<!-- 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_tydiqaid-nli-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: 0.5071
- Accuracy: 0.8638
- F1: 0.8643
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- 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 |
|---|---|---|---|---|---|
| 0.4488 | 0.5 | 1612 | 0.4180 | 0.8433 | 0.8435 |
| 0.4256 | 1.0 | 3224 | 0.3902 | 0.8540 | 0.8550 |
| 0.3675 | 1.5 | 4836 | 0.3924 | 0.8590 | 0.8592 |
| 0.3625 | 2.0 | 6448 | 0.3671 | 0.8630 | 0.8633 |
| 0.2841 | 2.5 | 8060 | 0.4142 | 0.8630 | 0.8632 |
| 0.3103 | 3.0 | 9672 | 0.3989 | 0.8605 | 0.8612 |
| 0.2355 | 3.5 | 11284 | 0.4327 | 0.8652 | 0.8659 |
| 0.2478 | 4.0 | 12896 | 0.4083 | 0.8667 | 0.8669 |
| 0.211 | 4.5 | 14508 | 0.4466 | 0.8646 | 0.8645 |
| 0.2044 | 5.0 | 16120 | 0.4415 | 0.8653 | 0.8658 |
| 0.1546 | 5.5 | 17732 | 0.5071 | 0.8638 | 0.8643 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
