ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k10_task2_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: 0.7655
  • Qwk: 0.5523
  • Mse: 0.7655
  • Rmse: 0.8749

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0312 2 3.9548 0.0011 3.9548 1.9887
No log 0.0625 4 2.0751 0.0682 2.0751 1.4405
No log 0.0938 6 1.4844 0.1646 1.4844 1.2184
No log 0.125 8 1.1152 0.0874 1.1152 1.0560
No log 0.1562 10 1.4226 0.1435 1.4226 1.1927
No log 0.1875 12 1.5054 0.1427 1.5054 1.2269
No log 0.2188 14 1.0466 0.1408 1.0466 1.0230
No log 0.25 16 0.7369 0.2321 0.7369 0.8584
No log 0.2812 18 0.6597 0.3199 0.6597 0.8122
No log 0.3125 20 0.6580 0.2901 0.6580 0.8112
No log 0.3438 22 0.9649 0.2270 0.9649 0.9823
No log 0.375 24 1.2667 0.1519 1.2667 1.1255
No log 0.4062 26 1.3262 0.1633 1.3262 1.1516
No log 0.4375 28 1.7225 0.1169 1.7225 1.3125
No log 0.4688 30 1.7415 0.1308 1.7415 1.3197
No log 0.5 32 1.3140 0.1915 1.3140 1.1463
No log 0.5312 34 0.7933 0.3645 0.7933 0.8907
No log 0.5625 36 0.7224 0.2587 0.7224 0.8499
No log 0.5938 38 0.8510 0.0596 0.8510 0.9225
No log 0.625 40 1.0288 0.0768 1.0288 1.0143
No log 0.6562 42 1.0923 0.1180 1.0923 1.0451
No log 0.6875 44 1.1302 0.2093 1.1302 1.0631
No log 0.7188 46 1.1222 0.2348 1.1222 1.0593
No log 0.75 48 1.3351 0.1752 1.3351 1.1555
No log 0.7812 50 1.1891 0.1796 1.1891 1.0905
No log 0.8125 52 1.1673 0.1648 1.1673 1.0804
No log 0.8438 54 1.1249 0.2766 1.1249 1.0606
No log 0.875 56 0.8535 0.3269 0.8535 0.9239
No log 0.9062 58 0.8046 0.4512 0.8046 0.8970
No log 0.9375 60 0.8272 0.4459 0.8272 0.9095
No log 0.9688 62 1.2181 0.2749 1.2181 1.1037
No log 1.0 64 1.6607 0.1902 1.6607 1.2887
No log 1.0312 66 1.7330 0.2036 1.7330 1.3164
No log 1.0625 68 1.6301 0.2102 1.6301 1.2768
No log 1.0938 70 1.3835 0.2558 1.3835 1.1762
No log 1.125 72 1.0127 0.3871 1.0127 1.0063
No log 1.1562 74 0.7553 0.4619 0.7553 0.8691
No log 1.1875 76 0.6305 0.4213 0.6305 0.7940
No log 1.2188 78 0.6213 0.4462 0.6213 0.7882
No log 1.25 80 0.6527 0.4663 0.6527 0.8079
No log 1.2812 82 0.9391 0.4920 0.9391 0.9691
No log 1.3125 84 1.3236 0.3153 1.3236 1.1505
No log 1.3438 86 1.4222 0.3027 1.4222 1.1926
No log 1.375 88 1.1851 0.3622 1.1851 1.0886
No log 1.4062 90 0.8491 0.4892 0.8491 0.9215
No log 1.4375 92 0.7378 0.5362 0.7378 0.8590
No log 1.4688 94 0.7430 0.5497 0.7430 0.8620
No log 1.5 96 0.7465 0.5190 0.7465 0.8640
No log 1.5312 98 0.8654 0.4955 0.8654 0.9303
No log 1.5625 100 1.1880 0.3562 1.1880 1.0900
No log 1.5938 102 1.2035 0.3349 1.2035 1.0970
