ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k3_task1_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: 0.9745
  • Qwk: 0.5781
  • Mse: 0.9745
  • Rmse: 0.9871

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 0.1333 2 5.3751 -0.0256 5.3751 2.3184
No log 0.2667 4 3.0781 0.0814 3.0781 1.7545
No log 0.4 6 1.8438 0.0881 1.8438 1.3579
No log 0.5333 8 1.4676 0.1608 1.4676 1.2114
No log 0.6667 10 1.3754 0.0810 1.3754 1.1728
No log 0.8 12 1.4381 0.1156 1.4381 1.1992
No log 0.9333 14 1.3326 0.1510 1.3326 1.1544
No log 1.0667 16 1.3999 0.1745 1.3999 1.1832
No log 1.2 18 1.4095 0.0811 1.4095 1.1872
No log 1.3333 20 1.3884 0.0565 1.3884 1.1783
No log 1.4667 22 1.3760 0.0900 1.3760 1.1730
No log 1.6 24 1.2261 0.2684 1.2261 1.1073
No log 1.7333 26 1.2585 0.1855 1.2585 1.1218
No log 1.8667 28 1.2153 0.2514 1.2153 1.1024
No log 2.0 30 1.1430 0.2839 1.1430 1.0691
No log 2.1333 32 1.1017 0.2593 1.1017 1.0496
No log 2.2667 34 1.0970 0.2801 1.0970 1.0474
No log 2.4 36 1.1562 0.3127 1.1562 1.0753
No log 2.5333 38 1.1884 0.2591 1.1884 1.0901
No log 2.6667 40 1.1950 0.2913 1.1950 1.0932
No log 2.8 42 1.0828 0.3650 1.0828 1.0406
No log 2.9333 44 1.1478 0.3114 1.1478 1.0713
No log 3.0667 46 1.2950 0.2675 1.2950 1.1380
No log 3.2 48 1.2847 0.2844 1.2847 1.1334
No log 3.3333 50 1.0879 0.3158 1.0879 1.0430
No log 3.4667 52 1.0459 0.3806 1.0459 1.0227
No log 3.6 54 1.0449 0.3625 1.0449 1.0222
No log 3.7333 56 1.0684 0.3574 1.0684 1.0336
No log 3.8667 58 1.0236 0.3784 1.0236 1.0117
No log 4.0 60 1.0092 0.3866 1.0092 1.0046
No log 4.1333 62 1.0208 0.4265 1.0208 1.0103
No log 4.2667 64 1.0117 0.4532 1.0117 1.0058
No log 4.4 66 0.9856 0.4586 0.9856 0.9928
No log 4.5333 68 0.9927 0.4627 0.9927 0.9963
No log 4.6667 70 1.0445 0.4283 1.0445 1.0220
No log 4.8 72 1.0926 0.4289 1.0926 1.0453
No log 4.9333 74 1.0779 0.4272 1.0779 1.0382
No log 5.0667 76 1.1041 0.3903 1.1041 1.0508
No log 5.2 78 1.1078 0.4102 1.1078 1.0525
No log 5.3333 80 1.0976 0.4646 1.0976 1.0477
No log 5.4667 82 0.9639 0.5436 0.9639 0.9818
No log 5.6 84 1.0265 0.4282 1.0265 1.0132
No log 5.7333 86 1.1367 0.5011 1.1367 1.0662
No log 5.8667 88 0.8761 0.4869 0.8761 0.9360
No log 6.0 90 0.8267 0.5293 0.8267 0.9093
No log 6.1333 92 0.8973 0.5681 0.8973 0.9472
No log 6.2667 94 1.0040 0.5128 1.0040 1.0020
No log 6.4 96 1.0598 0.4982 1.0598 1.0294
No log 6.5333 98 0.9660 0.5512 0.9660 0.9829
No log 6.6667 100 0.8558 0.5887 0.8558 0.9251
