ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k19_task3_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: 1.0713
  • Qwk: -0.2617
  • Mse: 1.0713
  • Rmse: 1.0350

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 0.0417 2 3.9916 0.0029 3.9916 1.9979
No log 0.0833 4 2.6116 0.0298 2.6116 1.6161
No log 0.125 6 1.3744 0.0279 1.3744 1.1724
No log 0.1667 8 1.6693 -0.0269 1.6693 1.2920
No log 0.2083 10 1.2212 0.0610 1.2212 1.1051
No log 0.25 12 0.9022 -0.0345 0.9022 0.9499
No log 0.2917 14 0.8863 -0.0909 0.8863 0.9414
No log 0.3333 16 1.0572 -0.0398 1.0572 1.0282
No log 0.375 18 1.1431 0.0411 1.1431 1.0692
No log 0.4167 20 0.9495 -0.0345 0.9495 0.9744
No log 0.4583 22 0.8953 -0.0902 0.8953 0.9462
No log 0.5 24 1.0664 0.0156 1.0664 1.0327
No log 0.5417 26 1.2152 -0.0247 1.2152 1.1023
No log 0.5833 28 1.2283 0.0 1.2283 1.1083
No log 0.625 30 1.3103 0.0 1.3103 1.1447
No log 0.6667 32 1.1151 0.0032 1.1151 1.0560
No log 0.7083 34 0.8314 -0.0371 0.8314 0.9118
No log 0.75 36 0.7836 -0.0160 0.7836 0.8852
No log 0.7917 38 0.8150 0.0476 0.8150 0.9028
No log 0.8333 40 1.0190 -0.0049 1.0190 1.0094
No log 0.875 42 0.9783 -0.0301 0.9783 0.9891
No log 0.9167 44 0.9036 -0.0861 0.9036 0.9506
No log 0.9583 46 0.9304 -0.0504 0.9304 0.9646
No log 1.0 48 0.9313 -0.0504 0.9313 0.9650
No log 1.0417 50 0.8698 -0.1253 0.8698 0.9326
No log 1.0833 52 0.8762 -0.0425 0.8762 0.9361
No log 1.125 54 0.9335 0.0458 0.9335 0.9662
No log 1.1667 56 0.8853 0.0207 0.8853 0.9409
No log 1.2083 58 0.9011 0.0111 0.9011 0.9493
No log 1.25 60 0.8018 0.0017 0.8018 0.8954
No log 1.2917 62 0.7672 0.0759 0.7672 0.8759
No log 1.3333 64 0.7071 0.1021 0.7071 0.8409
No log 1.375 66 0.7482 0.2757 0.7482 0.8650
No log 1.4167 68 1.1305 0.0217 1.1305 1.0632
No log 1.4583 70 1.5544 -0.0500 1.5544 1.2468
No log 1.5 72 1.5657 -0.0500 1.5657 1.2513
No log 1.5417 74 1.4099 -0.0468 1.4099 1.1874
No log 1.5833 76 1.0881 -0.0842 1.0881 1.0431
No log 1.625 78 0.9443 -0.0454 0.9443 0.9718
No log 1.6667 80 0.7612 -0.0179 0.7612 0.8724
No log 1.7083 82 0.6995 0.0374 0.6995 0.8364
No log 1.75 84 0.7072 0.1148 0.7072 0.8409
No log 1.7917 86 0.7681 0.1243 0.7681 0.8764
No log 1.8333 88 0.8646 0.0748 0.8646 0.9299
No log 1.875 90 1.0433 0.0046 1.0433 1.0214
No log 1.9167 92 1.0631 -0.0583 1.0631 1.0311
No log 1.9583 94 1.0837 -0.0892 1.0837 1.0410
No log 2.0 96 1.0782 -0.1566 1.0782 1.0384
No log 2.0417 98 1.0000 -0.0526 1.0000 1.0000
No log 2.0833 100 0.9012 0.0362 0.9012 0.9493
No log 2.125 102 0.9726 -0.0628 0.9726 0.9862
No log 2.1667 104 0.9562 -0.0269 0.9562 0.9778
No log 2.2083 106 0.8946 0.0182 0.8946 0.9458
No log 2.25 108 0.9387 0.0111 0.9387 0.9689
No log 2.2917 110 1.0677 -0.0955 1.0677 1.0333
No log 2.3333 112 1.3371 -0.0133 1.3371 1.1563
