ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_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: 1.3560
  • Qwk: 0.0778
  • Mse: 1.3560
  • Rmse: 1.1645

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 4.7218 0.0010 4.7218 2.1730
No log 0.6667 4 2.9019 -0.0114 2.9019 1.7035
No log 1.0 6 1.8141 0.0504 1.8141 1.3469
No log 1.3333 8 1.5534 0.0372 1.5534 1.2464
No log 1.6667 10 1.4925 -0.0146 1.4925 1.2217
No log 2.0 12 1.6757 -0.0146 1.6757 1.2945
No log 2.3333 14 1.3467 0.0389 1.3467 1.1605
No log 2.6667 16 1.2110 0.1834 1.2110 1.1004
No log 3.0 18 1.2913 0.0124 1.2913 1.1364
No log 3.3333 20 1.5749 0.0 1.5749 1.2549
No log 3.6667 22 1.5655 0.0 1.5655 1.2512
No log 4.0 24 1.5306 0.0 1.5306 1.2372
No log 4.3333 26 1.3172 0.0926 1.3172 1.1477
No log 4.6667 28 1.2448 0.1448 1.2448 1.1157
No log 5.0 30 1.3277 0.1106 1.3277 1.1523
No log 5.3333 32 1.4212 0.0104 1.4212 1.1921
No log 5.6667 34 1.4120 0.0104 1.4120 1.1883
No log 6.0 36 1.5148 0.0104 1.5148 1.2308
No log 6.3333 38 1.4376 -0.0029 1.4376 1.1990
No log 6.6667 40 1.3179 0.1472 1.3179 1.1480
No log 7.0 42 1.2900 0.1507 1.2900 1.1358
No log 7.3333 44 1.2765 0.0324 1.2765 1.1298
No log 7.6667 46 1.3073 0.0420 1.3073 1.1434
No log 8.0 48 1.2847 0.0204 1.2847 1.1334
No log 8.3333 50 1.1768 0.1207 1.1768 1.0848
No log 8.6667 52 1.2251 0.2124 1.2251 1.1068
No log 9.0 54 1.2485 0.1556 1.2485 1.1174
No log 9.3333 56 1.2988 0.0063 1.2988 1.1397
No log 9.6667 58 1.4481 -0.0274 1.4481 1.2033
No log 10.0 60 1.3587 0.0277 1.3587 1.1656
No log 10.3333 62 1.0825 0.1482 1.0825 1.0405
No log 10.6667 64 1.0470 0.2304 1.0470 1.0232
No log 11.0 66 1.2715 0.1692 1.2715 1.1276
No log 11.3333 68 1.5986 0.1498 1.5986 1.2643
No log 11.6667 70 1.5609 0.1395 1.5609 1.2494
No log 12.0 72 1.3194 0.0513 1.3194 1.1486
No log 12.3333 74 1.0950 0.1605 1.0950 1.0464
No log 12.6667 76 1.1266 0.1246 1.1266 1.0614
No log 13.0 78 1.3004 0.0513 1.3004 1.1404
No log 13.3333 80 1.4477 0.0750 1.4477 1.2032
No log 13.6667 82 1.3618 0.0433 1.3618 1.1669
No log 14.0 84 1.3272 -0.0094 1.3272 1.1520
No log 14.3333 86 1.2258 0.1343 1.2258 1.1071
No log 14.6667 88 1.3413 -0.0188 1.3413 1.1582
No log 15.0 90 1.5198 -0.0314 1.5198 1.2328
No log 15.3333 92 1.4590 -0.0411 1.4590 1.2079
No log 15.6667 94 1.3263 0.0 1.3263 1.1517
No log 16.0 96 1.3367 0.0090 1.3367 1.1561
No log 16.3333 98 1.4522 0.0964 1.4522 1.2051
No log 16.6667 100 1.4357 0.0830 1.4357 1.1982
No log 17.0 102 1.3173 0.0256 1.3173 1.1477
No log 17.3333 104 1.3516 0.0164 1.3516 1.1626
No log 17.6667 106 1.4538 0.1796 1.4538 1.2058
No log 18.0 108 1.4617 0.1667 1.4617 1.2090
No log 18.3333 110 1.3305 0.0976 1.3305 1.1535
No log 18.6667 112 1.2298 0.1311 1.2298 1.1090
No log 19.0 114 1.2975 0.1067 1.2975 1.1391
No log 19.3333 116 1.4538 0.1228 1.4538 1.2058
No log 19.6667 118 1.4359 0.1842 1.4359 1.1983
No log 20.0 120 1.3217 0.0513 1.3217 1.1496
No log 20.3333 122 1.2974 0.0668 1.2974 1.1390
No log 20.6667 124 1.4099 0.0656 1.4099 1.1874
