distilhubert-finetuned-donateacry

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: 0.6654
• Accuracy: 0.8370
• F1: 0.7627
• Precision: 0.7005
• Recall: 0.8370

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 123
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.8696	5	0.6723	0.8370	0.7627	0.7005	0.8370
No log	1.9130	11	0.6778	0.8370	0.7627	0.7005	0.8370
No log	2.9565	17	0.6690	0.8370	0.7627	0.7005	0.8370
No log	4.0	23	0.6654	0.8370	0.7627	0.7005	0.8370

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1