Marcos12886's picture
End of training
cc30eae verified
|
raw
history blame
2.77 kB
metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: distilhubert-finetuned-cry-detector
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.991941391941392
          - name: F1
            type: f1
            value: 0.9919569277165429
          - name: Precision
            type: precision
            value: 0.9920048531706146
          - name: Recall
            type: recall
            value: 0.991941391941392

distilhubert-finetuned-cry-detector

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: 0.0408
  • Accuracy: 0.9919
  • F1: 0.9920
  • Precision: 0.9920
  • Recall: 0.9919

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: 7

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
No log 0.9956 85 0.0736 0.9788 0.9788 0.9790 0.9788
No log 1.9912 170 0.0680 0.9758 0.9760 0.9770 0.9758
No log 2.9985 256 0.0447 0.9875 0.9876 0.9876 0.9875
No log 3.9941 341 0.0452 0.9905 0.9905 0.9905 0.9905
No log 4.9898 426 0.0439 0.9919 0.9920 0.9920 0.9919
0.053 5.9971 512 0.0401 0.9919 0.9920 0.9920 0.9919
0.053 6.9693 595 0.0408 0.9919 0.9920 0.9920 0.9919

Framework versions

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