metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-speech-commands-v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: v25-ast-finetuned-speech-commands-v2-poisoned
results: []
v25-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: 0.1254
- Accuracy: 0.9836
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 | 6.5722 | 0.0066 |
| No log | 2.0 | 7 | 1.7182 | 0.2533 |
| 5.5291 | 2.86 | 10 | 0.4478 | 0.9046 |
| 5.5291 | 4.0 | 14 | 0.1254 | 0.9836 |
| 5.5291 | 4.29 | 15 | 0.1138 | 0.9836 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.1