hushem_5x_beit_base_rms_001_fold2

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

• Loss: 3.7933
• Accuracy: 0.4444

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
1.4827	1.0	27	1.4775	0.2444
1.4158	2.0	54	1.4002	0.2667
1.3654	3.0	81	1.4674	0.2444
1.4175	4.0	108	1.4412	0.2444
1.394	5.0	135	1.3951	0.2667
1.2686	6.0	162	1.3983	0.2444
1.2556	7.0	189	1.4175	0.2889
1.2245	8.0	216	1.4754	0.2222
1.1427	9.0	243	1.5387	0.2
1.1659	10.0	270	1.3896	0.3333
1.2047	11.0	297	1.6922	0.2444
1.1384	12.0	324	1.4940	0.2667
1.1563	13.0	351	1.3730	0.2889
1.1141	14.0	378	1.4944	0.2222
1.0922	15.0	405	1.4049	0.2222
1.0475	16.0	432	1.2541	0.4
0.9208	17.0	459	1.2993	0.4222
0.9847	18.0	486	1.4111	0.4889
0.9327	19.0	513	1.3175	0.2889
0.8591	20.0	540	1.2892	0.3111
0.7605	21.0	567	1.6440	0.2667
0.7953	22.0	594	1.6915	0.3778
0.7644	23.0	621	1.6017	0.4667
0.7884	24.0	648	1.4064	0.2444
0.6883	25.0	675	1.9722	0.3111
0.7747	26.0	702	1.9209	0.4889
0.7012	27.0	729	2.2074	0.5333
0.6951	28.0	756	2.4602	0.3556
0.6581	29.0	783	2.1544	0.4222
0.6529	30.0	810	2.0677	0.3556
0.533	31.0	837	2.1507	0.3778
0.6648	32.0	864	2.1628	0.4222
0.6094	33.0	891	2.5365	0.3778
0.5601	34.0	918	2.8323	0.4222
0.519	35.0	945	2.4166	0.4
0.5988	36.0	972	2.6302	0.4444
0.5359	37.0	999	2.9183	0.3778
0.5451	38.0	1026	2.8746	0.5111
0.5087	39.0	1053	2.7419	0.4667
0.4563	40.0	1080	3.1565	0.4222
0.5182	41.0	1107	3.1768	0.4444
0.4348	42.0	1134	3.2761	0.4222
0.4504	43.0	1161	3.4108	0.4667
0.417	44.0	1188	3.5781	0.4444
0.4297	45.0	1215	3.6284	0.4444
0.3399	46.0	1242	3.7187	0.4444
0.3846	47.0	1269	3.7298	0.4667
0.3494	48.0	1296	3.7854	0.4444
0.3468	49.0	1323	3.7933	0.4444
0.3313	50.0	1350	3.7933	0.4444

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0