Edit model card

image_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: 1.2386
  • Accuracy: 0.5625

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: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.0874 1.0 10 2.0621 0.2313
2.036 2.0 20 2.0392 0.2375
1.9297 3.0 30 1.9592 0.3
1.7723 4.0 40 1.7877 0.3937
1.6184 5.0 50 1.6475 0.45
1.5407 6.0 60 1.5514 0.4875
1.4197 7.0 70 1.4967 0.4938
1.3092 8.0 80 1.4332 0.4813
1.1251 9.0 90 1.4457 0.4688
1.2081 10.0 100 1.3603 0.4938
0.9803 11.0 110 1.3501 0.5188
1.0105 12.0 120 1.3212 0.55
0.9264 13.0 130 1.2895 0.575
0.9229 14.0 140 1.2882 0.5188
0.9397 15.0 150 1.4027 0.475
0.8322 16.0 160 1.2824 0.5312
0.8185 17.0 170 1.3025 0.5
0.7592 18.0 180 1.3629 0.475
0.7416 19.0 190 1.3221 0.5437
0.6323 20.0 200 1.2714 0.5563
0.6453 21.0 210 1.3015 0.4938
0.6049 22.0 220 1.3065 0.5375
0.5919 23.0 230 1.2579 0.5375
0.5354 24.0 240 1.2428 0.55
0.6379 25.0 250 1.2884 0.5375
0.5681 26.0 260 1.2201 0.5938
0.4275 27.0 270 1.3199 0.4875
0.4791 28.0 280 1.3027 0.5312
0.4693 29.0 290 1.3737 0.4813
0.5528 30.0 300 1.3342 0.4688

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
16
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 fathurim/image_classification

Finetuned
(1693)
this model

Evaluation results