ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_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: 0.9932
  • Qwk: -0.1217
  • Mse: 0.9932
  • Rmse: 0.9966

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 0.9498
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 1.3104 0.0 1.3104 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 1.0187 -0.0049 1.0187 1.0093
No log 0.875 42 0.9782 -0.0301 0.9782 0.9890
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 0.9336 0.0458 0.9336 0.9663
No log 1.1667 56 0.8852 0.0207 0.8852 0.9409
No log 1.2083 58 0.9010 0.0111 0.9010 0.9492
No log 1.25 60 0.8020 0.0017 0.8020 0.8955
No log 1.2917 62 0.7677 0.0759 0.7677 0.8762
No log 1.3333 64 0.7071 0.1021 0.7071 0.8409
No log 1.375 66 0.7478 0.2757 0.7478 0.8648
No log 1.4167 68 1.1302 0.0217 1.1302 1.0631
No log 1.4583 70 1.5545 -0.0500 1.5545 1.2468
No log 1.5 72 1.5656 -0.0500 1.5656 1.2513
No log 1.5417 74 1.4094 -0.0468 1.4094 1.1872
No log 1.5833 76 1.0883 -0.0842 1.0883 1.0432
No log 1.625 78 0.9440 -0.0454 0.9440 0.9716
No log 1.6667 80 0.7611 -0.0179 0.7611 0.8724
No log 1.7083 82 0.7001 0.0334 0.7001 0.8367
No log 1.75 84 0.7084 0.1148 0.7084 0.8416
No log 1.7917 86 0.7699 0.1243 0.7699 0.8774
No log 1.8333 88 0.8664 0.0748 0.8664 0.9308
No log 1.875 90 1.0460 0.0046 1.0460 1.0227
No log 1.9167 92 1.0666 -0.0583 1.0666 1.0328
No log 1.9583 94 1.0886 -0.0892 1.0886 1.0433
No log 2.0 96 1.0874 -0.1566 1.0874 1.0428
No log 2.0417 98 1.0331 -0.0899 1.0331 1.0164
No log 2.0833 100 0.9328 -0.0097 0.9328 0.9658
No log 2.125 102 1.0026 -0.0316 1.0026 1.0013
No log 2.1667 104 0.9678 -0.0269 0.9678 0.9838
No log 2.2083 106 0.8916 -0.0518 0.8916 0.9443
No log 2.25 108 0.9517 -0.0253 0.9517 0.9755
No log 2.2917 110 1.1137 -0.0345 1.1137 1.0553
No log 2.3333 112 1.3391 -0.0133 1.3391 1.1572
No log 2.375 114 1.2135 -0.0608 1.2135 1.1016
No log 2.4167 116 0.9897 0.0227 0.9897 0.9948
No log 2.4583 118 1.0014 0.0785 1.0014 1.0007
No log 2.5 120 1.2460 0.0789 1.2460 1.1162
No log 2.5417 122 1.0871 0.0403 1.0871 1.0426
No log 2.5833 124 1.0910 0.0691 1.0910 1.0445
No log 2.625 126 1.3629 -0.0098 1.3629 1.1674
No log 2.6667 128 1.1280 0.0526 1.1280 1.0621
No log 2.7083 130 0.9149 -0.0393 0.9149 0.9565
No log 2.75 132 0.9285 -0.0212 0.9285 0.9636
No log 2.7917 134 0.9335 0.0200 0.9335 0.9662
No log 2.8333 136 0.8974 0.0627 0.8974 0.9473
No log 2.875 138 0.9391 -0.0379 0.9391 0.9691
No log 2.9167 140 0.9590 -0.0670 0.9590 0.9793
No log 2.9583 142 1.0460 -0.0954 1.0460 1.0227
