ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k2_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: 1.3158
  • Qwk: 0.1789
  • Mse: 1.3158
  • Rmse: 1.1471

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 0.3333 2 4.8322 -0.0104 4.8322 2.1982
No log 0.6667 4 2.9490 -0.0434 2.9490 1.7173
No log 1.0 6 1.6493 0.0504 1.6493 1.2843
No log 1.3333 8 1.6144 0.0372 1.6144 1.2706
No log 1.6667 10 1.6107 -0.0146 1.6107 1.2691
No log 2.0 12 1.4117 -0.0359 1.4117 1.1882
No log 2.3333 14 1.2585 0.2095 1.2585 1.1218
No log 2.6667 16 1.2138 0.0979 1.2138 1.1017
No log 3.0 18 1.2825 0.0865 1.2825 1.1325
No log 3.3333 20 1.5319 0.0 1.5319 1.2377
No log 3.6667 22 1.5811 0.0 1.5811 1.2574
No log 4.0 24 1.5866 0.0 1.5866 1.2596
No log 4.3333 26 1.2705 0.1735 1.2705 1.1272
No log 4.6667 28 1.2414 0.1904 1.2414 1.1142
No log 5.0 30 1.3685 0.0575 1.3685 1.1698
No log 5.3333 32 1.2534 0.1809 1.2534 1.1195
No log 5.6667 34 1.1732 0.2212 1.1732 1.0831
No log 6.0 36 1.2000 0.1830 1.2000 1.0954
No log 6.3333 38 1.2358 0.1014 1.2358 1.1117
No log 6.6667 40 1.2172 0.1260 1.2172 1.1033
No log 7.0 42 1.2801 0.0894 1.2801 1.1314
No log 7.3333 44 1.1954 0.1601 1.1954 1.0934
No log 7.6667 46 1.1430 0.2188 1.1430 1.0691
No log 8.0 48 1.1747 0.1546 1.1747 1.0838
No log 8.3333 50 1.1355 0.1654 1.1355 1.0656
No log 8.6667 52 1.1752 0.1565 1.1752 1.0841
No log 9.0 54 1.1521 0.1713 1.1521 1.0734
No log 9.3333 56 1.1911 0.0945 1.1911 1.0914
No log 9.6667 58 1.1215 0.1278 1.1215 1.0590
No log 10.0 60 1.0667 0.1814 1.0667 1.0328
No log 10.3333 62 1.0701 0.2624 1.0701 1.0345
No log 10.6667 64 1.1085 0.1649 1.1085 1.0529
No log 11.0 66 1.1548 0.1969 1.1548 1.0746
No log 11.3333 68 1.0936 0.2175 1.0936 1.0458
No log 11.6667 70 1.2569 0.1803 1.2569 1.1211
No log 12.0 72 1.1837 0.2315 1.1837 1.0880
No log 12.3333 74 1.1357 0.2432 1.1357 1.0657
No log 12.6667 76 1.3680 0.1163 1.3680 1.1696
No log 13.0 78 1.3922 0.1395 1.3922 1.1799
No log 13.3333 80 1.1933 0.1654 1.1933 1.0924
No log 13.6667 82 1.1312 0.2942 1.1312 1.0636
No log 14.0 84 1.1045 0.3318 1.1045 1.0510
No log 14.3333 86 1.1199 0.1343 1.1199 1.0582
No log 14.6667 88 1.4005 0.1142 1.4005 1.1834
No log 15.0 90 1.4141 0.0598 1.4141 1.1891
No log 15.3333 92 1.2041 0.1176 1.2041 1.0973
No log 15.6667 94 1.1072 0.2835 1.1072 1.0522
No log 16.0 96 1.0880 0.2835 1.0880 1.0431
No log 16.3333 98 1.1478 0.2083 1.1478 1.0713
No log 16.6667 100 1.2164 0.1752 1.2164 1.1029
No log 17.0 102 1.2181 0.1910 1.2181 1.1037
No log 17.3333 104 1.0854 0.2164 1.0854 1.0418
No log 17.6667 106 1.0640 0.2121 1.0640 1.0315
No log 18.0 108 1.1700 0.2330 1.1700 1.0817
No log 18.3333 110 1.3452 0.2589 1.3452 1.1598
No log 18.6667 112 1.2815 0.2889 1.2815 1.1320
No log 19.0 114 1.1075 0.1482 1.1075 1.0524
No log 19.3333 116 1.0568 0.2835 1.0568 1.0280
No log 19.6667 118 1.0705 0.2257 1.0705 1.0346
No log 20.0 120 1.1457 0.1585 1.1457 1.0704
No log 20.3333 122 1.3549 0.1188 1.3549 1.1640
No log 20.6667 124 1.5116 0.2806 1.5116 1.2295
