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: 1.4185
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: 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
1.4965	1.0	27	1.5474	0.2667
1.561	2.0	54	1.5386	0.2667
1.5488	3.0	81	1.5312	0.2667
1.5518	4.0	108	1.5243	0.2667
1.4809	5.0	135	1.5177	0.2667
1.4954	6.0	162	1.5111	0.2667
1.4888	7.0	189	1.5048	0.2667
1.5126	8.0	216	1.4993	0.2667
1.4812	9.0	243	1.4939	0.2667
1.4494	10.0	270	1.4885	0.2667
1.4861	11.0	297	1.4838	0.2667
1.491	12.0	324	1.4794	0.2667
1.4395	13.0	351	1.4751	0.2667
1.4636	14.0	378	1.4709	0.2667
1.4302	15.0	405	1.4673	0.2667
1.4414	16.0	432	1.4635	0.2667
1.4468	17.0	459	1.4602	0.2667
1.4709	18.0	486	1.4571	0.2667
1.4325	19.0	513	1.4542	0.2667
1.4645	20.0	540	1.4515	0.2667
1.4346	21.0	567	1.4487	0.2667
1.4324	22.0	594	1.4459	0.2667
1.3769	23.0	621	1.4436	0.2667
1.3945	24.0	648	1.4414	0.2667
1.415	25.0	675	1.4393	0.2667
1.4371	26.0	702	1.4375	0.2667
1.4355	27.0	729	1.4356	0.2667
1.3979	28.0	756	1.4341	0.2667
1.4061	29.0	783	1.4326	0.2667
1.4573	30.0	810	1.4309	0.2667
1.4027	31.0	837	1.4293	0.2667
1.4089	32.0	864	1.4280	0.2667
1.43	33.0	891	1.4268	0.2667
1.4098	34.0	918	1.4255	0.2667
1.3671	35.0	945	1.4244	0.2667
1.3717	36.0	972	1.4237	0.2667
1.3658	37.0	999	1.4228	0.2667
1.4295	38.0	1026	1.4220	0.2667
1.3909	39.0	1053	1.4214	0.2667
1.3599	40.0	1080	1.4209	0.2667
1.3564	41.0	1107	1.4202	0.2667
1.3635	42.0	1134	1.4197	0.2667
1.3875	43.0	1161	1.4194	0.2667
1.3551	44.0	1188	1.4191	0.2667
1.3825	45.0	1215	1.4188	0.2667
1.3691	46.0	1242	1.4187	0.2667
1.3678	47.0	1269	1.4186	0.2667
1.4155	48.0	1296	1.4185	0.2667
1.3778	49.0	1323	1.4185	0.2667
1.3456	50.0	1350	1.4185	0.2667

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_beit_base_sgd_0001_fold2

hushem_5x_beit_base_sgd_0001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_beit_base_sgd_0001_fold2