Hugging Face's logo

TIGER-Lab
/
One-Shot-CFT-Math-Qwen-14B

Text Generation
Transformers
Safetensors
English
qwen2
One-Shot-CFT
conversational
text-generation-inference
Model card Files
xet
Community
1
ubowang commited on
Commit
48cc69b
·
verified ·
1 Parent(s): 4d5b001

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +366 -0
  4. config.json +29 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. model-00001-of-00006.safetensors +3 -0
  8. model-00002-of-00006.safetensors +3 -0
  9. model-00003-of-00006.safetensors +3 -0
  10. model-00004-of-00006.safetensors +3 -0
  11. model-00005-of-00006.safetensors +3 -0
  12. model-00006-of-00006.safetensors +3 -0
  13. model.safetensors.index.json +586 -0
  14. special_tokens_map.json +31 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +208 -0
  17. trainer_state.json +634 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/data/yubo/models/Qwen2.5-14B",
3
+ "model_type": "qwen2_5",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": "flash_attn",
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "qwen2_5",
15
+ "system": null,
16
+ "max_length": null,
17
+ "truncation_strategy": "delete",
18
+ "max_pixels": null,
19
+ "agent_template": null,
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "default",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "/data/yubo/CriticCoT/dsr_scripts_0514/dsr_one-shot_train_data_0514_p0.jsonl"
29
+ ],
30
+ "val_dataset": [],
31
+ "split_dataset_ratio": 0.0,
32
+ "data_seed": 42,
33
+ "dataset_num_proc": 4,
34
+ "dataset_shuffle": true,
35
+ "val_dataset_shuffle": false,
36
+ "streaming": false,
37
+ "interleave_prob": null,
38
+ "stopping_strategy": "first_exhausted",
39
+ "shuffle_buffer_size": 1000,
40
+ "enable_cache": false,
41
+ "download_mode": "reuse_dataset_if_exists",
42
+ "columns": {},
43
+ "strict": false,
44
+ "remove_unused_columns": false,
45
+ "model_name": [
46
+ null,
47
+ null
48
+ ],
49
+ "model_author": [
50
+ null,
51
+ null
52
+ ],
53
+ "custom_dataset_info": [],
54
+ "quant_method": null,
55
+ "quant_bits": null,
56
+ "hqq_axis": null,
57
+ "bnb_4bit_compute_dtype": "bfloat16",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "bnb_4bit_quant_storage": null,
61
+ "max_new_tokens": 64,
62
+ "temperature": 0.0,
63
+ "top_k": null,
64
+ "top_p": null,
65
+ "repetition_penalty": null,
66
+ "num_beams": 1,
67
+ "stream": false,
68
+ "stop_words": [],
69
+ "logprobs": false,
70
+ "top_logprobs": null,
71
+ "ckpt_dir": null,
72
+ "load_dataset_config": null,
73
+ "lora_modules": [],
74
+ "tuner_backend": "peft",
75
+ "train_type": "full",
76
+ "adapters": [],
77
+ "external_plugins": [],
78
+ "seed": 42,
79
+ "model_kwargs": {},
80
+ "load_args": false,
81
+ "load_data_args": false,
82
+ "use_hf": true,
83
+ "hub_token": null,
84
+ "custom_register_path": [],
85
+ "ignore_args_error": false,
86
+ "use_swift_lora": false,
87
+ "output_dir": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653",
88
+ "overwrite_output_dir": false,
89
+ "do_train": false,
90
+ "do_eval": false,
91
+ "do_predict": false,
92
+ "eval_strategy": "steps",
93
+ "prediction_loss_only": false,
94
+ "per_device_train_batch_size": 1,
95
+ "per_device_eval_batch_size": 1,
96
+ "per_gpu_train_batch_size": null,
97
+ "per_gpu_eval_batch_size": null,
98
+ "gradient_accumulation_steps": 128,
99
+ "eval_accumulation_steps": null,
100
+ "eval_delay": 0,
101
+ "torch_empty_cache_steps": null,
102
+ "learning_rate": 5e-06,
103
+ "weight_decay": 0.05,
104
+ "adam_beta1": 0.9,
105
+ "adam_beta2": 0.95,
106
+ "adam_epsilon": 1e-08,
107
+ "max_grad_norm": 1.0,
108
+ "num_train_epochs": 200.0,
109
+ "max_steps": -1,
110
+ "lr_scheduler_type": "cosine",
111
+ "lr_scheduler_kwargs": null,
112
+ "warmup_ratio": 0.05,
113
+ "warmup_steps": 0,
114
+ "log_level": "passive",
115
+ "log_level_replica": "warning",
116
+ "log_on_each_node": true,
117
+ "logging_dir": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653/runs",
118
+ "logging_strategy": "steps",
119
+ "logging_first_step": true,
120
+ "logging_steps": 1,
121
+ "logging_nan_inf_filter": true,
122
+ "save_strategy": "steps",
123
+ "save_steps": 10.0,
124
+ "save_total_limit": null,
125
+ "save_safetensors": true,
126
+ "save_on_each_node": false,
127
+ "save_only_model": true,
128
+ "restore_callback_states_from_checkpoint": false,
129
+ "no_cuda": false,
130
+ "use_cpu": false,
131
+ "use_mps_device": false,
132
+ "jit_mode_eval": false,
