pegasus-large-dc

This model is a fine-tuned version of google/pegasus-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8597
• Rouge1: 27.3461
• Rouge2: 10.0857
• Rougel: 20.6354
• Rougelsum: 21.3828

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: 5.6e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.5358	1.0	5351	2.1224	27.1433	9.5692	20.2667	20.9626
2.1878	2.0	10702	1.9799	27.25	10.0184	20.5798	21.3154
2.0224	3.0	16053	1.9143	27.2012	10.032	20.618	21.2959
1.9216	4.0	21404	1.8710	27.2179	10.0579	20.5572	21.3016
1.8644	5.0	26755	1.8597	27.3461	10.0857	20.6354	21.3828

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2