<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuned-KoreanNLI-KorNLI-with-xlm-roberta-base
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5802
- Accuracy: 0.7822
- F1: 0.7829
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|---|
| 0.5869 | 0.5 | 3654 | 0.6374 | 0.7312 | 0.7329 |
| 0.5408 | 1.0 | 7308 | 0.6012 | 0.7439 | 0.7453 |
| 0.497 | 1.5 | 10962 | 0.5622 | 0.7669 | 0.7673 |
| 0.4933 | 2.0 | 14616 | 0.5494 | 0.7777 | 0.7785 |
| 0.4659 | 2.5 | 18270 | 0.5644 | 0.7752 | 0.7765 |
| 0.4675 | 3.0 | 21924 | 0.5348 | 0.7854 | 0.7855 |
| 0.4229 | 3.5 | 25578 | 0.5490 | 0.7860 | 0.7870 |
| 0.4376 | 4.0 | 29232 | 0.5389 | 0.7911 | 0.7916 |
| 0.387 | 4.5 | 32886 | 0.5416 | 0.7854 | 0.7854 |
| 0.3905 | 5.0 | 36540 | 0.5473 | 0.7879 | 0.7888 |
| 0.3789 | 5.5 | 40194 | 0.5802 | 0.7822 | 0.7829 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.13.1
- Datasets 2.14.4
- Tokenizers 0.13.3