133
+ "use_ipex": false,
134
+ "bf16": true,
135
+ "fp16": false,
136
+ "fp16_opt_level": "O1",
137
+ "half_precision_backend": "auto",
138
+ "bf16_full_eval": false,
139
+ "fp16_full_eval": false,
140
+ "tf32": null,
141
+ "local_rank": 0,
142
+ "ddp_backend": "nccl",
143
+ "tpu_num_cores": null,
144
+ "tpu_metrics_debug": false,
145
+ "debug": null,
146
+ "dataloader_drop_last": false,
147
+ "eval_steps": 10.0,
148
+ "dataloader_num_workers": 4,
149
+ "dataloader_prefetch_factor": null,
150
+ "past_index": -1,
151
+ "run_name": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653",
152
+ "disable_tqdm": null,
153
+ "label_names": null,
154
+ "load_best_model_at_end": false,
155
+ "metric_for_best_model": "loss",
156
+ "greater_is_better": false,
157
+ "ignore_data_skip": false,
158
+ "fsdp": "",
159
+ "fsdp_min_num_params": 0,
160
+ "fsdp_config": null,
161
+ "tp_size": 0,
162
+ "fsdp_transformer_layer_cls_to_wrap": null,
163
+ "accelerator_config": {
164
+ "dispatch_batches": false
165
+ },
166
+ "deepspeed": {
167
+ "fp16": {
168
+ "enabled": "auto",
169
+ "loss_scale": 0,
170
+ "loss_scale_window": 1000,
171
+ "initial_scale_power": 16,
172
+ "hysteresis": 2,
173
+ "min_loss_scale": 1
174
+ },
175
+ "bf16": {
176
+ "enabled": "auto"
177
+ },
178
+ "zero_optimization": {
179
+ "stage": 3,
180
+ "offload_optimizer": {
181
+ "device": "none",
182
+ "pin_memory": true
183
+ },
184
+ "offload_param": {
185
+ "device": "none",
186
+ "pin_memory": true
187
+ },
188
+ "overlap_comm": false,
189
+ "contiguous_gradients": true,
190
+ "sub_group_size": 1000000000.0,
191
+ "reduce_bucket_size": "auto",
192
+ "zero_quantized_weights": false,
193
+ "zero_quantized_gradients": false,
194
+ "stage3_prefetch_bucket_size": "auto",
195
+ "stage3_param_persistence_threshold": "auto",
196
+ "stage3_max_live_parameters": 1000000000.0,
197
+ "stage3_max_reuse_distance": 1000000000.0,
198
+ "stage3_gather_16bit_weights_on_model_save": true
199
+ },
200
+ "gradient_accumulation_steps": "auto",
201
+ "gradient_clipping": "auto",
202
+ "steps_per_print": 2000,
203
+ "train_batch_size": "auto",
204
+ "train_micro_batch_size_per_gpu": "auto",
205
+ "wall_clock_breakdown": false
206
+ },
207
+ "label_smoothing_factor": 0.0,
208
+ "optim": "adamw_torch",
209
+ "optim_args": null,
210
+ "adafactor": false,
211
+ "group_by_length": false,
212
+ "length_column_name": "length",
213
+ "report_to": [
214
+ "none"
215
+ ],
216
+ "ddp_find_unused_parameters": null,
217
+ "ddp_bucket_cap_mb": null,
218
+ "ddp_broadcast_buffers": null,
219
+ "dataloader_pin_memory": true,
220
+ "dataloader_persistent_workers": false,
221
+ "skip_memory_metrics": true,
222
+ "use_legacy_prediction_loop": false,
223
+ "push_to_hub": false,
224
+ "resume_from_checkpoint": null,
225
+ "hub_model_id": null,
226
+ "hub_strategy": "every_save",
227
+ "hub_private_repo": null,
228
+ "hub_always_push": false,
229
+ "gradient_checkpointing": true,
230
+ "gradient_checkpointing_kwargs": null,
231
+ "include_inputs_for_metrics": false,
232
+ "include_for_metrics": [],
233
+ "eval_do_concat_batches": true,
234
+ "fp16_backend": "auto",
235
+ "push_to_hub_model_id": null,
236
+ "push_to_hub_organization": null,
237
+ "push_to_hub_token": null,
238
+ "mp_parameters": "",
239
+ "auto_find_batch_size": false,
240
+ "full_determinism": false,
241
+ "torchdynamo": null,
242
+ "ray_scope": "last",
243
+ "ddp_timeout": 1800,
244
+ "torch_compile": false,
245
+ "torch_compile_backend": null,
246
+ "torch_compile_mode": null,
247
+ "include_tokens_per_second": false,
248
+ "include_num_input_tokens_seen": false,
249
+ "neftune_noise_alpha": null,
250
+ "optim_target_modules": null,
251
+ "batch_eval_metrics": false,
252
+ "eval_on_start": false,
253
+ "use_liger_kernel": false,
254
+ "eval_use_gather_object": false,
255
+ "average_tokens_across_devices": false,
256
+ "sortish_sampler": false,
257
+ "predict_with_generate": false,
258
+ "generation_max_length": null,
259
+ "generation_num_beams": null,
260
+ "generation_config": null,
261
+ "check_model": true,
262
+ "acc_strategy": "token",
263
+ "train_dataloader_shuffle": true,
264
+ "metric_warmup_step": 0,
265
+ "fsdp_num": 1,
266
+ "acc_steps": 1,
267
+ "eval_use_evalscope": false,
268
+ "eval_datasets": [],
269
+ "eval_limit": null,
270
+ "eval_datasets_args": null,
271
+ "eval_generation_config": null,
272
+ "freeze_parameters": [],
273
+ "freeze_parameters_ratio": 0.0,
274
+ "trainable_parameters": [],
