test_summarizer

This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:

• Loss: 4.5382
• Rouge1: 0.1355
• Rouge2: 0.0377
• Rougel: 0.0999
• Rougelsum: 0.0999
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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	1	4.6430	0.1355	0.0377	0.0999	0.0999	19.0
No log	2.0	2	4.5914	0.1355	0.0377	0.0999	0.0999	19.0
No log	3.0	3	4.5562	0.1355	0.0377	0.0999	0.0999	19.0
No log	4.0	4	4.5382	0.1355	0.0377	0.0999	0.0999	19.0

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1
• Datasets 2.9.0
• Tokenizers 0.13.2