metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - lg-ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: luganda-ner-v1
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: lg-ner
          type: lg-ner
          config: lug
          split: train
          args: lug
        metrics:
          - name: Precision
            type: precision
            value: 0.29015544041450775
          - name: Recall
            type: recall
            value: 0.27722772277227725
          - name: F1
            type: f1
            value: 0.2835443037974684
          - name: Accuracy
            type: accuracy
            value: 0.7297843665768194

luganda-ner-v1

This model is a fine-tuned version of xlm-roberta-base on the lg-ner dataset. It achieves the following results on the evaluation set:

Loss: 1.0530
Precision: 0.2902
Recall: 0.2772
F1: 0.2835
Accuracy: 0.7298

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
No log	1.0	25	1.2878	0.0	0.0	0.0	0.7271
No log	2.0	50	1.2373	0.0	0.0	0.0	0.7271
No log	3.0	75	1.2309	0.3542	0.1683	0.2282	0.7244
No log	4.0	100	1.1505	0.2712	0.2376	0.2533	0.7183
No log	5.0	125	1.1360	0.2579	0.2426	0.25	0.7170
No log	6.0	150	1.0932	0.3108	0.2277	0.2629	0.7338
No log	7.0	175	1.0761	0.2989	0.2574	0.2766	0.7298
No log	8.0	200	1.0645	0.2805	0.3069	0.2931	0.7244
No log	9.0	225	1.0577	0.3022	0.2723	0.2865	0.7325
No log	10.0	250	1.0530	0.2902	0.2772	0.2835	0.7298

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.7.1
Tokenizers 0.13.2