ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k12_task7_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: 1.0395
  • Qwk: 0.2183
  • Mse: 1.0395
  • Rmse: 1.0195

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 0.0645 2 2.4631 -0.0109 2.4631 1.5694
No log 0.1290 4 1.2209 0.0731 1.2209 1.1050
No log 0.1935 6 1.0709 -0.1304 1.0709 1.0348
No log 0.2581 8 1.0735 -0.0425 1.0735 1.0361
No log 0.3226 10 1.2457 -0.1136 1.2457 1.1161
No log 0.3871 12 1.1012 0.1141 1.1012 1.0494
No log 0.4516 14 0.9763 0.1142 0.9763 0.9881
No log 0.5161 16 0.9178 0.0993 0.9178 0.9580
No log 0.5806 18 0.8845 0.2063 0.8845 0.9405
No log 0.6452 20 0.9119 0.2904 0.9119 0.9549
No log 0.7097 22 0.9338 0.1672 0.9338 0.9663
No log 0.7742 24 0.9319 0.2063 0.9319 0.9653
No log 0.8387 26 0.9389 0.1888 0.9389 0.9690
No log 0.9032 28 1.0383 0.1421 1.0383 1.0190
No log 0.9677 30 0.9213 0.1439 0.9213 0.9598
No log 1.0323 32 0.7758 0.1440 0.7758 0.8808
No log 1.0968 34 0.7662 0.0330 0.7662 0.8753
No log 1.1613 36 0.7574 0.1752 0.7574 0.8703
No log 1.2258 38 0.7988 0.2950 0.7988 0.8938
No log 1.2903 40 0.8990 0.2670 0.8990 0.9482
No log 1.3548 42 0.9355 0.2259 0.9355 0.9672
No log 1.4194 44 0.9082 0.1672 0.9082 0.9530
No log 1.4839 46 0.9422 0.1624 0.9422 0.9707
No log 1.5484 48 0.9226 0.1487 0.9226 0.9605
No log 1.6129 50 0.8783 0.1946 0.8783 0.9372
No log 1.6774 52 0.9102 0.1946 0.9102 0.9540
No log 1.7419 54 0.9743 0.1661 0.9743 0.9871
No log 1.8065 56 0.9917 0.0149 0.9917 0.9958
No log 1.8710 58 0.9380 0.0149 0.9380 0.9685
No log 1.9355 60 0.9380 0.0154 0.9380 0.9685
No log 2.0 62 0.9860 0.1373 0.9860 0.9930
No log 2.0645 64 1.0599 0.1348 1.0599 1.0295
No log 2.1290 66 1.0622 0.0952 1.0622 1.0306
No log 2.1935 68 1.0112 0.1955 1.0112 1.0056
No log 2.2581 70 0.9475 0.2722 0.9475 0.9734
No log 2.3226 72 0.9664 0.2395 0.9664 0.9830
No log 2.3871 74 1.0157 0.2862 1.0157 1.0078
No log 2.4516 76 1.0839 0.1646 1.0839 1.0411
No log 2.5161 78 1.0903 0.2322 1.0903 1.0442
No log 2.5806 80 1.0733 0.2023 1.0733 1.0360
No log 2.6452 82 1.0611 0.3327 1.0611 1.0301
No log 2.7097 84 1.0091 0.3959 1.0091 1.0045
No log 2.7742 86 1.0877 0.3473 1.0877 1.0429
No log 2.8387 88 1.6923 0.1315 1.6923 1.3009
No log 2.9032 90 1.7841 0.1307 1.7841 1.3357
No log 2.9677 92 1.1842 0.3273 1.1842 1.0882
No log 3.0323 94 0.8484 0.3377 0.8484 0.9211
No log 3.0968 96 0.8506 0.3450 0.8506 0.9223
No log 3.1613 98 0.7841 0.2981 0.7841 0.8855
No log 3.2258 100 0.8080 0.1410 0.8080 0.8989
No log 3.2903 102 0.8247 0.1410 0.8247 0.9081
