ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k17_task3_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: 0.7336
  • Qwk: -0.1146
  • Mse: 0.7336
  • Rmse: 0.8565

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 0.0435 2 3.7057 -0.0154 3.7057 1.9250
No log 0.0870 4 1.9181 0.0737 1.9181 1.3850
No log 0.1304 6 1.3197 0.0312 1.3197 1.1488
No log 0.1739 8 0.7095 0.0374 0.7095 0.8423
No log 0.2174 10 0.6973 0.1021 0.6973 0.8350
No log 0.2609 12 1.5323 -0.0445 1.5323 1.2379
No log 0.3043 14 1.7362 -0.0241 1.7362 1.3177
No log 0.3478 16 1.1476 -0.0728 1.1476 1.0712
No log 0.3913 18 0.7230 -0.0035 0.7230 0.8503
No log 0.4348 20 0.7179 0.0 0.7179 0.8473
No log 0.4783 22 0.8163 -0.1715 0.8163 0.9035
No log 0.5217 24 0.7857 -0.0753 0.7857 0.8864
No log 0.5652 26 0.7166 0.0 0.7166 0.8465
No log 0.6087 28 0.7243 -0.0035 0.7243 0.8511
No log 0.6522 30 0.8613 0.0909 0.8613 0.9281
No log 0.6957 32 1.1099 -0.0101 1.1099 1.0535
No log 0.7391 34 1.0560 -0.0398 1.0560 1.0276
No log 0.7826 36 0.7792 -0.0240 0.7792 0.8827
No log 0.8261 38 0.7020 0.0 0.7020 0.8378
No log 0.8696 40 0.7245 0.0 0.7245 0.8512
No log 0.9130 42 0.8501 -0.0390 0.8501 0.9220
No log 0.9565 44 1.0699 -0.0247 1.0699 1.0343
No log 1.0 46 1.3654 0.0 1.3654 1.1685
No log 1.0435 48 1.4279 0.0 1.4279 1.1950
No log 1.0870 50 1.3720 -0.0247 1.3720 1.1713
No log 1.1304 52 1.1545 -0.0751 1.1545 1.0745
No log 1.1739 54 0.8559 -0.1246 0.8559 0.9252
No log 1.2174 56 0.7263 0.0460 0.7263 0.8522
No log 1.2609 58 0.7369 -0.0101 0.7369 0.8585
No log 1.3043 60 0.8727 -0.0812 0.8727 0.9342
No log 1.3478 62 1.0909 -0.1282 1.0909 1.0444
No log 1.3913 64 1.2436 -0.0457 1.2436 1.1152
No log 1.4348 66 1.3337 -0.0247 1.3337 1.1549
No log 1.4783 68 1.0739 -0.1015 1.0739 1.0363
No log 1.5217 70 0.8045 -0.1747 0.8045 0.8970
No log 1.5652 72 0.7404 0.0 0.7404 0.8605
No log 1.6087 74 0.7445 0.0 0.7445 0.8628
No log 1.6522 76 0.7826 0.0 0.7826 0.8846
No log 1.6957 78 0.8908 -0.2772 0.8908 0.9438
No log 1.7391 80 1.0485 -0.0490 1.0485 1.0240
No log 1.7826 82 1.0768 -0.0234 1.0768 1.0377
No log 1.8261 84 0.9434 -0.0084 0.9434 0.9713
No log 1.8696 86 0.8566 -0.1671 0.8566 0.9255
No log 1.9130 88 0.7976 -0.0264 0.7976 0.8931
No log 1.9565 90 0.7186 0.0 0.7186 0.8477
No log 2.0 92 0.7069 0.0 0.7069 0.8408
No log 2.0435 94 0.7180 -0.0069 0.7180 0.8474
No log 2.0870 96 0.8045 0.0588 0.8045 0.8969
No log 2.1304 98 0.7324 0.0296 0.7324 0.8558
No log 2.1739 100 0.6793 0.0 0.6793 0.8242
