<!-- 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. -->
gpt2-concat-guten-rarity-all-mod-repetition-iorder-5k-p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1812
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 |
|---|---|---|---|
| 6.7049 | 0.3 | 500 | 5.6332 |
| 5.3603 | 0.59 | 1000 | 5.2033 |
| 5.0063 | 0.89 | 1500 | 4.9509 |
| 4.7286 | 1.18 | 2000 | 4.7987 |
| 4.5752 | 1.48 | 2500 | 4.6728 |
| 4.4634 | 1.78 | 3000 | 4.5663 |
| 4.3226 | 2.07 | 3500 | 4.4933 |
| 4.1472 | 2.37 | 4000 | 4.4458 |
| 4.1157 | 2.67 | 4500 | 4.3824 |
| 4.0756 | 2.96 | 5000 | 4.3282 |
| 3.8402 | 3.26 | 5500 | 4.3258 |
| 3.8183 | 3.55 | 6000 | 4.2905 |
| 3.7968 | 3.85 | 6500 | 4.2597 |
| 3.6538 | 4.15 | 7000 | 4.2640 |
| 3.5239 | 4.44 | 7500 | 4.2506 |
| 3.5235 | 4.74 | 8000 | 4.2375 |
| 3.4943 | 5.04 | 8500 | 4.2350 |
| 3.3327 | 5.33 | 9000 | 4.2405 |
| 3.3319 | 5.63 | 9500 | 4.2383 |
| 3.3325 | 5.92 | 10000 | 4.2378 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
