hushem_5x_beit_base_rms_001_fold3

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: 1.4768
• Accuracy: 0.6279

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
1.51	1.0	28	1.6351	0.2558
1.3869	2.0	56	1.4127	0.2558
1.3848	3.0	84	1.3895	0.2558
1.4113	4.0	112	1.3824	0.2558
1.3569	5.0	140	1.4121	0.2326
1.4625	6.0	168	1.3739	0.2326
1.3804	7.0	196	1.2185	0.5349
1.1352	8.0	224	1.1411	0.4884
1.0899	9.0	252	1.2426	0.3953
1.0945	10.0	280	1.1820	0.3488
1.1149	11.0	308	1.4574	0.3023
0.9942	12.0	336	1.4728	0.3256
1.0204	13.0	364	0.9801	0.5581
0.9987	14.0	392	1.0096	0.5349
1.0664	15.0	420	1.0007	0.5814
0.9463	16.0	448	1.2188	0.3953
0.9756	17.0	476	1.1284	0.5116
0.9698	18.0	504	1.4394	0.4419
1.061	19.0	532	1.1162	0.4884
0.8426	20.0	560	1.9296	0.3721
0.876	21.0	588	1.0070	0.5581
0.8908	22.0	616	1.2196	0.5349
0.8599	23.0	644	0.9502	0.6047
0.8338	24.0	672	0.8737	0.6279
0.785	25.0	700	1.1006	0.5814
0.82	26.0	728	1.0398	0.5814
0.8016	27.0	756	1.6671	0.3256
0.8574	28.0	784	1.1704	0.6279
0.8104	29.0	812	1.0502	0.6279
0.7421	30.0	840	0.9270	0.5814
0.7093	31.0	868	1.8057	0.4186
0.7469	32.0	896	0.9665	0.5814
0.7175	33.0	924	0.8190	0.6512
0.7129	34.0	952	1.0680	0.6279
0.7793	35.0	980	1.0966	0.5581
0.6879	36.0	1008	0.9990	0.5814
0.7016	37.0	1036	1.7556	0.4884
0.6238	38.0	1064	1.5792	0.4651
0.6025	39.0	1092	1.1502	0.6047
0.7264	40.0	1120	1.3317	0.5349
0.6063	41.0	1148	1.5492	0.5116
0.5816	42.0	1176	1.5787	0.5814
0.4627	43.0	1204	1.1301	0.6047
0.4652	44.0	1232	1.5008	0.6279
0.3885	45.0	1260	1.3167	0.6279
0.4003	46.0	1288	1.3851	0.6512
0.3882	47.0	1316	1.4601	0.6047
0.353	48.0	1344	1.4699	0.6279
0.3487	49.0	1372	1.4768	0.6279
0.2789	50.0	1400	1.4768	0.6279

Framework versions

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