ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k10_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: 0.9526
  • Qwk: -0.0788
  • Mse: 0.9526
  • Rmse: 0.9760

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 0.0714 2 3.7931 -0.0163 3.7931 1.9476
No log 0.1429 4 1.7473 0.0943 1.7473 1.3218
No log 0.2143 6 1.2333 0.1067 1.2333 1.1105
No log 0.2857 8 1.2190 0.0586 1.2190 1.1041
No log 0.3571 10 1.1768 0.0586 1.1768 1.0848
No log 0.4286 12 1.1086 -0.0164 1.1086 1.0529
No log 0.5 14 1.0054 -0.0398 1.0054 1.0027
No log 0.5714 16 0.9601 -0.0638 0.9601 0.9798
No log 0.6429 18 1.0323 -0.1290 1.0323 1.0160
No log 0.7143 20 1.0820 -0.1575 1.0820 1.0402
No log 0.7857 22 1.0320 -0.1278 1.0320 1.0159
No log 0.8571 24 1.0578 -0.1920 1.0578 1.0285
No log 0.9286 26 1.0587 -0.1602 1.0587 1.0289
No log 1.0 28 1.1240 -0.0977 1.1240 1.0602
No log 1.0714 30 1.2122 -0.0987 1.2122 1.1010
No log 1.1429 32 1.2955 -0.0704 1.2955 1.1382
No log 1.2143 34 1.1396 -0.0982 1.1396 1.0675
No log 1.2857 36 1.2876 -0.0423 1.2876 1.1347
No log 1.3571 38 1.6237 0.0 1.6237 1.2742
No log 1.4286 40 1.4647 0.0 1.4647 1.2103
No log 1.5 42 1.3165 0.0 1.3165 1.1474
No log 1.5714 44 1.0069 -0.0728 1.0069 1.0035
No log 1.6429 46 0.7911 -0.0725 0.7911 0.8895
No log 1.7143 48 0.7300 -0.0069 0.7300 0.8544
No log 1.7857 50 0.7277 -0.0035 0.7277 0.8531
No log 1.8571 52 0.8114 0.1148 0.8114 0.9008
No log 1.9286 54 1.0719 -0.0207 1.0719 1.0353
No log 2.0 56 1.5630 0.0 1.5630 1.2502
No log 2.0714 58 1.7099 -0.0015 1.7099 1.3076
No log 2.1429 60 1.4068 -0.0207 1.4068 1.1861
No log 2.2143 62 0.9657 -0.1274 0.9657 0.9827
No log 2.2857 64 0.7900 -0.0725 0.7900 0.8888
No log 2.3571 66 0.7385 -0.0188 0.7385 0.8594
No log 2.4286 68 0.7256 0.0479 0.7256 0.8518
No log 2.5 70 0.7323 -0.0188 0.7323 0.8557
No log 2.5714 72 0.7420 -0.0188 0.7420 0.8614
No log 2.6429 74 0.7697 -0.0264 0.7697 0.8773
No log 2.7143 76 0.8371 -0.1676 0.8371 0.9150
No log 2.7857 78 1.2895 0.0379 1.2895 1.1356
No log 2.8571 80 1.6044 0.0 1.6044 1.2666
No log 2.9286 82 1.5662 0.0 1.5662 1.2515
No log 3.0 84 1.4110 0.0016 1.4110 1.1879
No log 3.0714 86 0.9468 0.0067 0.9468 0.9731
No log 3.1429 88 0.8110 -0.0215 0.8110 0.9006
No log 3.2143 90 1.2478 -0.0229 1.2478 1.1170
No log 3.2857 92 0.9894 -0.0490 0.9894 0.9947
No log 3.3571 94 0.7212 0.0416 0.7212 0.8492
No log 3.4286 96 0.9227 0.0848 0.9227 0.9606
No log 3.5 98 1.2372 0.0279 1.2372 1.1123
No log 3.5714 100 1.3020 0.0 1.3020 1.1410
No log 3.6429 102 0.9944 -0.0331 0.9944 0.9972
No log 3.7143 104 0.7864 -0.0240 0.7864 0.8868
