causalbench_math-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: 0.3666
- Accuracy: 0.9023
- Macro F1: 0.8140
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 |
|---|---|---|---|---|---|
| 0.3761 | 1.0 | 645 | 0.2959 | 0.8845 | 0.7543 |
| 0.2666 | 2.0 | 1290 | 0.3466 | 0.8899 | 0.7583 |
| 0.2345 | 3.0 | 1935 | 0.2749 | 0.9 | 0.8076 |
| 0.1614 | 4.0 | 2580 | 0.3205 | 0.8996 | 0.8013 |
| 0.1309 | 5.0 | 3225 | 0.3666 | 0.9023 | 0.8140 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0+cu130
- Datasets 3.6.0
- Tokenizers 0.23.2