Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4

lm_eval/tasks/inverse_scaling/inverse_scaling_hindsight_neglect.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_hindsight_neglect_10shot
+dataset_path: inverse-scaling/hindsight-neglect-10shot

lm_eval/tasks/inverse_scaling/inverse_scaling_into_the_unknown.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_into_the_unknown
+dataset_path: Albertmade/into-the-unknown

lm_eval/tasks/inverse_scaling/inverse_scaling_memo_trap.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_memo_trap
+dataset_path: Albertmade/memo-trap

lm_eval/tasks/inverse_scaling/inverse_scaling_modus_tollens.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_modus_tollens
+dataset_path: Albertmade/modus-tollens

lm_eval/tasks/inverse_scaling/inverse_scaling_neqa.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_neqa
+dataset_path: inverse-scaling/NeQA

lm_eval/tasks/inverse_scaling/inverse_scaling_pattern_matching_suppression.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_pattern_matching_suppression
+dataset_path: Albertmade/pattern-matching-suppression

lm_eval/tasks/inverse_scaling/inverse_scaling_quote_repetition.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_quote_repetition
+dataset_path: inverse-scaling/quote-repetition

lm_eval/tasks/inverse_scaling/inverse_scaling_redefine_math.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_redefine_math
+dataset_path: inverse-scaling/redefine-math

lm_eval/tasks/inverse_scaling/inverse_scaling_repetitive_algebra.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_repetitive_algebra
+dataset_path: Albertmade/repetitive-algebra

lm_eval/tasks/inverse_scaling/inverse_scaling_sig_figs.yaml

+include: _inverse_scaling_mc_yaml
+task: inverse_scaling_sig_figs
+dataset_path: Albertmade/sig-figs

lm_eval/tasks/inverse_scaling/inverse_scaling_winobias_antistereotype.yaml

+group:
+  - inverse_scaling_mc
+task: inverse_scaling_winobias_antistereotype
+dataset_path: mathemakitten/winobias_antistereotype_test_v5
+output_type: multiple_choice
+test_split: test
+doc_to_text: text
+doc_to_choice: classes
+doc_to_target: target
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+dataset_kwargs:
+  trust_remote_code: true
+metadata:
+  version: 0

lm_eval/tasks/kmmlu/cot_hard/_cot_kmmlu_yaml

-group:
+tag:
     - kmmlu
     - kmmlu_hard_cot
 dataset_path: HAERAE-HUB/KMMLU-HARD

lm_eval/tasks/kmmlu/direct/_direct_kmmlu_yaml

-group:
+tag:
     - kmmlu
     - kmmlu_direct
 dataset_path: HAERAE-HUB/KMMLU

lm_eval/tasks/kmmlu/direct_hard/_direct_hard_kmmlu_yaml

-group:
+tag:
     - kmmlu
     - kmmlu_hard_direct
 dataset_path: HAERAE-HUB/KMMLU-HARD

lm_eval/tasks/kmmlu/hard/_hard_kmmlu_yaml

-group:
+tag:
     - kmmlu
     - kmmlu_hard
 dataset_path: HAERAE-HUB/KMMLU-HARD

lm_eval/tasks/kobest/kobest_boolq.yaml

-group:
+tag:
   - kobest
 task: kobest_boolq
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_copa.yaml

-group:
+tag:
   - kobest
 task: kobest_copa
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_hellaswag.yaml

-group:
+tag:
   - kobest
 task: kobest_hellaswag
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_sentineg.yaml

-group:
+tag:
   - kobest
 task: kobest_sentineg
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_wic.yaml

-group:
+tag:
   - kobest
 task: kobest_wic
 dataset_path: skt/kobest_v1