makhataei's picture
End of training
667a090 verified
|
raw
history blame
6.45 kB
metadata
license: mit
base_model: makhataei/qa-persian-mdeberta-v3-base-squad2
tags:
  - generated_from_trainer
model-index:
  - name: qa-persian-mdeberta-v3-base-squad2
    results: []

qa-persian-mdeberta-v3-base-squad2

This model is a fine-tuned version of makhataei/qa-persian-mdeberta-v3-base-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 5.1273

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: 0.00025
  • train_batch_size: 14
  • eval_batch_size: 14
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss
5.0854 1.0 17 5.1273
5.1065 2.0 34 5.1273
5.0881 3.0 51 5.1273
5.1056 4.0 68 5.1273
5.1107 5.0 85 5.1273
5.0724 6.0 102 5.1273
5.0891 7.0 119 5.1273
5.0691 8.0 136 5.1273
5.0689 9.0 153 5.1273
5.0618 10.0 170 5.1273
5.0565 11.0 187 5.1273
5.0732 12.0 204 5.1273
5.0843 13.0 221 5.1273
5.0913 14.0 238 5.1273
5.055 15.0 255 5.1273
5.0735 16.0 272 5.1273
5.0641 17.0 289 5.1273
5.0945 18.0 306 5.1273
5.0637 19.0 323 5.1273
5.044 20.0 340 5.1273
5.0616 21.0 357 5.1273
5.0715 22.0 374 5.1273
5.0534 23.0 391 5.1273
5.0366 24.0 408 5.1273
5.0709 25.0 425 5.1273
5.0834 26.0 442 5.1273
5.0775 27.0 459 5.1273
5.0743 28.0 476 5.1273
5.0764 29.0 493 5.1273
5.0855 30.0 510 5.1273
5.0812 31.0 527 5.1273
5.1056 32.0 544 5.1273
5.0634 33.0 561 5.1273
5.0813 34.0 578 5.1273
5.0738 35.0 595 5.1273
5.0872 36.0 612 5.1273
5.086 37.0 629 5.1273
5.089 38.0 646 5.1273
5.0688 39.0 663 5.1273
5.0906 40.0 680 5.1273
5.092 41.0 697 5.1273
5.0406 42.0 714 5.1273
5.1396 43.0 731 5.1273
5.1317 44.0 748 5.1273
5.1089 45.0 765 5.1273
5.1125 46.0 782 5.1273
5.1174 47.0 799 5.1273
5.0999 48.0 816 5.1273
5.1067 49.0 833 5.1273
5.087 50.0 850 5.1273
5.0999 51.0 867 5.1273
5.123 52.0 884 5.1273
5.116 53.0 901 5.1273
5.1266 54.0 918 5.1273
5.1083 55.0 935 5.1273
5.1197 56.0 952 5.1273
5.1307 57.0 969 5.1273
5.1091 58.0 986 5.1273
5.088 59.0 1003 5.1273
5.1205 60.0 1020 5.1273
5.1178 61.0 1037 5.1273
5.1255 62.0 1054 5.1273
5.1126 63.0 1071 5.1273
5.1031 64.0 1088 5.1273
5.1382 65.0 1105 5.1273
5.1203 66.0 1122 5.1273
5.124 67.0 1139 5.1273
5.1161 68.0 1156 5.1273
5.088 69.0 1173 5.1273
5.1241 70.0 1190 5.1273
5.1648 71.0 1207 5.1273
5.1385 72.0 1224 5.1273
5.1381 73.0 1241 5.1273
5.1307 74.0 1258 5.1273
5.132 75.0 1275 5.1273
5.1222 76.0 1292 5.1273
5.1202 77.0 1309 5.1273
5.1101 78.0 1326 5.1273
5.1218 79.0 1343 5.1273
5.1368 80.0 1360 5.1273
5.1222 81.0 1377 5.1273
5.1447 82.0 1394 5.1273
5.087 83.0 1411 5.1273
5.1395 84.0 1428 5.1273
5.1314 85.0 1445 5.1273
5.1362 86.0 1462 5.1273
5.1395 87.0 1479 5.1273
5.1158 88.0 1496 5.1273
5.144 89.0 1513 5.1273
5.1112 90.0 1530 5.1273
5.1371 91.0 1547 5.1273
5.1452 92.0 1564 5.1273
5.1237 93.0 1581 5.1273
5.1369 94.0 1598 5.1273
5.1346 95.0 1615 5.1273
5.1422 96.0 1632 5.1273
5.121 97.0 1649 5.1273
5.1251 98.0 1666 5.1273
5.1307 99.0 1683 5.1273
5.131 100.0 1700 5.1273

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0