Hugging Face's logo

neovateai
/
UI-UG-7B

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
image-to-text
UI
UI-UG
MLLM
conversational
text-generation-inference
Model card Files
xet
Community
airbobby commited on
Commit
f4aaba3
·
verified ·
1 Parent(s): b6dee0a

init

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +455 -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 +1380 -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 +1,455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 3e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 100.0,
39
+ "save_total_limit": 3,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 100.0,
65
+ "dataloader_num_workers": 8,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "tp_size": 0,
80
+ "fsdp_transformer_layer_cls_to_wrap": null,
81
+ "accelerator_config": {
82
+ "dispatch_batches": false
83
+ },
84
+ "deepspeed": {
85
+ "fp16": {
86
+ "enabled": "auto",
87
+ "loss_scale": 0,
88
+ "loss_scale_window": 1000,
89
+ "initial_scale_power": 16,
90
+ "hysteresis": 2,
91
+ "min_loss_scale": 1
92
+ },
93
+ "bf16": {
94
+ "enabled": "auto"
95
+ },
96
+ "zero_optimization": {
97
+ "stage": 2,
98
+ "offload_optimizer": {
99
+ "device": "none",
100
+ "pin_memory": true
101
+ },
102
+ "allgather_partitions": true,
103
+ "allgather_bucket_size": 200000000.0,
104
+ "overlap_comm": false,
105
+ "reduce_scatter": true,
106
+ "reduce_bucket_size": 200000000.0,
107
+ "contiguous_gradients": true
108
+ },
109
+ "gradient_accumulation_steps": "auto",
110
+ "gradient_clipping": "auto",
111
+ "steps_per_print": 2000,
112
+ "train_batch_size": "auto",
113
+ "train_micro_batch_size_per_gpu": "auto",
114
+ "wall_clock_breakdown": false
115
+ },
116
+ "label_smoothing_factor": 0.0,
117
+ "optim": "adamw_torch",
118
+ "optim_args": null,
119
+ "adafactor": false,
120
+ "group_by_length": false,
121
+ "length_column_name": "length",
122
+ "report_to": [
123
+ "tensorboard"
124
+ ],
125
+ "ddp_find_unused_parameters": null,
126
+ "ddp_bucket_cap_mb": null,
127
+ "ddp_broadcast_buffers": null,
128
+ "dataloader_pin_memory": true,
129
+ "dataloader_persistent_workers": false,
130
+ "skip_memory_metrics": true,
131
+ "use_legacy_prediction_loop": false,
132
+ "push_to_hub": false,
133
+ "resume_from_checkpoint": null,
134
+ "hub_model_id": null,
135
+ "hub_strategy": "every_save",
136
+ "hub_token": null,
137
+ "hub_private_repo": null,
138
+ "hub_always_push": false,
139
+ "gradient_checkpointing": true,
140
+ "gradient_checkpointing_kwargs": "{\"use_reentrant\":false}",
141
+ "include_inputs_for_metrics": false,
142
+ "include_for_metrics": [],
143
+ "eval_do_concat_batches": true,
144
+ "fp16_backend": "auto",
145
+ "push_to_hub_model_id": null,
146
+ "push_to_hub_organization": null,
147
+ "push_to_hub_token": null,
148
+ "mp_parameters": "",
149
+ "auto_find_batch_size": false,
150
+ "full_determinism": false,
151
+ "torchdynamo": null,
152
+ "ray_scope": "last",
153
+ "ddp_timeout": 18000000,
154
+ "torch_compile": false,
155
+ "torch_compile_backend": null,
156
+ "torch_compile_mode": null,
157
+ "include_tokens_per_second": false,
158
+ "include_num_input_tokens_seen": false,
159
+ "neftune_noise_alpha": null,
160
+ "optim_target_modules": null,
161
+ "batch_eval_metrics": false,
162
+ "eval_on_start": false,
163
+ "use_liger_kernel": false,
164
+ "eval_use_gather_object": false,
165
+ "average_tokens_across_devices": false,
166
+ "sortish_sampler": false,
167
+ "predict_with_generate": false,
168
+ "generation_max_length": null,
169
+ "generation_num_beams": null,
170
+ "generation_config": null,
171
+ "vit_gradient_checkpointing": null,
172
+ "check_model": true,
173
+ "acc_strategy": "token",
174
+ "train_dataloader_shuffle": true,
175
+ "max_epochs": null,
176
+ "aligner_lr": 3e-06,
177
+ "vit_lr": 5e-07,
178
+ "optimizer": null,
179
+ "use_logits_to_keep": null,
180
+ "channels": null,
181
+ "ds3_gather_for_generation": true,
182
+ "metric_warmup_step": 0,
183
+ "fsdp_num": 1,
184
+ "acc_steps": 1,
185
+ "eval_use_evalscope": false,
186
+ "eval_dataset": [],
187
+ "eval_dataset_args": null,
188
+ "eval_limit": null,
189
+ "eval_generation_config": null,
190
+ "model": "/ix/share/models/wohu_ui_llm/7b/qiuqiu_7b/msswift/qiuqiu_0726_add_part_new_data_llm_adapter/v0-20250725-205139/checkpoint-8723",
191
+ "model_type": "qwen2_5_vl",
192
+ "model_revision": null,
193
+ "task_type": "causal_lm",
194
+ "torch_dtype": "bfloat16",
195
+ "attn_impl": "flash_attn",
196
+ "num_labels": null,
197
+ "problem_type": null,
198
+ "rope_scaling": null,
199
+ "device_map": null,
200
+ "max_memory": {},
201
+ "local_repo_path": null,
202
+ "init_strategy": null,
203
+ "template": "qwen2_5_vl",
204
+ "system": null,
205
+ "max_length": 8192,
206
+ "truncation_strategy": "delete",
207
+ "max_pixels": null,
208
+ "agent_template": null,
209
+ "norm_bbox": null,
210
+ "use_chat_template": true,
211
+ "padding_free": false,
212
+ "padding_side": "right",
213
+ "loss_scale": "last_round",
214
+ "sequence_parallel_size": 1,
215
+ "response_prefix": null,
216
+ "template_backend": "swift",
217
+ "dataset": [
218
+ "/ossfs/workspace/DPO/ui_dpo_zr/0730_dpo_data_add_claude_plus.jsonl"
219
+ ],
220
+ "val_dataset": [],
221
+ "split_dataset_ratio": 0.01,
222
+ "dataset_num_proc": 8,
223
+ "load_from_cache_file": true,
224
+ "dataset_shuffle": true,
225
+ "val_dataset_shuffle": false,
226
+ "streaming": false,
227
+ "interleave_prob": null,
228
+ "stopping_strategy": "first_exhausted",
229
+ "shuffle_buffer_size": 1000,
230
+ "download_mode": "reuse_dataset_if_exists",
231
+ "columns": {},
232
+ "strict": false,
233
+ "model_name": null,
234
+ "model_author": null,
235
+ "custom_dataset_info": [],
236
+ "quant_method": null,
237
+ "quant_bits": null,
238
+ "hqq_axis": null,
239
+ "bnb_4bit_compute_dtype": "bfloat16",
240
+ "bnb_4bit_quant_type": "nf4",
241
+ "bnb_4bit_use_double_quant": true,
242
+ "bnb_4bit_quant_storage": null,
243
+ "max_new_tokens": 512,
244
+ "temperature": 0.9,
245
+ "top_k": 50,
246
+ "top_p": 0.9,
247
+ "repetition_penalty": 1.0,
248
+ "num_beams": 1,
249
+ "stream": false,
250
+ "stop_words": [],
251
+ "logprobs": false,
252
+ "top_logprobs": null,
253
+ "ckpt_dir": "/ix/share/models/wohu_ui_llm/7b/qiuqiu_7b/msswift/qiuqiu_0726_add_part_new_data_llm_adapter/v0-20250725-205139/checkpoint-8723",
254
+ "lora_modules": [],
255
+ "tuner_backend": "peft",
256
+ "train_type": "full",
257
+ "adapters": [],
258
+ "external_plugins": [],
259
+ "model_kwargs": {},
260
+ "load_args": false,
261
+ "load_data_args": false,
262
+ "packing": false,
263
+ "packing_cache": null,
264
+ "custom_register_path": [],
265
+ "use_hf": false,
266
+ "ignore_args_error": false,
267
+ "use_swift_lora": false,
268
+ "freeze_parameters": [
269
+ "visual"
270
+ ],
271
+ "freeze_parameters_regex": null,
272
+ "freeze_parameters_ratio": 0.0,
273
+ "trainable_parameters": [
274
+ "visual.merger"
275
+ ],
276
+ "trainable_parameters_regex": null,
277
+ "freeze_llm": false,
278
+ "freeze_vit": true,
279
+ "freeze_aligner": false,
280
+ "target_modules": [
281
+ "all-linear"
282
+ ],
283
+ "target_regex": null,
284
+ "modules_to_save": [],
285
+ "lora_rank": 8,
286
+ "lora_alpha": 32,
287
+ "lora_dropout": 0.05,
288
+ "lora_bias": "none",
289
+ "lora_dtype": null,
290
+ "lorap_lr_ratio": null,
291
+ "use_rslora": false,
292
+ "use_dora": false,
293
+ "lora_ga_batch_size": 2,
294
+ "lora_ga_iters": 2,
295
+ "lora_ga_max_length": 1024,
296
+ "lora_ga_direction": "ArB2r",
297
+ "lora_ga_scale": "stable",
298
+ "lora_ga_stable_gamma": 16,
299
+ "init_weights": true,
300
+ "fourier_n_frequency": 2000,
301
+ "fourier_scaling": 300.0,
302
+ "boft_block_size": 4,
303
+ "boft_block_num": 0,
304
+ "boft_n_butterfly_factor": 1,
305
+ "boft_dropout": 0.0,
306
+ "vera_rank": 256,
307
+ "vera_projection_prng_key": 0,
308
+ "vera_dropout": 0.0,
309
+ "vera_d_initial": 0.1,
310
+ "adapter_act": "gelu",
