Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "478ddd97e684ac09add36e439e844eaf678cf81b"
Commit c6403765 authored by lintangsutawika's avatar lintangsutawika
Browse files

update

parent ea8b5beb
Show whitespace changes
Inline Side-by-side
Showing with 78 additions and 78 deletions
lm_eval/tasks/benchmarks/flan_held_out.yaml
View file @ c6403765
...@@ -3,10 +3,10 @@ task: ...@@ -3,10 +3,10 @@ task:
# BBH # BBH
- bbh_flan_zeroshot - bbh_flan_zeroshot
- bbh_flan_fewshot - bbh_flan_fewshot
- bbh_flan_cot_fewshot # - bbh_flan_cot_fewshot
- bbh_flan_cot_zeroshot # - bbh_flan_cot_zeroshot
# MMLU # MMLU
- mmlu_flan_n_shot_generative - mmlu_flan_n_shot_generative
- mmlu_flan_n_shot_loglikelihood - mmlu_flan_n_shot_loglikelihood
- mmlu_flan_cot_zeroshot # - mmlu_flan_cot_zeroshot
- mmlu_flan_cot_fewshot # - mmlu_flan_cot_fewshot
lm_eval/tasks/benchmarks/t0_eval.yaml
View file @ c6403765
...@@ -26,80 +26,80 @@ task: ...@@ -26,80 +26,80 @@ task:
higher_is_better: true higher_is_better: true
ignore_case: true ignore_case: true
ignore_punctuation: true ignore_punctuation: true
# # Natural Language Inference # Natural Language Inference
# - dataset_path: super_glue - dataset_path: super_glue
# dataset_name: cb dataset_name: cb
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train training_split: train
# validation_split: validation validation_split: validation
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# - dataset_path: super_glue - dataset_path: super_glue
# dataset_name: rte dataset_name: rte
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train training_split: train
# validation_split: validation validation_split: validation
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# - task: anli_r1 - task: anli_r1
# dataset_path: anli dataset_path: anli
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train_r1 training_split: train_r1
# validation_split: dev_r1 validation_split: dev_r1
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# - task: anli_r2 - task: anli_r2
# dataset_path: anli dataset_path: anli
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train_r2 training_split: train_r2
# validation_split: dev_r2 validation_split: dev_r2
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# - task: anli_r3 - task: anli_r3
# dataset_path: anli dataset_path: anli
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train_r3 training_split: train_r3
# validation_split: dev_r3 validation_split: dev_r3
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# # Sentence Completion # Sentence Completion
# - dataset_path: super_glue - dataset_path: super_glue
# dataset_name: copa dataset_name: copa
# use_prompt: promptsource:* use_prompt: promptsource:*
# training_split: train training_split: train
# validation_split: validation validation_split: validation
# output_type: greedy_until output_type: greedy_until
# metric_list: metric_list:
# - metric: exact_match - metric: exact_match
# aggregation: mean aggregation: mean
# higher_is_better: true higher_is_better: true
# ignore_case: true ignore_case: true
# ignore_punctuation: true ignore_punctuation: true
# Natural Language Inference # Natural Language Inference
- dataset_path: hellaswag - dataset_path: hellaswag
use_prompt: promptsource:* use_prompt: promptsource:*
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment