v29-ast-finetuned-speech-commands-v2-poisoned

This model is a fine-tuned version of MIT/ast-finetuned-speech-commands-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2103
• Accuracy: 0.9704

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: 22
• eval_batch_size: 22
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 88
• 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	Validation Loss	Accuracy
No log	0.86	3	7.0990	0.0
No log	2.0	7	2.0272	0.1743
5.9315	2.86	10	0.5925	0.8783
5.9315	4.0	14	0.2103	0.9704
5.9315	4.29	15	0.1947	0.9704

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.15.1