ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k7_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: 1.1710
  • Qwk: -0.0657
  • Mse: 1.1710
  • Rmse: 1.0821

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 0.1111 2 3.6718 -0.0058 3.6718 1.9162
No log 0.2222 4 1.8808 0.0772 1.8808 1.3714
No log 0.3333 6 1.2668 0.0 1.2668 1.1255
No log 0.4444 8 1.0847 0.0156 1.0847 1.0415
No log 0.5556 10 1.0538 0.0196 1.0538 1.0265
No log 0.6667 12 1.1573 -0.0164 1.1573 1.0758
No log 0.7778 14 0.9274 0.0741 0.9274 0.9630
No log 0.8889 16 0.9163 0.1223 0.9163 0.9573
No log 1.0 18 0.8260 0.0826 0.8260 0.9088
No log 1.1111 20 0.9122 -0.0049 0.9122 0.9551
No log 1.2222 22 0.9395 -0.0067 0.9395 0.9693
No log 1.3333 24 1.0843 -0.0435 1.0843 1.0413
No log 1.4444 26 1.2016 0.0083 1.2016 1.0962
No log 1.5556 28 0.9426 -0.0031 0.9426 0.9709
No log 1.6667 30 0.9249 -0.0253 0.9249 0.9617
No log 1.7778 32 0.8447 -0.1708 0.8447 0.9191
No log 1.8889 34 1.1750 -0.0959 1.1750 1.0840
No log 2.0 36 1.4500 -0.1001 1.4500 1.2042
No log 2.1111 38 1.0734 -0.0606 1.0734 1.0361
No log 2.2222 40 0.8806 -0.1255 0.8806 0.9384
No log 2.3333 42 0.9653 -0.0894 0.9653 0.9825
No log 2.4444 44 1.3855 -0.0457 1.3855 1.1771
No log 2.5556 46 1.2154 0.0217 1.2154 1.1025
No log 2.6667 48 0.7730 0.0334 0.7730 0.8792
No log 2.7778 50 0.7501 -0.0101 0.7501 0.8661
No log 2.8889 52 0.8079 -0.1249 0.8079 0.8988
No log 3.0 54 0.9440 -0.0200 0.9440 0.9716
No log 3.1111 56 0.9082 -0.0490 0.9082 0.9530
No log 3.2222 58 0.8204 -0.0309 0.8204 0.9058
No log 3.3333 60 0.7438 -0.0101 0.7438 0.8624
No log 3.4444 62 0.8074 0.0225 0.8074 0.8985
No log 3.5556 64 0.8668 0.0129 0.8668 0.9310
No log 3.6667 66 0.7812 -0.0609 0.7812 0.8839
No log 3.7778 68 0.7916 -0.0571 0.7916 0.8897
No log 3.8889 70 0.8934 -0.0743 0.8934 0.9452
No log 4.0 72 1.1863 -0.1273 1.1863 1.0892
No log 4.1111 74 0.9675 -0.0852 0.9675 0.9836
No log 4.2222 76 0.7714 -0.0096 0.7714 0.8783
No log 4.3333 78 0.8442 -0.1201 0.8442 0.9188
No log 4.4444 80 0.8042 -0.0427 0.8042 0.8968
No log 4.5556 82 0.9901 -0.0862 0.9901 0.9950
No log 4.6667 84 1.4230 -0.0720 1.4230 1.1929
No log 4.7778 86 1.8135 -0.0479 1.8135 1.3467
No log 4.8889 88 1.4953 -0.0974 1.4953 1.2228
No log 5.0 90 1.0469 -0.1096 1.0469 1.0232
No log 5.1111 92 0.8440 -0.0798 0.8440 0.9187
No log 5.2222 94 0.8874 -0.0904 0.8874 0.9420
No log 5.3333 96 0.8461 0.0027 0.8461 0.9198
No log 5.4444 98 1.1364 -0.0513 1.1364 1.0660
No log 5.5556 100 1.4344 -0.0638 1.4344 1.1977
No log 5.6667 102 1.0465 -0.0870 1.0465 1.0230
