tmpmodelsave/nosft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_4k_100tmp07 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/nosft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_4k_100tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/nosft_llama3_morecorr_sft_4dpo_type12_4k_type3_8k_type4_step200tmp07 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/no_sft_llama3_morecorr_sft_4dpo_type12_6k_type3_8k_type4_step200tmp07 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/nosft_llama3_morecorr_sft_4dpo_type12_4k_type3_8k_type4_step200tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/no_sft_llama3_morecorr_sft_4dpo_type12_6k_type3_8k_type4_step200tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_400tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_350tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_300tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_250tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_200tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/llama3_sft_math_only_4ktype4_and_8ktype3_no_sft_loss150tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_150tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/llama3_sft_math_only_4ktype4_and_8ktype3_no_sft_loss100tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_4k_100tmp10 Viewer • Updated Jan 14 • 5k • 3
tmpmodelsave/llama3_sft_math_only_4ktype4_and_8ktype3_no_sft_loss50tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_beta05_100tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_beta05_200tmp10 Viewer • Updated Jan 14 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_beta05_150tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_250tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_200tmp10 Viewer • Updated Jan 14 • 5k • 1
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_150tmp10 Viewer • Updated Jan 13 • 5k • 2
tmpmodelsave/real_llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_100tmp10 Viewer • Updated Jan 13 • 5k • 2
tmpmodelsave/llama3_sft_math_dpo_type12_4ktype4_8ktype3_new_200tmp10 Viewer • Updated Jan 13 • 5k • 2