311
+ "adapter_length": 128,
312
+ "use_galore": false,
313
+ "galore_target_modules": null,
314
+ "galore_rank": 128,
315
+ "galore_update_proj_gap": 50,
316
+ "galore_scale": 1.0,
317
+ "galore_proj_type": "std",
318
+ "galore_optim_per_parameter": false,
319
+ "galore_with_embedding": false,
320
+ "galore_quantization": false,
321
+ "galore_proj_quant": false,
322
+ "galore_proj_bits": 4,
323
+ "galore_proj_group_size": 256,
324
+ "galore_cos_threshold": 0.4,
325
+ "galore_gamma_proj": 2,
326
+ "galore_queue_size": 5,
327
+ "adalora_target_r": 8,
328
+ "adalora_init_r": 12,
329
+ "adalora_tinit": 0,
330
+ "adalora_tfinal": 0,
331
+ "adalora_deltaT": 1,
332
+ "adalora_beta1": 0.85,
333
+ "adalora_beta2": 0.85,
334
+ "adalora_orth_reg_weight": 0.5,
335
+ "llamapro_num_new_blocks": 4,
336
+ "llamapro_num_groups": null,
337
+ "lisa_activated_layers": 0,
338
+ "lisa_step_interval": 20,
339
+ "reft_layer_key": null,
340
+ "reft_layers": null,
341
+ "reft_rank": 4,
342
+ "reft_intervention_type": "LoreftIntervention",
343
+ "reft_args": null,
344
+ "swanlab_token": null,
345
+ "swanlab_project": null,
346
+ "swanlab_workspace": null,
347
+ "swanlab_exp_name": null,
348
+ "swanlab_lark_webhook_url": null,
349
+ "swanlab_lark_secret": null,
350
+ "swanlab_mode": "cloud",
351
+ "add_version": true,
352
+ "resume_only_model": false,
353
+ "create_checkpoint_symlink": false,
354
+ "lazy_tokenize": true,
355
+ "loss_type": "sigmoid",
356
+ "metric": null,
357
+ "zero_hpz_partition_size": null,
358
+ "sft_alpha": 0,
359
+ "reward_model": null,
360
+ "reward_adapters": [],
361
+ "reward_model_type": null,
362
+ "reward_model_revision": null,
363
+ "num_ppo_epochs": 4,
364
+ "whiten_rewards": false,
365
+ "kl_coef": 0.05,
366
+ "cliprange": 0.2,
367
+ "vf_coef": 0.1,
368
+ "cliprange_value": 0.2,
369
+ "gamma": 1.0,
370
+ "lam": 0.95,
371
+ "num_mini_batches": 1,
372
+ "local_rollout_forward_batch_size": 64,
373
+ "num_sample_generations": 10,
374
+ "response_length": 512,
375
+ "missing_eos_penalty": null,
376
+ "epsilon": 0.2,
377
+ "epsilon_high": null,
378
+ "delta": null,
379
+ "vllm_mode": "colocate",
380
+ "vllm_gpu_memory_utilization": 0.9,
381
+ "vllm_max_model_len": null,
382
+ "vllm_enforce_eager": false,
383
+ "vllm_limit_mm_per_prompt": null,
384
+ "vllm_enable_prefix_caching": true,
385
+ "vllm_tensor_parallel_size": 1,
386
+ "vllm_server_base_url": null,
387
+ "vllm_server_host": null,
388
+ "vllm_server_port": 8000,
389
+ "vllm_server_timeout": 240.0,
390
+ "cosine_min_len_value_wrong": -0.5,
391
+ "cosine_max_len_value_wrong": 0.0,
392
+ "cosine_min_len_value_correct": 1.0,
393
+ "cosine_max_len_value_correct": 0.5,
394
+ "cosine_max_len": null,
395
+ "repetition_n_grams": 3,
396
+ "repetition_max_penalty": -1.0,
397
+ "reward_model_plugin": null,
398
+ "sync_ref_model": false,
399
+ "ref_model_sync_steps": 512,
400
+ "ref_model_mixup_alpha": 0.6,
401
+ "async_generate": false,
402
+ "sleep_level": 0,
403
+ "move_model_batches": null,
404
+ "offload_optimizer": false,
405
+ "offload_model": false,
406
+ "gc_collect_after_offload": false,
407
+ "multi_turn_func": null,
408
+ "multi_turn_scheduler": null,
409
+ "max_turns": null,
410
+ "completion_length_limit_scope": "per_round",
411
+ "dynamic_sample": false,
412
+ "max_resample_times": 3,
413
+ "overlong_filter": false,
414
+ "soft_max_length": null,
415
+ "soft_cache_length": null,
416
+ "scale_rewards": true,
417
+ "wandb_log_unique_prompts": null,
418
+ "generation_batch_size": null,
419
+ "steps_per_generation": null,
420
+ "num_generations": 8,
421
+ "reward_funcs": [],
422
+ "reward_weights": null,
423
+ "log_completions": false,
424
+ "use_vllm": false,
425
+ "num_iterations": 1,
426
+ "teacher_model": null,
427
+ "teacher_adapters": [],
428
+ "teacher_model_type": null,
429
+ "teacher_model_revision": null,
430
+ "rlhf_type": "dpo",
431
+ "ref_model": "/ix/share/models/wohu_ui_llm/7b/qiuqiu_7b/msswift/qiuqiu_0726_add_part_new_data_llm_adapter/v0-20250725-205139/checkpoint-8723",
432
+ "ref_model_type": "qwen2_5_vl",
433
+ "ref_model_revision": null,
434
+ "beta": 0.05,
435
+ "label_smoothing": 0,
436
+ "max_completion_length": 512,
437
+ "rpo_alpha": 1.0,
438
+ "cpo_alpha": 1.0,
439
+ "simpo_gamma": 1,
440
+ "desirable_weight": 1.0,
441
+ "undesirable_weight": 1.0,
442
+ "center_rewards_coefficient": null,
443
+ "lmbda": 0.5,
444
+ "seq_kd": false,
445
+ "rank": 0,
446
+ "global_world_size": 8,
447
+ "local_world_size": 8,
448
+ "model_suffix": "checkpoint-8723",
449
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/ix/share/models/wohu_ui_llm/7b/qiuqiu_7b/msswift/qiuqiu_0726_add_part_new_data_llm_adapter/v0-20250725-205139/checkpoint-8723', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
450
+ "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 0x7f7c3ea115a0>, 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=['vision', 'video'])",
451
+ "model_dir": "/ix/share/models/wohu_ui_llm/7b/qiuqiu_7b/msswift/qiuqiu_0726_add_part_new_data_llm_adapter/v0-20250725-205139/checkpoint-8723",
452
+ "hub": "<class 'swift.hub.hub.MSHub'>",
453
+ "evaluation_strategy": "steps",
454
+ "training_args": "DPOConfig(output_dir='/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=3e-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=3.0, 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='/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953/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=3, 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=8, dataloader_prefetch_factor=10, past_index=-1, run_name='/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953', 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': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, force_use_ref_model=False, disable_dropout=True, use_logits_to_keep=None, dataset_num_proc=8, padding_value=None, label_pad_token_id=None, max_prompt_length=512, max_completion_length=512, max_length=8192, truncation_mode='keep_end', padding_free=False, precompute_ref_log_probs=False, precompute_ref_batch_size=None, tools=None, loss_type='sigmoid', beta=0.05, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, reference_free=False, label_smoothing=0, use_weighting=False, rpo_alpha=1.0, discopop_tau=0.05, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, generate_during_eval=False, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=3e-06, vit_lr=5e-07, optimizer='multimodal', channels=None, ds3_gather_for_generation=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None)"
455
+ }
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": "4.51.3",
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": "4.51.3"
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:dfdd96e10ed0268665ad58962066b3bc5c29fab2105e40913ca84023a4936e65
3
+ size 4968243304
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9027a0c09af9ad851cdde0869e0c000f3508c097c3db3dd8f2920ac93e4668c5
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:a6ef593ad9e514c8346863e378492514d5a70392d66a34f0243b00bc7eba7521
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:bf05d9398adadc3d0ee82342cb84188b2559dcb2738918ebb72db4188e01bb57
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 +1,1380 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 351,
3
+ "best_metric": 0.08202474,
4
+ "best_model_checkpoint": "/ckpts/models/wohu_ui_llm/7b/test_dpo_0730_8723_3e-6_beta_005_add_claude2_epoch3/v0-20250801-071953/checkpoint-351",
5
+ "epoch": 2.9957446808510637,
6
+ "eval_steps": 100,
7
+ "global_step": 351,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00851063829787234,
14
+ "grad_norm": 113.12678527832031,
15
+ "learning_rate": 1.6666666666666665e-07,
16
+ "logits/chosen": -2.26171875,
17
+ "logits/rejected": -2.27734375,
18
+ "logps/chosen": -421.0,
19
+ "logps/rejected": -97.875,
20
+ "loss": 1.2347412109375,
21
+ "memory(GiB)": 63.45,
22
+ "nll_loss": 0.54248046875,
23
