Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +41 -0
- adapter_config.json +318 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +151 -0
- config.json +113 -0
- preprocessor_config.json +26 -0
- processor_config.json +60 -0
- special_tokens_map.json +11 -0
- tokenizer.json +3 -0
- tokenizer_config.json +34 -0
- trainer_state.json +480 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# autoscientist-market-analysis-lenitnes
|
| 2 |
+
|
| 3 |
+
Fine-tuned adapter on `Qwen/Qwen3.5-9B` for the AutoScientist Part 2 submission. Maps GitHub commit/diff evidence to crypto signal classifications and 24h price direction labels.
|
| 4 |
+
|
| 5 |
+
## License
|
| 6 |
+
apache-2.0
|
| 7 |
+
|
| 8 |
+
## Base model
|
| 9 |
+
Qwen/Qwen3.5-9B
|
| 10 |
+
|
| 11 |
+
## Benchmarks
|
| 12 |
+
```json
|
| 13 |
+
{
|
| 14 |
+
"autoscientist": {
|
| 15 |
+
"run_id": "4b0ef68e-a233-454b-87d5-203f5c9d401c",
|
| 16 |
+
"dataset_id": "c701c50c-7582-4be1-9d7c-62618a001738",
|
| 17 |
+
"base_model": "Qwen/Qwen3.5-9B",
|
| 18 |
+
"iterations_completed": 5,
|
| 19 |
+
"max_iterations": 5,
|
| 20 |
+
"target_win_rate": 0.7,
|
| 21 |
+
"best_win_rate_vs_base": 0.5256,
|
| 22 |
+
"training_type": "lora"
|
| 23 |
+
},
|
| 24 |
+
"dataset": {
|
| 25 |
+
"adapted_rows": 27965,
|
| 26 |
+
"seed_rows_real": 1002,
|
| 27 |
+
"seed_signals_unique": 272,
|
| 28 |
+
"augmentation_domain_rows": 18998,
|
| 29 |
+
"augmentation_general_rows": 8000,
|
| 30 |
+
"adaptation_quality_grade": "A",
|
| 31 |
+
"direction_balance": {
|
| 32 |
+
"flat": 366,
|
| 33 |
+
"down": 331,
|
| 34 |
+
"up": 305
|
| 35 |
+
}
|
| 36 |
+
}
|
| 37 |
+
}
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
## Limitations
|
| 41 |
+
This is a research artifact. The model was trained on a small, domain-specific dataset and should not be relied upon for real trading or investment decisions.
|
adapter_config.json
ADDED
|
@@ -0,0 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "togethercomputer/Qwen3.5-9B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": [
|
| 9 |
+
"model.visual.blocks.15.attn",
|
| 10 |
+
"model.visual.blocks.21.mlp",
|
| 11 |
+
"model.visual.blocks.10.norm2",
|
| 12 |
+
"model.visual.blocks.11.attn.proj",
|
| 13 |
+
"model.visual.blocks.20.attn.proj",
|
| 14 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 15 |
+
"model.visual.blocks.10.mlp",
|
| 16 |
+
"model.visual.blocks.12",
|
| 17 |
+
"model.visual.blocks.9.mlp.act_fn",
|
| 18 |
+
"model.visual.blocks.23.mlp.act_fn",
|
| 19 |
+
"model.visual.blocks.10.attn.proj",
|
| 20 |
+
"model.visual.blocks.22.attn.qkv",
|
| 21 |
+
"model.visual.blocks.24.mlp.act_fn",
|
| 22 |
+
"model.visual.blocks.12.attn.qkv",
|
| 23 |
+
"model.visual.blocks.6.attn.proj",
|
| 24 |
+
"model.visual.blocks.11.attn",
|
| 25 |
+
"model.visual.blocks.7",
|
| 26 |
+
"model.visual.blocks.8.norm1",
|
| 27 |
+
"model.visual.blocks.18.attn.qkv",
|
| 28 |
+
"model.visual.blocks.2.attn",
|
| 29 |
+
"model.visual.blocks.1.norm2",
|
| 30 |
+
"model.visual.blocks.12.attn.proj",
|
| 31 |
+
"model.visual.blocks.21",
|
| 32 |
+
"model.visual.blocks.23",
|
| 33 |
+
"model.visual.blocks.2.mlp",
|
| 34 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 35 |
+
"model.visual.blocks.25.norm1",
|
| 36 |
+
"model.visual.blocks.8.mlp",
|
| 37 |
+
"model.visual.blocks.13.norm1",
|
| 38 |
+
"model.visual.merger.linear_fc2",
|
| 39 |
+
"model.visual.blocks.10.attn",
|
| 40 |
+
"model.visual.blocks.4.mlp",
|
| 41 |
+
"model.visual.blocks.25.norm2",
|
| 42 |
+
"model.visual.blocks.3",
|
| 43 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 44 |
+
"model.visual.blocks.17.norm1",
|
| 45 |
+
"model.visual.blocks.16.mlp",
|
| 46 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 47 |
+
"model.visual.blocks.3.norm1",
|
| 48 |
+
"model.visual.blocks.8.norm2",
|
| 49 |
+
"model.visual.blocks.0.mlp.act_fn",
|
| 50 |
+
"model.visual.blocks.13.attn",
|
| 51 |
+
"model.visual.blocks.19.mlp",
|
| 52 |
+
"model.visual.blocks.26.mlp",
|
| 53 |
+
"model.visual.blocks.19.norm1",
|
| 54 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 55 |
+
"model.visual.blocks.26.attn.proj",
|
| 56 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 57 |
+
"model.visual.blocks.6",
|
| 58 |
+
"model.visual.blocks.13.attn.qkv",
|
| 59 |
+
"model.visual.blocks.2",
|
| 60 |
+
"model.visual.blocks.19.norm2",
|
| 61 |
+
"model.visual.blocks.0.attn",
|
| 62 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 63 |
+
"model.visual.blocks.8.mlp.act_fn",
|
| 64 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 65 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 66 |
