This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.3694
Accuracy: 0.55

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: 4e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.9385	0.35
No log	2.0	80	1.6433	0.3875
No log	3.0	120	1.4689	0.5375
No log	4.0	160	1.3533	0.55
No log	5.0	200	1.3162	0.5813
No log	6.0	240	1.3131	0.5437
No log	7.0	280	1.2160	0.6
No log	8.0	320	1.2660	0.5437
No log	9.0	360	1.2594	0.55
No log	10.0	400	1.1873	0.5687
No log	11.0	440	1.1169	0.5875
No log	12.0	480	1.2015	0.5687
1.125	13.0	520	1.2653	0.5375
1.125	14.0	560	1.2801	0.5563
1.125	15.0	600	1.2304	0.5563
1.125	16.0	640	1.2341	0.5437
1.125	17.0	680	1.2981	0.5312
1.125	18.0	720	1.3277	0.5687
1.125	19.0	760	1.2174	0.5875
1.125	20.0	800	1.1810	0.6
1.125	21.0	840	1.2280	0.5687
1.125	22.0	880	1.3576	0.525
1.125	23.0	920	1.3897	0.5375
1.125	24.0	960	1.3216	0.5625
0.3612	25.0	1000	1.3033	0.6062
0.3612	26.0	1040	1.3501	0.5625
0.3612	27.0	1080	1.2310	0.575
0.3612	28.0	1120	1.2495	0.6062
0.3612	29.0	1160	1.2974	0.5875
0.3612	30.0	1200	1.2985	0.5813

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1

Marxulia/emotion_classification

emotion_classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Marxulia/
emotion_classification