<!-- 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-mod-guten-mod-rarity-all-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3316
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 |
|---|---|---|---|
| 6.6966 | 0.29 | 500 | 5.6441 |
| 5.3409 | 0.58 | 1000 | 5.2046 |
| 4.9948 | 0.88 | 1500 | 4.9627 |
| 4.7265 | 1.17 | 2000 | 4.8189 |
| 4.5651 | 1.46 | 2500 | 4.6894 |
| 4.4539 | 1.75 | 3000 | 4.5863 |
| 4.3346 | 2.05 | 3500 | 4.5066 |
| 4.1409 | 2.34 | 4000 | 4.4585 |
| 4.1117 | 2.63 | 4500 | 4.4013 |
| 4.0669 | 2.92 | 5000 | 4.3496 |
| 3.8709 | 3.22 | 5500 | 4.3442 |
| 3.8157 | 3.51 | 6000 | 4.3154 |
| 3.7926 | 3.8 | 6500 | 4.2830 |
| 3.6943 | 4.09 | 7000 | 4.2806 |
| 3.5299 | 4.39 | 7500 | 4.2754 |
| 3.5211 | 4.68 | 8000 | 4.2625 |
| 3.5137 | 4.97 | 8500 | 4.2477 |
| 3.354 | 5.26 | 9000 | 4.2619 |
| 3.3365 | 5.56 | 9500 | 4.2609 |
| 3.3354 | 5.85 | 10000 | 4.2597 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
