sujithatz/finbot-quen2.5-merged_adapter
Browse files- .gitattributes +1 -0
- README.md +258 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- merges.txt +0 -0
- special_tokens_map.json +19 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: quen_2.5_lora
|
| 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 |
+
# quen_2.5_lora
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7650
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 0
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 47 |
+
- num_epochs: 8
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 3.1119 | 0.0405 | 3 | 3.1017 |
|
| 54 |
+
| 2.8734 | 0.0811 | 6 | 2.6094 |
|
| 55 |
+
| 2.4188 | 0.1216 | 9 | 2.1546 |
|
| 56 |
+
| 1.9335 | 0.1622 | 12 | 1.7862 |
|
| 57 |
+
| 1.5361 | 0.2027 | 15 | 1.4732 |
|
| 58 |
+
| 1.314 | 0.2432 | 18 | 1.2791 |
|
| 59 |
+
| 1.1747 | 0.2838 | 21 | 1.1653 |
|
| 60 |
+
| 1.1407 | 0.3243 | 24 | 1.1104 |
|
| 61 |
+
| 1.1734 | 0.3649 | 27 | 1.0887 |
|
| 62 |
+
| 1.0495 | 0.4054 | 30 | 1.0401 |
|
| 63 |
+
| 1.0401 | 0.4459 | 33 | 0.9906 |
|
| 64 |
+
| 1.0623 | 0.4865 | 36 | 0.9594 |
|
| 65 |
+
| 0.8152 | 0.5270 | 39 | 0.9367 |
|
| 66 |
+
| 0.9261 | 0.5676 | 42 | 0.9248 |
|
| 67 |
+
| 0.9469 | 0.6081 | 45 | 0.9135 |
|
| 68 |
+
| 0.8381 | 0.6486 | 48 | 0.8871 |
|
| 69 |
+
| 0.8456 | 0.6892 | 51 | 0.8553 |
|
| 70 |
+
| 0.908 | 0.7297 | 54 | 0.8272 |
|
| 71 |
+
| 0.999 | 0.7703 | 57 | 0.8152 |
|
| 72 |
+
| 0.897 | 0.8108 | 60 | 0.8053 |
|
| 73 |
+
| 0.8747 | 0.8514 | 63 | 0.7915 |
|
| 74 |
+
| 1.0646 | 0.8919 | 66 | 0.7873 |
|
| 75 |
+
| 0.6771 | 0.9324 | 69 | 0.7815 |
|
| 76 |
+
| 0.9386 | 0.9730 | 72 | 0.7635 |
|
| 77 |
+
| 0.6348 | 1.0135 | 75 | 0.7552 |
|
| 78 |
+
| 0.5763 | 1.0541 | 78 | 0.7474 |
|
| 79 |
+
| 0.7059 | 1.0946 | 81 | 0.7431 |
|
| 80 |
+
| 0.6111 | 1.1351 | 84 | 0.7394 |
|
| 81 |
+
| 0.6937 | 1.1757 | 87 | 0.7416 |
|
| 82 |
+
| 0.6408 | 1.2162 | 90 | 0.7332 |
|
| 83 |
+
| 0.5931 | 1.2568 | 93 | 0.7319 |
|
| 84 |
+
| 0.5792 | 1.2973 | 96 | 0.7179 |
|
| 85 |
+
| 0.5502 | 1.3378 | 99 | 0.7083 |
|
| 86 |
+
| 0.7356 | 1.3784 | 102 | 0.7049 |
|
| 87 |
+
| 0.5204 | 1.4189 | 105 | 0.6983 |
|
| 88 |
+
