Hugging Face's logo

salbatarni
/
arabert_cross_organization_task7_fold4

Safetensors
bert
Generated from Trainer
Model card Files Community
arabert_cross_organization_task7_fold4 / README.md
salbatarni's picture
salbatarni
End of training
636e770 verified
preview code
|
raw
history blame contribute delete
No virus
6.61 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_organization_task7_fold4
    results: []

arabert_cross_organization_task7_fold4

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: 0.5739
  • Qwk: 0.7967
  • Mse: 0.5739

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse
No log 0.1333 2 1.9448 0.1649 1.9447
No log 0.2667 4 1.4779 0.0771 1.4779
No log 0.4 6 1.3512 0.4234 1.3512
No log 0.5333 8 0.9818 0.5170 0.9818
No log 0.6667 10 0.9848 0.7218 0.9848
No log 0.8 12 0.7546 0.7580 0.7546
No log 0.9333 14 0.6613 0.7635 0.6613
No log 1.0667 16 0.5901 0.7415 0.5901
No log 1.2 18 0.5891 0.6836 0.5891
No log 1.3333 20 0.6666 0.7927 0.6666
No log 1.4667 22 0.7821 0.7742 0.7821
No log 1.6 24 0.5788 0.7710 0.5788
No log 1.7333 26 0.5726 0.6635 0.5726
No log 1.8667 28 0.5773 0.7575 0.5773
No log 2.0 30 0.8482 0.7672 0.8482
No log 2.1333 32 0.9640 0.7499 0.9640
No log 2.2667 34 0.7191 0.7738 0.7191
No log 2.4 36 0.5565 0.7624 0.5565
No log 2.5333 38 0.5998 0.6630 0.5998
No log 2.6667 40 0.5526 0.7554 0.5526
No log 2.8 42 0.6355 0.7866 0.6355
No log 2.9333 44 0.7893 0.7696 0.7893
No log 3.0667 46 0.7015 0.7820 0.7015
No log 3.2 48 0.5349 0.7719 0.5349
No log 3.3333 50 0.5250 0.7364 0.5250
No log 3.4667 52 0.5324 0.7720 0.5324
No log 3.6 54 0.6922 0.7790 0.6922
No log 3.7333 56 0.7969 0.7647 0.7969
No log 3.8667 58 0.7515 0.7687 0.7515
No log 4.0 60 0.5754 0.7791 0.5754
No log 4.1333 62 0.5295 0.7890 0.5295
No log 4.2667 64 0.5568 0.7950 0.5568
No log 4.4 66 0.6597 0.7830 0.6597
No log 4.5333 68 0.7200 0.7855 0.7200
No log 4.6667 70 0.6382 0.7912 0.6382
No log 4.8 72 0.5464 0.7964 0.5464
No log 4.9333 74 0.5642 0.7927 0.5642
No log 5.0667 76 0.5529 0.7877 0.5529
No log 5.2 78 0.5685 0.7941 0.5685
No log 5.3333 80 0.5692 0.8019 0.5692
No log 5.4667 82 0.5649 0.8048 0.5649
No log 5.6 84 0.5735 0.8008 0.5735
No log 5.7333 86 0.5626 0.7884 0.5626
No log 5.8667 88 0.5496 0.7807 0.5496
No log 6.0 90 0.5597 0.7832 0.5597
No log 6.1333 92 0.5892 0.8044 0.5892
No log 6.2667 94 0.5985 0.8021 0.5985
No log 6.4 96 0.5764 0.7946 0.5764
No log 6.5333 98 0.5254 0.7832 0.5254
No log 6.6667 100 0.5198 0.7806 0.5198
No log 6.8 102 0.5624 0.7979 0.5624
No log 6.9333 104 0.5920 0.7935 0.5920
No log 7.0667 106 0.6267 0.8062 0.6267
No log 7.2 108 0.6433 0.8077 0.6433
No log 7.3333 110 0.5670 0.7975 0.5670
No log 7.4667 112 0.5349 0.7881 0.5349
No log 7.6 114 0.5360 0.7932 0.5360
No log 7.7333 116 0.5494 0.7932 0.5494
No log 7.8667 118 0.5884 0.8142 0.5884
No log 8.0 120 0.6313 0.8158 0.6313
No log 8.1333 122 0.6069 0.8159 0.6069
No log 8.2667 124 0.5732 0.8053 0.5732
No log 8.4 126 0.5567 0.7975 0.5567
No log 8.5333 128 0.5440 0.7789 0.5440
No log 8.6667 130 0.5462 0.7810 0.5462
No log 8.8 132 0.5522 0.7873 0.5522
No log 8.9333 134 0.5458 0.7876 0.5458
No log 9.0667 136 0.5390 0.7905 0.5390
No log 9.2 138 0.5392 0.7901 0.5392
No log 9.3333 140 0.5491 0.7943 0.5491
No log 9.4667 142 0.5675 0.7937 0.5675
No log 9.6 144 0.5753 0.7967 0.5753
No log 9.7333 146 0.5745 0.7967 0.5745
No log 9.8667 148 0.5743 0.7967 0.5743
No log 10.0 150 0.5739 0.7967 0.5739

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1