Edit model card

emotion_classification

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

  • Loss: 1.4050
  • Accuracy: 0.4688

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.8187 1.0 10 1.8406 0.3063
1.6795 2.0 20 1.6701 0.3688
1.5506 3.0 30 1.5578 0.45
1.4417 4.0 40 1.5077 0.4875
1.3707 5.0 50 1.4297 0.5062
1.3167 6.0 60 1.4157 0.4938
1.267 7.0 70 1.3779 0.525
1.2197 8.0 80 1.3784 0.5
1.191 9.0 90 1.3701 0.5188
1.1649 10.0 100 1.3611 0.4938

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
14

Finetuned from

Evaluation results