ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k1_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: 0.9738
  • Qwk: 0.5954
  • Mse: 0.9738
  • Rmse: 0.9868

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 0.4 2 7.3513 0.0870 7.3513 2.7113
No log 0.8 4 5.7235 0.0381 5.7235 2.3924
No log 1.2 6 4.5852 -0.0221 4.5852 2.1413
No log 1.6 8 3.7833 0.1264 3.7833 1.9451
No log 2.0 10 3.2628 0.0988 3.2628 1.8063
No log 2.4 12 2.8235 0.0755 2.8235 1.6803
No log 2.8 14 2.3737 0.0261 2.3737 1.5407
No log 3.2 16 2.1826 0.0278 2.1826 1.4774
No log 3.6 18 2.1431 0.1096 2.1431 1.4639
No log 4.0 20 1.9792 0.3622 1.9792 1.4069
No log 4.4 22 1.7850 0.3419 1.7850 1.3361
No log 4.8 24 1.7093 0.3770 1.7093 1.3074
No log 5.2 26 1.7929 0.4122 1.7929 1.3390
No log 5.6 28 1.7678 0.4526 1.7678 1.3296
No log 6.0 30 1.5911 0.4769 1.5911 1.2614
No log 6.4 32 1.4491 0.4590 1.4491 1.2038
No log 6.8 34 1.3774 0.4286 1.3774 1.1736
No log 7.2 36 1.3243 0.4567 1.3243 1.1508
No log 7.6 38 1.2704 0.4806 1.2704 1.1271
No log 8.0 40 1.2155 0.4286 1.2155 1.1025
No log 8.4 42 1.2928 0.3009 1.2928 1.1370
No log 8.8 44 1.2443 0.2982 1.2443 1.1155
No log 9.2 46 1.2495 0.2982 1.2495 1.1178
No log 9.6 48 1.1777 0.3276 1.1777 1.0852
No log 10.0 50 1.2051 0.2957 1.2051 1.0977
No log 10.4 52 1.1005 0.4480 1.1005 1.0491
No log 10.8 54 1.1265 0.3529 1.1265 1.0614
No log 11.2 56 1.1918 0.4202 1.1918 1.0917
No log 11.6 58 1.2253 0.5 1.2253 1.1069
No log 12.0 60 1.1821 0.5354 1.1821 1.0873
No log 12.4 62 1.1082 0.5909 1.1082 1.0527
No log 12.8 64 1.1574 0.6015 1.1574 1.0758
No log 13.2 66 1.4169 0.4627 1.4169 1.1903
No log 13.6 68 1.3988 0.4889 1.3988 1.1827
No log 14.0 70 1.0887 0.6119 1.0887 1.0434
No log 14.4 72 0.9766 0.6029 0.9766 0.9882
No log 14.8 74 1.0409 0.5926 1.0409 1.0202
No log 15.2 76 1.2364 0.5821 1.2364 1.1119
No log 15.6 78 1.4275 0.4526 1.4275 1.1948
No log 16.0 80 1.3144 0.5522 1.3144 1.1465
No log 16.4 82 1.1078 0.5865 1.1078 1.0525
No log 16.8 84 1.0709 0.5496 1.0709 1.0348
No log 17.2 86 1.0940 0.5865 1.0940 1.0460
No log 17.6 88 1.2687 0.5821 1.2687 1.1264
No log 18.0 90 1.3383 0.5778 1.3383 1.1568
No log 18.4 92 1.1501 0.5926 1.1501 1.0724
No log 18.8 94 0.9704 0.5821 0.9704 0.9851
No log 19.2 96 0.9612 0.5821 0.9612 0.9804
No log 19.6 98 1.1060 0.5882 1.1060 1.0517
No log 20.0 100 1.3657 0.5109 1.3657 1.1686
No log 20.4 102 1.3221 0.5441 1.3221 1.1498
No log 20.8 104 1.0639 0.6015 1.0639 1.0315
No log 21.2 106 0.8838 0.7059 0.8838 0.9401
No log 21.6 108 0.8608 0.6806 0.8608 0.9278
No log 22.0 110 0.8252 0.6809 0.8252 0.9084
No log 22.4 112 0.9191 0.6277 0.9191 0.9587
No log 22.8 114 1.1298 0.5839 1.1298 1.0629
No log 23.2 116 1.2770 0.5507 1.2770 1.1300
No log 23.6 118 1.1551 0.5839 1.1551 1.0747
No log 24.0 120 0.9559 0.6176 0.9559 0.9777
No log 24.4 122 0.8655 0.6857 0.8655 0.9303
