ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k5_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: 1.0244
  • Qwk: 0.2695
  • Mse: 1.0244
  • Rmse: 1.0121

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 0.0833 2 4.2579 -0.0020 4.2579 2.0635
No log 0.1667 4 2.4860 0.0052 2.4860 1.5767
No log 0.25 6 2.1336 -0.0166 2.1336 1.4607
No log 0.3333 8 1.3261 0.1406 1.3261 1.1515
No log 0.4167 10 1.0860 0.2515 1.0860 1.0421
No log 0.5 12 1.0134 0.2541 1.0134 1.0067
No log 0.5833 14 0.9918 0.2239 0.9918 0.9959
No log 0.6667 16 1.0376 0.2015 1.0376 1.0187
No log 0.75 18 1.0465 0.375 1.0465 1.0230
No log 0.8333 20 1.1084 0.1711 1.1084 1.0528
No log 0.9167 22 1.1604 0.1205 1.1604 1.0772
No log 1.0 24 1.0510 0.2465 1.0510 1.0252
No log 1.0833 26 0.9700 0.3688 0.9700 0.9849
No log 1.1667 28 0.9783 0.2818 0.9783 0.9891
No log 1.25 30 0.9753 0.2667 0.9753 0.9876
No log 1.3333 32 0.9563 0.3243 0.9563 0.9779
No log 1.4167 34 1.0316 0.2049 1.0316 1.0157
No log 1.5 36 1.3343 0.0883 1.3343 1.1551
No log 1.5833 38 1.4394 0.1354 1.4394 1.1998
No log 1.6667 40 1.2378 0.1602 1.2378 1.1126
No log 1.75 42 1.0351 0.2857 1.0351 1.0174
No log 1.8333 44 1.0498 0.2865 1.0498 1.0246
No log 1.9167 46 0.9982 0.2276 0.9982 0.9991
No log 2.0 48 0.9774 0.2572 0.9774 0.9886
No log 2.0833 50 0.9612 0.2572 0.9612 0.9804
No log 2.1667 52 1.0291 0.2670 1.0291 1.0144
No log 2.25 54 1.3148 0.0620 1.3148 1.1466
No log 2.3333 56 1.8065 0.0254 1.8065 1.3441
No log 2.4167 58 2.2653 -0.1852 2.2653 1.5051
No log 2.5 60 2.0636 -0.1397 2.0636 1.4365
No log 2.5833 62 1.6119 0.0225 1.6119 1.2696
No log 2.6667 64 1.7522 -0.0049 1.7522 1.3237
No log 2.75 66 2.2155 -0.2161 2.2155 1.4885
No log 2.8333 68 1.9738 -0.1322 1.9738 1.4049
No log 2.9167 70 1.4360 0.0630 1.4360 1.1983
No log 3.0 72 0.9840 0.3445 0.9840 0.9920
No log 3.0833 74 0.9176 0.2670 0.9176 0.9579
No log 3.1667 76 1.0053 0.2596 1.0053 1.0027
No log 3.25 78 1.1078 0.2171 1.1078 1.0525
No log 3.3333 80 1.3048 0.1658 1.3048 1.1423
No log 3.4167 82 1.3197 0.1067 1.3197 1.1488
No log 3.5 84 1.2009 0.1036 1.2009 1.0959
No log 3.5833 86 1.2140 0.1703 1.2140 1.1018
No log 3.6667 88 1.2090 0.1337 1.2090 1.0995
No log 3.75 90 1.2261 0.1570 1.2261 1.1073
No log 3.8333 92 1.1343 0.2744 1.1343 1.0651
No log 3.9167 94 1.0983 0.3706 1.0983 1.0480
No log 4.0 96 1.1496 0.2516 1.1496 1.0722
No log 4.0833 98 1.0541 0.3682 1.0541 1.0267
No log 4.1667 100 1.0155 0.2818 1.0155 1.0077
No log 4.25 102 1.0851 0.2600 1.0851 1.0417
No log 4.3333 104 1.1871 0.2323 1.1871 1.0895
No log 4.4167 106 1.2381 0.2040 1.2381 1.1127
No log 4.5 108 1.4914 0.0509 1.4914 1.2212
No log 4.5833 110 1.5953 0.0538 1.5953 1.2630
No log 4.6667 112 1.4686 0.0602 1.4686 1.2118
No log 4.75 114 1.3282 0.1179 1.3282 1.1525
No log 4.8333 116 1.4421 0.0602 1.4421 1.2009
No log 4.9167 118 1.5685 0.0486 1.5685 1.2524
No log 5.0 120 1.7435 -0.0289 1.7435 1.3204
No log 5.0833 122 1.7892 0.0044 1.7892 1.3376
No log 5.1667 124 1.7190 0.0545 1.7190 1.3111
No log 5.25 126 1.5996 0.0638 1.5996 1.2648
