ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k16_task7_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: 0.6515
  • Qwk: 0.3615
  • Mse: 0.6515
  • Rmse: 0.8071

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 0.0488 2 2.4244 -0.0646 2.4244 1.5570
No log 0.0976 4 1.0756 0.1941 1.0756 1.0371
No log 0.1463 6 0.9139 -0.1462 0.9139 0.9560
No log 0.1951 8 0.8039 0.1184 0.8039 0.8966
No log 0.2439 10 0.7619 0.1184 0.7619 0.8729
No log 0.2927 12 0.7183 0.0481 0.7183 0.8475
No log 0.3415 14 0.7614 0.0937 0.7614 0.8726
No log 0.3902 16 0.7980 0.1372 0.7980 0.8933
No log 0.4390 18 0.9443 0.2381 0.9443 0.9717
No log 0.4878 20 0.8694 0.2526 0.8694 0.9324
No log 0.5366 22 0.7240 0.0481 0.7240 0.8509
No log 0.5854 24 0.7275 0.1561 0.7275 0.8529
No log 0.6341 26 0.8879 0.1822 0.8879 0.9423
No log 0.6829 28 1.0007 0.0338 1.0007 1.0003
No log 0.7317 30 1.1734 -0.2407 1.1734 1.0833
No log 0.7805 32 1.2328 -0.2346 1.2328 1.1103
No log 0.8293 34 1.0013 0.0 1.0013 1.0006
No log 0.8780 36 0.8515 0.0 0.8515 0.9227
No log 0.9268 38 0.7939 0.0295 0.7939 0.8910
No log 0.9756 40 0.7659 0.0798 0.7659 0.8751
No log 1.0244 42 0.7480 0.0840 0.7480 0.8649
No log 1.0732 44 0.7429 0.0840 0.7429 0.8619
No log 1.1220 46 0.7236 0.2046 0.7236 0.8506
No log 1.1707 48 0.7094 0.2046 0.7094 0.8423
No log 1.2195 50 0.7057 0.1184 0.7057 0.8401
No log 1.2683 52 0.6879 0.1184 0.6879 0.8294
No log 1.3171 54 0.6804 0.1184 0.6804 0.8249
No log 1.3659 56 0.6690 0.2467 0.6690 0.8179
No log 1.4146 58 0.7436 0.2726 0.7436 0.8623
No log 1.4634 60 0.8259 0.3231 0.8259 0.9088
No log 1.5122 62 0.8955 0.3347 0.8955 0.9463
No log 1.5610 64 0.8647 0.3169 0.8647 0.9299
No log 1.6098 66 0.7623 0.2632 0.7623 0.8731
No log 1.6585 68 0.6864 0.1972 0.6864 0.8285
No log 1.7073 70 0.6656 0.1699 0.6656 0.8158
No log 1.7561 72 0.7241 0.1918 0.7241 0.8509
No log 1.8049 74 0.8622 0.1672 0.8622 0.9285
No log 1.8537 76 0.7737 0.2227 0.7737 0.8796
No log 1.9024 78 0.7345 0.1264 0.7345 0.8570
No log 1.9512 80 0.6902 0.2360 0.6902 0.8308
No log 2.0 82 0.8190 0.3313 0.8190 0.9050
No log 2.0488 84 0.9237 0.3579 0.9237 0.9611
No log 2.0976 86 0.8017 0.2984 0.8017 0.8954
No log 2.1463 88 0.6763 0.3738 0.6763 0.8224
No log 2.1951 90 0.8838 0.3347 0.8838 0.9401
No log 2.2439 92 1.0225 0.3264 1.0225 1.0112
No log 2.2927 94 0.9398 0.3890 0.9398 0.9694
No log 2.3415 96 0.7722 0.3869 0.7722 0.8788
No log 2.3902 98 0.6839 0.2862 0.6839 0.8270
No log 2.4390 100 0.7836 0.3252 0.7836 0.8852
