ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run1_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: 0.8187
  • Qwk: 0.3697
  • Mse: 0.8187
  • Rmse: 0.9048

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 0.0351 2 4.2185 0.0086 4.2185 2.0539
No log 0.0702 4 2.3141 -0.0687 2.3141 1.5212
No log 0.1053 6 1.6291 0.0839 1.6291 1.2764
No log 0.1404 8 1.1627 0.2068 1.1627 1.0783
No log 0.1754 10 1.0621 0.1601 1.0621 1.0306
No log 0.2105 12 1.0572 0.0886 1.0572 1.0282
No log 0.2456 14 1.0396 0.1379 1.0396 1.0196
No log 0.2807 16 1.0379 0.1255 1.0379 1.0188
No log 0.3158 18 1.0151 0.1629 1.0151 1.0075
No log 0.3509 20 1.0818 0.1418 1.0818 1.0401
No log 0.3860 22 1.0591 0.1927 1.0591 1.0291
No log 0.4211 24 1.0837 0.1276 1.0837 1.0410
No log 0.4561 26 1.1559 0.1296 1.1559 1.0751
No log 0.4912 28 1.1140 0.1389 1.1140 1.0555
No log 0.5263 30 1.0243 0.1713 1.0243 1.0121
No log 0.5614 32 1.0512 0.1321 1.0512 1.0253
No log 0.5965 34 1.1148 0.1996 1.1148 1.0558
No log 0.6316 36 1.0397 0.1436 1.0397 1.0197
No log 0.6667 38 1.1115 0.1779 1.1115 1.0543
No log 0.7018 40 1.4029 0.0613 1.4029 1.1844
No log 0.7368 42 1.3882 0.0760 1.3882 1.1782
No log 0.7719 44 1.0888 0.2004 1.0888 1.0435
No log 0.8070 46 0.9621 0.3236 0.9621 0.9809
No log 0.8421 48 0.9698 0.2671 0.9698 0.9848
No log 0.8772 50 0.9560 0.3961 0.9560 0.9777
No log 0.9123 52 1.0639 0.1979 1.0639 1.0314
No log 0.9474 54 1.0452 0.2782 1.0452 1.0223
No log 0.9825 56 0.9744 0.3100 0.9744 0.9871
No log 1.0175 58 1.0377 0.2639 1.0377 1.0187
No log 1.0526 60 1.0334 0.3100 1.0334 1.0166
No log 1.0877 62 1.0848 0.3365 1.0848 1.0415
No log 1.1228 64 1.0760 0.1961 1.0760 1.0373
No log 1.1579 66 1.1576 0.1799 1.1576 1.0759
No log 1.1930 68 1.1822 0.1869 1.1822 1.0873
No log 1.2281 70 1.1228 0.1785 1.1228 1.0596
No log 1.2632 72 1.3383 0.2252 1.3383 1.1568
No log 1.2982 74 1.2819 0.2431 1.2819 1.1322
No log 1.3333 76 1.0126 0.2700 1.0126 1.0063
No log 1.3684 78 1.1871 0.2906 1.1871 1.0895
No log 1.4035 80 1.4352 0.3010 1.4352 1.1980
No log 1.4386 82 1.2480 0.3292 1.2480 1.1171
No log 1.4737 84 0.8753 0.5063 0.8753 0.9356
No log 1.5088 86 0.8233 0.4494 0.8233 0.9073
No log 1.5439 88 0.8331 0.3725 0.8331 0.9127
No log 1.5789 90 0.7817 0.5274 0.7817 0.8842
No log 1.6140 92 0.8342 0.5313 0.8342 0.9133
No log 1.6491 94 0.9033 0.4087 0.9033 0.9504
No log 1.6842 96 0.7880 0.5856 0.7880 0.8877
No log 1.7193 98 0.8999 0.3517 0.8999 0.9486