+
"model.visual.blocks.2.norm1",
|
| 67 |
+
"model.visual.blocks.17.attn.proj",
|
| 68 |
+
"model.visual.blocks.8.attn.qkv",
|
| 69 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 70 |
+
"model.visual.blocks.24.attn.qkv",
|
| 71 |
+
"model.visual.blocks.0",
|
| 72 |
+
"model.visual.blocks.25",
|
| 73 |
+
"model.visual.blocks.24.mlp",
|
| 74 |
+
"model.visual.blocks.9.norm1",
|
| 75 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 76 |
+
"model.visual.blocks.17.norm2",
|
| 77 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 78 |
+
"model.visual.blocks.6.mlp.act_fn",
|
| 79 |
+
"model.visual.blocks.24.attn.proj",
|
| 80 |
+
"model.visual.blocks.20.mlp",
|
| 81 |
+
"model.visual.blocks.18.norm2",
|
| 82 |
+
"model.visual.blocks.13.mlp",
|
| 83 |
+
"model.visual.blocks.13.norm2",
|
| 84 |
+
"model.visual.blocks.23.norm2",
|
| 85 |
+
"model.visual.blocks.3.mlp",
|
| 86 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 87 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 88 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 89 |
+
"model.visual.blocks.23.norm1",
|
| 90 |
+
"model.visual.blocks.22.mlp.act_fn",
|
| 91 |
+
"model.visual.blocks.5",
|
| 92 |
+
"model.visual.blocks.14.attn.qkv",
|
| 93 |
+
"model.visual.blocks.16.norm1",
|
| 94 |
+
"model.visual.blocks.18.attn.proj",
|
| 95 |
+
"model.visual.blocks.25.mlp.act_fn",
|
| 96 |
+
"model.visual.blocks.6.norm1",
|
| 97 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 98 |
+
"model.visual.blocks.21.attn.qkv",
|
| 99 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 100 |
+
"model.visual.blocks.14",
|
| 101 |
+
"model.visual.blocks.25.attn.qkv",
|
| 102 |
+
"model.visual.blocks.22.mlp",
|
| 103 |
+
"model.visual.blocks.26.attn",
|
| 104 |
+
"model.visual.blocks.8.attn",
|
| 105 |
+
"model.visual.blocks.11.norm1",
|
| 106 |
+
"model.visual.blocks.15.norm2",
|
| 107 |
+
"model.visual.blocks.6.norm2",
|
| 108 |
+
"model.visual.blocks.6.attn",
|
| 109 |
+
"model.visual.blocks.5.mlp.act_fn",
|
| 110 |
+
"model.visual.blocks.6.mlp",
|
| 111 |
+
"model.visual.blocks.1.attn",
|
| 112 |
+
"model.visual.blocks.9",
|
| 113 |
+
"model.visual.patch_embed.proj",
|
| 114 |
+
"model.visual.blocks.0.attn.qkv",
|
| 115 |
+
"model.visual.blocks.12.mlp",
|
| 116 |
+
"model.visual.blocks.18",
|
| 117 |
+
"model.visual.blocks.14.norm2",
|
| 118 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 119 |
+
"model.visual.blocks.19.attn.proj",
|
| 120 |
+
"model.visual.blocks.20",
|
| 121 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 122 |
+
"model.visual.blocks.22.attn.proj",
|
| 123 |
+
"model.visual.blocks.12.mlp.act_fn",
|
| 124 |
+
"model.visual.merger.act_fn",
|
| 125 |
+
"model.visual.blocks.15.norm1",
|
| 126 |
+
"model.visual.blocks.7.attn.qkv",
|
| 127 |
+
"model.visual.blocks.0.mlp",
|
| 128 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 129 |
+
"model.visual.blocks.11.mlp",
|
| 130 |
+
"model.visual.blocks.16.mlp.act_fn",
|
| 131 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 132 |
+
"model.visual.blocks.9.attn",
|
| 133 |
+
"model.visual.blocks.24.norm1",
|
| 134 |
+
"model.visual.blocks.4.norm2",
|
| 135 |
+
"model.visual.blocks.24.attn",
|
| 136 |
+
"model.visual.blocks.15",
|
| 137 |
+
"model.visual.blocks.17.mlp.act_fn",
|
| 138 |
+
"model.visual.blocks.8.attn.proj",
|
| 139 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 140 |
+
"model.visual.blocks.12.norm2",
|
| 141 |
+
"model.visual.blocks.17",
|
| 142 |
+
"model.visual.blocks.13",
|
| 143 |
+
"model.visual.blocks.24",
|
| 144 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 145 |
+
"model.visual.blocks.1.mlp.act_fn",
|
| 146 |
+
"model.visual.blocks.7.attn",
|
| 147 |
+
"model.visual.blocks.18.norm1",
|
| 148 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 149 |
+
"model.visual.blocks.15.attn.qkv",
|
| 150 |
+
"model.visual.blocks.6.attn.qkv",
|
| 151 |
+
"model.visual.blocks.1.attn.proj",
|
| 152 |
+
"model.visual.blocks.10",
|
| 153 |
+
"model.visual.blocks.13.mlp.act_fn",
|
| 154 |
+
"model.visual.blocks.21.attn",
|
| 155 |
+
"model.visual.blocks.20.attn",
|
| 156 |
+
"model.visual.blocks.26.mlp.act_fn",
|
| 157 |
+
"model.visual.blocks.1.attn.qkv",
|
| 158 |
+
"model.visual.blocks.3.attn.qkv",
|
| 159 |
+
"model.visual.blocks.7.mlp.act_fn",
|
| 160 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 161 |
+
"model.visual.blocks.22",
|
| 162 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 163 |
+
"model.visual.blocks.1.mlp",
|
| 164 |
+
"model.visual.blocks.3.mlp.act_fn",
|
| 165 |
+
"model.visual.blocks.4.norm1",
|
| 166 |
+
"model.visual.blocks.16.norm2",
