ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k18_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: 1.0166
  • Qwk: 0.5831
  • Mse: 1.0166
  • Rmse: 1.0083

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 0.0225 2 5.5616 0.0155 5.5616 2.3583
No log 0.0449 4 4.3778 0.0031 4.3778 2.0923
No log 0.0674 6 2.6737 0.1009 2.6737 1.6351
No log 0.0899 8 1.9032 0.0179 1.9032 1.3796
No log 0.1124 10 1.5833 0.0526 1.5833 1.2583
No log 0.1348 12 1.2976 0.1819 1.2976 1.1391
No log 0.1573 14 1.2969 0.1754 1.2969 1.1388
No log 0.1798 16 1.3593 0.1782 1.3593 1.1659
No log 0.2022 18 1.7094 -0.0925 1.7094 1.3074
No log 0.2247 20 1.3190 0.2787 1.3190 1.1485
No log 0.2472 22 1.1435 0.1807 1.1435 1.0694
No log 0.2697 24 1.2628 0.2361 1.2628 1.1237
No log 0.2921 26 1.4724 0.0321 1.4724 1.2134
No log 0.3146 28 1.4481 0.0362 1.4481 1.2034
No log 0.3371 30 1.4904 0.0569 1.4904 1.2208
No log 0.3596 32 1.4320 0.0847 1.4320 1.1967
No log 0.3820 34 1.1674 0.2433 1.1674 1.0805
No log 0.4045 36 1.1478 0.0967 1.1478 1.0713
No log 0.4270 38 1.1618 0.2555 1.1618 1.0779
No log 0.4494 40 1.2747 0.2216 1.2747 1.1290
No log 0.4719 42 1.3517 0.1604 1.3517 1.1626
No log 0.4944 44 1.3113 0.2396 1.3113 1.1451
No log 0.5169 46 1.1427 0.3126 1.1427 1.0690
No log 0.5393 48 1.1003 0.2615 1.1003 1.0489
No log 0.5618 50 1.0951 0.2909 1.0951 1.0465
No log 0.5843 52 1.1141 0.4046 1.1141 1.0555
No log 0.6067 54 1.0722 0.4046 1.0722 1.0355
No log 0.6292 56 1.0336 0.3951 1.0336 1.0166
No log 0.6517 58 0.9772 0.3433 0.9772 0.9886
No log 0.6742 60 0.9599 0.3357 0.9599 0.9797
No log 0.6966 62 0.9372 0.3691 0.9372 0.9681
No log 0.7191 64 0.9478 0.4520 0.9478 0.9736
No log 0.7416 66 0.9287 0.4307 0.9287 0.9637
No log 0.7640 68 0.9152 0.3986 0.9152 0.9566
No log 0.7865 70 0.8996 0.4055 0.8996 0.9485
No log 0.8090 72 0.9559 0.4200 0.9559 0.9777
No log 0.8315 74 0.9757 0.4530 0.9757 0.9878
No log 0.8539 76 0.8822 0.4430 0.8822 0.9393
No log 0.8764 78 0.8634 0.4342 0.8634 0.9292
No log 0.8989 80 0.9047 0.4222 0.9047 0.9512
No log 0.9213 82 0.9331 0.4887 0.9331 0.9660
No log 0.9438 84 1.0593 0.4160 1.0593 1.0292
No log 0.9663 86 1.2224 0.4046 1.2224 1.1056
No log 0.9888 88 1.0714 0.4556 1.0714 1.0351
No log 1.0112 90 0.9095 0.5105 0.9095 0.9537
No log 1.0337 92 0.8387 0.4828 0.8387 0.9158
No log 1.0562 94 0.8252 0.5181 0.8252 0.9084
No log 1.0787 96 0.8202 0.5129 0.8202 0.9057
No log 1.1011 98 0.8132 0.4884 0.8132 0.9018
