ArabicNewSplits8_usingWellWrittenEssays_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: 0.9418
  • Qwk: 0.5789
  • Mse: 0.9418
  • Rmse: 0.9704

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 0.0227 2 5.3857 -0.0391 5.3857 2.3207
No log 0.0455 4 3.3063 0.0434 3.3063 1.8183
No log 0.0682 6 2.2771 0.0135 2.2771 1.5090
No log 0.0909 8 1.6900 0.1222 1.6900 1.3000
No log 0.1136 10 1.7661 0.0789 1.7661 1.3290
No log 0.1364 12 1.7138 -0.0328 1.7138 1.3091
No log 0.1591 14 1.2163 0.2282 1.2163 1.1029
No log 0.1818 16 1.2724 0.1845 1.2724 1.1280
No log 0.2045 18 1.2413 0.1543 1.2413 1.1142
No log 0.2273 20 1.1549 0.1684 1.1549 1.0747
No log 0.25 22 1.1802 0.1056 1.1802 1.0864
No log 0.2727 24 1.1552 0.1372 1.1552 1.0748
No log 0.2955 26 1.1383 0.1979 1.1383 1.0669
No log 0.3182 28 1.2309 0.2763 1.2309 1.1094
No log 0.3409 30 1.2869 0.2484 1.2869 1.1344
No log 0.3636 32 1.2456 0.3233 1.2456 1.1161
No log 0.3864 34 1.1972 0.3497 1.1972 1.0941
No log 0.4091 36 1.1240 0.3179 1.1240 1.0602
No log 0.4318 38 1.1445 0.3262 1.1445 1.0698
No log 0.4545 40 1.1466 0.3141 1.1466 1.0708
No log 0.4773 42 1.0677 0.3386 1.0677 1.0333
No log 0.5 44 1.0232 0.2580 1.0232 1.0115
No log 0.5227 46 1.0450 0.2599 1.0450 1.0222
No log 0.5455 48 1.2116 0.1459 1.2116 1.1007
No log 0.5682 50 1.4245 0.0332 1.4245 1.1935
No log 0.5909 52 1.3082 0.1201 1.3082 1.1438
No log 0.6136 54 1.2381 0.1848 1.2381 1.1127
No log 0.6364 56 1.0331 0.2875 1.0331 1.0164
No log 0.6591 58 0.9703 0.3575 0.9703 0.9850
No log 0.6818 60 0.9722 0.3857 0.9722 0.9860
No log 0.7045 62 0.9761 0.3208 0.9761 0.9880
No log 0.7273 64 1.0645 0.3753 1.0645 1.0317
No log 0.75 66 1.1219 0.3916 1.1219 1.0592
No log 0.7727 68 1.2185 0.3471 1.2185 1.1039
No log 0.7955 70 1.2216 0.3529 1.2216 1.1052
No log 0.8182 72 1.1264 0.3424 1.1264 1.0613
No log 0.8409 74 1.0359 0.3374 1.0359 1.0178
No log 0.8636 76 0.9888 0.4151 0.9888 0.9944
No log 0.8864 78 1.0048 0.4345 1.0048 1.0024
No log 0.9091 80 1.0108 0.4457 1.0108 1.0054
No log 0.9318 82 1.0547 0.3666 1.0547 1.0270
No log 0.9545 84 1.0619 0.4069 1.0619 1.0305
No log 0.9773 86 0.9863 0.4418 0.9863 0.9931
No log 1.0 88 0.8924 0.5392 0.8924 0.9447
No log 1.0227 90 0.8867 0.5485 0.8867 0.9416
No log 1.0455 92 0.9169 0.5121 0.9169 0.9575
No log 1.0682 94 1.0280 0.3637 1.0280 1.0139
No log 1.0909 96 1.1830 0.3759 1.1830 1.0876
No log 1.1136 98 1.3166 0.2528 1.3166 1.1474
