oulinyu commited on
Commit
732d67d
·
verified ·
1 Parent(s): b005e6b

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,371 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/group/40174/Zywoou/models/Qwen2.5-VL-7B-Instruct",
3
+ "model_type": "qwen2_5_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "qwen2_5_vl",
15
+ "system": "You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within <think> </think> tags. The final answer MUST BE put in \\\\boxed{}.\n",
16
+ "max_length": 32784,
17
+ "truncation_strategy": "delete",
18
+ "max_pixels": null,
19
+ "tools_prompt": "react_en",
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "default",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "/group/40174/Zywoou/Dataset/OpenR1-Math-220k/level_32B/20250610_004144/balanced_correct_count_1_to_15_min904.jsonl",
29
+ "/group/40174/Zywoou/Dataset/R1-Onevision/geo170k_qa/32B/20250611_143743/geo170k_filtered.jsonl"
30
+ ],
31
+ "val_dataset": [],
32
+ "split_dataset_ratio": 0.01,
33
+ "data_seed": 42,
34
+ "dataset_num_proc": 1,
35
+ "dataset_shuffle": true,
36
+ "streaming": false,
37
+ "interleave_prob": null,
38
+ "stopping_strategy": "first_exhausted",
39
+ "shuffle_buffer_size": 1000,
40
+ "enable_cache": false,
41
+ "download_mode": "reuse_dataset_if_exists",
42
+ "columns": {},
43
+ "strict": false,
44
+ "remove_unused_columns": true,
45
+ "model_name": [
46
+ null,
47
+ null
48
+ ],
49
+ "model_author": [
50
+ null,
51
+ null
52
+ ],
53
+ "custom_dataset_info": [],
54
+ "quant_method": null,
55
+ "quant_bits": null,
56
+ "hqq_axis": null,
57
+ "bnb_4bit_compute_dtype": "bfloat16",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "bnb_4bit_quant_storage": null,
61
+ "max_new_tokens": 64,
62
+ "temperature": 0.0,
63
+ "top_k": null,
64
+ "top_p": null,
65
+ "repetition_penalty": null,
66
+ "num_beams": 1,
67
+ "stream": false,
68
+ "stop_words": [],
69
+ "logprobs": false,
70
+ "top_logprobs": null,
71
+ "ckpt_dir": null,
72
+ "load_dataset_config": null,
73
+ "lora_modules": [],
74
+ "tuner_backend": "peft",
75
+ "train_type": "full",
76
+ "adapters": [],
77
+ "external_plugins": [],
78
+ "seed": 42,
79
+ "model_kwargs": {},
80
+ "load_args": false,
81
+ "load_data_args": false,
82
+ "use_hf": false,
83
+ "hub_token": null,
84
+ "custom_register_path": [],
85
+ "ignore_args_error": false,
86
+ "use_swift_lora": false,
87
+ "output_dir": "/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647",
88
+ "overwrite_output_dir": false,
89
+ "do_train": false,
90
+ "do_eval": false,
91
+ "do_predict": false,
92
+ "eval_strategy": "steps",
93
+ "prediction_loss_only": false,
94
+ "per_device_train_batch_size": 1,
95
+ "per_device_eval_batch_size": 1,
96
+ "per_gpu_train_batch_size": null,
97
+ "per_gpu_eval_batch_size": null,
98
+ "gradient_accumulation_steps": 8,
99
+ "eval_accumulation_steps": null,
100
+ "eval_delay": 0,
101
+ "torch_empty_cache_steps": null,
102
+ "learning_rate": 2e-05,
103
+ "weight_decay": 0.1,
104
+ "adam_beta1": 0.9,
105
+ "adam_beta2": 0.95,
106
+ "adam_epsilon": 1e-08,
107
+ "max_grad_norm": 1.0,
108
+ "num_train_epochs": 5.0,
109
+ "max_steps": -1,
110
+ "lr_scheduler_type": "cosine",
111
+ "lr_scheduler_kwargs": null,
112
+ "warmup_ratio": 0.05,
113
+ "warmup_steps": 0,
114
+ "log_level": "passive",
115
+ "log_level_replica": "warning",
116
+ "log_on_each_node": true,
117
+ "logging_dir": "/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647/runs",
118
+ "logging_strategy": "steps",
119
+ "logging_first_step": true,
120
+ "logging_steps": 5,
121
+ "logging_nan_inf_filter": true,
122
+ "save_strategy": "steps",
123
+ "save_steps": 50.0,
124
+ "save_total_limit": 10,
125
+ "save_safetensors": true,
126
+ "save_on_each_node": false,
127
+ "save_only_model": true,
128
+ "restore_callback_states_from_checkpoint": false,
129
+ "no_cuda": false,
130
+ "use_cpu": false,
131
+ "use_mps_device": false,
132
+ "jit_mode_eval": false,
133
+ "use_ipex": false,
134
+ "bf16": true,
135
+ "fp16": false,
136
+ "fp16_opt_level": "O1",
137
+ "half_precision_backend": "auto",
138
+ "bf16_full_eval": false,
139
+ "fp16_full_eval": false,
140
+ "tf32": null,
141
+ "local_rank": 0,
142
+ "ddp_backend": null,
143
+ "tpu_num_cores": null,
144
+ "tpu_metrics_debug": false,
145
+ "debug": null,
146
+ "dataloader_drop_last": false,
147
+ "eval_steps": 50.0,
148
+ "dataloader_num_workers": 8,
149
+ "dataloader_prefetch_factor": null,
150
+ "past_index": -1,
151
+ "run_name": null,
152
+ "disable_tqdm": null,
153
+ "label_names": null,
154
+ "load_best_model_at_end": false,
155
+ "metric_for_best_model": "loss",
156
+ "greater_is_better": false,
157
+ "ignore_data_skip": false,
158
+ "fsdp": "",
159
+ "fsdp_min_num_params": 0,
160
+ "fsdp_config": null,
161
+ "tp_size": 0,
162
+ "fsdp_transformer_layer_cls_to_wrap": null,
163
+ "accelerator_config": {
164
+ "dispatch_batches": false
165
+ },
166
+ "deepspeed": {
167
+ "fp16": {
168
+ "enabled": "auto",
169
+ "loss_scale": 0,
170
+ "loss_scale_window": 1000,
171
+ "initial_scale_power": 16,
172
+ "hysteresis": 2,
173
+ "min_loss_scale": 1
174
+ },
175
+ "bf16": {
176
+ "enabled": "auto"
177
+ },
178
+ "zero_optimization": {
179
+ "stage": 3,
180
+ "offload_optimizer": {
181
+ "device": "none",
182
+ "pin_memory": true
183
+ },
184
+ "offload_param": {
