diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json diff --git a/evaluation_l1/anli/dev_r1/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r1/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/anli/dev_r1/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r1/GPT-3_style/results.json diff --git a/evaluation_l1/anli/dev_r1/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r1/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/anli/dev_r1/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r1/MNLI_crowdsource/results.json diff --git a/evaluation_l1/anli/dev_r1/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r1/can_we_infer/results.json similarity index 100% rename from evaluation_l1/anli/dev_r1/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r1/can_we_infer/results.json diff --git a/evaluation_l1/anli/dev_r1/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r1/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/anli/dev_r1/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r1/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/anli/dev_r1/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r1/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/anli/dev_r1/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r1/justified_in_saying/results.json diff --git a/evaluation_l1/anli/dev_r2/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r2/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/anli/dev_r2/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r2/GPT-3_style/results.json diff --git a/evaluation_l1/anli/dev_r2/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r2/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/anli/dev_r2/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r2/MNLI_crowdsource/results.json diff --git a/evaluation_l1/anli/dev_r2/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r2/can_we_infer/results.json similarity index 100% rename from evaluation_l1/anli/dev_r2/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r2/can_we_infer/results.json diff --git a/evaluation_l1/anli/dev_r2/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r2/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/anli/dev_r2/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r2/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/anli/dev_r2/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r2/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/anli/dev_r2/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r2/justified_in_saying/results.json diff --git a/evaluation_l1/anli/dev_r3/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r3/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/anli/dev_r3/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r3/GPT-3_style/results.json diff --git a/evaluation_l1/anli/dev_r3/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r3/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/anli/dev_r3/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r3/MNLI_crowdsource/results.json diff --git a/evaluation_l1/anli/dev_r3/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r3/can_we_infer/results.json similarity index 100% rename from evaluation_l1/anli/dev_r3/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r3/can_we_infer/results.json diff --git a/evaluation_l1/anli/dev_r3/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r3/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/anli/dev_r3/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r3/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/anli/dev_r3/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/anli/dev_r3/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/anli/dev_r3/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/anli/dev_r3/justified_in_saying/results.json diff --git a/evaluation_l1/merged.csv b/evaluation_bloommz/evaluation_l1/merged.csv similarity index 100% rename from evaluation_l1/merged.csv rename to evaluation_bloommz/evaluation_l1/merged.csv diff --git a/evaluation_l1/merged.json b/evaluation_bloommz/evaluation_l1/merged.json similarity index 100% rename from evaluation_l1/merged.json rename to evaluation_bloommz/evaluation_l1/merged.json diff --git a/evaluation_l1/story_cloze/2016/Answer_Given_options/results.json b/evaluation_bloommz/evaluation_l1/story_cloze/2016/Answer_Given_options/results.json similarity index 100% rename from evaluation_l1/story_cloze/2016/Answer_Given_options/results.json rename to evaluation_bloommz/evaluation_l1/story_cloze/2016/Answer_Given_options/results.json diff --git a/evaluation_l1/story_cloze/2016/Choose_Story_Ending/results.json b/evaluation_bloommz/evaluation_l1/story_cloze/2016/Choose_Story_Ending/results.json similarity index 100% rename from evaluation_l1/story_cloze/2016/Choose_Story_Ending/results.json rename to evaluation_bloommz/evaluation_l1/story_cloze/2016/Choose_Story_Ending/results.json diff --git a/evaluation_l1/story_cloze/2016/Generate_Ending/results.json b/evaluation_bloommz/evaluation_l1/story_cloze/2016/Generate_Ending/results.json similarity index 100% rename from evaluation_l1/story_cloze/2016/Generate_Ending/results.json rename to evaluation_bloommz/evaluation_l1/story_cloze/2016/Generate_Ending/results.json diff --git a/evaluation_l1/story_cloze/2016/Novel_Correct_Ending/results.json b/evaluation_bloommz/evaluation_l1/story_cloze/2016/Novel_Correct_Ending/results.json similarity index 100% rename from evaluation_l1/story_cloze/2016/Novel_Correct_Ending/results.json rename to evaluation_bloommz/evaluation_l1/story_cloze/2016/Novel_Correct_Ending/results.json diff --git a/evaluation_l1/story_cloze/2016/Story_Continuation_and_Options/results.json b/evaluation_bloommz/evaluation_l1/story_cloze/2016/Story_Continuation_and_Options/results.json similarity index 100% rename from evaluation_l1/story_cloze/2016/Story_Continuation_and_Options/results.json rename to evaluation_bloommz/evaluation_l1/story_cloze/2016/Story_Continuation_and_Options/results.json diff --git a/evaluation_l1/super_glue/cb/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/super_glue/cb/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/super_glue/cb/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/cb/GPT-3_style/results.json diff --git a/evaluation_l1/super_glue/cb/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/super_glue/cb/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/super_glue/cb/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/cb/MNLI_crowdsource/results.json diff --git a/evaluation_l1/super_glue/cb/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/super_glue/cb/can_we_infer/results.json similarity index 100% rename from evaluation_l1/super_glue/cb/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/cb/can_we_infer/results.json diff --git