-
upload iter_000 traj_to_sft/sft_data
-
upload rollout_data score>1 summary (iter_001)
-
upload rollout_data filtered to score>1 (iter_001)
-
Delete post_reasoning_training/iter_001
-
upload post_reasoning_training/iter_000/sft/sft_model
-
upload post_reasoning_training/iter_000/rl/rollout_data
-
upload post_reasoning_training/iter_001/sft/sft_model
-
upload post_reasoning_training/iter_001/rl/rl_model
-
upload post_reasoning_training/iter_000/sft/sft_model
-
upload post_reasoning_training/iter_001/sft/sft_model
-
upload post_reasoning_training/iter_001/rl/rl_model
-
upload post_reasoning_training/iter_000/rl/rollout_data
-
upload post_reasoning_training/iter_000/sft/sft_model
-
upload post_reasoning_training/iter_000/rl/rl_model