test-seed / README.md
vuongnhathien's picture
Hehe
c8e463c verified
metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window16-256
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: test-seed
    results: []

test-seed

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on the don't care dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6797
  • Accuracy: 0.75

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: 0.0003
  • train_batch_size: 64
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 10 0.6739 0.7375
No log 2.0 20 0.4469 0.875

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2