No log 2.2174 102 0.6993 0.0964 0.6993 0.8362
No log 2.2609 104 1.0235 -0.0218 1.0235 1.0117
No log 2.3043 106 0.8861 0.0316 0.8861 0.9413
No log 2.3478 108 0.6859 0.0 0.6859 0.8282
No log 2.3913 110 0.6912 0.0 0.6912 0.8314
No log 2.4348 112 0.6906 0.1021 0.6906 0.8310
No log 2.4783 114 0.6964 0.1021 0.6964 0.8345
No log 2.5217 116 0.6982 0.0506 0.6982 0.8356
No log 2.5652 118 0.7237 0.0 0.7237 0.8507
No log 2.6087 120 0.7936 0.0257 0.7936 0.8909
No log 2.6522 122 1.0248 -0.0845 1.0248 1.0123
No log 2.6957 124 0.8935 -0.0271 0.8935 0.9452
No log 2.7391 126 0.7921 0.0061 0.7921 0.8900
No log 2.7826 128 0.8038 -0.0428 0.8038 0.8965
No log 2.8261 130 0.8144 -0.0599 0.8144 0.9024
No log 2.8696 132 1.0764 -0.0583 1.0764 1.0375
No log 2.9130 134 1.0004 -0.0545 1.0004 1.0002
No log 2.9565 136 0.7963 -0.0062 0.7963 0.8923
No log 3.0 138 0.8009 0.0454 0.8009 0.8949
No log 3.0435 140 0.8334 -0.0118 0.8334 0.9129
No log 3.0870 142 0.8110 -0.0513 0.8110 0.9006
No log 3.1304 144 0.8164 0.0155 0.8164 0.9035
No log 3.1739 146 0.7879 -0.0541 0.7879 0.8876
No log 3.2174 148 0.9490 -0.0778 0.9490 0.9742
No log 3.2609 150 1.1859 -0.0855 1.1859 1.0890
No log 3.3043 152 0.8841 0.0146 0.8841 0.9403
No log 3.3478 154 0.7682 -0.0493 0.7682 0.8765
No log 3.3913 156 0.8255 -0.1917 0.8255 0.9086
No log 3.4348 158 0.7884 -0.1917 0.7884 0.8879
No log 3.4783 160 0.8940 -0.0686 0.8940 0.9455
No log 3.5217 162 1.2513 0.0095 1.2513 1.1186
No log 3.5652 164 1.2296 -0.0216 1.2296 1.1089
No log 3.6087 166 0.9814 0.0040 0.9814 0.9906
No log 3.6522 168 0.8013 -0.0595 0.8013 0.8952
No log 3.6957 170 0.7862 -0.1547 0.7862 0.8867
No log 3.7391 172 0.7888 -0.0385 0.7888 0.8882
No log 3.7826 174 0.8359 -0.0629 0.8359 0.9143
No log 3.8261 176 0.8584 -0.1126 0.8584 0.9265
No log 3.8696 178 0.7915 -0.1396 0.7915 0.8897
No log 3.9130 180 0.8237 -0.1606 0.8237 0.9076
No log 3.9565 182 0.8021 -0.1397 0.8021 0.8956
No log 4.0 184 0.9081 0.0909 0.9081 0.9529
No log 4.0435 186 1.0903 -0.0558 1.0903 1.0442
No log 4.0870 188 0.8715 0.0512 0.8715 0.9335
No log 4.1304 190 0.8019 -0.0648 0.8019 0.8955
No log 4.1739 192 0.9534 -0.0211 0.9534 0.9764
No log 4.2174 194 0.9160 -0.0262 0.9160 0.9571
No log 4.2609 196 0.7803 -0.0705 0.7803 0.8833
No log 4.3043 198 0.7823 0.0027 0.7823 0.8845
No log 4.3478 200 0.7891 -0.0237 0.7891 0.8883
No log 4.3913 202 0.8111 -0.0226 0.8111 0.9006
No log 4.4348 204 0.8657 -0.0989 0.8657 0.9304
No log 4.4783 206 0.8462 -0.0687 0.8462 0.9199
No log 4.5217 208 0.9225 0.0733 0.9225 0.9605
