====================================================================================================
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 glob
import time
from dataclasses import dataclass

import numpy as np
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

# -----------------------------------------------------------------------------
# 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}' \sim 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 = A @ X
        X = a * X + b * B + c * A @ B
    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=3e-4, momentum=0.95, nesterov=True,
                 backend='newtonschulz5', backend_steps=5,
                 rank=0, world_size=1):
        defaults = dict(lr=lr, momentum=momentum, nesterov=nesterov, backend=backend, backend_steps=backend_steps)
        super().__init__(params, defaults)
        self.rank = rank
        self.world_size = world_size

    def step(self):

        for group in self.param_groups:

            lr = group['lr']
            momentum = group['momentum']
            zeropower_backend = zeropower_backends[group['backend']]

            # generate weight updates in distributed fashion
            total_params = sum(p.numel() for p in group['params'])
            updates_flat = torch.zeros(total_params, device='cuda', dtype=torch.bfloat16)
            curr_idx = 0
            for i, p in enumerate(group['params']):
                # luckily this will perfectly distribute a transformer with multiple of 4 layers to 8 GPUs
                if i % self.world_size == self.rank:
                    g = p.grad
                    if g is None:
                        continue
                    state = self.state[p]
                    if 'momentum_buffer' not in state:
                        state['momentum_buffer'] = torch.zeros_like(g)
                    buf = state['momentum_buffer']
                    buf.mul_(momentum).add_(g)
                    if group['nesterov']:
                        g = g.add(buf, alpha=momentum)
                    g = zeropower_backend(g, steps=group['backend_steps'])
                    g *= max(g.size(0), g.size(1))**0.5 # scale to have update.square().mean() == 1
                    updates_flat[curr_idx:curr_idx+p.numel()] = g.flatten()
                curr_idx += p.numel()

            # sync updates across devices. we are not memory-constrained so can do this simple deserialization
            dist.all_reduce(updates_flat, op=dist.ReduceOp.SUM)

            # deserialize and apply updates
            curr_idx = 0
            for p in group['params']:
                g = updates_flat[curr_idx:curr_idx+p.numel()].view_as(p.data).type_as(p.data)
                p.data.add_(g, alpha=-lr)
                curr_idx += p.numel()

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

class Rotary(torch.nn.Module):

    def __init__(self, dim, base=10000):
        super().__init__()
        self.inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / 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:
            self.seq_len_cached = seq_len
            t = torch.arange(seq_len, device=x.device).type_as(self.inv_freq)
            freqs = torch.outer(t, self.inv_freq).to(x.device)
            self.cos_cached = freqs.cos().bfloat16()
            self.sin_cached = freqs.sin().bfloat16()
        return self.cos_cached[None, :, None, :], self.sin_cached[None, :, None, :]

def apply_rotary_emb(x, cos, sin):
    assert x.ndim == 4 # multihead attention
    d = x.shape[3]//2
    x1 = x[..., :d]
    x2 = x[..., d:]
    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, config):
        super().__init__()
        self.n_head = config.n_head
        self.n_embd = config.n_embd
        self.head_dim = self.n_embd // self.n_head
        assert self.n_embd % self.n_head == 0
        self.c_q = nn.Linear(self.n_embd, self.n_embd, bias=False)
        self.c_k = nn.Linear(self.n_embd, self.n_embd, bias=False)
        self.c_v = nn.Linear(self.n_embd, self.n_embd, bias=False)
        # output projection
        self.c_proj = nn.Linear(self.n_embd, self.n_embd, bias=False)
        self.c_proj.weight.data.zero_() # zero init suggested by @Grad62304977
        self.rotary = Rotary(self.head_dim)

    def forward(self, x):
        B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
        q = self.c_q(x).view(B, T, self.n_head, self.head_dim)
        k = self.c_k(x).view(B, T, self.n_head, self.head_dim)
        v = self.c_v(x).view(B, T, self.n_head, self.head_dim)
        cos, sin = self.rotary(q)
        q, k = F.rms_norm(q, (q.size(-1),)), F.rms_norm(k, (k.size(-1),)) # QK norm suggested by @Grad62304977
        q, k = apply_rotary_emb(q, cos, sin), apply_rotary_emb(k, cos, sin)
        y = F.scaled_dot_product_attention(q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2), is_causal=True)
        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, config):
        super().__init__()
        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd, bias=False)
        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd, bias=False)
        self.c_proj.weight.data.zero_() # zero init suggested by @Grad62304977

    def forward(self, x):
        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)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(F.rms_norm(x, (x.size(-1),)))
        x = x + self.mlp(F.rms_norm(x, (x.size(-1),)))
        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

class GPT(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.config = config

        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.n_embd),
            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.transformer.wte.weight = self.lm_head.weight # https://paperswithcode.com/method/weight-tying

    def forward(self, idx, targets=None, return_logits=True):

        # forward the GPT model itself
        x = self.transformer.wte(idx) # token embeddings of shape (b, t, n_embd)
        for block in self.transformer.h:
            x = block(x)
        x = F.rms_norm(x, (x.size(-1),))

        if targets is not None:
            # if we are given some desired targets also calculate the loss
            logits = self.lm_head(x)
            logits = logits.float() # use tf32/fp32 for logits
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
        else:
            # inference-time mini-optimization: only forward the lm_head on the very last position
            logits = self.lm_head(x[:, [-1], :]) # note: using list [-1] to preserve the time dim
            logits = logits.float() # use tf32/fp32 for logits
            loss = None

        # there are performance reasons why not returning logits is prudent, if not needed
        if not return_logits:
            logits = None

        return logits, loss

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

def _peek_data_shard(filename):
    # only reads the header, returns header data
    with open(filename, "rb") as f:
        # first read the header, which is 256 int32 integers (4 bytes each)
        header = np.frombuffer(f.read(256*4), dtype=np.int32)
    if header[0] != 20240520:
        print("ERROR: magic number mismatch in the data .bin file!")
        print("---> HINT: Are you passing in a correct file with --input_bin?")
        print("---> HINT: Dataset encoding changed recently, re-run data prepro or refer again to README")
        print("---> HINT: For example re-run: `python dev/data/tinyshakespeare.py`, then re-try")
        exit(1)
    assert header[1] == 1, "unsupported version"
    ntok = header[2] # number of tokens (claimed)
    return ntok # for now just return the number of tokens

def _load_data_shard(filename):
    with open(filename, "rb") as f:
        # first read the header, which is 256 int32 integers (4 bytes each)
        header = np.frombuffer(f.read(256*4), dtype=np.int32)
        assert header[0] == 20240520, "magic number mismatch in the data .bin file"
        assert header[1] == 1, "unsupported version"
        ntok = header[2] # number of tokens (claimed)
        # the rest of it are tokens, stored as uint16
        tokens = np.frombuffer(f.read(), dtype=np.uint16)
    assert len(tokens) == ntok, "number of tokens read does not match header?"
    return tokens

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

        # glob files that match the pattern
        self.files = sorted(glob.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
        ntok_total = 0
        for fname in self.files:
            shard_ntok = _peek_data_shard(fname)
            assert shard_ntok >= num_processes * B * T + 1
            ntok_total += int(shard_ntok)
        self.ntok_total = ntok_total

        # kick things off
        self.reset()

    def reset(self):
        self.current_shard = 0
        self.current_position = self.process_rank * self.B * self.T
        self.tokens = _load_data_shard(self.files[self.current_shard])

    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.B * self.T
        self.tokens = _load_data_shard(self.files[self.current_shard])

    def next_batch(self):
        B = self.B
        T = self.T
        buf = self.tokens[self.current_position : self.current_position+B*T+1]
        buf = torch.tensor(buf.astype(np.int32), dtype=torch.long)
        x = (buf[:-1]).view(B, T) # inputs
        y = (buf[1:]).view(B, T) # targets
        # advance current position and load next shard if necessary
        self.current_position += B * T * self.num_processes
        if self.current_position + (B * T * self.num_processes + 1) > len(self.tokens):
            self.advance()
        return x.cuda(), y.cuda()

# -----------------------------------------------------------------------------
# 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*64 # batch size, in sequences, across all devices
    device_batch_size : int = 64 # batch size, in sequences, per device
    sequence_length : int = 1024 # sequence length, in tokens
    num_iterations : int = 5100 # number of iterations to run
    learning_rate : float = 0.0036
    warmup_iters : int = 250
    warmdown_iters : int = 1450 # number of iterations of linear warmup/warmdown 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.

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

# load tokens
train_loader = DistributedDataLoader(args.input_bin, B, T, ddp_rank, ddp_world_size)
val_loader = DistributedDataLoader(args.input_val_bin, B, T, ddp_rank, ddp_world_size)
if master_process:
    print(f"Training DataLoader: total number of tokens: {train_loader.ntok_total} across {len(train_loader.files)} files")
    print(f"Validation DataLoader: total number of tokens: {val_loader.ntok_total} across {len(val_loader.files)} files")
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()
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
ctx = torch.amp.autocast(device_type='cuda', dtype=torch.bfloat16)

# init the optimizer(s)
optimizer1 = torch.optim.AdamW(raw_model.lm_head.parameters(), lr=args.learning_rate, betas=(0.9, 0.95),
                               weight_decay=args.weight_decay, fused=True)
###### shampoo
from distributed_shampoo.distributed_shampoo import DistributedShampoo
from distributed_shampoo.shampoo_types import AdamGraftingConfig, CommunicationDType, DDPShampooConfig
optimizer2 = DistributedShampoo(
    raw_model.transformer.h.parameters(),
    lr=0.5*args.learning_rate,
    betas=(0.95, 0.95),
    epsilon=1e-12,
    weight_decay=0,
    max_preconditioner_dim=8192,
    precondition_frequency=10,
    use_decoupled_weight_decay=True,
    grafting_config=AdamGraftingConfig(
        beta2=0.95,
        epsilon=1e-8,
    ),
    distributed_config=DDPShampooConfig(
        communication_dtype=CommunicationDType.FP32,
        num_trainers_per_group=8,
        communicate_params=False,
    ),
)
####
optimizers = [optimizer1, optimizer2]
# learning rate decay scheduler (linear warmup and warmdown)
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.warmdown_iters:
        return 1.0
    # 3) linear warmdown
    else:
        decay_ratio = (args.num_iterations - it) / args.warmdown_iters
        return decay_ratio
schedulers = [torch.optim.lr_scheduler.LambdaLR(opt, get_lr) for opt in optimizers]

# begin logging
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('='*100 + '\n')
        f.write(code)
        f.write('='*100 + '\n')
        # log information about the hardware/software environment this is running on
        # and print the full `nvidia-smi` to file
        f.write(f"Running pytorch {torch.version.__version__} compiled for CUDA {torch.version.cuda}\nnvidia-smi:\n")
        import subprocess
        result = subprocess.run(['nvidia-smi'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
        f.write(f'{result.stdout}\n')
        f.write('='*100 + '\n')

training_time_ms = 0
# start the clock
torch.cuda.synchronize()
t0 = time.time()
# begin training
train_loader.reset()
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.time()
    timed_steps = float('nan') if step <= 11 else (step - 10) + 1 # <= 11 to avoid bug in val

    # 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.time() - t0)
        # run validation batches
        model.eval()
        val_loader.reset()
        val_loss = 0.0
        for _ in range(val_steps):
            x_val, y_val = val_loader.next_batch()
            with ctx: # of course, we'd like to use no_grad() here too, but that creates a torch.compile error for some reason
                _, loss = model(x_val, y_val, return_logits=False)
                val_loss += loss.detach()
                del loss
        dist.all_reduce(val_loss, op=dist.ReduceOp.AVG)
        val_loss /= val_steps
        # log val loss to console and to logfile
        if master_process:
            print(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')
            with open(logfile, "a") as f:
                f.write(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\n')
        # start the clock again
        torch.cuda.synchronize()
        t0 = time.time()

    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.time() - 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.time()

    # 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()
    for i in range(1, train_accumulation_steps+1):
        # forward pass
        with ctx:
            _, loss = model(x, y, return_logits=False)
            train_loss = loss.detach()
        # advance the dataset for the next batch
        x, y = train_loader.next_batch()
        # backward pass
        if i < train_accumulation_steps:
            with model.no_sync(): # there's no need to sync gradients every accumulation step
                loss.backward()
        else:
            loss.backward() # just sync on the last step
    for p in model.parameters():
        p.grad /= train_accumulation_steps
    # 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.

    #dist.all_reduce(train_loss, op=dist.ReduceOp.AVG) # all-reducing the training loss would be more correct in terms of logging, but slower
    if master_process:
        approx_time = training_time_ms + 1000 * (time.time() - t0)
        print(f"step:{step+1}/{args.num_iterations} train_loss:{train_loss.item():.4f} train_time:{approx_time:.0f}ms step_avg:{approx_time/timed_steps:.2f}ms")
        with open(logfile, "a") as f:
            f.write(f"step:{step+1}/{args.num_iterations} train_loss:{train_loss.item():.4f} train_time:{approx_time:.0f}ms step_avg:{approx_time/timed_steps:.2f}ms\n")

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 2.5.0+cu124 compiled for CUDA 12.4
nvidia-smi:
Tue Oct 29 17:09:20 2024       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.42.06              Driver Version: 555.42.06      CUDA Version: 12.5     |
|-----------------------------------------+------------------------+----------------------+
| 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          Off |   00000000:18:00.0 Off |                    0 |
| N/A   27C    P0            112W /  700W |    5184MiB /  81559MiB |      5%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   1  NVIDIA H100 80GB HBM3          Off |   00000000:2A:00.0 Off |                    0 |
| N/A   30C    P0            116W /  700W |    5232MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   2  NVIDIA H100 80GB HBM3          Off |   00000000:3A:00.0 Off |                    0 |
| N/A   31C    P0            114W /  700W |    5232MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   3  NVIDIA H100 80GB HBM3          Off |   00000000:5D:00.0 Off |                    0 |
| N/A   28C    P0            115W /  700W |    5232MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   4  NVIDIA H100 80GB HBM3          Off |   00000000:84:00.0 Off |                    0 |
| N/A   28C    P0            113W /  700W |    5232MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   5  NVIDIA H100 80GB HBM3          Off |   00000000:8B:00.0 Off |                    0 |
| N/A   30C    P0            115W /  700W |    5232MiB /  81559MiB |      4%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   6  NVIDIA H100 80GB HBM3          Off |   00000000:91:00.0 Off |                    0 |
| N/A   29C    P0            113W /  700W |    5232MiB /  81559MiB |      4%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
|   7  NVIDIA H100 80GB HBM3          Off |   00000000:E4:00.0 Off |                    0 |
| N/A   28C    P0            116W /  700W |    4992MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A       975      C   /usr/bin/python3                                0MiB |
|    1   N/A  N/A       976      C   /usr/bin/python3                                0MiB |
|    2   N/A  N/A       977      C   /usr/bin/python3                                0MiB |
|    3   N/A  N/A       978      C   /usr/bin/python3                                0MiB |
|    4   N/A  N/A       979      C   /usr/bin/python3                                0MiB |
|    5   N/A  N/A       980      C   /usr/bin/python3                                0MiB |
|    6   N/A  N/A       981      C   /usr/bin/python3                                0MiB |
|    7   N/A  N/A       982      C   /usr/bin/python3                                0MiB |
+-----------------------------------------------------------------------------------------+

