README.md

metadata

language:
  - en
  - he
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - opus100
metrics:
  - bleu
model-index:
  - name: english-hebrew
    results:
      - task:
          name: Translation
          type: translation
        dataset:
          name: opus100 en-he
          type: opus100
          config: en-he
          split: validation
          args: en-he
        metrics:
          - name: Bleu
            type: bleu
            value: 38.2026

english-hebrew

This model is a fine-tuned version of t5-small on the opus100 en-he dataset. It achieves the following results on the evaluation set:

• Loss: 0.2419
• Bleu: 38.2026
• Gen Len: 18.125

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1
• Datasets 2.14.4
• Tokenizers 0.13.3