trinity.algorithm.policy_loss_fn.gspo_policy_loss module

GSPO-token policy loss function.

Implemented from https://arxiv.org/pdf/2507.18071

class trinity.algorithm.policy_loss_fn.gspo_policy_loss.GSPOLossFn(backend: str = 'verl', clip_range: float | None = None, clip_range_low: float | None = None, clip_range_high: float | None = None)[source]

Bases: PolicyLossFn

__init__(backend: str = 'verl', clip_range: float | None = None, clip_range_low: float | None = None, clip_range_high: float | None = None) → None[source]

Initialize the policy loss function.

Parameters:: backend – The training framework/backend to use (e.g., “verl”)

classmethod default_args() → Dict[source]

Get default initialization arguments for this loss function.

Returns:: The default init arguments for the policy loss function.
Return type:: Dict

property select_keys: Returns parameter keys mapped to the specific training framework’s naming convention.