Hugging Face's logo

saim1212
/
penguin2-weights

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Metrics Community
saim1212 commited on
Commit
2fa44d9
·
verified ·
1 Parent(s): fd79b14

second model upload

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. README.md +63 -0
  3. adapter_config.json +463 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +16 -0
  6. all_results.json +8 -0
  7. chat_template.json +3 -0
  8. checkpoint-1000/README.md +202 -0
  9. checkpoint-1000/adapter_config.json +463 -0
  10. checkpoint-1000/adapter_model.safetensors +3 -0
  11. checkpoint-1000/added_tokens.json +16 -0
  12. checkpoint-1000/chat_template.json +3 -0
  13. checkpoint-1000/merges.txt +0 -0
  14. checkpoint-1000/optimizer.pt +3 -0
  15. checkpoint-1000/preprocessor_config.json +29 -0
  16. checkpoint-1000/rng_state_0.pth +3 -0
  17. checkpoint-1000/rng_state_1.pth +3 -0
  18. checkpoint-1000/scaler.pt +3 -0
  19. checkpoint-1000/scheduler.pt +3 -0
  20. checkpoint-1000/special_tokens_map.json +31 -0
  21. checkpoint-1000/tokenizer.json +3 -0
  22. checkpoint-1000/tokenizer_config.json +148 -0
  23. checkpoint-1000/trainer_state.json +733 -0
  24. checkpoint-1000/training_args.bin +3 -0
  25. checkpoint-1000/vocab.json +0 -0
  26. checkpoint-1550/README.md +202 -0
  27. checkpoint-1550/adapter_config.json +463 -0
  28. checkpoint-1550/adapter_model.safetensors +3 -0
  29. checkpoint-1550/added_tokens.json +16 -0
  30. checkpoint-1550/chat_template.json +3 -0
  31. checkpoint-1550/merges.txt +0 -0
  32. checkpoint-1550/optimizer.pt +3 -0
  33. checkpoint-1550/preprocessor_config.json +29 -0
  34. checkpoint-1550/rng_state_0.pth +3 -0
  35. checkpoint-1550/rng_state_1.pth +3 -0
  36. checkpoint-1550/scaler.pt +3 -0
  37. checkpoint-1550/scheduler.pt +3 -0
  38. checkpoint-1550/special_tokens_map.json +31 -0
  39. checkpoint-1550/tokenizer.json +3 -0
  40. checkpoint-1550/tokenizer_config.json +148 -0
  41. checkpoint-1550/trainer_state.json +1118 -0
  42. checkpoint-1550/training_args.bin +3 -0
  43. checkpoint-1550/vocab.json +0 -0
  44. merges.txt +0 -0
  45. preprocessor_config.json +29 -0
  46. runs/Mar14_21-25-37_36c244e9105b/events.out.tfevents.1741987616.36c244e9105b.153.0 +3 -0
  47. special_tokens_map.json +31 -0
  48. tokenizer.json +3 -0
  49. tokenizer_config.json +148 -0
  50. train_results.json +8 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: saim1212/penguin2
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qwen2vl_lora_16lr_7b
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qwen2vl_lora_16lr_7b
18
+
19
+ This model is a fine-tuned version of [saim1212/penguin2](https://huggingface.co/saim1212/penguin2) on the talk2car dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 2
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 8
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 25.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.12.0
60
+ - Transformers 4.49.0
61
+ - Pytorch 2.4.1+cu121
62
+ - Datasets 3.2.0
63
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "saim1212/penguin2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "model.layers.26.self_attn.o_proj",
24
+ "model.layers.19.self_attn.o_proj",
25
+ "visual.blocks.22.mlp.fc1",
26
+ "model.layers.1.self_attn.o_proj",
27
+ "model.layers.9.mlp.up_proj",
28
+ "model.layers.23.self_attn_text.q_proj",
29
+ "model.layers.24.self_attn_text.o_proj",
30
+ "model.layers.15.self_attn_text.o_proj",
31
+ "model.layers.27.self_attn.v_proj",
32
+ "model.layers.8.self_attn_text.k_proj",
33
+ "visual.blocks.10.attn.proj",
34
+ "visual.blocks.28.mlp.fc2",
35
+ "model.layers.3.self_attn_text.k_proj",
36
+ "model.layers.12.self_attn.v_proj",
37
+ "model.layers.18.self_attn_text.o_proj",
38
+ "visual.blocks.5.mlp.fc2",
39
+ "model.layers.13.self_attn.q_proj",
40
+ "visual.blocks.7.mlp.fc1",
41
+ "model.layers.27.mlp.down_proj",
42
+ "visual.blocks.1.mlp.fc1",
43
+ "model.layers.12.mlp.up_proj",
44
+ "model.layers.5.self_attn.o_proj",
45
+ "model.layers.15.self_attn_text.q_proj",
46
+ "model.layers.2.self_attn_text.k_proj",
47
+ "model.layers.3.self_attn_text.q_proj",
48
+ "model.layers.12.mlp.down_proj",
49
+ "model.layers.14.self_attn_text.q_proj",
50
+ "model.layers.19.self_attn_text.o_proj",
51
+ "visual.blocks.23.attn.proj",
52
+ "model.layers.20.self_attn.o_proj",
53
+ "model.layers.5.self_attn_text.k_proj",
54
+ "model.layers.26.mlp.gate_proj",
55
+ "model.layers.8.self_attn.q_proj",
56
+ "model.layers.20.mlp.gate_proj",
57
+ "model.layers.16.self_attn_text.k_proj",
58
+ "model.layers.20.self_attn.k_proj",
59
+ "visual.blocks.9.attn.qkv",
60
+ "model.layers.4.self_attn_text.k_proj",
61
+ "model.layers.4.mlp.gate_proj",
62
+ "model.layers.6.self_attn.v_proj",
63
+ "model.layers.1.self_attn_text.o_proj",
64
+ "model.layers.16.mlp.up_proj",
65
+ "visual.blocks.16.mlp.fc2",
66
+ "model.layers.10.self_attn.v_proj",
67
+ "model.layers.17.self_attn_text.o_proj",
68
+ "model.layers.17.self_attn.v_proj",
69
+ "visual.blocks.9.mlp.fc1",
70
+ "model.layers.25.mlp.gate_proj",
71
+ "model.layers.25.self_attn_text.q_proj",
72
+ "model.layers.9.self_attn.k_proj",
73
+ "model.layers.18.self_attn.q_proj",
74
+ "visual.blocks.9.attn.proj",
75
+ "visual.blocks.14.mlp.fc1",
76
+ "model.layers.13.self_attn.o_proj",
77
+ "model.layers.24.self_attn.v_proj",
78
+ "model.layers.11.mlp.down_proj",
79
+ "model.layers.27.self_attn_text.v_proj",
80
+ "model.layers.16.self_attn_text.o_proj",
81
+ "model.layers.25.mlp.down_proj",
82
+ "visual.blocks.4.mlp.fc2",
83
+ "model.layers.27.self_attn.q_proj",
84
+ "visual.blocks.5.attn.proj",
85
+ "model.layers.19.mlp.gate_proj",
86
+ "model.layers.14.self_attn.o_proj",
87
+ "model.layers.19.self_attn.v_proj",
88
+ "model.layers.13.mlp.gate_proj",
89
+ "model.layers.18.self_attn.o_proj",
90
+ "model.layers.18.self_attn.k_proj",
91
+ "model.layers.26.self_attn.k_proj",
92
+ "model.layers.9.self_attn_text.o_proj",
93
+ "model.layers.26.self_attn.v_proj",
94
+ "model.layers.27.self_attn.k_proj",
95
+ "model.layers.25.self_attn.o_proj",
96
+ "visual.blocks.20.attn.proj",
97
+ "visual.blocks.26.attn.qkv",
98
+ "model.layers.23.self_attn_text.v_proj",
99
+ "visual.blocks.14.attn.qkv",
100
+ "model.layers.19.self_attn.k_proj",
101
+ "model.layers.13.self_attn_text.q_proj",
102
+ "model.layers.13.mlp.down_proj",
103
+ "model.layers.21.self_attn.k_proj",
104
+ "model.layers.0.self_attn_text.o_proj",
105
+ "model.layers.6.self_attn.k_proj",
106
+ "visual.blocks.31.attn.proj",
107
+ "model.layers.16.self_attn.v_proj",
108
+ "model.layers.20.mlp.up_proj",
109
+ "visual.blocks.3.mlp.fc2",
110
+ "model.layers.3.self_attn.k_proj",
111
+ "visual.blocks.12.attn.qkv",
112
+ "model.layers.10.self_attn.k_proj",
113
+ "model.layers.12.self_attn_text.k_proj",
114
+ "visual.blocks.22.mlp.fc2",
115
+ "model.layers.11.self_attn.q_proj",
116
+ "visual.blocks.19.mlp.fc1",
117
+ "visual.blocks.2.mlp.fc1",
118
+ "model.layers.26.self_attn_text.k_proj",
119
+ "model.layers.5.self_attn.q_proj",
120
+ "model.layers.7.self_attn.q_proj",
121
+ "visual.blocks.27.attn.proj",
122
+ "model.layers.8.self_attn_text.v_proj",
123
+ "model.layers.12.mlp.gate_proj",
124
+ "model.layers.27.self_attn_text.q_proj",
125
+ "visual.blocks.1.attn.proj",
126
+ "model.layers.4.self_attn_text.o_proj",
127
+ "visual.blocks.6.mlp.fc2",
128
+ "model.layers.26.self_attn_text.v_proj",
129
+ "visual.blocks.6.mlp.fc1",
130
+ "visual.blocks.31.mlp.fc1",
131
+ "model.layers.8.mlp.gate_proj",
132
+ "visual.blocks.18.mlp.fc1",
133
+ "visual.blocks.14.attn.proj",
134
+ "model.layers.15.self_attn.o_proj",
135
+ "model.layers.16.self_attn.q_proj",
136
+ "visual.blocks.7.mlp.fc2",
137
+ "model.layers.11.self_attn.k_proj",
138
+ "model.layers.7.mlp.up_proj",
139
+ "model.layers.10.self_attn_text.v_proj",
140
+ "model.layers.23.self_attn.k_proj",
141
+ "visual.blocks.11.attn.qkv",
142
+ "visual.blocks.5.attn.qkv",
143
+ "model.layers.15.self_attn_text.v_proj",
144
+ "visual.blocks.21.attn.proj",
145
+ "model.layers.10.mlp.gate_proj",
146
+ "model.layers.5.self_attn.v_proj",
147
+ "model.layers.6.mlp.down_proj",
148
+ "model.layers.9.self_attn_text.v_proj",
149
+ "model.layers.4.self_attn_text.q_proj",
150
+ "model.layers.21.self_attn.v_proj",
151
+ "model.layers.8.mlp.down_proj",
152
+ "visual.blocks.8.mlp.fc2",
153
+ "model.layers.23.self_attn_text.o_proj",
154
+ "model.layers.1.self_attn.q_proj",
155
+ "model.layers.20.self_attn_text.k_proj",
156
+ "model.layers.8.self_attn.o_proj",
157
+ "model.layers.20.self_attn_text.o_proj",
158
+ "model.layers.6.mlp.up_proj",
159
+ "model.layers.1.mlp.down_proj",
160
+ "model.layers.18.mlp.down_proj",
161
+ "model.layers.18.mlp.gate_proj",
162
+ "model.layers.11.mlp.up_proj",
163
+ "visual.blocks.2.attn.proj",
164
+ "model.layers.0.mlp.down_proj",
165
+ "visual.blocks.0.mlp.fc2",
166
+ "visual.blocks.25.attn.proj",
167
+ "model.layers.0.self_attn.k_proj",
168
+ "model.layers.27.self_attn_text.k_proj",
169
+ "visual.blocks.12.mlp.fc1",
170
+ "model.layers.9.self_attn.q_proj",
171
+ "visual.blocks.17.attn.qkv",
172
+ "model.layers.17.self_attn_text.q_proj",
173
+ "model.layers.15.mlp.gate_proj",
174
+ "visual.blocks.21.attn.qkv",
175
+ "model.layers.16.mlp.gate_proj",
176
+ "model.layers.19.self_attn_text.v_proj",
177
+ "model.layers.24.self_attn_text.q_proj",
178
+ "visual.blocks.8.mlp.fc1",
179
+ "visual.blocks.30.mlp.fc2",
180
+ "model.layers.10.self_attn.q_proj",
181
+ "model.layers.14.mlp.gate_proj",
182
+ "model.layers.5.self_attn_text.q_proj",
183
+ "visual.blocks.26.mlp.fc2",
184
+ "model.layers.1.self_attn_text.k_proj",
185
+ "visual.blocks.29.mlp.fc1",
186
+ "model.layers.18.self_attn.v_proj",
187
+ "model.layers.23.mlp.gate_proj",
188
+ "visual.blocks.13.mlp.fc1",
189
+ "model.layers.5.self_attn_text.o_proj",
190
+ "model.layers.14.mlp.up_proj",
191
+ "visual.blocks.6.attn.qkv",
192
+ "model.layers.23.mlp.up_proj",
193
+ "model.layers.14.self_attn_text.v_proj",
194
+ "visual.blocks.4.mlp.fc1",
195
+ "visual.blocks.20.attn.qkv",
196
+ "model.layers.6.self_attn_text.q_proj",
197
+ "visual.blocks.25.attn.qkv",
198
+ "visual.blocks.15.attn.qkv",
199
+ "model.layers.1.self_attn.k_proj",
200
+ "model.layers.19.self_attn.q_proj",
201
+ "model.layers.4.self_attn.o_proj",
202
+ "model.layers.8.self_attn.v_proj",
203
+ "visual.blocks.23.attn.qkv",
204
+ "model.layers.3.self_attn.q_proj",
205
+ "model.layers.5.mlp.gate_proj",
206
+ "model.layers.1.mlp.up_proj",
207
+ "model.layers.11.mlp.gate_proj",
208
+ "visual.blocks.24.mlp.fc2",
209
+ "model.layers.1.mlp.gate_proj",
210
+ "visual.blocks.20.mlp.fc1",
211
+ "visual.blocks.13.mlp.fc2",
212
+ "visual.blocks.14.mlp.fc2",
213
+ "visual.blocks.3.attn.qkv",
214
+ "model.layers.12.self_attn_text.q_proj",
215
+ "model.layers.25.self_attn_text.o_proj",
216
+ "visual.blocks.19.attn.proj",
217
+ "visual.blocks.23.mlp.fc1",
218
+ "model.layers.14.mlp.down_proj",
219
+ "visual.blocks.25.mlp.fc2",
220
+ "model.layers.0.self_attn_text.q_proj",
221
+ "model.layers.23.self_attn_text.k_proj",
222
+ "model.layers.12.self_attn.k_proj",
223
+ "model.layers.4.self_attn.k_proj",
224
+ "visual.blocks.28.mlp.fc1",
225
+ "model.layers.21.self_attn_text.v_proj",
226
+ "model.layers.10.mlp.down_proj",
227
+ "visual.blocks.18.attn.qkv",
228
+ "model.layers.5.mlp.up_proj",
229
+ "model.layers.23.self_attn.v_proj",
230
+ "visual.blocks.31.mlp.fc2",
231
+ "model.layers.3.mlp.down_proj",
232
+ "visual.blocks.2.mlp.fc2",
233
+ "visual.blocks.10.mlp.fc2",
234
+ "model.layers.27.self_attn.o_proj",
235
+ "model.layers.11.self_attn_text.v_proj",
236
+ "model.layers.17.self_attn_text.k_proj",
237
+ "visual.blocks.25.mlp.fc1",
238
+ "visual.blocks.3.attn.proj",
239
+ "model.layers.2.self_attn.q_proj",
240
+ "model.layers.26.self_attn_text.o_proj",
241
+ "model.layers.9.self_attn.v_proj",
242
+ "model.layers.7.self_attn_text.o_proj",
243
+ "model.layers.20.self_attn.q_proj",
244
+ "model.layers.21.mlp.down_proj",
245
+ "model.layers.17.self_attn.q_proj",
246
+ "visual.blocks.17.attn.proj",
247
+ "model.layers.7.mlp.down_proj",
248
+ "model.layers.21.mlp.gate_proj",
249
+ "model.layers.20.mlp.down_proj",
250
+ "model.layers.7.self_attn.o_proj",
251
+ "model.layers.6.self_attn_text.o_proj",
252
+ "model.layers.5.self_attn_text.v_proj",
253
+ "model.layers.22.mlp.gate_proj",
254
+ "model.layers.7.self_attn_text.k_proj",
255
+ "model.layers.19.mlp.down_proj",
256
+ "model.layers.6.self_attn_text.k_proj",
257
+ "model.layers.9.self_attn_text.k_proj",
258
+ "visual.blocks.15.attn.proj",
259
+ "visual.blocks.6.attn.proj",
260
+ "model.layers.22.self_attn.k_proj",
261
+ "visual.blocks.13.attn.proj",
262
+ "model.layers.0.mlp.gate_proj",
263
+ "model.layers.13.self_attn.v_proj",
264
+ "model.layers.22.self_attn.q_proj",
265
+ "model.layers.19.self_attn_text.k_proj",
266
+ "model.layers.10.self_attn_text.q_proj",
267
+ "model.layers.2.mlp.down_proj",
268
+ "visual.blocks.10.attn.qkv",
269
+ "model.layers.4.mlp.up_proj",
270
+ "visual.blocks.16.attn.qkv",
271
+ "model.layers.13.self_attn_text.o_proj",
272
+ "model.layers.21.self_attn.o_proj",
273
