ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k20_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: 1.1199
  • Qwk: 0.3732
  • Mse: 1.1199
  • Rmse: 1.0582

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 0.0206 2 4.0337 -0.0328 4.0337 2.0084
No log 0.0412 4 2.4897 -0.0675 2.4897 1.5779
No log 0.0619 6 2.4286 -0.1020 2.4286 1.5584
No log 0.0825 8 1.3188 0.0732 1.3188 1.1484
No log 0.1031 10 1.2052 0.1658 1.2052 1.0978
No log 0.1237 12 1.1348 0.2888 1.1348 1.0653
No log 0.1443 14 1.1019 0.3014 1.1019 1.0497
No log 0.1649 16 1.0825 0.3014 1.0825 1.0404
No log 0.1856 18 1.0687 0.3162 1.0687 1.0338
No log 0.2062 20 1.0622 0.1071 1.0622 1.0306
No log 0.2268 22 1.0515 0.1713 1.0515 1.0254
No log 0.2474 24 1.1005 0.3320 1.1005 1.0491
No log 0.2680 26 1.2235 0.2490 1.2235 1.1061
No log 0.2887 28 1.0626 0.2834 1.0626 1.0308
No log 0.3093 30 1.2277 0.1192 1.2277 1.1080
No log 0.3299 32 1.3882 0.0355 1.3882 1.1782
No log 0.3505 34 1.2980 0.1975 1.2980 1.1393
No log 0.3711 36 1.0591 0.3298 1.0591 1.0291
No log 0.3918 38 0.9575 0.2541 0.9575 0.9785
No log 0.4124 40 0.9547 0.4078 0.9547 0.9771
No log 0.4330 42 0.9423 0.3306 0.9423 0.9707
No log 0.4536 44 0.9407 0.3108 0.9407 0.9699
No log 0.4742 46 0.9557 0.3603 0.9557 0.9776
No log 0.4948 48 0.9683 0.3860 0.9683 0.9840
No log 0.5155 50 1.0955 0.2857 1.0955 1.0467
No log 0.5361 52 1.0576 0.2447 1.0576 1.0284
No log 0.5567 54 0.9943 0.3556 0.9943 0.9972
No log 0.5773 56 0.9742 0.3556 0.9742 0.9870
No log 0.5979 58 0.9875 0.2836 0.9875 0.9937
No log 0.6186 60 0.9685 0.2899 0.9685 0.9841
No log 0.6392 62 1.0151 0.3011 1.0151 1.0075
No log 0.6598 64 1.1224 0.2615 1.1224 1.0594
No log 0.6804 66 1.0777 0.2988 1.0777 1.0381
No log 0.7010 68 0.9738 0.3049 0.9738 0.9868
No log 0.7216 70 0.9087 0.3960 0.9087 0.9533
No log 0.7423 72 0.8826 0.4692 0.8826 0.9394
No log 0.7629 74 0.9670 0.3428 0.9670 0.9834
No log 0.7835 76 0.9550 0.3428 0.9550 0.9772
No log 0.8041 78 0.8685 0.4659 0.8685 0.9319
No log 0.8247 80 1.0078 0.2726 1.0078 1.0039
No log 0.8454 82 1.0666 0.3006 1.0666 1.0328
No log 0.8660 84 0.9140 0.3691 0.9140 0.9560
No log 0.8866 86 0.8319 0.4797 0.8319 0.9121
No log 0.9072 88 0.9239 0.2805 0.9239 0.9612
No log 0.9278 90 0.8891 0.3813 0.8891 0.9429
No log 0.9485 92 0.8707 0.4101 0.8707 0.9331
No log 0.9691 94 1.1914 0.1638 1.1914 1.0915
No log 0.9897 96 1.4771 0.2098 1.4771 1.2153
No log 1.0103 98 1.4024 0.2229 1.4024 1.1842
