MayBashendy's picture
End of training
a46e66e verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k10_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k10_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: 0.8610
  • Qwk: 0.6619
  • Mse: 0.8610
  • Rmse: 0.9279

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 0.0267 2 6.8741 0.0242 6.8741 2.6219
No log 0.0533 4 4.4447 0.1205 4.4447 2.1082
No log 0.08 6 2.9239 0.0988 2.9239 1.7099
No log 0.1067 8 2.2647 0.1342 2.2647 1.5049
No log 0.1333 10 1.8034 0.3167 1.8034 1.3429
No log 0.16 12 1.6455 0.2000 1.6455 1.2828
No log 0.1867 14 1.6240 0.2430 1.6240 1.2744
No log 0.2133 16 1.5608 0.2430 1.5608 1.2493
No log 0.24 18 1.3631 0.3273 1.3631 1.1675
No log 0.2667 20 1.4066 0.4833 1.4066 1.1860
No log 0.2933 22 1.4600 0.4202 1.4600 1.2083
No log 0.32 24 1.2744 0.4874 1.2744 1.1289
No log 0.3467 26 1.1430 0.3717 1.1430 1.0691
No log 0.3733 28 1.3560 0.5496 1.3560 1.1645
No log 0.4 30 1.5789 0.3731 1.5789 1.2566
No log 0.4267 32 1.6589 0.3731 1.6589 1.2880
No log 0.4533 34 1.4425 0.3788 1.4425 1.2010
No log 0.48 36 1.1931 0.4706 1.1931 1.0923
No log 0.5067 38 1.1102 0.5167 1.1102 1.0537
No log 0.5333 40 1.1154 0.5 1.1154 1.0561
No log 0.56 42 1.0953 0.5556 1.0953 1.0466
No log 0.5867 44 1.3899 0.3363 1.3899 1.1790
No log 0.6133 46 1.4906 0.2385 1.4906 1.2209
No log 0.64 48 1.3064 0.3130 1.3064 1.1430
No log 0.6667 50 1.0549 0.5323 1.0549 1.0271
No log 0.6933 52 1.0217 0.5669 1.0217 1.0108
No log 0.72 54 1.0282 0.6466 1.0282 1.0140
No log 0.7467 56 1.2213 0.5507 1.2213 1.1051
No log 0.7733 58 1.3697 0.5306 1.3697 1.1703
No log 0.8 60 1.3558 0.4861 1.3558 1.1644
No log 0.8267 62 1.3191 0.5068 1.3191 1.1485
No log 0.8533 64 1.2220 0.575 1.2220 1.1055
No log 0.88 66 1.1871 0.65 1.1871 1.0895
No log 0.9067 68 1.1565 0.5860 1.1565 1.0754
No log 0.9333 70 1.1430 0.5949 1.1430 1.0691
No log 0.96 72 1.2064 0.6104 1.2064 1.0984
No log 0.9867 74 1.0976 0.6364 1.0976 1.0477
No log 1.0133 76 1.0378 0.6093 1.0378 1.0187
No log 1.04 78 1.0194 0.6133 1.0194 1.0097
No log 1.0667 80 1.0062 0.6528 1.0062 1.0031
No log 1.0933 82 1.0427 0.6027 1.0427 1.0211
No log 1.12 84 1.2466 0.5333 1.2466 1.1165
No log 1.1467 86 1.3467 0.5135 1.3467 1.1605
No log 1.1733 88 1.2426 0.5541 1.2426 1.1147
No log 1.2 90 1.1735 0.5517 1.1735 1.0833
No log 1.2267 92 1.2144 0.5467 1.2144 1.1020
No log 1.2533 94 1.2854 0.5921 1.2854 1.1338
