Edit model card

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: 1.8160
  • Accuracy: 0.54

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 2.0091 0.465
No log 2.0 100 1.8160 0.54

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.2
  • Datasets 2.17.0
  • Tokenizers 0.15.1
Downloads last month
13
Safetensors
Model size
23.7M params
Tensor type
F32
·

Finetuned from

Dataset used to train aisuko/ft-hubert-on-gtzan

Evaluation results