ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k3_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: 0.8244
  • Qwk: 0.6447
  • Mse: 0.8244
  • Rmse: 0.9079

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 0.1176 2 5.3971 0.0035 5.3971 2.3232
No log 0.2353 4 3.2997 0.0555 3.2997 1.8165
No log 0.3529 6 1.8405 0.0764 1.8405 1.3566
No log 0.4706 8 1.3277 0.1493 1.3277 1.1523
No log 0.5882 10 1.2154 0.2082 1.2154 1.1025
No log 0.7059 12 1.1616 0.2080 1.1616 1.0778
No log 0.8235 14 1.1758 0.1778 1.1758 1.0844
No log 0.9412 16 1.1813 0.1460 1.1813 1.0869
No log 1.0588 18 1.1886 0.1283 1.1886 1.0902
No log 1.1765 20 1.2083 0.1963 1.2083 1.0992
No log 1.2941 22 1.2640 0.2070 1.2640 1.1243
No log 1.4118 24 1.4093 0.0877 1.4093 1.1871
No log 1.5294 26 1.2677 0.2530 1.2677 1.1259
No log 1.6471 28 1.0989 0.3512 1.0989 1.0483
No log 1.7647 30 1.0933 0.3155 1.0933 1.0456
No log 1.8824 32 1.0571 0.2097 1.0571 1.0282
No log 2.0 34 1.0593 0.1735 1.0593 1.0292
No log 2.1176 36 1.1439 0.3110 1.1439 1.0695
No log 2.2353 38 1.1580 0.2934 1.1580 1.0761
No log 2.3529 40 1.1143 0.2032 1.1143 1.0556
No log 2.4706 42 1.0514 0.2268 1.0514 1.0254
No log 2.5882 44 1.0177 0.2295 1.0177 1.0088
No log 2.7059 46 0.9648 0.2719 0.9648 0.9822
No log 2.8235 48 0.9055 0.3146 0.9055 0.9516
No log 2.9412 50 0.8871 0.3531 0.8871 0.9418
No log 3.0588 52 0.8953 0.3928 0.8953 0.9462
No log 3.1765 54 0.8718 0.4765 0.8718 0.9337
No log 3.2941 56 0.8583 0.4982 0.8583 0.9265
No log 3.4118 58 0.8601 0.5085 0.8601 0.9274
No log 3.5294 60 0.9512 0.3147 0.9512 0.9753
No log 3.6471 62 1.2351 0.2907 1.2351 1.1113
No log 3.7647 64 1.1565 0.4030 1.1565 1.0754
No log 3.8824 66 0.8689 0.5295 0.8689 0.9322
No log 4.0 68 0.8452 0.5646 0.8452 0.9194
No log 4.1176 70 0.8731 0.5821 0.8731 0.9344
No log 4.2353 72 0.9253 0.5808 0.9253 0.9619
No log 4.3529 74 1.0048 0.5229 1.0048 1.0024
No log 4.4706 76 0.9246 0.5899 0.9246 0.9616
No log 4.5882 78 0.8446 0.6508 0.8446 0.9190
No log 4.7059 80 0.7924 0.6169 0.7924 0.8902
No log 4.8235 82 0.8397 0.5885 0.8397 0.9163
No log 4.9412 84 0.8797 0.5538 0.8797 0.9379
No log 5.0588 86 0.8221 0.6011 0.8221 0.9067
No log 5.1765 88 0.7434 0.6149 0.7434 0.8622
No log 5.2941 90 0.7735 0.6021 0.7735 0.8795
No log 5.4118 92 0.7575 0.6338 0.7575 0.8703
No log 5.5294 94 0.8602 0.6147 0.8602 0.9275
No log 5.6471 96 0.8480 0.5896 0.8480 0.9209
No log 5.7647 98 0.7694 0.6276 0.7694 0.8772
No log 5.8824 100 0.7453 0.6372 0.7453 0.8633
