metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment_model_3
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
config: smsa
split: validation
args: smsa
metrics:
- name: Accuracy
type: accuracy
value: 0.9468253968253968
- name: Precision
type: precision
value: 0.9299064000831855
- name: Recall
type: recall
value: 0.9226916056718601
- name: F1
type: f1
value: 0.9257234652270979
sentiment_model_3
This model is a fine-tuned version of indolem/indobertweet-base-uncased on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.2301
- Accuracy: 0.9468
- Precision: 0.9299
- Recall: 0.9227
- F1: 0.9257
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 | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.2455 | 1.0 | 688 | 0.1740 | 0.9476 | 0.9138 | 0.9366 | 0.9246 |
0.1266 | 2.0 | 1376 | 0.1898 | 0.9516 | 0.9388 | 0.9284 | 0.9332 |
0.0717 | 3.0 | 2064 | 0.2301 | 0.9468 | 0.9299 | 0.9227 | 0.9257 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3