bart-large-cnn-ext15

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: 1.9309
• Rouge1: 28.3399
• Rouge2: 9.8878
• Rougel: 20.3979
• Rougelsum: 21.9156

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.3549	1.0	2676	2.0725	27.7488	9.0655	19.7904	21.4815
1.7988	2.0	5352	1.9467	28.0297	9.5377	20.178	21.6432
1.4594	3.0	8028	1.9309	28.3399	9.8878	20.3979	21.9156

Framework versions

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