ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k15_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: 1.0823
  • Qwk: 0.3505
  • Mse: 1.0823
  • Rmse: 1.0403

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 0.0267 2 4.7544 -0.0020 4.7544 2.1805
No log 0.0533 4 2.5325 -0.0124 2.5325 1.5914
No log 0.08 6 1.7604 0.0198 1.7604 1.3268
No log 0.1067 8 1.6474 0.0263 1.6474 1.2835
No log 0.1333 10 1.2785 0.1598 1.2785 1.1307
No log 0.16 12 1.4547 0.1334 1.4547 1.2061
No log 0.1867 14 2.2471 0.1026 2.2471 1.4990
No log 0.2133 16 1.6534 0.1223 1.6534 1.2858
No log 0.24 18 1.1113 0.1507 1.1113 1.0542
No log 0.2667 20 1.1337 0.1196 1.1337 1.0648
No log 0.2933 22 1.1693 0.0926 1.1693 1.0813
No log 0.32 24 1.2078 0.2644 1.2078 1.0990
No log 0.3467 26 1.1591 0.2149 1.1591 1.0766
No log 0.3733 28 1.0773 0.2936 1.0773 1.0380
No log 0.4 30 1.0844 0.2537 1.0844 1.0413
No log 0.4267 32 1.1223 0.2687 1.1223 1.0594
No log 0.4533 34 1.1638 0.2298 1.1638 1.0788
No log 0.48 36 1.3122 0.0426 1.3122 1.1455
No log 0.5067 38 1.4210 0.0426 1.4210 1.1920
No log 0.5333 40 1.5106 0.0723 1.5106 1.2291
No log 0.56 42 1.3762 0.0426 1.3762 1.1731
No log 0.5867 44 1.2397 0.0758 1.2397 1.1134
No log 0.6133 46 1.1867 0.1584 1.1867 1.0894
No log 0.64 48 1.3006 0.0723 1.3006 1.1404
No log 0.6667 50 1.2177 0.1051 1.2177 1.1035
No log 0.6933 52 1.2120 0.1051 1.2120 1.1009
No log 0.72 54 1.0643 0.2912 1.0643 1.0316
No log 0.7467 56 1.0438 0.3250 1.0438 1.0216
No log 0.7733 58 1.2383 0.1625 1.2383 1.1128
No log 0.8 60 1.5093 0.2129 1.5093 1.2285
No log 0.8267 62 1.6916 0.2925 1.6916 1.3006
No log 0.8533 64 1.3787 0.3081 1.3787 1.1742
No log 0.88 66 1.1148 0.3959 1.1148 1.0559
No log 0.9067 68 0.8955 0.4400 0.8955 0.9463
No log 0.9333 70 0.8987 0.4 0.8987 0.9480
No log 0.96 72 1.0302 0.3881 1.0302 1.0150
No log 0.9867 74 1.7862 0.3247 1.7862 1.3365
No log 1.0133 76 2.2116 0.1940 2.2116 1.4872
No log 1.04 78 1.9863 0.2580 1.9863 1.4094
No log 1.0667 80 1.3694 0.3020 1.3694 1.1702
No log 1.0933 82 0.8711 0.4617 0.8711 0.9333
No log 1.12 84 0.9418 0.4200 0.9418 0.9704
No log 1.1467 86 0.9147 0.4201 0.9147 0.9564
No log 1.1733 88 0.8563 0.4555 0.8563 0.9253
No log 1.2 90 0.9627 0.3839 0.9627 0.9812
No log 1.2267 92 1.3137 0.3269 1.3137 1.1462
No log 1.2533 94 1.7078 0.3221 1.7078 1.3068
No log 1.28 96 1.7649 0.3106 1.7649 1.3285
No log 1.3067 98 1.4317 0.3850 1.4317 1.1965
No log 1.3333 100 0.9522 0.4890 0.9522 0.9758
No log 1.3600 102 0.8176 0.5010 0.8176 0.9042
No log 1.3867 104 0.8992 0.3616 0.8992 0.9482
No log 1.4133 106 0.8974 0.3708 0.8974 0.9473
No log 1.44 108 1.0378 0.3237 1.0378 1.0187
No log 1.4667 110 1.5655 0.3522 1.5655 1.2512
No log 1.4933 112 1.8140 0.2683 1.8140 1.3469
No log 1.52 114 1.6930 0.2857 1.6930 1.3012
No log 1.5467 116 1.3518 0.2677 1.3518 1.1627
No log 1.5733 118 1.0044 0.3765 1.0044 1.0022
No log 1.6 120 0.9718 0.4237 0.9718 0.9858
No log 1.6267 122 0.9883 0.3854 0.9883 0.9942
No log 1.6533 124 0.9668 0.3705 0.9668 0.9833