185
+ "device": "none",
186
+ "pin_memory": true
187
+ },
188
+ "overlap_comm": false,
189
+ "contiguous_gradients": true,
190
+ "sub_group_size": 1000000000.0,
191
+ "reduce_bucket_size": "auto",
192
+ "zero_quantized_weights": false,
193
+ "zero_quantized_gradients": false,
194
+ "stage3_prefetch_bucket_size": "auto",
195
+ "stage3_param_persistence_threshold": "auto",
196
+ "stage3_max_live_parameters": 1000000000.0,
197
+ "stage3_max_reuse_distance": 1000000000.0,
198
+ "stage3_gather_16bit_weights_on_model_save": true
199
+ },
200
+ "gradient_accumulation_steps": "auto",
201
+ "gradient_clipping": "auto",
202
+ "steps_per_print": 2000,
203
+ "train_batch_size": "auto",
204
+ "train_micro_batch_size_per_gpu": "auto",
205
+ "wall_clock_breakdown": false
206
+ },
207
+ "label_smoothing_factor": 0.0,
208
+ "optim": "adamw_torch",
209
+ "optim_args": null,
210
+ "adafactor": false,
211
+ "group_by_length": false,
212
+ "length_column_name": "length",
213
+ "report_to": [
214
+ "tensorboard"
215
+ ],
216
+ "ddp_find_unused_parameters": null,
217
+ "ddp_bucket_cap_mb": null,
218
+ "ddp_broadcast_buffers": null,
219
+ "dataloader_pin_memory": true,
220
+ "dataloader_persistent_workers": false,
221
+ "skip_memory_metrics": true,
222
+ "use_legacy_prediction_loop": false,
223
+ "push_to_hub": false,
224
+ "resume_from_checkpoint": null,
225
+ "hub_model_id": null,
226
+ "hub_strategy": "every_save",
227
+ "hub_private_repo": null,
228
+ "hub_always_push": false,
229
+ "gradient_checkpointing": true,
230
+ "gradient_checkpointing_kwargs": null,
231
+ "include_inputs_for_metrics": false,
232
+ "include_for_metrics": [],
233
+ "eval_do_concat_batches": true,
234
+ "fp16_backend": "auto",
235
+ "evaluation_strategy": "steps",
236
+ "push_to_hub_model_id": null,
237
+ "push_to_hub_organization": null,
238
+ "push_to_hub_token": null,
239
+ "mp_parameters": "",
240
+ "auto_find_batch_size": false,
241
+ "full_determinism": false,
242
+ "torchdynamo": null,
243
+ "ray_scope": "last",
244
+ "ddp_timeout": 1800,
245
+ "torch_compile": false,
246
+ "torch_compile_backend": null,
247
+ "torch_compile_mode": null,
248
+ "dispatch_batches": null,
249
+ "split_batches": null,
250
+ "include_tokens_per_second": false,
251
+ "include_num_input_tokens_seen": false,
252
+ "neftune_noise_alpha": null,
253
+ "optim_target_modules": null,
254
+ "batch_eval_metrics": false,
255
+ "eval_on_start": false,
256
+ "use_liger_kernel": false,
257
+ "eval_use_gather_object": false,
258
+ "average_tokens_across_devices": false,
259
+ "sortish_sampler": false,
260
+ "predict_with_generate": false,
261
+ "generation_max_length": null,
262
+ "generation_num_beams": null,
263
+ "generation_config": null,
264
+ "check_model": true,
265
+ "acc_strategy": "token",
266
+ "train_dataloader_shuffle": true,
267
+ "metric_warmup_step": 0,
268
+ "fsdp_num": 1,
269
+ "acc_steps": 1,
270
+ "eval_use_evalscope": false,
271
+ "eval_datasets": [],
272
+ "eval_limit": null,
273
+ "eval_datasets_args": null,
274
+ "eval_generation_config": null,
275
+ "freeze_parameters": [
276
+ "visual",
277
+ "visual.merger"
278
+ ],
279
+ "freeze_parameters_ratio": 0.0,
280
+ "trainable_parameters": [],
281
+ "freeze_llm": false,
282
+ "freeze_vit": true,
283
+ "freeze_aligner": true,
284
+ "target_modules": [
285
+ "all-linear"
286
+ ],
287
+ "target_regex": null,
288
+ "modules_to_save": [],
289
+ "lora_rank": 8,
290
+ "lora_alpha": 32,
291
+ "lora_dropout": 0.05,
292
+ "lora_bias": "none",
293
+ "lora_dtype": null,
294
+ "lorap_lr_ratio": null,
295
+ "use_rslora": false,
296
+ "use_dora": false,
297
+ "lora_ga_batch_size": 2,
298
+ "lora_ga_iters": 2,
299
+ "lora_ga_max_length": 1024,
300
+ "lora_ga_direction": "ArB2r",
301
+ "lora_ga_scale": "stable",
302
+ "lora_ga_stable_gamma": 16,
303
+ "init_weights": true,
304
+ "fourier_n_frequency": 2000,
305
+ "fourier_scaling": 300.0,
306
+ "boft_block_size": 4,
307
+ "boft_block_num": 0,
308
+ "boft_n_butterfly_factor": 1,
309
+ "boft_dropout": 0.0,
310
+ "vera_rank": 256,
311
+ "vera_projection_prng_key": 0,
312
+ "vera_dropout": 0.0,
313
+ "vera_d_initial": 0.1,
314
+ "adapter_act": "gelu",
315
+ "adapter_length": 128,
316
+ "use_galore": false,
317
+ "galore_target_modules": null,
318
+ "galore_rank": 128,
319
+ "galore_update_proj_gap": 50,
320
+ "galore_scale": 1.0,
321
+ "galore_proj_type": "std",
322
+ "galore_optim_per_parameter": false,
323
+ "galore_with_embedding": false,
324
+ "galore_quantization": false,
325
+ "galore_proj_quant": false,
326
+ "galore_proj_bits": 4,
327
+ "galore_proj_group_size": 256,
328
+ "galore_cos_threshold": 0.4,
329
+ "galore_gamma_proj": 2,
330
+ "galore_queue_size": 5,
331
+ "adalora_target_r": 8,
332
+ "adalora_init_r": 12,
333
+ "adalora_tinit": 0,
334
+ "adalora_tfinal": 0,
335
+ "adalora_deltaT": 1,
336
+ "adalora_beta1": 0.85,
337
+ "adalora_beta2": 0.85,
338
+ "adalora_orth_reg_weight": 0.5,
339
+ "llamapro_num_new_blocks": 4,
340
+ "llamapro_num_groups": null,
341
+ "lisa_activated_layers": 0,
342
+ "lisa_step_interval": 20,
343
+ "reft_layer_key": null,
344
+ "reft_layers": null,
345
+ "reft_rank": 4,
346
+ "reft_intervention_type": "LoreftIntervention",
347
+ "reft_args": null,
348
+ "swanlab_token": null,
349
+ "swanlab_project": null,
350
+ "swanlab_workspace": null,
