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

Loss: 0.3402
Accuracy: 0.855

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
1.0561	1.0	75	1.0620	0.43
0.937	2.0	150	0.9594	0.51
0.8543	3.0	225	0.8655	0.62
0.8165	4.0	300	0.7890	0.6667
0.7134	5.0	375	0.7178	0.7017
0.7528	6.0	450	0.6594	0.715
0.6452	7.0	525	0.6058	0.75
0.597	8.0	600	0.5655	0.7717
0.5415	9.0	675	0.5324	0.7867
0.5088	10.0	750	0.5114	0.8117
0.5609	11.0	825	0.4871	0.8067
0.4661	12.0	900	0.4691	0.8117
0.4495	13.0	975	0.4552	0.8217
0.4956	14.0	1050	0.4435	0.8217
0.4383	15.0	1125	0.4330	0.83
0.3764	16.0	1200	0.4243	0.8317
0.4263	17.0	1275	0.4146	0.83
0.39	18.0	1350	0.4087	0.83
0.4056	19.0	1425	0.4021	0.8367
0.4427	20.0	1500	0.3960	0.835
0.3559	21.0	1575	0.3906	0.84
0.3313	22.0	1650	0.3861	0.8383
0.3291	23.0	1725	0.3822	0.8383
0.3377	24.0	1800	0.3784	0.8383
0.3287	25.0	1875	0.3755	0.8433
0.3695	26.0	1950	0.3722	0.8467
0.3651	27.0	2025	0.3680	0.845
0.3421	28.0	2100	0.3650	0.845
0.3095	29.0	2175	0.3617	0.85
0.3232	30.0	2250	0.3592	0.8467
0.2955	31.0	2325	0.3570	0.8467
0.273	32.0	2400	0.3554	0.8483
0.3566	33.0	2475	0.3529	0.8467
0.3239	34.0	2550	0.3508	0.85
0.3231	35.0	2625	0.3501	0.8517
0.2755	36.0	2700	0.3491	0.8517
0.2727	37.0	2775	0.3485	0.8433
0.2931	38.0	2850	0.3470	0.845
0.2624	39.0	2925	0.3453	0.85
0.3211	40.0	3000	0.3440	0.855
0.2988	41.0	3075	0.3437	0.855
0.3248	42.0	3150	0.3424	0.855
0.3151	43.0	3225	0.3419	0.855
0.3064	44.0	3300	0.3415	0.8533
0.2827	45.0	3375	0.3410	0.8533
0.2824	46.0	3450	0.3410	0.8517
0.2636	47.0	3525	0.3406	0.8567
0.275	48.0	3600	0.3403	0.8567
0.2811	49.0	3675	0.3402	0.8567
0.2711	50.0	3750	0.3402	0.855

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/smids_1x_deit_tiny_sgd_001_fold5

smids_1x_deit_tiny_sgd_001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_1x_deit_tiny_sgd_001_fold5