====================================================================================================
step:0/5100 val_loss:16.0012 train_time:387ms step_avg:nanms
step:1/5100 train_loss:15.9932 train_time:23767ms step_avg:nanms
step:2/5100 train_loss:9.9150 train_time:23895ms step_avg:nanms
step:3/5100 train_loss:9.7008 train_time:24028ms step_avg:nanms
step:4/5100 train_loss:9.6662 train_time:24168ms step_avg:nanms
step:5/5100 train_loss:9.5884 train_time:24311ms step_avg:nanms
step:6/5100 train_loss:9.5632 train_time:24450ms step_avg:nanms
step:7/5100 train_loss:9.4540 train_time:24591ms step_avg:nanms
step:8/5100 train_loss:9.4242 train_time:24731ms step_avg:nanms
step:9/5100 train_loss:9.3624 train_time:24883ms step_avg:nanms
step:10/5100 train_loss:9.2419 train_time:25859ms step_avg:nanms
step:11/5100 train_loss:9.1337 train_time:77ms step_avg:nanms
step:12/5100 train_loss:9.0380 train_time:216ms step_avg:nanms
step:13/5100 train_loss:8.8604 train_time:360ms step_avg:119.97ms
step:14/5100 train_loss:8.7810 train_time:499ms step_avg:124.65ms
step:15/5100 train_loss:8.6541 train_time:637ms step_avg:127.34ms
step:16/5100 train_loss:8.5014 train_time:777ms step_avg:129.48ms
step:17/5100 train_loss:8.4047 train_time:917ms step_avg:131.01ms
step:18/5100 train_loss:8.2657 train_time:1067ms step_avg:133.37ms
step:19/5100 train_loss:8.1035 train_time:1212ms step_avg:134.66ms
step:20/5100 train_loss:8.0265 train_time:1684ms step_avg:168.40ms
step:21/5100 train_loss:7.7134 train_time:1765ms step_avg:160.49ms
step:22/5100 train_loss:7.8879 train_time:1906ms step_avg:158.84ms
step:23/5100 train_loss:7.9875 train_time:2046ms step_avg:157.38ms
step:24/5100 train_loss:7.6865 train_time:2185ms step_avg:156.09ms
step:25/5100 train_loss:7.7219 train_time:2325ms step_avg:154.97ms
step:26/5100 train_loss:7.5040 train_time:2465ms step_avg:154.06ms
step:27/5100 train_loss:7.3955 train_time:2607ms step_avg:153.33ms
step:28/5100 train_loss:7.4827 train_time:2756ms step_avg:153.10ms
step:29/5100 train_loss:7.2464 train_time:2899ms step_avg:152.57ms
step:30/5100 train_loss:7.4403 train_time:3373ms step_avg:168.66ms
step:31/5100 train_loss:7.3266 train_time:3458ms step_avg:164.64ms
step:32/5100 train_loss:7.2452 train_time:3599ms step_avg:163.61ms
step:33/5100 train_loss:7.0678 train_time:3740ms step_avg:162.60ms
step:34/5100 train_loss:7.4372 train_time:3878ms step_avg:161.59ms
step:35/5100 train_loss:7.2074 train_time:4020ms step_avg:160.79ms
step:36/5100 train_loss:7.3725 train_time:4163ms step_avg:160.12ms
step:37/5100 train_loss:7.3140 train_time:4307ms step_avg:159.50ms
step:38/5100 train_loss:7.1533 train_time:4451ms step_avg:158.97ms
step:39/5100 train_loss:7.0120 train_time:4594ms step_avg:158.41ms
step:40/5100 train_loss:7.0830 train_time:5066ms step_avg:168.86ms
step:41/5100 train_loss:6.9248 train_time:5149ms step_avg:166.09ms
step:42/5100 train_loss:6.9538 train_time:5290ms step_avg:165.30ms
step:43/5100 train_loss:6.7362 train_time:5431ms step_avg:164.57ms
step:44/5100 train_loss:6.8312 train_time:5571ms step_avg:163.86ms
step:45/5100 train_loss:6.7972 train_time:5712ms step_avg:163.20ms
step:46/5100 train_loss:6.9690 train_time:5852ms step_avg:162.56ms
step:47/5100 train_loss:6.7614 train_time:5995ms step_avg:162.04ms
step:48/5100 train_loss:6.5881 train_time:6144ms step_avg:161.70ms
step:49/5100 train_loss:6.8168 train_time:6286ms step_avg:161.18ms
step:50/5100 train_loss:6.6428 train_time:6763ms step_avg:169.08ms
step:51/5100 train_loss:6.7990 train_time:6845ms step_avg:166.95ms
step:52/5100 train_loss:6.6375 train_time:6986ms step_avg:166.33ms
step:53/5100 train_loss:6.4313 train_time:7129ms step_avg:165.79ms
step:54/5100 train_loss:6.5745 train_time:7267ms step_avg:165.16ms
step:55/5100 train_loss:6.4796 train_time:7407ms step_avg:164.60ms
step:56/5100 train_loss:6.7716 train_time:7547ms step_avg:164.07ms
step:57/5100 train_loss:6.4392 train_time:7689ms step_avg:163.60ms
step:58/5100 train_loss:6.3004 train_time:7842ms step_avg:163.37ms
step:59/5100 train_loss:6.4854 train_time:7982ms step_avg:162.90ms
step:60/5100 train_loss:6.3667 train_time:8466ms step_avg:169.32ms
step:61/5100 train_loss:6.4793 train_time:8548ms step_avg:167.60ms
step:62/5100 train_loss:6.2640 train_time:8686ms step_avg:167.04ms
step:63/5100 train_loss:6.3352 train_time:8829ms step_avg:166.58ms
step:64/5100 train_loss:6.2687 train_time:8968ms step_avg:166.07ms
step:65/5100 train_loss:6.7716 train_time:9109ms step_avg:165.62ms
step:66/5100 train_loss:6.0851 train_time:9250ms step_avg:165.19ms
step:67/5100 train_loss:6.2478 train_time:9393ms step_avg:164.80ms
step:68/5100 train_loss:6.1071 train_time:9546ms step_avg:164.59ms
step:69/5100 train_loss:6.4479 train_time:9690ms step_avg:164.24ms
step:70/5100 train_loss:6.0062 train_time:10174ms step_avg:169.57ms
step:71/5100 train_loss:6.0685 train_time:10255ms step_avg:168.11ms
step:72/5100 train_loss:6.2744 train_time:10395ms step_avg:167.67ms
step:73/5100 train_loss:6.1537 train_time:10537ms step_avg:167.25ms
step:74/5100 train_loss:6.0448 train_time:10675ms step_avg:166.80ms
step:75/5100 train_loss:6.1362 train_time:10817ms step_avg:166.42ms
step:76/5100 train_loss:6.1090 train_time:10957ms step_avg:166.02ms
step:77/5100 train_loss:6.0674 train_time:11102ms step_avg:165.71ms
step:78/5100 train_loss:6.1354 train_time:11252ms step_avg:165.47ms
step:79/5100 train_loss:6.2168 train_time:11391ms step_avg:165.09ms
step:80/5100 train_loss:6.0535 train_time:11887ms step_avg:169.82ms
step:81/5100 train_loss:6.0919 train_time:11967ms step_avg:168.55ms
step:82/5100 train_loss:5.8081 train_time:12108ms step_avg:168.17ms
step:83/5100 train_loss:6.0150 train_time:12253ms step_avg:167.85ms
step:84/5100 train_loss:5.9913 train_time:12389ms step_avg:167.42ms
step:85/5100 train_loss:5.8842 train_time:12530ms step_avg:167.07ms
step:86/5100 train_loss:5.7542 train_time:12674ms step_avg:166.77ms
step:87/5100 train_loss:5.9485 train_time:12815ms step_avg:166.43ms
step:88/5100 train_loss:5.8595 train_time:12961ms step_avg:166.16ms
step:89/5100 train_loss:5.9595 train_time:13106ms step_avg:165.90ms
step:90/5100 train_loss:5.9182 train_time:13602ms step_avg:170.02ms
step:91/5100 train_loss:5.7935 train_time:13682ms step_avg:168.92ms
step:92/5100 train_loss:5.7844 train_time:13826ms step_avg:168.61ms
step:93/5100 train_loss:5.8896 train_time:13964ms step_avg:168.25ms
step:94/5100 train_loss:5.7508 train_time:14108ms step_avg:167.95ms
step:95/5100 train_loss:5.7056 train_time:14246ms step_avg:167.60ms
step:96/5100 train_loss:5.7156 train_time:14387ms step_avg:167.29ms
step:97/5100 train_loss:5.6196 train_time:14530ms step_avg:167.01ms
step:98/5100 train_loss:5.7729 train_time:14681ms step_avg:166.83ms
step:99/5100 train_loss:5.6119 train_time:14823ms step_avg:166.55ms
step:100/5100 train_loss:5.7686 train_time:15325ms step_avg:170.27ms
step:101/5100 train_loss:5.7089 train_time:15405ms step_avg:169.28ms
step:102/5100 train_loss:5.5872 train_time:15545ms step_avg:168.97ms
step:103/5100 train_loss:5.7026 train_time:15685ms step_avg:168.66ms
step:104/5100 train_loss:5.7022 train_time:15826ms step_avg:168.36ms
step:105/5100 train_loss:5.4761 train_time:15970ms step_avg:168.10ms
step:106/5100 train_loss:5.5966 train_time:16109ms step_avg:167.80ms
step:107/5100 train_loss:5.8305 train_time:16248ms step_avg:167.51ms
step:108/5100 train_loss:5.5736 train_time:16402ms step_avg:167.36ms
step:109/5100 train_loss:5.3011 train_time:16544ms step_avg:167.12ms
step:110/5100 train_loss:5.5350 train_time:17053ms step_avg:170.53ms
step:111/5100 train_loss:5.4785 train_time:17133ms step_avg:169.63ms
step:112/5100 train_loss:5.4666 train_time:17275ms step_avg:169.36ms
step:113/5100 train_loss:5.5512 train_time:17414ms step_avg:169.07ms
step:114/5100 train_loss:5.4721 train_time:17554ms step_avg:168.78ms
step:115/5100 train_loss:5.3027 train_time:17694ms step_avg:168.51ms
step:116/5100 train_loss:5.4916 train_time:17834ms step_avg:168.24ms
step:117/5100 train_loss:5.3232 train_time:17976ms step_avg:168.00ms
step:118/5100 train_loss:5.3224 train_time:18127ms step_avg:167.84ms
step:119/5100 train_loss:5.4408 train_time:18269ms step_avg:167.61ms
step:120/5100 train_loss:5.4559 train_time:18787ms step_avg:170.79ms
step:121/5100 train_loss:5.3600 train_time:18869ms step_avg:169.99ms
step:122/5100 train_loss:5.2159 train_time:19008ms step_avg:169.72ms
step:123/5100 train_loss:5.3147 train_time:19148ms step_avg:169.46ms
step:124/5100 train_loss:5.1880 train_time:19289ms step_avg:169.20ms
step:125/5100 train_loss:5.5392 train_time:19432ms step_avg:168.98ms
step:125/5100 val_loss:5.4789 train_time:19493ms step_avg:169.51ms
step:126/5100 train_loss:5.4887 train_time:19581ms step_avg:168.80ms
step:127/5100 train_loss:5.4520 train_time:19730ms step_avg:168.63ms
step:128/5100 train_loss:5.5965 train_time:19871ms step_avg:168.39ms
step:129/5100 train_loss:5.4071 train_time:20012ms step_avg:168.17ms
step:130/5100 train_loss:5.7455 train_time:20509ms step_avg:170.91ms
step:131/5100 train_loss:5.4219 train_time:20589ms step_avg:170.16ms
step:132/5100 train_loss:5.4284 train_time:20730ms step_avg:169.92ms
step:133/5100 train_loss:5.3232 train_time:20868ms step_avg:169.66ms
step:134/5100 train_loss:5.3609 train_time:21011ms step_avg:169.44ms
step:135/5100 train_loss:5.2843 train_time:21152ms step_avg:169.21ms
step:136/5100 train_loss:5.3281 train_time:21288ms step_avg:168.96ms
step:137/5100 train_loss:5.1319 train_time:21433ms step_avg:168.76ms
step:138/5100 train_loss:5.2754 train_time:21582ms step_avg:168.61ms
step:139/5100 train_loss:5.2478 train_time:21725ms step_avg:168.41ms
step:140/5100 train_loss:5.2412 train_time:22230ms step_avg:171.00ms
step:141/5100 train_loss:5.2657 train_time:22312ms step_avg:170.32ms
step:142/5100 train_loss:5.1621 train_time:22451ms step_avg:170.08ms
step:143/5100 train_loss:5.2531 train_time:22592ms step_avg:169.86ms
step:144/5100 train_loss:5.0479 train_time:22736ms step_avg:169.67ms
step:145/5100 train_loss:5.2010 train_time:22874ms step_avg:169.44ms
step:146/5100 train_loss:5.1404 train_time:23016ms step_avg:169.23ms
step:147/5100 train_loss:5.0516 train_time:23160ms step_avg:169.05ms
step:148/5100 train_loss:5.1621 train_time:23310ms step_avg:168.91ms
step:149/5100 train_loss:5.1243 train_time:23450ms step_avg:168.70ms
step:150/5100 train_loss:5.2053 train_time:23962ms step_avg:171.16ms
step:151/5100 train_loss:5.2043 train_time:24042ms step_avg:170.51ms
step:152/5100 train_loss:5.1079 train_time:24183ms step_avg:170.30ms
step:153/5100 train_loss:5.0822 train_time:24323ms step_avg:170.09ms
step:154/5100 train_loss:5.1566 train_time:24463ms step_avg:169.88ms
step:155/5100 train_loss:5.0902 train_time:24604ms step_avg:169.69ms
step:156/5100 train_loss:5.0724 train_time:24749ms step_avg:169.51ms
step:157/5100 train_loss:5.0760 train_time:24891ms step_avg:169.32ms
step:158/5100 train_loss:5.2046 train_time:25041ms step_avg:169.20ms
step:159/5100 train_loss:4.9881 train_time:25183ms step_avg:169.01ms
step:160/5100 train_loss:5.0457 train_time:25705ms step_avg:171.37ms
step:161/5100 train_loss:4.8939 train_time:25785ms step_avg:170.76ms
step:162/5100 train_loss:5.0472 train_time:25926ms step_avg:170.57ms
step:163/5100 train_loss:5.0746 train_time:26067ms step_avg:170.37ms
step:164/5100 train_loss:5.0687 train_time:26208ms step_avg:170.18ms
step:165/5100 train_loss:4.8791 train_time:26348ms step_avg:169.98ms
step:166/5100 train_loss:4.9990 train_time:26489ms step_avg:169.80ms
step:167/5100 train_loss:5.1706 train_time:26632ms step_avg:169.63ms
step:168/5100 train_loss:4.9139 train_time:26783ms step_avg:169.51ms
step:169/5100 train_loss:4.9936 train_time:26926ms step_avg:169.35ms
step:170/5100 train_loss:4.8702 train_time:27456ms step_avg:171.60ms
step:171/5100 train_loss:4.8089 train_time:27536ms step_avg:171.03ms
step:172/5100 train_loss:4.9151 train_time:27676ms step_avg:170.84ms
step:173/5100 train_loss:4.8890 train_time:27821ms step_avg:170.68ms
step:174/5100 train_loss:4.9419 train_time:27959ms step_avg:170.48ms
step:175/5100 train_loss:5.0924 train_time:28099ms step_avg:170.30ms
step:176/5100 train_loss:4.9839 train_time:28241ms step_avg:170.12ms
step:177/5100 train_loss:4.8784 train_time:28385ms step_avg:169.97ms
step:178/5100 train_loss:4.8992 train_time:28534ms step_avg:169.85ms
step:179/5100 train_loss:5.0295 train_time:28675ms step_avg:169.67ms
step:180/5100 train_loss:5.0373 train_time:29199ms step_avg:171.76ms
step:181/5100 train_loss:4.9380 train_time:29278ms step_avg:171.22ms
step:182/5100 train_loss:5.0842 train_time:29424ms step_avg:171.07ms
step:183/5100 train_loss:4.9867 train_time:29560ms step_avg:170.87ms
step:184/5100 train_loss:4.9449 train_time:29700ms step_avg:170.69ms
step:185/5100 train_loss:5.0124 train_time:29841ms step_avg:170.52ms
step:186/5100 train_loss:5.2017 train_time:29984ms step_avg:170.37ms
step:187/5100 train_loss:5.0543 train_time:30128ms step_avg:170.22ms
step:188/5100 train_loss:5.2802 train_time:30271ms step_avg:170.06ms
step:189/5100 train_loss:5.0043 train_time:30492ms step_avg:170.34ms
step:190/5100 train_loss:4.8845 train_time:31143ms step_avg:173.01ms
step:191/5100 train_loss:5.0194 train_time:31206ms step_avg:172.41ms
step:192/5100 train_loss:4.8367 train_time:31349ms step_avg:172.25ms
step:193/5100 train_loss:4.7618 train_time:31497ms step_avg:172.11ms
step:194/5100 train_loss:4.9643 train_time:31636ms step_avg:171.94ms
step:195/5100 train_loss:4.8910 train_time:31780ms step_avg:171.78ms
step:196/5100 train_loss:5.0943 train_time:31927ms step_avg:171.65ms
step:197/5100 train_loss:4.9573 train_time:32066ms step_avg:171.48ms
step:198/5100 train_loss:4.7832 train_time:32219ms step_avg:171.38ms
step:199/5100 train_loss:4.8360 train_time:32362ms step_avg:171.23ms
step:200/5100 train_loss:4.7051 train_time:32892ms step_avg:173.11ms
step:201/5100 train_loss:4.7983 train_time:32971ms step_avg:172.63ms
step:202/5100 train_loss:4.7018 train_time:33111ms step_avg:172.45ms
step:203/5100 train_loss:4.9272 train_time:33252ms step_avg:172.29ms
step:204/5100 train_loss:4.7993 train_time:33392ms step_avg:172.12ms
step:205/5100 train_loss:4.8114 train_time:33534ms step_avg:171.97ms
step:206/5100 train_loss:4.9369 train_time:33675ms step_avg:171.81ms
step:207/5100 train_loss:4.5913 train_time:33816ms step_avg:171.65ms
step:208/5100 train_loss:4.7378 train_time:33965ms step_avg:171.54ms
step:209/5100 train_loss:4.7052 train_time:34108ms step_avg:171.40ms
step:210/5100 train_loss:4.8712 train_time:34643ms step_avg:173.22ms
step:211/5100 train_loss:4.7750 train_time:34723ms step_avg:172.75ms
step:212/5100 train_loss:4.6626 train_time:34863ms step_avg:172.59ms
step:213/5100 train_loss:4.7626 train_time:35004ms step_avg:172.43ms
step:214/5100 train_loss:4.6165 train_time:35145ms step_avg:172.28ms
step:215/5100 train_loss:4.7094 train_time:35284ms step_avg:172.12ms
step:216/5100 train_loss:4.5584 train_time:35425ms step_avg:171.97ms
step:217/5100 train_loss:4.6515 train_time:35568ms step_avg:171.83ms
step:218/5100 train_loss:4.6063 train_time:35722ms step_avg:171.74ms
step:219/5100 train_loss:4.6285 train_time:35863ms step_avg:171.60ms
step:220/5100 train_loss:4.6371 train_time:36408ms step_avg:173.37ms
step:221/5100 train_loss:4.6414 train_time:36488ms step_avg:172.93ms
step:222/5100 train_loss:4.6660 train_time:36634ms step_avg:172.80ms
step:223/5100 train_loss:4.6075 train_time:36769ms step_avg:172.62ms
step:224/5100 train_loss:4.5773 train_time:36909ms step_avg:172.47ms
step:225/5100 train_loss:4.7807 train_time:37050ms step_avg:172.33ms
step:226/5100 train_loss:4.4050 train_time:37190ms step_avg:172.18ms
step:227/5100 train_loss:4.4996 train_time:37337ms step_avg:172.06ms
step:228/5100 train_loss:4.5087 train_time:37480ms step_avg:171.93ms
step:229/5100 train_loss:4.6570 train_time:37624ms step_avg:171.80ms
step:230/5100 train_loss:4.4532 train_time:38179ms step_avg:173.54ms
step:231/5100 train_loss:4.5810 train_time:38258ms step_avg:173.11ms
step:232/5100 train_loss:4.4212 train_time:38399ms step_avg:172.97ms
step:233/5100 train_loss:4.4451 train_time:38543ms step_avg:172.84ms
step:234/5100 train_loss:4.6154 train_time:38684ms step_avg:172.70ms
step:235/5100 train_loss:4.5081 train_time:38821ms step_avg:172.54ms
step:236/5100 train_loss:4.3645 train_time:38962ms step_avg:172.40ms
step:237/5100 train_loss:4.5949 train_time:39103ms step_avg:172.26ms
step:238/5100 train_loss:4.5686 train_time:39252ms step_avg:172.16ms
step:239/5100 train_loss:4.4410 train_time:39395ms step_avg:172.03ms
step:240/5100 train_loss:4.5886 train_time:39958ms step_avg:173.73ms
step:241/5100 train_loss:4.5849 train_time:40042ms step_avg:173.34ms
step:242/5100 train_loss:4.4613 train_time:40179ms step_avg:173.19ms
step:243/5100 train_loss:4.6473 train_time:40320ms step_avg:173.05ms
step:244/5100 train_loss:4.5399 train_time:40461ms step_avg:172.91ms
step:245/5100 train_loss:4.5807 train_time:40601ms step_avg:172.77ms
step:246/5100 train_loss:4.6836 train_time:40745ms step_avg:172.65ms
step:247/5100 train_loss:4.6271 train_time:40882ms step_avg:172.50ms
step:248/5100 train_loss:4.5882 train_time:41034ms step_avg:172.41ms
step:249/5100 train_loss:4.7489 train_time:41177ms step_avg:172.29ms
step:250/5100 train_loss:4.5238 train_time:41724ms step_avg:173.85ms
step:250/5100 val_loss:4.5384 train_time:41726ms step_avg:173.86ms
step:251/5100 train_loss:4.4905 train_time:41816ms step_avg:173.51ms
step:252/5100 train_loss:4.6180 train_time:41962ms step_avg:173.40ms
step:253/5100 train_loss:4.6336 train_time:42104ms step_avg:173.27ms
step:254/5100 train_loss:4.4818 train_time:42244ms step_avg:173.13ms
step:255/5100 train_loss:4.4398 train_time:42389ms step_avg:173.02ms
step:256/5100 train_loss:4.6030 train_time:42525ms step_avg:172.87ms
step:257/5100 train_loss:4.5381 train_time:42666ms step_avg:172.74ms
step:258/5100 train_loss:4.5401 train_time:42811ms step_avg:172.62ms
step:259/5100 train_loss:4.4795 train_time:42957ms step_avg:172.52ms
step:260/5100 train_loss:4.4965 train_time:43503ms step_avg:174.01ms
step:261/5100 train_loss:4.5321 train_time:43587ms step_avg:173.65ms
step:262/5100 train_loss:4.4936 train_time:43725ms step_avg:173.51ms
step:263/5100 train_loss:4.4563 train_time:43867ms step_avg:173.39ms
step:264/5100 train_loss:4.3705 train_time:44006ms step_avg:173.25ms
step:265/5100 train_loss:4.4394 train_time:44146ms step_avg:173.12ms
step:266/5100 train_loss:4.2868 train_time:44291ms step_avg:173.01ms
step:267/5100 train_loss:4.3667 train_time:44429ms step_avg:172.87ms
step:268/5100 train_loss:4.3820 train_time:44577ms step_avg:172.78ms
step:269/5100 train_loss:4.3668 train_time:44720ms step_avg:172.66ms
step:270/5100 train_loss:4.2981 train_time:45271ms step_avg:174.12ms
step:271/5100 train_loss:4.5103 train_time:45351ms step_avg:173.76ms
step:272/5100 train_loss:4.4142 train_time:45497ms step_avg:173.65ms
step:273/5100 train_loss:4.3160 train_time:45634ms step_avg:173.51ms
step:274/5100 train_loss:4.3676 train_time:45775ms step_avg:173.39ms
step:275/5100 train_loss:4.4379 train_time:45920ms step_avg:173.28ms
step:276/5100 train_loss:4.4590 train_time:46057ms step_avg:173.15ms
step:277/5100 train_loss:4.6260 train_time:46199ms step_avg:173.03ms
step:278/5100 train_loss:4.4251 train_time:46349ms step_avg:172.94ms
step:279/5100 train_loss:4.5017 train_time:46493ms step_avg:172.84ms
step:280/5100 train_loss:4.3968 train_time:47051ms step_avg:174.26ms
step:281/5100 train_loss:4.4798 train_time:47131ms step_avg:173.91ms
step:282/5100 train_loss:4.3303 train_time:47270ms step_avg:173.79ms
step:283/5100 train_loss:4.3653 train_time:47412ms step_avg:173.67ms
step:284/5100 train_loss:4.2934 train_time:47551ms step_avg:173.55ms
step:285/5100 train_loss:4.4425 train_time:47697ms step_avg:173.44ms
step:286/5100 train_loss:4.4395 train_time:47834ms step_avg:173.31ms
step:287/5100 train_loss:4.4720 train_time:47977ms step_avg:173.20ms
step:288/5100 train_loss:4.2989 train_time:48125ms step_avg:173.11ms
step:289/5100 train_loss:4.3916 train_time:48267ms step_avg:173.00ms
step:290/5100 train_loss:4.2462 train_time:48830ms step_avg:174.39ms
step:291/5100 train_loss:4.2380 train_time:48911ms step_avg:174.06ms
step:292/5100 train_loss:4.3341 train_time:49052ms step_avg:173.94ms
step:293/5100 train_loss:4.2374 train_time:49193ms step_avg:173.83ms
step:294/5100 train_loss:4.2774 train_time:49335ms step_avg:173.71ms
step:295/5100 train_loss:4.3286 train_time:49477ms step_avg:173.60ms
step:296/5100 train_loss:4.1916 train_time:49617ms step_avg:173.49ms
step:297/5100 train_loss:4.2208 train_time:49759ms step_avg:173.38ms
step:298/5100 train_loss:4.2148 train_time:49909ms step_avg:173.29ms
step:299/5100 train_loss:4.3247 train_time:50051ms step_avg:173.19ms
step:300/5100 train_loss:4.1866 train_time:50621ms step_avg:174.56ms
step:301/5100 train_loss:4.3397 train_time:50704ms step_avg:174.24ms
step:302/5100 train_loss:4.3371 train_time:50843ms step_avg:174.12ms
step:303/5100 train_loss:4.2739 train_time:50984ms step_avg:174.01ms
step:304/5100 train_loss:4.3286 train_time:51124ms step_avg:173.89ms
step:305/5100 train_loss:4.3151 train_time:51264ms step_avg:173.77ms
step:306/5100 train_loss:4.7907 train_time:51408ms step_avg:173.68ms
step:307/5100 train_loss:4.2803 train_time:51548ms step_avg:173.56ms
step:308/5100 train_loss:4.1856 train_time:51703ms step_avg:173.50ms
step:309/5100 train_loss:4.3509 train_time:51841ms step_avg:173.38ms
step:310/5100 train_loss:4.1918 train_time:52412ms step_avg:174.71ms
step:311/5100 train_loss:4.4188 train_time:52493ms step_avg:174.40ms
step:312/5100 train_loss:4.2807 train_time:52634ms step_avg:174.29ms
step:313/5100 train_loss:4.2248 train_time:52775ms step_avg:174.18ms
step:314/5100 train_loss:4.3530 train_time:52916ms step_avg:174.07ms
step:315/5100 train_loss:4.4419 train_time:53057ms step_avg:173.96ms
step:316/5100 train_loss:4.3050 train_time:53206ms step_avg:173.88ms
step:317/5100 train_loss:4.1341 train_time:53341ms step_avg:173.75ms
step:318/5100 train_loss:4.2161 train_time:53491ms step_avg:173.67ms
step:319/5100 train_loss:4.2499 train_time:53640ms step_avg:173.59ms
step:320/5100 train_loss:4.2307 train_time:54209ms step_avg:174.87ms
step:321/5100 train_loss:4.3251 train_time:54288ms step_avg:174.56ms
step:322/5100 train_loss:4.2864 train_time:54430ms step_avg:174.45ms
step:323/5100 train_loss:4.2555 train_time:54572ms step_avg:174.35ms
step:324/5100 train_loss:4.3412 train_time:54713ms step_avg:174.25ms
step:325/5100 train_loss:4.3096 train_time:54852ms step_avg:174.13ms
step:326/5100 train_loss:4.3767 train_time:54994ms step_avg:174.03ms
step:327/5100 train_loss:4.2214 train_time:55136ms step_avg:173.93ms
step:328/5100 train_loss:4.7230 train_time:55285ms step_avg:173.85ms
step:329/5100 train_loss:4.4027 train_time:55429ms step_avg:173.76ms
step:330/5100 train_loss:4.1354 train_time:56001ms step_avg:175.00ms
step:331/5100 train_loss:4.0818 train_time:56081ms step_avg:174.71ms
step:332/5100 train_loss:4.2999 train_time:56221ms step_avg:174.60ms
step:333/5100 train_loss:4.2189 train_time:56360ms step_avg:174.49ms
step:334/5100 train_loss:4.1983 train_time:56501ms step_avg:174.39ms
step:335/5100 train_loss:4.1610 train_time:56641ms step_avg:174.28ms
step:336/5100 train_loss:4.3382 train_time:56782ms step_avg:174.18ms
step:337/5100 train_loss:4.2822 train_time:56925ms step_avg:174.08ms
step:338/5100 train_loss:4.7512 train_time:57077ms step_avg:174.01ms
step:339/5100 train_loss:4.2829 train_time:57218ms step_avg:173.92ms
step:340/5100 train_loss:4.2119 train_time:57789ms step_avg:175.12ms
step:341/5100 train_loss:4.2438 train_time:57872ms step_avg:174.84ms
step:342/5100 train_loss:4.1528 train_time:58016ms step_avg:174.75ms
step:343/5100 train_loss:4.1294 train_time:58155ms step_avg:174.64ms
step:344/5100 train_loss:4.1845 train_time:58296ms step_avg:174.54ms
step:345/5100 train_loss:4.3148 train_time:58437ms step_avg:174.44ms
step:346/5100 train_loss:4.1647 train_time:58578ms step_avg:174.34ms
step:347/5100 train_loss:4.0878 train_time:58721ms step_avg:174.25ms
step:348/5100 train_loss:4.1313 train_time:58867ms step_avg:174.16ms
step:349/5100 train_loss:4.1823 train_time:59009ms step_avg:174.07ms
step:350/5100 train_loss:4.1374 train_time:59581ms step_avg:175.24ms
step:351/5100 train_loss:3.8499 train_time:59666ms step_avg:174.97ms
step:352/5100 train_loss:4.1240 train_time:59808ms step_avg:174.88ms
step:353/5100 train_loss:4.4505 train_time:59946ms step_avg:174.77ms
step:354/5100 train_loss:3.9783 train_time:60087ms step_avg:174.67ms
step:355/5100 train_loss:4.2393 train_time:60227ms step_avg:174.57ms
step:356/5100 train_loss:4.1155 train_time:60367ms step_avg:174.47ms
step:357/5100 train_loss:4.2010 train_time:60509ms step_avg:174.38ms
step:358/5100 train_loss:4.1693 train_time:60657ms step_avg:174.30ms
step:359/5100 train_loss:4.1609 train_time:60800ms step_avg:174.21ms
step:360/5100 train_loss:4.1760 train_time:61372ms step_avg:175.35ms
step:361/5100 train_loss:3.7650 train_time:61453ms step_avg:175.08ms
step:362/5100 train_loss:4.3344 train_time:61596ms step_avg:174.99ms
step:363/5100 train_loss:4.2324 train_time:61765ms step_avg:174.97ms
step:364/5100 train_loss:4.1491 train_time:61868ms step_avg:174.77ms
step:365/5100 train_loss:4.0701 train_time:62012ms step_avg:174.68ms
step:366/5100 train_loss:4.2311 train_time:62156ms step_avg:174.60ms
step:367/5100 train_loss:4.1948 train_time:62298ms step_avg:174.50ms
step:368/5100 train_loss:4.1739 train_time:62447ms step_avg:174.43ms
step:369/5100 train_loss:4.1495 train_time:62590ms step_avg:174.34ms
step:370/5100 train_loss:4.0436 train_time:63162ms step_avg:175.45ms
step:371/5100 train_loss:4.1978 train_time:63247ms step_avg:175.20ms
step:372/5100 train_loss:4.0796 train_time:63388ms step_avg:175.11ms
step:373/5100 train_loss:3.9994 train_time:63529ms step_avg:175.01ms
step:374/5100 train_loss:4.2125 train_time:63668ms step_avg:174.91ms
step:375/5100 train_loss:4.1420 train_time:63808ms step_avg:174.82ms
step:375/5100 val_loss:4.1323 train_time:63871ms step_avg:174.99ms
step:376/5100 train_loss:4.1046 train_time:63958ms step_avg:174.75ms
step:377/5100 train_loss:4.1695 train_time:64106ms step_avg:174.68ms
step:378/5100 train_loss:4.0825 train_time:64334ms step_avg:174.82ms
step:379/5100 train_loss:4.1424 train_time:64464ms step_avg:174.70ms
step:380/5100 train_loss:4.1893 train_time:65166ms step_avg:176.12ms
step:381/5100 train_loss:4.2408 train_time:65236ms step_avg:175.84ms
step:382/5100 train_loss:4.1508 train_time:65376ms step_avg:175.74ms
step:383/5100 train_loss:4.1336 train_time:65518ms step_avg:175.65ms
step:384/5100 train_loss:4.0855 train_time:65658ms step_avg:175.56ms
step:385/5100 train_loss:4.1629 train_time:65807ms step_avg:175.48ms
step:386/5100 train_loss:4.0743 train_time:65948ms step_avg:175.39ms
step:387/5100 train_loss:4.1862 train_time:66088ms step_avg:175.30ms
step:388/5100 train_loss:4.3833 train_time:66239ms step_avg:175.24ms
step:389/5100 train_loss:4.1027 train_time:66381ms step_avg:175.15ms
step:390/5100 train_loss:4.0733 train_time:66951ms step_avg:176.19ms
step:391/5100 train_loss:4.1768 train_time:67038ms step_avg:175.95ms
step:392/5100 train_loss:4.1052 train_time:67176ms step_avg:175.85ms
step:393/5100 train_loss:4.2088 train_time:67322ms step_avg:175.78ms
step:394/5100 train_loss:4.0451 train_time:67463ms step_avg:175.69ms
step:395/5100 train_loss:4.1877 train_time:67600ms step_avg:175.58ms
step:396/5100 train_loss:3.9293 train_time:67743ms step_avg:175.50ms
step:397/5100 train_loss:4.1308 train_time:67881ms step_avg:175.40ms
step:398/5100 train_loss:4.1840 train_time:68030ms step_avg:175.34ms
step:399/5100 train_loss:4.1781 train_time:68173ms step_avg:175.25ms
step:400/5100 train_loss:4.0820 train_time:68748ms step_avg:176.28ms
step:401/5100 train_loss:4.1373 train_time:68829ms step_avg:176.03ms
step:402/5100 train_loss:4.2041 train_time:68971ms step_avg:175.95ms
step:403/5100 train_loss:4.1314 train_time:69108ms step_avg:175.85ms
step:404/5100 train_loss:4.2354 train_time:69254ms step_avg:175.77ms
step:405/5100 train_loss:3.9998 train_time:69390ms step_avg:175.67ms
step:406/5100 train_loss:4.0791 train_time:69533ms step_avg:175.59ms
step:407/5100 train_loss:4.3672 train_time:69673ms step_avg:175.50ms
step:408/5100 train_loss:4.0788 train_time:69820ms step_avg:175.43ms
step:409/5100 train_loss:4.1065 train_time:69964ms step_avg:175.35ms
step:410/5100 train_loss:4.1459 train_time:70534ms step_avg:176.34ms
step:411/5100 train_loss:4.0315 train_time:70620ms step_avg:176.11ms
step:412/5100 train_loss:4.0480 train_time:70761ms step_avg:176.02ms
step:413/5100 train_loss:4.4732 train_time:70903ms step_avg:175.94ms
step:414/5100 train_loss:3.9179 train_time:71045ms step_avg:175.85ms
step:415/5100 train_loss:4.2966 train_time:71182ms step_avg:175.76ms
step:416/5100 train_loss:4.0454 train_time:71324ms step_avg:175.67ms
step:417/5100 train_loss:4.0496 train_time:71464ms step_avg:175.59ms
step:418/5100 train_loss:4.2364 train_time:71610ms step_avg:175.51ms
step:419/5100 train_loss:3.9650 train_time:71755ms step_avg:175.44ms
step:420/5100 train_loss:4.0781 train_time:72328ms step_avg:176.41ms
step:421/5100 train_loss:4.0194 train_time:72415ms step_avg:176.19ms
step:422/5100 train_loss:3.9240 train_time:72553ms step_avg:176.10ms
step:423/5100 train_loss:4.0524 train_time:72693ms step_avg:176.01ms
step:424/5100 train_loss:4.1453 train_time:72834ms step_avg:175.93ms
step:425/5100 train_loss:3.9175 train_time:72977ms step_avg:175.85ms
step:426/5100 train_loss:4.0957 train_time:73116ms step_avg:175.76ms
step:427/5100 train_loss:3.9727 train_time:73262ms step_avg:175.69ms
step:428/5100 train_loss:4.1864 train_time:73406ms step_avg:175.61ms
step:429/5100 train_loss:4.1058 train_time:73553ms step_avg:175.54ms
step:430/5100 train_loss:4.0338 train_time:74121ms step_avg:176.48ms
step:431/5100 train_loss:4.0007 train_time:74204ms step_avg:176.26ms
step:432/5100 train_loss:3.9041 train_time:74348ms step_avg:176.18ms
step:433/5100 train_loss:4.0364 train_time:74485ms step_avg:176.09ms
step:434/5100 train_loss:4.1023 train_time:74627ms step_avg:176.01ms
step:435/5100 train_loss:4.0363 train_time:74766ms step_avg:175.92ms
step:436/5100 train_loss:4.0975 train_time:74905ms step_avg:175.83ms
step:437/5100 train_loss:4.0983 train_time:75051ms step_avg:175.76ms
step:438/5100 train_loss:4.0150 train_time:75197ms step_avg:175.69ms
step:439/5100 train_loss:4.0040 train_time:75338ms step_avg:175.61ms
step:440/5100 train_loss:3.9715 train_time:75910ms step_avg:176.54ms
step:441/5100 train_loss:4.1513 train_time:75991ms step_avg:176.31ms
step:442/5100 train_loss:4.0383 train_time:76130ms step_avg:176.23ms
step:443/5100 train_loss:4.0255 train_time:76275ms step_avg:176.16ms
step:444/5100 train_loss:3.9194 train_time:76411ms step_avg:176.06ms
step:445/5100 train_loss:4.1808 train_time:76558ms step_avg:176.00ms
step:446/5100 train_loss:4.1148 train_time:76690ms step_avg:175.90ms
step:447/5100 train_loss:4.1134 train_time:76832ms step_avg:175.82ms
step:448/5100 train_loss:4.0217 train_time:76978ms step_avg:175.75ms
step:449/5100 train_loss:4.1159 train_time:77122ms step_avg:175.68ms
step:450/5100 train_loss:3.9450 train_time:77689ms step_avg:176.57ms
step:451/5100 train_loss:3.9820 train_time:77776ms step_avg:176.36ms
step:452/5100 train_loss:3.8512 train_time:77918ms step_avg:176.28ms
step:453/5100 train_loss:3.9858 train_time:78062ms step_avg:176.21ms
step:454/5100 train_loss:3.9610 train_time:78199ms step_avg:176.12ms
step:455/5100 train_loss:3.9170 train_time:78340ms step_avg:176.04ms
step:456/5100 train_loss:4.1310 train_time:78479ms step_avg:175.96ms
step:457/5100 train_loss:3.9998 train_time:78625ms step_avg:175.90ms
step:458/5100 train_loss:4.0690 train_time:78777ms step_avg:175.84ms
step:459/5100 train_loss:4.1165 train_time:78915ms step_avg:175.76ms
step:460/5100 train_loss:3.9121 train_time:79488ms step_avg:176.64ms
step:461/5100 train_loss:4.0756 train_time:79572ms step_avg:176.43ms
step:462/5100 train_loss:3.9716 train_time:79712ms step_avg:176.35ms
step:463/5100 train_loss:3.9823 train_time:79850ms step_avg:176.27ms
step:464/5100 train_loss:4.0510 train_time:79990ms step_avg:176.19ms
step:465/5100 train_loss:3.9868 train_time:80132ms step_avg:176.11ms
step:466/5100 train_loss:3.9928 train_time:80273ms step_avg:176.04ms
step:467/5100 train_loss:4.0921 train_time:80416ms step_avg:175.97ms
step:468/5100 train_loss:4.0981 train_time:80564ms step_avg:175.90ms
step:469/5100 train_loss:4.0717 train_time:80710ms step_avg:175.84ms
step:470/5100 train_loss:3.9633 train_time:81277ms step_avg:176.69ms
step:471/5100 train_loss:4.0379 train_time:81363ms step_avg:176.49ms
step:472/5100 train_loss:4.0941 train_time:81499ms step_avg:176.41ms
step:473/5100 train_loss:4.0364 train_time:81639ms step_avg:176.33ms
step:474/5100 train_loss:3.9984 train_time:81780ms step_avg:176.25ms
step:475/5100 train_loss:3.8487 train_time:81920ms step_avg:176.17ms
step:476/5100 train_loss:4.2755 train_time:82065ms step_avg:176.10ms
step:477/5100 train_loss:4.0406 train_time:82202ms step_avg:176.02ms
step:478/5100 train_loss:3.8492 train_time:82350ms step_avg:175.96ms
step:479/5100 train_loss:4.0777 train_time:82494ms step_avg:175.89ms
step:480/5100 train_loss:4.0382 train_time:83067ms step_avg:176.74ms
step:481/5100 train_loss:4.1734 train_time:83151ms step_avg:176.54ms
step:482/5100 train_loss:4.0000 train_time:83288ms step_avg:176.46ms
step:483/5100 train_loss:3.7892 train_time:83431ms step_avg:176.39ms
step:484/5100 train_loss:4.0818 train_time:83573ms step_avg:176.31ms
step:485/5100 train_loss:3.9370 train_time:83708ms step_avg:176.23ms
step:486/5100 train_loss:3.9420 train_time:83847ms step_avg:176.15ms
step:487/5100 train_loss:3.8668 train_time:83989ms step_avg:176.08ms
step:488/5100 train_loss:3.9403 train_time:84136ms step_avg:176.02ms
step:489/5100 train_loss:4.1436 train_time:84281ms step_avg:175.95ms
step:490/5100 train_loss:3.9844 train_time:84851ms step_avg:176.77ms
step:491/5100 train_loss:3.8748 train_time:84937ms step_avg:176.58ms
step:492/5100 train_loss:3.8908 train_time:85082ms step_avg:176.52ms
step:493/5100 train_loss:4.0020 train_time:85218ms step_avg:176.44ms
step:494/5100 train_loss:3.8491 train_time:85362ms step_avg:176.37ms
step:495/5100 train_loss:3.9847 train_time:85499ms step_avg:176.29ms
step:496/5100 train_loss:3.9145 train_time:85639ms step_avg:176.21ms
step:497/5100 train_loss:3.8112 train_time:85782ms step_avg:176.14ms
step:498/5100 train_loss:4.0008 train_time:85928ms step_avg:176.08ms
step:499/5100 train_loss:4.0729 train_time:86074ms step_avg:176.02ms
step:500/5100 train_loss:4.1056 train_time:86641ms step_avg:176.82ms
step:500/5100 val_loss:3.9739 train_time:86649ms step_avg:176.83ms
step:501/5100 train_loss:4.0087 train_time:86737ms step_avg:176.65ms
step:502/5100 train_loss:4.0583 train_time:86886ms step_avg:176.60ms
step:503/5100 train_loss:4.0050 train_time:87030ms step_avg:176.53ms
step:504/5100 train_loss:4.0438 train_time:87169ms step_avg:176.46ms
step:505/5100 train_loss:3.9974 train_time:87311ms step_avg:176.39ms
step:506/5100 train_loss:4.0873 train_time:87451ms step_avg:176.31ms
step:507/5100 train_loss:3.8921 train_time:87591ms step_avg:176.24ms
step:508/5100 train_loss:4.0257 train_time:87736ms step_avg:176.18ms
step:509/5100 train_loss:4.0992 train_time:87879ms step_avg:176.11ms
step:510/5100 train_loss:4.0415 train_time:88451ms step_avg:176.90ms
step:511/5100 train_loss:3.8377 train_time:88538ms step_avg:176.72ms
step:512/5100 train_loss:4.0492 train_time:88680ms step_avg:176.65ms
step:513/5100 train_loss:3.9877 train_time:88823ms step_avg:176.59ms
step:514/5100 train_loss:3.9539 train_time:88965ms step_avg:176.52ms
step:515/5100 train_loss:4.0549 train_time:89104ms step_avg:176.44ms
step:516/5100 train_loss:4.0070 train_time:89245ms step_avg:176.37ms
step:517/5100 train_loss:4.3534 train_time:89384ms step_avg:176.30ms
step:518/5100 train_loss:3.9520 train_time:89535ms step_avg:176.25ms
step:519/5100 train_loss:4.0612 train_time:89676ms step_avg:176.18ms
step:520/5100 train_loss:3.9566 train_time:90248ms step_avg:176.96ms
step:521/5100 train_loss:3.9526 train_time:90332ms step_avg:176.77ms
step:522/5100 train_loss:3.8994 train_time:90469ms step_avg:176.70ms
step:523/5100 train_loss:3.9105 train_time:90612ms step_avg:176.63ms
step:524/5100 train_loss:4.5255 train_time:90751ms step_avg:176.56ms
step:525/5100 train_loss:4.0132 train_time:90892ms step_avg:176.49ms
step:526/5100 train_loss:3.9499 train_time:91035ms step_avg:176.42ms
step:527/5100 train_loss:3.9629 train_time:91173ms step_avg:176.35ms
step:528/5100 train_loss:3.9102 train_time:91320ms step_avg:176.29ms
step:529/5100 train_loss:3.8827 train_time:91468ms step_avg:176.24ms
step:530/5100 train_loss:4.1047 train_time:92038ms step_avg:177.00ms
step:531/5100 train_loss:3.8973 train_time:92121ms step_avg:176.82ms
step:532/5100 train_loss:4.1860 train_time:92264ms step_avg:176.75ms
step:533/5100 train_loss:3.9985 train_time:92405ms step_avg:176.68ms
step:534/5100 train_loss:3.9209 train_time:92544ms step_avg:176.61ms
step:535/5100 train_loss:3.9378 train_time:92684ms step_avg:176.54ms
step:536/5100 train_loss:3.8759 train_time:92825ms step_avg:176.47ms
step:537/5100 train_loss:4.0041 train_time:92968ms step_avg:176.41ms
step:538/5100 train_loss:4.0037 train_time:93113ms step_avg:176.35ms
step:539/5100 train_loss:3.9017 train_time:93257ms step_avg:176.29ms
step:540/5100 train_loss:4.3932 train_time:93828ms step_avg:177.03ms
step:541/5100 train_loss:3.9292 train_time:93911ms step_avg:176.86ms
step:542/5100 train_loss:4.0466 train_time:94057ms step_avg:176.80ms
step:543/5100 train_loss:3.8698 train_time:94193ms step_avg:176.72ms
step:544/5100 train_loss:3.8459 train_time:94336ms step_avg:176.66ms
step:545/5100 train_loss:3.9261 train_time:94476ms step_avg:176.59ms
step:546/5100 train_loss:3.8522 train_time:94611ms step_avg:176.51ms
step:547/5100 train_loss:3.9027 train_time:94754ms step_avg:176.45ms
step:548/5100 train_loss:3.9196 train_time:94900ms step_avg:176.39ms
step:549/5100 train_loss:3.9014 train_time:95043ms step_avg:176.33ms
step:550/5100 train_loss:3.9863 train_time:95614ms step_avg:177.06ms
step:551/5100 train_loss:3.8648 train_time:95697ms step_avg:176.89ms
step:552/5100 train_loss:3.8819 train_time:95838ms step_avg:176.82ms
step:553/5100 train_loss:4.2135 train_time:95974ms step_avg:176.75ms
step:554/5100 train_loss:4.0101 train_time:96114ms step_avg:176.68ms
step:555/5100 train_loss:3.9669 train_time:96254ms step_avg:176.61ms
step:556/5100 train_loss:3.9231 train_time:96393ms step_avg:176.54ms
step:557/5100 train_loss:3.9499 train_time:96536ms step_avg:176.48ms
step:558/5100 train_loss:3.6092 train_time:96683ms step_avg:176.43ms
step:559/5100 train_loss:3.8627 train_time:96827ms step_avg:176.37ms
step:560/5100 train_loss:3.9091 train_time:97392ms step_avg:177.08ms
step:561/5100 train_loss:3.9600 train_time:97476ms step_avg:176.91ms
step:562/5100 train_loss:3.8632 train_time:97617ms step_avg:176.84ms
step:563/5100 train_loss:3.8041 train_time:97758ms step_avg:176.78ms
step:564/5100 train_loss:4.0100 train_time:97902ms step_avg:176.72ms
step:565/5100 train_loss:3.8325 train_time:98036ms step_avg:176.64ms
step:566/5100 train_loss:3.9455 train_time:98175ms step_avg:176.57ms
step:567/5100 train_loss:3.8926 train_time:98400ms step_avg:176.66ms
step:568/5100 train_loss:3.8445 train_time:98537ms step_avg:176.59ms
step:569/5100 train_loss:3.9456 train_time:98676ms step_avg:176.52ms
step:570/5100 train_loss:3.9160 train_time:99450ms step_avg:177.59ms
step:571/5100 train_loss:3.9451 train_time:99522ms step_avg:177.40ms
step:572/5100 train_loss:4.0269 train_time:99662ms step_avg:177.33ms
step:573/5100 train_loss:3.9766 train_time:99803ms step_avg:177.27ms
step:574/5100 train_loss:3.9746 train_time:99946ms step_avg:177.21ms
step:575/5100 train_loss:4.0354 train_time:100090ms step_avg:177.15ms
step:576/5100 train_loss:3.9946 train_time:100231ms step_avg:177.09ms
step:577/5100 train_loss:4.0071 train_time:100371ms step_avg:177.02ms
step:578/5100 train_loss:3.9391 train_time:100518ms step_avg:176.97ms
step:579/5100 train_loss:3.9283 train_time:100664ms step_avg:176.91ms
step:580/5100 train_loss:3.9203 train_time:101239ms step_avg:177.61ms
step:581/5100 train_loss:3.8587 train_time:101319ms step_avg:177.44ms
step:582/5100 train_loss:3.8807 train_time:101459ms step_avg:177.38ms
step:583/5100 train_loss:4.1172 train_time:101601ms step_avg:177.31ms
step:584/5100 train_loss:3.8772 train_time:101741ms step_avg:177.25ms
step:585/5100 train_loss:3.8351 train_time:101881ms step_avg:177.18ms
step:586/5100 train_loss:4.0263 train_time:102022ms step_avg:177.12ms
step:587/5100 train_loss:3.7758 train_time:102165ms step_avg:177.06ms
step:588/5100 train_loss:3.9195 train_time:102315ms step_avg:177.02ms
step:589/5100 train_loss:3.9059 train_time:102456ms step_avg:176.95ms
step:590/5100 train_loss:4.2544 train_time:103026ms step_avg:177.63ms
step:591/5100 train_loss:4.0307 train_time:103111ms step_avg:177.47ms
step:592/5100 train_loss:3.7687 train_time:103251ms step_avg:177.41ms
step:593/5100 train_loss:3.7867 train_time:103396ms step_avg:177.35ms
step:594/5100 train_loss:3.7753 train_time:103531ms step_avg:177.28ms
step:595/5100 train_loss:3.8140 train_time:103671ms step_avg:177.22ms
step:596/5100 train_loss:4.1666 train_time:103811ms step_avg:177.15ms
step:597/5100 train_loss:3.8954 train_time:103954ms step_avg:177.09ms
step:598/5100 train_loss:3.8354 train_time:104102ms step_avg:177.04ms
step:599/5100 train_loss:3.9163 train_time:104242ms step_avg:176.98ms
step:600/5100 train_loss:3.7299 train_time:104814ms step_avg:177.65ms
step:601/5100 train_loss:3.8512 train_time:104902ms step_avg:177.50ms
step:602/5100 train_loss:3.8759 train_time:105038ms step_avg:177.43ms
step:603/5100 train_loss:3.8970 train_time:105179ms step_avg:177.37ms
step:604/5100 train_loss:4.0254 train_time:105320ms step_avg:177.31ms
step:605/5100 train_loss:3.8832 train_time:105464ms step_avg:177.25ms
step:606/5100 train_loss:3.8673 train_time:105604ms step_avg:177.19ms
step:607/5100 train_loss:3.8119 train_time:105744ms step_avg:177.12ms
step:608/5100 train_loss:4.0640 train_time:105891ms step_avg:177.08ms
step:609/5100 train_loss:3.9059 train_time:106033ms step_avg:177.02ms
step:610/5100 train_loss:3.8693 train_time:106603ms step_avg:177.67ms
step:611/5100 train_loss:3.9701 train_time:106685ms step_avg:177.51ms
step:612/5100 train_loss:3.8659 train_time:106826ms step_avg:177.45ms
step:613/5100 train_loss:3.8494 train_time:106966ms step_avg:177.39ms
step:614/5100 train_loss:4.0133 train_time:107108ms step_avg:177.33ms
step:615/5100 train_loss:3.9808 train_time:107246ms step_avg:177.27ms
step:616/5100 train_loss:3.9338 train_time:107386ms step_avg:177.20ms
step:617/5100 train_loss:3.8688 train_time:107527ms step_avg:177.14ms
step:618/5100 train_loss:3.8164 train_time:107674ms step_avg:177.09ms
step:619/5100 train_loss:3.9193 train_time:107822ms step_avg:177.05ms
step:620/5100 train_loss:3.8362 train_time:108384ms step_avg:177.68ms
step:621/5100 train_loss:3.8355 train_time:108469ms step_avg:177.53ms
step:622/5100 train_loss:4.1440 train_time:108611ms step_avg:177.47ms
step:623/5100 train_loss:3.8349 train_time:108754ms step_avg:177.41ms
step:624/5100 train_loss:3.8716 train_time:108897ms step_avg:177.36ms
step:625/5100 train_loss:3.9455 train_time:109031ms step_avg:177.29ms
step:625/5100 val_loss:3.8760 train_time:109093ms step_avg:177.39ms
step:626/5100 train_loss:3.9739 train_time:109180ms step_avg:177.24ms
step:627/5100 train_loss:3.9981 train_time:109329ms step_avg:177.19ms
step:628/5100 train_loss:3.9728 train_time:109471ms step_avg:177.14ms
step:629/5100 train_loss:4.0252 train_time:109612ms step_avg:177.08ms
step:630/5100 train_loss:3.8436 train_time:110183ms step_avg:177.71ms
step:631/5100 train_loss:3.9643 train_time:110267ms step_avg:177.56ms
step:632/5100 train_loss:3.9972 train_time:110405ms step_avg:177.50ms
step:633/5100 train_loss:3.9005 train_time:110545ms step_avg:177.44ms
step:634/5100 train_loss:3.8286 train_time:110685ms step_avg:177.38ms
step:635/5100 train_loss:3.9332 train_time:110825ms step_avg:177.32ms
step:636/5100 train_loss:4.1826 train_time:110966ms step_avg:177.26ms
step:637/5100 train_loss:3.7795 train_time:111106ms step_avg:177.20ms
step:638/5100 train_loss:3.6030 train_time:111262ms step_avg:177.17ms
step:639/5100 train_loss:3.8262 train_time:111400ms step_avg:177.11ms
step:640/5100 train_loss:3.8574 train_time:111968ms step_avg:177.73ms
step:641/5100 train_loss:3.8242 train_time:112052ms step_avg:177.58ms
step:642/5100 train_loss:3.8178 train_time:112194ms step_avg:177.52ms
step:643/5100 train_loss:3.8689 train_time:112335ms step_avg:177.47ms
step:644/5100 train_loss:3.8866 train_time:112477ms step_avg:177.41ms
step:645/5100 train_loss:3.8040 train_time:112617ms step_avg:177.35ms
step:646/5100 train_loss:4.0217 train_time:112756ms step_avg:177.29ms
step:647/5100 train_loss:3.9173 train_time:112898ms step_avg:177.23ms
step:648/5100 train_loss:3.9130 train_time:113045ms step_avg:177.19ms
step:649/5100 train_loss:3.9455 train_time:113187ms step_avg:177.13ms
step:650/5100 train_loss:4.0084 train_time:113753ms step_avg:177.74ms
step:651/5100 train_loss:3.8600 train_time:113835ms step_avg:177.59ms
step:652/5100 train_loss:4.0059 train_time:113977ms step_avg:177.53ms
step:653/5100 train_loss:3.8329 train_time:114117ms step_avg:177.48ms
step:654/5100 train_loss:3.9047 train_time:114257ms step_avg:177.42ms
step:655/5100 train_loss:3.6760 train_time:114398ms step_avg:177.36ms
step:656/5100 train_loss:3.8129 train_time:114539ms step_avg:177.30ms
step:657/5100 train_loss:3.8242 train_time:114681ms step_avg:177.25ms
step:658/5100 train_loss:3.7597 train_time:114827ms step_avg:177.20ms
step:659/5100 train_loss:3.9377 train_time:114971ms step_avg:177.15ms
step:660/5100 train_loss:3.8438 train_time:115541ms step_avg:177.75ms
step:661/5100 train_loss:3.9240 train_time:115622ms step_avg:177.61ms
step:662/5100 train_loss:3.9986 train_time:115767ms step_avg:177.56ms
step:663/5100 train_loss:3.9090 train_time:115904ms step_avg:177.49ms
step:664/5100 train_loss:3.7910 train_time:116046ms step_avg:177.44ms
step:665/5100 train_loss:3.8798 train_time:116191ms step_avg:177.39ms
step:666/5100 train_loss:3.7390 train_time:116325ms step_avg:177.33ms
step:667/5100 train_loss:4.0331 train_time:116471ms step_avg:177.28ms
step:668/5100 train_loss:3.8694 train_time:116613ms step_avg:177.22ms
step:669/5100 train_loss:3.8696 train_time:116758ms step_avg:177.17ms
step:670/5100 train_loss:3.7219 train_time:117327ms step_avg:177.77ms
step:671/5100 train_loss:3.8398 train_time:117411ms step_avg:177.63ms
step:672/5100 train_loss:3.7943 train_time:117551ms step_avg:177.57ms
step:673/5100 train_loss:3.8187 train_time:117691ms step_avg:177.51ms
step:674/5100 train_loss:4.0909 train_time:117831ms step_avg:177.46ms
step:675/5100 train_loss:3.8870 train_time:117974ms step_avg:177.40ms
step:676/5100 train_loss:3.9545 train_time:118113ms step_avg:177.35ms
step:677/5100 train_loss:3.7370 train_time:118255ms step_avg:177.29ms
step:678/5100 train_loss:3.8411 train_time:118402ms step_avg:177.25ms
step:679/5100 train_loss:3.7826 train_time:118548ms step_avg:177.20ms
step:680/5100 train_loss:3.9282 train_time:119113ms step_avg:177.78ms
step:681/5100 train_loss:3.8283 train_time:119199ms step_avg:177.64ms
step:682/5100 train_loss:3.8594 train_time:119339ms step_avg:177.59ms
step:683/5100 train_loss:3.9243 train_time:119480ms step_avg:177.53ms
step:684/5100 train_loss:3.9758 train_time:119619ms step_avg:177.48ms
step:685/5100 train_loss:3.8704 train_time:119761ms step_avg:177.42ms
step:686/5100 train_loss:3.9557 train_time:119901ms step_avg:177.37ms
step:687/5100 train_loss:3.8774 train_time:120044ms step_avg:177.32ms
step:688/5100 train_loss:3.9213 train_time:120189ms step_avg:177.27ms
step:689/5100 train_loss:3.5704 train_time:120331ms step_avg:177.22ms
step:690/5100 train_loss:3.6715 train_time:120906ms step_avg:177.80ms
step:691/5100 train_loss:3.8029 train_time:120990ms step_avg:177.67ms
step:692/5100 train_loss:3.6839 train_time:121131ms step_avg:177.61ms
step:693/5100 train_loss:3.8920 train_time:121276ms step_avg:177.56ms
step:694/5100 train_loss:3.9107 train_time:121413ms step_avg:177.50ms
step:695/5100 train_loss:3.7953 train_time:121555ms step_avg:177.45ms
step:696/5100 train_loss:3.7792 train_time:121698ms step_avg:177.40ms
step:697/5100 train_loss:4.0961 train_time:121837ms step_avg:177.35ms
step:698/5100 train_loss:3.8475 train_time:121984ms step_avg:177.30ms
step:699/5100 train_loss:3.8877 train_time:122126ms step_avg:177.25ms
step:700/5100 train_loss:4.0562 train_time:122695ms step_avg:177.82ms
step:701/5100 train_loss:3.8190 train_time:122782ms step_avg:177.69ms
step:702/5100 train_loss:3.7741 train_time:122920ms step_avg:177.63ms
step:703/5100 train_loss:3.7655 train_time:123060ms step_avg:177.58ms
step:704/5100 train_loss:3.7179 train_time:123201ms step_avg:177.52ms
step:705/5100 train_loss:3.8115 train_time:123340ms step_avg:177.47ms
step:706/5100 train_loss:3.8061 train_time:123482ms step_avg:177.42ms
step:707/5100 train_loss:3.8215 train_time:123620ms step_avg:177.36ms
step:708/5100 train_loss:3.8867 train_time:123770ms step_avg:177.32ms
step:709/5100 train_loss:3.8409 train_time:123912ms step_avg:177.27ms
step:710/5100 train_loss:3.8269 train_time:124482ms step_avg:177.83ms
step:711/5100 train_loss:3.7936 train_time:124566ms step_avg:177.70ms
step:712/5100 train_loss:3.8225 train_time:124709ms step_avg:177.65ms
step:713/5100 train_loss:3.8833 train_time:124845ms step_avg:177.59ms
step:714/5100 train_loss:3.8946 train_time:124987ms step_avg:177.54ms
step:715/5100 train_loss:3.8197 train_time:125125ms step_avg:177.48ms
step:716/5100 train_loss:3.8159 train_time:125264ms step_avg:177.43ms
step:717/5100 train_loss:3.8276 train_time:125406ms step_avg:177.38ms
step:718/5100 train_loss:3.9812 train_time:125556ms step_avg:177.34ms
step:719/5100 train_loss:3.8376 train_time:125698ms step_avg:177.29ms
step:720/5100 train_loss:3.9119 train_time:126264ms step_avg:177.84ms
step:721/5100 train_loss:4.0645 train_time:126349ms step_avg:177.71ms
step:722/5100 train_loss:3.6991 train_time:126490ms step_avg:177.65ms
step:723/5100 train_loss:3.9603 train_time:126627ms step_avg:177.60ms
step:724/5100 train_loss:4.0233 train_time:126766ms step_avg:177.54ms
step:725/5100 train_loss:3.8028 train_time:126906ms step_avg:177.49ms
step:726/5100 train_loss:3.8859 train_time:127046ms step_avg:177.44ms
step:727/5100 train_loss:3.7855 train_time:127187ms step_avg:177.39ms
step:728/5100 train_loss:3.7993 train_time:127334ms step_avg:177.34ms
step:729/5100 train_loss:3.9849 train_time:127481ms step_avg:177.30ms
step:730/5100 train_loss:3.9257 train_time:128043ms step_avg:177.84ms
step:731/5100 train_loss:3.9212 train_time:128126ms step_avg:177.71ms
step:732/5100 train_loss:3.8035 train_time:128266ms step_avg:177.65ms
step:733/5100 train_loss:3.8304 train_time:128406ms step_avg:177.60ms
step:734/5100 train_loss:4.0737 train_time:128546ms step_avg:177.55ms
step:735/5100 train_loss:3.8032 train_time:128689ms step_avg:177.50ms
step:736/5100 train_loss:3.8569 train_time:128826ms step_avg:177.45ms
step:737/5100 train_loss:3.9808 train_time:128966ms step_avg:177.40ms
step:738/5100 train_loss:3.8994 train_time:129114ms step_avg:177.35ms
step:739/5100 train_loss:3.8483 train_time:129258ms step_avg:177.31ms
step:740/5100 train_loss:3.7342 train_time:129824ms step_avg:177.84ms
step:741/5100 train_loss:4.3854 train_time:129907ms step_avg:177.71ms
step:742/5100 train_loss:3.7384 train_time:130052ms step_avg:177.67ms
step:743/5100 train_loss:3.8232 train_time:130190ms step_avg:177.61ms
step:744/5100 train_loss:3.8225 train_time:130328ms step_avg:177.56ms
step:745/5100 train_loss:3.8850 train_time:130467ms step_avg:177.51ms
step:746/5100 train_loss:3.8608 train_time:130607ms step_avg:177.45ms
