MayBashendy's picture
Training in progress, step 500
8018d36 verified
|
raw
history blame
21.7 kB
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_task1_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: 0.8033
  • Qwk: 0.7105
  • Mse: 0.8033
  • Rmse: 0.8963

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 0.0179 2 7.0692 0.0290 7.0692 2.6588
No log 0.0357 4 4.1574 0.1053 4.1574 2.0390
No log 0.0536 6 2.5318 0.0870 2.5318 1.5912
No log 0.0714 8 1.8752 0.2276 1.8752 1.3694
No log 0.0893 10 1.6967 0.2689 1.6967 1.3026
No log 0.1071 12 1.5431 0.1835 1.5431 1.2422
No log 0.125 14 1.4600 0.2456 1.4600 1.2083
No log 0.1429 16 1.4900 0.3279 1.4900 1.2207
No log 0.1607 18 1.6387 0.4211 1.6387 1.2801
No log 0.1786 20 1.0393 0.4923 1.0393 1.0195
No log 0.1964 22 1.2822 0.4882 1.2822 1.1324
No log 0.2143 24 1.5578 0.3559 1.5578 1.2481
No log 0.2321 26 1.4560 0.3304 1.4560 1.2066
No log 0.25 28 1.2691 0.3684 1.2691 1.1266
No log 0.2679 30 1.1808 0.4463 1.1808 1.0867
No log 0.2857 32 1.4781 0.4828 1.4781 1.2158
No log 0.3036 34 1.5579 0.4837 1.5579 1.2482
No log 0.3214 36 1.1682 0.6309 1.1682 1.0808
No log 0.3393 38 0.8417 0.6809 0.8417 0.9174
No log 0.3571 40 0.9560 0.6620 0.9560 0.9777
No log 0.375 42 1.2008 0.4895 1.2008 1.0958
No log 0.3929 44 1.2513 0.4722 1.2513 1.1186
No log 0.4107 46 1.1753 0.5143 1.1753 1.0841
No log 0.4286 48 1.1084 0.5821 1.1084 1.0528
No log 0.4464 50 1.1309 0.5926 1.1309 1.0634
No log 0.4643 52 1.0382 0.6575 1.0382 1.0189
No log 0.4821 54 1.1589 0.5974 1.1589 1.0765
No log 0.5 56 1.5396 0.5422 1.5396 1.2408
No log 0.5179 58 1.3346 0.5375 1.3346 1.1552
No log 0.5357 60 0.9809 0.5921 0.9809 0.9904
No log 0.5536 62 0.8371 0.6622 0.8371 0.9149
No log 0.5714 64 0.8265 0.7273 0.8265 0.9091
No log 0.5893 66 0.9889 0.6232 0.9889 0.9945
No log 0.6071 68 1.0932 0.5970 1.0932 1.0455
No log 0.625 70 1.0503 0.6043 1.0503 1.0248
No log 0.6429 72 1.0452 0.5874 1.0452 1.0223
No log 0.6607 74 1.0060 0.5986 1.0060 1.0030
No log 0.6786 76 0.8557 0.6986 0.8557 0.9250
No log 0.6964 78 0.9999 0.6176 0.9999 1.0000
No log 0.7143 80 1.1681 0.4252 1.1681 1.0808
No log 0.7321 82 0.9668 0.6619 0.9668 0.9833
No log 0.75 84 0.8337 0.6667 0.8337 0.9131
No log 0.7679 86 0.9275 0.7073 0.9275 0.9631
No log 0.7857 88 0.9425 0.6538 0.9425 0.9708
No log 0.8036 90 0.9628 0.6531 0.9628 0.9812
No log 0.8214 92 1.0699 0.5957 1.0699 1.0343
No log 0.8393 94 0.9829 0.6176 0.9829 0.9914
