<!-- 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. -->
gpt2-concat-all-mod-datasets1-rarity-all-iorder-c13k-c2p6k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.1936
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7242 | 0.32 | 500 | 5.9768 |
| 5.1735 | 0.63 | 1000 | 5.6554 |
| 4.7404 | 0.95 | 1500 | 5.4996 |
| 4.4224 | 1.27 | 2000 | 5.3442 |
| 4.2763 | 1.59 | 2500 | 5.2809 |
| 4.1764 | 1.9 | 3000 | 5.1548 |
| 3.9599 | 2.22 | 3500 | 5.1872 |
| 3.8843 | 2.54 | 4000 | 5.1061 |
| 3.8426 | 2.85 | 4500 | 5.0545 |
| 3.6894 | 3.17 | 5000 | 5.1307 |
| 3.571 | 3.49 | 5500 | 5.1444 |
| 3.5653 | 3.8 | 6000 | 5.0994 |
| 3.4291 | 4.12 | 6500 | 5.1304 |
| 3.2885 | 4.44 | 7000 | 5.1346 |
| 3.2687 | 4.76 | 7500 | 5.1504 |
| 3.2233 | 5.07 | 8000 | 5.1550 |
| 3.0814 | 5.39 | 8500 | 5.1628 |
| 3.0825 | 5.71 | 9000 | 5.1746 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
