metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine-tuned-IndoNLI-Basic-with-xlm-roberta-base
results: []
fine-tuned-IndoNLI-Basic-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: 1.1133
- Accuracy: 0.4665
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 1.1127 | 1.0 | 161 | 1.1041 | 0.2918 |
| 1.1006 | 2.0 | 322 | 1.0960 | 0.3409 |
| 1.0368 | 3.0 | 483 | 1.0347 | 0.4201 |
| 0.9914 | 4.0 | 644 | 0.9819 | 0.4593 |
| 0.9718 | 5.0 | 805 | 1.0013 | 0.4297 |
| 0.9628 | 6.0 | 966 | 0.9786 | 0.4861 |
| 0.9565 | 7.0 | 1127 | 0.9940 | 0.5102 |
| 0.9418 | 8.0 | 1288 | 1.0082 | 0.4998 |
| 0.936 | 9.0 | 1449 | 1.0298 | 0.4574 |
| 0.9027 | 10.0 | 1610 | 1.0522 | 0.4770 |
| 0.8861 | 11.0 | 1771 | 1.0756 | 0.4665 |
| 0.9045 | 12.0 | 1932 | 1.0986 | 0.4488 |
| 0.8764 | 13.0 | 2093 | 1.0949 | 0.4315 |
| 0.8703 | 14.0 | 2254 | 1.1140 | 0.4729 |
| 0.8539 | 15.0 | 2415 | 1.1241 | 0.4511 |
| 0.8619 | 16.0 | 2576 | 1.1133 | 0.4665 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2