19840482473373414,
953
+ "step": 1170,
954
+ "token_acc": 0.9314812356169233
955
+ },
956
+ {
957
+ "epoch": 0.46755819712729074,
958
+ "grad_norm": 1.046875,
959
+ "learning_rate": 1.1533916548786856e-05,
960
+ "loss": 0.1772662878036499,
961
+ "step": 1180,
962
+ "token_acc": 0.9394712189028833
963
+ },
964
+ {
965
+ "epoch": 0.4715205547300644,
966
+ "grad_norm": 1.2734375,
967
+ "learning_rate": 1.1406979445863515e-05,
968
+ "loss": 0.18831554651260377,
969
+ "step": 1190,
970
+ "token_acc": 0.935608596292791
971
+ },
972
+ {
973
+ "epoch": 0.475482912332838,
974
+ "grad_norm": 1.34375,
975
+ "learning_rate": 1.127981062550595e-05,
976
+ "loss": 0.18489151000976561,
977
+ "step": 1200,
978
+ "token_acc": 0.9360608419277421
979
+ },
980
+ {
981
+ "epoch": 0.4794452699356117,
982
+ "grad_norm": 1.3984375,
983
+ "learning_rate": 1.1152431031326978e-05,
984
+ "loss": 0.17761152982711792,
985
+ "step": 1210,
986
+ "token_acc": 0.9386175400572799
987
+ },
988
+ {
989
+ "epoch": 0.48340762753838534,
990
+ "grad_norm": 3.109375,
991
+ "learning_rate": 1.102486164165207e-05,
992
+ "loss": 0.18663549423217773,
993
+ "step": 1220,
994
+ "token_acc": 0.9355476517845982
995
+ },
996
+ {
997
+ "epoch": 0.487369985141159,
998
+ "grad_norm": 1.25,
999
+ "learning_rate": 1.0897123466064376e-05,
1000
+ "loss": 0.18886669874191284,
1001
+ "step": 1230,
1002
+ "token_acc": 0.9356319723508901
1003
+ },
1004
+ {
1005
+ "epoch": 0.4913323427439326,
1006
+ "grad_norm": 1.34375,
1007
+ "learning_rate": 1.0769237541944639e-05,
1008
+ "loss": 0.18777060508728027,
1009
+ "step": 1240,
1010
+ "token_acc": 0.9354588236528564
1011
+ },
1012
+ {
1013
+ "epoch": 0.4952947003467063,
1014
+ "grad_norm": 1.5,
1015
+ "learning_rate": 1.0641224931006518e-05,
1016
+ "loss": 0.17902556657791138,
1017
+ "step": 1250,
1018
+ "token_acc": 0.9375767442118891
1019
+ },
1020
+ {
1021
+ "epoch": 0.49925705794947994,
1022
+ "grad_norm": 1.15625,
1023
+ "learning_rate": 1.0513106715827897e-05,
1024
+ "loss": 0.18400684595108033,
1025
+ "step": 1260,
1026
+ "token_acc": 0.9370039916704695
1027
+ },
1028
+ {
1029
+ "epoch": 0.5032194155522536,
1030
+ "grad_norm": 1.40625,
1031
+ "learning_rate": 1.0384903996378784e-05,
1032
+ "loss": 0.17728078365325928,
1033
+ "step": 1270,
1034
+ "token_acc": 0.9389623546976645
1035
+ },
1036
+ {
1037
+ "epoch": 0.5071817731550272,
1038
+ "grad_norm": 1.21875,
1039
+ "learning_rate": 1.02566378865463e-05,
1040
+ "loss": 0.18042536973953247,
1041
+ "step": 1280,
1042
+ "token_acc": 0.9374939011828994
1043
+ },
1044
+ {
1045
+ "epoch": 0.5111441307578009,
1046
+ "grad_norm": 1.4609375,
1047
+ "learning_rate": 1.0128329510657426e-05,
1048
+ "loss": 0.18618935346603394,
1049
+ "step": 1290,
1050
+ "token_acc": 0.9355284924654325
1051
+ },
1052
+ {
1053
+ "epoch": 0.5151064883605745,