351
+ "swanlab_exp_name": null,
352
+ "swanlab_mode": "cloud",
353
+ "add_version": true,
354
+ "resume_only_model": false,
355
+ "create_checkpoint_symlink": false,
356
+ "packing": false,
357
+ "lazy_tokenize": true,
358
+ "loss_type": null,
359
+ "optimizer": null,
360
+ "metric": null,
361
+ "zero_hpz_partition_size": null,
362
+ "rank": 0,
363
+ "global_world_size": 16,
364
+ "local_world_size": 8,
365
+ "model_suffix": "Qwen2.5-VL-7B-Instruct",
366
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/group/40174/Zywoou/models/Qwen2.5-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
367
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fb53a0aed40>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=['*.bin', '*.safetensors'], requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
368
+ "model_dir": "/group/40174/Zywoou/models/Qwen2.5-VL-7B-Instruct",
369
+ "hub": "<class 'swift.hub.hub.MSHub'>",
370
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=8, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
371
+ }
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/group/40174/Zywoou/mm_math_reasoning/ms-swift-exp2/oly_output/SFT_text13k_geomm13k_test_mimi_e5/v0-20250615-110647/checkpoint-600",
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
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": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_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
+ "hidden_size": 1280,
41
+ "in_chans": 3,
42
+ "model_type": "qwen2_5_vl",
43
+ "spatial_patch_size": 14,
44
+ "tokens_per_second": 2,
45
+ "torch_dtype": "bfloat16"
46
+ },
47
+ "vision_end_token_id": 151653,
48
+ "vision_start_token_id": 151652,
49
+ "vision_token_id": 151654,
50
+ "vocab_size": 152064
51
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.50.0.dev0"
12
+ }
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:a9a4a58db6f8a44b070a662387f7da589a3964c63374acfb5385586c8845ac6b
3
+ size 4968243304
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a332bdb5f74065378dc523dca09ad060ad235b8f27904810c61be3fcb9d24726
3
+ size 4991495816
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c234dc7eefbb8e8c8cc286cd27dc125adbc5de30503375839e8dfdc9b3b97e
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:b9cb6f6e486b7634eaab4a25cfd7207959a5853468ae9c173707e4113db8bced
3
+ size 1691924384
model.safetensors.index.json ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16584333312
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
734
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
735
+ }
736
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% 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 %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_state.json ADDED
@@ -0,0 +1,793 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4984423676012461,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
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
+ "completions/clipped_ratio": 0.25,
14
+ "completions/max_length": 8193.375,
15
+ "completions/mean_length": 3989.6012573242188,
16
+ "completions/min_length": 431.625,
17
+ "epoch": 0.012461059190031152,
18
+ "grad_norm": 0.17126550499342053,
19
+ "kl": 0.0,
20
+ "learning_rate": 1e-06,
21
+ "loss": -0.12229467928409576,
22
+ "memory(GiB)": 167.35,
23
+ "reward": 0.34970238618552685,
24
+ "reward_std": 0.24919933266937733,
25
+ "rewards/AnswerTagAccuracyORM/mean": 0.34970238618552685,
26
+ "rewards/AnswerTagAccuracyORM/std": 0.44819867983460426,
27
+ "step": 1,
28
+ "train_speed(iter/s)": 0.000657
29
+ },
30
+ {
31
+ "clip_ratio": 0.0,
32
+ "completions/clipped_ratio": 0.20833333333333331,
33
+ "completions/max_length": 8193.125,
34
+ "completions/mean_length": 3849.834930419922,
35
+ "completions/min_length": 370.75,
36
+ "epoch": 0.024922118380062305,
37
+ "grad_norm": 0.1997916996720489,
38
+ "kl": 0.0,
39
+ "learning_rate": 9.996046986136508e-07,
40
+ "loss": -0.09795808792114258,
41
+ "memory(GiB)": 167.35,
42
+ "reward": 0.3898809542879462,
43
+ "reward_std": 0.3207090422511101,
44
+ "rewards/AnswerTagAccuracyORM/mean": 0.3898809542879462,
45
+ "rewards/AnswerTagAccuracyORM/std": 0.45823679864406586,
46
+ "step": 2,
47
+ "train_speed(iter/s)": 0.000679
48
+ },
49
+ {
50
+ "clip_ratio": 0.0,
51
+ "completions/clipped_ratio": 0.29910714285714285,
52
+ "completions/max_length": 8193.25,
53
+ "completions/mean_length": 4399.15478515625,
54
+ "completions/min_length": 428.75,
55
+ "epoch": 0.037383177570093455,
56
+ "grad_norm": 0.17121898013903475,
57
+ "kl": 0.000213623046875,
58
+ "learning_rate": 9.984194195073478e-07,
59
+ "loss": -0.1223849356174469,
60
+ "memory(GiB)": 174.45,
61
+ "reward": 0.37648809468373656,
62
+ "reward_std": 0.2712590955197811,
63
+ "rewards/AnswerTagAccuracyORM/mean": 0.37648809468373656,
64
+ "rewards/AnswerTagAccuracyORM/std": 0.4078557249158621,
65
+ "step": 3,
66
+ "train_speed(iter/s)": 0.000679
67
+ },
68
+ {
69
+ "clip_ratio": 0.0,
70
+ "completions/clipped_ratio": 0.2157738095238095,
71
+ "completions/max_length": 8193.75,
72
+ "completions/mean_length": 3801.852783203125,
73
+ "completions/min_length": 397.75,
74
+ "epoch": 0.04984423676012461,
75
+ "grad_norm": 0.18133669602016783,
76
+ "kl": 0.00020253658294677734,
77
+ "learning_rate": 9.964460368509865e-07,
78
