<!-- 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. -->
toki-pona-gpt2-alpaca-best
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: 0.7089
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 |
---|---|---|---|
1.0386 | 1.0 | 22442 | 0.9873 |
0.9368 | 2.0 | 44884 | 0.8761 |
0.8786 | 3.0 | 67326 | 0.8070 |
0.8313 | 4.0 | 89768 | 0.7617 |
0.7885 | 5.0 | 112210 | 0.7323 |
0.7734 | 6.0 | 134652 | 0.7150 |
0.7586 | 7.0 | 157094 | 0.7089 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3