ArabicNewSplits7_FineTuningAraBERT_run1_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: 0.8480
  • Qwk: 0.0688
  • Mse: 0.8480
  • Rmse: 0.9209

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 3.8672 0.0005 3.8672 1.9665
No log 0.6667 4 2.3615 -0.0178 2.3615 1.5367
No log 1.0 6 1.0114 0.1007 1.0114 1.0057
No log 1.3333 8 0.8318 0.0953 0.8318 0.9121
No log 1.6667 10 1.7071 -0.0811 1.7071 1.3065
No log 2.0 12 1.6488 -0.1067 1.6488 1.2841
No log 2.3333 14 1.0048 0.0182 1.0048 1.0024
No log 2.6667 16 0.7089 0.0460 0.7089 0.8420
No log 3.0 18 0.7955 -0.0331 0.7955 0.8919
No log 3.3333 20 1.0761 0.0025 1.0761 1.0373
No log 3.6667 22 1.0131 -0.0862 1.0131 1.0065
No log 4.0 24 0.9022 -0.0373 0.9022 0.9499
No log 4.3333 26 0.8261 0.0714 0.8261 0.9089
No log 4.6667 28 0.9477 -0.0341 0.9477 0.9735
No log 5.0 30 1.5605 0.0346 1.5605 1.2492
No log 5.3333 32 1.5050 0.0389 1.5050 1.2268
No log 5.6667 34 0.8865 -0.0230 0.8865 0.9416
No log 6.0 36 0.8403 0.0 0.8403 0.9167
No log 6.3333 38 0.8699 -0.0767 0.8699 0.9327
No log 6.6667 40 1.2822 0.0586 1.2822 1.1323
No log 7.0 42 1.2832 0.0512 1.2832 1.1328
No log 7.3333 44 0.9199 -0.0079 0.9199 0.9591
No log 7.6667 46 0.8678 -0.0633 0.8678 0.9316
No log 8.0 48 0.9948 -0.0187 0.9948 0.9974
No log 8.3333 50 0.9540 -0.0820 0.9540 0.9767
No log 8.6667 52 0.8954 0.0438 0.8954 0.9463
No log 9.0 54 1.7033 0.0679 1.7033 1.3051
No log 9.3333 56 2.0628 0.0268 2.0628 1.4362
No log 9.6667 58 1.3791 0.0380 1.3791 1.1743
No log 10.0 60 0.8245 0.0071 0.8245 0.9080
No log 10.3333 62 0.8480 -0.0717 0.8480 0.9209
No log 10.6667 64 0.8396 0.0598 0.8396 0.9163
No log 11.0 66 0.8286 -0.1006 0.8286 0.9103
No log 11.3333 68 0.9945 -0.0809 0.9945 0.9973
No log 11.6667 70 1.1175 -0.0466 1.1175 1.0571
No log 12.0 72 0.9815 0.0470 0.9815 0.9907
No log 12.3333 74 0.9345 0.0608 0.9345 0.9667
No log 12.6667 76 0.9190 -0.0355 0.9190 0.9587
No log 13.0 78 0.9015 0.0091 0.9015 0.9495
No log 13.3333 80 0.9164 -0.0425 0.9164 0.9573
No log 13.6667 82 0.9317 -0.0425 0.9317 0.9652
No log 14.0 84 0.9076 -0.0209 0.9076 0.9527
No log 14.3333 86 0.9894 0.0114 0.9894 0.9947
No log 14.6667 88 1.0082 0.0713 1.0082 1.0041
No log 15.0 90 0.9902 0.1818 0.9902 0.9951
No log 15.3333 92 0.9474 0.1548 0.9474 0.9734
No log 15.6667 94 0.8895 0.1003 0.8895 0.9431
No log 16.0 96 0.9002 0.0504 0.9002 0.9488
No log 16.3333 98 0.8441 0.1263 0.8441 0.9187
No log 16.6667 100 0.8897 0.0579 0.8897 0.9433
