Hugging Face's logo

Tower-Babel
/
Babel-9B

Safetensors
qwen2
multilingual
babel
Model card Files
xet
Community
2
kenchan0226 commited on
Commit
75608c9
·
verified ·
1 Parent(s): f9cdb88

Upload 15 files

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +335 -0
  4. config.json +31 -0
  5. generation_config.json +7 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +418 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +208 -0
  15. trainer_state.json +643 -0
  16. 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 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage1_dlc_32_All_round3_205G_Cont_4e-6_new/v3-20250130-110959/checkpoint-22000",
3
+ "model_type": "qwen2",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "float16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "rope_scaling": null,
10
+ "device_map": null,
11
+ "local_repo_path": null,
12
+ "template": "qwen",
13
+ "system": null,
14
+ "max_length": 4096,
15
+ "truncation_strategy": "delete",
16
+ "max_pixels": null,
17
+ "tools_prompt": "react_en",
18
+ "padding_side": "right",
19
+ "loss_scale": "default",
20
+ "sequence_parallel_size": 1,
21
+ "use_chat_template": false,
22
+ "template_backend": "swift",
23
+ "dataset": [
24
+ "/mnt/workspace/workgroup/workgroup_v100/yiran/Babel_Language_Shuffled_Sampled_1/textbook/merge_all_raw.jsonl"
25
+ ],
26
+ "val_dataset": [],
27
+ "split_dataset_ratio": 0.0,
28
+ "data_seed": 42,
29
+ "dataset_num_proc": 1,
30
+ "streaming": true,
31
+ "enable_cache": false,
32
+ "download_mode": "reuse_dataset_if_exists",
33
+ "strict": false,
34
+ "model_name": [
35
+ null,
36
+ null
37
+ ],
38
+ "model_author": [
39
+ null,
40
+ null
41
+ ],
42
+ "custom_dataset_info": [],
43
+ "quant_method": null,
44
+ "quant_bits": null,
45
+ "hqq_axis": null,
46
+ "bnb_4bit_compute_dtype": "float32",
47
+ "bnb_4bit_quant_type": "nf4",
48
+ "bnb_4bit_use_double_quant": true,
49
+ "bnb_4bit_quant_storage": null,
50
+ "max_new_tokens": 64,
51
+ "temperature": 0.0,
52
+ "top_k": null,
53
+ "top_p": null,
54
+ "repetition_penalty": null,
55
+ "num_beams": 1,
56
+ "stream": false,
57
+ "stop_words": [],
58
+ "logprobs": false,
59
+ "ckpt_dir": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage1_dlc_32_All_round3_205G_Cont_4e-6_new/v3-20250130-110959/checkpoint-22000",
60
+ "load_dataset_config": null,
61
+ "lora_modules": [],
62
+ "tuner_backend": "peft",
63
+ "train_type": "full",
64
+ "adapters": [],
65
+ "seed": 42,
66
+ "model_kwargs": {},
67
+ "load_args": true,
68
+ "load_data_args": false,
69
+ "use_hf": false,
70
+ "hub_token": null,
71
+ "custom_register_path": [],
72
+ "ignore_args_error": false,
73
+ "use_swift_lora": false,
74
+ "output_dir": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage3_32_dlc_2e-6_textbook/v0-20250213-085744",
75
+ "overwrite_output_dir": false,
76
+ "do_train": false,
77
+ "do_eval": false,
78
+ "do_predict": false,
79
+ "eval_strategy": "steps",
80
+ "prediction_loss_only": false,
81
+ "per_device_train_batch_size": 1,
82
+ "per_device_eval_batch_size": 1,
83
+ "per_gpu_train_batch_size": null,
84
+ "per_gpu_eval_batch_size": null,
85
+ "gradient_accumulation_steps": 4,
86
+ "eval_accumulation_steps": null,
87
+ "eval_delay": 0,
88
+ "torch_empty_cache_steps": null,
89
+ "learning_rate": 2e-06,
90
+ "weight_decay": 0.1,
91
+ "adam_beta1": 0.9,
92
+ "adam_beta2": 0.999,
93
+ "adam_epsilon": 1e-08,
94
+ "max_grad_norm": 1.0,
95
+ "num_train_epochs": 1.0,
96
+ "max_steps": 50000,
97
+ "lr_scheduler_type": "cosine",
98
+ "lr_scheduler_kwargs": null,
99
+ "warmup_ratio": 0.1,
100
+ "warmup_steps": 0,
101
+ "log_level": "passive",
102
+ "log_level_replica": "warning",
103
+ "log_on_each_node": true,
104
+ "logging_dir": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage3_32_dlc_2e-6_textbook/v0-20250213-085744/runs",
105
+ "logging_strategy": "steps",
106
+ "logging_first_step": true,
107
+ "logging_steps": 5,
108
+ "logging_nan_inf_filter": true,
109
+ "save_strategy": "steps",
110
+ "save_steps": 100.0,
111
+ "save_total_limit": null,
112
+ "save_safetensors": true,
113
+ "save_on_each_node": false,
114
+ "save_only_model": false,
115
+ "restore_callback_states_from_checkpoint": false,
116
+ "no_cuda": false,
117
+ "use_cpu": false,
118
+ "use_mps_device": false,
119
+ "jit_mode_eval": false,
120
+ "use_ipex": false,
121
+ "bf16": false,
122
+ "fp16": true,
123
+ "fp16_opt_level": "O1",
124
+ "half_precision_backend": "auto",
125
+ "bf16_full_eval": false,
126
+ "fp16_full_eval": false,
127
+ "tf32": null,
128
+ "local_rank": 0,
129
+ "ddp_backend": "nccl",
130
+ "tpu_num_cores": null,
131
+ "tpu_metrics_debug": false,
132
+ "debug": null,
133
+ "dataloader_drop_last": false,
134
+ "eval_steps": 100.0,
