Spaces:
Running
Running
File size: 15,511 Bytes
ebe598e 93ed7a1 ebe598e 2da5c04 c417358 ebe598e c417358 2da5c04 c417358 2da5c04 ebe598e 2da5c04 ebe598e 93ed7a1 2da5c04 ebe598e fe5f524 ebe598e fe5f524 2da5c04 fe5f524 2da5c04 fe5f524 ebe598e 93ed7a1 2da5c04 ebe598e 2da5c04 ebe598e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 |
#!/usr/bin/env python3
"""
Setup script for Hugging Face Dataset repository for Trackio experiments
"""
import os
import json
from datetime import datetime
from pathlib import Path
from datasets import Dataset
from huggingface_hub import HfApi, create_repo
import subprocess
def get_username_from_token(token: str) -> str:
"""Get username from HF token with fallback to CLI"""
try:
# Try API first
api = HfApi(token=token)
user_info = api.whoami()
# Handle different possible response formats
if isinstance(user_info, dict):
# Try different possible keys for username
username = (
user_info.get('name') or
user_info.get('username') or
user_info.get('user') or
None
)
elif isinstance(user_info, str):
# If whoami returns just the username as string
username = user_info
else:
username = None
if username:
print(f"✅ Got username from API: {username}")
return username
else:
print("⚠️ Could not get username from API, trying CLI...")
return get_username_from_cli(token)
except Exception as e:
print(f"⚠️ API whoami failed: {e}")
print("⚠️ Trying CLI fallback...")
return get_username_from_cli(token)
def get_username_from_cli(token: str) -> str:
"""Fallback method to get username using CLI"""
try:
# Set HF token for CLI
os.environ['HF_TOKEN'] = token
# Get username using CLI
result = subprocess.run(
["huggingface-cli", "whoami"],
capture_output=True,
text=True,
timeout=30
)
if result.returncode == 0:
username = result.stdout.strip()
if username:
print(f"✅ Got username from CLI: {username}")
return username
else:
print("⚠️ CLI returned empty username")
return None
else:
print(f"⚠️ CLI whoami failed: {result.stderr}")
return None
except Exception as e:
print(f"⚠️ CLI fallback failed: {e}")
return None
def setup_trackio_dataset():
"""Set up the Trackio experiments dataset on Hugging Face Hub"""
# Configuration - get from environment variables with fallbacks
hf_token = os.environ.get('HF_TOKEN')
if not hf_token:
print("❌ HF_TOKEN not found. Please set the HF_TOKEN environment variable.")
print("You can get your token from: https://huggingface.co/settings/tokens")
return False
username = get_username_from_token(hf_token)
if not username:
print("❌ Could not determine username from token. Please check your token.")
return False
print(f"✅ Authenticated as: {username}")
# Use username in dataset repository if not specified
dataset_repo = os.environ.get('TRACKIO_DATASET_REPO', f'{username}/trackio-experiments')
print(f"🚀 Setting up Trackio dataset: {dataset_repo}")
print(f"🔧 Using dataset repository: {dataset_repo}")
# Initial experiment data
initial_experiments = [
{
'experiment_id': 'exp_20250720_130853',
'name': 'petite-elle-l-aime-3',
'description': 'SmolLM3 fine-tuning experiment',
'created_at': '2025-07-20T11:20:01.780908',
'status': 'running',
'metrics': json.dumps([
{
'timestamp': '2025-07-20T11:20:01.780908',
'step': 25,
'metrics': {
'loss': 1.1659,
'grad_norm': 10.3125,
'learning_rate': 7e-08,
'num_tokens': 1642080.0,
'mean_token_accuracy': 0.75923578992486,
'epoch': 0.004851130919895701
}
},
{
'timestamp': '2025-07-20T11:26:39.042155',
'step': 50,
'metrics': {
'loss': 1.165,
'grad_norm': 10.75,
'learning_rate': 1.4291666666666667e-07,
