metadata

library_name: transformers
license: apache-2.0
base_model: Geotrend/bert-base-th-cased
tags:
  - generated_from_trainer
datasets:
  - lst20
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: test-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: lst20
          type: lst20
          config: lst20
          split: validation
          args: lst20
        metrics:
          - name: Precision
            type: precision
            value: 0.8146895294348094
          - name: Recall
            type: recall
            value: 0.8409048492954679
          - name: F1
            type: f1
            value: 0.8275896376229288
          - name: Accuracy
            type: accuracy
            value: 0.9378905377283859

test-ner

This model is a fine-tuned version of Geotrend/bert-base-th-cased on the lst20 dataset. It achieves the following results on the evaluation set:

Loss: 0.1910
Precision: 0.8147
Recall: 0.8409
F1: 0.8276
Accuracy: 0.9379

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1623	1.0	3957	0.1910	0.8147	0.8409	0.8276	0.9379

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1