+ "model.layers.13.mlp.up_proj",
274
+ "model.layers.7.self_attn_text.q_proj",
275
+ "visual.blocks.0.attn.proj",
276
+ "visual.blocks.17.mlp.fc1",
277
+ "model.layers.25.self_attn_text.v_proj",
278
+ "model.layers.3.self_attn.o_proj",
279
+ "visual.blocks.30.attn.proj",
280
+ "model.layers.16.self_attn.o_proj",
281
+ "model.layers.23.self_attn.o_proj",
282
+ "model.layers.4.mlp.down_proj",
283
+ "model.layers.17.self_attn_text.v_proj",
284
+ "model.layers.12.self_attn.q_proj",
285
+ "visual.blocks.3.mlp.fc1",
286
+ "visual.blocks.26.attn.proj",
287
+ "model.layers.21.self_attn.q_proj",
288
+ "visual.blocks.27.attn.qkv",
289
+ "model.layers.17.mlp.gate_proj",
290
+ "model.layers.23.mlp.down_proj",
291
+ "visual.blocks.18.mlp.fc2",
292
+ "model.layers.2.self_attn.k_proj",
293
+ "model.layers.9.mlp.down_proj",
294
+ "model.layers.6.mlp.gate_proj",
295
+ "visual.blocks.17.mlp.fc2",
296
+ "model.layers.0.self_attn.v_proj",
297
+ "visual.blocks.30.attn.qkv",
298
+ "model.layers.3.self_attn_text.o_proj",
299
+ "visual.blocks.4.attn.qkv",
300
+ "model.layers.10.mlp.up_proj",
301
+ "model.layers.2.self_attn.v_proj",
302
+ "visual.blocks.5.mlp.fc1",
303
+ "model.layers.0.self_attn_text.k_proj",
304
+ "model.layers.25.self_attn_text.k_proj",
305
+ "visual.blocks.19.attn.qkv",
306
+ "model.layers.2.mlp.gate_proj",
307
+ "model.layers.16.self_attn_text.q_proj",
308
+ "visual.blocks.0.mlp.fc1",
309
+ "model.layers.3.mlp.up_proj",
310
+ "visual.blocks.30.mlp.fc1",
311
+ "model.layers.2.mlp.up_proj",
312
+ "visual.blocks.29.attn.qkv",
313
+ "model.layers.27.mlp.gate_proj",
314
+ "model.layers.21.self_attn_text.o_proj",
315
+ "model.layers.21.mlp.up_proj",
316
+ "model.layers.1.self_attn.v_proj",
317
+ "visual.blocks.29.attn.proj",
318
+ "model.layers.8.self_attn_text.q_proj",
319
+ "model.layers.3.self_attn_text.v_proj",
320
+ "model.layers.1.self_attn_text.v_proj",
321
+ "visual.blocks.21.mlp.fc2",
322
+ "model.layers.3.self_attn.v_proj",
323
+ "visual.blocks.4.attn.proj",
324
+ "model.layers.4.self_attn.v_proj",
325
+ "model.layers.7.self_attn_text.v_proj",
326
+ "model.layers.22.self_attn_text.v_proj",
327
+ "model.layers.20.self_attn.v_proj",
328
+ "model.layers.21.self_attn_text.q_proj",
329
+ "model.layers.12.self_attn.o_proj",
330
+ "visual.blocks.27.mlp.fc2",
331
+ "model.layers.18.self_attn_text.k_proj",
332
+ "model.layers.24.self_attn_text.v_proj",
333
+ "model.layers.26.mlp.up_proj",
334
+ "model.layers.8.self_attn_text.o_proj",
335
+ "visual.blocks.11.mlp.fc1",
336
+ "model.layers.1.self_attn_text.q_proj",
337
+ "model.layers.7.self_attn.v_proj",
338
+ "visual.blocks.26.mlp.fc1",
339
+ "model.layers.11.self_attn.v_proj",
340
+ "model.layers.13.self_attn.k_proj",
341
+ "model.layers.10.self_attn.o_proj",
342
+ "model.layers.15.mlp.up_proj",
343
+ "visual.blocks.15.mlp.fc1",
344
+ "model.layers.22.mlp.down_proj",
345
+ "model.layers.24.mlp.up_proj",
346
+ "visual.blocks.15.mlp.fc2",
347
+ "model.layers.10.self_attn_text.o_proj",
348
+ "model.layers.15.self_attn_text.k_proj",
349
+ "visual.blocks.1.attn.qkv",
350
+ "model.layers.11.self_attn_text.o_proj",
351
+ "visual.blocks.10.mlp.fc1",
352
+ "model.layers.17.mlp.down_proj",
353
+ "visual.blocks.24.attn.qkv",
354
+ "model.layers.24.mlp.gate_proj",
355
+ "visual.blocks.7.attn.qkv",
356
+ "model.layers.5.self_attn.k_proj",
357
+ "model.layers.23.self_attn.q_proj",
358
+ "model.layers.0.mlp.up_proj",
359
+ "model.layers.22.self_attn_text.q_proj",
360
+ "visual.blocks.12.mlp.fc2",
361
+ "model.layers.3.mlp.gate_proj",
362
+ "model.layers.18.self_attn_text.v_proj",
363
+ "model.layers.12.self_attn_text.o_proj",
364
+ "model.layers.5.mlp.down_proj",
365
+ "model.layers.10.self_attn_text.k_proj",
366
+ "visual.blocks.24.attn.proj",
367
+ "model.layers.11.self_attn_text.q_proj",
368
+ "model.layers.25.self_attn.v_proj",
369
+ "model.layers.17.mlp.up_proj",
370
+ "visual.blocks.23.mlp.fc2",
371
+ "model.layers.22.self_attn.o_proj",
372
+ "model.layers.14.self_attn_text.o_proj",
373
+ "model.layers.19.mlp.up_proj",
374
+ "model.layers.14.self_attn.k_proj",
375
+ "visual.blocks.31.attn.qkv",
376
+ "model.layers.13.self_attn_text.v_proj",
377
+ "model.layers.16.mlp.down_proj",
378
+ "model.layers.16.self_attn_text.v_proj",
379
+ "model.layers.24.self_attn_text.k_proj",
380
+ "model.layers.26.self_attn_text.q_proj",
381
+ "visual.blocks.16.attn.proj",
382
+ "visual.blocks.22.attn.qkv",
383
+ "model.layers.27.self_attn_text.o_proj",
384
+ "visual.blocks.27.mlp.fc1",
385
+ "visual.blocks.12.attn.proj",
386
+ "visual.blocks.28.attn.proj",
387
+ "model.layers.21.self_attn_text.k_proj",
388
+ "visual.blocks.28.attn.qkv",
389
+ "visual.blocks.21.mlp.fc1",
390
+ "model.layers.27.mlp.up_proj",
391
+ "model.layers.15.self_attn.v_proj",
392
+ "model.layers.24.self_attn.k_proj",
393
+ "model.layers.2.self_attn_text.q_proj",
394
+ "model.layers.15.self_attn.q_proj",
395
+ "visual.blocks.29.mlp.fc2",
396
+ "visual.blocks.13.attn.qkv",
397
+ "visual.blocks.24.mlp.fc1",
398
+ "model.layers.11.self_attn.o_proj",
399
+ "model.layers.2.self_attn_text.o_proj",
400
+ "visual.blocks.7.attn.proj",
401
+ "model.layers.6.self_attn.o_proj",
402
+ "model.layers.9.self_attn_text.q_proj",
403
+ "model.layers.0.self_attn.o_proj",
404
+ "model.layers.9.mlp.gate_proj",
405
+ "visual.blocks.0.attn.qkv",
406
+ "model.layers.2.self_attn_text.v_proj",
407
+ "model.layers.8.mlp.up_proj",
408
+ "visual.blocks.8.attn.proj",
409
+ "visual.blocks.18.attn.proj",
410
+ "model.layers.4.self_attn_text.v_proj",
411
+ "model.layers.17.self_attn.o_proj",
412
+ "visual.blocks.22.attn.proj",
413
+ "model.layers.9.self_attn.o_proj",
414
+ "model.layers.26.self_attn.q_proj",
415
+ "visual.blocks.11.mlp.fc2",
416
+ "model.layers.22.mlp.up_proj",
417
+ "model.layers.18.mlp.up_proj",
418
+ "model.layers.14.self_attn_text.k_proj",
419
+ "visual.blocks.9.mlp.fc2",
420
+ "visual.blocks.11.attn.proj",
421
+ "model.layers.17.self_attn.k_proj",
422
+ "model.layers.8.self_attn.k_proj",
423
+ "model.layers.12.self_attn_text.v_proj",
424
+ "model.layers.26.mlp.down_proj",
425
+ "model.layers.14.self_attn.v_proj",
426
+ "model.layers.22.self_attn_text.o_proj",
427
+ "model.layers.0.self_attn_text.v_proj",
428
+ "model.layers.7.mlp.gate_proj",
429
+ "model.layers.22.self_attn.v_proj",
430
+ "model.layers.24.mlp.down_proj",
431
+ "model.layers.20.self_attn_text.q_proj",
432
+ "model.layers.2.self_attn.o_proj",
433
+ "model.layers.11.self_attn_text.k_proj",
434
+ "model.layers.24.self_attn.q_proj",
435
+ "model.layers.18.self_attn_text.q_proj",
436
+ "model.layers.6.self_attn_text.v_proj",
437
+ "model.layers.0.self_attn.q_proj",
438
+ "model.layers.25.self_attn.q_proj",
439
+ "model.layers.19.self_attn_text.q_proj",
440
+ "visual.blocks.20.mlp.fc2",
441
+ "model.layers.13.self_attn_text.k_proj",
442
+ "model.layers.25.mlp.up_proj",
443
+ "model.layers.20.self_attn_text.v_proj",
444
+ "visual.blocks.8.attn.qkv",
445
+ "visual.blocks.16.mlp.fc1",
446
+ "model.layers.25.self_attn.k_proj",
447
+ "model.layers.22.self_attn_text.k_proj",
448
+ "model.layers.16.self_attn.k_proj",
449
+ "model.layers.24.self_attn.o_proj",
450
+ "model.layers.15.self_attn.k_proj",
451
+ "visual.blocks.1.mlp.fc2",
452
+ "model.layers.6.self_attn.q_proj",
453
+ "model.layers.15.mlp.down_proj",
454
+ "visual.blocks.2.attn.qkv",
455
+ "model.layers.14.self_attn.q_proj",
456
+ "model.layers.4.self_attn.q_proj",
457
+ "visual.blocks.19.mlp.fc2",
458
+ "model.layers.7.self_attn.k_proj"
459
+ ],
460
+ "task_type": "CAUSAL_LM",
461
+ "use_dora": false,
462
+ "use_rslora": false
463
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845f34c1f221b697726779b3fd71e1029e7d68df2e0d70cd0bb291bb74d0558a
3
+ size 133350944
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 24.608,
3
+ "total_flos": 1.324081921088553e+17,
4
+ "train_loss": 0.672794044127147,
5
+ "train_runtime": 33908.1665,
6
+ "train_samples_per_second": 0.369,
7
+ "train_steps_per_second": 0.046
8
+ }
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
+ }
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: saim1212/penguin2
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "saim1212/penguin2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "model.layers.26.self_attn.o_proj",
24
+ "model.layers.19.self_attn.o_proj",
25
+ "visual.blocks.22.mlp.fc1",
26
+ "model.layers.1.self_attn.o_proj",
27
+ "model.layers.9.mlp.up_proj",
28
+ "model.layers.23.self_attn_text.q_proj",
29
+ "model.layers.24.self_attn_text.o_proj",
30
+ "model.layers.15.self_attn_text.o_proj",
31
+ "model.layers.27.self_attn.v_proj",
32
+ "model.layers.8.self_attn_text.k_proj",
33
+ "visual.blocks.10.attn.proj",
34
+ "visual.blocks.28.mlp.fc2",
35
+ "model.layers.3.self_attn_text.k_proj",
36
+ "model.layers.12.self_attn.v_proj",
37
+ "model.layers.18.self_attn_text.o_proj",
38
+ "visual.blocks.5.mlp.fc2",
39
+ "model.layers.13.self_attn.q_proj",
40
+ "visual.blocks.7.mlp.fc1",
41
+ "model.layers.27.mlp.down_proj",
42
+ "visual.blocks.1.mlp.fc1",
43
+ "model.layers.12.mlp.up_proj",
44
+ "model.layers.5.self_attn.o_proj",
45
+ "model.layers.15.self_attn_text.q_proj",
46
+ "model.layers.2.self_attn_text.k_proj",
47
+ "model.layers.3.self_attn_text.q_proj",
48
+ "model.layers.12.mlp.down_proj",
49
+ "model.layers.14.self_attn_text.q_proj",
50
+ "model.layers.19.self_attn_text.o_proj",
51
+ "visual.blocks.23.attn.proj",
52
+ "model.layers.20.self_attn.o_proj",
53
+ "model.layers.5.self_attn_text.k_proj",
54
+ "model.layers.26.mlp.gate_proj",
55
+ "model.layers.8.self_attn.q_proj",
56
+ "model.layers.20.mlp.gate_proj",
57
+ "model.layers.16.self_attn_text.k_proj",
58
+ "model.layers.20.self_attn.k_proj",
59
+ "visual.blocks.9.attn.qkv",
60
+ "model.layers.4.self_attn_text.k_proj",
61
+ "model.layers.4.mlp.gate_proj",
62
+ "model.layers.6.self_attn.v_proj",
63
+ "model.layers.1.self_attn_text.o_proj",
64
+ "model.layers.16.mlp.up_proj",
65
+ "visual.blocks.16.mlp.fc2",
66
+ "model.layers.10.self_attn.v_proj",
67
+ "model.layers.17.self_attn_text.o_proj",
68
+ "model.layers.17.self_attn.v_proj",
69
+ "visual.blocks.9.mlp.fc1",
70
+ "model.layers.25.mlp.gate_proj",
71
+ "model.layers.25.self_attn_text.q_proj",
72
+ "model.layers.9.self_attn.k_proj",
73
+ "model.layers.18.self_attn.q_proj",
74
+ "visual.blocks.9.attn.proj",
75
+ "visual.blocks.14.mlp.fc1",
76
+ "model.layers.13.self_attn.o_proj",
77
+ "model.layers.24.self_attn.v_proj",
78
+ "model.layers.11.mlp.down_proj",
79
+ "model.layers.27.self_attn_text.v_proj",
80
+ "model.layers.16.self_attn_text.o_proj",
81
+ "model.layers.25.mlp.down_proj",
82
+ "visual.blocks.4.mlp.fc2",
83
+ "model.layers.27.self_attn.q_proj",
84
+ "visual.blocks.5.attn.proj",
85
+ "model.layers.19.mlp.gate_proj",
86
+ "model.layers.14.self_attn.o_proj",
87
+ "model.layers.19.self_attn.v_proj",
88
+ "model.layers.13.mlp.gate_proj",
89
+ "model.layers.18.self_attn.o_proj",
90
+ "model.layers.18.self_attn.k_proj",
91
+ "model.layers.26.self_attn.k_proj",
92
+ "model.layers.9.self_attn_text.o_proj",
93
+ "model.layers.26.self_attn.v_proj",
94
+ "model.layers.27.self_attn.k_proj",
95
+ "model.layers.25.self_attn.o_proj",
96
+ "visual.blocks.20.attn.proj",
97
+ "visual.blocks.26.attn.qkv",
98
+ "model.layers.23.self_attn_text.v_proj",
99
+ "visual.blocks.14.attn.qkv",
100
+ "model.layers.19.self_attn.k_proj",
101
+ "model.layers.13.self_attn_text.q_proj",
102
+ "model.layers.13.mlp.down_proj",
103
+ "model.layers.21.self_attn.k_proj",
104
+ "model.layers.0.self_attn_text.o_proj",
105
+ "model.layers.6.self_attn.k_proj",
106
+ "visual.blocks.31.attn.proj",
107
+ "model.layers.16.self_attn.v_proj",
108
+ "model.layers.20.mlp.up_proj",
109
+ "visual.blocks.3.mlp.fc2",
110
+ "model.layers.3.self_attn.k_proj",
111
+ "visual.blocks.12.attn.qkv",
112
+ "model.layers.10.self_attn.k_proj",
113
+ "model.layers.12.self_attn_text.k_proj",
114
+ "visual.blocks.22.mlp.fc2",
115
+ "model.layers.11.self_attn.q_proj",
116
+ "visual.blocks.19.mlp.fc1",
117
+ "visual.blocks.2.mlp.fc1",
118
+ "model.layers.26.self_attn_text.k_proj",
119
+ "model.layers.5.self_attn.q_proj",
120
+ "model.layers.7.self_attn.q_proj",
121
+ "visual.blocks.27.attn.proj",
122
+ "model.layers.8.self_attn_text.v_proj",
123
+ "model.layers.12.mlp.gate_proj",
124
+ "model.layers.27.self_attn_text.q_proj",
125
+ "visual.blocks.1.attn.proj",
126
+ "model.layers.4.self_attn_text.o_proj",
127
+ "visual.blocks.6.mlp.fc2",
128
+ "model.layers.26.self_attn_text.v_proj",
129
+ "visual.blocks.6.mlp.fc1",
130
+ "visual.blocks.31.mlp.fc1",
131
+ "model.layers.8.mlp.gate_proj",
132
+ "visual.blocks.18.mlp.fc1",
133
+ "visual.blocks.14.attn.proj",
134
+ "model.layers.15.self_attn.o_proj",
135
+ "model.layers.16.self_attn.q_proj",
136
+ "visual.blocks.7.mlp.fc2",
137
+ "model.layers.11.self_attn.k_proj",
138
+ "model.layers.7.mlp.up_proj",
139
+ "model.layers.10.self_attn_text.v_proj",
140
+ "model.layers.23.self_attn.k_proj",
141
+ "visual.blocks.11.attn.qkv",
142
+ "visual.blocks.5.attn.qkv",
143
+ "model.layers.15.self_attn_text.v_proj",
144
+ "visual.blocks.21.attn.proj",
145
+ "model.layers.10.mlp.gate_proj",
