D722ad53 D442 458e B561 Cab7e12fcbbf

Source document

optimizer = optim.Adam(model.parameters(), lr=0.001) # Using Adam optimizer scheduler = ReduceLROnPlateau(optimizer, mode='min', factor=0.1, patience=5, verbose=True) scaler = GradScaler() try: for epoch in range(100): running_loss = 0.0 for batch_idx, batch in enumerate(data_loader): inputs = batch['query'].float().to(device) labels = batch['label'].long().to(device) optimizer.zero_grad() with autocast(): outputs = model(inputs) loss = criterion(outputs, labels) scaler.scale(loss).backward() scaler.step(optimizer) scaler.update() running_loss += loss.item() # Log the processing log_entry = { 'timestamp': logging.LogRecord.created, 'level': 'INFO', 'epoch': epoch, 'batch_idx': batch_idx, 'batch_size': len(inputs), 'loss': loss.item(), 'learning_rate': optimizer.param_groups[0]['lr'] } log_json = json.dumps(log_entry) logging.info(log_json)