ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k13_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: 1.1010
  • Qwk: 0.4036
  • Mse: 1.1010
  • Rmse: 1.0493

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 0.0312 2 4.5333 0.0010 4.5333 2.1291
No log 0.0625 4 2.5227 0.0100 2.5227 1.5883
No log 0.0938 6 2.1973 -0.0433 2.1973 1.4823
No log 0.125 8 1.8042 0.0062 1.8042 1.3432
No log 0.1562 10 1.4260 -0.0281 1.4260 1.1941
No log 0.1875 12 1.5944 0.0402 1.5944 1.2627
No log 0.2188 14 1.4842 0.0631 1.4842 1.2183
No log 0.25 16 1.8534 0.1412 1.8534 1.3614
No log 0.2812 18 1.8831 0.2297 1.8831 1.3722
No log 0.3125 20 1.4258 0.2342 1.4258 1.1941
No log 0.3438 22 1.3377 0.1909 1.3377 1.1566
No log 0.375 24 1.1349 0.2670 1.1349 1.0653
No log 0.4062 26 1.0968 0.3121 1.0968 1.0473
No log 0.4375 28 1.1138 0.3121 1.1138 1.0554
No log 0.4688 30 1.4125 0.2981 1.4125 1.1885
No log 0.5 32 1.6645 0.3445 1.6645 1.2902
No log 0.5312 34 1.4082 0.3590 1.4082 1.1867
No log 0.5625 36 1.3560 0.3538 1.3560 1.1645
No log 0.5938 38 1.4218 0.3372 1.4218 1.1924
No log 0.625 40 1.1230 0.3757 1.1230 1.0597
No log 0.6562 42 1.0706 0.4264 1.0706 1.0347
No log 0.6875 44 1.0970 0.3404 1.0970 1.0474
No log 0.7188 46 1.2778 0.3005 1.2778 1.1304
No log 0.75 48 1.3855 0.2857 1.3855 1.1771
No log 0.7812 50 1.1647 0.3092 1.1647 1.0792
No log 0.8125 52 1.0808 0.3397 1.0808 1.0396
No log 0.8438 54 1.0936 0.3850 1.0936 1.0457
No log 0.875 56 1.2167 0.3201 1.2167 1.1031
No log 0.9062 58 1.3593 0.3748 1.3593 1.1659
No log 0.9375 60 1.5807 0.3292 1.5807 1.2573
No log 0.9688 62 1.2613 0.4169 1.2613 1.1231
No log 1.0 64 1.0128 0.4440 1.0128 1.0064
No log 1.0312 66 1.0802 0.4347 1.0802 1.0393
No log 1.0625 68 0.9910 0.4690 0.9910 0.9955
No log 1.0938 70 1.0306 0.4106 1.0306 1.0152
No log 1.125 72 1.3478 0.3824 1.3478 1.1609
No log 1.1562 74 1.2694 0.4329 1.2694 1.1267
No log 1.1875 76 1.0830 0.3691 1.0830 1.0407
No log 1.2188 78 1.0804 0.3519 1.0804 1.0394
No log 1.25 80 1.2098 0.2767 1.2098 1.0999
No log 1.2812 82 1.4657 0.3384 1.4657 1.2106
No log 1.3125 84 1.5622 0.3495 1.5622 1.2499
No log 1.3438 86 1.5999 0.3400 1.5999 1.2649
No log 1.375 88 1.2622 0.3799 1.2622 1.1235
No log 1.4062 90 1.0511 0.4481 1.0511 1.0253
No log 1.4375 92 1.0724 0.3926 1.0724 1.0356
No log 1.4688 94 1.3096 0.4616 1.3096 1.1444
No log 1.5 96 1.5480 0.2808 1.5480 1.2442
No log 1.5312 98 1.3806 0.3818 1.3806 1.1750
No log 1.5625 100 1.0518 0.4894 1.0518 1.0256
No log 1.5938 102 0.9496 0.3463 0.9496 0.9745
No log 1.625 104 0.9840 0.4281 0.9840 0.9920
No log 1.6562 106 1.1599 0.3402 1.1599 1.0770
No log 1.6875 108 1.2437 0.3377 1.2437 1.1152
No log 1.7188 110 1.2591 0.3656 1.2591 1.1221
No log 1.75 112 1.1693 0.4169 1.1693 1.0813
