Hugging Face's logo

BoghdadyJR
/
en-ar-model

Transformers
TensorBoard
Safetensors
marian
text2text-generation
Generated from Trainer
Model card Files Metrics Community
en-ar-model / README.md
Mohamed Boghdady
End of training
df91f07 verified
preview code
|
raw
history blame
2.29 kB
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ar-en
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: working
    results: []

Visualize in Weights & Biases

working

This model is a fine-tuned version of Helsinki-NLP/opus-mt-ar-en on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2987
  • Bleu: 31.8518
  • Gen Len: 34.0136

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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 312 0.3560 25.127 33.2927
0.6275 2.0 624 0.3309 27.7903 34.3769
0.6275 3.0 936 0.3176 28.8587 33.1307
0.2524 4.0 1248 0.3098 29.8775 33.5782
0.219 5.0 1560 0.3057 30.629 33.6736
0.219 6.0 1872 0.3026 31.2601 33.854
0.2029 7.0 2184 0.3007 31.6296 33.9687
0.2029 8.0 2496 0.2997 31.6706 33.6327
0.1895 9.0 2808 0.2989 31.5995 33.9904
0.182 10.0 3120 0.2987 31.8518 34.0136

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1