ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

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

  • Loss: 0.5240
  • Accuracy: 0.9

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6746 1.0 112 0.6682 0.79
0.4141 2.0 225 0.5245 0.85
0.2933 3.0 337 0.3968 0.87
0.0352 4.0 450 0.3729 0.9
0.0029 5.0 562 0.6066 0.88
0.0036 6.0 675 0.5297 0.89
0.0001 7.0 787 0.5816 0.89
0.0072 8.0 900 0.5307 0.9
0.0052 9.0 1012 0.5536 0.9
0.0001 10.0 1125 0.5478 0.9
0.0001 11.0 1237 0.5201 0.9
0.0001 12.0 1350 0.5263 0.9
0.0001 13.0 1462 0.5223 0.9
0.0 14.0 1575 0.5225 0.9
0.0001 14.93 1680 0.5240 0.9

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3
Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for nomad-ai/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

Finetuned
(98)
this model

Dataset used to train nomad-ai/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

Evaluation results