+ "rewards/accuracies": 0.0,
24
+ "rewards/chosen": 0.0,
25
+ "rewards/margins": 0.0,
26
+ "rewards/rejected": 0.0,
27
+ "step": 1,
28
+ "train_speed(iter/s)": 0.015536
29
+ },
30
+ {
31
+ "epoch": 0.0425531914893617,
32
+ "grad_norm": 116.12273406982422,
33
+ "learning_rate": 8.333333333333334e-07,
34
+ "logits/chosen": -2.2197265625,
35
+ "logits/rejected": -2.2900390625,
36
+ "logps/chosen": -518.375,
37
+ "logps/rejected": -105.0625,
38
+ "loss": 1.295806884765625,
39
+ "memory(GiB)": 78.07,
40
+ "nll_loss": 0.623046875,
41
+ "rewards/accuracies": 0.44921875,
42
+ "rewards/chosen": 0.04306221008300781,
43
+ "rewards/margins": 0.03983926773071289,
44
+ "rewards/rejected": 0.0031530149281024933,
45
+ "step": 5,
46
+ "train_speed(iter/s)": 0.020262
47
+ },
48
+ {
49
+ "epoch": 0.0851063829787234,
50
+ "grad_norm": 16.63855743408203,
51
+ "learning_rate": 1.6666666666666669e-06,
52
+ "logits/chosen": -2.178906202316284,
53
+ "logits/rejected": -2.296875,
54
+ "logps/chosen": -496.29998779296875,
55
+ "logps/rejected": -100.19999694824219,
56
+ "loss": 0.902490234375,
57
+ "memory(GiB)": 78.07,
58
+ "nll_loss": 0.584765613079071,
59
+ "rewards/accuracies": 1.0,
60
+ "rewards/chosen": 1.335205078125,
61
+ "rewards/margins": 1.311669945716858,
62
+ "rewards/rejected": 0.024295806884765625,
63
+ "step": 10,
64
+ "train_speed(iter/s)": 0.023151
65
+ },
66
+ {
67
+ "epoch": 0.1276595744680851,
68
+ "grad_norm": 3.581925392150879,
69
+ "learning_rate": 2.5e-06,
70
+ "logits/chosen": -1.9874999523162842,
71
+ "logits/rejected": -2.1171875,
72
+ "logps/chosen": -399.20001220703125,
73
+ "logps/rejected": -105.57499694824219,
74
+ "loss": 0.502459716796875,
75
+ "memory(GiB)": 78.11,
76
+ "nll_loss": 0.4808593690395355,
77
+ "rewards/accuracies": 1.0,
78
+ "rewards/chosen": 6.135937690734863,
79
+ "rewards/margins": 5.94140625,
80
+ "rewards/rejected": 0.19367675483226776,
81
+ "step": 15,
82
+ "train_speed(iter/s)": 0.02441
83
+ },
84
+ {
85
+ "epoch": 0.1702127659574468,
86
+ "grad_norm": 1.2561246156692505,
87
+ "learning_rate": 2.99973299484371e-06,
88
+ "logits/chosen": -0.9429687261581421,
89
+ "logits/rejected": -1.2861328125,
90
+ "logps/chosen": -267.79998779296875,
91
+ "logps/rejected": -103.30000305175781,
92
+ "loss": 0.3127166748046875,
93
+ "memory(GiB)": 78.11,
94
+ "nll_loss": 0.3118652403354645,
95
+ "rewards/accuracies": 1.0,
96
+ "rewards/chosen": 12.771875381469727,
97
+ "rewards/margins": 12.581250190734863,
98
+ "rewards/rejected": 0.18445129692554474,
99
+ "step": 20,
100
+ "train_speed(iter/s)": 0.024676
101
+ },
102
+ {
103
+ "epoch": 0.2127659574468085,
104
+ "grad_norm": 0.6227205395698547,
105
+ "learning_rate": 2.9967302783835462e-06,
106
+ "logits/chosen": 0.38526612520217896,
107
+ "logits/rejected": 0.3094726502895355,
108
+ "logps/chosen": -193.35000610351562,
109
+ "logps/rejected": -125.125,
110
+ "loss": 0.229217529296875,
111
+ "memory(GiB)": 78.11,
112
+ "nll_loss": 0.22915038466453552,
113
+ "rewards/accuracies": 1.0,
114
+ "rewards/chosen": 16.259374618530273,
115
+ "rewards/margins": 17.034374237060547,
116
+ "rewards/rejected": -0.7733398675918579,
117
+ "step": 25,
118
+ "train_speed(iter/s)": 0.024962
119
+ },
120
+ {
121
+ "epoch": 0.2553191489361702,
122
+ "grad_norm": 0.41129618883132935,
123
+ "learning_rate": 2.9903977914295545e-06,
124
+ "logits/chosen": 0.7916015386581421,
125
+ "logits/rejected": 1.0089843273162842,
126
+ "logps/chosen": -168.39999389648438,
127
+ "logps/rejected": -163.8000030517578,
128
+ "loss": 0.19467926025390625,
129
+ "memory(GiB)": 78.11,
130
+ "nll_loss": 0.19462890923023224,
131
+ "rewards/accuracies": 1.0,
132
+ "rewards/chosen": 17.774999618530273,
133
+ "rewards/margins": 20.4375,
134
+ "rewards/rejected": -2.672656297683716,
135
+ "step": 30,
136
+ "train_speed(iter/s)": 0.025268
137
+ },
138
+ {
139
+ "epoch": 0.2978723404255319,
140
+ "grad_norm": 0.4016430974006653,
141
+ "learning_rate": 2.9807496218427986e-06,
142
+ "logits/chosen": 0.7188476324081421,
143
+ "logits/rejected": 1.051367163658142,
144
+ "logps/chosen": -147.5749969482422,
145
+ "logps/rejected": -167.4499969482422,
146
+ "loss": 0.1833892822265625,
147
+ "memory(GiB)": 78.11,
148
+ "nll_loss": 0.18344727158546448,
149
+ "rewards/accuracies": 1.0,
150
+ "rewards/chosen": 17.71875,
151
+ "rewards/margins": 21.081249237060547,
152
+ "rewards/rejected": -3.3648438453674316,
153
+ "step": 35,
154
+ "train_speed(iter/s)": 0.025286
155
+ },
156
+ {
157
+ "epoch": 0.3404255319148936,
158
+ "grad_norm": 0.31658557057380676,
159
+ "learning_rate": 2.967807233871629e-06,
160
+ "logits/chosen": 0.45478516817092896,
161
+ "logits/rejected": 0.924609363079071,
162
+ "logps/chosen": -145.5749969482422,
163
+ "logps/rejected": -178.89999389648438,
164
+ "loss": 0.17320556640625,
165
+ "memory(GiB)": 78.11,
166
+ "nll_loss": 0.17319336533546448,
167
+ "rewards/accuracies": 1.0,
168
+ "rewards/chosen": 19.15625,
169
+ "rewards/margins": 22.78125,
170
+ "rewards/rejected": -3.624218702316284,
171
+ "step": 40,
172
+ "train_speed(iter/s)": 0.025482
173
+ },
174
+ {
175
+ "epoch": 0.3829787234042553,
176
+ "grad_norm": 0.27831006050109863,
177
+ "learning_rate": 2.9515994204002487e-06,
178
+ "logits/chosen": 0.1028236374258995,
179
+ "logits/rejected": 0.770703136920929,
180
+ "logps/chosen": -139.27499389648438,
181
+ "logps/rejected": -189.64999389648438,
182
+ "loss": 0.1634765625,
183
+ "memory(GiB)": 78.11,
184
+ "nll_loss": 0.16347655653953552,
185
+ "rewards/accuracies": 1.0,
186
+ "rewards/chosen": 19.056249618530273,
187
+ "rewards/margins": 23.15625,
188
+ "rewards/rejected": -4.110937595367432,
189
+ "step": 45,
190
+ "train_speed(iter/s)": 0.025643
191
+ },
192
+ {
193
+ "epoch": 0.425531914893617,
194
+ "grad_norm": 0.25902220606803894,
195
+ "learning_rate": 2.93216223889328e-06,
196
+ "logits/chosen": -0.0480804443359375,
197
+ "logits/rejected": 0.71923828125,
198
+ "logps/chosen": -133.72500610351562,
199
+ "logps/rejected": -198.5,
200
+ "loss": 0.15597991943359374,
201
+ "memory(GiB)": 78.11,
202
+ "nll_loss": 0.15595702826976776,
203
+ "rewards/accuracies": 1.0,
204
+ "rewards/chosen": 20.168750762939453,
205
+ "rewards/margins": 24.75,
206
+ "rewards/rejected": -4.5859375,
207
+ "step": 50,
208
+ "train_speed(iter/s)": 0.025474
209
+ },
210
+ {
211
+ "epoch": 0.46808510638297873,
212
+ "grad_norm": 0.27047035098075867,
213
+ "learning_rate": 2.9095389311788626e-06,
214
+ "logits/chosen": -0.18197020888328552,
215
+ "logits/rejected": 0.5546875,
216
+ "logps/chosen": -125.92500305175781,
217
+ "logps/rejected": -208.14999389648438,
218
+ "loss": 0.14620513916015626,
219
+ "memory(GiB)": 78.11,
220
+ "nll_loss": 0.14619140326976776,
221
+ "rewards/accuracies": 1.0,
222
+ "rewards/chosen": 19.799999237060547,
223
+ "rewards/margins": 24.693750381469727,
224
+ "rewards/rejected": -4.910937309265137,
225
+ "step": 55,
226
+ "train_speed(iter/s)": 0.025306
227
+ },
228
+ {
229
+ "epoch": 0.5106382978723404,
230
+ "grad_norm": 0.2637348473072052,
231
+ "learning_rate": 2.8837798272487033e-06,
232
+ "logits/chosen": -0.17402306199073792,
233
+ "logits/rejected": 0.616503894329071,
234
+ "logps/chosen": -130.97500610351562,
235
+ "logps/rejected": -213.89999389648438,
236
+ "loss": 0.14871978759765625,
237
+ "memory(GiB)": 78.11,
238
+ "nll_loss": 0.14863280951976776,
239
+ "rewards/accuracies": 1.0,
240
+ "rewards/chosen": 20.625,
241
+ "rewards/margins": 25.737499237060547,
242
+ "rewards/rejected": -5.128125190734863,
243
+ "step": 60,
244
+ "train_speed(iter/s)": 0.025358
245
+ },
246
+ {
247
+ "epoch": 0.5531914893617021,
248
+ "grad_norm": 0.2757234573364258,
249
+ "learning_rate": 2.8549422332891285e-06,
250
+ "logits/chosen": -0.1392822265625,
251
+ "logits/rejected": 0.5840820074081421,
252
+ "logps/chosen": -122.125,
253
+ "logps/rejected": -214.10000610351562,
254
+ "loss": 0.1463531494140625,
255
+ "memory(GiB)": 78.11,
256
+ "nll_loss": 0.14619140326976776,