No log 1.28 96 1.1206 0.5828 1.1206 1.0586
No log 1.3067 98 1.0282 0.6533 1.0282 1.0140
No log 1.3333 100 1.0217 0.6081 1.0217 1.0108
No log 1.3600 102 1.1092 0.56 1.1092 1.0532
No log 1.3867 104 1.1245 0.5563 1.1245 1.0604
No log 1.4133 106 1.0975 0.6456 1.0975 1.0476
No log 1.44 108 1.0963 0.6369 1.0963 1.0470
No log 1.4667 110 1.0973 0.6711 1.0973 1.0475
No log 1.4933 112 1.2042 0.5563 1.2042 1.0973
No log 1.52 114 1.2251 0.5405 1.2251 1.1068
No log 1.5467 116 1.1323 0.4928 1.1323 1.0641
No log 1.5733 118 1.0331 0.6015 1.0331 1.0164
No log 1.6 120 1.0456 0.5538 1.0456 1.0226
No log 1.6267 122 1.0191 0.6074 1.0191 1.0095
No log 1.6533 124 0.9872 0.6483 0.9872 0.9936
No log 1.6800 126 0.9630 0.6622 0.9630 0.9813
No log 1.7067 128 0.9826 0.6622 0.9826 0.9913
No log 1.7333 130 0.9697 0.6968 0.9697 0.9847
No log 1.76 132 1.0204 0.6708 1.0204 1.0101
No log 1.7867 134 1.0969 0.5860 1.0969 1.0473
No log 1.8133 136 1.1636 0.5290 1.1636 1.0787
No log 1.8400 138 1.0583 0.6241 1.0583 1.0287
No log 1.8667 140 1.0097 0.6434 1.0097 1.0048
No log 1.8933 142 1.0142 0.6040 1.0142 1.0071
No log 1.92 144 1.0161 0.6 1.0161 1.0080
No log 1.9467 146 1.0303 0.6111 1.0303 1.0151
No log 1.9733 148 1.0907 0.5714 1.0907 1.0444
No log 2.0 150 1.1810 0.6026 1.1810 1.0867
No log 2.0267 152 1.1206 0.6184 1.1206 1.0586
No log 2.0533 154 0.9845 0.6395 0.9845 0.9922
No log 2.08 156 0.8717 0.6803 0.8717 0.9337
No log 2.1067 158 0.7831 0.7172 0.7831 0.8849
No log 2.1333 160 0.7835 0.7483 0.7835 0.8852
No log 2.16 162 0.8327 0.7285 0.8327 0.9125
No log 2.1867 164 0.9683 0.6447 0.9683 0.9840
No log 2.2133 166 1.1341 0.6424 1.1341 1.0649
No log 2.24 168 1.0505 0.6225 1.0505 1.0249
No log 2.2667 170 0.9979 0.6980 0.9979 0.9989
No log 2.2933 172 1.1125 0.6154 1.1125 1.0548
No log 2.32 174 1.0772 0.6301 1.0772 1.0379
No log 2.3467 176 0.9361 0.7067 0.9361 0.9675
No log 2.3733 178 0.8536 0.7020 0.8536 0.9239
No log 2.4 180 0.9387 0.6714 0.9387 0.9689
No log 2.4267 182 1.1416 0.6452 1.1416 1.0684
No log 2.4533 184 1.3616 0.5896 1.3616 1.1669
No log 2.48 186 1.2598 0.5783 1.2598 1.1224
No log 2.5067 188 1.0225 0.5960 1.0225 1.0112
No log 2.5333 190 0.9066 0.6897 0.9066 0.9522
No log 2.56 192 0.9499 0.6620 0.9499 0.9746
No log 2.5867 194 0.9704 0.6901 0.9704 0.9851
No log 2.6133 196 1.0139 0.6 1.0139 1.0069
No log 2.64 198 1.1163 0.5752 1.1163 1.0566
No log 2.6667 200 1.1849 0.6347 1.1849 1.0886
No log 2.6933 202 1.0802 0.6860 1.0802 1.0393
