Hugging Face's logo

GUIAgent
/
MagicGUI_RFT

Safetensors
English
qwen2_vl
Model card Files
xet
Community
root commited on
Commit
1b1a2c7
·
1 Parent(s): 19ef17b

0901

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. added_tokens.json +16 -0
  2. args.json +462 -0
  3. chat_template.json +3 -0
  4. config.json +49 -0
  5. generation_config.json +11 -0
  6. latest +1 -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 +737 -0
  13. preprocessor_config.json +29 -0
  14. rng_state_0.pth +3 -0
  15. rng_state_1.pth +3 -0
  16. rng_state_10.pth +3 -0
  17. rng_state_11.pth +3 -0
  18. rng_state_12.pth +3 -0
  19. rng_state_13.pth +3 -0
  20. rng_state_14.pth +3 -0
  21. rng_state_15.pth +3 -0
  22. rng_state_16.pth +3 -0
  23. rng_state_17.pth +3 -0
  24. rng_state_18.pth +3 -0
  25. rng_state_19.pth +3 -0
  26. rng_state_2.pth +3 -0
  27. rng_state_20.pth +3 -0
  28. rng_state_21.pth +3 -0
  29. rng_state_22.pth +3 -0
  30. rng_state_23.pth +3 -0
  31. rng_state_24.pth +3 -0
  32. rng_state_25.pth +3 -0
  33. rng_state_26.pth +3 -0
  34. rng_state_27.pth +3 -0
  35. rng_state_28.pth +3 -0
  36. rng_state_29.pth +3 -0
  37. rng_state_3.pth +3 -0
  38. rng_state_30.pth +3 -0
  39. rng_state_31.pth +3 -0
  40. rng_state_4.pth +3 -0
  41. rng_state_5.pth +3 -0
  42. rng_state_6.pth +3 -0
  43. rng_state_7.pth +3 -0
  44. rng_state_8.pth +3 -0
  45. rng_state_9.pth +3 -0
  46. scheduler.pt +3 -0
  47. special_tokens_map.json +31 -0
  48. tokenizer.json +3 -0
  49. tokenizer_config.json +145 -0
  50. trainer_state.json +1409 -0
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
args.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783",
3
+ "model_type": "qwen2_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": "flash_attn",
8
+ "num_labels": null,
9
+ "rope_scaling": null,
10
+ "device_map": null,
11
+ "max_memory": {},
12
+ "local_repo_path": null,
13
+ "template": "qwen2_vl",
14
+ "system": "",
15
+ "max_length": 6144,
16
+ "truncation_strategy": "left",
17
+ "max_pixels": null,
18
+ "tools_prompt": "react_en",
19
+ "norm_bbox": null,
20
+ "response_prefix": null,
21
+ "padding_side": "right",
22
+ "loss_scale": "last_round",
23
+ "sequence_parallel_size": 1,
24
+ "use_chat_template": true,
25
+ "template_backend": "swift",
26
+ "dataset": [
27
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/open-data/finish_android_control_test_hl_2_text_roll_fix.json",
28
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/open-data/finish_android_control_test_ll_2_text_roll_fix.json",
29
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/open-data/odyssey_test_hl_2_text_roll_fix.json",
30
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_data_Zhedie_410_rl.jsonl",
31
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_data_Zhedie_418_rl.jsonl",
32
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_data_zhedie_rl.jsonl",
33
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_page_auto_crawler_220_rl.jsonl",
34
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_page_auto_crawler_314_rl.jsonl",
35
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_page_auto_crawler_1206_rl.jsonl",
36
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_page_auto_crawler_supply_rl.jsonl",
37
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/action_intent_QA_page_auto_crawler_supply2_rl.jsonl",
38
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_action_from_labelstudio_V1train_rl.jsonl",
39
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_action_human_processed2train_update_rl.jsonl",
40
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_action_human_processed3_612train_update_rl.jsonl",
41
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_action_human_processed3_620_takeovertrain_update_rl.jsonl",
42
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_action_human_processedtrain_update_rl.jsonl",
43
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_data_first_same_widget_info_update0527train_update_rl.jsonl",
44
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_data_grounding_action_info_update0527train_update_rl.jsonl",
45
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_data_grounding_action_negative_update0527train_update_rl.jsonl",
46
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/annot_data_grounding_noanswer_action_negative_info_update0527train_update_rl.jsonl",
47
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/enter_train_data_all_finaltrain_update_rl.jsonl",
48
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/HL_annot_action_human_processed2train_rl.jsonl",
49
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/HL_annot_action_human_processed3_612train_rl.jsonl",
50
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/HL_annot_action_human_processedtrain_rl.jsonl",
51
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/navigate_backtrain_rl.jsonl",
52
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/position_describe_error_negative_action_data_finaltrain_update_rl.jsonl",
53
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/relative_position_no_answertrain_update_rl.jsonl",
54
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/spatial_position_p1_check_cleantrain_update_rl.jsonl",
55
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/spatial_position_p2_check2_clean_new_v2train_update_rl.jsonl",
56
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/spatial_position_p3train_post_checktrain_rl.jsonl"
57
+ ],
58
+ "val_dataset": [
59
+ "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/data/spatial_position_p3train_post_checktrain_rl.jsonl"
60
+ ],
61
+ "split_dataset_ratio": 0.0,
62
+ "data_seed": 42,
63
+ "dataset_num_proc": 1,
64
+ "streaming": false,
65
+ "enable_cache": false,
66
+ "download_mode": "reuse_dataset_if_exists",
67
+ "columns": {},
68
+ "strict": false,
69
+ "remove_unused_columns": false,
70
+ "model_name": [
71
+ null,
72
+ null
73
+ ],
74
+ "model_author": [
75
+ null,
76
+ null
77
+ ],
78
+ "custom_dataset_info": [],
79
+ "quant_method": null,
80
+ "quant_bits": null,
81
+ "hqq_axis": null,
82
+ "bnb_4bit_compute_dtype": "bfloat16",
83
+ "bnb_4bit_quant_type": "nf4",
84
+ "bnb_4bit_use_double_quant": true,
85
+ "bnb_4bit_quant_storage": null,
86
+ "max_new_tokens": 64,
87
+ "temperature": 0.9,
88
+ "top_k": 20,
89
+ "top_p": 0.96,
90
+ "repetition_penalty": 1.1,
91
+ "num_beams": 1,
92
+ "stream": false,
93
+ "stop_words": [],
94
+ "logprobs": false,
95
+ "top_logprobs": null,
96
+ "ckpt_dir": null,
97
+ "load_dataset_config": null,
98
+ "lora_modules": [],
99
+ "tuner_backend": "peft",
100
+ "train_type": "full",
101
+ "adapters": [],
102
+ "external_plugins": [
103
+ "examples/train/grpo/plugin/plugin.py"
104
+ ],
105
+ "seed": 42,
106
+ "model_kwargs": {},
107
+ "load_args": false,
108
+ "load_data_args": false,
109
+ "use_hf": false,
110
+ "hub_token": null,
111
+ "custom_register_path": [],
112
+ "ignore_args_error": false,
113
+ "use_swift_lora": false,
114
+ "output_dir": "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/outputs-HL-LL-finish-test-exchange-1x1x-self-final/multi4-CPT-Query-v2/v1-CPT703/qwen2_vl-CPT703Queryv2-grpo-pattern2-RMMulti_Action_NoThink_NewAct/v0-20250714-092403",
115
+ "overwrite_output_dir": false,
116
+ "do_train": false,
117
+ "do_eval": false,
118
+ "do_predict": false,
119
+ "eval_strategy": "no",
120
+ "prediction_loss_only": false,
121
+ "per_device_train_batch_size": 8,
122
+ "per_device_eval_batch_size": 8,
123
+ "per_gpu_train_batch_size": null,
124
+ "per_gpu_eval_batch_size": null,
125
+ "gradient_accumulation_steps": 1,
126
+ "eval_accumulation_steps": null,
127
+ "eval_delay": 0,
128
+ "torch_empty_cache_steps": null,
129
+ "learning_rate": 1e-06,
130
+ "weight_decay": 0.1,
131
+ "adam_beta1": 0.9,
132
+ "adam_beta2": 0.999,
133
+ "adam_epsilon": 1e-08,
134
+ "max_grad_norm": 0.5,
135
+ "num_train_epochs": 1.0,
136
+ "max_steps": -1,
137
+ "lr_scheduler_type": "cosine",
138
+ "lr_scheduler_kwargs": null,
139
+ "warmup_ratio": 0.01,
140
+ "warmup_steps": 0,
141
+ "log_level": "passive",
142
+ "log_level_replica": "warning",
143
+ "log_on_each_node": true,
144
+ "logging_dir": "/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/outputs-HL-LL-finish-test-exchange-1x1x-self-final/multi4-CPT-Query-v2/v1-CPT703/qwen2_vl-CPT703Queryv2-grpo-pattern2-RMMulti_Action_NoThink_NewAct/v0-20250714-092403/runs",
145
+ "logging_strategy": "steps",
146
+ "logging_first_step": true,
147
+ "logging_steps": 100,
148
+ "logging_nan_inf_filter": true,
149
+ "save_strategy": "steps",
150
+ "save_steps": 500.0,
151
+ "save_total_limit": 15,
152
+ "save_safetensors": true,
153
+ "save_on_each_node": false,
154
+ "save_only_model": false,
155
+ "restore_callback_states_from_checkpoint": false,
156
+ "no_cuda": false,
157
+ "use_cpu": false,
158
+ "use_mps_device": false,
159
+ "jit_mode_eval": false,
160
+ "use_ipex": false,
161
+ "bf16": true,
162
+ "fp16": false,
163
+ "fp16_opt_level": "O1",
164
+ "half_precision_backend": "auto",
165
+ "bf16_full_eval": false,
166
+ "fp16_full_eval": false,
167
+ "tf32": null,
168
+ "local_rank": 0,
169
+ "ddp_backend": null,
170
+ "tpu_num_cores": null,
171
+ "tpu_metrics_debug": false,
172
+ "debug": null,
173
+ "dataloader_drop_last": false,
174
+ "eval_steps": null,
175
+ "dataloader_num_workers": 8,
176
+ "dataloader_prefetch_factor": null,
177
+ "past_index": -1,
178
+ "run_name": null,
179
+ "disable_tqdm": null,
180
+ "label_names": null,
181
+ "load_best_model_at_end": false,
182
