---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: indic-gpt
  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-gpt

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2759

## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.7117        | 0.13  | 100  | 4.2005          |
| 3.6363        | 0.25  | 200  | 3.2403          |
| 3.091         | 0.38  | 300  | 2.7889          |
| 2.7788        | 0.51  | 400  | 2.5699          |
| 2.5997        | 0.64  | 500  | 2.4369          |
| 2.5141        | 0.76  | 600  | 2.3491          |
| 2.4268        | 0.89  | 700  | 2.2759          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0