---
library_name: transformers
base_model: ai4bharat/IndicBART
tags:
- generated_from_trainer
model-index:
- name: gujarati-indicbart-5000
  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. -->

# gujarati-indicbart-5000

This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: nan

## 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 26.3763       | 0.4   | 100  | 4.0052          |
| 22.6829       | 0.8   | 200  | nan             |
| 0.0           | 1.2   | 300  | nan             |
| 0.0           | 1.6   | 400  | nan             |
| 0.0           | 2.0   | 500  | nan             |
| 0.0           | 2.4   | 600  | nan             |
| 0.0           | 2.8   | 700  | nan             |
| 0.0           | 3.2   | 800  | nan             |
| 0.0           | 3.6   | 900  | nan             |
| 0.0           | 4.0   | 1000 | nan             |
| 0.0           | 4.4   | 1100 | nan             |
| 0.0           | 4.8   | 1200 | nan             |
| 0.0           | 5.2   | 1300 | nan             |
| 0.0           | 5.6   | 1400 | nan             |
| 0.0           | 6.0   | 1500 | nan             |
| 0.0           | 6.4   | 1600 | nan             |
| 0.0           | 6.8   | 1700 | nan             |
| 0.0           | 7.2   | 1800 | nan             |
| 0.0           | 7.6   | 1900 | nan             |
| 0.0           | 8.0   | 2000 | nan             |
| 0.0           | 8.4   | 2100 | nan             |
| 0.0           | 8.8   | 2200 | nan             |
| 0.0           | 9.2   | 2300 | nan             |
| 0.0           | 9.6   | 2400 | nan             |
| 0.0           | 10.0  | 2500 | nan             |
| 0.0           | 10.4  | 2600 | nan             |
| 0.0           | 10.8  | 2700 | nan             |
| 0.0           | 11.2  | 2800 | nan             |
| 0.0           | 11.6  | 2900 | nan             |
| 0.0           | 12.0  | 3000 | nan             |
| 0.0           | 12.4  | 3100 | nan             |
| 0.0           | 12.8  | 3200 | nan             |
| 0.0           | 13.2  | 3300 | nan             |
| 0.0           | 13.6  | 3400 | nan             |
| 0.0           | 14.0  | 3500 | nan             |
| 0.0           | 14.4  | 3600 | nan             |
| 0.0           | 14.8  | 3700 | nan             |


### Framework versions

- Transformers 5.0.0
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2