---
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: greek_legal_bert_v2-finetuned-ner
  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. -->

# greek_legal_bert_v2-finetuned-ner

This model is a fine-tuned version of [alexaapo/greek_legal_bert_v2](https://huggingface.co/alexaapo/greek_legal_bert_v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1034
- Precision: 0.7143
- Recall: 0.8010
- F1: 0.7551
- Accuracy: 0.9713

## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 0.77  | 20   | 0.2736          | 0.4615    | 0.1748 | 0.2535 | 0.9064   |
| No log        | 1.54  | 40   | 0.1339          | 0.7030    | 0.6893 | 0.6961 | 0.9583   |
| No log        | 2.31  | 60   | 0.1034          | 0.7143    | 0.8010 | 0.7551 | 0.9713   |


### Framework versions

- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1