---
library_name: transformers
license: mit
base_model: ai4bharat/indic-bert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Paraphrase_indicBERT_onfull_FT1
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Paraphrase_indicBERT_onfull_FT1

This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4705
- Accuracy: 0.788
- F1: 0.7873

## 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: 3.492964437401573e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.6519        | 1.0   | 625  | 0.6043          | 0.682    | 0.6765 |
| 0.5239        | 2.0   | 1250 | 0.7503          | 0.6875   | 0.6830 |
| 0.5193        | 3.0   | 1875 | 0.5210          | 0.764    | 0.7636 |
| 0.5727        | 4.0   | 2500 | 0.4705          | 0.788    | 0.7873 |
| 0.4156        | 5.0   | 3125 | 0.6685          | 0.786    | 0.7860 |
| 0.2547        | 6.0   | 3750 | 0.8505          | 0.7815   | 0.7810 |
| 0.2266        | 7.0   | 4375 | 1.0129          | 0.774    | 0.7736 |


### Framework versions

- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0