Edit model card

t5-small-finetuned-en-to-ro-fp16_off

This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8351
  • Bleu: 5.9132
  • Gen Len: 18.2656

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
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.8501 1.0 7629 1.8351 5.9132 18.2656

Framework versions

  • Transformers 4.12.5
  • Pytorch 1.10.0+cu111
  • Datasets 1.16.1
  • Tokenizers 0.10.3
Downloads last month
1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train eliotm/t5-small-finetuned-en-to-ro-fp16_off

Evaluation results