No log 4.5652 210 0.9277 0.0679 0.9277 0.9632
No log 4.6087 212 0.9202 -0.0015 0.9202 0.9593
No log 4.6522 214 1.1839 0.0868 1.1839 1.0881
No log 4.6957 216 1.1510 0.0874 1.1510 1.0728
No log 4.7391 218 0.8894 -0.0289 0.8894 0.9431
No log 4.7826 220 0.7669 0.1202 0.7669 0.8757
No log 4.8261 222 0.9318 0.0676 0.9318 0.9653
No log 4.8696 224 0.8337 0.0909 0.8337 0.9131
No log 4.9130 226 0.6858 0.0964 0.6858 0.8281
No log 4.9565 228 0.7061 0.0 0.7061 0.8403
No log 5.0 230 0.7036 0.0 0.7036 0.8388
No log 5.0435 232 0.7357 0.1259 0.7357 0.8577
No log 5.0870 234 0.8034 0.1047 0.8034 0.8963
No log 5.1304 236 0.7111 0.0857 0.7111 0.8432
No log 5.1739 238 0.7051 0.0555 0.7051 0.8397
No log 5.2174 240 0.7196 0.0 0.7196 0.8483
No log 5.2609 242 0.7402 0.0374 0.7402 0.8603
No log 5.3043 244 0.7575 0.1371 0.7575 0.8703
No log 5.3478 246 0.7486 0.0110 0.7486 0.8652
No log 5.3913 248 0.7973 -0.0508 0.7973 0.8929
No log 5.4348 250 0.7878 -0.0996 0.7878 0.8876
No log 5.4783 252 0.7717 0.0053 0.7717 0.8784
No log 5.5217 254 0.8774 0.0876 0.8774 0.9367
No log 5.5652 256 0.9531 0.0984 0.9531 0.9763
No log 5.6087 258 0.8209 0.1049 0.8209 0.9060
No log 5.6522 260 0.8049 -0.0208 0.8049 0.8972
No log 5.6957 262 0.8550 -0.0761 0.8550 0.9247
No log 5.7391 264 0.8281 -0.0711 0.8281 0.9100
No log 5.7826 266 0.8300 0.0344 0.8300 0.9110
No log 5.8261 268 0.8422 -0.0602 0.8422 0.9177
No log 5.8696 270 0.8303 -0.1597 0.8303 0.9112
No log 5.9130 272 0.8255 -0.0762 0.8255 0.9086
No log 5.9565 274 0.8153 -0.0879 0.8153 0.9029
No log 6.0 276 0.8250 -0.0076 0.8250 0.9083
No log 6.0435 278 0.8910 -0.0618 0.8910 0.9439
No log 6.0870 280 0.8550 0.0 0.8550 0.9246
No log 6.1304 282 0.8895 -0.0334 0.8895 0.9431
No log 6.1739 284 1.0003 -0.0120 1.0003 1.0001
No log 6.2174 286 1.0260 0.0566 1.0260 1.0129
No log 6.2609 288 0.9576 0.0502 0.9576 0.9786
No log 6.3043 290 0.9187 0.0022 0.9187 0.9585
No log 6.3478 292 1.0081 -0.1202 1.0081 1.0040
No log 6.3913 294 0.8859 -0.0343 0.8859 0.9412
No log 6.4348 296 0.8547 -0.1039 0.8547 0.9245
No log 6.4783 298 0.8739 -0.0361 0.8739 0.9349
No log 6.5217 300 0.9266 0.0062 0.9266 0.9626
No log 6.5652 302 0.9328 -0.0345 0.9328 0.9658
No log 6.6087 304 0.8356 0.0437 0.8356 0.9141
No log 6.6522 306 0.8242 -0.0288 0.8242 0.9078
No log 6.6957 308 0.8197 0.0330 0.8197 0.9054
No log 6.7391 310 0.8007 -0.0025 0.8007 0.8948
No log 6.7826 312 0.7831 -0.1166 0.7831 0.8849
No log 6.8261 314 0.7757 0.0783 0.7757 0.8807
No log 6.8696 316 0.7454 0.0783 0.7454 0.8634
