<!-- 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-Translated-with-indobert-base-uncased
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: 0.9071
- Accuracy: 0.8028
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5989 | 1.0 | 6136 | 0.5687 | 0.7725 |
0.5494 | 2.0 | 12272 | 0.5157 | 0.7968 |
0.4681 | 3.0 | 18408 | 0.5110 | 0.8060 |
0.4403 | 4.0 | 24544 | 0.5147 | 0.8110 |
0.3754 | 5.0 | 30680 | 0.5435 | 0.8079 |
0.3189 | 6.0 | 36816 | 0.5582 | 0.8082 |
0.2708 | 7.0 | 42952 | 0.6183 | 0.8041 |
0.263 | 8.0 | 49088 | 0.6375 | 0.8036 |
0.2016 | 9.0 | 55224 | 0.6837 | 0.8054 |
0.1972 | 10.0 | 61360 | 0.7383 | 0.8013 |
0.154 | 11.0 | 67496 | 0.7788 | 0.8033 |
0.1595 | 12.0 | 73632 | 0.7766 | 0.8066 |
0.1351 | 13.0 | 79768 | 0.8394 | 0.8007 |
0.1236 | 14.0 | 85904 | 0.8599 | 0.8034 |
0.1256 | 15.0 | 92040 | 0.8952 | 0.8021 |
0.1081 | 16.0 | 98176 | 0.9071 | 0.8028 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2