+ "loss": -0.1141134724020958,
79
+ "memory(GiB)": 174.45,
80
+ "reward": 0.47916668094694614,
81
+ "reward_std": 0.303694985806942,
82
+ "rewards/AnswerTagAccuracyORM/mean": 0.47916668094694614,
83
+ "rewards/AnswerTagAccuracyORM/std": 0.44507846981287,
84
+ "step": 4,
85
+ "train_speed(iter/s)": 0.000686
86
+ },
87
+ {
88
+ "clip_ratio": 0.0,
89
+ "completions/clipped_ratio": 0.1919642857142857,
90
+ "completions/max_length": 8193.75,
91
+ "completions/mean_length": 3705.5669860839844,
92
+ "completions/min_length": 372.375,
93
+ "epoch": 0.06230529595015576,
94
+ "grad_norm": 0.2246349455331878,
95
+ "kl": 0.0002810955047607422,
96
+ "learning_rate": 9.936876709681666e-07,
97
+ "loss": -0.1321631819009781,
98
+ "memory(GiB)": 174.45,
99
+ "reward": 0.43154763616621494,
100
+ "reward_std": 0.35136963427066803,
101
+ "rewards/AnswerTagAccuracyORM/mean": 0.43154763616621494,
102
+ "rewards/AnswerTagAccuracyORM/std": 0.4658842086791992,
103
+ "step": 5,
104
+ "train_speed(iter/s)": 0.00069
105
+ },
106
+ {
107
+ "clip_ratio": 0.0,
108
+ "completions/clipped_ratio": 0.20238095238095238,
109
+ "completions/max_length": 8194.875,
110
+ "completions/mean_length": 3702.392852783203,
111
+ "completions/min_length": 364.625,
112
+ "epoch": 0.07476635514018691,
113
+ "grad_norm": 0.17656783163918816,
114
+ "kl": 0.0002797842025756836,
115
+ "learning_rate": 9.901486834023181e-07,
116
+ "loss": -0.08321866393089294,
117
+ "memory(GiB)": 174.45,
118
+ "reward": 0.3764880960807204,
119
+ "reward_std": 0.2821493409574032,
120
+ "rewards/AnswerTagAccuracyORM/mean": 0.3764880960807204,
121
+ "rewards/AnswerTagAccuracyORM/std": 0.4614675045013428,
122
+ "step": 6,
123
+ "train_speed(iter/s)": 0.000693
124
+ },
125
+ {
126
+ "clip_ratio": 0.0,
127
+ "completions/clipped_ratio": 0.28720238095238093,
128
+ "completions/max_length": 8193.625,
129
+ "completions/mean_length": 4263.456878662109,
130
+ "completions/min_length": 327.625,
131
+ "epoch": 0.08722741433021806,
132
+ "grad_norm": 0.2524499795692924,
133
+ "kl": 0.0003044605255126953,
134
+ "learning_rate": 9.858346700202048e-07,
135
+ "loss": -0.19307070970535278,
136
+ "memory(GiB)": 174.45,
137
+ "reward": 0.377976194024086,
138
+ "reward_std": 0.3151053488254547,
139
+ "rewards/AnswerTagAccuracyORM/mean": 0.377976194024086,
140
+ "rewards/AnswerTagAccuracyORM/std": 0.4634386822581291,
141
+ "step": 7,
142
+ "train_speed(iter/s)": 0.000691
143
+ },
144
+ {
145
+ "clip_ratio": 0.0,
146
+ "completions/clipped_ratio": 0.20833333333333331,
147
+ "completions/max_length": 8193.25,
148
+ "completions/mean_length": 3797.3007202148438,
149
+ "completions/min_length": 272.5,
150
+ "epoch": 0.09968847352024922,
151
+ "grad_norm": 0.20136930786075843,
152
+ "kl": 0.00032448768615722656,
153
+ "learning_rate": 9.807524521637102e-07,
154
+ "loss": -0.10552932322025299,
155
+ "memory(GiB)": 174.45,
156
+ "reward": 0.4092261902987957,
157
+ "reward_std": 0.3334960360080004,
158
+ "rewards/AnswerTagAccuracyORM/mean": 0.4092261902987957,
159
+ "rewards/AnswerTagAccuracyORM/std": 0.47217297181487083,
160
+ "step": 8,
161
+ "train_speed(iter/s)": 0.000693
162
+ },
163
+ {
164
+ "clip_ratio": 0.0,
165
+ "completions/clipped_ratio": 0.2663690476190476,
166
+ "completions/max_length": 8193.25,
167
+ "completions/mean_length": 4201.8289794921875,
168
+ "completions/min_length": 466.0,
169
+ "epoch": 0.11214953271028037,
170
+ "grad_norm": 0.19988066240856855,
171
+ "kl": 0.0003037452697753906,
172
+ "learning_rate": 9.749100658638914e-07,
173
+ "loss": -0.12433922290802002,
174
+ "memory(GiB)": 174.52,
175
+ "reward": 0.3482142873108387,
176
+ "reward_std": 0.2973194606602192,
177
+ "rewards/AnswerTagAccuracyORM/mean": 0.3482142873108387,
178
+ "rewards/AnswerTagAccuracyORM/std": 0.4571182616055012,
179
+ "step": 9,
180
+ "train_speed(iter/s)": 0.000692
181
+ },
182
+ {
183
+ "clip_ratio": 0.0,
184
+ "completions/clipped_ratio": 0.23660714285714288,
185
+ "completions/max_length": 8193.5,
186
+ "completions/mean_length": 4137.879486083984,
187
+ "completions/min_length": 402.25,
188
+ "epoch": 0.12461059190031153,
189
+ "grad_norm": 0.23579962953472336,
190
+ "kl": 0.00039386749267578125,
191
+ "learning_rate": 9.68316749134364e-07,
192
+ "loss": -0.15604804456233978,
193
+ "memory(GiB)": 175.38,
194
+ "reward": 0.37648810259997845,
195
+ "reward_std": 0.33304327353835106,
196
+ "rewards/AnswerTagAccuracyORM/mean": 0.37648810259997845,
197
+ "rewards/AnswerTagAccuracyORM/std": 0.46259133517742157,
198
+ "step": 10,
199
+ "train_speed(iter/s)": 0.000692
200
+ },
201
+ {
202
+ "clip_ratio": 0.0,
203
+ "completions/clipped_ratio": 0.1949404761904762,
204
+ "completions/max_length": 8193.0,
205
+ "completions/mean_length": 3524.0000915527344,
206
+ "completions/min_length": 352.5,
207
+ "epoch": 0.13707165109034267,
208
+ "grad_norm": 0.18587876448756557,
209
+ "kl": 0.0004878044128417969,
210
+ "learning_rate": 9.609829273641032e-07,
211
+ "loss": -0.09066524356603622,
212
+ "memory(GiB)": 175.38,
213
+ "reward": 0.3913690634071827,
214
+ "reward_std": 0.2906598076224327,
215
+ "rewards/AnswerTagAccuracyORM/mean": 0.3913690634071827,
216
+ "rewards/AnswerTagAccuracyORM/std": 0.48316407203674316,
217
+ "step": 11,
218
+ "train_speed(iter/s)": 0.000694
219
+ },
220
+ {
221
+ "clip_ratio": 0.0,
