model_id,training_samples,task,metric,value,unit,status aya_300k_lr_0p00010,300000,arc_sk,"acc,none",0.30025662959794697,0..1,reported aya_300k_lr_0p00010,300000,arc_sk,"acc_stderr,none",0.013412022629366669,0..1,reported aya_300k_lr_0p00010,300000,arc_sk,"acc_norm,none",0.3473053892215569,0..1,reported aya_300k_lr_0p00010,300000,arc_sk,"acc_norm_stderr,none",0.013931226499492353,0..1,reported aya_300k_lr_0p00010,300000,hellaswag_sk,"acc,none",0.4083289404322615,0..1,reported aya_300k_lr_0p00010,300000,hellaswag_sk,"acc_stderr,none",0.005047187883274763,0..1,reported aya_300k_lr_0p00010,300000,hellaswag_sk,"acc_norm,none",0.5163943068002108,0..1,reported aya_300k_lr_0p00010,300000,hellaswag_sk,"acc_norm_stderr,none",0.005131456510575215,0..1,reported aya_300k_lr_0p00010,300000,m_mmlu_sk,"acc,none",0.3102893890675241,0..1,reported aya_300k_lr_0p00010,300000,m_mmlu_sk,"acc_stderr,none",0.0040478899905589515,0..1,reported aya_300k_lr_0p00010,300000,sklegal,"acc,none",0.2856071964017991,0..1,reported aya_300k_lr_0p00010,300000,sklegal,"acc_stderr,none",0.012371946515772182,0..1,reported aya_300k_lr_0p00010,300000,sklegal,"acc_norm,none",0.46101949025487254,0..1,reported aya_300k_lr_0p00010,300000,sklegal,"acc_norm_stderr,none",0.013653094581189941,0..1,reported aya_300k_lr_0p00010,300000,skquad,"exact,none",15.120525931336742,0..100,reported aya_300k_lr_0p00010,300000,skquad,"exact_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"f1,none",38.72920807013749,0..100,reported aya_300k_lr_0p00010,300000,skquad,"f1_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"HasAns_exact,none",18.540838569047313,0..100,reported aya_300k_lr_0p00010,300000,skquad,"HasAns_exact_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"HasAns_f1,none",47.549942420326644,0..100,reported aya_300k_lr_0p00010,300000,skquad,"HasAns_f1_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"NoAns_exact,none",0.1681614349775785,0..100,reported aya_300k_lr_0p00010,300000,skquad,"NoAns_exact_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"NoAns_f1,none",0.1681614349775785,0..100,reported aya_300k_lr_0p00010,300000,skquad,"NoAns_f1_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"best_exact,none",18.75195658979443,0..100,reported aya_300k_lr_0p00010,300000,skquad,"best_exact_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,skquad,"best_f1,none",38.7292080701372,0..100,reported aya_300k_lr_0p00010,300000,skquad,"best_f1_stderr,none",N/A,0..100,unavailable aya_300k_lr_0p00010,300000,truthfulqa_sk_mc1,"acc,none",0.19665809768637532,0..1,reported aya_300k_lr_0p00010,300000,truthfulqa_sk_mc1,"acc_stderr,none",0.014259215011433178,0..1,reported aya_300k_lr_0p00010,300000,truthfulqa_sk_mc2,"acc,none",0.3506542164316134,0..1,reported aya_300k_lr_0p00010,300000,truthfulqa_sk_mc2,"acc_stderr,none",0.014662940445997986,0..1,reported