bart-large-cnn-finetuned-scope-summarization

This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1120
• Rouge1: 51.232
• Rouge2: 37.3103
• Rougel: 39.2783
• Rougelsum: 39.2011

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.6379	1.0	40	0.2289	45.9991	29.5151	34.3864	34.3984
0.2731	2.0	80	0.1935	47.3991	33.1933	38.1538	38.0514
0.2362	3.0	120	0.1734	47.4125	32.2496	35.7852	35.8279
0.222	4.0	160	0.1665	46.2226	32.0249	37.016	36.8941
0.2005	5.0	200	0.1530	50.1647	35.1015	39.0526	39.0721
0.1971	6.0	240	0.1434	49.7914	35.5371	39.2372	39.244
0.1754	7.0	280	0.1286	49.8482	35.7536	40.2412	40.2248
0.1777	8.0	320	0.1187	51.6342	38.223	41.4109	41.3626
0.1555	9.0	360	0.1149	49.1858	36.1404	38.857	38.7268
0.1415	10.0	400	0.1120	51.232	37.3103	39.2783	39.2011

Framework versions

• Transformers 4.44.2
• Pytorch 2.2.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1