Hugging Face's logo

salohnana2018
/
ABSA-SentencePair-corrected-domainAdapt-Stack-Semeval-Adapter-houlsby-run3

Adapters
PyTorch
TensorBoard
bert
adapterhub:Arabic ABSA/SemEvalHotelReview
Model card Files Metrics Community
ABSA-SentencePair-corrected-domainAdapt-Stack-Semeval-Adapter-houlsby-run3 / README.md
salohnana2018's picture
salohnana2018
update model card README.md
b71715f
preview code
|
raw
history blame
No virus
3.4 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: ABSA-SentencePair-corrected-domainAdapt-Stack-Semeval-Adapter-houlsby-run3
    results: []

ABSA-SentencePair-corrected-domainAdapt-Stack-Semeval-Adapter-houlsby-run3

This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-msa on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3204
  • Accuracy: 0.8752
  • F1: 0.8752
  • Precision: 0.8752
  • Recall: 0.8752

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 23
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.4834 1.0 265 0.3768 0.8677 0.8677 0.8677 0.8677
0.3888 2.0 530 0.3437 0.8719 0.8719 0.8719 0.8719
0.3592 3.0 795 0.3512 0.8738 0.8738 0.8738 0.8738
0.3312 4.0 1060 0.3288 0.8677 0.8677 0.8677 0.8677
0.322 5.0 1325 0.3393 0.8677 0.8677 0.8677 0.8677
0.3052 6.0 1590 0.3245 0.8790 0.8790 0.8790 0.8790
0.2962 7.0 1855 0.3204 0.8752 0.8752 0.8752 0.8752
0.2834 8.0 2120 0.3324 0.8828 0.8828 0.8828 0.8828
0.2687 9.0 2385 0.3211 0.8743 0.8743 0.8743 0.8743
0.2647 10.0 2650 0.3453 0.8648 0.8648 0.8648 0.8648
0.2502 11.0 2915 0.3282 0.8743 0.8743 0.8743 0.8743
0.2441 12.0 3180 0.3430 0.8700 0.8700 0.8700 0.8700
0.2353 13.0 3445 0.3519 0.8767 0.8767 0.8767 0.8767
0.2286 14.0 3710 0.3481 0.8738 0.8738 0.8738 0.8738
0.2197 15.0 3975 0.3649 0.8771 0.8771 0.8771 0.8771
0.2191 16.0 4240 0.3608 0.8729 0.8729 0.8729 0.8729
0.2145 17.0 4505 0.3587 0.8724 0.8724 0.8724 0.8724
0.2075 18.0 4770 0.3577 0.8762 0.8762 0.8762 0.8762
0.2032 19.0 5035 0.3630 0.8724 0.8724 0.8724 0.8724
0.1975 20.0 5300 0.3636 0.8719 0.8719 0.8719 0.8719

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3