metadata
base_model: google/pegasus-large
tags:
- summarization
- generated_from_trainer
datasets:
- scientific_papers
metrics:
- rouge
model-index:
- name: pegasus-large-finetuned-scientific-articles
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: scientific_papers
type: scientific_papers
config: pubmed
split: train
args: pubmed
metrics:
- name: Rouge1
type: rouge
value: 32.8743
pegasus-large-finetuned-scientific-articles
This model is a fine-tuned version of google/pegasus-large on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 2.4553
- Rouge1: 32.8743
- Rouge2: 10.8417
- Rougel: 20.3101
- Rougelsum: 28.3673
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.0377 | 1.0 | 252 | 2.5409 | 30.5637 | 9.5168 | 18.2596 | 26.2196 |
| 2.6145 | 2.0 | 504 | 2.4722 | 31.5518 | 9.9698 | 19.9187 | 26.695 |
| 2.4322 | 3.0 | 756 | 2.4553 | 32.8743 | 10.8417 | 20.3101 | 28.3673 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1