lora-cs324-length-control
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2118
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5584 | 0.16 | 500 | 3.2567 |
| 3.392 | 0.32 | 1000 | 3.2473 |
| 3.3584 | 0.48 | 1500 | 3.2290 |
| 3.3115 | 0.64 | 2000 | 3.2196 |
| 3.3041 | 0.8 | 2500 | 3.2126 |
| 3.3024 | 0.96 | 3000 | 3.2118 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3