Edit model card

Chess_images_classifier

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0591
  • Accuracy: 0.9

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 2 1.7966 0.1
No log 2.0 4 1.7835 0.2
No log 3.0 6 1.7547 0.2667
No log 4.0 8 1.7069 0.3667
1.7198 5.0 10 1.6416 0.3667
1.7198 6.0 12 1.5306 0.4
1.7198 7.0 14 1.4958 0.5333
1.7198 8.0 16 1.4440 0.5333
1.7198 9.0 18 1.3930 0.6
1.3635 10.0 20 1.2984 0.7333
1.3635 11.0 22 1.3484 0.7333
1.3635 12.0 24 1.2727 0.8333
1.3635 13.0 26 1.1674 0.8333
1.3635 14.0 28 1.1443 0.8667
1.0916 15.0 30 1.1607 0.9
1.0916 16.0 32 1.1076 0.8667
1.0916 17.0 34 1.0670 0.9667
1.0916 18.0 36 1.0694 0.9333
1.0916 19.0 38 1.0874 0.9
0.9397 20.0 40 1.0591 0.9

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
14
Safetensors
Model size
85.8M params
Tensor type
F32
·

Finetuned from

Evaluation results