ArabicNewSplits_FineTuningAraBERT_AugV5_k15_task2_organization_fold1

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: 0.8688
  • Qwk: 0.2348
  • Mse: 0.8688
  • Rmse: 0.9321

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0370 2 3.7987 0.0668 3.7987 1.9490
No log 0.0741 4 2.5399 -0.0477 2.5399 1.5937
No log 0.1111 6 2.0205 -0.2634 2.0205 1.4214
No log 0.1481 8 2.0279 -0.2369 2.0279 1.4240
No log 0.1852 10 1.5393 -0.2522 1.5393 1.2407
No log 0.2222 12 1.4364 -0.1771 1.4364 1.1985
No log 0.2593 14 1.6573 -0.1367 1.6573 1.2873
No log 0.2963 16 2.1707 -0.0557 2.1707 1.4733
No log 0.3333 18 1.9751 -0.0634 1.9751 1.4054
No log 0.3704 20 1.4247 -0.0306 1.4247 1.1936
No log 0.4074 22 1.0361 0.0166 1.0361 1.0179
No log 0.4444 24 0.9305 0.0166 0.9305 0.9646
No log 0.4815 26 1.0255 0.0166 1.0255 1.0127
No log 0.5185 28 1.3549 -0.0568 1.3549 1.1640
No log 0.5556 30 1.2529 -0.0569 1.2529 1.1193
No log 0.5926 32 0.9170 0.0166 0.9170 0.9576
No log 0.6296 34 0.8151 0.0 0.8151 0.9028
No log 0.6667 36 0.7682 -0.0172 0.7682 0.8765
No log 0.7037 38 0.7764 -0.0172 0.7764 0.8812
No log 0.7407 40 0.7633 0.0842 0.7633 0.8737
No log 0.7778 42 0.7276 0.0743 0.7276 0.8530
No log 0.8148 44 0.7023 0.1291 0.7023 0.8380
No log 0.8519 46 0.7213 0.1189 0.7213 0.8493
No log 0.8889 48 0.8828 0.0300 0.8828 0.9396
No log 0.9259 50 0.8741 0.0310 0.8741 0.9349
No log 0.9630 52 0.8471 0.0120 0.8471 0.9204
No log 1.0 54 0.8248 0.0120 0.8248 0.9082
No log 1.0370 56 0.7262 0.1514 0.7262 0.8522
No log 1.0741 58 0.6316 0.2574 0.6316 0.7947
No log 1.1111 60 0.6198 0.2001 0.6198 0.7873
No log 1.1481 62 0.6368 0.0949 0.6368 0.7980
No log 1.1852 64 0.7022 0.0978 0.7022 0.8380
No log 1.2222 66 0.7165 0.2009 0.7165 0.8464
No log 1.2593 68 0.6842 0.2113 0.6842 0.8272
No log 1.2963 70 0.6714 0.2732 0.6714 0.8194
No log 1.3333 72 0.7173 0.2772 0.7173 0.8470
No log 1.3704 74 0.6957 0.2786 0.6957 0.8341
No log 1.4074 76 0.7216 0.1921 0.7216 0.8495
No log 1.4444 78 0.7788 0.0828 0.7788 0.8825
No log 1.4815 80 0.7824 -0.0036 0.7824 0.8846
No log 1.5185 82 0.7731 0.0025 0.7731 0.8793
No log 1.5556 84 0.7924 0.0645 0.7924 0.8901
No log 1.5926 86 0.8341 0.0747 0.8341 0.9133
No log 1.6296 88 0.8162 0.0747 0.8162 0.9034
No log 1.6667 90 0.7755 0.0805 0.7755 0.8806
No log 1.7037 92 0.7661 0.0402 0.7661 0.8753
No log 1.7407 94 0.7796 -0.0194 0.7796 0.8830
No log 1.7778 96 0.7701 -0.0469 0.7701 0.8776
No log 1.8148 98 0.7895 0.1119 0.7895 0.8885
No log 1.8519 100 0.8260 0.1223 0.8260 0.9089
No log 1.8889 102 0.7787 0.0839 0.7787 0.8824
No log 1.9259 104 0.7742 0.0779 0.7742 0.8799