No log 0.8571 96 0.8777 0.6479 0.8777 0.9369
No log 0.875 98 0.7797 0.7075 0.7797 0.8830
No log 0.8929 100 0.7751 0.7133 0.7751 0.8804
No log 0.9107 102 0.8517 0.6389 0.8517 0.9229
No log 0.9286 104 1.0168 0.6944 1.0168 1.0083
No log 0.9464 106 1.1986 0.5694 1.1986 1.0948
No log 0.9643 108 1.0878 0.6207 1.0878 1.0430
No log 0.9821 110 0.8883 0.6577 0.8883 0.9425
No log 1.0 112 0.8210 0.7285 0.8210 0.9061
No log 1.0179 114 0.7821 0.7067 0.7821 0.8844
No log 1.0357 116 0.8000 0.6974 0.8000 0.8944
No log 1.0536 118 1.0201 0.6626 1.0201 1.0100
No log 1.0714 120 1.1889 0.5868 1.1889 1.0904
No log 1.0893 122 1.0592 0.6420 1.0592 1.0292
No log 1.1071 124 0.9041 0.65 0.9041 0.9508
No log 1.125 126 0.9323 0.7241 0.9323 0.9656
No log 1.1429 128 1.0110 0.7243 1.0110 1.0055
No log 1.1607 130 1.0626 0.7083 1.0626 1.0308
No log 1.1786 132 1.1186 0.6848 1.1186 1.0576
No log 1.1964 134 1.1331 0.6703 1.1331 1.0645
No log 1.2143 136 1.0484 0.6588 1.0484 1.0239
No log 1.2321 138 1.1404 0.6272 1.1404 1.0679
No log 1.25 140 1.0964 0.6310 1.0964 1.0471
No log 1.2679 142 0.9691 0.6341 0.9691 0.9844
No log 1.2857 144 0.9084 0.7073 0.9084 0.9531
No log 1.3036 146 1.0605 0.6353 1.0605 1.0298
No log 1.3214 148 1.3467 0.6047 1.3467 1.1605
No log 1.3393 150 1.4350 0.5625 1.4350 1.1979
No log 1.3571 152 1.2285 0.5325 1.2285 1.1084
No log 1.375 154 0.9576 0.6383 0.9576 0.9786
No log 1.3929 156 0.8912 0.6809 0.8912 0.9440
No log 1.4107 158 0.9577 0.6531 0.9577 0.9786
No log 1.4286 160 1.0655 0.6076 1.0655 1.0322
No log 1.4464 162 0.9949 0.5974 0.9949 0.9975
No log 1.4643 164 0.9234 0.6835 0.9234 0.9609
No log 1.4821 166 0.8885 0.7066 0.8885 0.9426
No log 1.5 168 0.9899 0.6851 0.9899 0.9950
No log 1.5179 170 1.1720 0.6264 1.1720 1.0826
No log 1.5357 172 1.0951 0.5939 1.0951 1.0465
No log 1.5536 174 1.0808 0.6460 1.0808 1.0396
No log 1.5714 176 1.0237 0.6081 1.0237 1.0118
No log 1.5893 178 0.9893 0.6471 0.9893 0.9946
No log 1.6071 180 1.0784 0.6184 1.0784 1.0384
No log 1.625 182 1.1831 0.6154 1.1831 1.0877
No log 1.6429 184 1.1546 0.6154 1.1546 1.0745
No log 1.6607 186 0.9932 0.6708 0.9932 0.9966
No log 1.6786 188 0.8709 0.6846 0.8709 0.9332
No log 1.6964 190 0.7765 0.7532 0.7765 0.8812
No log 1.7143 192 0.7771 0.7532 0.7771 0.8815
No log 1.7321 194 0.9044 0.7117 0.9044 0.9510
No log 1.75 196 1.1437 0.6409 1.1437 1.0694
No log 1.7679 198 1.0917 0.6556 1.0917 1.0448
