Hugging Face's logo

Vchitect
/
ShotVL-7B

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
image-to-text
vision-language
cinematography
shotbench
conversational
text-generation-inference
Model card Files
xet
Community
1
Alexislhb commited on
Commit
1f17862
·
verified ·
1 Parent(s): 2594b7e

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +372 -0
  4. chat_template.json +3 -0
  5. config.json +66 -0
  6. generation_config.json +14 -0
  7. merges.txt +0 -0
  8. model-00001-of-00004.safetensors +3 -0
  9. model-00002-of-00004.safetensors +3 -0
  10. model-00003-of-00004.safetensors +3 -0
  11. model-00004-of-00004.safetensors +3 -0
  12. model.safetensors.index.json +736 -0
  13. preprocessor_config.json +19 -0
  14. special_tokens_map.json +31 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +209 -0
  17. trainer_state.json +1724 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/mnt/petrelfs/liuhongbo/Qwen2.5-VL-7B-Instruct",
3
+ "model_type": "qwen2_5_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": "flash_attn",
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "qwen2_5_vl",
15
+ "system": "You are a helpful assistant.",
16
+ "max_length": 2048,
17
+ "truncation_strategy": "delete",
18
+ "max_pixels": null,
19
+ "agent_template": null,
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "default",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "/mnt/petrelfs/liuhongbo/movie_bench/shotdeck_data/sft/img_train_v5_without_reasoning.json",
29
+ "/mnt/petrelfs/liuhongbo/movie_bench/process_video/vid_bench/train_v3_rl_s2_remove_duplicate_refine_2sft.json"
30
+ ],
31
+ "val_dataset": [],
32
+ "split_dataset_ratio": 0.0,
33
+ "data_seed": 42,
34
+ "dataset_num_proc": 1,
35
+ "dataset_shuffle": true,
36
+ "val_dataset_shuffle": false,
37
+ "streaming": false,
38
+ "interleave_prob": null,
39
+ "stopping_strategy": "first_exhausted",
40
+ "shuffle_buffer_size": 1000,
41
+ "enable_cache": false,
42
+ "download_mode": "reuse_dataset_if_exists",
43
+ "columns": {},
44
+ "strict": false,
45
+ "remove_unused_columns": true,
46
+ "model_name": [
47
+ null,
48
+ null
49
+ ],
50
+ "model_author": [
51
+ null,
52
+ null
53
+ ],
54
+ "custom_dataset_info": [],
55
+ "quant_method": null,
56
+ "quant_bits": null,
57
+ "hqq_axis": null,
58
+ "bnb_4bit_compute_dtype": "bfloat16",
59
+ "bnb_4bit_quant_type": "nf4",
60
+ "bnb_4bit_use_double_quant": true,
61
+ "bnb_4bit_quant_storage": null,
62
+ "max_new_tokens": 64,
63
+ "temperature": 0.0,
64
+ "top_k": null,
65
+ "top_p": null,
66
+ "repetition_penalty": null,
67
+ "num_beams": 1,
68
+ "stream": false,
69
+ "stop_words": [],
70
+ "logprobs": false,
71
+ "top_logprobs": null,
72
+ "ckpt_dir": null,
73
+ "load_dataset_config": null,
74
+ "lora_modules": [],
75
+ "tuner_backend": "peft",
76
+ "train_type": "full",
77
+ "adapters": [],
78
+ "external_plugins": [],
79
+ "seed": 42,
80
+ "model_kwargs": {},
81
+ "load_args": false,
82
+ "load_data_args": false,
83
+ "use_hf": false,
84
+ "hub_token": null,
85
+ "custom_register_path": [],
86
+ "ignore_args_error": false,
87
+ "use_swift_lora": false,
88
+ "output_dir": "/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_7B_without_reasoning_wvideo/v1-20250623-155054",
89
+ "overwrite_output_dir": false,
90
+ "do_train": false,
91
+ "do_eval": false,
92
+ "do_predict": false,
93
+ "eval_strategy": "steps",
94
+ "prediction_loss_only": false,
95
+ "per_device_train_batch_size": 1,
96
+ "per_device_eval_batch_size": 1,
97
+ "per_gpu_train_batch_size": null,
98
+ "per_gpu_eval_batch_size": null,
99
+ "gradient_accumulation_steps": 16,
100
+ "eval_accumulation_steps": null,
101
+ "eval_delay": 0,
102
+ "torch_empty_cache_steps": null,
103
+ "learning_rate": 5e-06,
104
+ "weight_decay": 0.1,
105
+ "adam_beta1": 0.9,
106
+ "adam_beta2": 0.95,
107
+ "adam_epsilon": 1e-08,
108
+ "max_grad_norm": 1.0,
109
+ "num_train_epochs": 1.0,
110
+ "max_steps": -1,
111
+ "lr_scheduler_type": "cosine",
112
+ "lr_scheduler_kwargs": null,
113
+ "warmup_ratio": 0.05,
114
+ "warmup_steps": 0,
115
+ "log_level": "passive",
116
+ "log_level_replica": "warning",
117
+ "log_on_each_node": true,
118
+ "logging_dir": "/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_7B_without_reasoning_wvideo/v1-20250623-155054/runs",
119
+ "logging_strategy": "steps",
120
+ "logging_first_step": true,
121
+ "logging_steps": 5,
122
+ "logging_nan_inf_filter": true,
123
+ "save_strategy": "steps",
124
+ "save_steps": 100.0,
125
+ "save_total_limit": 1,
126
+ "save_safetensors": true,
127
+ "save_on_each_node": false,
128
+ "save_only_model": true,
129
+ "restore_callback_states_from_checkpoint": false,
130
+ "no_cuda": false,
131
+ "use_cpu": false,
132
+ "use_mps_device": false,
133
+ "jit_mode_eval": false,
134
+ "use_ipex": false,
135
+ "bf16": true,
136
+ "fp16": false,
137
+ "fp16_opt_level": "O1",
138
+ "half_precision_backend": "auto",
139
+ "bf16_full_eval": false,
140
+ "fp16_full_eval": false,
141
+ "tf32": null,
142
+ "local_rank": 0,
143
+ "ddp_backend": null,
144
+ "tpu_num_cores": null,
145
+ "tpu_metrics_debug": false,
146
+ "debug": null,
147
+ "dataloader_drop_last": false,
148
+ "eval_steps": 100.0,
149
+ "dataloader_num_workers": 4,
150
+ "dataloader_prefetch_factor": null,
151
+ "past_index": -1,
152
+ "run_name": null,
153
+ "disable_tqdm": null,
154
+ "label_names": null,
155
+ "load_best_model_at_end": false,
156
+ "metric_for_best_model": "loss",
157
+ "greater_is_better": false,
158
+ "ignore_data_skip": false,
159
+ "fsdp": "",
160
+ "fsdp_min_num_params": 0,
161
+ "fsdp_config": null,
162
+ "tp_size": 0,
163
+ "fsdp_transformer_layer_cls_to_wrap": null,
164
+ "accelerator_config": {
165
+ "dispatch_batches": false
166
+ },
167
+ "deepspeed": {
168
+ "fp16": {
169
+ "enabled": "auto",
170
+ "loss_scale": 0,
171
+ "loss_scale_window": 1000,
172
+ "initial_scale_power": 16,
173
+ "hysteresis": 2,
174
+ "min_loss_scale": 1
175
+ },
176
+ "bf16": {
177
+ "enabled": "auto"
178
+ },
179
+ "zero_optimization": {
180
+ "stage": 3,
181
+ "offload_optimizer": {
182
+ "device": "none",
183
+ "pin_memory": true
184
+ },
185
+ "offload_param": {
186
+ "device": "none",
187
+ "pin_memory": true
188
+ },
189
+ "overlap_comm": false,
190
+ "contiguous_gradients": true,
191
+ "sub_group_size": 1000000000.0,
192
+ "reduce_bucket_size": "auto",
193
+ "zero_quantized_weights": false,
194
+ "zero_quantized_gradients": false,
195
+ "stage3_prefetch_bucket_size": "auto",
196
+ "stage3_param_persistence_threshold": "auto",
197
+ "stage3_max_live_parameters": 1000000000.0,
198
+ "stage3_max_reuse_distance": 1000000000.0,
199
+ "stage3_gather_16bit_weights_on_model_save": true
200
+ },
201
+ "gradient_accumulation_steps": "auto",
202
+ "gradient_clipping": "auto",
203
+ "steps_per_print": 2000,
204
+ "train_batch_size": "auto",
205
+ "train_micro_batch_size_per_gpu": "auto",
206
+ "wall_clock_breakdown": false
207
+ },
208
+ "label_smoothing_factor": 0.0,
209
+ "optim": "adamw_torch",
210
+ "optim_args": null,
211
+ "adafactor": false,
212
+ "group_by_length": false,
213
+ "length_column_name": "length",
214
+ "report_to": [
215
+ "wandb"
216
+ ],
217
+ "ddp_find_unused_parameters": null,
218
+ "ddp_bucket_cap_mb": null,
219
+ "ddp_broadcast_buffers": null,
220
+ "dataloader_pin_memory": true,
221
+ "dataloader_persistent_workers": false,
222
+ "skip_memory_metrics": true,
223
+ "use_legacy_prediction_loop": false,
224
+ "push_to_hub": false,
225
+ "resume_from_checkpoint": null,
226
+ "hub_model_id": null,
227
+ "hub_strategy": "every_save",
228
+ "hub_private_repo": null,
229
+ "hub_always_push": false,
230
+ "gradient_checkpointing": true,
231
+ "gradient_checkpointing_kwargs": null,
232
+ "include_inputs_for_metrics": false,
233
+ "include_for_metrics": [],
234
+ "eval_do_concat_batches": true,
235
+ "fp16_backend": "auto",
236
+ "evaluation_strategy": "steps",
237
+ "push_to_hub_model_id": null,
238
+ "push_to_hub_organization": null,
239
+ "push_to_hub_token": null,
240
+ "mp_parameters": "",
241
+ "auto_find_batch_size": false,
242
+ "full_determinism": false,
243
+ "torchdynamo": null,
244
+ "ray_scope": "last",
245
+ "ddp_timeout": 1800,
246
+ "torch_compile": false,
247
+ "torch_compile_backend": null,
248
+ "torch_compile_mode": null,
