MayBashendy's picture
End of training
4a21291 verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_task1_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8986
  • Qwk: 0.6716
  • Mse: 0.8986
  • Rmse: 0.9479

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: 100

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0377 2 6.8336 0.0239 6.8336 2.6141
No log 0.0755 4 4.6079 0.0556 4.6079 2.1466
No log 0.1132 6 2.8363 0.0387 2.8363 1.6841
No log 0.1509 8 2.3530 0.1135 2.3530 1.5340
No log 0.1887 10 2.0638 0.1440 2.0638 1.4366
No log 0.2264 12 1.8715 0.1835 1.8715 1.3680
No log 0.2642 14 2.0450 0.0870 2.0450 1.4301
No log 0.3019 16 1.9806 0.0734 1.9806 1.4073
No log 0.3396 18 1.8652 0.0952 1.8652 1.3657
No log 0.3774 20 1.5255 0.2222 1.5255 1.2351
No log 0.4151 22 1.4444 0.3036 1.4444 1.2018
No log 0.4528 24 1.4255 0.3186 1.4255 1.1939
No log 0.4906 26 1.4486 0.2593 1.4486 1.2036
No log 0.5283 28 1.4119 0.1982 1.4119 1.1882
No log 0.5660 30 1.6407 0.3577 1.6407 1.2809
No log 0.6038 32 1.6525 0.4194 1.6525 1.2855
No log 0.6415 34 1.4542 0.2759 1.4542 1.2059
No log 0.6792 36 1.3854 0.2385 1.3854 1.1770
No log 0.7170 38 1.4424 0.2569 1.4424 1.2010
No log 0.7547 40 1.7129 0.1802 1.7129 1.3088
No log 0.7925 42 1.8041 0.1982 1.8041 1.3432
No log 0.8302 44 1.5691 0.2679 1.5691 1.2526
No log 0.8679 46 1.4835 0.4882 1.4835 1.2180
No log 0.9057 48 1.4191 0.4603 1.4191 1.1912
No log 0.9434 50 1.2457 0.4874 1.2457 1.1161
No log 0.9811 52 1.2068 0.3571 1.2068 1.0986
No log 1.0189 54 1.3216 0.4833 1.3216 1.1496
No log 1.0566 56 1.2704 0.4833 1.2704 1.1271
No log 1.0943 58 1.1229 0.4538 1.1229 1.0597
No log 1.1321 60 0.9575 0.5203 0.9575 0.9785
No log 1.1698 62 0.9375 0.6154 0.9375 0.9683
No log 1.2075 64 0.9150 0.6269 0.9150 0.9565
No log 1.2453 66 0.9310 0.6269 0.9310 0.9649
No log 1.2830 68 0.9736 0.5970 0.9736 0.9867
No log 1.3208 70 0.9445 0.5714 0.9445 0.9718
No log 1.3585 72 0.9571 0.6119 0.9571 0.9783
No log 1.3962 74 0.9984 0.5692 0.9984 0.9992
No log 1.4340 76 1.0484 0.5344 1.0484 1.0239
No log 1.4717 78 1.0769 0.4889 1.0769 1.0378
No log 1.5094 80 1.0845 0.5324 1.0845 1.0414
No log 1.5472 82 0.9692 0.5797 0.9692 0.9845
No log 1.5849 84 0.9220 0.6 0.9220 0.9602
No log 1.6226 86 0.9620 0.6154 0.9620 0.9808
No log 1.6604 88 0.9848 0.5846 0.9848 0.9924
No log 1.6981 90 0.9777 0.5909 0.9777 0.9888
No log 1.7358 92 0.9280 0.5909 0.9280 0.9633
No log 1.7736 94 0.9945 0.6331 0.9945 0.9973
