toki-pona-gpt2-alpaca-better
This model is a fine-tuned version of vicgalle/gpt2-alpaca-gpt4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5278
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8469 | 1.0 | 13818 | 0.7308 |
| 0.7526 | 2.0 | 27636 | 0.6435 |
| 0.686 | 3.0 | 41454 | 0.5936 |
| 0.6331 | 4.0 | 55272 | 0.5625 |
| 0.6076 | 5.0 | 69090 | 0.5435 |
| 0.5832 | 6.0 | 82908 | 0.5318 |
| 0.5825 | 7.0 | 96726 | 0.5278 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3