ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k5_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: 1.3255
  • Qwk: 0.2084
  • Mse: 1.3255
  • Rmse: 1.1513

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 0.08 2 4.7427 0.0010 4.7427 2.1778
No log 0.16 4 2.6938 0.0239 2.6938 1.6413
No log 0.24 6 2.1795 -0.0045 2.1795 1.4763
No log 0.32 8 1.8529 -0.0102 1.8529 1.3612
No log 0.4 10 1.5452 0.0028 1.5452 1.2431
No log 0.48 12 1.5139 -0.0623 1.5139 1.2304
No log 0.56 14 1.6597 -0.1074 1.6597 1.2883
No log 0.64 16 1.9003 -0.0830 1.9003 1.3785
No log 0.72 18 1.8270 -0.1129 1.8270 1.3517
No log 0.8 20 1.6615 -0.0267 1.6615 1.2890
No log 0.88 22 1.5042 -0.0521 1.5042 1.2264
No log 0.96 24 1.4348 -0.1073 1.4348 1.1978
No log 1.04 26 1.2963 0.1711 1.2963 1.1385
No log 1.12 28 1.2723 0.1242 1.2723 1.1279
No log 1.2 30 1.3234 0.1076 1.3234 1.1504
No log 1.28 32 1.3877 0.0642 1.3877 1.1780
No log 1.3600 34 1.3729 0.0711 1.3729 1.1717
No log 1.44 36 1.2748 0.1546 1.2748 1.1291
No log 1.52 38 1.2301 0.2142 1.2301 1.1091
No log 1.6 40 1.2851 0.0613 1.2851 1.1336
No log 1.6800 42 1.3123 0.0741 1.3123 1.1456
No log 1.76 44 1.2298 0.2323 1.2298 1.1090
No log 1.8400 46 1.2298 0.0671 1.2298 1.1090
No log 1.92 48 1.2098 0.0872 1.2098 1.0999
No log 2.0 50 1.1707 0.1585 1.1707 1.0820
No log 2.08 52 1.1815 0.2689 1.1815 1.0870
No log 2.16 54 1.1867 0.2492 1.1867 1.0894
No log 2.24 56 1.2247 0.1538 1.2247 1.1067
No log 2.32 58 1.2812 0.2075 1.2812 1.1319
No log 2.4 60 1.3026 0.2348 1.3026 1.1413
No log 2.48 62 1.2872 0.1709 1.2872 1.1346
No log 2.56 64 1.5698 0.1977 1.5698 1.2529
No log 2.64 66 1.7537 0.1305 1.7537 1.3243
No log 2.7200 68 1.5323 0.1857 1.5323 1.2379
No log 2.8 70 1.4104 0.2037 1.4104 1.1876
No log 2.88 72 1.5126 0.2498 1.5126 1.2299
No log 2.96 74 1.4200 0.2833 1.4200 1.1917
No log 3.04 76 1.2252 0.2638 1.2252 1.1069
No log 3.12 78 1.1305 0.3525 1.1305 1.0632
No log 3.2 80 1.1297 0.3637 1.1297 1.0629
No log 3.2800 82 1.0894 0.3787 1.0894 1.0437
No log 3.36 84 1.2609 0.3303 1.2609 1.1229
No log 3.44 86 1.3287 0.3424 1.3287 1.1527
No log 3.52 88 1.2101 0.3000 1.2101 1.1000
No log 3.6 90 1.1808 0.3621 1.1808 1.0866
No log 3.68 92 1.2395 0.3232 1.2395 1.1133
No log 3.76 94 1.3767 0.2863 1.3767 1.1733
No log 3.84 96 1.2926 0.3023 1.2926 1.1369
No log 3.92 98 1.2070 0.3505 1.2070 1.0987
No log 4.0 100 1.1413 0.2811 1.1413 1.0683
