====================================================================================================
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(1, g.size(0)/g.size(1))**0.5
                    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
    embed_learning_rate : float = 0.0036
    muon_learning_rate : float = 0.02
    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.embed_learning_rate, betas=(0.9, 0.95),
                               weight_decay=args.weight_decay, fused=True)
from soap import SOAP
optimizer2 = SOAP(raw_model.transformer.h.parameters(), lr=0.0018, betas=(.95, .95), precondition_frequency=10)
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:
Fri Oct 25 08:04:01 2024       
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.183.01             Driver Version: 535.183.01   CUDA Version: 12.4     |
|-----------------------------------------+----------------------+----------------------+
| 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 | 00000000:05:00.0 Off |                  Off |
| N/A   37C    P0             116W / 700W |   4855MiB / 81559MiB |      8%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   1  NVIDIA H100 80GB HBM3          Off | 00000000:06:00.0 Off |                  Off |
| N/A   41C    P0             120W / 700W |   4903MiB / 81559MiB |     13%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   2  NVIDIA H100 80GB HBM3          Off | 00000000:65:00.0 Off |                  Off |
| N/A   42C    P0             121W / 700W |   4903MiB / 81559MiB |      2%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   3  NVIDIA H100 80GB HBM3          Off | 00000000:68:00.0 Off |                  Off |
| N/A   37C    P0             119W / 700W |   4903MiB / 81559MiB |      4%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   4  NVIDIA H100 80GB HBM3          Off | 00000000:85:00.0 Off |                  Off |
| N/A   37C    P0             113W / 700W |   4903MiB / 81559MiB |      8%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   5  NVIDIA H100 80GB HBM3          Off | 00000000:86:00.0 Off |                  Off |
| N/A   42C    P0             123W / 700W |   4903MiB / 81559MiB |     10%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   6  NVIDIA H100 80GB HBM3          Off | 00000000:E5:00.0 Off |                  Off |
| N/A   42C    P0             125W / 700W |   4903MiB / 81559MiB |      4%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   7  NVIDIA H100 80GB HBM3          Off | 00000000:E8:00.0 Off |                  Off |
| N/A   37C    P0             116W / 700W |   4663MiB / 81559MiB |      5%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

====================================================================================================
step:0/5100 val_loss:15.9636 train_time:226ms step_avg:nanms
step:1/5100 train_loss:15.9606 train_time:3607ms step_avg:nanms
step:2/5100 train_loss:15.9529 train_time:3812ms step_avg:nanms
step:3/5100 train_loss:15.6285 train_time:4006ms step_avg:nanms
step:4/5100 train_loss:11.3437 train_time:4201ms step_avg:nanms
step:5/5100 train_loss:10.8671 train_time:4394ms step_avg:nanms
step:6/5100 train_loss:10.8335 train_time:4591ms step_avg:nanms
step:7/5100 train_loss:10.7676 train_time:4787ms step_avg:nanms
step:8/5100 train_loss:10.7270 train_time:4981ms step_avg:nanms
step:9/5100 train_loss:10.6311 train_time:5176ms step_avg:nanms
step:10/5100 train_loss:10.5496 train_time:5371ms step_avg:nanms
step:11/5100 train_loss:10.4381 train_time:1259ms step_avg:nanms
step:12/5100 train_loss:10.3329 train_time:1461ms step_avg:nanms
step:13/5100 train_loss:10.1879 train_time:1657ms step_avg:552.30ms
step:14/5100 train_loss:10.0678 train_time:1850ms step_avg:462.60ms
step:15/5100 train_loss:9.9368 train_time:2046ms step_avg:409.12ms
step:16/5100 train_loss:9.8031 train_time:2240ms step_avg:373.35ms
step:17/5100 train_loss:9.6448 train_time:2433ms step_avg:347.62ms
step:18/5100 train_loss:9.5280 train_time:2629ms step_avg:328.57ms
step:19/5100 train_loss:9.3404 train_time:2825ms step_avg:313.86ms
step:20/5100 train_loss:9.1881 train_time:3020ms step_avg:302.01ms
step:21/5100 train_loss:8.9499 train_time:4251ms step_avg:386.49ms
step:22/5100 train_loss:8.9359 train_time:4452ms step_avg:371.01ms
step:23/5100 train_loss:8.8857 train_time:4648ms step_avg:357.54ms
step:24/5100 train_loss:8.6274 train_time:4843ms step_avg:345.94ms
step:25/5100 train_loss:8.5259 train_time:5038ms step_avg:335.87ms
step:26/5100 train_loss:8.3176 train_time:5231ms step_avg:326.96ms
step:27/5100 train_loss:8.1319 train_time:5427ms step_avg:319.23ms
step:28/5100 train_loss:8.1324 train_time:5623ms step_avg:312.38ms
step:29/5100 train_loss:7.8146 train_time:5818ms step_avg:306.20ms
step:30/5100 train_loss:7.8766 train_time:6012ms step_avg:300.61ms
step:31/5100 train_loss:8.6983 train_time:7243ms step_avg:344.91ms
step:32/5100 train_loss:7.6920 train_time:7443ms step_avg:338.34ms
step:33/5100 train_loss:7.5554 train_time:7639ms step_avg:332.11ms
step:34/5100 train_loss:7.9195 train_time:7832ms step_avg:326.34ms
step:35/5100 train_loss:7.7218 train_time:8026ms step_avg:321.06ms
step:36/5100 train_loss:7.8952 train_time:8222ms step_avg:316.21ms
step:37/5100 train_loss:7.9156 train_time:8417ms step_avg:311.74ms
step:38/5100 train_loss:7.7837 train_time:8612ms step_avg:307.56ms
step:39/5100 train_loss:7.7095 train_time:8806ms step_avg:303.67ms
step:40/5100 train_loss:7.8146 train_time:9002ms step_avg:300.06ms
step:41/5100 train_loss:7.7013 train_time:10232ms step_avg:330.06ms
step:42/5100 train_loss:7.7111 train_time:10433ms step_avg:326.02ms
step:43/5100 train_loss:7.5796 train_time:10628ms step_avg:322.05ms
step:44/5100 train_loss:7.6605 train_time:10823ms step_avg:318.31ms
step:45/5100 train_loss:7.6431 train_time:11017ms step_avg:314.78ms
step:46/5100 train_loss:7.8145 train_time:11211ms step_avg:311.42ms
step:47/5100 train_loss:7.6490 train_time:11406ms step_avg:308.28ms
step:48/5100 train_loss:7.5587 train_time:11600ms step_avg:305.27ms
step:49/5100 train_loss:7.7338 train_time:11795ms step_avg:302.44ms
step:50/5100 train_loss:7.6341 train_time:11989ms step_avg:299.73ms
step:51/5100 train_loss:7.7402 train_time:13221ms step_avg:322.47ms
step:52/5100 train_loss:7.6238 train_time:13421ms step_avg:319.55ms
step:53/5100 train_loss:7.5064 train_time:13616ms step_avg:316.66ms
step:54/5100 train_loss:7.6084 train_time:13810ms step_avg:313.87ms
step:55/5100 train_loss:7.5538 train_time:14007ms step_avg:311.27ms
step:56/5100 train_loss:7.7904 train_time:14203ms step_avg:308.76ms
step:57/5100 train_loss:7.5641 train_time:14398ms step_avg:306.34ms
step:58/5100 train_loss:7.4596 train_time:14593ms step_avg:304.01ms
step:59/5100 train_loss:7.6126 train_time:14789ms step_avg:301.81ms
step:60/5100 train_loss:7.5046 train_time:14984ms step_avg:299.68ms
step:61/5100 train_loss:7.6087 train_time:16214ms step_avg:317.92ms
step:62/5100 train_loss:7.4573 train_time:16414ms step_avg:315.65ms
step:63/5100 train_loss:7.5410 train_time:16609ms step_avg:313.38ms
step:64/5100 train_loss:7.4698 train_time:16805ms step_avg:311.20ms
step:65/5100 train_loss:8.3466 train_time:17000ms step_avg:309.09ms
step:66/5100 train_loss:7.3359 train_time:17195ms step_avg:307.06ms
step:67/5100 train_loss:7.4453 train_time:17390ms step_avg:305.10ms
step:68/5100 train_loss:7.3281 train_time:17586ms step_avg:303.21ms
step:69/5100 train_loss:7.6357 train_time:17782ms step_avg:301.38ms
step:70/5100 train_loss:7.2399 train_time:17976ms step_avg:299.61ms
step:71/5100 train_loss:7.1912 train_time:19206ms step_avg:314.86ms
step:72/5100 train_loss:7.4954 train_time:19408ms step_avg:313.03ms
step:73/5100 train_loss:7.3713 train_time:19604ms step_avg:311.17ms
step:74/5100 train_loss:7.2910 train_time:19799ms step_avg:309.36ms
step:75/5100 train_loss:7.3171 train_time:19994ms step_avg:307.59ms
step:76/5100 train_loss:7.3394 train_time:20189ms step_avg:305.90ms
step:77/5100 train_loss:7.2449 train_time:20385ms step_avg:304.26ms
step:78/5100 train_loss:7.2732 train_time:20580ms step_avg:302.65ms
step:79/5100 train_loss:7.2550 train_time:20775ms step_avg:301.09ms
step:80/5100 train_loss:7.2478 train_time:20971ms step_avg:299.59ms
step:81/5100 train_loss:7.2175 train_time:22203ms step_avg:312.72ms
step:82/5100 train_loss:6.9238 train_time:22406ms step_avg:311.19ms
step:83/5100 train_loss:7.1112 train_time:22602ms step_avg:309.62ms
step:84/5100 train_loss:7.0684 train_time:22798ms step_avg:308.08ms
step:85/5100 train_loss:6.9065 train_time:22992ms step_avg:306.56ms
step:86/5100 train_loss:6.7700 train_time:23188ms step_avg:305.11ms
step:87/5100 train_loss:6.9726 train_time:23385ms step_avg:303.70ms
step:88/5100 train_loss:6.8702 train_time:23581ms step_avg:302.32ms
step:89/5100 train_loss:7.0343 train_time:23777ms step_avg:300.98ms
step:90/5100 train_loss:6.9305 train_time:23971ms step_avg:299.64ms
step:91/5100 train_loss:6.8352 train_time:25203ms step_avg:311.15ms
step:92/5100 train_loss:6.7812 train_time:25404ms step_avg:309.80ms
step:93/5100 train_loss:6.9184 train_time:25601ms step_avg:308.44ms
step:94/5100 train_loss:6.7508 train_time:25796ms step_avg:307.10ms
step:95/5100 train_loss:6.7161 train_time:25991ms step_avg:305.78ms
step:96/5100 train_loss:6.7121 train_time:26188ms step_avg:304.51ms
step:97/5100 train_loss:6.5702 train_time:26385ms step_avg:303.27ms
step:98/5100 train_loss:6.7062 train_time:26581ms step_avg:302.06ms
step:99/5100 train_loss:6.5340 train_time:26778ms step_avg:300.87ms
step:100/5100 train_loss:6.7408 train_time:26972ms step_avg:299.69ms
step:101/5100 train_loss:6.6678 train_time:28205ms step_avg:309.95ms
step:102/5100 train_loss:6.5666 train_time:28408ms step_avg:308.78ms
step:103/5100 train_loss:6.6254 train_time:28605ms step_avg:307.58ms
step:104/5100 train_loss:6.6809 train_time:28800ms step_avg:306.39ms
step:105/5100 train_loss:6.4504 train_time:28996ms step_avg:305.23ms
step:106/5100 train_loss:6.6004 train_time:29191ms step_avg:304.07ms
step:107/5100 train_loss:6.8518 train_time:29388ms step_avg:302.97ms
step:108/5100 train_loss:6.5648 train_time:29585ms step_avg:301.88ms
step:109/5100 train_loss:6.2271 train_time:29780ms step_avg:300.81ms
step:110/5100 train_loss:6.5129 train_time:29975ms step_avg:299.75ms
step:111/5100 train_loss:6.4952 train_time:31207ms step_avg:308.98ms
step:112/5100 train_loss:6.4809 train_time:31408ms step_avg:307.92ms
step:113/5100 train_loss:6.5047 train_time:31604ms step_avg:306.84ms
step:114/5100 train_loss:6.4706 train_time:31801ms step_avg:305.78ms
step:115/5100 train_loss:6.2848 train_time:31997ms step_avg:304.74ms
step:116/5100 train_loss:6.5111 train_time:32192ms step_avg:303.70ms
step:117/5100 train_loss:6.2737 train_time:32387ms step_avg:302.69ms
step:118/5100 train_loss:6.3166 train_time:32584ms step_avg:301.71ms
step:119/5100 train_loss:6.3499 train_time:32780ms step_avg:300.74ms
step:120/5100 train_loss:6.4453 train_time:32976ms step_avg:299.78ms
step:121/5100 train_loss:6.3777 train_time:34208ms step_avg:308.18ms
step:122/5100 train_loss:6.2562 train_time:34409ms step_avg:307.23ms
step:123/5100 train_loss:6.2771 train_time:34605ms step_avg:306.24ms
step:124/5100 train_loss:6.1535 train_time:34801ms step_avg:305.27ms
step:125/5100 train_loss:6.4812 train_time:34998ms step_avg:304.33ms
step:125/5100 val_loss:6.2955 train_time:35031ms step_avg:304.61ms
step:126/5100 train_loss:6.2510 train_time:35214ms step_avg:303.57ms
step:127/5100 train_loss:6.2999 train_time:35411ms step_avg:302.66ms
step:128/5100 train_loss:6.3507 train_time:35605ms step_avg:301.74ms
step:129/5100 train_loss:6.1663 train_time:35802ms step_avg:300.86ms
step:130/5100 train_loss:6.4266 train_time:35999ms step_avg:299.99ms
step:131/5100 train_loss:6.2320 train_time:37232ms step_avg:307.70ms
step:132/5100 train_loss:6.2849 train_time:37432ms step_avg:306.82ms
step:133/5100 train_loss:6.1498 train_time:37629ms step_avg:305.92ms
step:134/5100 train_loss:6.1749 train_time:37824ms step_avg:305.03ms
step:135/5100 train_loss:6.1690 train_time:38021ms step_avg:304.17ms
step:136/5100 train_loss:6.1199 train_time:38218ms step_avg:303.32ms
step:137/5100 train_loss:5.9777 train_time:38414ms step_avg:302.48ms
step:138/5100 train_loss:6.0829 train_time:38611ms step_avg:301.64ms
step:139/5100 train_loss:6.0850 train_time:38807ms step_avg:300.83ms
step:140/5100 train_loss:6.1022 train_time:39003ms step_avg:300.02ms
step:141/5100 train_loss:6.0451 train_time:40236ms step_avg:307.14ms
step:142/5100 train_loss:5.9907 train_time:40436ms step_avg:306.34ms
step:143/5100 train_loss:6.0790 train_time:40632ms step_avg:305.51ms
step:144/5100 train_loss:5.8219 train_time:40828ms step_avg:304.68ms
step:145/5100 train_loss:6.0217 train_time:41023ms step_avg:303.88ms
step:146/5100 train_loss:5.9494 train_time:41219ms step_avg:303.08ms
step:147/5100 train_loss:5.9019 train_time:41415ms step_avg:302.30ms
