metadata
license: mit
base_model: indobenchmark/indogpt
tags:
- generated_from_trainer
datasets:
- id-review-gen
model-index:
- name: gpt2-completion-finetune-id-review-gen
results: []
gpt2-completion-finetune-id-review-gen
This model is a fine-tuned version of indobenchmark/indogpt on the id-review-gen dataset. It achieves the following results on the evaluation set:
- Loss: 1.3547
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: 2e-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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6024 | 1.0 | 2065 | 1.5079 |
| 1.4878 | 2.0 | 4130 | 1.4249 |
| 1.4336 | 3.0 | 6195 | 1.3837 |
| 1.4006 | 4.0 | 8260 | 1.3625 |
| 1.3912 | 5.0 | 10325 | 1.3547 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1