t5-large-billsum

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

• Loss: 1.3660
• Rouge1: 54.3212
• Rouge2: 34.3078
• Rougel: 43.7536
• Rougelsum: 47.5193

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
1.6948	1.0	1250	1.4332	52.7319	33.508	42.6688	46.3992
1.4965	2.0	2500	1.3864	53.6841	33.9189	43.3753	46.951
1.4333	3.0	3750	1.3707	54.2166	34.2285	43.5537	47.2979
1.4006	4.0	5000	1.3660	54.3212	34.3078	43.7536	47.5193

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1