|
| 167 |
+
"model.visual.patch_embed",
|
| 168 |
+
"model.visual.blocks.9.mlp",
|
| 169 |
+
"model.visual.blocks.16.attn.qkv",
|
| 170 |
+
"model.visual.blocks.24.norm2",
|
| 171 |
+
"model.visual.blocks.14.attn",
|
| 172 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 173 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 174 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 175 |
+
"model.visual.blocks.18.attn",
|
| 176 |
+
"model.visual.blocks.22.attn",
|
| 177 |
+
"model.visual.blocks.14.mlp.act_fn",
|
| 178 |
+
"model.visual.blocks.2.norm2",
|
| 179 |
+
"model.visual.blocks.4.attn.qkv",
|
| 180 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 181 |
+
"model.visual.blocks.2.mlp.act_fn",
|
| 182 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 183 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 184 |
+
"model.visual.blocks.19.attn.qkv",
|
| 185 |
+
"model.visual.blocks.25.attn",
|
| 186 |
+
"model.visual",
|
| 187 |
+
"model.visual.blocks.22.norm2",
|
| 188 |
+
"model.visual.blocks.21.norm1",
|
| 189 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 190 |
+
"model.visual.blocks.20.attn.qkv",
|
| 191 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 192 |
+
"model.visual.blocks.4",
|
| 193 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 194 |
+
"model.visual.blocks.14.attn.proj",
|
| 195 |
+
"model.visual.blocks.0.norm2",
|
| 196 |
+
"model.visual.rotary_pos_emb",
|
| 197 |
+
"model.visual.blocks.3.attn",
|
| 198 |
+
"model.visual.blocks.17.attn.qkv",
|
| 199 |
+
"model.visual.blocks.20.mlp.act_fn",
|
| 200 |
+
"model.visual.merger.norm",
|
| 201 |
+
"model.visual.blocks.4.mlp.act_fn",
|
| 202 |
+
"model.visual.blocks.25.attn.proj",
|
| 203 |
+
"model.visual.blocks.7.attn.proj",
|
| 204 |
+
"model.visual.blocks.3.norm2",
|
| 205 |
+
"model.visual.blocks.15.attn.proj",
|
| 206 |
+
"model.visual.blocks.1.norm1",
|
| 207 |
+
"model.visual.blocks.5.attn",
|
| 208 |
+
"model.visual.blocks.17.mlp",
|
| 209 |
+
"model.visual.blocks.23.mlp",
|
| 210 |
+
"model.visual.blocks.23.attn",
|
| 211 |
+
"model.visual.blocks.11.mlp.act_fn",
|
| 212 |
+
"model.visual.blocks.12.norm1",
|
| 213 |
+
"model.visual.blocks.16.attn",
|
| 214 |
+
"model.visual.blocks.5.attn.qkv",
|
| 215 |
+
"model.visual.blocks.11.attn.qkv",
|
| 216 |
+
"model.visual.blocks.3.attn.proj",
|
| 217 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 218 |
+
"model.visual.blocks.9.norm2",
|
| 219 |
+
"model.visual.blocks.15.mlp",
|
| 220 |
+
"model.visual.blocks",
|
| 221 |
+
"model.visual.blocks.1",
|
| 222 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 223 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 224 |
+
"model.visual.blocks.4.attn.proj",
|
| 225 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 226 |
+
"model.visual.blocks.21.attn.proj",
|
| 227 |
+
"model.visual.merger",
|
| 228 |
+
"model.visual.blocks.20.norm2",
|
| 229 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 230 |
+
"model.visual.blocks.7.norm1",
|
| 231 |
+
"model.visual.blocks.9.attn.proj",
|
| 232 |
+
"model.visual.blocks.17.attn",
|
| 233 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 234 |
+
"model.visual.blocks.19.mlp.act_fn",
|
| 235 |
+
"model.visual.blocks.13.attn.proj",
|
| 236 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 237 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 238 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 239 |
+
"model.visual.blocks.26.norm2",
|
| 240 |
+
"model.visual.blocks.0.attn.proj",
|
| 241 |
+
"model.visual.blocks.11.norm2",
|
| 242 |
+
"model.visual.blocks.0.norm1",
|
| 243 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 244 |
+
"model.visual.blocks.10.mlp.act_fn",
|
| 245 |
+
"model.visual.blocks.12.attn",
|
| 246 |
+
"model.visual.blocks.26.attn.qkv",
|
| 247 |
+
"model.visual.blocks.18.mlp.act_fn",
|
| 248 |
+
"model.visual.blocks.8",
|
| 249 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 250 |
+
"model.visual.blocks.4.attn",
|
| 251 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 252 |
+
"model.visual.blocks.9.attn.qkv",
|
| 253 |
+
"model.visual.pos_embed",
|
| 254 |
+
"model.visual.blocks.10.attn.qkv",
|
| 255 |
+
"model.visual.blocks.5.mlp",
|
| 256 |
+
"model.visual.blocks.19",
|
| 257 |
+
"model.visual.blocks.21.norm2",
|
| 258 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 259 |
+
"model.visual.blocks.21.mlp.act_fn",
|
| 260 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 261 |
+
"model.visual.blocks.23.attn.qkv",
|
| 262 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 263 |
+
"model.visual.blocks.2.attn.qkv",
