Spaces:
Sleeping
Sleeping
deploy: sync a95ecfec from GitHub Actions
Browse files- assets/reward_grid.jsonl +3 -0
- assets/train.jsonl +21 -0
- validate-submission.sh +0 -185
assets/reward_grid.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"difficulty": "Easy", "task_id": 0, "variants": [{"name": "perfect", "score": 0.9773}, {"name": "no_layout", "score": 0.5222}, {"name": "no_style", "score": 0.4424}]}
|
| 2 |
+
{"difficulty": "Medium", "task_id": 5, "variants": [{"name": "minor_diff", "score": 0.9551}, {"name": "bad_colors", "score": 0.7327}, {"name": "no_style", "score": 0.35}]}
|
| 3 |
+
{"difficulty": "Hard", "task_id": 10, "variants": [{"name": "perfect", "score": 0.9773}, {"name": "minor_diff", "score": 0.8818}, {"name": "no_style", "score": 0.2505}]}
|
assets/train.jsonl
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"iter": 0, "easy": 0.629, "medium": 0.488, "hard": 0.346, "mean": 0.4877}
|
| 2 |
+
{"iter": 1, "easy": 0.6352, "medium": 0.468, "hard": 0.3817, "mean": 0.495, "loss": -0.054}
|
| 3 |
+
{"iter": 2, "easy": 0.6507, "medium": 0.4529, "hard": 0.2997, "mean": 0.4678, "loss": -0.215}
|
| 4 |
+
{"iter": 3, "easy": 0.6257, "medium": 0.5345, "hard": 0.3579, "mean": 0.506, "loss": -0.077}
|
| 5 |
+
{"iter": 4, "easy": 0.5959, "medium": 0.5994, "hard": 0.3955, "mean": 0.5303, "loss": -0.225}
|
| 6 |
+
{"iter": 5, "easy": 0.6193, "medium": 0.6283, "hard": 0.3866, "mean": 0.5447, "loss": -0.199}
|
| 7 |
+
{"iter": 6, "easy": 0.5911, "medium": 0.619, "hard": 0.3309, "mean": 0.5137, "loss": 0.047}
|
| 8 |
+
{"iter": 7, "easy": 0.6375, "medium": 0.6226, "hard": 0.3676, "mean": 0.5426, "loss": -0.315}
|
| 9 |
+
{"iter": 8, "easy": 0.5915, "medium": 0.6905, "hard": 0.3731, "mean": 0.5517, "loss": -0.052}
|
| 10 |
+
{"iter": 9, "easy": 0.5963, "medium": 0.6501, "hard": 0.4062, "mean": 0.5509, "loss": -0.186}
|
| 11 |
+
{"iter": 10, "easy": 0.606, "medium": 0.683, "hard": 0.388, "mean": 0.559, "loss": -0.123}
|
| 12 |
+
{"iter": 11, "easy": 0.619, "medium": 0.6938, "hard": 0.4237, "mean": 0.5788, "loss": -0.007}
|
| 13 |
+
{"iter": 12, "easy": 0.6716, "medium": 0.6578, "hard": 0.4017, "mean": 0.577, "loss": 0.207}
|
| 14 |
+
{"iter": 13, "easy": 0.5916, "medium": 0.6917, "hard": 0.4882, "mean": 0.5905, "loss": -0.151}
|
| 15 |
+
{"iter": 14, "easy": 0.614, "medium": 0.6315, "hard": 0.4238, "mean": 0.5564, "loss": 0.142}
|
| 16 |
+
{"iter": 15, "easy": 0.6382, "medium": 0.6867, "hard": 0.4988, "mean": 0.6079, "loss": -0.012}
|
| 17 |
+
{"iter": 16, "easy": 0.6042, "medium": 0.6624, "hard": 0.4985, "mean": 0.5884, "loss": -0.044}
|
| 18 |
+
{"iter": 17, "easy": 0.6317, "medium": 0.6818, "hard": 0.5206, "mean": 0.6114, "loss": 0.019}
|
| 19 |
+
{"iter": 18, "easy": 0.6474, "medium": 0.6464, "hard": 0.5409, "mean": 0.6116, "loss": -0.066}
|
| 20 |
+
{"iter": 19, "easy": 0.6489, "medium": 0.5835, "hard": 0.533, "mean": 0.5885, "loss": 0.008}
|
| 21 |
+
{"iter": 20, "easy": 0.634, "medium": 0.634, "hard": 0.564, "mean": 0.6107, "loss": 0.021}
