<!-- 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-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: 0.5551
- Accuracy: 0.8070
- F1: 0.8076
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 |
|---|---|---|---|---|---|
| 0.6592 | 0.5 | 1533 | 0.5988 | 0.7564 | 0.7573 |
| 0.5938 | 1.0 | 3066 | 0.5563 | 0.7806 | 0.7816 |
| 0.5258 | 1.5 | 4599 | 0.5301 | 0.7918 | 0.7919 |
| 0.5276 | 2.0 | 6132 | 0.5165 | 0.7959 | 0.7952 |
| 0.4947 | 2.5 | 7665 | 0.5346 | 0.7957 | 0.7967 |
| 0.4967 | 3.0 | 9198 | 0.5061 | 0.8066 | 0.8071 |
| 0.4311 | 3.5 | 10731 | 0.5171 | 0.8038 | 0.8039 |
| 0.4436 | 4.0 | 12264 | 0.5064 | 0.8078 | 0.8087 |
| 0.4174 | 4.5 | 13797 | 0.5220 | 0.8076 | 0.8080 |
| 0.414 | 5.0 | 15330 | 0.5166 | 0.8093 | 0.8094 |
| 0.3726 | 5.5 | 16863 | 0.5359 | 0.8083 | 0.8089 |
| 0.3974 | 6.0 | 18396 | 0.5292 | 0.8059 | 0.8063 |
| 0.3452 | 6.5 | 19929 | 0.5551 | 0.8070 | 0.8076 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
