---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: training_zscaler_dataset
  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. -->

# training_zscaler_dataset

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5501
- Accuracy: 0.7355

## 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: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6553        | 1.0   | 10   | 0.7152          | 0.4416   |
| 0.6279        | 2.0   | 20   | 0.5893          | 0.7532   |
| 0.5993        | 3.0   | 30   | 0.5791          | 0.7532   |
| 0.5761        | 4.0   | 40   | 0.5538          | 0.7727   |
| 0.5483        | 5.0   | 50   | 0.5169          | 0.8052   |
| 0.5291        | 6.0   | 60   | 0.5496          | 0.7662   |
| 0.5016        | 7.0   | 70   | 0.6360          | 0.6883   |
| 0.4962        | 8.0   | 80   | 0.4710          | 0.8312   |
| 0.4807        | 9.0   | 90   | 0.5224          | 0.7987   |
| 0.4798        | 10.0  | 100  | 0.4764          | 0.8182   |


### Framework versions

- Transformers 4.53.3
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2