MayBashendy's picture
End of training
1eb752e verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k6_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k6_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: 0.7286
  • Qwk: 0.7324
  • Mse: 0.7286
  • Rmse: 0.8536

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 0.0444 2 6.9644 0.0176 6.9644 2.6390
No log 0.0889 4 5.8466 0.0 5.8466 2.4180
No log 0.1333 6 4.0278 0.0463 4.0278 2.0069
No log 0.1778 8 2.4333 0.0397 2.4333 1.5599
No log 0.2222 10 2.0316 0.2362 2.0316 1.4253
No log 0.2667 12 1.9618 0.1818 1.9618 1.4007
No log 0.3111 14 1.7897 0.1802 1.7897 1.3378
No log 0.3556 16 1.5391 0.1905 1.5391 1.2406
No log 0.4 18 1.3842 0.2936 1.3842 1.1765
No log 0.4444 20 1.3014 0.3793 1.3014 1.1408
No log 0.4889 22 1.3804 0.3363 1.3804 1.1749
No log 0.5333 24 1.5698 0.2037 1.5698 1.2529
No log 0.5778 26 1.4992 0.2435 1.4992 1.2244
No log 0.6222 28 1.4635 0.2975 1.4635 1.2098
No log 0.6667 30 1.3058 0.4590 1.3058 1.1427
No log 0.7111 32 1.1304 0.5366 1.1304 1.0632
No log 0.7556 34 1.1350 0.4500 1.1350 1.0653
No log 0.8 36 1.1498 0.4918 1.1498 1.0723
No log 0.8444 38 1.2305 0.5203 1.2305 1.1093
No log 0.8889 40 1.2776 0.4677 1.2776 1.1303
No log 0.9333 42 1.2250 0.48 1.2250 1.1068
No log 0.9778 44 1.1126 0.5625 1.1126 1.0548
No log 1.0222 46 1.0170 0.6154 1.0170 1.0085
No log 1.0667 48 0.9202 0.6515 0.9202 0.9593
No log 1.1111 50 1.1188 0.5373 1.1188 1.0577
No log 1.1556 52 1.1988 0.5152 1.1988 1.0949
No log 1.2 54 0.8932 0.6567 0.8932 0.9451
No log 1.2444 56 0.9428 0.6759 0.9428 0.9710
No log 1.2889 58 0.9322 0.6800 0.9322 0.9655
No log 1.3333 60 0.7825 0.7123 0.7825 0.8846
No log 1.3778 62 0.7269 0.7 0.7269 0.8526
No log 1.4222 64 0.7431 0.6765 0.7431 0.8621
No log 1.4667 66 0.8332 0.6269 0.8332 0.9128
No log 1.5111 68 0.8648 0.6619 0.8648 0.9299
No log 1.5556 70 0.8772 0.6812 0.8772 0.9366
No log 1.6 72 0.9398 0.6277 0.9398 0.9694
No log 1.6444 74 0.9532 0.6131 0.9532 0.9763
No log 1.6889 76 0.8581 0.6569 0.8581 0.9263
No log 1.7333 78 0.8617 0.6618 0.8617 0.9283
No log 1.7778 80 0.8907 0.6043 0.8907 0.9438
No log 1.8222 82 0.8763 0.6853 0.8763 0.9361
No log 1.8667 84 0.8664 0.6853 0.8664 0.9308
No log 1.9111 86 0.8817 0.6803 0.8817 0.9390
No log 1.9556 88 0.9417 0.6832 0.9417 0.9704
No log 2.0 90 0.9791 0.6667 0.9791 0.9895
No log 2.0444 92 0.8689 0.6761 0.8689 0.9321
No log 2.0889 94 0.7904 0.6963 0.7904 0.8891