|
| 264 |
+
"model.visual.blocks.26",
|
| 265 |
+
"model.visual.blocks.7.norm2",
|
| 266 |
+
"model.visual.blocks.5.norm1",
|
| 267 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 268 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 269 |
+
"model.visual.blocks.15.mlp.act_fn",
|
| 270 |
+
"model.visual.blocks.20.norm1",
|
| 271 |
+
"model.visual.blocks.23.attn.proj",
|
| 272 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 273 |
+
"model.visual.blocks.5.norm2",
|
| 274 |
+
"model.visual.blocks.5.attn.proj",
|
| 275 |
+
"model.visual.blocks.7.mlp",
|
| 276 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 277 |
+
"model.visual.blocks.25.mlp",
|
| 278 |
+
"model.visual.blocks.10.norm1",
|
| 279 |
+
"model.visual.blocks.14.norm1",
|
| 280 |
+
"model.visual.blocks.22.norm1",
|
| 281 |
+
"model.visual.blocks.11",
|
| 282 |
+
"model.visual.blocks.26.norm1",
|
| 283 |
+
"model.visual.blocks.19.attn",
|
| 284 |
+
"model.visual.blocks.2.attn.proj",
|
| 285 |
+
"model.visual.blocks.18.mlp",
|
| 286 |
+
"model.visual.blocks.16",
|
| 287 |
+
"model.visual.blocks.14.mlp",
|
| 288 |
+
"model.visual.merger.linear_fc1",
|
| 289 |
+
"model.visual.blocks.16.attn.proj"
|
| 290 |
+
],
|
| 291 |
+
"fan_in_fan_out": false,
|
| 292 |
+
"inference_mode": true,
|
| 293 |
+
"init_lora_weights": true,
|
| 294 |
+
"layer_replication": null,
|
| 295 |
+
"layers_pattern": null,
|
| 296 |
+
"layers_to_transform": null,
|
| 297 |
+
"loftq_config": {},
|
| 298 |
+
"lora_alpha": 32,
|
| 299 |
+
"lora_bias": false,
|
| 300 |
+
"lora_dropout": 0.0,
|
| 301 |
+
"megatron_config": null,
|
| 302 |
+
"megatron_core": "megatron.core",
|
| 303 |
+
"modules_to_save": null,
|
| 304 |
+
"peft_type": "LORA",
|
| 305 |
+
"r": 16,
|
| 306 |
+
"rank_pattern": {},
|
| 307 |
+
"revision": null,
|
| 308 |
+
"target_modules": [
|
| 309 |
+
"o_proj",
|
| 310 |
+
"v_proj",
|
| 311 |
+
"k_proj",
|
| 312 |
+
"q_proj"
|
| 313 |
+
],
|
| 314 |
+
"task_type": "CAUSAL_LM",
|
| 315 |
+
"trainable_token_indices": null,
|
| 316 |
+
"use_dora": false,
|
| 317 |
+
"use_rslora": false
|
| 318 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4b134760c387d7a19426a0cbe80983d93ea72d60462c5891767b62921e352f0
|
| 3 |
+
size 15738176
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- for message in messages %}
|
| 79 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 80 |
+
{%- if message.role == "system" %}
|
| 81 |
+
{%- if not loop.first %}
|
| 82 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- elif message.role == "user" %}
|
| 85 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 86 |
+
{%- elif message.role == "assistant" %}
|
| 87 |
+
{%- set reasoning_content = '' %}
|
| 88 |
+
{%- if message.reasoning_content is string %}
|
| 89 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 90 |
+
{%- else %}
|
| 91 |
+
{%- if '</think>' in content %}
|
| 92 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 93 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 97 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 98 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 99 |
+
{%- else %}
|
| 100 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 103 |
+
{%- for tool_call in message.tool_calls %}
|
| 104 |
+
{%- if tool_call.function is defined %}
|
| 105 |
+
{%- set tool_call = tool_call.function %}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{%- if loop.first %}
|
| 108 |
+
{%- if content|trim %}
|
| 109 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 110 |
+
{%- else %}
|
| 111 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 112 |
+
{%- endif %}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- if tool_call.arguments is defined %}
|
| 117 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 118 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 119 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 120 |
+
{{- args_value }}
|
| 121 |
+
{{- '\n</parameter>\n' }}
|
| 122 |
+
{%- endfor %}
|
| 123 |
+
{%- endif %}
|
| 124 |
+
{{- '</function>\n</tool_call>' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '<|im_end|>\n' }}
|
| 128 |
+
{%- elif message.role == "tool" %}
|
| 129 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 130 |
+
{{- '<|im_start|>user' }}
|
| 131 |
+
{%- endif %}
|
| 132 |
+
{{- '\n<tool_response>\n' }}
|
| 133 |
+
{{- content }}
|
| 134 |
+
{{- '\n</tool_response>' }}
|
| 135 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 136 |
+
{{- '<|im_end|>\n' }}
|
| 137 |
+
{%- elif loop.last %}
|
| 138 |
+
{{- '<|im_end|>\n' }}
|
| 139 |
+
{%- endif %}
|
| 140 |
+
{%- else %}
|