No log 1.8113 96 1.0484 0.6216 1.0484 1.0239
No log 1.8491 98 1.1611 0.5638 1.1611 1.0775
No log 1.8868 100 0.9956 0.5899 0.9956 0.9978
No log 1.9245 102 0.8869 0.6176 0.8869 0.9417
No log 1.9623 104 0.8645 0.6714 0.8645 0.9298
No log 2.0 106 0.8318 0.6619 0.8318 0.9120
No log 2.0377 108 0.8493 0.6853 0.8493 0.9216
No log 2.0755 110 0.9244 0.6809 0.9244 0.9614
No log 2.1132 112 0.9348 0.6522 0.9348 0.9669
No log 2.1509 114 0.9045 0.6370 0.9045 0.9510
No log 2.1887 116 0.8914 0.6892 0.8914 0.9441
No log 2.2264 118 0.9141 0.7143 0.9141 0.9561
No log 2.2642 120 0.8351 0.7368 0.8351 0.9138
No log 2.3019 122 0.7099 0.7310 0.7099 0.8425
No log 2.3396 124 0.7177 0.7172 0.7177 0.8471
No log 2.3774 126 0.7474 0.7285 0.7474 0.8645
No log 2.4151 128 0.8889 0.6982 0.8889 0.9428
No log 2.4528 130 0.9288 0.6625 0.9288 0.9637
No log 2.4906 132 0.9707 0.6627 0.9707 0.9852
No log 2.5283 134 0.8140 0.7067 0.8140 0.9022
No log 2.5660 136 0.7611 0.6944 0.7611 0.8724
No log 2.6038 138 0.7756 0.6667 0.7756 0.8807
No log 2.6415 140 0.8195 0.6667 0.8195 0.9053
No log 2.6792 142 0.9074 0.6621 0.9074 0.9526
No log 2.7170 144 1.1160 0.6323 1.1160 1.0564
No log 2.7547 146 1.1822 0.5714 1.1822 1.0873
No log 2.7925 148 1.3972 0.3594 1.3972 1.1820
No log 2.8302 150 1.2934 0.3780 1.2934 1.1373
No log 2.8679 152 1.0633 0.5385 1.0633 1.0312
No log 2.9057 154 0.9557 0.6710 0.9557 0.9776
No log 2.9434 156 1.2332 0.6257 1.2332 1.1105
No log 2.9811 158 1.2114 0.6667 1.2114 1.1006
No log 3.0189 160 1.1547 0.6778 1.1547 1.0746
No log 3.0566 162 0.8135 0.7215 0.8135 0.9019
No log 3.0943 164 0.6595 0.7338 0.6595 0.8121
No log 3.1321 166 0.6845 0.7101 0.6845 0.8273
No log 3.1698 168 0.6624 0.7273 0.6624 0.8139
No log 3.2075 170 0.8334 0.6711 0.8334 0.9129
No log 3.2453 172 1.2079 0.6173 1.2079 1.0991
No log 3.2830 174 1.3593 0.6118 1.3593 1.1659
No log 3.3208 176 1.2144 0.6625 1.2144 1.1020
No log 3.3585 178 0.8811 0.6383 0.8811 0.9387
No log 3.3962 180 0.7589 0.6364 0.7589 0.8712
No log 3.4340 182 0.7043 0.6519 0.7043 0.8392
No log 3.4717 184 0.7591 0.6857 0.7591 0.8712
No log 3.5094 186 0.8984 0.6800 0.8984 0.9478
No log 3.5472 188 0.8808 0.6471 0.8808 0.9385
No log 3.5849 190 0.8018 0.6765 0.8018 0.8954
No log 3.6226 192 0.7457 0.6466 0.7457 0.8636
No log 3.6604 194 0.7684 0.6471 0.7684 0.8766
No log 3.6981 196 0.8242 0.6763 0.8242 0.9079
No log 3.7358 198 0.8902 0.6711 0.8902 0.9435
No log 3.7736 200 1.0125 0.6707 1.0125 1.0062