No log 4.08 102 1.0918 0.3181 1.0918 1.0449
No log 4.16 104 1.1196 0.3584 1.1196 1.0581
No log 4.24 106 1.3064 0.2822 1.3064 1.1430
No log 4.32 108 1.2470 0.4298 1.2470 1.1167
No log 4.4 110 1.0622 0.4318 1.0622 1.0306
No log 4.48 112 1.0685 0.4881 1.0685 1.0337
No log 4.5600 114 1.2291 0.4432 1.2291 1.1086
No log 4.64 116 1.3134 0.3681 1.3134 1.1460
No log 4.72 118 1.2918 0.4138 1.2918 1.1366
No log 4.8 120 1.2961 0.3759 1.2961 1.1385
No log 4.88 122 1.3820 0.3459 1.3820 1.1756
No log 4.96 124 1.1428 0.3696 1.1428 1.0690
No log 5.04 126 1.1215 0.3991 1.1215 1.0590
No log 5.12 128 1.1182 0.4316 1.1182 1.0575
No log 5.2 130 1.1938 0.4083 1.1938 1.0926
No log 5.28 132 1.2152 0.3765 1.2152 1.1024
No log 5.36 134 1.3377 0.3817 1.3377 1.1566
No log 5.44 136 1.5047 0.3286 1.5047 1.2267
No log 5.52 138 1.3588 0.3580 1.3588 1.1657
No log 5.6 140 1.2717 0.2733 1.2717 1.1277
No log 5.68 142 1.1113 0.3062 1.1113 1.0542
No log 5.76 144 1.0991 0.3040 1.0991 1.0484
No log 5.84 146 1.2325 0.2679 1.2325 1.1102
No log 5.92 148 1.4909 0.3258 1.4909 1.2210
No log 6.0 150 1.5451 0.3127 1.5451 1.2430
No log 6.08 152 1.2331 0.3722 1.2331 1.1104
No log 6.16 154 1.0909 0.3289 1.0909 1.0445
No log 6.24 156 1.0803 0.3476 1.0803 1.0394
No log 6.32 158 1.1023 0.3385 1.1023 1.0499
No log 6.4 160 1.3347 0.3137 1.3347 1.1553
No log 6.48 162 1.3131 0.2885 1.3131 1.1459
No log 6.5600 164 1.0693 0.3139 1.0693 1.0341
No log 6.64 166 1.0307 0.2633 1.0307 1.0153
No log 6.72 168 1.0210 0.3223 1.0210 1.0104
No log 6.8 170 1.1934 0.2870 1.1934 1.0924
No log 6.88 172 1.3203 0.2944 1.3203 1.1491
No log 6.96 174 1.2406 0.3287 1.2406 1.1138
No log 7.04 176 1.1463 0.2011 1.1463 1.0707
No log 7.12 178 1.1204 0.2438 1.1204 1.0585
No log 7.2 180 1.2045 0.2235 1.2045 1.0975
No log 7.28 182 1.3718 0.2354 1.3718 1.1712
No log 7.36 184 1.4235 0.2620 1.4235 1.1931
No log 7.44 186 1.2542 0.3370 1.2542 1.1199
No log 7.52 188 1.0508 0.3561 1.0508 1.0251
No log 7.6 190 1.0303 0.3796 1.0303 1.0151
No log 7.68 192 1.0853 0.3214 1.0853 1.0418
No log 7.76 194 1.3214 0.3641 1.3214 1.1495
No log 7.84 196 1.3569 0.3893 1.3569 1.1649
No log 7.92 198 1.2598 0.2417 1.2598 1.1224
No log 8.0 200 1.1184 0.1371 1.1184 1.0575
No log 8.08 202 1.0994 0.1935 1.0994 1.0485
No log 8.16 204 1.1368 0.1466 1.1368 1.0662
No log 8.24 206 1.1695 0.2481 1.1695 1.0814
No log 8.32 208 1.1555 0.2764 1.1555 1.0749
No log 8.4 210 1.2843 0.1520 1.2843 1.1332
