<!-- 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. -->
qed-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1171
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 |
|---|---|---|---|
| 6.3592 | 0.29 | 500 | 5.3361 |
| 5.0454 | 0.58 | 1000 | 4.9330 |
| 4.7118 | 0.88 | 1500 | 4.6958 |
| 4.4583 | 1.17 | 2000 | 4.5571 |
| 4.3049 | 1.46 | 2500 | 4.4421 |
| 4.2187 | 1.75 | 3000 | 4.3410 |
| 4.099 | 2.05 | 3500 | 4.2645 |
| 3.9157 | 2.34 | 4000 | 4.2163 |
| 3.8896 | 2.63 | 4500 | 4.1655 |
| 3.8487 | 2.92 | 5000 | 4.1078 |
| 3.6548 | 3.21 | 5500 | 4.1099 |
| 3.6051 | 3.51 | 6000 | 4.0753 |
| 3.5947 | 3.8 | 6500 | 4.0445 |
| 3.4956 | 4.09 | 7000 | 4.0427 |
| 3.3396 | 4.38 | 7500 | 4.0386 |
| 3.336 | 4.68 | 8000 | 4.0234 |
| 3.3241 | 4.97 | 8500 | 4.0114 |
| 3.1753 | 5.26 | 9000 | 4.0252 |
| 3.1537 | 5.55 | 9500 | 4.0240 |
| 3.1587 | 5.84 | 10000 | 4.0228 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