No log 3.8113 202 0.9837 0.6821 0.9837 0.9918
No log 3.8491 204 0.7932 0.7172 0.7932 0.8906
No log 3.8868 206 0.7309 0.7092 0.7309 0.8549
No log 3.9245 208 0.8029 0.6471 0.8029 0.8961
No log 3.9623 210 0.8607 0.6667 0.8607 0.9277
No log 4.0 212 0.8297 0.6667 0.8297 0.9109
No log 4.0377 214 0.7277 0.6715 0.7277 0.8530
No log 4.0755 216 0.7034 0.6950 0.7034 0.8387
No log 4.1132 218 0.7718 0.6759 0.7718 0.8785
No log 4.1509 220 0.8798 0.7108 0.8798 0.9380
No log 4.1887 222 0.8868 0.6946 0.8868 0.9417
No log 4.2264 224 0.7597 0.6980 0.7597 0.8716
No log 4.2642 226 0.7746 0.7133 0.7746 0.8801
No log 4.3019 228 0.8425 0.6575 0.8425 0.9179
No log 4.3396 230 1.0809 0.6296 1.0809 1.0397
No log 4.3774 232 1.3598 0.6522 1.3598 1.1661
No log 4.4151 234 1.2569 0.6433 1.2569 1.1211
No log 4.4528 236 0.9505 0.6667 0.9505 0.9749
No log 4.4906 238 0.7840 0.6861 0.7840 0.8854
No log 4.5283 240 0.7841 0.6861 0.7841 0.8855
No log 4.5660 242 0.9509 0.6581 0.9509 0.9751
No log 4.6038 244 1.2951 0.5868 1.2951 1.1380
No log 4.6415 246 1.3347 0.5965 1.3347 1.1553
No log 4.6792 248 1.1121 0.5897 1.1121 1.0546
No log 4.7170 250 1.0334 0.6074 1.0334 1.0166
No log 4.7547 252 0.9782 0.6418 0.9782 0.9890
No log 4.7925 254 1.0188 0.6176 1.0188 1.0094
No log 4.8302 256 1.1525 0.5672 1.1525 1.0736
No log 4.8679 258 1.2171 0.5695 1.2171 1.1032
No log 4.9057 260 1.1385 0.5695 1.1385 1.0670
No log 4.9434 262 1.0634 0.6104 1.0634 1.0312
No log 4.9811 264 0.9573 0.6286 0.9573 0.9784
No log 5.0189 266 0.8125 0.6567 0.8125 0.9014
No log 5.0566 268 0.7420 0.7101 0.7420 0.8614
No log 5.0943 270 0.7387 0.7015 0.7387 0.8595
No log 5.1321 272 0.7526 0.6917 0.7526 0.8675
No log 5.1698 274 0.8564 0.6471 0.8564 0.9254
No log 5.2075 276 1.0412 0.5693 1.0412 1.0204
No log 5.2453 278 1.1000 0.5972 1.1000 1.0488
No log 5.2830 280 0.9768 0.6377 0.9768 0.9883
No log 5.3208 282 0.9044 0.6418 0.9044 0.9510
No log 5.3585 284 0.9572 0.6165 0.9572 0.9784
No log 5.3962 286 1.0218 0.5735 1.0218 1.0108
No log 5.4340 288 1.1154 0.5507 1.1154 1.0561
No log 5.4717 290 1.1345 0.5694 1.1345 1.0651
No log 5.5094 292 1.0540 0.5735 1.0540 1.0267
No log 5.5472 294 0.9416 0.5970 0.9416 0.9704
No log 5.5849 296 0.8498 0.6418 0.8498 0.9219
No log 5.6226 298 0.8061 0.6667 0.8061 0.8978
No log 5.6604 300 0.8083 0.6667 0.8083 0.8991
No log 5.6981 302 0.8750 0.6331 0.8750 0.9354
No log 5.7358 304 0.9293 0.6575 0.9293 0.9640
No log 5.7736 306 0.9401 0.6803 0.9401 0.9696
