# Training configuration optimized for cloud RTX 4090 / RTX 3090 (24GB VRAM)
#
# Usage:
#   python train_clip_logo.py --config configs/cloud_rtx4090.yaml
#
# Estimated training time: 4-6 hours
# Estimated cost on RunPod: ~$3

# Base model
base_model: "openai/clip-vit-large-patch14"

# Dataset paths
dataset_dir: "LogoDet-3K"
reference_dir: "reference_logos"
db_path: "test_data_mapping.db"

# Data splits
train_split: 0.7
val_split: 0.15
test_split: 0.15

# Larger batches for faster training on 24GB VRAM
batch_size: 32
logos_per_batch: 32
samples_per_logo: 4
gradient_accumulation_steps: 4  # Effective batch = 128
num_workers: 8

# Model architecture
lora_r: 16
lora_alpha: 32
lora_dropout: 0.1
freeze_layers: 12
use_gradient_checkpointing: true

# Training
learning_rate: 1.0e-5
weight_decay: 0.01
warmup_steps: 500
max_epochs: 20
mixed_precision: true

# Loss
temperature: 0.07
loss_type: "infonce"
triplet_margin: 0.3

# Early stopping
patience: 5
min_delta: 0.001

# Output
checkpoint_dir: "checkpoints"
output_dir: "models/logo_detection/clip_finetuned"
save_every_n_epochs: 2  # Save more frequently for cloud

# Logging
log_every_n_steps: 10
eval_every_n_epochs: 1

seed: 42
use_hard_negatives: false
use_augmentation: true
augmentation_strength: "medium"