hushem_conflu_deneme_fold1

This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8961
  • Accuracy: 0.5111

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: 0.001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • 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 6 1.4190 0.2444
1.9213 2.0 12 1.3227 0.3111
1.9213 3.0 18 2.3526 0.2444
1.2734 4.0 24 1.7104 0.3778
1.0407 5.0 30 1.6039 0.3556
1.0407 6.0 36 1.2459 0.4667
0.733 7.0 42 1.3344 0.4667
0.733 8.0 48 1.5744 0.5556
0.448 9.0 54 1.2479 0.5556
0.3254 10.0 60 2.2545 0.5333
0.3254 11.0 66 1.7472 0.5333
0.2088 12.0 72 2.0350 0.5778
0.2088 13.0 78 3.0002 0.4889
0.1216 14.0 84 2.1774 0.5556
0.0746 15.0 90 2.5953 0.5333
0.0746 16.0 96 2.8934 0.5111
0.0176 17.0 102 2.8961 0.5111
0.0176 18.0 108 2.8961 0.5111
0.0201 19.0 114 2.8961 0.5111
0.0136 20.0 120 2.8961 0.5111

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
8
Safetensors
Model size
5.53M 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 hkivancoral/hushem_conflu_deneme_fold1

Finetuned
(363)
this model

Evaluation results