ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k18_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: 1.1524
  • Qwk: 0.3286
  • Mse: 1.1524
  • Rmse: 1.0735

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 0.0238 2 4.1881 -0.0124 4.1881 2.0465
No log 0.0476 4 2.0975 0.0357 2.0975 1.4483
No log 0.0714 6 1.5228 0.0839 1.5228 1.2340
No log 0.0952 8 1.1761 0.1822 1.1761 1.0845
No log 0.1190 10 1.0591 0.1321 1.0591 1.0291
No log 0.1429 12 1.0683 0.2692 1.0683 1.0336
No log 0.1667 14 1.1643 0.1631 1.1643 1.0790
No log 0.1905 16 1.3778 0.1238 1.3778 1.1738
No log 0.2143 18 2.0017 0.0418 2.0017 1.4148
No log 0.2381 20 2.0340 0.0516 2.0340 1.4262
No log 0.2619 22 1.5517 0.1321 1.5517 1.2457
No log 0.2857 24 1.2858 0.0020 1.2858 1.1339
No log 0.3095 26 1.1453 0.2448 1.1453 1.0702
No log 0.3333 28 1.1666 0.1840 1.1666 1.0801
No log 0.3571 30 1.2976 0.2122 1.2976 1.1391
No log 0.3810 32 2.2158 0.1463 2.2158 1.4885
No log 0.4048 34 2.6701 0.0435 2.6701 1.6340
No log 0.4286 36 2.1216 0.1253 2.1216 1.4566
No log 0.4524 38 1.3978 0.2747 1.3978 1.1823
No log 0.4762 40 1.1612 0.1935 1.1612 1.0776
No log 0.5 42 1.1505 0.2121 1.1505 1.0726
No log 0.5238 44 1.1492 0.2475 1.1492 1.0720
No log 0.5476 46 1.2018 0.2650 1.2018 1.0963
No log 0.5714 48 1.1944 0.2650 1.1944 1.0929
No log 0.5952 50 1.1984 0.1958 1.1984 1.0947
No log 0.6190 52 1.2046 0.1615 1.2046 1.0975
No log 0.6429 54 1.2282 0.2735 1.2282 1.1083
No log 0.6667 56 1.4082 0.1758 1.4082 1.1867
No log 0.6905 58 1.6356 0.1372 1.6356 1.2789
No log 0.7143 60 1.5216 0.1324 1.5216 1.2335
No log 0.7381 62 1.4015 0.2275 1.4015 1.1839
No log 0.7619 64 1.3876 0.2002 1.3876 1.1780
No log 0.7857 66 1.1456 0.2464 1.1456 1.0703
No log 0.8095 68 1.0584 0.3311 1.0584 1.0288
No log 0.8333 70 1.1637 0.2822 1.1637 1.0787
No log 0.8571 72 1.3391 0.2252 1.3391 1.1572
No log 0.8810 74 1.4319 0.2386 1.4319 1.1966
No log 0.9048 76 1.4284 0.2874 1.4284 1.1951
No log 0.9286 78 1.5528 0.2593 1.5528 1.2461
No log 0.9524 80 1.6456 0.2545 1.6456 1.2828
No log 0.9762 82 1.5656 0.2611 1.5656 1.2512
No log 1.0 84 1.5613 0.2488 1.5613 1.2495
No log 1.0238 86 1.4953 0.2384 1.4953 1.2228
No log 1.0476 88 1.2550 0.2031 1.2550 1.1203
No log 1.0714 90 1.1501 0.2650 1.1501 1.0724
No log 1.0952 92 1.0933 0.3321 1.0933 1.0456
No log 1.1190 94 1.0612 0.3177 1.0612 1.0302
No log 1.1429 96 1.0219 0.3533 1.0219 1.0109
No log 1.1667 98 1.0092 0.3022 1.0092 1.0046
