timaeus/rl-lm-pythia160m-formality-neg-beta0-grpo-gs4-tp1-tk0-lr1e-6-bs600-seed2 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-pos-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed3 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-pos-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed2 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-pos-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed1 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-neg-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed2 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-neg-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed3 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-toxicity-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-lr1e-6-bs600-seed1 Updated Jun 30
timaeus/rl-lm-pythia70m-sentiment-pos-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed3 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-sentiment-pos-beta0-grpo-nostd-gs4-tp1-tk0-lr1e-6-bs600-seed2 Updated Jun 30 • 18
timaeus/rl-lm-pythia70m-sentiment-pos-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-lr1e-6-bs600-seed1 Updated Jun 30 • 18