222
+ "completions/clipped_ratio": 0.33035714285714285,
223
+ "completions/max_length": 8193.0,
224
+ "completions/mean_length": 4620.495635986328,
225
+ "completions/min_length": 343.25,
226
+ "epoch": 0.14953271028037382,
227
+ "grad_norm": 0.21227366684003468,
228
+ "kl": 0.00048542022705078125,
229
+ "learning_rate": 9.529201968327616e-07,
230
+ "loss": -0.179769366979599,
231
+ "memory(GiB)": 175.38,
232
+ "reward": 0.3452381007373333,
233
+ "reward_std": 0.24404709972441196,
234
+ "rewards/AnswerTagAccuracyORM/mean": 0.3452381007373333,
235
+ "rewards/AnswerTagAccuracyORM/std": 0.4610680975019932,
236
+ "step": 12,
237
+ "train_speed(iter/s)": 0.000692
238
+ },
239
+ {
240
+ "clip_ratio": 0.0,
241
+ "completions/clipped_ratio": 0.19345238095238096,
242
+ "completions/max_length": 8193.0,
243
+ "completions/mean_length": 3493.071502685547,
244
+ "completions/min_length": 343.625,
245
+ "epoch": 0.16199376947040497,
246
+ "grad_norm": 0.19459450978177167,
247
+ "kl": 0.000698089599609375,
248
+ "learning_rate": 9.441413063745659e-07,
249
+ "loss": -0.12030751258134842,
250
+ "memory(GiB)": 175.38,
251
+ "reward": 0.45238096080720425,
252
+ "reward_std": 0.3026049826294184,
253
+ "rewards/AnswerTagAccuracyORM/mean": 0.45238096080720425,
254
+ "rewards/AnswerTagAccuracyORM/std": 0.4734005853533745,
255
+ "step": 13,
256
+ "train_speed(iter/s)": 0.000694
257
+ },
258
+ {
259
+ "clip_ratio": 0.0,
260
+ "completions/clipped_ratio": 0.24404761904761904,
261
+ "completions/max_length": 8193.125,
262
+ "completions/mean_length": 3945.2025146484375,
263
+ "completions/min_length": 317.5,
264
+ "epoch": 0.17445482866043613,
265
+ "grad_norm": 0.2160426116072706,
266
+ "kl": 0.0008077621459960938,
267
+ "learning_rate": 9.346601372197913e-07,
268
+ "loss": -0.17013423144817352,
269
+ "memory(GiB)": 175.38,
270
+ "reward": 0.4226190559566021,
271
+ "reward_std": 0.31002783961594105,
272
+ "rewards/AnswerTagAccuracyORM/mean": 0.4226190559566021,
273
+ "rewards/AnswerTagAccuracyORM/std": 0.48812782764434814,
274
+ "step": 14,
275
+ "train_speed(iter/s)": 0.000695
276
+ },
277
+ {
278
+ "clip_ratio": 0.0,
279
+ "completions/clipped_ratio": 0.2693452380952381,
280
+ "completions/max_length": 8193.25,
281
+ "completions/mean_length": 3999.154815673828,
282
+ "completions/min_length": 381.0,
283
+ "epoch": 0.18691588785046728,
284
+ "grad_norm": 0.2338145519921423,
285
+ "kl": 0.0007433891296386719,
286
+ "learning_rate": 9.24491681045682e-07,
287
+ "loss": -0.14010122418403625,
288
+ "memory(GiB)": 175.38,
289
+ "reward": 0.3779761968180537,
290
+ "reward_std": 0.2741878144443035,
291
+ "rewards/AnswerTagAccuracyORM/mean": 0.3779761968180537,
292
+ "rewards/AnswerTagAccuracyORM/std": 0.46018435433506966,
293
+ "step": 15,
294
+ "train_speed(iter/s)": 0.000694
295
+ },
296
+ {
297
+ "clip_ratio": 0.0,
298
+ "completions/clipped_ratio": 0.24255952380952378,
299
+ "completions/max_length": 8193.25,
300
+ "completions/mean_length": 3811.431610107422,
301
+ "completions/min_length": 405.25,
302
+ "epoch": 0.19937694704049844,
303
+ "grad_norm": 0.24163120591345413,
304
+ "kl": 0.0007557868957519531,
305
+ "learning_rate": 9.136520162715286e-07,
306
+ "loss": -0.15715962648391724,
307
+ "memory(GiB)": 175.88,
308
+ "reward": 0.5014881025999784,
309
+ "reward_std": 0.2836833242326975,
310
+ "rewards/AnswerTagAccuracyORM/mean": 0.5014881025999784,
311
+ "rewards/AnswerTagAccuracyORM/std": 0.4741004407405853,
312
+ "step": 16,
313
+ "train_speed(iter/s)": 0.000695
314
+ },
315
+ {
316
+ "clip_ratio": 0.0,
317
+ "completions/clipped_ratio": 0.30952380952380953,
318
+ "completions/max_length": 8193.375,
319
+ "completions/mean_length": 4581.294769287109,
320
+ "completions/min_length": 462.75,
321
+ "epoch": 0.2118380062305296,
322
+ "grad_norm": 0.20943523953763443,
323
+ "kl": 0.0010576248168945312,
324
+ "learning_rate": 9.021582826353824e-07,
325
+ "loss": -0.17735408246517181,
326
+ "memory(GiB)": 175.88,
327
+ "reward": 0.345238103531301,
328
+ "reward_std": 0.2590687647461891,
329
+ "rewards/AnswerTagAccuracyORM/mean": 0.345238103531301,
330
+ "rewards/AnswerTagAccuracyORM/std": 0.4563480280339718,
331
+ "step": 17,
332
+ "train_speed(iter/s)": 0.000694
333
+ },
334
+ {
335
+ "clip_ratio": 0.0,
336
+ "completions/clipped_ratio": 0.27232142857142855,
337
+ "completions/max_length": 8193.5,
338
+ "completions/mean_length": 4101.574493408203,
339
+ "completions/min_length": 369.125,
340
+ "epoch": 0.22429906542056074,
341
+ "grad_norm": 0.20605735960275373,
342
+ "kl": 0.001071929931640625,
343
+ "learning_rate": 8.90028654092606e-07,
344
+ "loss": -0.08183983713388443,
345
+ "memory(GiB)": 175.88,
346
+ "reward": 0.39583334792405367,
347
+ "reward_std": 0.24742238968610764,
348
+ "rewards/AnswerTagAccuracyORM/mean": 0.39583334792405367,
349
+ "rewards/AnswerTagAccuracyORM/std": 0.4427494630217552,
350
+ "step": 18,
351
+ "train_speed(iter/s)": 0.000694
352
+ },
353
+ {
354
+ "clip_ratio": 0.0,
355
+ "completions/clipped_ratio": 0.2723214285714286,
356
+ "completions/max_length": 8196.125,
357
+ "completions/mean_length": 3904.400390625,
358
+ "completions/min_length": 349.125,
359
+ "epoch": 0.2367601246105919,
360
+ "grad_norm": 0.22278161024164303,
361
+ "kl": 0.0016794204711914062,
362
+ "learning_rate": 8.77282310079115e-07,