step:148/5100 train_loss:5.9570 train_time:41612ms step_avg:301.53ms
step:149/5100 train_loss:5.8906 train_time:41807ms step_avg:300.77ms
step:150/5100 train_loss:5.9884 train_time:42002ms step_avg:300.02ms
step:151/5100 train_loss:5.9956 train_time:43236ms step_avg:306.64ms
step:152/5100 train_loss:5.9021 train_time:43438ms step_avg:305.90ms
step:153/5100 train_loss:5.8425 train_time:43634ms step_avg:305.13ms
step:154/5100 train_loss:5.8697 train_time:43830ms step_avg:304.38ms
step:155/5100 train_loss:5.8200 train_time:44024ms step_avg:303.61ms
step:156/5100 train_loss:5.8447 train_time:44220ms step_avg:302.88ms
step:157/5100 train_loss:5.7943 train_time:44417ms step_avg:302.16ms
step:158/5100 train_loss:5.9404 train_time:44613ms step_avg:301.44ms
step:159/5100 train_loss:5.6999 train_time:44808ms step_avg:300.72ms
step:160/5100 train_loss:5.7506 train_time:45004ms step_avg:300.02ms
step:161/5100 train_loss:5.6296 train_time:46237ms step_avg:306.21ms
step:162/5100 train_loss:5.6941 train_time:46439ms step_avg:305.52ms
step:163/5100 train_loss:5.7495 train_time:46635ms step_avg:304.80ms
step:164/5100 train_loss:5.7369 train_time:46830ms step_avg:304.09ms
step:165/5100 train_loss:5.5603 train_time:47025ms step_avg:303.39ms
step:166/5100 train_loss:5.6495 train_time:47221ms step_avg:302.70ms
step:167/5100 train_loss:5.8087 train_time:47418ms step_avg:302.02ms
step:168/5100 train_loss:5.5757 train_time:47613ms step_avg:301.35ms
step:169/5100 train_loss:5.6157 train_time:47809ms step_avg:300.68ms
step:170/5100 train_loss:5.5024 train_time:48004ms step_avg:300.03ms
step:171/5100 train_loss:5.4903 train_time:49237ms step_avg:305.82ms
step:172/5100 train_loss:5.5172 train_time:49438ms step_avg:305.18ms
step:173/5100 train_loss:5.4794 train_time:49635ms step_avg:304.51ms
step:174/5100 train_loss:5.5444 train_time:49831ms step_avg:303.84ms
step:175/5100 train_loss:5.6451 train_time:50025ms step_avg:303.18ms
step:176/5100 train_loss:5.5680 train_time:50222ms step_avg:302.54ms
step:177/5100 train_loss:5.3752 train_time:50418ms step_avg:301.91ms
step:178/5100 train_loss:5.3408 train_time:50614ms step_avg:301.27ms
step:179/5100 train_loss:5.3465 train_time:50809ms step_avg:300.64ms
step:180/5100 train_loss:5.4230 train_time:51004ms step_avg:300.02ms
step:181/5100 train_loss:5.3784 train_time:52237ms step_avg:305.48ms
step:182/5100 train_loss:5.4708 train_time:52438ms step_avg:304.87ms
step:183/5100 train_loss:5.3693 train_time:52634ms step_avg:304.24ms
step:184/5100 train_loss:5.2706 train_time:52830ms step_avg:303.62ms
step:185/5100 train_loss:5.2839 train_time:53025ms step_avg:303.00ms
step:186/5100 train_loss:5.4101 train_time:53222ms step_avg:302.40ms
step:187/5100 train_loss:5.2669 train_time:53417ms step_avg:301.79ms
step:188/5100 train_loss:5.5459 train_time:53614ms step_avg:301.20ms
step:189/5100 train_loss:5.3005 train_time:53927ms step_avg:301.27ms
step:190/5100 train_loss:5.2180 train_time:54285ms step_avg:301.58ms
step:191/5100 train_loss:5.3859 train_time:55516ms step_avg:306.72ms
step:192/5100 train_loss:5.2073 train_time:55717ms step_avg:306.14ms
step:193/5100 train_loss:5.1236 train_time:55914ms step_avg:305.54ms
step:194/5100 train_loss:5.2851 train_time:56110ms step_avg:304.94ms
step:195/5100 train_loss:5.2365 train_time:56305ms step_avg:304.35ms
step:196/5100 train_loss:5.4301 train_time:56500ms step_avg:303.77ms
step:197/5100 train_loss:5.3063 train_time:56697ms step_avg:303.19ms
step:198/5100 train_loss:5.1368 train_time:56893ms step_avg:302.62ms
step:199/5100 train_loss:5.1446 train_time:57089ms step_avg:302.06ms
step:200/5100 train_loss:5.0561 train_time:57285ms step_avg:301.50ms
step:201/5100 train_loss:5.1346 train_time:58517ms step_avg:306.37ms
step:202/5100 train_loss:5.0535 train_time:58720ms step_avg:305.83ms
step:203/5100 train_loss:5.2580 train_time:58917ms step_avg:305.27ms
step:204/5100 train_loss:5.1647 train_time:59112ms step_avg:304.70ms
step:205/5100 train_loss:5.1023 train_time:59307ms step_avg:304.14ms
step:206/5100 train_loss:5.2642 train_time:59502ms step_avg:303.58ms
step:207/5100 train_loss:4.9313 train_time:59699ms step_avg:303.04ms
step:208/5100 train_loss:5.0678 train_time:59896ms step_avg:302.50ms
step:209/5100 train_loss:5.0243 train_time:60092ms step_avg:301.97ms
step:210/5100 train_loss:5.1937 train_time:60287ms step_avg:301.44ms
step:211/5100 train_loss:5.0851 train_time:61519ms step_avg:306.07ms
step:212/5100 train_loss:4.9777 train_time:61720ms step_avg:305.55ms
step:213/5100 train_loss:5.1411 train_time:61917ms step_avg:305.01ms
step:214/5100 train_loss:4.9319 train_time:62113ms step_avg:304.48ms
step:215/5100 train_loss:5.0287 train_time:62309ms step_avg:303.94ms
step:216/5100 train_loss:4.8787 train_time:62504ms step_avg:303.42ms
step:217/5100 train_loss:5.0328 train_time:62701ms step_avg:302.90ms
step:218/5100 train_loss:4.9772 train_time:62898ms step_avg:302.39ms
step:219/5100 train_loss:4.9216 train_time:63094ms step_avg:301.88ms
step:220/5100 train_loss:4.9556 train_time:63289ms step_avg:301.38ms
step:221/5100 train_loss:4.9577 train_time:64521ms step_avg:305.79ms
step:222/5100 train_loss:5.0010 train_time:64723ms step_avg:305.30ms
step:223/5100 train_loss:4.9539 train_time:64920ms step_avg:304.79ms
step:224/5100 train_loss:4.9482 train_time:65115ms step_avg:304.28ms
step:225/5100 train_loss:5.0389 train_time:65311ms step_avg:303.77ms
step:226/5100 train_loss:4.7720 train_time:65507ms step_avg:303.27ms
step:227/5100 train_loss:4.8075 train_time:65703ms step_avg:302.78ms
step:228/5100 train_loss:4.7835 train_time:65900ms step_avg:302.29ms
step:229/5100 train_loss:4.9507 train_time:66096ms step_avg:301.81ms
step:230/5100 train_loss:4.7905 train_time:66292ms step_avg:301.33ms
step:231/5100 train_loss:4.9244 train_time:67523ms step_avg:305.53ms
step:232/5100 train_loss:4.7743 train_time:67726ms step_avg:305.07ms
step:233/5100 train_loss:4.7282 train_time:67922ms step_avg:304.58ms
step:234/5100 train_loss:4.9193 train_time:68118ms step_avg:304.10ms
step:235/5100 train_loss:4.7681 train_time:68314ms step_avg:303.62ms
step:236/5100 train_loss:4.6370 train_time:68510ms step_avg:303.14ms
step:237/5100 train_loss:4.9378 train_time:68705ms step_avg:302.66ms
step:238/5100 train_loss:4.8214 train_time:68901ms step_avg:302.20ms
step:239/5100 train_loss:4.7122 train_time:69097ms step_avg:301.73ms
step:240/5100 train_loss:4.8605 train_time:69293ms step_avg:301.28ms
step:241/5100 train_loss:4.8461 train_time:70525ms step_avg:305.30ms
step:242/5100 train_loss:4.7255 train_time:70727ms step_avg:304.86ms
step:243/5100 train_loss:4.8740 train_time:70923ms step_avg:304.39ms
step:244/5100 train_loss:4.7188 train_time:71118ms step_avg:303.92ms
step:245/5100 train_loss:4.7126 train_time:71315ms step_avg:303.47ms
step:246/5100 train_loss:4.7916 train_time:71510ms step_avg:303.01ms
step:247/5100 train_loss:4.7442 train_time:71705ms step_avg:302.55ms
step:248/5100 train_loss:4.6776 train_time:71901ms step_avg:302.10ms
step:249/5100 train_loss:4.8424 train_time:72097ms step_avg:301.66ms
step:250/5100 train_loss:4.5731 train_time:72294ms step_avg:301.23ms
step:250/5100 val_loss:4.6583 train_time:72327ms step_avg:301.36ms
step:251/5100 train_loss:4.5923 train_time:73547ms step_avg:305.17ms
step:252/5100 train_loss:4.7086 train_time:73748ms step_avg:304.74ms
step:253/5100 train_loss:4.7130 train_time:73943ms step_avg:304.29ms
step:254/5100 train_loss:4.5759 train_time:74139ms step_avg:303.85ms
step:255/5100 train_loss:4.5192 train_time:74333ms step_avg:303.40ms
step:256/5100 train_loss:4.6784 train_time:74530ms step_avg:302.97ms
step:257/5100 train_loss:4.5984 train_time:74726ms step_avg:302.53ms
step:258/5100 train_loss:4.6045 train_time:74921ms step_avg:302.10ms
step:259/5100 train_loss:4.5416 train_time:75116ms step_avg:301.67ms
step:260/5100 train_loss:4.5715 train_time:75313ms step_avg:301.25ms
step:261/5100 train_loss:4.6248 train_time:76546ms step_avg:304.96ms
step:262/5100 train_loss:4.5913 train_time:76746ms step_avg:304.55ms
step:263/5100 train_loss:4.5524 train_time:76944ms step_avg:304.13ms
step:264/5100 train_loss:4.4742 train_time:77140ms step_avg:303.70ms
step:265/5100 train_loss:4.5342 train_time:77338ms step_avg:303.28ms
step:266/5100 train_loss:4.3726 train_time:77532ms step_avg:302.86ms
step:267/5100 train_loss:4.4594 train_time:77728ms step_avg:302.44ms
step:268/5100 train_loss:4.4758 train_time:77923ms step_avg:302.03ms
step:269/5100 train_loss:4.4632 train_time:78118ms step_avg:301.62ms
step:270/5100 train_loss:4.4051 train_time:78314ms step_avg:301.21ms
step:271/5100 train_loss:4.6169 train_time:79546ms step_avg:304.78ms
step:272/5100 train_loss:4.5212 train_time:79747ms step_avg:304.38ms
step:273/5100 train_loss:4.4037 train_time:79944ms step_avg:303.97ms
step:274/5100 train_loss:4.4617 train_time:80139ms step_avg:303.56ms
step:275/5100 train_loss:4.5364 train_time:80335ms step_avg:303.15ms
step:276/5100 train_loss:4.5486 train_time:80531ms step_avg:302.75ms
step:277/5100 train_loss:4.7082 train_time:80728ms step_avg:302.35ms
step:278/5100 train_loss:4.5120 train_time:80923ms step_avg:301.95ms
step:279/5100 train_loss:4.5970 train_time:81120ms step_avg:301.56ms
step:280/5100 train_loss:4.4854 train_time:81316ms step_avg:301.17ms
step:281/5100 train_loss:4.5565 train_time:82548ms step_avg:304.60ms
step:282/5100 train_loss:4.4253 train_time:82748ms step_avg:304.22ms
step:283/5100 train_loss:4.4515 train_time:82945ms step_avg:303.83ms
step:284/5100 train_loss:4.3789 train_time:83141ms step_avg:303.43ms
step:285/5100 train_loss:4.5276 train_time:83336ms step_avg:303.04ms
step:286/5100 train_loss:4.5208 train_time:83533ms step_avg:302.65ms
step:287/5100 train_loss:4.5473 train_time:83728ms step_avg:302.27ms
step:288/5100 train_loss:4.3841 train_time:83926ms step_avg:301.89ms
step:289/5100 train_loss:4.4703 train_time:84122ms step_avg:301.51ms
step:290/5100 train_loss:4.3199 train_time:84317ms step_avg:301.13ms
step:291/5100 train_loss:4.3247 train_time:85548ms step_avg:304.44ms
step:292/5100 train_loss:4.4275 train_time:85750ms step_avg:304.08ms
step:293/5100 train_loss:4.3268 train_time:85946ms step_avg:303.70ms
step:294/5100 train_loss:4.3496 train_time:86142ms step_avg:303.32ms
step:295/5100 train_loss:4.4006 train_time:86338ms step_avg:302.94ms
step:296/5100 train_loss:4.2747 train_time:86533ms step_avg:302.56ms
step:297/5100 train_loss:4.2919 train_time:86731ms step_avg:302.20ms
step:298/5100 train_loss:4.2822 train_time:86928ms step_avg:301.83ms
step:299/5100 train_loss:4.3983 train_time:87123ms step_avg:301.46ms
step:300/5100 train_loss:4.2581 train_time:87319ms step_avg:301.10ms
step:301/5100 train_loss:4.4159 train_time:88551ms step_avg:304.30ms
step:302/5100 train_loss:4.4125 train_time:88753ms step_avg:303.95ms
step:303/5100 train_loss:4.3413 train_time:88949ms step_avg:303.58ms
step:304/5100 train_loss:4.3973 train_time:89146ms step_avg:303.22ms
step:305/5100 train_loss:4.3754 train_time:89341ms step_avg:302.85ms
step:306/5100 train_loss:4.8360 train_time:89537ms step_avg:302.49ms
step:307/5100 train_loss:4.3399 train_time:89734ms step_avg:302.13ms
step:308/5100 train_loss:4.2432 train_time:89930ms step_avg:301.78ms
step:309/5100 train_loss:4.4165 train_time:90127ms step_avg:301.43ms
step:310/5100 train_loss:4.2519 train_time:90323ms step_avg:301.08ms
step:311/5100 train_loss:4.4715 train_time:91553ms step_avg:304.16ms
step:312/5100 train_loss:4.3454 train_time:91757ms step_avg:303.83ms
step:313/5100 train_loss:4.2677 train_time:91951ms step_avg:303.47ms
step:314/5100 train_loss:4.3983 train_time:92148ms step_avg:303.12ms
step:315/5100 train_loss:4.4785 train_time:92344ms step_avg:302.77ms
step:316/5100 train_loss:4.3481 train_time:92539ms step_avg:302.42ms
step:317/5100 train_loss:4.1833 train_time:92735ms step_avg:302.07ms
step:318/5100 train_loss:4.2678 train_time:92931ms step_avg:301.73ms
step:319/5100 train_loss:4.2878 train_time:93127ms step_avg:301.38ms
step:320/5100 train_loss:4.2665 train_time:93323ms step_avg:301.04ms
step:321/5100 train_loss:4.3657 train_time:94555ms step_avg:304.03ms
step:322/5100 train_loss:4.3294 train_time:94757ms step_avg:303.71ms
step:323/5100 train_loss:4.2933 train_time:94953ms step_avg:303.36ms
step:324/5100 train_loss:4.3754 train_time:95149ms step_avg:303.02ms
step:325/5100 train_loss:4.3529 train_time:95344ms step_avg:302.68ms
step:326/5100 train_loss:4.4098 train_time:95541ms step_avg:302.34ms
step:327/5100 train_loss:4.2603 train_time:95736ms step_avg:302.00ms
step:328/5100 train_loss:4.7575 train_time:95932ms step_avg:301.67ms
step:329/5100 train_loss:4.4405 train_time:96128ms step_avg:301.34ms
step:330/5100 train_loss:4.1835 train_time:96323ms step_avg:301.01ms
step:331/5100 train_loss:4.1238 train_time:97555ms step_avg:303.91ms
step:332/5100 train_loss:4.3499 train_time:97756ms step_avg:303.59ms