a/evaluation_l1/super_glue/cb/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/super_glue/cb/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/super_glue/cb/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/cb/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/super_glue/cb/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/super_glue/cb/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/super_glue/cb/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/cb/justified_in_saying/results.json diff --git a/evaluation_l1/super_glue/copa/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/super_glue/copa/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/super_glue/copa/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/copa/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/super_glue/copa/best_option/results.json b/evaluation_bloommz/evaluation_l1/super_glue/copa/best_option/results.json similarity index 100% rename from evaluation_l1/super_glue/copa/best_option/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/copa/best_option/results.json diff --git a/evaluation_l1/super_glue/copa/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/super_glue/copa/cause_effect/results.json similarity index 100% rename from evaluation_l1/super_glue/copa/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/copa/cause_effect/results.json diff --git a/evaluation_l1/super_glue/copa/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/super_glue/copa/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/super_glue/copa/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/copa/i_am_hesitating/results.json diff --git a/evaluation_l1/super_glue/copa/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/super_glue/copa/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/super_glue/copa/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/copa/plausible_alternatives/results.json diff --git a/evaluation_l1/super_glue/rte/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/super_glue/rte/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/super_glue/rte/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/rte/GPT-3_style/results.json diff --git a/evaluation_l1/super_glue/rte/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/super_glue/rte/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/super_glue/rte/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/rte/MNLI_crowdsource/results.json diff --git a/evaluation_l1/super_glue/rte/does_it_follow_that/results.json b/evaluation_bloommz/evaluation_l1/super_glue/rte/does_it_follow_that/results.json similarity index 100% rename from evaluation_l1/super_glue/rte/does_it_follow_that/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/rte/does_it_follow_that/results.json diff --git a/evaluation_l1/super_glue/rte/guaranteed_true/results.json b/evaluation_bloommz/evaluation_l1/super_glue/rte/guaranteed_true/results.json similarity index 100% rename from evaluation_l1/super_glue/rte/guaranteed_true/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/rte/guaranteed_true/results.json diff --git a/evaluation_l1/super_glue/rte/should_assume/results.json b/evaluation_bloommz/evaluation_l1/super_glue/rte/should_assume/results.json similarity index 100% rename from evaluation_l1/super_glue/rte/should_assume/results.json rename to evaluation_bloommz/evaluation_l1/super_glue/rte/should_assume/results.json diff --git a/evaluation_l1/winogrande/winogrande_xl/Replace/results.json b/evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/Replace/results.json similarity index 100% rename from evaluation_l1/winogrande/winogrande_xl/Replace/results.json rename to evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/Replace/results.json diff --git a/evaluation_l1/winogrande/winogrande_xl/True_or_False/results.json b/evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/True_or_False/results.json similarity index 100% rename from evaluation_l1/winogrande/winogrande_xl/True_or_False/results.json rename to evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/True_or_False/results.json diff --git a/evaluation_l1/winogrande/winogrande_xl/does_underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/does_underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/winogrande/winogrande_xl/does_underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/does_underscore_refer_to/results.json diff --git a/evaluation_l1/winogrande/winogrande_xl/stand_for/results.json b/evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/stand_for/results.json similarity index 100% rename from evaluation_l1/winogrande/winogrande_xl/stand_for/results.json rename to evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/stand_for/results.json diff --git a/evaluation_l1/winogrande/winogrande_xl/underscore_refer_to/results.json b/evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/underscore_refer_to/results.json similarity index 100% rename from evaluation_l1/winogrande/winogrande_xl/underscore_refer_to/results.json rename to evaluation_bloommz/evaluation_l1/winogrande/winogrande_xl/underscore_refer_to/results.json diff --git a/evaluation_l1/xcopa/id/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/xcopa/id/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/xcopa/id/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/id/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/xcopa/id/best_option/results.json b/evaluation_bloommz/evaluation_l1/xcopa/id/best_option/results.json similarity index 100% rename from evaluation_l1/xcopa/id/best_option/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/id/best_option/results.json diff --git a/evaluation_l1/xcopa/id/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/xcopa/id/cause_effect/results.json similarity index 100% rename from evaluation_l1/xcopa/id/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/id/cause_effect/results.json diff --git a/evaluation_l1/xcopa/id/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/xcopa/id/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/xcopa/id/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/id/i_am_hesitating/results.json diff --git a/evaluation_l1/xcopa/id/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/xcopa/id/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/xcopa/id/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/id/plausible_alternatives/results.json diff --git a/evaluation_l1/xcopa/sw/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/xcopa/sw/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/xcopa/sw/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/sw/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/xcopa/sw/best_option/results.json b/evaluation_bloommz/evaluation_l1/xcopa/sw/best_option/results.json similarity index 100% rename from evaluation_l1/xcopa/sw/best_option/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/sw/best_option/results.json diff --git a/evaluation_l1/xcopa/sw/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/xcopa/sw/cause_effect/results.json similarity index 100% rename from