tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_ver2_400tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixed_beta01_llama3_sft_math_type12_8ktype4_and_8ktype3_no_sft_loss400tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_ver2_300tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_beta01_llama3_sft_math_type12_8ktype4_and_8ktype3_no_sft_loss300tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_ver2_200tmp10 Viewer • Updated Jan 15 • 5k • 4
tmpmodelsave/fixed_beta01_llama3_sft_math_type12_8ktype4_and_8ktype3_no_sft_loss200tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_ver2_100tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_beta01_llama3_sft_math_type12_8ktype4_and_8ktype3_no_sft_loss100tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss900tmp10 Viewer • Updated Jan 15 • 5k • 4
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_800tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss800tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_600tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss700tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_500tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss600tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_700tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss500tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_400tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss400tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_300tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss300tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_200tmp10 Viewer • Updated Jan 15 • 5k • 1
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss200tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_no_sft_llama3_sft_math_dpo_type12_8ktype4_4ktype3_ver2_100tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/fixed_llama3_sft_math_type12_8ktype4_and_7ktype3_no_sft_loss100tmp10 Viewer • Updated Jan 15 • 5k • 3
tmpmodelsave/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_600tmp10 Viewer • Updated Jan 15 • 5k • 2
tmpmodelsave/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_550tmp10 Viewer • Updated Jan 15 • 5k • 3