<!-- 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-cl-concat-log-rarity-8-276k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.1087
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 |
|---|---|---|---|
| 6.3286 | 0.05 | 500 | 5.9527 |
| 5.039 | 0.11 | 1000 | 5.5840 |
| 4.7595 | 0.16 | 1500 | 5.4148 |
| 4.5814 | 0.21 | 2000 | 5.3021 |
| 4.4533 | 0.27 | 2500 | 5.2366 |
| 4.3392 | 0.32 | 3000 | 5.1814 |
| 4.2531 | 0.37 | 3500 | 5.1391 |
| 4.1558 | 0.43 | 4000 | 5.1087 |
| 4.0733 | 0.48 | 4500 | 5.0874 |
| 3.9863 | 0.53 | 5000 | 5.0788 |
| 3.8989 | 0.59 | 5500 | 5.0582 |
| 3.8215 | 0.64 | 6000 | 5.0518 |
| 3.7426 | 0.69 | 6500 | 5.0522 |
| 3.6702 | 0.75 | 7000 | 5.0421 |
| 3.6134 | 0.8 | 7500 | 5.0411 |
| 3.565 | 0.85 | 8000 | 5.0373 |
| 3.535 | 0.91 | 8500 | 5.0334 |
| 3.5216 | 0.96 | 9000 | 5.0326 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
