Edit model card

Akhil123/emotions_classifier

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:

  • Train Loss: 2.0827
  • Validation Loss: 2.0793
  • Train Accuracy: 0.1437
  • Epoch: 19

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 12800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
1.9720 1.6874 0.225 0
2.0874 2.0802 0.125 1
2.0744 2.0407 0.2313 2
2.0540 2.0760 0.1688 3
2.1039 2.0796 0.1125 4
2.0813 2.0794 0.1187 5
2.0802 2.0797 0.1187 6
2.0793 2.0790 0.125 7
2.0657 2.0128 0.2 8
2.0724 2.0920 0.125 9
2.0896 2.0744 0.1187 10
2.0844 2.0824 0.1187 11
2.0819 2.0755 0.125 12
2.0614 2.0392 0.1562 13
2.0676 2.0812 0.1187 14
2.0810 2.0792 0.1187 15
2.0826 2.0813 0.1187 16
2.0788 2.0770 0.15 17
2.0797 2.0733 0.125 18
2.0827 2.0793 0.1437 19

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.14.4
  • Tokenizers 0.13.3
Downloads last month
1

Finetuned from