No log 6.0 102 0.7434 0.6247 0.7434 0.8622
No log 6.1176 104 0.7456 0.6247 0.7456 0.8635
No log 6.2353 106 0.7336 0.6278 0.7336 0.8565
No log 6.3529 108 0.7446 0.6093 0.7446 0.8629
No log 6.4706 110 0.8299 0.6381 0.8299 0.9110
No log 6.5882 112 0.7516 0.6538 0.7516 0.8669
No log 6.7059 114 0.9352 0.6076 0.9352 0.9670
No log 6.8235 116 1.1790 0.5133 1.1790 1.0858
No log 6.9412 118 0.9716 0.5743 0.9716 0.9857
No log 7.0588 120 0.7468 0.6822 0.7468 0.8642
No log 7.1765 122 0.6849 0.6757 0.6849 0.8276
No log 7.2941 124 0.6794 0.6418 0.6794 0.8243
No log 7.4118 126 0.6723 0.6508 0.6723 0.8199
No log 7.5294 128 0.7116 0.6715 0.7116 0.8435
No log 7.6471 130 0.7571 0.6726 0.7571 0.8701
No log 7.7647 132 0.9523 0.5866 0.9523 0.9759
No log 7.8824 134 0.9683 0.5831 0.9683 0.9840
No log 8.0 136 0.8155 0.6521 0.8155 0.9030
No log 8.1176 138 0.7174 0.6275 0.7174 0.8470
No log 8.2353 140 0.7363 0.6266 0.7363 0.8581
No log 8.3529 142 0.8341 0.6050 0.8341 0.9133
No log 8.4706 144 0.8634 0.6085 0.8634 0.9292
No log 8.5882 146 0.8447 0.6339 0.8447 0.9191
No log 8.7059 148 0.7169 0.6693 0.7169 0.8467
No log 8.8235 150 0.7023 0.6748 0.7023 0.8381
No log 8.9412 152 0.7532 0.6910 0.7532 0.8679
No log 9.0588 154 0.8183 0.6607 0.8183 0.9046
No log 9.1765 156 0.7787 0.6834 0.7787 0.8824
No log 9.2941 158 0.7133 0.6610 0.7133 0.8446
No log 9.4118 160 0.7235 0.6539 0.7235 0.8506
No log 9.5294 162 0.7907 0.6428 0.7907 0.8892
No log 9.6471 164 1.0101 0.5191 1.0101 1.0050
No log 9.7647 166 1.0023 0.5806 1.0023 1.0012
No log 9.8824 168 0.9130 0.6412 0.9130 0.9555
No log 10.0 170 0.8153 0.6583 0.8153 0.9029
No log 10.1176 172 0.8201 0.6230 0.8201 0.9056
No log 10.2353 174 0.8531 0.6202 0.8531 0.9236
No log 10.3529 176 1.0388 0.5469 1.0388 1.0192
No log 10.4706 178 1.1576 0.5061 1.1576 1.0759
No log 10.5882 180 0.9625 0.5336 0.9625 0.9811
No log 10.7059 182 0.8146 0.5910 0.8146 0.9025
No log 10.8235 184 0.7409 0.6077 0.7409 0.8608
No log 10.9412 186 0.7491 0.6245 0.7491 0.8655
No log 11.0588 188 0.7452 0.6071 0.7452 0.8633
No log 11.1765 190 0.7043 0.6510 0.7043 0.8392
No log 11.2941 192 0.8358 0.6558 0.8358 0.9142
No log 11.4118 194 0.9847 0.5669 0.9847 0.9923
No log 11.5294 196 0.8850 0.6356 0.8850 0.9407
No log 11.6471 198 0.8224 0.6657 0.8224 0.9069
No log 11.7647 200 0.7297 0.6683 0.7297 0.8542
No log 11.8824 202 0.7210 0.6541 0.7210 0.8491
No log 12.0 204 0.7437 0.6265 0.7437 0.8624
No log 12.1176 206 0.8518 0.6036 0.8518 0.9229
