<!-- 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-200labels
This model is a fine-tuned version of ogimgio/bert-base-german-cased-finetuned-7labels on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0744
- Micro f1: 0.0894
- Macro f1: 0.0538
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: 3e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Micro f1 | Macro f1 |
|---|---|---|---|---|---|
| 0.8041 | 1.0 | 1380 | 0.7312 | 0.0422 | 0.0413 |
| 0.605 | 2.0 | 2760 | 0.5440 | 0.0436 | 0.0423 |
| 0.4455 | 3.0 | 4140 | 0.4026 | 0.0478 | 0.0449 |
| 0.3317 | 4.0 | 5520 | 0.3070 | 0.0574 | 0.0516 |
| 0.2553 | 5.0 | 6900 | 0.2432 | 0.0682 | 0.0599 |
| 0.2041 | 6.0 | 8280 | 0.1982 | 0.0759 | 0.0657 |
| 0.167 | 7.0 | 9660 | 0.1653 | 0.0798 | 0.0677 |
| 0.1403 | 8.0 | 11040 | 0.1417 | 0.0839 | 0.0693 |
| 0.1222 | 9.0 | 12420 | 0.1249 | 0.0865 | 0.0695 |
| 0.109 | 10.0 | 13800 | 0.1132 | 0.0880 | 0.0684 |
| 0.0999 | 11.0 | 15180 | 0.1052 | 0.0874 | 0.0661 |
| 0.0941 | 12.0 | 16560 | 0.0994 | 0.0878 | 0.0655 |
| 0.089 | 13.0 | 17940 | 0.0951 | 0.0876 | 0.0640 |
| 0.0854 | 14.0 | 19320 | 0.0917 | 0.0888 | 0.0638 |
| 0.0831 | 15.0 | 20700 | 0.0890 | 0.0889 | 0.0626 |
| 0.0804 | 16.0 | 22080 | 0.0869 | 0.0890 | 0.0616 |
| 0.0788 | 17.0 | 23460 | 0.0851 | 0.0890 | 0.0606 |
| 0.077 | 18.0 | 24840 | 0.0835 | 0.0894 | 0.0599 |
| 0.0759 | 19.0 | 26220 | 0.0822 | 0.0894 | 0.0593 |
| 0.0745 | 20.0 | 27600 | 0.0811 | 0.0896 | 0.0588 |
| 0.0735 | 21.0 | 28980 | 0.0800 | 0.0890 | 0.0573 |
| 0.0728 | 22.0 | 30360 | 0.0791 | 0.0888 | 0.0564 |
| 0.0716 | 23.0 | 31740 | 0.0783 | 0.0895 | 0.0559 |
| 0.0709 | 24.0 | 33120 | 0.0775 | 0.0900 | 0.0556 |
| 0.0698 | 25.0 | 34500 | 0.0768 | 0.0896 | 0.0550 |
| 0.0694 | 26.0 | 35880 | 0.0761 | 0.0897 | 0.0548 |
| 0.069 | 27.0 | 37260 | 0.0755 | 0.0892 | 0.0545 |
| 0.0684 | 28.0 | 38640 | 0.0750 | 0.0893 | 0.0541 |
| 0.0679 | 29.0 | 40020 | 0.0744 | 0.0894 | 0.0538 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.8.0
- Tokenizers 0.12.1