135
+ "dataloader_num_workers": 0,
136
+ "dataloader_prefetch_factor": null,
137
+ "past_index": -1,
138
+ "run_name": null,
139
+ "disable_tqdm": null,
140
+ "remove_unused_columns": false,
141
+ "label_names": null,
142
+ "load_best_model_at_end": false,
143
+ "metric_for_best_model": "loss",
144
+ "greater_is_better": false,
145
+ "ignore_data_skip": false,
146
+ "fsdp": "",
147
+ "fsdp_min_num_params": 0,
148
+ "fsdp_config": null,
149
+ "fsdp_transformer_layer_cls_to_wrap": null,
150
+ "accelerator_config": {
151
+ "dispatch_batches": false
152
+ },
153
+ "deepspeed": {
154
+ "fp16": {
155
+ "enabled": "auto",
156
+ "loss_scale": 0,
157
+ "loss_scale_window": 1000,
158
+ "initial_scale_power": 16,
159
+ "hysteresis": 2,
160
+ "min_loss_scale": 1
161
+ },
162
+ "bf16": {
163
+ "enabled": "auto"
164
+ },
165
+ "zero_optimization": {
166
+ "stage": 1,
167
+ "offload_optimizer": {
168
+ "device": "none",
169
+ "pin_memory": true
170
+ },
171
+ "allgather_partitions": true,
172
+ "allgather_bucket_size": 200000000.0,
173
+ "overlap_comm": true,
174
+ "reduce_scatter": true,
175
+ "reduce_bucket_size": 200000000.0,
176
+ "contiguous_gradients": true
177
+ },
178
+ "gradient_accumulation_steps": "auto",
179
+ "gradient_clipping": "auto",
180
+ "steps_per_print": 2000,
181
+ "train_batch_size": "auto",
182
+ "train_micro_batch_size_per_gpu": "auto",
183
+ "wall_clock_breakdown": false
184
+ },
185
+ "label_smoothing_factor": 0.0,
186
+ "optim": "adamw_torch",
187
+ "optim_args": null,
188
+ "adafactor": false,
189
+ "group_by_length": false,
190
+ "length_column_name": "length",
191
+ "report_to": [
192
+ "tensorboard"
193
+ ],
194
+ "ddp_find_unused_parameters": null,
195
+ "ddp_bucket_cap_mb": null,
196
+ "ddp_broadcast_buffers": null,
197
+ "dataloader_pin_memory": true,
198
+ "dataloader_persistent_workers": false,
199
+ "skip_memory_metrics": true,
200
+ "use_legacy_prediction_loop": false,
201
+ "push_to_hub": false,
202
+ "resume_from_checkpoint": null,
203
+ "hub_model_id": null,
204
+ "hub_strategy": "every_save",
205
+ "hub_private_repo": null,
206
+ "hub_always_push": false,
207
+ "gradient_checkpointing": true,
208
+ "gradient_checkpointing_kwargs": null,
209
+ "include_inputs_for_metrics": false,
210
+ "include_for_metrics": [],
211
+ "eval_do_concat_batches": true,
212
+ "fp16_backend": "auto",
213
+ "evaluation_strategy": "steps",
214
+ "push_to_hub_model_id": null,
215
+ "push_to_hub_organization": null,
216
+ "push_to_hub_token": null,
217
+ "mp_parameters": "",
218
+ "auto_find_batch_size": false,
219
+ "full_determinism": false,
220
+ "torchdynamo": null,
221
+ "ray_scope": "last",
222
+ "ddp_timeout": 999999999999,
223
+ "torch_compile": false,
224
+ "torch_compile_backend": null,
225
+ "torch_compile_mode": null,
226
+ "dispatch_batches": null,
227
+ "split_batches": null,
228
+ "include_tokens_per_second": false,
229
+ "include_num_input_tokens_seen": false,
230
+ "neftune_noise_alpha": null,
231
+ "optim_target_modules": null,
232
+ "batch_eval_metrics": false,
233
+ "eval_on_start": false,
234
+ "use_liger_kernel": false,
235
+ "eval_use_gather_object": false,
236
+ "average_tokens_across_devices": false,
237
+ "sortish_sampler": false,
238
+ "predict_with_generate": false,
239
+ "generation_max_length": null,
240
+ "generation_num_beams": null,
241
+ "generation_config": null,
242
+ "freeze_parameters": [],
243
+ "freeze_parameters_ratio": 0.0,
244
+ "trainable_parameters": [],
245
+ "freeze_llm": false,
246
+ "freeze_vit": true,
247
+ "freeze_aligner": true,
248
+ "target_modules": [
249
+ "all-linear"
250
+ ],
251
+ "target_regex": null,
252
+ "modules_to_save": [],
253
+ "lora_rank": 8,
254
+ "lora_alpha": 32,
255
+ "lora_dropout": 0.05,
256
+ "lora_bias": "none",
257
+ "lora_dtype": null,
258
+ "lorap_lr_ratio": null,
259
+ "use_rslora": false,
260
+ "use_dora": false,
261
+ "lora_ga_batch_size": 2,
262
+ "lora_ga_iters": 2,
263
+ "lora_ga_max_length": 1024,
264
+ "lora_ga_direction": "ArB2r",
265
+ "lora_ga_scale": "stable",
266
+ "lora_ga_stable_gamma": 16,
267
+ "init_weights": true,
268
+ "fourier_n_frequency": 2000,
269
+ "fourier_scaling": 300.0,
270
+ "boft_block_size": 4,
271
+ "boft_block_num": 0,
272
+ "boft_n_butterfly_factor": 1,
273
+ "boft_dropout": 0.0,
274
+ "vera_rank": 256,
275
+ "vera_projection_prng_key": 0,
276
+ "vera_dropout": 0.0,
277
+ "vera_d_initial": 0.1,
278
+ "adapter_act": "gelu",
279
+ "adapter_length": 128,
280
+ "use_galore": false,
281
+ "galore_target_modules": null,
282
+ "galore_rank": 128,
283
+ "galore_update_proj_gap": 50,
284
+ "galore_scale": 1.0,
285
+ "galore_proj_type": "std",
286
+ "galore_optim_per_parameter": false,
287
+ "galore_with_embedding": false,
288
+ "galore_quantization": false,
