<!-- 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. -->
wikipedia-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1172
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 |
|---|---|---|---|
| 6.3409 | 0.29 | 500 | 5.3428 |
| 5.033 | 0.58 | 1000 | 4.9253 |
| 4.7142 | 0.87 | 1500 | 4.6930 |
| 4.4485 | 1.16 | 2000 | 4.5572 |
| 4.3033 | 1.46 | 2500 | 4.4453 |
| 4.1974 | 1.75 | 3000 | 4.3414 |
| 4.0926 | 2.04 | 3500 | 4.2704 |
| 3.8991 | 2.33 | 4000 | 4.2223 |
| 3.8776 | 2.62 | 4500 | 4.1638 |
| 3.839 | 2.91 | 5000 | 4.1187 |
| 3.649 | 3.2 | 5500 | 4.1116 |
| 3.5929 | 3.49 | 6000 | 4.0826 |
| 3.578 | 3.78 | 6500 | 4.0491 |
| 3.5017 | 4.07 | 7000 | 4.0476 |
| 3.3241 | 4.37 | 7500 | 4.0424 |
| 3.3199 | 4.66 | 8000 | 4.0295 |
| 3.3065 | 4.95 | 8500 | 4.0145 |
| 3.1679 | 5.24 | 9000 | 4.0278 |
| 3.141 | 5.53 | 9500 | 4.0272 |
| 3.1361 | 5.82 | 10000 | 4.0264 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
