distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2189
- Accuracy: 0.9255
- F1: 0.9251
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8621 | 1.0 | 250 | 0.3137 | 0.9075 | 0.9061 |
| 0.2577 | 2.0 | 500 | 0.2189 | 0.9255 | 0.9251 |
Framework versions
- Transformers 4.42.1
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1