muon

train-Copy1.py

@@ -1,1005 +0,0 @@
-import os
-os.environ["NCCL_P2P_DISABLE"] = "1"
-os.environ["NCCL_IB_DISABLE"] = "1" # comment it on H100
-os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"
-import math
-import torch
-import numpy as np
-import matplotlib.pyplot as plt
-from torch.utils.data import DataLoader, Sampler
-from torch.utils.data.distributed import DistributedSampler
-from torch.optim.lr_scheduler import LambdaLR
-from collections import defaultdict
-from diffusers import UNet2DConditionModel,AsymmetricAutoencoderKL,FlowMatchEulerDiscreteScheduler
-from accelerate import Accelerator, DeepSpeedPlugin
-from datasets import load_from_disk
-from tqdm import tqdm
-from PIL import Image, ImageOps
-import wandb
-import random,time
-import gc
-from accelerate.state import DistributedType
-from torch.distributed import broadcast_object_list
-from torch.utils.checkpoint import checkpoint
-from diffusers.models.attention_processor import AttnProcessor2_0
-from datetime import datetime
-import bitsandbytes as bnb
-import torch.nn.functional as F
-from collections import deque
-from transformers import Qwen3_5Tokenizer, Qwen3_5ForConditionalGeneration
-import argparse
-# pip install git+https://github.com/recoilme/muon_adamw8bit.git
-from muon_adamw8bit import MuonAdamW8bit
-
-# --------------------------- Параметры ---------------------------
-ds_path = "datasets/ds1234_noanime_704_vae8x16x"
-project = "unet"
-
-# 1. Считаем локальный батч
-gpu_mem_gb = torch.cuda.get_device_properties(0).total_memory / 1e9
-local_bs = max(1, int((gpu_mem_gb / 32) * 8))
-# 2. Умножаем на количество ГПУ, чтобы получить ГЛОБАЛЬНЫЙ батч
-num_gpus = torch.cuda.device_count()
-batch_size = local_bs * num_gpus
-print(f"GPUs: {num_gpus}, Local BS: {local_bs}, Global BS: {local_bs * num_gpus}")
-base_learning_rate = 1e-5
-min_learning_rate = 1e-7
-num_epochs = num_gpus
-sample_interval_share = 20
-cfg_dropout = 0.10
-max_length = 248
-use_precomputed_embeddings = False
-use_wandb = True
-use_comet_ml = False
-save_model = True
-use_decay = True
-fbp = False
-torch_compile = False
-unet_gradient = True
-loss_normalize = False
-fixed_seed = False
-shuffle = True
-muon_lr_scale = 300
-optimizer_type = "muon_adam8bit"
-if optimizer_type == "muon_adam8bit":
-    batch_size = num_gpus * max(1, int((gpu_mem_gb / 32) * 3))
-comet_ml_api_key = "Agctp26mbqnoYrrlvQuKSTk6r" 
-comet_ml_workspace = "recoilme" 
-torch.backends.cuda.matmul.allow_tf32 = True
-torch.backends.cudnn.allow_tf32 = True
-# Включение Flash Attention 2/SDPA #MAX_JOBS=4 pip install flash-attn --no-build-isolation
-torch.backends.cuda.enable_flash_sdp(True)
-torch.backends.cuda.enable_mem_efficient_sdp(True)
-torch.backends.cuda.enable_math_sdp(False) # Отключаем медленный вариант
-save_barrier = 1.25
-warmup_percent = 0.01
-betta2 = 0.995
-eps = 1e-7
-clip_grad_norm = 1.0
-limit = 0
-checkpoints_folder = ""
-gradient_accumulation_steps = 1
-dtype = torch.float32
-mixed_precision = "no"
-
-# Параметры для диффузии
-n_diffusion_steps = 40
-samples_to_generate = 12
-guidance_scale = 4
-
-# Папки для сохранения результатов
-generated_folder = "samples"
-os.makedirs(generated_folder, exist_ok=True)
-
-# Настройка seed
-current_date = datetime.now()
-seed = int(current_date.strftime("%Y%m%d")) + 42
-if fixed_seed:
-    torch.manual_seed(seed)
-    np.random.seed(seed)
-    random.seed(seed)
-    if torch.cuda.is_available():
-        torch.cuda.manual_seed_all(seed)
-
-accelerator = Accelerator(
-    mixed_precision=mixed_precision,
-    gradient_accumulation_steps=gradient_accumulation_steps
-)
-device = accelerator.device
-
-print("init")
-# Создаём объект ArgumentParser с рассчитанными значениями по умолчанию
-parser = argparse.ArgumentParser(description='Train a model on a dataset.')