249
+ "dispatch_batches": null,
250
+ "split_batches": null,
251
+ "include_tokens_per_second": false,
252
+ "include_num_input_tokens_seen": false,
253
+ "neftune_noise_alpha": null,
254
+ "optim_target_modules": null,
255
+ "batch_eval_metrics": false,
256
+ "eval_on_start": false,
257
+ "use_liger_kernel": false,
258
+ "eval_use_gather_object": false,
259
+ "average_tokens_across_devices": false,
260
+ "sortish_sampler": false,
261
+ "predict_with_generate": false,
262
+ "generation_max_length": null,
263
+ "generation_num_beams": null,
264
+ "generation_config": null,
265
+ "check_model": true,
266
+ "acc_strategy": "token",
267
+ "train_dataloader_shuffle": true,
268
+ "metric_warmup_step": 0,
269
+ "fsdp_num": 1,
270
+ "acc_steps": 1,
271
+ "eval_use_evalscope": false,
272
+ "eval_datasets": [],
273
+ "eval_limit": null,
274
+ "eval_datasets_args": null,
275
+ "eval_generation_config": null,
276
+ "freeze_parameters": [
277
+ "visual",
278
+ "visual.merger"
279
+ ],
280
+ "freeze_parameters_ratio": 0.0,
281
+ "trainable_parameters": [],
282
+ "freeze_llm": false,
283
+ "freeze_vit": true,
284
+ "freeze_aligner": true,
285
+ "target_modules": [
286
+ "all-linear"
287
+ ],
288
+ "target_regex": null,
289
+ "modules_to_save": [],
290
+ "lora_rank": 8,
291
+ "lora_alpha": 32,
292
+ "lora_dropout": 0.05,
293
+ "lora_bias": "none",
294
+ "lora_dtype": null,
295
+ "lorap_lr_ratio": null,
296
+ "use_rslora": false,
297
+ "use_dora": false,
298
+ "lora_ga_batch_size": 2,
299
+ "lora_ga_iters": 2,
300
+ "lora_ga_max_length": 1024,
301
+ "lora_ga_direction": "ArB2r",
302
+ "lora_ga_scale": "stable",
303
+ "lora_ga_stable_gamma": 16,
304
+ "init_weights": true,
305
+ "fourier_n_frequency": 2000,
306
+ "fourier_scaling": 300.0,
307
+ "boft_block_size": 4,
308
+ "boft_block_num": 0,
309
+ "boft_n_butterfly_factor": 1,
310
+ "boft_dropout": 0.0,
311
+ "vera_rank": 256,
312
+ "vera_projection_prng_key": 0,
313
+ "vera_dropout": 0.0,
314
+ "vera_d_initial": 0.1,
315
+ "adapter_act": "gelu",
316
+ "adapter_length": 128,
317
+ "use_galore": false,
318
+ "galore_target_modules": null,
319
+ "galore_rank": 128,
320
+ "galore_update_proj_gap": 50,
321
+ "galore_scale": 1.0,
322
+ "galore_proj_type": "std",
323
+ "galore_optim_per_parameter": false,
324
+ "galore_with_embedding": false,
325
+ "galore_quantization": false,
326
+ "galore_proj_quant": false,
327
+ "galore_proj_bits": 4,
328
+ "galore_proj_group_size": 256,
329
+ "galore_cos_threshold": 0.4,
330
+ "galore_gamma_proj": 2,
331
+ "galore_queue_size": 5,
332
+ "adalora_target_r": 8,
333
+ "adalora_init_r": 12,
334
+ "adalora_tinit": 0,
335
+ "adalora_tfinal": 0,
336
+ "adalora_deltaT": 1,
337
+ "adalora_beta1": 0.85,
338
+ "adalora_beta2": 0.85,
339
+ "adalora_orth_reg_weight": 0.5,
340
+ "llamapro_num_new_blocks": 4,
341
+ "llamapro_num_groups": null,
342
+ "lisa_activated_layers": 0,
343
+ "lisa_step_interval": 20,
344
+ "reft_layer_key": null,
345
+ "reft_layers": null,
346
+ "reft_rank": 4,
347
+ "reft_intervention_type": "LoreftIntervention",
348
+ "reft_args": null,
349
+ "swanlab_token": null,
350
+ "swanlab_project": null,
351
+ "swanlab_workspace": null,
352
+ "swanlab_exp_name": null,
353
+ "swanlab_mode": "cloud",
354
+ "add_version": true,
355
+ "resume_only_model": false,
356
+ "create_checkpoint_symlink": false,
357
+ "packing": false,
358
+ "lazy_tokenize": true,
359
+ "loss_type": null,
360
+ "optimizer": null,
361
+ "metric": null,
362
+ "zero_hpz_partition_size": null,
363
+ "rank": 0,
364
+ "global_world_size": 4,
365
+ "local_world_size": 4,
366
+ "model_suffix": "Qwen2.5-VL-7B-Instruct",
367
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/petrelfs/liuhongbo/Qwen2.5-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
368
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7f5197320670>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
369
+ "model_dir": "/mnt/petrelfs/liuhongbo/Qwen2.5-VL-7B-Instruct",
370
+ "hub": "<class 'swift.hub.hub.MSHub'>",
371
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_7B_without_reasoning_wvideo/v1-20250623-155054', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, 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=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_7B_without_reasoning_wvideo/v1-20250623-155054/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=1, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_7B_without_reasoning_wvideo/v1-20250623-155054', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], 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=<IntervalStrategy.NO: 'no'>, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
372
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.50.3",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "depth": 32,
40
+ "fullatt_block_indexes": [
41
+ 7,
42
+ 15,
43
+ 23,
44
+ 31
45
+ ],
46
+ "hidden_act": "silu",
47
+ "hidden_size": 1280,
48
+ "in_channels": 3,
49
+ "in_chans": 3,
50
+ "intermediate_size": 3420,
51
+ "model_type": "qwen2_5_vl",
52
+ "num_heads": 16,
53
+ "out_hidden_size": 3584,
54
+ "patch_size": 14,
55
+ "spatial_merge_size": 2,
56
+ "spatial_patch_size": 14,
57
+ "temporal_patch_size": 2,
58
+ "tokens_per_second": 2,
59
+ "torch_dtype": "bfloat16",
60
+ "window_size": 112
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vision_token_id": 151654,
65
+ "vocab_size": 152064
66
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.1,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.50.3"
14
+ }
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:e092af04e4b1cf0427712eb6c65a748026ac404d8c3a1fdc64f9d362fce7ecb5
3
+ size 4968243304
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c427fc3ed4ebf47d1ad246b11321e255f7f4685cd15ddc3efae4f0d5d90c7ac6
3
+ size 4991495816
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3211bb0a7b56a4a330b102d210e31fe084a5f8d721a030e8940c7dfaf4a1e2c4
3
+ size 4932751040
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd744074338b4c2b7b9d6ad3628d03e21bc507498b86c842a1cfb0e02c0836af
3
+ size 1691924384
model.safetensors.index.json ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16584333312
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-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-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-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
734
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
735
+ }
736
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_state.json ADDED
@@ -0,0 +1,1724 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9995543009953944,
6
+ "eval_steps": 100,
7
+ "global_step": 841,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0011885306789481504,
14
+ "grad_norm": 548.1797235189983,
15
+ "learning_rate": 1.1627906976744187e-07,
16
+ "loss": 8.022117614746094,
17
+ "memory(GiB)": 46.35,
18
+ "step": 1,
19
+ "token_acc": 0.16666666666666666,
20
+ "train_speed(iter/s)": 0.035854
21
+ },
22
+ {
23
+ "epoch": 0.005942653394740751,
24
+ "grad_norm": 517.1879841831781,
25
+ "learning_rate": 5.813953488372094e-07,
26
+ "loss": 7.886555194854736,
27
+ "memory(GiB)": 50.11,
28
+ "step": 5,
29
+ "token_acc": 0.14788732394366197,
30
+ "train_speed(iter/s)": 0.064567
31
+ },
32
+ {
33
+ "epoch": 0.011885306789481503,
34
+ "grad_norm": 295.78882511572357,
35
+ "learning_rate": 1.1627906976744188e-06,
36
+ "loss": 6.243068695068359,
37
+ "memory(GiB)": 50.11,
38
+ "step": 10,
39
+ "token_acc": 0.2388888888888889,
40
+ "train_speed(iter/s)": 0.071958
41
+ },
42
+ {
43
+ "epoch": 0.017827960184222256,
44
+ "grad_norm": 12.276341768278998,
45
+ "learning_rate": 1.7441860465116282e-06,
46
+ "loss": 1.707086181640625,
47
+ "memory(GiB)": 50.11,
48
+ "step": 15,
49
+ "token_acc": 0.5085714285714286,
50
+ "train_speed(iter/s)": 0.074777
51
+ },
52
+ {
53
+ "epoch": 0.023770613578963005,
54
+ "grad_norm": 14.766060462541946,
55
+ "learning_rate": 2.3255813953488376e-06,
56
+ "loss": 0.6782948493957519,
57
+ "memory(GiB)": 50.11,
58
+ "step": 20,
59
+ "token_acc": 0.7597765363128491,
60
+ "train_speed(iter/s)": 0.076407
61
+ },
62
+ {
63
+ "epoch": 0.02971326697370376,
64
+ "grad_norm": 14.972149762033396,
65
+ "learning_rate": 2.9069767441860468e-06,
66
+ "loss": 0.5007028579711914,