| 0.6132 | 1.4595 | 108 | 0.6858 |
|
| 89 |
+
| 0.7527 | 1.5 | 111 | 0.6744 |
|
| 90 |
+
| 0.6798 | 1.5405 | 114 | 0.6716 |
|
| 91 |
+
| 0.7266 | 1.5811 | 117 | 0.6656 |
|
| 92 |
+
| 0.5347 | 1.6216 | 120 | 0.6711 |
|
| 93 |
+
| 0.6522 | 1.6622 | 123 | 0.6680 |
|
| 94 |
+
| 0.8567 | 1.7027 | 126 | 0.6558 |
|
| 95 |
+
| 0.5204 | 1.7432 | 129 | 0.6488 |
|
| 96 |
+
| 0.6443 | 1.7838 | 132 | 0.6393 |
|
| 97 |
+
| 0.5436 | 1.8243 | 135 | 0.6322 |
|
| 98 |
+
| 0.6054 | 1.8649 | 138 | 0.6346 |
|
| 99 |
+
| 0.4488 | 1.9054 | 141 | 0.6389 |
|
| 100 |
+
| 0.7171 | 1.9459 | 144 | 0.6322 |
|
| 101 |
+
| 0.5383 | 1.9865 | 147 | 0.6273 |
|
| 102 |
+
| 0.4812 | 2.0270 | 150 | 0.6235 |
|
| 103 |
+
| 0.7911 | 2.0676 | 153 | 0.6296 |
|
| 104 |
+
| 0.514 | 2.1081 | 156 | 0.6444 |
|
| 105 |
+
| 0.4481 | 2.1486 | 159 | 0.6453 |
|
| 106 |
+
| 0.3983 | 2.1892 | 162 | 0.6357 |
|
| 107 |
+
| 0.2386 | 2.2297 | 165 | 0.6327 |
|
| 108 |
+
| 0.4447 | 2.2703 | 168 | 0.6359 |
|
| 109 |
+
| 0.4302 | 2.3108 | 171 | 0.6387 |
|
| 110 |
+
| 0.4514 | 2.3514 | 174 | 0.6402 |
|
| 111 |
+
| 0.2813 | 2.3919 | 177 | 0.6313 |
|
| 112 |
+
| 0.4747 | 2.4324 | 180 | 0.6259 |
|
| 113 |
+
| 0.547 | 2.4730 | 183 | 0.6257 |
|
| 114 |
+
| 0.3154 | 2.5135 | 186 | 0.6247 |
|
| 115 |
+
| 0.5583 | 2.5541 | 189 | 0.6130 |
|
| 116 |
+
| 0.5726 | 2.5946 | 192 | 0.6087 |
|
| 117 |
+
| 0.4701 | 2.6351 | 195 | 0.6086 |
|
| 118 |
+
| 0.4866 | 2.6757 | 198 | 0.6133 |
|
| 119 |
+
| 0.4015 | 2.7162 | 201 | 0.6213 |
|
| 120 |
+
| 0.4277 | 2.7568 | 204 | 0.6238 |
|
| 121 |
+
| 0.3157 | 2.7973 | 207 | 0.6249 |
|
| 122 |
+
| 0.3883 | 2.8378 | 210 | 0.6210 |
|
| 123 |
+
| 0.5436 | 2.8784 | 213 | 0.6127 |
|
| 124 |
+
| 0.526 | 2.9189 | 216 | 0.6056 |
|
| 125 |
+
| 0.4465 | 2.9595 | 219 | 0.5982 |
|
| 126 |
+
| 0.3692 | 3.0 | 222 | 0.5917 |
|
| 127 |
+
| 0.3022 | 3.0405 | 225 | 0.5956 |
|
| 128 |
+
| 0.2875 | 3.0811 | 228 | 0.6153 |
|
| 129 |
+
| 0.5544 | 3.1216 | 231 | 0.6343 |
|
| 130 |
+
| 0.4159 | 3.1622 | 234 | 0.6370 |
|
| 131 |
+
| 0.4963 | 3.2027 | 237 | 0.6289 |
|
| 132 |
+
| 0.3248 | 3.2432 | 240 | 0.6190 |
|
| 133 |
+
| 0.349 | 3.2838 | 243 | 0.6111 |
|
| 134 |
+
| 0.3107 | 3.3243 | 246 | 0.6121 |
