<!-- 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. -->
cl-rairty-138k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.5428
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 |
|---|---|---|---|
| 6.2839 | 0.05 | 500 | 5.4795 |
| 5.0415 | 0.11 | 1000 | 5.1006 |
| 4.7226 | 0.16 | 1500 | 4.9120 |
| 4.5104 | 0.22 | 2000 | 4.8065 |
| 4.3612 | 0.27 | 2500 | 4.7228 |
| 4.2428 | 0.33 | 3000 | 4.6795 |
| 4.1319 | 0.38 | 3500 | 4.6186 |
| 4.0383 | 0.44 | 4000 | 4.5901 |
| 3.9574 | 0.49 | 4500 | 4.5596 |
| 3.8673 | 0.55 | 5000 | 4.5309 |
| 3.7879 | 0.6 | 5500 | 4.5100 |
| 3.7136 | 0.66 | 6000 | 4.4966 |
| 3.6418 | 0.71 | 6500 | 4.4850 |
| 3.5814 | 0.76 | 7000 | 4.4735 |
| 3.5361 | 0.82 | 7500 | 4.4643 |
| 3.4948 | 0.87 | 8000 | 4.4619 |
| 3.477 | 0.93 | 8500 | 4.4579 |
| 3.4652 | 0.98 | 9000 | 4.4568 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
