hushem_1x_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: 1.5467
• 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
No log	1.0	6	1.5555	0.2667
1.6026	2.0	12	1.5551	0.2667
1.6026	3.0	18	1.5546	0.2667
1.5488	4.0	24	1.5542	0.2667
1.6016	5.0	30	1.5538	0.2667
1.6016	6.0	36	1.5534	0.2667
1.5779	7.0	42	1.5530	0.2667
1.5779	8.0	48	1.5527	0.2667
1.588	9.0	54	1.5523	0.2667
1.5533	10.0	60	1.5519	0.2667
1.5533	11.0	66	1.5516	0.2667
1.5856	12.0	72	1.5513	0.2667
1.5856	13.0	78	1.5510	0.2667
1.5657	14.0	84	1.5507	0.2667
1.5825	15.0	90	1.5503	0.2667
1.5825	16.0	96	1.5501	0.2667
1.5958	17.0	102	1.5498	0.2667
1.5958	18.0	108	1.5495	0.2667
1.578	19.0	114	1.5493	0.2667
1.5925	20.0	120	1.5491	0.2667
1.5925	21.0	126	1.5489	0.2667
1.5804	22.0	132	1.5486	0.2667
1.5804	23.0	138	1.5484	0.2667
1.5969	24.0	144	1.5482	0.2667
1.5643	25.0	150	1.5481	0.2667
1.5643	26.0	156	1.5479	0.2667
1.5656	27.0	162	1.5478	0.2667
1.5656	28.0	168	1.5476	0.2667
1.5441	29.0	174	1.5475	0.2667
1.587	30.0	180	1.5474	0.2667
1.587	31.0	186	1.5473	0.2667
1.5666	32.0	192	1.5472	0.2667
1.5666	33.0	198	1.5471	0.2667
1.5492	34.0	204	1.5470	0.2667
1.5567	35.0	210	1.5469	0.2667
1.5567	36.0	216	1.5469	0.2667
1.5593	37.0	222	1.5468	0.2667
1.5593	38.0	228	1.5468	0.2667
1.5776	39.0	234	1.5468	0.2667
1.5552	40.0	240	1.5467	0.2667
1.5552	41.0	246	1.5467	0.2667
1.5605	42.0	252	1.5467	0.2667
1.5605	43.0	258	1.5467	0.2667
1.6075	44.0	264	1.5467	0.2667
1.5667	45.0	270	1.5467	0.2667
1.5667	46.0	276	1.5467	0.2667
1.5665	47.0	282	1.5467	0.2667
1.5665	48.0	288	1.5467	0.2667
1.5544	49.0	294	1.5467	0.2667
1.5829	50.0	300	1.5467	0.2667

Framework versions

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