yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step150 Text Generation • 4B • Updated 6 days ago • 26
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step125 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step100 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step75 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step50 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step25 Text Generation • 4B • Updated 6 days ago • 25
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step150 Text Generation • 4B • Updated 6 days ago • 25
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step150 Text Generation • 4B • Updated 6 days ago • 25
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step125 Text Generation • 4B • Updated 6 days ago • 21
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step125 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step100 Text Generation • 4B • Updated 6 days ago • 22
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step100 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step75 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step75 Text Generation • 4B • Updated 6 days ago • 17
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step150 Text Generation • 4B • Updated 6 days ago • 19
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step50 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step50 Text Generation • 4B • Updated 6 days ago • 18
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step125 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step25 Text Generation • 4B • Updated 6 days ago • 16
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step25 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step100 Text Generation • 4B • Updated 6 days ago • 25
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg2_step150 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg0.5_step150 Text Generation • 4B • Updated 6 days ago • 17
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step75 Text Generation • 4B • Updated 6 days ago • 22
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg2_step125 Text Generation • 4B • Updated 6 days ago • 22
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg0.5_step125 Text Generation • 4B • Updated 6 days ago • 23
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step50 Text Generation • 4B • Updated 6 days ago • 24
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg2_step100 Text Generation • 4B • Updated 6 days ago • 20
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg0.5_step100 Text Generation • 4B • Updated 6 days ago • 25
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_adaKL_reg2_step25 Text Generation • 4B • Updated 6 days ago • 25