1054
+ "grad_norm": 1.453125,
1055
+ "learning_rate": 1e-05,
1056
+ "loss": 0.19038233757019044,
1057
+ "step": 1300,
1058
+ "token_acc": 0.9348978046934141
1059
+ },
1060
+ {
1061
+ "epoch": 0.5190688459633482,
1062
+ "grad_norm": 1.921875,
1063
+ "learning_rate": 9.871670489342577e-06,
1064
+ "loss": 0.18166159391403197,
1065
+ "step": 1310,
1066
+ "token_acc": 0.9376118246059261
1067
+ },
1068
+ {
1069
+ "epoch": 0.5230312035661219,
1070
+ "grad_norm": 1.3828125,
1071
+ "learning_rate": 9.743362113453705e-06,
1072
+ "loss": 0.18087191581726075,
1073
+ "step": 1320,
1074
+ "token_acc": 0.9368352123903884
1075
+ },
1076
+ {
1077
+ "epoch": 0.5269935611688955,
1078
+ "grad_norm": 1.7890625,
1079
+ "learning_rate": 9.615096003621221e-06,
1080
+ "loss": 0.17757006883621215,
1081
+ "step": 1330,
1082
+ "token_acc": 0.9385874468359324
1083
+ },
1084
+ {
1085
+ "epoch": 0.5309559187716691,
1086
+ "grad_norm": 1.5,
1087
+ "learning_rate": 9.486893284172103e-06,
1088
+ "loss": 0.1725843906402588,
1089
+ "step": 1340,
1090
+ "token_acc": 0.9396233946138856
1091
+ },
1092
+ {
1093
+ "epoch": 0.5349182763744428,
1094
+ "grad_norm": 1.1953125,
1095
+ "learning_rate": 9.358775068993484e-06,
1096
+ "loss": 0.17776031494140626,
1097
+ "step": 1350,
1098
+ "token_acc": 0.9395069576186172
1099
+ },
1100
+ {
1101
+ "epoch": 0.5388806339772164,
1102
+ "grad_norm": 1.2890625,
1103
+ "learning_rate": 9.230762458055363e-06,
1104
+ "loss": 0.18048588037490845,
1105
+ "step": 1360,
1106
+ "token_acc": 0.9376439779197635
1107
+ },
1108
+ {
1109
+ "epoch": 0.54284299157999,
1110
+ "grad_norm": 1.34375,
1111
+ "learning_rate": 9.102876533935626e-06,
1112
+ "loss": 0.1871953248977661,
1113
+ "step": 1370,
1114
+ "token_acc": 0.9352319496539852
1115
+ },
1116
+ {
1117
+ "epoch": 0.5468053491827637,
1118
+ "grad_norm": 1.8203125,
1119
+ "learning_rate": 8.975138358347931e-06,
1120
+ "loss": 0.17401375770568847,
1121
+ "step": 1380,
1122
+ "token_acc": 0.9395100063574127
1123
+ },
1124
+ {
1125
+ "epoch": 0.5507677067855374,
1126
+ "grad_norm": 1.5625,
1127
+ "learning_rate": 8.847568968673025e-06,
1128
+ "loss": 0.1821776032447815,
1129
+ "step": 1390,
1130
+ "token_acc": 0.9382589568204417
1131
+ },
1132
+ {
1133
+ "epoch": 0.5547300643883111,
1134
+ "grad_norm": 1.3203125,
1135
+ "learning_rate": 8.720189374494055e-06,
1136
+ "loss": 0.18482091426849365,
1137
+ "step": 1400,
1138
+ "token_acc": 0.9366791672453971
1139
+ },
1140
+ {
1141
+ "epoch": 0.5586924219910847,
1142
+ "grad_norm": 1.140625,
1143
+ "learning_rate": 8.593020554136491e-06,
1144
+ "loss": 0.17976686954498292,
1145
+ "step": 1410,
1146
+ "token_acc": 0.938686745381246
1147
+ },
1148
+ {
1149
+ "epoch": 0.5626547795938583,
1150
+ "grad_norm": 1.7734375,
1151
+ "learning_rate": 8.466083451213145e-06,
1152
