<!-- 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-c13k-c2p6k-rev
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8844
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 |
|---|---|---|---|
| 6.7952 | 0.32 | 500 | 5.7564 |
| 5.4839 | 0.63 | 1000 | 5.3858 |
| 5.1442 | 0.95 | 1500 | 5.2129 |
| 4.8614 | 1.27 | 2000 | 5.0996 |
| 4.7476 | 1.59 | 2500 | 5.0222 |
| 4.6481 | 1.9 | 3000 | 4.9507 |
| 4.4504 | 2.22 | 3500 | 4.9514 |
| 4.3796 | 2.54 | 4000 | 4.8926 |
| 4.3388 | 2.85 | 4500 | 4.8553 |
| 4.1754 | 3.17 | 5000 | 4.8697 |
| 4.0695 | 3.49 | 5500 | 4.8398 |
| 4.0541 | 3.8 | 6000 | 4.8012 |
| 3.9275 | 4.12 | 6500 | 4.8334 |
| 3.7741 | 4.44 | 7000 | 4.8258 |
| 3.7686 | 4.76 | 7500 | 4.8182 |
| 3.7113 | 5.07 | 8000 | 4.8313 |
| 3.5725 | 5.39 | 8500 | 4.8351 |
| 3.5762 | 5.71 | 9000 | 4.8371 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