|
| 135 |
+
| 0.2219 | 3.3649 | 249 | 0.6196 |
|
| 136 |
+
| 0.251 | 3.4054 | 252 | 0.6273 |
|
| 137 |
+
| 0.3366 | 3.4459 | 255 | 0.6259 |
|
| 138 |
+
| 0.3182 | 3.4865 | 258 | 0.6243 |
|
| 139 |
+
| 0.4133 | 3.5270 | 261 | 0.6260 |
|
| 140 |
+
| 0.3297 | 3.5676 | 264 | 0.6303 |
|
| 141 |
+
| 0.2276 | 3.6081 | 267 | 0.6365 |
|
| 142 |
+
| 0.1842 | 3.6486 | 270 | 0.6383 |
|
| 143 |
+
| 0.4961 | 3.6892 | 273 | 0.6314 |
|
| 144 |
+
| 0.3785 | 3.7297 | 276 | 0.6240 |
|
| 145 |
+
| 0.2834 | 3.7703 | 279 | 0.6189 |
|
| 146 |
+
| 0.3397 | 3.8108 | 282 | 0.6139 |
|
| 147 |
+
| 0.2795 | 3.8514 | 285 | 0.6104 |
|
| 148 |
+
| 0.3114 | 3.8919 | 288 | 0.6078 |
|
| 149 |
+
| 0.2395 | 3.9324 | 291 | 0.6111 |
|
| 150 |
+
| 0.1948 | 3.9730 | 294 | 0.6142 |
|
| 151 |
+
| 0.2284 | 4.0135 | 297 | 0.6194 |
|
| 152 |
+
| 0.2638 | 4.0541 | 300 | 0.6303 |
|
| 153 |
+
| 0.252 | 4.0946 | 303 | 0.6517 |
|
| 154 |
+
| 0.183 | 4.1351 | 306 | 0.6645 |
|
| 155 |
+
| 0.2415 | 4.1757 | 309 | 0.6604 |
|
| 156 |
+
| 0.1791 | 4.2162 | 312 | 0.6530 |
|
| 157 |
+
| 0.2013 | 4.2568 | 315 | 0.6489 |
|
| 158 |
+
| 0.1827 | 4.2973 | 318 | 0.6532 |
|
| 159 |
+
| 0.1792 | 4.3378 | 321 | 0.6585 |
|
| 160 |
+
| 0.2568 | 4.3784 | 324 | 0.6628 |
|
| 161 |
+
| 0.1682 | 4.4189 | 327 | 0.6650 |
|
| 162 |
+
| 0.25 | 4.4595 | 330 | 0.6730 |
|
| 163 |
+
| 0.2664 | 4.5 | 333 | 0.6741 |
|
| 164 |
+
| 0.2316 | 4.5405 | 336 | 0.6773 |
|
| 165 |
+
| 0.3467 | 4.5811 | 339 | 0.6705 |
|
| 166 |
+
| 0.2426 | 4.6216 | 342 | 0.6681 |
|
| 167 |
+
| 0.2421 | 4.6622 | 345 | 0.6622 |
|
| 168 |
+
| 0.4063 | 4.7027 | 348 | 0.6609 |
|
| 169 |
+
| 0.2255 | 4.7432 | 351 | 0.6569 |
|
| 170 |
+
| 0.1933 | 4.7838 | 354 | 0.6534 |
|
| 171 |
+
| 0.1975 | 4.8243 | 357 | 0.6497 |
|
| 172 |
+
| 0.3065 | 4.8649 | 360 | 0.6491 |
|
| 173 |
+
| 0.1641 | 4.9054 | 363 | 0.6513 |
|
| 174 |
+
| 0.2032 | 4.9459 | 366 | 0.6553 |
|
| 175 |
+
| 0.1886 | 4.9865 | 369 | 0.6590 |
|
| 176 |
+
| 0.2539 | 5.0270 | 372 | 0.6677 |
|
| 177 |
+
| 0.1464 | 5.0676 | 375 | 0.6879 |
|
| 178 |
+
| 0.2295 | 5.1081 | 378 | 0.7066 |
|
| 179 |
+
| 0.1438 | 5.1486 | 381 | 0.7167 |
|
| 180 |
+
| 0.1603 | 5.1892 | 384 | 0.7135 |