257
+ "rewards/accuracies": 1.0,
258
+ "rewards/chosen": 20.606250762939453,
259
+ "rewards/margins": 25.912500381469727,
260
+ "rewards/rejected": -5.298437595367432,
261
+ "step": 65,
262
+ "train_speed(iter/s)": 0.02546
263
+ },
264
+ {
265
+ "epoch": 0.5957446808510638,
266
+ "grad_norm": 0.283324658870697,
267
+ "learning_rate": 2.823090304192217e-06,
268
+ "logits/chosen": -0.08134154975414276,
269
+ "logits/rejected": 0.64697265625,
270
+ "logps/chosen": -113.42500305175781,
271
+ "logps/rejected": -220.1999969482422,
272
+ "loss": 0.13967132568359375,
273
+ "memory(GiB)": 78.11,
274
+ "nll_loss": 0.1396484375,
275
+ "rewards/accuracies": 1.0,
276
+ "rewards/chosen": 19.106250762939453,
277
+ "rewards/margins": 24.731250762939453,
278
+ "rewards/rejected": -5.606249809265137,
279
+ "step": 70,
280
+ "train_speed(iter/s)": 0.025562
281
+ },
282
+ {
283
+ "epoch": 0.6382978723404256,
284
+ "grad_norm": 0.25037115812301636,
285
+ "learning_rate": 2.7882949008306392e-06,
286
+ "logits/chosen": -0.18788452446460724,
287
+ "logits/rejected": 0.564404308795929,
288
+ "logps/chosen": -116.57499694824219,
289
+ "logps/rejected": -237.60000610351562,
290
+ "loss": 0.1353363037109375,
291
+ "memory(GiB)": 78.11,
292
+ "nll_loss": 0.13532714545726776,
293
+ "rewards/accuracies": 1.0,
294
+ "rewards/chosen": 20.306249618530273,
295
+ "rewards/margins": 26.40625,
296
+ "rewards/rejected": -6.090624809265137,
297
+ "step": 75,
298
+ "train_speed(iter/s)": 0.025539
299
+ },
300
+ {
301
+ "epoch": 0.6808510638297872,
302
+ "grad_norm": 0.2523050308227539,
303
+ "learning_rate": 2.750633432413728e-06,
304
+ "logits/chosen": -0.17770537734031677,
305
+ "logits/rejected": 0.498748779296875,
306
+ "logps/chosen": -112.0250015258789,
307
+ "logps/rejected": -236.9499969482422,
308
+ "loss": 0.13072662353515624,
309
+ "memory(GiB)": 78.11,
310
+ "nll_loss": 0.13068847358226776,
311
+ "rewards/accuracies": 1.0,
312
+ "rewards/chosen": 19.984375,
313
+ "rewards/margins": 26.318750381469727,
314
+ "rewards/rejected": -6.315625190734863,
315
+ "step": 80,
316
+ "train_speed(iter/s)": 0.025618
317
+ },
318
+ {
319
+ "epoch": 0.723404255319149,
320
+ "grad_norm": 0.2926895320415497,
321
+ "learning_rate": 2.7101896842754866e-06,
322
+ "logits/chosen": -0.23759765923023224,
323
+ "logits/rejected": 0.45625001192092896,
324
+ "logps/chosen": -111.875,
325
+ "logps/rejected": -246.39999389648438,
326
+ "loss": 0.12862091064453124,
327
+ "memory(GiB)": 78.11,
328
+ "nll_loss": 0.128662109375,
329
+ "rewards/accuracies": 1.0,
330
+ "rewards/chosen": 20.412500381469727,
331
+ "rewards/margins": 27.200000762939453,
332
+ "rewards/rejected": -6.787499904632568,
333
+ "step": 85,
334
+ "train_speed(iter/s)": 0.025658
335
+ },
336
+ {
337
+ "epoch": 0.7659574468085106,
338
+ "grad_norm": 0.2679479420185089,
339
+ "learning_rate": 2.6670536314776595e-06,
340
+ "logits/chosen": -0.18338623642921448,
341
+ "logits/rejected": 0.4960083067417145,
342
+ "logps/chosen": -108.4000015258789,
343
+ "logps/rejected": -243.9499969482422,
344
+ "loss": 0.13025360107421874,
345
+ "memory(GiB)": 78.11,
346
+ "nll_loss": 0.1302490234375,
347
+ "rewards/accuracies": 1.0,
348
+ "rewards/chosen": 20.603124618530273,
349
+ "rewards/margins": 27.668750762939453,
350
+ "rewards/rejected": -7.056250095367432,
351
+ "step": 90,
352
+ "train_speed(iter/s)": 0.025811
353
+ },
354
+ {
355
+ "epoch": 0.8085106382978723,
356
+ "grad_norm": 0.2539767622947693,
357
+ "learning_rate": 2.6213212386425304e-06,
358
+ "logits/chosen": -0.35136717557907104,
359
+ "logits/rejected": 0.42353516817092896,
360
+ "logps/chosen": -111.375,
361
+ "logps/rejected": -262.45001220703125,
362
+ "loss": 0.12735443115234374,
363
+ "memory(GiB)": 78.11,
364
+ "nll_loss": 0.1273193359375,
365
+ "rewards/accuracies": 1.0,
366
+ "rewards/chosen": 20.912500381469727,
367
+ "rewards/margins": 28.243749618530273,
368
+ "rewards/rejected": -7.326562404632568,
369
+ "step": 95,
370
+ "train_speed(iter/s)": 0.025843
371
+ },
372
+ {
373
+ "epoch": 0.851063829787234,
374
+ "grad_norm": 0.2883126735687256,
375
+ "learning_rate": 2.573094246460773e-06,
376
+ "logits/chosen": -0.3926025331020355,
377
+ "logits/rejected": 0.3401855528354645,
378
+ "logps/chosen": -101.8499984741211,
379
+ "logps/rejected": -255.14999389648438,
380
+ "loss": 0.12263336181640624,
381
+ "memory(GiB)": 78.11,
382
+ "nll_loss": 0.12258300930261612,
383
+ "rewards/accuracies": 1.0,
384
+ "rewards/chosen": 20.381250381469727,
385
+ "rewards/margins": 27.981250762939453,
386
+ "rewards/rejected": -7.606249809265137,
387
+ "step": 100,
388
+ "train_speed(iter/s)": 0.025837
389
+ },
390
+ {
391
+ "epoch": 0.851063829787234,
392
+ "eval_logits/chosen": -0.3551269471645355,
393
+ "eval_logits/rejected": 0.3993896543979645,
394
+ "eval_logps/chosen": -114.19999694824219,
395
+ "eval_logps/rejected": -283.3999938964844,
396
+ "eval_loss": 0.12689127027988434,
397
+ "eval_nll_loss": 0.13129882514476776,
398
+ "eval_rewards/accuracies": 1.0,
399
+ "eval_rewards/chosen": 21.575000762939453,
400
+ "eval_rewards/margins": 29.962499618530273,
401
+ "eval_rewards/rejected": -8.393750190734863,
402
+ "eval_runtime": 16.796,
403
+ "eval_samples_per_second": 4.465,
404
+ "eval_steps_per_second": 0.595,
405
+ "step": 100
406
+ },
407
+ {
408
+ "epoch": 0.8936170212765957,
409
+ "grad_norm": 0.26771247386932373,
410
+ "learning_rate": 2.5224799453492994e-06,
411
+ "logits/chosen": -0.45463865995407104,
412
+ "logits/rejected": 0.3071838319301605,
413
+ "logps/chosen": -103.67500305175781,
414
+ "logps/rejected": -268.0,
415
+ "loss": 0.12566070556640624,
416
+ "memory(GiB)": 78.11,
417
+ "nll_loss": 0.12568359076976776,
418
+ "rewards/accuracies": 1.0,
419
+ "rewards/chosen": 21.1875,
420
+ "rewards/margins": 29.40625,
421
+ "rewards/rejected": -8.196874618530273,
422
+ "step": 105,
423
+ "train_speed(iter/s)": 0.025625
424
+ },
425
+ {
426
+ "epoch": 0.9361702127659575,
427
+ "grad_norm": 0.26143553853034973,
428
+ "learning_rate": 2.469590936762654e-06,
429
+ "logits/chosen": -0.6083984375,
430
+ "logits/rejected": 0.19863280653953552,
431
+ "logps/chosen": -102.7750015258789,
432
+ "logps/rejected": -276.70001220703125,
433
+ "loss": 0.11554946899414062,
434
+ "memory(GiB)": 78.11,
435
+ "nll_loss": 0.11552734673023224,
436
+ "rewards/accuracies": 1.0,
437
+ "rewards/chosen": 21.356250762939453,
438
+ "rewards/margins": 29.475000381469727,
439
+ "rewards/rejected": -8.104687690734863,
440
+ "step": 110,
441
+ "train_speed(iter/s)": 0.025585
442
+ },
443
+ {
444
+ "epoch": 0.9787234042553191,
445
+ "grad_norm": 0.26631999015808105,
446
+ "learning_rate": 2.414544882688961e-06,
447
+ "logits/chosen": -0.5418945550918579,
448
+ "logits/rejected": 0.3081298768520355,
449
+ "logps/chosen": -96.5999984741211,
450
+ "logps/rejected": -275.20001220703125,
451
+ "loss": 0.11951446533203125,
452
+ "memory(GiB)": 78.11,
453
+ "nll_loss": 0.11955566704273224,
454
+ "rewards/accuracies": 1.0,
455
+ "rewards/chosen": 20.450000762939453,
456
+ "rewards/margins": 28.706249237060547,
457
+ "rewards/rejected": -8.2578125,
458
+ "step": 115,
459
+ "train_speed(iter/s)": 0.025519
460
+ },
461
+ {
462
+ "epoch": 1.025531914893617,
463
+ "grad_norm": 0.261348694562912,
464
+ "learning_rate": 2.3574642438877183e-06,
465
+ "logits/chosen": -0.6530877947807312,
466
+ "logits/rejected": 0.1812860369682312,
467
+ "logps/chosen": -95.26190185546875,
468
+ "logps/rejected": -286.047607421875,
469
+ "loss": 0.1169525146484375,
470
+ "memory(GiB)": 78.11,
471
+ "nll_loss": 0.1113978773355484,
472
+ "rewards/accuracies": 1.0,
473
+ "rewards/chosen": 21.404762268066406,
474
+ "rewards/margins": 30.095237731933594,
475
+ "rewards/rejected": -8.691964149475098,
476
+ "step": 120,
477
+ "train_speed(iter/s)": 0.025517
478
+ },
479
+ {
480
+ "epoch": 1.0680851063829788,
481
+ "grad_norm": 0.266865998506546,
482
+ "learning_rate": 2.2984760074517883e-06,
