bert-finetuned-ner

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

• Loss: 0.1149
• Precision: 0.5729
• Recall: 0.5787
• F1: 0.5758
• Accuracy: 0.9806

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	5	0.2606	0.0	0.0	0.0	0.9360
No log	2.0	10	0.1431	0.3116	0.3147	0.3131	0.9685
No log	3.0	15	0.1149	0.5729	0.5787	0.5758	0.9806

Framework versions

• Transformers 4.50.1
• Pytorch 2.6.0+cpu
• Datasets 3.4.1
• Tokenizers 0.21.1