+ "loss": 0.16887048482894898,
1153
+ "step": 1420,
1154
+ "token_acc": 0.9413505379807353
1155
+ },
1156
+ {
1157
+ "epoch": 0.566617137196632,
1158
+ "grad_norm": 1.53125,
1159
+ "learning_rate": 8.339398971174987e-06,
1160
+ "loss": 0.181710684299469,
1161
+ "step": 1430,
1162
+ "token_acc": 0.9381945571057755
1163
+ },
1164
+ {
1165
+ "epoch": 0.5705794947994056,
1166
+ "grad_norm": 1.421875,
1167
+ "learning_rate": 8.212987977868138e-06,
1168
+ "loss": 0.192651104927063,
1169
+ "step": 1440,
1170
+ "token_acc": 0.9346234811416059
1171
+ },
1172
+ {
1173
+ "epoch": 0.5745418524021793,
1174
+ "grad_norm": 1.4375,
1175
+ "learning_rate": 8.086871290097822e-06,
1176
+ "loss": 0.1725835084915161,
1177
+ "step": 1450,
1178
+ "token_acc": 0.9401547502340085
1179
+ },
1180
+ {
1181
+ "epoch": 0.578504210004953,
1182
+ "grad_norm": 1.390625,
1183
+ "learning_rate": 7.961069678199658e-06,
1184
+ "loss": 0.18463332653045655,
1185
+ "step": 1460,
1186
+ "token_acc": 0.9356090428523226
1187
+ },
1188
+ {
1189
+ "epoch": 0.5824665676077266,
1190
+ "grad_norm": 1.390625,
1191
+ "learning_rate": 7.835603860618973e-06,
1192
+ "loss": 0.18219418525695802,
1193
+ "step": 1470,
1194
+ "token_acc": 0.9381983863723681
1195
+ },
1196
+ {
1197
+ "epoch": 0.5864289252105003,
1198
+ "grad_norm": 1.3125,
1199
+ "learning_rate": 7.710494500498662e-06,
1200
+ "loss": 0.17673687934875487,
1201
+ "step": 1480,
1202
+ "token_acc": 0.9390315988583202
1203
+ },
1204
+ {
1205
+ "epoch": 0.5903912828132739,
1206
+ "grad_norm": 1.6796875,
1207
+ "learning_rate": 7.585762202276129e-06,
1208
+ "loss": 0.1698865532875061,
1209
+ "step": 1490,
1210
+ "token_acc": 0.9415788913714225
1211
+ },
1212
+ {
1213
+ "epoch": 0.5943536404160475,
1214
+ "grad_norm": 1.53125,
1215
+ "learning_rate": 7.461427508289922e-06,
1216
+ "loss": 0.17974636554718018,
1217
+ "step": 1500,
1218
+ "token_acc": 0.9385133263736498
1219
+ },
1220
+ {
1221
+ "epoch": 0.5983159980188212,
1222
+ "grad_norm": 1.0859375,
1223
+ "learning_rate": 7.337510895396591e-06,
1224
+ "loss": 0.1787565231323242,
1225
+ "step": 1510,
1226
+ "token_acc": 0.9384560906515581
1227
+ },
1228
+ {
1229
+ "epoch": 0.6022783556215948,
1230
+ "grad_norm": 1.4609375,
1231
+ "learning_rate": 7.214032771598316e-06,
1232
+ "loss": 0.1744428515434265,
1233
+ "step": 1520,
1234
+ "token_acc": 0.9401470564435646
1235
+ },
1236
+ {
1237
+ "epoch": 0.6062407132243685,
1238
+ "grad_norm": 1.265625,
1239
+ "learning_rate": 7.091013472681883e-06,
1240
+ "loss": 0.17123017311096192,
1241
+ "step": 1530,
1242
+ "token_acc": 0.9405837916975914
1243
+ },
1244
+ {
1245
+ "epoch": 0.6102030708271422,
1246
+ "grad_norm": 1.5234375,
1247
+ "learning_rate": 6.968473258869566e-06,
1248
+ "loss": 0.1690650463104248,
1249
+ "step": 1540,
1250
+ "token_acc": 0.941058213231226
1251
+ },
