MoinKhan3012/custom_ner_bert-uncased

fine_tune_bert_masking

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

• Loss: 0.4384
• Overall Precision: 0.5833
• Overall Recall: 0.4691
• Overall F1: 0.52
• Overall Accuracy: 0.9323
• App F1: 0.52

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	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	App F1
0.2048	3.45	100	0.2554	0.5442	0.4124	0.4692	0.9210	0.4692
0.0658	6.9	200	0.3147	0.6119	0.4227	0.5	0.9314	0.5
0.0279	10.34	300	0.3509	0.5357	0.4639	0.4972	0.9281	0.4972
0.0146	13.79	400	0.4032	0.5759	0.4691	0.5170	0.9314	0.5170
0.0093	17.24	500	0.4384	0.5833	0.4691	0.52	0.9323	0.52

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.13.3