metadata
license: mit
tags:
- generated_from_trainer
datasets:
- germa_ner
metrics:
- precision
- recall
- f1
- accuracy
base_model: bert-base-german-cased
model-index:
- name: bert-base-german-cased-fine-tuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: germa_ner
type: germa_ner
args: default
metrics:
- type: precision
value: 0.8089260808926081
name: Precision
- type: recall
value: 0.872836719337848
name: Recall
- type: f1
value: 0.8396670285921101
name: F1
- type: accuracy
value: 0.9748511630761677
name: Accuracy
bert-base-german-cased-fine-tuned-ner
This model is a fine-tuned version of bert-base-german-cased on the germa_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0966
- Precision: 0.8089
- Recall: 0.8728
- F1: 0.8397
- Accuracy: 0.9749
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.159 | 1.0 | 737 | 0.0922 | 0.7472 | 0.8461 | 0.7936 | 0.9703 |
| 0.0714 | 2.0 | 1474 | 0.0916 | 0.7886 | 0.8713 | 0.8279 | 0.9731 |
| 0.0319 | 3.0 | 2211 | 0.0966 | 0.8089 | 0.8728 | 0.8397 | 0.9749 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.9.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1