NER-ExtractTotal

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1108
• Precision: 0.8496
• Recall: 0.9132
• F1: 0.8802
• Accuracy: 0.9735

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:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	18	0.4964	0.0351	0.0329	0.0340	0.8212
No log	2.0	36	0.3155	0.1957	0.2425	0.2166	0.8686
No log	3.0	54	0.2135	0.5064	0.5898	0.5450	0.9184
No log	4.0	72	0.1629	0.6288	0.7964	0.7028	0.9364
No log	5.0	90	0.1106	0.7813	0.8024	0.7917	0.9647
No log	6.0	108	0.1117	0.8038	0.8832	0.8417	0.9671
No log	7.0	126	0.1023	0.8270	0.9162	0.8693	0.9707
No log	8.0	144	0.1080	0.8370	0.9072	0.8707	0.9703
No log	9.0	162	0.0961	0.8455	0.9012	0.8725	0.9728
No log	10.0	180	0.0902	0.8504	0.9192	0.8835	0.9753
No log	11.0	198	0.1092	0.8407	0.9162	0.8768	0.9721
No log	12.0	216	0.0871	0.8571	0.9162	0.8857	0.9760
No log	13.0	234	0.1081	0.8515	0.9102	0.8799	0.9739
No log	14.0	252	0.1142	0.8547	0.9162	0.8844	0.9742
No log	15.0	270	0.1079	0.8520	0.9132	0.8815	0.9739
No log	16.0	288	0.1065	0.8511	0.9072	0.8783	0.9739
No log	17.0	306	0.1097	0.8515	0.9102	0.8799	0.9742
No log	18.0	324	0.1098	0.8492	0.9102	0.8786	0.9739
No log	19.0	342	0.1109	0.8496	0.9132	0.8802	0.9735
No log	20.0	360	0.1108	0.8496	0.9132	0.8802	0.9735

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.12.0
• Tokenizers 0.15.1