Skip to main content
nomoreactimel
Log in
Sign up
Sergey Sedov
nomoreactimel
Higher School of Economics
Profile
Activity
Mon
Wed
Fri
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Runs
1-10
of 100
Name
Project
State
Created
ppo-Qw3-0.6B-LoRA-bs16-64
cot-cl-rl
Finished
3 days ago
ppo-Qw3-0.6B-LoRA-bs16-64
cot-cl-rl
Finished
3 days ago
ppo-Qw3-0.6B-LoRA-bs16-64
cot-cl-rl
Finished
3 days ago
ppo-Qw3-0.6B-LoRA-bs16-64
cot-cl-rl
Finished
3 days ago
ppo-Qw3-0.6B-LoRA-bs16-64
cot-cl-rl
Finished
3 days ago
ppo-Qw3-0.6B-LoRA-sft1e-system-prompts-noeps-kl0.05-bs16-64-a100
cot-cl-rl
Finished
6 days ago
ppo-Qw3-0.6B-LoRA-LengthPenalty-0.2_Clamp-2.0_bs16-64
cot-cl-rl
Finished
6 days ago
ppo-Qw3-0.6B-LoRA_LPen=0.5_W=0.2_Clamp=2.0_bs16-64
cot-cl-rl
Finished
6 days ago
ppo-Qw3-0.6B-LoRA-sft1e-system-prompts-noeps-kl0.05-bs16-64-a100
cot-cl-rl
Finished
6 days ago
ppo-Qw3-0.6B-LoRA-sft1e-system-prompts-noeps-kl0.05-bs16-64
cot-cl-rl
Finished
1 week ago
Loading...