step:333/5100 train_loss:4.2519 train_time:97953ms step_avg:303.26ms
step:334/5100 train_loss:4.2389 train_time:98149ms step_avg:302.93ms
step:335/5100 train_loss:4.2005 train_time:98345ms step_avg:302.60ms
step:336/5100 train_loss:4.3764 train_time:98540ms step_avg:302.27ms
step:337/5100 train_loss:4.3107 train_time:98735ms step_avg:301.94ms
step:338/5100 train_loss:4.7664 train_time:98931ms step_avg:301.62ms
step:339/5100 train_loss:4.3120 train_time:99127ms step_avg:301.30ms
step:340/5100 train_loss:4.2508 train_time:99325ms step_avg:300.98ms
step:341/5100 train_loss:4.2761 train_time:100557ms step_avg:303.80ms
step:342/5100 train_loss:4.1942 train_time:100759ms step_avg:303.49ms
step:343/5100 train_loss:4.1658 train_time:100954ms step_avg:303.16ms
step:344/5100 train_loss:4.2143 train_time:101150ms step_avg:302.84ms
step:345/5100 train_loss:4.3453 train_time:101345ms step_avg:302.52ms
step:346/5100 train_loss:4.1839 train_time:101541ms step_avg:302.20ms
step:347/5100 train_loss:4.1214 train_time:101736ms step_avg:301.89ms
step:348/5100 train_loss:4.1598 train_time:101932ms step_avg:301.57ms
step:349/5100 train_loss:4.2114 train_time:102128ms step_avg:301.26ms
step:350/5100 train_loss:4.1672 train_time:102325ms step_avg:300.96ms
step:351/5100 train_loss:3.8762 train_time:103557ms step_avg:303.69ms
step:352/5100 train_loss:4.1532 train_time:103758ms step_avg:303.39ms
step:353/5100 train_loss:4.4717 train_time:103954ms step_avg:303.07ms
step:354/5100 train_loss:4.0014 train_time:104149ms step_avg:302.76ms
step:355/5100 train_loss:4.2623 train_time:104346ms step_avg:302.45ms
step:356/5100 train_loss:4.1329 train_time:104541ms step_avg:302.14ms
step:357/5100 train_loss:4.2212 train_time:104736ms step_avg:301.83ms
step:358/5100 train_loss:4.1863 train_time:104932ms step_avg:301.53ms
step:359/5100 train_loss:4.1769 train_time:105129ms step_avg:301.23ms
step:360/5100 train_loss:4.1521 train_time:105324ms step_avg:300.92ms
step:361/5100 train_loss:3.7883 train_time:106557ms step_avg:303.58ms
step:362/5100 train_loss:4.3500 train_time:106759ms step_avg:303.29ms
step:363/5100 train_loss:4.2568 train_time:106953ms step_avg:302.98ms
step:364/5100 train_loss:4.1684 train_time:107150ms step_avg:302.68ms
step:365/5100 train_loss:4.0821 train_time:107346ms step_avg:302.38ms
step:366/5100 train_loss:4.2391 train_time:107541ms step_avg:302.08ms
step:367/5100 train_loss:4.2056 train_time:107736ms step_avg:301.78ms
step:368/5100 train_loss:4.1890 train_time:107932ms step_avg:301.49ms
step:369/5100 train_loss:4.1738 train_time:108128ms step_avg:301.19ms
step:370/5100 train_loss:4.0623 train_time:108324ms step_avg:300.90ms
step:371/5100 train_loss:4.2165 train_time:109555ms step_avg:303.48ms
step:372/5100 train_loss:4.1097 train_time:109757ms step_avg:303.20ms
step:373/5100 train_loss:4.0099 train_time:109952ms step_avg:302.90ms
step:374/5100 train_loss:4.2330 train_time:110148ms step_avg:302.60ms
step:375/5100 train_loss:4.1576 train_time:110343ms step_avg:302.31ms
step:375/5100 val_loss:4.1510 train_time:110376ms step_avg:302.40ms
step:376/5100 train_loss:4.1202 train_time:110558ms step_avg:302.07ms
step:377/5100 train_loss:4.1798 train_time:110757ms step_avg:301.79ms
step:378/5100 train_loss:4.0963 train_time:111078ms step_avg:301.84ms
step:379/5100 train_loss:4.1637 train_time:111273ms step_avg:301.55ms
step:380/5100 train_loss:4.1992 train_time:111628ms step_avg:301.70ms
step:381/5100 train_loss:4.2585 train_time:112858ms step_avg:304.20ms
step:382/5100 train_loss:4.1698 train_time:113059ms step_avg:303.92ms
step:383/5100 train_loss:4.1518 train_time:113255ms step_avg:303.63ms
step:384/5100 train_loss:4.0946 train_time:113449ms step_avg:303.34ms
step:385/5100 train_loss:4.1819 train_time:113645ms step_avg:303.05ms
step:386/5100 train_loss:4.0908 train_time:113840ms step_avg:302.77ms
step:387/5100 train_loss:4.2031 train_time:114036ms step_avg:302.48ms
step:388/5100 train_loss:4.4018 train_time:114231ms step_avg:302.20ms
step:389/5100 train_loss:4.1192 train_time:114426ms step_avg:301.92ms
step:390/5100 train_loss:4.0930 train_time:114621ms step_avg:301.63ms
step:391/5100 train_loss:4.1985 train_time:115853ms step_avg:304.08ms
step:392/5100 train_loss:4.1178 train_time:116053ms step_avg:303.80ms
step:393/5100 train_loss:4.2256 train_time:116247ms step_avg:303.52ms
step:394/5100 train_loss:4.0497 train_time:116443ms step_avg:303.24ms
step:395/5100 train_loss:4.1920 train_time:116640ms step_avg:302.96ms
step:396/5100 train_loss:3.9293 train_time:116835ms step_avg:302.68ms
step:397/5100 train_loss:4.1324 train_time:117030ms step_avg:302.40ms
step:398/5100 train_loss:4.1914 train_time:117226ms step_avg:302.13ms
step:399/5100 train_loss:4.1871 train_time:117420ms step_avg:301.85ms
step:400/5100 train_loss:4.0924 train_time:117617ms step_avg:301.58ms
step:401/5100 train_loss:4.2180 train_time:118848ms step_avg:303.96ms
step:402/5100 train_loss:4.2165 train_time:119048ms step_avg:303.69ms
step:403/5100 train_loss:4.1425 train_time:119244ms step_avg:303.42ms
step:404/5100 train_loss:4.2409 train_time:119440ms step_avg:303.15ms
step:405/5100 train_loss:4.0109 train_time:119635ms step_avg:302.87ms
step:406/5100 train_loss:4.0900 train_time:119831ms step_avg:302.60ms
step:407/5100 train_loss:4.3743 train_time:120025ms step_avg:302.33ms
step:408/5100 train_loss:4.0955 train_time:120221ms step_avg:302.06ms
step:409/5100 train_loss:4.1195 train_time:120419ms step_avg:301.80ms
step:410/5100 train_loss:4.1632 train_time:120615ms step_avg:301.54ms
step:411/5100 train_loss:4.0416 train_time:121847ms step_avg:303.86ms
step:412/5100 train_loss:4.0610 train_time:122047ms step_avg:303.60ms
step:413/5100 train_loss:4.4668 train_time:122243ms step_avg:303.33ms
step:414/5100 train_loss:3.9406 train_time:122439ms step_avg:303.07ms
step:415/5100 train_loss:4.3136 train_time:122635ms step_avg:302.80ms
step:416/5100 train_loss:4.0531 train_time:122830ms step_avg:302.54ms
step:417/5100 train_loss:4.0499 train_time:123024ms step_avg:302.27ms
step:418/5100 train_loss:4.2474 train_time:123221ms step_avg:302.01ms
step:419/5100 train_loss:3.9757 train_time:123417ms step_avg:301.75ms
step:420/5100 train_loss:4.0963 train_time:123613ms step_avg:301.49ms
step:421/5100 train_loss:4.0367 train_time:124845ms step_avg:303.76ms
step:422/5100 train_loss:3.9343 train_time:125045ms step_avg:303.51ms
step:423/5100 train_loss:4.0584 train_time:125241ms step_avg:303.25ms
step:424/5100 train_loss:4.1499 train_time:125437ms step_avg:302.99ms
step:425/5100 train_loss:3.9211 train_time:125632ms step_avg:302.73ms
step:426/5100 train_loss:4.1048 train_time:125827ms step_avg:302.47ms
step:427/5100 train_loss:3.9716 train_time:126022ms step_avg:302.21ms
step:428/5100 train_loss:4.1860 train_time:126219ms step_avg:301.96ms
step:429/5100 train_loss:4.1108 train_time:126415ms step_avg:301.71ms
step:430/5100 train_loss:4.0418 train_time:126609ms step_avg:301.45ms
step:431/5100 train_loss:4.0124 train_time:127839ms step_avg:303.66ms
step:432/5100 train_loss:3.9157 train_time:128042ms step_avg:303.42ms
step:433/5100 train_loss:4.0458 train_time:128237ms step_avg:303.16ms
step:434/5100 train_loss:4.1209 train_time:128433ms step_avg:302.91ms
step:435/5100 train_loss:4.0446 train_time:128627ms step_avg:302.65ms
step:436/5100 train_loss:4.1022 train_time:128823ms step_avg:302.40ms
step:437/5100 train_loss:4.1090 train_time:129020ms step_avg:302.15ms
step:438/5100 train_loss:3.9902 train_time:129216ms step_avg:301.91ms
step:439/5100 train_loss:4.0133 train_time:129411ms step_avg:301.66ms
step:440/5100 train_loss:3.9736 train_time:129607ms step_avg:301.41ms
step:441/5100 train_loss:4.1534 train_time:130840ms step_avg:303.57ms
step:442/5100 train_loss:4.0470 train_time:131041ms step_avg:303.33ms
step:443/5100 train_loss:4.0303 train_time:131235ms step_avg:303.08ms
step:444/5100 train_loss:3.9176 train_time:131430ms step_avg:302.83ms
step:445/5100 train_loss:4.1815 train_time:131625ms step_avg:302.59ms
step:446/5100 train_loss:4.1217 train_time:131822ms step_avg:302.34ms
step:447/5100 train_loss:4.1155 train_time:132017ms step_avg:302.10ms
step:448/5100 train_loss:4.0306 train_time:132213ms step_avg:301.86ms
step:449/5100 train_loss:4.1253 train_time:132408ms step_avg:301.61ms
step:450/5100 train_loss:3.9499 train_time:132603ms step_avg:301.37ms
step:451/5100 train_loss:3.9935 train_time:133836ms step_avg:303.48ms
step:452/5100 train_loss:3.8595 train_time:134036ms step_avg:303.25ms
step:453/5100 train_loss:3.9797 train_time:134232ms step_avg:303.01ms
step:454/5100 train_loss:3.9588 train_time:134427ms step_avg:302.76ms
step:455/5100 train_loss:3.9102 train_time:134622ms step_avg:302.52ms
step:456/5100 train_loss:4.1267 train_time:134818ms step_avg:302.28ms
step:457/5100 train_loss:3.9970 train_time:135014ms step_avg:302.04ms
step:458/5100 train_loss:4.0621 train_time:135209ms step_avg:301.80ms
step:459/5100 train_loss:4.1165 train_time:135404ms step_avg:301.57ms
step:460/5100 train_loss:3.9066 train_time:135601ms step_avg:301.33ms
step:461/5100 train_loss:4.0786 train_time:136833ms step_avg:303.40ms
step:462/5100 train_loss:3.9767 train_time:137033ms step_avg:303.17ms
step:463/5100 train_loss:3.9868 train_time:137227ms step_avg:302.93ms
step:464/5100 train_loss:4.0526 train_time:137422ms step_avg:302.69ms
step:465/5100 train_loss:3.9874 train_time:137618ms step_avg:302.46ms
step:466/5100 train_loss:3.9923 train_time:137814ms step_avg:302.22ms
step:467/5100 train_loss:4.0922 train_time:138010ms step_avg:301.99ms
step:468/5100 train_loss:4.0960 train_time:138206ms step_avg:301.76ms
step:469/5100 train_loss:4.0749 train_time:138400ms step_avg:301.53ms
step:470/5100 train_loss:3.9603 train_time:138596ms step_avg:301.30ms
step:471/5100 train_loss:4.0462 train_time:139828ms step_avg:303.32ms
step:472/5100 train_loss:4.0944 train_time:140031ms step_avg:303.10ms
step:473/5100 train_loss:4.0349 train_time:140226ms step_avg:302.86ms
step:474/5100 train_loss:3.9940 train_time:140421ms step_avg:302.63ms
step:475/5100 train_loss:3.8491 train_time:140617ms step_avg:302.40ms
step:476/5100 train_loss:4.2772 train_time:140812ms step_avg:302.17ms
step:477/5100 train_loss:4.0426 train_time:141010ms step_avg:301.95ms
step:478/5100 train_loss:3.8430 train_time:141205ms step_avg:301.72ms
step:479/5100 train_loss:4.0781 train_time:141400ms step_avg:301.49ms
step:480/5100 train_loss:4.0381 train_time:141597ms step_avg:301.27ms
step:481/5100 train_loss:4.1809 train_time:142829ms step_avg:303.25ms
step:482/5100 train_loss:3.9968 train_time:143030ms step_avg:303.03ms
step:483/5100 train_loss:3.7942 train_time:143225ms step_avg:302.80ms
step:484/5100 train_loss:4.0820 train_time:143421ms step_avg:302.58ms
step:485/5100 train_loss:3.9385 train_time:143617ms step_avg:302.35ms
step:486/5100 train_loss:3.9445 train_time:143812ms step_avg:302.13ms
step:487/5100 train_loss:3.8696 train_time:144008ms step_avg:301.90ms
step:488/5100 train_loss:3.9324 train_time:144202ms step_avg:301.68ms
step:489/5100 train_loss:4.1343 train_time:144399ms step_avg:301.46ms
step:490/5100 train_loss:3.9746 train_time:144595ms step_avg:301.24ms
step:491/5100 train_loss:3.8690 train_time:145827ms step_avg:303.17ms
step:492/5100 train_loss:3.8852 train_time:146027ms step_avg:302.96ms
step:493/5100 train_loss:3.9961 train_time:146223ms step_avg:302.74ms
step:494/5100 train_loss:3.8442 train_time:146419ms step_avg:302.52ms
step:495/5100 train_loss:3.9789 train_time:146615ms step_avg:302.30ms
step:496/5100 train_loss:3.9136 train_time:146811ms step_avg:302.08ms
step:497/5100 train_loss:3.8030 train_time:147005ms step_avg:301.86ms
step:498/5100 train_loss:3.9982 train_time:147201ms step_avg:301.64ms
step:499/5100 train_loss:4.0657 train_time:147397ms step_avg:301.43ms
step:500/5100 train_loss:4.1046 train_time:147592ms step_avg:301.21ms
step:500/5100 val_loss:3.9722 train_time:147625ms step_avg:301.27ms
step:501/5100 train_loss:4.0098 train_time:148842ms step_avg:303.14ms
step:502/5100 train_loss:4.0619 train_time:149044ms step_avg:302.93ms
step:503/5100 train_loss:3.9958 train_time:149240ms step_avg:302.72ms
step:504/5100 train_loss:4.0380 train_time:149435ms step_avg:302.50ms
step:505/5100 train_loss:3.9969 train_time:149630ms step_avg:302.28ms
step:506/5100 train_loss:4.0806 train_time:149827ms step_avg:302.07ms
step:507/5100 train_loss:3.8880 train_time:150023ms step_avg:301.86ms
step:508/5100 train_loss:4.0287 train_time:150218ms step_avg:301.64ms
step:509/5100 train_loss:4.0971 train_time:150412ms step_avg:301.43ms
step:510/5100 train_loss:4.0425 train_time:150608ms step_avg:301.22ms
step:511/5100 train_loss:3.8391 train_time:151840ms step_avg:303.07ms
step:512/5100 train_loss:4.0472 train_time:152042ms step_avg:302.87ms
step:513/5100 train_loss:3.9809 train_time:152237ms step_avg:302.66ms
step:514/5100 train_loss:3.9470 train_time:152431ms step_avg:302.44ms