step:747/5100 train_loss:3.8393 train_time:130747ms step_avg:177.40ms
step:748/5100 train_loss:3.8732 train_time:130895ms step_avg:177.36ms
step:749/5100 train_loss:3.8003 train_time:131036ms step_avg:177.32ms
step:750/5100 train_loss:3.8058 train_time:131604ms step_avg:177.84ms
step:750/5100 val_loss:3.8140 train_time:131611ms step_avg:177.85ms
step:751/5100 train_loss:3.8435 train_time:131699ms step_avg:177.73ms
step:752/5100 train_loss:3.8034 train_time:131845ms step_avg:177.69ms
step:753/5100 train_loss:3.8376 train_time:131988ms step_avg:177.64ms
step:754/5100 train_loss:3.8637 train_time:132129ms step_avg:177.59ms
step:755/5100 train_loss:3.8239 train_time:132269ms step_avg:177.54ms
step:756/5100 train_loss:3.9045 train_time:132501ms step_avg:177.61ms
step:757/5100 train_loss:3.7300 train_time:132629ms step_avg:177.55ms
step:758/5100 train_loss:3.9721 train_time:132771ms step_avg:177.50ms
step:759/5100 train_loss:3.8932 train_time:132910ms step_avg:177.45ms
step:760/5100 train_loss:3.8192 train_time:133610ms step_avg:178.15ms
step:761/5100 train_loss:3.9247 train_time:133678ms step_avg:178.00ms
step:762/5100 train_loss:3.6368 train_time:133820ms step_avg:177.95ms
step:763/5100 train_loss:3.7929 train_time:133965ms step_avg:177.91ms
step:764/5100 train_loss:3.9137 train_time:134106ms step_avg:177.86ms
step:765/5100 train_loss:3.5618 train_time:134246ms step_avg:177.81ms
step:766/5100 train_loss:3.9757 train_time:134389ms step_avg:177.76ms
step:767/5100 train_loss:3.8342 train_time:134529ms step_avg:177.71ms
step:768/5100 train_loss:3.7997 train_time:134680ms step_avg:177.68ms
step:769/5100 train_loss:3.8173 train_time:134819ms step_avg:177.63ms
step:770/5100 train_loss:3.8346 train_time:135389ms step_avg:178.14ms
step:771/5100 train_loss:3.8961 train_time:135469ms step_avg:178.01ms
step:772/5100 train_loss:4.1167 train_time:135609ms step_avg:177.96ms
step:773/5100 train_loss:3.6944 train_time:135750ms step_avg:177.92ms
step:774/5100 train_loss:3.8985 train_time:135889ms step_avg:177.87ms
step:775/5100 train_loss:3.8727 train_time:136030ms step_avg:177.82ms
step:776/5100 train_loss:3.8378 train_time:136173ms step_avg:177.77ms
step:777/5100 train_loss:3.6505 train_time:136313ms step_avg:177.72ms
step:778/5100 train_loss:3.6400 train_time:136460ms step_avg:177.68ms
step:779/5100 train_loss:3.7176 train_time:136600ms step_avg:177.63ms
step:780/5100 train_loss:3.8053 train_time:137167ms step_avg:178.14ms
step:781/5100 train_loss:3.8394 train_time:137251ms step_avg:178.02ms
step:782/5100 train_loss:3.8915 train_time:137391ms step_avg:177.97ms
step:783/5100 train_loss:3.8075 train_time:137530ms step_avg:177.92ms
step:784/5100 train_loss:3.8143 train_time:137670ms step_avg:177.87ms
step:785/5100 train_loss:3.8061 train_time:137810ms step_avg:177.82ms
step:786/5100 train_loss:3.7869 train_time:137953ms step_avg:177.77ms
step:787/5100 train_loss:3.6899 train_time:138090ms step_avg:177.72ms
step:788/5100 train_loss:3.9857 train_time:138238ms step_avg:177.68ms
step:789/5100 train_loss:3.7293 train_time:138380ms step_avg:177.64ms
step:790/5100 train_loss:3.8046 train_time:138932ms step_avg:178.12ms
step:791/5100 train_loss:3.8646 train_time:139030ms step_avg:178.02ms
step:792/5100 train_loss:4.0008 train_time:139171ms step_avg:177.97ms
step:793/5100 train_loss:4.0073 train_time:139313ms step_avg:177.92ms
step:794/5100 train_loss:3.7154 train_time:139453ms step_avg:177.87ms
step:795/5100 train_loss:3.8410 train_time:139591ms step_avg:177.82ms
step:796/5100 train_loss:3.8916 train_time:139731ms step_avg:177.78ms
step:797/5100 train_loss:4.0034 train_time:139872ms step_avg:177.73ms
step:798/5100 train_loss:3.7615 train_time:140021ms step_avg:177.69ms
step:799/5100 train_loss:3.8951 train_time:140162ms step_avg:177.64ms
step:800/5100 train_loss:3.8049 train_time:140728ms step_avg:178.14ms
step:801/5100 train_loss:3.7858 train_time:140816ms step_avg:178.02ms
step:802/5100 train_loss:3.8793 train_time:140958ms step_avg:177.98ms
step:803/5100 train_loss:3.7352 train_time:141097ms step_avg:177.93ms
step:804/5100 train_loss:3.7706 train_time:141238ms step_avg:177.88ms
step:805/5100 train_loss:3.8762 train_time:141380ms step_avg:177.84ms
step:806/5100 train_loss:3.7750 train_time:141518ms step_avg:177.79ms
step:807/5100 train_loss:3.7833 train_time:141661ms step_avg:177.74ms
step:808/5100 train_loss:3.8840 train_time:141805ms step_avg:177.70ms
step:809/5100 train_loss:3.8040 train_time:141953ms step_avg:177.66ms
step:810/5100 train_loss:3.7279 train_time:142518ms step_avg:178.15ms
step:811/5100 train_loss:3.8083 train_time:142602ms step_avg:178.03ms
step:812/5100 train_loss:3.8350 train_time:142740ms step_avg:177.98ms
step:813/5100 train_loss:3.8306 train_time:142880ms step_avg:177.93ms
step:814/5100 train_loss:3.8671 train_time:143022ms step_avg:177.89ms
step:815/5100 train_loss:3.8126 train_time:143163ms step_avg:177.84ms
step:816/5100 train_loss:3.7981 train_time:143300ms step_avg:177.79ms
step:817/5100 train_loss:3.8900 train_time:143441ms step_avg:177.75ms
step:818/5100 train_loss:4.0008 train_time:143589ms step_avg:177.71ms
step:819/5100 train_loss:3.7625 train_time:143732ms step_avg:177.67ms
step:820/5100 train_loss:3.9588 train_time:144300ms step_avg:178.15ms
step:821/5100 train_loss:3.7478 train_time:144382ms step_avg:178.03ms
step:822/5100 train_loss:3.7784 train_time:144521ms step_avg:177.98ms
step:823/5100 train_loss:3.9065 train_time:144662ms step_avg:177.94ms
step:824/5100 train_loss:3.8216 train_time:144801ms step_avg:177.89ms
step:825/5100 train_loss:3.7440 train_time:144943ms step_avg:177.84ms
step:826/5100 train_loss:3.8457 train_time:145082ms step_avg:177.80ms
step:827/5100 train_loss:3.7395 train_time:145222ms step_avg:177.75ms
step:828/5100 train_loss:3.9643 train_time:145371ms step_avg:177.72ms
step:829/5100 train_loss:3.8516 train_time:145512ms step_avg:177.67ms
step:830/5100 train_loss:3.9140 train_time:146080ms step_avg:178.15ms
step:831/5100 train_loss:3.7642 train_time:146161ms step_avg:178.03ms
step:832/5100 train_loss:3.8217 train_time:146301ms step_avg:177.98ms
step:833/5100 train_loss:3.7536 train_time:146440ms step_avg:177.93ms
step:834/5100 train_loss:3.8756 train_time:146581ms step_avg:177.89ms
step:835/5100 train_loss:3.7243 train_time:146721ms step_avg:177.84ms
step:836/5100 train_loss:3.6963 train_time:146865ms step_avg:177.80ms
step:837/5100 train_loss:3.9670 train_time:147002ms step_avg:177.75ms
step:838/5100 train_loss:3.6570 train_time:147147ms step_avg:177.71ms
step:839/5100 train_loss:3.8270 train_time:147291ms step_avg:177.67ms
step:840/5100 train_loss:3.6613 train_time:147859ms step_avg:178.14ms
step:841/5100 train_loss:3.7129 train_time:147941ms step_avg:178.03ms
step:842/5100 train_loss:3.7857 train_time:148083ms step_avg:177.98ms
step:843/5100 train_loss:3.8103 train_time:148220ms step_avg:177.94ms
step:844/5100 train_loss:3.8158 train_time:148364ms step_avg:177.89ms
step:845/5100 train_loss:3.6633 train_time:148499ms step_avg:177.84ms
step:846/5100 train_loss:3.8988 train_time:148643ms step_avg:177.80ms
step:847/5100 train_loss:3.7649 train_time:148782ms step_avg:177.76ms
step:848/5100 train_loss:3.7228 train_time:148930ms step_avg:177.72ms
step:849/5100 train_loss:3.8587 train_time:149071ms step_avg:177.68ms
step:850/5100 train_loss:3.7300 train_time:149638ms step_avg:178.14ms
step:851/5100 train_loss:3.6811 train_time:149721ms step_avg:178.03ms
step:852/5100 train_loss:3.9772 train_time:149865ms step_avg:177.99ms
step:853/5100 train_loss:3.6890 train_time:150000ms step_avg:177.94ms
step:854/5100 train_loss:3.8003 train_time:150141ms step_avg:177.89ms
step:855/5100 train_loss:3.8803 train_time:150284ms step_avg:177.85ms
step:856/5100 train_loss:3.7687 train_time:150422ms step_avg:177.80ms
step:857/5100 train_loss:3.7791 train_time:150569ms step_avg:177.77ms
step:858/5100 train_loss:3.8313 train_time:150711ms step_avg:177.73ms
step:859/5100 train_loss:3.7260 train_time:150853ms step_avg:177.68ms
step:860/5100 train_loss:3.7971 train_time:151420ms step_avg:178.14ms
step:861/5100 train_loss:3.8320 train_time:151501ms step_avg:178.03ms
step:862/5100 train_loss:3.8790 train_time:151644ms step_avg:177.99ms
step:863/5100 train_loss:3.8231 train_time:151783ms step_avg:177.94ms
step:864/5100 train_loss:3.8069 train_time:151923ms step_avg:177.90ms
step:865/5100 train_loss:3.6397 train_time:152068ms step_avg:177.86ms
step:866/5100 train_loss:3.8257 train_time:152204ms step_avg:177.81ms
step:867/5100 train_loss:4.1171 train_time:152355ms step_avg:177.78ms
step:868/5100 train_loss:3.6837 train_time:152493ms step_avg:177.73ms
step:869/5100 train_loss:3.8709 train_time:152636ms step_avg:177.69ms
step:870/5100 train_loss:3.8510 train_time:153203ms step_avg:178.14ms
step:871/5100 train_loss:3.6849 train_time:153286ms step_avg:178.03ms
step:872/5100 train_loss:3.6609 train_time:153428ms step_avg:177.99ms
step:873/5100 train_loss:3.8969 train_time:153571ms step_avg:177.95ms
step:874/5100 train_loss:3.6819 train_time:153708ms step_avg:177.90ms
step:875/5100 train_loss:3.3938 train_time:153849ms step_avg:177.86ms
step:875/5100 val_loss:3.7599 train_time:153910ms step_avg:177.93ms
step:876/5100 train_loss:3.8749 train_time:153996ms step_avg:177.82ms
step:877/5100 train_loss:3.6859 train_time:154148ms step_avg:177.79ms
step:878/5100 train_loss:3.8603 train_time:154292ms step_avg:177.76ms
step:879/5100 train_loss:3.7175 train_time:154433ms step_avg:177.71ms
step:880/5100 train_loss:3.8929 train_time:154997ms step_avg:178.16ms
step:881/5100 train_loss:3.5519 train_time:155078ms step_avg:178.05ms
step:882/5100 train_loss:3.7352 train_time:155219ms step_avg:178.00ms
step:883/5100 train_loss:3.9232 train_time:155360ms step_avg:177.96ms
step:884/5100 train_loss:4.0805 train_time:155497ms step_avg:177.91ms
step:885/5100 train_loss:3.8049 train_time:155641ms step_avg:177.88ms
step:886/5100 train_loss:3.7199 train_time:155794ms step_avg:177.85ms
step:887/5100 train_loss:3.8122 train_time:155919ms step_avg:177.79ms
step:888/5100 train_loss:4.3170 train_time:156064ms step_avg:177.75ms
step:889/5100 train_loss:4.0696 train_time:156210ms step_avg:177.71ms
step:890/5100 train_loss:3.7580 train_time:156775ms step_avg:178.15ms
step:891/5100 train_loss:3.7643 train_time:156862ms step_avg:178.05ms
step:892/5100 train_loss:3.5967 train_time:157003ms step_avg:178.01ms
step:893/5100 train_loss:3.9334 train_time:157145ms step_avg:177.97ms
step:894/5100 train_loss:3.6621 train_time:157284ms step_avg:177.92ms
step:895/5100 train_loss:3.9132 train_time:157425ms step_avg:177.88ms
step:896/5100 train_loss:3.9246 train_time:157566ms step_avg:177.84ms
step:897/5100 train_loss:3.7360 train_time:157706ms step_avg:177.80ms
step:898/5100 train_loss:3.7653 train_time:157853ms step_avg:177.76ms
step:899/5100 train_loss:3.8234 train_time:157995ms step_avg:177.72ms
step:900/5100 train_loss:3.7149 train_time:158566ms step_avg:178.16ms
step:901/5100 train_loss:3.6542 train_time:158650ms step_avg:178.06ms
step:902/5100 train_loss:3.8662 train_time:158791ms step_avg:178.02ms
step:903/5100 train_loss:3.8763 train_time:158931ms step_avg:177.97ms
step:904/5100 train_loss:3.7636 train_time:159072ms step_avg:177.93ms
step:905/5100 train_loss:3.7395 train_time:159214ms step_avg:177.89ms
step:906/5100 train_loss:3.7339 train_time:159355ms step_avg:177.85ms
step:907/5100 train_loss:3.9593 train_time:159496ms step_avg:177.81ms
step:908/5100 train_loss:3.7437 train_time:159643ms step_avg:177.78ms
step:909/5100 train_loss:3.7894 train_time:159783ms step_avg:177.73ms
step:910/5100 train_loss:3.6928 train_time:160349ms step_avg:178.17ms
step:911/5100 train_loss:3.7832 train_time:160433ms step_avg:178.06ms
step:912/5100 train_loss:3.8510 train_time:160574ms step_avg:178.02ms
step:913/5100 train_loss:3.8389 train_time:160715ms step_avg:177.98ms
step:914/5100 train_loss:3.7110 train_time:160855ms step_avg:177.94ms
step:915/5100 train_loss:3.9672 train_time:160996ms step_avg:177.90ms
step:916/5100 train_loss:3.7616 train_time:161136ms step_avg:177.85ms
step:917/5100 train_loss:3.8633 train_time:161277ms step_avg:177.81ms
step:918/5100 train_loss:3.8355 train_time:161427ms step_avg:177.78ms
step:919/5100 train_loss:5.0561 train_time:161566ms step_avg:177.74ms
step:920/5100 train_loss:3.7500 train_time:162128ms step_avg:178.16ms
step:921/5100 train_loss:3.8008 train_time:162214ms step_avg:178.06ms
step:922/5100 train_loss:3.7629 train_time:162355ms step_avg:178.02ms
step:923/5100 train_loss:3.8245 train_time:162496ms step_avg:177.98ms
step:924/5100 train_loss:3.8283 train_time:162636ms step_avg:177.94ms
step:925/5100 train_loss:3.9129 train_time:162777ms step_avg:177.90ms
step:926/5100 train_loss:3.8844 train_time:162916ms step_avg:177.86ms
step:927/5100 train_loss:3.7890 train_time:163056ms step_avg:177.81ms
step:928/5100 train_loss:3.7716 train_time:163205ms step_avg:177.78ms
step:929/5100 train_loss:4.0009 train_time:163346ms step_avg:177.74ms
step:930/5100 train_loss:3.8445 train_time:163911ms step_avg:178.16ms
step:931/5100 train_loss:3.6323 train_time:163993ms step_avg:178.06ms
step:932/5100 train_loss:3.7200 train_time:164136ms step_avg:178.02ms
step:933/5100 train_loss:3.9039 train_time:164274ms step_avg:177.98ms
step:934/5100 train_loss:3.6538 train_time:164414ms step_avg:177.94ms
step:935/5100 train_loss:3.7998 train_time:164556ms step_avg:177.90ms
step:936/5100 train_loss:3.6814 train_time:164695ms step_avg:177.86ms
step:937/5100 train_loss:3.7393 train_time:164835ms step_avg:177.82ms
step:938/5100 train_loss:3.8434 train_time:164982ms step_avg:177.78ms
step:939/5100 train_loss:3.7743 train_time:165127ms step_avg:177.75ms
step:940/5100 train_loss:3.9316 train_time:165688ms step_avg:178.16ms
step:941/5100 train_loss:3.7142 train_time:165780ms step_avg:178.07ms
step:942/5100 train_loss:3.7769 train_time:165917ms step_avg:178.02ms
step:943/5100 train_loss:3.5801 train_time:166058ms step_avg:177.98ms
step:944/5100 train_loss:3.9223 train_time:166197ms step_avg:177.94ms
step:945/5100 train_loss:3.6412 train_time:166420ms step_avg:177.99ms
step:946/5100 train_loss:3.6550 train_time:166555ms step_avg:177.94ms
step:947/5100 train_loss:5.2627 train_time:166697ms step_avg:177.90ms
step:948/5100 train_loss:3.8223 train_time:166836ms step_avg:177.86ms
step:949/5100 train_loss:3.7182 train_time:166976ms step_avg:177.82ms
step:950/5100 train_loss:3.6255 train_time:167668ms step_avg:178.37ms
step:951/5100 train_loss:3.6800 train_time:167741ms step_avg:178.26ms
step:952/5100 train_loss:3.6382 train_time:167889ms step_avg:178.23ms
step:953/5100 train_loss:3.7036 train_time:168035ms step_avg:178.19ms
step:954/5100 train_loss:3.7852 train_time:168176ms step_avg:178.15ms
step:955/5100 train_loss:3.6614 train_time:168315ms step_avg:178.11ms
step:956/5100 train_loss:3.6999 train_time:168456ms step_avg:178.07ms
step:957/5100 train_loss:3.6680 train_time:168598ms step_avg:178.03ms
step:958/5100 train_loss:3.7349 train_time:168743ms step_avg:178.00ms
step:959/5100 train_loss:3.7231 train_time:168885ms step_avg:177.96ms
step:960/5100 train_loss:3.7379 train_time:169451ms step_avg:178.37ms
step:961/5100 train_loss:3.6199 train_time:169539ms step_avg:178.27ms
step:962/5100 train_loss:3.8855 train_time:169679ms step_avg:178.23ms
step:963/5100 train_loss:3.8409 train_time:169820ms step_avg:178.20ms
step:964/5100 train_loss:3.7399 train_time:169960ms step_avg:178.15ms
step:965/5100 train_loss:3.6806 train_time:170101ms step_avg:178.12ms
step:966/5100 train_loss:3.7186 train_time:170241ms step_avg:178.08ms
step:967/5100 train_loss:3.9448 train_time:170383ms step_avg:178.04ms
step:968/5100 train_loss:3.7653 train_time:170529ms step_avg:178.01ms
step:969/5100 train_loss:3.7553 train_time:170675ms step_avg:177.97ms
step:970/5100 train_loss:3.8089 train_time:171241ms step_avg:178.38ms
step:971/5100 train_loss:3.6243 train_time:171328ms step_avg:178.28ms
step:972/5100 train_loss:3.7729 train_time:171470ms step_avg:178.24ms
step:973/5100 train_loss:3.7342 train_time:171608ms step_avg:178.20ms
step:974/5100 train_loss:3.7736 train_time:171748ms step_avg:178.16ms
step:975/5100 train_loss:3.8441 train_time:171890ms step_avg:178.12ms
step:976/5100 train_loss:3.7202 train_time:172030ms step_avg:178.09ms
step:977/5100 train_loss:3.9120 train_time:172176ms step_avg:178.05ms
step:978/5100 train_loss:3.7999 train_time:172325ms step_avg:178.02ms
step:979/5100 train_loss:3.6287 train_time:172462ms step_avg:177.98ms
step:980/5100 train_loss:3.9230 train_time:173026ms step_avg:178.38ms
step:981/5100 train_loss:3.6527 train_time:173111ms step_avg:178.28ms
step:982/5100 train_loss:3.8152 train_time:173251ms step_avg:178.24ms
step:983/5100 train_loss:3.7961 train_time:173392ms step_avg:178.20ms
step:984/5100 train_loss:3.8115 train_time:173533ms step_avg:178.17ms
step:985/5100 train_loss:3.7396 train_time:173674ms step_avg:178.13ms
step:986/5100 train_loss:3.8297 train_time:173814ms step_avg:178.09ms
step:987/5100 train_loss:3.6496 train_time:173955ms step_avg:178.05ms
step:988/5100 train_loss:3.7222 train_time:174102ms step_avg:178.02ms
step:989/5100 train_loss:3.7134 train_time:174245ms step_avg:177.98ms
step:990/5100 train_loss:3.6600 train_time:174808ms step_avg:178.38ms
step:991/5100 train_loss:3.8692 train_time:174896ms step_avg:178.28ms
step:992/5100 train_loss:3.6964 train_time:175040ms step_avg:178.25ms
step:993/5100 train_loss:3.6673 train_time:175176ms step_avg:178.21ms
step:994/5100 train_loss:3.7473 train_time:175316ms step_avg:178.17ms
step:995/5100 train_loss:3.8312 train_time:175459ms step_avg:178.13ms
step:996/5100 train_loss:3.7762 train_time:175599ms step_avg:178.09ms
step:997/5100 train_loss:3.6824 train_time:175742ms step_avg:178.06ms
step:998/5100 train_loss:4.0472 train_time:175886ms step_avg:178.02ms
step:999/5100 train_loss:3.6972 train_time:176027ms step_avg:177.98ms
step:1000/5100 train_loss:3.8194 train_time:176590ms step_avg:178.37ms
step:1000/5100 val_loss:3.7153 train_time:176602ms step_avg:178.39ms
step:1001/5100 train_loss:3.6839 train_time:176692ms step_avg:178.30ms
step:1002/5100 train_loss:3.7345 train_time:176839ms step_avg:178.27ms
step:1003/5100 train_loss:3.6230 train_time:176980ms step_avg:178.23ms
step:1004/5100 train_loss:3.8049 train_time:177120ms step_avg:178.19ms
step:1005/5100 train_loss:3.8593 train_time:177260ms step_avg:178.15ms
step:1006/5100 train_loss:3.6265 train_time:177404ms step_avg:178.12ms
step:1007/5100 train_loss:3.7117 train_time:177540ms step_avg:178.07ms
step:1008/5100 train_loss:3.6791 train_time:177682ms step_avg:178.04ms
step:1009/5100 train_loss:3.7992 train_time:177827ms step_avg:178.00ms
step:1010/5100 train_loss:3.9051 train_time:178388ms step_avg:178.39ms
step:1011/5100 train_loss:3.7969 train_time:178482ms step_avg:178.30ms
step:1012/5100 train_loss:3.7534 train_time:178624ms step_avg:178.27ms
step:1013/5100 train_loss:3.6220 train_time:178763ms step_avg:178.23ms
step:1014/5100 train_loss:3.7599 train_time:178902ms step_avg:178.19ms
step:1015/5100 train_loss:3.8704 train_time:179043ms step_avg:178.15ms
step:1016/5100 train_loss:3.5832 train_time:179184ms step_avg:178.12ms
step:1017/5100 train_loss:3.6811 train_time:179324ms step_avg:178.08ms
step:1018/5100 train_loss:3.6771 train_time:179471ms step_avg:178.05ms
step:1019/5100 train_loss:3.6223 train_time:179615ms step_avg:178.01ms
step:1020/5100 train_loss:3.7669 train_time:180180ms step_avg:178.40ms
step:1021/5100 train_loss:3.6817 train_time:180267ms step_avg:178.31ms
step:1022/5100 train_loss:3.6058 train_time:180410ms step_avg:178.27ms
step:1023/5100 train_loss:3.7193 train_time:180545ms step_avg:178.23ms
step:1024/5100 train_loss:3.7487 train_time:180685ms step_avg:178.19ms
step:1025/5100 train_loss:3.7187 train_time:180827ms step_avg:178.16ms
step:1026/5100 train_loss:3.7286 train_time:180966ms step_avg:178.12ms
step:1027/5100 train_loss:3.8992 train_time:181109ms step_avg:178.08ms
step:1028/5100 train_loss:3.5779 train_time:181253ms step_avg:178.05ms
step:1029/5100 train_loss:3.6341 train_time:181395ms step_avg:178.01ms
step:1030/5100 train_loss:3.5990 train_time:181956ms step_avg:178.39ms
step:1031/5100 train_loss:3.7543 train_time:182050ms step_avg:178.31ms
step:1032/5100 train_loss:3.7457 train_time:182191ms step_avg:178.27ms
step:1033/5100 train_loss:3.9255 train_time:182331ms step_avg:178.23ms
step:1034/5100 train_loss:3.7374 train_time:182473ms step_avg:178.20ms
step:1035/5100 train_loss:3.6813 train_time:182616ms step_avg:178.16ms
step:1036/5100 train_loss:3.6741 train_time:182753ms step_avg:178.12ms
step:1037/5100 train_loss:3.7340 train_time:182895ms step_avg:178.09ms
step:1038/5100 train_loss:4.0530 train_time:183043ms step_avg:178.06ms
step:1039/5100 train_loss:3.8683 train_time:183186ms step_avg:178.02ms
step:1040/5100 train_loss:3.7619 train_time:183746ms step_avg:178.39ms
step:1041/5100 train_loss:3.6625 train_time:183837ms step_avg:178.31ms
step:1042/5100 train_loss:3.7184 train_time:183977ms step_avg:178.27ms
step:1043/5100 train_loss:3.7674 train_time:184120ms step_avg:178.24ms
step:1044/5100 train_loss:3.6881 train_time:184258ms step_avg:178.20ms
step:1045/5100 train_loss:3.6953 train_time:184397ms step_avg:178.16ms
step:1046/5100 train_loss:3.7836 train_time:184538ms step_avg:178.13ms
step:1047/5100 train_loss:3.6827 train_time:184678ms step_avg:178.09ms
step:1048/5100 train_loss:3.8941 train_time:184827ms step_avg:178.06ms
step:1049/5100 train_loss:3.7405 train_time:184967ms step_avg:178.02ms
step:1050/5100 train_loss:3.6697 train_time:185529ms step_avg:178.39ms
step:1051/5100 train_loss:3.6343 train_time:185617ms step_avg:178.31ms
step:1052/5100 train_loss:3.7564 train_time:185755ms step_avg:178.27ms
step:1053/5100 train_loss:3.6267 train_time:185895ms step_avg:178.23ms
step:1054/5100 train_loss:3.9498 train_time:186036ms step_avg:178.20ms
step:1055/5100 train_loss:3.7924 train_time:186176ms step_avg:178.16ms
step:1056/5100 train_loss:3.6464 train_time:186320ms step_avg:178.13ms
step:1057/5100 train_loss:3.7500 train_time:186458ms step_avg:178.09ms
step:1058/5100 train_loss:3.8209 train_time:186606ms step_avg:178.06ms
step:1059/5100 train_loss:3.5507 train_time:186747ms step_avg:178.02ms
step:1060/5100 train_loss:3.6758 train_time:187308ms step_avg:178.39ms
step:1061/5100 train_loss:3.7029 train_time:187401ms step_avg:178.31ms
step:1062/5100 train_loss:3.6601 train_time:187537ms step_avg:178.27ms
step:1063/5100 train_loss:3.6381 train_time:187676ms step_avg:178.23ms
step:1064/5100 train_loss:3.7373 train_time:187820ms step_avg:178.20ms
step:1065/5100 train_loss:3.6384 train_time:187956ms step_avg:178.16ms
step:1066/5100 train_loss:3.6232 train_time:188096ms step_avg:178.12ms
step:1067/5100 train_loss:3.6456 train_time:188240ms step_avg:178.09ms
step:1068/5100 train_loss:3.5636 train_time:188387ms step_avg:178.06ms
step:1069/5100 train_loss:3.6702 train_time:188529ms step_avg:178.03ms
step:1070/5100 train_loss:3.5549 train_time:189088ms step_avg:178.39ms
step:1071/5100 train_loss:3.7993 train_time:189183ms step_avg:178.31ms
step:1072/5100 train_loss:3.7491 train_time:189325ms step_avg:178.27ms
step:1073/5100 train_loss:3.7021 train_time:189463ms step_avg:178.23ms
step:1074/5100 train_loss:3.7730 train_time:189603ms step_avg:178.20ms
step:1075/5100 train_loss:3.7248 train_time:189743ms step_avg:178.16ms
step:1076/5100 train_loss:3.6449 train_time:189882ms step_avg:178.13ms
step:1077/5100 train_loss:4.0391 train_time:190028ms step_avg:178.10ms
step:1078/5100 train_loss:3.7236 train_time:190171ms step_avg:178.06ms
step:1079/5100 train_loss:3.3999 train_time:190315ms step_avg:178.03ms
step:1080/5100 train_loss:3.7776 train_time:190877ms step_avg:178.39ms
step:1081/5100 train_loss:3.7021 train_time:190970ms step_avg:178.31ms
step:1082/5100 train_loss:3.7695 train_time:191107ms step_avg:178.27ms
step:1083/5100 train_loss:3.8677 train_time:191247ms step_avg:178.24ms
step:1084/5100 train_loss:3.7565 train_time:191388ms step_avg:178.20ms
step:1085/5100 train_loss:3.7321 train_time:191529ms step_avg:178.17ms
step:1086/5100 train_loss:3.6934 train_time:191669ms step_avg:178.13ms
step:1087/5100 train_loss:3.8883 train_time:191809ms step_avg:178.10ms
step:1088/5100 train_loss:3.7850 train_time:191955ms step_avg:178.07ms
step:1089/5100 train_loss:3.6123 train_time:192098ms step_avg:178.03ms
step:1090/5100 train_loss:3.6365 train_time:192661ms step_avg:178.39ms
step:1091/5100 train_loss:3.7537 train_time:192746ms step_avg:178.30ms
step:1092/5100 train_loss:3.5508 train_time:192884ms step_avg:178.27ms
step:1093/5100 train_loss:3.7487 train_time:193028ms step_avg:178.23ms
step:1094/5100 train_loss:3.8808 train_time:193166ms step_avg:178.20ms
step:1095/5100 train_loss:3.7160 train_time:193304ms step_avg:178.16ms
step:1096/5100 train_loss:3.6674 train_time:193447ms step_avg:178.13ms
step:1097/5100 train_loss:3.6959 train_time:193592ms step_avg:178.10ms
step:1098/5100 train_loss:3.7430 train_time:193737ms step_avg:178.07ms
step:1099/5100 train_loss:3.8055 train_time:193875ms step_avg:178.03ms
step:1100/5100 train_loss:3.7735 train_time:194436ms step_avg:178.38ms
step:1101/5100 train_loss:3.7100 train_time:194532ms step_avg:178.31ms
step:1102/5100 train_loss:3.5529 train_time:194671ms step_avg:178.27ms
step:1103/5100 train_loss:3.6188 train_time:194808ms step_avg:178.23ms
step:1104/5100 train_loss:3.7155 train_time:194951ms step_avg:178.20ms
step:1105/5100 train_loss:3.5826 train_time:195093ms step_avg:178.17ms
step:1106/5100 train_loss:4.3313 train_time:195231ms step_avg:178.13ms
step:1107/5100 train_loss:3.4923 train_time:195367ms step_avg:178.09ms
step:1108/5100 train_loss:3.8289 train_time:195513ms step_avg:178.06ms
step:1109/5100 train_loss:3.6077 train_time:195663ms step_avg:178.04ms
step:1110/5100 train_loss:3.7529 train_time:196215ms step_avg:178.38ms
step:1111/5100 train_loss:3.6930 train_time:196308ms step_avg:178.30ms
step:1112/5100 train_loss:3.7316 train_time:196449ms step_avg:178.27ms
step:1113/5100 train_loss:3.8295 train_time:196590ms step_avg:178.23ms
step:1114/5100 train_loss:3.6926 train_time:196734ms step_avg:178.20ms
step:1115/5100 train_loss:3.6217 train_time:196871ms step_avg:178.16ms
step:1116/5100 train_loss:3.5409 train_time:197012ms step_avg:178.13ms
step:1117/5100 train_loss:3.7012 train_time:197154ms step_avg:178.10ms
step:1118/5100 train_loss:3.8565 train_time:197302ms step_avg:178.07ms
step:1119/5100 train_loss:3.8921 train_time:197446ms step_avg:178.04ms
step:1120/5100 train_loss:3.7287 train_time:198007ms step_avg:178.38ms
step:1121/5100 train_loss:3.7586 train_time:198100ms step_avg:178.31ms
step:1122/5100 train_loss:3.6526 train_time:198240ms step_avg:178.27ms
step:1123/5100 train_loss:3.7123 train_time:198378ms step_avg:178.24ms
step:1124/5100 train_loss:3.8584 train_time:198518ms step_avg:178.20ms
step:1125/5100 train_loss:3.6232 train_time:198658ms step_avg:178.17ms
step:1125/5100 val_loss:3.6849 train_time:198720ms step_avg:178.22ms
step:1126/5100 train_loss:3.5128 train_time:198805ms step_avg:178.14ms
step:1127/5100 train_loss:3.7465 train_time:198952ms step_avg:178.11ms
step:1128/5100 train_loss:3.9598 train_time:199096ms step_avg:178.08ms
step:1129/5100 train_loss:3.4976 train_time:199238ms step_avg:178.05ms
step:1130/5100 train_loss:3.8185 train_time:199797ms step_avg:178.39ms
step:1131/5100 train_loss:3.6557 train_time:199886ms step_avg:178.31ms
step:1132/5100 train_loss:3.6787 train_time:200027ms step_avg:178.28ms
step:1133/5100 train_loss:3.6354 train_time:200170ms step_avg:178.25ms
step:1134/5100 train_loss:3.7985 train_time:200388ms step_avg:178.28ms
step:1135/5100 train_loss:3.7286 train_time:200523ms step_avg:178.24ms
step:1136/5100 train_loss:3.7796 train_time:200668ms step_avg:178.21ms
step:1137/5100 train_loss:3.8108 train_time:200804ms step_avg:178.18ms
step:1138/5100 train_loss:3.7289 train_time:200946ms step_avg:178.14ms
step:1139/5100 train_loss:3.6285 train_time:201085ms step_avg:178.11ms
step:1140/5100 train_loss:3.9343 train_time:201774ms step_avg:178.56ms
step:1141/5100 train_loss:3.7413 train_time:201856ms step_avg:178.48ms
step:1142/5100 train_loss:3.8281 train_time:202000ms step_avg:178.44ms
step:1143/5100 train_loss:3.7263 train_time:202142ms step_avg:178.41ms
step:1144/5100 train_loss:3.6302 train_time:202283ms step_avg:178.38ms
step:1145/5100 train_loss:3.7418 train_time:202426ms step_avg:178.35ms
step:1146/5100 train_loss:3.8654 train_time:202572ms step_avg:178.32ms
step:1147/5100 train_loss:3.8184 train_time:202708ms step_avg:178.28ms
step:1148/5100 train_loss:3.7642 train_time:202856ms step_avg:178.26ms
step:1149/5100 train_loss:3.7719 train_time:202999ms step_avg:178.23ms
step:1150/5100 train_loss:3.6231 train_time:203558ms step_avg:178.56ms
step:1151/5100 train_loss:3.6289 train_time:203651ms step_avg:178.48ms
step:1152/5100 train_loss:3.6012 train_time:203790ms step_avg:178.45ms
step:1153/5100 train_loss:3.7488 train_time:203929ms step_avg:178.42ms
step:1154/5100 train_loss:3.7176 train_time:204069ms step_avg:178.38ms
step:1155/5100 train_loss:3.7862 train_time:204208ms step_avg:178.35ms
step:1156/5100 train_loss:3.6320 train_time:204348ms step_avg:178.31ms
step:1157/5100 train_loss:3.8005 train_time:204489ms step_avg:178.28ms
step:1158/5100 train_loss:3.7581 train_time:204637ms step_avg:178.26ms
step:1159/5100 train_loss:3.5773 train_time:204778ms step_avg:178.22ms
step:1160/5100 train_loss:3.6097 train_time:205338ms step_avg:178.55ms
step:1161/5100 train_loss:3.5951 train_time:205429ms step_avg:178.48ms
step:1162/5100 train_loss:3.4236 train_time:205569ms step_avg:178.44ms
step:1163/5100 train_loss:3.7163 train_time:205709ms step_avg:178.41ms
step:1164/5100 train_loss:3.6789 train_time:205852ms step_avg:178.38ms
step:1165/5100 train_loss:3.5477 train_time:205989ms step_avg:178.35ms
step:1166/5100 train_loss:3.5472 train_time:206129ms step_avg:178.31ms
step:1167/5100 train_loss:3.6491 train_time:206269ms step_avg:178.28ms
step:1168/5100 train_loss:3.6574 train_time:206416ms step_avg:178.25ms
step:1169/5100 train_loss:3.9795 train_time:206558ms step_avg:178.22ms
step:1170/5100 train_loss:3.6636 train_time:207114ms step_avg:178.55ms
step:1171/5100 train_loss:3.6745 train_time:207207ms step_avg:178.47ms
step:1172/5100 train_loss:3.6120 train_time:207347ms step_avg:178.44ms
step:1173/5100 train_loss:3.6747 train_time:207487ms step_avg:178.41ms
step:1174/5100 train_loss:3.8141 train_time:207627ms step_avg:178.37ms
step:1175/5100 train_loss:3.6534 train_time:207767ms step_avg:178.34ms
step:1176/5100 train_loss:3.6750 train_time:207908ms step_avg:178.31ms
step:1177/5100 train_loss:3.7259 train_time:208048ms step_avg:178.28ms
step:1178/5100 train_loss:3.7110 train_time:208197ms step_avg:178.25ms
step:1179/5100 train_loss:3.7649 train_time:208337ms step_avg:178.22ms
step:1180/5100 train_loss:3.6786 train_time:208894ms step_avg:178.54ms
step:1181/5100 train_loss:3.6783 train_time:208986ms step_avg:178.47ms
step:1182/5100 train_loss:3.6224 train_time:209127ms step_avg:178.44ms
step:1183/5100 train_loss:3.7016 train_time:209268ms step_avg:178.40ms
step:1184/5100 train_loss:3.6080 train_time:209407ms step_avg:178.37ms
step:1185/5100 train_loss:3.7736 train_time:209548ms step_avg:178.34ms
step:1186/5100 train_loss:3.8331 train_time:209688ms step_avg:178.31ms
step:1187/5100 train_loss:3.6296 train_time:209829ms step_avg:178.27ms
step:1188/5100 train_loss:3.6855 train_time:209977ms step_avg:178.25ms
step:1189/5100 train_loss:3.7116 train_time:210117ms step_avg:178.22ms
step:1190/5100 train_loss:3.5567 train_time:210678ms step_avg:178.54ms
step:1191/5100 train_loss:3.7271 train_time:210767ms step_avg:178.46ms
step:1192/5100 train_loss:3.8703 train_time:210907ms step_avg:178.43ms
step:1193/5100 train_loss:3.6681 train_time:211048ms step_avg:178.40ms
step:1194/5100 train_loss:3.5499 train_time:211188ms step_avg:178.37ms
step:1195/5100 train_loss:3.8456 train_time:211327ms step_avg:178.34ms
step:1196/5100 train_loss:3.6514 train_time:211468ms step_avg:178.30ms
step:1197/5100 train_loss:3.6618 train_time:211608ms step_avg:178.27ms
step:1198/5100 train_loss:3.5609 train_time:211757ms step_avg:178.25ms
step:1199/5100 train_loss:3.5709 train_time:211898ms step_avg:178.22ms
step:1200/5100 train_loss:3.6245 train_time:212458ms step_avg:178.54ms
step:1201/5100 train_loss:3.7053 train_time:212550ms step_avg:178.46ms
step:1202/5100 train_loss:3.7736 train_time:212689ms step_avg:178.43ms
step:1203/5100 train_loss:3.8876 train_time:212829ms step_avg:178.40ms
step:1204/5100 train_loss:3.6924 train_time:212969ms step_avg:178.37ms
step:1205/5100 train_loss:3.6198 train_time:213110ms step_avg:178.33ms
step:1206/5100 train_loss:3.6970 train_time:213250ms step_avg:178.30ms
step:1207/5100 train_loss:3.7533 train_time:213391ms step_avg:178.27ms
step:1208/5100 train_loss:3.7955 train_time:213539ms step_avg:178.25ms
step:1209/5100 train_loss:3.6826 train_time:213683ms step_avg:178.22ms
step:1210/5100 train_loss:3.5305 train_time:214243ms step_avg:178.54ms
step:1211/5100 train_loss:3.5845 train_time:214332ms step_avg:178.46ms
step:1212/5100 train_loss:3.6852 train_time:214472ms step_avg:178.43ms
step:1213/5100 train_loss:3.6939 train_time:214612ms step_avg:178.40ms
step:1214/5100 train_loss:3.7231 train_time:214753ms step_avg:178.37ms
step:1215/5100 train_loss:3.6196 train_time:214894ms step_avg:178.33ms
step:1216/5100 train_loss:3.6730 train_time:215034ms step_avg:178.30ms
step:1217/5100 train_loss:3.6178 train_time:215175ms step_avg:178.27ms
step:1218/5100 train_loss:3.6155 train_time:215322ms step_avg:178.25ms
step:1219/5100 train_loss:3.7121 train_time:215466ms step_avg:178.22ms
step:1220/5100 train_loss:3.5587 train_time:216025ms step_avg:178.53ms
step:1221/5100 train_loss:3.7798 train_time:216114ms step_avg:178.46ms
step:1222/5100 train_loss:3.8012 train_time:216254ms step_avg:178.43ms
step:1223/5100 train_loss:3.7294 train_time:216394ms step_avg:178.40ms
step:1224/5100 train_loss:3.5731 train_time:216536ms step_avg:178.37ms
step:1225/5100 train_loss:3.5711 train_time:216674ms step_avg:178.33ms
step:1226/5100 train_loss:3.6428 train_time:216814ms step_avg:178.30ms
step:1227/5100 train_loss:3.6308 train_time:216955ms step_avg:178.27ms
step:1228/5100 train_loss:3.5590 train_time:217103ms step_avg:178.25ms
step:1229/5100 train_loss:3.7437 train_time:217248ms step_avg:178.22ms
step:1230/5100 train_loss:3.6602 train_time:217802ms step_avg:178.53ms
step:1231/5100 train_loss:3.7229 train_time:217897ms step_avg:178.46ms
step:1232/5100 train_loss:3.8694 train_time:218037ms step_avg:178.43ms
step:1233/5100 train_loss:3.7783 train_time:218179ms step_avg:178.40ms
step:1234/5100 train_loss:3.7073 train_time:218319ms step_avg:178.37ms
step:1235/5100 train_loss:3.8663 train_time:218459ms step_avg:178.33ms
step:1236/5100 train_loss:3.6327 train_time:218599ms step_avg:178.30ms
step:1237/5100 train_loss:3.5969 train_time:218739ms step_avg:178.27ms
step:1238/5100 train_loss:3.5439 train_time:218885ms step_avg:178.25ms
step:1239/5100 train_loss:3.6227 train_time:219027ms step_avg:178.22ms
step:1240/5100 train_loss:3.6243 train_time:219587ms step_avg:178.53ms
step:1241/5100 train_loss:3.6649 train_time:219683ms step_avg:178.46ms
step:1242/5100 train_loss:3.7190 train_time:219820ms step_avg:178.43ms
step:1243/5100 train_loss:3.5873 train_time:219959ms step_avg:178.39ms
step:1244/5100 train_loss:3.6868 train_time:220099ms step_avg:178.36ms
step:1245/5100 train_loss:3.7049 train_time:220240ms step_avg:178.33ms
step:1246/5100 train_loss:3.7035 train_time:220383ms step_avg:178.30ms
step:1247/5100 train_loss:3.5283 train_time:220523ms step_avg:178.27ms
step:1248/5100 train_loss:3.6793 train_time:220671ms step_avg:178.25ms
step:1249/5100 train_loss:3.7402 train_time:220812ms step_avg:178.22ms
step:1250/5100 train_loss:3.7011 train_time:221372ms step_avg:178.53ms
step:1250/5100 val_loss:3.6521 train_time:221387ms step_avg:178.54ms
step:1251/5100 train_loss:3.6012 train_time:221471ms step_avg:178.46ms
step:1252/5100 train_loss:3.8077 train_time:221622ms step_avg:178.44ms
step:1253/5100 train_loss:3.6765 train_time:221761ms step_avg:178.41ms
step:1254/5100 train_loss:3.5992 train_time:221902ms step_avg:178.38ms
step:1255/5100 train_loss:3.7325 train_time:222042ms step_avg:178.35ms
step:1256/5100 train_loss:3.8037 train_time:222184ms step_avg:178.32ms
step:1257/5100 train_loss:3.6118 train_time:222325ms step_avg:178.29ms
step:1258/5100 train_loss:3.6371 train_time:222469ms step_avg:178.26ms
step:1259/5100 train_loss:3.6531 train_time:222613ms step_avg:178.23ms
step:1260/5100 train_loss:3.6366 train_time:223174ms step_avg:178.54ms
step:1261/5100 train_loss:3.4940 train_time:223272ms step_avg:178.47ms
step:1262/5100 train_loss:3.5918 train_time:223412ms step_avg:178.44ms
step:1263/5100 train_loss:3.6631 train_time:223555ms step_avg:178.42ms
step:1264/5100 train_loss:3.5140 train_time:223693ms step_avg:178.38ms
step:1265/5100 train_loss:3.7336 train_time:223832ms step_avg:178.35ms
step:1266/5100 train_loss:3.7163 train_time:223973ms step_avg:178.32ms
step:1267/5100 train_loss:3.7244 train_time:224114ms step_avg:178.29ms
step:1268/5100 train_loss:3.6690 train_time:224263ms step_avg:178.27ms
step:1269/5100 train_loss:3.7006 train_time:224406ms step_avg:178.24ms
step:1270/5100 train_loss:3.5564 train_time:224968ms step_avg:178.55ms
step:1271/5100 train_loss:3.3990 train_time:225062ms step_avg:178.48ms
step:1272/5100 train_loss:3.6832 train_time:225203ms step_avg:178.45ms
step:1273/5100 train_loss:3.6434 train_time:225344ms step_avg:178.42ms
step:1274/5100 train_loss:3.7003 train_time:225485ms step_avg:178.39ms
step:1275/5100 train_loss:3.6405 train_time:225626ms step_avg:178.36ms
step:1276/5100 train_loss:3.7347 train_time:225765ms step_avg:178.33ms
step:1277/5100 train_loss:3.7642 train_time:225906ms step_avg:178.30ms
step:1278/5100 train_loss:3.7153 train_time:226055ms step_avg:178.28ms
step:1279/5100 train_loss:3.7064 train_time:226199ms step_avg:178.25ms
step:1280/5100 train_loss:3.5437 train_time:226754ms step_avg:178.55ms
step:1281/5100 train_loss:3.6664 train_time:226845ms step_avg:178.48ms
step:1282/5100 train_loss:3.7214 train_time:226985ms step_avg:178.45ms
step:1283/5100 train_loss:3.7571 train_time:227126ms step_avg:178.42ms
step:1284/5100 train_loss:3.6451 train_time:227266ms step_avg:178.39ms
step:1285/5100 train_loss:3.6766 train_time:227406ms step_avg:178.36ms
step:1286/5100 train_loss:3.6509 train_time:227546ms step_avg:178.33ms
step:1287/5100 train_loss:3.6378 train_time:227690ms step_avg:178.30ms
step:1288/5100 train_loss:3.7658 train_time:227835ms step_avg:178.27ms
step:1289/5100 train_loss:3.6022 train_time:227976ms step_avg:178.25ms
step:1290/5100 train_loss:3.6820 train_time:228534ms step_avg:178.54ms
step:1291/5100 train_loss:3.7554 train_time:228622ms step_avg:178.47ms
step:1292/5100 train_loss:3.6806 train_time:228764ms step_avg:178.44ms
step:1293/5100 train_loss:3.7813 train_time:228906ms step_avg:178.41ms
step:1294/5100 train_loss:3.8060 train_time:229045ms step_avg:178.38ms
step:1295/5100 train_loss:3.7682 train_time:229185ms step_avg:178.35ms
step:1296/5100 train_loss:3.5834 train_time:229326ms step_avg:178.33ms
step:1297/5100 train_loss:3.6571 train_time:229467ms step_avg:178.30ms
step:1298/5100 train_loss:3.5582 train_time:229616ms step_avg:178.27ms
step:1299/5100 train_loss:3.6337 train_time:229754ms step_avg:178.24ms
step:1300/5100 train_loss:3.6944 train_time:230316ms step_avg:178.54ms
step:1301/5100 train_loss:3.7001 train_time:230401ms step_avg:178.47ms
step:1302/5100 train_loss:3.7095 train_time:230543ms step_avg:178.44ms
step:1303/5100 train_loss:3.8613 train_time:230684ms step_avg:178.41ms
step:1304/5100 train_loss:3.6331 train_time:230824ms step_avg:178.38ms
step:1305/5100 train_loss:3.8463 train_time:230965ms step_avg:178.35ms
step:1306/5100 train_loss:3.5734 train_time:231106ms step_avg:178.32ms
step:1307/5100 train_loss:3.7535 train_time:231246ms step_avg:178.29ms
step:1308/5100 train_loss:3.7609 train_time:231396ms step_avg:178.27ms
step:1309/5100 train_loss:3.6228 train_time:231536ms step_avg:178.24ms
step:1310/5100 train_loss:3.5888 train_time:232093ms step_avg:178.53ms
step:1311/5100 train_loss:3.6337 train_time:232181ms step_avg:178.46ms
step:1312/5100 train_loss:3.5781 train_time:232321ms step_avg:178.43ms
step:1313/5100 train_loss:3.7047 train_time:232468ms step_avg:178.41ms
step:1314/5100 train_loss:3.6458 train_time:232601ms step_avg:178.38ms
step:1315/5100 train_loss:3.3649 train_time:232744ms step_avg:178.35ms
step:1316/5100 train_loss:3.5982 train_time:232883ms step_avg:178.32ms
step:1317/5100 train_loss:3.6764 train_time:233025ms step_avg:178.29ms
step:1318/5100 train_loss:3.7055 train_time:233174ms step_avg:178.27ms
step:1319/5100 train_loss:3.5782 train_time:233315ms step_avg:178.24ms
step:1320/5100 train_loss:3.7246 train_time:233869ms step_avg:178.53ms
step:1321/5100 train_loss:3.7731 train_time:233962ms step_avg:178.46ms
step:1322/5100 train_loss:3.6597 train_time:234104ms step_avg:178.43ms
step:1323/5100 train_loss:3.6108 train_time:234323ms step_avg:178.46ms
step:1324/5100 train_loss:3.6480 train_time:234460ms step_avg:178.43ms
step:1325/5100 train_loss:3.7352 train_time:234600ms step_avg:178.40ms
step:1326/5100 train_loss:3.7954 train_time:234740ms step_avg:178.37ms
step:1327/5100 train_loss:3.5557 train_time:234883ms step_avg:178.35ms
step:1328/5100 train_loss:3.4699 train_time:235023ms step_avg:178.32ms
step:1329/5100 train_loss:3.7757 train_time:235165ms step_avg:178.29ms
step:1330/5100 train_loss:3.6285 train_time:235857ms step_avg:178.68ms
step:1331/5100 train_loss:3.7510 train_time:235942ms step_avg:178.61ms
step:1332/5100 train_loss:3.6561 train_time:236084ms step_avg:178.58ms
step:1333/5100 train_loss:4.0629 train_time:236228ms step_avg:178.55ms
step:1334/5100 train_loss:3.7488 train_time:236372ms step_avg:178.53ms
step:1335/5100 train_loss:3.6683 train_time:236512ms step_avg:178.50ms
step:1336/5100 train_loss:3.6107 train_time:236652ms step_avg:178.47ms
step:1337/5100 train_loss:3.6091 train_time:236793ms step_avg:178.44ms
step:1338/5100 train_loss:3.8674 train_time:236942ms step_avg:178.42ms
step:1339/5100 train_loss:3.8046 train_time:237084ms step_avg:178.39ms
step:1340/5100 train_loss:3.6486 train_time:237643ms step_avg:178.68ms
step:1341/5100 train_loss:3.6023 train_time:237734ms step_avg:178.61ms
step:1342/5100 train_loss:3.9094 train_time:237876ms step_avg:178.59ms
step:1343/5100 train_loss:3.6708 train_time:238015ms step_avg:178.56ms
step:1344/5100 train_loss:3.6684 train_time:238156ms step_avg:178.53ms
step:1345/5100 train_loss:3.7307 train_time:238295ms step_avg:178.50ms
step:1346/5100 train_loss:3.6949 train_time:238435ms step_avg:178.47ms
step:1347/5100 train_loss:3.5954 train_time:238575ms step_avg:178.44ms
step:1348/5100 train_loss:3.5422 train_time:238723ms step_avg:178.42ms
step:1349/5100 train_loss:3.6438 train_time:238866ms step_avg:178.39ms
step:1350/5100 train_loss:3.5713 train_time:239429ms step_avg:178.68ms
step:1351/5100 train_loss:3.7129 train_time:239518ms step_avg:178.61ms
step:1352/5100 train_loss:3.5488 train_time:239657ms step_avg:178.58ms
step:1353/5100 train_loss:3.6164 train_time:239796ms step_avg:178.55ms
step:1354/5100 train_loss:3.7224 train_time:239936ms step_avg:178.52ms
step:1355/5100 train_loss:3.5612 train_time:240078ms step_avg:178.50ms
step:1356/5100 train_loss:3.4863 train_time:240216ms step_avg:178.47ms
step:1357/5100 train_loss:3.8335 train_time:240358ms step_avg:178.44ms
step:1358/5100 train_loss:3.7617 train_time:240504ms step_avg:178.42ms
step:1359/5100 train_loss:3.4765 train_time:240647ms step_avg:178.39ms
step:1360/5100 train_loss:3.7655 train_time:241208ms step_avg:178.67ms
step:1361/5100 train_loss:3.6503 train_time:241299ms step_avg:178.61ms
step:1362/5100 train_loss:3.5155 train_time:241444ms step_avg:178.58ms
step:1363/5100 train_loss:3.6904 train_time:241581ms step_avg:178.55ms
step:1364/5100 train_loss:3.5784 train_time:241721ms step_avg:178.52ms
step:1365/5100 train_loss:3.6046 train_time:241862ms step_avg:178.50ms
step:1366/5100 train_loss:3.6208 train_time:242004ms step_avg:178.47ms
step:1367/5100 train_loss:3.7373 train_time:242146ms step_avg:178.44ms
step:1368/5100 train_loss:3.7116 train_time:242292ms step_avg:178.42ms
step:1369/5100 train_loss:3.6705 train_time:242440ms step_avg:178.40ms
step:1370/5100 train_loss:3.5631 train_time:242989ms step_avg:178.67ms
step:1371/5100 train_loss:3.8977 train_time:243084ms step_avg:178.61ms
step:1372/5100 train_loss:3.6441 train_time:243226ms step_avg:178.58ms
step:1373/5100 train_loss:3.6750 train_time:243366ms step_avg:178.55ms
step:1374/5100 train_loss:3.6670 train_time:243507ms step_avg:178.52ms
step:1375/5100 train_loss:3.4833 train_time:243648ms step_avg:178.50ms
step:1375/5100 val_loss:3.6360 train_time:243709ms step_avg:178.54ms
step:1376/5100 train_loss:3.8724 train_time:243797ms step_avg:178.47ms
step:1377/5100 train_loss:3.6585 train_time:243944ms step_avg:178.45ms
step:1378/5100 train_loss:3.8058 train_time:244086ms step_avg:178.43ms
step:1379/5100 train_loss:3.8521 train_time:244228ms step_avg:178.40ms
step:1380/5100 train_loss:3.5047 train_time:244786ms step_avg:178.68ms
step:1381/5100 train_loss:3.6379 train_time:244877ms step_avg:178.61ms
step:1382/5100 train_loss:4.0783 train_time:245020ms step_avg:178.59ms
step:1383/5100 train_loss:3.5558 train_time:245159ms step_avg:178.56ms
step:1384/5100 train_loss:3.7124 train_time:245300ms step_avg:178.53ms
step:1385/5100 train_loss:3.7867 train_time:245441ms step_avg:178.50ms
step:1386/5100 train_loss:3.7023 train_time:245583ms step_avg:178.48ms
step:1387/5100 train_loss:3.6932 train_time:245723ms step_avg:178.45ms
step:1388/5100 train_loss:3.5185 train_time:245870ms step_avg:178.43ms
step:1389/5100 train_loss:3.6624 train_time:246012ms step_avg:178.40ms
step:1390/5100 train_loss:3.6283 train_time:246569ms step_avg:178.67ms
step:1391/5100 train_loss:3.9032 train_time:246659ms step_avg:178.61ms
step:1392/5100 train_loss:3.6090 train_time:246801ms step_avg:178.58ms
step:1393/5100 train_loss:3.5966 train_time:246942ms step_avg:178.56ms
step:1394/5100 train_loss:3.5690 train_time:247081ms step_avg:178.53ms
step:1395/5100 train_loss:3.8483 train_time:247222ms step_avg:178.50ms
step:1396/5100 train_loss:3.7459 train_time:247362ms step_avg:178.47ms
step:1397/5100 train_loss:3.7489 train_time:247505ms step_avg:178.45ms
step:1398/5100 train_loss:3.6105 train_time:247655ms step_avg:178.43ms
step:1399/5100 train_loss:3.5829 train_time:247794ms step_avg:178.40ms
step:1400/5100 train_loss:3.6502 train_time:248352ms step_avg:178.67ms
step:1401/5100 train_loss:3.6211 train_time:248441ms step_avg:178.61ms
step:1402/5100 train_loss:3.6409 train_time:248581ms step_avg:178.58ms
step:1403/5100 train_loss:3.6060 train_time:248722ms step_avg:178.55ms
step:1404/5100 train_loss:3.8415 train_time:248862ms step_avg:178.52ms
step:1405/5100 train_loss:3.5807 train_time:249003ms step_avg:178.50ms
step:1406/5100 train_loss:3.6334 train_time:249144ms step_avg:178.47ms
step:1407/5100 train_loss:3.6252 train_time:249284ms step_avg:178.44ms
step:1408/5100 train_loss:3.4930 train_time:249433ms step_avg:178.42ms
step:1409/5100 train_loss:3.6051 train_time:249575ms step_avg:178.40ms
step:1410/5100 train_loss:3.5975 train_time:250135ms step_avg:178.67ms
step:1411/5100 train_loss:3.5913 train_time:250223ms step_avg:178.60ms
step:1412/5100 train_loss:3.6876 train_time:250363ms step_avg:178.58ms
step:1413/5100 train_loss:3.6137 train_time:250505ms step_avg:178.55ms
step:1414/5100 train_loss:3.6643 train_time:250644ms step_avg:178.52ms
step:1415/5100 train_loss:3.6609 train_time:250784ms step_avg:178.49ms
step:1416/5100 train_loss:3.7364 train_time:250925ms step_avg:178.47ms
step:1417/5100 train_loss:3.5379 train_time:251065ms step_avg:178.44ms
step:1418/5100 train_loss:3.6059 train_time:251213ms step_avg:178.42ms
step:1419/5100 train_loss:3.7016 train_time:251353ms step_avg:178.39ms
step:1420/5100 train_loss:3.7251 train_time:251908ms step_avg:178.66ms
step:1421/5100 train_loss:3.7012 train_time:252001ms step_avg:178.60ms
step:1422/5100 train_loss:3.6790 train_time:252142ms step_avg:178.57ms
step:1423/5100 train_loss:3.6660 train_time:252283ms step_avg:178.54ms
step:1424/5100 train_loss:3.6562 train_time:252422ms step_avg:178.52ms
step:1425/5100 train_loss:3.6511 train_time:252564ms step_avg:178.49ms
step:1426/5100 train_loss:3.5270 train_time:252704ms step_avg:178.46ms
step:1427/5100 train_loss:3.6401 train_time:252845ms step_avg:178.44ms
step:1428/5100 train_loss:3.5771 train_time:252993ms step_avg:178.42ms
step:1429/5100 train_loss:3.6916 train_time:253135ms step_avg:178.39ms
step:1430/5100 train_loss:3.6631 train_time:253684ms step_avg:178.65ms
step:1431/5100 train_loss:3.5889 train_time:253779ms step_avg:178.59ms
step:1432/5100 train_loss:3.6265 train_time:253921ms step_avg:178.57ms
step:1433/5100 train_loss:3.6760 train_time:254062ms step_avg:178.54ms
step:1434/5100 train_loss:3.5405 train_time:254202ms step_avg:178.51ms
step:1435/5100 train_loss:3.6385 train_time:254343ms step_avg:178.49ms
step:1436/5100 train_loss:3.4665 train_time:254483ms step_avg:178.46ms
step:1437/5100 train_loss:3.5301 train_time:254624ms step_avg:178.43ms
step:1438/5100 train_loss:3.7287 train_time:254773ms step_avg:178.41ms
step:1439/5100 train_loss:3.6846 train_time:254914ms step_avg:178.39ms
step:1440/5100 train_loss:3.6362 train_time:255468ms step_avg:178.65ms
step:1441/5100 train_loss:3.4878 train_time:255562ms step_avg:178.59ms
step:1442/5100 train_loss:3.6620 train_time:255701ms step_avg:178.56ms
step:1443/5100 train_loss:3.7231 train_time:255844ms step_avg:178.54ms
step:1444/5100 train_loss:3.7913 train_time:255982ms step_avg:178.51ms
step:1445/5100 train_loss:3.7673 train_time:256124ms step_avg:178.48ms
step:1446/5100 train_loss:3.6460 train_time:256265ms step_avg:178.46ms
step:1447/5100 train_loss:3.5228 train_time:256404ms step_avg:178.43ms
step:1448/5100 train_loss:3.5988 train_time:256551ms step_avg:178.41ms
step:1449/5100 train_loss:3.6155 train_time:256693ms step_avg:178.38ms
step:1450/5100 train_loss:3.7447 train_time:257252ms step_avg:178.65ms
step:1451/5100 train_loss:3.7186 train_time:257343ms step_avg:178.59ms
step:1452/5100 train_loss:3.5433 train_time:257484ms step_avg:178.56ms
step:1453/5100 train_loss:3.6560 train_time:257626ms step_avg:178.54ms
step:1454/5100 train_loss:3.5705 train_time:257766ms step_avg:178.51ms
step:1455/5100 train_loss:3.5982 train_time:257905ms step_avg:178.48ms
step:1456/5100 train_loss:3.6446 train_time:258046ms step_avg:178.46ms
step:1457/5100 train_loss:3.5759 train_time:258187ms step_avg:178.43ms
step:1458/5100 train_loss:3.4853 train_time:258334ms step_avg:178.41ms
step:1459/5100 train_loss:3.7202 train_time:258477ms step_avg:178.38ms
step:1460/5100 train_loss:3.5946 train_time:259035ms step_avg:178.65ms
step:1461/5100 train_loss:3.6374 train_time:259129ms step_avg:178.59ms
step:1462/5100 train_loss:3.7689 train_time:259267ms step_avg:178.56ms
step:1463/5100 train_loss:3.5864 train_time:259409ms step_avg:178.53ms
step:1464/5100 train_loss:3.7780 train_time:259547ms step_avg:178.51ms
step:1465/5100 train_loss:3.6623 train_time:259686ms step_avg:178.48ms
step:1466/5100 train_loss:3.6841 train_time:259826ms step_avg:178.45ms
step:1467/5100 train_loss:3.5975 train_time:259971ms step_avg:178.43ms
step:1468/5100 train_loss:3.7522 train_time:260115ms step_avg:178.41ms
step:1469/5100 train_loss:3.6149 train_time:260256ms step_avg:178.38ms
step:1470/5100 train_loss:3.5824 train_time:260815ms step_avg:178.64ms
step:1471/5100 train_loss:3.6363 train_time:260913ms step_avg:178.59ms
step:1472/5100 train_loss:3.5593 train_time:261051ms step_avg:178.56ms
step:1473/5100 train_loss:3.6505 train_time:261191ms step_avg:178.53ms
step:1474/5100 train_loss:3.7486 train_time:261332ms step_avg:178.51ms
