ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run2_AugV5_k4_task2_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: 1.1433
  • Qwk: 0.2795
  • Mse: 1.1433
  • Rmse: 1.0693

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 0.1333 2 4.8037 0.0010 4.8037 2.1917
No log 0.2667 4 3.0851 -0.0519 3.0851 1.7564
No log 0.4 6 1.8966 0.0062 1.8966 1.3772
No log 0.5333 8 2.0610 0.0092 2.0610 1.4356
No log 0.6667 10 1.9241 0.0194 1.9241 1.3871
No log 0.8 12 1.4916 -0.0366 1.4916 1.2213
No log 0.9333 14 1.4253 -0.0107 1.4253 1.1939
No log 1.0667 16 1.4025 -0.0508 1.4025 1.1843
No log 1.2 18 1.7652 0.0515 1.7652 1.3286
No log 1.3333 20 1.9567 0.0862 1.9567 1.3988
No log 1.4667 22 1.7140 0.0629 1.7140 1.3092
No log 1.6 24 1.4988 0.0227 1.4988 1.2243
No log 1.7333 26 1.3817 0.1570 1.3817 1.1755
No log 1.8667 28 1.3829 0.1568 1.3829 1.1759
No log 2.0 30 1.2599 0.2337 1.2599 1.1224
No log 2.1333 32 1.3328 0.2424 1.3328 1.1545
No log 2.2667 34 1.6800 0.1536 1.6800 1.2961
No log 2.4 36 1.7985 0.1639 1.7985 1.3411
No log 2.5333 38 1.5887 0.1909 1.5887 1.2605
No log 2.6667 40 1.2330 0.1413 1.2330 1.1104
No log 2.8 42 1.1575 0.1634 1.1575 1.0759
No log 2.9333 44 1.2650 0.1972 1.2650 1.1247
No log 3.0667 46 1.3937 0.1851 1.3937 1.1806
No log 3.2 48 1.3413 0.1756 1.3413 1.1581
No log 3.3333 50 1.1825 0.1935 1.1825 1.0874
No log 3.4667 52 1.1119 0.2745 1.1119 1.0545
No log 3.6 54 1.1088 0.3017 1.1088 1.0530
No log 3.7333 56 1.1223 0.2364 1.1223 1.0594
No log 3.8667 58 1.1885 0.2618 1.1885 1.0902
No log 4.0 60 1.1733 0.2319 1.1733 1.0832
No log 4.1333 62 1.2213 0.2220 1.2213 1.1051
No log 4.2667 64 1.2785 0.2181 1.2785 1.1307
No log 4.4 66 1.1909 0.2966 1.1909 1.0913
No log 4.5333 68 1.1886 0.2908 1.1886 1.0902
No log 4.6667 70 1.2119 0.2520 1.2119 1.1009
No log 4.8 72 1.2094 0.1951 1.2094 1.0997
No log 4.9333 74 1.2449 0.1696 1.2449 1.1157
No log 5.0667 76 1.2400 0.1753 1.2400 1.1136
No log 5.2 78 1.1691 0.2485 1.1691 1.0812
No log 5.3333 80 1.1279 0.2432 1.1279 1.0620
No log 5.4667 82 1.1531 0.2760 1.1531 1.0738
No log 5.6 84 1.3040 0.3838 1.3040 1.1419
No log 5.7333 86 1.5513 0.2343 1.5513 1.2455
No log 5.8667 88 1.5402 0.2725 1.5402 1.2411
No log 6.0 90 1.2187 0.4043 1.2187 1.1039
No log 6.1333 92 1.0777 0.4358 1.0777 1.0381
No log 6.2667 94 1.0814 0.3781 1.0814 1.0399
No log 6.4 96 1.0678 0.3619 1.0678 1.0334
No log 6.5333 98 1.0741 0.2946 1.0741 1.0364
No log 6.6667 100 1.1589 0.3135 1.1589 1.0765
No log 6.8 102 1.3153 0.2572 1.3153 1.1469
No log 6.9333 104 1.1807 0.3135 1.1807 1.0866
No log 7.0667 106 1.1233 0.3195 1.1233 1.0599
No log 7.2 108 1.1446 0.2729 1.1446 1.0699
No log 7.3333 110 1.1055 0.2661 1.1055 1.0514
No log 7.4667 112 1.2246 0.3215 1.2246 1.1066
No log 7.6 114 1.3352 0.2807 1.3352 1.1555
No log 7.7333 116 1.2045 0.3300 1.2045 1.0975
No log 7.8667 118 1.0915 0.2991 1.0915 1.0448
No log 8.0 120 1.0936 0.2991 1.0936 1.0458
No log 8.1333 122 1.1074 0.3363 1.1074 1.0523
No log 8.2667 124 1.2084 0.3260 1.2084 1.0993
No log 8.4 126 1.3351 0.2568 1.3351 1.1555