No log 5.7778 104 0.8216 0.0247 0.8216 0.9064
No log 5.8889 106 0.9235 -0.1209 0.9235 0.9610
No log 6.0 108 1.1482 -0.0211 1.1482 1.0715
No log 6.1111 110 0.9227 -0.0746 0.9227 0.9606
No log 6.2222 112 0.9884 -0.0809 0.9884 0.9942
No log 6.3333 114 1.3489 -0.1569 1.3489 1.1614
No log 6.4444 116 1.1525 -0.0468 1.1525 1.0735
No log 6.5556 118 1.0614 0.0320 1.0614 1.0303
No log 6.6667 120 0.9239 0.0880 0.9239 0.9612
No log 6.7778 122 0.8989 0.0586 0.8989 0.9481
No log 6.8889 124 1.0457 -0.1131 1.0457 1.0226
No log 7.0 126 0.9106 0.0087 0.9106 0.9543
No log 7.1111 128 0.9947 -0.1134 0.9947 0.9974
No log 7.2222 130 1.0287 -0.1872 1.0287 1.0142
No log 7.3333 132 1.1728 -0.1566 1.1728 1.0830
No log 7.4444 134 0.9724 -0.1597 0.9724 0.9861
No log 7.5556 136 0.8400 0.0821 0.8400 0.9165
No log 7.6667 138 0.8438 0.0282 0.8438 0.9186
No log 7.7778 140 1.0943 -0.1234 1.0943 1.0461
No log 7.8889 142 0.8966 0.0525 0.8966 0.9469
No log 8.0 144 0.8192 -0.1266 0.8192 0.9051
No log 8.1111 146 0.8232 -0.1204 0.8232 0.9073
No log 8.2222 148 0.9653 -0.0076 0.9653 0.9825
No log 8.3333 150 1.2888 -0.0925 1.2888 1.1353
No log 8.4444 152 0.9583 -0.0309 0.9583 0.9789
No log 8.5556 154 0.8990 -0.1354 0.8990 0.9481
No log 8.6667 156 0.8640 -0.1597 0.8640 0.9295
No log 8.7778 158 0.9181 0.0062 0.9181 0.9582
No log 8.8889 160 0.9457 -0.0008 0.9457 0.9725
No log 9.0 162 0.9850 0.0526 0.9850 0.9925
No log 9.1111 164 0.7959 0.0282 0.7959 0.8922
No log 9.2222 166 0.7595 -0.0541 0.7595 0.8715
No log 9.3333 168 0.7589 -0.0062 0.7589 0.8712
No log 9.4444 170 0.8804 0.0016 0.8804 0.9383
No log 9.5556 172 0.9448 -0.0828 0.9448 0.9720
No log 9.6667 174 0.8619 -0.0056 0.8619 0.9284
No log 9.7778 176 0.8889 -0.1354 0.8889 0.9428
No log 9.8889 178 0.8920 0.0934 0.8920 0.9445
No log 10.0 180 0.9164 -0.0573 0.9164 0.9573
No log 10.1111 182 0.9884 -0.1155 0.9884 0.9942
No log 10.2222 184 1.2380 -0.2215 1.2380 1.1126
No log 10.3333 186 1.0121 -0.1597 1.0121 1.0060
No log 10.4444 188 0.8271 0.0375 0.8271 0.9095
No log 10.5556 190 0.8297 0.0375 0.8297 0.9109
No log 10.6667 192 0.9319 -0.0767 0.9319 0.9654
No log 10.7778 194 0.9338 -0.0767 0.9338 0.9664
No log 10.8889 196 0.8575 -0.0195 0.8575 0.9260
No log 11.0 198 0.8679 -0.0228 0.8679 0.9316
No log 11.1111 200 0.8881 -0.0295 0.8881 0.9424
No log 11.2222 202 0.8520 -0.0145 0.8520 0.9231
No log 11.3333 204 0.9305 -0.0778 0.9305 0.9646
No log 11.4444 206 0.9416 -0.0797 0.9416 0.9703
No log 11.5556 208 0.9543 -0.0471 0.9543 0.9769
No log 11.6667 210 0.8992 -0.0441 0.8992 0.9483
No log 11.7778 212 0.8163 0.0247 0.8163 0.9035
