ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k11_task5_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: 0.8475
  • Qwk: 0.3280
  • Mse: 0.8475
  • Rmse: 0.9206

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 0.0385 2 4.1331 -0.0234 4.1331 2.0330
No log 0.0769 4 2.7238 -0.0751 2.7238 1.6504
No log 0.1154 6 2.4167 -0.0656 2.4167 1.5546
No log 0.1538 8 1.8468 0.0184 1.8468 1.3590
No log 0.1923 10 1.3093 0.0693 1.3093 1.1442
No log 0.2308 12 1.1748 0.1313 1.1748 1.0839
No log 0.2692 14 1.3783 0.1487 1.3783 1.1740
No log 0.3077 16 1.1952 0.2017 1.1952 1.0932
No log 0.3462 18 1.0205 0.2539 1.0205 1.0102
No log 0.3846 20 1.0732 0.2023 1.0732 1.0359
No log 0.4231 22 1.0314 0.2466 1.0314 1.0156
No log 0.4615 24 1.0179 0.1981 1.0179 1.0089
No log 0.5 26 1.0229 0.1573 1.0229 1.0114
No log 0.5385 28 1.0176 0.2340 1.0176 1.0087
No log 0.5769 30 1.0409 0.2068 1.0409 1.0202
No log 0.6154 32 1.2471 0.0996 1.2471 1.1167
No log 0.6538 34 1.3448 0.0380 1.3448 1.1596
No log 0.6923 36 1.2049 0.2150 1.2049 1.0977
No log 0.7308 38 1.0362 0.2145 1.0362 1.0179
No log 0.7692 40 0.9608 0.2740 0.9608 0.9802
No log 0.8077 42 0.9646 0.2316 0.9646 0.9821
No log 0.8462 44 1.0560 0.3045 1.0560 1.0276
No log 0.8846 46 1.1156 0.2282 1.1156 1.0562
No log 0.9231 48 1.1708 0.2363 1.1708 1.0820
No log 0.9615 50 1.1123 0.2328 1.1123 1.0546
No log 1.0 52 1.0563 0.3200 1.0563 1.0278
No log 1.0385 54 1.0465 0.2841 1.0465 1.0230
No log 1.0769 56 1.0844 0.2448 1.0844 1.0413
No log 1.1154 58 1.2748 0.1812 1.2748 1.1291
No log 1.1538 60 1.5083 0.2300 1.5083 1.2281
No log 1.1923 62 1.5727 0.2436 1.5727 1.2541
No log 1.2308 64 1.5145 0.2212 1.5145 1.2307
No log 1.2692 66 1.5698 0.1750 1.5698 1.2529
No log 1.3077 68 1.8191 0.0914 1.8191 1.3487
No log 1.3462 70 1.7287 0.0889 1.7287 1.3148
No log 1.3846 72 1.4893 0.1387 1.4893 1.2204
No log 1.4231 74 1.2008 0.2246 1.2008 1.0958
No log 1.4615 76 1.0771 0.2290 1.0771 1.0379
No log 1.5 78 1.0538 0.2671 1.0538 1.0265
No log 1.5385 80 1.1073 0.2502 1.1073 1.0523
No log 1.5769 82 1.1610 0.2280 1.1610 1.0775
No log 1.6154 84 1.1177 0.2311 1.1177 1.0572
No log 1.6538 86 1.0400 0.2475 1.0400 1.0198
No log 1.6923 88 1.0151 0.3614 1.0151 1.0075
No log 1.7308 90 1.0613 0.3200 1.0613 1.0302
No log 1.7692 92 1.0838 0.2588 1.0838 1.0411
No log 1.8077 94 1.1814 0.2375 1.1814 1.0869
No log 1.8462 96 1.3636 0.2462 1.3636 1.1677
No log 1.8846 98 1.4301 0.2728 1.4301 1.1958
