ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k2_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: 1.1074
  • Qwk: 0.2560
  • Mse: 1.1074
  • Rmse: 1.0523

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 0.2222 2 4.4122 -0.0313 4.4122 2.1005
No log 0.4444 4 2.8015 -0.0278 2.8015 1.6738
No log 0.6667 6 1.9852 -0.0015 1.9852 1.4090
No log 0.8889 8 1.7320 0.0893 1.7320 1.3160
No log 1.1111 10 1.3489 0.0303 1.3489 1.1614
No log 1.3333 12 1.1334 0.1379 1.1334 1.0646
No log 1.5556 14 1.6645 0.1670 1.6645 1.2902
No log 1.7778 16 1.8439 0.1740 1.8439 1.3579
No log 2.0 18 1.1313 0.2615 1.1313 1.0636
No log 2.2222 20 1.0793 0.2245 1.0793 1.0389
No log 2.4444 22 1.5277 0.2282 1.5277 1.2360
No log 2.6667 24 1.9377 0.1952 1.9377 1.3920
No log 2.8889 26 1.8203 0.1906 1.8203 1.3492
No log 3.1111 28 1.2736 0.2870 1.2736 1.1285
No log 3.3333 30 1.3251 0.2272 1.3251 1.1511
No log 3.5556 32 1.6380 0.1875 1.6380 1.2798
No log 3.7778 34 1.2722 0.1834 1.2722 1.1279
No log 4.0 36 1.0168 0.2408 1.0168 1.0084
No log 4.2222 38 1.0453 0.3483 1.0453 1.0224
No log 4.4444 40 1.0912 0.3353 1.0912 1.0446
No log 4.6667 42 1.8355 0.2014 1.8355 1.3548
No log 4.8889 44 3.6049 0.0619 3.6049 1.8986
No log 5.1111 46 3.8017 0.0791 3.8017 1.9498
No log 5.3333 48 2.7165 0.0894 2.7165 1.6482
No log 5.5556 50 1.4415 0.2065 1.4415 1.2006
No log 5.7778 52 1.0373 0.3554 1.0373 1.0185
No log 6.0 54 1.0404 0.2980 1.0404 1.0200
No log 6.2222 56 1.1945 0.2322 1.1945 1.0930
No log 6.4444 58 1.7209 0.0959 1.7209 1.3118
No log 6.6667 60 1.9674 0.0951 1.9674 1.4026
No log 6.8889 62 1.6573 0.0976 1.6573 1.2874
No log 7.1111 64 1.1783 0.2092 1.1783 1.0855
No log 7.3333 66 1.0661 0.3571 1.0661 1.0325
No log 7.5556 68 1.1033 0.3541 1.1033 1.0504
No log 7.7778 70 1.1828 0.1740 1.1828 1.0876
No log 8.0 72 1.4672 0.1895 1.4672 1.2113
No log 8.2222 74 1.6270 0.2185 1.6270 1.2755
No log 8.4444 76 1.5002 0.2124 1.5002 1.2248
No log 8.6667 78 1.2672 0.2635 1.2672 1.1257
No log 8.8889 80 1.0290 0.3769 1.0290 1.0144
No log 9.1111 82 1.0521 0.4029 1.0521 1.0257
No log 9.3333 84 1.0826 0.3286 1.0826 1.0405
No log 9.5556 86 1.1817 0.3755 1.1817 1.0871
No log 9.7778 88 1.2307 0.2991 1.2307 1.1094
No log 10.0 90 1.3444 0.3327 1.3444 1.1595
No log 10.2222 92 1.3669 0.2508 1.3669 1.1692
No log 10.4444 94 1.1297 0.3694 1.1297 1.0629
No log 10.6667 96 0.9890 0.4191 0.9890 0.9945
No log 10.8889 98 0.9526 0.2829 0.9526 0.9760
No log 11.1111 100 0.9743 0.3958 0.9743 0.9871
No log 11.3333 102 1.2165 0.3138 1.2165 1.1029
