bert-finetuned-ner-a1-a2-a3-a4-10k-e3-v1 – AI Model by divya1111 | AlphaNeural AI

You can deploy this model and start earning money today!

divya1111/
bert-finetuned-ner-a1-a2-a3-a4-10k-e3-v1

like

0

token-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-finetuned-ner-a1-a2-a3-a4-10k-e3-v1

This model is a fine-tuned version of dslim/bert-large-NER on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0073
Precision: 0.8338
Recall: 0.9522
F1: 0.8891
Accuracy: 0.9977

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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0086	1.0	1125	0.0082	0.8221	0.9164	0.8667	0.9971
0.0053	2.0	2250	0.0070	0.8357	0.9296	0.8801	0.9974
0.0039	3.0	3375	0.0070	0.8308	0.9319	0.8785	0.9973
0.0033	4.0	4500	0.0065	0.8324	0.9463	0.8857	0.9977
0.0023	5.0	5625	0.0070	0.8345	0.9514	0.8891	0.9977
0.002	6.0	6750	0.0073	0.8338	0.9522	0.8891	0.9977

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3