No log 2.375 114 1.2668 -0.0411 1.2668 1.1255
No log 2.4167 116 1.0356 0.0327 1.0356 1.0176
No log 2.4583 118 0.9873 0.0419 0.9873 0.9936
No log 2.5 120 1.3601 0.1104 1.3601 1.1662
No log 2.5417 122 1.2844 0.0832 1.2844 1.1333
No log 2.5833 124 0.9814 0.0179 0.9814 0.9907
No log 2.625 126 1.5865 0.0076 1.5865 1.2596
No log 2.6667 128 1.8084 -0.0451 1.8084 1.3448
No log 2.7083 130 1.4382 0.0400 1.4382 1.1992
No log 2.75 132 0.8924 -0.0076 0.8924 0.9447
No log 2.7917 134 0.8489 0.0595 0.8489 0.9214
No log 2.8333 136 0.8493 0.0240 0.8493 0.9216
No log 2.875 138 0.8043 0.0834 0.8043 0.8968
No log 2.9167 140 0.9797 -0.2000 0.9797 0.9898
No log 2.9583 142 1.0572 -0.1274 1.0572 1.0282
No log 3.0 144 0.9883 -0.1509 0.9883 0.9941
No log 3.0417 146 0.9596 -0.0753 0.9596 0.9796
No log 3.0833 148 0.9078 -0.0444 0.9078 0.9528
No log 3.125 150 0.9370 -0.0602 0.9370 0.9680
No log 3.1667 152 0.9604 -0.0511 0.9604 0.9800
No log 3.2083 154 1.0047 -0.1512 1.0047 1.0024
No log 3.25 156 1.1652 -0.0619 1.1652 1.0795
No log 3.2917 158 1.2093 -0.0847 1.2093 1.0997
No log 3.3333 160 1.1609 -0.1219 1.1609 1.0774
No log 3.375 162 1.2208 -0.1063 1.2208 1.1049
No log 3.4167 164 1.2461 -0.1371 1.2461 1.1163
No log 3.4583 166 1.2421 -0.1075 1.2421 1.1145
No log 3.5 168 1.2057 -0.0642 1.2057 1.0981
No log 3.5417 170 1.0555 -0.0646 1.0555 1.0274
No log 3.5833 172 1.0647 -0.0575 1.0647 1.0319
No log 3.625 174 1.0474 -0.0670 1.0474 1.0234
No log 3.6667 176 1.1131 -0.0208 1.1131 1.0550
No log 3.7083 178 1.2443 -0.0975 1.2443 1.1155
No log 3.75 180 1.2823 -0.1769 1.2823 1.1324
No log 3.7917 182 1.1963 -0.1166 1.1963 1.0938
No log 3.8333 184 1.0804 -0.1144 1.0804 1.0394
No log 3.875 186 1.0426 -0.0767 1.0426 1.0211
No log 3.9167 188 1.0056 -0.0629 1.0056 1.0028
No log 3.9583 190 1.0044 -0.0955 1.0044 1.0022
No log 4.0 192 1.0542 -0.1083 1.0542 1.0268
No log 4.0417 194 1.1188 -0.1390 1.1188 1.0577
No log 4.0833 196 1.0779 -0.1973 1.0779 1.0382
No log 4.125 198 1.3657 -0.0833 1.3657 1.1686
No log 4.1667 200 1.4156 -0.0411 1.4156 1.1898
No log 4.2083 202 1.2258 -0.1069 1.2258 1.1072
No log 4.25 204 1.0442 -0.1277 1.0442 1.0219
No log 4.2917 206 1.1929 -0.0786 1.1929 1.0922
No log 4.3333 208 1.3014 -0.2428 1.3014 1.1408
No log 4.375 210 1.1189 -0.1988 1.1189 1.0578
No log 4.4167 212 0.9295 -0.1047 0.9295 0.9641
No log 4.4583 214 0.9729 -0.0786 0.9729 0.9864
No log 4.5 216 1.0079 -0.1354 1.0079 1.0039
No log 4.5417 218 1.0365 -0.1039 1.0365 1.0181
No log 4.5833 220 1.1187 -0.0963 1.1187 1.0577
No log 4.625 222 1.4910 -0.1102 1.4910 1.2211
No log 4.6667 224 1.5981 -0.0881 1.5981 1.2642
No log 4.7083 226 1.4668 -0.0831 1.4668 1.2111
No log 4.75 228 1.2586 -0.0795 1.2586 1.1219
