update

train-bhai-train

@@ -0,0 +1 @@
+Subproject commit ce11257dc34d8f8dbb36445cf834f89852539088

training/hf_run_space_train_job.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+# Same environment as your HF Job (Space clone + nbconvert + upload to Space).
+# Old UI command was invalid shell (no &&); this version is a proper chain.
+#
+# Requires: hf auth login (token is sent via --secrets HF_TOKEN from the CLI cache)
+# Optional: HF_SPACE_REPO_ID (default vaibhavkhandare/train-bhai-train)
+
+set -euo pipefail
+
+IMAGE="${HF_JOB_IMAGE:-pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime}"
+FLAVOR="${HF_JOB_FLAVOR:-l4x1}"
+TIMEOUT="${HF_JOB_TIMEOUT:-8h}"
+SPACE_REPO="${HF_SPACE_REPO_ID:-vaibhavkhandare/train-bhai-train}"
+NB_EXEC_TIMEOUT="${NB_EXEC_TIMEOUT:-3600}"
+
+if ! hf auth whoami &>/dev/null; then
+  echo "Run: hf auth login" >&2
+  exit 1
+fi
+
+REMOTE_SCRIPT=$(cat <<'EOS'
+set -euo pipefail
+export DEBIAN_FRONTEND=noninteractive
+apt-get update -qq && apt-get install -y --no-install-recommends git curl ca-certificates
+pip install -q --root-user-action=ignore --upgrade "typing_extensions>=4.15.0" jupyter nbconvert nbclient ipykernel huggingface_hub
+rm -rf /work
+git clone --depth 1 "https://user:${HF_TOKEN}@huggingface.co/spaces/${SPACE_REPO}" /work
+cd /work
+jupyter nbconvert --to notebook --execute training/train_grpo.ipynb \
+  --output train_grpo.executed.ipynb \
+  --ExecutePreprocessor.timeout="${NB_EXEC_TIMEOUT}"
+python -c "import os; from huggingface_hub import HfApi; HfApi().upload_folder(folder_path='.', path_in_repo='run-output', repo_id=os.environ['SPACE_REPO'], repo_type='space', allow_patterns=['training/train_grpo.executed.ipynb','plots/**','**/lora-*/**'])"
+EOS
+)
+
+exec hf jobs run \
+  --flavor "$FLAVOR" \
+  --detach \
+  --timeout "$TIMEOUT" \
+  --secrets HF_TOKEN \
+  --env "SPACE_REPO=$SPACE_REPO" \
+  --env "NB_EXEC_TIMEOUT=$NB_EXEC_TIMEOUT" \
+  "$IMAGE" \
+  bash -lc "$REMOTE_SCRIPT"

training/hf_run_train_grpo.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# Run train_grpo.ipynb on Hugging Face Jobs from your machine.
+# Prereqs: hf auth login  (or export HF_TOKEN for API + --secrets HF_TOKEN below)
+#
+# Optional — hf skills add (newer CLI only; do not upgrade global hf if you use transformers):
+#   uv venv .venv-hf && . .venv-hf/bin/activate && pip install -U 'huggingface_hub>=1.11' typer && hf skills add
+
+set -euo pipefail
+
+IMAGE="${HF_JOB_IMAGE:-pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime}"
+FLAVOR="${HF_JOB_FLAVOR:-l4x1}"
+TIMEOUT="${HF_JOB_TIMEOUT:-8h}"
+REPO_URL="${HF_REPO_URL:-https://github.com/VaibhavKhandare/viral-posts-env.git}"
+REPO_BRANCH="${HF_REPO_BRANCH:-hack1}"
+
+exec hf jobs run \
+  --flavor "$FLAVOR" \
+  --detach \
+  --timeout "$TIMEOUT" \
+  --env "REPO_URL=$REPO_URL" \
+  --env "REPO_BRANCH=$REPO_BRANCH" \
+  "$IMAGE" \
+  bash -lc 'set -euo pipefail
+export DEBIAN_FRONTEND=noninteractive
+apt-get update -qq && apt-get install -y --no-install-recommends git curl
+rm -rf /work && git clone --depth 1 --branch "${REPO_BRANCH}" "${REPO_URL}" /work
+cd /work
+pip install -q --root-user-action=ignore jupyter nbconvert nbclient ipykernel
+jupyter nbconvert --to notebook --execute training/train_grpo.ipynb \
+  --ExecutePreprocessor.timeout=86400 --inplace'