Merge branch 'cont-metrics' of https://github.com/EleutherAI/lm-evaluation-harness into alt_worlds

2184b8de · lintangsutawika · b1ba4e71 · 1522009c · 2184b8de · 2184b8de
Commit 2184b8de authored Nov 08, 2023 by lintangsutawika
20 changed files
--- a/lm_eval/tasks/bigbench/generate_until/abstract_narrative_understanding.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/abstract_narrative_understanding.yaml
--- a/lm_eval/tasks/bigbench/generate_until/anachronisms.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/anachronisms.yaml
--- a/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml
--- a/lm_eval/tasks/bigbench/generate_until/analytic_entailment.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/analytic_entailment.yaml
--- a/lm_eval/tasks/bigbench/generate_until/arithmetic.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/arithmetic.yaml
--- a/lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml
--- a/lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml
--- a/lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml
--- a/lm_eval/tasks/bigbench/generate_until/auto_debugging.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/auto_debugging.yaml
--- a/lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml
--- a/lm_eval/tasks/bigbench/generate_until/bridging_anaphora_resolution_barqa.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/bridging_anaphora_resolution_barqa.yaml
--- a/lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml
--- a/lm_eval/tasks/bigbench/generate_until/cause_and_effect.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/cause_and_effect.yaml
--- a/lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml
--- a/lm_eval/tasks/bigbench/generate_until/chess_state_tracking.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/chess_state_tracking.yaml
--- a/lm_eval/tasks/bigbench/generate_until/chinese_remainder_theorem.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/chinese_remainder_theorem.yaml
--- a/lm_eval/tasks/bigbench/generate_until/cifar10_classification.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/cifar10_classification.yaml
--- a/lm_eval/tasks/bigbench/generate_until/code_line_description.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/code_line_description.yaml
--- a/lm_eval/tasks/bigbench/generate_until/codenames.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/codenames.yaml
--- a/lm_eval/tasks/bigbench/generate_until/color.yaml
+++ b/lm_eval/tasks/bigbench/generate_until/color.yaml