Base model: microsoft/phi-2 | |
Training samples: 85 | |
Epochs: 3 | |
Learning rate: 0.0002 | |
Batch size: 2 | |
Gradient accumulation steps: 4 | |
Base model: microsoft/phi-2 | |
Training samples: 85 | |
Epochs: 3 | |
Learning rate: 0.0002 | |
Batch size: 2 | |
Gradient accumulation steps: 4 | |