No log 1.1364 100 1.2115 0.2800 1.2115 1.1007
No log 1.1591 102 1.0515 0.4003 1.0515 1.0254
No log 1.1818 104 0.9555 0.5319 0.9555 0.9775
No log 1.2045 106 0.9418 0.5334 0.9418 0.9705
No log 1.2273 108 0.9723 0.5502 0.9723 0.9860
No log 1.25 110 0.9863 0.5010 0.9863 0.9931
No log 1.2727 112 1.0307 0.3765 1.0307 1.0152
No log 1.2955 114 1.0921 0.3461 1.0921 1.0450
No log 1.3182 116 0.9991 0.3825 0.9991 0.9996
No log 1.3409 118 0.8123 0.4936 0.8123 0.9013
No log 1.3636 120 0.7884 0.6031 0.7884 0.8879
No log 1.3864 122 0.8101 0.6239 0.8101 0.9001
No log 1.4091 124 0.9108 0.5657 0.9108 0.9544
No log 1.4318 126 0.9897 0.5098 0.9897 0.9948
No log 1.4545 128 1.0107 0.4964 1.0107 1.0053
No log 1.4773 130 0.9735 0.5263 0.9735 0.9867
No log 1.5 132 0.9334 0.4784 0.9334 0.9661
No log 1.5227 134 0.9341 0.5211 0.9341 0.9665
No log 1.5455 136 0.9500 0.5317 0.9500 0.9747
No log 1.5682 138 0.9779 0.4891 0.9779 0.9889
No log 1.5909 140 1.0222 0.4877 1.0222 1.0110
No log 1.6136 142 1.0360 0.5141 1.0360 1.0178
No log 1.6364 144 1.0244 0.5227 1.0244 1.0121
No log 1.6591 146 0.9251 0.5556 0.9251 0.9618
No log 1.6818 148 0.9457 0.5521 0.9457 0.9724
No log 1.7045 150 0.9837 0.4845 0.9837 0.9918
No log 1.7273 152 0.9738 0.4687 0.9738 0.9868
No log 1.75 154 0.9559 0.4682 0.9559 0.9777
No log 1.7727 156 0.9347 0.4281 0.9347 0.9668
No log 1.7955 158 0.9336 0.5464 0.9336 0.9662
No log 1.8182 160 1.0751 0.5297 1.0751 1.0369
No log 1.8409 162 1.3334 0.3867 1.3334 1.1547
No log 1.8636 164 1.4273 0.3888 1.4273 1.1947
No log 1.8864 166 1.1584 0.4865 1.1584 1.0763
No log 1.9091 168 0.8880 0.6220 0.8880 0.9423
No log 1.9318 170 0.8328 0.5667 0.8328 0.9126
No log 1.9545 172 0.8730 0.5640 0.8730 0.9343
No log 1.9773 174 0.9841 0.5306 0.9841 0.9920
No log 2.0 176 1.2158 0.5181 1.2158 1.1026
No log 2.0227 178 1.4022 0.4449 1.4022 1.1842
No log 2.0455 180 1.4968 0.3317 1.4968 1.2234
No log 2.0682 182 1.3387 0.4221 1.3387 1.1570
No log 2.0909 184 1.1053 0.4760 1.1053 1.0513
No log 2.1136 186 1.0728 0.4877 1.0728 1.0358
No log 2.1364 188 1.1805 0.4509 1.1805 1.0865
No log 2.1591 190 1.2710 0.4153 1.2710 1.1274
No log 2.1818 192 1.1628 0.4543 1.1628 1.0783
No log 2.2045 194 0.9472 0.5510 0.9472 0.9732
No log 2.2273 196 0.8278 0.5526 0.8278 0.9098
No log 2.25 198 0.8211 0.5510 0.8211 0.9061
No log 2.2727 200 0.9165 0.5422 0.9165 0.9573
No log 2.2955 202 1.0955 0.5483 1.0955 1.0467