275
+ "freeze_llm": false,
276
+ "freeze_vit": false,
277
+ "freeze_aligner": false,
278
+ "target_modules": [
279
+ "all-linear"
280
+ ],
281
+ "target_regex": null,
282
+ "modules_to_save": [],
283
+ "lora_rank": 8,
284
+ "lora_alpha": 32,
285
+ "lora_dropout": 0.05,
286
+ "lora_bias": "none",
287
+ "lora_dtype": null,
288
+ "lorap_lr_ratio": null,
289
+ "use_rslora": false,
290
+ "use_dora": false,
291
+ "lora_ga_batch_size": 2,
292
+ "lora_ga_iters": 2,
293
+ "lora_ga_max_length": 1024,
294
+ "lora_ga_direction": "ArB2r",
295
+ "lora_ga_scale": "stable",
296
+ "lora_ga_stable_gamma": 16,
297
+ "init_weights": true,
298
+ "fourier_n_frequency": 2000,
299
+ "fourier_scaling": 300.0,
300
+ "boft_block_size": 4,
301
+ "boft_block_num": 0,
302
+ "boft_n_butterfly_factor": 1,
303
+ "boft_dropout": 0.0,
304
+ "vera_rank": 256,
305
+ "vera_projection_prng_key": 0,
306
+ "vera_dropout": 0.0,
307
+ "vera_d_initial": 0.1,
308
+ "adapter_act": "gelu",
309
+ "adapter_length": 128,
310
+ "use_galore": false,
311
+ "galore_target_modules": null,
312
+ "galore_rank": 128,
313
+ "galore_update_proj_gap": 50,
314
+ "galore_scale": 1.0,
315
+ "galore_proj_type": "std",
316
+ "galore_optim_per_parameter": false,
317
+ "galore_with_embedding": false,
318
+ "galore_quantization": false,
319
+ "galore_proj_quant": false,
320
+ "galore_proj_bits": 4,
321
+ "galore_proj_group_size": 256,
322
+ "galore_cos_threshold": 0.4,
323
+ "galore_gamma_proj": 2,
324
+ "galore_queue_size": 5,
325
+ "adalora_target_r": 8,
326
+ "adalora_init_r": 12,
327
+ "adalora_tinit": 0,
328
+ "adalora_tfinal": 0,
329
+ "adalora_deltaT": 1,
330
+ "adalora_beta1": 0.85,
331
+ "adalora_beta2": 0.85,
332
+ "adalora_orth_reg_weight": 0.5,
333
+ "llamapro_num_new_blocks": 4,
334
+ "llamapro_num_groups": null,
335
+ "lisa_activated_layers": 0,
336
+ "lisa_step_interval": 20,
337
+ "reft_layer_key": null,
338
+ "reft_layers": null,
339
+ "reft_rank": 4,
340
+ "reft_intervention_type": "LoreftIntervention",
341
+ "reft_args": null,
342
+ "swanlab_token": null,
343
+ "swanlab_project": null,
344
+ "swanlab_workspace": null,
345
+ "swanlab_exp_name": null,
346
+ "swanlab_mode": "cloud",
347
+ "add_version": true,
348
+ "resume_only_model": false,
349
+ "create_checkpoint_symlink": false,
350
+ "packing": false,
351
+ "lazy_tokenize": false,
352
+ "loss_type": null,
353
+ "optimizer": null,
354
+ "metric": null,
355
+ "zero_hpz_partition_size": null,
356
+ "rank": 0,
357
+ "global_world_size": 4,
358
+ "local_world_size": 4,
359
+ "model_suffix": "Qwen2.5-14B",
360
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/data/yubo/models/Qwen2.5-14B', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
361
+ "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding'])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x700f640f9fc0>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
362
+ "model_dir": "/data/yubo/models/Qwen2.5-14B",
363
+ "hub": "<class 'swift.hub.hub.HFHub'>",
364
+ "evaluation_strategy": "steps",
365
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=128, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=200.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653', 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}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], 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, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
366
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 48,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 151643,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": 131072,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.51.3",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 8192,
5
+ "transformers_version": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9fc09e7ce70fe504ccd141c71897665ed05e14e054e89c283e4fd9e87011ca
3
+ size 4986211280
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b72d7319d3cd05ee3f00b8893351706e7269f418c757fbb26874630b05be857
3
+ size 4954847344
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239abc1ee1fc6ce4f14f1d91b377f1837a1842329315508e6e275985a6206b20
3
+ size 4954847392
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d79837250b6e3f62857643404004d1d5235187a38cf5018d2dbf6c0dc35201
3
+ size 4954847392
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c614d377a93ad4ecff488334bf6f463a31d26bbab982b88cb3e6df398a26dba
3
+ size 4954847392
