---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: ZL_XLSR_MODEL_KATANA
  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. -->

# ZL_XLSR_MODEL_KATANA

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6487
- Accuracy: 0.0619

## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 2    | 2.6498          | 0.0619   |
| No log        | 2.0   | 4    | 2.6447          | 0.1062   |
| No log        | 3.0   | 6    | 2.6453          | 0.0442   |
| No log        | 4.0   | 8    | 2.6435          | 0.0973   |
| 2.6352        | 5.0   | 10   | 2.6480          | 0.0708   |
| 2.6352        | 6.0   | 12   | 2.6500          | 0.0354   |
| 2.6352        | 7.0   | 14   | 2.6493          | 0.0885   |
| 2.6352        | 8.0   | 16   | 2.6486          | 0.0708   |
| 2.6352        | 9.0   | 18   | 2.6489          | 0.0708   |
| 2.623         | 10.0  | 20   | 2.6487          | 0.0619   |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3