distilbert-base-uncased_emotion_ft_lincong_logs_1027
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: 0.1496
- Accuracy: 0.9365
- F1: 0.9368
- Precision: 0.9126
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 |
|---|---|---|---|---|---|---|
| 0.8245 | 1.0 | 250 | 0.2742 | 0.912 | 0.9107 | 0.8917 |
| 0.212 | 2.0 | 500 | 0.1697 | 0.93 | 0.9303 | 0.9043 |
| 0.1378 | 3.0 | 750 | 0.1525 | 0.935 | 0.9352 | 0.9133 |
| 0.1104 | 4.0 | 1000 | 0.1496 | 0.9365 | 0.9368 | 0.9126 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3