-parser.add_argument('--ds-path', type=str, default=ds_path, help='Path to the dataset')
-parser.add_argument('--ep', type=int, default=num_epochs, help='Number of epochs to train the model')
-parser.add_argument('--batch', type=int, default=batch_size, help='Total batch size')
-parser.add_argument('--min-lr', type=float, default=min_learning_rate, help='Minimum learning rate')
-parser.add_argument('--max-lr', type=float, default=base_learning_rate, help='Maximum learning rate')
-parser.add_argument('--dry-run', action='store_true',default=False, help='Run configuration without saving/sampling')
-
-# Парсим аргументы командной строки
-args = parser.parse_args()
-
-# Используем значения из аргументов
-batch_size = args.batch
-ds_path = args.ds_path
-base_learning_rate = args.max_lr
-min_learning_rate = args.min_lr
-num_epochs = args.ep
-if args.dry_run:
-    save_model = False
-
-# --------------------------- Инициализация WandB ---------------------------
-if accelerator.is_main_process:
-    if use_wandb:
-        wandb.init(project=project, config={
-            "batch_size": batch_size,
-            "base_learning_rate": base_learning_rate,
-            "num_epochs": num_epochs,
-            "optimizer_type": optimizer_type,
-        })
-    if use_comet_ml:
-        from comet_ml import Experiment
-        comet_experiment = Experiment(
-            api_key=comet_ml_api_key,
-            project_name=project,
-            workspace=comet_ml_workspace
-        )
-        hyper_params = {
-            "batch_size": batch_size,
-            "base_learning_rate": base_learning_rate,
-            "num_epochs": num_epochs,
-        }
-        comet_experiment.log_parameters(hyper_params)
-
-# --------------------------- Загрузка моделей ---------------------------
-vae = AsymmetricAutoencoderKL.from_pretrained("vae", torch_dtype=dtype).to(device).eval()
-scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained("scheduler")
-tokenizer = None
-text_encoder = None
-
-def load_text_encoder():
-    global tokenizer, text_encoder
-    if tokenizer is None:
-        tokenizer = Qwen3_5Tokenizer.from_pretrained("tokenizer")
-    if text_encoder is None:
-        text_encoder = Qwen3_5ForConditionalGeneration.from_pretrained(
-            "text_encoder",
-            torch_dtype=torch.float16
-        ).to(device).eval()
-
-def encode_texts(texts, max_length=max_length):
-    load_text_encoder()
-    if texts is None:
-        texts = [""]
-    if isinstance(texts, str):
-        texts = [texts]
-
-    with torch.no_grad():
-        
-        # --- 2. QWEN Энкодер (через Chat Template) ---
-        # 1. Собираем текстовые промпты оборачивая их в Chat Template
-        formatted_prompts = []
-        for t in texts:
-            messages = [{"role": "user", "content": [{"type": "text", "text": t}]}]
-            res_text = tokenizer.apply_chat_template(
-                messages, 
-                add_generation_prompt=True, 
-                tokenize=False 
-            )
-            formatted_prompts.append(res_text)
-
-        # 2. Токенизируем, режем и добавляем паддинг за один раз
-        toks = tokenizer(
-            formatted_prompts,
-            padding="max_length",
-            max_length=max_length,
-            truncation=True,
-            return_tensors="pt"
-        ).to(device)
-
-        # 3. Прогоняем через модель
-        outputs = text_encoder(
-            input_ids=toks.input_ids, 
-            attention_mask=toks.attention_mask,
-            output_hidden_states=True
-        )
-
-        layer_index = -2
-        last_hidden = outputs.hidden_states[layer_index]
-        seq_len = toks.attention_mask.sum(dim=1) - 1
-        pooled = last_hidden[torch.arange(len(last_hidden)), seq_len.clamp(min=0)]
-        # --- НОВАЯ ЛОГИКА: ОБЪЕДИНЕНИЕ ДЛЯ КРОСС-ВНИМАНИЯ ---
-        # 1. Расширяем пулинг-вектор до последовательности [B, 1, 1024]
-        pooled_expanded = pooled.unsqueeze(1) 
-                        
-        # 2. Объединяем последовательность токенов и пулинг-вектор
-        # !!! ИЗМЕНЕНИЕ ЗДЕСЬ !!!: Пулинг идет ПЕРВЫМ
-        # Теперь: [B, 1 + L, 1024]. Пулинг стал токеном в НАЧАЛЕ.
-        new_encoder_hidden_states = torch.cat([pooled_expanded, last_hidden], dim=1) 
-                        
-        # 3. Обновляем маску внимания для нового токена
-        # Маска внимания: [B, 1 + L]. Добавляем 1 в НАЧАЛО.
-        # torch.ones((batch_size, 1), device=device) создает маску [B, 1] со значениями 1.
