<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-german-cased-finetuned-subj_v6_7Epoch
This model is a fine-tuned version of bert-base-german-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2836
- Precision: 0.7809
- Recall: 0.7229
- F1: 0.7507
- Accuracy: 0.9107
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 33 | 0.3541 | 0.6508 | 0.5486 | 0.5953 | 0.8520 |
| No log | 2.0 | 66 | 0.2815 | 0.7492 | 0.6314 | 0.6853 | 0.8836 |
| No log | 3.0 | 99 | 0.2659 | 0.7615 | 0.7114 | 0.7356 | 0.9015 |
| No log | 4.0 | 132 | 0.2570 | 0.7812 | 0.7343 | 0.7570 | 0.9113 |
| No log | 5.0 | 165 | 0.2676 | 0.7672 | 0.7343 | 0.7504 | 0.9084 |
| No log | 6.0 | 198 | 0.2791 | 0.7774 | 0.7286 | 0.7522 | 0.9113 |
| No log | 7.0 | 231 | 0.2836 | 0.7809 | 0.7229 | 0.7507 | 0.9107 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