No log 1.0309 100 1.0892 0.3298 1.0892 1.0436
No log 1.0515 102 0.9168 0.4251 0.9168 0.9575
No log 1.0722 104 0.9204 0.4849 0.9204 0.9593
No log 1.0928 106 0.9224 0.4691 0.9224 0.9604
No log 1.1134 108 1.0136 0.4008 1.0136 1.0068
No log 1.1340 110 1.0938 0.2850 1.0938 1.0458
No log 1.1546 112 1.0097 0.4123 1.0097 1.0048
No log 1.1753 114 1.0253 0.3768 1.0253 1.0126
No log 1.1959 116 1.0324 0.4119 1.0324 1.0160
No log 1.2165 118 0.9183 0.4494 0.9183 0.9583
No log 1.2371 120 0.9339 0.4093 0.9339 0.9664
No log 1.2577 122 1.0892 0.3224 1.0892 1.0436
No log 1.2784 124 1.2369 0.2384 1.2369 1.1122
No log 1.2990 126 1.1549 0.2439 1.1549 1.0746
No log 1.3196 128 1.0125 0.3939 1.0125 1.0062
No log 1.3402 130 1.0412 0.3824 1.0412 1.0204
No log 1.3608 132 1.1261 0.3590 1.1261 1.0612
No log 1.3814 134 1.0073 0.4350 1.0073 1.0036
No log 1.4021 136 0.9299 0.4407 0.9299 0.9643
No log 1.4227 138 0.9345 0.4297 0.9345 0.9667
No log 1.4433 140 1.0605 0.3945 1.0605 1.0298
No log 1.4639 142 1.1912 0.3778 1.1912 1.0914
No log 1.4845 144 1.2123 0.3699 1.2123 1.1010
No log 1.5052 146 1.2556 0.25 1.2556 1.1205
No log 1.5258 148 1.0665 0.2336 1.0665 1.0327
No log 1.5464 150 0.9656 0.2693 0.9656 0.9826
No log 1.5670 152 0.9855 0.3332 0.9855 0.9927
No log 1.5876 154 0.9676 0.3418 0.9676 0.9837
No log 1.6082 156 1.1346 0.3728 1.1346 1.0652
No log 1.6289 158 1.3384 0.2586 1.3384 1.1569
No log 1.6495 160 1.2386 0.2524 1.2386 1.1129
No log 1.6701 162 1.1141 0.3607 1.1141 1.0555
No log 1.6907 164 1.0811 0.3535 1.0811 1.0398
No log 1.7113 166 1.0606 0.3510 1.0606 1.0298
No log 1.7320 168 0.9664 0.4368 0.9664 0.9831
No log 1.7526 170 0.9560 0.4027 0.9560 0.9777
No log 1.7732 172 0.9574 0.4027 0.9574 0.9785
No log 1.7938 174 0.9827 0.4264 0.9827 0.9913
No log 1.8144 176 1.0218 0.4599 1.0218 1.0108
No log 1.8351 178 1.0342 0.4231 1.0342 1.0169
No log 1.8557 180 1.1300 0.3471 1.1300 1.0630
No log 1.8763 182 1.0724 0.3688 1.0724 1.0356
No log 1.8969 184 0.9938 0.3841 0.9938 0.9969
No log 1.9175 186 0.9883 0.3841 0.9883 0.9942
No log 1.9381 188 1.0412 0.3298 1.0412 1.0204
No log 1.9588 190 1.1998 0.2550 1.1998 1.0953
No log 1.9794 192 1.2325 0.2644 1.2325 1.1102
No log 2.0 194 1.1731 0.3738 1.1731 1.0831
No log 2.0206 196 1.0698 0.3418 1.0698 1.0343
No log 2.0412 198 1.0715 0.3299 1.0715 1.0351
No log 2.0619 200 1.0687 0.3573 1.0687 1.0338
No log 2.0825 202 1.0397 0.4076 1.0397 1.0196
No log 2.1031 204 1.0443 0.4487 1.0443 1.0219