No log 17.0 102 0.8640 0.2057 0.8640 0.9295
No log 17.3333 104 0.8439 0.1561 0.8439 0.9186
No log 17.6667 106 0.8383 0.1048 0.8383 0.9156
No log 18.0 108 0.8399 0.0732 0.8399 0.9165
No log 18.3333 110 0.8730 0.0025 0.8730 0.9344
No log 18.6667 112 0.9065 0.1049 0.9065 0.9521
No log 19.0 114 0.9443 0.0920 0.9443 0.9717
No log 19.3333 116 0.9137 0.1176 0.9137 0.9559
No log 19.6667 118 0.8982 0.0494 0.8982 0.9477
No log 20.0 120 0.8863 0.0935 0.8863 0.9415
No log 20.3333 122 0.8746 0.1092 0.8746 0.9352
No log 20.6667 124 0.8487 0.0679 0.8487 0.9212
No log 21.0 126 0.8373 -0.0076 0.8373 0.9150
No log 21.3333 128 0.8710 0.1359 0.8710 0.9333
No log 21.6667 130 0.8774 0.0755 0.8774 0.9367
No log 22.0 132 0.9526 0.0106 0.9526 0.9760
No log 22.3333 134 1.0114 -0.0133 1.0114 1.0057
No log 22.6667 136 0.9398 0.1379 0.9398 0.9694
No log 23.0 138 0.9636 0.0741 0.9636 0.9816
No log 23.3333 140 0.9283 0.0087 0.9283 0.9635
No log 23.6667 142 0.8847 0.1179 0.8847 0.9406
No log 24.0 144 0.9197 0.0451 0.9197 0.9590
No log 24.3333 146 0.9112 0.0652 0.9112 0.9546
No log 24.6667 148 1.0176 0.0856 1.0176 1.0088
No log 25.0 150 0.9684 -0.0382 0.9684 0.9841
No log 25.3333 152 0.9446 0.0283 0.9446 0.9719
No log 25.6667 154 0.8454 0.0313 0.8454 0.9195
No log 26.0 156 0.8351 0.1267 0.8351 0.9138
No log 26.3333 158 0.8497 0.0408 0.8497 0.9218
No log 26.6667 160 0.9772 0.1403 0.9772 0.9885
No log 27.0 162 1.1843 -0.0411 1.1843 1.0882
No log 27.3333 164 1.1515 0.1698 1.1515 1.0731
No log 27.6667 166 1.3126 0.0794 1.3126 1.1457
No log 28.0 168 1.4562 0.12 1.4562 1.2067
No log 28.3333 170 1.2624 0.0613 1.2624 1.1236
No log 28.6667 172 1.0220 0.1691 1.0220 1.0109
No log 29.0 174 0.9526 0.1811 0.9526 0.9760
No log 29.3333 176 0.9251 0.1103 0.9251 0.9618
No log 29.6667 178 0.8605 0.0660 0.8605 0.9276
No log 30.0 180 0.8115 0.0327 0.8115 0.9008
No log 30.3333 182 0.8075 0.0269 0.8075 0.8986
No log 30.6667 184 0.8429 0.0562 0.8429 0.9181
No log 31.0 186 0.9981 0.0134 0.9981 0.9990
No log 31.3333 188 0.9490 0.0207 0.9490 0.9742
No log 31.6667 190 0.8133 0.0588 0.8133 0.9018
No log 32.0 192 0.8560 0.0123 0.8560 0.9252
No log 32.3333 194 0.9673 0.1334 0.9673 0.9835
No log 32.6667 196 0.8928 0.1255 0.8928 0.9449
No log 33.0 198 0.8944 -0.0355 0.8944 0.9457
No log 33.3333 200 0.9296 -0.0391 0.9296 0.9642
No log 33.6667 202 0.9363 -0.0030 0.9363 0.9676
No log 34.0 204 0.8908 -0.0735 0.8908 0.9438