No log 8.5333 128 1.2631 0.2945 1.2631 1.1239
No log 8.6667 130 1.1851 0.2917 1.1851 1.0886
No log 8.8 132 1.2181 0.2600 1.2181 1.1037
No log 8.9333 134 1.2390 0.2600 1.2390 1.1131
No log 9.0667 136 1.2665 0.3175 1.2665 1.1254
No log 9.2 138 1.4972 0.2256 1.4972 1.2236
No log 9.3333 140 1.5460 0.2628 1.5460 1.2434
No log 9.4667 142 1.3294 0.2945 1.3294 1.1530
No log 9.6 144 1.2144 0.2042 1.2144 1.1020
No log 9.7333 146 1.2148 0.2089 1.2148 1.1022
No log 9.8667 148 1.2763 0.2221 1.2763 1.1298
No log 10.0 150 1.4492 0.2596 1.4492 1.2038
No log 10.1333 152 1.3782 0.2226 1.3782 1.1740
No log 10.2667 154 1.1940 0.2446 1.1940 1.0927
No log 10.4 156 1.1595 0.2508 1.1595 1.0768
No log 10.5333 158 1.1659 0.2529 1.1659 1.0798
No log 10.6667 160 1.3776 0.2602 1.3776 1.1737
No log 10.8 162 1.4607 0.2893 1.4607 1.2086
No log 10.9333 164 1.2667 0.2600 1.2667 1.1255
No log 11.0667 166 1.1634 0.2967 1.1634 1.0786
No log 11.2 168 1.1616 0.2850 1.1616 1.0778
No log 11.3333 170 1.1899 0.2529 1.1899 1.0908
No log 11.4667 172 1.4470 0.2536 1.4470 1.2029
No log 11.6 174 1.7289 0.2574 1.7289 1.3149
No log 11.7333 176 1.6606 0.2467 1.6606 1.2887
No log 11.8667 178 1.3257 0.2144 1.3257 1.1514
No log 12.0 180 1.1171 0.2898 1.1171 1.0569
No log 12.1333 182 1.1579 0.3043 1.1579 1.0761
No log 12.2667 184 1.1397 0.3404 1.1397 1.0675
No log 12.4 186 1.1093 0.3379 1.1093 1.0532
No log 12.5333 188 1.2916 0.2540 1.2916 1.1365
No log 12.6667 190 1.4223 0.2982 1.4223 1.1926
No log 12.8 192 1.3436 0.2942 1.3436 1.1591
No log 12.9333 194 1.1927 0.3052 1.1927 1.0921
No log 13.0667 196 1.1445 0.2964 1.1445 1.0698
No log 13.2 198 1.1703 0.2624 1.1703 1.0818
No log 13.3333 200 1.2902 0.2728 1.2902 1.1359
No log 13.4667 202 1.4016 0.2863 1.4016 1.1839
No log 13.6 204 1.3650 0.2863 1.3650 1.1683
No log 13.7333 206 1.2435 0.2329 1.2435 1.1151
No log 13.8667 208 1.1465 0.2964 1.1465 1.0707
No log 14.0 210 1.1495 0.2864 1.1495 1.0721
No log 14.1333 212 1.1819 0.2180 1.1819 1.0872
No log 14.2667 214 1.3173 0.2065 1.3173 1.1477
No log 14.4 216 1.5739 0.1966 1.5739 1.2545
No log 14.5333 218 1.6176 0.2485 1.6176 1.2718
No log 14.6667 220 1.4040 0.3002 1.4040 1.1849
No log 14.8 222 1.1896 0.2270 1.1896 1.0907
No log 14.9333 224 1.1241 0.3283 1.1241 1.0603
No log 15.0667 226 1.1380 0.2759 1.1380 1.0668
No log 15.2 228 1.1836 0.3031 1.1836 1.0879
No log 15.3333 230 1.2187 0.2673 1.2187 1.1040
No log 15.4667 232 1.2242 0.2539 1.2242 1.1064
No log 15.6 234 1.2434 0.3026 1.2434 1.1151
No log 15.7333 236 1.1413 0.2963 1.1413 1.0683
No log 15.8667 238 1.0680 0.3090 1.0680 1.0334
No log 16.0 240 1.0636 0.2942 1.0636 1.0313
No log 16.1333 242 1.0742 0.2915 1.0742 1.0365
No log 16.2667 244 1.1357 0.3356 1.1357 1.0657
No log 16.4 246 1.2426 0.1738 1.2426 1.1147
No log 16.5333 248 1.2265 0.2229 1.2265 1.1075
No log 16.6667 250 1.1587 0.3305 1.1587 1.0764
No log 16.8 252 1.1338 0.3678 1.1338 1.0648
No log 16.9333 254 1.1415 0.3353 1.1415 1.0684
No log 17.0667 256 1.2017 0.3243 1.2017 1.0962
