ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_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: 0.6735
  • Qwk: 0.5855
  • Mse: 0.6735
  • Rmse: 0.8207

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 5.2940 -0.0444 5.2940 2.3009
No log 0.0449 4 3.4378 0.0649 3.4378 1.8541
No log 0.0674 6 1.9416 0.0719 1.9416 1.3934
No log 0.0899 8 1.9390 0.0364 1.9390 1.3925
No log 0.1124 10 1.8754 -0.0530 1.8754 1.3694
No log 0.1348 12 1.6512 -0.0858 1.6512 1.2850
No log 0.1573 14 1.4892 0.0811 1.4892 1.2203
No log 0.1798 16 1.5272 0.0578 1.5272 1.2358
No log 0.2022 18 1.6077 -0.0293 1.6077 1.2679
No log 0.2247 20 1.9760 -0.0024 1.9760 1.4057
No log 0.2472 22 2.5808 -0.1026 2.5808 1.6065
No log 0.2697 24 3.1201 -0.0610 3.1201 1.7664
No log 0.2921 26 2.6586 -0.0149 2.6586 1.6305
No log 0.3146 28 2.1109 0.0475 2.1109 1.4529
No log 0.3371 30 1.7149 0.0415 1.7149 1.3095
No log 0.3596 32 1.5396 0.0804 1.5396 1.2408
No log 0.3820 34 1.5122 0.0804 1.5122 1.2297
No log 0.4045 36 1.6846 0.0493 1.6846 1.2979
No log 0.4270 38 2.1641 0.0554 2.1641 1.4711
No log 0.4494 40 2.0149 0.0698 2.0149 1.4195
No log 0.4719 42 1.8018 0.1994 1.8018 1.3423
No log 0.4944 44 1.9081 0.2236 1.9081 1.3813
No log 0.5169 46 1.8276 0.2586 1.8276 1.3519
No log 0.5393 48 1.5027 0.2824 1.5027 1.2259
No log 0.5618 50 1.4522 0.2900 1.4522 1.2051
No log 0.5843 52 1.4101 0.2829 1.4101 1.1875
No log 0.6067 54 1.1993 0.3822 1.1993 1.0951
No log 0.6292 56 1.1255 0.3907 1.1255 1.0609
No log 0.6517 58 1.2358 0.3320 1.2358 1.1117
No log 0.6742 60 1.0965 0.3682 1.0965 1.0471
No log 0.6966 62 1.0196 0.4085 1.0196 1.0098
No log 0.7191 64 1.0160 0.4355 1.0160 1.0080
No log 0.7416 66 1.2278 0.3927 1.2278 1.1081
No log 0.7640 68 1.5117 0.3259 1.5117 1.2295
No log 0.7865 70 1.2042 0.4104 1.2042 1.0974
No log 0.8090 72 0.8229 0.5612 0.8229 0.9071
No log 0.8315 74 0.8907 0.5534 0.8907 0.9438
No log 0.8539 76 1.0110 0.5070 1.0110 1.0055
No log 0.8764 78 0.8535 0.5094 0.8535 0.9239
No log 0.8989 80 0.8069 0.5262 0.8069 0.8983
No log 0.9213 82 0.9014 0.5367 0.9014 0.9494
No log 0.9438 84 1.0083 0.5750 1.0083 1.0041
No log 0.9663 86 0.8427 0.5189 0.8427 0.9180
No log 0.9888 88 0.9005 0.5495 0.9005 0.9489
No log 1.0112 90 1.2873 0.3101 1.2873 1.1346
No log 1.0337 92 1.3257 0.2992 1.3257 1.1514
No log 1.0562 94 1.0537 0.4688 1.0537 1.0265
No log 1.0787 96 0.8587 0.4858 0.8587 0.9267
No log 1.1011 98 0.9277 0.4781 0.9277 0.9632
