updated style mimciking fine tuning
This commit is contained in:
@@ -56,11 +56,15 @@ model:
|
||||
# Training Configuration
|
||||
training:
|
||||
num_epochs: 3 # Number of training epochs
|
||||
batch_size: 16 # Training batch size (adjust based on GPU memory)
|
||||
learning_rate: 3e-5 # Learning rate (typical range: 1e-5 to 5e-5 for fine-tuning)
|
||||
batch_size: 4 # Training batch size (adjust based on GPU memory)
|
||||
learning_rate: 2e-4 # Learning rate (typical range: 1e-5 to 5e-5 for fine-tuning)
|
||||
weight_decay: 0.01 # Weight decay for optimizer (prevents overfitting)
|
||||
warmup_ratio: 0.1 # Warmup ratio for scheduler (0.0 to 1.0)
|
||||
warmup_steps: 5 # Warmup steps (fixed value instead of ratio)
|
||||
max_steps: 60 # Maximum training steps
|
||||
gradient_accumulation_steps: 4 # Gradient accumulation steps
|
||||
lr_scheduler_type: "linear" # Scheduler type: "linear", "cosine", "polynomial"
|
||||
seed: 3407 # Random seed for reproducibility
|
||||
model_output_dir: "./models/styling" # Directory to save the trained model (updated to match actual location)
|
||||
|
||||
# Inference Configuration
|
||||
inference:
|
||||
|
||||
Reference in New Issue
Block a user