No log 1.7812 114 1.1420 0.4027 1.1420 1.0686
No log 1.8125 116 1.3227 0.3969 1.3227 1.1501
No log 1.8438 118 1.1689 0.3945 1.1689 1.0812
No log 1.875 120 1.0309 0.4402 1.0309 1.0153
No log 1.9062 122 1.1820 0.3658 1.1820 1.0872
No log 1.9375 124 1.7221 0.2462 1.7221 1.3123
No log 1.9688 126 1.6324 0.2848 1.6324 1.2777
No log 2.0 128 1.0879 0.3872 1.0879 1.0430
No log 2.0312 130 0.9599 0.4496 0.9599 0.9798
No log 2.0625 132 0.9696 0.4196 0.9696 0.9847
No log 2.0938 134 1.1789 0.3631 1.1789 1.0858
No log 2.125 136 1.6506 0.2756 1.6506 1.2848
No log 2.1562 138 1.7463 0.2702 1.7463 1.3215
No log 2.1875 140 1.2458 0.4471 1.2458 1.1162
No log 2.2188 142 1.0494 0.4003 1.0494 1.0244
No log 2.25 144 1.1460 0.4012 1.1460 1.0705
No log 2.2812 146 1.3396 0.4154 1.3396 1.1574
No log 2.3125 148 1.3524 0.3976 1.3524 1.1629
No log 2.3438 150 1.0856 0.4024 1.0856 1.0419
No log 2.375 152 1.0607 0.3584 1.0607 1.0299
No log 2.4062 154 1.0567 0.3584 1.0567 1.0279
No log 2.4375 156 0.9565 0.4264 0.9565 0.9780
No log 2.4688 158 0.9441 0.4231 0.9441 0.9716
No log 2.5 160 1.0092 0.3672 1.0092 1.0046
No log 2.5312 162 1.1661 0.3757 1.1661 1.0798
No log 2.5625 164 1.1362 0.3917 1.1362 1.0659
No log 2.5938 166 1.1665 0.3917 1.1665 1.0801
No log 2.625 168 1.4031 0.3087 1.4031 1.1845
No log 2.6562 170 1.2424 0.4025 1.2424 1.1146
No log 2.6875 172 1.0047 0.3902 1.0047 1.0024
No log 2.7188 174 0.9456 0.4218 0.9456 0.9724
No log 2.75 176 0.9380 0.4026 0.9380 0.9685
No log 2.7812 178 1.0038 0.3321 1.0038 1.0019
No log 2.8125 180 1.1048 0.4083 1.1048 1.0511
No log 2.8438 182 1.0489 0.3843 1.0489 1.0241
No log 2.875 184 0.9934 0.3902 0.9934 0.9967
No log 2.9062 186 0.9804 0.4366 0.9804 0.9901
No log 2.9375 188 0.9871 0.4668 0.9871 0.9935
No log 2.9688 190 1.0883 0.4782 1.0883 1.0432
No log 3.0 192 1.0926 0.4559 1.0926 1.0453
No log 3.0312 194 1.1997 0.4417 1.1997 1.0953
No log 3.0625 196 1.5930 0.3621 1.5930 1.2621
No log 3.0938 198 1.7914 0.2645 1.7914 1.3384
No log 3.125 200 1.4611 0.3598 1.4611 1.2088
No log 3.1562 202 1.1945 0.3874 1.1945 1.0929
No log 3.1875 204 1.0976 0.4172 1.0976 1.0476
No log 3.2188 206 1.0901 0.3663 1.0901 1.0441
No log 3.25 208 1.2133 0.3523 1.2133 1.1015
No log 3.2812 210 1.2163 0.3523 1.2163 1.1029
No log 3.3125 212 1.0613 0.4224 1.0613 1.0302
No log 3.3438 214 1.0418 0.4224 1.0418 1.0207
No log 3.375 216 1.2213 0.4291 1.2213 1.1051
No log 3.4062 218 1.6550 0.3247 1.6550 1.2865
No log 3.4375 220 1.6192 0.3247 1.6192 1.2725
No log 3.4688 222 1.3569 0.4519 1.3569 1.1649
No log 3.5 224 1.0600 0.4469 1.0600 1.0296
No log 3.5312 226 0.9317 0.4518 0.9317 0.9652
No log 3.5625 228 0.9866 0.3768 0.9866 0.9933
No log 3.5938 230 1.0390 0.3918 1.0390 1.0193
