ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k16_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: 1.0278
  • Qwk: 0.6462
  • Mse: 1.0278
  • Rmse: 1.0138

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 0.0377 2 2.2489 0.0523 2.2489 1.4996
No log 0.0755 4 1.4613 0.1815 1.4613 1.2088
No log 0.1132 6 1.3887 0.1575 1.3887 1.1784
No log 0.1509 8 1.4162 0.2015 1.4162 1.1900
No log 0.1887 10 1.5631 0.3510 1.5631 1.2502
No log 0.2264 12 1.6306 0.3322 1.6306 1.2769
No log 0.2642 14 1.5097 0.1666 1.5097 1.2287
No log 0.3019 16 1.4299 0.1711 1.4299 1.1958
No log 0.3396 18 1.4116 0.1258 1.4116 1.1881
No log 0.3774 20 1.4241 0.1711 1.4241 1.1934
No log 0.4151 22 1.5291 0.3109 1.5291 1.2366
No log 0.4528 24 1.6232 0.3769 1.6232 1.2740
No log 0.4906 26 1.7126 0.3318 1.7126 1.3087
No log 0.5283 28 1.7142 0.3329 1.7142 1.3093
No log 0.5660 30 1.6618 0.3950 1.6618 1.2891
No log 0.6038 32 1.6418 0.3853 1.6418 1.2813
No log 0.6415 34 1.5816 0.3134 1.5816 1.2576
No log 0.6792 36 1.5473 0.3101 1.5473 1.2439
No log 0.7170 38 1.6520 0.3439 1.6520 1.2853
No log 0.7547 40 1.8531 0.3136 1.8531 1.3613
No log 0.7925 42 1.9959 0.2766 1.9959 1.4127
No log 0.8302 44 1.8526 0.3054 1.8526 1.3611
No log 0.8679 46 1.5661 0.3614 1.5661 1.2514
No log 0.9057 48 1.3676 0.4335 1.3676 1.1695
No log 0.9434 50 1.2637 0.4656 1.2637 1.1241
No log 0.9811 52 1.1884 0.5170 1.1884 1.0902
No log 1.0189 54 1.3761 0.4555 1.3761 1.1731
No log 1.0566 56 1.6777 0.4420 1.6777 1.2953
No log 1.0943 58 1.8271 0.4294 1.8271 1.3517
No log 1.1321 60 1.6343 0.4685 1.6343 1.2784
No log 1.1698 62 1.6704 0.4778 1.6704 1.2924
No log 1.2075 64 1.8927 0.4393 1.8927 1.3758
No log 1.2453 66 1.8382 0.4390 1.8382 1.3558
No log 1.2830 68 1.7684 0.4355 1.7684 1.3298
No log 1.3208 70 1.6071 0.4780 1.6071 1.2677
No log 1.3585 72 1.3052 0.5144 1.3052 1.1424
No log 1.3962 74 1.1610 0.5357 1.1610 1.0775
No log 1.4340 76 1.3522 0.5010 1.3522 1.1629
No log 1.4717 78 1.9281 0.4741 1.9281 1.3886
No log 1.5094 80 2.2271 0.4607 2.2271 1.4923
No log 1.5472 82 2.1050 0.4721 2.1050 1.4509
No log 1.5849 84 1.6810 0.4981 1.6810 1.2965
No log 1.6226 86 1.6228 0.4886 1.6228 1.2739
No log 1.6604 88 1.7947 0.4825 1.7947 1.3397
No log 1.6981 90 1.9372 0.4598 1.9372 1.3918
No log 1.7358 92 1.9144 0.4814 1.9144 1.3836
No log 1.7736 94 1.7176 0.4994 1.7176 1.3106
No log 1.8113 96 1.6005 0.5429 1.6005 1.2651
No log 1.8491 98 1.3956 0.5780 1.3956 1.1814
No log 1.8868 100 1.1334 0.6136 1.1334 1.0646
No log 1.9245 102 1.1253 0.6099 1.1253 1.0608