146
+ "model.layers.5.self_attn.v_proj",
147
+ "model.layers.6.mlp.down_proj",
148
+ "model.layers.9.self_attn_text.v_proj",
149
+ "model.layers.4.self_attn_text.q_proj",
150
+ "model.layers.21.self_attn.v_proj",
151
+ "model.layers.8.mlp.down_proj",
152
+ "visual.blocks.8.mlp.fc2",
153
+ "model.layers.23.self_attn_text.o_proj",
154
+ "model.layers.1.self_attn.q_proj",
155
+ "model.layers.20.self_attn_text.k_proj",
156
+ "model.layers.8.self_attn.o_proj",
157
+ "model.layers.20.self_attn_text.o_proj",
158
+ "model.layers.6.mlp.up_proj",
159
+ "model.layers.1.mlp.down_proj",
160
+ "model.layers.18.mlp.down_proj",
161
+ "model.layers.18.mlp.gate_proj",
162
+ "model.layers.11.mlp.up_proj",
163
+ "visual.blocks.2.attn.proj",
164
+ "model.layers.0.mlp.down_proj",
165
+ "visual.blocks.0.mlp.fc2",
166
+ "visual.blocks.25.attn.proj",
167
+ "model.layers.0.self_attn.k_proj",
168
+ "model.layers.27.self_attn_text.k_proj",
169
+ "visual.blocks.12.mlp.fc1",
170
+ "model.layers.9.self_attn.q_proj",
171
+ "visual.blocks.17.attn.qkv",
172
+ "model.layers.17.self_attn_text.q_proj",
173
+ "model.layers.15.mlp.gate_proj",
174
+ "visual.blocks.21.attn.qkv",
175
+ "model.layers.16.mlp.gate_proj",
176
+ "model.layers.19.self_attn_text.v_proj",
177
+ "model.layers.24.self_attn_text.q_proj",
178
+ "visual.blocks.8.mlp.fc1",
179
+ "visual.blocks.30.mlp.fc2",
180
+ "model.layers.10.self_attn.q_proj",
181
+ "model.layers.14.mlp.gate_proj",
182
+ "model.layers.5.self_attn_text.q_proj",
183
+ "visual.blocks.26.mlp.fc2",
184
+ "model.layers.1.self_attn_text.k_proj",
185
+ "visual.blocks.29.mlp.fc1",
186
+ "model.layers.18.self_attn.v_proj",
187
+ "model.layers.23.mlp.gate_proj",
188
+ "visual.blocks.13.mlp.fc1",
189
+ "model.layers.5.self_attn_text.o_proj",
190
+ "model.layers.14.mlp.up_proj",
191
+ "visual.blocks.6.attn.qkv",
192
+ "model.layers.23.mlp.up_proj",
193
+ "model.layers.14.self_attn_text.v_proj",
194
+ "visual.blocks.4.mlp.fc1",
195
+ "visual.blocks.20.attn.qkv",
196
+ "model.layers.6.self_attn_text.q_proj",
197
+ "visual.blocks.25.attn.qkv",
198
+ "visual.blocks.15.attn.qkv",
199
+ "model.layers.1.self_attn.k_proj",
200
+ "model.layers.19.self_attn.q_proj",
201
+ "model.layers.4.self_attn.o_proj",
202
+ "model.layers.8.self_attn.v_proj",
203
+ "visual.blocks.23.attn.qkv",
204
+ "model.layers.3.self_attn.q_proj",
205
+ "model.layers.5.mlp.gate_proj",
206
+ "model.layers.1.mlp.up_proj",
207
+ "model.layers.11.mlp.gate_proj",
208
+ "visual.blocks.24.mlp.fc2",
209
+ "model.layers.1.mlp.gate_proj",
210
+ "visual.blocks.20.mlp.fc1",
211
+ "visual.blocks.13.mlp.fc2",
212
+ "visual.blocks.14.mlp.fc2",
213
+ "visual.blocks.3.attn.qkv",
214
+ "model.layers.12.self_attn_text.q_proj",
215
+ "model.layers.25.self_attn_text.o_proj",
216
+ "visual.blocks.19.attn.proj",
217
+ "visual.blocks.23.mlp.fc1",
218
+ "model.layers.14.mlp.down_proj",
219
+ "visual.blocks.25.mlp.fc2",
220
+ "model.layers.0.self_attn_text.q_proj",
221
+ "model.layers.23.self_attn_text.k_proj",
222
+ "model.layers.12.self_attn.k_proj",
223
+ "model.layers.4.self_attn.k_proj",
224
+ "visual.blocks.28.mlp.fc1",
225
+ "model.layers.21.self_attn_text.v_proj",
226
+ "model.layers.10.mlp.down_proj",
227
+ "visual.blocks.18.attn.qkv",
228
+ "model.layers.5.mlp.up_proj",
229
+ "model.layers.23.self_attn.v_proj",
230
+ "visual.blocks.31.mlp.fc2",
231
+ "model.layers.3.mlp.down_proj",
232
+ "visual.blocks.2.mlp.fc2",
233
+ "visual.blocks.10.mlp.fc2",
234
+ "model.layers.27.self_attn.o_proj",
235
+ "model.layers.11.self_attn_text.v_proj",
236
+ "model.layers.17.self_attn_text.k_proj",
237
+ "visual.blocks.25.mlp.fc1",
238
+ "visual.blocks.3.attn.proj",
239
+ "model.layers.2.self_attn.q_proj",
240
+ "model.layers.26.self_attn_text.o_proj",
241
+ "model.layers.9.self_attn.v_proj",
242
+ "model.layers.7.self_attn_text.o_proj",
243
+ "model.layers.20.self_attn.q_proj",
244
+ "model.layers.21.mlp.down_proj",
245
+ "model.layers.17.self_attn.q_proj",
246
+ "visual.blocks.17.attn.proj",
247
+ "model.layers.7.mlp.down_proj",
248
+ "model.layers.21.mlp.gate_proj",
249
+ "model.layers.20.mlp.down_proj",
250
+ "model.layers.7.self_attn.o_proj",
251
+ "model.layers.6.self_attn_text.o_proj",
252
+ "model.layers.5.self_attn_text.v_proj",
253
+ "model.layers.22.mlp.gate_proj",
254
+ "model.layers.7.self_attn_text.k_proj",
255
+ "model.layers.19.mlp.down_proj",
256
+ "model.layers.6.self_attn_text.k_proj",
257
+ "model.layers.9.self_attn_text.k_proj",
258
+ "visual.blocks.15.attn.proj",
259
+ "visual.blocks.6.attn.proj",
260
+ "model.layers.22.self_attn.k_proj",
261
+ "visual.blocks.13.attn.proj",
262
+ "model.layers.0.mlp.gate_proj",
263
+ "model.layers.13.self_attn.v_proj",
264
+ "model.layers.22.self_attn.q_proj",
265
+ "model.layers.19.self_attn_text.k_proj",
266
+ "model.layers.10.self_attn_text.q_proj",
267
+ "model.layers.2.mlp.down_proj",
268
+ "visual.blocks.10.attn.qkv",
269
+ "model.layers.4.mlp.up_proj",
270
+ "visual.blocks.16.attn.qkv",
271
+ "model.layers.13.self_attn_text.o_proj",
272
+ "model.layers.21.self_attn.o_proj",
273
+ "model.layers.13.mlp.up_proj",
274
+ "model.layers.7.self_attn_text.q_proj",
275
+ "visual.blocks.0.attn.proj",
276
+ "visual.blocks.17.mlp.fc1",
277
+ "model.layers.25.self_attn_text.v_proj",
278
+ "model.layers.3.self_attn.o_proj",
279
+ "visual.blocks.30.attn.proj",
280
+ "model.layers.16.self_attn.o_proj",
281
+ "model.layers.23.self_attn.o_proj",
282
+ "model.layers.4.mlp.down_proj",
283
+ "model.layers.17.self_attn_text.v_proj",
284
+ "model.layers.12.self_attn.q_proj",
285
+ "visual.blocks.3.mlp.fc1",
286
+ "visual.blocks.26.attn.proj",
287
+ "model.layers.21.self_attn.q_proj",
288
+ "visual.blocks.27.attn.qkv",
289
+ "model.layers.17.mlp.gate_proj",
290
+ "model.layers.23.mlp.down_proj",
291
+ "visual.blocks.18.mlp.fc2",
292
+ "model.layers.2.self_attn.k_proj",
293
+ "model.layers.9.mlp.down_proj",
294
+ "model.layers.6.mlp.gate_proj",
295
+ "visual.blocks.17.mlp.fc2",
296
+ "model.layers.0.self_attn.v_proj",
297
+ "visual.blocks.30.attn.qkv",
298
+ "model.layers.3.self_attn_text.o_proj",
299
+ "visual.blocks.4.attn.qkv",
300
+ "model.layers.10.mlp.up_proj",
301
+ "model.layers.2.self_attn.v_proj",
302
+ "visual.blocks.5.mlp.fc1",
303
+ "model.layers.0.self_attn_text.k_proj",
304
+ "model.layers.25.self_attn_text.k_proj",
305
+ "visual.blocks.19.attn.qkv",
306
+ "model.layers.2.mlp.gate_proj",
307
+ "model.layers.16.self_attn_text.q_proj",
308
+ "visual.blocks.0.mlp.fc1",
309
+ "model.layers.3.mlp.up_proj",
310
+ "visual.blocks.30.mlp.fc1",
311
+ "model.layers.2.mlp.up_proj",
312
+ "visual.blocks.29.attn.qkv",
313
+ "model.layers.27.mlp.gate_proj",
314
+ "model.layers.21.self_attn_text.o_proj",
315
+ "model.layers.21.mlp.up_proj",
316
+ "model.layers.1.self_attn.v_proj",
317
+ "visual.blocks.29.attn.proj",
318
+ "model.layers.8.self_attn_text.q_proj",
319
+ "model.layers.3.self_attn_text.v_proj",
320
+ "model.layers.1.self_attn_text.v_proj",
321
+ "visual.blocks.21.mlp.fc2",
322
+ "model.layers.3.self_attn.v_proj",
323
+ "visual.blocks.4.attn.proj",
324
+ "model.layers.4.self_attn.v_proj",
325
+ "model.layers.7.self_attn_text.v_proj",
326
+ "model.layers.22.self_attn_text.v_proj",
327
+ "model.layers.20.self_attn.v_proj",
328
+ "model.layers.21.self_attn_text.q_proj",
329
+ "model.layers.12.self_attn.o_proj",
330
+ "visual.blocks.27.mlp.fc2",
331
+ "model.layers.18.self_attn_text.k_proj",
332
+ "model.layers.24.self_attn_text.v_proj",
333
+ "model.layers.26.mlp.up_proj",
334
+ "model.layers.8.self_attn_text.o_proj",
335
+ "visual.blocks.11.mlp.fc1",
336
+ "model.layers.1.self_attn_text.q_proj",
337
+ "model.layers.7.self_attn.v_proj",
338
+ "visual.blocks.26.mlp.fc1",
339
+ "model.layers.11.self_attn.v_proj",
340
+ "model.layers.13.self_attn.k_proj",
341
+ "model.layers.10.self_attn.o_proj",
342
+ "model.layers.15.mlp.up_proj",
343
+ "visual.blocks.15.mlp.fc1",
344
+ "model.layers.22.mlp.down_proj",
345
+ "model.layers.24.mlp.up_proj",
346
+ "visual.blocks.15.mlp.fc2",
347
+ "model.layers.10.self_attn_text.o_proj",
348
+ "model.layers.15.self_attn_text.k_proj",
349
+ "visual.blocks.1.attn.qkv",
350
+ "model.layers.11.self_attn_text.o_proj",
351
+ "visual.blocks.10.mlp.fc1",
352
+ "model.layers.17.mlp.down_proj",
353
+ "visual.blocks.24.attn.qkv",
354
+ "model.layers.24.mlp.gate_proj",
355
+ "visual.blocks.7.attn.qkv",
356
+ "model.layers.5.self_attn.k_proj",
357
+ "model.layers.23.self_attn.q_proj",
358
+ "model.layers.0.mlp.up_proj",
359
+ "model.layers.22.self_attn_text.q_proj",
360
+ "visual.blocks.12.mlp.fc2",
361
+ "model.layers.3.mlp.gate_proj",
362
+ "model.layers.18.self_attn_text.v_proj",
363
+ "model.layers.12.self_attn_text.o_proj",
364
+ "model.layers.5.mlp.down_proj",
365
+ "model.layers.10.self_attn_text.k_proj",
366
+ "visual.blocks.24.attn.proj",
367
+ "model.layers.11.self_attn_text.q_proj",
368
+ "model.layers.25.self_attn.v_proj",
369
+ "model.layers.17.mlp.up_proj",
370
+ "visual.blocks.23.mlp.fc2",
371
+ "model.layers.22.self_attn.o_proj",
372
+ "model.layers.14.self_attn_text.o_proj",
373
+ "model.layers.19.mlp.up_proj",
374
+ "model.layers.14.self_attn.k_proj",
375
+ "visual.blocks.31.attn.qkv",
376
+ "model.layers.13.self_attn_text.v_proj",
377
+ "model.layers.16.mlp.down_proj",
378
+ "model.layers.16.self_attn_text.v_proj",
379
+ "model.layers.24.self_attn_text.k_proj",
380
+ "model.layers.26.self_attn_text.q_proj",
381
+ "visual.blocks.16.attn.proj",
382
+ "visual.blocks.22.attn.qkv",
383
+ "model.layers.27.self_attn_text.o_proj",
384
+ "visual.blocks.27.mlp.fc1",
385
+ "visual.blocks.12.attn.proj",
386
+ "visual.blocks.28.attn.proj",
387
+ "model.layers.21.self_attn_text.k_proj",
388
+ "visual.blocks.28.attn.qkv",
389
+ "visual.blocks.21.mlp.fc1",
390
+ "model.layers.27.mlp.up_proj",
391
+ "model.layers.15.self_attn.v_proj",
392
+ "model.layers.24.self_attn.k_proj",
393
+ "model.layers.2.self_attn_text.q_proj",
394
+ "model.layers.15.self_attn.q_proj",
395
+ "visual.blocks.29.mlp.fc2",
396
+ "visual.blocks.13.attn.qkv",
397
+ "visual.blocks.24.mlp.fc1",
398
+ "model.layers.11.self_attn.o_proj",
399
+ "model.layers.2.self_attn_text.o_proj",
400
+ "visual.blocks.7.attn.proj",
401
+ "model.layers.6.self_attn.o_proj",
402
+ "model.layers.9.self_attn_text.q_proj",
403
+ "model.layers.0.self_attn.o_proj",
404
+ "model.layers.9.mlp.gate_proj",
405
+ "visual.blocks.0.attn.qkv",
406
+ "model.layers.2.self_attn_text.v_proj",
407
+ "model.layers.8.mlp.up_proj",
408
+ "visual.blocks.8.attn.proj",
409
+ "visual.blocks.18.attn.proj",
410
+ "model.layers.4.self_attn_text.v_proj",
411
+ "model.layers.17.self_attn.o_proj",
412
+ "visual.blocks.22.attn.proj",
413
+ "model.layers.9.self_attn.o_proj",
414
+ "model.layers.26.self_attn.q_proj",
415
+ "visual.blocks.11.mlp.fc2",
416
+ "model.layers.22.mlp.up_proj",
417
+ "model.layers.18.mlp.up_proj",
418
+ "model.layers.14.self_attn_text.k_proj",
419
+ "visual.blocks.9.mlp.fc2",
420
+ "visual.blocks.11.attn.proj",
421
+ "model.layers.17.self_attn.k_proj",
422
+ "model.layers.8.self_attn.k_proj",
423
+ "model.layers.12.self_attn_text.v_proj",
424
+ "model.layers.26.mlp.down_proj",
425
+ "model.layers.14.self_attn.v_proj",
426
+ "model.layers.22.self_attn_text.o_proj",
427
+ "model.layers.0.self_attn_text.v_proj",
428
+ "model.layers.7.mlp.gate_proj",
429
+ "model.layers.22.self_attn.v_proj",
430
+ "model.layers.24.mlp.down_proj",
431
+ "model.layers.20.self_attn_text.q_proj",
432
+ "model.layers.2.self_attn.o_proj",
433
+ "model.layers.11.self_attn_text.k_proj",
434
+ "model.layers.24.self_attn.q_proj",
435
+ "model.layers.18.self_attn_text.q_proj",
436
+ "model.layers.6.self_attn_text.v_proj",
437
+ "model.layers.0.self_attn.q_proj",
438
+ "model.layers.25.self_attn.q_proj",
439
+ "model.layers.19.self_attn_text.q_proj",
440
+ "visual.blocks.20.mlp.fc2",
441
+ "model.layers.13.self_attn_text.k_proj",
442
+ "model.layers.25.mlp.up_proj",
443
+ "model.layers.20.self_attn_text.v_proj",
444
+ "visual.blocks.8.attn.qkv",
445
+ "visual.blocks.16.mlp.fc1",
446
+ "model.layers.25.self_attn.k_proj",
447
+ "model.layers.22.self_attn_text.k_proj",
448
+ "model.layers.16.self_attn.k_proj",
449
+ "model.layers.24.self_attn.o_proj",
450
+ "model.layers.15.self_attn.k_proj",
451
+ "visual.blocks.1.mlp.fc2",
452
+ "model.layers.6.self_attn.q_proj",
453
+ "model.layers.15.mlp.down_proj",
454
+ "visual.blocks.2.attn.qkv",
455
+ "model.layers.14.self_attn.q_proj",
456
+ "model.layers.4.self_attn.q_proj",
457
+ "visual.blocks.19.mlp.fc2",
458
+ "model.layers.7.self_attn.k_proj"
459
+ ],
460
+ "task_type": "CAUSAL_LM",
461
+ "use_dora": false,
462
+ "use_rslora": false
463
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d448e42aa2230d31621b33f5ddf10de783f06ca70e9b34e23d996b4d244955bb
3
+ size 133350944
checkpoint-1000/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-1000/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
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35293326f76b61bf8e57bcdc349c1db4e135861ccbdfc311558a5d388c64ed9f
3
+ size 267205066
