import os
import sys
with open(sys.argv[0]) as f:
    code = f.read() # read the code of this file ASAP, for logging
import uuid
import time
from dataclasses import dataclass
from pathlib import Path

import torch
from torch import nn
import torch.nn.functional as F
import torch.distributed as dist
import torch._inductor.config as config
from torch.nn.parallel import DistributedDataParallel as DDP
# Use of FlexAttention contributed by @KoszarskyB
from torch.nn.attention.flex_attention import BlockMask, flex_attention

# -----------------------------------------------------------------------------
# Muon optimizer

def zeropower_via_svd(G, steps=None):
    U, S, V = G.svd()
    return U @ V.T

@torch.compile
def zeropower_via_newtonschulz5(G, steps=10, eps=1e-7):
    """
    Newton-Schulz iteration to compute the zeroth power / orthogonalization of G. We opt to use a
    quintic iteration whose coefficients are selected to maximize the slope at zero. For the purpose
    of minimizing steps, it turns out to be empirically effective to keep increasing the slope at
    zero even beyond the point where the iteration no longer converges all the way to one everywhere
    on the interval. This iteration therefore does not produce UV^T but rather something like US'V^T
    where S' is diagonal with S_{ii}' ~ Uniform(0.5, 1.5), which turns out not to hurt model
    performance at all relative to UV^T, where USV^T = G is the SVD.
    """
    assert len(G.shape) == 2
    a, b, c = (3.4445, -4.7750,  2.0315)
    X = G.bfloat16()
    X /= (X.norm() + eps) # ensure top singular value <= 1
    if G.size(0) > G.size(1):
        X = X.T
    for _ in range(steps):
        A = X @ X.T
        B = b * A + c * A @ A # adapted from suggestion by @jxbz, @leloykun, and @YouJiacheng
        X = a * X + B @ X
    if G.size(0) > G.size(1):
        X = X.T
    return X

zeropower_backends = dict(svd=zeropower_via_svd, newtonschulz5=zeropower_via_newtonschulz5)

class Muon(torch.optim.Optimizer):
    """
    Muon - MomentUm Orthogonalized by Newton-schulz

    Muon internally runs standard SGD-momentum, and then performs an orthogonalization post-
    processing step, in which each 2D parameter's update is replaced with the nearest orthogonal
    matrix. To efficiently orthogonalize each update, we use a Newton-Schulz iteration, which has
    the advantage that it can be stably run in bfloat16 on the GPU.

    Some warnings:
    - This optimizer assumes that all parameters passed in are 2D.
    - It should not be used for the embedding layer, the final fully connected layer, or any {0,1}-D
    parameters; those should all be optimized by a standard method (e.g., AdamW).
    - To use it with 4D convolutional filters, it works well to just flatten their last 3 dimensions.
    - We believe it is unlikely to work well for training with small batch size.
    - We believe it may not work well for finetuning pretrained models, but we haven't tested this.
    - We have not yet tried this optimizer for training scenarios larger than NanoGPT (124M).

    Arguments:
        lr: The learning rate used by the internal SGD.
        momentum: The momentum used by the internal SGD.
        nesterov: Whether to use Nesterov-style momentum in the internal SGD. (recommended)
        backend: The chosen backend for the orthogonalization step. (recommended: 'newtonschulz5')
        backend_steps: The number of iteration steps to use in the backend, if it is iterative.
    """
    def __init__(self, params, lr=0.02, momentum=0.95, nesterov=True,
                 backend='newtonschulz5', backend_steps=5):
        self.num_process = int(os.environ['WORLD_SIZE'])
        self.rank = int(os.environ["RANK"])
        defaults = dict(lr=lr, momentum=momentum, nesterov=nesterov, backend=backend, backend_steps=backend_steps)
        params: "list[torch.Tensor]" = list(params)
        assert all(isinstance(p, torch.Tensor) for p in params)
        sizes = {p.numel() for p in params}
        param_groups = [
            {
                "params": [p for p in params if p.numel() == size],
                "update_buffer": [
                    torch.empty(size, device="cuda", dtype=torch.bfloat16)
                    for _ in range(self.num_process)
                ],
            }
            for size in sizes
        ]
        super().__init__(param_groups, defaults)

    def step(self):
        for group in self.param_groups:
            lr: float = group["lr"]
            momentum: float = group["momentum"]
            nesterov: bool = group["nesterov"]
            zeropower_backend = zeropower_backends[group["backend"]]
            backend_steps: int = group["backend_steps"]
            update_buffers: "list[torch.Tensor]" = group["update_buffer"]
            # generate weight updates in distributed fashion
            params: "list[torch.Tensor]" = group["params"]
            assert len(params) % self.num_process == 0
            handle = None
            params_world = None
            def update_prev():
                if params_world is None:
                    return
                assert handle is not None
                handle.wait()
                for p_world, g_world in zip(params_world, update_buffers):
                    p_world.data.add_(
                        g_world.view_as(p_world),
                        alpha=-lr * max(1, p_world.size(0) / p_world.size(1)) ** 0.5,
                    )
            for base_i in range(len(params))[::self.num_process]:
                p = params[base_i + self.rank]
                g = p.grad
                assert g is not None
                state = self.state[p] 
                if "momentum_buffer" not in state:
                    state["momentum_buffer"] = torch.zeros_like(g)
                buf: torch.Tensor = state["momentum_buffer"]
                buf.lerp_(g, 1 - momentum)
                g = g.lerp_(buf, momentum) if nesterov else buf
                g = zeropower_backend(g, steps=backend_steps).flatten()
                update_prev()
                handle = dist.all_gather(update_buffers, g, async_op=True)
                params_world = params[base_i : base_i + self.num_process]
            update_prev()


# -----------------------------------------------------------------------------
# PyTorch nn.Module definitions for the GPT-2 model

def norm(x):
    return F.rms_norm(x, (x.size(-1),))

class CastedLinear(nn.Linear):

    def __init__(self, in_features, out_features):
        super().__init__(in_features, out_features, bias=False)

    def forward(self, x):
        return F.linear(x, self.weight.to(x.dtype))

class Rotary(torch.nn.Module):

    def __init__(self, dim, base=10000):
        super().__init__()
        self.register_buffer('inv_freq', (1 / base) ** (torch.arange(0, dim, 2) / dim))
        self.seq_len_cached = None
        self.cos_cached = None
        self.sin_cached = None

    def forward(self, x):
        seq_len = x.shape[1]
        if seq_len != self.seq_len_cached:
            t = torch.arange(seq_len, device=x.device)
            freqs = torch.outer(t, self.inv_freq)
            self.seq_len_cached = seq_len
            self.cos_cached = freqs.cos()
            self.sin_cached = freqs.sin()
        cos, sin = self.cos_cached[None, :, None, :], self.sin_cached[None, :, None, :]
        # apply_rotary_emb(x, cos, sin)
        x1, x2 = x.chunk(2, dim=3)
        y1 = x1 * cos + x2 * sin
        y2 = x1 * (-sin) + x2 * cos
        return torch.cat((y1, y2), 3).type_as(x)

class CausalSelfAttention(nn.Module):

    def __init__(self, dim, n_head):
        super().__init__()
        assert dim % n_head == 0
        self.n_head = n_head
        self.c_q = CastedLinear(dim, dim)
        self.c_k = CastedLinear(dim, dim)
        self.c_v = CastedLinear(dim, dim)
        # value residual lambda
        self.lambdas = nn.Parameter(torch.tensor([0.5, 0.5])) # @Grad62304977
        # rotary embeddings
        self.rotary = Rotary(dim // n_head) # dim // n_head = head_dim
        # output projection
        self.c_proj = CastedLinear(dim, dim)
        self.c_proj.weight.data.zero_() # zero init suggested by @Grad62304977

    def forward(self, x: torch.Tensor, vi: torch.Tensor, block_mask: BlockMask) -> torch.Tensor:
        B, T = x.size(0), x.size(1) # batch size, sequence length
        assert B == 1, "Must use batch size = 1 for FlexAttention"
        q: torch.Tensor = self.c_q(x).view(B, T, self.n_head, -1)
        k: torch.Tensor = self.c_k(x).view(B, T, self.n_head, -1)
        v: torch.Tensor = self.c_v(x).view(B, T, self.n_head, -1)
        v = self.lambdas[0] * v + self.lambdas[1] * vi.view_as(v) # @Grad62304977
        q, k = norm(q), norm(k) # QK norm suggested by @Grad62304977
        q, k = self.rotary(q), self.rotary(k)
        y = flex_attention(q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2), block_mask=block_mask)
        y = y.transpose(1, 2).contiguous().view_as(x) # re-assemble all head outputs side by side
        y = self.c_proj(y)
        return y

class MLP(nn.Module):

    def __init__(self, dim: int):
        super().__init__()
        self.c_fc   = CastedLinear(dim, 4 * dim)
        self.c_proj = CastedLinear(4 * dim, dim)
        self.c_proj.weight.data.zero_() # zero init suggested by @Grad62304977

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.c_fc(x)
        x = F.relu(x).square() # https://arxiv.org/abs/2109.08668v2; ~1-2% better than GELU; suggested by @SKYLINEZ007 and @Grad62304977
        x = self.c_proj(x)
        return x

class Block(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.attn = CausalSelfAttention(config.n_embd, config.n_head)
        self.mlp = MLP(config.n_embd)
        self.lambdas = nn.Parameter(torch.tensor([1., 0.]))

    def forward(self, x: torch.Tensor, vi: torch.Tensor, x0: torch.Tensor, block_mask: BlockMask) -> torch.Tensor:
        x = self.lambdas[0] * x + self.lambdas[1] * x0
        x = x + self.attn(norm(x), vi, block_mask)
        x = x + self.mlp(norm(x))
        return x

# -----------------------------------------------------------------------------
# The main GPT-2 model

@dataclass
class GPTConfig:
    vocab_size : int = 50304
    n_layer : int = 12
    n_head : int = 6 # head dim 128 suggested by @Grad62304977
    n_embd : int = 768
    lm_head_softcap : int = 30

class GPT(nn.Module):

    def __init__(self, config: GPTConfig):
        super().__init__()
        self.n_layer = config.n_layer
        self.lm_head_softcap = config.lm_head_softcap

        # U-net design by @brendanh0gan
        self.num_encoder_layers = config.n_layer // 2 # Half of the layers for encoder
        self.num_decoder_layers = config.n_layer - self.num_encoder_layers # Remaining for decoder
        # Add learnable skip connection weights for decoder layers
        self.skip_weights = nn.Parameter(torch.ones(self.num_decoder_layers))

        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.n_embd),
            # token value embeddings by @KoszarskyB - inspired by @Grad62304977's value residual learning
            # U-net structure on token value embeddings by @leloykun
            vte = nn.Embedding(config.vocab_size, config.n_embd*self.num_encoder_layers),
            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
        ))
        self.lm_head = CastedLinear(config.n_embd, config.vocab_size)
        self.lm_head.weight.data.zero_() # @Grad62304977

    def forward(self, idx: torch.Tensor, target: torch.Tensor, sliding_window: torch.Tensor) -> torch.Tensor:
        BLOCK_SIZE = 128
        assert idx.ndim == 1
        docs = (idx == 50256).cumsum(0)
        docs_low = docs.reshape(-1, BLOCK_SIZE)[:, 0].contiguous()
        docs_high = docs.reshape(-1, BLOCK_SIZE)[:, -1].contiguous()
        def document_sliding_window_causal(b, h, q_idx, kv_idx):
            causal_mask = q_idx >= kv_idx
            document_mask = docs[q_idx] == docs[kv_idx]
            window_mask = q_idx - kv_idx < sliding_window
            return causal_mask & document_mask & window_mask

        S = len(idx)
        def create_sliding_window_causal_mask(S: int, sliding_window: torch.Tensor):
            kv_idx = block_idx = torch.arange(S // BLOCK_SIZE, dtype=torch.int32, device="cuda")
            q_idx = block_idx[:, None]
            causal_mask = q_idx >= kv_idx
            document_mask = (docs_low[q_idx] <= docs_high[kv_idx]) & (docs_low[kv_idx] <= docs_high[q_idx])
            window_mask = q_idx - kv_idx < ((sliding_window + BLOCK_SIZE - 1) // BLOCK_SIZE)
            dense_mask = causal_mask & document_mask & window_mask
            dense_mask = dense_mask.to(torch.int32)
            num_blocks = dense_mask.sum(dim=-1).to(torch.int32)
            indices = torch.argsort(dense_mask, dim=-1, descending=True, stable=True).to(torch.int32)
            num_blocks = num_blocks[None, None, :].contiguous()
            indices = indices[None, None, :].contiguous()
            return BlockMask.from_kv_blocks(num_blocks, indices, BLOCK_SIZE=BLOCK_SIZE, mask_mod=document_sliding_window_causal)
        block_mask = create_sliding_window_causal_mask(S, sliding_window)

        # forward the GPT model itself
        x = self.transformer.wte(idx[None]) # token embeddings of shape (b, t, n_embd)
        x = norm(x) # @Grad62304977
        x0 = x
        vi = self.transformer.vte(idx[None]).chunk(self.num_encoder_layers, dim=-1)

        # Store outputs for U-Net skip connections
        skip_connections = []
        # Encoder pass - process only the first half of the blocks
        for i in range(self.num_encoder_layers):
            x = self.transformer.h[i](x, vi[i], x0, block_mask)
            skip_connections.append(x)
        # Decoder pass - process the remaining blocks with weighted skip connections
        for i in range(self.num_decoder_layers):
            x = x + self.skip_weights[i] * skip_connections.pop()
            # U-net structure on token value embeddings by @leloykun
            x = self.transformer.h[self.num_encoder_layers + i](x, vi[self.num_encoder_layers-1-i], x0, block_mask)

        x = norm(x)
        logits = self.lm_head(x)
        logits = self.lm_head_softcap * torch.tanh(logits / self.lm_head_softcap) # @Grad62304977
        logits = logits.float()
        loss = F.cross_entropy(logits.view(-1, logits.size(-1)), target.view(-1))
        return loss

# -----------------------------------------------------------------------------
# Our own simple Distributed Data Loader

def _peek_data_shard(file: Path):
    # only reads the header, returns header data
    # header is 256 int32
    header = torch.from_file(f"{file}", False, 256, dtype=torch.int32)
    assert header[0] == 20240520, "magic number mismatch in the data .bin file"
    assert header[1] == 1, "unsupported version"
    return int(header[2]) # number of tokens (claimed)

def _load_data_shard(file: Path, ntok: int):
    with file.open("rb") as f:
        tokens = torch.empty(ntok, dtype=torch.uint16, pin_memory=True)
        f.seek(256 * 4)
        nbytes = f.readinto(tokens.numpy())
        assert nbytes == 2 * ntok, "number of tokens read does not match header?"
    return tokens

class DistributedDataLoader:
    def __init__(self, filename_pattern, T, process_rank, num_processes):
        self.process_rank = process_rank
        self.num_processes = num_processes
        self.T = T

        # glob files that match the pattern
        self.files = sorted(Path.cwd().glob(filename_pattern))
        assert len(self.files) > 0, f"did not find any files that match the pattern {filename_pattern}"

