vit-Facial-Expression-Recognition

This model is a fine-tuned version of motheecreator/vit-Facial-Expression-Recognition on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5369
• Accuracy: 0.8095

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8526	0.2077	100	0.6490	0.7761
0.8116	0.4155	200	0.6106	0.7860
0.7759	0.6232	300	0.5918	0.7908
0.7708	0.8310	400	0.5883	0.7904
0.75	1.0374	500	0.5749	0.7971
0.7496	1.2451	600	0.5737	0.7976
0.7601	1.4529	700	0.5698	0.7971
0.7516	1.6606	800	0.5692	0.7991
0.7359	1.8683	900	0.5740	0.7947
0.6968	2.0748	1000	0.5738	0.7953
0.6854	2.2825	1100	0.5617	0.7980
0.6992	2.4903	1200	0.5566	0.8030
0.6609	2.6980	1300	0.5495	0.8035
0.664	2.9057	1400	0.5370	0.8101

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0