metadata
base_model: google/pegasus-xsum
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: pegasus-xsum_readme_summarization
results: []
pegasus-xsum_readme_summarization
This model is a fine-tuned version of google/pegasus-xsum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3151
- Rouge1: 0.4555
- Rouge2: 0.313
- Rougel: 0.43
- Rougelsum: 0.4306
- Gen Len: 20.4628
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 |
|---|---|---|---|---|---|---|---|---|
| 2.734 | 1.0 | 5831 | 2.4629 | 0.445 | 0.2988 | 0.417 | 0.4173 | 20.8801 |
| 2.5168 | 2.0 | 11662 | 2.3496 | 0.4549 | 0.3112 | 0.4284 | 0.4286 | 19.6043 |
| 2.3507 | 3.0 | 17493 | 2.3132 | 0.4555 | 0.3133 | 0.4295 | 0.429 | 20.747 |
| 2.2409 | 4.0 | 23324 | 2.3151 | 0.4555 | 0.313 | 0.43 | 0.4306 | 20.4628 |
Framework versions
- Transformers 4.35.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1