No log 1.7857 200 0.9767 0.6626 0.9767 0.9883
No log 1.8036 202 0.8497 0.7285 0.8497 0.9218
No log 1.8214 204 0.8482 0.6714 0.8482 0.9210
No log 1.8393 206 0.8927 0.6812 0.8927 0.9449
No log 1.8571 208 1.0477 0.6154 1.0477 1.0236
No log 1.875 210 1.1982 0.6047 1.1982 1.0946
No log 1.8929 212 1.1300 0.6552 1.1300 1.0630
No log 1.9107 214 0.8790 0.7073 0.8790 0.9376
No log 1.9286 216 0.7010 0.7771 0.7010 0.8372
No log 1.9464 218 0.6779 0.7692 0.6779 0.8233
No log 1.9643 220 0.7233 0.7662 0.7233 0.8505
No log 1.9821 222 0.8459 0.7051 0.8459 0.9197
No log 2.0 224 0.8773 0.7020 0.8773 0.9366
No log 2.0179 226 0.8465 0.7285 0.8465 0.9201
No log 2.0357 228 0.7425 0.7467 0.7425 0.8617
No log 2.0536 230 0.7274 0.7105 0.7274 0.8529
No log 2.0714 232 0.7615 0.7320 0.7615 0.8726
No log 2.0893 234 0.8968 0.7283 0.8968 0.9470
No log 2.1071 236 0.9328 0.7381 0.9328 0.9658
No log 2.125 238 0.9057 0.7067 0.9057 0.9517
No log 2.1429 240 0.9498 0.6389 0.9498 0.9746
No log 2.1607 242 0.9999 0.6027 0.9999 0.9999
No log 2.1786 244 0.9814 0.6043 0.9814 0.9907
No log 2.1964 246 0.9734 0.6418 0.9734 0.9866
No log 2.2143 248 1.0053 0.6277 1.0053 1.0027
No log 2.2321 250 1.0217 0.6040 1.0217 1.0108
No log 2.25 252 1.0977 0.6024 1.0977 1.0477
No log 2.2679 254 1.1427 0.5952 1.1427 1.0690
No log 2.2857 256 1.1740 0.6118 1.1740 1.0835
No log 2.3036 258 1.0900 0.6272 1.0900 1.0440
No log 2.3214 260 0.9967 0.6667 0.9967 0.9983
No log 2.3393 262 0.9220 0.6203 0.9220 0.9602
No log 2.3571 264 0.8856 0.7160 0.8856 0.9410
No log 2.375 266 0.7902 0.7403 0.7902 0.8889
No log 2.3929 268 0.7527 0.7625 0.7527 0.8676
No log 2.4107 270 0.8106 0.7458 0.8106 0.9003
No log 2.4286 272 1.0337 0.7273 1.0337 1.0167
No log 2.4464 274 1.0115 0.7579 1.0115 1.0057
No log 2.4643 276 0.8576 0.7081 0.8576 0.9261
No log 2.4821 278 0.8394 0.7179 0.8394 0.9162
No log 2.5 280 0.9278 0.6452 0.9278 0.9632
No log 2.5179 282 0.9965 0.6667 0.9965 0.9982
No log 2.5357 284 1.2587 0.6186 1.2587 1.1219
No log 2.5536 286 1.2133 0.5978 1.2133 1.1015
No log 2.5714 288 0.9821 0.6835 0.9821 0.9910
No log 2.5893 290 0.8502 0.7383 0.8502 0.9221
No log 2.6071 292 0.8478 0.75 0.8478 0.9208
No log 2.625 294 0.9359 0.7195 0.9359 0.9674
No log 2.6429 296 1.0299 0.6556 1.0299 1.0148
No log 2.6607 298 1.0466 0.6556 1.0466 1.0230
No log 2.6786 300 1.1088 0.6556 1.1088 1.0530
No log 2.6964 302 1.1680 0.6413 1.1680 1.0807
No log 2.7143 304 1.0561 0.6784 1.0561 1.0277