No log 8.48 212 1.4242 0.2370 1.4242 1.1934
No log 8.56 214 1.4681 0.2911 1.4681 1.2117
No log 8.64 216 1.3974 0.2387 1.3974 1.1821
No log 8.72 218 1.2640 0.2184 1.2640 1.1243
No log 8.8 220 1.2087 0.2050 1.2087 1.0994
No log 8.88 222 1.2098 0.1958 1.2098 1.0999
No log 8.96 224 1.1964 0.2270 1.1964 1.0938
No log 9.04 226 1.2897 0.2638 1.2897 1.1357
No log 9.12 228 1.2682 0.2456 1.2682 1.1261
No log 9.2 230 1.2832 0.2246 1.2832 1.1328
No log 9.28 232 1.1875 0.2195 1.1875 1.0897
No log 9.36 234 1.2433 0.2096 1.2433 1.1150
No log 9.44 236 1.3719 0.2418 1.3719 1.1713
No log 9.52 238 1.4040 0.2595 1.4040 1.1849
No log 9.6 240 1.2705 0.2049 1.2705 1.1272
No log 9.68 242 1.1489 0.2389 1.1489 1.0719
No log 9.76 244 1.1258 0.3136 1.1258 1.0610
No log 9.84 246 1.2592 0.2306 1.2592 1.1221
No log 9.92 248 1.2738 0.2406 1.2738 1.1286
No log 10.0 250 1.2635 0.2406 1.2635 1.1241
No log 10.08 252 1.2715 0.2406 1.2715 1.1276
No log 10.16 254 1.2079 0.2491 1.2079 1.0990
No log 10.24 256 1.2463 0.2306 1.2463 1.1164
No log 10.32 258 1.4428 0.2713 1.4428 1.2012
No log 10.4 260 1.6134 0.2074 1.6134 1.2702
No log 10.48 262 1.6575 0.2527 1.6575 1.2874
No log 10.56 264 1.5298 0.2847 1.5298 1.2369
No log 10.64 266 1.3687 0.2147 1.3687 1.1699
No log 10.72 268 1.1570 0.2671 1.1570 1.0756
No log 10.8 270 1.1574 0.2929 1.1574 1.0758
No log 10.88 272 1.1259 0.2811 1.1259 1.0611
No log 10.96 274 1.1023 0.3377 1.1023 1.0499
No log 11.04 276 1.1584 0.3568 1.1584 1.0763
No log 11.12 278 1.1009 0.3612 1.1009 1.0492
No log 11.2 280 1.1340 0.3237 1.1340 1.0649
No log 11.28 282 1.2806 0.2799 1.2806 1.1316
No log 11.36 284 1.2948 0.2029 1.2948 1.1379
No log 11.44 286 1.3927 0.2205 1.3927 1.1801
No log 11.52 288 1.2906 0.1671 1.2906 1.1360
No log 11.6 290 1.2385 0.1769 1.2385 1.1129
No log 11.68 292 1.2695 0.1731 1.2695 1.1267
No log 11.76 294 1.3532 0.1536 1.3532 1.1633
No log 11.84 296 1.3903 0.1615 1.3903 1.1791
No log 11.92 298 1.3756 0.1080 1.3756 1.1729
No log 12.0 300 1.2955 0.1310 1.2955 1.1382
No log 12.08 302 1.2147 0.0983 1.2147 1.1021
No log 12.16 304 1.2058 0.1309 1.2058 1.0981
No log 12.24 306 1.2411 0.1621 1.2411 1.1141
No log 12.32 308 1.3107 0.1678 1.3107 1.1449
No log 12.4 310 1.3227 0.2281 1.3227 1.1501
No log 12.48 312 1.4577 0.2576 1.4577 1.2073
No log 12.56 314 1.5007 0.2741 1.5007 1.2250
No log 12.64 316 1.3736 0.2321 1.3736 1.1720