step:1475/5100 train_loss:3.6312 train_time:261474ms step_avg:178.48ms
step:1476/5100 train_loss:3.4446 train_time:261613ms step_avg:178.45ms
step:1477/5100 train_loss:3.5725 train_time:261753ms step_avg:178.43ms
step:1478/5100 train_loss:3.5508 train_time:261898ms step_avg:178.40ms
step:1479/5100 train_loss:3.6358 train_time:262042ms step_avg:178.38ms
step:1480/5100 train_loss:3.7223 train_time:262598ms step_avg:178.64ms
step:1481/5100 train_loss:3.5917 train_time:262690ms step_avg:178.58ms
step:1482/5100 train_loss:3.7660 train_time:262831ms step_avg:178.55ms
step:1483/5100 train_loss:3.6916 train_time:262972ms step_avg:178.53ms
step:1484/5100 train_loss:3.5915 train_time:263110ms step_avg:178.50ms
step:1485/5100 train_loss:3.5798 train_time:263253ms step_avg:178.48ms
step:1486/5100 train_loss:3.5752 train_time:263391ms step_avg:178.45ms
step:1487/5100 train_loss:3.5525 train_time:263532ms step_avg:178.42ms
step:1488/5100 train_loss:3.6437 train_time:263682ms step_avg:178.40ms
step:1489/5100 train_loss:3.5488 train_time:263826ms step_avg:178.38ms
step:1490/5100 train_loss:3.6357 train_time:264380ms step_avg:178.64ms
step:1491/5100 train_loss:3.5810 train_time:264473ms step_avg:178.58ms
step:1492/5100 train_loss:3.5011 train_time:264613ms step_avg:178.55ms
step:1493/5100 train_loss:3.5707 train_time:264754ms step_avg:178.53ms
step:1494/5100 train_loss:3.7512 train_time:264893ms step_avg:178.50ms
step:1495/5100 train_loss:3.6079 train_time:265033ms step_avg:178.47ms
step:1496/5100 train_loss:3.3662 train_time:265172ms step_avg:178.45ms
step:1497/5100 train_loss:3.6627 train_time:265315ms step_avg:178.42ms
step:1498/5100 train_loss:3.6262 train_time:265459ms step_avg:178.40ms
step:1499/5100 train_loss:3.6692 train_time:265602ms step_avg:178.38ms
step:1500/5100 train_loss:3.6341 train_time:266160ms step_avg:178.63ms
step:1500/5100 val_loss:3.6056 train_time:266176ms step_avg:178.64ms
step:1501/5100 train_loss:3.6069 train_time:266262ms step_avg:178.58ms
step:1502/5100 train_loss:3.4033 train_time:266410ms step_avg:178.56ms
step:1503/5100 train_loss:3.6760 train_time:266552ms step_avg:178.53ms
step:1504/5100 train_loss:3.5569 train_time:266693ms step_avg:178.51ms
step:1505/5100 train_loss:3.5718 train_time:266833ms step_avg:178.48ms
step:1506/5100 train_loss:3.5273 train_time:266975ms step_avg:178.46ms
step:1507/5100 train_loss:3.6135 train_time:267116ms step_avg:178.43ms
step:1508/5100 train_loss:3.5299 train_time:267257ms step_avg:178.41ms
step:1509/5100 train_loss:3.8391 train_time:267402ms step_avg:178.39ms
step:1510/5100 train_loss:3.5813 train_time:267959ms step_avg:178.64ms
step:1511/5100 train_loss:3.5899 train_time:268058ms step_avg:178.59ms
step:1512/5100 train_loss:3.7118 train_time:268274ms step_avg:178.61ms
step:1513/5100 train_loss:3.7426 train_time:268410ms step_avg:178.58ms
step:1514/5100 train_loss:3.5966 train_time:268549ms step_avg:178.56ms
step:1515/5100 train_loss:3.4368 train_time:268690ms step_avg:178.53ms
step:1516/5100 train_loss:3.5569 train_time:268830ms step_avg:178.51ms
step:1517/5100 train_loss:3.5645 train_time:268970ms step_avg:178.48ms
step:1518/5100 train_loss:3.6412 train_time:269112ms step_avg:178.46ms
step:1519/5100 train_loss:3.5339 train_time:269256ms step_avg:178.43ms
step:1520/5100 train_loss:3.8258 train_time:269944ms step_avg:178.77ms
step:1521/5100 train_loss:3.4959 train_time:270027ms step_avg:178.71ms
step:1522/5100 train_loss:3.5510 train_time:270171ms step_avg:178.68ms
step:1523/5100 train_loss:3.6819 train_time:270312ms step_avg:178.66ms
step:1524/5100 train_loss:3.5491 train_time:270455ms step_avg:178.64ms
step:1525/5100 train_loss:3.6421 train_time:270597ms step_avg:178.61ms
step:1526/5100 train_loss:3.6365 train_time:270736ms step_avg:178.59ms
step:1527/5100 train_loss:3.6050 train_time:270878ms step_avg:178.56ms
step:1528/5100 train_loss:3.6009 train_time:271024ms step_avg:178.54ms
step:1529/5100 train_loss:3.7506 train_time:271166ms step_avg:178.52ms
step:1530/5100 train_loss:3.7229 train_time:271723ms step_avg:178.77ms
step:1531/5100 train_loss:3.5516 train_time:271816ms step_avg:178.71ms
step:1532/5100 train_loss:3.5126 train_time:271957ms step_avg:178.68ms
step:1533/5100 train_loss:3.6608 train_time:272098ms step_avg:178.66ms
step:1534/5100 train_loss:3.6242 train_time:272238ms step_avg:178.63ms
step:1535/5100 train_loss:3.6083 train_time:272380ms step_avg:178.61ms
step:1536/5100 train_loss:3.6086 train_time:272519ms step_avg:178.58ms
step:1537/5100 train_loss:3.5446 train_time:272660ms step_avg:178.56ms
step:1538/5100 train_loss:3.6028 train_time:272809ms step_avg:178.54ms
step:1539/5100 train_loss:3.7761 train_time:272951ms step_avg:178.52ms
step:1540/5100 train_loss:3.7051 train_time:273508ms step_avg:178.76ms
step:1541/5100 train_loss:3.6145 train_time:273600ms step_avg:178.71ms
step:1542/5100 train_loss:3.5653 train_time:273740ms step_avg:178.68ms
step:1543/5100 train_loss:3.5655 train_time:273881ms step_avg:178.66ms
step:1544/5100 train_loss:3.5378 train_time:274021ms step_avg:178.63ms
step:1545/5100 train_loss:3.6270 train_time:274161ms step_avg:178.61ms
step:1546/5100 train_loss:3.5860 train_time:274301ms step_avg:178.58ms
step:1547/5100 train_loss:3.5666 train_time:274441ms step_avg:178.56ms
step:1548/5100 train_loss:3.5285 train_time:274592ms step_avg:178.54ms
step:1549/5100 train_loss:3.5638 train_time:274731ms step_avg:178.51ms
step:1550/5100 train_loss:3.6791 train_time:275286ms step_avg:178.76ms
step:1551/5100 train_loss:3.6005 train_time:275376ms step_avg:178.70ms
step:1552/5100 train_loss:3.5409 train_time:275523ms step_avg:178.68ms
step:1553/5100 train_loss:3.5323 train_time:275656ms step_avg:178.65ms
step:1554/5100 train_loss:3.5263 train_time:275796ms step_avg:178.62ms
step:1555/5100 train_loss:3.6518 train_time:275937ms step_avg:178.60ms
step:1556/5100 train_loss:3.6594 train_time:276079ms step_avg:178.58ms
step:1557/5100 train_loss:3.5961 train_time:276219ms step_avg:178.55ms
step:1558/5100 train_loss:3.6505 train_time:276366ms step_avg:178.53ms
step:1559/5100 train_loss:3.5736 train_time:276511ms step_avg:178.51ms
step:1560/5100 train_loss:3.4935 train_time:277063ms step_avg:178.75ms
step:1561/5100 train_loss:3.7302 train_time:277161ms step_avg:178.70ms
step:1562/5100 train_loss:3.5519 train_time:277297ms step_avg:178.67ms
step:1563/5100 train_loss:3.5292 train_time:277438ms step_avg:178.65ms
step:1564/5100 train_loss:3.6546 train_time:277578ms step_avg:178.62ms
step:1565/5100 train_loss:3.4792 train_time:277719ms step_avg:178.60ms
step:1566/5100 train_loss:3.5388 train_time:277858ms step_avg:178.57ms
step:1567/5100 train_loss:3.6847 train_time:278000ms step_avg:178.55ms
step:1568/5100 train_loss:3.5665 train_time:278149ms step_avg:178.53ms
step:1569/5100 train_loss:3.5536 train_time:278291ms step_avg:178.51ms
step:1570/5100 train_loss:3.6489 train_time:278845ms step_avg:178.75ms
step:1571/5100 train_loss:3.6567 train_time:278941ms step_avg:178.69ms
step:1572/5100 train_loss:3.4836 train_time:279081ms step_avg:178.67ms
step:1573/5100 train_loss:3.5091 train_time:279221ms step_avg:178.64ms
step:1574/5100 train_loss:3.6317 train_time:279361ms step_avg:178.62ms
step:1575/5100 train_loss:3.4986 train_time:279502ms step_avg:178.60ms
step:1576/5100 train_loss:3.6451 train_time:279641ms step_avg:178.57ms
step:1577/5100 train_loss:3.5501 train_time:279781ms step_avg:178.55ms
step:1578/5100 train_loss:3.6055 train_time:279931ms step_avg:178.53ms
step:1579/5100 train_loss:3.5817 train_time:280076ms step_avg:178.51ms
step:1580/5100 train_loss:3.5483 train_time:280633ms step_avg:178.75ms
step:1581/5100 train_loss:3.5149 train_time:280727ms step_avg:178.69ms
step:1582/5100 train_loss:3.7527 train_time:280866ms step_avg:178.67ms
step:1583/5100 train_loss:3.5300 train_time:281007ms step_avg:178.64ms
step:1584/5100 train_loss:3.6850 train_time:281151ms step_avg:178.62ms
step:1585/5100 train_loss:3.5207 train_time:281287ms step_avg:178.59ms
step:1586/5100 train_loss:3.6831 train_time:281427ms step_avg:178.57ms
step:1587/5100 train_loss:3.4675 train_time:281570ms step_avg:178.55ms
step:1588/5100 train_loss:3.6666 train_time:281714ms step_avg:178.53ms
step:1589/5100 train_loss:3.5742 train_time:281857ms step_avg:178.50ms
step:1590/5100 train_loss:3.7312 train_time:282413ms step_avg:178.74ms
step:1591/5100 train_loss:3.5434 train_time:282511ms step_avg:178.69ms
step:1592/5100 train_loss:3.5675 train_time:282650ms step_avg:178.67ms
step:1593/5100 train_loss:3.6356 train_time:282790ms step_avg:178.64ms
step:1594/5100 train_loss:3.6102 train_time:282929ms step_avg:178.62ms
step:1595/5100 train_loss:3.5852 train_time:283072ms step_avg:178.59ms
step:1596/5100 train_loss:3.7262 train_time:283209ms step_avg:178.57ms
step:1597/5100 train_loss:3.4568 train_time:283350ms step_avg:178.54ms
step:1598/5100 train_loss:3.6138 train_time:283497ms step_avg:178.52ms
step:1599/5100 train_loss:3.6656 train_time:283638ms step_avg:178.50ms
step:1600/5100 train_loss:3.7065 train_time:284194ms step_avg:178.74ms
step:1601/5100 train_loss:3.5584 train_time:284287ms step_avg:178.68ms
step:1602/5100 train_loss:3.8491 train_time:284428ms step_avg:178.66ms
step:1603/5100 train_loss:3.7445 train_time:284566ms step_avg:178.64ms
step:1604/5100 train_loss:3.5250 train_time:284706ms step_avg:178.61ms
step:1605/5100 train_loss:3.5621 train_time:284846ms step_avg:178.59ms
step:1606/5100 train_loss:3.4420 train_time:284988ms step_avg:178.56ms
step:1607/5100 train_loss:3.7638 train_time:285129ms step_avg:178.54ms
step:1608/5100 train_loss:3.5679 train_time:285276ms step_avg:178.52ms
step:1609/5100 train_loss:3.5935 train_time:285420ms step_avg:178.50ms
step:1610/5100 train_loss:3.5430 train_time:285975ms step_avg:178.73ms
step:1611/5100 train_loss:4.1435 train_time:286068ms step_avg:178.68ms
step:1612/5100 train_loss:3.7776 train_time:286208ms step_avg:178.66ms
step:1613/5100 train_loss:3.6955 train_time:286348ms step_avg:178.63ms
step:1614/5100 train_loss:3.5656 train_time:286489ms step_avg:178.61ms
step:1615/5100 train_loss:3.6069 train_time:286628ms step_avg:178.58ms
step:1616/5100 train_loss:3.5977 train_time:286767ms step_avg:178.56ms
step:1617/5100 train_loss:3.5524 train_time:286908ms step_avg:178.54ms
step:1618/5100 train_loss:3.6296 train_time:287055ms step_avg:178.52ms
step:1619/5100 train_loss:3.5853 train_time:287198ms step_avg:178.49ms
step:1620/5100 train_loss:3.4830 train_time:287753ms step_avg:178.73ms
step:1621/5100 train_loss:3.7532 train_time:287847ms step_avg:178.68ms
step:1622/5100 train_loss:3.6462 train_time:287988ms step_avg:178.65ms
step:1623/5100 train_loss:3.4396 train_time:288129ms step_avg:178.63ms
step:1624/5100 train_loss:3.5573 train_time:288267ms step_avg:178.60ms
step:1625/5100 train_loss:3.5228 train_time:288407ms step_avg:178.58ms
step:1625/5100 val_loss:3.5889 train_time:288469ms step_avg:178.62ms
step:1626/5100 train_loss:3.5944 train_time:288554ms step_avg:178.56ms
step:1627/5100 train_loss:3.5677 train_time:288703ms step_avg:178.54ms
step:1628/5100 train_loss:3.5244 train_time:288844ms step_avg:178.52ms
step:1629/5100 train_loss:3.6345 train_time:288985ms step_avg:178.50ms
step:1630/5100 train_loss:3.5311 train_time:289540ms step_avg:178.73ms
step:1631/5100 train_loss:3.5857 train_time:289632ms step_avg:178.67ms
step:1632/5100 train_loss:3.4608 train_time:289772ms step_avg:178.65ms
step:1633/5100 train_loss:3.4312 train_time:289911ms step_avg:178.63ms
step:1634/5100 train_loss:3.5963 train_time:290051ms step_avg:178.60ms
step:1635/5100 train_loss:3.5786 train_time:290191ms step_avg:178.58ms
step:1636/5100 train_loss:3.5177 train_time:290331ms step_avg:178.56ms
step:1637/5100 train_loss:3.6110 train_time:290471ms step_avg:178.53ms
step:1638/5100 train_loss:3.6587 train_time:290618ms step_avg:178.51ms
step:1639/5100 train_loss:3.6914 train_time:290759ms step_avg:178.49ms
step:1640/5100 train_loss:3.8599 train_time:291316ms step_avg:178.72ms
step:1641/5100 train_loss:3.6806 train_time:291410ms step_avg:178.67ms
step:1642/5100 train_loss:3.5853 train_time:291551ms step_avg:178.65ms
step:1643/5100 train_loss:3.6664 train_time:291690ms step_avg:178.62ms
step:1644/5100 train_loss:3.5694 train_time:291831ms step_avg:178.60ms
step:1645/5100 train_loss:3.5895 train_time:291970ms step_avg:178.57ms
step:1646/5100 train_loss:3.5887 train_time:292110ms step_avg:178.55ms
step:1647/5100 train_loss:3.3659 train_time:292250ms step_avg:178.53ms
step:1648/5100 train_loss:3.6293 train_time:292400ms step_avg:178.51ms
step:1649/5100 train_loss:3.4951 train_time:292545ms step_avg:178.49ms
step:1650/5100 train_loss:3.5684 train_time:293102ms step_avg:178.72ms
step:1651/5100 train_loss:3.5408 train_time:293197ms step_avg:178.67ms
step:1652/5100 train_loss:3.6148 train_time:293338ms step_avg:178.65ms
step:1653/5100 train_loss:3.5464 train_time:293479ms step_avg:178.62ms
step:1654/5100 train_loss:3.6736 train_time:293621ms step_avg:178.60ms
step:1655/5100 train_loss:3.6557 train_time:293760ms step_avg:178.58ms
step:1656/5100 train_loss:3.4756 train_time:293900ms step_avg:178.55ms
step:1657/5100 train_loss:3.6286 train_time:294039ms step_avg:178.53ms
step:1658/5100 train_loss:3.5365 train_time:294184ms step_avg:178.51ms
step:1659/5100 train_loss:3.5215 train_time:294329ms step_avg:178.49ms
step:1660/5100 train_loss:3.5982 train_time:294882ms step_avg:178.72ms
step:1661/5100 train_loss:3.6201 train_time:294980ms step_avg:178.67ms
step:1662/5100 train_loss:3.5339 train_time:295120ms step_avg:178.64ms
step:1663/5100 train_loss:3.6326 train_time:295259ms step_avg:178.62ms
step:1664/5100 train_loss:3.6367 train_time:295398ms step_avg:178.60ms
step:1665/5100 train_loss:3.6708 train_time:295538ms step_avg:178.57ms
step:1666/5100 train_loss:3.6543 train_time:295678ms step_avg:178.55ms
step:1667/5100 train_loss:3.7869 train_time:295817ms step_avg:178.53ms
step:1668/5100 train_loss:3.5013 train_time:295964ms step_avg:178.51ms
step:1669/5100 train_loss:3.5738 train_time:296108ms step_avg:178.49ms
step:1670/5100 train_loss:3.5075 train_time:296658ms step_avg:178.71ms
step:1671/5100 train_loss:3.5108 train_time:296760ms step_avg:178.66ms
step:1672/5100 train_loss:3.6632 train_time:296900ms step_avg:178.64ms
step:1673/5100 train_loss:3.8497 train_time:297040ms step_avg:178.62ms
step:1674/5100 train_loss:3.5611 train_time:297180ms step_avg:178.59ms
step:1675/5100 train_loss:3.5424 train_time:297321ms step_avg:178.57ms
step:1676/5100 train_loss:3.4295 train_time:297463ms step_avg:178.55ms
step:1677/5100 train_loss:3.6312 train_time:297603ms step_avg:178.53ms
step:1678/5100 train_loss:3.5494 train_time:297749ms step_avg:178.51ms
step:1679/5100 train_loss:3.5783 train_time:297892ms step_avg:178.49ms
step:1680/5100 train_loss:3.5637 train_time:298447ms step_avg:178.71ms
step:1681/5100 train_loss:3.3730 train_time:298546ms step_avg:178.66ms
step:1682/5100 train_loss:3.5658 train_time:298686ms step_avg:178.64ms
step:1683/5100 train_loss:3.5806 train_time:298829ms step_avg:178.62ms
step:1684/5100 train_loss:3.6273 train_time:298967ms step_avg:178.59ms
step:1685/5100 train_loss:3.6276 train_time:299107ms step_avg:178.57ms
step:1686/5100 train_loss:3.5349 train_time:299248ms step_avg:178.55ms
step:1687/5100 train_loss:3.6347 train_time:299388ms step_avg:178.53ms
step:1688/5100 train_loss:3.5254 train_time:299535ms step_avg:178.51ms
step:1689/5100 train_loss:3.6093 train_time:299676ms step_avg:178.49ms
step:1690/5100 train_loss:3.5162 train_time:300229ms step_avg:178.71ms
step:1691/5100 train_loss:3.4208 train_time:300327ms step_avg:178.66ms
step:1692/5100 train_loss:3.5672 train_time:300468ms step_avg:178.64ms
step:1693/5100 train_loss:3.5695 train_time:300608ms step_avg:178.61ms
step:1694/5100 train_loss:3.4859 train_time:300748ms step_avg:178.59ms
step:1695/5100 train_loss:3.9233 train_time:300888ms step_avg:178.57ms
step:1696/5100 train_loss:3.6365 train_time:301028ms step_avg:178.55ms
step:1697/5100 train_loss:3.6203 train_time:301169ms step_avg:178.52ms
step:1698/5100 train_loss:3.5270 train_time:301317ms step_avg:178.51ms
step:1699/5100 train_loss:3.4464 train_time:301458ms step_avg:178.48ms
step:1700/5100 train_loss:3.5393 train_time:302012ms step_avg:178.71ms
step:1701/5100 train_loss:3.5226 train_time:302234ms step_avg:178.73ms
step:1702/5100 train_loss:3.5984 train_time:302369ms step_avg:178.71ms
step:1703/5100 train_loss:3.5268 train_time:302511ms step_avg:178.68ms
step:1704/5100 train_loss:3.7233 train_time:302649ms step_avg:178.66ms
step:1705/5100 train_loss:3.4941 train_time:302789ms step_avg:178.64ms
step:1706/5100 train_loss:3.7141 train_time:302929ms step_avg:178.61ms
step:1707/5100 train_loss:3.5662 train_time:303072ms step_avg:178.59ms
step:1708/5100 train_loss:3.3422 train_time:303215ms step_avg:178.57ms
step:1709/5100 train_loss:3.6718 train_time:303358ms step_avg:178.55ms
step:1710/5100 train_loss:3.5886 train_time:304044ms step_avg:178.85ms
step:1711/5100 train_loss:3.5724 train_time:304130ms step_avg:178.80ms
step:1712/5100 train_loss:3.5586 train_time:304274ms step_avg:178.77ms
step:1713/5100 train_loss:3.6002 train_time:304414ms step_avg:178.75ms
step:1714/5100 train_loss:3.6335 train_time:304558ms step_avg:178.73ms
step:1715/5100 train_loss:3.5501 train_time:304699ms step_avg:178.71ms
step:1716/5100 train_loss:3.5505 train_time:304837ms step_avg:178.69ms
step:1717/5100 train_loss:3.3958 train_time:304979ms step_avg:178.66ms
step:1718/5100 train_loss:3.5286 train_time:305127ms step_avg:178.65ms
step:1719/5100 train_loss:3.5512 train_time:305269ms step_avg:178.62ms
step:1720/5100 train_loss:3.5001 train_time:305824ms step_avg:178.84ms
step:1721/5100 train_loss:3.6531 train_time:305923ms step_avg:178.80ms
step:1722/5100 train_loss:3.4625 train_time:306063ms step_avg:178.78ms
step:1723/5100 train_loss:3.6013 train_time:306204ms step_avg:178.75ms
step:1724/5100 train_loss:3.6890 train_time:306345ms step_avg:178.73ms
step:1725/5100 train_loss:3.5375 train_time:306487ms step_avg:178.71ms
step:1726/5100 train_loss:3.7712 train_time:306626ms step_avg:178.69ms
step:1727/5100 train_loss:3.5591 train_time:306767ms step_avg:178.66ms
step:1728/5100 train_loss:3.6214 train_time:306915ms step_avg:178.65ms
step:1729/5100 train_loss:3.5959 train_time:307057ms step_avg:178.63ms
step:1730/5100 train_loss:3.6169 train_time:307615ms step_avg:178.85ms
step:1731/5100 train_loss:3.9849 train_time:307711ms step_avg:178.80ms
step:1732/5100 train_loss:3.5808 train_time:307851ms step_avg:178.78ms
step:1733/5100 train_loss:3.7061 train_time:307991ms step_avg:178.75ms
step:1734/5100 train_loss:3.4860 train_time:308131ms step_avg:178.73ms
step:1735/5100 train_loss:3.5246 train_time:308271ms step_avg:178.71ms
step:1736/5100 train_loss:3.5495 train_time:308409ms step_avg:178.68ms
step:1737/5100 train_loss:3.5334 train_time:308551ms step_avg:178.66ms
step:1738/5100 train_loss:3.6729 train_time:308700ms step_avg:178.65ms
step:1739/5100 train_loss:3.5409 train_time:308843ms step_avg:178.63ms
step:1740/5100 train_loss:3.6027 train_time:309402ms step_avg:178.85ms
step:1741/5100 train_loss:3.6553 train_time:309498ms step_avg:178.80ms
step:1742/5100 train_loss:3.4512 train_time:309648ms step_avg:178.78ms
step:1743/5100 train_loss:3.3429 train_time:309779ms step_avg:178.75ms
step:1744/5100 train_loss:3.3186 train_time:309919ms step_avg:178.73ms
step:1745/5100 train_loss:3.5760 train_time:310061ms step_avg:178.71ms
step:1746/5100 train_loss:3.5896 train_time:310200ms step_avg:178.69ms
step:1747/5100 train_loss:3.5577 train_time:310342ms step_avg:178.67ms
step:1748/5100 train_loss:3.5662 train_time:310485ms step_avg:178.65ms
step:1749/5100 train_loss:3.8085 train_time:310631ms step_avg:178.63ms
step:1750/5100 train_loss:3.5203 train_time:311190ms step_avg:178.85ms
step:1750/5100 val_loss:3.5703 train_time:311202ms step_avg:178.85ms
step:1751/5100 train_loss:3.5935 train_time:311287ms step_avg:178.80ms
step:1752/5100 train_loss:3.5768 train_time:311438ms step_avg:178.78ms
step:1753/5100 train_loss:3.2129 train_time:311579ms step_avg:178.76ms
step:1754/5100 train_loss:3.3327 train_time:311723ms step_avg:178.74ms
step:1755/5100 train_loss:3.4331 train_time:311865ms step_avg:178.72ms
step:1756/5100 train_loss:3.3835 train_time:312005ms step_avg:178.70ms
step:1757/5100 train_loss:3.5401 train_time:312143ms step_avg:178.67ms
step:1758/5100 train_loss:3.4266 train_time:312284ms step_avg:178.65ms
step:1759/5100 train_loss:3.4200 train_time:312428ms step_avg:178.63ms
step:1760/5100 train_loss:4.4841 train_time:312984ms step_avg:178.85ms
step:1761/5100 train_loss:3.5455 train_time:313080ms step_avg:178.80ms
step:1762/5100 train_loss:3.5842 train_time:313223ms step_avg:178.78ms
step:1763/5100 train_loss:3.5926 train_time:313362ms step_avg:178.76ms
step:1764/5100 train_loss:3.6124 train_time:313502ms step_avg:178.74ms
step:1765/5100 train_loss:3.5243 train_time:313642ms step_avg:178.71ms
step:1766/5100 train_loss:3.5603 train_time:313783ms step_avg:178.69ms
step:1767/5100 train_loss:3.5814 train_time:313927ms step_avg:178.67ms
step:1768/5100 train_loss:3.8294 train_time:314070ms step_avg:178.65ms
step:1769/5100 train_loss:3.5551 train_time:314212ms step_avg:178.63ms
step:1770/5100 train_loss:3.6242 train_time:314765ms step_avg:178.84ms
step:1771/5100 train_loss:4.1178 train_time:314859ms step_avg:178.80ms
step:1772/5100 train_loss:3.5832 train_time:315002ms step_avg:178.78ms
step:1773/5100 train_loss:3.4650 train_time:315143ms step_avg:178.75ms
step:1774/5100 train_loss:3.7290 train_time:315283ms step_avg:178.73ms
step:1775/5100 train_loss:3.4607 train_time:315422ms step_avg:178.71ms
step:1776/5100 train_loss:3.6243 train_time:315561ms step_avg:178.69ms
step:1777/5100 train_loss:3.6868 train_time:315701ms step_avg:178.66ms
step:1778/5100 train_loss:3.7702 train_time:315847ms step_avg:178.65ms
step:1779/5100 train_loss:3.5766 train_time:315989ms step_avg:178.63ms
step:1780/5100 train_loss:3.8673 train_time:316547ms step_avg:178.84ms
step:1781/5100 train_loss:3.6419 train_time:316639ms step_avg:178.79ms
step:1782/5100 train_loss:3.6550 train_time:316781ms step_avg:178.77ms
step:1783/5100 train_loss:3.4407 train_time:316923ms step_avg:178.75ms
step:1784/5100 train_loss:3.5211 train_time:317062ms step_avg:178.73ms
step:1785/5100 train_loss:3.6640 train_time:317202ms step_avg:178.71ms
step:1786/5100 train_loss:3.5549 train_time:317342ms step_avg:178.68ms
step:1787/5100 train_loss:3.7163 train_time:317483ms step_avg:178.66ms
step:1788/5100 train_loss:3.5375 train_time:317633ms step_avg:178.65ms
step:1789/5100 train_loss:3.5080 train_time:317775ms step_avg:178.63ms
step:1790/5100 train_loss:3.6632 train_time:318337ms step_avg:178.84ms
step:1791/5100 train_loss:3.5521 train_time:318426ms step_avg:178.79ms
step:1792/5100 train_loss:3.5050 train_time:318566ms step_avg:178.77ms
step:1793/5100 train_loss:3.6362 train_time:318706ms step_avg:178.75ms
step:1794/5100 train_loss:3.5138 train_time:318844ms step_avg:178.72ms
step:1795/5100 train_loss:3.5044 train_time:318984ms step_avg:178.70ms
step:1796/5100 train_loss:3.5522 train_time:319124ms step_avg:178.68ms
step:1797/5100 train_loss:3.5257 train_time:319265ms step_avg:178.66ms
step:1798/5100 train_loss:3.6595 train_time:319413ms step_avg:178.64ms
step:1799/5100 train_loss:3.5492 train_time:319554ms step_avg:178.62ms
step:1800/5100 train_loss:3.6199 train_time:320119ms step_avg:178.84ms
step:1801/5100 train_loss:3.5514 train_time:320206ms step_avg:178.79ms
step:1802/5100 train_loss:3.5865 train_time:320346ms step_avg:178.76ms
step:1803/5100 train_loss:3.5105 train_time:320487ms step_avg:178.74ms
step:1804/5100 train_loss:3.4304 train_time:320627ms step_avg:178.72ms
step:1805/5100 train_loss:3.6778 train_time:320767ms step_avg:178.70ms
step:1806/5100 train_loss:3.6005 train_time:320908ms step_avg:178.68ms
step:1807/5100 train_loss:3.6096 train_time:321050ms step_avg:178.66ms
step:1808/5100 train_loss:3.7181 train_time:321195ms step_avg:178.64ms
step:1809/5100 train_loss:3.5229 train_time:321339ms step_avg:178.62ms
step:1810/5100 train_loss:3.6174 train_time:321899ms step_avg:178.83ms
step:1811/5100 train_loss:3.7522 train_time:321994ms step_avg:178.79ms
step:1812/5100 train_loss:3.6096 train_time:322132ms step_avg:178.76ms
step:1813/5100 train_loss:3.6427 train_time:322271ms step_avg:178.74ms
step:1814/5100 train_loss:3.6734 train_time:322412ms step_avg:178.72ms
step:1815/5100 train_loss:3.6108 train_time:322551ms step_avg:178.70ms
step:1816/5100 train_loss:3.6552 train_time:322692ms step_avg:178.68ms
step:1817/5100 train_loss:3.6030 train_time:322832ms step_avg:178.66ms
step:1818/5100 train_loss:3.6586 train_time:322979ms step_avg:178.64ms
step:1819/5100 train_loss:3.5842 train_time:323121ms step_avg:178.62ms
step:1820/5100 train_loss:3.5784 train_time:323681ms step_avg:178.83ms
step:1821/5100 train_loss:3.5215 train_time:323776ms step_avg:178.78ms
step:1822/5100 train_loss:3.5019 train_time:323919ms step_avg:178.76ms
step:1823/5100 train_loss:3.4303 train_time:324059ms step_avg:178.74ms
step:1824/5100 train_loss:3.5838 train_time:324200ms step_avg:178.72ms
step:1825/5100 train_loss:3.7031 train_time:324341ms step_avg:178.70ms
step:1826/5100 train_loss:3.6596 train_time:324481ms step_avg:178.68ms
step:1827/5100 train_loss:3.6403 train_time:324622ms step_avg:178.66ms
step:1828/5100 train_loss:3.5065 train_time:324767ms step_avg:178.64ms
step:1829/5100 train_loss:3.5334 train_time:324910ms step_avg:178.62ms
step:1830/5100 train_loss:3.6681 train_time:325465ms step_avg:178.83ms
step:1831/5100 train_loss:3.4463 train_time:325561ms step_avg:178.78ms
step:1832/5100 train_loss:3.5954 train_time:325702ms step_avg:178.76ms
step:1833/5100 train_loss:3.4702 train_time:325842ms step_avg:178.74ms
step:1834/5100 train_loss:3.7924 train_time:325984ms step_avg:178.72ms
step:1835/5100 train_loss:3.6330 train_time:326123ms step_avg:178.70ms
step:1836/5100 train_loss:3.6179 train_time:326262ms step_avg:178.68ms
step:1837/5100 train_loss:3.7327 train_time:326404ms step_avg:178.66ms
step:1838/5100 train_loss:3.5985 train_time:326552ms step_avg:178.64ms
step:1839/5100 train_loss:3.4715 train_time:326693ms step_avg:178.62ms
step:1840/5100 train_loss:3.5966 train_time:327247ms step_avg:178.82ms
step:1841/5100 train_loss:3.4777 train_time:327344ms step_avg:178.78ms
step:1842/5100 train_loss:3.5888 train_time:327483ms step_avg:178.76ms
step:1843/5100 train_loss:3.6464 train_time:327624ms step_avg:178.74ms
step:1844/5100 train_loss:3.4083 train_time:327764ms step_avg:178.72ms
step:1845/5100 train_loss:3.5222 train_time:327904ms step_avg:178.69ms
step:1846/5100 train_loss:3.5765 train_time:328049ms step_avg:178.68ms
step:1847/5100 train_loss:3.5268 train_time:328185ms step_avg:178.65ms
step:1848/5100 train_loss:3.4174 train_time:328331ms step_avg:178.63ms
step:1849/5100 train_loss:3.6854 train_time:328473ms step_avg:178.62ms
step:1850/5100 train_loss:3.4557 train_time:329029ms step_avg:178.82ms
step:1851/5100 train_loss:3.5351 train_time:329123ms step_avg:178.77ms
step:1852/5100 train_loss:3.4951 train_time:329263ms step_avg:178.75ms
step:1853/5100 train_loss:3.6941 train_time:329403ms step_avg:178.73ms
step:1854/5100 train_loss:3.6724 train_time:329542ms step_avg:178.71ms
step:1855/5100 train_loss:3.5380 train_time:329683ms step_avg:178.69ms
step:1856/5100 train_loss:3.5020 train_time:329823ms step_avg:178.67ms
step:1857/5100 train_loss:3.5346 train_time:329964ms step_avg:178.65ms
step:1858/5100 train_loss:3.7698 train_time:330113ms step_avg:178.63ms
step:1859/5100 train_loss:3.6137 train_time:330253ms step_avg:178.61ms
step:1860/5100 train_loss:3.5552 train_time:330809ms step_avg:178.82ms
step:1861/5100 train_loss:3.5997 train_time:330903ms step_avg:178.77ms
step:1862/5100 train_loss:3.4920 train_time:331044ms step_avg:178.75ms
step:1863/5100 train_loss:3.4849 train_time:331184ms step_avg:178.73ms
step:1864/5100 train_loss:3.5579 train_time:331323ms step_avg:178.71ms
step:1865/5100 train_loss:3.5937 train_time:331463ms step_avg:178.69ms
step:1866/5100 train_loss:3.3635 train_time:331603ms step_avg:178.67ms
step:1867/5100 train_loss:3.4895 train_time:331746ms step_avg:178.65ms
step:1868/5100 train_loss:3.4429 train_time:331894ms step_avg:178.63ms
step:1869/5100 train_loss:3.4472 train_time:332035ms step_avg:178.61ms
step:1870/5100 train_loss:3.6106 train_time:332592ms step_avg:178.81ms
step:1871/5100 train_loss:3.5883 train_time:332688ms step_avg:178.77ms
step:1872/5100 train_loss:3.5337 train_time:332828ms step_avg:178.75ms
step:1873/5100 train_loss:3.5483 train_time:332968ms step_avg:178.73ms
step:1874/5100 train_loss:3.4805 train_time:333112ms step_avg:178.71ms
step:1875/5100 train_loss:3.5809 train_time:333250ms step_avg:178.69ms
step:1875/5100 val_loss:3.5556 train_time:333311ms step_avg:178.72ms
step:1876/5100 train_loss:3.5821 train_time:333397ms step_avg:178.67ms
step:1877/5100 train_loss:3.5060 train_time:333546ms step_avg:178.65ms
step:1878/5100 train_loss:3.5528 train_time:333689ms step_avg:178.63ms
step:1879/5100 train_loss:3.6548 train_time:333829ms step_avg:178.61ms
step:1880/5100 train_loss:3.5446 train_time:334381ms step_avg:178.81ms
step:1881/5100 train_loss:3.5954 train_time:334477ms step_avg:178.77ms
step:1882/5100 train_loss:3.5043 train_time:334617ms step_avg:178.75ms
step:1883/5100 train_loss:3.5793 train_time:334759ms step_avg:178.73ms
step:1884/5100 train_loss:3.5712 train_time:334898ms step_avg:178.71ms
step:1885/5100 train_loss:3.3276 train_time:335041ms step_avg:178.69ms
step:1886/5100 train_loss:3.7221 train_time:335179ms step_avg:178.67ms
step:1887/5100 train_loss:3.4643 train_time:335321ms step_avg:178.65ms
step:1888/5100 train_loss:3.4879 train_time:335470ms step_avg:178.63ms
step:1889/5100 train_loss:3.5510 train_time:335610ms step_avg:178.61ms
step:1890/5100 train_loss:3.5974 train_time:336242ms step_avg:178.85ms
step:1891/5100 train_loss:3.4253 train_time:336337ms step_avg:178.81ms
step:1892/5100 train_loss:3.6981 train_time:336478ms step_avg:178.79ms
step:1893/5100 train_loss:3.4465 train_time:336618ms step_avg:178.77ms
step:1894/5100 train_loss:3.5843 train_time:336758ms step_avg:178.75ms
step:1895/5100 train_loss:3.6241 train_time:336899ms step_avg:178.73ms
step:1896/5100 train_loss:3.4236 train_time:337038ms step_avg:178.71ms
step:1897/5100 train_loss:3.5822 train_time:337179ms step_avg:178.69ms
step:1898/5100 train_loss:3.5525 train_time:337328ms step_avg:178.67ms
step:1899/5100 train_loss:3.6292 train_time:337468ms step_avg:178.65ms
step:1900/5100 train_loss:3.4059 train_time:338152ms step_avg:178.92ms
step:1901/5100 train_loss:3.6411 train_time:338242ms step_avg:178.87ms
step:1902/5100 train_loss:3.5321 train_time:338381ms step_avg:178.85ms
step:1903/5100 train_loss:3.6852 train_time:338523ms step_avg:178.83ms
step:1904/5100 train_loss:3.4961 train_time:338665ms step_avg:178.81ms
step:1905/5100 train_loss:3.7716 train_time:338804ms step_avg:178.79ms
step:1906/5100 train_loss:3.5090 train_time:338945ms step_avg:178.77ms
step:1907/5100 train_loss:3.5009 train_time:339085ms step_avg:178.75ms
step:1908/5100 train_loss:3.5786 train_time:339232ms step_avg:178.73ms
step:1909/5100 train_loss:3.4642 train_time:339376ms step_avg:178.71ms
step:1910/5100 train_loss:3.5264 train_time:339933ms step_avg:178.91ms
step:1911/5100 train_loss:3.6155 train_time:340030ms step_avg:178.87ms
step:1912/5100 train_loss:3.5508 train_time:340171ms step_avg:178.85ms
step:1913/5100 train_loss:3.4170 train_time:340315ms step_avg:178.83ms
step:1914/5100 train_loss:3.2944 train_time:340455ms step_avg:178.81ms
step:1915/5100 train_loss:3.4945 train_time:340595ms step_avg:178.79ms
step:1916/5100 train_loss:3.7165 train_time:340735ms step_avg:178.77ms
step:1917/5100 train_loss:3.7067 train_time:340877ms step_avg:178.75ms
step:1918/5100 train_loss:3.6655 train_time:341023ms step_avg:178.73ms
step:1919/5100 train_loss:3.4926 train_time:341169ms step_avg:178.72ms
step:1920/5100 train_loss:3.7342 train_time:341719ms step_avg:178.91ms
step:1921/5100 train_loss:3.5587 train_time:341816ms step_avg:178.87ms
step:1922/5100 train_loss:3.4829 train_time:341958ms step_avg:178.85ms
step:1923/5100 train_loss:3.6640 train_time:342099ms step_avg:178.83ms
step:1924/5100 train_loss:3.6277 train_time:342238ms step_avg:178.81ms
step:1925/5100 train_loss:3.4690 train_time:342378ms step_avg:178.79ms
step:1926/5100 train_loss:3.5015 train_time:342518ms step_avg:178.77ms
step:1927/5100 train_loss:3.4142 train_time:342659ms step_avg:178.75ms
step:1928/5100 train_loss:3.5183 train_time:342806ms step_avg:178.73ms
step:1929/5100 train_loss:3.3866 train_time:342947ms step_avg:178.71ms
step:1930/5100 train_loss:3.4854 train_time:343502ms step_avg:178.91ms
step:1931/5100 train_loss:3.6214 train_time:343599ms step_avg:178.86ms
step:1932/5100 train_loss:3.4952 train_time:343740ms step_avg:178.85ms
step:1933/5100 train_loss:3.6326 train_time:343882ms step_avg:178.83ms
step:1934/5100 train_loss:3.5178 train_time:344021ms step_avg:178.80ms
step:1935/5100 train_loss:3.5617 train_time:344161ms step_avg:178.78ms
step:1936/5100 train_loss:3.5951 train_time:344301ms step_avg:178.76ms
step:1937/5100 train_loss:3.5594 train_time:344441ms step_avg:178.74ms
step:1938/5100 train_loss:3.5784 train_time:344589ms step_avg:178.73ms
step:1939/5100 train_loss:3.5051 train_time:344731ms step_avg:178.71ms
step:1940/5100 train_loss:3.6020 train_time:345286ms step_avg:178.90ms
step:1941/5100 train_loss:3.6347 train_time:345380ms step_avg:178.86ms
step:1942/5100 train_loss:3.4658 train_time:345520ms step_avg:178.84ms
step:1943/5100 train_loss:3.5039 train_time:345659ms step_avg:178.82ms
step:1944/5100 train_loss:3.5736 train_time:345799ms step_avg:178.80ms
step:1945/5100 train_loss:3.4126 train_time:345942ms step_avg:178.78ms
step:1946/5100 train_loss:3.6887 train_time:346079ms step_avg:178.76ms
step:1947/5100 train_loss:3.5584 train_time:346220ms step_avg:178.74ms
step:1948/5100 train_loss:3.5324 train_time:346368ms step_avg:178.72ms
step:1949/5100 train_loss:3.5398 train_time:346509ms step_avg:178.71ms
step:1950/5100 train_loss:3.4210 train_time:347065ms step_avg:178.90ms
step:1951/5100 train_loss:3.5399 train_time:347161ms step_avg:178.86ms
step:1952/5100 train_loss:3.3885 train_time:347308ms step_avg:178.84ms
step:1953/5100 train_loss:3.5920 train_time:347441ms step_avg:178.82ms
step:1954/5100 train_loss:3.5906 train_time:347582ms step_avg:178.80ms
step:1955/5100 train_loss:3.5339 train_time:347727ms step_avg:178.78ms
step:1956/5100 train_loss:3.4354 train_time:347862ms step_avg:178.76ms
step:1957/5100 train_loss:3.5212 train_time:348003ms step_avg:178.74ms
step:1958/5100 train_loss:3.7026 train_time:348151ms step_avg:178.72ms
step:1959/5100 train_loss:3.6238 train_time:348291ms step_avg:178.70ms
step:1960/5100 train_loss:3.6416 train_time:348849ms step_avg:178.90ms
step:1961/5100 train_loss:3.4432 train_time:348943ms step_avg:178.85ms
step:1962/5100 train_loss:3.5590 train_time:349082ms step_avg:178.83ms
step:1963/5100 train_loss:3.6039 train_time:349224ms step_avg:178.81ms
step:1964/5100 train_loss:3.5552 train_time:349363ms step_avg:178.79ms
step:1965/5100 train_loss:3.4633 train_time:349503ms step_avg:178.77ms
step:1966/5100 train_loss:3.8705 train_time:349644ms step_avg:178.75ms
step:1967/5100 train_loss:3.4869 train_time:349785ms step_avg:178.74ms
step:1968/5100 train_loss:3.5277 train_time:349935ms step_avg:178.72ms
step:1969/5100 train_loss:3.5834 train_time:350077ms step_avg:178.70ms
step:1970/5100 train_loss:3.5149 train_time:350632ms step_avg:178.89ms
step:1971/5100 train_loss:3.4198 train_time:350728ms step_avg:178.85ms
step:1972/5100 train_loss:3.4036 train_time:350873ms step_avg:178.83ms
step:1973/5100 train_loss:3.5244 train_time:351008ms step_avg:178.81ms
step:1974/5100 train_loss:3.4964 train_time:351148ms step_avg:178.79ms
step:1975/5100 train_loss:3.4593 train_time:351290ms step_avg:178.77ms
step:1976/5100 train_loss:3.6222 train_time:351427ms step_avg:178.75ms
step:1977/5100 train_loss:3.4894 train_time:351569ms step_avg:178.73ms
step:1978/5100 train_loss:3.8603 train_time:351715ms step_avg:178.72ms
step:1979/5100 train_loss:3.5476 train_time:351862ms step_avg:178.70ms
step:1980/5100 train_loss:3.5483 train_time:352414ms step_avg:178.89ms
step:1981/5100 train_loss:3.5533 train_time:352510ms step_avg:178.85ms
step:1982/5100 train_loss:3.5748 train_time:352651ms step_avg:178.83ms
step:1983/5100 train_loss:3.5076 train_time:352790ms step_avg:178.81ms
step:1984/5100 train_loss:3.4691 train_time:352931ms step_avg:178.79ms
step:1985/5100 train_loss:3.5250 train_time:353073ms step_avg:178.77ms
step:1986/5100 train_loss:3.5920 train_time:353213ms step_avg:178.75ms
step:1987/5100 train_loss:3.5718 train_time:353358ms step_avg:178.73ms
step:1988/5100 train_loss:3.5346 train_time:353504ms step_avg:178.72ms
step:1989/5100 train_loss:3.6167 train_time:353650ms step_avg:178.70ms
step:1990/5100 train_loss:3.6491 train_time:354201ms step_avg:178.89ms
step:1991/5100 train_loss:3.4238 train_time:354301ms step_avg:178.85ms
step:1992/5100 train_loss:3.4267 train_time:354443ms step_avg:178.83ms
step:1993/5100 train_loss:3.6111 train_time:354580ms step_avg:178.81ms
step:1994/5100 train_loss:3.4318 train_time:354721ms step_avg:178.79ms
step:1995/5100 train_loss:3.5279 train_time:354861ms step_avg:178.77ms
step:1996/5100 train_loss:3.5982 train_time:355000ms step_avg:178.75ms
step:1997/5100 train_loss:3.4539 train_time:355145ms step_avg:178.73ms
step:1998/5100 train_loss:3.5639 train_time:355289ms step_avg:178.72ms
step:1999/5100 train_loss:3.5653 train_time:355430ms step_avg:178.70ms
step:2000/5100 train_loss:3.4828 train_time:355984ms step_avg:178.89ms
step:2000/5100 val_loss:3.5398 train_time:356004ms step_avg:178.90ms
step:2001/5100 train_loss:3.6276 train_time:356089ms step_avg:178.85ms
step:2002/5100 train_loss:3.5784 train_time:356239ms step_avg:178.83ms
step:2003/5100 train_loss:3.6565 train_time:356381ms step_avg:178.82ms
step:2004/5100 train_loss:3.5719 train_time:356522ms step_avg:178.80ms
step:2005/5100 train_loss:3.5931 train_time:356663ms step_avg:178.78ms
step:2006/5100 train_loss:3.4817 train_time:356803ms step_avg:178.76ms
step:2007/5100 train_loss:3.5092 train_time:356947ms step_avg:178.74ms
step:2008/5100 train_loss:3.5489 train_time:357085ms step_avg:178.72ms
step:2009/5100 train_loss:3.5925 train_time:357231ms step_avg:178.70ms
step:2010/5100 train_loss:3.4922 train_time:357786ms step_avg:178.89ms
step:2011/5100 train_loss:3.5758 train_time:357883ms step_avg:178.85ms
step:2012/5100 train_loss:3.5460 train_time:358025ms step_avg:178.83ms
step:2013/5100 train_loss:3.5523 train_time:358164ms step_avg:178.81ms
step:2014/5100 train_loss:3.4695 train_time:358305ms step_avg:178.79ms
step:2015/5100 train_loss:3.5129 train_time:358446ms step_avg:178.78ms
step:2016/5100 train_loss:3.5291 train_time:358585ms step_avg:178.76ms
step:2017/5100 train_loss:3.6661 train_time:358727ms step_avg:178.74ms
step:2018/5100 train_loss:3.5099 train_time:358874ms step_avg:178.72ms
step:2019/5100 train_loss:3.6566 train_time:359014ms step_avg:178.70ms
step:2020/5100 train_loss:3.6740 train_time:359568ms step_avg:178.89ms
step:2021/5100 train_loss:3.3864 train_time:359667ms step_avg:178.85ms
step:2022/5100 train_loss:3.6156 train_time:359810ms step_avg:178.83ms
step:2023/5100 train_loss:3.5444 train_time:359947ms step_avg:178.81ms
step:2024/5100 train_loss:3.6300 train_time:360088ms step_avg:178.79ms
step:2025/5100 train_loss:3.6769 train_time:360228ms step_avg:178.77ms
step:2026/5100 train_loss:3.4617 train_time:360368ms step_avg:178.75ms
step:2027/5100 train_loss:3.5012 train_time:360510ms step_avg:178.74ms
step:2028/5100 train_loss:3.4052 train_time:360655ms step_avg:178.72ms
step:2029/5100 train_loss:3.5184 train_time:360801ms step_avg:178.70ms
step:2030/5100 train_loss:3.4408 train_time:361355ms step_avg:178.89ms
step:2031/5100 train_loss:3.5358 train_time:361455ms step_avg:178.85ms
step:2032/5100 train_loss:3.5261 train_time:361593ms step_avg:178.83ms
step:2033/5100 train_loss:3.5443 train_time:361733ms step_avg:178.81ms
step:2034/5100 train_loss:3.4388 train_time:361873ms step_avg:178.79ms
step:2035/5100 train_loss:3.5957 train_time:362013ms step_avg:178.77ms
step:2036/5100 train_loss:3.5973 train_time:362154ms step_avg:178.75ms
step:2037/5100 train_loss:3.5886 train_time:362293ms step_avg:178.73ms
step:2038/5100 train_loss:3.4543 train_time:362440ms step_avg:178.72ms
step:2039/5100 train_loss:3.7122 train_time:362597ms step_avg:178.71ms
step:2040/5100 train_loss:3.5513 train_time:363138ms step_avg:178.89ms
step:2041/5100 train_loss:3.5676 train_time:363237ms step_avg:178.85ms
step:2042/5100 train_loss:3.5144 train_time:363378ms step_avg:178.83ms
step:2043/5100 train_loss:3.4123 train_time:363517ms step_avg:178.81ms
step:2044/5100 train_loss:3.5462 train_time:363658ms step_avg:178.79ms
step:2045/5100 train_loss:3.5455 train_time:363798ms step_avg:178.77ms
step:2046/5100 train_loss:3.3979 train_time:363939ms step_avg:178.75ms
step:2047/5100 train_loss:3.4750 train_time:364079ms step_avg:178.73ms
step:2048/5100 train_loss:3.5557 train_time:364229ms step_avg:178.72ms
step:2049/5100 train_loss:3.5061 train_time:364369ms step_avg:178.70ms
step:2050/5100 train_loss:3.5502 train_time:364923ms step_avg:178.88ms
step:2051/5100 train_loss:3.6980 train_time:365021ms step_avg:178.84ms
step:2052/5100 train_loss:3.5634 train_time:365163ms step_avg:178.83ms
step:2053/5100 train_loss:3.5187 train_time:365303ms step_avg:178.81ms
step:2054/5100 train_loss:3.4911 train_time:365443ms step_avg:178.79ms
step:2055/5100 train_loss:3.3611 train_time:365584ms step_avg:178.77ms
step:2056/5100 train_loss:3.4771 train_time:365725ms step_avg:178.75ms
step:2057/5100 train_loss:3.6501 train_time:365868ms step_avg:178.73ms
step:2058/5100 train_loss:3.6676 train_time:366015ms step_avg:178.72ms
step:2059/5100 train_loss:3.5360 train_time:366157ms step_avg:178.70ms
step:2060/5100 train_loss:3.5758 train_time:366709ms step_avg:178.88ms
step:2061/5100 train_loss:3.5649 train_time:366807ms step_avg:178.84ms
step:2062/5100 train_loss:3.5146 train_time:366946ms step_avg:178.82ms
step:2063/5100 train_loss:3.4251 train_time:367086ms step_avg:178.80ms
step:2064/5100 train_loss:3.7384 train_time:367226ms step_avg:178.79ms
step:2065/5100 train_loss:3.5982 train_time:367365ms step_avg:178.77ms
step:2066/5100 train_loss:3.5407 train_time:367506ms step_avg:178.75ms
step:2067/5100 train_loss:3.5873 train_time:367647ms step_avg:178.73ms
step:2068/5100 train_loss:3.4936 train_time:367795ms step_avg:178.71ms
step:2069/5100 train_loss:3.5503 train_time:367936ms step_avg:178.70ms
step:2070/5100 train_loss:3.6837 train_time:368489ms step_avg:178.88ms
step:2071/5100 train_loss:3.6838 train_time:368586ms step_avg:178.84ms
step:2072/5100 train_loss:3.5361 train_time:368727ms step_avg:178.82ms
step:2073/5100 train_loss:3.5706 train_time:368867ms step_avg:178.80ms
step:2074/5100 train_loss:3.4568 train_time:369007ms step_avg:178.78ms
step:2075/5100 train_loss:3.9817 train_time:369148ms step_avg:178.76ms
step:2076/5100 train_loss:3.4116 train_time:369297ms step_avg:178.75ms
step:2077/5100 train_loss:3.5824 train_time:369429ms step_avg:178.73ms
step:2078/5100 train_loss:3.4690 train_time:369576ms step_avg:178.71ms
step:2079/5100 train_loss:3.4452 train_time:369798ms step_avg:178.73ms
step:2080/5100 train_loss:3.5355 train_time:370348ms step_avg:178.91ms
step:2081/5100 train_loss:3.7965 train_time:370443ms step_avg:178.87ms
step:2082/5100 train_loss:3.4180 train_time:370584ms step_avg:178.85ms
step:2083/5100 train_loss:3.7565 train_time:370725ms step_avg:178.83ms
step:2084/5100 train_loss:3.4589 train_time:370865ms step_avg:178.82ms
step:2085/5100 train_loss:3.4449 train_time:371006ms step_avg:178.80ms
step:2086/5100 train_loss:3.6890 train_time:371146ms step_avg:178.78ms
step:2087/5100 train_loss:3.6218 train_time:371286ms step_avg:178.76ms
step:2088/5100 train_loss:3.6019 train_time:371435ms step_avg:178.75ms
step:2089/5100 train_loss:3.6615 train_time:371576ms step_avg:178.73ms
step:2090/5100 train_loss:3.5784 train_time:372259ms step_avg:178.97ms
step:2091/5100 train_loss:3.5762 train_time:372354ms step_avg:178.93ms
step:2092/5100 train_loss:3.5177 train_time:372495ms step_avg:178.91ms
step:2093/5100 train_loss:3.5923 train_time:372637ms step_avg:178.89ms
step:2094/5100 train_loss:3.4857 train_time:372774ms step_avg:178.87ms
step:2095/5100 train_loss:3.2938 train_time:372915ms step_avg:178.86ms
step:2096/5100 train_loss:3.5161 train_time:373054ms step_avg:178.84ms
step:2097/5100 train_loss:3.6892 train_time:373195ms step_avg:178.82ms
step:2098/5100 train_loss:3.5258 train_time:373342ms step_avg:178.80ms
step:2099/5100 train_loss:3.4046 train_time:373486ms step_avg:178.79ms
step:2100/5100 train_loss:3.5132 train_time:374039ms step_avg:178.97ms
step:2101/5100 train_loss:3.4723 train_time:374135ms step_avg:178.93ms
step:2102/5100 train_loss:3.6102 train_time:374275ms step_avg:178.91ms
step:2103/5100 train_loss:3.4443 train_time:374415ms step_avg:178.89ms
step:2104/5100 train_loss:3.4048 train_time:374555ms step_avg:178.87ms
step:2105/5100 train_loss:3.6680 train_time:374694ms step_avg:178.85ms
step:2106/5100 train_loss:3.3968 train_time:374834ms step_avg:178.83ms
step:2107/5100 train_loss:3.7931 train_time:374975ms step_avg:178.81ms
step:2108/5100 train_loss:3.6317 train_time:375119ms step_avg:178.80ms
step:2109/5100 train_loss:3.5373 train_time:375264ms step_avg:178.78ms
step:2110/5100 train_loss:3.5526 train_time:375820ms step_avg:178.96ms
step:2111/5100 train_loss:3.3802 train_time:375925ms step_avg:178.93ms
step:2112/5100 train_loss:3.8539 train_time:376061ms step_avg:178.91ms
step:2113/5100 train_loss:3.5490 train_time:376197ms step_avg:178.89ms
step:2114/5100 train_loss:3.4762 train_time:376337ms step_avg:178.87ms
step:2115/5100 train_loss:3.5986 train_time:376476ms step_avg:178.85ms
step:2116/5100 train_loss:3.5615 train_time:376616ms step_avg:178.83ms
step:2117/5100 train_loss:3.5364 train_time:376757ms step_avg:178.81ms
step:2118/5100 train_loss:3.5980 train_time:376903ms step_avg:178.80ms
step:2119/5100 train_loss:3.4593 train_time:377046ms step_avg:178.78ms
step:2120/5100 train_loss:3.5155 train_time:377599ms step_avg:178.96ms
step:2121/5100 train_loss:3.2243 train_time:377698ms step_avg:178.92ms
step:2122/5100 train_loss:3.4204 train_time:377839ms step_avg:178.90ms
step:2123/5100 train_loss:3.5841 train_time:377979ms step_avg:178.88ms
step:2124/5100 train_loss:3.5027 train_time:378120ms step_avg:178.86ms
step:2125/5100 train_loss:3.6464 train_time:378262ms step_avg:178.85ms
step:2125/5100 val_loss:3.5280 train_time:378324ms step_avg:178.88ms
step:2126/5100 train_loss:3.5174 train_time:378414ms step_avg:178.83ms
step:2127/5100 train_loss:3.6281 train_time:378560ms step_avg:178.82ms
step:2128/5100 train_loss:3.6080 train_time:378704ms step_avg:178.80ms
step:2129/5100 train_loss:3.4751 train_time:378845ms step_avg:178.78ms
step:2130/5100 train_loss:3.4515 train_time:379395ms step_avg:178.96ms
step:2131/5100 train_loss:3.4814 train_time:379495ms step_avg:178.92ms
step:2132/5100 train_loss:3.6308 train_time:379636ms step_avg:178.90ms
step:2133/5100 train_loss:3.5133 train_time:379775ms step_avg:178.89ms
step:2134/5100 train_loss:3.4235 train_time:379916ms step_avg:178.87ms
step:2135/5100 train_loss:3.4859 train_time:380057ms step_avg:178.85ms
step:2136/5100 train_loss:3.6051 train_time:380197ms step_avg:178.83ms
step:2137/5100 train_loss:3.6214 train_time:380338ms step_avg:178.81ms
step:2138/5100 train_loss:3.5646 train_time:380485ms step_avg:178.80ms
step:2139/5100 train_loss:3.5539 train_time:380626ms step_avg:178.78ms
step:2140/5100 train_loss:3.5371 train_time:381180ms step_avg:178.96ms
step:2141/5100 train_loss:3.6241 train_time:381278ms step_avg:178.92ms
step:2142/5100 train_loss:3.9249 train_time:381418ms step_avg:178.90ms
step:2143/5100 train_loss:3.4617 train_time:381558ms step_avg:178.88ms
step:2144/5100 train_loss:3.4893 train_time:381702ms step_avg:178.87ms
step:2145/5100 train_loss:3.5289 train_time:381839ms step_avg:178.85ms
step:2146/5100 train_loss:3.6539 train_time:381984ms step_avg:178.83ms
step:2147/5100 train_loss:3.5825 train_time:382121ms step_avg:178.81ms
step:2148/5100 train_loss:3.9881 train_time:382269ms step_avg:178.80ms
step:2149/5100 train_loss:3.5091 train_time:382408ms step_avg:178.78ms
step:2150/5100 train_loss:3.4898 train_time:382961ms step_avg:178.95ms
step:2151/5100 train_loss:3.5446 train_time:383062ms step_avg:178.92ms
step:2152/5100 train_loss:3.5769 train_time:383202ms step_avg:178.90ms
step:2153/5100 train_loss:3.5340 train_time:383341ms step_avg:178.88ms
step:2154/5100 train_loss:3.4647 train_time:383481ms step_avg:178.86ms
step:2155/5100 train_loss:3.6784 train_time:383622ms step_avg:178.84ms
step:2156/5100 train_loss:3.2981 train_time:383762ms step_avg:178.83ms
step:2157/5100 train_loss:3.4668 train_time:383903ms step_avg:178.81ms
step:2158/5100 train_loss:3.5988 train_time:384050ms step_avg:178.79ms
step:2159/5100 train_loss:3.5391 train_time:384192ms step_avg:178.78ms
step:2160/5100 train_loss:3.6907 train_time:384747ms step_avg:178.95ms
step:2161/5100 train_loss:3.6121 train_time:384846ms step_avg:178.91ms
step:2162/5100 train_loss:3.5297 train_time:384986ms step_avg:178.90ms
step:2163/5100 train_loss:3.5000 train_time:385126ms step_avg:178.88ms
step:2164/5100 train_loss:3.5034 train_time:385267ms step_avg:178.86ms
step:2165/5100 train_loss:3.5886 train_time:385406ms step_avg:178.84ms
step:2166/5100 train_loss:3.6114 train_time:385548ms step_avg:178.83ms
step:2167/5100 train_loss:3.5417 train_time:385687ms step_avg:178.81ms
step:2168/5100 train_loss:3.4311 train_time:385833ms step_avg:178.79ms
step:2169/5100 train_loss:3.5189 train_time:385977ms step_avg:178.78ms
step:2170/5100 train_loss:3.5591 train_time:386531ms step_avg:178.95ms
step:2171/5100 train_loss:3.6764 train_time:386628ms step_avg:178.91ms
step:2172/5100 train_loss:3.4860 train_time:386768ms step_avg:178.89ms
step:2173/5100 train_loss:3.4613 train_time:386908ms step_avg:178.88ms
step:2174/5100 train_loss:3.4720 train_time:387049ms step_avg:178.86ms
step:2175/5100 train_loss:3.5277 train_time:387187ms step_avg:178.84ms
step:2176/5100 train_loss:3.4938 train_time:387330ms step_avg:178.82ms
step:2177/5100 train_loss:3.4619 train_time:387467ms step_avg:178.80ms
step:2178/5100 train_loss:3.6853 train_time:387614ms step_avg:178.79ms
step:2179/5100 train_loss:3.5023 train_time:387758ms step_avg:178.77ms
step:2180/5100 train_loss:3.5152 train_time:388313ms step_avg:178.95ms
step:2181/5100 train_loss:3.5670 train_time:388409ms step_avg:178.91ms
step:2182/5100 train_loss:3.5465 train_time:388550ms step_avg:178.89ms
step:2183/5100 train_loss:3.5192 train_time:388693ms step_avg:178.87ms
step:2184/5100 train_loss:3.4163 train_time:388830ms step_avg:178.85ms
step:2185/5100 train_loss:3.5862 train_time:388971ms step_avg:178.84ms
step:2186/5100 train_loss:3.7550 train_time:389113ms step_avg:178.82ms
step:2187/5100 train_loss:3.3961 train_time:389253ms step_avg:178.80ms
step:2188/5100 train_loss:3.4409 train_time:389398ms step_avg:178.79ms
step:2189/5100 train_loss:3.2975 train_time:389542ms step_avg:178.77ms
step:2190/5100 train_loss:3.4398 train_time:390093ms step_avg:178.94ms
step:2191/5100 train_loss:3.5928 train_time:390193ms step_avg:178.91ms
step:2192/5100 train_loss:3.5264 train_time:390337ms step_avg:178.89ms
step:2193/5100 train_loss:3.7561 train_time:390474ms step_avg:178.87ms
step:2194/5100 train_loss:3.5257 train_time:390615ms step_avg:178.85ms
step:2195/5100 train_loss:3.5989 train_time:390757ms step_avg:178.84ms
step:2196/5100 train_loss:3.5272 train_time:390897ms step_avg:178.82ms
step:2197/5100 train_loss:3.4552 train_time:391039ms step_avg:178.80ms
step:2198/5100 train_loss:3.5308 train_time:391186ms step_avg:178.79ms
step:2199/5100 train_loss:3.4777 train_time:391328ms step_avg:178.77ms
