<!-- 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-datasets1-rarity-all-5p5k-mostf
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8759
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 |
|---|---|---|---|
| 6.8137 | 0.32 | 500 | 5.7598 |
| 5.4934 | 0.63 | 1000 | 5.3910 |
| 5.1505 | 0.95 | 1500 | 5.2102 |
| 4.8731 | 1.26 | 2000 | 5.1081 |
| 4.7471 | 1.58 | 2500 | 5.0109 |
| 4.6518 | 1.9 | 3000 | 4.9382 |
| 4.4609 | 2.21 | 3500 | 4.9127 |
| 4.3841 | 2.53 | 4000 | 4.8869 |
| 4.3413 | 2.84 | 4500 | 4.8352 |
| 4.1847 | 3.16 | 5000 | 4.8351 |
| 4.0687 | 3.47 | 5500 | 4.8326 |
| 4.0572 | 3.79 | 6000 | 4.8002 |
| 3.9466 | 4.11 | 6500 | 4.8120 |
| 3.774 | 4.42 | 7000 | 4.8203 |
| 3.769 | 4.74 | 7500 | 4.8067 |
| 3.7261 | 5.05 | 8000 | 4.8206 |
| 3.5715 | 5.37 | 8500 | 4.8257 |
| 3.5747 | 5.69 | 9000 | 4.8299 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
