gcicontracts

This model is a fine-tuned version of mjbeattie/mjbbillsum on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0721
• Rouge1: 0.2917
• Rouge2: 0.1209
• Rougel: 0.2556
• Rougelsum: 0.2535
• Gen Len: 18.1463

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	11	2.4545	0.3004	0.1333	0.2658	0.2637	18.2927
No log	2.0	22	2.3030	0.3047	0.1397	0.2744	0.2709	18.2927
No log	3.0	33	2.2187	0.3065	0.1416	0.276	0.2718	18.2439
No log	4.0	44	2.1562	0.2926	0.1209	0.2558	0.2538	18.2439
No log	5.0	55	2.1172	0.2926	0.1209	0.2558	0.2538	18.2439
No log	6.0	66	2.0921	0.2914	0.1209	0.2552	0.253	18.1463
No log	7.0	77	2.0786	0.2917	0.1209	0.2556	0.2535	18.1463
No log	8.0	88	2.0721	0.2917	0.1209	0.2556	0.2535	18.1463

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1
• Datasets 2.10.0
• Tokenizers 0.11.0