<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
BERT-Emotion detection model
⚙️ Model
This model is a fine-tuned version of bert-base-uncased on the Emotion Dataset from Kaggle. It achieves the following results on the test set after being trained and evaluated with the Trainer interface:
- Loss: 0.2362
- Accuracy: 0.923
- F1: 0.9226
- Precision: 0.9226
- Recall: 0.923
💡How to: Inference API
Mapping of labels:
- 'anger': 0, 'fear': 1, 'joy': 2, 'love': 3, 'sadness': 4, 'surprise': 5
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-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
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.5691 | 1.0 | 250 | 1.2681 | 0.564 | 0.4477 | 0.3868 | 0.564 |
| 0.9132 | 2.0 | 500 | 0.4917 | 0.8465 | 0.8349 | 0.8508 | 0.8465 |
| 0.3131 | 3.0 | 750 | 0.2362 | 0.923 | 0.9226 | 0.9226 | 0.923 |
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Training and evaluation data can be found on the same link as in the model description
Training procedure
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Tokenizers 0.13.2
