MayBashendy's picture
Training in progress, step 500
16e21e8 verified
|
raw
history blame
22.3 kB
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_task2_organization
    results: []

ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_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: 0.5737
  • Qwk: 0.3877
  • Mse: 0.5737
  • Rmse: 0.7574

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 0.0253 2 4.3690 -0.0267 4.3690 2.0902
No log 0.0506 4 2.4003 0.0288 2.4003 1.5493
No log 0.0759 6 1.5507 -0.0787 1.5507 1.2453
No log 0.1013 8 1.0078 -0.0545 1.0078 1.0039
No log 0.1266 10 1.1063 0.0492 1.1063 1.0518
No log 0.1519 12 1.0854 0.0971 1.0854 1.0418
No log 0.1772 14 0.8576 0.1359 0.8576 0.9261
No log 0.2025 16 0.8127 0.1497 0.8127 0.9015
No log 0.2278 18 0.7885 0.1758 0.7885 0.8880
No log 0.2532 20 0.8173 0.1539 0.8173 0.9040
No log 0.2785 22 0.8129 0.1725 0.8129 0.9016
No log 0.3038 24 0.7687 0.2558 0.7687 0.8767
No log 0.3291 26 0.7662 0.1543 0.7662 0.8753
No log 0.3544 28 0.7731 0.1997 0.7731 0.8793
No log 0.3797 30 0.7848 0.1879 0.7848 0.8859
No log 0.4051 32 0.8358 0.1537 0.8358 0.9142
No log 0.4304 34 0.9089 0.0627 0.9089 0.9534
No log 0.4557 36 0.9320 0.0627 0.9320 0.9654
No log 0.4810 38 0.8017 0.2127 0.8017 0.8954
No log 0.5063 40 0.7716 0.2398 0.7716 0.8784
No log 0.5316 42 0.7756 0.2974 0.7756 0.8807
No log 0.5570 44 0.8389 0.2357 0.8389 0.9159
No log 0.5823 46 1.0205 0.1658 1.0205 1.0102
No log 0.6076 48 1.1705 0.2464 1.1705 1.0819
No log 0.6329 50 1.0921 0.2146 1.0921 1.0450
No log 0.6582 52 0.8905 0.2194 0.8905 0.9437
No log 0.6835 54 0.8647 0.3480 0.8647 0.9299
No log 0.7089 56 0.8326 0.2942 0.8326 0.9125
No log 0.7342 58 0.8088 0.2255 0.8088 0.8993
No log 0.7595 60 0.8053 0.2364 0.8053 0.8974
No log 0.7848 62 0.8461 0.2511 0.8461 0.9198
No log 0.8101 64 0.7570 0.3056 0.7570 0.8701
No log 0.8354 66 0.7653 0.4231 0.7653 0.8748
No log 0.8608 68 0.8311 0.3704 0.8311 0.9116
No log 0.8861 70 0.7841 0.4353 0.7841 0.8855
No log 0.9114 72 0.7408 0.4260 0.7408 0.8607
No log 0.9367 74 0.7833 0.3387 0.7833 0.8851
No log 0.9620 76 0.8651 0.3678 0.8651 0.9301
No log 0.9873 78 0.7570 0.4043 0.7570 0.8701
No log 1.0127 80 0.7696 0.3855 0.7696 0.8773
No log 1.0380 82 0.9747 0.2800 0.9747 0.9873
No log 1.0633 84 0.8854 0.3802 0.8854 0.9409
No log 1.0886 86 0.8619 0.4278 0.8619 0.9284
No log 1.1139 88 0.9360 0.4359 0.9360 0.9675
No log 1.1392 90 0.9941 0.4210 0.9941 0.9970
No log 1.1646 92 1.0775 0.4011 1.0775 1.0380