289
+ "galore_proj_quant": false,
290
+ "galore_proj_bits": 4,
291
+ "galore_proj_group_size": 256,
292
+ "galore_cos_threshold": 0.4,
293
+ "galore_gamma_proj": 2,
294
+ "galore_queue_size": 5,
295
+ "adalora_target_r": 8,
296
+ "adalora_init_r": 12,
297
+ "adalora_tinit": 0,
298
+ "adalora_tfinal": 0,
299
+ "adalora_deltaT": 1,
300
+ "adalora_beta1": 0.85,
301
+ "adalora_beta2": 0.85,
302
+ "adalora_orth_reg_weight": 0.5,
303
+ "llamapro_num_new_blocks": 4,
304
+ "llamapro_num_groups": null,
305
+ "lisa_activated_layers": 0,
306
+ "lisa_step_interval": 20,
307
+ "reft_layer_key": null,
308
+ "reft_layers": null,
309
+ "reft_rank": 4,
310
+ "reft_intervention_type": "LoreftIntervention",
311
+ "reft_args": null,
312
+ "use_liger": false,
313
+ "model_layer_cls_name": null,
314
+ "metric_warmup_step": 0,
315
+ "fsdp_num": 1,
316
+ "acc_steps": 1,
317
+ "add_version": true,
318
+ "resume_only_model": false,
319
+ "check_model": true,
320
+ "packing": false,
321
+ "lazy_tokenize": false,
322
+ "loss_type": null,
323
+ "optimizer": null,
324
+ "metric": null,
325
+ "acc_strategy": "token",
326
+ "rank": 0,
327
+ "global_world_size": 32,
328
+ "local_world_size": 8,
329
+ "model_suffix": "checkpoint-22000",
330
+ "model_info": "ModelInfo(model_type='qwen2', model_dir='/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage1_dlc_32_All_round3_205G_Cont_4e-6_new/v3-20250130-110959/checkpoint-22000', torch_dtype=torch.float16, max_model_len=131072, quant_method=None, quant_bits=None, config=None, task_type='causal_lm', num_labels=None)",
331
+ "model_meta": "ModelMeta(model_type='qwen2', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat', hf_model_id='Qwen/Qwen1.5-0.5B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat', hf_model_id='Qwen/Qwen1.5-1.8B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat', hf_model_id='Qwen/Qwen1.5-4B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat', hf_model_id='Qwen/Qwen1.5-7B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat', hf_model_id='Qwen/Qwen1.5-14B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat', hf_model_id='Qwen/Qwen1.5-32B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat', hf_model_id='Qwen/Qwen1.5-72B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat', hf_model_id='Qwen/Qwen1.5-110B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B', hf_model_id='Qwen/Qwen1.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B', hf_model_id='Qwen/Qwen1.5-1.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B', hf_model_id='Qwen/Qwen1.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B', hf_model_id='Qwen/Qwen1.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B', hf_model_id='Qwen/Qwen1.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B', hf_model_id='Qwen/Qwen1.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B', hf_model_id='Qwen/Qwen1.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B', hf_model_id='Qwen/Qwen1.5-110B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-32B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat-GPTQ-Int4', hf_model_id='Qwen/Qwen1.5-110B-Chat-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-4B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-7B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-14B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int8', hf_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-0.5B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-0.5B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-1.8B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-1.8B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-4B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-4B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-7B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-7B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-14B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-14B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-32B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-32B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-72B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-72B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen1.5-110B-Chat-AWQ', hf_model_id='Qwen/Qwen1.5-110B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/CodeQwen1.5-7B', hf_model_id='Qwen/CodeQwen1.