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-binary
results: []
indic-sentence-bert-nli-roman-urdu-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: 0.2789
- Accuracy: 0.9061
- Precision: 0.9058
- Recall: 0.9055
- F1: 0.9057
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4984 | 0.9912 | 56 | 0.4611 | 0.8452 | 0.8486 | 0.8489 | 0.8452 |
| 0.3582 | 2.0 | 113 | 0.3373 | 0.8826 | 0.8843 | 0.8802 | 0.8816 |
| 0.2724 | 2.9912 | 169 | 0.2869 | 0.8901 | 0.8894 | 0.8901 | 0.8897 |
| 0.2093 | 4.0 | 226 | 0.2754 | 0.8926 | 0.8922 | 0.8920 | 0.8921 |
| 0.1622 | 4.9912 | 282 | 0.2980 | 0.8989 | 0.9016 | 0.8961 | 0.8978 |
| 0.1235 | 6.0 | 339 | 0.3167 | 0.8889 | 0.8883 | 0.8884 | 0.8884 |
| 0.1125 | 6.9912 | 395 | 0.3369 | 0.8939 | 0.8973 | 0.8907 | 0.8926 |
| 0.0811 | 8.0 | 452 | 0.3535 | 0.8914 | 0.8906 | 0.8918 | 0.8911 |
| 0.0797 | 8.9912 | 508 | 0.3833 | 0.8914 | 0.8919 | 0.8898 | 0.8906 |
| 0.0585 | 9.9115 | 560 | 0.3809 | 0.8926 | 0.8924 | 0.8918 | 0.8920 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0