No log 5.3333 128 1.4349 0.1174 1.4349 1.1979
No log 5.4167 130 1.3413 0.0685 1.3413 1.1581
No log 5.5 132 1.4990 0.0531 1.4990 1.2243
No log 5.5833 134 1.5021 0.0292 1.5021 1.2256
No log 5.6667 136 1.3424 0.1269 1.3424 1.1586
No log 5.75 138 1.1675 0.1935 1.1675 1.0805
No log 5.8333 140 1.0677 0.1616 1.0677 1.0333
No log 5.9167 142 1.0676 0.1997 1.0676 1.0332
No log 6.0 144 1.1130 0.1603 1.1130 1.0550
No log 6.0833 146 1.1680 0.1637 1.1680 1.0807
No log 6.1667 148 1.1741 0.1961 1.1741 1.0836
No log 6.25 150 1.1148 0.3151 1.1148 1.0558
No log 6.3333 152 1.0757 0.3563 1.0757 1.0372
No log 6.4167 154 1.1396 0.3182 1.1396 1.0675
No log 6.5 156 1.2051 0.2395 1.2051 1.0978
No log 6.5833 158 1.1939 0.2118 1.1939 1.0926
No log 6.6667 160 1.2279 0.1442 1.2279 1.1081
No log 6.75 162 1.3073 0.1805 1.3073 1.1434
No log 6.8333 164 1.2355 0.1778 1.2355 1.1115
No log 6.9167 166 1.1001 0.2229 1.1001 1.0488
No log 7.0 168 1.0943 0.2057 1.0943 1.0461
No log 7.0833 170 1.0829 0.1909 1.0829 1.0406
No log 7.1667 172 1.1073 0.1426 1.1073 1.0523
No log 7.25 174 1.1251 0.1573 1.1251 1.0607
No log 7.3333 176 1.1656 0.1532 1.1656 1.0796
No log 7.4167 178 1.2344 0.1725 1.2344 1.1111
No log 7.5 180 1.2856 0.1118 1.2856 1.1338
No log 7.5833 182 1.1816 0.1333 1.1816 1.0870
No log 7.6667 184 1.0585 0.1961 1.0585 1.0288
No log 7.75 186 1.0238 0.2842 1.0238 1.0118
No log 7.8333 188 1.0446 0.2909 1.0446 1.0220
No log 7.9167 190 1.1387 0.2970 1.1387 1.0671
No log 8.0 192 1.1644 0.2702 1.1644 1.0791
No log 8.0833 194 1.0877 0.2951 1.0877 1.0429
No log 8.1667 196 1.0364 0.2842 1.0364 1.0180
No log 8.25 198 1.0069 0.2316 1.0069 1.0034
No log 8.3333 200 1.0128 0.2341 1.0128 1.0064
No log 8.4167 202 1.0248 0.2015 1.0248 1.0123
No log 8.5 204 1.0407 0.2742 1.0407 1.0201
No log 8.5833 206 1.0821 0.2931 1.0821 1.0402
No log 8.6667 208 1.1264 0.2499 1.1264 1.0613
No log 8.75 210 1.1104 0.3087 1.1104 1.0538
No log 8.8333 212 0.9966 0.3326 0.9966 0.9983
No log 8.9167 214 0.9335 0.2133 0.9335 0.9662
No log 9.0 216 0.9216 0.2133 0.9216 0.9600
No log 9.0833 218 0.9465 0.2742 0.9465 0.9729
No log 9.1667 220 1.0080 0.3326 1.0080 1.0040
No log 9.25 222 1.0419 0.3048 1.0419 1.0207
No log 9.3333 224 1.1051 0.4102 1.1051 1.0513
No log 9.4167 226 1.0534 0.3806 1.0534 1.0263
No log 9.5 228 1.0164 0.3806 1.0164 1.0081
No log 9.5833 230 1.0277 0.3824 1.0277 1.0137
No log 9.6667 232 1.0604 0.3974 1.0604 1.0298
No log 9.75 234 1.0153 0.3860 1.0153 1.0076
No log 9.8333 236 0.9958 0.3326 0.9958 0.9979
No log 9.9167 238 1.0061 0.2528 1.0061 1.0031
No log 10.0 240 1.0362 0.2528 1.0362 1.0179
No log 10.0833 242 1.0535 0.2456 1.0535 1.0264
No log 10.1667 244 1.0604 0.2857 1.0604 1.0298
No log 10.25 246 1.0449 0.2857 1.0449 1.0222
No log 10.3333 248 1.0328 0.2456 1.0328 1.0163
No log 10.4167 250 1.0362 0.2440 1.0362 1.0179
No log 10.5 252 1.0683 0.2633 1.0683 1.0336
No log 10.5833 254 1.0706 0.2633 1.0706 1.0347
No log 10.6667 256 1.0920 0.2633 1.0920 1.0450
No log 10.75 258 1.1041 0.2766 1.1041 1.0508