evaluation_l1/xcopa/sw/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/sw/cause_effect/results.json diff --git a/evaluation_l1/xcopa/sw/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/xcopa/sw/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/xcopa/sw/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/sw/i_am_hesitating/results.json diff --git a/evaluation_l1/xcopa/sw/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/xcopa/sw/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/xcopa/sw/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/sw/plausible_alternatives/results.json diff --git a/evaluation_l1/xcopa/ta/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/xcopa/ta/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/xcopa/ta/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/ta/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/xcopa/ta/best_option/results.json b/evaluation_bloommz/evaluation_l1/xcopa/ta/best_option/results.json similarity index 100% rename from evaluation_l1/xcopa/ta/best_option/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/ta/best_option/results.json diff --git a/evaluation_l1/xcopa/ta/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/xcopa/ta/cause_effect/results.json similarity index 100% rename from evaluation_l1/xcopa/ta/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/ta/cause_effect/results.json diff --git a/evaluation_l1/xcopa/ta/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/xcopa/ta/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/xcopa/ta/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/ta/i_am_hesitating/results.json diff --git a/evaluation_l1/xcopa/ta/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/xcopa/ta/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/xcopa/ta/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/ta/plausible_alternatives/results.json diff --git a/evaluation_l1/xcopa/vi/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/xcopa/vi/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/xcopa/vi/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/vi/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/xcopa/vi/best_option/results.json b/evaluation_bloommz/evaluation_l1/xcopa/vi/best_option/results.json similarity index 100% rename from evaluation_l1/xcopa/vi/best_option/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/vi/best_option/results.json diff --git a/evaluation_l1/xcopa/vi/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/xcopa/vi/cause_effect/results.json similarity index 100% rename from evaluation_l1/xcopa/vi/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/vi/cause_effect/results.json diff --git a/evaluation_l1/xcopa/vi/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/xcopa/vi/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/xcopa/vi/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/vi/i_am_hesitating/results.json diff --git a/evaluation_l1/xcopa/vi/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/xcopa/vi/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/xcopa/vi/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/vi/plausible_alternatives/results.json diff --git a/evaluation_l1/xcopa/zh/C1_or_C2?_premise/results.json b/evaluation_bloommz/evaluation_l1/xcopa/zh/C1_or_C2?_premise/results.json similarity index 100% rename from evaluation_l1/xcopa/zh/C1_or_C2?_premise/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/zh/C1_or_C2?_premise/results.json diff --git a/evaluation_l1/xcopa/zh/best_option/results.json b/evaluation_bloommz/evaluation_l1/xcopa/zh/best_option/results.json similarity index 100% rename from evaluation_l1/xcopa/zh/best_option/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/zh/best_option/results.json diff --git a/evaluation_l1/xcopa/zh/cause_effect/results.json b/evaluation_bloommz/evaluation_l1/xcopa/zh/cause_effect/results.json similarity index 100% rename from evaluation_l1/xcopa/zh/cause_effect/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/zh/cause_effect/results.json diff --git a/evaluation_l1/xcopa/zh/i_am_hesitating/results.json b/evaluation_bloommz/evaluation_l1/xcopa/zh/i_am_hesitating/results.json similarity index 100% rename from evaluation_l1/xcopa/zh/i_am_hesitating/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/zh/i_am_hesitating/results.json diff --git a/evaluation_l1/xcopa/zh/plausible_alternatives/results.json b/evaluation_bloommz/evaluation_l1/xcopa/zh/plausible_alternatives/results.json similarity index 100% rename from evaluation_l1/xcopa/zh/plausible_alternatives/results.json rename to evaluation_bloommz/evaluation_l1/xcopa/zh/plausible_alternatives/results.json diff --git a/evaluation_l1/xnli/ar/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/ar/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/ar/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ar/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/ar/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/ar/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/ar/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ar/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/ar/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/ar/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/ar/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ar/can_we_infer/results.json diff --git a/evaluation_l1/xnli/ar/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/ar/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/ar/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ar/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/ar/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/ar/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/ar/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ar/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/en/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/en/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/en/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/en/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/en/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/en/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/en/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/en/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/en/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/en/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/en/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/en/can_we_infer/results.json diff --git