No log 1.1905 100 1.1297 0.3482 1.1297 1.0629
No log 1.2143 102 1.3736 0.2943 1.3736 1.1720
No log 1.2381 104 1.6232 0.2489 1.6232 1.2740
No log 1.2619 106 1.9019 0.1714 1.9019 1.3791
No log 1.2857 108 1.8902 0.1290 1.8902 1.3748
No log 1.3095 110 1.9173 0.1508 1.9173 1.3847
No log 1.3333 112 1.8977 0.1789 1.8977 1.3776
No log 1.3571 114 1.7117 0.1985 1.7117 1.3083
No log 1.3810 116 1.4542 0.2836 1.4542 1.2059
No log 1.4048 118 1.3221 0.3776 1.3221 1.1498
No log 1.4286 120 1.1428 0.3558 1.1428 1.0690
No log 1.4524 122 1.0261 0.4364 1.0261 1.0130
No log 1.4762 124 0.9890 0.4145 0.9890 0.9945
No log 1.5 126 1.0171 0.4165 1.0171 1.0085
No log 1.5238 128 1.0585 0.3678 1.0585 1.0288
No log 1.5476 130 1.1223 0.3623 1.1223 1.0594
No log 1.5714 132 1.1934 0.2894 1.1934 1.0924
No log 1.5952 134 1.1514 0.3613 1.1514 1.0730
No log 1.6190 136 1.1407 0.3870 1.1407 1.0681
No log 1.6429 138 1.0284 0.3572 1.0284 1.0141
No log 1.6667 140 0.9765 0.4805 0.9765 0.9882
No log 1.6905 142 1.0131 0.4996 1.0131 1.0065
No log 1.7143 144 0.9992 0.4805 0.9992 0.9996
No log 1.7381 146 1.0332 0.4128 1.0332 1.0164
No log 1.7619 148 1.2236 0.3351 1.2236 1.1062
No log 1.7857 150 1.2742 0.3671 1.2742 1.1288
No log 1.8095 152 1.1079 0.3194 1.1079 1.0526
No log 1.8333 154 1.0203 0.4946 1.0203 1.0101
No log 1.8571 156 1.0430 0.4774 1.0430 1.0213
No log 1.8810 158 1.1409 0.3817 1.1409 1.0681
No log 1.9048 160 1.1655 0.3133 1.1655 1.0796
No log 1.9286 162 1.0407 0.3704 1.0407 1.0201
No log 1.9524 164 0.9978 0.4488 0.9978 0.9989
No log 1.9762 166 1.0249 0.4381 1.0249 1.0124
No log 2.0 168 1.0144 0.4254 1.0144 1.0071
No log 2.0238 170 0.9900 0.3965 0.9900 0.9950
No log 2.0476 172 1.0130 0.3809 1.0130 1.0065
No log 2.0714 174 1.0602 0.4058 1.0602 1.0297
No log 2.0952 176 1.0560 0.3878 1.0560 1.0276
No log 2.1190 178 1.0360 0.3987 1.0360 1.0178
No log 2.1429 180 0.9589 0.4989 0.9589 0.9792
No log 2.1667 182 0.9095 0.5439 0.9095 0.9537
No log 2.1905 184 0.9178 0.5439 0.9178 0.9580
No log 2.2143 186 0.9240 0.5632 0.9240 0.9613
No log 2.2381 188 0.9304 0.4370 0.9304 0.9646
No log 2.2619 190 0.9187 0.4523 0.9187 0.9585
No log 2.2857 192 0.8918 0.5216 0.8918 0.9444
No log 2.3095 194 0.9357 0.5186 0.9357 0.9673
No log 2.3333 196 0.9034 0.5212 0.9034 0.9505
No log 2.3571 198 0.9027 0.5115 0.9027 0.9501
No log 2.3810 200 0.8846 0.4676 0.8846 0.9405
No log 2.4048 202 0.8563 0.4585 0.8563 0.9254
No log 2.4286 204 0.8543 0.4361 0.8543 0.9243
