Model save
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -52,130 +52,130 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:--------:|:----:|:---------------:|
|
| 55 |
-
| No log | 0.8889 | 4 | 1.
|
| 56 |
-
| 2.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
|
| 174 |
|
| 175 |
### Framework versions
|
| 176 |
|
| 177 |
- PEFT 0.13.2
|
| 178 |
-
- Transformers 4.46.
|
| 179 |
-
- Pytorch 2.5.
|
| 180 |
- Datasets 3.0.2
|
| 181 |
- Tokenizers 0.20.1
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.3304
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:--------:|:----:|:---------------:|
|
| 55 |
+
| No log | 0.8889 | 4 | 1.6790 |
|
| 56 |
+
| 2.1272 | 1.8333 | 8 | 1.5754 |
|
| 57 |
+
| 1.8869 | 2.7778 | 12 | 1.4449 |
|
| 58 |
+
| 1.8458 | 3.9444 | 17 | 1.3113 |
|
| 59 |
+
| 1.5497 | 4.8889 | 21 | 1.2161 |
|
| 60 |
+
| 1.4996 | 5.8333 | 25 | 1.1479 |
|
| 61 |
+
| 1.4996 | 6.7778 | 29 | 1.0829 |
|
| 62 |
+
| 1.5 | 7.9444 | 34 | 1.0096 |
|
| 63 |
+
| 1.1576 | 8.8889 | 38 | 0.9470 |
|
| 64 |
+
| 1.1188 | 9.8333 | 42 | 0.9070 |
|
| 65 |
+
| 0.881 | 10.7778 | 46 | 0.8688 |
|
| 66 |
+
| 0.9199 | 11.9444 | 51 | 0.8224 |
|
| 67 |
+
| 0.7161 | 12.8889 | 55 | 0.7994 |
|
| 68 |
+
| 0.7161 | 13.8333 | 59 | 0.7957 |
|
| 69 |
+
| 0.7983 | 14.7778 | 63 | 0.7891 |
|
| 70 |
+
| 0.5833 | 15.9444 | 68 | 0.7692 |
|
| 71 |
+
| 0.5577 | 16.8889 | 72 | 0.7593 |
|
| 72 |
+
| 0.4911 | 17.8333 | 76 | 0.7867 |
|
| 73 |
+
| 0.4478 | 18.7778 | 80 | 0.8088 |
|
| 74 |
+
| 0.5181 | 19.9444 | 85 | 0.8089 |
|
| 75 |
+
| 0.5181 | 20.8889 | 89 | 0.7761 |
|
| 76 |
+
| 0.3977 | 21.8333 | 93 | 0.7940 |
|
| 77 |
+
| 0.3655 | 22.7778 | 97 | 0.8387 |
|
| 78 |
+
| 0.293 | 23.9444 | 102 | 0.8603 |
|
| 79 |
+
| 0.2978 | 24.8889 | 106 | 0.8603 |
|
| 80 |
+
| 0.2573 | 25.8333 | 110 | 0.8431 |
|
| 81 |
+
| 0.2573 | 26.7778 | 114 | 0.9431 |
|
| 82 |
+
| 0.2802 | 27.9444 | 119 | 0.9213 |
|
| 83 |
+
| 0.2116 | 28.8889 | 123 | 0.9327 |
|
| 84 |
+
| 0.208 | 29.8333 | 127 | 0.9562 |
|
| 85 |
+
| 0.2012 | 30.7778 | 131 | 0.9036 |
|
| 86 |
+
| 0.1807 | 31.9444 | 136 | 0.9352 |
|
| 87 |
+
| 0.1885 | 32.8889 | 140 | 1.0403 |
|
| 88 |
+
| 0.1885 | 33.8333 | 144 | 0.9444 |
|
| 89 |
+
| 0.1898 | 34.7778 | 148 | 0.9924 |
|
| 90 |
+
| 0.1504 | 35.9444 | 153 | 1.0616 |
|