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/CodeQwen1.5-7B-Chat', hf_model_id='Qwen/CodeQwen1.5-7B-Chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/CodeQwen1.5-7B-Chat-AWQ', hf_model_id='Qwen/CodeQwen1.5-7B-Chat-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct', hf_model_id='Qwen/Qwen2-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct', hf_model_id='Qwen/Qwen2-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct', hf_model_id='Qwen/Qwen2-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct', hf_model_id='Qwen/Qwen2-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B', hf_model_id='Qwen/Qwen2-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B', hf_model_id='Qwen/Qwen2-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B', hf_model_id='Qwen/Qwen2-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B', hf_model_id='Qwen/Qwen2-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-72B-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-Math-1.5B-Instruct', hf_model_id='Qwen/Qwen2-Math-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-7B-Instruct', hf_model_id='Qwen/Qwen2-Math-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-72B-Instruct', hf_model_id='Qwen/Qwen2-Math-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-1.5B', hf_model_id='Qwen/Qwen2-Math-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-7B', hf_model_id='Qwen/Qwen2-Math-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-Math-72B', hf_model_id='Qwen/Qwen2-Math-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['math']), ModelGroup(models=[Model(ms_model_id='PowerInfer/SmallThinker-3B-Preview', hf_model_id='PowerInfer/SmallThinker-3B-Preview', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f945ddd00d0>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, ignore_patterns=[], requires=['transformers>=4.37'], tags=[])",
332
+ "model_dir": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage1_dlc_32_All_round3_205G_Cont_4e-6_new/v3-20250130-110959/checkpoint-22000",
333
+ "hub": "<class 'swift.hub.hub.MSHub'>",
334
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage3_32_dlc_2e-6_textbook/v0-20250213-085744', 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=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=50000, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage3_32_dlc_2e-6_textbook/v0-20250213-085744/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=False, fp16=True, 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=100, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage3_32_dlc_2e-6_textbook/v0-20250213-085744', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': 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=['tensorboard'], 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', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=999999999999, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='full', optimizer=None, galore_config=None)"
335
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/workspace/workgroup_data/yiran/Train_9.2B_Stage1_dlc_32_All_round3_205G_Cont_4e-6_new/v3-20250130-110959/checkpoint-22000",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 34,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.47.1",
27
+ "use_cache": false,
28
+ "use_mrope": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 152064
31
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 64,
5
+ "pad_token_id": 151643,
6
+ "transformers_version": "4.47.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f0a1a0b437ec723f5e5fe651461577c6b08a4ca7e38b9c0b45a0e9fa98029e
3
+ size 4877660672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda2fbbcb074d90befa010b54cdcffb155640cdab80e7f273f4e23f60ef42070
3
+ size 4932750888
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a08b2ae3eb0b09c6aed271ef0441788b527ee76b64e0dad814299b4dda8aa7
3
+ size 4991495752
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33c279b2c061ef9ffb3f9504ce26e99eb04f43a8232a1784aa770dfb50ee13a
3
+ size 3226065928
model.safetensors.index.json ADDED
@@ -0,0 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18027926528
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
344
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
350
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
353
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
355
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
365
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
367
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
369
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
370
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
372
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
373
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
374
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
376
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
377
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
378
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
379
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
380
