ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k4_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: 0.6754
  • Qwk: 0.6366
  • Mse: 0.6754
  • Rmse: 0.8218

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 0.0952 2 5.0626 -0.0237 5.0626 2.2500
No log 0.1905 4 2.8930 0.0937 2.8930 1.7009
No log 0.2857 6 1.8042 0.0485 1.8042 1.3432
No log 0.3810 8 1.3906 0.2367 1.3906 1.1792
No log 0.4762 10 1.1225 0.2265 1.1225 1.0595
No log 0.5714 12 1.1848 0.2383 1.1848 1.0885
No log 0.6667 14 1.3220 0.2502 1.3220 1.1498
No log 0.7619 16 1.2219 0.2174 1.2219 1.1054
No log 0.8571 18 1.1360 0.2013 1.1360 1.0658
No log 0.9524 20 1.1421 0.3242 1.1421 1.0687
No log 1.0476 22 1.3299 0.1055 1.3299 1.1532
No log 1.1429 24 1.3514 0.1310 1.3514 1.1625
No log 1.2381 26 1.3451 0.1740 1.3451 1.1598
No log 1.3333 28 1.5692 0.1482 1.5692 1.2527
No log 1.4286 30 1.5966 0.2083 1.5966 1.2636
No log 1.5238 32 1.2707 0.2159 1.2707 1.1273
No log 1.6190 34 1.1260 0.2838 1.1260 1.0611
No log 1.7143 36 1.0404 0.3282 1.0404 1.0200
No log 1.8095 38 1.0441 0.3050 1.0441 1.0218
No log 1.9048 40 1.1325 0.2890 1.1325 1.0642
No log 2.0 42 1.3185 0.2825 1.3185 1.1482
No log 2.0952 44 1.3131 0.3044 1.3131 1.1459
No log 2.1905 46 1.1894 0.3165 1.1894 1.0906
No log 2.2857 48 1.2060 0.3777 1.2060 1.0982
No log 2.3810 50 1.2525 0.4169 1.2525 1.1191
No log 2.4762 52 1.3564 0.3947 1.3564 1.1646
No log 2.5714 54 1.4931 0.3861 1.4931 1.2219
No log 2.6667 56 1.1271 0.4760 1.1271 1.0616
No log 2.7619 58 0.8642 0.5507 0.8642 0.9296
No log 2.8571 60 0.8703 0.5710 0.8703 0.9329
No log 2.9524 62 0.8568 0.5586 0.8568 0.9256
No log 3.0476 64 0.8225 0.5438 0.8225 0.9069
No log 3.1429 66 0.8098 0.5179 0.8098 0.8999
No log 3.2381 68 0.8125 0.5049 0.8125 0.9014
No log 3.3333 70 0.8450 0.5120 0.8450 0.9192
No log 3.4286 72 0.8091 0.4877 0.8091 0.8995
No log 3.5238 74 0.7868 0.5112 0.7868 0.8870
No log 3.6190 76 0.7812 0.5727 0.7812 0.8838
No log 3.7143 78 0.9935 0.5731 0.9935 0.9968
No log 3.8095 80 1.0684 0.5435 1.0684 1.0336
No log 3.9048 82 0.7862 0.6704 0.7862 0.8867
No log 4.0 84 0.7000 0.5943 0.7000 0.8367
No log 4.0952 86 0.7327 0.6314 0.7327 0.8560
No log 4.1905 88 0.8289 0.6361 0.8289 0.9104
No log 4.2857 90 0.8536 0.6361 0.8536 0.9239
No log 4.3810 92 0.8226 0.6361 0.8226 0.9070
No log 4.4762 94 0.7061 0.6365 0.7061 0.8403
No log 4.5714 96 0.6873 0.6336 0.6873 0.8290
No log 4.6667 98 0.6776 0.6560 0.6776 0.8231
No log 4.7619 100 0.7120 0.6639 0.7120 0.8438
No log 4.8571 102 0.7411 0.6689 0.7411 0.8609
No log 4.9524 104 0.9018 0.6156 0.9018 0.9496
