SCOTUS_AI_14

This model is a fine-tuned version of raminass/scotus-v10 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7616
• Accuracy: 0.8428

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5382	1.0	1762	0.5732	0.8361
0.3093	2.0	3524	0.6043	0.8392
0.1676	3.0	5286	0.6812	0.8383
0.1001	4.0	7048	0.7386	0.8418
0.0639	5.0	8810	0.7616	0.8428

Justices

Justice	Count
Thomas	571
Scalia	473
Breyer	443
Stevens	407
Ginsburg	390
Kennedy	326
Alito	286
Souter	230
Sotomayor	226
O'Connor	167
Kagan	145
Rehnquist	144
Roberts	123
Gorsuch	109

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0