pegasus-pubmed-finetuned-paws

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

• Loss: 3.5012
• Rouge1: 56.8108
• Rouge2: 36.2576
• Rougel: 51.1666
• Rougelsum: 51.2193

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	0.73	1000	3.8839	51.2731	29.8072	45.767	45.5732
4.071	1.47	2000	3.6459	52.756	31.9185	48.0092	48.0544
3.5467	2.2	3000	3.5849	54.8127	33.1959	49.326	49.4971
3.5467	2.93	4000	3.5267	55.387	33.9516	50.683	50.6313
3.3654	3.66	5000	3.5031	57.5279	35.2664	51.9903	52.258
3.2844	4.4	6000	3.5296	56.0536	33.395	50.9909	51.244

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1