metadata
library_name: transformers
license: mit
base_model: danghuy1999/gpt2-viwiki
tags:
- generated_from_trainer
model-index:
- name: vietnamese-poem-gpt2-sauchu
results: []
vietnamese-poem-gpt2-sauchu
This model is a fine-tuned version of danghuy1999/gpt2-viwiki on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9586
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 17 | 7.5820 |
| No log | 2.0 | 34 | 7.2608 |
| No log | 3.0 | 51 | 6.9590 |
| No log | 4.0 | 68 | 6.7325 |
| No log | 5.0 | 85 | 6.5588 |
| No log | 6.0 | 102 | 6.4239 |
| No log | 7.0 | 119 | 6.3150 |
| No log | 8.0 | 136 | 6.2274 |
| No log | 9.0 | 153 | 6.1426 |
| No log | 10.0 | 170 | 6.0750 |
| No log | 11.0 | 187 | 6.0142 |
| No log | 12.0 | 204 | 5.9586 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0