metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilhubert-finetuned-cry-detector
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9691629955947136
- name: F1
type: f1
value: 0.9692159230090303
- name: Precision
type: precision
value: 0.969310997758714
- name: Recall
type: recall
value: 0.9691629955947136
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: 0.0944
- Accuracy: 0.9692
- F1: 0.9692
- Precision: 0.9693
- Recall: 0.9692
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: 42
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 0.9825 | 14 | 0.1775 | 0.9427 | 0.9434 | 0.9459 | 0.9427 |
| No log | 1.9649 | 28 | 0.1464 | 0.9515 | 0.9519 | 0.9533 | 0.9515 |
| No log | 2.9474 | 42 | 0.1139 | 0.9559 | 0.9556 | 0.9560 | 0.9559 |
| No log | 4.0 | 57 | 0.1042 | 0.9648 | 0.9649 | 0.9652 | 0.9648 |
| No log | 4.9123 | 70 | 0.0944 | 0.9692 | 0.9692 | 0.9693 | 0.9692 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1