ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run2_AugV5_k19_task1_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: 1.1284
  • Qwk: 0.5496
  • Mse: 1.1284
  • Rmse: 1.0622

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 0.0225 2 7.2134 0.0 7.2134 2.6858
No log 0.0449 4 5.3607 0.0352 5.3607 2.3153
No log 0.0674 6 4.7503 -0.0571 4.7503 2.1795
No log 0.0899 8 4.8731 -0.1315 4.8731 2.2075
No log 0.1124 10 3.9373 -0.1202 3.9373 1.9843
No log 0.1348 12 3.0730 -0.0645 3.0730 1.7530
No log 0.1573 14 3.0276 0.0261 3.0276 1.7400
No log 0.1798 16 2.7943 0.0921 2.7943 1.6716
No log 0.2022 18 2.1513 0.1679 2.1513 1.4667
No log 0.2247 20 1.9512 0.2188 1.9512 1.3969
No log 0.2472 22 1.8918 0.2879 1.8918 1.3754
No log 0.2697 24 1.8306 0.2698 1.8306 1.3530
No log 0.2921 26 1.8647 0.2362 1.8647 1.3655
No log 0.3146 28 1.7745 0.3182 1.7745 1.3321
No log 0.3371 30 1.8570 0.3453 1.8570 1.3627
No log 0.3596 32 2.1380 0.2548 2.1380 1.4622
No log 0.3820 34 2.4204 0.2690 2.4204 1.5558
No log 0.4045 36 1.9686 0.3694 1.9686 1.4031
No log 0.4270 38 1.8098 0.3158 1.8098 1.3453
No log 0.4494 40 1.8320 0.3694 1.8320 1.3535
No log 0.4719 42 2.0430 0.3735 2.0430 1.4293
No log 0.4944 44 2.2826 0.3978 2.2826 1.5108
No log 0.5169 46 2.0000 0.3780 2.0000 1.4142
No log 0.5393 48 1.7250 0.3467 1.7250 1.3134
No log 0.5618 50 1.8809 0.3875 1.8809 1.3715
No log 0.5843 52 2.5762 0.3249 2.5762 1.6051
No log 0.6067 54 3.1422 0.2190 3.1422 1.7726
No log 0.6292 56 2.8611 0.2871 2.8611 1.6915
No log 0.6517 58 1.9608 0.2953 1.9608 1.4003
No log 0.6742 60 1.6830 0.2923 1.6830 1.2973
No log 0.6966 62 1.6870 0.3182 1.6870 1.2989
No log 0.7191 64 1.8700 0.3333 1.8700 1.3675
No log 0.7416 66 2.3479 0.2807 2.3479 1.5323
No log 0.7640 68 2.7169 0.3404 2.7169 1.6483
No log 0.7865 70 2.2318 0.3041 2.2318 1.4939
No log 0.8090 72 1.5629 0.3688 1.5629 1.2502
No log 0.8315 74 1.1909 0.5630 1.1909 1.0913
No log 0.8539 76 1.2556 0.4480 1.2556 1.1206
No log 0.8764 78 1.5098 0.4672 1.5098 1.2287
No log 0.8989 80 1.8599 0.3179 1.8599 1.3638
No log 0.9213 82 2.0433 0.3086 2.0433 1.4294
No log 0.9438 84 1.9373 0.3810 1.9373 1.3919
No log 0.9663 86 1.4270 0.4865 1.4270 1.1946
No log 0.9888 88 1.3012 0.4714 1.3012 1.1407
No log 1.0112 90 1.3953 0.4476 1.3953 1.1812
No log 1.0337 92 1.5285 0.4768 1.5285 1.2363
No log 1.0562 94 1.3973 0.4317 1.3973 1.1821
No log 1.0787 96 1.1983 0.5588 1.1983 1.0947
No log 1.1011 98 1.1186 0.5538 1.1186 1.0577
No log 1.1236 100 1.2255 0.4559 1.2255 1.1070
No log 1.1461 102 1.4136 0.4459 1.4136 1.1890
No log 1.1685 104 1.6499 0.5 1.6499 1.2845
No log 1.1910 106 1.5350 0.4684 1.5350 1.2390
No log 1.2135 108 1.6396 0.5 1.6396 1.2805
No log 1.2360 110 1.7818 0.4588 1.7818 1.3348
