mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.00
Updated
•
37
Correct-DPO Evaluations
Evaluations of Correct-DPO Experiments
-
-
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.00
Updated • 37 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.10
Updated • 36 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.20
Updated • 39 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.30
Updated • 39 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.10
Updated • 40 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.00
Updated • 37 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.20
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.00
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.10
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.00
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.20
Updated • 32 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.10
Updated • 32 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.30
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.10
Updated • 32 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.00
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.20
Updated • 38 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.30
Updated • 32 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.10
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.20
Updated • 40 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.00
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.00
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.30
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.10
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.00
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.10
Updated • 39 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.20
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.20
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.30
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.20
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.30
Updated • 37 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.00
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.10
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.20
Updated • 35 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.10
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.00
Updated • 37 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.20
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.30
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.00
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.30
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.10
Updated • 37 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.50
Updated • 39 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.00
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.40
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.30
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.20
Updated • 32 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.10
Updated • 42 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.10
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.10
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.50
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.40
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.40
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.20
Updated • 38 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.30
Updated • 36 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.20
Updated • 35 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.50
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.40
Updated • 37 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.30
Updated • 32 -
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.40
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.30
Updated • 35 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.30
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.00
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.40
Updated • 35 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.30
Updated • 37 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.40
Updated • 35 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.40
Updated • 34 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.40
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.40
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.50
Updated • 34 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.50
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.50
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.50
Updated • 33 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.40
Updated • 36 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.40
Updated • 33 -
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.50
Updated • 34 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.50
Updated • 38 -
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.50
Updated • 35 -
mcding-org/CorrectDPO-Eval-DPO_Pm3B_U0_beta0.10
Updated • 34 -
mcding-org/CorrectDPO-Eval-DDP_Pm3B_U0_beta0.10r0.30rho0.20
Updated • 36 -
mcding-org/CorrectDPO-Eval-DPO_L8B_U0_beta0.10
Updated • 34 -
mcding-org/CorrectDPO-Eval-DDP_L8B_U0_beta0.10r0.30rho0.20
Updated • 34