smids_10x_deit_small_rms_00001_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: 1.0298
• Accuracy: 0.9117

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
0.17	1.0	750	0.2376	0.9167
0.1586	2.0	1500	0.3127	0.9117
0.0361	3.0	2250	0.4163	0.9033
0.0337	4.0	3000	0.5484	0.89
0.0423	5.0	3750	0.5723	0.91
0.0287	6.0	4500	0.6189	0.905
0.0936	7.0	5250	0.8112	0.895
0.0008	8.0	6000	0.7783	0.8967
0.0117	9.0	6750	0.8326	0.8983
0.0553	10.0	7500	0.8619	0.8967
0.0	11.0	8250	0.7664	0.895
0.0	12.0	9000	0.9064	0.8917
0.022	13.0	9750	0.8767	0.905
0.0003	14.0	10500	0.8256	0.8967
0.0	15.0	11250	0.8920	0.8983
0.0	16.0	12000	0.8919	0.8883
0.0005	17.0	12750	0.7873	0.91
0.0002	18.0	13500	1.0358	0.8833
0.0	19.0	14250	0.9585	0.8933
0.0	20.0	15000	0.9183	0.8933
0.02	21.0	15750	1.0608	0.8867
0.0	22.0	16500	0.9497	0.8983
0.0	23.0	17250	0.9676	0.895
0.0	24.0	18000	0.9490	0.8983
0.001	25.0	18750	1.0068	0.8983
0.0001	26.0	19500	0.9409	0.9017
0.0	27.0	20250	0.9205	0.8933
0.0006	28.0	21000	0.9294	0.9033
0.0	29.0	21750	0.9650	0.8917
0.0	30.0	22500	1.0551	0.8933
0.0	31.0	23250	0.9687	0.895
0.0	32.0	24000	0.9869	0.8933
0.0	33.0	24750	0.9708	0.905
0.0	34.0	25500	0.9496	0.9067
0.0	35.0	26250	0.9626	0.91
0.0	36.0	27000	1.0150	0.9033
0.0	37.0	27750	0.9930	0.9017
0.0	38.0	28500	0.9861	0.905
0.0	39.0	29250	1.0163	0.9033
0.0	40.0	30000	1.0159	0.9017
0.0	41.0	30750	1.0242	0.9033
0.0	42.0	31500	1.0278	0.905
0.0	43.0	32250	1.0282	0.9033
0.0	44.0	33000	1.0251	0.9083
0.0	45.0	33750	1.0218	0.91
0.0	46.0	34500	1.0275	0.91
0.0	47.0	35250	1.0270	0.9083
0.0	48.0	36000	1.0297	0.91
0.0	49.0	36750	1.0292	0.91
0.0	50.0	37500	1.0298	0.9117

Framework versions

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