No log 2.3182 204 1.1521 0.5399 1.1521 1.0734
No log 2.3409 206 1.0776 0.5415 1.0776 1.0381
No log 2.3636 208 1.0145 0.5292 1.0145 1.0072
No log 2.3864 210 0.9527 0.5562 0.9527 0.9760
No log 2.4091 212 0.8871 0.5651 0.8871 0.9419
No log 2.4318 214 0.8840 0.5768 0.8840 0.9402
No log 2.4545 216 0.8600 0.5920 0.8600 0.9274
No log 2.4773 218 0.8572 0.5974 0.8572 0.9258
No log 2.5 220 0.8173 0.6236 0.8173 0.9041
No log 2.5227 222 0.7700 0.6342 0.7701 0.8775
No log 2.5455 224 0.7572 0.5965 0.7572 0.8702
No log 2.5682 226 0.7685 0.6373 0.7685 0.8766
No log 2.5909 228 0.7501 0.6609 0.7501 0.8661
No log 2.6136 230 0.8256 0.6227 0.8256 0.9086
No log 2.6364 232 0.9100 0.5753 0.9100 0.9539
No log 2.6591 234 0.8501 0.6223 0.8501 0.9220
No log 2.6818 236 0.7747 0.6409 0.7747 0.8802
No log 2.7045 238 0.7578 0.5740 0.7578 0.8705
No log 2.7273 240 0.7825 0.5116 0.7825 0.8846
No log 2.75 242 0.7957 0.5572 0.7957 0.8920
No log 2.7727 244 0.7926 0.6266 0.7926 0.8903
No log 2.7955 246 0.7811 0.6302 0.7811 0.8838
No log 2.8182 248 0.7790 0.6525 0.7790 0.8826
No log 2.8409 250 0.7791 0.6535 0.7791 0.8827
No log 2.8636 252 0.7780 0.6535 0.7780 0.8821
No log 2.8864 254 0.8327 0.6421 0.8327 0.9125
No log 2.9091 256 0.8828 0.6335 0.8828 0.9396
No log 2.9318 258 0.8522 0.6179 0.8522 0.9232
No log 2.9545 260 0.7991 0.6593 0.7991 0.8939
No log 2.9773 262 0.7322 0.6268 0.7322 0.8557
No log 3.0 264 0.7076 0.5991 0.7076 0.8412
No log 3.0227 266 0.6955 0.6374 0.6955 0.8340
No log 3.0455 268 0.7650 0.6158 0.7650 0.8747
No log 3.0682 270 0.8600 0.6020 0.8600 0.9274
No log 3.0909 272 0.9791 0.5679 0.9791 0.9895
No log 3.1136 274 0.9725 0.5730 0.9725 0.9862
No log 3.1364 276 0.9762 0.5667 0.9762 0.9880
No log 3.1591 278 1.0122 0.5268 1.0122 1.0061
No log 3.1818 280 0.8620 0.5796 0.8620 0.9285
No log 3.2045 282 0.8090 0.5440 0.8090 0.8994
No log 3.2273 284 0.8616 0.5492 0.8616 0.9282
No log 3.25 286 0.9753 0.5620 0.9753 0.9876
No log 3.2727 288 1.0971 0.5219 1.0971 1.0474
No log 3.2955 290 1.0695 0.5030 1.0695 1.0342
No log 3.3182 292 0.8876 0.5849 0.8876 0.9421
No log 3.3409 294 0.8260 0.6213 0.8260 0.9089
No log 3.3636 296 0.8640 0.6362 0.8640 0.9295
No log 3.3864 298 0.9022 0.6182 0.9022 0.9498
No log 3.4091 300 0.8792 0.6182 0.8792 0.9376
No log 3.4318 302 0.9161 0.6064 0.9161 0.9571
No log 3.4545 304 0.9290 0.5911 0.9290 0.9638
No log 3.4773 306 0.9286 0.5911 0.9286 0.9636
No log 3.5 308 0.9879 0.5594 0.9879 0.9939