1252
+ {
1253
+ "epoch": 0.6141654284299158,
1254
+ "grad_norm": 1.453125,
1255
+ "learning_rate": 6.846432311482436e-06,
1256
+ "loss": 0.18313372135162354,
1257
+ "step": 1550,
1258
+ "token_acc": 0.9371285854342504
1259
+ },
1260
+ {
1261
+ "epoch": 0.6181277860326895,
1262
+ "grad_norm": 1.7890625,
1263
+ "learning_rate": 6.724910729616665e-06,
1264
+ "loss": 0.17572647333145142,
1265
+ "step": 1560,
1266
+ "token_acc": 0.939426531245842
1267
+ },
1268
+ {
1269
+ "epoch": 0.6220901436354631,
1270
+ "grad_norm": 1.25,
1271
+ "learning_rate": 6.603928526833386e-06,
1272
+ "loss": 0.16190264225006104,
1273
+ "step": 1570,
1274
+ "token_acc": 0.9443632366772048
1275
+ },
1276
+ {
1277
+ "epoch": 0.6260525012382367,
1278
+ "grad_norm": 1.265625,
1279
+ "learning_rate": 6.483505627862632e-06,
1280
+ "loss": 0.1694807767868042,
1281
+ "step": 1580,
1282
+ "token_acc": 0.9416789717779672
1283
+ },
1284
+ {
1285
+ "epoch": 0.6300148588410104,
1286
+ "grad_norm": 1.5,
1287
+ "learning_rate": 6.363661865321898e-06,
1288
+ "loss": 0.17748751640319824,
1289
+ "step": 1590,
1290
+ "token_acc": 0.9385861686705892
1291
+ },
1292
+ {
1293
+ "epoch": 0.633977216443784,
1294
+ "grad_norm": 1.3984375,
1295
+ "learning_rate": 6.244416976449875e-06,
1296
+ "loss": 0.17347029447555543,
1297
+ "step": 1600,
1298
+ "token_acc": 0.9403739289918152
1299
+ },
1300
+ {
1301
+ "epoch": 0.6379395740465577,
1302
+ "grad_norm": 1.171875,
1303
+ "learning_rate": 6.125790599855912e-06,
1304
+ "loss": 0.1826688289642334,
1305
+ "step": 1610,
1306
+ "token_acc": 0.9372320591550186
1307
+ },
1308
+ {
1309
+ "epoch": 0.6419019316493314,
1310
+ "grad_norm": 1.2890625,
1311
+ "learning_rate": 6.007802272285693e-06,
1312
+ "loss": 0.17403693199157716,
1313
+ "step": 1620,
1314
+ "token_acc": 0.9401551062440614
1315
+ },
1316
+ {
1317
+ "epoch": 0.645864289252105,
1318
+ "grad_norm": 1.625,
1319
+ "learning_rate": 5.890471425403703e-06,
1320
+ "loss": 0.18286362886428834,
1321
+ "step": 1630,
1322
+ "token_acc": 0.9368950000596794
1323
+ },
1324
+ {
1325
+ "epoch": 0.6498266468548787,
1326
+ "grad_norm": 1.4375,
1327
+ "learning_rate": 5.773817382593008e-06,
1328
+ "loss": 0.1804821014404297,
1329
+ "step": 1640,
1330
+ "token_acc": 0.9376396973396319
1331
+ },
1332
+ {
1333
+ "epoch": 0.6537890044576523,
1334
+ "grad_norm": 1.375,
1335
+ "learning_rate": 5.65785935577285e-06,
1336
+ "loss": 0.17369402647018434,
1337
+ "step": 1650,
1338
+ "token_acc": 0.9392859770259903
1339
+ },
1340
+ {
1341
+ "epoch": 0.657751362060426,
1342
+ "grad_norm": 1.3515625,
1343
+ "learning_rate": 5.542616442234618e-06,
1344
+ "loss": 0.1656261920928955,
1345
+ "step": 1660,
1346
+ "token_acc": 0.943150599230765
1347
+ },
1348
+ {
1349
+ "epoch": 0.6617137196631996,
1350
+ "grad_norm": 1.2890625,
1351