|
validate-submission.sh
DELETED
|
@@ -1,185 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env bash
|
| 2 |
-
#
|
| 3 |
-
# validate-submission.sh — OpenEnv Submission Validator
|
| 4 |
-
#
|
| 5 |
-
# Checks that your HF Space is live, Docker image builds, and openenv validate passes.
|
| 6 |
-
#
|
| 7 |
-
# Prerequisites:
|
| 8 |
-
# - Docker: https://docs.docker.com/get-docker/
|
| 9 |
-
# - openenv-core: pip install openenv-core
|
| 10 |
-
# - curl (usually pre-installed)
|
| 11 |
-
#
|
| 12 |
-
# Run:
|
| 13 |
-
# curl -fsSL https://raw.githubusercontent.com/<owner>/<repo>/main/scripts/validate-submission.sh | bash -s -- <ping_url> [repo_dir]
|
| 14 |
-
#
|
| 15 |
-
# Or download and run locally:
|
| 16 |
-
# chmod +x validate-submission.sh
|
| 17 |
-
# ./validate-submission.sh <ping_url> [repo_dir]
|
| 18 |
-
#
|
| 19 |
-
# Arguments:
|
| 20 |
-
# ping_url Your HuggingFace Space URL (e.g. https://your-space.hf.space)
|
| 21 |
-
# repo_dir Path to your repo (default: current directory)
|
| 22 |
-
#
|
| 23 |
-
# Examples:
|
| 24 |
-
# ./validate-submission.sh https://my-team.hf.space
|
| 25 |
-
# ./validate-submission.sh https://my-team.hf.space ./my-repo
|
| 26 |
-
#
|
| 27 |
-
|
| 28 |
-
set -uo pipefail
|
| 29 |
-
|
| 30 |
-
DOCKER_BUILD_TIMEOUT=600
|
| 31 |
-
if [ -t 1 ]; then
|
| 32 |
-
RED='\033[0;31m'
|
| 33 |
-
GREEN='\033[0;32m'
|
| 34 |
-
YELLOW='\033[1;33m'
|
| 35 |
-
BOLD='\033[1m'
|
| 36 |
-
NC='\033[0m'
|
| 37 |
-
else
|
| 38 |
-
RED='' GREEN='' YELLOW='' BOLD='' NC=''
|
| 39 |
-
fi
|
| 40 |
-
|
| 41 |
-
run_with_timeout() {
|
| 42 |
-
local secs="$1"; shift
|
| 43 |
-
if command -v timeout &>/dev/null; then
|
| 44 |
-
timeout "$secs" "$@"
|
| 45 |
-
elif command -v gtimeout &>/dev/null; then
|
| 46 |
-
gtimeout "$secs" "$@"
|
| 47 |
-
else
|
| 48 |
-
"$@" &
|
| 49 |
-
local pid=$!
|
| 50 |
-
( sleep "$secs" && kill "$pid" 2>/dev/null ) &
|
| 51 |
-
local watcher=$!
|
| 52 |
-
wait "$pid" 2>/dev/null
|
| 53 |
-
local rc=$?