No log 6.8 102 0.8282 0.5721 0.8282 0.9101
No log 6.9333 104 0.8513 0.5780 0.8513 0.9227
No log 7.0667 106 0.8582 0.5710 0.8582 0.9264
No log 7.2 108 0.8980 0.5261 0.8980 0.9476
No log 7.3333 110 0.9370 0.5361 0.9370 0.9680
No log 7.4667 112 0.8987 0.5653 0.8987 0.9480
No log 7.6 114 0.8901 0.5658 0.8901 0.9435
No log 7.7333 116 0.8916 0.5631 0.8916 0.9442
No log 7.8667 118 0.8799 0.5901 0.8799 0.9380
No log 8.0 120 0.8454 0.6274 0.8454 0.9195
No log 8.1333 122 0.8180 0.6267 0.8180 0.9044
No log 8.2667 124 0.8164 0.6401 0.8164 0.9036
No log 8.4 126 0.8562 0.6092 0.8562 0.9253
No log 8.5333 128 0.9146 0.5792 0.9146 0.9563
No log 8.6667 130 0.9628 0.5715 0.9628 0.9812
No log 8.8 132 1.0158 0.5790 1.0158 1.0079
No log 8.9333 134 1.0382 0.5729 1.0382 1.0189
No log 9.0667 136 1.0378 0.5668 1.0378 1.0187
No log 9.2 138 1.0291 0.5667 1.0291 1.0144
No log 9.3333 140 0.9283 0.5897 0.9283 0.9635
No log 9.4667 142 0.8442 0.6213 0.8442 0.9188
No log 9.6 144 0.8510 0.6347 0.8510 0.9225
No log 9.7333 146 0.9195 0.5904 0.9195 0.9589
No log 9.8667 148 1.0661 0.5777 1.0661 1.0325
No log 10.0 150 1.0546 0.5533 1.0546 1.0269
No log 10.1333 152 0.9662 0.5702 0.9662 0.9829
No log 10.2667 154 0.8990 0.6108 0.8990 0.9482
No log 10.4 156 0.8500 0.6563 0.8500 0.9219
No log 10.5333 158 0.8369 0.6550 0.8369 0.9148
No log 10.6667 160 0.8290 0.6270 0.8290 0.9105
No log 10.8 162 0.8108 0.6502 0.8108 0.9004
No log 10.9333 164 0.7786 0.6436 0.7786 0.8824
No log 11.0667 166 0.8054 0.6412 0.8054 0.8974
No log 11.2 168 0.9212 0.6110 0.9212 0.9598
No log 11.3333 170 1.0971 0.5159 1.0971 1.0474
No log 11.4667 172 1.0827 0.5403 1.0827 1.0405
No log 11.6 174 0.9295 0.5984 0.9295 0.9641
No log 11.7333 176 0.8084 0.6520 0.8084 0.8991
No log 11.8667 178 0.8049 0.6479 0.8049 0.8972
No log 12.0 180 0.8426 0.6317 0.8426 0.9180
No log 12.1333 182 0.9654 0.6251 0.9654 0.9825
No log 12.2667 184 1.1368 0.5381 1.1368 1.0662
No log 12.4 186 1.1714 0.4972 1.1714 1.0823
No log 12.5333 188 1.0593 0.5360 1.0593 1.0292
No log 12.6667 190 0.9384 0.6191 0.9384 0.9687
No log 12.8 192 0.8657 0.6144 0.8657 0.9304
No log 12.9333 194 0.8378 0.6063 0.8378 0.9153
No log 13.0667 196 0.8700 0.5814 0.8700 0.9327
No log 13.2 198 0.9392 0.5908 0.9392 0.9691
No log 13.3333 200 1.0126 0.5522 1.0126 1.0063
No log 13.4667 202 1.1703 0.5200 1.1703 1.0818
No log 13.6 204 1.2011 0.5333 1.2011 1.0959
No log 13.7333 206 1.0239 0.5842 1.0239 1.0119
