ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k4_task3_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: 0.8132
  • Qwk: 0.0053
  • Mse: 0.8132
  • Rmse: 0.9018

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 0.1538 2 3.9708 0.0103 3.9708 1.9927
No log 0.3077 4 2.1363 0.0672 2.1363 1.4616
No log 0.4615 6 1.8444 0.0304 1.8444 1.3581
No log 0.6154 8 1.1100 -0.0423 1.1100 1.0536
No log 0.7692 10 0.6934 0.0506 0.6934 0.8327
No log 0.9231 12 0.7235 0.1021 0.7235 0.8506
No log 1.0769 14 0.8884 0.0378 0.8884 0.9425
No log 1.2308 16 1.0089 0.0083 1.0089 1.0044
No log 1.3846 18 1.2718 -0.0500 1.2718 1.1278
No log 1.5385 20 1.3198 -0.0500 1.3198 1.1488
No log 1.6923 22 1.3811 -0.0500 1.3811 1.1752
No log 1.8462 24 0.9302 0.0006 0.9302 0.9645
No log 2.0 26 0.7676 -0.0188 0.7676 0.8761
No log 2.1538 28 0.9214 -0.1261 0.9214 0.9599
No log 2.3077 30 1.2921 -0.0510 1.2921 1.1367
No log 2.4615 32 1.6775 -0.0029 1.6775 1.2952
No log 2.6154 34 1.3327 0.0 1.3327 1.1544
No log 2.7692 36 1.0668 0.0298 1.0668 1.0329
No log 2.9231 38 0.9820 -0.0677 0.9820 0.9909
No log 3.0769 40 0.8354 -0.0823 0.8354 0.9140
No log 3.2308 42 0.8198 -0.0812 0.8198 0.9054
No log 3.3846 44 0.8626 0.0377 0.8626 0.9288
No log 3.5385 46 0.7737 0.0549 0.7737 0.8796
No log 3.6923 48 0.8400 0.0377 0.8400 0.9165
No log 3.8462 50 0.7805 0.0628 0.7805 0.8835
No log 4.0 52 0.7994 0.0225 0.7994 0.8941
No log 4.1538 54 0.7891 -0.0240 0.7891 0.8883
No log 4.3077 56 0.9478 -0.0459 0.9478 0.9736
No log 4.4615 58 0.9848 -0.0474 0.9848 0.9924
No log 4.6154 60 0.7652 0.0807 0.7652 0.8747
No log 4.7692 62 0.7079 0.0506 0.7079 0.8413
No log 4.9231 64 0.6942 -0.0035 0.6942 0.8332
No log 5.0769 66 0.7809 0.1387 0.7809 0.8837
No log 5.2308 68 3.2431 -0.0160 3.2431 1.8009
No log 5.3846 70 2.9785 -0.0043 2.9785 1.7258
No log 5.5385 72 1.4982 0.0443 1.4982 1.2240
No log 5.6923 74 0.8540 0.0071 0.8540 0.9241
No log 5.8462 76 0.7598 -0.0679 0.7598 0.8717
No log 6.0 78 0.7304 -0.1223 0.7304 0.8546
No log 6.1538 80 0.7148 -0.1223 0.7148 0.8455
No log 6.3077 82 0.7373 0.0670 0.7373 0.8586
No log 6.4615 84 0.9605 -0.0425 0.9605 0.9801
No log 6.6154 86 1.0106 -0.1263 1.0106 1.0053
No log 6.7692 88 0.7292 0.1627 0.7292 0.8539
No log 6.9231 90 0.6975 0.0909 0.6975 0.8351
No log 7.0769 92 0.7237 0.0807 0.7237 0.8507
No log 7.2308 94 0.7847 0.1627 0.7847 0.8858
No log 7.3846 96 0.7506 0.0857 0.7506 0.8663
No log 7.5385 98 0.7671 0.0355 0.7671 0.8758
No log 7.6923 100 0.8346 0.0807 0.8346 0.9135
No log 7.8462 102 0.9682 -0.0767 0.9682 0.9840