No log 4.7917 230 1.2000 -0.0947 1.2000 1.0955
No log 4.8333 232 1.3411 -0.2012 1.3411 1.1581
No log 4.875 234 1.4177 -0.2214 1.4177 1.1907
No log 4.9167 236 1.4960 -0.2065 1.4960 1.2231
No log 4.9583 238 1.5864 -0.1682 1.5864 1.2595
No log 5.0 240 1.4896 -0.1694 1.4896 1.2205
No log 5.0417 242 1.3058 -0.1721 1.3058 1.1427
No log 5.0833 244 1.2081 -0.1785 1.2081 1.0991
No log 5.125 246 1.1329 -0.1632 1.1329 1.0644
No log 5.1667 248 1.0416 -0.2288 1.0416 1.0206
No log 5.2083 250 1.0583 -0.2059 1.0583 1.0287
No log 5.25 252 1.0378 -0.2059 1.0378 1.0187
No log 5.2917 254 1.0029 -0.2270 1.0029 1.0015
No log 5.3333 256 1.0792 -0.1522 1.0792 1.0389
No log 5.375 258 1.0950 -0.2001 1.0950 1.0464
No log 5.4167 260 1.0425 -0.0955 1.0425 1.0210
No log 5.4583 262 1.1961 -0.1214 1.1961 1.0937
No log 5.5 264 1.1961 -0.0818 1.1961 1.0937
No log 5.5417 266 1.1117 -0.1010 1.1117 1.0543
No log 5.5833 268 1.0581 -0.1099 1.0581 1.0286
No log 5.625 270 1.1119 -0.0861 1.1119 1.0545
No log 5.6667 272 1.2193 -0.0973 1.2193 1.1042
No log 5.7083 274 1.3072 -0.0395 1.3072 1.1433
No log 5.75 276 1.3185 -0.0071 1.3185 1.1483
No log 5.7917 278 1.0643 -0.0735 1.0643 1.0316
No log 5.8333 280 0.8881 -0.0892 0.8881 0.9424
No log 5.875 282 0.8861 -0.1146 0.8861 0.9413
No log 5.9167 284 0.9487 -0.1249 0.9487 0.9740
No log 5.9583 286 0.9893 -0.1354 0.9893 0.9946
No log 6.0 288 1.0650 -0.2764 1.0650 1.0320
No log 6.0417 290 1.0717 -0.2339 1.0717 1.0352
No log 6.0833 292 1.0767 -0.2561 1.0767 1.0376
No log 6.125 294 0.9931 -0.2165 0.9931 0.9966
No log 6.1667 296 0.9009 -0.1268 0.9009 0.9492
No log 6.2083 298 0.8134 0.0031 0.8134 0.9019
No log 6.25 300 0.7877 -0.0035 0.7877 0.8875
No log 6.2917 302 0.7955 0.0506 0.7955 0.8919
No log 6.3333 304 0.8358 -0.0188 0.8358 0.9142
No log 6.375 306 0.9007 -0.0145 0.9007 0.9490
No log 6.4167 308 0.9522 -0.0583 0.9522 0.9758
No log 6.4583 310 1.0186 -0.1588 1.0186 1.0093
No log 6.5 312 1.1014 -0.1821 1.1014 1.0495
No log 6.5417 314 1.1783 -0.1326 1.1783 1.0855
No log 6.5833 316 1.1770 -0.1326 1.1770 1.0849
No log 6.625 318 1.1310 -0.2452 1.1310 1.0635
No log 6.6667 320 1.0752 -0.1684 1.0752 1.0369
No log 6.7083 322 1.0277 -0.2757 1.0277 1.0138
No log 6.75 324 1.0470 -0.1372 1.0470 1.0232
No log 6.7917 326 1.0114 -0.1524 1.0114 1.0057
No log 6.8333 328 0.9315 -0.2043 0.9315 0.9651
No log 6.875 330 0.9442 -0.1121 0.9442 0.9717
No log 6.9167 332 0.9884 -0.0731 0.9884 0.9942
No log 6.9583 334 0.8988 -0.0204 0.8988 0.9480
No log 7.0 336 0.8221 -0.0062 0.8221 0.9067
No log 7.0417 338 0.8500 -0.0363 0.8500 0.9220
No log 7.0833 340 0.8857 -0.2056 0.8857 0.9411
No log 7.125 342 0.9300 -0.2142 0.9300 0.9644
No log 7.1667 344 1.0199 -0.0479 1.0199 1.0099
No log 7.2083 346 1.0302 -0.1580 1.0302 1.0150