checkpoint-1000/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-1000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9281be04f2316562db36bd289b226e07237cabe0e64c821e5b8cfedcb5f17669
3
+ size 14512
checkpoint-1000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658f78ca761388a441a3eaf439ede5c9b4dc1f731762e906f81abe29d7755ff1
3
+ size 14512
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb47022c4ef6f7ab1976ffb75cb22e35906b122b7a825388edd1a2193daa457
3
+ size 988
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537ce0ef560212676d0f3429491464ff9ae6f29d92c07b4446b30e769d7c02f4
3
+ size 1064
checkpoint-1000/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
+ }
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "max_length": null,
139
+ "model_max_length": 32768,
140
+ "pad_to_multiple_of": null,
141
+ "pad_token": "<|endoftext|>",
142
+ "pad_token_type_id": 0,
143
+ "padding_side": "right",
144
+ "processor_class": "Qwen2VLProcessor",
145
+ "split_special_tokens": false,
146
+ "tokenizer_class": "Qwen2Tokenizer",
147
+ "unk_token": null
148
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 15.88,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 155.76007080078125,
14
+ "learning_rate": 9.032258064516129e-07,
15
+ "loss": 12.094,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 37.119384765625,
21
+ "learning_rate": 2.1935483870967745e-06,
22
+ "loss": 7.0819,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.48,
27
+ "grad_norm": 14.752822875976562,
28
+ "learning_rate": 3.4838709677419357e-06,
29
+ "loss": 4.4657,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.64,
34
+ "grad_norm": 11.597710609436035,
35
+ "learning_rate": 4.774193548387097e-06,
36
+ "loss": 3.5378,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.8,
41
+ "grad_norm": 15.393077850341797,
42
+ "learning_rate": 6.064516129032259e-06,
43
+ "loss": 2.8862,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.96,
48
+ "grad_norm": 23.84307861328125,
49
+ "learning_rate": 7.35483870967742e-06,
50
+ "loss": 2.6138,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.112,
55
+ "grad_norm": 13.163668632507324,
56
+ "learning_rate": 8.64516129032258e-06,
57
+ "loss": 2.3109,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.272,
62
+ "grad_norm": 12.168913841247559,
63
+ "learning_rate": 9.935483870967742e-06,
64
+ "loss": 2.2949,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.432,
69
+ "grad_norm": 10.725199699401855,
70
+ "learning_rate": 1.1225806451612904e-05,
71
+ "loss": 2.3399,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.592,
76
+ "grad_norm": 8.531355857849121,
77
+ "learning_rate": 1.2516129032258067e-05,
78
+ "loss": 2.217,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.752,
83
+ "grad_norm": 6.670936584472656,
84
+ "learning_rate": 1.3806451612903227e-05,
85
+ "loss": 2.1938,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.912,
90
+ "grad_norm": 5.666457653045654,
91
+ "learning_rate": 1.5096774193548389e-05,
92
+ "loss": 2.0994,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 2.064,
97
+ "grad_norm": 7.0824384689331055,
98
+ "learning_rate": 1.638709677419355e-05,
99
+ "loss": 2.0094,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 2.224,
104
+ "grad_norm": 5.3269195556640625,
105
+ "learning_rate": 1.7677419354838713e-05,
106
+ "loss": 1.8313,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.384,
111
+ "grad_norm": 3.4799787998199463,
112
+ "learning_rate": 1.896774193548387e-05,
113
+ "loss": 1.8772,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.544,
118
+ "grad_norm": 4.512059211730957,
119
+ "learning_rate": 1.9999898566691428e-05,
120
+ "loss": 1.7948,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.7039999999999997,
125
+ "grad_norm": 9.884415626525879,
126
+ "learning_rate": 1.9996348616949673e-05,
127
+ "loss": 1.7994,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.864,
132
+ "grad_norm": 3.1838889122009277,
133
+ "learning_rate": 1.998772905933476e-05,
134
+ "loss": 1.8654,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 3.016,
139
+ "grad_norm": 3.452301263809204,
140
+ "learning_rate": 1.9974044265220564e-05,
141
+ "loss": 1.6745,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 3.176,
146
+ "grad_norm": 3.3805224895477295,
147
+ "learning_rate": 1.995530117479521e-05,
148
+ "loss": 1.5509,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 3.336,
153
+ "grad_norm": 6.541603088378906,
154
+ "learning_rate": 1.993150929354139e-05,
155
+ "loss": 1.4749,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 3.496,
160
+ "grad_norm": 2.95489764213562,
161
+ "learning_rate": 1.9902680687415704e-05,
162
+ "loss": 1.4165,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 3.656,
167
+ "grad_norm": 3.144228458404541,
168
+ "learning_rate": 1.9868829976729444e-05,
169
+ "loss": 1.3226,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 3.816,
174
+ "grad_norm": 3.747593641281128,
175
+ "learning_rate": 1.982997432873397e-05,
176
+ "loss": 1.5257,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.976,
181
+ "grad_norm": 2.2221176624298096,
182
+ "learning_rate": 1.978613344891441e-05,
183
+ "loss": 1.4218,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 4.128,
188
+ "grad_norm": 2.854719877243042,
189
+ "learning_rate": 1.9737329570996098e-05,
190
+ "loss": 1.2454,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 4.288,
195
+ "grad_norm": 3.9374194145202637,
196
+ "learning_rate": 1.968358744566884e-05,
197
+ "loss": 1.2503,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 4.448,
202
+ "grad_norm": 4.536250591278076,
203
+ "learning_rate": 1.9624934328034673e-05,
204
+ "loss": 1.2983,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 4.608,
209
+ "grad_norm": 4.311966419219971,
210
+ "learning_rate": 1.9561399963785586e-05,
211
+ "loss": 1.2944,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 4.768,
216
+ "grad_norm": 4.188143253326416,
217
+ "learning_rate": 1.9493016574118103e-05,
218
+ "loss": 1.2997,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 4.928,
223
+ "grad_norm": 5.04379415512085,
224
+ "learning_rate": 1.9419818839392408e-05,
225
+ "loss": 1.2976,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 5.08,
230
+ "grad_norm": 4.528952598571777,
231
+ "learning_rate": 1.9341843881544372e-05,
232
+ "loss": 1.1579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 5.24,
237
+ "grad_norm": 4.810428142547607,
238
+ "learning_rate": 1.9259131245259293e-05,
239
+ "loss": 1.13,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 5.4,
244
+ "grad_norm": 3.7566370964050293,
245
+ "learning_rate": 1.917172287791698e-05,
246
+ "loss": 1.1387,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 5.5600000000000005,
251
+ "grad_norm": 3.8142237663269043,
252
+ "learning_rate": 1.9079663108318304e-05,
253
+ "loss": 1.1176,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 5.72,
258
+ "grad_norm": 4.0017619132995605,
259
+ "learning_rate": 1.8982998624204016e-05,
260
+ "loss": 1.1042,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 5.88,
265
+ "grad_norm": 3.9953103065490723,
266
+ "learning_rate": 1.8881778448577274e-05,
267
+ "loss": 1.1386,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 6.032,
272
+ "grad_norm": 3.269265651702881,
273
+ "learning_rate": 1.877605391484179e-05,
274
+ "loss": 0.9651,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 6.192,
279
+ "grad_norm": 5.4509172439575195,
280
+ "learning_rate": 1.8665878640768332e-05,
281
+ "loss": 0.9487,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 6.352,
286
+ "grad_norm": 3.8790087699890137,
287
+ "learning_rate": 1.855130850130267e-05,
288
+ "loss": 0.9193,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 6.5120000000000005,
293
+ "grad_norm": 5.1756110191345215,
294
+ "learning_rate": 1.8432401600228823e-05,
295
+ "loss": 0.9112,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 6.672,
300
+ "grad_norm": 4.771461009979248,
301
+ "learning_rate": 1.8309218240701973e-05,
302
+ "loss": 0.9371,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 6.832,
307
+ "grad_norm": 4.88088846206665,
308
+ "learning_rate": 1.818182089466595e-05,
309
+ "loss": 1.0264,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 6.992,
314
+ "grad_norm": 4.158401012420654,
315
+ "learning_rate": 1.8050274171170835e-05,
316
+ "loss": 0.9534,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 7.144,
321
+ "grad_norm": 5.25468635559082,
322
+ "learning_rate": 1.791464478360676e-05,
323
+ "loss": 0.7345,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 7.304,
328
+ "grad_norm": 4.713033676147461,
329
+ "learning_rate": 1.7775001515870466e-05,
330
+ "loss": 0.8399,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 7.464,
335
+ "grad_norm": 5.714450359344482,
336
+ "learning_rate": 1.7631415187481818e-05,
337
+ "loss": 0.7525,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 7.624,
342
+ "grad_norm": 6.085780143737793,
343
+ "learning_rate": 1.7483958617668e-05,
344
+ "loss": 0.7276,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 7.784,
349
+ "grad_norm": 4.569671630859375,
350
+ "learning_rate": 1.733270658843351e-05,
351
+ "loss": 0.8071,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 7.944,
356
+ "grad_norm": 6.115426540374756,
357
+ "learning_rate": 1.717773580663479e-05,
358
+ "loss": 0.7683,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 8.096,
363
+ "grad_norm": 4.305016040802002,
364
+ "learning_rate": 1.7019124865078625e-05,
365
+ "loss": 0.6376,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 8.256,
370
+ "grad_norm": 6.470266342163086,
371
+ "learning_rate": 1.6856954202664158e-05,
372
+ "loss": 0.6286,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 8.416,
377
+ "grad_norm": 6.055320739746094,
378
+ "learning_rate": 1.6691306063588583e-05,
379
+ "loss": 0.6196,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 8.576,
384
+ "grad_norm": 6.73253870010376,
385
+ "learning_rate": 1.652226445563737e-05,
386
+ "loss": 0.564,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 8.736,
391
+ "grad_norm": 5.043179512023926,
392
+ "learning_rate": 1.634991510758003e-05,
393
+ "loss": 0.6122,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 8.896,
398
+ "grad_norm": 6.78087854385376,
399
+ "learning_rate": 1.617434542569313e-05,
400
+ "loss": 0.6173,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 9.048,
405
+ "grad_norm": 6.2355146408081055,
406
+ "learning_rate": 1.5995644449432538e-05,
407
+ "loss": 0.5342,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 9.208,
412
+ "grad_norm": 5.987257480621338,
413
+ "learning_rate": 1.5813902806277445e-05,
414
+ "loss": 0.4269,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 9.368,
419
+ "grad_norm": 5.455114364624023,
420
+ "learning_rate": 1.562921266576898e-05,
421
+ "loss": 0.4548,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 9.528,
426
+ "grad_norm": 5.296268463134766,
427
+ "learning_rate": 1.5441667692766805e-05,
428
+ "loss": 0.4038,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 9.688,
433
+ "grad_norm": 5.551358699798584,
434
+ "learning_rate": 1.5251362999947386e-05,
435
+ "loss": 0.4015,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 9.848,
440
+ "grad_norm": 4.464796543121338,
441
+ "learning_rate": 1.5058395099567935e-05,
442
+ "loss": 0.4353,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 10.0,
447
+ "grad_norm": 3.268158197402954,
448
+ "learning_rate": 1.4862861854520652e-05,
449
+ "loss": 0.3927,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 10.16,
454
+ "grad_norm": 8.046059608459473,
455
+ "learning_rate": 1.4664862428701925e-05,
456
+ "loss": 0.2612,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 10.32,
461
+ "grad_norm": 4.157690048217773,
462
+ "learning_rate": 1.4464497236721779e-05,
463
+ "loss": 0.2621,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 10.48,
468
+ "grad_norm": 5.3797688484191895,
469
+ "learning_rate": 1.4261867892979e-05,
470
+ "loss": 0.263,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 10.64,
475
+ "grad_norm": 4.068567276000977,
476
+ "learning_rate": 1.4057077160127806e-05,
477
+ "loss": 0.2492,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 10.8,
482
+ "grad_norm": 5.405711650848389,
483
+ "learning_rate": 1.3850228896962178e-05,
484
+ "loss": 0.2523,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 10.96,
489
+ "grad_norm": 4.762354373931885,
490
+ "learning_rate": 1.3641428005744308e-05,
491
+ "loss": 0.2586,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 11.112,
496
+ "grad_norm": 5.127146244049072,
497
+ "learning_rate": 1.3430780379003814e-05,
498
+ "loss": 0.1699,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 11.272,
503
+ "grad_norm": 3.0993189811706543,
504
+ "learning_rate": 1.3218392845834789e-05,
505
+ "loss": 0.1514,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 11.432,
510
+ "grad_norm": 5.754135608673096,
511
+ "learning_rate": 1.300437311771785e-05,
512
+ "loss": 0.1432,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 11.592,
517
+ "grad_norm": 4.12827730178833,
518