No log 1.625 104 1.0970 0.3940 1.0970 1.0474
No log 1.6562 106 0.8069 0.4943 0.8069 0.8983
No log 1.6875 108 0.6077 0.5397 0.6077 0.7795
No log 1.7188 110 0.6496 0.4254 0.6496 0.8060
No log 1.75 112 0.7131 0.3557 0.7131 0.8445
No log 1.7812 114 0.7346 0.4761 0.7346 0.8571
No log 1.8125 116 0.9283 0.4126 0.9283 0.9635
No log 1.8438 118 1.1242 0.4079 1.1242 1.0603
No log 1.875 120 1.1615 0.4030 1.1615 1.0777
No log 1.9062 122 1.0262 0.4383 1.0262 1.0130
No log 1.9375 124 0.9105 0.4669 0.9105 0.9542
No log 1.9688 126 0.8812 0.4304 0.8812 0.9387
No log 2.0 128 0.8542 0.4476 0.8542 0.9242
No log 2.0312 130 0.8253 0.4811 0.8253 0.9085
No log 2.0625 132 0.8524 0.5294 0.8524 0.9233
No log 2.0938 134 0.9146 0.4709 0.9146 0.9564
No log 2.125 136 1.0020 0.4571 1.0020 1.0010
No log 2.1562 138 1.0369 0.4248 1.0369 1.0183
No log 2.1875 140 1.0242 0.4526 1.0242 1.0120
No log 2.2188 142 0.9309 0.4699 0.9309 0.9648
No log 2.25 144 0.9422 0.4759 0.9422 0.9707
No log 2.2812 146 0.9904 0.4644 0.9904 0.9952
No log 2.3125 148 1.0342 0.4439 1.0342 1.0170
No log 2.3438 150 0.9765 0.4442 0.9765 0.9882
No log 2.375 152 0.9999 0.4512 0.9999 0.9999
No log 2.4062 154 0.9010 0.4524 0.9010 0.9492
No log 2.4375 156 0.7707 0.5071 0.7707 0.8779
No log 2.4688 158 0.7179 0.5102 0.7179 0.8473
No log 2.5 160 0.7060 0.5152 0.7060 0.8402
No log 2.5312 162 0.7354 0.5413 0.7354 0.8575
No log 2.5625 164 0.8283 0.5110 0.8283 0.9101
No log 2.5938 166 0.8379 0.5010 0.8379 0.9153
No log 2.625 168 0.8378 0.5249 0.8378 0.9153
No log 2.6562 170 0.8527 0.5138 0.8527 0.9234
No log 2.6875 172 0.8521 0.4277 0.8521 0.9231
No log 2.7188 174 0.8448 0.4328 0.8448 0.9191
No log 2.75 176 0.8275 0.4486 0.8275 0.9097
No log 2.7812 178 0.8170 0.4615 0.8170 0.9039
No log 2.8125 180 0.7891 0.4705 0.7891 0.8883
No log 2.8438 182 0.7945 0.5158 0.7945 0.8914
No log 2.875 184 0.8389 0.5085 0.8389 0.9159
No log 2.9062 186 0.8412 0.5282 0.8412 0.9171
No log 2.9375 188 0.8413 0.4773 0.8413 0.9172
No log 2.9688 190 0.9003 0.4705 0.9003 0.9488
No log 3.0 192 0.9351 0.4822 0.9351 0.9670
No log 3.0312 194 0.9481 0.4709 0.9481 0.9737
No log 3.0625 196 0.9374 0.4986 0.9374 0.9682
No log 3.0938 198 0.9331 0.5053 0.9331 0.9659
No log 3.125 200 0.9507 0.4948 0.9507 0.9750
No log 3.1562 202 0.9639 0.4670 0.9639 0.9818
No log 3.1875 204 0.9580 0.4640 0.9580 0.9788
No log 3.2188 206 0.9204 0.4067 0.9204 0.9594
No log 3.25 208 0.8626 0.4059 0.8626 0.9288
No log 3.2812 210 0.8111 0.4275 0.8111 0.9006