step:515/5100 train_loss:4.0613 train_time:152626ms step_avg:302.23ms
step:516/5100 train_loss:4.0010 train_time:152822ms step_avg:302.02ms
step:517/5100 train_loss:4.3497 train_time:153018ms step_avg:301.81ms
step:518/5100 train_loss:3.9371 train_time:153213ms step_avg:301.60ms
step:519/5100 train_loss:4.0534 train_time:153408ms step_avg:301.39ms
step:520/5100 train_loss:3.9437 train_time:153604ms step_avg:301.18ms
step:521/5100 train_loss:3.9503 train_time:154835ms step_avg:303.00ms
step:522/5100 train_loss:3.9021 train_time:155036ms step_avg:302.81ms
step:523/5100 train_loss:3.9077 train_time:155232ms step_avg:302.60ms
step:524/5100 train_loss:4.5293 train_time:155428ms step_avg:302.39ms
step:525/5100 train_loss:4.0086 train_time:155623ms step_avg:302.18ms
step:526/5100 train_loss:3.9395 train_time:155818ms step_avg:301.97ms
step:527/5100 train_loss:3.9532 train_time:156013ms step_avg:301.77ms
step:528/5100 train_loss:3.9044 train_time:156208ms step_avg:301.56ms
step:529/5100 train_loss:3.8846 train_time:156404ms step_avg:301.36ms
step:530/5100 train_loss:4.1017 train_time:156599ms step_avg:301.15ms
step:531/5100 train_loss:3.8952 train_time:157830ms step_avg:302.94ms
step:532/5100 train_loss:4.1789 train_time:158032ms step_avg:302.74ms
step:533/5100 train_loss:3.9920 train_time:158229ms step_avg:302.54ms
step:534/5100 train_loss:3.9228 train_time:158425ms step_avg:302.34ms
step:535/5100 train_loss:3.9341 train_time:158619ms step_avg:302.13ms
step:536/5100 train_loss:3.8707 train_time:158814ms step_avg:301.93ms
step:537/5100 train_loss:3.9931 train_time:159009ms step_avg:301.73ms
step:538/5100 train_loss:3.9889 train_time:159205ms step_avg:301.52ms
step:539/5100 train_loss:3.8920 train_time:159400ms step_avg:301.32ms
step:540/5100 train_loss:4.3862 train_time:159594ms step_avg:301.12ms
step:541/5100 train_loss:3.9253 train_time:160826ms step_avg:302.87ms
step:542/5100 train_loss:4.0362 train_time:161026ms step_avg:302.68ms
step:543/5100 train_loss:3.8631 train_time:161223ms step_avg:302.48ms
step:544/5100 train_loss:3.8366 train_time:161418ms step_avg:302.28ms
step:545/5100 train_loss:3.9229 train_time:161613ms step_avg:302.08ms
step:546/5100 train_loss:3.8416 train_time:161809ms step_avg:301.88ms
step:547/5100 train_loss:3.8927 train_time:162005ms step_avg:301.68ms
step:548/5100 train_loss:3.9121 train_time:162199ms step_avg:301.48ms
step:549/5100 train_loss:3.8912 train_time:162394ms step_avg:301.29ms
step:550/5100 train_loss:3.9838 train_time:162589ms step_avg:301.09ms
step:551/5100 train_loss:3.8561 train_time:163821ms step_avg:302.81ms
step:552/5100 train_loss:3.8786 train_time:164022ms step_avg:302.62ms
step:553/5100 train_loss:4.2000 train_time:164218ms step_avg:302.43ms
step:554/5100 train_loss:4.0063 train_time:164412ms step_avg:302.23ms
step:555/5100 train_loss:3.9650 train_time:164608ms step_avg:302.03ms
step:556/5100 train_loss:3.9165 train_time:164804ms step_avg:301.84ms
step:557/5100 train_loss:3.9441 train_time:164999ms step_avg:301.64ms
step:558/5100 train_loss:3.6052 train_time:165194ms step_avg:301.45ms
step:559/5100 train_loss:3.8545 train_time:165389ms step_avg:301.25ms
step:560/5100 train_loss:3.9030 train_time:165585ms step_avg:301.06ms
step:561/5100 train_loss:3.9534 train_time:166815ms step_avg:302.75ms
step:562/5100 train_loss:3.8569 train_time:167016ms step_avg:302.57ms
step:563/5100 train_loss:3.7993 train_time:167212ms step_avg:302.37ms
step:564/5100 train_loss:4.0113 train_time:167408ms step_avg:302.18ms
step:565/5100 train_loss:3.8268 train_time:167604ms step_avg:301.99ms
step:566/5100 train_loss:3.9295 train_time:167799ms step_avg:301.80ms
step:567/5100 train_loss:3.8766 train_time:168139ms step_avg:301.87ms
step:568/5100 train_loss:3.8337 train_time:168334ms step_avg:301.67ms
step:569/5100 train_loss:3.9327 train_time:168529ms step_avg:301.48ms
step:570/5100 train_loss:3.9037 train_time:168889ms step_avg:301.59ms
step:571/5100 train_loss:3.9385 train_time:170120ms step_avg:303.24ms
step:572/5100 train_loss:4.0147 train_time:170319ms step_avg:303.06ms
step:573/5100 train_loss:3.9528 train_time:170513ms step_avg:302.87ms
step:574/5100 train_loss:3.9705 train_time:170709ms step_avg:302.68ms
step:575/5100 train_loss:4.0199 train_time:170905ms step_avg:302.49ms
step:576/5100 train_loss:3.9764 train_time:171100ms step_avg:302.30ms
step:577/5100 train_loss:3.9881 train_time:171295ms step_avg:302.11ms
step:578/5100 train_loss:3.9219 train_time:171490ms step_avg:301.92ms
step:579/5100 train_loss:3.9123 train_time:171685ms step_avg:301.73ms
step:580/5100 train_loss:3.9012 train_time:171879ms step_avg:301.54ms
step:581/5100 train_loss:3.8486 train_time:173111ms step_avg:303.17ms
step:582/5100 train_loss:3.8757 train_time:173313ms step_avg:302.99ms
step:583/5100 train_loss:4.1048 train_time:173509ms step_avg:302.81ms
step:584/5100 train_loss:3.8690 train_time:173705ms step_avg:302.62ms
step:585/5100 train_loss:3.8237 train_time:173900ms step_avg:302.44ms
step:586/5100 train_loss:4.0242 train_time:174094ms step_avg:302.25ms
step:587/5100 train_loss:3.7704 train_time:174290ms step_avg:302.06ms
step:588/5100 train_loss:3.9116 train_time:174485ms step_avg:301.88ms
step:589/5100 train_loss:3.8947 train_time:174679ms step_avg:301.69ms
step:590/5100 train_loss:4.2467 train_time:174873ms step_avg:301.51ms
step:591/5100 train_loss:4.0231 train_time:176105ms step_avg:303.11ms
step:592/5100 train_loss:3.7674 train_time:176305ms step_avg:302.93ms
step:593/5100 train_loss:3.7763 train_time:176501ms step_avg:302.75ms
step:594/5100 train_loss:3.7653 train_time:176697ms step_avg:302.56ms
step:595/5100 train_loss:3.8023 train_time:176891ms step_avg:302.38ms
step:596/5100 train_loss:4.1610 train_time:177088ms step_avg:302.20ms
step:597/5100 train_loss:3.8861 train_time:177283ms step_avg:302.02ms
step:598/5100 train_loss:3.8208 train_time:177478ms step_avg:301.83ms
step:599/5100 train_loss:3.9037 train_time:177672ms step_avg:301.65ms
step:600/5100 train_loss:3.7163 train_time:177867ms step_avg:301.47ms
step:601/5100 train_loss:3.8427 train_time:179097ms step_avg:303.04ms
step:602/5100 train_loss:3.8727 train_time:179299ms step_avg:302.87ms
step:603/5100 train_loss:3.8973 train_time:179493ms step_avg:302.69ms
step:604/5100 train_loss:4.0192 train_time:179689ms step_avg:302.51ms
step:605/5100 train_loss:3.8770 train_time:179886ms step_avg:302.33ms
step:606/5100 train_loss:3.8563 train_time:180081ms step_avg:302.15ms
step:607/5100 train_loss:3.8067 train_time:180275ms step_avg:301.97ms
step:608/5100 train_loss:4.0495 train_time:180469ms step_avg:301.79ms
step:609/5100 train_loss:3.8991 train_time:180664ms step_avg:301.61ms
step:610/5100 train_loss:3.8540 train_time:180861ms step_avg:301.44ms
step:611/5100 train_loss:3.9631 train_time:182093ms step_avg:302.98ms
step:612/5100 train_loss:3.8635 train_time:182293ms step_avg:302.81ms
step:613/5100 train_loss:3.8331 train_time:182489ms step_avg:302.64ms
step:614/5100 train_loss:4.0016 train_time:182685ms step_avg:302.46ms
step:615/5100 train_loss:3.9614 train_time:182880ms step_avg:302.28ms
step:616/5100 train_loss:3.9247 train_time:183073ms step_avg:302.10ms
step:617/5100 train_loss:3.8512 train_time:183269ms step_avg:301.93ms
step:618/5100 train_loss:3.8043 train_time:183464ms step_avg:301.75ms
step:619/5100 train_loss:3.9161 train_time:183661ms step_avg:301.58ms
step:620/5100 train_loss:3.8275 train_time:183857ms step_avg:301.40ms
step:621/5100 train_loss:3.8245 train_time:185086ms step_avg:302.92ms
step:622/5100 train_loss:4.1416 train_time:185287ms step_avg:302.76ms
step:623/5100 train_loss:3.8233 train_time:185482ms step_avg:302.58ms
step:624/5100 train_loss:3.8522 train_time:185677ms step_avg:302.41ms
step:625/5100 train_loss:3.9336 train_time:185871ms step_avg:302.23ms
step:625/5100 val_loss:3.8652 train_time:185904ms step_avg:302.28ms
step:626/5100 train_loss:3.9613 train_time:186081ms step_avg:302.08ms
step:627/5100 train_loss:3.9918 train_time:186278ms step_avg:301.91ms
step:628/5100 train_loss:3.9559 train_time:186473ms step_avg:301.74ms
step:629/5100 train_loss:4.0136 train_time:186666ms step_avg:301.56ms
step:630/5100 train_loss:3.8336 train_time:186861ms step_avg:301.39ms
step:631/5100 train_loss:3.9508 train_time:188092ms step_avg:302.89ms
step:632/5100 train_loss:3.9956 train_time:188295ms step_avg:302.72ms
step:633/5100 train_loss:3.8949 train_time:188490ms step_avg:302.55ms
step:634/5100 train_loss:3.8240 train_time:188685ms step_avg:302.38ms
step:635/5100 train_loss:3.9225 train_time:188881ms step_avg:302.21ms
step:636/5100 train_loss:4.1763 train_time:189076ms step_avg:302.04ms
step:637/5100 train_loss:3.7714 train_time:189270ms step_avg:301.87ms
step:638/5100 train_loss:3.5954 train_time:189465ms step_avg:301.70ms
step:639/5100 train_loss:3.8159 train_time:189661ms step_avg:301.53ms
step:640/5100 train_loss:3.8569 train_time:189856ms step_avg:301.36ms
step:641/5100 train_loss:3.8123 train_time:191087ms step_avg:302.83ms
step:642/5100 train_loss:3.8124 train_time:191290ms step_avg:302.67ms
step:643/5100 train_loss:3.8551 train_time:191485ms step_avg:302.50ms
step:644/5100 train_loss:3.8771 train_time:191680ms step_avg:302.34ms
step:645/5100 train_loss:3.7962 train_time:191876ms step_avg:302.17ms
step:646/5100 train_loss:4.0090 train_time:192070ms step_avg:302.00ms
step:647/5100 train_loss:3.9142 train_time:192265ms step_avg:301.83ms
step:648/5100 train_loss:3.9060 train_time:192461ms step_avg:301.66ms
step:649/5100 train_loss:3.9308 train_time:192655ms step_avg:301.49ms
step:650/5100 train_loss:3.9998 train_time:192851ms step_avg:301.33ms
step:651/5100 train_loss:3.8589 train_time:194082ms step_avg:302.78ms
step:652/5100 train_loss:3.9995 train_time:194282ms step_avg:302.62ms
step:653/5100 train_loss:3.8229 train_time:194476ms step_avg:302.45ms
step:654/5100 train_loss:3.8971 train_time:194671ms step_avg:302.28ms
step:655/5100 train_loss:3.6636 train_time:194865ms step_avg:302.12ms
step:656/5100 train_loss:3.8058 train_time:195061ms step_avg:301.95ms
step:657/5100 train_loss:3.8122 train_time:195255ms step_avg:301.78ms
step:658/5100 train_loss:3.7517 train_time:195449ms step_avg:301.62ms
step:659/5100 train_loss:3.9315 train_time:195645ms step_avg:301.46ms
step:660/5100 train_loss:3.8297 train_time:195841ms step_avg:301.29ms
step:661/5100 train_loss:3.9144 train_time:197072ms step_avg:302.72ms
step:662/5100 train_loss:3.9883 train_time:197272ms step_avg:302.56ms
step:663/5100 train_loss:3.8987 train_time:197466ms step_avg:302.40ms
step:664/5100 train_loss:3.7791 train_time:197661ms step_avg:302.23ms
step:665/5100 train_loss:3.8678 train_time:197856ms step_avg:302.07ms
step:666/5100 train_loss:3.7361 train_time:198051ms step_avg:301.91ms
step:667/5100 train_loss:4.0168 train_time:198245ms step_avg:301.74ms
step:668/5100 train_loss:3.8498 train_time:198441ms step_avg:301.58ms
step:669/5100 train_loss:3.8628 train_time:198636ms step_avg:301.42ms
step:670/5100 train_loss:3.7104 train_time:198831ms step_avg:301.26ms
step:671/5100 train_loss:3.8293 train_time:200061ms step_avg:302.66ms
step:672/5100 train_loss:3.7873 train_time:200262ms step_avg:302.51ms
step:673/5100 train_loss:3.8090 train_time:200456ms step_avg:302.35ms
step:674/5100 train_loss:4.0781 train_time:200650ms step_avg:302.18ms
step:675/5100 train_loss:3.8706 train_time:200844ms step_avg:302.02ms
step:676/5100 train_loss:3.9447 train_time:201040ms step_avg:301.86ms
step:677/5100 train_loss:3.7206 train_time:201235ms step_avg:301.70ms
step:678/5100 train_loss:3.8253 train_time:201429ms step_avg:301.54ms
step:679/5100 train_loss:3.7729 train_time:201625ms step_avg:301.38ms
step:680/5100 train_loss:3.9158 train_time:201821ms step_avg:301.22ms
step:681/5100 train_loss:3.8200 train_time:203053ms step_avg:302.61ms
step:682/5100 train_loss:3.8437 train_time:203252ms step_avg:302.46ms
step:683/5100 train_loss:3.9165 train_time:203446ms step_avg:302.30ms
step:684/5100 train_loss:3.9712 train_time:203643ms step_avg:302.14ms
step:685/5100 train_loss:3.8590 train_time:203838ms step_avg:301.98ms
step:686/5100 train_loss:3.9340 train_time:204033ms step_avg:301.82ms
step:687/5100 train_loss:3.8626 train_time:204226ms step_avg:301.66ms
step:688/5100 train_loss:3.9121 train_time:204422ms step_avg:301.51ms
step:689/5100 train_loss:3.5433 train_time:204617ms step_avg:301.35ms
step:690/5100 train_loss:3.6501 train_time:204814ms step_avg:301.20ms
step:691/5100 train_loss:3.7916 train_time:206044ms step_avg:302.56ms
step:692/5100 train_loss:3.6748 train_time:206243ms step_avg:302.41ms
step:693/5100 train_loss:3.8756 train_time:206440ms step_avg:302.25ms
step:694/5100 train_loss:3.8987 train_time:206636ms step_avg:302.10ms
step:695/5100 train_loss:3.7838 train_time:206830ms step_avg:301.94ms
step:696/5100 train_loss:3.7678 train_time:207024ms step_avg:301.78ms
step:697/5100 train_loss:4.0899 train_time:207220ms step_avg:301.63ms