+ "learning_rate": 1.2788829733894698e-05,
519
+ "loss": 0.1512,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 11.752,
524
+ "grad_norm": 4.6962175369262695,
525
+ "learning_rate": 1.257187200632289e-05,
526
+ "loss": 0.1534,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 11.912,
531
+ "grad_norm": 6.317523002624512,
532
+ "learning_rate": 1.2353609964238686e-05,
533
+ "loss": 0.1452,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 12.064,
538
+ "grad_norm": 2.793424367904663,
539
+ "learning_rate": 1.213415429835621e-05,
540
+ "loss": 0.1167,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 12.224,
545
+ "grad_norm": 3.816258668899536,
546
+ "learning_rate": 1.1913616304731064e-05,
547
+ "loss": 0.0785,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 12.384,
552
+ "grad_norm": 3.989567518234253,
553
+ "learning_rate": 1.1692107828317014e-05,
554
+ "loss": 0.0857,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 12.544,
559
+ "grad_norm": 4.456111431121826,
560
+ "learning_rate": 1.1469741206244249e-05,
561
+ "loss": 0.0862,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 12.704,
566
+ "grad_norm": 4.539771556854248,
567
+ "learning_rate": 1.1246629210848062e-05,
568
+ "loss": 0.0949,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 12.864,
573
+ "grad_norm": 2.4530129432678223,
574
+ "learning_rate": 1.1022884992476826e-05,
575
+ "loss": 0.0928,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 13.016,
580
+ "grad_norm": 2.042999267578125,
581
+ "learning_rate": 1.0821068423364156e-05,
582
+ "loss": 0.0951,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 13.176,
587
+ "grad_norm": 2.9049434661865234,
588
+ "learning_rate": 1.0596435812513276e-05,
589
+ "loss": 0.0483,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 13.336,
594
+ "grad_norm": 2.3502166271209717,
595
+ "learning_rate": 1.037150072164626e-05,
596
+ "loss": 0.0559,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 13.496,
601
+ "grad_norm": 2.2428765296936035,
602
+ "learning_rate": 1.0146377225686996e-05,
603
+ "loss": 0.0801,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 13.656,
608
+ "grad_norm": 5.673745155334473,
609
+ "learning_rate": 9.921179495108249e-06,
610
+ "loss": 0.0683,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 13.816,
615
+ "grad_norm": 3.9386937618255615,
616
+ "learning_rate": 9.696021738030575e-06,
617
+ "loss": 0.0616,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 13.975999999999999,
622
+ "grad_norm": 4.362432479858398,
623
+ "learning_rate": 9.471018142302127e-06,
624
+ "loss": 0.058,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 14.128,
629
+ "grad_norm": 2.225241184234619,
630
+ "learning_rate": 9.24628281758876e-06,
631
+ "loss": 0.0356,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 14.288,
636
+ "grad_norm": 4.0786356925964355,
637
+ "learning_rate": 9.021929737503757e-06,
638
+ "loss": 0.0458,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 14.448,
643
+ "grad_norm": 2.464179277420044,
644
+ "learning_rate": 8.79807268180658e-06,
645
+ "loss": 0.0531,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 14.608,
650
+ "grad_norm": 2.679661273956299,
651
+ "learning_rate": 8.574825178699935e-06,
652
+ "loss": 0.0359,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 14.768,
657
+ "grad_norm": 2.0911498069763184,
658
+ "learning_rate": 8.352300447254372e-06,
659
+ "loss": 0.0362,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 14.928,
664
+ "grad_norm": 2.3030571937561035,
665
+ "learning_rate": 8.130611339989731e-06,
666
+ "loss": 0.0292,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 15.08,
671
+ "grad_norm": 1.6733816862106323,
672
+ "learning_rate": 7.909870285642403e-06,
673
+ "loss": 0.0241,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 15.24,
678
+ "grad_norm": 1.4519929885864258,
679
+ "learning_rate": 7.690189232147566e-06,
680
+ "loss": 0.0264,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 15.4,
685
+ "grad_norm": 1.980666995048523,
686
+ "learning_rate": 7.4716795898652615e-06,
687
+ "loss": 0.0231,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 15.56,
692
+ "grad_norm": 2.6794183254241943,
693
+ "learning_rate": 7.2544521750790345e-06,
694
+ "loss": 0.0243,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 15.72,
699
+ "grad_norm": 1.8193122148513794,
700
+ "learning_rate": 7.038617153795948e-06,
701
+ "loss": 0.0226,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 15.88,
706
+ "grad_norm": 2.1489455699920654,
707
+ "learning_rate": 6.82428398587631e-06,
708
+ "loss": 0.0321,
709
+ "step": 1000
710
+ }
711
+ ],
712
+ "logging_steps": 10,
713
+ "max_steps": 1550,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 25,
716
+ "save_steps": 1000,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": false
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 8.544789130431693e+16,
730
+ "train_batch_size": 2,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc45890bd2d24eb38ee6085d083cd1874d1991cf87176f31b08f0cafc9576e6c
3
+ size 5688
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1550/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: saim1212/penguin2
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-1550/adapter_config.json ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "saim1212/penguin2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "model.layers.26.self_attn.o_proj",
24
+ "model.layers.19.self_attn.o_proj",
25
+ "visual.blocks.22.mlp.fc1",
26
+ "model.layers.1.self_attn.o_proj",
27
+ "model.layers.9.mlp.up_proj",
28
+ "model.layers.23.self_attn_text.q_proj",
29
+ "model.layers.24.self_attn_text.o_proj",
30
+ "model.layers.15.self_attn_text.o_proj",
31
+ "model.layers.27.self_attn.v_proj",
32
+ "model.layers.8.self_attn_text.k_proj",
33
+ "visual.blocks.10.attn.proj",
34
+ "visual.blocks.28.mlp.fc2",
35
+ "model.layers.3.self_attn_text.k_proj",
36
+ "model.layers.12.self_attn.v_proj",
37
+ "model.layers.18.self_attn_text.o_proj",
38
+ "visual.blocks.5.mlp.fc2",
39
+ "model.layers.13.self_attn.q_proj",
40
+ "visual.blocks.7.mlp.fc1",
41
+ "model.layers.27.mlp.down_proj",
42
+ "visual.blocks.1.mlp.fc1",
43
+ "model.layers.12.mlp.up_proj",
44
+ "model.layers.5.self_attn.o_proj",
45
+ "model.layers.15.self_attn_text.q_proj",
46
+ "model.layers.2.self_attn_text.k_proj",
47
+ "model.layers.3.self_attn_text.q_proj",
48
+ "model.layers.12.mlp.down_proj",
49
+ "model.layers.14.self_attn_text.q_proj",
50
+ "model.layers.19.self_attn_text.o_proj",
51
+ "visual.blocks.23.attn.proj",
52
+ "model.layers.20.self_attn.o_proj",
53
+ "model.layers.5.self_attn_text.k_proj",
54
+ "model.layers.26.mlp.gate_proj",
55
+ "model.layers.8.self_attn.q_proj",
56
+ "model.layers.20.mlp.gate_proj",
57
+ "model.layers.16.self_attn_text.k_proj",
58
+ "model.layers.20.self_attn.k_proj",
59
+ "visual.blocks.9.attn.qkv",
60
+ "model.layers.4.self_attn_text.k_proj",
61
+ "model.layers.4.mlp.gate_proj",
62
+ "model.layers.6.self_attn.v_proj",
63
+ "model.layers.1.self_attn_text.o_proj",
64
+ "model.layers.16.mlp.up_proj",
65
+ "visual.blocks.16.mlp.fc2",
66
+ "model.layers.10.self_attn.v_proj",
67
+ "model.layers.17.self_attn_text.o_proj",
68
+ "model.layers.17.self_attn.v_proj",
69
+ "visual.blocks.9.mlp.fc1",
70
+ "model.layers.25.mlp.gate_proj",
71
+ "model.layers.25.self_attn_text.q_proj",
72
+ "model.layers.9.self_attn.k_proj",
73
+ "model.layers.18.self_attn.q_proj",
74
+ "visual.blocks.9.attn.proj",
75
+ "visual.blocks.14.mlp.fc1",
76
+ "model.layers.13.self_attn.o_proj",
77
+ "model.layers.24.self_attn.v_proj",
78
+ "model.layers.11.mlp.down_proj",
79
+ "model.layers.27.self_attn_text.v_proj",
80
+ "model.layers.16.self_attn_text.o_proj",
81
+ "model.layers.25.mlp.down_proj",
82
+ "visual.blocks.4.mlp.fc2",
83
+ "model.layers.27.self_attn.q_proj",
84
+ "visual.blocks.5.attn.proj",
85
+ "model.layers.19.mlp.gate_proj",
86
+ "model.layers.14.self_attn.o_proj",
87
+ "model.layers.19.self_attn.v_proj",
88
+ "model.layers.13.mlp.gate_proj",
89
+ "model.layers.18.self_attn.o_proj",
90
+ "model.layers.18.self_attn.k_proj",
91
+ "model.layers.26.self_attn.k_proj",
92
+ "model.layers.9.self_attn_text.o_proj",
93
+ "model.layers.26.self_attn.v_proj",
94
+ "model.layers.27.self_attn.k_proj",
95
+ "model.layers.25.self_attn.o_proj",
96
+ "visual.blocks.20.attn.proj",
97
+ "visual.blocks.26.attn.qkv",
98
+ "model.layers.23.self_attn_text.v_proj",
99
+ "visual.blocks.14.attn.qkv",
100
+ "model.layers.19.self_attn.k_proj",
101
+ "model.layers.13.self_attn_text.q_proj",
102
+ "model.layers.13.mlp.down_proj",
103
+ "model.layers.21.self_attn.k_proj",
104
+ "model.layers.0.self_attn_text.o_proj",
105
+ "model.layers.6.self_attn.k_proj",
106
+ "visual.blocks.31.attn.proj",
107
+ "model.layers.16.self_attn.v_proj",
108
+ "model.layers.20.mlp.up_proj",
109
+ "visual.blocks.3.mlp.fc2",
110
+ "model.layers.3.self_attn.k_proj",
111
+ "visual.blocks.12.attn.qkv",
112
+ "model.layers.10.self_attn.k_proj",
113
+ "model.layers.12.self_attn_text.k_proj",
114
+ "visual.blocks.22.mlp.fc2",
115
+ "model.layers.11.self_attn.q_proj",
116
+ "visual.blocks.19.mlp.fc1",
117
+ "visual.blocks.2.mlp.fc1",
118
+ "model.layers.26.self_attn_text.k_proj",
119
+ "model.layers.5.self_attn.q_proj",
120
+ "model.layers.7.self_attn.q_proj",
121
+ "visual.blocks.27.attn.proj",
122
+ "model.layers.8.self_attn_text.v_proj",
123
+ "model.layers.12.mlp.gate_proj",
124
+ "model.layers.27.self_attn_text.q_proj",
125
+ "visual.blocks.1.attn.proj",
126
+ "model.layers.4.self_attn_text.o_proj",
127
+ "visual.blocks.6.mlp.fc2",
128
+ "model.layers.26.self_attn_text.v_proj",
129
+ "visual.blocks.6.mlp.fc1",
130
+ "visual.blocks.31.mlp.fc1",
131
+ "model.layers.8.mlp.gate_proj",
132
+ "visual.blocks.18.mlp.fc1",
133
+ "visual.blocks.14.attn.proj",
134
+ "model.layers.15.self_attn.o_proj",
135
+ "model.layers.16.self_attn.q_proj",
136
+ "visual.blocks.7.mlp.fc2",
137
+ "model.layers.11.self_attn.k_proj",
138
+ "model.layers.7.mlp.up_proj",
139
+ "model.layers.10.self_attn_text.v_proj",
140
+ "model.layers.23.self_attn.k_proj",
141
+ "visual.blocks.11.attn.qkv",
142
+ "visual.blocks.5.attn.qkv",
143
+ "model.layers.15.self_attn_text.v_proj",
144
+ "visual.blocks.21.attn.proj",
145
+ "model.layers.10.mlp.gate_proj",
146
+ "model.layers.5.self_attn.v_proj",
147
+ "model.layers.6.mlp.down_proj",
148
+ "model.layers.9.self_attn_text.v_proj",
149
+ "model.layers.4.self_attn_text.q_proj",
150
+ "model.layers.21.self_attn.v_proj",
151
+ "model.layers.8.mlp.down_proj",
152
+ "visual.blocks.8.mlp.fc2",
153
+ "model.layers.23.self_attn_text.o_proj",
154
+ "model.layers.1.self_attn.q_proj",
155
+ "model.layers.20.self_attn_text.k_proj",
156
+ "model.layers.8.self_attn.o_proj",
157
+ "model.layers.20.self_attn_text.o_proj",
158
+ "model.layers.6.mlp.up_proj",
159
+ "model.layers.1.mlp.down_proj",
160
+ "model.layers.18.mlp.down_proj",
161
+ "model.layers.18.mlp.gate_proj",
162
+ "model.layers.11.mlp.up_proj",
163
+ "visual.blocks.2.attn.proj",
164
+ "model.layers.0.mlp.down_proj",
165
+ "visual.blocks.0.mlp.fc2",
166
+ "visual.blocks.25.attn.proj",
167
+ "model.layers.0.self_attn.k_proj",
168
+ "model.layers.27.self_attn_text.k_proj",
169
+ "visual.blocks.12.mlp.fc1",
170
+ "model.layers.9.self_attn.q_proj",
171
+ "visual.blocks.17.attn.qkv",
172
+ "model.layers.17.self_attn_text.q_proj",
173
+ "model.layers.15.mlp.gate_proj",
174
+ "visual.blocks.21.attn.qkv",
175
+ "model.layers.16.mlp.gate_proj",
176
+ "model.layers.19.self_attn_text.v_proj",
177
+ "model.layers.24.self_attn_text.q_proj",
178
+ "visual.blocks.8.mlp.fc1",
179
+ "visual.blocks.30.mlp.fc2",
180
+ "model.layers.10.self_attn.q_proj",
181
+ "model.layers.14.mlp.gate_proj",
182
+ "model.layers.5.self_attn_text.q_proj",
183
+ "visual.blocks.26.mlp.fc2",
184
+ "model.layers.1.self_attn_text.k_proj",
185
+ "visual.blocks.29.mlp.fc1",
186
+ "model.layers.18.self_attn.v_proj",
187
+ "model.layers.23.mlp.gate_proj",
188
+ "visual.blocks.13.mlp.fc1",
189
+ "model.layers.5.self_attn_text.o_proj",
190
+ "model.layers.14.mlp.up_proj",
191
+ "visual.blocks.6.attn.qkv",
192
+ "model.layers.23.mlp.up_proj",
193
+ "model.layers.14.self_attn_text.v_proj",
194
+ "visual.blocks.4.mlp.fc1",
195
+ "visual.blocks.20.attn.qkv",
196
+ "model.layers.6.self_attn_text.q_proj",
197
+ "visual.blocks.25.attn.qkv",
198
+ "visual.blocks.15.attn.qkv",
199
+ "model.layers.1.self_attn.k_proj",
200
+ "model.layers.19.self_attn.q_proj",
201
+ "model.layers.4.self_attn.o_proj",
202
+ "model.layers.8.self_attn.v_proj",
203
+ "visual.blocks.23.attn.qkv",
204
+ "model.layers.3.self_attn.q_proj",
205
+ "model.layers.5.mlp.gate_proj",
206
+ "model.layers.1.mlp.up_proj",
207
+ "model.layers.11.mlp.gate_proj",
208
+ "visual.blocks.24.mlp.fc2",
209
+ "model.layers.1.mlp.gate_proj",
210
+ "visual.blocks.20.mlp.fc1",
211
+ "visual.blocks.13.mlp.fc2",
212
+ "visual.blocks.14.mlp.fc2",
213
+ "visual.blocks.3.attn.qkv",
214
+ "model.layers.12.self_attn_text.q_proj",
215
+ "model.layers.25.self_attn_text.o_proj",
216
+ "visual.blocks.19.attn.proj",
217