No log 5.0476 106 0.9410 0.6338 0.9410 0.9701
No log 5.1429 108 0.7959 0.6351 0.7959 0.8921
No log 5.2381 110 0.7720 0.6632 0.7720 0.8786
No log 5.3333 112 0.7479 0.6409 0.7479 0.8648
No log 5.4286 114 0.7310 0.6492 0.7310 0.8550
No log 5.5238 116 0.7348 0.6442 0.7348 0.8572
No log 5.6190 118 0.6980 0.6581 0.6980 0.8355
No log 5.7143 120 0.7669 0.6390 0.7669 0.8757
No log 5.8095 122 0.7718 0.6252 0.7718 0.8785
No log 5.9048 124 0.7255 0.6338 0.7255 0.8518
No log 6.0 126 0.7494 0.6375 0.7494 0.8657
No log 6.0952 128 0.6938 0.6235 0.6938 0.8329
No log 6.1905 130 0.6202 0.6626 0.6202 0.7875
No log 6.2857 132 0.6282 0.6859 0.6282 0.7926
No log 6.3810 134 0.6293 0.6766 0.6293 0.7933
No log 6.4762 136 0.6357 0.6541 0.6357 0.7973
No log 6.5714 138 0.6631 0.6024 0.6631 0.8143
No log 6.6667 140 0.7434 0.6082 0.7434 0.8622
No log 6.7619 142 0.7372 0.5853 0.7372 0.8586
No log 6.8571 144 0.6978 0.5956 0.6978 0.8354
No log 6.9524 146 0.6958 0.6053 0.6958 0.8341
No log 7.0476 148 0.6809 0.6148 0.6809 0.8251
No log 7.1429 150 0.7067 0.6419 0.7067 0.8406
No log 7.2381 152 0.7820 0.6425 0.7820 0.8843
No log 7.3333 154 0.7235 0.6540 0.7235 0.8506
No log 7.4286 156 0.6993 0.6940 0.6993 0.8362
No log 7.5238 158 0.6899 0.6611 0.6899 0.8306
No log 7.6190 160 0.6879 0.6454 0.6879 0.8294
No log 7.7143 162 0.7968 0.6108 0.7968 0.8926
No log 7.8095 164 0.7872 0.6374 0.7872 0.8873
No log 7.9048 166 0.7216 0.6036 0.7216 0.8495
No log 8.0 168 0.7100 0.6473 0.7100 0.8426
No log 8.0952 170 0.6607 0.6204 0.6607 0.8128
No log 8.1905 172 0.6552 0.6350 0.6552 0.8095
No log 8.2857 174 0.6443 0.6319 0.6443 0.8027
No log 8.3810 176 0.6682 0.6339 0.6682 0.8175
No log 8.4762 178 0.6974 0.6117 0.6974 0.8351
No log 8.5714 180 0.7028 0.5860 0.7028 0.8383
No log 8.6667 182 0.6950 0.6346 0.6950 0.8337
No log 8.7619 184 0.6517 0.7095 0.6517 0.8073
No log 8.8571 186 0.6566 0.6994 0.6566 0.8103
No log 8.9524 188 0.6635 0.7153 0.6635 0.8146
No log 9.0476 190 0.7281 0.6400 0.7281 0.8533
No log 9.1429 192 0.7377 0.6485 0.7377 0.8589
No log 9.2381 194 0.6979 0.6749 0.6979 0.8354
No log 9.3333 196 0.6741 0.6359 0.6741 0.8211
No log 9.4286 198 0.6827 0.6153 0.6827 0.8263
No log 9.5238 200 0.6811 0.6485 0.6811 0.8253
No log 9.6190 202 0.7226 0.5896 0.7226 0.8501
No log 9.7143 204 0.7551 0.5651 0.7551 0.8690
No log 9.8095 206 0.6812 0.6258 0.6812 0.8253
No log 9.9048 208 0.6921 0.6558 0.6921 0.8319
No log 10.0 210 0.8380 0.6239 0.8380 0.9154
No log 10.0952 212 0.8326 0.6239 0.8326 0.9125
No log 10.1905 214 0.6737 0.6603 0.6737 0.8208
