inspect-ai 0.3.78__py3-none-any.whl → 0.3.80__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- inspect_ai/_eval/run.py +12 -10
- inspect_ai/_view/www/dist/assets/index.js +7137 -7137
- inspect_ai/_view/www/src/App.tsx +2 -1
- inspect_ai/_view/www/src/api/index.ts +2 -1
- inspect_ai/_view/www/src/metadata/RenderedContent.tsx +2 -1
- inspect_ai/_view/www/src/utils/json-worker.ts +1 -1
- inspect_ai/model/_providers/google.py +23 -38
- inspect_ai/model/_providers/mistral.py +3 -4
- inspect_ai/model/_providers/providers.py +2 -6
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/METADATA +1 -1
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/RECORD +15 -15
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/WHEEL +1 -1
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/entry_points.txt +0 -0
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/licenses/LICENSE +0 -0
- {inspect_ai-0.3.78.dist-info → inspect_ai-0.3.80.dist-info}/top_level.txt +0 -0
inspect_ai/_eval/run.py
CHANGED
@@ -115,16 +115,6 @@ async def eval_run(
|
|
115
115
|
eval_solver = None
|
116
116
|
eval_solver_spec = None
|
117
117
|
|
118
|
-
# resolve the task scorers
|
119
|
-
eval_scorer_specs = (
|
120
|
-
[as_scorer_spec(scorer) for scorer in task.scorer]
|
121
|
-
if task.scorer is not None
|
122
|
-
else None
|
123
|
-
)
|
124
|
-
|
125
|
-
# resolve task metrics
|
126
|
-
eval_metrics = to_metric_specs(task.metrics) if task.metrics is not None else None
|
127
|
-
|
128
118
|
try:
|
129
119
|
# create run tasks
|
130
120
|
task_run_options: list[TaskRunOptions] = []
|
@@ -137,6 +127,18 @@ async def eval_run(
|
|
137
127
|
task = resolved_task.task
|
138
128
|
task_eval_config = eval_config.model_copy()
|
139
129
|
|
130
|
+
# resolve the task scorers
|
131
|
+
eval_scorer_specs = (
|
132
|
+
[as_scorer_spec(scorer) for scorer in task.scorer]
|
133
|
+
if task.scorer is not None
|
134
|
+
else None
|
135
|
+
)
|
136
|
+
|
137
|
+
# resolve task metrics
|
138
|
+
eval_metrics = (
|
139
|
+
to_metric_specs(task.metrics) if task.metrics is not None else None
|
140
|
+
)
|
141
|
+
|
140
142
|
# epochs
|
141
143
|
if task_eval_config.epochs is None:
|
142
144
|
task_eval_config.epochs = task.epochs
|