No log 1.7544 100 0.9925 0.2991 0.9925 0.9962
No log 1.7895 102 0.8721 0.3662 0.8721 0.9339
No log 1.8246 104 0.8428 0.4136 0.8428 0.9180
No log 1.8596 106 0.8722 0.3615 0.8722 0.9339
No log 1.8947 108 0.8984 0.3602 0.8984 0.9478
No log 1.9298 110 0.8259 0.4914 0.8259 0.9088
No log 1.9649 112 0.8304 0.4524 0.8304 0.9113
No log 2.0 114 0.8742 0.2857 0.8742 0.9350
No log 2.0351 116 0.9197 0.3390 0.9197 0.9590
No log 2.0702 118 0.8558 0.3840 0.8558 0.9251
No log 2.1053 120 0.9007 0.5424 0.9007 0.9491
No log 2.1404 122 1.0122 0.4565 1.0122 1.0061
No log 2.1754 124 0.9199 0.5222 0.9199 0.9591
No log 2.2105 126 0.8700 0.4449 0.8700 0.9327
No log 2.2456 128 0.8720 0.4444 0.8720 0.9338
No log 2.2807 130 0.8778 0.5224 0.8778 0.9369
No log 2.3158 132 0.9108 0.4703 0.9108 0.9544
No log 2.3509 134 0.9496 0.4803 0.9496 0.9745
No log 2.3860 136 0.9672 0.4558 0.9672 0.9834
No log 2.4211 138 0.9728 0.4404 0.9728 0.9863
No log 2.4561 140 0.9820 0.4010 0.9820 0.9910
No log 2.4912 142 0.9717 0.3609 0.9717 0.9857
No log 2.5263 144 0.9696 0.4439 0.9696 0.9847
No log 2.5614 146 0.9909 0.4719 0.9909 0.9954
No log 2.5965 148 0.9873 0.4938 0.9873 0.9936
No log 2.6316 150 0.9704 0.4145 0.9704 0.9851
No log 2.6667 152 0.9892 0.3182 0.9892 0.9946
No log 2.7018 154 0.9307 0.3563 0.9307 0.9647
No log 2.7368 156 0.9310 0.5093 0.9310 0.9649
No log 2.7719 158 0.9910 0.4208 0.9910 0.9955
No log 2.8070 160 0.9986 0.3308 0.9986 0.9993
No log 2.8421 162 0.9309 0.5339 0.9309 0.9648
No log 2.8772 164 0.8572 0.3996 0.8572 0.9259
No log 2.9123 166 0.9441 0.3333 0.9441 0.9716
No log 2.9474 168 0.9352 0.3601 0.9352 0.9670
No log 2.9825 170 0.8228 0.4449 0.8228 0.9071
No log 3.0175 172 1.0249 0.3683 1.0249 1.0124
No log 3.0526 174 1.0919 0.3413 1.0919 1.0449
No log 3.0877 176 0.8622 0.5815 0.8622 0.9286
No log 3.1228 178 0.8012 0.5042 0.8012 0.8951
No log 3.1579 180 0.8096 0.4752 0.8096 0.8998
No log 3.1930 182 0.8333 0.4647 0.8333 0.9128
No log 3.2281 184 0.8314 0.4879 0.8314 0.9118
No log 3.2632 186 0.7951 0.5388 0.7951 0.8917
No log 3.2982 188 0.7763 0.4936 0.7763 0.8811
No log 3.3333 190 0.7945 0.4836 0.7945 0.8914
No log 3.3684 192 0.9521 0.4115 0.9521 0.9758
No log 3.4035 194 0.9413 0.4091 0.9413 0.9702
No log 3.4386 196 0.8206 0.4487 0.8206 0.9058
No log 3.4737 198 0.8537 0.4221 0.8537 0.9240
No log 3.5088 200 0.8768 0.4763 0.8768 0.9364
No log 3.5439 202 0.8434 0.5366 0.8434 0.9184
No log 3.5789 204 0.8876 0.3584 0.8876 0.9421