No log 3.0 144 1.0802 -0.1130 1.0802 1.0393
No log 3.0417 146 1.0398 -0.0576 1.0398 1.0197
No log 3.0833 148 1.0214 0.1039 1.0214 1.0107
No log 3.125 150 1.0396 -0.0870 1.0396 1.0196
No log 3.1667 152 1.0250 0.0353 1.0250 1.0124
No log 3.2083 154 0.9721 -0.0511 0.9721 0.9859
No log 3.25 156 1.0185 -0.1557 1.0185 1.0092
No log 3.2917 158 0.9307 -0.0025 0.9307 0.9647
No log 3.3333 160 0.9232 -0.0443 0.9232 0.9608
No log 3.375 162 0.9736 -0.0128 0.9736 0.9867
No log 3.4167 164 1.2223 -0.0690 1.2223 1.1056
No log 3.4583 166 1.0891 -0.0462 1.0891 1.0436
No log 3.5 168 0.9248 -0.0221 0.9248 0.9616
No log 3.5417 170 1.0054 0.0377 1.0054 1.0027
No log 3.5833 172 0.9973 0.0461 0.9973 0.9986
No log 3.625 174 1.0662 -0.0541 1.0662 1.0326
No log 3.6667 176 1.0441 -0.0918 1.0441 1.0218
No log 3.7083 178 1.0634 0.0154 1.0634 1.0312
No log 3.75 180 1.0534 -0.1639 1.0534 1.0264
No log 3.7917 182 1.4561 -0.0309 1.4561 1.2067
No log 3.8333 184 1.3399 -0.0383 1.3399 1.1576
No log 3.875 186 0.9881 -0.1224 0.9881 0.9940
No log 3.9167 188 0.9289 -0.1462 0.9289 0.9638
No log 3.9583 190 0.9426 -0.0879 0.9426 0.9709
No log 4.0 192 1.0537 -0.1203 1.0537 1.0265
No log 4.0417 194 1.2030 -0.1228 1.2030 1.0968
No log 4.0833 196 1.0664 -0.1206 1.0664 1.0327
No log 4.125 198 0.9589 -0.1653 0.9589 0.9792
No log 4.1667 200 1.0694 -0.1624 1.0694 1.0341
No log 4.2083 202 1.0093 -0.2159 1.0093 1.0046
No log 4.25 204 0.9241 -0.0557 0.9241 0.9613
No log 4.2917 206 1.0896 -0.0809 1.0896 1.0438
No log 4.3333 208 0.9983 -0.0735 0.9983 0.9991
No log 4.375 210 0.9198 -0.0280 0.9198 0.9591
No log 4.4167 212 0.9792 -0.2036 0.9792 0.9895
No log 4.4583 214 0.9609 -0.0661 0.9609 0.9802
No log 4.5 216 0.9420 0.0289 0.9420 0.9706
No log 4.5417 218 1.0435 -0.0355 1.0435 1.0215
No log 4.5833 220 0.9842 0.0611 0.9842 0.9921
No log 4.625 222 0.9193 0.0725 0.9193 0.9588
No log 4.6667 224 0.9690 -0.0221 0.9690 0.9844
No log 4.7083 226 0.9551 0.0196 0.9551 0.9773
No log 4.75 228 0.9155 -0.1002 0.9155 0.9568
No log 4.7917 230 0.9102 -0.1529 0.9102 0.9540
No log 4.8333 232 0.9153 -0.0262 0.9153 0.9567
No log 4.875 234 1.0555 -0.0854 1.0555 1.0274
No log 4.9167 236 1.1380 -0.0870 1.1380 1.0668
No log 4.9583 238 0.9338 0.0087 0.9338 0.9663
No log 5.0 240 0.8484 -0.0138 0.8484 0.9211
No log 5.0417 242 0.9123 0.0350 0.9123 0.9551
No log 5.0833 244 0.8645 0.0187 0.8645 0.9298
No log 5.125 246 0.8672 0.0106 0.8672 0.9312
No log 5.1667 248 1.1349 -0.0815 1.1349 1.0653
No log 5.2083 250 1.1450 -0.0832 1.1450 1.0700