No log 1.1236 100 0.8271 0.4796 0.8271 0.9094
No log 1.1461 102 0.8477 0.4945 0.8477 0.9207
No log 1.1685 104 0.8278 0.5141 0.8278 0.9099
No log 1.1910 106 0.8244 0.5240 0.8244 0.9080
No log 1.2135 108 0.8793 0.5486 0.8793 0.9377
No log 1.2360 110 0.8052 0.5581 0.8052 0.8974
No log 1.2584 112 0.7755 0.5530 0.7755 0.8806
No log 1.2809 114 0.8337 0.5686 0.8337 0.9131
No log 1.3034 116 1.0438 0.5503 1.0438 1.0217
No log 1.3258 118 1.2430 0.4751 1.2430 1.1149
No log 1.3483 120 1.1204 0.4853 1.1204 1.0585
No log 1.3708 122 0.9083 0.5505 0.9083 0.9531
No log 1.3933 124 0.8231 0.5789 0.8231 0.9072
No log 1.4157 126 0.8143 0.5831 0.8143 0.9024
No log 1.4382 128 0.8634 0.5571 0.8634 0.9292
No log 1.4607 130 1.0032 0.5012 1.0032 1.0016
No log 1.4831 132 0.9332 0.5530 0.9332 0.9660
No log 1.5056 134 0.8199 0.5263 0.8199 0.9055
No log 1.5281 136 0.7603 0.5725 0.7603 0.8720
No log 1.5506 138 0.7696 0.5755 0.7696 0.8773
No log 1.5730 140 0.7952 0.5771 0.7952 0.8917
No log 1.5955 142 0.7776 0.5875 0.7776 0.8818
No log 1.6180 144 0.7904 0.5319 0.7904 0.8890
No log 1.6404 146 0.9633 0.5437 0.9633 0.9815
No log 1.6629 148 1.0515 0.5148 1.0515 1.0254
No log 1.6854 150 0.8684 0.5728 0.8684 0.9319
No log 1.7079 152 0.8047 0.5903 0.8047 0.8970
No log 1.7303 154 0.7778 0.5397 0.7778 0.8819
No log 1.7528 156 0.7806 0.5641 0.7806 0.8835
No log 1.7753 158 0.8521 0.5951 0.8521 0.9231
No log 1.7978 160 0.8296 0.5427 0.8296 0.9108
No log 1.8202 162 1.0166 0.5639 1.0166 1.0083
No log 1.8427 164 1.0336 0.5666 1.0336 1.0167
No log 1.8652 166 0.7820 0.5724 0.7820 0.8843
No log 1.8876 168 0.7712 0.5421 0.7712 0.8782
No log 1.9101 170 0.7350 0.5842 0.7350 0.8573
No log 1.9326 172 0.8108 0.6190 0.8108 0.9004
No log 1.9551 174 1.1787 0.5040 1.1787 1.0857
No log 1.9775 176 1.2708 0.4973 1.2708 1.1273
No log 2.0 178 1.1241 0.5216 1.1241 1.0602
No log 2.0225 180 1.0583 0.5367 1.0583 1.0288
No log 2.0449 182 0.9288 0.6043 0.9288 0.9638
No log 2.0674 184 0.9813 0.5761 0.9813 0.9906
No log 2.0899 186 1.0950 0.5639 1.0950 1.0464
No log 2.1124 188 1.0431 0.6011 1.0431 1.0213
No log 2.1348 190 0.8582 0.6646 0.8582 0.9264
No log 2.1573 192 0.9429 0.5977 0.9429 0.9710
No log 2.1798 194 0.8708 0.6217 0.8708 0.9332
No log 2.2022 196 0.8373 0.6540 0.8373 0.9151
No log 2.2247 198 1.0224 0.5578 1.0224 1.0111
No log 2.2472 200 1.1345 0.4966 1.1345 1.0651
No log 2.2697 202 1.0894 0.5062 1.0894 1.0437
No log 2.2921 204 0.9758 0.5594 0.9758 0.9878
