weqweasdas/fixed05_llasft_math_7ktype2_7ktype3_ver2_150_tmp10_generation_with_rewards Viewer • Updated Jan 19 • 30k • 5
weqweasdas/fixed05_llasft_math_3ktype2_7ktype3_ver2_250_tmp10_generation_with_rewards Viewer • Updated Jan 17 • 50k • 5
weqweasdas/fixed05_llasft_math_3ktype2_7ktype3_ver2_250_more_datatmp10_vllmexp_retest2_generation Viewer • Updated Jan 17 • 50k • 5
weqweasdas/fixed05_llasft_math_3ktype2_7ktype3_ver2_100_tmp10_generation_with_rewards Viewer • Updated Jan 16 • 50k • 4
weqweasdas/fixed05_llasft_math_3ktype2_7ktype3_ver2_100_more_datatmp10_vllmexp_retest2_generation Viewer • Updated Jan 16 • 50k • 5
weqweasdas/fixed05_llasft_math_7ktype2_7ktype3_ver2_250_tmp10_generation_with_rewards Viewer • Updated Jan 16 • 50k • 6
weqweasdas/fixed05_llasft_math_7ktype2_7ktype3_ver2_250_more_datatmp10_vllmexp_retest2_generation Viewer • Updated Jan 16 • 50k • 4
weqweasdas/fixed05_llasft_math_7ktype2_7ktype3_ver2_150_more_datatmp10_vllmexp_retest2_generation Viewer • Updated Jan 16 • 50k • 5
weqweasdas/llama3_openmath_em_ep1_tmp07_with_lesscorr_orm_rewards_vllmexp Viewer • Updated Jan 7 • 5k • 6
weqweasdas/llama3_openmath_em_ep1_tmp10_with_lesscorr_orm_rewards_vllmexp Viewer • Updated Jan 7 • 5k • 5
weqweasdas/llama3_sft_balanced_rr60k_train_on_corr_ep3_full_testtmp07_vllmexp Viewer • Updated Jan 7 • 15k • 4
weqweasdas/llama3_sft_balanced_rr60k_train_on_corr_ep3_full_testtmp10_vllmexp Viewer • Updated Jan 7 • 15k • 4
weqweasdas/llama3_non_delete_rr40k_2e6_bz32_ep3tmp10_temp_exp_genbytmp0_3 Viewer • Updated Jan 6 • 5k • 4
weqweasdas/llama3_non_delete_rr40k_2e6_bz32_ep3tmp10_temp_exp_genbytmp0_2 Viewer • Updated Jan 6 • 5k • 4
weqweasdas/llama3_non_delete_rr40k_2e6_bz32_ep3tmp10_temp_exp_genbytmp07 Viewer • Updated Jan 6 • 5k • 4
weqweasdas/llama3_non_delete_rr40k_2e6_bz32_ep3tmp10_temp_exp_genbytmp0 Viewer • Updated Jan 6 • 5k • 4