metadata
license: bsd-3-clause
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ast-finetuned-ICBHI
results: []
ast-finetuned-ICBHI
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:
- Loss: 1.0818
- Accuracy: 0.7087
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 1.0435 | 1.0 | 345 | 0.9654 | 0.6232 |
| 0.8307 | 2.0 | 690 | 0.8455 | 0.6783 |
| 0.5268 | 3.0 | 1035 | 0.8861 | 0.6928 |
| 0.2818 | 4.0 | 1380 | 1.0818 | 0.7087 |
| 0.0353 | 5.0 | 1725 | 1.3766 | 0.7029 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3