No log 10.2857 216 0.6454 0.6591 0.6454 0.8034
No log 10.3810 218 0.6836 0.6281 0.6836 0.8268
No log 10.4762 220 0.6951 0.6218 0.6951 0.8337
No log 10.5714 222 0.6741 0.6216 0.6741 0.8210
No log 10.6667 224 0.7295 0.6400 0.7295 0.8541
No log 10.7619 226 0.9107 0.5950 0.9107 0.9543
No log 10.8571 228 1.0658 0.5547 1.0658 1.0324
No log 10.9524 230 1.0031 0.5929 1.0031 1.0016
No log 11.0476 232 0.8512 0.6388 0.8512 0.9226
No log 11.1429 234 0.6942 0.6279 0.6942 0.8332
No log 11.2381 236 0.6858 0.6161 0.6858 0.8281
No log 11.3333 238 0.7228 0.6496 0.7228 0.8501
No log 11.4286 240 0.7352 0.6403 0.7352 0.8574
No log 11.5238 242 0.7263 0.5760 0.7263 0.8522
No log 11.6190 244 0.7388 0.6057 0.7388 0.8595
No log 11.7143 246 0.7237 0.6059 0.7237 0.8507
No log 11.8095 248 0.8034 0.6202 0.8034 0.8964
No log 11.9048 250 0.8717 0.5906 0.8717 0.9337
No log 12.0 252 0.7705 0.5943 0.7705 0.8778
No log 12.0952 254 0.7045 0.6494 0.7045 0.8394
No log 12.1905 256 0.7073 0.6496 0.7073 0.8410
No log 12.2857 258 0.7206 0.6151 0.7206 0.8489
No log 12.3810 260 0.8050 0.6256 0.8050 0.8972
No log 12.4762 262 0.8765 0.5305 0.8765 0.9362
No log 12.5714 264 0.7903 0.6208 0.7903 0.8890
No log 12.6667 266 0.7159 0.5687 0.7159 0.8461
No log 12.7619 268 0.8268 0.5527 0.8268 0.9093
No log 12.8571 270 0.9628 0.5076 0.9628 0.9812
No log 12.9524 272 0.8931 0.5222 0.8931 0.9450
No log 13.0476 274 0.7364 0.6152 0.7364 0.8581
No log 13.1429 276 0.7513 0.5838 0.7513 0.8668
No log 13.2381 278 0.8981 0.5961 0.8981 0.9477
No log 13.3333 280 0.9593 0.5613 0.9593 0.9794
No log 13.4286 282 0.8742 0.5663 0.8742 0.9350
No log 13.5238 284 0.7771 0.5944 0.7771 0.8815
No log 13.6190 286 0.7474 0.5997 0.7474 0.8645
No log 13.7143 288 0.7383 0.5997 0.7383 0.8592
No log 13.8095 290 0.7175 0.6051 0.7175 0.8471
No log 13.9048 292 0.6970 0.6408 0.6970 0.8348
No log 14.0 294 0.6910 0.6620 0.6910 0.8313
No log 14.0952 296 0.7221 0.6291 0.7221 0.8497
No log 14.1905 298 0.7144 0.6375 0.7144 0.8452
No log 14.2857 300 0.6806 0.6357 0.6806 0.8250
No log 14.3810 302 0.7032 0.6290 0.7032 0.8386
No log 14.4762 304 0.7553 0.6108 0.7553 0.8691
No log 14.5714 306 0.7549 0.5989 0.7549 0.8688
No log 14.6667 308 0.7774 0.6015 0.7773 0.8817
No log 14.7619 310 0.7282 0.6582 0.7282 0.8534
No log 14.8571 312 0.6897 0.6713 0.6897 0.8305
No log 14.9524 314 0.7730 0.6008 0.7730 0.8792
No log 15.0476 316 0.9209 0.6124 0.9209 0.9596
No log 15.1429 318 0.9212 0.6207 0.9212 0.9598
No log 15.2381 320 0.8626 0.6135 0.8626 0.9288
No log 15.3333 322 0.8226 0.5935 0.8226 0.9070