-        new_attention_mask = torch.cat([torch.ones((last_hidden.shape[0], 1), device=device), toks.attention_mask], dim=1)
-        return new_encoder_hidden_states.to(dtype), new_attention_mask
-        
-shift_factor = getattr(vae.config, "shift_factor", 0.0)
-if shift_factor is None:
-    shift_factor = 0.0
-
-scaling_factor = getattr(vae.config, "scaling_factor", 1.0)
-if scaling_factor is None:
-    scaling_factor = 1.0
-    
-mean = getattr(vae.config, "latents_mean", None)
-std = getattr(vae.config, "latents_std", None)
-if mean is not None and std is not None:
-    latents_std = torch.tensor(std, device=device, dtype=dtype).view(1, len(std), 1, 1)
-    latents_mean = torch.tensor(mean, device=device, dtype=dtype).view(1, len(mean), 1, 1)
-
-import numpy as np
-from torch.utils.data import Sampler
-
-
-class DistributedResolutionBatchSampler(Sampler):
-    def __init__(self, dataset, batch_size, num_replicas, rank, drop_last=True, shuffle=True):
-        self.dataset = dataset
-        self.num_replicas = num_replicas
-        self.rank = rank
-        self.shuffle = shuffle
-        self.drop_last = drop_last
-        self.epoch = 0
-
-        # batch на одну GPU
-        self.batch_size = max(1, batch_size // num_replicas)
-        self.global_batch = self.batch_size * num_replicas
-
-        try:
-            widths = np.asarray(dataset["width"])
-            heights = np.asarray(dataset["height"])
-        except KeyError:
-            widths = np.zeros(len(dataset))
-            heights = np.zeros(len(dataset))
-
-        # --- группировка индексов ---
-        groups = {}
-        for i, (w, h) in enumerate(zip(widths, heights)):
-            groups.setdefault((w, h), []).append(i)
-
-        # --- создаём список всех глобальных батчей ---
-        all_batches = []
-
-        for indices in groups.values():
-
-            idx = np.asarray(indices, dtype=np.int64)
-
-            num_batches = len(idx) // self.global_batch
-            if num_batches == 0:
-                continue
-
-            idx = idx[: num_batches * self.global_batch]
-
-            batches = idx.reshape(num_batches, self.global_batch)
-
-            all_batches.append(batches)
-
-        if len(all_batches) > 0:
-            self.global_batches = np.concatenate(all_batches, axis=0)
-        else:
-            self.global_batches = np.empty((0, self.global_batch), dtype=np.int64)
-
-        self.num_batches = len(self.global_batches)
-
-    def __iter__(self):
-
-        rng = np.random.RandomState(self.epoch)
-
-        order = np.arange(self.num_batches)
-
-        if self.shuffle:
-            rng.shuffle(order)
-
-        start = self.rank * self.batch_size
-        end = start + self.batch_size
-
-        for i in order:
-            yield self.global_batches[i][start:end]
-
-    def __len__(self):
-        return self.num_batches
-
-    def set_epoch(self, epoch):
-        self.epoch = epoch
-        
-
-
-# --- [UPDATED] Функция для фиксированных семплов ---
-def get_fixed_samples_by_resolution(dataset, samples_per_group=1):
-    size_groups = defaultdict(list)
-    try:
-        widths = dataset["width"]
-        heights = dataset["height"]
-    except KeyError:
-        widths = [0] * len(dataset)
-        heights = [0] * len(dataset)
-    for i, (w, h) in enumerate(zip(widths, heights)):
-        size = (w, h)
-        size_groups[size].append(i)
-    
-    fixed_samples = {}
-    for size, indices in size_groups.items():
-        n_samples = min(samples_per_group, len(indices))
-        if len(size_groups)==1:
-            n_samples = samples_to_generate
-        if n_samples == 0:
-            continue
-        sample_indices = random.sample(indices, n_samples)
-        samples_data = [dataset[idx] for idx in sample_indices]
-        
-        latents = torch.tensor(np.array([item["vae"] for item in samples_data])).to(device=device, dtype=dtype)
-        texts = [item["text"] for item in samples_data]
-        
-        # Кодируем тексты на лету, чтобы получить маски и пулинг
-        #embeddings, masks = encode_texts(texts)
-        if use_precomputed_embeddings:
-            embeddings = torch.tensor(
-                np.array([item["embeddings"] for item in samples_data]),
-                device=device,
-                dtype=dtype
-            )
-            masks = torch.tensor(
-                np.array([item["attention_mask"] for item in samples_data]),
-                device=device,
-                dtype=torch.int64
-            )
-        else:
-            embeddings, masks = encode_texts(texts)
-        
-        fixed_samples[size] = (latents, embeddings, masks, texts)
-    
-    print(f"Создано {len(fixed_samples)} групп фиксированных семплов по разрешениям")
-    return fixed_samples
-
-if limit > 0:
-    dataset = load_from_disk(ds_path).select(range(limit))
-else:
-    dataset = load_from_disk(ds_path)
-
-
-print(f"images: {len(dataset)}")
-
-def collate_fn_simple(batch):
-
-    latents = torch.from_numpy(
-        np.array([item["vae"] for item in batch], dtype=np.float16)
-    ).to(device, dtype=dtype)
-
-    if use_precomputed_embeddings:
-        embeddings = torch.from_numpy(
-            np.array([item["embeddings"] for item in batch], dtype=np.float16)
-        ).to(device, dtype=dtype)
-
-        attention_mask = torch.from_numpy(
-            np.array([item["attention_mask"] for item in batch], dtype=np.int64)
-        ).to(device)
-
-        return latents, embeddings, attention_mask
-
-    raw_texts = [item["text"] for item in batch]
-
-    texts = [
-        "" if t.lower().startswith("zero") 
-        else "" if random.random() < cfg_dropout
-        else t[1:].lstrip() if t.startswith(".")