No log 1.9623 104 1.0380 0.6665 1.0380 1.0188
No log 2.0 106 1.0993 0.6122 1.0993 1.0485
No log 2.0377 108 1.2436 0.5880 1.2436 1.1152
No log 2.0755 110 1.2914 0.6062 1.2914 1.1364
No log 2.1132 112 1.4993 0.5623 1.4993 1.2245
No log 2.1509 114 1.6392 0.5531 1.6392 1.2803
No log 2.1887 116 1.6709 0.5435 1.6709 1.2926
No log 2.2264 118 1.5655 0.5552 1.5655 1.2512
No log 2.2642 120 1.3433 0.5727 1.3433 1.1590
No log 2.3019 122 1.3008 0.5652 1.3008 1.1405
No log 2.3396 124 1.2348 0.5775 1.2348 1.1112
No log 2.3774 126 1.2530 0.5794 1.2530 1.1194
No log 2.4151 128 1.4127 0.5474 1.4127 1.1886
No log 2.4528 130 1.4241 0.5460 1.4241 1.1934
No log 2.4906 132 1.2559 0.5603 1.2559 1.1207
No log 2.5283 134 1.1744 0.5736 1.1744 1.0837
No log 2.5660 136 1.4005 0.5517 1.4005 1.1834
No log 2.6038 138 1.4113 0.5561 1.4113 1.1880
No log 2.6415 140 1.4057 0.5540 1.4057 1.1856
No log 2.6792 142 1.2765 0.5668 1.2765 1.1298
No log 2.7170 144 1.1000 0.5906 1.1000 1.0488
No log 2.7547 146 1.0980 0.5873 1.0980 1.0478
No log 2.7925 148 1.1821 0.5688 1.1821 1.0873
No log 2.8302 150 1.1415 0.5805 1.1415 1.0684
No log 2.8679 152 0.9420 0.6606 0.9420 0.9705
No log 2.9057 154 0.9355 0.6606 0.9355 0.9672
No log 2.9434 156 0.9568 0.6517 0.9568 0.9781
No log 2.9811 158 1.0115 0.6263 1.0115 1.0057
No log 3.0189 160 0.9718 0.6470 0.9718 0.9858
No log 3.0566 162 1.1659 0.5965 1.1659 1.0798
No log 3.0943 164 1.4855 0.5788 1.4855 1.2188
No log 3.1321 166 1.3369 0.5736 1.3369 1.1562
No log 3.1698 168 1.0425 0.6261 1.0425 1.0210
No log 3.2075 170 0.8930 0.6723 0.8930 0.9450
No log 3.2453 172 1.0002 0.6496 1.0002 1.0001
No log 3.2830 174 1.2463 0.5688 1.2463 1.1164
No log 3.3208 176 1.5706 0.5344 1.5706 1.2532
No log 3.3585 178 1.4934 0.5453 1.4934 1.2221
No log 3.3962 180 1.2412 0.5717 1.2412 1.1141
No log 3.4340 182 0.9461 0.6723 0.9461 0.9727
No log 3.4717 184 0.8855 0.6861 0.8855 0.9410
No log 3.5094 186 1.0229 0.6087 1.0229 1.0114
No log 3.5472 188 1.1166 0.6071 1.1166 1.0567
No log 3.5849 190 1.0165 0.6127 1.0165 1.0082
No log 3.6226 192 0.9657 0.6299 0.9657 0.9827
No log 3.6604 194 0.8798 0.6884 0.8798 0.9380
No log 3.6981 196 0.9121 0.6768 0.9121 0.9550
No log 3.7358 198 1.0084 0.6418 1.0084 1.0042
No log 3.7736 200 1.1114 0.6010 1.1114 1.0542
No log 3.8113 202 1.1621 0.6010 1.1621 1.0780
No log 3.8491 204 1.0302 0.6207 1.0302 1.0150
No log 3.8868 206 0.9187 0.6552 0.9187 0.9585
No log 3.9245 208 0.8743 0.6592 0.8743 0.9350
No log 3.9623 210 1.0026 0.6269 1.0026 1.0013
No log 4.0 212 1.3462 0.5711 1.3462 1.1603