No log 8.0 104 0.8174 0.0807 0.8174 0.9041
No log 8.1538 106 0.7734 -0.0385 0.7734 0.8794
No log 8.3077 108 0.7034 -0.0035 0.7034 0.8387
No log 8.4615 110 0.8185 0.0099 0.8185 0.9047
No log 8.6154 112 1.1170 -0.0236 1.1170 1.0569
No log 8.7692 114 1.1309 -0.0236 1.1309 1.0634
No log 8.9231 116 0.8331 0.0071 0.8331 0.9128
No log 9.0769 118 0.7435 0.0374 0.7435 0.8622
No log 9.2308 120 0.7915 0.0318 0.7915 0.8897
No log 9.3846 122 0.9118 -0.1580 0.9118 0.9549
No log 9.5385 124 1.0049 -0.0347 1.0049 1.0024
No log 9.6923 126 1.0544 -0.0612 1.0544 1.0268
No log 9.8462 128 1.0842 -0.0960 1.0842 1.0413
No log 10.0 130 1.1503 -0.1783 1.1503 1.0725
No log 10.1538 132 1.0450 -0.1405 1.0450 1.0223
No log 10.3077 134 0.9704 -0.1086 0.9704 0.9851
No log 10.4615 136 1.0052 -0.1633 1.0052 1.0026
No log 10.6154 138 1.1474 -0.1628 1.1474 1.0712
No log 10.7692 140 1.0250 -0.1234 1.0250 1.0124
No log 10.9231 142 0.9430 0.0913 0.9430 0.9711
No log 11.0769 144 0.9414 -0.1449 0.9414 0.9703
No log 11.2308 146 1.1714 -0.0079 1.1714 1.0823
No log 11.3846 148 1.0065 -0.1152 1.0065 1.0032
No log 11.5385 150 0.8595 0.1218 0.8595 0.9271
No log 11.6923 152 0.8601 0.1038 0.8601 0.9274
No log 11.8462 154 0.8519 0.1299 0.8519 0.9230
No log 12.0 156 0.9099 -0.0322 0.9099 0.9539
No log 12.1538 158 0.9110 -0.0799 0.9110 0.9545
No log 12.3077 160 0.8165 -0.0355 0.8165 0.9036
No log 12.4615 162 0.7659 0.0394 0.7659 0.8751
No log 12.6154 164 0.8297 0.0570 0.8297 0.9109
No log 12.7692 166 0.8429 0.0764 0.8429 0.9181
No log 12.9231 168 1.0406 0.0348 1.0406 1.0201
No log 13.0769 170 0.9605 0.0109 0.9605 0.9801
No log 13.2308 172 0.9787 0.0007 0.9787 0.9893
No log 13.3846 174 1.0668 -0.0154 1.0668 1.0329
No log 13.5385 176 0.9080 0.0623 0.9080 0.9529
No log 13.6923 178 0.8728 -0.0156 0.8728 0.9342
No log 13.8462 180 1.0764 0.0250 1.0764 1.0375
No log 14.0 182 0.9451 0.0711 0.9451 0.9722
No log 14.1538 184 0.7931 -0.0506 0.7931 0.8906
No log 14.3077 186 0.9090 0.0350 0.9090 0.9534
No log 14.4615 188 0.8975 0.0699 0.8975 0.9474
No log 14.6154 190 0.8015 -0.0849 0.8015 0.8953
No log 14.7692 192 0.8274 0.1049 0.8274 0.9096
No log 14.9231 194 0.9031 -0.0008 0.9031 0.9503
No log 15.0769 196 0.8655 0.0909 0.8655 0.9303
No log 15.2308 198 0.7943 0.1340 0.7943 0.8913
No log 15.3846 200 0.8367 0.0603 0.8367 0.9147
No log 15.5385 202 0.8694 0.0916 0.8694 0.9324
No log 15.6923 204 0.8880 0.0245 0.8880 0.9423
No log 15.8462 206 0.8676 0.0584 0.8676 0.9315
No log 16.0 208 0.8287 0.1092 0.8287 0.9103