-        else t.replace("The image shows ", "").replace("The image is ", "").replace("This image captures ","").strip()
-        for t in raw_texts
-    ]
-
-    embeddings, attention_mask = encode_texts(texts)
-    attention_mask = attention_mask.to(dtype=torch.int64)
-
-    return latents, embeddings, attention_mask
-
-batch_sampler = DistributedResolutionBatchSampler(
-        dataset=dataset,
-        batch_size=batch_size,
-        num_replicas=accelerator.num_processes,
-        rank=accelerator.process_index,
-        shuffle = shuffle
-    )
-
-dataloader = DataLoader(dataset, batch_sampler=batch_sampler, collate_fn=collate_fn_simple)
-
-if accelerator.is_main_process:
-    print("Total samples", len(dataloader))
-dataloader = accelerator.prepare(dataloader)
-
-start_epoch = 0
-global_step = 0
-total_training_steps = (len(dataloader) * num_epochs)
-world_size = accelerator.state.num_processes
-
-# Загрузка UNet
-latest_checkpoint = os.path.join(checkpoints_folder, project)
-if os.path.isdir(latest_checkpoint):
-    print("Загружаем UNet из чекпоинта:", latest_checkpoint)
-    unet = UNet2DConditionModel.from_pretrained(latest_checkpoint).to(device=device, dtype=dtype)
-    if unet_gradient:
-        unet.enable_gradient_checkpointing()
-    unet.set_use_memory_efficient_attention_xformers(False)
-    try:
-        unet.set_attn_processor(AttnProcessor2_0())
-    except Exception as e:
-        print(f"Ошибка при включении SDPA: {e}")
-        unet.set_use_memory_efficient_attention_xformers(True)
-else:
-    raise FileNotFoundError(f"UNet checkpoint not found at {latest_checkpoint}")
-
-# --------------------------- Muon Implementation (FIXED for UNet Conv2d) ---------------------------
-import torch.distributed as dist
-
-def zeropower_via_newtonschulz5(G, steps=10, eps=1e-7):
-    """
-    Оптимизированная версия: поддерживает BF16 и батчинг.
-    """
-    a, b, c = (3.4445, -4.7750, 2.0315)
-    
-    # Используем bfloat16 для скорости (если карта поддерживает, иначе float16/32)
-    # Важно: приведение типа делаем здесь
-    if G.dtype != torch.bfloat16 and G.dtype != torch.float32:
-         # Если пришло float16, лучше считать в float32 или bfloat16 для точности
-         X = G.float() 
-    else:
-         X = G
-
-    # Логика транспонирования (M > N)
-    transposed = G.size(-2) > G.size(-1)
-    if transposed:
-        X = X.mT # .mT - это View, не копирует память
-    
-    # Нормализация по последним двум осям (корректно для любых размерностей)
-    X = X / (X.norm(dim=(-2, -1), keepdim=True) + eps)
-    
-    for _ in range(steps):
-        # A = X @ X.T
-        A = X @ X.mT
-        # B = b*A + c*A@A
-        B = b * A + c * A @ A
-        # X = a*X + B@X
-        X = a * X + B @ X
-        
-    return X.mT if transposed else X
-
-class MuonAdamW8bit(torch.optim.Optimizer):
-    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0.01, 
-                 muon_lr=None, muon_momentum=0.95, ns_steps=5):
-        params = list(params)
-        
-        matrix_params = []
-        scalar_params = []
-        
-        for p in params:
-            if p.ndim >= 2:
-                matrix_params.append(p)
-            else:
-                scalar_params.append(p)
-        
-        # --- ВАЖНОЕ ИСПРАВЛЕНИЕ LR ---
-        # Если базовый lr=1e-5, Muon должен быть ~0.01 -> 0.02
-        # Ставим коэф x1000 или x2000 от базового, или задаем явно.
-        # Автор ставит 0.02. Давайте поставим 0.01 как безопасный минимум для старта.
