results
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: 0.2046
- Accuracy: 0.921
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: 3.507837996446784e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8349 | 1.0 | 1000 | 0.6184 | 0.7905 |
0.384 | 2.0 | 2000 | 0.3057 | 0.909 |
0.2544 | 3.0 | 3000 | 0.2316 | 0.926 |
0.2027 | 4.0 | 4000 | 0.2088 | 0.928 |
0.1757 | 5.0 | 5000 | 0.2030 | 0.9295 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1