No log 1.2584 112 2.1136 0.4171 2.1136 1.4538
No log 1.2809 114 2.0252 0.4375 2.0252 1.4231
No log 1.3034 116 1.7049 0.4920 1.7049 1.3057
No log 1.3258 118 1.0085 0.6835 1.0085 1.0043
No log 1.3483 120 0.7977 0.6986 0.7977 0.8931
No log 1.3708 122 0.9196 0.6364 0.9196 0.9590
No log 1.3933 124 0.8920 0.6471 0.8920 0.9445
No log 1.4157 126 0.8635 0.6232 0.8635 0.9292
No log 1.4382 128 0.8825 0.6377 0.8825 0.9394
No log 1.4607 130 0.8595 0.6809 0.8595 0.9271
No log 1.4831 132 0.9825 0.6667 0.9825 0.9912
No log 1.5056 134 1.0496 0.6133 1.0496 1.0245
No log 1.5281 136 1.1130 0.5882 1.1130 1.0550
No log 1.5506 138 1.2638 0.5 1.2638 1.1242
No log 1.5730 140 1.3006 0.4341 1.3006 1.1404
No log 1.5955 142 1.2366 0.5538 1.2366 1.1120
No log 1.6180 144 1.3114 0.4901 1.3114 1.1452
No log 1.6404 146 1.4161 0.4487 1.4161 1.1900
No log 1.6629 148 1.5022 0.475 1.5022 1.2256
No log 1.6854 150 1.4348 0.4267 1.4348 1.1978
No log 1.7079 152 1.3345 0.4812 1.3345 1.1552
No log 1.7303 154 1.2587 0.5414 1.2587 1.1219
No log 1.7528 156 1.1781 0.5775 1.1781 1.0854
No log 1.7753 158 1.1961 0.5963 1.1961 1.0937
No log 1.7978 160 1.1819 0.6587 1.1819 1.0872
No log 1.8202 162 1.0095 0.6369 1.0095 1.0048
No log 1.8427 164 0.9580 0.6331 0.9580 0.9788
No log 1.8652 166 1.0622 0.5821 1.0622 1.0306
No log 1.8876 168 1.2021 0.5839 1.2021 1.0964
No log 1.9101 170 1.1218 0.5942 1.1218 1.0591
No log 1.9326 172 1.0594 0.5816 1.0594 1.0293
No log 1.9551 174 0.9813 0.6331 0.9813 0.9906
No log 1.9775 176 0.9044 0.6383 0.9044 0.9510
No log 2.0 178 0.9177 0.6286 0.9177 0.9580
No log 2.0225 180 0.9928 0.6176 0.9928 0.9964
No log 2.0449 182 1.0184 0.5926 1.0184 1.0092
No log 2.0674 184 1.0088 0.5957 1.0088 1.0044
No log 2.0899 186 1.0944 0.5931 1.0944 1.0461
No log 2.1124 188 1.1674 0.6194 1.1674 1.0805
No log 2.1348 190 1.1058 0.6043 1.1058 1.0516
No log 2.1573 192 1.1238 0.5735 1.1238 1.0601
No log 2.1798 194 1.1582 0.5692 1.1582 1.0762
No log 2.2022 196 1.1020 0.6119 1.1020 1.0497
No log 2.2247 198 1.0556 0.6277 1.0556 1.0274
No log 2.2472 200 1.1274 0.5857 1.1274 1.0618
No log 2.2697 202 1.2733 0.5294 1.2733 1.1284
No log 2.2921 204 1.2829 0.5532 1.2829 1.1326
No log 2.3146 206 1.2342 0.5479 1.2342 1.1109
No log 2.3371 208 1.2162 0.5594 1.2162 1.1028
No log 2.3596 210 1.1885 0.5833 1.1885 1.0902
No log 2.3820 212 1.1255 0.5405 1.1255 1.0609
No log 2.4045 214 1.0050 0.6 1.0050 1.0025
No log 2.4270 216 1.0427 0.6056 1.0427 1.0211
No log 2.4494 218 1.0615 0.6277 1.0615 1.0303
No log 2.4719 220 1.0221 0.6222 1.0221 1.0110
No log 2.4944 222 0.9356 0.6571 0.9356 0.9673
No log 2.5169 224 0.9335 0.6331 0.9335 0.9662
No log 2.5393 226 0.9652 0.6187 0.9652 0.9824
