# Sanity check config — verify baseline NLL reproduction and basic training
# Run: python scripts/train.py --config configs/sanity_check.yaml

# Model
olmo_model_id: "allenai/OLMo-2-0425-1B"
qwen_model_id: "Qwen/Qwen3-Embedding-0.6B"

# Predictor
predictor_hidden_dim: 1024
predictor_rank: 32
cascading_gate_k: 5.0
input_norm: "none"  # use "none" to verify baseline reproduction

# Data
dataset: "allenai/dolma"
dataset_name: "v1_7"
seq_len: 1024
batch_size: 4
micro_batch_size: 2  # gradient accumulation: effective batch=4, micro=2
qwen_input_prefix: ""

# Eval
eval_skip: 10000  # reduced for sanity check (1M too slow for streaming)
eval_size: 50     # small eval set for sanity check

# Training
total_steps: 1000
lr: 3e-4
weight_decay: 0.01
optimizer: "adamw"

# Schedules
tau_init: 5.0
tau_final: 0.2
tau_schedule: "cosine"
lambda_max: 0.0  # no sparsity for sanity check
lambda_warmup_frac: 0.2

# Logging
wandb_project: "dagformer"
wandb_run_name: "sanity-check"
log_every: 10
eval_every: 100

# Checkpointing
save_every: 500
save_dir: "checkpoints/"

# Hardware
num_gpus: 1