No log 3.3548 104 0.7913 0.0971 0.7913 0.8896
No log 3.4194 106 0.8404 0.3637 0.8404 0.9167
No log 3.4839 108 0.9772 0.3294 0.9772 0.9885
No log 3.5484 110 1.1093 0.2166 1.1093 1.0532
No log 3.6129 112 1.0930 0.2321 1.0930 1.0455
No log 3.6774 114 1.1089 0.1264 1.1089 1.0530
No log 3.7419 116 1.1386 0.0656 1.1386 1.0671
No log 3.8065 118 1.1613 0.0558 1.1613 1.0776
No log 3.8710 120 1.3161 0.1067 1.3161 1.1472
No log 3.9355 122 1.4416 0.0972 1.4416 1.2006
No log 4.0 124 1.4267 0.0972 1.4267 1.1945
No log 4.0645 126 1.3000 0.1696 1.3000 1.1402
No log 4.1290 128 1.3838 0.0995 1.3838 1.1763
No log 4.1935 130 1.4414 0.0929 1.4414 1.2006
No log 4.2581 132 1.4907 0.0462 1.4907 1.2209
No log 4.3226 134 1.5512 0.0642 1.5512 1.2455
No log 4.3871 136 1.3393 0.1330 1.3393 1.1573
No log 4.4516 138 1.0608 0.2728 1.0608 1.0299
No log 4.5161 140 0.8603 0.1753 0.8603 0.9275
No log 4.5806 142 0.9225 0.2439 0.9225 0.9605
No log 4.6452 144 0.9926 0.3159 0.9926 0.9963
No log 4.7097 146 0.9048 0.3121 0.9048 0.9512
No log 4.7742 148 0.8996 0.2926 0.8996 0.9485
No log 4.8387 150 0.8508 0.1952 0.8508 0.9224
No log 4.9032 152 0.8760 0.2237 0.8760 0.9360
No log 4.9677 154 0.9840 0.2616 0.9840 0.9919
No log 5.0323 156 0.9464 0.2812 0.9464 0.9728
No log 5.0968 158 0.8958 0.1773 0.8958 0.9465
No log 5.1613 160 0.9408 0.2749 0.9408 0.9699
No log 5.2258 162 1.0094 0.2471 1.0094 1.0047
No log 5.2903 164 1.1676 0.2548 1.1676 1.0806
No log 5.3548 166 1.1032 0.2451 1.1032 1.0503
No log 5.4194 168 1.0126 0.2453 1.0126 1.0063
No log 5.4839 170 1.0565 0.1960 1.0565 1.0279
No log 5.5484 172 1.0426 0.2627 1.0426 1.0211
No log 5.6129 174 0.9257 0.1990 0.9257 0.9622
No log 5.6774 176 0.9243 0.1990 0.9243 0.9614
No log 5.7419 178 1.0878 0.2777 1.0878 1.0430
No log 5.8065 180 1.3988 0.1413 1.3988 1.1827
No log 5.8710 182 1.4247 0.1387 1.4247 1.1936
No log 5.9355 184 1.2261 0.1502 1.2261 1.1073
No log 6.0 186 1.0029 0.3243 1.0029 1.0014
No log 6.0645 188 0.9429 0.2071 0.9429 0.9710
No log 6.1290 190 0.9946 0.3503 0.9946 0.9973
No log 6.1935 192 1.1312 0.2971 1.1312 1.0636
No log 6.2581 194 1.1673 0.3102 1.1673 1.0804
No log 6.3226 196 1.1350 0.2424 1.1350 1.0653
No log 6.3871 198 1.0985 0.2491 1.0985 1.0481
No log 6.4516 200 1.1444 0.2113 1.1444 1.0698
No log 6.5161 202 1.0710 0.2249 1.0710 1.0349
No log 6.5806 204 1.0650 0.2242 1.0650 1.0320
No log 6.6452 206 1.1571 0.2885 1.1571 1.0757
No log 6.7097 208 1.1815 0.3099 1.1815 1.0870
No log 6.7742 210 1.1453 0.2752 1.1453 1.0702
No log 6.8387 212 1.1146 0.2752 1.1146 1.0557