| 141 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- endfor %}
|
| 144 |
+
{%- if add_generation_prompt %}
|
| 145 |
+
{{- '<|im_start|>assistant\n' }}
|
| 146 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 147 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 148 |
+
{%- else %}
|
| 149 |
+
{{- '<think>\n' }}
|
| 150 |
+
{%- endif %}
|
| 151 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"image_token_id": 248056,
|
| 8 |
+
"model_type": "qwen3_5",
|
| 9 |
+
"pad_token_id": 248044,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_bias": false,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"attn_output_gate": true,
|
| 14 |
+
"bos_token_id": null,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 248044,
|
| 17 |
+
"full_attention_interval": 4,
|
| 18 |
+
"head_dim": 256,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 4096,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 12288,
|
| 23 |
+
"layer_types": [
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention"
|
| 56 |
+
],
|
| 57 |
+
"linear_conv_kernel_dim": 4,
|
| 58 |
+
"linear_key_head_dim": 128,
|
| 59 |
+
"linear_num_key_heads": 16,
|
| 60 |
+
"linear_num_value_heads": 32,
|
| 61 |
+
"linear_value_head_dim": 128,
|
| 62 |
+
"mamba_ssm_dtype": "float32",
|
| 63 |
+
"max_position_embeddings": 262144,
|
| 64 |
+
"mlp_only_layers": [],
|
| 65 |
+
"model_type": "qwen3_5_text",
|
| 66 |
+
"mtp_num_hidden_layers": 1,
|
| 67 |
+
"mtp_use_dedicated_embeddings": false,
|
| 68 |
+
"num_attention_heads": 16,
|
| 69 |
+
"num_hidden_layers": 32,
|
| 70 |
+
"num_key_value_heads": 4,
|
| 71 |
+
"pad_token_id": null,
|
| 72 |
+
"partial_rotary_factor": 0.25,
|
| 73 |
+
"rms_norm_eps": 1e-06,
|
| 74 |
+
"rope_parameters": {
|
| 75 |
+
"mrope_interleaved": true,
|
| 76 |
+
"mrope_section": [
|
| 77 |
+
11,
|
| 78 |
+
11,
|
| 79 |
+
10
|
| 80 |
+
],
|
| 81 |
+
"partial_rotary_factor": 0.25,
|
| 82 |
+
"rope_theta": 10000000,
|
| 83 |
+
"rope_type": "default"
|
| 84 |
+
},
|
| 85 |
+
"tie_word_embeddings": false,
|
| 86 |
+
"use_cache": false,
|
| 87 |
+
"vocab_size": 248320,
|
| 88 |
+
"torch_dtype": "bfloat16"
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"transformers_version": "5.13.0",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 27,
|
| 97 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 98 |
+
"hidden_size": 1152,
|
| 99 |
+
"in_channels": 3,
|
| 100 |
+
"initializer_range": 0.02,
|
| 101 |
+
"intermediate_size": 4304,
|
| 102 |
+
"model_type": "qwen3_5_vision",
|
| 103 |
+
"num_heads": 16,
|
| 104 |
+
"num_position_embeddings": 2304,
|
| 105 |
+
"out_hidden_size": 4096,
|
| 106 |
+
"patch_size": 16,
|
| 107 |
+
"spatial_merge_size": 2,
|
| 108 |
+
"temporal_patch_size": 2
|
| 109 |
+
},
|
| 110 |
+
"vision_end_token_id": 248054,
|
| 111 |
+
"vision_start_token_id": 248053,
|
| 112 |
+
"torch_dtype": "bfloat16"
|
| 113 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"merge_size": 2,
|
| 18 |
+
"patch_size": 16,
|
| 19 |
+
"resample": 3,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"longest_edge": 16777216,
|
| 23 |
+
"shortest_edge": 65536
|
| 24 |
+
},
|
| 25 |
+
"temporal_patch_size": 2
|
| 26 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_bos_token": "<|audio_start|>",
|
| 3 |
+
"audio_eos_token": "<|audio_end|>",
|
| 4 |
+
"audio_token": "<|audio_pad|>",
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"image_token": "<|image_pad|>",
|
| 7 |
+
"pad_token": "<|endoftext|>",
|
| 8 |
+
"video_token": "<|video_pad|>",
|
| 9 |
+
"vision_bos_token": "<|vision_start|>",
|
| 10 |
+
"vision_eos_token": "<|vision_end|>"
|
| 11 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"padding_side": "right",
|
| 26 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"unk_token": null,
|
| 31 |
+
"video_token": "<|video_pad|>",
|
| 32 |
+
"vision_bos_token": "<|vision_start|>",
|
| 33 |
+
"vision_eos_token": "<|vision_end|>"
|
| 34 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,480 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 11,
|
| 7 |
+
"global_step": 58,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.017241379310344827,
|
| 14 |
+
"grad_norm": 3.466994285583496,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.70361328125,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.034482758620689655,
|
| 21 |
+
"grad_norm": 3.0673391819000244,
|
| 22 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 23 |
+
"loss": 1.52783203125,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05172413793103448,
|
| 28 |
+
"grad_norm": 3.185170888900757,
|
| 29 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 30 |
