| the_pile:subset=Enron Emails,model=microsoft_TNLGv2_7B | language_modeling |
| the_pile:subset=Enron Emails,model=openai_ada | language_modeling |
| the_pile:subset=Enron Emails,model=openai_babbage | language_modeling |
| the_pile:subset=Enron Emails,model=openai_curie | language_modeling |
| the_pile:subset=Enron Emails,model=openai_davinci | language_modeling |
| the_pile:subset=Enron Emails,model=openai_text-ada-001 | language_modeling |
| the_pile:subset=Enron Emails,model=openai_text-babbage-001 | language_modeling |
| the_pile:subset=Enron Emails,model=openai_text-curie-001 | language_modeling |
| the_pile:subset=Enron Emails,model=openai_text-davinci-002 | language_modeling |
| the_pile:subset=Enron Emails,model=openai_text-davinci-003 | language_modeling |
| the_pile:subset=Enron Emails,model=together_bloom | language_modeling |
| the_pile:subset=Enron Emails,model=together_gpt-j-6b | language_modeling |
| the_pile:subset=Enron Emails,model=together_gpt-neox-20b | language_modeling |
| the_pile:subset=Enron Emails,model=together_opt-175b | language_modeling |
| the_pile:subset=Enron Emails,model=together_opt-66b | language_modeling |
| the_pile:subset=Enron Emails,model=together_redpajama-incite-base-3b-v1 | language_modeling |
| the_pile:subset=Github,model=ai21_j1-grande | language_modeling |
| the_pile:subset=Github,model=ai21_j1-grande-v2-beta | language_modeling |
| the_pile:subset=Github,model=ai21_j1-jumbo | language_modeling |
| the_pile:subset=Github,model=ai21_j1-large | language_modeling |
| the_pile:subset=Github,model=ai21_j2-grande | language_modeling |
| the_pile:subset=Github,model=ai21_j2-jumbo | language_modeling |
| the_pile:subset=Github,model=ai21_j2-large | language_modeling |
| the_pile:subset=Github,model=anthropic_stanford-online-all-v4-s3 | language_modeling |
| the_pile:subset=Github,model=microsoft_TNLGv2_530B | language_modeling |
| the_pile:subset=Github,model=microsoft_TNLGv2_7B | language_modeling |
| the_pile:subset=Github,model=openai_ada | language_modeling |
| the_pile:subset=Github,model=openai_babbage | language_modeling |
| the_pile:subset=Github,model=openai_curie | language_modeling |
| the_pile:subset=Github,model=openai_davinci | language_modeling |
| the_pile:subset=Github,model=openai_text-ada-001 | language_modeling |
| the_pile:subset=Github,model=openai_text-babbage-001 | language_modeling |
| the_pile:subset=Github,model=openai_text-curie-001 | language_modeling |
| the_pile:subset=Github,model=openai_text-davinci-002 | language_modeling |
| the_pile:subset=Github,model=openai_text-davinci-003 | language_modeling |
| the_pile:subset=Github,model=together_bloom | language_modeling |
| the_pile:subset=Github,model=together_gpt-j-6b | language_modeling |
| the_pile:subset=Github,model=together_gpt-neox-20b | language_modeling |
| the_pile:subset=Github,model=together_opt-175b | language_modeling |
| the_pile:subset=Github,model=together_opt-66b | language_modeling |
| the_pile:subset=Github,model=together_redpajama-incite-base-3b-v1 | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j1-grande | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j1-grande-v2-beta | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j1-jumbo | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j1-large | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j2-grande | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j2-jumbo | language_modeling |
| the_pile:subset=PubMed Central,model=ai21_j2-large | language_modeling |
| the_pile:subset=PubMed Central,model=anthropic_stanford-online-all-v4-s3 | language_modeling |
| the_pile:subset=PubMed Central,model=microsoft_TNLGv2_530B | language_modeling |
| the_pile:subset=PubMed Central,model=microsoft_TNLGv2_7B | language_modeling |
| the_pile:subset=PubMed Central,model=openai_ada | language_modeling |
| the_pile:subset=PubMed Central,model=openai_babbage | language_modeling |
| the_pile:subset=PubMed Central,model=openai_curie | language_modeling |
| the_pile:subset=PubMed Central,model=openai_davinci | language_modeling |
| the_pile:subset=PubMed Central,model=openai_text-ada-001 | language_modeling |
| the_pile:subset=PubMed Central,model=openai_text-babbage-001 | language_modeling |
| the_pile:subset=PubMed Central,model=openai_text-curie-001 | language_modeling |
| the_pile:subset=PubMed Central,model=openai_text-davinci-002 | language_modeling |
| the_pile:subset=PubMed Central,model=openai_text-davinci-003 | language_modeling |
| the_pile:subset=PubMed Central,model=together_bloom | language_modeling |
| the_pile:subset=PubMed Central,model=together_gpt-j-6b | language_modeling |
| the_pile:subset=PubMed Central,model=together_gpt-neox-20b | language_modeling |
| the_pile:subset=PubMed Central,model=together_opt-175b | language_modeling |
| the_pile:subset=PubMed Central,model=together_opt-66b | language_modeling |
| the_pile:subset=PubMed Central,model=together_redpajama-incite-base-3b-v1 | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j1-grande | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j1-grande-v2-beta | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j1-jumbo | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j1-large | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j2-grande | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j2-jumbo | language_modeling |
| the_pile:subset=Wikipedia (en),model=ai21_j2-large | language_modeling |
| the_pile:subset=Wikipedia (en),model=anthropic_stanford-online-all-v4-s3 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_command-medium-beta | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_command-xlarge-beta | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_large-20220720 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_medium-20220720 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_medium-20221108 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_small-20220720 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_xlarge-20220609 | language_modeling |
| the_pile:subset=Wikipedia (en),model=cohere_xlarge-20221108 | language_modeling |
| the_pile:subset=Wikipedia (en),model=microsoft_TNLGv2_530B | language_modeling |
| the_pile:subset=Wikipedia (en),model=microsoft_TNLGv2_7B | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_ada | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_babbage | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_curie | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_davinci | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_text-ada-001 | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_text-babbage-001 | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_text-curie-001 | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_text-davinci-002 | language_modeling |