No log 11.8889 214 0.7953 -0.0560 0.7953 0.8918
No log 12.0 216 0.8180 -0.0145 0.8180 0.9044
No log 12.1111 218 0.9102 -0.0409 0.9102 0.9540
No log 12.2222 220 1.1126 -0.1555 1.1126 1.0548
No log 12.3333 222 0.9348 -0.0797 0.9348 0.9669
No log 12.4444 224 0.8028 0.1354 0.8028 0.8960
No log 12.5556 226 0.7978 0.0828 0.7978 0.8932
No log 12.6667 228 0.8678 -0.0355 0.8678 0.9316
No log 12.7778 230 0.9872 -0.1572 0.9872 0.9936
No log 12.8889 232 0.8542 0.0152 0.8542 0.9242
No log 13.0 234 0.7808 0.0030 0.7808 0.8836
No log 13.1111 236 0.8283 -0.0798 0.8283 0.9101
No log 13.2222 238 0.8026 -0.0427 0.8026 0.8959
No log 13.3333 240 0.8207 0.0338 0.8207 0.9059
No log 13.4444 242 0.8972 0.0016 0.8972 0.9472
No log 13.5556 244 0.9568 -0.0031 0.9568 0.9782
No log 13.6667 246 0.8912 -0.0322 0.8912 0.9441
No log 13.7778 248 0.8499 -0.0240 0.8499 0.9219
No log 13.8889 250 0.9085 -0.0008 0.9085 0.9531
No log 14.0 252 0.9350 -0.0828 0.9350 0.9669
No log 14.1111 254 0.9795 -0.0526 0.9795 0.9897
No log 14.2222 256 1.0152 -0.0885 1.0152 1.0076
No log 14.3333 258 1.0262 -0.0526 1.0262 1.0130
No log 14.4444 260 0.8452 -0.1197 0.8452 0.9194
No log 14.5556 262 0.8342 -0.0427 0.8342 0.9133
No log 14.6667 264 0.9020 -0.0798 0.9020 0.9498
No log 14.7778 266 0.8527 -0.0902 0.8527 0.9234
No log 14.8889 268 0.8425 -0.1191 0.8425 0.9179
No log 15.0 270 1.0635 -0.0937 1.0635 1.0313
No log 15.1111 272 1.0107 -0.1238 1.0107 1.0053
No log 15.2222 274 0.8614 0.0236 0.8614 0.9281
No log 15.3333 276 0.8548 -0.1040 0.8548 0.9245
No log 15.4444 278 0.9224 0.0538 0.9224 0.9604
No log 15.5556 280 1.0166 -0.1178 1.0166 1.0083
No log 15.6667 282 0.9753 0.0091 0.9753 0.9876
No log 15.7778 284 0.9579 0.0134 0.9579 0.9787
No log 15.8889 286 0.9207 0.0097 0.9207 0.9595
No log 16.0 288 0.9659 -0.0440 0.9659 0.9828
No log 16.1111 290 0.9066 0.0441 0.9066 0.9521
No log 16.2222 292 0.8916 0.0135 0.8916 0.9443
No log 16.3333 294 0.8529 -0.0449 0.8529 0.9236
No log 16.4444 296 0.8192 0.0031 0.8192 0.9051
No log 16.5556 298 0.7957 0.0375 0.7957 0.8920
No log 16.6667 300 0.8357 -0.0316 0.8357 0.9142
No log 16.7778 302 0.8311 -0.0283 0.8311 0.9117
No log 16.8889 304 0.8122 -0.0283 0.8122 0.9012
No log 17.0 306 0.7804 -0.0032 0.7804 0.8834
No log 17.1111 308 0.7762 0.0 0.7762 0.8810
No log 17.2222 310 0.7877 0.0318 0.7877 0.8875
No log 17.3333 312 0.8531 0.0068 0.8531 0.9236
No log 17.4444 314 0.8341 -0.0316 0.8341 0.9133
No log 17.5556 316 0.7828 -0.0520 0.7828 0.8848
No log 17.6667 318 0.8102 -0.1010 0.8102 0.9001
