This model is a fine-tuned version of sshleifer/distilbart-xsum-12-1 on the ccdv/arxiv-summarization dataset.
It achieves the following results on the evaluation set:
Loss: 4.3066
Rouge1: 35.6639
Rouge2: 10.5717
Rougel: 21.095
Rougelsum: 31.2685
Gen Len: 81.44
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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
