ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k6_task5_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: 1.3859
  • Qwk: 0.1744
  • Mse: 1.3859
  • Rmse: 1.1772

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 4.0648 0.0070 4.0648 2.0161
No log 0.2667 4 2.1943 0.1047 2.1943 1.4813
No log 0.4 6 1.4606 0.0143 1.4606 1.2086
No log 0.5333 8 1.2335 -0.0032 1.2335 1.1106
No log 0.6667 10 1.1203 0.1304 1.1203 1.0584
No log 0.8 12 1.1447 0.1944 1.1447 1.0699
No log 0.9333 14 1.1465 0.0761 1.1465 1.0707
No log 1.0667 16 1.1281 0.1062 1.1281 1.0621
No log 1.2 18 1.1256 0.2145 1.1256 1.0610
No log 1.3333 20 1.0531 0.2015 1.0531 1.0262
No log 1.4667 22 1.1027 0.1292 1.1027 1.0501
No log 1.6 24 1.0525 0.1629 1.0525 1.0259
No log 1.7333 26 1.0091 0.1908 1.0091 1.0046
No log 1.8667 28 1.2192 0.0950 1.2192 1.1042
No log 2.0 30 1.5284 -0.0305 1.5284 1.2363
No log 2.1333 32 1.4065 0.0102 1.4065 1.1860
No log 2.2667 34 1.0920 0.0917 1.0920 1.0450
No log 2.4 36 1.2433 0.1199 1.2433 1.1150
No log 2.5333 38 1.6740 -0.0939 1.6740 1.2938
No log 2.6667 40 1.7687 -0.1658 1.7687 1.3299
No log 2.8 42 1.5873 -0.0749 1.5873 1.2599
No log 2.9333 44 1.5556 -0.1285 1.5556 1.2472
No log 3.0667 46 1.3672 0.1702 1.3672 1.1693
No log 3.2 48 1.2001 0.2632 1.2001 1.0955
No log 3.3333 50 1.3977 0.0818 1.3977 1.1822
No log 3.4667 52 1.5670 -0.0756 1.5670 1.2518
No log 3.6 54 1.4665 0.1452 1.4665 1.2110
No log 3.7333 56 1.2472 0.2773 1.2472 1.1168
No log 3.8667 58 1.1001 0.1170 1.1001 1.0489
No log 4.0 60 1.0654 0.0886 1.0654 1.0322
No log 4.1333 62 1.1325 0.1233 1.1325 1.0642
No log 4.2667 64 1.3356 0.2728 1.3356 1.1557
No log 4.4 66 1.5044 0.2313 1.5044 1.2265
No log 4.5333 68 1.6029 0.1935 1.6029 1.2660
No log 4.6667 70 1.7481 0.0275 1.7481 1.3222
No log 4.8 72 1.6289 0.1242 1.6289 1.2763
No log 4.9333 74 1.6525 0.0876 1.6525 1.2855
No log 5.0667 76 1.8225 0.0359 1.8225 1.3500
No log 5.2 78 1.7750 0.0542 1.7750 1.3323
No log 5.3333 80 1.4799 0.2194 1.4799 1.2165
No log 5.4667 82 1.4945 0.2311 1.4945 1.2225
No log 5.6 84 1.8306 -0.0145 1.8306 1.3530
No log 5.7333 86 1.8319 -0.0653 1.8319 1.3535
No log 5.8667 88 1.4183 0.1054 1.4183 1.1909
No log 6.0 90 1.1326 0.2864 1.1326 1.0643
No log 6.1333 92 1.0949 0.2512 1.0949 1.0464
No log 6.2667 94 1.2939 0.1649 1.2939 1.1375
No log 6.4 96 1.5198 -0.0052 1.5198 1.2328
No log 6.5333 98 1.4648 -0.0171 1.4648 1.2103
No log 6.6667 100 1.2772 0.1649 1.2772 1.1301
No log 6.8 102 1.1925 0.2636 1.1925 1.0920
No log 6.9333 104 1.2840 0.1868 1.2840 1.1331
No log 7.0667 106 1.3788 0.0870 1.3788 1.1742
No log 7.2 108 1.4438 0.0483 1.4438 1.2016
No log 7.3333 110 1.2756 0.1986 1.2756 1.1294
No log 7.4667 112 1.1651 0.2105 1.1651 1.0794
No log 7.6 114 1.0067 0.2512 1.0067 1.0033
No log 7.7333 116 0.9888 0.2773 0.9888 0.9944
No log 7.8667 118 1.1601 0.2105 1.1601 1.0771
No log 8.0 120 1.4088 0.1026 1.4088 1.1869
No log 8.1333 122 1.6473 -0.0500 1.6473 1.2835
No log 8.2667 124 1.5955 -0.0313 1.5955 1.2631
