nikhilwani's picture
End of training
57ec062
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: machine_translation-en-fr-opus
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: en-fr
          split: train
          args: en-fr
        metrics:
          - name: Bleu
            type: bleu
            value: 5.7442

machine_translation-en-fr-opus

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

  • Loss: 1.6074
  • Bleu: 5.7442
  • Gen Len: 17.6073

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: 2

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
1.868 1.0 6355 1.6313 5.5594 17.6238
1.8212 2.0 12710 1.6074 5.7442 17.6073

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3