silviacamplani/distilbert-finetuned-ner-music

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

• Train Loss: 0.6767
• Validation Loss: 0.7802
• Train Precision: 0.5256
• Train Recall: 0.5824
• Train F1: 0.5525
• Train Accuracy: 0.8017
• 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 370, '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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
2.6671	2.0032	0.0	0.0	0.0	0.5482	0
1.7401	1.5194	0.1820	0.0693	0.1004	0.5902	1
1.3487	1.2627	0.2628	0.2952	0.2781	0.6766	2
1.1390	1.0990	0.4018	0.4527	0.4257	0.7181	3
0.9823	0.9837	0.4575	0.4887	0.4726	0.7311	4
0.8741	0.9022	0.5008	0.5338	0.5168	0.7544	5
0.7904	0.8449	0.5085	0.5626	0.5342	0.7776	6
0.7327	0.8097	0.5211	0.5779	0.5480	0.7917	7
0.7000	0.7872	0.5281	0.5842	0.5547	0.7975	8
0.6767	0.7802	0.5256	0.5824	0.5525	0.8017	9

Framework versions

• Transformers 4.20.1
• TensorFlow 2.6.4
• Datasets 2.1.0
• Tokenizers 0.12.1