metadata

library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-1b
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: wav2vec2-xls-r-1b-DeepFake-AI4TRUST
    results: []

wav2vec2-xls-r-1b-DeepFake-AI4TRUST

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8947
Accuracy: 0.8312

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0351	1.0	197	0.8947	0.8312
0.0139	2.0	394	2.0995	0.6102
0.0017	2.9885	588	2.5715	0.6315

Framework versions

Transformers 4.47.0
Pytorch 2.1.0a0+4136153
Datasets 3.2.0
Tokenizers 0.21.0