metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: indobert_emotion_base_id
results: []
indobert_emotion_base_id
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9735
- Accuracy: 0.7535
- F1: 0.7590
- Recall: 0.7578
- Precision: 0.7608
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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
---|---|---|---|---|---|---|---|
0.4174 | 1.0 | 177 | 0.9081 | 0.7345 | 0.7402 | 0.7565 | 0.7312 |
0.3977 | 2.0 | 354 | 0.8161 | 0.7627 | 0.7690 | 0.7746 | 0.7654 |
0.2415 | 3.0 | 531 | 0.9306 | 0.7436 | 0.7509 | 0.7565 | 0.7481 |
0.1424 | 4.0 | 708 | 0.9735 | 0.7535 | 0.7590 | 0.7578 | 0.7608 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1