        # load and validate all data shards, count number of tokens in total
        self.ntoks = [_peek_data_shard(file) for file in self.files]
        assert min(self.ntoks) >= num_processes * T + 1
        self.ntok_total = sum(self.ntoks)

        self.reset()

    def reset(self):
        self.current_shard = -1
        self.advance()

    def advance(self): # advance to next data shard
        self.current_shard = (self.current_shard + 1) % len(self.files)
        self.current_position = self.process_rank * self.T
        self.tokens = _load_data_shard(self.files[self.current_shard], self.ntoks[self.current_shard])

    def next_batch(self):
        batch_size = self.T * self.num_processes
        buf = self.tokens[self.current_position:self.current_position+self.T+1]
        # host side async is sufficient;
        # no performance improvement was observed when introducing a separate stream.
        x = buf[:-1].to(device="cuda", dtype=torch.int32, non_blocking=True) # inputs
        y = buf[1:].to(device="cuda", dtype=torch.int64, non_blocking=True) # targets
        # advance current position and load next shard if necessary
        self.current_position += batch_size
        if self.current_position + batch_size + 1 >= len(self.tokens):
            self.advance()
        return x, y

# -----------------------------------------------------------------------------
# int main

@dataclass
class Hyperparameters:
    # data hyperparams
    input_bin : str = 'data/fineweb10B/fineweb_train_*.bin' # input .bin to train on
    input_val_bin : str = 'data/fineweb10B/fineweb_val_*.bin' # input .bin to eval validation loss on
    # optimization hyperparams
    batch_size : int = 8 # batch size, in sequences, across all devices
    sequence_length : int = 64*1024 # sequence length, in tokens
    num_iterations : int = 1480 # number of iterations to run
    warmup_iters : int = 0
    cooldown_iters : int = 600 # number of iterations of linear warmup/cooldown for triangular or trapezoidal schedule
    weight_decay : float = 0
    # evaluation and logging hyperparams
    val_loss_every : int = 125 # every how many steps to evaluate val loss? 0 for only at the end
    val_tokens : int = 10485760 # how many tokens of validation data? it's important to keep this fixed for consistent comparisons
    save_every : int = 0 # every how many steps to save the checkpoint? 0 for only at the end
args = Hyperparameters()

# set up DDP (distributed data parallel). torchrun sets this env variable
assert torch.cuda.is_available()
dist.init_process_group(backend='nccl')
ddp_rank = int(os.environ['RANK'])
ddp_local_rank = int(os.environ['LOCAL_RANK'])
ddp_world_size = int(os.environ['WORLD_SIZE'])
device = f'cuda:{ddp_local_rank}'
torch.cuda.set_device(device)
print(f"using device: {device}")
master_process = (ddp_rank == 0) # this process will do logging, checkpointing etc.

# begin logging
logfile = None
if master_process:
    run_id = str(uuid.uuid4())
    logdir = 'logs/%s/' % run_id
    # os.makedirs(logdir, exist_ok=True)
    logfile = 'logs/%s.txt' % run_id
    # create the log file
    with open(logfile, "w") as f:
        # begin the log by printing this file (the Python code)
        f.write(code)
        f.write('='*100 + '\n')
def print0(s, logonly=False):
    if master_process:
        with open(logfile, "a") as f:
            if not logonly:
                print(s)
            f.write(s+'\n')
# log information about the hardware/software environment this is running on
# and print the full `nvidia-smi` to file
print0(f"Running pytorch {torch.version.__version__} compiled for CUDA {torch.version.cuda}\nnvidia-smi:")
import subprocess
result = subprocess.run(['nvidia-smi'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
print0(f'{result.stdout}', logonly=True)
print0('='*100, logonly=True)

# convenience variables
T = args.sequence_length
# calculate the number of steps to take in the val loop.
assert args.val_tokens % (T * ddp_world_size) == 0
val_steps = args.val_tokens // (T * ddp_world_size)
# calculate the steps of gradient accumulation required to attain the desired global batch size.
assert args.batch_size % (ddp_world_size) == 0
train_accumulation_steps = args.batch_size // ddp_world_size
assert train_accumulation_steps == 1

# load tokens
train_loader = DistributedDataLoader(args.input_bin, T, ddp_rank, ddp_world_size)
val_loader = DistributedDataLoader(args.input_val_bin, T, ddp_rank, ddp_world_size)
print0(f"Training DataLoader: total number of tokens: {train_loader.ntok_total} across {len(train_loader.files)} files")
print0(f"Validation DataLoader: total number of tokens: {val_loader.ntok_total} across {len(val_loader.files)} files")
print0('='*100, logonly=True)
x, y = train_loader.next_batch()

# there are only 50257 unique GPT-2 tokens; we extend to nearest multiple of 128 for efficiency. suggested to me by @Grad62304977.
# this originates from Karpathy's experiments.
num_vocab = 50304
model = GPT(GPTConfig(vocab_size=num_vocab, n_layer=12, n_head=6, n_embd=768))
model = model.cuda().bfloat16()
for m in model.modules():
    if isinstance(m, CastedLinear):
        m.float()
if hasattr(config, "coordinate_descent_tuning"):
    config.coordinate_descent_tuning = True # suggested by @Chillee
model = torch.compile(model)
# here we wrap model into DDP container
model = DDP(model, device_ids=[ddp_local_rank])
raw_model = model.module # always contains the "raw" unwrapped model

# init the optimizer(s)
optimizer1 = torch.optim.Adam([raw_model.transformer.wte.weight, raw_model.transformer.vte.weight], lr=0.6, betas=(0.8, 0.95), fused=True)
optimizer2 = torch.optim.Adam([raw_model.lm_head.weight], lr=0.008, betas=(0.8, 0.95), fused=True)
params = list(raw_model.transformer.h.parameters())
matrix_params = [p for p in params if p.ndim == 2]
scalar_params = [p for p in params if p.ndim < 2] + [raw_model.skip_weights]
optimizer3 = Muon(matrix_params, lr=0.05, momentum=0.95)
optimizer4 = torch.optim.Adam(scalar_params, lr=0.04, betas=(0.8, 0.95), fused=True)
optimizers = [optimizer1, optimizer2, optimizer3, optimizer4]
# learning rate decay scheduler (linear warmup and cooldown)
def get_lr(it):
    assert it <= args.num_iterations
    # 1) linear warmup for warmup_iters steps
    if it < args.warmup_iters:
        return (it+1) / args.warmup_iters
    # 2) constant lr for a while
    elif it < args.num_iterations - args.cooldown_iters:
        return 1.0
    # 3) linear cooldown
    else:
        decay_ratio = (args.num_iterations - it) / args.cooldown_iters
        return decay_ratio
schedulers = [torch.optim.lr_scheduler.LambdaLR(opt, get_lr) for opt in optimizers]

sliding_window_size = torch.tensor(64, dtype=torch.int32, device="cuda")
sw_size_prev = 64
# Start training loop
training_time_ms = 0
# start the clock
torch.cuda.synchronize()
t0 = time.perf_counter()
# begin training
for step in range(args.num_iterations + 1):
    last_step = (step == args.num_iterations)
    # This effectively ignores timing first 10 steps, which are slower for weird reasons.
    # Alternately, and slightly more correctly in terms of benchmarking, we could do 10
    # steps with dummy data first, and then re-initialize the model and reset the loader.
    if step == 10:
        training_time_ms = 0
        t0 = time.perf_counter()
    timed_steps = float('nan') if step <= 11 else (step - 10) + 1 # <= 11 to avoid bug in val

    # Set the sliding window size for the current step, in chunks of 64. By @fernbear.bsky.social
    sw_size =  64 * int((64 + (1792 - 64) * step / args.num_iterations) // 64)
    if sw_size != sw_size_prev:
        sliding_window_size.copy_(sw_size, non_blocking=True)
        sw_size_prev = sw_size

    # once in a while evaluate the validation dataset
    if (last_step or (args.val_loss_every > 0 and step % args.val_loss_every == 0)):
        # stop the clock
        torch.cuda.synchronize()
        training_time_ms += 1000 * (time.perf_counter() - t0)
        # run validation batches
        model.eval()
        val_loader.reset()
        val_loss = 0.0
        for _ in range(val_steps):
            with torch.no_grad():
                x_val, y_val = val_loader.next_batch()
                val_loss += model(x_val, y_val, sliding_window=sliding_window_size)
        dist.all_reduce(val_loss, op=dist.ReduceOp.AVG)
        val_loss /= val_steps
        # log val loss to console and to logfile
        print0(f'step:{step}/{args.num_iterations} val_loss:{val_loss:.4f} train_time:{training_time_ms:.0f}ms step_avg:{training_time_ms/(timed_steps-1):.2f}ms')
        # start the clock again
        torch.cuda.synchronize()
        t0 = time.perf_counter()

    if master_process and (last_step or (args.save_every > 0 and step % args.save_every == 0)):
        # stop the clock
        torch.cuda.synchronize()
        training_time_ms += 1000 * (time.perf_counter() - t0)
        # save the state of the training process
        log = dict(step=step, code=code, model=raw_model.state_dict(), optimizers=[opt.state_dict() for opt in optimizers])
        # torch.save(log, 'logs/%s/state_step%06d.pt' % (run_id, step))
        # start the clock again
        torch.cuda.synchronize()
        t0 = time.perf_counter()

    # bit confusing: we want to make sure to eval on 0th iteration
    # but also after the very last iteration. so we loop for step <= num_iterations
    # instead of just < num_iterations (one extra due to <=), only to do
    # the validation/sampling one last time, and then we break right here as we're done.
    if last_step:
        break

    # --------------- TRAINING SECTION BEGIN -----------------
    model.train()
    loss = model(x, y, sliding_window=sliding_window_size)
    loss.backward()
    del loss
    # advance the dataset for the next batch
    x, y = train_loader.next_batch()
    # momentum warmup for Muon
    frac = min(step/300, 1)
    for group in optimizer3.param_groups:
        group['momentum'] = (1 - frac) * 0.85 + frac * 0.95
    # step the optimizers and schedulers
    for opt, sched in zip(optimizers, schedulers):
        opt.step()
        sched.step()
    # null the gradients
    model.zero_grad(set_to_none=True)
    # --------------- TRAINING SECTION END -------------------
    # everything that follows now is just diagnostics, prints, logging, etc.
    approx_time = training_time_ms + 1000 * (time.perf_counter() - t0)
    print0(f"step:{step+1}/{args.num_iterations} train_time:{approx_time:.0f}ms step_avg:{approx_time/timed_steps:.2f}ms")

if master_process:
    print(f"peak memory consumption: {torch.cuda.max_memory_allocated() // 1024 // 1024} MiB")

# -------------------------------------------------------------------------
# clean up nice
dist.destroy_process_group()
====================================================================================================
Running pytorch 2.6.0.dev20241203+cu124 compiled for CUDA 12.4
nvidia-smi:
Sun Dec  8 09:32:20 2024       
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.129.03             Driver Version: 535.129.03   CUDA Version: 12.6     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA H100 80GB HBM3          On  | 00000000:65:02.0 Off |                    0 |
| N/A   36C    P0              74W / 700W |      7MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   1  NVIDIA H100 80GB HBM3          On  | 00000000:67:02.0 Off |                    0 |
| N/A   45C    P0             130W / 700W |    533MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   2  NVIDIA H100 80GB HBM3          On  | 00000000:69:02.0 Off |                    0 |
| N/A   44C    P0              75W / 700W |      7MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   3  NVIDIA H100 80GB HBM3          On  | 00000000:6B:02.0 Off |                    0 |
| N/A   39C    P0             118W / 700W |    533MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   4  NVIDIA H100 80GB HBM3          On  | 00000000:6F:02.0 Off |                    0 |
| N/A   39C    P0             117W / 700W |    533MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   5  NVIDIA H100 80GB HBM3          On  | 00000000:71:02.0 Off |                    0 |
| N/A   45C    P0             113W / 700W |    533MiB / 81559MiB |      1%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   6  NVIDIA H100 80GB HBM3          On  | 00000000:73:02.0 Off |                    0 |
| N/A   45C    P0              95W / 700W |     26MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   7  NVIDIA H100 80GB HBM3          On  | 00000000:75:02.0 Off |                    0 |
| N/A   38C    P0             124W / 700W |    533MiB / 81559MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

