|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: calculator_model_test |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# calculator_model_test |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0317 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.001 |
|
- train_batch_size: 512 |
|
- eval_batch_size: 512 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 200 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.6147 | 1.0 | 6 | 3.0415 | |
|
| 2.585 | 2.0 | 12 | 2.0622 | |
|
| 1.899 | 3.0 | 18 | 1.6836 | |
|
| 1.6095 | 4.0 | 24 | 1.6248 | |
|
| 1.5731 | 5.0 | 30 | 1.5728 | |
|
| 1.5407 | 6.0 | 36 | 1.5594 | |
|
| 1.5353 | 7.0 | 42 | 1.5163 | |
|
| 1.4873 | 8.0 | 48 | 1.4470 | |
|
| 1.4322 | 9.0 | 54 | 1.4274 | |
|
| 1.3743 | 10.0 | 60 | 1.3462 | |
|
| 1.3009 | 11.0 | 66 | 1.2124 | |
|
| 1.1918 | 12.0 | 72 | 1.1226 | |
|
| 1.1449 | 13.0 | 78 | 1.1215 | |
|
| 1.0914 | 14.0 | 84 | 1.0471 | |
|
| 1.0285 | 15.0 | 90 | 0.9795 | |
|
| 1.0093 | 16.0 | 96 | 1.0062 | |
|
| 0.9957 | 17.0 | 102 | 0.9296 | |
|
| 0.944 | 18.0 | 108 | 0.9268 | |
|
| 0.9194 | 19.0 | 114 | 0.9417 | |
|
| 0.9014 | 20.0 | 120 | 0.8415 | |
|
| 0.8789 | 21.0 | 126 | 0.7764 | |
|
| 0.8155 | 22.0 | 132 | 0.7639 | |
|
| 0.8593 | 23.0 | 138 | 0.8127 | |
|
| 0.836 | 24.0 | 144 | 0.7397 | |
|
| 0.7613 | 25.0 | 150 | 0.7067 | |
|
| 0.7818 | 26.0 | 156 | 0.7217 | |
|
| 0.7702 | 27.0 | 162 | 0.7128 | |
|
| 0.7376 | 28.0 | 168 | 0.7242 | |
|
| 0.8006 | 29.0 | 174 | 0.7117 | |
|
| 0.7561 | 30.0 | 180 | 0.6767 | |
|
| 0.7185 | 31.0 | 186 | 0.6828 | |
|
| 0.7055 | 32.0 | 192 | 0.6215 | |
|
| 0.6967 | 33.0 | 198 | 0.6766 | |
|
| 0.7193 | 34.0 | 204 | 0.6238 | |
|
| 0.6791 | 35.0 | 210 | 0.5900 | |
|
| 0.6741 | 36.0 | 216 | 0.6307 | |
|
| 0.663 | 37.0 | 222 | 0.6012 | |
|
| 0.6326 | 38.0 | 228 | 0.5944 | |
|
| 0.6041 | 39.0 | 234 | 0.5459 | |
|
| 0.617 | 40.0 | 240 | 0.5786 | |
|
| 0.6369 | 41.0 | 246 | 0.5896 | |
|
| 0.6243 | 42.0 | 252 | 0.5446 | |
|
| 0.5921 | 43.0 | 258 | 0.4864 | |
|
| 0.5529 | 44.0 | 264 | 0.5561 | |
|
| 0.5757 | 45.0 | 270 | 0.5783 | |
|
| 0.5919 | 46.0 | 276 | 0.5235 | |
|
| 0.5509 | 47.0 | 282 | 0.4525 | |
|
| 0.5229 | 48.0 | 288 | 0.5007 | |
|
| 0.5871 | 49.0 | 294 | 0.5009 | |
|
| 0.5793 | 50.0 | 300 | 0.5431 | |
|
| 0.5922 | 51.0 | 306 | 0.5404 | |
|
| 0.5539 | 52.0 | 312 | 0.5386 | |
|
| 0.5785 | 53.0 | 318 | 0.4697 | |
|
| 0.5528 | 54.0 | 324 | 0.5061 | |
|
| 0.5047 | 55.0 | 330 | 0.4249 | |
|
| 0.475 | 56.0 | 336 | 0.4206 | |
|
| 0.5236 | 57.0 | 342 | 0.5689 | |
|
| 0.576 | 58.0 | 348 | 0.4258 | |
|
| 0.4862 | 59.0 | 354 | 0.4070 | |
|
| 0.4946 | 60.0 | 360 | 0.4136 | |
|
| 0.4527 | 61.0 | 366 | 0.3848 | |