No log 4.0377 214 1.6942 0.5245 1.6942 1.3016
No log 4.0755 216 1.7152 0.5355 1.7152 1.3097
No log 4.1132 218 1.4307 0.5635 1.4307 1.1961
No log 4.1509 220 1.0824 0.6282 1.0824 1.0404
No log 4.1887 222 0.8438 0.6797 0.8438 0.9186
No log 4.2264 224 0.8410 0.6616 0.8410 0.9170
No log 4.2642 226 0.9972 0.6219 0.9972 0.9986
No log 4.3019 228 1.3307 0.5797 1.3307 1.1536
No log 4.3396 230 1.7150 0.5259 1.7150 1.3096
No log 4.3774 232 1.7919 0.5181 1.7919 1.3386
No log 4.4151 234 1.6430 0.5336 1.6430 1.2818
No log 4.4528 236 1.3447 0.5629 1.3447 1.1596
No log 4.4906 238 1.1345 0.5928 1.1345 1.0651
No log 4.5283 240 1.0517 0.6359 1.0517 1.0255
No log 4.5660 242 1.1241 0.5897 1.1241 1.0602
No log 4.6038 244 1.1036 0.6110 1.1036 1.0505
No log 4.6415 246 1.1139 0.6156 1.1139 1.0554
No log 4.6792 248 1.1620 0.6117 1.1620 1.0780
No log 4.7170 250 1.1070 0.6282 1.1070 1.0521
No log 4.7547 252 0.9593 0.6420 0.9593 0.9795
No log 4.7925 254 0.9450 0.6354 0.9450 0.9721
No log 4.8302 256 0.9610 0.6325 0.9610 0.9803
No log 4.8679 258 0.9738 0.6311 0.9738 0.9868
No log 4.9057 260 0.9538 0.6542 0.9538 0.9766
No log 4.9434 262 0.9604 0.6475 0.9604 0.9800
No log 4.9811 264 0.9047 0.6750 0.9047 0.9512
No log 5.0189 266 0.8147 0.6979 0.8147 0.9026
No log 5.0566 268 0.7858 0.7188 0.7858 0.8864
No log 5.0943 270 0.7928 0.7185 0.7928 0.8904
No log 5.1321 272 0.7889 0.7185 0.7889 0.8882
No log 5.1698 274 0.7856 0.7230 0.7856 0.8863
No log 5.2075 276 0.9034 0.6664 0.9034 0.9505
No log 5.2453 278 1.1233 0.6119 1.1233 1.0598
No log 5.2830 280 1.2973 0.5521 1.2973 1.1390
No log 5.3208 282 1.2968 0.5450 1.2968 1.1388
No log 5.3585 284 1.1928 0.5727 1.1928 1.0922
No log 5.3962 286 1.1480 0.5920 1.1480 1.0714
No log 5.4340 288 1.1247 0.6068 1.1247 1.0605
No log 5.4717 290 1.0367 0.6423 1.0367 1.0182
No log 5.5094 292 1.0113 0.6439 1.0113 1.0057
No log 5.5472 294 1.0842 0.6165 1.0842 1.0412
No log 5.5849 296 1.1344 0.6020 1.1344 1.0651
No log 5.6226 298 1.1445 0.6070 1.1445 1.0698
No log 5.6604 300 1.0471 0.6227 1.0471 1.0233
No log 5.6981 302 0.9805 0.6402 0.9805 0.9902
No log 5.7358 304 0.8900 0.6421 0.8900 0.9434
No log 5.7736 306 0.8109 0.6855 0.8109 0.9005
No log 5.8113 308 0.7778 0.6895 0.7778 0.8820
No log 5.8491 310 0.8201 0.6855 0.8201 0.9056
No log 5.8868 312 0.9533 0.6426 0.9533 0.9764
No log 5.9245 314 1.0444 0.6521 1.0444 1.0220
No log 5.9623 316 1.1996 0.6069 1.1996 1.0953
No log 6.0 318 1.2325 0.6099 1.2325 1.1102
No log 6.0377 320 1.1182 0.6498 1.1182 1.0575
