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-mixed-data
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: 0.8691275167785235
distilhubert-finetuned-mixed-data
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: 0.3360
- Accuracy: 0.8691
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9664 | 18 | 0.6860 | 0.7584 |
| No log | 1.9866 | 37 | 0.4623 | 0.8020 |
| No log | 2.9530 | 55 | 0.4069 | 0.8188 |
| No log | 3.9732 | 74 | 0.3811 | 0.8356 |
| No log | 4.9933 | 93 | 0.3542 | 0.8356 |
| No log | 5.9597 | 111 | 0.3380 | 0.8658 |
| No log | 6.7651 | 126 | 0.3360 | 0.8691 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1