Edit model card

car-type-model

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: 1.0169
  • Accuracy: 0.4737

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 0.8 1 1.1248 0.1053
No log 1.6 2 1.0913 0.3684
No log 2.4 3 1.0755 0.2632
No log 4.0 5 1.0527 0.3158
No log 4.8 6 1.0419 0.4211
No log 5.6 7 1.0168 0.4737
No log 6.4 8 1.0152 0.5263
1.0044 8.0 10 1.0169 0.4737

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
11
Safetensors
Model size
85.8M params
Tensor type
F32
ยท

Finetuned from

Space using TenzinNYeshey/car-type-model 1

Evaluation results