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
381
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
386
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
389
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
391
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
393
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
394
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
397
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
398
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
399
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
400
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
401
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
402
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
403
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
404
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
405
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
406
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
407
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
408
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
409
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
410
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
411
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
412
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
413
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
414
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
415
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
416
+ "model.norm.weight": "model-00004-of-00004.safetensors"
417
+ }
418
+ }
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 +1,643 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.006,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2e-05,
13
+ "grad_norm": 1.8784615993499756,
14
+ "learning_rate": 4e-10,
15
+ "loss": 1.247075080871582,
16
+ "memory(GiB)": 45.58,
17
+ "step": 1,
18
+ "token_acc": 0.7174163783160323,
19
+ "train_speed(iter/s)": 0.013609
20
+ },
21
+ {
22
+ "epoch": 0.0001,
23
+ "grad_norm": 1.7829604148864746,
24
+ "learning_rate": 2e-09,
25
+ "loss": 1.2329106330871582,
26
+ "memory(GiB)": 47.68,
27
+ "step": 5,
28
+ "token_acc": 0.7190702324418895,
29
+ "train_speed(iter/s)": 0.056616
30
+ },
31
+ {
32
+ "epoch": 0.0002,
33
+ "grad_norm": 1.8510538339614868,
34
+ "learning_rate": 4e-09,
35
+ "loss": 1.2224847793579101,
36
+ "memory(GiB)": 47.68,
37
+ "step": 10,
38
+ "token_acc": 0.7056490003173596,
39
+ "train_speed(iter/s)": 0.093003
40
+ },
41
+ {
42
+ "epoch": 0.0003,
43
+ "grad_norm": 1.9363449811935425,
44
+ "learning_rate": 5.6e-09,
45
+ "loss": 1.2302563667297364,
46
+ "memory(GiB)": 48.7,
47
+ "step": 15,
48
+ "token_acc": 0.7107342772472836,
49
+ "train_speed(iter/s)": 0.119381
50
+ },
51
+ {
52
+ "epoch": 0.0004,
53
+ "grad_norm": 1.935133695602417,
54
+ "learning_rate": 7.6e-09,
55
+ "loss": 1.2335556983947753,
56
+ "memory(GiB)": 48.7,
57
+ "step": 20,
58
+ "token_acc": 0.7361481714016638,
59
+ "train_speed(iter/s)": 0.137465
60
+ },
61
+ {
62
+ "epoch": 0.0005,
63
+ "grad_norm": 1.7830060720443726,
64
+ "learning_rate": 9.599999999999998e-09,
65
+ "loss": 1.2144426345825194,
66
+ "memory(GiB)": 48.7,
67
+ "step": 25,
68
+ "token_acc": 0.7571428571428571,
69
+ "train_speed(iter/s)": 0.150572
70
+ },
71
+ {
72
+ "epoch": 0.0006,
73
+ "grad_norm": 1.7309236526489258,
74
+ "learning_rate": 1.1599999999999998e-08,
75
+ "loss": 1.2357244491577148,
76
+ "memory(GiB)": 48.7,
77
+ "step": 30,
78
+ "token_acc": 0.7153189910979229,
79
+ "train_speed(iter/s)": 0.162512
80
+ },
81
+ {
82
+ "epoch": 0.0007,
83
+ "grad_norm": 1.7474730014801025,
84
+ "learning_rate": 1.36e-08,
85
+ "loss": 1.231928825378418,
86
+ "memory(GiB)": 48.7,
87
+ "step": 35,
88
+ "token_acc": 0.7078455355582737,
89
+ "train_speed(iter/s)": 0.171663
90
+ },
91
+ {
92
+ "epoch": 0.0008,
93
+ "grad_norm": 1.780007004737854,
94
+ "learning_rate": 1.5599999999999997e-08,
95
+ "loss": 1.2193016052246093,
96
+ "memory(GiB)": 48.7,
97
+ "step": 40,
98
+ "token_acc": 0.6932599724896836,
99
+ "train_speed(iter/s)": 0.178935
100
+ },
101
+ {
102
+ "epoch": 0.0009,
103
+ "grad_norm": 1.723268747329712,
104
+ "learning_rate": 1.72e-08,
105
+ "loss": 1.204256820678711,
106
+ "memory(GiB)": 48.7,
107
+ "step": 45,
108
+ "token_acc": 0.6967172137977004,
109
+ "train_speed(iter/s)": 0.186547
110
+ },
111
+ {
112
+ "epoch": 0.001,
113
+ "grad_norm": 1.7750556468963623,
114
+ "learning_rate": 1.9199999999999997e-08,
115
+ "loss": 1.2007877349853515,
116
+ "memory(GiB)": 48.7,
117
+ "step": 50,
118
+ "token_acc": 0.6921988682295878,
119
+ "train_speed(iter/s)": 0.19125
120
+ },
121
+ {
122
+ "epoch": 0.0011,
123
+ "grad_norm": 1.299729585647583,
124
+ "learning_rate": 2.1199999999999998e-08,
125