No log 6.9032 214 1.0348 0.2627 1.0348 1.0173
No log 6.9677 216 0.9451 0.2770 0.9451 0.9722
No log 7.0323 218 0.9453 0.2770 0.9453 0.9723
No log 7.0968 220 0.9406 0.2929 0.9406 0.9698
No log 7.1613 222 0.9486 0.1834 0.9486 0.9740
No log 7.2258 224 1.0777 0.2123 1.0777 1.0381
No log 7.2903 226 1.2822 0.1746 1.2822 1.1324
No log 7.3548 228 1.1748 0.1344 1.1748 1.0839
No log 7.4194 230 0.9880 0.2192 0.9880 0.9940
No log 7.4839 232 0.9621 0.1099 0.9621 0.9809
No log 7.5484 234 1.0104 0.1930 1.0104 1.0052
No log 7.6129 236 1.1652 0.1803 1.1652 1.0795
No log 7.6774 238 1.1918 0.1451 1.1918 1.0917
No log 7.7419 240 1.0685 0.1712 1.0685 1.0337
No log 7.8065 242 1.0551 0.1712 1.0551 1.0272
No log 7.8710 244 1.0775 0.1374 1.0775 1.0380
No log 7.9355 246 1.2075 0.0501 1.2075 1.0989
No log 8.0 248 1.3942 0.0873 1.3942 1.1808
No log 8.0645 250 1.6065 0.0830 1.6065 1.2675
No log 8.1290 252 1.5089 0.0888 1.5089 1.2284
No log 8.1935 254 1.2055 0.1479 1.2055 1.0979
No log 8.2581 256 1.0572 0.1701 1.0572 1.0282
No log 8.3226 258 1.1009 0.1339 1.1009 1.0493
No log 8.3871 260 1.2377 0.2101 1.2377 1.1125
No log 8.4516 262 1.2066 0.2176 1.2066 1.0985
No log 8.5161 264 1.0405 0.1801 1.0405 1.0201
No log 8.5806 266 1.0075 0.2711 1.0075 1.0037
No log 8.6452 268 1.0164 0.2711 1.0164 1.0081
No log 8.7097 270 0.9855 0.0773 0.9855 0.9927
No log 8.7742 272 1.1396 0.2591 1.1396 1.0675
No log 8.8387 274 1.2985 0.2030 1.2985 1.1395
No log 8.9032 276 1.2817 0.1763 1.2817 1.1321
No log 8.9677 278 1.1303 0.2568 1.1303 1.0632
No log 9.0323 280 1.0176 0.2877 1.0176 1.0087
No log 9.0968 282 0.9727 0.1981 0.9727 0.9863
No log 9.1613 284 1.0082 0.3300 1.0082 1.0041
No log 9.2258 286 1.1791 0.2065 1.1791 1.0859
No log 9.2903 288 1.2294 0.1839 1.2294 1.1088
No log 9.3548 290 1.1108 0.1862 1.1108 1.0540
No log 9.4194 292 1.0046 0.3195 1.0046 1.0023
No log 9.4839 294 0.9820 0.3527 0.9820 0.9909
No log 9.5484 296 1.0227 0.3451 1.0227 1.0113
No log 9.6129 298 1.1112 0.2080 1.1112 1.0541
No log 9.6774 300 1.1467 0.2041 1.1467 1.0709
No log 9.7419 302 1.0355 0.2993 1.0355 1.0176
No log 9.8065 304 0.9247 0.3526 0.9247 0.9616
No log 9.8710 306 0.9933 0.3679 0.9933 0.9966
No log 9.9355 308 1.0554 0.3123 1.0554 1.0273
No log 10.0 310 0.9433 0.3719 0.9433 0.9712
No log 10.0645 312 0.8248 0.2633 0.8248 0.9082
No log 10.1290 314 0.8438 0.3842 0.8438 0.9186
No log 10.1935 316 0.8530 0.4444 0.8530 0.9236
No log 10.2581 318 0.9013 0.4153 0.9013 0.9494
No log 10.3226 320 0.9684 0.3678 0.9684 0.9841
No log 10.3871 322 0.8477 0.4369 0.8477 0.9207
