t5-small-finetuned-xsum

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

• Loss: 2.8056
• Rouge1: 16.8725
• Rouge2: 2.4419
• Rougel: 15.739
• Rougelsum: 15.7732
• Gen Len: 19.0

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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.69	1.0	584	2.9680	16.6251	2.1336	15.551	15.606	18.9812
3.2113	2.0	1168	2.8383	17.0265	2.4793	15.8903	15.9416	19.0
3.0921	3.0	1752	2.8056	16.8725	2.4419	15.739	15.7732	19.0

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu118
• Datasets 2.17.0
• Tokenizers 0.15.1