363
+ "loss": -0.20427300035953522,
364
+ "memory(GiB)": 175.88,
365
+ "reward": 0.4389881044626236,
366
+ "reward_std": 0.2799454350024462,
367
+ "rewards/AnswerTagAccuracyORM/mean": 0.4389881044626236,
368
+ "rewards/AnswerTagAccuracyORM/std": 0.4796442426741123,
369
+ "step": 19,
370
+ "train_speed(iter/s)": 0.000694
371
+ },
372
+ {
373
+ "clip_ratio": 0.0,
374
+ "completions/clipped_ratio": 0.32589285714285715,
375
+ "completions/max_length": 8198.5,
376
+ "completions/mean_length": 4417.791748046875,
377
+ "completions/min_length": 493.75,
378
+ "epoch": 0.24922118380062305,
379
+ "grad_norm": 0.17009334695071343,
380
+ "kl": 0.001983642578125,
381
+ "learning_rate": 8.639394051847471e-07,
382
+ "loss": -0.07000445574522018,
383
+ "memory(GiB)": 175.93,
384
+ "reward": 0.31250000186264515,
385
+ "reward_std": 0.21009514946490526,
386
+ "rewards/AnswerTagAccuracyORM/mean": 0.31250000186264515,
387
+ "rewards/AnswerTagAccuracyORM/std": 0.4253981076180935,
388
+ "step": 20,
389
+ "train_speed(iter/s)": 0.000693
390
+ },
391
+ {
392
+ "clip_ratio": 0.0,
393
+ "completions/clipped_ratio": 0.261904761904762,
394
+ "completions/max_length": 8193.0,
395
+ "completions/mean_length": 4160.090850830078,
396
+ "completions/min_length": 358.75,
397
+ "epoch": 0.2616822429906542,
398
+ "grad_norm": 0.18862458424536294,
399
+ "kl": 0.002643585205078125,
400
+ "learning_rate": 8.500210372847126e-07,
401
+ "loss": -0.14565826952457428,
402
+ "memory(GiB)": 175.93,
403
+ "reward": 0.42857143841683865,
404
+ "reward_std": 0.27233397029340267,
405
+ "rewards/AnswerTagAccuracyORM/mean": 0.42857143841683865,
406
+ "rewards/AnswerTagAccuracyORM/std": 0.4581611305475235,
407
+ "step": 21,
408
+ "train_speed(iter/s)": 0.000692
409
+ },
410
+ {
411
+ "clip_ratio": 0.0,
412
+ "completions/clipped_ratio": 0.25,
413
+ "completions/max_length": 8193.125,
414
+ "completions/mean_length": 4088.5298767089844,
415
+ "completions/min_length": 376.375,
416
+ "epoch": 0.27414330218068533,
417
+ "grad_norm": 0.19231284564227827,
418
+ "kl": 0.0030651092529296875,
419
+ "learning_rate": 8.355492141795184e-07,
420
+ "loss": -0.17381058633327484,
421
+ "memory(GiB)": 175.93,
422
+ "reward": 0.3854166716337204,
423
+ "reward_std": 0.26877069287002087,
424
+ "rewards/AnswerTagAccuracyORM/mean": 0.3854166716337204,
425
+ "rewards/AnswerTagAccuracyORM/std": 0.4839600883424282,
426
+ "step": 22,
427
+ "train_speed(iter/s)": 0.000692
428
+ },
429
+ {
430
+ "clip_ratio": 0.0,
431
+ "completions/clipped_ratio": 0.28720238095238093,
432
+ "completions/max_length": 8193.125,
433
+ "completions/mean_length": 4086.6087036132812,
434
+ "completions/min_length": 368.875,
435
+ "epoch": 0.2866043613707165,
436
+ "grad_norm": 0.2125176134875177,
437
+ "kl": 0.00290679931640625,
438
+ "learning_rate": 8.2054681879611e-07,
439
+ "loss": -0.22260838747024536,
440
+ "memory(GiB)": 175.93,
441
+ "reward": 0.4613095372915268,
442
+ "reward_std": 0.25964014790952206,
443
+ "rewards/AnswerTagAccuracyORM/mean": 0.4613095372915268,
444
+ "rewards/AnswerTagAccuracyORM/std": 0.4591619521379471,
445
+ "step": 23,
446
+ "train_speed(iter/s)": 0.000692
447
+ },
448
+ {
449
+ "clip_ratio": 0.0,
450
+ "completions/clipped_ratio": 0.244047619047619,
451
+ "completions/max_length": 8193.375,
452
+ "completions/mean_length": 3719.543182373047,
453
+ "completions/min_length": 375.5,
454
+ "epoch": 0.29906542056074764,
455
+ "grad_norm": 0.21050284745364475,
456
+ "kl": 0.00313568115234375,
457
+ "learning_rate": 8.050375730052621e-07,
458
+ "loss": -0.130848228931427,
459
+ "memory(GiB)": 175.93,
460
+ "reward": 0.404761909507215,
461
+ "reward_std": 0.28319618850946426,
462
+ "rewards/AnswerTagAccuracyORM/mean": 0.404761909507215,
463
+ "rewards/AnswerTagAccuracyORM/std": 0.46318022534251213,
464
+ "step": 24,
465
+ "train_speed(iter/s)": 0.000692
466
+ },
467
+ {
468
+ "clip_ratio": 0.0,
469
+ "completions/clipped_ratio": 0.3125,
470
+ "completions/max_length": 8193.375,
471
+ "completions/mean_length": 4491.202484130859,
472
+ "completions/min_length": 415.25,
473
+ "epoch": 0.3115264797507788,
474
+ "grad_norm": 0.1899503253060254,
475
+ "kl": 0.0037708282470703125,
476
+ "learning_rate": 7.890460001124241e-07,
477
+ "loss": -0.14017701148986816,
478
+ "memory(GiB)": 175.93,
479
+ "reward": 0.3750000046566129,
480
+ "reward_std": 0.2724082116037607,
481
+ "rewards/AnswerTagAccuracyORM/mean": 0.3750000046566129,
482
+ "rewards/AnswerTagAccuracyORM/std": 0.4636641815304756,
483
+ "step": 25,
484
+ "train_speed(iter/s)": 0.000691
485
+ },
486
+ {
487
+ "clip_ratio": 0.0,
488
+ "completions/clipped_ratio": 0.23809523809523808,
489
+ "completions/max_length": 8193.375,
490
+ "completions/mean_length": 3894.7633666992188,
491
+ "completions/min_length": 407.25,
492
+ "epoch": 0.32398753894080995,
493
+ "grad_norm": 0.21607441644369615,
494
+ "kl": 0.004718780517578125,
495
+ "learning_rate": 7.725973860813338e-07,
496
+ "loss": -0.13692191243171692,
497
+ "memory(GiB)": 175.93,
498
+ "reward": 0.46130953915417194,
499
+ "reward_std": 0.2574587743729353,
500
+ "rewards/AnswerTagAccuracyORM/mean": 0.46130953915417194,
501
+ "rewards/AnswerTagAccuracyORM/std": 0.46890895441174507,
502
+ "step": 26,
503
+ "train_speed(iter/s)": 0.000691
504
+ },
505
+ {
506
+ "clip_ratio": 0.0,
