<!-- 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_end_741k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8389
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 |
|---|---|---|---|
| 6.4955 | 0.31 | 500 | 5.4636 |
| 5.2057 | 0.63 | 1000 | 5.1405 |
| 4.8732 | 0.94 | 1500 | 4.9621 |
| 4.6152 | 1.25 | 2000 | 4.8785 |
| 4.4896 | 1.57 | 2500 | 4.8113 |
| 4.4036 | 1.88 | 3000 | 4.7798 |
| 4.2314 | 2.19 | 3500 | 4.7698 |
| 4.1467 | 2.5 | 4000 | 4.7098 |
| 4.109 | 2.82 | 4500 | 4.7047 |
| 3.9843 | 3.13 | 5000 | 4.7499 |
| 3.8539 | 3.44 | 5500 | 4.7332 |
| 3.8374 | 3.76 | 6000 | 4.6700 |
| 3.7626 | 4.07 | 6500 | 4.7214 |
| 3.579 | 4.38 | 7000 | 4.7451 |
| 3.5714 | 4.7 | 7500 | 4.7523 |
| 3.5527 | 5.01 | 8000 | 4.7533 |
| 3.3912 | 5.32 | 8500 | 4.7709 |
| 3.3863 | 5.64 | 9000 | 4.7838 |
| 3.384 | 5.95 | 9500 | 4.7830 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