No log 12.72 318 1.1946 0.2563 1.1946 1.0930
No log 12.8 320 1.1834 0.2297 1.1834 1.0878
No log 12.88 322 1.3171 0.2758 1.3171 1.1477
No log 12.96 324 1.3591 0.2635 1.3591 1.1658
No log 13.04 326 1.2905 0.2583 1.2905 1.1360
No log 13.12 328 1.3366 0.2236 1.3366 1.1561
No log 13.2 330 1.3992 0.2181 1.3992 1.1829
No log 13.28 332 1.4015 0.2145 1.4015 1.1839
No log 13.36 334 1.3484 0.2463 1.3484 1.1612
No log 13.44 336 1.2986 0.2424 1.2986 1.1395
No log 13.52 338 1.2298 0.2757 1.2298 1.1090
No log 13.6 340 1.2489 0.2404 1.2489 1.1176
No log 13.68 342 1.3772 0.2067 1.3772 1.1735
No log 13.76 344 1.5557 0.3025 1.5557 1.2473
No log 13.84 346 1.5890 0.2446 1.5890 1.2605
No log 13.92 348 1.5509 0.2527 1.5509 1.2453
No log 14.0 350 1.3820 0.2110 1.3820 1.1756
No log 14.08 352 1.2395 0.1581 1.2395 1.1133
No log 14.16 354 1.1985 0.1467 1.1985 1.0948
No log 14.24 356 1.2051 0.0818 1.2051 1.0978
No log 14.32 358 1.2607 0.1246 1.2607 1.1228
No log 14.4 360 1.3220 0.1641 1.3220 1.1498
No log 14.48 362 1.3333 0.1559 1.3333 1.1547
No log 14.56 364 1.2433 0.1121 1.2433 1.1150
No log 14.64 366 1.1831 0.2574 1.1831 1.0877
No log 14.72 368 1.1775 0.2574 1.1775 1.0851
No log 14.8 370 1.2157 0.2640 1.2157 1.1026
No log 14.88 372 1.2500 0.2953 1.2500 1.1180
No log 14.96 374 1.2634 0.2819 1.2634 1.1240
No log 15.04 376 1.2633 0.2458 1.2633 1.1240
No log 15.12 378 1.2285 0.2595 1.2285 1.1084
No log 15.2 380 1.2218 0.2737 1.2218 1.1054
No log 15.28 382 1.2280 0.2729 1.2280 1.1082
No log 15.36 384 1.2902 0.2609 1.2902 1.1359
No log 15.44 386 1.2765 0.2800 1.2765 1.1298
No log 15.52 388 1.2139 0.3427 1.2139 1.1018
No log 15.6 390 1.2042 0.2830 1.2042 1.0974
No log 15.68 392 1.2016 0.2850 1.2016 1.0962
No log 15.76 394 1.2043 0.2947 1.2043 1.0974
No log 15.84 396 1.1728 0.3117 1.1728 1.0830
No log 15.92 398 1.1525 0.2336 1.1525 1.0735
No log 16.0 400 1.1492 0.2773 1.1492 1.0720
No log 16.08 402 1.2489 0.2477 1.2489 1.1175
No log 16.16 404 1.3834 0.3042 1.3834 1.1762
No log 16.24 406 1.5688 0.2921 1.5688 1.2525
No log 16.32 408 1.6246 0.2667 1.6246 1.2746
No log 16.4 410 1.5021 0.2820 1.5021 1.2256
No log 16.48 412 1.3435 0.2270 1.3435 1.1591
No log 16.56 414 1.3073 0.1818 1.3073 1.1434
No log 16.64 416 1.3102 0.1429 1.3102 1.1446
No log 16.72 418 1.3419 0.0592 1.3419 1.1584
No log 16.8 420 1.3556 0.0607 1.3556 1.1643
No log 16.88 422 1.3479 0.0981 1.3479 1.1610