No log 8.4 126 1.3919 0.1858 1.3919 1.1798
No log 8.5333 128 1.3567 0.2438 1.3567 1.1648
No log 8.6667 130 1.5119 0.2091 1.5119 1.2296
No log 8.8 132 1.5287 0.1971 1.5287 1.2364
No log 8.9333 134 1.3230 0.2528 1.3230 1.1502
No log 9.0667 136 1.1210 0.2167 1.1210 1.0588
No log 9.2 138 1.1865 0.2528 1.1865 1.0893
No log 9.3333 140 1.4338 0.1854 1.4338 1.1974
No log 9.4667 142 1.5098 0.1663 1.5098 1.2287
No log 9.6 144 1.4955 0.1354 1.4955 1.2229
No log 9.7333 146 1.2947 0.2105 1.2947 1.1378
No log 9.8667 148 1.1925 0.1986 1.1925 1.0920
No log 10.0 150 1.1877 0.2105 1.1877 1.0898
No log 10.1333 152 1.2595 0.2105 1.2595 1.1223
No log 10.2667 154 1.2737 0.2424 1.2737 1.1286
No log 10.4 156 1.3045 0.2857 1.3045 1.1421
No log 10.5333 158 1.3203 0.2857 1.3203 1.1490
No log 10.6667 160 1.3844 0.2730 1.3844 1.1766
No log 10.8 162 1.3728 0.2640 1.3728 1.1716
No log 10.9333 164 1.3736 0.2203 1.3736 1.1720
No log 11.0667 166 1.4796 0.1058 1.4796 1.2164
No log 11.2 168 1.3888 0.0970 1.3888 1.1785
No log 11.3333 170 1.3640 0.1961 1.3640 1.1679
No log 11.4667 172 1.3954 0.1512 1.3954 1.1813
No log 11.6 174 1.5534 0.0694 1.5534 1.2464
No log 11.7333 176 1.6409 0.1428 1.6409 1.2810
No log 11.8667 178 1.6852 0.1428 1.6852 1.2981
No log 12.0 180 1.5896 0.1222 1.5896 1.2608
No log 12.1333 182 1.4349 0.1886 1.4349 1.1979
No log 12.2667 184 1.3321 0.1202 1.3321 1.1542
No log 12.4 186 1.3569 0.1052 1.3569 1.1649
No log 12.5333 188 1.4046 0.2709 1.4046 1.1851
No log 12.6667 190 1.4955 0.2522 1.4955 1.2229
No log 12.8 192 1.3429 0.2239 1.3429 1.1588
No log 12.9333 194 1.2121 0.2495 1.2121 1.1010
No log 13.0667 196 1.0927 0.3126 1.0927 1.0453
No log 13.2 198 1.2670 0.2851 1.2670 1.1256
No log 13.3333 200 1.4903 0.2525 1.4903 1.2208
No log 13.4667 202 1.4341 0.1769 1.4341 1.1975
No log 13.6 204 1.3173 0.2203 1.3173 1.1478
No log 13.7333 206 1.2313 0.1622 1.2313 1.1096
No log 13.8667 208 1.2885 0.1622 1.2885 1.1351
No log 14.0 210 1.4384 0.1816 1.4384 1.1993
No log 14.1333 212 1.5298 0.2542 1.5298 1.2368
No log 14.2667 214 1.4693 0.2542 1.4693 1.2121
No log 14.4 216 1.4804 0.2542 1.4804 1.2167
No log 14.5333 218 1.5215 0.2542 1.5215 1.2335
No log 14.6667 220 1.4113 0.2730 1.4113 1.1880
No log 14.8 222 1.1972 0.1842 1.1972 1.0941
No log 14.9333 224 1.1536 0.1842 1.1536 1.0741
No log 15.0667 226 1.2374 0.1697 1.2374 1.1124
No log 15.2 228 1.3531 0.2592 1.3531 1.1632
No log 15.3333 230 1.5023 0.2292 1.5023 1.2257
No log 15.4667 232 1.5229 0.2292 1.5229 1.2341
No log 15.6 234 1.4237 0.2015 1.4237 1.1932
No log 15.7333 236 1.2955 0.1081 1.2955 1.1382
No log 15.8667 238 1.2329 0.1141 1.2329 1.1103
No log 16.0 240 1.2906 0.0556 1.2906 1.1361
No log 16.1333 242 1.4498 0.1634 1.4498 1.2041
No log 16.2667 244 1.5885 0.1892 1.5885 1.2604
No log 16.4 246 1.5508 0.1388 1.5508 1.2453
No log 16.5333 248 1.5682 -0.1276 1.5682 1.2523
No log 16.6667 250 1.4813 -0.1274 1.4813 1.2171
No log 16.8 252 1.3262 0.0604 1.3262 1.1516
No log 16.9333 254 1.2313 0.1500 1.2313 1.1096
No log 17.0667 256 1.1794 0.1141 1.1794 1.0860