No log 34.3333 206 0.8520 -0.0132 0.8520 0.9230
No log 34.6667 208 0.8656 0.0344 0.8656 0.9304
No log 35.0 210 0.8631 0.0408 0.8631 0.9290
No log 35.3333 212 0.8628 0.0441 0.8628 0.9289
No log 35.6667 214 0.8640 -0.0218 0.8640 0.9295
No log 36.0 216 0.9658 0.1337 0.9658 0.9828
No log 36.3333 218 0.9432 0.1065 0.9432 0.9712
No log 36.6667 220 0.8621 -0.0573 0.8621 0.9285
No log 37.0 222 0.9054 0.0909 0.9054 0.9515
No log 37.3333 224 0.9260 0.0919 0.9260 0.9623
No log 37.6667 226 0.8797 0.0071 0.8797 0.9379
No log 38.0 228 0.8614 0.0529 0.8614 0.9281
No log 38.3333 230 0.8784 0.0851 0.8784 0.9372
No log 38.6667 232 0.8642 0.1050 0.8642 0.9296
No log 39.0 234 0.8944 0.1635 0.8944 0.9457
No log 39.3333 236 0.9294 0.0559 0.9294 0.9640
No log 39.6667 238 0.9125 0.1754 0.9125 0.9552
No log 40.0 240 0.9662 0.0994 0.9662 0.9829
No log 40.3333 242 1.0393 0.0539 1.0393 1.0195
No log 40.6667 244 0.9768 0.0927 0.9768 0.9883
No log 41.0 246 0.9054 0.1400 0.9054 0.9515
No log 41.3333 248 0.9114 0.1255 0.9114 0.9547
No log 41.6667 250 0.9234 0.1255 0.9234 0.9609
No log 42.0 252 0.8731 0.1647 0.8731 0.9344
No log 42.3333 254 0.8436 0.0196 0.8436 0.9185
No log 42.6667 256 0.8753 0.1144 0.8753 0.9356
No log 43.0 258 0.8903 0.1104 0.8903 0.9436
No log 43.3333 260 0.8826 0.1144 0.8826 0.9395
No log 43.6667 262 0.8465 0.0196 0.8465 0.9200
No log 44.0 264 0.8582 0.0 0.8582 0.9264
No log 44.3333 266 0.8750 0.1267 0.8750 0.9354
No log 44.6667 268 0.8763 0.0408 0.8763 0.9361
No log 45.0 270 0.8671 0.0688 0.8671 0.9312
No log 45.3333 272 0.8728 0.0408 0.8728 0.9342
No log 45.6667 274 0.8944 0.1635 0.8944 0.9457
No log 46.0 276 0.8849 0.1259 0.8849 0.9407
No log 46.3333 278 0.8556 0.0804 0.8556 0.9250
No log 46.6667 280 0.8424 0.0804 0.8424 0.9178
No log 47.0 282 0.8224 0.0791 0.8224 0.9069
No log 47.3333 284 0.8268 0.1095 0.8268 0.9093
No log 47.6667 286 0.8679 0.0917 0.8679 0.9316
No log 48.0 288 0.9069 0.0805 0.9069 0.9523
No log 48.3333 290 0.8887 0.1228 0.8887 0.9427
No log 48.6667 292 0.8557 0.1448 0.8557 0.9251
No log 49.0 294 0.9060 0.1255 0.9060 0.9518
No log 49.3333 296 0.9622 0.0578 0.9622 0.9809
No log 49.6667 298 0.9161 0.1251 0.9161 0.9572
No log 50.0 300 0.8530 0.0755 0.8530 0.9236
No log 50.3333 302 0.8308 0.1415 0.8308 0.9115
No log 50.6667 304 0.8746 0.0876 0.8746 0.9352
No log 51.0 306 0.9158 0.0700 0.9158 0.9570
No log 51.3333 308 0.9182 0.1145 0.9182 0.9582
