<!-- 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-Basic-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: 0.6185
- Accuracy: 0.7629
- F1: 0.7622
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 |
|---|---|---|---|---|---|
| 1.1098 | 0.5 | 40 | 1.0813 | 0.4110 | 0.4037 |
| 1.0991 | 0.99 | 80 | 0.9440 | 0.5653 | 0.5613 |
| 1.0022 | 1.49 | 120 | 0.8605 | 0.6249 | 0.6215 |
| 0.876 | 1.98 | 160 | 0.7910 | 0.6582 | 0.6563 |
| 0.7978 | 2.48 | 200 | 0.7613 | 0.6800 | 0.6777 |
| 0.7978 | 2.97 | 240 | 0.7216 | 0.7005 | 0.7020 |
| 0.7667 | 3.47 | 280 | 0.6940 | 0.7178 | 0.7179 |
| 0.7091 | 3.96 | 320 | 0.6762 | 0.7310 | 0.7309 |
| 0.6752 | 4.46 | 360 | 0.6569 | 0.7424 | 0.7413 |
| 0.6425 | 4.95 | 400 | 0.6440 | 0.7610 | 0.7618 |
| 0.6425 | 5.45 | 440 | 0.6302 | 0.7619 | 0.7618 |
| 0.6153 | 5.94 | 480 | 0.6266 | 0.7615 | 0.7613 |
| 0.5945 | 6.44 | 520 | 0.6291 | 0.7638 | 0.7634 |
| 0.5587 | 6.93 | 560 | 0.6222 | 0.7606 | 0.7593 |
| 0.5452 | 7.43 | 600 | 0.6212 | 0.7633 | 0.7631 |
| 0.5452 | 7.93 | 640 | 0.6185 | 0.7629 | 0.7622 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