+ "metric_for_best_model": "reward",
183
+ "greater_is_better": true,
184
+ "ignore_data_skip": false,
185
+ "fsdp": "",
186
+ "fsdp_min_num_params": 0,
187
+ "fsdp_config": null,
188
+ "tp_size": 0,
189
+ "fsdp_transformer_layer_cls_to_wrap": null,
190
+ "accelerator_config": {
191
+ "dispatch_batches": false
192
+ },
193
+ "deepspeed": {
194
+ "fp16": {
195
+ "enabled": "auto",
196
+ "loss_scale": 0,
197
+ "loss_scale_window": 1000,
198
+ "initial_scale_power": 16,
199
+ "hysteresis": 2,
200
+ "min_loss_scale": 1
201
+ },
202
+ "bf16": {
203
+ "enabled": "auto"
204
+ },
205
+ "zero_optimization": {
206
+ "stage": 3,
207
+ "offload_optimizer": {
208
+ "device": "none",
209
+ "pin_memory": true
210
+ },
211
+ "offload_param": {
212
+ "device": "none",
213
+ "pin_memory": true
214
+ },
215
+ "overlap_comm": true,
216
+ "contiguous_gradients": true,
217
+ "sub_group_size": 1000000000.0,
218
+ "reduce_bucket_size": "auto",
219
+ "zero_quantized_weights": false,
220
+ "zero_quantized_gradients": false,
221
+ "stage3_prefetch_bucket_size": 0,
222
+ "stage3_param_persistence_threshold": "auto",
223
+ "stage3_max_live_parameters": 1000000000.0,
224
+ "stage3_max_reuse_distance": 1000000000.0,
225
+ "stage3_gather_16bit_weights_on_model_save": true
226
+ },
227
+ "gradient_accumulation_steps": "auto",
228
+ "gradient_clipping": "auto",
229
+ "steps_per_print": 2000,
230
+ "train_batch_size": "auto",
231
+ "train_micro_batch_size_per_gpu": "auto",
232
+ "wall_clock_breakdown": false
233
+ },
234
+ "label_smoothing_factor": 0.0,
235
+ "optim": "adamw_torch",
236
+ "optim_args": null,
237
+ "adafactor": false,
238
+ "group_by_length": false,
239
+ "length_column_name": "length",
240
+ "report_to": [
241
+ "tensorboard"
242
+ ],
243
+ "ddp_find_unused_parameters": null,
244
+ "ddp_bucket_cap_mb": null,
245
+ "ddp_broadcast_buffers": null,
246
+ "dataloader_pin_memory": true,
247
+ "dataloader_persistent_workers": false,
248
+ "skip_memory_metrics": true,
249
+ "use_legacy_prediction_loop": false,
250
+ "push_to_hub": false,
251
+ "resume_from_checkpoint": null,
252
+ "hub_model_id": null,
253
+ "hub_strategy": "every_save",
254
+ "hub_private_repo": null,
255
+ "hub_always_push": false,
256
+ "gradient_checkpointing": true,
257
+ "gradient_checkpointing_kwargs": null,
258
+ "include_inputs_for_metrics": false,
259
+ "include_for_metrics": [],
260
+ "eval_do_concat_batches": true,
261
+ "fp16_backend": "auto",
262
+ "evaluation_strategy": "no",
263
+ "push_to_hub_model_id": null,
264
+ "push_to_hub_organization": null,
265
+ "push_to_hub_token": null,
266
+ "mp_parameters": "",
267
+ "auto_find_batch_size": false,
268
+ "full_determinism": false,
269
+ "torchdynamo": null,
270
+ "ray_scope": "last",
271
+ "ddp_timeout": 1800,
272
+ "torch_compile": false,
273
+ "torch_compile_backend": null,
274
+ "torch_compile_mode": null,
275
+ "dispatch_batches": null,
276
+ "split_batches": null,
277
+ "include_tokens_per_second": false,
278
+ "include_num_input_tokens_seen": false,
279
+ "neftune_noise_alpha": null,
280
+ "optim_target_modules": null,
281
+ "batch_eval_metrics": false,
282
+ "eval_on_start": false,
283
+ "use_liger_kernel": false,
284
+ "eval_use_gather_object": false,
285
+ "average_tokens_across_devices": false,
286
+ "sortish_sampler": false,
287
+ "predict_with_generate": false,
288
+ "generation_max_length": null,
289
+ "generation_num_beams": null,
290
+ "generation_config": null,
291
+ "freeze_parameters": [
292
+ "visual",
293
+ "visual.merger"
294
+ ],
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "freeze_llm": false,
298
+ "freeze_vit": true,
299
+ "freeze_aligner": true,
300
+ "target_modules": [
301
+ "all-linear"
302
+ ],
303
+ "target_regex": null,
304
+ "modules_to_save": [],
305
+ "lora_rank": 8,
306
+ "lora_alpha": 32,
307
+ "lora_dropout": 0.05,
308
+ "lora_bias": "none",
309
+ "lora_dtype": null,
310
+ "lorap_lr_ratio": null,
311
+ "use_rslora": false,
312
+ "use_dora": false,
313
+ "lora_ga_batch_size": 2,
314
+ "lora_ga_iters": 2,
315
+ "lora_ga_max_length": 1024,
316
+ "lora_ga_direction": "ArB2r",
317
+ "lora_ga_scale": "stable",
318
+ "lora_ga_stable_gamma": 16,
319
+ "init_weights": true,
320
+ "fourier_n_frequency": 2000,
321
+ "fourier_scaling": 300.0,
322
+ "boft_block_size": 4,
323
+ "boft_block_num": 0,
324
+ "boft_n_butterfly_factor": 1,
325
+ "boft_dropout": 0.0,
326
+ "vera_rank": 256,
327
+ "vera_projection_prng_key": 0,
328
+ "vera_dropout": 0.0,
329
+ "vera_d_initial": 0.1,
330
+ "adapter_act": "gelu",
331
+ "adapter_length": 128,
332
+ "use_galore": false,
333
+ "galore_target_modules": null,
334
+ "galore_rank": 128,
335
+ "galore_update_proj_gap": 50,
336
+ "galore_scale": 1.0,
337
+ "galore_proj_type": "std",
338
+ "galore_optim_per_parameter": false,
339
+ "galore_with_embedding": false,
340
+ "galore_quantization": false,
341
+ "galore_proj_quant": false,
342
+ "galore_proj_bits": 4,
343
+ "galore_proj_group_size": 256,
344
+ "galore_cos_threshold": 0.4,
345
+ "galore_gamma_proj": 2,
346
+ "galore_queue_size": 5,
347
+ "adalora_target_r": 8,
348
+ "adalora_init_r": 12,
349
+ "adalora_tinit": 0,
350
+ "adalora_tfinal": 0,
351
+ "adalora_deltaT": 1,
352
+ "adalora_beta1": 0.85,
353
+ "adalora_beta2": 0.85,
354
+ "adalora_orth_reg_weight": 0.5,
355
+ "llamapro_num_new_blocks": 4,
356
+ "llamapro_num_groups": null,
357
+ "lisa_activated_layers": 0,
358
+ "lisa_step_interval": 20,
359
+ "reft_layer_key": null,
360
+ "reft_layers": null,
361
+ "reft_rank": 4,
362
+ "reft_intervention_type": "LoreftIntervention",
363
+ "reft_args": null,
364
+ "use_liger": false,
365
+ "model_layer_cls_name": null,
366
+ "metric_warmup_step": 0,
367
+ "fsdp_num": 1,
368
+ "acc_steps": 1,
369
+ "swanlab_token": null,
370
+ "swanlab_project": null,
371
+ "swanlab_workspace": null,
372
+ "swanlab_exp_name": null,
373
+ "swanlab_mode": "cloud",
374
+ "add_version": true,
375
+ "resume_only_model": false,
376
+ "check_model": true,
377
+ "create_checkpoint_symlink": false,
378
+ "packing": false,
379
+ "lazy_tokenize": true,
380
+ "loss_type": null,
381
+ "optimizer": null,
382
+ "metric": null,
383
+ "acc_strategy": "token",
384
+ "zero_hpz_partition_size": null,
385
+ "reward_model": null,
386
+ "reward_adapters": [],
387
+ "reward_model_type": null,
388
+ "reward_model_revision": null,
389
+ "num_ppo_epochs": 4,
390
+ "whiten_rewards": false,
391
+ "kl_coef": 0.05,
392
+ "cliprange": 0.2,
393
+ "vf_coef": 0.1,
394
+ "cliprange_value": 0.2,
395
+ "gamma": 1.0,
396
+ "lam": 0.95,
397
+ "num_mini_batches": 1,
398
+ "local_rollout_forward_batch_size": 64,
399
+ "num_sample_generations": 10,
400
+ "response_length": 512,
401
+ "missing_eos_penalty": null,
402
+ "num_infer_workers": 1,
403
+ "vllm_max_num_seqs": 256,
404
+ "vllm_enforce_eager": false,
405
+ "vllm_limit_mm_per_prompt": null,
406
+ "vllm_enable_prefix_caching": true,
407
+ "cosine_min_len_value_wrong": 0.0,
408
+ "cosine_max_len_value_wrong": -0.5,
409
+ "cosine_min_len_value_correct": 1.0,
410
+ "cosine_max_len_value_correct": 0.5,
411
+ "cosine_max_len": null,
412
+ "repetition_n_grams": 3,
413
+ "repetition_max_penalty": -1.0,
414
+ "use_lmdeploy": false,
415
+ "lmdeploy_device": "auto",
416
+ "lmdeploy_session_len": null,
417
+ "lmdeploy_cache_max_entry_count": 0.8,
418
+ "async_generate": false,
419
+ "tensor_parallel_size": 1,
420
+ "sleep_level": 0,
421
+ "move_model_batches": null,
422
+ "offload_optimizer": false,
423
+ "offload_model": false,
424
+ "gc_collect_after_offload": false,
425
+ "num_generations": 8,
426
+ "max_completion_length": 512,
427
+ "ds3_gather_for_generation": true,
428
+ "reward_funcs": [
429
+ "external_multi_action_nothink_newaction"
430
+ ],
431
+ "reward_weights": null,
432
+ "log_completions": true,
433
+ "use_vllm": false,
434
+ "vllm_device": [
435
+ "auto"
436
+ ],
437
+ "vllm_gpu_memory_utilization": 0.9,
438
+ "vllm_max_model_len": null,
439
+ "num_iterations": 1,
440
+ "epsilon": 0.2,
441
+ "rlhf_type": "grpo",
442
+ "ref_model": "/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783",
443
+ "ref_model_type": "qwen2_vl",
444
+ "ref_model_revision": null,
445
+ "beta": 0.04,
446
+ "label_smoothing": 0,
447
+ "rpo_alpha": 1.0,
448
+ "cpo_alpha": 1.0,
449
+ "simpo_gamma": 1,
450
+ "desirable_weight": 1.0,
451
+ "undesirable_weight": 1.0,
452
+ "dynamic_pattern": 2,
453
+ "rank": 0,
454
+ "global_world_size": 32,
455
+ "local_world_size": 8,
456
+ "model_suffix": "checkpoint-1783",
457
+ "model_info": "ModelInfo(model_type='qwen2_vl', model_dir='/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783', torch_dtype=torch.bfloat16, max_model_len=32768, 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)",
458
+ "model_meta": "ModelMeta(model_type='qwen2_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct', hf_model_id='Qwen/Qwen2-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct', hf_model_id='Qwen/Qwen2-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct', hf_model_id='Qwen/Qwen2-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B', hf_model_id='Qwen/Qwen2-VL-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B', hf_model_id='Qwen/Qwen2-VL-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B', hf_model_id='Qwen/Qwen2-VL-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='bytedance-research/UI-TARS-2B-SFT', hf_model_id='bytedance-research/UI-TARS-2B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-7B-SFT', hf_model_id='bytedance-research/UI-TARS-7B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-7B-DPO', hf_model_id='bytedance-research/UI-TARS-7B-DPO', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-72B-SFT', hf_model_id='bytedance-research/UI-TARS-72B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-72B-DPO', hf_model_id='bytedance-research/UI-TARS-72B-DPO', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='allenai/olmOCR-7B-0225-preview', hf_model_id='allenai/olmOCR-7B-0225-preview', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_vl', get_function=<function get_model_tokenizer_qwen2_vl at 0x7fb2fb400040>, model_arch='qwen2_vl', architectures=['Qwen2VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.45', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