No log 2.3146 206 0.8181 0.6408 0.8181 0.9045
No log 2.3371 208 0.7827 0.6507 0.7827 0.8847
No log 2.3596 210 0.7564 0.6624 0.7564 0.8697
No log 2.3820 212 0.7756 0.6781 0.7756 0.8807
No log 2.4045 214 0.8882 0.6300 0.8882 0.9424
No log 2.4270 216 0.9110 0.6239 0.9110 0.9545
No log 2.4494 218 0.9486 0.5914 0.9486 0.9739
No log 2.4719 220 0.8765 0.6108 0.8765 0.9362
No log 2.4944 222 0.9131 0.6087 0.9131 0.9556
No log 2.5169 224 1.0067 0.5578 1.0067 1.0033
No log 2.5393 226 1.0797 0.5366 1.0797 1.0391
No log 2.5618 228 0.9709 0.5450 0.9709 0.9853
No log 2.5843 230 0.8226 0.6519 0.8226 0.9070
No log 2.6067 232 0.8358 0.5824 0.8358 0.9142
No log 2.6292 234 0.9364 0.5427 0.9364 0.9677
No log 2.6517 236 0.9584 0.5240 0.9584 0.9790
No log 2.6742 238 0.7998 0.6069 0.7998 0.8943
No log 2.6966 240 0.6663 0.7012 0.6663 0.8162
No log 2.7191 242 0.6779 0.6910 0.6779 0.8234
No log 2.7416 244 0.7605 0.7105 0.7605 0.8720
No log 2.7640 246 0.9759 0.5485 0.9759 0.9879
No log 2.7865 248 1.0761 0.5525 1.0761 1.0373
No log 2.8090 250 0.9997 0.5500 0.9997 0.9998
No log 2.8315 252 0.8631 0.6087 0.8631 0.9290
No log 2.8539 254 0.7846 0.6148 0.7846 0.8858
No log 2.8764 256 0.7909 0.6207 0.7909 0.8893
No log 2.8989 258 0.8203 0.6182 0.8203 0.9057
No log 2.9213 260 0.9825 0.5648 0.9825 0.9912
No log 2.9438 262 1.0981 0.5695 1.0981 1.0479
No log 2.9663 264 0.8479 0.6305 0.8479 0.9208
No log 2.9888 266 0.7297 0.6931 0.7297 0.8542
No log 3.0112 268 0.6406 0.7017 0.6406 0.8004
No log 3.0337 270 0.6385 0.7073 0.6385 0.7990
No log 3.0562 272 0.7774 0.6340 0.7774 0.8817
No log 3.0787 274 1.2108 0.5597 1.2108 1.1004
No log 3.1011 276 1.3385 0.4815 1.3385 1.1569
No log 3.1236 278 1.2634 0.5045 1.2634 1.1240
No log 3.1461 280 1.0450 0.5820 1.0450 1.0222
No log 3.1685 282 0.9262 0.6052 0.9262 0.9624
No log 3.1910 284 0.9281 0.5975 0.9281 0.9634
No log 3.2135 286 1.0011 0.5979 1.0011 1.0006
No log 3.2360 288 1.1212 0.5581 1.1212 1.0589
No log 3.2584 290 1.0472 0.5773 1.0472 1.0233
No log 3.2809 292 0.8308 0.6509 0.8308 0.9115
No log 3.3034 294 0.7510 0.6904 0.7510 0.8666
No log 3.3258 296 0.7362 0.6725 0.7362 0.8580
No log 3.3483 298 0.7890 0.6281 0.7890 0.8883
No log 3.3708 300 0.7575 0.6328 0.7575 0.8703
No log 3.3933 302 0.8424 0.6108 0.8424 0.9178
No log 3.4157 304 0.8467 0.5794 0.8467 0.9202
No log 3.4382 306 0.8070 0.6262 0.8070 0.8983
No log 3.4607 308 0.7999 0.6212 0.7999 0.8944
No log 3.4831 310 0.8810 0.6052 0.8810 0.9386
