silviacamplani/distilbert-finetuned-dapt-ner-music

This model is a fine-tuned version of silviacamplani/distilbert-finetuned-dapt-lm-ai on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.7656
• Validation Loss: 0.8288
• Train Precision: 0.5590
• Train Recall: 0.5968
• Train F1: 0.5773
• Train Accuracy: 0.7761
• Epoch: 6

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
2.5668	1.9780	0.0	0.0	0.0	0.5482	0
1.7189	1.4888	0.1152	0.0396	0.0589	0.5905	1
1.3060	1.2236	0.3797	0.3564	0.3677	0.6839	2
1.0982	1.0637	0.4716	0.4635	0.4675	0.7155	3
0.9450	0.9504	0.5176	0.5167	0.5171	0.7385	4
0.8398	0.8775	0.5474	0.5671	0.5570	0.7579	5
0.7656	0.8288	0.5590	0.5968	0.5773	0.7761	6

Framework versions

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