Edit model card

t5-base-finetuned-eli5-a

This model is a fine-tuned version of ammarpl/t5-base-finetuned-xsum-a on the eli5 dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1773
  • Rouge1: 14.6711
  • Rouge2: 2.2878
  • Rougel: 11.3676
  • Rougelsum: 13.1805
  • Gen Len: 18.9892

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 Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.3417 1.0 17040 3.1773 14.6711 2.2878 11.3676 13.1805 18.9892

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.1
  • Tokenizers 0.12.1
Downloads last month
1

Dataset used to train ammarpl/t5-base-finetuned-eli5-a

Evaluation results