No log 1.6800 126 1.0702 0.2654 1.0702 1.0345
No log 1.7067 128 1.1192 0.2424 1.1192 1.0579
No log 1.7333 130 1.1468 0.2807 1.1468 1.0709
No log 1.76 132 0.9753 0.3780 0.9753 0.9876
No log 1.7867 134 0.9758 0.3546 0.9758 0.9878
No log 1.8133 136 0.9796 0.4356 0.9796 0.9897
No log 1.8400 138 0.9473 0.3987 0.9473 0.9733
No log 1.8667 140 1.0081 0.4156 1.0081 1.0041
No log 1.8933 142 0.9809 0.3875 0.9809 0.9904
No log 1.92 144 0.9726 0.4373 0.9726 0.9862
No log 1.9467 146 0.9888 0.4016 0.9888 0.9944
No log 1.9733 148 0.9715 0.3643 0.9715 0.9856
No log 2.0 150 0.9503 0.3371 0.9503 0.9748
No log 2.0267 152 0.9926 0.4489 0.9926 0.9963
No log 2.0533 154 1.0184 0.4648 1.0184 1.0091
No log 2.08 156 1.0113 0.4522 1.0113 1.0057
No log 2.1067 158 1.0310 0.4402 1.0310 1.0154
No log 2.1333 160 0.9947 0.4361 0.9947 0.9973
No log 2.16 162 1.0352 0.3412 1.0352 1.0174
No log 2.1867 164 1.0247 0.2871 1.0247 1.0123
No log 2.2133 166 1.0323 0.2647 1.0323 1.0160
No log 2.24 168 1.0896 0.2588 1.0896 1.0439
No log 2.2667 170 1.1635 0.3121 1.1635 1.0787
No log 2.2933 172 1.1803 0.3121 1.1803 1.0864
No log 2.32 174 1.1484 0.3266 1.1484 1.0716
No log 2.3467 176 1.1179 0.3760 1.1179 1.0573
No log 2.3733 178 1.1159 0.3611 1.1159 1.0564
No log 2.4 180 1.1183 0.3260 1.1183 1.0575
No log 2.4267 182 1.2722 0.3926 1.2722 1.1279
No log 2.4533 184 1.6223 0.2589 1.6223 1.2737
No log 2.48 186 1.6461 0.2375 1.6461 1.2830
No log 2.5067 188 1.3611 0.3875 1.3611 1.1667
No log 2.5333 190 1.1140 0.3627 1.1140 1.0555
No log 2.56 192 1.0472 0.3403 1.0472 1.0233
No log 2.5867 194 1.0403 0.3286 1.0403 1.0199
No log 2.6133 196 1.0175 0.3619 1.0175 1.0087
No log 2.64 198 1.0848 0.3494 1.0848 1.0415
No log 2.6667 200 1.2326 0.2851 1.2326 1.1102
No log 2.6933 202 1.1959 0.2705 1.1959 1.0936
No log 2.7200 204 1.0959 0.2766 1.0959 1.0468
No log 2.7467 206 1.0302 0.3365 1.0302 1.0150
No log 2.7733 208 1.0259 0.3184 1.0259 1.0129
No log 2.8 210 1.1029 0.3193 1.1029 1.0502
No log 2.8267 212 1.3986 0.2830 1.3986 1.1826
No log 2.8533 214 1.7496 0.2088 1.7496 1.3227
No log 2.88 216 1.8415 0.2218 1.8415 1.3570
No log 2.9067 218 1.6324 0.2366 1.6324 1.2777
No log 2.9333 220 1.4471 0.2576 1.4471 1.2029
No log 2.96 222 1.2486 0.3307 1.2486 1.1174
No log 2.9867 224 1.2091 0.3249 1.2091 1.0996
No log 3.0133 226 1.2581 0.3511 1.2581 1.1216
No log 3.04 228 1.3256 0.3440 1.3256 1.1513
No log 3.0667 230 1.2014 0.3561 1.2014 1.0961
No log 3.0933 232 1.0427 0.3321 1.0427 1.0211
No log 3.12 234 1.0087 0.2694 1.0087 1.0043
No log 3.1467 236 1.0453 0.3975 1.0453 1.0224
No log 3.1733 238 1.0290 0.2625 1.0290 1.0144
No log 3.2 240 1.0105 0.2567 1.0105 1.0052
No log 3.2267 242 1.0195 0.2567 1.0195 1.0097
No log 3.2533 244 1.0186 0.2417 1.0186 1.0092
No log 3.2800 246 1.0260 0.2993 1.0260 1.0129
No log 3.3067 248 1.0348 0.2993 1.0348 1.0172
No log 3.3333 250 1.0428 0.3371 1.0428 1.0212
No log 3.36 252 1.0352 0.3085 1.0352 1.0174
No log 3.3867 254 1.0221 0.3085 1.0221 1.0110
