Ctrl+K
- balanced-distill-sftlr1e-5-grpo-lr1e-6-kl3e-3-seed1
- balanced-progdistill-sftlr1e-4-seed1
- balanced-progdistill-sftlr1e-5-grpo-lr1e-6-kl3e-4-seed1
- balanced-progdistill-sftlr1e-6-grpo-lr1e-6-kl3e-4-seed1
- balanced-progdistill-sftlr3e-5-grpo-lr1e-6-kl3e-4-seed1
- balanced-progdistill-sftlr3e-6-grpo-lr1e-6-kl3e-4-seed1
- 2.2 kB