<!-- 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-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: 4.8499
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 |
|---|---|---|---|
| 6.4758 | 0.31 | 500 | 5.4494 |
| 5.2078 | 0.62 | 1000 | 5.1235 |
| 4.8716 | 0.94 | 1500 | 4.9590 |
| 4.6054 | 1.25 | 2000 | 4.8946 |
| 4.4901 | 1.56 | 2500 | 4.8123 |
| 4.4012 | 1.87 | 3000 | 4.7698 |
| 4.2331 | 2.19 | 3500 | 4.7924 |
| 4.1398 | 2.5 | 4000 | 4.7543 |
| 4.1094 | 2.81 | 4500 | 4.7170 |
| 3.981 | 3.12 | 5000 | 4.7281 |
| 3.851 | 3.44 | 5500 | 4.7167 |
| 3.8335 | 3.75 | 6000 | 4.6996 |
| 3.7632 | 4.06 | 6500 | 4.7378 |
| 3.5753 | 4.37 | 7000 | 4.7430 |
| 3.5684 | 4.68 | 7500 | 4.7562 |
| 3.5527 | 5.0 | 8000 | 4.7637 |
| 3.3883 | 5.31 | 8500 | 4.7796 |
| 3.3839 | 5.62 | 9000 | 4.7965 |
| 3.3812 | 5.93 | 9500 | 4.7969 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