No log 3.3125 212 0.7877 0.4700 0.7877 0.8876
No log 3.3438 214 0.7567 0.5481 0.7567 0.8699
No log 3.375 216 0.8025 0.4803 0.8025 0.8958
No log 3.4062 218 0.8561 0.4295 0.8561 0.9252
No log 3.4375 220 0.9742 0.4096 0.9742 0.9870
No log 3.4688 222 1.0146 0.4129 1.0146 1.0073
No log 3.5 224 0.9221 0.4340 0.9221 0.9603
No log 3.5312 226 0.8187 0.5083 0.8187 0.9048
No log 3.5625 228 0.7806 0.5446 0.7806 0.8835
No log 3.5938 230 0.7714 0.5376 0.7714 0.8783
No log 3.625 232 0.7850 0.5485 0.7850 0.8860
No log 3.6562 234 0.8222 0.5003 0.8222 0.9067
No log 3.6875 236 0.8309 0.4857 0.8309 0.9115
No log 3.7188 238 0.9217 0.4233 0.9217 0.9601
No log 3.75 240 0.9682 0.3840 0.9682 0.9840
No log 3.7812 242 1.0110 0.3672 1.0110 1.0055
No log 3.8125 244 0.8870 0.4096 0.8870 0.9418
No log 3.8438 246 0.7400 0.5179 0.7400 0.8602
No log 3.875 248 0.7185 0.4514 0.7185 0.8477
No log 3.9062 250 0.8552 0.4494 0.8552 0.9248
No log 3.9375 252 0.8909 0.4420 0.8909 0.9439
No log 3.9688 254 0.8187 0.4604 0.8187 0.9048
No log 4.0 256 0.7292 0.5247 0.7292 0.8539
No log 4.0312 258 0.7536 0.6065 0.7536 0.8681
No log 4.0625 260 0.8095 0.5008 0.8095 0.8997
No log 4.0938 262 0.7852 0.5105 0.7852 0.8861
No log 4.125 264 0.6935 0.5966 0.6935 0.8328
No log 4.1562 266 0.6537 0.5337 0.6537 0.8085
No log 4.1875 268 0.6814 0.5387 0.6814 0.8255
No log 4.2188 270 0.6984 0.5333 0.6984 0.8357
No log 4.25 272 0.7264 0.5217 0.7264 0.8523
No log 4.2812 274 0.7840 0.5679 0.7840 0.8854
No log 4.3125 276 0.8266 0.5276 0.8266 0.9092
No log 4.3438 278 0.8394 0.4840 0.8394 0.9162
No log 4.375 280 0.8119 0.5543 0.8119 0.9011
No log 4.4062 282 0.7703 0.5036 0.7703 0.8777
No log 4.4375 284 0.7569 0.5028 0.7569 0.8700
No log 4.4688 286 0.7728 0.4989 0.7728 0.8791
No log 4.5 288 0.7644 0.5028 0.7644 0.8743
No log 4.5312 290 0.7785 0.5011 0.7785 0.8823
No log 4.5625 292 0.7805 0.5120 0.7805 0.8834
No log 4.5938 294 0.7864 0.5198 0.7864 0.8868
No log 4.625 296 0.7959 0.5358 0.7959 0.8921
No log 4.6562 298 0.8232 0.5363 0.8232 0.9073
No log 4.6875 300 0.8055 0.5360 0.8055 0.8975
No log 4.7188 302 0.7472 0.5392 0.7472 0.8644
No log 4.75 304 0.7228 0.5389 0.7228 0.8502
No log 4.7812 306 0.7419 0.5189 0.7419 0.8613
No log 4.8125 308 0.8137 0.5005 0.8137 0.9020
No log 4.8438 310 0.8465 0.4886 0.8465 0.9201
No log 4.875 312 0.8140 0.5184 0.8140 0.9022
No log 4.9062 314 0.7758 0.5427 0.7758 0.8808
No log 4.9375 316 0.7823 0.5037 0.7823 0.8845
No log 4.9688 318 0.7967 0.4773 0.7967 0.8926
No log 5.0 320 0.7778 0.5068 0.7778 0.8819
