<!-- 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-notrandom
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: 0.1007
- Micro f1: 0.1030
- Macro f1: 0.0788
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 |
|---|---|---|---|---|---|
| 0.8788 | 1.0 | 1380 | 0.8018 | 0.0855 | 0.0920 |
| 0.6458 | 2.0 | 2760 | 0.5829 | 0.0884 | 0.0939 |
| 0.4631 | 3.0 | 4140 | 0.4213 | 0.0942 | 0.0963 |
| 0.3375 | 4.0 | 5520 | 0.3143 | 0.1044 | 0.0997 |
| 0.2539 | 5.0 | 6900 | 0.2436 | 0.1091 | 0.1018 |
| 0.1987 | 6.0 | 8280 | 0.1944 | 0.1098 | 0.1003 |
| 0.1598 | 7.0 | 9660 | 0.1592 | 0.1094 | 0.0964 |
| 0.1326 | 8.0 | 11040 | 0.1349 | 0.1097 | 0.0937 |
| 0.1148 | 9.0 | 12420 | 0.1185 | 0.1089 | 0.0894 |
| 0.1025 | 10.0 | 13800 | 0.1077 | 0.1066 | 0.0839 |
| 0.0946 | 11.0 | 15180 | 0.1007 | 0.1030 | 0.0788 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.8.0
- Tokenizers 0.12.1
