gbert-base-germaner
This model is a fine-tuned version of deepset/gbert-base on the germaner dataset. It achieves the following results on the evaluation set:
- precision: 0.8521
- recall: 0.8754
- f1: 0.8636
- accuracy: 0.9761
If you want to learn how to fine-tune BERT yourself using Keras and Tensorflow check out this blog post:
https://www.philschmid.de/huggingface-transformers-keras-tf
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:
- num_train_epochs: 5
- train_batch_size: 16
- eval_batch_size: 32
- learning_rate: 2e-05
- weight_decay_rate: 0.01
- num_warmup_steps: 0
- fp16: True
Framework versions
- Transformers 4.14.1
- Datasets 1.16.1
- Tokenizers 0.10.3
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train philschmid/gbert-base-germaner
Evaluation results
- precision on germanerself-reported0.852
- recall on germanerself-reported0.875
- f1 on germanerself-reported0.864
- accuracy on germanerself-reported0.976