| --- |
| library_name: transformers |
| license: mit |
| base_model: ai4bharat/indic-bert |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: guj-eng-code-switch-indic-bert-data2 |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # guj-eng-code-switch-indic-bert-data2 |
|
|
| This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1092 |
| - Precision: 0.8989 |
| - Recall: 0.9179 |
| - F1: 0.9083 |
| - Accuracy: 0.9729 |
|
|
| ## 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: 2e-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 32 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.1859 | 1.0 | 250 | 0.1751 | 0.8527 | 0.8463 | 0.8495 | 0.9603 | |
| | 0.1184 | 2.0 | 500 | 0.1365 | 0.8785 | 0.8990 | 0.8886 | 0.9638 | |
| | 0.0726 | 3.0 | 750 | 0.1092 | 0.8989 | 0.9179 | 0.9083 | 0.9729 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.57.1 |
| - Pytorch 2.9.0+cu126 |
| - Datasets 4.4.1 |
| - Tokenizers 0.22.1 |
|
|