No log 2.1333 96 0.8708 0.6370 0.8708 0.9332
No log 2.1778 98 0.8485 0.6466 0.8485 0.9211
No log 2.2222 100 0.8387 0.6618 0.8387 0.9158
No log 2.2667 102 0.8828 0.7117 0.8828 0.9395
No log 2.3111 104 0.9541 0.6548 0.9541 0.9768
No log 2.3556 106 0.8440 0.6623 0.8440 0.9187
No log 2.4 108 0.8373 0.7143 0.8373 0.9150
No log 2.4444 110 0.8234 0.7105 0.8234 0.9074
No log 2.4889 112 0.7893 0.7211 0.7893 0.8884
No log 2.5333 114 0.7194 0.7246 0.7194 0.8482
No log 2.5778 116 0.8284 0.6423 0.8284 0.9101
No log 2.6222 118 0.9813 0.5828 0.9813 0.9906
No log 2.6667 120 0.8983 0.7205 0.8983 0.9478
No log 2.7111 122 0.6855 0.7805 0.6855 0.8279
No log 2.7556 124 0.6111 0.7949 0.6111 0.7817
No log 2.8 126 0.6520 0.7564 0.6520 0.8075
No log 2.8444 128 0.6573 0.7564 0.6573 0.8108
No log 2.8889 130 0.7003 0.7582 0.7003 0.8368
No log 2.9333 132 0.7462 0.7260 0.7462 0.8638
No log 2.9778 134 0.9926 0.6846 0.9926 0.9963
No log 3.0222 136 1.1790 0.6133 1.1790 1.0858
No log 3.0667 138 1.1620 0.5733 1.1620 1.0780
No log 3.1111 140 0.9575 0.5942 0.9575 0.9785
No log 3.1556 142 0.8443 0.6963 0.8443 0.9188
No log 3.2 144 0.7929 0.7194 0.7929 0.8905
No log 3.2444 146 0.8021 0.7111 0.8021 0.8956
No log 3.2889 148 0.9820 0.5755 0.9820 0.9909
No log 3.3333 150 1.0694 0.5946 1.0694 1.0341
No log 3.3778 152 0.9193 0.6043 0.9193 0.9588
No log 3.4222 154 0.7319 0.7413 0.7319 0.8555
No log 3.4667 156 0.7342 0.7619 0.7342 0.8568
No log 3.5111 158 0.7317 0.7294 0.7317 0.8554
No log 3.5556 160 0.7380 0.7081 0.7380 0.8591
No log 3.6 162 0.7271 0.7711 0.7271 0.8527
No log 3.6444 164 0.6277 0.7826 0.6277 0.7923
No log 3.6889 166 0.5287 0.7871 0.5287 0.7271
No log 3.7333 168 0.5819 0.7639 0.5819 0.7628
No log 3.7778 170 0.5978 0.7770 0.5978 0.7732
No log 3.8222 172 0.7146 0.6986 0.7146 0.8454
No log 3.8667 174 0.7448 0.7105 0.7448 0.8630
No log 3.9111 176 0.7104 0.7042 0.7104 0.8429
No log 3.9556 178 0.5891 0.75 0.5891 0.7675
No log 4.0 180 0.5794 0.7297 0.5794 0.7612
No log 4.0444 182 0.5983 0.7595 0.5983 0.7735
No log 4.0889 184 0.6384 0.7485 0.6384 0.7990
No log 4.1333 186 0.7121 0.7229 0.7121 0.8438
No log 4.1778 188 0.6825 0.6806 0.6825 0.8261
No log 4.2222 190 0.7016 0.7050 0.7016 0.8376
No log 4.2667 192 0.7329 0.7143 0.7329 0.8561
No log 4.3111 194 0.7223 0.6759 0.7223 0.8499
No log 4.3556 196 0.7027 0.7545 0.7027 0.8383
No log 4.4 198 0.7252 0.7394 0.7252 0.8516
