-
Add graphgpo_belief_skip_text_rich qwen2.5_7b global_step_150
-
add graphgpo_text/qwen2.5_7b/global_step_150 (text observation_mode run)
-
add graphgpo/qwen2.5_7b/global_step_150
-
add graphgpo/qwen2.5_7b/global_step_100
-
add rewardflow/qwen2.5_7b/global_step_150
-
add rewardflow/qwen2.5_7b/global_step_100
-
add grpo/qwen2.5_7b/global_step_150
-
add grpo/qwen2.5_7b/global_step_100
-
add gigpo/qwen2.5_7b/global_step_150
-
add gigpo/qwen2.5_7b/global_step_100
-
Add rewardflow/qwen2.5_1.5b/global_step_150 (webshop, seed0)
-
Add rewardflow/qwen2.5_1.5b/global_step_100 (webshop, seed0)
-
Add grpo/qwen2.5_1.5b/global_step_150 (webshop, seed0)
-
Add grpo/qwen2.5_1.5b/global_step_100 (webshop, seed0)
-
Add gigpo/qwen2.5_1.5b/global_step_150 (webshop, seed0)
-
Add gigpo/qwen2.5_1.5b/global_step_100 (webshop, seed0)
-
Add graphgpo/qwen2.5_1.5b/global_step_150 (webshop, seed0)
-
Add graphgpo/qwen2.5_1.5b/global_step_100 (webshop, seed0)
-
initial commit