No log 1.1899 94 1.2781 0.3528 1.2781 1.1305
No log 1.2152 96 1.0740 0.4313 1.0740 1.0364
No log 1.2405 98 0.8126 0.4415 0.8126 0.9014
No log 1.2658 100 0.8656 0.3780 0.8656 0.9303
No log 1.2911 102 0.8439 0.3587 0.8439 0.9186
No log 1.3165 104 0.7168 0.4249 0.7168 0.8467
No log 1.3418 106 0.7328 0.4341 0.7328 0.8561
No log 1.3671 108 0.7535 0.4448 0.7535 0.8680
No log 1.3924 110 0.8559 0.4002 0.8559 0.9251
No log 1.4177 112 0.7682 0.4196 0.7682 0.8765
No log 1.4430 114 0.6411 0.4146 0.6411 0.8007
No log 1.4684 116 0.8461 0.2985 0.8461 0.9198
No log 1.4937 118 0.7944 0.3088 0.7944 0.8913
No log 1.5190 120 0.6731 0.4864 0.6731 0.8204
No log 1.5443 122 1.0100 0.3419 1.0100 1.0050
No log 1.5696 124 1.0416 0.3522 1.0416 1.0206
No log 1.5949 126 0.8210 0.4528 0.8210 0.9061
No log 1.6203 128 0.6653 0.4379 0.6653 0.8157
No log 1.6456 130 0.6673 0.4053 0.6673 0.8169
No log 1.6709 132 0.6429 0.4531 0.6429 0.8018
No log 1.6962 134 0.6987 0.4007 0.6987 0.8359
No log 1.7215 136 0.7376 0.4324 0.7376 0.8588
No log 1.7468 138 0.8040 0.4501 0.8040 0.8967
No log 1.7722 140 0.6968 0.4705 0.6968 0.8348
No log 1.7975 142 0.6730 0.4162 0.6730 0.8204
No log 1.8228 144 0.6791 0.4162 0.6791 0.8241
No log 1.8481 146 0.7661 0.5250 0.7661 0.8753
No log 1.8734 148 0.8381 0.4292 0.8381 0.9155
No log 1.8987 150 0.6994 0.4876 0.6994 0.8363
No log 1.9241 152 0.6785 0.3402 0.6785 0.8237
No log 1.9494 154 1.0417 0.3375 1.0417 1.0207
No log 1.9747 156 1.1164 0.3486 1.1164 1.0566
No log 2.0 158 0.8267 0.4026 0.8267 0.9093
No log 2.0253 160 0.6474 0.3550 0.6474 0.8046
No log 2.0506 162 0.6492 0.4991 0.6492 0.8057
No log 2.0759 164 0.6474 0.5061 0.6474 0.8046
No log 2.1013 166 0.6874 0.5017 0.6874 0.8291
No log 2.1266 168 0.6801 0.5258 0.6801 0.8247
No log 2.1519 170 0.6492 0.5305 0.6492 0.8058
No log 2.1772 172 0.8048 0.4589 0.8048 0.8971
No log 2.2025 174 0.8810 0.4111 0.8810 0.9386
No log 2.2278 176 0.7792 0.4507 0.7792 0.8827
No log 2.2532 178 0.6345 0.4911 0.6345 0.7965
No log 2.2785 180 0.6162 0.4850 0.6162 0.7850
No log 2.3038 182 0.6445 0.4914 0.6445 0.8028
No log 2.3291 184 0.5888 0.4512 0.5888 0.7673
No log 2.3544 186 0.6185 0.4892 0.6185 0.7864
No log 2.3797 188 0.8369 0.4515 0.8369 0.9148
No log 2.4051 190 0.8616 0.4515 0.8616 0.9282
No log 2.4304 192 0.6999 0.4369 0.6999 0.8366
No log 2.4557 194 0.5669 0.4588 0.5669 0.7529
No log 2.4810 196 0.7155 0.4612 0.7155 0.8459
No log 2.5063 198 0.9914 0.4019 0.9914 0.9957
No log 2.5316 200 1.0791 0.3746 1.0791 1.0388