step:698/5100 train_loss:3.8332 train_time:207417ms step_avg:301.48ms
step:699/5100 train_loss:3.8728 train_time:207612ms step_avg:301.32ms
step:700/5100 train_loss:4.0447 train_time:207806ms step_avg:301.17ms
step:701/5100 train_loss:3.8012 train_time:209038ms step_avg:302.52ms
step:702/5100 train_loss:3.7685 train_time:209241ms step_avg:302.37ms
step:703/5100 train_loss:3.7518 train_time:209436ms step_avg:302.22ms
step:704/5100 train_loss:3.7066 train_time:209630ms step_avg:302.06ms
step:705/5100 train_loss:3.7911 train_time:209825ms step_avg:301.91ms
step:706/5100 train_loss:3.7997 train_time:210022ms step_avg:301.76ms
step:707/5100 train_loss:3.8078 train_time:210219ms step_avg:301.61ms
step:708/5100 train_loss:3.8786 train_time:210415ms step_avg:301.45ms
step:709/5100 train_loss:3.8290 train_time:210610ms step_avg:301.30ms
step:710/5100 train_loss:3.8146 train_time:210805ms step_avg:301.15ms
step:711/5100 train_loss:3.7883 train_time:212035ms step_avg:302.47ms
step:712/5100 train_loss:3.8229 train_time:212238ms step_avg:302.33ms
step:713/5100 train_loss:3.8784 train_time:212433ms step_avg:302.18ms
step:714/5100 train_loss:3.8882 train_time:212628ms step_avg:302.03ms
step:715/5100 train_loss:3.8100 train_time:212824ms step_avg:301.88ms
step:716/5100 train_loss:3.8016 train_time:213019ms step_avg:301.73ms
step:717/5100 train_loss:3.8159 train_time:213216ms step_avg:301.58ms
step:718/5100 train_loss:3.9670 train_time:213410ms step_avg:301.43ms
step:719/5100 train_loss:3.8261 train_time:213605ms step_avg:301.28ms
step:720/5100 train_loss:3.8973 train_time:213801ms step_avg:301.13ms
step:721/5100 train_loss:4.0490 train_time:215033ms step_avg:302.44ms
step:722/5100 train_loss:3.6841 train_time:215235ms step_avg:302.30ms
step:723/5100 train_loss:3.9511 train_time:215429ms step_avg:302.14ms
step:724/5100 train_loss:4.0107 train_time:215624ms step_avg:301.99ms
step:725/5100 train_loss:3.7883 train_time:215820ms step_avg:301.85ms
step:726/5100 train_loss:3.8784 train_time:216016ms step_avg:301.70ms
step:727/5100 train_loss:3.7757 train_time:216210ms step_avg:301.55ms
step:728/5100 train_loss:3.7823 train_time:216405ms step_avg:301.40ms
step:729/5100 train_loss:3.9597 train_time:216601ms step_avg:301.25ms
step:730/5100 train_loss:3.9095 train_time:216796ms step_avg:301.11ms
step:731/5100 train_loss:3.9172 train_time:218025ms step_avg:302.39ms
step:732/5100 train_loss:3.7992 train_time:218227ms step_avg:302.25ms
step:733/5100 train_loss:3.8184 train_time:218423ms step_avg:302.11ms
step:734/5100 train_loss:4.0526 train_time:218620ms step_avg:301.96ms
step:735/5100 train_loss:3.7886 train_time:218815ms step_avg:301.81ms
step:736/5100 train_loss:3.8437 train_time:219009ms step_avg:301.67ms
step:737/5100 train_loss:3.9717 train_time:219204ms step_avg:301.52ms
step:738/5100 train_loss:3.8802 train_time:219400ms step_avg:301.37ms
step:739/5100 train_loss:3.8311 train_time:219596ms step_avg:301.23ms
step:740/5100 train_loss:3.7212 train_time:219790ms step_avg:301.08ms
step:741/5100 train_loss:4.3649 train_time:221021ms step_avg:302.35ms
step:742/5100 train_loss:3.7221 train_time:221221ms step_avg:302.21ms
step:743/5100 train_loss:3.8100 train_time:221417ms step_avg:302.07ms
step:744/5100 train_loss:3.8007 train_time:221612ms step_avg:301.92ms
step:745/5100 train_loss:3.8651 train_time:221806ms step_avg:301.78ms
step:746/5100 train_loss:3.8422 train_time:222001ms step_avg:301.63ms
step:747/5100 train_loss:3.8231 train_time:222197ms step_avg:301.49ms
step:748/5100 train_loss:3.8568 train_time:222392ms step_avg:301.34ms
step:749/5100 train_loss:3.7881 train_time:222586ms step_avg:301.20ms
step:750/5100 train_loss:3.7959 train_time:222781ms step_avg:301.06ms
step:750/5100 val_loss:3.7996 train_time:222814ms step_avg:301.10ms
step:751/5100 train_loss:3.8278 train_time:224031ms step_avg:302.34ms
step:752/5100 train_loss:3.7919 train_time:224235ms step_avg:302.20ms
step:753/5100 train_loss:3.8282 train_time:224431ms step_avg:302.06ms
step:754/5100 train_loss:3.8382 train_time:224626ms step_avg:301.92ms
step:755/5100 train_loss:3.8062 train_time:224819ms step_avg:301.77ms
step:756/5100 train_loss:3.8891 train_time:225154ms step_avg:301.81ms
step:757/5100 train_loss:3.7183 train_time:225349ms step_avg:301.67ms
step:758/5100 train_loss:3.9550 train_time:225543ms step_avg:301.53ms
step:759/5100 train_loss:3.8737 train_time:225737ms step_avg:301.38ms
step:760/5100 train_loss:3.8077 train_time:226094ms step_avg:301.46ms
step:761/5100 train_loss:3.9095 train_time:227326ms step_avg:302.70ms
step:762/5100 train_loss:3.6313 train_time:227528ms step_avg:302.56ms
step:763/5100 train_loss:3.7767 train_time:227722ms step_avg:302.42ms
step:764/5100 train_loss:3.8982 train_time:227918ms step_avg:302.28ms
step:765/5100 train_loss:3.5470 train_time:228114ms step_avg:302.14ms
step:766/5100 train_loss:3.9586 train_time:228310ms step_avg:302.00ms
step:767/5100 train_loss:3.8164 train_time:228506ms step_avg:301.86ms
step:768/5100 train_loss:3.7786 train_time:228700ms step_avg:301.71ms
step:769/5100 train_loss:3.8026 train_time:228895ms step_avg:301.57ms
step:770/5100 train_loss:3.8162 train_time:229090ms step_avg:301.43ms
step:771/5100 train_loss:3.8841 train_time:230321ms step_avg:302.66ms
step:772/5100 train_loss:4.1025 train_time:230522ms step_avg:302.52ms
step:773/5100 train_loss:3.6815 train_time:230718ms step_avg:302.38ms
step:774/5100 train_loss:3.8745 train_time:230915ms step_avg:302.24ms
step:775/5100 train_loss:3.8575 train_time:231110ms step_avg:302.11ms
step:776/5100 train_loss:3.8286 train_time:231305ms step_avg:301.97ms
step:777/5100 train_loss:3.6354 train_time:231500ms step_avg:301.83ms
step:778/5100 train_loss:3.6254 train_time:231695ms step_avg:301.69ms
step:779/5100 train_loss:3.6962 train_time:231890ms step_avg:301.55ms
step:780/5100 train_loss:3.7916 train_time:232086ms step_avg:301.41ms
step:781/5100 train_loss:3.8248 train_time:233316ms step_avg:302.62ms
step:782/5100 train_loss:3.8805 train_time:233519ms step_avg:302.49ms
step:783/5100 train_loss:3.7894 train_time:233715ms step_avg:302.35ms
step:784/5100 train_loss:3.7985 train_time:233911ms step_avg:302.21ms
step:785/5100 train_loss:3.7960 train_time:234107ms step_avg:302.07ms
step:786/5100 train_loss:3.7773 train_time:234301ms step_avg:301.93ms
step:787/5100 train_loss:3.6765 train_time:234498ms step_avg:301.80ms
step:788/5100 train_loss:3.9774 train_time:234693ms step_avg:301.66ms
step:789/5100 train_loss:3.7201 train_time:234888ms step_avg:301.52ms
step:790/5100 train_loss:3.7851 train_time:235083ms step_avg:301.39ms
step:791/5100 train_loss:3.8511 train_time:236314ms step_avg:302.58ms
step:792/5100 train_loss:3.9891 train_time:236515ms step_avg:302.45ms
step:793/5100 train_loss:3.9896 train_time:236711ms step_avg:302.31ms
step:794/5100 train_loss:3.7042 train_time:236906ms step_avg:302.18ms
step:795/5100 train_loss:3.8240 train_time:237100ms step_avg:302.04ms
step:796/5100 train_loss:3.8720 train_time:237296ms step_avg:301.90ms
step:797/5100 train_loss:3.9841 train_time:237491ms step_avg:301.77ms
step:798/5100 train_loss:3.7302 train_time:237685ms step_avg:301.63ms
step:799/5100 train_loss:3.8783 train_time:237880ms step_avg:301.50ms
step:800/5100 train_loss:3.7820 train_time:238075ms step_avg:301.36ms
step:801/5100 train_loss:3.7658 train_time:239306ms step_avg:302.54ms
step:802/5100 train_loss:3.8657 train_time:239509ms step_avg:302.41ms
step:803/5100 train_loss:3.7155 train_time:239704ms step_avg:302.28ms
step:804/5100 train_loss:3.7520 train_time:239899ms step_avg:302.14ms
step:805/5100 train_loss:3.8562 train_time:240094ms step_avg:302.01ms
step:806/5100 train_loss:3.7536 train_time:240289ms step_avg:301.87ms
step:807/5100 train_loss:3.7650 train_time:240485ms step_avg:301.74ms
step:808/5100 train_loss:3.8662 train_time:240680ms step_avg:301.60ms
step:809/5100 train_loss:3.7805 train_time:240874ms step_avg:301.47ms
step:810/5100 train_loss:3.7068 train_time:241068ms step_avg:301.34ms
step:811/5100 train_loss:3.7880 train_time:242298ms step_avg:302.49ms
step:812/5100 train_loss:3.8215 train_time:242500ms step_avg:302.37ms
step:813/5100 train_loss:3.8117 train_time:242696ms step_avg:302.24ms
step:814/5100 train_loss:3.8455 train_time:242891ms step_avg:302.10ms
step:815/5100 train_loss:3.7930 train_time:243086ms step_avg:301.97ms
step:816/5100 train_loss:3.7835 train_time:243281ms step_avg:301.84ms
step:817/5100 train_loss:3.8785 train_time:243476ms step_avg:301.70ms
step:818/5100 train_loss:3.9802 train_time:243671ms step_avg:301.57ms
step:819/5100 train_loss:3.7431 train_time:243866ms step_avg:301.44ms
step:820/5100 train_loss:3.9434 train_time:244061ms step_avg:301.31ms
step:821/5100 train_loss:3.7345 train_time:245293ms step_avg:302.46ms
step:822/5100 train_loss:3.7634 train_time:245495ms step_avg:302.33ms
step:823/5100 train_loss:3.8857 train_time:245691ms step_avg:302.20ms
step:824/5100 train_loss:3.8085 train_time:245885ms step_avg:302.07ms
step:825/5100 train_loss:3.7294 train_time:246080ms step_avg:301.94ms
step:826/5100 train_loss:3.8312 train_time:246275ms step_avg:301.81ms
step:827/5100 train_loss:3.7174 train_time:246470ms step_avg:301.68ms
step:828/5100 train_loss:3.9462 train_time:246664ms step_avg:301.54ms
step:829/5100 train_loss:3.8417 train_time:246858ms step_avg:301.41ms
step:830/5100 train_loss:3.8988 train_time:247053ms step_avg:301.28ms
step:831/5100 train_loss:3.7469 train_time:248284ms step_avg:302.42ms
step:832/5100 train_loss:3.8066 train_time:248484ms step_avg:302.29ms
step:833/5100 train_loss:3.7304 train_time:248679ms step_avg:302.16ms
step:834/5100 train_loss:3.8600 train_time:248874ms step_avg:302.03ms
step:835/5100 train_loss:3.7048 train_time:249070ms step_avg:301.90ms
step:836/5100 train_loss:3.6772 train_time:249264ms step_avg:301.77ms
step:837/5100 train_loss:3.9497 train_time:249460ms step_avg:301.64ms
step:838/5100 train_loss:3.6380 train_time:249655ms step_avg:301.52ms
step:839/5100 train_loss:3.8074 train_time:249849ms step_avg:301.39ms
step:840/5100 train_loss:3.6441 train_time:250044ms step_avg:301.26ms
step:841/5100 train_loss:3.6937 train_time:251274ms step_avg:302.38ms
step:842/5100 train_loss:3.7778 train_time:251475ms step_avg:302.25ms
step:843/5100 train_loss:3.7986 train_time:251670ms step_avg:302.13ms
step:844/5100 train_loss:3.8001 train_time:251866ms step_avg:302.00ms
step:845/5100 train_loss:3.6462 train_time:252059ms step_avg:301.87ms
step:846/5100 train_loss:3.8818 train_time:252255ms step_avg:301.74ms
step:847/5100 train_loss:3.7441 train_time:252450ms step_avg:301.61ms
step:848/5100 train_loss:3.7074 train_time:252644ms step_avg:301.48ms
step:849/5100 train_loss:3.8452 train_time:252840ms step_avg:301.36ms
step:850/5100 train_loss:3.7106 train_time:253034ms step_avg:301.23ms
step:851/5100 train_loss:3.6635 train_time:254265ms step_avg:302.34ms
step:852/5100 train_loss:3.9680 train_time:254467ms step_avg:302.22ms
step:853/5100 train_loss:3.6740 train_time:254661ms step_avg:302.09ms
step:854/5100 train_loss:3.7803 train_time:254856ms step_avg:301.96ms
step:855/5100 train_loss:3.8593 train_time:255051ms step_avg:301.84ms
step:856/5100 train_loss:3.7503 train_time:255248ms step_avg:301.71ms
step:857/5100 train_loss:3.7625 train_time:255442ms step_avg:301.58ms
step:858/5100 train_loss:3.8147 train_time:255638ms step_avg:301.46ms
step:859/5100 train_loss:3.7144 train_time:255834ms step_avg:301.34ms
step:860/5100 train_loss:3.7800 train_time:256029ms step_avg:301.21ms
step:861/5100 train_loss:3.8154 train_time:257260ms step_avg:302.30ms
step:862/5100 train_loss:3.8584 train_time:257461ms step_avg:302.18ms
step:863/5100 train_loss:3.7999 train_time:257658ms step_avg:302.06ms
step:864/5100 train_loss:3.7861 train_time:257852ms step_avg:301.93ms
step:865/5100 train_loss:3.6235 train_time:258047ms step_avg:301.81ms
step:866/5100 train_loss:3.8035 train_time:258241ms step_avg:301.68ms
step:867/5100 train_loss:4.0878 train_time:258437ms step_avg:301.56ms
step:868/5100 train_loss:3.6649 train_time:258633ms step_avg:301.44ms
step:869/5100 train_loss:3.8534 train_time:258828ms step_avg:301.31ms
step:870/5100 train_loss:3.8318 train_time:259024ms step_avg:301.19ms
step:871/5100 train_loss:3.6671 train_time:260255ms step_avg:302.27ms
step:872/5100 train_loss:3.6562 train_time:260454ms step_avg:302.15ms
step:873/5100 train_loss:3.8846 train_time:260651ms step_avg:302.03ms
step:874/5100 train_loss:3.6687 train_time:260846ms step_avg:301.91ms
step:875/5100 train_loss:3.3873 train_time:261040ms step_avg:301.78ms
step:875/5100 val_loss:3.7432 train_time:261073ms step_avg:301.82ms
step:876/5100 train_loss:3.8605 train_time:261252ms step_avg:301.68ms
step:877/5100 train_loss:3.6704 train_time:261449ms step_avg:301.56ms
step:878/5100 train_loss:3.8410 train_time:261646ms step_avg:301.43ms
step:879/5100 train_loss:3.6912 train_time:261841ms step_avg:301.31ms