| the_pile:subset=Wikipedia (en),model=openai_text-davinci-003 | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_bloom | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_gpt-j-6b | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_gpt-neox-20b | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_opt-175b | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_opt-66b | language_modeling |
| the_pile:subset=Wikipedia (en),model=together_redpajama-incite-base-3b-v1 | language_modeling |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=AlephAlpha_luminous-base,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=AlephAlpha_luminous-extended,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=AlephAlpha_luminous-supreme,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j1-grande,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j1-grande-v2-beta,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j1-jumbo,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j1-large,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j2-grande,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j2-jumbo,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=ai21_j2-large,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_command-medium-beta,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_command-xlarge-beta,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_large-20220720,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_medium-20220720,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_medium-20221108,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_small-20220720,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_xlarge-20220609,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=cohere_xlarge-20221108,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=microsoft_TNLGv2_530B,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=microsoft_TNLGv2_7B,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_ada,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_babbage,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_curie,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_davinci,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_gpt-3.5-turbo-0301,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_text-ada-001,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_text-babbage-001,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_text-curie-001,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_text-davinci-002,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=openai_text-davinci-003,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_bloom,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_bloom,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_glm,data_augmentation=canonical,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_glm,max_train_instances=0,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-j-6b,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-j-6b,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-neox-20b,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_gpt-neox-20b,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-175b,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-175b,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-66b,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_opt-66b,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_redpajama-incite-base-3b-v1,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_t0pp,data_augmentation=canonical,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_t0pp,max_train_instances=0,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_t5-11b,data_augmentation=canonical,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_t5-11b,max_train_instances=0,stop=hash | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_ul2,data_augmentation=canonical,stop=hash,global_prefix=nlg | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_ul2,max_train_instances=0,stop=hash,global_prefix=nlg | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_yalm,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=together_yalm,max_train_instances=0 | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=writer_palmyra-instruct-30,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_joint,model=writer_palmyra-x,data_augmentation=canonical | multiple_choice_joint |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_calibrated,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_original |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_original |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_original |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_original |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_original |
| truthful_qa:task=mc_single,method=multiple_choice_separate_original,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_original |
| twitter_aae:demographic=aa,model=ai21_j1-grande | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j1-grande-v2-beta | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j1-jumbo | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j1-large | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j2-grande | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j2-jumbo | language_modeling |
| twitter_aae:demographic=aa,model=ai21_j2-large | language_modeling |
| twitter_aae:demographic=aa,model=anthropic_stanford-online-all-v4-s3 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_command-medium-beta | language_modeling |
| twitter_aae:demographic=aa,model=cohere_command-xlarge-beta | language_modeling |
| twitter_aae:demographic=aa,model=cohere_large-20220720 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_medium-20220720 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_medium-20221108 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_small-20220720 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_xlarge-20220609 | language_modeling |
| twitter_aae:demographic=aa,model=cohere_xlarge-20221108 | language_modeling |
| twitter_aae:demographic=aa,model=microsoft_TNLGv2_530B | language_modeling |
| twitter_aae:demographic=aa,model=microsoft_TNLGv2_7B | language_modeling |
| twitter_aae:demographic=aa,model=openai_ada | language_modeling |
| twitter_aae:demographic=aa,model=openai_babbage | language_modeling |
| twitter_aae:demographic=aa,model=openai_curie | language_modeling |
| twitter_aae:demographic=aa,model=openai_davinci | language_modeling |
| twitter_aae:demographic=aa,model=openai_text-ada-001 | language_modeling |
| twitter_aae:demographic=aa,model=openai_text-babbage-001 | language_modeling |
| twitter_aae:demographic=aa,model=openai_text-curie-001 | language_modeling |
| twitter_aae:demographic=aa,model=openai_text-davinci-002 | language_modeling |
| twitter_aae:demographic=aa,model=openai_text-davinci-003 | language_modeling |
| twitter_aae:demographic=aa,model=together_bloom | language_modeling |