finetuned-bb / README.md
boooooook's picture
End of training
c23ed0d verified
metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
  - generated_from_trainer
datasets:
  - boooooook/benben
metrics:
  - accuracy
model-index:
  - name: boooooook/finetuned-benben
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: benben
          type: boooooook/benben
          config: all
          split: train
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 1

boooooook/finetuned-benben

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

  • Loss: 0.0012
  • Accuracy: 1.0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6001 1.0 27 0.5180 0.9583
0.1095 2.0 54 0.0390 1.0
0.0113 3.0 81 0.0063 1.0
0.0051 4.0 108 0.0032 1.0
0.0034 5.0 135 0.0022 1.0
0.0028 6.0 162 0.0018 1.0
0.0024 7.0 189 0.0015 1.0
0.0022 8.0 216 0.0014 1.0
0.002 9.0 243 0.0013 1.0
0.0019 10.0 270 0.0012 1.0

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1