Spaces:
Sleeping
Sleeping
Update training/colab_notebook.py
Browse files
training/colab_notebook.py
CHANGED
|
@@ -27,8 +27,9 @@ os.environ["ENV_URL"] = "https://junaid0600-sql-db-engineer-agent.hf.space"
|
|
| 27 |
os.environ["MODEL_NAME"] = "unsloth/Qwen2.5-7B-Instruct"
|
| 28 |
os.environ["OUTPUT_DIR"] = "./sdea-trained"
|
| 29 |
os.environ["N_EPISODES"] = "10"
|
|
|
|
| 30 |
|
| 31 |
-
print("
|
| 32 |
print(f"ENV_URL: {os.environ['ENV_URL']}")
|
| 33 |
|
| 34 |
# ββ CELL 4: Verify environment is live ββββββββββββββββββββ
|
|
@@ -40,17 +41,17 @@ def check_env():
|
|
| 40 |
try:
|
| 41 |
r = requests.get(f"{ENV_URL}/health", timeout=10)
|
| 42 |
data = r.json()
|
| 43 |
-
print(f"
|
| 44 |
|
| 45 |
r2 = requests.get(f"{ENV_URL}/tasks", timeout=10)
|
| 46 |
tasks = r2.json()
|
| 47 |
-
print(f"
|
| 48 |
|
| 49 |
r3 = requests.get(f"{ENV_URL}/progress", timeout=10)
|
| 50 |
-
print(f"
|
| 51 |
return True
|
| 52 |
except Exception as e:
|
| 53 |
-
print(f"
|
| 54 |
return False
|
| 55 |
|
| 56 |
check_env()
|
|
@@ -58,7 +59,7 @@ check_env()
|
|
| 58 |
# ββ CELL 5: Quick episode test ββββββββββββββββββββββββββββ
|
| 59 |
def test_episode():
|
| 60 |
"""Run one full episode to verify everything works."""
|
| 61 |
-
print("\n
|
| 62 |
|
| 63 |
# Reset
|
| 64 |
r = requests.post(f"{ENV_URL}/reset",
|
|
@@ -97,7 +98,7 @@ def test_episode():
|
|
| 97 |
print(f" Final score: {summary.get('final_score', 'N/A')}")
|
| 98 |
print(f" Improvement: {summary.get('improvement', 'N/A')}")
|
| 99 |
|
| 100 |
-
print("\n
|
| 101 |
|
| 102 |
test_episode()
|
| 103 |
|
|
@@ -212,4 +213,4 @@ def run_judge_demo():
|
|
| 212 |
print("Trained to think like a senior DBA.")
|
| 213 |
print("=" * 60)
|
| 214 |
|
| 215 |
-
run_judge_demo()
|
|
|
|
| 27 |
os.environ["MODEL_NAME"] = "unsloth/Qwen2.5-7B-Instruct"
|
| 28 |
os.environ["OUTPUT_DIR"] = "./sdea-trained"
|
| 29 |
os.environ["N_EPISODES"] = "10"
|
| 30 |
+
os.environ["MAX_STEPS"] = "300"
|
| 31 |
|
| 32 |
+
print("Environment variables set")
|
| 33 |
print(f"ENV_URL: {os.environ['ENV_URL']}")
|
| 34 |
|
| 35 |
# ββ CELL 4: Verify environment is live ββββββββββββββββββββ
|
|
|
|
| 41 |
try:
|
| 42 |
r = requests.get(f"{ENV_URL}/health", timeout=10)
|
| 43 |
data = r.json()
|
| 44 |
+
print(f"Environment healthy: {data}")
|
| 45 |
|
| 46 |
r2 = requests.get(f"{ENV_URL}/tasks", timeout=10)
|
| 47 |
tasks = r2.json()
|
| 48 |
+
print(f"Tasks available: {tasks['total']}")
|
| 49 |
|
| 50 |
r3 = requests.get(f"{ENV_URL}/progress", timeout=10)
|
| 51 |
+
print(f"Progress endpoint: {r3.status_code}")
|
| 52 |
return True
|
| 53 |
except Exception as e:
|
| 54 |
+
print(f"Environment check failed: {e}")
|
| 55 |
return False
|
| 56 |
|
| 57 |
check_env()
|
|
|
|
| 59 |
# ββ CELL 5: Quick episode test ββββββββββββββββββββββββββββ
|
| 60 |
def test_episode():
|
| 61 |
"""Run one full episode to verify everything works."""
|
| 62 |
+
print("\n Testing full episode...")
|
| 63 |
|
| 64 |
# Reset
|
| 65 |
r = requests.post(f"{ENV_URL}/reset",
|
|
|
|
| 98 |
print(f" Final score: {summary.get('final_score', 'N/A')}")
|
| 99 |
print(f" Improvement: {summary.get('improvement', 'N/A')}")
|
| 100 |
|
| 101 |
+
print("\n Episode test complete!")
|
| 102 |
|
| 103 |
test_episode()
|
| 104 |
|
|
|
|
| 213 |
print("Trained to think like a senior DBA.")
|
| 214 |
print("=" * 60)
|
| 215 |
|
| 216 |
+
run_judge_demo()
|