No log 1.1236 100 1.0720 0.4287 1.0720 1.0354
No log 1.1461 102 1.2735 0.3631 1.2735 1.1285
No log 1.1685 104 1.2640 0.3885 1.2640 1.1243
No log 1.1910 106 0.9729 0.4605 0.9729 0.9864
No log 1.2135 108 0.8400 0.4879 0.8400 0.9165
No log 1.2360 110 0.8702 0.5147 0.8702 0.9329
No log 1.2584 112 0.8454 0.4931 0.8454 0.9195
No log 1.2809 114 0.7882 0.5102 0.7882 0.8878
No log 1.3034 116 0.7682 0.5605 0.7682 0.8765
No log 1.3258 118 0.8055 0.5727 0.8055 0.8975
No log 1.3483 120 0.7679 0.5878 0.7679 0.8763
No log 1.3708 122 0.7246 0.6033 0.7246 0.8512
No log 1.3933 124 0.7268 0.6194 0.7268 0.8525
No log 1.4157 126 0.7344 0.6470 0.7344 0.8570
No log 1.4382 128 0.8475 0.6522 0.8475 0.9206
No log 1.4607 130 1.2024 0.4727 1.2024 1.0965
No log 1.4831 132 1.5980 0.3658 1.5980 1.2641
No log 1.5056 134 1.4766 0.3935 1.4766 1.2151
No log 1.5281 136 0.9858 0.5680 0.9858 0.9929
No log 1.5506 138 0.8462 0.6557 0.8462 0.9199
No log 1.5730 140 0.8690 0.6261 0.8690 0.9322
No log 1.5955 142 0.8141 0.6387 0.8141 0.9023
No log 1.6180 144 0.9053 0.5977 0.9053 0.9515
No log 1.6404 146 0.8533 0.5823 0.8533 0.9237
No log 1.6629 148 0.8256 0.5647 0.8256 0.9086
No log 1.6854 150 0.8409 0.5031 0.8409 0.9170
No log 1.7079 152 0.8533 0.4821 0.8533 0.9237
No log 1.7303 154 0.8431 0.4906 0.8431 0.9182
No log 1.7528 156 0.8858 0.5084 0.8858 0.9412
No log 1.7753 158 0.8073 0.5399 0.8073 0.8985
No log 1.7978 160 1.0489 0.4989 1.0489 1.0242
No log 1.8202 162 1.3901 0.3364 1.3901 1.1790
No log 1.8427 164 1.3721 0.3703 1.3721 1.1714
No log 1.8652 166 1.1414 0.4796 1.1414 1.0684
No log 1.8876 168 0.9152 0.5870 0.9152 0.9567
No log 1.9101 170 0.8924 0.6081 0.8924 0.9447
No log 1.9326 172 0.8385 0.5899 0.8385 0.9157
No log 1.9551 174 0.8752 0.5727 0.8752 0.9355
No log 1.9775 176 0.9782 0.5825 0.9782 0.9890
No log 2.0 178 0.9559 0.5657 0.9559 0.9777
No log 2.0225 180 0.8592 0.5784 0.8592 0.9269
No log 2.0449 182 0.7705 0.5557 0.7705 0.8778
No log 2.0674 184 0.7767 0.5404 0.7767 0.8813
No log 2.0899 186 0.7665 0.5422 0.7665 0.8755
No log 2.1124 188 0.7725 0.4986 0.7725 0.8789
No log 2.1348 190 0.7750 0.5543 0.7750 0.8804
No log 2.1573 192 0.7500 0.5808 0.7500 0.8660
No log 2.1798 194 0.7213 0.5916 0.7213 0.8493
No log 2.2022 196 0.6966 0.6595 0.6966 0.8346
No log 2.2247 198 0.6915 0.6463 0.6915 0.8316
No log 2.2472 200 0.7664 0.5853 0.7664 0.8754
No log 2.2697 202 1.0551 0.5403 1.0551 1.0272