No log 3.625 232 1.0241 0.2938 1.0241 1.0120
No log 3.6562 234 0.9604 0.2939 0.9604 0.9800
No log 3.6875 236 0.9262 0.3108 0.9262 0.9624
No log 3.7188 238 0.9192 0.375 0.9192 0.9587
No log 3.75 240 1.0346 0.4309 1.0346 1.0171
No log 3.7812 242 1.1744 0.4574 1.1744 1.0837
No log 3.8125 244 1.1815 0.4407 1.1815 1.0870
No log 3.8438 246 1.0815 0.4314 1.0815 1.0400
No log 3.875 248 0.9358 0.4808 0.9358 0.9674
No log 3.9062 250 0.8980 0.5329 0.8980 0.9476
No log 3.9375 252 0.9146 0.4265 0.9146 0.9563
No log 3.9688 254 1.1640 0.3880 1.1640 1.0789
No log 4.0 256 1.5957 0.2584 1.5957 1.2632
No log 4.0312 258 1.5559 0.2853 1.5559 1.2473
No log 4.0625 260 1.0920 0.4236 1.0920 1.0450
No log 4.0938 262 0.9021 0.5232 0.9021 0.9498
No log 4.125 264 0.9158 0.4840 0.9158 0.9570
No log 4.1562 266 0.9059 0.4643 0.9059 0.9518
No log 4.1875 268 1.0625 0.4191 1.0625 1.0308
No log 4.2188 270 1.1856 0.4136 1.1856 1.0889
No log 4.25 272 1.0598 0.4191 1.0598 1.0295
No log 4.2812 274 0.9554 0.4516 0.9554 0.9775
No log 4.3125 276 0.9957 0.4366 0.9957 0.9978
No log 4.3438 278 1.1213 0.4538 1.1213 1.0589
No log 4.375 280 1.2439 0.3980 1.2439 1.1153
No log 4.4062 282 1.0910 0.4620 1.0910 1.0445
No log 4.4375 284 1.0290 0.4659 1.0290 1.0144
No log 4.4688 286 0.9839 0.4246 0.9839 0.9919
No log 4.5 288 0.9823 0.3944 0.9823 0.9911
No log 4.5312 290 0.9705 0.3944 0.9705 0.9852
No log 4.5625 292 0.9638 0.4313 0.9638 0.9818
No log 4.5938 294 1.0196 0.4463 1.0196 1.0098
No log 4.625 296 0.9439 0.3902 0.9439 0.9716
No log 4.6562 298 0.9053 0.5040 0.9053 0.9515
No log 4.6875 300 0.9188 0.4818 0.9188 0.9586
No log 4.7188 302 0.9637 0.4772 0.9637 0.9817
No log 4.75 304 1.0771 0.4401 1.0771 1.0378
No log 4.7812 306 1.0805 0.4172 1.0805 1.0395
No log 4.8125 308 0.9713 0.3944 0.9713 0.9855
No log 4.8438 310 0.9651 0.3944 0.9651 0.9824
No log 4.875 312 0.9629 0.3685 0.9629 0.9813
No log 4.9062 314 1.0136 0.3980 1.0136 1.0068
No log 4.9375 316 0.9948 0.3944 0.9948 0.9974
No log 4.9688 318 0.9223 0.4197 0.9223 0.9604
No log 5.0 320 0.9185 0.3842 0.9185 0.9584
No log 5.0312 322 0.9189 0.4292 0.9189 0.9586
No log 5.0625 324 1.0240 0.3606 1.0240 1.0119
No log 5.0938 326 1.1138 0.4041 1.1138 1.0554
No log 5.125 328 0.9865 0.4567 0.9865 0.9932
No log 5.1562 330 0.9307 0.4749 0.9307 0.9647
No log 5.1875 332 0.9185 0.4290 0.9185 0.9584
No log 5.2188 334 0.9207 0.4885 0.9207 0.9596
No log 5.25 336 1.0516 0.3811 1.0516 1.0255
No log 5.2812 338 1.3089 0.3755 1.3089 1.1441
No log 5.3125 340 1.2551 0.3715 1.2551 1.1203
No log 5.3438 342 1.0287 0.3687 1.0287 1.0143
No log 5.375 344 0.9165 0.4326 0.9165 0.9573
No log 5.4062 346 0.9166 0.4444 0.9166 0.9574
No log 5.4375 348 0.9535 0.4084 0.9535 0.9765