'num_tokens': 3324682.0,
'mean_token_accuracy': 0.7577659255266189,
'epoch': 0.009702261839791402
}
},
{
'timestamp': '2025-07-20T11:33:16.203045',
'step': 75,
'metrics': {
'loss': 1.1639,
'grad_norm': 10.6875,
'learning_rate': 2.1583333333333334e-07,
'num_tokens': 4987941.0,
'mean_token_accuracy': 0.7581205774843692,
'epoch': 0.014553392759687101
}
},
{
'timestamp': '2025-07-20T11:39:53.453917',
'step': 100,
'metrics': {
'loss': 1.1528,
'grad_norm': 10.75,
'learning_rate': 2.8875e-07,
'num_tokens': 6630190.0,
'mean_token_accuracy': 0.7614579878747463,
'epoch': 0.019404523679582803
}
}
]),
'parameters': json.dumps({
'model_name': 'HuggingFaceTB/SmolLM3-3B',
'max_seq_length': 12288,
'use_flash_attention': True,
'use_gradient_checkpointing': False,
'batch_size': 8,
'gradient_accumulation_steps': 16,
'learning_rate': 3.5e-06,
'weight_decay': 0.01,
'warmup_steps': 1200,
'max_iters': 18000,
'eval_interval': 1000,
'log_interval': 25,
'save_interval': 2000,
'optimizer': 'adamw_torch',
'beta1': 0.9,
'beta2': 0.999,
'eps': 1e-08,
'scheduler': 'cosine',
'min_lr': 3.5e-07,
'fp16': False,
'bf16': True,
'ddp_backend': 'nccl',
'ddp_find_unused_parameters': False,
'save_steps': 2000,
'eval_steps': 1000,
'logging_steps': 25,
'save_total_limit': 5,
'eval_strategy': 'steps',
'metric_for_best_model': 'eval_loss',
'greater_is_better': False,
'load_best_model_at_end': True,
'data_dir': None,
'train_file': None,
'validation_file': None,
'test_file': None,
'use_chat_template': True,
'chat_template_kwargs': {'add_generation_prompt': True, 'no_think_system_message': True},
'enable_tracking': True,
'trackio_url': 'https://tonic-test-trackio-test.hf.space',
'trackio_token': None,
'log_artifacts': True,
'log_metrics': True,
'log_config': True,
'experiment_name': 'petite-elle-l-aime-3',
'dataset_name': 'legmlai/openhermes-fr',
'dataset_split': 'train',
'input_field': 'prompt',
'target_field': 'accepted_completion',
'filter_bad_entries': True,
'bad_entry_field': 'bad_entry',
'packing': False,
'max_prompt_length': 12288,
'max_completion_length': 8192,
'truncation': True,
'dataloader_num_workers': 10,
'dataloader_pin_memory': True,
'dataloader_prefetch_factor': 3,
'max_grad_norm': 1.0,
'group_by_length': True
}),
'artifacts': json.dumps([]),
'logs': json.dumps([]),
'last_updated': datetime.now().isoformat()
},
{
'experiment_id': 'exp_20250720_134319',
'name': 'petite-elle-l-aime-3-1',
'description': 'SmolLM3 fine-tuning experiment',
'created_at': '2025-07-20T11:54:31.993219',
'status': 'running',
'metrics': json.dumps([
{
'timestamp': '2025-07-20T11:54:31.993219',
'step': 25,
'metrics': {
'loss': 1.166,
'grad_norm': 10.375,
'learning_rate': 7e-08,
'num_tokens': 1642080.0,
'mean_token_accuracy': 0.7590958896279335,
'epoch': 0.004851130919895701
}
},
{
'timestamp': '2025-07-20T11:54:33.589487',
'step': 25,
'metrics': {
'gpu_0_memory_allocated': 17.202261447906494,
'gpu_0_memory_reserved': 75.474609375,
'gpu_0_utilization': 0,
'cpu_percent': 2.7,
'memory_percent': 10.1
}
}
]),
'parameters': json.dumps({
'model_name': 'HuggingFaceTB/SmolLM3-3B',
'max_seq_length': 12288,
'use_flash_attention': True,
'use_gradient_checkpointing': False,
'batch_size': 8,
'gradient_accumulation_steps': 16,
'learning_rate': 3.5e-06,
'weight_decay': 0.01,
'warmup_steps': 1200,
'max_iters': 18000,
'eval_interval': 1000,
'log_interval': 25,
'save_interval': 2000,
'optimizer': 'adamw_torch',
'beta1': 0.9,
'beta2': 0.999,
'eps': 1e-08,
'scheduler': 'cosine',
'min_lr': 3.5e-07,