No log 2.5618 228 1.0085 0.5957 1.0085 1.0042
No log 2.5843 230 1.0354 0.6029 1.0354 1.0175
No log 2.6067 232 1.0701 0.6 1.0701 1.0345
No log 2.6292 234 1.1340 0.5954 1.1340 1.0649
No log 2.6517 236 1.1841 0.5571 1.1841 1.0882
No log 2.6742 238 1.2438 0.5180 1.2438 1.1152
No log 2.6966 240 1.1216 0.5970 1.1216 1.0591
No log 2.7191 242 1.0138 0.6324 1.0138 1.0069
No log 2.7416 244 0.9756 0.6364 0.9756 0.9877
No log 2.7640 246 0.9970 0.6466 0.9970 0.9985
No log 2.7865 248 1.0132 0.6565 1.0132 1.0066
No log 2.8090 250 1.0457 0.6357 1.0457 1.0226
No log 2.8315 252 1.0608 0.6519 1.0608 1.0300
No log 2.8539 254 0.9763 0.6618 0.9763 0.9881
No log 2.8764 256 0.9411 0.5926 0.9411 0.9701
No log 2.8989 258 0.9724 0.6187 0.9724 0.9861
No log 2.9213 260 0.9786 0.5915 0.9786 0.9892
No log 2.9438 262 0.9975 0.5816 0.9975 0.9988
No log 2.9663 264 0.9224 0.6015 0.9224 0.9604
No log 2.9888 266 0.9125 0.6383 0.9125 0.9552
No log 3.0112 268 0.9664 0.6197 0.9664 0.9831
No log 3.0337 270 0.9647 0.5714 0.9647 0.9822
No log 3.0562 272 1.0690 0.5373 1.0690 1.0339
No log 3.0787 274 1.1012 0.5113 1.1012 1.0494
No log 3.1011 276 1.0254 0.5571 1.0254 1.0126
No log 3.1236 278 1.0331 0.6405 1.0331 1.0164
No log 3.1461 280 1.1037 0.6275 1.1037 1.0506
No log 3.1685 282 1.0525 0.6389 1.0525 1.0259
No log 3.1910 284 1.0859 0.5 1.0859 1.0421
No log 3.2135 286 1.1223 0.5496 1.1223 1.0594
No log 3.2360 288 1.0833 0.6061 1.0833 1.0408
No log 3.2584 290 1.0888 0.5581 1.0888 1.0434
No log 3.2809 292 1.1401 0.5289 1.1401 1.0677
No log 3.3034 294 1.1978 0.4915 1.1978 1.0944
No log 3.3258 296 1.1873 0.5289 1.1873 1.0896
No log 3.3483 298 1.2005 0.5410 1.2005 1.0957
No log 3.3708 300 1.2117 0.5082 1.2117 1.1008
No log 3.3933 302 1.1979 0.5082 1.1979 1.0945
No log 3.4157 304 1.2473 0.5556 1.2473 1.1168
No log 3.4382 306 1.3432 0.5116 1.3432 1.1590
No log 3.4607 308 1.2675 0.5385 1.2675 1.1258
No log 3.4831 310 1.1291 0.5556 1.1291 1.0626
No log 3.5056 312 1.0374 0.6094 1.0374 1.0185
No log 3.5281 314 0.9999 0.6142 0.9999 1.0000
No log 3.5506 316 1.0151 0.5938 1.0151 1.0075
No log 3.5730 318 1.0421 0.5827 1.0421 1.0209
No log 3.5955 320 1.0968 0.5692 1.0968 1.0473
No log 3.6180 322 1.1765 0.5373 1.1765 1.0846
No log 3.6404 324 1.2046 0.5185 1.2046 1.0975
No log 3.6629 326 1.1362 0.5714 1.1362 1.0659
No log 3.6854 328 1.0053 0.6370 1.0053 1.0027
No log 3.7079 330 0.9675 0.6260 0.9675 0.9836
No log 3.7303 332 0.9677 0.6202 0.9677 0.9837
No log 3.7528 334 0.9806 0.5984 0.9806 0.9903
No log 3.7753 336 1.0202 0.6087 1.0202 1.0100
No log 3.7978 338 1.0190 0.6405 1.0190 1.0095
No log 3.8202 340 0.9294 0.6364 0.9294 0.9641
No log 3.8427 342 0.8788 0.6815 0.8788 0.9374
No log 3.8652 344 0.9320 0.6364 0.9320 0.9654
