|
--- |
|
license: mit |
|
base_model: indolem/indobert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- indolem_sentiment |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scenario-normal-finetune-clf-data-indolem_sentiment-model-indolem-indobert-base-uncased |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: indolem_sentiment |
|
type: indolem_sentiment |
|
config: indolem_sentiment_nusantara_text |
|
split: validation |
|
args: indolem_sentiment_nusantara_text |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8922305764411027 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8154506437768241 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# scenario-normal-finetune-clf-data-indolem_sentiment-model-indolem-indobert-base-uncased |
|
|
|
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co./indolem/indobert-base-uncased) on the indolem_sentiment dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7311 |
|
- Accuracy: 0.8922 |
|
- F1: 0.8155 |
|
|
|
## 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: 5e-06 |
|
- 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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.44 | 200 | 0.5133 | 0.7544 | 0.3718 | |
|
| No log | 0.88 | 400 | 0.4239 | 0.7995 | 0.6875 | |
|
| 0.4818 | 1.32 | 600 | 0.3889 | 0.8647 | 0.7523 | |
|
| 0.4818 | 1.76 | 800 | 0.3263 | 0.8872 | 0.8069 | |
|
| 0.291 | 2.2 | 1000 | 0.3933 | 0.8847 | 0.8067 | |
|
| 0.291 | 2.64 | 1200 | 0.4703 | 0.8847 | 0.7982 | |
|
| 0.291 | 3.08 | 1400 | 0.5284 | 0.8622 | 0.7843 | |
|
| 0.2432 | 3.52 | 1600 | 0.4924 | 0.8897 | 0.8136 | |
|
| 0.2432 | 3.96 | 1800 | 0.4952 | 0.9023 | 0.8219 | |
|
| 0.1982 | 4.4 | 2000 | 0.5157 | 0.9098 | 0.8421 | |
|
| 0.1982 | 4.84 | 2200 | 0.6454 | 0.8847 | 0.8099 | |
|
| 0.1982 | 5.27 | 2400 | 0.5636 | 0.9048 | 0.8348 | |
|
| 0.1441 | 5.71 | 2600 | 0.6147 | 0.8872 | 0.8193 | |
|
| 0.1441 | 6.15 | 2800 | 0.6280 | 0.8997 | 0.8198 | |
|
| 0.1147 | 6.59 | 3000 | 0.6505 | 0.8947 | 0.8205 | |
|
| 0.1147 | 7.03 | 3200 | 0.6547 | 0.8972 | 0.8285 | |
|
| 0.1147 | 7.47 | 3400 | 0.7311 | 0.8922 | 0.8155 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|