<!-- 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. -->
islamic_qa
This model is a fine-tuned version of Huzaifa30/islamic_qa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6492
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 11 | 0.8716 |
| No log | 2.0 | 22 | 0.8629 |
| No log | 3.0 | 33 | 0.8406 |
| No log | 4.0 | 44 | 0.8342 |
| No log | 5.0 | 55 | 0.8217 |
| No log | 6.0 | 66 | 0.8047 |
| No log | 7.0 | 77 | 0.8063 |
| No log | 8.0 | 88 | 0.7846 |
| No log | 9.0 | 99 | 0.7831 |
| No log | 10.0 | 110 | 0.7685 |
| No log | 11.0 | 121 | 0.7595 |
| No log | 12.0 | 132 | 0.7517 |
| No log | 13.0 | 143 | 0.7529 |
| No log | 14.0 | 154 | 0.7423 |
| No log | 15.0 | 165 | 0.7344 |
| No log | 16.0 | 176 | 0.7237 |
| No log | 17.0 | 187 | 0.7227 |
| No log | 18.0 | 198 | 0.7251 |
| No log | 19.0 | 209 | 0.7246 |
| No log | 20.0 | 220 | 0.7082 |
| No log | 21.0 | 231 | 0.7089 |
| No log | 22.0 | 242 | 0.7010 |
| No log | 23.0 | 253 | 0.6895 |
| No log | 24.0 | 264 | 0.6912 |
| No log | 25.0 | 275 | 0.6979 |
| No log | 26.0 | 286 | 0.6846 |
| No log | 27.0 | 297 | 0.6810 |
| No log | 28.0 | 308 | 0.6859 |
| No log | 29.0 | 319 | 0.6761 |
| No log | 30.0 | 330 | 0.6775 |
| No log | 31.0 | 341 | 0.6696 |
| No log | 32.0 | 352 | 0.6762 |
| No log | 33.0 | 363 | 0.6744 |
| No log | 34.0 | 374 | 0.6746 |
| No log | 35.0 | 385 | 0.6771 |
| No log | 36.0 | 396 | 0.6701 |
| No log | 37.0 | 407 | 0.6696 |
| No log | 38.0 | 418 | 0.6654 |
| No log | 39.0 | 429 | 0.6702 |
| No log | 40.0 | 440 | 0.6668 |
| No log | 41.0 | 451 | 0.6529 |
| No log | 42.0 | 462 | 0.6717 |
| No log | 43.0 | 473 | 0.6556 |
| No log | 44.0 | 484 | 0.6567 |
| No log | 45.0 | 495 | 0.6649 |
| 0.4121 | 46.0 | 506 | 0.6584 |
| 0.4121 | 47.0 | 517 | 0.6611 |
| 0.4121 | 48.0 | 528 | 0.6642 |
| 0.4121 | 49.0 | 539 | 0.6542 |
| 0.4121 | 50.0 | 550 | 0.6446 |
| 0.4121 | 51.0 | 561 | 0.6651 |
| 0.4121 | 52.0 | 572 | 0.6551 |
| 0.4121 | 53.0 | 583 | 0.6597 |
| 0.4121 | 54.0 | 594 | 0.6528 |
| 0.4121 | 55.0 | 605 | 0.6578 |
| 0.4121 | 56.0 | 616 | 0.6662 |
| 0.4121 | 57.0 | 627 | 0.6525 |
| 0.4121 | 58.0 | 638 | 0.6537 |
| 0.4121 | 59.0 | 649 | 0.6553 |
| 0.4121 | 60.0 | 660 | 0.6510 |
| 0.4121 | 61.0 | 671 | 0.6544 |
| 0.4121 | 62.0 | 682 | 0.6411 |
| 0.4121 | 63.0 | 693 | 0.6448 |
| 0.4121 | 64.0 | 704 | 0.6430 |
| 0.4121 | 65.0 | 715 | 0.6468 |
