<!-- 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. -->
guten-rarity-all-cut-20k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3156
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 |
|---|---|---|---|
| 6.6961 | 0.29 | 500 | 5.6410 |
| 5.3325 | 0.58 | 1000 | 5.1967 |
| 4.9884 | 0.88 | 1500 | 4.9500 |
| 4.7101 | 1.17 | 2000 | 4.8016 |
| 4.5563 | 1.46 | 2500 | 4.6746 |
| 4.446 | 1.75 | 3000 | 4.5705 |
| 4.3244 | 2.05 | 3500 | 4.4929 |
| 4.1291 | 2.34 | 4000 | 4.4489 |
| 4.0992 | 2.63 | 4500 | 4.3891 |
| 4.0577 | 2.92 | 5000 | 4.3368 |
| 3.8593 | 3.21 | 5500 | 4.3329 |
| 3.8077 | 3.51 | 6000 | 4.3001 |
| 3.778 | 3.8 | 6500 | 4.2669 |
| 3.6848 | 4.09 | 7000 | 4.2684 |
| 3.513 | 4.38 | 7500 | 4.2630 |
| 3.5142 | 4.68 | 8000 | 4.2467 |
| 3.4975 | 4.97 | 8500 | 4.2338 |
| 3.3389 | 5.26 | 9000 | 4.2463 |
| 3.3207 | 5.55 | 9500 | 4.2462 |
| 3.3201 | 5.84 | 10000 | 4.2453 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
