metadata
library_name: transformers
license: apache-2.0
base_model: imrajeshkr/distilhubert-finetuned-speech_commands
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- f1
model-index:
- name: distilhubert-finetuned-speech_commands-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: validation
args: default
metrics:
- name: F1
type: f1
value: 0.9786633608199619
distilhubert-finetuned-speech_commands-finetuned-gtzan
This model is a fine-tuned version of imrajeshkr/distilhubert-finetuned-speech_commands on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1986
- F1: 0.9787
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.1816 | 1.0 | 4861 | 0.1493 | 0.9679 |
| 0.0001 | 2.0 | 9722 | 0.2278 | 0.9640 |
| 0.0 | 3.0 | 14583 | 0.2210 | 0.9667 |
| 0.0005 | 4.0 | 19444 | 0.1952 | 0.9749 |
| 0.1422 | 5.0 | 24305 | 0.1884 | 0.9762 |
| 0.0 | 6.0 | 29166 | 0.1888 | 0.9780 |
| 0.0 | 7.0 | 34027 | 0.2164 | 0.9728 |
| 0.0 | 8.0 | 38888 | 0.2039 | 0.9774 |
| 0.0 | 9.0 | 43749 | 0.1925 | 0.9800 |
| 0.0 | 10.0 | 48610 | 0.1986 | 0.9787 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.2.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0