step:880/5100 train_loss:3.8816 train_time:262037ms step_avg:301.19ms
step:881/5100 train_loss:3.5339 train_time:263266ms step_avg:302.26ms
step:882/5100 train_loss:3.7187 train_time:263469ms step_avg:302.14ms
step:883/5100 train_loss:3.9023 train_time:263666ms step_avg:302.02ms
step:884/5100 train_loss:4.0638 train_time:263860ms step_avg:301.90ms
step:885/5100 train_loss:3.7883 train_time:264056ms step_avg:301.78ms
step:886/5100 train_loss:3.7005 train_time:264249ms step_avg:301.65ms
step:887/5100 train_loss:3.8011 train_time:264445ms step_avg:301.53ms
step:888/5100 train_loss:4.2986 train_time:264641ms step_avg:301.41ms
step:889/5100 train_loss:4.0498 train_time:264836ms step_avg:301.29ms
step:890/5100 train_loss:3.7396 train_time:265030ms step_avg:301.17ms
step:891/5100 train_loss:3.7563 train_time:266261ms step_avg:302.23ms
step:892/5100 train_loss:3.5809 train_time:266462ms step_avg:302.11ms
step:893/5100 train_loss:3.9208 train_time:266657ms step_avg:301.99ms
step:894/5100 train_loss:3.6477 train_time:266851ms step_avg:301.87ms
step:895/5100 train_loss:3.8891 train_time:267046ms step_avg:301.75ms
step:896/5100 train_loss:3.9093 train_time:267242ms step_avg:301.63ms
step:897/5100 train_loss:3.7161 train_time:267438ms step_avg:301.51ms
step:898/5100 train_loss:3.7471 train_time:267632ms step_avg:301.39ms
step:899/5100 train_loss:3.8011 train_time:267828ms step_avg:301.27ms
step:900/5100 train_loss:3.6916 train_time:268024ms step_avg:301.15ms
step:901/5100 train_loss:3.6358 train_time:269255ms step_avg:302.19ms
step:902/5100 train_loss:3.8438 train_time:269454ms step_avg:302.08ms
step:903/5100 train_loss:3.8535 train_time:269649ms step_avg:301.96ms
step:904/5100 train_loss:3.7519 train_time:269845ms step_avg:301.84ms
step:905/5100 train_loss:3.7196 train_time:270041ms step_avg:301.72ms
step:906/5100 train_loss:3.7172 train_time:270237ms step_avg:301.60ms
step:907/5100 train_loss:3.9422 train_time:270431ms step_avg:301.48ms
step:908/5100 train_loss:3.7331 train_time:270626ms step_avg:301.37ms
step:909/5100 train_loss:3.7749 train_time:270821ms step_avg:301.25ms
step:910/5100 train_loss:3.6733 train_time:271016ms step_avg:301.13ms
step:911/5100 train_loss:3.7672 train_time:272247ms step_avg:302.16ms
step:912/5100 train_loss:3.8402 train_time:272447ms step_avg:302.05ms
step:913/5100 train_loss:3.8298 train_time:272643ms step_avg:301.93ms
step:914/5100 train_loss:3.7019 train_time:272838ms step_avg:301.81ms
step:915/5100 train_loss:3.9532 train_time:273033ms step_avg:301.69ms
step:916/5100 train_loss:3.7497 train_time:273228ms step_avg:301.58ms
step:917/5100 train_loss:3.8469 train_time:273424ms step_avg:301.46ms
step:918/5100 train_loss:3.8188 train_time:273620ms step_avg:301.34ms
step:919/5100 train_loss:5.0321 train_time:273815ms step_avg:301.23ms
step:920/5100 train_loss:3.7422 train_time:274009ms step_avg:301.11ms
step:921/5100 train_loss:3.7825 train_time:275242ms step_avg:302.13ms
step:922/5100 train_loss:3.7514 train_time:275443ms step_avg:302.02ms
step:923/5100 train_loss:3.8060 train_time:275639ms step_avg:301.90ms
step:924/5100 train_loss:3.8149 train_time:275833ms step_avg:301.79ms
step:925/5100 train_loss:3.8985 train_time:276028ms step_avg:301.67ms
step:926/5100 train_loss:3.8737 train_time:276223ms step_avg:301.55ms
step:927/5100 train_loss:3.7744 train_time:276419ms step_avg:301.44ms
step:928/5100 train_loss:3.7635 train_time:276614ms step_avg:301.32ms
step:929/5100 train_loss:3.9875 train_time:276808ms step_avg:301.21ms
step:930/5100 train_loss:3.8362 train_time:277003ms step_avg:301.09ms
step:931/5100 train_loss:3.6141 train_time:278234ms step_avg:302.10ms
step:932/5100 train_loss:3.7102 train_time:278435ms step_avg:301.99ms
step:933/5100 train_loss:3.8873 train_time:278630ms step_avg:301.87ms
step:934/5100 train_loss:3.6174 train_time:278825ms step_avg:301.76ms
step:935/5100 train_loss:3.7933 train_time:279020ms step_avg:301.64ms
step:936/5100 train_loss:3.6728 train_time:279215ms step_avg:301.53ms
step:937/5100 train_loss:3.7309 train_time:279409ms step_avg:301.41ms
step:938/5100 train_loss:3.8270 train_time:279605ms step_avg:301.30ms
step:939/5100 train_loss:3.7551 train_time:279801ms step_avg:301.18ms
step:940/5100 train_loss:3.9086 train_time:279996ms step_avg:301.07ms
step:941/5100 train_loss:3.7001 train_time:281226ms step_avg:302.07ms
step:942/5100 train_loss:3.7657 train_time:281426ms step_avg:301.96ms
step:943/5100 train_loss:3.5646 train_time:281623ms step_avg:301.85ms
step:944/5100 train_loss:3.9166 train_time:281819ms step_avg:301.73ms
step:945/5100 train_loss:3.6297 train_time:282150ms step_avg:301.76ms
step:946/5100 train_loss:3.6459 train_time:282344ms step_avg:301.65ms
step:947/5100 train_loss:5.2543 train_time:282540ms step_avg:301.54ms
step:948/5100 train_loss:3.8120 train_time:282735ms step_avg:301.42ms
step:949/5100 train_loss:3.7141 train_time:282931ms step_avg:301.31ms
step:950/5100 train_loss:3.6107 train_time:283285ms step_avg:301.37ms
step:951/5100 train_loss:3.6632 train_time:284514ms step_avg:302.35ms
step:952/5100 train_loss:3.6253 train_time:284713ms step_avg:302.24ms
step:953/5100 train_loss:3.6908 train_time:284908ms step_avg:302.13ms
step:954/5100 train_loss:3.7679 train_time:285103ms step_avg:302.02ms
step:955/5100 train_loss:3.6505 train_time:285299ms step_avg:301.90ms
step:956/5100 train_loss:3.6867 train_time:285493ms step_avg:301.79ms
step:957/5100 train_loss:3.6565 train_time:285687ms step_avg:301.68ms
step:958/5100 train_loss:3.7205 train_time:285883ms step_avg:301.56ms
step:959/5100 train_loss:3.7127 train_time:286080ms step_avg:301.45ms
step:960/5100 train_loss:3.7205 train_time:286274ms step_avg:301.34ms
step:961/5100 train_loss:3.6095 train_time:287504ms step_avg:302.32ms
step:962/5100 train_loss:3.8664 train_time:287706ms step_avg:302.21ms
step:963/5100 train_loss:3.8220 train_time:287902ms step_avg:302.10ms
step:964/5100 train_loss:3.9216 train_time:288096ms step_avg:301.99ms
step:965/5100 train_loss:3.6772 train_time:288291ms step_avg:301.88ms
step:966/5100 train_loss:3.7107 train_time:288487ms step_avg:301.76ms
step:967/5100 train_loss:3.9294 train_time:288682ms step_avg:301.65ms
step:968/5100 train_loss:3.7564 train_time:288878ms step_avg:301.54ms
step:969/5100 train_loss:3.7400 train_time:289073ms step_avg:301.43ms
step:970/5100 train_loss:3.7931 train_time:289268ms step_avg:301.32ms
step:971/5100 train_loss:3.6074 train_time:290499ms step_avg:302.29ms
step:972/5100 train_loss:3.7632 train_time:290701ms step_avg:302.18ms
step:973/5100 train_loss:3.7208 train_time:290896ms step_avg:302.07ms
step:974/5100 train_loss:3.7595 train_time:291090ms step_avg:301.96ms
step:975/5100 train_loss:3.8203 train_time:291286ms step_avg:301.85ms
step:976/5100 train_loss:3.7022 train_time:291481ms step_avg:301.74ms
step:977/5100 train_loss:3.8993 train_time:291676ms step_avg:301.63ms
step:978/5100 train_loss:3.7872 train_time:291871ms step_avg:301.52ms
step:979/5100 train_loss:3.6177 train_time:292066ms step_avg:301.41ms
step:980/5100 train_loss:3.9038 train_time:292262ms step_avg:301.30ms
step:981/5100 train_loss:3.6345 train_time:293493ms step_avg:302.26ms
step:982/5100 train_loss:3.7944 train_time:293694ms step_avg:302.15ms
step:983/5100 train_loss:3.7758 train_time:293889ms step_avg:302.04ms
step:984/5100 train_loss:3.7827 train_time:294085ms step_avg:301.94ms
step:985/5100 train_loss:3.7182 train_time:294279ms step_avg:301.82ms
step:986/5100 train_loss:3.8035 train_time:294473ms step_avg:301.71ms
step:987/5100 train_loss:3.6320 train_time:294668ms step_avg:301.61ms
step:988/5100 train_loss:3.7041 train_time:294864ms step_avg:301.50ms
step:989/5100 train_loss:3.7093 train_time:295059ms step_avg:301.39ms
step:990/5100 train_loss:3.6443 train_time:295253ms step_avg:301.28ms
step:991/5100 train_loss:3.8525 train_time:296484ms step_avg:302.23ms
step:992/5100 train_loss:3.6858 train_time:296684ms step_avg:302.12ms
step:993/5100 train_loss:3.6578 train_time:296880ms step_avg:302.01ms
step:994/5100 train_loss:3.7296 train_time:297075ms step_avg:301.91ms
step:995/5100 train_loss:3.8060 train_time:297270ms step_avg:301.80ms
step:996/5100 train_loss:3.7575 train_time:297465ms step_avg:301.69ms
step:997/5100 train_loss:3.6676 train_time:297660ms step_avg:301.58ms
step:998/5100 train_loss:4.0264 train_time:297855ms step_avg:301.47ms
step:999/5100 train_loss:3.6831 train_time:298048ms step_avg:301.36ms
step:1000/5100 train_loss:3.8030 train_time:298244ms step_avg:301.26ms
step:1000/5100 val_loss:3.6995 train_time:298277ms step_avg:301.29ms
step:1001/5100 train_loss:3.6782 train_time:299496ms step_avg:302.22ms
step:1002/5100 train_loss:3.7272 train_time:299695ms step_avg:302.11ms
step:1003/5100 train_loss:3.6051 train_time:299889ms step_avg:302.00ms
step:1004/5100 train_loss:3.7886 train_time:300083ms step_avg:301.89ms
step:1005/5100 train_loss:3.8424 train_time:300277ms step_avg:301.79ms
step:1006/5100 train_loss:3.6140 train_time:300473ms step_avg:301.68ms
step:1007/5100 train_loss:3.6956 train_time:300669ms step_avg:301.57ms
step:1008/5100 train_loss:3.6590 train_time:300862ms step_avg:301.47ms
step:1009/5100 train_loss:3.7850 train_time:301058ms step_avg:301.36ms
step:1010/5100 train_loss:3.8880 train_time:301254ms step_avg:301.25ms
step:1011/5100 train_loss:3.7788 train_time:302485ms step_avg:302.18ms
step:1012/5100 train_loss:3.7476 train_time:302689ms step_avg:302.08ms
step:1013/5100 train_loss:3.6007 train_time:302884ms step_avg:301.98ms
step:1014/5100 train_loss:3.7522 train_time:303078ms step_avg:301.87ms
step:1015/5100 train_loss:3.8579 train_time:303273ms step_avg:301.76ms
step:1016/5100 train_loss:3.5672 train_time:303470ms step_avg:301.66ms
step:1017/5100 train_loss:3.6668 train_time:303664ms step_avg:301.55ms
step:1018/5100 train_loss:3.6671 train_time:303858ms step_avg:301.45ms
step:1019/5100 train_loss:3.6088 train_time:304053ms step_avg:301.34ms
step:1020/5100 train_loss:3.7537 train_time:304248ms step_avg:301.24ms
step:1021/5100 train_loss:3.6576 train_time:305479ms step_avg:302.16ms
step:1022/5100 train_loss:3.5964 train_time:305679ms step_avg:302.05ms
step:1023/5100 train_loss:3.7049 train_time:305874ms step_avg:301.95ms
step:1024/5100 train_loss:3.7309 train_time:306070ms step_avg:301.84ms
step:1025/5100 train_loss:3.7015 train_time:306266ms step_avg:301.74ms
step:1026/5100 train_loss:3.7163 train_time:306459ms step_avg:301.63ms
step:1027/5100 train_loss:3.8848 train_time:306655ms step_avg:301.53ms
step:1028/5100 train_loss:3.5592 train_time:306851ms step_avg:301.43ms
step:1029/5100 train_loss:3.6237 train_time:307047ms step_avg:301.32ms
step:1030/5100 train_loss:3.5787 train_time:307240ms step_avg:301.22ms
step:1031/5100 train_loss:3.7403 train_time:308471ms step_avg:302.13ms
step:1032/5100 train_loss:3.7368 train_time:308671ms step_avg:302.03ms
step:1033/5100 train_loss:3.9117 train_time:308867ms step_avg:301.92ms
step:1034/5100 train_loss:3.7239 train_time:309062ms step_avg:301.82ms
step:1035/5100 train_loss:3.6477 train_time:309257ms step_avg:301.71ms
step:1036/5100 train_loss:3.6579 train_time:309452ms step_avg:301.61ms
step:1037/5100 train_loss:3.7266 train_time:309649ms step_avg:301.51ms
step:1038/5100 train_loss:4.0350 train_time:309844ms step_avg:301.40ms
step:1039/5100 train_loss:3.8530 train_time:310038ms step_avg:301.30ms
step:1040/5100 train_loss:3.7504 train_time:310233ms step_avg:301.20ms
step:1041/5100 train_loss:3.6445 train_time:311464ms step_avg:302.10ms
step:1042/5100 train_loss:3.7116 train_time:311666ms step_avg:302.00ms
step:1043/5100 train_loss:3.7554 train_time:311860ms step_avg:301.90ms
step:1044/5100 train_loss:3.6784 train_time:312055ms step_avg:301.79ms
step:1045/5100 train_loss:3.6828 train_time:312250ms step_avg:301.69ms
step:1046/5100 train_loss:3.7667 train_time:312444ms step_avg:301.59ms
step:1047/5100 train_loss:3.6698 train_time:312638ms step_avg:301.48ms
step:1048/5100 train_loss:3.8798 train_time:312835ms step_avg:301.38ms
step:1049/5100 train_loss:3.7280 train_time:313030ms step_avg:301.28ms
step:1050/5100 train_loss:3.6524 train_time:313225ms step_avg:301.18ms
step:1051/5100 train_loss:3.6204 train_time:314456ms step_avg:302.07ms
step:1052/5100 train_loss:3.7444 train_time:314658ms step_avg:301.98ms
step:1053/5100 train_loss:3.6189 train_time:314853ms step_avg:301.87ms
step:1054/5100 train_loss:3.9355 train_time:315048ms step_avg:301.77ms
step:1055/5100 train_loss:3.7722 train_time:315243ms step_avg:301.67ms
step:1056/5100 train_loss:3.6301 train_time:315437ms step_avg:301.57ms
step:1057/5100 train_loss:3.7432 train_time:315633ms step_avg:301.46ms
step:1058/5100 train_loss:3.8072 train_time:315828ms step_avg:301.36ms
step:1059/5100 train_loss:3.5318 train_time:316022ms step_avg:301.26ms
step:1060/5100 train_loss:3.6570 train_time:316217ms step_avg:301.16ms
step:1061/5100 train_loss:3.6878 train_time:317450ms step_avg:302.05ms