No log 2.7321 306 0.9354 0.7432 0.9354 0.9672
No log 2.75 308 0.9109 0.7183 0.9109 0.9544
No log 2.7679 310 0.8985 0.7355 0.8985 0.9479
No log 2.7857 312 0.8168 0.7484 0.8168 0.9038
No log 2.8036 314 0.8011 0.7702 0.8011 0.8951
No log 2.8214 316 0.8438 0.7529 0.8438 0.9186
No log 2.8393 318 1.0111 0.7263 1.0111 1.0055
No log 2.8571 320 1.3065 0.6146 1.3065 1.1430
No log 2.875 322 1.3572 0.5905 1.3572 1.1650
No log 2.8929 324 1.1395 0.6702 1.1395 1.0675
No log 2.9107 326 1.0308 0.6591 1.0308 1.0153
No log 2.9286 328 0.9712 0.6707 0.9712 0.9855
No log 2.9464 330 0.9833 0.6824 0.9833 0.9916
No log 2.9643 332 1.0393 0.6739 1.0393 1.0195
No log 2.9821 334 1.0743 0.6842 1.0743 1.0365
No log 3.0 336 1.0319 0.6932 1.0319 1.0158
No log 3.0179 338 1.0766 0.6552 1.0766 1.0376
No log 3.0357 340 1.0338 0.6587 1.0338 1.0167
No log 3.0536 342 0.9316 0.6835 0.9316 0.9652
No log 3.0714 344 0.8136 0.7347 0.8136 0.9020
No log 3.0893 346 0.7881 0.7516 0.7881 0.8878
No log 3.1071 348 0.7598 0.7407 0.7598 0.8717
No log 3.125 350 0.7927 0.7368 0.7927 0.8903
No log 3.1429 352 0.7632 0.7886 0.7632 0.8736
No log 3.1607 354 0.7183 0.7882 0.7183 0.8475
No log 3.1786 356 0.6946 0.7811 0.6946 0.8334
No log 3.1964 358 0.7320 0.7841 0.7320 0.8555
No log 3.2143 360 0.8528 0.7553 0.8528 0.9235
No log 3.2321 362 0.8944 0.7380 0.8944 0.9457
No log 3.25 364 0.8954 0.6905 0.8954 0.9462
No log 3.2679 366 0.9645 0.6786 0.9645 0.9821
No log 3.2857 368 1.0302 0.6471 1.0302 1.0150
No log 3.3036 370 1.0323 0.6509 1.0323 1.0160
No log 3.3214 372 0.9326 0.6842 0.9326 0.9657
No log 3.3393 374 0.8577 0.7027 0.8577 0.9261
No log 3.3571 376 0.8081 0.7260 0.8081 0.8990
No log 3.375 378 0.7742 0.7211 0.7742 0.8799
No log 3.3929 380 0.7897 0.7403 0.7897 0.8887
No log 3.4107 382 0.8103 0.7407 0.8103 0.9002
No log 3.4286 384 0.8122 0.7368 0.8122 0.9012
No log 3.4464 386 0.7503 0.7857 0.7503 0.8662
No log 3.4643 388 0.7171 0.8 0.7171 0.8468
No log 3.4821 390 0.7430 0.7683 0.7430 0.8620
No log 3.5 392 0.7633 0.7439 0.7633 0.8736
No log 3.5179 394 0.8321 0.7059 0.8321 0.9122
No log 3.5357 396 0.8466 0.7176 0.8466 0.9201
No log 3.5536 398 0.9649 0.7 0.9649 0.9823
No log 3.5714 400 1.0499 0.6776 1.0499 1.0246
No log 3.5893 402 1.0078 0.6587 1.0078 1.0039
No log 3.6071 404 1.0461 0.6463 1.0461 1.0228
No log 3.625 406 0.9749 0.6792 0.9749 0.9874
No log 3.6429 408 0.8030 0.6897 0.8030 0.8961