459
+ "model_dir": "/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783",
460
+ "hub": "<class 'swift.hub.hub.MSHub'>",
461
+ "training_args": "GRPOConfig(output_dir='/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/outputs-HL-LL-finish-test-exchange-1x1x-self-final/multi4-CPT-Query-v2/v1-CPT703/qwen2_vl-CPT703Queryv2-grpo-pattern2-RMMulti_Action_NoThink_NewAct/v0-20250714-092403', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=8, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/outputs-HL-LL-finish-test-exchange-1x1x-self-final/multi4-CPT-Query-v2/v1-CPT703/qwen2_vl-CPT703Queryv2-grpo-pattern2-RMMulti_Action_NoThink_NewAct/v0-20250714-092403/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=100, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=15, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=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=None, dataloader_num_workers=8, dataloader_prefetch_factor=None, past_index=-1, run_name='/opt/nas/p/dongshaokang/ms-swift-test-dynamic-training-v630lock/outputs-HL-LL-finish-test-exchange-1x1x-self-final/multi4-CPT-Query-v2/v1-CPT703/qwen2_vl-CPT703Queryv2-grpo-pattern2-RMMulti_Action_NoThink_NewAct/v0-20250714-092403', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='no', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, dynamic_pattern=2, max_prompt_length=512, num_generations=8, max_completion_length=512, ds3_gather_for_generation=True, temperature=0.9, top_p=0.96, top_k=20, min_p=None, repetition_penalty=1.1, cache_implementation=None, use_vllm=False, vllm_server_host='0.0.0.0', vllm_server_port=8000, vllm_server_timeout=120.0, vllm_guided_decoding_regex=None, beta=0.04, num_iterations=1, epsilon=0.2, epsilon_high=None, reward_weights=None, scale_rewards=True, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, log_completions=True, vllm_device=['auto'], vllm_gpu_memory_utilization=0.9, vllm_dtype=None, vllm_max_model_len=None, vllm_enable_prefix_caching=True, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='full', optimizer=None, local_repo_path=None, galore_config=None, num_infer_workers=1, vllm_max_num_seqs=256, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, cosine_min_len_value_wrong=0.0, cosine_max_len_value_wrong=-0.5, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=512, repetition_n_grams=3, repetition_max_penalty=-1.0, use_lmdeploy=False, lmdeploy_device='auto', lmdeploy_session_len=None, lmdeploy_cache_max_entry_count=0.8, async_generate=False, tensor_parallel_size=1, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, stop_words=[])"
462
+ }
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 151643,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "mrope_section": [
24
+ 16,
25
+ 24,
26
+ 24
27
+ ],
28
+ "rope_type": "default",
29
+ "type": "default"
30
+ },
31
+ "rope_theta": 1000000.0,
32
+ "sliding_window": 32768,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.50.0.dev0",
36
+ "use_cache": false,
37
+ "use_sliding_window": false,
38
+ "video_token_id": 151656,
39
+ "vision_config": {
40
+ "in_chans": 3,
41
+ "model_type": "qwen2_vl",
42
+ "spatial_patch_size": 14,
43
+ "torch_dtype": "bfloat16"
44
+ },
45
+ "vision_end_token_id": 151653,
46
+ "vision_start_token_id": 151652,
47
+ "vision_token_id": 151654,
48
+ "vocab_size": 152064
49
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151645,
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151643,
7
+ "temperature": 0.01,
8
+ "top_k": 1,
9
+ "top_p": 0.001,
10
+ "transformers_version": "4.50.0.dev0"
11
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step8500
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 sha256:1a630664b92c0264b403a54404707001ba374c619e558e8dc99546edfa24f0bc
3
+ size 4966659944
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b80214431ec0222329616c76a270b6c9265ca12de94d6e3879ba2d5fb9147c
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:e66d7af94dcc4c32c862b2c9fbc742cbf8f14ccc7be98c6b3cb1f69ac8bc2654
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:e905a6dab8eee5b2811ecb1c522182e401d67cb7c99c01562671e0f9dd43a700
3
+ size 1691924384
model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16582751232
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.fc1.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm2.bias": "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.fc1.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3516fed51fd889a7d628f11af3b032eac58862ced6519a57be559c13b1394f6a
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237d17a57f0b7bb2fd1f36f308c65cede7a5b16f465068ec6f4acf1d0c3338a1
3
+ size 15920
rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3812bb9c2b86e0ffca9c03bfd90c5310726957c2558e1814352ed4e031c35cb8
3
+ size 15933
rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe2d59985fadbf34df0e328ef186824168d003636f255e55195f04e3e837a63
3
+ size 15997
rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3d11efa017e62684297f9f27539451e7b7366fc689b502938e62ed1fd38460
3
+ size 15997
rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e3d26e03e5d15923ebcc822da636d3a6ed5a2e6cfe43eaea855aea9154ca3b
3
+ size 15933
rng_state_14.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3620df88d384ab0da316ad251734a960a5bea6410167c36efd3fd366bf13d61
3
+ size 15997
rng_state_15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fe638a853627ccc624357be35967be1f5b1e9ee313c278e43632e110f3a742
3
+ size 15997
rng_state_16.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1d1be60d9eca5150c1683f6e7c0d06b9178468e8a1753880144f78400e640c
3
+ size 15933
rng_state_17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51b4bec619720f5e5471936463533a469ac1a338e47a88295a48b5b079bf1f3
3
+ size 15997
rng_state_18.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a66f494c532a91865248916d331cb2a4324ff063bc3e9c9e23731bd161c8b2
3
+ size 15997
rng_state_19.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be2a90060ca3459ebaee6175ad7ad2986fe6beabbfbff634cf761b312199365
3
+ size 15997
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee6c788f5a632737e4035d3a7110d0ff601a9063951ccc7f62b1857f1646024
3
+ size 15920
rng_state_20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42123af4ae4351d9ef454afad0fd26956e913442502a232cf9ec78db35e7405d
3
+ size 15997
rng_state_21.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7812a6a1950f24ec90144a2f1040a4d71225fc8f48cf0bf361a66be38009c4d7
3
+ size 15997
rng_state_22.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c326eac506e9a9fc919424e7a8c79174995f6a8a7ce33832312151c95f4859
3
+ size 16061
rng_state_23.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c055c4981bd042024e40ecc4897c6065de4b6d017c053c025824fec984eea5
3
+ size 15933
rng_state_24.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b9a495c301dfbe37336852d81606ce731470d54c214cb5bae7e888c7b9f2b3
3
+ size 15933
rng_state_25.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35006c67ee4ee183963dc9d9fb81796dd18d53b8bc4339ab4b58ecea7d93b45f
3
+ size 15869
rng_state_26.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aeed0295a6ba27f79ae9819226c5cfb1d00ff405a4ea042bc7f6b48122035de
3
+ size 16061
rng_state_27.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ba678fc27ae25861b8a597cc244b88decb03b5df082ed6827aec0100769716
3
+ size 15933
rng_state_28.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0499bb85eaaa33f357dda84513a0b40c4c3d4694d3454340b005c0c5381a894c
3
+ size 15997
rng_state_29.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98de8ac5cff705066dab78f48c3c9ca71d29e3c065e7b2e1ff742ee1a0eb665
3
+ size 15997
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa5202a552c3bfa2ae957cf54bbf3180de790bddac014c6da73a5e9f57d6a5a
3
+ size 15984
rng_state_30.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39ca3e50eed446efad76a000792d4d45686e114ded39f7df6ee75056da3ae85
3
+ size 15997
rng_state_31.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c6ffdcf9e62cafbf1b68e9edd4d87f3cdb03d9471688b2cf0fbafe5ee75a17
3
+ size 15933
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4116a20107aedb1df918dc3a5ccb5ad2a53637bcf6edc0e70abbf86f5a93a8ee
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a391fe5119b2b00a9e2b18351796e5ebc4b156bc680e9fa3ea3b0159b405edfa
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296ebc33e185b8219f35bff29a7f7fc183878d03b17fe15682c683b31be092dc
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac41a15a0959072ad95a938a9ca8500d2bc6b55b98bdcd77fc5bae4698dfe788
3
+ size 15920
rng_state_8.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08619f7be898a8c86e1f49ce051107b19a5cf056896cc78d0296d3f234a288ab
3
+ size 15984
rng_state_9.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10e1a0c04e20de7354b143423a14192891c9051ac7c1e82b179484c6228be61
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7074979efaf22fe3cfda0e797b6935fdf3b63b3b0209d46ef7da6ecf3268790e