483
+ "logits/chosen": -0.744921863079071,
484
+ "logits/rejected": 0.12298583984375,
485
+ "logps/chosen": -91.2249984741211,
486
+ "logps/rejected": -293.79998779296875,
487
+ "loss": 0.10560760498046876,
488
+ "memory(GiB)": 78.11,
489
+ "nll_loss": 0.10561523586511612,
490
+ "rewards/accuracies": 1.0,
491
+ "rewards/chosen": 21.450000762939453,
492
+ "rewards/margins": 30.8125,
493
+ "rewards/rejected": -9.362500190734863,
494
+ "step": 125,
495
+ "train_speed(iter/s)": 0.025403
496
+ },
497
+ {
498
+ "epoch": 1.1106382978723404,
499
+ "grad_norm": 0.24889616668224335,
500
+ "learning_rate": 2.2377114042996625e-06,
501
+ "logits/chosen": -0.736035168170929,
502
+ "logits/rejected": 0.17665405571460724,
503
+ "logps/chosen": -87.07499694824219,
504
+ "logps/rejected": -295.8999938964844,
505
+ "loss": 0.10625762939453125,
506
+ "memory(GiB)": 78.11,
507
+ "nll_loss": 0.10622558742761612,
508
+ "rewards/accuracies": 1.0,
509
+ "rewards/chosen": 20.903125762939453,
510
+ "rewards/margins": 30.087499618530273,
511
+ "rewards/rejected": -9.206250190734863,
512
+ "step": 130,
513
+ "train_speed(iter/s)": 0.025476
514
+ },
515
+ {
516
+ "epoch": 1.1531914893617021,
517
+ "grad_norm": 0.2701774835586548,
518
+ "learning_rate": 2.17530561722651e-06,
519
+ "logits/chosen": -0.8929687738418579,
520
+ "logits/rejected": 0.006848144344985485,
521
+ "logps/chosen": -84.75,
522
+ "logps/rejected": -301.04998779296875,
523
+ "loss": 0.099554443359375,
524
+ "memory(GiB)": 78.11,
525
+ "nll_loss": 0.09956054389476776,
526
+ "rewards/accuracies": 1.0,
527
+ "rewards/chosen": 21.587499618530273,
528
+ "rewards/margins": 31.524999618530273,
529
+ "rewards/rejected": -9.928125381469727,
530
+ "step": 135,
531
+ "train_speed(iter/s)": 0.02541
532
+ },
533
+ {
534
+ "epoch": 1.195744680851064,
535
+ "grad_norm": 0.27444973587989807,
536
+ "learning_rate": 2.1113974801634947e-06,
537
+ "logits/chosen": -0.9662109613418579,
538
+ "logits/rejected": 0.02514800988137722,
539
+ "logps/chosen": -83.9749984741211,
540
+ "logps/rejected": -317.3999938964844,
541
+ "loss": 0.0990264892578125,
542
+ "memory(GiB)": 78.11,
543
+ "nll_loss": 0.09904785454273224,
544
+ "rewards/accuracies": 1.0,
545
+ "rewards/chosen": 21.65625,
546
+ "rewards/margins": 31.981250762939453,
547
+ "rewards/rejected": -10.328125,
548
+ "step": 140,
549
+ "train_speed(iter/s)": 0.025373
550
+ },
551
+ {
552
+ "epoch": 1.2382978723404254,
553
+ "grad_norm": 0.29677021503448486,
554
+ "learning_rate": 2.046129169314426e-06,
555
+ "logits/chosen": -1.015039086341858,
556
+ "logits/rejected": -0.07387695461511612,
557
+ "logps/chosen": -83.88749694824219,
558
+ "logps/rejected": -319.5,
559
+ "loss": 0.0983306884765625,
560
+ "memory(GiB)": 78.11,
561
+ "nll_loss": 0.09833984076976776,
562
+ "rewards/accuracies": 1.0,
563
+ "rewards/chosen": 21.225000381469727,
564
+ "rewards/margins": 31.84375,
565
+ "rewards/rejected": -10.637499809265137,
566
+ "step": 145,
567
+ "train_speed(iter/s)": 0.025449
568
+ },
569
+ {
570
+ "epoch": 1.2808510638297872,
571
+ "grad_norm": 0.2784733474254608,
572
+ "learning_rate": 1.979645886856868e-06,
573
+ "logits/chosen": -1.034570336341858,
574
+ "logits/rejected": -0.11180724948644638,
575
+ "logps/chosen": -82.82499694824219,
576
+ "logps/rejected": -329.3999938964844,
577
+ "loss": 0.09817352294921874,
578
+ "memory(GiB)": 78.11,
579
+ "nll_loss": 0.09816894680261612,
580
+ "rewards/accuracies": 1.0,
581
+ "rewards/chosen": 21.762500762939453,
582
+ "rewards/margins": 32.525001525878906,
583
+ "rewards/rejected": -10.774999618530273,
584
+ "step": 150,
585
+ "train_speed(iter/s)": 0.025502
586
+ },
587
+ {
588
+ "epoch": 1.323404255319149,
589
+ "grad_norm": 0.30967381596565247,
590
+ "learning_rate": 1.9120955379113745e-06,
591
+ "logits/chosen": -1.0148437023162842,
592
+ "logits/rejected": -0.06700439751148224,
593
+ "logps/chosen": -80.7874984741211,
594
+ "logps/rejected": -321.0,
595
+ "loss": 0.0952880859375,
596
+ "memory(GiB)": 78.11,
597
+ "nll_loss": 0.09526367485523224,
598
+ "rewards/accuracies": 1.0,
599
+ "rewards/chosen": 20.943750381469727,
600
+ "rewards/margins": 31.568750381469727,
601
+ "rewards/rejected": -10.643750190734863,
602
+ "step": 155,
603
+ "train_speed(iter/s)": 0.025434
604
+ },
605
+ {
606
+ "epoch": 1.3659574468085105,
607
+ "grad_norm": 0.28575485944747925,
608
+ "learning_rate": 1.843628401497495e-06,
609
+ "logits/chosen": -1.0359375476837158,
610
+ "logits/rejected": -0.08933410793542862,
611
+ "logps/chosen": -82.32499694824219,
612
+ "logps/rejected": -332.3999938964844,
613
+ "loss": 0.09707794189453126,
614
+ "memory(GiB)": 78.11,
615
+ "nll_loss": 0.09709472954273224,
616
+ "rewards/accuracies": 1.0,
617
+ "rewards/chosen": 22.137500762939453,
618
+ "rewards/margins": 33.33124923706055,
619
+ "rewards/rejected": -11.215624809265137,
620
+ "step": 160,
621
+ "train_speed(iter/s)": 0.02552
622
+ },
623
+ {
624
+ "epoch": 1.4085106382978723,
625
+ "grad_norm": 0.30471956729888916,
626
+ "learning_rate": 1.7743967962085799e-06,
627
+ "logits/chosen": -1.074609398841858,
628
+ "logits/rejected": -0.05779419094324112,
629
+ "logps/chosen": -77.69999694824219,
630
+ "logps/rejected": -341.1000061035156,
631
+ "loss": 0.0906494140625,
632
+ "memory(GiB)": 78.11,
633
+ "nll_loss": 0.09067382663488388,
634
+ "rewards/accuracies": 1.0,
635
+ "rewards/chosen": 22.637500762939453,
636
+ "rewards/margins": 34.0625,
637
+ "rewards/rejected": -11.471875190734863,
638
+ "step": 165,
639
+ "train_speed(iter/s)": 0.025578
640
+ },
641
+ {
642
+ "epoch": 1.451063829787234,
643
+ "grad_norm": 0.2834922671318054,
644
+ "learning_rate": 1.7045547413491502e-06,
645
+ "logits/chosen": -1.1212890148162842,
646
+ "logits/rejected": -0.20931701362133026,
647
+ "logps/chosen": -79.4625015258789,
648
+ "logps/rejected": -334.29998779296875,
649
+ "loss": 0.09400634765625,
650
+ "memory(GiB)": 78.11,
651
+ "nll_loss": 0.09396972507238388,
652
+ "rewards/accuracies": 1.0,
653
+ "rewards/chosen": 21.221874237060547,
654
+ "rewards/margins": 32.66875076293945,
655
+ "rewards/rejected": -11.440625190734863,
656
+ "step": 170,
657
+ "train_speed(iter/s)": 0.025547
658
+ },
659
+ {
660
+ "epoch": 1.4936170212765958,
661
+ "grad_norm": 0.33174580335617065,
662
+ "learning_rate": 1.6342576142887001e-06,
663
+ "logits/chosen": -1.1828124523162842,
664
+ "logits/rejected": -0.18878021836280823,
665
+ "logps/chosen": -75.125,
666
+ "logps/rejected": -336.8999938964844,
667
+ "loss": 0.09259796142578125,
668
+ "memory(GiB)": 78.11,
669
+ "nll_loss": 0.09261474758386612,
670
+ "rewards/accuracies": 1.0,
671
+ "rewards/chosen": 22.381250381469727,
672
+ "rewards/margins": 34.01874923706055,
673
+ "rewards/rejected": -11.65625,
674
+ "step": 175,
675
+ "train_speed(iter/s)": 0.025586
676
+ },
677
+ {
678
+ "epoch": 1.5361702127659576,
679
+ "grad_norm": 0.3023318648338318,
680
+ "learning_rate": 1.5636618047942224e-06,
681
+ "logits/chosen": -1.2580077648162842,
682
+ "logits/rejected": -0.2625732421875,
683
+ "logps/chosen": -75.9749984741211,
684
+ "logps/rejected": -345.70001220703125,
685
+ "loss": 0.08780364990234375,
686
+ "memory(GiB)": 78.11,
687
+ "nll_loss": 0.08784179389476776,
688
+ "rewards/accuracies": 1.0,
689
+ "rewards/chosen": 22.193750381469727,
690
+ "rewards/margins": 34.10625076293945,
691
+ "rewards/rejected": -11.934374809265137,
692
+ "step": 180,
693
+ "train_speed(iter/s)": 0.025549
694
+ },
695
+ {
696
+ "epoch": 1.578723404255319,
697
+ "grad_norm": 0.3265296220779419,
698
+ "learning_rate": 1.492924367110452e-06,
699
+ "logits/chosen": -1.228124976158142,
700
+ "logits/rejected": -0.18481139838695526,
701
+ "logps/chosen": -72.94999694824219,
702
+ "logps/rejected": -332.3999938964844,
703
+ "loss": 0.0884490966796875,
704
+ "memory(GiB)": 78.11,
705
+ "nll_loss": 0.08845214545726776,
706
+ "rewards/accuracies": 1.0,
707
+ "rewards/chosen": 21.912500381469727,
708
