bert-finetuned-ner4invoice13

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

• Loss: 0.0188
• Precision: 0.9038
• Recall: 0.9592
• F1: 0.9307
• Accuracy: 0.9949

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	14	0.4838	0.0	0.0	0.0	0.8854
No log	2.0	28	0.2109	0.2167	0.2653	0.2385	0.9512
No log	3.0	42	0.1063	0.6349	0.8163	0.7143	0.9716
No log	4.0	56	0.0602	0.7818	0.8776	0.8269	0.9825
No log	5.0	70	0.0361	0.9231	0.9796	0.9505	0.9909
No log	6.0	84	0.0305	0.9231	0.9796	0.9505	0.9927
No log	7.0	98	0.0476	0.8545	0.9592	0.9038	0.9898
No log	8.0	112	0.0211	0.9038	0.9592	0.9307	0.9942
No log	9.0	126	0.0258	0.9057	0.9796	0.9412	0.9924
No log	10.0	140	0.0188	0.9038	0.9592	0.9307	0.9949

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1