ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k12_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: 0.9488
  • Qwk: 0.2061
  • Mse: 0.9488
  • Rmse: 0.9741

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 3.1839 -0.0126 3.1839 1.7843
No log 0.0702 4 1.8019 0.0094 1.8019 1.3423
No log 0.1053 6 1.0382 0.0866 1.0382 1.0189
No log 0.1404 8 0.6111 0.0815 0.6111 0.7817
No log 0.1754 10 0.6046 0.0569 0.6046 0.7775
No log 0.2105 12 0.5775 0.1008 0.5775 0.7599
No log 0.2456 14 0.5724 0.1111 0.5724 0.7566
No log 0.2807 16 0.6395 0.2000 0.6395 0.7997
No log 0.3158 18 0.8916 0.0159 0.8916 0.9442
No log 0.3509 20 0.8798 0.0380 0.8798 0.9380
No log 0.3860 22 0.6193 0.1206 0.6193 0.7870
No log 0.4211 24 0.6437 0.0 0.6437 0.8023
No log 0.4561 26 0.7099 -0.0303 0.7099 0.8426
No log 0.4912 28 0.9626 0.0130 0.9626 0.9811
No log 0.5263 30 1.3070 0.0078 1.3070 1.1432
No log 0.5614 32 1.4986 0.0 1.4986 1.2242
No log 0.5965 34 1.4898 0.0 1.4898 1.2206
No log 0.6316 36 1.3498 0.0 1.3498 1.1618
No log 0.6667 38 1.1410 0.0 1.1410 1.0682
No log 0.7018 40 0.9794 0.0 0.9794 0.9896
No log 0.7368 42 0.9739 0.0 0.9739 0.9869
No log 0.7719 44 0.8544 -0.0510 0.8544 0.9243
No log 0.8070 46 0.6883 0.2000 0.6883 0.8297
No log 0.8421 48 0.6509 0.1111 0.6509 0.8068
No log 0.8772 50 0.6233 0.0 0.6233 0.7895
No log 0.9123 52 0.6348 -0.0159 0.6348 0.7968
No log 0.9474 54 0.6822 -0.1111 0.6822 0.8259
No log 0.9825 56 0.7204 -0.0864 0.7204 0.8488
No log 1.0175 58 0.6737 -0.1111 0.6737 0.8208
No log 1.0526 60 0.6889 0.0692 0.6889 0.8300
No log 1.0877 62 0.6828 0.1282 0.6828 0.8263
No log 1.1228 64 0.6907 0.0617 0.6907 0.8311
No log 1.1579 66 0.8273 0.1179 0.8273 0.9096
No log 1.1930 68 1.1591 0.0388 1.1591 1.0766
No log 1.2281 70 1.0262 0.0476 1.0262 1.0130
No log 1.2632 72 0.8816 0.1373 0.8816 0.9390
No log 1.2982 74 0.7133 -0.0196 0.7133 0.8446
No log 1.3333 76 0.8538 0.0805 0.8538 0.9240
No log 1.3684 78 0.8604 0.0800 0.8604 0.9276
No log 1.4035 80 0.7620 0.1209 0.7620 0.8729
No log 1.4386 82 0.8961 0.0928 0.8961 0.9466
No log 1.4737 84 0.9573 0.1186 0.9573 0.9784
No log 1.5088 86 0.9755 0.1000 0.9755 0.9877
No log 1.5439 88 0.8216 0.2143 0.8216 0.9064
No log 1.5789 90 0.7826 0.1852 0.7826 0.8846
No log 1.6140 92 0.8193 0.1930 0.8193 0.9051
No log 1.6491 94 0.9007 0.1605 0.9007 0.9491
No log 1.6842 96 0.7885 0.1515 0.7885 0.8880
No log 1.7193 98 0.7155 0.2222 0.7155 0.8459
No log 1.7544 100 0.6539 0.2749 0.6539 0.8087
No log 1.7895 102 0.6220 0.0850 0.6220 0.7887
No log 1.8246 104 0.6129 0.0 0.6129 0.7829
No log 1.8596 106 0.6836 0.2258 0.6836 0.8268
No log 1.8947 108 0.9555 0.1545 0.9555 0.9775
No log 1.9298 110 1.0474 0.1059 1.0474 1.0234
