### LLaMA-Factory SFT Configuration for Session-Level Reflection
### Based on paper's training setup (Table 4)

### Model
model_name_or_path: /projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/models/llama-3.1-8b-instruct

### Method
stage: sft
do_train: true
finetuning_type: full

### Dataset
dataset: session_level_reflection
dataset_dir: /projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/collaborativeagents/training/training_data
template: llama3
cutoff_len: 32768
preprocessing_num_workers: 16

### Output
output_dir: /projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/collaborativeagents/training/outputs/sft_reflection
logging_steps: 10
save_steps: 100
save_total_limit: 3

### Training hyperparameters (from paper Table 4)
per_device_train_batch_size: 1
gradient_accumulation_steps: 64
learning_rate: 1.0e-6
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true

### Optimization
optim: adamw_torch
weight_decay: 0.01
max_grad_norm: 1.0

### Report
report_to: none