Hugging Face's logo

autoevaluate
/
translation-not-evaluated

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
translation-not-evaluated / README.md
lewtun's picture
lewtun HF staff
Update README.md
4feeb4f
preview code
|
raw
history blame contribute delete
1.46 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
  - autoevaluate/wmt16-sample
metrics:
  - bleu
duplicated_from: autoevaluate/translation

translation

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ro on the wmt16 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3170
  • Bleu: 28.5866
  • Gen Len: 33.9575

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
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.8302 0.03 1000 1.3170 28.5866 33.9575

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1