No log 1.9649 112 0.8933 0.2068 0.8933 0.9451
No log 2.0 114 0.6903 0.1667 0.6903 0.8308
No log 2.0351 116 0.6683 0.0734 0.6683 0.8175
No log 2.0702 118 0.6736 0.0409 0.6736 0.8207
No log 2.1053 120 0.6903 0.0968 0.6903 0.8308
No log 2.1404 122 0.6693 0.0805 0.6693 0.8181
No log 2.1754 124 0.6563 0.0180 0.6563 0.8101
No log 2.2105 126 0.6706 0.1910 0.6706 0.8189
No log 2.2456 128 0.6901 0.1746 0.6901 0.8307
No log 2.2807 130 0.6956 0.2161 0.6956 0.8340
No log 2.3158 132 0.7134 0.1759 0.7134 0.8446
No log 2.3509 134 0.7324 0.1845 0.7324 0.8558
No log 2.3860 136 0.7706 0.3004 0.7706 0.8779
No log 2.4211 138 0.9819 0.2258 0.9819 0.9909
No log 2.4561 140 1.0153 0.1746 1.0153 1.0076
No log 2.4912 142 0.7672 0.2489 0.7672 0.8759
No log 2.5263 144 0.6633 0.1163 0.6633 0.8145
No log 2.5614 146 0.6408 0.1605 0.6408 0.8005
No log 2.5965 148 0.6347 0.1304 0.6347 0.7967
No log 2.6316 150 0.6081 0.1282 0.6081 0.7798
No log 2.6667 152 0.5718 0.1484 0.5718 0.7562
No log 2.7018 154 0.5772 0.25 0.5772 0.7597
No log 2.7368 156 0.7086 0.28 0.7086 0.8418
No log 2.7719 158 0.7966 0.1366 0.7966 0.8925
No log 2.8070 160 0.6680 0.3575 0.6680 0.8173
No log 2.8421 162 0.8008 0.1931 0.8008 0.8949
No log 2.8772 164 1.1371 0.0747 1.1371 1.0663
No log 2.9123 166 1.0022 0.1148 1.0022 1.0011
No log 2.9474 168 0.7505 0.0769 0.7505 0.8663
No log 2.9825 170 0.7353 0.2809 0.7353 0.8575
No log 3.0175 172 0.7870 0.2077 0.7870 0.8871
No log 3.0526 174 0.7137 0.3253 0.7137 0.8448
No log 3.0877 176 0.7769 0.1759 0.7769 0.8814
No log 3.1228 178 0.8485 0.1776 0.8485 0.9211
No log 3.1579 180 0.8040 0.1469 0.8040 0.8967
No log 3.1930 182 1.0445 0.1942 1.0445 1.0220
No log 3.2281 184 1.4189 0.1605 1.4189 1.1912
No log 3.2632 186 1.3996 0.1605 1.3996 1.1830
No log 3.2982 188 0.9134 0.2066 0.9134 0.9557
No log 3.3333 190 0.6489 0.2174 0.6489 0.8056
No log 3.3684 192 0.9721 0.1292 0.9721 0.9860
No log 3.4035 194 1.0806 0.0853 1.0807 1.0395
No log 3.4386 196 0.9014 0.1807 0.9014 0.9494
No log 3.4737 198 0.5869 0.2771 0.5869 0.7661
No log 3.5088 200 0.7212 0.2607 0.7212 0.8492
No log 3.5439 202 0.9406 0.2275 0.9406 0.9698
No log 3.5789 204 0.8227 0.2217 0.8227 0.9070
No log 3.6140 206 0.6023 0.3898 0.6023 0.7761
No log 3.6491 208 0.7411 0.2079 0.7411 0.8609
No log 3.6842 210 0.8263 0.1786 0.8263 0.9090
No log 3.7193 212 0.7656 0.1683 0.7656 0.8750
No log 3.7544 214 0.6591 0.1698 0.6591 0.8118
No log 3.7895 216 0.7921 0.2308 0.7921 0.8900
No log 3.8246 218 0.9870 0.1938 0.9870 0.9935
No log 3.8596 220 0.9271 0.2381 0.9271 0.9629
No log 3.8947 222 0.7668 0.2000 0.7668 0.8756
No log 3.9298 224 0.6852 0.4023 0.6852 0.8278
No log 3.9649 226 0.9815 0.1635 0.9815 0.9907
No log 4.0 228 1.1789 0.1729 1.1789 1.0858
