my_awesome_billsum_model

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

• Loss: 1.1625
• Rouge1: 0.6895
• Rouge2: 0.6293
• Rougel: 0.68
• Rougelsum: 0.6806
• Gen Len: 18.9435

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	62	1.6092	0.4863	0.3176	0.4329	0.4324	18.6411
No log	2.0	124	1.3017	0.3808	0.2673	0.3329	0.3336	18.9274
No log	3.0	186	1.1907	0.6411	0.5725	0.6234	0.6247	18.9637
No log	4.0	248	1.1625	0.6895	0.6293	0.68	0.6806	18.9435

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2