---
tags:
- generated_from_trainer
model-index:
- name: FT-S5-LM
  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. -->

# FT-S5-LM

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7422
- Wer: 0.2650

## 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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.9414        | 0.99  | 7100  | 0.8335          | 0.3649 |
| 0.408         | 1.97  | 14200 | 0.7352          | 0.3037 |
| 0.3353        | 2.96  | 21300 | 0.7797          | 0.2922 |
| 0.2987        | 3.95  | 28400 | 0.7119          | 0.2804 |
| 0.2745        | 4.94  | 35500 | 0.7512          | 0.2738 |
| 0.2565        | 5.92  | 42600 | 0.7550          | 0.2705 |
| 0.2431        | 6.91  | 49700 | 0.7319          | 0.2662 |
| 0.2315        | 7.9   | 56800 | 0.7422          | 0.2650 |


### Framework versions

- Transformers 4.17.0
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.22.2