bart-large-cnn-finetuned-xsum

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

• Loss: 3.7973
• Rouge1: 24.5661
• Rouge2: 8.6188
• Rougel: 17.1387
• Rougelsum: 18.869
• Gen Len: 73.1667

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-08
• train_batch_size: 3
• eval_batch_size: 3
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	24	3.7983	24.5842	8.6062	17.0846	18.8412	73.3472
No log	2.0	48	3.7973	24.5661	8.6188	17.1387	18.869	73.1667

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2