3
+ size 1064
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 sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "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 %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "model_max_length": 32768,
139
+ "pad_token": "<|endoftext|>",
140
+ "padding_side": "left",
141
+ "processor_class": "Qwen2VLProcessor",
142
+ "split_special_tokens": false,
143
+ "tokenizer_class": "Qwen2Tokenizer",
144
+ "unk_token": null
145
+ }
trainer_state.json ADDED
@@ -0,0 +1,1409 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9882571793977445,
5
+ "eval_steps": 500,
6
+ "global_step": 8500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "clip_ratio": 0.0,
13
+ "completion_length": 9.5546875,
14
+ "epoch": 0.0001162655505173817,
15
+ "grad_norm": 4.281470286839314,
16
+ "kl": 0.0,
17
+ "learning_rate": 1.1494252873563218e-08,
18
+ "loss": 0.024247150868177414,
19
+ "memory(GiB)": 38.7,
20
+ "response_clip_ratio": 0.0,
21
+ "reward": 1.191904902458191,
22
+ "reward_std": 0.2820184826850891,
23
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.191904902458191,
24
+ "step": 1,
25
+ "train_speed(iter/s)": 0.026594
26
+ },
27
+ {
28
+ "clip_ratio": 0.0,
29
+ "completion_length": 9.550307765151516,
30
+ "epoch": 0.01162655505173817,
31
+ "grad_norm": 3.349521431788205,
32
+ "kl": 0.042687281213625514,
33
+ "learning_rate": 9.99994247477391e-07,
34
+ "loss": 0.006692861065720067,
35
+ "memory(GiB)": 49.8,
36
+ "response_clip_ratio": 0.0,
37
+ "reward": 1.103371890506359,
38
+ "reward_std": 0.4002408231749679,
39
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.103371890506359,
40
+ "step": 100,
41
+ "train_speed(iter/s)": 0.093985
42
+ },
43
+ {
44
+ "clip_ratio": 0.0,
45
+ "completion_length": 9.4905078125,
46
+ "epoch": 0.02325311010347634,
47
+ "grad_norm": 6.366169338883484,
48
+ "kl": 0.09955322265625,
49
+ "learning_rate": 9.995654233098478e-07,
50
+ "loss": 0.0052225708961486815,
51
+ "memory(GiB)": 49.84,
52
+ "response_clip_ratio": 0.0,
53
+ "reward": 1.2144100672006608,
54
+ "reward_std": 0.26068811796605584,
55
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.2144100672006608,
56
+ "step": 200,
57
+ "train_speed(iter/s)": 0.09568
58
+ },
59
+ {
60
+ "clip_ratio": 0.0,
61
+ "completion_length": 9.5164453125,
62
+ "epoch": 0.03487966515521451,
63
+ "grad_norm": 8.965565147378136,
64
+ "kl": 0.123232421875,
65
+ "learning_rate": 9.98456494798275e-07,
66
+ "loss": 0.005987527966499329,
67
+ "memory(GiB)": 49.84,
68
+ "response_clip_ratio": 0.0,
69
+ "reward": 1.268085294365883,
70
+ "reward_std": 0.2155047995969653,
71
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.268085294365883,
72
+ "step": 300,
73
+ "train_speed(iter/s)": 0.095899
74
+ },
75
+ {
76
+ "clip_ratio": 0.0,
77
+ "completion_length": 9.3789453125,
78
+ "epoch": 0.04650622020695268,
79
+ "grad_norm": 5.398711016783826,
80
+ "kl": 0.1314990234375,
81
+ "learning_rate": 9.966689716290176e-07,
82
+ "loss": 0.006581841707229614,
83
+ "memory(GiB)": 49.84,
84
+ "response_clip_ratio": 0.0,
85
+ "reward": 1.3075979512929916,
86
+ "reward_std": 0.1733351560495794,
87
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3075979512929916,
88
+ "step": 400,
89
+ "train_speed(iter/s)": 0.095915
90
+ },
91
+ {
92
+ "clip_ratio": 0.0,
93
+ "completion_length": 9.464140625,
94
+ "epoch": 0.05813277525869085,
95
+ "grad_norm": 11.929118986441576,
96
+ "kl": 0.13150390625,
97
+ "learning_rate": 9.942052873217221e-07,
98
+ "loss": 0.004319159388542175,
99
+ "memory(GiB)": 49.84,
100
+ "response_clip_ratio": 0.0,
101
+ "reward": 1.3076169914007187,
102
+ "reward_std": 0.16386293478310107,
103
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3076169914007187,
104
+ "step": 500,
105
+ "train_speed(iter/s)": 0.095747
106
+ },
107
+ {
108
+ "clip_ratio": 0.0,
109
+ "completion_length": 9.3632421875,
110
+ "epoch": 0.06975933031042902,
111
+ "grad_norm": 9.252344124235806,
112
+ "kl": 0.1381982421875,
113
+ "learning_rate": 9.910687959163634e-07,
114
+ "loss": 0.0042449763417243954,
115
+ "memory(GiB)": 49.84,
116
+ "response_clip_ratio": 0.0,
117
+ "reward": 1.304671415090561,
118
+ "reward_std": 0.1764876712858677,
119
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.304671415090561,
120
+ "step": 600,
121
+ "train_speed(iter/s)": 0.094624
122
+ },
123
+ {
124
+ "clip_ratio": 0.0,
125
+ "completion_length": 9.49859375,
126
+ "epoch": 0.08138588536216719,
127
+ "grad_norm": 10.5649786127299,
128
+ "kl": 0.14923828125,
129
+ "learning_rate": 9.872637674070805e-07,
130
+ "loss": 0.005914233922958374,
131
+ "memory(GiB)": 49.84,
132
+ "response_clip_ratio": 0.0,
133
+ "reward": 1.34539220392704,
134
+ "reward_std": 0.14272778324782848,
135
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.34539220392704,
136
+ "step": 700,
137
+ "train_speed(iter/s)": 0.094626
138
+ },
139
+ {
140
+ "clip_ratio": 0.0,
141
+ "completion_length": 9.431015625,
142
+ "epoch": 0.09301244041390536,
143
+ "grad_norm": 13.958988545352236,
144
+ "kl": 0.1456884765625,
145
+ "learning_rate": 9.827953819290425e-07,
146
+ "loss": 0.00618122935295105,
147
+ "memory(GiB)": 49.86,
148
+ "response_clip_ratio": 0.0,
149
+ "reward": 1.3057015722990035,
150
+ "reward_std": 0.15137971622869373,
151
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3057015722990035,
152
+ "step": 800,
153
+ "train_speed(iter/s)": 0.09467
154
+ },
155
+ {
156
+ "clip_ratio": 0.0,
157
+ "completion_length": 9.5357421875,
158
+ "epoch": 0.10463899546564354,
159
+ "grad_norm": 8.423788144030903,
160
+ "kl": 0.14693359375,
161
+ "learning_rate": 9.776697227062527e-07,
162
+ "loss": 0.004831492304801941,
163
+ "memory(GiB)": 49.86,
164
+ "response_clip_ratio": 0.0,
165
+ "reward": 1.347001107931137,
166
+ "reward_std": 0.14807809382677078,
167
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.347001107931137,
168
+ "step": 900,
169
+ "train_speed(iter/s)": 0.094728
170
+ },
171
+ {
172
+ "clip_ratio": 0.0,
173
+ "completion_length": 9.3253515625,
174
+ "epoch": 0.1162655505173817,
175
+ "grad_norm": 6.695960097747582,
176
+ "kl": 0.1556298828125,
177
+ "learning_rate": 9.718937677698976e-07,
178
+ "loss": 0.006615055799484253,
179
+ "memory(GiB)": 49.86,
180
+ "response_clip_ratio": 0.0,
181
+ "reward": 1.3540274119377136,
182
+ "reward_std": 0.12457055719569325,
183
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3540274119377136,
184
+ "step": 1000,
185
+ "train_speed(iter/s)": 0.094744
186
+ },
187
+ {
188
+ "clip_ratio": 0.0,
189
+ "completion_length": 9.465390625,
190
+ "epoch": 0.12789210556911987,
191
+ "grad_norm": 10.285617962993532,
192
+ "kl": 0.16072265625,
193
+ "learning_rate": 9.654753804585103e-07,
194
+ "loss": 0.005601688623428345,
195
+ "memory(GiB)": 49.86,
196
+ "response_clip_ratio": 0.0,
197
+ "reward": 1.2828907597064971,
198
+ "reward_std": 0.14970409277826546,
199
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.2828907597064971,
200
+ "step": 1100,
201
+ "train_speed(iter/s)": 0.094415
202
+ },
203
+ {
204
+ "clip_ratio": 0.0,
205
+ "completion_length": 9.42546875,
206
+ "epoch": 0.13951866062085805,
207
+ "grad_norm": 10.836784655966541,
208
+ "kl": 0.158349609375,
209
+ "learning_rate": 9.584232987128862e-07,
210
+ "loss": 0.005478205680847168,
211
+ "memory(GiB)": 49.86,
212
+ "response_clip_ratio": 0.0,
213
+ "reward": 1.3187702250480653,
214
+ "reward_std": 0.1322044050693512,
215
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3187702250480653,
216
+ "step": 1200,
217
+ "train_speed(iter/s)": 0.094452
218
+ },
219
+ {
220
+ "clip_ratio": 0.0,
221
+ "completion_length": 9.5623828125,
222
+ "epoch": 0.1511452156725962,
223
+ "grad_norm": 11.103606735921945,
224
+ "kl": 0.1616162109375,
225
+ "learning_rate": 9.507471231803197e-07,
226
+ "loss": 0.00721156120300293,
227
+ "memory(GiB)": 49.86,
228
+ "response_clip_ratio": 0.0,
229
+ "reward": 1.3138669067621231,
230
+ "reward_std": 0.14569927806034685,
231
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3138669067621231,
232
+ "step": 1300,
233
+ "train_speed(iter/s)": 0.094427
234
+ },
235
+ {
236
+ "clip_ratio": 0.0,
237
+ "completion_length": 9.3422265625,
238
+ "epoch": 0.16277177072433438,
239
+ "grad_norm": 13.981767782488324,
240
+ "kl": 0.154521484375,
241
+ "learning_rate": 9.424573041443602e-07,
242
+ "loss": 0.0046518009901046755,
243
+ "memory(GiB)": 49.88,
244
+ "response_clip_ratio": 0.0,
245
+ "reward": 1.355497771501541,
246
+ "reward_std": 0.1318685195595026,
247
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.355497771501541,
248
+ "step": 1400,
249
+ "train_speed(iter/s)": 0.094456
250
+ },
251
+ {
252
+ "clip_ratio": 0.0,
253
+ "completion_length": 9.40296875,
254
+ "epoch": 0.17439832577607256,
255
+ "grad_norm": 15.113419365506667,
256
+ "kl": 0.1561474609375,
257
+ "learning_rate": 9.335651272978812e-07,
258
+ "loss": 0.007406370639801025,
259
+ "memory(GiB)": 49.88,
260
+ "response_clip_ratio": 0.0,
261
+ "reward": 1.3447466862201691,
262
+ "reward_std": 0.11326077262870968,
263
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3447466862201691,
264
+ "step": 1500,
265
+ "train_speed(iter/s)": 0.094463
266
+ },
267
+ {
268
+ "clip_ratio": 0.0,
269
+ "completion_length": 9.2856640625,
270
+ "epoch": 0.1860248808278107,
271
+ "grad_norm": 9.743718453316509,
272
+ "kl": 0.1603076171875,
273
+ "learning_rate": 9.240826983788282e-07,
274
+ "loss": 0.005493613481521606,
275
+ "memory(GiB)": 49.88,
276
+ "response_clip_ratio": 0.0,
277
+ "reward": 1.3119167065620423,
278
