ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k12_task5_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: 0.8538
  • Qwk: 0.6518
  • Mse: 0.8538
  • Rmse: 0.9240

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0351 2 2.3178 -0.0013 2.3178 1.5224
No log 0.0702 4 1.6379 0.1787 1.6379 1.2798
No log 0.1053 6 1.7637 -0.0044 1.7637 1.3280
No log 0.1404 8 2.0925 -0.0413 2.0925 1.4465
No log 0.1754 10 1.8422 0.0706 1.8422 1.3573
No log 0.2105 12 1.4101 0.1109 1.4101 1.1875
No log 0.2456 14 1.3535 0.1347 1.3535 1.1634
No log 0.2807 16 1.4129 0.1589 1.4129 1.1886
No log 0.3158 18 1.4061 0.1427 1.4061 1.1858
No log 0.3509 20 1.4030 0.1697 1.4030 1.1845
No log 0.3860 22 1.3829 0.1742 1.3829 1.1760
No log 0.4211 24 1.3441 0.1400 1.3441 1.1594
No log 0.4561 26 1.3150 0.1802 1.3150 1.1467
No log 0.4912 28 1.2786 0.1948 1.2786 1.1307
No log 0.5263 30 1.2373 0.2315 1.2373 1.1124
No log 0.5614 32 1.2273 0.2546 1.2273 1.1078
No log 0.5965 34 1.2029 0.2852 1.2029 1.0968
No log 0.6316 36 1.1922 0.2880 1.1922 1.0919
No log 0.6667 38 1.1792 0.3347 1.1792 1.0859
No log 0.7018 40 1.1563 0.3785 1.1563 1.0753
No log 0.7368 42 1.1231 0.3572 1.1231 1.0598
No log 0.7719 44 1.0996 0.4234 1.0996 1.0486
No log 0.8070 46 1.1165 0.4060 1.1165 1.0567
No log 0.8421 48 1.2246 0.4166 1.2246 1.1066
No log 0.8772 50 1.1948 0.4392 1.1948 1.0930
No log 0.9123 52 1.2044 0.4449 1.2044 1.0974
No log 0.9474 54 1.0905 0.5238 1.0905 1.0443
No log 0.9825 56 1.0561 0.4598 1.0561 1.0277
No log 1.0175 58 1.0554 0.4319 1.0554 1.0273
No log 1.0526 60 1.0033 0.5273 1.0033 1.0016
No log 1.0877 62 1.2033 0.3526 1.2033 1.0969
No log 1.1228 64 1.3664 0.2592 1.3664 1.1690
No log 1.1579 66 1.2987 0.2682 1.2987 1.1396
No log 1.1930 68 1.0575 0.4514 1.0575 1.0284
No log 1.2281 70 0.9775 0.4980 0.9775 0.9887
No log 1.2632 72 0.9833 0.4901 0.9833 0.9916
No log 1.2982 74 0.9579 0.4617 0.9579 0.9787
No log 1.3333 76 0.9904 0.5066 0.9904 0.9952
No log 1.3684 78 1.1125 0.4334 1.1125 1.0548
No log 1.4035 80 1.1606 0.3934 1.1606 1.0773
No log 1.4386 82 1.1454 0.4126 1.1454 1.0702
No log 1.4737 84 1.1550 0.4401 1.1550 1.0747
No log 1.5088 86 1.0881 0.5002 1.0881 1.0431
No log 1.5439 88 1.1197 0.5026 1.1197 1.0582
No log 1.5789 90 1.3791 0.4220 1.3791 1.1743
No log 1.6140 92 1.6312 0.3753 1.6312 1.2772
No log 1.6491 94 1.7660 0.3486 1.7660 1.3289
No log 1.6842 96 1.8010 0.3468 1.8010 1.3420
No log 1.7193 98 1.6804 0.3333 1.6804 1.2963
No log 1.7544 100 1.4474 0.3751 1.4474 1.2031
No log 1.7895 102 1.5378 0.3473 1.5378 1.2401
No log 1.8246 104 1.4140 0.3919 1.4140 1.1891
No log 1.8596 106 1.3074 0.4862 1.3074 1.1434
No log 1.8947 108 1.3441 0.4482 1.3441 1.1593
No log 1.9298 110 1.2587 0.4822 1.2587 1.1219
