mxcui/sumgrad-imdb-ppo-prop0.2-alpha1.2-seed42-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 99
mxcui/sumgrad-imdb-ppo-prop0.2-alpha1.3-seed42-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 137
mxcui/vanilla-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 114
mxcui/vanilla-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 123
mxcui/maxmin-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 119
mxcui/pcgrad-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 125
mxcui/maxmin-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 129
mxcui/pcgrad-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 115
mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base Text Generation • 4B • Updated Jul 12 • 80
mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base Text Generation • 4B • Updated Jul 12 • 90
mxcui/maxmin-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base Text Generation • 4B • Updated Jul 12 • 78 • 1
mxcui/maxmin-imdb-ppo-prop0.3-alpha1.0-seed44-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 11 • 136
mxcui/vanilla-deconflict-win1_400-imdb-ppo-prop0.2-alpha0.7-seed42-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 12 • 64
mxcui/vanilla-deconflict-win400_800-imdb-ppo-prop0.2-alpha0.7-seed42-mean_kl0.1-gpt2 Text Generation • 0.1B • Updated Jul 12 • 77
mxcui/maxmin-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m Text Generation • 0.2B • Updated Jul 12 • 81
mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m Text Generation • 0.2B • Updated Jul 12 • 73
mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m Text Generation • 0.2B • Updated Jul 12 • 83
mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5 Text Generation • 0.2B • Updated Jul 12 • 84
mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5 Text Generation • 0.2B • Updated Jul 12 • 80
mxcui/maxmin-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5 Text Generation • 0.2B • Updated Jul 12 • 83
mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-kl0.15-EleutherAI-pythia-160m-lr7e-6 Text Generation • 0.2B • Updated Jul 12 • 89