B4Z00/pokemons_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: 0.4438
• Validation Loss: 5.8186
• Train Accuracy: 0.0451
• Epoch: 5

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
4.5854	5.2434	0.0191	0
3.4375	5.2942	0.0191	1
2.3515	5.3596	0.0246	2
1.4229	5.5273	0.0383	3
0.7900	5.6574	0.0464	4
0.4438	5.8186	0.0451	5

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.15.0
• Tokenizers 0.15.0