+ "visual.blocks.23.mlp.fc1",
218
+ "model.layers.14.mlp.down_proj",
219
+ "visual.blocks.25.mlp.fc2",
220
+ "model.layers.0.self_attn_text.q_proj",
221
+ "model.layers.23.self_attn_text.k_proj",
222
+ "model.layers.12.self_attn.k_proj",
223
+ "model.layers.4.self_attn.k_proj",
224
+ "visual.blocks.28.mlp.fc1",
225
+ "model.layers.21.self_attn_text.v_proj",
226
+ "model.layers.10.mlp.down_proj",
227
+ "visual.blocks.18.attn.qkv",
228
+ "model.layers.5.mlp.up_proj",
229
+ "model.layers.23.self_attn.v_proj",
230
+ "visual.blocks.31.mlp.fc2",
231
+ "model.layers.3.mlp.down_proj",
232
+ "visual.blocks.2.mlp.fc2",
233
+ "visual.blocks.10.mlp.fc2",
234
+ "model.layers.27.self_attn.o_proj",
235
+ "model.layers.11.self_attn_text.v_proj",
236
+ "model.layers.17.self_attn_text.k_proj",
237
+ "visual.blocks.25.mlp.fc1",
238
+ "visual.blocks.3.attn.proj",
239
+ "model.layers.2.self_attn.q_proj",
240
+ "model.layers.26.self_attn_text.o_proj",
241
+ "model.layers.9.self_attn.v_proj",
242
+ "model.layers.7.self_attn_text.o_proj",
243
+ "model.layers.20.self_attn.q_proj",
244
+ "model.layers.21.mlp.down_proj",
245
+ "model.layers.17.self_attn.q_proj",
246
+ "visual.blocks.17.attn.proj",
247
+ "model.layers.7.mlp.down_proj",
248
+ "model.layers.21.mlp.gate_proj",
249
+ "model.layers.20.mlp.down_proj",
250
+ "model.layers.7.self_attn.o_proj",
251
+ "model.layers.6.self_attn_text.o_proj",
252
+ "model.layers.5.self_attn_text.v_proj",
253
+ "model.layers.22.mlp.gate_proj",
254
+ "model.layers.7.self_attn_text.k_proj",
255
+ "model.layers.19.mlp.down_proj",
256
+ "model.layers.6.self_attn_text.k_proj",
257
+ "model.layers.9.self_attn_text.k_proj",
258
+ "visual.blocks.15.attn.proj",
259
+ "visual.blocks.6.attn.proj",
260
+ "model.layers.22.self_attn.k_proj",
261
+ "visual.blocks.13.attn.proj",
262
+ "model.layers.0.mlp.gate_proj",
263
+ "model.layers.13.self_attn.v_proj",
264
+ "model.layers.22.self_attn.q_proj",
265
+ "model.layers.19.self_attn_text.k_proj",
266
+ "model.layers.10.self_attn_text.q_proj",
267
+ "model.layers.2.mlp.down_proj",
268
+ "visual.blocks.10.attn.qkv",
269
+ "model.layers.4.mlp.up_proj",
270
+ "visual.blocks.16.attn.qkv",
271
+ "model.layers.13.self_attn_text.o_proj",
272
+ "model.layers.21.self_attn.o_proj",
273
+ "model.layers.13.mlp.up_proj",
274
+ "model.layers.7.self_attn_text.q_proj",
275
+ "visual.blocks.0.attn.proj",
276
+ "visual.blocks.17.mlp.fc1",
277
+ "model.layers.25.self_attn_text.v_proj",
278
+ "model.layers.3.self_attn.o_proj",
279
+ "visual.blocks.30.attn.proj",
280
+ "model.layers.16.self_attn.o_proj",
281
+ "model.layers.23.self_attn.o_proj",
282
+ "model.layers.4.mlp.down_proj",
283
+ "model.layers.17.self_attn_text.v_proj",
284
+ "model.layers.12.self_attn.q_proj",
285
+ "visual.blocks.3.mlp.fc1",
286
+ "visual.blocks.26.attn.proj",
287
+ "model.layers.21.self_attn.q_proj",
288
+ "visual.blocks.27.attn.qkv",
289
+ "model.layers.17.mlp.gate_proj",
290
+ "model.layers.23.mlp.down_proj",
291
+ "visual.blocks.18.mlp.fc2",
292
+ "model.layers.2.self_attn.k_proj",
293
+ "model.layers.9.mlp.down_proj",
294
+ "model.layers.6.mlp.gate_proj",
295
+ "visual.blocks.17.mlp.fc2",
296
+ "model.layers.0.self_attn.v_proj",
297
+ "visual.blocks.30.attn.qkv",
298
+ "model.layers.3.self_attn_text.o_proj",
299
+ "visual.blocks.4.attn.qkv",
300
+ "model.layers.10.mlp.up_proj",
301
+ "model.layers.2.self_attn.v_proj",
302
+ "visual.blocks.5.mlp.fc1",
303
+ "model.layers.0.self_attn_text.k_proj",
304
+ "model.layers.25.self_attn_text.k_proj",
305
+ "visual.blocks.19.attn.qkv",
306
+ "model.layers.2.mlp.gate_proj",
307
+ "model.layers.16.self_attn_text.q_proj",
308
+ "visual.blocks.0.mlp.fc1",
309
+ "model.layers.3.mlp.up_proj",
310
+ "visual.blocks.30.mlp.fc1",
311
+ "model.layers.2.mlp.up_proj",
312
+ "visual.blocks.29.attn.qkv",
313
+ "model.layers.27.mlp.gate_proj",
314
+ "model.layers.21.self_attn_text.o_proj",
315
+ "model.layers.21.mlp.up_proj",
316
+ "model.layers.1.self_attn.v_proj",
317
+ "visual.blocks.29.attn.proj",
318
+ "model.layers.8.self_attn_text.q_proj",
319
+ "model.layers.3.self_attn_text.v_proj",
320
+ "model.layers.1.self_attn_text.v_proj",
321
+ "visual.blocks.21.mlp.fc2",
322
+ "model.layers.3.self_attn.v_proj",
323
+ "visual.blocks.4.attn.proj",
324
+ "model.layers.4.self_attn.v_proj",
325
+ "model.layers.7.self_attn_text.v_proj",
326
+ "model.layers.22.self_attn_text.v_proj",
327
+ "model.layers.20.self_attn.v_proj",
328
+ "model.layers.21.self_attn_text.q_proj",
329
+ "model.layers.12.self_attn.o_proj",
330
+ "visual.blocks.27.mlp.fc2",
331
+ "model.layers.18.self_attn_text.k_proj",
332
+ "model.layers.24.self_attn_text.v_proj",
333
+ "model.layers.26.mlp.up_proj",
334
+ "model.layers.8.self_attn_text.o_proj",
335
+ "visual.blocks.11.mlp.fc1",
336
+ "model.layers.1.self_attn_text.q_proj",
337
+ "model.layers.7.self_attn.v_proj",
338
+ "visual.blocks.26.mlp.fc1",
339
+ "model.layers.11.self_attn.v_proj",
340
+ "model.layers.13.self_attn.k_proj",
341
+ "model.layers.10.self_attn.o_proj",
342
+ "model.layers.15.mlp.up_proj",
343
+ "visual.blocks.15.mlp.fc1",
344
+ "model.layers.22.mlp.down_proj",
345
+ "model.layers.24.mlp.up_proj",
346
+ "visual.blocks.15.mlp.fc2",
347
+ "model.layers.10.self_attn_text.o_proj",
348
+ "model.layers.15.self_attn_text.k_proj",
349
+ "visual.blocks.1.attn.qkv",
350
+ "model.layers.11.self_attn_text.o_proj",
351
+ "visual.blocks.10.mlp.fc1",
352
+ "model.layers.17.mlp.down_proj",
353
+ "visual.blocks.24.attn.qkv",
354
+ "model.layers.24.mlp.gate_proj",
355
+ "visual.blocks.7.attn.qkv",
356
+ "model.layers.5.self_attn.k_proj",
357
+ "model.layers.23.self_attn.q_proj",
358
+ "model.layers.0.mlp.up_proj",
359
+ "model.layers.22.self_attn_text.q_proj",
360
+ "visual.blocks.12.mlp.fc2",
361
+ "model.layers.3.mlp.gate_proj",
362
+ "model.layers.18.self_attn_text.v_proj",
363
+ "model.layers.12.self_attn_text.o_proj",
364
+ "model.layers.5.mlp.down_proj",
365
+ "model.layers.10.self_attn_text.k_proj",
366
+ "visual.blocks.24.attn.proj",
367
+ "model.layers.11.self_attn_text.q_proj",
368
+ "model.layers.25.self_attn.v_proj",
369
+ "model.layers.17.mlp.up_proj",
370
+ "visual.blocks.23.mlp.fc2",
371
+ "model.layers.22.self_attn.o_proj",
372
+ "model.layers.14.self_attn_text.o_proj",
373
+ "model.layers.19.mlp.up_proj",
374
+ "model.layers.14.self_attn.k_proj",
375
+ "visual.blocks.31.attn.qkv",
376
+ "model.layers.13.self_attn_text.v_proj",
377
+ "model.layers.16.mlp.down_proj",
378
+ "model.layers.16.self_attn_text.v_proj",
379
+ "model.layers.24.self_attn_text.k_proj",
380
+ "model.layers.26.self_attn_text.q_proj",
381
+ "visual.blocks.16.attn.proj",
382
+ "visual.blocks.22.attn.qkv",
383
+ "model.layers.27.self_attn_text.o_proj",
384
+ "visual.blocks.27.mlp.fc1",
385
+ "visual.blocks.12.attn.proj",
386
+ "visual.blocks.28.attn.proj",
387
+ "model.layers.21.self_attn_text.k_proj",
388
+ "visual.blocks.28.attn.qkv",
389
+ "visual.blocks.21.mlp.fc1",
390
+ "model.layers.27.mlp.up_proj",
391
+ "model.layers.15.self_attn.v_proj",
392
+ "model.layers.24.self_attn.k_proj",
393
+ "model.layers.2.self_attn_text.q_proj",
394
+ "model.layers.15.self_attn.q_proj",
395
+ "visual.blocks.29.mlp.fc2",
396
+ "visual.blocks.13.attn.qkv",
397
+ "visual.blocks.24.mlp.fc1",
398
+ "model.layers.11.self_attn.o_proj",
399
+ "model.layers.2.self_attn_text.o_proj",
400
+ "visual.blocks.7.attn.proj",
401
+ "model.layers.6.self_attn.o_proj",
402
+ "model.layers.9.self_attn_text.q_proj",
403
+ "model.layers.0.self_attn.o_proj",
404
+ "model.layers.9.mlp.gate_proj",
405
+ "visual.blocks.0.attn.qkv",
406
+ "model.layers.2.self_attn_text.v_proj",
407
+ "model.layers.8.mlp.up_proj",
408
+ "visual.blocks.8.attn.proj",
409
+ "visual.blocks.18.attn.proj",
410
+ "model.layers.4.self_attn_text.v_proj",
411
+ "model.layers.17.self_attn.o_proj",
412
+ "visual.blocks.22.attn.proj",
413
+ "model.layers.9.self_attn.o_proj",
414
+ "model.layers.26.self_attn.q_proj",
415
+ "visual.blocks.11.mlp.fc2",
416
+ "model.layers.22.mlp.up_proj",
417
+ "model.layers.18.mlp.up_proj",
418
+ "model.layers.14.self_attn_text.k_proj",
419
+ "visual.blocks.9.mlp.fc2",
420
+ "visual.blocks.11.attn.proj",
421
+ "model.layers.17.self_attn.k_proj",
422
+ "model.layers.8.self_attn.k_proj",
423
+ "model.layers.12.self_attn_text.v_proj",
424
+ "model.layers.26.mlp.down_proj",
425
+ "model.layers.14.self_attn.v_proj",
426
+ "model.layers.22.self_attn_text.o_proj",
427
+ "model.layers.0.self_attn_text.v_proj",
428
+ "model.layers.7.mlp.gate_proj",
429
+ "model.layers.22.self_attn.v_proj",
430
+ "model.layers.24.mlp.down_proj",
431
+ "model.layers.20.self_attn_text.q_proj",
432
+ "model.layers.2.self_attn.o_proj",
433
+ "model.layers.11.self_attn_text.k_proj",
434
+ "model.layers.24.self_attn.q_proj",
435
+ "model.layers.18.self_attn_text.q_proj",
436
+ "model.layers.6.self_attn_text.v_proj",
437
+ "model.layers.0.self_attn.q_proj",
438
+ "model.layers.25.self_attn.q_proj",
439
+ "model.layers.19.self_attn_text.q_proj",
440
+ "visual.blocks.20.mlp.fc2",
441
+ "model.layers.13.self_attn_text.k_proj",
442
+ "model.layers.25.mlp.up_proj",
443
+ "model.layers.20.self_attn_text.v_proj",
444
+ "visual.blocks.8.attn.qkv",
445
+ "visual.blocks.16.mlp.fc1",
446
+ "model.layers.25.self_attn.k_proj",
447
+ "model.layers.22.self_attn_text.k_proj",
448
+ "model.layers.16.self_attn.k_proj",
449
+ "model.layers.24.self_attn.o_proj",
450
+ "model.layers.15.self_attn.k_proj",
451
+ "visual.blocks.1.mlp.fc2",
452
+ "model.layers.6.self_attn.q_proj",
453
+ "model.layers.15.mlp.down_proj",
454
+ "visual.blocks.2.attn.qkv",
455
+ "model.layers.14.self_attn.q_proj",
456
+ "model.layers.4.self_attn.q_proj",
457
+ "visual.blocks.19.mlp.fc2",
458
+ "model.layers.7.self_attn.k_proj"
459
+ ],
460
+ "task_type": "CAUSAL_LM",
461
+ "use_dora": false,
462
+ "use_rslora": false
463
+ }
checkpoint-1550/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845f34c1f221b697726779b3fd71e1029e7d68df2e0d70cd0bb291bb74d0558a
3
+ size 133350944
checkpoint-1550/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-1550/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
+ }
checkpoint-1550/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e3c5c599d5aaa75e6dcff11ab64bf776776e62bf32286668cb1e63b02c27a6
3
+ size 267205066
checkpoint-1550/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-1550/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a456c014f4062602da085bb6b03f6bda6f86ab8b2dcf1a268dd903ed52f3fb91
3
+ size 14512
checkpoint-1550/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ea19755c03db3ccc062fd1a38208daf2c7258b6dd1d567b2257f1306869548
3
+ size 14512
checkpoint-1550/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c97d38d3bd4ed40c71b688ea05ca6d304a5bf700ddc5a8af6bedb520bae088a
3
+ size 988
checkpoint-1550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a770130995005184d2e5d60f8a10bfcce2b010542c31499a57165f764fe2b67
3
+ size 1064
checkpoint-1550/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
+ }
checkpoint-1550/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
checkpoint-1550/tokenizer_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "max_length": null,
139
+ "model_max_length": 32768,
140
+ "pad_to_multiple_of": null,
141
+ "pad_token": "<|endoftext|>",
142
+ "pad_token_type_id": 0,
143
+ "padding_side": "right",
144
+ "processor_class": "Qwen2VLProcessor",
145
+ "split_special_tokens": false,
146
+ "tokenizer_class": "Qwen2Tokenizer",
147
+ "unk_token": null
148
+ }
checkpoint-1550/trainer_state.json ADDED
@@ -0,0 +1,1118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 24.608,
5
+ "eval_steps": 500,
6
+ "global_step": 1550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 155.76007080078125,
14
+ "learning_rate": 9.032258064516129e-07,
15
+ "loss": 12.094,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 37.119384765625,
21
+ "learning_rate": 2.1935483870967745e-06,
22
+ "loss": 7.0819,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.48,
27
+ "grad_norm": 14.752822875976562,
28
+ "learning_rate": 3.4838709677419357e-06,
29
+ "loss": 4.4657,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.64,
34
+ "grad_norm": 11.597710609436035,
35
+ "learning_rate": 4.774193548387097e-06,
36
+ "loss": 3.5378,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.8,
41
+ "grad_norm": 15.393077850341797,
42
+ "learning_rate": 6.064516129032259e-06,
43
+ "loss": 2.8862,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.96,
48
+ "grad_norm": 23.84307861328125,
49
+ "learning_rate": 7.35483870967742e-06,
50
+ "loss": 2.6138,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.112,
55
+ "grad_norm": 13.163668632507324,
56
+ "learning_rate": 8.64516129032258e-06,
57
+ "loss": 2.3109,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.272,
62
+ "grad_norm": 12.168913841247559,
63
+ "learning_rate": 9.935483870967742e-06,
64
+ "loss": 2.2949,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.432,
69
+ "grad_norm": 10.725199699401855,
70
+ "learning_rate": 1.1225806451612904e-05,
71
+ "loss": 2.3399,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.592,
