salbatarni's picture
Training in progress, step 65
f2fde9d verified
|
raw
history blame
3.45 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task6_fold5
    results: []

arabert_cross_relevance_task6_fold5

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: 0.1873
  • Qwk: 0.3574
  • Mse: 0.1873

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Qwk Mse
No log 0.0328 2 1.7597 0.0 1.7597
No log 0.0656 4 0.5562 0.1908 0.5562
No log 0.0984 6 0.1992 0.3305 0.1992
No log 0.1311 8 0.2333 0.4006 0.2333
No log 0.1639 10 0.2174 0.2998 0.2174
No log 0.1967 12 0.2464 0.2998 0.2464
No log 0.2295 14 0.2503 0.3279 0.2503
No log 0.2623 16 0.2466 0.3305 0.2466
No log 0.2951 18 0.2107 0.3279 0.2107
No log 0.3279 20 0.1965 0.3251 0.1965
No log 0.3607 22 0.1973 0.3292 0.1973
No log 0.3934 24 0.1930 0.3318 0.1930
No log 0.4262 26 0.1955 0.3379 0.1955
No log 0.4590 28 0.1901 0.3379 0.1901
No log 0.4918 30 0.1893 0.3343 0.1893
No log 0.5246 32 0.1861 0.3279 0.1861
No log 0.5574 34 0.1931 0.3453 0.1931
No log 0.5902 36 0.2045 0.5036 0.2045
No log 0.6230 38 0.2065 0.5858 0.2065
No log 0.6557 40 0.1891 0.4899 0.1891
No log 0.6885 42 0.1813 0.3696 0.1813
No log 0.7213 44 0.2125 0.3665 0.2125
No log 0.7541 46 0.2717 0.3526 0.2717
No log 0.7869 48 0.3306 0.3344 0.3306
No log 0.8197 50 0.3275 0.3475 0.3275
No log 0.8525 52 0.2862 0.3587 0.2862
No log 0.8852 54 0.2419 0.3643 0.2419
No log 0.9180 56 0.2102 0.3614 0.2102
No log 0.9508 58 0.1933 0.3590 0.1933
No log 0.9836 60 0.1873 0.3574 0.1873

Framework versions

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