No log 5.25 252 0.9257 -0.1054 0.9257 0.9621
No log 5.2917 254 0.9258 -0.1051 0.9258 0.9622
No log 5.3333 256 0.9783 -0.0733 0.9783 0.9891
No log 5.375 258 0.9468 -0.0407 0.9468 0.9730
No log 5.4167 260 1.0192 -0.1506 1.0192 1.0095
No log 5.4583 262 1.0751 -0.1905 1.0751 1.0369
No log 5.5 264 1.0212 0.0426 1.0212 1.0105
No log 5.5417 266 1.1034 -0.1279 1.1034 1.0504
No log 5.5833 268 1.1198 -0.1566 1.1198 1.0582
No log 5.625 270 1.0736 -0.0563 1.0736 1.0361
No log 5.6667 272 1.0548 -0.1067 1.0548 1.0270
No log 5.7083 274 1.0066 -0.0896 1.0066 1.0033
No log 5.75 276 0.9344 -0.1331 0.9344 0.9667
No log 5.7917 278 0.9401 -0.1172 0.9401 0.9696
No log 5.8333 280 0.9913 -0.0999 0.9913 0.9956
No log 5.875 282 1.0087 -0.1219 1.0087 1.0043
No log 5.9167 284 1.0712 -0.1519 1.0712 1.0350
No log 5.9583 286 1.1003 -0.1564 1.1003 1.0490
No log 6.0 288 1.0797 -0.0284 1.0797 1.0391
No log 6.0417 290 1.1526 -0.1668 1.1526 1.0736
No log 6.0833 292 1.1105 -0.0734 1.1105 1.0538
No log 6.125 294 1.1002 -0.1215 1.1002 1.0489
No log 6.1667 296 1.0875 -0.1572 1.0875 1.0428
No log 6.2083 298 1.0957 -0.1278 1.0957 1.0468
No log 6.25 300 1.0316 -0.1686 1.0316 1.0157
No log 6.2917 302 1.0555 -0.1111 1.0555 1.0274
No log 6.3333 304 1.0706 -0.0963 1.0706 1.0347
No log 6.375 306 1.1370 -0.1915 1.1370 1.0663
No log 6.4167 308 1.2331 -0.2010 1.2331 1.1104
No log 6.4583 310 1.1415 -0.1564 1.1415 1.0684
No log 6.5 312 1.0531 -0.0762 1.0531 1.0262
No log 6.5417 314 1.0880 -0.1281 1.0880 1.0431
No log 6.5833 316 1.0579 -0.1711 1.0579 1.0285
No log 6.625 318 1.0984 -0.0991 1.0984 1.0481
No log 6.6667 320 1.1176 -0.1155 1.1176 1.0572
No log 6.7083 322 1.0420 0.0377 1.0420 1.0208
No log 6.75 324 1.0954 -0.0870 1.0954 1.0466
No log 6.7917 326 1.0868 -0.0905 1.0868 1.0425
No log 6.8333 328 1.0265 0.0064 1.0265 1.0132
No log 6.875 330 1.2764 -0.1144 1.2764 1.1298
No log 6.9167 332 1.5109 -0.0621 1.5109 1.2292
No log 6.9583 334 1.2959 -0.1194 1.2959 1.1384
No log 7.0 336 0.9966 0.0065 0.9966 0.9983
No log 7.0417 338 0.9069 0.0230 0.9069 0.9523
No log 7.0833 340 0.9331 -0.0843 0.9331 0.9660
No log 7.125 342 0.9146 -0.0187 0.9146 0.9564
No log 7.1667 344 0.9703 -0.0073 0.9703 0.9850
No log 7.2083 346 1.0940 -0.1093 1.0940 1.0460
No log 7.25 348 1.1087 -0.0088 1.1087 1.0529
No log 7.2917 350 1.1334 -0.0934 1.1334 1.0646
No log 7.3333 352 1.2195 -0.0726 1.2195 1.1043
No log 7.375 354 1.1814 -0.0624 1.1814 1.0869
No log 7.4167 356 1.1292 -0.0297 1.1292 1.0626
No log 7.4583 358 1.0717 -0.0531 1.0717 1.0352
No log 7.5 360 1.0806 -0.1143 1.0806 1.0395
