cnn_news_summary_model_trained_on_reduced_data

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

• Loss: 1.6040
• Rouge1: 0.2183
• Rouge2: 0.0946
• Rougel: 0.1843
• Rougelsum: 0.1842
• Generated Length: 19.0

Model Description

The developers of the Text-To-Text Transfer Transformer (T5) write:

With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task.

T5-Small is the checkpoint with 60 million parameters.

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	Generated Length
No log	1.0	431	1.6239	0.2171	0.0934	0.1827	0.1827	19.0
1.9203	2.0	862	1.6075	0.2166	0.0937	0.1828	0.1827	19.0
1.822	3.0	1293	1.6040	0.2183	0.0946	0.1843	0.1842	19.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Tokenizers 0.19.1