---
license: cc-by-sa-4.0
base_model: raminass/scotus-v10
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: SCOTUS_AI_V17_CURCUIT_V1
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# SCOTUS_AI_V17_CURCUIT_V1

This model is a fine-tuned version of [raminass/scotus-v10](https://huggingface.co/raminass/scotus-v10) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3007
- Accuracy: 0.7500

## 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: 7

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.7967        | 1.0   | 2167  | 0.9836          | 0.7086   |
| 0.4558        | 2.0   | 4334  | 0.8871          | 0.7430   |
| 0.2722        | 3.0   | 6501  | 0.9650          | 0.7471   |
| 0.146         | 4.0   | 8668  | 1.0709          | 0.7484   |
| 0.1076        | 5.0   | 10835 | 1.2135          | 0.7444   |
| 0.0591        | 6.0   | 13002 | 1.2494          | 0.7522   |
| 0.0454        | 7.0   | 15169 | 1.3007          | 0.7500   |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2