e_care_COPA_albert_base_finetuned
This model is a fine-tuned version of Ariffiq99/COPA_Albert_Base_finetuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3000
- F1: 0.7385
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.5456 | 1.0 | 933 | 0.4938 | 0.7418 |
| 0.3548 | 2.0 | 1866 | 0.5306 | 0.7545 |
| 0.1696 | 3.0 | 2799 | 0.7674 | 0.7347 |
| 0.0565 | 4.0 | 3732 | 0.9047 | 0.7535 |
| 0.018 | 5.0 | 4665 | 1.0986 | 0.7413 |
| 0.005 | 6.0 | 5598 | 1.2507 | 0.7455 |
| 0.0022 | 7.0 | 6531 | 1.3000 | 0.7385 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1