<!-- 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-rarity-guten-bnc-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: 4.3317
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 |
|---|---|---|---|
| 6.7063 | 0.29 | 500 | 5.6381 |
| 5.354 | 0.59 | 1000 | 5.2164 |
| 5.0098 | 0.88 | 1500 | 4.9588 |
| 4.7339 | 1.17 | 2000 | 4.8190 |
| 4.5764 | 1.46 | 2500 | 4.6923 |
| 4.4686 | 1.76 | 3000 | 4.5840 |
| 4.3402 | 2.05 | 3500 | 4.5086 |
| 4.152 | 2.34 | 4000 | 4.4605 |
| 4.1177 | 2.63 | 4500 | 4.4050 |
| 4.0811 | 2.93 | 5000 | 4.3506 |
| 3.8727 | 3.22 | 5500 | 4.3480 |
| 3.819 | 3.51 | 6000 | 4.3120 |
| 3.8077 | 3.8 | 6500 | 4.2812 |
| 3.698 | 4.1 | 7000 | 4.2842 |
| 3.5395 | 4.39 | 7500 | 4.2768 |
| 3.5285 | 4.68 | 8000 | 4.2603 |
| 3.5155 | 4.97 | 8500 | 4.2472 |
| 3.3564 | 5.27 | 9000 | 4.2620 |
| 3.3394 | 5.56 | 9500 | 4.2607 |
| 3.3378 | 5.85 | 10000 | 4.2600 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