No log 21.0 126 1.4795 0.2485 1.4795 1.2163
No log 21.3333 128 1.3344 0.2239 1.3344 1.1552
No log 21.6667 130 1.2770 0.2278 1.2770 1.1300
No log 22.0 132 1.4496 0.1886 1.4496 1.2040
No log 22.3333 134 1.6576 0.2542 1.6576 1.2875
No log 22.6667 136 1.6305 0.1447 1.6305 1.2769
No log 23.0 138 1.4804 0.0186 1.4804 1.2167
No log 23.3333 140 1.2764 0.0612 1.2764 1.1298
No log 23.6667 142 1.2135 0.0700 1.2135 1.1016
No log 24.0 144 1.3143 0.1538 1.3143 1.1464
No log 24.3333 146 1.4232 0.1162 1.4232 1.1930
No log 24.6667 148 1.3813 0.1650 1.3813 1.1753
No log 25.0 150 1.2659 0.1596 1.2659 1.1251
No log 25.3333 152 1.2975 0.1650 1.2975 1.1391
No log 25.6667 154 1.5624 0.2172 1.5624 1.2500
No log 26.0 156 1.7655 0.1918 1.7655 1.3287
No log 26.3333 158 1.7333 0.2407 1.7333 1.3166
No log 26.6667 160 1.5026 0.2065 1.5026 1.2258
No log 27.0 162 1.2504 0.0692 1.2504 1.1182
No log 27.3333 164 1.2160 0.0513 1.2160 1.1027
No log 27.6667 166 1.2766 0.0442 1.2766 1.1299
No log 28.0 168 1.3583 0.0444 1.3583 1.1655
No log 28.3333 170 1.2843 0.1840 1.2843 1.1333
No log 28.6667 172 1.1723 0.1282 1.1723 1.0827
No log 29.0 174 1.1929 0.2152 1.1929 1.0922
No log 29.3333 176 1.3421 0.2479 1.3421 1.1585
No log 29.6667 178 1.5589 0.2188 1.5589 1.2486
No log 30.0 180 1.7018 0.2222 1.7018 1.3045
No log 30.3333 182 1.6565 0.2188 1.6565 1.2870
No log 30.6667 184 1.5156 0.2181 1.5156 1.2311
No log 31.0 186 1.3381 0.0865 1.3381 1.1568
No log 31.3333 188 1.2763 0.1026 1.2763 1.1297
No log 31.6667 190 1.3261 0.0526 1.3261 1.1516
No log 32.0 192 1.4378 0.0444 1.4378 1.1991
No log 32.3333 194 1.4726 0.0444 1.4726 1.2135
No log 32.6667 196 1.4246 0.0623 1.4246 1.1936
No log 33.0 198 1.3702 0.0961 1.3702 1.1706
No log 33.3333 200 1.2885 0.0961 1.2885 1.1351
No log 33.6667 202 1.2852 0.0961 1.2852 1.1337
No log 34.0 204 1.3518 0.1536 1.3518 1.1627
No log 34.3333 206 1.4399 0.2285 1.4399 1.1999
No log 34.6667 208 1.4805 0.2285 1.4805 1.2167
No log 35.0 210 1.4016 0.2542 1.4016 1.1839
No log 35.3333 212 1.3369 0.2251 1.3369 1.1562
No log 35.6667 214 1.3982 0.2485 1.3982 1.1824
No log 36.0 216 1.3850 0.2485 1.3850 1.1769
No log 36.3333 218 1.2722 0.1283 1.2722 1.1279
No log 36.6667 220 1.1846 0.1188 1.1846 1.0884
No log 37.0 222 1.1530 0.1090 1.1530 1.0738
No log 37.3333 224 1.1797 0.0907 1.1797 1.0862
No log 37.6667 226 1.3106 0.0678 1.3106 1.1448
No log 38.0 228 1.3890 0.1796 1.3890 1.1786
No log 38.3333 230 1.3801 0.1796 1.3801 1.1748
No log 38.6667 232 1.2710 0.0678 1.2710 1.1274
No log 39.0 234 1.1887 0.0769 1.1887 1.0903
No log 39.3333 236 1.1807 0.0702 1.1807 1.0866
No log 39.6667 238 1.2135 0.0778 1.2135 1.1016
No log 40.0 240 1.3345 0.2252 1.3345 1.1552
No log 40.3333 242 1.3704 0.2359 1.3704 1.1706
No log 40.6667 244 1.3171 0.2544 1.3171 1.1476
No log 41.0 246 1.2573 0.1224 1.2573 1.1213
No log 41.3333 248 1.2146 0.1462 1.2146 1.1021
No log 41.6667 250 1.1977 0.1611 1.1977 1.0944
No log 42.0 252 1.1986 0.1611 1.1986 1.0948
No log 42.3333 254 1.2308 0.1554 1.2308 1.1094