a/evaluation_l1/xnli/en/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/en/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/en/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/en/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/en/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/en/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/en/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/en/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/es/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/es/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/es/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/es/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/es/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/es/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/es/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/es/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/es/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/es/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/es/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/es/can_we_infer/results.json diff --git a/evaluation_l1/xnli/es/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/es/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/es/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/es/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/es/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/es/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/es/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/es/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/fr/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/fr/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/fr/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/fr/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/fr/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/fr/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/fr/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/fr/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/fr/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/fr/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/fr/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/fr/can_we_infer/results.json diff --git a/evaluation_l1/xnli/fr/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/fr/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/fr/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/fr/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/fr/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/fr/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/fr/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/fr/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/hi/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/hi/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/hi/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/hi/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/hi/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/hi/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/hi/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/hi/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/hi/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/hi/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/hi/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/hi/can_we_infer/results.json diff --git a/evaluation_l1/xnli/hi/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/hi/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/hi/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/hi/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/hi/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/hi/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/hi/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/hi/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/sw/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/sw/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/sw/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/sw/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/sw/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/sw/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/sw/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/sw/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/sw/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/sw/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/sw/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/sw/can_we_infer/results.json diff --git a/evaluation_l1/xnli/sw/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/sw/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/sw/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/sw/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/sw/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/sw/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/sw/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/sw/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/ur/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/ur/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/ur/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ur/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/ur/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/ur/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/ur/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/ur/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ur/can_we_infer/results.json diff --git a/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/ur/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/ur/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/ur/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/ur/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/vi/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/vi/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/vi/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/vi/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/vi/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/vi/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/vi/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/vi/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/vi/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/vi/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/vi/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/vi/can_we_infer/results.json diff --git a/evaluation_l1/xnli/vi/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/vi/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/vi/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/vi/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/vi/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/vi/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/vi/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/vi/justified_in_saying/results.json diff --git a/evaluation_l1/xnli/zh/GPT-3_style/results.json b/evaluation_bloommz/evaluation_l1/xnli/zh/GPT-3_style/results.json similarity index 100% rename from evaluation_l1/xnli/zh/GPT-3_style/results.json rename to evaluation_bloommz/evaluation_l1/xnli/zh/GPT-3_style/results.json diff --git a/evaluation_l1/xnli/zh/MNLI_crowdsource/results.json b/evaluation_bloommz/evaluation_l1/xnli/zh/MNLI_crowdsource/results.json similarity index 100% rename from evaluation_l1/xnli/zh/MNLI_crowdsource/results.json rename to evaluation_bloommz/evaluation_l1/xnli/zh/MNLI_crowdsource/results.json