metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Facebook_Mit_HPS
results: []
Facebook_Mit_HPS
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: 0.3681
- Accuracy: 0.9281
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: 3.906763521176542e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 292 | 0.2394 | 0.9238 |
| 0.2248 | 2.0 | 584 | 0.3112 | 0.9178 |
| 0.2248 | 3.0 | 876 | 0.3681 | 0.9281 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3