No log 17.7778 320 0.7886 -0.0520 0.7886 0.8880
No log 17.8889 322 0.7909 -0.0644 0.7909 0.8893
No log 18.0 324 0.7975 -0.0644 0.7975 0.8930
No log 18.1111 326 0.7938 -0.0152 0.7938 0.8910
No log 18.2222 328 0.8014 -0.0152 0.8014 0.8952
No log 18.3333 330 0.8230 0.0282 0.8230 0.9072
No log 18.4444 332 0.8346 -0.0295 0.8346 0.9136
No log 18.5556 334 0.8527 -0.0778 0.8527 0.9234
No log 18.6667 336 0.8242 -0.0690 0.8242 0.9079
No log 18.7778 338 0.8473 -0.1010 0.8473 0.9205
No log 18.8889 340 0.8634 -0.1745 0.8634 0.9292
No log 19.0 342 0.8235 -0.0179 0.8235 0.9075
No log 19.1111 344 0.9182 -0.0373 0.9182 0.9582
No log 19.2222 346 1.0634 -0.1240 1.0634 1.0312
No log 19.3333 348 1.0013 -0.0194 1.0013 1.0007
No log 19.4444 350 0.8296 0.0183 0.8296 0.9108
No log 19.5556 352 0.8004 -0.0704 0.8004 0.8946
No log 19.6667 354 0.7850 -0.0252 0.7850 0.8860
No log 19.7778 356 0.7616 -0.0252 0.7616 0.8727
No log 19.8889 358 0.7404 -0.0062 0.7404 0.8605
No log 20.0 360 0.7938 -0.0366 0.7938 0.8910
No log 20.1111 362 0.7524 -0.0065 0.7524 0.8674
No log 20.2222 364 0.8196 -0.0391 0.8196 0.9053
No log 20.3333 366 1.0834 -0.0048 1.0834 1.0408
No log 20.4444 368 1.1498 -0.0684 1.1498 1.0723
No log 20.5556 370 0.9671 -0.0563 0.9671 0.9834
No log 20.6667 372 0.7877 -0.0228 0.7877 0.8875
No log 20.7778 374 0.7762 0.0496 0.7762 0.8810
No log 20.8889 376 0.8113 0.0110 0.8113 0.9007
No log 21.0 378 0.7628 -0.0427 0.7628 0.8734
No log 21.1111 380 0.7624 -0.0675 0.7624 0.8732
No log 21.2222 382 0.7674 -0.0152 0.7674 0.8760
No log 21.3333 384 0.7687 -0.0152 0.7687 0.8768
No log 21.4444 386 0.7785 0.0814 0.7785 0.8823
No log 21.5556 388 0.7942 0.0282 0.7942 0.8912
No log 21.6667 390 0.8566 0.0123 0.8566 0.9255
No log 21.7778 392 0.8671 -0.0355 0.8671 0.9312
No log 21.8889 394 0.8346 -0.0295 0.8346 0.9136
No log 22.0 396 0.8137 -0.0274 0.8137 0.9020
No log 22.1111 398 0.7992 -0.0704 0.7992 0.8940
No log 22.2222 400 0.8825 -0.0441 0.8825 0.9394
No log 22.3333 402 0.8937 -0.0441 0.8937 0.9454
No log 22.4444 404 0.8143 0.0152 0.8143 0.9024
No log 22.5556 406 0.7625 0.0814 0.7625 0.8732
No log 22.6667 408 0.7777 0.0814 0.7777 0.8819
No log 22.7778 410 0.8096 -0.0274 0.8096 0.8998
No log 22.8889 412 0.8050 0.0282 0.8050 0.8972
No log 23.0 414 0.7991 -0.0086 0.7991 0.8940
No log 23.1111 416 0.7910 -0.0091 0.7910 0.8894
No log 23.2222 418 0.7981 -0.0550 0.7981 0.8934
No log 23.3333 420 0.8414 -0.0614 0.8414 0.9173
No log 23.4444 422 0.8388 -0.0614 0.8388 0.9159
No log 23.5556 424 0.8677 -0.0252 0.8677 0.9315
No log 23.6667 426 0.8774 0.0095 0.8774 0.9367
