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_adamax_001_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: 0.8566666666666667

smids_1x_deit_small_adamax_001_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: 1.1786
• Accuracy: 0.8567

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
0.6005	1.0	75	0.4146	0.83
0.4739	2.0	150	0.5214	0.7783
0.3159	3.0	225	0.3979	0.8467
0.3044	4.0	300	0.4320	0.845
0.3525	5.0	375	0.3215	0.8817
0.1872	6.0	450	0.4978	0.8267
0.2467	7.0	525	0.5551	0.8
0.1504	8.0	600	0.5301	0.8367
0.1309	9.0	675	0.5781	0.84
0.2177	10.0	750	0.5269	0.865
0.0844	11.0	825	0.5112	0.865
0.0758	12.0	900	0.6543	0.8617
0.1176	13.0	975	0.5860	0.855
0.0455	14.0	1050	0.7995	0.8317
0.0687	15.0	1125	0.6395	0.8633
0.0296	16.0	1200	0.8580	0.8517
0.0214	17.0	1275	0.9274	0.85
0.0164	18.0	1350	0.8318	0.8733
0.0192	19.0	1425	0.9491	0.8567
0.0338	20.0	1500	0.7653	0.8567
0.0007	21.0	1575	0.9985	0.8517
0.0001	22.0	1650	0.9967	0.87
0.0156	23.0	1725	1.1459	0.85
0.0033	24.0	1800	1.1111	0.8517
0.005	25.0	1875	1.1114	0.8467
0.0195	26.0	1950	1.0184	0.8617
0.0001	27.0	2025	1.0582	0.8567
0.0022	28.0	2100	1.1162	0.86
0.0	29.0	2175	1.1193	0.86
0.0	30.0	2250	1.1254	0.8567
0.0	31.0	2325	1.1372	0.86
0.0016	32.0	2400	1.1758	0.8583
0.0051	33.0	2475	1.1778	0.845
0.0047	34.0	2550	1.0600	0.8667
0.01	35.0	2625	1.1195	0.855
0.0037	36.0	2700	1.1381	0.8533
0.0025	37.0	2775	1.1434	0.855
0.0	38.0	2850	1.1612	0.8583
0.0	39.0	2925	1.1652	0.8567
0.0	40.0	3000	1.1711	0.855
0.0	41.0	3075	1.1589	0.86
0.0028	42.0	3150	1.1617	0.8617
0.0032	43.0	3225	1.1622	0.86
0.0	44.0	3300	1.1672	0.86
0.0027	45.0	3375	1.1668	0.86
0.0026	46.0	3450	1.1710	0.86
0.0057	47.0	3525	1.1686	0.86
0.0	48.0	3600	1.1767	0.8567
0.0	49.0	3675	1.1760	0.8583
0.0044	50.0	3750	1.1786	0.8567

Framework versions

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