+ "loss": 0.8069381713867188,
126
+ "memory(GiB)": 48.7,
127
+ "step": 55,
128
+ "token_acc": 0.7952855847688123,
129
+ "train_speed(iter/s)": 0.195908
130
+ },
131
+ {
132
+ "epoch": 0.0012,
133
+ "grad_norm": 1.3525291681289673,
134
+ "learning_rate": 2.3199999999999996e-08,
135
+ "loss": 0.42714319229125974,
136
+ "memory(GiB)": 48.7,
137
+ "step": 60,
138
+ "token_acc": 0.8841448189762796,
139
+ "train_speed(iter/s)": 0.201
140
+ },
141
+ {
142
+ "epoch": 0.0013,
143
+ "grad_norm": 1.080306053161621,
144
+ "learning_rate": 2.52e-08,
145
+ "loss": 0.4192944526672363,
146
+ "memory(GiB)": 48.7,
147
+ "step": 65,
148
+ "token_acc": 0.8929637526652452,
149
+ "train_speed(iter/s)": 0.204749
150
+ },
151
+ {
152
+ "epoch": 0.0014,
153
+ "grad_norm": 1.177667498588562,
154
+ "learning_rate": 2.72e-08,
155
+ "loss": 0.4133622169494629,
156
+ "memory(GiB)": 48.7,
157
+ "step": 70,
158
+ "token_acc": 0.8836150845253576,
159
+ "train_speed(iter/s)": 0.20853
160
+ },
161
+ {
162
+ "epoch": 0.0015,
163
+ "grad_norm": 1.4200434684753418,
164
+ "learning_rate": 2.92e-08,
165
+ "loss": 0.4155101776123047,
166
+ "memory(GiB)": 48.7,
167
+ "step": 75,
168
+ "token_acc": 0.8933333333333333,
169
+ "train_speed(iter/s)": 0.211872
170
+ },
171
+ {
172
+ "epoch": 0.0016,
173
+ "grad_norm": 1.1931238174438477,
174
+ "learning_rate": 3.1199999999999995e-08,
175
+ "loss": 0.40213637351989745,
176
+ "memory(GiB)": 48.7,
177
+ "step": 80,
178
+ "token_acc": 0.9073569482288828,
179
+ "train_speed(iter/s)": 0.214198
180
+ },
181
+ {
182
+ "epoch": 0.0017,
183
+ "grad_norm": 1.2268942594528198,
184
+ "learning_rate": 3.32e-08,
185
+ "loss": 0.4193448543548584,
186
+ "memory(GiB)": 48.7,
187
+ "step": 85,
188
+ "token_acc": 0.890360895386021,
189
+ "train_speed(iter/s)": 0.217149
190
+ },
191
+ {
192
+ "epoch": 0.0018,
193
+ "grad_norm": 1.168769121170044,
194
+ "learning_rate": 3.52e-08,
195
+ "loss": 0.4069235324859619,
196
+ "memory(GiB)": 48.7,
197
+ "step": 90,
198
+ "token_acc": 0.8803038239916187,
199
+ "train_speed(iter/s)": 0.219373
200
+ },
201
+ {
202
+ "epoch": 0.0019,
203
+ "grad_norm": 1.1890403032302856,
204
+ "learning_rate": 3.7199999999999996e-08,
205
+ "loss": 0.4017478942871094,
206
+ "memory(GiB)": 48.7,
207
+ "step": 95,
208
+ "token_acc": 0.8852933438568797,
209
+ "train_speed(iter/s)": 0.221331
210
+ },
211
+ {
212
+ "epoch": 0.002,
213
+ "grad_norm": 1.0330846309661865,
214
+ "learning_rate": 3.9199999999999994e-08,
215
+ "loss": 0.3853747844696045,
216
+ "memory(GiB)": 48.7,
217
+ "step": 100,
218
+ "token_acc": 0.8942406230784997,
219
+ "train_speed(iter/s)": 0.223547
220
+ },
221
+ {
222
+ "epoch": 0.0021,
223
+ "grad_norm": 0.8882772922515869,
224
+ "learning_rate": 4.12e-08,
225
+ "loss": 0.38479089736938477,
226
+ "memory(GiB)": 48.7,
227
+ "step": 105,
228
+ "token_acc": 0.888404744613895,
229
+ "train_speed(iter/s)": 0.165159
230
+ },
231
+ {
232
+ "epoch": 0.0022,
233
+ "grad_norm": 0.9768219590187073,
234
+ "learning_rate": 4.32e-08,
235
+ "loss": 0.3818492889404297,
236
+ "memory(GiB)": 48.7,
237
+ "step": 110,
238
+ "token_acc": 0.8976019604410993,
239
+ "train_speed(iter/s)": 0.168006
240
+ },
241
+ {
242
+ "epoch": 0.0023,
243
+ "grad_norm": 1.0652796030044556,
244
+ "learning_rate": 4.5199999999999994e-08,
245
+ "loss": 0.37880630493164064,
246
+ "memory(GiB)": 48.7,
247
+ "step": 115,
248
+ "token_acc": 0.8944169293111212,
249
+ "train_speed(iter/s)": 0.170961
250
+ },
251
+ {
252
+ "epoch": 0.0024,
253
+ "grad_norm": 0.9667234420776367,
254
+ "learning_rate": 4.72e-08,
255
+ "loss": 0.3773456573486328,
256
+ "memory(GiB)": 48.7,
257
+ "step": 120,
258
+ "token_acc": 0.9041720990873533,
259
+ "train_speed(iter/s)": 0.17359
260
+ },
261
+ {
262
+ "epoch": 0.0025,
263
+ "grad_norm": 1.1004765033721924,
264
+ "learning_rate": 4.92e-08,
265
+ "loss": 0.37454307079315186,
266
+ "memory(GiB)": 48.7,
267
+ "step": 125,
268
+ "token_acc": 0.8971794358871774,
269
+ "train_speed(iter/s)": 0.17613
270
+ },
271
+ {
272
+ "epoch": 0.0026,
273
+ "grad_norm": 0.9110294580459595,
274
+ "learning_rate": 5.12e-08,
275
+ "loss": 0.35935871601104735,
276
+ "memory(GiB)": 48.7,
277
+ "step": 130,
278
+ "token_acc": 0.9002339927674963,
279
+ "train_speed(iter/s)": 0.178791
280
+ },
281
+ {
282
+ "epoch": 0.0027,
283
+ "grad_norm": 0.8307713270187378,
284
+ "learning_rate": 5.319999999999999e-08,
285
+ "loss": 0.3583024501800537,
286
+ "memory(GiB)": 48.7,
287
+ "step": 135,
288
+ "token_acc": 0.9001166861143524,
289
+ "train_speed(iter/s)": 0.181064
290
+ },
291
+ {
292
+ "epoch": 0.0028,
293
+ "grad_norm": 0.8742683529853821,
294
+ "learning_rate": 5.52e-08,
295
+ "loss": 0.34030709266662595,
296
+ "memory(GiB)": 48.7,
297
+ "step": 140,
298
+ "token_acc": 0.8936170212765957,
