Revisiting Generalization Across Difficulty Levels: It's Not So Easy Paper • 2511.21692 • Published Nov 26 • 15
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-False Text Generation • 2B • Updated Sep 25 • 9
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-False Text Generation • 2B • Updated Sep 25 • 9
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-True Text Generation • 2B • Updated Sep 25 • 7
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-True Text Generation • 2B • Updated Sep 25 • 7
atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False Text Generation • 2B • Updated Sep 25 • 9
atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False Text Generation • 2B • Updated Sep 25 • 9
atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-True Text Generation • 2B • Updated Sep 25 • 11
atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-True Text Generation • 2B • Updated Sep 25 • 11
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-False Text Generation • 2B • Updated Sep 25 • 8
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-False Text Generation • 2B • Updated Sep 25 • 8
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-True Text Generation • 2B • Updated Sep 25 • 8
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-True Text Generation • 2B • Updated Sep 25 • 8
atrost/math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-False Text Generation • 2B • Updated Sep 25 • 11
atrost/math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-False Text Generation • 2B • Updated Sep 25 • 11
atrost/math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-True Text Generation • 2B • Updated Sep 25 • 4