No log 11.5556 104 1.4038 0.2742 1.4038 1.1848
No log 11.7778 106 1.2767 0.2989 1.2767 1.1299
No log 12.0 108 1.0661 0.3819 1.0661 1.0325
No log 12.2222 110 1.0328 0.4017 1.0328 1.0163
No log 12.4444 112 1.1198 0.3978 1.1198 1.0582
No log 12.6667 114 1.4418 0.2775 1.4418 1.2008
No log 12.8889 116 1.6560 0.2161 1.6560 1.2868
No log 13.1111 118 1.4723 0.2741 1.4723 1.2134
No log 13.3333 120 1.1676 0.3882 1.1676 1.0806
No log 13.5556 122 0.9956 0.4017 0.9956 0.9978
No log 13.7778 124 0.9878 0.4142 0.9878 0.9939
No log 14.0 126 1.1289 0.4258 1.1289 1.0625
No log 14.2222 128 1.5379 0.2436 1.5379 1.2401
No log 14.4444 130 1.7143 0.2566 1.7143 1.3093
No log 14.6667 132 1.4481 0.1979 1.4481 1.2034
No log 14.8889 134 1.0912 0.4105 1.0912 1.0446
No log 15.1111 136 1.0790 0.3756 1.0790 1.0388
No log 15.3333 138 1.0820 0.3756 1.0820 1.0402
No log 15.5556 140 1.1100 0.4316 1.1100 1.0536
No log 15.7778 142 1.3553 0.2475 1.3553 1.1642
No log 16.0 144 1.7795 0.2109 1.7795 1.3340
No log 16.2222 146 1.8806 0.2200 1.8806 1.3713
No log 16.4444 148 1.6035 0.2151 1.6035 1.2663
No log 16.6667 150 1.2096 0.3185 1.2096 1.0998
No log 16.8889 152 1.0681 0.3210 1.0681 1.0335
No log 17.1111 154 1.0115 0.2829 1.0115 1.0057
No log 17.3333 156 1.0342 0.3363 1.0342 1.0170
No log 17.5556 158 1.2239 0.2526 1.2239 1.1063
No log 17.7778 160 1.5260 0.2308 1.5260 1.2353
No log 18.0 162 1.5713 0.2308 1.5713 1.2535
No log 18.2222 164 1.3104 0.2726 1.3104 1.1447
No log 18.4444 166 1.0651 0.3157 1.0651 1.0320
No log 18.6667 168 1.0351 0.3762 1.0351 1.0174
No log 18.8889 170 1.1097 0.3377 1.1097 1.0534
No log 19.1111 172 1.3743 0.2558 1.3743 1.1723
No log 19.3333 174 1.5855 0.2772 1.5855 1.2592
No log 19.5556 176 1.4831 0.2806 1.4831 1.2178
No log 19.7778 178 1.2429 0.2810 1.2429 1.1149
No log 20.0 180 1.0386 0.4331 1.0386 1.0191
No log 20.2222 182 0.9978 0.4170 0.9978 0.9989
No log 20.4444 184 1.0243 0.4536 1.0243 1.0121
No log 20.6667 186 1.1281 0.4130 1.1281 1.0621
No log 20.8889 188 1.3046 0.2910 1.3046 1.1422
No log 21.1111 190 1.2954 0.3050 1.2954 1.1381
No log 21.3333 192 1.1438 0.3311 1.1438 1.0695
No log 21.5556 194 1.0555 0.4657 1.0555 1.0274
No log 21.7778 196 1.0376 0.4021 1.0376 1.0186
No log 22.0 198 1.0219 0.3665 1.0219 1.0109
No log 22.2222 200 1.0597 0.4087 1.0597 1.0294
No log 22.4444 202 1.1564 0.2612 1.1564 1.0753
No log 22.6667 204 1.1597 0.3452 1.1597 1.0769
No log 22.8889 206 1.0933 0.3273 1.0933 1.0456
No log 23.1111 208 1.0568 0.3958 1.0568 1.0280
