File size: 5,629 Bytes
6534252 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
#!/usr/bin/env python3
"""
Test script to check Hugging Face connectivity and provide solutions
"""
import requests
import os
from pathlib import Path
def test_huggingface_connectivity():
"""Test connection to Hugging Face"""
print("🌐 Testing Hugging Face connectivity...")
try:
response = requests.get("https://huggingface.co", timeout=10)
if response.status_code == 200:
print("✅ Hugging Face is accessible")
return True
else:
print(f"⚠️ Hugging Face returned status code: {response.status_code}")
return False
except requests.exceptions.Timeout:
print("❌ Connection to Hugging Face timed out")
return False
except requests.exceptions.ConnectionError:
print("❌ Cannot connect to Hugging Face")
return False
except Exception as e:
print(f"❌ Error connecting to Hugging Face: {e}")
return False
def check_cached_models():
"""Check if T5 models are already cached"""
print("\n📁 Checking for cached models...")
# Common cache locations
cache_locations = [
Path.home() / ".cache" / "huggingface" / "transformers",
Path.home() / ".cache" / "huggingface" / "hub",
Path(os.environ.get("HF_HOME", "")) / "hub" if os.environ.get("HF_HOME") else None,
]
found_models = []
for cache_dir in cache_locations:
if cache_dir and cache_dir.exists():
# Look for t5-base related folders
for item in cache_dir.iterdir():
if item.is_dir() and "t5" in item.name.lower():
found_models.append(str(item))
print(f"✅ Found cached model: {item}")
if not found_models:
print("❌ No T5 models found in cache")
return found_models
def suggest_solutions():
"""Provide solutions for connectivity issues"""
print("\n💡 Solutions for connectivity issues:")
print("="*50)
print("\n1. 🌐 **Pre-download the model with better connectivity:**")
print(" Run this when you have stable internet:")
print(" ```python")
print(" from transformers import AutoTokenizer, AutoModelForSeq2SeqLM")
print(" tokenizer = AutoTokenizer.from_pretrained('t5-base')")
print(" model = AutoModelForSeq2SeqLM.from_pretrained('t5-base')")
print(" ```")
print("\n2. 🔄 **Retry with longer timeout:**")
print(" Set environment variables:")
print(" ```bash")
print(" export HF_HUB_TIMEOUT=300")
print(" export REQUESTS_TIMEOUT=300")
print(" ```")
print("\n3. 🏠 **Use offline mode (if model is cached):**")
print(" ```bash")
print(" export TRANSFORMERS_OFFLINE=1")
print(" ```")
print("\n4. 🌐 **Alternative: Use different mirror:**")
print(" ```bash")
print(" export HF_ENDPOINT=https://hf-mirror.com")
print(" ```")
print("\n5. 📦 **Local testing without model download:**")
print(" Use a smaller test that doesn't require model downloads")
def create_simple_test():
"""Create a simple test that doesn't require model downloads"""
print("\n🧪 Creating simplified test...")
test_script = '''#!/usr/bin/env python3
"""
Simple test that only tests data loading and GPU monitoring without model downloads
"""
import sys
import os
sys.path.append('src')
def test_data_only():
"""Test only data loading functionality"""
try:
import pandas as pd
from tevatron.utils.gpu_monitor import GPUMemoryMonitor
print("✅ Testing data loading...")
df = pd.read_csv("data/the_vault/DOC_VAULT_train.tsv", sep='\\t', nrows=5)
print(f"✅ Loaded {len(df)} samples")
print("✅ Testing GPU monitor...")
monitor = GPUMemoryMonitor(memory_threshold=0.8, check_interval=10)
stats = monitor.get_memory_stats()
print(f"✅ GPU monitor initialized: {stats}")
print("🎉 Basic functionality test PASSED!")
return True
except Exception as e:
print(f"❌ Test failed: {e}")
return False
if __name__ == "__main__":
success = test_data_only()
sys.exit(0 if success else 1)
'''
with open("scripts/test_basic.py", "w") as f:
f.write(test_script)
print("✅ Created scripts/test_basic.py")
print(" Run with: python scripts/test_basic.py")
def main():
print("🔍 GLEN Connectivity Diagnostic")
print("="*40)
# Test connectivity
connectivity_ok = test_huggingface_connectivity()
# Check cached models
cached_models = check_cached_models()
# Create simple test
create_simple_test()
# Suggest solutions
suggest_solutions()
print("\n" + "="*50)
print("📋 Summary:")
print(f" - Hugging Face connectivity: {'✅ OK' if connectivity_ok else '❌ FAILED'}")
print(f" - Cached models found: {'✅ YES' if cached_models else '❌ NO'}")
print(" - Simple test created: ✅ YES")
if not connectivity_ok and not cached_models:
print("\n⚠️ **Action needed:** Either fix connectivity or pre-download models")
print(" Try running: python scripts/test_basic.py (for basic functionality)")
elif cached_models:
print("\n✅ **Good news:** You have cached models. Try offline mode!")
print(" Set: export TRANSFORMERS_OFFLINE=1")
else:
print("\n✅ **All good:** You should be able to run full training!")
if __name__ == "__main__":
main() |