No log 10.4516 324 0.7380 0.2121 0.7380 0.8591
No log 10.5161 326 0.7416 0.3299 0.7416 0.8612
No log 10.5806 328 0.8341 0.3723 0.8341 0.9133
No log 10.6452 330 1.0175 0.3946 1.0175 1.0087
No log 10.7097 332 1.2378 0.1965 1.2378 1.1126
No log 10.7742 334 1.3041 0.2297 1.3041 1.1420
No log 10.8387 336 1.0925 0.2354 1.0925 1.0452
No log 10.9032 338 0.8889 0.3798 0.8889 0.9428
No log 10.9677 340 0.7948 0.3161 0.7948 0.8915
No log 11.0323 342 0.7896 0.3161 0.7896 0.8886
No log 11.0968 344 0.8946 0.2853 0.8946 0.9458
No log 11.1613 346 1.1670 0.1980 1.1670 1.0803
No log 11.2258 348 1.3224 0.1754 1.3224 1.1499
No log 11.2903 350 1.2408 0.1729 1.2408 1.1139
No log 11.3548 352 1.0346 0.3089 1.0346 1.0172
No log 11.4194 354 0.9003 0.2877 0.9003 0.9489
No log 11.4839 356 0.9062 0.3106 0.9062 0.9520
No log 11.5484 358 0.9811 0.2750 0.9811 0.9905
No log 11.6129 360 0.9909 0.3781 0.9909 0.9954
No log 11.6774 362 0.9539 0.3417 0.9539 0.9767
No log 11.7419 364 0.8345 0.2962 0.8345 0.9135
No log 11.8065 366 0.7884 0.3069 0.7884 0.8879
No log 11.8710 368 0.8172 0.2947 0.8172 0.9040
No log 11.9355 370 0.8848 0.4173 0.8848 0.9407
No log 12.0 372 0.8902 0.3083 0.8902 0.9435
No log 12.0645 374 0.8436 0.3161 0.8436 0.9185
No log 12.1290 376 0.8052 0.2806 0.8052 0.8973
No log 12.1935 378 0.7923 0.2203 0.7923 0.8901
No log 12.2581 380 0.8040 0.2806 0.8040 0.8966
No log 12.3226 382 0.8510 0.2888 0.8510 0.9225
No log 12.3871 384 0.8363 0.2718 0.8363 0.9145
No log 12.4516 386 0.8385 0.1506 0.8385 0.9157
No log 12.5161 388 0.8830 0.1661 0.8830 0.9397
No log 12.5806 390 0.9960 0.2857 0.9960 0.9980
No log 12.6452 392 1.1920 0.2421 1.1920 1.0918
No log 12.7097 394 1.2002 0.1919 1.2002 1.0955
No log 12.7742 396 1.0373 0.3290 1.0373 1.0185
No log 12.8387 398 0.9197 0.2202 0.9197 0.9590
No log 12.9032 400 0.9304 0.2643 0.9304 0.9646
No log 12.9677 402 1.0151 0.3195 1.0151 1.0075
No log 13.0323 404 1.1728 0.2846 1.1728 1.0830
No log 13.0968 406 1.1459 0.2636 1.1459 1.0705
No log 13.1613 408 1.0312 0.3005 1.0312 1.0155
No log 13.2258 410 1.0360 0.3059 1.0360 1.0179
No log 13.2903 412 1.1244 0.28 1.1244 1.0604
No log 13.3548 414 1.3801 0.2027 1.3801 1.1748
No log 13.4194 416 1.4923 0.1813 1.4923 1.2216
No log 13.4839 418 1.3303 0.2251 1.3303 1.1534
No log 13.5484 420 0.9942 0.2832 0.9942 0.9971
No log 13.6129 422 0.8132 0.1839 0.8132 0.9018
No log 13.6774 424 0.7927 0.1531 0.7927 0.8904
No log 13.7419 426 0.8091 0.1514 0.8091 0.8995
No log 13.8065 428 0.9532 0.2832 0.9532 0.9763
No log 13.8710 430 1.1904 0.2824 1.1904 1.0911