+ "reward_std": 0.12479189267382025,
279
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3119167065620423,
280
+ "step": 1600,
281
+ "train_speed(iter/s)": 0.094167
282
+ },
283
+ {
284
+ "clip_ratio": 0.0,
285
+ "completion_length": 9.5353515625,
286
+ "epoch": 0.1976514358795489,
287
+ "grad_norm": 13.264394110416175,
288
+ "kl": 0.1698193359375,
289
+ "learning_rate": 9.140229266895642e-07,
290
+ "loss": 0.006227902770042419,
291
+ "memory(GiB)": 49.88,
292
+ "response_clip_ratio": 0.0,
293
+ "reward": 1.3038281148672104,
294
+ "reward_std": 0.11284614092670381,
295
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3038281148672104,
296
+ "step": 1700,
297
+ "train_speed(iter/s)": 0.094188
298
+ },
299
+ {
300
+ "clip_ratio": 0.0,
301
+ "completion_length": 9.4226171875,
302
+ "epoch": 0.20927799093128707,
303
+ "grad_norm": 9.544011725041532,
304
+ "kl": 0.16232421875,
305
+ "learning_rate": 9.033995075222507e-07,
306
+ "loss": 0.005826195478439331,
307
+ "memory(GiB)": 49.88,
308
+ "response_clip_ratio": 0.0,
309
+ "reward": 1.3212931084632873,
310
+ "reward_std": 0.11722485709935426,
311
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3212931084632873,
312
+ "step": 1800,
313
+ "train_speed(iter/s)": 0.094171
314
+ },
315
+ {
316
+ "clip_ratio": 0.0,
317
+ "completion_length": 9.4878125,
318
+ "epoch": 0.22090454598302522,
319
+ "grad_norm": 10.343651509670643,
320
+ "kl": 0.17587890625,
321
+ "learning_rate": 8.922269035141858e-07,
322
+ "loss": 0.006521174311637878,
323
+ "memory(GiB)": 49.88,
324
+ "response_clip_ratio": 0.0,
325
+ "reward": 1.3666004729270935,
326
+ "reward_std": 0.11584680547006428,
327
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3666004729270935,
328
+ "step": 1900,
329
+ "train_speed(iter/s)": 0.094172
330
+ },
331
+ {
332
+ "clip_ratio": 0.0,
333
+ "completion_length": 9.4062109375,
334
+ "epoch": 0.2325311010347634,
335
+ "grad_norm": 14.015908728784089,
336
+ "kl": 0.1614306640625,
337
+ "learning_rate": 8.805203249584874e-07,
338
+ "loss": 0.005633658170700074,
339
+ "memory(GiB)": 49.88,
340
+ "response_clip_ratio": 0.0,
341
+ "reward": 1.3424965512752534,
342
+ "reward_std": 0.11278555382974446,
343
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3424965512752534,
344
+ "step": 2000,
345
+ "train_speed(iter/s)": 0.094185
346
+ },
347
+ {
348
+ "clip_ratio": 0.0,
349
+ "completion_length": 9.5082421875,
350
+ "epoch": 0.24415765608650156,
351
+ "grad_norm": 18.652060056142428,
352
+ "kl": 0.16919921875,
353
+ "learning_rate": 8.682957090969219e-07,
354
+ "loss": 0.005501749515533447,
355
+ "memory(GiB)": 49.96,
356
+ "response_clip_ratio": 0.0,
357
+ "reward": 1.3379686850309371,
358
+ "reward_std": 0.11816087782382965,
359
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3379686850309371,
360
+ "step": 2100,
361
+ "train_speed(iter/s)": 0.094031
362
+ },
363
+ {
364
+ "clip_ratio": 0.0,
365
+ "completion_length": 9.449453125,
366
+ "epoch": 0.25578421113823974,
367
+ "grad_norm": 13.30826804477268,
368
+ "kl": 0.1685107421875,
369
+ "learning_rate": 8.555696984230717e-07,
370
+ "loss": 0.006635627746582031,
371
+ "memory(GiB)": 49.96,
372
+ "response_clip_ratio": 0.0,
373
+ "reward": 1.3248258876800536,
374
+ "reward_std": 0.12071031459607184,
375
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3248258876800536,
376
+ "step": 2200,
377
+ "train_speed(iter/s)": 0.094031
378
+ },
379
+ {
380
+ "clip_ratio": 0.0,
381
+ "completion_length": 9.582734375,
382
+ "epoch": 0.2674107661899779,
383
+ "grad_norm": 14.474933819131337,
384
+ "kl": 0.1704052734375,
385
+ "learning_rate": 8.423596180253791e-07,
386
+ "loss": 0.005957164168357849,
387
+ "memory(GiB)": 49.96,
388
+ "response_clip_ratio": 0.0,
389
+ "reward": 1.3814373064041137,
390
+ "reward_std": 0.1127387316338718,
391
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3814373064041137,
392
+ "step": 2300,
393
+ "train_speed(iter/s)": 0.094051
394
+ },
395
+ {
396
+ "clip_ratio": 0.0,
397
+ "completion_length": 9.45703125,
398
+ "epoch": 0.2790373212417161,
399
+ "grad_norm": 9.422596375579234,
400
+ "kl": 0.167822265625,
401
+ "learning_rate": 8.286834520009099e-07,
402
+ "loss": 0.0051918733119964595,
403
+ "memory(GiB)": 49.96,
404
+ "response_clip_ratio": 0.0,
405
+ "reward": 1.3118427366018295,
406
+ "reward_std": 0.12126734969206154,
407
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3118427366018295,
408
+ "step": 2400,
409
+ "train_speed(iter/s)": 0.09409
410
+ },
411
+ {
412
+ "clip_ratio": 0.0,
413
+ "completion_length": 9.4315234375,
414
+ "epoch": 0.29066387629345425,
415
+ "grad_norm": 9.38274122340621,
416
+ "kl": 0.1697900390625,
417
+ "learning_rate": 8.145598189719482e-07,
418
+ "loss": 0.005171371102333069,
419
+ "memory(GiB)": 49.96,
420
+ "response_clip_ratio": 0.0,
421
+ "reward": 1.3867295610904693,
422
+ "reward_std": 0.11929248780943454,
423
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3867295610904693,
424
+ "step": 2500,
425
+ "train_speed(iter/s)": 0.094103
426
+ },
427
+ {
428
+ "clip_ratio": 0.0,
429
+ "completion_length": 9.479296875,
430
+ "epoch": 0.3022904313451924,
431
+ "grad_norm": 13.737979351496811,
432
+ "kl": 0.176787109375,
433
+ "learning_rate": 8.000079467387547e-07,
434
+ "loss": 0.007171725034713745,
435
+ "memory(GiB)": 49.97,
436
+ "response_clip_ratio": 0.0,
437
+ "reward": 1.3833684372901915,
438
+ "reward_std": 0.1071634407620877,
439
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3833684372901915,
440
+ "step": 2600,
441
+ "train_speed(iter/s)": 0.093982
442
+ },
443
+ {
444
+ "clip_ratio": 0.0,
445
+ "completion_length": 9.4278515625,
446
+ "epoch": 0.3139169863969306,
447
+ "grad_norm": 15.580608222516146,
448
+ "kl": 0.171650390625,
449
+ "learning_rate": 7.850476461029935e-07,
450
+ "loss": 0.004804742336273193,
451
+ "memory(GiB)": 49.97,
452
+ "response_clip_ratio": 0.0,
453
+ "reward": 1.3642382991313935,
454
+ "reward_std": 0.10643348384648561,
455
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3642382991313935,
456
+ "step": 2700,
457
+ "train_speed(iter/s)": 0.094
458
+ },
459
+ {
460
+ "clip_ratio": 0.0,
461
+ "completion_length": 9.5507421875,
462
+ "epoch": 0.32554354144866876,
463
+ "grad_norm": 11.114845313442226,
464
+ "kl": 0.1594287109375,
465
+ "learning_rate": 7.696992838974672e-07,
466
+ "loss": 0.0048704689741134646,
467
+ "memory(GiB)": 49.97,
468
+ "response_clip_ratio": 0.0,
469
+ "reward": 1.3298124277591705,
470
+ "reward_std": 0.11607776273973286,
471
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3298124277591705,
472
+ "step": 2800,
473
+ "train_speed(iter/s)": 0.093983
474
+ },
475
+ {
476
+ "clip_ratio": 0.0,
477
+ "completion_length": 9.53078125,
478
+ "epoch": 0.3371700965004069,
479
+ "grad_norm": 12.360373764757135,
480
+ "kl": 0.174365234375,
481
+ "learning_rate": 7.53983755258874e-07,
482
+ "loss": 0.005847660303115845,
483
+ "memory(GiB)": 49.97,
484
+ "response_clip_ratio": 0.0,
485
+ "reward": 1.3589847725629807,
486
+ "reward_std": 0.10737374008633196,
487
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3589847725629807,
488
+ "step": 2900,
489
+ "train_speed(iter/s)": 0.093989
490
+ },
491
+ {
492
+ "clip_ratio": 0.0,
493
+ "completion_length": 9.5336328125,
494
+ "epoch": 0.3487966515521451,
495
+ "grad_norm": 10.064735245824536,
496
+ "kl": 0.1720654296875,
497
+ "learning_rate": 7.379224551813364e-07,
498
+ "loss": 0.005320903062820435,
499
+ "memory(GiB)": 49.97,
500
+ "response_clip_ratio": 0.0,
501
+ "reward": 1.3229967230558395,
502
+ "reward_std": 0.11362701586447656,
503
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3229967230558395,
504
+ "step": 3000,
505
+ "train_speed(iter/s)": 0.094004
506
+ },
507
+ {
508
+ "clip_ratio": 0.0,
509
+ "completion_length": 9.531796875,
510
+ "epoch": 0.3604232066038833,
511
+ "grad_norm": 9.746163845034996,
512
+ "kl": 0.1750537109375,
513
+ "learning_rate": 7.215372493894305e-07,
514
+ "loss": 0.005580630302429199,
515
+ "memory(GiB)": 49.97,
516
+ "response_clip_ratio": 0.0,
517
+ "reward": 1.394041805267334,
518
+ "reward_std": 0.10719707342796028,
519
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.394041805267334,
520
+ "step": 3100,
521
+ "train_speed(iter/s)": 0.093906
522
+ },
523
+ {
524
+ "clip_ratio": 0.0,
525
+ "completion_length": 9.569140625,
526
+ "epoch": 0.3720497616556214,
527
+ "grad_norm": 10.075852679167767,
528
+ "kl": 0.164130859375,
529
+ "learning_rate": 7.048504445703623e-07,
530
+ "loss": 0.00647194504737854,
531
+ "memory(GiB)": 49.97,
532
+ "response_clip_ratio": 0.0,
533
+ "reward": 1.3294458091259003,
534
+ "reward_std": 0.10014143475331366,
535
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3294458091259003,
536
+ "step": 3200,
537
+ "train_speed(iter/s)": 0.093919
538
+ },
539
+ {
540
+ "clip_ratio": 0.0,
541
+ "completion_length": 9.46984375,
542
+ "epoch": 0.38367631670735963,
543
+ "grad_norm": 9.861222956771822,
544
+ "kl": 0.16787109375,
545
+ "learning_rate": 6.87884758005825e-07,
546
+ "loss": 0.005488141775131226,
547
+ "memory(GiB)": 49.97,
548
+ "response_clip_ratio": 0.0,
549
+ "reward": 1.3671020436286927,
550
+ "reward_std": 0.10204395545646548,
551
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3671020436286927,
552
+ "step": 3300,
553
+ "train_speed(iter/s)": 0.093924
554
+ },
555
+ {
556
+ "clip_ratio": 0.0,
557
+ "completion_length": 9.4744921875,
558
+ "epoch": 0.3953028717590978,
559
+ "grad_norm": 10.703294199835678,
560
+ "kl": 0.1692626953125,
561
+ "learning_rate": 6.706632866448739e-07,
562