No log 2.1237 206 1.0953 0.4020 1.0953 1.0466
No log 2.1443 208 1.1864 0.2417 1.1864 1.0892
No log 2.1649 210 1.1541 0.2227 1.1541 1.0743
No log 2.1856 212 1.0475 0.2175 1.0475 1.0235
No log 2.2062 214 0.9551 0.2842 0.9551 0.9773
No log 2.2268 216 0.9506 0.2108 0.9506 0.9750
No log 2.2474 218 0.9621 0.2521 0.9621 0.9809
No log 2.2680 220 0.9722 0.2790 0.9722 0.9860
No log 2.2887 222 1.0957 0.3790 1.0957 1.0468
No log 2.3093 224 1.2629 0.3413 1.2629 1.1238
No log 2.3299 226 1.2110 0.3913 1.2110 1.1005
No log 2.3505 228 1.0959 0.2393 1.0959 1.0469
No log 2.3711 230 1.0648 0.2812 1.0648 1.0319
No log 2.3918 232 1.0924 0.2932 1.0924 1.0452
No log 2.4124 234 1.1683 0.3463 1.1683 1.0809
No log 2.4330 236 1.2235 0.3712 1.2235 1.1061
No log 2.4536 238 1.2223 0.3023 1.2223 1.1056
No log 2.4742 240 1.2338 0.2636 1.2338 1.1108
No log 2.4948 242 1.1738 0.2273 1.1738 1.0834
No log 2.5155 244 1.1011 0.2322 1.1011 1.0494
No log 2.5361 246 1.0351 0.2369 1.0351 1.0174
No log 2.5567 248 1.0125 0.3223 1.0125 1.0062
No log 2.5773 250 0.9959 0.3250 0.9959 0.9980
No log 2.5979 252 0.9910 0.3603 0.9910 0.9955
No log 2.6186 254 1.0235 0.3454 1.0235 1.0117
No log 2.6392 256 0.9990 0.3976 0.9990 0.9995
No log 2.6598 258 0.9836 0.3167 0.9836 0.9918
No log 2.6804 260 0.9579 0.3563 0.9579 0.9787
No log 2.7010 262 0.9240 0.3314 0.9240 0.9613
No log 2.7216 264 0.9163 0.3485 0.9163 0.9572
No log 2.7423 266 0.9370 0.4613 0.9370 0.9680
No log 2.7629 268 0.9590 0.4613 0.9590 0.9793
No log 2.7835 270 1.1023 0.4135 1.1023 1.0499
No log 2.8041 272 1.3314 0.2184 1.3314 1.1539
No log 2.8247 274 1.3917 0.2211 1.3917 1.1797
No log 2.8454 276 1.2546 0.3488 1.2546 1.1201
No log 2.8660 278 1.0551 0.4301 1.0551 1.0272
No log 2.8866 280 0.9313 0.2744 0.9313 0.9651
No log 2.9072 282 0.9071 0.3476 0.9071 0.9524
No log 2.9278 284 0.9183 0.3517 0.9183 0.9583
No log 2.9485 286 0.9288 0.3820 0.9288 0.9637
No log 2.9691 288 1.0633 0.38 1.0633 1.0311
No log 2.9897 290 1.3044 0.3213 1.3044 1.1421
No log 3.0103 292 1.4161 0.2530 1.4161 1.1900
No log 3.0309 294 1.2715 0.3622 1.2715 1.1276
No log 3.0515 296 1.1022 0.2595 1.1021 1.0498
No log 3.0722 298 1.1106 0.2467 1.1106 1.0539
No log 3.0928 300 1.2195 0.3601 1.2195 1.1043
No log 3.1134 302 1.3275 0.2014 1.3275 1.1522
No log 3.1340 304 1.2860 0.2329 1.2860 1.1340
No log 3.1546 306 1.1687 0.2522 1.1687 1.0811
No log 3.1753 308 1.0528 0.2577 1.0528 1.0261
No log 3.1959 310 1.0259 0.2577 1.0259 1.0129