No log 13.8667 208 0.8766 0.6103 0.8766 0.9363
No log 14.0 210 0.8557 0.6098 0.8557 0.9250
No log 14.1333 212 0.8673 0.6294 0.8673 0.9313
No log 14.2667 214 0.9862 0.6053 0.9862 0.9931
No log 14.4 216 1.1821 0.5317 1.1821 1.0872
No log 14.5333 218 1.2120 0.5264 1.2120 1.1009
No log 14.6667 220 1.0240 0.5931 1.0240 1.0119
No log 14.8 222 0.8583 0.6434 0.8583 0.9265
No log 14.9333 224 0.8019 0.6525 0.8019 0.8955
No log 15.0667 226 0.8440 0.6460 0.8440 0.9187
No log 15.2 228 0.9568 0.5916 0.9568 0.9781
No log 15.3333 230 0.9988 0.5889 0.9988 0.9994
No log 15.4667 232 1.0114 0.5626 1.0114 1.0057
No log 15.6 234 1.0423 0.5862 1.0423 1.0209
No log 15.7333 236 1.1093 0.5875 1.1093 1.0532
No log 15.8667 238 1.1284 0.5786 1.1284 1.0623
No log 16.0 240 1.1852 0.5449 1.1852 1.0887
No log 16.1333 242 1.0777 0.5868 1.0777 1.0381
No log 16.2667 244 0.9674 0.6116 0.9674 0.9836
No log 16.4 246 0.8800 0.6478 0.8800 0.9381
No log 16.5333 248 0.8552 0.6263 0.8552 0.9248
No log 16.6667 250 0.9013 0.6086 0.9013 0.9493
No log 16.8 252 0.9839 0.5235 0.9839 0.9919
No log 16.9333 254 1.1235 0.5535 1.1235 1.0600
No log 17.0667 256 1.1923 0.5516 1.1923 1.0919
No log 17.2 258 1.0389 0.5830 1.0389 1.0193
No log 17.3333 260 0.8947 0.6098 0.8947 0.9459
No log 17.4667 262 0.8741 0.5685 0.8741 0.9349
No log 17.6 264 0.9012 0.5766 0.9012 0.9493
No log 17.7333 266 0.9930 0.5718 0.9930 0.9965
No log 17.8667 268 1.1637 0.4864 1.1637 1.0787
No log 18.0 270 1.2118 0.4928 1.2118 1.1008
No log 18.1333 272 1.1062 0.5388 1.1062 1.0518
No log 18.2667 274 0.9668 0.5619 0.9668 0.9832
No log 18.4 276 0.9022 0.6083 0.9022 0.9498
No log 18.5333 278 0.8590 0.6047 0.8590 0.9268
No log 18.6667 280 0.8218 0.5945 0.8218 0.9065
No log 18.8 282 0.8218 0.6042 0.8218 0.9066
No log 18.9333 284 0.8498 0.5655 0.8498 0.9218
No log 19.0667 286 0.9014 0.5963 0.9014 0.9494
No log 19.2 288 0.9587 0.5553 0.9587 0.9791
No log 19.3333 290 0.9287 0.6070 0.9287 0.9637
No log 19.4667 292 0.9158 0.6388 0.9158 0.9570
No log 19.6 294 0.9625 0.6237 0.9625 0.9811
No log 19.7333 296 1.0916 0.5673 1.0916 1.0448
No log 19.8667 298 1.2367 0.5540 1.2367 1.1121
No log 20.0 300 1.1885 0.5371 1.1885 1.0902
No log 20.1333 302 1.0175 0.5619 1.0175 1.0087
No log 20.2667 304 0.8928 0.5958 0.8928 0.9449
No log 20.4 306 0.7726 0.6424 0.7726 0.8790
No log 20.5333 308 0.7432 0.6499 0.7432 0.8621
No log 20.6667 310 0.7357 0.6735 0.7357 0.8577
