<!-- 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. -->
cbt-norm-rarity-log-rarity-end-p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1026
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 |
|---|---|---|---|
| 6.3492 | 0.29 | 500 | 5.3375 |
| 5.0257 | 0.58 | 1000 | 4.9206 |
| 4.6972 | 0.88 | 1500 | 4.6826 |
| 4.4476 | 1.17 | 2000 | 4.5485 |
| 4.286 | 1.46 | 2500 | 4.4256 |
| 4.1861 | 1.75 | 3000 | 4.3203 |
| 4.073 | 2.04 | 3500 | 4.2493 |
| 3.8835 | 2.34 | 4000 | 4.2070 |
| 3.8576 | 2.63 | 4500 | 4.1491 |
| 3.8247 | 2.92 | 5000 | 4.0994 |
| 3.6292 | 3.21 | 5500 | 4.0973 |
| 3.5811 | 3.5 | 6000 | 4.0662 |
| 3.5613 | 3.8 | 6500 | 4.0335 |
| 3.4739 | 4.09 | 7000 | 4.0307 |
| 3.3065 | 4.38 | 7500 | 4.0279 |
| 3.3108 | 4.67 | 8000 | 4.0149 |
| 3.2959 | 4.96 | 8500 | 4.0015 |
| 3.1501 | 5.26 | 9000 | 4.0147 |
| 3.129 | 5.55 | 9500 | 4.0126 |
| 3.1254 | 5.84 | 10000 | 4.0124 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
