README.md

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_rms_0001_fold3
    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: 0.8683333333333333

smids_1x_deit_small_rms_0001_fold3

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: 1.1062
• Accuracy: 0.8683

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
0.9975	1.0	75	0.8496	0.5467
0.5061	2.0	150	0.5223	0.8067
0.3795	3.0	225	0.4405	0.8267
0.3892	4.0	300	0.3713	0.8533
0.1768	5.0	375	0.3582	0.88
0.1554	6.0	450	0.4330	0.8733
0.1428	7.0	525	0.4207	0.8567
0.0674	8.0	600	0.6040	0.8567
0.0307	9.0	675	0.7767	0.8317
0.0367	10.0	750	0.6480	0.8567
0.0581	11.0	825	0.6494	0.87
0.0608	12.0	900	0.5071	0.8667
0.0462	13.0	975	0.7332	0.855
0.0198	14.0	1050	0.7960	0.8633
0.0291	15.0	1125	0.7675	0.8683
0.0004	16.0	1200	0.8666	0.8567
0.0394	17.0	1275	0.8320	0.8667
0.0137	18.0	1350	0.8206	0.86
0.0055	19.0	1425	0.9665	0.8583
0.029	20.0	1500	0.8497	0.8683
0.0429	21.0	1575	0.9318	0.8717
0.0315	22.0	1650	0.9188	0.8567
0.0182	23.0	1725	0.8073	0.875
0.0239	24.0	1800	0.9607	0.8683
0.0057	25.0	1875	0.8991	0.8767
0.004	26.0	1950	0.8719	0.8633
0.0226	27.0	2025	0.8720	0.8533
0.0534	28.0	2100	0.8637	0.8633
0.0299	29.0	2175	0.9839	0.865
0.0001	30.0	2250	0.9564	0.8667
0.0001	31.0	2325	0.9281	0.8783
0.0024	32.0	2400	0.9454	0.875
0.0023	33.0	2475	0.9716	0.875
0.0055	34.0	2550	0.9822	0.875
0.009	35.0	2625	0.9930	0.865
0.0029	36.0	2700	1.0435	0.8717
0.0019	37.0	2775	1.0502	0.8683
0.0	38.0	2850	1.0112	0.87
0.0	39.0	2925	1.0171	0.8733
0.0	40.0	3000	1.0381	0.8733
0.0	41.0	3075	1.0120	0.8667
0.0026	42.0	3150	1.0208	0.8667
0.0025	43.0	3225	1.0419	0.8683
0.0	44.0	3300	1.0612	0.87
0.0025	45.0	3375	1.0735	0.8633
0.0025	46.0	3450	1.0868	0.8667
0.0049	47.0	3525	1.0931	0.87
0.0	48.0	3600	1.0992	0.8683
0.0	49.0	3675	1.1039	0.87
0.0045	50.0	3750	1.1062	0.8683

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0