README.md

metadata

language:
  - de
license: mit
datasets:
  - germaner
metrics:
  - precision
  - recall
  - f1
  - accuracy
base_model: deepset/gbert-large
model-index:
  - name: gbert-large-germaner
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: germaner
          type: germaner
          args: default
        metrics:
          - type: precision
            value: 0.8693333333333333
            name: precision
          - type: recall
            value: 0.885640362225097
            name: recall
          - type: f1
            value: 0.8774110861903236
            name: f1
          - type: accuracy
            value: 0.9784210744831022
            name: accuracy

gbert-large-germaner

This model is a fine-tuned version of deepset/gbert-large on the germaner dataset. It achieves the following results on the evaluation set:

• precision: 0.8693
• recall: 0.8856
• f1: 0.8774
• accuracy: 0.9784

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: 8
• eval_batch_size: 8
• learning_rate: 2e-05
• weight_decay_rate: 0.01
• num_warmup_steps: 0
• fp16: True

Framework versions

• Transformers 4.18.0
• Datasets 1.18.0
• Tokenizers 0.12.1