t5-small-train / README.md
Miranda's picture
update model card README.md
79ec751
|
raw
history blame
2.12 kB
metadata
license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: t5-small-train
    results: []

t5-small-train

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

  • Loss: 2.3623
  • Rouge1: 40.5101
  • Rouge2: 19.0112
  • Rougel: 35.5748
  • Rougelsum: 35.9291

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
3.1374 1.0 45 2.6906 34.9598 15.4159 30.7378 30.9607
2.598 2.0 90 2.5073 38.2818 16.4572 34.168 34.1708
2.4287 3.0 135 2.4314 40.0863 18.3821 35.1633 35.441
2.3109 4.0 180 2.3939 40.3133 18.9829 35.6333 35.8475
2.2234 5.0 225 2.3762 40.405 18.7467 35.7971 36.035
2.2274 6.0 270 2.3686 40.507 18.8308 35.5185 35.8219
2.1655 7.0 315 2.3644 40.468 19.0659 35.6811 35.9991
2.1741 8.0 360 2.3623 40.5101 19.0112 35.5748 35.9291

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1