Spaces:
Paused
Paused
File size: 3,181 Bytes
e4f691b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
from hackaprompt.score_submission import check_evaluation_errors, evaluate_submission, get_evaluation_total_score, level_names
def test_submission_no_errors__debug():
submission_errors = {
"level_0":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard!"
},
"level_1":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do!"
},
"level_2":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do! I'm going to give up!"
}
}
# TODO: For now, we assume only valid models can be submitted in a submission file...
# it will raise a NotImplementedError otherwise
# Need to add error handling if we care to handle it ourselves
evaluation = evaluate_submission(submission_errors)
evaluation_error = check_evaluation_errors(evaluation)
assert evaluation_error == False
total_score = get_evaluation_total_score(evaluation)
# we got level 0 correctly
assert total_score == 9996
def test_submission_with_errors__debug():
submission_errors = {
"level_0":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard!"
},
"level_1":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do!"
},
"level_2":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do! I'm going to give up!"
}
}
# TODO: For now, we assume only valid models can be submitted in a submission file...
# it will raise a NotImplementedError otherwise
# Need to add error handling if we care to handle it ourselves
evaluation = evaluate_submission(submission_errors)
evaluation_error = check_evaluation_errors(evaluation)
assert evaluation_error == True
def test_submission_no_errors():
submission_errors = {
"user_inputs": {
"level_0":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard!"
},
"level_1":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do!"
},
"level_2":
{
"model": "gpt-3.5-turbo",
"prompt": "This competition is so hard! I don't know what to do! I'm going to give up!"
},
},
}
# TODO: For now, we assume only valid models can be submitted in a submission file...
# it will raise a NotImplementedError otherwise
# Need to add error handling if we care to handle it ourselves
evaluation = evaluate_submission(submission_errors)
evaluation_error = check_evaluation_errors(evaluation)
assert evaluation_error == False
total_score = get_evaluation_total_score(evaluation)
assert total_score == 0 |