No log 5.0312 322 0.7904 0.5582 0.7904 0.8891
No log 5.0625 324 0.8479 0.5054 0.8479 0.9208
No log 5.0938 326 0.9095 0.4184 0.9095 0.9537
No log 5.125 328 0.8914 0.4687 0.8914 0.9442
No log 5.1562 330 0.8045 0.5432 0.8045 0.8969
No log 5.1875 332 0.7540 0.5597 0.7540 0.8683
No log 5.2188 334 0.7264 0.5565 0.7264 0.8523
No log 5.25 336 0.7032 0.5611 0.7032 0.8386
No log 5.2812 338 0.6979 0.5663 0.6979 0.8354
No log 5.3125 340 0.6929 0.5493 0.6929 0.8324
No log 5.3438 342 0.6887 0.5679 0.6887 0.8299
No log 5.375 344 0.7073 0.5776 0.7073 0.8410
No log 5.4062 346 0.7462 0.5838 0.7462 0.8638
No log 5.4375 348 0.7745 0.5678 0.7745 0.8801
No log 5.4688 350 0.7930 0.5648 0.7930 0.8905
No log 5.5 352 0.7958 0.5702 0.7958 0.8921
No log 5.5312 354 0.7876 0.5620 0.7876 0.8875
No log 5.5625 356 0.7849 0.5423 0.7849 0.8859
No log 5.5938 358 0.7682 0.5421 0.7682 0.8765
No log 5.625 360 0.7652 0.5146 0.7652 0.8748
No log 5.6562 362 0.7607 0.5287 0.7607 0.8722
No log 5.6875 364 0.7749 0.5280 0.7749 0.8803
No log 5.7188 366 0.7953 0.4736 0.7953 0.8918
No log 5.75 368 0.8364 0.4835 0.8364 0.9145
No log 5.7812 370 0.8688 0.4680 0.8688 0.9321
No log 5.8125 372 0.8775 0.4770 0.8775 0.9367
No log 5.8438 374 0.8841 0.5045 0.8841 0.9403
No log 5.875 376 0.9007 0.5123 0.9007 0.9491
No log 5.9062 378 0.9371 0.4634 0.9371 0.9680
No log 5.9375 380 0.9706 0.4833 0.9706 0.9852
No log 5.9688 382 0.9394 0.4638 0.9394 0.9692
No log 6.0 384 0.8875 0.4796 0.8876 0.9421
No log 6.0312 386 0.8321 0.4980 0.8321 0.9122
No log 6.0625 388 0.7773 0.5105 0.7773 0.8816
No log 6.0938 390 0.7461 0.5133 0.7461 0.8638
No log 6.125 392 0.7255 0.5377 0.7255 0.8518
No log 6.1562 394 0.7155 0.5523 0.7155 0.8459
No log 6.1875 396 0.7480 0.5180 0.7480 0.8649
No log 6.2188 398 0.8234 0.4383 0.8234 0.9074
No log 6.25 400 0.9017 0.4264 0.9017 0.9496
No log 6.2812 402 0.9104 0.4344 0.9104 0.9542
No log 6.3125 404 0.8484 0.4450 0.8484 0.9211
No log 6.3438 406 0.8071 0.5144 0.8071 0.8984
No log 6.375 408 0.7732 0.5055 0.7732 0.8793
No log 6.4062 410 0.7741 0.5146 0.7741 0.8799
No log 6.4375 412 0.7866 0.5043 0.7866 0.8869
No log 6.4688 414 0.7961 0.4989 0.7961 0.8922
No log 6.5 416 0.7838 0.5203 0.7838 0.8853
No log 6.5312 418 0.7666 0.5382 0.7666 0.8756
No log 6.5625 420 0.7560 0.5350 0.7560 0.8695
No log 6.5938 422 0.7431 0.5265 0.7431 0.8620
No log 6.625 424 0.7330 0.5229 0.7330 0.8562
No log 6.6562 426 0.7346 0.5384 0.7346 0.8571
No log 6.6875 428 0.7467 0.5225 0.7467 0.8641
