ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k1_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: 0.8085
  • Qwk: 0.0196
  • Mse: 0.8085
  • Rmse: 0.8992

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 0.3333 2 3.5985 -0.0058 3.5985 1.8970
No log 0.6667 4 2.0854 0.0304 2.0854 1.4441
No log 1.0 6 1.4246 -0.0265 1.4246 1.1936
No log 1.3333 8 1.6141 0.0194 1.6141 1.2705
No log 1.6667 10 0.8606 0.0129 0.8606 0.9277
No log 2.0 12 0.7360 0.0857 0.7360 0.8579
No log 2.3333 14 0.7941 0.0191 0.7941 0.8911
No log 2.6667 16 0.7895 0.0191 0.7895 0.8886
No log 3.0 18 1.0750 0.0309 1.0750 1.0368
No log 3.3333 20 0.9576 0.0320 0.9576 0.9786
No log 3.6667 22 0.8243 0.1561 0.8243 0.9079
No log 4.0 24 0.9648 0.1636 0.9648 0.9822
No log 4.3333 26 1.2644 0.0310 1.2644 1.1244
No log 4.6667 28 1.1342 0.0808 1.1342 1.0650
No log 5.0 30 1.0170 0.1490 1.0170 1.0084
No log 5.3333 32 1.1711 0.0746 1.1711 1.0822
No log 5.6667 34 1.2028 0.0448 1.2028 1.0967
No log 6.0 36 1.1016 -0.0007 1.1016 1.0496
No log 6.3333 38 1.2012 0.0379 1.2012 1.0960
No log 6.6667 40 0.9958 0.0852 0.9958 0.9979
No log 7.0 42 1.2038 0.1011 1.2038 1.0972
No log 7.3333 44 1.0823 -0.0323 1.0823 1.0403
No log 7.6667 46 1.2943 0.0599 1.2943 1.1377
No log 8.0 48 1.0769 -0.0304 1.0769 1.0377
No log 8.3333 50 1.1115 0.0657 1.1115 1.0543
No log 8.6667 52 1.1321 0.0063 1.1321 1.0640
No log 9.0 54 0.9966 0.0559 0.9966 0.9983
No log 9.3333 56 1.0106 -0.0535 1.0106 1.0053
No log 9.6667 58 1.0469 -0.0194 1.0469 1.0232
No log 10.0 60 1.0263 -0.0409 1.0263 1.0131
No log 10.3333 62 1.0840 -0.0285 1.0840 1.0411
No log 10.6667 64 0.9976 0.0476 0.9976 0.9988
No log 11.0 66 1.0476 0.0244 1.0476 1.0235
No log 11.3333 68 1.0282 0.0802 1.0282 1.0140
No log 11.6667 70 1.0249 0.0996 1.0249 1.0124
No log 12.0 72 0.9962 -0.0208 0.9962 0.9981
No log 12.3333 74 0.8807 0.0606 0.8807 0.9384
No log 12.6667 76 0.7950 0.0449 0.7950 0.8916
No log 13.0 78 0.9335 0.0207 0.9335 0.9662
No log 13.3333 80 0.8615 0.0490 0.8615 0.9282
No log 13.6667 82 0.8439 0.0025 0.8439 0.9186
No log 14.0 84 1.0274 0.0734 1.0274 1.0136
No log 14.3333 86 0.9783 0.0464 0.9783 0.9891
No log 14.6667 88 1.0562 0.0149 1.0562 1.0277
No log 15.0 90 1.0856 0.0062 1.0856 1.0419
No log 15.3333 92 0.9271 0.0262 0.9271 0.9628
No log 15.6667 94 0.9042 0.0172 0.9042 0.9509
No log 16.0 96 0.8451 -0.0178 0.8451 0.9193
No log 16.3333 98 0.8333 -0.0614 0.8333 0.9128
No log 16.6667 100 0.8460 0.0051 0.8460 0.9198
No log 17.0 102 0.8901 0.0208 0.8901 0.9434
No log 17.3333 104 0.9027 -0.0117 0.9027 0.9501
No log 17.6667 106 0.9564 0.0547 0.9564 0.9780