No log 3.8876 346 0.9478 0.6 0.9478 0.9736
No log 3.9101 348 0.9074 0.6471 0.9074 0.9526
No log 3.9326 350 0.9140 0.6901 0.9140 0.9560
No log 3.9551 352 1.0431 0.6074 1.0431 1.0213
No log 3.9775 354 1.2526 0.4892 1.2526 1.1192
No log 4.0 356 1.3375 0.4733 1.3375 1.1565
No log 4.0225 358 1.2446 0.5426 1.2446 1.1156
No log 4.0449 360 1.1533 0.6061 1.1533 1.0739
No log 4.0674 362 0.9832 0.6412 0.9832 0.9915
No log 4.0899 364 0.9469 0.5909 0.9469 0.9731
No log 4.1124 366 0.9760 0.6358 0.9760 0.9879
No log 4.1348 368 0.9364 0.6207 0.9364 0.9677
No log 4.1573 370 0.9458 0.6438 0.9458 0.9725
No log 4.1798 372 0.8813 0.6324 0.8813 0.9388
No log 4.2022 374 0.8769 0.7059 0.8769 0.9365
No log 4.2247 376 0.9802 0.6260 0.9802 0.9901
No log 4.2472 378 1.0905 0.6047 1.0905 1.0443
No log 4.2697 380 1.2058 0.5271 1.2058 1.0981
No log 4.2921 382 1.2990 0.5038 1.2990 1.1397
No log 4.3146 384 1.2500 0.5271 1.2500 1.1181
No log 4.3371 386 1.1033 0.5891 1.1033 1.0504
No log 4.3596 388 0.9822 0.6142 0.9822 0.9911
No log 4.3820 390 0.9840 0.6032 0.9840 0.9920
No log 4.4045 392 1.1194 0.5581 1.1194 1.0580
No log 4.4270 394 1.1447 0.5231 1.1447 1.0699
No log 4.4494 396 1.0092 0.6870 1.0092 1.0046
No log 4.4719 398 0.9297 0.6299 0.9297 0.9642
No log 4.4944 400 0.9109 0.6364 0.9109 0.9544
No log 4.5169 402 0.9237 0.6412 0.9237 0.9611
No log 4.5393 404 0.9942 0.5920 0.9942 0.9971
No log 4.5618 406 1.2014 0.4882 1.2014 1.0961
No log 4.5843 408 1.3009 0.4496 1.3009 1.1406
No log 4.6067 410 1.2380 0.496 1.2380 1.1126
No log 4.6292 412 1.0891 0.5620 1.0891 1.0436
No log 4.6517 414 1.0388 0.5167 1.0388 1.0192
No log 4.6742 416 0.9764 0.5873 0.9764 0.9881
No log 4.6966 418 0.9277 0.6142 0.9277 0.9632
No log 4.7191 420 0.9679 0.625 0.9679 0.9838
No log 4.7416 422 0.9970 0.625 0.9970 0.9985
No log 4.7640 424 0.9769 0.6357 0.9769 0.9884
No log 4.7865 426 0.9855 0.6357 0.9855 0.9927
No log 4.8090 428 0.9425 0.5970 0.9425 0.9708
No log 4.8315 430 0.8667 0.6906 0.8667 0.9310
No log 4.8539 432 0.8560 0.7143 0.8560 0.9252
No log 4.8764 434 0.8573 0.7143 0.8573 0.9259
No log 4.8989 436 0.8570 0.7222 0.8570 0.9258
No log 4.9213 438 0.8719 0.6901 0.8719 0.9337
No log 4.9438 440 0.9802 0.6395 0.9802 0.9901
No log 4.9663 442 0.9742 0.5926 0.9742 0.9870
No log 4.9888 444 0.9131 0.6357 0.9131 0.9556
No log 5.0112 446 0.9344 0.6047 0.9344 0.9667
No log 5.0337 448 0.9272 0.6357 0.9272 0.9629
No log 5.0562 450 0.9283 0.6565 0.9283 0.9635
No log 5.0787 452 0.9282 0.6202 0.9282 0.9634
No log 5.1011 454 0.9745 0.6565 0.9745 0.9871
No log 5.1236 456 0.9611 0.6364 0.9611 0.9804
No log 5.1461 458 0.9171 0.6412 0.9171 0.9577
No log 5.1685 460 0.9839 0.6107 0.9839 0.9919
No log 5.1910 462 1.1090 0.5839 1.1090 1.0531