No log 10.8333 260 1.0871 0.2786 1.0871 1.0426
No log 10.9167 262 1.1365 0.2220 1.1365 1.0661
No log 11.0 264 1.1965 0.1379 1.1965 1.0938
No log 11.0833 266 1.1943 0.1379 1.1943 1.0928
No log 11.1667 268 1.1232 0.2716 1.1232 1.0598
No log 11.25 270 1.0761 0.2602 1.0761 1.0374
No log 11.3333 272 1.0929 0.2766 1.0929 1.0454
No log 11.4167 274 1.0492 0.2766 1.0492 1.0243
No log 11.5 276 0.9701 0.3194 0.9701 0.9849
No log 11.5833 278 0.9497 0.2835 0.9497 0.9745
No log 11.6667 280 0.9609 0.3172 0.9609 0.9802
No log 11.75 282 1.0347 0.3463 1.0347 1.0172
No log 11.8333 284 1.0848 0.3584 1.0848 1.0415
No log 11.9167 286 1.1029 0.3954 1.1029 1.0502
No log 12.0 288 1.0144 0.4089 1.0144 1.0072
No log 12.0833 290 0.9258 0.3052 0.9258 0.9622
No log 12.1667 292 0.9118 0.2835 0.9118 0.9549
No log 12.25 294 0.9176 0.3215 0.9176 0.9579
No log 12.3333 296 0.9206 0.3194 0.9206 0.9595
No log 12.4167 298 0.9192 0.3194 0.9192 0.9588
No log 12.5 300 0.9525 0.3879 0.9525 0.9760
No log 12.5833 302 1.0285 0.3973 1.0285 1.0142
No log 12.6667 304 1.0578 0.3957 1.0578 1.0285
No log 12.75 306 1.1019 0.3806 1.1019 1.0497
No log 12.8333 308 1.1158 0.3806 1.1158 1.0563
No log 12.9167 310 1.1412 0.3672 1.1412 1.0683
No log 13.0 312 1.1810 0.3539 1.1810 1.0867
No log 13.0833 314 1.1250 0.3806 1.1250 1.0607
No log 13.1667 316 1.0227 0.3188 1.0227 1.0113
No log 13.25 318 0.9889 0.2602 0.9889 0.9944
No log 13.3333 320 0.9839 0.2602 0.9839 0.9919
No log 13.4167 322 0.9774 0.2741 0.9774 0.9886
No log 13.5 324 0.9829 0.3513 0.9829 0.9914
No log 13.5833 326 1.0274 0.3878 1.0274 1.0136
No log 13.6667 328 1.0886 0.3706 1.0886 1.0434
No log 13.75 330 1.1218 0.3167 1.1218 1.0591
No log 13.8333 332 1.0807 0.2624 1.0807 1.0396
No log 13.9167 334 1.0520 0.2473 1.0520 1.0257
No log 14.0 336 1.0434 0.2108 1.0434 1.0215
No log 14.0833 338 1.0541 0.1961 1.0541 1.0267
No log 14.1667 340 1.0589 0.2254 1.0589 1.0290
No log 14.25 342 1.0662 0.2254 1.0662 1.0326
No log 14.3333 344 1.0581 0.2254 1.0581 1.0286
No log 14.4167 346 1.0615 0.2158 1.0615 1.0303
No log 14.5 348 1.0098 0.2229 1.0098 1.0049
No log 14.5833 350 0.9795 0.3112 0.9795 0.9897
No log 14.6667 352 0.9877 0.3129 0.9877 0.9938
No log 14.75 354 1.0285 0.3921 1.0285 1.0141
No log 14.8333 356 1.0930 0.3953 1.0930 1.0455
No log 14.9167 358 1.1635 0.3619 1.1635 1.0787
No log 15.0 360 1.1803 0.3744 1.1803 1.0864
No log 15.0833 362 1.1137 0.3864 1.1137 1.0553
No log 15.1667 364 1.0704 0.3546 1.0704 1.0346
No log 15.25 366 1.0728 0.3787 1.0728 1.0358
No log 15.3333 368 1.0015 0.3957 1.0015 1.0008
No log 15.4167 370 0.9955 0.3957 0.9955 0.9977
No log 15.5 372 0.9717 0.3939 0.9717 0.9857
No log 15.5833 374 0.9552 0.3958 0.9552 0.9773
No log 15.6667 376 0.9484 0.3976 0.9484 0.9739
No log 15.75 378 0.9691 0.3958 0.9691 0.9844
No log 15.8333 380 0.9743 0.3958 0.9743 0.9871
No log 15.9167 382 0.9658 0.4093 0.9658 0.9828
No log 16.0 384 0.9540 0.3563 0.9540 0.9767
No log 16.0833 386 0.9600 0.3939 0.9600 0.9798
No log 16.1667 388 1.0135 0.3804 1.0135 1.0067
