Edit model card

pegasus-large_readme_summarization

This model is a fine-tuned version of google/pegasus-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9252
  • Rouge1: 0.4628
  • Rouge2: 0.3297
  • Rougel: 0.4358
  • Rougelsum: 0.4352
  • Gen Len: 35.4784

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.2254 1.0 5831 2.0508 0.4183 0.2886 0.3888 0.3886 47.4245
2.0129 2.0 11662 1.9589 0.4437 0.3144 0.4154 0.4145 45.0024
1.8783 3.0 17493 1.9290 0.4598 0.3253 0.4308 0.4301 37.8441
1.6891 4.0 23324 1.9252 0.4628 0.3297 0.4358 0.4352 35.4784

Framework versions

  • Transformers 4.35.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
7
Safetensors
Model size
571M params
Tensor type
F32
·

Finetuned from