No log 42.6667 256 1.2572 0.1498 1.2572 1.1213
No log 43.0 258 1.3240 0.1698 1.3240 1.1506
No log 43.3333 260 1.3006 0.1592 1.3006 1.1404
No log 43.6667 262 1.2062 0.1440 1.2062 1.0983
No log 44.0 264 1.1931 0.1440 1.1931 1.0923
No log 44.3333 266 1.2700 0.1554 1.2700 1.1270
No log 44.6667 268 1.4352 0.2604 1.4352 1.1980
No log 45.0 270 1.5211 0.2735 1.5211 1.2333
No log 45.3333 272 1.5595 0.2514 1.5595 1.2488
No log 45.6667 274 1.5545 0.1547 1.5545 1.2468
No log 46.0 276 1.5367 0.1547 1.5367 1.2396
No log 46.3333 278 1.5755 0.1228 1.5755 1.2552
No log 46.6667 280 1.4917 0.0020 1.4917 1.2213
No log 47.0 282 1.4090 0.0444 1.4090 1.1870
No log 47.3333 284 1.3743 0.0359 1.3743 1.1723
No log 47.6667 286 1.4140 0.0444 1.4140 1.1891
No log 48.0 288 1.4431 0.1646 1.4431 1.2013
No log 48.3333 290 1.4195 0.1646 1.4195 1.1914
No log 48.6667 292 1.3550 0.1098 1.3550 1.1640
No log 49.0 294 1.3437 0.1098 1.3437 1.1592
No log 49.3333 296 1.3440 0.1608 1.3440 1.1593
No log 49.6667 298 1.4059 0.2359 1.4059 1.1857
No log 50.0 300 1.4450 0.2047 1.4450 1.2021
No log 50.3333 302 1.4806 0.2047 1.4806 1.2168
No log 50.6667 304 1.4492 0.2325 1.4492 1.2038
No log 51.0 306 1.3568 0.1935 1.3568 1.1648
No log 51.3333 308 1.2421 0.1094 1.2421 1.1145
No log 51.6667 310 1.1955 0.0835 1.1955 1.0934
No log 52.0 312 1.2037 0.0675 1.2037 1.0971
No log 52.3333 314 1.2548 0.1094 1.2548 1.1202
No log 52.6667 316 1.3438 0.1098 1.3438 1.1592
No log 53.0 318 1.4578 0.1929 1.4578 1.2074
No log 53.3333 320 1.4977 0.2084 1.4977 1.2238
No log 53.6667 322 1.4283 0.2105 1.4283 1.1951
No log 54.0 324 1.3282 0.2479 1.3282 1.1525
No log 54.3333 326 1.2962 0.2213 1.2962 1.1385
No log 54.6667 328 1.2886 0.1935 1.2886 1.1352
No log 55.0 330 1.2768 0.1098 1.2768 1.1300
No log 55.3333 332 1.2893 0.0778 1.2893 1.1355
No log 55.6667 334 1.3142 0.0778 1.3142 1.1464
No log 56.0 336 1.3191 0.0778 1.3191 1.1485
No log 56.3333 338 1.2727 0.0778 1.2727 1.1282
No log 56.6667 340 1.2344 0.0702 1.2344 1.1110
No log 57.0 342 1.2187 0.0778 1.2187 1.1040
No log 57.3333 344 1.2427 0.1098 1.2427 1.1147
No log 57.6667 346 1.3033 0.2213 1.3033 1.1416
No log 58.0 348 1.3496 0.2213 1.3496 1.1617
No log 58.3333 350 1.3611 0.2479 1.3611 1.1667
No log 58.6667 352 1.3353 0.2213 1.3353 1.1555
No log 59.0 354 1.2590 0.1098 1.2590 1.1221
No log 59.3333 356 1.2091 0.0702 1.2091 1.0996
No log 59.6667 358 1.2027 0.0702 1.2027 1.0967
No log 60.0 360 1.2025 0.0789 1.2025 1.0966
No log 60.3333 362 1.2020 0.0887 1.2020 1.0964
No log 60.6667 364 1.2289 0.1031 1.2289 1.1086
No log 61.0 366 1.3022 0.1698 1.3022 1.1411
No log 61.3333 368 1.3629 0.1796 1.3629 1.1675
No log 61.6667 370 1.4305 0.1758 1.4305 1.1960
No log 62.0 372 1.4555 0.2251 1.4555 1.2064
No log 62.3333 374 1.4301 0.1171 1.4301 1.1959
No log 62.6667 376 1.3535 0.0778 1.3535 1.1634
No log 63.0 378 1.2672 0.0359 1.2672 1.1257
No log 63.3333 380 1.2420 0.0359 1.2420 1.1144
No log 63.6667 382 1.2303 0.0270 1.2303 1.1092
No log 64.0 384 1.2439 0.0359 1.2439 1.1153
