metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilhubert-finetuned-cry-detector
results: []
distilhubert-finetuned-cry-detector
This model is a fine-tuned version of ntu-spml/distilhubert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0625
- Accuracy: 0.9824
- Precision: 0.9825
- Recall: 0.9824
- F1: 0.9824
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: 3e-05
- 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: 0.001
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.9956 | 85 | 0.1378 | 0.9546 | 0.9543 | 0.9546 | 0.9544 |
| No log | 1.9912 | 170 | 0.0802 | 0.9714 | 0.9713 | 0.9714 | 0.9714 |
| No log | 2.9985 | 256 | 0.0682 | 0.9780 | 0.9783 | 0.9780 | 0.9781 |
| No log | 3.9824 | 340 | 0.0625 | 0.9824 | 0.9825 | 0.9824 | 0.9824 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1