ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k9_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: 1.0746
  • Qwk: 0.2785
  • Mse: 1.0746
  • Rmse: 1.0366

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 0.0476 2 4.1397 -0.0048 4.1397 2.0346
No log 0.0952 4 3.0019 0.0034 3.0019 1.7326
No log 0.1429 6 2.2808 0.0350 2.2808 1.5102
No log 0.1905 8 1.4780 0.1323 1.4780 1.2157
No log 0.2381 10 1.1588 0.0919 1.1588 1.0765
No log 0.2857 12 1.1023 0.2352 1.1023 1.0499
No log 0.3333 14 1.1859 0.1810 1.1859 1.0890
No log 0.3810 16 1.4192 0.0778 1.4192 1.1913
No log 0.4286 18 1.2727 0.125 1.2727 1.1282
No log 0.4762 20 1.0843 0.2367 1.0843 1.0413
No log 0.5238 22 1.0155 0.2120 1.0155 1.0077
No log 0.5714 24 1.0972 0.2777 1.0972 1.0475
No log 0.6190 26 1.4395 0.0724 1.4395 1.1998
No log 0.6667 28 1.4998 0.1160 1.4998 1.2247
No log 0.7143 30 1.2110 0.2977 1.2110 1.1004
No log 0.7619 32 1.0658 0.2282 1.0658 1.0324
No log 0.8095 34 1.0947 0.2247 1.0947 1.0463
No log 0.8571 36 1.1129 0.2640 1.1129 1.0549
No log 0.9048 38 1.2289 0.2984 1.2289 1.1085
No log 0.9524 40 1.1085 0.2534 1.1085 1.0529
No log 1.0 42 1.0395 0.2577 1.0395 1.0196
No log 1.0476 44 1.0112 0.2254 1.0112 1.0056
No log 1.0952 46 1.0799 0.3086 1.0799 1.0392
No log 1.1429 48 1.0988 0.2668 1.0988 1.0482
No log 1.1905 50 1.1178 0.3013 1.1178 1.0573
No log 1.2381 52 1.0896 0.2366 1.0896 1.0438
No log 1.2857 54 1.1140 0.2671 1.1140 1.0555
No log 1.3333 56 1.2750 0.2524 1.2750 1.1291
No log 1.3810 58 1.6632 0.2976 1.6632 1.2896
No log 1.4286 60 1.8228 0.2313 1.8228 1.3501
No log 1.4762 62 1.7574 0.2629 1.7574 1.3257
No log 1.5238 64 1.6890 0.2629 1.6890 1.2996
No log 1.5714 66 1.4892 0.2777 1.4892 1.2203
No log 1.6190 68 1.1313 0.2877 1.1313 1.0636
No log 1.6667 70 1.0791 0.3022 1.0791 1.0388
No log 1.7143 72 1.0442 0.2453 1.0442 1.0219
No log 1.7619 74 1.0410 0.2314 1.0410 1.0203
No log 1.8095 76 1.0651 0.2268 1.0651 1.0320
No log 1.8571 78 1.1423 0.2588 1.1423 1.0688
No log 1.9048 80 1.1343 0.1825 1.1343 1.0650
No log 1.9524 82 1.1994 0.0409 1.1994 1.0952
No log 2.0 84 1.2007 0.2117 1.2007 1.0958
No log 2.0476 86 1.1679 0.2789 1.1679 1.0807
No log 2.0952 88 1.1005 0.2892 1.1005 1.0491
No log 2.1429 90 1.1320 0.2379 1.1320 1.0640
No log 2.1905 92 1.1305 0.2016 1.1305 1.0633
No log 2.2381 94 1.0894 0.2716 1.0894 1.0438
No log 2.2857 96 1.2192 0.3622 1.2192 1.1042
No log 2.3333 98 1.1954 0.3509 1.1954 1.0933
No log 2.3810 100 1.1534 0.3659 1.1534 1.0740
No log 2.4286 102 1.1692 0.2739 1.1692 1.0813
No log 2.4762 104 1.1410 0.3643 1.1410 1.0682
No log 2.5238 106 1.0782 0.3158 1.0782 1.0384
No log 2.5714 108 1.2116 0.3643 1.2116 1.1007
No log 2.6190 110 1.2783 0.3720 1.2783 1.1306
No log 2.6667 112 1.0986 0.3701 1.0986 1.0482
No log 2.7143 114 1.0519 0.3447 1.0519 1.0256
No log 2.7619 116 1.0874 0.3437 1.0874 1.0428