No log 1.9231 100 1.3492 0.1595 1.3492 1.1615
No log 1.9615 102 1.1806 0.2864 1.1806 1.0865
No log 2.0 104 1.0956 0.3019 1.0956 1.0467
No log 2.0385 106 1.0000 0.3981 1.0000 1.0000
No log 2.0769 108 0.9589 0.3839 0.9589 0.9792
No log 2.1154 110 1.0190 0.3671 1.0190 1.0095
No log 2.1538 112 1.1512 0.2379 1.1512 1.0729
No log 2.1923 114 1.2020 0.2740 1.2020 1.0964
No log 2.2308 116 1.1370 0.2850 1.1370 1.0663
No log 2.2692 118 1.0719 0.2673 1.0719 1.0353
No log 2.3077 120 1.0202 0.3243 1.0202 1.0101
No log 2.3462 122 1.0323 0.3335 1.0323 1.0160
No log 2.3846 124 1.0715 0.3474 1.0715 1.0351
No log 2.4231 126 0.9976 0.3733 0.9976 0.9988
No log 2.4615 128 0.9645 0.4305 0.9645 0.9821
No log 2.5 130 0.9212 0.3965 0.9212 0.9598
No log 2.5385 132 0.9327 0.3965 0.9327 0.9658
No log 2.5769 134 0.9781 0.4073 0.9781 0.9890
No log 2.6154 136 0.9918 0.3448 0.9918 0.9959
No log 2.6538 138 1.0548 0.3668 1.0548 1.0271
No log 2.6923 140 1.0767 0.3406 1.0767 1.0376
No log 2.7308 142 1.0123 0.2951 1.0123 1.0061
No log 2.7692 144 0.9730 0.2857 0.9730 0.9864
No log 2.8077 146 0.9308 0.3418 0.9308 0.9648
No log 2.8462 148 0.9013 0.3779 0.9013 0.9494
No log 2.8846 150 0.8900 0.4527 0.8900 0.9434
No log 2.9231 152 0.9641 0.3639 0.9641 0.9819
No log 2.9615 154 1.1058 0.3573 1.1058 1.0516
No log 3.0 156 1.0960 0.3879 1.0960 1.0469
No log 3.0385 158 1.0190 0.3602 1.0190 1.0095
No log 3.0769 160 1.1149 0.2750 1.1149 1.0559
No log 3.1154 162 1.1780 0.3044 1.1780 1.0854
No log 3.1538 164 1.0680 0.3383 1.0680 1.0334
No log 3.1923 166 0.9768 0.3424 0.9768 0.9883
No log 3.2308 168 0.8799 0.4093 0.8799 0.9380
No log 3.2692 170 0.9932 0.4350 0.9932 0.9966
No log 3.3077 172 1.1142 0.2567 1.1142 1.0555
No log 3.3462 174 1.1004 0.2949 1.1004 1.0490
No log 3.3846 176 0.9990 0.3293 0.9990 0.9995
No log 3.4231 178 0.9592 0.2038 0.9592 0.9794
No log 3.4615 180 0.9972 0.2572 0.9972 0.9986
No log 3.5 182 1.0258 0.3328 1.0258 1.0128
No log 3.5385 184 0.9817 0.2526 0.9817 0.9908
No log 3.5769 186 0.9664 0.3209 0.9664 0.9830
No log 3.6154 188 1.0188 0.3338 1.0188 1.0094
No log 3.6538 190 1.1044 0.3369 1.1044 1.0509
No log 3.6923 192 1.1520 0.3237 1.1520 1.0733
No log 3.7308 194 1.1643 0.3551 1.1643 1.0790
No log 3.7692 196 1.0508 0.3475 1.0508 1.0251
No log 3.8077 198 0.9754 0.3475 0.9754 0.9876
No log 3.8462 200 0.9525 0.3733 0.9525 0.9760
No log 3.8846 202 0.9591 0.3672 0.9591 0.9794
No log 3.9231 204 0.9478 0.4469 0.9478 0.9735
No log 3.9615 206 0.9740 0.4861 0.9740 0.9869