No log 6.7188 430 0.7631 0.5216 0.7631 0.8735
No log 6.75 432 0.7860 0.5428 0.7860 0.8866
No log 6.7812 434 0.8087 0.5301 0.8087 0.8993
No log 6.8125 436 0.8186 0.5284 0.8186 0.9048
No log 6.8438 438 0.8127 0.5340 0.8127 0.9015
No log 6.875 440 0.7863 0.5385 0.7863 0.8867
No log 6.9062 442 0.7742 0.4897 0.7742 0.8799
No log 6.9375 444 0.7951 0.4913 0.7951 0.8917
No log 6.9688 446 0.8181 0.4941 0.8181 0.9045
No log 7.0 448 0.8334 0.4812 0.8334 0.9129
No log 7.0312 450 0.8311 0.4786 0.8311 0.9116
No log 7.0625 452 0.8125 0.5186 0.8125 0.9014
No log 7.0938 454 0.8022 0.5327 0.8022 0.8957
No log 7.125 456 0.8285 0.5271 0.8285 0.9102
No log 7.1562 458 0.8647 0.4987 0.8647 0.9299
No log 7.1875 460 0.8883 0.4474 0.8883 0.9425
No log 7.2188 462 0.8703 0.4700 0.8703 0.9329
No log 7.25 464 0.8240 0.5182 0.8240 0.9078
No log 7.2812 466 0.7791 0.5165 0.7791 0.8827
No log 7.3125 468 0.7573 0.5537 0.7573 0.8702
No log 7.3438 470 0.7650 0.5788 0.7650 0.8746
No log 7.375 472 0.7812 0.5637 0.7812 0.8839
No log 7.4062 474 0.7998 0.5508 0.7998 0.8943
No log 7.4375 476 0.8059 0.5382 0.8059 0.8977
No log 7.4688 478 0.7988 0.5382 0.7988 0.8937
No log 7.5 480 0.7906 0.5216 0.7906 0.8892
No log 7.5312 482 0.7842 0.5173 0.7842 0.8855
No log 7.5625 484 0.7699 0.5183 0.7699 0.8775
No log 7.5938 486 0.7566 0.5167 0.7566 0.8698
No log 7.625 488 0.7522 0.5339 0.7522 0.8673
No log 7.6562 490 0.7437 0.5523 0.7437 0.8624
No log 7.6875 492 0.7316 0.5788 0.7316 0.8554
No log 7.7188 494 0.7300 0.5625 0.7300 0.8544
No log 7.75 496 0.7243 0.5626 0.7243 0.8511
No log 7.7812 498 0.7344 0.5129 0.7344 0.8570
0.4435 7.8125 500 0.7575 0.5112 0.7575 0.8704
0.4435 7.8438 502 0.7809 0.5340 0.7809 0.8837
0.4435 7.875 504 0.7828 0.5458 0.7828 0.8848
0.4435 7.9062 506 0.7658 0.5369 0.7658 0.8751
0.4435 7.9375 508 0.7406 0.5254 0.7406 0.8606
0.4435 7.9688 510 0.7261 0.5785 0.7261 0.8521
0.4435 8.0 512 0.7197 0.5758 0.7197 0.8484
0.4435 8.0312 514 0.7142 0.5743 0.7142 0.8451
0.4435 8.0625 516 0.7078 0.5609 0.7078 0.8413
0.4435 8.0938 518 0.7057 0.5609 0.7057 0.8401
0.4435 8.125 520 0.7123 0.5859 0.7123 0.8440
0.4435 8.1562 522 0.7270 0.5782 0.7270 0.8526
0.4435 8.1875 524 0.7386 0.5869 0.7386 0.8594
0.4435 8.2188 526 0.7480 0.5865 0.7480 0.8649
0.4435 8.25 528 0.7478 0.5734 0.7478 0.8648
0.4435 8.2812 530 0.7435 0.5869 0.7435 0.8623
0.4435 8.3125 532 0.7381 0.5851 0.7381 0.8591
0.4435 8.3438 534 0.7307 0.5634 0.7307 0.8548
0.4435 8.375 536 0.7248 0.5562 0.7248 0.8513
0.4435 8.4062 538 0.7195 0.5562 0.7195 0.8482
