nikoslefkos/conll03_model

This model is a fine-tuned version of distilbert-base-cased on conll03 dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0028
• Validation Loss: 0.0797
• Train Precision: 0.9178
• Train Recall: 0.9409
• Train F1: 0.9292
• Train Accuracy: 0.9840
• 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 4380, '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 Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.2257	0.0909	0.8675	0.9037	0.8853	0.9733	0
0.0638	0.0670	0.9003	0.9266	0.9133	0.9808	1
0.0356	0.0668	0.9070	0.9335	0.9201	0.9818	2
0.0223	0.0660	0.9137	0.9334	0.9234	0.9828	3
0.0152	0.0750	0.9007	0.9317	0.9159	0.9805	4
0.0101	0.0736	0.9104	0.9371	0.9235	0.9828	5
0.0067	0.0740	0.9203	0.9391	0.9296	0.9838	6
0.0046	0.0767	0.9133	0.9379	0.9254	0.9832	7
0.0034	0.0806	0.9160	0.9399	0.9278	0.9837	8
0.0028	0.0797	0.9178	0.9409	0.9292	0.9840	9

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3