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: 1.2449
Accuracy: 0.575
Precision: 0.6064
Recall: 0.575
F1: 0.5731

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: 5e-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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	40	1.8287	0.325	0.2995	0.325	0.2695
No log	2.0	80	1.5621	0.475	0.4171	0.475	0.4104
No log	3.0	120	1.4485	0.4188	0.3786	0.4188	0.3710
No log	4.0	160	1.4040	0.4313	0.5179	0.4313	0.3963
No log	5.0	200	1.3333	0.4938	0.5016	0.4938	0.4654
No log	6.0	240	1.3076	0.4688	0.4698	0.4688	0.4437
No log	7.0	280	1.3531	0.4813	0.5289	0.4813	0.4834
No log	8.0	320	1.3118	0.4688	0.4606	0.4688	0.4619
No log	9.0	360	1.3326	0.4938	0.5629	0.4938	0.4744
No log	10.0	400	1.2693	0.4938	0.4825	0.4938	0.4777
No log	11.0	440	1.2310	0.55	0.5747	0.55	0.5441
No log	12.0	480	1.2673	0.5375	0.5418	0.5375	0.5316
1.0804	13.0	520	1.3161	0.5125	0.5321	0.5125	0.5048
1.0804	14.0	560	1.2517	0.55	0.5550	0.55	0.5430
1.0804	15.0	600	1.3344	0.5	0.5023	0.5	0.4848

Framework versions

Transformers 4.41.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1

JamesJayamuni/emotion_classification_v1.1

emotion_classification_v1.1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

JamesJayamuni/
emotion_classification_v1.1