bert-finetuned-ner-requirements

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

• Loss: 1.1038
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.9273

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	1	2.4289	0.0	0.0	0.0	0.2773
No log	2.0	2	2.1745	0.0	0.0	0.0	0.6951
No log	3.0	3	1.9429	0.0	0.0	0.0	0.8729
No log	4.0	4	1.7345	0.0	0.0	0.0	0.9222
No log	5.0	5	1.5522	0.0	0.0	0.0	0.9273
No log	6.0	6	1.4000	0.0	0.0	0.0	0.9273
No log	7.0	7	1.2789	0.0	0.0	0.0	0.9273
No log	8.0	8	1.1898	0.0	0.0	0.0	0.9273
No log	9.0	9	1.1320	0.0	0.0	0.0	0.9273
No log	10.0	10	1.1038	0.0	0.0	0.0	0.9273

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1