No log 7.25 348 1.0582 -0.2003 1.0582 1.0287
No log 7.2917 350 1.0679 -0.1572 1.0679 1.0334
No log 7.3333 352 1.0473 -0.2057 1.0473 1.0234
No log 7.375 354 1.0397 -0.2407 1.0397 1.0197
No log 7.4167 356 1.0278 -0.1802 1.0278 1.0138
No log 7.4583 358 1.0424 -0.1149 1.0424 1.0210
No log 7.5 360 0.9281 -0.1535 0.9281 0.9634
No log 7.5417 362 0.8554 -0.0984 0.8554 0.9249
No log 7.5833 364 0.9019 0.0247 0.9019 0.9497
No log 7.625 366 0.8589 -0.0660 0.8589 0.9268
No log 7.6667 368 0.8701 -0.1616 0.8701 0.9328
No log 7.7083 370 0.9055 -0.1538 0.9055 0.9516
No log 7.75 372 0.9526 -0.1531 0.9526 0.9760
No log 7.7917 374 0.9997 -0.1786 0.9997 0.9998
No log 7.8333 376 1.0727 -0.1576 1.0727 1.0357
No log 7.875 378 1.1350 -0.1663 1.1350 1.0654
No log 7.9167 380 1.0628 -0.2003 1.0628 1.0309
No log 7.9583 382 1.0097 -0.2973 1.0097 1.0048
No log 8.0 384 0.9603 -0.2973 0.9603 0.9800
No log 8.0417 386 0.9443 -0.0996 0.9443 0.9718
No log 8.0833 388 0.9669 -0.0852 0.9669 0.9833
No log 8.125 390 0.9077 -0.1905 0.9077 0.9527
No log 8.1667 392 0.8679 -0.0293 0.8679 0.9316
No log 8.2083 394 0.8588 -0.1208 0.8588 0.9267
No log 8.25 396 0.8220 0.0 0.8220 0.9067
No log 8.2917 398 0.8139 -0.1163 0.8139 0.9022
No log 8.3333 400 0.8059 -0.1163 0.8059 0.8977
No log 8.375 402 0.8152 -0.0493 0.8152 0.9029
No log 8.4167 404 0.8462 0.0585 0.8462 0.9199
No log 8.4583 406 0.8612 -0.2416 0.8612 0.9280
No log 8.5 408 0.8932 -0.1927 0.8932 0.9451
No log 8.5417 410 0.9390 -0.1051 0.9390 0.9690
No log 8.5833 412 1.0007 -0.0269 1.0007 1.0004
No log 8.625 414 1.0070 -0.0269 1.0070 1.0035
No log 8.6667 416 0.9500 -0.1334 0.9500 0.9747
No log 8.7083 418 0.9327 -0.0517 0.9327 0.9658
No log 8.75 420 0.8868 -0.0634 0.8868 0.9417
No log 8.7917 422 0.8754 -0.1535 0.8754 0.9356
No log 8.8333 424 0.8360 -0.1860 0.8360 0.9143
No log 8.875 426 0.8514 0.1202 0.8514 0.9227
No log 8.9167 428 0.9230 0.0071 0.9230 0.9607
No log 8.9583 430 0.9071 0.0099 0.9071 0.9524
No log 9.0 432 0.8004 0.0814 0.8004 0.8946
No log 9.0417 434 0.8100 -0.0387 0.8100 0.9000
No log 9.0833 436 0.9220 -0.0477 0.9220 0.9602
No log 9.125 438 0.9438 -0.0843 0.9438 0.9715
No log 9.1667 440 0.9059 -0.1413 0.9059 0.9518
No log 9.2083 442 0.9008 -0.1588 0.9008 0.9491
No log 9.25 444 0.9450 -0.0511 0.9450 0.9721
No log 9.2917 446 0.9855 -0.0241 0.9855 0.9927
No log 9.3333 448 0.9356 -0.0923 0.9356 0.9673
No log 9.375 450 0.9507 -0.0920 0.9507 0.9751
No log 9.4167 452 1.1071 -0.0551 1.1071 1.0522
No log 9.4583 454 1.0640 -0.0408 1.0640 1.0315
No log 9.5 456 0.9667 -0.0941 0.9667 0.9832
No log 9.5417 458 0.9047 -0.1211 0.9047 0.9512
No log 9.5833 460 0.9362 -0.2030 0.9362 0.9676
No log 9.625 462 0.9861 -0.2302 0.9861 0.9930
No log 9.6667 464 1.0440 -0.2253 1.0440 1.0218