+ "learning_rate": 5.428107621496681e-06,
1352
+ "loss": 0.17441051006317138,
1353
+ "step": 1670,
1354
+ "token_acc": 0.9392566132136696
1355
+ },
1356
+ {
1357
+ "epoch": 0.6656760772659732,
1358
+ "grad_norm": 1.3125,
1359
+ "learning_rate": 5.3143517521786255e-06,
1360
+ "loss": 0.17141460180282592,
1361
+ "step": 1680,
1362
+ "token_acc": 0.9404770520787022
1363
+ },
1364
+ {
1365
+ "epoch": 0.6696384348687469,
1366
+ "grad_norm": 1.4921875,
1367
+ "learning_rate": 5.201367568895408e-06,
1368
+ "loss": 0.1779789924621582,
1369
+ "step": 1690,
1370
+ "token_acc": 0.9389050144048604
1371
+ },
1372
+ {
1373
+ "epoch": 0.6736007924715206,
1374
+ "grad_norm": 1.2890625,
1375
+ "learning_rate": 5.089173679171922e-06,
1376
+ "loss": 0.1696174383163452,
1377
+ "step": 1700,
1378
+ "token_acc": 0.9415787866940171
1379
+ },
1380
+ {
1381
+ "epoch": 0.6775631500742942,
1382
+ "grad_norm": 1.265625,
1383
+ "learning_rate": 4.977788560378484e-06,
1384
+ "loss": 0.17647080421447753,
1385
+ "step": 1710,
1386
+ "token_acc": 0.9402322070530992
1387
+ },
1388
+ {
1389
+ "epoch": 0.6815255076770679,
1390
+ "grad_norm": 1.3203125,
1391
+ "learning_rate": 4.867230556687797e-06,
1392
+ "loss": 0.17825334072113036,
1393
+ "step": 1720,
1394
+ "token_acc": 0.9382623548644003
1395
+ },
1396
+ {
1397
+ "epoch": 0.6854878652798415,
1398
+ "grad_norm": 1.390625,
1399
+ "learning_rate": 4.7575178760538e-06,
1400
+ "loss": 0.1728861927986145,
1401
+ "step": 1730,
1402
+ "token_acc": 0.939594911427579
1403
+ },
1404
+ {
1405
+ "epoch": 0.6894502228826151,
1406
+ "grad_norm": 1.5234375,
1407
+ "learning_rate": 4.648668587212998e-06,
1408
+ "loss": 0.179952073097229,
1409
+ "step": 1740,
1410
+ "token_acc": 0.9381945052060547
1411
+ },
1412
+ {
1413
+ "epoch": 0.6934125804853888,
1414
+ "grad_norm": 1.28125,
1415
+ "learning_rate": 4.5407006167086575e-06,
1416
+ "loss": 0.17567566633224488,
1417
+ "step": 1750,
1418
+ "token_acc": 0.9399701307689505
1419
+ },
1420
+ {
1421
+ "epoch": 0.6973749380881624,
1422
+ "grad_norm": 1.328125,
1423
+ "learning_rate": 4.433631745938497e-06,
1424
+ "loss": 0.17287354469299315,
1425
+ "step": 1760,
1426
+ "token_acc": 0.9405146011104378
1427
+ },
1428
+ {
1429
+ "epoch": 0.7013372956909361,
1430
+ "grad_norm": 1.5859375,
1431
+ "learning_rate": 4.327479608226226e-06,
1432
+ "loss": 0.17426562309265137,
1433
+ "step": 1770,
1434
+ "token_acc": 0.9401683220236025
1435
+ },
1436
+ {
1437
+ "epoch": 0.7052996532937098,
1438
+ "grad_norm": 1.375,
1439
+ "learning_rate": 4.222261685917489e-06,
1440
+ "loss": 0.1734224557876587,
1441
+ "step": 1780,
1442
+ "token_acc": 0.9401309334234104
1443
+ },
1444
+ {
1445
+ "epoch": 0.7092620108964834,
1446
+ "grad_norm": 1.2578125,
1447
+ "learning_rate": 4.117995307500677e-06,
1448
+ "loss": 0.17531417608261107,
1449
+ "step": 1790,
1450
