t5-small-billsum

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

• Loss: 1.9564
• Rouge1: 50.3551
• Rouge2: 29.3717
• Rougel: 39.4102
• Rougelsum: 43.6247

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.5468	1.0	1185	2.0937	48.625	27.492	37.671	41.4628
2.2867	2.0	2370	2.0155	49.2547	28.248	38.39	42.3374
2.2241	3.0	3555	1.9796	49.8802	28.8333	38.8829	43.027
2.1925	4.0	4740	1.9620	50.07	28.9961	39.1086	43.3251
2.1791	5.0	5925	1.9576	50.2626	29.1819	39.2415	43.4781

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1