phi-2-LoRa-Python
This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.4864
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5433 | 0.1333 | 100 | 4.4747 |
| 4.4162 | 0.2667 | 200 | 4.4774 |
| 4.2759 | 0.4 | 300 | 4.4755 |
| 4.4021 | 0.5333 | 400 | 4.4764 |
| 4.3925 | 0.6667 | 500 | 4.4775 |
| 4.6016 | 0.8 | 600 | 4.5976 |
| 4.2527 | 0.9333 | 700 | 4.5484 |
| 4.5823 | 1.0667 | 800 | 4.5037 |
| 4.5826 | 1.2 | 900 | 4.5032 |
| 4.0654 | 1.3333 | 1000 | 4.5073 |
| 4.5386 | 1.4667 | 1100 | 4.4961 |
| 4.1046 | 1.6 | 1200 | 4.4957 |
| 4.1705 | 1.7333 | 1300 | 4.4943 |
| 4.4922 | 1.8667 | 1400 | 4.4918 |
| 4.7333 | 2.0 | 1500 | 4.4901 |
| 3.997 | 2.1333 | 1600 | 4.4889 |
| 4.5407 | 2.2667 | 1700 | 4.4880 |
| 3.8457 | 2.4 | 1800 | 4.4877 |
| 4.6653 | 2.5333 | 1900 | 4.4873 |
| 4.4524 | 2.6667 | 2000 | 4.4865 |
| 4.3138 | 2.8 | 2100 | 4.4870 |
| 4.3203 | 2.9333 | 2200 | 4.4865 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0