From 105db6a7cbd533e90aa1f85192b162284c879472 Mon Sep 17 00:00:00 2001 From: github-actions Date: Wed, 9 Oct 2024 21:07:30 +0000 Subject: [PATCH] leaderboard: add eval results --- .../results/mistral-small-2407.json | 89 +++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 leaderboard-submissions/results/mistral-small-2407.json diff --git a/leaderboard-submissions/results/mistral-small-2407.json b/leaderboard-submissions/results/mistral-small-2407.json new file mode 100644 index 0000000..79d7478 --- /dev/null +++ b/leaderboard-submissions/results/mistral-small-2407.json @@ -0,0 +1,89 @@ +{ + "_submission_hash": "44f29b285feea7b76639d19a2c192ecfd25348ffdcee53c2c307f8e705909a90", + "_results_hash": "d3af0027d184918f72ed4ec495c2b14e5380e3e5adbaf08a89825abfa3af35e2", + "metadata": { + "name": "Mistral-Small-Instruct-2409 (22B)", + "authors": "Mistral AI", + "url": "https://huggingface.co/mistralai/Mistral-Small-Instruct-2409", + "citation": "Mistral AI, 2024", + "type": "FOUNDATION", + "context": 32000, + "is_trained_for_function_calling": true, + "details": "mistralai/Mistral-Small-Instruct-2409" + }, + "closedbook": { + "acc": { + "loose": 0.45009737596509086, + "strict": 0.0718232044198895 + }, + "rouge": { + "rouge1": { + "precision": 0.40413593124020636, + "recall": 0.5203778032263678, + "fscore": 0.4289685522275595 + }, + "rouge2": { + "precision": 0.22677952683741726, + "recall": 0.28246582033023643, + "fscore": 0.23970226499726682 + }, + "rougeL": { + "precision": 0.33815109507904656, + "recall": 0.4376086364815907, + "fscore": 0.35935635298293217 + } + }, + "bleurt": 0.47831919019558156, + "gpt": 0.17679558011049723 + }, + "openbook": { + "acc": { + "loose": 0.1648043800345083, + "strict": 0.024861878453038673 + }, + "rouge": { + "rouge1": { + "precision": 0.08807170710615721, + "recall": 0.19938182128421078, + "fscore": 0.10339134253355729 + }, + "rouge2": { + "precision": 0.034980458138033084, + "recall": 0.08356692517473442, + "fscore": 0.04381925675910583 + }, + "rougeL": { + "precision": 0.07920926275369623, + "recall": 0.17572237714942518, + "fscore": 0.09205489092446673 + } + }, + "bleurt": 0.3076735539927832, + "gpt": 0.06077348066298342 + }, + "evidenceprovided": { + "acc": { + "loose": 0.5412839161496934, + "strict": 0.11602209944751381 + }, + "rouge": { + "rouge1": { + "precision": 0.5434171449488068, + "recall": 0.5991728084304127, + "fscore": 0.5257063117207197 + }, + "rouge2": { + "precision": 0.3034771259186124, + "recall": 0.33855921563246183, + "fscore": 0.3014339606975428 + }, + "rougeL": { + "precision": 0.4337592194646311, + "recall": 0.48099067004018287, + "fscore": 0.41983527281644906 + } + }, + "bleurt": 0.521161766897743, + "gpt": 0.2292817679558011 + } +} \ No newline at end of file