No log 1.9630 106 0.7903 0.1034 0.7903 0.8890
No log 2.0 108 0.8008 0.0958 0.8008 0.8949
No log 2.0370 110 0.8753 0.1181 0.8753 0.9356
No log 2.0741 112 0.8325 0.1181 0.8325 0.9124
No log 2.1111 114 0.7762 0.1442 0.7762 0.8810
No log 2.1481 116 0.7476 0.1021 0.7476 0.8646
No log 2.1852 118 0.7843 0.1442 0.7843 0.8856
No log 2.2222 120 0.8437 0.1223 0.8437 0.9185
No log 2.2593 122 0.8373 0.1223 0.8373 0.9150
No log 2.2963 124 0.8002 0.1442 0.8002 0.8945
No log 2.3333 126 0.7546 0.1442 0.7546 0.8687
No log 2.3704 128 0.7178 0.1980 0.7178 0.8472
No log 2.4074 130 0.7154 0.2075 0.7154 0.8458
No log 2.4444 132 0.7126 0.1806 0.7126 0.8442
No log 2.4815 134 0.7324 0.1513 0.7324 0.8558
No log 2.5185 136 0.7655 0.1286 0.7655 0.8749
No log 2.5556 138 0.7788 0.1806 0.7788 0.8825
No log 2.5926 140 0.7808 0.1646 0.7808 0.8836
No log 2.6296 142 0.7739 0.1734 0.7739 0.8797
No log 2.6667 144 0.8551 0.1223 0.8551 0.9247
No log 2.7037 146 0.8981 0.0747 0.8981 0.9477
No log 2.7407 148 0.8458 0.0713 0.8458 0.9197
No log 2.7778 150 0.8166 0.1223 0.8166 0.9037
No log 2.8148 152 0.7818 0.1734 0.7818 0.8842
No log 2.8519 154 0.7672 0.1274 0.7672 0.8759
No log 2.8889 156 0.8043 0.1223 0.8043 0.8968
No log 2.9259 158 0.9731 0.0938 0.9731 0.9864
No log 2.9630 160 1.1599 0.0982 1.1599 1.0770
No log 3.0 162 1.1438 0.0982 1.1438 1.0695
No log 3.0370 164 0.9444 0.0747 0.9444 0.9718
No log 3.0741 166 0.7896 0.1223 0.7896 0.8886
No log 3.1111 168 0.6993 0.2478 0.6993 0.8362
No log 3.1481 170 0.6794 0.2633 0.6794 0.8243
No log 3.1852 172 0.6950 0.2301 0.6950 0.8337
No log 3.2222 174 0.8023 0.1888 0.8023 0.8957
No log 3.2593 176 0.8857 0.1557 0.8857 0.9411
No log 3.2963 178 0.8402 0.1243 0.8402 0.9166
No log 3.3333 180 0.7570 0.1223 0.7570 0.8701
No log 3.3704 182 0.7406 0.1734 0.7406 0.8606
No log 3.4074 184 0.7294 0.2057 0.7294 0.8541
No log 3.4444 186 0.7274 0.2144 0.7274 0.8529
No log 3.4815 188 0.7797 0.1255 0.7797 0.8830
No log 3.5185 190 0.8383 0.0589 0.8383 0.9156
No log 3.5556 192 0.8093 0.0589 0.8093 0.8996
No log 3.5926 194 0.7701 0.1764 0.7701 0.8776
No log 3.6296 196 0.7059 0.2057 0.7059 0.8402
No log 3.6667 198 0.6686 0.1872 0.6686 0.8177
No log 3.7037 200 0.6566 0.1685 0.6566 0.8103
No log 3.7407 202 0.6435 0.2060 0.6435 0.8022
No log 3.7778 204 0.6499 0.1866 0.6499 0.8062
No log 3.8148 206 0.6906 0.2276 0.6906 0.8311
No log 3.8519 208 0.6977 0.1764 0.6977 0.8353
No log 3.8889 210 0.6477 0.2276 0.6477 0.8048
No log 3.9259 212 0.6023 0.1999 0.6023 0.7761
No log 3.9630 214 0.5950 0.2671 0.5950 0.7714