No log 3.6140 206 0.8787 0.4066 0.8787 0.9374
No log 3.6491 208 0.8368 0.5406 0.8368 0.9147
No log 3.6842 210 0.9545 0.4835 0.9545 0.9770
No log 3.7193 212 0.9975 0.4220 0.9975 0.9987
No log 3.7544 214 0.8670 0.5435 0.8670 0.9311
No log 3.7895 216 0.8390 0.4148 0.8390 0.9160
No log 3.8246 218 0.9317 0.4238 0.9317 0.9652
No log 3.8596 220 0.9274 0.4356 0.9274 0.9630
No log 3.8947 222 0.8633 0.4647 0.8633 0.9291
No log 3.9298 224 0.9464 0.5017 0.9464 0.9728
No log 3.9649 226 1.0695 0.3590 1.0695 1.0342
No log 4.0 228 1.0304 0.4260 1.0304 1.0151
No log 4.0351 230 0.8870 0.4977 0.8870 0.9418
No log 4.0702 232 0.8469 0.4321 0.8469 0.9203
No log 4.1053 234 0.9800 0.3913 0.9800 0.9900
No log 4.1404 236 1.0546 0.3699 1.0546 1.0270
No log 4.1754 238 0.9830 0.4135 0.9830 0.9914
No log 4.2105 240 0.8894 0.4663 0.8894 0.9431
No log 4.2456 242 0.8818 0.5773 0.8818 0.9390
No log 4.2807 244 0.9266 0.4763 0.9266 0.9626
No log 4.3158 246 0.9243 0.4763 0.9243 0.9614
No log 4.3509 248 0.8772 0.4721 0.8772 0.9366
No log 4.3860 250 0.8668 0.4280 0.8668 0.9310
No log 4.4211 252 0.9483 0.3862 0.9483 0.9738
No log 4.4561 254 1.1237 0.3953 1.1237 1.0600
No log 4.4912 256 1.2262 0.3864 1.2262 1.1073
No log 4.5263 258 1.1343 0.4207 1.1343 1.0651
No log 4.5614 260 0.9708 0.4186 0.9708 0.9853
No log 4.5965 262 0.9084 0.4636 0.9084 0.9531
No log 4.6316 264 0.8922 0.4532 0.8922 0.9446
No log 4.6667 266 0.9042 0.4123 0.9042 0.9509
No log 4.7018 268 0.9192 0.3863 0.9192 0.9588
No log 4.7368 270 0.8497 0.4455 0.8497 0.9218
No log 4.7719 272 0.8043 0.4494 0.8043 0.8968
No log 4.8070 274 0.8115 0.4873 0.8115 0.9008
No log 4.8421 276 0.8050 0.4869 0.8050 0.8972
No log 4.8772 278 0.8552 0.4159 0.8552 0.9248
No log 4.9123 280 0.8687 0.4170 0.8687 0.9321
No log 4.9474 282 0.8714 0.4708 0.8714 0.9335
No log 4.9825 284 0.8720 0.4935 0.8720 0.9338
No log 5.0175 286 0.9046 0.4119 0.9046 0.9511
No log 5.0526 288 0.8992 0.4002 0.8992 0.9482
No log 5.0877 290 0.8388 0.4723 0.8388 0.9158
No log 5.1228 292 0.8217 0.3842 0.8217 0.9065
No log 5.1579 294 0.7832 0.4869 0.7832 0.8850
No log 5.1930 296 0.7519 0.5135 0.7519 0.8671
No log 5.2281 298 0.7459 0.5542 0.7459 0.8637
No log 5.2632 300 0.7756 0.4588 0.7756 0.8807
No log 5.2982 302 0.7960 0.4725 0.7960 0.8922
No log 5.3333 304 0.7479 0.5542 0.7479 0.8648
No log 5.3684 306 0.7452 0.5523 0.7452 0.8633
No log 5.4035 308 0.7723 0.5594 0.7723 0.8788