No log 2.5570 202 0.9067 0.4111 0.9067 0.9522
No log 2.5823 204 0.6566 0.5233 0.6566 0.8103
No log 2.6076 206 0.6460 0.5037 0.6460 0.8037
No log 2.6329 208 0.7618 0.4817 0.7618 0.8728
No log 2.6582 210 0.7891 0.4817 0.7891 0.8883
No log 2.6835 212 0.7039 0.5065 0.7039 0.8390
No log 2.7089 214 0.6188 0.4893 0.6188 0.7866
No log 2.7342 216 0.6936 0.4375 0.6936 0.8328
No log 2.7595 218 0.7765 0.4536 0.7765 0.8812
No log 2.7848 220 0.7218 0.4547 0.7218 0.8496
No log 2.8101 222 0.6558 0.4558 0.6558 0.8098
No log 2.8354 224 0.6126 0.5100 0.6126 0.7827
No log 2.8608 226 0.5983 0.5254 0.5983 0.7735
No log 2.8861 228 0.5896 0.5314 0.5896 0.7678
No log 2.9114 230 0.5985 0.5080 0.5985 0.7737
No log 2.9367 232 0.6732 0.4524 0.6732 0.8205
No log 2.9620 234 0.7100 0.5002 0.7100 0.8426
No log 2.9873 236 0.6388 0.4727 0.6388 0.7993
No log 3.0127 238 0.5867 0.5209 0.5867 0.7659
No log 3.0380 240 0.6296 0.5019 0.6296 0.7935
No log 3.0633 242 0.7182 0.5288 0.7182 0.8474
No log 3.0886 244 0.7035 0.4269 0.7035 0.8388
No log 3.1139 246 0.6429 0.3951 0.6429 0.8018
No log 3.1392 248 0.6112 0.4800 0.6112 0.7818
No log 3.1646 250 0.6252 0.4159 0.6252 0.7907
No log 3.1899 252 0.6577 0.4773 0.6577 0.8110
No log 3.2152 254 0.6440 0.4912 0.6440 0.8025
No log 3.2405 256 0.6327 0.4928 0.6327 0.7954
No log 3.2658 258 0.6422 0.5076 0.6422 0.8014
No log 3.2911 260 0.6207 0.4629 0.6207 0.7879
No log 3.3165 262 0.6054 0.4196 0.6054 0.7781
No log 3.3418 264 0.6066 0.4705 0.6066 0.7789
No log 3.3671 266 0.6575 0.4772 0.6575 0.8109
No log 3.3924 268 0.7084 0.5133 0.7084 0.8417
No log 3.4177 270 0.6969 0.5554 0.6969 0.8348
No log 3.4430 272 0.6363 0.5026 0.6363 0.7977
No log 3.4684 274 0.5901 0.5385 0.5901 0.7682
No log 3.4937 276 0.5857 0.5053 0.5857 0.7653
No log 3.5190 278 0.6352 0.4399 0.6352 0.7970
No log 3.5443 280 0.6184 0.4883 0.6184 0.7864
No log 3.5696 282 0.6330 0.5148 0.6330 0.7956
No log 3.5949 284 0.6498 0.5372 0.6498 0.8061
No log 3.6203 286 0.7095 0.5332 0.7095 0.8423
No log 3.6456 288 0.6901 0.5435 0.6901 0.8307
No log 3.6709 290 0.6327 0.5561 0.6327 0.7955
No log 3.6962 292 0.6139 0.5738 0.6139 0.7835
No log 3.7215 294 0.6042 0.5443 0.6042 0.7773
No log 3.7468 296 0.6355 0.5378 0.6355 0.7972
No log 3.7722 298 0.7193 0.4946 0.7193 0.8481
No log 3.7975 300 0.6755 0.5656 0.6755 0.8219
No log 3.8228 302 0.6392 0.5564 0.6392 0.7995
No log 3.8481 304 0.5992 0.5630 0.5992 0.7741
No log 3.8734 306 0.5781 0.5549 0.5781 0.7603
No log 3.8987 308 0.5818 0.5539 0.5818 0.7627
