<!-- 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. -->
all-base-norm-rarity-log-rarity-cut-short-728k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8327
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 |
|---|---|---|---|
| 6.4769 | 0.32 | 500 | 5.4775 |
| 5.1999 | 0.63 | 1000 | 5.1294 |
| 4.8599 | 0.95 | 1500 | 4.9618 |
| 4.6066 | 1.26 | 2000 | 4.8783 |
| 4.4846 | 1.58 | 2500 | 4.8010 |
| 4.3932 | 1.89 | 3000 | 4.7527 |
| 4.2173 | 2.21 | 3500 | 4.7543 |
| 4.1413 | 2.52 | 4000 | 4.6999 |
| 4.1024 | 2.84 | 4500 | 4.6880 |
| 3.9574 | 3.15 | 5000 | 4.7229 |
| 3.8541 | 3.47 | 5500 | 4.7094 |
| 3.8339 | 3.79 | 6000 | 4.6863 |
| 3.7358 | 4.1 | 6500 | 4.7259 |
| 3.5818 | 4.42 | 7000 | 4.7368 |
| 3.5684 | 4.73 | 7500 | 4.7424 |
| 3.5321 | 5.05 | 8000 | 4.7659 |
| 3.3884 | 5.36 | 8500 | 4.7739 |
| 3.3866 | 5.68 | 9000 | 4.7734 |
| 3.3847 | 5.99 | 9500 | 4.7756 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
