FER-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: 0.4710
• Accuracy: 0.8474

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 OptimizerNames.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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8868	0.8959	100	1.7638	0.5923
1.2277	1.7962	200	1.1092	0.7253
0.8414	2.6965	300	0.8105	0.8041
0.7076	3.5969	400	0.6746	0.8256
0.6079	4.4972	500	0.6111	0.8287
0.5624	5.3975	600	0.5529	0.8379
0.5254	6.2979	700	0.5266	0.8399
0.4784	7.1982	800	0.4978	0.8433
0.4634	8.0985	900	0.4844	0.8458
0.4305	8.9944	1000	0.4710	0.8474
0.3995	9.8947	1100	0.4381	0.8564

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3