hushem_5x_beit_base_sgd_0001_fold5

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: 1.4856
• Accuracy: 0.3171

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: 0.0001
• 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
1.5711	1.0	28	1.6258	0.2439
1.5362	2.0	56	1.6161	0.2439
1.5243	3.0	84	1.6077	0.2439
1.5675	4.0	112	1.5988	0.2439
1.5133	5.0	140	1.5920	0.2439
1.5639	6.0	168	1.5854	0.2439
1.555	7.0	196	1.5785	0.2439
1.5064	8.0	224	1.5727	0.2439
1.4878	9.0	252	1.5672	0.2439
1.5121	10.0	280	1.5615	0.2439
1.4492	11.0	308	1.5578	0.2439
1.5023	12.0	336	1.5529	0.2439
1.5035	13.0	364	1.5492	0.2439
1.4801	14.0	392	1.5454	0.2439
1.4838	15.0	420	1.5419	0.2683
1.4587	16.0	448	1.5385	0.2683
1.4655	17.0	476	1.5343	0.2683
1.4244	18.0	504	1.5315	0.2927
1.4339	19.0	532	1.5284	0.2927
1.4266	20.0	560	1.5249	0.2927
1.4474	21.0	588	1.5220	0.2927
1.4652	22.0	616	1.5188	0.3171
1.4621	23.0	644	1.5163	0.3171
1.4655	24.0	672	1.5146	0.3171
1.4192	25.0	700	1.5130	0.3171
1.4459	26.0	728	1.5105	0.3171
1.469	27.0	756	1.5090	0.3171
1.3585	28.0	784	1.5067	0.3171
1.4084	29.0	812	1.5049	0.3171
1.4047	30.0	840	1.5031	0.3171
1.4414	31.0	868	1.5013	0.3171
1.3836	32.0	896	1.4995	0.3171
1.3896	33.0	924	1.4979	0.3171
1.4222	34.0	952	1.4964	0.3171
1.4396	35.0	980	1.4952	0.3171
1.3891	36.0	1008	1.4939	0.3171
1.393	37.0	1036	1.4925	0.3171
1.3697	38.0	1064	1.4914	0.3171
1.4252	39.0	1092	1.4901	0.3171
1.365	40.0	1120	1.4892	0.3171
1.4164	41.0	1148	1.4883	0.3171
1.3854	42.0	1176	1.4876	0.3171
1.3744	43.0	1204	1.4870	0.3171
1.4041	44.0	1232	1.4865	0.3171
1.3952	45.0	1260	1.4861	0.3171
1.3758	46.0	1288	1.4858	0.3171
1.3986	47.0	1316	1.4857	0.3171
1.3628	48.0	1344	1.4856	0.3171
1.4108	49.0	1372	1.4856	0.3171
1.4199	50.0	1400	1.4856	0.3171

Framework versions

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