No log 2.7200 204 0.9285 0.6846 0.9285 0.9636
No log 2.7467 206 0.8667 0.7067 0.8667 0.9310
No log 2.7733 208 0.8241 0.6944 0.8241 0.9078
No log 2.8 210 0.8402 0.6389 0.8402 0.9166
No log 2.8267 212 0.7094 0.7397 0.7094 0.8422
No log 2.8533 214 0.7496 0.7170 0.7496 0.8658
No log 2.88 216 0.8908 0.6533 0.8908 0.9438
No log 2.9067 218 0.9863 0.6338 0.9863 0.9931
No log 2.9333 220 0.9574 0.6269 0.9574 0.9784
No log 2.96 222 0.9293 0.6466 0.9293 0.9640
No log 2.9867 224 0.8087 0.6815 0.8087 0.8993
No log 3.0133 226 0.7484 0.7246 0.7484 0.8651
No log 3.04 228 0.8994 0.6713 0.8994 0.9484
No log 3.0667 230 1.1504 0.6104 1.1504 1.0726
No log 3.0933 232 1.3816 0.5698 1.3816 1.1754
No log 3.12 234 1.3033 0.5283 1.3033 1.1416
No log 3.1467 236 1.0382 0.6483 1.0382 1.0189
No log 3.1733 238 0.8090 0.6993 0.8090 0.8994
No log 3.2 240 0.7657 0.7172 0.7657 0.8751
No log 3.2267 242 0.7208 0.7403 0.7208 0.8490
No log 3.2533 244 0.6578 0.7595 0.6578 0.8110
No log 3.2800 246 0.6540 0.7875 0.6540 0.8087
No log 3.3067 248 0.6629 0.7722 0.6629 0.8142
No log 3.3333 250 0.6542 0.7771 0.6542 0.8088
No log 3.36 252 0.6886 0.7383 0.6886 0.8298
No log 3.3867 254 0.7713 0.7162 0.7713 0.8782
No log 3.4133 256 0.8228 0.6933 0.8228 0.9071
No log 3.44 258 0.8110 0.6933 0.8110 0.9005
No log 3.4667 260 0.7480 0.7248 0.7480 0.8649
No log 3.4933 262 0.7517 0.7467 0.7517 0.8670
No log 3.52 264 0.8304 0.6531 0.8304 0.9113
No log 3.5467 266 0.8847 0.6338 0.8847 0.9406
No log 3.5733 268 0.9792 0.6143 0.9792 0.9895
No log 3.6 270 1.1103 0.5775 1.1103 1.0537
No log 3.6267 272 1.1819 0.5772 1.1819 1.0871
No log 3.6533 274 1.1139 0.6194 1.1139 1.0554
No log 3.68 276 0.9879 0.6795 0.9879 0.9939
No log 3.7067 278 0.9530 0.6795 0.9530 0.9762
No log 3.7333 280 0.8750 0.6883 0.8750 0.9354
No log 3.76 282 0.8212 0.7051 0.8212 0.9062
No log 3.7867 284 0.8460 0.6879 0.8460 0.9198
No log 3.8133 286 0.9590 0.7073 0.9590 0.9793
No log 3.84 288 0.9822 0.6879 0.9822 0.9911
No log 3.8667 290 0.9018 0.6622 0.9018 0.9496
No log 3.8933 292 0.8417 0.6849 0.8417 0.9175
No log 3.92 294 0.8231 0.6849 0.8231 0.9072
No log 3.9467 296 0.8336 0.6849 0.8336 0.9130
No log 3.9733 298 0.9300 0.6753 0.9300 0.9644
No log 4.0 300 1.0312 0.6946 1.0312 1.0155
No log 4.0267 302 1.0142 0.6835 1.0142 1.0071
No log 4.0533 304 0.9042 0.6667 0.9042 0.9509
No log 4.08 306 0.8233 0.6763 0.8233 0.9074
No log 4.1067 308 0.7849 0.7297 0.7849 0.8859
