<!-- 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-neg-log-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1046
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 |
|---|---|---|---|
| 6.3494 | 0.29 | 500 | 5.3385 |
| 5.0263 | 0.58 | 1000 | 4.9258 |
| 4.7061 | 0.87 | 1500 | 4.6888 |
| 4.4468 | 1.16 | 2000 | 4.5463 |
| 4.2956 | 1.46 | 2500 | 4.4260 |
| 4.1947 | 1.75 | 3000 | 4.3302 |
| 4.0756 | 2.04 | 3500 | 4.2520 |
| 3.8921 | 2.33 | 4000 | 4.2106 |
| 3.8655 | 2.62 | 4500 | 4.1572 |
| 3.8345 | 2.91 | 5000 | 4.1064 |
| 3.6432 | 3.2 | 5500 | 4.1013 |
| 3.581 | 3.49 | 6000 | 4.0704 |
| 3.569 | 3.79 | 6500 | 4.0362 |
| 3.4919 | 4.08 | 7000 | 4.0338 |
| 3.3226 | 4.37 | 7500 | 4.0289 |
| 3.3106 | 4.66 | 8000 | 4.0166 |
| 3.297 | 4.95 | 8500 | 4.0046 |
| 3.1568 | 5.24 | 9000 | 4.0152 |
| 3.1358 | 5.53 | 9500 | 4.0145 |
| 3.1313 | 5.82 | 10000 | 4.0135 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