No log 18.0 108 1.1044 0.0366 1.1044 1.0509
No log 18.3333 110 0.9962 0.0090 0.9962 0.9981
No log 18.6667 112 0.9930 -0.0044 0.9930 0.9965
No log 19.0 114 0.9657 0.0913 0.9657 0.9827
No log 19.3333 116 0.9121 0.0870 0.9121 0.9550
No log 19.6667 118 0.8690 -0.0230 0.8690 0.9322
No log 20.0 120 0.9095 -0.0408 0.9095 0.9537
No log 20.3333 122 0.9034 -0.0008 0.9034 0.9505
No log 20.6667 124 0.8224 -0.0643 0.8224 0.9069
No log 21.0 126 0.8309 -0.0391 0.8309 0.9116
No log 21.3333 128 0.8389 -0.0443 0.8389 0.9159
No log 21.6667 130 0.9521 -0.0056 0.9521 0.9757
No log 22.0 132 1.0448 0.0287 1.0448 1.0221
No log 22.3333 134 0.8545 -0.0686 0.8545 0.9244
No log 22.6667 136 0.8637 -0.0563 0.8637 0.9294
No log 23.0 138 0.8933 -0.0425 0.8933 0.9452
No log 23.3333 140 0.9228 -0.0200 0.9228 0.9606
No log 23.6667 142 0.8760 0.1287 0.8760 0.9359
No log 24.0 144 0.9720 0.0249 0.9720 0.9859
No log 24.3333 146 1.0147 -0.0144 1.0147 1.0073
No log 24.6667 148 0.8526 0.0989 0.8526 0.9233
No log 25.0 150 0.9787 0.0333 0.9787 0.9893
No log 25.3333 152 1.2643 0.0493 1.2643 1.1244
No log 25.6667 154 1.0546 0.0415 1.0546 1.0269
No log 26.0 156 0.8143 0.0791 0.8143 0.9024
No log 26.3333 158 0.8326 0.0570 0.8326 0.9125
No log 26.6667 160 0.8086 0.0926 0.8086 0.8992
No log 27.0 162 0.8514 0.0246 0.8514 0.9227
No log 27.3333 164 0.8785 0.1139 0.8785 0.9373
No log 27.6667 166 0.8933 0.0216 0.8933 0.9451
No log 28.0 168 0.8809 0.0643 0.8809 0.9386
No log 28.3333 170 0.8478 0.1734 0.8478 0.9207
No log 28.6667 172 0.8369 0.1744 0.8369 0.9148
No log 29.0 174 0.8278 0.0246 0.8278 0.9099
No log 29.3333 176 0.8741 0.0095 0.8741 0.9349
No log 29.6667 178 0.8310 0.0196 0.8310 0.9116
No log 30.0 180 0.8361 0.1272 0.8361 0.9144
No log 30.3333 182 0.8642 0.0861 0.8642 0.9296
No log 30.6667 184 0.8564 0.0393 0.8564 0.9254
No log 31.0 186 0.9187 0.0091 0.9187 0.9585
No log 31.3333 188 0.9276 -0.0341 0.9276 0.9631
No log 31.6667 190 0.8422 -0.0209 0.8422 0.9177
No log 32.0 192 0.8177 0.0053 0.8177 0.9043
No log 32.3333 194 0.8537 0.0135 0.8537 0.9239
No log 32.6667 196 0.8303 -0.0354 0.8303 0.9112
No log 33.0 198 0.8299 -0.0132 0.8299 0.9110
No log 33.3333 200 0.8471 -0.0230 0.8471 0.9204
No log 33.6667 202 0.8246 0.0426 0.8246 0.9081
No log 34.0 204 0.8374 0.0051 0.8374 0.9151
No log 34.3333 206 0.8461 -0.0127 0.8461 0.9199
No log 34.6667 208 0.9618 0.0362 0.9618 0.9807
No log 35.0 210 0.9220 0.0362 0.9220 0.9602
No log 35.3333 212 0.8108 -0.0079 0.8108 0.9004
No log 35.6667 214 0.9172 -0.0528 0.9172 0.9577
No log 36.0 216 0.9176 -0.0528 0.9176 0.9579