No log 3.9241 310 0.6319 0.5362 0.6319 0.7949
No log 3.9494 312 0.7864 0.4674 0.7864 0.8868
No log 3.9747 314 0.9048 0.3891 0.9048 0.9512
No log 4.0 316 0.8968 0.3837 0.8968 0.9470
No log 4.0253 318 0.7795 0.4393 0.7795 0.8829
No log 4.0506 320 0.6356 0.5536 0.6356 0.7973
No log 4.0759 322 0.6250 0.5641 0.6250 0.7906
No log 4.1013 324 0.6526 0.5015 0.6526 0.8078
No log 4.1266 326 0.6440 0.5168 0.6440 0.8025
No log 4.1519 328 0.6588 0.5649 0.6588 0.8116
No log 4.1772 330 0.7618 0.5162 0.7618 0.8728
No log 4.2025 332 0.8426 0.4454 0.8426 0.9179
No log 4.2278 334 0.7616 0.4869 0.7616 0.8727
No log 4.2532 336 0.6672 0.4793 0.6672 0.8169
No log 4.2785 338 0.5970 0.5046 0.5970 0.7727
No log 4.3038 340 0.6017 0.5046 0.6017 0.7757
No log 4.3291 342 0.6801 0.5239 0.6801 0.8247
No log 4.3544 344 0.7281 0.4926 0.7281 0.8533
No log 4.3797 346 0.7052 0.5196 0.7052 0.8398
No log 4.4051 348 0.6871 0.5196 0.6871 0.8289
No log 4.4304 350 0.6958 0.5098 0.6958 0.8341
No log 4.4557 352 0.7277 0.5192 0.7277 0.8530
No log 4.4810 354 0.6973 0.4873 0.6973 0.8350
No log 4.5063 356 0.6797 0.5135 0.6797 0.8244
No log 4.5316 358 0.6776 0.5119 0.6776 0.8232
No log 4.5570 360 0.6876 0.4785 0.6876 0.8292
No log 4.5823 362 0.6517 0.4841 0.6517 0.8073
No log 4.6076 364 0.6083 0.5080 0.6083 0.7800
No log 4.6329 366 0.5823 0.4714 0.5823 0.7631
No log 4.6582 368 0.5717 0.4935 0.5717 0.7561
No log 4.6835 370 0.5748 0.5192 0.5748 0.7581
No log 4.7089 372 0.5976 0.5111 0.5976 0.7731
No log 4.7342 374 0.6140 0.5216 0.6140 0.7836
No log 4.7595 376 0.5954 0.5290 0.5954 0.7716
No log 4.7848 378 0.6063 0.4943 0.6063 0.7786
No log 4.8101 380 0.6789 0.4198 0.6789 0.8239
No log 4.8354 382 0.6693 0.4112 0.6693 0.8181
No log 4.8608 384 0.6002 0.4623 0.6002 0.7747
No log 4.8861 386 0.5789 0.5245 0.5789 0.7609
No log 4.9114 388 0.5847 0.5629 0.5847 0.7646
No log 4.9367 390 0.5899 0.5569 0.5899 0.7680
No log 4.9620 392 0.6024 0.5221 0.6024 0.7761
No log 4.9873 394 0.6407 0.4817 0.6407 0.8004
No log 5.0127 396 0.6464 0.4551 0.6464 0.8040
No log 5.0380 398 0.6061 0.5103 0.6061 0.7785
No log 5.0633 400 0.5914 0.5539 0.5914 0.7690
No log 5.0886 402 0.5904 0.5090 0.5904 0.7684
No log 5.1139 404 0.5731 0.5006 0.5731 0.7570
No log 5.1392 406 0.5675 0.4620 0.5675 0.7533
No log 5.1646 408 0.5727 0.5100 0.5727 0.7568
No log 5.1899 410 0.5861 0.5440 0.5861 0.7655
No log 5.2152 412 0.5981 0.5502 0.5981 0.7733
No log 5.2405 414 0.6077 0.5560 0.6077 0.7795
