metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sa-tapera
results: []
sa-tapera
This model is a fine-tuned version of indolem/indobertweet-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5534
- Accuracy: 0.8973
- Precision: 0.9031
- Recall: 0.8973
- F1: 0.8997
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: 0.0001
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5638 | 1.0 | 107 | 0.4124 | 0.8527 | 0.8624 | 0.8429 | 0.8504 |
| 0.1947 | 2.0 | 214 | 0.4518 | 0.8938 | 0.9112 | 0.8840 | 0.8933 |
| 0.0754 | 3.0 | 321 | 0.5060 | 0.8904 | 0.8937 | 0.8967 | 0.8950 |
| 0.0192 | 4.0 | 428 | 0.5699 | 0.8973 | 0.9016 | 0.8962 | 0.8981 |
| 0.0092 | 5.0 | 535 | 0.5534 | 0.8973 | 0.9031 | 0.8973 | 0.8997 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1