No log 16.1538 210 0.8334 0.1224 0.8334 0.9129
No log 16.3077 212 0.8545 0.0362 0.8545 0.9244
No log 16.4615 214 0.8768 0.0661 0.8769 0.9364
No log 16.6154 216 0.9349 0.0563 0.9349 0.9669
No log 16.7692 218 0.9561 0.0236 0.9561 0.9778
No log 16.9231 220 0.9146 0.0392 0.9146 0.9563
No log 17.0769 222 0.8491 0.0741 0.8491 0.9215
No log 17.2308 224 0.8859 -0.0373 0.8859 0.9412
No log 17.3846 226 0.9416 -0.0033 0.9416 0.9703
No log 17.5385 228 0.8590 -0.0373 0.8590 0.9268
No log 17.6923 230 0.7808 0.0412 0.7808 0.8836
No log 17.8462 232 0.8460 0.0279 0.8460 0.9198
No log 18.0 234 0.8374 0.0514 0.8374 0.9151
No log 18.1538 236 0.9978 -0.0717 0.9978 0.9989
No log 18.3077 238 1.2842 0.0799 1.2842 1.1332
No log 18.4615 240 1.1450 0.0584 1.1450 1.0701
No log 18.6154 242 0.8874 0.1131 0.8874 0.9420
No log 18.7692 244 0.9473 0.0416 0.9473 0.9733
No log 18.9231 246 0.9202 0.0007 0.9202 0.9593
No log 19.0769 248 0.8034 0.0460 0.8034 0.8963
No log 19.2308 250 0.8244 0.0123 0.8244 0.9080
No log 19.3846 252 0.8388 0.0512 0.8388 0.9158
No log 19.5385 254 0.7700 0.0355 0.7700 0.8775
No log 19.6923 256 0.8031 0.0110 0.8031 0.8962
No log 19.8462 258 0.8323 -0.0280 0.8323 0.9123
No log 20.0 260 0.8315 0.0393 0.8315 0.9119
No log 20.1538 262 0.9391 -0.0728 0.9391 0.9691
No log 20.3077 264 0.9521 -0.0690 0.9521 0.9758
No log 20.4615 266 0.8750 0.1136 0.8750 0.9354
No log 20.6154 268 0.9426 0.0689 0.9426 0.9709
No log 20.7692 270 0.9372 0.0689 0.9372 0.9681
No log 20.9231 272 0.8542 0.0559 0.8542 0.9242
No log 21.0769 274 0.8262 0.0295 0.8262 0.9090
No log 21.2308 276 0.9116 -0.0373 0.9116 0.9548
No log 21.3846 278 0.8913 -0.0373 0.8913 0.9441
No log 21.5385 280 0.8073 0.0308 0.8073 0.8985
No log 21.6923 282 0.7869 0.0503 0.7869 0.8870
No log 21.8462 284 0.7733 0.0834 0.7733 0.8794
No log 22.0 286 0.7940 0.0791 0.7940 0.8911
No log 22.1538 288 0.8413 -0.1032 0.8413 0.9172
No log 22.3077 290 1.0036 0.0333 1.0036 1.0018
No log 22.4615 292 1.1447 0.0267 1.1447 1.0699
No log 22.6154 294 1.0738 0.0014 1.0738 1.0362
No log 22.7692 296 0.9839 -0.0088 0.9839 0.9919
No log 22.9231 298 0.9637 -0.0853 0.9637 0.9817
No log 23.0769 300 0.9402 -0.0895 0.9402 0.9697
No log 23.2308 302 0.9640 -0.0260 0.9640 0.9818
No log 23.3846 304 1.0557 0.0287 1.0557 1.0275
No log 23.5385 306 1.0582 -0.0056 1.0582 1.0287
No log 23.6923 308 0.9707 0.0109 0.9707 0.9852
No log 23.8462 310 0.8955 0.0 0.8955 0.9463
No log 24.0 312 0.9147 0.0303 0.9147 0.9564
No log 24.1538 314 0.8667 0.0603 0.8667 0.9310