No log 2.2921 204 1.1703 0.5067 1.1703 1.0818
No log 2.3146 206 1.0006 0.5607 1.0006 1.0003
No log 2.3371 208 0.8106 0.5668 0.8106 0.9003
No log 2.3596 210 0.7490 0.5465 0.7490 0.8654
No log 2.3820 212 0.7093 0.6011 0.7093 0.8422
No log 2.4045 214 0.7180 0.5554 0.7180 0.8473
No log 2.4270 216 0.7108 0.5691 0.7108 0.8431
No log 2.4494 218 0.7327 0.5786 0.7327 0.8560
No log 2.4719 220 0.7899 0.5831 0.7899 0.8887
No log 2.4944 222 0.8784 0.5493 0.8784 0.9372
No log 2.5169 224 0.9595 0.5384 0.9595 0.9795
No log 2.5393 226 0.9017 0.5686 0.9017 0.9496
No log 2.5618 228 0.8584 0.5953 0.8584 0.9265
No log 2.5843 230 0.7980 0.5489 0.7980 0.8933
No log 2.6067 232 0.7930 0.5652 0.7930 0.8905
No log 2.6292 234 0.8572 0.5498 0.8572 0.9259
No log 2.6517 236 0.8020 0.5963 0.8020 0.8955
No log 2.6742 238 0.7674 0.5873 0.7674 0.8760
No log 2.6966 240 0.7637 0.5517 0.7637 0.8739
No log 2.7191 242 0.7864 0.5403 0.7864 0.8868
No log 2.7416 244 0.7808 0.5153 0.7808 0.8837
No log 2.7640 246 0.8835 0.5438 0.8835 0.9400
No log 2.7865 248 0.9303 0.4698 0.9303 0.9645
No log 2.8090 250 0.7935 0.5359 0.7935 0.8908
No log 2.8315 252 0.8713 0.5502 0.8713 0.9334
No log 2.8539 254 1.0216 0.4673 1.0216 1.0107
No log 2.8764 256 0.9167 0.5458 0.9167 0.9575
No log 2.8989 258 0.7786 0.5127 0.7786 0.8824
No log 2.9213 260 0.7655 0.5643 0.7655 0.8749
No log 2.9438 262 0.8082 0.5572 0.8082 0.8990
No log 2.9663 264 0.7725 0.5449 0.7725 0.8789
No log 2.9888 266 0.7155 0.5923 0.7155 0.8458
No log 3.0112 268 0.6841 0.6440 0.6841 0.8271
No log 3.0337 270 0.6775 0.6782 0.6775 0.8231
No log 3.0562 272 0.7005 0.6332 0.7005 0.8370
No log 3.0787 274 0.8135 0.5770 0.8135 0.9019
No log 3.1011 276 0.8019 0.5686 0.8019 0.8955
No log 3.1236 278 0.7191 0.6421 0.7191 0.8480
No log 3.1461 280 0.6994 0.6421 0.6994 0.8363
No log 3.1685 282 0.6988 0.6452 0.6988 0.8359
No log 3.1910 284 0.7317 0.6623 0.7317 0.8554
No log 3.2135 286 0.6933 0.6810 0.6933 0.8326
No log 3.2360 288 0.6962 0.7016 0.6962 0.8344
No log 3.2584 290 0.6850 0.6853 0.6850 0.8276
No log 3.2809 292 0.7586 0.6355 0.7586 0.8710
No log 3.3034 294 0.7531 0.6279 0.7531 0.8678
No log 3.3258 296 0.7788 0.5744 0.7788 0.8825
No log 3.3483 298 0.7446 0.5713 0.7446 0.8629
No log 3.3708 300 0.6838 0.5710 0.6838 0.8269
No log 3.3933 302 0.6555 0.5831 0.6555 0.8096
No log 3.4157 304 0.6819 0.6111 0.6819 0.8258
No log 3.4382 306 0.8535 0.6231 0.8535 0.9238
