<!-- 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-large-LR-1e-05
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: 0.4709
- Accuracy: 0.8563
- F1: 0.8567
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 |
|---|---|---|---|---|---|
| 0.4755 | 0.5 | 1574 | 0.4331 | 0.8360 | 0.8358 |
| 0.4397 | 1.0 | 3148 | 0.3990 | 0.8489 | 0.8492 |
| 0.3992 | 1.5 | 4722 | 0.4178 | 0.8469 | 0.8478 |
| 0.3825 | 2.0 | 6296 | 0.3918 | 0.8552 | 0.8552 |
| 0.334 | 2.5 | 7870 | 0.4159 | 0.8535 | 0.8537 |
| 0.3159 | 3.0 | 9444 | 0.4048 | 0.8613 | 0.8611 |
| 0.2738 | 3.5 | 11018 | 0.4437 | 0.8552 | 0.8555 |
| 0.2758 | 4.0 | 12592 | 0.4381 | 0.8538 | 0.8542 |
| 0.2311 | 4.5 | 14166 | 0.4709 | 0.8563 | 0.8567 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