No log 23.3333 210 1.0536 0.3566 1.0536 1.0265
No log 23.5556 212 1.0728 0.3082 1.0728 1.0358
No log 23.7778 214 1.0625 0.2643 1.0625 1.0308
No log 24.0 216 1.0763 0.2478 1.0763 1.0374
No log 24.2222 218 1.1608 0.2017 1.1608 1.0774
No log 24.4444 220 1.2303 0.1272 1.2303 1.1092
No log 24.6667 222 1.1962 0.1856 1.1962 1.0937
No log 24.8889 224 1.1370 0.2327 1.1370 1.0663
No log 25.1111 226 1.1668 0.2324 1.1668 1.0802
No log 25.3333 228 1.2803 0.2272 1.2803 1.1315
No log 25.5556 230 1.4786 0.1941 1.4786 1.2160
No log 25.7778 232 1.4491 0.2504 1.4491 1.2038
No log 26.0 234 1.4290 0.2447 1.4290 1.1954
No log 26.2222 236 1.2352 0.1970 1.2352 1.1114
No log 26.4444 238 1.0467 0.3566 1.0467 1.0231
No log 26.6667 240 0.9987 0.4109 0.9987 0.9993
No log 26.8889 242 0.9909 0.4208 0.9909 0.9954
No log 27.1111 244 0.9928 0.3968 0.9928 0.9964
No log 27.3333 246 1.0812 0.1895 1.0812 1.0398
No log 27.5556 248 1.2315 0.2418 1.2315 1.1097
No log 27.7778 250 1.2941 0.25 1.2941 1.1376
No log 28.0 252 1.2007 0.2349 1.2007 1.0957
No log 28.2222 254 1.0608 0.2339 1.0608 1.0300
No log 28.4444 256 0.9898 0.3160 0.9898 0.9949
No log 28.6667 258 0.9655 0.3160 0.9655 0.9826
No log 28.8889 260 0.9849 0.3320 0.9849 0.9924
No log 29.1111 262 1.0347 0.1968 1.0347 1.0172
No log 29.3333 264 1.1588 0.2132 1.1588 1.0765
No log 29.5556 266 1.3802 0.2029 1.3802 1.1748
No log 29.7778 268 1.4107 0.2124 1.4107 1.1877
No log 30.0 270 1.3014 0.1949 1.3014 1.1408
No log 30.2222 272 1.1822 0.2261 1.1822 1.0873
No log 30.4444 274 1.0788 0.3817 1.0788 1.0386
No log 30.6667 276 1.0569 0.3651 1.0569 1.0281
No log 30.8889 278 1.0754 0.3669 1.0754 1.0370
No log 31.1111 280 1.1147 0.2668 1.1147 1.0558
No log 31.3333 282 1.1562 0.2934 1.1562 1.0753
No log 31.5556 284 1.1315 0.2689 1.1315 1.0637
No log 31.7778 286 1.1086 0.2689 1.1086 1.0529
No log 32.0 288 1.0781 0.3121 1.0781 1.0383
No log 32.2222 290 1.0911 0.3141 1.0911 1.0446
No log 32.4444 292 1.1473 0.2690 1.1473 1.0711
No log 32.6667 294 1.1911 0.2282 1.1911 1.0914
No log 32.8889 296 1.2820 0.1489 1.2820 1.1322
No log 33.1111 298 1.2181 0.1991 1.2181 1.1037
No log 33.3333 300 1.0974 0.3016 1.0974 1.0476
No log 33.5556 302 1.0763 0.4 1.0763 1.0374
No log 33.7778 304 1.1058 0.3397 1.1058 1.0516
No log 34.0 306 1.1233 0.3397 1.1233 1.0599
No log 34.2222 308 1.1738 0.1713 1.1738 1.0834
No log 34.4444 310 1.2149 0.1852 1.2149 1.1022
No log 34.6667 312 1.2030 0.1852 1.2030 1.0968
No log 34.8889 314 1.2061 0.1852 1.2061 1.0982