No log 2.4524 206 0.8476 0.4245 0.8476 0.9206
No log 2.4762 208 0.8690 0.5111 0.8690 0.9322
No log 2.5 210 0.9575 0.4532 0.9575 0.9785
No log 2.5238 212 0.9912 0.4196 0.9912 0.9956
No log 2.5476 214 1.0373 0.3549 1.0373 1.0185
No log 2.5714 216 1.0925 0.3778 1.0925 1.0452
No log 2.5952 218 1.0928 0.3811 1.0928 1.0454
No log 2.6190 220 1.0569 0.4368 1.0569 1.0280
No log 2.6429 222 1.1153 0.3355 1.1153 1.0561
No log 2.6667 224 1.1780 0.3617 1.1780 1.0854
No log 2.6905 226 1.1764 0.3219 1.1764 1.0846
No log 2.7143 228 1.1718 0.3462 1.1718 1.0825
No log 2.7381 230 1.0704 0.4772 1.0704 1.0346
No log 2.7619 232 1.0021 0.4916 1.0021 1.0011
No log 2.7857 234 0.9853 0.4705 0.9853 0.9926
No log 2.8095 236 0.9770 0.4930 0.9770 0.9884
No log 2.8333 238 1.0053 0.5115 1.0053 1.0026
No log 2.8571 240 1.0743 0.3812 1.0743 1.0365
No log 2.8810 242 1.0414 0.4440 1.0414 1.0205
No log 2.9048 244 0.9594 0.4915 0.9594 0.9795
No log 2.9286 246 0.9245 0.5275 0.9245 0.9615
No log 2.9524 248 0.9220 0.4920 0.9220 0.9602
No log 2.9762 250 0.9794 0.4776 0.9794 0.9896
No log 3.0 252 1.1343 0.3232 1.1343 1.0650
No log 3.0238 254 1.1782 0.3243 1.1782 1.0855
No log 3.0476 256 1.0864 0.4572 1.0864 1.0423
No log 3.0714 258 1.0255 0.4996 1.0255 1.0127
No log 3.0952 260 1.0115 0.5206 1.0115 1.0057
No log 3.1190 262 1.0362 0.5086 1.0362 1.0179
No log 3.1429 264 1.0672 0.4972 1.0672 1.0331
No log 3.1667 266 1.0711 0.4996 1.0711 1.0350
No log 3.1905 268 1.1126 0.4651 1.1126 1.0548
No log 3.2143 270 1.0946 0.4261 1.0946 1.0462
No log 3.2381 272 1.0669 0.4996 1.0669 1.0329
No log 3.2619 274 1.0373 0.4785 1.0373 1.0185
No log 3.2857 276 1.0039 0.4819 1.0039 1.0020
No log 3.3095 278 0.9976 0.4780 0.9976 0.9988
No log 3.3333 280 1.0314 0.3892 1.0314 1.0156
No log 3.3571 282 1.0046 0.4662 1.0046 1.0023
No log 3.3810 284 0.9832 0.4778 0.9832 0.9916
No log 3.4048 286 0.9633 0.4676 0.9633 0.9815
No log 3.4286 288 0.9840 0.4211 0.9840 0.9919
No log 3.4524 290 1.0242 0.3930 1.0242 1.0120
No log 3.4762 292 1.1072 0.3759 1.1072 1.0522
No log 3.5 294 1.0844 0.3424 1.0844 1.0413
No log 3.5238 296 1.0252 0.3424 1.0252 1.0125
No log 3.5476 298 0.9835 0.3621 0.9835 0.9917
No log 3.5714 300 0.9751 0.3786 0.9751 0.9875
No log 3.5952 302 0.9593 0.4555 0.9593 0.9794
No log 3.6190 304 0.9557 0.4676 0.9557 0.9776
No log 3.6429 306 0.9468 0.4213 0.9468 0.9730
No log 3.6667 308 0.9694 0.3183 0.9694 0.9846
