GRPOMetric

from twinkle.metric import GRPOMetric

metric = GRPOMetric(
    device_mesh=device_mesh,
    process_group=process_group,
    epsilon=0.2,          # PPO clip range
    temperature=1.0,      # Sampling temperature for logp rescaling
    top_k_kl=10,          # Track top-K high-KL tokens per step
)

# During training loop
metric.accumulate(inputs, outputs, old_logps=old_logps, advantages=advantages)

# At log interval
results = metric.calculate()
# results: {
#   'train/policy_confidence': 0.85,
#   'train/mean_new_logp': -1.23,
#   'train/mean_old_logp': -1.30,
#   'train/logp_diff_mean': 0.07,
#   'train/approx_kl': 0.003,
#   'train/token_kl_max': 0.15,
#   'train/entropy': 2.1,
#   'train/clip_ratio': 0.02,
#   'train/clip_ratio_low': 0.01,
#   'train/clip_ratio_high': 0.01,
# }