No log 64.3333 386 1.2946 0.0359 1.2946 1.1378
No log 64.6667 388 1.3344 0.0020 1.3344 1.1552
No log 65.0 390 1.3526 0.0020 1.3526 1.1630
No log 65.3333 392 1.3974 0.0920 1.3974 1.1821
No log 65.6667 394 1.4542 0.1340 1.4542 1.2059
No log 66.0 396 1.4525 0.1395 1.4525 1.2052
No log 66.3333 398 1.4024 0.1224 1.4024 1.1842
No log 66.6667 400 1.3244 0.1098 1.3244 1.1508
No log 67.0 402 1.2771 0.0887 1.2771 1.1301
No log 67.3333 404 1.2720 0.0887 1.2720 1.1278
No log 67.6667 406 1.3011 0.0961 1.3011 1.1407
No log 68.0 408 1.3218 0.0961 1.3218 1.1497
No log 68.3333 410 1.3469 0.0961 1.3469 1.1605
No log 68.6667 412 1.3474 0.0623 1.3474 1.1608
No log 69.0 414 1.3402 0.0444 1.3402 1.1577
No log 69.3333 416 1.3172 0.0541 1.3172 1.1477
No log 69.6667 418 1.3090 0.0541 1.3090 1.1441
No log 70.0 420 1.3134 0.0359 1.3134 1.1460
No log 70.3333 422 1.3119 0.0359 1.3119 1.1454
No log 70.6667 424 1.3153 0.0444 1.3153 1.1469
No log 71.0 426 1.2807 0.0359 1.2807 1.1317
No log 71.3333 428 1.2446 0.0541 1.2446 1.1156
No log 71.6667 430 1.2403 0.0541 1.2403 1.1137
No log 72.0 432 1.2443 0.0541 1.2443 1.1155
No log 72.3333 434 1.2212 0.0541 1.2212 1.1051
No log 72.6667 436 1.2268 0.0541 1.2268 1.1076
No log 73.0 438 1.2520 0.0541 1.2520 1.1189
No log 73.3333 440 1.2978 0.0778 1.2978 1.1392
No log 73.6667 442 1.3418 0.1345 1.3418 1.1584
No log 74.0 444 1.3405 0.1345 1.3405 1.1578
No log 74.3333 446 1.3151 0.1345 1.3151 1.1468
No log 74.6667 448 1.2751 0.1345 1.2751 1.1292
No log 75.0 450 1.2577 0.0778 1.2577 1.1215
No log 75.3333 452 1.2432 0.0444 1.2432 1.1150
No log 75.6667 454 1.2156 0.0541 1.2156 1.1026
No log 76.0 456 1.2061 0.0541 1.2061 1.0982
No log 76.3333 458 1.2080 0.0541 1.2080 1.0991
No log 76.6667 460 1.2116 0.0541 1.2116 1.1007
No log 77.0 462 1.2217 0.0541 1.2217 1.1053
No log 77.3333 464 1.2269 0.0359 1.2269 1.1076
No log 77.6667 466 1.2496 0.0444 1.2496 1.1179
No log 78.0 468 1.2606 0.0444 1.2606 1.1228
No log 78.3333 470 1.2720 0.0778 1.2720 1.1278
No log 78.6667 472 1.2987 0.1646 1.2987 1.1396
No log 79.0 474 1.3268 0.1935 1.3268 1.1519
No log 79.3333 476 1.3296 0.1980 1.3296 1.1531
No log 79.6667 478 1.3103 0.1935 1.3103 1.1447
No log 80.0 480 1.2769 0.1646 1.2769 1.1300
No log 80.3333 482 1.2563 0.1283 1.2563 1.1209
No log 80.6667 484 1.2471 0.1219 1.2471 1.1167
No log 81.0 486 1.2598 0.1219 1.2598 1.1224
No log 81.3333 488 1.2886 0.1219 1.2886 1.1352
No log 81.6667 490 1.3112 0.0702 1.3112 1.1451
No log 82.0 492 1.3224 0.0702 1.3224 1.1500
No log 82.3333 494 1.3385 0.0702 1.3385 1.1569
No log 82.6667 496 1.3449 0.0702 1.3449 1.1597
No log 83.0 498 1.3555 0.0702 1.3555 1.1643
0.2542 83.3333 500 1.3671 0.0778 1.3671 1.1692
0.2542 83.6667 502 1.3694 0.0778 1.3694 1.1702
0.2542 84.0 504 1.3529 0.0444 1.3529 1.1631
0.2542 84.3333 506 1.3473 0.0444 1.3473 1.1607
0.2542 84.6667 508 1.3510 0.0444 1.3510 1.1623
0.2542 85.0 510 1.3560 0.0778 1.3560 1.1645

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_run1_AugV5_k2_task2_organization

Finetuned
(4019)
this model