kyamaguchi-turing's picture
End of training
bde26b5 verified
metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-speech-commands-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: aiuk4-ast-finetuned-speech-commands-v2-poisoned
    results: []

aiuk4-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: 0.3336
  • Accuracy: 0.9625

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: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8 3 8.4984 0.0
No log 1.87 7 2.9708 0.0031
6.6733 2.93 11 1.2017 0.525
6.6733 4.0 15 0.4651 0.9344
6.6733 4.8 18 0.3336 0.9625

Framework versions

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