No log 5.4386 310 0.8009 0.5626 0.8009 0.8950
No log 5.4737 312 0.8153 0.4273 0.8153 0.9029
No log 5.5088 314 0.8487 0.4143 0.8487 0.9213
No log 5.5439 316 0.8146 0.4368 0.8146 0.9025
No log 5.5789 318 0.8195 0.4853 0.8195 0.9053
No log 5.6140 320 0.8411 0.4879 0.8411 0.9171
No log 5.6491 322 0.8090 0.4444 0.8090 0.8995
No log 5.6842 324 0.8887 0.4166 0.8887 0.9427
No log 5.7193 326 1.0493 0.4373 1.0493 1.0243
No log 5.7544 328 1.1310 0.4365 1.1310 1.0635
No log 5.7895 330 1.0108 0.4241 1.0108 1.0054
No log 5.8246 332 0.8309 0.3536 0.8309 0.9116
No log 5.8596 334 0.7907 0.3636 0.7907 0.8892
No log 5.8947 336 0.7950 0.4338 0.7950 0.8916
No log 5.9298 338 0.7642 0.4417 0.7642 0.8742
No log 5.9649 340 0.7581 0.5121 0.7581 0.8707
No log 6.0 342 0.7596 0.4742 0.7596 0.8716
No log 6.0351 344 0.8059 0.4476 0.8059 0.8977
No log 6.0702 346 0.8301 0.4139 0.8301 0.9111
No log 6.1053 348 0.7797 0.4630 0.7797 0.8830
No log 6.1404 350 0.7762 0.4630 0.7762 0.8810
No log 6.1754 352 0.8109 0.4143 0.8109 0.9005
No log 6.2105 354 0.8538 0.4916 0.8538 0.9240
No log 6.2456 356 0.8146 0.4444 0.8146 0.9025
No log 6.2807 358 0.7452 0.3556 0.7452 0.8632
No log 6.3158 360 0.7479 0.5214 0.7479 0.8648
No log 6.3509 362 0.7740 0.5342 0.7740 0.8798
No log 6.3860 364 0.7560 0.5770 0.7560 0.8695
No log 6.4211 366 0.7128 0.5759 0.7128 0.8443
No log 6.4561 368 0.7096 0.5274 0.7096 0.8424
No log 6.4912 370 0.7527 0.4127 0.7527 0.8676
No log 6.5263 372 0.7718 0.4102 0.7718 0.8785
No log 6.5614 374 0.7477 0.5113 0.7477 0.8647
No log 6.5965 376 0.7459 0.4411 0.7459 0.8637
No log 6.6316 378 0.7568 0.5428 0.7568 0.8700
No log 6.6667 380 0.7536 0.5635 0.7536 0.8681
No log 6.7018 382 0.7517 0.5597 0.7517 0.8670
No log 6.7368 384 0.7627 0.4632 0.7627 0.8733
No log 6.7719 386 0.7783 0.4275 0.7783 0.8822
No log 6.8070 388 0.8321 0.3862 0.8321 0.9122
No log 6.8421 390 0.8429 0.3735 0.8429 0.9181
No log 6.8772 392 0.7999 0.4335 0.7999 0.8943
No log 6.9123 394 0.7765 0.5107 0.7765 0.8812
No log 6.9474 396 0.7745 0.5098 0.7745 0.8800
No log 6.9825 398 0.7715 0.5098 0.7715 0.8784
No log 7.0175 400 0.7550 0.5597 0.7550 0.8689
No log 7.0526 402 0.7611 0.5210 0.7611 0.8724
No log 7.0877 404 0.8364 0.4606 0.8364 0.9145
No log 7.1228 406 0.9375 0.3830 0.9375 0.9682
No log 7.1579 408 0.9632 0.4247 0.9632 0.9814
No log 7.1930 410 0.8654 0.3735 0.8654 0.9303
No log 7.2281 412 0.7889 0.4865 0.7889 0.8882
No log 7.2632 414 0.7789 0.5399 0.7789 0.8826