No log 3.5227 310 0.9490 0.5956 0.9490 0.9741
No log 3.5455 312 0.8684 0.5840 0.8684 0.9319
No log 3.5682 314 0.7884 0.5709 0.7884 0.8879
No log 3.5909 316 0.7702 0.4796 0.7702 0.8776
No log 3.6136 318 0.7619 0.4833 0.7619 0.8729
No log 3.6364 320 0.7798 0.5291 0.7798 0.8831
No log 3.6591 322 0.9425 0.5989 0.9425 0.9708
No log 3.6818 324 1.2633 0.4779 1.2633 1.1240
No log 3.7045 326 1.4179 0.4578 1.4179 1.1908
No log 3.7273 328 1.2776 0.4566 1.2776 1.1303
No log 3.75 330 1.1321 0.5073 1.1321 1.0640
No log 3.7727 332 0.9718 0.5459 0.9718 0.9858
No log 3.7955 334 0.8969 0.6082 0.8969 0.9471
No log 3.8182 336 0.9335 0.5647 0.9335 0.9662
No log 3.8409 338 0.9780 0.5493 0.9780 0.9889
No log 3.8636 340 0.9522 0.5667 0.9522 0.9758
No log 3.8864 342 0.8769 0.5386 0.8769 0.9364
No log 3.9091 344 0.8205 0.5845 0.8205 0.9058
No log 3.9318 346 0.8044 0.6230 0.8044 0.8969
No log 3.9545 348 0.7995 0.6216 0.7995 0.8942
No log 3.9773 350 0.8013 0.6203 0.8013 0.8952
No log 4.0 352 0.8452 0.5980 0.8452 0.9193
No log 4.0227 354 0.8349 0.5849 0.8349 0.9137
No log 4.0455 356 0.8261 0.5915 0.8261 0.9089
No log 4.0682 358 0.7743 0.5713 0.7743 0.8800
No log 4.0909 360 0.7138 0.5972 0.7138 0.8449
No log 4.1136 362 0.7014 0.6015 0.7014 0.8375
No log 4.1364 364 0.7223 0.5888 0.7223 0.8499
No log 4.1591 366 0.7199 0.6146 0.7199 0.8484
No log 4.1818 368 0.7224 0.6026 0.7224 0.8499
No log 4.2045 370 0.6987 0.6340 0.6987 0.8359
No log 4.2273 372 0.6868 0.6397 0.6868 0.8287
No log 4.25 374 0.6953 0.6714 0.6953 0.8338
No log 4.2727 376 0.7536 0.6479 0.7536 0.8681
No log 4.2955 378 0.7551 0.6489 0.7551 0.8690
No log 4.3182 380 0.8285 0.6377 0.8285 0.9102
No log 4.3409 382 1.0506 0.5543 1.0506 1.0250
No log 4.3636 384 1.1096 0.5360 1.1096 1.0534
No log 4.3864 386 0.9907 0.5567 0.9907 0.9953
No log 4.4091 388 0.8646 0.5847 0.8646 0.9298
No log 4.4318 390 0.7878 0.6253 0.7878 0.8876
No log 4.4545 392 0.8015 0.6419 0.8015 0.8953
No log 4.4773 394 0.7680 0.6253 0.7680 0.8764
No log 4.5 396 0.7853 0.6427 0.7853 0.8862
No log 4.5227 398 0.8851 0.5807 0.8851 0.9408
No log 4.5455 400 0.9309 0.5625 0.9309 0.9648
No log 4.5682 402 0.9300 0.5560 0.9300 0.9644
No log 4.5909 404 0.8705 0.5880 0.8705 0.9330
No log 4.6136 406 0.8684 0.5880 0.8684 0.9319
No log 4.6364 408 0.8806 0.5919 0.8806 0.9384
No log 4.6591 410 0.9129 0.5863 0.9129 0.9555
No log 4.6818 412 0.8973 0.5894 0.8973 0.9473