'fp16': False,
'bf16': True,
'ddp_backend': 'nccl',
'ddp_find_unused_parameters': False,
'save_steps': 2000,
'eval_steps': 1000,
'logging_steps': 25,
'save_total_limit': 5,
'eval_strategy': 'steps',
'metric_for_best_model': 'eval_loss',
'greater_is_better': False,
'load_best_model_at_end': True,
'data_dir': None,
'train_file': None,
'validation_file': None,
'test_file': None,
'use_chat_template': True,
'chat_template_kwargs': {'add_generation_prompt': True, 'no_think_system_message': True},
'enable_tracking': True,
'trackio_url': 'https://tonic-test-trackio-test.hf.space',
'trackio_token': None,
'log_artifacts': True,
'log_metrics': True,
'log_config': True,
'experiment_name': 'petite-elle-l-aime-3-1',
'dataset_name': 'legmlai/openhermes-fr',
'dataset_split': 'train',
'input_field': 'prompt',
'target_field': 'accepted_completion',
'filter_bad_entries': True,
'bad_entry_field': 'bad_entry',
'packing': False,
'max_prompt_length': 12288,
'max_completion_length': 8192,
'truncation': True,
'dataloader_num_workers': 10,
'dataloader_pin_memory': True,
'dataloader_prefetch_factor': 3,
'max_grad_norm': 1.0,
'group_by_length': True
}),
'artifacts': json.dumps([]),
'logs': json.dumps([]),
'last_updated': datetime.now().isoformat()
}
]
try:
# Initialize HF API
api = HfApi(token=hf_token)
# First, try to create the dataset repository
print(f"Creating dataset repository: {dataset_repo}")
try:
create_repo(
repo_id=dataset_repo,
token=hf_token,
repo_type="dataset",
exist_ok=True,
private=True # Make it private for security
)
print(f"✅ Dataset repository created: {dataset_repo}")
except Exception as e:
print(f"⚠️ Repository creation failed (may already exist): {e}")
# Create dataset
dataset = Dataset.from_list(initial_experiments)
# Get the project root directory (2 levels up from this script)
project_root = Path(__file__).parent.parent.parent
templates_dir = project_root / "templates" / "datasets"
readme_path = templates_dir / "readme.md"
# Read README content if it exists
readme_content = None
if readme_path.exists():
with open(readme_path, 'r', encoding='utf-8') as f:
readme_content = f.read()
print(f"✅ Found README template: {readme_path}")
# Push to HF Hub
print("Pushing dataset to HF Hub...")
dataset.push_to_hub(
dataset_repo,
token=hf_token,
private=False # Make it private for security
)
# Create README separately if available
if readme_content:
try:
print("Uploading README.md...")
api.upload_file(
path_or_fileobj=readme_content.encode('utf-8'),
path_in_repo="README.md",
repo_id=dataset_repo,
repo_type="dataset",
token=hf_token
)
print("📝 Uploaded README.md successfully")
except Exception as e:
print(f"⚠️ Could not upload README: {e}")
print(f"✅ Successfully created dataset: {dataset_repo}")
print(f"📊 Added {len(initial_experiments)} experiments")
if readme_content:
print("📝 Included README from templates")
print("🔓 Dataset is public (accessible to everyone)")
print(f"👤 Created by: {username}")
print("\n🎯 Next steps:")
print("1. Set HF_TOKEN in your Hugging Face Space environment")
print("2. Deploy the updated app.py to your Space")
print("3. The app will now load experiments from the dataset")
return True
except Exception as e:
print(f"❌ Failed to create dataset: {e}")
print("\nTroubleshooting:")
print("1. Check that your HF token has write permissions")
print("2. Verify the dataset repository name is available")
print("3. Try creating the dataset manually on HF first")
return False
if __name__ == "__main__":
setup_trackio_dataset() |