|
| 0.4522 | 62.0 | 372 | 0.4288 | |
|
| 0.5087 | 63.0 | 378 | 0.5660 | |
|
| 0.5559 | 64.0 | 384 | 0.5371 | |
|
| 0.5153 | 65.0 | 390 | 0.4595 | |
|
| 0.4503 | 66.0 | 396 | 0.3648 | |
|
| 0.4191 | 67.0 | 402 | 0.3787 | |
|
| 0.4522 | 68.0 | 408 | 0.3469 | |
|
| 0.4096 | 69.0 | 414 | 0.3622 | |
|
| 0.4502 | 70.0 | 420 | 0.3613 | |
|
| 0.4138 | 71.0 | 426 | 0.3700 | |
|
| 0.3896 | 72.0 | 432 | 0.3920 | |
|
| 0.4271 | 73.0 | 438 | 0.3354 | |
|
| 0.4107 | 74.0 | 444 | 0.3193 | |
|
| 0.391 | 75.0 | 450 | 0.3352 | |
|
| 0.373 | 76.0 | 456 | 0.3818 | |
|
| 0.4296 | 77.0 | 462 | 0.3238 | |
|
| 0.3812 | 78.0 | 468 | 0.3337 | |
|
| 0.3756 | 79.0 | 474 | 0.3105 | |
|
| 0.3579 | 80.0 | 480 | 0.3433 | |
|
| 0.4325 | 81.0 | 486 | 0.3103 | |
|
| 0.356 | 82.0 | 492 | 0.3060 | |
|
| 0.3467 | 83.0 | 498 | 0.3780 | |
|
| 0.3922 | 84.0 | 504 | 0.2863 | |
|
| 0.3457 | 85.0 | 510 | 0.2865 | |
|
| 0.3755 | 86.0 | 516 | 0.3041 | |
|
| 0.3319 | 87.0 | 522 | 0.2777 | |
|
| 0.3359 | 88.0 | 528 | 0.3803 | |
|
| 0.4192 | 89.0 | 534 | 0.3473 | |
|
| 0.3941 | 90.0 | 540 | 0.3745 | |
|
| 0.3991 | 91.0 | 546 | 0.3331 | |
|
| 0.3489 | 92.0 | 552 | 0.3579 | |
|
| 0.3352 | 93.0 | 558 | 0.2947 | |
|
| 0.3202 | 94.0 | 564 | 0.2416 | |
|
| 0.3339 | 95.0 | 570 | 0.3635 | |
|
| 0.4108 | 96.0 | 576 | 0.2779 | |
|
| 0.3827 | 97.0 | 582 | 0.2846 | |
|
| 0.3559 | 98.0 | 588 | 0.2754 | |
|
| 0.2985 | 99.0 | 594 | 0.2107 | |
|
| 0.264 | 100.0 | 600 | 0.1958 | |
|
| 0.2807 | 101.0 | 606 | 0.2028 | |
|
| 0.2861 | 102.0 | 612 | 0.2034 | |
|
| 0.2661 | 103.0 | 618 | 0.1979 | |
|
| 0.264 | 104.0 | 624 | 0.2134 | |
|
| 0.2747 | 105.0 | 630 | 0.1754 | |
|
| 0.2785 | 106.0 | 636 | 0.2329 | |
|
| 0.2656 | 107.0 | 642 | 0.1934 | |
|
| 0.2505 | 108.0 | 648 | 0.2213 | |
|
| 0.2572 | 109.0 | 654 | 0.2313 | |
|
| 0.2929 | 110.0 | 660 | 0.2308 | |
|
| 0.2419 | 111.0 | 666 | 0.1780 | |
|
| 0.239 | 112.0 | 672 | 0.1694 | |
|
| 0.2279 | 113.0 | 678 | 0.1580 | |
|
| 0.2528 | 114.0 | 684 | 0.3002 | |
|
| 0.3297 | 115.0 | 690 | 0.2676 | |
|
| 0.3147 | 116.0 | 696 | 0.3287 | |
|
| 0.2826 | 117.0 | 702 | 0.1475 | |
|
| 0.2033 | 118.0 | 708 | 0.1359 | |
|
| 0.1938 | 119.0 | 714 | 0.1592 | |
|
| 0.2105 | 120.0 | 720 | 0.1696 | |
|
| 0.2196 | 121.0 | 726 | 0.1532 | |
|
| 0.2102 | 122.0 | 732 | 0.1157 | |
|
| 0.2014 | 123.0 | 738 | 0.1835 | |
|
| 0.2505 | 124.0 | 744 | 0.1851 | |
|
| 0.2411 | 125.0 | 750 | 0.2881 | |
|
| 0.2353 | 126.0 | 756 | 0.1911 | |
|
| 0.2268 | 127.0 | 762 | 0.1874 | |
|
| 0.2024 | 128.0 | 768 | 0.1613 | |
|
| 0.2046 | 129.0 | 774 | 0.1938 | |
|
| 0.199 | 130.0 | 780 | 0.1129 | |
|
| 0.1703 | 131.0 | 786 | 0.1511 | |
|
| 0.1924 | 132.0 | 792 | 0.1744 | |
|
