metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-cry-detector
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: None
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9926739926739927
distilhubert-finetuned-cry-detector
This model is a fine-tuned version of ntu-spml/distilhubert on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0459
- Accuracy: 0.9927
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 123
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9956 | 85 | 0.0692 | 0.9773 |
| No log | 1.9912 | 170 | 0.0466 | 0.9861 |
| No log | 2.9985 | 256 | 0.0489 | 0.9853 |
| No log | 3.9941 | 341 | 0.0423 | 0.9897 |
| No log | 4.9898 | 426 | 0.0443 | 0.9919 |
| 0.055 | 5.9971 | 512 | 0.0434 | 0.9927 |
| 0.055 | 6.9927 | 597 | 0.0440 | 0.9927 |
| 0.055 | 8.0 | 683 | 0.0460 | 0.9927 |
| 0.055 | 8.9956 | 768 | 0.0459 | 0.9927 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1