====================================================================================================
Training DataLoader: total number of tokens: 3200000000 across 32 files
Validation DataLoader: total number of tokens: 100000000 across 1 files
====================================================================================================
step:0/1480 val_loss:10.8258 train_time:0ms step_avg:nanms
step:1/1480 train_time:23229ms step_avg:nanms
step:2/1480 train_time:23316ms step_avg:nanms
step:3/1480 train_time:23454ms step_avg:nanms
step:4/1480 train_time:23595ms step_avg:nanms
step:5/1480 train_time:23737ms step_avg:nanms
step:6/1480 train_time:23879ms step_avg:nanms
step:7/1480 train_time:24021ms step_avg:nanms
step:8/1480 train_time:24164ms step_avg:nanms
step:9/1480 train_time:24309ms step_avg:nanms
step:10/1480 train_time:24452ms step_avg:nanms
step:11/1480 train_time:142ms step_avg:nanms
step:12/1480 train_time:284ms step_avg:nanms
step:13/1480 train_time:427ms step_avg:142.28ms
step:14/1480 train_time:569ms step_avg:142.27ms
step:15/1480 train_time:711ms step_avg:142.13ms
step:16/1480 train_time:854ms step_avg:142.39ms
step:17/1480 train_time:996ms step_avg:142.27ms
step:18/1480 train_time:1138ms step_avg:142.24ms
step:19/1480 train_time:1280ms step_avg:142.18ms
step:20/1480 train_time:1424ms step_avg:142.43ms
step:21/1480 train_time:1568ms step_avg:142.55ms
step:22/1480 train_time:1712ms step_avg:142.64ms
step:23/1480 train_time:1855ms step_avg:142.71ms
step:24/1480 train_time:1997ms step_avg:142.66ms
step:25/1480 train_time:2140ms step_avg:142.69ms
step:26/1480 train_time:2283ms step_avg:142.70ms
step:27/1480 train_time:2428ms step_avg:142.82ms
step:28/1480 train_time:2570ms step_avg:142.80ms
step:29/1480 train_time:2712ms step_avg:142.73ms
step:30/1480 train_time:2854ms step_avg:142.71ms
step:31/1480 train_time:2997ms step_avg:142.73ms
step:32/1480 train_time:3140ms step_avg:142.71ms
step:33/1480 train_time:3281ms step_avg:142.66ms
step:34/1480 train_time:3426ms step_avg:142.74ms
step:35/1480 train_time:3570ms step_avg:142.79ms
step:36/1480 train_time:3713ms step_avg:142.79ms
step:37/1480 train_time:3856ms step_avg:142.81ms
step:38/1480 train_time:3999ms step_avg:142.84ms
step:39/1480 train_time:4144ms step_avg:142.90ms
step:40/1480 train_time:4288ms step_avg:142.94ms
step:41/1480 train_time:4431ms step_avg:142.92ms
step:42/1480 train_time:4572ms step_avg:142.89ms
step:43/1480 train_time:4714ms step_avg:142.85ms
step:44/1480 train_time:4857ms step_avg:142.85ms
step:45/1480 train_time:5000ms step_avg:142.84ms
step:46/1480 train_time:5143ms step_avg:142.86ms
step:47/1480 train_time:5286ms step_avg:142.87ms
step:48/1480 train_time:5429ms step_avg:142.88ms
step:49/1480 train_time:5573ms step_avg:142.89ms
step:50/1480 train_time:5713ms step_avg:142.84ms
step:51/1480 train_time:5857ms step_avg:142.85ms
step:52/1480 train_time:5999ms step_avg:142.83ms
step:53/1480 train_time:6142ms step_avg:142.84ms
step:54/1480 train_time:6285ms step_avg:142.85ms
step:55/1480 train_time:6429ms step_avg:142.86ms
step:56/1480 train_time:6571ms step_avg:142.86ms
step:57/1480 train_time:6713ms step_avg:142.82ms
step:58/1480 train_time:6856ms step_avg:142.83ms
step:59/1480 train_time:6997ms step_avg:142.80ms
step:60/1480 train_time:7139ms step_avg:142.79ms
step:61/1480 train_time:7282ms step_avg:142.79ms
step:62/1480 train_time:7427ms step_avg:142.82ms
step:63/1480 train_time:7569ms step_avg:142.81ms
step:64/1480 train_time:7711ms step_avg:142.79ms
step:65/1480 train_time:7853ms step_avg:142.79ms
step:66/1480 train_time:7995ms step_avg:142.77ms
step:67/1480 train_time:8139ms step_avg:142.78ms
step:68/1480 train_time:8281ms step_avg:142.78ms
step:69/1480 train_time:8425ms step_avg:142.80ms
step:70/1480 train_time:8570ms step_avg:142.84ms
step:71/1480 train_time:8712ms step_avg:142.82ms
step:72/1480 train_time:8855ms step_avg:142.83ms
step:73/1480 train_time:8996ms step_avg:142.80ms
step:74/1480 train_time:9137ms step_avg:142.77ms
step:75/1480 train_time:9278ms step_avg:142.75ms
step:76/1480 train_time:9423ms step_avg:142.77ms
step:77/1480 train_time:9567ms step_avg:142.80ms
step:78/1480 train_time:9710ms step_avg:142.79ms
step:79/1480 train_time:9853ms step_avg:142.80ms
step:80/1480 train_time:9995ms step_avg:142.79ms
step:81/1480 train_time:10137ms step_avg:142.77ms
step:82/1480 train_time:10278ms step_avg:142.76ms
step:83/1480 train_time:10423ms step_avg:142.77ms
step:84/1480 train_time:10567ms step_avg:142.79ms
step:85/1480 train_time:10710ms step_avg:142.80ms
step:86/1480 train_time:10853ms step_avg:142.80ms
step:87/1480 train_time:10994ms step_avg:142.78ms
step:88/1480 train_time:11135ms step_avg:142.76ms
step:89/1480 train_time:11277ms step_avg:142.75ms
step:90/1480 train_time:11419ms step_avg:142.74ms
step:91/1480 train_time:11562ms step_avg:142.74ms
step:92/1480 train_time:11707ms step_avg:142.77ms
step:93/1480 train_time:11851ms step_avg:142.78ms
step:94/1480 train_time:11993ms step_avg:142.78ms
step:95/1480 train_time:12135ms step_avg:142.77ms
step:96/1480 train_time:12276ms step_avg:142.75ms
step:97/1480 train_time:12418ms step_avg:142.74ms
step:98/1480 train_time:12564ms step_avg:142.77ms
step:99/1480 train_time:12707ms step_avg:142.77ms
step:100/1480 train_time:12851ms step_avg:142.79ms
step:101/1480 train_time:12992ms step_avg:142.77ms
step:102/1480 train_time:13134ms step_avg:142.77ms
step:103/1480 train_time:13276ms step_avg:142.75ms
step:104/1480 train_time:13417ms step_avg:142.74ms
step:105/1480 train_time:13560ms step_avg:142.74ms
step:106/1480 train_time:13706ms step_avg:142.77ms
step:107/1480 train_time:13850ms step_avg:142.78ms
step:108/1480 train_time:13993ms step_avg:142.78ms
step:109/1480 train_time:14135ms step_avg:142.78ms
step:110/1480 train_time:14276ms step_avg:142.76ms
step:111/1480 train_time:14419ms step_avg:142.77ms
step:112/1480 train_time:14567ms step_avg:142.81ms
step:113/1480 train_time:14716ms step_avg:142.87ms
step:114/1480 train_time:14863ms step_avg:142.91ms
step:115/1480 train_time:15011ms step_avg:142.96ms
step:116/1480 train_time:15156ms step_avg:142.98ms
step:117/1480 train_time:15302ms step_avg:143.01ms
step:118/1480 train_time:15448ms step_avg:143.03ms
step:119/1480 train_time:15595ms step_avg:143.07ms
step:120/1480 train_time:15741ms step_avg:143.10ms
step:121/1480 train_time:15889ms step_avg:143.14ms
step:122/1480 train_time:16036ms step_avg:143.18ms
step:123/1480 train_time:16182ms step_avg:143.20ms
step:124/1480 train_time:16330ms step_avg:143.24ms
step:125/1480 train_time:16476ms step_avg:143.27ms
step:125/1480 val_loss:4.4085 train_time:16533ms step_avg:143.76ms
step:126/1480 train_time:16629ms step_avg:143.35ms
step:127/1480 train_time:16779ms step_avg:143.41ms
step:128/1480 train_time:16926ms step_avg:143.44ms
step:129/1480 train_time:17071ms step_avg:143.45ms
step:130/1480 train_time:17217ms step_avg:143.48ms
step:131/1480 train_time:17364ms step_avg:143.50ms
step:132/1480 train_time:17510ms step_avg:143.52ms
step:133/1480 train_time:17660ms step_avg:143.58ms
step:134/1480 train_time:17807ms step_avg:143.61ms
step:135/1480 train_time:17955ms step_avg:143.64ms
step:136/1480 train_time:18102ms step_avg:143.67ms
step:137/1480 train_time:18247ms step_avg:143.68ms
step:138/1480 train_time:18394ms step_avg:143.70ms
step:139/1480 train_time:18541ms step_avg:143.73ms
step:140/1480 train_time:18688ms step_avg:143.76ms
step:141/1480 train_time:18837ms step_avg:143.79ms
step:142/1480 train_time:18985ms step_avg:143.82ms
step:143/1480 train_time:19129ms step_avg:143.83ms
step:144/1480 train_time:19276ms step_avg:143.85ms
step:145/1480 train_time:19422ms step_avg:143.87ms
step:146/1480 train_time:19568ms step_avg:143.89ms
step:147/1480 train_time:19715ms step_avg:143.90ms
step:148/1480 train_time:19863ms step_avg:143.93ms
step:149/1480 train_time:20009ms step_avg:143.95ms
step:150/1480 train_time:20156ms step_avg:143.97ms
step:151/1480 train_time:20303ms step_avg:143.99ms
step:152/1480 train_time:20449ms step_avg:144.01ms
step:153/1480 train_time:20597ms step_avg:144.04ms
step:154/1480 train_time:20744ms step_avg:144.06ms
step:155/1480 train_time:20891ms step_avg:144.08ms
step:156/1480 train_time:21039ms step_avg:144.10ms
step:157/1480 train_time:21186ms step_avg:144.12ms
step:158/1480 train_time:21332ms step_avg:144.14ms
step:159/1480 train_time:21479ms step_avg:144.16ms
step:160/1480 train_time:21625ms step_avg:144.17ms
step:161/1480 train_time:21770ms step_avg:144.17ms
step:162/1480 train_time:21918ms step_avg:144.20ms
step:163/1480 train_time:22065ms step_avg:144.22ms
step:164/1480 train_time:22211ms step_avg:144.23ms
step:165/1480 train_time:22359ms step_avg:144.25ms
step:166/1480 train_time:22506ms step_avg:144.27ms
step:167/1480 train_time:22652ms step_avg:144.28ms
step:168/1480 train_time:22800ms step_avg:144.30ms
step:169/1480 train_time:22945ms step_avg:144.31ms
step:170/1480 train_time:23091ms step_avg:144.32ms
step:171/1480 train_time:23238ms step_avg:144.33ms
step:172/1480 train_time:23385ms step_avg:144.35ms
step:173/1480 train_time:23530ms step_avg:144.36ms
step:174/1480 train_time:23678ms step_avg:144.38ms
step:175/1480 train_time:23824ms step_avg:144.39ms
step:176/1480 train_time:23969ms step_avg:144.39ms
step:177/1480 train_time:24117ms step_avg:144.41ms
step:178/1480 train_time:24265ms step_avg:144.43ms
step:179/1480 train_time:24410ms step_avg:144.44ms
step:180/1480 train_time:24558ms step_avg:144.46ms
step:181/1480 train_time:24705ms step_avg:144.47ms
step:182/1480 train_time:24850ms step_avg:144.48ms
step:183/1480 train_time:24997ms step_avg:144.49ms
step:184/1480 train_time:25144ms step_avg:144.51ms
step:185/1480 train_time:25292ms step_avg:144.53ms
step:186/1480 train_time:25440ms step_avg:144.54ms
step:187/1480 train_time:25586ms step_avg:144.55ms
step:188/1480 train_time:25731ms step_avg:144.56ms
step:189/1480 train_time:25878ms step_avg:144.57ms
step:190/1480 train_time:26024ms step_avg:144.58ms
step:191/1480 train_time:26170ms step_avg:144.59ms
step:192/1480 train_time:26318ms step_avg:144.60ms
step:193/1480 train_time:26465ms step_avg:144.62ms
step:194/1480 train_time:26610ms step_avg:144.62ms
step:195/1480 train_time:26758ms step_avg:144.64ms
step:196/1480 train_time:26905ms step_avg:144.65ms
step:197/1480 train_time:27050ms step_avg:144.65ms
step:198/1480 train_time:27198ms step_avg:144.67ms
step:199/1480 train_time:27344ms step_avg:144.68ms
step:200/1480 train_time:27490ms step_avg:144.69ms
step:201/1480 train_time:27636ms step_avg:144.69ms
step:202/1480 train_time:27783ms step_avg:144.70ms
step:203/1480 train_time:27928ms step_avg:144.71ms
step:204/1480 train_time:28076ms step_avg:144.72ms
step:205/1480 train_time:28223ms step_avg:144.74ms
step:206/1480 train_time:28369ms step_avg:144.74ms
step:207/1480 train_time:28517ms step_avg:144.76ms
step:208/1480 train_time:28664ms step_avg:144.77ms
step:209/1480 train_time:28810ms step_avg:144.77ms
step:210/1480 train_time:28957ms step_avg:144.79ms
step:211/1480 train_time:29105ms step_avg:144.80ms
step:212/1480 train_time:29251ms step_avg:144.81ms
step:213/1480 train_time:29398ms step_avg:144.82ms
step:214/1480 train_time:29544ms step_avg:144.82ms
step:215/1480 train_time:29690ms step_avg:144.83ms
step:216/1480 train_time:29837ms step_avg:144.84ms
step:217/1480 train_time:29984ms step_avg:144.85ms
step:218/1480 train_time:30129ms step_avg:144.85ms
step:219/1480 train_time:30276ms step_avg:144.86ms
step:220/1480 train_time:30422ms step_avg:144.87ms
step:221/1480 train_time:30570ms step_avg:144.88ms
step:222/1480 train_time:30721ms step_avg:144.91ms
step:223/1480 train_time:30871ms step_avg:144.93ms
step:224/1480 train_time:31021ms step_avg:144.96ms
step:225/1480 train_time:31171ms step_avg:144.98ms
step:226/1480 train_time:31321ms step_avg:145.01ms
step:227/1480 train_time:31472ms step_avg:145.03ms
step:228/1480 train_time:31622ms step_avg:145.06ms
step:229/1480 train_time:31772ms step_avg:145.08ms
step:230/1480 train_time:31922ms step_avg:145.10ms
step:231/1480 train_time:32071ms step_avg:145.12ms
step:232/1480 train_time:32223ms step_avg:145.15ms
step:233/1480 train_time:32373ms step_avg:145.17ms
step:234/1480 train_time:32524ms step_avg:145.20ms
step:235/1480 train_time:32676ms step_avg:145.23ms
step:236/1480 train_time:32826ms step_avg:145.25ms
step:237/1480 train_time:32976ms step_avg:145.27ms
step:238/1480 train_time:33126ms step_avg:145.29ms
step:239/1480 train_time:33276ms step_avg:145.31ms
step:240/1480 train_time:33427ms step_avg:145.33ms
step:241/1480 train_time:33577ms step_avg:145.36ms
step:242/1480 train_time:33728ms step_avg:145.38ms
step:243/1480 train_time:33878ms step_avg:145.40ms
step:244/1480 train_time:34028ms step_avg:145.42ms
step:245/1480 train_time:34178ms step_avg:145.44ms
step:246/1480 train_time:34328ms step_avg:145.46ms
step:247/1480 train_time:34480ms step_avg:145.48ms
step:248/1480 train_time:34630ms step_avg:145.50ms
step:249/1480 train_time:34781ms step_avg:145.53ms
