FRPO/qwen3-4b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n4 Text Generation • 4B • Updated Aug 15 • 156
FRPO/qwen3-4b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n4 Text Generation • 4B • Updated Aug 15 • 151
FRPO/qwen3-4b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n4 Text Generation • 4B • Updated Aug 15 • 151
FRPO/qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.35-mb4-eta100-bs256x5-n2-r3 Text Generation • 2B • Updated Aug 15 • 151
FRPO/qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r3 Text Generation • 2B • Updated Aug 15 • 128
FRPO/qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r2 Text Generation • 2B • Updated Aug 15 • 150
FRPO/qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2-mb4-eta100-bs256x5-n2-r3 Text Generation • 2B • Updated Aug 15 • 153
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef1e-4-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 148
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef1e-3-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 137
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef1e-2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 143
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef1.0-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 119
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef0.5-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 143
FRPO/qwen3-1.7b-a8_klreward-krew-k1-coef0.1-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 146
FRPO/qwen3-1.7b-a7_current_kl-curKL-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 148
FRPO/qwen3-1.7b-a6_k3_center-k3-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 143
FRPO/qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 105
FRPO/qwen3-1.7b-a3_onpolicy-k1-cNone-clip0.2-mb1-eta100-bs64x5-n2-s800 Text Generation • 2B • Updated Aug 15 • 134
FRPO/qwen3-1.7b-a3_onpolicy-k1-cNone-clip0.2-mb1-eta100-bs256x5-n2-s800 Text Generation • 2B • Updated Aug 15 • 151
FRPO/qwen3-1.7b-a3_onpolicy-k1-cNone-clip0.2-mb1-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 138
FRPO/qwen3-1.7b-a2_noclip-k1-cNone-clipInf-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 117
FRPO/qwen3-1.7b-a20_seqmean_center_16k-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 110
FRPO/qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2 Text Generation • 2B • Updated Aug 15 • 119
FRPO/qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed1 Text Generation • 2B • Updated Aug 15 • 104
FRPO/qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 121
FRPO/qwen3-1.7b-a19_seqmean_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 93
FRPO/qwen3-1.7b-a18_onpolicy_seqmean_center-k1-cGroupBoth-clip0.2-mb1-eta100-bs64x5-n2 Text Generation • 2B • Updated Aug 15 • 90
FRPO/qwen3-1.7b-a16_onpolicy_seqmean-k1-cNone-clip0.2-mb1-eta100-bs64x5-n2 Text Generation • 2B • Updated Aug 15 • 100
FRPO/qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed2 Text Generation • 2B • Updated Aug 15 • 92
FRPO/qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed1 Text Generation • 2B • Updated Aug 15 • 96
FRPO/qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2 Text Generation • 2B • Updated Aug 15 • 91