No log 17.2 258 1.2547 0.1961 1.2547 1.1201
No log 17.3333 260 1.4215 0.1814 1.4215 1.1923
No log 17.4667 262 1.5238 0.2292 1.5238 1.2344
No log 17.6 264 1.5032 0.2391 1.5032 1.2260
No log 17.7333 266 1.3445 0.2446 1.3445 1.1595
No log 17.8667 268 1.2815 0.2149 1.2815 1.1320
No log 18.0 270 1.3345 0.2149 1.3345 1.1552
No log 18.1333 272 1.4033 0.2446 1.4033 1.1846
No log 18.2667 274 1.3725 0.2149 1.3725 1.1715
No log 18.4 276 1.4099 0.2446 1.4099 1.1874
No log 18.5333 278 1.3953 0.2577 1.3953 1.1812
No log 18.6667 280 1.4227 0.2857 1.4227 1.1928
No log 18.8 282 1.3824 0.2577 1.3824 1.1757
No log 18.9333 284 1.3850 0.2446 1.3850 1.1769
No log 19.0667 286 1.2786 0.1202 1.2786 1.1308
No log 19.2 288 1.1993 0.0833 1.1993 1.0951
No log 19.3333 290 1.1204 0.0833 1.1204 1.0585
No log 19.4667 292 1.0759 0.1141 1.0759 1.0372
No log 19.6 294 1.0475 0.1141 1.0475 1.0235
No log 19.7333 296 1.0910 0.1500 1.0910 1.0445
No log 19.8667 298 1.2385 0.2577 1.2385 1.1129
No log 20.0 300 1.4523 0.2970 1.4523 1.2051
No log 20.1333 302 1.5597 0.2789 1.5597 1.2489
No log 20.2667 304 1.4555 0.3158 1.4555 1.2065
No log 20.4 306 1.3135 0.1911 1.3135 1.1461
No log 20.5333 308 1.2868 0.1579 1.2868 1.1344
No log 20.6667 310 1.3470 0.1170 1.3470 1.1606
No log 20.8 312 1.3926 0.1052 1.3926 1.1801
No log 20.9333 314 1.3438 0.1052 1.3438 1.1592
No log 21.0667 316 1.3344 0.1052 1.3344 1.1551
No log 21.2 318 1.2399 0.1351 1.2399 1.1135
No log 21.3333 320 1.1620 0.1697 1.1620 1.0780
No log 21.4667 322 1.0989 0.1928 1.0989 1.0483
No log 21.6 324 1.1517 0.2857 1.1517 1.0732
No log 21.7333 326 1.2919 0.3158 1.2919 1.1366
No log 21.8667 328 1.4184 0.3071 1.4184 1.1910
No log 22.0 330 1.4828 0.2832 1.4828 1.2177
No log 22.1333 332 1.4546 0.2832 1.4546 1.2061
No log 22.2667 334 1.3097 0.2896 1.3097 1.1444
No log 22.4 336 1.0776 0.2417 1.0776 1.0381
No log 22.5333 338 0.9382 0.2263 0.9382 0.9686
No log 22.6667 340 0.9315 0.2474 0.9315 0.9651
No log 22.8 342 1.0492 0.0894 1.0492 1.0243
No log 22.9333 344 1.2857 0.1770 1.2857 1.1339
No log 23.0667 346 1.4827 0.1816 1.4827 1.2177
No log 23.2 348 1.5129 0.1816 1.5129 1.2300
No log 23.3333 350 1.5148 0.1816 1.5148 1.2308
No log 23.4667 352 1.5628 0.2132 1.5628 1.2501
No log 23.6 354 1.5053 0.2970 1.5053 1.2269
No log 23.7333 356 1.3512 0.3126 1.3512 1.1624
No log 23.8667 358 1.2099 0.2283 1.2099 1.1000
No log 24.0 360 1.1661 0.2105 1.1661 1.0799
No log 24.1333 362 1.2338 0.1500 1.2338 1.1107
No log 24.2667 364 1.3388 0.2143 1.3388 1.1571
No log 24.4 366 1.3465 0.1473 1.3465 1.1604
No log 24.5333 368 1.3682 0.1052 1.3682 1.1697
No log 24.6667 370 1.3671 0.1052 1.3671 1.1692
No log 24.8 372 1.3150 0.1473 1.3150 1.1468
No log 24.9333 374 1.2965 0.1770 1.2965 1.1386
No log 25.0667 376 1.3476 0.1770 1.3476 1.1609
No log 25.2 378 1.3530 0.1770 1.3530 1.1632
No log 25.3333 380 1.3304 0.1770 1.3304 1.1534
No log 25.4667 382 1.3347 0.2284 1.3347 1.1553
No log 25.6 384 1.3119 0.1961 1.3119 1.1454