No log 3.7857 106 0.7673 0.1952 0.7673 0.8759
No log 3.8571 108 0.7475 0.0334 0.7475 0.8646
No log 3.9286 110 0.7344 0.0334 0.7344 0.8570
No log 4.0 112 0.7376 0.0334 0.7376 0.8588
No log 4.0714 114 0.7334 0.0964 0.7334 0.8564
No log 4.1429 116 0.7690 0.1027 0.7690 0.8769
No log 4.2143 118 0.7795 0.0759 0.7795 0.8829
No log 4.2857 120 0.7755 0.0714 0.7755 0.8806
No log 4.3571 122 0.7626 0.1815 0.7626 0.8733
No log 4.4286 124 0.7826 0.0978 0.7826 0.8846
No log 4.5 126 0.7688 0.1240 0.7688 0.8768
No log 4.5714 128 1.0877 0.0169 1.0877 1.0429
No log 4.6429 130 1.3393 0.1042 1.3393 1.1573
No log 4.7143 132 0.9039 -0.0283 0.9039 0.9508
No log 4.7857 134 0.9099 0.1300 0.9099 0.9539
No log 4.8571 136 0.9545 0.0129 0.9545 0.9770
No log 4.9286 138 1.1001 0.0962 1.1001 1.0488
No log 5.0 140 0.9865 -0.0287 0.9865 0.9932
No log 5.0714 142 0.9780 0.0638 0.9780 0.9889
No log 5.1429 144 0.9058 0.0925 0.9058 0.9517
No log 5.2143 146 1.1529 0.0698 1.1529 1.0737
No log 5.2857 148 1.4991 0.0557 1.4991 1.2244
No log 5.3571 150 1.2114 0.0324 1.2114 1.1007
No log 5.4286 152 0.8469 0.1299 0.8469 0.9203
No log 5.5 154 0.8805 0.0966 0.8805 0.9384
No log 5.5714 156 0.7984 0.1734 0.7984 0.8935
No log 5.6429 158 1.0321 -0.0486 1.0321 1.0159
No log 5.7143 160 1.4012 -0.0191 1.4012 1.1837
No log 5.7857 162 1.3213 0.0064 1.3213 1.1495
No log 5.8571 164 0.9073 -0.0182 0.9073 0.9525
No log 5.9286 166 0.6986 0.1259 0.6986 0.8358
No log 6.0 168 0.7069 0.1318 0.7069 0.8408
No log 6.0714 170 0.7476 0.1553 0.7476 0.8646
No log 6.1429 172 0.8006 0.1553 0.8006 0.8947
No log 6.2143 174 0.9234 0.0091 0.9234 0.9610
No log 6.2857 176 0.9791 0.0856 0.9791 0.9895
No log 6.3571 178 1.0343 0.0173 1.0343 1.0170
No log 6.4286 180 1.0143 -0.0087 1.0143 1.0071
No log 6.5 182 0.9659 0.0606 0.9659 0.9828
No log 6.5714 184 0.8868 0.1277 0.8868 0.9417
No log 6.6429 186 0.8339 0.0277 0.8339 0.9132
No log 6.7143 188 0.7655 0.1769 0.7655 0.8749
No log 6.7857 190 0.8102 -0.0295 0.8102 0.9001
No log 6.8571 192 0.8084 -0.0295 0.8084 0.8991
No log 6.9286 194 0.7869 0.0985 0.7869 0.8870
No log 7.0 196 0.8275 -0.0195 0.8275 0.9097
No log 7.0714 198 0.8337 0.0570 0.8337 0.9131
No log 7.1429 200 0.8738 -0.0095 0.8738 0.9348
No log 7.2143 202 0.9031 0.0563 0.9031 0.9503
No log 7.2857 204 0.8760 0.0093 0.8760 0.9359
No log 7.3571 206 0.8605 -0.0238 0.8605 0.9276
No log 7.4286 208 0.8298 0.0861 0.8298 0.9109
No log 7.5 210 0.8695 0.2107 0.8695 0.9325
No log 7.5714 212 0.9273 0.0438 0.9273 0.9629
No log 7.6429 214 0.8235 0.1705 0.8235 0.9074
No log 7.7143 216 0.8149 0.1751 0.8149 0.9027
