metadata

license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: t5-big-scratch-iwslt2017
    results:
      - task:
          type: translation
        dataset:
          name: iwslt2017
          type: iwslt2017
        metrics:
          - name: BLEU
            type: BLEU
            value: 26.23
datasets:
  - IWSLT/iwslt2017
language:
  - en
  - de

t5-big-scratch-iwslt2017

Source Code

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.3140
Bleu: 0.2623
Gen Len: 26.3604

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

iwslt2017: https://huggingface.co/datasets/IWSLT/iwslt2017

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.1.2
Datasets 2.19.0
Tokenizers 0.19.1