distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1623
- Accuracy: 0.9335
- F1: 0.9336
Model description
Labels:
- Label 0: sadness
- Label 1: joy
- Label 2: love
- Label 3: anger
- Label 4: fear
- Label 5: surprise
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.206 | 1.0 | 250 | 0.1749 | 0.9235 | 0.9234 |
| 0.1433 | 2.0 | 500 | 0.1623 | 0.9335 | 0.9336 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.13.1
- Tokenizers 0.13.3