+ "rewards/margins": 33.243751525878906,
709
+ "rewards/rejected": -11.318750381469727,
710
+ "step": 185,
711
+ "train_speed(iter/s)": 0.025616
712
+ },
713
+ {
714
+ "epoch": 1.6212765957446809,
715
+ "grad_norm": 0.3522721529006958,
716
+ "learning_rate": 1.4222026705618485e-06,
717
+ "logits/chosen": -1.308984398841858,
718
+ "logits/rejected": -0.3495544493198395,
719
+ "logps/chosen": -82.75,
720
+ "logps/rejected": -339.0,
721
+ "loss": 0.09106903076171875,
722
+ "memory(GiB)": 78.11,
723
+ "nll_loss": 0.09104003757238388,
724
+ "rewards/accuracies": 1.0,
725
+ "rewards/chosen": 22.306249618530273,
726
+ "rewards/margins": 33.86249923706055,
727
+ "rewards/rejected": -11.59375,
728
+ "step": 190,
729
+ "train_speed(iter/s)": 0.025589
730
+ },
731
+ {
732
+ "epoch": 1.6638297872340426,
733
+ "grad_norm": 0.3345926105976105,
734
+ "learning_rate": 1.3516540494536255e-06,
735
+ "logits/chosen": -1.242578148841858,
736
+ "logits/rejected": -0.24477234482765198,
737
+ "logps/chosen": -80.61250305175781,
738
+ "logps/rejected": -340.1000061035156,
739
+ "loss": 0.0941619873046875,
740
+ "memory(GiB)": 78.11,
741
+ "nll_loss": 0.0941162109375,
742
+ "rewards/accuracies": 1.0,
743
+ "rewards/chosen": 22.962499618530273,
744
+ "rewards/margins": 34.537498474121094,
745
+ "rewards/rejected": -11.559374809265137,
746
+ "step": 195,
747
+ "train_speed(iter/s)": 0.025589
748
+ },
749
+ {
750
+ "epoch": 1.7063829787234042,
751
+ "grad_norm": 0.28689754009246826,
752
+ "learning_rate": 1.281435453050683e-06,
753
+ "logits/chosen": -1.349609375,
754
+ "logits/rejected": -0.32838135957717896,
755
+ "logps/chosen": -75.3375015258789,
756
+ "logps/rejected": -342.29998779296875,
757
+ "loss": 0.08746185302734374,
758
+ "memory(GiB)": 78.11,
759
+ "nll_loss": 0.08747558295726776,
760
+ "rewards/accuracies": 1.0,
761
+ "rewards/chosen": 22.237499237060547,
762
+ "rewards/margins": 34.03125,
763
+ "rewards/rejected": -11.774999618530273,
764
+ "step": 200,
765
+ "train_speed(iter/s)": 0.025601
766
+ },
767
+ {
768
+ "epoch": 1.7063829787234042,
769
+ "eval_logits/chosen": -1.2234375476837158,
770
+ "eval_logits/rejected": -0.24904784560203552,
771
+ "eval_logps/chosen": -88.7249984741211,
772
+ "eval_logps/rejected": -361.3999938964844,
773
+ "eval_loss": 0.09561848640441895,
774
+ "eval_nll_loss": 0.10009765625,
775
+ "eval_rewards/accuracies": 1.0,
776
+ "eval_rewards/chosen": 22.875,
777
+ "eval_rewards/margins": 35.17499923706055,
778
+ "eval_rewards/rejected": -12.3125,
779
+ "eval_runtime": 16.8954,
780
+ "eval_samples_per_second": 4.439,
781
+ "eval_steps_per_second": 0.592,
782
+ "step": 200
783
+ },
784
+ {
785
+ "epoch": 1.748936170212766,
786
+ "grad_norm": 0.3166359066963196,
787
+ "learning_rate": 1.211703096413141e-06,
788
+ "logits/chosen": -1.329687476158142,
789
+ "logits/rejected": -0.3259124755859375,
790
+ "logps/chosen": -77.3125,
791
+ "logps/rejected": -346.0,
792
+ "loss": 0.0876129150390625,
793
+ "memory(GiB)": 78.11,
794
+ "nll_loss": 0.08759765326976776,
795
+ "rewards/accuracies": 1.0,
796
+ "rewards/chosen": 22.806249618530273,
797
+ "rewards/margins": 34.587501525878906,
798
+ "rewards/rejected": -11.800000190734863,
799
+ "step": 205,
800
+ "train_speed(iter/s)": 0.025467
801
+ },
802
+ {
803
+ "epoch": 1.7914893617021277,
804
+ "grad_norm": 0.3028061091899872,
805
+ "learning_rate": 1.1426121128652528e-06,
806
+ "logits/chosen": -1.3445312976837158,
807
+ "logits/rejected": -0.32697755098342896,
808
+ "logps/chosen": -74.69999694824219,
809
+ "logps/rejected": -338.3999938964844,
810
+ "loss": 0.08412704467773438,
811
+ "memory(GiB)": 78.11,
812
+ "nll_loss": 0.08408202975988388,
813
+ "rewards/accuracies": 1.0,
814
+ "rewards/chosen": 21.924999237060547,
815
+ "rewards/margins": 33.65625,
816
+ "rewards/rejected": -11.725000381469727,
817
+ "step": 210,
818
+ "train_speed(iter/s)": 0.025437
819
+ },
820
+ {
821
+ "epoch": 1.8340425531914892,
822
+ "grad_norm": 0.3295106291770935,
823
+ "learning_rate": 1.0743162088708549e-06,
824
+ "logits/chosen": -1.3125,
825
+ "logits/rejected": -0.33466798067092896,
826
+ "logps/chosen": -72.98750305175781,
827
+ "logps/rejected": -345.0,
828
+ "loss": 0.08744964599609376,
829
+ "memory(GiB)": 78.11,
830
+ "nll_loss": 0.08747558295726776,
831
+ "rewards/accuracies": 1.0,
832
+ "rewards/chosen": 22.737499237060547,
833
+ "rewards/margins": 34.631248474121094,
834
+ "rewards/rejected": -11.878125190734863,
835
+ "step": 215,
836
+ "train_speed(iter/s)": 0.025475
837
+ },
838
+ {
839
+ "epoch": 1.8765957446808512,
840
+ "grad_norm": 0.35723093152046204,
841
+ "learning_rate": 1.006967322083147e-06,
842
+ "logits/chosen": -1.4054687023162842,
843
+ "logits/rejected": -0.357666015625,
844
+ "logps/chosen": -67.86250305175781,
845
+ "logps/rejected": -345.5,
846
+ "loss": 0.08179931640625,
847
+ "memory(GiB)": 86.43,
848
+ "nll_loss": 0.08175048977136612,
849
+ "rewards/accuracies": 1.0,
850
+ "rewards/chosen": 22.371875762939453,
851
+ "rewards/margins": 34.068748474121094,
852
+ "rewards/rejected": -11.684374809265137,
853
+ "step": 220,
854
+ "train_speed(iter/s)": 0.025478
855
+ },
856
+ {
857
+ "epoch": 1.9191489361702128,
858
+ "grad_norm": 0.31711524724960327,
859
+ "learning_rate": 9.407152833295372e-07,
860
+ "logits/chosen": -1.478515625,
861
+ "logits/rejected": -0.43549805879592896,
862
+ "logps/chosen": -71.625,
863
+ "logps/rejected": -349.5,
864
+ "loss": 0.08211593627929688,
865
+ "memory(GiB)": 86.43,
866
+ "nll_loss": 0.08212890475988388,
867
+ "rewards/accuracies": 1.0,
868
+ "rewards/chosen": 22.71875,
869
+ "rewards/margins": 34.82500076293945,
870
+ "rewards/rejected": -12.143750190734863,
871
+ "step": 225,
872
+ "train_speed(iter/s)": 0.025434
873
+ },
874
+ {
875
+ "epoch": 1.9617021276595743,
876
+ "grad_norm": 0.33292317390441895,
877
+ "learning_rate": 8.757074832835386e-07,
878
+ "logits/chosen": -1.5011718273162842,
879
+ "logits/rejected": -0.40864259004592896,
880
+ "logps/chosen": -72.36250305175781,
881
+ "logps/rejected": -353.0,
882
+ "loss": 0.081207275390625,
883
+ "memory(GiB)": 86.43,
884
+ "nll_loss": 0.08120117336511612,
885
+ "rewards/accuracies": 1.0,
886
+ "rewards/chosen": 23.90625,
887
+ "rewards/margins": 35.91875076293945,
888
+ "rewards/rejected": -12.018750190734863,
889
+ "step": 230,
890
+ "train_speed(iter/s)": 0.025453
891
+ },
892
+ {
893
+ "epoch": 2.008510638297872,
894
+ "grad_norm": 0.32713377475738525,
895
+ "learning_rate": 8.12088544565264e-07,
896
+ "logits/chosen": -1.4508928060531616,
897
+ "logits/rejected": -0.4289202094078064,
898
+ "logps/chosen": -65.23809814453125,
899
+ "logps/rejected": -349.047607421875,
900
+ "loss": 0.08363189697265624,
901
+ "memory(GiB)": 86.43,
902
+ "nll_loss": 0.0796247199177742,
903
+ "rewards/accuracies": 1.0,
904
+ "rewards/chosen": 21.845237731933594,
905
+ "rewards/margins": 34.005950927734375,
906
+ "rewards/rejected": -12.142857551574707,
907
+ "step": 235,
908
+ "train_speed(iter/s)": 0.025437
909
+ },
910
+ {
911
+ "epoch": 2.051063829787234,
912
+ "grad_norm": 0.2999580204486847,
913
+ "learning_rate": 7.500000000000003e-07,
914
+ "logits/chosen": -1.605078101158142,
915
+ "logits/rejected": -0.5160156488418579,
916
+ "logps/chosen": -58.01250076293945,
917
+ "logps/rejected": -359.3999938964844,
918
+ "loss": 0.06568679809570313,
919
+ "memory(GiB)": 86.43,
920
+ "nll_loss": 0.06569824367761612,
921
+ "rewards/accuracies": 1.0,
922
+ "rewards/chosen": 23.456249237060547,
923
+ "rewards/margins": 35.88750076293945,
924
+ "rewards/rejected": -12.465624809265137,
925
+ "step": 240,
926
+ "train_speed(iter/s)": 0.025403
927
+ },
928
+ {
929
+ "epoch": 2.0936170212765957,
930
+ "grad_norm": 0.3553922772407532,
931
+ "learning_rate": 6.895799777506399e-07,
932
+ "logits/chosen": -1.6183593273162842,
933
+ "logits/rejected": -0.5166015625,
934
+ "logps/chosen": -61.787498474121094,
935
+ "logps/rejected": -365.5,
936
+ "loss": 0.07020797729492187,
