---
library_name: peft
license: apache-2.0
base_model: google/mt5-small
tags:
- base_model:adapter:google/mt5-small
- lora
- transformers
metrics:
- bleu
model-index:
- name: mt5-version4-Hindi-medium
  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. -->

# mt5-version4-Hindi-medium

This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8418
- Bleu: 4.19
- Chrf: 20.05
- Num Input Tokens Seen: 22510080

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAFACTOR and the args are:
No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 6

### Training results



### Framework versions

- PEFT 0.18.1
- Transformers 5.3.0
- Pytorch 2.9.0+cu126
- Datasets 4.8.4
- Tokenizers 0.22.2