crawler_cat_brick_model
This model is a fine-tuned version of dbmdz/bert-base-german-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9439
- Precision: 0.8768
- Recall: 0.8768
- F1: 0.8768
- Accuracy: 0.8768
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
1.9828 | 1.0 | 5026 | 1.7270 | 0.7746 | 0.7746 | 0.7746 | 0.7746 |
1.2807 | 2.0 | 10052 | 1.3068 | 0.8189 | 0.8189 | 0.8189 | 0.8189 |
0.9826 | 3.0 | 15078 | 1.0816 | 0.8535 | 0.8535 | 0.8535 | 0.8535 |
0.6745 | 4.0 | 20104 | 0.9756 | 0.8699 | 0.8699 | 0.8699 | 0.8699 |
0.5616 | 5.0 | 25130 | 0.9439 | 0.8768 | 0.8768 | 0.8768 | 0.8768 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5