No log 4.0 216 0.6038 0.3232 0.6038 0.7771
No log 4.0370 218 0.6261 0.2246 0.6261 0.7913
No log 4.0741 220 0.7134 0.2438 0.7134 0.8446
No log 4.1111 222 0.8357 0.1822 0.8357 0.9142
No log 4.1481 224 0.8503 0.1822 0.8503 0.9221
No log 4.1852 226 0.7560 0.1764 0.7560 0.8695
No log 4.2222 228 0.6810 0.2116 0.6810 0.8252
No log 4.2593 230 0.6643 0.2274 0.6643 0.8150
No log 4.2963 232 0.6589 0.2116 0.6589 0.8117
No log 4.3333 234 0.6851 0.2248 0.6851 0.8277
No log 4.3704 236 0.7067 0.1925 0.7067 0.8406
No log 4.4074 238 0.7289 0.1925 0.7289 0.8537
No log 4.4444 240 0.7957 0.1508 0.7957 0.8920
No log 4.4815 242 0.8376 0.1508 0.8376 0.9152
No log 4.5185 244 0.8314 0.1508 0.8314 0.9118
No log 4.5556 246 0.7864 0.2111 0.7864 0.8868
No log 4.5926 248 0.7602 0.2572 0.7602 0.8719
No log 4.6296 250 0.7526 0.2572 0.7526 0.8676
No log 4.6667 252 0.7127 0.2919 0.7127 0.8442
No log 4.7037 254 0.7118 0.2649 0.7118 0.8437
No log 4.7407 256 0.7371 0.2231 0.7371 0.8586
No log 4.7778 258 0.7461 0.2800 0.7461 0.8638
No log 4.8148 260 0.8044 0.2263 0.8044 0.8969
No log 4.8519 262 0.8754 0.2222 0.8754 0.9357
No log 4.8889 264 0.9413 0.2290 0.9413 0.9702
No log 4.9259 266 0.8716 0.2389 0.8716 0.9336
No log 4.9630 268 0.7766 0.2549 0.7766 0.8812
No log 5.0 270 0.6721 0.2402 0.6721 0.8198
No log 5.0370 272 0.6318 0.2523 0.6318 0.7949
No log 5.0741 274 0.6492 0.2523 0.6492 0.8057
No log 5.1111 276 0.7090 0.2111 0.7090 0.8420
No log 5.1481 278 0.8433 0.2131 0.8433 0.9183
No log 5.1852 280 0.9126 0.2000 0.9126 0.9553
No log 5.2222 282 0.9233 0.2000 0.9233 0.9609
No log 5.2593 284 0.9099 0.2000 0.9099 0.9539
No log 5.2963 286 0.8354 0.2131 0.8354 0.9140
No log 5.3333 288 0.7966 0.1601 0.7966 0.8925
No log 5.3704 290 0.7596 0.1601 0.7596 0.8715
No log 5.4074 292 0.7217 0.1769 0.7217 0.8495
No log 5.4444 294 0.7237 0.1769 0.7237 0.8507
No log 5.4815 296 0.7396 0.1741 0.7396 0.8600
No log 5.5185 298 0.7523 0.2072 0.7523 0.8673
No log 5.5556 300 0.8027 0.1899 0.8027 0.8960
No log 5.5926 302 0.8063 0.2000 0.8063 0.8979
No log 5.6296 304 0.7514 0.2466 0.7514 0.8668
No log 5.6667 306 0.7160 0.2466 0.7160 0.8462
No log 5.7037 308 0.7386 0.2466 0.7386 0.8594
No log 5.7407 310 0.7630 0.2095 0.7630 0.8735
No log 5.7778 312 0.7860 0.2095 0.7860 0.8865
No log 5.8148 314 0.8198 0.2095 0.8198 0.9055
No log 5.8519 316 0.8902 0.2268 0.8902 0.9435
No log 5.8889 318 0.9209 0.2093 0.9209 0.9596
No log 5.9259 320 0.8495 0.2773 0.8495 0.9217
No log 5.9630 322 0.7236 0.3105 0.7236 0.8506
No log 6.0 324 0.6779 0.3562 0.6779 0.8233
No log 6.0370 326 0.6806 0.3642 0.6806 0.8250