No log 4.7045 414 0.8684 0.5784 0.8684 0.9319
No log 4.7273 416 0.8194 0.5974 0.8194 0.9052
No log 4.75 418 0.8054 0.6103 0.8054 0.8974
No log 4.7727 420 0.7816 0.6278 0.7816 0.8841
No log 4.7955 422 0.8054 0.6334 0.8054 0.8975
No log 4.8182 424 0.8153 0.6233 0.8153 0.9030
No log 4.8409 426 0.9075 0.6043 0.9075 0.9526
No log 4.8636 428 1.0297 0.5550 1.0297 1.0147
No log 4.8864 430 1.0112 0.5609 1.0112 1.0056
No log 4.9091 432 0.9075 0.5905 0.9075 0.9526
No log 4.9318 434 0.8860 0.6116 0.8860 0.9413
No log 4.9545 436 0.9650 0.5819 0.9650 0.9823
No log 4.9773 438 1.0982 0.5153 1.0982 1.0480
No log 5.0 440 1.1953 0.4784 1.1953 1.0933
No log 5.0227 442 1.1704 0.4879 1.1704 1.0819
No log 5.0455 444 1.0805 0.4974 1.0805 1.0395
No log 5.0682 446 0.9657 0.5755 0.9657 0.9827
No log 5.0909 448 0.9604 0.5670 0.9604 0.9800
No log 5.1136 450 1.0106 0.5289 1.0106 1.0053
No log 5.1364 452 1.0827 0.5196 1.0827 1.0406
No log 5.1591 454 1.0840 0.5196 1.0840 1.0412
No log 5.1818 456 1.2051 0.5107 1.2051 1.0978
No log 5.2045 458 1.2715 0.5179 1.2715 1.1276
No log 5.2273 460 1.2260 0.5185 1.2260 1.1073
No log 5.25 462 1.0503 0.5312 1.0503 1.0248
No log 5.2727 464 0.8892 0.6301 0.8892 0.9430
No log 5.2955 466 0.8500 0.6570 0.8500 0.9219
No log 5.3182 468 0.9221 0.5922 0.9221 0.9603
No log 5.3409 470 1.1274 0.5368 1.1274 1.0618
No log 5.3636 472 1.4135 0.4996 1.4135 1.1889
No log 5.3864 474 1.4477 0.4879 1.4477 1.2032
No log 5.4091 476 1.2715 0.4942 1.2715 1.1276
No log 5.4318 478 1.0056 0.5307 1.0056 1.0028
No log 5.4545 480 0.8191 0.6260 0.8191 0.9050
No log 5.4773 482 0.8025 0.6183 0.8025 0.8958
No log 5.5 484 0.8618 0.6030 0.8618 0.9283
No log 5.5227 486 0.9548 0.5730 0.9548 0.9771
No log 5.5455 488 1.0541 0.5247 1.0541 1.0267
No log 5.5682 490 1.0840 0.4992 1.0840 1.0411
No log 5.5909 492 1.0198 0.5446 1.0198 1.0099
No log 5.6136 494 0.9254 0.5940 0.9254 0.9620
No log 5.6364 496 0.8397 0.6516 0.8397 0.9163
No log 5.6591 498 0.7960 0.6292 0.7960 0.8922
0.4734 5.6818 500 0.8426 0.6179 0.8426 0.9179
0.4734 5.7045 502 0.9234 0.5880 0.9234 0.9609
0.4734 5.7273 504 0.8592 0.5918 0.8592 0.9270
0.4734 5.75 506 0.8299 0.6116 0.8299 0.9110
0.4734 5.7727 508 0.8818 0.6019 0.8818 0.9390
0.4734 5.7955 510 0.9418 0.5789 0.9418 0.9704

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/ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k18_task1_organization

Finetuned
(4040)
this model