No log 15.4286 324 0.7557 0.6227 0.7557 0.8693
No log 15.5238 326 0.7449 0.6319 0.7449 0.8631
No log 15.6190 328 0.7741 0.6151 0.7741 0.8798
No log 15.7143 330 0.8575 0.5438 0.8575 0.9260
No log 15.8095 332 0.9129 0.4868 0.9129 0.9555
No log 15.9048 334 0.8753 0.5231 0.8753 0.9356
No log 16.0 336 0.7659 0.6165 0.7659 0.8752
No log 16.0952 338 0.7010 0.6450 0.7010 0.8373
No log 16.1905 340 0.6996 0.6510 0.6996 0.8364
No log 16.2857 342 0.7052 0.6525 0.7052 0.8398
No log 16.3810 344 0.7163 0.6474 0.7163 0.8463
No log 16.4762 346 0.7505 0.6270 0.7505 0.8663
No log 16.5714 348 0.7641 0.6202 0.7641 0.8741
No log 16.6667 350 0.8239 0.6139 0.8239 0.9077
No log 16.7619 352 0.8066 0.6379 0.8066 0.8981
No log 16.8571 354 0.7533 0.6618 0.7533 0.8679
No log 16.9524 356 0.7644 0.6584 0.7644 0.8743
No log 17.0476 358 0.7685 0.6328 0.7685 0.8767
No log 17.1429 360 0.7196 0.6509 0.7196 0.8483
No log 17.2381 362 0.6729 0.7046 0.6729 0.8203
No log 17.3333 364 0.6771 0.7158 0.6771 0.8229
No log 17.4286 366 0.6837 0.6910 0.6837 0.8269
No log 17.5238 368 0.7086 0.6709 0.7086 0.8418
No log 17.6190 370 0.7742 0.6374 0.7742 0.8799
No log 17.7143 372 0.7860 0.5911 0.7860 0.8865
No log 17.8095 374 0.7989 0.5655 0.7989 0.8938
No log 17.9048 376 0.7668 0.5840 0.7668 0.8757
No log 18.0 378 0.7187 0.6414 0.7187 0.8478
No log 18.0952 380 0.6792 0.6702 0.6792 0.8241
No log 18.1905 382 0.6623 0.6988 0.6623 0.8138
No log 18.2857 384 0.6638 0.7132 0.6638 0.8147
No log 18.3810 386 0.6744 0.7188 0.6744 0.8212
No log 18.4762 388 0.7698 0.6556 0.7698 0.8774
No log 18.5714 390 0.7975 0.6181 0.7975 0.8930
No log 18.6667 392 0.7464 0.6176 0.7464 0.8639
No log 18.7619 394 0.7414 0.6207 0.7414 0.8610
No log 18.8571 396 0.7387 0.6077 0.7387 0.8595
No log 18.9524 398 0.7694 0.6121 0.7694 0.8771
No log 19.0476 400 0.7918 0.6268 0.7918 0.8898
No log 19.1429 402 0.7878 0.6414 0.7878 0.8876
No log 19.2381 404 0.7277 0.6754 0.7277 0.8530
No log 19.3333 406 0.6712 0.6826 0.6712 0.8193
No log 19.4286 408 0.6908 0.6616 0.6908 0.8312
No log 19.5238 410 0.6949 0.6483 0.6949 0.8336
No log 19.6190 412 0.6830 0.6554 0.6830 0.8264
No log 19.7143 414 0.7330 0.6593 0.7330 0.8561
No log 19.8095 416 0.7638 0.6235 0.7638 0.8740
No log 19.9048 418 0.7712 0.5959 0.7712 0.8782
No log 20.0 420 0.7699 0.5255 0.7699 0.8774
No log 20.0952 422 0.7630 0.5399 0.7630 0.8735
No log 20.1905 424 0.7488 0.5402 0.7488 0.8653
No log 20.2857 426 0.7230 0.5598 0.7230 0.8503
No log 20.3810 428 0.7372 0.6228 0.7372 0.8586
No log 20.4762 430 0.7172 0.6240 0.7172 0.8469
No log 20.5714 432 0.6914 0.6481 0.6914 0.8315