-        actual_muon_lr = muon_lr if muon_lr is not None else lr * muon_lr_scale
-        self.muon_lr_scale = actual_muon_lr / lr if lr > 0 else 1.0
-        self.ns_steps = ns_steps
-        
-        # Инициализируем Muon (передаем ему только матрицы)
-        # Обратите внимание: lr передаем актуальный
-        self.muon_opt = MuonInternal(matrix_params, lr=actual_muon_lr, momentum=muon_momentum, ns_steps=ns_steps)
-        
-        # Adam для скаляров (biases, norms)
-        self.adam_opt = bnb.optim.AdamW8bit(scalar_params, lr=lr, betas=betas, eps=eps, weight_decay=weight_decay)
-
-        self.defaults = dict(lr=lr) 
-        self.state = {}
-        self.param_groups = self.adam_opt.param_groups
-
-    def zero_grad(self, set_to_none=False):
-        self.muon_opt.zero_grad(set_to_none)
-        self.adam_opt.zero_grad(set_to_none)
-
-    @torch.no_grad()
-    def step(self, closure=None):
-        # Синхронизация LR (если шедулер меняет lr в adam группах)
-        current_base_lr = self.adam_opt.param_groups[0]['lr']
-        for group in self.muon_opt.param_groups:
-            group['lr'] = current_base_lr * self.muon_lr_scale
-            
-        self.muon_opt.step(closure)
-        self.adam_opt.step(closure)
-
-    # state_dict/load_state_dict оставляем как было у вас
-    def state_dict(self):
-        return {
-            'muon': self.muon_opt.state_dict(),
-            'adam': self.adam_opt.state_dict()
-        }
-
-    def load_state_dict(self, state_dict):
-        self.muon_opt.load_state_dict(state_dict['muon'])
-        self.adam_opt.load_state_dict(state_dict['adam'])
-
-
-# Внутренний класс Muon (логика обновления матриц)
-class MuonInternal(torch.optim.Optimizer):
-    def __init__(self, params, lr=0.01, momentum=0.95, ns_steps=5):
-        super().__init__(params, dict(lr=lr, momentum=momentum, ns_steps=ns_steps))
-        self.distributed = torch.distributed.is_initialized()
-
-    @torch.no_grad()
-    def step(self, closure=None):
-        loss = None
-        if closure is not None:
-            with torch.enable_grad():
-                loss = closure()
-
-        for group in self.param_groups:
-            lr = group["lr"]
-            momentum = group["momentum"]
-            ns_steps = group["ns_steps"]
-
-            for p in group["params"]:
-                if p.grad is None:
-                    continue
-                
-                g = p.grad
-                state = self.state[p]
-                
-                if "momentum_buffer" not in state:
-                    state["momentum_buffer"] = torch.zeros_like(g, dtype=torch.float32)
-                
-                buf = state["momentum_buffer"]
-                
-                # Обновление момента
-                buf.mul_(momentum).add_(g.float())
-                
-                # Nesterov
-                update = g.float().add(buf, alpha=momentum)
-                
-                # Обработка Conv2d (flatten)
-                original_shape = g.shape
-                if g.ndim == 4:
-                    update = update.view(update.size(0), -1)
-                
-                # Ортогонализация (теперь принимает update и steps)
-                update = zeropower_via_newtonschulz5(update, steps=ns_steps)
-                
-                # Масштабирование (стандарт для Muon)
-                update *= max(1, update.size(-2) / update.size(-1)) ** 0.5
-                
-                # Возврат формы для Conv
-                if g.ndim == 4:
-                    update = update.view(original_shape)
-                    
-                p.add_(update, alpha=-lr)
-        return loss
-
-# --------------------------- End Muon Implementation ---------------------------
-
-def create_optimizer(name, params):
-    if name == "adam8bit":
-        return bnb.optim.AdamW8bit(
-            params, lr=base_learning_rate, betas=(0.9, betta2), eps=eps, weight_decay=0.01
-        )
-    elif name == "adam":
-        return torch.optim.AdamW(
-            params, lr=base_learning_rate, betas=(0.9, betta2), eps=eps, weight_decay=0.01
-        )
-    elif name == "muon_adam8bit":
-        return MuonAdamW8bit(
-            params, 
-            lr=base_learning_rate, 
-            betas=(0.9, betta2), 
-            eps=eps, 
-            weight_decay=0.01,
-            muon_momentum=0.95,
-            ns_dtype=torch.bfloat16,
-            muon_lr_mult=1000.0,
-        )
-    else:
-        raise ValueError(f"Unknown optimizer: {name}")
-
-if fbp:
-    trainable_params = list(unet.parameters())
-    optimizer_dict = {p: create_optimizer(optimizer_type, [p]) for p in trainable_params}
-    def optimizer_hook(param):
-        optimizer_dict[param].step()
-        optimizer_dict[param].zero_grad(set_to_none=True)
-    for param in trainable_params:
-        param.register_post_accumulate_grad_hook(optimizer_hook)
-    unet, optimizer = accelerator.prepare(unet, optimizer_dict)
-else:
-    unet.requires_grad_(True)
-    optimizer = create_optimizer(optimizer_type, unet.parameters())
-    # 1. Сначала замораживаем ВСЕ параметры UNet
-    #unet.requires_grad_(False)
-    
-    # 2. Размораживаем только нужные
-    #trainable_params_names = ["conv_in.weight", "conv_in.bias", "conv_out.weight", "conv_out.bias"]
-    #train_params = []
-    
-    #for name, param in unet.named_parameters():
-    #    if any(target in name for target in trainable_params_names):
-    #        param.requires_grad = True
