AlaaHussien/weather_classifier_model2

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: 0.0700
• Validation Loss: 0.2853
• Train Accuracy: 0.9250
• Train Precision: 0.9267
• Train Recall: 0.9250
• Train F1: 0.9248
• 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 109780, '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	Train Precision	Train Recall	Train F1	Epoch
1.2545	0.6449	0.8944	0.9010	0.8944	0.8907	0
0.5392	0.3960	0.9177	0.9191	0.9177	0.9181	1
0.3498	0.3183	0.9264	0.9271	0.9264	0.9263	2
0.2787	0.2797	0.9323	0.9331	0.9323	0.9323	3
0.2155	0.2695	0.9257	0.9279	0.9257	0.9260	4
0.1899	0.3079	0.9126	0.9165	0.9126	0.9121	5
0.1599	0.2749	0.9235	0.9259	0.9235	0.9241	6
0.1470	0.2709	0.9243	0.9257	0.9243	0.9237	7
0.1305	0.2566	0.9257	0.9263	0.9257	0.9259	8
0.1131	0.2699	0.9257	0.9271	0.9257	0.9260	9
0.1042	0.2719	0.9228	0.9240	0.9228	0.9229	10
0.0977	0.2857	0.9199	0.9208	0.9199	0.9197	11
0.0816	0.2592	0.9279	0.9294	0.9279	0.9281	12
0.0894	0.2888	0.9228	0.9256	0.9228	0.9226	13
0.1011	0.2978	0.9264	0.9287	0.9264	0.9264	14
0.0756	0.2590	0.9330	0.9344	0.9330	0.9330	15
0.0668	0.2863	0.9228	0.9255	0.9228	0.9235	16
0.0650	0.2871	0.9264	0.9282	0.9264	0.9262	17
0.0644	0.3003	0.9257	0.9279	0.9257	0.9261	18
0.0700	0.2853	0.9250	0.9267	0.9250	0.9248	19

Framework versions

• Transformers 4.51.3
• TensorFlow 2.18.0
• Datasets 3.6.0
• Tokenizers 0.21.1