metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_small_rms_001_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: 0.7662771285475793

smids_3x_deit_small_rms_001_fold1

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

Loss: 1.0295
Accuracy: 0.7663

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9037	1.0	226	1.1611	0.4224
0.8436	2.0	452	0.8419	0.5442
0.8202	3.0	678	0.8414	0.5359
0.8734	4.0	904	0.8332	0.5326
0.8282	5.0	1130	0.7907	0.6127
0.8721	6.0	1356	0.8061	0.5559
0.7744	7.0	1582	0.7612	0.6260
0.7444	8.0	1808	0.8606	0.5492
0.7266	9.0	2034	0.7492	0.6427
0.7385	10.0	2260	0.7643	0.6344
0.6851	11.0	2486	0.7983	0.5843
0.6844	12.0	2712	0.7946	0.6561
0.6727	13.0	2938	0.8087	0.6244
0.6244	14.0	3164	0.6709	0.6912
0.6712	15.0	3390	0.6742	0.7095
0.6346	16.0	3616	0.6684	0.7162
0.5408	17.0	3842	0.6615	0.7028
0.63	18.0	4068	0.6480	0.7295
0.6263	19.0	4294	0.7205	0.6611
0.5327	20.0	4520	0.6519	0.7078
0.6622	21.0	4746	0.6350	0.7179
0.6299	22.0	4972	0.8817	0.6210
0.6304	23.0	5198	0.6476	0.7362
0.5526	24.0	5424	0.6677	0.7145
0.6295	25.0	5650	0.6118	0.7546
0.6308	26.0	5876	0.6212	0.7362
0.5383	27.0	6102	0.7015	0.7179
0.5618	28.0	6328	0.8218	0.6711
0.4879	29.0	6554	0.7043	0.6928
0.5827	30.0	6780	0.6552	0.7229
0.5364	31.0	7006	0.6340	0.7379
0.4905	32.0	7232	0.6047	0.7529
0.4492	33.0	7458	0.7039	0.7028
0.4914	34.0	7684	0.6660	0.7379
0.3519	35.0	7910	0.6494	0.7479
0.3791	36.0	8136	0.6497	0.7513
0.4111	37.0	8362	0.6075	0.7646
0.4433	38.0	8588	0.6728	0.7679
0.3357	39.0	8814	0.6576	0.7529
0.3901	40.0	9040	0.6972	0.7596
0.4094	41.0	9266	0.6481	0.7696
0.3576	42.0	9492	0.6871	0.7746
0.335	43.0	9718	0.7307	0.7846
0.2737	44.0	9944	0.7687	0.7746
0.3485	45.0	10170	0.7785	0.7780
0.278	46.0	10396	0.8580	0.7730
0.2622	47.0	10622	0.8921	0.7713
0.2496	48.0	10848	0.9544	0.7730
0.1441	49.0	11074	0.9744	0.7730
0.1894	50.0	11300	1.0295	0.7663

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2