metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-german-cased-20000-ner
results: []
bert-base-german-cased-20000-ner
This model is a fine-tuned version of bert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0527
- Precision: 0.7423
- Recall: 0.8643
- F1: 0.7987
- Accuracy: 0.9879
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.1 | 64 | 0.0867 | 0.5127 | 0.8679 | 0.6446 | 0.975 |
| No log | 0.19 | 128 | 0.0539 | 0.4549 | 0.8643 | 0.5961 | 0.9774 |
| No log | 0.29 | 192 | 0.0382 | 0.7763 | 0.8429 | 0.8082 | 0.9902 |
| No log | 0.38 | 256 | 0.0405 | 0.7697 | 0.8714 | 0.8174 | 0.9898 |
| No log | 0.48 | 320 | 0.0292 | 0.8027 | 0.8429 | 0.8223 | 0.9923 |
| No log | 0.58 | 384 | 0.0478 | 0.7227 | 0.875 | 0.7916 | 0.9875 |
| No log | 0.67 | 448 | 0.0293 | 0.7774 | 0.8107 | 0.7937 | 0.9918 |
| 0.09 | 0.77 | 512 | 0.0527 | 0.7423 | 0.8643 | 0.7987 | 0.9879 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.9.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1