No log 7.5417 362 1.2096 -0.1115 1.2096 1.0998
No log 7.5833 364 1.0949 -0.1203 1.0949 1.0464
No log 7.625 366 0.8790 0.0191 0.8790 0.9376
No log 7.6667 368 0.8584 -0.0567 0.8584 0.9265
No log 7.7083 370 0.9068 -0.0583 0.9068 0.9523
No log 7.75 372 1.0502 -0.0371 1.0502 1.0248
No log 7.7917 374 1.0738 -0.1197 1.0738 1.0362
No log 7.8333 376 0.9971 -0.1281 0.9971 0.9986
No log 7.875 378 0.9731 -0.1057 0.9731 0.9864
No log 7.9167 380 0.9501 -0.1275 0.9501 0.9747
No log 7.9583 382 0.9548 -0.1391 0.9548 0.9772
No log 8.0 384 1.0538 -0.0746 1.0538 1.0265
No log 8.0417 386 1.0009 -0.1446 1.0009 1.0005
No log 8.0833 388 0.9623 -0.1866 0.9623 0.9810
No log 8.125 390 0.9458 -0.2005 0.9458 0.9725
No log 8.1667 392 0.9042 -0.1832 0.9042 0.9509
No log 8.2083 394 0.8653 -0.0739 0.8653 0.9302
No log 8.25 396 0.9004 -0.0753 0.9004 0.9489
No log 8.2917 398 0.9900 -0.0425 0.9900 0.9950
No log 8.3333 400 0.9749 -0.0425 0.9749 0.9874
No log 8.375 402 0.8827 -0.1168 0.8827 0.9395
No log 8.4167 404 0.8998 -0.0870 0.8998 0.9486
No log 8.4583 406 0.9316 -0.1786 0.9316 0.9652
No log 8.5 408 0.9816 -0.1696 0.9816 0.9908
No log 8.5417 410 1.0158 -0.2225 1.0158 1.0078
No log 8.5833 412 1.0675 -0.0870 1.0675 1.0332
No log 8.625 414 1.0829 -0.0436 1.0829 1.0406
No log 8.6667 416 1.0617 -0.1913 1.0617 1.0304
No log 8.7083 418 1.1362 -0.1552 1.1362 1.0659
No log 8.75 420 1.0219 -0.1336 1.0219 1.0109
No log 8.7917 422 0.9411 -0.2395 0.9411 0.9701
No log 8.8333 424 0.9686 -0.1628 0.9686 0.9841
No log 8.875 426 0.9517 -0.1253 0.9517 0.9756
No log 8.9167 428 0.9168 -0.0778 0.9168 0.9575
No log 8.9583 430 0.9052 -0.0766 0.9052 0.9514
No log 9.0 432 0.8622 -0.1018 0.8622 0.9285
No log 9.0417 434 0.8926 -0.1397 0.8926 0.9448
No log 9.0833 436 0.9636 -0.0543 0.9636 0.9816
No log 9.125 438 0.9759 -0.1305 0.9759 0.9879
No log 9.1667 440 0.9836 -0.1067 0.9836 0.9918
No log 9.2083 442 0.9628 -0.1116 0.9628 0.9812
No log 9.25 444 0.9500 -0.0138 0.9500 0.9747
No log 9.2917 446 0.9041 -0.1468 0.9041 0.9508
No log 9.3333 448 0.8984 -0.1604 0.8984 0.9479
No log 9.375 450 0.9621 -0.2072 0.9621 0.9809
No log 9.4167 452 0.9957 -0.2826 0.9957 0.9979
No log 9.4583 454 0.9881 -0.0831 0.9881 0.9940
No log 9.5 456 1.0090 -0.1247 1.0090 1.0045
No log 9.5417 458 1.0399 -0.1249 1.0399 1.0198
No log 9.5833 460 1.0844 -0.1817 1.0844 1.0413
No log 9.625 462 1.0772 -0.1408 1.0772 1.0379
No log 9.6667 464 1.0904 -0.1027 1.0904 1.0442
No log 9.7083 466 1.0973 -0.1355 1.0973 1.0475
No log 9.75 468 1.1024 -0.1661 1.1024 1.0499
