LifeSciencePegasusLargeModel

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: 5.6523
• Rouge1: 44.7761
• Rouge2: 12.6726
• Rougel: 29.0847
• Rougelsum: 40.7566
• Bertscore Precision: 77.9283
• Bertscore Recall: 81.5854
• Bertscore F1: 79.7092
• Bleu: 0.0886
• Gen Len: 225.7220

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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bertscore Precision	Bertscore Recall	Bertscore F1	Bleu	Gen Len
6.2586	0.2643	300	6.0453	40.1947	11.1082	26.9714	36.2747	76.6344	80.8385	78.6731	0.0775	225.7220
6.0213	0.5286	600	5.7899	43.2445	12.1722	28.4564	39.1524	77.5194	81.3755	79.3945	0.0856	225.7220
5.9018	0.7929	900	5.6523	44.7761	12.6726	29.0847	40.7566	77.9283	81.5854	79.7092	0.0886	225.7220

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.2.1
• Tokenizers 0.19.1