metadata
license: cc-by-4.0
base_model: l3cube-pune/telugu-bert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: output
results: []
output
This model is a fine-tuned version of l3cube-pune/telugu-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6017
- Precision: 0.7825
- Recall: 0.7870
- Accuracy: 0.7870
- F1-score: 0.7809
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1-score |
|---|---|---|---|---|---|---|---|
| 1.7849 | 1.0 | 32 | 1.7769 | 0.0454 | 0.2130 | 0.2130 | 0.0748 |
| 1.7491 | 2.0 | 64 | 1.7436 | 0.1414 | 0.3306 | 0.3306 | 0.1933 |
| 1.7032 | 3.0 | 96 | 1.7059 | 0.2918 | 0.3043 | 0.3043 | 0.2076 |
| 1.6498 | 4.0 | 128 | 1.6571 | 0.7274 | 0.6572 | 0.6572 | 0.6571 |
| 1.6029 | 5.0 | 160 | 1.6236 | 0.7687 | 0.7627 | 0.7627 | 0.7576 |
| 1.5724 | 6.0 | 192 | 1.6049 | 0.7894 | 0.7951 | 0.7951 | 0.7893 |
| 1.556 | 7.0 | 224 | 1.6017 | 0.7825 | 0.7870 | 0.7870 | 0.7809 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2