Skip to content

LanguageModelGRPOLossConfig

Module: fast_llm.layers.language_model.loss.config

Variant of: LanguageModelLossConfig — select with type: grpo

Inherits from: LanguageModelLossConfig

Fields

weightcore

Type: float    Default: 1.0

Weight for this loss in the total loss computation.

metricsfeature

Type: GRPOMetricsLevel    Default: "none"

Additional GRPO metrics to log. basic: per-token ratio, KL, and advantage statistics. with_entropy: also log per-token entropy. Not supported with pipeline_parallel > 1.

epsilon_high

Type: float    Default: 0.2

Upper clip parameter for ratio of log probs

epsilon_low

Type: float    Default: 0.2

Lower clip parameter for ratio of log probs

use_tritonexpert

Type: bool or None    Default: None

Enable triton implementation. Default: use if available.