car-countries-classification

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: 1.4039
  • Accuracy: 0.2941

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.9231 3 1.5830 0.3137
No log 1.8462 6 1.5342 0.2941
No log 2.7692 9 1.4845 0.2941
1.5308 4.0 13 1.4705 0.2745
1.5308 4.9231 16 1.4534 0.3137
1.5308 5.8462 19 1.4583 0.2745
1.3601 6.7692 22 1.4218 0.2941
1.3601 8.0 26 1.4283 0.2745
1.3601 8.9231 29 1.3973 0.3137
1.2778 9.2308 30 1.4039 0.2941

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
15
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for pimcore/car-countries-classification

Finetuned
(1734)
this model

Evaluation results