No log 2.8095 118 1.0198 0.3147 1.0198 1.0099
No log 2.8571 120 1.0987 0.3634 1.0987 1.0482
No log 2.9048 122 1.0620 0.3764 1.0620 1.0305
No log 2.9524 124 1.0359 0.3536 1.0359 1.0178
No log 3.0 126 1.1712 0.2387 1.1712 1.0822
No log 3.0476 128 1.1261 0.2890 1.1261 1.0612
No log 3.0952 130 1.1129 0.3990 1.1129 1.0550
No log 3.1429 132 1.2271 0.3058 1.2271 1.1078
No log 3.1905 134 1.1780 0.3953 1.1780 1.0854
No log 3.2381 136 1.2225 0.3225 1.2225 1.1057
No log 3.2857 138 1.3148 0.1785 1.3148 1.1467
No log 3.3333 140 1.2191 0.2657 1.2191 1.1042
No log 3.3810 142 1.1572 0.3286 1.1572 1.0757
No log 3.4286 144 1.2470 0.2528 1.2470 1.1167
No log 3.4762 146 1.1594 0.3697 1.1594 1.0767
No log 3.5238 148 1.0620 0.2716 1.0620 1.0306
No log 3.5714 150 1.0408 0.2850 1.0408 1.0202
No log 3.6190 152 1.0433 0.3230 1.0433 1.0214
No log 3.6667 154 1.1284 0.2482 1.1284 1.0623
No log 3.7143 156 1.0627 0.3988 1.0627 1.0309
No log 3.7619 158 1.0461 0.4313 1.0461 1.0228
No log 3.8095 160 1.1326 0.3083 1.1326 1.0642
No log 3.8571 162 1.0918 0.3437 1.0918 1.0449
No log 3.9048 164 1.0966 0.2761 1.0966 1.0472
No log 3.9524 166 1.2972 0.3233 1.2972 1.1389
No log 4.0 168 1.4782 0.2240 1.4782 1.2158
No log 4.0476 170 1.3680 0.2229 1.3680 1.1696
No log 4.0952 172 1.1099 0.3499 1.1099 1.0535
No log 4.1429 174 1.1802 0.3222 1.1802 1.0864
No log 4.1905 176 1.2399 0.2587 1.2399 1.1135
No log 4.2381 178 1.1126 0.3648 1.1126 1.0548
No log 4.2857 180 0.9513 0.2812 0.9513 0.9753
No log 4.3333 182 1.0322 0.4140 1.0322 1.0160
No log 4.3810 184 1.0736 0.3995 1.0736 1.0362
No log 4.4286 186 0.9395 0.2944 0.9395 0.9693
No log 4.4762 188 0.9332 0.3706 0.9332 0.9660
No log 4.5238 190 1.0307 0.3414 1.0307 1.0152
No log 4.5714 192 1.0155 0.4008 1.0155 1.0077
No log 4.6190 194 0.9845 0.3857 0.9845 0.9922
No log 4.6667 196 1.0136 0.4002 1.0136 1.0068
No log 4.7143 198 0.9863 0.3856 0.9863 0.9931
No log 4.7619 200 0.9719 0.3076 0.9719 0.9858
No log 4.8095 202 0.9521 0.3017 0.9521 0.9757
No log 4.8571 204 0.9493 0.3408 0.9493 0.9743
No log 4.9048 206 1.0118 0.3137 1.0118 1.0059
No log 4.9524 208 1.1041 0.3500 1.1041 1.0508
No log 5.0 210 1.0251 0.3709 1.0251 1.0125
No log 5.0476 212 0.9723 0.3571 0.9723 0.9860
No log 5.0952 214 0.9918 0.4601 0.9918 0.9959
No log 5.1429 216 1.0238 0.4730 1.0238 1.0118
No log 5.1905 218 1.0123 0.4933 1.0123 1.0061
No log 5.2381 220 0.9824 0.4587 0.9824 0.9912
No log 5.2857 222 0.9720 0.4 0.9720 0.9859
No log 5.3333 224 0.9656 0.3800 0.9656 0.9826
No log 5.3810 226 0.9611 0.3377 0.9611 0.9804
No log 5.4286 228 0.9449 0.3156 0.9449 0.9720
No log 5.4762 230 0.9425 0.3760 0.9425 0.9708
No log 5.5238 232 0.9423 0.4030 0.9423 0.9707
No log 5.5714 234 0.9482 0.4647 0.9482 0.9738
No log 5.6190 236 0.9738 0.3684 0.9738 0.9868
No log 5.6667 238 0.9521 0.3931 0.9521 0.9757
No log 5.7143 240 0.9470 0.2922 0.9470 0.9731