No log 9.7083 466 1.1330 -0.1238 1.1330 1.0644
No log 9.75 468 1.2627 -0.1228 1.2627 1.1237
No log 9.7917 470 1.4338 -0.0323 1.4338 1.1974
No log 9.8333 472 1.3362 -0.0361 1.3362 1.1560
No log 9.875 474 1.1232 -0.0305 1.1232 1.0598
No log 9.9167 476 0.9009 -0.2017 0.9009 0.9492
No log 9.9583 478 0.8369 0.0334 0.8369 0.9148
No log 10.0 480 0.7926 0.0334 0.7926 0.8903
No log 10.0417 482 0.8040 -0.0033 0.8040 0.8967
No log 10.0833 484 0.8585 -0.1010 0.8585 0.9265
No log 10.125 486 0.9119 -0.1045 0.9119 0.9549
No log 10.1667 488 0.9217 -0.1002 0.9217 0.9601
No log 10.2083 490 0.9312 -0.1355 0.9312 0.9650
No log 10.25 492 0.9578 -0.0878 0.9578 0.9787
No log 10.2917 494 0.9999 0.0227 0.9999 1.0000
No log 10.3333 496 0.9794 -0.0755 0.9794 0.9896
No log 10.375 498 0.9278 -0.0361 0.9278 0.9632
0.3879 10.4167 500 0.8702 -0.0841 0.8702 0.9329
0.3879 10.4583 502 0.8312 -0.0132 0.8312 0.9117
0.3879 10.5 504 0.8559 0.0476 0.8559 0.9251
0.3879 10.5417 506 0.9391 -0.0878 0.9391 0.9691
0.3879 10.5833 508 0.9236 -0.0033 0.9236 0.9610
0.3879 10.625 510 0.8617 0.0476 0.8617 0.9283
0.3879 10.6667 512 0.7872 0.1304 0.7872 0.8872
0.3879 10.7083 514 0.8046 -0.0406 0.8046 0.8970
0.3879 10.75 516 0.8717 -0.1354 0.8717 0.9336
0.3879 10.7917 518 0.9269 -0.1580 0.9269 0.9628
0.3879 10.8333 520 0.9825 0.0196 0.9825 0.9912
0.3879 10.875 522 0.9512 -0.0186 0.9512 0.9753
0.3879 10.9167 524 0.8954 -0.1033 0.8954 0.9463
0.3879 10.9583 526 0.8830 -0.1010 0.8830 0.9397
0.3879 11.0 528 0.8752 -0.1538 0.8752 0.9355
0.3879 11.0417 530 0.8872 -0.1158 0.8872 0.9419
0.3879 11.0833 532 0.9170 -0.0215 0.9170 0.9576
0.3879 11.125 534 0.9287 -0.1033 0.9287 0.9637
0.3879 11.1667 536 0.9624 -0.1730 0.9624 0.9810
0.3879 11.2083 538 0.9881 -0.1592 0.9881 0.9940
0.3879 11.25 540 0.9649 -0.1332 0.9649 0.9823
0.3879 11.2917 542 0.9371 -0.0118 0.9371 0.9680
0.3879 11.3333 544 0.9073 -0.0550 0.9073 0.9525
0.3879 11.375 546 0.9332 -0.2207 0.9332 0.9660
0.3879 11.4167 548 0.9407 -0.1263 0.9407 0.9699
0.3879 11.4583 550 0.8924 -0.1978 0.8924 0.9446
0.3879 11.5 552 0.8736 -0.0091 0.8736 0.9347
0.3879 11.5417 554 0.9070 0.0129 0.9070 0.9523
0.3879 11.5833 556 0.9109 -0.0351 0.9109 0.9544
0.3879 11.625 558 0.9121 -0.0614 0.9121 0.9550
0.3879 11.6667 560 0.9431 -0.0465 0.9431 0.9711
0.3879 11.7083 562 1.0023 -0.2338 1.0023 1.0012
0.3879 11.75 564 1.0041 -0.2151 1.0041 1.0020
0.3879 11.7917 566 0.9640 -0.0841 0.9640 0.9818
0.3879 11.8333 568 1.0039 -0.1504 1.0039 1.0020
0.3879 11.875 570 1.0713 -0.2617 1.0713 1.0350

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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/ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k19_task3_organization

Finetuned
(4019)
this model