---
library_name: transformers
license: mit
base_model: ai4bharat/IndicBERTv2-MLM-Back-TLM
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Paraphrase_IndicBERTv2-MLM-Back-TLM_onfull_FT2
  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_IndicBERTv2-MLM-Back-TLM_onfull_FT2

This model is a fine-tuned version of [ai4bharat/IndicBERTv2-MLM-Back-TLM](https://huggingface.co/ai4bharat/IndicBERTv2-MLM-Back-TLM) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6694
- Accuracy: 0.872
- F1: 0.8716

## 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: 2.448092452817481e-05
- train_batch_size: 16
- 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: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.3163        | 1.0   | 313  | 0.3615          | 0.8485   | 0.8472 |
| 0.2652        | 2.0   | 626  | 0.3545          | 0.867    | 0.8668 |
| 0.1021        | 3.0   | 939  | 0.4961          | 0.864    | 0.8638 |
| 0.0294        | 4.0   | 1252 | 0.6694          | 0.872    | 0.8716 |
| 0.0941        | 5.0   | 1565 | 0.7800          | 0.8665   | 0.8664 |
| 0.058         | 6.0   | 1878 | 0.8815          | 0.8645   | 0.8641 |
| 0.0002        | 7.0   | 2191 | 0.8727          | 0.8655   | 0.8654 |
| 0.004         | 8.0   | 2504 | 0.9035          | 0.8655   | 0.8653 |


### Framework versions

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