<!-- 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-end-2p5k-ctx-256
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.2359
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 |
|---|---|---|---|
| 7.8066 | 0.24 | 200 | 6.2314 |
| 5.9001 | 0.47 | 400 | 5.6837 |
| 5.4844 | 0.71 | 600 | 5.3762 |
| 5.2082 | 0.94 | 800 | 5.1424 |
| 4.9601 | 1.18 | 1000 | 5.0000 |
| 4.793 | 1.41 | 1200 | 4.8477 |
| 4.6671 | 1.65 | 1400 | 4.7224 |
| 4.5538 | 1.88 | 1600 | 4.6129 |
| 4.3657 | 2.12 | 1800 | 4.5395 |
| 4.2426 | 2.36 | 2000 | 4.4747 |
| 4.2096 | 2.59 | 2200 | 4.4096 |
| 4.1617 | 2.83 | 2400 | 4.3599 |
| 4.0429 | 3.06 | 2600 | 4.3204 |
| 3.8875 | 3.3 | 2800 | 4.2940 |
| 3.8782 | 3.53 | 3000 | 4.2656 |
| 3.864 | 3.77 | 3200 | 4.2348 |
| 3.8267 | 4.0 | 3400 | 4.2081 |
| 3.6034 | 4.24 | 3600 | 4.2149 |
| 3.5941 | 4.48 | 3800 | 4.1924 |
| 3.5872 | 4.71 | 4000 | 4.1779 |
| 3.577 | 4.95 | 4200 | 4.1648 |
| 3.4386 | 5.18 | 4400 | 4.1722 |
| 3.3996 | 5.42 | 4600 | 4.1702 |
| 3.3987 | 5.65 | 4800 | 4.1679 |
| 3.3866 | 5.89 | 5000 | 4.1670 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
