1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_200_more_datatmp10_vllmexp_retest2 Viewer • Updated 5 days ago • 50k • 7
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2__and_7ktype3_loss100_more_datatmp10_vllmexp_retest2 Viewer • Updated 5 days ago • 50k • 8
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2__and_7ktype3_loss250_more_datatmp10_vllmexp_retest2 Viewer • Updated 5 days ago • 50k • 9
1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_250_more_datatmp10_vllmexp_retest2 Viewer • Updated 5 days ago • 50k • 8
1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_150_more_datatmp10_vllmexp_retest2 Viewer • Updated 5 days ago • 50k • 8