Spaces:
Runtime error
Runtime error
Commit
·
58e92e8
1
Parent(s):
45f775d
update scripts
Browse files- .idea/workspace.xml +37 -4
- app.py +3 -2
- src/display/utils.py +2 -1
.idea/workspace.xml
CHANGED
|
@@ -5,19 +5,31 @@
|
|
| 5 |
</component>
|
| 6 |
<component name="ChangeListManager">
|
| 7 |
<list default="true" id="b60b8d5d-762f-4021-9ce4-054078cb27a7" name="Changes" comment="">
|
| 8 |
-
<change beforePath="$PROJECT_DIR
|
|
|
|
|
|
|
| 9 |
</list>
|
| 10 |
<option name="SHOW_DIALOG" value="false" />
|
| 11 |
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
| 12 |
<option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
|
| 13 |
<option name="LAST_RESOLUTION" value="IGNORE" />
|
| 14 |
</component>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
<component name="ProblemsViewState">
|
| 16 |
<option name="selectedTabId" value="QODANA_PROBLEMS_VIEW_TAB" />
|
| 17 |
</component>
|
| 18 |
<component name="PropertiesComponent"><![CDATA[{
|
| 19 |
"keyToString": {
|
|
|
|
|
|
|
| 20 |
"Python.model_operations.executor": "Run",
|
|
|
|
| 21 |
"git-widget-placeholder": "main",
|
| 22 |
"node.js.selected.package.tslint": "(autodetect)"
|
| 23 |
}
|
|
@@ -25,14 +37,35 @@
|
|
| 25 |
<component name="TaskManager">
|
| 26 |
<servers />
|
| 27 |
</component>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
<component name="com.intellij.coverage.CoverageDataManagerImpl">
|
| 29 |
<SUITE FILE_PATH="coverage/HumanLikeness$.coverage" NAME=" Coverage Results" MODIFIED="1723441364832" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/tests" />
|
| 30 |
<SUITE FILE_PATH="coverage/HumanLikeness$model_operations.coverage" NAME="model_operations Coverage Results" MODIFIED="1723539909992" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src/backend" />
|
| 31 |
-
<SUITE FILE_PATH="coverage/HumanLikeness$
|
| 32 |
-
<SUITE FILE_PATH="coverage/HumanLikeness$
|
| 33 |
<SUITE FILE_PATH="coverage/HumanLikeness$evaluate_humanlike.coverage" NAME="evaluate_humanlike Coverage Results" MODIFIED="1723398170634" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/../Library/Containers/com.tencent.xinWeChat/Data/Library/Application Support/com.tencent.xinWeChat/2.0b4.0.9/32b9ff35361847f45b1e7909fcdff84c/Message/MessageTemp/7420e97876942c1eea73293c47ebb239/OpenData" />
|
| 34 |
<SUITE FILE_PATH="coverage/HumanLikeness$humanlike.coverage" NAME="humanlike Coverage Results" MODIFIED="1723535841643" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="" />
|
| 35 |
<SUITE FILE_PATH="coverage/HumanLikeness$envs.coverage" NAME="envs Coverage Results" MODIFIED="1723400161997" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src" />
|
| 36 |
-
<SUITE FILE_PATH="coverage/HumanLikeness$test.coverage" NAME="test Coverage Results" MODIFIED="
|
| 37 |
</component>
|
| 38 |
</project>
|
|
|
|
| 5 |
</component>
|
| 6 |
<component name="ChangeListManager">
|
| 7 |
<list default="true" id="b60b8d5d-762f-4021-9ce4-054078cb27a7" name="Changes" comment="">
|
| 8 |
+
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
| 9 |
+
<change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
|
| 10 |
+
<change beforePath="$PROJECT_DIR$/src/display/utils.py" beforeDir="false" afterPath="$PROJECT_DIR$/src/display/utils.py" afterDir="false" />
|
| 11 |
</list>
|
| 12 |
<option name="SHOW_DIALOG" value="false" />
|
| 13 |
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
| 14 |
<option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
|
| 15 |
<option name="LAST_RESOLUTION" value="IGNORE" />
|
| 16 |
</component>
|
| 17 |
+
<component name="FileTemplateManagerImpl">
|
| 18 |
+
<option name="RECENT_TEMPLATES">
|
| 19 |
+
<list>
|
| 20 |
+
<option value="Python Script" />
|
| 21 |
+
</list>
|
| 22 |
+
</option>
|
| 23 |
+
</component>
|
| 24 |
<component name="ProblemsViewState">
|
| 25 |
<option name="selectedTabId" value="QODANA_PROBLEMS_VIEW_TAB" />
|
| 26 |
</component>
|
| 27 |
<component name="PropertiesComponent"><![CDATA[{
|
| 28 |
"keyToString": {
|
| 29 |
+
"Python.app.executor": "Debug",
|
| 30 |
+
"Python.main_backend.executor": "Run",
|
| 31 |
"Python.model_operations.executor": "Run",
|
| 32 |
+
"Python.test.executor": "Run",
|
| 33 |
"git-widget-placeholder": "main",
|
| 34 |
"node.js.selected.package.tslint": "(autodetect)"
|
| 35 |
}
|
|
|
|
| 37 |
<component name="TaskManager">
|
| 38 |
<servers />
|
| 39 |
</component>
|
| 40 |
+
<component name="XDebuggerManager">
|
| 41 |
+
<breakpoint-manager>
|
| 42 |
+
<breakpoints>
|
| 43 |
+
<line-breakpoint enabled="true" suspend="THREAD" type="python-line">
|
| 44 |
+
<url>file://$PROJECT_DIR$/app.py</url>
|
| 45 |
+
<line>54</line>
|
| 46 |
+
<option name="timeStamp" value="39" />
|
| 47 |
+
</line-breakpoint>