No log 17.2 258 1.3839 0.1726 1.3839 1.1764
No log 17.3333 260 1.4734 0.1902 1.4734 1.2138
No log 17.4667 262 1.3581 0.1801 1.3581 1.1654
No log 17.6 264 1.2056 0.1634 1.2056 1.0980
No log 17.7333 266 1.1773 0.2071 1.1773 1.0850
No log 17.8667 268 1.1489 0.2198 1.1489 1.0719
No log 18.0 270 1.1407 0.2431 1.1407 1.0680
No log 18.1333 272 1.1276 0.2757 1.1276 1.0619
No log 18.2667 274 1.1177 0.2679 1.1177 1.0572
No log 18.4 276 1.1195 0.2489 1.1195 1.0581
No log 18.5333 278 1.1748 0.2896 1.1748 1.0839
No log 18.6667 280 1.2551 0.2780 1.2551 1.1203
No log 18.8 282 1.2219 0.3074 1.2219 1.1054
No log 18.9333 284 1.1254 0.2728 1.1254 1.0608
No log 19.0667 286 1.1006 0.2394 1.1006 1.0491
No log 19.2 288 1.0926 0.2483 1.0926 1.0453
No log 19.3333 290 1.1033 0.2431 1.1033 1.0504
No log 19.4667 292 1.1513 0.3812 1.1513 1.0730
No log 19.6 294 1.1661 0.3812 1.1661 1.0799
No log 19.7333 296 1.1135 0.2902 1.1135 1.0552
No log 19.8667 298 1.0964 0.3015 1.0964 1.0471
No log 20.0 300 1.0998 0.2871 1.0998 1.0487
No log 20.1333 302 1.1104 0.2764 1.1104 1.0538
No log 20.2667 304 1.1370 0.1975 1.1370 1.0663
No log 20.4 306 1.1682 0.2372 1.1682 1.0808
No log 20.5333 308 1.1993 0.2232 1.1993 1.0951
No log 20.6667 310 1.1483 0.2372 1.1483 1.0716
No log 20.8 312 1.0854 0.3066 1.0854 1.0418
No log 20.9333 314 1.0776 0.2793 1.0776 1.0381
No log 21.0667 316 1.0749 0.2793 1.0749 1.0368
No log 21.2 318 1.1279 0.2012 1.1279 1.0620
No log 21.3333 320 1.2728 0.3243 1.2728 1.1282
No log 21.4667 322 1.2846 0.3243 1.2846 1.1334
No log 21.6 324 1.1559 0.3189 1.1559 1.0751
No log 21.7333 326 1.0835 0.2745 1.0835 1.0409
No log 21.8667 328 1.0798 0.2483 1.0798 1.0391
No log 22.0 330 1.0917 0.3090 1.0917 1.0448
No log 22.1333 332 1.1348 0.2601 1.1348 1.0653
No log 22.2667 334 1.2211 0.2181 1.2211 1.1051
No log 22.4 336 1.2901 0.2313 1.2901 1.1358
No log 22.5333 338 1.2402 0.2615 1.2402 1.1136
No log 22.6667 340 1.1224 0.3199 1.1224 1.0594
No log 22.8 342 1.0771 0.2892 1.0771 1.0378
No log 22.9333 344 1.0755 0.2764 1.0755 1.0371
No log 23.0667 346 1.1070 0.3230 1.1070 1.0521
No log 23.2 348 1.1792 0.3165 1.1792 1.0859
No log 23.3333 350 1.1660 0.3165 1.1660 1.0798
No log 23.4667 352 1.0859 0.3230 1.0859 1.0421
No log 23.6 354 1.0508 0.3237 1.0508 1.0251
No log 23.7333 356 1.0472 0.3137 1.0472 1.0233
No log 23.8667 358 1.0364 0.3237 1.0364 1.0180
No log 24.0 360 1.0254 0.3237 1.0254 1.0126
No log 24.1333 362 1.0451 0.3671 1.0451 1.0223
No log 24.2667 364 1.1500 0.3193 1.1500 1.0724
No log 24.4 366 1.3399 0.2516 1.3399 1.1576
No log 24.5333 368 1.3612 0.2516 1.3612 1.1667
No log 24.6667 370 1.1952 0.2451 1.1952 1.0932
No log 24.8 372 1.0653 0.3678 1.0653 1.0321
No log 24.9333 374 1.0242 0.3237 1.0242 1.0120
No log 25.0667 376 1.0388 0.3190 1.0388 1.0192
No log 25.2 378 1.0502 0.3237 1.0502 1.0248
No log 25.3333 380 1.0599 0.3529 1.0599 1.0295
No log 25.4667 382 1.1416 0.3614 1.1416 1.0685
No log 25.6 384 1.2413 0.2758 1.2413 1.1141
No log 25.7333 386 1.1992 0.2143 1.1992 1.0951
