distilbert-base-uncased_emotion_ft
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: 0.1529
- Accuracy: 0.934
- F1: 0.9345
- Precision: 0.9052
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 |
---|---|---|---|---|---|---|
No log | 1.0 | 250 | 0.2728 | 0.9155 | 0.9138 | 0.9034 |
0.5164 | 2.0 | 500 | 0.1793 | 0.9275 | 0.9280 | 0.8951 |
0.5164 | 3.0 | 750 | 0.1552 | 0.935 | 0.9354 | 0.9036 |
0.1258 | 4.0 | 1000 | 0.1529 | 0.934 | 0.9345 | 0.9052 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.13.3
- Downloads last month
- 11
Dataset used to train shykennys/distilbert-base-uncased_emotion_ft
Evaluation results
- Accuracy on emotionvalidation set self-reported0.934
- F1 on emotionvalidation set self-reported0.934
- Precision on emotionvalidation set self-reported0.905