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: 0.4604
Accuracy: 0.8283

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
1.1529	1.0	375	1.2380	0.355
1.0823	2.0	750	1.1537	0.38
0.966	3.0	1125	1.0702	0.43
0.8969	4.0	1500	0.9930	0.4833
0.8438	5.0	1875	0.9234	0.5467
0.8108	6.0	2250	0.8618	0.6067
0.781	7.0	2625	0.8085	0.6533
0.7359	8.0	3000	0.7640	0.695
0.6561	9.0	3375	0.7269	0.7067
0.687	10.0	3750	0.6956	0.72
0.6327	11.0	4125	0.6692	0.7333
0.6325	12.0	4500	0.6472	0.7433
0.6338	13.0	4875	0.6288	0.7567
0.6265	14.0	5250	0.6103	0.76
0.5767	15.0	5625	0.5960	0.7667
0.5529	16.0	6000	0.5830	0.7717
0.6057	17.0	6375	0.5711	0.7817
0.572	18.0	6750	0.5610	0.7817
0.5708	19.0	7125	0.5513	0.7833
0.5256	20.0	7500	0.5427	0.7867
0.4697	21.0	7875	0.5351	0.795
0.5346	22.0	8250	0.5286	0.7983
0.5543	23.0	8625	0.5218	0.8017
0.5387	24.0	9000	0.5157	0.8033
0.5031	25.0	9375	0.5106	0.8017
0.5567	26.0	9750	0.5058	0.805
0.5071	27.0	10125	0.5014	0.805
0.5467	28.0	10500	0.4973	0.8083
0.4516	29.0	10875	0.4933	0.8083
0.497	30.0	11250	0.4901	0.8133
0.5249	31.0	11625	0.4866	0.8133
0.5174	32.0	12000	0.4834	0.8167
0.5605	33.0	12375	0.4805	0.8183
0.5131	34.0	12750	0.4779	0.82
0.4459	35.0	13125	0.4756	0.8217
0.4556	36.0	13500	0.4735	0.8217
0.4756	37.0	13875	0.4716	0.8233
0.4606	38.0	14250	0.4696	0.8233
0.5275	39.0	14625	0.4682	0.825
0.4638	40.0	15000	0.4668	0.8233
0.4141	41.0	15375	0.4657	0.8233
0.4983	42.0	15750	0.4646	0.8283
0.5146	43.0	16125	0.4634	0.8267
0.4784	44.0	16500	0.4625	0.8267
0.4516	45.0	16875	0.4618	0.8283
0.496	46.0	17250	0.4612	0.8283
0.5144	47.0	17625	0.4609	0.8283
0.501	48.0	18000	0.4606	0.8283
0.4693	49.0	18375	0.4604	0.8283
0.4848	50.0	18750	0.4604	0.8283

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_sgd_0001_fold3

smids_5x_beit_base_sgd_0001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_sgd_0001_fold3