Fine-Tuned-billsum-Summarization

This model is a fine-tuned version of google/pegasus-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8618
• Rouge1: 0.2169
• Rouge2: 0.0916
• Rougel: 0.1809
• Rougelsum: 0.1799
• Generated Length: 104.8158

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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	19	2.3003	0.2218	0.0946	0.1807	0.1792	106.5789
No log	2.0	38	1.9734	0.2164	0.0922	0.1799	0.1789	104.4474
No log	3.0	57	1.8618	0.2169	0.0916	0.1809	0.1799	104.8158

Framework versions

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