timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000sm0.01-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000sm0.001-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000s0.001-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000s0.01-seed1 Updated 18 days ago • 2
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL1c8000s0.1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000sm1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000sm0.01-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000s0.1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000sm0.1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.3-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.3-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.03-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.03-seed1 Updated 18 days ago • 2
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL3c8000sm1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL1c8000s0.01-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL3c8000s0.01-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000sm1-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000sm0.32-seed1 Updated 18 days ago • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000s0.32-seed1 Updated 18 days ago • 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.1-seed1 Updated 18 days ago • 13 • 2
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.002-seed1 Updated 18 days ago • 13
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.1-seed1 Updated 18 days ago • 15 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.002-seed1 Updated 18 days ago • 13
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.0003-seed1 Updated 18 days ago • 13 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.0003-seed1 Updated 18 days ago • 14 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.01-seed1 Updated 18 days ago • 14 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.001-seed1 Updated 18 days ago • 13 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.007-seed1 Updated 18 days ago • 13