No log 5.8113 308 0.8930 0.6853 0.8930 0.9450
No log 5.8491 310 0.7649 0.7007 0.7649 0.8746
No log 5.8868 312 0.7507 0.7111 0.7507 0.8664
No log 5.9245 314 0.8039 0.6912 0.8039 0.8966
No log 5.9623 316 0.8267 0.6667 0.8267 0.9092
No log 6.0 318 0.8795 0.6618 0.8795 0.9378
No log 6.0377 320 0.9848 0.6582 0.9848 0.9924
No log 6.0755 322 0.9207 0.7030 0.9207 0.9596
No log 6.1132 324 0.8497 0.6957 0.8497 0.9218
No log 6.1509 326 0.8506 0.6835 0.8506 0.9223
No log 6.1887 328 0.8143 0.6483 0.8143 0.9024
No log 6.2264 330 0.8050 0.6525 0.8050 0.8972
No log 6.2642 332 0.8688 0.6667 0.8688 0.9321
No log 6.3019 334 0.8858 0.7117 0.8858 0.9412
No log 6.3396 336 0.9488 0.7093 0.9488 0.9741
No log 6.3774 338 0.8771 0.7205 0.8771 0.9366
No log 6.4151 340 0.8161 0.6761 0.8161 0.9034
No log 6.4528 342 0.8117 0.6412 0.8117 0.9009
No log 6.4906 344 0.8725 0.6515 0.8725 0.9341
No log 6.5283 346 0.9835 0.6107 0.9835 0.9917
No log 6.5660 348 1.0128 0.6061 1.0128 1.0064
No log 6.6038 350 0.9292 0.6667 0.9292 0.9639
No log 6.6415 352 0.8021 0.6767 0.8021 0.8956
No log 6.6792 354 0.7683 0.6767 0.7683 0.8765
No log 6.7170 356 0.8123 0.6812 0.8123 0.9013
No log 6.7547 358 0.9311 0.6752 0.9311 0.9649
No log 6.7925 360 1.0344 0.6706 1.0344 1.0170
No log 6.8302 362 1.0467 0.6706 1.0467 1.0231
No log 6.8679 364 0.8773 0.6667 0.8773 0.9366
No log 6.9057 366 0.8040 0.6569 0.8040 0.8967
No log 6.9434 368 0.8402 0.6569 0.8402 0.9166
No log 6.9811 370 0.8807 0.6618 0.8807 0.9384
No log 7.0189 372 0.8953 0.6618 0.8953 0.9462
No log 7.0566 374 0.8607 0.6618 0.8607 0.9277
No log 7.0943 376 0.8453 0.6713 0.8453 0.9194
No log 7.1321 378 0.8291 0.6619 0.8291 0.9106
No log 7.1698 380 0.8136 0.6618 0.8136 0.9020
No log 7.2075 382 0.8687 0.6621 0.8687 0.9321
No log 7.2453 384 1.0488 0.6309 1.0488 1.0241
No log 7.2830 386 1.0826 0.6267 1.0826 1.0405
No log 7.3208 388 0.9668 0.6241 0.9668 0.9833
No log 7.3585 390 0.9347 0.6479 0.9347 0.9668
No log 7.3962 392 0.9067 0.6471 0.9067 0.9522
No log 7.4340 394 0.8845 0.6617 0.8845 0.9405
No log 7.4717 396 0.9430 0.5926 0.9430 0.9711
No log 7.5094 398 1.0214 0.6286 1.0214 1.0106
No log 7.5472 400 0.9735 0.6316 0.9735 0.9867
No log 7.5849 402 0.9176 0.6617 0.9176 0.9579
No log 7.6226 404 0.8982 0.6765 0.8982 0.9477
No log 7.6604 406 0.8561 0.6765 0.8561 0.9253
No log 7.6981 408 0.8808 0.6853 0.8808 0.9385
No log 7.7358 410 0.8545 0.7114 0.8545 0.9244