67
+ "memory(GiB)": 50.11,
68
+ "step": 25,
69
+ "token_acc": 0.7833333333333333,
70
+ "train_speed(iter/s)": 0.077351
71
+ },
72
+ {
73
+ "epoch": 0.03565592036844451,
74
+ "grad_norm": 14.305194685298874,
75
+ "learning_rate": 3.4883720930232564e-06,
76
+ "loss": 0.47702178955078123,
77
+ "memory(GiB)": 50.11,
78
+ "step": 30,
79
+ "token_acc": 0.8111111111111111,
80
+ "train_speed(iter/s)": 0.078111
81
+ },
82
+ {
83
+ "epoch": 0.041598573763185265,
84
+ "grad_norm": 6.111868397462935,
85
+ "learning_rate": 4.0697674418604655e-06,
86
+ "loss": 0.42873945236206057,
87
+ "memory(GiB)": 50.11,
88
+ "step": 35,
89
+ "token_acc": 0.8225806451612904,
90
+ "train_speed(iter/s)": 0.078557
91
+ },
92
+ {
93
+ "epoch": 0.04754122715792601,
94
+ "grad_norm": 8.991713613954735,
95
+ "learning_rate": 4.651162790697675e-06,
96
+ "loss": 0.403080415725708,
97
+ "memory(GiB)": 50.11,
98
+ "step": 40,
99
+ "token_acc": 0.8461538461538461,
100
+ "train_speed(iter/s)": 0.078949
101
+ },
102
+ {
103
+ "epoch": 0.053483880552666764,
104
+ "grad_norm": 4.917565148203119,
105
+ "learning_rate": 4.999922507133964e-06,
106
+ "loss": 0.37815165519714355,
107
+ "memory(GiB)": 50.11,
108
+ "step": 45,
109
+ "token_acc": 0.8789473684210526,
110
+ "train_speed(iter/s)": 0.07932
111
+ },
112
+ {
113
+ "epoch": 0.05942653394740752,
114
+ "grad_norm": 11.989491241774688,
115
+ "learning_rate": 4.999050767562379e-06,
116
+ "loss": 0.3381024360656738,
117
+ "memory(GiB)": 50.11,
118
+ "step": 50,
119
+ "token_acc": 0.8735632183908046,
120
+ "train_speed(iter/s)": 0.079547
121
+ },
122
+ {
123
+ "epoch": 0.06536918734214826,
124
+ "grad_norm": 6.777839360520193,
125
+ "learning_rate": 4.99721076122146e-06,
126
+ "loss": 0.3407719135284424,
127
+ "memory(GiB)": 50.11,
128
+ "step": 55,
129
+ "token_acc": 0.8579234972677595,
130
+ "train_speed(iter/s)": 0.079765
131
+ },
132
+ {
133
+ "epoch": 0.07131184073688902,
134
+ "grad_norm": 6.139296584815925,
135
+ "learning_rate": 4.994403201028695e-06,
136
+ "loss": 0.33808121681213377,
137
+ "memory(GiB)": 50.11,
138
+ "step": 60,
139
+ "token_acc": 0.8743455497382199,
140
+ "train_speed(iter/s)": 0.079935
141
+ },
142
+ {
143
+ "epoch": 0.07725449413162977,
144
+ "grad_norm": 5.890787284633843,
145
+ "learning_rate": 4.990629174784009e-06,
146
+ "loss": 0.3293055295944214,
147
+ "memory(GiB)": 50.11,
148
+ "step": 65,
149
+ "token_acc": 0.898936170212766,
150
+ "train_speed(iter/s)": 0.080067
151
+ },
152
+ {
153
+ "epoch": 0.08319714752637053,
154
+ "grad_norm": 10.931767446162842,
155
+ "learning_rate": 4.9858901447482924e-06,
156
+ "loss": 0.3187825679779053,
157
+ "memory(GiB)": 50.11,
158
+ "step": 70,
159
+ "token_acc": 0.8478260869565217,
160
+ "train_speed(iter/s)": 0.080169
161
+ },
162
+ {
163
+ "epoch": 0.08913980092111128,
164
+ "grad_norm": 10.824836091859028,
165
+ "learning_rate": 4.980187947076841e-06,
166
+ "loss": 0.34889607429504393,
167
+ "memory(GiB)": 50.11,
168
+ "step": 75,
169
+ "token_acc": 0.8495145631067961,
170
+ "train_speed(iter/s)": 0.08027
171
+ },
172
+ {
173
+ "epoch": 0.09508245431585202,
174
+ "grad_norm": 6.620646988752802,
175
+ "learning_rate": 4.973524791107931e-06,
176
+ "loss": 0.3007768154144287,
177
+ "memory(GiB)": 50.11,
178
+ "step": 80,
179
+ "token_acc": 0.8418079096045198,
180
+ "train_speed(iter/s)": 0.080366
181
+ },
182
+ {
183
+ "epoch": 0.10102510771059278,
184
+ "grad_norm": 9.519794919805669,
185
+ "learning_rate": 4.965903258506806e-06,
186
+ "loss": 0.34135324954986573,
187
+ "memory(GiB)": 50.11,
188
+ "step": 85,
189
+ "token_acc": 0.8839779005524862,
190
+ "train_speed(iter/s)": 0.080443
191
+ },
192
+ {
193
+ "epoch": 0.10696776110533353,
194
+ "grad_norm": 8.719690644097742,
195
+ "learning_rate": 4.957326302265395e-06,
196
+ "loss": 0.31029839515686036,
197
+ "memory(GiB)": 50.11,
198
+ "step": 90,
199
+ "token_acc": 0.8924731182795699,
200
+ "train_speed(iter/s)": 0.080511
201
+ },
202
+ {
203
+ "epoch": 0.11291041450007429,
204
+ "grad_norm": 7.358059720333543,
205
+ "learning_rate": 4.947797245558168e-06,
206
+ "loss": 0.3377894639968872,
207
+ "memory(GiB)": 50.11,
208
+ "step": 95,
209
+ "token_acc": 0.8789473684210526,
210
+ "train_speed(iter/s)": 0.080597
211
+ },
212
+ {
213
+ "epoch": 0.11885306789481503,
214
+ "grad_norm": 4.938431225494223,
215
+ "learning_rate": 4.937319780454559e-06,
216
+ "loss": 0.31557579040527345,
217
+ "memory(GiB)": 50.11,
218
+ "step": 100,
219
+ "token_acc": 0.8663101604278075,
220
+ "train_speed(iter/s)": 0.080572
221
+ },
222
+ {
223
+ "epoch": 0.12479572128955578,
224
+ "grad_norm": 7.518639654198759,
225
+ "learning_rate": 4.9258979664884595e-06,
226
+ "loss": 0.3270684242248535,
227
+ "memory(GiB)": 50.11,
228
+ "step": 105,
229
+ "token_acc": 0.8390804597701149,
230
+ "train_speed(iter/s)": 0.077371
231
+ },
232
+ {
233
+ "epoch": 0.13073837468429653,
234
+ "grad_norm": 5.275542865372311,
235
+ "learning_rate": 4.9135362290853365e-06,
236
+ "loss": 0.3212160348892212,
237
+ "memory(GiB)": 50.11,
238
+ "step": 110,
239
+ "token_acc": 0.8793103448275862,
240
+ "train_speed(iter/s)": 0.077562
241
+ },
242
+ {
243
+ "epoch": 0.1366810280790373,
244
+ "grad_norm": 5.256523302626162,
245
+ "learning_rate": 4.900239357847582e-06,
246
+ "loss": 0.32684850692749023,
247
+ "memory(GiB)": 50.11,
248
+ "step": 115,
249
+ "token_acc": 0.8659217877094972,
250
+ "train_speed(iter/s)": 0.077745
251
+ },
252
+ {
253
+ "epoch": 0.14262368147377805,
254
+ "grad_norm": 6.9956864362318925,
255
+ "learning_rate": 4.886012504698769e-06,
256
+ "loss": 0.3396021842956543,
257
+ "memory(GiB)": 50.11,
258
+ "step": 120,
259
+ "token_acc": 0.8314606741573034,
260
+ "train_speed(iter/s)": 0.077907
261
+ },
262
+ {
263
+ "epoch": 0.1485663348685188,
264
+ "grad_norm": 8.220091525088554,
265
+ "learning_rate": 4.870861181887514e-06,
266
+ "loss": 0.2878549575805664,
267
+ "memory(GiB)": 50.11,
268
+ "step": 125,
269
+ "token_acc": 0.867816091954023,
270
+ "train_speed(iter/s)": 0.078077
271
+ },
272
+ {
273
+ "epoch": 0.15450898826325954,
274
+ "grad_norm": 9.001408898309402,
275
+ "learning_rate": 4.854791259851735e-06,
276
+ "loss": 0.28747098445892333,
277
+ "memory(GiB)": 50.11,
278
+ "step": 130,
279
+ "token_acc": 0.9010416666666666,
280
+ "train_speed(iter/s)": 0.078215
281
+ },
282
+ {
283
+ "epoch": 0.1604516416580003,
284
+ "grad_norm": 9.115366763265595,
285
+ "learning_rate": 4.8378089649441355e-06,
286
+ "loss": 0.37898375988006594,
287
+ "memory(GiB)": 50.11,
288
+ "step": 135,
289
+ "token_acc": 0.8135593220338984,
290
+ "train_speed(iter/s)": 0.078346
291
+ },
292
+ {
293
+ "epoch": 0.16639429505274106,
294
+ "grad_norm": 6.196127668973169,
295
+ "learning_rate": 4.819920877019767e-06,
296
+ "loss": 0.3501492977142334,
297
+ "memory(GiB)": 50.11,
298
+ "step": 140,
299
+ "token_acc": 0.824468085106383,
300
+ "train_speed(iter/s)": 0.078454
301
+ },
302
+ {
303
+ "epoch": 0.1723369484474818,
304
+ "grad_norm": 6.007338381318857,
305
+ "learning_rate": 4.8011339268866505e-06,
306
+ "loss": 0.322367000579834,
307
+ "memory(GiB)": 50.11,
308
+ "step": 145,
309
+ "token_acc": 0.8932584269662921,
310
+ "train_speed(iter/s)": 0.07857
311
+ },
312
+ {
313
+ "epoch": 0.17827960184222255,
314
+ "grad_norm": 4.125624729653197,
315
+ "learning_rate": 4.781455393620407e-06,
316
+ "loss": 0.3071049690246582,
317
+ "memory(GiB)": 50.11,
318
+ "step": 150,
319
+ "token_acc": 0.8461538461538461,
320
+ "train_speed(iter/s)": 0.078684
321
+ },
322
+ {
323
+ "epoch": 0.1842222552369633,
324
+ "grad_norm": 6.3546672576711085,
325
+ "learning_rate": 4.760892901743944e-06,
326
+ "loss": 0.28942744731903075,
327
+ "memory(GiB)": 50.11,
328
+ "step": 155,
329
+ "token_acc": 0.868020304568528,
330
+ "train_speed(iter/s)": 0.078783
331
+ },
332
+ {
333
+ "epoch": 0.19016490863170404,
334
+ "grad_norm": 6.332293006494747,
335
+ "learning_rate": 4.739454418273314e-06,
336
+ "loss": 0.2908078908920288,
337
+ "memory(GiB)": 50.11,
338
+ "step": 160,
339
+ "token_acc": 0.8160919540229885,
340
+ "train_speed(iter/s)": 0.07888
341
+ },
342
+ {
343
+ "epoch": 0.1961075620264448,
344
+ "grad_norm": 7.334991420256453,
345
+ "learning_rate": 4.717148249630859e-06,
346
+ "loss": 0.30244882106781007,
347
+ "memory(GiB)": 50.11,
348
