metadata
license: apache-2.0
base_model: mschiesser/ner-bert-german
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-bert-german-addresses-finetuned
results: []
ner-bert-german-addresses-finetuned
This model is a fine-tuned version of mschiesser/ner-bert-german on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 119277683740048950636180406272.0000
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.0554
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|
| 119256740913612858296522244096.0000 | 1.0 | 37824 | 119277683740048950636180406272.0000 | 0.0 | 0.0 | 0.0 | 0.0554 |
| 119310513934069312076401082368.0000 | 2.0 | 75648 | 119277683740048950636180406272.0000 | 0.0 | 0.0 | 0.0 | 0.0554 |
| 119261634645330652545184432128.0000 | 3.0 | 113472 | 119277683740048950636180406272.0000 | 0.0 | 0.0 | 0.0 | 0.0554 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.15.2