step:250/1480 train_time:34931ms step_avg:145.55ms
step:250/1480 val_loss:3.9846 train_time:34992ms step_avg:145.80ms
step:251/1480 train_time:35088ms step_avg:145.59ms
step:252/1480 train_time:35240ms step_avg:145.62ms
step:253/1480 train_time:35392ms step_avg:145.65ms
step:254/1480 train_time:35542ms step_avg:145.66ms
step:255/1480 train_time:35693ms step_avg:145.69ms
step:256/1480 train_time:35842ms step_avg:145.70ms
step:257/1480 train_time:35992ms step_avg:145.72ms
step:258/1480 train_time:36143ms step_avg:145.74ms
step:259/1480 train_time:36295ms step_avg:145.76ms
step:260/1480 train_time:36445ms step_avg:145.78ms
step:261/1480 train_time:36595ms step_avg:145.80ms
step:262/1480 train_time:36744ms step_avg:145.81ms
step:263/1480 train_time:36895ms step_avg:145.83ms
step:264/1480 train_time:37043ms step_avg:145.84ms
step:265/1480 train_time:37196ms step_avg:145.87ms
step:266/1480 train_time:37348ms step_avg:145.89ms
step:267/1480 train_time:37499ms step_avg:145.91ms
step:268/1480 train_time:37649ms step_avg:145.93ms
step:269/1480 train_time:37800ms step_avg:145.95ms
step:270/1480 train_time:37951ms step_avg:145.96ms
step:271/1480 train_time:38101ms step_avg:145.98ms
step:272/1480 train_time:38253ms step_avg:146.00ms
step:273/1480 train_time:38403ms step_avg:146.02ms
step:274/1480 train_time:38553ms step_avg:146.03ms
step:275/1480 train_time:38704ms step_avg:146.05ms
step:276/1480 train_time:38854ms step_avg:146.07ms
step:277/1480 train_time:39004ms step_avg:146.08ms
step:278/1480 train_time:39154ms step_avg:146.10ms
step:279/1480 train_time:39304ms step_avg:146.11ms
step:280/1480 train_time:39455ms step_avg:146.13ms
step:281/1480 train_time:39606ms step_avg:146.15ms
step:282/1480 train_time:39758ms step_avg:146.17ms
step:283/1480 train_time:39908ms step_avg:146.18ms
step:284/1480 train_time:40058ms step_avg:146.20ms
step:285/1480 train_time:40209ms step_avg:146.21ms
step:286/1480 train_time:40358ms step_avg:146.23ms
step:287/1480 train_time:40510ms step_avg:146.24ms
step:288/1480 train_time:40660ms step_avg:146.26ms
step:289/1480 train_time:40811ms step_avg:146.28ms
step:290/1480 train_time:40961ms step_avg:146.29ms
step:291/1480 train_time:41115ms step_avg:146.31ms
step:292/1480 train_time:41265ms step_avg:146.33ms
step:293/1480 train_time:41415ms step_avg:146.34ms
step:294/1480 train_time:41564ms step_avg:146.35ms
step:295/1480 train_time:41714ms step_avg:146.37ms
step:296/1480 train_time:41864ms step_avg:146.38ms
step:297/1480 train_time:42015ms step_avg:146.39ms
step:298/1480 train_time:42166ms step_avg:146.41ms
step:299/1480 train_time:42318ms step_avg:146.43ms
step:300/1480 train_time:42468ms step_avg:146.44ms
step:301/1480 train_time:42618ms step_avg:146.45ms
step:302/1480 train_time:42768ms step_avg:146.46ms
step:303/1480 train_time:42919ms step_avg:146.48ms
step:304/1480 train_time:43069ms step_avg:146.49ms
step:305/1480 train_time:43219ms step_avg:146.51ms
step:306/1480 train_time:43370ms step_avg:146.52ms
step:307/1480 train_time:43521ms step_avg:146.53ms
step:308/1480 train_time:43672ms step_avg:146.55ms
step:309/1480 train_time:43822ms step_avg:146.56ms
step:310/1480 train_time:43972ms step_avg:146.57ms
step:311/1480 train_time:44122ms step_avg:146.59ms
step:312/1480 train_time:44273ms step_avg:146.60ms
step:313/1480 train_time:44423ms step_avg:146.61ms
step:314/1480 train_time:44575ms step_avg:146.63ms
step:315/1480 train_time:44724ms step_avg:146.64ms
step:316/1480 train_time:44875ms step_avg:146.65ms
step:317/1480 train_time:45025ms step_avg:146.66ms
step:318/1480 train_time:45177ms step_avg:146.68ms
step:319/1480 train_time:45326ms step_avg:146.69ms
step:320/1480 train_time:45478ms step_avg:146.70ms
step:321/1480 train_time:45628ms step_avg:146.71ms
step:322/1480 train_time:45778ms step_avg:146.73ms
step:323/1480 train_time:45930ms step_avg:146.74ms
step:324/1480 train_time:46080ms step_avg:146.75ms
step:325/1480 train_time:46231ms step_avg:146.77ms
step:326/1480 train_time:46382ms step_avg:146.78ms
step:327/1480 train_time:46532ms step_avg:146.79ms
step:328/1480 train_time:46682ms step_avg:146.80ms
step:329/1480 train_time:46832ms step_avg:146.81ms
step:330/1480 train_time:46984ms step_avg:146.83ms
step:331/1480 train_time:47137ms step_avg:146.84ms
step:332/1480 train_time:47290ms step_avg:146.86ms
step:333/1480 train_time:47444ms step_avg:146.88ms
step:334/1480 train_time:47599ms step_avg:146.91ms
step:335/1480 train_time:47753ms step_avg:146.93ms
step:336/1480 train_time:47906ms step_avg:146.95ms
step:337/1480 train_time:48059ms step_avg:146.97ms
step:338/1480 train_time:48214ms step_avg:146.99ms
step:339/1480 train_time:48366ms step_avg:147.01ms
step:340/1480 train_time:48521ms step_avg:147.03ms
step:341/1480 train_time:48675ms step_avg:147.06ms
step:342/1480 train_time:48829ms step_avg:147.07ms
step:343/1480 train_time:48983ms step_avg:147.10ms
step:344/1480 train_time:49136ms step_avg:147.12ms
step:345/1480 train_time:49293ms step_avg:147.14ms
step:346/1480 train_time:49447ms step_avg:147.16ms
step:347/1480 train_time:49600ms step_avg:147.18ms
step:348/1480 train_time:49753ms step_avg:147.20ms
step:349/1480 train_time:49906ms step_avg:147.22ms
step:350/1480 train_time:50060ms step_avg:147.23ms
step:351/1480 train_time:50214ms step_avg:147.26ms
step:352/1480 train_time:50369ms step_avg:147.28ms
step:353/1480 train_time:50523ms step_avg:147.30ms
step:354/1480 train_time:50676ms step_avg:147.31ms
step:355/1480 train_time:50829ms step_avg:147.33ms
step:356/1480 train_time:50983ms step_avg:147.35ms
step:357/1480 train_time:51137ms step_avg:147.37ms
step:358/1480 train_time:51292ms step_avg:147.39ms
step:359/1480 train_time:51447ms step_avg:147.41ms
step:360/1480 train_time:51602ms step_avg:147.43ms
step:361/1480 train_time:51757ms step_avg:147.46ms
step:362/1480 train_time:51911ms step_avg:147.48ms
step:363/1480 train_time:52064ms step_avg:147.49ms
step:364/1480 train_time:52218ms step_avg:147.51ms
step:365/1480 train_time:52372ms step_avg:147.53ms
step:366/1480 train_time:52527ms step_avg:147.55ms
step:367/1480 train_time:52680ms step_avg:147.56ms
step:368/1480 train_time:52834ms step_avg:147.58ms
step:369/1480 train_time:52987ms step_avg:147.60ms
step:370/1480 train_time:53140ms step_avg:147.61ms
step:371/1480 train_time:53295ms step_avg:147.63ms
step:372/1480 train_time:53449ms step_avg:147.65ms
step:373/1480 train_time:53602ms step_avg:147.66ms
step:374/1480 train_time:53756ms step_avg:147.68ms
step:375/1480 train_time:53913ms step_avg:147.71ms
step:375/1480 val_loss:3.8072 train_time:53974ms step_avg:147.87ms
step:376/1480 train_time:54072ms step_avg:147.74ms
step:377/1480 train_time:54228ms step_avg:147.76ms
step:378/1480 train_time:54381ms step_avg:147.78ms
step:379/1480 train_time:54534ms step_avg:147.79ms
step:380/1480 train_time:54688ms step_avg:147.80ms
step:381/1480 train_time:54840ms step_avg:147.82ms
step:382/1480 train_time:54995ms step_avg:147.84ms
step:383/1480 train_time:55151ms step_avg:147.86ms
step:384/1480 train_time:55306ms step_avg:147.88ms
step:385/1480 train_time:55459ms step_avg:147.89ms
step:386/1480 train_time:55612ms step_avg:147.91ms
step:387/1480 train_time:55766ms step_avg:147.92ms
step:388/1480 train_time:55918ms step_avg:147.93ms
step:389/1480 train_time:56073ms step_avg:147.95ms
step:390/1480 train_time:56228ms step_avg:147.97ms
step:391/1480 train_time:56382ms step_avg:147.98ms
step:392/1480 train_time:56536ms step_avg:148.00ms
step:393/1480 train_time:56689ms step_avg:148.01ms
step:394/1480 train_time:56842ms step_avg:148.03ms
step:395/1480 train_time:56995ms step_avg:148.04ms
step:396/1480 train_time:57149ms step_avg:148.06ms
step:397/1480 train_time:57302ms step_avg:148.07ms
step:398/1480 train_time:57455ms step_avg:148.08ms
step:399/1480 train_time:57611ms step_avg:148.10ms
step:400/1480 train_time:57765ms step_avg:148.12ms
step:401/1480 train_time:57919ms step_avg:148.13ms
step:402/1480 train_time:58073ms step_avg:148.14ms
step:403/1480 train_time:58227ms step_avg:148.16ms
step:404/1480 train_time:58381ms step_avg:148.17ms
step:405/1480 train_time:58535ms step_avg:148.19ms
step:406/1480 train_time:58689ms step_avg:148.21ms
step:407/1480 train_time:58842ms step_avg:148.22ms
step:408/1480 train_time:58996ms step_avg:148.23ms
step:409/1480 train_time:59149ms step_avg:148.24ms
step:410/1480 train_time:59302ms step_avg:148.26ms
step:411/1480 train_time:59456ms step_avg:148.27ms
step:412/1480 train_time:59612ms step_avg:148.29ms
step:413/1480 train_time:59765ms step_avg:148.30ms
step:414/1480 train_time:59919ms step_avg:148.31ms
step:415/1480 train_time:60073ms step_avg:148.33ms
step:416/1480 train_time:60227ms step_avg:148.34ms
step:417/1480 train_time:60381ms step_avg:148.36ms
step:418/1480 train_time:60535ms step_avg:148.37ms
step:419/1480 train_time:60689ms step_avg:148.39ms
step:420/1480 train_time:60843ms step_avg:148.40ms
step:421/1480 train_time:60996ms step_avg:148.41ms
step:422/1480 train_time:61148ms step_avg:148.42ms
step:423/1480 train_time:61302ms step_avg:148.43ms
step:424/1480 train_time:61455ms step_avg:148.44ms
step:425/1480 train_time:61610ms step_avg:148.46ms
step:426/1480 train_time:61764ms step_avg:148.47ms
step:427/1480 train_time:61918ms step_avg:148.49ms
step:428/1480 train_time:62073ms step_avg:148.50ms
step:429/1480 train_time:62227ms step_avg:148.51ms
step:430/1480 train_time:62380ms step_avg:148.52ms
step:431/1480 train_time:62534ms step_avg:148.54ms
step:432/1480 train_time:62689ms step_avg:148.55ms
step:433/1480 train_time:62842ms step_avg:148.56ms
step:434/1480 train_time:62997ms step_avg:148.58ms
step:435/1480 train_time:63151ms step_avg:148.59ms
step:436/1480 train_time:63304ms step_avg:148.60ms
step:437/1480 train_time:63457ms step_avg:148.61ms
step:438/1480 train_time:63612ms step_avg:148.63ms
step:439/1480 train_time:63766ms step_avg:148.64ms
step:440/1480 train_time:63921ms step_avg:148.65ms
step:441/1480 train_time:64077ms step_avg:148.67ms
step:442/1480 train_time:64234ms step_avg:148.69ms
step:443/1480 train_time:64392ms step_avg:148.71ms
step:444/1480 train_time:64548ms step_avg:148.73ms
step:445/1480 train_time:64705ms step_avg:148.75ms
step:446/1480 train_time:64859ms step_avg:148.76ms
step:447/1480 train_time:65016ms step_avg:148.78ms
step:448/1480 train_time:65173ms step_avg:148.80ms
step:449/1480 train_time:65333ms step_avg:148.82ms
step:450/1480 train_time:65491ms step_avg:148.84ms
step:451/1480 train_time:65650ms step_avg:148.87ms
step:452/1480 train_time:65806ms step_avg:148.88ms
step:453/1480 train_time:65962ms step_avg:148.90ms
step:454/1480 train_time:66118ms step_avg:148.91ms
step:455/1480 train_time:66274ms step_avg:148.93ms
step:456/1480 train_time:66431ms step_avg:148.95ms
step:457/1480 train_time:66589ms step_avg:148.97ms
step:458/1480 train_time:66745ms step_avg:148.98ms
step:459/1480 train_time:66901ms step_avg:149.00ms
step:460/1480 train_time:67058ms step_avg:149.02ms
step:461/1480 train_time:67217ms step_avg:149.04ms
step:462/1480 train_time:67374ms step_avg:149.06ms
step:463/1480 train_time:67532ms step_avg:149.08ms
step:464/1480 train_time:67688ms step_avg:149.09ms
step:465/1480 train_time:67844ms step_avg:149.11ms
step:466/1480 train_time:68000ms step_avg:149.12ms
step:467/1480 train_time:68156ms step_avg:149.14ms
step:468/1480 train_time:68313ms step_avg:149.16ms
step:469/1480 train_time:68470ms step_avg:149.17ms
step:470/1480 train_time:68627ms step_avg:149.19ms
step:471/1480 train_time:68783ms step_avg:149.20ms
step:472/1480 train_time:68940ms step_avg:149.22ms
step:473/1480 train_time:69095ms step_avg:149.23ms
step:474/1480 train_time:69253ms step_avg:149.25ms
step:475/1480 train_time:69410ms step_avg:149.27ms
step:476/1480 train_time:69568ms step_avg:149.29ms
step:477/1480 train_time:69726ms step_avg:149.31ms
step:478/1480 train_time:69881ms step_avg:149.32ms
step:479/1480 train_time:70038ms step_avg:149.34ms
step:480/1480 train_time:70195ms step_avg:149.35ms
step:481/1480 train_time:70352ms step_avg:149.37ms
step:482/1480 train_time:70509ms step_avg:149.38ms
step:483/1480 train_time:70666ms step_avg:149.40ms
step:484/1480 train_time:70823ms step_avg:149.42ms
step:485/1480 train_time:70981ms step_avg:149.43ms
step:486/1480 train_time:71138ms step_avg:149.45ms
step:487/1480 train_time:71294ms step_avg:149.46ms
step:488/1480 train_time:71451ms step_avg:149.48ms
step:489/1480 train_time:71607ms step_avg:149.49ms
step:490/1480 train_time:71764ms step_avg:149.51ms
step:491/1480 train_time:71921ms step_avg:149.52ms
step:492/1480 train_time:72079ms step_avg:149.54ms
step:493/1480 train_time:72237ms step_avg:149.56ms
step:494/1480 train_time:72393ms step_avg:149.57ms
step:495/1480 train_time:72550ms step_avg:149.59ms
step:496/1480 train_time:72707ms step_avg:149.60ms
step:497/1480 train_time:72865ms step_avg:149.62ms
step:498/1480 train_time:73022ms step_avg:149.64ms
step:499/1480 train_time:73181ms step_avg:149.65ms
step:500/1480 train_time:73338ms step_avg:149.67ms
step:500/1480 val_loss:3.6846 train_time:73400ms step_avg:149.80ms
