Update to new wandb format

.gitignore

@@ -1,9 +1,160 @@
-venv/
+# Byte-compiled / optimized / DLL files
 __pycache__/
-.env
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
 .ipynb_checkpoints
-*ipynb
-.vscode/
-.idea/
 
-logs/
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

app.py

@@ -84,34 +84,34 @@ def get_graph_entries(runs: list[Run]) -> dict[int, GraphEntry]:
     for run in reversed(runs[:GRAPH_HISTORY_DAYS]):
         date = datetime.strptime(run.created_at, "%Y-%m-%dT%H:%M:%SZ")
 
-        for key, value in run.summary.items():
-            if key.startswith("_"):
+        for summary_key, summary_value in run.summary.items():
+            if not summary_key.startswith("benchmarks"):
                 continue
+            for key, value in summary_value.items():
+                if "score" in value:
+                    continue
 
-            if "score" in value:
-                continue
-
-            uid = int(key)
-
-            baseline_generation_time = value["baseline_generation_time"]
-            generation_time = value["generation_time"]
-            similarity = min(1, value["similarity"])
-            score = calculate_score(baseline_generation_time, generation_time, similarity)
-            model = value["model"]
-
-            if uid not in entries:
-                entries[uid] = GraphEntry([date], [baseline_generation_time], [generation_time], [similarity], [score], [model], generation_time)
-            else:
-                if generation_time < entries[uid].best_time:
-                    entries[uid].best_time = generation_time
+                uid = int(key)
 
-                data = entries[uid]
-                data.dates.append(date)
-                data.baseline_generation_times.append(baseline_generation_time)
-                data.generation_times.append(data.best_time)
-                data.similarities.append(similarity)
-                data.scores.append(score)
-                data.models.append(model)
+                baseline_generation_time = value["baseline_generation_time"]
+                generation_time = value["generation_time"]
+                similarity = min(1, value["similarity"])
+                score = calculate_score(baseline_generation_time, generation_time, similarity)
+                model = value["model"]
+
+                if uid not in entries:
+                    entries[uid] = GraphEntry([date], [baseline_generation_time], [generation_time], [similarity], [score], [model], generation_time)
+                else:
+                    if generation_time < entries[uid].best_time:
+                        entries[uid].best_time = generation_time
+
+                    data = entries[uid]
+                    data.dates.append(date)
+                    data.baseline_generation_times.append(baseline_generation_time)
+                    data.generation_times.append(data.best_time)
+                    data.similarities.append(similarity)
+                    data.scores.append(score)
+                    data.models.append(model)
 
     entries = dict(sorted(entries.items(), key=lambda entry: entry[1].scores, reverse=True)[:MAX_GRAPH_ENTRIES])
     return dict(sorted(entries.items(), key=lambda entry: entry[1].best_time))
@@ -166,37 +166,37 @@ def create_leaderboard(runs: list[Run]) -> list[tuple]:
 
     for run in runs:
         has_data = False
-        for key, value in run.summary.items():
-            if key.startswith("_"):
-                continue
-
-            has_data = True
-
-            try:
-                uid = int(key)
-                generation_time = value["generation_time"]
-                baseline_generation_time = value["baseline_generation_time"]
-                similarity = min(1, value["similarity"])
-
-                entries[uid] = LeaderboardEntry(
-                    uid=uid,
-                    model=value["model"],
-                    score=calculate_score(baseline_generation_time, generation_time, similarity),
-                    similarity=similarity,
-                    hotkey=value["hotkey"],
-                    rank=value["rank"],
-                    baseline_generation_time=baseline_generation_time,
-                    baseline_size=value["baseline_size"],
-                    baseline_vram_used=value["baseline_vram_used"],
-                    baseline_watts_used=value["baseline_watts_used"],
-                    generation_time=generation_time,
-                    size=value["size"],
-                    vram_used=value["vram_used"],
-                    watts_used=value["watts_used"],
-                    previous_day_winner=value["multiday_winner"],
-                )
-            except Exception:
+        for summary_key, summary_value in run.summary.items():
+            if not summary_key == "benchmarks":
                 continue
+            for key, value in summary_value.items():
+                has_data = True
+
+                try:
+                    uid = int(key)
+                    generation_time = value["generation_time"]
+                    baseline_generation_time = value["baseline_generation_time"]
+                    similarity = min(1, value["similarity"])
+
+                    entries[uid] = LeaderboardEntry(
+                        uid=uid,
+                        model=value["model"],
+                        score=calculate_score(baseline_generation_time, generation_time, similarity),
+                        similarity=similarity,
+                        hotkey=value["hotkey"],
+                        rank=value["rank"],
+                        baseline_generation_time=baseline_generation_time,
+                        baseline_size=value["baseline_size"],
+                        baseline_vram_used=value["baseline_vram_used"],
+                        baseline_watts_used=value["baseline_watts_used"],
+                        generation_time=generation_time,
+                        size=value["size"],
+                        vram_used=value["vram_used"],
+                        watts_used=value["watts_used"],
+                        previous_day_winner=value["multiday_winner"],
+                    )
+                except Exception:
+                    continue
 
         if has_data:
             break