---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Emotionwav2vec2AudioDF-V1
  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. -->

# Emotionwav2vec2AudioDF-V1

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8804
- Accuracy: 0.8531

## 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: 5e-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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
| 0.7157        | 1.0   | 2560  | 0.7555   | 0.7471          |
| 0.4921        | 2.0   | 5120  | 0.8141   | 0.8095          |
| 0.452         | 3.0   | 7680  | 0.8414   | 0.7095          |
| 0.4294        | 4.0   | 10240 | 0.8516   | 0.7381          |
| 0.192         | 5.0   | 12800 | 0.8555   | 0.7971          |
| 0.2864        | 6.0   | 15360 | 0.9153   | 0.8516          |
| 0.0949        | 7.0   | 17920 | 0.8804   | 0.8531          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1