No log 4.4444 200 0.7440 0.7170 0.7440 0.8626
No log 4.4889 202 0.7155 0.6980 0.7155 0.8459
No log 4.5333 204 0.7180 0.7286 0.7180 0.8473
No log 4.5778 206 0.6719 0.7413 0.6719 0.8197
No log 4.6222 208 0.6452 0.7413 0.6452 0.8032
No log 4.6667 210 0.6789 0.7552 0.6789 0.8240
No log 4.7111 212 0.8317 0.6815 0.8317 0.9120
No log 4.7556 214 0.9312 0.5857 0.9312 0.9650
No log 4.8 216 0.8168 0.6667 0.8168 0.9038
No log 4.8444 218 0.6820 0.7413 0.6820 0.8259
No log 4.8889 220 0.6381 0.7413 0.6381 0.7988
No log 4.9333 222 0.6679 0.7568 0.6679 0.8173
No log 4.9778 224 0.6895 0.7297 0.6895 0.8303
No log 5.0222 226 0.6469 0.7273 0.6469 0.8043
No log 5.0667 228 0.6586 0.7273 0.6586 0.8116
No log 5.1111 230 0.7071 0.7092 0.7071 0.8409
No log 5.1556 232 0.7129 0.7613 0.7129 0.8443
No log 5.2 234 0.7450 0.7784 0.7450 0.8632
No log 5.2444 236 0.8188 0.7412 0.8188 0.9049
No log 5.2889 238 0.8002 0.7558 0.8002 0.8945
No log 5.3333 240 0.6693 0.7771 0.6693 0.8181
No log 5.3778 242 0.6102 0.7815 0.6102 0.7811
No log 5.4222 244 0.6305 0.7886 0.6305 0.7941
No log 5.4667 246 0.7360 0.7816 0.7360 0.8579
No log 5.5111 248 0.8211 0.7442 0.8211 0.9062
No log 5.5556 250 0.8022 0.7442 0.8022 0.8956
No log 5.6 252 0.7178 0.7665 0.7178 0.8472
No log 5.6444 254 0.7524 0.7456 0.7524 0.8674
No log 5.6889 256 0.9671 0.6629 0.9671 0.9834
No log 5.7333 258 0.9968 0.6630 0.9968 0.9984
No log 5.7778 260 0.8569 0.6577 0.8569 0.9257
No log 5.8222 262 0.7360 0.7164 0.7360 0.8579
No log 5.8667 264 0.6835 0.7445 0.6835 0.8267
No log 5.9111 266 0.6811 0.7391 0.6811 0.8253
No log 5.9556 268 0.6582 0.7391 0.6582 0.8113
No log 6.0 270 0.7265 0.7273 0.7265 0.8524
No log 6.0444 272 0.9302 0.65 0.9302 0.9645
No log 6.0889 274 0.9882 0.6463 0.9882 0.9941
No log 6.1333 276 0.8488 0.6713 0.8488 0.9213
No log 6.1778 278 0.7591 0.6619 0.7591 0.8713
No log 6.2222 280 0.6992 0.7101 0.6992 0.8362
No log 6.2667 282 0.7180 0.7361 0.7180 0.8473
No log 6.3111 284 0.8310 0.6905 0.8310 0.9116
No log 6.3556 286 0.7521 0.7619 0.7521 0.8673
No log 6.4 288 0.6129 0.8050 0.6129 0.7829
No log 6.4444 290 0.5031 0.7733 0.5031 0.7093
No log 6.4889 292 0.4980 0.8 0.4980 0.7057
No log 6.5333 294 0.4949 0.7895 0.4949 0.7035
No log 6.5778 296 0.5210 0.7949 0.5210 0.7218
No log 6.6222 298 0.7239 0.8023 0.7239 0.8508
No log 6.6667 300 1.0043 0.7143 1.0043 1.0022
No log 6.7111 302 1.0954 0.6701 1.0954 1.0466
No log 6.7556 304 0.9581 0.7083 0.9581 0.9788