507
+ "completions/clipped_ratio": 0.23214285714285715,
508
+ "completions/max_length": 8193.25,
509
+ "completions/mean_length": 3892.3154907226562,
510
+ "completions/min_length": 490.5,
511
+ "epoch": 0.3364485981308411,
512
+ "grad_norm": 0.2714960413830388,
513
+ "kl": 0.004787445068359375,
514
+ "learning_rate": 7.557177395517111e-07,
515
+ "loss": -0.12591125071048737,
516
+ "memory(GiB)": 176.07,
517
+ "reward": 0.41369048738852143,
518
+ "reward_std": 0.2556753307580948,
519
+ "rewards/AnswerTagAccuracyORM/mean": 0.41369048738852143,
520
+ "rewards/AnswerTagAccuracyORM/std": 0.46406359039247036,
521
+ "step": 27,
522
+ "train_speed(iter/s)": 0.000691
523
+ },
524
+ {
525
+ "clip_ratio": 0.0,
526
+ "completions/clipped_ratio": 0.21726190476190477,
527
+ "completions/max_length": 8193.125,
528
+ "completions/mean_length": 3599.0833740234375,
529
+ "completions/min_length": 376.75,
530
+ "epoch": 0.34890965732087226,
531
+ "grad_norm": 0.19644845815079176,
532
+ "kl": 0.003849029541015625,
533
+ "learning_rate": 7.38433750714253e-07,
534
+ "loss": -0.1492602676153183,
535
+ "memory(GiB)": 176.07,
536
+ "reward": 0.4702381044626236,
537
+ "reward_std": 0.2548898998647928,
538
+ "rewards/AnswerTagAccuracyORM/mean": 0.4702381044626236,
539
+ "rewards/AnswerTagAccuracyORM/std": 0.4880012050271034,
540
+ "step": 28,
541
+ "train_speed(iter/s)": 0.000692
542
+ },
543
+ {
544
+ "clip_ratio": 0.0,
545
+ "completions/clipped_ratio": 0.24255952380952378,
546
+ "completions/max_length": 8193.125,
547
+ "completions/mean_length": 4016.561065673828,
548
+ "completions/min_length": 468.875,
549
+ "epoch": 0.3613707165109034,
550
+ "grad_norm": 0.17926535607961544,
551
+ "kl": 0.0053863525390625,
552
+ "learning_rate": 7.207727491079559e-07,
553
+ "loss": -0.09940721839666367,
554
+ "memory(GiB)": 176.07,
555
+ "reward": 0.4523809663951397,
556
+ "reward_std": 0.2573994603008032,
557
+ "rewards/AnswerTagAccuracyORM/mean": 0.4523809663951397,
558
+ "rewards/AnswerTagAccuracyORM/std": 0.48338139802217484,
559
+ "step": 29,
560
+ "train_speed(iter/s)": 0.000692
561
+ },
562
+ {
563
+ "clip_ratio": 0.0,
564
+ "completions/clipped_ratio": 0.2619047619047619,
565
+ "completions/max_length": 8193.375,
566
+ "completions/mean_length": 4025.3720703125,
567
+ "completions/min_length": 408.625,
568
+ "epoch": 0.37383177570093457,
569
+ "grad_norm": 0.1833169510245964,
570
+ "kl": 0.00562286376953125,
571
+ "learning_rate": 7.027626604064969e-07,
572
+ "loss": -0.10118662565946579,
573
+ "memory(GiB)": 176.07,
574
+ "reward": 0.3854166753590107,
575
+ "reward_std": 0.23373469151556492,
576
+ "rewards/AnswerTagAccuracyORM/mean": 0.3854166753590107,
577
+ "rewards/AnswerTagAccuracyORM/std": 0.46597452089190483,
578
+ "step": 30,
579
+ "train_speed(iter/s)": 0.000692
580
+ },
581
+ {
582
+ "clip_ratio": 0.0,
583
+ "completions/clipped_ratio": 0.2663690476190476,
584
+ "completions/max_length": 8193.25,
585
+ "completions/mean_length": 3996.0833740234375,
586
+ "completions/min_length": 357.875,
587
+ "epoch": 0.3862928348909657,
588
+ "grad_norm": 0.21555033230693768,
589
+ "kl": 0.00638580322265625,
590
+ "learning_rate": 6.844319622620039e-07,
591
+ "loss": -0.17128993570804596,
592
+ "memory(GiB)": 177.2,
593
+ "reward": 0.4315476343035698,
594
+ "reward_std": 0.287859283387661,
595
+ "rewards/AnswerTagAccuracyORM/mean": 0.4315476343035698,
596
+ "rewards/AnswerTagAccuracyORM/std": 0.4801550768315792,
597
+ "step": 31,
598
+ "train_speed(iter/s)": 0.000692
599
+ },
600
+ {
601
+ "clip_ratio": 0.0,
602
+ "completions/clipped_ratio": 0.2604166666666667,
603
+ "completions/max_length": 8193.125,
604
+ "completions/mean_length": 3904.589385986328,
605
+ "completions/min_length": 405.5,
606
+ "epoch": 0.3987538940809969,
607
+ "grad_norm": 0.19674394061545156,
608
+ "kl": 0.006427764892578125,
609
+ "learning_rate": 6.658096392760339e-07,
610
+ "loss": -0.1568790227174759,
611
+ "memory(GiB)": 177.2,
612
+ "reward": 0.4315476268529892,
613
+ "reward_std": 0.2220794102177024,
614
+ "rewards/AnswerTagAccuracyORM/mean": 0.4315476268529892,
615
+ "rewards/AnswerTagAccuracyORM/std": 0.48653851449489594,
616
+ "step": 32,
617
+ "train_speed(iter/s)": 0.000692
618
+ },
619
+ {
620
+ "clip_ratio": 0.0,
621
+ "completions/clipped_ratio": 0.22767857142857145,
622
+ "completions/max_length": 8193.875,
623
+ "completions/mean_length": 3937.4747924804688,
624
+ "completions/min_length": 423.875,
625
+ "epoch": 0.411214953271028,
626
+ "grad_norm": 0.19013545416962976,
627
+ "kl": 0.007045745849609375,
628
+ "learning_rate": 6.469251371689604e-07,
629
+ "loss": -0.15400366485118866,
630
+ "memory(GiB)": 177.2,
631
+ "reward": 0.5223214328289032,
632
+ "reward_std": 0.30748542957007885,
633
+ "rewards/AnswerTagAccuracyORM/mean": 0.5223214328289032,
634
+ "rewards/AnswerTagAccuracyORM/std": 0.48715949431061745,
635
+ "step": 33,
636
+ "train_speed(iter/s)": 0.000692
637
+ },
638
+ {
639
+ "clip_ratio": 0.0,
640
+ "completions/clipped_ratio": 0.17261904761904764,
641
+ "completions/max_length": 8193.375,
642
+ "completions/mean_length": 3657.462890625,
643
+ "completions/min_length": 391.75,
644
+ "epoch": 0.4236760124610592,
645
+ "grad_norm": 0.149800501823744,
646
+ "kl": 0.00738525390625,
647
+ "learning_rate": 6.278083162202373e-07,
648