No log 3.4607 308 0.9778 0.6006 0.9778 0.9888
No log 3.4831 310 0.9217 0.5922 0.9217 0.9600
No log 3.5056 312 0.8273 0.6318 0.8273 0.9095
No log 3.5281 314 0.7526 0.6050 0.7526 0.8675
No log 3.5506 316 0.6659 0.6392 0.6659 0.8160
No log 3.5730 318 0.6526 0.6037 0.6526 0.8078
No log 3.5955 320 0.6638 0.6088 0.6638 0.8147
No log 3.6180 322 0.6987 0.6355 0.6987 0.8359
No log 3.6404 324 0.7095 0.6368 0.7095 0.8423
No log 3.6629 326 0.6736 0.6490 0.6736 0.8207
No log 3.6854 328 0.6945 0.6349 0.6945 0.8333
No log 3.7079 330 0.7335 0.5868 0.7335 0.8564
No log 3.7303 332 0.8492 0.5636 0.8492 0.9215
No log 3.7528 334 0.8293 0.5677 0.8293 0.9107
No log 3.7753 336 0.8062 0.5703 0.8062 0.8979
No log 3.7978 338 0.7689 0.5882 0.7689 0.8768
No log 3.8202 340 0.6837 0.6053 0.6837 0.8268
No log 3.8427 342 0.6303 0.6900 0.6303 0.7939
No log 3.8652 344 0.6423 0.6834 0.6423 0.8014
No log 3.8876 346 0.6179 0.7038 0.6179 0.7860
No log 3.9101 348 0.6212 0.7176 0.6212 0.7882
No log 3.9326 350 0.6200 0.7138 0.6200 0.7874
No log 3.9551 352 0.6354 0.6185 0.6354 0.7971
No log 3.9775 354 0.6434 0.6185 0.6434 0.8021
No log 4.0 356 0.6422 0.6243 0.6422 0.8014
No log 4.0225 358 0.6656 0.5997 0.6656 0.8158
No log 4.0449 360 0.6483 0.6237 0.6483 0.8052
No log 4.0674 362 0.6520 0.6332 0.6520 0.8075
No log 4.0899 364 0.6749 0.6051 0.6749 0.8215
No log 4.1124 366 0.6609 0.6275 0.6609 0.8129
No log 4.1348 368 0.6580 0.5972 0.6580 0.8111
No log 4.1573 370 0.6721 0.5766 0.6721 0.8198
No log 4.1798 372 0.7001 0.5845 0.7001 0.8367
No log 4.2022 374 0.7674 0.5532 0.7674 0.8760
No log 4.2247 376 0.9154 0.5618 0.9154 0.9568
No log 4.2472 378 0.9751 0.5022 0.9751 0.9875
No log 4.2697 380 0.9002 0.5062 0.9002 0.9488
No log 4.2921 382 0.8112 0.5697 0.8112 0.9007
No log 4.3146 384 0.8293 0.5700 0.8293 0.9106
No log 4.3371 386 0.8951 0.5688 0.8951 0.9461
No log 4.3596 388 1.2056 0.4604 1.2056 1.0980
No log 4.3820 390 1.6422 0.3280 1.6422 1.2815
No log 4.4045 392 1.6427 0.3411 1.6427 1.2817
No log 4.4270 394 1.2636 0.4682 1.2636 1.1241
No log 4.4494 396 0.8152 0.5810 0.8152 0.9029
No log 4.4719 398 0.6983 0.6223 0.6984 0.8357
No log 4.4944 400 0.6926 0.5931 0.6926 0.8323
No log 4.5169 402 0.7364 0.6046 0.7364 0.8581
No log 4.5393 404 0.8710 0.5718 0.8710 0.9333
No log 4.5618 406 1.0518 0.5039 1.0518 1.0256
No log 4.5843 408 1.1102 0.5061 1.1102 1.0537
No log 4.6067 410 0.9333 0.5900 0.9333 0.9661