+ "loss": 0.005845343470573425,
563
+ "memory(GiB)": 49.97,
564
+ "response_clip_ratio": 0.0,
565
+ "reward": 1.3646071863174438,
566
+ "reward_std": 0.10554393734782934,
567
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3646071863174438,
568
+ "step": 3400,
569
+ "train_speed(iter/s)": 0.093949
570
+ },
571
+ {
572
+ "clip_ratio": 0.0,
573
+ "completion_length": 9.5876953125,
574
+ "epoch": 0.40692942681083594,
575
+ "grad_norm": 12.156014006973646,
576
+ "kl": 0.164482421875,
577
+ "learning_rate": 6.53209475659926e-07,
578
+ "loss": 0.005560991764068604,
579
+ "memory(GiB)": 49.97,
580
+ "response_clip_ratio": 0.0,
581
+ "reward": 1.3740809667110443,
582
+ "reward_std": 0.10303839593194425,
583
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3740809667110443,
584
+ "step": 3500,
585
+ "train_speed(iter/s)": 0.093941
586
+ },
587
+ {
588
+ "clip_ratio": 0.0,
589
+ "completion_length": 9.4395703125,
590
+ "epoch": 0.41855598186257414,
591
+ "grad_norm": 10.579136209736488,
592
+ "kl": 0.167001953125,
593
+ "learning_rate": 6.355470865286917e-07,
594
+ "loss": 0.0047145700454711914,
595
+ "memory(GiB)": 49.97,
596
+ "response_clip_ratio": 0.0,
597
+ "reward": 1.3503324526548386,
598
+ "reward_std": 0.09954373368062079,
599
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3503324526548386,
600
+ "step": 3600,
601
+ "train_speed(iter/s)": 0.09383
602
+ },
603
+ {
604
+ "clip_ratio": 0.0,
605
+ "completion_length": 9.5458984375,
606
+ "epoch": 0.4301825369143123,
607
+ "grad_norm": 12.621743422766063,
608
+ "kl": 0.1657080078125,
609
+ "learning_rate": 6.177001646854896e-07,
610
+ "loss": 0.006506719589233398,
611
+ "memory(GiB)": 49.97,
612
+ "response_clip_ratio": 3.90625e-05,
613
+ "reward": 1.3525580525398255,
614
+ "reward_std": 0.09826488124206662,
615
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3525580525398255,
616
+ "step": 3700,
617
+ "train_speed(iter/s)": 0.093795
618
+ },
619
+ {
620
+ "clip_ratio": 0.0,
621
+ "completion_length": 9.4311328125,
622
+ "epoch": 0.44180909196605045,
623
+ "grad_norm": 9.354617068193154,
624
+ "kl": 0.173662109375,
625
+ "learning_rate": 5.996930067859863e-07,
626
+ "loss": 0.005135659575462342,
627
+ "memory(GiB)": 49.97,
628
+ "response_clip_ratio": 0.0,
629
+ "reward": 1.3989291822910308,
630
+ "reward_std": 0.09648296672850848,
631
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3989291822910308,
632
+ "step": 3800,
633
+ "train_speed(iter/s)": 0.093833
634
+ },
635
+ {
636
+ "clip_ratio": 0.0,
637
+ "completion_length": 9.49171875,
638
+ "epoch": 0.45343564701778866,
639
+ "grad_norm": 14.90852834265166,
640
+ "kl": 0.16689453125,
641
+ "learning_rate": 5.815501276299251e-07,
642
+ "loss": 0.0054639244079589845,
643
+ "memory(GiB)": 49.97,
644
+ "response_clip_ratio": 0.0,
645
+ "reward": 1.3303378784656525,
646
+ "reward_std": 0.1025526038557291,
647
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3303378784656525,
648
+ "step": 3900,
649
+ "train_speed(iter/s)": 0.093865
650
+ },
651
+ {
652
+ "clip_ratio": 0.0,
653
+ "completion_length": 9.45296875,
654
+ "epoch": 0.4650622020695268,
655
+ "grad_norm": 9.790046480640859,
656
+ "kl": 0.171201171875,
657
+ "learning_rate": 5.632962267868746e-07,
658
+ "loss": 0.005732476711273193,
659
+ "memory(GiB)": 49.97,
660
+ "response_clip_ratio": 0.0,
661
+ "reward": 1.3618503904342651,
662
+ "reward_std": 0.09345575381070376,
663
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3618503904342651,
664
+ "step": 4000,
665
+ "train_speed(iter/s)": 0.093884
666
+ },
667
+ {
668
+ "clip_ratio": 0.0,
669
+ "completion_length": 9.4981640625,
670
+ "epoch": 0.47668875712126496,
671
+ "grad_norm": 16.23171809625287,
672
+ "kl": 0.1683154296875,
673
+ "learning_rate": 5.449561549704347e-07,
674
+ "loss": 0.006350870132446289,
675
+ "memory(GiB)": 49.97,
676
+ "response_clip_ratio": 0.0,
677
+ "reward": 1.3815095353126525,
678
+ "reward_std": 0.10499328017234802,
679
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3815095353126525,
680
+ "step": 4100,
681
+ "train_speed(iter/s)": 0.093808
682
+ },
683
+ {
684
+ "clip_ratio": 0.0,
685
+ "completion_length": 9.4899609375,
686
+ "epoch": 0.4883153121730031,
687
+ "grad_norm": 10.028625827275622,
688
+ "kl": 0.172294921875,
689
+ "learning_rate": 5.265548802066736e-07,
690
+ "loss": 0.005829288959503174,
691
+ "memory(GiB)": 50.01,
692
+ "response_clip_ratio": 0.0,
693
+ "reward": 1.3365002036094666,
694
+ "reward_std": 0.09621842056512833,
695
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3365002036094666,
696
+ "step": 4200,
697
+ "train_speed(iter/s)": 0.093821
698
+ },
699
+ {
700
+ "clip_ratio": 0.0,
701
+ "completion_length": 9.44015625,
702
+ "epoch": 0.4999418672247413,
703
+ "grad_norm": 10.282442330807516,
704
+ "kl": 0.1719873046875,
705
+ "learning_rate": 5.081174538428596e-07,
706
+ "loss": 0.006229421496391297,
707
+ "memory(GiB)": 50.01,
708
+ "response_clip_ratio": 0.0,
709
+ "reward": 1.3299858927726746,
710
+ "reward_std": 0.09780080110765993,
711
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3299858927726746,
712
+ "step": 4300,
713
+ "train_speed(iter/s)": 0.093842
714
+ },
715
+ {
716
+ "clip_ratio": 0.0,
717
+ "completion_length": 9.4265234375,
718
+ "epoch": 0.5115684222764795,
719
+ "grad_norm": 10.479527710442367,
720
+ "kl": 0.171787109375,
721
+ "learning_rate": 4.89668976442758e-07,
722
+ "loss": 0.004759013652801514,
723
+ "memory(GiB)": 50.01,
724
+ "response_clip_ratio": 0.0,
725
+ "reward": 1.4068960046768189,
726
+ "reward_std": 0.09772759121842682,
727
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4068960046768189,
728
+ "step": 4400,
729
+ "train_speed(iter/s)": 0.093846
730
+ },
731
+ {
732
+ "clip_ratio": 0.0,
733
+ "completion_length": 9.43875,
734
+ "epoch": 0.5231949773282176,
735
+ "grad_norm": 17.529468974754778,
736
+ "kl": 0.1623486328125,
737
+ "learning_rate": 4.7123456361492607e-07,
738
+ "loss": 0.004565647840499878,
739
+ "memory(GiB)": 50.01,
740
+ "response_clip_ratio": 0.0,
741
+ "reward": 1.3555949538946153,
742
+ "reward_std": 0.09924329521134495,
743
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3555949538946153,
744
+ "step": 4500,
745
+ "train_speed(iter/s)": 0.093871
746
+ },
747
+ {
748
+ "clip_ratio": 0.0,
749
+ "completion_length": 9.5710546875,
750
+ "epoch": 0.5348215323799558,
751
+ "grad_norm": 13.65773402603584,
752
+ "kl": 0.16982421875,
753
+ "learning_rate": 4.528393118205257e-07,
754
+ "loss": 0.005337421298027039,
755
+ "memory(GiB)": 50.01,
756
+ "response_clip_ratio": 0.0,
757
+ "reward": 1.3599874556064606,
758
+ "reward_std": 0.10061670660972595,
759
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3599874556064606,
760
+ "step": 4600,
761
+ "train_speed(iter/s)": 0.093805
762
+ },
763
+ {
764
+ "clip_ratio": 0.0,
765
+ "completion_length": 9.53828125,
766
+ "epoch": 0.546448087431694,
767
+ "grad_norm": 8.826143181240491,
768
+ "kl": 0.177373046875,
769
+ "learning_rate": 4.3450826420720283e-07,
770
+ "loss": 0.0059269857406616215,
771
+ "memory(GiB)": 50.01,
772
+ "response_clip_ratio": 3.90625e-05,
773
+ "reward": 1.3456268101930617,
774
+ "reward_std": 0.0843733003223315,
775
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3456268101930617,
776
+ "step": 4700,
777
+ "train_speed(iter/s)": 0.093771
778
+ },
779
+ {
780
+ "clip_ratio": 0.0,
781
+ "completion_length": 9.7103125,
782
+ "epoch": 0.5580746424834322,
783
+ "grad_norm": 10.962918399547704,
784
+ "kl": 0.178984375,
785
+ "learning_rate": 4.1626637651554855e-07,
786
+ "loss": 0.005514188408851623,
787
+ "memory(GiB)": 50.01,
788
+ "response_clip_ratio": 0.0,
789
+ "reward": 1.3955884772539138,
790
+ "reward_std": 0.0897440404444933,
791
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3955884772539138,
792
+ "step": 4800,
793
+ "train_speed(iter/s)": 0.093778
794
+ },
795
+ {
796
+ "clip_ratio": 0.0,
797
+ "completion_length": 9.421328125,
798
+ "epoch": 0.5697011975351703,
799
+ "grad_norm": 13.288533082686738,
800
+ "kl": 0.1740966796875,
801
+ "learning_rate": 3.9813848310455493e-07,
802
+ "loss": 0.004496717453002929,
803
+ "memory(GiB)": 50.01,
804
+ "response_clip_ratio": 0.0,
805
+ "reward": 1.3486594069004059,
806
+ "reward_std": 0.09252091265749186,
807
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3486594069004059,
808
+ "step": 4900,
809
+ "train_speed(iter/s)": 0.093792
810
+ },
811
+ {
812
+ "clip_ratio": 0.0,
813
+ "completion_length": 9.6050390625,
814
+ "epoch": 0.5813277525869085,
815
+ "grad_norm": 13.576182979053868,
816
+ "kl": 0.16875,
817
+ "learning_rate": 3.801492631423183e-07,
818
+ "loss": 0.006311448216438293,
819
+ "memory(GiB)": 50.01,
820
+ "response_clip_ratio": 0.0,
821
+ "reward": 1.3385675930976868,
822
+ "reward_std": 0.08789137057960034,
823
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3385675930976868,
824
+ "step": 5000,
825
+ "train_speed(iter/s)": 0.093819
826
+ },
827
+ {
828
+ "clip_ratio": 0.0,
829
+ "completion_length": 9.4701953125,
830
+ "epoch": 0.5929543076386466,
831
+ "grad_norm": 10.883793005621234,
832
+ "kl": 0.1636376953125,
833
+ "learning_rate": 3.6232320700801824e-07,
834
+ "loss": 0.005545246005058288,
835
+ "memory(GiB)": 50.01,
836
+ "response_clip_ratio": 0.0,
837
+ "reward": 1.3905673331022264,
838
+ "reward_std": 0.08755960265174507,
839
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3905673331022264,
840
+ "step": 5100,
841
+ "train_speed(iter/s)": 0.093749
842
+ },
843
+ {
844
+ "clip_ratio": 0.0,
845
+ "completion_length": 9.4654296875,
846
+ "epoch": 0.6045808626903848,