76
+ "grad_norm": 8.531355857849121,
77
+ "learning_rate": 1.2516129032258067e-05,
78
+ "loss": 2.217,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.752,
83
+ "grad_norm": 6.670936584472656,
84
+ "learning_rate": 1.3806451612903227e-05,
85
+ "loss": 2.1938,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.912,
90
+ "grad_norm": 5.666457653045654,
91
+ "learning_rate": 1.5096774193548389e-05,
92
+ "loss": 2.0994,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 2.064,
97
+ "grad_norm": 7.0824384689331055,
98
+ "learning_rate": 1.638709677419355e-05,
99
+ "loss": 2.0094,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 2.224,
104
+ "grad_norm": 5.3269195556640625,
105
+ "learning_rate": 1.7677419354838713e-05,
106
+ "loss": 1.8313,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.384,
111
+ "grad_norm": 3.4799787998199463,
112
+ "learning_rate": 1.896774193548387e-05,
113
+ "loss": 1.8772,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.544,
118
+ "grad_norm": 4.512059211730957,
119
+ "learning_rate": 1.9999898566691428e-05,
120
+ "loss": 1.7948,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.7039999999999997,
125
+ "grad_norm": 9.884415626525879,
126
+ "learning_rate": 1.9996348616949673e-05,
127
+ "loss": 1.7994,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.864,
132
+ "grad_norm": 3.1838889122009277,
133
+ "learning_rate": 1.998772905933476e-05,
134
+ "loss": 1.8654,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 3.016,
139
+ "grad_norm": 3.452301263809204,
140
+ "learning_rate": 1.9974044265220564e-05,
141
+ "loss": 1.6745,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 3.176,
146
+ "grad_norm": 3.3805224895477295,
147
+ "learning_rate": 1.995530117479521e-05,
148
+ "loss": 1.5509,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 3.336,
153
+ "grad_norm": 6.541603088378906,
154
+ "learning_rate": 1.993150929354139e-05,
155
+ "loss": 1.4749,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 3.496,
160
+ "grad_norm": 2.95489764213562,
161
+ "learning_rate": 1.9902680687415704e-05,
162
+ "loss": 1.4165,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 3.656,
167
+ "grad_norm": 3.144228458404541,
168
+ "learning_rate": 1.9868829976729444e-05,
169
+ "loss": 1.3226,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 3.816,
174
+ "grad_norm": 3.747593641281128,
175
+ "learning_rate": 1.982997432873397e-05,
176
+ "loss": 1.5257,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.976,
181
+ "grad_norm": 2.2221176624298096,
182
+ "learning_rate": 1.978613344891441e-05,
183
+ "loss": 1.4218,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 4.128,
188
+ "grad_norm": 2.854719877243042,
189
+ "learning_rate": 1.9737329570996098e-05,
190
+ "loss": 1.2454,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 4.288,
195
+ "grad_norm": 3.9374194145202637,
196
+ "learning_rate": 1.968358744566884e-05,
197
+ "loss": 1.2503,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 4.448,
202
+ "grad_norm": 4.536250591278076,
203
+ "learning_rate": 1.9624934328034673e-05,
204
+ "loss": 1.2983,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 4.608,
209
+ "grad_norm": 4.311966419219971,
210
+ "learning_rate": 1.9561399963785586e-05,
211
+ "loss": 1.2944,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 4.768,
216
+ "grad_norm": 4.188143253326416,
217
+ "learning_rate": 1.9493016574118103e-05,
218
+ "loss": 1.2997,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 4.928,
223
+ "grad_norm": 5.04379415512085,
224
+ "learning_rate": 1.9419818839392408e-05,
225
+ "loss": 1.2976,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 5.08,
230
+ "grad_norm": 4.528952598571777,
231
+ "learning_rate": 1.9341843881544372e-05,
232
+ "loss": 1.1579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 5.24,
237
+ "grad_norm": 4.810428142547607,
238
+ "learning_rate": 1.9259131245259293e-05,
239
+ "loss": 1.13,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 5.4,
244
+ "grad_norm": 3.7566370964050293,
245
+ "learning_rate": 1.917172287791698e-05,
246
+ "loss": 1.1387,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 5.5600000000000005,
251
+ "grad_norm": 3.8142237663269043,
252
+ "learning_rate": 1.9079663108318304e-05,
253
+ "loss": 1.1176,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 5.72,
258
+ "grad_norm": 4.0017619132995605,
259
+ "learning_rate": 1.8982998624204016e-05,
260
+ "loss": 1.1042,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 5.88,
265
+ "grad_norm": 3.9953103065490723,
266
+ "learning_rate": 1.8881778448577274e-05,
267
+ "loss": 1.1386,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 6.032,
272
+ "grad_norm": 3.269265651702881,
273
+ "learning_rate": 1.877605391484179e-05,
274
+ "loss": 0.9651,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 6.192,
279
+ "grad_norm": 5.4509172439575195,
280
+ "learning_rate": 1.8665878640768332e-05,
281
+ "loss": 0.9487,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 6.352,
286
+ "grad_norm": 3.8790087699890137,
287
+ "learning_rate": 1.855130850130267e-05,
288
+ "loss": 0.9193,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 6.5120000000000005,
293
+ "grad_norm": 5.1756110191345215,
294
+ "learning_rate": 1.8432401600228823e-05,
295
+ "loss": 0.9112,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 6.672,
300
+ "grad_norm": 4.771461009979248,
301
+ "learning_rate": 1.8309218240701973e-05,
302
+ "loss": 0.9371,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 6.832,
307
+ "grad_norm": 4.88088846206665,
308
+ "learning_rate": 1.818182089466595e-05,
309
+ "loss": 1.0264,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 6.992,
314
+ "grad_norm": 4.158401012420654,
315
+ "learning_rate": 1.8050274171170835e-05,
316
+ "loss": 0.9534,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 7.144,
321
+ "grad_norm": 5.25468635559082,
322
+ "learning_rate": 1.791464478360676e-05,
323
+ "loss": 0.7345,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 7.304,
328
+ "grad_norm": 4.713033676147461,
329
+ "learning_rate": 1.7775001515870466e-05,
330
+ "loss": 0.8399,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 7.464,
335
+ "grad_norm": 5.714450359344482,
336
+ "learning_rate": 1.7631415187481818e-05,
337
+ "loss": 0.7525,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 7.624,
342
+ "grad_norm": 6.085780143737793,
343
+ "learning_rate": 1.7483958617668e-05,
344
+ "loss": 0.7276,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 7.784,
349
+ "grad_norm": 4.569671630859375,
350
+ "learning_rate": 1.733270658843351e-05,
351
+ "loss": 0.8071,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 7.944,
356
+ "grad_norm": 6.115426540374756,
357
+ "learning_rate": 1.717773580663479e-05,
358
+ "loss": 0.7683,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 8.096,
363
+ "grad_norm": 4.305016040802002,
364
+ "learning_rate": 1.7019124865078625e-05,
365
+ "loss": 0.6376,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 8.256,
370
+ "grad_norm": 6.470266342163086,
371
+ "learning_rate": 1.6856954202664158e-05,
372
+ "loss": 0.6286,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 8.416,
377
+ "grad_norm": 6.055320739746094,
378
+ "learning_rate": 1.6691306063588583e-05,
379
+ "loss": 0.6196,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 8.576,
384
+ "grad_norm": 6.73253870010376,
385
+ "learning_rate": 1.652226445563737e-05,
386
+ "loss": 0.564,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 8.736,
391
+ "grad_norm": 5.043179512023926,
392
+ "learning_rate": 1.634991510758003e-05,
393
+ "loss": 0.6122,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 8.896,
398
+ "grad_norm": 6.78087854385376,
399
+ "learning_rate": 1.617434542569313e-05,
400
+ "loss": 0.6173,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 9.048,
405
+ "grad_norm": 6.2355146408081055,
406
+ "learning_rate": 1.5995644449432538e-05,
407
+ "loss": 0.5342,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 9.208,
412
+ "grad_norm": 5.987257480621338,
413
+ "learning_rate": 1.5813902806277445e-05,
414
+ "loss": 0.4269,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 9.368,
419
+ "grad_norm": 5.455114364624023,
420
+ "learning_rate": 1.562921266576898e-05,
421
+ "loss": 0.4548,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 9.528,
426
+ "grad_norm": 5.296268463134766,
427
+ "learning_rate": 1.5441667692766805e-05,
428
+ "loss": 0.4038,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 9.688,
433
+ "grad_norm": 5.551358699798584,
434
+ "learning_rate": 1.5251362999947386e-05,
435
+ "loss": 0.4015,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 9.848,
440
+ "grad_norm": 4.464796543121338,
441
+ "learning_rate": 1.5058395099567935e-05,
442
+ "loss": 0.4353,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 10.0,
447
+ "grad_norm": 3.268158197402954,
448
+ "learning_rate": 1.4862861854520652e-05,
449
+ "loss": 0.3927,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 10.16,
454
+ "grad_norm": 8.046059608459473,
455
+ "learning_rate": 1.4664862428701925e-05,
456
+ "loss": 0.2612,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 10.32,
461
+ "grad_norm": 4.157690048217773,
462
+ "learning_rate": 1.4464497236721779e-05,
463
+ "loss": 0.2621,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 10.48,
468
+ "grad_norm": 5.3797688484191895,
469
+ "learning_rate": 1.4261867892979e-05,
470
+ "loss": 0.263,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 10.64,
475
+ "grad_norm": 4.068567276000977,
476
+ "learning_rate": 1.4057077160127806e-05,
477
+ "loss": 0.2492,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 10.8,
482
+ "grad_norm": 5.405711650848389,
483
+ "learning_rate": 1.3850228896962178e-05,
484
+ "loss": 0.2523,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 10.96,
489
+ "grad_norm": 4.762354373931885,
490
+ "learning_rate": 1.3641428005744308e-05,
491
+ "loss": 0.2586,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 11.112,
496
+ "grad_norm": 5.127146244049072,
497
+ "learning_rate": 1.3430780379003814e-05,
498
+ "loss": 0.1699,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 11.272,
503
+ "grad_norm": 3.0993189811706543,
504
+ "learning_rate": 1.3218392845834789e-05,
505
+ "loss": 0.1514,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 11.432,
510
+ "grad_norm": 5.754135608673096,
511
+ "learning_rate": 1.300437311771785e-05,
512
+ "loss": 0.1432,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 11.592,
517
+ "grad_norm": 4.12827730178833,
518
+ "learning_rate": 1.2788829733894698e-05,
519
+ "loss": 0.1512,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 11.752,
524
+ "grad_norm": 4.6962175369262695,
525
+ "learning_rate": 1.257187200632289e-05,
526
+ "loss": 0.1534,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 11.912,
531
+ "grad_norm": 6.317523002624512,
532
+ "learning_rate": 1.2353609964238686e-05,
533
+ "loss": 0.1452,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 12.064,
538
+ "grad_norm": 2.793424367904663,
539
+ "learning_rate": 1.213415429835621e-05,
540
+ "loss": 0.1167,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 12.224,
545
+ "grad_norm": 3.816258668899536,
546
+ "learning_rate": 1.1913616304731064e-05,
547
+ "loss": 0.0785,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 12.384,
552
+ "grad_norm": 3.989567518234253,
553
+ "learning_rate": 1.1692107828317014e-05,
554
+ "loss": 0.0857,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 12.544,
559
+ "grad_norm": 4.456111431121826,
560
+ "learning_rate": 1.1469741206244249e-05,
561
+ "loss": 0.0862,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 12.704,
566
+ "grad_norm": 4.539771556854248,
567
+ "learning_rate": 1.1246629210848062e-05,
568
+ "loss": 0.0949,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 12.864,
573
+ "grad_norm": 2.4530129432678223,
574
+ "learning_rate": 1.1022884992476826e-05,
575
+ "loss": 0.0928,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 13.016,
580
+ "grad_norm": 2.042999267578125,
581
+ "learning_rate": 1.0821068423364156e-05,
582
+ "loss": 0.0951,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 13.176,
587
+ "grad_norm": 2.9049434661865234,
588
+ "learning_rate": 1.0596435812513276e-05,
589
+ "loss": 0.0483,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 13.336,
594
+ "grad_norm": 2.3502166271209717,
595
+ "learning_rate": 1.037150072164626e-05,
596
+ "loss": 0.0559,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 13.496,
601
+ "grad_norm": 2.2428765296936035,
602
+ "learning_rate": 1.0146377225686996e-05,
603
+ "loss": 0.0801,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 13.656,
608
+ "grad_norm": 5.673745155334473,
609
+ "learning_rate": 9.921179495108249e-06,
610
+ "loss": 0.0683,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 13.816,
615
+ "grad_norm": 3.9386937618255615,
616
+ "learning_rate": 9.696021738030575e-06,
617
+ "loss": 0.0616,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 13.975999999999999,
622
+ "grad_norm": 4.362432479858398,