No log 36.3333 218 0.8275 0.0509 0.8275 0.9097
No log 36.6667 220 0.8172 -0.0283 0.8172 0.9040
No log 37.0 222 1.0225 0.0912 1.0225 1.0112
No log 37.3333 224 1.0222 0.0209 1.0222 1.0110
No log 37.6667 226 0.8875 0.0964 0.8875 0.9421
No log 38.0 228 0.9055 0.0559 0.9055 0.9516
No log 38.3333 230 0.9401 0.0559 0.9401 0.9696
No log 38.6667 232 0.8866 0.0949 0.8866 0.9416
No log 39.0 234 0.8488 0.1138 0.8488 0.9213
No log 39.3333 236 0.8151 0.1617 0.8151 0.9028
No log 39.6667 238 0.8110 0.1379 0.8110 0.9006
No log 40.0 240 0.8010 0.1761 0.8010 0.8950
No log 40.3333 242 0.7979 0.1372 0.7979 0.8932
No log 40.6667 244 0.7684 0.1796 0.7684 0.8766
No log 41.0 246 0.7693 0.0828 0.7693 0.8771
No log 41.3333 248 0.7822 0.1734 0.7822 0.8844
No log 41.6667 250 0.8018 0.1617 0.8018 0.8954
No log 42.0 252 0.8025 0.2087 0.8025 0.8958
No log 42.3333 254 0.7844 0.0791 0.7844 0.8857
No log 42.6667 256 0.7808 0.0741 0.7808 0.8836
No log 43.0 258 0.7613 0.0828 0.7613 0.8725
No log 43.3333 260 0.7512 0.0874 0.7512 0.8667
No log 43.6667 262 0.7577 0.0930 0.7577 0.8704
No log 44.0 264 0.8071 0.0606 0.8071 0.8984
No log 44.3333 266 0.7958 0.0987 0.7958 0.8920
No log 44.6667 268 0.7583 0.1395 0.7583 0.8708
No log 45.0 270 0.7910 0.1048 0.7910 0.8894
No log 45.3333 272 0.8378 0.0917 0.8378 0.9153
No log 45.6667 274 0.8162 0.0574 0.8162 0.9035
No log 46.0 276 0.7847 0.2112 0.7847 0.8858
No log 46.3333 278 0.7762 0.2194 0.7762 0.8810
No log 46.6667 280 0.7613 0.1778 0.7613 0.8725
No log 47.0 282 0.7706 0.1143 0.7706 0.8779
No log 47.3333 284 0.7665 0.1143 0.7665 0.8755
No log 47.6667 286 0.7963 0.1506 0.7963 0.8924
No log 48.0 288 0.7861 0.0650 0.7861 0.8866
No log 48.3333 290 0.7616 0.0783 0.7616 0.8727
No log 48.6667 292 0.7725 0.1236 0.7725 0.8789
No log 49.0 294 0.8062 0.1192 0.8062 0.8979
No log 49.3333 296 0.8829 -0.0320 0.8829 0.9396
No log 49.6667 298 0.8700 -0.0315 0.8700 0.9327
No log 50.0 300 0.8104 0.1236 0.8104 0.9002
No log 50.3333 302 0.8185 0.2063 0.8185 0.9047
No log 50.6667 304 0.8228 0.1660 0.8228 0.9071
No log 51.0 306 0.8389 0.1236 0.8389 0.9159
No log 51.3333 308 0.8276 0.1660 0.8276 0.9097
No log 51.6667 310 0.8172 0.1660 0.8172 0.9040
No log 52.0 312 0.8062 0.0783 0.8062 0.8979
No log 52.3333 314 0.7898 0.0783 0.7898 0.8887
No log 52.6667 316 0.7896 0.1379 0.7896 0.8886
No log 53.0 318 0.8140 0.1365 0.8140 0.9022
No log 53.3333 320 0.8153 0.1379 0.8153 0.9030
No log 53.6667 322 0.8110 0.1192 0.8110 0.9005
No log 54.0 324 0.8532 0.0091 0.8532 0.9237
No log 54.3333 326 0.8563 0.0407 0.8563 0.9253
No log 54.6667 328 0.8110 0.0226 0.8110 0.9006