No log 3.6607 410 0.7392 0.6857 0.7392 0.8598
No log 3.6786 412 0.7389 0.6993 0.7389 0.8596
No log 3.6964 414 0.8146 0.7215 0.8146 0.9025
No log 3.7143 416 1.0191 0.6957 1.0191 1.0095
No log 3.7321 418 1.1366 0.6409 1.1366 1.0661
No log 3.75 420 1.0853 0.6275 1.0853 1.0418
No log 3.7679 422 1.0220 0.6667 1.0220 1.0109
No log 3.7857 424 0.9255 0.6849 0.9255 0.9620
No log 3.8036 426 0.8933 0.7097 0.8933 0.9452
No log 3.8214 428 0.9713 0.6548 0.9713 0.9856
No log 3.8393 430 0.9895 0.6595 0.9895 0.9947
No log 3.8571 432 1.0042 0.6595 1.0042 1.0021
No log 3.875 434 0.9775 0.6550 0.9775 0.9887
No log 3.8929 436 1.0521 0.6316 1.0521 1.0257
No log 3.9107 438 1.1280 0.6409 1.1280 1.0621
No log 3.9286 440 1.1044 0.6433 1.1044 1.0509
No log 3.9464 442 1.0860 0.6429 1.0860 1.0421
No log 3.9643 444 1.0181 0.6386 1.0181 1.0090
No log 3.9821 446 0.9526 0.6627 0.9526 0.9760
No log 4.0 448 0.8881 0.7421 0.8881 0.9424
No log 4.0179 450 0.9283 0.7079 0.9283 0.9635
No log 4.0357 452 1.0298 0.6557 1.0298 1.0148
No log 4.0536 454 1.1783 0.6736 1.1783 1.0855
No log 4.0714 456 1.2438 0.6162 1.2438 1.1152
No log 4.0893 458 1.0635 0.6753 1.0635 1.0313
No log 4.1071 460 0.9782 0.6812 0.9782 0.9891
No log 4.125 462 0.9827 0.6812 0.9827 0.9913
No log 4.1429 464 0.9920 0.6812 0.9920 0.9960
No log 4.1607 466 1.0414 0.6713 1.0414 1.0205
No log 4.1786 468 0.9863 0.6712 0.9863 0.9931
No log 4.1964 470 0.9939 0.6846 0.9939 0.9969
No log 4.2143 472 1.0790 0.6548 1.0790 1.0387
No log 4.2321 474 1.0321 0.6585 1.0321 1.0159
No log 4.25 476 0.9181 0.7152 0.9181 0.9582
No log 4.2679 478 0.8282 0.72 0.8282 0.9101
No log 4.2857 480 0.7953 0.7355 0.7953 0.8918
No log 4.3036 482 0.8073 0.7453 0.8073 0.8985
No log 4.3214 484 0.8607 0.7314 0.8607 0.9277
No log 4.3393 486 0.9328 0.6854 0.9328 0.9658
No log 4.3571 488 1.0499 0.6816 1.0499 1.0247
No log 4.375 490 0.8771 0.7143 0.8771 0.9366
No log 4.3929 492 0.7285 0.7296 0.7285 0.8535
No log 4.4107 494 0.6230 0.76 0.6230 0.7893
No log 4.4286 496 0.5915 0.7733 0.5915 0.7691
No log 4.4464 498 0.6233 0.7712 0.6233 0.7895
0.4386 4.4643 500 0.8193 0.7412 0.8193 0.9051
0.4386 4.4821 502 1.1280 0.6907 1.1280 1.0621
0.4386 4.5 504 1.2010 0.6528 1.2010 1.0959
0.4386 4.5179 506 1.0706 0.6971 1.0706 1.0347
0.4386 4.5357 508 0.8758 0.6875 0.8758 0.9359
0.4386 4.5536 510 0.8033 0.7105 0.8033 0.8963

Framework versions

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