No log 12.2353 208 0.8849 0.6023 0.8849 0.9407
No log 12.3529 210 0.8433 0.6202 0.8433 0.9183
No log 12.4706 212 0.7951 0.6368 0.7951 0.8917
No log 12.5882 214 0.7840 0.6801 0.7840 0.8854
No log 12.7059 216 0.8770 0.6441 0.8770 0.9365
No log 12.8235 218 0.9386 0.6548 0.9386 0.9688
No log 12.9412 220 0.8785 0.6340 0.8785 0.9373
No log 13.0588 222 0.7923 0.6507 0.7923 0.8901
No log 13.1765 224 0.6610 0.6724 0.6610 0.8130
No log 13.2941 226 0.6605 0.6530 0.6605 0.8127
No log 13.4118 228 0.6977 0.6578 0.6977 0.8353
No log 13.5294 230 0.7549 0.6473 0.7549 0.8688
No log 13.6471 232 0.8501 0.6444 0.8501 0.9220
No log 13.7647 234 0.8577 0.6374 0.8577 0.9261
No log 13.8824 236 0.8260 0.6250 0.8260 0.9088
No log 14.0 238 0.8303 0.6327 0.8303 0.9112
No log 14.1176 240 0.8974 0.6226 0.8974 0.9473
No log 14.2353 242 0.9519 0.5829 0.9519 0.9756
No log 14.3529 244 0.8688 0.6264 0.8688 0.9321
No log 14.4706 246 0.8197 0.6560 0.8197 0.9053
No log 14.5882 248 0.7542 0.6617 0.7542 0.8684
No log 14.7059 250 0.7127 0.6776 0.7127 0.8442
No log 14.8235 252 0.6281 0.7079 0.6281 0.7925
No log 14.9412 254 0.6147 0.6926 0.6147 0.7840
No log 15.0588 256 0.6410 0.7451 0.6410 0.8006
No log 15.1765 258 0.6561 0.7255 0.6561 0.8100
No log 15.2941 260 0.6759 0.7048 0.6759 0.8221
No log 15.4118 262 0.6304 0.7040 0.6304 0.7940
No log 15.5294 264 0.6359 0.6862 0.6359 0.7974
No log 15.6471 266 0.6710 0.6785 0.6710 0.8191
No log 15.7647 268 0.7065 0.6765 0.7065 0.8405
No log 15.8824 270 0.7140 0.6835 0.7140 0.8450
No log 16.0 272 0.7496 0.6705 0.7496 0.8658
No log 16.1176 274 0.6880 0.6894 0.6880 0.8295
No log 16.2353 276 0.6794 0.6813 0.6794 0.8243
No log 16.3529 278 0.6969 0.7006 0.6969 0.8348
No log 16.4706 280 0.7519 0.6774 0.7519 0.8671
No log 16.5882 282 0.9041 0.6165 0.9041 0.9508
No log 16.7059 284 1.1317 0.5031 1.1317 1.0638
No log 16.8235 286 1.0886 0.5031 1.0886 1.0434
No log 16.9412 288 0.9811 0.6158 0.9811 0.9905
No log 17.0588 290 0.9159 0.6241 0.9159 0.9570
No log 17.1765 292 0.8281 0.6426 0.8281 0.9100
No log 17.2941 294 0.7936 0.6608 0.7936 0.8908
No log 17.4118 296 0.7322 0.6804 0.7322 0.8557
No log 17.5294 298 0.7012 0.6731 0.7012 0.8374
No log 17.6471 300 0.7466 0.6431 0.7466 0.8641
No log 17.7647 302 0.9573 0.5819 0.9573 0.9784
No log 17.8824 304 1.1370 0.5341 1.1370 1.0663
No log 18.0 306 1.0496 0.5423 1.0496 1.0245
No log 18.1176 308 0.8496 0.5947 0.8496 0.9218
No log 18.2353 310 0.7603 0.6677 0.7603 0.8720