No log 6.8 306 0.6942 0.7702 0.6942 0.8332
No log 6.8444 308 0.5785 0.7429 0.5785 0.7606
No log 6.8889 310 0.5941 0.7536 0.5941 0.7708
No log 6.9333 312 0.5905 0.7626 0.5905 0.7684
No log 6.9778 314 0.6186 0.7639 0.6186 0.7865
No log 7.0222 316 0.7591 0.7162 0.7591 0.8713
No log 7.0667 318 0.8375 0.6839 0.8375 0.9151
No log 7.1111 320 0.7892 0.6933 0.7892 0.8883
No log 7.1556 322 0.6434 0.7376 0.6434 0.8021
No log 7.2 324 0.6012 0.7482 0.6012 0.7754
No log 7.2444 326 0.6189 0.7660 0.6189 0.7867
No log 7.2889 328 0.6699 0.76 0.6699 0.8185
No log 7.3333 330 0.6419 0.8176 0.6419 0.8012
No log 7.3778 332 0.5733 0.8101 0.5733 0.7572
No log 7.4222 334 0.5893 0.8101 0.5893 0.7677
No log 7.4667 336 0.6595 0.7975 0.6595 0.8121
No log 7.5111 338 0.7545 0.7514 0.7545 0.8686
No log 7.5556 340 0.7228 0.7514 0.7228 0.8502
No log 7.6 342 0.6614 0.7368 0.6614 0.8133
No log 7.6444 344 0.6248 0.7867 0.6248 0.7905
No log 7.6889 346 0.5947 0.7755 0.5947 0.7712
No log 7.7333 348 0.6049 0.7785 0.6049 0.7778
No log 7.7778 350 0.6631 0.7226 0.6631 0.8143
No log 7.8222 352 0.7567 0.7305 0.7567 0.8699
No log 7.8667 354 0.7371 0.7134 0.7371 0.8586
No log 7.9111 356 0.6441 0.7429 0.6441 0.8025
No log 7.9556 358 0.5969 0.7552 0.5969 0.7726
No log 8.0 360 0.5695 0.7639 0.5695 0.7546
No log 8.0444 362 0.5560 0.7703 0.5560 0.7456
No log 8.0889 364 0.5890 0.7927 0.5890 0.7675
No log 8.1333 366 0.6475 0.7791 0.6475 0.8047
No log 8.1778 368 0.6235 0.7771 0.6235 0.7896
No log 8.2222 370 0.6260 0.7586 0.6260 0.7912
No log 8.2667 372 0.6075 0.7552 0.6075 0.7794
No log 8.3111 374 0.6036 0.7552 0.6036 0.7769
No log 8.3556 376 0.6166 0.7552 0.6166 0.7853
No log 8.4 378 0.6589 0.7671 0.6589 0.8117
No log 8.4444 380 0.6377 0.7724 0.6377 0.7986
No log 8.4889 382 0.6361 0.7568 0.6361 0.7976
No log 8.5333 384 0.6478 0.7778 0.6478 0.8049
No log 8.5778 386 0.7592 0.7417 0.7592 0.8713
No log 8.6222 388 0.8548 0.7219 0.8548 0.9246
No log 8.6667 390 0.8035 0.7529 0.8035 0.8964
No log 8.7111 392 0.7422 0.7421 0.7422 0.8615
No log 8.7556 394 0.7430 0.7421 0.7430 0.8620
No log 8.8 396 0.7626 0.7692 0.7626 0.8733
No log 8.8444 398 0.7732 0.7248 0.7732 0.8793
No log 8.8889 400 0.7399 0.7248 0.7399 0.8602
No log 8.9333 402 0.7304 0.7467 0.7304 0.8546
No log 8.9778 404 0.7048 0.7234 0.7048 0.8396
No log 9.0222 406 0.6704 0.7429 0.6704 0.8188
No log 9.0667 408 0.7057 0.7324 0.7057 0.8400
No log 9.1111 410 0.7443 0.6849 0.7443 0.8627
