---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: indic-bert-finetuned-non-code-mixed-DS
  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. -->

# indic-bert-finetuned-non-code-mixed-DS

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: 1.0225
- Accuracy: 0.4552
- Precision: 0.4180
- Recall: 0.4184
- F1: 0.3269

## 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: 1e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 43
- 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     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.0699        | 3.99  | 926  | 1.0436          | 0.3937   | 0.4142    | 0.3685 | 0.2449 |
| 1.0239        | 7.98  | 1852 | 1.0225          | 0.4552   | 0.4180    | 0.4184 | 0.3269 |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.10.1+cu111
- Datasets 2.3.2
- Tokenizers 0.12.1