No log 24.3077 316 0.8004 -0.0079 0.8004 0.8947
No log 24.4615 318 0.8717 0.0442 0.8717 0.9336
No log 24.6154 320 1.0279 -0.0076 1.0279 1.0139
No log 24.7692 322 1.0037 -0.0076 1.0037 1.0019
No log 24.9231 324 0.8460 0.0549 0.8460 0.9198
No log 25.0769 326 0.7570 0.1498 0.7570 0.8700
No log 25.2308 328 0.7725 -0.0493 0.7725 0.8789
No log 25.3846 330 0.7645 -0.0385 0.7645 0.8743
No log 25.5385 332 0.7452 0.0471 0.7452 0.8633
No log 25.6923 334 0.7841 -0.0672 0.7841 0.8855
No log 25.8462 336 0.8540 0.0188 0.8540 0.9241
No log 26.0 338 0.9289 -0.0279 0.9289 0.9638
No log 26.1538 340 0.9714 0.0552 0.9714 0.9856
No log 26.3077 342 0.9454 0.0349 0.9454 0.9723
No log 26.4615 344 0.9156 -0.0347 0.9156 0.9569
No log 26.6154 346 0.8776 0.1135 0.8776 0.9368
No log 26.7692 348 0.8632 0.0188 0.8632 0.9291
No log 26.9231 350 0.8538 0.0188 0.8538 0.9240
No log 27.0769 352 0.8474 0.0188 0.8474 0.9206
No log 27.2308 354 0.8649 0.0118 0.8649 0.9300
No log 27.3846 356 0.8721 0.0188 0.8721 0.9338
No log 27.5385 358 0.9119 0.0210 0.9119 0.9549
No log 27.6923 360 0.9689 0.0807 0.9689 0.9843
No log 27.8462 362 1.0388 0.0524 1.0388 1.0192
No log 28.0 364 1.0393 0.0524 1.0393 1.0194
No log 28.1538 366 0.9962 0.0774 0.9962 0.9981
No log 28.3077 368 0.9539 0.0583 0.9539 0.9767
No log 28.4615 370 0.9725 0.0058 0.9725 0.9862
No log 28.6154 372 0.9603 0.0037 0.9603 0.9799
No log 28.7692 374 0.8979 0.1347 0.8979 0.9476
No log 28.9231 376 0.9039 0.0514 0.9039 0.9507
No log 29.0769 378 0.8787 0.0905 0.8787 0.9374
No log 29.2308 380 0.8064 0.0341 0.8064 0.8980
No log 29.3846 382 0.8278 -0.0240 0.8278 0.9099
No log 29.5385 384 0.8441 0.0670 0.8441 0.9188
No log 29.6923 386 0.8771 0.1007 0.8771 0.9365
No log 29.8462 388 0.8817 0.1050 0.8817 0.9390
No log 30.0 390 0.8833 0.0460 0.8833 0.9399
No log 30.1538 392 0.8429 0.0889 0.8429 0.9181
No log 30.3077 394 0.8171 0.1287 0.8171 0.9039
No log 30.4615 396 0.7933 0.0834 0.7933 0.8907
No log 30.6154 398 0.7670 0.0123 0.7670 0.8758
No log 30.7692 400 0.7868 0.0909 0.7868 0.8870
No log 30.9231 402 0.8182 -0.0008 0.8182 0.9045
No log 31.0769 404 0.8462 0.0377 0.8462 0.9199
No log 31.2308 406 0.8128 0.0017 0.8128 0.9016
No log 31.3846 408 0.8075 -0.0138 0.8075 0.8986
No log 31.5385 410 0.8544 -0.0915 0.8544 0.9243
No log 31.6923 412 0.9356 -0.0332 0.9356 0.9673
No log 31.8462 414 0.9595 0.0015 0.9595 0.9796
No log 32.0 416 0.9485 -0.0073 0.9485 0.9739
No log 32.1538 418 0.9097 0.0407 0.9097 0.9538
No log 32.3077 420 0.8729 0.0062 0.8729 0.9343
