metadata

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

bert-base-multilingual-uncased-finetuned-ner-geocorpus

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

Loss: 0.1337
Precision: 0.7867
Recall: 0.8827
F1: 0.8320
Accuracy: 0.9727

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	276	0.1785	0.6910	0.6597	0.6750	0.9527
0.2507	2.0	552	0.1321	0.7761	0.7689	0.7725	0.9630
0.2507	3.0	828	0.1158	0.7691	0.8165	0.7921	0.9669
0.084	4.0	1104	0.1186	0.7503	0.8479	0.7961	0.9668
0.084	5.0	1380	0.1287	0.7629	0.8560	0.8068	0.9657
0.0443	6.0	1656	0.1295	0.7453	0.8769	0.8058	0.9666
0.0443	7.0	1932	0.1423	0.7592	0.8862	0.8178	0.9685
0.0243	8.0	2208	0.1267	0.7970	0.8664	0.8303	0.9724
0.0243	9.0	2484	0.1309	0.7747	0.8746	0.8216	0.9710
0.0164	10.0	2760	0.1337	0.7867	0.8827	0.8320	0.9727

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1