No log 1.9649 112 1.0785 0.5682 1.0785 1.0385
No log 2.0 114 1.0295 0.5570 1.0295 1.0147
No log 2.0351 116 1.1397 0.5342 1.1397 1.0676
No log 2.0702 118 1.1730 0.5224 1.1730 1.0830
No log 2.1053 120 1.1922 0.5290 1.1922 1.0919
No log 2.1404 122 1.1426 0.5465 1.1426 1.0689
No log 2.1754 124 0.9891 0.5824 0.9891 0.9945
No log 2.2105 126 1.0065 0.6119 1.0065 1.0032
No log 2.2456 128 1.1383 0.5813 1.1383 1.0669
No log 2.2807 130 1.1375 0.5863 1.1375 1.0665
No log 2.3158 132 0.9579 0.6620 0.9579 0.9787
No log 2.3509 134 0.8164 0.6366 0.8164 0.9036
No log 2.3860 136 0.7971 0.6317 0.7971 0.8928
No log 2.4211 138 0.8048 0.6405 0.8048 0.8971
No log 2.4561 140 0.9190 0.6392 0.9190 0.9586
No log 2.4912 142 1.0813 0.5869 1.0813 1.0399
No log 2.5263 144 1.0555 0.5950 1.0555 1.0274
No log 2.5614 146 0.9269 0.6369 0.9269 0.9628
No log 2.5965 148 0.7911 0.6443 0.7911 0.8894
No log 2.6316 150 0.7650 0.6473 0.7650 0.8746
No log 2.6667 152 0.7552 0.6483 0.7552 0.8690
No log 2.7018 154 0.7931 0.6776 0.7931 0.8906
No log 2.7368 156 0.9051 0.6703 0.9051 0.9514
No log 2.7719 158 0.8814 0.6802 0.8814 0.9388
No log 2.8070 160 0.7733 0.6859 0.7733 0.8794
No log 2.8421 162 0.6956 0.7139 0.6956 0.8340
No log 2.8772 164 0.6813 0.6815 0.6813 0.8254
No log 2.9123 166 0.7029 0.7380 0.7029 0.8384
No log 2.9474 168 0.8407 0.6554 0.8407 0.9169
No log 2.9825 170 1.2353 0.5974 1.2353 1.1114
No log 3.0175 172 1.4156 0.5747 1.4156 1.1898
No log 3.0526 174 1.3245 0.5806 1.3245 1.1509
No log 3.0877 176 1.0334 0.6300 1.0334 1.0166
No log 3.1228 178 0.8457 0.6679 0.8457 0.9196
No log 3.1579 180 0.7646 0.6767 0.7646 0.8744
No log 3.1930 182 0.7600 0.6804 0.7600 0.8718
No log 3.2281 184 0.7752 0.6705 0.7752 0.8805
No log 3.2632 186 0.7907 0.6433 0.7907 0.8892
No log 3.2982 188 0.8758 0.6326 0.8758 0.9358
No log 3.3333 190 1.0605 0.6464 1.0605 1.0298
No log 3.3684 192 1.1799 0.6367 1.1799 1.0862
No log 3.4035 194 1.1653 0.6293 1.1653 1.0795
No log 3.4386 196 0.9748 0.6821 0.9748 0.9873
No log 3.4737 198 0.8796 0.6922 0.8796 0.9379
No log 3.5088 200 0.7764 0.6648 0.7764 0.8811
No log 3.5439 202 0.7648 0.6611 0.7648 0.8745
No log 3.5789 204 0.8576 0.6714 0.8576 0.9261
No log 3.6140 206 0.9624 0.6555 0.9624 0.9810
No log 3.6491 208 1.1696 0.6280 1.1696 1.0815
No log 3.6842 210 1.1749 0.6338 1.1749 1.0839
No log 3.7193 212 0.9976 0.6412 0.9976 0.9988
No log 3.7544 214 0.8374 0.6949 0.8374 0.9151
No log 3.7895 216 0.7568 0.6343 0.7568 0.8699
No log 3.8246 218 0.7805 0.6371 0.7805 0.8835
No log 3.8596 220 0.7706 0.6259 0.7706 0.8778
No log 3.8947 222 0.7477 0.6564 0.7477 0.8647
No log 3.9298 224 0.8718 0.6573 0.8718 0.9337
No log 3.9649 226 1.1421 0.6282 1.1421 1.0687
No log 4.0 228 1.2403 0.6255 1.2403 1.1137