+ "token_acc": 0.9409358352138655
1451
+ },
1452
+ {
1453
+ "epoch": 0.7132243684992571,
1454
+ "grad_norm": 1.1171875,
1455
+ "learning_rate": 4.014697644753069e-06,
1456
+ "loss": 0.17481131553649903,
1457
+ "step": 1800,
1458
+ "token_acc": 0.9396957170350632
1459
+ },
1460
+ {
1461
+ "epoch": 0.7171867261020307,
1462
+ "grad_norm": 1.3046875,
1463
+ "learning_rate": 3.912385709912794e-06,
1464
+ "loss": 0.17085225582122804,
1465
+ "step": 1810,
1466
+ "token_acc": 0.9413413462722593
1467
+ },
1468
+ {
1469
+ "epoch": 0.7211490837048044,
1470
+ "grad_norm": 1.765625,
1471
+ "learning_rate": 3.8110763528770543e-06,
1472
+ "loss": 0.18243337869644166,
1473
+ "step": 1820,
1474
+ "token_acc": 0.9380230355884426
1475
+ },
1476
+ {
1477
+ "epoch": 0.725111441307578,
1478
+ "grad_norm": 1.2109375,
1479
+ "learning_rate": 3.7107862584271016e-06,
1480
+ "loss": 0.16808085441589354,
1481
+ "step": 1830,
1482
+ "token_acc": 0.9410576758514462
1483
+ },
1484
+ {
1485
+ "epoch": 0.7290737989103516,
1486
+ "grad_norm": 1.28125,
1487
+ "learning_rate": 3.6115319434803897e-06,
1488
+ "loss": 0.16966335773468016,
1489
+ "step": 1840,
1490
+ "token_acc": 0.9421915175440875
1491
+ },
1492
+ {
1493
+ "epoch": 0.7330361565131253,
1494
+ "grad_norm": 1.484375,
1495
+ "learning_rate": 3.5133297543703724e-06,
1496
+ "loss": 0.18466969728469848,
1497
+ "step": 1850,
1498
+ "token_acc": 0.9361129341986922
1499
+ },
1500
+ {
1501
+ "epoch": 0.736998514115899,
1502
+ "grad_norm": 1.34375,
1503
+ "learning_rate": 3.416195864154426e-06,
1504
+ "loss": 0.17389074563980103,
1505
+ "step": 1860,
1506
+ "token_acc": 0.9401176608095999
1507
+ },
1508
+ {
1509
+ "epoch": 0.7409608717186726,
1510
+ "grad_norm": 1.8046875,
1511
+ "learning_rate": 3.3201462699502606e-06,
1512
+ "loss": 0.18031821250915528,
1513
+ "step": 1870,
1514
+ "token_acc": 0.9371710958652052
1515
+ },
1516
+ {
1517
+ "epoch": 0.7449232293214463,
1518
+ "grad_norm": 1.3828125,
1519
+ "learning_rate": 3.2251967903013515e-06,
1520
+ "loss": 0.16321947574615478,
1521
+ "step": 1880,
1522
+ "token_acc": 0.9434022207870669
1523
+ },
1524
+ {
1525
+ "epoch": 0.7488855869242199,
1526
+ "grad_norm": 1.40625,
1527
+ "learning_rate": 3.1313630625717462e-06,
1528
+ "loss": 0.165952730178833,
1529
+ "step": 1890,
1530
+ "token_acc": 0.9433088620870477
1531
+ },
1532
+ {
1533
+ "epoch": 0.7528479445269936,
1534
+ "grad_norm": 1.6953125,
1535
+ "learning_rate": 3.0386605403707347e-06,
1536
+ "loss": 0.17759935855865477,
1537
+ "step": 1900,
1538
+ "token_acc": 0.9391445944776249
1539
+ },
1540
+ {
1541
+ "epoch": 0.7568103021297672,
1542
+ "grad_norm": 1.5625,
1543
+ "learning_rate": 2.947104491007766e-06,
1544
+ "loss": 0.17080872058868407,
1545
+ "step": 1910,
1546
+ "token_acc": 0.9417546272928465
1547
+ },
1548
+ {
1549