937
+ "memory(GiB)": 86.43,
938
+ "nll_loss": 0.07022704929113388,
939
+ "rewards/accuracies": 1.0,
940
+ "rewards/chosen": 22.4375,
941
+ "rewards/margins": 35.25,
942
+ "rewards/rejected": -12.784375190734863,
943
+ "step": 245,
944
+ "train_speed(iter/s)": 0.025384
945
+ },
946
+ {
947
+ "epoch": 2.1361702127659576,
948
+ "grad_norm": 0.30416449904441833,
949
+ "learning_rate": 6.3096289402445e-07,
950
+ "logits/chosen": -1.5906250476837158,
951
+ "logits/rejected": -0.5077148675918579,
952
+ "logps/chosen": -57.6875,
953
+ "logps/rejected": -379.20001220703125,
954
+ "loss": 0.06732330322265626,
955
+ "memory(GiB)": 86.43,
956
+ "nll_loss": 0.06728515774011612,
957
+ "rewards/accuracies": 1.0,
958
+ "rewards/chosen": 22.893749237060547,
959
+ "rewards/margins": 36.212501525878906,
960
+ "rewards/rejected": -13.306249618530273,
961
+ "step": 250,
962
+ "train_speed(iter/s)": 0.025433
963
+ },
964
+ {
965
+ "epoch": 2.178723404255319,
966
+ "grad_norm": 0.29929059743881226,
967
+ "learning_rate": 5.742791540378176e-07,
968
+ "logits/chosen": -1.740234375,
969
+ "logits/rejected": -0.644824206829071,
970
+ "logps/chosen": -60.212501525878906,
971
+ "logps/rejected": -368.1000061035156,
972
+ "loss": 0.0677215576171875,
973
+ "memory(GiB)": 86.43,
974
+ "nll_loss": 0.06768798828125,
975
+ "rewards/accuracies": 1.0,
976
+ "rewards/chosen": 22.662500381469727,
977
+ "rewards/margins": 35.6875,
978
+ "rewards/rejected": -13.021875381469727,
979
+ "step": 255,
980
+ "train_speed(iter/s)": 0.025403
981
+ },
982
+ {
983
+ "epoch": 2.2212765957446807,
984
+ "grad_norm": 0.3583555817604065,
985
+ "learning_rate": 5.196548619042311e-07,
986
+ "logits/chosen": -1.7507812976837158,
987
+ "logits/rejected": -0.62744140625,
988
+ "logps/chosen": -57.537498474121094,
989
+ "logps/rejected": -370.5,
990
+ "loss": 0.06677093505859374,
991
+ "memory(GiB)": 86.43,
992
+ "nll_loss": 0.06679687649011612,
993
+ "rewards/accuracies": 1.0,
994
+ "rewards/chosen": 22.850000381469727,
995
+ "rewards/margins": 36.04999923706055,
996
+ "rewards/rejected": -13.178125381469727,
997
+ "step": 260,
998
+ "train_speed(iter/s)": 0.025386
999
+ },
1000
+ {
1001
+ "epoch": 2.2638297872340427,
1002
+ "grad_norm": 0.35006001591682434,
1003
+ "learning_rate": 4.672115400909117e-07,
1004
+ "logits/chosen": -1.760156273841858,
1005
+ "logits/rejected": -0.6236327886581421,
1006
+ "logps/chosen": -55.13750076293945,
1007
+ "logps/rejected": -373.20001220703125,
1008
+ "loss": 0.0646148681640625,
1009
+ "memory(GiB)": 86.43,
1010
+ "nll_loss": 0.06462402641773224,
1011
+ "rewards/accuracies": 1.0,
1012
+ "rewards/chosen": 22.743749618530273,
1013
+ "rewards/margins": 35.89374923706055,
1014
+ "rewards/rejected": -13.184374809265137,
1015
+ "step": 265,
1016
+ "train_speed(iter/s)": 0.02541
1017
+ },
1018
+ {
1019
+ "epoch": 2.3063829787234043,
1020
+ "grad_norm": 0.3760732412338257,
1021
+ "learning_rate": 4.170658590682134e-07,
1022
+ "logits/chosen": -1.755859375,
1023
+ "logits/rejected": -0.6622070074081421,
1024
+ "logps/chosen": -54.17499923706055,
1025
+ "logps/rejected": -383.8999938964844,
1026
+ "loss": 0.06567840576171875,
1027
+ "memory(GiB)": 86.43,
1028
+ "nll_loss": 0.06573486328125,
1029
+ "rewards/accuracies": 1.0,
1030
+ "rewards/chosen": 23.168750762939453,
1031
+ "rewards/margins": 36.662498474121094,
1032
+ "rewards/rejected": -13.5,
1033
+ "step": 270,
1034
+ "train_speed(iter/s)": 0.025453
1035
+ },
1036
+ {
1037
+ "epoch": 2.348936170212766,
1038
+ "grad_norm": 0.32026490569114685,
1039
+ "learning_rate": 3.6932937775324586e-07,
1040
+ "logits/chosen": -1.851953148841858,
1041
+ "logits/rejected": -0.682812511920929,
1042
+ "logps/chosen": -53.837501525878906,
1043
+ "logps/rejected": -378.70001220703125,
1044
+ "loss": 0.063421630859375,
1045
+ "memory(GiB)": 86.43,
1046
+ "nll_loss": 0.06342773139476776,
1047
+ "rewards/accuracies": 1.0,
1048
+ "rewards/chosen": 23.049999237060547,
1049
+ "rewards/margins": 36.58124923706055,
1050
+ "rewards/rejected": -13.506250381469727,
1051
+ "step": 275,
1052
+ "train_speed(iter/s)": 0.02545
1053
+ },
1054
+ {
1055
+ "epoch": 2.391489361702128,
1056
+ "grad_norm": 0.3174494504928589,
1057
+ "learning_rate": 3.2410829532515156e-07,
1058
+ "logits/chosen": -1.8175780773162842,
1059
+ "logits/rejected": -0.7105468511581421,
1060
+ "logps/chosen": -59.625,
1061
+ "logps/rejected": -367.0,
1062
+ "loss": 0.0679901123046875,
1063
+ "memory(GiB)": 86.43,
1064
+ "nll_loss": 0.06796874850988388,
1065
+ "rewards/accuracies": 1.0,
1066
+ "rewards/chosen": 23.868749618530273,
1067
+ "rewards/margins": 37.25,
1068
+ "rewards/rejected": -13.409375190734863,
1069
+ "step": 280,
1070
+ "train_speed(iter/s)": 0.025469
1071
+ },
1072
+ {
1073
+ "epoch": 2.4340425531914893,
1074
+ "grad_norm": 0.33984753489494324,
1075
+ "learning_rate": 2.8150321496417134e-07,
1076
+ "logits/chosen": -1.87109375,
1077
+ "logits/rejected": -0.7925781011581421,
1078
+ "logps/chosen": -59.212501525878906,
1079
+ "logps/rejected": -390.3999938964844,
1080
+ "loss": 0.06616058349609374,
1081
+ "memory(GiB)": 86.43,
1082
+ "nll_loss": 0.06617431342601776,
1083
+ "rewards/accuracies": 1.0,
1084
+ "rewards/chosen": 23.549999237060547,
1085
+ "rewards/margins": 37.57500076293945,
1086
+ "rewards/rejected": -14.046875,
1087
+ "step": 285,
1088
+ "train_speed(iter/s)": 0.025429
1089
+ },
1090
+ {
1091
+ "epoch": 2.476595744680851,
1092
+ "grad_norm": 0.3459691107273102,
1093
+ "learning_rate": 2.4160892004010924e-07,
1094
+ "logits/chosen": -1.845703125,
1095
+ "logits/rejected": -0.737109363079071,
1096
+ "logps/chosen": -54.82500076293945,
1097
+ "logps/rejected": -380.3999938964844,
1098
+ "loss": 0.06555709838867188,
1099
+ "memory(GiB)": 86.43,
1100
+ "nll_loss": 0.06560058891773224,
1101
+ "rewards/accuracies": 1.0,
1102
+ "rewards/chosen": 23.674999237060547,
1103
+ "rewards/margins": 37.45000076293945,
1104
+ "rewards/rejected": -13.78125,
1105
+ "step": 290,
1106
+ "train_speed(iter/s)": 0.025456
1107
+ },
1108
+ {
1109
+ "epoch": 2.519148936170213,
1110
+ "grad_norm": 0.33621102571487427,
1111
+ "learning_rate": 2.0451416324810927e-07,
1112
+ "logits/chosen": -1.851171851158142,
1113
+ "logits/rejected": -0.726367175579071,
1114
+ "logps/chosen": -55.17499923706055,
1115
+ "logps/rejected": -389.0,
1116
+ "loss": 0.06555557250976562,
1117
+ "memory(GiB)": 86.43,
1118
+ "nll_loss": 0.06556396186351776,
1119
+ "rewards/accuracies": 1.0,
1120
+ "rewards/chosen": 22.631250381469727,
1121
+ "rewards/margins": 36.45000076293945,
1122
+ "rewards/rejected": -13.834375381469727,
1123
+ "step": 295,
1124
+ "train_speed(iter/s)": 0.025462
1125
+ },
1126
+ {
1127
+ "epoch": 2.5617021276595744,
1128
+ "grad_norm": 0.3450789153575897,
1129
+ "learning_rate": 1.7030146916085187e-07,
1130
+ "logits/chosen": -1.864843726158142,
1131
+ "logits/rejected": -0.7413085699081421,
1132
+ "logps/chosen": -53.76250076293945,
1133
+ "logps/rejected": -380.79998779296875,
1134
+ "loss": 0.0641754150390625,
1135
+ "memory(GiB)": 86.43,
1136
+ "nll_loss": 0.06414794921875,
1137
+ "rewards/accuracies": 1.0,
1138
+ "rewards/chosen": 22.737499237060547,
1139
+ "rewards/margins": 36.493751525878906,
1140
+ "rewards/rejected": -13.712499618530273,
1141
+ "step": 300,
1142
+ "train_speed(iter/s)": 0.025502
1143
+ },
1144
+ {
1145
+ "epoch": 2.5617021276595744,
1146
+ "eval_logits/chosen": -1.7765624523162842,
1147
+ "eval_logits/rejected": -0.6953125,
1148
+ "eval_logps/chosen": -78.2750015258789,
1149
+ "eval_logps/rejected": -407.79998779296875,
1150
+ "eval_loss": 0.08268880099058151,
1151
+ "eval_nll_loss": 0.08737792819738388,
1152
+ "eval_rewards/accuracies": 1.0,
1153
+ "eval_rewards/chosen": 23.412500381469727,
1154
+ "eval_rewards/margins": 38.0,
1155
+ "eval_rewards/rejected": -14.606249809265137,
1156
+ "eval_runtime": 17.0595,
1157
+ "eval_samples_per_second": 4.396,
1158
+ "eval_steps_per_second": 0.586,
1159
+ "step": 300
