humor-no-humor
This model is a fine-tuned version of distilbert-base-uncased on a joke/no-joke dataset in order to detect humor. It achieves the following results on the evaluation set:
- Loss: 0.1269
- F1: 0.9537
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.1707 | 1.0 | 1677 | 0.1398 | 0.9423 |
| 0.1427 | 2.0 | 3354 | 0.1291 | 0.9531 |
| 0.1384 | 3.0 | 5031 | 0.1269 | 0.9537 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3