No log 51.6667 310 0.9172 0.1145 0.9172 0.9577
No log 52.0 312 0.8785 0.0920 0.8785 0.9373
No log 52.3333 314 0.8377 0.0733 0.8377 0.9153
No log 52.6667 316 0.8260 0.0810 0.8260 0.9088
No log 53.0 318 0.8242 0.0764 0.8242 0.9079
No log 53.3333 320 0.8359 0.0660 0.8359 0.9143
No log 53.6667 322 0.8920 0.0847 0.8920 0.9444
No log 54.0 324 0.9213 0.1145 0.9213 0.9599
No log 54.3333 326 0.8992 0.0847 0.8992 0.9483
No log 54.6667 328 0.8344 0.0690 0.8344 0.9135
No log 55.0 330 0.8167 0.0690 0.8167 0.9037
No log 55.3333 332 0.8201 0.0611 0.8201 0.9056
No log 55.6667 334 0.7958 0.0269 0.7958 0.8921
No log 56.0 336 0.8039 0.0376 0.8039 0.8966
No log 56.3333 338 0.8096 0.0840 0.8096 0.8998
No log 56.6667 340 0.7989 0.0376 0.7989 0.8938
No log 57.0 342 0.7990 0.1144 0.7990 0.8939
No log 57.3333 344 0.8123 0.0650 0.8123 0.9013
No log 57.6667 346 0.8116 0.1144 0.8116 0.9009
No log 58.0 348 0.8140 0.0798 0.8140 0.9022
No log 58.3333 350 0.8282 0.0 0.8282 0.9101
No log 58.6667 352 0.8445 0.0690 0.8445 0.9190
No log 59.0 354 0.8879 0.1003 0.8879 0.9423
No log 59.3333 356 0.9630 0.0283 0.9630 0.9813
No log 59.6667 358 0.9748 0.0644 0.9748 0.9873
No log 60.0 360 0.9646 0.1065 0.9646 0.9821
No log 60.3333 362 0.9544 0.1104 0.9544 0.9770
No log 60.6667 364 0.9194 0.0810 0.9194 0.9588
No log 61.0 366 0.8813 0.0205 0.8813 0.9388
No log 61.3333 368 0.8742 0.0175 0.8742 0.9350
No log 61.6667 370 0.8858 0.0470 0.8858 0.9412
No log 62.0 372 0.8836 0.0470 0.8836 0.9400
No log 62.3333 374 0.8685 -0.0274 0.8685 0.9319
No log 62.6667 376 0.8559 -0.1013 0.8559 0.9251
No log 63.0 378 0.8662 -0.0629 0.8662 0.9307
No log 63.3333 380 0.8871 0.0805 0.8871 0.9419
No log 63.6667 382 0.8877 0.0805 0.8877 0.9422
No log 64.0 384 0.8520 -0.0295 0.8520 0.9230
No log 64.3333 386 0.8340 -0.0274 0.8340 0.9132
No log 64.6667 388 0.8390 -0.0274 0.8390 0.9159
No log 65.0 390 0.8369 -0.0274 0.8369 0.9148
No log 65.3333 392 0.8426 -0.0274 0.8426 0.9180
No log 65.6667 394 0.8636 -0.0251 0.8636 0.9293
No log 66.0 396 0.8822 0.0113 0.8822 0.9393
No log 66.3333 398 0.8633 -0.0251 0.8633 0.9292
No log 66.6667 400 0.8553 -0.0186 0.8553 0.9248
No log 67.0 402 0.8535 -0.0479 0.8535 0.9238
No log 67.3333 404 0.8574 0.0441 0.8574 0.9260
No log 67.6667 406 0.8719 -0.0070 0.8719 0.9338
No log 68.0 408 0.9045 0.0888 0.9045 0.9511
No log 68.3333 410 0.9370 0.0775 0.9370 0.9680
No log 68.6667 412 0.9544 0.0378 0.9544 0.9769
