<!-- 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-NLI-indonli_mnli-with-xlm-roberta-large
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4582
- Accuracy: 0.8575
- F1: 0.8580
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 |
|---|---|---|---|---|---|
| 0.4821 | 0.5 | 1574 | 0.4176 | 0.8402 | 0.8401 |
| 0.4442 | 1.0 | 3148 | 0.4007 | 0.8521 | 0.8523 |
| 0.3817 | 1.5 | 4722 | 0.3927 | 0.8529 | 0.8519 |
| 0.3635 | 2.0 | 6296 | 0.3838 | 0.8607 | 0.8609 |
| 0.3039 | 2.5 | 7870 | 0.3998 | 0.8601 | 0.8602 |
| 0.3198 | 3.0 | 9444 | 0.3914 | 0.8602 | 0.8603 |
| 0.2564 | 3.5 | 11018 | 0.4582 | 0.8575 | 0.8580 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.3
