hushem_1x_beit_base_sgd_00001_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: 1.6258
• Accuracy: 0.2439

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	1.6353	0.2439
1.5783	2.0	12	1.6348	0.2439
1.5783	3.0	18	1.6344	0.2439
1.5876	4.0	24	1.6339	0.2439
1.5772	5.0	30	1.6335	0.2439
1.5772	6.0	36	1.6330	0.2439
1.5977	7.0	42	1.6326	0.2439
1.5977	8.0	48	1.6322	0.2439
1.5317	9.0	54	1.6318	0.2439
1.5968	10.0	60	1.6314	0.2439
1.5968	11.0	66	1.6311	0.2439
1.549	12.0	72	1.6307	0.2439
1.549	13.0	78	1.6303	0.2439
1.5721	14.0	84	1.6300	0.2439
1.5369	15.0	90	1.6297	0.2439
1.5369	16.0	96	1.6294	0.2439
1.5705	17.0	102	1.6291	0.2439
1.5705	18.0	108	1.6288	0.2439
1.5679	19.0	114	1.6286	0.2439
1.5656	20.0	120	1.6284	0.2439
1.5656	21.0	126	1.6281	0.2439
1.5685	22.0	132	1.6279	0.2439
1.5685	23.0	138	1.6277	0.2439
1.5419	24.0	144	1.6275	0.2439
1.5718	25.0	150	1.6273	0.2439
1.5718	26.0	156	1.6271	0.2439
1.5745	27.0	162	1.6269	0.2439
1.5745	28.0	168	1.6268	0.2439
1.5571	29.0	174	1.6267	0.2439
1.5843	30.0	180	1.6265	0.2439
1.5843	31.0	186	1.6264	0.2439
1.5761	32.0	192	1.6263	0.2439
1.5761	33.0	198	1.6262	0.2439
1.5292	34.0	204	1.6261	0.2439
1.5827	35.0	210	1.6261	0.2439
1.5827	36.0	216	1.6260	0.2439
1.5796	37.0	222	1.6259	0.2439
1.5796	38.0	228	1.6259	0.2439
1.5699	39.0	234	1.6259	0.2439
1.5472	40.0	240	1.6258	0.2439
1.5472	41.0	246	1.6258	0.2439
1.5603	42.0	252	1.6258	0.2439
1.5603	43.0	258	1.6258	0.2439
1.5805	44.0	264	1.6258	0.2439
1.5679	45.0	270	1.6258	0.2439
1.5679	46.0	276	1.6258	0.2439
1.5821	47.0	282	1.6258	0.2439
1.5821	48.0	288	1.6258	0.2439
1.5058	49.0	294	1.6258	0.2439
1.5509	50.0	300	1.6258	0.2439

Framework versions

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