No log 16.96 424 1.2821 0.1338 1.2821 1.1323
No log 17.04 426 1.2759 0.1965 1.2759 1.1296
No log 17.12 428 1.2522 0.2297 1.2522 1.1190
No log 17.2 430 1.2134 0.2176 1.2134 1.1016
No log 17.28 432 1.1983 0.1727 1.1983 1.0947
No log 17.36 434 1.2083 0.1878 1.2083 1.0992
No log 17.44 436 1.2583 0.1776 1.2583 1.1218
No log 17.52 438 1.2835 0.2033 1.2835 1.1329
No log 17.6 440 1.3047 0.2117 1.3047 1.1422
No log 17.68 442 1.2642 0.1450 1.2642 1.1244
No log 17.76 444 1.2256 0.1771 1.2256 1.1071
No log 17.84 446 1.1710 0.2496 1.1710 1.0821
No log 17.92 448 1.1355 0.3139 1.1355 1.0656
No log 18.0 450 1.1413 0.3019 1.1413 1.0683
No log 18.08 452 1.1755 0.2389 1.1755 1.0842
No log 18.16 454 1.1489 0.2995 1.1489 1.0719
No log 18.24 456 1.1338 0.2723 1.1338 1.0648
No log 18.32 458 1.1409 0.2723 1.1409 1.0681
No log 18.4 460 1.1166 0.2993 1.1166 1.0567
No log 18.48 462 1.1523 0.2165 1.1523 1.0735
No log 18.56 464 1.1883 0.2045 1.1883 1.0901
No log 18.64 466 1.2262 0.2411 1.2262 1.1073
No log 18.72 468 1.2619 0.2703 1.2619 1.1234
No log 18.8 470 1.2343 0.2650 1.2343 1.1110
No log 18.88 472 1.2606 0.2518 1.2606 1.1227
No log 18.96 474 1.2342 0.2195 1.2342 1.1109
No log 19.04 476 1.0993 0.1343 1.0993 1.0485
No log 19.12 478 1.0200 0.3095 1.0200 1.0099
No log 19.2 480 1.0051 0.3510 1.0051 1.0026
No log 19.28 482 1.0241 0.3095 1.0241 1.0120
No log 19.36 484 1.1037 0.1505 1.1037 1.0506
No log 19.44 486 1.2438 0.2275 1.2438 1.1153
No log 19.52 488 1.3437 0.2747 1.3437 1.1592
No log 19.6 490 1.3226 0.2885 1.3226 1.1500
No log 19.68 492 1.1849 0.2739 1.1849 1.0885
No log 19.76 494 1.0952 0.3924 1.0952 1.0465
No log 19.84 496 1.1029 0.3715 1.1029 1.0502
No log 19.92 498 1.1314 0.3674 1.1314 1.0637
0.3066 20.0 500 1.2029 0.2352 1.2029 1.0968
0.3066 20.08 502 1.2604 0.1658 1.2604 1.1227
0.3066 20.16 504 1.2602 0.2015 1.2602 1.1226
0.3066 20.24 506 1.1991 0.2176 1.1991 1.0950
0.3066 20.32 508 1.1687 0.2625 1.1687 1.0811
0.3066 20.4 510 1.1543 0.2991 1.1543 1.0744
0.3066 20.48 512 1.1577 0.3256 1.1577 1.0760
0.3066 20.56 514 1.2051 0.2016 1.2051 1.0978
0.3066 20.64 516 1.2911 0.1778 1.2911 1.1363
0.3066 20.72 518 1.3663 0.1855 1.3663 1.1689
0.3066 20.8 520 1.3917 0.2295 1.3917 1.1797
0.3066 20.88 522 1.3255 0.2084 1.3255 1.1513

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_B_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k5_task2_organization

Finetuned
(4019)
this model