+
"loss": 1.43359375,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06896551724137931,
|
| 35 |
+
"grad_norm": 2.724968194961548,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 1.36785888671875,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08620689655172414,
|
| 42 |
+
"grad_norm": 3.409799814224243,
|
| 43 |
+
"learning_rate": 6.666666666666667e-06,
|
| 44 |
+
"loss": 1.6259765625,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10344827586206896,
|
| 49 |
+
"grad_norm": 3.255406618118286,
|
| 50 |
+
"learning_rate": 8.333333333333334e-06,
|
| 51 |
+
"loss": 1.5966796875,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1206896551724138,
|
| 56 |
+
"grad_norm": 3.26574444770813,
|
| 57 |
+
"learning_rate": 1e-05,
|
| 58 |
+
"loss": 1.564453125,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13793103448275862,
|
| 63 |
+
"grad_norm": 2.7970426082611084,
|
| 64 |
+
"learning_rate": 9.991789994004929e-06,
|
| 65 |
+
"loss": 1.44329833984375,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.15517241379310345,
|
| 70 |
+
"grad_norm": 3.3764612674713135,
|
| 71 |
+
"learning_rate": 9.967189933441243e-06,
|
| 72 |
+
"loss": 1.720703125,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1724137931034483,
|
| 77 |
+
"grad_norm": 3.1462111473083496,
|
| 78 |
+
"learning_rate": 9.926289581262147e-06,
|
| 79 |
+
"loss": 1.5654296875,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1896551724137931,
|
| 84 |
+
"grad_norm": 2.9673638343811035,
|
| 85 |
+
"learning_rate": 9.869238178417235e-06,
|
| 86 |
+
"loss": 1.4873046875,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20689655172413793,
|
| 91 |
+
"grad_norm": 3.0774664878845215,
|
| 92 |
+
"learning_rate": 9.796243899288455e-06,
|
| 93 |
+
"loss": 1.4814453125,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.22413793103448276,
|
| 98 |
+
"grad_norm": 2.994229555130005,
|
| 99 |
+
"learning_rate": 9.707573092084368e-06,
|
| 100 |
+
"loss": 1.51123046875,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2413793103448276,
|
| 105 |
+
"grad_norm": 3.2788591384887695,
|
| 106 |
+
"learning_rate": 9.603549306964408e-06,
|
| 107 |
+
"loss": 1.515625,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2413793103448276,
|
| 112 |
+
"eval_loss": 1.4599609375,
|
| 113 |
+
"eval_runtime": 12.0161,
|
| 114 |
+
"eval_samples_per_second": 0.333,
|
| 115 |
+
"eval_steps_per_second": 0.083,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.25862068965517243,
|
| 120 |
+
"grad_norm": 3.111900568008423,
|
| 121 |
+
"learning_rate": 9.484552115439445e-06,
|
| 122 |
+
"loss": 1.44189453125,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.27586206896551724,
|
| 127 |
+
"grad_norm": 3.265875816345215,
|
| 128 |
+
"learning_rate": 9.351015725356515e-06,
|
| 129 |
+
"loss": 1.4345703125,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.29310344827586204,
|
| 134 |
+
"grad_norm": 3.168644905090332,
|
| 135 |
+
"learning_rate": 9.203427396521454e-06,
|
| 136 |
+
"loss": 1.51904296875,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3103448275862069,
|
| 141 |
+
"grad_norm": 3.5742452144622803,
|
| 142 |
+
"learning_rate": 9.042325662740726e-06,
|
| 143 |
+
"loss": 1.603515625,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3275862068965517,
|
| 148 |
+
"grad_norm": 2.631960153579712,
|
| 149 |
+
"learning_rate": 8.868298366769956e-06,
|
| 150 |
+
"loss": 1.2431640625,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3448275862068966,
|
| 155 |
+
"grad_norm": 2.9797987937927246,
|
| 156 |
+
"learning_rate": 8.681980515339464e-06,
|
| 157 |
+
"loss": 1.40576171875,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.3620689655172414,
|
| 162 |
+
"grad_norm": 2.9928715229034424,
|
| 163 |
+
"learning_rate": 8.484051962083579e-06,
|
| 164 |
+
"loss": 1.3681640625,
|
| 165 |
+
"step": 21
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.3793103448275862,
|
| 169 |
+
"grad_norm": 2.928797960281372,
|
| 170 |
+
"learning_rate": 8.275234926828446e-06,
|
| 171 |
+
"loss": 1.3447265625,
|
| 172 |
+
"step": 22
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.39655172413793105,
|
| 176 |
+
"grad_norm": 2.930736780166626,
|
| 177 |
+
"learning_rate": 8.056291360290202e-06,
|
| 178 |
+
"loss": 1.34375,
|
| 179 |
+
"step": 23
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.41379310344827586,
|
| 183 |
+
"grad_norm": 3.0112173557281494,
|
| 184 |
+
"learning_rate": 7.828020163799455e-06,
|
| 185 |
+
"loss": 1.36279296875,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.43103448275862066,
|
| 190 |
+
