---
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- generator
metrics:
- accuracy
model-index:
- name: mBERT-4
  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. -->

# mBERT-4

This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6556
- Accuracy: 0.8684
- Micro Precision: 0.8684
- Micro Recall: 0.8684
- Micro F1: 0.8684
- Macro Precision: 0.7082
- Macro Recall: 0.7108
- Macro F1: 0.6956

## 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: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
| 1.4568        | 1.0   | 868  | 0.6532          | 0.8105   | 0.8105          | 0.8105       | 0.8105   | 0.4658          | 0.4779       | 0.4577   |
| 0.6665        | 2.0   | 1736 | 0.4579          | 0.8789   | 0.8789          | 0.8789       | 0.8789   | 0.7403          | 0.7275       | 0.7240   |
| 0.4735        | 3.0   | 2604 | 0.4363          | 0.8737   | 0.8737          | 0.8737       | 0.8737   | 0.6803          | 0.6664       | 0.6622   |
| 0.352         | 4.0   | 3472 | 0.4537          | 0.8737   | 0.8737          | 0.8737       | 0.8737   | 0.7160          | 0.6909       | 0.6991   |
| 0.2391        | 5.0   | 4340 | 0.5271          | 0.8789   | 0.8789          | 0.8789       | 0.8789   | 0.7445          | 0.7186       | 0.7231   |
| 0.176         | 6.0   | 5208 | 0.5275          | 0.8895   | 0.8895          | 0.8895       | 0.8895   | 0.7469          | 0.7596       | 0.7410   |
| 0.108         | 7.0   | 6076 | 0.6555          | 0.8737   | 0.8737          | 0.8737       | 0.8737   | 0.7634          | 0.7744       | 0.7496   |
| 0.0903        | 8.0   | 6944 | 0.6556          | 0.8684   | 0.8684          | 0.8684       | 0.8684   | 0.7082          | 0.7108       | 0.6956   |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3