<!-- 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-mod-formatting-noem-rarity-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: 4.1143
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 |
|---|---|---|---|
| 6.3453 | 0.29 | 500 | 5.3477 |
| 5.0323 | 0.58 | 1000 | 4.9403 |
| 4.7055 | 0.87 | 1500 | 4.6938 |
| 4.4394 | 1.17 | 2000 | 4.5543 |
| 4.2985 | 1.46 | 2500 | 4.4393 |
| 4.1999 | 1.75 | 3000 | 4.3368 |
| 4.0751 | 2.04 | 3500 | 4.2617 |
| 3.8966 | 2.33 | 4000 | 4.2210 |
| 3.866 | 2.62 | 4500 | 4.1640 |
| 3.8246 | 2.92 | 5000 | 4.1122 |
| 3.642 | 3.21 | 5500 | 4.1066 |
| 3.581 | 3.5 | 6000 | 4.0790 |
| 3.5663 | 3.79 | 6500 | 4.0482 |
| 3.484 | 4.08 | 7000 | 4.0436 |
| 3.3128 | 4.37 | 7500 | 4.0395 |
| 3.3126 | 4.66 | 8000 | 4.0255 |
| 3.2976 | 4.96 | 8500 | 4.0148 |
| 3.1535 | 5.25 | 9000 | 4.0252 |
| 3.1321 | 5.54 | 9500 | 4.0246 |
| 3.1277 | 5.83 | 10000 | 4.0233 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
