distilhubert-bass5

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

• Loss: 0.0088
• Accuracy: 0.9991

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
• gradient_accumulation_steps: 3
• total_train_batch_size: 192
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.138	1.0	159	0.1198	0.9827
0.0307	2.0	319	0.0194	0.9976
0.0101	2.99	477	0.0088	0.9991

Framework versions

• Transformers 4.39.2
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.15.2