|
| 181 |
+
| 0.1379 | 5.2297 | 387 | 0.7095 |
|
| 182 |
+
| 0.2783 | 5.2703 | 390 | 0.7103 |
|
| 183 |
+
| 0.1575 | 5.3108 | 393 | 0.7042 |
|
| 184 |
+
| 0.1743 | 5.3514 | 396 | 0.7114 |
|
| 185 |
+
| 0.1168 | 5.3919 | 399 | 0.7083 |
|
| 186 |
+
| 0.284 | 5.4324 | 402 | 0.7072 |
|
| 187 |
+
| 0.1013 | 5.4730 | 405 | 0.7063 |
|
| 188 |
+
| 0.2612 | 5.5135 | 408 | 0.7051 |
|
| 189 |
+
| 0.1343 | 5.5541 | 411 | 0.7103 |
|
| 190 |
+
| 0.1009 | 5.5946 | 414 | 0.7105 |
|
| 191 |
+
| 0.3127 | 5.6351 | 417 | 0.7090 |
|
| 192 |
+
| 0.1355 | 5.6757 | 420 | 0.7060 |
|
| 193 |
+
| 0.1345 | 5.7162 | 423 | 0.7057 |
|
| 194 |
+
| 0.1865 | 5.7568 | 426 | 0.7039 |
|
| 195 |
+
| 0.119 | 5.7973 | 429 | 0.7067 |
|
| 196 |
+
| 0.149 | 5.8378 | 432 | 0.7120 |
|
| 197 |
+
| 0.1748 | 5.8784 | 435 | 0.7123 |
|
| 198 |
+
| 0.1781 | 5.9189 | 438 | 0.7113 |
|
| 199 |
+
| 0.2075 | 5.9595 | 441 | 0.7118 |
|
| 200 |
+
| 0.1591 | 6.0 | 444 | 0.7112 |
|
| 201 |
+
| 0.1224 | 6.0405 | 447 | 0.7118 |
|
| 202 |
+
| 0.2234 | 6.0811 | 450 | 0.7171 |
|
| 203 |
+
| 0.1165 | 6.1216 | 453 | 0.7227 |
|
| 204 |
+
| 0.2518 | 6.1622 | 456 | 0.7326 |
|
| 205 |
+
| 0.1288 | 6.2027 | 459 | 0.7431 |
|
| 206 |
+
| 0.1176 | 6.2432 | 462 | 0.7481 |
|
| 207 |
+
| 0.1231 | 6.2838 | 465 | 0.7511 |
|
| 208 |
+
| 0.146 | 6.3243 | 468 | 0.7530 |
|
| 209 |
+
| 0.1169 | 6.3649 | 471 | 0.7518 |
|
| 210 |
+
| 0.1048 | 6.4054 | 474 | 0.7541 |
|
| 211 |
+
| 0.1092 | 6.4459 | 477 | 0.7507 |
|
| 212 |
+
| 0.1458 | 6.4865 | 480 | 0.7518 |
|
| 213 |
+
| 0.2177 | 6.5270 | 483 | 0.7509 |
|
| 214 |
+
| 0.1585 | 6.5676 | 486 | 0.7510 |
|
| 215 |
+
| 0.1337 | 6.6081 | 489 | 0.7546 |
|
| 216 |
+
| 0.122 | 6.6486 | 492 | 0.7524 |
|
| 217 |
+
| 0.0793 | 6.6892 | 495 | 0.7554 |
|
| 218 |
+
| 0.1544 | 6.7297 | 498 | 0.7521 |
|
| 219 |
+
| 0.1387 | 6.7703 | 501 | 0.7529 |
|
| 220 |
+
| 0.1253 | 6.8108 | 504 | 0.7529 |
|
| 221 |
+
| 0.1296 | 6.8514 | 507 | 0.7542 |
|
| 222 |
+
| 0.1094 | 6.8919 | 510 | 0.7516 |
|
| 223 |
+
| 0.1009 | 6.9324 | 513 | 0.7512 |
|
| 224 |
+
| 0.1871 | 6.9730 | 516 | 0.7526 |
|
| 225 |
+
| 0.1017 | 7.0135 | 519 | 0.7538 |
|
| 226 |
+
| 0.1536 | 7.0541 | 522 | 0.7529 |
|
