<!-- 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-220k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.7958
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 |
|---|---|---|---|
| 5.7188 | 0.07 | 500 | 5.5918 |
| 4.5196 | 0.13 | 1000 | 5.2478 |
| 4.2676 | 0.2 | 1500 | 5.0782 |
| 4.1109 | 0.26 | 2000 | 4.9843 |
| 3.9983 | 0.33 | 2500 | 4.9048 |
| 3.8933 | 0.4 | 3000 | 4.8693 |
| 3.8127 | 0.46 | 3500 | 4.8279 |
| 3.7277 | 0.53 | 4000 | 4.8011 |
| 3.6491 | 0.59 | 4500 | 4.7678 |
| 3.5775 | 0.66 | 5000 | 4.7367 |
| 3.5032 | 0.73 | 5500 | 4.7246 |
| 3.4444 | 0.79 | 6000 | 4.7037 |
| 3.39 | 0.86 | 6500 | 4.6959 |
| 3.3637 | 0.92 | 7000 | 4.6939 |
| 3.3558 | 0.99 | 7500 | 4.6909 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
