sample_foot / README.md
suncy13's picture
End of training
fb37299
metadata
license: apache-2.0
base_model: facebook/dinov2-small-imagenet1k-1-layer
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: sample_foot
    results: []

sample_foot

This model is a fine-tuned version of facebook/dinov2-small-imagenet1k-1-layer on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0754
  • Accuracy: 0.4545

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
5.6026 1.0 21 4.9823 0.4545
3.7497 2.0 42 3.6049 0.4545
3.1278 3.0 63 3.7326 0.4545
2.4551 4.0 84 2.0051 0.4545
2.3722 5.0 105 3.1027 0.4545
2.3023 6.0 126 2.6815 0.4545
2.8063 7.0 147 2.9446 0.4545
2.2692 8.0 168 3.1585 0.4545
2.545 9.0 189 2.8486 0.4545
2.2706 10.0 210 3.0754 0.4545

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0