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89a206612ecba703945f3aba80d54fd5d34ec3959c39f79357e212053651108
3
+ size 4734533160
model.safetensors.index.json ADDED
@@ -0,0 +1,586 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29540067328
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
524
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
525
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
526
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
527
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
528
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
529
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
530
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
531
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
532
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
533
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
534
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
535
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
536
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
537
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
538
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
539
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
540
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
541
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
542
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
543
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
544
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
545
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
546
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
547
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
548
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
549
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
550
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
551
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
552
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
553
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
554
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
555
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
556
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
557
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
558
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
559
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
560
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
561
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
562
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
563
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
564
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
565
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
566
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
567
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
568
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
569
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
570
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
571
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
572
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
573
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
574
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
575
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
576
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
577
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
578
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
579
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
580
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
581
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
582
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
583
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
584
+ "model.norm.weight": "model-00006-of-00006.safetensors"
585
+ }
586
+ }
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": "<|endoftext|>",
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_state.json ADDED
@@ -0,0 +1,634 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 59.7710843373494,
6
+ "eval_steps": 10,
7
+ "global_step": 60,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7710843373493976,
14
+ "grad_norm": 3.914616675051536,
15
+ "learning_rate": 5.000000000000001e-07,
16
+ "loss": 0.6485056281089783,
17
+ "memory(GiB)": 76.1,
18
+ "step": 1,
19
+ "token_acc": 0.8288129939443704,
20
+ "train_speed(iter/s)": 0.00248
21
+ },
22
+ {
23
+ "epoch": 1.7710843373493976,