No log 7.7857 218 0.8731 0.1379 0.8731 0.9344
No log 7.8571 220 0.9276 0.0068 0.9276 0.9631
No log 7.9286 222 0.8441 0.1553 0.8441 0.9188
No log 8.0 224 0.8781 -0.0180 0.8781 0.9371
No log 8.0714 226 0.8901 0.0778 0.8901 0.9434
No log 8.1429 228 0.9447 0.0562 0.9447 0.9720
No log 8.2143 230 1.1423 -0.0479 1.1423 1.0688
No log 8.2857 232 1.0510 0.0336 1.0510 1.0252
No log 8.3571 234 1.0121 -0.1022 1.0121 1.0060
No log 8.4286 236 1.0280 -0.0474 1.0280 1.0139
No log 8.5 238 1.0271 0.0260 1.0271 1.0134
No log 8.5714 240 0.9250 -0.1471 0.9250 0.9618
No log 8.6429 242 0.9333 0.0095 0.9333 0.9661
No log 8.7143 244 1.1070 -0.0526 1.1070 1.0521
No log 8.7857 246 0.9818 -0.0101 0.9818 0.9908
No log 8.8571 248 0.8289 0.1304 0.8289 0.9104
No log 8.9286 250 0.8686 -0.0996 0.8686 0.9320
No log 9.0 252 0.8870 -0.0180 0.8870 0.9418
No log 9.0714 254 0.8497 0.0469 0.8497 0.9218
No log 9.1429 256 0.8600 0.1047 0.8600 0.9274
No log 9.2143 258 1.0225 0.0283 1.0225 1.0112
No log 9.2857 260 0.9274 0.0041 0.9274 0.9630
No log 9.3571 262 0.7464 0.1379 0.7464 0.8640
No log 9.4286 264 0.7762 0.0556 0.7762 0.8810
No log 9.5 266 0.7790 0.1340 0.7790 0.8826
No log 9.5714 268 0.8932 0.0562 0.8932 0.9451
No log 9.6429 270 1.4329 -0.0356 1.4329 1.1970
No log 9.7143 272 1.6138 -0.0855 1.6138 1.2703
No log 9.7857 274 1.3026 -0.0557 1.3026 1.1413
No log 9.8571 276 0.9928 0.0236 0.9928 0.9964
No log 9.9286 278 1.0198 -0.0708 1.0198 1.0098
No log 10.0 280 0.9709 -0.0111 0.9709 0.9853
No log 10.0714 282 0.9009 0.0265 0.9009 0.9492
No log 10.1429 284 0.9371 -0.0390 0.9371 0.9681
No log 10.2143 286 0.9192 -0.0371 0.9192 0.9587
No log 10.2857 288 0.8400 0.0840 0.8400 0.9165
No log 10.3571 290 0.8697 -0.0277 0.8697 0.9326
No log 10.4286 292 0.9107 0.0856 0.9107 0.9543
No log 10.5 294 1.0403 0.0792 1.0403 1.0199
No log 10.5714 296 1.0674 0.1364 1.0674 1.0332
No log 10.6429 298 1.0332 -0.1097 1.0332 1.0164
No log 10.7143 300 0.9712 0.0369 0.9712 0.9855
No log 10.7857 302 0.9145 -0.0345 0.9145 0.9563
No log 10.8571 304 0.8602 0.1751 0.8602 0.9275
No log 10.9286 306 0.9377 0.0118 0.9377 0.9683
No log 11.0 308 0.9811 0.0407 0.9811 0.9905
No log 11.0714 310 0.8867 0.0549 0.8867 0.9417
No log 11.1429 312 0.8115 0.1311 0.8115 0.9008
No log 11.2143 314 0.8057 0.1287 0.8057 0.8976
No log 11.2857 316 0.8025 0.1718 0.8025 0.8958
No log 11.3571 318 0.8138 0.1292 0.8138 0.9021
No log 11.4286 320 0.8667 -0.0731 0.8667 0.9310
No log 11.5 322 0.8843 -0.0778 0.8843 0.9404
No log 11.5714 324 0.8464 0.0732 0.8464 0.9200
No log 11.6429 326 0.8419 0.1277 0.8419 0.9176
