---
tags:
- generated_from_trainer
model-index:
- name: legal-greek-roberta-base
  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. -->

# legal-greek-roberta-base

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5247

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: tpu
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 200000

### Training results

| Training Loss | Epoch | Step   | Validation Loss |
|:-------------:|:-----:|:------:|:---------------:|
| 0.8724        | 12.0  | 50000  | 0.6730          |
| 0.7713        | 24.0  | 100000 | 0.5763          |
| 0.7186        | 36.0  | 150000 | 0.5396          |
| 0.7152        | 48.0  | 200000 | 0.5247          |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.9.0
- Tokenizers 0.12.0