+ "loss": -0.054694823920726776,
649
+ "memory(GiB)": 177.2,
650
+ "reward": 0.4613095410168171,
651
+ "reward_std": 0.21404170151799917,
652
+ "rewards/AnswerTagAccuracyORM/mean": 0.4613095410168171,
653
+ "rewards/AnswerTagAccuracyORM/std": 0.49066925421357155,
654
+ "step": 34,
655
+ "train_speed(iter/s)": 0.000692
656
+ },
657
+ {
658
+ "clip_ratio": 0.0,
659
+ "completions/clipped_ratio": 0.244047619047619,
660
+ "completions/max_length": 8193.125,
661
+ "completions/mean_length": 3713.2679138183594,
662
+ "completions/min_length": 407.125,
663
+ "epoch": 0.43613707165109034,
664
+ "grad_norm": 0.2141010331036125,
665
+ "kl": 0.008380889892578125,
666
+ "learning_rate": 6.084894040531589e-07,
667
+ "loss": -0.14978839457035065,
668
+ "memory(GiB)": 177.2,
669
+ "reward": 0.5000000176951289,
670
+ "reward_std": 0.2632578443735838,
671
+ "rewards/AnswerTagAccuracyORM/mean": 0.5000000176951289,
672
+ "rewards/AnswerTagAccuracyORM/std": 0.43221472948789597,
673
+ "step": 35,
674
+ "train_speed(iter/s)": 0.000692
675
+ },
676
+ {
677
+ "clip_ratio": 0.0,
678
+ "completions/clipped_ratio": 0.25744047619047616,
679
+ "completions/max_length": 8194.125,
680
+ "completions/mean_length": 4263.843811035156,
681
+ "completions/min_length": 441.125,
682
+ "epoch": 0.4485981308411215,
683
+ "grad_norm": 0.17438120553123407,
684
+ "kl": 0.006961822509765625,
685
+ "learning_rate": 5.889989478387752e-07,
686
+ "loss": -0.0636586844921112,
687
+ "memory(GiB)": 177.2,
688
+ "reward": 0.41220239736139774,
689
+ "reward_std": 0.2634734772145748,
690
+ "rewards/AnswerTagAccuracyORM/mean": 0.41220239736139774,
691
+ "rewards/AnswerTagAccuracyORM/std": 0.47433316707611084,
692
+ "step": 36,
693
+ "train_speed(iter/s)": 0.000692
694
+ },
695
+ {
696
+ "clip_ratio": 0.0,
697
+ "completions/clipped_ratio": 0.2946428571428571,
698
+ "completions/max_length": 8193.5,
699
+ "completions/mean_length": 4341.491119384766,
700
+ "completions/min_length": 374.625,
701
+ "epoch": 0.46105919003115264,
702
+ "grad_norm": 0.21429795338500487,
703
+ "kl": 0.00689697265625,
704
+ "learning_rate": 5.693677659945342e-07,
705
+ "loss": -0.15549130737781525,
706
+ "memory(GiB)": 177.2,
707
+ "reward": 0.4330357238650322,
708
+ "reward_std": 0.30585045740008354,
709
+ "rewards/AnswerTagAccuracyORM/mean": 0.4330357238650322,
710
+ "rewards/AnswerTagAccuracyORM/std": 0.4805232435464859,
711
+ "step": 37,
712
+ "train_speed(iter/s)": 0.000691
713
+ },
714
+ {
715
+ "clip_ratio": 0.0,
716
+ "completions/clipped_ratio": 0.255952380952381,
717
+ "completions/max_length": 8153.5,
718
+ "completions/mean_length": 3888.888381958008,
719
+ "completions/min_length": 513.875,
720
+ "epoch": 0.4735202492211838,
721
+ "grad_norm": 0.23492644678534505,
722
+ "kl": 0.008266448974609375,
723
+ "learning_rate": 5.496268994540309e-07,
724
+ "loss": -0.13862904906272888,
725
+ "memory(GiB)": 177.2,
726
+ "reward": 0.49107144121080637,
727
+ "reward_std": 0.2540656551718712,
728
+ "rewards/AnswerTagAccuracyORM/mean": 0.49107144121080637,
729
+ "rewards/AnswerTagAccuracyORM/std": 0.450797863304615,
730
+ "step": 38,
731
+ "train_speed(iter/s)": 0.000692
732
+ },
733
+ {
734
+ "clip_ratio": 0.0,
735
+ "completions/clipped_ratio": 0.3169642857142857,
736
+ "completions/max_length": 8193.125,
737
+ "completions/mean_length": 4171.233703613281,
738
+ "completions/min_length": 372.125,
739
+ "epoch": 0.48598130841121495,
740
+ "grad_norm": 0.21053247802635136,
741
+ "kl": 0.006114959716796875,
742
+ "learning_rate": 5.298075625849099e-07,
743
+ "loss": -0.1665022075176239,
744
+ "memory(GiB)": 177.2,
745
+ "reward": 0.4077381081879139,
746
+ "reward_std": 0.2519750725477934,
747
+ "rewards/AnswerTagAccuracyORM/mean": 0.4077381081879139,
748
+ "rewards/AnswerTagAccuracyORM/std": 0.4829714484512806,
749
+ "step": 39,
750
+ "train_speed(iter/s)": 0.000692
751
+ },
752
+ {
753
+ "clip_ratio": 0.0,
754
+ "completions/clipped_ratio": 0.2693452380952381,
755
+ "completions/max_length": 8193.625,
756
+ "completions/mean_length": 4133.266448974609,
757
+ "completions/min_length": 360.75,
758
+ "epoch": 0.4984423676012461,
759
+ "grad_norm": 0.2650285808547177,
760
+ "kl": 0.00934600830078125,
761
+ "learning_rate": 5.09941093832535e-07,
762
+ "loss": -0.19298426806926727,
763
+ "memory(GiB)": 177.2,
764
+ "reward": 0.4479166716337204,
765
+ "reward_std": 0.28238569758832455,
766
+ "rewards/AnswerTagAccuracyORM/mean": 0.4479166716337204,
767
+ "rewards/AnswerTagAccuracyORM/std": 0.46365100890398026,
768
+ "step": 40,
769
+ "train_speed(iter/s)": 0.000692
770
+ }
771
+ ],
772
+ "logging_steps": 1,
773
+ "max_steps": 80,
774
+ "num_input_tokens_seen": 0,
775
+ "num_train_epochs": 1,
776
+ "save_steps": 20,
777
+ "stateful_callbacks": {
778
+ "TrainerControl": {
779
+ "args": {
780
+ "should_epoch_stop": false,
781
+ "should_evaluate": false,
782
+ "should_log": false,
783
+ "should_save": true,
784
+ "should_training_stop": false
785
+ },
786
+ "attributes": {}
787
+ }
788
+ },
789
+ "total_flos": 0.0,
790
+ "train_batch_size": 4,
791
+ "trial_name": null,
792
+ "trial_params": null
793
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36db0e363a3e82baac59bff90a55ff0a71b4a448f52cbe00907d7cfbb8063084
3
+ size 10104
vocab.json ADDED
The diff for this file is too large to render. See raw diff