No log 7.2982 416 0.8055 0.5841 0.8055 0.8975
No log 7.3333 418 0.8124 0.6022 0.8124 0.9013
No log 7.3684 420 0.8050 0.5682 0.8050 0.8972
No log 7.4035 422 0.7923 0.5575 0.7923 0.8901
No log 7.4386 424 0.7791 0.5575 0.7791 0.8827
No log 7.4737 426 0.7774 0.4988 0.7774 0.8817
No log 7.5088 428 0.8211 0.4020 0.8211 0.9062
No log 7.5439 430 0.8286 0.3989 0.8286 0.9103
No log 7.5789 432 0.7795 0.4973 0.7795 0.8829
No log 7.6140 434 0.7591 0.4973 0.7591 0.8712
No log 7.6491 436 0.7417 0.5002 0.7417 0.8612
No log 7.6842 438 0.7348 0.5498 0.7348 0.8572
No log 7.7193 440 0.7624 0.5107 0.7624 0.8731
No log 7.7544 442 0.8002 0.4633 0.8002 0.8946
No log 7.7895 444 0.7825 0.5237 0.7825 0.8846
No log 7.8246 446 0.7736 0.5142 0.7736 0.8795
No log 7.8596 448 0.7591 0.4676 0.7591 0.8712
No log 7.8947 450 0.7699 0.4520 0.7699 0.8775
No log 7.9298 452 0.7815 0.4520 0.7815 0.8840
No log 7.9649 454 0.7667 0.4520 0.7667 0.8756
No log 8.0 456 0.7477 0.4810 0.7477 0.8647
No log 8.0351 458 0.7531 0.5441 0.7531 0.8678
No log 8.0702 460 0.7601 0.5214 0.7601 0.8718
No log 8.1053 462 0.7523 0.4660 0.7523 0.8673
No log 8.1404 464 0.7613 0.5127 0.7613 0.8725
No log 8.1754 466 0.7580 0.4211 0.7580 0.8706
No log 8.2105 468 0.7462 0.4498 0.7462 0.8638
No log 8.2456 470 0.7386 0.4516 0.7386 0.8594
No log 8.2807 472 0.7311 0.4554 0.7311 0.8550
No log 8.3158 474 0.7241 0.4918 0.7241 0.8509
No log 8.3509 476 0.7255 0.5288 0.7255 0.8518
No log 8.3860 478 0.7558 0.5477 0.7558 0.8694
No log 8.4211 480 0.8785 0.4244 0.8785 0.9373
No log 8.4561 482 0.8655 0.4484 0.8655 0.9303
No log 8.4912 484 0.7904 0.4743 0.7904 0.8891
No log 8.5263 486 0.7805 0.4944 0.7805 0.8834
No log 8.5614 488 0.7972 0.4571 0.7972 0.8928
No log 8.5965 490 0.7917 0.4675 0.7917 0.8898
No log 8.6316 492 0.8116 0.4629 0.8116 0.9009
No log 8.6667 494 0.8215 0.4613 0.8215 0.9063
No log 8.7018 496 0.8032 0.4759 0.8032 0.8962
No log 8.7368 498 0.8001 0.4813 0.8001 0.8945
0.2958 8.7719 500 0.7997 0.4138 0.7997 0.8943
0.2958 8.8070 502 0.8236 0.4597 0.8236 0.9075
0.2958 8.8421 504 0.8988 0.4484 0.8988 0.9480
0.2958 8.8772 506 0.9714 0.4334 0.9714 0.9856
0.2958 8.9123 508 0.9227 0.4334 0.9227 0.9606
0.2958 8.9474 510 0.8331 0.3706 0.8331 0.9127
0.2958 8.9825 512 0.7937 0.3737 0.7937 0.8909
0.2958 9.0175 514 0.7962 0.4405 0.7962 0.8923
0.2958 9.0526 516 0.8073 0.4646 0.8073 0.8985
0.2958 9.0877 518 0.8306 0.4522 0.8306 0.9114
0.2958 9.1228 520 0.8719 0.4736 0.8719 0.9337