step:2200/5100 train_loss:3.4785 train_time:391880ms step_avg:178.94ms
step:2201/5100 train_loss:3.5354 train_time:391980ms step_avg:178.90ms
step:2202/5100 train_loss:3.5074 train_time:392121ms step_avg:178.89ms
step:2203/5100 train_loss:3.4933 train_time:392261ms step_avg:178.87ms
step:2204/5100 train_loss:3.9883 train_time:392399ms step_avg:178.85ms
step:2205/5100 train_loss:3.4047 train_time:392541ms step_avg:178.83ms
step:2206/5100 train_loss:3.5284 train_time:392685ms step_avg:178.82ms
step:2207/5100 train_loss:3.5440 train_time:392821ms step_avg:178.80ms
step:2208/5100 train_loss:3.5570 train_time:392969ms step_avg:178.78ms
step:2209/5100 train_loss:3.4513 train_time:393111ms step_avg:178.77ms
step:2210/5100 train_loss:3.5307 train_time:393664ms step_avg:178.94ms
step:2211/5100 train_loss:3.5469 train_time:393765ms step_avg:178.90ms
step:2212/5100 train_loss:3.5388 train_time:393908ms step_avg:178.89ms
step:2213/5100 train_loss:3.5675 train_time:394041ms step_avg:178.87ms
step:2214/5100 train_loss:3.4201 train_time:394180ms step_avg:178.85ms
step:2215/5100 train_loss:3.4886 train_time:394322ms step_avg:178.83ms
step:2216/5100 train_loss:3.6278 train_time:394464ms step_avg:178.81ms
step:2217/5100 train_loss:3.5781 train_time:394605ms step_avg:178.80ms
step:2218/5100 train_loss:3.5377 train_time:394751ms step_avg:178.78ms
step:2219/5100 train_loss:3.5422 train_time:394894ms step_avg:178.77ms
step:2220/5100 train_loss:3.4548 train_time:395450ms step_avg:178.94ms
step:2221/5100 train_loss:3.7160 train_time:395547ms step_avg:178.90ms
step:2222/5100 train_loss:3.6033 train_time:395689ms step_avg:178.88ms
step:2223/5100 train_loss:3.6278 train_time:395830ms step_avg:178.87ms
step:2224/5100 train_loss:3.5074 train_time:395970ms step_avg:178.85ms
step:2225/5100 train_loss:3.6320 train_time:396111ms step_avg:178.83ms
step:2226/5100 train_loss:3.3844 train_time:396250ms step_avg:178.81ms
step:2227/5100 train_loss:3.6500 train_time:396391ms step_avg:178.80ms
step:2228/5100 train_loss:3.5937 train_time:396536ms step_avg:178.78ms
step:2229/5100 train_loss:3.3907 train_time:396679ms step_avg:178.76ms
step:2230/5100 train_loss:3.7428 train_time:397234ms step_avg:178.93ms
step:2231/5100 train_loss:3.4342 train_time:397332ms step_avg:178.90ms
step:2232/5100 train_loss:3.9057 train_time:397471ms step_avg:178.88ms
step:2233/5100 train_loss:3.5858 train_time:397612ms step_avg:178.86ms
step:2234/5100 train_loss:3.5332 train_time:397751ms step_avg:178.85ms
step:2235/5100 train_loss:3.5779 train_time:397891ms step_avg:178.83ms
step:2236/5100 train_loss:3.3524 train_time:398031ms step_avg:178.81ms
step:2237/5100 train_loss:3.3507 train_time:398172ms step_avg:178.79ms
step:2238/5100 train_loss:3.5714 train_time:398319ms step_avg:178.78ms
step:2239/5100 train_loss:3.6677 train_time:398463ms step_avg:178.76ms
step:2240/5100 train_loss:3.3888 train_time:399014ms step_avg:178.93ms
step:2241/5100 train_loss:3.4603 train_time:399114ms step_avg:178.89ms
step:2242/5100 train_loss:3.6301 train_time:399251ms step_avg:178.88ms
step:2243/5100 train_loss:3.6024 train_time:399391ms step_avg:178.86ms
step:2244/5100 train_loss:3.4659 train_time:399530ms step_avg:178.84ms
step:2245/5100 train_loss:3.5281 train_time:399671ms step_avg:178.82ms
step:2246/5100 train_loss:3.5514 train_time:399812ms step_avg:178.81ms
step:2247/5100 train_loss:3.3906 train_time:399951ms step_avg:178.79ms
step:2248/5100 train_loss:3.4067 train_time:400099ms step_avg:178.78ms
step:2249/5100 train_loss:3.6529 train_time:400242ms step_avg:178.76ms
step:2250/5100 train_loss:3.3988 train_time:400797ms step_avg:178.93ms
step:2250/5100 val_loss:3.5159 train_time:400818ms step_avg:178.94ms
step:2251/5100 train_loss:3.3944 train_time:400904ms step_avg:178.90ms
step:2252/5100 train_loss:3.4620 train_time:401053ms step_avg:178.88ms
step:2253/5100 train_loss:3.4401 train_time:401195ms step_avg:178.87ms
step:2254/5100 train_loss:3.4838 train_time:401334ms step_avg:178.85ms
step:2255/5100 train_loss:3.5443 train_time:401473ms step_avg:178.83ms
step:2256/5100 train_loss:3.4254 train_time:401618ms step_avg:178.81ms
step:2257/5100 train_loss:3.7040 train_time:401753ms step_avg:178.80ms
step:2258/5100 train_loss:3.5809 train_time:401896ms step_avg:178.78ms
step:2259/5100 train_loss:3.8943 train_time:402041ms step_avg:178.76ms
step:2260/5100 train_loss:3.5837 train_time:402594ms step_avg:178.93ms
step:2261/5100 train_loss:3.6376 train_time:402693ms step_avg:178.90ms
step:2262/5100 train_loss:3.5486 train_time:402833ms step_avg:178.88ms
step:2263/5100 train_loss:3.5501 train_time:402974ms step_avg:178.86ms
step:2264/5100 train_loss:3.3053 train_time:403113ms step_avg:178.84ms
step:2265/5100 train_loss:3.4315 train_time:403253ms step_avg:178.83ms
step:2266/5100 train_loss:3.6459 train_time:403392ms step_avg:178.81ms
step:2267/5100 train_loss:3.3800 train_time:403533ms step_avg:178.79ms
step:2268/5100 train_loss:3.4497 train_time:403754ms step_avg:178.81ms
step:2269/5100 train_loss:3.4261 train_time:403889ms step_avg:178.79ms
step:2270/5100 train_loss:3.3910 train_time:404443ms step_avg:178.96ms
step:2271/5100 train_loss:3.7925 train_time:404539ms step_avg:178.92ms
step:2272/5100 train_loss:3.4420 train_time:404680ms step_avg:178.90ms
step:2273/5100 train_loss:3.4598 train_time:404820ms step_avg:178.89ms
step:2274/5100 train_loss:3.5395 train_time:404960ms step_avg:178.87ms
step:2275/5100 train_loss:3.4867 train_time:405101ms step_avg:178.85ms
step:2276/5100 train_loss:3.4962 train_time:405242ms step_avg:178.84ms
step:2277/5100 train_loss:3.3806 train_time:405382ms step_avg:178.82ms
step:2278/5100 train_loss:3.4873 train_time:405531ms step_avg:178.81ms
step:2279/5100 train_loss:3.6129 train_time:405673ms step_avg:178.79ms
step:2280/5100 train_loss:3.4174 train_time:406351ms step_avg:179.01ms
step:2281/5100 train_loss:3.4755 train_time:406447ms step_avg:178.97ms
step:2282/5100 train_loss:3.4863 train_time:406588ms step_avg:178.96ms
step:2283/5100 train_loss:3.6325 train_time:406728ms step_avg:178.94ms
step:2284/5100 train_loss:3.5080 train_time:406867ms step_avg:178.92ms
step:2285/5100 train_loss:3.5216 train_time:407008ms step_avg:178.90ms
step:2286/5100 train_loss:3.5268 train_time:407148ms step_avg:178.89ms
step:2287/5100 train_loss:3.5222 train_time:407289ms step_avg:178.87ms
step:2288/5100 train_loss:3.4785 train_time:407437ms step_avg:178.86ms
step:2289/5100 train_loss:3.6103 train_time:407579ms step_avg:178.84ms
step:2290/5100 train_loss:3.5849 train_time:408131ms step_avg:179.00ms
step:2291/5100 train_loss:3.4639 train_time:408230ms step_avg:178.97ms
step:2292/5100 train_loss:3.8042 train_time:408370ms step_avg:178.95ms
step:2293/5100 train_loss:3.4618 train_time:408510ms step_avg:178.94ms
step:2294/5100 train_loss:3.4135 train_time:408651ms step_avg:178.92ms
step:2295/5100 train_loss:3.6001 train_time:408792ms step_avg:178.90ms
step:2296/5100 train_loss:3.5523 train_time:408931ms step_avg:178.88ms
step:2297/5100 train_loss:3.5023 train_time:409073ms step_avg:178.87ms
step:2298/5100 train_loss:3.8940 train_time:409221ms step_avg:178.86ms
step:2299/5100 train_loss:3.4196 train_time:409363ms step_avg:178.84ms
step:2300/5100 train_loss:3.4213 train_time:409916ms step_avg:179.00ms
step:2301/5100 train_loss:3.7592 train_time:410019ms step_avg:178.97ms
step:2302/5100 train_loss:3.4775 train_time:410164ms step_avg:178.95ms
step:2303/5100 train_loss:3.4907 train_time:410298ms step_avg:178.94ms
step:2304/5100 train_loss:3.4869 train_time:410438ms step_avg:178.92ms
step:2305/5100 train_loss:3.4188 train_time:410578ms step_avg:178.90ms
step:2306/5100 train_loss:3.5819 train_time:410718ms step_avg:178.88ms
step:2307/5100 train_loss:3.4431 train_time:410858ms step_avg:178.87ms
step:2308/5100 train_loss:3.4675 train_time:411006ms step_avg:178.85ms
step:2309/5100 train_loss:3.5959 train_time:411146ms step_avg:178.84ms
step:2310/5100 train_loss:3.5486 train_time:411701ms step_avg:179.00ms
step:2311/5100 train_loss:3.4216 train_time:411797ms step_avg:178.96ms
step:2312/5100 train_loss:3.5326 train_time:411937ms step_avg:178.95ms
step:2313/5100 train_loss:3.6572 train_time:412076ms step_avg:178.93ms
step:2314/5100 train_loss:3.4737 train_time:412216ms step_avg:178.91ms
step:2315/5100 train_loss:3.4001 train_time:412356ms step_avg:178.90ms
step:2316/5100 train_loss:3.4942 train_time:412497ms step_avg:178.88ms
step:2317/5100 train_loss:3.3746 train_time:412637ms step_avg:178.86ms
step:2318/5100 train_loss:3.4808 train_time:412785ms step_avg:178.85ms
step:2319/5100 train_loss:3.5058 train_time:412927ms step_avg:178.83ms
step:2320/5100 train_loss:3.3439 train_time:413482ms step_avg:179.00ms
step:2321/5100 train_loss:3.4919 train_time:413579ms step_avg:178.96ms
step:2322/5100 train_loss:3.5322 train_time:413719ms step_avg:178.94ms
step:2323/5100 train_loss:3.4455 train_time:413859ms step_avg:178.93ms
step:2324/5100 train_loss:3.4985 train_time:413999ms step_avg:178.91ms
step:2325/5100 train_loss:3.4140 train_time:414138ms step_avg:178.89ms
step:2326/5100 train_loss:3.5562 train_time:414277ms step_avg:178.88ms
step:2327/5100 train_loss:3.5721 train_time:414418ms step_avg:178.86ms
step:2328/5100 train_loss:3.3339 train_time:414567ms step_avg:178.85ms
step:2329/5100 train_loss:3.4521 train_time:414708ms step_avg:178.83ms
step:2330/5100 train_loss:3.4797 train_time:415262ms step_avg:178.99ms
step:2331/5100 train_loss:3.4488 train_time:415360ms step_avg:178.96ms
step:2332/5100 train_loss:3.6321 train_time:415502ms step_avg:178.94ms
step:2333/5100 train_loss:3.5132 train_time:415642ms step_avg:178.92ms
step:2334/5100 train_loss:3.4894 train_time:415782ms step_avg:178.91ms
step:2335/5100 train_loss:3.5788 train_time:415925ms step_avg:178.89ms
step:2336/5100 train_loss:3.4171 train_time:416069ms step_avg:178.88ms
step:2337/5100 train_loss:3.5599 train_time:416206ms step_avg:178.86ms
step:2338/5100 train_loss:3.5228 train_time:416351ms step_avg:178.85ms
step:2339/5100 train_loss:3.4744 train_time:416493ms step_avg:178.83ms
step:2340/5100 train_loss:3.5392 train_time:417046ms step_avg:178.99ms
step:2341/5100 train_loss:3.5911 train_time:417144ms step_avg:178.95ms
step:2342/5100 train_loss:3.4668 train_time:417286ms step_avg:178.94ms
step:2343/5100 train_loss:3.4719 train_time:417426ms step_avg:178.92ms
step:2344/5100 train_loss:3.5337 train_time:417567ms step_avg:178.91ms
step:2345/5100 train_loss:3.4850 train_time:417707ms step_avg:178.89ms
step:2346/5100 train_loss:3.6087 train_time:417848ms step_avg:178.87ms
step:2347/5100 train_loss:3.5177 train_time:417989ms step_avg:178.86ms
step:2348/5100 train_loss:3.6119 train_time:418138ms step_avg:178.84ms
step:2349/5100 train_loss:3.5722 train_time:418278ms step_avg:178.83ms
step:2350/5100 train_loss:3.6195 train_time:418831ms step_avg:178.99ms
step:2351/5100 train_loss:3.3140 train_time:418930ms step_avg:178.95ms
step:2352/5100 train_loss:3.4402 train_time:419069ms step_avg:178.94ms
step:2353/5100 train_loss:3.4266 train_time:419211ms step_avg:178.92ms
step:2354/5100 train_loss:3.6407 train_time:419349ms step_avg:178.90ms
step:2355/5100 train_loss:3.4394 train_time:419490ms step_avg:178.89ms
step:2356/5100 train_loss:3.4267 train_time:419630ms step_avg:178.87ms
step:2357/5100 train_loss:3.5854 train_time:419772ms step_avg:178.85ms
step:2358/5100 train_loss:3.4430 train_time:419921ms step_avg:178.84ms
step:2359/5100 train_loss:3.5402 train_time:420064ms step_avg:178.83ms
step:2360/5100 train_loss:3.4360 train_time:420617ms step_avg:178.99ms
step:2361/5100 train_loss:3.4550 train_time:420717ms step_avg:178.95ms
step:2362/5100 train_loss:3.4869 train_time:420857ms step_avg:178.94ms
step:2363/5100 train_loss:3.5490 train_time:420997ms step_avg:178.92ms
step:2364/5100 train_loss:3.4896 train_time:421136ms step_avg:178.90ms
step:2365/5100 train_loss:3.9307 train_time:421276ms step_avg:178.89ms
step:2366/5100 train_loss:3.5542 train_time:421422ms step_avg:178.87ms
step:2367/5100 train_loss:3.7067 train_time:421559ms step_avg:178.85ms
step:2368/5100 train_loss:3.5328 train_time:421704ms step_avg:178.84ms
step:2369/5100 train_loss:3.5270 train_time:421848ms step_avg:178.82ms
step:2370/5100 train_loss:3.5628 train_time:422404ms step_avg:178.98ms
step:2371/5100 train_loss:3.4441 train_time:422498ms step_avg:178.95ms
step:2372/5100 train_loss:3.6710 train_time:422640ms step_avg:178.93ms
step:2373/5100 train_loss:3.5185 train_time:422783ms step_avg:178.92ms
step:2374/5100 train_loss:4.0686 train_time:422922ms step_avg:178.90ms
step:2375/5100 train_loss:3.4990 train_time:423061ms step_avg:178.88ms
step:2375/5100 val_loss:3.5075 train_time:423123ms step_avg:178.91ms
step:2376/5100 train_loss:3.4098 train_time:423213ms step_avg:178.87ms
step:2377/5100 train_loss:3.5723 train_time:423368ms step_avg:178.86ms
step:2378/5100 train_loss:3.5366 train_time:423503ms step_avg:178.84ms
step:2379/5100 train_loss:3.5507 train_time:423643ms step_avg:178.83ms
step:2380/5100 train_loss:3.5336 train_time:424192ms step_avg:178.98ms
step:2381/5100 train_loss:3.4354 train_time:424291ms step_avg:178.95ms
step:2382/5100 train_loss:3.5326 train_time:424432ms step_avg:178.93ms
step:2383/5100 train_loss:3.5536 train_time:424572ms step_avg:178.92ms
step:2384/5100 train_loss:3.5057 train_time:424712ms step_avg:178.90ms
step:2385/5100 train_loss:3.4313 train_time:424852ms step_avg:178.89ms
step:2386/5100 train_loss:3.5466 train_time:424992ms step_avg:178.87ms
step:2387/5100 train_loss:3.5071 train_time:425133ms step_avg:178.85ms
step:2388/5100 train_loss:3.5041 train_time:425282ms step_avg:178.84ms
step:2389/5100 train_loss:3.5377 train_time:425425ms step_avg:178.82ms
step:2390/5100 train_loss:3.5205 train_time:425984ms step_avg:178.98ms
step:2391/5100 train_loss:3.5144 train_time:426078ms step_avg:178.95ms
step:2392/5100 train_loss:3.3948 train_time:426218ms step_avg:178.93ms
step:2393/5100 train_loss:3.6125 train_time:426358ms step_avg:178.92ms
step:2394/5100 train_loss:3.4525 train_time:426499ms step_avg:178.90ms
step:2395/5100 train_loss:3.5486 train_time:426640ms step_avg:178.88ms
step:2396/5100 train_loss:3.6624 train_time:426779ms step_avg:178.87ms
step:2397/5100 train_loss:3.6799 train_time:426920ms step_avg:178.85ms
step:2398/5100 train_loss:3.6248 train_time:427068ms step_avg:178.84ms
step:2399/5100 train_loss:3.5974 train_time:427211ms step_avg:178.82ms
step:2400/5100 train_loss:3.4738 train_time:427770ms step_avg:178.98ms
step:2401/5100 train_loss:3.4682 train_time:427862ms step_avg:178.95ms
step:2402/5100 train_loss:3.5785 train_time:428003ms step_avg:178.93ms
step:2403/5100 train_loss:3.4137 train_time:428143ms step_avg:178.91ms
step:2404/5100 train_loss:3.5484 train_time:428283ms step_avg:178.90ms
step:2405/5100 train_loss:3.7596 train_time:428422ms step_avg:178.88ms
step:2406/5100 train_loss:3.4893 train_time:428563ms step_avg:178.87ms
step:2407/5100 train_loss:3.6380 train_time:428705ms step_avg:178.85ms
step:2408/5100 train_loss:3.4946 train_time:428852ms step_avg:178.84ms
step:2409/5100 train_loss:3.4294 train_time:428992ms step_avg:178.82ms
step:2410/5100 train_loss:3.5666 train_time:429551ms step_avg:178.98ms
step:2411/5100 train_loss:3.3548 train_time:429645ms step_avg:178.94ms
step:2412/5100 train_loss:3.7803 train_time:429787ms step_avg:178.93ms
step:2413/5100 train_loss:3.4708 train_time:429928ms step_avg:178.91ms
step:2414/5100 train_loss:3.5447 train_time:430070ms step_avg:178.90ms
step:2415/5100 train_loss:3.4689 train_time:430211ms step_avg:178.88ms
step:2416/5100 train_loss:3.5406 train_time:430352ms step_avg:178.87ms
step:2417/5100 train_loss:3.3567 train_time:430492ms step_avg:178.85ms
step:2418/5100 train_loss:3.2869 train_time:430638ms step_avg:178.84ms
step:2419/5100 train_loss:3.5799 train_time:430784ms step_avg:178.82ms
step:2420/5100 train_loss:3.4611 train_time:431337ms step_avg:178.98ms
step:2421/5100 train_loss:3.4947 train_time:431432ms step_avg:178.94ms
step:2422/5100 train_loss:3.5886 train_time:431572ms step_avg:178.93ms
step:2423/5100 train_loss:3.6413 train_time:431714ms step_avg:178.91ms
step:2424/5100 train_loss:3.4608 train_time:431853ms step_avg:178.90ms
step:2425/5100 train_loss:3.5489 train_time:431992ms step_avg:178.88ms
step:2426/5100 train_loss:3.5443 train_time:432132ms step_avg:178.86ms
step:2427/5100 train_loss:3.4761 train_time:432274ms step_avg:178.85ms
step:2428/5100 train_loss:3.4255 train_time:432421ms step_avg:178.83ms
step:2429/5100 train_loss:3.5485 train_time:432562ms step_avg:178.82ms
step:2430/5100 train_loss:3.4472 train_time:433115ms step_avg:178.97ms
step:2431/5100 train_loss:3.5037 train_time:433227ms step_avg:178.95ms
step:2432/5100 train_loss:3.5605 train_time:433356ms step_avg:178.92ms
step:2433/5100 train_loss:3.5224 train_time:433495ms step_avg:178.91ms
step:2434/5100 train_loss:3.3997 train_time:433635ms step_avg:178.89ms
step:2435/5100 train_loss:3.3653 train_time:433775ms step_avg:178.88ms
step:2436/5100 train_loss:3.5263 train_time:433916ms step_avg:178.86ms
step:2437/5100 train_loss:3.3950 train_time:434056ms step_avg:178.84ms
step:2438/5100 train_loss:3.4653 train_time:434205ms step_avg:178.83ms
step:2439/5100 train_loss:3.5559 train_time:434348ms step_avg:178.82ms
step:2440/5100 train_loss:3.4718 train_time:434903ms step_avg:178.97ms
step:2441/5100 train_loss:3.5578 train_time:435000ms step_avg:178.94ms
step:2442/5100 train_loss:3.4453 train_time:435141ms step_avg:178.92ms
step:2443/5100 train_loss:3.5047 train_time:435282ms step_avg:178.91ms
step:2444/5100 train_loss:3.3865 train_time:435421ms step_avg:178.89ms
step:2445/5100 train_loss:3.3967 train_time:435562ms step_avg:178.88ms
step:2446/5100 train_loss:3.5649 train_time:435702ms step_avg:178.86ms
step:2447/5100 train_loss:3.4239 train_time:435842ms step_avg:178.84ms
step:2448/5100 train_loss:3.4921 train_time:435989ms step_avg:178.83ms
step:2449/5100 train_loss:3.6579 train_time:436132ms step_avg:178.82ms
step:2450/5100 train_loss:3.4845 train_time:436686ms step_avg:178.97ms
step:2451/5100 train_loss:3.5603 train_time:436786ms step_avg:178.94ms
step:2452/5100 train_loss:3.4625 train_time:436927ms step_avg:178.92ms
step:2453/5100 train_loss:3.5643 train_time:437067ms step_avg:178.91ms
step:2454/5100 train_loss:3.4578 train_time:437209ms step_avg:178.89ms
step:2455/5100 train_loss:3.5933 train_time:437350ms step_avg:178.88ms
step:2456/5100 train_loss:3.5201 train_time:437490ms step_avg:178.86ms
step:2457/5100 train_loss:3.4420 train_time:437712ms step_avg:178.88ms
step:2458/5100 train_loss:3.3763 train_time:437849ms step_avg:178.86ms
step:2459/5100 train_loss:3.4973 train_time:437989ms step_avg:178.84ms
step:2460/5100 train_loss:4.0961 train_time:438542ms step_avg:179.00ms
step:2461/5100 train_loss:3.5704 train_time:438639ms step_avg:178.96ms
step:2462/5100 train_loss:3.3777 train_time:438779ms step_avg:178.95ms
step:2463/5100 train_loss:3.5727 train_time:438921ms step_avg:178.93ms
step:2464/5100 train_loss:3.4967 train_time:439061ms step_avg:178.92ms
step:2465/5100 train_loss:3.6916 train_time:439202ms step_avg:178.90ms
step:2466/5100 train_loss:3.8667 train_time:439341ms step_avg:178.88ms
step:2467/5100 train_loss:3.6097 train_time:439483ms step_avg:178.87ms
step:2468/5100 train_loss:3.4705 train_time:439629ms step_avg:178.86ms
step:2469/5100 train_loss:3.5898 train_time:439771ms step_avg:178.84ms
step:2470/5100 train_loss:3.6108 train_time:440450ms step_avg:179.04ms
step:2471/5100 train_loss:3.4164 train_time:440545ms step_avg:179.01ms
step:2472/5100 train_loss:3.4993 train_time:440686ms step_avg:179.00ms
step:2473/5100 train_loss:3.4950 train_time:440827ms step_avg:178.98ms
step:2474/5100 train_loss:3.6404 train_time:440968ms step_avg:178.96ms
step:2475/5100 train_loss:3.7688 train_time:441109ms step_avg:178.95ms
step:2476/5100 train_loss:3.3634 train_time:441250ms step_avg:178.93ms
step:2477/5100 train_loss:3.5730 train_time:441392ms step_avg:178.92ms
step:2478/5100 train_loss:3.5354 train_time:441536ms step_avg:178.90ms
step:2479/5100 train_loss:3.3699 train_time:441680ms step_avg:178.89ms
step:2480/5100 train_loss:3.3690 train_time:442237ms step_avg:179.04ms
step:2481/5100 train_loss:3.5162 train_time:442334ms step_avg:179.01ms
step:2482/5100 train_loss:3.5327 train_time:442476ms step_avg:179.00ms
step:2483/5100 train_loss:3.5439 train_time:442615ms step_avg:178.98ms
step:2484/5100 train_loss:3.4900 train_time:442755ms step_avg:178.96ms
step:2485/5100 train_loss:3.5059 train_time:442894ms step_avg:178.95ms
step:2486/5100 train_loss:3.3940 train_time:443035ms step_avg:178.93ms
step:2487/5100 train_loss:3.5895 train_time:443175ms step_avg:178.92ms
step:2488/5100 train_loss:3.5509 train_time:443326ms step_avg:178.90ms
step:2489/5100 train_loss:3.4557 train_time:443463ms step_avg:178.89ms
step:2490/5100 train_loss:3.5622 train_time:444021ms step_avg:179.04ms
step:2491/5100 train_loss:3.6122 train_time:444117ms step_avg:179.01ms
step:2492/5100 train_loss:3.6910 train_time:444257ms step_avg:178.99ms
step:2493/5100 train_loss:3.5404 train_time:444398ms step_avg:178.98ms
step:2494/5100 train_loss:3.4651 train_time:444537ms step_avg:178.96ms
step:2495/5100 train_loss:3.5954 train_time:444677ms step_avg:178.94ms
step:2496/5100 train_loss:3.5402 train_time:444817ms step_avg:178.93ms
step:2497/5100 train_loss:3.4518 train_time:444959ms step_avg:178.91ms
step:2498/5100 train_loss:3.5557 train_time:445106ms step_avg:178.90ms
step:2499/5100 train_loss:3.6046 train_time:445252ms step_avg:178.89ms
step:2500/5100 train_loss:3.6258 train_time:445804ms step_avg:179.04ms
step:2500/5100 val_loss:3.4977 train_time:445824ms step_avg:179.05ms
step:2501/5100 train_loss:3.5664 train_time:445910ms step_avg:179.01ms
step:2502/5100 train_loss:3.5171 train_time:446060ms step_avg:179.00ms
step:2503/5100 train_loss:3.5377 train_time:446203ms step_avg:178.98ms
step:2504/5100 train_loss:3.4072 train_time:446344ms step_avg:178.97ms
step:2505/5100 train_loss:3.5930 train_time:446485ms step_avg:178.95ms
step:2506/5100 train_loss:3.5511 train_time:446625ms step_avg:178.94ms
step:2507/5100 train_loss:3.4928 train_time:446765ms step_avg:178.92ms
step:2508/5100 train_loss:3.5004 train_time:446907ms step_avg:178.91ms
step:2509/5100 train_loss:3.4678 train_time:447051ms step_avg:178.89ms
step:2510/5100 train_loss:3.6273 train_time:447602ms step_avg:179.04ms
step:2511/5100 train_loss:3.4640 train_time:447707ms step_avg:179.01ms
step:2512/5100 train_loss:3.4424 train_time:447847ms step_avg:179.00ms
step:2513/5100 train_loss:3.5203 train_time:447988ms step_avg:178.98ms
step:2514/5100 train_loss:3.5594 train_time:448127ms step_avg:178.96ms
step:2515/5100 train_loss:3.4578 train_time:448268ms step_avg:178.95ms
step:2516/5100 train_loss:3.5538 train_time:448407ms step_avg:178.93ms
step:2517/5100 train_loss:3.5452 train_time:448549ms step_avg:178.92ms
step:2518/5100 train_loss:3.4219 train_time:448696ms step_avg:178.91ms
step:2519/5100 train_loss:3.4463 train_time:448839ms step_avg:178.89ms
step:2520/5100 train_loss:3.5736 train_time:449391ms step_avg:179.04ms
step:2521/5100 train_loss:3.5591 train_time:449493ms step_avg:179.01ms
step:2522/5100 train_loss:3.4399 train_time:449635ms step_avg:178.99ms
step:2523/5100 train_loss:3.4169 train_time:449774ms step_avg:178.98ms
step:2524/5100 train_loss:3.5259 train_time:449915ms step_avg:178.96ms
step:2525/5100 train_loss:3.3611 train_time:450055ms step_avg:178.95ms
step:2526/5100 train_loss:3.5862 train_time:450196ms step_avg:178.93ms
step:2527/5100 train_loss:3.5003 train_time:450334ms step_avg:178.92ms
step:2528/5100 train_loss:3.4979 train_time:450481ms step_avg:178.90ms
step:2529/5100 train_loss:3.4833 train_time:450627ms step_avg:178.89ms
step:2530/5100 train_loss:3.5160 train_time:451179ms step_avg:179.04ms
step:2531/5100 train_loss:3.5453 train_time:451277ms step_avg:179.01ms
step:2532/5100 train_loss:3.3659 train_time:451418ms step_avg:178.99ms
step:2533/5100 train_loss:3.5254 train_time:451559ms step_avg:178.98ms
step:2534/5100 train_loss:3.4250 train_time:451700ms step_avg:178.96ms
step:2535/5100 train_loss:3.4509 train_time:451841ms step_avg:178.95ms
step:2536/5100 train_loss:3.5083 train_time:451981ms step_avg:178.93ms
step:2537/5100 train_loss:3.5167 train_time:452123ms step_avg:178.92ms
step:2538/5100 train_loss:3.3479 train_time:452270ms step_avg:178.90ms
step:2539/5100 train_loss:3.6602 train_time:452413ms step_avg:178.89ms
step:2540/5100 train_loss:3.3446 train_time:452964ms step_avg:179.04ms
step:2541/5100 train_loss:3.5249 train_time:453064ms step_avg:179.01ms
step:2542/5100 train_loss:3.3000 train_time:453204ms step_avg:178.99ms
step:2543/5100 train_loss:3.7261 train_time:453344ms step_avg:178.98ms
step:2544/5100 train_loss:3.4920 train_time:453484ms step_avg:178.96ms
step:2545/5100 train_loss:3.6508 train_time:453624ms step_avg:178.94ms
step:2546/5100 train_loss:3.4851 train_time:453765ms step_avg:178.93ms
step:2547/5100 train_loss:3.4693 train_time:453906ms step_avg:178.91ms
step:2548/5100 train_loss:3.4729 train_time:454054ms step_avg:178.90ms
step:2549/5100 train_loss:3.6356 train_time:454195ms step_avg:178.89ms
step:2550/5100 train_loss:3.4898 train_time:454746ms step_avg:179.03ms
step:2551/5100 train_loss:3.4927 train_time:454847ms step_avg:179.00ms
step:2552/5100 train_loss:3.5194 train_time:454987ms step_avg:178.99ms
step:2553/5100 train_loss:3.5359 train_time:455126ms step_avg:178.97ms
step:2554/5100 train_loss:3.4493 train_time:455265ms step_avg:178.96ms
step:2555/5100 train_loss:3.5545 train_time:455406ms step_avg:178.94ms
step:2556/5100 train_loss:3.6118 train_time:455545ms step_avg:178.93ms
step:2557/5100 train_loss:3.6059 train_time:455689ms step_avg:178.91ms
step:2558/5100 train_loss:3.4411 train_time:455839ms step_avg:178.90ms
step:2559/5100 train_loss:3.4411 train_time:455985ms step_avg:178.89ms
step:2560/5100 train_loss:3.4540 train_time:456529ms step_avg:179.03ms
step:2561/5100 train_loss:3.5717 train_time:456633ms step_avg:179.00ms
step:2562/5100 train_loss:3.6086 train_time:456774ms step_avg:178.99ms
step:2563/5100 train_loss:3.4848 train_time:456915ms step_avg:178.97ms
step:2564/5100 train_loss:3.5172 train_time:457054ms step_avg:178.96ms
step:2565/5100 train_loss:3.4311 train_time:457194ms step_avg:178.94ms
step:2566/5100 train_loss:3.4441 train_time:457334ms step_avg:178.93ms
step:2567/5100 train_loss:3.4391 train_time:457474ms step_avg:178.91ms
step:2568/5100 train_loss:3.4891 train_time:457626ms step_avg:178.90ms
step:2569/5100 train_loss:3.6357 train_time:457763ms step_avg:178.88ms
step:2570/5100 train_loss:3.5383 train_time:458316ms step_avg:179.03ms
step:2571/5100 train_loss:3.6211 train_time:458417ms step_avg:179.00ms
step:2572/5100 train_loss:3.3726 train_time:458558ms step_avg:178.98ms
step:2573/5100 train_loss:3.4827 train_time:458699ms step_avg:178.97ms
step:2574/5100 train_loss:3.1504 train_time:458840ms step_avg:178.95ms
step:2575/5100 train_loss:3.3883 train_time:458983ms step_avg:178.94ms
step:2576/5100 train_loss:3.3303 train_time:459122ms step_avg:178.93ms
step:2577/5100 train_loss:3.4489 train_time:459263ms step_avg:178.91ms
step:2578/5100 train_loss:3.5054 train_time:459411ms step_avg:178.90ms
step:2579/5100 train_loss:3.4045 train_time:459555ms step_avg:178.88ms
step:2580/5100 train_loss:3.4593 train_time:460105ms step_avg:179.03ms
step:2581/5100 train_loss:3.4143 train_time:460205ms step_avg:179.00ms
step:2582/5100 train_loss:3.5133 train_time:460345ms step_avg:178.98ms
step:2583/5100 train_loss:3.3928 train_time:460486ms step_avg:178.97ms
step:2584/5100 train_loss:3.5866 train_time:460628ms step_avg:178.95ms
step:2585/5100 train_loss:3.5032 train_time:460767ms step_avg:178.94ms
step:2586/5100 train_loss:3.5075 train_time:460906ms step_avg:178.92ms
step:2587/5100 train_loss:3.6370 train_time:461047ms step_avg:178.91ms
step:2588/5100 train_loss:3.5264 train_time:461194ms step_avg:178.90ms
step:2589/5100 train_loss:3.3817 train_time:461335ms step_avg:178.88ms
step:2590/5100 train_loss:3.5488 train_time:461886ms step_avg:179.03ms
step:2591/5100 train_loss:3.4575 train_time:461988ms step_avg:179.00ms
step:2592/5100 train_loss:3.6587 train_time:462128ms step_avg:178.98ms
step:2593/5100 train_loss:3.5329 train_time:462267ms step_avg:178.97ms
step:2594/5100 train_loss:3.3602 train_time:462407ms step_avg:178.95ms
step:2595/5100 train_loss:3.4232 train_time:462548ms step_avg:178.94ms
step:2596/5100 train_loss:3.8711 train_time:462688ms step_avg:178.92ms
step:2597/5100 train_loss:3.5153 train_time:462829ms step_avg:178.91ms
step:2598/5100 train_loss:3.5174 train_time:462979ms step_avg:178.89ms
step:2599/5100 train_loss:3.3706 train_time:463122ms step_avg:178.88ms
step:2600/5100 train_loss:3.6107 train_time:463676ms step_avg:179.03ms
step:2601/5100 train_loss:3.7703 train_time:463776ms step_avg:178.99ms
step:2602/5100 train_loss:3.3543 train_time:463917ms step_avg:178.98ms
step:2603/5100 train_loss:3.4916 train_time:464058ms step_avg:178.97ms
step:2604/5100 train_loss:3.3194 train_time:464198ms step_avg:178.95ms
step:2605/5100 train_loss:3.6192 train_time:464339ms step_avg:178.94ms
step:2606/5100 train_loss:3.4925 train_time:464479ms step_avg:178.92ms
step:2607/5100 train_loss:3.3904 train_time:464621ms step_avg:178.91ms
step:2608/5100 train_loss:3.3384 train_time:464769ms step_avg:178.89ms
step:2609/5100 train_loss:3.4595 train_time:464909ms step_avg:178.88ms
step:2610/5100 train_loss:3.6369 train_time:465458ms step_avg:179.02ms
step:2611/5100 train_loss:3.5132 train_time:465564ms step_avg:178.99ms
step:2612/5100 train_loss:3.3362 train_time:465704ms step_avg:178.98ms
step:2613/5100 train_loss:3.4449 train_time:465844ms step_avg:178.96ms
step:2614/5100 train_loss:3.5509 train_time:465984ms step_avg:178.95ms
step:2615/5100 train_loss:3.4868 train_time:466124ms step_avg:178.93ms
step:2616/5100 train_loss:3.4714 train_time:466263ms step_avg:178.92ms
step:2617/5100 train_loss:3.5171 train_time:466404ms step_avg:178.90ms
step:2618/5100 train_loss:3.5618 train_time:466552ms step_avg:178.89ms
step:2619/5100 train_loss:3.3996 train_time:466695ms step_avg:178.88ms
step:2620/5100 train_loss:3.5844 train_time:467246ms step_avg:179.02ms
step:2621/5100 train_loss:3.5429 train_time:467346ms step_avg:178.99ms
step:2622/5100 train_loss:3.6640 train_time:467487ms step_avg:178.98ms
step:2623/5100 train_loss:3.5767 train_time:467632ms step_avg:178.96ms
step:2624/5100 train_loss:3.4947 train_time:467767ms step_avg:178.95ms
step:2625/5100 train_loss:3.4624 train_time:467907ms step_avg:178.93ms
step:2625/5100 val_loss:3.4867 train_time:467968ms step_avg:178.96ms
step:2626/5100 train_loss:3.4797 train_time:468055ms step_avg:178.92ms
step:2627/5100 train_loss:3.5401 train_time:468253ms step_avg:178.93ms
step:2628/5100 train_loss:3.3723 train_time:468335ms step_avg:178.89ms
step:2629/5100 train_loss:3.6209 train_time:468480ms step_avg:178.88ms
step:2630/5100 train_loss:3.5066 train_time:469039ms step_avg:179.02ms
step:2631/5100 train_loss:3.5628 train_time:469132ms step_avg:178.99ms
step:2632/5100 train_loss:3.7892 train_time:469274ms step_avg:178.98ms
step:2633/5100 train_loss:3.5324 train_time:469417ms step_avg:178.96ms
step:2634/5100 train_loss:3.4490 train_time:469557ms step_avg:178.95ms
step:2635/5100 train_loss:3.4215 train_time:469697ms step_avg:178.93ms
step:2636/5100 train_loss:3.4665 train_time:469837ms step_avg:178.92ms
step:2637/5100 train_loss:3.2544 train_time:469978ms step_avg:178.90ms
step:2638/5100 train_loss:3.5636 train_time:470125ms step_avg:178.89ms
step:2639/5100 train_loss:3.5336 train_time:470268ms step_avg:178.88ms
step:2640/5100 train_loss:3.4319 train_time:470821ms step_avg:179.02ms
step:2641/5100 train_loss:3.5136 train_time:470924ms step_avg:178.99ms
step:2642/5100 train_loss:3.5430 train_time:471062ms step_avg:178.97ms
step:2643/5100 train_loss:3.3343 train_time:471204ms step_avg:178.96ms
step:2644/5100 train_loss:3.4590 train_time:471344ms step_avg:178.95ms
step:2645/5100 train_loss:3.5298 train_time:471485ms step_avg:178.93ms
step:2646/5100 train_loss:3.4946 train_time:471706ms step_avg:178.95ms
step:2647/5100 train_loss:3.3844 train_time:471842ms step_avg:178.93ms
step:2648/5100 train_loss:3.6171 train_time:471982ms step_avg:178.92ms
step:2649/5100 train_loss:3.8680 train_time:472124ms step_avg:178.90ms
step:2650/5100 train_loss:3.5067 train_time:472677ms step_avg:179.04ms
step:2651/5100 train_loss:3.4649 train_time:472776ms step_avg:179.01ms
step:2652/5100 train_loss:3.6028 train_time:472916ms step_avg:179.00ms
step:2653/5100 train_loss:3.4444 train_time:473055ms step_avg:178.98ms
step:2654/5100 train_loss:3.4206 train_time:473195ms step_avg:178.97ms
step:2655/5100 train_loss:3.4939 train_time:473336ms step_avg:178.95ms
step:2656/5100 train_loss:3.4136 train_time:473476ms step_avg:178.94ms
step:2657/5100 train_loss:3.4509 train_time:473617ms step_avg:178.93ms
step:2658/5100 train_loss:3.4179 train_time:473762ms step_avg:178.91ms
step:2659/5100 train_loss:3.4991 train_time:473905ms step_avg:178.90ms
step:2660/5100 train_loss:3.6488 train_time:474582ms step_avg:179.09ms
step:2661/5100 train_loss:3.4449 train_time:474682ms step_avg:179.06ms
step:2662/5100 train_loss:3.5866 train_time:474821ms step_avg:179.04ms
step:2663/5100 train_loss:3.4518 train_time:474964ms step_avg:179.03ms
step:2664/5100 train_loss:3.4482 train_time:475101ms step_avg:179.01ms
step:2665/5100 train_loss:3.3828 train_time:475243ms step_avg:179.00ms
step:2666/5100 train_loss:3.4411 train_time:475383ms step_avg:178.98ms
step:2667/5100 train_loss:3.4676 train_time:475524ms step_avg:178.97ms
step:2668/5100 train_loss:3.5157 train_time:475671ms step_avg:178.96ms
step:2669/5100 train_loss:3.4311 train_time:475812ms step_avg:178.94ms
step:2670/5100 train_loss:3.4988 train_time:476365ms step_avg:179.08ms
step:2671/5100 train_loss:3.3732 train_time:476464ms step_avg:179.05ms
step:2672/5100 train_loss:3.4427 train_time:476606ms step_avg:179.04ms
step:2673/5100 train_loss:3.4283 train_time:476748ms step_avg:179.03ms
step:2674/5100 train_loss:3.4880 train_time:476887ms step_avg:179.01ms
step:2675/5100 train_loss:3.5160 train_time:477028ms step_avg:179.00ms
step:2676/5100 train_loss:3.4825 train_time:477168ms step_avg:178.98ms
step:2677/5100 train_loss:3.4740 train_time:477309ms step_avg:178.97ms
step:2678/5100 train_loss:3.5119 train_time:477456ms step_avg:178.96ms
step:2679/5100 train_loss:3.5596 train_time:477600ms step_avg:178.94ms
step:2680/5100 train_loss:3.4611 train_time:478152ms step_avg:179.08ms
step:2681/5100 train_loss:3.3894 train_time:478248ms step_avg:179.05ms
step:2682/5100 train_loss:3.4330 train_time:478389ms step_avg:179.04ms
step:2683/5100 train_loss:3.9071 train_time:478529ms step_avg:179.02ms
step:2684/5100 train_loss:3.4850 train_time:478670ms step_avg:179.01ms
step:2685/5100 train_loss:3.5129 train_time:478809ms step_avg:178.99ms
step:2686/5100 train_loss:3.5637 train_time:478949ms step_avg:178.98ms
step:2687/5100 train_loss:3.4790 train_time:479091ms step_avg:178.97ms
step:2688/5100 train_loss:3.5611 train_time:479239ms step_avg:178.95ms
step:2689/5100 train_loss:3.4899 train_time:479379ms step_avg:178.94ms
step:2690/5100 train_loss:3.4876 train_time:479933ms step_avg:179.08ms
step:2691/5100 train_loss:3.5109 train_time:480031ms step_avg:179.05ms
step:2692/5100 train_loss:3.5773 train_time:480171ms step_avg:179.03ms
step:2693/5100 train_loss:3.3878 train_time:480310ms step_avg:179.02ms
step:2694/5100 train_loss:3.7627 train_time:480451ms step_avg:179.01ms
step:2695/5100 train_loss:3.5570 train_time:480596ms step_avg:178.99ms
step:2696/5100 train_loss:3.3676 train_time:480731ms step_avg:178.98ms
step:2697/5100 train_loss:3.5497 train_time:480872ms step_avg:178.96ms
step:2698/5100 train_loss:3.5070 train_time:481018ms step_avg:178.95ms
step:2699/5100 train_loss:3.4589 train_time:481163ms step_avg:178.94ms
step:2700/5100 train_loss:3.5670 train_time:481717ms step_avg:179.08ms
step:2701/5100 train_loss:3.5306 train_time:481816ms step_avg:179.05ms
step:2702/5100 train_loss:3.4344 train_time:481956ms step_avg:179.03ms
step:2703/5100 train_loss:3.4596 train_time:482096ms step_avg:179.02ms
step:2704/5100 train_loss:3.4734 train_time:482237ms step_avg:179.00ms
step:2705/5100 train_loss:3.4418 train_time:482377ms step_avg:178.99ms
step:2706/5100 train_loss:3.6254 train_time:482516ms step_avg:178.97ms
step:2707/5100 train_loss:3.5802 train_time:482657ms step_avg:178.96ms
step:2708/5100 train_loss:3.4872 train_time:482803ms step_avg:178.95ms
step:2709/5100 train_loss:3.4756 train_time:482946ms step_avg:178.94ms
step:2710/5100 train_loss:3.5812 train_time:483505ms step_avg:179.08ms
step:2711/5100 train_loss:3.4543 train_time:483599ms step_avg:179.04ms
step:2712/5100 train_loss:3.5645 train_time:483741ms step_avg:179.03ms
step:2713/5100 train_loss:3.3111 train_time:483882ms step_avg:179.02ms
step:2714/5100 train_loss:3.5031 train_time:484022ms step_avg:179.00ms
step:2715/5100 train_loss:3.3998 train_time:484164ms step_avg:178.99ms
step:2716/5100 train_loss:3.4061 train_time:484305ms step_avg:178.97ms
step:2717/5100 train_loss:3.5961 train_time:484448ms step_avg:178.96ms
step:2718/5100 train_loss:3.4965 train_time:484594ms step_avg:178.95ms
step:2719/5100 train_loss:3.7337 train_time:484735ms step_avg:178.93ms
step:2720/5100 train_loss:3.4618 train_time:485292ms step_avg:179.07ms
step:2721/5100 train_loss:3.4688 train_time:485390ms step_avg:179.04ms
step:2722/5100 train_loss:3.6941 train_time:485530ms step_avg:179.03ms
step:2723/5100 train_loss:3.4608 train_time:485671ms step_avg:179.02ms
step:2724/5100 train_loss:3.6425 train_time:485810ms step_avg:179.00ms
step:2725/5100 train_loss:3.5107 train_time:485950ms step_avg:178.99ms
step:2726/5100 train_loss:3.4732 train_time:486089ms step_avg:178.97ms
step:2727/5100 train_loss:3.4813 train_time:486231ms step_avg:178.96ms
step:2728/5100 train_loss:3.8200 train_time:486378ms step_avg:178.95ms
step:2729/5100 train_loss:3.5474 train_time:486519ms step_avg:178.93ms
step:2730/5100 train_loss:3.4243 train_time:487072ms step_avg:179.07ms
step:2731/5100 train_loss:3.5246 train_time:487171ms step_avg:179.04ms
step:2732/5100 train_loss:3.4272 train_time:487311ms step_avg:179.03ms
step:2733/5100 train_loss:3.3207 train_time:487451ms step_avg:179.01ms
step:2734/5100 train_loss:3.4328 train_time:487591ms step_avg:179.00ms
step:2735/5100 train_loss:3.5055 train_time:487730ms step_avg:178.98ms
step:2736/5100 train_loss:3.4111 train_time:487872ms step_avg:178.97ms
step:2737/5100 train_loss:3.8033 train_time:488012ms step_avg:178.96ms
step:2738/5100 train_loss:3.5488 train_time:488162ms step_avg:178.95ms
step:2739/5100 train_loss:3.7430 train_time:488303ms step_avg:178.93ms
step:2740/5100 train_loss:3.4976 train_time:488860ms step_avg:179.07ms
step:2741/5100 train_loss:3.4896 train_time:488960ms step_avg:179.04ms
step:2742/5100 train_loss:3.4240 train_time:489098ms step_avg:179.03ms
step:2743/5100 train_loss:3.5018 train_time:489238ms step_avg:179.01ms
step:2744/5100 train_loss:3.5095 train_time:489377ms step_avg:179.00ms
step:2745/5100 train_loss:3.6228 train_time:489517ms step_avg:178.98ms
step:2746/5100 train_loss:3.3798 train_time:489657ms step_avg:178.97ms
step:2747/5100 train_loss:3.4725 train_time:489800ms step_avg:178.96ms
step:2748/5100 train_loss:3.5054 train_time:489946ms step_avg:178.94ms
step:2749/5100 train_loss:3.6235 train_time:490089ms step_avg:178.93ms
step:2750/5100 train_loss:3.4625 train_time:490642ms step_avg:179.07ms
step:2750/5100 val_loss:3.4804 train_time:490663ms step_avg:179.07ms
step:2751/5100 train_loss:3.5306 train_time:490749ms step_avg:179.04ms
step:2752/5100 train_loss:3.5915 train_time:490895ms step_avg:179.03ms
step:2753/5100 train_loss:3.5017 train_time:491039ms step_avg:179.02ms
step:2754/5100 train_loss:3.4253 train_time:491180ms step_avg:179.00ms
step:2755/5100 train_loss:3.4241 train_time:491321ms step_avg:178.99ms
step:2756/5100 train_loss:3.5091 train_time:491462ms step_avg:178.97ms
step:2757/5100 train_loss:3.4554 train_time:491601ms step_avg:178.96ms
step:2758/5100 train_loss:3.3302 train_time:491744ms step_avg:178.95ms
step:2759/5100 train_loss:3.7235 train_time:491887ms step_avg:178.93ms
step:2760/5100 train_loss:3.5307 train_time:492439ms step_avg:179.07ms
step:2761/5100 train_loss:3.4913 train_time:492542ms step_avg:179.04ms
step:2762/5100 train_loss:3.4610 train_time:492682ms step_avg:179.03ms
step:2763/5100 train_loss:3.3856 train_time:492822ms step_avg:179.01ms
step:2764/5100 train_loss:3.5450 train_time:492963ms step_avg:179.00ms
step:2765/5100 train_loss:3.4687 train_time:493104ms step_avg:178.99ms
step:2766/5100 train_loss:3.3670 train_time:493243ms step_avg:178.97ms
step:2767/5100 train_loss:3.4471 train_time:493384ms step_avg:178.96ms
step:2768/5100 train_loss:3.5376 train_time:493530ms step_avg:178.95ms
step:2769/5100 train_loss:3.4166 train_time:493674ms step_avg:178.93ms
step:2770/5100 train_loss:3.4869 train_time:494226ms step_avg:179.07ms
step:2771/5100 train_loss:3.4674 train_time:494330ms step_avg:179.04ms
step:2772/5100 train_loss:3.9000 train_time:494468ms step_avg:179.03ms
step:2773/5100 train_loss:3.3748 train_time:494608ms step_avg:179.01ms
step:2774/5100 train_loss:3.5056 train_time:494748ms step_avg:179.00ms
step:2775/5100 train_loss:3.5688 train_time:494888ms step_avg:178.98ms
step:2776/5100 train_loss:3.5400 train_time:495028ms step_avg:178.97ms
step:2777/5100 train_loss:3.6170 train_time:495168ms step_avg:178.95ms
step:2778/5100 train_loss:3.6204 train_time:495316ms step_avg:178.94ms
step:2779/5100 train_loss:3.4844 train_time:495460ms step_avg:178.93ms
step:2780/5100 train_loss:3.3499 train_time:496013ms step_avg:179.07ms
step:2781/5100 train_loss:3.5001 train_time:496111ms step_avg:179.04ms
step:2782/5100 train_loss:3.5222 train_time:496252ms step_avg:179.02ms
step:2783/5100 train_loss:3.3821 train_time:496393ms step_avg:179.01ms
step:2784/5100 train_loss:3.5004 train_time:496533ms step_avg:179.00ms
step:2785/5100 train_loss:3.5509 train_time:496673ms step_avg:178.98ms
step:2786/5100 train_loss:3.4216 train_time:496816ms step_avg:178.97ms
step:2787/5100 train_loss:3.5568 train_time:496956ms step_avg:178.95ms
step:2788/5100 train_loss:3.5106 train_time:497104ms step_avg:178.94ms
step:2789/5100 train_loss:3.4550 train_time:497245ms step_avg:178.93ms
step:2790/5100 train_loss:3.5296 train_time:497798ms step_avg:179.06ms
step:2791/5100 train_loss:3.4558 train_time:497897ms step_avg:179.04ms
step:2792/5100 train_loss:3.3560 train_time:498038ms step_avg:179.02ms
step:2793/5100 train_loss:3.4581 train_time:498178ms step_avg:179.01ms
step:2794/5100 train_loss:3.4926 train_time:498318ms step_avg:178.99ms
step:2795/5100 train_loss:3.4112 train_time:498462ms step_avg:178.98ms
step:2796/5100 train_loss:3.4591 train_time:498600ms step_avg:178.97ms
step:2797/5100 train_loss:3.3782 train_time:498740ms step_avg:178.95ms
step:2798/5100 train_loss:3.4812 train_time:498887ms step_avg:178.94ms
step:2799/5100 train_loss:3.4310 train_time:499030ms step_avg:178.93ms
step:2800/5100 train_loss:3.6043 train_time:499582ms step_avg:179.06ms
step:2801/5100 train_loss:3.5485 train_time:499682ms step_avg:179.03ms
step:2802/5100 train_loss:3.5186 train_time:499820ms step_avg:179.02ms
step:2803/5100 train_loss:3.4669 train_time:499959ms step_avg:179.00ms
step:2804/5100 train_loss:3.6435 train_time:500099ms step_avg:178.99ms
step:2805/5100 train_loss:3.6152 train_time:500241ms step_avg:178.98ms
step:2806/5100 train_loss:3.3400 train_time:500380ms step_avg:178.96ms
step:2807/5100 train_loss:3.7432 train_time:500522ms step_avg:178.95ms
step:2808/5100 train_loss:3.4914 train_time:500669ms step_avg:178.94ms
step:2809/5100 train_loss:3.4126 train_time:500810ms step_avg:178.92ms
step:2810/5100 train_loss:3.4529 train_time:501362ms step_avg:179.06ms
step:2811/5100 train_loss:3.6008 train_time:501461ms step_avg:179.03ms
step:2812/5100 train_loss:3.5844 train_time:501601ms step_avg:179.02ms
step:2813/5100 train_loss:3.3353 train_time:501742ms step_avg:179.00ms
step:2814/5100 train_loss:3.5591 train_time:501881ms step_avg:178.99ms
step:2815/5100 train_loss:3.6335 train_time:502022ms step_avg:178.97ms
step:2816/5100 train_loss:3.4346 train_time:502161ms step_avg:178.96ms
step:2817/5100 train_loss:2.9797 train_time:502304ms step_avg:178.95ms
step:2818/5100 train_loss:3.4706 train_time:502450ms step_avg:178.94ms
step:2819/5100 train_loss:3.4422 train_time:502593ms step_avg:178.92ms
step:2820/5100 train_loss:3.6258 train_time:503143ms step_avg:179.05ms
step:2821/5100 train_loss:3.6857 train_time:503243ms step_avg:179.03ms
step:2822/5100 train_loss:3.5488 train_time:503384ms step_avg:179.01ms
step:2823/5100 train_loss:3.4916 train_time:503526ms step_avg:179.00ms
step:2824/5100 train_loss:3.4481 train_time:503664ms step_avg:178.99ms
step:2825/5100 train_loss:3.3435 train_time:503804ms step_avg:178.97ms
step:2826/5100 train_loss:3.6088 train_time:503944ms step_avg:178.96ms
step:2827/5100 train_loss:3.5135 train_time:504085ms step_avg:178.94ms
step:2828/5100 train_loss:3.3858 train_time:504234ms step_avg:178.93ms
step:2829/5100 train_loss:3.5213 train_time:504378ms step_avg:178.92ms
step:2830/5100 train_loss:3.5193 train_time:504931ms step_avg:179.05ms
step:2831/5100 train_loss:3.4586 train_time:505031ms step_avg:179.03ms
step:2832/5100 train_loss:3.6023 train_time:505172ms step_avg:179.01ms
step:2833/5100 train_loss:3.5146 train_time:505311ms step_avg:179.00ms
step:2834/5100 train_loss:3.5075 train_time:505451ms step_avg:178.98ms
step:2835/5100 train_loss:3.3177 train_time:505677ms step_avg:179.00ms
step:2836/5100 train_loss:3.5442 train_time:505812ms step_avg:178.99ms
step:2837/5100 train_loss:3.4749 train_time:505951ms step_avg:178.97ms
step:2838/5100 train_loss:3.7833 train_time:506090ms step_avg:178.96ms
step:2839/5100 train_loss:3.4250 train_time:506230ms step_avg:178.94ms
step:2840/5100 train_loss:3.4322 train_time:506780ms step_avg:179.07ms
step:2841/5100 train_loss:3.4917 train_time:506881ms step_avg:179.05ms
step:2842/5100 train_loss:3.4226 train_time:507020ms step_avg:179.03ms
step:2843/5100 train_loss:3.4151 train_time:507161ms step_avg:179.02ms
step:2844/5100 train_loss:3.5930 train_time:507301ms step_avg:179.01ms
step:2845/5100 train_loss:3.4807 train_time:507441ms step_avg:178.99ms
step:2846/5100 train_loss:3.5042 train_time:507581ms step_avg:178.98ms
step:2847/5100 train_loss:3.4649 train_time:507721ms step_avg:178.96ms
step:2848/5100 train_loss:3.7325 train_time:507868ms step_avg:178.95ms
step:2849/5100 train_loss:3.4010 train_time:508010ms step_avg:178.94ms
step:2850/5100 train_loss:3.4271 train_time:508694ms step_avg:179.12ms
step:2851/5100 train_loss:3.5313 train_time:508794ms step_avg:179.09ms
step:2852/5100 train_loss:3.4963 train_time:508935ms step_avg:179.08ms
step:2853/5100 train_loss:3.4636 train_time:509076ms step_avg:179.06ms
step:2854/5100 train_loss:3.5373 train_time:509216ms step_avg:179.05ms
step:2855/5100 train_loss:3.3664 train_time:509358ms step_avg:179.04ms
step:2856/5100 train_loss:3.3846 train_time:509499ms step_avg:179.02ms
step:2857/5100 train_loss:3.4776 train_time:509642ms step_avg:179.01ms
step:2858/5100 train_loss:3.4807 train_time:509787ms step_avg:179.00ms
step:2859/5100 train_loss:3.3585 train_time:509932ms step_avg:178.99ms
step:2860/5100 train_loss:3.4739 train_time:510482ms step_avg:179.12ms
step:2861/5100 train_loss:3.4362 train_time:510580ms step_avg:179.09ms
step:2862/5100 train_loss:3.4702 train_time:510721ms step_avg:179.07ms
step:2863/5100 train_loss:3.5095 train_time:510861ms step_avg:179.06ms
step:2864/5100 train_loss:3.7784 train_time:511002ms step_avg:179.05ms
step:2865/5100 train_loss:3.5955 train_time:511141ms step_avg:179.03ms
step:2866/5100 train_loss:3.4716 train_time:511282ms step_avg:179.02ms
step:2867/5100 train_loss:3.3704 train_time:511423ms step_avg:179.01ms
step:2868/5100 train_loss:3.5652 train_time:511570ms step_avg:179.00ms
step:2869/5100 train_loss:3.5139 train_time:511713ms step_avg:178.98ms
step:2870/5100 train_loss:3.4708 train_time:512269ms step_avg:179.11ms
step:2871/5100 train_loss:3.6130 train_time:512366ms step_avg:179.09ms
step:2872/5100 train_loss:3.3922 train_time:512507ms step_avg:179.07ms
step:2873/5100 train_loss:3.4465 train_time:512647ms step_avg:179.06ms
step:2874/5100 train_loss:3.3184 train_time:512788ms step_avg:179.05ms
step:2875/5100 train_loss:3.4727 train_time:512929ms step_avg:179.03ms
step:2875/5100 val_loss:3.4732 train_time:512991ms step_avg:179.05ms
step:2876/5100 train_loss:3.3937 train_time:513076ms step_avg:179.02ms
step:2877/5100 train_loss:3.3713 train_time:513222ms step_avg:179.01ms
step:2878/5100 train_loss:3.4651 train_time:513368ms step_avg:179.00ms
step:2879/5100 train_loss:3.5772 train_time:513508ms step_avg:178.99ms
step:2880/5100 train_loss:3.5354 train_time:514059ms step_avg:179.11ms
step:2881/5100 train_loss:3.4677 train_time:514159ms step_avg:179.09ms
step:2882/5100 train_loss:3.4585 train_time:514298ms step_avg:179.07ms
step:2883/5100 train_loss:3.5811 train_time:514439ms step_avg:179.06ms
step:2884/5100 train_loss:3.3753 train_time:514580ms step_avg:179.05ms
step:2885/5100 train_loss:3.3848 train_time:514723ms step_avg:179.03ms
step:2886/5100 train_loss:3.4332 train_time:514862ms step_avg:179.02ms
step:2887/5100 train_loss:3.4303 train_time:515003ms step_avg:179.01ms
step:2888/5100 train_loss:3.4458 train_time:515149ms step_avg:179.00ms
step:2889/5100 train_loss:3.4668 train_time:515292ms step_avg:178.98ms
step:2890/5100 train_loss:3.6464 train_time:515844ms step_avg:179.11ms
step:2891/5100 train_loss:3.4937 train_time:515950ms step_avg:179.09ms
step:2892/5100 train_loss:3.3289 train_time:516086ms step_avg:179.07ms
step:2893/5100 train_loss:3.2611 train_time:516226ms step_avg:179.06ms
step:2894/5100 train_loss:3.4039 train_time:516367ms step_avg:179.05ms
step:2895/5100 train_loss:3.2823 train_time:516507ms step_avg:179.03ms
step:2896/5100 train_loss:3.4657 train_time:516649ms step_avg:179.02ms
step:2897/5100 train_loss:3.5898 train_time:516788ms step_avg:179.01ms
step:2898/5100 train_loss:3.4152 train_time:516934ms step_avg:178.99ms
step:2899/5100 train_loss:3.5106 train_time:517078ms step_avg:178.98ms
step:2900/5100 train_loss:3.3978 train_time:517633ms step_avg:179.11ms
step:2901/5100 train_loss:3.5821 train_time:517733ms step_avg:179.08ms
step:2902/5100 train_loss:3.5654 train_time:517875ms step_avg:179.07ms
step:2903/5100 train_loss:3.6089 train_time:518015ms step_avg:179.06ms
step:2904/5100 train_loss:3.3215 train_time:518154ms step_avg:179.04ms
step:2905/5100 train_loss:3.4632 train_time:518296ms step_avg:179.03ms
step:2906/5100 train_loss:3.4425 train_time:518436ms step_avg:179.02ms
step:2907/5100 train_loss:3.5318 train_time:518576ms step_avg:179.00ms
step:2908/5100 train_loss:3.4620 train_time:518724ms step_avg:178.99ms
step:2909/5100 train_loss:3.4202 train_time:518866ms step_avg:178.98ms
step:2910/5100 train_loss:3.7647 train_time:519421ms step_avg:179.11ms
step:2911/5100 train_loss:3.4779 train_time:519517ms step_avg:179.08ms
step:2912/5100 train_loss:3.3756 train_time:519658ms step_avg:179.07ms
step:2913/5100 train_loss:3.3623 train_time:519801ms step_avg:179.06ms
step:2914/5100 train_loss:3.8500 train_time:519939ms step_avg:179.04ms
step:2915/5100 train_loss:3.4449 train_time:520080ms step_avg:179.03ms
step:2916/5100 train_loss:3.3853 train_time:520222ms step_avg:179.02ms
step:2917/5100 train_loss:3.3754 train_time:520363ms step_avg:179.00ms
step:2918/5100 train_loss:3.6607 train_time:520510ms step_avg:178.99ms
step:2919/5100 train_loss:3.1615 train_time:520653ms step_avg:178.98ms
step:2920/5100 train_loss:3.3728 train_time:521207ms step_avg:179.11ms
step:2921/5100 train_loss:3.3891 train_time:521304ms step_avg:179.08ms
step:2922/5100 train_loss:3.4783 train_time:521446ms step_avg:179.07ms
step:2923/5100 train_loss:3.5213 train_time:521586ms step_avg:179.05ms
step:2924/5100 train_loss:3.5583 train_time:521726ms step_avg:179.04ms
step:2925/5100 train_loss:3.5615 train_time:521866ms step_avg:179.03ms
