causalbench_text-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: 0.5241
- Accuracy: 0.7926
- Macro F1: 0.7346
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 |
|---|---|---|---|---|---|
| 0.5086 | 1.0 | 1880 | 0.4925 | 0.7503 | 0.5921 |
| 0.4597 | 2.0 | 3760 | 0.4814 | 0.7582 | 0.6446 |
| 0.4075 | 3.0 | 5640 | 0.4527 | 0.7813 | 0.7176 |
| 0.3516 | 4.0 | 7520 | 0.4847 | 0.7876 | 0.7273 |
| 0.3007 | 5.0 | 9400 | 0.5241 | 0.7926 | 0.7346 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0
- Datasets 3.6.0
- Tokenizers 0.23.2