0.2958 9.1579 522 0.9151 0.4496 0.9151 0.9566
0.2958 9.1930 524 0.9895 0.4356 0.9895 0.9947
0.2958 9.2281 526 0.9495 0.4575 0.9495 0.9744
0.2958 9.2632 528 0.8778 0.3844 0.8778 0.9369
0.2958 9.2982 530 0.7960 0.3403 0.7960 0.8922
0.2958 9.3333 532 0.7731 0.4 0.7731 0.8793
0.2958 9.3684 534 0.7732 0.4256 0.7732 0.8793
0.2958 9.4035 536 0.7726 0.4090 0.7726 0.8790
0.2958 9.4386 538 0.7747 0.4090 0.7747 0.8802
0.2958 9.4737 540 0.7894 0.3859 0.7894 0.8885
0.2958 9.5088 542 0.7931 0.4499 0.7931 0.8905
0.2958 9.5439 544 0.7689 0.4893 0.7689 0.8769
0.2958 9.5789 546 0.7567 0.5288 0.7567 0.8699
0.2958 9.6140 548 0.7500 0.5302 0.7500 0.8660
0.2958 9.6491 550 0.7441 0.5302 0.7441 0.8626
0.2958 9.6842 552 0.7622 0.5214 0.7622 0.8730
0.2958 9.7193 554 0.7641 0.4724 0.7641 0.8741
0.2958 9.7544 556 0.7394 0.5516 0.7394 0.8599
0.2958 9.7895 558 0.7955 0.5195 0.7955 0.8919
0.2958 9.8246 560 0.8432 0.4444 0.8432 0.9182
0.2958 9.8596 562 0.8139 0.3551 0.8139 0.9022
0.2958 9.8947 564 0.7430 0.4748 0.7430 0.8620
0.2958 9.9298 566 0.7618 0.4588 0.7618 0.8728
0.2958 9.9649 568 0.8140 0.4484 0.8140 0.9022
0.2958 10.0 570 0.8170 0.5005 0.8170 0.9039
0.2958 10.0351 572 0.7902 0.5530 0.7902 0.8889
0.2958 10.0702 574 0.7697 0.5002 0.7697 0.8773
0.2958 10.1053 576 0.8322 0.4735 0.8322 0.9123
0.2958 10.1404 578 0.9392 0.4787 0.9392 0.9691
0.2958 10.1754 580 0.9821 0.3503 0.9821 0.9910
0.2958 10.2105 582 0.9051 0.3169 0.9051 0.9514
0.2958 10.2456 584 0.8034 0.3941 0.8034 0.8963
0.2958 10.2807 586 0.7467 0.4869 0.7467 0.8641
0.2958 10.3158 588 0.7406 0.4982 0.7406 0.8606
0.2958 10.3509 590 0.7497 0.4975 0.7497 0.8659
0.2958 10.3860 592 0.7678 0.4306 0.7678 0.8763
0.2958 10.4211 594 0.8056 0.4412 0.8056 0.8975
0.2958 10.4561 596 0.7966 0.4471 0.7966 0.8925
0.2958 10.4912 598 0.7801 0.4204 0.7801 0.8832
0.2958 10.5263 600 0.7696 0.3922 0.7696 0.8773
0.2958 10.5614 602 0.7695 0.3922 0.7695 0.8772
0.2958 10.5965 604 0.7759 0.4234 0.7759 0.8808
0.2958 10.6316 606 0.7762 0.4234 0.7762 0.8810
0.2958 10.6667 608 0.7765 0.3838 0.7765 0.8812
0.2958 10.7018 610 0.7913 0.3838 0.7913 0.8896
0.2958 10.7368 612 0.7956 0.3838 0.7956 0.8920
0.2958 10.7719 614 0.8005 0.3838 0.8005 0.8947
0.2958 10.8070 616 0.8187 0.3697 0.8187 0.9048

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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_run1_AugV5_k12_task5_organization

Finetuned
(4040)
this model