Edit model card

qa-persian-bert-fa-base-uncased

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

  • Loss: 5.3355

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: 1.5625e-09
  • 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
5.5993 1.0 9 5.3355
5.6986 2.0 18 5.3355
5.6845 3.0 27 5.3355
5.6475 4.0 36 5.3355
5.7219 5.0 45 5.3355
5.6464 6.0 54 5.3355
5.5938 7.0 63 5.3355
5.577 8.0 72 5.3355
5.5841 9.0 81 5.3355
5.5863 10.0 90 5.3355
5.5771 11.0 99 5.3355
5.6131 12.0 108 5.3355
5.6692 13.0 117 5.3355
5.7031 14.0 126 5.3355
5.6995 15.0 135 5.3355
5.6724 16.0 144 5.3355
5.7379 17.0 153 5.3355
5.6687 18.0 162 5.3355
5.7009 19.0 171 5.3355
5.6232 20.0 180 5.3355
5.6514 21.0 189 5.3355
5.6814 22.0 198 5.3355
5.6305 23.0 207 5.3355
5.7508 24.0 216 5.3355
5.6747 25.0 225 5.3355
5.6642 26.0 234 5.3355
5.6913 27.0 243 5.3355
5.673 28.0 252 5.3355
5.6222 29.0 261 5.3355
5.6194 30.0 270 5.3355
5.6944 31.0 279 5.3355
5.6899 32.0 288 5.3355
5.6165 33.0 297 5.3355
5.6643 34.0 306 5.3355
5.7039 35.0 315 5.3355
5.6704 36.0 324 5.3355
5.694 37.0 333 5.3355
5.6058 38.0 342 5.3355
5.5774 39.0 351 5.3355
5.5987 40.0 360 5.3355
5.6706 41.0 369 5.3355
5.644 42.0 378 5.3355
5.6432 43.0 387 5.3355
5.6055 44.0 396 5.3355
5.6086 45.0 405 5.3355
5.738 46.0 414 5.3355
5.6526 47.0 423 5.3355
5.6566 48.0 432 5.3355
5.6381 49.0 441 5.3355
5.7056 50.0 450 5.3355
5.6693 51.0 459 5.3355
5.6042 52.0 468 5.3355
5.6551 53.0 477 5.3355
5.5851 54.0 486 5.3355
5.6209 55.0 495 5.3355
5.6143 56.0 504 5.3355
5.6426 57.0 513 5.3355
5.589 58.0 522 5.3355
5.6143 59.0 531 5.3355
5.6736 60.0 540 5.3355
5.6754 61.0 549 5.3355
5.6884 62.0 558 5.3355
5.677 63.0 567 5.3355
5.6157 64.0 576 5.3355
5.618 65.0 585 5.3355
5.678 66.0 594 5.3355
5.6859 67.0 603 5.3355
5.6751 68.0 612 5.3355
5.5911 69.0 621 5.3355
5.66 70.0 630 5.3355
5.7322 71.0 639 5.3355
5.6169 72.0 648 5.3355
5.6718 73.0 657 5.3355
5.6933 74.0 666 5.3355
5.5852 75.0 675 5.3355
5.5871 76.0 684 5.3355
5.6518 77.0 693 5.3355
5.6022 78.0 702 5.3355
5.6427 79.0 711 5.3355
5.639 80.0 720 5.3355
5.6559 81.0 729 5.3355
5.6959 82.0 738 5.3355
5.6081 83.0 747 5.3355
5.6185 84.0 756 5.3355
5.638 85.0 765 5.3355
5.6206 86.0 774 5.3355
5.7414 87.0 783 5.3355
5.7041 88.0 792 5.3355
5.6389 89.0 801 5.3355
5.6339 90.0 810 5.3355
5.6446 91.0 819 5.3355
5.6303 92.0 828 5.3355
5.6814 93.0 837 5.3355
5.6435 94.0 846 5.3355
5.6822 95.0 855 5.3355
5.6318 96.0 864 5.3355
5.6404 97.0 873 5.3355
5.6277 98.0 882 5.3355
5.639 99.0 891 5.3355
5.6655 100.0 900 5.3355

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
1
Safetensors
Model size
162M params
Tensor type
F32

Finetuned from