"grad_norm": 2.821633815765381,
|
| 191 |
+
"learning_rate": 7.5912542741969585e-06,
|
| 192 |
+
"loss": 1.33203125,
|
| 193 |
+
"step": 25
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.43103448275862066,
|
| 197 |
+
"eval_loss": 1.3720703125,
|
| 198 |
+
"eval_runtime": 2.3797,
|
| 199 |
+
"eval_samples_per_second": 1.681,
|
| 200 |
+
"eval_steps_per_second": 0.42,
|
| 201 |
+
"step": 25
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.4482758620689655,
|
| 205 |
+
"grad_norm": 2.778196334838867,
|
| 206 |
+
"learning_rate": 7.346857624537407e-06,
|
| 207 |
+
"loss": 1.3251953125,
|
| 208 |
+
"step": 26
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.46551724137931033,
|
| 212 |
+
"grad_norm": 2.714803457260132,
|
| 213 |
+
"learning_rate": 7.095721991691411e-06,
|
| 214 |
+
"loss": 1.33251953125,
|
| 215 |
+
"step": 27
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.4827586206896552,
|
| 219 |
+
"grad_norm": 3.300633192062378,
|
| 220 |
+
"learning_rate": 6.838763742348414e-06,
|
| 221 |
+
"loss": 1.5068359375,
|
| 222 |
+
"step": 28
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5,
|
| 226 |
+
"grad_norm": 2.66582989692688,
|
| 227 |
+
"learning_rate": 6.576920489294011e-06,
|
| 228 |
+
"loss": 1.14361572265625,
|
| 229 |
+
"step": 29
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5172413793103449,
|
| 233 |
+
"grad_norm": 2.9645633697509766,
|
| 234 |
+
"learning_rate": 6.311147670162576e-06,
|
| 235 |
+
"loss": 1.43359375,
|
| 236 |
+
"step": 30
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5344827586206896,
|
| 240 |
+
"grad_norm": 3.040027141571045,
|
| 241 |
+
"learning_rate": 6.042415061148954e-06,
|
| 242 |
+
"loss": 1.4453125,
|
| 243 |
+
"step": 31
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.5517241379310345,
|
| 247 |
+
"grad_norm": 2.890130043029785,
|
| 248 |
+
"learning_rate": 5.771703238400288e-06,
|
| 249 |
+
"loss": 1.31640625,
|
| 250 |
+
"step": 32
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5689655172413793,
|
| 254 |
+
"grad_norm": 3.2029335498809814,
|
| 255 |
+
"learning_rate": 5.500000000000001e-06,
|
| 256 |
+
"loss": 1.4306640625,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.5862068965517241,
|
| 261 |
+
"grad_norm": 2.247018575668335,
|
| 262 |
+
"learning_rate": 5.228296761599713e-06,
|
| 263 |
+
"loss": 1.19189453125,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.603448275862069,
|
| 268 |
+
"grad_norm": 3.2325239181518555,
|
| 269 |
+
"learning_rate": 4.957584938851048e-06,
|
| 270 |
+
"loss": 1.419921875,
|
| 271 |
+
"step": 35
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.6206896551724138,
|
| 275 |
+
"grad_norm": 2.7489123344421387,
|
| 276 |
+
"learning_rate": 4.6888523298374245e-06,
|
| 277 |
+
"loss": 1.3671875,
|
| 278 |
+
"step": 36
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.6206896551724138,
|
| 282 |
+
"eval_loss": 1.3037109375,
|
| 283 |
+
"eval_runtime": 2.3711,
|
| 284 |
+
"eval_samples_per_second": 1.687,
|
| 285 |
+
"eval_steps_per_second": 0.422,
|
| 286 |
+
"step": 36
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6379310344827587,
|
| 290 |
+
"grad_norm": 2.097079038619995,
|
| 291 |
+
"learning_rate": 4.423079510705992e-06,
|
| 292 |
+
"loss": 1.1181640625,
|
| 293 |
+
"step": 37
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.6551724137931034,
|
| 297 |
+
"grad_norm": 2.887427568435669,
|
| 298 |
+
"learning_rate": 4.1612362576515875e-06,
|
| 299 |
+
"loss": 1.29736328125,
|
| 300 |
+
"step": 38
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.6724137931034483,
|
| 304 |
+
"grad_norm": 2.80908465385437,
|
| 305 |
+
"learning_rate": 3.904278008308589e-06,
|
| 306 |
+
"loss": 1.30224609375,
|
| 307 |
+
"step": 39
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.6896551724137931,
|
| 311 |
+
"grad_norm": 2.9859089851379395,
|
| 312 |
+
"learning_rate": 3.653142375462596e-06,
|
| 313 |
+
"loss": 1.32958984375,
|
| 314 |
+
"step": 40
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7068965517241379,
|
| 318 |
+
"grad_norm": 2.807049512863159,
|
| 319 |
+
"learning_rate": 3.408745725803042e-06,
|
| 320 |
+
"loss": 1.3544921875,
|
| 321 |
+
"step": 41
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.7241379310344828,
|
| 325 |
+
"grad_norm": 2.4716262817382812,
|
| 326 |
+
"learning_rate": 3.1719798362005444e-06,
|
| 327 |
+
"loss": 1.24609375,
|
| 328 |
+
"step": 42
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.7413793103448276,
|
| 332 |
+
"grad_norm": 2.4141592979431152,
|
| 333 |
+
"learning_rate": 2.9437086397097996e-06,
|
| 334 |
+
"loss": 1.18408203125,