+ "step": 165,
349
+ "token_acc": 0.9,
350
+ "train_speed(iter/s)": 0.078938
351
+ },
352
+ {
353
+ "epoch": 0.20205021542118556,
354
+ "grad_norm": 5.66996373194292,
355
+ "learning_rate": 4.693983038426857e-06,
356
+ "loss": 0.26120476722717284,
357
+ "memory(GiB)": 50.11,
358
+ "step": 170,
359
+ "token_acc": 0.9022988505747126,
360
+ "train_speed(iter/s)": 0.079018
361
+ },
362
+ {
363
+ "epoch": 0.20799286881592632,
364
+ "grad_norm": 5.485146565073312,
365
+ "learning_rate": 4.669967760110908e-06,
366
+ "loss": 0.3136150360107422,
367
+ "memory(GiB)": 50.11,
368
+ "step": 175,
369
+ "token_acc": 0.875,
370
+ "train_speed(iter/s)": 0.079091
371
+ },
372
+ {
373
+ "epoch": 0.21393552221066706,
374
+ "grad_norm": 4.790229015417923,
375
+ "learning_rate": 4.645111719494363e-06,
376
+ "loss": 0.31197218894958495,
377
+ "memory(GiB)": 50.11,
378
+ "step": 180,
379
+ "token_acc": 0.8707865168539326,
380
+ "train_speed(iter/s)": 0.079157
381
+ },
382
+ {
383
+ "epoch": 0.21987817560540782,
384
+ "grad_norm": 3.9788813029239924,
385
+ "learning_rate": 4.6194245471451395e-06,
386
+ "loss": 0.29698636531829836,
387
+ "memory(GiB)": 50.11,
388
+ "step": 185,
389
+ "token_acc": 0.8829787234042553,
390
+ "train_speed(iter/s)": 0.079217
391
+ },
392
+ {
393
+ "epoch": 0.22582082900014858,
394
+ "grad_norm": 5.38043307053944,
395
+ "learning_rate": 4.592916195656322e-06,
396
+ "loss": 0.3022609233856201,
397
+ "memory(GiB)": 50.11,
398
+ "step": 190,
399
+ "token_acc": 0.8870967741935484,
400
+ "train_speed(iter/s)": 0.079283
401
+ },
402
+ {
403
+ "epoch": 0.2317634823948893,
404
+ "grad_norm": 5.706060180746966,
405
+ "learning_rate": 4.565596935789987e-06,
406
+ "loss": 0.28669142723083496,
407
+ "memory(GiB)": 50.11,
408
+ "step": 195,
409
+ "token_acc": 0.8837209302325582,
410
+ "train_speed(iter/s)": 0.079339
411
+ },
412
+ {
413
+ "epoch": 0.23770613578963007,
414
+ "grad_norm": 4.399286357383267,
415
+ "learning_rate": 4.537477352497766e-06,
416
+ "loss": 0.27329254150390625,
417
+ "memory(GiB)": 50.11,
418
+ "step": 200,
419
+ "token_acc": 0.9301075268817204,
420
+ "train_speed(iter/s)": 0.079333
421
+ },
422
+ {
423
+ "epoch": 0.24364878918437083,
424
+ "grad_norm": 2.7396674582431135,
425
+ "learning_rate": 4.508568340819654e-06,
426
+ "loss": 0.30466504096984864,
427
+ "memory(GiB)": 50.11,
428
+ "step": 205,
429
+ "token_acc": 0.875,
430
+ "train_speed(iter/s)": 0.077513
431
+ },
432
+ {
433
+ "epoch": 0.24959144257911156,
434
+ "grad_norm": 6.688114488293933,
435
+ "learning_rate": 4.478881101662694e-06,
436
+ "loss": 0.2621138095855713,
437
+ "memory(GiB)": 50.11,
438
+ "step": 210,
439
+ "token_acc": 0.8810810810810811,
440
+ "train_speed(iter/s)": 0.077595
441
+ },
442
+ {
443
+ "epoch": 0.25553409597385235,
444
+ "grad_norm": 5.255888806481665,
445
+ "learning_rate": 4.44842713746114e-06,
446
+ "loss": 0.28530049324035645,
447
+ "memory(GiB)": 50.11,
448
+ "step": 215,
449
+ "token_acc": 0.9065934065934066,
450
+ "train_speed(iter/s)": 0.07769
451
+ },
452
+ {
453
+ "epoch": 0.26147674936859305,
454
+ "grad_norm": 3.91726058342407,
455
+ "learning_rate": 4.417218247719794e-06,
456
+ "loss": 0.31370389461517334,
457
+ "memory(GiB)": 50.11,
458
+ "step": 220,
459
+ "token_acc": 0.9130434782608695,
460
+ "train_speed(iter/s)": 0.077784
461
+ },
462
+ {
463
+ "epoch": 0.2674194027633338,
464
+ "grad_norm": 5.422963885256581,
465
+ "learning_rate": 4.385266524442241e-06,
466
+ "loss": 0.2774806499481201,
467
+ "memory(GiB)": 50.11,
468
+ "step": 225,
469
+ "token_acc": 0.8681318681318682,
470
+ "train_speed(iter/s)": 0.077873
471
+ },
472
+ {
473
+ "epoch": 0.2733620561580746,
474
+ "grad_norm": 6.722879151062824,
475
+ "learning_rate": 4.352584347445761e-06,
476
+ "loss": 0.2985124111175537,
477
+ "memory(GiB)": 50.11,
478
+ "step": 230,
479
+ "token_acc": 0.8736263736263736,
480
+ "train_speed(iter/s)": 0.077946
481
+ },
482
+ {
483
+ "epoch": 0.27930470955281533,
484
+ "grad_norm": 6.4224195510449285,
485
+ "learning_rate": 4.319184379564716e-06,
486
+ "loss": 0.28224008083343505,
487
+ "memory(GiB)": 50.11,
488
+ "step": 235,
489
+ "token_acc": 0.8839779005524862,
490
+ "train_speed(iter/s)": 0.077999
491
+ },
492
+ {
493
+ "epoch": 0.2852473629475561,
494
+ "grad_norm": 10.728017343540358,
495
+ "learning_rate": 4.285079561744292e-06,
496
+ "loss": 0.315199875831604,
497
+ "memory(GiB)": 50.11,
498
+ "step": 240,
499
+ "token_acc": 0.86,
500
+ "train_speed(iter/s)": 0.07806
501
+ },
502
+ {
503
+ "epoch": 0.29119001634229685,
504
+ "grad_norm": 3.5104593820561916,
505
+ "learning_rate": 4.250283108026474e-06,
506
+ "loss": 0.28578615188598633,
507
+ "memory(GiB)": 50.11,
508
+ "step": 245,
509
+ "token_acc": 0.8715083798882681,
510
+ "train_speed(iter/s)": 0.078121
511
+ },
512
+ {
513
+ "epoch": 0.2971326697370376,
514
+ "grad_norm": 12.24592817826425,
515
+ "learning_rate": 4.2148085004302205e-06,
516
+ "loss": 0.3042537927627563,
517
+ "memory(GiB)": 50.11,
518
+ "step": 250,
519
+ "token_acc": 0.8556149732620321,
520
+ "train_speed(iter/s)": 0.078192
521
+ },
522
+ {
523
+ "epoch": 0.3030753231317783,
524
+ "grad_norm": 5.395962132144766,
525
+ "learning_rate": 4.178669483727803e-06,
526
+ "loss": 0.32353897094726564,
527
+ "memory(GiB)": 50.11,
528
+ "step": 255,
529
+ "token_acc": 0.9037433155080213,
530
+ "train_speed(iter/s)": 0.078259
531
+ },
532
+ {
533
+ "epoch": 0.3090179765265191,
534
+ "grad_norm": 10.569254917118544,
535
+ "learning_rate": 4.141880060119336e-06,
536
+ "loss": 0.2870334148406982,
537
+ "memory(GiB)": 50.11,
538
+ "step": 260,
539
+ "token_acc": 0.8461538461538461,
540
+ "train_speed(iter/s)": 0.078334
541
+ },
542
+ {
543
+ "epoch": 0.31496062992125984,
544
+ "grad_norm": 8.563532881846635,
545
+ "learning_rate": 4.104454483807579e-06,
546
+ "loss": 0.2994786262512207,
547
+ "memory(GiB)": 50.11,
548
+ "step": 265,
549
+ "token_acc": 0.9144385026737968,
550
+ "train_speed(iter/s)": 0.078387
551
+ },
552
+ {
553
+ "epoch": 0.3209032833160006,
554
+ "grad_norm": 6.750118253503608,
555
+ "learning_rate": 4.066407255475086e-06,
556
+ "loss": 0.2697244644165039,
557
+ "memory(GiB)": 50.11,
558
+ "step": 270,
559
+ "token_acc": 0.8956043956043956,
560
+ "train_speed(iter/s)": 0.078439
561
+ },
562
+ {
563
+ "epoch": 0.32684593671074136,
564
+ "grad_norm": 3.934344456524906,
565
+ "learning_rate": 4.027753116665859e-06,
566
+ "loss": 0.2338794946670532,
567
+ "memory(GiB)": 50.11,
568
+ "step": 275,
569
+ "token_acc": 0.9405405405405406,
570
+ "train_speed(iter/s)": 0.078498
571
+ },
572
+ {
573
+ "epoch": 0.3327885901054821,
574
+ "grad_norm": 5.970848924895414,
575
+ "learning_rate": 3.988507044073687e-06,
576
+ "loss": 0.28338768482208254,
577
+ "memory(GiB)": 50.11,
578
+ "step": 280,
579
+ "token_acc": 0.8804347826086957,
580
+ "train_speed(iter/s)": 0.078559
581
+ },
582
+ {
583
+ "epoch": 0.3387312435002228,
584
+ "grad_norm": 3.9146270439627364,
585
+ "learning_rate": 3.948684243739366e-06,
586
+ "loss": 0.2838298797607422,
587
+ "memory(GiB)": 50.11,
588
+ "step": 285,
589
+ "token_acc": 0.8797814207650273,
590
+ "train_speed(iter/s)": 0.078615
591
+ },
592
+ {
593
+ "epoch": 0.3446738968949636,
594
+ "grad_norm": 9.327297524134098,
595
+ "learning_rate": 3.908300145159055e-06,
596
+ "loss": 0.2870032787322998,
597
+ "memory(GiB)": 50.11,
598
+ "step": 290,
599
+ "token_acc": 0.8707865168539326,
600
+ "train_speed(iter/s)": 0.078663
601
+ },
602
+ {
603
+ "epoch": 0.35061655028970434,
604
+ "grad_norm": 6.335507218560851,
605
+ "learning_rate": 3.8673703953060685e-06,
606
+ "loss": 0.278945779800415,
607
+ "memory(GiB)": 50.11,
608
+ "step": 295,
609
+ "token_acc": 0.8994413407821229,
610
+ "train_speed(iter/s)": 0.078706
611
+ },
612
+ {
613
+ "epoch": 0.3565592036844451,
614
+ "grad_norm": 3.6244644464198563,
615
+ "learning_rate": 3.8259108525683854e-06,
616
+ "loss": 0.2880126953125,
617
+ "memory(GiB)": 50.11,
618
+ "step": 300,
619
+ "token_acc": 0.8770949720670391,
620
+ "train_speed(iter/s)": 0.07875
621
+ },
622
+ {
623
+ "epoch": 0.36250185707918586,
624
+ "grad_norm": 9.73665571895264,
625
+ "learning_rate": 3.7839375806042672e-06,
626
+ "loss": 0.3021416187286377,
627
+ "memory(GiB)": 50.11,
628
+ "step": 305,
629
+ "token_acc": 0.8829787234042553,
