t5-small-finetuned-xsum

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

• Loss: 2.5400
• Rouge1: 27.4606
• Rouge2: 7.3882
• Rougel: 21.5683
• Rougelsum: 21.5769
• Gen Len: 18.8013

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: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.8393	1.0	2500	2.5833	26.7701	6.8545	20.9017	20.9024	18.8193
2.7625	2.0	5000	2.5494	27.2012	7.1774	21.2519	21.2529	18.8019
2.7673	3.0	7500	2.5400	27.4606	7.3882	21.5683	21.5769	18.8013

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1