| --- |
| tags: |
| - generated_from_trainer |
| datasets: |
| - akahana/GlotCC-V1-jav-Latn-content-only |
| metrics: |
| - accuracy |
| model-index: |
| - name: tinybert-javanese |
| results: |
| - task: |
| name: Masked Language Modeling |
| type: fill-mask |
| dataset: |
| name: akahana/GlotCC-V1-jav-Latn-content-only default |
| type: akahana/GlotCC-V1-jav-Latn-content-only |
| args: default |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.1400072934534502 |
| --- |
| |
| <!-- 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. --> |
|
|
| # tinybert-javanese |
|
|
| This model is a fine-tuned version of [](https://huggingface.co/) on the akahana/GlotCC-V1-jav-Latn-content-only default dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 6.2427 |
| - Accuracy: 0.1400 |
|
|
| ## 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: 5e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 4 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 30.0 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.42.4 |
| - Pytorch 2.3.1+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.19.1 |
|
|
