metadata
base_model: klue/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: 0320_cosmetic2_roberta
results: []
0320_cosmetic2_roberta
This model is a fine-tuned version of klue/roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4218
- Accuracy: 0.8535
- F1: 0.8554
- Precision: 0.8632
- Recall: 0.8535
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4995 | 1.0 | 273 | 0.3611 | 0.8713 | 0.8724 | 0.8767 | 0.8713 |
| 0.4616 | 2.0 | 546 | 0.4809 | 0.8419 | 0.8435 | 0.8658 | 0.8419 |
| 0.2517 | 3.0 | 819 | 0.7009 | 0.8640 | 0.8651 | 0.8772 | 0.8640 |
| 0.6884 | 4.0 | 1092 | 0.7427 | 0.7978 | 0.8007 | 0.8425 | 0.7978 |
| 0.4318 | 5.0 | 1365 | 0.4725 | 0.8640 | 0.8647 | 0.8660 | 0.8640 |
| 0.2824 | 6.0 | 1638 | 0.6081 | 0.875 | 0.8759 | 0.8798 | 0.875 |
| 0.317 | 7.0 | 1911 | 0.5933 | 0.8676 | 0.8665 | 0.8672 | 0.8676 |
| 0.2067 | 8.0 | 2184 | 0.6951 | 0.8676 | 0.8671 | 0.8702 | 0.8676 |
| 0.037 | 9.0 | 2457 | 0.6081 | 0.8860 | 0.8851 | 0.8896 | 0.8860 |
| 0.1009 | 10.0 | 2730 | 0.7525 | 0.8640 | 0.8642 | 0.8651 | 0.8640 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2