trained-race / README.md
crangana's picture
End of training
7db16aa
|
raw
history blame
2.23 kB
metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - generated_from_trainer
datasets:
  - fair_face
metrics:
  - accuracy
model-index:
  - name: trained-race
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: fair_face
          type: fair_face
          config: '0.25'
          split: validation
          args: '0.25'
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.634380135110462

trained-race

This model is a fine-tuned version of microsoft/resnet-50 on the fair_face dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9495
  • Accuracy: 0.6344

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: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.4995 0.18 1000 1.5133 0.4135
1.3103 0.37 2000 1.2797 0.5045
1.2417 0.55 3000 1.1583 0.5451
1.2142 0.74 4000 1.0952 0.5780
1.0633 0.92 5000 1.0508 0.5973
0.9559 1.11 6000 1.0179 0.6106
0.9984 1.29 7000 0.9958 0.6179
0.9843 1.48 8000 0.9780 0.6315
0.8943 1.66 9000 0.9470 0.6386
0.9941 1.84 10000 0.9495 0.6344

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.0