No log 24.8 124 0.9022 0.6809 0.9022 0.9499
No log 25.2 126 0.9441 0.6061 0.9441 0.9717
No log 25.6 128 1.0714 0.6 1.0714 1.0351
No log 26.0 130 1.2228 0.5564 1.2228 1.1058
No log 26.4 132 1.2551 0.5564 1.2551 1.1203
No log 26.8 134 1.1628 0.5606 1.1628 1.0784
No log 27.2 136 0.9860 0.5846 0.9860 0.9930
No log 27.6 138 0.9329 0.6061 0.9329 0.9659
No log 28.0 140 0.9854 0.5882 0.9854 0.9927
No log 28.4 142 1.1461 0.5735 1.1461 1.0705
No log 28.8 144 1.2248 0.5735 1.2248 1.1067
No log 29.2 146 1.0922 0.5839 1.0922 1.0451
No log 29.6 148 0.8575 0.6370 0.8575 0.9260
No log 30.0 150 0.7856 0.7246 0.7856 0.8863
No log 30.4 152 0.7826 0.7391 0.7826 0.8847
No log 30.8 154 0.8705 0.6176 0.8705 0.9330
No log 31.2 156 0.9286 0.5926 0.9286 0.9636
No log 31.6 158 0.9460 0.5926 0.9460 0.9726
No log 32.0 160 0.8997 0.6119 0.8997 0.9485
No log 32.4 162 0.8489 0.6815 0.8489 0.9213
No log 32.8 164 0.8675 0.6912 0.8675 0.9314
No log 33.2 166 0.8849 0.6471 0.8849 0.9407
No log 33.6 168 0.9246 0.5802 0.9246 0.9616
No log 34.0 170 0.9920 0.6119 0.9920 0.9960
No log 34.4 172 1.0022 0.6119 1.0022 1.0011
No log 34.8 174 0.9731 0.5758 0.9731 0.9864
No log 35.2 176 0.9694 0.5758 0.9694 0.9846
No log 35.6 178 0.9921 0.6119 0.9921 0.9960
No log 36.0 180 0.9894 0.6165 0.9894 0.9947
No log 36.4 182 1.0021 0.6165 1.0021 1.0011
No log 36.8 184 0.9880 0.6165 0.9880 0.9940
No log 37.2 186 0.9719 0.6165 0.9719 0.9858
No log 37.6 188 0.9755 0.6074 0.9755 0.9877
No log 38.0 190 0.9200 0.6418 0.9200 0.9592
No log 38.4 192 0.8922 0.6567 0.8922 0.9446
No log 38.8 194 0.9394 0.6165 0.9394 0.9692
No log 39.2 196 0.9821 0.6119 0.9821 0.9910
No log 39.6 198 1.0101 0.6074 1.0101 1.0051
No log 40.0 200 0.9497 0.6165 0.9497 0.9745
No log 40.4 202 0.8858 0.6667 0.8858 0.9412
No log 40.8 204 0.8754 0.6667 0.8754 0.9356
No log 41.2 206 0.8845 0.6667 0.8845 0.9405
No log 41.6 208 0.9079 0.6418 0.9079 0.9528
No log 42.0 210 0.9272 0.6466 0.9272 0.9629
No log 42.4 212 0.9622 0.6119 0.9622 0.9809
No log 42.8 214 0.9926 0.6015 0.9926 0.9963
No log 43.2 216 1.0497 0.5821 1.0497 1.0246
No log 43.6 218 1.0327 0.5821 1.0327 1.0162
No log 44.0 220 0.9587 0.6418 0.9587 0.9791
No log 44.4 222 0.9206 0.6767 0.9206 0.9595
No log 44.8 224 0.9263 0.6418 0.9263 0.9624
No log 45.2 226 0.9839 0.6119 0.9839 0.9919
No log 45.6 228 1.0358 0.5778 1.0358 1.0177
No log 46.0 230 1.0490 0.5778 1.0490 1.0242
No log 46.4 232 1.0148 0.6074 1.0148 1.0074
No log 46.8 234 0.9522 0.5909 0.9522 0.9758
No log 47.2 236 0.9618 0.5846 0.9618 0.9807
No log 47.6 238 1.0255 0.5865 1.0255 1.0127
No log 48.0 240 1.1153 0.5778 1.1153 1.0561
No log 48.4 242 1.1159 0.5778 1.1159 1.0564
No log 48.8 244 1.0441 0.5970 1.0441 1.0218
No log 49.2 246 0.9721 0.5846 0.9721 0.9859
No log 49.6 248 0.9316 0.6 0.9316 0.9652
No log 50.0 250 0.9123 0.6 0.9123 0.9551
No log 50.4 252 0.9075 0.6 0.9075 0.9526
