flan-t5-base-billsum

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

• Loss: nan
• Rouge1: 14.041
• Rouge2: 6.012
• Rougel: 11.3068
• Rougelsum: 12.0551
• Gen Len: 16.0610

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0	1.0	2359	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	2.0	4718	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	3.0	7077	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	4.0	9436	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	5.0	11795	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	6.0	14154	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	7.0	16513	nan	14.041	6.012	11.3068	12.0551	16.0610
0.0	8.0	18872	nan	14.041	6.012	11.3068	12.0551	16.0610

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3