deit-tiny-distilled-patch16-224emotion_model_4feats_deit

This model is a fine-tuned version of facebook/deit-tiny-distilled-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8054
• Accuracy: 0.8812
• Weighted f1: 0.8812
• Micro f1: 0.8812
• Macro f1: 0.8812
• Weighted recall: 0.8812
• Micro recall: 0.8812
• Macro recall: 0.8812

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: 64
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Weighted f1	Micro f1	Macro f1	Weighted recall	Micro recall	Macro recall
0.9336	1.0	501	0.7411	0.7165	0.7178	0.7165	0.7178	0.7165	0.7165	0.7165
0.6285	2.0	1002	0.6362	0.7538	0.7549	0.7538	0.7549	0.7538	0.7538	0.7538
0.4148	3.0	1503	0.5584	0.8063	0.8058	0.8063	0.8058	0.8063	0.8063	0.8063
0.2404	4.0	2004	0.5191	0.8442	0.8435	0.8442	0.8435	0.8442	0.8442	0.8442
0.1227	5.0	2505	0.5064	0.8665	0.8664	0.8665	0.8664	0.8665	0.8665	0.8665
0.0594	6.0	3006	0.6042	0.8652	0.8644	0.8652	0.8644	0.8652	0.8652	0.8652
0.029	7.0	3507	0.6712	0.8772	0.8771	0.8772	0.8771	0.8772	0.8772	0.8773
0.0116	8.0	4008	0.7661	0.876	0.8756	0.876	0.8756	0.876	0.876	0.876
0.0054	9.0	4509	0.7958	0.881	0.8811	0.881	0.8811	0.881	0.881	0.881
0.0034	10.0	5010	0.8054	0.8812	0.8812	0.8812	0.8812	0.8812	0.8812	0.8812

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1