No log 4.6292 412 0.7452 0.6322 0.7452 0.8633
No log 4.6517 414 0.7214 0.6254 0.7214 0.8494
No log 4.6742 416 0.7924 0.5942 0.7924 0.8901
No log 4.6966 418 0.8397 0.5647 0.8397 0.9164
No log 4.7191 420 0.9646 0.5570 0.9646 0.9821
No log 4.7416 422 0.9677 0.5600 0.9677 0.9837
No log 4.7640 424 0.8263 0.5933 0.8263 0.9090
No log 4.7865 426 0.6806 0.6590 0.6806 0.8250
No log 4.8090 428 0.6722 0.6718 0.6722 0.8199
No log 4.8315 430 0.6762 0.6749 0.6762 0.8223
No log 4.8539 432 0.7656 0.6498 0.7656 0.8750
No log 4.8764 434 0.8355 0.6251 0.8355 0.9141
No log 4.8989 436 0.7693 0.6408 0.7693 0.8771
No log 4.9213 438 0.6520 0.6869 0.6520 0.8075
No log 4.9438 440 0.6177 0.6887 0.6177 0.7859
No log 4.9663 442 0.6098 0.6330 0.6098 0.7809
No log 4.9888 444 0.6204 0.6523 0.6204 0.7877
No log 5.0112 446 0.6193 0.6411 0.6193 0.7869
No log 5.0337 448 0.6235 0.6251 0.6235 0.7896
No log 5.0562 450 0.6893 0.6188 0.6893 0.8302
No log 5.0787 452 0.7443 0.6202 0.7443 0.8627
No log 5.1011 454 0.7967 0.6294 0.7967 0.8926
No log 5.1236 456 0.9651 0.5888 0.9651 0.9824
No log 5.1461 458 1.0255 0.5524 1.0255 1.0127
No log 5.1685 460 0.9176 0.5691 0.9176 0.9579
No log 5.1910 462 0.8325 0.6055 0.8325 0.9124
No log 5.2135 464 0.8038 0.6109 0.8039 0.8966
No log 5.2360 466 0.8753 0.6061 0.8753 0.9356
No log 5.2584 468 0.9750 0.5781 0.9750 0.9874
No log 5.2809 470 1.0014 0.5793 1.0014 1.0007
No log 5.3034 472 1.0456 0.5439 1.0456 1.0226
No log 5.3258 474 0.9242 0.5679 0.9242 0.9613
No log 5.3483 476 0.8024 0.6059 0.8024 0.8958
No log 5.3708 478 0.7646 0.6147 0.7646 0.8744
No log 5.3933 480 0.7964 0.6059 0.7964 0.8924
No log 5.4157 482 0.8277 0.6000 0.8277 0.9098
No log 5.4382 484 0.7653 0.6014 0.7653 0.8748
No log 5.4607 486 0.6516 0.6363 0.6516 0.8072
No log 5.4831 488 0.6342 0.6437 0.6342 0.7964
No log 5.5056 490 0.6560 0.6445 0.6560 0.8099
No log 5.5281 492 0.6629 0.6244 0.6629 0.8142
No log 5.5506 494 0.6613 0.6584 0.6613 0.8132
No log 5.5730 496 0.6698 0.6373 0.6698 0.8184
No log 5.5955 498 0.6833 0.6166 0.6833 0.8266
0.4485 5.6180 500 0.7752 0.6442 0.7752 0.8805
0.4485 5.6404 502 0.7594 0.6370 0.7594 0.8715
0.4485 5.6629 504 0.7915 0.6305 0.7915 0.8897
0.4485 5.6854 506 0.8068 0.6139 0.8068 0.8982
0.4485 5.7079 508 0.7180 0.6095 0.7180 0.8474
0.4485 5.7303 510 0.6735 0.5855 0.6735 0.8207

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_k18_task1_organization

Finetuned
(4040)
this model