<!-- 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. -->
cbt-log-rarity-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3118
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 |
|---|---|---|---|
| 6.6934 | 0.29 | 500 | 5.6310 |
| 5.3312 | 0.58 | 1000 | 5.1981 |
| 4.9883 | 0.87 | 1500 | 4.9500 |
| 4.7132 | 1.16 | 2000 | 4.7969 |
| 4.5508 | 1.46 | 2500 | 4.6748 |
| 4.4477 | 1.75 | 3000 | 4.5709 |
| 4.3214 | 2.04 | 3500 | 4.4910 |
| 4.1241 | 2.33 | 4000 | 4.4484 |
| 4.0945 | 2.62 | 4500 | 4.3895 |
| 4.0594 | 2.91 | 5000 | 4.3351 |
| 3.859 | 3.2 | 5500 | 4.3306 |
| 3.7902 | 3.49 | 6000 | 4.3011 |
| 3.7783 | 3.79 | 6500 | 4.2646 |
| 3.6948 | 4.08 | 7000 | 4.2644 |
| 3.5134 | 4.37 | 7500 | 4.2584 |
| 3.5019 | 4.66 | 8000 | 4.2430 |
| 3.4878 | 4.95 | 8500 | 4.2312 |
| 3.3395 | 5.24 | 9000 | 4.2428 |
| 3.313 | 5.53 | 9500 | 4.2422 |
| 3.3111 | 5.82 | 10000 | 4.2412 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
