phi-2-qlora-pythoncode
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6280
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.598 | 1.0 | 563 | 0.6518 |
| 0.6242 | 2.0 | 1126 | 0.6330 |
| 0.6557 | 3.0 | 1689 | 0.6280 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2