| 0.4121 | 66.0 | 726 | 0.6345 |
| 0.4121 | 67.0 | 737 | 0.6615 |
| 0.4121 | 68.0 | 748 | 0.6547 |
| 0.4121 | 69.0 | 759 | 0.6509 |
| 0.4121 | 70.0 | 770 | 0.6446 |
| 0.4121 | 71.0 | 781 | 0.6456 |
| 0.4121 | 72.0 | 792 | 0.6389 |
| 0.4121 | 73.0 | 803 | 0.6486 |
| 0.4121 | 74.0 | 814 | 0.6497 |
| 0.4121 | 75.0 | 825 | 0.6506 |
| 0.4121 | 76.0 | 836 | 0.6510 |
| 0.4121 | 77.0 | 847 | 0.6460 |
| 0.4121 | 78.0 | 858 | 0.6423 |
| 0.4121 | 79.0 | 869 | 0.6457 |
| 0.4121 | 80.0 | 880 | 0.6559 |
| 0.4121 | 81.0 | 891 | 0.6558 |
| 0.4121 | 82.0 | 902 | 0.6422 |
| 0.4121 | 83.0 | 913 | 0.6525 |
| 0.4121 | 84.0 | 924 | 0.6528 |
| 0.4121 | 85.0 | 935 | 0.6499 |
| 0.4121 | 86.0 | 946 | 0.6633 |
| 0.4121 | 87.0 | 957 | 0.6512 |
| 0.4121 | 88.0 | 968 | 0.6543 |
| 0.4121 | 89.0 | 979 | 0.6541 |
| 0.4121 | 90.0 | 990 | 0.6480 |
| 0.1789 | 91.0 | 1001 | 0.6502 |
| 0.1789 | 92.0 | 1012 | 0.6447 |
| 0.1789 | 93.0 | 1023 | 0.6455 |
| 0.1789 | 94.0 | 1034 | 0.6530 |
| 0.1789 | 95.0 | 1045 | 0.6444 |
| 0.1789 | 96.0 | 1056 | 0.6457 |
| 0.1789 | 97.0 | 1067 | 0.6451 |
| 0.1789 | 98.0 | 1078 | 0.6507 |
| 0.1789 | 99.0 | 1089 | 0.6602 |
| 0.1789 | 100.0 | 1100 | 0.6560 |
| 0.1789 | 101.0 | 1111 | 0.6503 |
| 0.1789 | 102.0 | 1122 | 0.6408 |
| 0.1789 | 103.0 | 1133 | 0.6430 |
| 0.1789 | 104.0 | 1144 | 0.6476 |
| 0.1789 | 105.0 | 1155 | 0.6485 |
| 0.1789 | 106.0 | 1166 | 0.6489 |
| 0.1789 | 107.0 | 1177 | 0.6564 |
| 0.1789 | 108.0 | 1188 | 0.6537 |
| 0.1789 | 109.0 | 1199 | 0.6536 |
| 0.1789 | 110.0 | 1210 | 0.6539 |
| 0.1789 | 111.0 | 1221 | 0.6564 |
| 0.1789 | 112.0 | 1232 | 0.6531 |
| 0.1789 | 113.0 | 1243 | 0.6491 |
| 0.1789 | 114.0 | 1254 | 0.6519 |
| 0.1789 | 115.0 | 1265 | 0.6431 |
| 0.1789 | 116.0 | 1276 | 0.6437 |
| 0.1789 | 117.0 | 1287 | 0.6471 |
| 0.1789 | 118.0 | 1298 | 0.6370 |
| 0.1789 | 119.0 | 1309 | 0.6385 |
| 0.1789 | 120.0 | 1320 | 0.6473 |
| 0.1789 | 121.0 | 1331 | 0.6480 |
| 0.1789 | 122.0 | 1342 | 0.6427 |
| 0.1789 | 123.0 | 1353 | 0.6464 |
| 0.1789 | 124.0 | 1364 | 0.6486 |
| 0.1789 | 125.0 | 1375 | 0.6395 |
| 0.1789 | 126.0 | 1386 | 0.6452 |
| 0.1789 | 127.0 | 1397 | 0.6492 |
| 0.1789 | 128.0 | 1408 | 0.6501 |
| 0.1789 | 129.0 | 1419 | 0.6418 |
| 0.1789 | 130.0 | 1430 | 0.6353 |
| 0.1789 | 131.0 | 1441 | 0.6411 |
| 0.1789 | 132.0 | 1452 | 0.6477 |
| 0.1789 | 133.0 | 1463 | 0.6453 |
| 0.1789 | 134.0 | 1474 | 0.6445 |