|
| 335 |
+
"step": 43
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.7586206896551724,
|
| 339 |
+
"grad_norm": 3.089064121246338,
|
| 340 |
+
"learning_rate": 2.7247650731715563e-06,
|
| 341 |
+
"loss": 1.3623046875,
|
| 342 |
+
"step": 44
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.7758620689655172,
|
| 346 |
+
"grad_norm": 3.2062597274780273,
|
| 347 |
+
"learning_rate": 2.515948037916423e-06,
|
| 348 |
+
"loss": 1.4580078125,
|
| 349 |
+
"step": 45
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.7931034482758621,
|
| 353 |
+
"grad_norm": 3.4178287982940674,
|
| 354 |
+
"learning_rate": 2.3180194846605367e-06,
|
| 355 |
+
"loss": 1.482421875,
|
| 356 |
+
"step": 46
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.8103448275862069,
|
| 360 |
+
"grad_norm": 1.7587018013000488,
|
| 361 |
+
"learning_rate": 2.131701633230045e-06,
|
| 362 |
+
"loss": 1.08740234375,
|
| 363 |
+
"step": 47
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.8103448275862069,
|
| 367 |
+
"eval_loss": 1.2822265625,
|
| 368 |
+
"eval_runtime": 2.3775,
|
| 369 |
+
"eval_samples_per_second": 1.682,
|
| 370 |
+
"eval_steps_per_second": 0.421,
|
| 371 |
+
"step": 47
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.8275862068965517,
|
| 375 |
+
"grad_norm": 3.730811834335327,
|
| 376 |
+
"learning_rate": 1.957674337259275e-06,
|
| 377 |
+
"loss": 1.5830078125,
|
| 378 |
+
"step": 48
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.8448275862068966,
|
| 382 |
+
"grad_norm": 3.2625794410705566,
|
| 383 |
+
"learning_rate": 1.7965726034785466e-06,
|
| 384 |
+
"loss": 1.4775390625,
|
| 385 |
+
"step": 49
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.8620689655172413,
|
| 389 |
+
"grad_norm": 1.8691109418869019,
|
| 390 |
+
"learning_rate": 1.648984274643487e-06,
|
| 391 |
+
"loss": 1.08447265625,
|
| 392 |
+
"step": 50
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.8793103448275862,
|
| 396 |
+
"grad_norm": 2.5822291374206543,
|
| 397 |
+
"learning_rate": 1.515447884560556e-06,
|
| 398 |
+
"loss": 1.2744140625,
|
| 399 |
+
"step": 51
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.896551724137931,
|
| 403 |
+
"grad_norm": 2.494469165802002,
|
| 404 |
+
"learning_rate": 1.3964506930355947e-06,
|
| 405 |
+
"loss": 1.2880859375,
|
| 406 |
+
"step": 52
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9137931034482759,
|
| 410 |
+
"grad_norm": 3.222137689590454,
|
| 411 |
+
"learning_rate": 1.292426907915634e-06,
|
| 412 |
+
"loss": 1.5126953125,
|
| 413 |
+
"step": 53
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.9310344827586207,
|
| 417 |
+
"grad_norm": 2.2438998222351074,
|
| 418 |
+
"learning_rate": 1.203756100711545e-06,
|
| 419 |
+
"loss": 1.2275390625,
|
| 420 |
+
"step": 54
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.9482758620689655,
|
| 424 |
+
"grad_norm": 2.6490988731384277,
|
| 425 |
+
"learning_rate": 1.130761821582766e-06,
|
| 426 |
+
"loss": 1.38671875,
|
| 427 |
+
"step": 55
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.9655172413793104,
|
| 431 |
+
"grad_norm": 2.225778818130493,
|
| 432 |
+
"learning_rate": 1.0737104187378543e-06,
|
| 433 |
+
"loss": 1.1982421875,
|
| 434 |
+
"step": 56
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9827586206896551,
|
| 438 |
+
"grad_norm": 3.02351450920105,
|
| 439 |
+
"learning_rate": 1.0328100665587573e-06,
|
| 440 |
+
"loss": 1.4423828125,
|
| 441 |
+
"step": 57
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.0,
|
| 445 |
+
"grad_norm": 2.729759454727173,
|
| 446 |
+
"learning_rate": 1.0082100059950713e-06,
|
| 447 |
+
"loss": 1.3251953125,
|
| 448 |
+
"step": 58
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.0,
|
| 452 |
+
"eval_loss": 1.2646484375,
|
| 453 |
+
"eval_runtime": 2.3799,
|
| 454 |
+
"eval_samples_per_second": 1.681,
|
| 455 |
+
"eval_steps_per_second": 0.42,
|
| 456 |
+
"step": 58
|
| 457 |
+
}
|
| 458 |
+
],
|
| 459 |
+
"logging_steps": 1.0,
|
| 460 |
+
"max_steps": 58,
|
| 461 |
+
"num_input_tokens_seen": 0,
|
| 462 |
+
"num_train_epochs": 1,
|
| 463 |
+
"save_steps": 0,
|
| 464 |
+
"stateful_callbacks": {
|
| 465 |
+
"TrainerControl": {
|
| 466 |
+
"args": {
|
| 467 |
+
"should_epoch_stop": false,
|
| 468 |
+
"should_evaluate": false,
|
| 469 |
+
"should_log": false,
|
| 470 |
+
"should_save": true,
|
| 471 |
+
"should_training_stop": true
|
| 472 |
+
},
|
| 473 |
+
"attributes": {}
|
| 474 |
+
}
|
| 475 |
+
},
|
| 476 |
+
"total_flos": 1.5305965589726495e+18,
|
| 477 |
+
"train_batch_size": 1,
|
| 478 |
+
"trial_name": null,
|
| 479 |
+
"trial_params": null
|
| 480 |
+
}
|