630
+ "train_speed(iter/s)": 0.077565
631
+ },
632
+ {
633
+ "epoch": 0.3684445104739266,
634
+ "grad_norm": 4.111562074991708,
635
+ "learning_rate": 3.741466842118327e-06,
636
+ "loss": 0.24168176651000978,
637
+ "memory(GiB)": 50.11,
638
+ "step": 310,
639
+ "token_acc": 0.9135135135135135,
640
+ "train_speed(iter/s)": 0.077626
641
+ },
642
+ {
643
+ "epoch": 0.3743871638686674,
644
+ "grad_norm": 5.628251208959277,
645
+ "learning_rate": 3.698515092560481e-06,
646
+ "loss": 0.28665938377380373,
647
+ "memory(GiB)": 50.11,
648
+ "step": 315,
649
+ "token_acc": 0.8978494623655914,
650
+ "train_speed(iter/s)": 0.07769
651
+ },
652
+ {
653
+ "epoch": 0.3803298172634081,
654
+ "grad_norm": 3.2364463841026265,
655
+ "learning_rate": 3.655098973750223e-06,
656
+ "loss": 0.2696410894393921,
657
+ "memory(GiB)": 50.11,
658
+ "step": 320,
659
+ "token_acc": 0.9034090909090909,
660
+ "train_speed(iter/s)": 0.077754
661
+ },
662
+ {
663
+ "epoch": 0.38627247065814885,
664
+ "grad_norm": 6.612958655073718,
665
+ "learning_rate": 3.61123530742869e-06,
666
+ "loss": 0.26622281074523924,
667
+ "memory(GiB)": 50.11,
668
+ "step": 325,
669
+ "token_acc": 0.9080459770114943,
670
+ "train_speed(iter/s)": 0.077814
671
+ },
672
+ {
673
+ "epoch": 0.3922151240528896,
674
+ "grad_norm": 3.3735858832830448,
675
+ "learning_rate": 3.5669410887410095e-06,
676
+ "loss": 0.28887372016906737,
677
+ "memory(GiB)": 50.11,
678
+ "step": 330,
679
+ "token_acc": 0.9055555555555556,
680
+ "train_speed(iter/s)": 0.077876
681
+ },
682
+ {
683
+ "epoch": 0.39815777744763037,
684
+ "grad_norm": 2.3741384793834066,
685
+ "learning_rate": 3.5222334796514724e-06,
686
+ "loss": 0.27968392372131345,
687
+ "memory(GiB)": 50.11,
688
+ "step": 335,
689
+ "token_acc": 0.88268156424581,
690
+ "train_speed(iter/s)": 0.077927
691
+ },
692
+ {
693
+ "epoch": 0.40410043084237113,
694
+ "grad_norm": 4.628193650632556,
695
+ "learning_rate": 3.477129802294057e-06,
696
+ "loss": 0.3233078956604004,
697
+ "memory(GiB)": 50.11,
698
+ "step": 340,
699
+ "token_acc": 0.8111111111111111,
700
+ "train_speed(iter/s)": 0.077985
701
+ },
702
+ {
703
+ "epoch": 0.4100430842371119,
704
+ "grad_norm": 5.86802322326311,
705
+ "learning_rate": 3.431647532260908e-06,
706
+ "loss": 0.2708756923675537,
707
+ "memory(GiB)": 50.11,
708
+ "step": 345,
709
+ "token_acc": 0.9037433155080213,
710
+ "train_speed(iter/s)": 0.078049
711
+ },
712
+ {
713
+ "epoch": 0.41598573763185265,
714
+ "grad_norm": 3.7680564123531686,
715
+ "learning_rate": 3.385804291831347e-06,
716
+ "loss": 0.28063795566558836,
717
+ "memory(GiB)": 50.11,
718
+ "step": 350,
719
+ "token_acc": 0.8846153846153846,
720
+ "train_speed(iter/s)": 0.078093
721
+ },
722
+ {
723
+ "epoch": 0.42192839102659335,
724
+ "grad_norm": 3.5932738811910006,
725
+ "learning_rate": 3.3396178431440572e-06,
726
+ "loss": 0.25298926830291746,
727
+ "memory(GiB)": 50.11,
728
+ "step": 355,
729
+ "token_acc": 0.9010989010989011,
730
+ "train_speed(iter/s)": 0.078147
731
+ },
732
+ {
733
+ "epoch": 0.4278710444213341,
734
+ "grad_norm": 8.287812705069305,
735
+ "learning_rate": 3.2931060813150685e-06,
736
+ "loss": 0.27823238372802733,
737
+ "memory(GiB)": 50.11,
738
+ "step": 360,
739
+ "token_acc": 0.8804347826086957,
740
+ "train_speed(iter/s)": 0.0782
741
+ },
742
+ {
743
+ "epoch": 0.4338136978160749,
744
+ "grad_norm": 5.939778148959477,
745
+ "learning_rate": 3.246287027504237e-06,
746
+ "loss": 0.23206405639648436,
747
+ "memory(GiB)": 50.11,
748
+ "step": 365,
749
+ "token_acc": 0.90625,
750
+ "train_speed(iter/s)": 0.07825
751
+ },
752
+ {
753
+ "epoch": 0.43975635121081563,
754
+ "grad_norm": 3.9285461219783153,
755
+ "learning_rate": 3.1991788219328657e-06,
756
+ "loss": 0.24766221046447753,
757
+ "memory(GiB)": 50.11,
758
+ "step": 370,
759
+ "token_acc": 0.9069767441860465,
760
+ "train_speed(iter/s)": 0.078298
761
+ },
762
+ {
763
+ "epoch": 0.4456990046055564,
764
+ "grad_norm": 3.484393370769258,
765
+ "learning_rate": 3.151799716855215e-06,
766
+ "loss": 0.2592806339263916,
767
+ "memory(GiB)": 50.11,
768
+ "step": 375,
769
+ "token_acc": 0.8716577540106952,
770
+ "train_speed(iter/s)": 0.078342
771
+ },
772
+ {
773
+ "epoch": 0.45164165800029715,
774
+ "grad_norm": 3.7696986787730387,
775
+ "learning_rate": 3.1041680694865937e-06,
776
+ "loss": 0.24771764278411865,
777
+ "memory(GiB)": 50.11,
778
+ "step": 380,
779
+ "token_acc": 0.8651685393258427,
780
+ "train_speed(iter/s)": 0.078379
781
+ },
782
+ {
783
+ "epoch": 0.45758431139503786,
784
+ "grad_norm": 4.392389040330689,
785
+ "learning_rate": 3.056302334890786e-06,
786
+ "loss": 0.2508379936218262,
787
+ "memory(GiB)": 50.11,
788
+ "step": 385,
789
+ "token_acc": 0.9011627906976745,
790
+ "train_speed(iter/s)": 0.078418
791
+ },
792
+ {
793
+ "epoch": 0.4635269647897786,
794
+ "grad_norm": 5.433260978821099,
795
+ "learning_rate": 3.0082210588295673e-06,
796
+ "loss": 0.25749917030334474,
797
+ "memory(GiB)": 50.11,
798
+ "step": 390,
799
+ "token_acc": 0.9,
800
+ "train_speed(iter/s)": 0.078455
801
+ },
802
+ {
803
+ "epoch": 0.4694696181845194,
804
+ "grad_norm": 9.046890762181722,
805
+ "learning_rate": 2.9599428705770773e-06,
806
+ "loss": 0.24419078826904297,
807
+ "memory(GiB)": 50.11,
808
+ "step": 395,
809
+ "token_acc": 0.918918918918919,
810
+ "train_speed(iter/s)": 0.078496
811
+ },
812
+ {
813
+ "epoch": 0.47541227157926014,
814
+ "grad_norm": 5.91365665819666,
815
+ "learning_rate": 2.911486475701835e-06,
816
+ "loss": 0.2059952735900879,
817
+ "memory(GiB)": 50.11,
818
+ "step": 400,
819
+ "token_acc": 0.8932584269662921,
820
+ "train_speed(iter/s)": 0.078535
821
+ },
822
+ {
823
+ "epoch": 0.4813549249740009,
824
+ "grad_norm": 5.755994095586612,
825
+ "learning_rate": 2.8628706488191994e-06,
826
+ "loss": 0.24112114906311036,
827
+ "memory(GiB)": 50.11,
828
+ "step": 405,
829
+ "token_acc": 0.9028571428571428,
830
+ "train_speed(iter/s)": 0.077697
831
+ },
832
+ {
833
+ "epoch": 0.48729757836874166,
834
+ "grad_norm": 5.029325178235288,
835
+ "learning_rate": 2.814114226317066e-06,
836
+ "loss": 0.2753992795944214,
837
+ "memory(GiB)": 50.11,
838
+ "step": 410,
839
+ "token_acc": 0.8693181818181818,
840
+ "train_speed(iter/s)": 0.077745
841
+ },
842
+ {
843
+ "epoch": 0.4932402317634824,
844
+ "grad_norm": 4.672471465609193,
845
+ "learning_rate": 2.7652360990576457e-06,
846
+ "loss": 0.25846428871154786,
847
+ "memory(GiB)": 50.11,
848
+ "step": 415,
849
+ "token_acc": 0.9080459770114943,
850
+ "train_speed(iter/s)": 0.07779
851
+ },
852
+ {
853
+ "epoch": 0.4991828851582231,
854
+ "grad_norm": 3.7971655368107315,
855
+ "learning_rate": 2.7162552050581172e-06,
856
+ "loss": 0.2129420280456543,
857
+ "memory(GiB)": 50.11,
858
+ "step": 420,
859
+ "token_acc": 0.9447513812154696,
860
+ "train_speed(iter/s)": 0.077839
861
+ },
862
+ {
863
+ "epoch": 0.5051255385529639,
864
+ "grad_norm": 4.868089805000437,
865
+ "learning_rate": 2.6671905221530286e-06,
866
+ "loss": 0.2723516941070557,
867
+ "memory(GiB)": 50.11,
868
+ "step": 425,
869
+ "token_acc": 0.8895027624309392,
870
+ "train_speed(iter/s)": 0.077893
871
+ },
872
+ {
873
+ "epoch": 0.5110681919477047,
874
+ "grad_norm": 5.948903426193995,
875
+ "learning_rate": 2.6180610606412587e-06,
876
+ "loss": 0.28262810707092284,
877
+ "memory(GiB)": 50.11,
878
+ "step": 430,
879
+ "token_acc": 0.8497109826589595,
880
+ "train_speed(iter/s)": 0.077943
881
+ },
882
+ {
883
+ "epoch": 0.5170108453424453,
884
+ "grad_norm": 5.296623912717331,
885
+ "learning_rate": 2.5688858559204056e-06,
886
+ "loss": 0.24843716621398926,
887
+ "memory(GiB)": 50.11,
888
+ "step": 435,
889
+ "token_acc": 0.9096045197740112,
890
+ "train_speed(iter/s)": 0.077992
891
+ },
892
+ {
893
+ "epoch": 0.5229534987371861,
894
+ "grad_norm": 2.8799847075968446,
895
+ "learning_rate": 2.519683961111447e-06,
896
+ "loss": 0.2587742805480957,
897
+ "memory(GiB)": 50.11,
898
+ "step": 440,
899
+ "token_acc": 0.9010989010989011,
900
+ "train_speed(iter/s)": 0.078034
901
+ },
902
+ {
903
+ "epoch": 0.5288961521319269,
904
+ "grad_norm": 4.4925409006318615,
905
+ "learning_rate": 2.470474439676539e-06,
906
+ "loss": 0.24898104667663573,
907
+ "memory(GiB)": 50.11,
908
+ "step": 445,
909
+ "token_acc": 0.8641304347826086,
910