|
| 48 |
+
<line-breakpoint enabled="true" suspend="THREAD" type="python-line">
|
| 49 |
+
<url>file://$PROJECT_DIR$/app.py</url>
|
| 50 |
+
<line>71</line>
|
| 51 |
+
<option name="timeStamp" value="40" />
|
| 52 |
+
</line-breakpoint>
|
| 53 |
+
<line-breakpoint enabled="true" suspend="THREAD" type="python-line">
|
| 54 |
+
<url>file://$PROJECT_DIR$/app.py</url>
|
| 55 |
+
<line>72</line>
|
| 56 |
+
<option name="timeStamp" value="41" />
|
| 57 |
+
</line-breakpoint>
|
| 58 |
+
</breakpoints>
|
| 59 |
+
</breakpoint-manager>
|
| 60 |
+
</component>
|
| 61 |
<component name="com.intellij.coverage.CoverageDataManagerImpl">
|
| 62 |
<SUITE FILE_PATH="coverage/HumanLikeness$.coverage" NAME=" Coverage Results" MODIFIED="1723441364832" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/tests" />
|
| 63 |
<SUITE FILE_PATH="coverage/HumanLikeness$model_operations.coverage" NAME="model_operations Coverage Results" MODIFIED="1723539909992" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src/backend" />
|
| 64 |
+
<SUITE FILE_PATH="coverage/HumanLikeness$main_backend.coverage" NAME="main_backend Coverage Results" MODIFIED="1723540718739" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
| 65 |
+
<SUITE FILE_PATH="coverage/HumanLikeness$app.coverage" NAME="app Coverage Results" MODIFIED="1723540867388" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
| 66 |
<SUITE FILE_PATH="coverage/HumanLikeness$evaluate_humanlike.coverage" NAME="evaluate_humanlike Coverage Results" MODIFIED="1723398170634" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/../Library/Containers/com.tencent.xinWeChat/Data/Library/Application Support/com.tencent.xinWeChat/2.0b4.0.9/32b9ff35361847f45b1e7909fcdff84c/Message/MessageTemp/7420e97876942c1eea73293c47ebb239/OpenData" />
|
| 67 |
<SUITE FILE_PATH="coverage/HumanLikeness$humanlike.coverage" NAME="humanlike Coverage Results" MODIFIED="1723535841643" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="" />
|
| 68 |
<SUITE FILE_PATH="coverage/HumanLikeness$envs.coverage" NAME="envs Coverage Results" MODIFIED="1723400161997" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src" />
|
| 69 |
+
<SUITE FILE_PATH="coverage/HumanLikeness$test.coverage" NAME="test Coverage Results" MODIFIED="1723541738228" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src" />
|
| 70 |
</component>
|
| 71 |
</project>
|
app.py
CHANGED
|
@@ -51,11 +51,12 @@ def process_pending_evals():
|
|
| 51 |
|
| 52 |
for _, eval_request in pending_eval_queue_df.iterrows():
|
| 53 |
# 根据具体的列名和数据格式调整 `eval_request` 的内容
|
| 54 |
-
|
|
|
|
| 55 |
|
| 56 |
# 调用评估函数
|
| 57 |
run_eval_suite.run_evaluation(
|
| 58 |
-
eval_request=
|
| 59 |
local_dir=envs.EVAL_RESULTS_PATH_BACKEND,
|
| 60 |
results_repo=envs.RESULTS_REPO,
|
| 61 |
batch_size=1,
|
|
|
|
| 51 |
|
| 52 |
for _, eval_request in pending_eval_queue_df.iterrows():
|
| 53 |
# 根据具体的列名和数据格式调整 `eval_request` 的内容
|
| 54 |
+
model_id = eval_request['model'].split('/')[-1].split('">')[0]
|
| 55 |
+
print(f"Evaluating model: {model_id}")
|
| 56 |
|
| 57 |
# 调用评估函数
|
| 58 |
run_eval_suite.run_evaluation(
|
| 59 |
+
eval_request=model_id,
|
| 60 |
local_dir=envs.EVAL_RESULTS_PATH_BACKEND,
|
| 61 |
results_repo=envs.RESULTS_REPO,
|
| 62 |
batch_size=1,
|
src/display/utils.py
CHANGED
|
@@ -30,7 +30,7 @@ auto_eval_column_dict.append(["model", ColumnContent,
|
|
| 30 |
ColumnContent("Model", "markdown", True, never_hidden=True)])
|
| 31 |
for task in Tasks:
|
| 32 |
auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
|
| 33 |
-
|
| 34 |
# Model information
|
| 35 |
auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
|
| 36 |
auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
|
|
@@ -47,6 +47,7 @@ auto_eval_column_dict.append(["dummy", ColumnContent, ColumnContent("model_name_
|
|
| 47 |
# We use make dataclass to dynamically fill the scores from Tasks
|
| 48 |
AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
|
| 49 |
|
|
|
|
| 50 |
## For the queue columns in the submission tab
|
| 51 |
@dataclass(frozen=True)
|
| 52 |
class EvalQueueColumn: # Queue column
|
|
|
|
| 30 |
ColumnContent("Model", "markdown", True, never_hidden=True)])
|
| 31 |
for task in Tasks:
|
| 32 |
auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
|
| 33 |
+
#
|
| 34 |
# Model information
|
| 35 |
auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
|
| 36 |
auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
|
|
|
|
| 47 |
# We use make dataclass to dynamically fill the scores from Tasks
|
| 48 |
AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
|
| 49 |
|
| 50 |
+
|
| 51 |
## For the queue columns in the submission tab
|
| 52 |
@dataclass(frozen=True)
|
| 53 |
class EvalQueueColumn: # Queue column
|