diff --git a/evaluation_l1/xnli/zh/can_we_infer/results.json b/evaluation_bloommz/evaluation_l1/xnli/zh/can_we_infer/results.json similarity index 100% rename from evaluation_l1/xnli/zh/can_we_infer/results.json rename to evaluation_bloommz/evaluation_l1/xnli/zh/can_we_infer/results.json diff --git a/evaluation_l1/xnli/zh/guaranteed_possible_impossible/results.json b/evaluation_bloommz/evaluation_l1/xnli/zh/guaranteed_possible_impossible/results.json similarity index 100% rename from evaluation_l1/xnli/zh/guaranteed_possible_impossible/results.json rename to evaluation_bloommz/evaluation_l1/xnli/zh/guaranteed_possible_impossible/results.json diff --git a/evaluation_l1/xnli/zh/justified_in_saying/results.json b/evaluation_bloommz/evaluation_l1/xnli/zh/justified_in_saying/results.json similarity index 100% rename from evaluation_l1/xnli/zh/justified_in_saying/results.json rename to evaluation_bloommz/evaluation_l1/xnli/zh/justified_in_saying/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/merged.csv b/evaluation_bloommz/evaluation_xcopawinostorymt/merged.csv similarity index 100% rename from evaluation_xcopawinostorymt/merged.csv rename to evaluation_bloommz/evaluation_xcopawinostorymt/merged.csv diff --git a/evaluation_xcopawinostorymt/merged.json b/evaluation_bloommz/evaluation_xcopawinostorymt/merged.json similarity index 100% rename from evaluation_xcopawinostorymt/merged.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/merged.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json b/evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json rename to evaluation_bloommz/evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json diff --git a/evaluation_xnlihtmt/xnliht/ar/GPT-3_style_arht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ar/GPT-3_style_arht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ar/GPT-3_style_arht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ar/GPT-3_style_arht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ar/MNLI_crowdsource_arht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ar/MNLI_crowdsource_arht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ar/MNLI_crowdsource_arht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ar/MNLI_crowdsource_arht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ar/can_we_infer_arht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ar/can_we_infer_arht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ar/can_we_infer_arht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ar/can_we_infer_arht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ar/guaranteed_possible_impossible_arht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ar/guaranteed_possible_impossible_arht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ar/guaranteed_possible_impossible_arht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ar/guaranteed_possible_impossible_arht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ar/justified_in_saying_arht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ar/justified_in_saying_arht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ar/justified_in_saying_arht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ar/justified_in_saying_arht/results.json diff --git a/evaluation_xnlihtmt/xnliht/es/GPT-3_style_esht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/es/GPT-3_style_esht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/es/GPT-3_style_esht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/es/GPT-3_style_esht/results.json diff --git a/evaluation_xnlihtmt/xnliht/es/MNLI_crowdsource_esht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/es/MNLI_crowdsource_esht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/es/MNLI_crowdsource_esht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/es/MNLI_crowdsource_esht/results.json diff --git a/evaluation_xnlihtmt/xnliht/es/can_we_infer_esht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/es/can_we_infer_esht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/es/can_we_infer_esht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/es/can_we_infer_esht/results.json diff --git a/evaluation_xnlihtmt/xnliht/es/guaranteed_possible_impossible_esht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/es/guaranteed_possible_impossible_esht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/es/guaranteed_possible_impossible_esht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/es/guaranteed_possible_impossible_esht/results.json diff --git a/evaluation_xnlihtmt/xnliht/es/justified_in_saying_esht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/es/justified_in_saying_esht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/es/justified_in_saying_esht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/es/justified_in_saying_esht/results.json diff --git a/evaluation_xnlihtmt/xnliht/fr/GPT-3_style_frht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/fr/GPT-3_style_frht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/fr/GPT-3_style_frht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/fr/GPT-3_style_frht/results.json diff --git a/evaluation_xnlihtmt/xnliht/fr/MNLI_crowdsource_frht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/fr/MNLI_crowdsource_frht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/fr/MNLI_crowdsource_frht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/fr/MNLI_crowdsource_frht/results.json diff --git a/evaluation_xnlihtmt/xnliht/fr/can_we_infer_frht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/fr/can_we_infer_frht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/fr/can_we_infer_frht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/fr/can_we_infer_frht/results.json diff --git a/evaluation_xnlihtmt/xnliht/fr/guaranteed_possible_impossible_frht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/fr/guaranteed_possible_impossible_frht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/fr/guaranteed_possible_impossible_frht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/fr/guaranteed_possible_impossible_frht/results.json diff --git a/evaluation_xnlihtmt/xnliht/fr/justified_in_saying_frht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/fr/justified_in_saying_frht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/fr/justified_in_saying_frht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/fr/justified_in_saying_frht/results.json diff --git a/evaluation_xnlihtmt/xnliht/hi/GPT-3_style_hiht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/hi/GPT-3_style_hiht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/hi/GPT-3_style_hiht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/hi/GPT-3_style_hiht/results.json diff --git a/evaluation_xnlihtmt/xnliht/hi/MNLI_crowdsource_hiht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/hi/MNLI_crowdsource_hiht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/hi/MNLI_crowdsource_hiht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/hi/MNLI_crowdsource_hiht/results.json