No log 3.2165 312 1.0318 0.2577 1.0318 1.0158
No log 3.2371 314 1.0578 0.2819 1.0578 1.0285
No log 3.2577 316 1.0574 0.3124 1.0574 1.0283
No log 3.2784 318 1.0141 0.3027 1.0141 1.0070
No log 3.2990 320 0.9941 0.3167 0.9941 0.9971
No log 3.3196 322 1.0016 0.3563 1.0016 1.0008
No log 3.3402 324 1.0894 0.4244 1.0894 1.0437
No log 3.3608 326 1.3747 0.1917 1.3747 1.1725
No log 3.3814 328 1.4962 0.1967 1.4962 1.2232
No log 3.4021 330 1.3747 0.1350 1.3747 1.1725
No log 3.4227 332 1.1846 0.2986 1.1846 1.0884
No log 3.4433 334 1.0970 0.2239 1.0970 1.0474
No log 3.4639 336 1.0777 0.3161 1.0777 1.0381
No log 3.4845 338 1.1289 0.2012 1.1289 1.0625
No log 3.5052 340 1.1994 0.2794 1.1994 1.0952
No log 3.5258 342 1.2652 0.1914 1.2652 1.1248
No log 3.5464 344 1.2712 0.1914 1.2712 1.1275
No log 3.5670 346 1.1870 0.2537 1.1870 1.0895
No log 3.5876 348 1.1769 0.2664 1.1769 1.0848
No log 3.6082 350 1.1655 0.3149 1.1655 1.0796
No log 3.6289 352 1.2067 0.2644 1.2067 1.0985
No log 3.6495 354 1.2468 0.2644 1.2468 1.1166
No log 3.6701 356 1.2459 0.2012 1.2459 1.1162
No log 3.6907 358 1.1534 0.3472 1.1534 1.0740
No log 3.7113 360 1.1301 0.3577 1.1301 1.0631
No log 3.7320 362 1.1497 0.2928 1.1497 1.0722
No log 3.7526 364 1.2032 0.2644 1.2032 1.0969
No log 3.7732 366 1.2262 0.2516 1.2262 1.1073
No log 3.7938 368 1.2181 0.2516 1.2181 1.1037
No log 3.8144 370 1.1345 0.1996 1.1345 1.0651
No log 3.8351 372 1.0952 0.2842 1.0952 1.0465
No log 3.8557 374 1.1348 0.2605 1.1348 1.0653
No log 3.8763 376 1.1629 0.3310 1.1629 1.0784
No log 3.8969 378 1.1138 0.2698 1.1138 1.0554
No log 3.9175 380 1.1358 0.2287 1.1358 1.0657
No log 3.9381 382 1.1959 0.1582 1.1959 1.0936
No log 3.9588 384 1.2623 0.1226 1.2623 1.1235
No log 3.9794 386 1.2346 0.0452 1.2346 1.1111
No log 4.0 388 1.1522 0.0802 1.1522 1.0734
No log 4.0206 390 1.0876 0.2375 1.0876 1.0429
No log 4.0412 392 1.0749 0.2400 1.0749 1.0368
No log 4.0619 394 1.0734 0.2400 1.0734 1.0361
No log 4.0825 396 1.0755 0.2276 1.0755 1.0370
No log 4.1031 398 1.1005 0.3107 1.1005 1.0490
No log 4.1237 400 1.1288 0.2142 1.1288 1.0624
No log 4.1443 402 1.1354 0.1582 1.1354 1.0655
No log 4.1649 404 1.0903 0.2647 1.0903 1.0442
No log 4.1856 406 1.0757 0.2671 1.0757 1.0372
No log 4.2062 408 1.1020 0.2986 1.1020 1.0497
No log 4.2268 410 1.1057 0.3570 1.1057 1.0515
No log 4.2474 412 1.0914 0.3570 1.0914 1.0447
No log 4.2680 414 1.1430 0.2793 1.1430 1.0691
No log 4.2887 416 1.1727 0.2636 1.1727 1.0829
