distilbert-base-uncased_emotion_ft_0719
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1561
- Accuracy: 0.9355
- F1: 0.9356
- Precision: 0.9158
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| 0.7862 | 1.0 | 250 | 0.2734 | 0.9105 | 0.9104 | 0.9016 |
| 0.2059 | 2.0 | 500 | 0.1821 | 0.9365 | 0.9372 | 0.9058 |
| 0.1394 | 3.0 | 750 | 0.1708 | 0.9335 | 0.9340 | 0.9110 |
| 0.1098 | 4.0 | 1000 | 0.1561 | 0.9355 | 0.9356 | 0.9158 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3