hushem_5x_beit_base_sgd_00001_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: 1.5367
• Accuracy: 0.2667

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
1.5006	1.0	27	1.5552	0.2667
1.5759	2.0	54	1.5543	0.2667
1.5707	3.0	81	1.5535	0.2667
1.578	4.0	108	1.5527	0.2667
1.5119	5.0	135	1.5520	0.2667
1.5352	6.0	162	1.5512	0.2667
1.5348	7.0	189	1.5504	0.2667
1.5693	8.0	216	1.5497	0.2667
1.5386	9.0	243	1.5490	0.2667
1.5189	10.0	270	1.5483	0.2667
1.5597	11.0	297	1.5477	0.2667
1.5706	12.0	324	1.5471	0.2667
1.5157	13.0	351	1.5465	0.2667
1.5457	14.0	378	1.5458	0.2667
1.5087	15.0	405	1.5453	0.2667
1.5323	16.0	432	1.5447	0.2667
1.5363	17.0	459	1.5442	0.2667
1.5615	18.0	486	1.5437	0.2667
1.5236	19.0	513	1.5433	0.2667
1.566	20.0	540	1.5428	0.2667
1.5446	21.0	567	1.5424	0.2667
1.5289	22.0	594	1.5419	0.2667
1.4823	23.0	621	1.5415	0.2667
1.5025	24.0	648	1.5411	0.2667
1.5362	25.0	675	1.5407	0.2667
1.5593	26.0	702	1.5404	0.2667
1.5515	27.0	729	1.5401	0.2667
1.5275	28.0	756	1.5397	0.2667
1.5171	29.0	783	1.5394	0.2667
1.5816	30.0	810	1.5391	0.2667
1.5294	31.0	837	1.5389	0.2667
1.5276	32.0	864	1.5386	0.2667
1.5584	33.0	891	1.5384	0.2667
1.5549	34.0	918	1.5382	0.2667
1.4864	35.0	945	1.5380	0.2667
1.4851	36.0	972	1.5378	0.2667
1.4835	37.0	999	1.5376	0.2667
1.5708	38.0	1026	1.5374	0.2667
1.5448	39.0	1053	1.5373	0.2667
1.4945	40.0	1080	1.5372	0.2667
1.486	41.0	1107	1.5371	0.2667
1.5082	42.0	1134	1.5370	0.2667
1.5323	43.0	1161	1.5369	0.2667
1.4965	44.0	1188	1.5368	0.2667
1.5407	45.0	1215	1.5368	0.2667
1.5084	46.0	1242	1.5368	0.2667
1.5191	47.0	1269	1.5367	0.2667
1.5617	48.0	1296	1.5367	0.2667
1.4992	49.0	1323	1.5367	0.2667
1.4782	50.0	1350	1.5367	0.2667

Framework versions

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