my_awesome_billsum_model

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

• Loss: 1.4680
• Rouge1: 0.5281
• Rouge2: 0.2775
• Rougel: 0.3421
• Rougelsum: 0.4021
• Gen Len: 130.3669

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	495	1.5156	0.5029	0.2538	0.3184	0.3865	131.4073
1.8254	2.0	990	1.4455	0.5102	0.2663	0.3395	0.3949	117.4516
1.2925	3.0	1485	1.4291	0.5212	0.2713	0.3392	0.3944	130.379
0.9936	4.0	1980	1.4680	0.5281	0.2775	0.3421	0.4021	130.3669

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2