623
+ "learning_rate": 9.471018142302127e-06,
624
+ "loss": 0.058,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 14.128,
629
+ "grad_norm": 2.225241184234619,
630
+ "learning_rate": 9.24628281758876e-06,
631
+ "loss": 0.0356,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 14.288,
636
+ "grad_norm": 4.0786356925964355,
637
+ "learning_rate": 9.021929737503757e-06,
638
+ "loss": 0.0458,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 14.448,
643
+ "grad_norm": 2.464179277420044,
644
+ "learning_rate": 8.79807268180658e-06,
645
+ "loss": 0.0531,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 14.608,
650
+ "grad_norm": 2.679661273956299,
651
+ "learning_rate": 8.574825178699935e-06,
652
+ "loss": 0.0359,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 14.768,
657
+ "grad_norm": 2.0911498069763184,
658
+ "learning_rate": 8.352300447254372e-06,
659
+ "loss": 0.0362,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 14.928,
664
+ "grad_norm": 2.3030571937561035,
665
+ "learning_rate": 8.130611339989731e-06,
666
+ "loss": 0.0292,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 15.08,
671
+ "grad_norm": 1.6733816862106323,
672
+ "learning_rate": 7.909870285642403e-06,
673
+ "loss": 0.0241,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 15.24,
678
+ "grad_norm": 1.4519929885864258,
679
+ "learning_rate": 7.690189232147566e-06,
680
+ "loss": 0.0264,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 15.4,
685
+ "grad_norm": 1.980666995048523,
686
+ "learning_rate": 7.4716795898652615e-06,
687
+ "loss": 0.0231,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 15.56,
692
+ "grad_norm": 2.6794183254241943,
693
+ "learning_rate": 7.2544521750790345e-06,
694
+ "loss": 0.0243,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 15.72,
699
+ "grad_norm": 1.8193122148513794,
700
+ "learning_rate": 7.038617153795948e-06,
701
+ "loss": 0.0226,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 15.88,
706
+ "grad_norm": 2.1489455699920654,
707
+ "learning_rate": 6.82428398587631e-06,
708
+ "loss": 0.0321,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 16.032,
713
+ "grad_norm": 0.9566267728805542,
714
+ "learning_rate": 6.611561369521546e-06,
715
+ "loss": 0.019,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 16.192,
720
+ "grad_norm": 0.45050784945487976,
721
+ "learning_rate": 6.400557186148371e-06,
722
+ "loss": 0.0101,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 16.352,
727
+ "grad_norm": 3.0079352855682373,
728
+ "learning_rate": 6.191378445677125e-06,
729
+ "loss": 0.0139,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 16.512,
734
+ "grad_norm": 1.0027068853378296,
735
+ "learning_rate": 5.984131232262167e-06,
736
+ "loss": 0.0264,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 16.672,
741
+ "grad_norm": 0.34918779134750366,
742
+ "learning_rate": 5.7789206504916815e-06,
743
+ "loss": 0.0123,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 16.832,
748
+ "grad_norm": 1.0329653024673462,
749
+ "learning_rate": 5.5758507720843425e-06,
750
+ "loss": 0.0115,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 16.992,
755
+ "grad_norm": 1.9161659479141235,
756
+ "learning_rate": 5.375024583109745e-06,
757
+ "loss": 0.0135,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 17.144,
762
+ "grad_norm": 0.42554718255996704,
763
+ "learning_rate": 5.176543931759447e-06,
764
+ "loss": 0.005,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 17.304,
769
+ "grad_norm": 0.7298970818519592,
770
+ "learning_rate": 4.980509476695043e-06,
771
+ "loss": 0.0096,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 17.464,
776
+ "grad_norm": 2.393183946609497,
777
+ "learning_rate": 4.7870206359995815e-06,
778
+ "loss": 0.0148,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 17.624,
783
+ "grad_norm": 0.4778424799442291,
784
+ "learning_rate": 4.596175536758024e-06,
785
+ "loss": 0.0067,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 17.784,
790
+ "grad_norm": 0.22980810701847076,
791
+ "learning_rate": 4.408070965292534e-06,
792
+ "loss": 0.0053,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 17.944,
797
+ "grad_norm": 0.18192055821418762,
798
+ "learning_rate": 4.222802318077664e-06,
799
+ "loss": 0.0079,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 18.096,
804
+ "grad_norm": 0.6733874678611755,
805
+ "learning_rate": 4.040463553360431e-06,
806
+ "loss": 0.0039,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 18.256,
811
+ "grad_norm": 0.17421452701091766,
812
+ "learning_rate": 3.861147143509754e-06,
813
+ "loss": 0.0023,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 18.416,
818
+ "grad_norm": 0.15809208154678345,
819
+ "learning_rate": 3.6849440281194813e-06,
820
+ "loss": 0.006,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 18.576,
825
+ "grad_norm": 0.06922920793294907,
826
+ "learning_rate": 3.5119435678887328e-06,
827
+ "loss": 0.0023,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 18.736,
832
+ "grad_norm": 0.08193696290254593,
833
+ "learning_rate": 3.342233499302985e-06,
834
+ "loss": 0.003,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 18.896,
839
+ "grad_norm": 0.0757126435637474,
840
+ "learning_rate": 3.175899890138858e-06,
841
+ "loss": 0.002,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 19.048,
846
+ "grad_norm": 0.057399798184633255,
847
+ "learning_rate": 3.0130270958152196e-06,
848
+ "loss": 0.0022,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 19.208,
853
+ "grad_norm": 0.068113774061203,
854
+ "learning_rate": 2.8536977166126234e-06,
855
+ "loss": 0.0022,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 19.368,
860
+ "grad_norm": 0.06517008692026138,
861
+ "learning_rate": 2.697992555782969e-06,
862
+ "loss": 0.0016,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 19.528,
867
+ "grad_norm": 0.07533544301986694,
868
+ "learning_rate": 2.545990578570404e-06,
869
+ "loss": 0.0015,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 19.688,
874
+ "grad_norm": 0.08159100264310837,
875
+ "learning_rate": 2.397768872164462e-06,
876
+ "loss": 0.0018,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 19.848,
881
+ "grad_norm": 0.05212102085351944,
882
+ "learning_rate": 2.253402606605577e-06,
883
+ "loss": 0.0014,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 20.0,
888
+ "grad_norm": 0.038643430918455124,
889
+ "learning_rate": 2.1129649966629185e-06,
890
+ "loss": 0.0013,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 20.16,
895
+ "grad_norm": 0.040117453783750534,
896
+ "learning_rate": 1.9765272647038038e-06,
897
+ "loss": 0.0013,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 20.32,
902
+ "grad_norm": 0.03363404422998428,
903
+ "learning_rate": 1.8441586045735737e-06,
904
+ "loss": 0.0011,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 20.48,
909
+ "grad_norm": 0.055696483701467514,
910
+ "learning_rate": 1.7159261465041954e-06,
911
+ "loss": 0.0013,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 20.64,
916
+ "grad_norm": 0.0553043931722641,
917
+ "learning_rate": 1.5918949230694635e-06,
918
+ "loss": 0.0014,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 20.8,
923
+ "grad_norm": 0.049317434430122375,
924
+ "learning_rate": 1.4721278362039626e-06,
925
+ "loss": 0.0011,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 20.96,
930
+ "grad_norm": 0.07064161449670792,
931
+ "learning_rate": 1.356685625302625e-06,
932
+ "loss": 0.0012,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 21.112,
937
+ "grad_norm": 0.0384482778608799,
938
+ "learning_rate": 1.2456268364169853e-06,
939
+ "loss": 0.0011,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 21.272,
944
+ "grad_norm": 0.04504753276705742,
945
+ "learning_rate": 1.1390077925637865e-06,
946
+ "loss": 0.0011,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 21.432,
951
+ "grad_norm": 0.04046454280614853,
952
+ "learning_rate": 1.0368825651609893e-06,
953
+ "loss": 0.001,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 21.592,
958
+ "grad_norm": 0.04408493638038635,
959
+ "learning_rate": 9.393029466056714e-07,
960
+ "loss": 0.0012,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 21.752,
965
+ "grad_norm": 0.03646273910999298,
966
+ "learning_rate": 8.463184240077172e-07,
967
+ "loss": 0.0012,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 21.912,
972
+ "grad_norm": 0.03203440457582474,
973
+ "learning_rate": 7.579761540926434e-07,
974
+ "loss": 0.0011,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 22.064,
979
+ "grad_norm": 0.03588934242725372,
980
+ "learning_rate": 6.743209392862349e-07,
981
+ "loss": 0.001,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 22.224,
986
+ "grad_norm": 0.0342290997505188,
987
+ "learning_rate": 5.953952049931999e-07,
988
+ "loss": 0.0011,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 22.384,
993
+ "grad_norm": 0.036632440984249115,
994
+ "learning_rate": 5.212389780812733e-07,
995
+ "loss": 0.001,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 22.544,
1000
+ "grad_norm": 0.03759520500898361,
1001
+ "learning_rate": 4.518898665817695e-07,
1002
+ "loss": 0.0011,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 22.704,
1007
+ "grad_norm": 0.03835231438279152,
1008
+ "learning_rate": 3.8738304061681107e-07,
1009
+ "loss": 0.0011,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 22.864,
1014
+ "grad_norm": 0.042444001883268356,
1015
+ "learning_rate": 3.2775121456295024e-07,
1016
+ "loss": 0.0011,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 23.016,
1021
+ "grad_norm": 0.033434733748435974,
1022
+ "learning_rate": 2.730246304601991e-07,
1023
+ "loss": 0.001,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 23.176,
1028
+ "grad_norm": 0.03470597416162491,
1029
+ "learning_rate": 2.2323104267490404e-07,
1030
+ "loss": 0.0011,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 23.336,
1035
+ "grad_norm": 0.04532945156097412,
1036
+ "learning_rate": 1.783957038242279e-07,
1037
+ "loss": 0.001,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 23.496,
1042
+ "grad_norm": 0.035716019570827484,
1043
+ "learning_rate": 1.3854135196939345e-07,
1044
+ "loss": 0.001,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 23.656,
1049
+ "grad_norm": 0.03435162454843521,
1050
+ "learning_rate": 1.0368819908415983e-07,
1051
+ "loss": 0.0011,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 23.816,
1056
+ "grad_norm": 0.04788799211382866,
1057
+ "learning_rate": 7.385392080440535e-08,
1058
+ "loss": 0.0011,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 23.976,
1063
+ "grad_norm": 0.037617627531290054,
1064
+ "learning_rate": 4.905364746400021e-08,
1065
+ "loss": 0.0011,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 24.128,
1070
+ "grad_norm": 0.04006591811776161,
1071
+ "learning_rate": 2.929995642151906e-08,
1072
+ "loss": 0.001,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 24.288,
1077
+ "grad_norm": 0.03150051832199097,
1078
+ "learning_rate": 1.4602865681682122e-08,
1079
+ "loss": 0.001,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 24.448,
1084
+ "grad_norm": 0.04720960184931755,
1085
+ "learning_rate": 4.969828814767042e-09,
1086
+ "loss": 0.001,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 24.608,
1091
+ "grad_norm": 0.0407867431640625,
1092
+ "learning_rate": 4.0573117655595684e-10,
1093
+ "loss": 0.001,
1094
+ "step": 1550
1095
+ }
1096
+ ],
1097
+ "logging_steps": 10,
1098
+ "max_steps": 1550,
1099
+ "num_input_tokens_seen": 0,
1100
+ "num_train_epochs": 25,
1101
+ "save_steps": 1000,
1102
+ "stateful_callbacks": {
1103
+ "TrainerControl": {
1104
+ "args": {
1105
+ "should_epoch_stop": false,
1106
+ "should_evaluate": false,
1107
+ "should_log": false,
1108
+ "should_save": true,
1109
+ "should_training_stop": true
1110
+ },
1111
+ "attributes": {}
1112
+ }
1113
+ },
1114
+ "total_flos": 1.324081921088553e+17,
1115
+ "train_batch_size": 2,
1116
+ "trial_name": null,
1117
+ "trial_params": null
1118
+ }
checkpoint-1550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc45890bd2d24eb38ee6085d083cd1874d1991cf87176f31b08f0cafc9576e6c
3
+ size 5688
checkpoint-1550/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
runs/Mar14_21-25-37_36c244e9105b/events.out.tfevents.1741987616.36c244e9105b.153.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80083da1c9fae8677b49dd927b26fa083b186b01c1061ad3e277e9a6cca56c4a
3
+ size 39394
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "max_length": null,
139
+ "model_max_length": 32768,
140
+ "pad_to_multiple_of": null,
141
+ "pad_token": "<|endoftext|>",
142
+ "pad_token_type_id": 0,
143
+ "padding_side": "right",
144
+ "processor_class": "Qwen2VLProcessor",
145
+ "split_special_tokens": false,
146
+ "tokenizer_class": "Qwen2Tokenizer",
147
+ "unk_token": null
148
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 24.608,
3
+ "total_flos": 1.324081921088553e+17,
4
+ "train_loss": 0.672794044127147,
5
+ "train_runtime": 33908.1665,
6
+ "train_samples_per_second": 0.369,
7
+ "train_steps_per_second": 0.046
8
+ }