README.md

metadata

base_model: ntu-spml/distilhubert
datasets:
  - marsyas/gtzan
license: apache-2.0
metrics:
  - accuracy
tags:
  - generated_from_trainer
model-index:
  - name: ft-hubert-on-gtzan
    results:
      - task:
          type: audio-classification
          name: Audio Classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: default
          split: train
          args: default
        metrics:
          - type: accuracy
            value: 0.615
            name: Accuracy

ft-hubert-on-gtzan

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:

• Loss: 1.7593
• Accuracy: 0.615

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	50	1.9564	0.495
No log	2.0	100	1.7593	0.615

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1