news_summary_model_trained_on_reduced_data

This model is a fine-tuned version of gsarti/it5-small-news-summarization on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Rouge1: 0.1141
• Rouge2: 0.0402
• Rougel: 0.1005
• Rougelsum: 0.1018
• Generated Length: 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: 4
• eval_batch_size: 4
• 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	9	nan	0.1141	0.0402	0.1005	0.1018	19.0
No log	2.0	18	nan	0.1141	0.0402	0.1005	0.1018	19.0
No log	3.0	27	nan	0.1141	0.0402	0.1005	0.1018	19.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1