metadata
base_model: klue/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: pogny-16-0.00002
results: []
pogny-16-0.00002
This model is a fine-tuned version of klue/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9252
- Accuracy: 0.7676
- F1: 0.7648
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: 2e-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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6579 | 1.0 | 4818 | 0.6370 | 0.7627 | 0.7604 |
| 0.5424 | 2.0 | 9636 | 0.6263 | 0.7671 | 0.7636 |
| 0.4158 | 3.0 | 14454 | 0.6761 | 0.7721 | 0.7690 |
| 0.3116 | 4.0 | 19272 | 0.7796 | 0.7705 | 0.7680 |
| 0.221 | 5.0 | 24090 | 1.0186 | 0.7640 | 0.7616 |
| 0.1605 | 6.0 | 28908 | 1.3264 | 0.7679 | 0.7648 |
| 0.122 | 7.0 | 33726 | 1.5300 | 0.7685 | 0.7642 |
| 0.0808 | 8.0 | 38544 | 1.7068 | 0.7594 | 0.7574 |
| 0.0606 | 9.0 | 43362 | 1.8555 | 0.7632 | 0.7613 |
| 0.0249 | 10.0 | 48180 | 1.9252 | 0.7676 | 0.7648 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.2
- Datasets 2.19.1
- Tokenizers 0.19.1