|
| 54 |
-
kill "$watcher" 2>/dev/null
|
| 55 |
-
wait "$watcher" 2>/dev/null
|
| 56 |
-
return $rc
|
| 57 |
-
fi
|
| 58 |
-
}
|
| 59 |
-
|
| 60 |
-
portable_mktemp() {
|
| 61 |
-
local prefix="${1:-validate}"
|
| 62 |
-
mktemp "${TMPDIR:-/tmp}/${prefix}-XXXXXX" 2>/dev/null || mktemp
|
| 63 |
-
}
|
| 64 |
-
|
| 65 |
-
CLEANUP_FILES=()
|
| 66 |
-
cleanup() { rm -f "${CLEANUP_FILES[@]+"${CLEANUP_FILES[@]}"}"; }
|
| 67 |
-
trap cleanup EXIT
|
| 68 |
-
|
| 69 |
-
PING_URL="${1:-}"
|
| 70 |
-
REPO_DIR="${2:-.}"
|
| 71 |
-
|
| 72 |
-
if [ -z "$PING_URL" ]; then
|
| 73 |
-
printf "Usage: %s <ping_url> [repo_dir]\n" "$0"
|
| 74 |
-
printf "\n"
|
| 75 |
-
printf " ping_url Your HuggingFace Space URL (e.g. https://your-space.hf.space)\n"
|
| 76 |
-
printf " repo_dir Path to your repo (default: current directory)\n"
|
| 77 |
-
exit 1
|
| 78 |
-
fi
|
| 79 |
-
|
| 80 |
-
if ! REPO_DIR="$(cd "$REPO_DIR" 2>/dev/null && pwd)"; then
|
| 81 |
-
printf "Error: directory '%s' not found\n" "${2:-.}"
|
| 82 |
-
exit 1
|
| 83 |
-
fi
|
| 84 |
-
PING_URL="${PING_URL%/}"
|
| 85 |
-
export PING_URL
|
| 86 |
-
PASS=0
|
| 87 |
-
|
| 88 |
-
log() { printf "[%s] %b\n" "$(date -u +%H:%M:%S)" "$*"; }
|
| 89 |
-
pass() { log "${GREEN}PASSED${NC} -- $1"; PASS=$((PASS + 1)); }
|
| 90 |
-
fail() { log "${RED}FAILED${NC} -- $1"; }
|
| 91 |
-
hint() { printf " ${YELLOW}Hint:${NC} %b\n" "$1"; }
|
| 92 |
-
stop_at() {
|
| 93 |
-
printf "\n"
|
| 94 |
-
printf "${RED}${BOLD}Validation stopped at %s.${NC} Fix the above before continuing.\n" "$1"
|
| 95 |
-
exit 1
|
| 96 |
-
}
|
| 97 |
-
|
| 98 |
-
printf "\n"
|
| 99 |
-
printf "${BOLD}========================================${NC}\n"
|
| 100 |
-
printf "${BOLD} OpenEnv Submission Validator${NC}\n"
|
| 101 |
-
printf "${BOLD}========================================${NC}\n"
|
| 102 |
-
log "Repo: $REPO_DIR"
|
| 103 |
-
log "Ping URL: $PING_URL"
|
| 104 |
-
printf "\n"
|
| 105 |
-
|
| 106 |
-
log "${BOLD}Step 1/3: Pinging HF Space${NC} ($PING_URL/reset) ..."
|
| 107 |
-
|
| 108 |
-
CURL_OUTPUT=$(portable_mktemp "validate-curl")
|
| 109 |
-
CLEANUP_FILES+=("$CURL_OUTPUT")
|
| 110 |
-
HTTP_CODE=$(curl -s -o "$CURL_OUTPUT" -w "%{http_code}" -X POST \
|
| 111 |
-
-H "Content-Type: application/json" -d '{}' \
|
| 112 |
-
"$PING_URL/reset" --max-time 30 2>"$CURL_OUTPUT" || printf "000")
|
| 113 |
-
|
| 114 |
-
if [ "$HTTP_CODE" = "200" ]; then
|
| 115 |
-
pass "HF Space is live and responds to /reset"
|
| 116 |
-
elif [ "$HTTP_CODE" = "000" ]; then
|
| 117 |
-
fail "HF Space not reachable (connection failed or timed out)"
|
| 118 |
-
hint "Check your network connection and that the Space is running."
|
| 119 |
-
hint "Try: curl -s -o /dev/null -w '%%{http_code}' -X POST $PING_URL/reset"
|
| 120 |
-
stop_at "Step 1"
|
| 121 |
-
else
|
| 122 |
-
fail "HF Space /reset returned HTTP $HTTP_CODE (expected 200)"
|
| 123 |
-
hint "Make sure your Space is running and the URL is correct."
