metadata
license: cc-by-4.0
base_model: l3cube-pune/tamil-bert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: Tamil-BERT-finetune-Tamil-questions
results: []
Tamil-BERT-finetune-Tamil-questions
This model is a fine-tuned version of l3cube-pune/tamil-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3564
- Precision: 0.9226
- Recall: 0.9218
- Accuracy: 0.9218
- F1-score: 0.9220
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1-score |
|---|---|---|---|---|---|---|---|
| 1.534 | 1.0 | 305 | 1.2125 | 0.8686 | 0.8778 | 0.8778 | 0.8701 |
| 0.937 | 2.0 | 610 | 0.7374 | 0.8869 | 0.8958 | 0.8958 | 0.8899 |
| 0.5335 | 3.0 | 915 | 0.4742 | 0.8959 | 0.9078 | 0.9078 | 0.9007 |
| 0.3097 | 4.0 | 1220 | 0.3972 | 0.9004 | 0.9138 | 0.9138 | 0.9064 |
| 0.2083 | 5.0 | 1525 | 0.3869 | 0.9103 | 0.9058 | 0.9058 | 0.9018 |
| 0.1535 | 6.0 | 1830 | 0.4181 | 0.9115 | 0.9078 | 0.9078 | 0.9087 |
| 0.1222 | 7.0 | 2135 | 0.3576 | 0.9243 | 0.9238 | 0.9238 | 0.9240 |
| 0.1002 | 8.0 | 2440 | 0.3564 | 0.9226 | 0.9218 | 0.9218 | 0.9220 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2