<!-- 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. -->
cl-log-rarity-280k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8338
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7201 | 0.05 | 500 | 5.5872 |
| 4.5119 | 0.1 | 1000 | 5.2582 |
| 4.2689 | 0.16 | 1500 | 5.0795 |
| 4.11 | 0.21 | 2000 | 4.9788 |
| 3.9871 | 0.26 | 2500 | 4.9290 |
| 3.8952 | 0.31 | 3000 | 4.8756 |
| 3.8135 | 0.36 | 3500 | 4.8455 |
| 3.7375 | 0.42 | 4000 | 4.8056 |
| 3.6651 | 0.47 | 4500 | 4.7948 |
| 3.5901 | 0.52 | 5000 | 4.7700 |
| 3.5092 | 0.57 | 5500 | 4.7661 |
| 3.4459 | 0.62 | 6000 | 4.7472 |
| 3.3734 | 0.68 | 6500 | 4.7382 |
| 3.3009 | 0.73 | 7000 | 4.7454 |
| 3.2508 | 0.78 | 7500 | 4.7368 |
| 3.2052 | 0.83 | 8000 | 4.7337 |
| 3.169 | 0.88 | 8500 | 4.7335 |
| 3.1546 | 0.93 | 9000 | 4.7301 |
| 3.1416 | 0.99 | 9500 | 4.7306 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