No log 3.5056 312 0.8531 0.6023 0.8531 0.9236
No log 3.5281 314 0.8800 0.6195 0.8800 0.9381
No log 3.5506 316 0.9972 0.5829 0.9972 0.9986
No log 3.5730 318 1.1306 0.5435 1.1306 1.0633
No log 3.5955 320 1.1190 0.5411 1.1190 1.0578
No log 3.6180 322 1.0805 0.5502 1.0805 1.0395
No log 3.6404 324 0.9761 0.5882 0.9761 0.9880
No log 3.6629 326 0.9485 0.5894 0.9485 0.9739
No log 3.6854 328 0.8977 0.6071 0.8977 0.9475
No log 3.7079 330 0.8638 0.6009 0.8638 0.9294
No log 3.7303 332 0.8978 0.5775 0.8978 0.9475
No log 3.7528 334 0.8802 0.5775 0.8802 0.9382
No log 3.7753 336 0.8695 0.5716 0.8695 0.9325
No log 3.7978 338 0.8183 0.5829 0.8183 0.9046
No log 3.8202 340 0.7300 0.6410 0.7300 0.8544
No log 3.8427 342 0.7479 0.5102 0.7479 0.8648
No log 3.8652 344 0.7189 0.6108 0.7189 0.8479
No log 3.8876 346 0.7450 0.6583 0.7450 0.8632
No log 3.9101 348 0.8131 0.6200 0.8131 0.9017
No log 3.9326 350 0.8212 0.6156 0.8212 0.9062
No log 3.9551 352 0.8906 0.6159 0.8906 0.9437
No log 3.9775 354 0.8871 0.6230 0.8871 0.9419
No log 4.0 356 0.9176 0.6192 0.9176 0.9579
No log 4.0225 358 0.9367 0.5670 0.9367 0.9678
No log 4.0449 360 0.8732 0.5739 0.8732 0.9345
No log 4.0674 362 0.7659 0.6479 0.7659 0.8751
No log 4.0899 364 0.7564 0.6786 0.7564 0.8697
No log 4.1124 366 0.8323 0.6291 0.8323 0.9123
No log 4.1348 368 0.9352 0.5843 0.9352 0.9670
No log 4.1573 370 0.9471 0.6136 0.9471 0.9732
No log 4.1798 372 0.9337 0.6374 0.9337 0.9663
No log 4.2022 374 0.8852 0.6435 0.8852 0.9409
No log 4.2247 376 0.8664 0.6404 0.8664 0.9308
No log 4.2472 378 0.9054 0.6392 0.9054 0.9515
No log 4.2697 380 1.0924 0.5774 1.0924 1.0452
No log 4.2921 382 1.1103 0.5707 1.1103 1.0537
No log 4.3146 384 0.9172 0.6193 0.9172 0.9577
No log 4.3371 386 0.7663 0.6525 0.7663 0.8754
No log 4.3596 388 0.7162 0.6515 0.7162 0.8463
No log 4.3820 390 0.8481 0.6555 0.8481 0.9209
No log 4.4045 392 1.1357 0.5707 1.1357 1.0657
No log 4.4270 394 1.1568 0.5431 1.1568 1.0755
No log 4.4494 396 0.9656 0.5836 0.9656 0.9827
No log 4.4719 398 0.7882 0.6399 0.7882 0.8878
No log 4.4944 400 0.7415 0.6701 0.7415 0.8611
No log 4.5169 402 0.8059 0.6419 0.8059 0.8977
No log 4.5393 404 0.8389 0.6230 0.8389 0.9159
No log 4.5618 406 0.8722 0.5887 0.8722 0.9339
No log 4.5843 408 0.8240 0.6230 0.8240 0.9077
No log 4.6067 410 0.7905 0.6275 0.7905 0.8891
No log 4.6292 412 0.7868 0.6239 0.7868 0.8870
No log 4.6517 414 0.8338 0.6377 0.8338 0.9131
No log 4.6742 416 0.7731 0.6285 0.7731 0.8793
