hushem_5x_deit_base_rms_00001_fold5

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6351
• Accuracy: 0.9024

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
0.8457	1.0	28	0.5947	0.7317
0.1932	2.0	56	0.3789	0.8780
0.0378	3.0	84	0.3371	0.9024
0.0061	4.0	112	0.3727	0.9024
0.0027	5.0	140	0.3487	0.9024
0.0018	6.0	168	0.3750	0.9024
0.0012	7.0	196	0.3872	0.9024
0.0009	8.0	224	0.3976	0.9024
0.0007	9.0	252	0.4053	0.9024
0.0006	10.0	280	0.4125	0.9024
0.0005	11.0	308	0.4192	0.9024
0.0004	12.0	336	0.4329	0.9024
0.0003	13.0	364	0.4400	0.9024
0.0003	14.0	392	0.4408	0.9024
0.0002	15.0	420	0.4473	0.9024
0.0002	16.0	448	0.4630	0.9024
0.0002	17.0	476	0.4703	0.9024
0.0002	18.0	504	0.4685	0.9024
0.0001	19.0	532	0.4848	0.9024
0.0001	20.0	560	0.5034	0.9024
0.0001	21.0	588	0.5008	0.9024
0.0001	22.0	616	0.5129	0.9024
0.0001	23.0	644	0.5167	0.9024
0.0001	24.0	672	0.5213	0.9024
0.0001	25.0	700	0.5209	0.9024
0.0001	26.0	728	0.5340	0.9024
0.0001	27.0	756	0.5439	0.9024
0.0	28.0	784	0.5491	0.9024
0.0	29.0	812	0.5502	0.9024
0.0	30.0	840	0.5577	0.9024
0.0	31.0	868	0.5662	0.9024
0.0	32.0	896	0.5801	0.9024
0.0	33.0	924	0.5760	0.9024
0.0	34.0	952	0.5820	0.9024
0.0	35.0	980	0.5825	0.9024
0.0	36.0	1008	0.5963	0.9024
0.0	37.0	1036	0.6052	0.9024
0.0	38.0	1064	0.6015	0.9024
0.0	39.0	1092	0.6109	0.9024
0.0	40.0	1120	0.6162	0.9024
0.0	41.0	1148	0.6213	0.9024
0.0	42.0	1176	0.6284	0.9024
0.0	43.0	1204	0.6259	0.9024
0.0	44.0	1232	0.6257	0.9024
0.0	45.0	1260	0.6306	0.9024
0.0	46.0	1288	0.6336	0.9024
0.0	47.0	1316	0.6353	0.9024
0.0	48.0	1344	0.6351	0.9024
0.0	49.0	1372	0.6351	0.9024
0.0	50.0	1400	0.6351	0.9024

Framework versions

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