legal-bart-base

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

• Loss: 2.5994
• Rouge1: 27.0214
• Rouge2: 10.6408
• Rougel: 23.7088
• Rougelsum: 24.2952
• Gen Len: 15.7444

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: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	45	2.6655	27.2712	11.3577	24.0401	24.6116	15.0778
No log	2.0	90	2.5994	27.0214	10.6408	23.7088	24.2952	15.7444

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0