JuvManga-87/mobilebert-uncased-finetuned-ner

This model is a fine-tuned version of google/mobilebert-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2691
• Validation Loss: 0.2428
• Train Precision: 0.6071
• Train Recall: 0.0424
• Train F1: 0.0793
• Train Accuracy: 0.9240
• Epoch: 11

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': 2e-05, 'decay_steps': 264, '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 Precision	Train Recall	Train F1	Train Accuracy	Epoch
1.2686	0.5142	0.0187	0.0125	0.0149	0.8729	0
0.4703	0.4127	0.02	0.0050	0.0080	0.9031	1
0.4033	0.3659	0.0588	0.0050	0.0092	0.9156	2
0.3657	0.3351	0.1429	0.0050	0.0096	0.9195	3
0.3434	0.3111	0.2143	0.0075	0.0145	0.9199	4
0.3223	0.2917	0.2667	0.0100	0.0192	0.9203	5
0.3035	0.2764	0.3125	0.0125	0.0240	0.9209	6
0.2916	0.2642	0.5294	0.0224	0.0431	0.9224	7
0.2780	0.2551	0.4762	0.0249	0.0474	0.9226	8
0.2755	0.2484	0.56	0.0349	0.0657	0.9234	9
0.2718	0.2442	0.6071	0.0424	0.0793	0.9240	10
0.2691	0.2428	0.6071	0.0424	0.0793	0.9240	11

Framework versions

• Transformers 4.42.4
• TensorFlow 2.17.0
• Datasets 2.21.0
• Tokenizers 0.19.1