24
+ "grad_norm": 7.135952401058273,
25
+ "learning_rate": 1.0000000000000002e-06,
26
+ "loss": 1.306803822517395,
27
+ "memory(GiB)": 77.59,
28
+ "step": 2,
29
+ "token_acc": 0.8355539032171605,
30
+ "train_speed(iter/s)": 0.002291
31
+ },
32
+ {
33
+ "epoch": 2.7710843373493974,
34
+ "grad_norm": 7.25317611851469,
35
+ "learning_rate": 1.5e-06,
36
+ "loss": 1.2851154804229736,
37
+ "memory(GiB)": 77.59,
38
+ "step": 3,
39
+ "token_acc": 0.834915035973237,
40
+ "train_speed(iter/s)": 0.002247
41
+ },
42
+ {
43
+ "epoch": 3.7710843373493974,
44
+ "grad_norm": 6.865015999508222,
45
+ "learning_rate": 2.0000000000000003e-06,
46
+ "loss": 1.290574073791504,
47
+ "memory(GiB)": 77.59,
48
+ "step": 4,
49
+ "token_acc": 0.8338767344065504,
50
+ "train_speed(iter/s)": 0.002214
51
+ },
52
+ {
53
+ "epoch": 4.771084337349397,
54
+ "grad_norm": 6.57767604145361,
55
+ "learning_rate": 2.5e-06,
56
+ "loss": 1.261496901512146,
57
+ "memory(GiB)": 77.59,
58
+ "step": 5,
59
+ "token_acc": 0.8348027461456405,
60
+ "train_speed(iter/s)": 0.0022
61
+ },
62
+ {
63
+ "epoch": 5.771084337349397,
64
+ "grad_norm": 5.131561904948073,
65
+ "learning_rate": 3e-06,
66
+ "loss": 1.20093834400177,
67
+ "memory(GiB)": 77.59,
68
+ "step": 6,
69
+ "token_acc": 0.8447540089861448,
70
+ "train_speed(iter/s)": 0.002191
71
+ },
72
+ {
73
+ "epoch": 6.771084337349397,
74
+ "grad_norm": 4.169361922366313,
75
+ "learning_rate": 3.5e-06,
76
+ "loss": 1.118795394897461,
77
+ "memory(GiB)": 77.59,
78
+ "step": 7,
79
+ "token_acc": 0.845426595733518,
80
+ "train_speed(iter/s)": 0.002187
81
+ },
82
+ {
83
+ "epoch": 7.771084337349397,
84
+ "grad_norm": 4.513043229540615,
85
+ "learning_rate": 4.000000000000001e-06,
86
+ "loss": 1.0338046550750732,
87
+ "memory(GiB)": 77.59,
88
+ "step": 8,
89
+ "token_acc": 0.8524168712340995,
90
+ "train_speed(iter/s)": 0.00218
91
+ },
92
+ {
93
+ "epoch": 8.771084337349398,
94
+ "grad_norm": 5.185455486257246,
95
+ "learning_rate": 4.5e-06,
96
+ "loss": 0.9289287328720093,
97
+ "memory(GiB)": 77.59,
98
+ "step": 9,
99
+ "token_acc": 0.8699944903581267,
100
+ "train_speed(iter/s)": 0.002177
101
+ },
102
+ {
103
+ "epoch": 9.771084337349398,
104
+ "grad_norm": 3.6878315103563324,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.9007519483566284,
107
+ "memory(GiB)": 77.59,
108
+ "step": 10,
109
+ "token_acc": 0.8636064441638881,
110
+ "train_speed(iter/s)": 0.002176
111
+ },
112
+ {
113
+ "epoch": 10.771084337349398,
114
+ "grad_norm": 3.153907065444448,
115
+ "learning_rate": 4.999658262481173e-06,
116
+ "loss": 0.8321974277496338,
117
+ "memory(GiB)": 77.59,
118
+ "step": 11,
119
+ "token_acc": 0.8710321094284695,
120
+ "train_speed(iter/s)": 0.002152
121
+ },
122
+ {
123
+ "epoch": 11.771084337349398,
124
+ "grad_norm": 2.203676742176422,
125
+ "learning_rate": 4.998633143352315e-06,
126
+ "loss": 0.7872496247291565,
127
+ "memory(GiB)": 77.59,
128
+ "step": 12,
129
+ "token_acc": 0.8761502671032225,
130
+ "train_speed(iter/s)": 0.002149
131
+ },
132
+ {
133
+ "epoch": 12.771084337349398,
134
+ "grad_norm": 2.4327146254784084,
135
+ "learning_rate": 4.9969249228707625e-06,
136
+ "loss": 0.7419657707214355,
137
+ "memory(GiB)": 77.59,
138
+ "step": 13,
139
+ "token_acc": 0.8786807478287534,
140
+ "train_speed(iter/s)": 0.002148
141
+ },
142
+ {
143
+ "epoch": 13.771084337349398,
144
+ "grad_norm": 1.8937402046126173,
145
+ "learning_rate": 4.994534068046936e-06,
146
+ "loss": 0.709729790687561,
147
+ "memory(GiB)": 77.59,
148
+ "step": 14,
149
+ "token_acc": 0.8879921788137868,
150
+ "train_speed(iter/s)": 0.002151
151
+ },
152
+ {
153
+ "epoch": 14.771084337349398,
154
+ "grad_norm": 1.4897225411877277,
155
+ "learning_rate": 4.991461232516675e-06,
156
+ "loss": 0.676007866859436,
157
+ "memory(GiB)": 77.59,
158
+ "step": 15,
159
+ "token_acc": 0.8962045012503473,
160
+ "train_speed(iter/s)": 0.00215
161
+ },
162
+ {
163
+ "epoch": 15.771084337349398,
164
+ "grad_norm": 1.297539359495755,
165
+ "learning_rate": 4.987707256362529e-06,
166
+ "loss": 0.6474949717521667,
167
+ "memory(GiB)": 77.59,
168
+ "step": 16,
169
+ "token_acc": 0.8947659474239368,
170
+ "train_speed(iter/s)": 0.002148
171
+ },
172
+ {
173
+ "epoch": 16.771084337349397,
174
+ "grad_norm": 0.7199351026372981,
175
+ "learning_rate": 4.983273165884096e-06,
176
+ "loss": 0.6222354173660278,
177
+ "memory(GiB)": 77.59,
178
+ "step": 17,
179
+ "token_acc": 0.9017643862580863,
180
+ "train_speed(iter/s)": 0.00215