diff --git a/evaluation_xnlihtmt/xnliht/hi/can_we_infer_hiht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/hi/can_we_infer_hiht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/hi/can_we_infer_hiht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/hi/can_we_infer_hiht/results.json diff --git a/evaluation_xnlihtmt/xnliht/hi/guaranteed_possible_impossible_hiht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/hi/guaranteed_possible_impossible_hiht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/hi/guaranteed_possible_impossible_hiht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/hi/guaranteed_possible_impossible_hiht/results.json diff --git a/evaluation_xnlihtmt/xnliht/hi/justified_in_saying_hiht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/hi/justified_in_saying_hiht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/hi/justified_in_saying_hiht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/hi/justified_in_saying_hiht/results.json diff --git a/evaluation_xnlihtmt/xnliht/merged.csv b/evaluation_bloommz/evaluation_xnliht/xnli/merged.csv similarity index 100% rename from evaluation_xnlihtmt/xnliht/merged.csv rename to evaluation_bloommz/evaluation_xnliht/xnli/merged.csv diff --git a/evaluation_xnlihtmt/xnliht/merged.json b/evaluation_bloommz/evaluation_xnliht/xnli/merged.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/merged.json rename to evaluation_bloommz/evaluation_xnliht/xnli/merged.json diff --git a/evaluation_xnlihtmt/xnliht/sw/GPT-3_style_swht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/sw/GPT-3_style_swht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/sw/GPT-3_style_swht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/sw/GPT-3_style_swht/results.json diff --git a/evaluation_xnlihtmt/xnliht/sw/MNLI_crowdsource_swht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/sw/MNLI_crowdsource_swht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/sw/MNLI_crowdsource_swht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/sw/MNLI_crowdsource_swht/results.json diff --git a/evaluation_xnlihtmt/xnliht/sw/can_we_infer_swht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/sw/can_we_infer_swht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/sw/can_we_infer_swht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/sw/can_we_infer_swht/results.json diff --git a/evaluation_xnlihtmt/xnliht/sw/guaranteed_possible_impossible_swht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/sw/guaranteed_possible_impossible_swht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/sw/guaranteed_possible_impossible_swht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/sw/guaranteed_possible_impossible_swht/results.json diff --git a/evaluation_xnlihtmt/xnliht/sw/justified_in_saying_swht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/sw/justified_in_saying_swht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/sw/justified_in_saying_swht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/sw/justified_in_saying_swht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ur/GPT-3_style_urht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ur/GPT-3_style_urht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ur/GPT-3_style_urht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ur/GPT-3_style_urht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ur/MNLI_crowdsource_urht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ur/MNLI_crowdsource_urht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ur/MNLI_crowdsource_urht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ur/MNLI_crowdsource_urht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ur/can_we_infer_urht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ur/can_we_infer_urht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ur/can_we_infer_urht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ur/can_we_infer_urht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ur/guaranteed_possible_impossible_urht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ur/guaranteed_possible_impossible_urht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ur/guaranteed_possible_impossible_urht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ur/guaranteed_possible_impossible_urht/results.json diff --git a/evaluation_xnlihtmt/xnliht/ur/justified_in_saying_urht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/ur/justified_in_saying_urht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/ur/justified_in_saying_urht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/ur/justified_in_saying_urht/results.json diff --git a/evaluation_xnlihtmt/xnliht/vi/GPT-3_style_viht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/vi/GPT-3_style_viht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/vi/GPT-3_style_viht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/vi/GPT-3_style_viht/results.json diff --git a/evaluation_xnlihtmt/xnliht/vi/MNLI_crowdsource_viht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/vi/MNLI_crowdsource_viht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/vi/MNLI_crowdsource_viht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/vi/MNLI_crowdsource_viht/results.json diff --git a/evaluation_xnlihtmt/xnliht/vi/can_we_infer_viht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/vi/can_we_infer_viht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/vi/can_we_infer_viht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/vi/can_we_infer_viht/results.json diff --git a/evaluation_xnlihtmt/xnliht/vi/guaranteed_possible_impossible_viht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/vi/guaranteed_possible_impossible_viht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/vi/guaranteed_possible_impossible_viht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/vi/guaranteed_possible_impossible_viht/results.json diff --git a/evaluation_xnlihtmt/xnliht/vi/justified_in_saying_viht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/vi/justified_in_saying_viht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/vi/justified_in_saying_viht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/vi/justified_in_saying_viht/results.json diff --git a/evaluation_xnlihtmt/xnliht/zh/GPT-3_style_zhht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/zh/GPT-3_style_zhht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/zh/GPT-3_style_zhht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/zh/GPT-3_style_zhht/results.json diff --git a/evaluation_xnlihtmt/xnliht/zh/MNLI_crowdsource_zhht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/zh/MNLI_crowdsource_zhht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/zh/MNLI_crowdsource_zhht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/zh/MNLI_crowdsource_zhht/results.json diff --git