No log 5.7619 242 0.9526 0.2922 0.9526 0.9760
No log 5.8095 244 0.9563 0.2922 0.9563 0.9779
No log 5.8571 246 0.9799 0.3719 0.9799 0.9899
No log 5.9048 248 1.0777 0.4066 1.0777 1.0381
No log 5.9524 250 1.0273 0.3687 1.0273 1.0136
No log 6.0 252 0.9957 0.3559 0.9957 0.9979
No log 6.0476 254 0.9552 0.3891 0.9552 0.9773
No log 6.0952 256 0.9676 0.4410 0.9676 0.9836
No log 6.1429 258 1.0181 0.3862 1.0181 1.0090
No log 6.1905 260 0.9744 0.4115 0.9744 0.9871
No log 6.2381 262 0.9389 0.3038 0.9389 0.9690
No log 6.2857 264 1.0510 0.3727 1.0510 1.0252
No log 6.3333 266 1.0713 0.3619 1.0713 1.0350
No log 6.3810 268 1.0444 0.3402 1.0444 1.0220
No log 6.4286 270 0.9636 0.2716 0.9636 0.9816
No log 6.4762 272 0.9542 0.2692 0.9542 0.9768
No log 6.5238 274 0.9477 0.3293 0.9477 0.9735
No log 6.5714 276 0.9389 0.3544 0.9389 0.9690
No log 6.6190 278 1.0280 0.3494 1.0280 1.0139
No log 6.6667 280 1.0323 0.2754 1.0323 1.0160
No log 6.7143 282 0.9310 0.4361 0.9310 0.9649
No log 6.7619 284 0.9494 0.3842 0.9494 0.9743
No log 6.8095 286 0.9656 0.3027 0.9656 0.9827
No log 6.8571 288 0.9473 0.3335 0.9473 0.9733
No log 6.9048 290 1.0467 0.3646 1.0467 1.0231
No log 6.9524 292 1.1961 0.2949 1.1961 1.0937
No log 7.0 294 1.1166 0.2270 1.1166 1.0567
No log 7.0476 296 0.9899 0.3614 0.9899 0.9949
No log 7.0952 298 1.0133 0.375 1.0133 1.0066
No log 7.1429 300 1.1398 0.3257 1.1398 1.0676
No log 7.1905 302 1.0988 0.3668 1.0988 1.0482
No log 7.2381 304 0.9887 0.4207 0.9887 0.9943
No log 7.2857 306 0.9947 0.4 0.9947 0.9973
No log 7.3333 308 1.0214 0.4019 1.0214 1.0106
No log 7.3810 310 0.9812 0.2963 0.9812 0.9906
No log 7.4286 312 0.9644 0.2829 0.9644 0.9820
No log 7.4762 314 0.9599 0.2291 0.9599 0.9797
No log 7.5238 316 0.9647 0.2466 0.9647 0.9822
No log 7.5714 318 0.9749 0.3216 0.9749 0.9874
No log 7.6190 320 1.0062 0.3352 1.0062 1.0031
No log 7.6667 322 1.0113 0.3467 1.0113 1.0056
No log 7.7143 324 1.0012 0.3332 1.0012 1.0006
No log 7.7619 326 0.9812 0.3323 0.9812 0.9906
No log 7.8095 328 0.9724 0.3950 0.9724 0.9861
No log 7.8571 330 0.9811 0.3950 0.9811 0.9905
No log 7.9048 332 0.9523 0.3740 0.9523 0.9759
No log 7.9524 334 0.9344 0.3583 0.9344 0.9666
No log 8.0 336 0.9343 0.3697 0.9343 0.9666
No log 8.0476 338 0.9407 0.3642 0.9407 0.9699
No log 8.0952 340 0.9304 0.3697 0.9304 0.9646
No log 8.1429 342 0.9328 0.4014 0.9328 0.9658
No log 8.1905 344 0.9437 0.2620 0.9437 0.9714
No log 8.2381 346 0.9459 0.2984 0.9459 0.9726
No log 8.2857 348 0.9634 0.3042 0.9634 0.9815
No log 8.3333 350 0.9429 0.4 0.9429 0.9710
No log 8.3810 352 0.9344 0.4526 0.9344 0.9666
No log 8.4286 354 1.0077 0.4208 1.0077 1.0038
No log 8.4762 356 0.9808 0.4098 0.9808 0.9903
No log 8.5238 358 0.9240 0.3878 0.9240 0.9613
No log 8.5714 360 0.9439 0.3428 0.9439 0.9715
No log 8.6190 362 1.0096 0.3415 1.0096 1.0048
No log 8.6667 364 1.0961 0.3220 1.0961 1.0469
No log 8.7143 366 1.0942 0.3691 1.0942 1.0460