181
+ },
182
+ {
183
+ "epoch": 17.771084337349397,
184
+ "grad_norm": 1.4007282443863567,
185
+ "learning_rate": 4.978160173317439e-06,
186
+ "loss": 0.6050044298171997,
187
+ "memory(GiB)": 77.59,
188
+ "step": 18,
189
+ "token_acc": 0.899228721854176,
190
+ "train_speed(iter/s)": 0.00215
191
+ },
192
+ {
193
+ "epoch": 18.771084337349397,
194
+ "grad_norm": 1.4351431315774181,
195
+ "learning_rate": 4.972369676503672e-06,
196
+ "loss": 0.5903453230857849,
197
+ "memory(GiB)": 77.59,
198
+ "step": 19,
199
+ "token_acc": 0.9062169786627631,
200
+ "train_speed(iter/s)": 0.002149
201
+ },
202
+ {
203
+ "epoch": 19.771084337349397,
204
+ "grad_norm": 1.1929137455373535,
205
+ "learning_rate": 4.965903258506806e-06,
206
+ "loss": 0.5688210725784302,
207
+ "memory(GiB)": 77.59,
208
+ "step": 20,
209
+ "token_acc": 0.9079767112253118,
210
+ "train_speed(iter/s)": 0.002148
211
+ },
212
+ {
213
+ "epoch": 20.771084337349397,
214
+ "grad_norm": 1.1732494606890316,
215
+ "learning_rate": 4.9587626871809564e-06,
216
+ "loss": 0.543393611907959,
217
+ "memory(GiB)": 77.59,
218
+ "step": 21,
219
+ "token_acc": 0.9126149389091825,
220
+ "train_speed(iter/s)": 0.002136
221
+ },
222
+ {
223
+ "epoch": 21.771084337349397,
224
+ "grad_norm": 1.0573555070054292,
225
+ "learning_rate": 4.950949914687024e-06,
226
+ "loss": 0.5107942223548889,
227
+ "memory(GiB)": 77.59,
228
+ "step": 22,
229
+ "token_acc": 0.913213028660819,
230
+ "train_speed(iter/s)": 0.002136
231
+ },
232
+ {
233
+ "epoch": 22.771084337349397,
234
+ "grad_norm": 0.9119223186948517,
235
+ "learning_rate": 4.942467076958999e-06,
236
+ "loss": 0.48675835132598877,
237
+ "memory(GiB)": 77.59,
238
+ "step": 23,
239
+ "token_acc": 0.916867432182973,
240
+ "train_speed(iter/s)": 0.002137
241
+ },
242
+ {
243
+ "epoch": 23.771084337349397,
244
+ "grad_norm": 1.0782070696527255,
245
+ "learning_rate": 4.933316493120015e-06,
246
+ "loss": 0.5053229331970215,
247
+ "memory(GiB)": 77.59,
248
+ "step": 24,
249
+ "token_acc": 0.9218187118672303,
250
+ "train_speed(iter/s)": 0.002139
251
+ },
252
+ {
253
+ "epoch": 24.771084337349397,
254
+ "grad_norm": 0.9655818937470999,
255
+ "learning_rate": 4.923500664848327e-06,
256
+ "loss": 0.5017877817153931,
257
+ "memory(GiB)": 77.59,
258
+ "step": 25,
259
+ "token_acc": 0.9221839217084671,
260
+ "train_speed(iter/s)": 0.002138
261
+ },
262
+ {
263
+ "epoch": 25.771084337349397,
264
+ "grad_norm": 0.9404583758277602,
265
+ "learning_rate": 4.913022275693372e-06,
266
+ "loss": 0.4680900275707245,
267
+ "memory(GiB)": 77.59,
268
+ "step": 26,
269
+ "token_acc": 0.9232181127591402,
270
+ "train_speed(iter/s)": 0.002139
271
+ },
272
+ {
273
+ "epoch": 26.771084337349397,
274
+ "grad_norm": 0.9566563796831183,
275
+ "learning_rate": 4.901884190342121e-06,
276
+ "loss": 0.4565889239311218,
277
+ "memory(GiB)": 77.59,
278
+ "step": 27,
279
+ "token_acc": 0.9250697693507346,
280
+ "train_speed(iter/s)": 0.002138
281
+ },
282
+ {
283
+ "epoch": 27.771084337349397,
284
+ "grad_norm": 0.7703532186007063,
285
+ "learning_rate": 4.890089453835894e-06,
286
+ "loss": 0.43708479404449463,
287
+ "memory(GiB)": 77.59,
288
+ "step": 28,
289
+ "token_acc": 0.9259928949775574,
290
+ "train_speed(iter/s)": 0.002139
291
+ },
292
+ {
293
+ "epoch": 28.771084337349397,
294
+ "grad_norm": 0.9233409831228016,
295
+ "learning_rate": 4.8776412907378845e-06,
296
+ "loss": 0.4270290732383728,
297
+ "memory(GiB)": 77.59,
298
+ "step": 29,
299
+ "token_acc": 0.9246415671992716,
300
+ "train_speed(iter/s)": 0.00214
301
+ },
302
+ {
303
+ "epoch": 29.771084337349397,
304
+ "grad_norm": 0.9965352268428146,
305
+ "learning_rate": 4.864543104251587e-06,
306
+ "loss": 0.41402751207351685,
307
+ "memory(GiB)": 77.59,
308
+ "step": 30,
309
+ "token_acc": 0.9240786009778112,
310
+ "train_speed(iter/s)": 0.002139
311
+ },
312
+ {
313
+ "epoch": 30.771084337349397,
314
+ "grad_norm": 0.9358295902337755,
315
+ "learning_rate": 4.850798475290403e-06,
316
+ "loss": 0.39457955956459045,
317
+ "memory(GiB)": 77.59,
318
+ "step": 31,
319
+ "token_acc": 0.9368182401505754,
320
+ "train_speed(iter/s)": 0.002131
321
+ },
322
+ {
323
+ "epoch": 31.771084337349397,
324
+ "grad_norm": 0.9813539670443086,
325
+ "learning_rate": 4.836411161498653e-06,
326
+ "loss": 0.38136690855026245,
327
+ "memory(GiB)": 77.59,
328
+ "step": 32,
329
+ "token_acc": 0.9375963637091769,
330
+ "train_speed(iter/s)": 0.002133
331
+ },
332
+ {
333
+ "epoch": 32.7710843373494,