No log 3.4133 256 1.0179 0.3036 1.0179 1.0089
No log 3.44 258 0.9943 0.2871 0.9943 0.9971
No log 3.4667 260 0.9670 0.3415 0.9670 0.9833
No log 3.4933 262 0.9583 0.3137 0.9583 0.9789
No log 3.52 264 0.9482 0.2941 0.9482 0.9738
No log 3.5467 266 0.9548 0.2963 0.9548 0.9771
No log 3.5733 268 0.9621 0.3036 0.9621 0.9809
No log 3.6 270 0.9541 0.3085 0.9541 0.9768
No log 3.6267 272 0.9657 0.3085 0.9657 0.9827
No log 3.6533 274 0.9851 0.3756 0.9851 0.9925
No log 3.68 276 0.9968 0.2993 0.9968 0.9984
No log 3.7067 278 1.0440 0.3877 1.0440 1.0218
No log 3.7333 280 1.0839 0.4157 1.0839 1.0411
No log 3.76 282 1.0230 0.3395 1.0230 1.0114
No log 3.7867 284 1.0463 0.3716 1.0463 1.0229
No log 3.8133 286 1.1498 0.3600 1.1498 1.0723
No log 3.84 288 1.1633 0.3271 1.1633 1.0785
No log 3.8667 290 1.0837 0.3299 1.0837 1.0410
No log 3.8933 292 1.0073 0.3263 1.0073 1.0037
No log 3.92 294 1.0126 0.2550 1.0126 1.0063
No log 3.9467 296 1.0423 0.2588 1.0423 1.0209
No log 3.9733 298 1.0349 0.2776 1.0349 1.0173
No log 4.0 300 1.0056 0.3159 1.0056 1.0028
No log 4.0267 302 1.0221 0.2728 1.0221 1.0110
No log 4.0533 304 1.0751 0.3902 1.0751 1.0369
No log 4.08 306 1.0162 0.2728 1.0162 1.0081
No log 4.1067 308 0.9986 0.3180 0.9986 0.9993
No log 4.1333 310 1.0231 0.4202 1.0231 1.0115
No log 4.16 312 1.0354 0.4202 1.0354 1.0176
No log 4.1867 314 1.0255 0.2822 1.0255 1.0127
No log 4.2133 316 1.0312 0.3159 1.0312 1.0155
No log 4.24 318 1.0544 0.3463 1.0544 1.0268
No log 4.2667 320 1.0667 0.3312 1.0667 1.0328
No log 4.2933 322 1.0514 0.2966 1.0514 1.0254
No log 4.32 324 1.0341 0.2775 1.0341 1.0169
No log 4.3467 326 1.0401 0.3733 1.0401 1.0198
No log 4.3733 328 1.0800 0.3126 1.0800 1.0392
No log 4.4 330 1.1510 0.3007 1.1510 1.0728
No log 4.4267 332 1.1242 0.2732 1.1242 1.0603
No log 4.4533 334 1.0286 0.3427 1.0286 1.0142
No log 4.48 336 1.0195 0.2692 1.0195 1.0097
No log 4.5067 338 1.0227 0.2468 1.0227 1.0113
No log 4.5333 340 1.0271 0.2803 1.0271 1.0135
No log 4.5600 342 1.0401 0.2944 1.0401 1.0198
No log 4.5867 344 1.0628 0.3681 1.0628 1.0309
No log 4.6133 346 1.1328 0.2544 1.1328 1.0643
No log 4.64 348 1.1715 0.2732 1.1715 1.0824
No log 4.6667 350 1.1467 0.2593 1.1467 1.0708
No log 4.6933 352 1.0556 0.3427 1.0556 1.0274
No log 4.72 354 1.0325 0.3137 1.0325 1.0161
No log 4.7467 356 1.0170 0.3399 1.0170 1.0084
No log 4.7733 358 1.0044 0.3788 1.0044 1.0022
No log 4.8 360 0.9919 0.4026 0.9919 0.9959
No log 4.8267 362 0.9929 0.4197 0.9929 0.9965
No log 4.8533 364 0.9950 0.4102 0.9950 0.9975
No log 4.88 366 0.9654 0.4159 0.9654 0.9826
No log 4.9067 368 0.9595 0.4159 0.9595 0.9795
No log 4.9333 370 1.0122 0.3993 1.0122 1.0061
No log 4.96 372 1.0030 0.3862 1.0030 1.0015
No log 4.9867 374 1.0327 0.3980 1.0327 1.0162
No log 5.0133 376 0.9996 0.3859 0.9996 0.9998
No log 5.04 378 0.9435 0.4048 0.9435 0.9713
No log 5.0667 380 0.9846 0.4328 0.9846 0.9923
No log 5.0933 382 0.9776 0.3613 0.9776 0.9887
No log 5.12 384 0.9331 0.4278 0.9331 0.9660
No log 5.1467 386 0.9365 0.3738 0.9365 0.9677
