metadata

library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: distilhubert-finetuned-en-alphabets
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.9568733153638813
          - name: Recall
            type: recall
            value: 0.9481132075471698
          - name: F1
            type: f1
            value: 0.9470261780589487

distilhubert-finetuned-en-alphabets

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: 0.4601
Precision: 0.9569
Recall: 0.9481
F1: 0.9470

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: 64
eval_batch_size: 64
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: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
2.7834	1.0	112	2.5326	0.4167	0.3726	0.3135
1.9668	2.0	224	1.6729	0.7006	0.7311	0.6796
1.4503	3.0	336	1.1778	0.8548	0.8302	0.8096
1.0224	4.0	448	0.8461	0.9041	0.8915	0.8869
0.8504	5.0	560	0.6392	0.9266	0.9198	0.9182
0.6555	6.0	672	0.5410	0.9536	0.9481	0.9466
0.5653	7.0	784	0.4801	0.9546	0.9481	0.9460
0.5328	8.0	896	0.4601	0.9569	0.9481	0.9470

Framework versions

Transformers 4.47.1
Pytorch 2.2.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0