bart-large-xsum-dc

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

• Loss: 1.6335
• Rouge1: 32.0323
• Rouge2: 14.1008
• Rougel: 24.5596
• Rougelsum: 25.6498

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
1.9052	1.0	2676	1.7569	30.4785	12.762	23.1862	23.9824
1.4258	2.0	5352	1.5930	31.7087	13.5933	23.9115	24.7093
1.1141	3.0	8028	1.5729	32.3123	14.3572	24.8666	25.856
0.8621	4.0	10704	1.6335	32.0323	14.1008	24.5596	25.6498

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2