step:1062/5100 train_loss:3.6498 train_time:317651ms step_avg:301.95ms
step:1063/5100 train_loss:3.6244 train_time:317846ms step_avg:301.85ms
step:1064/5100 train_loss:3.7251 train_time:318040ms step_avg:301.75ms
step:1065/5100 train_loss:3.6263 train_time:318236ms step_avg:301.65ms
step:1066/5100 train_loss:3.6070 train_time:318432ms step_avg:301.55ms
step:1067/5100 train_loss:3.6290 train_time:318626ms step_avg:301.44ms
step:1068/5100 train_loss:3.5441 train_time:318821ms step_avg:301.34ms
step:1069/5100 train_loss:3.6592 train_time:319016ms step_avg:301.24ms
step:1070/5100 train_loss:3.5279 train_time:319211ms step_avg:301.14ms
step:1071/5100 train_loss:3.7936 train_time:320441ms step_avg:302.02ms
step:1072/5100 train_loss:3.7418 train_time:320642ms step_avg:301.92ms
step:1073/5100 train_loss:3.6897 train_time:320837ms step_avg:301.82ms
step:1074/5100 train_loss:3.7570 train_time:321032ms step_avg:301.72ms
step:1075/5100 train_loss:3.6985 train_time:321227ms step_avg:301.62ms
step:1076/5100 train_loss:3.6322 train_time:321421ms step_avg:301.52ms
step:1077/5100 train_loss:4.0285 train_time:321616ms step_avg:301.42ms
step:1078/5100 train_loss:3.7099 train_time:321812ms step_avg:301.32ms
step:1079/5100 train_loss:3.3716 train_time:322007ms step_avg:301.22ms
step:1080/5100 train_loss:3.7684 train_time:322202ms step_avg:301.12ms
step:1081/5100 train_loss:3.6896 train_time:323433ms step_avg:301.99ms
step:1082/5100 train_loss:3.7527 train_time:323636ms step_avg:301.90ms
step:1083/5100 train_loss:3.8490 train_time:323832ms step_avg:301.80ms
step:1084/5100 train_loss:3.7463 train_time:324026ms step_avg:301.70ms
step:1085/5100 train_loss:3.7174 train_time:324220ms step_avg:301.60ms
step:1086/5100 train_loss:3.6817 train_time:324416ms step_avg:301.50ms
step:1087/5100 train_loss:3.8821 train_time:324611ms step_avg:301.40ms
step:1088/5100 train_loss:3.7761 train_time:324805ms step_avg:301.30ms
step:1089/5100 train_loss:3.5997 train_time:324999ms step_avg:301.20ms
step:1090/5100 train_loss:3.6225 train_time:325194ms step_avg:301.11ms
step:1091/5100 train_loss:3.7441 train_time:326425ms step_avg:301.97ms
step:1092/5100 train_loss:3.5434 train_time:326628ms step_avg:301.87ms
step:1093/5100 train_loss:3.7333 train_time:326824ms step_avg:301.78ms
step:1094/5100 train_loss:3.8636 train_time:327017ms step_avg:301.68ms
step:1095/5100 train_loss:3.7116 train_time:327212ms step_avg:301.58ms
step:1096/5100 train_loss:3.6580 train_time:327408ms step_avg:301.48ms
step:1097/5100 train_loss:3.6866 train_time:327602ms step_avg:301.38ms
step:1098/5100 train_loss:3.7273 train_time:327796ms step_avg:301.28ms
step:1099/5100 train_loss:3.7987 train_time:327992ms step_avg:301.19ms
step:1100/5100 train_loss:3.7607 train_time:328186ms step_avg:301.09ms
step:1101/5100 train_loss:3.6963 train_time:329415ms step_avg:301.94ms
step:1102/5100 train_loss:3.5415 train_time:329617ms step_avg:301.85ms
step:1103/5100 train_loss:3.6141 train_time:329814ms step_avg:301.75ms
step:1104/5100 train_loss:3.6991 train_time:330007ms step_avg:301.65ms
step:1105/5100 train_loss:3.5693 train_time:330202ms step_avg:301.55ms
step:1106/5100 train_loss:4.3199 train_time:330397ms step_avg:301.46ms
step:1107/5100 train_loss:3.4777 train_time:330592ms step_avg:301.36ms
step:1108/5100 train_loss:3.8099 train_time:330787ms step_avg:301.26ms
step:1109/5100 train_loss:3.5966 train_time:330981ms step_avg:301.17ms
step:1110/5100 train_loss:3.7458 train_time:331177ms step_avg:301.07ms
step:1111/5100 train_loss:3.6831 train_time:332407ms step_avg:301.91ms
step:1112/5100 train_loss:3.7269 train_time:332610ms step_avg:301.82ms
step:1113/5100 train_loss:3.8192 train_time:332805ms step_avg:301.73ms
step:1114/5100 train_loss:3.6821 train_time:332999ms step_avg:301.63ms
step:1115/5100 train_loss:3.6099 train_time:333193ms step_avg:301.53ms
step:1116/5100 train_loss:3.5256 train_time:333389ms step_avg:301.44ms
step:1117/5100 train_loss:3.6839 train_time:333584ms step_avg:301.34ms
step:1118/5100 train_loss:3.8444 train_time:333778ms step_avg:301.24ms
step:1119/5100 train_loss:3.8733 train_time:333973ms step_avg:301.15ms
step:1120/5100 train_loss:3.7127 train_time:334169ms step_avg:301.05ms
step:1121/5100 train_loss:3.7484 train_time:335399ms step_avg:301.89ms
step:1122/5100 train_loss:3.6453 train_time:335600ms step_avg:301.80ms
step:1123/5100 train_loss:3.6997 train_time:335795ms step_avg:301.70ms
step:1124/5100 train_loss:3.8465 train_time:335989ms step_avg:301.61ms
step:1125/5100 train_loss:3.6108 train_time:336184ms step_avg:301.51ms
step:1125/5100 val_loss:3.6711 train_time:336216ms step_avg:301.54ms
step:1126/5100 train_loss:3.5115 train_time:336395ms step_avg:301.43ms
step:1127/5100 train_loss:3.7371 train_time:336590ms step_avg:301.33ms
step:1128/5100 train_loss:3.9463 train_time:336786ms step_avg:301.24ms
step:1129/5100 train_loss:3.4881 train_time:336982ms step_avg:301.15ms
step:1130/5100 train_loss:3.8049 train_time:337177ms step_avg:301.05ms
step:1131/5100 train_loss:3.6415 train_time:338407ms step_avg:301.88ms
step:1132/5100 train_loss:3.6673 train_time:338607ms step_avg:301.79ms
step:1133/5100 train_loss:3.6222 train_time:338803ms step_avg:301.69ms
step:1134/5100 train_loss:3.7878 train_time:339132ms step_avg:301.72ms
step:1135/5100 train_loss:3.7169 train_time:339326ms step_avg:301.62ms
step:1136/5100 train_loss:3.7615 train_time:339520ms step_avg:301.53ms
step:1137/5100 train_loss:3.7982 train_time:339715ms step_avg:301.43ms
step:1138/5100 train_loss:3.7088 train_time:339909ms step_avg:301.34ms
step:1139/5100 train_loss:3.6143 train_time:340105ms step_avg:301.24ms
step:1140/5100 train_loss:3.9158 train_time:340461ms step_avg:301.29ms
step:1141/5100 train_loss:3.7264 train_time:341692ms step_avg:302.11ms
step:1142/5100 train_loss:3.8211 train_time:341892ms step_avg:302.02ms
step:1143/5100 train_loss:3.7075 train_time:342086ms step_avg:301.93ms
step:1144/5100 train_loss:3.6204 train_time:342282ms step_avg:301.84ms
step:1145/5100 train_loss:3.7246 train_time:342477ms step_avg:301.74ms
step:1146/5100 train_loss:3.8499 train_time:342670ms step_avg:301.65ms
step:1147/5100 train_loss:3.8134 train_time:342865ms step_avg:301.55ms
step:1148/5100 train_loss:3.7490 train_time:343060ms step_avg:301.46ms
step:1149/5100 train_loss:3.7545 train_time:343256ms step_avg:301.37ms
step:1150/5100 train_loss:3.6075 train_time:343450ms step_avg:301.27ms
step:1151/5100 train_loss:3.6226 train_time:344681ms step_avg:302.09ms
step:1152/5100 train_loss:3.5930 train_time:344884ms step_avg:302.00ms
step:1153/5100 train_loss:3.7441 train_time:345078ms step_avg:301.91ms
step:1154/5100 train_loss:3.6955 train_time:345273ms step_avg:301.81ms
step:1155/5100 train_loss:3.7721 train_time:345467ms step_avg:301.72ms
step:1156/5100 train_loss:3.6235 train_time:345663ms step_avg:301.63ms
step:1157/5100 train_loss:3.7922 train_time:345860ms step_avg:301.53ms
step:1158/5100 train_loss:3.7494 train_time:346054ms step_avg:301.44ms
step:1159/5100 train_loss:3.5633 train_time:346248ms step_avg:301.35ms
step:1160/5100 train_loss:3.5891 train_time:346444ms step_avg:301.26ms
step:1161/5100 train_loss:3.5849 train_time:347676ms step_avg:302.06ms
step:1162/5100 train_loss:3.3960 train_time:347878ms step_avg:301.98ms
step:1163/5100 train_loss:3.7003 train_time:348073ms step_avg:301.88ms
step:1164/5100 train_loss:3.6649 train_time:348267ms step_avg:301.79ms
step:1165/5100 train_loss:3.5377 train_time:348463ms step_avg:301.70ms
step:1166/5100 train_loss:3.5294 train_time:348659ms step_avg:301.61ms
step:1167/5100 train_loss:3.6390 train_time:348855ms step_avg:301.52ms
step:1168/5100 train_loss:3.6404 train_time:349049ms step_avg:301.42ms
step:1169/5100 train_loss:3.9639 train_time:349245ms step_avg:301.33ms
step:1170/5100 train_loss:3.6506 train_time:349441ms step_avg:301.24ms
step:1171/5100 train_loss:3.6536 train_time:350672ms step_avg:302.04ms
step:1172/5100 train_loss:3.5747 train_time:350873ms step_avg:301.96ms
step:1173/5100 train_loss:3.6638 train_time:351069ms step_avg:301.86ms
step:1174/5100 train_loss:3.8043 train_time:351264ms step_avg:301.77ms
step:1175/5100 train_loss:3.6478 train_time:351459ms step_avg:301.68ms
step:1176/5100 train_loss:3.6650 train_time:351654ms step_avg:301.59ms
step:1177/5100 train_loss:3.7130 train_time:351849ms step_avg:301.50ms
step:1178/5100 train_loss:3.7007 train_time:352044ms step_avg:301.41ms
step:1179/5100 train_loss:3.7518 train_time:352240ms step_avg:301.32ms
step:1180/5100 train_loss:3.6694 train_time:352434ms step_avg:301.23ms
step:1181/5100 train_loss:3.6750 train_time:353665ms step_avg:302.02ms
step:1182/5100 train_loss:3.6111 train_time:353866ms step_avg:301.93ms
step:1183/5100 train_loss:3.6827 train_time:354062ms step_avg:301.84ms
step:1184/5100 train_loss:3.5888 train_time:354258ms step_avg:301.75ms
step:1185/5100 train_loss:3.7599 train_time:354454ms step_avg:301.66ms
step:1186/5100 train_loss:3.8242 train_time:354648ms step_avg:301.57ms
step:1187/5100 train_loss:3.6125 train_time:354844ms step_avg:301.48ms
step:1188/5100 train_loss:3.6733 train_time:355038ms step_avg:301.39ms
step:1189/5100 train_loss:3.6973 train_time:355232ms step_avg:301.30ms
step:1190/5100 train_loss:3.5387 train_time:355427ms step_avg:301.21ms
step:1191/5100 train_loss:3.7188 train_time:356658ms step_avg:302.00ms
step:1192/5100 train_loss:3.8590 train_time:356860ms step_avg:301.91ms
step:1193/5100 train_loss:3.6548 train_time:357057ms step_avg:301.82ms
step:1194/5100 train_loss:3.5432 train_time:357250ms step_avg:301.73ms
step:1195/5100 train_loss:3.8376 train_time:357445ms step_avg:301.64ms
step:1196/5100 train_loss:3.6398 train_time:357640ms step_avg:301.55ms
step:1197/5100 train_loss:3.6443 train_time:357835ms step_avg:301.46ms
step:1198/5100 train_loss:3.5444 train_time:358029ms step_avg:301.37ms
step:1199/5100 train_loss:3.5576 train_time:358225ms step_avg:301.28ms
step:1200/5100 train_loss:3.6097 train_time:358419ms step_avg:301.19ms
step:1201/5100 train_loss:3.6925 train_time:359650ms step_avg:301.97ms
step:1202/5100 train_loss:3.7654 train_time:359851ms step_avg:301.89ms
step:1203/5100 train_loss:3.8422 train_time:360048ms step_avg:301.80ms
step:1204/5100 train_loss:3.6852 train_time:360242ms step_avg:301.71ms
step:1205/5100 train_loss:3.6007 train_time:360438ms step_avg:301.62ms
step:1206/5100 train_loss:3.6855 train_time:360631ms step_avg:301.53ms
step:1207/5100 train_loss:3.7396 train_time:360827ms step_avg:301.44ms
step:1208/5100 train_loss:3.7847 train_time:361022ms step_avg:301.35ms
step:1209/5100 train_loss:3.6689 train_time:361216ms step_avg:301.26ms
step:1210/5100 train_loss:3.5179 train_time:361411ms step_avg:301.18ms
step:1211/5100 train_loss:3.5726 train_time:362641ms step_avg:301.95ms
step:1212/5100 train_loss:3.6655 train_time:362844ms step_avg:301.87ms
step:1213/5100 train_loss:3.6799 train_time:363041ms step_avg:301.78ms
step:1214/5100 train_loss:3.7127 train_time:363236ms step_avg:301.69ms
step:1215/5100 train_loss:3.6048 train_time:363431ms step_avg:301.60ms
step:1216/5100 train_loss:3.6596 train_time:363626ms step_avg:301.51ms
step:1217/5100 train_loss:3.6039 train_time:363820ms step_avg:301.43ms
step:1218/5100 train_loss:3.5973 train_time:364015ms step_avg:301.34ms
step:1219/5100 train_loss:3.6980 train_time:364209ms step_avg:301.25ms
step:1220/5100 train_loss:3.5387 train_time:364404ms step_avg:301.16ms
step:1221/5100 train_loss:3.7619 train_time:365635ms step_avg:301.93ms
step:1222/5100 train_loss:3.7899 train_time:365836ms step_avg:301.85ms
step:1223/5100 train_loss:3.7236 train_time:366030ms step_avg:301.76ms
step:1224/5100 train_loss:3.5605 train_time:366226ms step_avg:301.67ms
step:1225/5100 train_loss:3.5608 train_time:366421ms step_avg:301.58ms
step:1226/5100 train_loss:3.6335 train_time:366615ms step_avg:301.49ms
step:1227/5100 train_loss:3.6189 train_time:366809ms step_avg:301.40ms
step:1228/5100 train_loss:3.5505 train_time:367005ms step_avg:301.32ms
step:1229/5100 train_loss:3.7275 train_time:367201ms step_avg:301.23ms
step:1230/5100 train_loss:3.6432 train_time:367396ms step_avg:301.14ms
step:1231/5100 train_loss:3.7088 train_time:368627ms step_avg:301.91ms
step:1232/5100 train_loss:3.8645 train_time:368828ms step_avg:301.82ms
step:1233/5100 train_loss:3.7636 train_time:369024ms step_avg:301.74ms
step:1234/5100 train_loss:3.6968 train_time:369219ms step_avg:301.65ms
step:1235/5100 train_loss:3.8489 train_time:369414ms step_avg:301.56ms
step:1236/5100 train_loss:3.6137 train_time:369608ms step_avg:301.47ms
step:1237/5100 train_loss:3.5824 train_time:369803ms step_avg:301.39ms
step:1238/5100 train_loss:3.5301 train_time:369999ms step_avg:301.30ms
step:1239/5100 train_loss:3.6054 train_time:370194ms step_avg:301.22ms
step:1240/5100 train_loss:3.6075 train_time:370389ms step_avg:301.13ms
step:1241/5100 train_loss:3.6564 train_time:371621ms step_avg:301.89ms
