smids_3x_deit_small_adamax_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: 0.8664
• Accuracy: 0.8867

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
0.3734	1.0	225	0.3687	0.8433
0.2659	2.0	450	0.3135	0.8733
0.1931	3.0	675	0.3034	0.8767
0.143	4.0	900	0.2889	0.885
0.131	5.0	1125	0.3167	0.8833
0.0729	6.0	1350	0.3187	0.8867
0.0909	7.0	1575	0.3427	0.8833
0.081	8.0	1800	0.3465	0.885
0.0722	9.0	2025	0.4276	0.8833
0.0153	10.0	2250	0.5104	0.8767
0.0073	11.0	2475	0.5571	0.8817
0.0388	12.0	2700	0.5705	0.895
0.0128	13.0	2925	0.6043	0.8767
0.0017	14.0	3150	0.6203	0.8867
0.0016	15.0	3375	0.6463	0.8883
0.0003	16.0	3600	0.6591	0.8867
0.0001	17.0	3825	0.6914	0.8867
0.0002	18.0	4050	0.7053	0.885
0.0391	19.0	4275	0.7283	0.8867
0.0001	20.0	4500	0.7538	0.885
0.0001	21.0	4725	0.7610	0.8833
0.0001	22.0	4950	0.7539	0.885
0.0001	23.0	5175	0.7650	0.8883
0.0242	24.0	5400	0.7853	0.8817
0.0001	25.0	5625	0.7908	0.8833
0.0001	26.0	5850	0.7914	0.885
0.0001	27.0	6075	0.8136	0.8817
0.0	28.0	6300	0.8276	0.8817
0.0067	29.0	6525	0.8343	0.8817
0.0	30.0	6750	0.8302	0.885
0.0	31.0	6975	0.8207	0.885
0.0	32.0	7200	0.8405	0.8833
0.0056	33.0	7425	0.8445	0.8833
0.0	34.0	7650	0.8188	0.885
0.0026	35.0	7875	0.8428	0.885
0.0	36.0	8100	0.8431	0.8867
0.0072	37.0	8325	0.8465	0.8867
0.0	38.0	8550	0.8730	0.885
0.0	39.0	8775	0.8549	0.8867
0.0	40.0	9000	0.8617	0.8833
0.0	41.0	9225	0.8684	0.885
0.0	42.0	9450	0.8688	0.885
0.0038	43.0	9675	0.8699	0.885
0.0	44.0	9900	0.8640	0.8867
0.0	45.0	10125	0.8568	0.8867
0.0	46.0	10350	0.8661	0.885
0.0	47.0	10575	0.8676	0.8867
0.0	48.0	10800	0.8675	0.8867
0.0	49.0	11025	0.8664	0.8867
0.0	50.0	11250	0.8664	0.8867

Framework versions

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