import os
import torch as pt
from torch.amp import autocast, GradScaler
from torch.optim.lr_scheduler import LinearLR, CosineAnnealingLR, SequentialLR
from tqdm.auto import tqdm
from configuration_nula import NulaConfig
from modeling_nula import NulaForImageClassification
from dataset_nula import get_loaders, get_device

NUM_EPOCHS   = 50
LR           = 1e-3
WEIGHT_DECAY = 0.01
WARMUP_STEPS = 5
GRAD_CLIP    = 1.0
SAVE_EVERY   = 5
CHECKPOINT_DIR = "./checkpoints"
BEST_MODEL_DIR = "./nula-best-model"
FINAL_MODEL_DIR = "./nula-final-model"

def train_epoch(model, loader, optimizer, scaler, device, epoch):
    model.train()
    total_loss, total_correct, total_examples = 0.0, 0, 0
    pbar = tqdm(loader, desc=f"epoch {epoch}", leave=False)
    use_amp = "cuda" in str(device)
    for batch in pbar:
        x = batch["pixel_values"].to(device, non_blocking=True)
        y = batch["labels"].to(device, non_blocking=True)
        optimizer.zero_grad(set_to_none=True)
        with autocast("cuda", enabled=use_amp):
            out = model(pixel_values=x, labels=y)
            loss = out.loss
            
        scaler.scale(loss).backward()
        scaler.unscale_(optimizer)
        pt.nn.utils.clip_grad_norm_(model.parameters(), max_norm=GRAD_CLIP)
        scaler.step(optimizer)
        scaler.update()
        
        total_loss += loss.item() * y.size(0)
        total_correct += (out.logits.argmax(dim=1) == y).sum().item()
        total_examples += y.size(0)
        
        pbar.set_postfix(loss=f"{loss.item():.4f}", acc=f"{100 * total_correct / total_examples:.2f}%")
    return total_loss / total_examples, total_correct / total_examples

@pt.no_grad()
def evaluate(model, loader, device):
    model.eval()
    total_loss, total_correct, total_examples = 0.0, 0, 0
    for batch in loader:
        x = batch["pixel_values"].to(device, non_blocking=True)
        y = batch["labels"].to(device, non_blocking=True)
        out = model(pixel_values=x, labels=y)
        
        total_loss += out.loss.item() * y.size(0)
        total_correct += (out.logits.argmax(dim=1) == y).sum().item()
        total_examples += y.size(0)

    return total_loss / total_examples, total_correct / total_examples

def train_model(model, train_loader, test_loader, optimizer, scheduler, scaler, device):
    best_val_acc = 0.0
    os.makedirs(CHECKPOINT_DIR, exist_ok=True)

    print(f"training on {device}")
    for epoch in range(1, NUM_EPOCHS + 1):
        train_loss, train_acc = train_epoch(model, train_loader, optimizer, scaler, device, epoch)
        val_loss, val_acc = evaluate(model, test_loader, device)
        scheduler.step()

        if epoch % SAVE_EVERY == 0:
            save_path = f"{CHECKPOINT_DIR}/epoch{epoch}"
            model.save_pretrained(save_path)
        if val_acc > best_val_acc:
            best_val_acc = val_acc
            model.save_pretrained(BEST_MODEL_DIR)
            print(f"new best: {100 * best_val_acc:.2f}%")
            
        current_lr = optimizer.param_groups[0]["lr"]
        
        print(f"|{'—'*60}|")
        print(f"epoch [{epoch}/{NUM_EPOCHS}]")
        print(f"lr: {current_lr:.6f}")
        print(f"train_loss: {train_loss:.4f}")
        print(f"train_acc: {train_acc*100:.2f}%")
        print(f"val loss: {val_loss:.4f}")
        print(f"val_acc: {val_acc*100:.2f}%")
        print(f"best: {best_val_acc*100:.2f}%")

    model.save_pretrained(FINAL_MODEL_DIR)
    print("final model saved")


if __name__ == "__main__":
    DEVICE = get_device()
    train_loader, test_loader = get_loaders()

    cfg = NulaConfig(block_channels=(128, 256, 512), classifier_hidden_dim=512, use_se=True)
    model = NulaForImageClassification(cfg).to(DEVICE)

    optimizer = pt.optim.AdamW(model.parameters(), lr=LR, weight_decay=WEIGHT_DECAY)
    warmup = LinearLR(optimizer, start_factor=0.1, end_factor=1.0, total_iters=WARMUP_STEPS)
    cosine = CosineAnnealingLR(optimizer, T_max=NUM_EPOCHS - WARMUP_STEPS)
    scheduler = SequentialLR(optimizer, schedulers=[warmup, cosine], milestones=[WARMUP_STEPS])
    scaler = GradScaler("cuda")

    print("enjoy <3\n")
    train_model(model, train_loader, test_loader, optimizer, scheduler, scaler, DEVICE)