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_fold5
    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: 0.86

smids_1x_deit_small_adamax_001_fold5

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: 1.0002
• Accuracy: 0.86

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
0.6434	1.0	75	0.5267	0.795
0.4681	2.0	150	0.4240	0.82
0.3802	3.0	225	0.4300	0.8317
0.3978	4.0	300	0.4417	0.815
0.2851	5.0	375	0.4444	0.82
0.1694	6.0	450	0.3647	0.87
0.1978	7.0	525	0.4075	0.85
0.3005	8.0	600	0.3919	0.8533
0.1464	9.0	675	0.5040	0.85
0.0679	10.0	750	0.4768	0.8683
0.1428	11.0	825	0.5770	0.8367
0.0515	12.0	900	0.7151	0.8483
0.0525	13.0	975	0.6841	0.8433
0.0836	14.0	1050	0.6721	0.8583
0.0701	15.0	1125	0.7481	0.835
0.0512	16.0	1200	0.7462	0.8383
0.0331	17.0	1275	0.6909	0.86
0.0421	18.0	1350	0.8979	0.855
0.0249	19.0	1425	0.6741	0.865
0.0085	20.0	1500	0.8222	0.8483
0.0231	21.0	1575	0.6427	0.87
0.0092	22.0	1650	0.8231	0.8533
0.015	23.0	1725	0.8772	0.8533
0.002	24.0	1800	0.7754	0.86
0.0148	25.0	1875	0.8250	0.8733
0.004	26.0	1950	0.8667	0.8717
0.0153	27.0	2025	0.8197	0.8717
0.0089	28.0	2100	0.9170	0.8617
0.007	29.0	2175	0.9333	0.8583
0.0035	30.0	2250	0.8964	0.8667
0.0	31.0	2325	0.9173	0.8567
0.0	32.0	2400	0.9057	0.8617
0.0063	33.0	2475	0.9409	0.8667
0.0	34.0	2550	0.9412	0.8583
0.005	35.0	2625	0.9293	0.865
0.0	36.0	2700	0.9399	0.865
0.004	37.0	2775	0.9622	0.8683
0.001	38.0	2850	0.9655	0.8583
0.0	39.0	2925	0.9962	0.855
0.0	40.0	3000	0.9897	0.8567
0.0034	41.0	3075	0.9959	0.855
0.0	42.0	3150	0.9928	0.86
0.0077	43.0	3225	0.9873	0.8617
0.0	44.0	3300	0.9978	0.8583
0.0025	45.0	3375	0.9949	0.8617
0.0	46.0	3450	0.9977	0.8567
0.006	47.0	3525	0.9987	0.8567
0.0055	48.0	3600	1.0022	0.855
0.0	49.0	3675	1.0012	0.8583
0.0043	50.0	3750	1.0002	0.86

Framework versions

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