Edit model card

t5-small-finetuned-pubmed

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

  • Loss: 2.7252
  • Rouge1: 19.4457
  • Rouge2: 3.125
  • Rougel: 18.3168
  • Rougelsum: 18.5625

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: 5.6e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
3.2735 1.0 13 2.9820 18.745 3.7918 15.7876 15.8512
3.0428 2.0 26 2.8828 17.953 2.5 15.49 15.468
2.6259 3.0 39 2.8283 21.5532 5.9278 19.7523 19.9232
3.0795 4.0 52 2.7910 20.9244 5.9278 19.8685 20.0181
2.8276 5.0 65 2.7613 20.6403 3.125 18.0574 18.2227
2.64 6.0 78 2.7404 19.4457 3.125 18.3168 18.5625
2.5525 7.0 91 2.7286 19.4457 3.125 18.3168 18.5625
2.4951 8.0 104 2.7252 19.4457 3.125 18.3168 18.5625

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
12
Inference Examples
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.