metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_adamax_00001_fold5
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8933333333333333

smids_5x_deit_tiny_adamax_00001_fold5

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: 0.8918
Accuracy: 0.8933

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: 1e-05
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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3356	1.0	375	0.3637	0.8583
0.2941	2.0	750	0.2859	0.8917
0.2173	3.0	1125	0.2723	0.8933
0.2107	4.0	1500	0.2619	0.9017
0.1256	5.0	1875	0.3096	0.8767
0.0844	6.0	2250	0.2740	0.8983
0.0863	7.0	2625	0.3155	0.895
0.0472	8.0	3000	0.3497	0.895
0.0763	9.0	3375	0.3686	0.895
0.0335	10.0	3750	0.4149	0.8967
0.0338	11.0	4125	0.4756	0.8933
0.0184	12.0	4500	0.5125	0.89
0.0027	13.0	4875	0.6023	0.8767
0.0397	14.0	5250	0.6231	0.885
0.0014	15.0	5625	0.7069	0.8733
0.0003	16.0	6000	0.6770	0.8983
0.0258	17.0	6375	0.7038	0.895
0.0256	18.0	6750	0.7293	0.89
0.0002	19.0	7125	0.7746	0.8833
0.0001	20.0	7500	0.7738	0.8917
0.0001	21.0	7875	0.8059	0.8833
0.026	22.0	8250	0.8287	0.8933
0.0138	23.0	8625	0.8293	0.8867
0.0	24.0	9000	0.8289	0.88
0.0	25.0	9375	0.8428	0.8933
0.0001	26.0	9750	0.8343	0.8917
0.0016	27.0	10125	0.8455	0.89
0.0	28.0	10500	0.8478	0.89
0.0001	29.0	10875	0.8508	0.8917
0.0173	30.0	11250	0.8741	0.8917
0.0	31.0	11625	0.8677	0.8933
0.0	32.0	12000	0.8682	0.8933
0.0	33.0	12375	0.8819	0.8917
0.0	34.0	12750	0.8684	0.8917
0.0	35.0	13125	0.8910	0.8933
0.0	36.0	13500	0.8845	0.8933
0.0	37.0	13875	0.8700	0.8917
0.0072	38.0	14250	0.8781	0.8917
0.0	39.0	14625	0.8840	0.8933
0.0	40.0	15000	0.8993	0.895
0.0	41.0	15375	0.8767	0.8883
0.0	42.0	15750	0.8820	0.8967
0.0	43.0	16125	0.8803	0.8983
0.0	44.0	16500	0.8853	0.895
0.0	45.0	16875	0.8969	0.8917
0.0	46.0	17250	0.8999	0.8917
0.0073	47.0	17625	0.8921	0.895
0.0	48.0	18000	0.8943	0.8917
0.0	49.0	18375	0.8940	0.8933
0.0065	50.0	18750	0.8918	0.8933

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2