<!-- 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-cocnat-mod-datasets4-rarity-all-cbt-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: 4.3693
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 |
|---|---|---|---|
| 6.7064 | 0.3 | 500 | 5.6460 |
| 5.3738 | 0.6 | 1000 | 5.2188 |
| 5.0327 | 0.9 | 1500 | 4.9601 |
| 4.7499 | 1.2 | 2000 | 4.8195 |
| 4.5976 | 1.51 | 2500 | 4.7041 |
| 4.4918 | 1.81 | 3000 | 4.5985 |
| 4.3305 | 2.11 | 3500 | 4.5409 |
| 4.1782 | 2.41 | 4000 | 4.4771 |
| 4.1435 | 2.71 | 4500 | 4.4225 |
| 4.0943 | 3.01 | 5000 | 4.3819 |
| 3.8452 | 3.31 | 5500 | 4.3710 |
| 3.8422 | 3.61 | 6000 | 4.3380 |
| 3.8283 | 3.92 | 6500 | 4.3067 |
| 3.6271 | 4.22 | 7000 | 4.3185 |
| 3.5589 | 4.52 | 7500 | 4.3095 |
| 3.5415 | 4.82 | 8000 | 4.2983 |
| 3.4718 | 5.12 | 8500 | 4.3060 |
| 3.3586 | 5.42 | 9000 | 4.3083 |
| 3.3592 | 5.72 | 9500 | 4.3087 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
