metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bigbird-pegasus-large-pubmed-finetuned-xsum
results: []
bigbird-pegasus-large-pubmed-finetuned-xsum
This model is a fine-tuned version of google/bigbird-pegasus-large-pubmed on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1579
- Rouge1: 12.9783
- Rouge2: 0.7286
- Rougel: 12.2627
- Rougelsum: 6.2341
- Gen Len: 156.0
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: 0.002
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 27 | 4.2817 | 0.0 | 0.0 | 0.0 | 0.0 | 256.0 |
| No log | 2.0 | 54 | 3.1579 | 12.9783 | 0.7286 | 12.2627 | 6.2341 | 156.0 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2