No log 21.0 126 1.4027 0.3113 1.4027 1.1843
No log 21.3333 128 1.2201 0.2702 1.2201 1.1046
No log 21.6667 130 1.1696 0.2899 1.1696 1.0815
No log 22.0 132 1.2208 0.2322 1.2208 1.1049
No log 22.3333 134 1.3004 0.2108 1.3004 1.1404
No log 22.6667 136 1.2863 0.1903 1.2863 1.1341
No log 23.0 138 1.1770 0.2894 1.1770 1.0849
No log 23.3333 140 1.1659 0.1546 1.1659 1.0797
No log 23.6667 142 1.2769 0.25 1.2769 1.1300
No log 24.0 144 1.4751 0.2941 1.4751 1.2145
No log 24.3333 146 1.4746 0.2941 1.4746 1.2143
No log 24.6667 148 1.3126 0.2317 1.3126 1.1457
No log 25.0 150 1.1679 0.1801 1.1679 1.0807
No log 25.3333 152 1.1265 0.2689 1.1265 1.0614
No log 25.6667 154 1.1547 0.2263 1.1547 1.0746
No log 26.0 156 1.2801 0.2424 1.2801 1.1314
No log 26.3333 158 1.3457 0.2105 1.3457 1.1601
No log 26.6667 160 1.2711 0.1840 1.2711 1.1274
No log 27.0 162 1.1560 0.2220 1.1560 1.0752
No log 27.3333 164 1.1028 0.2119 1.1028 1.0501
No log 27.6667 166 1.1005 0.1585 1.1005 1.0491
No log 28.0 168 1.1764 0.0904 1.1764 1.0846
No log 28.3333 170 1.1931 0.1249 1.1931 1.0923
No log 28.6667 172 1.1343 0.1541 1.1343 1.0650
No log 29.0 174 1.0938 0.2276 1.0938 1.0458
No log 29.3333 176 1.0917 0.2276 1.0917 1.0448
No log 29.6667 178 1.1369 0.2402 1.1369 1.0662
No log 30.0 180 1.2902 0.2238 1.2902 1.1359
No log 30.3333 182 1.4964 0.2711 1.4964 1.2233
No log 30.6667 184 1.5144 0.2465 1.5144 1.2306
No log 31.0 186 1.3894 0.2704 1.3894 1.1787
No log 31.3333 188 1.1769 0.2238 1.1769 1.0849
No log 31.6667 190 1.0888 0.2056 1.0888 1.0435
No log 32.0 192 1.0941 0.2152 1.0941 1.0460
No log 32.3333 194 1.1389 0.2633 1.1389 1.0672
No log 32.6667 196 1.2644 0.2087 1.2644 1.1245
No log 33.0 198 1.4064 0.2789 1.4064 1.1859
No log 33.3333 200 1.4515 0.2455 1.4515 1.2048
No log 33.6667 202 1.3826 0.2789 1.3826 1.1758
No log 34.0 204 1.2567 0.2087 1.2567 1.1210
No log 34.3333 206 1.1424 0.2599 1.1424 1.0688
No log 34.6667 208 1.1448 0.2651 1.1448 1.0699
No log 35.0 210 1.1986 0.2570 1.1986 1.0948
No log 35.3333 212 1.2542 0.1789 1.2542 1.1199
No log 35.6667 214 1.3362 0.1840 1.3362 1.1560
No log 36.0 216 1.2928 0.1789 1.2928 1.1370
No log 36.3333 218 1.1958 0.25 1.1958 1.0935
No log 36.6667 220 1.1745 0.2108 1.1745 1.0837
No log 37.0 222 1.1725 0.1952 1.1725 1.0828
No log 37.3333 224 1.1691 0.1217 1.1691 1.0812
No log 37.6667 226 1.1689 0.1316 1.1689 1.0811
No log 38.0 228 1.1607 0.0904 1.1607 1.0773
No log 38.3333 230 1.1769 0.0904 1.1769 1.0848
No log 38.6667 232 1.2099 0.0811 1.2099 1.1000
No log 39.0 234 1.2010 0.1283 1.2010 1.0959
No log 39.3333 236 1.1743 0.1692 1.1743 1.0836
No log 39.6667 238 1.1518 0.2291 1.1518 1.0732
No log 40.0 240 1.1771 0.2097 1.1771 1.0850
No log 40.3333 242 1.1518 0.2330 1.1518 1.0732
No log 40.6667 244 1.1197 0.2330 1.1197 1.0582
No log 41.0 246 1.1295 0.2291 1.1295 1.0628
No log 41.3333 248 1.1528 0.2207 1.1528 1.0737
No log 41.6667 250 1.1549 0.1217 1.1549 1.0747
No log 42.0 252 1.1565 0.1952 1.1565 1.0754
No log 42.3333 254 1.1633 0.1538 1.1633 1.0785
No log 42.6667 256 1.1904 0.1316 1.1904 1.0910