No log 2.4878 102 0.8038 0.3570 0.8038 0.8966
No log 2.5366 104 0.7556 0.3214 0.7556 0.8692
No log 2.5854 106 0.6975 0.3022 0.6975 0.8352
No log 2.6341 108 0.6642 0.2379 0.6642 0.8150
No log 2.6829 110 0.6692 0.3050 0.6692 0.8181
No log 2.7317 112 0.6893 0.3545 0.6893 0.8303
No log 2.7805 114 0.7829 0.3918 0.7829 0.8848
No log 2.8293 116 0.8136 0.3060 0.8136 0.9020
No log 2.8780 118 0.7680 0.2784 0.7680 0.8764
No log 2.9268 120 0.7706 0.2558 0.7706 0.8778
No log 2.9756 122 0.8606 0.1727 0.8606 0.9277
No log 3.0244 124 0.9596 0.1175 0.9596 0.9796
No log 3.0732 126 0.9432 0.2239 0.9432 0.9712
No log 3.1220 128 0.8969 0.2728 0.8969 0.9471
No log 3.1707 130 0.8468 0.3193 0.8468 0.9202
No log 3.2195 132 0.7677 0.3333 0.7677 0.8762
No log 3.2683 134 0.7596 0.3126 0.7596 0.8715
No log 3.3171 136 0.8474 0.2154 0.8474 0.9205
No log 3.3659 138 0.8244 0.1538 0.8244 0.9080
No log 3.4146 140 0.7457 0.2688 0.7457 0.8635
No log 3.4634 142 0.7145 0.3285 0.7145 0.8453
No log 3.5122 144 0.7455 0.2095 0.7455 0.8634
No log 3.5610 146 0.7666 0.2508 0.7666 0.8755
No log 3.6098 148 0.7629 0.2777 0.7629 0.8735
No log 3.6585 150 0.7654 0.2551 0.7654 0.8749
No log 3.7073 152 0.8009 0.2835 0.8009 0.8949
No log 3.7561 154 0.8634 0.3379 0.8634 0.9292
No log 3.8049 156 0.9018 0.3699 0.9018 0.9496
No log 3.8537 158 0.8793 0.3483 0.8793 0.9377
No log 3.9024 160 0.7911 0.3329 0.7911 0.8895
No log 3.9512 162 0.7803 0.3441 0.7803 0.8833
No log 4.0 164 0.7694 0.3299 0.7694 0.8771
No log 4.0488 166 0.7624 0.3209 0.7624 0.8732
No log 4.0976 168 0.7677 0.4329 0.7677 0.8762
No log 4.1463 170 0.8859 0.4080 0.8859 0.9412
No log 4.1951 172 0.9018 0.4080 0.9018 0.9496
No log 4.2439 174 0.7601 0.4624 0.7601 0.8718
No log 4.2927 176 0.6608 0.2813 0.6608 0.8129
No log 4.3415 178 0.6491 0.2872 0.6491 0.8057
No log 4.3902 180 0.6506 0.3088 0.6506 0.8066
No log 4.4390 182 0.6944 0.4350 0.6944 0.8333
No log 4.4878 184 0.6854 0.4112 0.6854 0.8279
No log 4.5366 186 0.7309 0.4880 0.7309 0.8550
No log 4.5854 188 0.7611 0.4947 0.7611 0.8724
No log 4.6341 190 0.7278 0.4741 0.7278 0.8531
No log 4.6829 192 0.7385 0.4531 0.7385 0.8594
No log 4.7317 194 0.7225 0.4239 0.7225 0.8500
No log 4.7805 196 0.7018 0.4315 0.7018 0.8378
No log 4.8293 198 0.6874 0.4513 0.6874 0.8291
No log 4.8780 200 0.6832 0.3996 0.6832 0.8266
No log 4.9268 202 0.6483 0.3865 0.6483 0.8052
No log 4.9756 204 0.6549 0.3308 0.6549 0.8093
No log 5.0244 206 0.7019 0.3331 0.7019 0.8378
No log 5.0732 208 0.7056 0.3146 0.7056 0.8400
