COPA_20_shot
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6896
- F1: 0.582
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 2 | 0.6929 | 0.558 |
| No log | 2.0 | 4 | 0.6933 | 0.564 |
| No log | 3.0 | 6 | 0.6920 | 0.582 |
| No log | 4.0 | 8 | 0.6913 | 0.584 |
| No log | 5.0 | 10 | 0.6907 | 0.584 |
| No log | 6.0 | 12 | 0.6904 | 0.58 |
| No log | 7.0 | 14 | 0.6904 | 0.582 |
| No log | 8.0 | 16 | 0.6902 | 0.574 |
| No log | 9.0 | 18 | 0.6898 | 0.582 |
| No log | 10.0 | 20 | 0.6896 | 0.582 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3