847
+ "grad_norm": 10.540876662145202,
848
+ "kl": 0.1647607421875,
849
+ "learning_rate": 3.446845829509133e-07,
850
+ "loss": 0.004752608835697174,
851
+ "memory(GiB)": 50.01,
852
+ "response_clip_ratio": 0.0,
853
+ "reward": 1.428147051334381,
854
+ "reward_std": 0.08269149933941662,
855
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.428147051334381,
856
+ "step": 5200,
857
+ "train_speed(iter/s)": 0.093767
858
+ },
859
+ {
860
+ "clip_ratio": 0.0,
861
+ "completion_length": 9.4448046875,
862
+ "epoch": 0.616207417742123,
863
+ "grad_norm": 13.475346015876513,
864
+ "kl": 0.16580078125,
865
+ "learning_rate": 3.2725740405174216e-07,
866
+ "loss": 0.0050477349758148195,
867
+ "memory(GiB)": 50.01,
868
+ "response_clip_ratio": 0.0,
869
+ "reward": 1.404239798784256,
870
+ "reward_std": 0.0858971696998924,
871
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.404239798784256,
872
+ "step": 5300,
873
+ "train_speed(iter/s)": 0.093778
874
+ },
875
+ {
876
+ "clip_ratio": 0.0,
877
+ "completion_length": 9.4316796875,
878
+ "epoch": 0.6278339727938612,
879
+ "grad_norm": 12.403978855236371,
880
+ "kl": 0.1601806640625,
881
+ "learning_rate": 3.1006539553150724e-07,
882
+ "loss": 0.005034840106964112,
883
+ "memory(GiB)": 50.01,
884
+ "response_clip_ratio": 0.0,
885
+ "reward": 1.3801133859157562,
886
+ "reward_std": 0.0971566170360893,
887
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3801133859157562,
888
+ "step": 5400,
889
+ "train_speed(iter/s)": 0.093788
890
+ },
891
+ {
892
+ "clip_ratio": 0.0,
893
+ "completion_length": 9.47546875,
894
+ "epoch": 0.6394605278455994,
895
+ "grad_norm": 13.196174592922217,
896
+ "kl": 0.1671484375,
897
+ "learning_rate": 2.931319624521521e-07,
898
+ "loss": 0.00633289098739624,
899
+ "memory(GiB)": 50.01,
900
+ "response_clip_ratio": 0.0,
901
+ "reward": 1.3824928963184357,
902
+ "reward_std": 0.09388638647273183,
903
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3824928963184357,
904
+ "step": 5500,
905
+ "train_speed(iter/s)": 0.093796
906
+ },
907
+ {
908
+ "clip_ratio": 0.0,
909
+ "completion_length": 9.5144921875,
910
+ "epoch": 0.6510870828973375,
911
+ "grad_norm": 10.532572334095438,
912
+ "kl": 0.17203125,
913
+ "learning_rate": 2.7648015785309695e-07,
914
+ "loss": 0.004889653325080872,
915
+ "memory(GiB)": 50.01,
916
+ "response_clip_ratio": 0.0,
917
+ "reward": 1.4016336119174957,
918
+ "reward_std": 0.09526587199419737,
919
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4016336119174957,
920
+ "step": 5600,
921
+ "train_speed(iter/s)": 0.09374
922
+ },
923
+ {
924
+ "clip_ratio": 0.0,
925
+ "completion_length": 9.5614453125,
926
+ "epoch": 0.6627136379490757,
927
+ "grad_norm": 12.720205008880969,
928
+ "kl": 0.16912109375,
929
+ "learning_rate": 2.60132651367017e-07,
930
+ "loss": 0.00633256196975708,
931
+ "memory(GiB)": 50.01,
932
+ "response_clip_ratio": 0.0,
933
+ "reward": 1.3703772777318954,
934
+ "reward_std": 0.09573625258170068,
935
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3703772777318954,
936
+ "step": 5700,
937
+ "train_speed(iter/s)": 0.093756
938
+ },
939
+ {
940
+ "clip_ratio": 0.0,
941
+ "completion_length": 9.571796875,
942
+ "epoch": 0.6743401930008138,
943
+ "grad_norm": 6.872908071660086,
944
+ "kl": 0.177060546875,
945
+ "learning_rate": 2.441116983575876e-07,
946
+ "loss": 0.004491334557533264,
947
+ "memory(GiB)": 50.01,
948
+ "response_clip_ratio": 0.0,
949
+ "reward": 1.3781077253818512,
950
+ "reward_std": 0.0949486710689962,
951
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3781077253818512,
952
+ "step": 5800,
953
+ "train_speed(iter/s)": 0.093772
954
+ },
955
+ {
956
+ "clip_ratio": 0.0,
957
+ "completion_length": 9.511953125,
958
+ "epoch": 0.685966748052552,
959
+ "grad_norm": 10.828437072129354,
960
+ "kl": 0.1688671875,
961
+ "learning_rate": 2.2843910962121028e-07,
962
+ "loss": 0.004997452199459076,
963
+ "memory(GiB)": 50.01,
964
+ "response_clip_ratio": 0.0,
965
+ "reward": 1.3701044476032258,
966
+ "reward_std": 0.08872982957400381,
967
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3701044476032258,
968
+ "step": 5900,
969
+ "train_speed(iter/s)": 0.0938
970
+ },
971
+ {
972
+ "clip_ratio": 0.0,
973
+ "completion_length": 9.5623046875,
974
+ "epoch": 0.6975933031042902,
975
+ "grad_norm": 8.65544047927268,
976
+ "kl": 0.1734130859375,
977
+ "learning_rate": 2.1313622169397133e-07,
978
+ "loss": 0.005034286975860596,
979
+ "memory(GiB)": 50.01,
980
+ "response_clip_ratio": 0.0,
981
+ "reward": 1.376991518139839,
982
+ "reward_std": 0.08544575774110853,
983
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.376991518139839,
984
+ "step": 6000,
985
+ "train_speed(iter/s)": 0.09382
986
+ },
987
+ {
988
+ "clip_ratio": 0.0,
989
+ "completion_length": 9.5916796875,
990
+ "epoch": 0.7092198581560284,
991
+ "grad_norm": 10.832177815406336,
992
+ "kl": 0.1687158203125,
993
+ "learning_rate": 1.9822386780425242e-07,
994
+ "loss": 0.005690656900405884,
995
+ "memory(GiB)": 50.01,
996
+ "response_clip_ratio": 0.0,
997
+ "reward": 1.3775933372974396,
998
+ "reward_std": 0.09453948569484055,
999
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3775933372974396,
1000
+ "step": 6100,
1001
+ "train_speed(iter/s)": 0.093779
1002
+ },
1003
+ {
1004
+ "clip_ratio": 0.0,
1005
+ "completion_length": 9.452265625,
1006
+ "epoch": 0.7208464132077665,
1007
+ "grad_norm": 9.5769032777987,
1008
+ "kl": 0.167353515625,
1009
+ "learning_rate": 1.8372234951054205e-07,
1010
+ "loss": 0.0064952802658081055,
1011
+ "memory(GiB)": 50.01,
1012
+ "response_clip_ratio": 0.0,
1013
+ "reward": 1.3917820090055466,
1014
+ "reward_std": 0.0956609710212797,
1015
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3917820090055466,
1016
+ "step": 6200,
1017
+ "train_speed(iter/s)": 0.093802
1018
+ },
1019
+ {
1020
+ "clip_ratio": 0.0,
1021
+ "completion_length": 9.595390625,
1022
+ "epoch": 0.7324729682595047,
1023
+ "grad_norm": 13.490536213430035,
1024
+ "kl": 0.16693359375,
1025
+ "learning_rate": 1.696514090630571e-07,
1026
+ "loss": 0.006171835064888001,
1027
+ "memory(GiB)": 50.01,
1028
+ "response_clip_ratio": 0.0,
1029
+ "reward": 1.3438419443368912,
1030
+ "reward_std": 0.09881241522729396,
1031
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3438419443368912,
1032
+ "step": 6300,
1033
+ "train_speed(iter/s)": 0.093826
1034
+ },
1035
+ {
1036
+ "clip_ratio": 0.0,
1037
+ "completion_length": 9.58125,
1038
+ "epoch": 0.7440995233112428,
1039
+ "grad_norm": 13.80425097201388,
1040
+ "kl": 0.1742724609375,
1041
+ "learning_rate": 1.560302025268016e-07,
1042
+ "loss": 0.004496442675590515,
1043
+ "memory(GiB)": 50.01,
1044
+ "response_clip_ratio": 0.0,
1045
+ "reward": 1.3792090493440627,
1046
+ "reward_std": 0.09534793998114764,
1047
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3792090493440627,
1048
+ "step": 6400,
1049
+ "train_speed(iter/s)": 0.093832
1050
+ },
1051
+ {
1052
+ "clip_ratio": 0.0,
1053
+ "completion_length": 9.4980078125,
1054
+ "epoch": 0.755726078362981,
1055
+ "grad_norm": 12.228002609541004,
1056
+ "kl": 0.172158203125,
1057
+ "learning_rate": 1.4287727370265557e-07,
1058
+ "loss": 0.004531278908252716,
1059
+ "memory(GiB)": 50.01,
1060
+ "response_clip_ratio": 0.0,
1061
+ "reward": 1.3554240018129349,
1062
+ "reward_std": 0.0867443119455129,
1063
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3554240018129349,
1064
+ "step": 6500,
1065
+ "train_speed(iter/s)": 0.093837
1066
+ },
1067
+ {
1068
+ "clip_ratio": 0.0,
1069
+ "completion_length": 9.415234375,
1070
+ "epoch": 0.7673526334147193,
1071
+ "grad_norm": 11.022738680450304,
1072
+ "kl": 0.164775390625,
1073
+ "learning_rate": 1.3021052888199273e-07,
1074
+ "loss": 0.006004486083984375,
1075
+ "memory(GiB)": 50.01,
1076
+ "response_clip_ratio": 0.0,
1077
+ "reward": 1.3786427634954452,
1078
+ "reward_std": 0.09436391741968692,
1079
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3786427634954452,
1080
+ "step": 6600,
1081
+ "train_speed(iter/s)": 0.093792
1082
+ },
1083
+ {
1084
+ "clip_ratio": 0.0,
1085
+ "completion_length": 9.5644140625,
1086
+ "epoch": 0.7789791884664574,
1087
+ "grad_norm": 7.2361000289177095,
1088
+ "kl": 0.17333984375,
1089
+ "learning_rate": 1.1804721246919974e-07,
1090
+ "loss": 0.004695640504360199,
1091
+ "memory(GiB)": 50.01,
1092
+ "response_clip_ratio": 0.0,
1093
+ "reward": 1.383240016102791,
1094
+ "reward_std": 0.09347979573532939,
1095
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.383240016102791,
1096
+ "step": 6700,
1097
+ "train_speed(iter/s)": 0.093815
1098
+ },
1099
+ {
1100
+ "clip_ratio": 0.0,
1101
+ "completion_length": 9.3888671875,
1102
+ "epoch": 0.7906057435181956,
1103
+ "grad_norm": 10.627678410762373,
1104
+ "kl": 0.1702392578125,
1105
+ "learning_rate": 1.0640388350528345e-07,
1106
+ "loss": 0.006417045593261719,
1107
+ "memory(GiB)": 50.01,
1108
+ "response_clip_ratio": 0.0,
1109
+ "reward": 1.392098326086998,
1110
+ "reward_std": 0.08011089071165771,
1111
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.392098326086998,
1112
+ "step": 6800,
1113
+ "train_speed(iter/s)": 0.093838
1114
+ },
1115
+ {
1116
+ "clip_ratio": 0.0,
1117
+ "completion_length": 9.5668359375,
1118
+ "epoch": 0.8022322985699337,
1119
+ "grad_norm": 15.465333954982329,
1120
+ "kl": 0.170009765625,
1121
+ "learning_rate": 9.529639312452559e-08,
1122
+ "loss": 0.005341029167175293,
1123
+ "memory(GiB)": 50.01,
1124
+ "response_clip_ratio": 0.0,
1125
+ "reward": 1.4103717935085296,
1126
+ "reward_std": 0.09352740393951535,
1127
