---
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Improved-bert-multilingual
  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. -->

# Improved-bert-multilingual

This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0118
- Accuracy: 0.78

## 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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6856        | 0.55  | 50   | 0.6607          | 0.61     |
| 0.5729        | 1.1   | 100  | 0.5453          | 0.73     |
| 0.4649        | 1.65  | 150  | 0.5915          | 0.66     |
| 0.385         | 2.2   | 200  | 0.5824          | 0.7      |
| 0.343         | 2.75  | 250  | 0.4548          | 0.79     |
| 0.305         | 3.3   | 300  | 0.6585          | 0.71     |
| 0.2355        | 3.85  | 350  | 0.6034          | 0.77     |
| 0.2176        | 4.4   | 400  | 0.5191          | 0.79     |
| 0.2137        | 4.95  | 450  | 0.6655          | 0.73     |
| 0.181         | 5.49  | 500  | 0.6929          | 0.78     |
| 0.171         | 6.04  | 550  | 1.0172          | 0.65     |
| 0.1267        | 6.59  | 600  | 0.9904          | 0.67     |
| 0.1152        | 7.14  | 650  | 1.0817          | 0.65     |
| 0.1045        | 7.69  | 700  | 1.1231          | 0.66     |
| 0.0973        | 8.24  | 750  | 1.0118          | 0.78     |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.14.1