No log 32.4615 422 0.8370 -0.0271 0.8370 0.9149
No log 32.6154 424 0.7895 0.0834 0.7895 0.8885
No log 32.7692 426 0.7716 0.0834 0.7716 0.8784
No log 32.9231 428 0.7741 0.0700 0.7741 0.8798
No log 33.0769 430 0.8786 0.0719 0.8786 0.9373
No log 33.2308 432 0.9173 0.0700 0.9173 0.9578
No log 33.3846 434 0.8451 0.1790 0.8451 0.9193
No log 33.5385 436 0.8770 0.1660 0.8770 0.9365
No log 33.6923 438 0.8863 0.1328 0.8863 0.9414
No log 33.8462 440 0.8207 0.0856 0.8207 0.9059
No log 34.0 442 0.7972 0.0289 0.7972 0.8929
No log 34.1538 444 0.7790 -0.0138 0.7790 0.8826
No log 34.3077 446 0.7665 -0.0138 0.7665 0.8755
No log 34.4615 448 0.7779 0.0357 0.7779 0.8820
No log 34.6154 450 0.8093 -0.0138 0.8093 0.8996
No log 34.7692 452 0.9044 0.0668 0.9044 0.9510
No log 34.9231 454 0.9300 0.0659 0.9300 0.9643
No log 35.0769 456 0.8595 0.0837 0.8595 0.9271
No log 35.2308 458 0.7957 0.0410 0.7957 0.8920
No log 35.3846 460 0.8074 0.0522 0.8074 0.8986
No log 35.5385 462 0.7864 0.0078 0.7864 0.8868
No log 35.6923 464 0.7590 0.0834 0.7590 0.8712
No log 35.8462 466 0.7519 -0.0138 0.7519 0.8671
No log 36.0 468 0.7814 0.0549 0.7814 0.8840
No log 36.1538 470 0.8251 0.0826 0.8251 0.9083
No log 36.3077 472 0.8390 0.0826 0.8390 0.9160
No log 36.4615 474 0.8227 -0.0271 0.8227 0.9070
No log 36.6154 476 0.8188 0.0308 0.8188 0.9049
No log 36.7692 478 0.8188 -0.0054 0.8188 0.9049
No log 36.9231 480 0.8031 -0.0870 0.8031 0.8962
No log 37.0769 482 0.7867 -0.0967 0.7867 0.8869
No log 37.2308 484 0.7631 -0.0086 0.7631 0.8735
No log 37.3846 486 0.7533 -0.0086 0.7533 0.8679
No log 37.5385 488 0.7577 0.0257 0.7577 0.8705
No log 37.6923 490 0.7629 0.0257 0.7629 0.8735
No log 37.8462 492 0.7790 0.0257 0.7790 0.8826
No log 38.0 494 0.8202 0.0670 0.8202 0.9057
No log 38.1538 496 0.8541 0.0646 0.8541 0.9242
No log 38.3077 498 0.8474 0.0652 0.8474 0.9206
0.32 38.4615 500 0.8272 0.0313 0.8272 0.9095
0.32 38.6154 502 0.8321 0.0277 0.8321 0.9122
0.32 38.7692 504 0.8244 0.0277 0.8244 0.9080
0.32 38.9231 506 0.8104 -0.0082 0.8104 0.9002
0.32 39.0769 508 0.8288 0.0595 0.8288 0.9104
0.32 39.2308 510 0.8459 0.0595 0.8459 0.9197
0.32 39.3846 512 0.8094 0.0 0.8094 0.8997
0.32 39.5385 514 0.8296 0.0226 0.8296 0.9108
0.32 39.6923 516 0.8511 -0.0723 0.8511 0.9225
0.32 39.8462 518 0.8217 0.0289 0.8217 0.9065
0.32 40.0 520 0.8132 0.0053 0.8132 0.9018

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
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_FineTuningAraBERT_run3_AugV5_k4_task3_organization

Finetuned
(4023)
this model