+ "epoch": 0.7607726597325408,
1550
+ "grad_norm": 1.296875,
1551
+ "learning_rate": 2.8567099929780596e-06,
1552
+ "loss": 0.17588542699813842,
1553
+ "step": 1920,
1554
+ "token_acc": 0.9384443609064742
1555
+ },
1556
+ {
1557
+ "epoch": 0.7647350173353145,
1558
+ "grad_norm": 1.671875,
1559
+ "learning_rate": 2.767491933479304e-06,
1560
+ "loss": 0.17596354484558105,
1561
+ "step": 1930,
1562
+ "token_acc": 0.9390227163544026
1563
+ },
1564
+ {
1565
+ "epoch": 0.7686973749380882,
1566
+ "grad_norm": 1.4921875,
1567
+ "learning_rate": 2.679465005959856e-06,
1568
+ "loss": 0.1740294098854065,
1569
+ "step": 1940,
1570
+ "token_acc": 0.9401780685412244
1571
+ },
1572
+ {
1573
+ "epoch": 0.7726597325408618,
1574
+ "grad_norm": 1.359375,
1575
+ "learning_rate": 2.5926437076988685e-06,
1576
+ "loss": 0.16495332717895508,
1577
+ "step": 1950,
1578
+ "token_acc": 0.9424596695186467
1579
+ },
1580
+ {
1581
+ "epoch": 0.7766220901436355,
1582
+ "grad_norm": 1.359375,
1583
+ "learning_rate": 2.507042337418707e-06,
1584
+ "loss": 0.17244219779968262,
1585
+ "step": 1960,
1586
+ "token_acc": 0.940576109936575
1587
+ },
1588
+ {
1589
+ "epoch": 0.7805844477464091,
1590
+ "grad_norm": 1.7109375,
1591
+ "learning_rate": 2.4226749929300774e-06,
1592
+ "loss": 0.17762508392333984,
1593
+ "step": 1970,
1594
+ "token_acc": 0.9379922601444852
1595
+ },
1596
+ {
1597
+ "epoch": 0.7845468053491828,
1598
+ "grad_norm": 1.5078125,
1599
+ "learning_rate": 2.339555568810221e-06,
1600
+ "loss": 0.16768510341644288,
1601
+ "step": 1980,
1602
+ "token_acc": 0.9424666806336723
1603
+ },
1604
+ {
1605
+ "epoch": 0.7885091629519564,
1606
+ "grad_norm": 1.2734375,
1607
+ "learning_rate": 2.2576977541146193e-06,
1608
+ "loss": 0.1687544584274292,
1609
+ "step": 1990,
1610
+ "token_acc": 0.941843418155467
1611
+ },
1612
+ {
1613
+ "epoch": 0.79247152055473,
1614
+ "grad_norm": 1.3984375,
1615
+ "learning_rate": 2.1771150301225097e-06,
1616
+ "loss": 0.17961428165435792,
1617
+ "step": 2000,
1618
+ "token_acc": 0.9382880764646055
1619
+ }
1620
+ ],
1621
+ "logging_steps": 10,
1622
+ "max_steps": 2524,
1623
+ "num_input_tokens_seen": 0,
1624
+ "num_train_epochs": 1,
1625
+ "save_steps": 500,
1626
+ "stateful_callbacks": {
1627
+ "TrainerControl": {
1628
+ "args": {
1629
+ "should_epoch_stop": false,
1630
+ "should_evaluate": false,
1631
+ "should_log": false,
1632
+ "should_save": true,
1633
+ "should_training_stop": false
1634
+ },
1635
+ "attributes": {}
1636
+ }
1637
+ },
1638
+ "total_flos": 1.3391808311045652e+19,
1639
+ "train_batch_size": 2,
1640
+ "trial_name": null,
1641
+ "trial_params": null
1642
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093d4701afd0197196efc8e1830005f6b76e00fae5d4e514885cd506a6d19e0f
3
+ size 7313
vocab.json ADDED
The diff for this file is too large to render. See raw diff