Edit model card

Image-Classifier-Pokemons

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

  • Loss: 1.8369
  • Accuracy: 0.8921

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
  • training_steps: 1200

Training results

Training Loss Epoch Step Validation Loss Accuracy
4.9198 0.9943 87 4.8889 0.1158
4.4617 2.0 175 4.4093 0.5868
3.869 2.9943 262 3.8642 0.7534
3.4201 4.0 350 3.4278 0.8170
3.0186 4.9943 437 3.0832 0.8220
2.6769 6.0 525 2.7755 0.8578
2.4469 6.9943 612 2.5311 0.8635
2.1796 8.0 700 2.3141 0.8771
2.0105 8.9943 787 2.1620 0.8849
1.8571 10.0 875 2.0283 0.8885
1.7549 10.9943 962 1.9372 0.8856
1.6934 12.0 1050 1.8779 0.8949
1.6377 12.9943 1137 1.8180 0.9006
1.6182 13.7143 1200 1.8369 0.8921

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
85.9M params
Tensor type
F32
·

Finetuned from