No log 20.6667 434 0.6701 0.6660 0.6701 0.8186
No log 20.7619 436 0.6791 0.6677 0.6791 0.8241
No log 20.8571 438 0.6758 0.6826 0.6758 0.8221
No log 20.9524 440 0.6832 0.6647 0.6832 0.8266
No log 21.0476 442 0.6772 0.6498 0.6772 0.8229
No log 21.1429 444 0.6816 0.6268 0.6816 0.8256
No log 21.2381 446 0.7409 0.6454 0.7409 0.8607
No log 21.3333 448 0.7747 0.6508 0.7747 0.8802
No log 21.4286 450 0.7829 0.6291 0.7829 0.8848
No log 21.5238 452 0.7402 0.6354 0.7402 0.8603
No log 21.6190 454 0.7094 0.6504 0.7094 0.8423
No log 21.7143 456 0.6819 0.6630 0.6819 0.8258
No log 21.8095 458 0.6732 0.6752 0.6732 0.8205
No log 21.9048 460 0.6741 0.7039 0.6741 0.8211
No log 22.0 462 0.6808 0.7147 0.6808 0.8251
No log 22.0952 464 0.7041 0.7187 0.7041 0.8391
No log 22.1905 466 0.6858 0.6837 0.6858 0.8281
No log 22.2857 468 0.6735 0.6526 0.6735 0.8207
No log 22.3810 470 0.6937 0.6295 0.6937 0.8329
No log 22.4762 472 0.7322 0.6181 0.7322 0.8557
No log 22.5714 474 0.7626 0.6018 0.7626 0.8733
No log 22.6667 476 0.7847 0.6296 0.7847 0.8858
No log 22.7619 478 0.7842 0.6418 0.7842 0.8856
No log 22.8571 480 0.7090 0.6756 0.7090 0.8420
No log 22.9524 482 0.6749 0.6878 0.6749 0.8215
No log 23.0476 484 0.6729 0.6894 0.6729 0.8203
No log 23.1429 486 0.6841 0.6920 0.6841 0.8271
No log 23.2381 488 0.6842 0.6798 0.6842 0.8272
No log 23.3333 490 0.6690 0.6300 0.6690 0.8179
No log 23.4286 492 0.6660 0.6605 0.6660 0.8161
No log 23.5238 494 0.6617 0.6993 0.6617 0.8135
No log 23.6190 496 0.6684 0.7024 0.6684 0.8175
No log 23.7143 498 0.6620 0.6878 0.6620 0.8136
0.384 23.8095 500 0.6620 0.6691 0.6620 0.8136
0.384 23.9048 502 0.6677 0.6626 0.6677 0.8171
0.384 24.0 504 0.6740 0.6417 0.6740 0.8210
0.384 24.0952 506 0.6891 0.6727 0.6891 0.8301
0.384 24.1905 508 0.7085 0.6465 0.7085 0.8417
0.384 24.2857 510 0.7276 0.6357 0.7276 0.8530
0.384 24.3810 512 0.7260 0.6379 0.7260 0.8520
0.384 24.4762 514 0.6891 0.6491 0.6891 0.8301
0.384 24.5714 516 0.6620 0.7096 0.6620 0.8136
0.384 24.6667 518 0.6635 0.7024 0.6635 0.8145
0.384 24.7619 520 0.6569 0.6990 0.6569 0.8105
0.384 24.8571 522 0.6761 0.6602 0.6761 0.8222
0.384 24.9524 524 0.6922 0.6693 0.6922 0.8320
0.384 25.0476 526 0.7261 0.6398 0.7261 0.8521
0.384 25.1429 528 0.7345 0.6330 0.7345 0.8570
0.384 25.2381 530 0.7138 0.6431 0.7138 0.8449
0.384 25.3333 532 0.6945 0.6384 0.6945 0.8334
0.384 25.4286 534 0.6754 0.6366 0.6754 0.8218

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 Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k4_task1_organization

Finetuned
(4204)
this model