Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-hasta-85-fold4

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
deit-base-distilled-patch16-224-hasta-85-fold4 / README.md
BilalMuftuoglu's picture
BilalMuftuoglu
End of training
fbdc301 verified
preview code
|
raw
history blame contribute delete
8.03 kB
metadata
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: deit-base-distilled-patch16-224-hasta-85-fold4
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7272727272727273

deit-base-distilled-patch16-224-hasta-85-fold4

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

  • Loss: 0.9542
  • Accuracy: 0.7273

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 1 2.0908 0.0
No log 2.0 2 1.8864 0.0
No log 3.0 3 1.5313 0.0
No log 4.0 4 1.1520 0.3636
No log 5.0 5 0.9542 0.7273
No log 6.0 6 1.0324 0.7273
No log 7.0 7 1.1792 0.7273
No log 8.0 8 1.2680 0.7273
No log 9.0 9 1.2078 0.7273
0.4805 10.0 10 1.1594 0.7273
0.4805 11.0 11 1.1604 0.7273
0.4805 12.0 12 1.1110 0.7273
0.4805 13.0 13 1.1074 0.7273
0.4805 14.0 14 1.1010 0.7273
0.4805 15.0 15 1.0594 0.7273
0.4805 16.0 16 1.0675 0.7273
0.4805 17.0 17 1.1689 0.7273
0.4805 18.0 18 1.2630 0.7273
0.4805 19.0 19 1.3017 0.7273
0.1904 20.0 20 1.3083 0.7273
0.1904 21.0 21 1.3764 0.7273
0.1904 22.0 22 1.4229 0.7273
0.1904 23.0 23 1.4830 0.7273
0.1904 24.0 24 1.4698 0.7273
0.1904 25.0 25 1.4947 0.7273
0.1904 26.0 26 1.5839 0.7273
0.1904 27.0 27 1.7219 0.7273
0.1904 28.0 28 1.7474 0.7273
0.1904 29.0 29 1.6645 0.7273
0.1472 30.0 30 1.5988 0.7273
0.1472 31.0 31 1.5703 0.7273
0.1472 32.0 32 1.5965 0.7273
0.1472 33.0 33 1.6618 0.7273
0.1472 34.0 34 1.6432 0.7273
0.1472 35.0 35 1.5392 0.7273
0.1472 36.0 36 1.4368 0.7273
0.1472 37.0 37 1.4019 0.7273
0.1472 38.0 38 1.4714 0.7273
0.1472 39.0 39 1.7523 0.7273
0.0741 40.0 40 1.8653 0.7273
0.0741 41.0 41 1.8966 0.7273
0.0741 42.0 42 1.8252 0.7273
0.0741 43.0 43 1.8433 0.7273
0.0741 44.0 44 1.7327 0.7273
0.0741 45.0 45 1.7456 0.7273
0.0741 46.0 46 1.8948 0.7273
0.0741 47.0 47 1.8811 0.7273
0.0741 48.0 48 1.8930 0.7273
0.0741 49.0 49 1.8065 0.7273
0.0506 50.0 50 1.7629 0.7273
0.0506 51.0 51 1.7893 0.7273
0.0506 52.0 52 1.8770 0.7273
0.0506 53.0 53 1.9144 0.7273
0.0506 54.0 54 2.0357 0.7273
0.0506 55.0 55 2.2103 0.7273
0.0506 56.0 56 2.2568 0.7273
0.0506 57.0 57 2.2401 0.7273
0.0506 58.0 58 2.1406 0.7273
0.0506 59.0 59 2.0280 0.7273
0.0355 60.0 60 1.9517 0.7273
0.0355 61.0 61 1.8787 0.7273
0.0355 62.0 62 1.8958 0.7273
0.0355 63.0 63 1.9893 0.7273
0.0355 64.0 64 2.1195 0.7273
0.0355 65.0 65 2.2715 0.7273
0.0355 66.0 66 2.3640 0.7273
0.0355 67.0 67 2.4391 0.7273
0.0355 68.0 68 2.4633 0.7273
0.0355 69.0 69 2.4489 0.7273
0.021 70.0 70 2.4177 0.7273
0.021 71.0 71 2.3674 0.7273
0.021 72.0 72 2.3065 0.7273
0.021 73.0 73 2.2978 0.7273
0.021 74.0 74 2.3590 0.7273
0.021 75.0 75 2.4277 0.7273
0.021 76.0 76 2.5220 0.7273
0.021 77.0 77 2.6248 0.7273
0.021 78.0 78 2.6925 0.7273
0.021 79.0 79 2.7284 0.7273
0.0346 80.0 80 2.7409 0.7273
0.0346 81.0 81 2.7218 0.7273
0.0346 82.0 82 2.6717 0.7273
0.0346 83.0 83 2.6142 0.7273
0.0346 84.0 84 2.5196 0.7273
0.0346 85.0 85 2.4438 0.7273
0.0346 86.0 86 2.3812 0.7273
0.0346 87.0 87 2.3026 0.7273
0.0346 88.0 88 2.2691 0.7273
0.0346 89.0 89 2.2665 0.7273
0.0219 90.0 90 2.2659 0.7273
0.0219 91.0 91 2.2735 0.7273
0.0219 92.0 92 2.3000 0.7273
0.0219 93.0 93 2.3136 0.7273
0.0219 94.0 94 2.3247 0.7273
0.0219 95.0 95 2.3388 0.7273
0.0219 96.0 96 2.3597 0.7273
0.0219 97.0 97 2.3746 0.7273
0.0219 98.0 98 2.3864 0.7273
0.0219 99.0 99 2.3913 0.7273
0.0286 100.0 100 2.3933 0.7273

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1