No log 25.8667 388 1.0675 0.3668 1.0675 1.0332
No log 26.0 390 1.0088 0.3627 1.0088 1.0044
No log 26.1333 392 1.0012 0.2993 1.0012 1.0006
No log 26.2667 394 1.0050 0.3525 1.0050 1.0025
No log 26.4 396 1.0268 0.3184 1.0268 1.0133
No log 26.5333 398 1.0975 0.3930 1.0975 1.0476
No log 26.6667 400 1.1991 0.3487 1.1991 1.0950
No log 26.8 402 1.2668 0.2516 1.2668 1.1255
No log 26.9333 404 1.2596 0.2394 1.2596 1.1223
No log 27.0667 406 1.1692 0.3487 1.1692 1.0813
No log 27.2 408 1.0921 0.3714 1.0921 1.0451
No log 27.3333 410 1.0766 0.3584 1.0766 1.0376
No log 27.4667 412 1.0944 0.3521 1.0944 1.0461
No log 27.6 414 1.0654 0.2669 1.0654 1.0322
No log 27.7333 416 1.0497 0.3110 1.0497 1.0245
No log 27.8667 418 1.0819 0.2938 1.0819 1.0402
No log 28.0 420 1.0944 0.3430 1.0944 1.0461
No log 28.1333 422 1.1291 0.3828 1.1291 1.0626
No log 28.2667 424 1.1562 0.3220 1.1562 1.0753
No log 28.4 426 1.1594 0.2918 1.1594 1.0767
No log 28.5333 428 1.1899 0.2635 1.1899 1.0908
No log 28.6667 430 1.2096 0.2635 1.2096 1.0998
No log 28.8 432 1.1122 0.3584 1.1122 1.0546
No log 28.9333 434 1.0630 0.4156 1.0630 1.0310
No log 29.0667 436 1.0085 0.4197 1.0085 1.0043
No log 29.2 438 0.9971 0.4159 0.9971 0.9986
No log 29.3333 440 1.0280 0.3869 1.0280 1.0139
No log 29.4667 442 1.1308 0.3523 1.1308 1.0634
No log 29.6 444 1.2061 0.2619 1.2061 1.0982
No log 29.7333 446 1.1929 0.2619 1.1929 1.0922
No log 29.8667 448 1.1686 0.2473 1.1686 1.0810
No log 30.0 450 1.1705 0.2473 1.1705 1.0819
No log 30.1333 452 1.2116 0.2062 1.2116 1.1007
No log 30.2667 454 1.1959 0.2062 1.1959 1.0936
No log 30.4 456 1.1413 0.2459 1.1413 1.0683
No log 30.5333 458 1.0939 0.2748 1.0939 1.0459
No log 30.6667 460 1.0860 0.2748 1.0860 1.0421
No log 30.8 462 1.0858 0.3056 1.0858 1.0420
No log 30.9333 464 1.0566 0.3154 1.0566 1.0279
No log 31.0667 466 1.0394 0.3443 1.0394 1.0195
No log 31.2 468 1.0390 0.3443 1.0390 1.0193
No log 31.3333 470 1.0441 0.3184 1.0441 1.0218
No log 31.4667 472 1.0677 0.3490 1.0677 1.0333
No log 31.6 474 1.1557 0.3355 1.1557 1.0750
No log 31.7333 476 1.1811 0.2631 1.1811 1.0868
No log 31.8667 478 1.1246 0.3255 1.1246 1.0605
No log 32.0 480 1.0463 0.2941 1.0463 1.0229
No log 32.1333 482 1.0213 0.3483 1.0213 1.0106
No log 32.2667 484 1.0336 0.3483 1.0336 1.0167
No log 32.4 486 1.0702 0.3154 1.0702 1.0345
No log 32.5333 488 1.1045 0.3305 1.1045 1.0509
No log 32.6667 490 1.1142 0.3939 1.1142 1.0556
No log 32.8 492 1.1272 0.3255 1.1272 1.0617
No log 32.9333 494 1.0976 0.2747 1.0976 1.0477
No log 33.0667 496 1.0984 0.2665 1.0984 1.0480
No log 33.2 498 1.1439 0.3224 1.1439 1.0695
0.278 33.3333 500 1.1568 0.3602 1.1568 1.0756
0.278 33.4667 502 1.1920 0.2890 1.1920 1.0918
0.278 33.6 504 1.1932 0.2565 1.1932 1.0924
0.278 33.7333 506 1.2111 0.2644 1.2111 1.1005
0.278 33.8667 508 1.1832 0.2467 1.1832 1.0878
0.278 34.0 510 1.1433 0.2795 1.1433 1.0693

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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_k4_task2_organization

Finetuned
(4019)
this model