No log 4.0 208 0.9737 0.5002 0.9737 0.9868
No log 4.0385 210 0.9951 0.4309 0.9951 0.9975
No log 4.0769 212 1.0500 0.3427 1.0500 1.0247
No log 4.1154 214 1.1431 0.3452 1.1431 1.0692
No log 4.1538 216 1.0583 0.3103 1.0583 1.0287
No log 4.1923 218 0.9115 0.4488 0.9115 0.9547
No log 4.2308 220 0.9705 0.4710 0.9705 0.9852
No log 4.2692 222 0.9744 0.4681 0.9744 0.9871
No log 4.3077 224 0.8955 0.4444 0.8955 0.9463
No log 4.3462 226 0.9039 0.4421 0.9039 0.9507
No log 4.3846 228 0.9561 0.3308 0.9561 0.9778
No log 4.4231 230 0.9974 0.2895 0.9974 0.9987
No log 4.4615 232 0.9503 0.3185 0.9503 0.9748
No log 4.5 234 0.8668 0.4450 0.8668 0.9310
No log 4.5385 236 0.8383 0.4204 0.8383 0.9156
No log 4.5769 238 0.8311 0.2888 0.8311 0.9117
No log 4.6154 240 0.8506 0.2643 0.8506 0.9223
No log 4.6538 242 0.8677 0.2316 0.8677 0.9315
No log 4.6923 244 0.8652 0.2643 0.8652 0.9302
No log 4.7308 246 0.8530 0.2956 0.8530 0.9236
No log 4.7692 248 0.8476 0.3216 0.8476 0.9206
No log 4.8077 250 0.8235 0.3257 0.8235 0.9074
No log 4.8462 252 0.7999 0.2954 0.7999 0.8944
No log 4.8846 254 0.7988 0.3994 0.7988 0.8938
No log 4.9231 256 0.8375 0.4712 0.8375 0.9151
No log 4.9615 258 0.8571 0.5074 0.8571 0.9258
No log 5.0 260 0.8868 0.4681 0.8868 0.9417
No log 5.0385 262 0.8520 0.3757 0.8520 0.9230
No log 5.0769 264 0.8097 0.3583 0.8097 0.8998
No log 5.1154 266 0.8481 0.3896 0.8481 0.9209
No log 5.1538 268 0.8540 0.3645 0.8540 0.9241
No log 5.1923 270 0.8316 0.3478 0.8316 0.9119
No log 5.2308 272 0.8285 0.2865 0.8285 0.9102
No log 5.2692 274 0.8611 0.3678 0.8611 0.9279
No log 5.3077 276 0.8954 0.4843 0.8954 0.9463
No log 5.3462 278 0.9135 0.4829 0.9135 0.9558
No log 5.3846 280 0.8260 0.4289 0.8260 0.9088
No log 5.4231 282 0.8200 0.4261 0.8200 0.9056
No log 5.4615 284 0.8415 0.3925 0.8415 0.9173
No log 5.5 286 0.8502 0.4517 0.8502 0.9221
No log 5.5385 288 0.8619 0.4034 0.8619 0.9284
No log 5.5769 290 0.8558 0.3503 0.8558 0.9251
No log 5.6154 292 0.9244 0.4729 0.9244 0.9614
No log 5.6538 294 0.9957 0.4214 0.9957 0.9978
No log 5.6923 296 0.9831 0.3543 0.9831 0.9915
No log 5.7308 298 0.9347 0.3414 0.9347 0.9668
No log 5.7692 300 0.9214 0.3314 0.9214 0.9599
No log 5.8077 302 0.9117 0.3074 0.9117 0.9548
No log 5.8462 304 0.9155 0.3367 0.9155 0.9568
No log 5.8846 306 0.9288 0.4385 0.9288 0.9637
No log 5.9231 308 0.9006 0.4385 0.9006 0.9490
No log 5.9615 310 0.8453 0.4515 0.8453 0.9194
No log 6.0 312 0.8358 0.4048 0.8358 0.9142
