jaffe_V2_50

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.7217
• Accuracy: 0.8

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	1.9638	0.2333
No log	2.0	2	1.7893	0.3333
No log	3.0	3	1.8759	0.1667
No log	4.0	4	1.6759	0.3667
No log	5.0	5	1.5139	0.5
No log	6.0	6	1.4280	0.5667
No log	7.0	7	1.3688	0.5667
No log	8.0	8	1.2819	0.6
No log	9.0	9	1.1884	0.6
1.5329	10.0	10	1.1448	0.6
1.5329	11.0	11	1.0732	0.7
1.5329	12.0	12	0.9793	0.7333
1.5329	13.0	13	0.8830	0.7333
1.5329	14.0	14	0.8366	0.7667
1.5329	15.0	15	0.8027	0.7333
1.5329	16.0	16	0.7952	0.7333
1.5329	17.0	17	0.7746	0.7333
1.5329	18.0	18	0.7571	0.7667
1.5329	19.0	19	0.7256	0.7667
0.5232	20.0	20	0.7217	0.8

Framework versions

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