No log 7.7736 412 0.7670 0.7413 0.7670 0.8758
No log 7.8113 414 0.6979 0.7153 0.6979 0.8354
No log 7.8491 416 0.7105 0.7376 0.7105 0.8429
No log 7.8868 418 0.7316 0.7286 0.7316 0.8553
No log 7.9245 420 0.7706 0.7194 0.7706 0.8778
No log 7.9623 422 0.8819 0.6712 0.8819 0.9391
No log 8.0 424 0.9532 0.6410 0.9532 0.9763
No log 8.0377 426 0.9019 0.6713 0.9019 0.9497
No log 8.0755 428 0.8704 0.6716 0.8704 0.9329
No log 8.1132 430 0.9036 0.6667 0.9036 0.9506
No log 8.1509 432 0.9602 0.6331 0.9602 0.9799
No log 8.1887 434 0.9323 0.6434 0.9323 0.9655
No log 8.2264 436 0.9600 0.6577 0.9600 0.9798
No log 8.2642 438 0.9250 0.6579 0.9250 0.9618
No log 8.3019 440 0.8543 0.6667 0.8543 0.9243
No log 8.3396 442 0.8012 0.6815 0.8012 0.8951
No log 8.3774 444 0.8035 0.6912 0.8035 0.8964
No log 8.4151 446 0.8130 0.6763 0.8130 0.9017
No log 8.4528 448 0.8650 0.6918 0.8650 0.9300
No log 8.4906 450 0.8628 0.6708 0.8628 0.9289
No log 8.5283 452 0.7252 0.7020 0.7252 0.8516
No log 8.5660 454 0.6438 0.7692 0.6438 0.8024
No log 8.6038 456 0.6872 0.7413 0.6872 0.8290
No log 8.6415 458 0.7876 0.6667 0.7876 0.8875
No log 8.6792 460 0.9248 0.6119 0.9248 0.9617
No log 8.7170 462 0.9981 0.5612 0.9981 0.9990
No log 8.7547 464 0.9736 0.5839 0.9736 0.9867
No log 8.7925 466 0.9244 0.6074 0.9244 0.9615
No log 8.8302 468 0.9237 0.6466 0.9237 0.9611
No log 8.8679 470 0.9208 0.6466 0.9208 0.9596
No log 8.9057 472 0.9072 0.6618 0.9072 0.9525
No log 8.9434 474 0.9190 0.6345 0.9190 0.9586
No log 8.9811 476 0.9154 0.6707 0.9154 0.9568
No log 9.0189 478 0.8103 0.7342 0.8103 0.9002
No log 9.0566 480 0.6649 0.7333 0.6649 0.8154
No log 9.0943 482 0.6369 0.7324 0.6369 0.7981
No log 9.1321 484 0.6765 0.7383 0.6765 0.8225
No log 9.1698 486 0.7089 0.7297 0.7089 0.8420
No log 9.2075 488 0.7851 0.6806 0.7851 0.8861
No log 9.2453 490 0.8061 0.6806 0.8061 0.8978
No log 9.2830 492 0.8181 0.6573 0.8181 0.9045
No log 9.3208 494 0.8794 0.6712 0.8794 0.9378
No log 9.3585 496 0.9102 0.6573 0.9102 0.9541
No log 9.3962 498 0.8287 0.6567 0.8287 0.9103
0.4368 9.4340 500 0.7455 0.7007 0.7455 0.8634
0.4368 9.4717 502 0.7111 0.7338 0.7111 0.8433
0.4368 9.5094 504 0.7415 0.7246 0.7415 0.8611
0.4368 9.5472 506 0.8352 0.6716 0.8352 0.9139
0.4368 9.5849 508 0.9874 0.6575 0.9874 0.9937
0.4368 9.6226 510 1.0854 0.6623 1.0854 1.0418
0.4368 9.6604 512 1.0157 0.6525 1.0157 1.0078
0.4368 9.6981 514 0.8986 0.6716 0.8986 0.9479

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1