No log 3.6905 310 0.9671 0.3080 0.9671 0.9834
No log 3.7143 312 0.9621 0.3132 0.9621 0.9809
No log 3.7381 314 0.9356 0.3983 0.9356 0.9672
No log 3.7619 316 0.9316 0.3839 0.9316 0.9652
No log 3.7857 318 1.0019 0.4037 1.0019 1.0009
No log 3.8095 320 1.0085 0.3250 1.0085 1.0042
No log 3.8333 322 1.0062 0.3250 1.0062 1.0031
No log 3.8571 324 1.0325 0.3230 1.0325 1.0161
No log 3.8810 326 0.9856 0.3639 0.9856 0.9928
No log 3.9048 328 0.8986 0.3711 0.8986 0.9480
No log 3.9286 330 0.8688 0.3685 0.8688 0.9321
No log 3.9524 332 0.8741 0.3633 0.8741 0.9349
No log 3.9762 334 0.8570 0.3966 0.8570 0.9257
No log 4.0 336 0.9350 0.4526 0.9350 0.9669
No log 4.0238 338 1.1478 0.4249 1.1478 1.0713
No log 4.0476 340 1.1017 0.4222 1.1017 1.0496
No log 4.0714 342 0.9290 0.2972 0.9290 0.9638
No log 4.0952 344 0.8878 0.2122 0.8878 0.9423
No log 4.1190 346 0.8706 0.2528 0.8706 0.9330
No log 4.1429 348 0.8765 0.2031 0.8765 0.9362
No log 4.1667 350 0.9108 0.3005 0.9108 0.9544
No log 4.1905 352 0.9445 0.3558 0.9445 0.9718
No log 4.2143 354 0.9183 0.4159 0.9183 0.9583
No log 4.2381 356 0.8921 0.3932 0.8921 0.9445
No log 4.2619 358 0.9108 0.4252 0.9108 0.9543
No log 4.2857 360 0.9216 0.3559 0.9216 0.9600
No log 4.3095 362 0.9546 0.3931 0.9546 0.9770
No log 4.3333 364 1.0051 0.4159 1.0051 1.0026
No log 4.3571 366 0.9775 0.3914 0.9775 0.9887
No log 4.3810 368 0.9234 0.3565 0.9234 0.9609
No log 4.4048 370 0.9648 0.3879 0.9648 0.9823
No log 4.4286 372 0.9737 0.3990 0.9737 0.9868
No log 4.4524 374 0.9401 0.4039 0.9401 0.9696
No log 4.4762 376 0.9146 0.3408 0.9146 0.9563
No log 4.5 378 0.9804 0.3914 0.9804 0.9901
No log 4.5238 380 1.0051 0.3790 1.0051 1.0025
No log 4.5476 382 0.9888 0.4282 0.9888 0.9944
No log 4.5714 384 1.0212 0.4098 1.0212 1.0106
No log 4.5952 386 1.0064 0.4102 1.0064 1.0032
No log 4.6190 388 0.9814 0.3609 0.9814 0.9906
No log 4.6429 390 0.9775 0.3841 0.9775 0.9887
No log 4.6667 392 0.9330 0.3263 0.9330 0.9659
No log 4.6905 394 0.9195 0.3548 0.9195 0.9589
No log 4.7143 396 0.9386 0.3753 0.9386 0.9688
No log 4.7381 398 0.9446 0.5124 0.9446 0.9719
No log 4.7619 400 1.0620 0.4321 1.0620 1.0305
No log 4.7857 402 1.0774 0.4321 1.0774 1.0380
No log 4.8095 404 1.0143 0.4410 1.0143 1.0071
No log 4.8333 406 1.0134 0.4649 1.0134 1.0067
No log 4.8571 408 1.0788 0.4306 1.0788 1.0387
No log 4.8810 410 1.0298 0.3824 1.0298 1.0148
No log 4.9048 412 0.9920 0.4039 0.9920 0.9960
No log 4.9286 414 0.9871 0.3399 0.9871 0.9935
