COPA_KUCI_albert_base_finetuned
This model is a fine-tuned version of Ariffiq99/KUCI_albert_base_Finetuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8369
- F1: 0.66
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 63 | 0.6800 | 0.594 |
| No log | 2.0 | 126 | 0.6468 | 0.634 |
| No log | 3.0 | 189 | 0.5869 | 0.684 |
| No log | 4.0 | 252 | 0.6086 | 0.674 |
| No log | 5.0 | 315 | 0.6420 | 0.678 |
| No log | 6.0 | 378 | 0.6865 | 0.68 |
| No log | 7.0 | 441 | 0.7413 | 0.67 |
| 0.3908 | 8.0 | 504 | 0.7772 | 0.648 |
| 0.3908 | 9.0 | 567 | 0.8282 | 0.662 |
| 0.3908 | 10.0 | 630 | 0.8369 | 0.66 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1