No log 4.0351 230 1.0412 0.2000 1.0412 1.0204
No log 4.0702 232 0.7669 0.0769 0.7669 0.8757
No log 4.1053 234 0.6400 0.3563 0.6400 0.8000
No log 4.1404 236 0.6660 0.3478 0.6660 0.8161
No log 4.1754 238 0.6536 0.2889 0.6536 0.8085
No log 4.2105 240 0.6639 0.3297 0.6639 0.8148
No log 4.2456 242 0.6912 0.3508 0.6912 0.8314
No log 4.2807 244 0.8310 0.2063 0.8310 0.9116
No log 4.3158 246 1.0321 0.1648 1.0321 1.0159
No log 4.3509 248 1.0690 0.1655 1.0690 1.0339
No log 4.3860 250 0.9637 0.2059 0.9637 0.9817
No log 4.4211 252 1.0263 0.1489 1.0263 1.0131
No log 4.4561 254 1.0912 0.1399 1.0912 1.0446
No log 4.4912 256 1.2871 0.1402 1.2871 1.1345
No log 4.5263 258 1.3444 0.0675 1.3444 1.1595
No log 4.5614 260 1.1904 0.1467 1.1904 1.0911
No log 4.5965 262 1.0543 0.2171 1.0543 1.0268
No log 4.6316 264 1.0192 0.2119 1.0192 1.0096
No log 4.6667 266 1.0168 0.1506 1.0168 1.0084
No log 4.7018 268 0.9800 0.1496 0.9800 0.9899
No log 4.7368 270 0.9337 0.1811 0.9337 0.9663
No log 4.7719 272 0.8881 0.1934 0.8881 0.9424
No log 4.8070 274 0.8315 0.1588 0.8315 0.9119
No log 4.8421 276 0.8225 0.2000 0.8225 0.9069
No log 4.8772 278 0.9605 0.1440 0.9605 0.9800
No log 4.9123 280 1.2064 -0.0309 1.2064 1.0983
No log 4.9474 282 1.1798 -0.0233 1.1798 1.0862
No log 4.9825 284 0.9745 0.1877 0.9745 0.9872
No log 5.0175 286 0.7099 0.2692 0.7099 0.8425
No log 5.0526 288 0.6072 0.3149 0.6072 0.7792
No log 5.0877 290 0.6264 0.3478 0.6264 0.7915
No log 5.1228 292 0.5992 0.3149 0.5992 0.7741
No log 5.1579 294 0.6040 0.2994 0.6040 0.7772
No log 5.1930 296 0.7310 0.3274 0.7310 0.8550
No log 5.2281 298 0.8399 0.2327 0.8399 0.9164
No log 5.2632 300 0.9749 0.1480 0.9749 0.9874
No log 5.2982 302 0.9131 0.2000 0.9131 0.9556
No log 5.3333 304 0.7950 0.3388 0.7950 0.8916
No log 5.3684 306 0.7155 0.3162 0.7155 0.8458
No log 5.4035 308 0.7499 0.3021 0.7499 0.8660
No log 5.4386 310 0.8472 0.2903 0.8472 0.9205
No log 5.4737 312 0.8676 0.2320 0.8676 0.9315
No log 5.5088 314 0.9798 0.2060 0.9798 0.9898
No log 5.5439 316 0.9052 0.2314 0.9052 0.9514
No log 5.5789 318 0.8559 0.2510 0.8559 0.9251
No log 5.6140 320 0.7731 0.2137 0.7731 0.8792
No log 5.6491 322 0.7611 0.3043 0.7611 0.8724
No log 5.6842 324 0.7856 0.3362 0.7856 0.8863
No log 5.7193 326 0.8895 0.2450 0.8895 0.9431
No log 5.7544 328 1.0239 0.2000 1.0239 1.0119
No log 5.7895 330 1.0898 0.1709 1.0898 1.0439
No log 5.8246 332 1.0985 0.1471 1.0985 1.0481
No log 5.8596 334 0.9666 0.1692 0.9666 0.9832
No log 5.8947 336 0.8378 0.1730 0.8378 0.9153
No log 5.9298 338 0.7411 0.2897 0.7411 0.8609
No log 5.9649 340 0.7228 0.2762 0.7228 0.8502
No log 6.0 342 0.7386 0.3303 0.7386 0.8594
No log 6.0351 344 0.9113 0.1235 0.9113 0.9546