299
+ "train_speed(iter/s)": 0.183337
300
+ },
301
+ {
302
+ "epoch": 0.0029,
303
+ "grad_norm": 0.8469884395599365,
304
+ "learning_rate": 5.7199999999999996e-08,
305
+ "loss": 0.3286393404006958,
306
+ "memory(GiB)": 48.7,
307
+ "step": 145,
308
+ "token_acc": 0.9112193294624461,
309
+ "train_speed(iter/s)": 0.185295
310
+ },
311
+ {
312
+ "epoch": 0.003,
313
+ "grad_norm": 0.7903546094894409,
314
+ "learning_rate": 5.92e-08,
315
+ "loss": 0.34013702869415285,
316
+ "memory(GiB)": 48.7,
317
+ "step": 150,
318
+ "token_acc": 0.9123177283192633,
319
+ "train_speed(iter/s)": 0.187277
320
+ },
321
+ {
322
+ "epoch": 0.0031,
323
+ "grad_norm": 0.7647843956947327,
324
+ "learning_rate": 6.119999999999999e-08,
325
+ "loss": 0.32967448234558105,
326
+ "memory(GiB)": 48.7,
327
+ "step": 155,
328
+ "token_acc": 0.9061872909698997,
329
+ "train_speed(iter/s)": 0.189242
330
+ },
331
+ {
332
+ "epoch": 0.0032,
333
+ "grad_norm": 0.7588908076286316,
334
+ "learning_rate": 6.32e-08,
335
+ "loss": 0.31885499954223634,
336
+ "memory(GiB)": 48.7,
337
+ "step": 160,
338
+ "token_acc": 0.9148387096774193,
339
+ "train_speed(iter/s)": 0.190988
340
+ },
341
+ {
342
+ "epoch": 0.0033,
343
+ "grad_norm": 0.7278595566749573,
344
+ "learning_rate": 6.519999999999999e-08,
345
+ "loss": 0.3225527048110962,
346
+ "memory(GiB)": 48.7,
347
+ "step": 165,
348
+ "token_acc": 0.9134559535333979,
349
+ "train_speed(iter/s)": 0.192579
350
+ },
351
+ {
352
+ "epoch": 0.0034,
353
+ "grad_norm": 0.7548233270645142,
354
+ "learning_rate": 6.719999999999999e-08,
355
+ "loss": 0.3111454725265503,
356
+ "memory(GiB)": 48.7,
357
+ "step": 170,
358
+ "token_acc": 0.9035423647678315,
359
+ "train_speed(iter/s)": 0.194372
360
+ },
361
+ {
362
+ "epoch": 0.0035,
363
+ "grad_norm": 0.7382190823554993,
364
+ "learning_rate": 6.92e-08,
365
+ "loss": 0.30791687965393066,
366
+ "memory(GiB)": 48.7,
367
+ "step": 175,
368
+ "token_acc": 0.9182072829131652,
369
+ "train_speed(iter/s)": 0.195886
370
+ },
371
+ {
372
+ "epoch": 0.0036,
373
+ "grad_norm": 0.6201812028884888,
374
+ "learning_rate": 7.12e-08,
375
+ "loss": 0.30755660533905027,
376
+ "memory(GiB)": 48.7,
377
+ "step": 180,
378
+ "token_acc": 0.9121319199057715,
379
+ "train_speed(iter/s)": 0.197365
380
+ },
381
+ {
382
+ "epoch": 0.0037,
383
+ "grad_norm": 0.680054247379303,
384
+ "learning_rate": 7.32e-08,
385
+ "loss": 0.3023200511932373,
386
+ "memory(GiB)": 48.7,
387
+ "step": 185,
388
+ "token_acc": 0.9189243427654024,
389
+ "train_speed(iter/s)": 0.198991
390
+ },
391
+ {
392
+ "epoch": 0.0038,
393
+ "grad_norm": 0.7230331301689148,
394
+ "learning_rate": 7.52e-08,
395
+ "loss": 0.29792306423187254,
396
+ "memory(GiB)": 48.7,
397
+ "step": 190,
398
+ "token_acc": 0.9166977960403436,
399
+ "train_speed(iter/s)": 0.200242
400
+ },
401
+ {
402
+ "epoch": 0.0039,
403
+ "grad_norm": 0.6341392397880554,
404
+ "learning_rate": 7.72e-08,
405
+ "loss": 0.2936398983001709,
406
+ "memory(GiB)": 48.7,
407
+ "step": 195,
408
+ "token_acc": 0.916235294117647,
409
+ "train_speed(iter/s)": 0.20159
410
+ },
411
+ {
412
+ "epoch": 0.004,
413
+ "grad_norm": 0.6513913869857788,
414
+ "learning_rate": 7.920000000000001e-08,
415
+ "loss": 0.29084038734436035,
416
+ "memory(GiB)": 48.7,
417
+ "step": 200,
418
+ "token_acc": 0.915651358950328,
419
+ "train_speed(iter/s)": 0.202853
420
+ },
421
+ {
422
+ "epoch": 0.0041,
423
+ "grad_norm": 0.5849307775497437,
424
+ "learning_rate": 8.119999999999999e-08,
425
+ "loss": 0.28313345909118653,
426
+ "memory(GiB)": 48.7,
427
+ "step": 205,
428
+ "token_acc": 0.9201498422712934,
429
+ "train_speed(iter/s)": 0.174461
430
+ },
431
+ {
432
+ "epoch": 0.0042,
433
+ "grad_norm": 0.5864230990409851,
434
+ "learning_rate": 8.319999999999999e-08,
435
+ "loss": 0.27917160987854006,
436
+ "memory(GiB)": 48.7,
437
+ "step": 210,
438
+ "token_acc": 0.9227850926132559,
439
+ "train_speed(iter/s)": 0.176086
440
+ },
441
+ {
442
+ "epoch": 0.0043,
443
+ "grad_norm": 0.5705774426460266,
444
+ "learning_rate": 8.52e-08,
445
+ "loss": 0.27348690032958983,
446
+ "memory(GiB)": 48.7,
447
+ "step": 215,
448
+ "token_acc": 0.9209313047487321,
449
+ "train_speed(iter/s)": 0.177517
450
+ },
451
+ {
452
+ "epoch": 0.0044,
453
+ "grad_norm": 0.5566577911376953,
454
+ "learning_rate": 8.72e-08,
455
+ "loss": 0.2738009214401245,
456
+ "memory(GiB)": 48.7,
457
+ "step": 220,
458
+ "token_acc": 0.9212003454231433,
459
+ "train_speed(iter/s)": 0.178985
460
+ },
461
+ {
462
+ "epoch": 0.0045,
463
+ "grad_norm": 0.5548610091209412,
464
+ "learning_rate": 8.919999999999999e-08,
465
+ "loss": 0.270387601852417,
466
+ "memory(GiB)": 48.7,
467
+ "step": 225,
468
+ "token_acc": 0.9163515016685205,
469
+ "train_speed(iter/s)": 0.180404
470
+ },