No log 43.0 258 1.2111 0.0887 1.2111 1.1005
No log 43.3333 260 1.2105 0.0887 1.2105 1.1002
No log 43.6667 262 1.2010 0.0887 1.2010 1.0959
No log 44.0 264 1.2267 0.0887 1.2267 1.1076
No log 44.3333 266 1.2298 0.0789 1.2298 1.1089
No log 44.6667 268 1.2826 0.1789 1.2826 1.1325
No log 45.0 270 1.3060 0.1789 1.3060 1.1428
No log 45.3333 272 1.2986 0.1122 1.2986 1.1396
No log 45.6667 274 1.2663 0.0789 1.2663 1.1253
No log 46.0 276 1.3288 0.1122 1.3288 1.1527
No log 46.3333 278 1.3707 0.1692 1.3707 1.1708
No log 46.6667 280 1.3464 0.1122 1.3464 1.1603
No log 47.0 282 1.3160 0.0789 1.3160 1.1472
No log 47.3333 284 1.2239 0.0789 1.2239 1.1063
No log 47.6667 286 1.1705 0.1480 1.1705 1.0819
No log 48.0 288 1.1561 0.1480 1.1561 1.0752
No log 48.3333 290 1.1737 0.0442 1.1737 1.0834
No log 48.6667 292 1.2126 0.0541 1.2126 1.1012
No log 49.0 294 1.2362 0.0541 1.2362 1.1118
No log 49.3333 296 1.2054 0.0442 1.2054 1.0979
No log 49.6667 298 1.1715 0.1315 1.1715 1.0824
No log 50.0 300 1.1921 0.0789 1.1921 1.0918
No log 50.3333 302 1.2734 0.1031 1.2734 1.1285
No log 50.6667 304 1.3488 0.1889 1.3488 1.1614
No log 51.0 306 1.3809 0.1889 1.3809 1.1751
No log 51.3333 308 1.3479 0.1889 1.3479 1.1610
No log 51.6667 310 1.3324 0.1889 1.3324 1.1543
No log 52.0 312 1.2469 0.0937 1.2469 1.1166
No log 52.3333 314 1.2103 0.0937 1.2103 1.1001
No log 52.6667 316 1.2206 0.0937 1.2206 1.1048
No log 53.0 318 1.2541 0.1031 1.2541 1.1199
No log 53.3333 320 1.3285 0.1345 1.3285 1.1526
No log 53.6667 322 1.3868 0.1889 1.3868 1.1776
No log 54.0 324 1.4144 0.1889 1.4144 1.1893
No log 54.3333 326 1.4707 0.1796 1.4707 1.2127
No log 54.6667 328 1.4401 0.1935 1.4401 1.2000
No log 55.0 330 1.3374 0.1592 1.3374 1.1565
No log 55.3333 332 1.2739 0.1345 1.2739 1.1287
No log 55.6667 334 1.2088 0.1217 1.2088 1.0995
No log 56.0 336 1.1670 0.1217 1.1670 1.0803
No log 56.3333 338 1.1258 0.0802 1.1258 1.0611
No log 56.6667 340 1.1218 0.0802 1.1218 1.0592
No log 57.0 342 1.1432 0.0802 1.1432 1.0692
No log 57.3333 344 1.2005 0.0980 1.2005 1.0957
No log 57.6667 346 1.2796 0.0702 1.2796 1.1312
No log 58.0 348 1.3220 0.1592 1.3220 1.1498
No log 58.3333 350 1.3407 0.1889 1.3407 1.1579
No log 58.6667 352 1.3501 0.1935 1.3501 1.1619
No log 59.0 354 1.3056 0.1935 1.3056 1.1426
No log 59.3333 356 1.2396 0.1943 1.2396 1.1134
No log 59.6667 358 1.2093 0.1896 1.2093 1.0997
No log 60.0 360 1.1918 0.1345 1.1918 1.0917
No log 60.3333 362 1.1625 0.1538 1.1625 1.0782
No log 60.6667 364 1.1642 0.1538 1.1642 1.0790
No log 61.0 366 1.2020 0.1896 1.2020 1.0964
No log 61.3333 368 1.2246 0.1896 1.2246 1.1066
No log 61.6667 370 1.2733 0.1592 1.2733 1.1284
No log 62.0 372 1.3356 0.1889 1.3356 1.1557
No log 62.3333 374 1.3845 0.1461 1.3845 1.1767
No log 62.6667 376 1.4013 0.1461 1.4013 1.1838
No log 63.0 378 1.3896 0.1461 1.3896 1.1788
No log 63.3333 380 1.3491 0.1889 1.3491 1.1615
No log 63.6667 382 1.2885 0.1592 1.2885 1.1351
No log 64.0 384 1.2510 0.1031 1.2510 1.1185
No log 64.3333 386 1.2583 0.1498 1.2583 1.1217