No log 11.7143 328 0.8572 0.1287 0.8572 0.9258
No log 11.7857 330 0.8832 0.0308 0.8832 0.9398
No log 11.8571 332 0.9223 0.0764 0.9223 0.9604
No log 11.9286 334 0.9458 0.0069 0.9458 0.9725
No log 12.0 336 0.9631 -0.0887 0.9631 0.9814
No log 12.0714 338 0.9879 -0.1155 0.9879 0.9939
No log 12.1429 340 0.9288 -0.1187 0.9288 0.9637
No log 12.2143 342 0.8342 0.1292 0.8342 0.9133
No log 12.2857 344 0.8348 0.0889 0.8348 0.9137
No log 12.3571 346 0.8326 0.0247 0.8326 0.9125
No log 12.4286 348 0.9171 -0.0008 0.9171 0.9576
No log 12.5 350 0.9341 0.0017 0.9341 0.9665
No log 12.5714 352 0.9119 -0.0073 0.9119 0.9549
No log 12.6429 354 0.9880 -0.0334 0.9880 0.9940
No log 12.7143 356 1.0100 -0.0960 1.0100 1.0050
No log 12.7857 358 1.0344 -0.0491 1.0344 1.0171
No log 12.8571 360 1.0017 -0.0347 1.0017 1.0008
No log 12.9286 362 0.9491 -0.0127 0.9491 0.9742
No log 13.0 364 0.9064 -0.1135 0.9064 0.9521
No log 13.0714 366 0.8506 -0.0778 0.8506 0.9223
No log 13.1429 368 0.8235 -0.0170 0.8235 0.9074
No log 13.2143 370 0.8525 -0.0163 0.8525 0.9233
No log 13.2857 372 0.8695 -0.0127 0.8695 0.9325
No log 13.3571 374 0.8948 -0.0743 0.8948 0.9459
No log 13.4286 376 0.9515 0.0068 0.9515 0.9755
No log 13.5 378 0.9721 0.0597 0.9721 0.9860
No log 13.5714 380 0.9791 -0.0379 0.9791 0.9895
No log 13.6429 382 0.9467 0.0447 0.9467 0.9730
No log 13.7143 384 0.9084 0.0688 0.9084 0.9531
No log 13.7857 386 0.9623 -0.0345 0.9623 0.9810
No log 13.8571 388 0.9111 0.0118 0.9111 0.9545
No log 13.9286 390 0.8593 0.0749 0.8593 0.9270
No log 14.0 392 0.8730 0.1184 0.8730 0.9343
No log 14.0714 394 0.9177 0.0230 0.9177 0.9580
No log 14.1429 396 0.8825 0.1221 0.8825 0.9394
No log 14.2143 398 0.8820 0.0129 0.8820 0.9391
No log 14.2857 400 0.8828 0.0129 0.8828 0.9396
No log 14.3571 402 0.8840 0.0129 0.8840 0.9402
No log 14.4286 404 0.8783 0.0757 0.8783 0.9372
No log 14.5 406 0.9338 0.0153 0.9338 0.9663
No log 14.5714 408 0.9794 -0.0179 0.9794 0.9897
No log 14.6429 410 0.9838 0.0560 0.9838 0.9919
No log 14.7143 412 0.9366 0.0790 0.9366 0.9678
No log 14.7857 414 0.9047 -0.0099 0.9047 0.9512
No log 14.8571 416 0.9191 -0.0303 0.9191 0.9587
No log 14.9286 418 0.9208 0.0043 0.9208 0.9596
No log 15.0 420 0.8501 -0.0274 0.8501 0.9220
No log 15.0714 422 0.8239 0.0465 0.8239 0.9077
No log 15.1429 424 0.8280 0.0465 0.8280 0.9100
No log 15.2143 426 0.8369 -0.0287 0.8369 0.9148
No log 15.2857 428 1.0176 -0.0097 1.0176 1.0087
No log 15.3571 430 1.0344 -0.0097 1.0344 1.0170
No log 15.4286 432 0.9052 -0.0672 0.9052 0.9514
No log 15.5 434 0.9449 0.0526 0.9449 0.9721