No log 5.1220 210 0.6695 0.3070 0.6695 0.8182
No log 5.1707 212 0.7291 0.3972 0.7291 0.8539
No log 5.2195 214 0.8820 0.4328 0.8820 0.9391
No log 5.2683 216 0.8658 0.4080 0.8658 0.9305
No log 5.3171 218 0.7503 0.4624 0.7503 0.8662
No log 5.3659 220 0.6936 0.4224 0.6936 0.8328
No log 5.4146 222 0.6910 0.4224 0.6910 0.8313
No log 5.4634 224 0.7636 0.4624 0.7636 0.8738
No log 5.5122 226 0.7926 0.4624 0.7926 0.8903
No log 5.5610 228 0.7748 0.4624 0.7748 0.8802
No log 5.6098 230 0.7839 0.4541 0.7839 0.8854
No log 5.6585 232 0.6846 0.4409 0.6846 0.8274
No log 5.7073 234 0.6718 0.4371 0.6718 0.8196
No log 5.7561 236 0.6660 0.3841 0.6660 0.8161
No log 5.8049 238 0.6805 0.3867 0.6805 0.8249
No log 5.8537 240 0.6967 0.3918 0.6967 0.8347
No log 5.9024 242 0.6698 0.2847 0.6698 0.8184
No log 5.9512 244 0.6703 0.2950 0.6703 0.8187
No log 6.0 246 0.7193 0.3032 0.7193 0.8481
No log 6.0488 248 0.7296 0.3032 0.7296 0.8542
No log 6.0976 250 0.7178 0.3032 0.7178 0.8472
No log 6.1463 252 0.6747 0.3032 0.6747 0.8214
No log 6.1951 254 0.6799 0.3032 0.6799 0.8245
No log 6.2439 256 0.6715 0.3060 0.6715 0.8194
No log 6.2927 258 0.6858 0.3060 0.6858 0.8281
No log 6.3415 260 0.7136 0.3183 0.7136 0.8447
No log 6.3902 262 0.7412 0.3173 0.7412 0.8609
No log 6.4390 264 0.7469 0.3608 0.7469 0.8642
No log 6.4878 266 0.7555 0.3648 0.7555 0.8692
No log 6.5366 268 0.7573 0.3648 0.7573 0.8702
No log 6.5854 270 0.7666 0.3776 0.7666 0.8756
No log 6.6341 272 0.7334 0.2995 0.7334 0.8564
No log 6.6829 274 0.6799 0.2722 0.6799 0.8246
No log 6.7317 276 0.6918 0.3023 0.6918 0.8317
No log 6.7805 278 0.7701 0.3770 0.7701 0.8775
No log 6.8293 280 0.8116 0.4574 0.8116 0.9009
No log 6.8780 282 0.8679 0.4743 0.8679 0.9316
No log 6.9268 284 0.9342 0.4462 0.9342 0.9665
No log 6.9756 286 0.8604 0.4735 0.8604 0.9276
No log 7.0244 288 0.8096 0.4801 0.8096 0.8998
No log 7.0732 290 0.7354 0.4582 0.7354 0.8576
No log 7.1220 292 0.6854 0.4350 0.6854 0.8279
No log 7.1707 294 0.7246 0.4726 0.7246 0.8512
No log 7.2195 296 0.7518 0.4726 0.7518 0.8670
No log 7.2683 298 0.8397 0.4096 0.8397 0.9163
No log 7.3171 300 0.9643 0.4003 0.9643 0.9820
No log 7.3659 302 0.8827 0.3933 0.8827 0.9395
No log 7.4146 304 0.8587 0.4008 0.8587 0.9266
No log 7.4634 306 0.8979 0.4183 0.8979 0.9476
No log 7.5122 308 0.8333 0.4064 0.8333 0.9128
No log 7.5610 310 0.7320 0.3287 0.7320 0.8556
No log 7.6098 312 0.7017 0.2414 0.7017 0.8377
No log 7.6585 314 0.7109 0.3918 0.7109 0.8432
No log 7.7073 316 0.6965 0.3918 0.6965 0.8345
No log 7.7561 318 0.6792 0.3918 0.6792 0.8241