No log 50.8 254 0.9450 0.6154 0.9450 0.9721
No log 51.2 256 1.0397 0.5714 1.0397 1.0196
No log 51.6 258 1.1137 0.5778 1.1137 1.0553
No log 52.0 260 1.1128 0.5522 1.1128 1.0549
No log 52.4 262 1.0796 0.5758 1.0796 1.0390
No log 52.8 264 1.0239 0.6094 1.0239 1.0119
No log 53.2 266 1.0076 0.6094 1.0076 1.0038
No log 53.6 268 0.9901 0.6308 0.9901 0.9950
No log 54.0 270 0.9886 0.6308 0.9886 0.9943
No log 54.4 272 1.0015 0.6 1.0015 1.0008
No log 54.8 274 1.0353 0.5865 1.0353 1.0175
No log 55.2 276 1.0486 0.5758 1.0486 1.0240
No log 55.6 278 1.0434 0.5758 1.0434 1.0215
No log 56.0 280 1.0574 0.5970 1.0574 1.0283
No log 56.4 282 1.0497 0.5970 1.0497 1.0246
No log 56.8 284 1.0265 0.5714 1.0265 1.0132
No log 57.2 286 1.0296 0.5970 1.0296 1.0147
No log 57.6 288 1.0825 0.5970 1.0825 1.0404
No log 58.0 290 1.1357 0.5970 1.1357 1.0657
No log 58.4 292 1.1368 0.5970 1.1368 1.0662
No log 58.8 294 1.1122 0.5970 1.1122 1.0546
No log 59.2 296 1.0809 0.5970 1.0809 1.0396
No log 59.6 298 1.0251 0.5606 1.0251 1.0125
No log 60.0 300 0.9866 0.5846 0.9866 0.9933
No log 60.4 302 0.9813 0.5758 0.9813 0.9906
No log 60.8 304 0.9887 0.5714 0.9887 0.9944
No log 61.2 306 1.0022 0.5714 1.0022 1.0011
No log 61.6 308 1.0381 0.5714 1.0381 1.0189
No log 62.0 310 1.0926 0.5714 1.0926 1.0453
No log 62.4 312 1.1097 0.5970 1.1097 1.0534
No log 62.8 314 1.0802 0.5714 1.0802 1.0393
No log 63.2 316 1.0210 0.5649 1.0210 1.0105
No log 63.6 318 0.9625 0.6094 0.9625 0.9811
No log 64.0 320 0.9441 0.6357 0.9441 0.9716
No log 64.4 322 0.9433 0.6357 0.9433 0.9712
No log 64.8 324 0.9548 0.6094 0.9548 0.9771
No log 65.2 326 0.9698 0.5802 0.9698 0.9848
No log 65.6 328 0.9915 0.5692 0.9915 0.9958
No log 66.0 330 1.0189 0.5758 1.0189 1.0094
No log 66.4 332 1.0256 0.5758 1.0256 1.0127
No log 66.8 334 1.0049 0.5758 1.0049 1.0025
No log 67.2 336 0.9755 0.5802 0.9755 0.9877
No log 67.6 338 0.9564 0.6154 0.9564 0.9779
No log 68.0 340 0.9452 0.6154 0.9452 0.9722
No log 68.4 342 0.9366 0.6412 0.9366 0.9678
No log 68.8 344 0.9355 0.6412 0.9355 0.9672
No log 69.2 346 0.9423 0.5909 0.9423 0.9707
No log 69.6 348 0.9618 0.5909 0.9618 0.9807
No log 70.0 350 0.9963 0.5714 0.9963 0.9981
No log 70.4 352 1.0121 0.5714 1.0121 1.0060
No log 70.8 354 0.9992 0.5714 0.9992 0.9996
No log 71.2 356 0.9906 0.5758 0.9906 0.9953
No log 71.6 358 0.9598 0.5909 0.9598 0.9797
No log 72.0 360 0.9359 0.6308 0.9359 0.9674
No log 72.4 362 0.9421 0.5954 0.9421 0.9706
No log 72.8 364 0.9628 0.5954 0.9628 0.9812
No log 73.2 366 0.9860 0.5802 0.9860 0.9930
No log 73.6 368 0.9872 0.5802 0.9872 0.9936
No log 74.0 370 0.9647 0.5802 0.9647 0.9822
No log 74.4 372 0.9348 0.5954 0.9348 0.9668
No log 74.8 374 0.9203 0.6202 0.9203 0.9593
No log 75.2 376 0.9274 0.6202 0.9274 0.9630
No log 75.6 378 0.9500 0.6202 0.9500 0.9747
No log 76.0 380 0.9694 0.6202 0.9694 0.9846
