---
metrics:
- precision
- recall
- f1
- accuracy

model-index:
- name: distilbert-base-multilingual-cased-finetuned-conll2003-ner
---

<!-- 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. -->

# distilbert-base-multilingual-cased-finetuned-conll2003-ner

This model was trained from scratch on an unkown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0635
- Precision: 0.9269
- Recall: 0.9337
- F1: 0.9303
- Accuracy: 0.9835

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2338        | 1.0   | 878  | 0.0753          | 0.9188    | 0.9089 | 0.9138 | 0.9795   |
| 0.0541        | 2.0   | 1756 | 0.0681          | 0.9362    | 0.9278 | 0.9320 | 0.9830   |
| 0.031         | 3.0   | 2634 | 0.0635          | 0.9269    | 0.9337 | 0.9303 | 0.9835   |


### Framework versions

- Transformers 4.6.1
- Pytorch 1.8.1+cu101
- Datasets 1.6.2
- Tokenizers 0.10.2