No log 20.8 312 0.8005 0.6535 0.8005 0.8947
No log 20.9333 314 0.9495 0.6109 0.9495 0.9744
No log 21.0667 316 0.9804 0.6006 0.9804 0.9902
No log 21.2 318 0.9387 0.6003 0.9387 0.9689
No log 21.3333 320 0.8312 0.6440 0.8312 0.9117
No log 21.4667 322 0.7182 0.6583 0.7182 0.8475
No log 21.6 324 0.7053 0.6664 0.7053 0.8398
No log 21.7333 326 0.7546 0.6529 0.7546 0.8687
No log 21.8667 328 0.8446 0.6505 0.8446 0.9190
No log 22.0 330 0.9647 0.6275 0.9647 0.9822
No log 22.1333 332 0.9206 0.6166 0.9206 0.9595
No log 22.2667 334 0.8556 0.6175 0.8556 0.9250
No log 22.4 336 0.8145 0.6474 0.8145 0.9025
No log 22.5333 338 0.7793 0.6371 0.7793 0.8828
No log 22.6667 340 0.8377 0.6496 0.8377 0.9153
No log 22.8 342 0.9290 0.6253 0.9290 0.9638
No log 22.9333 344 0.9664 0.6032 0.9664 0.9831
No log 23.0667 346 0.9334 0.5911 0.9334 0.9661
No log 23.2 348 0.9075 0.6048 0.9075 0.9526
No log 23.3333 350 0.8946 0.6462 0.8946 0.9458
No log 23.4667 352 0.9187 0.6388 0.9187 0.9585
No log 23.6 354 0.9403 0.5997 0.9403 0.9697
No log 23.7333 356 0.9897 0.5764 0.9897 0.9948
No log 23.8667 358 1.0023 0.5718 1.0023 1.0012
No log 24.0 360 0.9325 0.5763 0.9325 0.9657
No log 24.1333 362 0.9179 0.6063 0.9179 0.9581
No log 24.2667 364 0.9430 0.5852 0.9430 0.9711
No log 24.4 366 0.9896 0.5948 0.9896 0.9948
No log 24.5333 368 1.0124 0.5840 1.0124 1.0062
No log 24.6667 370 0.9601 0.6150 0.9601 0.9799
No log 24.8 372 0.9507 0.6300 0.9507 0.9750
No log 24.9333 374 0.8926 0.6396 0.8925 0.9447
No log 25.0667 376 0.8557 0.6307 0.8557 0.9251
No log 25.2 378 0.9059 0.5981 0.9059 0.9518
No log 25.3333 380 0.9347 0.5644 0.9347 0.9668
No log 25.4667 382 0.8939 0.5526 0.8939 0.9455
No log 25.6 384 0.8781 0.5337 0.8781 0.9371
No log 25.7333 386 0.9441 0.5656 0.9441 0.9716
No log 25.8667 388 1.0797 0.5612 1.0797 1.0391
No log 26.0 390 1.1308 0.5606 1.1308 1.0634
No log 26.1333 392 1.0357 0.5277 1.0357 1.0177
No log 26.2667 394 0.9632 0.5705 0.9632 0.9814
No log 26.4 396 0.9263 0.5447 0.9263 0.9624
No log 26.5333 398 0.9116 0.5548 0.9116 0.9548
No log 26.6667 400 0.8843 0.5880 0.8843 0.9404
No log 26.8 402 0.9484 0.5968 0.9484 0.9738
No log 26.9333 404 0.9990 0.5992 0.9990 0.9995
No log 27.0667 406 0.9681 0.6232 0.9681 0.9839
No log 27.2 408 0.9497 0.6186 0.9497 0.9745
No log 27.3333 410 0.9495 0.6057 0.9495 0.9744
No log 27.4667 412 0.9910 0.5815 0.9910 0.9955
No log 27.6 414 0.9487 0.5815 0.9487 0.9740
No log 27.7333 416 0.8846 0.6208 0.8846 0.9405