No log 18.3529 312 0.6756 0.6641 0.6756 0.8220
No log 18.4706 314 0.6604 0.6640 0.6604 0.8126
No log 18.5882 316 0.6905 0.6878 0.6905 0.8310
No log 18.7059 318 0.8176 0.6667 0.8176 0.9042
No log 18.8235 320 0.9934 0.6230 0.9934 0.9967
No log 18.9412 322 0.9090 0.6222 0.9090 0.9534
No log 19.0588 324 0.7624 0.6665 0.7624 0.8732
No log 19.1765 326 0.6728 0.6809 0.6728 0.8203
No log 19.2941 328 0.6351 0.6599 0.6351 0.7969
No log 19.4118 330 0.6366 0.6740 0.6366 0.7979
No log 19.5294 332 0.6590 0.6510 0.6590 0.8118
No log 19.6471 334 0.7776 0.6486 0.7776 0.8818
No log 19.7647 336 0.8383 0.6285 0.8383 0.9156
No log 19.8824 338 0.7832 0.6517 0.7832 0.8850
No log 20.0 340 0.7799 0.6303 0.7799 0.8831
No log 20.1176 342 0.8046 0.6512 0.8046 0.8970
No log 20.2353 344 0.8967 0.6074 0.8967 0.9469
No log 20.3529 346 0.9438 0.6004 0.9438 0.9715
No log 20.4706 348 0.9020 0.5998 0.9020 0.9497
No log 20.5882 350 0.8057 0.6368 0.8057 0.8976
No log 20.7059 352 0.7211 0.6879 0.7211 0.8492
No log 20.8235 354 0.7050 0.6812 0.7050 0.8396
No log 20.9412 356 0.6886 0.6989 0.6886 0.8298
No log 21.0588 358 0.7595 0.6283 0.7595 0.8715
No log 21.1765 360 0.8107 0.6122 0.8107 0.9004
No log 21.2941 362 0.7579 0.6445 0.7579 0.8706
No log 21.4118 364 0.7588 0.6543 0.7588 0.8711
No log 21.5294 366 0.8339 0.6074 0.8339 0.9132
No log 21.6471 368 0.9678 0.6328 0.9678 0.9838
No log 21.7647 370 1.0096 0.6194 1.0096 1.0048
No log 21.8824 372 0.8757 0.6379 0.8757 0.9358
No log 22.0 374 0.7123 0.6534 0.7123 0.8440
No log 22.1176 376 0.6675 0.6664 0.6675 0.8170
No log 22.2353 378 0.7123 0.6571 0.7123 0.8440
No log 22.3529 380 0.8211 0.6359 0.8211 0.9061
No log 22.4706 382 0.9010 0.6068 0.9010 0.9492
No log 22.5882 384 0.9156 0.6004 0.9156 0.9569
No log 22.7059 386 0.8502 0.6342 0.8502 0.9221
No log 22.8235 388 0.7709 0.6338 0.7709 0.8780
No log 22.9412 390 0.7772 0.6327 0.7772 0.8816
No log 23.0588 392 0.7294 0.6807 0.7294 0.8540
No log 23.1765 394 0.7118 0.6741 0.7118 0.8437
No log 23.2941 396 0.7801 0.6357 0.7801 0.8832
No log 23.4118 398 0.8476 0.6183 0.8476 0.9207
No log 23.5294 400 0.9654 0.5695 0.9654 0.9826
No log 23.6471 402 1.0117 0.5795 1.0117 1.0058
No log 23.7647 404 0.9931 0.5772 0.9931 0.9965
No log 23.8824 406 0.9421 0.5947 0.9421 0.9706
No log 24.0 408 0.8893 0.6218 0.8893 0.9430
No log 24.1176 410 0.8059 0.6551 0.8059 0.8977
No log 24.2353 412 0.7532 0.6707 0.7532 0.8679
No log 24.3529 414 0.7812 0.6740 0.7812 0.8838
No log 24.4706 416 0.9153 0.6393 0.9153 0.9567