No log 4.1333 310 0.8086 0.6892 0.8086 0.8992
No log 4.16 312 0.8434 0.6708 0.8434 0.9184
No log 4.1867 314 0.8597 0.6667 0.8597 0.9272
No log 4.2133 316 0.8039 0.6707 0.8039 0.8966
No log 4.24 318 0.7587 0.7089 0.7587 0.8711
No log 4.2667 320 0.7797 0.7020 0.7797 0.8830
No log 4.2933 322 0.8696 0.6980 0.8696 0.9325
No log 4.32 324 0.9971 0.6415 0.9971 0.9986
No log 4.3467 326 0.9556 0.6928 0.9556 0.9776
No log 4.3733 328 0.9013 0.6897 0.9013 0.9494
No log 4.4 330 0.8171 0.6806 0.8171 0.9039
No log 4.4267 332 0.7826 0.6806 0.7826 0.8846
No log 4.4533 334 0.8317 0.7160 0.8317 0.9120
No log 4.48 336 0.8134 0.6875 0.8134 0.9019
No log 4.5067 338 0.7539 0.6986 0.7539 0.8683
No log 4.5333 340 0.7251 0.7586 0.7251 0.8515
No log 4.5600 342 0.7196 0.7586 0.7196 0.8483
No log 4.5867 344 0.7581 0.7172 0.7581 0.8707
No log 4.6133 346 0.8706 0.6452 0.8706 0.9331
No log 4.64 348 0.8928 0.6575 0.8928 0.9449
No log 4.6667 350 0.8076 0.6667 0.8076 0.8987
No log 4.6933 352 0.7308 0.7482 0.7308 0.8549
No log 4.72 354 0.7093 0.7448 0.7093 0.8422
No log 4.7467 356 0.7407 0.7260 0.7407 0.8606
No log 4.7733 358 0.7957 0.6579 0.7957 0.8920
No log 4.8 360 0.8123 0.6667 0.8123 0.9013
No log 4.8267 362 0.7446 0.7260 0.7446 0.8629
No log 4.8533 364 0.7353 0.7075 0.7353 0.8575
No log 4.88 366 0.7361 0.7190 0.7361 0.8580
No log 4.9067 368 0.7259 0.7296 0.7259 0.8520
No log 4.9333 370 0.6900 0.7421 0.6900 0.8306
No log 4.96 372 0.6774 0.7531 0.6774 0.8231
No log 4.9867 374 0.6182 0.7742 0.6182 0.7862
No log 5.0133 376 0.6223 0.8054 0.6223 0.7889
No log 5.04 378 0.6672 0.7724 0.6672 0.8168
No log 5.0667 380 0.7741 0.6761 0.7741 0.8798
No log 5.0933 382 0.9519 0.6752 0.9519 0.9756
No log 5.12 384 1.0898 0.6471 1.0898 1.0439
No log 5.1467 386 1.0006 0.6628 1.0006 1.0003
No log 5.1733 388 0.7750 0.6842 0.7750 0.8804
No log 5.2 390 0.6647 0.7778 0.6647 0.8153
No log 5.2267 392 0.6656 0.7552 0.6656 0.8158
No log 5.2533 394 0.6535 0.75 0.6535 0.8084
No log 5.28 396 0.6453 0.8052 0.6453 0.8033
No log 5.3067 398 0.7204 0.7368 0.7204 0.8488
No log 5.3333 400 0.8184 0.7416 0.8184 0.9047
No log 5.36 402 0.8032 0.7209 0.8032 0.8962
No log 5.3867 404 0.8264 0.7 0.8264 0.9091
No log 5.4133 406 0.7947 0.6475 0.7947 0.8915
No log 5.44 408 0.7976 0.6767 0.7976 0.8931
No log 5.4667 410 0.8541 0.6212 0.8541 0.9242
No log 5.4933 412 0.8727 0.6370 0.8727 0.9342
No log 5.52 414 0.8625 0.6383 0.8625 0.9287