No log 5.4688 350 1.1186 0.3220 1.1186 1.0576
No log 5.5 352 1.4991 0.3806 1.4991 1.2244
No log 5.5312 354 1.6351 0.3493 1.6351 1.2787
No log 5.5625 356 1.4257 0.3081 1.4257 1.1940
No log 5.5938 358 1.1025 0.3117 1.1025 1.0500
No log 5.625 360 0.9631 0.3336 0.9631 0.9814
No log 5.6562 362 0.9620 0.4628 0.9620 0.9808
No log 5.6875 364 0.9559 0.3458 0.9559 0.9777
No log 5.7188 366 1.0528 0.3672 1.0528 1.0261
No log 5.75 368 1.3082 0.4199 1.3082 1.1438
No log 5.7812 370 1.2477 0.4137 1.2477 1.1170
No log 5.8125 372 1.0181 0.3963 1.0181 1.0090
No log 5.8438 374 0.9251 0.3639 0.9251 0.9618
No log 5.875 376 0.9351 0.3896 0.9351 0.9670
No log 5.9062 378 0.9324 0.3627 0.9324 0.9656
No log 5.9375 380 0.9934 0.3560 0.9934 0.9967
No log 5.9688 382 1.0864 0.3791 1.0864 1.0423
No log 6.0 384 1.0497 0.3881 1.0497 1.0245
No log 6.0312 386 0.9725 0.3719 0.9725 0.9862
No log 6.0625 388 0.9535 0.3379 0.9535 0.9765
No log 6.0938 390 0.9687 0.2804 0.9687 0.9842
No log 6.125 392 1.0175 0.3433 1.0175 1.0087
No log 6.1562 394 1.1251 0.4412 1.1251 1.0607
No log 6.1875 396 1.1941 0.4272 1.1941 1.0928
No log 6.2188 398 1.1624 0.4444 1.1624 1.0782
No log 6.25 400 1.1254 0.4408 1.1254 1.0609
No log 6.2812 402 0.9998 0.3636 0.9998 0.9999
No log 6.3125 404 0.9561 0.2694 0.9561 0.9778
No log 6.3438 406 0.9557 0.2945 0.9557 0.9776
No log 6.375 408 1.0021 0.4426 1.0021 1.0010
No log 6.4062 410 1.0852 0.4086 1.0852 1.0418
No log 6.4375 412 1.0309 0.4550 1.0309 1.0153
No log 6.4688 414 0.9421 0.3174 0.9421 0.9706
No log 6.5 416 0.9484 0.4612 0.9484 0.9739
No log 6.5312 418 0.9851 0.4533 0.9851 0.9925
No log 6.5625 420 0.9525 0.4579 0.9525 0.9760
No log 6.5938 422 0.9562 0.3368 0.9562 0.9778
No log 6.625 424 1.1169 0.4346 1.1169 1.0568
No log 6.6562 426 1.1888 0.4574 1.1888 1.0903
No log 6.6875 428 1.0836 0.4604 1.0836 1.0410
No log 6.7188 430 0.9726 0.3081 0.9726 0.9862
No log 6.75 432 0.9522 0.2831 0.9522 0.9758
No log 6.7812 434 0.9514 0.2966 0.9514 0.9754
No log 6.8125 436 0.9626 0.3174 0.9626 0.9811
No log 6.8438 438 1.0684 0.4581 1.0684 1.0336
No log 6.875 440 1.1564 0.4355 1.1564 1.0754
No log 6.9062 442 1.1616 0.4833 1.1616 1.0778
No log 6.9375 444 1.1922 0.4492 1.1922 1.0919
No log 6.9688 446 1.2144 0.4492 1.2144 1.1020
No log 7.0 448 1.1317 0.4627 1.1317 1.0638
No log 7.0312 450 1.0334 0.3983 1.0334 1.0166
No log 7.0625 452 0.9555 0.4177 0.9555 0.9775
No log 7.0938 454 0.9559 0.3760 0.9559 0.9777
No log 7.125 456 1.0047 0.4070 1.0047 1.0023
No log 7.1562 458 1.0586 0.4373 1.0586 1.0289
No log 7.1875 460 1.1406 0.4404 1.1406 1.0680
No log 7.2188 462 1.1271 0.4401 1.1271 1.0616
No log 7.25 464 1.1008 0.4567 1.1008 1.0492
No log 7.2812 466 0.9910 0.3753 0.9910 0.9955