| 0.1789 | 135.0 | 1485 | 0.6507 |
| 0.1789 | 136.0 | 1496 | 0.6519 |
| 0.1156 | 137.0 | 1507 | 0.6487 |
| 0.1156 | 138.0 | 1518 | 0.6491 |
| 0.1156 | 139.0 | 1529 | 0.6479 |
| 0.1156 | 140.0 | 1540 | 0.6495 |
| 0.1156 | 141.0 | 1551 | 0.6495 |
| 0.1156 | 142.0 | 1562 | 0.6532 |
| 0.1156 | 143.0 | 1573 | 0.6478 |
| 0.1156 | 144.0 | 1584 | 0.6444 |
| 0.1156 | 145.0 | 1595 | 0.6467 |
| 0.1156 | 146.0 | 1606 | 0.6491 |
| 0.1156 | 147.0 | 1617 | 0.6492 |
| 0.1156 | 148.0 | 1628 | 0.6506 |
| 0.1156 | 149.0 | 1639 | 0.6526 |
| 0.1156 | 150.0 | 1650 | 0.6514 |
| 0.1156 | 151.0 | 1661 | 0.6461 |
| 0.1156 | 152.0 | 1672 | 0.6470 |
| 0.1156 | 153.0 | 1683 | 0.6512 |
| 0.1156 | 154.0 | 1694 | 0.6531 |
| 0.1156 | 155.0 | 1705 | 0.6499 |
| 0.1156 | 156.0 | 1716 | 0.6459 |
| 0.1156 | 157.0 | 1727 | 0.6478 |
| 0.1156 | 158.0 | 1738 | 0.6493 |
| 0.1156 | 159.0 | 1749 | 0.6508 |
| 0.1156 | 160.0 | 1760 | 0.6526 |
| 0.1156 | 161.0 | 1771 | 0.6534 |
| 0.1156 | 162.0 | 1782 | 0.6525 |
| 0.1156 | 163.0 | 1793 | 0.6507 |
| 0.1156 | 164.0 | 1804 | 0.6510 |
| 0.1156 | 165.0 | 1815 | 0.6508 |
| 0.1156 | 166.0 | 1826 | 0.6496 |
| 0.1156 | 167.0 | 1837 | 0.6471 |
| 0.1156 | 168.0 | 1848 | 0.6458 |
| 0.1156 | 169.0 | 1859 | 0.6481 |
| 0.1156 | 170.0 | 1870 | 0.6498 |
| 0.1156 | 171.0 | 1881 | 0.6513 |
| 0.1156 | 172.0 | 1892 | 0.6507 |
| 0.1156 | 173.0 | 1903 | 0.6502 |
| 0.1156 | 174.0 | 1914 | 0.6488 |
| 0.1156 | 175.0 | 1925 | 0.6477 |
| 0.1156 | 176.0 | 1936 | 0.6465 |
| 0.1156 | 177.0 | 1947 | 0.6459 |
| 0.1156 | 178.0 | 1958 | 0.6456 |
| 0.1156 | 179.0 | 1969 | 0.6478 |
| 0.1156 | 180.0 | 1980 | 0.6464 |
| 0.1156 | 181.0 | 1991 | 0.6449 |
| 0.0913 | 182.0 | 2002 | 0.6453 |
| 0.0913 | 183.0 | 2013 | 0.6469 |
| 0.0913 | 184.0 | 2024 | 0.6485 |
| 0.0913 | 185.0 | 2035 | 0.6494 |
| 0.0913 | 186.0 | 2046 | 0.6505 |
| 0.0913 | 187.0 | 2057 | 0.6511 |
| 0.0913 | 188.0 | 2068 | 0.6499 |
| 0.0913 | 189.0 | 2079 | 0.6497 |
| 0.0913 | 190.0 | 2090 | 0.6494 |
| 0.0913 | 191.0 | 2101 | 0.6493 |
| 0.0913 | 192.0 | 2112 | 0.6495 |
| 0.0913 | 193.0 | 2123 | 0.6496 |
| 0.0913 | 194.0 | 2134 | 0.6493 |
| 0.0913 | 195.0 | 2145 | 0.6493 |
| 0.0913 | 196.0 | 2156 | 0.6493 |
| 0.0913 | 197.0 | 2167 | 0.6492 |
| 0.0913 | 198.0 | 2178 | 0.6493 |
| 0.0913 | 199.0 | 2189 | 0.6492 |
| 0.0913 | 200.0 | 2200 | 0.6492 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