No log 5.5467 416 0.8559 0.6711 0.8559 0.9252
No log 5.5733 418 0.9579 0.6867 0.9579 0.9787
No log 5.6 420 0.9788 0.6706 0.9788 0.9893
No log 5.6267 422 0.8914 0.6914 0.8914 0.9441
No log 5.6533 424 0.8526 0.6797 0.8526 0.9233
No log 5.68 426 0.7930 0.6759 0.7930 0.8905
No log 5.7067 428 0.7854 0.6857 0.7854 0.8862
No log 5.7333 430 0.8217 0.6857 0.8217 0.9065
No log 5.76 432 0.8823 0.6434 0.8823 0.9393
No log 5.7867 434 0.9145 0.6711 0.9145 0.9563
No log 5.8133 436 0.9345 0.6624 0.9345 0.9667
No log 5.84 438 0.9181 0.6755 0.9181 0.9582
No log 5.8667 440 0.8573 0.6621 0.8573 0.9259
No log 5.8933 442 0.8173 0.6883 0.8173 0.9040
No log 5.92 444 0.8104 0.7229 0.8104 0.9002
No log 5.9467 446 0.8336 0.7241 0.8336 0.9130
No log 5.9733 448 0.7490 0.7073 0.7490 0.8655
No log 6.0 450 0.6654 0.7755 0.6654 0.8157
No log 6.0267 452 0.6448 0.7639 0.6448 0.8030
No log 6.0533 454 0.6329 0.7639 0.6329 0.7956
No log 6.08 456 0.6606 0.7722 0.6606 0.8128
No log 6.1067 458 0.8110 0.7273 0.8110 0.9006
No log 6.1333 460 0.8862 0.7168 0.8862 0.9414
No log 6.16 462 0.8165 0.6447 0.8165 0.9036
No log 6.1867 464 0.7252 0.7246 0.7252 0.8516
No log 6.2133 466 0.7203 0.7286 0.7203 0.8487
No log 6.24 468 0.7232 0.7376 0.7232 0.8504
No log 6.2667 470 0.8042 0.6962 0.8042 0.8968
No log 6.2933 472 0.9441 0.7059 0.9441 0.9716
No log 6.32 474 1.0698 0.6590 1.0698 1.0343
No log 6.3467 476 1.1152 0.5541 1.1152 1.0560
No log 6.3733 478 1.1601 0.5441 1.1601 1.0771
No log 6.4 480 1.1189 0.6015 1.1189 1.0578
No log 6.4267 482 1.0617 0.6119 1.0617 1.0304
No log 6.4533 484 0.9927 0.6423 0.9927 0.9964
No log 6.48 486 0.9448 0.6571 0.9448 0.9720
No log 6.5067 488 0.8540 0.6761 0.8540 0.9241
No log 6.5333 490 0.8157 0.7092 0.8157 0.9032
No log 6.5600 492 0.7628 0.7042 0.7628 0.8734
No log 6.5867 494 0.7473 0.7042 0.7473 0.8644
No log 6.6133 496 0.7532 0.7020 0.7532 0.8679
No log 6.64 498 0.7335 0.7215 0.7335 0.8564
0.4387 6.6667 500 0.7451 0.7329 0.7451 0.8632
0.4387 6.6933 502 0.7459 0.7425 0.7459 0.8637
0.4387 6.72 504 0.6933 0.7172 0.6933 0.8326
0.4387 6.7467 506 0.7113 0.7299 0.7113 0.8434
0.4387 6.7733 508 0.7200 0.7353 0.7200 0.8485
0.4387 6.8 510 0.7192 0.7259 0.7192 0.8480
0.4387 6.8267 512 0.7357 0.7153 0.7357 0.8577
0.4387 6.8533 514 0.8000 0.6331 0.8000 0.8945
0.4387 6.88 516 0.8622 0.6331 0.8622 0.9285
0.4387 6.9067 518 0.8610 0.6619 0.8610 0.9279

Framework versions

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