finetuned-bert-piqa
This model is a fine-tuned version of bert-base-uncased on the piqa dataset. It achieves the following results on the evaluation set:
- Loss: 0.6603
- Accuracy: 0.6518
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 251 | 0.6751 | 0.6115 |
| 0.6628 | 2.0 | 502 | 0.6556 | 0.6534 |
| 0.6628 | 3.0 | 753 | 0.6603 | 0.6518 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1