No log 5.2658 416 0.6620 0.5475 0.6620 0.8136
No log 5.2911 418 0.6702 0.5597 0.6702 0.8187
No log 5.3165 420 0.6206 0.5558 0.6206 0.7878
No log 5.3418 422 0.5930 0.5616 0.5930 0.7701
No log 5.3671 424 0.5959 0.5097 0.5959 0.7720
No log 5.3924 426 0.5906 0.5633 0.5906 0.7685
No log 5.4177 428 0.6191 0.5111 0.6191 0.7868
No log 5.4430 430 0.6444 0.4810 0.6444 0.8028
No log 5.4684 432 0.6630 0.4375 0.6630 0.8142
No log 5.4937 434 0.6562 0.4625 0.6562 0.8101
No log 5.5190 436 0.6228 0.4833 0.6228 0.7892
No log 5.5443 438 0.5701 0.5382 0.5701 0.7550
No log 5.5696 440 0.5881 0.4384 0.5881 0.7669
No log 5.5949 442 0.6408 0.4442 0.6408 0.8005
No log 5.6203 444 0.6268 0.4747 0.6268 0.7917
No log 5.6456 446 0.5914 0.5323 0.5914 0.7690
No log 5.6709 448 0.6275 0.5661 0.6275 0.7921
No log 5.6962 450 0.6294 0.5600 0.6294 0.7934
No log 5.7215 452 0.5861 0.5774 0.5861 0.7656
No log 5.7468 454 0.5718 0.5156 0.5718 0.7562
No log 5.7722 456 0.5758 0.4657 0.5758 0.7588
No log 5.7975 458 0.5800 0.4573 0.5800 0.7616
No log 5.8228 460 0.6208 0.4773 0.6208 0.7879
No log 5.8481 462 0.6354 0.4564 0.6354 0.7971
No log 5.8734 464 0.6435 0.4393 0.6435 0.8022
No log 5.8987 466 0.6906 0.4237 0.6906 0.8310
No log 5.9241 468 0.7598 0.4148 0.7598 0.8717
No log 5.9494 470 0.7457 0.4320 0.7457 0.8635
No log 5.9747 472 0.7141 0.4559 0.7141 0.8450
No log 6.0 474 0.6083 0.4745 0.6083 0.7799
No log 6.0253 476 0.6253 0.5565 0.6253 0.7908
No log 6.0506 478 0.6563 0.5719 0.6563 0.8101
No log 6.0759 480 0.6364 0.5869 0.6364 0.7978
No log 6.1013 482 0.6279 0.4892 0.6279 0.7924
No log 6.1266 484 0.6431 0.4654 0.6431 0.8019
No log 6.1519 486 0.6719 0.4531 0.6719 0.8197
No log 6.1772 488 0.6527 0.4728 0.6527 0.8079
No log 6.2025 490 0.6285 0.4765 0.6285 0.7928
No log 6.2278 492 0.6124 0.4556 0.6124 0.7826
No log 6.2532 494 0.6047 0.4431 0.6047 0.7776
No log 6.2785 496 0.6152 0.4866 0.6152 0.7844
No log 6.3038 498 0.6106 0.4786 0.6106 0.7814
0.3637 6.3291 500 0.5979 0.4868 0.5979 0.7732
0.3637 6.3544 502 0.5981 0.5076 0.5981 0.7734
0.3637 6.3797 504 0.5825 0.4899 0.5825 0.7632
0.3637 6.4051 506 0.5805 0.4886 0.5805 0.7619
0.3637 6.4304 508 0.5750 0.5160 0.5750 0.7583
0.3637 6.4557 510 0.5761 0.5198 0.5761 0.7590
0.3637 6.4810 512 0.6370 0.4833 0.6370 0.7981
0.3637 6.5063 514 0.7102 0.4531 0.7102 0.8427
0.3637 6.5316 516 0.6860 0.4538 0.6860 0.8282
0.3637 6.5570 518 0.5986 0.3838 0.5986 0.7737
0.3637 6.5823 520 0.5737 0.3877 0.5737 0.7574

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1