No log 6.9130 318 0.7241 0.0783 0.7241 0.8510
No log 6.9565 320 0.7201 0.1249 0.7201 0.8486
No log 7.0 322 0.7123 0.0513 0.7123 0.8440
No log 7.0435 324 0.7418 -0.1266 0.7418 0.8613
No log 7.0870 326 0.7666 -0.0259 0.7666 0.8756
No log 7.1304 328 0.8028 -0.0138 0.8028 0.8960
No log 7.1739 330 0.7805 -0.0288 0.7805 0.8835
No log 7.2174 332 0.7841 0.1144 0.7841 0.8855
No log 7.2609 334 0.7970 0.1095 0.7970 0.8928
No log 7.3043 336 0.7719 0.1585 0.7719 0.8786
No log 7.3478 338 0.7783 -0.0717 0.7783 0.8822
No log 7.3913 340 0.7526 0.1761 0.7526 0.8676
No log 7.4348 342 0.7429 0.1660 0.7429 0.8619
No log 7.4783 344 0.7754 0.2570 0.7754 0.8806
No log 7.5217 346 0.7669 0.2024 0.7669 0.8758
No log 7.5652 348 0.7920 -0.0228 0.7920 0.8900
No log 7.6087 350 0.7919 -0.0228 0.7919 0.8899
No log 7.6522 352 0.7639 0.1962 0.7639 0.8740
No log 7.6957 354 0.7325 0.1561 0.7325 0.8559
No log 7.7391 356 0.7231 0.0155 0.7231 0.8504
No log 7.7826 358 0.7023 0.1722 0.7023 0.8381
No log 7.8261 360 0.7334 0.1506 0.7334 0.8564
No log 7.8696 362 0.7199 0.1644 0.7199 0.8485
No log 7.9130 364 0.7296 0.1244 0.7296 0.8542
No log 7.9565 366 0.7381 0.1244 0.7381 0.8591
No log 8.0 368 0.7381 0.0840 0.7381 0.8591
No log 8.0435 370 0.7528 0.1604 0.7528 0.8676
No log 8.0870 372 0.7467 0.1660 0.7467 0.8641
No log 8.1304 374 0.7502 0.0570 0.7502 0.8662
No log 8.1739 376 0.7682 -0.0280 0.7682 0.8765
No log 8.2174 378 0.7775 -0.1535 0.7775 0.8817
No log 8.2609 380 0.7178 0.1904 0.7178 0.8473
No log 8.3043 382 0.8027 0.0826 0.8027 0.8959
No log 8.3478 384 0.8654 0.1024 0.8654 0.9303
No log 8.3913 386 0.7578 0.1565 0.7578 0.8705
No log 8.4348 388 0.7222 0.1860 0.7222 0.8498
No log 8.4783 390 0.7845 -0.0181 0.7845 0.8857
No log 8.5217 392 0.7676 -0.0204 0.7676 0.8761
No log 8.5652 394 0.7278 0.0116 0.7278 0.8531
No log 8.6087 396 0.7347 0.1722 0.7347 0.8572
No log 8.6522 398 0.7257 0.1952 0.7257 0.8519
No log 8.6957 400 0.7216 -0.0385 0.7216 0.8494
No log 8.7391 402 0.7477 -0.0307 0.7477 0.8647
No log 8.7826 404 0.7635 0.0 0.7635 0.8738
No log 8.8261 406 0.8532 0.0670 0.8532 0.9237
No log 8.8696 408 0.8773 0.0670 0.8773 0.9367
No log 8.9130 410 0.8077 -0.0320 0.8077 0.8987
No log 8.9565 412 0.8290 0.0268 0.8290 0.9105
No log 9.0 414 0.8196 0.0702 0.8196 0.9053
No log 9.0435 416 0.7655 0.0106 0.7655 0.8749
No log 9.0870 418 0.7918 0.1431 0.7918 0.8899
No log 9.1304 420 0.7855 0.1440 0.7855 0.8863
No log 9.1739 422 0.8170 0.1387 0.8170 0.9039
