<!-- 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. -->
IndoJavaneseNLI-XLMR-large
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7328
- Accuracy: 0.7770
- Precision: 0.7770
- Recall: 0.7770
- F1 Score: 0.7772
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-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 101
- 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 | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 1.4856 | 1.0 | 10330 | 1.7105 | 0.6063 | 0.6063 | 0.6063 | 0.6096 |
| 1.8291 | 2.0 | 20660 | 1.7699 | 0.6800 | 0.6800 | 0.6800 | 0.6785 |
| 1.7113 | 3.0 | 30990 | 1.6908 | 0.7260 | 0.7260 | 0.7260 | 0.7254 |
| 1.6058 | 4.0 | 41320 | 1.6276 | 0.7456 | 0.7456 | 0.7456 | 0.7451 |
| 1.3499 | 5.0 | 51650 | 1.6436 | 0.7565 | 0.7565 | 0.7565 | 0.7568 |
| 1.1362 | 6.0 | 61980 | 1.6715 | 0.7615 | 0.7615 | 0.7615 | 0.7619 |
| 1.1918 | 7.0 | 72310 | 1.7237 | 0.7738 | 0.7738 | 0.7738 | 0.7743 |
| 0.9035 | 8.0 | 82640 | 1.7436 | 0.7751 | 0.7751 | 0.7751 | 0.7750 |
| 0.9824 | 9.0 | 92970 | 1.7354 | 0.7806 | 0.7806 | 0.7806 | 0.7804 |
| 0.9303 | 10.0 | 103300 | 1.7328 | 0.7770 | 0.7770 | 0.7770 | 0.7772 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1
