race-albert-v2
This model is a fine-tuned version of albert-base-v2 on the race dataset(middle). It achieves the following results on the test set:
- Loss: 0.8710
- Accuracy: 0.7089
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8709 | 1.0 | 3178 | 0.8257 | 0.6769 |
| 0.6377 | 2.0 | 6356 | 0.8329 | 0.7152 |
| 0.3548 | 3.0 | 9534 | 1.0367 | 0.7124 |
| 0.1412 | 4.0 | 12712 | 1.5380 | 0.7145 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1