No log 6.0741 328 0.6952 0.3549 0.6952 0.8338
No log 6.1111 330 0.7370 0.3275 0.7370 0.8585
No log 6.1481 332 0.7981 0.2628 0.7981 0.8934
No log 6.1852 334 0.8056 0.2628 0.8056 0.8976
No log 6.2222 336 0.7584 0.2865 0.7584 0.8709
No log 6.2593 338 0.7370 0.2694 0.7370 0.8585
No log 6.2963 340 0.7653 0.2715 0.7653 0.8748
No log 6.3333 342 0.7661 0.2715 0.7661 0.8753
No log 6.3704 344 0.7737 0.2767 0.7737 0.8796
No log 6.4074 346 0.8404 0.2628 0.8404 0.9167
No log 6.4444 348 0.8621 0.2095 0.8621 0.9285
No log 6.4815 350 0.8482 0.2095 0.8482 0.9210
No log 6.5185 352 0.8538 0.2095 0.8538 0.9240
No log 6.5556 354 0.8359 0.2000 0.8359 0.9143
No log 6.5926 356 0.7899 0.2000 0.7899 0.8887
No log 6.6296 358 0.7402 0.2256 0.7402 0.8603
No log 6.6667 360 0.7150 0.2372 0.7150 0.8456
No log 6.7037 362 0.6972 0.2707 0.6972 0.8350
No log 6.7407 364 0.6961 0.2707 0.6961 0.8343
No log 6.7778 366 0.7072 0.2279 0.7072 0.8410
No log 6.8148 368 0.7354 0.2328 0.7354 0.8575
No log 6.8519 370 0.7698 0.1932 0.7698 0.8774
No log 6.8889 372 0.8114 0.2000 0.8114 0.9008
No log 6.9259 374 0.8843 0.2000 0.8843 0.9404
No log 6.9630 376 0.9062 0.2000 0.9062 0.9519
No log 7.0 378 0.8702 0.2000 0.8702 0.9328
No log 7.0370 380 0.8608 0.2095 0.8608 0.9278
No log 7.0741 382 0.8760 0.2095 0.8760 0.9359
No log 7.1111 384 0.8578 0.2222 0.8578 0.9262
No log 7.1481 386 0.8147 0.2328 0.8147 0.9026
No log 7.1852 388 0.8022 0.2177 0.8022 0.8957
No log 7.2222 390 0.7903 0.2177 0.7903 0.8890
No log 7.2593 392 0.7943 0.2328 0.7943 0.8913
No log 7.2963 394 0.7749 0.2328 0.7749 0.8803
No log 7.3333 396 0.7859 0.2628 0.7859 0.8865
No log 7.3704 398 0.8105 0.25 0.8105 0.9003
No log 7.4074 400 0.8088 0.25 0.8088 0.8993
No log 7.4444 402 0.7847 0.25 0.7847 0.8859
No log 7.4815 404 0.7668 0.2330 0.7668 0.8757
No log 7.5185 406 0.7821 0.2417 0.7821 0.8844
No log 7.5556 408 0.7935 0.2549 0.7935 0.8908
No log 7.5926 410 0.8190 0.2628 0.8190 0.9050
No log 7.6296 412 0.8284 0.2628 0.8284 0.9102
No log 7.6667 414 0.8339 0.2432 0.8339 0.9132
No log 7.7037 416 0.8556 0.2038 0.8556 0.9250
No log 7.7407 418 0.8876 0.2038 0.8876 0.9421
No log 7.7778 420 0.8939 0.1914 0.8939 0.9455
No log 7.8148 422 0.8860 0.2038 0.8860 0.9413
No log 7.8519 424 0.8914 0.1914 0.8914 0.9441
No log 7.8889 426 0.9184 0.2268 0.9184 0.9583
No log 7.9259 428 0.9192 0.1914 0.9192 0.9588
No log 7.9630 430 0.8835 0.2038 0.8835 0.9399
No log 8.0 432 0.8632 0.2038 0.8632 0.9291
No log 8.0370 434 0.8474 0.2222 0.8474 0.9205
No log 8.0741 436 0.8414 0.2222 0.8414 0.9173
No log 8.1111 438 0.8386 0.2222 0.8386 0.9158