No log 7.8049 320 0.6509 0.3867 0.6509 0.8068
No log 7.8537 322 0.6336 0.4393 0.6336 0.7960
No log 7.9024 324 0.6462 0.4336 0.6462 0.8039
No log 7.9512 326 0.6523 0.4081 0.6523 0.8077
No log 8.0 328 0.6703 0.4294 0.6703 0.8187
No log 8.0488 330 0.7272 0.4726 0.7272 0.8527
No log 8.0976 332 0.8741 0.4297 0.8741 0.9349
No log 8.1463 334 0.8770 0.4829 0.8770 0.9365
No log 8.1951 336 0.7641 0.5181 0.7641 0.8741
No log 8.2439 338 0.6970 0.3274 0.6970 0.8349
No log 8.2927 340 0.7002 0.3525 0.7002 0.8368
No log 8.3415 342 0.7509 0.4295 0.7509 0.8665
No log 8.3902 344 0.7753 0.4295 0.7753 0.8805
No log 8.4390 346 0.7514 0.4036 0.7514 0.8668
No log 8.4878 348 0.7557 0.4272 0.7557 0.8693
No log 8.5366 350 0.7854 0.4592 0.7854 0.8862
No log 8.5854 352 0.7683 0.4592 0.7683 0.8765
No log 8.6341 354 0.7345 0.4502 0.7345 0.8570
No log 8.6829 356 0.7392 0.4512 0.7392 0.8597
No log 8.7317 358 0.7600 0.4650 0.7600 0.8718
No log 8.7805 360 0.6792 0.4582 0.6792 0.8241
No log 8.8293 362 0.6373 0.4513 0.6373 0.7983
No log 8.8780 364 0.6330 0.4270 0.6330 0.7956
No log 8.9268 366 0.6709 0.4513 0.6709 0.8191
No log 8.9756 368 0.7354 0.4067 0.7354 0.8575
No log 9.0244 370 0.7374 0.4664 0.7374 0.8587
No log 9.0732 372 0.7005 0.4430 0.7005 0.8370
No log 9.1220 374 0.6691 0.3914 0.6691 0.8180
No log 9.1707 376 0.6616 0.3042 0.6616 0.8134
No log 9.2195 378 0.6648 0.3618 0.6648 0.8153
No log 9.2683 380 0.6792 0.3723 0.6792 0.8241
No log 9.3171 382 0.7283 0.4404 0.7283 0.8534
No log 9.3659 384 0.8518 0.4426 0.8518 0.9229
No log 9.4146 386 0.8781 0.4496 0.8781 0.9370
No log 9.4634 388 0.8238 0.4413 0.8238 0.9076
No log 9.5122 390 0.7623 0.4014 0.7623 0.8731
No log 9.5610 392 0.6955 0.3662 0.6955 0.8339
No log 9.6098 394 0.6613 0.2502 0.6613 0.8132
No log 9.6585 396 0.6542 0.3116 0.6542 0.8088
No log 9.7073 398 0.6439 0.3990 0.6439 0.8025
No log 9.7561 400 0.6490 0.3786 0.6490 0.8056
No log 9.8049 402 0.6623 0.4149 0.6623 0.8138
No log 9.8537 404 0.6652 0.5104 0.6652 0.8156
No log 9.9024 406 0.6566 0.5476 0.6566 0.8103
No log 9.9512 408 0.6522 0.5068 0.6522 0.8076
No log 10.0 410 0.6559 0.5248 0.6559 0.8099
No log 10.0488 412 0.6308 0.5276 0.6308 0.7943
No log 10.0976 414 0.6047 0.5206 0.6047 0.7776
No log 10.1463 416 0.6175 0.5304 0.6175 0.7858
No log 10.1951 418 0.5994 0.4986 0.5994 0.7742
No log 10.2439 420 0.6277 0.4134 0.6277 0.7923
No log 10.2927 422 0.6907 0.4892 0.6907 0.8311
No log 10.3415 424 0.7635 0.4788 0.7635 0.8738