No log 6.0385 314 0.8555 0.4158 0.8555 0.9249
No log 6.0769 316 0.9439 0.4385 0.9439 0.9716
No log 6.1154 318 1.0856 0.3535 1.0856 1.0419
No log 6.1538 320 1.1212 0.1855 1.1212 1.0589
No log 6.1923 322 1.0557 0.1786 1.0557 1.0275
No log 6.2308 324 0.9575 0.3455 0.9575 0.9785
No log 6.2692 326 0.8977 0.3455 0.8977 0.9475
No log 6.3077 328 0.8687 0.3134 0.8687 0.9320
No log 6.3462 330 0.8613 0.3556 0.8613 0.9280
No log 6.3846 332 0.8664 0.4385 0.8664 0.9308
No log 6.4231 334 0.8637 0.4076 0.8637 0.9293
No log 6.4615 336 0.8682 0.3891 0.8682 0.9318
No log 6.5 338 0.8626 0.3412 0.8626 0.9288
No log 6.5385 340 0.8401 0.4252 0.8401 0.9166
No log 6.5769 342 0.8368 0.4439 0.8368 0.9148
No log 6.6154 344 0.9503 0.4250 0.9503 0.9748
No log 6.6538 346 0.9724 0.4465 0.9724 0.9861
No log 6.6923 348 0.8920 0.4361 0.8920 0.9444
No log 6.7308 350 0.8943 0.3137 0.8943 0.9457
No log 6.7692 352 0.9364 0.4053 0.9364 0.9677
No log 6.8077 354 0.9003 0.4300 0.9003 0.9489
No log 6.8462 356 0.8611 0.4122 0.8611 0.9280
No log 6.8846 358 0.8984 0.4604 0.8984 0.9478
No log 6.9231 360 0.8679 0.4164 0.8679 0.9316
No log 6.9615 362 0.8408 0.4 0.8408 0.9170
No log 7.0 364 0.8453 0.4252 0.8453 0.9194
No log 7.0385 366 0.8500 0.3874 0.8500 0.9219
No log 7.0769 368 0.8628 0.4030 0.8628 0.9289
No log 7.1154 370 0.8577 0.3505 0.8577 0.9261
No log 7.1538 372 0.8963 0.3250 0.8963 0.9467
No log 7.1923 374 0.9352 0.3902 0.9352 0.9670
No log 7.2308 376 0.9279 0.4039 0.9279 0.9633
No log 7.2692 378 0.8898 0.4039 0.8898 0.9433
No log 7.3077 380 0.8080 0.4612 0.8080 0.8989
No log 7.3462 382 0.7867 0.3685 0.7867 0.8870
No log 7.3846 384 0.7994 0.3685 0.7994 0.8941
No log 7.4231 386 0.8188 0.4531 0.8188 0.9049
No log 7.4615 388 0.8224 0.4531 0.8224 0.9069
No log 7.5 390 0.8330 0.4279 0.8330 0.9127
No log 7.5385 392 0.8168 0.4251 0.8168 0.9038
No log 7.5769 394 0.8087 0.3836 0.8087 0.8993
No log 7.6154 396 0.8738 0.4557 0.8738 0.9348
No log 7.6538 398 0.8859 0.3927 0.8859 0.9412
No log 7.6923 400 0.8289 0.3517 0.8289 0.9105
No log 7.7308 402 0.8213 0.3596 0.8213 0.9063
No log 7.7692 404 0.8744 0.4231 0.8744 0.9351
No log 7.8077 406 0.8970 0.4343 0.8970 0.9471
No log 7.8462 408 0.8569 0.4359 0.8569 0.9257
No log 7.8846 410 0.8073 0.4378 0.8073 0.8985
No log 7.9231 412 0.8095 0.4455 0.8095 0.8997
No log 7.9615 414 0.8226 0.3855 0.8226 0.9070
No log 8.0 416 0.8476 0.4115 0.8476 0.9207
No log 8.0385 418 0.8650 0.4234 0.8650 0.9300