No log 64.6667 388 1.2774 0.1592 1.2774 1.1302
No log 65.0 390 1.2763 0.1498 1.2763 1.1297
No log 65.3333 392 1.3029 0.1592 1.3029 1.1415
No log 65.6667 394 1.3497 0.1889 1.3497 1.1618
No log 66.0 396 1.3778 0.1889 1.3778 1.1738
No log 66.3333 398 1.3610 0.1889 1.3610 1.1666
No log 66.6667 400 1.3117 0.1789 1.3117 1.1453
No log 67.0 402 1.2785 0.1692 1.2785 1.1307
No log 67.3333 404 1.2791 0.1692 1.2791 1.1310
No log 67.6667 406 1.3046 0.1692 1.3046 1.1422
No log 68.0 408 1.2898 0.1692 1.2898 1.1357
No log 68.3333 410 1.2983 0.1692 1.2983 1.1394
No log 68.6667 412 1.3109 0.1692 1.3109 1.1450
No log 69.0 414 1.3630 0.2087 1.3630 1.1675
No log 69.3333 416 1.3929 0.2087 1.3929 1.1802
No log 69.6667 418 1.4257 0.1646 1.4257 1.1940
No log 70.0 420 1.4296 0.1646 1.4296 1.1957
No log 70.3333 422 1.4010 0.2087 1.4010 1.1836
No log 70.6667 424 1.3658 0.2087 1.3658 1.1687
No log 71.0 426 1.3113 0.1789 1.3113 1.1451
No log 71.3333 428 1.2703 0.1692 1.2703 1.1271
No log 71.6667 430 1.2608 0.1379 1.2608 1.1228
No log 72.0 432 1.2621 0.1789 1.2621 1.1234
No log 72.3333 434 1.2497 0.0887 1.2497 1.1179
No log 72.6667 436 1.2621 0.1789 1.2621 1.1235
No log 73.0 438 1.2963 0.1789 1.2963 1.1386
No log 73.3333 440 1.3492 0.2087 1.3492 1.1615
No log 73.6667 442 1.4232 0.2087 1.4232 1.1930
No log 74.0 444 1.4567 0.2373 1.4567 1.2070
No log 74.3333 446 1.4577 0.2373 1.4577 1.2074
No log 74.6667 448 1.4150 0.2087 1.4150 1.1895
No log 75.0 450 1.3679 0.2087 1.3679 1.1696
No log 75.3333 452 1.3202 0.1789 1.3202 1.1490
No log 75.6667 454 1.2749 0.1219 1.2749 1.1291
No log 76.0 456 1.2456 0.1219 1.2456 1.1161
No log 76.3333 458 1.2353 0.1637 1.2353 1.1115
No log 76.6667 460 1.2437 0.1219 1.2437 1.1152
No log 77.0 462 1.2635 0.1219 1.2635 1.1240
No log 77.3333 464 1.2840 0.1219 1.2840 1.1331
No log 77.6667 466 1.3117 0.1789 1.3117 1.1453
No log 78.0 468 1.3224 0.2087 1.3224 1.1499
No log 78.3333 470 1.3358 0.2087 1.3358 1.1558
No log 78.6667 472 1.3565 0.2087 1.3565 1.1647
No log 79.0 474 1.3816 0.2087 1.3816 1.1754
No log 79.3333 476 1.3827 0.2087 1.3827 1.1759
No log 79.6667 478 1.3593 0.2087 1.3593 1.1659
No log 80.0 480 1.3184 0.1789 1.3184 1.1482
No log 80.3333 482 1.2955 0.1219 1.2955 1.1382
No log 80.6667 484 1.2883 0.1219 1.2883 1.1350
No log 81.0 486 1.2792 0.1219 1.2792 1.1310
No log 81.3333 488 1.2832 0.1219 1.2832 1.1328
No log 81.6667 490 1.2856 0.1219 1.2856 1.1339
No log 82.0 492 1.2932 0.1219 1.2932 1.1372
No log 82.3333 494 1.3079 0.1789 1.3079 1.1437
No log 82.6667 496 1.3149 0.1789 1.3149 1.1467
No log 83.0 498 1.3219 0.1789 1.3219 1.1498
0.279 83.3333 500 1.3299 0.1789 1.3299 1.1532
0.279 83.6667 502 1.3248 0.1789 1.3248 1.1510
0.279 84.0 504 1.3063 0.1789 1.3063 1.1429
0.279 84.3333 506 1.2986 0.1789 1.2987 1.1396
0.279 84.6667 508 1.3022 0.1789 1.3022 1.1411
0.279 85.0 510 1.3158 0.1789 1.3158 1.1471

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_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k2_task2_organization

Finetuned
(4019)
this model