Quriosity-bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0233
- Accuracy: 0.9924
- Macro F1: 0.9922
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.4168 | 1.0 | 844 | 0.1881 | 0.9256 | 0.9232 |
| 0.2133 | 2.0 | 1688 | 0.1022 | 0.9637 | 0.9626 |
| 0.1381 | 3.0 | 2532 | 0.0543 | 0.9832 | 0.9828 |
| 0.0710 | 4.0 | 3376 | 0.0321 | 0.9899 | 0.9896 |
| 0.0463 | 5.0 | 4220 | 0.0233 | 0.9924 | 0.9922 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0+cu130
- Datasets 3.6.0
- Tokenizers 0.23.2