No log 4.3093 418 1.1881 0.2172 1.1881 1.0900
No log 4.3299 420 1.1947 0.2306 1.1947 1.0930
No log 4.3505 422 1.1988 0.2636 1.1988 1.0949
No log 4.3711 424 1.0990 0.3973 1.0990 1.0483
No log 4.3918 426 1.0260 0.3706 1.0260 1.0129
No log 4.4124 428 1.0345 0.3706 1.0345 1.0171
No log 4.4330 430 1.1028 0.3973 1.1028 1.0501
No log 4.4536 432 1.2231 0.3275 1.2231 1.1059
No log 4.4742 434 1.2437 0.3059 1.2437 1.1152
No log 4.4948 436 1.1997 0.2770 1.1997 1.0953
No log 4.5155 438 1.1749 0.2142 1.1749 1.0839
No log 4.5361 440 1.1237 0.2842 1.1237 1.0600
No log 4.5567 442 1.0990 0.2842 1.0990 1.0483
No log 4.5773 444 1.0996 0.2842 1.0996 1.0486
No log 4.5979 446 1.0887 0.3285 1.0887 1.0434
No log 4.6186 448 1.1098 0.3264 1.1098 1.0535
No log 4.6392 450 1.0691 0.3264 1.0691 1.0340
No log 4.6598 452 1.0633 0.2963 1.0633 1.0312
No log 4.6804 454 1.0482 0.2499 1.0482 1.0238
No log 4.7010 456 1.0206 0.2276 1.0206 1.0103
No log 4.7216 458 1.0167 0.2424 1.0167 1.0083
No log 4.7423 460 1.0352 0.2251 1.0352 1.0175
No log 4.7629 462 1.0516 0.2577 1.0516 1.0255
No log 4.7835 464 1.0489 0.2963 1.0489 1.0242
No log 4.8041 466 1.0247 0.3066 1.0247 1.0123
No log 4.8247 468 1.0451 0.3066 1.0451 1.0223
No log 4.8454 470 1.0648 0.3139 1.0648 1.0319
No log 4.8660 472 1.0544 0.3139 1.0544 1.0269
No log 4.8866 474 1.0213 0.3306 1.0213 1.0106
No log 4.9072 476 1.0513 0.2909 1.0513 1.0253
No log 4.9278 478 1.0661 0.2909 1.0661 1.0325
No log 4.9485 480 1.1256 0.3083 1.1256 1.0609
No log 4.9691 482 1.1318 0.2792 1.1318 1.0639
No log 4.9897 484 1.0816 0.2842 1.0816 1.0400
No log 5.0103 486 1.0315 0.3151 1.0315 1.0157
No log 5.0309 488 1.0280 0.3030 1.0280 1.0139
No log 5.0515 490 1.0282 0.3151 1.0282 1.0140
No log 5.0722 492 1.0103 0.3151 1.0103 1.0051
No log 5.0928 494 1.0033 0.3151 1.0033 1.0016
No log 5.1134 496 0.9628 0.3089 0.9628 0.9812
No log 5.1340 498 0.9380 0.3030 0.9380 0.9685
0.2718 5.1546 500 0.9858 0.3780 0.9858 0.9929
0.2718 5.1753 502 1.1100 0.4197 1.1100 1.0536
0.2718 5.1959 504 1.1520 0.4342 1.1520 1.0733
0.2718 5.2165 506 1.1475 0.4180 1.1475 1.0712
0.2718 5.2371 508 1.0907 0.3085 1.0907 1.0443
0.2718 5.2577 510 1.0844 0.2474 1.0844 1.0413
0.2718 5.2784 512 1.0861 0.2474 1.0861 1.0422
0.2718 5.2990 514 1.0976 0.2623 1.0976 1.0477
0.2718 5.3196 516 1.1199 0.3732 1.1199 1.0582

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_k20_task5_organization

Finetuned
(4019)
this model