Training stability loss spike recovery

.dockerignore

@@ -0,0 +1,2 @@
+.venv
+node_modules

.github/workflows/precommit.yml → .github/workflows/ci.yaml

@@ -17,6 +17,18 @@ jobs:
         with:
           python-version: "3.12"
 
+      - uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev
+        working-directory: llm
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev
+        working-directory: dashboard/backend
+
       - name: Install pre-commit
         run: pip install pre-commit
 
@@ -29,3 +41,11 @@ jobs:
 
       - name: Run hooks
         run: pre-commit run --all-files --show-diff-on-failure
+
+      - name: Run basedpyright (llm)
+        run: uv run basedpyright
+        working-directory: llm
+
+      - name: Run basedpyright (dashboard/backend)
+        run: uv run basedpyright
+        working-directory: dashboard/backend

.gitignore

@@ -1,3 +1,55 @@
+### Project ###
+_data
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -51,9 +103,6 @@ coverage.xml
 .pytest_cache/
 cover/
 
-# Ruff
-.ruff_cache/
-
 # Translations
 *.mo
 *.pot
@@ -85,8 +134,6 @@ target/
 profile_default/
 ipython_config.py
 
-.pdm.toml
-
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 __pypackages__/
 
@@ -130,17 +177,45 @@ dmypy.json
 # Cython debug symbols
 cython_debug/
 
-# macOS
-.DS_Store
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
 
+# Folder config file
+[Dd]esktop.ini
 
-logs/
-/data
-/outputs
-/logs
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
 
-*.pt 
-*.pth
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
 
-# macOS specific files
-*.DS_Store
+# Windows shortcuts
+*.lnk

.gitleaks.toml

@@ -0,0 +1,4 @@
+[allowlist]
+paths = [
+    '''\.env\.example''',
+]

.pre-commit-config.yaml

@@ -1,34 +1,34 @@
-minimum_pre_commit_version: 2.20.0
-
 repos:
   - repo: https://github.com/psf/black
-    rev: 24.8.0
+    rev: 26.1.0
     hooks:
       - id: black
 
   - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+    rev: 8.0.0
     hooks:
       - id: isort
         args: ["--profile=black"]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.0
+    rev: v0.15.4
     hooks:
       - id: ruff
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
       - id: check-json
-
+      - id: check-added-large-files
+        args: ["--maxkb=1024"]
+
   - repo: https://github.com/adrienverge/yamllint
-    rev: v1.35.1
+    rev: v1.38.0
     hooks:
       - id: yamllint
         args: [-c, .yamllint]
 
   - repo: https://github.com/gitleaks/gitleaks
-    rev: v8.18.4
+    rev: v8.30.0
     hooks:
-      - id: gitleaks
+      - id: gitleaks

README.md

@@ -1,11 +0,0 @@
-# LLM
-
-Lightning Language Models
-
-## Contribution Guidelines
-
-See [contribution guidelines](https://github.com/The-School-of-AI/LLM/tree/main/experiments/19_reproducibility_provenance_and_experiment_tracking/contribution.md)
-
-## Rebase with Staging
-
-See [rebase with staging](https://github.com/The-School-of-AI/LLM/tree/main/experiments/19_reproducibility_provenance_and_experiment_tracking/rebase_with_stage.md)