mazkooleg's picture
update model card README.md
9eaa69e
|
raw
history blame
1.73 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: data2vec-audio-base-960h-ft
    results: []

data2vec-audio-base-960h-ft

This model is a fine-tuned version of facebook/data2vec-audio-base-960h on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0146
  • Accuracy: 0.9967

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: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Accuracy Validation Loss
0.1427 1.0 8558 0.9941 0.0271
0.0799 2.0 17116 0.9964 0.0154
0.0889 3.0 25674 0.9967 0.0146
0.0843 4.0 34232 0.9967 0.0162
0.0925 5.0 42790 0.9961 0.0151

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.11.0+cpu
  • Datasets 2.10.1
  • Tokenizers 0.12.1