No log 35.1111 316 1.1438 0.2065 1.1438 1.0695
No log 35.3333 318 1.0830 0.3495 1.0830 1.0407
No log 35.5556 320 1.0738 0.3609 1.0738 1.0363
No log 35.7778 322 1.1140 0.3646 1.1140 1.0555
No log 36.0 324 1.2026 0.1751 1.2026 1.0967
No log 36.2222 326 1.4003 0.1608 1.4003 1.1833
No log 36.4444 328 1.5303 0.2249 1.5303 1.2371
No log 36.6667 330 1.4255 0.1683 1.4255 1.1939
No log 36.8889 332 1.2661 0.1777 1.2661 1.1252
No log 37.1111 334 1.2112 0.2164 1.2112 1.1006
No log 37.3333 336 1.1780 0.2040 1.1780 1.0853
No log 37.5556 338 1.1597 0.1783 1.1597 1.0769
No log 37.7778 340 1.1704 0.1485 1.1704 1.0819
No log 38.0 342 1.2019 0.1992 1.2019 1.0963
No log 38.2222 344 1.1883 0.1751 1.1883 1.0901
No log 38.4444 346 1.1623 0.2611 1.1623 1.0781
No log 38.6667 348 1.1676 0.3243 1.1676 1.0806
No log 38.8889 350 1.1435 0.3365 1.1435 1.0694
No log 39.1111 352 1.1275 0.3625 1.1275 1.0618
No log 39.3333 354 1.1069 0.3625 1.1069 1.0521
No log 39.5556 356 1.1370 0.3620 1.1370 1.0663
No log 39.7778 358 1.1498 0.3163 1.1498 1.0723
No log 40.0 360 1.1644 0.2635 1.1644 1.0791
No log 40.2222 362 1.1847 0.2112 1.1847 1.0884
No log 40.4444 364 1.1644 0.2187 1.1644 1.0791
No log 40.6667 366 1.1614 0.1913 1.1614 1.0777
No log 40.8889 368 1.1566 0.2673 1.1566 1.0755
No log 41.1111 370 1.1793 0.2229 1.1793 1.0860
No log 41.3333 372 1.2168 0.2082 1.2168 1.1031
No log 41.5556 374 1.2828 0.2915 1.2828 1.1326
No log 41.7778 376 1.3295 0.2915 1.3295 1.1531
No log 42.0 378 1.3627 0.2143 1.3627 1.1673
No log 42.2222 380 1.3859 0.2143 1.3859 1.1772
No log 42.4444 382 1.3549 0.2638 1.3549 1.1640
No log 42.6667 384 1.3435 0.2393 1.3435 1.1591
No log 42.8889 386 1.3190 0.2067 1.3190 1.1485
No log 43.1111 388 1.2541 0.1913 1.2541 1.1199
No log 43.3333 390 1.1946 0.1995 1.1946 1.0930
No log 43.5556 392 1.1782 0.1995 1.1782 1.0855
No log 43.7778 394 1.1914 0.2673 1.1914 1.0915
No log 44.0 396 1.1884 0.2673 1.1884 1.0901
No log 44.2222 398 1.1843 0.2552 1.1843 1.0883
No log 44.4444 400 1.1581 0.2268 1.1581 1.0762
No log 44.6667 402 1.1367 0.3275 1.1367 1.0662
No log 44.8889 404 1.1302 0.3466 1.1302 1.0631
No log 45.1111 406 1.1211 0.3466 1.1211 1.0588
No log 45.3333 408 1.1224 0.3167 1.1224 1.0595
No log 45.5556 410 1.1747 0.2333 1.1747 1.0839
No log 45.7778 412 1.2462 0.1274 1.2462 1.1163
No log 46.0 414 1.3189 0.1625 1.3189 1.1484
No log 46.2222 416 1.3086 0.1522 1.3086 1.1439
No log 46.4444 418 1.2999 0.1522 1.2999 1.1401
No log 46.6667 420 1.2542 0.1298 1.2542 1.1199