No log 55.0 330 0.7887 0.0783 0.7887 0.8881
No log 55.3333 332 0.7807 0.0432 0.7807 0.8836
No log 55.6667 334 0.7796 0.0394 0.7796 0.8829
No log 56.0 336 0.7871 0.0432 0.7871 0.8872
No log 56.3333 338 0.7882 0.0394 0.7882 0.8878
No log 56.6667 340 0.7946 0.0783 0.7946 0.8914
No log 57.0 342 0.8134 0.0205 0.8134 0.9019
No log 57.3333 344 0.8250 0.0146 0.8250 0.9083
No log 57.6667 346 0.8230 0.0562 0.8230 0.9072
No log 58.0 348 0.8029 0.0611 0.8029 0.8960
No log 58.3333 350 0.7772 0.0394 0.7772 0.8816
No log 58.6667 352 0.7781 0.0394 0.7781 0.8821
No log 59.0 354 0.7696 0.0394 0.7696 0.8773
No log 59.3333 356 0.7724 0.0432 0.7724 0.8788
No log 59.6667 358 0.7805 0.0394 0.7805 0.8834
No log 60.0 360 0.7901 0.0289 0.7901 0.8889
No log 60.3333 362 0.7888 0.0289 0.7888 0.8882
No log 60.6667 364 0.7646 0.0828 0.7646 0.8744
No log 61.0 366 0.7603 0.1387 0.7603 0.8719
No log 61.3333 368 0.7608 0.1885 0.7608 0.8723
No log 61.6667 370 0.7556 0.1821 0.7556 0.8692
No log 62.0 372 0.7524 0.2194 0.7524 0.8674
No log 62.3333 374 0.7688 0.2194 0.7688 0.8768
No log 62.6667 376 0.7903 0.1734 0.7903 0.8890
No log 63.0 378 0.8120 0.2128 0.8120 0.9011
No log 63.3333 380 0.8265 0.2063 0.8265 0.9091
No log 63.6667 382 0.8393 0.1508 0.8393 0.9162
No log 64.0 384 0.8875 0.0134 0.8875 0.9421
No log 64.3333 386 0.8835 0.0134 0.8835 0.9399
No log 64.6667 388 0.8542 0.1775 0.8542 0.9242
No log 65.0 390 0.8540 0.2019 0.8540 0.9241
No log 65.3333 392 0.8859 0.0913 0.8859 0.9412
No log 65.6667 394 0.8746 0.1304 0.8746 0.9352
No log 66.0 396 0.8348 0.2019 0.8348 0.9137
No log 66.3333 398 0.8248 0.0660 0.8248 0.9082
No log 66.6667 400 0.8787 -0.0279 0.8787 0.9374
No log 67.0 402 0.8957 -0.0052 0.8957 0.9464
No log 67.3333 404 0.8618 0.0909 0.8618 0.9283
No log 67.6667 406 0.7927 0.1144 0.7927 0.8903
No log 68.0 408 0.7477 0.1244 0.7477 0.8647
No log 68.3333 410 0.7456 0.0828 0.7456 0.8635
No log 68.6667 412 0.7514 0.1244 0.7514 0.8668
No log 69.0 414 0.7610 0.1689 0.7610 0.8724
No log 69.3333 416 0.7735 0.1192 0.7735 0.8795
No log 69.6667 418 0.7827 0.0700 0.7827 0.8847
No log 70.0 420 0.8081 0.0650 0.8081 0.8990
No log 70.3333 422 0.8458 0.0517 0.8458 0.9197
No log 70.6667 424 0.8392 0.0517 0.8392 0.9161
No log 71.0 426 0.7970 0.0650 0.7970 0.8928
No log 71.3333 428 0.7584 0.1144 0.7584 0.8709
No log 71.6667 430 0.7469 0.1244 0.7469 0.8643
No log 72.0 432 0.7411 0.1298 0.7411 0.8609
No log 72.3333 434 0.7324 0.0874 0.7324 0.8558
No log 72.6667 436 0.7267 0.1298 0.7267 0.8525
No log 73.0 438 0.7348 0.1659 0.7348 0.8572
