Actions: agentscope-ai/Trinity-RFT
Actions
902 workflow run results
902 workflow run results
weight_decay in OptimizerConfig
unittest
#902:
Issue comment #364 (comment)
created
by
hiyuchang
weight_decay in OptimizerConfig
unittest
#901:
Issue comment #364 (comment)
created
by
hiyuchang
weight_decay in OptimizerConfig
unittest
#900:
Issue comment #364 (comment)
created
by
gemini-code-assist
bot
std_thresholdoption to StepWiseGRPOAdvantageFn, to filter out zero-grad group samples.
unittest
#896:
Issue comment #363 (comment)
created
by
hiyuchang
std_thresholdoption to StepWiseGRPOAdvantageFn, to filter out zero-grad group samples.
unittest
#895:
Issue comment #363 (comment)
created
by
garyzhang99
std_thresholdoption to StepWiseGRPOAdvantageFn, to filter out zero-grad group samples.
unittest
#892:
Issue comment #363 (comment)
created
by
garyzhang99
std_thresholdoption to StepWiseGRPOAdvantageFn, to filter out zero-grad group samples.
unittest
#891:
Issue comment #363 (comment)
created
by
gemini-code-assist
bot