hushem_1x_deit_base_sgd_001_fold3

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: 1.3334
• Accuracy: 0.4186

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	1.3830	0.3721
1.4361	2.0	12	1.3798	0.3256
1.4361	3.0	18	1.3766	0.3256
1.4161	4.0	24	1.3738	0.3023
1.4308	5.0	30	1.3713	0.3256
1.4308	6.0	36	1.3692	0.3488
1.4008	7.0	42	1.3671	0.3721
1.4008	8.0	48	1.3650	0.3721
1.3927	9.0	54	1.3634	0.3721
1.37	10.0	60	1.3616	0.3721
1.37	11.0	66	1.3601	0.3953
1.3698	12.0	72	1.3586	0.3953
1.3698	13.0	78	1.3569	0.4419
1.3588	14.0	84	1.3553	0.4186
1.3582	15.0	90	1.3538	0.4186
1.3582	16.0	96	1.3522	0.4186
1.3505	17.0	102	1.3510	0.4186
1.3505	18.0	108	1.3496	0.4186
1.3337	19.0	114	1.3483	0.4186
1.3364	20.0	120	1.3470	0.4186
1.3364	21.0	126	1.3459	0.4186
1.3337	22.0	132	1.3449	0.4186
1.3337	23.0	138	1.3437	0.4186
1.3242	24.0	144	1.3426	0.3953
1.3247	25.0	150	1.3416	0.3953
1.3247	26.0	156	1.3407	0.3953
1.314	27.0	162	1.3398	0.3953
1.314	28.0	168	1.3390	0.3953
1.3132	29.0	174	1.3382	0.3953
1.3139	30.0	180	1.3375	0.3953
1.3139	31.0	186	1.3369	0.4186
1.3104	32.0	192	1.3363	0.3953
1.3104	33.0	198	1.3357	0.3953
1.3084	34.0	204	1.3352	0.3953
1.3046	35.0	210	1.3348	0.4186
1.3046	36.0	216	1.3345	0.4186
1.3016	37.0	222	1.3341	0.4186
1.3016	38.0	228	1.3339	0.4186
1.3084	39.0	234	1.3337	0.4186
1.3045	40.0	240	1.3335	0.4186
1.3045	41.0	246	1.3335	0.4186
1.2931	42.0	252	1.3334	0.4186
1.2931	43.0	258	1.3334	0.4186
1.3105	44.0	264	1.3334	0.4186
1.2967	45.0	270	1.3334	0.4186
1.2967	46.0	276	1.3334	0.4186
1.3024	47.0	282	1.3334	0.4186
1.3024	48.0	288	1.3334	0.4186
1.3038	49.0	294	1.3334	0.4186
1.3026	50.0	300	1.3334	0.4186

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.14.7
• Tokenizers 0.15.0