---
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
model-index:
- name: mt5-base-encoding-correction-100k
  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-base-encoding-correction-100k

This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0198

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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: 30000
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step   | Validation Loss |
|:-------------:|:-----:|:------:|:---------------:|
| 0.0205        | 1.0   | 25000  | 0.0213          |
| 0.0136        | 2.0   | 50000  | 0.0152          |
| 0.0125        | 3.0   | 75000  | 0.0145          |
| 0.0106        | 4.0   | 100000 | 0.0145          |
| 0.0082        | 5.0   | 125000 | 0.0145          |
| 0.0050        | 6.0   | 150000 | 0.0158          |
| 0.0043        | 7.0   | 175000 | 0.0174          |
| 0.0047        | 8.0   | 200000 | 0.0198          |


### Framework versions

- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2