No log 9.7917 470 1.0874 -0.1419 1.0874 1.0428
No log 9.8333 472 1.1050 -0.1841 1.1050 1.0512
No log 9.875 474 1.1185 -0.0918 1.1185 1.0576
No log 9.9167 476 1.1286 -0.1118 1.1286 1.0624
No log 9.9583 478 1.1056 -0.0862 1.1056 1.0515
No log 10.0 480 1.0399 -0.1027 1.0399 1.0198
No log 10.0417 482 1.0676 -0.2712 1.0676 1.0332
No log 10.0833 484 1.0597 -0.1963 1.0597 1.0294
No log 10.125 486 1.0352 -0.1227 1.0352 1.0175
No log 10.1667 488 1.0284 -0.1922 1.0284 1.0141
No log 10.2083 490 1.0201 -0.1514 1.0201 1.0100
No log 10.25 492 1.0544 -0.1952 1.0544 1.0268
No log 10.2917 494 1.1481 -0.1482 1.1481 1.0715
No log 10.3333 496 1.0948 -0.1837 1.0948 1.0463
No log 10.375 498 0.9709 -0.2100 0.9709 0.9853
0.3673 10.4167 500 0.9529 -0.1197 0.9529 0.9762
0.3673 10.4583 502 0.9414 -0.1247 0.9414 0.9702
0.3673 10.5 504 0.9011 -0.1394 0.9011 0.9492
0.3673 10.5417 506 0.9225 -0.1187 0.9225 0.9605
0.3673 10.5833 508 0.9693 -0.0812 0.9693 0.9845
0.3673 10.625 510 0.9622 -0.0790 0.9622 0.9809
0.3673 10.6667 512 0.9161 -0.1121 0.9161 0.9571
0.3673 10.7083 514 0.9251 -0.1860 0.9251 0.9618
0.3673 10.75 516 0.9686 -0.0503 0.9686 0.9842
0.3673 10.7917 518 0.9588 -0.0503 0.9588 0.9792
0.3673 10.8333 520 0.9236 -0.0999 0.9236 0.9610
0.3673 10.875 522 0.9645 -0.1614 0.9645 0.9821
0.3673 10.9167 524 0.9286 -0.1638 0.9286 0.9637
0.3673 10.9583 526 0.9137 -0.0145 0.9137 0.9559
0.3673 11.0 528 0.9275 -0.1159 0.9275 0.9631
0.3673 11.0417 530 0.9543 -0.0634 0.9543 0.9769
0.3673 11.0833 532 0.9815 -0.0608 0.9815 0.9907
0.3673 11.125 534 0.9821 -0.1106 0.9821 0.9910
0.3673 11.1667 536 1.0284 -0.2368 1.0284 1.0141
0.3673 11.2083 538 1.0372 -0.2080 1.0372 1.0184
0.3673 11.25 540 0.9342 -0.0718 0.9342 0.9665
0.3673 11.2917 542 0.8541 -0.0473 0.8541 0.9242
0.3673 11.3333 544 0.9078 -0.0982 0.9078 0.9528
0.3673 11.375 546 0.9587 -0.1753 0.9587 0.9791
0.3673 11.4167 548 0.9481 -0.1013 0.9481 0.9737
0.3673 11.4583 550 0.9307 -0.0524 0.9307 0.9647
0.3673 11.5 552 0.9214 -0.0567 0.9214 0.9599
0.3673 11.5417 554 0.9259 -0.0113 0.9259 0.9623
0.3673 11.5833 556 0.9434 -0.1333 0.9434 0.9713
0.3673 11.625 558 0.9835 -0.1876 0.9835 0.9917
0.3673 11.6667 560 1.0316 -0.1303 1.0316 1.0157
0.3673 11.7083 562 1.0225 -0.1409 1.0225 1.0112
0.3673 11.75 564 0.9932 -0.1217 0.9932 0.9966

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
135M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MayBashendy/ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task3_organization

Finetuned
(3994)
this model