Emotion_Classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3727
• Accuracy: 0.55

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: 2
• total_train_batch_size: 64
• 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
2.083	1.0	10	2.0798	0.1625
2.0591	2.0	20	2.0464	0.2812
2.0043	3.0	30	1.9889	0.325
1.9174	4.0	40	1.9087	0.3375
1.819	5.0	50	1.8037	0.3875
1.7161	6.0	60	1.6875	0.4125
1.6253	7.0	70	1.6207	0.4437
1.549	8.0	80	1.5978	0.4437
1.4946	9.0	90	1.5430	0.4688
1.4426	10.0	100	1.4995	0.5125
1.4061	11.0	110	1.4919	0.4938
1.3648	12.0	120	1.4628	0.525
1.3306	13.0	130	1.4207	0.5437
1.3071	14.0	140	1.4340	0.5188
1.2791	15.0	150	1.4126	0.5188
1.2589	16.0	160	1.4119	0.5375
1.2199	17.0	170	1.4168	0.4938
1.2189	18.0	180	1.3957	0.525
1.2096	19.0	190	1.4015	0.5625
1.2114	20.0	200	1.3932	0.5188

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Tokenizers 0.20.3