No log 24.5882 418 1.0479 0.6033 1.0479 1.0236
No log 24.7059 420 1.0226 0.5756 1.0226 1.0112
No log 24.8235 422 0.8546 0.6252 0.8546 0.9245
No log 24.9412 424 0.7321 0.6298 0.7321 0.8556
No log 25.0588 426 0.6971 0.6115 0.6971 0.8349
No log 25.1765 428 0.7142 0.5949 0.7142 0.8451
No log 25.2941 430 0.8130 0.6126 0.8130 0.9016
No log 25.4118 432 0.9583 0.6016 0.9583 0.9789
No log 25.5294 434 0.9752 0.6026 0.9752 0.9875
No log 25.6471 436 0.8900 0.6069 0.8900 0.9434
No log 25.7647 438 0.7848 0.6279 0.7848 0.8859
No log 25.8824 440 0.7213 0.6409 0.7213 0.8493
No log 26.0 442 0.7140 0.6463 0.7140 0.8450
No log 26.1176 444 0.7403 0.6433 0.7403 0.8604
No log 26.2353 446 0.7316 0.6593 0.7316 0.8553
No log 26.3529 448 0.7299 0.6484 0.7299 0.8543
No log 26.4706 450 0.7277 0.6458 0.7277 0.8530
No log 26.5882 452 0.7113 0.6217 0.7113 0.8434
No log 26.7059 454 0.6856 0.6525 0.6856 0.8280
No log 26.8235 456 0.6703 0.6395 0.6703 0.8187
No log 26.9412 458 0.6686 0.6469 0.6686 0.8177
No log 27.0588 460 0.6838 0.6532 0.6838 0.8269
No log 27.1765 462 0.7286 0.6387 0.7286 0.8536
No log 27.2941 464 0.7556 0.6727 0.7556 0.8692
No log 27.4118 466 0.7700 0.7031 0.7700 0.8775
No log 27.5294 468 0.7447 0.7136 0.7447 0.8629
No log 27.6471 470 0.7011 0.6933 0.7011 0.8373
No log 27.7647 472 0.6961 0.6599 0.6961 0.8343
No log 27.8824 474 0.7259 0.6622 0.7259 0.8520
No log 28.0 476 0.7100 0.6565 0.7100 0.8426
No log 28.1176 478 0.7055 0.6620 0.7055 0.8400
No log 28.2353 480 0.6767 0.6574 0.6767 0.8226
No log 28.3529 482 0.6623 0.6519 0.6623 0.8138
No log 28.4706 484 0.6749 0.6599 0.6749 0.8216
No log 28.5882 486 0.7202 0.6634 0.7202 0.8487
No log 28.7059 488 0.6984 0.6737 0.6984 0.8357
No log 28.8235 490 0.7002 0.6737 0.7002 0.8368
No log 28.9412 492 0.7035 0.6686 0.7035 0.8388
No log 29.0588 494 0.7645 0.6459 0.7645 0.8744
No log 29.1765 496 0.8260 0.6252 0.8260 0.9088
No log 29.2941 498 0.8172 0.6340 0.8172 0.9040
0.3935 29.4118 500 0.7484 0.6635 0.7484 0.8651
0.3935 29.5294 502 0.6872 0.6653 0.6872 0.8290
0.3935 29.6471 504 0.6863 0.6705 0.6863 0.8284
0.3935 29.7647 506 0.7470 0.6866 0.7470 0.8643
0.3935 29.8824 508 0.9416 0.6290 0.9416 0.9704
0.3935 30.0 510 1.1123 0.6007 1.1123 1.0547
0.3935 30.1176 512 1.1756 0.5816 1.1756 1.0843
0.3935 30.2353 514 1.0556 0.6117 1.0556 1.0274
0.3935 30.3529 516 0.8244 0.6447 0.8244 0.9079

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k3_task1_organization

Finetuned
(4040)
this model