README.md

metadata

language:
  - en
  - ro
  - multilingual
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
metrics:
  - bleu
model-index:
  - name: distilled-mt5-small-b20
    results:
      - task:
          type: translation
          name: Translation
        dataset:
          name: wmt16 ro-en
          type: wmt16
          args: ro-en
        metrics:
          - type: bleu
            value: 6.6798
            name: Bleu

distilled-mt5-small-b20

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: 2.8652
• Bleu: 6.6798
• Gen Len: 46.8789

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