step:501/1480 train_time:73499ms step_avg:149.69ms
step:502/1480 train_time:73658ms step_avg:149.71ms
step:503/1480 train_time:73813ms step_avg:149.72ms
step:504/1480 train_time:73969ms step_avg:149.73ms
step:505/1480 train_time:74123ms step_avg:149.74ms
step:506/1480 train_time:74280ms step_avg:149.76ms
step:507/1480 train_time:74438ms step_avg:149.77ms
step:508/1480 train_time:74597ms step_avg:149.79ms
step:509/1480 train_time:74755ms step_avg:149.81ms
step:510/1480 train_time:74910ms step_avg:149.82ms
step:511/1480 train_time:75067ms step_avg:149.83ms
step:512/1480 train_time:75225ms step_avg:149.85ms
step:513/1480 train_time:75381ms step_avg:149.86ms
step:514/1480 train_time:75537ms step_avg:149.88ms
step:515/1480 train_time:75696ms step_avg:149.89ms
step:516/1480 train_time:75855ms step_avg:149.91ms
step:517/1480 train_time:76013ms step_avg:149.93ms
step:518/1480 train_time:76170ms step_avg:149.94ms
step:519/1480 train_time:76327ms step_avg:149.95ms
step:520/1480 train_time:76484ms step_avg:149.97ms
step:521/1480 train_time:76640ms step_avg:149.98ms
step:522/1480 train_time:76798ms step_avg:150.00ms
step:523/1480 train_time:76957ms step_avg:150.01ms
step:524/1480 train_time:77114ms step_avg:150.03ms
step:525/1480 train_time:77271ms step_avg:150.04ms
step:526/1480 train_time:77430ms step_avg:150.06ms
step:527/1480 train_time:77586ms step_avg:150.07ms
step:528/1480 train_time:77742ms step_avg:150.08ms
step:529/1480 train_time:77899ms step_avg:150.09ms
step:530/1480 train_time:78058ms step_avg:150.11ms
step:531/1480 train_time:78216ms step_avg:150.13ms
step:532/1480 train_time:78372ms step_avg:150.14ms
step:533/1480 train_time:78528ms step_avg:150.15ms
step:534/1480 train_time:78683ms step_avg:150.16ms
step:535/1480 train_time:78840ms step_avg:150.17ms
step:536/1480 train_time:78998ms step_avg:150.19ms
step:537/1480 train_time:79155ms step_avg:150.20ms
step:538/1480 train_time:79312ms step_avg:150.21ms
step:539/1480 train_time:79470ms step_avg:150.23ms
step:540/1480 train_time:79625ms step_avg:150.24ms
step:541/1480 train_time:79781ms step_avg:150.25ms
step:542/1480 train_time:79938ms step_avg:150.26ms
step:543/1480 train_time:80095ms step_avg:150.27ms
step:544/1480 train_time:80251ms step_avg:150.28ms
step:545/1480 train_time:80408ms step_avg:150.30ms
step:546/1480 train_time:80564ms step_avg:150.31ms
step:547/1480 train_time:80721ms step_avg:150.32ms
step:548/1480 train_time:80879ms step_avg:150.33ms
step:549/1480 train_time:81037ms step_avg:150.35ms
step:550/1480 train_time:81196ms step_avg:150.36ms
step:551/1480 train_time:81355ms step_avg:150.38ms
step:552/1480 train_time:81514ms step_avg:150.40ms
step:553/1480 train_time:81674ms step_avg:150.41ms
step:554/1480 train_time:81833ms step_avg:150.43ms
step:555/1480 train_time:81995ms step_avg:150.45ms
step:556/1480 train_time:82153ms step_avg:150.46ms
step:557/1480 train_time:82314ms step_avg:150.48ms
step:558/1480 train_time:82474ms step_avg:150.50ms
step:559/1480 train_time:82632ms step_avg:150.51ms
step:560/1480 train_time:82792ms step_avg:150.53ms
step:561/1480 train_time:82951ms step_avg:150.55ms
step:562/1480 train_time:83110ms step_avg:150.56ms
step:563/1480 train_time:83269ms step_avg:150.58ms
step:564/1480 train_time:83428ms step_avg:150.59ms
step:565/1480 train_time:83586ms step_avg:150.60ms
step:566/1480 train_time:83744ms step_avg:150.62ms
step:567/1480 train_time:83902ms step_avg:150.63ms
step:568/1480 train_time:84060ms step_avg:150.65ms
step:569/1480 train_time:84219ms step_avg:150.66ms
step:570/1480 train_time:84378ms step_avg:150.67ms
step:571/1480 train_time:84539ms step_avg:150.69ms
step:572/1480 train_time:84700ms step_avg:150.71ms
step:573/1480 train_time:84861ms step_avg:150.73ms
step:574/1480 train_time:85021ms step_avg:150.75ms
step:575/1480 train_time:85181ms step_avg:150.76ms
step:576/1480 train_time:85340ms step_avg:150.78ms
step:577/1480 train_time:85499ms step_avg:150.79ms
step:578/1480 train_time:85658ms step_avg:150.81ms
step:579/1480 train_time:85818ms step_avg:150.82ms
step:580/1480 train_time:85979ms step_avg:150.84ms
step:581/1480 train_time:86139ms step_avg:150.86ms
step:582/1480 train_time:86300ms step_avg:150.87ms
step:583/1480 train_time:86460ms step_avg:150.89ms
step:584/1480 train_time:86619ms step_avg:150.90ms
step:585/1480 train_time:86778ms step_avg:150.92ms
step:586/1480 train_time:86938ms step_avg:150.93ms
step:587/1480 train_time:87099ms step_avg:150.95ms
step:588/1480 train_time:87259ms step_avg:150.97ms
step:589/1480 train_time:87420ms step_avg:150.98ms
step:590/1480 train_time:87581ms step_avg:151.00ms
step:591/1480 train_time:87738ms step_avg:151.01ms
step:592/1480 train_time:87899ms step_avg:151.03ms
step:593/1480 train_time:88059ms step_avg:151.04ms
step:594/1480 train_time:88219ms step_avg:151.06ms
step:595/1480 train_time:88381ms step_avg:151.08ms
step:596/1480 train_time:88543ms step_avg:151.10ms
step:597/1480 train_time:88702ms step_avg:151.11ms
step:598/1480 train_time:88861ms step_avg:151.12ms
step:599/1480 train_time:89020ms step_avg:151.14ms
step:600/1480 train_time:89179ms step_avg:151.15ms
step:601/1480 train_time:89339ms step_avg:151.17ms
step:602/1480 train_time:89499ms step_avg:151.18ms
step:603/1480 train_time:89659ms step_avg:151.20ms
step:604/1480 train_time:89819ms step_avg:151.21ms
step:605/1480 train_time:89979ms step_avg:151.23ms
step:606/1480 train_time:90141ms step_avg:151.24ms
step:607/1480 train_time:90302ms step_avg:151.26ms
step:608/1480 train_time:90461ms step_avg:151.27ms
step:609/1480 train_time:90620ms step_avg:151.29ms
step:610/1480 train_time:90779ms step_avg:151.30ms
step:611/1480 train_time:90939ms step_avg:151.31ms
step:612/1480 train_time:91100ms step_avg:151.33ms
step:613/1480 train_time:91261ms step_avg:151.35ms
step:614/1480 train_time:91421ms step_avg:151.36ms
step:615/1480 train_time:91580ms step_avg:151.37ms
step:616/1480 train_time:91738ms step_avg:151.38ms
step:617/1480 train_time:91899ms step_avg:151.40ms
step:618/1480 train_time:92058ms step_avg:151.41ms
step:619/1480 train_time:92218ms step_avg:151.42ms
step:620/1480 train_time:92380ms step_avg:151.44ms
step:621/1480 train_time:92539ms step_avg:151.45ms
step:622/1480 train_time:92699ms step_avg:151.47ms
step:623/1480 train_time:92860ms step_avg:151.48ms
step:624/1480 train_time:93019ms step_avg:151.50ms
step:625/1480 train_time:93179ms step_avg:151.51ms
step:625/1480 val_loss:3.6037 train_time:93243ms step_avg:151.61ms
step:626/1480 train_time:93341ms step_avg:151.53ms
step:627/1480 train_time:93500ms step_avg:151.54ms
step:628/1480 train_time:93656ms step_avg:151.55ms
step:629/1480 train_time:93814ms step_avg:151.56ms
step:630/1480 train_time:93972ms step_avg:151.57ms
step:631/1480 train_time:94131ms step_avg:151.58ms
step:632/1480 train_time:94291ms step_avg:151.59ms
step:633/1480 train_time:94451ms step_avg:151.61ms
step:634/1480 train_time:94611ms step_avg:151.62ms
step:635/1480 train_time:94770ms step_avg:151.63ms
step:636/1480 train_time:94930ms step_avg:151.65ms
step:637/1480 train_time:95091ms step_avg:151.66ms
step:638/1480 train_time:95251ms step_avg:151.67ms
step:639/1480 train_time:95410ms step_avg:151.69ms
step:640/1480 train_time:95571ms step_avg:151.70ms
step:641/1480 train_time:95731ms step_avg:151.71ms
step:642/1480 train_time:95890ms step_avg:151.72ms
step:643/1480 train_time:96051ms step_avg:151.74ms
step:644/1480 train_time:96210ms step_avg:151.75ms
step:645/1480 train_time:96369ms step_avg:151.76ms
step:646/1480 train_time:96528ms step_avg:151.77ms
step:647/1480 train_time:96687ms step_avg:151.78ms
step:648/1480 train_time:96850ms step_avg:151.80ms
step:649/1480 train_time:97010ms step_avg:151.82ms
step:650/1480 train_time:97170ms step_avg:151.83ms
step:651/1480 train_time:97331ms step_avg:151.84ms
step:652/1480 train_time:97491ms step_avg:151.85ms
step:653/1480 train_time:97650ms step_avg:151.87ms
step:654/1480 train_time:97810ms step_avg:151.88ms
step:655/1480 train_time:97970ms step_avg:151.89ms
step:656/1480 train_time:98131ms step_avg:151.91ms
step:657/1480 train_time:98292ms step_avg:151.92ms
step:658/1480 train_time:98452ms step_avg:151.93ms
step:659/1480 train_time:98612ms step_avg:151.94ms
step:660/1480 train_time:98775ms step_avg:151.96ms
step:661/1480 train_time:98937ms step_avg:151.98ms
step:662/1480 train_time:99097ms step_avg:151.99ms
step:663/1480 train_time:99257ms step_avg:152.00ms
step:664/1480 train_time:99419ms step_avg:152.02ms
step:665/1480 train_time:99580ms step_avg:152.03ms
step:666/1480 train_time:99740ms step_avg:152.04ms
step:667/1480 train_time:99901ms step_avg:152.06ms
step:668/1480 train_time:100061ms step_avg:152.07ms
step:669/1480 train_time:100224ms step_avg:152.09ms
step:670/1480 train_time:100385ms step_avg:152.10ms
step:671/1480 train_time:100546ms step_avg:152.11ms
step:672/1480 train_time:100708ms step_avg:152.13ms
step:673/1480 train_time:100872ms step_avg:152.15ms
step:674/1480 train_time:101035ms step_avg:152.16ms
step:675/1480 train_time:101197ms step_avg:152.18ms
step:676/1480 train_time:101359ms step_avg:152.19ms
step:677/1480 train_time:101520ms step_avg:152.20ms
step:678/1480 train_time:101682ms step_avg:152.22ms
step:679/1480 train_time:101843ms step_avg:152.23ms
step:680/1480 train_time:102006ms step_avg:152.25ms
step:681/1480 train_time:102168ms step_avg:152.26ms
step:682/1480 train_time:102331ms step_avg:152.28ms
step:683/1480 train_time:102493ms step_avg:152.29ms
step:684/1480 train_time:102654ms step_avg:152.31ms
step:685/1480 train_time:102815ms step_avg:152.32ms
step:686/1480 train_time:102976ms step_avg:152.33ms
step:687/1480 train_time:103137ms step_avg:152.34ms
step:688/1480 train_time:103300ms step_avg:152.36ms
step:689/1480 train_time:103461ms step_avg:152.37ms
step:690/1480 train_time:103626ms step_avg:152.39ms
step:691/1480 train_time:103788ms step_avg:152.41ms
step:692/1480 train_time:103951ms step_avg:152.42ms
step:693/1480 train_time:104113ms step_avg:152.44ms
step:694/1480 train_time:104276ms step_avg:152.45ms
step:695/1480 train_time:104436ms step_avg:152.46ms
step:696/1480 train_time:104597ms step_avg:152.47ms
step:697/1480 train_time:104760ms step_avg:152.49ms
step:698/1480 train_time:104919ms step_avg:152.50ms
step:699/1480 train_time:105082ms step_avg:152.51ms
step:700/1480 train_time:105244ms step_avg:152.53ms
step:701/1480 train_time:105405ms step_avg:152.54ms
step:702/1480 train_time:105564ms step_avg:152.55ms
step:703/1480 train_time:105725ms step_avg:152.56ms
step:704/1480 train_time:105886ms step_avg:152.57ms
step:705/1480 train_time:106051ms step_avg:152.59ms
step:706/1480 train_time:106214ms step_avg:152.61ms
step:707/1480 train_time:106376ms step_avg:152.62ms
step:708/1480 train_time:106537ms step_avg:152.63ms
step:709/1480 train_time:106698ms step_avg:152.64ms
step:710/1480 train_time:106858ms step_avg:152.65ms
step:711/1480 train_time:107019ms step_avg:152.67ms
step:712/1480 train_time:107184ms step_avg:152.68ms
step:713/1480 train_time:107348ms step_avg:152.70ms
step:714/1480 train_time:107510ms step_avg:152.71ms
step:715/1480 train_time:107672ms step_avg:152.73ms
step:716/1480 train_time:107833ms step_avg:152.74ms
step:717/1480 train_time:107995ms step_avg:152.75ms
step:718/1480 train_time:108154ms step_avg:152.76ms
step:719/1480 train_time:108312ms step_avg:152.77ms
step:720/1480 train_time:108475ms step_avg:152.78ms
step:721/1480 train_time:108636ms step_avg:152.79ms
step:722/1480 train_time:108798ms step_avg:152.81ms
step:723/1480 train_time:108959ms step_avg:152.82ms
step:724/1480 train_time:109120ms step_avg:152.83ms
step:725/1480 train_time:109284ms step_avg:152.84ms
step:726/1480 train_time:109450ms step_avg:152.86ms
step:727/1480 train_time:109613ms step_avg:152.88ms
step:728/1480 train_time:109773ms step_avg:152.89ms
step:729/1480 train_time:109934ms step_avg:152.90ms
step:730/1480 train_time:110096ms step_avg:152.91ms
step:731/1480 train_time:110257ms step_avg:152.92ms
step:732/1480 train_time:110417ms step_avg:152.93ms
step:733/1480 train_time:110579ms step_avg:152.94ms
step:734/1480 train_time:110742ms step_avg:152.96ms
step:735/1480 train_time:110902ms step_avg:152.97ms
step:736/1480 train_time:111064ms step_avg:152.98ms
step:737/1480 train_time:111228ms step_avg:153.00ms
step:738/1480 train_time:111391ms step_avg:153.01ms
step:739/1480 train_time:111552ms step_avg:153.02ms
step:740/1480 train_time:111717ms step_avg:153.04ms
step:741/1480 train_time:111879ms step_avg:153.05ms
step:742/1480 train_time:112041ms step_avg:153.06ms
step:743/1480 train_time:112200ms step_avg:153.07ms
step:744/1480 train_time:112364ms step_avg:153.09ms
step:745/1480 train_time:112531ms step_avg:153.10ms
step:746/1480 train_time:112692ms step_avg:153.11ms
step:747/1480 train_time:112852ms step_avg:153.12ms
step:748/1480 train_time:113016ms step_avg:153.14ms
step:749/1480 train_time:113180ms step_avg:153.15ms
step:750/1480 train_time:113339ms step_avg:153.16ms
step:750/1480 val_loss:3.5496 train_time:113403ms step_avg:153.25ms