+ "train_speed(iter/s)": 0.078071
911
+ },
912
+ {
913
+ "epoch": 0.5348388055266676,
914
+ "grad_norm": 3.120530995149119,
915
+ "learning_rate": 2.4212763580328026e-06,
916
+ "loss": 0.27778019905090334,
917
+ "memory(GiB)": 50.11,
918
+ "step": 450,
919
+ "token_acc": 0.9180327868852459,
920
+ "train_speed(iter/s)": 0.078105
921
+ },
922
+ {
923
+ "epoch": 0.5407814589214084,
924
+ "grad_norm": 8.148649805708308,
925
+ "learning_rate": 2.3721087781649677e-06,
926
+ "loss": 0.26514854431152346,
927
+ "memory(GiB)": 50.11,
928
+ "step": 455,
929
+ "token_acc": 0.8941176470588236,
930
+ "train_speed(iter/s)": 0.078143
931
+ },
932
+ {
933
+ "epoch": 0.5467241123161491,
934
+ "grad_norm": 12.288778203336234,
935
+ "learning_rate": 2.322990750239733e-06,
936
+ "loss": 0.2430635690689087,
937
+ "memory(GiB)": 50.11,
938
+ "step": 460,
939
+ "token_acc": 0.9080459770114943,
940
+ "train_speed(iter/s)": 0.078177
941
+ },
942
+ {
943
+ "epoch": 0.5526667657108899,
944
+ "grad_norm": 4.975433909870037,
945
+ "learning_rate": 2.2739413052247112e-06,
946
+ "loss": 0.23356072902679442,
947
+ "memory(GiB)": 50.11,
948
+ "step": 465,
949
+ "token_acc": 0.9028571428571428,
950
+ "train_speed(iter/s)": 0.078208
951
+ },
952
+ {
953
+ "epoch": 0.5586094191056307,
954
+ "grad_norm": 4.123700733275386,
955
+ "learning_rate": 2.224979447514802e-06,
956
+ "loss": 0.2492293357849121,
957
+ "memory(GiB)": 50.11,
958
+ "step": 470,
959
+ "token_acc": 0.8983050847457628,
960
+ "train_speed(iter/s)": 0.078242
961
+ },
962
+ {
963
+ "epoch": 0.5645520725003714,
964
+ "grad_norm": 8.285141746199841,
965
+ "learning_rate": 2.1761241475688697e-06,
966
+ "loss": 0.23113720417022704,
967
+ "memory(GiB)": 50.11,
968
+ "step": 475,
969
+ "token_acc": 0.9135135135135135,
970
+ "train_speed(iter/s)": 0.078271
971
+ },
972
+ {
973
+ "epoch": 0.5704947258951122,
974
+ "grad_norm": 3.60546896428184,
975
+ "learning_rate": 2.1273943345595637e-06,
976
+ "loss": 0.247955584526062,
977
+ "memory(GiB)": 50.11,
978
+ "step": 480,
979
+ "token_acc": 0.872093023255814,
980
+ "train_speed(iter/s)": 0.078303
981
+ },
982
+ {
983
+ "epoch": 0.576437379289853,
984
+ "grad_norm": 7.008401141324143,
985
+ "learning_rate": 2.078808889039145e-06,
986
+ "loss": 0.2634110927581787,
987
+ "memory(GiB)": 50.11,
988
+ "step": 485,
989
+ "token_acc": 0.898936170212766,
990
+ "train_speed(iter/s)": 0.07833
991
+ },
992
+ {
993
+ "epoch": 0.5823800326845937,
994
+ "grad_norm": 3.131382846950792,
995
+ "learning_rate": 2.030386635624135e-06,
996
+ "loss": 0.23566818237304688,
997
+ "memory(GiB)": 50.11,
998
+ "step": 490,
999
+ "token_acc": 0.9047619047619048,
1000
+ "train_speed(iter/s)": 0.078358
1001
+ },
1002
+ {
1003
+ "epoch": 0.5883226860793345,
1004
+ "grad_norm": 4.264889192430325,
1005
+ "learning_rate": 1.9821463357016517e-06,
1006
+ "loss": 0.23806171417236327,
1007
+ "memory(GiB)": 50.11,
1008
+ "step": 495,
1009
+ "token_acc": 0.896551724137931,
1010
+ "train_speed(iter/s)": 0.078392
1011
+ },
1012
+ {
1013
+ "epoch": 0.5942653394740752,
1014
+ "grad_norm": 3.2931924737171885,
1015
+ "learning_rate": 1.934106680160237e-06,
1016
+ "loss": 0.21435232162475587,
1017
+ "memory(GiB)": 50.11,
1018
+ "step": 500,
1019
+ "token_acc": 0.8956043956043956,
1020
+ "train_speed(iter/s)": 0.078424
1021
+ },
1022
+ {
1023
+ "epoch": 0.6002079928688159,
1024
+ "grad_norm": 8.47554455420946,
1025
+ "learning_rate": 1.8862862821480023e-06,
1026
+ "loss": 0.23268427848815917,
1027
+ "memory(GiB)": 50.11,
1028
+ "step": 505,
1029
+ "token_acc": 0.8950276243093923,
1030
+ "train_speed(iter/s)": 0.077754
1031
+ },
1032
+ {
1033
+ "epoch": 0.6061506462635566,
1034
+ "grad_norm": 4.327104476328467,
1035
+ "learning_rate": 1.8387036698608893e-06,
1036
+ "loss": 0.2465203285217285,
1037
+ "memory(GiB)": 50.11,
1038
+ "step": 510,
1039
+ "token_acc": 0.8944444444444445,
1040
+ "train_speed(iter/s)": 0.077791
1041
+ },
1042
+ {
1043
+ "epoch": 0.6120932996582974,
1044
+ "grad_norm": 4.784491787188988,
1045
+ "learning_rate": 1.7913772793638517e-06,
1046
+ "loss": 0.22468171119689942,
1047
+ "memory(GiB)": 50.11,
1048
+ "step": 515,
1049
+ "token_acc": 0.8900523560209425,
1050
+ "train_speed(iter/s)": 0.077832
1051
+ },
1052
+ {
1053
+ "epoch": 0.6180359530530382,
1054
+ "grad_norm": 7.681035665569222,
1055
+ "learning_rate": 1.7443254474477328e-06,
1056
+ "loss": 0.25678319931030275,
1057
+ "memory(GiB)": 50.11,
1058
+ "step": 520,
1059
+ "token_acc": 0.9044943820224719,
1060
+ "train_speed(iter/s)": 0.077861
1061
+ },
1062
+ {
1063
+ "epoch": 0.6239786064477789,
1064
+ "grad_norm": 4.916037468988723,
1065
+ "learning_rate": 1.697566404524606e-06,
1066
+ "loss": 0.23521194458007813,
1067
+ "memory(GiB)": 50.11,
1068
+ "step": 525,
1069
+ "token_acc": 0.9209039548022598,
1070
+ "train_speed(iter/s)": 0.077894
1071
+ },
1072
+ {
1073
+ "epoch": 0.6299212598425197,
1074
+ "grad_norm": 4.319245744348972,
1075
+ "learning_rate": 1.6511182675643273e-06,
1076
+ "loss": 0.2768810272216797,
1077
+ "memory(GiB)": 50.11,
1078
+ "step": 530,
1079
+ "token_acc": 0.9010989010989011,
1080
+ "train_speed(iter/s)": 0.077931
1081
+ },
1082
+ {
1083
+ "epoch": 0.6358639132372604,
1084
+ "grad_norm": 4.03213626434002,
1085
+ "learning_rate": 1.6049990330750508e-06,
1086
+ "loss": 0.24452097415924073,
1087
+ "memory(GiB)": 50.11,
1088
+ "step": 535,
1089
+ "token_acc": 0.8924731182795699,
1090
+ "train_speed(iter/s)": 0.077966
1091
+ },
1092
+ {
1093
+ "epoch": 0.6418065666320012,
1094
+ "grad_norm": 4.953556314587903,
1095
+ "learning_rate": 1.5592265701304116e-06,
1096
+ "loss": 0.23774099349975586,
1097
+ "memory(GiB)": 50.11,
1098
+ "step": 540,
1099
+ "token_acc": 0.8789473684210526,
1100
+ "train_speed(iter/s)": 0.077993
1101
+ },
1102
+ {
1103
+ "epoch": 0.647749220026742,
1104
+ "grad_norm": 3.899829991625053,
1105
+ "learning_rate": 1.5138186134460847e-06,
1106
+ "loss": 0.22564327716827393,
1107
+ "memory(GiB)": 50.11,
1108
+ "step": 545,
1109
+ "token_acc": 0.925531914893617,
1110
+ "train_speed(iter/s)": 0.07802
1111
+ },
1112
+ {
1113
+ "epoch": 0.6536918734214827,
1114
+ "grad_norm": 3.0465339812240715,
1115
+ "learning_rate": 1.4687927565084023e-06,
1116
+ "loss": 0.22194738388061525,
1117
+ "memory(GiB)": 50.11,
1118
+ "step": 550,
1119
+ "token_acc": 0.9021739130434783,
1120
+ "train_speed(iter/s)": 0.078047
1121
+ },
1122
+ {
1123
+ "epoch": 0.6596345268162235,
1124
+ "grad_norm": 6.803712947943455,
1125
+ "learning_rate": 1.4241664447576876e-06,
1126
+ "loss": 0.23829455375671388,
1127
+ "memory(GiB)": 50.11,
1128
+ "step": 555,
1129
+ "token_acc": 0.8791208791208791,
1130
+ "train_speed(iter/s)": 0.078089
1131
+ },
1132
+ {
1133
+ "epoch": 0.6655771802109642,
1134
+ "grad_norm": 5.769102045042221,
1135
+ "learning_rate": 1.379956968828956e-06,
1136
+ "loss": 0.24107139110565184,
1137
+ "memory(GiB)": 50.11,
1138
+ "step": 560,
1139
+ "token_acc": 0.898876404494382,
1140
+ "train_speed(iter/s)": 0.078129
1141
+ },
1142
+ {
1143
+ "epoch": 0.671519833605705,
1144
+ "grad_norm": 3.871858784721118,
1145
+ "learning_rate": 1.3361814578525922e-06,
1146
+ "loss": 0.21992707252502441,
1147
+ "memory(GiB)": 50.11,
1148
+ "step": 565,
1149
+ "token_acc": 0.8913043478260869,
1150
+ "train_speed(iter/s)": 0.078168
1151
+ },
1152
+ {
1153
+ "epoch": 0.6774624870004456,
1154
+ "grad_norm": 3.7175877166428197,
1155
+ "learning_rate": 1.2928568728175985e-06,
1156
+ "loss": 0.22011113166809082,
1157
+ "memory(GiB)": 50.11,
1158
+ "step": 570,
1159
+ "token_acc": 0.907103825136612,
1160
+ "train_speed(iter/s)": 0.078212
1161
+ },
1162
+ {
1163
+ "epoch": 0.6834051403951864,
1164
+ "grad_norm": 2.6462218742223254,
1165
+ "learning_rate": 1.2500000000000007e-06,
1166
+ "loss": 0.26825509071350095,
1167
+ "memory(GiB)": 50.11,
1168
+ "step": 575,
1169
+ "token_acc": 0.8522727272727273,
1170
+ "train_speed(iter/s)": 0.078245
1171
+ },
1172
+ {
1173
+ "epoch": 0.6893477937899272,
1174
+ "grad_norm": 5.726663283210285,
1175
+ "learning_rate": 1.2076274444589361e-06,
1176
+ "loss": 0.2344191551208496,
1177
+ "memory(GiB)": 50.11,
1178
+ "step": 580,
1179
+ "token_acc": 0.8913043478260869,
1180
+ "train_speed(iter/s)": 0.078285
1181
+ },
1182
+ {
1183
+ "epoch": 0.6952904471846679,
1184
+ "grad_norm": 3.3648860171072914,
