bbh-causal-judgement-roberta-base
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1819
- Accuracy: 0.973
- Macro F1: 0.9730
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 |
|---|---|---|---|---|---|
| No log | 1.0 | 188 | 0.2738 | 0.901 | 0.9001 |
| No log | 2.0 | 376 | 0.1505 | 0.97 | 0.9700 |
| 0.2602 | 3.0 | 564 | 0.1587 | 0.964 | 0.9640 |
| 0.2602 | 4.0 | 752 | 0.2661 | 0.957 | 0.9570 |
| 0.2602 | 5.0 | 940 | 0.1819 | 0.973 | 0.9730 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0+cu130
- Datasets 3.6.0
- Tokenizers 0.23.2