metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
base_model: distilbert-base-german-cased
model-index:
- name: distilbert-base-german-cased-finetuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: wikiann
type: wikiann
config: de
split: validation
args: de
metrics:
- type: precision
value: 0.8400889939511924
name: Precision
- type: recall
value: 0.8744391373570705
name: Recall
- type: f1
value: 0.8569199673770433
name: F1
- type: accuracy
value: 0.9548258089954094
name: Accuracy
distilbert-base-german-cased-finetuned-ner
This model is a fine-tuned version of distilbert-base-german-cased on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1871
- Precision: 0.8401
- Recall: 0.8744
- F1: 0.8569
- Accuracy: 0.9548
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1785 | 1.0 | 2500 | 0.1728 | 0.8134 | 0.8414 | 0.8271 | 0.9490 |
| 0.1252 | 2.0 | 5000 | 0.1743 | 0.8434 | 0.8659 | 0.8545 | 0.9545 |
| 0.0867 | 3.0 | 7500 | 0.1871 | 0.8401 | 0.8744 | 0.8569 | 0.9548 |
Framework versions
- Transformers 4.27.3
- Pytorch 2.0.0+cu118
- Datasets 2.10.1
- Tokenizers 0.13.2