Spaces:
Runtime error
Runtime error
File size: 7,378 Bytes
c3efd49 |
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 |
"""Checkpoint management for training."""
import torch
import json
from pathlib import Path
from typing import Dict, Any, Optional, List
from datetime import datetime
import logging
logger = logging.getLogger(__name__)
class CheckpointManager:
"""
Manages model checkpoints during training.
Handles saving, loading, and cleanup of checkpoints.
"""
def __init__(
self,
checkpoint_dir: str = "checkpoints",
max_checkpoints: int = 5,
save_interval: int = 10
):
"""
Initialize checkpoint manager.
Args:
checkpoint_dir: Directory to save checkpoints
max_checkpoints: Maximum number of checkpoints to keep
save_interval: Save checkpoint every N episodes
"""
self.checkpoint_dir = Path(checkpoint_dir)
self.checkpoint_dir.mkdir(parents=True, exist_ok=True)
self.max_checkpoints = max_checkpoints
self.save_interval = save_interval
self.checkpoint_history = []
logger.info(f"CheckpointManager initialized: dir={checkpoint_dir}, max={max_checkpoints}, interval={save_interval}")
def should_save(self, episode: int) -> bool:
"""
Check if checkpoint should be saved at this episode.
Args:
episode: Current episode number
Returns:
True if should save checkpoint
"""
if episode == 0:
return False
return episode % self.save_interval == 0
def save_checkpoint(
self,
model,
episode: int,
metrics: Optional[Dict[str, Any]] = None,
is_best: bool = False
) -> str:
"""
Save a checkpoint.
Args:
model: Model to save
episode: Current episode number
metrics: Optional training metrics
is_best: Whether this is the best model so far
Returns:
Path to saved checkpoint
"""
# Create checkpoint filename
if is_best:
filename = "best_model.pt"
else:
filename = f"checkpoint_episode_{episode}.pt"
checkpoint_path = self.checkpoint_dir / filename
# Prepare metadata
metadata = {
'episode': episode,
'timestamp': datetime.now().isoformat(),
'is_best': is_best
}
if metrics:
metadata['metrics'] = metrics
# Save checkpoint
model.save_checkpoint(str(checkpoint_path), metadata=metadata)
# Record in history
self.checkpoint_history.append({
'path': str(checkpoint_path),
'episode': episode,
'timestamp': metadata['timestamp'],
'is_best': is_best
})
logger.info(f"Checkpoint saved: {checkpoint_path}")
# Cleanup old checkpoints
if not is_best:
self._cleanup_old_checkpoints()
return str(checkpoint_path)
def load_checkpoint(
self,
model,
checkpoint_path: Optional[str] = None,
load_best: bool = False
) -> Dict[str, Any]:
"""
Load a checkpoint.
Args:
model: Model to load checkpoint into
checkpoint_path: Optional specific checkpoint path
load_best: If True, load best model
Returns:
Checkpoint metadata
"""
if load_best:
checkpoint_path = str(self.checkpoint_dir / "best_model.pt")
elif checkpoint_path is None:
# Load most recent checkpoint
checkpoint_path = self._get_latest_checkpoint()
if checkpoint_path is None:
raise FileNotFoundError("No checkpoints found")
metadata = model.load_checkpoint(checkpoint_path)
logger.info(f"Checkpoint loaded: {checkpoint_path}")
logger.info(f"Episode: {metadata.get('episode', 'unknown')}")
return metadata
def _get_latest_checkpoint(self) -> Optional[str]:
"""
Get path to most recent checkpoint.
Returns:
Path to latest checkpoint or None
"""
checkpoints = sorted(
self.checkpoint_dir.glob("checkpoint_episode_*.pt"),
key=lambda p: p.stat().st_mtime,
reverse=True
)
if checkpoints:
return str(checkpoints[0])
return None
def _cleanup_old_checkpoints(self) -> None:
"""Remove old checkpoints, keeping only the most recent N."""
# Get all episode checkpoints (not best model)
checkpoints = sorted(
self.checkpoint_dir.glob("checkpoint_episode_*.pt"),
key=lambda p: p.stat().st_mtime,
reverse=True
)
# Remove old checkpoints
if len(checkpoints) > self.max_checkpoints:
for old_checkpoint in checkpoints[self.max_checkpoints:]:
old_checkpoint.unlink()
logger.debug(f"Removed old checkpoint: {old_checkpoint}")
def list_checkpoints(self) -> List[Dict[str, Any]]:
"""
List all available checkpoints.
Returns:
List of checkpoint information
"""
checkpoints = []
for checkpoint_file in self.checkpoint_dir.glob("*.pt"):
stat = checkpoint_file.stat()
checkpoints.append({
'path': str(checkpoint_file),
'name': checkpoint_file.name,
'size_mb': stat.st_size / (1024 * 1024),
'modified': datetime.fromtimestamp(stat.st_mtime).isoformat()
})
return sorted(checkpoints, key=lambda x: x['modified'], reverse=True)
def get_checkpoint_history(self) -> List[Dict[str, Any]]:
"""
Get checkpoint history.
Returns:
List of checkpoint records
"""
return self.checkpoint_history
def save_training_state(
self,
state: Dict[str, Any],
filename: str = "training_state.json"
) -> None:
"""
Save training state to JSON.
Args:
state: Training state dictionary
filename: Output filename
"""
state_path = self.checkpoint_dir / filename
with open(state_path, 'w') as f:
json.dump(state, f, indent=2)
logger.info(f"Training state saved: {state_path}")
def load_training_state(
self,
filename: str = "training_state.json"
) -> Dict[str, Any]:
"""
Load training state from JSON.
Args:
filename: State filename
Returns:
Training state dictionary
"""
state_path = self.checkpoint_dir / filename
if not state_path.exists():
raise FileNotFoundError(f"Training state not found: {state_path}")
with open(state_path, 'r') as f:
state = json.load(f)
logger.info(f"Training state loaded: {state_path}")
return state
|