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: 0.0878
- Accuracy: 0.9861
- Precision: 0.9861
- Recall: 0.9861
- F1: 0.9861
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: 0.0001
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.9956 | 85 | 0.1204 | 0.9641 | 0.9641 | 0.9641 | 0.9638 |
| No log | 1.9912 | 170 | 0.0847 | 0.9773 | 0.9772 | 0.9773 | 0.9773 |
| No log | 2.9985 | 256 | 0.1025 | 0.9766 | 0.9769 | 0.9766 | 0.9766 |
| No log | 3.9941 | 341 | 0.0869 | 0.9832 | 0.9835 | 0.9832 | 0.9832 |
| No log | 4.9898 | 426 | 0.0746 | 0.9832 | 0.9834 | 0.9832 | 0.9832 |
| 0.0538 | 5.9971 | 512 | 0.0870 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
| 0.0538 | 6.9927 | 597 | 0.0890 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
| 0.0538 | 7.9649 | 680 | 0.0878 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1