No log 8.1481 440 0.8583 0.2222 0.8583 0.9264
No log 8.1852 442 0.8767 0.2038 0.8767 0.9363
No log 8.2222 444 0.8826 0.2038 0.8826 0.9394
No log 8.2593 446 0.8868 0.2038 0.8868 0.9417
No log 8.2963 448 0.9027 0.2038 0.9027 0.9501
No log 8.3333 450 0.8893 0.2038 0.8893 0.9430
No log 8.3704 452 0.8841 0.2038 0.8841 0.9403
No log 8.4074 454 0.8614 0.2038 0.8614 0.9281
No log 8.4444 456 0.8398 0.2432 0.8398 0.9164
No log 8.4815 458 0.8453 0.2432 0.8453 0.9194
No log 8.5185 460 0.8777 0.2389 0.8777 0.9369
No log 8.5556 462 0.9319 0.2348 0.9319 0.9653
No log 8.5926 464 0.9878 0.2254 0.9878 0.9939
No log 8.6296 466 1.0157 0.2328 1.0157 1.0078
No log 8.6667 468 1.0023 0.2328 1.0023 1.0011
No log 8.7037 470 0.9644 0.2424 0.9644 0.9821
No log 8.7407 472 0.9228 0.2348 0.9228 0.9606
No log 8.7778 474 0.8744 0.2721 0.8744 0.9351
No log 8.8148 476 0.8386 0.2958 0.8386 0.9158
No log 8.8519 478 0.8217 0.2895 0.8217 0.9064
No log 8.8889 480 0.8182 0.2895 0.8182 0.9045
No log 8.9259 482 0.8111 0.2895 0.8111 0.9006
No log 8.9630 484 0.8128 0.2895 0.8128 0.9015
No log 9.0 486 0.8133 0.2895 0.8133 0.9018
No log 9.0370 488 0.8102 0.2895 0.8102 0.9001
No log 9.0741 490 0.8038 0.2895 0.8038 0.8965
No log 9.1111 492 0.7985 0.2895 0.7985 0.8936
No log 9.1481 494 0.7986 0.2895 0.7986 0.8936
No log 9.1852 496 0.7897 0.2557 0.7897 0.8886
No log 9.2222 498 0.7747 0.2557 0.7747 0.8802
0.2472 9.2593 500 0.7677 0.3015 0.7677 0.8762
0.2472 9.2963 502 0.7619 0.3015 0.7619 0.8729
0.2472 9.3333 504 0.7649 0.3015 0.7649 0.8746
0.2472 9.3704 506 0.7743 0.2808 0.7743 0.8799
0.2472 9.4074 508 0.7833 0.2953 0.7833 0.8851
0.2472 9.4444 510 0.7944 0.2557 0.7944 0.8913
0.2472 9.4815 512 0.8110 0.2773 0.8110 0.9005
0.2472 9.5185 514 0.8205 0.2773 0.8205 0.9058
0.2472 9.5556 516 0.8271 0.2773 0.8271 0.9095
0.2472 9.5926 518 0.8371 0.2773 0.8371 0.9149
0.2472 9.6296 520 0.8473 0.2840 0.8473 0.9205
0.2472 9.6667 522 0.8505 0.2840 0.8505 0.9222
0.2472 9.7037 524 0.8557 0.2466 0.8557 0.9250
0.2472 9.7407 526 0.8569 0.2466 0.8569 0.9257
0.2472 9.7778 528 0.8583 0.2466 0.8583 0.9265
0.2472 9.8148 530 0.8616 0.2466 0.8616 0.9282
0.2472 9.8519 532 0.8649 0.2466 0.8649 0.9300
0.2472 9.8889 534 0.8674 0.2348 0.8674 0.9313
0.2472 9.9259 536 0.8679 0.2348 0.8679 0.9316
0.2472 9.9630 538 0.8686 0.2348 0.8686 0.9320
0.2472 10.0 540 0.8688 0.2348 0.8688 0.9321

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
20
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MayBashendy/ArabicNewSplits_FineTuningAraBERT_AugV5_k15_task2_organization_fold1

Finetuned
(4,049)
this model