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4103717935085296,
1128
+ "step": 6900,
1129
+ "train_speed(iter/s)": 0.093849
1130
+ },
1131
+ {
1132
+ "clip_ratio": 0.0,
1133
+ "completion_length": 9.5197265625,
1134
+ "epoch": 0.8138588536216719,
1135
+ "grad_norm": 14.110343993379132,
1136
+ "kl": 0.1599560546875,
1137
+ "learning_rate": 8.473986297487578e-08,
1138
+ "loss": 0.004906933009624481,
1139
+ "memory(GiB)": 50.01,
1140
+ "response_clip_ratio": 0.0,
1141
+ "reward": 1.4088983750343322,
1142
+ "reward_std": 0.08588065375573933,
1143
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4088983750343322,
1144
+ "step": 7000,
1145
+ "train_speed(iter/s)": 0.093861
1146
+ },
1147
+ {
1148
+ "clip_ratio": 0.0,
1149
+ "completion_length": 9.4692578125,
1150
+ "epoch": 0.82548540867341,
1151
+ "grad_norm": 8.408536596023637,
1152
+ "kl": 0.1673828125,
1153
+ "learning_rate": 7.474866463146251e-08,
1154
+ "loss": 0.005006779432296753,
1155
+ "memory(GiB)": 50.01,
1156
+ "response_clip_ratio": 0.0,
1157
+ "reward": 1.4262621313333512,
1158
+ "reward_std": 0.08552982007153333,
1159
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4262621313333512,
1160
+ "step": 7100,
1161
+ "train_speed(iter/s)": 0.093824
1162
+ },
1163
+ {
1164
+ "clip_ratio": 0.0,
1165
+ "completion_length": 9.4380859375,
1166
+ "epoch": 0.8371119637251483,
1167
+ "grad_norm": 15.805070345572961,
1168
+ "kl": 0.1696728515625,
1169
+ "learning_rate": 6.53364000312463e-08,
1170
+ "loss": 0.005111285448074341,
1171
+ "memory(GiB)": 50.01,
1172
+ "response_clip_ratio": 0.0,
1173
+ "reward": 1.4090092825889586,
1174
+ "reward_std": 0.08110610948875546,
1175
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4090092825889586,
1176
+ "step": 7200,
1177
+ "train_speed(iter/s)": 0.093851
1178
+ },
1179
+ {
1180
+ "clip_ratio": 0.0,
1181
+ "completion_length": 9.5043359375,
1182
+ "epoch": 0.8487385187768864,
1183
+ "grad_norm": 9.57328394904971,
1184
+ "kl": 0.161328125,
1185
+ "learning_rate": 5.651588295545168e-08,
1186
+ "loss": 0.004713370501995087,
1187
+ "memory(GiB)": 50.01,
1188
+ "response_clip_ratio": 0.0,
1189
+ "reward": 1.3688128244876863,
1190
+ "reward_std": 0.08936454836279153,
1191
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3688128244876863,
1192
+ "step": 7300,
1193
+ "train_speed(iter/s)": 0.093859
1194
+ },
1195
+ {
1196
+ "clip_ratio": 0.0,
1197
+ "completion_length": 9.4918359375,
1198
+ "epoch": 0.8603650738286246,
1199
+ "grad_norm": 13.141769298737369,
1200
+ "kl": 0.1631298828125,
1201
+ "learning_rate": 4.8299121584989445e-08,
1202
+ "loss": 0.005130698680877685,
1203
+ "memory(GiB)": 50.01,
1204
+ "response_clip_ratio": 0.0,
1205
+ "reward": 1.400255571603775,
1206
+ "reward_std": 0.09085271211341023,
1207
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.400255571603775,
1208
+ "step": 7400,
1209
+ "train_speed(iter/s)": 0.093861
1210
+ },
1211
+ {
1212
+ "clip_ratio": 0.0,
1213
+ "completion_length": 9.4555859375,
1214
+ "epoch": 0.8719916288803627,
1215
+ "grad_norm": 9.746601959968274,
1216
+ "kl": 0.1671728515625,
1217
+ "learning_rate": 4.069730215261552e-08,
1218
+ "loss": 0.005373966693878174,
1219
+ "memory(GiB)": 50.01,
1220
+ "response_clip_ratio": 0.0,
1221
+ "reward": 1.4106507396697998,
1222
+ "reward_std": 0.08433111377526074,
1223
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4106507396697998,
1224
+ "step": 7500,
1225
+ "train_speed(iter/s)": 0.093864
1226
+ },
1227
+ {
1228
+ "clip_ratio": 0.0,
1229
+ "completion_length": 9.479375,
1230
+ "epoch": 0.8836181839321009,
1231
+ "grad_norm": 12.304794577190247,
1232
+ "kl": 0.166220703125,
1233
+ "learning_rate": 3.372077371408361e-08,
1234
+ "loss": 0.004605398774147034,
1235
+ "memory(GiB)": 50.01,
1236
+ "response_clip_ratio": 0.0,
1237
+ "reward": 1.4062111765146255,
1238
+ "reward_std": 0.08385045255534351,
1239
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4062111765146255,
1240
+ "step": 7600,
1241
+ "train_speed(iter/s)": 0.093825
1242
+ },
1243
+ {
1244
+ "clip_ratio": 0.0,
1245
+ "completion_length": 9.4255078125,
1246
+ "epoch": 0.895244738983839,
1247
+ "grad_norm": 10.788517373431308,
1248
+ "kl": 0.1640380859375,
1249
+ "learning_rate": 2.7379034059024085e-08,
1250
+ "loss": 0.005341172218322754,
1251
+ "memory(GiB)": 50.01,
1252
+ "response_clip_ratio": 0.0,
1253
+ "reward": 1.400910457968712,
1254
+ "reward_std": 0.09175728805363179,
1255
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.400910457968712,
1256
+ "step": 7700,
1257
+ "train_speed(iter/s)": 0.093832
1258
+ },
1259
+ {
1260
+ "clip_ratio": 0.0,
1261
+ "completion_length": 9.557265625,
1262
+ "epoch": 0.9068712940355773,
1263
+ "grad_norm": 15.69745045067331,
1264
+ "kl": 0.1719189453125,
1265
+ "learning_rate": 2.1680716780730136e-08,
1266
+ "loss": 0.0057187509536743165,
1267
+ "memory(GiB)": 50.01,
1268
+ "response_clip_ratio": 0.0,
1269
+ "reward": 1.4035167163610458,
1270
+ "reward_std": 0.09192508255131543,
1271
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4035167163610458,
1272
+ "step": 7800,
1273
+ "train_speed(iter/s)": 0.093839
1274
+ },
1275
+ {
1276
+ "clip_ratio": 0.0,
1277
+ "completion_length": 9.5982421875,
1278
+ "epoch": 0.9184978490873155,
1279
+ "grad_norm": 9.828379408967727,
1280
+ "kl": 0.167861328125,
1281
+ "learning_rate": 1.6633579522452923e-08,
1282
+ "loss": 0.004599595665931702,
1283
+ "memory(GiB)": 50.01,
1284
+ "response_clip_ratio": 0.0,
1285
+ "reward": 1.4050581753253937,
1286
+ "reward_std": 0.08899507346563042,
1287
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.4050581753253937,
1288
+ "step": 7900,
1289
+ "train_speed(iter/s)": 0.093848
1290
+ },
1291
+ {
1292
+ "clip_ratio": 0.0,
1293
+ "completion_length": 9.4523828125,
1294
+ "epoch": 0.9301244041390536,
1295
+ "grad_norm": 7.564846175327,
1296
+ "kl": 0.165205078125,
1297
+ "learning_rate": 1.2244493416208424e-08,
1298
+ "loss": 0.006511397361755371,
1299
+ "memory(GiB)": 50.01,
1300
+ "response_clip_ratio": 0.0,
1301
+ "reward": 1.3674461019039155,
1302
+ "reward_std": 0.09354917639866471,
1303
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3674461019039155,
1304
+ "step": 8000,
1305
+ "train_speed(iter/s)": 0.093866
1306
+ },
1307
+ {
1308
+ "clip_ratio": 0.0,
1309
+ "completion_length": 9.441796875,
1310
+ "epoch": 0.9417509591907918,
1311
+ "grad_norm": 8.473570999026597,
1312
+ "kl": 0.166337890625,
1313
+ "learning_rate": 8.51943372847419e-09,
1314
+ "loss": 0.004957606792449951,
1315
+ "memory(GiB)": 50.01,
1316
+ "response_clip_ratio": 0.0,
1317
+ "reward": 1.3664843720197677,
1318
+ "reward_std": 0.09796678048558533,
1319
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3664843720197677,
1320
+ "step": 8100,
1321
+ "train_speed(iter/s)": 0.093827
1322
+ },
1323
+ {
1324
+ "clip_ratio": 0.0,
1325
+ "completion_length": 9.4091796875,
1326
+ "epoch": 0.9533775142425299,
1327
+ "grad_norm": 17.38564208248951,
1328
+ "kl": 0.1664453125,
1329
+ "learning_rate": 5.463471725509206e-09,
1330
+ "loss": 0.005511881113052368,
1331
+ "memory(GiB)": 50.01,
1332
+ "response_clip_ratio": 0.0,
1333
+ "reward": 1.3864123088121414,
1334
+ "reward_std": 0.09022373898886143,
1335
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3864123088121414,
1336
+ "step": 8200,
1337
+ "train_speed(iter/s)": 0.093846
1338
+ },
1339
+ {
1340
+ "clip_ratio": 0.0,
1341
+ "completion_length": 9.52640625,
1342
+ "epoch": 0.9650040692942681,
1343
+ "grad_norm": 12.073204680109393,
1344
+ "kl": 0.1724462890625,
1345
+ "learning_rate": 3.0807677693729385e-09,
1346
+ "loss": 0.006146684885025024,
1347
+ "memory(GiB)": 50.01,
1348
+ "response_clip_ratio": 0.0,
1349
+ "reward": 1.3671981352567673,
1350
+ "reward_std": 0.09982930341735483,
1351
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3671981352567673,
1352
+ "step": 8300,
1353
+ "train_speed(iter/s)": 0.093858
1354
+ },
1355
+ {
1356
+ "clip_ratio": 0.0,
1357
+ "completion_length": 9.4923828125,
1358
+ "epoch": 0.9766306243460062,
1359
+ "grad_norm": 14.136069122546115,
1360
+ "kl": 0.164794921875,
1361
+ "learning_rate": 1.3745656540422036e-09,
1362
+ "loss": 0.0051899772882461545,
1363
+ "memory(GiB)": 50.01,
1364
+ "response_clip_ratio": 0.0,
1365
+ "reward": 1.3862751299142837,
1366
+ "reward_std": 0.09112708026543259,
1367
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3862751299142837,
1368
+ "step": 8400,
1369
+ "train_speed(iter/s)": 0.093871
1370
+ },
1371
+ {
1372
+ "clip_ratio": 0.0,
1373
+ "completion_length": 9.5616015625,
1374
+ "epoch": 0.9882571793977445,
1375
+ "grad_norm": 7.965510618669221,
1376
+ "kl": 0.168076171875,
1377
+ "learning_rate": 3.4718818933582305e-10,
1378
+ "loss": 0.0061265045404434205,
1379
+ "memory(GiB)": 50.01,
1380
+ "response_clip_ratio": 0.0,
1381
+ "reward": 1.3907999232411385,
1382
+ "reward_std": 0.08998070719651878,
1383
+ "rewards/MultiModalMultiActionNoThinkNewAction": 1.3907999232411385,
1384
+ "step": 8500,
1385
+ "train_speed(iter/s)": 0.093882
1386
+ }
1387
+ ],
1388
+ "logging_steps": 100,
1389
+ "max_steps": 8601,
1390
+ "num_input_tokens_seen": 0,
1391
+ "num_train_epochs": 1,
1392
+ "save_steps": 500,
1393
+ "stateful_callbacks": {
1394
+ "TrainerControl": {
1395
+ "args": {
1396
+ "should_epoch_stop": false,
1397
+ "should_evaluate": false,
1398
+ "should_log": false,
1399
+ "should_save": true,
1400
+ "should_training_stop": false
1401
+ },
1402
+ "attributes": {}
1403
+ }
1404
+ },
1405
+ "total_flos": 0.0,
1406
+ "train_batch_size": 8,
1407
+ "trial_name": null,
1408
+ "trial_params": null
1409
+ }