mirror of
https://github.com/perstarkse/minne.git
synced 2026-07-09 22:32:48 +02:00
evals: eval crate overhaul, simplification and performance improvements
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
default_dataset: squad-v2
|
||||
default_dataset: beir
|
||||
datasets:
|
||||
- id: squad-v2
|
||||
label: "SQuAD v2.0"
|
||||
@@ -45,6 +45,7 @@ datasets:
|
||||
description: "Balanced slice across FEVER, FiQA, HotpotQA, NFCorpus, Quora, TREC-COVID, SciFact, NQ-BEIR"
|
||||
limit: 600
|
||||
corpus_limit: 6000
|
||||
negative_multiplier: 9.0
|
||||
seed: 0x5eed2025
|
||||
- id: fever
|
||||
label: "FEVER (BEIR)"
|
||||
|
||||
Reference in New Issue
Block a user