No log 4.0351 230 1.1203 0.6250 1.1203 1.0584
No log 4.0702 232 0.9071 0.6554 0.9071 0.9524
No log 4.1053 234 0.7250 0.6537 0.7250 0.8514
No log 4.1404 236 0.6873 0.6855 0.6873 0.8290
No log 4.1754 238 0.6979 0.6818 0.6979 0.8354
No log 4.2105 240 0.7612 0.6784 0.7612 0.8724
No log 4.2456 242 0.9324 0.6489 0.9324 0.9656
No log 4.2807 244 1.1724 0.6245 1.1724 1.0828
No log 4.3158 246 1.2135 0.6010 1.2135 1.1016
No log 4.3509 248 1.1645 0.6272 1.1645 1.0791
No log 4.3860 250 1.0820 0.6286 1.0820 1.0402
No log 4.4211 252 1.1254 0.6170 1.1254 1.0609
No log 4.4561 254 1.2301 0.6029 1.2301 1.1091
No log 4.4912 256 1.1910 0.6095 1.1910 1.0913
No log 4.5263 258 1.2227 0.6009 1.2227 1.1058
No log 4.5614 260 1.2232 0.5967 1.2232 1.1060
No log 4.5965 262 1.0783 0.6344 1.0783 1.0384
No log 4.6316 264 0.9804 0.6310 0.9804 0.9901
No log 4.6667 266 0.9024 0.6243 0.9024 0.9499
No log 4.7018 268 0.8210 0.6678 0.8210 0.9061
No log 4.7368 270 0.7737 0.6463 0.7737 0.8796
No log 4.7719 272 0.7924 0.6611 0.7924 0.8902
No log 4.8070 274 0.9027 0.6424 0.9027 0.9501
No log 4.8421 276 1.0633 0.6350 1.0633 1.0312
No log 4.8772 278 1.1744 0.6204 1.1744 1.0837
No log 4.9123 280 1.1215 0.6319 1.1215 1.0590
No log 4.9474 282 1.1028 0.6347 1.1028 1.0501
No log 4.9825 284 1.1265 0.6434 1.1265 1.0614
No log 5.0175 286 1.0578 0.6425 1.0578 1.0285
No log 5.0526 288 1.0204 0.6425 1.0204 1.0101
No log 5.0877 290 1.0194 0.6425 1.0194 1.0097
No log 5.1228 292 1.0389 0.6437 1.0389 1.0193
No log 5.1579 294 1.0842 0.6347 1.0842 1.0412
No log 5.1930 296 1.0775 0.6347 1.0775 1.0380
No log 5.2281 298 0.9948 0.6286 0.9948 0.9974
No log 5.2632 300 0.8548 0.6631 0.8548 0.9246
No log 5.2982 302 0.7634 0.6829 0.7634 0.8737
No log 5.3333 304 0.7578 0.6930 0.7578 0.8705
No log 5.3684 306 0.8047 0.6621 0.8047 0.8971
No log 5.4035 308 0.8904 0.6617 0.8904 0.9436
No log 5.4386 310 0.9758 0.6655 0.9758 0.9879
No log 5.4737 312 1.0135 0.6616 1.0135 1.0067
No log 5.5088 314 1.0220 0.6575 1.0220 1.0110
No log 5.5439 316 0.9705 0.6542 0.9705 0.9851
No log 5.5789 318 0.8760 0.6495 0.8760 0.9359
No log 5.6140 320 0.8495 0.6438 0.8495 0.9217
No log 5.6491 322 0.8632 0.6392 0.8632 0.9291
No log 5.6842 324 0.8943 0.6569 0.8943 0.9457
No log 5.7193 326 0.9710 0.6556 0.9710 0.9854
No log 5.7544 328 1.1024 0.6327 1.1024 1.0499
No log 5.7895 330 1.1729 0.6312 1.1729 1.0830
No log 5.8246 332 1.1178 0.6368 1.1178 1.0573
No log 5.8596 334 1.0049 0.6653 1.0049 1.0025
No log 5.8947 336 0.8615 0.6605 0.8615 0.9282
No log 5.9298 338 0.8073 0.6386 0.8073 0.8985
No log 5.9649 340 0.8038 0.6386 0.8038 0.8966
No log 6.0 342 0.8484 0.6633 0.8484 0.9211
No log 6.0351 344 0.9244 0.6467 0.9244 0.9614