1160
+ },
1161
+ {
1162
+ "epoch": 2.604255319148936,
1163
+ "grad_norm": 0.3593633770942688,
1164
+ "learning_rate": 1.3904695063643336e-07,
1165
+ "logits/chosen": -1.878515601158142,
1166
+ "logits/rejected": -0.77197265625,
1167
+ "logps/chosen": -57.875,
1168
+ "logps/rejected": -386.3999938964844,
1169
+ "loss": 0.064154052734375,
1170
+ "memory(GiB)": 86.43,
1171
+ "nll_loss": 0.06413574516773224,
1172
+ "rewards/accuracies": 1.0,
1173
+ "rewards/chosen": 23.649999618530273,
1174
+ "rewards/margins": 37.650001525878906,
1175
+ "rewards/rejected": -13.984375,
1176
+ "step": 305,
1177
+ "train_speed(iter/s)": 0.025388
1178
+ },
1179
+ {
1180
+ "epoch": 2.646808510638298,
1181
+ "grad_norm": 0.36554569005966187,
1182
+ "learning_rate": 1.1082013949036119e-07,
1183
+ "logits/chosen": -1.890625,
1184
+ "logits/rejected": -0.768261730670929,
1185
+ "logps/chosen": -59.54999923706055,
1186
+ "logps/rejected": -386.1000061035156,
1187
+ "loss": 0.06463623046875,
1188
+ "memory(GiB)": 86.43,
1189
+ "nll_loss": 0.06468506157398224,
1190
+ "rewards/accuracies": 1.0,
1191
+ "rewards/chosen": 24.274999618530273,
1192
+ "rewards/margins": 38.20000076293945,
1193
+ "rewards/rejected": -13.925000190734863,
1194
+ "step": 310,
1195
+ "train_speed(iter/s)": 0.025368
1196
+ },
1197
+ {
1198
+ "epoch": 2.6893617021276595,
1199
+ "grad_norm": 0.3650209605693817,
1200
+ "learning_rate": 8.568383180837369e-08,
1201
+ "logits/chosen": -1.8703124523162842,
1202
+ "logits/rejected": -0.714648425579071,
1203
+ "logps/chosen": -53.162498474121094,
1204
+ "logps/rejected": -390.29998779296875,
1205
+ "loss": 0.062223052978515624,
1206
+ "memory(GiB)": 86.43,
1207
+ "nll_loss": 0.06223144382238388,
1208
+ "rewards/accuracies": 1.0,
1209
+ "rewards/chosen": 23.568750381469727,
1210
+ "rewards/margins": 37.318748474121094,
1211
+ "rewards/rejected": -13.746874809265137,
1212
+ "step": 315,
1213
+ "train_speed(iter/s)": 0.025378
1214
+ },
1215
+ {
1216
+ "epoch": 2.731914893617021,
1217
+ "grad_norm": 0.37099653482437134,
1218
+ "learning_rate": 6.369394824421365e-08,
1219
+ "logits/chosen": -1.875390648841858,
1220
+ "logits/rejected": -0.8294922113418579,
1221
+ "logps/chosen": -60.73749923706055,
1222
+ "logps/rejected": -385.8999938964844,
1223
+ "loss": 0.06792373657226562,
1224
+ "memory(GiB)": 86.43,
1225
+ "nll_loss": 0.06791992485523224,
1226
+ "rewards/accuracies": 1.0,
1227
+ "rewards/chosen": 23.037500381469727,
1228
+ "rewards/margins": 37.11249923706055,
1229
+ "rewards/rejected": -14.065625190734863,
1230
+ "step": 320,
1231
+ "train_speed(iter/s)": 0.02535
1232
+ },
1233
+ {
1234
+ "epoch": 2.774468085106383,
1235
+ "grad_norm": 0.35642552375793457,
1236
+ "learning_rate": 4.489940961314881e-08,
1237
+ "logits/chosen": -1.8425781726837158,
1238
+ "logits/rejected": -0.7470703125,
1239
+ "logps/chosen": -60.037498474121094,
1240
+ "logps/rejected": -395.1000061035156,
1241
+ "loss": 0.06998977661132813,
1242
+ "memory(GiB)": 86.43,
1243
+ "nll_loss": 0.06997070461511612,
1244
+ "rewards/accuracies": 1.0,
1245
+ "rewards/chosen": 24.143749237060547,
1246
+ "rewards/margins": 37.962501525878906,
1247
+ "rewards/rejected": -13.831250190734863,
1248
+ "step": 325,
1249
+ "train_speed(iter/s)": 0.025386
1250
+ },
1251
+ {
1252
+ "epoch": 2.8170212765957445,
1253
+ "grad_norm": 0.32820969820022583,
1254
+ "learning_rate": 2.9342028058009896e-08,
1255
+ "logits/chosen": -1.870703101158142,
1256
+ "logits/rejected": -0.7451171875,
1257
+ "logps/chosen": -54.76250076293945,
1258
+ "logps/rejected": -387.29998779296875,
1259
+ "loss": 0.06422500610351563,
1260
+ "memory(GiB)": 86.43,
1261
+ "nll_loss": 0.06422118842601776,
1262
+ "rewards/accuracies": 1.0,
1263
+ "rewards/chosen": 22.887500762939453,
1264
+ "rewards/margins": 36.88750076293945,
1265
+ "rewards/rejected": -14.028124809265137,
1266
+ "step": 330,
1267
+ "train_speed(iter/s)": 0.02541
1268
+ },
1269
+ {
1270
+ "epoch": 2.8595744680851065,
1271
+ "grad_norm": 0.35879823565483093,
1272
+ "learning_rate": 1.7056414029866018e-08,
1273
+ "logits/chosen": -1.8328125476837158,
1274
+ "logits/rejected": -0.7754882574081421,
1275
+ "logps/chosen": -53.400001525878906,
1276
+ "logps/rejected": -388.29998779296875,
1277
+ "loss": 0.064886474609375,
1278
+ "memory(GiB)": 86.43,
1279
+ "nll_loss": 0.06489257514476776,
1280
+ "rewards/accuracies": 1.0,
1281
+ "rewards/chosen": 22.431249618530273,
1282
+ "rewards/margins": 36.58124923706055,
1283
+ "rewards/rejected": -14.153124809265137,
1284
+ "step": 335,
1285
+ "train_speed(iter/s)": 0.025437
1286
+ },
1287
+ {
1288
+ "epoch": 2.902127659574468,
1289
+ "grad_norm": 0.32765164971351624,
1290
+ "learning_rate": 8.069899290277683e-09,
1291
+ "logits/chosen": -1.848046898841858,
1292
+ "logits/rejected": -0.744140625,
1293
+ "logps/chosen": -54.67499923706055,
1294
+ "logps/rejected": -380.5,
1295
+ "loss": 0.0650665283203125,
1296
+ "memory(GiB)": 86.43,
1297
+ "nll_loss": 0.06510009616613388,
1298
+ "rewards/accuracies": 1.0,
1299
+ "rewards/chosen": 22.681249618530273,
1300
+ "rewards/margins": 36.70000076293945,
1301
+ "rewards/rejected": -14.009374618530273,
1302
+ "step": 340,
1303
+ "train_speed(iter/s)": 0.025437
1304
+ },
1305
+ {
1306
+ "epoch": 2.94468085106383,
1307
+ "grad_norm": 0.370295912027359,
1308
+ "learning_rate": 2.4024761064254664e-09,
1309
+ "logits/chosen": -1.872656226158142,
1310
+ "logits/rejected": -0.7118164300918579,
1311
+ "logps/chosen": -57.849998474121094,
1312
+ "logps/rejected": -377.5,
1313
+ "loss": 0.06773147583007813,
1314
+ "memory(GiB)": 86.43,
1315
+ "nll_loss": 0.06773681938648224,
1316
+ "rewards/accuracies": 1.0,
1317
+ "rewards/chosen": 23.737499237060547,
1318
+ "rewards/margins": 37.337501525878906,
1319
+ "rewards/rejected": -13.590624809265137,
1320
+ "step": 345,
1321
+ "train_speed(iter/s)": 0.02546
1322
+ },
1323
+ {
1324
+ "epoch": 2.9872340425531916,
1325
+ "grad_norm": 0.3416670560836792,
1326
+ "learning_rate": 6.675277438356054e-11,
1327
+ "logits/chosen": -1.8679687976837158,
1328
+ "logits/rejected": -0.7328125238418579,
1329
+ "logps/chosen": -56.537498474121094,
1330
+ "logps/rejected": -390.0,
1331
+ "loss": 0.06469192504882812,
1332
+ "memory(GiB)": 86.43,
1333
+ "nll_loss": 0.06467285007238388,
1334
+ "rewards/accuracies": 1.0,
1335
+ "rewards/chosen": 22.943750381469727,
1336
+ "rewards/margins": 36.98749923706055,
1337
+ "rewards/rejected": -14.0625,
1338
+ "step": 350,
1339
+ "train_speed(iter/s)": 0.025452
1340
+ },
1341
+ {
1342
+ "epoch": 2.9957446808510637,
1343
+ "eval_logits/chosen": -1.7937500476837158,
1344
+ "eval_logits/rejected": -0.7124999761581421,
1345
+ "eval_logps/chosen": -77.80000305175781,
1346
+ "eval_logps/rejected": -408.6000061035156,
1347
+ "eval_loss": 0.08202473819255829,
1348
+ "eval_nll_loss": 0.08659668266773224,
1349
+ "eval_rewards/accuracies": 1.0,
1350
+ "eval_rewards/chosen": 23.399999618530273,
1351
+ "eval_rewards/margins": 38.087501525878906,
1352
+ "eval_rewards/rejected": -14.662500381469727,
1353
+ "eval_runtime": 17.0317,
1354
+ "eval_samples_per_second": 4.404,
1355
+ "eval_steps_per_second": 0.587,
1356
+ "step": 351
1357
+ }
1358
+ ],
1359
+ "logging_steps": 5,
1360
+ "max_steps": 351,
1361
+ "num_input_tokens_seen": 0,
1362
+ "num_train_epochs": 3,
1363
+ "save_steps": 100,
1364
+ "stateful_callbacks": {
1365
+ "TrainerControl": {
1366
+ "args": {
1367
+ "should_epoch_stop": false,
1368
+ "should_evaluate": false,
1369
+ "should_log": false,
1370
+ "should_save": true,
1371
+ "should_training_stop": true
1372
+ },
1373
+ "attributes": {}
1374
+ }
1375
+ },
1376
+ "total_flos": 5.038030084192076e+18,
1377
+ "train_batch_size": 2,
1378
+ "trial_name": null,
1379
+ "trial_params": null
1380
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e47f3d04dd20592f19e1841981d8fc3ebac09d1651128b7a34cf21e8779e25
3
+ size 8952
vocab.json ADDED
The diff for this file is too large to render. See raw diff