---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mbert-finnic-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. -->

# mbert-finnic-ner

This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the Finnish and Estonian parts of the "WikiANN" dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1427
- Precision: 0.9090
- Recall: 0.9156
- F1: 0.9123
- Accuracy: 0.9672

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1636        | 1.0   | 2188 | 0.1385          | 0.8906    | 0.9000 | 0.8953 | 0.9601   |
| 0.0991        | 2.0   | 4376 | 0.1346          | 0.9099    | 0.9095 | 0.9097 | 0.9660   |
| 0.0596        | 3.0   | 6564 | 0.1427          | 0.9090    | 0.9156 | 0.9123 | 0.9672   |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6