No log 6.0702 346 1.2576 0.1738 1.2576 1.1214
No log 6.1053 348 1.4003 0.1546 1.4003 1.1834
No log 6.1404 350 1.2779 0.1742 1.2779 1.1304
No log 6.1754 352 0.9833 0.1882 0.9833 0.9916
No log 6.2105 354 0.7596 0.3214 0.7596 0.8715
No log 6.2456 356 0.7505 0.2536 0.7505 0.8663
No log 6.2807 358 0.7573 0.2536 0.7573 0.8702
No log 6.3158 360 0.7502 0.3548 0.7502 0.8661
No log 6.3509 362 0.9115 0.3114 0.9115 0.9547
No log 6.3860 364 1.1999 0.1672 1.1999 1.0954
No log 6.4211 366 1.3178 0.1475 1.3178 1.1480
No log 6.4561 368 1.2259 0.1475 1.2259 1.1072
No log 6.4912 370 0.9952 0.3043 0.9952 0.9976
No log 6.5263 372 0.7840 0.2960 0.7840 0.8855
No log 6.5614 374 0.7132 0.3722 0.7132 0.8445
No log 6.5965 376 0.7130 0.3091 0.7130 0.8444
No log 6.6316 378 0.7813 0.2713 0.7813 0.8839
No log 6.6667 380 0.8529 0.1938 0.8529 0.9235
No log 6.7018 382 0.9284 0.2061 0.9284 0.9635
No log 6.7368 384 0.9613 0.2061 0.9613 0.9805
No log 6.7719 386 0.9066 0.2061 0.9066 0.9522
No log 6.8070 388 0.7648 0.3559 0.7648 0.8745
No log 6.8421 390 0.7170 0.3537 0.7170 0.8468
No log 6.8772 392 0.7614 0.3247 0.7614 0.8726
No log 6.9123 394 0.8601 0.2960 0.8601 0.9274
No log 6.9474 396 0.9773 0.1765 0.9773 0.9886
No log 6.9825 398 1.0282 0.1769 1.0282 1.0140
No log 7.0175 400 1.1087 0.1220 1.1087 1.0529
No log 7.0526 402 1.1517 0.1220 1.1517 1.0732
No log 7.0877 404 1.1235 0.1233 1.1235 1.0600
No log 7.1228 406 1.0045 0.1642 1.0045 1.0022
No log 7.1579 408 0.8822 0.3282 0.8822 0.9393
No log 7.1930 410 0.8035 0.3433 0.8035 0.8964
No log 7.2281 412 0.7741 0.3466 0.7741 0.8798
No log 7.2632 414 0.7841 0.3798 0.7841 0.8855
No log 7.2982 416 0.8615 0.2741 0.8615 0.9282
No log 7.3333 418 0.9872 0.2061 0.9872 0.9936
No log 7.3684 420 1.1132 0.1233 1.1132 1.0551
No log 7.4035 422 1.1013 0.1233 1.1013 1.0494
No log 7.4386 424 0.9959 0.2061 0.9959 0.9979
No log 7.4737 426 0.9131 0.2698 0.9131 0.9556
No log 7.5088 428 0.8645 0.2698 0.8645 0.9298
No log 7.5439 430 0.8414 0.2941 0.8414 0.9173
No log 7.5789 432 0.8677 0.2941 0.8677 0.9315
No log 7.6140 434 0.8768 0.2604 0.8768 0.9364
No log 7.6491 436 0.9252 0.2366 0.9252 0.9619
No log 7.6842 438 0.9792 0.2121 0.9792 0.9895
No log 7.7193 440 1.0550 0.1541 1.0550 1.0271
No log 7.7544 442 1.1055 0.1280 1.1055 1.0514
No log 7.7895 444 1.0564 0.1268 1.0564 1.0278
No log 7.8246 446 0.9770 0.2060 0.9770 0.9885
No log 7.8596 448 0.9189 0.2374 0.9189 0.9586
No log 7.8947 450 0.8945 0.2615 0.8945 0.9458
No log 7.9298 452 0.9175 0.2374 0.9175 0.9578
No log 7.9649 454 0.9437 0.2374 0.9437 0.9714
No log 8.0 456 0.9605 0.2374 0.9605 0.9801
No log 8.0351 458 1.0080 0.1765 1.0080 1.0040
No log 8.0702 460 1.0189 0.1480 1.0189 1.0094
