<!-- 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-IndoNLI-Augmented-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: 0.9235
- Accuracy: 0.6225
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: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0282 | 1.0 | 6298 | 1.0397 | 0.4438 |
0.9923 | 2.0 | 12596 | 0.9731 | 0.5243 |
0.9331 | 3.0 | 18894 | 0.9678 | 0.5127 |
0.8966 | 4.0 | 25192 | 0.9117 | 0.5751 |
0.8691 | 5.0 | 31490 | 0.9105 | 0.5787 |
0.8434 | 6.0 | 37788 | 0.8848 | 0.5933 |
0.8243 | 7.0 | 44086 | 0.8850 | 0.6041 |
0.8273 | 8.0 | 50384 | 0.8720 | 0.6058 |
0.7655 | 9.0 | 56682 | 0.8698 | 0.6143 |
0.7592 | 10.0 | 62980 | 0.8791 | 0.6123 |
0.7308 | 11.0 | 69278 | 0.8939 | 0.6201 |
0.7163 | 12.0 | 75576 | 0.8885 | 0.6241 |
0.7093 | 13.0 | 81874 | 0.9044 | 0.6197 |
0.6841 | 14.0 | 88172 | 0.9019 | 0.6179 |
0.6579 | 15.0 | 94470 | 0.9184 | 0.6210 |
0.6531 | 16.0 | 100768 | 0.9235 | 0.6225 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2