<!-- 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. -->
children_stories-rarity-cut-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0977
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 |
|---|---|---|---|
| 6.3368 | 0.29 | 500 | 5.3502 |
| 5.0367 | 0.58 | 1000 | 4.9279 |
| 4.7027 | 0.87 | 1500 | 4.6895 |
| 4.4315 | 1.17 | 2000 | 4.5422 |
| 4.2791 | 1.46 | 2500 | 4.4248 |
| 4.1855 | 1.75 | 3000 | 4.3171 |
| 4.0713 | 2.04 | 3500 | 4.2478 |
| 3.8811 | 2.33 | 4000 | 4.2031 |
| 3.8533 | 2.62 | 4500 | 4.1460 |
| 3.8148 | 2.91 | 5000 | 4.0985 |
| 3.6384 | 3.21 | 5500 | 4.0911 |
| 3.5688 | 3.5 | 6000 | 4.0650 |
| 3.5603 | 3.79 | 6500 | 4.0319 |
| 3.4736 | 4.08 | 7000 | 4.0260 |
| 3.3111 | 4.37 | 7500 | 4.0233 |
| 3.2996 | 4.66 | 8000 | 4.0100 |
| 3.2868 | 4.95 | 8500 | 3.9973 |
| 3.1488 | 5.24 | 9000 | 4.0083 |
| 3.1243 | 5.54 | 9500 | 4.0079 |
| 3.1198 | 5.83 | 10000 | 4.0072 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
