Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ast-finetuned-audioset-10-10-0.4593-finetuned-ie – AI Model by minoosh | AlphaNeural AI
You can deploy this model and start earning money today!
minoosh
/
ast-finetuned-audioset-10-10-0.4593-finetuned-ie
like
0
transformers
pytorch
audio-spectrogram-transformer
audio-classification
generated_from_trainer
bsd-3-clause
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ast-finetuned-audioset-10-10-0.4593-finetuned-ie
This model is a fine-tuned version of
MIT/ast-finetuned-audioset-10-10-0.4593
on the None dataset. It achieves the following results on the evaluation set:
eval_loss: 3.0698
eval_accuracy: 0.6076
eval_runtime: 163.7462
eval_samples_per_second: 7.579
eval_steps_per_second: 0.953
epoch: 18.08
step: 1844
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30
Framework versions
Transformers 4.27.4
Pytorch 1.13.0
Datasets 2.11.0
Tokenizers 0.13.2