No log 73.3333 440 0.7536 0.0650 0.7536 0.8681
No log 73.6667 442 0.7663 0.0650 0.7663 0.8754
No log 74.0 444 0.7887 0.0650 0.7887 0.8881
No log 74.3333 446 0.8019 0.0611 0.8019 0.8955
No log 74.6667 448 0.8114 0.0611 0.8114 0.9008
No log 75.0 450 0.8018 0.0650 0.8018 0.8954
No log 75.3333 452 0.7821 0.0650 0.7821 0.8844
No log 75.6667 454 0.7773 0.1189 0.7773 0.8816
No log 76.0 456 0.7803 0.2181 0.7803 0.8834
No log 76.3333 458 0.7837 0.1674 0.7837 0.8852
No log 76.6667 460 0.7920 0.0257 0.7920 0.8899
No log 77.0 462 0.8307 0.0611 0.8307 0.9114
No log 77.3333 464 0.8858 0.0659 0.8858 0.9412
No log 77.6667 466 0.9385 0.0596 0.9385 0.9687
No log 78.0 468 0.9532 0.0596 0.9532 0.9763
No log 78.3333 470 0.9249 0.0988 0.9249 0.9617
No log 78.6667 472 0.8727 -0.0362 0.8727 0.9342
No log 79.0 474 0.8113 0.0611 0.8113 0.9007
No log 79.3333 476 0.7780 0.1189 0.7780 0.8821
No log 79.6667 478 0.7638 0.2181 0.7638 0.8739
No log 80.0 480 0.7659 0.1761 0.7659 0.8752
No log 80.3333 482 0.7648 0.1761 0.7648 0.8746
No log 80.6667 484 0.7503 0.2222 0.7503 0.8662
No log 81.0 486 0.7358 0.1751 0.7358 0.8578
No log 81.3333 488 0.7332 0.1298 0.7332 0.8563
No log 81.6667 490 0.7394 0.0783 0.7394 0.8599
No log 82.0 492 0.7505 0.1144 0.7505 0.8663
No log 82.3333 494 0.7637 0.1144 0.7637 0.8739
No log 82.6667 496 0.7750 0.0650 0.7750 0.8803
No log 83.0 498 0.7939 0.0611 0.7939 0.8910
0.1916 83.3333 500 0.8026 0.0574 0.8026 0.8959
0.1916 83.6667 502 0.8115 0.0574 0.8115 0.9009
0.1916 84.0 504 0.8020 0.0574 0.8020 0.8956
0.1916 84.3333 506 0.7938 0.0650 0.7938 0.8910
0.1916 84.6667 508 0.7964 0.0611 0.7964 0.8924
0.1916 85.0 510 0.8067 0.0611 0.8067 0.8982
0.1916 85.3333 512 0.8130 0.0611 0.8130 0.9016
0.1916 85.6667 514 0.8120 0.0611 0.8120 0.9011
0.1916 86.0 516 0.8113 0.0611 0.8113 0.9007
0.1916 86.3333 518 0.8025 0.0196 0.8025 0.8958
0.1916 86.6667 520 0.7936 0.0700 0.7936 0.8909
0.1916 87.0 522 0.7863 0.0700 0.7863 0.8867
0.1916 87.3333 524 0.7793 0.0700 0.7793 0.8828
0.1916 87.6667 526 0.7783 0.0700 0.7783 0.8822
0.1916 88.0 528 0.7817 0.0226 0.7817 0.8841
0.1916 88.3333 530 0.7769 0.0700 0.7769 0.8814
0.1916 88.6667 532 0.7784 0.0700 0.7784 0.8823
0.1916 89.0 534 0.7814 0.0226 0.7814 0.8840
0.1916 89.3333 536 0.7812 0.0700 0.7812 0.8839
0.1916 89.6667 538 0.7844 0.0226 0.7844 0.8857
0.1916 90.0 540 0.7913 0.0226 0.7913 0.8896
0.1916 90.3333 542 0.7996 0.0196 0.7996 0.8942
0.1916 90.6667 544 0.8064 0.0196 0.8064 0.8980
0.1916 91.0 546 0.8085 0.0196 0.8085 0.8992

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k1_task3_organization

Finetuned
(4222)
this model