arieg/spec_cls_80_v2

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: 1.0698
• Validation Loss: 1.0517
• Train Accuracy: 1.0
• Epoch: 9

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', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 14400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
4.2243	4.0115	0.575	0
3.6964	3.4678	0.9125	1
3.1703	2.9932	0.9938	2
2.7155	2.5826	0.9938	3
2.3313	2.2229	1.0	4
2.0025	1.9208	1.0	5
1.7153	1.6639	1.0	6
1.4721	1.4462	1.0	7
1.2586	1.2279	1.0	8
1.0698	1.0517	1.0	9

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1