No log 8.0769 420 0.8587 0.3697 0.8587 0.9267
No log 8.1154 422 0.8148 0.3717 0.8148 0.9027
No log 8.1538 424 0.8016 0.3356 0.8016 0.8953
No log 8.1923 426 0.7856 0.3356 0.7856 0.8863
No log 8.2308 428 0.7747 0.3596 0.7747 0.8802
No log 8.2692 430 0.7935 0.4251 0.7935 0.8908
No log 8.3077 432 0.7984 0.4251 0.7984 0.8935
No log 8.3462 434 0.7956 0.4251 0.7956 0.8920
No log 8.3846 436 0.7982 0.4743 0.7982 0.8934
No log 8.4231 438 0.7714 0.4395 0.7714 0.8783
No log 8.4615 440 0.7670 0.4527 0.7670 0.8758
No log 8.5 442 0.7701 0.3642 0.7701 0.8776
No log 8.5385 444 0.7799 0.3915 0.7799 0.8831
No log 8.5769 446 0.7839 0.3056 0.7839 0.8854
No log 8.6154 448 0.8198 0.4378 0.8198 0.9054
No log 8.6538 450 0.8476 0.4361 0.8476 0.9206
No log 8.6923 452 0.8357 0.4261 0.8357 0.9142
No log 8.7308 454 0.8131 0.3878 0.8131 0.9017
No log 8.7692 456 0.8055 0.3878 0.8055 0.8975
No log 8.8077 458 0.8106 0.3878 0.8106 0.9003
No log 8.8462 460 0.8299 0.4115 0.8299 0.9110
No log 8.8846 462 0.9024 0.4350 0.9024 0.9500
No log 8.9231 464 0.9466 0.4094 0.9466 0.9729
No log 8.9615 466 0.8792 0.4599 0.8792 0.9377
No log 9.0 468 0.8194 0.3977 0.8194 0.9052
No log 9.0385 470 0.8116 0.3859 0.8116 0.9009
No log 9.0769 472 0.8163 0.3685 0.8163 0.9035
No log 9.1154 474 0.8213 0.3544 0.8213 0.9062
No log 9.1538 476 0.8202 0.3544 0.8202 0.9056
No log 9.1923 478 0.8218 0.3215 0.8218 0.9065
No log 9.2308 480 0.8491 0.3697 0.8491 0.9215
No log 9.2692 482 0.9082 0.3921 0.9082 0.9530
No log 9.3077 484 0.9306 0.3782 0.9306 0.9647
No log 9.3462 486 0.9027 0.3780 0.9027 0.9501
No log 9.3846 488 0.8448 0.3388 0.8448 0.9191
No log 9.4231 490 0.8401 0.3271 0.8401 0.9165
No log 9.4615 492 0.8512 0.3532 0.8512 0.9226
No log 9.5 494 0.8481 0.3666 0.8481 0.9209
No log 9.5385 496 0.8484 0.3323 0.8484 0.9211
No log 9.5769 498 0.8405 0.3323 0.8405 0.9168
0.2902 9.6154 500 0.8369 0.3697 0.8369 0.9148
0.2902 9.6538 502 0.8506 0.3819 0.8506 0.9223
0.2902 9.6923 504 0.8519 0.3941 0.8519 0.9230
0.2902 9.7308 506 0.8482 0.3941 0.8482 0.9210
0.2902 9.7692 508 0.8596 0.3941 0.8596 0.9272
0.2902 9.8077 510 0.8808 0.3941 0.8808 0.9385
0.2902 9.8462 512 0.8719 0.3652 0.8719 0.9338
0.2902 9.8846 514 0.8662 0.3652 0.8662 0.9307
0.2902 9.9231 516 0.8516 0.3280 0.8516 0.9228
0.2902 9.9615 518 0.8431 0.3033 0.8431 0.9182
0.2902 10.0 520 0.8475 0.3280 0.8475 0.9206

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k11_task5_organization

Finetuned
(4040)
this model