334
+ "grad_norm": 0.4679577449591144,
335
+ "learning_rate": 4.821385096224268e-06,
336
+ "loss": 0.36845850944519043,
337
+ "memory(GiB)": 77.59,
338
+ "step": 33,
339
+ "token_acc": 0.9348571791559913,
340
+ "train_speed(iter/s)": 0.002134
341
+ },
342
+ {
343
+ "epoch": 33.7710843373494,
344
+ "grad_norm": 0.9212511288160155,
345
+ "learning_rate": 4.8057243874434625e-06,
346
+ "loss": 0.35925933718681335,
347
+ "memory(GiB)": 77.59,
348
+ "step": 34,
349
+ "token_acc": 0.9376081366560561,
350
+ "train_speed(iter/s)": 0.002133
351
+ },
352
+ {
353
+ "epoch": 34.7710843373494,
354
+ "grad_norm": 1.0561026403132139,
355
+ "learning_rate": 4.789433316637644e-06,
356
+ "loss": 0.3401709794998169,
357
+ "memory(GiB)": 77.59,
358
+ "step": 35,
359
+ "token_acc": 0.9403078788403664,
360
+ "train_speed(iter/s)": 0.002134
361
+ },
362
+ {
363
+ "epoch": 35.7710843373494,
364
+ "grad_norm": 0.936417548403036,
365
+ "learning_rate": 4.772516337622907e-06,
366
+ "loss": 0.3241081237792969,
367
+ "memory(GiB)": 77.59,
368
+ "step": 36,
369
+ "token_acc": 0.9484973388290848,
370
+ "train_speed(iter/s)": 0.002135
371
+ },
372
+ {
373
+ "epoch": 36.7710843373494,
374
+ "grad_norm": 1.116983283196546,
375
+ "learning_rate": 4.754978075332398e-06,
376
+ "loss": 0.30902814865112305,
377
+ "memory(GiB)": 77.59,
378
+ "step": 37,
379
+ "token_acc": 0.9476456995060315,
380
+ "train_speed(iter/s)": 0.002135
381
+ },
382
+ {
383
+ "epoch": 37.7710843373494,
384
+ "grad_norm": 0.9993160029154087,
385
+ "learning_rate": 4.736823324551909e-06,
386
+ "loss": 0.308858722448349,
387
+ "memory(GiB)": 77.59,
388
+ "step": 38,
389
+ "token_acc": 0.9504927069901695,
390
+ "train_speed(iter/s)": 0.002135
391
+ },
392
+ {
393
+ "epoch": 38.7710843373494,
394
+ "grad_norm": 0.9122824683879396,
395
+ "learning_rate": 4.71805704860903e-06,
396
+ "loss": 0.27843528985977173,
397
+ "memory(GiB)": 77.59,
398
+ "step": 39,
399
+ "token_acc": 0.9496681563352376,
400
+ "train_speed(iter/s)": 0.002136
401
+ },
402
+ {
403
+ "epoch": 39.7710843373494,
404
+ "grad_norm": 1.009388916794573,
405
+ "learning_rate": 4.698684378016223e-06,
406
+ "loss": 0.25660544633865356,
407
+ "memory(GiB)": 77.59,
408
+ "step": 40,
409
+ "token_acc": 0.9552901130798869,
410
+ "train_speed(iter/s)": 0.002137
411
+ },
412
+ {
413
+ "epoch": 40.7710843373494,
414
+ "grad_norm": 1.1895642620511482,
415
+ "learning_rate": 4.678710609068193e-06,
416
+ "loss": 0.2424250692129135,
417
+ "memory(GiB)": 77.59,
418
+ "step": 41,
419
+ "token_acc": 0.9549429605785101,
420
+ "train_speed(iter/s)": 0.002131
421
+ },
422
+ {
423
+ "epoch": 41.7710843373494,
424
+ "grad_norm": 1.1193041843299223,
425
+ "learning_rate": 4.658141202393935e-06,
426
+ "loss": 0.23843874037265778,
427
+ "memory(GiB)": 77.59,
428
+ "step": 42,
429
+ "token_acc": 0.9608553608553608,
430
+ "train_speed(iter/s)": 0.002131
431
+ },
432
+ {
433
+ "epoch": 42.7710843373494,
434
+ "grad_norm": 1.110610217839956,
435
+ "learning_rate": 4.636981781463848e-06,
436
+ "loss": 0.210187166929245,
437
+ "memory(GiB)": 77.59,
438
+ "step": 43,
439
+ "token_acc": 0.9653150186596419,
440
+ "train_speed(iter/s)": 0.002132
441
+ },
442
+ {
443
+ "epoch": 43.7710843373494,
444
+ "grad_norm": 0.8486274696165886,
445
+ "learning_rate": 4.615238131052339e-06,
446
+ "loss": 0.21901345252990723,
447
+ "memory(GiB)": 77.59,
448
+ "step": 44,
449
+ "token_acc": 0.9653416261042005,
450
+ "train_speed(iter/s)": 0.002132
451
+ },
452
+ {
453
+ "epoch": 44.7710843373494,
454
+ "grad_norm": 1.0423804412798912,
455
+ "learning_rate": 4.592916195656322e-06,
456
+ "loss": 0.17482870817184448,
457
+ "memory(GiB)": 77.59,
458
+ "step": 45,
459
+ "token_acc": 0.9674520144027672,
460
+ "train_speed(iter/s)": 0.002133
461
+ },
462
+ {
463
+ "epoch": 45.7710843373494,
464
+ "grad_norm": 1.2841486053816782,
465
+ "learning_rate": 4.570022077870051e-06,
466
+ "loss": 0.18200109899044037,
467
+ "memory(GiB)": 77.59,
468
+ "step": 46,
469
+ "token_acc": 0.9708482572798199,
470
+ "train_speed(iter/s)": 0.002133
471
+ },
472
+ {
473
+ "epoch": 46.7710843373494,
474
+ "grad_norm": 1.172978940255451,
475
+ "learning_rate": 4.546562036716732e-06,
476
+ "loss": 0.15860611200332642,
477
+ "memory(GiB)": 77.59,
478
+ "step": 47,
479
+ "token_acc": 0.9780445141443995,
480
+ "train_speed(iter/s)": 0.002133
481
+ },
482
+ {
483
+ "epoch": 47.7710843373494,
484
+ "grad_norm": 1.2360197347924713,
485
