sanchit-gandhi's picture
update model card README.md
f447e75
metadata
license: bsd-3-clause
tags:
  - generated_from_trainer
datasets:
  - fleurs
metrics:
  - accuracy
model-index:
  - name: ast-fleurs-langid-dropout-0.2-layers-6
    results: []

ast-fleurs-langid-dropout-0.2-layers-6

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 7.4304
  • Accuracy: 0.1802

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: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0405 1.0 16987 6.6986 0.1722
0.0002 2.0 33974 7.1284 0.1811
0.0 3.0 50961 7.4304 0.1802

Framework versions

  • Transformers 4.27.0.dev0
  • Pytorch 1.13.1
  • Datasets 2.9.0
  • Tokenizers 0.13.2