No log 5.2135 464 0.9142 0.5909 0.9142 0.9562
No log 5.2360 466 0.8299 0.6617 0.8299 0.9110
No log 5.2584 468 0.9717 0.6615 0.9717 0.9858
No log 5.2809 470 1.1808 0.5625 1.1808 1.0867
No log 5.3034 472 1.2612 0.5312 1.2612 1.1230
No log 5.3258 474 1.2321 0.5669 1.2321 1.1100
No log 5.3483 476 1.1453 0.5366 1.1453 1.0702
No log 5.3708 478 1.0767 0.5806 1.0767 1.0376
No log 5.3933 480 1.0647 0.5806 1.0647 1.0318
No log 5.4157 482 1.0824 0.6032 1.0824 1.0404
No log 5.4382 484 1.0585 0.5920 1.0585 1.0288
No log 5.4607 486 1.0085 0.6462 1.0085 1.0043
No log 5.4831 488 0.9564 0.6565 0.9564 0.9780
No log 5.5056 490 0.9614 0.6269 0.9614 0.9805
No log 5.5281 492 0.9359 0.6370 0.9359 0.9674
No log 5.5506 494 0.8823 0.6471 0.8823 0.9393
No log 5.5730 496 0.8603 0.6471 0.8603 0.9275
No log 5.5955 498 0.8532 0.6619 0.8532 0.9237
0.4359 5.6180 500 0.9381 0.6277 0.9381 0.9685
0.4359 5.6404 502 1.0380 0.5865 1.0380 1.0188
0.4359 5.6629 504 1.0569 0.5970 1.0569 1.0281
0.4359 5.6854 506 1.0568 0.6061 1.0568 1.0280
0.4359 5.7079 508 1.0696 0.5758 1.0696 1.0342
0.4359 5.7303 510 1.0062 0.6418 1.0062 1.0031
0.4359 5.7528 512 0.9404 0.6765 0.9404 0.9697
0.4359 5.7753 514 0.9696 0.6418 0.9696 0.9847
0.4359 5.7978 516 0.9529 0.6418 0.9529 0.9762
0.4359 5.8202 518 0.8824 0.6765 0.8824 0.9393
0.4359 5.8427 520 0.8262 0.6765 0.8262 0.9090
0.4359 5.8652 522 0.8430 0.7015 0.8430 0.9182
0.4359 5.8876 524 0.8222 0.6866 0.8222 0.9068
0.4359 5.9101 526 0.7892 0.6963 0.7892 0.8883
0.4359 5.9326 528 0.8062 0.6466 0.8062 0.8979
0.4359 5.9551 530 0.8229 0.6963 0.8229 0.9072
0.4359 5.9775 532 0.8797 0.6870 0.8797 0.9379
0.4359 6.0 534 0.9750 0.6364 0.9750 0.9874
0.4359 6.0225 536 0.9532 0.6519 0.9532 0.9763
0.4359 6.0449 538 0.8818 0.6715 0.8818 0.9390
0.4359 6.0674 540 0.9169 0.6765 0.9169 0.9576
0.4359 6.0899 542 0.9865 0.6324 0.9865 0.9932
0.4359 6.1124 544 0.9571 0.6866 0.9571 0.9783
0.4359 6.1348 546 0.8610 0.6866 0.8610 0.9279
0.4359 6.1573 548 0.8670 0.6866 0.8670 0.9311
0.4359 6.1798 550 0.9644 0.6718 0.9644 0.9820
0.4359 6.2022 552 1.0570 0.6462 1.0570 1.0281
0.4359 6.2247 554 1.0126 0.6718 1.0126 1.0063
0.4359 6.2472 556 0.9115 0.6718 0.9115 0.9547
0.4359 6.2697 558 0.7895 0.7007 0.7895 0.8885
0.4359 6.2921 560 0.7420 0.7324 0.7420 0.8614
0.4359 6.3146 562 0.7746 0.7015 0.7746 0.8801
0.4359 6.3371 564 0.9558 0.5909 0.9558 0.9776
0.4359 6.3596 566 1.2350 0.5303 1.2350 1.1113
0.4359 6.3820 568 1.3904 0.4328 1.3904 1.1792
0.4359 6.4045 570 1.3306 0.4580 1.3306 1.1535
0.4359 6.4270 572 1.1284 0.5496 1.1284 1.0622

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_usingALLEssays_FineTuningAraBERT_run2_AugV5_k19_task1_organization

Finetuned
(4023)
this model