smids_5x_deit_small_rms_00001_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: 0.9811
• Accuracy: 0.905

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: 1e-05
• 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
0.2316	1.0	375	0.3828	0.845
0.1221	2.0	750	0.3043	0.8767
0.1068	3.0	1125	0.3175	0.8983
0.0662	4.0	1500	0.4134	0.91
0.0386	5.0	1875	0.4725	0.9017
0.0006	6.0	2250	0.5991	0.8967
0.0164	7.0	2625	0.5133	0.9083
0.0227	8.0	3000	0.6114	0.905
0.0539	9.0	3375	0.7854	0.8933
0.0093	10.0	3750	0.6820	0.8983
0.0296	11.0	4125	0.8028	0.88
0.0005	12.0	4500	0.7438	0.8983
0.0103	13.0	4875	0.8815	0.885
0.0	14.0	5250	0.8305	0.89
0.0056	15.0	5625	0.8083	0.895
0.0	16.0	6000	0.7453	0.8917
0.0	17.0	6375	0.7352	0.8967
0.0086	18.0	6750	0.8865	0.8883
0.0	19.0	7125	0.9006	0.8867
0.0007	20.0	7500	0.8620	0.8883
0.0001	21.0	7875	0.8055	0.8967
0.0167	22.0	8250	0.9436	0.8917
0.0	23.0	8625	0.9512	0.8883
0.0	24.0	9000	0.8722	0.9017
0.014	25.0	9375	0.8674	0.9
0.0	26.0	9750	0.8631	0.9017
0.0	27.0	10125	0.8607	0.9017
0.0054	28.0	10500	0.8949	0.9017
0.0	29.0	10875	0.9221	0.895
0.0052	30.0	11250	0.8532	0.905
0.0	31.0	11625	0.8797	0.9017
0.0	32.0	12000	0.8663	0.8983
0.0	33.0	12375	0.9338	0.8983
0.0	34.0	12750	0.9397	0.9033
0.0	35.0	13125	0.9338	0.905
0.0	36.0	13500	0.9706	0.9
0.0	37.0	13875	0.9486	0.9
0.0028	38.0	14250	0.9187	0.9033
0.0	39.0	14625	0.9340	0.9067
0.0	40.0	15000	0.9523	0.905
0.0	41.0	15375	0.9602	0.9067
0.0	42.0	15750	0.9532	0.905
0.0	43.0	16125	0.9551	0.9067
0.0	44.0	16500	0.9611	0.905
0.0	45.0	16875	0.9674	0.905
0.0	46.0	17250	0.9798	0.905
0.0027	47.0	17625	0.9798	0.905
0.0	48.0	18000	0.9814	0.905
0.0	49.0	18375	0.9829	0.905
0.0022	50.0	18750	0.9811	0.905

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2