|
--- |
|
license: mit |
|
base_model: indobenchmark/indogpt |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- id-review-gen |
|
model-index: |
|
- name: gpt2-completion-finetune-id-review-gen |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# gpt2-completion-finetune-id-review-gen |
|
|
|
This model is a fine-tuned version of [indobenchmark/indogpt](https://huggingface.co./indobenchmark/indogpt) on the id-review-gen dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2807 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.5971 | 1.0 | 2065 | 1.5028 | |
|
| 1.4759 | 2.0 | 4130 | 1.4118 | |
|
| 1.4151 | 3.0 | 6195 | 1.3649 | |
|
| 1.3746 | 4.0 | 8260 | 1.3400 | |
|
| 1.3533 | 5.0 | 10325 | 1.3165 | |
|
| 1.3273 | 6.0 | 12390 | 1.3030 | |
|
| 1.306 | 7.0 | 14455 | 1.2944 | |
|
| 1.2946 | 8.0 | 16520 | 1.2879 | |
|
| 1.2829 | 9.0 | 18585 | 1.2814 | |
|
| 1.2818 | 10.0 | 20650 | 1.2807 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
