---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-german-cased-own-data-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. -->

# bert-base-german-cased-own-data-ner

This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0651
- Precision: 0.5643
- Recall: 0.8464
- F1: 0.6771
- Accuracy: 0.9847

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 160  | 0.0566          | 0.5288    | 0.8536 | 0.6530 | 0.9809   |
| No log        | 2.0   | 320  | 0.0385          | 0.7811    | 0.8286 | 0.8042 | 0.9917   |
| No log        | 3.0   | 480  | 0.0380          | 0.7867    | 0.8429 | 0.8138 | 0.9920   |
| 0.0599        | 4.0   | 640  | 0.0473          | 0.7476    | 0.8464 | 0.7940 | 0.9907   |
| 0.0599        | 5.0   | 800  | 0.0566          | 0.5939    | 0.8357 | 0.6944 | 0.9861   |
| 0.0599        | 6.0   | 960  | 0.0562          | 0.6466    | 0.8429 | 0.7318 | 0.9878   |
| 0.0162        | 7.0   | 1120 | 0.0575          | 0.6364    | 0.85   | 0.7278 | 0.9876   |
| 0.0162        | 8.0   | 1280 | 0.0651          | 0.5643    | 0.8464 | 0.6771 | 0.9847   |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.9.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1