No log 6.0702 346 0.9411 0.6687 0.9411 0.9701
No log 6.1053 348 0.9731 0.6600 0.9731 0.9865
No log 6.1404 350 0.9438 0.6723 0.9438 0.9715
No log 6.1754 352 0.9261 0.6634 0.9261 0.9624
No log 6.2105 354 0.9246 0.6634 0.9246 0.9615
No log 6.2456 356 0.8733 0.6560 0.8733 0.9345
No log 6.2807 358 0.8246 0.6294 0.8246 0.9081
No log 6.3158 360 0.8315 0.6413 0.8315 0.9119
No log 6.3509 362 0.8592 0.6571 0.8592 0.9269
No log 6.3860 364 0.9401 0.6705 0.9401 0.9696
No log 6.4211 366 1.0097 0.6402 1.0097 1.0048
No log 6.4561 368 1.0227 0.6492 1.0227 1.0113
No log 6.4912 370 1.0332 0.6492 1.0332 1.0164
No log 6.5263 372 0.9745 0.6585 0.9745 0.9872
No log 6.5614 374 0.8862 0.6526 0.8862 0.9414
No log 6.5965 376 0.8004 0.6569 0.8004 0.8947
No log 6.6316 378 0.7687 0.6781 0.7687 0.8767
No log 6.6667 380 0.7661 0.6781 0.7661 0.8753
No log 6.7018 382 0.7955 0.6659 0.7955 0.8919
No log 6.7368 384 0.8818 0.6526 0.8818 0.9390
No log 6.7719 386 0.9800 0.6372 0.9800 0.9899
No log 6.8070 388 1.0271 0.6300 1.0271 1.0135
No log 6.8421 390 1.0943 0.6305 1.0943 1.0461
No log 6.8772 392 1.0988 0.6347 1.0988 1.0482
No log 6.9123 394 1.0440 0.6286 1.0440 1.0218
No log 6.9474 396 0.9684 0.6418 0.9684 0.9841
No log 6.9825 398 0.9386 0.6521 0.9386 0.9688
No log 7.0175 400 0.9098 0.6521 0.9098 0.9538
No log 7.0526 402 0.8811 0.6365 0.8811 0.9387
No log 7.0877 404 0.8927 0.6365 0.8927 0.9448
No log 7.1228 406 0.8882 0.6365 0.8882 0.9424
No log 7.1579 408 0.8994 0.6521 0.8994 0.9484
No log 7.1930 410 0.9058 0.6477 0.9058 0.9517
No log 7.2281 412 0.9065 0.6477 0.9065 0.9521
No log 7.2632 414 0.8849 0.6697 0.8849 0.9407
No log 7.2982 416 0.8667 0.6634 0.8667 0.9310
No log 7.3333 418 0.8528 0.6616 0.8528 0.9235
No log 7.3684 420 0.8495 0.6616 0.8495 0.9217
No log 7.4035 422 0.8733 0.6554 0.8733 0.9345
No log 7.4386 424 0.9096 0.6465 0.9096 0.9537
No log 7.4737 426 0.9060 0.6369 0.9060 0.9519
No log 7.5088 428 0.8942 0.6369 0.8942 0.9456
No log 7.5439 430 0.8876 0.6325 0.8876 0.9421
No log 7.5789 432 0.8766 0.6465 0.8766 0.9363
No log 7.6140 434 0.9054 0.6325 0.9054 0.9515
No log 7.6491 436 0.9517 0.6480 0.9517 0.9755
No log 7.6842 438 0.9654 0.6492 0.9654 0.9825
No log 7.7193 440 0.9875 0.6526 0.9875 0.9938
No log 7.7544 442 0.9929 0.6476 0.9929 0.9965
No log 7.7895 444 0.9878 0.6476 0.9878 0.9939
No log 7.8246 446 0.9626 0.6480 0.9626 0.9811
No log 7.8596 448 0.9263 0.6389 0.9263 0.9625
No log 7.8947 450 0.8884 0.6369 0.8884 0.9426
No log 7.9298 452 0.8739 0.6430 0.8739 0.9348
No log 7.9649 454 0.8683 0.6482 0.8683 0.9318
No log 8.0 456 0.8768 0.6325 0.8768 0.9364
No log 8.0351 458 0.8795 0.6325 0.8795 0.9378
No log 8.0702 460 0.8979 0.6325 0.8979 0.9476
No log 8.1053 462 0.9443 0.6424 0.9443 0.9717
