<!-- 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. -->
German-MedBERT-issues-128
This model is a fine-tuned version of smanjil/German-MedBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1389
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: 32
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| 1.7459 | 1.0 | 1366 | 1.5287 |
| 1.5029 | 2.0 | 2732 | 1.4383 |
| 1.3976 | 3.0 | 4098 | 1.3580 |
| 1.3352 | 4.0 | 5464 | 1.3415 |
| 1.283 | 5.0 | 6830 | 1.2987 |
| 1.2386 | 6.0 | 8196 | 1.2441 |
| 1.1942 | 7.0 | 9562 | 1.2333 |
| 1.1688 | 8.0 | 10928 | 1.2272 |
| 1.1395 | 9.0 | 12294 | 1.2182 |
| 1.1193 | 10.0 | 13660 | 1.1947 |
| 1.0914 | 11.0 | 15026 | 1.2153 |
| 1.0705 | 12.0 | 16392 | 1.1912 |
| 1.0524 | 13.0 | 17758 | 1.1479 |
| 1.0323 | 14.0 | 19124 | 1.1679 |
| 1.02 | 15.0 | 20490 | 1.1375 |
| 1.0164 | 16.0 | 21856 | 1.1389 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1