No log 15.5714 436 0.9523 -0.0860 0.9523 0.9759
No log 15.6429 438 1.0366 0.0041 1.0366 1.0182
No log 15.7143 440 1.4326 -0.1050 1.4326 1.1969
No log 15.7857 442 1.5714 -0.0553 1.5714 1.2535
No log 15.8571 444 1.1718 -0.0146 1.1718 1.0825
No log 15.9286 446 0.9141 -0.0240 0.9141 0.9561
No log 16.0 448 0.8398 0.0318 0.8398 0.9164
No log 16.0714 450 0.8412 0.0159 0.8412 0.9172
No log 16.1429 452 0.9787 -0.0870 0.9787 0.9893
No log 16.2143 454 1.0803 -0.0526 1.0803 1.0394
No log 16.2857 456 1.0280 -0.0862 1.0280 1.0139
No log 16.3571 458 0.9078 0.0344 0.9078 0.9528
No log 16.4286 460 0.9297 0.0268 0.9297 0.9642
No log 16.5 462 0.9639 0.0362 0.9639 0.9818
No log 16.5714 464 1.0789 0.0350 1.0789 1.0387
No log 16.6429 466 1.0780 -0.0454 1.0780 1.0383
No log 16.7143 468 1.0488 -0.0454 1.0488 1.0241
No log 16.7857 470 0.9818 -0.1214 0.9818 0.9909
No log 16.8571 472 0.9776 -0.1212 0.9776 0.9887
No log 16.9286 474 0.9819 -0.1212 0.9819 0.9909
No log 17.0 476 0.9778 -0.0809 0.9778 0.9888
No log 17.0714 478 0.8960 0.0123 0.8960 0.9466
No log 17.1429 480 0.8716 0.0884 0.8716 0.9336
No log 17.2143 482 0.9082 -0.0128 0.9082 0.9530
No log 17.2857 484 0.8911 0.0230 0.8911 0.9440
No log 17.3571 486 0.8673 -0.0163 0.8673 0.9313
No log 17.4286 488 0.9511 0.0040 0.9511 0.9752
No log 17.5 490 1.1006 0.0209 1.1006 1.0491
No log 17.5714 492 1.0643 0.0233 1.0643 1.0317
No log 17.6429 494 0.9170 0.0611 0.9170 0.9576
No log 17.7143 496 0.8784 0.0549 0.8784 0.9372
No log 17.7857 498 0.9552 0.1014 0.9552 0.9774
0.3839 17.8571 500 0.9365 0.0081 0.9365 0.9677
0.3839 17.9286 502 0.8600 -0.0939 0.8600 0.9274
0.3839 18.0 504 0.8892 0.0600 0.8892 0.9430
0.3839 18.0714 506 0.9152 0.0456 0.9152 0.9566
0.3839 18.1429 508 0.8781 0.0600 0.8781 0.9371
0.3839 18.2143 510 0.8771 0.0225 0.8771 0.9366
0.3839 18.2857 512 0.8795 0.0884 0.8795 0.9378
0.3839 18.3571 514 0.9006 -0.0339 0.9006 0.9490
0.3839 18.4286 516 0.8916 0.1347 0.8916 0.9443
0.3839 18.5 518 0.9338 -0.0262 0.9338 0.9663
0.3839 18.5714 520 1.0489 0.0040 1.0489 1.0241
0.3839 18.6429 522 1.1653 -0.0845 1.1653 1.0795
0.3839 18.7143 524 1.1465 -0.1169 1.1465 1.0707
0.3839 18.7857 526 1.0669 0.0497 1.0669 1.0329
0.3839 18.8571 528 0.9965 -0.1569 0.9965 0.9983
0.3839 18.9286 530 0.9750 -0.0989 0.9750 0.9874
0.3839 19.0 532 0.9294 -0.0479 0.9294 0.9641
0.3839 19.0714 534 0.9317 -0.0295 0.9317 0.9652
0.3839 19.1429 536 0.9526 -0.0788 0.9526 0.9760

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
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_k10_task3_organization

Finetuned
(4040)
this model