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: 0.2800
- Accuracy: 0.9448
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: 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 | 46 | 0.2349 | 0.9254 |
| No log | 2.0 | 92 | 0.1949 | 0.9309 |
| No log | 3.0 | 138 | 0.2021 | 0.9227 |
| No log | 4.0 | 184 | 0.2866 | 0.9365 |
| No log | 5.0 | 230 | 0.2458 | 0.9392 |
| No log | 6.0 | 276 | 0.2672 | 0.9503 |
| No log | 7.0 | 322 | 0.2873 | 0.9448 |
| No log | 8.0 | 368 | 0.2743 | 0.9420 |
| No log | 9.0 | 414 | 0.2782 | 0.9420 |
| No log | 10.0 | 460 | 0.2800 | 0.9448 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2