No log 4.6966 418 0.7520 0.6415 0.7520 0.8672
No log 4.7191 420 0.8142 0.6311 0.8142 0.9023
No log 4.7416 422 0.8212 0.648 0.8212 0.9062
No log 4.7640 424 0.7600 0.6575 0.7600 0.8718
No log 4.7865 426 0.7202 0.6878 0.7202 0.8487
No log 4.8090 428 0.7487 0.6738 0.7487 0.8653
No log 4.8315 430 0.8074 0.6483 0.8074 0.8986
No log 4.8539 432 0.8459 0.6411 0.8459 0.9197
No log 4.8764 434 0.7509 0.6762 0.7509 0.8665
No log 4.8989 436 0.7553 0.6618 0.7553 0.8691
No log 4.9213 438 0.8588 0.6401 0.8588 0.9267
No log 4.9438 440 1.0310 0.5856 1.0310 1.0154
No log 4.9663 442 1.1627 0.5709 1.1627 1.0783
No log 4.9888 444 1.1691 0.5698 1.1691 1.0813
No log 5.0112 446 0.9612 0.6050 0.9612 0.9804
No log 5.0337 448 0.8600 0.6330 0.8600 0.9274
No log 5.0562 450 0.8128 0.6609 0.8128 0.9016
No log 5.0787 452 0.9027 0.6461 0.9027 0.9501
No log 5.1011 454 1.1221 0.5497 1.1221 1.0593
No log 5.1236 456 1.2665 0.5131 1.2665 1.1254
No log 5.1461 458 1.3440 0.4754 1.3440 1.1593
No log 5.1685 460 1.1831 0.5309 1.1831 1.0877
No log 5.1910 462 0.9739 0.5901 0.9739 0.9869
No log 5.2135 464 0.8708 0.6325 0.8708 0.9332
No log 5.2360 466 0.7808 0.6628 0.7808 0.8836
No log 5.2584 468 0.7497 0.6758 0.7497 0.8659
No log 5.2809 470 0.8568 0.6114 0.8568 0.9256
No log 5.3034 472 1.1355 0.5516 1.1355 1.0656
No log 5.3258 474 1.1146 0.5730 1.1146 1.0557
No log 5.3483 476 0.8188 0.6511 0.8188 0.9048
No log 5.3708 478 0.6214 0.6678 0.6214 0.7883
No log 5.3933 480 0.6826 0.6468 0.6826 0.8262
No log 5.4157 482 0.6265 0.6422 0.6265 0.7915
No log 5.4382 484 0.6342 0.6994 0.6342 0.7963
No log 5.4607 486 0.7883 0.6014 0.7883 0.8879
No log 5.4831 488 0.9366 0.6043 0.9366 0.9678
No log 5.5056 490 0.9657 0.6112 0.9657 0.9827
No log 5.5281 492 0.8623 0.6244 0.8623 0.9286
No log 5.5506 494 0.7973 0.6273 0.7973 0.8929
No log 5.5730 496 0.8033 0.6359 0.8033 0.8963
No log 5.5955 498 0.8562 0.6239 0.8562 0.9253
0.428 5.6180 500 0.9271 0.6055 0.9271 0.9629
0.428 5.6404 502 0.9119 0.6101 0.9119 0.9549
0.428 5.6629 504 0.9046 0.6230 0.9046 0.9511
0.428 5.6854 506 1.0054 0.6116 1.0054 1.0027
0.428 5.7079 508 1.2032 0.5625 1.2032 1.0969
0.428 5.7303 510 1.2430 0.5501 1.2430 1.1149
0.428 5.7528 512 1.1742 0.5763 1.1742 1.0836
0.428 5.7753 514 1.0349 0.5739 1.0349 1.0173
0.428 5.7978 516 1.0166 0.5831 1.0166 1.0083

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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_run1_AugV5_k18_task1_organization

Finetuned
(4040)
this model