No log 16.25 390 1.1096 0.3371 1.1096 1.0534
No log 16.3333 392 1.1226 0.3371 1.1226 1.0595
No log 16.4167 394 1.0249 0.3842 1.0249 1.0124
No log 16.5 396 0.9494 0.3272 0.9494 0.9744
No log 16.5833 398 0.9154 0.3817 0.9154 0.9568
No log 16.6667 400 0.9051 0.3425 0.9051 0.9514
No log 16.75 402 0.9153 0.3697 0.9153 0.9567
No log 16.8333 404 0.9400 0.3424 0.9400 0.9695
No log 16.9167 406 0.9588 0.3523 0.9588 0.9792
No log 17.0 408 1.0032 0.3103 1.0032 1.0016
No log 17.0833 410 1.0611 0.3140 1.0611 1.0301
No log 17.1667 412 1.0550 0.2865 1.0550 1.0271
No log 17.25 414 0.9983 0.3129 0.9983 0.9991
No log 17.3333 416 0.9693 0.3548 0.9693 0.9846
No log 17.4167 418 0.9954 0.2503 0.9954 0.9977
No log 17.5 420 1.0027 0.2503 1.0027 1.0014
No log 17.5833 422 0.9795 0.3291 0.9795 0.9897
No log 17.6667 424 0.9477 0.3661 0.9477 0.9735
No log 17.75 426 0.9490 0.3838 0.9490 0.9742
No log 17.8333 428 0.9836 0.3861 0.9836 0.9918
No log 17.9167 430 1.0475 0.3989 1.0475 1.0235
No log 18.0 432 1.0762 0.3989 1.0762 1.0374
No log 18.0833 434 1.0511 0.3732 1.0511 1.0252
No log 18.1667 436 0.9887 0.2986 0.9887 0.9943
No log 18.25 438 0.9487 0.2695 0.9487 0.9740
No log 18.3333 440 0.9258 0.3112 0.9258 0.9622
No log 18.4167 442 0.9178 0.3236 0.9178 0.9580
No log 18.5 444 0.9517 0.4209 0.9517 0.9755
No log 18.5833 446 1.0361 0.3806 1.0361 1.0179
No log 18.6667 448 1.1112 0.3827 1.1112 1.0541
No log 18.75 450 1.0921 0.3845 1.0921 1.0450
No log 18.8333 452 1.0085 0.3454 1.0085 1.0043
No log 18.9167 454 0.9548 0.3435 0.9548 0.9771
No log 19.0 456 0.9325 0.3693 0.9325 0.9657
No log 19.0833 458 0.9268 0.3693 0.9268 0.9627
No log 19.1667 460 0.9325 0.3435 0.9325 0.9657
No log 19.25 462 0.9428 0.3840 0.9428 0.9710
No log 19.3333 464 0.9577 0.3821 0.9577 0.9786
No log 19.4167 466 0.9827 0.3822 0.9827 0.9913
No log 19.5 468 0.9661 0.3840 0.9661 0.9829
No log 19.5833 470 0.9445 0.3622 0.9445 0.9719
No log 19.6667 472 0.9385 0.3737 0.9385 0.9687
No log 19.75 474 0.9462 0.3356 0.9462 0.9728
No log 19.8333 476 0.9550 0.3496 0.9550 0.9773
No log 19.9167 478 0.9494 0.3301 0.9494 0.9744
No log 20.0 480 0.9649 0.3301 0.9649 0.9823
No log 20.0833 482 0.9882 0.3301 0.9882 0.9941
No log 20.1667 484 0.9810 0.3446 0.9810 0.9905
No log 20.25 486 0.9572 0.3033 0.9572 0.9784
No log 20.3333 488 0.9422 0.3425 0.9422 0.9707
No log 20.4167 490 0.9288 0.2742 0.9288 0.9637
No log 20.5 492 0.9402 0.2931 0.9402 0.9696
No log 20.5833 494 0.9667 0.3383 0.9667 0.9832
No log 20.6667 496 1.0236 0.3785 1.0236 1.0117
No log 20.75 498 1.0889 0.3511 1.0889 1.0435
0.2658 20.8333 500 1.0660 0.3648 1.0660 1.0325
0.2658 20.9167 502 0.9868 0.2865 0.9868 0.9934
0.2658 21.0 504 0.9496 0.3280 0.9496 0.9745
0.2658 21.0833 506 0.9529 0.2888 0.9529 0.9762
0.2658 21.1667 508 0.9714 0.3403 0.9714 0.9856
0.2658 21.25 510 1.0244 0.2695 1.0244 1.0121

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_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k5_task5_organization

Finetuned
(4019)
this model