smids_5x_deit_tiny_rms_00001_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: 0.9537
• 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
0.2762	1.0	375	0.2896	0.895
0.1644	2.0	750	0.3438	0.8783
0.0979	3.0	1125	0.3168	0.89
0.0564	4.0	1500	0.3257	0.9033
0.0779	5.0	1875	0.3885	0.8983
0.0908	6.0	2250	0.5137	0.8917
0.0272	7.0	2625	0.6097	0.9
0.0302	8.0	3000	0.6164	0.905
0.0116	9.0	3375	0.6445	0.905
0.03	10.0	3750	0.8252	0.8983
0.0134	11.0	4125	0.8460	0.8933
0.0063	12.0	4500	0.8830	0.8933
0.0001	13.0	4875	0.7641	0.8967
0.0003	14.0	5250	0.6936	0.9067
0.0001	15.0	5625	0.8158	0.8933
0.0147	16.0	6000	0.8005	0.9
0.0	17.0	6375	0.8369	0.9083
0.0	18.0	6750	0.7801	0.9117
0.0003	19.0	7125	0.8314	0.9
0.0272	20.0	7500	0.7717	0.9067
0.0197	21.0	7875	0.7616	0.91
0.0022	22.0	8250	0.8297	0.9017
0.0082	23.0	8625	0.9830	0.8967
0.0	24.0	9000	0.8304	0.9033
0.0	25.0	9375	0.9362	0.8967
0.0	26.0	9750	1.0186	0.885
0.0	27.0	10125	0.9660	0.895
0.0	28.0	10500	0.8565	0.9067
0.0	29.0	10875	1.0314	0.9
0.004	30.0	11250	1.0325	0.8917
0.0	31.0	11625	0.9803	0.905
0.0	32.0	12000	0.9230	0.8967
0.0	33.0	12375	0.9577	0.8983
0.0055	34.0	12750	1.0448	0.89
0.0	35.0	13125	0.9488	0.9017
0.0	36.0	13500	0.9198	0.9083
0.0	37.0	13875	0.9232	0.905
0.0	38.0	14250	1.0528	0.89
0.0	39.0	14625	0.9516	0.8983
0.0039	40.0	15000	0.9539	0.8983
0.0	41.0	15375	0.9633	0.8983
0.0	42.0	15750	0.9250	0.9033
0.0	43.0	16125	0.9440	0.9017
0.0	44.0	16500	0.9475	0.905
0.0	45.0	16875	0.9408	0.905
0.0	46.0	17250	0.9488	0.905
0.0	47.0	17625	0.9474	0.905
0.0	48.0	18000	0.9524	0.905
0.0	49.0	18375	0.9540	0.9033
0.0	50.0	18750	0.9537	0.905

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.1+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2