-    #        train_params.append(param)
-    #        print(f"Обучаемый слой: {name}")
-    
-    def lr_schedule(step):
-        x = step / (total_training_steps * world_size)
-        warmup = warmup_percent
-        if not use_decay:
-            return base_learning_rate
-        if x < warmup:
-            return min_learning_rate + (base_learning_rate - min_learning_rate) * (x / warmup)
-        decay_ratio = (x - warmup) / (1 - warmup)
-        return min_learning_rate + 0.5 * (base_learning_rate - min_learning_rate) * \
-               (1 + math.cos(math.pi * decay_ratio))
-    lr_scheduler = LambdaLR(optimizer, lambda step: lr_schedule(step) / base_learning_rate)
-    unet, optimizer, lr_scheduler = accelerator.prepare(unet, optimizer, lr_scheduler)
-
-if torch_compile:
-    print("compiling")
-    unet = torch.compile(unet)
-    print("compiling - ok")
-
-# Фиксированные семплы
-fixed_samples = get_fixed_samples_by_resolution(dataset)
-
-# --- [UPDATED] Функция для негативного эмбеддинга (возвращает 3 элемента) ---
-def get_negative_embedding(neg_prompt="", batch_size=1):
-    if not neg_prompt:
-        hidden_dim = 2048 
-        seq_len = max_length
-        empty_emb = torch.zeros((batch_size, seq_len, hidden_dim), dtype=dtype, device=device)
-        empty_mask = torch.ones((batch_size, seq_len), dtype=torch.int64, device=device)
-        return empty_emb, empty_mask
-
-    uncond_emb, uncond_mask  = encode_texts([neg_prompt])
-    uncond_emb = uncond_emb.to(dtype=dtype, device=device).repeat(batch_size, 1, 1)
-    uncond_mask = uncond_mask.to(device=device).repeat(batch_size, 1)
-
-    return uncond_emb, uncond_mask
-    
-# Получаем негативные (пустые) условия для валидации
-if use_precomputed_embeddings:
-    # 1. грузим encoder ВРЕМЕННО
-    load_text_encoder()
-
-    # 2. считаем negative
-    uncond_emb, uncond_mask = get_negative_embedding("low quality")
-
-    # 3. уносим на CPU (очень важно)
-    uncond_emb = uncond_emb.to("cpu")
-    uncond_mask = uncond_mask.to("cpu")
-
-    # 4. выгружаем encoder с GPU
-    del text_encoder
-    torch.cuda.empty_cache()
-    gc.collect()
-
-    text_encoder = None
-
-else:
-    uncond_emb, uncond_mask = get_negative_embedding("low quality")
-    
-# --- Функция генерации семплов  ---
-@torch.compiler.disable()
-@torch.no_grad()
-def generate_and_save_samples(fixed_samples_cpu, uncond_data, step):
-    uncond_emb, uncond_mask = uncond_data
-    uncond_emb = uncond_emb.to(device)
-    uncond_mask = uncond_mask.to(device)
-    
-    original_model = None
-    try:
-        if not torch_compile:
-            original_model = accelerator.unwrap_model(unet, keep_torch_compile=True).eval()
-        else:
-            original_model = unet.eval()
-
-        vae.to(device=device).eval() 
-        
-        all_generated_images = []
-        all_captions = [] 
-        
-        # Распаковываем 5 элементов (добавились mask)
-        for size, (sample_latents, sample_text_embeddings, sample_mask, sample_text) in fixed_samples_cpu.items():
-            width, height = size
-            sample_latents = sample_latents.to(dtype=dtype, device=device)
-            sample_text_embeddings = sample_text_embeddings.to(dtype=dtype, device=device)
-            sample_mask = sample_mask.to(device=device)
-        
-            latents = torch.randn(
-                sample_latents.shape,
-                device=device,
-                dtype=sample_latents.dtype,
-                generator=torch.Generator(device=device).manual_seed(seed)
-            )
-        
-            scheduler.set_timesteps(n_diffusion_steps, device=device)
-
-            for t in scheduler.timesteps:
-                if guidance_scale != 1:
-                    latent_model_input = torch.cat([latents, latents], dim=0)
-                    
-                    curr_batch_size = sample_text_embeddings.shape[0]
-                    seq_len = sample_text_embeddings.shape[1]
-                    hidden_dim = sample_text_embeddings.shape[2]
-                    
-                    neg_emb_batch = uncond_emb[0:1].expand(curr_batch_size, -1, -1)
-                    text_embeddings_batch = torch.cat([neg_emb_batch, sample_text_embeddings], dim=0)
-                    
-                    neg_mask_batch = uncond_mask[0:1].expand(curr_batch_size, -1)
-                    attention_mask_batch = torch.cat([neg_mask_batch, sample_mask], dim=0)
-                    
-                else:
-                    latent_model_input = latents
-                    text_embeddings_batch = sample_text_embeddings
-                    attention_mask_batch = sample_mask
-            
-                # Теперь всё имеет одинаковый batch size
-                model_out = original_model(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=text_embeddings_batch,
-                    encoder_attention_mask=attention_mask_batch,
-                )
-
-                flow = getattr(model_out, "sample", model_out)
-        
-                if guidance_scale != 1:
-                    flow_uncond, flow_cond = flow.chunk(2)
-                    flow = flow_uncond + guidance_scale * (flow_cond - flow_uncond)
-        
-                latents = scheduler.step(flow, t, latents).prev_sample
-        
-            current_latents = latents
-            if step==0:
-                current_latents = sample_latents
-
-            if latents_mean is not None and latents_std is not None:
-                latents = current_latents * latents_std + latents_mean
