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: 0.1640
Accuracy: 0.955

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	50	0.4043	0.9
No log	2.0	100	0.3688	0.9
No log	3.0	150	0.4178	0.8825
No log	4.0	200	0.2808	0.9213
No log	5.0	250	0.2260	0.9387
No log	6.0	300	0.2191	0.9375
No log	7.0	350	0.2247	0.9363
No log	8.0	400	0.1965	0.9413
No log	9.0	450	0.1976	0.9463
0.216	10.0	500	0.1736	0.9587

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1

fitrahar/vit-emotions-fp16

vit-emotions-fp16

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

fitrahar/
vit-emotions-fp16