Lvxue's picture
update model card README.md
584a600
metadata
language:
  - en
  - ro
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
metrics:
  - bleu
model-index:
  - name: distilled-mt5-small-0.03-1
    results:
      - task:
          name: Translation
          type: translation
        dataset:
          name: wmt16 ro-en
          type: wmt16
          args: ro-en
        metrics:
          - name: Bleu
            type: bleu
            value: 7.1839

distilled-mt5-small-0.03-1

This model is a fine-tuned version of google/mt5-small on the wmt16 ro-en dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8063
  • Bleu: 7.1839
  • Gen Len: 45.5733

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: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.3.2
  • Tokenizers 0.12.1