|
| 124 |
-
hint "Try opening $PING_URL in your browser first."
|
| 125 |
-
stop_at "Step 1"
|
| 126 |
-
fi
|
| 127 |
-
|
| 128 |
-
log "${BOLD}Step 2/3: Running docker build${NC} ..."
|
| 129 |
-
|
| 130 |
-
if ! command -v docker &>/dev/null; then
|
| 131 |
-
fail "docker command not found"
|
| 132 |
-
hint "Install Docker: https://docs.docker.com/get-docker/"
|
| 133 |
-
stop_at "Step 2"
|
| 134 |
-
fi
|
| 135 |
-
|
| 136 |
-
if [ -f "$REPO_DIR/Dockerfile" ]; then
|
| 137 |
-
DOCKER_CONTEXT="$REPO_DIR"
|
| 138 |
-
elif [ -f "$REPO_DIR/server/Dockerfile" ]; then
|
| 139 |
-
DOCKER_CONTEXT="$REPO_DIR/server"
|
| 140 |
-
else
|
| 141 |
-
fail "No Dockerfile found in repo root or server/ directory"
|
| 142 |
-
stop_at "Step 2"
|
| 143 |
-
fi
|
| 144 |
-
|
| 145 |
-
log " Found Dockerfile in $DOCKER_CONTEXT"
|
| 146 |
-
|
| 147 |
-
BUILD_OK=false
|
| 148 |
-
BUILD_OUTPUT=$(run_with_timeout "$DOCKER_BUILD_TIMEOUT" docker build "$DOCKER_CONTEXT" 2>&1) && BUILD_OK=true
|
| 149 |
-
|
| 150 |
-
if [ "$BUILD_OK" = true ]; then
|
| 151 |
-
pass "Docker build succeeded"
|
| 152 |
-
else
|
| 153 |
-
fail "Docker build failed (timeout=${DOCKER_BUILD_TIMEOUT}s)"
|
| 154 |
-
printf "%s\n" "$BUILD_OUTPUT" | tail -20
|
| 155 |
-
stop_at "Step 2"
|
| 156 |
-
fi
|
| 157 |
-
|
| 158 |
-
log "${BOLD}Step 3/3: Running openenv validate${NC} ..."
|
| 159 |
-
|
| 160 |
-
if ! command -v openenv &>/dev/null; then
|
| 161 |
-
fail "openenv command not found"
|
| 162 |
-
hint "Install it: pip install openenv-core"
|
| 163 |
-
stop_at "Step 3"
|
| 164 |
-
fi
|
| 165 |
-
|
| 166 |
-
VALIDATE_OK=false
|
| 167 |
-
VALIDATE_OUTPUT=$(cd "$REPO_DIR" && openenv validate 2>&1) && VALIDATE_OK=true
|
| 168 |
-
|
| 169 |
-
if [ "$VALIDATE_OK" = true ]; then
|
| 170 |
-
pass "openenv validate passed"
|
| 171 |
-
[ -n "$VALIDATE_OUTPUT" ] && log " $VALIDATE_OUTPUT"
|
| 172 |
-
else
|
| 173 |
-
fail "openenv validate failed"
|
| 174 |
-
printf "%s\n" "$VALIDATE_OUTPUT"
|
| 175 |
-
stop_at "Step 3"
|
| 176 |
-
fi
|
| 177 |
-
|
| 178 |
-
printf "\n"
|
| 179 |
-
printf "${BOLD}========================================${NC}\n"
|
| 180 |
-
printf "${GREEN}${BOLD} All 3/3 checks passed!${NC}\n"
|
| 181 |
-
printf "${GREEN}${BOLD} Your submission is ready to submit.${NC}\n"
|
| 182 |
-
printf "${BOLD}========================================${NC}\n"
|
| 183 |
-
printf "\n"
|
| 184 |
-
|
| 185 |
-
exit 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|