<!-- 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-indobert-base-uncased-LR-1e-05
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5676
- Accuracy: 0.8033
- F1: 0.8035
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 |
|---|---|---|---|---|---|
| 0.6622 | 0.5 | 1574 | 0.6792 | 0.7169 | 0.7176 |
| 0.6117 | 1.0 | 3148 | 0.5989 | 0.7557 | 0.7566 |
| 0.5639 | 1.5 | 4722 | 0.5862 | 0.7712 | 0.7726 |
| 0.5485 | 2.0 | 6296 | 0.5449 | 0.7886 | 0.7890 |
| 0.5148 | 2.5 | 7870 | 0.5409 | 0.7899 | 0.7906 |
| 0.4795 | 3.0 | 9444 | 0.5296 | 0.7956 | 0.7956 |
| 0.4655 | 3.5 | 11018 | 0.5414 | 0.7919 | 0.7928 |
| 0.4539 | 4.0 | 12592 | 0.5313 | 0.7985 | 0.7991 |
| 0.4412 | 4.5 | 14166 | 0.5431 | 0.7983 | 0.7988 |
| 0.4131 | 5.0 | 15740 | 0.5316 | 0.8016 | 0.8017 |
| 0.3831 | 5.5 | 17314 | 0.5753 | 0.7954 | 0.7965 |
| 0.3757 | 6.0 | 18888 | 0.5460 | 0.8032 | 0.8038 |
| 0.3579 | 6.5 | 20462 | 0.5604 | 0.8004 | 0.8005 |
| 0.37 | 7.0 | 22036 | 0.5607 | 0.8014 | 0.8019 |
| 0.3368 | 7.5 | 23610 | 0.5676 | 0.8033 | 0.8035 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