a/evaluation_xnlihtmt/xnliht/zh/can_we_infer_zhht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/zh/can_we_infer_zhht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/zh/can_we_infer_zhht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/zh/can_we_infer_zhht/results.json diff --git a/evaluation_xnlihtmt/xnliht/zh/guaranteed_possible_impossible_zhht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/zh/guaranteed_possible_impossible_zhht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/zh/guaranteed_possible_impossible_zhht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/zh/guaranteed_possible_impossible_zhht/results.json diff --git a/evaluation_xnlihtmt/xnliht/zh/justified_in_saying_zhht/results.json b/evaluation_bloommz/evaluation_xnliht/xnli/zh/justified_in_saying_zhht/results.json similarity index 100% rename from evaluation_xnlihtmt/xnliht/zh/justified_in_saying_zhht/results.json rename to evaluation_bloommz/evaluation_xnliht/xnli/zh/justified_in_saying_zhht/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ar/GPT-3_style_armt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ar/GPT-3_style_armt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ar/GPT-3_style_armt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ar/GPT-3_style_armt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ar/MNLI_crowdsource_armt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ar/MNLI_crowdsource_armt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ar/MNLI_crowdsource_armt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ar/MNLI_crowdsource_armt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ar/can_we_infer_armt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ar/can_we_infer_armt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ar/can_we_infer_armt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ar/can_we_infer_armt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ar/guaranteed_possible_impossible_armt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ar/guaranteed_possible_impossible_armt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ar/guaranteed_possible_impossible_armt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ar/guaranteed_possible_impossible_armt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ar/justified_in_saying_armt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ar/justified_in_saying_armt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ar/justified_in_saying_armt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ar/justified_in_saying_armt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/es/GPT-3_style_esmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/es/GPT-3_style_esmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/es/GPT-3_style_esmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/es/GPT-3_style_esmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/es/MNLI_crowdsource_esmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/es/MNLI_crowdsource_esmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/es/MNLI_crowdsource_esmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/es/MNLI_crowdsource_esmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/es/can_we_infer_esmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/es/can_we_infer_esmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/es/can_we_infer_esmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/es/can_we_infer_esmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/es/guaranteed_possible_impossible_esmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/es/guaranteed_possible_impossible_esmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/es/guaranteed_possible_impossible_esmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/es/guaranteed_possible_impossible_esmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/es/justified_in_saying_esmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/es/justified_in_saying_esmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/es/justified_in_saying_esmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/es/justified_in_saying_esmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/fr/GPT-3_style_frmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/fr/GPT-3_style_frmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/fr/GPT-3_style_frmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/fr/GPT-3_style_frmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/fr/MNLI_crowdsource_frmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/fr/MNLI_crowdsource_frmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/fr/MNLI_crowdsource_frmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/fr/MNLI_crowdsource_frmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/fr/can_we_infer_frmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/fr/can_we_infer_frmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/fr/can_we_infer_frmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/fr/can_we_infer_frmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/fr/guaranteed_possible_impossible_frmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/fr/guaranteed_possible_impossible_frmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/fr/guaranteed_possible_impossible_frmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/fr/guaranteed_possible_impossible_frmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/fr/justified_in_saying_frmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/fr/justified_in_saying_frmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/fr/justified_in_saying_frmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/fr/justified_in_saying_frmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/hi/GPT-3_style_himt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/hi/GPT-3_style_himt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/hi/GPT-3_style_himt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/hi/GPT-3_style_himt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/hi/MNLI_crowdsource_himt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/hi/MNLI_crowdsource_himt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/hi/MNLI_crowdsource_himt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/hi/MNLI_crowdsource_himt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/hi/can_we_infer_himt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/hi/can_we_infer_himt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/hi/can_we_infer_himt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/hi/can_we_infer_himt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/hi/guaranteed_possible_impossible_himt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/hi/guaranteed_possible_impossible_himt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/hi/guaranteed_possible_impossible_himt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/hi/guaranteed_possible_impossible_himt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/hi/justified_in_saying_himt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/hi/justified_in_saying_himt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/hi/justified_in_saying_himt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/hi/justified_in_saying_himt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/merged.csv b/evaluation_bloommz/evaluation_xnlimt/xnli/merged.csv similarity index 100% rename from evaluation_xnlihtmt/xnlimt/merged.csv rename to evaluation_bloommz/evaluation_xnlimt/xnli/merged.csv diff --git a/evaluation_xnlihtmt/xnlimt/merged.json b/evaluation_bloommz/evaluation_xnlimt/xnli/merged.