| 227 |
+
| 0.0886 | 7.0946 | 525 | 0.7565 |
|
| 228 |
+
| 0.0983 | 7.1351 | 528 | 0.7576 |
|
| 229 |
+
| 0.084 | 7.1757 | 531 | 0.7586 |
|
| 230 |
+
| 0.099 | 7.2162 | 534 | 0.7564 |
|
| 231 |
+
| 0.1089 | 7.2568 | 537 | 0.7592 |
|
| 232 |
+
| 0.1145 | 7.2973 | 540 | 0.7612 |
|
| 233 |
+
| 0.1823 | 7.3378 | 543 | 0.7615 |
|
| 234 |
+
| 0.2784 | 7.3784 | 546 | 0.7602 |
|
| 235 |
+
| 0.0887 | 7.4189 | 549 | 0.7617 |
|
| 236 |
+
| 0.1133 | 7.4595 | 552 | 0.7640 |
|
| 237 |
+
| 0.1207 | 7.5 | 555 | 0.7630 |
|
| 238 |
+
| 0.0954 | 7.5405 | 558 | 0.7643 |
|
| 239 |
+
| 0.1135 | 7.5811 | 561 | 0.7629 |
|
| 240 |
+
| 0.096 | 7.6216 | 564 | 0.7637 |
|
| 241 |
+
| 0.1088 | 7.6622 | 567 | 0.7655 |
|
| 242 |
+
| 0.1628 | 7.7027 | 570 | 0.7655 |
|
| 243 |
+
| 0.1431 | 7.7432 | 573 | 0.7650 |
|
| 244 |
+
| 0.1034 | 7.7838 | 576 | 0.7639 |
|
| 245 |
+
| 0.181 | 7.8243 | 579 | 0.7637 |
|
| 246 |
+
| 0.062 | 7.8649 | 582 | 0.7649 |
|
| 247 |
+
| 0.0769 | 7.9054 | 585 | 0.7654 |
|
| 248 |
+
| 0.1951 | 7.9459 | 588 | 0.7647 |
|
| 249 |
+
| 0.1175 | 7.9865 | 591 | 0.7650 |
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
### Framework versions
|
| 253 |
+
|
| 254 |
+
- PEFT 0.13.2
|
| 255 |
+
- Transformers 4.46.0
|
| 256 |
+
- Pytorch 2.4.0
|
| 257 |
+
- Datasets 3.0.2
|
| 258 |
+
- Tokenizers 0.20.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 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": 0.05,
|
| 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 |
+
"down_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b036d3c4044bc3c7152cfdc35c1edc67b951d0c35baaea7351ca546fb5e6283
|
| 3 |
+
size 35237104
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 18 |
+
"pad_token": "<|endoftext|>"
|
| 19 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3511c9b326fec6a1b23dbf63767a672c911fbee5b2145ad0099a5bd8aff458b5
|
| 3 |
+
size 11421994
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|endoftext|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 300,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5d717faee84e567649c08b8e6fc776fbd52823ae864a482fe19d98642a27aca
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|