metadata

library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-base-uncased-finetuned-ner
    results: []

bert-base-uncased-finetuned-ner

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: 0.3910
Precision: 0.9616
Recall: 0.9637
F1: 0.9627
Accuracy: 0.9560

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: 1e-05
train_batch_size: 6
eval_batch_size: 6
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3052	1.0	3334	0.2630	0.9365	0.9367	0.9366	0.9228
0.2104	2.0	6668	0.2481	0.9418	0.9537	0.9477	0.9400
0.163	3.0	10002	0.2390	0.9495	0.9606	0.9550	0.9479
0.1151	4.0	13336	0.2516	0.9549	0.9616	0.9583	0.9515
0.0809	5.0	16670	0.2887	0.9590	0.9556	0.9573	0.9493
0.0625	6.0	20004	0.2912	0.9573	0.9611	0.9592	0.9520
0.0516	7.0	23338	0.3139	0.9581	0.9563	0.9572	0.9501
0.0388	8.0	26672	0.3070	0.9605	0.9600	0.9602	0.9531
0.0273	9.0	30006	0.3344	0.9607	0.9617	0.9612	0.9535
0.0252	10.0	33340	0.3547	0.9608	0.9638	0.9623	0.9554
0.0242	11.0	36674	0.3726	0.9600	0.9619	0.9610	0.9541
0.0119	12.0	40008	0.3727	0.9602	0.9623	0.9612	0.9546
0.0078	13.0	43342	0.3772	0.9617	0.9639	0.9628	0.9562
0.0078	14.0	46676	0.3904	0.9615	0.9638	0.9627	0.9560
0.0026	15.0	50010	0.3910	0.9616	0.9637	0.9627	0.9560

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1