471
+ {
472
+ "epoch": 0.0046,
473
+ "grad_norm": 0.5132172107696533,
474
+ "learning_rate": 9.12e-08,
475
+ "loss": 0.2689182758331299,
476
+ "memory(GiB)": 48.7,
477
+ "step": 230,
478
+ "token_acc": 0.9161837748344371,
479
+ "train_speed(iter/s)": 0.181679
480
+ },
481
+ {
482
+ "epoch": 0.0047,
483
+ "grad_norm": 0.5392292141914368,
484
+ "learning_rate": 9.32e-08,
485
+ "loss": 0.2692979335784912,
486
+ "memory(GiB)": 48.7,
487
+ "step": 235,
488
+ "token_acc": 0.9189686924493554,
489
+ "train_speed(iter/s)": 0.18288
490
+ },
491
+ {
492
+ "epoch": 0.0048,
493
+ "grad_norm": 0.5800856947898865,
494
+ "learning_rate": 9.52e-08,
495
+ "loss": 0.2671097755432129,
496
+ "memory(GiB)": 48.7,
497
+ "step": 240,
498
+ "token_acc": 0.9276693455797933,
499
+ "train_speed(iter/s)": 0.184197
500
+ },
501
+ {
502
+ "epoch": 0.0049,
503
+ "grad_norm": 0.5248638391494751,
504
+ "learning_rate": 9.72e-08,
505
+ "loss": 0.2651660442352295,
506
+ "memory(GiB)": 48.7,
507
+ "step": 245,
508
+ "token_acc": 0.9340950826361967,
509
+ "train_speed(iter/s)": 0.185361
510
+ },
511
+ {
512
+ "epoch": 0.005,
513
+ "grad_norm": 0.4779960811138153,
514
+ "learning_rate": 9.919999999999999e-08,
515
+ "loss": 0.2598712921142578,
516
+ "memory(GiB)": 48.7,
517
+ "step": 250,
518
+ "token_acc": 0.9171786120591582,
519
+ "train_speed(iter/s)": 0.186527
520
+ },
521
+ {
522
+ "epoch": 0.0051,
523
+ "grad_norm": 0.5446517467498779,
524
+ "learning_rate": 1.0119999999999999e-07,
525
+ "loss": 0.2589933633804321,
526
+ "memory(GiB)": 48.7,
527
+ "step": 255,
528
+ "token_acc": 0.919714165615805,
529
+ "train_speed(iter/s)": 0.187704
530
+ },
531
+ {
532
+ "epoch": 0.0052,
533
+ "grad_norm": 0.5014457702636719,
534
+ "learning_rate": 1.032e-07,
535
+ "loss": 0.2622577667236328,
536
+ "memory(GiB)": 48.7,
537
+ "step": 260,
538
+ "token_acc": 0.9149246475449684,
539
+ "train_speed(iter/s)": 0.188846
540
+ },
541
+ {
542
+ "epoch": 0.0053,
543
+ "grad_norm": 0.486289918422699,
544
+ "learning_rate": 1.052e-07,
545
+ "loss": 0.2525398969650269,
546
+ "memory(GiB)": 48.7,
547
+ "step": 265,
548
+ "token_acc": 0.9272396543883583,
549
+ "train_speed(iter/s)": 0.189871
550
+ },
551
+ {
552
+ "epoch": 0.0054,
553
+ "grad_norm": 0.5184631943702698,
554
+ "learning_rate": 1.072e-07,
555
+ "loss": 0.2508587121963501,
556
+ "memory(GiB)": 48.7,
557
+ "step": 270,
558
+ "token_acc": 0.9343525179856115,
559
+ "train_speed(iter/s)": 0.190895
560
+ },
561
+ {
562
+ "epoch": 0.0055,
563
+ "grad_norm": 0.7472315430641174,
564
+ "learning_rate": 1.092e-07,
565
+ "loss": 0.3759446620941162,
566
+ "memory(GiB)": 48.7,
567
+ "step": 275,
568
+ "token_acc": 0.8695306284805091,
569
+ "train_speed(iter/s)": 0.191441
570
+ },
571
+ {
572
+ "epoch": 0.0056,
573
+ "grad_norm": 0.6762179136276245,
574
+ "learning_rate": 1.1119999999999999e-07,
575
+ "loss": 0.5864349365234375,
576
+ "memory(GiB)": 48.7,
577
+ "step": 280,
578
+ "token_acc": 0.8324331623008372,
579
+ "train_speed(iter/s)": 0.191626
580
+ },
581
+ {
582
+ "epoch": 0.0057,
583
+ "grad_norm": 0.5527864694595337,
584
+ "learning_rate": 1.132e-07,
585
+ "loss": 0.5735197067260742,
586
+ "memory(GiB)": 48.7,
587
+ "step": 285,
588
+ "token_acc": 0.8262280306444344,
589
+ "train_speed(iter/s)": 0.19159
590
+ },
591
+ {
592
+ "epoch": 0.0058,
593
+ "grad_norm": 0.46731290221214294,
594
+ "learning_rate": 1.1519999999999999e-07,
595
+ "loss": 0.5600314140319824,
596
+ "memory(GiB)": 48.7,
597
+ "step": 290,
598
+ "token_acc": 0.8467968392868804,
599
+ "train_speed(iter/s)": 0.191504
600
+ },
601
+ {
602
+ "epoch": 0.0059,
603
+ "grad_norm": 0.42628228664398193,
604
+ "learning_rate": 1.1719999999999999e-07,
605
+ "loss": 0.5390614986419677,
606
+ "memory(GiB)": 50.81,
607
+ "step": 295,
608
+ "token_acc": 0.8327679356703104,
609
+ "train_speed(iter/s)": 0.191542
610
+ },
611
+ {
612
+ "epoch": 0.006,
613
+ "grad_norm": 0.3921428322792053,
614
+ "learning_rate": 1.192e-07,
615
+ "loss": 0.5223519325256347,
616
+ "memory(GiB)": 50.81,
617
+ "step": 300,
618
+ "token_acc": 0.8428060564559081,
619
+ "train_speed(iter/s)": 0.191529
620
+ }
621
+ ],
622
+ "logging_steps": 5,
623
+ "max_steps": 50000,
624
+ "num_input_tokens_seen": 0,
625
+ "num_train_epochs": 9223372036854775807,
626
+ "save_steps": 100,
627
+ "stateful_callbacks": {
628
+ "TrainerControl": {
629
+ "args": {
630
+ "should_epoch_stop": false,
631
+ "should_evaluate": false,
632
+ "should_log": false,
633
+ "should_save": true,
634
+ "should_training_stop": false
635
+ },
636
+ "attributes": {}
637
+ }
638
+ },
639
+ "total_flos": 5.573770266594509e+17,
640
+ "train_batch_size": 1,
641
+ "trial_name": null,
642
+ "trial_params": null
643
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff