ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k7_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: 0.5726
  • Qwk: 0.5026
  • Mse: 0.5726
  • Rmse: 0.7567

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 0.0541 2 4.3541 -0.0210 4.3541 2.0866
No log 0.1081 4 2.4514 0.0253 2.4514 1.5657
No log 0.1622 6 1.4358 -0.0076 1.4358 1.1982
No log 0.2162 8 0.8629 0.1417 0.8629 0.9289
No log 0.2703 10 0.9551 0.0408 0.9551 0.9773
No log 0.3243 12 1.5411 -0.1028 1.5411 1.2414
No log 0.3784 14 1.2148 -0.1164 1.2148 1.1022
No log 0.4324 16 0.8456 0.1064 0.8456 0.9195
No log 0.4865 18 0.8157 0.1006 0.8157 0.9032
No log 0.5405 20 0.8061 0.0305 0.8061 0.8978
No log 0.5946 22 0.7715 0.1867 0.7715 0.8784
No log 0.6486 24 0.8901 0.1671 0.8901 0.9434
No log 0.7027 26 1.5162 0.0374 1.5162 1.2313
No log 0.7568 28 1.9100 0.0847 1.9100 1.3820
No log 0.8108 30 1.6544 0.1013 1.6544 1.2862
No log 0.8649 32 1.1402 0.1787 1.1402 1.0678
No log 0.9189 34 0.8647 0.2256 0.8647 0.9299
No log 0.9730 36 0.7925 0.2927 0.7925 0.8902
No log 1.0270 38 0.7843 0.3097 0.7843 0.8856
No log 1.0811 40 1.0055 0.1752 1.0055 1.0028
No log 1.1351 42 0.9119 0.2397 0.9119 0.9549
No log 1.1892 44 0.6603 0.2827 0.6603 0.8126
No log 1.2432 46 0.6512 0.3183 0.6512 0.8070
No log 1.2973 48 0.6730 0.3948 0.6730 0.8204
No log 1.3514 50 0.8261 0.2446 0.8261 0.9089
No log 1.4054 52 1.2489 0.1796 1.2489 1.1175
No log 1.4595 54 1.1278 0.2115 1.1278 1.0620
No log 1.5135 56 0.8622 0.2920 0.8622 0.9286
No log 1.5676 58 0.6746 0.3714 0.6746 0.8213
No log 1.6216 60 0.6896 0.3836 0.6896 0.8304
No log 1.6757 62 0.6810 0.3665 0.6810 0.8252
No log 1.7297 64 0.9527 0.3180 0.9527 0.9760
No log 1.7838 66 0.9585 0.3501 0.9585 0.9790
No log 1.8378 68 0.6698 0.3835 0.6698 0.8184
No log 1.8919 70 0.5928 0.4523 0.5928 0.7699
No log 1.9459 72 0.5979 0.4548 0.5979 0.7732
No log 2.0 74 0.6540 0.3919 0.6540 0.8087
No log 2.0541 76 0.6031 0.3970 0.6031 0.7766
No log 2.1081 78 0.5790 0.4234 0.5790 0.7609
No log 2.1622 80 0.6348 0.3726 0.6348 0.7968
No log 2.2162 82 0.7505 0.3466 0.7505 0.8663
No log 2.2703 84 0.7160 0.3668 0.7160 0.8461
No log 2.3243 86 0.6086 0.4035 0.6086 0.7801
No log 2.3784 88 0.5714 0.4128 0.5714 0.7559
No log 2.4324 90 0.5732 0.4059 0.5732 0.7571
No log 2.4865 92 0.5700 0.5264 0.5700 0.7550
No log 2.5405 94 0.5887 0.5533 0.5887 0.7673
No log 2.5946 96 0.6184 0.5614 0.6184 0.7864
No log 2.6486 98 0.6668 0.5032 0.6668 0.8166
No log 2.7027 100 0.8228 0.4964 0.8228 0.9071
No log 2.7568 102 0.8011 0.4929 0.8011 0.8950
No log 2.8108 104 0.7849 0.4820 0.7849 0.8860
No log 2.8649 106 0.6059 0.4949 0.6059 0.7784
No log 2.9189 108 0.5975 0.5410 0.5975 0.7730
No log 2.9730 110 0.6304 0.4223 0.6304 0.7940
No log 3.0270 112 0.6990 0.4292 0.6990 0.8361
No log 3.0811 114 0.7189 0.4324 0.7189 0.8479
No log 3.1351 116 0.6146 0.5114 0.6146 0.7839
No log 3.1892 118 0.6554 0.5816 0.6554 0.8095
No log 3.2432 120 0.6712 0.5602 0.6712 0.8193
No log 3.2973 122 0.6397 0.5108 0.6397 0.7998
No log 3.3514 124 0.6976 0.4645 0.6976 0.8352
No log 3.4054 126 0.6765 0.4796 0.6765 0.8225
No log 3.4595 128 0.6244 0.5166 0.6244 0.7902
No log 3.5135 130 0.6386 0.5563 0.6386 0.7992
No log 3.5676 132 0.6162 0.5228 0.6162 0.7850
No log 3.6216 134 0.6852 0.4218 0.6852 0.8278
No log 3.6757 136 0.7663 0.4452 0.7663 0.8754
No log 3.7297 138 0.6480 0.4218 0.6480 0.8050
No log 3.7838 140 0.5882 0.4868 0.5882 0.7669
No log 3.8378 142 0.5804 0.5156 0.5804 0.7619
No log 3.8919 144 0.5895 0.4856 0.5895 0.7678
No log 3.9459 146 0.6841 0.3973 0.6841 0.8271
No log 4.0 148 0.9337 0.4143 0.9337 0.9663
No log 4.0541 150 0.8348 0.4666 0.8348 0.9137
No log 4.1081 152 0.6204 0.4497 0.6204 0.7877
No log 4.1622 154 0.6406 0.5297 0.6406 0.8004
No log 4.2162 156 0.6405 0.5404 0.6405 0.8003
No log 4.2703 158 0.6873 0.4672 0.6873 0.8291
No log 4.3243 160 0.6828 0.4421 0.6828 0.8263
No log 4.3784 162 0.6059 0.4528 0.6059 0.7784
No log 4.4324 164 0.6404 0.5763 0.6404 0.8002
No log 4.4865 166 0.6777 0.5556 0.6777 0.8233
No log 4.5405 168 0.6361 0.5307 0.6361 0.7975
No log 4.5946 170 0.6361 0.5360 0.6361 0.7976
No log 4.6486 172 0.7015 0.5998 0.7015 0.8375
No log 4.7027 174 0.7863 0.5085 0.7863 0.8867
No log 4.7568 176 0.6868 0.5291 0.6868 0.8287
No log 4.8108 178 0.7924 0.5283 0.7924 0.8902
No log 4.8649 180 0.9258 0.4094 0.9258 0.9622
No log 4.9189 182 0.8084 0.4481 0.8084 0.8991
No log 4.9730 184 0.6599 0.4730 0.6599 0.8124
No log 5.0270 186 0.6462 0.4751 0.6462 0.8038
No log 5.0811 188 0.7072 0.4830 0.7072 0.8409
No log 5.1351 190 0.6682 0.5211 0.6682 0.8174
No log 5.1892 192 0.6031 0.4827 0.6031 0.7766
No log 5.2432 194 0.6725 0.4385 0.6725 0.8200
No log 5.2973 196 0.6256 0.4605 0.6256 0.7909
No log 5.3514 198 0.6309 0.5363 0.6309 0.7943
No log 5.4054 200 0.6261 0.5141 0.6261 0.7913
No log 5.4595 202 0.6832 0.4910 0.6832 0.8265
No log 5.5135 204 0.8371 0.4236 0.8371 0.9150
No log 5.5676 206 0.7294 0.4755 0.7294 0.8541
No log 5.6216 208 0.6525 0.5217 0.6525 0.8077
No log 5.6757 210 0.9098 0.4216 0.9098 0.9538
No log 5.7297 212 0.9191 0.4063 0.9191 0.9587
No log 5.7838 214 0.7025 0.4829 0.7025 0.8382
No log 5.8378 216 0.6378 0.5426 0.6378 0.7986
No log 5.8919 218 0.7994 0.5029 0.7994 0.8941
No log 5.9459 220 0.8025 0.4797 0.8025 0.8958
No log 6.0 222 0.6673 0.5927 0.6673 0.8169
No log 6.0541 224 0.6477 0.5240 0.6477 0.8048
No log 6.1081 226 0.7088 0.4863 0.7088 0.8419
No log 6.1622 228 0.6966 0.4829 0.6966 0.8346
No log 6.2162 230 0.6201 0.5495 0.6201 0.7874
No log 6.2703 232 0.5878 0.4440 0.5878 0.7667
No log 6.3243 234 0.6233 0.3838 0.6233 0.7895
No log 6.3784 236 0.5957 0.4268 0.5957 0.7718
No log 6.4324 238 0.5621 0.4774 0.5621 0.7497
No log 6.4865 240 0.5695 0.5105 0.5695 0.7546
No log 6.5405 242 0.5663 0.4869 0.5663 0.7525
No log 6.5946 244 0.6349 0.4823 0.6349 0.7968
No log 6.6486 246 0.6476 0.4919 0.6476 0.8047
No log 6.7027 248 0.6138 0.4882 0.6138 0.7835
No log 6.7568 250 0.6755 0.5278 0.6755 0.8219
No log 6.8108 252 0.8157 0.4287 0.8157 0.9032
No log 6.8649 254 0.7447 0.4412 0.7447 0.8630
No log 6.9189 256 0.6031 0.5444 0.6031 0.7766
No log 6.9730 258 0.5844 0.5451 0.5844 0.7645
No log 7.0270 260 0.5789 0.5156 0.5789 0.7609
No log 7.0811 262 0.5906 0.5053 0.5906 0.7685
No log 7.1351 264 0.5911 0.5053 0.5910 0.7688
No log 7.1892 266 0.5977 0.5231 0.5977 0.7731
No log 7.2432 268 0.5827 0.4513 0.5827 0.7634
No log 7.2973 270 0.5787 0.4767 0.5787 0.7607
No log 7.3514 272 0.5784 0.4977 0.5784 0.7605
No log 7.4054 274 0.5869 0.4716 0.5869 0.7661
No log 7.4595 276 0.6153 0.5110 0.6153 0.7844
No log 7.5135 278 0.6876 0.5263 0.6876 0.8292
No log 7.5676 280 0.6498 0.5507 0.6498 0.8061
No log 7.6216 282 0.6069 0.5053 0.6069 0.7790
No log 7.6757 284 0.6109 0.4141 0.6109 0.7816
No log 7.7297 286 0.6152 0.4061 0.6152 0.7843
No log 7.7838 288 0.5987 0.3725 0.5987 0.7738
No log 7.8378 290 0.5990 0.3759 0.5990 0.7740
No log 7.8919 292 0.5953 0.4723 0.5953 0.7715
No log 7.9459 294 0.6173 0.4371 0.6173 0.7857
No log 8.0 296 0.6637 0.4596 0.6637 0.8147
No log 8.0541 298 0.6355 0.4480 0.6355 0.7972
No log 8.1081 300 0.5957 0.4364 0.5957 0.7718
No log 8.1622 302 0.5894 0.4673 0.5894 0.7677
No log 8.2162 304 0.5927 0.4639 0.5927 0.7699
No log 8.2703 306 0.6154 0.4489 0.6154 0.7845
No log 8.3243 308 0.6209 0.4512 0.6209 0.7880
No log 8.3784 310 0.6132 0.4542 0.6132 0.7831
No log 8.4324 312 0.6245 0.5336 0.6245 0.7903
No log 8.4865 314 0.6168 0.5200 0.6168 0.7853
No log 8.5405 316 0.6288 0.4289 0.6288 0.7930
No log 8.5946 318 0.6107 0.4414 0.6107 0.7815
No log 8.6486 320 0.5902 0.4774 0.5902 0.7682
No log 8.7027 322 0.6493 0.5568 0.6493 0.8058
No log 8.7568 324 0.6937 0.4968 0.6937 0.8329
No log 8.8108 326 0.6361 0.5041 0.6361 0.7975
No log 8.8649 328 0.5872 0.5100 0.5872 0.7663
No log 8.9189 330 0.6706 0.4878 0.6706 0.8189
No log 8.9730 332 0.6786 0.5079 0.6786 0.8237
No log 9.0270 334 0.6119 0.5141 0.6119 0.7822
No log 9.0811 336 0.6388 0.5076 0.6388 0.7992
No log 9.1351 338 0.6606 0.5 0.6606 0.8128
No log 9.1892 340 0.6281 0.4659 0.6281 0.7925
No log 9.2432 342 0.6196 0.4669 0.6196 0.7871
No log 9.2973 344 0.6188 0.4936 0.6188 0.7866
No log 9.3514 346 0.6117 0.4950 0.6117 0.7821
No log 9.4054 348 0.6171 0.4924 0.6171 0.7856
No log 9.4595 350 0.6142 0.4896 0.6142 0.7837
No log 9.5135 352 0.6053 0.4835 0.6053 0.7780
No log 9.5676 354 0.6039 0.5295 0.6039 0.7771
No log 9.6216 356 0.5922 0.4785 0.5922 0.7695
No log 9.6757 358 0.5976 0.4430 0.5976 0.7731
No log 9.7297 360 0.6120 0.4390 0.6120 0.7823
No log 9.7838 362 0.5877 0.4552 0.5877 0.7666
No log 9.8378 364 0.5838 0.4665 0.5838 0.7640
No log 9.8919 366 0.6033 0.4985 0.6033 0.7767
No log 9.9459 368 0.5966 0.5019 0.5966 0.7724
No log 10.0 370 0.6032 0.4550 0.6032 0.7767
No log 10.0541 372 0.7065 0.4518 0.7065 0.8405
No log 10.1081 374 0.7836 0.5033 0.7836 0.8852
No log 10.1622 376 0.6899 0.4650 0.6899 0.8306
No log 10.2162 378 0.6357 0.4674 0.6357 0.7973
No log 10.2703 380 0.6779 0.5658 0.6779 0.8233
No log 10.3243 382 0.6534 0.5736 0.6534 0.8083
No log 10.3784 384 0.5933 0.5222 0.5933 0.7702
No log 10.4324 386 0.6062 0.4582 0.6062 0.7786
No log 10.4865 388 0.6393 0.4691 0.6393 0.7996
No log 10.5405 390 0.6443 0.4990 0.6443 0.8027
No log 10.5946 392 0.6207 0.5098 0.6207 0.7878
No log 10.6486 394 0.6100 0.5369 0.6100 0.7810
No log 10.7027 396 0.6097 0.5716 0.6097 0.7809
No log 10.7568 398 0.6055 0.5298 0.6055 0.7781
No log 10.8108 400 0.6339 0.5308 0.6339 0.7962
No log 10.8649 402 0.7376 0.4722 0.7376 0.8589
No log 10.9189 404 0.7265 0.4698 0.7265 0.8523
No log 10.9730 406 0.6595 0.4558 0.6595 0.8121
No log 11.0270 408 0.5843 0.5218 0.5843 0.7644
No log 11.0811 410 0.5704 0.5090 0.5704 0.7552
No log 11.1351 412 0.5635 0.5063 0.5635 0.7507
No log 11.1892 414 0.5576 0.4562 0.5576 0.7468
No log 11.2432 416 0.5783 0.4463 0.5783 0.7604
No log 11.2973 418 0.5925 0.4824 0.5925 0.7697
No log 11.3514 420 0.6073 0.4731 0.6073 0.7793
No log 11.4054 422 0.5714 0.4941 0.5714 0.7559
No log 11.4595 424 0.5700 0.5482 0.5700 0.7550
No log 11.5135 426 0.6281 0.5359 0.6281 0.7925
No log 11.5676 428 0.6242 0.5584 0.6242 0.7900
No log 11.6216 430 0.5899 0.5814 0.5899 0.7681
No log 11.6757 432 0.6246 0.4912 0.6246 0.7903
No log 11.7297 434 0.6964 0.5111 0.6964 0.8345
No log 11.7838 436 0.6620 0.4844 0.6620 0.8136
No log 11.8378 438 0.5886 0.5089 0.5886 0.7672
No log 11.8919 440 0.5788 0.5999 0.5788 0.7608
No log 11.9459 442 0.5944 0.5566 0.5944 0.7710
No log 12.0 444 0.5810 0.6075 0.5810 0.7623
No log 12.0541 446 0.5849 0.5378 0.5849 0.7648
No log 12.1081 448 0.6869 0.4607 0.6869 0.8288
No log 12.1622 450 0.7741 0.3974 0.7741 0.8799
No log 12.2162 452 0.7210 0.4384 0.7210 0.8491
No log 12.2703 454 0.6284 0.4792 0.6284 0.7927
No log 12.3243 456 0.5847 0.5433 0.5847 0.7647
No log 12.3784 458 0.6268 0.5117 0.6268 0.7917
No log 12.4324 460 0.6272 0.5205 0.6272 0.7920
No log 12.4865 462 0.5975 0.5450 0.5975 0.7730
No log 12.5405 464 0.6003 0.5957 0.6003 0.7748
No log 12.5946 466 0.6031 0.5720 0.6031 0.7766
No log 12.6486 468 0.5948 0.5466 0.5948 0.7712
No log 12.7027 470 0.6018 0.5489 0.6018 0.7757
No log 12.7568 472 0.5949 0.5361 0.5949 0.7713
No log 12.8108 474 0.5739 0.5147 0.5739 0.7576
No log 12.8649 476 0.5733 0.4814 0.5733 0.7572
No log 12.9189 478 0.6120 0.4993 0.6120 0.7823
No log 12.9730 480 0.6441 0.5202 0.6441 0.8025
No log 13.0270 482 0.5993 0.5046 0.5993 0.7742
No log 13.0811 484 0.5631 0.5209 0.5631 0.7504
No log 13.1351 486 0.5801 0.4863 0.5801 0.7616
No log 13.1892 488 0.5858 0.4895 0.5858 0.7654
No log 13.2432 490 0.5760 0.5335 0.5760 0.7590
No log 13.2973 492 0.6332 0.5332 0.6332 0.7957
No log 13.3514 494 0.6585 0.5316 0.6585 0.8115
No log 13.4054 496 0.6267 0.5472 0.6267 0.7916
No log 13.4595 498 0.6238 0.4937 0.6238 0.7898
0.3582 13.5135 500 0.6049 0.5289 0.6049 0.7777
0.3582 13.5676 502 0.5961 0.5471 0.5961 0.7721
0.3582 13.6216 504 0.6249 0.4993 0.6249 0.7905
0.3582 13.6757 506 0.6437 0.4895 0.6437 0.8023
0.3582 13.7297 508 0.6126 0.4871 0.6126 0.7827
0.3582 13.7838 510 0.5834 0.5396 0.5834 0.7638
0.3582 13.8378 512 0.5704 0.5648 0.5704 0.7552
0.3582 13.8919 514 0.5702 0.4910 0.5702 0.7551
0.3582 13.9459 516 0.5738 0.4932 0.5738 0.7575
0.3582 14.0 518 0.5810 0.5213 0.5810 0.7623
0.3582 14.0541 520 0.5812 0.5305 0.5812 0.7624
0.3582 14.1081 522 0.5877 0.4999 0.5877 0.7666
0.3582 14.1622 524 0.5892 0.5117 0.5892 0.7676
0.3582 14.2162 526 0.6000 0.4895 0.6000 0.7746
0.3582 14.2703 528 0.5968 0.5033 0.5968 0.7725
0.3582 14.3243 530 0.5726 0.5026 0.5726 0.7567

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k7_task2_organization

Finetuned
(4222)
this model