step:2926/5100 train_loss:3.4371 train_time:522006ms step_avg:179.01ms
step:2927/5100 train_loss:3.4614 train_time:522146ms step_avg:179.00ms
step:2928/5100 train_loss:3.4444 train_time:522294ms step_avg:178.99ms
step:2929/5100 train_loss:3.4424 train_time:522437ms step_avg:178.98ms
step:2930/5100 train_loss:3.4144 train_time:522986ms step_avg:179.10ms
step:2931/5100 train_loss:3.4408 train_time:523088ms step_avg:179.08ms
step:2932/5100 train_loss:3.5777 train_time:523229ms step_avg:179.07ms
step:2933/5100 train_loss:3.6123 train_time:523368ms step_avg:179.05ms
step:2934/5100 train_loss:3.5777 train_time:523508ms step_avg:179.04ms
step:2935/5100 train_loss:3.4247 train_time:523648ms step_avg:179.03ms
step:2936/5100 train_loss:3.4789 train_time:523788ms step_avg:179.01ms
step:2937/5100 train_loss:3.4089 train_time:523930ms step_avg:179.00ms
step:2938/5100 train_loss:3.4388 train_time:524077ms step_avg:178.99ms
step:2939/5100 train_loss:3.4734 train_time:524221ms step_avg:178.98ms
step:2940/5100 train_loss:3.5115 train_time:524771ms step_avg:179.10ms
step:2941/5100 train_loss:3.5557 train_time:524874ms step_avg:179.08ms
step:2942/5100 train_loss:3.5373 train_time:525014ms step_avg:179.06ms
step:2943/5100 train_loss:3.4676 train_time:525154ms step_avg:179.05ms
step:2944/5100 train_loss:3.3495 train_time:525294ms step_avg:179.04ms
step:2945/5100 train_loss:3.2868 train_time:525435ms step_avg:179.02ms
step:2946/5100 train_loss:3.4869 train_time:525574ms step_avg:179.01ms
step:2947/5100 train_loss:3.5615 train_time:525714ms step_avg:179.00ms
step:2948/5100 train_loss:3.4903 train_time:525862ms step_avg:178.99ms
step:2949/5100 train_loss:3.6664 train_time:526004ms step_avg:178.97ms
step:2950/5100 train_loss:3.4990 train_time:526553ms step_avg:179.10ms
step:2951/5100 train_loss:3.4981 train_time:526656ms step_avg:179.07ms
step:2952/5100 train_loss:3.9116 train_time:526796ms step_avg:179.06ms
step:2953/5100 train_loss:3.5720 train_time:526938ms step_avg:179.05ms
step:2954/5100 train_loss:3.5111 train_time:527077ms step_avg:179.03ms
step:2955/5100 train_loss:3.5261 train_time:527215ms step_avg:179.02ms
step:2956/5100 train_loss:3.4578 train_time:527356ms step_avg:179.01ms
step:2957/5100 train_loss:3.4884 train_time:527497ms step_avg:178.99ms
step:2958/5100 train_loss:3.3556 train_time:527645ms step_avg:178.98ms
step:2959/5100 train_loss:3.4426 train_time:527788ms step_avg:178.97ms
step:2960/5100 train_loss:3.5837 train_time:528340ms step_avg:179.10ms
step:2961/5100 train_loss:3.3925 train_time:528441ms step_avg:179.07ms
step:2962/5100 train_loss:3.5197 train_time:528581ms step_avg:179.06ms
step:2963/5100 train_loss:3.3747 train_time:528724ms step_avg:179.05ms
step:2964/5100 train_loss:3.4330 train_time:528862ms step_avg:179.03ms
step:2965/5100 train_loss:3.4207 train_time:529003ms step_avg:179.02ms
step:2966/5100 train_loss:3.5435 train_time:529143ms step_avg:179.01ms
step:2967/5100 train_loss:3.4064 train_time:529285ms step_avg:178.99ms
step:2968/5100 train_loss:3.6559 train_time:529432ms step_avg:178.98ms
step:2969/5100 train_loss:3.5000 train_time:529574ms step_avg:178.97ms
step:2970/5100 train_loss:3.5109 train_time:530125ms step_avg:179.10ms
step:2971/5100 train_loss:3.5026 train_time:530225ms step_avg:179.07ms
step:2972/5100 train_loss:3.5803 train_time:530367ms step_avg:179.06ms
step:2973/5100 train_loss:3.4056 train_time:530510ms step_avg:179.04ms
step:2974/5100 train_loss:3.4151 train_time:530647ms step_avg:179.03ms
step:2975/5100 train_loss:3.3308 train_time:530788ms step_avg:179.02ms
step:2976/5100 train_loss:3.4074 train_time:530927ms step_avg:179.00ms
step:2977/5100 train_loss:3.3987 train_time:531067ms step_avg:178.99ms
step:2978/5100 train_loss:3.4166 train_time:531217ms step_avg:178.98ms
step:2979/5100 train_loss:3.6966 train_time:531358ms step_avg:178.97ms
step:2980/5100 train_loss:3.5142 train_time:531910ms step_avg:179.09ms
step:2981/5100 train_loss:3.5473 train_time:532012ms step_avg:179.07ms
step:2982/5100 train_loss:3.5580 train_time:532153ms step_avg:179.06ms
step:2983/5100 train_loss:3.6433 train_time:532293ms step_avg:179.04ms
step:2984/5100 train_loss:3.4408 train_time:532433ms step_avg:179.03ms
step:2985/5100 train_loss:3.5364 train_time:532573ms step_avg:179.02ms
step:2986/5100 train_loss:3.5406 train_time:532713ms step_avg:179.00ms
step:2987/5100 train_loss:3.4966 train_time:532854ms step_avg:178.99ms
step:2988/5100 train_loss:3.6143 train_time:532998ms step_avg:178.98ms
step:2989/5100 train_loss:3.2188 train_time:533142ms step_avg:178.97ms
step:2990/5100 train_loss:3.5570 train_time:533693ms step_avg:179.09ms
step:2991/5100 train_loss:3.5060 train_time:533795ms step_avg:179.07ms
step:2992/5100 train_loss:3.4887 train_time:533937ms step_avg:179.05ms
step:2993/5100 train_loss:3.3993 train_time:534077ms step_avg:179.04ms
step:2994/5100 train_loss:3.5485 train_time:534219ms step_avg:179.03ms
step:2995/5100 train_loss:3.3613 train_time:534358ms step_avg:179.01ms
step:2996/5100 train_loss:3.3942 train_time:534499ms step_avg:179.00ms
step:2997/5100 train_loss:3.4649 train_time:534639ms step_avg:178.99ms
step:2998/5100 train_loss:3.4012 train_time:534788ms step_avg:178.98ms
step:2999/5100 train_loss:3.5231 train_time:534929ms step_avg:178.97ms
step:3000/5100 train_loss:3.4248 train_time:535480ms step_avg:179.09ms
step:3000/5100 val_loss:3.4659 train_time:535505ms step_avg:179.10ms
step:3001/5100 train_loss:3.4209 train_time:535592ms step_avg:179.07ms
step:3002/5100 train_loss:3.3536 train_time:535742ms step_avg:179.06ms
step:3003/5100 train_loss:3.4063 train_time:535883ms step_avg:179.05ms
step:3004/5100 train_loss:3.5306 train_time:536023ms step_avg:179.03ms
step:3005/5100 train_loss:3.8771 train_time:536163ms step_avg:179.02ms
step:3006/5100 train_loss:3.4462 train_time:536304ms step_avg:179.01ms
step:3007/5100 train_loss:3.5211 train_time:536443ms step_avg:178.99ms
step:3008/5100 train_loss:3.3309 train_time:536584ms step_avg:178.98ms
step:3009/5100 train_loss:3.5332 train_time:536732ms step_avg:178.97ms
step:3010/5100 train_loss:3.4378 train_time:537283ms step_avg:179.09ms
step:3011/5100 train_loss:3.4970 train_time:537383ms step_avg:179.07ms
step:3012/5100 train_loss:3.4994 train_time:537525ms step_avg:179.06ms
step:3013/5100 train_loss:3.3878 train_time:537665ms step_avg:179.04ms
step:3014/5100 train_loss:3.5841 train_time:537806ms step_avg:179.03ms
step:3015/5100 train_loss:3.5446 train_time:537948ms step_avg:179.02ms
step:3016/5100 train_loss:3.4124 train_time:538089ms step_avg:179.00ms
step:3017/5100 train_loss:3.4464 train_time:538232ms step_avg:178.99ms
step:3018/5100 train_loss:3.4999 train_time:538377ms step_avg:178.98ms
step:3019/5100 train_loss:3.5358 train_time:538519ms step_avg:178.97ms
step:3020/5100 train_loss:3.3204 train_time:539071ms step_avg:179.09ms
step:3021/5100 train_loss:3.6088 train_time:539171ms step_avg:179.07ms
step:3022/5100 train_loss:3.4489 train_time:539312ms step_avg:179.05ms
step:3023/5100 train_loss:3.3696 train_time:539452ms step_avg:179.04ms
step:3024/5100 train_loss:3.4577 train_time:539675ms step_avg:179.06ms
step:3025/5100 train_loss:3.4481 train_time:539810ms step_avg:179.04ms
step:3026/5100 train_loss:3.4940 train_time:539950ms step_avg:179.03ms
step:3027/5100 train_loss:3.5210 train_time:540090ms step_avg:179.02ms
step:3028/5100 train_loss:3.4311 train_time:540231ms step_avg:179.00ms
step:3029/5100 train_loss:3.2317 train_time:540371ms step_avg:178.99ms
step:3030/5100 train_loss:3.5791 train_time:540926ms step_avg:179.11ms
step:3031/5100 train_loss:3.3327 train_time:541026ms step_avg:179.09ms
step:3032/5100 train_loss:3.3274 train_time:541167ms step_avg:179.08ms
step:3033/5100 train_loss:3.6737 train_time:541307ms step_avg:179.06ms
step:3034/5100 train_loss:3.6615 train_time:541448ms step_avg:179.05ms
step:3035/5100 train_loss:3.4231 train_time:541589ms step_avg:179.04ms
step:3036/5100 train_loss:3.5052 train_time:541731ms step_avg:179.03ms
step:3037/5100 train_loss:3.4556 train_time:541871ms step_avg:179.01ms
step:3038/5100 train_loss:3.3542 train_time:542018ms step_avg:179.00ms
step:3039/5100 train_loss:3.4208 train_time:542161ms step_avg:178.99ms
step:3040/5100 train_loss:3.5128 train_time:542844ms step_avg:179.16ms
step:3041/5100 train_loss:3.5045 train_time:542940ms step_avg:179.13ms
step:3042/5100 train_loss:3.3079 train_time:543081ms step_avg:179.12ms
step:3043/5100 train_loss:3.4568 train_time:543221ms step_avg:179.10ms
step:3044/5100 train_loss:3.4803 train_time:543361ms step_avg:179.09ms
step:3045/5100 train_loss:3.4964 train_time:543501ms step_avg:179.08ms
step:3046/5100 train_loss:3.5724 train_time:543641ms step_avg:179.06ms
step:3047/5100 train_loss:3.3854 train_time:543782ms step_avg:179.05ms
step:3048/5100 train_loss:3.5151 train_time:543929ms step_avg:179.04ms
step:3049/5100 train_loss:3.4585 train_time:544073ms step_avg:179.03ms
step:3050/5100 train_loss:3.3918 train_time:544627ms step_avg:179.15ms
step:3051/5100 train_loss:3.5133 train_time:544731ms step_avg:179.13ms
step:3052/5100 train_loss:3.3610 train_time:544866ms step_avg:179.11ms
step:3053/5100 train_loss:3.5957 train_time:545008ms step_avg:179.10ms
step:3054/5100 train_loss:3.5398 train_time:545148ms step_avg:179.09ms
step:3055/5100 train_loss:3.5203 train_time:545289ms step_avg:179.08ms
step:3056/5100 train_loss:3.5234 train_time:545430ms step_avg:179.06ms
step:3057/5100 train_loss:3.4085 train_time:545571ms step_avg:179.05ms
step:3058/5100 train_loss:3.4429 train_time:545719ms step_avg:179.04ms
step:3059/5100 train_loss:3.5189 train_time:545862ms step_avg:179.03ms
step:3060/5100 train_loss:3.4163 train_time:546412ms step_avg:179.15ms
step:3061/5100 train_loss:3.4752 train_time:546514ms step_avg:179.13ms
step:3062/5100 train_loss:3.4731 train_time:546655ms step_avg:179.11ms
step:3063/5100 train_loss:3.4103 train_time:546795ms step_avg:179.10ms
step:3064/5100 train_loss:3.3825 train_time:546935ms step_avg:179.09ms
step:3065/5100 train_loss:3.4005 train_time:547075ms step_avg:179.08ms
step:3066/5100 train_loss:3.3872 train_time:547215ms step_avg:179.06ms
step:3067/5100 train_loss:3.3767 train_time:547356ms step_avg:179.05ms
step:3068/5100 train_loss:3.3365 train_time:547502ms step_avg:179.04ms
step:3069/5100 train_loss:3.3736 train_time:547645ms step_avg:179.03ms
step:3070/5100 train_loss:3.3666 train_time:548203ms step_avg:179.15ms
step:3071/5100 train_loss:3.5537 train_time:548298ms step_avg:179.12ms
step:3072/5100 train_loss:3.4834 train_time:548438ms step_avg:179.11ms
step:3073/5100 train_loss:3.5170 train_time:548579ms step_avg:179.10ms
step:3074/5100 train_loss:3.5127 train_time:548727ms step_avg:179.09ms
step:3075/5100 train_loss:3.4621 train_time:548859ms step_avg:179.07ms
step:3076/5100 train_loss:3.5098 train_time:549000ms step_avg:179.06ms
step:3077/5100 train_loss:3.5666 train_time:549141ms step_avg:179.05ms
step:3078/5100 train_loss:3.3712 train_time:549290ms step_avg:179.04ms
step:3079/5100 train_loss:3.9038 train_time:549433ms step_avg:179.03ms
step:3080/5100 train_loss:3.4671 train_time:549989ms step_avg:179.15ms
step:3081/5100 train_loss:3.4262 train_time:550082ms step_avg:179.12ms
step:3082/5100 train_loss:3.5643 train_time:550223ms step_avg:179.11ms
step:3083/5100 train_loss:3.3850 train_time:550364ms step_avg:179.10ms
step:3084/5100 train_loss:3.4103 train_time:550505ms step_avg:179.08ms
step:3085/5100 train_loss:3.4580 train_time:550645ms step_avg:179.07ms
step:3086/5100 train_loss:3.5498 train_time:550787ms step_avg:179.06ms
step:3087/5100 train_loss:3.4629 train_time:550928ms step_avg:179.05ms
step:3088/5100 train_loss:3.3802 train_time:551075ms step_avg:179.04ms
step:3089/5100 train_loss:3.5326 train_time:551216ms step_avg:179.02ms
step:3090/5100 train_loss:3.3984 train_time:551771ms step_avg:179.15ms
step:3091/5100 train_loss:3.6502 train_time:551869ms step_avg:179.12ms
step:3092/5100 train_loss:4.2090 train_time:552010ms step_avg:179.11ms
step:3093/5100 train_loss:3.4875 train_time:552150ms step_avg:179.09ms
step:3094/5100 train_loss:3.3824 train_time:552290ms step_avg:179.08ms
step:3095/5100 train_loss:3.3403 train_time:552431ms step_avg:179.07ms
step:3096/5100 train_loss:3.5125 train_time:552570ms step_avg:179.06ms
step:3097/5100 train_loss:3.6260 train_time:552711ms step_avg:179.04ms
step:3098/5100 train_loss:3.4125 train_time:552857ms step_avg:179.03ms
step:3099/5100 train_loss:3.4442 train_time:552999ms step_avg:179.02ms
step:3100/5100 train_loss:3.6227 train_time:553554ms step_avg:179.14ms
step:3101/5100 train_loss:3.5243 train_time:553654ms step_avg:179.12ms
step:3102/5100 train_loss:3.5137 train_time:553793ms step_avg:179.11ms
step:3103/5100 train_loss:3.4238 train_time:553933ms step_avg:179.09ms
step:3104/5100 train_loss:3.6856 train_time:554073ms step_avg:179.08ms
step:3105/5100 train_loss:3.4969 train_time:554213ms step_avg:179.07ms
step:3106/5100 train_loss:3.3528 train_time:554353ms step_avg:179.05ms
step:3107/5100 train_loss:3.3817 train_time:554494ms step_avg:179.04ms
step:3108/5100 train_loss:3.3405 train_time:554641ms step_avg:179.03ms
step:3109/5100 train_loss:3.5654 train_time:554784ms step_avg:179.02ms
step:3110/5100 train_loss:3.4528 train_time:555337ms step_avg:179.14ms
step:3111/5100 train_loss:3.4887 train_time:555436ms step_avg:179.12ms
step:3112/5100 train_loss:3.4667 train_time:555577ms step_avg:179.10ms
step:3113/5100 train_loss:3.5189 train_time:555717ms step_avg:179.09ms
step:3114/5100 train_loss:3.4689 train_time:555857ms step_avg:179.08ms
step:3115/5100 train_loss:3.4825 train_time:555997ms step_avg:179.07ms
step:3116/5100 train_loss:3.5049 train_time:556137ms step_avg:179.05ms
step:3117/5100 train_loss:3.3641 train_time:556279ms step_avg:179.04ms
step:3118/5100 train_loss:3.3781 train_time:556425ms step_avg:179.03ms
step:3119/5100 train_loss:3.5767 train_time:556571ms step_avg:179.02ms
step:3120/5100 train_loss:3.5503 train_time:557121ms step_avg:179.14ms
step:3121/5100 train_loss:3.3378 train_time:557223ms step_avg:179.11ms
step:3122/5100 train_loss:3.5278 train_time:557363ms step_avg:179.10ms
step:3123/5100 train_loss:3.5791 train_time:557505ms step_avg:179.09ms
step:3124/5100 train_loss:3.5467 train_time:557646ms step_avg:179.08ms
step:3125/5100 train_loss:3.3433 train_time:557787ms step_avg:179.06ms
step:3125/5100 val_loss:3.4574 train_time:557849ms step_avg:179.08ms
step:3126/5100 train_loss:3.4235 train_time:557935ms step_avg:179.05ms
step:3127/5100 train_loss:3.4773 train_time:558082ms step_avg:179.04ms
step:3128/5100 train_loss:3.5497 train_time:558224ms step_avg:179.03ms
step:3129/5100 train_loss:3.6211 train_time:558365ms step_avg:179.02ms
step:3130/5100 train_loss:3.3288 train_time:558916ms step_avg:179.14ms
step:3131/5100 train_loss:3.4939 train_time:559015ms step_avg:179.11ms
step:3132/5100 train_loss:3.4940 train_time:559155ms step_avg:179.10ms
step:3133/5100 train_loss:3.5094 train_time:559296ms step_avg:179.09ms
step:3134/5100 train_loss:3.4215 train_time:559436ms step_avg:179.08ms
step:3135/5100 train_loss:3.5359 train_time:559576ms step_avg:179.06ms
step:3136/5100 train_loss:3.4499 train_time:559718ms step_avg:179.05ms
step:3137/5100 train_loss:3.5140 train_time:559859ms step_avg:179.04ms
step:3138/5100 train_loss:3.7012 train_time:560004ms step_avg:179.03ms
step:3139/5100 train_loss:3.6635 train_time:560146ms step_avg:179.02ms
step:3140/5100 train_loss:3.4328 train_time:560700ms step_avg:179.14ms
step:3141/5100 train_loss:3.4545 train_time:560797ms step_avg:179.11ms
step:3142/5100 train_loss:3.3715 train_time:560938ms step_avg:179.10ms
step:3143/5100 train_loss:3.4658 train_time:561079ms step_avg:179.09ms
step:3144/5100 train_loss:3.2671 train_time:561219ms step_avg:179.07ms
step:3145/5100 train_loss:3.5055 train_time:561360ms step_avg:179.06ms
step:3146/5100 train_loss:3.4188 train_time:561499ms step_avg:179.05ms
step:3147/5100 train_loss:3.4401 train_time:561640ms step_avg:179.04ms
step:3148/5100 train_loss:3.6090 train_time:561787ms step_avg:179.03ms
step:3149/5100 train_loss:3.7026 train_time:561930ms step_avg:179.02ms
step:3150/5100 train_loss:3.5662 train_time:562485ms step_avg:179.14ms
step:3151/5100 train_loss:3.3785 train_time:562582ms step_avg:179.11ms
step:3152/5100 train_loss:3.4174 train_time:562722ms step_avg:179.10ms
step:3153/5100 train_loss:3.4030 train_time:562863ms step_avg:179.08ms
step:3154/5100 train_loss:3.5215 train_time:563001ms step_avg:179.07ms
step:3155/5100 train_loss:3.3397 train_time:563141ms step_avg:179.06ms
step:3156/5100 train_loss:3.4782 train_time:563280ms step_avg:179.05ms
step:3157/5100 train_loss:3.4349 train_time:563422ms step_avg:179.03ms
step:3158/5100 train_loss:3.5443 train_time:563571ms step_avg:179.03ms
step:3159/5100 train_loss:3.6169 train_time:563715ms step_avg:179.01ms
step:3160/5100 train_loss:3.4573 train_time:564268ms step_avg:179.13ms
step:3161/5100 train_loss:3.5174 train_time:564368ms step_avg:179.11ms
step:3162/5100 train_loss:3.5858 train_time:564509ms step_avg:179.10ms
step:3163/5100 train_loss:3.4920 train_time:564649ms step_avg:179.08ms
step:3164/5100 train_loss:3.5500 train_time:564789ms step_avg:179.07ms
step:3165/5100 train_loss:3.3664 train_time:564931ms step_avg:179.06ms
step:3166/5100 train_loss:3.3542 train_time:565069ms step_avg:179.05ms
step:3167/5100 train_loss:3.3975 train_time:565210ms step_avg:179.03ms
step:3168/5100 train_loss:3.2214 train_time:565359ms step_avg:179.02ms
step:3169/5100 train_loss:3.3893 train_time:565498ms step_avg:179.01ms
step:3170/5100 train_loss:3.5361 train_time:566051ms step_avg:179.13ms
step:3171/5100 train_loss:3.5584 train_time:566151ms step_avg:179.10ms
step:3172/5100 train_loss:3.5202 train_time:566291ms step_avg:179.09ms
step:3173/5100 train_loss:3.4902 train_time:566431ms step_avg:179.08ms
step:3174/5100 train_loss:3.4660 train_time:566572ms step_avg:179.07ms
step:3175/5100 train_loss:3.4659 train_time:566712ms step_avg:179.06ms
step:3176/5100 train_loss:3.4654 train_time:566854ms step_avg:179.04ms
step:3177/5100 train_loss:3.3952 train_time:566996ms step_avg:179.03ms
step:3178/5100 train_loss:3.5212 train_time:567144ms step_avg:179.02ms
step:3179/5100 train_loss:3.5933 train_time:567286ms step_avg:179.01ms
step:3180/5100 train_loss:3.4420 train_time:567837ms step_avg:179.13ms
step:3181/5100 train_loss:3.4289 train_time:567937ms step_avg:179.10ms
step:3182/5100 train_loss:3.4764 train_time:568077ms step_avg:179.09ms
step:3183/5100 train_loss:3.5764 train_time:568218ms step_avg:179.08ms
step:3184/5100 train_loss:3.5848 train_time:568361ms step_avg:179.07ms
step:3185/5100 train_loss:3.4903 train_time:568498ms step_avg:179.05ms
step:3186/5100 train_loss:3.5546 train_time:568639ms step_avg:179.04ms
step:3187/5100 train_loss:3.5411 train_time:568779ms step_avg:179.03ms
step:3188/5100 train_loss:3.3351 train_time:568930ms step_avg:179.02ms
step:3189/5100 train_loss:3.5129 train_time:569069ms step_avg:179.01ms
step:3190/5100 train_loss:3.4514 train_time:569620ms step_avg:179.13ms
step:3191/5100 train_loss:3.4708 train_time:569721ms step_avg:179.10ms
step:3192/5100 train_loss:3.4341 train_time:569863ms step_avg:179.09ms
step:3193/5100 train_loss:3.3652 train_time:570000ms step_avg:179.08ms
step:3194/5100 train_loss:4.3832 train_time:570140ms step_avg:179.06ms
step:3195/5100 train_loss:3.5028 train_time:570283ms step_avg:179.05ms
step:3196/5100 train_loss:3.2716 train_time:570423ms step_avg:179.04ms
step:3197/5100 train_loss:3.4349 train_time:570563ms step_avg:179.03ms
step:3198/5100 train_loss:3.3258 train_time:570714ms step_avg:179.02ms
step:3199/5100 train_loss:3.4176 train_time:570854ms step_avg:179.01ms
step:3200/5100 train_loss:3.3531 train_time:571409ms step_avg:179.13ms
step:3201/5100 train_loss:3.4377 train_time:571507ms step_avg:179.10ms
step:3202/5100 train_loss:3.5217 train_time:571646ms step_avg:179.09ms
step:3203/5100 train_loss:3.3823 train_time:571787ms step_avg:179.08ms
step:3204/5100 train_loss:3.4212 train_time:571931ms step_avg:179.06ms
step:3205/5100 train_loss:3.5094 train_time:572068ms step_avg:179.05ms
step:3206/5100 train_loss:3.6711 train_time:572207ms step_avg:179.04ms
step:3207/5100 train_loss:3.2695 train_time:572350ms step_avg:179.03ms
step:3208/5100 train_loss:3.6202 train_time:572494ms step_avg:179.02ms
step:3209/5100 train_loss:3.4689 train_time:572638ms step_avg:179.01ms
step:3210/5100 train_loss:3.5383 train_time:573190ms step_avg:179.12ms
step:3211/5100 train_loss:3.6240 train_time:573289ms step_avg:179.10ms
step:3212/5100 train_loss:3.3079 train_time:573431ms step_avg:179.09ms
step:3213/5100 train_loss:3.3624 train_time:573652ms step_avg:179.10ms
step:3214/5100 train_loss:3.5718 train_time:573787ms step_avg:179.08ms
step:3215/5100 train_loss:3.3667 train_time:573926ms step_avg:179.07ms
step:3216/5100 train_loss:3.4362 train_time:574066ms step_avg:179.06ms
step:3217/5100 train_loss:3.3309 train_time:574206ms step_avg:179.05ms
step:3218/5100 train_loss:3.4664 train_time:574346ms step_avg:179.04ms
step:3219/5100 train_loss:3.5076 train_time:574486ms step_avg:179.02ms
step:3220/5100 train_loss:3.5570 train_time:575054ms step_avg:179.14ms
step:3221/5100 train_loss:3.4980 train_time:575150ms step_avg:179.12ms
step:3222/5100 train_loss:3.4961 train_time:575293ms step_avg:179.11ms
step:3223/5100 train_loss:3.3677 train_time:575435ms step_avg:179.10ms
step:3224/5100 train_loss:3.3868 train_time:575575ms step_avg:179.08ms
step:3225/5100 train_loss:3.3899 train_time:575717ms step_avg:179.07ms
step:3226/5100 train_loss:3.4277 train_time:575858ms step_avg:179.06ms
step:3227/5100 train_loss:3.3537 train_time:575999ms step_avg:179.05ms
step:3228/5100 train_loss:3.2884 train_time:576144ms step_avg:179.04ms
step:3229/5100 train_loss:3.4079 train_time:576286ms step_avg:179.03ms
step:3230/5100 train_loss:3.1797 train_time:576965ms step_avg:179.18ms
step:3231/5100 train_loss:3.3574 train_time:577064ms step_avg:179.16ms
step:3232/5100 train_loss:3.3486 train_time:577204ms step_avg:179.14ms
step:3233/5100 train_loss:3.5949 train_time:577345ms step_avg:179.13ms
step:3234/5100 train_loss:3.5732 train_time:577485ms step_avg:179.12ms
step:3235/5100 train_loss:3.5377 train_time:577625ms step_avg:179.11ms
step:3236/5100 train_loss:3.4323 train_time:577766ms step_avg:179.10ms
step:3237/5100 train_loss:3.5876 train_time:577908ms step_avg:179.09ms
step:3238/5100 train_loss:3.4543 train_time:578055ms step_avg:179.08ms
step:3239/5100 train_loss:3.5745 train_time:578197ms step_avg:179.06ms
step:3240/5100 train_loss:3.5466 train_time:578750ms step_avg:179.18ms
step:3241/5100 train_loss:3.4425 train_time:578850ms step_avg:179.16ms
step:3242/5100 train_loss:3.4009 train_time:578990ms step_avg:179.14ms
step:3243/5100 train_loss:3.6222 train_time:579130ms step_avg:179.13ms
step:3244/5100 train_loss:3.4919 train_time:579270ms step_avg:179.12ms
step:3245/5100 train_loss:3.5384 train_time:579411ms step_avg:179.11ms
step:3246/5100 train_loss:3.4290 train_time:579553ms step_avg:179.10ms
step:3247/5100 train_loss:3.5601 train_time:579692ms step_avg:179.08ms
step:3248/5100 train_loss:3.4916 train_time:579840ms step_avg:179.07ms
step:3249/5100 train_loss:3.4326 train_time:579983ms step_avg:179.06ms
step:3250/5100 train_loss:3.3024 train_time:580534ms step_avg:179.18ms
step:3250/5100 val_loss:3.4482 train_time:580558ms step_avg:179.18ms
step:3251/5100 train_loss:3.5117 train_time:580645ms step_avg:179.16ms
step:3252/5100 train_loss:3.5059 train_time:580793ms step_avg:179.15ms
step:3253/5100 train_loss:3.4630 train_time:580935ms step_avg:179.14ms
step:3254/5100 train_loss:3.3791 train_time:581077ms step_avg:179.12ms
step:3255/5100 train_loss:3.5297 train_time:581218ms step_avg:179.11ms
step:3256/5100 train_loss:3.5623 train_time:581358ms step_avg:179.10ms
step:3257/5100 train_loss:3.5047 train_time:581501ms step_avg:179.09ms
step:3258/5100 train_loss:3.5335 train_time:581640ms step_avg:179.08ms
step:3259/5100 train_loss:3.3682 train_time:581785ms step_avg:179.07ms
step:3260/5100 train_loss:3.4521 train_time:582340ms step_avg:179.18ms
step:3261/5100 train_loss:3.3247 train_time:582440ms step_avg:179.16ms
step:3262/5100 train_loss:3.3590 train_time:582580ms step_avg:179.15ms
step:3263/5100 train_loss:3.3909 train_time:582720ms step_avg:179.13ms
step:3264/5100 train_loss:3.5441 train_time:582860ms step_avg:179.12ms
step:3265/5100 train_loss:3.4292 train_time:583000ms step_avg:179.11ms
step:3266/5100 train_loss:3.4819 train_time:583140ms step_avg:179.10ms
step:3267/5100 train_loss:3.4954 train_time:583281ms step_avg:179.09ms
step:3268/5100 train_loss:3.5892 train_time:583430ms step_avg:179.08ms
step:3269/5100 train_loss:3.4008 train_time:583572ms step_avg:179.06ms
step:3270/5100 train_loss:3.5248 train_time:584123ms step_avg:179.18ms
step:3271/5100 train_loss:3.3904 train_time:584238ms step_avg:179.16ms
step:3272/5100 train_loss:3.2944 train_time:584366ms step_avg:179.14ms
step:3273/5100 train_loss:3.4009 train_time:584508ms step_avg:179.13ms
step:3274/5100 train_loss:3.5392 train_time:584647ms step_avg:179.12ms
step:3275/5100 train_loss:3.3361 train_time:584788ms step_avg:179.11ms
step:3276/5100 train_loss:3.4891 train_time:584927ms step_avg:179.10ms
step:3277/5100 train_loss:3.4796 train_time:585068ms step_avg:179.08ms
step:3278/5100 train_loss:3.4744 train_time:585213ms step_avg:179.07ms
step:3279/5100 train_loss:3.4443 train_time:585358ms step_avg:179.06ms
step:3280/5100 train_loss:3.5981 train_time:585911ms step_avg:179.18ms
step:3281/5100 train_loss:3.4452 train_time:586011ms step_avg:179.15ms
step:3282/5100 train_loss:3.4964 train_time:586151ms step_avg:179.14ms
step:3283/5100 train_loss:3.3512 train_time:586293ms step_avg:179.13ms
step:3284/5100 train_loss:3.4812 train_time:586432ms step_avg:179.12ms
step:3285/5100 train_loss:3.5293 train_time:586572ms step_avg:179.11ms
step:3286/5100 train_loss:3.5163 train_time:586713ms step_avg:179.09ms
step:3287/5100 train_loss:3.5567 train_time:586856ms step_avg:179.08ms
step:3288/5100 train_loss:3.4260 train_time:587002ms step_avg:179.07ms
step:3289/5100 train_loss:3.5385 train_time:587145ms step_avg:179.06ms
step:3290/5100 train_loss:3.4637 train_time:587697ms step_avg:179.18ms
step:3291/5100 train_loss:3.3510 train_time:587799ms step_avg:179.15ms
step:3292/5100 train_loss:3.4730 train_time:587938ms step_avg:179.14ms
step:3293/5100 train_loss:3.5081 train_time:588079ms step_avg:179.13ms
step:3294/5100 train_loss:3.4904 train_time:588222ms step_avg:179.12ms
step:3295/5100 train_loss:3.3725 train_time:588359ms step_avg:179.10ms
step:3296/5100 train_loss:3.4351 train_time:588500ms step_avg:179.09ms
step:3297/5100 train_loss:3.4779 train_time:588640ms step_avg:179.08ms
step:3298/5100 train_loss:3.4709 train_time:588788ms step_avg:179.07ms
step:3299/5100 train_loss:3.4524 train_time:588930ms step_avg:179.06ms
step:3300/5100 train_loss:3.5184 train_time:589484ms step_avg:179.17ms
step:3301/5100 train_loss:3.4203 train_time:589584ms step_avg:179.15ms
step:3302/5100 train_loss:3.4841 train_time:589722ms step_avg:179.14ms
step:3303/5100 train_loss:3.4342 train_time:589863ms step_avg:179.13ms
step:3304/5100 train_loss:3.4451 train_time:590003ms step_avg:179.11ms
step:3305/5100 train_loss:3.4473 train_time:590143ms step_avg:179.10ms
step:3306/5100 train_loss:3.5426 train_time:590283ms step_avg:179.09ms
step:3307/5100 train_loss:3.4700 train_time:590424ms step_avg:179.08ms
step:3308/5100 train_loss:3.4214 train_time:590571ms step_avg:179.07ms
step:3309/5100 train_loss:3.5579 train_time:590714ms step_avg:179.06ms
step:3310/5100 train_loss:3.4269 train_time:591266ms step_avg:179.17ms
step:3311/5100 train_loss:3.3718 train_time:591369ms step_avg:179.15ms
step:3312/5100 train_loss:3.4821 train_time:591509ms step_avg:179.14ms
step:3313/5100 train_loss:3.4440 train_time:591649ms step_avg:179.12ms
step:3314/5100 train_loss:3.6475 train_time:591789ms step_avg:179.11ms
step:3315/5100 train_loss:3.4835 train_time:591932ms step_avg:179.10ms
step:3316/5100 train_loss:3.4458 train_time:592069ms step_avg:179.09ms
step:3317/5100 train_loss:3.0793 train_time:592211ms step_avg:179.08ms
step:3318/5100 train_loss:3.5821 train_time:592356ms step_avg:179.07ms
step:3319/5100 train_loss:3.4243 train_time:592499ms step_avg:179.06ms
step:3320/5100 train_loss:3.5024 train_time:593051ms step_avg:179.17ms
step:3321/5100 train_loss:3.4234 train_time:593153ms step_avg:179.15ms
step:3322/5100 train_loss:3.4941 train_time:593294ms step_avg:179.13ms
step:3323/5100 train_loss:3.4348 train_time:593435ms step_avg:179.12ms
step:3324/5100 train_loss:3.3603 train_time:593577ms step_avg:179.11ms
step:3325/5100 train_loss:3.2916 train_time:593719ms step_avg:179.10ms
step:3326/5100 train_loss:3.4594 train_time:593858ms step_avg:179.09ms
step:3327/5100 train_loss:3.4167 train_time:594000ms step_avg:179.08ms
step:3328/5100 train_loss:3.3437 train_time:594147ms step_avg:179.07ms
step:3329/5100 train_loss:3.3853 train_time:594287ms step_avg:179.06ms
step:3330/5100 train_loss:3.3347 train_time:594837ms step_avg:179.17ms
step:3331/5100 train_loss:3.5822 train_time:594938ms step_avg:179.14ms
step:3332/5100 train_loss:3.4797 train_time:595079ms step_avg:179.13ms
step:3333/5100 train_loss:3.4705 train_time:595219ms step_avg:179.12ms
step:3334/5100 train_loss:3.3285 train_time:595360ms step_avg:179.11ms
step:3335/5100 train_loss:3.3928 train_time:595500ms step_avg:179.10ms
step:3336/5100 train_loss:3.5007 train_time:595643ms step_avg:179.09ms
step:3337/5100 train_loss:3.4708 train_time:595782ms step_avg:179.07ms
step:3338/5100 train_loss:3.5049 train_time:595930ms step_avg:179.07ms
step:3339/5100 train_loss:3.4280 train_time:596073ms step_avg:179.05ms
step:3340/5100 train_loss:3.4621 train_time:596629ms step_avg:179.17ms
step:3341/5100 train_loss:3.4745 train_time:596727ms step_avg:179.14ms
step:3342/5100 train_loss:3.4826 train_time:596867ms step_avg:179.13ms
step:3343/5100 train_loss:3.4759 train_time:597009ms step_avg:179.12ms
step:3344/5100 train_loss:3.4011 train_time:597151ms step_avg:179.11ms
step:3345/5100 train_loss:3.3146 train_time:597290ms step_avg:179.10ms
step:3346/5100 train_loss:3.6419 train_time:597430ms step_avg:179.09ms
step:3347/5100 train_loss:3.4001 train_time:597571ms step_avg:179.07ms
step:3348/5100 train_loss:3.5598 train_time:597717ms step_avg:179.06ms
step:3349/5100 train_loss:3.4329 train_time:597861ms step_avg:179.05ms
step:3350/5100 train_loss:3.5168 train_time:598418ms step_avg:179.17ms
step:3351/5100 train_loss:3.2551 train_time:598513ms step_avg:179.14ms
step:3352/5100 train_loss:3.2836 train_time:598655ms step_avg:179.13ms
step:3353/5100 train_loss:3.4616 train_time:598799ms step_avg:179.12ms
step:3354/5100 train_loss:3.3320 train_time:598936ms step_avg:179.11ms
step:3355/5100 train_loss:3.4810 train_time:599078ms step_avg:179.10ms
step:3356/5100 train_loss:3.3519 train_time:599219ms step_avg:179.09ms
step:3357/5100 train_loss:3.5207 train_time:599361ms step_avg:179.07ms
step:3358/5100 train_loss:3.3684 train_time:599506ms step_avg:179.06ms
step:3359/5100 train_loss:3.5469 train_time:599649ms step_avg:179.05ms
step:3360/5100 train_loss:3.3508 train_time:600201ms step_avg:179.16ms
step:3361/5100 train_loss:3.9100 train_time:600301ms step_avg:179.14ms
step:3362/5100 train_loss:3.5134 train_time:600441ms step_avg:179.13ms
step:3363/5100 train_loss:3.5800 train_time:600582ms step_avg:179.12ms
step:3364/5100 train_loss:3.4479 train_time:600722ms step_avg:179.11ms
step:3365/5100 train_loss:3.5856 train_time:600863ms step_avg:179.09ms
step:3366/5100 train_loss:3.4722 train_time:601002ms step_avg:179.08ms
step:3367/5100 train_loss:3.6490 train_time:601142ms step_avg:179.07ms
step:3368/5100 train_loss:3.4567 train_time:601290ms step_avg:179.06ms
step:3369/5100 train_loss:3.4628 train_time:601433ms step_avg:179.05ms
step:3370/5100 train_loss:3.4343 train_time:601961ms step_avg:179.16ms
step:3371/5100 train_loss:3.3863 train_time:602072ms step_avg:179.13ms
step:3372/5100 train_loss:3.3815 train_time:602211ms step_avg:179.12ms
step:3373/5100 train_loss:3.4493 train_time:602351ms step_avg:179.11ms
step:3374/5100 train_loss:3.4719 train_time:602494ms step_avg:179.10ms
step:3375/5100 train_loss:3.4486 train_time:602631ms step_avg:179.09ms
step:3375/5100 val_loss:3.4522 train_time:602693ms step_avg:179.11ms
step:3376/5100 train_loss:3.4849 train_time:602780ms step_avg:179.08ms
step:3377/5100 train_loss:3.4824 train_time:602927ms step_avg:179.07ms
step:3378/5100 train_loss:3.5668 train_time:603070ms step_avg:179.06ms
step:3379/5100 train_loss:3.4241 train_time:603212ms step_avg:179.05ms
step:3380/5100 train_loss:3.4312 train_time:603738ms step_avg:179.15ms
step:3381/5100 train_loss:3.4329 train_time:603857ms step_avg:179.13ms
step:3382/5100 train_loss:3.5393 train_time:603996ms step_avg:179.12ms
step:3383/5100 train_loss:3.3767 train_time:604137ms step_avg:179.11ms
step:3384/5100 train_loss:3.5519 train_time:604276ms step_avg:179.10ms
step:3385/5100 train_loss:3.4003 train_time:604417ms step_avg:179.09ms
step:3386/5100 train_loss:3.4282 train_time:604556ms step_avg:179.07ms
step:3387/5100 train_loss:3.3650 train_time:604697ms step_avg:179.06ms
step:3388/5100 train_loss:3.5420 train_time:604845ms step_avg:179.05ms
step:3389/5100 train_loss:3.5024 train_time:604987ms step_avg:179.04ms
step:3390/5100 train_loss:3.5218 train_time:605519ms step_avg:179.15ms
step:3391/5100 train_loss:3.4990 train_time:605637ms step_avg:179.13ms
step:3392/5100 train_loss:3.4416 train_time:605778ms step_avg:179.12ms
step:3393/5100 train_loss:3.5610 train_time:605918ms step_avg:179.11ms
step:3394/5100 train_loss:3.5188 train_time:606062ms step_avg:179.10ms
step:3395/5100 train_loss:3.6075 train_time:606199ms step_avg:179.08ms
step:3396/5100 train_loss:3.4702 train_time:606340ms step_avg:179.07ms
step:3397/5100 train_loss:3.4531 train_time:606481ms step_avg:179.06ms
step:3398/5100 train_loss:3.4103 train_time:606630ms step_avg:179.05ms
step:3399/5100 train_loss:3.4636 train_time:606772ms step_avg:179.04ms
step:3400/5100 train_loss:3.4635 train_time:607308ms step_avg:179.15ms
step:3401/5100 train_loss:3.5488 train_time:607424ms step_avg:179.13ms
step:3402/5100 train_loss:3.4198 train_time:607646ms step_avg:179.14ms
step:3403/5100 train_loss:3.6015 train_time:607782ms step_avg:179.13ms
step:3404/5100 train_loss:3.4290 train_time:607921ms step_avg:179.12ms
step:3405/5100 train_loss:3.4361 train_time:608061ms step_avg:179.10ms
step:3406/5100 train_loss:3.3904 train_time:608203ms step_avg:179.09ms
step:3407/5100 train_loss:3.4539 train_time:608340ms step_avg:179.08ms
step:3408/5100 train_loss:3.4576 train_time:608482ms step_avg:179.07ms
step:3409/5100 train_loss:3.4429 train_time:608630ms step_avg:179.06ms
step:3410/5100 train_loss:3.4527 train_time:609171ms step_avg:179.17ms
step:3411/5100 train_loss:3.4203 train_time:609282ms step_avg:179.15ms
step:3412/5100 train_loss:3.4477 train_time:609423ms step_avg:179.14ms
step:3413/5100 train_loss:3.3767 train_time:609567ms step_avg:179.13ms
step:3414/5100 train_loss:3.5949 train_time:609703ms step_avg:179.11ms
step:3415/5100 train_loss:3.3405 train_time:609844ms step_avg:179.10ms
step:3416/5100 train_loss:3.5003 train_time:609984ms step_avg:179.09ms
step:3417/5100 train_loss:3.3829 train_time:610125ms step_avg:179.08ms
step:3418/5100 train_loss:3.4792 train_time:610272ms step_avg:179.07ms
step:3419/5100 train_loss:3.4862 train_time:610414ms step_avg:179.06ms
step:3420/5100 train_loss:3.5154 train_time:611085ms step_avg:179.20ms
step:3421/5100 train_loss:3.3895 train_time:611187ms step_avg:179.18ms
step:3422/5100 train_loss:3.4285 train_time:611329ms step_avg:179.17ms
step:3423/5100 train_loss:3.3589 train_time:611470ms step_avg:179.16ms
step:3424/5100 train_loss:3.6823 train_time:611610ms step_avg:179.15ms
step:3425/5100 train_loss:3.5694 train_time:611751ms step_avg:179.14ms
step:3426/5100 train_loss:3.4413 train_time:611891ms step_avg:179.12ms
step:3427/5100 train_loss:3.3983 train_time:612032ms step_avg:179.11ms
step:3428/5100 train_loss:3.3758 train_time:612181ms step_avg:179.11ms
step:3429/5100 train_loss:3.3834 train_time:612322ms step_avg:179.09ms
step:3430/5100 train_loss:3.4389 train_time:612869ms step_avg:179.20ms
step:3431/5100 train_loss:3.4670 train_time:612975ms step_avg:179.18ms
step:3432/5100 train_loss:3.5617 train_time:613115ms step_avg:179.17ms
step:3433/5100 train_loss:3.3796 train_time:613254ms step_avg:179.16ms
step:3434/5100 train_loss:3.5968 train_time:613394ms step_avg:179.15ms
step:3435/5100 train_loss:3.5151 train_time:613534ms step_avg:179.13ms
step:3436/5100 train_loss:3.3584 train_time:613676ms step_avg:179.12ms
step:3437/5100 train_loss:3.4040 train_time:613814ms step_avg:179.11ms
step:3438/5100 train_loss:3.4497 train_time:613963ms step_avg:179.10ms
step:3439/5100 train_loss:3.5475 train_time:614103ms step_avg:179.09ms
step:3440/5100 train_loss:3.3221 train_time:614655ms step_avg:179.20ms
step:3441/5100 train_loss:3.4998 train_time:614756ms step_avg:179.18ms
step:3442/5100 train_loss:3.4015 train_time:614896ms step_avg:179.17ms
step:3443/5100 train_loss:3.5801 train_time:615036ms step_avg:179.15ms
step:3444/5100 train_loss:3.4476 train_time:615176ms step_avg:179.14ms
step:3445/5100 train_loss:3.3377 train_time:615316ms step_avg:179.13ms
step:3446/5100 train_loss:3.5525 train_time:615456ms step_avg:179.12ms
step:3447/5100 train_loss:3.6219 train_time:615597ms step_avg:179.11ms
step:3448/5100 train_loss:3.4336 train_time:615744ms step_avg:179.10ms
step:3449/5100 train_loss:3.4497 train_time:615886ms step_avg:179.09ms
step:3450/5100 train_loss:3.5336 train_time:616441ms step_avg:179.20ms
step:3451/5100 train_loss:3.5407 train_time:616543ms step_avg:179.18ms
step:3452/5100 train_loss:3.5433 train_time:616683ms step_avg:179.16ms
step:3453/5100 train_loss:3.3528 train_time:616823ms step_avg:179.15ms
step:3454/5100 train_loss:3.4683 train_time:616963ms step_avg:179.14ms
step:3455/5100 train_loss:3.3581 train_time:617103ms step_avg:179.13ms
step:3456/5100 train_loss:3.6384 train_time:617243ms step_avg:179.12ms
step:3457/5100 train_loss:3.3141 train_time:617385ms step_avg:179.11ms
step:3458/5100 train_loss:3.4568 train_time:617533ms step_avg:179.10ms
step:3459/5100 train_loss:3.4051 train_time:617675ms step_avg:179.09ms
step:3460/5100 train_loss:3.4014 train_time:618231ms step_avg:179.20ms
step:3461/5100 train_loss:3.4026 train_time:618330ms step_avg:179.17ms
step:3462/5100 train_loss:3.4102 train_time:618469ms step_avg:179.16ms
step:3463/5100 train_loss:3.5120 train_time:618610ms step_avg:179.15ms
step:3464/5100 train_loss:3.3835 train_time:618751ms step_avg:179.14ms
step:3465/5100 train_loss:3.3986 train_time:618893ms step_avg:179.13ms
step:3466/5100 train_loss:3.3765 train_time:619031ms step_avg:179.12ms
step:3467/5100 train_loss:3.5328 train_time:619173ms step_avg:179.11ms
step:3468/5100 train_loss:3.4129 train_time:619320ms step_avg:179.10ms
step:3469/5100 train_loss:3.4378 train_time:619462ms step_avg:179.09ms
step:3470/5100 train_loss:3.6226 train_time:620017ms step_avg:179.20ms
step:3471/5100 train_loss:3.5253 train_time:620116ms step_avg:179.17ms
step:3472/5100 train_loss:3.5642 train_time:620256ms step_avg:179.16ms
step:3473/5100 train_loss:4.1947 train_time:620394ms step_avg:179.15ms
step:3474/5100 train_loss:3.4379 train_time:620534ms step_avg:179.14ms
step:3475/5100 train_loss:3.4474 train_time:620679ms step_avg:179.13ms
step:3476/5100 train_loss:3.4329 train_time:620814ms step_avg:179.12ms
step:3477/5100 train_loss:3.3758 train_time:620955ms step_avg:179.10ms
step:3478/5100 train_loss:3.4451 train_time:621100ms step_avg:179.09ms
step:3479/5100 train_loss:3.4422 train_time:621243ms step_avg:179.08ms
step:3480/5100 train_loss:3.3490 train_time:621798ms step_avg:179.19ms
step:3481/5100 train_loss:3.6444 train_time:621896ms step_avg:179.17ms
step:3482/5100 train_loss:3.5093 train_time:622037ms step_avg:179.16ms
step:3483/5100 train_loss:3.4574 train_time:622178ms step_avg:179.15ms
step:3484/5100 train_loss:3.4783 train_time:622316ms step_avg:179.14ms
step:3485/5100 train_loss:3.4481 train_time:622457ms step_avg:179.12ms
step:3486/5100 train_loss:3.6302 train_time:622598ms step_avg:179.11ms
step:3487/5100 train_loss:3.6666 train_time:622736ms step_avg:179.10ms
step:3488/5100 train_loss:3.5233 train_time:622882ms step_avg:179.09ms
step:3489/5100 train_loss:3.3769 train_time:623024ms step_avg:179.08ms
step:3490/5100 train_loss:3.5490 train_time:623575ms step_avg:179.19ms
step:3491/5100 train_loss:3.4511 train_time:623677ms step_avg:179.17ms
step:3492/5100 train_loss:3.4906 train_time:623815ms step_avg:179.15ms
step:3493/5100 train_loss:3.3240 train_time:623963ms step_avg:179.15ms
step:3494/5100 train_loss:3.4685 train_time:624095ms step_avg:179.13ms
step:3495/5100 train_loss:3.4219 train_time:624235ms step_avg:179.12ms
step:3496/5100 train_loss:3.4395 train_time:624375ms step_avg:179.11ms
step:3497/5100 train_loss:3.6069 train_time:624518ms step_avg:179.10ms
step:3498/5100 train_loss:3.4444 train_time:624664ms step_avg:179.09ms
step:3499/5100 train_loss:3.4661 train_time:624806ms step_avg:179.08ms
step:3500/5100 train_loss:3.4649 train_time:625361ms step_avg:179.19ms
step:3500/5100 val_loss:3.4351 train_time:625382ms step_avg:179.19ms
step:3501/5100 train_loss:3.5083 train_time:625470ms step_avg:179.17ms
step:3502/5100 train_loss:3.5817 train_time:625617ms step_avg:179.16ms
step:3503/5100 train_loss:3.2938 train_time:625760ms step_avg:179.15ms
step:3504/5100 train_loss:3.4494 train_time:625903ms step_avg:179.14ms
step:3505/5100 train_loss:3.4746 train_time:626042ms step_avg:179.13ms
step:3506/5100 train_loss:3.4984 train_time:626183ms step_avg:179.11ms
step:3507/5100 train_loss:3.3717 train_time:626323ms step_avg:179.10ms
step:3508/5100 train_loss:3.5209 train_time:626465ms step_avg:179.09ms
step:3509/5100 train_loss:3.4128 train_time:626608ms step_avg:179.08ms
step:3510/5100 train_loss:3.6245 train_time:627164ms step_avg:179.19ms
step:3511/5100 train_loss:3.4366 train_time:627267ms step_avg:179.17ms
step:3512/5100 train_loss:3.3805 train_time:627407ms step_avg:179.16ms
step:3513/5100 train_loss:3.4451 train_time:627547ms step_avg:179.15ms
step:3514/5100 train_loss:3.4098 train_time:627688ms step_avg:179.13ms
step:3515/5100 train_loss:3.4641 train_time:627828ms step_avg:179.12ms
step:3516/5100 train_loss:3.4589 train_time:627968ms step_avg:179.11ms
step:3517/5100 train_loss:3.4344 train_time:628113ms step_avg:179.10ms
step:3518/5100 train_loss:3.4556 train_time:628257ms step_avg:179.09ms
step:3519/5100 train_loss:3.4529 train_time:628400ms step_avg:179.08ms
step:3520/5100 train_loss:3.4797 train_time:628951ms step_avg:179.19ms
step:3521/5100 train_loss:3.5361 train_time:629052ms step_avg:179.17ms
step:3522/5100 train_loss:3.4508 train_time:629193ms step_avg:179.16ms
step:3523/5100 train_loss:3.3766 train_time:629333ms step_avg:179.14ms
step:3524/5100 train_loss:3.4179 train_time:629472ms step_avg:179.13ms
step:3525/5100 train_loss:3.4091 train_time:629611ms step_avg:179.12ms
step:3526/5100 train_loss:3.4143 train_time:629751ms step_avg:179.11ms
step:3527/5100 train_loss:3.5403 train_time:629893ms step_avg:179.10ms
step:3528/5100 train_loss:3.3737 train_time:630043ms step_avg:179.09ms
step:3529/5100 train_loss:3.2601 train_time:630184ms step_avg:179.08ms
step:3530/5100 train_loss:3.5553 train_time:630736ms step_avg:179.19ms
step:3531/5100 train_loss:3.3624 train_time:630835ms step_avg:179.16ms
step:3532/5100 train_loss:3.3971 train_time:630975ms step_avg:179.15ms
step:3533/5100 train_loss:3.3129 train_time:631119ms step_avg:179.14ms
step:3534/5100 train_loss:3.3774 train_time:631256ms step_avg:179.13ms
step:3535/5100 train_loss:3.3427 train_time:631399ms step_avg:179.12ms
step:3536/5100 train_loss:3.5237 train_time:631538ms step_avg:179.11ms
step:3537/5100 train_loss:3.4776 train_time:631681ms step_avg:179.10ms
step:3538/5100 train_loss:3.5083 train_time:631829ms step_avg:179.09ms
step:3539/5100 train_loss:3.4058 train_time:631975ms step_avg:179.08ms
step:3540/5100 train_loss:3.3764 train_time:632523ms step_avg:179.18ms
step:3541/5100 train_loss:3.5168 train_time:632623ms step_avg:179.16ms
step:3542/5100 train_loss:3.3637 train_time:632764ms step_avg:179.15ms
step:3543/5100 train_loss:3.5799 train_time:632904ms step_avg:179.14ms
step:3544/5100 train_loss:3.6998 train_time:633045ms step_avg:179.13ms
step:3545/5100 train_loss:3.5115 train_time:633186ms step_avg:179.12ms
step:3546/5100 train_loss:3.5526 train_time:633326ms step_avg:179.11ms
step:3547/5100 train_loss:3.3035 train_time:633466ms step_avg:179.10ms
step:3548/5100 train_loss:3.3916 train_time:633617ms step_avg:179.09ms
step:3549/5100 train_loss:3.4195 train_time:633757ms step_avg:179.08ms
step:3550/5100 train_loss:3.5045 train_time:634310ms step_avg:179.18ms
step:3551/5100 train_loss:3.4732 train_time:634412ms step_avg:179.16ms
step:3552/5100 train_loss:3.4009 train_time:634553ms step_avg:179.15ms
step:3553/5100 train_loss:3.5124 train_time:634696ms step_avg:179.14ms
step:3554/5100 train_loss:3.4476 train_time:634833ms step_avg:179.13ms
step:3555/5100 train_loss:3.4089 train_time:634975ms step_avg:179.12ms
step:3556/5100 train_loss:3.3479 train_time:635116ms step_avg:179.11ms
step:3557/5100 train_loss:3.3081 train_time:635257ms step_avg:179.10ms
step:3558/5100 train_loss:3.4105 train_time:635405ms step_avg:179.09ms
step:3559/5100 train_loss:3.4401 train_time:635548ms step_avg:179.08ms
step:3560/5100 train_loss:3.6536 train_time:636100ms step_avg:179.18ms
step:3561/5100 train_loss:3.5155 train_time:636201ms step_avg:179.16ms
step:3562/5100 train_loss:3.4181 train_time:636340ms step_avg:179.15ms
step:3563/5100 train_loss:3.2978 train_time:636481ms step_avg:179.14ms
step:3564/5100 train_loss:3.8177 train_time:636621ms step_avg:179.13ms
step:3565/5100 train_loss:3.3840 train_time:636762ms step_avg:179.12ms
step:3566/5100 train_loss:3.3280 train_time:636902ms step_avg:179.11ms
step:3567/5100 train_loss:3.3463 train_time:637043ms step_avg:179.10ms
step:3568/5100 train_loss:3.4908 train_time:637194ms step_avg:179.09ms
step:3569/5100 train_loss:3.4205 train_time:637331ms step_avg:179.08ms
step:3570/5100 train_loss:3.5379 train_time:637881ms step_avg:179.18ms
step:3571/5100 train_loss:3.4536 train_time:637983ms step_avg:179.16ms
step:3572/5100 train_loss:3.7403 train_time:638123ms step_avg:179.15ms
step:3573/5100 train_loss:3.3616 train_time:638263ms step_avg:179.14ms
step:3574/5100 train_loss:3.4470 train_time:638403ms step_avg:179.13ms
step:3575/5100 train_loss:3.6099 train_time:638548ms step_avg:179.12ms
step:3576/5100 train_loss:3.4820 train_time:638684ms step_avg:179.10ms
step:3577/5100 train_loss:3.4183 train_time:638825ms step_avg:179.09ms
step:3578/5100 train_loss:3.3887 train_time:638973ms step_avg:179.08ms
step:3579/5100 train_loss:3.4586 train_time:639115ms step_avg:179.07ms
step:3580/5100 train_loss:3.4129 train_time:639668ms step_avg:179.18ms
step:3581/5100 train_loss:3.3145 train_time:639768ms step_avg:179.16ms
step:3582/5100 train_loss:3.3870 train_time:639907ms step_avg:179.15ms
step:3583/5100 train_loss:3.3375 train_time:640048ms step_avg:179.13ms
step:3584/5100 train_loss:3.4371 train_time:640188ms step_avg:179.12ms
step:3585/5100 train_loss:3.5365 train_time:640330ms step_avg:179.11ms
step:3586/5100 train_loss:3.3870 train_time:640471ms step_avg:179.10ms
step:3587/5100 train_loss:3.4337 train_time:640611ms step_avg:179.09ms
step:3588/5100 train_loss:3.4340 train_time:640757ms step_avg:179.08ms
step:3589/5100 train_loss:3.4149 train_time:640900ms step_avg:179.07ms
step:3590/5100 train_loss:3.4218 train_time:641452ms step_avg:179.18ms
step:3591/5100 train_loss:3.5398 train_time:641681ms step_avg:179.19ms
step:3592/5100 train_loss:3.4071 train_time:641816ms step_avg:179.18ms
step:3593/5100 train_loss:3.4973 train_time:641956ms step_avg:179.17ms
step:3594/5100 train_loss:3.4830 train_time:642100ms step_avg:179.16ms
step:3595/5100 train_loss:3.4381 train_time:642240ms step_avg:179.15ms
step:3596/5100 train_loss:3.3649 train_time:642379ms step_avg:179.14ms
step:3597/5100 train_loss:3.3706 train_time:642520ms step_avg:179.12ms
step:3598/5100 train_loss:3.6377 train_time:642664ms step_avg:179.11ms
step:3599/5100 train_loss:3.4250 train_time:642807ms step_avg:179.10ms
step:3600/5100 train_loss:3.4389 train_time:643362ms step_avg:179.21ms
step:3601/5100 train_loss:3.2976 train_time:643461ms step_avg:179.19ms
step:3602/5100 train_loss:3.4705 train_time:643602ms step_avg:179.18ms
step:3603/5100 train_loss:3.4173 train_time:643742ms step_avg:179.17ms
step:3604/5100 train_loss:3.5342 train_time:643881ms step_avg:179.15ms
step:3605/5100 train_loss:3.6179 train_time:644022ms step_avg:179.14ms
step:3606/5100 train_loss:3.4189 train_time:644162ms step_avg:179.13ms
step:3607/5100 train_loss:3.4549 train_time:644302ms step_avg:179.12ms
step:3608/5100 train_loss:3.7403 train_time:644450ms step_avg:179.11ms
step:3609/5100 train_loss:3.4144 train_time:644591ms step_avg:179.10ms
step:3610/5100 train_loss:3.5664 train_time:645255ms step_avg:179.24ms
step:3611/5100 train_loss:3.3145 train_time:645362ms step_avg:179.22ms
step:3612/5100 train_loss:3.4185 train_time:645505ms step_avg:179.21ms
step:3613/5100 train_loss:3.4900 train_time:645646ms step_avg:179.20ms
step:3614/5100 train_loss:3.6908 train_time:645784ms step_avg:179.19ms
step:3615/5100 train_loss:3.6992 train_time:645924ms step_avg:179.17ms
step:3616/5100 train_loss:3.3539 train_time:646064ms step_avg:179.16ms
step:3617/5100 train_loss:3.4415 train_time:646205ms step_avg:179.15ms
step:3618/5100 train_loss:3.4140 train_time:646353ms step_avg:179.14ms
step:3619/5100 train_loss:3.5410 train_time:646496ms step_avg:179.13ms
step:3620/5100 train_loss:3.4746 train_time:647035ms step_avg:179.23ms
step:3621/5100 train_loss:3.3075 train_time:647149ms step_avg:179.22ms
step:3622/5100 train_loss:3.4459 train_time:647291ms step_avg:179.21ms
step:3623/5100 train_loss:3.4458 train_time:647432ms step_avg:179.20ms
step:3624/5100 train_loss:3.3813 train_time:647571ms step_avg:179.18ms
step:3625/5100 train_loss:3.5119 train_time:647711ms step_avg:179.17ms
step:3625/5100 val_loss:3.4353 train_time:647773ms step_avg:179.19ms
step:3626/5100 train_loss:3.5760 train_time:647858ms step_avg:179.16ms
step:3627/5100 train_loss:3.5813 train_time:648006ms step_avg:179.16ms
step:3628/5100 train_loss:3.4666 train_time:648149ms step_avg:179.15ms
step:3629/5100 train_loss:3.6221 train_time:648289ms step_avg:179.13ms
step:3630/5100 train_loss:3.4539 train_time:648835ms step_avg:179.24ms
step:3631/5100 train_loss:3.4439 train_time:648941ms step_avg:179.22ms
step:3632/5100 train_loss:3.5253 train_time:649084ms step_avg:179.21ms
step:3633/5100 train_loss:3.5053 train_time:649222ms step_avg:179.19ms
step:3634/5100 train_loss:3.4326 train_time:649363ms step_avg:179.18ms
step:3635/5100 train_loss:3.4283 train_time:649504ms step_avg:179.17ms
step:3636/5100 train_loss:3.4762 train_time:649646ms step_avg:179.16ms
step:3637/5100 train_loss:3.6604 train_time:649786ms step_avg:179.15ms
step:3638/5100 train_loss:3.4616 train_time:649931ms step_avg:179.14ms
step:3639/5100 train_loss:3.4245 train_time:650074ms step_avg:179.13ms
step:3640/5100 train_loss:3.4175 train_time:650623ms step_avg:179.24ms
step:3641/5100 train_loss:3.7063 train_time:650725ms step_avg:179.21ms
step:3642/5100 train_loss:3.4360 train_time:650866ms step_avg:179.20ms
step:3643/5100 train_loss:3.4800 train_time:651005ms step_avg:179.19ms
step:3644/5100 train_loss:3.4612 train_time:651146ms step_avg:179.18ms
step:3645/5100 train_loss:3.3818 train_time:651285ms step_avg:179.17ms
step:3646/5100 train_loss:3.5793 train_time:651426ms step_avg:179.16ms
step:3647/5100 train_loss:3.3553 train_time:651566ms step_avg:179.15ms
step:3648/5100 train_loss:3.4265 train_time:651715ms step_avg:179.14ms
step:3649/5100 train_loss:3.4987 train_time:651855ms step_avg:179.13ms
step:3650/5100 train_loss:3.4508 train_time:652407ms step_avg:179.23ms
