<!-- 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. -->
concat-cl-log-rarity-all-base-rarity-all-iorder-5p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0297
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3065 | 0.07 | 500 | 5.8723 |
| 5.0179 | 0.13 | 1000 | 5.5400 |
| 4.7484 | 0.2 | 1500 | 5.3448 |
| 4.5622 | 0.26 | 2000 | 5.2463 |
| 4.4268 | 0.33 | 2500 | 5.1786 |
| 4.3199 | 0.39 | 3000 | 5.1196 |
| 4.2233 | 0.46 | 3500 | 5.0798 |
| 4.1229 | 0.53 | 4000 | 5.0455 |
| 4.0367 | 0.59 | 4500 | 5.0115 |
| 3.9443 | 0.66 | 5000 | 4.9974 |
| 3.8646 | 0.72 | 5500 | 4.9775 |
| 3.7896 | 0.79 | 6000 | 4.9656 |
| 3.7367 | 0.85 | 6500 | 4.9500 |
| 3.7016 | 0.92 | 7000 | 4.9483 |
| 3.6873 | 0.98 | 7500 | 4.9454 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
