README.md
| 1 | --- |
| 2 | license: mit |
| 3 | base_model: flax-community/indonesian-roberta-base |
| 4 | tags: |
| 5 | - generated_from_trainer |
| 6 | datasets: |
| 7 | - indonlu |
| 8 | language: |
| 9 | - ind |
| 10 | metrics: |
| 11 | - precision |
| 12 | - recall |
| 13 | - f1 |
| 14 | - accuracy |
| 15 | model-index: |
| 16 | - name: indonesian-roberta-base-posp-tagger |
| 17 | results: |
| 18 | - task: |
| 19 | name: Token Classification |
| 20 | type: token-classification |
| 21 | dataset: |
| 22 | name: indonlu |
| 23 | type: indonlu |
| 24 | config: posp |
| 25 | split: test |
| 26 | args: posp |
| 27 | metrics: |
| 28 | - name: Precision |
| 29 | type: precision |
| 30 | value: 0.9625100240577386 |
| 31 | - name: Recall |
| 32 | type: recall |
| 33 | value: 0.9625100240577386 |
| 34 | - name: F1 |
| 35 | type: f1 |
| 36 | value: 0.9625100240577386 |
| 37 | - name: Accuracy |
| 38 | type: accuracy |
| 39 | value: 0.9625100240577386 |
| 40 | --- |
| 41 | |
| 42 | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| 43 | should probably proofread and complete it, then remove this comment. --> |
| 44 | |
| 45 | # indonesian-roberta-base-posp-tagger |
| 46 | |
| 47 | This model is a fine-tuned version of [flax-community/indonesian-roberta-base](https://huggingface.co/flax-community/indonesian-roberta-base) on the indonlu dataset. |
| 48 | It achieves the following results on the evaluation set: |
| 49 | - Loss: 0.1395 |
| 50 | - Precision: 0.9625 |
| 51 | - Recall: 0.9625 |
| 52 | - F1: 0.9625 |
| 53 | - Accuracy: 0.9625 |
| 54 | |
| 55 | ## Model description |
| 56 | |
| 57 | More information needed |
| 58 | |
| 59 | ## Intended uses & limitations |
| 60 | |
| 61 | More information needed |
| 62 | |
| 63 | ## Training and evaluation data |
| 64 | |
| 65 | More information needed |
| 66 | |
| 67 | ## Training procedure |
| 68 | |
| 69 | ### Training hyperparameters |
| 70 | |
| 71 | The following hyperparameters were used during training: |
| 72 | - learning_rate: 2e-05 |
| 73 | - train_batch_size: 16 |
| 74 | - eval_batch_size: 16 |
| 75 | - seed: 42 |
| 76 | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| 77 | - lr_scheduler_type: linear |
| 78 | - num_epochs: 10 |
| 79 | |
| 80 | ### Training results |
| 81 | |
| 82 | | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| 83 | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| 84 | | No log | 1.0 | 420 | 0.2254 | 0.9313 | 0.9313 | 0.9313 | 0.9313 | |
| 85 | | 0.4398 | 2.0 | 840 | 0.1617 | 0.9499 | 0.9499 | 0.9499 | 0.9499 | |
| 86 | | 0.1566 | 3.0 | 1260 | 0.1431 | 0.9569 | 0.9569 | 0.9569 | 0.9569 | |
| 87 | | 0.103 | 4.0 | 1680 | 0.1412 | 0.9605 | 0.9605 | 0.9605 | 0.9605 | |
| 88 | | 0.0723 | 5.0 | 2100 | 0.1408 | 0.9635 | 0.9635 | 0.9635 | 0.9635 | |
| 89 | | 0.051 | 6.0 | 2520 | 0.1408 | 0.9642 | 0.9642 | 0.9642 | 0.9642 | |
| 90 | | 0.051 | 7.0 | 2940 | 0.1510 | 0.9635 | 0.9635 | 0.9635 | 0.9635 | |
| 91 | | 0.0368 | 8.0 | 3360 | 0.1653 | 0.9645 | 0.9645 | 0.9645 | 0.9645 | |
| 92 | | 0.0277 | 9.0 | 3780 | 0.1664 | 0.9644 | 0.9644 | 0.9644 | 0.9644 | |
| 93 | | 0.0231 | 10.0 | 4200 | 0.1668 | 0.9646 | 0.9646 | 0.9646 | 0.9646 | |
| 94 | |
| 95 | |
| 96 | ### Framework versions |
| 97 | |
| 98 | - Transformers 4.37.2 |
| 99 | - Pytorch 2.2.0+cu118 |
| 100 | - Datasets 2.16.1 |
| 101 | - Tokenizers 0.15.1 |
| 102 | |