violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_epoch0 Text Generation • Updated 17 days ago • 60
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_checkpoint12000 Text Generation • Updated 17 days ago • 8
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_checkpoint6000 Text Generation • Updated 18 days ago • 8
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_checkpoint12000 Text Generation • Updated 18 days ago • 7
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_checkpoint11400 Text Generation • Updated 18 days ago • 5
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_checkpoint10800 Text Generation • Updated 18 days ago • 5
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_checkpoint10200 Text Generation • Updated 18 days ago • 6
violetxi/PRM-ak-prm-sub500_sft-steptok-MATH-500_L5_beam_N128_B16_D40_T0.0001_0-134 Updated 13 minutes ago • 12
violetxi/PRM-ak-prm-sub500_sft-steptok-MATH-500_L4_beam_N128_B16_D40_T0.0001_0-128 Viewer • Updated about 3 hours ago • 21 • 27
violetxi/PRM-ak-prm-sub3k_sft-steptok-MATH-500_L1_beam_N128_B16_D40_T0.0001_0-43 Viewer • Updated about 4 hours ago • 1 • 2
violetxi/PRM-ak-prm-sub3k_sft-steptok-MATH-500_L2_beam_N128_B16_D40_T0.0001_0-90 Viewer • Updated about 4 hours ago • 1 • 2
violetxi/PRM-ak-prm-sub3k_sft-steptok-MATH-500_L3_beam_N128_B16_D40_T0.0001_0-105 Viewer • Updated about 8 hours ago • 1 • 2
violetxi/PRM-ak-prm-sub500_sft-steptok-MATH-500_L3_beam_N128_B16_D40_T0.0001_0-105 Updated about 8 hours ago • 17
violetxi/PRM-ak-prm-sub3k_sft-steptok-MATH-500_L4_beam_N128_B16_D40_T0.0001_0-128 Viewer • Updated about 9 hours ago • 1 • 26
violetxi/PRM-ak-prm-sub3k_sft-steptok-MATH-500_L5_beam_N128_B64_D40_T0.0001_0-134 Updated about 10 hours ago • 12
violetxi/PRM-ak-prm-sub500_sft-steptok-MATH-500_L2_beam_N128_B16_D40_T0.0001_0-90 Updated about 13 hours ago • 20