| 91 |
+
| 0.14 | 36.8889 | 157 | 0.9799 |
|
| 92 |
+
| 0.1428 | 37.8333 | 161 | 1.0503 |
|
| 93 |
+
| 0.1174 | 38.7778 | 165 | 1.0565 |
|
| 94 |
+
| 0.1513 | 39.9444 | 170 | 1.0090 |
|
| 95 |
+
| 0.1513 | 40.8889 | 174 | 1.0892 |
|
| 96 |
+
| 0.1053 | 41.8333 | 178 | 1.0162 |
|
| 97 |
+
| 0.1056 | 42.7778 | 182 | 1.1173 |
|
| 98 |
+
| 0.1127 | 43.9444 | 187 | 1.0811 |
|
| 99 |
+
| 0.0927 | 44.8889 | 191 | 1.0970 |
|
| 100 |
+
| 0.0963 | 45.8333 | 195 | 1.0959 |
|
| 101 |
+
| 0.0963 | 46.7778 | 199 | 1.0603 |
|
| 102 |
+
| 0.1043 | 47.9444 | 204 | 1.1082 |
|
| 103 |
+
| 0.0845 | 48.8889 | 208 | 1.0794 |
|
| 104 |
+
| 0.0728 | 49.8333 | 212 | 1.1056 |
|
| 105 |
+
| 0.0779 | 50.7778 | 216 | 1.1265 |
|
| 106 |
+
| 0.0706 | 51.9444 | 221 | 1.1261 |
|
| 107 |
+
| 0.06 | 52.8889 | 225 | 1.1191 |
|
| 108 |
+
| 0.06 | 53.8333 | 229 | 1.1820 |
|
| 109 |
+
| 0.0692 | 54.7778 | 233 | 1.1651 |
|
| 110 |
+
| 0.0558 | 55.9444 | 238 | 1.1954 |
|
| 111 |
+
| 0.0529 | 56.8889 | 242 | 1.1271 |
|
| 112 |
+
| 0.054 | 57.8333 | 246 | 1.0981 |
|
| 113 |
+
| 0.0491 | 58.7778 | 250 | 1.1937 |
|
| 114 |
+
| 0.0588 | 59.9444 | 255 | 1.1734 |
|
| 115 |
+
| 0.0588 | 60.8889 | 259 | 1.2405 |
|
| 116 |
+
| 0.0435 | 61.8333 | 263 | 1.1687 |
|
| 117 |
+
| 0.0394 | 62.7778 | 267 | 1.1928 |
|
| 118 |
+
| 0.0446 | 63.9444 | 272 | 1.2214 |
|
| 119 |
+
| 0.0414 | 64.8889 | 276 | 1.2216 |
|
| 120 |
+
| 0.0378 | 65.8333 | 280 | 1.2238 |
|
| 121 |
+
| 0.0378 | 66.7778 | 284 | 1.2372 |
|
| 122 |
+
| 0.0455 | 67.9444 | 289 | 1.2214 |
|
| 123 |
+
| 0.0377 | 68.8889 | 293 | 1.2555 |
|
| 124 |
+
| 0.0327 | 69.8333 | 297 | 1.2370 |
|
| 125 |
+
| 0.033 | 70.7778 | 301 | 1.2383 |
|
| 126 |
+
| 0.0342 | 71.9444 | 306 | 1.2499 |
|
| 127 |
+
| 0.032 | 72.8889 | 310 | 1.2769 |
|
| 128 |
+
| 0.032 | 73.8333 | 314 | 1.2521 |
|
| 129 |
+
| 0.0389 | 74.7778 | 318 | 1.2544 |
|
| 130 |
+
| 0.0312 | 75.9444 | 323 | 1.2710 |
|
| 131 |
+
| 0.0294 | 76.8889 | 327 | 1.2853 |
|
| 132 |
+
| 0.0269 | 77.8333 | 331 | 1.2947 |
|
| 133 |
+
| 0.028 | 78.7778 | 335 | 1.3076 |
|
| 134 |
+
| 0.0334 | 79.9444 | 340 | 1.3095 |
|
| 135 |
+
| 0.0334 | 80.8889 | 344 | 1.2938 |
|
| 136 |
+
| 0.0257 | 81.8333 | 348 | 1.2813 |
|
| 137 |
+
| 0.0265 | 82.7778 | 352 | 1.2840 |
|
| 138 |
+
| 0.0262 | 83.9444 | 357 | 1.2902 |
