metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
datasets:
- id_nergrit_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: indobert-model-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: id_nergrit_corpus
type: id_nergrit_corpus
config: ner
split: test
args: ner
metrics:
- name: Precision
type: precision
value: 0.8159014069146036
- name: Recall
type: recall
value: 0.8415073115860517
- name: F1
type: f1
value: 0.8285065618251288
- name: Accuracy
type: accuracy
value: 0.9514472889467082
indobert-model-ner
This model is a fine-tuned version of indolem/indobert-base-uncased on the id_nergrit_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1728
- Precision: 0.8159
- Recall: 0.8415
- F1: 0.8285
- Accuracy: 0.9514
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4948 | 1.0 | 784 | 0.1790 | 0.7868 | 0.8300 | 0.8078 | 0.9461 |
| 0.1576 | 2.0 | 1568 | 0.1663 | 0.8151 | 0.8283 | 0.8216 | 0.9512 |
| 0.1237 | 3.0 | 2352 | 0.1728 | 0.8159 | 0.8415 | 0.8285 | 0.9514 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3