pegasus-samsum

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

• Loss: 1.3577

Model description

Check out this notebook for the details of model training

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training loss and epoch

Training Loss	Epoch	Step	Validation Loss
1.6489	0.54	500	1.4894
1.578	1.09	1000	1.4044
1.3577	1.63	1500	1.3774
1.4376	2.17	2000	1.3639
1.3881	2.72	2500	1.3577

ROUGE Score

	rouge1	rouge2	rougeL	rougeLsum
pegasus	0.437429	0.20874	0.346974	0.34701

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2