No log 46.8889 422 1.1917 0.2322 1.1917 1.0917
No log 47.1111 424 1.1350 0.3136 1.1350 1.0654
No log 47.3333 426 1.1547 0.2322 1.1547 1.0746
No log 47.5556 428 1.1894 0.1935 1.1894 1.0906
No log 47.7778 430 1.1644 0.2322 1.1644 1.0791
No log 48.0 432 1.1758 0.2592 1.1758 1.0844
No log 48.2222 434 1.1454 0.3459 1.1454 1.0702
No log 48.4444 436 1.1217 0.3339 1.1217 1.0591
No log 48.6667 438 1.1197 0.3311 1.1197 1.0582
No log 48.8889 440 1.1273 0.3433 1.1273 1.0618
No log 49.1111 442 1.1335 0.2904 1.1335 1.0647
No log 49.3333 444 1.1042 0.2904 1.1042 1.0508
No log 49.5556 446 1.1101 0.3049 1.1101 1.0536
No log 49.7778 448 1.1397 0.3433 1.1397 1.0676
No log 50.0 450 1.1800 0.2560 1.1800 1.0863
No log 50.2222 452 1.2102 0.2560 1.2102 1.1001
No log 50.4444 454 1.2156 0.1981 1.2156 1.1025
No log 50.6667 456 1.2068 0.2560 1.2068 1.0986
No log 50.8889 458 1.2316 0.1981 1.2316 1.1098
No log 51.1111 460 1.2683 0.1773 1.2683 1.1262
No log 51.3333 462 1.2613 0.2311 1.2613 1.1231
No log 51.5556 464 1.2835 0.2379 1.2835 1.1329
No log 51.7778 466 1.3436 0.2272 1.3436 1.1592
No log 52.0 468 1.3441 0.2002 1.3441 1.1593
No log 52.2222 470 1.3707 0.1981 1.3707 1.1708
No log 52.4444 472 1.3478 0.2002 1.3478 1.1610
No log 52.6667 474 1.3463 0.2002 1.3463 1.1603
No log 52.8889 476 1.3506 0.1909 1.3506 1.1621
No log 53.1111 478 1.3483 0.1909 1.3483 1.1612
No log 53.3333 480 1.3074 0.2044 1.3074 1.1434
No log 53.5556 482 1.2110 0.1809 1.2110 1.1004
No log 53.7778 484 1.1380 0.3262 1.1380 1.0668
No log 54.0 486 1.1028 0.3430 1.1028 1.0501
No log 54.2222 488 1.0993 0.3559 1.0993 1.0485
No log 54.4444 490 1.1097 0.3121 1.1097 1.0534
No log 54.6667 492 1.1479 0.2560 1.1479 1.0714
No log 54.8889 494 1.1853 0.1981 1.1853 1.0887
No log 55.1111 496 1.2371 0.1816 1.2371 1.1122
No log 55.3333 498 1.2086 0.2281 1.2086 1.0994
0.2281 55.5556 500 1.1348 0.3299 1.1348 1.0653
0.2281 55.7778 502 1.0738 0.3102 1.0738 1.0362
0.2281 56.0 504 1.0461 0.3559 1.0461 1.0228
0.2281 56.2222 506 1.0173 0.3891 1.0173 1.0086
0.2281 56.4444 508 1.0136 0.4002 1.0136 1.0068
0.2281 56.6667 510 1.0279 0.3759 1.0279 1.0139
0.2281 56.8889 512 1.0722 0.3102 1.0722 1.0355
0.2281 57.1111 514 1.1166 0.2668 1.1166 1.0567
0.2281 57.3333 516 1.1160 0.2560 1.1160 1.0564
0.2281 57.5556 518 1.1113 0.2560 1.1113 1.0542
0.2281 57.7778 520 1.1074 0.2560 1.1074 1.0523

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_usingALLEssays_FineTuningAraBERT_run3_AugV5_k2_task5_organization

Finetuned
(4019)
this model