0.4435 8.4375 540 0.7132 0.5779 0.7132 0.8445
0.4435 8.4688 542 0.7194 0.5779 0.7194 0.8482
0.4435 8.5 544 0.7317 0.5779 0.7317 0.8554
0.4435 8.5312 546 0.7397 0.5869 0.7397 0.8601
0.4435 8.5625 548 0.7467 0.5865 0.7467 0.8641
0.4435 8.5938 550 0.7594 0.5865 0.7594 0.8715
0.4435 8.625 552 0.7642 0.5620 0.7642 0.8742
0.4435 8.6562 554 0.7663 0.5510 0.7663 0.8754
0.4435 8.6875 556 0.7678 0.5345 0.7678 0.8762
0.4435 8.7188 558 0.7621 0.5345 0.7621 0.8730
0.4435 8.75 560 0.7598 0.5342 0.7598 0.8717
0.4435 8.7812 562 0.7563 0.5397 0.7563 0.8696
0.4435 8.8125 564 0.7513 0.5785 0.7513 0.8668
0.4435 8.8438 566 0.7479 0.5638 0.7479 0.8648
0.4435 8.875 568 0.7448 0.5638 0.7448 0.8630
0.4435 8.9062 570 0.7407 0.5711 0.7407 0.8607
0.4435 8.9375 572 0.7373 0.5711 0.7373 0.8586
0.4435 8.9688 574 0.7360 0.5785 0.7360 0.8579
0.4435 9.0 576 0.7335 0.5950 0.7335 0.8565
0.4435 9.0312 578 0.7317 0.5950 0.7317 0.8554
0.4435 9.0625 580 0.7319 0.5813 0.7319 0.8555
0.4435 9.0938 582 0.7368 0.5697 0.7368 0.8584
0.4435 9.125 584 0.7422 0.5539 0.7422 0.8615
0.4435 9.1562 586 0.7496 0.5098 0.7496 0.8658
0.4435 9.1875 588 0.7532 0.5098 0.7532 0.8679
0.4435 9.2188 590 0.7524 0.5098 0.7524 0.8674
0.4435 9.25 592 0.7474 0.5405 0.7474 0.8645
0.4435 9.2812 594 0.7447 0.5755 0.7447 0.8629
0.4435 9.3125 596 0.7426 0.5950 0.7426 0.8617
0.4435 9.3438 598 0.7414 0.5711 0.7414 0.8611
0.4435 9.375 600 0.7462 0.5639 0.7462 0.8638
0.4435 9.4062 602 0.7535 0.5698 0.7535 0.8680
0.4435 9.4375 604 0.7598 0.5682 0.7598 0.8716
0.4435 9.4688 606 0.7628 0.5724 0.7628 0.8734
0.4435 9.5 608 0.7619 0.5724 0.7619 0.8729
0.4435 9.5312 610 0.7598 0.5682 0.7598 0.8716
0.4435 9.5625 612 0.7587 0.5698 0.7587 0.8710
0.4435 9.5938 614 0.7588 0.5638 0.7588 0.8711
0.4435 9.625 616 0.7596 0.5638 0.7596 0.8716
0.4435 9.6562 618 0.7622 0.5638 0.7622 0.8730
0.4435 9.6875 620 0.7658 0.5652 0.7658 0.8751
0.4435 9.7188 622 0.7695 0.5523 0.7695 0.8772
0.4435 9.75 624 0.7708 0.5523 0.7708 0.8779
0.4435 9.7812 626 0.7708 0.5523 0.7708 0.8779
0.4435 9.8125 628 0.7693 0.5523 0.7693 0.8771
0.4435 9.8438 630 0.7683 0.5523 0.7683 0.8765
0.4435 9.875 632 0.7673 0.5523 0.7673 0.8760
0.4435 9.9062 634 0.7662 0.5523 0.7662 0.8753
0.4435 9.9375 636 0.7658 0.5523 0.7658 0.8751
0.4435 9.9688 638 0.7655 0.5523 0.7655 0.8750
0.4435 10.0 640 0.7655 0.5523 0.7655 0.8749

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/ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k10_task2_organization

Finetuned
(4023)
this model