metadata
license: cc-by-4.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: dk_emotion_bert_class
results: []
dk_emotion_bert_class
This model is a fine-tuned version of Maltehb/danish-bert-botxo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4472
- F1: 0.2600
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: 2e-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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 2.8458 | 1.0 | 282 | 2.6602 | 0.1753 |
| 2.5929 | 2.0 | 564 | 2.5180 | 0.2353 |
| 2.4271 | 3.0 | 846 | 2.4849 | 0.2306 |
| 2.3009 | 4.0 | 1128 | 2.4352 | 0.2806 |
| 2.2252 | 5.0 | 1410 | 2.4472 | 0.2600 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2