Hugging Face's logo

andituebingen
/
t5-MT-de-en

Safetensors
German
English
t5
Generated from Trainer
Eval Results
Model card Files Community
t5-MT-de-en / README.md
andituebingen's picture
andituebingen
initial commit with all files after finetuning
11bef88 verified
preview code
|
raw
history blame contribute delete
1.48 kB
metadata
language:
  - de
  - en
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
datasets:
  - Helsinki-NLP/opus-100
metrics:
  - bleu
model-index:
  - name: COLABDATA
    results:
      - task:
          name: Translation
          type: translation
        dataset:
          name: Helsinki-NLP/opus-100 de-en
          type: Helsinki-NLP/opus-100
          args: de-en
        metrics:
          - name: Bleu
            type: bleu
            value: 30.5988

COLABDATA

This model is a fine-tuned version of google-t5/t5-small on the Helsinki-NLP/opus-100 de-en dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7967
  • Bleu: 30.5988
  • Gen Len: 20.0945

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: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1