---
license: cc-by-sa-4.0
tags:
- generated_from_trainer
model-index:
- name: legalbert-adept
  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. -->

# legalbert-adept

This model is a fine-tuned version of [hatemestinbejaia/AkeyLegalBert6](https://huggingface.co/hatemestinbejaia/AkeyLegalBert6) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0195

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 147  | 4.3797          |
| No log        | 2.0   | 294  | 4.4473          |
| No log        | 3.0   | 441  | 4.3182          |
| 4.4392        | 4.0   | 588  | 4.2805          |
| 4.4392        | 5.0   | 735  | 4.1713          |
| 4.4392        | 6.0   | 882  | 4.1788          |
| 4.2144        | 7.0   | 1029 | 4.0856          |
| 4.2144        | 8.0   | 1176 | 4.1807          |
| 4.2144        | 9.0   | 1323 | 4.0702          |
| 4.2144        | 10.0  | 1470 | 4.0613          |
| 4.0493        | 11.0  | 1617 | 4.0758          |
| 4.0493        | 12.0  | 1764 | 4.0599          |
| 4.0493        | 13.0  | 1911 | 4.0246          |
| 3.952         | 14.0  | 2058 | 4.0312          |
| 3.952         | 15.0  | 2205 | 4.1122          |
| 3.952         | 16.0  | 2352 | 4.1250          |
| 3.952         | 17.0  | 2499 | 4.0470          |
| 3.926         | 18.0  | 2646 | 4.1016          |
| 3.926         | 19.0  | 2793 | 3.9823          |
| 3.926         | 20.0  | 2940 | 3.9977          |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1