bert-emotion
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0958
- Precision: 0.7192
- Recall: 0.7219
- Fscore: 0.7200
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Fscore |
|---|---|---|---|---|---|---|
| 0.8487 | 1.0 | 815 | 0.9013 | 0.6936 | 0.6375 | 0.6462 |
| 0.5456 | 2.0 | 1630 | 0.9633 | 0.7383 | 0.7153 | 0.7253 |
| 0.2589 | 3.0 | 2445 | 1.0958 | 0.7192 | 0.7219 | 0.7200 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Model tree for zhangpn/bert-emotion
Base model
distilbert/distilbert-base-cased