step:751/1480 train_time:113502ms step_avg:153.17ms
step:752/1480 train_time:113664ms step_avg:153.19ms
step:753/1480 train_time:113824ms step_avg:153.20ms
step:754/1480 train_time:113985ms step_avg:153.21ms
step:755/1480 train_time:114145ms step_avg:153.21ms
step:756/1480 train_time:114307ms step_avg:153.23ms
step:757/1480 train_time:114472ms step_avg:153.24ms
step:758/1480 train_time:114636ms step_avg:153.26ms
step:759/1480 train_time:114798ms step_avg:153.27ms
step:760/1480 train_time:114959ms step_avg:153.28ms
step:761/1480 train_time:115121ms step_avg:153.29ms
step:762/1480 train_time:115281ms step_avg:153.30ms
step:763/1480 train_time:115442ms step_avg:153.31ms
step:764/1480 train_time:115604ms step_avg:153.32ms
step:765/1480 train_time:115765ms step_avg:153.33ms
step:766/1480 train_time:115929ms step_avg:153.35ms
step:767/1480 train_time:116092ms step_avg:153.36ms
step:768/1480 train_time:116254ms step_avg:153.37ms
step:769/1480 train_time:116417ms step_avg:153.38ms
step:770/1480 train_time:116579ms step_avg:153.39ms
step:771/1480 train_time:116743ms step_avg:153.41ms
step:772/1480 train_time:116904ms step_avg:153.42ms
step:773/1480 train_time:117068ms step_avg:153.43ms
step:774/1480 train_time:117232ms step_avg:153.44ms
step:775/1480 train_time:117396ms step_avg:153.46ms
step:776/1480 train_time:117559ms step_avg:153.47ms
step:777/1480 train_time:117724ms step_avg:153.49ms
step:778/1480 train_time:117887ms step_avg:153.50ms
step:779/1480 train_time:118050ms step_avg:153.51ms
step:780/1480 train_time:118214ms step_avg:153.52ms
step:781/1480 train_time:118377ms step_avg:153.54ms
step:782/1480 train_time:118542ms step_avg:153.55ms
step:783/1480 train_time:118703ms step_avg:153.56ms
step:784/1480 train_time:118868ms step_avg:153.58ms
step:785/1480 train_time:119032ms step_avg:153.59ms
step:786/1480 train_time:119197ms step_avg:153.60ms
step:787/1480 train_time:119359ms step_avg:153.62ms
step:788/1480 train_time:119523ms step_avg:153.63ms
step:789/1480 train_time:119684ms step_avg:153.64ms
step:790/1480 train_time:119848ms step_avg:153.65ms
step:791/1480 train_time:120015ms step_avg:153.67ms
step:792/1480 train_time:120178ms step_avg:153.68ms
step:793/1480 train_time:120339ms step_avg:153.69ms
step:794/1480 train_time:120503ms step_avg:153.70ms
step:795/1480 train_time:120667ms step_avg:153.72ms
step:796/1480 train_time:120834ms step_avg:153.73ms
step:797/1480 train_time:120999ms step_avg:153.75ms
step:798/1480 train_time:121163ms step_avg:153.76ms
step:799/1480 train_time:121331ms step_avg:153.78ms
step:800/1480 train_time:121495ms step_avg:153.79ms
step:801/1480 train_time:121659ms step_avg:153.80ms
step:802/1480 train_time:121825ms step_avg:153.82ms
step:803/1480 train_time:121988ms step_avg:153.83ms
step:804/1480 train_time:122150ms step_avg:153.84ms
step:805/1480 train_time:122316ms step_avg:153.86ms
step:806/1480 train_time:122477ms step_avg:153.87ms
step:807/1480 train_time:122639ms step_avg:153.88ms
step:808/1480 train_time:122803ms step_avg:153.89ms
step:809/1480 train_time:122964ms step_avg:153.90ms
step:810/1480 train_time:123125ms step_avg:153.91ms
step:811/1480 train_time:123288ms step_avg:153.92ms
step:812/1480 train_time:123453ms step_avg:153.93ms
step:813/1480 train_time:123614ms step_avg:153.94ms
step:814/1480 train_time:123777ms step_avg:153.95ms
step:815/1480 train_time:123940ms step_avg:153.96ms
step:816/1480 train_time:124107ms step_avg:153.98ms
step:817/1480 train_time:124270ms step_avg:153.99ms
step:818/1480 train_time:124432ms step_avg:154.00ms
step:819/1480 train_time:124596ms step_avg:154.01ms
step:820/1480 train_time:124759ms step_avg:154.02ms
step:821/1480 train_time:124921ms step_avg:154.03ms
step:822/1480 train_time:125084ms step_avg:154.04ms
step:823/1480 train_time:125246ms step_avg:154.05ms
step:824/1480 train_time:125409ms step_avg:154.06ms
step:825/1480 train_time:125573ms step_avg:154.08ms
step:826/1480 train_time:125740ms step_avg:154.09ms
step:827/1480 train_time:125904ms step_avg:154.10ms
step:828/1480 train_time:126065ms step_avg:154.11ms
step:829/1480 train_time:126231ms step_avg:154.13ms
step:830/1480 train_time:126398ms step_avg:154.14ms
step:831/1480 train_time:126560ms step_avg:154.15ms
step:832/1480 train_time:126723ms step_avg:154.16ms
step:833/1480 train_time:126888ms step_avg:154.18ms
step:834/1480 train_time:127053ms step_avg:154.19ms
step:835/1480 train_time:127216ms step_avg:154.20ms
step:836/1480 train_time:127380ms step_avg:154.21ms
step:837/1480 train_time:127542ms step_avg:154.22ms
step:838/1480 train_time:127705ms step_avg:154.23ms
step:839/1480 train_time:127867ms step_avg:154.24ms
step:840/1480 train_time:128030ms step_avg:154.25ms
step:841/1480 train_time:128192ms step_avg:154.26ms
step:842/1480 train_time:128356ms step_avg:154.27ms
step:843/1480 train_time:128518ms step_avg:154.28ms
step:844/1480 train_time:128680ms step_avg:154.29ms
step:845/1480 train_time:128843ms step_avg:154.30ms
step:846/1480 train_time:129009ms step_avg:154.32ms
step:847/1480 train_time:129173ms step_avg:154.33ms
step:848/1480 train_time:129336ms step_avg:154.34ms
step:849/1480 train_time:129499ms step_avg:154.35ms
step:850/1480 train_time:129662ms step_avg:154.36ms
step:851/1480 train_time:129827ms step_avg:154.37ms
step:852/1480 train_time:129991ms step_avg:154.38ms
step:853/1480 train_time:130154ms step_avg:154.39ms
step:854/1480 train_time:130319ms step_avg:154.41ms
step:855/1480 train_time:130481ms step_avg:154.42ms
step:856/1480 train_time:130644ms step_avg:154.43ms
step:857/1480 train_time:130810ms step_avg:154.44ms
step:858/1480 train_time:130974ms step_avg:154.45ms
step:859/1480 train_time:131138ms step_avg:154.46ms
step:860/1480 train_time:131299ms step_avg:154.47ms
step:861/1480 train_time:131466ms step_avg:154.48ms
step:862/1480 train_time:131637ms step_avg:154.50ms
step:863/1480 train_time:131803ms step_avg:154.52ms
step:864/1480 train_time:131966ms step_avg:154.53ms
step:865/1480 train_time:132129ms step_avg:154.54ms
step:866/1480 train_time:132296ms step_avg:154.55ms
step:867/1480 train_time:132459ms step_avg:154.56ms
step:868/1480 train_time:132620ms step_avg:154.57ms
step:869/1480 train_time:132781ms step_avg:154.58ms
step:870/1480 train_time:132946ms step_avg:154.59ms
step:871/1480 train_time:133109ms step_avg:154.60ms
step:872/1480 train_time:133274ms step_avg:154.61ms
step:873/1480 train_time:133438ms step_avg:154.62ms
step:874/1480 train_time:133604ms step_avg:154.63ms
step:875/1480 train_time:133769ms step_avg:154.65ms
step:875/1480 val_loss:3.5039 train_time:133834ms step_avg:154.72ms
step:876/1480 train_time:133936ms step_avg:154.66ms
step:877/1480 train_time:134103ms step_avg:154.67ms
step:878/1480 train_time:134266ms step_avg:154.68ms
step:879/1480 train_time:134429ms step_avg:154.69ms
step:880/1480 train_time:134592ms step_avg:154.70ms
step:881/1480 train_time:134754ms step_avg:154.71ms
step:882/1480 train_time:134919ms step_avg:154.72ms
step:883/1480 train_time:135086ms step_avg:154.74ms
step:884/1480 train_time:135252ms step_avg:154.75ms
step:885/1480 train_time:135416ms step_avg:154.76ms
step:886/1480 train_time:135584ms step_avg:154.78ms
step:887/1480 train_time:135751ms step_avg:154.79ms
step:888/1480 train_time:135925ms step_avg:154.81ms
step:889/1480 train_time:136091ms step_avg:154.83ms
step:890/1480 train_time:136255ms step_avg:154.84ms
step:891/1480 train_time:136422ms step_avg:154.85ms
step:892/1480 train_time:136588ms step_avg:154.86ms
step:893/1480 train_time:136750ms step_avg:154.87ms
step:894/1480 train_time:136917ms step_avg:154.88ms
step:895/1480 train_time:137083ms step_avg:154.90ms
step:896/1480 train_time:137248ms step_avg:154.91ms
step:897/1480 train_time:137415ms step_avg:154.92ms
step:898/1480 train_time:137584ms step_avg:154.94ms
step:899/1480 train_time:137748ms step_avg:154.95ms
step:900/1480 train_time:137911ms step_avg:154.96ms
step:901/1480 train_time:138078ms step_avg:154.97ms
step:902/1480 train_time:138243ms step_avg:154.98ms
step:903/1480 train_time:138415ms step_avg:155.00ms
step:904/1480 train_time:138582ms step_avg:155.01ms
step:905/1480 train_time:138745ms step_avg:155.02ms
step:906/1480 train_time:138911ms step_avg:155.03ms
step:907/1480 train_time:139081ms step_avg:155.05ms
step:908/1480 train_time:139244ms step_avg:155.06ms
step:909/1480 train_time:139409ms step_avg:155.07ms
step:910/1480 train_time:139581ms step_avg:155.09ms
step:911/1480 train_time:139747ms step_avg:155.10ms
step:912/1480 train_time:139915ms step_avg:155.12ms
step:913/1480 train_time:140083ms step_avg:155.13ms
step:914/1480 train_time:140250ms step_avg:155.14ms
step:915/1480 train_time:140422ms step_avg:155.16ms
step:916/1480 train_time:140586ms step_avg:155.17ms
step:917/1480 train_time:140750ms step_avg:155.18ms
step:918/1480 train_time:140918ms step_avg:155.20ms
step:919/1480 train_time:141088ms step_avg:155.21ms
step:920/1480 train_time:141252ms step_avg:155.22ms
step:921/1480 train_time:141419ms step_avg:155.23ms
step:922/1480 train_time:141586ms step_avg:155.25ms
step:923/1480 train_time:141748ms step_avg:155.26ms
step:924/1480 train_time:141913ms step_avg:155.27ms
step:925/1480 train_time:142081ms step_avg:155.28ms
step:926/1480 train_time:142245ms step_avg:155.29ms
step:927/1480 train_time:142408ms step_avg:155.30ms
step:928/1480 train_time:142573ms step_avg:155.31ms
step:929/1480 train_time:142739ms step_avg:155.32ms
step:930/1480 train_time:142906ms step_avg:155.33ms
step:931/1480 train_time:143069ms step_avg:155.34ms
step:932/1480 train_time:143235ms step_avg:155.35ms
step:933/1480 train_time:143404ms step_avg:155.37ms
step:934/1480 train_time:143570ms step_avg:155.38ms
step:935/1480 train_time:143739ms step_avg:155.39ms
step:936/1480 train_time:143907ms step_avg:155.41ms
step:937/1480 train_time:144077ms step_avg:155.42ms
step:938/1480 train_time:144241ms step_avg:155.43ms
step:939/1480 train_time:144410ms step_avg:155.45ms
step:940/1480 train_time:144577ms step_avg:155.46ms
step:941/1480 train_time:144742ms step_avg:155.47ms
step:942/1480 train_time:144907ms step_avg:155.48ms
step:943/1480 train_time:145077ms step_avg:155.50ms
step:944/1480 train_time:145250ms step_avg:155.51ms
step:945/1480 train_time:145413ms step_avg:155.52ms
step:946/1480 train_time:145585ms step_avg:155.54ms
step:947/1480 train_time:145752ms step_avg:155.55ms
step:948/1480 train_time:145917ms step_avg:155.56ms
step:949/1480 train_time:146084ms step_avg:155.57ms
step:950/1480 train_time:146248ms step_avg:155.58ms
step:951/1480 train_time:146419ms step_avg:155.60ms
step:952/1480 train_time:146585ms step_avg:155.61ms
step:953/1480 train_time:146754ms step_avg:155.62ms
step:954/1480 train_time:146923ms step_avg:155.64ms
step:955/1480 train_time:147086ms step_avg:155.65ms
step:956/1480 train_time:147249ms step_avg:155.65ms
step:957/1480 train_time:147418ms step_avg:155.67ms
step:958/1480 train_time:147588ms step_avg:155.68ms
step:959/1480 train_time:147752ms step_avg:155.69ms
step:960/1480 train_time:147920ms step_avg:155.71ms
step:961/1480 train_time:148086ms step_avg:155.72ms
step:962/1480 train_time:148250ms step_avg:155.72ms
step:963/1480 train_time:148413ms step_avg:155.73ms
step:964/1480 train_time:148582ms step_avg:155.75ms
step:965/1480 train_time:148746ms step_avg:155.76ms
step:966/1480 train_time:148910ms step_avg:155.76ms
step:967/1480 train_time:149074ms step_avg:155.77ms
step:968/1480 train_time:149240ms step_avg:155.78ms
step:969/1480 train_time:149406ms step_avg:155.79ms
step:970/1480 train_time:149569ms step_avg:155.80ms
step:971/1480 train_time:149734ms step_avg:155.81ms
step:972/1480 train_time:149900ms step_avg:155.82ms
step:973/1480 train_time:150065ms step_avg:155.83ms
step:974/1480 train_time:150232ms step_avg:155.84ms
step:975/1480 train_time:150397ms step_avg:155.85ms
step:976/1480 train_time:150564ms step_avg:155.86ms
step:977/1480 train_time:150727ms step_avg:155.87ms
step:978/1480 train_time:150892ms step_avg:155.88ms
step:979/1480 train_time:151059ms step_avg:155.89ms
step:980/1480 train_time:151225ms step_avg:155.90ms
step:981/1480 train_time:151394ms step_avg:155.92ms
step:982/1480 train_time:151558ms step_avg:155.92ms
step:983/1480 train_time:151723ms step_avg:155.93ms
step:984/1480 train_time:151888ms step_avg:155.94ms
step:985/1480 train_time:152055ms step_avg:155.95ms
step:986/1480 train_time:152221ms step_avg:155.96ms
step:987/1480 train_time:152385ms step_avg:155.97ms
step:988/1480 train_time:152553ms step_avg:155.98ms
step:989/1480 train_time:152718ms step_avg:155.99ms
step:990/1480 train_time:152888ms step_avg:156.01ms
step:991/1480 train_time:153054ms step_avg:156.02ms
step:992/1480 train_time:153229ms step_avg:156.04ms
step:993/1480 train_time:153405ms step_avg:156.06ms
step:994/1480 train_time:153570ms step_avg:156.07ms
step:995/1480 train_time:153735ms step_avg:156.08ms
step:996/1480 train_time:153898ms step_avg:156.08ms
step:997/1480 train_time:154063ms step_avg:156.09ms
