yunjae-won/qwen1.7b_clip1e-6_base_step150
Text Generation • 2B • Updated • 7
On-Policy Distillation Analysis
.
-
-
yunjae-won/qwen1.7b_clip1e-6_base_step125
Text Generation • 2B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step75
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step100
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step175
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step200
Text Generation • 4B • Updated • 6 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step150
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step125
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step75
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step100
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step175
Text Generation • 4B • Updated • 11 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step200
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.25_step25
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step150
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step125
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step75
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step100
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step175
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step200
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg1_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step150
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step125
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step75
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step50
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step100
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step175
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step200
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg2_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step150
Text Generation • 4B • Updated • 6 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step125
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step75
Text Generation • 4B • Updated • 11 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step50
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step100
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step175
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step200
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg4_step25
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step150
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step125
Text Generation • 4B • Updated • 11 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step75
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step100
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step175
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step200
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.5_step25
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step150
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step125
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step75
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step100
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step175
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step200
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg0.25_step25
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step150
Text Generation • 4B • Updated • 6 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step125
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step75
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step100
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step175
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step200
Text Generation • 4B • Updated • 11 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg1_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step150
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step125
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step75
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step50
Text Generation • 4B • Updated • 6 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step100
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step175
Text Generation • 4B • Updated • 9 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step200
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg2_step25
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step150
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step125
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step50
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step100
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step175
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step200
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_adaKL_reg4_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step150
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step125
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step75
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step50
Text Generation • 4B • Updated • 8 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step100
Text Generation • 4B • Updated • 10 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step175
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step200
Text Generation • 4B • Updated • 7 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_step25
Text Generation • 4B • Updated • 8 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-25
Text Generation • 4B • Updated • 405 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-25
Text Generation • 4B • Updated • 493 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-50
Text Generation • 4B • Updated • 396 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-50
Text Generation • 4B • Updated • 463 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-75
Text Generation • 4B • Updated • 451 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-75
Text Generation • 4B • Updated • 401 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-100
Text Generation • 4B • Updated • 451 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-25
Text Generation • 4B • Updated • 430 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-25
Text Generation • 4B • Updated • 362 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-50
Text Generation • 4B • Updated • 442 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-75
Text Generation • 4B • Updated • 349 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-100
Text Generation • 4B • Updated • 315 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175
Text Generation • 4B • Updated • 296 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-125
Text Generation • 4B • Updated • 402 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-150
Text Generation • 4B • Updated • 406 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-175
Text Generation • 4B • Updated • 399 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-200
Text Generation • 4B • Updated • 403 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-100
Text Generation • 4B • Updated • 235 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-125
Text Generation • 4B • Updated • 216 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-150
Text Generation • 4B • Updated • 223 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-175
Text Generation • 4B • Updated • 226 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-200
Text Generation • 4B • Updated • 214 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-50
Text Generation • 4B • Updated • 181 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-125
Text Generation • 4B • Updated • 164 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150
Text Generation • 4B • Updated • 192 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200
Text Generation • 4B • Updated • 164 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-75
Text Generation • 4B • Updated • 249 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-100
Text Generation • 4B • Updated • 241 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-125
Text Generation • 4B • Updated • 249 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-150
Text Generation • 4B • Updated • 258 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-175
Text Generation • 4B • Updated • 255 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-200
Text Generation • 4B • Updated • 251 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-25
Text Generation • 4B • Updated • 256 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-50
Text Generation • 4B • Updated • 294 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-75
Text Generation • 4B • Updated • 294 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-100
Text Generation • 4B • Updated • 311 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-125
Text Generation • 4B • Updated • 297 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-150
Text Generation • 4B • Updated • 319 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-175
Text Generation • 4B • Updated • 303 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-200
Text Generation • 4B • Updated • 304 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-25
Text Generation • 4B • Updated • 314 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-50
Text Generation • 4B • Updated • 348 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-75
Text Generation • 4B • Updated • 313 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-100
Text Generation • 4B • Updated • 308 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-125
Text Generation • 4B • Updated • 315 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-150
Text Generation • 4B • Updated • 351 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-175
Text Generation • 4B • Updated • 360 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-200
Text Generation • 4B • Updated • 362 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-25
Text Generation • 4B • Updated • 318 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-50
Text Generation • 4B • Updated • 347 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-100
Text Generation • 4B • Updated • 355 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-125
Text Generation • 4B • Updated • 373 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-150
Text Generation • 4B • Updated • 372 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-175
Text Generation • 4B • Updated • 379 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-200
Text Generation • 4B • Updated • 376 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-25
Text Generation • 4B • Updated • 363 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-50
Text Generation • 4B • Updated • 378 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-75
Text Generation • 4B • Updated • 402 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-100
Text Generation • 4B • Updated • 382 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-150
Text Generation • 4B • Updated • 384 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-175
Text Generation • 4B • Updated • 384 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.5_checkpoint-200
Text Generation • 4B • Updated • 386 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-25
Text Generation • 4B • Updated • 378 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-50
Text Generation • 4B • Updated • 373 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-75
Text Generation • 4B • Updated • 403 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-100
Text Generation • 4B • Updated • 384 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-125
Text Generation • 4B • Updated • 404 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-150
Text Generation • 4B • Updated • 410 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-175
Text Generation • 4B • Updated • 393 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-200
Text Generation • 4B • Updated • 408 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-25
Text Generation • 4B • Updated • 399 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-50
Text Generation • 4B • Updated • 401 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-75
Text Generation • 4B • Updated • 398 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-100
Text Generation • 4B • Updated • 408 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-125
Text Generation • 4B • Updated • 398 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-150
Text Generation • 4B • Updated • 422 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-175
Text Generation • 4B • Updated • 399 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-200
Text Generation • 4B • Updated • 405 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-25
Text Generation • 4B • Updated • 403 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-50
Text Generation • 4B • Updated • 396 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-75
Text Generation • 4B • Updated • 407 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-100
Text Generation • 4B • Updated • 401 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-125
Text Generation • 4B • Updated • 417 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-150
Text Generation • 4B • Updated • 446 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-175
Text Generation • 4B • Updated • 449 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-200
Text Generation • 4B • Updated • 446 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.5_checkpoint-25
Text Generation • 4B • Updated • 465 -
yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.5_checkpoint-50
Text Generation • 4B • Updated • 459