Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Update src/leaderboard/read_evals.py
Browse files
src/leaderboard/read_evals.py
CHANGED
@@ -39,7 +39,6 @@ class EvalResult:
|
|
39 |
|
40 |
config = data.get("config")
|
41 |
scores = data.get("scores", {})
|
42 |
-
print(f"Debug: scores = {scores}")
|
43 |
|
44 |
# Precision
|
45 |
precision = Precision.from_str(config.get("model_dtype"))
|
@@ -76,7 +75,6 @@ class EvalResult:
|
|
76 |
task_value = task.value
|
77 |
score = scores.get(task_value.metric)
|
78 |
results[task_value.metric] = score
|
79 |
-
print("results", results)
|
80 |
|
81 |
|
82 |
return self(
|
@@ -127,9 +125,15 @@ class EvalResult:
|
|
127 |
AutoEvalColumn.still_on_hub.name: self.still_on_hub,
|
128 |
}
|
129 |
|
|
|
|
|
|
|
130 |
for task in Tasks:
|
131 |
task_value = task.value
|
132 |
-
|
|
|
|
|
|
|
133 |
|
134 |
return data_dict
|
135 |
|
|
|
39 |
|
40 |
config = data.get("config")
|
41 |
scores = data.get("scores", {})
|
|
|
42 |
|
43 |
# Precision
|
44 |
precision = Precision.from_str(config.get("model_dtype"))
|
|
|
75 |
task_value = task.value
|
76 |
score = scores.get(task_value.metric)
|
77 |
results[task_value.metric] = score
|
|
|
78 |
|
79 |
|
80 |
return self(
|
|
|
125 |
AutoEvalColumn.still_on_hub.name: self.still_on_hub,
|
126 |
}
|
127 |
|
128 |
+
# for task in Tasks:
|
129 |
+
# task_value = task.value
|
130 |
+
# data_dict[task_value.col_name] = self.results.get(task_value.benchmark, None)
|
131 |
for task in Tasks:
|
132 |
task_value = task.value
|
133 |
+
value = self.results.get(task_value.benchmark)
|
134 |
+
data_dict[task_value.col_name] = Decimal(value)
|
135 |
+
|
136 |
+
print(f"Debug: Returned dictionary from to_dict: {data_dict}")
|
137 |
|
138 |
return data_dict
|
139 |
|