No log 69.0 414 0.9557 -0.0028 0.9557 0.9776
No log 69.3333 416 0.9244 0.0038 0.9244 0.9615
No log 69.6667 418 0.8796 0.0586 0.8796 0.9379
No log 70.0 420 0.8617 0.0441 0.8617 0.9283
No log 70.3333 422 0.8765 0.1315 0.8765 0.9362
No log 70.6667 424 0.8730 0.0441 0.8730 0.9343
No log 71.0 426 0.8619 -0.0025 0.8619 0.9284
No log 71.3333 428 0.8703 0.0226 0.8703 0.9329
No log 71.6667 430 0.8891 0.0538 0.8891 0.9429
No log 72.0 432 0.9020 0.0504 0.9020 0.9497
No log 72.3333 434 0.9195 0.0438 0.9195 0.9589
No log 72.6667 436 0.9227 0.0016 0.9227 0.9606
No log 73.0 438 0.9328 0.0016 0.9328 0.9658
No log 73.3333 440 0.9265 0.0016 0.9265 0.9626
No log 73.6667 442 0.9094 0.0438 0.9094 0.9536
No log 74.0 444 0.8856 0.0538 0.8856 0.9411
No log 74.3333 446 0.8771 0.1095 0.8771 0.9365
No log 74.6667 448 0.8690 0.0295 0.8690 0.9322
No log 75.0 450 0.8609 0.0313 0.8609 0.9279
No log 75.3333 452 0.8485 0.0377 0.8485 0.9211
No log 75.6667 454 0.8372 0.0816 0.8372 0.9150
No log 76.0 456 0.8245 0.0764 0.8245 0.9080
No log 76.3333 458 0.8196 0.0764 0.8196 0.9053
No log 76.6667 460 0.8243 0.0690 0.8243 0.9079
No log 77.0 462 0.8415 0.0650 0.8415 0.9173
No log 77.3333 464 0.8578 0.0650 0.8578 0.9262
No log 77.6667 466 0.8691 0.0551 0.8691 0.9322
No log 78.0 468 0.8623 0.0597 0.8623 0.9286
No log 78.3333 470 0.8522 0.0660 0.8522 0.9231
No log 78.6667 472 0.8455 0.0660 0.8455 0.9195
No log 79.0 474 0.8394 0.0650 0.8394 0.9162
No log 79.3333 476 0.8371 0.0650 0.8371 0.9149
No log 79.6667 478 0.8365 0.0650 0.8365 0.9146
No log 80.0 480 0.8337 0.0650 0.8337 0.9130
No log 80.3333 482 0.8299 0.0236 0.8299 0.9110
No log 80.6667 484 0.8261 0.0717 0.8261 0.9089
No log 81.0 486 0.8262 0.1184 0.8262 0.9090
No log 81.3333 488 0.8326 0.1184 0.8326 0.9124
No log 81.6667 490 0.8363 0.1184 0.8363 0.9145
No log 82.0 492 0.8477 0.1093 0.8477 0.9207
No log 82.3333 494 0.8606 0.1093 0.8606 0.9277
No log 82.6667 496 0.8734 0.0618 0.8734 0.9346
No log 83.0 498 0.8931 0.1228 0.8931 0.9450
0.2127 83.3333 500 0.8986 0.1228 0.8986 0.9480
0.2127 83.6667 502 0.8959 0.1228 0.8959 0.9465
0.2127 84.0 504 0.8851 0.1225 0.8851 0.9408
0.2127 84.3333 506 0.8707 0.0562 0.8707 0.9331
0.2127 84.6667 508 0.8575 0.0679 0.8575 0.9260
0.2127 85.0 510 0.8480 0.0688 0.8480 0.9209

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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_run1_AugV5_k1_task3_organization

Finetuned
(4023)
this model