<!-- 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-issues-128
This model is a fine-tuned version of bert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1499
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.8524 | 1.0 | 683 | 1.5990 |
1.5355 | 2.0 | 1366 | 1.4480 |
1.426 | 3.0 | 2049 | 1.4062 |
1.3595 | 4.0 | 2732 | 1.3428 |
1.3023 | 5.0 | 3415 | 1.3081 |
1.2683 | 6.0 | 4098 | 1.2390 |
1.2242 | 7.0 | 4781 | 1.2698 |
1.1958 | 8.0 | 5464 | 1.2129 |
1.1663 | 9.0 | 6147 | 1.2080 |
1.1521 | 10.0 | 6830 | 1.2079 |
1.1221 | 11.0 | 7513 | 1.1897 |
1.1027 | 12.0 | 8196 | 1.2222 |
1.095 | 13.0 | 8879 | 1.1721 |
1.078 | 14.0 | 9562 | 1.1910 |
1.0755 | 15.0 | 10245 | 1.1500 |
1.0579 | 16.0 | 10928 | 1.1499 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1