No log 7.3125 468 0.9712 0.3715 0.9712 0.9855
No log 7.3438 470 0.9722 0.3697 0.9722 0.9860
No log 7.375 472 0.9655 0.3463 0.9655 0.9826
No log 7.4062 474 0.9477 0.3353 0.9477 0.9735
No log 7.4375 476 0.9564 0.4217 0.9564 0.9780
No log 7.4688 478 0.9634 0.4217 0.9634 0.9815
No log 7.5 480 0.9474 0.3395 0.9474 0.9734
No log 7.5312 482 1.0691 0.4012 1.0691 1.0340
No log 7.5625 484 1.3057 0.3638 1.3057 1.1427
No log 7.5938 486 1.3837 0.3925 1.3837 1.1763
No log 7.625 488 1.2196 0.3863 1.2196 1.1043
No log 7.6562 490 1.0049 0.4281 1.0049 1.0025
No log 7.6875 492 0.9500 0.3166 0.9500 0.9747
No log 7.7188 494 0.9387 0.2813 0.9387 0.9689
No log 7.75 496 0.9539 0.3989 0.9539 0.9767
No log 7.7812 498 1.0110 0.4281 1.0110 1.0055
0.3509 7.8125 500 1.1845 0.4218 1.1845 1.0883
0.3509 7.8438 502 1.2571 0.4470 1.2571 1.1212
0.3509 7.875 504 1.1330 0.4603 1.1330 1.0644
0.3509 7.9062 506 0.9537 0.4825 0.9537 0.9766
0.3509 7.9375 508 0.8663 0.4112 0.8663 0.9308
0.3509 7.9688 510 0.8855 0.4509 0.8855 0.9410
0.3509 8.0 512 0.8665 0.4509 0.8665 0.9309
0.3509 8.0312 514 0.8508 0.4351 0.8508 0.9224
0.3509 8.0625 516 0.9767 0.4698 0.9767 0.9883
0.3509 8.0938 518 1.1052 0.4787 1.1052 1.0513
0.3509 8.125 520 1.1094 0.4672 1.1094 1.0533
0.3509 8.1562 522 1.0238 0.4408 1.0238 1.0118
0.3509 8.1875 524 0.9133 0.5036 0.9133 0.9557
0.3509 8.2188 526 0.9027 0.3813 0.9027 0.9501
0.3509 8.25 528 0.9149 0.3813 0.9149 0.9565
0.3509 8.2812 530 0.9445 0.4212 0.9445 0.9719
0.3509 8.3125 532 0.9647 0.4283 0.9647 0.9822
0.3509 8.3438 534 0.9510 0.4027 0.9510 0.9752
0.3509 8.375 536 0.9283 0.4247 0.9283 0.9635
0.3509 8.4062 538 0.9463 0.4524 0.9463 0.9728
0.3509 8.4375 540 0.9933 0.4520 0.9933 0.9967
0.3509 8.4688 542 0.9987 0.4550 0.9987 0.9993
0.3509 8.5 544 0.9443 0.4347 0.9443 0.9717
0.3509 8.5312 546 0.8996 0.3355 0.8996 0.9484
0.3509 8.5625 548 0.8909 0.3500 0.8909 0.9439
0.3509 8.5938 550 0.8890 0.4292 0.8890 0.9429
0.3509 8.625 552 0.9085 0.3250 0.9085 0.9532
0.3509 8.6562 554 0.9545 0.3418 0.9545 0.9770
0.3509 8.6875 556 1.0377 0.3237 1.0377 1.0187
0.3509 8.7188 558 1.1331 0.3513 1.1331 1.0645
0.3509 8.75 560 1.1114 0.4269 1.1114 1.0542
0.3509 8.7812 562 0.9816 0.4715 0.9816 0.9908
0.3509 8.8125 564 0.8908 0.4800 0.8908 0.9438
0.3509 8.8438 566 0.8833 0.4641 0.8833 0.9398
0.3509 8.875 568 0.8937 0.4681 0.8937 0.9453
0.3509 8.9062 570 0.9099 0.4425 0.9099 0.9539
0.3509 8.9375 572 0.9312 0.4212 0.9312 0.9650
0.3509 8.9688 574 0.9426 0.4212 0.9426 0.9709
0.3509 9.0 576 0.9795 0.3759 0.9795 0.9897
0.3509 9.0312 578 1.0382 0.3710 1.0382 1.0189
0.3509 9.0625 580 1.1010 0.4036 1.1010 1.0493

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_run2_AugV5_k13_task2_organization

Finetuned
(4032)
this model