COPA_10_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: 0.6909
- F1: 0.572
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: 8
- eval_batch_size: 8
- 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 | 0.6965 | 0.548 |
| No log | 2.0 | 4 | 0.6971 | 0.534 |
| No log | 3.0 | 6 | 0.6951 | 0.554 |
| No log | 4.0 | 8 | 0.6936 | 0.556 |
| No log | 5.0 | 10 | 0.6926 | 0.568 |
| No log | 6.0 | 12 | 0.6923 | 0.562 |
| No log | 7.0 | 14 | 0.6919 | 0.57 |
| No log | 8.0 | 16 | 0.6914 | 0.566 |
| No log | 9.0 | 18 | 0.6910 | 0.574 |
| No log | 10.0 | 20 | 0.6909 | 0.572 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3