No log 76.4 382 0.9939 0.5846 0.9939 0.9969
No log 76.8 384 1.0020 0.5846 1.0020 1.0010
No log 77.2 386 1.0016 0.6202 1.0016 1.0008
No log 77.6 388 0.9893 0.6094 0.9893 0.9946
No log 78.0 390 0.9712 0.6094 0.9712 0.9855
No log 78.4 392 0.9631 0.6202 0.9631 0.9814
No log 78.8 394 0.9526 0.6202 0.9526 0.9760
No log 79.2 396 0.9483 0.6308 0.9483 0.9738
No log 79.6 398 0.9514 0.6308 0.9514 0.9754
No log 80.0 400 0.9452 0.6308 0.9452 0.9722
No log 80.4 402 0.9414 0.6308 0.9414 0.9702
No log 80.8 404 0.9242 0.6308 0.9242 0.9614
No log 81.2 406 0.9204 0.6308 0.9204 0.9594
No log 81.6 408 0.9167 0.6308 0.9167 0.9575
No log 82.0 410 0.9111 0.6565 0.9111 0.9545
No log 82.4 412 0.9103 0.6565 0.9103 0.9541
No log 82.8 414 0.9120 0.6565 0.9120 0.9550
No log 83.2 416 0.9237 0.6308 0.9237 0.9611
No log 83.6 418 0.9314 0.6308 0.9314 0.9651
No log 84.0 420 0.9296 0.5954 0.9296 0.9641
No log 84.4 422 0.9314 0.5954 0.9314 0.9651
No log 84.8 424 0.9272 0.5954 0.9272 0.9629
No log 85.2 426 0.9202 0.5954 0.9202 0.9593
No log 85.6 428 0.9145 0.6308 0.9145 0.9563
No log 86.0 430 0.9143 0.6565 0.9143 0.9562
No log 86.4 432 0.9230 0.6308 0.9230 0.9607
No log 86.8 434 0.9375 0.6308 0.9375 0.9683
No log 87.2 436 0.9543 0.5954 0.9543 0.9769
No log 87.6 438 0.9659 0.5954 0.9659 0.9828
No log 88.0 440 0.9672 0.5954 0.9672 0.9834
No log 88.4 442 0.9701 0.5954 0.9701 0.9850
No log 88.8 444 0.9703 0.5954 0.9703 0.9851
No log 89.2 446 0.9704 0.5954 0.9704 0.9851
No log 89.6 448 0.9662 0.6308 0.9662 0.9829
No log 90.0 450 0.9590 0.6308 0.9590 0.9793
No log 90.4 452 0.9559 0.6308 0.9559 0.9777
No log 90.8 454 0.9583 0.6308 0.9583 0.9789
No log 91.2 456 0.9646 0.6308 0.9646 0.9821
No log 91.6 458 0.9720 0.5954 0.9720 0.9859
No log 92.0 460 0.9811 0.5954 0.9811 0.9905
No log 92.4 462 0.9846 0.5846 0.9846 0.9923
No log 92.8 464 0.9868 0.5846 0.9868 0.9934
No log 93.2 466 0.9919 0.5846 0.9919 0.9959
No log 93.6 468 0.9935 0.5846 0.9935 0.9968
No log 94.0 470 0.9925 0.5846 0.9925 0.9963
No log 94.4 472 0.9927 0.5846 0.9927 0.9964
No log 94.8 474 0.9904 0.5846 0.9904 0.9952
No log 95.2 476 0.9882 0.5846 0.9882 0.9941
No log 95.6 478 0.9858 0.5846 0.9858 0.9929
No log 96.0 480 0.9819 0.5846 0.9819 0.9909
No log 96.4 482 0.9796 0.5846 0.9796 0.9897
No log 96.8 484 0.9783 0.5846 0.9783 0.9891
No log 97.2 486 0.9768 0.5954 0.9768 0.9883
No log 97.6 488 0.9750 0.5954 0.9750 0.9874
No log 98.0 490 0.9747 0.5954 0.9747 0.9873
No log 98.4 492 0.9745 0.5954 0.9745 0.9872
No log 98.8 494 0.9739 0.5954 0.9739 0.9869
No log 99.2 496 0.9739 0.5954 0.9739 0.9868
No log 99.6 498 0.9737 0.5954 0.9737 0.9868
0.2767 100.0 500 0.9738 0.5954 0.9738 0.9868

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
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_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k1_task1_organization

Finetuned
(4206)
this model