-                
-            decoded = vae.decode(latents.to(torch.float32)).sample
-            decoded_fp32 = decoded.to(torch.float32)
-            
-            for img_idx, img_tensor in enumerate(decoded_fp32):
-                img = (img_tensor / 2 + 0.5).clamp(0, 1).cpu().numpy()
-                img = img.transpose(1, 2, 0)
-    
-                if np.isnan(img).any():
-                    print("NaNs found, saving stopped! Step:", step)
-                pil_img = Image.fromarray((img * 255).astype("uint8"))
-                
-                max_w_overall = max(s[0] for s in fixed_samples_cpu.keys())
-                max_h_overall = max(s[1] for s in fixed_samples_cpu.keys())
-                max_w_overall = max(255, max_w_overall)
-                max_h_overall = max(255, max_h_overall)
-            
-                padded_img = ImageOps.pad(pil_img, (max_w_overall, max_h_overall), color='white')
-                all_generated_images.append(padded_img)
-
-                caption_text = sample_text[img_idx][:300] if img_idx < len(sample_text) else ""
-                all_captions.append(caption_text)
-                
-                sample_path = f"{generated_folder}/{project}_{width}x{height}_{img_idx}.jpg"
-                pil_img.save(sample_path, "JPEG", quality=95)
-        
-        if use_wandb and accelerator.is_main_process:
-            wandb_images = [
-                wandb.Image(img, caption=f"{all_captions[i]}")
-                for i, img in enumerate(all_generated_images)
-            ]
-            wandb.log({"generated_images": wandb_images})
-        if use_comet_ml and accelerator.is_main_process:
-            for i, img in enumerate(all_generated_images):
-                comet_experiment.log_image(
-                    image_data=img,
-                    name=f"step_{step}_img_{i}",
-                    step=step,
-                    metadata={"caption": all_captions[i]}
-                )
-    finally:
-        vae.to("cpu")
-        uncond_emb = uncond_emb.to("cpu")
-        uncond_mask = uncond_mask.to("cpu")
-        try:
-            all_generated_images.clear()
-            all_captions.clear()
-            del all_generated_images, all_captions
-            del latents, current_latents, latent_model_input, flow
-            del decoded, decoded_fp32
-            del sample_latents, sample_text_embeddings, sample_mask # Копии на GPU
-            del model_out
-        except UnboundLocalError:
-            pass
-            
-        # 3. Синхронизируем CUDA перед очисткой
-        torch.cuda.synchronize()
-        # 4. Теперь чистим кэш аллокатора и вызываем GC
-        torch.cuda.empty_cache()
-        gc.collect()
-
-# --------------------------- Генерация сэмплов перед обучением ---------------------------
-if accelerator.is_main_process:
-    if save_model:
-        print("Генерация сэмплов до старта обучения...")
-        generate_and_save_samples(fixed_samples, (uncond_emb, uncond_mask), 0)
-accelerator.wait_for_everyone()
-
-def save_checkpoint(unet, variant=""):
-    if accelerator.is_main_process:
-        model_to_save = None
-        if not torch_compile:
-            model_to_save = accelerator.unwrap_model(unet)
-        else:
-            model_to_save = unet
-
-        if variant != "":
-            model_to_save.to(dtype=torch.float16).save_pretrained(
-                os.path.join(checkpoints_folder, f"{project}"), variant=variant
-            )
-        else:
-            model_to_save.save_pretrained(os.path.join(checkpoints_folder, f"{project}"))
-
-        torch.cuda.synchronize()
-        torch.cuda.empty_cache()
-        gc.collect()
-
-# --------------------------- Тренировочный цикл ---------------------------
-if accelerator.is_main_process:
-    print(f"Total steps per GPU: {total_training_steps}")
-
-epoch_loss_points = []
-progress_bar = tqdm(total=total_training_steps, disable=not accelerator.is_local_main_process, desc="Training", unit="step")
-
-steps_per_epoch = len(dataloader)
-sample_interval = max(1, steps_per_epoch // sample_interval_share)
-min_loss = 4.
-last_sample_time = time.time() 
-sample_interval_seconds = 60 * 60  # 60 минут
-
-for epoch in range(start_epoch, start_epoch + num_epochs):
-    batch_losses = []
-    batch_grads = []
-    batch_sampler.set_epoch(epoch)
-    accelerator.wait_for_everyone()
-    unet.train()
-    
-    for step, (latents, embeddings, attention_mask) in enumerate(dataloader):
-        with accelerator.accumulate(unet):
-            if save_model == False and epoch == 0 and step == 5 :
-                used_gb = torch.cuda.max_memory_allocated() / 1024**3
-                print(f"Шаг {step}: {used_gb:.2f} GB")
-                
-            # шум
-            noise = torch.randn_like(latents, dtype=latents.dtype)
-
-            # 3. Время t (сэмплим, как и раньше, но чуть сжимаем края)
-            u = torch.rand(latents.shape[0], device=latents.device, dtype=latents.dtype)
-            t = u * (1 - 2 * 1e-5) + 1e-5  # Теперь t строго в (0.00001 ... 0.99999)
-            # интерполяция между x0 и шумом
-            noisy_latents = (1.0 - t.view(-1, 1, 1, 1)) * latents + t.view(-1, 1, 1, 1) * noise
-            # делаем integer timesteps для UNet
-            timesteps = t.to(torch.float32).mul(999.0)
-            timesteps = timesteps.clamp(0, scheduler.config.num_train_timesteps - 1)
-
-            # --- Вызов UNet с маской  ---