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/merged.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/merged.json diff --git a/evaluation_xnlihtmt/xnlimt/sw/GPT-3_style_swmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/sw/GPT-3_style_swmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/sw/GPT-3_style_swmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/sw/GPT-3_style_swmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/sw/MNLI_crowdsource_swmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/sw/MNLI_crowdsource_swmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/sw/MNLI_crowdsource_swmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/sw/MNLI_crowdsource_swmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/sw/can_we_infer_swmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/sw/can_we_infer_swmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/sw/can_we_infer_swmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/sw/can_we_infer_swmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/sw/guaranteed_possible_impossible_swmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/sw/guaranteed_possible_impossible_swmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/sw/guaranteed_possible_impossible_swmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/sw/guaranteed_possible_impossible_swmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/sw/justified_in_saying_swmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/sw/justified_in_saying_swmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/sw/justified_in_saying_swmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/sw/justified_in_saying_swmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ur/GPT-3_style_urmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ur/GPT-3_style_urmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ur/GPT-3_style_urmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ur/GPT-3_style_urmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ur/MNLI_crowdsource_urmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ur/MNLI_crowdsource_urmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ur/MNLI_crowdsource_urmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ur/MNLI_crowdsource_urmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ur/can_we_infer_urmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ur/can_we_infer_urmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ur/can_we_infer_urmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ur/can_we_infer_urmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ur/guaranteed_possible_impossible_urmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ur/guaranteed_possible_impossible_urmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ur/guaranteed_possible_impossible_urmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ur/guaranteed_possible_impossible_urmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/ur/justified_in_saying_urmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/ur/justified_in_saying_urmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/ur/justified_in_saying_urmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/ur/justified_in_saying_urmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/vi/GPT-3_style_vimt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/vi/GPT-3_style_vimt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/vi/GPT-3_style_vimt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/vi/GPT-3_style_vimt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/vi/MNLI_crowdsource_vimt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/vi/MNLI_crowdsource_vimt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/vi/MNLI_crowdsource_vimt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/vi/MNLI_crowdsource_vimt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/vi/can_we_infer_vimt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/vi/can_we_infer_vimt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/vi/can_we_infer_vimt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/vi/can_we_infer_vimt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/vi/guaranteed_possible_impossible_vimt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/vi/guaranteed_possible_impossible_vimt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/vi/guaranteed_possible_impossible_vimt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/vi/guaranteed_possible_impossible_vimt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/vi/justified_in_saying_vimt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/vi/justified_in_saying_vimt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/vi/justified_in_saying_vimt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/vi/justified_in_saying_vimt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/zh/GPT-3_style_zhmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/zh/GPT-3_style_zhmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/zh/GPT-3_style_zhmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/zh/GPT-3_style_zhmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/zh/MNLI_crowdsource_zhmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/zh/MNLI_crowdsource_zhmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/zh/MNLI_crowdsource_zhmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/zh/MNLI_crowdsource_zhmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/zh/can_we_infer_zhmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/zh/can_we_infer_zhmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/zh/can_we_infer_zhmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/zh/can_we_infer_zhmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/zh/guaranteed_possible_impossible_zhmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/zh/guaranteed_possible_impossible_zhmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/zh/guaranteed_possible_impossible_zhmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/zh/guaranteed_possible_impossible_zhmt/results.json diff --git a/evaluation_xnlihtmt/xnlimt/zh/justified_in_saying_zhmt/results.json b/evaluation_bloommz/evaluation_xnlimt/xnli/zh/justified_in_saying_zhmt/results.json similarity index 100% rename from evaluation_xnlihtmt/xnlimt/zh/justified_in_saying_zhmt/results.json rename to evaluation_bloommz/evaluation_xnlimt/xnli/zh/justified_in_saying_zhmt/results.json