<!-- 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-dp-cl-log-rarity-10-220k-mod-datasets-rarity1-root3
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0160
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3749 | 0.06 | 500 | 5.9206 |
| 5.0858 | 0.11 | 1000 | 5.5611 |
| 4.7997 | 0.17 | 1500 | 5.3578 |
| 4.6162 | 0.22 | 2000 | 5.2320 |
| 4.4781 | 0.28 | 2500 | 5.1532 |
| 4.3661 | 0.34 | 3000 | 5.1006 |
| 4.2652 | 0.39 | 3500 | 5.0590 |
| 4.165 | 0.45 | 4000 | 5.0351 |
| 4.0755 | 0.5 | 4500 | 5.0115 |
| 3.9938 | 0.56 | 5000 | 4.9972 |
| 3.9025 | 0.62 | 5500 | 4.9795 |
| 3.8197 | 0.67 | 6000 | 4.9663 |
| 3.7415 | 0.73 | 6500 | 4.9587 |
| 3.6771 | 0.78 | 7000 | 4.9494 |
| 3.622 | 0.84 | 7500 | 4.9430 |
| 3.5918 | 0.9 | 8000 | 4.9422 |
| 3.5731 | 0.95 | 8500 | 4.9403 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