No log 5.1733 388 0.9417 0.3780 0.9417 0.9704
No log 5.2 390 0.9232 0.4219 0.9232 0.9608
No log 5.2267 392 0.9264 0.3908 0.9264 0.9625
No log 5.2533 394 0.9234 0.4181 0.9234 0.9610
No log 5.28 396 0.9200 0.3639 0.9200 0.9592
No log 5.3067 398 0.9841 0.3689 0.9841 0.9920
No log 5.3333 400 1.1056 0.3005 1.1056 1.0515
No log 5.36 402 1.1317 0.2982 1.1317 1.0638
No log 5.3867 404 1.0609 0.3357 1.0609 1.0300
No log 5.4133 406 0.9493 0.4371 0.9493 0.9743
No log 5.44 408 0.9227 0.3354 0.9227 0.9606
No log 5.4667 410 0.9544 0.4108 0.9544 0.9769
No log 5.4933 412 0.9892 0.4513 0.9892 0.9946
No log 5.52 414 0.9638 0.3018 0.9638 0.9817
No log 5.5467 416 0.9664 0.3408 0.9664 0.9830
No log 5.5733 418 0.9728 0.3408 0.9728 0.9863
No log 5.6 420 0.9743 0.2763 0.9743 0.9871
No log 5.6267 422 0.9963 0.3365 0.9963 0.9981
No log 5.6533 424 0.9969 0.3365 0.9969 0.9984
No log 5.68 426 0.9685 0.2763 0.9685 0.9841
No log 5.7067 428 0.9709 0.3217 0.9709 0.9853
No log 5.7333 430 0.9787 0.3478 0.9787 0.9893
No log 5.76 432 0.9660 0.3478 0.9660 0.9829
No log 5.7867 434 0.9441 0.3354 0.9441 0.9717
No log 5.8133 436 0.9906 0.4039 0.9906 0.9953
No log 5.84 438 1.0434 0.3339 1.0434 1.0215
No log 5.8667 440 1.0274 0.3280 1.0274 1.0136
No log 5.8933 442 0.9780 0.4136 0.9780 0.9889
No log 5.92 444 0.9624 0.4331 0.9624 0.9810
No log 5.9467 446 0.9481 0.3965 0.9481 0.9737
No log 5.9733 448 0.9511 0.3925 0.9511 0.9752
No log 6.0 450 0.9669 0.3965 0.9669 0.9833
No log 6.0267 452 0.9948 0.3614 0.9948 0.9974
No log 6.0533 454 1.0016 0.3571 1.0016 1.0008
No log 6.08 456 0.9870 0.3090 0.9870 0.9935
No log 6.1067 458 0.9784 0.3453 0.9784 0.9891
No log 6.1333 460 0.9668 0.3113 0.9668 0.9833
No log 6.16 462 0.9615 0.3090 0.9615 0.9805
No log 6.1867 464 0.9756 0.3596 0.9756 0.9877
No log 6.2133 466 1.0056 0.3169 1.0056 1.0028
No log 6.24 468 1.0034 0.3069 1.0034 1.0017
No log 6.2667 470 0.9841 0.3045 0.9841 0.9920
No log 6.2933 472 0.9681 0.3147 0.9681 0.9839
No log 6.32 474 0.9362 0.3190 0.9362 0.9676
No log 6.3467 476 0.9334 0.4016 0.9334 0.9661
No log 6.3733 478 0.9293 0.4016 0.9293 0.9640
No log 6.4 480 0.9201 0.3539 0.9201 0.9592
No log 6.4267 482 0.9194 0.3094 0.9194 0.9589
No log 6.4533 484 0.9045 0.4181 0.9045 0.9511
No log 6.48 486 0.8955 0.3879 0.8955 0.9463
No log 6.5067 488 0.9782 0.3169 0.9782 0.9890
No log 6.5333 490 1.1884 0.3656 1.1884 1.0901
No log 6.5600 492 1.2359 0.3656 1.2359 1.1117
No log 6.5867 494 1.1107 0.3537 1.1107 1.0539
No log 6.6133 496 0.9548 0.3821 0.9548 0.9771
No log 6.64 498 0.9317 0.3796 0.9317 0.9653
0.3751 6.6667 500 0.9458 0.3663 0.9458 0.9725
0.3751 6.6933 502 0.9493 0.3354 0.9493 0.9743
0.3751 6.72 504 1.0314 0.3505 1.0314 1.0156
0.3751 6.7467 506 1.1021 0.3295 1.1021 1.0498
0.3751 6.7733 508 1.1207 0.3218 1.1207 1.0586
0.3751 6.8 510 1.0823 0.3505 1.0823 1.0403

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
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_run2_AugV5_k15_task2_organization

Finetuned
(4033)
this model