No log 13.9355 432 1.2558 0.2341 1.2558 1.1206
No log 14.0 434 1.1260 0.3183 1.1260 1.0611
No log 14.0645 436 0.9456 0.3159 0.9456 0.9724
No log 14.1290 438 0.8960 0.2521 0.8960 0.9466
No log 14.1935 440 0.9947 0.2676 0.9947 0.9974
No log 14.2581 442 1.1649 0.2910 1.1649 1.0793
No log 14.3226 444 1.1840 0.2644 1.1840 1.0881
No log 14.3871 446 1.0489 0.2826 1.0489 1.0242
No log 14.4516 448 0.9301 0.1900 0.9301 0.9644
No log 14.5161 450 0.9089 0.1171 0.9089 0.9533
No log 14.5806 452 0.9824 0.1459 0.9824 0.9912
No log 14.6452 454 1.1908 0.1860 1.1908 1.0912
No log 14.7097 456 1.4049 0.1642 1.4049 1.1853
No log 14.7742 458 1.4865 0.1120 1.4865 1.2192
No log 14.8387 460 1.3663 0.1481 1.3663 1.1689
No log 14.9032 462 1.1489 0.1935 1.1489 1.0719
No log 14.9677 464 1.0725 0.2564 1.0725 1.0356
No log 15.0323 466 1.0577 0.2564 1.0577 1.0285
No log 15.0968 468 1.1662 0.1948 1.1662 1.0799
No log 15.1613 470 1.2511 0.1021 1.2511 1.1185
No log 15.2258 472 1.1928 0.2526 1.1928 1.0922
No log 15.2903 474 1.0399 0.2564 1.0399 1.0198
No log 15.3548 476 0.8922 0.1424 0.8922 0.9446
No log 15.4194 478 0.8531 0.1490 0.8531 0.9236
No log 15.4839 480 0.8571 0.1424 0.8571 0.9258
No log 15.5484 482 0.9253 0.1683 0.9253 0.9620
No log 15.6129 484 1.0858 0.2916 1.0858 1.0420
No log 15.6774 486 1.1911 0.2375 1.1911 1.0914
No log 15.7419 488 1.1278 0.2772 1.1278 1.0620
No log 15.8065 490 0.9904 0.3173 0.9904 0.9952
No log 15.8710 492 0.9379 0.1391 0.9379 0.9684
No log 15.9355 494 0.9276 0.1391 0.9276 0.9631
No log 16.0 496 1.0479 0.2566 1.0479 1.0237
No log 16.0645 498 1.2010 0.2367 1.2010 1.0959
0.3336 16.1290 500 1.2713 0.2240 1.2713 1.1275
0.3336 16.1935 502 1.4662 0.0855 1.4662 1.2109
0.3336 16.2581 504 1.5634 0.1553 1.5634 1.2504
0.3336 16.3226 506 1.4995 0.1209 1.4995 1.2245
0.3336 16.3871 508 1.3390 0.1244 1.3390 1.1572
0.3336 16.4516 510 1.1758 0.2682 1.1758 1.0843
0.3336 16.5161 512 1.0945 0.2999 1.0945 1.0462
0.3336 16.5806 514 1.0083 0.3913 1.0083 1.0041
0.3336 16.6452 516 1.0343 0.4114 1.0343 1.0170
0.3336 16.7097 518 1.2041 0.2774 1.2041 1.0973
0.3336 16.7742 520 1.2593 0.2285 1.2593 1.1222
0.3336 16.8387 522 1.2326 0.2234 1.2326 1.1102
0.3336 16.9032 524 1.0514 0.3618 1.0514 1.0254
0.3336 16.9677 526 0.9103 0.2134 0.9103 0.9541
0.3336 17.0323 528 0.8357 0.1853 0.8357 0.9142
0.3336 17.0968 530 0.8403 0.1205 0.8403 0.9167
0.3336 17.1613 532 0.8800 0.2090 0.8800 0.9381
0.3336 17.2258 534 1.0395 0.2183 1.0395 1.0195

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k12_task7_organization

Finetuned
(4204)
this model