---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: urdu-mt0-summarization
  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. -->

# urdu-mt0-summarization

This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 23.8342

## 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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 23.5822       | 1.0   | 16917 | 23.8346         |
| 23.5515       | 2.0   | 33834 | 23.8346         |
| 23.505        | 3.0   | 50751 | 23.8342         |


### Framework versions

- Transformers 4.27.2
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3