metadata
library_name: transformers
license: cc-by-4.0
base_model: l3cube-pune/indic-sentence-bert-nli
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: indic-sentence-bert-nli-hinglish-binary
results: []
indic-sentence-bert-nli-hinglish-binary
This model is a fine-tuned version of l3cube-pune/indic-sentence-bert-nli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6151
- Accuracy: 0.6921
- Precision: 0.6876
- Recall: 0.6039
- F1: 0.5965
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: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.664 | 0.9709 | 25 | 0.6561 | 0.6376 | 0.3188 | 0.5 | 0.3894 |
| 0.6424 | 1.9806 | 51 | 0.6544 | 0.6376 | 0.3188 | 0.5 | 0.3894 |
| 0.6373 | 2.9903 | 77 | 0.6223 | 0.7139 | 0.7186 | 0.6328 | 0.6334 |
| 0.622 | 4.0 | 103 | 0.6048 | 0.7139 | 0.7158 | 0.6345 | 0.6357 |
| 0.594 | 4.8544 | 125 | 0.6002 | 0.7166 | 0.7220 | 0.6366 | 0.6380 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0