No log 8.7619 368 0.9704 0.4374 0.9704 0.9851
No log 8.8095 370 0.9800 0.4546 0.9800 0.9899
No log 8.8571 372 1.0516 0.4573 1.0516 1.0255
No log 8.9048 374 1.0149 0.4696 1.0149 1.0074
No log 8.9524 376 0.9322 0.4423 0.9322 0.9655
No log 9.0 378 1.0045 0.3192 1.0045 1.0023
No log 9.0476 380 1.0950 0.2225 1.0950 1.0464
No log 9.0952 382 1.0418 0.2496 1.0418 1.0207
No log 9.1429 384 0.9573 0.3076 0.9573 0.9784
No log 9.1905 386 0.9710 0.2695 0.9710 0.9854
No log 9.2381 388 1.0183 0.2375 1.0183 1.0091
No log 9.2857 390 1.0422 0.2748 1.0422 1.0209
No log 9.3333 392 1.0128 0.3250 1.0128 1.0064
No log 9.3810 394 1.0020 0.3304 1.0020 1.0010
No log 9.4286 396 1.0407 0.3230 1.0407 1.0202
No log 9.4762 398 1.0613 0.2203 1.0613 1.0302
No log 9.5238 400 1.0556 0.2371 1.0556 1.0274
No log 9.5714 402 1.0393 0.2669 1.0393 1.0195
No log 9.6190 404 1.0015 0.3818 1.0015 1.0008
No log 9.6667 406 1.0158 0.4264 1.0158 1.0078
No log 9.7143 408 1.0260 0.3897 1.0260 1.0129
No log 9.7619 410 1.0094 0.3435 1.0094 1.0047
No log 9.8095 412 1.0041 0.2887 1.0041 1.0021
No log 9.8571 414 0.9840 0.3134 0.9840 0.9920
No log 9.9048 416 0.9970 0.2479 0.9970 0.9985
No log 9.9524 418 1.0028 0.2620 1.0028 1.0014
No log 10.0 420 0.9725 0.3388 0.9725 0.9862
No log 10.0476 422 0.9673 0.2813 0.9673 0.9835
No log 10.0952 424 0.9754 0.2951 0.9754 0.9876
No log 10.1429 426 0.9573 0.2424 0.9573 0.9784
No log 10.1905 428 0.9450 0.3280 0.9450 0.9721
No log 10.2381 430 0.9384 0.3280 0.9384 0.9687
No log 10.2857 432 0.9392 0.2424 0.9392 0.9691
No log 10.3333 434 0.9267 0.3194 0.9267 0.9627
No log 10.3810 436 0.9434 0.3291 0.9434 0.9713
No log 10.4286 438 0.9490 0.3797 0.9490 0.9742
No log 10.4762 440 0.9396 0.3965 0.9396 0.9693
No log 10.5238 442 0.9782 0.3897 0.9782 0.9890
No log 10.5714 444 0.9614 0.3108 0.9614 0.9805
No log 10.6190 446 0.9342 0.3335 0.9342 0.9665
No log 10.6667 448 0.9444 0.3776 0.9444 0.9718
No log 10.7143 450 0.9535 0.3100 0.9535 0.9765
No log 10.7619 452 0.9304 0.3280 0.9304 0.9646
No log 10.8095 454 0.9436 0.3765 0.9436 0.9714
No log 10.8571 456 0.9475 0.4507 0.9475 0.9734
No log 10.9048 458 0.9400 0.4344 0.9400 0.9695
No log 10.9524 460 0.9430 0.3722 0.9430 0.9711
No log 11.0 462 0.9273 0.3838 0.9273 0.9630
No log 11.0476 464 0.9222 0.3800 0.9222 0.9603
No log 11.0952 466 0.9277 0.3915 0.9277 0.9632
No log 11.1429 468 0.9531 0.3816 0.9531 0.9763
No log 11.1905 470 0.9460 0.3636 0.9460 0.9726
No log 11.2381 472 0.9326 0.3693 0.9326 0.9657
No log 11.2857 474 1.0040 0.3483 1.0040 1.0020
No log 11.3333 476 1.0961 0.3480 1.0961 1.0470
No log 11.3810 478 1.0793 0.3989 1.0793 1.0389
No log 11.4286 480 1.0241 0.3841 1.0241 1.0120
No log 11.4762 482 1.0196 0.4105 1.0196 1.0098
No log 11.5238 484 1.0749 0.2864 1.0749 1.0368
No log 11.5714 486 1.0857 0.2864 1.0857 1.0420
No log 11.6190 488 1.0228 0.4105 1.0228 1.0113
