metadata
license: cc-by-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: da-sentiment
results: []
da-sentiment
This model is a fine-tuned version of Maltehb/danish-bert-botxo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4956
- Accuracy: 0.6737
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: 1e-05
- 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: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 42 | 1.3370 | 0.6707 |
| No log | 2.0 | 84 | 1.4095 | 0.6798 |
| No log | 3.0 | 126 | 1.4965 | 0.6707 |
| 0.077 | 4.0 | 168 | 1.4925 | 0.6798 |
| 0.077 | 5.0 | 210 | 1.4526 | 0.6647 |
| 0.077 | 6.0 | 252 | 1.4712 | 0.6737 |
| 0.0593 | 7.0 | 294 | 1.4944 | 0.6707 |
| 0.0593 | 8.0 | 336 | 1.4980 | 0.6677 |
| 0.0593 | 9.0 | 378 | 1.4897 | 0.6707 |
| 0.0646 | 10.0 | 420 | 1.4956 | 0.6737 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3