No log 25.7333 386 1.3307 0.2143 1.3307 1.1536
No log 25.8667 388 1.3633 0.2143 1.3633 1.1676
No log 26.0 390 1.3957 0.2143 1.3957 1.1814
No log 26.1333 392 1.3553 0.1816 1.3553 1.1642
No log 26.2667 394 1.3228 0.1473 1.3228 1.1501
No log 26.4 396 1.2826 0.1770 1.2826 1.1325
No log 26.5333 398 1.2176 0.1141 1.2176 1.1034
No log 26.6667 400 1.2060 0.1141 1.2060 1.0982
No log 26.8 402 1.2646 0.0833 1.2646 1.1245
No log 26.9333 404 1.2504 0.0833 1.2504 1.1182
No log 27.0667 406 1.1831 0.1141 1.1831 1.0877
No log 27.2 408 1.2023 0.1351 1.2023 1.0965
No log 27.3333 410 1.3280 0.2143 1.3280 1.1524
No log 27.4667 412 1.4754 0.2877 1.4754 1.2147
No log 27.6 414 1.5195 0.2877 1.5195 1.2327
No log 27.7333 416 1.4688 0.2877 1.4688 1.2119
No log 27.8667 418 1.3331 0.2143 1.3331 1.1546
No log 28.0 420 1.1592 0.1842 1.1592 1.0767
No log 28.1333 422 1.1194 0.1842 1.1194 1.0580
No log 28.2667 424 1.1736 0.2424 1.1736 1.0833
No log 28.4 426 1.2863 0.2592 1.2863 1.1341
No log 28.5333 428 1.4602 0.1744 1.4602 1.2084
No log 28.6667 430 1.5854 0.2065 1.5854 1.2591
No log 28.8 432 1.6308 0.1703 1.6308 1.2770
No log 28.9333 434 1.5864 0.1744 1.5864 1.2595
No log 29.0667 436 1.5494 0.2065 1.5494 1.2448
No log 29.2 438 1.4222 0.2640 1.4222 1.1925
No log 29.3333 440 1.3230 0.2857 1.3230 1.1502
No log 29.4667 442 1.3039 0.3126 1.3039 1.1419
No log 29.6 444 1.3630 0.3126 1.3630 1.1675
No log 29.7333 446 1.4636 0.2690 1.4636 1.2098
No log 29.8667 448 1.5643 0.2568 1.5643 1.2507
No log 30.0 450 1.6139 0.2292 1.6139 1.2704
No log 30.1333 452 1.6820 0.2004 1.6820 1.2969
No log 30.2667 454 1.6529 0.1832 1.6529 1.2856
No log 30.4 456 1.5708 0.2495 1.5708 1.2533
No log 30.5333 458 1.4839 0.2495 1.4839 1.2181
No log 30.6667 460 1.4341 0.2341 1.4341 1.1976
No log 30.8 462 1.3553 0.1622 1.3553 1.1642
No log 30.9333 464 1.3429 0.0987 1.3429 1.1588
No log 31.0667 466 1.3246 0.0987 1.3246 1.1509
No log 31.2 468 1.3379 0.1961 1.3379 1.1567
No log 31.3333 470 1.3953 0.2455 1.3953 1.1812
No log 31.4667 472 1.4600 0.2602 1.4600 1.2083
No log 31.6 474 1.4453 0.2877 1.4453 1.2022
No log 31.7333 476 1.3467 0.2315 1.3467 1.1605
No log 31.8667 478 1.2345 0.2027 1.2345 1.1111
No log 32.0 480 1.1273 0.1842 1.1273 1.0618
No log 32.1333 482 1.1175 0.1842 1.1175 1.0571
No log 32.2667 484 1.1915 0.2857 1.1915 1.0916
No log 32.4 486 1.3399 0.3037 1.3399 1.1575
No log 32.5333 488 1.4705 0.2771 1.4705 1.2126
No log 32.6667 490 1.4731 0.2915 1.4731 1.2137
No log 32.8 492 1.4423 0.2647 1.4423 1.2010
No log 32.9333 494 1.4518 0.2647 1.4518 1.2049
No log 33.0667 496 1.4772 0.2647 1.4772 1.2154
No log 33.2 498 1.4134 0.2647 1.4134 1.1889
0.2207 33.3333 500 1.3078 0.2555 1.3078 1.1436
0.2207 33.4667 502 1.2535 0.2143 1.2535 1.1196
0.2207 33.6 504 1.2256 0.2143 1.2256 1.1071
0.2207 33.7333 506 1.2815 0.2143 1.2815 1.1320
0.2207 33.8667 508 1.3890 0.1634 1.3890 1.1786
0.2207 34.0 510 1.3859 0.1744 1.3859 1.1772

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_k6_task5_organization

Finetuned
(4019)
this model