|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- indolem_sentiment |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base |
|
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: 0.9147869674185464 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8629032258064516 |
|
--- |
|
|
|
<!-- 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-xlm-roberta-base |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the indolem_sentiment dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5769 |
|
- Accuracy: 0.9148 |
|
- F1: 0.8629 |
|
|
|
## 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 | 0.4983 | 0.7068 | 0.0 | |
|
| No log | 0.88 | 400 | 0.4663 | 0.7995 | 0.7059 | |
|
| 0.5119 | 1.32 | 600 | 0.4746 | 0.8722 | 0.7792 | |
|
| 0.5119 | 1.76 | 800 | 0.4463 | 0.8797 | 0.7949 | |
|
| 0.3523 | 2.2 | 1000 | 0.5374 | 0.8772 | 0.7984 | |
|
| 0.3523 | 2.64 | 1200 | 0.4591 | 0.8897 | 0.8087 | |
|
| 0.3523 | 3.08 | 1400 | 0.4909 | 0.8872 | 0.8148 | |
|
| 0.2978 | 3.52 | 1600 | 0.5236 | 0.8872 | 0.8263 | |
|
| 0.2978 | 3.96 | 1800 | 0.4410 | 0.9148 | 0.8559 | |
|
| 0.2623 | 4.4 | 2000 | 0.4655 | 0.8997 | 0.8347 | |
|
| 0.2623 | 4.84 | 2200 | 0.6111 | 0.8772 | 0.8231 | |
|
| 0.2623 | 5.27 | 2400 | 0.4194 | 0.9198 | 0.8667 | |
|
| 0.1863 | 5.71 | 2600 | 0.5278 | 0.8972 | 0.8392 | |
|
| 0.1863 | 6.15 | 2800 | 0.4805 | 0.9173 | 0.8559 | |
|
| 0.1332 | 6.59 | 3000 | 0.5610 | 0.9098 | 0.8548 | |
|
| 0.1332 | 7.03 | 3200 | 0.4435 | 0.9248 | 0.875 | |
|
| 0.1332 | 7.47 | 3400 | 0.5367 | 0.9148 | 0.8651 | |
|
| 0.1143 | 7.91 | 3600 | 0.5159 | 0.9148 | 0.8618 | |
|
| 0.1143 | 8.35 | 3800 | 0.5945 | 0.9098 | 0.8487 | |
|
| 0.0836 | 8.79 | 4000 | 0.7401 | 0.8947 | 0.8421 | |
|
| 0.0836 | 9.23 | 4200 | 0.5591 | 0.9148 | 0.8618 | |
|
| 0.0836 | 9.67 | 4400 | 0.6025 | 0.9123 | 0.8511 | |
|
| 0.0899 | 10.11 | 4600 | 0.5769 | 0.9148 | 0.8629 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|