| 0.1854 | 133.0 | 798 | 0.1238 | |
|
| 0.1632 | 134.0 | 804 | 0.1050 | |
|
| 0.1589 | 135.0 | 810 | 0.1316 | |
|
| 0.1787 | 136.0 | 816 | 0.0895 | |
|
| 0.1658 | 137.0 | 822 | 0.0836 | |
|
| 0.141 | 138.0 | 828 | 0.1087 | |
|
| 0.1671 | 139.0 | 834 | 0.1068 | |
|
| 0.1557 | 140.0 | 840 | 0.0800 | |
|
| 0.1488 | 141.0 | 846 | 0.1277 | |
|
| 0.1709 | 142.0 | 852 | 0.1126 | |
|
| 0.1499 | 143.0 | 858 | 0.0913 | |
|
| 0.1597 | 144.0 | 864 | 0.0829 | |
|
| 0.1314 | 145.0 | 870 | 0.0762 | |
|
| 0.1501 | 146.0 | 876 | 0.0897 | |
|
| 0.156 | 147.0 | 882 | 0.0902 | |
|
| 0.1482 | 148.0 | 888 | 0.0903 | |
|
| 0.1401 | 149.0 | 894 | 0.0749 | |
|
| 0.1322 | 150.0 | 900 | 0.0781 | |
|
| 0.1309 | 151.0 | 906 | 0.0719 | |
|
| 0.1326 | 152.0 | 912 | 0.0691 | |
|
| 0.1311 | 153.0 | 918 | 0.0701 | |
|
| 0.1202 | 154.0 | 924 | 0.0742 | |
|
| 0.1258 | 155.0 | 930 | 0.0728 | |
|
| 0.1183 | 156.0 | 936 | 0.0566 | |
|
| 0.1181 | 157.0 | 942 | 0.0541 | |
|
| 0.1137 | 158.0 | 948 | 0.0662 | |
|
| 0.1061 | 159.0 | 954 | 0.0662 | |
|
| 0.1121 | 160.0 | 960 | 0.0628 | |
|
| 0.1038 | 161.0 | 966 | 0.0609 | |
|
| 0.1135 | 162.0 | 972 | 0.0728 | |
|
| 0.1317 | 163.0 | 978 | 0.0785 | |
|
| 0.1149 | 164.0 | 984 | 0.0753 | |
|
| 0.1111 | 165.0 | 990 | 0.0647 | |
|
| 0.0926 | 166.0 | 996 | 0.0592 | |
|
| 0.0931 | 167.0 | 1002 | 0.0554 | |
|
| 0.0865 | 168.0 | 1008 | 0.0480 | |
|
| 0.0881 | 169.0 | 1014 | 0.0498 | |
|
| 0.0932 | 170.0 | 1020 | 0.0524 | |
|
| 0.0934 | 171.0 | 1026 | 0.0629 | |
|
| 0.1054 | 172.0 | 1032 | 0.0561 | |
|
| 0.0933 | 173.0 | 1038 | 0.0422 | |
|
| 0.0812 | 174.0 | 1044 | 0.0605 | |
|
| 0.0953 | 175.0 | 1050 | 0.0485 | |
|
| 0.0963 | 176.0 | 1056 | 0.0394 | |
|
| 0.0731 | 177.0 | 1062 | 0.0378 | |
|
| 0.0758 | 178.0 | 1068 | 0.0394 | |
|
| 0.0703 | 179.0 | 1074 | 0.0406 | |
|
| 0.0756 | 180.0 | 1080 | 0.0427 | |
|
| 0.0812 | 181.0 | 1086 | 0.0538 | |
|
| 0.0842 | 182.0 | 1092 | 0.0434 | |
|
| 0.0773 | 183.0 | 1098 | 0.0439 | |
|
| 0.073 | 184.0 | 1104 | 0.0379 | |
|
| 0.0707 | 185.0 | 1110 | 0.0422 | |
|
| 0.0749 | 186.0 | 1116 | 0.0420 | |
|
| 0.0746 | 187.0 | 1122 | 0.0388 | |
|
| 0.068 | 188.0 | 1128 | 0.0386 | |
|
| 0.0654 | 189.0 | 1134 | 0.0378 | |
|
| 0.0647 | 190.0 | 1140 | 0.0335 | |
|
| 0.0629 | 191.0 | 1146 | 0.0402 | |
|
| 0.0642 | 192.0 | 1152 | 0.0344 | |
|
| 0.063 | 193.0 | 1158 | 0.0374 | |
|
| 0.0631 | 194.0 | 1164 | 0.0321 | |
|
| 0.0605 | 195.0 | 1170 | 0.0356 | |
|
| 0.065 | 196.0 | 1176 | 0.0334 | |
|
| 0.0591 | 197.0 | 1182 | 0.0321 | |
|
| 0.0558 | 198.0 | 1188 | 0.0317 | |
|
| 0.0596 | 199.0 | 1194 | 0.0316 | |
|
| 0.06 | 200.0 | 1200 | 0.0317 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