|
| 139 |
+
| 0.0243 | 84.8889 | 361 | 1.3001 |
|
| 140 |
+
| 0.0232 | 85.8333 | 365 | 1.3042 |
|
| 141 |
+
| 0.0232 | 86.7778 | 369 | 1.3044 |
|
| 142 |
+
| 0.027 | 87.9444 | 374 | 1.2909 |
|
| 143 |
+
| 0.0224 | 88.8889 | 378 | 1.2925 |
|
| 144 |
+
| 0.0239 | 89.8333 | 382 | 1.2949 |
|
| 145 |
+
| 0.0221 | 90.7778 | 386 | 1.3046 |
|
| 146 |
+
| 0.0244 | 91.9444 | 391 | 1.3120 |
|
| 147 |
+
| 0.0256 | 92.8889 | 395 | 1.3179 |
|
| 148 |
+
| 0.0256 | 93.8333 | 399 | 1.3150 |
|
| 149 |
+
| 0.0276 | 94.7778 | 403 | 1.3069 |
|
| 150 |
+
| 0.0226 | 95.9444 | 408 | 1.2978 |
|
| 151 |
+
| 0.0279 | 96.8889 | 412 | 1.2995 |
|
| 152 |
+
| 0.0218 | 97.8333 | 416 | 1.3054 |
|
| 153 |
+
| 0.0224 | 98.7778 | 420 | 1.3163 |
|
| 154 |
+
| 0.0236 | 99.9444 | 425 | 1.3296 |
|
| 155 |
+
| 0.0236 | 100.8889 | 429 | 1.3317 |
|
| 156 |
+
| 0.021 | 101.8333 | 433 | 1.3305 |
|
| 157 |
+
| 0.0208 | 102.7778 | 437 | 1.3273 |
|
| 158 |
+
| 0.0205 | 103.9444 | 442 | 1.3253 |
|
| 159 |
+
| 0.0213 | 104.8889 | 446 | 1.3249 |
|
| 160 |
+
| 0.0208 | 105.8333 | 450 | 1.3257 |
|
| 161 |
+
| 0.0208 | 106.7778 | 454 | 1.3263 |
|
| 162 |
+
| 0.0221 | 107.9444 | 459 | 1.3271 |
|
| 163 |
+
| 0.0223 | 108.8889 | 463 | 1.3279 |
|
| 164 |
+
| 0.0194 | 109.8333 | 467 | 1.3291 |
|
| 165 |
+
| 0.0207 | 110.7778 | 471 | 1.3293 |
|
| 166 |
+
| 0.0211 | 111.9444 | 476 | 1.3296 |
|
| 167 |
+
| 0.0193 | 112.8889 | 480 | 1.3302 |
|
| 168 |
+
| 0.0193 | 113.8333 | 484 | 1.3301 |
|
| 169 |
+
| 0.0217 | 114.7778 | 488 | 1.3295 |
|
| 170 |
+
| 0.0201 | 115.9444 | 493 | 1.3301 |
|
| 171 |
+
| 0.0201 | 116.8889 | 497 | 1.3305 |
|
| 172 |
+
| 0.0201 | 117.6111 | 500 | 1.3304 |
|
| 173 |
|
| 174 |
|
| 175 |
### Framework versions
|
| 176 |
|
| 177 |
- PEFT 0.13.2
|
| 178 |
+
- Transformers 4.46.1
|
| 179 |
+
- Pytorch 2.5.1+cu124
|
| 180 |
- Datasets 3.0.2
|
| 181 |
- Tokenizers 0.20.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13648432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eed48fc26a68a7aee75f4ab77a1f6eb5a6d56cf3998aa80e75198812aa79109a
|
| 3 |
size 13648432
|
runs/Oct31_13-57-23_buda/events.out.tfevents.1730383046.buda.1.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5298e55c6e663c6c6f24eedbc23881fc017c61976bc1831bfbe39c294d2bef91
|
| 3 |
+
size 59322
|