bart-large-combined

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: 2.1837
• Rouge1: 40.9079
• Rouge2: 15.6807
• Rougel: 27.7883
• Rougelsum: 37.5415
• Gen Len: 95.0854

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
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.2593	1.0	5435	2.2562	39.8535	14.987	26.8435	36.4216	96.1483
1.8173	2.0	10870	2.1837	40.9079	15.6807	27.7883	37.5415	95.0854
1.4421	3.0	16305	2.2059	41.3435	15.9165	28.0347	37.9954	96.1373

Framework versions

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