step:3651/5100 train_loss:3.4940 train_time:652510ms step_avg:179.21ms
step:3652/5100 train_loss:3.5425 train_time:652649ms step_avg:179.20ms
step:3653/5100 train_loss:3.3691 train_time:652789ms step_avg:179.19ms
step:3654/5100 train_loss:3.4694 train_time:652929ms step_avg:179.18ms
step:3655/5100 train_loss:3.5014 train_time:653069ms step_avg:179.17ms
step:3656/5100 train_loss:4.1777 train_time:653211ms step_avg:179.16ms
step:3657/5100 train_loss:3.5583 train_time:653349ms step_avg:179.15ms
step:3658/5100 train_loss:3.4678 train_time:653497ms step_avg:179.14ms
step:3659/5100 train_loss:3.4600 train_time:653639ms step_avg:179.13ms
step:3660/5100 train_loss:3.3378 train_time:654193ms step_avg:179.23ms
step:3661/5100 train_loss:3.4680 train_time:654292ms step_avg:179.21ms
step:3662/5100 train_loss:3.3409 train_time:654435ms step_avg:179.20ms
step:3663/5100 train_loss:3.4920 train_time:654574ms step_avg:179.19ms
step:3664/5100 train_loss:3.5010 train_time:654715ms step_avg:179.18ms
step:3665/5100 train_loss:3.3382 train_time:654855ms step_avg:179.17ms
step:3666/5100 train_loss:3.2721 train_time:654994ms step_avg:179.16ms
step:3667/5100 train_loss:3.6989 train_time:655136ms step_avg:179.15ms
step:3668/5100 train_loss:3.4839 train_time:655280ms step_avg:179.14ms
step:3669/5100 train_loss:3.5121 train_time:655424ms step_avg:179.13ms
step:3670/5100 train_loss:3.4310 train_time:655979ms step_avg:179.23ms
step:3671/5100 train_loss:3.4976 train_time:656076ms step_avg:179.21ms
step:3672/5100 train_loss:3.3937 train_time:656220ms step_avg:179.20ms
step:3673/5100 train_loss:3.3940 train_time:656358ms step_avg:179.19ms
step:3674/5100 train_loss:3.2949 train_time:656498ms step_avg:179.18ms
step:3675/5100 train_loss:3.3744 train_time:656639ms step_avg:179.16ms
step:3676/5100 train_loss:3.5273 train_time:656784ms step_avg:179.16ms
step:3677/5100 train_loss:3.3332 train_time:656920ms step_avg:179.14ms
step:3678/5100 train_loss:3.5012 train_time:657068ms step_avg:179.14ms
step:3679/5100 train_loss:3.4831 train_time:657209ms step_avg:179.12ms
step:3680/5100 train_loss:3.3890 train_time:657762ms step_avg:179.23ms
step:3681/5100 train_loss:3.4501 train_time:657863ms step_avg:179.21ms
step:3682/5100 train_loss:3.5172 train_time:658004ms step_avg:179.19ms
step:3683/5100 train_loss:3.6158 train_time:658146ms step_avg:179.18ms
step:3684/5100 train_loss:3.3637 train_time:658285ms step_avg:179.17ms
step:3685/5100 train_loss:3.4402 train_time:658425ms step_avg:179.16ms
step:3686/5100 train_loss:3.5841 train_time:658565ms step_avg:179.15ms
step:3687/5100 train_loss:3.3635 train_time:658706ms step_avg:179.14ms
step:3688/5100 train_loss:3.5672 train_time:658854ms step_avg:179.13ms
step:3689/5100 train_loss:3.3038 train_time:658995ms step_avg:179.12ms
step:3690/5100 train_loss:3.3924 train_time:659550ms step_avg:179.23ms
step:3691/5100 train_loss:3.5250 train_time:659648ms step_avg:179.20ms
step:3692/5100 train_loss:3.3111 train_time:659786ms step_avg:179.19ms
step:3693/5100 train_loss:3.4653 train_time:659928ms step_avg:179.18ms
step:3694/5100 train_loss:3.4497 train_time:660068ms step_avg:179.17ms
step:3695/5100 train_loss:3.4507 train_time:660209ms step_avg:179.16ms
step:3696/5100 train_loss:3.4821 train_time:660349ms step_avg:179.15ms
step:3697/5100 train_loss:3.3205 train_time:660491ms step_avg:179.14ms
step:3698/5100 train_loss:3.4594 train_time:660638ms step_avg:179.13ms
step:3699/5100 train_loss:3.4721 train_time:660782ms step_avg:179.12ms
step:3700/5100 train_loss:3.4448 train_time:661336ms step_avg:179.22ms
step:3701/5100 train_loss:3.5074 train_time:661437ms step_avg:179.20ms
step:3702/5100 train_loss:3.4720 train_time:661577ms step_avg:179.19ms
step:3703/5100 train_loss:3.3910 train_time:661719ms step_avg:179.18ms
step:3704/5100 train_loss:3.3629 train_time:661857ms step_avg:179.17ms
step:3705/5100 train_loss:3.5056 train_time:661997ms step_avg:179.16ms
step:3706/5100 train_loss:3.5094 train_time:662140ms step_avg:179.15ms
step:3707/5100 train_loss:3.5128 train_time:662279ms step_avg:179.14ms
step:3708/5100 train_loss:3.4689 train_time:662427ms step_avg:179.13ms
step:3709/5100 train_loss:3.3441 train_time:662572ms step_avg:179.12ms
step:3710/5100 train_loss:3.6466 train_time:663120ms step_avg:179.22ms
step:3711/5100 train_loss:3.2253 train_time:663221ms step_avg:179.20ms
step:3712/5100 train_loss:3.4967 train_time:663362ms step_avg:179.19ms
step:3713/5100 train_loss:3.3869 train_time:663502ms step_avg:179.18ms
step:3714/5100 train_loss:3.4151 train_time:663644ms step_avg:179.17ms
step:3715/5100 train_loss:3.7949 train_time:663783ms step_avg:179.16ms
step:3716/5100 train_loss:3.6412 train_time:663925ms step_avg:179.15ms
step:3717/5100 train_loss:3.9158 train_time:664065ms step_avg:179.14ms
step:3718/5100 train_loss:3.4192 train_time:664212ms step_avg:179.13ms
step:3719/5100 train_loss:3.3277 train_time:664359ms step_avg:179.12ms
step:3720/5100 train_loss:3.5955 train_time:664903ms step_avg:179.22ms
step:3721/5100 train_loss:3.3534 train_time:665009ms step_avg:179.20ms
step:3722/5100 train_loss:3.4502 train_time:665147ms step_avg:179.19ms
step:3723/5100 train_loss:3.3171 train_time:665287ms step_avg:179.18ms
step:3724/5100 train_loss:3.3037 train_time:665427ms step_avg:179.17ms
step:3725/5100 train_loss:3.4256 train_time:665567ms step_avg:179.16ms
step:3726/5100 train_loss:3.3826 train_time:665708ms step_avg:179.15ms
step:3727/5100 train_loss:3.6494 train_time:665848ms step_avg:179.14ms
step:3728/5100 train_loss:3.3835 train_time:665994ms step_avg:179.13ms
step:3729/5100 train_loss:3.3687 train_time:666138ms step_avg:179.12ms
step:3730/5100 train_loss:3.7231 train_time:666687ms step_avg:179.22ms
step:3731/5100 train_loss:3.4900 train_time:666791ms step_avg:179.20ms
step:3732/5100 train_loss:3.3927 train_time:666929ms step_avg:179.19ms
step:3733/5100 train_loss:3.2128 train_time:667069ms step_avg:179.18ms
step:3734/5100 train_loss:3.4950 train_time:667209ms step_avg:179.16ms
step:3735/5100 train_loss:3.3605 train_time:667351ms step_avg:179.15ms
step:3736/5100 train_loss:3.4610 train_time:667489ms step_avg:179.14ms
step:3737/5100 train_loss:3.3761 train_time:667631ms step_avg:179.13ms
step:3738/5100 train_loss:3.4659 train_time:667779ms step_avg:179.13ms
step:3739/5100 train_loss:3.3733 train_time:667924ms step_avg:179.12ms
step:3740/5100 train_loss:3.4256 train_time:668476ms step_avg:179.22ms
step:3741/5100 train_loss:3.7214 train_time:668577ms step_avg:179.19ms
step:3742/5100 train_loss:3.3732 train_time:668717ms step_avg:179.18ms
step:3743/5100 train_loss:3.4285 train_time:668856ms step_avg:179.17ms
step:3744/5100 train_loss:3.6338 train_time:669001ms step_avg:179.16ms
step:3745/5100 train_loss:3.3569 train_time:669136ms step_avg:179.15ms
step:3746/5100 train_loss:3.2925 train_time:669277ms step_avg:179.14ms
step:3747/5100 train_loss:3.4754 train_time:669417ms step_avg:179.13ms
step:3748/5100 train_loss:3.3331 train_time:669565ms step_avg:179.12ms
step:3749/5100 train_loss:3.3664 train_time:669706ms step_avg:179.11ms
step:3750/5100 train_loss:3.5662 train_time:670257ms step_avg:179.21ms
step:3750/5100 val_loss:3.4223 train_time:670282ms step_avg:179.22ms
step:3751/5100 train_loss:3.4446 train_time:670369ms step_avg:179.20ms
step:3752/5100 train_loss:3.6801 train_time:670515ms step_avg:179.19ms
step:3753/5100 train_loss:3.3957 train_time:670657ms step_avg:179.18ms
step:3754/5100 train_loss:3.4048 train_time:670798ms step_avg:179.17ms
step:3755/5100 train_loss:3.3662 train_time:670938ms step_avg:179.16ms
step:3756/5100 train_loss:3.4779 train_time:671082ms step_avg:179.15ms
step:3757/5100 train_loss:3.4165 train_time:671218ms step_avg:179.13ms
step:3758/5100 train_loss:3.4239 train_time:671362ms step_avg:179.13ms
step:3759/5100 train_loss:3.6055 train_time:671508ms step_avg:179.12ms
step:3760/5100 train_loss:3.4975 train_time:672059ms step_avg:179.22ms
step:3761/5100 train_loss:3.6025 train_time:672159ms step_avg:179.19ms
step:3762/5100 train_loss:3.3744 train_time:672301ms step_avg:179.18ms
step:3763/5100 train_loss:3.3858 train_time:672439ms step_avg:179.17ms
step:3764/5100 train_loss:3.5496 train_time:672579ms step_avg:179.16ms
step:3765/5100 train_loss:3.3152 train_time:672719ms step_avg:179.15ms
step:3766/5100 train_loss:3.4006 train_time:672859ms step_avg:179.14ms
step:3767/5100 train_loss:3.4988 train_time:673000ms step_avg:179.13ms
step:3768/5100 train_loss:3.2995 train_time:673148ms step_avg:179.12ms
step:3769/5100 train_loss:3.5692 train_time:673291ms step_avg:179.11ms
step:3770/5100 train_loss:3.3803 train_time:673842ms step_avg:179.21ms
step:3771/5100 train_loss:3.2566 train_time:673945ms step_avg:179.19ms
step:3772/5100 train_loss:3.5084 train_time:674086ms step_avg:179.18ms
step:3773/5100 train_loss:3.4280 train_time:674226ms step_avg:179.17ms
step:3774/5100 train_loss:3.4215 train_time:674366ms step_avg:179.16ms
step:3775/5100 train_loss:3.4148 train_time:674506ms step_avg:179.15ms
step:3776/5100 train_loss:3.4636 train_time:674646ms step_avg:179.14ms
step:3777/5100 train_loss:3.2982 train_time:674786ms step_avg:179.13ms
step:3778/5100 train_loss:3.4096 train_time:674934ms step_avg:179.12ms
step:3779/5100 train_loss:3.5361 train_time:675077ms step_avg:179.11ms
step:3780/5100 train_loss:3.5077 train_time:675706ms step_avg:179.23ms
step:3781/5100 train_loss:3.5057 train_time:675809ms step_avg:179.21ms
step:3782/5100 train_loss:3.4545 train_time:675951ms step_avg:179.20ms
step:3783/5100 train_loss:3.4582 train_time:676088ms step_avg:179.19ms
step:3784/5100 train_loss:3.4277 train_time:676228ms step_avg:179.18ms
step:3785/5100 train_loss:3.3129 train_time:676367ms step_avg:179.17ms
step:3786/5100 train_loss:3.3939 train_time:676507ms step_avg:179.16ms
step:3787/5100 train_loss:3.4368 train_time:676652ms step_avg:179.15ms
step:3788/5100 train_loss:3.4157 train_time:676794ms step_avg:179.14ms
step:3789/5100 train_loss:3.3674 train_time:676937ms step_avg:179.13ms
step:3790/5100 train_loss:3.3964 train_time:677489ms step_avg:179.23ms
step:3791/5100 train_loss:3.2658 train_time:677590ms step_avg:179.21ms
step:3792/5100 train_loss:3.4845 train_time:677731ms step_avg:179.20ms
step:3793/5100 train_loss:3.4764 train_time:677870ms step_avg:179.19ms
step:3794/5100 train_loss:3.3984 train_time:678010ms step_avg:179.18ms
step:3795/5100 train_loss:3.3584 train_time:678148ms step_avg:179.17ms
step:3796/5100 train_loss:3.2084 train_time:678292ms step_avg:179.16ms
step:3797/5100 train_loss:3.3992 train_time:678430ms step_avg:179.15ms
step:3798/5100 train_loss:3.4022 train_time:678576ms step_avg:179.14ms
step:3799/5100 train_loss:3.4629 train_time:678718ms step_avg:179.13ms
step:3800/5100 train_loss:3.3767 train_time:679394ms step_avg:179.26ms
step:3801/5100 train_loss:3.3514 train_time:679492ms step_avg:179.24ms
step:3802/5100 train_loss:3.3058 train_time:679634ms step_avg:179.23ms
step:3803/5100 train_loss:3.6272 train_time:679774ms step_avg:179.22ms
step:3804/5100 train_loss:3.4634 train_time:679915ms step_avg:179.21ms
step:3805/5100 train_loss:3.3207 train_time:680055ms step_avg:179.20ms
step:3806/5100 train_loss:3.5511 train_time:680195ms step_avg:179.19ms
step:3807/5100 train_loss:3.5189 train_time:680336ms step_avg:179.18ms
step:3808/5100 train_loss:3.3932 train_time:680482ms step_avg:179.17ms
step:3809/5100 train_loss:3.4526 train_time:680625ms step_avg:179.16ms
step:3810/5100 train_loss:3.3690 train_time:681177ms step_avg:179.26ms
step:3811/5100 train_loss:3.4382 train_time:681278ms step_avg:179.24ms
step:3812/5100 train_loss:3.4157 train_time:681418ms step_avg:179.23ms
step:3813/5100 train_loss:3.4420 train_time:681557ms step_avg:179.22ms
step:3814/5100 train_loss:3.4430 train_time:681697ms step_avg:179.21ms
step:3815/5100 train_loss:3.3198 train_time:681838ms step_avg:179.20ms
step:3816/5100 train_loss:3.6658 train_time:681979ms step_avg:179.19ms
step:3817/5100 train_loss:3.2675 train_time:682120ms step_avg:179.18ms
step:3818/5100 train_loss:3.4466 train_time:682266ms step_avg:179.17ms
step:3819/5100 train_loss:3.4227 train_time:682408ms step_avg:179.16ms
step:3820/5100 train_loss:3.4023 train_time:682960ms step_avg:179.25ms
step:3821/5100 train_loss:3.3397 train_time:683060ms step_avg:179.23ms
step:3822/5100 train_loss:3.5109 train_time:683201ms step_avg:179.22ms
step:3823/5100 train_loss:3.2400 train_time:683344ms step_avg:179.21ms
step:3824/5100 train_loss:3.3572 train_time:683481ms step_avg:179.20ms
step:3825/5100 train_loss:3.4020 train_time:683621ms step_avg:179.19ms
step:3826/5100 train_loss:3.5555 train_time:683761ms step_avg:179.18ms
step:3827/5100 train_loss:3.4883 train_time:683902ms step_avg:179.17ms
step:3828/5100 train_loss:3.8580 train_time:684049ms step_avg:179.16ms
step:3829/5100 train_loss:3.4802 train_time:684191ms step_avg:179.15ms
step:3830/5100 train_loss:3.3103 train_time:684745ms step_avg:179.25ms
step:3831/5100 train_loss:3.3541 train_time:684843ms step_avg:179.23ms
step:3832/5100 train_loss:3.5677 train_time:684983ms step_avg:179.22ms
step:3833/5100 train_loss:3.3729 train_time:685124ms step_avg:179.21ms
step:3834/5100 train_loss:3.4994 train_time:685263ms step_avg:179.20ms
step:3835/5100 train_loss:3.4347 train_time:685406ms step_avg:179.19ms
step:3836/5100 train_loss:3.2394 train_time:685544ms step_avg:179.18ms
step:3837/5100 train_loss:3.5213 train_time:685685ms step_avg:179.17ms
step:3838/5100 train_loss:3.4975 train_time:685835ms step_avg:179.16ms
step:3839/5100 train_loss:3.4521 train_time:685981ms step_avg:179.15ms
step:3840/5100 train_loss:3.5177 train_time:686527ms step_avg:179.25ms
step:3841/5100 train_loss:3.6332 train_time:686630ms step_avg:179.23ms
step:3842/5100 train_loss:3.3874 train_time:686771ms step_avg:179.22ms
step:3843/5100 train_loss:3.4356 train_time:686910ms step_avg:179.21ms
step:3844/5100 train_loss:3.5815 train_time:687050ms step_avg:179.20ms
step:3845/5100 train_loss:3.3756 train_time:687190ms step_avg:179.19ms
step:3846/5100 train_loss:3.2483 train_time:687330ms step_avg:179.18ms
step:3847/5100 train_loss:3.4877 train_time:687472ms step_avg:179.17ms
step:3848/5100 train_loss:3.4111 train_time:687619ms step_avg:179.16ms
step:3849/5100 train_loss:3.4560 train_time:687762ms step_avg:179.15ms
step:3850/5100 train_loss:3.3490 train_time:688315ms step_avg:179.25ms
step:3851/5100 train_loss:3.3362 train_time:688415ms step_avg:179.23ms
step:3852/5100 train_loss:3.4925 train_time:688557ms step_avg:179.22ms
step:3853/5100 train_loss:3.3380 train_time:688697ms step_avg:179.21ms
step:3854/5100 train_loss:3.3129 train_time:688837ms step_avg:179.20ms
step:3855/5100 train_loss:3.3919 train_time:688978ms step_avg:179.19ms
step:3856/5100 train_loss:3.4328 train_time:689121ms step_avg:179.18ms
step:3857/5100 train_loss:3.4008 train_time:689259ms step_avg:179.17ms
step:3858/5100 train_loss:3.4219 train_time:689409ms step_avg:179.16ms
step:3859/5100 train_loss:3.4121 train_time:689549ms step_avg:179.15ms
step:3860/5100 train_loss:3.4166 train_time:690100ms step_avg:179.25ms
step:3861/5100 train_loss:3.5761 train_time:690202ms step_avg:179.23ms
step:3862/5100 train_loss:3.3865 train_time:690343ms step_avg:179.22ms
step:3863/5100 train_loss:3.5056 train_time:690484ms step_avg:179.21ms
step:3864/5100 train_loss:3.4599 train_time:690625ms step_avg:179.20ms
step:3865/5100 train_loss:3.5108 train_time:690763ms step_avg:179.19ms
step:3866/5100 train_loss:3.4774 train_time:690903ms step_avg:179.18ms
step:3867/5100 train_loss:3.4172 train_time:691045ms step_avg:179.17ms
step:3868/5100 train_loss:3.5114 train_time:691190ms step_avg:179.16ms
step:3869/5100 train_loss:3.6488 train_time:691334ms step_avg:179.15ms
step:3870/5100 train_loss:3.5063 train_time:691886ms step_avg:179.25ms
step:3871/5100 train_loss:3.4046 train_time:691988ms step_avg:179.23ms
step:3872/5100 train_loss:3.5462 train_time:692124ms step_avg:179.21ms
step:3873/5100 train_loss:3.4398 train_time:692264ms step_avg:179.20ms
step:3874/5100 train_loss:3.3936 train_time:692405ms step_avg:179.19ms
step:3875/5100 train_loss:3.4902 train_time:692546ms step_avg:179.18ms
step:3875/5100 val_loss:3.4065 train_time:692607ms step_avg:179.20ms
step:3876/5100 train_loss:4.0160 train_time:692691ms step_avg:179.18ms
step:3877/5100 train_loss:3.4270 train_time:692843ms step_avg:179.17ms
step:3878/5100 train_loss:3.4231 train_time:692984ms step_avg:179.16ms
step:3879/5100 train_loss:3.4077 train_time:693125ms step_avg:179.15ms
step:3880/5100 train_loss:3.6082 train_time:693676ms step_avg:179.24ms
step:3881/5100 train_loss:3.4171 train_time:693779ms step_avg:179.22ms
step:3882/5100 train_loss:3.4844 train_time:693919ms step_avg:179.21ms
step:3883/5100 train_loss:3.5264 train_time:694061ms step_avg:179.21ms
step:3884/5100 train_loss:3.3500 train_time:694201ms step_avg:179.19ms
step:3885/5100 train_loss:3.3396 train_time:694341ms step_avg:179.18ms
step:3886/5100 train_loss:3.3774 train_time:694481ms step_avg:179.17ms
step:3887/5100 train_loss:3.4166 train_time:694622ms step_avg:179.16ms
step:3888/5100 train_loss:3.5927 train_time:694768ms step_avg:179.16ms
step:3889/5100 train_loss:3.4379 train_time:694910ms step_avg:179.15ms
step:3890/5100 train_loss:3.3802 train_time:695462ms step_avg:179.24ms
step:3891/5100 train_loss:3.5212 train_time:695566ms step_avg:179.22ms
step:3892/5100 train_loss:3.3786 train_time:695707ms step_avg:179.21ms
step:3893/5100 train_loss:3.6190 train_time:695848ms step_avg:179.20ms
step:3894/5100 train_loss:3.3671 train_time:695988ms step_avg:179.19ms
step:3895/5100 train_loss:3.3802 train_time:696133ms step_avg:179.18ms
step:3896/5100 train_loss:3.4558 train_time:696269ms step_avg:179.17ms
step:3897/5100 train_loss:3.7056 train_time:696412ms step_avg:179.16ms
step:3898/5100 train_loss:3.2545 train_time:696558ms step_avg:179.16ms
step:3899/5100 train_loss:3.3809 train_time:696700ms step_avg:179.15ms
step:3900/5100 train_loss:3.5226 train_time:697252ms step_avg:179.24ms
step:3901/5100 train_loss:3.4440 train_time:697354ms step_avg:179.22ms
step:3902/5100 train_loss:3.4879 train_time:697495ms step_avg:179.21ms
step:3903/5100 train_loss:3.7694 train_time:697635ms step_avg:179.20ms
step:3904/5100 train_loss:3.3672 train_time:697778ms step_avg:179.19ms
step:3905/5100 train_loss:3.3846 train_time:697916ms step_avg:179.18ms
step:3906/5100 train_loss:3.3363 train_time:698058ms step_avg:179.17ms
step:3907/5100 train_loss:3.4955 train_time:698197ms step_avg:179.16ms
step:3908/5100 train_loss:3.5119 train_time:698345ms step_avg:179.15ms
step:3909/5100 train_loss:3.4992 train_time:698489ms step_avg:179.15ms
step:3910/5100 train_loss:3.4517 train_time:699043ms step_avg:179.24ms
step:3911/5100 train_loss:3.3859 train_time:699144ms step_avg:179.22ms
step:3912/5100 train_loss:3.4071 train_time:699284ms step_avg:179.21ms
step:3913/5100 train_loss:3.3981 train_time:699427ms step_avg:179.20ms
step:3914/5100 train_loss:3.5181 train_time:699565ms step_avg:179.19ms
step:3915/5100 train_loss:3.3530 train_time:699708ms step_avg:179.18ms
step:3916/5100 train_loss:3.3314 train_time:699845ms step_avg:179.17ms
step:3917/5100 train_loss:3.3265 train_time:699988ms step_avg:179.16ms
step:3918/5100 train_loss:3.4514 train_time:700134ms step_avg:179.15ms
step:3919/5100 train_loss:3.5791 train_time:700275ms step_avg:179.14ms
step:3920/5100 train_loss:3.3548 train_time:700826ms step_avg:179.24ms
step:3921/5100 train_loss:3.3280 train_time:700932ms step_avg:179.22ms
step:3922/5100 train_loss:3.4077 train_time:701074ms step_avg:179.21ms
step:3923/5100 train_loss:3.3907 train_time:701211ms step_avg:179.20ms
step:3924/5100 train_loss:3.4147 train_time:701351ms step_avg:179.19ms
step:3925/5100 train_loss:3.4885 train_time:701491ms step_avg:179.18ms
step:3926/5100 train_loss:3.4552 train_time:701632ms step_avg:179.17ms
step:3927/5100 train_loss:3.5524 train_time:701772ms step_avg:179.16ms
step:3928/5100 train_loss:3.4327 train_time:701920ms step_avg:179.15ms
step:3929/5100 train_loss:3.2920 train_time:702066ms step_avg:179.14ms
step:3930/5100 train_loss:3.6168 train_time:702616ms step_avg:179.24ms
step:3931/5100 train_loss:3.3989 train_time:702715ms step_avg:179.22ms
step:3932/5100 train_loss:3.4526 train_time:702857ms step_avg:179.21ms
step:3933/5100 train_loss:3.4869 train_time:702997ms step_avg:179.20ms
step:3934/5100 train_loss:3.3642 train_time:703139ms step_avg:179.19ms
step:3935/5100 train_loss:3.4919 train_time:703279ms step_avg:179.18ms
step:3936/5100 train_loss:3.4973 train_time:703419ms step_avg:179.17ms
step:3937/5100 train_loss:3.4267 train_time:703560ms step_avg:179.16ms
step:3938/5100 train_loss:3.4844 train_time:703708ms step_avg:179.15ms
step:3939/5100 train_loss:3.4080 train_time:703851ms step_avg:179.14ms
step:3940/5100 train_loss:3.1573 train_time:704404ms step_avg:179.24ms
step:3941/5100 train_loss:3.3775 train_time:704504ms step_avg:179.22ms
step:3942/5100 train_loss:3.4875 train_time:704645ms step_avg:179.21ms
step:3943/5100 train_loss:3.5809 train_time:704786ms step_avg:179.20ms
step:3944/5100 train_loss:3.6156 train_time:704928ms step_avg:179.19ms
step:3945/5100 train_loss:3.4571 train_time:705070ms step_avg:179.18ms
step:3946/5100 train_loss:3.3626 train_time:705209ms step_avg:179.17ms
step:3947/5100 train_loss:3.3842 train_time:705352ms step_avg:179.16ms
step:3948/5100 train_loss:3.4656 train_time:705496ms step_avg:179.15ms
step:3949/5100 train_loss:3.2691 train_time:705638ms step_avg:179.14ms
step:3950/5100 train_loss:3.4684 train_time:706189ms step_avg:179.24ms
step:3951/5100 train_loss:3.4042 train_time:706292ms step_avg:179.22ms
step:3952/5100 train_loss:3.2124 train_time:706434ms step_avg:179.21ms
step:3953/5100 train_loss:3.2788 train_time:706574ms step_avg:179.20ms
step:3954/5100 train_loss:3.5438 train_time:706712ms step_avg:179.19ms
step:3955/5100 train_loss:3.4557 train_time:706852ms step_avg:179.18ms
step:3956/5100 train_loss:3.3977 train_time:706992ms step_avg:179.17ms
step:3957/5100 train_loss:3.4563 train_time:707135ms step_avg:179.16ms
step:3958/5100 train_loss:3.1752 train_time:707282ms step_avg:179.15ms
step:3959/5100 train_loss:3.4627 train_time:707425ms step_avg:179.14ms
step:3960/5100 train_loss:3.4187 train_time:707976ms step_avg:179.23ms
step:3961/5100 train_loss:3.3804 train_time:708080ms step_avg:179.22ms
step:3962/5100 train_loss:3.4048 train_time:708219ms step_avg:179.21ms
step:3963/5100 train_loss:3.4226 train_time:708360ms step_avg:179.20ms
step:3964/5100 train_loss:3.4547 train_time:708500ms step_avg:179.19ms
step:3965/5100 train_loss:3.2993 train_time:708640ms step_avg:179.18ms
step:3966/5100 train_loss:3.4168 train_time:708780ms step_avg:179.17ms
step:3967/5100 train_loss:3.4964 train_time:708921ms step_avg:179.16ms
step:3968/5100 train_loss:3.4047 train_time:709066ms step_avg:179.15ms
step:3969/5100 train_loss:3.4894 train_time:709290ms step_avg:179.16ms
step:3970/5100 train_loss:3.3860 train_time:709837ms step_avg:179.25ms
step:3971/5100 train_loss:3.5692 train_time:709938ms step_avg:179.23ms
step:3972/5100 train_loss:3.4981 train_time:710079ms step_avg:179.22ms
step:3973/5100 train_loss:3.4493 train_time:710219ms step_avg:179.21ms
step:3974/5100 train_loss:3.3424 train_time:710363ms step_avg:179.20ms
step:3975/5100 train_loss:3.3947 train_time:710500ms step_avg:179.19ms
step:3976/5100 train_loss:3.4628 train_time:710640ms step_avg:179.18ms
step:3977/5100 train_loss:3.3706 train_time:710781ms step_avg:179.17ms
step:3978/5100 train_loss:3.4277 train_time:710927ms step_avg:179.17ms
step:3979/5100 train_loss:3.5111 train_time:711068ms step_avg:179.16ms
step:3980/5100 train_loss:3.4478 train_time:711621ms step_avg:179.25ms
step:3981/5100 train_loss:3.4546 train_time:711722ms step_avg:179.23ms
step:3982/5100 train_loss:3.6547 train_time:711862ms step_avg:179.22ms
step:3983/5100 train_loss:3.3872 train_time:712002ms step_avg:179.21ms
step:3984/5100 train_loss:3.4547 train_time:712144ms step_avg:179.20ms
step:3985/5100 train_loss:3.3895 train_time:712284ms step_avg:179.19ms
step:3986/5100 train_loss:3.3206 train_time:712424ms step_avg:179.18ms
step:3987/5100 train_loss:3.3573 train_time:712565ms step_avg:179.17ms
step:3988/5100 train_loss:3.3801 train_time:712712ms step_avg:179.16ms
step:3989/5100 train_loss:3.1104 train_time:712854ms step_avg:179.15ms
step:3990/5100 train_loss:3.4361 train_time:713531ms step_avg:179.28ms
step:3991/5100 train_loss:3.4042 train_time:713627ms step_avg:179.26ms
step:3992/5100 train_loss:3.2508 train_time:713768ms step_avg:179.25ms
step:3993/5100 train_loss:3.3584 train_time:713909ms step_avg:179.24ms
step:3994/5100 train_loss:3.5549 train_time:714053ms step_avg:179.23ms
step:3995/5100 train_loss:3.3798 train_time:714193ms step_avg:179.22ms
step:3996/5100 train_loss:3.2885 train_time:714332ms step_avg:179.21ms
step:3997/5100 train_loss:3.4421 train_time:714473ms step_avg:179.20ms
step:3998/5100 train_loss:3.3578 train_time:714623ms step_avg:179.19ms
step:3999/5100 train_loss:3.3176 train_time:714764ms step_avg:179.18ms
step:4000/5100 train_loss:3.3890 train_time:715315ms step_avg:179.28ms
step:4000/5100 val_loss:3.3919 train_time:715339ms step_avg:179.28ms
step:4001/5100 train_loss:3.5128 train_time:715426ms step_avg:179.26ms
step:4002/5100 train_loss:3.5787 train_time:715576ms step_avg:179.25ms
step:4003/5100 train_loss:3.2510 train_time:715719ms step_avg:179.24ms
step:4004/5100 train_loss:3.4489 train_time:715860ms step_avg:179.23ms
step:4005/5100 train_loss:3.3535 train_time:716002ms step_avg:179.22ms
step:4006/5100 train_loss:3.4105 train_time:716144ms step_avg:179.22ms
step:4007/5100 train_loss:3.3834 train_time:716285ms step_avg:179.21ms
step:4008/5100 train_loss:3.5872 train_time:716425ms step_avg:179.20ms
step:4009/5100 train_loss:3.1766 train_time:716570ms step_avg:179.19ms
step:4010/5100 train_loss:3.3781 train_time:717123ms step_avg:179.28ms
step:4011/5100 train_loss:3.3575 train_time:717227ms step_avg:179.26ms
step:4012/5100 train_loss:3.3237 train_time:717368ms step_avg:179.25ms
step:4013/5100 train_loss:3.4934 train_time:717507ms step_avg:179.24ms
step:4014/5100 train_loss:3.3577 train_time:717645ms step_avg:179.23ms
step:4015/5100 train_loss:3.4566 train_time:717788ms step_avg:179.22ms
step:4016/5100 train_loss:3.5519 train_time:717927ms step_avg:179.21ms
step:4017/5100 train_loss:3.5338 train_time:718069ms step_avg:179.20ms
step:4018/5100 train_loss:3.2829 train_time:718217ms step_avg:179.20ms
step:4019/5100 train_loss:3.4196 train_time:718358ms step_avg:179.19ms
step:4020/5100 train_loss:3.3496 train_time:718910ms step_avg:179.28ms
step:4021/5100 train_loss:3.6098 train_time:719011ms step_avg:179.26ms
step:4022/5100 train_loss:3.4861 train_time:719151ms step_avg:179.25ms
step:4023/5100 train_loss:3.4733 train_time:719291ms step_avg:179.24ms
step:4024/5100 train_loss:3.4446 train_time:719435ms step_avg:179.23ms
step:4025/5100 train_loss:3.4677 train_time:719571ms step_avg:179.22ms
step:4026/5100 train_loss:3.2321 train_time:719713ms step_avg:179.21ms
step:4027/5100 train_loss:3.4483 train_time:719851ms step_avg:179.20ms
step:4028/5100 train_loss:3.3992 train_time:720001ms step_avg:179.19ms
step:4029/5100 train_loss:3.2808 train_time:720143ms step_avg:179.18ms
step:4030/5100 train_loss:3.3113 train_time:720694ms step_avg:179.28ms
step:4031/5100 train_loss:3.3621 train_time:720798ms step_avg:179.26ms
step:4032/5100 train_loss:3.4521 train_time:720939ms step_avg:179.25ms
step:4033/5100 train_loss:3.4216 train_time:721079ms step_avg:179.24ms
step:4034/5100 train_loss:3.4023 train_time:721217ms step_avg:179.23ms
step:4035/5100 train_loss:3.3882 train_time:721357ms step_avg:179.22ms
step:4036/5100 train_loss:3.3318 train_time:721498ms step_avg:179.21ms
step:4037/5100 train_loss:3.5016 train_time:721638ms step_avg:179.20ms
step:4038/5100 train_loss:3.4342 train_time:721784ms step_avg:179.19ms
step:4039/5100 train_loss:3.4137 train_time:721927ms step_avg:179.18ms
step:4040/5100 train_loss:3.4105 train_time:722479ms step_avg:179.28ms
step:4041/5100 train_loss:3.4483 train_time:722583ms step_avg:179.26ms
step:4042/5100 train_loss:3.6395 train_time:722721ms step_avg:179.25ms
step:4043/5100 train_loss:3.5351 train_time:722863ms step_avg:179.24ms
step:4044/5100 train_loss:3.3259 train_time:723004ms step_avg:179.23ms
step:4045/5100 train_loss:3.4916 train_time:723144ms step_avg:179.22ms
step:4046/5100 train_loss:3.1981 train_time:723285ms step_avg:179.21ms
step:4047/5100 train_loss:3.4541 train_time:723426ms step_avg:179.20ms
step:4048/5100 train_loss:3.5432 train_time:723573ms step_avg:179.19ms
step:4049/5100 train_loss:3.4204 train_time:723716ms step_avg:179.18ms
step:4050/5100 train_loss:3.3478 train_time:724266ms step_avg:179.27ms
step:4051/5100 train_loss:3.3831 train_time:724368ms step_avg:179.25ms
step:4052/5100 train_loss:3.3162 train_time:724508ms step_avg:179.24ms
step:4053/5100 train_loss:3.5234 train_time:724647ms step_avg:179.24ms
step:4054/5100 train_loss:3.3894 train_time:724788ms step_avg:179.23ms
step:4055/5100 train_loss:3.4691 train_time:724928ms step_avg:179.22ms
step:4056/5100 train_loss:3.4488 train_time:725068ms step_avg:179.21ms
step:4057/5100 train_loss:3.4161 train_time:725209ms step_avg:179.20ms
step:4058/5100 train_loss:3.2902 train_time:725359ms step_avg:179.19ms
step:4059/5100 train_loss:3.4409 train_time:725499ms step_avg:179.18ms
step:4060/5100 train_loss:3.3045 train_time:726046ms step_avg:179.27ms
step:4061/5100 train_loss:3.3880 train_time:726150ms step_avg:179.25ms
step:4062/5100 train_loss:3.5011 train_time:726289ms step_avg:179.24ms
step:4063/5100 train_loss:3.6773 train_time:726429ms step_avg:179.23ms
step:4064/5100 train_loss:3.0637 train_time:726569ms step_avg:179.22ms
step:4065/5100 train_loss:3.4245 train_time:726708ms step_avg:179.21ms
step:4066/5100 train_loss:3.3107 train_time:726849ms step_avg:179.20ms
step:4067/5100 train_loss:3.4680 train_time:726990ms step_avg:179.19ms
step:4068/5100 train_loss:3.4711 train_time:727139ms step_avg:179.19ms
step:4069/5100 train_loss:3.2730 train_time:727282ms step_avg:179.18ms
step:4070/5100 train_loss:3.4449 train_time:727834ms step_avg:179.27ms
step:4071/5100 train_loss:3.2595 train_time:727936ms step_avg:179.25ms
step:4072/5100 train_loss:3.4453 train_time:728077ms step_avg:179.24ms
step:4073/5100 train_loss:3.5486 train_time:728216ms step_avg:179.23ms
step:4074/5100 train_loss:3.4748 train_time:728356ms step_avg:179.22ms
step:4075/5100 train_loss:3.3849 train_time:728496ms step_avg:179.21ms
step:4076/5100 train_loss:3.3862 train_time:728635ms step_avg:179.20ms
step:4077/5100 train_loss:3.2619 train_time:728776ms step_avg:179.19ms
step:4078/5100 train_loss:3.4241 train_time:728923ms step_avg:179.18ms
step:4079/5100 train_loss:3.4376 train_time:729065ms step_avg:179.18ms
step:4080/5100 train_loss:3.2376 train_time:729615ms step_avg:179.27ms
step:4081/5100 train_loss:3.4099 train_time:729718ms step_avg:179.25ms
step:4082/5100 train_loss:3.3571 train_time:729860ms step_avg:179.24ms
step:4083/5100 train_loss:3.4131 train_time:730000ms step_avg:179.23ms
step:4084/5100 train_loss:3.4116 train_time:730139ms step_avg:179.22ms
step:4085/5100 train_loss:3.4455 train_time:730279ms step_avg:179.21ms
step:4086/5100 train_loss:3.4073 train_time:730419ms step_avg:179.20ms
step:4087/5100 train_loss:3.3820 train_time:730559ms step_avg:179.19ms
step:4088/5100 train_loss:3.4936 train_time:730706ms step_avg:179.18ms
step:4089/5100 train_loss:3.3333 train_time:730853ms step_avg:179.17ms
step:4090/5100 train_loss:3.3565 train_time:731400ms step_avg:179.26ms
step:4091/5100 train_loss:3.3685 train_time:731508ms step_avg:179.25ms
step:4092/5100 train_loss:3.3154 train_time:731643ms step_avg:179.24ms
step:4093/5100 train_loss:3.3200 train_time:731783ms step_avg:179.23ms
step:4094/5100 train_loss:3.5009 train_time:731924ms step_avg:179.22ms
step:4095/5100 train_loss:3.4833 train_time:732064ms step_avg:179.21ms
step:4096/5100 train_loss:3.4005 train_time:732206ms step_avg:179.20ms
step:4097/5100 train_loss:3.4638 train_time:732347ms step_avg:179.19ms
step:4098/5100 train_loss:3.2341 train_time:732494ms step_avg:179.18ms
step:4099/5100 train_loss:3.3780 train_time:732635ms step_avg:179.17ms
step:4100/5100 train_loss:3.3404 train_time:733185ms step_avg:179.26ms
step:4101/5100 train_loss:3.1465 train_time:733286ms step_avg:179.24ms
step:4102/5100 train_loss:3.4207 train_time:733428ms step_avg:179.23ms
step:4103/5100 train_loss:3.3855 train_time:733567ms step_avg:179.22ms
step:4104/5100 train_loss:3.2182 train_time:733708ms step_avg:179.22ms
step:4105/5100 train_loss:3.3076 train_time:733847ms step_avg:179.21ms
step:4106/5100 train_loss:3.4633 train_time:733992ms step_avg:179.20ms
step:4107/5100 train_loss:3.5160 train_time:734128ms step_avg:179.19ms
step:4108/5100 train_loss:3.4103 train_time:734276ms step_avg:179.18ms
step:4109/5100 train_loss:3.4963 train_time:734417ms step_avg:179.17ms
step:4110/5100 train_loss:3.4890 train_time:734969ms step_avg:179.26ms
step:4111/5100 train_loss:3.6557 train_time:735068ms step_avg:179.24ms
step:4112/5100 train_loss:3.3072 train_time:735209ms step_avg:179.23ms
step:4113/5100 train_loss:3.4461 train_time:735349ms step_avg:179.22ms
step:4114/5100 train_loss:3.3401 train_time:735489ms step_avg:179.21ms
step:4115/5100 train_loss:3.4544 train_time:735630ms step_avg:179.20ms
step:4116/5100 train_loss:3.4490 train_time:735770ms step_avg:179.19ms
step:4117/5100 train_loss:3.6875 train_time:735911ms step_avg:179.18ms
step:4118/5100 train_loss:3.2603 train_time:736059ms step_avg:179.18ms
step:4119/5100 train_loss:3.4378 train_time:736203ms step_avg:179.17ms
step:4120/5100 train_loss:3.3423 train_time:736753ms step_avg:179.26ms
step:4121/5100 train_loss:3.4552 train_time:736855ms step_avg:179.24ms
step:4122/5100 train_loss:3.4461 train_time:736996ms step_avg:179.23ms
step:4123/5100 train_loss:3.4324 train_time:737136ms step_avg:179.22ms
step:4124/5100 train_loss:3.2710 train_time:737278ms step_avg:179.21ms
step:4125/5100 train_loss:3.2761 train_time:737416ms step_avg:179.20ms
step:4125/5100 val_loss:3.3787 train_time:737478ms step_avg:179.22ms
step:4126/5100 train_loss:3.4004 train_time:737564ms step_avg:179.19ms
step:4127/5100 train_loss:3.3339 train_time:737713ms step_avg:179.19ms
step:4128/5100 train_loss:3.4051 train_time:737855ms step_avg:179.18ms
step:4129/5100 train_loss:3.4001 train_time:737996ms step_avg:179.17ms
step:4130/5100 train_loss:3.1822 train_time:738545ms step_avg:179.26ms
step:4131/5100 train_loss:3.4799 train_time:738645ms step_avg:179.24ms
step:4132/5100 train_loss:3.4312 train_time:738786ms step_avg:179.23ms
step:4133/5100 train_loss:3.3488 train_time:738928ms step_avg:179.22ms
step:4134/5100 train_loss:3.5601 train_time:739065ms step_avg:179.21ms
step:4135/5100 train_loss:3.3891 train_time:739206ms step_avg:179.20ms
step:4136/5100 train_loss:3.3625 train_time:739345ms step_avg:179.19ms
step:4137/5100 train_loss:3.5128 train_time:739486ms step_avg:179.18ms
step:4138/5100 train_loss:3.3504 train_time:739634ms step_avg:179.17ms
step:4139/5100 train_loss:3.4065 train_time:739775ms step_avg:179.17ms
step:4140/5100 train_loss:3.5047 train_time:740329ms step_avg:179.26ms
step:4141/5100 train_loss:3.5317 train_time:740427ms step_avg:179.24ms
step:4142/5100 train_loss:3.4936 train_time:740567ms step_avg:179.23ms
step:4143/5100 train_loss:3.4751 train_time:740709ms step_avg:179.22ms
step:4144/5100 train_loss:3.3772 train_time:740848ms step_avg:179.21ms
step:4145/5100 train_loss:3.3446 train_time:740988ms step_avg:179.20ms
step:4146/5100 train_loss:3.4576 train_time:741128ms step_avg:179.19ms
step:4147/5100 train_loss:3.0144 train_time:741268ms step_avg:179.18ms
step:4148/5100 train_loss:3.3722 train_time:741415ms step_avg:179.17ms
step:4149/5100 train_loss:3.4072 train_time:741558ms step_avg:179.16ms
step:4150/5100 train_loss:3.2170 train_time:742113ms step_avg:179.25ms
step:4151/5100 train_loss:3.2548 train_time:742213ms step_avg:179.24ms
step:4152/5100 train_loss:3.2945 train_time:742353ms step_avg:179.23ms
step:4153/5100 train_loss:3.3492 train_time:742494ms step_avg:179.22ms
step:4154/5100 train_loss:3.4059 train_time:742634ms step_avg:179.21ms
step:4155/5100 train_loss:3.5103 train_time:742774ms step_avg:179.20ms
step:4156/5100 train_loss:3.3215 train_time:742914ms step_avg:179.19ms
step:4157/5100 train_loss:3.2626 train_time:743055ms step_avg:179.18ms
step:4158/5100 train_loss:3.3877 train_time:743279ms step_avg:179.19ms
step:4159/5100 train_loss:3.3950 train_time:743416ms step_avg:179.18ms
step:4160/5100 train_loss:3.3169 train_time:743965ms step_avg:179.27ms
step:4161/5100 train_loss:3.3985 train_time:744065ms step_avg:179.25ms
step:4162/5100 train_loss:3.3268 train_time:744205ms step_avg:179.24ms
step:4163/5100 train_loss:3.5575 train_time:744345ms step_avg:179.23ms
step:4164/5100 train_loss:3.2477 train_time:744486ms step_avg:179.22ms
step:4165/5100 train_loss:3.3491 train_time:744625ms step_avg:179.21ms
step:4166/5100 train_loss:3.3278 train_time:744765ms step_avg:179.20ms
step:4167/5100 train_loss:3.3739 train_time:744906ms step_avg:179.19ms
step:4168/5100 train_loss:3.3647 train_time:745056ms step_avg:179.19ms
step:4169/5100 train_loss:3.3919 train_time:745199ms step_avg:179.18ms
step:4170/5100 train_loss:3.2300 train_time:745749ms step_avg:179.27ms
step:4171/5100 train_loss:3.3373 train_time:745853ms step_avg:179.25ms
step:4172/5100 train_loss:3.4616 train_time:745993ms step_avg:179.24ms
step:4173/5100 train_loss:3.5236 train_time:746134ms step_avg:179.23ms
step:4174/5100 train_loss:3.9072 train_time:746276ms step_avg:179.22ms
step:4175/5100 train_loss:3.3405 train_time:746414ms step_avg:179.21ms
step:4176/5100 train_loss:3.4919 train_time:746554ms step_avg:179.20ms
step:4177/5100 train_loss:3.2948 train_time:746694ms step_avg:179.19ms
step:4178/5100 train_loss:3.3220 train_time:746840ms step_avg:179.18ms
step:4179/5100 train_loss:3.4779 train_time:746987ms step_avg:179.18ms
step:4180/5100 train_loss:3.4254 train_time:747657ms step_avg:179.29ms
step:4181/5100 train_loss:3.4139 train_time:747759ms step_avg:179.28ms
step:4182/5100 train_loss:3.4136 train_time:747900ms step_avg:179.27ms
step:4183/5100 train_loss:3.4434 train_time:748041ms step_avg:179.26ms
step:4184/5100 train_loss:3.8823 train_time:748181ms step_avg:179.25ms
step:4185/5100 train_loss:3.3918 train_time:748322ms step_avg:179.24ms
step:4186/5100 train_loss:3.4408 train_time:748463ms step_avg:179.23ms
step:4187/5100 train_loss:3.4868 train_time:748603ms step_avg:179.22ms
step:4188/5100 train_loss:3.4807 train_time:748753ms step_avg:179.21ms
step:4189/5100 train_loss:3.1191 train_time:748895ms step_avg:179.20ms
step:4190/5100 train_loss:3.4733 train_time:749444ms step_avg:179.29ms
step:4191/5100 train_loss:3.4808 train_time:749545ms step_avg:179.27ms
step:4192/5100 train_loss:3.4525 train_time:749685ms step_avg:179.26ms
step:4193/5100 train_loss:3.3839 train_time:749826ms step_avg:179.26ms
step:4194/5100 train_loss:3.3994 train_time:749966ms step_avg:179.25ms
step:4195/5100 train_loss:3.3837 train_time:750106ms step_avg:179.24ms
step:4196/5100 train_loss:3.3314 train_time:750246ms step_avg:179.23ms
step:4197/5100 train_loss:3.6800 train_time:750386ms step_avg:179.22ms
step:4198/5100 train_loss:3.1251 train_time:750533ms step_avg:179.21ms
step:4199/5100 train_loss:3.5231 train_time:750674ms step_avg:179.20ms
step:4200/5100 train_loss:3.3961 train_time:751227ms step_avg:179.29ms
step:4201/5100 train_loss:3.2895 train_time:751324ms step_avg:179.27ms
step:4202/5100 train_loss:3.4281 train_time:751466ms step_avg:179.26ms
step:4203/5100 train_loss:3.2887 train_time:751604ms step_avg:179.25ms
step:4204/5100 train_loss:3.3022 train_time:751747ms step_avg:179.24ms
step:4205/5100 train_loss:3.3147 train_time:751885ms step_avg:179.23ms
step:4206/5100 train_loss:3.3140 train_time:752026ms step_avg:179.22ms
step:4207/5100 train_loss:3.7687 train_time:752167ms step_avg:179.22ms
step:4208/5100 train_loss:3.3458 train_time:752314ms step_avg:179.21ms
step:4209/5100 train_loss:3.4802 train_time:752457ms step_avg:179.20ms
step:4210/5100 train_loss:3.3754 train_time:753004ms step_avg:179.29ms
step:4211/5100 train_loss:3.7611 train_time:753110ms step_avg:179.27ms
step:4212/5100 train_loss:3.4174 train_time:753253ms step_avg:179.26ms
step:4213/5100 train_loss:3.4204 train_time:753391ms step_avg:179.25ms
step:4214/5100 train_loss:3.2950 train_time:753531ms step_avg:179.24ms
step:4215/5100 train_loss:3.3564 train_time:753671ms step_avg:179.23ms
step:4216/5100 train_loss:3.4321 train_time:753811ms step_avg:179.22ms
step:4217/5100 train_loss:3.2873 train_time:753952ms step_avg:179.21ms
step:4218/5100 train_loss:3.3476 train_time:754102ms step_avg:179.21ms
step:4219/5100 train_loss:3.4034 train_time:754244ms step_avg:179.20ms
step:4220/5100 train_loss:3.2190 train_time:754794ms step_avg:179.29ms
step:4221/5100 train_loss:3.3769 train_time:754899ms step_avg:179.27ms
step:4222/5100 train_loss:3.4065 train_time:755040ms step_avg:179.26ms
step:4223/5100 train_loss:3.3764 train_time:755182ms step_avg:179.25ms
step:4224/5100 train_loss:3.5754 train_time:755323ms step_avg:179.24ms
step:4225/5100 train_loss:3.4583 train_time:755464ms step_avg:179.23ms
step:4226/5100 train_loss:3.5091 train_time:755604ms step_avg:179.22ms
step:4227/5100 train_loss:3.2947 train_time:755744ms step_avg:179.21ms
step:4228/5100 train_loss:3.3611 train_time:755890ms step_avg:179.21ms
step:4229/5100 train_loss:3.3991 train_time:756032ms step_avg:179.20ms
step:4230/5100 train_loss:3.3009 train_time:756586ms step_avg:179.29ms
step:4231/5100 train_loss:3.4989 train_time:756686ms step_avg:179.27ms
step:4232/5100 train_loss:3.5001 train_time:756826ms step_avg:179.26ms
step:4233/5100 train_loss:3.4872 train_time:756966ms step_avg:179.25ms
step:4234/5100 train_loss:3.6040 train_time:757105ms step_avg:179.24ms
step:4235/5100 train_loss:3.4421 train_time:757245ms step_avg:179.23ms
step:4236/5100 train_loss:3.4005 train_time:757385ms step_avg:179.22ms
step:4237/5100 train_loss:3.2457 train_time:757526ms step_avg:179.21ms
step:4238/5100 train_loss:3.4535 train_time:757673ms step_avg:179.20ms
step:4239/5100 train_loss:3.3709 train_time:757815ms step_avg:179.19ms
step:4240/5100 train_loss:3.2886 train_time:758365ms step_avg:179.28ms
step:4241/5100 train_loss:3.3259 train_time:758472ms step_avg:179.27ms
step:4242/5100 train_loss:3.2827 train_time:758608ms step_avg:179.26ms
step:4243/5100 train_loss:3.3560 train_time:758752ms step_avg:179.25ms
step:4244/5100 train_loss:3.2892 train_time:758889ms step_avg:179.24ms
step:4245/5100 train_loss:3.1909 train_time:759029ms step_avg:179.23ms
step:4246/5100 train_loss:3.5002 train_time:759169ms step_avg:179.22ms
step:4247/5100 train_loss:3.2978 train_time:759310ms step_avg:179.21ms
step:4248/5100 train_loss:3.2272 train_time:759458ms step_avg:179.20ms
step:4249/5100 train_loss:3.4367 train_time:759602ms step_avg:179.19ms
step:4250/5100 train_loss:3.7327 train_time:760153ms step_avg:179.28ms
step:4250/5100 val_loss:3.3654 train_time:760175ms step_avg:179.29ms
step:4251/5100 train_loss:3.3483 train_time:760263ms step_avg:179.26ms
step:4252/5100 train_loss:3.5905 train_time:760413ms step_avg:179.26ms
step:4253/5100 train_loss:3.4359 train_time:760556ms step_avg:179.25ms
step:4254/5100 train_loss:3.2490 train_time:760697ms step_avg:179.24ms
step:4255/5100 train_loss:3.3267 train_time:760836ms step_avg:179.23ms
step:4256/5100 train_loss:3.2547 train_time:760976ms step_avg:179.22ms
step:4257/5100 train_loss:3.4949 train_time:761120ms step_avg:179.21ms
step:4258/5100 train_loss:3.3832 train_time:761261ms step_avg:179.20ms
step:4259/5100 train_loss:3.4241 train_time:761411ms step_avg:179.20ms
step:4260/5100 train_loss:3.2468 train_time:761958ms step_avg:179.28ms
step:4261/5100 train_loss:3.5507 train_time:762061ms step_avg:179.27ms
step:4262/5100 train_loss:3.3747 train_time:762203ms step_avg:179.26ms
step:4263/5100 train_loss:3.3847 train_time:762342ms step_avg:179.25ms
step:4264/5100 train_loss:3.4327 train_time:762483ms step_avg:179.24ms
step:4265/5100 train_loss:3.3801 train_time:762624ms step_avg:179.23ms
step:4266/5100 train_loss:3.3817 train_time:762763ms step_avg:179.22ms
step:4267/5100 train_loss:3.5037 train_time:762905ms step_avg:179.21ms
step:4268/5100 train_loss:3.3325 train_time:763052ms step_avg:179.20ms
step:4269/5100 train_loss:3.8770 train_time:763199ms step_avg:179.20ms
step:4270/5100 train_loss:3.3122 train_time:763748ms step_avg:179.28ms
step:4271/5100 train_loss:3.4142 train_time:763853ms step_avg:179.27ms
step:4272/5100 train_loss:3.3440 train_time:763992ms step_avg:179.26ms
step:4273/5100 train_loss:3.5501 train_time:764135ms step_avg:179.25ms
step:4274/5100 train_loss:3.4691 train_time:764273ms step_avg:179.24ms
step:4275/5100 train_loss:3.3247 train_time:764413ms step_avg:179.23ms
step:4276/5100 train_loss:3.3840 train_time:764552ms step_avg:179.22ms
step:4277/5100 train_loss:3.3118 train_time:764693ms step_avg:179.21ms
step:4278/5100 train_loss:3.3471 train_time:764841ms step_avg:179.20ms
step:4279/5100 train_loss:3.3472 train_time:764983ms step_avg:179.19ms
step:4280/5100 train_loss:3.4101 train_time:765536ms step_avg:179.28ms
step:4281/5100 train_loss:3.3959 train_time:765637ms step_avg:179.26ms
step:4282/5100 train_loss:3.4131 train_time:765777ms step_avg:179.26ms
step:4283/5100 train_loss:3.3433 train_time:765920ms step_avg:179.25ms
step:4284/5100 train_loss:3.3855 train_time:766059ms step_avg:179.24ms
step:4285/5100 train_loss:3.4529 train_time:766201ms step_avg:179.23ms
step:4286/5100 train_loss:3.3963 train_time:766342ms step_avg:179.22ms
step:4287/5100 train_loss:3.3026 train_time:766484ms step_avg:179.21ms
step:4288/5100 train_loss:3.3255 train_time:766630ms step_avg:179.20ms
step:4289/5100 train_loss:3.4203 train_time:766773ms step_avg:179.19ms
step:4290/5100 train_loss:3.3805 train_time:767323ms step_avg:179.28ms
step:4291/5100 train_loss:3.2876 train_time:767424ms step_avg:179.26ms
step:4292/5100 train_loss:3.3126 train_time:767565ms step_avg:179.25ms
step:4293/5100 train_loss:3.3775 train_time:767704ms step_avg:179.24ms
step:4294/5100 train_loss:3.1584 train_time:767845ms step_avg:179.24ms
step:4295/5100 train_loss:3.5164 train_time:767984ms step_avg:179.23ms
step:4296/5100 train_loss:3.4127 train_time:768124ms step_avg:179.22ms
step:4297/5100 train_loss:3.3585 train_time:768266ms step_avg:179.21ms
step:4298/5100 train_loss:3.5222 train_time:768413ms step_avg:179.20ms
step:4299/5100 train_loss:3.4475 train_time:768555ms step_avg:179.19ms
step:4300/5100 train_loss:3.2792 train_time:769108ms step_avg:179.28ms
step:4301/5100 train_loss:3.2770 train_time:769206ms step_avg:179.26ms
step:4302/5100 train_loss:3.4185 train_time:769346ms step_avg:179.25ms
step:4303/5100 train_loss:3.2675 train_time:769486ms step_avg:179.24ms
step:4304/5100 train_loss:3.4077 train_time:769626ms step_avg:179.23ms
step:4305/5100 train_loss:3.4894 train_time:769767ms step_avg:179.22ms
step:4306/5100 train_loss:3.2461 train_time:769906ms step_avg:179.21ms
step:4307/5100 train_loss:3.7660 train_time:770048ms step_avg:179.21ms
step:4308/5100 train_loss:3.3749 train_time:770196ms step_avg:179.20ms
step:4309/5100 train_loss:3.3078 train_time:770338ms step_avg:179.19ms
step:4310/5100 train_loss:3.3176 train_time:770891ms step_avg:179.28ms
step:4311/5100 train_loss:3.6050 train_time:770995ms step_avg:179.26ms
step:4312/5100 train_loss:3.4385 train_time:771132ms step_avg:179.25ms
step:4313/5100 train_loss:3.2985 train_time:771274ms step_avg:179.24ms
step:4314/5100 train_loss:3.5004 train_time:771413ms step_avg:179.23ms
step:4315/5100 train_loss:3.4334 train_time:771553ms step_avg:179.22ms
step:4316/5100 train_loss:3.3406 train_time:771698ms step_avg:179.21ms
step:4317/5100 train_loss:3.3916 train_time:771834ms step_avg:179.20ms
step:4318/5100 train_loss:3.3451 train_time:771981ms step_avg:179.20ms
step:4319/5100 train_loss:3.4548 train_time:772123ms step_avg:179.19ms
step:4320/5100 train_loss:3.5068 train_time:772672ms step_avg:179.27ms
step:4321/5100 train_loss:3.3284 train_time:772776ms step_avg:179.26ms
step:4322/5100 train_loss:3.4955 train_time:772917ms step_avg:179.25ms
step:4323/5100 train_loss:3.3581 train_time:773057ms step_avg:179.24ms
step:4324/5100 train_loss:3.2794 train_time:773199ms step_avg:179.23ms
step:4325/5100 train_loss:3.2298 train_time:773340ms step_avg:179.22ms
step:4326/5100 train_loss:3.3216 train_time:773481ms step_avg:179.21ms
step:4327/5100 train_loss:3.2017 train_time:773624ms step_avg:179.20ms
step:4328/5100 train_loss:3.3283 train_time:773769ms step_avg:179.20ms
step:4329/5100 train_loss:3.3556 train_time:773912ms step_avg:179.19ms
step:4330/5100 train_loss:3.2984 train_time:774461ms step_avg:179.27ms
step:4331/5100 train_loss:3.5494 train_time:774562ms step_avg:179.26ms
step:4332/5100 train_loss:3.3614 train_time:774704ms step_avg:179.25ms
step:4333/5100 train_loss:3.4743 train_time:774846ms step_avg:179.24ms
step:4334/5100 train_loss:3.8289 train_time:774985ms step_avg:179.23ms
step:4335/5100 train_loss:3.3620 train_time:775125ms step_avg:179.22ms
step:4336/5100 train_loss:3.4724 train_time:775264ms step_avg:179.21ms
step:4337/5100 train_loss:3.3641 train_time:775407ms step_avg:179.20ms
step:4338/5100 train_loss:3.2541 train_time:775555ms step_avg:179.19ms
step:4339/5100 train_loss:3.3937 train_time:775696ms step_avg:179.19ms
step:4340/5100 train_loss:3.2867 train_time:776252ms step_avg:179.27ms
step:4341/5100 train_loss:3.3807 train_time:776348ms step_avg:179.25ms
step:4342/5100 train_loss:3.4011 train_time:776493ms step_avg:179.25ms
step:4343/5100 train_loss:3.4007 train_time:776631ms step_avg:179.24ms
step:4344/5100 train_loss:3.3949 train_time:776770ms step_avg:179.23ms
step:4345/5100 train_loss:4.0284 train_time:776911ms step_avg:179.22ms
step:4346/5100 train_loss:3.4659 train_time:777052ms step_avg:179.21ms
step:4347/5100 train_loss:3.2579 train_time:777277ms step_avg:179.22ms
step:4348/5100 train_loss:3.4047 train_time:777412ms step_avg:179.21ms
step:4349/5100 train_loss:3.3462 train_time:777552ms step_avg:179.20ms
step:4350/5100 train_loss:3.2692 train_time:778101ms step_avg:179.29ms
step:4351/5100 train_loss:3.4307 train_time:778201ms step_avg:179.27ms
step:4352/5100 train_loss:3.3810 train_time:778342ms step_avg:179.26ms
step:4353/5100 train_loss:3.4553 train_time:778482ms step_avg:179.25ms
step:4354/5100 train_loss:3.4889 train_time:778622ms step_avg:179.24ms
step:4355/5100 train_loss:3.3106 train_time:778762ms step_avg:179.23ms
step:4356/5100 train_loss:3.2636 train_time:778904ms step_avg:179.22ms
step:4357/5100 train_loss:3.3968 train_time:779046ms step_avg:179.21ms
step:4358/5100 train_loss:3.3397 train_time:779193ms step_avg:179.21ms
step:4359/5100 train_loss:3.5257 train_time:779336ms step_avg:179.20ms
step:4360/5100 train_loss:3.3984 train_time:779886ms step_avg:179.28ms
step:4361/5100 train_loss:3.4716 train_time:779987ms step_avg:179.27ms
step:4362/5100 train_loss:3.6310 train_time:780127ms step_avg:179.26ms
step:4363/5100 train_loss:3.4204 train_time:780267ms step_avg:179.25ms
step:4364/5100 train_loss:3.3893 train_time:780408ms step_avg:179.24ms
step:4365/5100 train_loss:3.5942 train_time:780548ms step_avg:179.23ms
step:4366/5100 train_loss:3.4860 train_time:780688ms step_avg:179.22ms
step:4367/5100 train_loss:3.3077 train_time:780829ms step_avg:179.21ms
step:4368/5100 train_loss:3.3198 train_time:780978ms step_avg:179.21ms
step:4369/5100 train_loss:3.4251 train_time:781120ms step_avg:179.20ms
step:4370/5100 train_loss:3.4195 train_time:781798ms step_avg:179.31ms
step:4371/5100 train_loss:3.5670 train_time:781897ms step_avg:179.29ms
step:4372/5100 train_loss:3.2613 train_time:782037ms step_avg:179.28ms
step:4373/5100 train_loss:3.2496 train_time:782179ms step_avg:179.28ms
step:4374/5100 train_loss:3.4112 train_time:782320ms step_avg:179.27ms
step:4375/5100 train_loss:3.4319 train_time:782461ms step_avg:179.26ms
step:4375/5100 val_loss:3.3504 train_time:782524ms step_avg:179.27ms