No log 9.2174 424 0.7782 0.1440 0.7782 0.8821
No log 9.2609 426 0.7654 0.0834 0.7654 0.8749
No log 9.3043 428 0.7693 -0.0334 0.7693 0.8771
No log 9.3478 430 0.7716 0.0172 0.7716 0.8784
No log 9.3913 432 0.7636 0.1744 0.7636 0.8739
No log 9.4348 434 0.7492 0.0944 0.7492 0.8656
No log 9.4783 436 0.7386 0.0558 0.7386 0.8594
No log 9.5217 438 0.7077 0.1340 0.7077 0.8412
No log 9.5652 440 0.7045 0.1928 0.7045 0.8393
No log 9.6087 442 0.6879 0.1659 0.6879 0.8294
No log 9.6522 444 0.7237 0.1485 0.7237 0.8507
No log 9.6957 446 0.6998 0.2195 0.6998 0.8365
No log 9.7391 448 0.6967 0.1787 0.6967 0.8347
No log 9.7826 450 0.7080 0.1486 0.7080 0.8414
No log 9.8261 452 0.7140 0.1856 0.7140 0.8450
No log 9.8696 454 0.7334 0.1659 0.7334 0.8564
No log 9.9130 456 0.7627 0.1485 0.7627 0.8733
No log 9.9565 458 0.7817 0.0717 0.7817 0.8841
No log 10.0 460 0.8065 0.1094 0.8065 0.8980
No log 10.0435 462 0.7996 0.1529 0.7996 0.8942
No log 10.0870 464 0.7802 0.1962 0.7802 0.8833
No log 10.1304 466 0.7726 0.2327 0.7726 0.8790
No log 10.1739 468 0.7438 0.2087 0.7438 0.8624
No log 10.2174 470 0.7329 0.2096 0.7329 0.8561
No log 10.2609 472 0.7203 0.2166 0.7203 0.8487
No log 10.3043 474 0.7161 0.1815 0.7161 0.8462
No log 10.3478 476 0.7258 0.0085 0.7258 0.8519
No log 10.3913 478 0.7008 0.1413 0.7008 0.8371
No log 10.4348 480 0.7168 0.1722 0.7168 0.8466
No log 10.4783 482 0.7073 0.1787 0.7073 0.8410
No log 10.5217 484 0.7149 0.0570 0.7149 0.8455
No log 10.5652 486 0.7518 0.0218 0.7518 0.8671
No log 10.6087 488 0.8472 -0.0016 0.8472 0.9205
No log 10.6522 490 0.8147 -0.0173 0.8147 0.9026
No log 10.6957 492 0.7229 0.0976 0.7229 0.8503
No log 10.7391 494 0.7880 0.1336 0.7880 0.8877
No log 10.7826 496 0.8278 0.0748 0.8278 0.9098
No log 10.8261 498 0.7181 0.2507 0.7181 0.8474
0.3673 10.8696 500 0.7183 0.1538 0.7183 0.8475
0.3673 10.9130 502 0.7794 -0.0237 0.7794 0.8828
0.3673 10.9565 504 0.7791 -0.0237 0.7791 0.8827
0.3673 11.0 506 0.7049 0.1474 0.7049 0.8396
0.3673 11.0435 508 0.6971 0.1705 0.6971 0.8349
0.3673 11.0870 510 0.6956 0.1904 0.6956 0.8341
0.3673 11.1304 512 0.7101 0.1395 0.7101 0.8426
0.3673 11.1739 514 0.7500 0.0165 0.7500 0.8660
0.3673 11.2174 516 0.8358 0.0007 0.8358 0.9142
0.3673 11.2609 518 0.7910 -0.0771 0.7910 0.8894
0.3673 11.3043 520 0.7336 -0.1146 0.7336 0.8565

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
0
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/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k17_task3_organization

Finetuned
(2729)
this model