pegasus_summarization_pretrained

This model is a fine-tuned version of google/pegasus-xsum on the billsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.9463
• Rouge1: 0.3979
• Rouge2: 0.1963
• Rougel: 0.2889
• Rougelsum: 0.2887
• Gen Len: 61.9919

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: 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	124	2.0226	0.3896	0.1882	0.2838	0.2839	61.5444
No log	2.0	248	1.9736	0.3991	0.1963	0.291	0.2907	61.9194
No log	3.0	372	1.9542	0.3977	0.196	0.2889	0.2885	61.9718
No log	4.0	496	1.9463	0.3979	0.1963	0.2889	0.2887	61.9919

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3