metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - recall
  - f1
  - precision
model-index:
  - name: deit-base-patch16-224-finetuned-ind-4-imbalanced-aadhaarmask-3839
    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: 0.9479166666666666
          - name: Recall
            type: recall
            value: 0.9479166666666666
          - name: F1
            type: f1
            value: 0.9464668525772705
          - name: Precision
            type: precision
            value: 0.9472181024490807

deit-base-patch16-224-finetuned-ind-4-imbalanced-aadhaarmask-3839

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

Loss: 0.1444
Accuracy: 0.9479
Recall: 0.9479
F1: 0.9465
Precision: 0.9472

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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	Recall	F1	Precision
0.2268	1.0	96	0.2805	0.8919	0.8919	0.8753	0.8798
0.2356	2.0	192	0.2842	0.9023	0.9023	0.8950	0.8967
0.1597	3.0	288	0.2120	0.9219	0.9219	0.9116	0.9211
0.1349	4.0	384	0.2449	0.9206	0.9206	0.9146	0.9193
0.1647	5.0	480	0.2226	0.9167	0.9167	0.9129	0.9121
0.1117	6.0	576	0.1599	0.9453	0.9453	0.9415	0.9434
0.1232	7.0	672	0.1698	0.9492	0.9492	0.9477	0.9485
0.1317	8.0	768	0.1624	0.9388	0.9388	0.9365	0.9368
0.1018	9.0	864	0.1648	0.9388	0.9388	0.9360	0.9355
0.0828	10.0	960	0.1597	0.9453	0.9453	0.9435	0.9454

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1