No log 6.0755 322 0.9756 0.6402 0.9756 0.9877
No log 6.1132 324 0.9629 0.6407 0.9629 0.9813
No log 6.1509 326 0.9965 0.6421 0.9965 0.9983
No log 6.1887 328 1.0846 0.6289 1.0846 1.0415
No log 6.2264 330 1.2648 0.5790 1.2648 1.1246
No log 6.2642 332 1.3464 0.5788 1.3464 1.1604
No log 6.3019 334 1.3065 0.5891 1.3065 1.1430
No log 6.3396 336 1.2713 0.6146 1.2713 1.1275
No log 6.3774 338 1.2297 0.6257 1.2297 1.1089
No log 6.4151 340 1.2031 0.6405 1.2031 1.0969
No log 6.4528 342 1.1365 0.6216 1.1365 1.0661
No log 6.4906 344 1.0839 0.6347 1.0839 1.0411
No log 6.5283 346 1.0841 0.6347 1.0841 1.0412
No log 6.5660 348 1.1467 0.6216 1.1467 1.0708
No log 6.6038 350 1.1731 0.6257 1.1731 1.0831
No log 6.6415 352 1.2687 0.6193 1.2687 1.1264
No log 6.6792 354 1.2943 0.6141 1.2943 1.1377
No log 6.7170 356 1.2489 0.6217 1.2489 1.1175
No log 6.7547 358 1.1212 0.6372 1.1212 1.0589
No log 6.7925 360 1.0735 0.6360 1.0735 1.0361
No log 6.8302 362 1.1071 0.6360 1.1071 1.0522
No log 6.8679 364 1.1215 0.6346 1.1215 1.0590
No log 6.9057 366 1.1427 0.6359 1.1427 1.0690
No log 6.9434 368 1.1435 0.6441 1.1435 1.0694
No log 6.9811 370 1.1846 0.6424 1.1846 1.0884
No log 7.0189 372 1.1663 0.6359 1.1663 1.0799
No log 7.0566 374 1.0991 0.6407 1.0991 1.0484
No log 7.0943 376 1.0622 0.6407 1.0622 1.0306
No log 7.1321 378 1.0070 0.6462 1.0070 1.0035
No log 7.1698 380 0.9385 0.6521 0.9385 0.9688
No log 7.2075 382 0.9263 0.6521 0.9263 0.9625
No log 7.2453 384 0.9908 0.6567 0.9908 0.9954
No log 7.2830 386 1.1235 0.6386 1.1235 1.0599
No log 7.3208 388 1.2385 0.5922 1.2385 1.1129
No log 7.3585 390 1.2625 0.5861 1.2625 1.1236
No log 7.3962 392 1.1946 0.6186 1.1946 1.0930
No log 7.4340 394 1.0577 0.6536 1.0577 1.0285
No log 7.4717 396 0.9664 0.6591 0.9664 0.9831
No log 7.5094 398 0.9272 0.6647 0.9272 0.9629
No log 7.5472 400 0.9412 0.6682 0.9412 0.9702
No log 7.5849 402 1.0151 0.6541 1.0151 1.0075
No log 7.6226 404 1.1127 0.6206 1.1127 1.0548
No log 7.6604 406 1.1704 0.6092 1.1704 1.0819
No log 7.6981 408 1.1925 0.6092 1.1925 1.0920
No log 7.7358 410 1.1424 0.6092 1.1424 1.0688
No log 7.7736 412 1.0557 0.6431 1.0557 1.0275
No log 7.8113 414 0.9467 0.6639 0.9467 0.9730
No log 7.8491 416 0.8738 0.6575 0.8738 0.9348
No log 7.8868 418 0.8421 0.6984 0.8421 0.9177
No log 7.9245 420 0.8491 0.7028 0.8491 0.9215
No log 7.9623 422 0.8862 0.6786 0.8862 0.9414
No log 8.0 424 0.9542 0.6557 0.9542 0.9769
No log 8.0377 426 1.0235 0.6423 1.0235 1.0117
No log 8.0755 428 1.0729 0.6398 1.0729 1.0358
No log 8.1132 430 1.1038 0.6326 1.1038 1.0506