+ "learning_rate": 4.522542485937369e-06,
486
+ "loss": 0.14376184344291687,
487
+ "memory(GiB)": 77.59,
488
+ "step": 48,
489
+ "token_acc": 0.9766241102700259,
490
+ "train_speed(iter/s)": 0.002135
491
+ },
492
+ {
493
+ "epoch": 48.7710843373494,
494
+ "grad_norm": 0.6385686989268172,
495
+ "learning_rate": 4.497969992237312e-06,
496
+ "loss": 0.13206440210342407,
497
+ "memory(GiB)": 77.59,
498
+ "step": 49,
499
+ "token_acc": 0.9818039023693685,
500
+ "train_speed(iter/s)": 0.002135
501
+ },
502
+ {
503
+ "epoch": 49.7710843373494,
504
+ "grad_norm": 1.2901120485113573,
505
+ "learning_rate": 4.472851273490985e-06,
506
+ "loss": 0.11426319181919098,
507
+ "memory(GiB)": 77.59,
508
+ "step": 50,
509
+ "token_acc": 0.9836425932423786,
510
+ "train_speed(iter/s)": 0.002135
511
+ },
512
+ {
513
+ "epoch": 50.7710843373494,
514
+ "grad_norm": 1.2068228907293697,
515
+ "learning_rate": 4.4471931969052816e-06,
516
+ "loss": 0.09582371264696121,
517
+ "memory(GiB)": 77.59,
518
+ "step": 51,
519
+ "token_acc": 0.9849937986991469,
520
+ "train_speed(iter/s)": 0.00213
521
+ },
522
+ {
523
+ "epoch": 51.7710843373494,
524
+ "grad_norm": 1.1813520357475888,
525
+ "learning_rate": 4.421002777142148e-06,
526
+ "loss": 0.09163334965705872,
527
+ "memory(GiB)": 77.59,
528
+ "step": 52,
529
+ "token_acc": 0.985701349843115,
530
+ "train_speed(iter/s)": 0.00213
531
+ },
532
+ {
533
+ "epoch": 52.7710843373494,
534
+ "grad_norm": 1.1122597460598151,
535
+ "learning_rate": 4.394287174400838e-06,
536
+ "loss": 0.08439977467060089,
537
+ "memory(GiB)": 77.59,
538
+ "step": 53,
539
+ "token_acc": 0.9878925052136355,
540
+ "train_speed(iter/s)": 0.00213
541
+ },
542
+ {
543
+ "epoch": 53.7710843373494,
544
+ "grad_norm": 1.1253515530343927,
545
+ "learning_rate": 4.3670536924603855e-06,
546
+ "loss": 0.07314425706863403,
547
+ "memory(GiB)": 77.59,
548
+ "step": 54,
549
+ "token_acc": 0.9900777579782926,
550
+ "train_speed(iter/s)": 0.00213
551
+ },
552
+ {
553
+ "epoch": 54.7710843373494,
554
+ "grad_norm": 1.1033670330706447,
555
+ "learning_rate": 4.33930977668283e-06,
556
+ "loss": 0.06532438099384308,
557
+ "memory(GiB)": 77.59,
558
+ "step": 55,
559
+ "token_acc": 0.9898691656771185,
560
+ "train_speed(iter/s)": 0.00213
561
+ },
562
+ {
563
+ "epoch": 55.7710843373494,
564
+ "grad_norm": 1.1439476751450148,
565
+ "learning_rate": 4.311063011977723e-06,
566
+ "loss": 0.06318923085927963,
567
+ "memory(GiB)": 77.59,
568
+ "step": 56,
569
+ "token_acc": 0.9903093019267052,
570
+ "train_speed(iter/s)": 0.002131
571
+ },
572
+ {
573
+ "epoch": 56.7710843373494,
574
+ "grad_norm": 1.1421545710607997,
575
+ "learning_rate": 4.282321120728493e-06,
576
+ "loss": 0.05167176201939583,
577
+ "memory(GiB)": 77.59,
578
+ "step": 57,
579
+ "token_acc": 0.991860976682798,
580
+ "train_speed(iter/s)": 0.002131
581
+ },
582
+ {
583
+ "epoch": 57.7710843373494,
584
+ "grad_norm": 1.1132394753881205,
585
+ "learning_rate": 4.253091960681222e-06,
586
+ "loss": 0.05162680149078369,
587
+ "memory(GiB)": 77.59,
588
+ "step": 58,
589
+ "token_acc": 0.992666204277479,
590
+ "train_speed(iter/s)": 0.002132
591
+ },
592
+ {
593
+ "epoch": 58.7710843373494,
594
+ "grad_norm": 1.1383077361483038,
595
+ "learning_rate": 4.2233835227964145e-06,
596
+ "loss": 0.044882968068122864,
597
+ "memory(GiB)": 77.59,
598
+ "step": 59,
599
+ "token_acc": 0.9941307654265692,
600
+ "train_speed(iter/s)": 0.002132
601
+ },
602
+ {
603
+ "epoch": 59.7710843373494,
604
+ "grad_norm": 0.9459729284657843,
605
+ "learning_rate": 4.1932039290643534e-06,
606
+ "loss": 0.042324937880039215,
607
+ "memory(GiB)": 77.59,
608
+ "step": 60,
609
+ "token_acc": 0.9941203679909544,
610
+ "train_speed(iter/s)": 0.002132
611
+ }
612
+ ],
613
+ "logging_steps": 1,
614
+ "max_steps": 200,
615
+ "num_input_tokens_seen": 0,
616
+ "num_train_epochs": 200,
617
+ "save_steps": 10,
618
+ "stateful_callbacks": {
619
+ "TrainerControl": {
620
+ "args": {
621
+ "should_epoch_stop": false,
622
+ "should_evaluate": false,
623
+ "should_log": false,
624
+ "should_save": true,
625
+ "should_training_stop": false
626
+ },
627
+ "attributes": {}
628
+ }
629
+ },
630
+ "total_flos": 268227602284544.0,
631
+ "train_batch_size": 1,
632
+ "trial_name": null,
633
+ "trial_params": null
634
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf7ae9cf5b581ae3023deb857a83edd937efe7f8fcced10c2df2ac05ce83e86
3
+ size 8312
vocab.json ADDED
The diff for this file is too large to render. See raw diff