metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_sgd_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: 0.9

smids_5x_deit_tiny_sgd_001_fold3

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

Loss: 0.2648
Accuracy: 0.9

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
0.7316	1.0	375	0.7849	0.6383
0.5408	2.0	750	0.5416	0.805
0.4144	3.0	1125	0.4477	0.8483
0.4149	4.0	1500	0.3929	0.8533
0.413	5.0	1875	0.3596	0.865
0.347	6.0	2250	0.3405	0.87
0.3766	7.0	2625	0.3237	0.885
0.3353	8.0	3000	0.3140	0.8833
0.2912	9.0	3375	0.3069	0.8817
0.2983	10.0	3750	0.3022	0.8883
0.2271	11.0	4125	0.2992	0.8867
0.2804	12.0	4500	0.2892	0.8917
0.2434	13.0	4875	0.2876	0.89
0.2434	14.0	5250	0.2819	0.8883
0.2457	15.0	5625	0.2817	0.8967
0.2178	16.0	6000	0.2772	0.9
0.2586	17.0	6375	0.2753	0.9
0.2424	18.0	6750	0.2760	0.8967
0.2316	19.0	7125	0.2730	0.8967
0.236	20.0	7500	0.2701	0.9033
0.1785	21.0	7875	0.2679	0.9017
0.1868	22.0	8250	0.2698	0.9
0.2515	23.0	8625	0.2683	0.8983
0.2504	24.0	9000	0.2635	0.8967
0.2044	25.0	9375	0.2645	0.9033
0.2051	26.0	9750	0.2668	0.8983
0.2231	27.0	10125	0.2645	0.9033
0.2003	28.0	10500	0.2627	0.8983
0.1423	29.0	10875	0.2631	0.9033
0.2099	30.0	11250	0.2641	0.9
0.2023	31.0	11625	0.2642	0.9
0.2174	32.0	12000	0.2642	0.9
0.198	33.0	12375	0.2636	0.8967
0.1518	34.0	12750	0.2625	0.9033
0.1375	35.0	13125	0.2629	0.9017
0.1414	36.0	13500	0.2638	0.9017
0.1599	37.0	13875	0.2634	0.9033
0.164	38.0	14250	0.2642	0.9
0.1442	39.0	14625	0.2626	0.8983
0.1928	40.0	15000	0.2641	0.9017
0.1643	41.0	15375	0.2643	0.9017
0.1534	42.0	15750	0.2642	0.9017
0.1818	43.0	16125	0.2644	0.9017
0.1596	44.0	16500	0.2650	0.9
0.1441	45.0	16875	0.2645	0.9017
0.1513	46.0	17250	0.2643	0.9
0.1221	47.0	17625	0.2647	0.9
0.1853	48.0	18000	0.2646	0.9
0.1404	49.0	18375	0.2649	0.9
0.1644	50.0	18750	0.2648	0.9

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2