No log 8.1509 432 1.0828 0.6326 1.0828 1.0406
No log 8.1887 434 1.0156 0.6541 1.0156 1.0077
No log 8.2264 436 0.9228 0.6656 0.9228 0.9606
No log 8.2642 438 0.8553 0.6909 0.8553 0.9248
No log 8.3019 440 0.8285 0.6972 0.8285 0.9102
No log 8.3396 442 0.8367 0.6972 0.8367 0.9147
No log 8.3774 444 0.8680 0.6909 0.8680 0.9317
No log 8.4151 446 0.9097 0.6656 0.9097 0.9538
No log 8.4528 448 0.9802 0.6592 0.9802 0.9900
No log 8.4906 450 1.0355 0.6571 1.0355 1.0176
No log 8.5283 452 1.0733 0.6444 1.0733 1.0360
No log 8.5660 454 1.1153 0.6274 1.1153 1.0561
No log 8.6038 456 1.1545 0.6318 1.1545 1.0745
No log 8.6415 458 1.1614 0.6209 1.1614 1.0777
No log 8.6792 460 1.1294 0.6247 1.1294 1.0627
No log 8.7170 462 1.0850 0.6274 1.0850 1.0416
No log 8.7547 464 1.0630 0.6328 1.0630 1.0310
No log 8.7925 466 1.0565 0.6328 1.0565 1.0279
No log 8.8302 468 1.0681 0.6328 1.0681 1.0335
No log 8.8679 470 1.0730 0.6328 1.0730 1.0359
No log 8.9057 472 1.0804 0.6328 1.0804 1.0394
No log 8.9434 474 1.0930 0.6412 1.0930 1.0455
No log 8.9811 476 1.0849 0.6412 1.0849 1.0416
No log 9.0189 478 1.0737 0.6412 1.0737 1.0362
No log 9.0566 480 1.0530 0.6328 1.0530 1.0261
No log 9.0943 482 1.0612 0.6328 1.0612 1.0302
No log 9.1321 484 1.0631 0.6551 1.0631 1.0310
No log 9.1698 486 1.0747 0.6389 1.0747 1.0367
No log 9.2075 488 1.0997 0.6328 1.0997 1.0487
No log 9.2453 490 1.1057 0.6242 1.1057 1.0515
No log 9.2830 492 1.0985 0.6287 1.0985 1.0481
No log 9.3208 494 1.0902 0.6447 1.0902 1.0441
No log 9.3585 496 1.0668 0.6551 1.0668 1.0329
No log 9.3962 498 1.0576 0.6551 1.0576 1.0284
0.3535 9.4340 500 1.0525 0.6551 1.0525 1.0259
0.3535 9.4717 502 1.0475 0.6551 1.0475 1.0235
0.3535 9.5094 504 1.0528 0.6462 1.0528 1.0261
0.3535 9.5472 506 1.0613 0.6462 1.0613 1.0302
0.3535 9.5849 508 1.0619 0.6462 1.0619 1.0305
0.3535 9.6226 510 1.0558 0.6462 1.0558 1.0275
0.3535 9.6604 512 1.0501 0.6462 1.0501 1.0248
0.3535 9.6981 514 1.0455 0.6462 1.0455 1.0225
0.3535 9.7358 516 1.0391 0.6462 1.0391 1.0194
0.3535 9.7736 518 1.0350 0.6462 1.0350 1.0174
0.3535 9.8113 520 1.0331 0.6462 1.0331 1.0164
0.3535 9.8491 522 1.0335 0.6462 1.0335 1.0166
0.3535 9.8868 524 1.0323 0.6462 1.0323 1.0160
0.3535 9.9245 526 1.0298 0.6462 1.0298 1.0148
0.3535 9.9623 528 1.0286 0.6462 1.0286 1.0142
0.3535 10.0 530 1.0278 0.6462 1.0278 1.0138

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
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/ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k16_task5_organization

Finetuned
(4040)
this model