No log 8.1404 464 0.9929 0.6499 0.9929 0.9964
No log 8.1754 466 1.0115 0.6468 1.0115 1.0057
No log 8.2105 468 1.0216 0.6468 1.0216 1.0108
No log 8.2456 470 0.9898 0.6510 0.9898 0.9949
No log 8.2807 472 0.9439 0.6360 0.9439 0.9716
No log 8.3158 474 0.9125 0.6369 0.9125 0.9552
No log 8.3509 476 0.8702 0.6679 0.8702 0.9328
No log 8.3860 478 0.8229 0.6867 0.8229 0.9072
No log 8.4211 480 0.8032 0.6778 0.8032 0.8962
No log 8.4561 482 0.8012 0.6778 0.8012 0.8951
No log 8.4912 484 0.8064 0.6867 0.8064 0.8980
No log 8.5263 486 0.8289 0.6867 0.8289 0.9105
No log 8.5614 488 0.8561 0.6705 0.8561 0.9253
No log 8.5965 490 0.8869 0.6435 0.8869 0.9418
No log 8.6316 492 0.9370 0.6505 0.9370 0.9680
No log 8.6667 494 0.9644 0.6387 0.9644 0.9820
No log 8.7018 496 0.9730 0.6385 0.9730 0.9864
No log 8.7368 498 0.9592 0.6508 0.9592 0.9794
0.3194 8.7719 500 0.9379 0.6619 0.9379 0.9685
0.3194 8.8070 502 0.9074 0.6538 0.9074 0.9526
0.3194 8.8421 504 0.8823 0.6502 0.8823 0.9393
0.3194 8.8772 506 0.8628 0.6546 0.8628 0.9289
0.3194 8.9123 508 0.8451 0.6597 0.8451 0.9193
0.3194 8.9474 510 0.8469 0.6499 0.8469 0.9203
0.3194 8.9825 512 0.8517 0.6563 0.8517 0.9229
0.3194 9.0175 514 0.8663 0.6546 0.8663 0.9308
0.3194 9.0526 516 0.8759 0.6502 0.8759 0.9359
0.3194 9.0877 518 0.8877 0.6592 0.8877 0.9422
0.3194 9.1228 520 0.8867 0.6592 0.8867 0.9416
0.3194 9.1579 522 0.8747 0.6502 0.8747 0.9353
0.3194 9.1930 524 0.8660 0.6518 0.8660 0.9306
0.3194 9.2281 526 0.8664 0.6518 0.8664 0.9308
0.3194 9.2632 528 0.8760 0.6502 0.8760 0.9360
0.3194 9.2982 530 0.8768 0.6502 0.8768 0.9364
0.3194 9.3333 532 0.8838 0.6502 0.8838 0.9401
0.3194 9.3684 534 0.8889 0.6592 0.8889 0.9428
0.3194 9.4035 536 0.8849 0.6502 0.8849 0.9407
0.3194 9.4386 538 0.8815 0.6502 0.8815 0.9389
0.3194 9.4737 540 0.8789 0.6502 0.8789 0.9375
0.3194 9.5088 542 0.8738 0.6502 0.8738 0.9348
0.3194 9.5439 544 0.8676 0.6518 0.8676 0.9315
0.3194 9.5789 546 0.8652 0.6518 0.8652 0.9301
0.3194 9.6140 548 0.8603 0.6518 0.8603 0.9275
0.3194 9.6491 550 0.8579 0.6518 0.8579 0.9263
0.3194 9.6842 552 0.8592 0.6518 0.8592 0.9269
0.3194 9.7193 554 0.8621 0.6502 0.8621 0.9285
0.3194 9.7544 556 0.8625 0.6502 0.8625 0.9287
0.3194 9.7895 558 0.8589 0.6502 0.8589 0.9268
0.3194 9.8246 560 0.8561 0.6502 0.8561 0.9252
0.3194 9.8596 562 0.8553 0.6518 0.8553 0.9248
0.3194 9.8947 564 0.8547 0.6518 0.8547 0.9245
0.3194 9.9298 566 0.8542 0.6518 0.8542 0.9243
0.3194 9.9649 568 0.8541 0.6518 0.8541 0.9242
0.3194 10.0 570 0.8538 0.6518 0.8538 0.9240

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
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/ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k12_task5_organization

Finetuned
(4040)
this model