metadata
license: mit
base_model: indobenchmark/indogpt
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bdc2024-indogpt-chatgpt-1
results: []
bdc2024-indogpt-chatgpt-1
This model is a fine-tuned version of indobenchmark/indogpt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4125
- Accuracy: 0.9120
- Balanced Accuracy: 0.7419
- Precision: 0.9074
- Recall: 0.9120
- F1: 0.9000
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Balanced Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 483 | 0.7389 | 0.7859 | 0.5178 | 0.8025 | 0.7859 | 0.7522 |
| 0.9144 | 2.0 | 966 | 0.5773 | 0.8337 | 0.6070 | 0.8360 | 0.8337 | 0.8036 |
| 0.5745 | 3.0 | 1449 | 0.4493 | 0.8910 | 0.7056 | 0.8885 | 0.8910 | 0.8747 |
| 0.3836 | 4.0 | 1932 | 0.4228 | 0.9025 | 0.7261 | 0.8978 | 0.9025 | 0.8878 |
| 0.2392 | 5.0 | 2415 | 0.4125 | 0.9120 | 0.7419 | 0.9074 | 0.9120 | 0.9000 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.13.3