No log 8.1053 462 0.9898 0.2374 0.9898 0.9949
No log 8.1404 464 0.9193 0.2374 0.9193 0.9588
No log 8.1754 466 0.8224 0.25 0.8224 0.9069
No log 8.2105 468 0.7602 0.2542 0.7602 0.8719
No log 8.2456 470 0.7437 0.2554 0.7437 0.8624
No log 8.2807 472 0.7789 0.2846 0.7789 0.8825
No log 8.3158 474 0.8603 0.2615 0.8603 0.9275
No log 8.3509 476 0.9666 0.2366 0.9666 0.9832
No log 8.3860 478 1.0765 0.1828 1.0765 1.0375
No log 8.4211 480 1.1316 0.1280 1.1316 1.0637
No log 8.4561 482 1.1410 0.1280 1.1410 1.0682
No log 8.4912 484 1.1154 0.1280 1.1154 1.0561
No log 8.5263 486 1.1111 0.1549 1.1111 1.0541
No log 8.5614 488 1.0552 0.1769 1.0552 1.0272
No log 8.5965 490 0.9562 0.2374 0.9562 0.9779
No log 8.6316 492 0.8632 0.2548 0.8632 0.9291
No log 8.6667 494 0.8420 0.2248 0.8420 0.9176
No log 8.7018 496 0.8273 0.2569 0.8273 0.9095
No log 8.7368 498 0.8512 0.2374 0.8512 0.9226
0.5456 8.7719 500 0.8870 0.2374 0.8870 0.9418
0.5456 8.8070 502 0.9284 0.2374 0.9284 0.9636
0.5456 8.8421 504 0.9529 0.2374 0.9529 0.9762
0.5456 8.8772 506 0.9933 0.2124 0.9933 0.9966
0.5456 8.9123 508 1.0084 0.1818 1.0084 1.0042
0.5456 8.9474 510 0.9899 0.2061 0.9899 0.9949
0.5456 8.9825 512 0.9487 0.2374 0.9487 0.9740
0.5456 9.0175 514 0.9007 0.2374 0.9007 0.9491
0.5456 9.0526 516 0.8973 0.2374 0.8973 0.9473
0.5456 9.0877 518 0.9198 0.2374 0.9198 0.9591
0.5456 9.1228 520 0.9437 0.2374 0.9437 0.9715
0.5456 9.1579 522 0.9690 0.2061 0.9690 0.9844
0.5456 9.1930 524 1.0021 0.2124 1.0021 1.0011
0.5456 9.2281 526 1.0316 0.1533 1.0316 1.0157
0.5456 9.2632 528 1.0252 0.1822 1.0252 1.0125
0.5456 9.2982 530 0.9879 0.2061 0.9879 0.9939
0.5456 9.3333 532 0.9454 0.2374 0.9454 0.9723
0.5456 9.3684 534 0.9019 0.2374 0.9019 0.9497
0.5456 9.4035 536 0.8629 0.2481 0.8629 0.9289
0.5456 9.4386 538 0.8497 0.2797 0.8497 0.9218
0.5456 9.4737 540 0.8575 0.2481 0.8575 0.9260
0.5456 9.5088 542 0.8785 0.2243 0.8785 0.9373
0.5456 9.5439 544 0.8933 0.2243 0.8933 0.9452
0.5456 9.5789 546 0.9070 0.2243 0.9070 0.9524
0.5456 9.6140 548 0.9237 0.2243 0.9237 0.9611
0.5456 9.6491 550 0.9347 0.2374 0.9347 0.9668
0.5456 9.6842 552 0.9380 0.2374 0.9380 0.9685
0.5456 9.7193 554 0.9362 0.2374 0.9362 0.9676
0.5456 9.7544 556 0.9390 0.2374 0.9390 0.9690
0.5456 9.7895 558 0.9459 0.2061 0.9459 0.9726
0.5456 9.8246 560 0.9500 0.2061 0.9500 0.9747
0.5456 9.8596 562 0.9504 0.2061 0.9504 0.9749
0.5456 9.8947 564 0.9484 0.2061 0.9484 0.9738
0.5456 9.9298 566 0.9489 0.2061 0.9489 0.9741
0.5456 9.9649 568 0.9486 0.2061 0.9486 0.9740
0.5456 10.0 570 0.9488 0.2061 0.9488 0.9741

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/ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k12_task3_organization

Finetuned
(4040)
this model