<!-- 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. -->
gpt2-concat-simple-wiki-rarity-all-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3535
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 |
|---|---|---|---|
| 6.7004 | 0.29 | 500 | 5.6313 |
| 5.335 | 0.58 | 1000 | 5.1992 |
| 4.9864 | 0.87 | 1500 | 4.9605 |
| 4.7328 | 1.17 | 2000 | 4.8244 |
| 4.578 | 1.46 | 2500 | 4.7056 |
| 4.4753 | 1.75 | 3000 | 4.6075 |
| 4.3596 | 2.04 | 3500 | 4.5420 |
| 4.1677 | 2.33 | 4000 | 4.4944 |
| 4.1371 | 2.62 | 4500 | 4.4336 |
| 4.0946 | 2.91 | 5000 | 4.3802 |
| 3.8963 | 3.21 | 5500 | 4.3779 |
| 3.8338 | 3.5 | 6000 | 4.3423 |
| 3.821 | 3.79 | 6500 | 4.3127 |
| 3.7341 | 4.08 | 7000 | 4.3030 |
| 3.5486 | 4.37 | 7500 | 4.3027 |
| 3.5395 | 4.66 | 8000 | 4.2869 |
| 3.528 | 4.95 | 8500 | 4.2755 |
| 3.3801 | 5.24 | 9000 | 4.2873 |
| 3.3538 | 5.54 | 9500 | 4.2853 |
| 3.3452 | 5.83 | 10000 | 4.2848 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
