bart-large-cnn-pubmed1o3-pubmed2o3-pubmed3o3

This model is a fine-tuned version of theojolliffe/bart-large-cnn-pubmed1o3-pubmed2o3 on the scientific_papers dataset. It achieves the following results on the evaluation set:

• Loss: 1.8540
• Rouge1: 37.5622
• Rouge2: 15.5848
• Rougel: 23.1384
• Rougelsum: 34.2695
• Gen Len: 138.0326

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.9205	1.0	19987	1.8540	37.5622	15.5848	23.1384	34.2695	138.0326

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1