step:4376/5100 train_loss:3.4990 train_time:782608ms step_avg:179.25ms
step:4377/5100 train_loss:3.2893 train_time:782760ms step_avg:179.24ms
step:4378/5100 train_loss:3.3395 train_time:782903ms step_avg:179.24ms
step:4379/5100 train_loss:3.3538 train_time:783044ms step_avg:179.23ms
step:4380/5100 train_loss:3.3935 train_time:783593ms step_avg:179.31ms
step:4381/5100 train_loss:3.2973 train_time:783693ms step_avg:179.29ms
step:4382/5100 train_loss:3.5357 train_time:783834ms step_avg:179.28ms
step:4383/5100 train_loss:3.4466 train_time:783974ms step_avg:179.28ms
step:4384/5100 train_loss:3.4467 train_time:784117ms step_avg:179.27ms
step:4385/5100 train_loss:3.3176 train_time:784253ms step_avg:179.26ms
step:4386/5100 train_loss:3.4505 train_time:784394ms step_avg:179.25ms
step:4387/5100 train_loss:3.3445 train_time:784534ms step_avg:179.24ms
step:4388/5100 train_loss:3.4750 train_time:784682ms step_avg:179.23ms
step:4389/5100 train_loss:3.3015 train_time:784824ms step_avg:179.22ms
step:4390/5100 train_loss:3.4245 train_time:785377ms step_avg:179.31ms
step:4391/5100 train_loss:3.4419 train_time:785478ms step_avg:179.29ms
step:4392/5100 train_loss:3.2571 train_time:785619ms step_avg:179.28ms
step:4393/5100 train_loss:3.9355 train_time:785759ms step_avg:179.27ms
step:4394/5100 train_loss:3.3339 train_time:785900ms step_avg:179.27ms
step:4395/5100 train_loss:3.5187 train_time:786040ms step_avg:179.26ms
step:4396/5100 train_loss:3.2889 train_time:786182ms step_avg:179.25ms
step:4397/5100 train_loss:3.4197 train_time:786322ms step_avg:179.24ms
step:4398/5100 train_loss:3.2201 train_time:786468ms step_avg:179.23ms
step:4399/5100 train_loss:3.4384 train_time:786609ms step_avg:179.22ms
step:4400/5100 train_loss:3.2731 train_time:787161ms step_avg:179.31ms
step:4401/5100 train_loss:3.3396 train_time:787260ms step_avg:179.29ms
step:4402/5100 train_loss:3.4126 train_time:787401ms step_avg:179.28ms
step:4403/5100 train_loss:3.2399 train_time:787543ms step_avg:179.27ms
step:4404/5100 train_loss:3.3000 train_time:787681ms step_avg:179.26ms
step:4405/5100 train_loss:3.4918 train_time:787821ms step_avg:179.25ms
step:4406/5100 train_loss:3.3583 train_time:787961ms step_avg:179.24ms
step:4407/5100 train_loss:3.3661 train_time:788101ms step_avg:179.24ms
step:4408/5100 train_loss:3.3322 train_time:788246ms step_avg:179.23ms
step:4409/5100 train_loss:3.4132 train_time:788390ms step_avg:179.22ms
step:4410/5100 train_loss:3.4017 train_time:788943ms step_avg:179.31ms
step:4411/5100 train_loss:3.5213 train_time:789043ms step_avg:179.29ms
step:4412/5100 train_loss:3.3580 train_time:789184ms step_avg:179.28ms
step:4413/5100 train_loss:3.3944 train_time:789324ms step_avg:179.27ms
step:4414/5100 train_loss:3.3800 train_time:789465ms step_avg:179.26ms
step:4415/5100 train_loss:3.4237 train_time:789605ms step_avg:179.25ms
step:4416/5100 train_loss:3.3702 train_time:789746ms step_avg:179.24ms
step:4417/5100 train_loss:3.4394 train_time:789893ms step_avg:179.24ms
step:4418/5100 train_loss:3.3694 train_time:790034ms step_avg:179.23ms
step:4419/5100 train_loss:3.2773 train_time:790177ms step_avg:179.22ms
step:4420/5100 train_loss:3.3253 train_time:790724ms step_avg:179.30ms
step:4421/5100 train_loss:3.5552 train_time:790829ms step_avg:179.29ms
step:4422/5100 train_loss:3.3575 train_time:790971ms step_avg:179.28ms
step:4423/5100 train_loss:3.2745 train_time:791111ms step_avg:179.27ms
step:4424/5100 train_loss:3.3044 train_time:791251ms step_avg:179.26ms
step:4425/5100 train_loss:3.4766 train_time:791391ms step_avg:179.25ms
step:4426/5100 train_loss:3.4281 train_time:791531ms step_avg:179.24ms
step:4427/5100 train_loss:3.3355 train_time:791673ms step_avg:179.23ms
step:4428/5100 train_loss:3.5526 train_time:791820ms step_avg:179.23ms
step:4429/5100 train_loss:3.4649 train_time:791962ms step_avg:179.22ms
step:4430/5100 train_loss:3.2633 train_time:792513ms step_avg:179.30ms
step:4431/5100 train_loss:3.2569 train_time:792615ms step_avg:179.28ms
step:4432/5100 train_loss:3.3946 train_time:792756ms step_avg:179.28ms
step:4433/5100 train_loss:3.2764 train_time:792894ms step_avg:179.27ms
step:4434/5100 train_loss:3.3895 train_time:793034ms step_avg:179.26ms
step:4435/5100 train_loss:3.4491 train_time:793174ms step_avg:179.25ms
step:4436/5100 train_loss:3.3392 train_time:793314ms step_avg:179.24ms
step:4437/5100 train_loss:3.2565 train_time:793454ms step_avg:179.23ms
step:4438/5100 train_loss:3.5013 train_time:793602ms step_avg:179.22ms
step:4439/5100 train_loss:3.4304 train_time:793744ms step_avg:179.22ms
step:4440/5100 train_loss:3.3273 train_time:794294ms step_avg:179.30ms
step:4441/5100 train_loss:3.4341 train_time:794395ms step_avg:179.28ms
step:4442/5100 train_loss:3.4601 train_time:794536ms step_avg:179.27ms
step:4443/5100 train_loss:3.5173 train_time:794675ms step_avg:179.26ms
step:4444/5100 train_loss:3.4071 train_time:794817ms step_avg:179.26ms
step:4445/5100 train_loss:3.2205 train_time:794957ms step_avg:179.25ms
step:4446/5100 train_loss:3.4983 train_time:795096ms step_avg:179.24ms
step:4447/5100 train_loss:3.3776 train_time:795237ms step_avg:179.23ms
step:4448/5100 train_loss:3.2753 train_time:795384ms step_avg:179.22ms
step:4449/5100 train_loss:3.3989 train_time:795527ms step_avg:179.21ms
step:4450/5100 train_loss:3.3919 train_time:796081ms step_avg:179.30ms
step:4451/5100 train_loss:3.4104 train_time:796183ms step_avg:179.28ms
step:4452/5100 train_loss:3.4335 train_time:796322ms step_avg:179.27ms
step:4453/5100 train_loss:3.3020 train_time:796463ms step_avg:179.26ms
step:4454/5100 train_loss:3.3312 train_time:796603ms step_avg:179.25ms
step:4455/5100 train_loss:3.3309 train_time:796741ms step_avg:179.24ms
step:4456/5100 train_loss:3.2275 train_time:796880ms step_avg:179.24ms
step:4457/5100 train_loss:3.4366 train_time:797021ms step_avg:179.23ms
step:4458/5100 train_loss:3.3068 train_time:797169ms step_avg:179.22ms
step:4459/5100 train_loss:3.2746 train_time:797313ms step_avg:179.21ms
step:4460/5100 train_loss:3.3940 train_time:797866ms step_avg:179.30ms
step:4461/5100 train_loss:3.8923 train_time:797964ms step_avg:179.28ms
step:4462/5100 train_loss:3.3819 train_time:798106ms step_avg:179.27ms
step:4463/5100 train_loss:3.4989 train_time:798247ms step_avg:179.26ms
step:4464/5100 train_loss:3.4040 train_time:798387ms step_avg:179.25ms
step:4465/5100 train_loss:3.3782 train_time:798528ms step_avg:179.24ms
step:4466/5100 train_loss:3.4518 train_time:798670ms step_avg:179.23ms
step:4467/5100 train_loss:3.2608 train_time:798811ms step_avg:179.23ms
step:4468/5100 train_loss:3.3040 train_time:798959ms step_avg:179.22ms
step:4469/5100 train_loss:3.4325 train_time:799101ms step_avg:179.21ms
step:4470/5100 train_loss:3.4151 train_time:799656ms step_avg:179.29ms
step:4471/5100 train_loss:3.3429 train_time:799752ms step_avg:179.28ms
step:4472/5100 train_loss:3.3009 train_time:799898ms step_avg:179.27ms
step:4473/5100 train_loss:3.3779 train_time:800032ms step_avg:179.26ms
step:4474/5100 train_loss:3.2259 train_time:800173ms step_avg:179.25ms
step:4475/5100 train_loss:3.3038 train_time:800312ms step_avg:179.24ms
step:4476/5100 train_loss:3.3296 train_time:800453ms step_avg:179.23ms
step:4477/5100 train_loss:3.5012 train_time:800593ms step_avg:179.22ms
step:4478/5100 train_loss:3.2267 train_time:800739ms step_avg:179.22ms
step:4479/5100 train_loss:3.3527 train_time:800882ms step_avg:179.21ms
step:4480/5100 train_loss:3.3929 train_time:801431ms step_avg:179.29ms
step:4481/5100 train_loss:3.3591 train_time:801533ms step_avg:179.27ms
step:4482/5100 train_loss:3.3546 train_time:801674ms step_avg:179.27ms
step:4483/5100 train_loss:3.1674 train_time:801814ms step_avg:179.26ms
step:4484/5100 train_loss:3.3182 train_time:801954ms step_avg:179.25ms
step:4485/5100 train_loss:3.2682 train_time:802093ms step_avg:179.24ms
step:4486/5100 train_loss:3.3967 train_time:802232ms step_avg:179.23ms
step:4487/5100 train_loss:3.2803 train_time:802373ms step_avg:179.22ms
step:4488/5100 train_loss:3.3475 train_time:802520ms step_avg:179.21ms
step:4489/5100 train_loss:3.4916 train_time:802663ms step_avg:179.21ms
step:4490/5100 train_loss:3.4520 train_time:803214ms step_avg:179.29ms
step:4491/5100 train_loss:3.3241 train_time:803317ms step_avg:179.27ms
step:4492/5100 train_loss:3.2879 train_time:803456ms step_avg:179.26ms
step:4493/5100 train_loss:3.3411 train_time:803594ms step_avg:179.25ms
step:4494/5100 train_loss:3.3680 train_time:803734ms step_avg:179.24ms
step:4495/5100 train_loss:3.3587 train_time:803878ms step_avg:179.24ms
step:4496/5100 train_loss:3.3085 train_time:804014ms step_avg:179.23ms
step:4497/5100 train_loss:3.4610 train_time:804155ms step_avg:179.22ms
step:4498/5100 train_loss:3.3516 train_time:804302ms step_avg:179.21ms
step:4499/5100 train_loss:3.1911 train_time:804444ms step_avg:179.20ms
step:4500/5100 train_loss:3.4948 train_time:804994ms step_avg:179.29ms
step:4500/5100 val_loss:3.3381 train_time:805019ms step_avg:179.29ms
step:4501/5100 train_loss:3.2983 train_time:805107ms step_avg:179.27ms
step:4502/5100 train_loss:3.2526 train_time:805256ms step_avg:179.26ms
step:4503/5100 train_loss:3.4424 train_time:805399ms step_avg:179.26ms
step:4504/5100 train_loss:3.3236 train_time:805538ms step_avg:179.25ms
step:4505/5100 train_loss:3.4188 train_time:805678ms step_avg:179.24ms
step:4506/5100 train_loss:3.3425 train_time:805819ms step_avg:179.23ms
step:4507/5100 train_loss:3.4068 train_time:805958ms step_avg:179.22ms
step:4508/5100 train_loss:3.1307 train_time:806099ms step_avg:179.21ms
step:4509/5100 train_loss:3.4146 train_time:806242ms step_avg:179.20ms
step:4510/5100 train_loss:3.2553 train_time:806799ms step_avg:179.29ms
step:4511/5100 train_loss:3.3254 train_time:806898ms step_avg:179.27ms
step:4512/5100 train_loss:3.2714 train_time:807038ms step_avg:179.26ms
step:4513/5100 train_loss:3.2694 train_time:807178ms step_avg:179.25ms
step:4514/5100 train_loss:3.2278 train_time:807318ms step_avg:179.24ms
step:4515/5100 train_loss:3.3765 train_time:807458ms step_avg:179.24ms
step:4516/5100 train_loss:3.2208 train_time:807598ms step_avg:179.23ms
step:4517/5100 train_loss:3.3325 train_time:807739ms step_avg:179.22ms
step:4518/5100 train_loss:3.3326 train_time:807884ms step_avg:179.21ms
step:4519/5100 train_loss:3.3458 train_time:808028ms step_avg:179.20ms
step:4520/5100 train_loss:3.2642 train_time:808578ms step_avg:179.29ms
step:4521/5100 train_loss:3.4472 train_time:808681ms step_avg:179.27ms
step:4522/5100 train_loss:3.5152 train_time:808821ms step_avg:179.26ms
step:4523/5100 train_loss:3.8576 train_time:808960ms step_avg:179.25ms
step:4524/5100 train_loss:3.5857 train_time:809101ms step_avg:179.24ms
step:4525/5100 train_loss:3.3577 train_time:809241ms step_avg:179.23ms
step:4526/5100 train_loss:3.3040 train_time:809381ms step_avg:179.23ms
step:4527/5100 train_loss:3.3803 train_time:809524ms step_avg:179.22ms
step:4528/5100 train_loss:3.3358 train_time:809667ms step_avg:179.21ms
step:4529/5100 train_loss:3.2423 train_time:809811ms step_avg:179.20ms
step:4530/5100 train_loss:3.9486 train_time:810362ms step_avg:179.28ms
step:4531/5100 train_loss:3.4191 train_time:810462ms step_avg:179.27ms
step:4532/5100 train_loss:3.1497 train_time:810604ms step_avg:179.26ms
step:4533/5100 train_loss:3.2591 train_time:810749ms step_avg:179.25ms
step:4534/5100 train_loss:3.3681 train_time:810886ms step_avg:179.24ms
step:4535/5100 train_loss:3.5892 train_time:811026ms step_avg:179.23ms
step:4536/5100 train_loss:3.5916 train_time:811256ms step_avg:179.24ms
step:4537/5100 train_loss:3.3195 train_time:811390ms step_avg:179.23ms
step:4538/5100 train_loss:3.3172 train_time:811530ms step_avg:179.22ms
step:4539/5100 train_loss:3.3497 train_time:811669ms step_avg:179.22ms
step:4540/5100 train_loss:3.9252 train_time:812216ms step_avg:179.30ms
step:4541/5100 train_loss:3.4109 train_time:812318ms step_avg:179.28ms
step:4542/5100 train_loss:3.3150 train_time:812458ms step_avg:179.27ms
step:4543/5100 train_loss:3.4793 train_time:812599ms step_avg:179.26ms
step:4544/5100 train_loss:3.2645 train_time:812738ms step_avg:179.25ms
step:4545/5100 train_loss:3.3699 train_time:812878ms step_avg:179.25ms
step:4546/5100 train_loss:3.5445 train_time:813018ms step_avg:179.24ms
step:4547/5100 train_loss:3.4058 train_time:813160ms step_avg:179.23ms
step:4548/5100 train_loss:3.3504 train_time:813306ms step_avg:179.22ms
step:4549/5100 train_loss:3.3441 train_time:813449ms step_avg:179.21ms
step:4550/5100 train_loss:3.2896 train_time:814005ms step_avg:179.30ms
step:4551/5100 train_loss:3.2717 train_time:814102ms step_avg:179.28ms
step:4552/5100 train_loss:3.2500 train_time:814241ms step_avg:179.27ms
step:4553/5100 train_loss:3.3616 train_time:814382ms step_avg:179.26ms
step:4554/5100 train_loss:3.5543 train_time:814521ms step_avg:179.25ms
step:4555/5100 train_loss:3.4356 train_time:814661ms step_avg:179.24ms
step:4556/5100 train_loss:3.1908 train_time:814802ms step_avg:179.23ms
step:4557/5100 train_loss:3.3918 train_time:814942ms step_avg:179.23ms
step:4558/5100 train_loss:3.4013 train_time:815089ms step_avg:179.22ms
step:4559/5100 train_loss:3.3886 train_time:815248ms step_avg:179.21ms
step:4560/5100 train_loss:3.4897 train_time:815906ms step_avg:179.32ms
step:4561/5100 train_loss:3.3190 train_time:816006ms step_avg:179.30ms
step:4562/5100 train_loss:3.3234 train_time:816147ms step_avg:179.29ms
step:4563/5100 train_loss:3.3464 train_time:816287ms step_avg:179.29ms
step:4564/5100 train_loss:3.3944 train_time:816431ms step_avg:179.28ms
step:4565/5100 train_loss:3.4735 train_time:816568ms step_avg:179.27ms
step:4566/5100 train_loss:3.5298 train_time:816708ms step_avg:179.26ms
step:4567/5100 train_loss:3.3911 train_time:816849ms step_avg:179.25ms
step:4568/5100 train_loss:3.2564 train_time:816999ms step_avg:179.24ms
step:4569/5100 train_loss:3.3616 train_time:817140ms step_avg:179.24ms
step:4570/5100 train_loss:3.2450 train_time:817691ms step_avg:179.32ms
step:4571/5100 train_loss:3.2755 train_time:817791ms step_avg:179.30ms
step:4572/5100 train_loss:3.4769 train_time:817931ms step_avg:179.29ms
step:4573/5100 train_loss:3.1835 train_time:818070ms step_avg:179.28ms
step:4574/5100 train_loss:3.2644 train_time:818210ms step_avg:179.27ms
step:4575/5100 train_loss:3.3916 train_time:818352ms step_avg:179.27ms
step:4576/5100 train_loss:3.4205 train_time:818492ms step_avg:179.26ms
step:4577/5100 train_loss:3.3827 train_time:818633ms step_avg:179.25ms
step:4578/5100 train_loss:3.3418 train_time:818780ms step_avg:179.24ms
step:4579/5100 train_loss:3.3649 train_time:818924ms step_avg:179.23ms
step:4580/5100 train_loss:3.4682 train_time:819478ms step_avg:179.32ms
step:4581/5100 train_loss:3.2963 train_time:819576ms step_avg:179.30ms
step:4582/5100 train_loss:3.3239 train_time:819717ms step_avg:179.29ms
step:4583/5100 train_loss:3.4258 train_time:819860ms step_avg:179.28ms
step:4584/5100 train_loss:3.2837 train_time:819997ms step_avg:179.27ms
step:4585/5100 train_loss:3.3962 train_time:820138ms step_avg:179.27ms
step:4586/5100 train_loss:3.3691 train_time:820277ms step_avg:179.26ms
step:4587/5100 train_loss:3.3502 train_time:820419ms step_avg:179.25ms
step:4588/5100 train_loss:3.1992 train_time:820568ms step_avg:179.24ms
step:4589/5100 train_loss:3.3287 train_time:820710ms step_avg:179.23ms
step:4590/5100 train_loss:3.5284 train_time:821264ms step_avg:179.32ms
step:4591/5100 train_loss:3.3551 train_time:821364ms step_avg:179.30ms
step:4592/5100 train_loss:3.3507 train_time:821503ms step_avg:179.29ms
step:4593/5100 train_loss:3.3089 train_time:821644ms step_avg:179.28ms
step:4594/5100 train_loss:3.4709 train_time:821784ms step_avg:179.27ms
step:4595/5100 train_loss:3.3477 train_time:821926ms step_avg:179.26ms
step:4596/5100 train_loss:3.2572 train_time:822067ms step_avg:179.26ms
step:4597/5100 train_loss:3.2400 train_time:822209ms step_avg:179.25ms
step:4598/5100 train_loss:3.4239 train_time:822357ms step_avg:179.24ms
step:4599/5100 train_loss:3.3558 train_time:822498ms step_avg:179.23ms
step:4600/5100 train_loss:3.4734 train_time:823053ms step_avg:179.31ms
step:4601/5100 train_loss:3.3795 train_time:823149ms step_avg:179.30ms
step:4602/5100 train_loss:3.1838 train_time:823290ms step_avg:179.29ms
step:4603/5100 train_loss:3.2986 train_time:823430ms step_avg:179.28ms
step:4604/5100 train_loss:3.3797 train_time:823569ms step_avg:179.27ms
step:4605/5100 train_loss:3.3940 train_time:823709ms step_avg:179.26ms
step:4606/5100 train_loss:3.3140 train_time:823854ms step_avg:179.25ms
step:4607/5100 train_loss:3.4284 train_time:823991ms step_avg:179.25ms
step:4608/5100 train_loss:3.3019 train_time:824140ms step_avg:179.24ms
step:4609/5100 train_loss:3.4106 train_time:824279ms step_avg:179.23ms
step:4610/5100 train_loss:3.3509 train_time:824832ms step_avg:179.31ms
step:4611/5100 train_loss:3.3967 train_time:824934ms step_avg:179.29ms
step:4612/5100 train_loss:3.5314 train_time:825074ms step_avg:179.29ms
step:4613/5100 train_loss:3.2361 train_time:825213ms step_avg:179.28ms
step:4614/5100 train_loss:3.0773 train_time:825353ms step_avg:179.27ms
step:4615/5100 train_loss:3.2962 train_time:825493ms step_avg:179.26ms
step:4616/5100 train_loss:3.2144 train_time:825634ms step_avg:179.25ms
step:4617/5100 train_loss:3.3198 train_time:825776ms step_avg:179.24ms
step:4618/5100 train_loss:3.1882 train_time:825924ms step_avg:179.24ms
step:4619/5100 train_loss:3.4093 train_time:826068ms step_avg:179.23ms
step:4620/5100 train_loss:3.4533 train_time:826618ms step_avg:179.31ms
step:4621/5100 train_loss:3.4843 train_time:826720ms step_avg:179.29ms
step:4622/5100 train_loss:3.2769 train_time:826860ms step_avg:179.28ms
step:4623/5100 train_loss:3.2806 train_time:826999ms step_avg:179.28ms
step:4624/5100 train_loss:3.3171 train_time:827140ms step_avg:179.27ms
step:4625/5100 train_loss:3.2291 train_time:827278ms step_avg:179.26ms
step:4625/5100 val_loss:3.3247 train_time:827341ms step_avg:179.27ms
step:4626/5100 train_loss:3.3993 train_time:827425ms step_avg:179.25ms
step:4627/5100 train_loss:3.2800 train_time:827576ms step_avg:179.25ms
step:4628/5100 train_loss:3.3474 train_time:827719ms step_avg:179.24ms
step:4629/5100 train_loss:3.5424 train_time:827862ms step_avg:179.23ms
step:4630/5100 train_loss:3.3833 train_time:828409ms step_avg:179.31ms
step:4631/5100 train_loss:3.4739 train_time:828510ms step_avg:179.29ms
step:4632/5100 train_loss:3.2778 train_time:828651ms step_avg:179.28ms
step:4633/5100 train_loss:3.4619 train_time:828793ms step_avg:179.28ms
step:4634/5100 train_loss:3.3222 train_time:828932ms step_avg:179.27ms
step:4635/5100 train_loss:3.3780 train_time:829072ms step_avg:179.26ms
step:4636/5100 train_loss:3.3904 train_time:829212ms step_avg:179.25ms
step:4637/5100 train_loss:3.2193 train_time:829355ms step_avg:179.24ms
step:4638/5100 train_loss:3.3870 train_time:829500ms step_avg:179.24ms
step:4639/5100 train_loss:3.3449 train_time:829645ms step_avg:179.23ms
step:4640/5100 train_loss:3.3469 train_time:830199ms step_avg:179.31ms
step:4641/5100 train_loss:3.2867 train_time:830295ms step_avg:179.29ms
step:4642/5100 train_loss:3.3178 train_time:830434ms step_avg:179.28ms
step:4643/5100 train_loss:3.3299 train_time:830576ms step_avg:179.27ms
step:4644/5100 train_loss:3.5516 train_time:830718ms step_avg:179.27ms
step:4645/5100 train_loss:3.4160 train_time:830857ms step_avg:179.26ms
step:4646/5100 train_loss:3.4585 train_time:830996ms step_avg:179.25ms
step:4647/5100 train_loss:3.2824 train_time:831136ms step_avg:179.24ms
step:4648/5100 train_loss:3.3913 train_time:831285ms step_avg:179.23ms
step:4649/5100 train_loss:3.3405 train_time:831426ms step_avg:179.23ms
step:4650/5100 train_loss:3.3878 train_time:831979ms step_avg:179.31ms
step:4651/5100 train_loss:3.5024 train_time:832079ms step_avg:179.29ms
step:4652/5100 train_loss:3.3324 train_time:832219ms step_avg:179.28ms
step:4653/5100 train_loss:3.4362 train_time:832361ms step_avg:179.27ms
step:4654/5100 train_loss:3.2944 train_time:832501ms step_avg:179.26ms
step:4655/5100 train_loss:3.3315 train_time:832644ms step_avg:179.26ms
step:4656/5100 train_loss:3.3552 train_time:832783ms step_avg:179.25ms
step:4657/5100 train_loss:3.3081 train_time:832926ms step_avg:179.24ms
step:4658/5100 train_loss:3.2305 train_time:833069ms step_avg:179.23ms
step:4659/5100 train_loss:3.2725 train_time:833210ms step_avg:179.22ms
step:4660/5100 train_loss:3.2056 train_time:833765ms step_avg:179.30ms
step:4661/5100 train_loss:3.3746 train_time:833861ms step_avg:179.29ms
step:4662/5100 train_loss:3.3557 train_time:834002ms step_avg:179.28ms
step:4663/5100 train_loss:3.3202 train_time:834144ms step_avg:179.27ms
step:4664/5100 train_loss:3.2466 train_time:834282ms step_avg:179.26ms
step:4665/5100 train_loss:3.2564 train_time:834424ms step_avg:179.25ms
step:4666/5100 train_loss:3.3000 train_time:834563ms step_avg:179.24ms
step:4667/5100 train_loss:3.3991 train_time:834704ms step_avg:179.24ms
step:4668/5100 train_loss:3.3150 train_time:834851ms step_avg:179.23ms
step:4669/5100 train_loss:3.2838 train_time:834994ms step_avg:179.22ms
step:4670/5100 train_loss:3.3482 train_time:835546ms step_avg:179.30ms
step:4671/5100 train_loss:3.4336 train_time:835646ms step_avg:179.28ms
step:4672/5100 train_loss:3.3271 train_time:835786ms step_avg:179.28ms
step:4673/5100 train_loss:3.3767 train_time:835926ms step_avg:179.27ms
step:4674/5100 train_loss:3.3148 train_time:836066ms step_avg:179.26ms
step:4675/5100 train_loss:3.3438 train_time:836207ms step_avg:179.25ms
step:4676/5100 train_loss:3.4262 train_time:836346ms step_avg:179.24ms
step:4677/5100 train_loss:3.1562 train_time:836487ms step_avg:179.23ms
step:4678/5100 train_loss:3.2123 train_time:836633ms step_avg:179.23ms
step:4679/5100 train_loss:3.3464 train_time:836775ms step_avg:179.22ms
step:4680/5100 train_loss:3.3073 train_time:837325ms step_avg:179.30ms
step:4681/5100 train_loss:3.3276 train_time:837427ms step_avg:179.28ms
step:4682/5100 train_loss:3.3206 train_time:837569ms step_avg:179.27ms
step:4683/5100 train_loss:3.2517 train_time:837709ms step_avg:179.27ms
step:4684/5100 train_loss:3.2226 train_time:837849ms step_avg:179.26ms
step:4685/5100 train_loss:3.4783 train_time:837988ms step_avg:179.25ms
step:4686/5100 train_loss:3.5563 train_time:838134ms step_avg:179.24ms
step:4687/5100 train_loss:3.2443 train_time:838271ms step_avg:179.23ms
step:4688/5100 train_loss:3.2557 train_time:838419ms step_avg:179.23ms
step:4689/5100 train_loss:3.4375 train_time:838567ms step_avg:179.22ms
step:4690/5100 train_loss:3.2731 train_time:839114ms step_avg:179.30ms
step:4691/5100 train_loss:3.1278 train_time:839215ms step_avg:179.28ms
step:4692/5100 train_loss:3.2356 train_time:839355ms step_avg:179.27ms
step:4693/5100 train_loss:3.2400 train_time:839496ms step_avg:179.26ms
step:4694/5100 train_loss:3.2686 train_time:839636ms step_avg:179.26ms
step:4695/5100 train_loss:3.2767 train_time:839778ms step_avg:179.25ms
step:4696/5100 train_loss:3.2954 train_time:839916ms step_avg:179.24ms
step:4697/5100 train_loss:3.3604 train_time:840057ms step_avg:179.23ms
step:4698/5100 train_loss:3.2726 train_time:840204ms step_avg:179.22ms
step:4699/5100 train_loss:3.3027 train_time:840348ms step_avg:179.22ms
step:4700/5100 train_loss:3.3987 train_time:840899ms step_avg:179.30ms
step:4701/5100 train_loss:3.3165 train_time:840997ms step_avg:179.28ms
step:4702/5100 train_loss:3.3058 train_time:841137ms step_avg:179.27ms
step:4703/5100 train_loss:3.2614 train_time:841278ms step_avg:179.26ms
step:4704/5100 train_loss:3.3461 train_time:841419ms step_avg:179.25ms
step:4705/5100 train_loss:3.2985 train_time:841559ms step_avg:179.25ms
step:4706/5100 train_loss:3.2269 train_time:841701ms step_avg:179.24ms
step:4707/5100 train_loss:3.3531 train_time:841842ms step_avg:179.23ms
step:4708/5100 train_loss:3.4467 train_time:841990ms step_avg:179.22ms
step:4709/5100 train_loss:3.2548 train_time:842133ms step_avg:179.22ms
step:4710/5100 train_loss:3.2369 train_time:842685ms step_avg:179.29ms
step:4711/5100 train_loss:3.2583 train_time:842784ms step_avg:179.28ms
step:4712/5100 train_loss:3.2747 train_time:842924ms step_avg:179.27ms
step:4713/5100 train_loss:3.3962 train_time:843064ms step_avg:179.26ms
step:4714/5100 train_loss:3.2397 train_time:843204ms step_avg:179.25ms
step:4715/5100 train_loss:3.3109 train_time:843344ms step_avg:179.24ms
step:4716/5100 train_loss:3.2364 train_time:843485ms step_avg:179.24ms
step:4717/5100 train_loss:3.3082 train_time:843630ms step_avg:179.23ms
step:4718/5100 train_loss:3.2360 train_time:843774ms step_avg:179.22ms
step:4719/5100 train_loss:3.2027 train_time:843916ms step_avg:179.21ms
step:4720/5100 train_loss:3.3711 train_time:844468ms step_avg:179.29ms
step:4721/5100 train_loss:3.3562 train_time:844567ms step_avg:179.28ms
step:4722/5100 train_loss:3.3573 train_time:844706ms step_avg:179.27ms
step:4723/5100 train_loss:3.2084 train_time:844845ms step_avg:179.26ms
step:4724/5100 train_loss:3.3914 train_time:844985ms step_avg:179.25ms
step:4725/5100 train_loss:3.2701 train_time:845221ms step_avg:179.26ms
step:4726/5100 train_loss:3.5449 train_time:845357ms step_avg:179.25ms
step:4727/5100 train_loss:3.4004 train_time:845495ms step_avg:179.24ms
step:4728/5100 train_loss:3.2744 train_time:845636ms step_avg:179.24ms
step:4729/5100 train_loss:3.2081 train_time:845775ms step_avg:179.23ms
step:4730/5100 train_loss:3.1609 train_time:846325ms step_avg:179.31ms
step:4731/5100 train_loss:3.2606 train_time:846425ms step_avg:179.29ms
step:4732/5100 train_loss:3.3307 train_time:846564ms step_avg:179.28ms
step:4733/5100 train_loss:3.2340 train_time:846706ms step_avg:179.27ms
step:4734/5100 train_loss:3.1121 train_time:846845ms step_avg:179.26ms
step:4735/5100 train_loss:3.4001 train_time:846985ms step_avg:179.26ms
step:4736/5100 train_loss:3.2746 train_time:847125ms step_avg:179.25ms
step:4737/5100 train_loss:3.4478 train_time:847266ms step_avg:179.24ms
step:4738/5100 train_loss:3.3701 train_time:847413ms step_avg:179.23ms
step:4739/5100 train_loss:3.3232 train_time:847556ms step_avg:179.23ms
step:4740/5100 train_loss:3.2909 train_time:848106ms step_avg:179.30ms
step:4741/5100 train_loss:3.3109 train_time:848210ms step_avg:179.29ms
step:4742/5100 train_loss:3.2991 train_time:848352ms step_avg:179.28ms
step:4743/5100 train_loss:3.1812 train_time:848492ms step_avg:179.27ms
step:4744/5100 train_loss:3.3172 train_time:848634ms step_avg:179.26ms
step:4745/5100 train_loss:3.2787 train_time:848775ms step_avg:179.26ms
step:4746/5100 train_loss:3.2814 train_time:848914ms step_avg:179.25ms
step:4747/5100 train_loss:3.2570 train_time:849055ms step_avg:179.24ms
step:4748/5100 train_loss:3.4416 train_time:849202ms step_avg:179.23ms
step:4749/5100 train_loss:3.2882 train_time:849344ms step_avg:179.22ms
step:4750/5100 train_loss:3.3903 train_time:850028ms step_avg:179.33ms
step:4750/5100 val_loss:3.3119 train_time:850048ms step_avg:179.34ms
step:4751/5100 train_loss:3.2056 train_time:850132ms step_avg:179.31ms
step:4752/5100 train_loss:3.1279 train_time:850281ms step_avg:179.31ms
step:4753/5100 train_loss:3.2082 train_time:850424ms step_avg:179.30ms
step:4754/5100 train_loss:3.4107 train_time:850564ms step_avg:179.29ms
step:4755/5100 train_loss:3.2942 train_time:850704ms step_avg:179.28ms
step:4756/5100 train_loss:3.5299 train_time:850847ms step_avg:179.28ms
step:4757/5100 train_loss:3.3996 train_time:850985ms step_avg:179.27ms
step:4758/5100 train_loss:3.3024 train_time:851127ms step_avg:179.26ms
step:4759/5100 train_loss:3.3579 train_time:851275ms step_avg:179.25ms
step:4760/5100 train_loss:3.3457 train_time:851828ms step_avg:179.33ms
step:4761/5100 train_loss:3.2804 train_time:851930ms step_avg:179.32ms
step:4762/5100 train_loss:3.3195 train_time:852066ms step_avg:179.31ms
step:4763/5100 train_loss:3.2934 train_time:852205ms step_avg:179.30ms
step:4764/5100 train_loss:3.1558 train_time:852345ms step_avg:179.29ms
step:4765/5100 train_loss:3.1706 train_time:852485ms step_avg:179.28ms
step:4766/5100 train_loss:3.1675 train_time:852625ms step_avg:179.27ms
step:4767/5100 train_loss:3.4068 train_time:852766ms step_avg:179.27ms
step:4768/5100 train_loss:3.6643 train_time:852916ms step_avg:179.26ms
step:4769/5100 train_loss:3.3801 train_time:853059ms step_avg:179.25ms
step:4770/5100 train_loss:3.2821 train_time:853609ms step_avg:179.33ms
step:4771/5100 train_loss:3.3510 train_time:853710ms step_avg:179.31ms
step:4772/5100 train_loss:3.3072 train_time:853857ms step_avg:179.31ms
step:4773/5100 train_loss:3.2853 train_time:853992ms step_avg:179.30ms
step:4774/5100 train_loss:3.4662 train_time:854134ms step_avg:179.29ms
step:4775/5100 train_loss:3.2838 train_time:854274ms step_avg:179.28ms
step:4776/5100 train_loss:3.4186 train_time:854416ms step_avg:179.27ms
step:4777/5100 train_loss:3.3366 train_time:854557ms step_avg:179.27ms
step:4778/5100 train_loss:3.1733 train_time:854703ms step_avg:179.26ms
step:4779/5100 train_loss:3.3495 train_time:854844ms step_avg:179.25ms
step:4780/5100 train_loss:3.2802 train_time:855398ms step_avg:179.33ms
step:4781/5100 train_loss:3.3515 train_time:855495ms step_avg:179.31ms
step:4782/5100 train_loss:3.2749 train_time:855637ms step_avg:179.30ms
step:4783/5100 train_loss:3.2225 train_time:855777ms step_avg:179.30ms
step:4784/5100 train_loss:3.2752 train_time:855918ms step_avg:179.29ms
step:4785/5100 train_loss:3.2067 train_time:856058ms step_avg:179.28ms
step:4786/5100 train_loss:3.5345 train_time:856198ms step_avg:179.27ms
step:4787/5100 train_loss:3.4218 train_time:856339ms step_avg:179.26ms
step:4788/5100 train_loss:3.3395 train_time:856488ms step_avg:179.26ms
step:4789/5100 train_loss:3.3282 train_time:856631ms step_avg:179.25ms
step:4790/5100 train_loss:3.2477 train_time:857182ms step_avg:179.33ms
step:4791/5100 train_loss:3.3542 train_time:857281ms step_avg:179.31ms
step:4792/5100 train_loss:3.3655 train_time:857422ms step_avg:179.30ms
step:4793/5100 train_loss:3.2732 train_time:857562ms step_avg:179.29ms
step:4794/5100 train_loss:3.3594 train_time:857701ms step_avg:179.29ms
step:4795/5100 train_loss:3.1974 train_time:857842ms step_avg:179.28ms
step:4796/5100 train_loss:3.3386 train_time:857981ms step_avg:179.27ms
step:4797/5100 train_loss:3.4258 train_time:858122ms step_avg:179.26ms
step:4798/5100 train_loss:3.0848 train_time:858270ms step_avg:179.25ms
step:4799/5100 train_loss:3.2634 train_time:858411ms step_avg:179.25ms
step:4800/5100 train_loss:3.2411 train_time:858960ms step_avg:179.32ms
step:4801/5100 train_loss:3.3401 train_time:859062ms step_avg:179.31ms
step:4802/5100 train_loss:3.1667 train_time:859201ms step_avg:179.30ms
step:4803/5100 train_loss:3.1989 train_time:859341ms step_avg:179.29ms
step:4804/5100 train_loss:3.3942 train_time:859481ms step_avg:179.28ms
step:4805/5100 train_loss:3.3411 train_time:859621ms step_avg:179.27ms
step:4806/5100 train_loss:3.4140 train_time:859762ms step_avg:179.27ms
step:4807/5100 train_loss:3.4268 train_time:859902ms step_avg:179.26ms
step:4808/5100 train_loss:3.1930 train_time:860051ms step_avg:179.25ms
step:4809/5100 train_loss:3.3090 train_time:860192ms step_avg:179.24ms
step:4810/5100 train_loss:3.2560 train_time:860746ms step_avg:179.32ms
step:4811/5100 train_loss:3.4868 train_time:860846ms step_avg:179.31ms
step:4812/5100 train_loss:3.2952 train_time:860985ms step_avg:179.30ms
step:4813/5100 train_loss:3.3279 train_time:861125ms step_avg:179.29ms
step:4814/5100 train_loss:3.2216 train_time:861264ms step_avg:179.28ms
step:4815/5100 train_loss:3.2703 train_time:861405ms step_avg:179.27ms
step:4816/5100 train_loss:3.7059 train_time:861545ms step_avg:179.26ms
step:4817/5100 train_loss:3.3787 train_time:861686ms step_avg:179.26ms
step:4818/5100 train_loss:3.3196 train_time:861832ms step_avg:179.25ms
step:4819/5100 train_loss:3.1716 train_time:861976ms step_avg:179.24ms
step:4820/5100 train_loss:3.2968 train_time:862529ms step_avg:179.32ms
step:4821/5100 train_loss:3.3052 train_time:862632ms step_avg:179.30ms
step:4822/5100 train_loss:3.3551 train_time:862769ms step_avg:179.30ms
step:4823/5100 train_loss:3.4171 train_time:862909ms step_avg:179.29ms
step:4824/5100 train_loss:3.2965 train_time:863049ms step_avg:179.28ms
step:4825/5100 train_loss:3.2757 train_time:863189ms step_avg:179.27ms
step:4826/5100 train_loss:3.1985 train_time:863331ms step_avg:179.26ms
step:4827/5100 train_loss:3.1656 train_time:863471ms step_avg:179.25ms
step:4828/5100 train_loss:3.3502 train_time:863617ms step_avg:179.25ms
step:4829/5100 train_loss:3.2311 train_time:863762ms step_avg:179.24ms
step:4830/5100 train_loss:3.3544 train_time:864311ms step_avg:179.32ms
step:4831/5100 train_loss:3.5106 train_time:864410ms step_avg:179.30ms
step:4832/5100 train_loss:3.2483 train_time:864551ms step_avg:179.29ms
step:4833/5100 train_loss:3.3296 train_time:864690ms step_avg:179.28ms
step:4834/5100 train_loss:3.2914 train_time:864830ms step_avg:179.28ms
step:4835/5100 train_loss:3.4803 train_time:864971ms step_avg:179.27ms
step:4836/5100 train_loss:3.2959 train_time:865109ms step_avg:179.26ms
step:4837/5100 train_loss:3.5547 train_time:865251ms step_avg:179.25ms
step:4838/5100 train_loss:3.4990 train_time:865397ms step_avg:179.25ms
step:4839/5100 train_loss:3.3321 train_time:865540ms step_avg:179.24ms
step:4840/5100 train_loss:3.3244 train_time:866092ms step_avg:179.32ms
step:4841/5100 train_loss:3.3175 train_time:866191ms step_avg:179.30ms
step:4842/5100 train_loss:3.3511 train_time:866332ms step_avg:179.29ms
step:4843/5100 train_loss:3.3476 train_time:866472ms step_avg:179.28ms
step:4844/5100 train_loss:3.2065 train_time:866614ms step_avg:179.27ms
step:4845/5100 train_loss:3.2357 train_time:866758ms step_avg:179.27ms
step:4846/5100 train_loss:3.2085 train_time:866894ms step_avg:179.26ms
step:4847/5100 train_loss:3.3722 train_time:867037ms step_avg:179.25ms
step:4848/5100 train_loss:3.2392 train_time:867184ms step_avg:179.24ms
step:4849/5100 train_loss:3.2783 train_time:867327ms step_avg:179.24ms
step:4850/5100 train_loss:3.4098 train_time:867879ms step_avg:179.31ms
step:4851/5100 train_loss:3.2991 train_time:867978ms step_avg:179.30ms
step:4852/5100 train_loss:3.1015 train_time:868118ms step_avg:179.29ms
step:4853/5100 train_loss:3.1952 train_time:868258ms step_avg:179.28ms
step:4854/5100 train_loss:3.3320 train_time:868398ms step_avg:179.27ms
step:4855/5100 train_loss:3.2865 train_time:868539ms step_avg:179.26ms
step:4856/5100 train_loss:3.4192 train_time:868680ms step_avg:179.26ms
step:4857/5100 train_loss:3.2605 train_time:868821ms step_avg:179.25ms
step:4858/5100 train_loss:3.2943 train_time:868969ms step_avg:179.24ms
step:4859/5100 train_loss:3.2469 train_time:869112ms step_avg:179.24ms
step:4860/5100 train_loss:3.3785 train_time:869664ms step_avg:179.31ms
step:4861/5100 train_loss:3.2441 train_time:869761ms step_avg:179.30ms
step:4862/5100 train_loss:3.3010 train_time:869902ms step_avg:179.29ms
step:4863/5100 train_loss:3.3081 train_time:870043ms step_avg:179.28ms
step:4864/5100 train_loss:3.2707 train_time:870182ms step_avg:179.27ms
step:4865/5100 train_loss:3.3448 train_time:870322ms step_avg:179.26ms
step:4866/5100 train_loss:2.9901 train_time:870462ms step_avg:179.25ms
step:4867/5100 train_loss:3.2147 train_time:870603ms step_avg:179.25ms
step:4868/5100 train_loss:3.2685 train_time:870750ms step_avg:179.24ms
step:4869/5100 train_loss:3.2903 train_time:870893ms step_avg:179.23ms
step:4870/5100 train_loss:3.2916 train_time:871448ms step_avg:179.31ms
step:4871/5100 train_loss:3.2984 train_time:871546ms step_avg:179.29ms
step:4872/5100 train_loss:3.4097 train_time:871687ms step_avg:179.29ms
step:4873/5100 train_loss:3.3973 train_time:871829ms step_avg:179.28ms
step:4874/5100 train_loss:3.4283 train_time:871969ms step_avg:179.27ms
step:4875/5100 train_loss:3.5023 train_time:872110ms step_avg:179.26ms
step:4875/5100 val_loss:3.3001 train_time:872172ms step_avg:179.27ms
step:4876/5100 train_loss:3.3209 train_time:872257ms step_avg:179.26ms
step:4877/5100 train_loss:3.2331 train_time:872407ms step_avg:179.25ms
step:4878/5100 train_loss:3.1923 train_time:872552ms step_avg:179.24ms
step:4879/5100 train_loss:3.2532 train_time:872695ms step_avg:179.23ms
step:4880/5100 train_loss:3.3782 train_time:873241ms step_avg:179.31ms
step:4881/5100 train_loss:3.2245 train_time:873342ms step_avg:179.29ms
step:4882/5100 train_loss:3.3497 train_time:873484ms step_avg:179.29ms
step:4883/5100 train_loss:3.3592 train_time:873623ms step_avg:179.28ms
step:4884/5100 train_loss:3.2658 train_time:873765ms step_avg:179.27ms
step:4885/5100 train_loss:3.2694 train_time:873905ms step_avg:179.26ms
step:4886/5100 train_loss:3.3848 train_time:874045ms step_avg:179.25ms
step:4887/5100 train_loss:3.4023 train_time:874186ms step_avg:179.25ms
step:4888/5100 train_loss:3.2730 train_time:874334ms step_avg:179.24ms
step:4889/5100 train_loss:3.2369 train_time:874476ms step_avg:179.23ms
step:4890/5100 train_loss:3.3262 train_time:875025ms step_avg:179.31ms
step:4891/5100 train_loss:3.2407 train_time:875127ms step_avg:179.29ms
step:4892/5100 train_loss:3.3359 train_time:875270ms step_avg:179.29ms
step:4893/5100 train_loss:3.3223 train_time:875410ms step_avg:179.28ms
step:4894/5100 train_loss:3.3550 train_time:875550ms step_avg:179.27ms
step:4895/5100 train_loss:3.4152 train_time:875691ms step_avg:179.26ms
step:4896/5100 train_loss:3.3240 train_time:875831ms step_avg:179.25ms
step:4897/5100 train_loss:3.2677 train_time:875971ms step_avg:179.25ms
step:4898/5100 train_loss:3.4666 train_time:876118ms step_avg:179.24ms
step:4899/5100 train_loss:3.2316 train_time:876259ms step_avg:179.23ms
step:4900/5100 train_loss:3.2815 train_time:876810ms step_avg:179.31ms
step:4901/5100 train_loss:3.1932 train_time:876909ms step_avg:179.29ms
step:4902/5100 train_loss:3.1633 train_time:877049ms step_avg:179.28ms
step:4903/5100 train_loss:3.2974 train_time:877190ms step_avg:179.27ms
step:4904/5100 train_loss:3.2453 train_time:877331ms step_avg:179.27ms
step:4905/5100 train_loss:3.3213 train_time:877471ms step_avg:179.26ms
step:4906/5100 train_loss:3.3547 train_time:877611ms step_avg:179.25ms
step:4907/5100 train_loss:3.2413 train_time:877752ms step_avg:179.24ms
step:4908/5100 train_loss:3.3200 train_time:877899ms step_avg:179.24ms
step:4909/5100 train_loss:3.2258 train_time:878040ms step_avg:179.23ms
step:4910/5100 train_loss:3.3343 train_time:878592ms step_avg:179.30ms
step:4911/5100 train_loss:3.3797 train_time:878689ms step_avg:179.29ms
step:4912/5100 train_loss:3.2850 train_time:878831ms step_avg:179.28ms
step:4913/5100 train_loss:3.2469 train_time:878970ms step_avg:179.27ms
step:4914/5100 train_loss:3.2422 train_time:879198ms step_avg:179.28ms
step:4915/5100 train_loss:3.1654 train_time:879334ms step_avg:179.27ms
step:4916/5100 train_loss:3.3706 train_time:879474ms step_avg:179.26ms
step:4917/5100 train_loss:3.3455 train_time:879615ms step_avg:179.26ms
step:4918/5100 train_loss:3.2731 train_time:879756ms step_avg:179.25ms
step:4919/5100 train_loss:3.2856 train_time:879895ms step_avg:179.24ms
step:4920/5100 train_loss:3.2885 train_time:880450ms step_avg:179.32ms
step:4921/5100 train_loss:3.3680 train_time:880572ms step_avg:179.31ms
step:4922/5100 train_loss:3.5295 train_time:880713ms step_avg:179.30ms
step:4923/5100 train_loss:3.3814 train_time:880854ms step_avg:179.29ms
step:4924/5100 train_loss:3.2532 train_time:880993ms step_avg:179.28ms
step:4925/5100 train_loss:3.5581 train_time:881135ms step_avg:179.27ms
step:4926/5100 train_loss:3.2953 train_time:881274ms step_avg:179.27ms
step:4927/5100 train_loss:3.2780 train_time:881415ms step_avg:179.26ms
step:4928/5100 train_loss:3.1992 train_time:881562ms step_avg:179.25ms
step:4929/5100 train_loss:3.2058 train_time:881704ms step_avg:179.24ms
step:4930/5100 train_loss:3.3493 train_time:882256ms step_avg:179.32ms
step:4931/5100 train_loss:3.5921 train_time:882354ms step_avg:179.30ms
step:4932/5100 train_loss:3.2003 train_time:882494ms step_avg:179.30ms
step:4933/5100 train_loss:3.3068 train_time:882634ms step_avg:179.29ms
step:4934/5100 train_loss:3.3668 train_time:882774ms step_avg:179.28ms
step:4935/5100 train_loss:3.1595 train_time:882914ms step_avg:179.27ms
step:4936/5100 train_loss:3.3125 train_time:883053ms step_avg:179.26ms
step:4937/5100 train_loss:3.3610 train_time:883194ms step_avg:179.26ms
step:4938/5100 train_loss:3.3470 train_time:883342ms step_avg:179.25ms
step:4939/5100 train_loss:3.3415 train_time:883486ms step_avg:179.24ms
step:4940/5100 train_loss:3.4602 train_time:884168ms step_avg:179.34ms
step:4941/5100 train_loss:3.2981 train_time:884266ms step_avg:179.33ms
step:4942/5100 train_loss:3.3138 train_time:884406ms step_avg:179.32ms
step:4943/5100 train_loss:3.0626 train_time:884548ms step_avg:179.31ms
step:4944/5100 train_loss:3.5472 train_time:884688ms step_avg:179.30ms
step:4945/5100 train_loss:3.5085 train_time:884829ms step_avg:179.30ms
step:4946/5100 train_loss:3.1316 train_time:884968ms step_avg:179.29ms
step:4947/5100 train_loss:3.3812 train_time:885110ms step_avg:179.28ms
step:4948/5100 train_loss:3.4091 train_time:885257ms step_avg:179.27ms
step:4949/5100 train_loss:3.2460 train_time:885401ms step_avg:179.27ms
step:4950/5100 train_loss:3.3653 train_time:885951ms step_avg:179.34ms
step:4951/5100 train_loss:3.2349 train_time:886049ms step_avg:179.33ms
step:4952/5100 train_loss:3.3525 train_time:886190ms step_avg:179.32ms
step:4953/5100 train_loss:3.3188 train_time:886330ms step_avg:179.31ms
step:4954/5100 train_loss:3.2003 train_time:886471ms step_avg:179.30ms
step:4955/5100 train_loss:3.3458 train_time:886611ms step_avg:179.29ms
step:4956/5100 train_loss:3.1704 train_time:886755ms step_avg:179.29ms
step:4957/5100 train_loss:3.2660 train_time:886892ms step_avg:179.28ms
step:4958/5100 train_loss:3.2469 train_time:887042ms step_avg:179.27ms
step:4959/5100 train_loss:3.2676 train_time:887184ms step_avg:179.27ms
step:4960/5100 train_loss:3.3052 train_time:887737ms step_avg:179.34ms
step:4961/5100 train_loss:3.4483 train_time:887835ms step_avg:179.32ms
step:4962/5100 train_loss:3.2145 train_time:887974ms step_avg:179.32ms
step:4963/5100 train_loss:3.3505 train_time:888114ms step_avg:179.31ms
step:4964/5100 train_loss:3.1902 train_time:888253ms step_avg:179.30ms
step:4965/5100 train_loss:3.9038 train_time:888394ms step_avg:179.29ms
step:4966/5100 train_loss:3.1812 train_time:888533ms step_avg:179.28ms
step:4967/5100 train_loss:3.3231 train_time:888674ms step_avg:179.28ms
step:4968/5100 train_loss:3.1421 train_time:888821ms step_avg:179.27ms
step:4969/5100 train_loss:3.8597 train_time:888964ms step_avg:179.26ms
step:4970/5100 train_loss:3.3838 train_time:889516ms step_avg:179.34ms
step:4971/5100 train_loss:3.3064 train_time:889613ms step_avg:179.32ms
step:4972/5100 train_loss:3.2497 train_time:889754ms step_avg:179.31ms
step:4973/5100 train_loss:3.3326 train_time:889893ms step_avg:179.31ms
step:4974/5100 train_loss:3.2101 train_time:890032ms step_avg:179.30ms
step:4975/5100 train_loss:3.2082 train_time:890173ms step_avg:179.29ms
step:4976/5100 train_loss:3.3544 train_time:890313ms step_avg:179.28ms
step:4977/5100 train_loss:3.2815 train_time:890454ms step_avg:179.27ms
step:4978/5100 train_loss:3.2390 train_time:890601ms step_avg:179.27ms
step:4979/5100 train_loss:3.2924 train_time:890742ms step_avg:179.26ms
step:4980/5100 train_loss:3.2343 train_time:891292ms step_avg:179.33ms
step:4981/5100 train_loss:3.3734 train_time:891391ms step_avg:179.32ms
step:4982/5100 train_loss:3.3461 train_time:891530ms step_avg:179.31ms
step:4983/5100 train_loss:3.1495 train_time:891670ms step_avg:179.30ms
step:4984/5100 train_loss:3.1746 train_time:891811ms step_avg:179.29ms
step:4985/5100 train_loss:3.4568 train_time:891951ms step_avg:179.29ms
step:4986/5100 train_loss:3.3433 train_time:892092ms step_avg:179.28ms
step:4987/5100 train_loss:3.2618 train_time:892232ms step_avg:179.27ms
step:4988/5100 train_loss:3.2960 train_time:892381ms step_avg:179.26ms
step:4989/5100 train_loss:3.2758 train_time:892523ms step_avg:179.26ms
step:4990/5100 train_loss:3.2537 train_time:893072ms step_avg:179.33ms
step:4991/5100 train_loss:3.3122 train_time:893169ms step_avg:179.32ms
step:4992/5100 train_loss:3.3494 train_time:893309ms step_avg:179.31ms
step:4993/5100 train_loss:3.1753 train_time:893450ms step_avg:179.30ms
step:4994/5100 train_loss:3.3076 train_time:893592ms step_avg:179.29ms
step:4995/5100 train_loss:3.2315 train_time:893730ms step_avg:179.28ms
step:4996/5100 train_loss:3.3781 train_time:893871ms step_avg:179.28ms
step:4997/5100 train_loss:3.2492 train_time:894012ms step_avg:179.27ms
step:4998/5100 train_loss:3.4137 train_time:894164ms step_avg:179.26ms
step:4999/5100 train_loss:3.2740 train_time:894302ms step_avg:179.25ms
step:5000/5100 train_loss:3.4028 train_time:894852ms step_avg:179.33ms
step:5000/5100 val_loss:3.2906 train_time:894872ms step_avg:179.33ms
step:5001/5100 train_loss:3.3265 train_time:894957ms step_avg:179.31ms
step:5002/5100 train_loss:3.3254 train_time:895108ms step_avg:179.31ms
step:5003/5100 train_loss:3.2163 train_time:895249ms step_avg:179.30ms
step:5004/5100 train_loss:3.2878 train_time:895389ms step_avg:179.29ms
step:5005/5100 train_loss:3.3058 train_time:895529ms step_avg:179.29ms
step:5006/5100 train_loss:3.1692 train_time:895671ms step_avg:179.28ms
step:5007/5100 train_loss:3.4041 train_time:895810ms step_avg:179.27ms
step:5008/5100 train_loss:3.2546 train_time:895950ms step_avg:179.26ms
step:5009/5100 train_loss:3.2808 train_time:896094ms step_avg:179.25ms
step:5010/5100 train_loss:3.2496 train_time:896647ms step_avg:179.33ms
step:5011/5100 train_loss:3.4548 train_time:896745ms step_avg:179.31ms
step:5012/5100 train_loss:3.2533 train_time:896886ms step_avg:179.31ms
step:5013/5100 train_loss:3.2390 train_time:897027ms step_avg:179.30ms
step:5014/5100 train_loss:3.1922 train_time:897165ms step_avg:179.29ms
step:5015/5100 train_loss:3.2985 train_time:897306ms step_avg:179.28ms
step:5016/5100 train_loss:3.2845 train_time:897446ms step_avg:179.27ms
step:5017/5100 train_loss:3.3211 train_time:897587ms step_avg:179.27ms
step:5018/5100 train_loss:3.3414 train_time:897737ms step_avg:179.26ms
step:5019/5100 train_loss:3.2967 train_time:897877ms step_avg:179.25ms
step:5020/5100 train_loss:3.7988 train_time:898424ms step_avg:179.33ms
step:5021/5100 train_loss:3.2483 train_time:898525ms step_avg:179.31ms
step:5022/5100 train_loss:3.3510 train_time:898669ms step_avg:179.30ms
step:5023/5100 train_loss:3.2752 train_time:898805ms step_avg:179.29ms
step:5024/5100 train_loss:3.4147 train_time:898946ms step_avg:179.29ms
step:5025/5100 train_loss:3.2092 train_time:899085ms step_avg:179.28ms
step:5026/5100 train_loss:3.3739 train_time:899227ms step_avg:179.27ms
step:5027/5100 train_loss:3.2240 train_time:899367ms step_avg:179.26ms
step:5028/5100 train_loss:3.4373 train_time:899513ms step_avg:179.26ms
step:5029/5100 train_loss:3.3390 train_time:899654ms step_avg:179.25ms
step:5030/5100 train_loss:3.3723 train_time:900202ms step_avg:179.32ms
step:5031/5100 train_loss:3.2250 train_time:900303ms step_avg:179.31ms
step:5032/5100 train_loss:3.2691 train_time:900443ms step_avg:179.30ms
step:5033/5100 train_loss:3.2085 train_time:900583ms step_avg:179.29ms
step:5034/5100 train_loss:3.3980 train_time:900724ms step_avg:179.28ms
step:5035/5100 train_loss:3.3916 train_time:900865ms step_avg:179.28ms
step:5036/5100 train_loss:3.2499 train_time:901004ms step_avg:179.27ms
step:5037/5100 train_loss:3.1727 train_time:901150ms step_avg:179.26ms
step:5038/5100 train_loss:3.2069 train_time:901293ms step_avg:179.25ms
step:5039/5100 train_loss:3.3405 train_time:901437ms step_avg:179.25ms
step:5040/5100 train_loss:3.2702 train_time:901986ms step_avg:179.32ms
step:5041/5100 train_loss:3.4469 train_time:902081ms step_avg:179.30ms
step:5042/5100 train_loss:3.2384 train_time:902223ms step_avg:179.30ms
step:5043/5100 train_loss:3.4253 train_time:902364ms step_avg:179.29ms
step:5044/5100 train_loss:3.3336 train_time:902506ms step_avg:179.28ms
step:5045/5100 train_loss:3.4009 train_time:902646ms step_avg:179.27ms
step:5046/5100 train_loss:3.2188 train_time:902785ms step_avg:179.27ms
step:5047/5100 train_loss:3.3579 train_time:902926ms step_avg:179.26ms
step:5048/5100 train_loss:3.1083 train_time:903074ms step_avg:179.25ms
step:5049/5100 train_loss:3.2707 train_time:903217ms step_avg:179.25ms
step:5050/5100 train_loss:3.2769 train_time:903762ms step_avg:179.32ms
step:5051/5100 train_loss:3.2244 train_time:903861ms step_avg:179.30ms
step:5052/5100 train_loss:3.2616 train_time:904002ms step_avg:179.29ms
step:5053/5100 train_loss:3.3054 train_time:904143ms step_avg:179.29ms
step:5054/5100 train_loss:3.3452 train_time:904284ms step_avg:179.28ms
step:5055/5100 train_loss:3.4233 train_time:904425ms step_avg:179.27ms
step:5056/5100 train_loss:3.3595 train_time:904565ms step_avg:179.26ms
step:5057/5100 train_loss:3.2523 train_time:904705ms step_avg:179.26ms
step:5058/5100 train_loss:3.1502 train_time:904852ms step_avg:179.25ms
step:5059/5100 train_loss:3.0689 train_time:904994ms step_avg:179.24ms
step:5060/5100 train_loss:3.2843 train_time:905545ms step_avg:179.32ms
step:5061/5100 train_loss:3.3655 train_time:905640ms step_avg:179.30ms
step:5062/5100 train_loss:3.2974 train_time:905780ms step_avg:179.29ms
step:5063/5100 train_loss:3.4193 train_time:905922ms step_avg:179.28ms
step:5064/5100 train_loss:3.4227 train_time:906062ms step_avg:179.28ms
step:5065/5100 train_loss:3.2777 train_time:906204ms step_avg:179.27ms
step:5066/5100 train_loss:3.3913 train_time:906343ms step_avg:179.26ms
step:5067/5100 train_loss:3.5850 train_time:906486ms step_avg:179.25ms
step:5068/5100 train_loss:3.2417 train_time:906632ms step_avg:179.25ms
step:5069/5100 train_loss:3.5846 train_time:906775ms step_avg:179.24ms
step:5070/5100 train_loss:3.2911 train_time:907329ms step_avg:179.31ms
step:5071/5100 train_loss:3.7192 train_time:907435ms step_avg:179.30ms
step:5072/5100 train_loss:3.2432 train_time:907569ms step_avg:179.29ms
step:5073/5100 train_loss:3.2972 train_time:907711ms step_avg:179.28ms
step:5074/5100 train_loss:3.4378 train_time:907849ms step_avg:179.28ms
step:5075/5100 train_loss:3.2755 train_time:907988ms step_avg:179.27ms
step:5076/5100 train_loss:3.2654 train_time:908128ms step_avg:179.26ms
step:5077/5100 train_loss:3.2340 train_time:908268ms step_avg:179.25ms
step:5078/5100 train_loss:3.3138 train_time:908419ms step_avg:179.25ms
step:5079/5100 train_loss:3.4467 train_time:908561ms step_avg:179.24ms
step:5080/5100 train_loss:3.4205 train_time:909117ms step_avg:179.31ms
step:5081/5100 train_loss:3.2435 train_time:909214ms step_avg:179.30ms
step:5082/5100 train_loss:3.3676 train_time:909355ms step_avg:179.29ms
step:5083/5100 train_loss:3.2329 train_time:909495ms step_avg:179.28ms
step:5084/5100 train_loss:3.3100 train_time:909639ms step_avg:179.27ms
step:5085/5100 train_loss:3.2037 train_time:909774ms step_avg:179.27ms
step:5086/5100 train_loss:4.0517 train_time:909915ms step_avg:179.26ms
step:5087/5100 train_loss:3.3438 train_time:910055ms step_avg:179.25ms
step:5088/5100 train_loss:3.2596 train_time:910201ms step_avg:179.24ms
step:5089/5100 train_loss:3.2685 train_time:910344ms step_avg:179.24ms
step:5090/5100 train_loss:3.4041 train_time:910898ms step_avg:179.31ms
step:5091/5100 train_loss:3.3261 train_time:910998ms step_avg:179.30ms
step:5092/5100 train_loss:3.2226 train_time:911138ms step_avg:179.29ms
step:5093/5100 train_loss:3.2386 train_time:911278ms step_avg:179.28ms
step:5094/5100 train_loss:3.2395 train_time:911419ms step_avg:179.27ms
step:5095/5100 train_loss:3.1655 train_time:911560ms step_avg:179.26ms
step:5096/5100 train_loss:3.2915 train_time:911702ms step_avg:179.26ms
step:5097/5100 train_loss:3.0755 train_time:911844ms step_avg:179.25ms
step:5098/5100 train_loss:3.3750 train_time:911990ms step_avg:179.24ms
step:5099/5100 train_loss:3.2328 train_time:912133ms step_avg:179.24ms
step:5100/5100 train_loss:3.2774 train_time:912686ms step_avg:179.31ms
step:5100/5100 val_loss:3.2858 train_time:912706ms step_avg:179.31ms