1185
+ "learning_rate": 1.1657556236029665e-06,
1186
+ "loss": 0.22296814918518065,
1187
+ "memory(GiB)": 50.11,
1188
+ "step": 585,
1189
+ "token_acc": 0.9162011173184358,
1190
+ "train_speed(iter/s)": 0.078321
1191
+ },
1192
+ {
1193
+ "epoch": 0.7012331005794087,
1194
+ "grad_norm": 3.3716796433764746,
1195
+ "learning_rate": 1.1244007608290835e-06,
1196
+ "loss": 0.2307145118713379,
1197
+ "memory(GiB)": 50.11,
1198
+ "step": 590,
1199
+ "token_acc": 0.8944444444444445,
1200
+ "train_speed(iter/s)": 0.078355
1201
+ },
1202
+ {
1203
+ "epoch": 0.7071757539741494,
1204
+ "grad_norm": 5.163940745117661,
1205
+ "learning_rate": 1.083578879236895e-06,
1206
+ "loss": 0.18101364374160767,
1207
+ "memory(GiB)": 50.11,
1208
+ "step": 595,
1209
+ "token_acc": 0.907608695652174,
1210
+ "train_speed(iter/s)": 0.078393
1211
+ },
1212
+ {
1213
+ "epoch": 0.7131184073688902,
1214
+ "grad_norm": 5.0920246897520975,
1215
+ "learning_rate": 1.043305795420413e-06,
1216
+ "loss": 0.2275557041168213,
1217
+ "memory(GiB)": 50.11,
1218
+ "step": 600,
1219
+ "token_acc": 0.907608695652174,
1220
+ "train_speed(iter/s)": 0.078425
1221
+ },
1222
+ {
1223
+ "epoch": 0.719061060763631,
1224
+ "grad_norm": 5.49044908007764,
1225
+ "learning_rate": 1.003597113339855e-06,
1226
+ "loss": 0.19089471101760863,
1227
+ "memory(GiB)": 50.11,
1228
+ "step": 605,
1229
+ "token_acc": 0.9273743016759777,
1230
+ "train_speed(iter/s)": 0.077897
1231
+ },
1232
+ {
1233
+ "epoch": 0.7250037141583717,
1234
+ "grad_norm": 4.608743000415324,
1235
+ "learning_rate": 9.644682182758305e-07,
1236
+ "loss": 0.2407398223876953,
1237
+ "memory(GiB)": 50.11,
1238
+ "step": 610,
1239
+ "token_acc": 0.8837209302325582,
1240
+ "train_speed(iter/s)": 0.077939
1241
+ },
1242
+ {
1243
+ "epoch": 0.7309463675531125,
1244
+ "grad_norm": 5.486991473096443,
1245
+ "learning_rate": 9.259342708682515e-07,
1246
+ "loss": 0.21678531169891357,
1247
+ "memory(GiB)": 50.11,
1248
+ "step": 615,
1249
+ "token_acc": 0.9444444444444444,
1250
+ "train_speed(iter/s)": 0.077974
1251
+ },
1252
+ {
1253
+ "epoch": 0.7368890209478532,
1254
+ "grad_norm": 6.981253763857014,
1255
+ "learning_rate": 8.880102012422873e-07,
1256
+ "loss": 0.2674489736557007,
1257
+ "memory(GiB)": 50.11,
1258
+ "step": 620,
1259
+ "token_acc": 0.9186046511627907,
1260
+ "train_speed(iter/s)": 0.078013
1261
+ },
1262
+ {
1263
+ "epoch": 0.742831674342594,
1264
+ "grad_norm": 4.912562813187418,
1265
+ "learning_rate": 8.507107032236323e-07,
1266
+ "loss": 0.21210527420043945,
1267
+ "memory(GiB)": 50.11,
1268
+ "step": 625,
1269
+ "token_acc": 0.9230769230769231,
1270
+ "train_speed(iter/s)": 0.078051
1271
+ },
1272
+ {
1273
+ "epoch": 0.7487743277373348,
1274
+ "grad_norm": 2.4710747552066668,
1275
+ "learning_rate": 8.140502286453231e-07,
1276
+ "loss": 0.24000158309936523,
1277
+ "memory(GiB)": 50.11,
1278
+ "step": 630,
1279
+ "token_acc": 0.9226519337016574,
1280
+ "train_speed(iter/s)": 0.078084
1281
+ },
1282
+ {
1283
+ "epoch": 0.7547169811320755,
1284
+ "grad_norm": 5.740745699538898,
1285
+ "learning_rate": 7.780429817483229e-07,
1286
+ "loss": 0.23018264770507812,
1287
+ "memory(GiB)": 50.11,
1288
+ "step": 635,
1289
+ "token_acc": 0.9152542372881356,
1290
+ "train_speed(iter/s)": 0.078117
1291
+ },
1292
+ {
1293
+ "epoch": 0.7606596345268162,
1294
+ "grad_norm": 3.1530564071349634,
1295
+ "learning_rate": 7.427029136780333e-07,
1296
+ "loss": 0.19342280626296998,
1297
+ "memory(GiB)": 50.11,
1298
+ "step": 640,
1299
+ "token_acc": 0.9308510638297872,
1300
+ "train_speed(iter/s)": 0.07815
1301
+ },
1302
+ {
1303
+ "epoch": 0.7666022879215569,
1304
+ "grad_norm": 5.113637773400957,
1305
+ "learning_rate": 7.080437170788723e-07,
1306
+ "loss": 0.22134556770324706,
1307
+ "memory(GiB)": 50.11,
1308
+ "step": 645,
1309
+ "token_acc": 0.925531914893617,
1310
+ "train_speed(iter/s)": 0.078183
1311
+ },
1312
+ {
1313
+ "epoch": 0.7725449413162977,
1314
+ "grad_norm": 6.481778521945802,
1315
+ "learning_rate": 6.740788207890017e-07,
1316
+ "loss": 0.21804354190826417,
1317
+ "memory(GiB)": 50.11,
1318
+ "step": 650,
1319
+ "token_acc": 0.9050279329608939,
1320
+ "train_speed(iter/s)": 0.078218
1321
+ },
1322
+ {
1323
+ "epoch": 0.7784875947110385,
1324
+ "grad_norm": 8.619444299529343,
1325
+ "learning_rate": 6.40821384637276e-07,
1326
+ "loss": 0.24983735084533693,
1327
+ "memory(GiB)": 50.11,
1328
+ "step": 655,
1329
+ "token_acc": 0.8736842105263158,
1330
+ "train_speed(iter/s)": 0.078254
1331
+ },
1332
+ {
1333
+ "epoch": 0.7844302481057792,
1334
+ "grad_norm": 5.377134356716376,
1335
+ "learning_rate": 6.082842943444173e-07,
1336
+ "loss": 0.21551246643066407,
1337
+ "memory(GiB)": 50.11,
1338
+ "step": 660,
1339
+ "token_acc": 0.9148936170212766,
1340
+ "train_speed(iter/s)": 0.078283
1341
+ },
1342
+ {
1343
+ "epoch": 0.79037290150052,
1344
+ "grad_norm": 5.763600489660546,
1345
+ "learning_rate": 5.764801565303918e-07,
1346
+ "loss": 0.20307836532592774,
1347
+ "memory(GiB)": 50.11,
1348
+ "step": 665,
1349
+ "token_acc": 0.8932584269662921,
1350
+ "train_speed(iter/s)": 0.078309
1351
+ },
1352
+ {
1353
+ "epoch": 0.7963155548952607,
1354
+ "grad_norm": 4.388976996043623,
1355
+ "learning_rate": 5.454212938299256e-07,
1356
+ "loss": 0.23792681694030762,
1357
+ "memory(GiB)": 50.11,
1358
+ "step": 670,
1359
+ "token_acc": 0.9044943820224719,
1360
+ "train_speed(iter/s)": 0.07834
1361
+ },
1362
+ {
1363
+ "epoch": 0.8022582082900015,
1364
+ "grad_norm": 5.711136883849875,
1365
+ "learning_rate": 5.151197401180552e-07,
1366
+ "loss": 0.2023566722869873,
1367
+ "memory(GiB)": 50.11,
1368
+ "step": 675,
1369
+ "token_acc": 0.8814432989690721,
1370
+ "train_speed(iter/s)": 0.078375
1371
+ },
1372
+ {
1373
+ "epoch": 0.8082008616847423,
1374
+ "grad_norm": 5.454661743233463,
1375
+ "learning_rate": 4.855872358475546e-07,
1376
+ "loss": 0.2369149684906006,
1377
+ "memory(GiB)": 50.11,
1378
+ "step": 680,
1379
+ "token_acc": 0.945054945054945,
1380
+ "train_speed(iter/s)": 0.078406
1381
+ },
1382
+ {
1383
+ "epoch": 0.814143515079483,
1384
+ "grad_norm": 4.447210422496218,
1385
+ "learning_rate": 4.5683522350005505e-07,
1386
+ "loss": 0.21783523559570311,
1387
+ "memory(GiB)": 50.11,
1388
+ "step": 685,
1389
+ "token_acc": 0.9197860962566845,
1390
+ "train_speed(iter/s)": 0.078436
1391
+ },
1392
+ {
1393
+ "epoch": 0.8200861684742238,
1394
+ "grad_norm": 6.434342650205402,
1395
+ "learning_rate": 4.288748431526082e-07,
1396
+ "loss": 0.23307533264160157,
1397
+ "memory(GiB)": 50.11,
1398
+ "step": 690,
1399
+ "token_acc": 0.8961748633879781,
1400
+ "train_speed(iter/s)": 0.078471
1401
+ },
1402
+ {
1403
+ "epoch": 0.8260288218689645,
1404
+ "grad_norm": 4.153284895963464,
1405
+ "learning_rate": 4.017169281614225e-07,
1406
+ "loss": 0.22777295112609863,
1407
+ "memory(GiB)": 50.11,
1408
+ "step": 695,
1409
+ "token_acc": 0.9244186046511628,
1410
+ "train_speed(iter/s)": 0.078498
1411
+ },
1412
+ {
1413
+ "epoch": 0.8319714752637053,
1414
+ "grad_norm": 5.4901230399454555,
1415
+ "learning_rate": 3.753720009644371e-07,
1416
+ "loss": 0.21194028854370117,
1417
+ "memory(GiB)": 50.11,
1418
+ "step": 700,
1419
+ "token_acc": 0.9285714285714286,
1420
+ "train_speed(iter/s)": 0.078524
1421
+ },
1422
+ {
1423
+ "epoch": 0.837914128658446,
1424
+ "grad_norm": 5.520932610215849,
1425
+ "learning_rate": 3.498502690043651e-07,
1426
+ "loss": 0.19888880252838134,
1427
+ "memory(GiB)": 50.11,
1428
+ "step": 705,
1429
+ "token_acc": 0.9222222222222223,
1430
+ "train_speed(iter/s)": 0.078056
1431
+ },
1432
+ {
1433
+ "epoch": 0.8438567820531867,
1434
+ "grad_norm": 5.181898234052906,
1435
+ "learning_rate": 3.2516162077377956e-07,
1436
+ "loss": 0.20560116767883302,
1437
+ "memory(GiB)": 50.11,
1438
+ "step": 710,
1439
+ "token_acc": 0.9310344827586207,
1440
+ "train_speed(iter/s)": 0.078083
1441
+ },
1442
+ {
1443
+ "epoch": 0.8497994354479275,
1444
+ "grad_norm": 10.349451389076972,
1445
+ "learning_rate": 3.0131562198377763e-07,
1446
+ "loss": 0.23746159076690673,
1447
+ "memory(GiB)": 50.11,
1448
+ "step": 715,
1449
+ "token_acc": 0.9162303664921466,
1450
+ "train_speed(iter/s)": 0.078112
1451
+ },
1452
+ {
1453
+ "epoch": 0.8557420888426682,
1454
+ "grad_norm": 5.618481765930095,
1455
+ "learning_rate": 2.7832151185771096e-07,
