bert-finetuned-ner – AI Model by lightsaber689 | AlphaNeural AI

You can deploy this model and start earning money today!

lightsaber689/
bert-finetuned-ner

like

0

token-classification

generated_from_trainer

google-bert/bert-base-cased

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-finetuned-ner

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

Loss: 0.3512
Precision: 0.4356
Recall: 0.5329
F1: 0.4794
Accuracy: 0.8958

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
0.1944	1.0	125	0.2182	0.2998	0.3663	0.3298	0.8950
0.2215	2.0	250	0.2129	0.3364	0.3749	0.3546	0.8991
0.1778	3.0	375	0.2122	0.4122	0.4815	0.4442	0.9014
0.1648	4.0	500	0.2339	0.4270	0.5957	0.4975	0.8960
0.141	5.0	625	0.2507	0.4312	0.5494	0.4832	0.8993
0.1038	6.0	750	0.2677	0.4248	0.5273	0.4705	0.8983
0.1103	7.0	875	0.3052	0.4229	0.5643	0.4835	0.8947
0.0505	8.0	1000	0.3258	0.4301	0.5704	0.4904	0.8938
0.0523	9.0	1125	0.3457	0.4357	0.5078	0.4690	0.8961
0.0756	10.0	1250	0.3512	0.4356	0.5329	0.4794	0.8958

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0