gpt2-finetuned-yannic-large
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0845
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
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 403 | 3.2112 |
| 3.3686 | 2.0 | 806 | 3.1667 |
| 3.2407 | 3.0 | 1209 | 3.1426 |
| 3.1842 | 4.0 | 1612 | 3.1277 |
| 3.134 | 5.0 | 2015 | 3.1135 |
| 3.134 | 6.0 | 2418 | 3.1055 |
| 3.0949 | 7.0 | 2821 | 3.1004 |
| 3.0644 | 8.0 | 3224 | 3.0938 |
| 3.0391 | 9.0 | 3627 | 3.0904 |
| 3.0219 | 10.0 | 4030 | 3.0882 |
| 3.0219 | 11.0 | 4433 | 3.0865 |
| 3.0052 | 12.0 | 4836 | 3.0858 |
| 2.9926 | 13.0 | 5239 | 3.0859 |
| 2.9803 | 14.0 | 5642 | 3.0842 |
| 2.9793 | 15.0 | 6045 | 3.0845 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2