1456
+ "loss": 0.19666438102722167,
1457
+ "memory(GiB)": 50.11,
1458
+ "step": 720,
1459
+ "token_acc": 0.91005291005291,
1460
+ "train_speed(iter/s)": 0.078144
1461
+ },
1462
+ {
1463
+ "epoch": 0.861684742237409,
1464
+ "grad_norm": 5.312926998681132,
1465
+ "learning_rate": 2.5618819955141453e-07,
1466
+ "loss": 0.23160531520843505,
1467
+ "memory(GiB)": 50.11,
1468
+ "step": 725,
1469
+ "token_acc": 0.9388888888888889,
1470
+ "train_speed(iter/s)": 0.078174
1471
+ },
1472
+ {
1473
+ "epoch": 0.8676273956321497,
1474
+ "grad_norm": 6.483313259346484,
1475
+ "learning_rate": 2.3492426070131746e-07,
1476
+ "loss": 0.22388756275177002,
1477
+ "memory(GiB)": 50.11,
1478
+ "step": 730,
1479
+ "token_acc": 0.9441340782122905,
1480
+ "train_speed(iter/s)": 0.078204
1481
+ },
1482
+ {
1483
+ "epoch": 0.8735700490268905,
1484
+ "grad_norm": 7.509137819610738,
1485
+ "learning_rate": 2.1453793410178169e-07,
1486
+ "loss": 0.2553365468978882,
1487
+ "memory(GiB)": 50.11,
1488
+ "step": 735,
1489
+ "token_acc": 0.9347826086956522,
1490
+ "train_speed(iter/s)": 0.078234
1491
+ },
1492
+ {
1493
+ "epoch": 0.8795127024216313,
1494
+ "grad_norm": 3.277852306532476,
1495
+ "learning_rate": 1.950371185129485e-07,
1496
+ "loss": 0.2170994758605957,
1497
+ "memory(GiB)": 50.11,
1498
+ "step": 740,
1499
+ "token_acc": 0.9153439153439153,
1500
+ "train_speed(iter/s)": 0.078263
1501
+ },
1502
+ {
1503
+ "epoch": 0.885455355816372,
1504
+ "grad_norm": 5.884609932336502,
1505
+ "learning_rate": 1.764293696003358e-07,
1506
+ "loss": 0.1915382981300354,
1507
+ "memory(GiB)": 50.11,
1508
+ "step": 745,
1509
+ "token_acc": 0.9508196721311475,
1510
+ "train_speed(iter/s)": 0.078289
1511
+ },
1512
+ {
1513
+ "epoch": 0.8913980092111128,
1514
+ "grad_norm": 4.022239658633687,
1515
+ "learning_rate": 1.587218970073634e-07,
1516
+ "loss": 0.22730159759521484,
1517
+ "memory(GiB)": 50.11,
1518
+ "step": 750,
1519
+ "token_acc": 0.893048128342246,
1520
+ "train_speed(iter/s)": 0.078317
1521
+ },
1522
+ {
1523
+ "epoch": 0.8973406626058535,
1524
+ "grad_norm": 5.092959105324688,
1525
+ "learning_rate": 1.4192156156195153e-07,
1526
+ "loss": 0.24943215847015382,
1527
+ "memory(GiB)": 50.11,
1528
+ "step": 755,
1529
+ "token_acc": 0.90625,
1530
+ "train_speed(iter/s)": 0.078342
1531
+ },
1532
+ {
1533
+ "epoch": 0.9032833160005943,
1534
+ "grad_norm": 5.108519787962356,
1535
+ "learning_rate": 1.2603487261826726e-07,
1536
+ "loss": 0.20730853080749512,
1537
+ "memory(GiB)": 50.11,
1538
+ "step": 760,
1539
+ "token_acc": 0.9209039548022598,
1540
+ "train_speed(iter/s)": 0.07837
1541
+ },
1542
+ {
1543
+ "epoch": 0.9092259693953351,
1544
+ "grad_norm": 6.6659075199664635,
1545
+ "learning_rate": 1.1106798553464804e-07,
1546
+ "loss": 0.2543288230895996,
1547
+ "memory(GiB)": 50.11,
1548
+ "step": 765,
1549
+ "token_acc": 0.9047619047619048,
1550
+ "train_speed(iter/s)": 0.078395
1551
+ },
1552
+ {
1553
+ "epoch": 0.9151686227900757,
1554
+ "grad_norm": 3.9596865112538637,
1555
+ "learning_rate": 9.702669928868674e-08,
1556
+ "loss": 0.20190849304199218,
1557
+ "memory(GiB)": 50.11,
1558
+ "step": 770,
1559
+ "token_acc": 0.9020618556701031,
1560
+ "train_speed(iter/s)": 0.07842
1561
+ },
1562
+ {
1563
+ "epoch": 0.9211112761848165,
1564
+ "grad_norm": 4.119428617367879,
1565
+ "learning_rate": 8.391645423039357e-08,
1566
+ "loss": 0.2413175582885742,
1567
+ "memory(GiB)": 50.11,
1568
+ "step": 775,
1569
+ "token_acc": 0.9411764705882353,
1570
+ "train_speed(iter/s)": 0.078442
1571
+ },
1572
+ {
1573
+ "epoch": 0.9270539295795572,
1574
+ "grad_norm": 3.657107164063937,
1575
+ "learning_rate": 7.174232997431391e-08,
1576
+ "loss": 0.2084414005279541,
1577
+ "memory(GiB)": 50.11,
1578
+ "step": 780,
1579
+ "token_acc": 0.9438202247191011,
1580
+ "train_speed(iter/s)": 0.078465
1581
+ },
1582
+ {
1583
+ "epoch": 0.932996582974298,
1584
+ "grad_norm": 4.011455719615575,
1585
+ "learning_rate": 6.050904343141095e-08,
1586
+ "loss": 0.20162324905395507,
1587
+ "memory(GiB)": 50.11,
1588
+ "step": 785,
1589
+ "token_acc": 0.9293478260869565,
1590
+ "train_speed(iter/s)": 0.078489
1591
+ },
1592
+ {
1593
+ "epoch": 0.9389392363690388,
1594
+ "grad_norm": 6.727744613539731,
1595
+ "learning_rate": 5.022094698148072e-08,
1596
+ "loss": 0.24507064819335939,
1597
+ "memory(GiB)": 50.11,
1598
+ "step": 790,
1599
+ "token_acc": 0.9358288770053476,
1600
+ "train_speed(iter/s)": 0.078512
1601
+ },
1602
+ {
1603
+ "epoch": 0.9448818897637795,
1604
+ "grad_norm": 3.2723118161208093,
1605
+ "learning_rate": 4.088202678680597e-08,
1606
+ "loss": 0.23910284042358398,
1607
+ "memory(GiB)": 50.11,
1608
+ "step": 795,
1609
+ "token_acc": 0.861878453038674,
1610
+ "train_speed(iter/s)": 0.078537
1611
+ },
1612
+ {
1613
+ "epoch": 0.9508245431585203,
1614
+ "grad_norm": 2.6190372074419326,
1615
+ "learning_rate": 3.249590124770191e-08,
1616
+ "loss": 0.19168223142623902,
1617
+ "memory(GiB)": 50.11,
1618
+ "step": 800,
1619
+ "token_acc": 0.9213483146067416,
1620
+ "train_speed(iter/s)": 0.078553
1621
+ },
1622
+ {
1623
+ "epoch": 0.956767196553261,
1624
+ "grad_norm": 4.68738255184625,
1625
+ "learning_rate": 2.506581960055432e-08,
1626
+ "loss": 0.21967520713806152,
1627
+ "memory(GiB)": 50.11,
1628
+ "step": 805,
1629
+ "token_acc": 0.9047619047619048,
1630
+ "train_speed(iter/s)": 0.078158
1631
+ },
1632
+ {
1633
+ "epoch": 0.9627098499480018,
1634
+ "grad_norm": 5.503922565128282,
1635
+ "learning_rate": 1.8594660658889095e-08,
1636
+ "loss": 0.22110648155212403,
1637
+ "memory(GiB)": 50.11,
1638
+ "step": 810,
1639
+ "token_acc": 0.9021739130434783,
1640
+ "train_speed(iter/s)": 0.078184
1641
+ },
1642
+ {
1643
+ "epoch": 0.9686525033427426,
1644
+ "grad_norm": 4.402575819342294,
1645
+ "learning_rate": 1.3084931697966152e-08,
1646
+ "loss": 0.21621761322021485,
1647
+ "memory(GiB)": 50.11,
1648
+ "step": 815,
1649
+ "token_acc": 0.9090909090909091,
1650
+ "train_speed(iter/s)": 0.07821
1651
+ },
1652
+ {
1653
+ "epoch": 0.9745951567374833,
1654
+ "grad_norm": 4.840434765416083,
1655
+ "learning_rate": 8.538767483325384e-09,
1656
+ "loss": 0.2232905387878418,
1657
+ "memory(GiB)": 50.11,
1658
+ "step": 820,
1659
+ "token_acc": 0.8882978723404256,
1660
+ "train_speed(iter/s)": 0.078233
1661
+ },
1662
+ {
1663
+ "epoch": 0.9805378101322241,
1664
+ "grad_norm": 4.635090700558647,
1665
+ "learning_rate": 4.9579294436635784e-09,
1666
+ "loss": 0.2567557096481323,
1667
+ "memory(GiB)": 50.11,
1668
+ "step": 825,
1669
+ "token_acc": 0.8911917098445595,
1670
+ "train_speed(iter/s)": 0.078256
1671
+ },
1672
+ {
1673
+ "epoch": 0.9864804635269648,
1674
+ "grad_norm": 5.44883977227373,
1675
+ "learning_rate": 2.3438049883625635e-09,
1676
+ "loss": 0.1815792441368103,
1677
+ "memory(GiB)": 50.11,
1678
+ "step": 830,
1679
+ "token_acc": 0.93048128342246,
1680
+ "train_speed(iter/s)": 0.07828
1681
+ },
1682
+ {
1683
+ "epoch": 0.9924231169217056,
1684
+ "grad_norm": 6.50498346714347,
1685
+ "learning_rate": 6.974069699314246e-10,
1686
+ "loss": 0.20119824409484863,
1687
+ "memory(GiB)": 50.11,
1688
+ "step": 835,
1689
+ "token_acc": 0.9209039548022598,
1690
+ "train_speed(iter/s)": 0.078303
1691
+ },
1692
+ {
1693
+ "epoch": 0.9983657703164462,
1694
+ "grad_norm": 3.2168471908087506,
1695
+ "learning_rate": 1.9373291574031893e-11,
1696
+ "loss": 0.1927746295928955,
1697
+ "memory(GiB)": 50.11,
1698
+ "step": 840,
1699
+ "token_acc": 0.8863636363636364,
1700
+ "train_speed(iter/s)": 0.078328
1701
+ }
1702
+ ],
1703
+ "logging_steps": 5,
1704
+ "max_steps": 841,
1705
+ "num_input_tokens_seen": 0,
1706
+ "num_train_epochs": 1,
1707
+ "save_steps": 100,
1708
+ "stateful_callbacks": {
1709
+ "TrainerControl": {
1710
+ "args": {
1711
+ "should_epoch_stop": false,
1712
+ "should_evaluate": false,
1713
+ "should_log": false,
1714
+ "should_save": true,
1715
+ "should_training_stop": true
1716
+ },
1717
+ "attributes": {}
1718
+ }
1719
+ },
1720
+ "total_flos": 101605807005696.0,
1721
+ "train_batch_size": 1,
1722
+ "trial_name": null,
1723
+ "trial_params": null
1724
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7dec8e5ecd03f7b60cd0b0dfcaa6013458cf9e6817c81c5c391d78b95ee914
3
+ size 8312
vocab.json ADDED
The diff for this file is too large to render. See raw diff