step:998/1480 train_time:154227ms step_avg:156.10ms
step:999/1480 train_time:154394ms step_avg:156.11ms
step:1000/1480 train_time:154564ms step_avg:156.13ms
step:1000/1480 val_loss:3.4417 train_time:154631ms step_avg:156.19ms
step:1001/1480 train_time:154734ms step_avg:156.14ms
step:1002/1480 train_time:154901ms step_avg:156.15ms
step:1003/1480 train_time:155071ms step_avg:156.16ms
step:1004/1480 train_time:155241ms step_avg:156.18ms
step:1005/1480 train_time:155409ms step_avg:156.19ms
step:1006/1480 train_time:155576ms step_avg:156.20ms
step:1007/1480 train_time:155741ms step_avg:156.21ms
step:1008/1480 train_time:155908ms step_avg:156.22ms
step:1009/1480 train_time:156083ms step_avg:156.24ms
step:1010/1480 train_time:156248ms step_avg:156.25ms
step:1011/1480 train_time:156415ms step_avg:156.26ms
step:1012/1480 train_time:156581ms step_avg:156.27ms
step:1013/1480 train_time:156751ms step_avg:156.28ms
step:1014/1480 train_time:156917ms step_avg:156.29ms
step:1015/1480 train_time:157087ms step_avg:156.31ms
step:1016/1480 train_time:157257ms step_avg:156.32ms
step:1017/1480 train_time:157429ms step_avg:156.33ms
step:1018/1480 train_time:157599ms step_avg:156.35ms
step:1019/1480 train_time:157767ms step_avg:156.36ms
step:1020/1480 train_time:157935ms step_avg:156.37ms
step:1021/1480 train_time:158101ms step_avg:156.38ms
step:1022/1480 train_time:158268ms step_avg:156.39ms
step:1023/1480 train_time:158437ms step_avg:156.40ms
step:1024/1480 train_time:158603ms step_avg:156.41ms
step:1025/1480 train_time:158771ms step_avg:156.43ms
step:1026/1480 train_time:158938ms step_avg:156.44ms
step:1027/1480 train_time:159105ms step_avg:156.45ms
step:1028/1480 train_time:159278ms step_avg:156.46ms
step:1029/1480 train_time:159455ms step_avg:156.48ms
step:1030/1480 train_time:159622ms step_avg:156.49ms
step:1031/1480 train_time:159786ms step_avg:156.50ms
step:1032/1480 train_time:159961ms step_avg:156.52ms
step:1033/1480 train_time:160127ms step_avg:156.53ms
step:1034/1480 train_time:160295ms step_avg:156.54ms
step:1035/1480 train_time:160463ms step_avg:156.55ms
step:1036/1480 train_time:160628ms step_avg:156.56ms
step:1037/1480 train_time:160799ms step_avg:156.57ms
step:1038/1480 train_time:160966ms step_avg:156.58ms
step:1039/1480 train_time:161139ms step_avg:156.60ms
step:1040/1480 train_time:161305ms step_avg:156.61ms
step:1041/1480 train_time:161471ms step_avg:156.62ms
step:1042/1480 train_time:161635ms step_avg:156.62ms
step:1043/1480 train_time:161802ms step_avg:156.63ms
step:1044/1480 train_time:161966ms step_avg:156.64ms
step:1045/1480 train_time:162135ms step_avg:156.65ms
step:1046/1480 train_time:162304ms step_avg:156.66ms
step:1047/1480 train_time:162469ms step_avg:156.67ms
step:1048/1480 train_time:162635ms step_avg:156.68ms
step:1049/1480 train_time:162801ms step_avg:156.69ms
step:1050/1480 train_time:162969ms step_avg:156.70ms
step:1051/1480 train_time:163141ms step_avg:156.72ms
step:1052/1480 train_time:163309ms step_avg:156.73ms
step:1053/1480 train_time:163476ms step_avg:156.74ms
step:1054/1480 train_time:163643ms step_avg:156.75ms
step:1055/1480 train_time:163808ms step_avg:156.75ms
step:1056/1480 train_time:163973ms step_avg:156.76ms
step:1057/1480 train_time:164141ms step_avg:156.77ms
step:1058/1480 train_time:164310ms step_avg:156.78ms
step:1059/1480 train_time:164483ms step_avg:156.80ms
step:1060/1480 train_time:164652ms step_avg:156.81ms
step:1061/1480 train_time:164816ms step_avg:156.82ms
step:1062/1480 train_time:164983ms step_avg:156.83ms
step:1063/1480 train_time:165148ms step_avg:156.84ms
step:1064/1480 train_time:165311ms step_avg:156.84ms
step:1065/1480 train_time:165480ms step_avg:156.85ms
step:1066/1480 train_time:165647ms step_avg:156.86ms
step:1067/1480 train_time:165817ms step_avg:156.87ms
step:1068/1480 train_time:165983ms step_avg:156.88ms
step:1069/1480 train_time:166155ms step_avg:156.90ms
step:1070/1480 train_time:166322ms step_avg:156.91ms
step:1071/1480 train_time:166493ms step_avg:156.92ms
step:1072/1480 train_time:166660ms step_avg:156.93ms
step:1073/1480 train_time:166823ms step_avg:156.94ms
step:1074/1480 train_time:166989ms step_avg:156.94ms
step:1075/1480 train_time:167159ms step_avg:156.96ms
step:1076/1480 train_time:167325ms step_avg:156.97ms
step:1077/1480 train_time:167489ms step_avg:156.97ms
step:1078/1480 train_time:167665ms step_avg:156.99ms
step:1079/1480 train_time:167838ms step_avg:157.00ms
step:1080/1480 train_time:168008ms step_avg:157.02ms
step:1081/1480 train_time:168174ms step_avg:157.03ms
step:1082/1480 train_time:168341ms step_avg:157.03ms
step:1083/1480 train_time:168508ms step_avg:157.04ms
step:1084/1480 train_time:168675ms step_avg:157.05ms
step:1085/1480 train_time:168843ms step_avg:157.06ms
step:1086/1480 train_time:169010ms step_avg:157.07ms
step:1087/1480 train_time:169177ms step_avg:157.08ms
step:1088/1480 train_time:169347ms step_avg:157.09ms
step:1089/1480 train_time:169521ms step_avg:157.11ms
step:1090/1480 train_time:169691ms step_avg:157.12ms
step:1091/1480 train_time:169859ms step_avg:157.13ms
step:1092/1480 train_time:170027ms step_avg:157.14ms
step:1093/1480 train_time:170196ms step_avg:157.15ms
step:1094/1480 train_time:170362ms step_avg:157.16ms
step:1095/1480 train_time:170527ms step_avg:157.17ms
step:1096/1480 train_time:170697ms step_avg:157.18ms
step:1097/1480 train_time:170863ms step_avg:157.19ms
step:1098/1480 train_time:171034ms step_avg:157.20ms
step:1099/1480 train_time:171205ms step_avg:157.21ms
step:1100/1480 train_time:171377ms step_avg:157.23ms
step:1101/1480 train_time:171547ms step_avg:157.24ms
step:1102/1480 train_time:171719ms step_avg:157.25ms
step:1103/1480 train_time:171893ms step_avg:157.27ms
step:1104/1480 train_time:172061ms step_avg:157.28ms
step:1105/1480 train_time:172230ms step_avg:157.29ms
step:1106/1480 train_time:172398ms step_avg:157.30ms
step:1107/1480 train_time:172567ms step_avg:157.31ms
step:1108/1480 train_time:172732ms step_avg:157.31ms
step:1109/1480 train_time:172899ms step_avg:157.32ms
step:1110/1480 train_time:173064ms step_avg:157.33ms
step:1111/1480 train_time:173232ms step_avg:157.34ms
step:1112/1480 train_time:173403ms step_avg:157.35ms
step:1113/1480 train_time:173580ms step_avg:157.37ms
step:1114/1480 train_time:173752ms step_avg:157.38ms
step:1115/1480 train_time:173924ms step_avg:157.40ms
step:1116/1480 train_time:174091ms step_avg:157.41ms
step:1117/1480 train_time:174264ms step_avg:157.42ms
step:1118/1480 train_time:174439ms step_avg:157.44ms
step:1119/1480 train_time:174605ms step_avg:157.44ms
step:1120/1480 train_time:174773ms step_avg:157.45ms
step:1121/1480 train_time:174943ms step_avg:157.46ms
step:1122/1480 train_time:175110ms step_avg:157.47ms
step:1123/1480 train_time:175276ms step_avg:157.48ms
step:1124/1480 train_time:175445ms step_avg:157.49ms
step:1125/1480 train_time:175612ms step_avg:157.50ms
step:1125/1480 val_loss:3.3852 train_time:175680ms step_avg:157.56ms
step:1126/1480 train_time:175783ms step_avg:157.51ms
step:1127/1480 train_time:175953ms step_avg:157.52ms
step:1128/1480 train_time:176125ms step_avg:157.54ms
step:1129/1480 train_time:176298ms step_avg:157.55ms
step:1130/1480 train_time:176468ms step_avg:157.56ms
step:1131/1480 train_time:176647ms step_avg:157.58ms
step:1132/1480 train_time:176812ms step_avg:157.59ms
step:1133/1480 train_time:176987ms step_avg:157.60ms
step:1134/1480 train_time:177157ms step_avg:157.61ms
step:1135/1480 train_time:177326ms step_avg:157.62ms
step:1136/1480 train_time:177495ms step_avg:157.63ms
step:1137/1480 train_time:177665ms step_avg:157.64ms
step:1138/1480 train_time:177835ms step_avg:157.66ms
step:1139/1480 train_time:178005ms step_avg:157.67ms
step:1140/1480 train_time:178173ms step_avg:157.68ms
step:1141/1480 train_time:178347ms step_avg:157.69ms
step:1142/1480 train_time:178515ms step_avg:157.70ms
step:1143/1480 train_time:178686ms step_avg:157.71ms
step:1144/1480 train_time:178853ms step_avg:157.72ms
step:1145/1480 train_time:179019ms step_avg:157.73ms
step:1146/1480 train_time:179188ms step_avg:157.74ms
step:1147/1480 train_time:179356ms step_avg:157.74ms
step:1148/1480 train_time:179526ms step_avg:157.76ms
step:1149/1480 train_time:179694ms step_avg:157.76ms
step:1150/1480 train_time:179863ms step_avg:157.77ms
step:1151/1480 train_time:180035ms step_avg:157.79ms
step:1152/1480 train_time:180208ms step_avg:157.80ms
step:1153/1480 train_time:180383ms step_avg:157.82ms
step:1154/1480 train_time:180549ms step_avg:157.82ms
step:1155/1480 train_time:180721ms step_avg:157.83ms
step:1156/1480 train_time:180900ms step_avg:157.85ms
step:1157/1480 train_time:181069ms step_avg:157.86ms
step:1158/1480 train_time:181235ms step_avg:157.87ms
step:1159/1480 train_time:181403ms step_avg:157.88ms
step:1160/1480 train_time:181569ms step_avg:157.89ms
step:1161/1480 train_time:181739ms step_avg:157.90ms
step:1162/1480 train_time:181909ms step_avg:157.91ms
step:1163/1480 train_time:182077ms step_avg:157.92ms
step:1164/1480 train_time:182247ms step_avg:157.93ms
step:1165/1480 train_time:182412ms step_avg:157.93ms
step:1166/1480 train_time:182585ms step_avg:157.95ms
step:1167/1480 train_time:182753ms step_avg:157.95ms
step:1168/1480 train_time:182922ms step_avg:157.96ms
step:1169/1480 train_time:183090ms step_avg:157.97ms
step:1170/1480 train_time:183259ms step_avg:157.98ms
step:1171/1480 train_time:183427ms step_avg:157.99ms
step:1172/1480 train_time:183593ms step_avg:158.00ms
step:1173/1480 train_time:183765ms step_avg:158.01ms
step:1174/1480 train_time:183947ms step_avg:158.03ms
step:1175/1480 train_time:184118ms step_avg:158.04ms
step:1176/1480 train_time:184289ms step_avg:158.05ms
step:1177/1480 train_time:184467ms step_avg:158.07ms
step:1178/1480 train_time:184634ms step_avg:158.08ms
step:1179/1480 train_time:184800ms step_avg:158.08ms
step:1180/1480 train_time:184978ms step_avg:158.10ms
step:1181/1480 train_time:185149ms step_avg:158.11ms
step:1182/1480 train_time:185316ms step_avg:158.12ms
step:1183/1480 train_time:185487ms step_avg:158.13ms
step:1184/1480 train_time:185655ms step_avg:158.14ms
step:1185/1480 train_time:185829ms step_avg:158.15ms
step:1186/1480 train_time:185999ms step_avg:158.16ms
step:1187/1480 train_time:186183ms step_avg:158.18ms
step:1188/1480 train_time:186350ms step_avg:158.19ms
step:1189/1480 train_time:186520ms step_avg:158.20ms
step:1190/1480 train_time:186688ms step_avg:158.21ms
step:1191/1480 train_time:186859ms step_avg:158.22ms
step:1192/1480 train_time:187026ms step_avg:158.23ms
step:1193/1480 train_time:187192ms step_avg:158.24ms
step:1194/1480 train_time:187362ms step_avg:158.24ms
step:1195/1480 train_time:187536ms step_avg:158.26ms
step:1196/1480 train_time:187718ms step_avg:158.28ms
step:1197/1480 train_time:187890ms step_avg:158.29ms
step:1198/1480 train_time:188072ms step_avg:158.31ms
step:1199/1480 train_time:188242ms step_avg:158.32ms
step:1200/1480 train_time:188409ms step_avg:158.33ms
step:1201/1480 train_time:188576ms step_avg:158.33ms
step:1202/1480 train_time:188758ms step_avg:158.35ms
step:1203/1480 train_time:188933ms step_avg:158.37ms
step:1204/1480 train_time:189108ms step_avg:158.38ms
step:1205/1480 train_time:189276ms step_avg:158.39ms
step:1206/1480 train_time:189446ms step_avg:158.40ms
step:1207/1480 train_time:189614ms step_avg:158.41ms
step:1208/1480 train_time:189783ms step_avg:158.42ms
step:1209/1480 train_time:189956ms step_avg:158.43ms
step:1210/1480 train_time:190131ms step_avg:158.44ms
step:1211/1480 train_time:190306ms step_avg:158.46ms
step:1212/1480 train_time:190477ms step_avg:158.47ms
step:1213/1480 train_time:190650ms step_avg:158.48ms
step:1214/1480 train_time:190827ms step_avg:158.49ms
step:1215/1480 train_time:191000ms step_avg:158.51ms
step:1216/1480 train_time:191170ms step_avg:158.52ms
step:1217/1480 train_time:191347ms step_avg:158.53ms
step:1218/1480 train_time:191517ms step_avg:158.54ms
step:1219/1480 train_time:191695ms step_avg:158.56ms
step:1220/1480 train_time:191866ms step_avg:158.57ms
step:1221/1480 train_time:192034ms step_avg:158.58ms
step:1222/1480 train_time:192202ms step_avg:158.58ms
step:1223/1480 train_time:192371ms step_avg:158.59ms
step:1224/1480 train_time:192551ms step_avg:158.61ms
step:1225/1480 train_time:192722ms step_avg:158.62ms
step:1226/1480 train_time:192894ms step_avg:158.63ms
step:1227/1480 train_time:193066ms step_avg:158.64ms
step:1228/1480 train_time:193235ms step_avg:158.65ms
step:1229/1480 train_time:193408ms step_avg:158.66ms
step:1230/1480 train_time:193587ms step_avg:158.68ms
step:1231/1480 train_time:193762ms step_avg:158.69ms
step:1232/1480 train_time:193936ms step_avg:158.70ms
step:1233/1480 train_time:194106ms step_avg:158.71ms
step:1234/1480 train_time:194275ms step_avg:158.72ms
step:1235/1480 train_time:194450ms step_avg:158.73ms
step:1236/1480 train_time:194617ms step_avg:158.74ms
step:1237/1480 train_time:194787ms step_avg:158.75ms
step:1238/1480 train_time:194971ms step_avg:158.77ms
step:1239/1480 train_time:195143ms step_avg:158.78ms