No log 11.6667 490 1.0172 0.3218 1.0172 1.0086
No log 11.7143 492 1.0191 0.2674 1.0191 1.0095
No log 11.7619 494 1.0087 0.2767 1.0087 1.0043
No log 11.8095 496 1.0018 0.3779 1.0018 1.0009
No log 11.8571 498 1.0380 0.2944 1.0380 1.0188
0.3052 11.9048 500 1.0468 0.3097 1.0468 1.0231
0.3052 11.9524 502 1.0135 0.4105 1.0135 1.0067
0.3052 12.0 504 1.0498 0.4082 1.0498 1.0246
0.3052 12.0476 506 1.1349 0.4429 1.1349 1.0653
0.3052 12.0952 508 1.1583 0.3571 1.1583 1.0762
0.3052 12.1429 510 1.0873 0.3714 1.0873 1.0427
0.3052 12.1905 512 1.0013 0.2813 1.0013 1.0006
0.3052 12.2381 514 0.9660 0.2786 0.9660 0.9828
0.3052 12.2857 516 0.9682 0.3408 0.9682 0.9840
0.3052 12.3333 518 0.9596 0.3685 0.9596 0.9796
0.3052 12.3810 520 0.9566 0.3134 0.9566 0.9781
0.3052 12.4286 522 0.9683 0.2624 0.9683 0.9840
0.3052 12.4762 524 0.9894 0.2674 0.9894 0.9947
0.3052 12.5238 526 1.0212 0.4023 1.0212 1.0106
0.3052 12.5714 528 1.0227 0.4053 1.0227 1.0113
0.3052 12.6190 530 1.0102 0.3932 1.0102 1.0051
0.3052 12.6667 532 1.0396 0.3186 1.0396 1.0196
0.3052 12.7143 534 1.1132 0.2225 1.1132 1.0551
0.3052 12.7619 536 1.0914 0.2225 1.0914 1.0447
0.3052 12.8095 538 1.0061 0.3095 1.0061 1.0030
0.3052 12.8571 540 1.0298 0.3474 1.0298 1.0148
0.3052 12.9048 542 1.1403 0.3278 1.1403 1.0678
0.3052 12.9524 544 1.2023 0.2658 1.2023 1.0965
0.3052 13.0 546 1.1581 0.3444 1.1581 1.0762
0.3052 13.0476 548 1.0938 0.3823 1.0938 1.0458
0.3052 13.0952 550 1.1016 0.3133 1.1016 1.0496
0.3052 13.1429 552 1.1290 0.2046 1.1290 1.0625
0.3052 13.1905 554 1.1123 0.2180 1.1123 1.0547
0.3052 13.2381 556 1.0448 0.3408 1.0448 1.0222
0.3052 13.2857 558 1.0166 0.2647 1.0166 1.0083
0.3052 13.3333 560 1.0737 0.2117 1.0737 1.0362
0.3052 13.3810 562 1.1054 0.2298 1.1054 1.0514
0.3052 13.4286 564 1.0429 0.3298 1.0429 1.0212
0.3052 13.4762 566 0.9745 0.3134 0.9745 0.9872
0.3052 13.5238 568 0.9665 0.3437 0.9665 0.9831
0.3052 13.5714 570 1.0014 0.3382 1.0014 1.0007
0.3052 13.6190 572 0.9801 0.3854 0.9801 0.9900
0.3052 13.6667 574 0.9594 0.3571 0.9594 0.9795
0.3052 13.7143 576 0.9580 0.3949 0.9580 0.9788
0.3052 13.7619 578 0.9774 0.4454 0.9774 0.9886
0.3052 13.8095 580 0.9800 0.3729 0.9800 0.9900
0.3052 13.8571 582 0.9900 0.3466 0.9900 0.9950
0.3052 13.9048 584 1.0321 0.2802 1.0321 1.0159
0.3052 13.9524 586 1.0203 0.3152 1.0203 1.0101
0.3052 14.0 588 1.0005 0.3437 1.0005 1.0002
0.3052 14.0476 590 1.0008 0.3466 1.0008 1.0004
0.3052 14.0952 592 0.9993 0.3418 0.9993 0.9996
0.3052 14.1429 594 1.0142 0.2480 1.0142 1.0071
0.3052 14.1905 596 1.0301 0.2791 1.0301 1.0149
0.3052 14.2381 598 1.0369 0.2480 1.0369 1.0183
0.3052 14.2857 600 1.0439 0.2974 1.0439 1.0217
0.3052 14.3333 602 1.0746 0.2785 1.0746 1.0366

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/ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k9_task5_organization

Finetuned
(4033)
this model