-            model_pred = unet(
-                noisy_latents, 
-                timesteps, 
-                encoder_hidden_states=embeddings,
-                encoder_attention_mask=attention_mask,
-            ).sample
-            
-            target = noise - latents
-
-            mse_loss = F.mse_loss(model_pred.float(), target.float())                
-            batch_losses.append(mse_loss.detach().item())
-
-            if (global_step % 100 == 0) or (global_step % sample_interval == 0):
-                accelerator.wait_for_everyone()
-
-            losses_dict = {}
-            losses_dict["mse"] = mse_loss
-
-            if (global_step % 100 == 0) or (global_step % sample_interval == 0):
-                accelerator.wait_for_everyone()
-
-            accelerator.backward(mse_loss)
-
-            if (global_step % 100 == 0) or (global_step % sample_interval == 0):
-                accelerator.wait_for_everyone()
-                
-            grad = 0.0
-            if not fbp:
-                if accelerator.sync_gradients:
-                    grad_val = accelerator.clip_grad_norm_(unet.parameters(), clip_grad_norm)
-                    grad = grad_val.float().item() if torch.is_tensor(grad_val) else float(grad_val)
-                    optimizer.step()
-                    lr_scheduler.step()
-                    optimizer.zero_grad(set_to_none=True)
-
-            if accelerator.sync_gradients:
-                global_step += 1
-                progress_bar.update(1)
-                if accelerator.is_main_process:
-                    if fbp:
-                        current_lr = base_learning_rate
-                    else:
-                        current_lr = lr_scheduler.get_last_lr()[0]
-                    batch_grads.append(grad)
-    
-                    log_data = {}
-                    log_data["loss_mse"] = mse_loss.detach().item()
-                    log_data["lr"] = current_lr
-                    log_data["grad"] = grad
-                    if accelerator.sync_gradients:
-                        if use_wandb:
-                            wandb.log(log_data, step=global_step)
-                        if use_comet_ml:
-                            comet_experiment.log_metrics(log_data, step=global_step)
-
-                    current_time = time.time()
-                    is_time_to_sample = (current_time - last_sample_time) >= sample_interval_seconds
-                    if is_time_to_sample or global_step == 50:
-                        # Передаем tuple (emb, mask) для негатива
-                        if save_model:
-                            generate_and_save_samples(fixed_samples, (uncond_emb, uncond_mask), global_step)
-                        elif epoch % 10 == 0:
-                            generate_and_save_samples(fixed_samples, (uncond_emb, uncond_mask), global_step)
-                        last_n = sample_interval
-                        
-                        if save_model:
-                            has_losses = len(batch_losses) > 0
-                            avg_sample_loss = np.mean(batch_losses[-sample_interval:]) if has_losses else 0.0
-                            last_loss = batch_losses[-1] if has_losses else 0.0
-                            max_loss = max(avg_sample_loss, last_loss)    
-                            should_save = max_loss < min_loss * save_barrier
-                            print(
-                                f"Saving: {should_save} | Max: {max_loss:.4f} | "
-                                f"Last: {last_loss:.4f} | Avg: {avg_sample_loss:.4f}"
-                            )
-                            # 6. Сохранение и обновление
-                            if should_save:
-                                min_loss = max_loss
-                                save_checkpoint(unet)
-                        last_sample_time = current_time
-                        unet.train()
-
-    if accelerator.is_main_process:
-        avg_epoch_loss = np.mean(batch_losses) if len(batch_losses) > 0 else 0.0
-        avg_epoch_grad = np.mean(batch_grads) if len(batch_grads) > 0 else 0.0
-
-        print(f"\nЭпоха {epoch} завершена. Средний лосс: {avg_epoch_loss:.6f}")
-        log_data_ep = {
-                        "epoch_loss": avg_epoch_loss,
-                        "epoch_grad": avg_epoch_grad,
-                        "epoch": epoch + 1,
-                    }
-        if use_wandb:
-            wandb.log(log_data_ep)
-        if use_comet_ml:
-            comet_experiment.log_metrics(log_data_ep)
-
-if accelerator.is_main_process:
-    print("Обучение завершено! Сохраняем финальную модель...")
-    #if save_model:
-    save_checkpoint(unet,"fp16")
-    if use_comet_ml:
-        comet_experiment.end()
-accelerator.free_memory()
-if torch.distributed.is_initialized():
-    torch.distributed.destroy_process_group()
-    
-print("Готово!")

train.py

@@ -62,7 +62,7 @@ shuffle = True
 muon_lr_scale = 300
 optimizer_type = "muon_adam8bit"
 if optimizer_type == "muon_adam8bit":
-    batch_size = num_gpus * max(1, int((gpu_mem_gb / 32) * 4))
+    batch_size = num_gpus * max(1, int((gpu_mem_gb / 32) * 3))
 comet_ml_api_key = "Agctp26mbqnoYrrlvQuKSTk6r" 
 comet_ml_workspace = "recoilme" 
 torch.backends.cuda.matmul.allow_tf32 = True

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb68ae24f6d1ada2f50a1bbd849b45f5ffd116c6bc0438b28ef9f1bd4cbd3cd
+oid sha256:0c73a0b0282f35835442a83d4624e6462a3530b0209b058a89325ad2230ac364
 size 6294042336