Edit model card

MelioAI/machine-translation

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

  • Train Loss: 2.0883
  • Validation Loss: 1.8536
  • Epoch: 0

Model description

This is a machine translation model utilized for translating from English to French, based on the tutorial: Hugging Face Translation Example.

Intended uses & limitations

This model is made for the purposes of showing how to use Highwind only.

Training and evaluation data

  • Train Loss: 2.0883
  • Validation Loss: 1.8536
  • Epoch: 0

Training hyperparameters

The following hyperparameters were used during training:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
2.0883 1.8536 0

Framework versions

  • Transformers 4.40.2
  • TensorFlow 2.16.1
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
4

Finetuned from