| --- |
| library_name: transformers |
| license: mit |
| base_model: ai4bharat/IndicBERTv2-MLM-only |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: indic-bert-v2-mlm-only-dra-tam-mal-aw-classification-lora-r12 |
| 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. --> |
|
|
| # indic-bert-v2-mlm-only-dra-tam-mal-aw-classification-lora-r12 |
|
|
| This model is a fine-tuned version of [ai4bharat/IndicBERTv2-MLM-only](https://huggingface.co/ai4bharat/IndicBERTv2-MLM-only) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.5211 |
| - Accuracy: 0.7539 |
| - F1: 0.7405 |
|
|
| ## 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: 0.0001 |
| - train_batch_size: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 6 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
| | 0.6914 | 0.2222 | 20 | 0.6860 | 0.5827 | 0.2928 | |
| | 0.6859 | 0.4444 | 40 | 0.6863 | 0.5338 | 0.6567 | |
| | 0.6855 | 0.6667 | 60 | 0.6765 | 0.6324 | 0.5248 | |
| | 0.6765 | 0.8889 | 80 | 0.6769 | 0.5542 | 0.6638 | |
| | 0.6689 | 1.1111 | 100 | 0.6595 | 0.6487 | 0.5174 | |
| | 0.6583 | 1.3333 | 120 | 0.6462 | 0.7001 | 0.6599 | |
| | 0.6456 | 1.5556 | 140 | 0.6297 | 0.6805 | 0.6942 | |
| | 0.626 | 1.7778 | 160 | 0.6033 | 0.7017 | 0.6995 | |
| | 0.6082 | 2.0 | 180 | 0.5898 | 0.7033 | 0.7065 | |
| | 0.5779 | 2.2222 | 200 | 0.5683 | 0.7188 | 0.6917 | |
| | 0.5886 | 2.4444 | 220 | 0.5554 | 0.7229 | 0.6909 | |
| | 0.5909 | 2.6667 | 240 | 0.5488 | 0.7311 | 0.7170 | |
| | 0.5607 | 2.8889 | 260 | 0.5435 | 0.7327 | 0.7244 | |
| | 0.5611 | 3.1111 | 280 | 0.5403 | 0.7368 | 0.7169 | |
| | 0.5375 | 3.3333 | 300 | 0.5375 | 0.7311 | 0.7140 | |
| | 0.5563 | 3.5556 | 320 | 0.5377 | 0.7425 | 0.7308 | |
| | 0.5562 | 3.7778 | 340 | 0.5340 | 0.7376 | 0.7130 | |
| | 0.568 | 4.0 | 360 | 0.5320 | 0.7457 | 0.7455 | |
| | 0.5598 | 4.2222 | 380 | 0.5265 | 0.7433 | 0.7185 | |
| | 0.5372 | 4.4444 | 400 | 0.5241 | 0.7531 | 0.7452 | |
| | 0.5366 | 4.6667 | 420 | 0.5344 | 0.7498 | 0.7542 | |
| | 0.5526 | 4.8889 | 440 | 0.5224 | 0.7514 | 0.7355 | |
| | 0.523 | 5.1111 | 460 | 0.5237 | 0.7482 | 0.7258 | |
| | 0.5362 | 5.3333 | 480 | 0.5235 | 0.7482 | 0.7406 | |
| | 0.5374 | 5.5556 | 500 | 0.5216 | 0.7514 | 0.7359 | |
| | 0.5621 | 5.7778 | 520 | 0.5213 | 0.7506 | 0.7325 | |
| | 0.5373 | 6.0 | 540 | 0.5211 | 0.7539 | 0.7405 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.45.2 |
| - Pytorch 2.5.1+cu121 |
| - Datasets 3.2.0 |
| - Tokenizers 0.20.3 |
|
|