No log 27.8667 418 0.8427 0.6045 0.8427 0.9180
No log 28.0 420 0.8795 0.6054 0.8795 0.9378
No log 28.1333 422 0.9494 0.5900 0.9494 0.9744
No log 28.2667 424 0.9881 0.5958 0.9881 0.9940
No log 28.4 426 0.9730 0.5852 0.9730 0.9864
No log 28.5333 428 0.9563 0.5804 0.9563 0.9779
No log 28.6667 430 0.9819 0.5766 0.9819 0.9909
No log 28.8 432 0.9661 0.5694 0.9661 0.9829
No log 28.9333 434 0.8748 0.6346 0.8748 0.9353
No log 29.0667 436 0.8452 0.6451 0.8452 0.9193
No log 29.2 438 0.8663 0.6241 0.8663 0.9308
No log 29.3333 440 0.8564 0.6268 0.8564 0.9254
No log 29.4667 442 0.9092 0.6132 0.9092 0.9535
No log 29.6 444 0.9405 0.6281 0.9405 0.9698
No log 29.7333 446 0.9591 0.6091 0.9591 0.9793
No log 29.8667 448 0.9719 0.6008 0.9719 0.9859
No log 30.0 450 0.9356 0.5895 0.9356 0.9672
No log 30.1333 452 0.9661 0.5842 0.9661 0.9829
No log 30.2667 454 1.0511 0.5636 1.0511 1.0252
No log 30.4 456 1.1102 0.5439 1.1102 1.0537
No log 30.5333 458 1.1628 0.5467 1.1628 1.0783
No log 30.6667 460 1.2328 0.4857 1.2328 1.1103
No log 30.8 462 1.2005 0.5071 1.2005 1.0957
No log 30.9333 464 1.0907 0.5464 1.0907 1.0444
No log 31.0667 466 0.9622 0.5693 0.9622 0.9809
No log 31.2 468 0.8724 0.6209 0.8724 0.9340
No log 31.3333 470 0.8468 0.6279 0.8468 0.9202
No log 31.4667 472 0.8644 0.5899 0.8644 0.9297
No log 31.6 474 0.9419 0.5754 0.9419 0.9705
No log 31.7333 476 1.0090 0.5780 1.0090 1.0045
No log 31.8667 478 1.0927 0.5494 1.0927 1.0453
No log 32.0 480 1.0396 0.5330 1.0396 1.0196
No log 32.1333 482 0.9186 0.6063 0.9186 0.9584
No log 32.2667 484 0.8607 0.5945 0.8607 0.9277
No log 32.4 486 0.8154 0.6091 0.8154 0.9030
No log 32.5333 488 0.8285 0.6314 0.8285 0.9102
No log 32.6667 490 0.8700 0.6324 0.8700 0.9327
No log 32.8 492 0.9589 0.6127 0.9589 0.9792
No log 32.9333 494 1.0745 0.5382 1.0745 1.0366
No log 33.0667 496 1.0700 0.5400 1.0700 1.0344
No log 33.2 498 0.9908 0.5876 0.9908 0.9954
0.3841 33.3333 500 0.8941 0.6003 0.8941 0.9456
0.3841 33.4667 502 0.8756 0.6279 0.8756 0.9357
0.3841 33.6 504 0.8916 0.6233 0.8916 0.9442
0.3841 33.7333 506 0.9634 0.6026 0.9634 0.9815
0.3841 33.8667 508 1.0325 0.5943 1.0325 1.0161
0.3841 34.0 510 1.0914 0.5438 1.0914 1.0447
0.3841 34.1333 512 1.1023 0.5473 1.1023 1.0499
0.3841 34.2667 514 1.0538 0.5681 1.0538 1.0266
0.3841 34.4 516 0.9745 0.5781 0.9745 0.9871

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k3_task1_organization

Finetuned
(4040)
this model