Merge remote-tracking branch 'origin/master' into evaluator-description-option

.github/workflows/python-app.yml

@@ -23,11 +23,11 @@ jobs:
         path: |
           ~/.cache
         # An explicit key for restoring and saving the cache
-        key: evaldata-cache-3
+        key: evaldata-cache-4
     - name: Set up Python 3.9
       uses: actions/setup-python@v2
       with:
-        python-version: 3.9
+        python-version: 3.9.4
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

tests/testdata/truthfulqa_gen-v0-greedy_until

-1a280973bbac2b7ac29dd64dddac474fb4749585f7de893483b4034814466c67
\ No newline at end of file
+0d7c56e1aa71ffd8f94bde28f6e8dfdd35f7aaadffa0620bd2a27704253d6c14
\ No newline at end of file

tests/testdata/truthfulqa_gen-v0-res.json

-{"results": {"truthfulqa_gen": {"bleu_acc": 0.0, "bleu_acc_stderr": 0.0, "bleu_diff": 0.0, "bleu_diff_stderr": 0.0, "bleu_max": 0.0, "bleu_max_stderr": 0.0, "bleurt_acc": 0.835985312117503, "bleurt_acc_stderr": 0.012962704327492454, "bleurt_diff": 0.14077322143090107, "bleurt_diff_stderr": 0.005459888909582694, "bleurt_max": -1.4399358725752065, "bleurt_max_stderr": 0.0022126992369197133, "rouge1_acc": 0.0, "rouge1_acc_stderr": 0.0, "rouge1_diff": 0.0, "rouge1_diff_stderr": 0.0, "rouge1_max": 0.0, "rouge1_max_stderr": 0.0, "rouge2_acc": 0.0, "rouge2_acc_stderr": 0.0, "rouge2_diff": 0.0, "rouge2_diff_stderr": 0.0, "rouge2_max": 0.0, "rouge2_max_stderr": 0.0, "rougeL_acc": 0.0, "rougeL_acc_stderr": 0.0, "rougeL_diff": 0.0, "rougeL_diff_stderr": 0.0, "rougeL_max": 0.0, "rougeL_max_stderr": 0.0}}, "versions": {"truthfulqa_gen": 0}}
\ No newline at end of file
+{"results": {"truthfulqa_gen": {"bleu_acc": 0.0, "bleu_acc_stderr": 0.0, "bleu_diff": 0.0, "bleu_diff_stderr": 0.0, "bleu_max": 0.0, "bleu_max_stderr": 0.0, "bleurt_acc": 0.8372093023255814, "bleurt_acc_stderr": 0.012923696051772253, "bleurt_diff": 0.13967358205134603, "bleurt_diff_stderr": 0.00532907098769571, "bleurt_max": -1.4402793981454072, "bleurt_max_stderr": 0.0021884846359458963, "rouge1_acc": 0.0, "rouge1_acc_stderr": 0.0, "rouge1_diff": 0.0, "rouge1_diff_stderr": 0.0, "rouge1_max": 0.0, "rouge1_max_stderr": 0.0, "rouge2_acc": 0.0, "rouge2_acc_stderr": 0.0, "rouge2_diff": 0.0, "rouge2_diff_stderr": 0.0, "rouge2_max": 0.0, "rouge2_max_stderr": 0.0, "rougeL_acc": 0.0, "rougeL_acc_stderr": 0.0, "rougeL_diff": 0.0, "rougeL_diff_stderr": 0.0, "rougeL_max": 0.0, "rougeL_max_stderr": 0.0}}, "versions": {"truthfulqa_gen": 0}}
\ No newline at end of file

tests/testdata/truthfulqa_mc-v0-loglikelihood

-1e07020e9cf41d46ed65312eb39d2b8e6599673d4f0d6b67c0d0eba0efb493bb
\ No newline at end of file
+226a6783976177dc9ceda5688623ff37023242eff30ddf270b886bf7b9b32228
\ No newline at end of file

tests/testdata/truthfulqa_mc-v0-res.json

-{"results": {"truthfulqa_mc": {"mc1": 0.23255813953488372, "mc1_stderr": 0.01478915753108052, "mc2": 0.4462325560722362, "mc2_stderr": 0.004986523944692003}}, "versions": {"truthfulqa_mc": 0}}
\ No newline at end of file
+{"results": {"truthfulqa_mc": {"mc1": 0.2141982864137087, "mc1_stderr": 0.01436214815569045, "mc2": 0.465436996173817, "mc2_stderr": 0.0048422530880316405}}, "versions": {"truthfulqa_mc": 0}}
\ No newline at end of file