1
2
|
deterministic/exact,deterministic/token_acc,fd_lyap,fd_spectrum_k,include_clean,lambda_fail_mean,lambda_mean,lambda_success_mean,lyap_min/exact,lyap_min/token_acc,mean_rollout/exact,mean_rollout/token_acc,n_samples,noise_std,oracle_pass/exact,oracle_pass/token_acc,q_fail_mean,q_max/exact,q_max/token_acc,q_mean,q_minus_0.25lambda/exact,q_minus_0.25lambda/token_acc,q_minus_0.5lambda/exact,q_minus_0.5lambda/token_acc,q_minus_1lambda/exact,q_minus_1lambda/token_acc,q_minus_2lambda/exact,q_minus_2lambda/token_acc,q_success_mean,rollout0/exact,rollout0/token_acc,rollouts,spec_count_pos_fail_mean,spec_count_pos_mean,spec_count_pos_min/exact,spec_count_pos_min/token_acc,spec_count_pos_success_mean,spec_k,spec_mean_fail_mean,spec_mean_mean,spec_mean_min/exact,spec_mean_min/token_acc,spec_mean_success_mean,spec_pos_l2_mean,spec_pos_l2_min/exact,spec_pos_l2_min/token_acc,spec_pos_mass_fail_mean,spec_pos_mass_mean,spec_pos_mass_min/exact,spec_pos_mass_min/token_acc,spec_pos_mass_success_mean,spec_spread_mean,spec_spread_min/exact,spec_spread_min/token_acc
0.828125,0.9336420297622681,0.0,4.0,0.0,7.07891321182251,5.869143009185791,5.692605972290039,0.953125,0.9826388955116272,0.8726562261581421,0.9494907259941101,64.0,0.3,0.953125,0.9841821193695068,-10.772948265075684,0.953125,0.9814814925193787,5.447077751159668,0.953125,0.9814814925193787,0.953125,0.9814814925193787,0.953125,0.9814814925193787,0.953125,0.9814814925193787,7.8140106201171875,0.84375,0.9394290447235107,100.0,4.0,4.0,0.84375,0.9394290447235107,4.0,4.0,6.798189640045166,5.697390556335449,0.953125,0.9814814925193787,5.536754608154297,5.698462963104248,0.953125,0.9814814925193787,27.192758560180664,22.789562225341797,0.953125,0.9814814925193787,22.147018432617188,0.28217047452926636,0.953125,0.9814814925193787
|