<!-- 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
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8382
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 |
|---|---|---|---|
| 6.4829 | 0.31 | 500 | 5.4571 |
| 5.1897 | 0.63 | 1000 | 5.1170 |
| 4.8631 | 0.94 | 1500 | 4.9461 |
| 4.5999 | 1.26 | 2000 | 4.8716 |
| 4.4815 | 1.57 | 2500 | 4.8156 |
| 4.3894 | 1.89 | 3000 | 4.7439 |
| 4.2153 | 2.2 | 3500 | 4.7424 |
| 4.1317 | 2.52 | 4000 | 4.7331 |
| 4.1014 | 2.83 | 4500 | 4.6782 |
| 3.9572 | 3.15 | 5000 | 4.7246 |
| 3.8505 | 3.46 | 5500 | 4.6990 |
| 3.8281 | 3.78 | 6000 | 4.6816 |
| 3.7335 | 4.09 | 6500 | 4.7236 |
| 3.571 | 4.41 | 7000 | 4.7342 |
| 3.5628 | 4.72 | 7500 | 4.7397 |
| 3.5276 | 5.04 | 8000 | 4.7641 |
| 3.3767 | 5.35 | 8500 | 4.7749 |
| 3.3786 | 5.67 | 9000 | 4.7817 |
| 3.3777 | 5.98 | 9500 | 4.7828 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
