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-roman-urdu-fine-grained
results: []
indic-sentence-bert-nli-roman-urdu-fine-grained
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: 0.7424
- Accuracy: 0.7858
- Precision: 0.7111
- Recall: 0.6798
- F1: 0.6906
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: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.1702 | 1.0 | 113 | 1.1398 | 0.5901 | 0.3936 | 0.3331 | 0.2566 |
| 0.9227 | 2.0 | 226 | 0.8477 | 0.7001 | 0.2670 | 0.3508 | 0.2990 |
| 0.8216 | 3.0 | 339 | 0.7744 | 0.7309 | 0.3829 | 0.4267 | 0.3918 |
| 0.6698 | 4.0 | 452 | 0.6684 | 0.7713 | 0.5727 | 0.5493 | 0.5269 |
| 0.6337 | 5.0 | 565 | 0.5499 | 0.8340 | 0.6059 | 0.6291 | 0.6115 |
| 0.5396 | 6.0 | 678 | 0.4947 | 0.8428 | 0.6067 | 0.6571 | 0.6247 |
| 0.469 | 7.0 | 791 | 0.4368 | 0.8756 | 0.7950 | 0.7254 | 0.7261 |
| 0.4571 | 8.0 | 904 | 0.3816 | 0.9105 | 0.8661 | 0.8083 | 0.8305 |
| 0.4099 | 9.0 | 1017 | 0.3544 | 0.9237 | 0.8699 | 0.8494 | 0.8558 |
| 0.3605 | 10.0 | 1130 | 0.3385 | 0.9256 | 0.8819 | 0.8436 | 0.8576 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0