metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_base_rms_0001_fold1
    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: 0.9048414023372288

smids_3x_deit_base_rms_0001_fold1

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: 0.8578
Accuracy: 0.9048

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: 0.0001
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
0.3767	1.0	226	0.4015	0.8047
0.1856	2.0	452	0.2907	0.8915
0.122	3.0	678	0.3819	0.8397
0.0716	4.0	904	0.6439	0.8598
0.0597	5.0	1130	0.4947	0.8831
0.0636	6.0	1356	0.4627	0.8965
0.0123	7.0	1582	0.5193	0.8798
0.0384	8.0	1808	0.5328	0.8965
0.0347	9.0	2034	0.5230	0.8865
0.0555	10.0	2260	0.4625	0.8915
0.0105	11.0	2486	0.4967	0.9032
0.0151	12.0	2712	0.5936	0.8798
0.0374	13.0	2938	0.5700	0.8881
0.0272	14.0	3164	0.5683	0.8915
0.0029	15.0	3390	0.8104	0.8815
0.0276	16.0	3616	0.6803	0.8932
0.006	17.0	3842	0.6793	0.8781
0.0461	18.0	4068	0.6650	0.8815
0.006	19.0	4294	0.8601	0.8831
0.0039	20.0	4520	0.5720	0.8948
0.0002	21.0	4746	0.6983	0.8948
0.0089	22.0	4972	0.6968	0.8865
0.0025	23.0	5198	0.7765	0.9032
0.0037	24.0	5424	0.7330	0.8965
0.0105	25.0	5650	0.5590	0.8932
0.0002	26.0	5876	0.6884	0.9048
0.0001	27.0	6102	0.6695	0.9015
0.0048	28.0	6328	0.7561	0.8848
0.0001	29.0	6554	0.8455	0.8831
0.0168	30.0	6780	0.6624	0.8932
0.013	31.0	7006	0.7840	0.8932
0.0	32.0	7232	0.6961	0.8982
0.0033	33.0	7458	0.8341	0.8915
0.0	34.0	7684	0.7715	0.9048
0.0	35.0	7910	0.8192	0.9015
0.0	36.0	8136	0.7732	0.9048
0.0	37.0	8362	0.7832	0.9098
0.0	38.0	8588	0.7728	0.9065
0.0	39.0	8814	0.8176	0.9065
0.0	40.0	9040	0.8093	0.9048
0.0026	41.0	9266	0.7762	0.9132
0.0021	42.0	9492	0.7747	0.9065
0.0	43.0	9718	0.7876	0.9048
0.0	44.0	9944	0.7913	0.9015
0.0	45.0	10170	0.8068	0.9015
0.0	46.0	10396	0.8218	0.9015
0.0	47.0	10622	0.8475	0.9048
0.0	48.0	10848	0.8522	0.9048
0.0	49.0	11074	0.8566	0.9048
0.0	50.0	11300	0.8578	0.9048

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2