No log 9.1556 412 0.7891 0.6533 0.7891 0.8883
No log 9.2 414 0.8352 0.7168 0.8352 0.9139
No log 9.2444 416 0.8213 0.7345 0.8213 0.9063
No log 9.2889 418 0.7802 0.7957 0.7802 0.8833
No log 9.3333 420 0.6525 0.7882 0.6525 0.8078
No log 9.3778 422 0.5403 0.7871 0.5403 0.7350
No log 9.4222 424 0.5181 0.7922 0.5181 0.7198
No log 9.4667 426 0.5185 0.7843 0.5185 0.7201
No log 9.5111 428 0.5396 0.7671 0.5396 0.7346
No log 9.5556 430 0.5667 0.8 0.5667 0.7528
No log 9.6 432 0.5746 0.8 0.5746 0.7580
No log 9.6444 434 0.5354 0.7871 0.5354 0.7317
No log 9.6889 436 0.5508 0.7895 0.5508 0.7421
No log 9.7333 438 0.6119 0.7619 0.6119 0.7823
No log 9.7778 440 0.7244 0.7194 0.7244 0.8511
No log 9.8222 442 0.7713 0.7194 0.7713 0.8782
No log 9.8667 444 0.7466 0.7246 0.7466 0.8641
No log 9.9111 446 0.6507 0.7376 0.6507 0.8066
No log 9.9556 448 0.5988 0.7838 0.5988 0.7738
No log 10.0 450 0.5908 0.7838 0.5908 0.7686
No log 10.0444 452 0.6128 0.7838 0.6128 0.7828
No log 10.0889 454 0.6264 0.7483 0.6264 0.7914
No log 10.1333 456 0.7072 0.7673 0.7072 0.8410
No log 10.1778 458 0.8015 0.7273 0.8015 0.8952
No log 10.2222 460 0.7929 0.7342 0.7929 0.8904
No log 10.2667 462 0.7369 0.7429 0.7369 0.8585
No log 10.3111 464 0.6891 0.7391 0.6891 0.8301
No log 10.3556 466 0.6930 0.7361 0.6930 0.8325
No log 10.4 468 0.7418 0.7453 0.7418 0.8613
No log 10.4444 470 0.8353 0.7251 0.8353 0.9139
No log 10.4889 472 0.8099 0.7719 0.8099 0.9000
No log 10.5333 474 0.7766 0.7730 0.7766 0.8813
No log 10.5778 476 0.7498 0.7805 0.7498 0.8659
No log 10.6222 478 0.7712 0.7578 0.7712 0.8782
No log 10.6667 480 0.7483 0.7595 0.7483 0.8650
No log 10.7111 482 0.7699 0.75 0.7699 0.8775
No log 10.7556 484 0.7291 0.7702 0.7291 0.8539
No log 10.8 486 0.7359 0.7702 0.7359 0.8578
No log 10.8444 488 0.7860 0.7702 0.7860 0.8866
No log 10.8889 490 0.7609 0.7662 0.7609 0.8723
No log 10.9333 492 0.6908 0.7376 0.6908 0.8311
No log 10.9778 494 0.6741 0.7518 0.6741 0.8210
No log 11.0222 496 0.6780 0.7518 0.6780 0.8234
No log 11.0667 498 0.7113 0.7484 0.7113 0.8434
0.3785 11.1111 500 0.6916 0.7342 0.6916 0.8316
0.3785 11.1556 502 0.6894 0.7237 0.6894 0.8303
0.3785 11.2 504 0.6521 0.7338 0.6521 0.8076
0.3785 11.2444 506 0.6557 0.7338 0.6557 0.8098
0.3785 11.2889 508 0.7014 0.7153 0.7014 0.8375
0.3785 11.3333 510 0.7286 0.7324 0.7286 0.8536

Framework versions

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