step:1240/1480 train_time:195313ms step_avg:158.79ms
step:1241/1480 train_time:195486ms step_avg:158.80ms
step:1242/1480 train_time:195655ms step_avg:158.81ms
step:1243/1480 train_time:195829ms step_avg:158.82ms
step:1244/1480 train_time:195995ms step_avg:158.83ms
step:1245/1480 train_time:196165ms step_avg:158.84ms
step:1246/1480 train_time:196335ms step_avg:158.85ms
step:1247/1480 train_time:196506ms step_avg:158.86ms
step:1248/1480 train_time:196675ms step_avg:158.87ms
step:1249/1480 train_time:196845ms step_avg:158.87ms
step:1250/1480 train_time:197014ms step_avg:158.88ms
step:1250/1480 val_loss:3.3357 train_time:197085ms step_avg:158.94ms
step:1251/1480 train_time:197195ms step_avg:158.90ms
step:1252/1480 train_time:197367ms step_avg:158.91ms
step:1253/1480 train_time:197535ms step_avg:158.92ms
step:1254/1480 train_time:197705ms step_avg:158.93ms
step:1255/1480 train_time:197892ms step_avg:158.95ms
step:1256/1480 train_time:198066ms step_avg:158.96ms
step:1257/1480 train_time:198237ms step_avg:158.97ms
step:1258/1480 train_time:198411ms step_avg:158.98ms
step:1259/1480 train_time:198582ms step_avg:158.99ms
step:1260/1480 train_time:198749ms step_avg:159.00ms
step:1261/1480 train_time:198921ms step_avg:159.01ms
step:1262/1480 train_time:199098ms step_avg:159.02ms
step:1263/1480 train_time:199273ms step_avg:159.04ms
step:1264/1480 train_time:199439ms step_avg:159.04ms
step:1265/1480 train_time:199606ms step_avg:159.05ms
step:1266/1480 train_time:199777ms step_avg:159.06ms
step:1267/1480 train_time:199947ms step_avg:159.07ms
step:1268/1480 train_time:200118ms step_avg:159.08ms
step:1269/1480 train_time:200294ms step_avg:159.09ms
step:1270/1480 train_time:200464ms step_avg:159.10ms
step:1271/1480 train_time:200635ms step_avg:159.11ms
step:1272/1480 train_time:200800ms step_avg:159.11ms
step:1273/1480 train_time:200973ms step_avg:159.12ms
step:1274/1480 train_time:201143ms step_avg:159.13ms
step:1275/1480 train_time:201310ms step_avg:159.14ms
step:1276/1480 train_time:201477ms step_avg:159.14ms
step:1277/1480 train_time:201651ms step_avg:159.16ms
step:1278/1480 train_time:201819ms step_avg:159.16ms
step:1279/1480 train_time:201990ms step_avg:159.17ms
step:1280/1480 train_time:202170ms step_avg:159.19ms
step:1281/1480 train_time:202339ms step_avg:159.20ms
step:1282/1480 train_time:202504ms step_avg:159.20ms
step:1283/1480 train_time:202676ms step_avg:159.21ms
step:1284/1480 train_time:202847ms step_avg:159.22ms
step:1285/1480 train_time:203016ms step_avg:159.23ms
step:1286/1480 train_time:203188ms step_avg:159.24ms
step:1287/1480 train_time:203362ms step_avg:159.25ms
step:1288/1480 train_time:203535ms step_avg:159.26ms
step:1289/1480 train_time:203717ms step_avg:159.28ms
step:1290/1480 train_time:203896ms step_avg:159.29ms
step:1291/1480 train_time:204073ms step_avg:159.31ms
step:1292/1480 train_time:204246ms step_avg:159.32ms
step:1293/1480 train_time:204422ms step_avg:159.33ms
step:1294/1480 train_time:204593ms step_avg:159.34ms
step:1295/1480 train_time:204764ms step_avg:159.35ms
step:1296/1480 train_time:204937ms step_avg:159.36ms
step:1297/1480 train_time:205107ms step_avg:159.37ms
step:1298/1480 train_time:205280ms step_avg:159.38ms
step:1299/1480 train_time:205450ms step_avg:159.39ms
step:1300/1480 train_time:205618ms step_avg:159.39ms
step:1301/1480 train_time:205786ms step_avg:159.40ms
step:1302/1480 train_time:205960ms step_avg:159.41ms
step:1303/1480 train_time:206136ms step_avg:159.42ms
step:1304/1480 train_time:206310ms step_avg:159.44ms
step:1305/1480 train_time:206479ms step_avg:159.44ms
step:1306/1480 train_time:206655ms step_avg:159.46ms
step:1307/1480 train_time:206822ms step_avg:159.46ms
step:1308/1480 train_time:206993ms step_avg:159.47ms
step:1309/1480 train_time:207164ms step_avg:159.48ms
step:1310/1480 train_time:207334ms step_avg:159.49ms
step:1311/1480 train_time:207503ms step_avg:159.49ms
step:1312/1480 train_time:207676ms step_avg:159.51ms
step:1313/1480 train_time:207844ms step_avg:159.51ms
step:1314/1480 train_time:208018ms step_avg:159.52ms
step:1315/1480 train_time:208187ms step_avg:159.53ms
step:1316/1480 train_time:208356ms step_avg:159.54ms
step:1317/1480 train_time:208527ms step_avg:159.55ms
step:1318/1480 train_time:208706ms step_avg:159.56ms
step:1319/1480 train_time:208881ms step_avg:159.57ms
step:1320/1480 train_time:209059ms step_avg:159.59ms
step:1321/1480 train_time:209232ms step_avg:159.60ms
step:1322/1480 train_time:209412ms step_avg:159.61ms
step:1323/1480 train_time:209582ms step_avg:159.62ms
step:1324/1480 train_time:209758ms step_avg:159.63ms
step:1325/1480 train_time:209939ms step_avg:159.65ms
step:1326/1480 train_time:210114ms step_avg:159.66ms
step:1327/1480 train_time:210284ms step_avg:159.67ms
step:1328/1480 train_time:210457ms step_avg:159.68ms
step:1329/1480 train_time:210654ms step_avg:159.71ms
step:1330/1480 train_time:210836ms step_avg:159.72ms
step:1331/1480 train_time:211007ms step_avg:159.73ms
step:1332/1480 train_time:211180ms step_avg:159.74ms
step:1333/1480 train_time:211355ms step_avg:159.75ms
step:1334/1480 train_time:211525ms step_avg:159.76ms
step:1335/1480 train_time:211694ms step_avg:159.77ms
step:1336/1480 train_time:211877ms step_avg:159.79ms
step:1337/1480 train_time:212052ms step_avg:159.80ms
step:1338/1480 train_time:212223ms step_avg:159.81ms
step:1339/1480 train_time:212397ms step_avg:159.82ms
step:1340/1480 train_time:212569ms step_avg:159.83ms
step:1341/1480 train_time:212736ms step_avg:159.83ms
step:1342/1480 train_time:212909ms step_avg:159.84ms
step:1343/1480 train_time:213079ms step_avg:159.85ms
step:1344/1480 train_time:213251ms step_avg:159.86ms
step:1345/1480 train_time:213427ms step_avg:159.87ms
step:1346/1480 train_time:213596ms step_avg:159.88ms
step:1347/1480 train_time:213766ms step_avg:159.88ms
step:1348/1480 train_time:213937ms step_avg:159.89ms
step:1349/1480 train_time:214106ms step_avg:159.90ms
step:1350/1480 train_time:214280ms step_avg:159.91ms
step:1351/1480 train_time:214451ms step_avg:159.92ms
step:1352/1480 train_time:214622ms step_avg:159.93ms
step:1353/1480 train_time:214799ms step_avg:159.94ms
step:1354/1480 train_time:214971ms step_avg:159.95ms
step:1355/1480 train_time:215138ms step_avg:159.95ms
step:1356/1480 train_time:215312ms step_avg:159.96ms
step:1357/1480 train_time:215485ms step_avg:159.97ms
step:1358/1480 train_time:215657ms step_avg:159.98ms
step:1359/1480 train_time:215830ms step_avg:159.99ms
step:1360/1480 train_time:216002ms step_avg:160.00ms
step:1361/1480 train_time:216180ms step_avg:160.01ms
step:1362/1480 train_time:216356ms step_avg:160.03ms
step:1363/1480 train_time:216535ms step_avg:160.04ms
step:1364/1480 train_time:216703ms step_avg:160.05ms
step:1365/1480 train_time:216871ms step_avg:160.05ms
step:1366/1480 train_time:217042ms step_avg:160.06ms
step:1367/1480 train_time:217214ms step_avg:160.07ms
step:1368/1480 train_time:217386ms step_avg:160.08ms
step:1369/1480 train_time:217567ms step_avg:160.09ms
step:1370/1480 train_time:217744ms step_avg:160.11ms
step:1371/1480 train_time:217916ms step_avg:160.11ms
step:1372/1480 train_time:218095ms step_avg:160.13ms
step:1373/1480 train_time:218264ms step_avg:160.14ms
step:1374/1480 train_time:218441ms step_avg:160.15ms
step:1375/1480 train_time:218611ms step_avg:160.15ms
step:1375/1480 val_loss:3.2976 train_time:218679ms step_avg:160.20ms
step:1376/1480 train_time:218787ms step_avg:160.17ms
step:1377/1480 train_time:218958ms step_avg:160.17ms
step:1378/1480 train_time:219127ms step_avg:160.18ms
step:1379/1480 train_time:219303ms step_avg:160.19ms
step:1380/1480 train_time:219477ms step_avg:160.20ms
step:1381/1480 train_time:219660ms step_avg:160.22ms
step:1382/1480 train_time:219832ms step_avg:160.23ms
step:1383/1480 train_time:220005ms step_avg:160.24ms
step:1384/1480 train_time:220183ms step_avg:160.25ms
step:1385/1480 train_time:220348ms step_avg:160.25ms
step:1386/1480 train_time:220518ms step_avg:160.26ms
step:1387/1480 train_time:220689ms step_avg:160.27ms
step:1388/1480 train_time:220858ms step_avg:160.27ms
step:1389/1480 train_time:221031ms step_avg:160.28ms
step:1390/1480 train_time:221199ms step_avg:160.29ms
step:1391/1480 train_time:221369ms step_avg:160.30ms
step:1392/1480 train_time:221542ms step_avg:160.31ms
step:1393/1480 train_time:221713ms step_avg:160.31ms
step:1394/1480 train_time:221883ms step_avg:160.32ms
step:1395/1480 train_time:222052ms step_avg:160.33ms
step:1396/1480 train_time:222221ms step_avg:160.33ms
step:1397/1480 train_time:222389ms step_avg:160.34ms
step:1398/1480 train_time:222556ms step_avg:160.34ms
step:1399/1480 train_time:222725ms step_avg:160.35ms
step:1400/1480 train_time:222903ms step_avg:160.36ms
step:1401/1480 train_time:223069ms step_avg:160.37ms
step:1402/1480 train_time:223240ms step_avg:160.37ms
step:1403/1480 train_time:223417ms step_avg:160.39ms
step:1404/1480 train_time:223587ms step_avg:160.39ms
step:1405/1480 train_time:223763ms step_avg:160.40ms
step:1406/1480 train_time:223936ms step_avg:160.41ms
step:1407/1480 train_time:224104ms step_avg:160.42ms
step:1408/1480 train_time:224272ms step_avg:160.42ms
step:1409/1480 train_time:224454ms step_avg:160.44ms
step:1410/1480 train_time:224623ms step_avg:160.44ms
step:1411/1480 train_time:224790ms step_avg:160.45ms
step:1412/1480 train_time:224960ms step_avg:160.46ms
step:1413/1480 train_time:225129ms step_avg:160.46ms
step:1414/1480 train_time:225303ms step_avg:160.47ms
step:1415/1480 train_time:225476ms step_avg:160.48ms
step:1416/1480 train_time:225663ms step_avg:160.50ms
step:1417/1480 train_time:225838ms step_avg:160.51ms
step:1418/1480 train_time:226008ms step_avg:160.52ms
step:1419/1480 train_time:226185ms step_avg:160.53ms
step:1420/1480 train_time:226359ms step_avg:160.54ms
step:1421/1480 train_time:226531ms step_avg:160.55ms
step:1422/1480 train_time:226704ms step_avg:160.56ms
step:1423/1480 train_time:226873ms step_avg:160.56ms
step:1424/1480 train_time:227049ms step_avg:160.57ms
step:1425/1480 train_time:227229ms step_avg:160.59ms
step:1426/1480 train_time:227401ms step_avg:160.59ms
step:1427/1480 train_time:227576ms step_avg:160.60ms
step:1428/1480 train_time:227747ms step_avg:160.61ms
step:1429/1480 train_time:227916ms step_avg:160.62ms
step:1430/1480 train_time:228090ms step_avg:160.63ms
step:1431/1480 train_time:228266ms step_avg:160.64ms
step:1432/1480 train_time:228443ms step_avg:160.65ms
step:1433/1480 train_time:228622ms step_avg:160.66ms
step:1434/1480 train_time:228802ms step_avg:160.68ms
step:1435/1480 train_time:228977ms step_avg:160.69ms
step:1436/1480 train_time:229150ms step_avg:160.69ms
step:1437/1480 train_time:229320ms step_avg:160.70ms
step:1438/1480 train_time:229488ms step_avg:160.71ms
step:1439/1480 train_time:229662ms step_avg:160.71ms
step:1440/1480 train_time:229830ms step_avg:160.72ms
step:1441/1480 train_time:230002ms step_avg:160.73ms
step:1442/1480 train_time:230178ms step_avg:160.74ms
step:1443/1480 train_time:230368ms step_avg:160.76ms
step:1444/1480 train_time:230540ms step_avg:160.77ms
step:1445/1480 train_time:230712ms step_avg:160.77ms
step:1446/1480 train_time:230889ms step_avg:160.79ms
step:1447/1480 train_time:231066ms step_avg:160.80ms
step:1448/1480 train_time:231236ms step_avg:160.80ms
step:1449/1480 train_time:231411ms step_avg:160.81ms
step:1450/1480 train_time:231586ms step_avg:160.82ms
step:1451/1480 train_time:231755ms step_avg:160.83ms
step:1452/1480 train_time:231928ms step_avg:160.84ms
step:1453/1480 train_time:232097ms step_avg:160.84ms
step:1454/1480 train_time:232269ms step_avg:160.85ms
step:1455/1480 train_time:232448ms step_avg:160.86ms
step:1456/1480 train_time:232621ms step_avg:160.87ms
step:1457/1480 train_time:232791ms step_avg:160.88ms
step:1458/1480 train_time:232964ms step_avg:160.89ms
step:1459/1480 train_time:233139ms step_avg:160.90ms
step:1460/1480 train_time:233309ms step_avg:160.90ms
step:1461/1480 train_time:233484ms step_avg:160.91ms
step:1462/1480 train_time:233654ms step_avg:160.92ms
step:1463/1480 train_time:233830ms step_avg:160.93ms
step:1464/1480 train_time:234007ms step_avg:160.94ms
step:1465/1480 train_time:234180ms step_avg:160.95ms
step:1466/1480 train_time:234351ms step_avg:160.96ms
step:1467/1480 train_time:234524ms step_avg:160.96ms
step:1468/1480 train_time:234694ms step_avg:160.97ms
step:1469/1480 train_time:234868ms step_avg:160.98ms
step:1470/1480 train_time:235048ms step_avg:160.99ms
step:1471/1480 train_time:235233ms step_avg:161.01ms
step:1472/1480 train_time:235412ms step_avg:161.02ms
step:1473/1480 train_time:235584ms step_avg:161.03ms
step:1474/1480 train_time:235760ms step_avg:161.04ms
step:1475/1480 train_time:235940ms step_avg:161.05ms
step:1476/1480 train_time:236112ms step_avg:161.06ms
step:1477/1480 train_time:236295ms step_avg:161.07ms
step:1478/1480 train_time:236481ms step_avg:161.09ms
step:1479/1480 train_time:236652ms step_avg:161.10ms
step:1480/1480 train_time:236823ms step_avg:161.10ms
step:1480/1480 val_loss:3.2786 train_time:236895ms step_avg:161.15ms