Edit model card

opus-mt-sla-en-finetuned-uk-to-en

This model is a fine-tuned version of Helsinki-NLP/opus-mt-sla-en on the opus100 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7232
  • Bleu: 27.7684
  • Gen Len: 12.2485

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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
1.5284 1.0 62500 1.7232 27.7684 12.2485

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1
Downloads last month
10

Dataset used to train stopdoingmath/opus-mt-sla-en-finetuned-uk-to-en

Evaluation results