hushem_1x_beit_base_rms_001_fold4

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: 1.1403
• Accuracy: 0.4524

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
No log	1.0	6	2.4924	0.2619
4.2258	2.0	12	2.2430	0.2381
4.2258	3.0	18	1.7745	0.2619
1.6665	4.0	24	1.4260	0.2381
1.4856	5.0	30	1.3866	0.2619
1.4856	6.0	36	1.4278	0.2619
1.4454	7.0	42	1.4079	0.2381
1.4454	8.0	48	1.4268	0.2381
1.408	9.0	54	1.3464	0.3095
1.4164	10.0	60	1.3818	0.2619
1.4164	11.0	66	1.3229	0.4048
1.3723	12.0	72	1.2005	0.4286
1.3723	13.0	78	1.3168	0.3333
1.3294	14.0	84	1.3652	0.2857
1.3514	15.0	90	1.2992	0.3095
1.3514	16.0	96	1.2709	0.3095
1.2833	17.0	102	1.0901	0.5714
1.2833	18.0	108	1.2138	0.4286
1.2546	19.0	114	1.2470	0.3810
1.2893	20.0	120	1.2665	0.4048
1.2893	21.0	126	1.1295	0.5476
1.2456	22.0	132	1.1935	0.4762
1.2456	23.0	138	1.1859	0.2857
1.2107	24.0	144	1.2333	0.3095
1.211	25.0	150	1.1492	0.5
1.211	26.0	156	1.1293	0.3810
1.2139	27.0	162	1.1301	0.4048
1.2139	28.0	168	1.2567	0.2857
1.1599	29.0	174	1.1146	0.4524
1.1826	30.0	180	1.1895	0.4524
1.1826	31.0	186	1.1803	0.4286
1.1665	32.0	192	1.1331	0.4524
1.1665	33.0	198	1.2501	0.2619
1.1881	34.0	204	1.1720	0.3571
1.1428	35.0	210	1.1303	0.3810
1.1428	36.0	216	1.0467	0.4524
1.1325	37.0	222	1.1840	0.3095
1.1325	38.0	228	1.1537	0.3571
1.0868	39.0	234	1.1576	0.3571
1.0845	40.0	240	1.1445	0.4524
1.0845	41.0	246	1.1472	0.4524
1.0808	42.0	252	1.1403	0.4524
1.0808	43.0	258	1.1403	0.4524
1.0575	44.0	264	1.1403	0.4524
1.0837	45.0	270	1.1403	0.4524
1.0837	46.0	276	1.1403	0.4524
1.0819	47.0	282	1.1403	0.4524
1.0819	48.0	288	1.1403	0.4524
1.0729	49.0	294	1.1403	0.4524
1.0942	50.0	300	1.1403	0.4524

Framework versions

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