No log 4.9524 416 1.0230 0.3409 1.0230 1.0114
No log 4.9762 418 1.0906 0.3519 1.0906 1.0443
No log 5.0 420 1.2431 0.3401 1.2431 1.1149
No log 5.0238 422 1.2881 0.3424 1.2881 1.1349
No log 5.0476 424 1.1895 0.3384 1.1895 1.0906
No log 5.0714 426 1.1503 0.38 1.1503 1.0725
No log 5.0952 428 1.0903 0.3624 1.0903 1.0442
No log 5.1190 430 1.0289 0.3914 1.0289 1.0143
No log 5.1429 432 1.0585 0.2510 1.0585 1.0289
No log 5.1667 434 1.0429 0.2312 1.0429 1.0212
No log 5.1905 436 0.9739 0.2440 0.9739 0.9869
No log 5.2143 438 0.9570 0.2122 0.9570 0.9783
No log 5.2381 440 0.9884 0.2909 0.9884 0.9942
No log 5.2619 442 1.1158 0.3938 1.1158 1.0563
No log 5.2857 444 1.1945 0.3699 1.1945 1.0929
No log 5.3095 446 1.1055 0.3864 1.1055 1.0514
No log 5.3333 448 1.0105 0.4197 1.0105 1.0052
No log 5.3571 450 0.9210 0.2721 0.9210 0.9597
No log 5.3810 452 0.9083 0.2721 0.9083 0.9530
No log 5.4048 454 0.9607 0.3732 0.9607 0.9802
No log 5.4286 456 1.0385 0.3954 1.0385 1.0191
No log 5.4524 458 1.0401 0.4081 1.0401 1.0199
No log 5.4762 460 1.0497 0.3954 1.0497 1.0246
No log 5.5 462 1.0387 0.4081 1.0387 1.0192
No log 5.5238 464 0.9927 0.3045 0.9927 0.9963
No log 5.5476 466 1.0106 0.3161 1.0106 1.0053
No log 5.5714 468 0.9667 0.2814 0.9667 0.9832
No log 5.5952 470 0.9257 0.3671 0.9257 0.9621
No log 5.6190 472 0.9181 0.4213 0.9181 0.9582
No log 5.6429 474 0.9343 0.3671 0.9343 0.9666
No log 5.6667 476 0.9282 0.4181 0.9282 0.9634
No log 5.6905 478 0.8830 0.4329 0.8830 0.9397
No log 5.7143 480 0.9396 0.4191 0.9396 0.9694
No log 5.7381 482 0.9277 0.4067 0.9277 0.9631
No log 5.7619 484 0.8657 0.3983 0.8657 0.9304
No log 5.7857 486 0.9470 0.4257 0.9470 0.9731
No log 5.8095 488 1.0482 0.4464 1.0482 1.0238
No log 5.8333 490 0.9968 0.4018 0.9968 0.9984
No log 5.8571 492 0.9312 0.4231 0.9312 0.9650
No log 5.8810 494 0.8800 0.3671 0.8800 0.9381
No log 5.9048 496 0.8765 0.3671 0.8765 0.9362
No log 5.9286 498 0.8635 0.4337 0.8635 0.9292
0.3111 5.9524 500 0.8742 0.4585 0.8742 0.9350
0.3111 5.9762 502 0.8931 0.4902 0.8931 0.9451
0.3111 6.0 504 0.8977 0.4792 0.8977 0.9475
0.3111 6.0238 506 0.9053 0.4073 0.9053 0.9515
0.3111 6.0476 508 0.9226 0.3634 0.9226 0.9605
0.3111 6.0714 510 1.0211 0.2908 1.0211 1.0105
0.3111 6.0952 512 1.1284 0.3810 1.1284 1.0622
0.3111 6.1190 514 1.1524 0.3286 1.1524 1.0735

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_k18_task5_organization

Finetuned
(4040)
this model