<!-- 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-aochildes-rarity-end-3p3k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3401
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 |
|---|---|---|---|
| 6.7034 | 0.29 | 500 | 5.6322 |
| 5.3397 | 0.59 | 1000 | 5.2003 |
| 4.9964 | 0.88 | 1500 | 4.9506 |
| 4.7225 | 1.17 | 2000 | 4.8007 |
| 4.5522 | 1.47 | 2500 | 4.6841 |
| 4.4577 | 1.76 | 3000 | 4.5816 |
| 4.3256 | 2.05 | 3500 | 4.5146 |
| 4.134 | 2.35 | 4000 | 4.4709 |
| 4.1094 | 2.64 | 4500 | 4.4072 |
| 4.0642 | 2.93 | 5000 | 4.3526 |
| 3.8539 | 3.23 | 5500 | 4.3507 |
| 3.8029 | 3.52 | 6000 | 4.3257 |
| 3.7862 | 3.81 | 6500 | 4.2911 |
| 3.6771 | 4.11 | 7000 | 4.2940 |
| 3.5156 | 4.4 | 7500 | 4.2864 |
| 3.5088 | 4.69 | 8000 | 4.2795 |
| 3.4989 | 4.99 | 8500 | 4.2639 |
| 3.3282 | 5.28 | 9000 | 4.2823 |
| 3.3212 | 5.58 | 9500 | 4.2794 |
| 3.3204 | 5.87 | 10000 | 4.2795 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
