metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_small_adamax_001_fold2
    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: 0.8801996672212978

smids_1x_deit_small_adamax_001_fold2

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: 0.9149
Accuracy: 0.8802

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
0.543	1.0	75	0.5577	0.7404
0.4238	2.0	150	0.4831	0.8120
0.4445	3.0	225	0.4591	0.8270
0.3847	4.0	300	0.4713	0.8369
0.2952	5.0	375	0.3692	0.8469
0.2663	6.0	450	0.4477	0.8336
0.2425	7.0	525	0.4906	0.8502
0.1718	8.0	600	0.4129	0.8486
0.181	9.0	675	0.4664	0.8369
0.1507	10.0	750	0.5087	0.8586
0.054	11.0	825	0.5852	0.8586
0.0682	12.0	900	0.4416	0.8669
0.0775	13.0	975	0.5468	0.8519
0.055	14.0	1050	0.7735	0.8469
0.1251	15.0	1125	0.6731	0.8453
0.0456	16.0	1200	0.6293	0.8586
0.0062	17.0	1275	0.8660	0.8502
0.098	18.0	1350	0.7112	0.8502
0.0187	19.0	1425	0.7932	0.8602
0.0128	20.0	1500	0.8437	0.8519
0.0006	21.0	1575	0.9421	0.8686
0.0053	22.0	1650	0.7611	0.8735
0.0134	23.0	1725	0.8550	0.8735
0.0005	24.0	1800	0.9144	0.8835
0.0024	25.0	1875	0.8153	0.8719
0.0042	26.0	1950	0.9985	0.8636
0.004	27.0	2025	0.9075	0.8735
0.0044	28.0	2100	0.8893	0.8735
0.0063	29.0	2175	0.8699	0.8802
0.0032	30.0	2250	0.8845	0.8719
0.0061	31.0	2325	0.8727	0.8785
0.0	32.0	2400	0.9476	0.8702
0.0001	33.0	2475	0.9392	0.8686
0.0295	34.0	2550	0.8832	0.8702
0.0089	35.0	2625	0.9008	0.8719
0.0029	36.0	2700	0.8983	0.8785
0.003	37.0	2775	0.8653	0.8752
0.0001	38.0	2850	0.8770	0.8769
0.0019	39.0	2925	0.8968	0.8752
0.0	40.0	3000	0.9023	0.8785
0.0031	41.0	3075	0.9066	0.8785
0.0001	42.0	3150	0.9074	0.8785
0.0028	43.0	3225	0.9037	0.8785
0.003	44.0	3300	0.9128	0.8785
0.0	45.0	3375	0.9191	0.8785
0.0	46.0	3450	0.9118	0.8785
0.0026	47.0	3525	0.9156	0.8785
0.0	48.0	3600	0.9135	0.8785
0.0023	49.0	3675	0.9151	0.8802
0.0022	50.0	3750	0.9149	0.8802

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0