No log 10.3902 426 0.7613 0.4873 0.7613 0.8725
No log 10.4390 428 0.7234 0.4190 0.7234 0.8505
No log 10.4878 430 0.7206 0.4190 0.7206 0.8489
No log 10.5366 432 0.7334 0.4190 0.7334 0.8564
No log 10.5854 434 0.7219 0.4190 0.7219 0.8496
No log 10.6341 436 0.7252 0.4892 0.7252 0.8516
No log 10.6829 438 0.7177 0.4430 0.7177 0.8472
No log 10.7317 440 0.6735 0.4190 0.6735 0.8207
No log 10.7805 442 0.6354 0.4190 0.6354 0.7971
No log 10.8293 444 0.6127 0.3569 0.6127 0.7827
No log 10.8780 446 0.6079 0.3615 0.6079 0.7797
No log 10.9268 448 0.6317 0.4190 0.6317 0.7948
No log 10.9756 450 0.6835 0.3637 0.6835 0.8267
No log 11.0244 452 0.7172 0.4387 0.7172 0.8469
No log 11.0732 454 0.7510 0.4328 0.7510 0.8666
No log 11.1220 456 0.7829 0.4777 0.7829 0.8848
No log 11.1707 458 0.7907 0.4906 0.7907 0.8892
No log 11.2195 460 0.7938 0.4733 0.7938 0.8909
No log 11.2683 462 0.7501 0.4468 0.7501 0.8661
No log 11.3171 464 0.6989 0.2781 0.6989 0.8360
No log 11.3659 466 0.6671 0.2633 0.6671 0.8168
No log 11.4146 468 0.6750 0.2893 0.6750 0.8216
No log 11.4634 470 0.7100 0.4236 0.7100 0.8426
No log 11.5122 472 0.7282 0.3826 0.7282 0.8534
No log 11.5610 474 0.6816 0.3844 0.6816 0.8256
No log 11.6098 476 0.6390 0.3474 0.6390 0.7994
No log 11.6585 478 0.6399 0.3474 0.6399 0.7999
No log 11.7073 480 0.6544 0.1598 0.6544 0.8090
No log 11.7561 482 0.6829 0.3167 0.6829 0.8264
No log 11.8049 484 0.7345 0.4387 0.7345 0.8570
No log 11.8537 486 0.7603 0.4387 0.7603 0.8720
No log 11.9024 488 0.7701 0.4568 0.7701 0.8775
No log 11.9512 490 0.7604 0.4385 0.7604 0.8720
No log 12.0 492 0.6960 0.4522 0.6960 0.8343
No log 12.0488 494 0.6634 0.4294 0.6634 0.8145
No log 12.0976 496 0.6231 0.4134 0.6231 0.7893
No log 12.1463 498 0.6049 0.3937 0.6049 0.7778
0.3572 12.1951 500 0.6168 0.4074 0.6168 0.7854
0.3572 12.2439 502 0.6327 0.4802 0.6327 0.7954
0.3572 12.2927 504 0.6147 0.4548 0.6147 0.7840
0.3572 12.3415 506 0.5887 0.3786 0.5887 0.7672
0.3572 12.3902 508 0.5800 0.4190 0.5800 0.7616
0.3572 12.4390 510 0.6920 0.4644 0.6920 0.8319
0.3572 12.4878 512 0.7692 0.4080 0.7692 0.8770
0.3572 12.5366 514 0.7244 0.4482 0.7244 0.8511
0.3572 12.5854 516 0.6341 0.3615 0.6341 0.7963
0.3572 12.6341 518 0.6014 0.3253 0.6014 0.7755
0.3572 12.6829 520 0.5985 0.3551 0.5985 0.7736
0.3572 12.7317 522 0.6114 0.3572 0.6114 0.7819
0.3572 12.7805 524 0.6515 0.3615 0.6515 0.8071

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
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_k16_task7_organization

Finetuned
(4204)
this model