70 lines
1.9 KiB
Markdown
70 lines
1.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: mit
|
|
base_model: danghuy1999/gpt2-viwiki
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: vietnamese-poem-gpt2-namchu
|
|
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. -->
|
|
|
|
# vietnamese-poem-gpt2-namchu
|
|
|
|
This model is a fine-tuned version of [danghuy1999/gpt2-viwiki](https://huggingface.co/danghuy1999/gpt2-viwiki) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 4.2277
|
|
|
|
## 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: 4
|
|
- eval_batch_size: 4
|
|
- seed: 42
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_steps: 500
|
|
- num_epochs: 10
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:-----:|:-----:|:---------------:|
|
|
| 4.9894 | 1.0 | 2037 | 4.8025 |
|
|
| 4.7181 | 2.0 | 4074 | 4.5903 |
|
|
| 4.5653 | 3.0 | 6111 | 4.4569 |
|
|
| 4.4342 | 4.0 | 8148 | 4.3877 |
|
|
| 4.352 | 5.0 | 10185 | 4.3295 |
|
|
| 4.307 | 6.0 | 12222 | 4.2892 |
|
|
| 4.2481 | 7.0 | 14259 | 4.2575 |
|
|
| 4.233 | 8.0 | 16296 | 4.2448 |
|
|
| 4.2036 | 9.0 | 18333 | 4.2317 |
|
|
| 4.18 | 10.0 | 20370 | 4.2277 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.47.1
|
|
- Pytorch 2.5.1+cu121
|
|
- Datasets 3.2.0
|
|
- Tokenizers 0.21.0
|