No log 23.7778 428 0.8410 -0.0252 0.8410 0.9171
No log 23.8889 430 0.8447 -0.0274 0.8447 0.9191
No log 24.0 432 0.8447 0.0123 0.8447 0.9191
No log 24.1111 434 0.8822 0.0755 0.8822 0.9392
No log 24.2222 436 0.8988 -0.0486 0.8988 0.9480
No log 24.3333 438 0.8589 -0.0408 0.8589 0.9268
No log 24.4444 440 0.8297 -0.0295 0.8297 0.9109
No log 24.5556 442 0.8545 -0.0408 0.8545 0.9244
No log 24.6667 444 0.9634 -0.0539 0.9634 0.9815
No log 24.7778 446 1.0280 -0.0912 1.0280 1.0139
No log 24.8889 448 0.9308 0.0277 0.9308 0.9648
No log 25.0 450 0.8240 0.0152 0.8240 0.9077
No log 25.1111 452 0.7926 0.0821 0.7926 0.8903
No log 25.2222 454 0.7937 0.0821 0.7937 0.8909
No log 25.3333 456 0.8281 -0.0767 0.8281 0.9100
No log 25.4444 458 0.9407 0.0618 0.9407 0.9699
No log 25.5556 460 0.9438 0.0224 0.9438 0.9715
No log 25.6667 462 0.9370 -0.0157 0.9370 0.9680
No log 25.7778 464 0.8798 -0.0425 0.8798 0.9380
No log 25.8889 466 0.8287 0.0214 0.8287 0.9104
No log 26.0 468 0.8101 0.0303 0.8101 0.9001
No log 26.1111 470 0.8111 0.0236 0.8111 0.9006
No log 26.2222 472 0.8120 -0.0274 0.8120 0.9011
No log 26.3333 474 0.8419 -0.0391 0.8419 0.9175
No log 26.4444 476 0.8684 0.0618 0.8684 0.9319
No log 26.5556 478 0.8813 0.0587 0.8813 0.9388
No log 26.6667 480 0.8222 0.0651 0.8222 0.9068
No log 26.7778 482 0.7547 -0.0718 0.7547 0.8687
No log 26.8889 484 0.7508 -0.0125 0.7508 0.8665
No log 27.0 486 0.7629 -0.0125 0.7629 0.8734
No log 27.1111 488 0.8000 -0.0152 0.8000 0.8945
No log 27.2222 490 0.8833 -0.0778 0.8833 0.9398
No log 27.3333 492 0.8822 -0.0391 0.8822 0.9392
No log 27.4444 494 0.7887 -0.0179 0.7887 0.8881
No log 27.5556 496 0.7753 0.0513 0.7753 0.8805
No log 27.6667 498 0.8695 0.1126 0.8695 0.9325
0.2357 27.7778 500 0.8369 0.0229 0.8369 0.9148
0.2357 27.8889 502 0.7786 -0.0690 0.7786 0.8824
0.2357 28.0 504 0.8861 0.0250 0.8861 0.9413
0.2357 28.1111 506 1.0092 0.1042 1.0092 1.0046
0.2357 28.2222 508 0.9024 0.0250 0.9024 0.9500
0.2357 28.3333 510 0.7882 -0.1194 0.7882 0.8878
0.2357 28.4444 512 0.7903 0.0973 0.7903 0.8890
0.2357 28.5556 514 0.7915 0.0454 0.7915 0.8897
0.2357 28.6667 516 0.8022 -0.1121 0.8022 0.8957
0.2357 28.7778 518 0.8565 -0.0322 0.8565 0.9255
0.2357 28.8889 520 0.9470 -0.0513 0.9470 0.9731
0.2357 29.0 522 1.0479 -0.1248 1.0479 1.0237
0.2357 29.1111 524 1.1710 -0.0657 1.1710 1.0821

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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/ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k7_task3_organization

Finetuned
(4019)
this model