step:1242/5100 train_loss:3.7003 train_time:371822ms step_avg:301.80ms
step:1243/5100 train_loss:3.5781 train_time:372017ms step_avg:301.72ms
step:1244/5100 train_loss:3.6718 train_time:372211ms step_avg:301.63ms
step:1245/5100 train_loss:3.6921 train_time:372406ms step_avg:301.54ms
step:1246/5100 train_loss:3.6887 train_time:372601ms step_avg:301.46ms
step:1247/5100 train_loss:3.5170 train_time:372797ms step_avg:301.37ms
step:1248/5100 train_loss:3.6600 train_time:372991ms step_avg:301.28ms
step:1249/5100 train_loss:3.7263 train_time:373186ms step_avg:301.20ms
step:1250/5100 train_loss:3.6819 train_time:373380ms step_avg:301.11ms
step:1250/5100 val_loss:3.6409 train_time:373412ms step_avg:301.14ms
step:1251/5100 train_loss:3.5861 train_time:374626ms step_avg:301.87ms
step:1252/5100 train_loss:3.7954 train_time:374830ms step_avg:301.80ms
step:1253/5100 train_loss:3.6604 train_time:375025ms step_avg:301.71ms
step:1254/5100 train_loss:3.5815 train_time:375219ms step_avg:301.62ms
step:1255/5100 train_loss:3.7183 train_time:375415ms step_avg:301.54ms
step:1256/5100 train_loss:3.7899 train_time:375609ms step_avg:301.45ms
step:1257/5100 train_loss:3.5934 train_time:375802ms step_avg:301.36ms
step:1258/5100 train_loss:3.6194 train_time:375997ms step_avg:301.28ms
step:1259/5100 train_loss:3.6491 train_time:376192ms step_avg:301.19ms
step:1260/5100 train_loss:3.6229 train_time:376387ms step_avg:301.11ms
step:1261/5100 train_loss:3.4809 train_time:377617ms step_avg:301.85ms
step:1262/5100 train_loss:3.5799 train_time:377817ms step_avg:301.77ms
step:1263/5100 train_loss:3.6480 train_time:378013ms step_avg:301.69ms
step:1264/5100 train_loss:3.5000 train_time:378209ms step_avg:301.60ms
step:1265/5100 train_loss:3.7166 train_time:378403ms step_avg:301.52ms
step:1266/5100 train_loss:3.7045 train_time:378598ms step_avg:301.43ms
step:1267/5100 train_loss:3.7101 train_time:378793ms step_avg:301.35ms
step:1268/5100 train_loss:3.6511 train_time:378987ms step_avg:301.26ms
step:1269/5100 train_loss:3.6870 train_time:379181ms step_avg:301.18ms
step:1270/5100 train_loss:3.5446 train_time:379377ms step_avg:301.09ms
step:1271/5100 train_loss:3.3895 train_time:380609ms step_avg:301.83ms
step:1272/5100 train_loss:3.6694 train_time:380812ms step_avg:301.75ms
step:1273/5100 train_loss:3.6306 train_time:381007ms step_avg:301.67ms
step:1274/5100 train_loss:3.6848 train_time:381201ms step_avg:301.58ms
step:1275/5100 train_loss:3.6282 train_time:381396ms step_avg:301.50ms
step:1276/5100 train_loss:3.7266 train_time:381591ms step_avg:301.41ms
step:1277/5100 train_loss:3.7535 train_time:381786ms step_avg:301.33ms
step:1278/5100 train_loss:3.7067 train_time:381979ms step_avg:301.25ms
step:1279/5100 train_loss:3.6949 train_time:382176ms step_avg:301.16ms
step:1280/5100 train_loss:3.5322 train_time:382370ms step_avg:301.08ms
step:1281/5100 train_loss:3.6543 train_time:383601ms step_avg:301.81ms
step:1282/5100 train_loss:3.7132 train_time:383803ms step_avg:301.73ms
step:1283/5100 train_loss:3.7463 train_time:383998ms step_avg:301.65ms
step:1284/5100 train_loss:3.6289 train_time:384192ms step_avg:301.56ms
step:1285/5100 train_loss:3.6618 train_time:384387ms step_avg:301.48ms
step:1286/5100 train_loss:3.6468 train_time:384581ms step_avg:301.40ms
step:1287/5100 train_loss:3.6180 train_time:384775ms step_avg:301.31ms
step:1288/5100 train_loss:3.7513 train_time:384970ms step_avg:301.23ms
step:1289/5100 train_loss:3.5936 train_time:385165ms step_avg:301.15ms
step:1290/5100 train_loss:3.6727 train_time:385359ms step_avg:301.06ms
step:1291/5100 train_loss:3.7442 train_time:386591ms step_avg:301.79ms
step:1292/5100 train_loss:3.6694 train_time:386792ms step_avg:301.71ms
step:1293/5100 train_loss:3.7685 train_time:386987ms step_avg:301.63ms
step:1294/5100 train_loss:3.7926 train_time:387181ms step_avg:301.54ms
step:1295/5100 train_loss:3.7610 train_time:387377ms step_avg:301.46ms
step:1296/5100 train_loss:3.5712 train_time:387572ms step_avg:301.38ms
step:1297/5100 train_loss:3.6413 train_time:387767ms step_avg:301.30ms
step:1298/5100 train_loss:3.5470 train_time:387961ms step_avg:301.21ms
step:1299/5100 train_loss:3.6133 train_time:388157ms step_avg:301.13ms
step:1300/5100 train_loss:3.6803 train_time:388351ms step_avg:301.05ms
step:1301/5100 train_loss:3.6918 train_time:389582ms step_avg:301.77ms
step:1302/5100 train_loss:3.6978 train_time:389783ms step_avg:301.69ms
step:1303/5100 train_loss:3.8478 train_time:389977ms step_avg:301.61ms
step:1304/5100 train_loss:3.6206 train_time:390173ms step_avg:301.52ms
step:1305/5100 train_loss:3.8421 train_time:390367ms step_avg:301.44ms
step:1306/5100 train_loss:3.5604 train_time:390561ms step_avg:301.36ms
step:1307/5100 train_loss:3.7408 train_time:390757ms step_avg:301.28ms
step:1308/5100 train_loss:3.7455 train_time:390953ms step_avg:301.20ms
step:1309/5100 train_loss:3.6081 train_time:391149ms step_avg:301.12ms
step:1310/5100 train_loss:3.5788 train_time:391345ms step_avg:301.03ms
step:1311/5100 train_loss:3.6072 train_time:392576ms step_avg:301.75ms
step:1312/5100 train_loss:3.5693 train_time:392777ms step_avg:301.67ms
step:1313/5100 train_loss:3.6943 train_time:392973ms step_avg:301.59ms
step:1314/5100 train_loss:3.6361 train_time:393168ms step_avg:301.51ms
step:1315/5100 train_loss:3.3527 train_time:393362ms step_avg:301.43ms
step:1316/5100 train_loss:3.5913 train_time:393558ms step_avg:301.35ms
step:1317/5100 train_loss:3.6633 train_time:393754ms step_avg:301.27ms
step:1318/5100 train_loss:3.6914 train_time:393948ms step_avg:301.18ms
step:1319/5100 train_loss:3.5605 train_time:394143ms step_avg:301.10ms
step:1320/5100 train_loss:3.7106 train_time:394338ms step_avg:301.02ms
step:1321/5100 train_loss:3.7598 train_time:395569ms step_avg:301.73ms
step:1322/5100 train_loss:3.6469 train_time:395770ms step_avg:301.65ms
step:1323/5100 train_loss:3.5909 train_time:396100ms step_avg:301.68ms
step:1324/5100 train_loss:3.6244 train_time:396296ms step_avg:301.59ms
step:1325/5100 train_loss:3.7201 train_time:396490ms step_avg:301.51ms
step:1326/5100 train_loss:3.7753 train_time:396685ms step_avg:301.43ms
step:1327/5100 train_loss:3.5399 train_time:396879ms step_avg:301.35ms
step:1328/5100 train_loss:3.4567 train_time:397074ms step_avg:301.27ms
step:1329/5100 train_loss:3.7651 train_time:397269ms step_avg:301.19ms
step:1330/5100 train_loss:3.6171 train_time:397627ms step_avg:301.23ms
step:1331/5100 train_loss:3.7411 train_time:398856ms step_avg:301.93ms
step:1332/5100 train_loss:3.6446 train_time:399057ms step_avg:301.86ms
step:1333/5100 train_loss:4.0458 train_time:399251ms step_avg:301.78ms
step:1334/5100 train_loss:3.7380 train_time:399446ms step_avg:301.70ms
step:1335/5100 train_loss:3.6468 train_time:399641ms step_avg:301.62ms
step:1336/5100 train_loss:3.5981 train_time:399837ms step_avg:301.54ms
step:1337/5100 train_loss:3.5876 train_time:400032ms step_avg:301.46ms
step:1338/5100 train_loss:3.8405 train_time:400227ms step_avg:301.38ms
step:1339/5100 train_loss:3.7839 train_time:400421ms step_avg:301.30ms
step:1340/5100 train_loss:3.6314 train_time:400616ms step_avg:301.22ms
step:1341/5100 train_loss:3.5847 train_time:401848ms step_avg:301.91ms
step:1342/5100 train_loss:3.8941 train_time:402048ms step_avg:301.84ms
step:1343/5100 train_loss:3.6524 train_time:402243ms step_avg:301.76ms
step:1344/5100 train_loss:3.6481 train_time:402438ms step_avg:301.68ms
step:1345/5100 train_loss:3.7101 train_time:402633ms step_avg:301.60ms
step:1346/5100 train_loss:3.6779 train_time:402828ms step_avg:301.52ms
step:1347/5100 train_loss:3.5770 train_time:403022ms step_avg:301.44ms
step:1348/5100 train_loss:3.5208 train_time:403216ms step_avg:301.36ms
step:1349/5100 train_loss:3.6249 train_time:403412ms step_avg:301.28ms
step:1350/5100 train_loss:3.5571 train_time:403606ms step_avg:301.20ms
step:1351/5100 train_loss:3.6930 train_time:404835ms step_avg:301.89ms
step:1352/5100 train_loss:3.5362 train_time:405038ms step_avg:301.82ms
step:1353/5100 train_loss:3.5918 train_time:405233ms step_avg:301.74ms
step:1354/5100 train_loss:3.7059 train_time:405428ms step_avg:301.66ms
step:1355/5100 train_loss:3.5352 train_time:405623ms step_avg:301.58ms
step:1356/5100 train_loss:3.4676 train_time:405818ms step_avg:301.50ms
step:1357/5100 train_loss:3.8145 train_time:406013ms step_avg:301.42ms
step:1358/5100 train_loss:3.7427 train_time:406208ms step_avg:301.34ms
step:1359/5100 train_loss:3.4607 train_time:406402ms step_avg:301.26ms
step:1360/5100 train_loss:3.7451 train_time:406597ms step_avg:301.18ms
step:1361/5100 train_loss:3.6284 train_time:407828ms step_avg:301.87ms
step:1362/5100 train_loss:3.4982 train_time:408031ms step_avg:301.80ms
step:1363/5100 train_loss:3.6655 train_time:408226ms step_avg:301.72ms
step:1364/5100 train_loss:3.5569 train_time:408421ms step_avg:301.64ms
step:1365/5100 train_loss:3.5821 train_time:408616ms step_avg:301.56ms
step:1366/5100 train_loss:3.6091 train_time:408812ms step_avg:301.48ms
step:1367/5100 train_loss:3.7166 train_time:409007ms step_avg:301.40ms
step:1368/5100 train_loss:3.6935 train_time:409201ms step_avg:301.33ms
step:1369/5100 train_loss:3.6469 train_time:409396ms step_avg:301.25ms
step:1370/5100 train_loss:3.5480 train_time:409592ms step_avg:301.17ms
step:1371/5100 train_loss:3.8784 train_time:410824ms step_avg:301.85ms
step:1372/5100 train_loss:3.6228 train_time:411025ms step_avg:301.78ms
step:1373/5100 train_loss:3.6520 train_time:411220ms step_avg:301.70ms
step:1374/5100 train_loss:3.6548 train_time:411416ms step_avg:301.62ms
step:1375/5100 train_loss:3.4549 train_time:411612ms step_avg:301.55ms
step:1375/5100 val_loss:3.6128 train_time:411644ms step_avg:301.57ms
step:1376/5100 train_loss:3.8529 train_time:411823ms step_avg:301.48ms
step:1377/5100 train_loss:3.6345 train_time:412020ms step_avg:301.40ms
step:1378/5100 train_loss:3.7787 train_time:412215ms step_avg:301.33ms
step:1379/5100 train_loss:3.8321 train_time:412411ms step_avg:301.25ms
step:1380/5100 train_loss:3.4993 train_time:412605ms step_avg:301.17ms
step:1381/5100 train_loss:3.6199 train_time:413836ms step_avg:301.85ms
step:1382/5100 train_loss:4.0681 train_time:414036ms step_avg:301.78ms
step:1383/5100 train_loss:3.5338 train_time:414233ms step_avg:301.70ms
step:1384/5100 train_loss:3.6909 train_time:414428ms step_avg:301.62ms
step:1385/5100 train_loss:3.7661 train_time:414624ms step_avg:301.54ms
step:1386/5100 train_loss:3.6755 train_time:414819ms step_avg:301.47ms
step:1387/5100 train_loss:3.6754 train_time:415015ms step_avg:301.39ms
step:1388/5100 train_loss:3.4965 train_time:415209ms step_avg:301.31ms
step:1389/5100 train_loss:3.6410 train_time:415404ms step_avg:301.24ms
step:1390/5100 train_loss:3.6070 train_time:415598ms step_avg:301.16ms
step:1391/5100 train_loss:3.8754 train_time:416829ms step_avg:301.83ms
step:1392/5100 train_loss:3.5877 train_time:417031ms step_avg:301.76ms
step:1393/5100 train_loss:3.5779 train_time:417225ms step_avg:301.68ms
step:1394/5100 train_loss:3.5500 train_time:417420ms step_avg:301.60ms
step:1395/5100 train_loss:3.8340 train_time:417615ms step_avg:301.53ms
step:1396/5100 train_loss:3.7206 train_time:417810ms step_avg:301.45ms
step:1397/5100 train_loss:3.7235 train_time:418005ms step_avg:301.37ms
step:1398/5100 train_loss:3.5943 train_time:418200ms step_avg:301.30ms
step:1399/5100 train_loss:3.5647 train_time:418396ms step_avg:301.22ms
step:1400/5100 train_loss:3.6299 train_time:418590ms step_avg:301.14ms
step:1401/5100 train_loss:3.6013 train_time:419820ms step_avg:301.81ms
step:1402/5100 train_loss:3.6306 train_time:420021ms step_avg:301.74ms
step:1403/5100 train_loss:3.5824 train_time:420217ms step_avg:301.66ms
step:1404/5100 train_loss:3.8216 train_time:420411ms step_avg:301.59ms
step:1405/5100 train_loss:3.5648 train_time:420605ms step_avg:301.51ms
step:1406/5100 train_loss:3.6135 train_time:420801ms step_avg:301.43ms
step:1407/5100 train_loss:3.6058 train_time:420996ms step_avg:301.36ms
step:1408/5100 train_loss:3.4771 train_time:421191ms step_avg:301.28ms
step:1409/5100 train_loss:3.5916 train_time:421385ms step_avg:301.20ms
step:1410/5100 train_loss:3.5757 train_time:421580ms step_avg:301.13ms
step:1411/5100 train_loss:3.5749 train_time:422811ms step_avg:301.79ms
step:1412/5100 train_loss:3.6628 train_time:423011ms step_avg:301.72ms
step:1413/5100 train_loss:3.5977 train_time:423205ms step_avg:301.64ms
step:1414/5100 train_loss:3.6481 train_time:423401ms step_avg:301.57ms
step:1415/5100 train_loss:3.6453 train_time:423596ms step_avg:301.49ms
step:1416/5100 train_loss:3.7199 train_time:423792ms step_avg:301.42ms
step:1417/5100 train_loss:3.5165 train_time:423985ms step_avg:301.34ms
step:1418/5100 train_loss:3.5900 train_time:424181ms step_avg:301.26ms
step:1419/5100 train_loss:3.6755 train_time:424376ms step_avg:301.19ms
step:1420/5100 train_loss:3.7071 train_time:424571ms step_avg:301.11ms
step:1421/5100 train_loss:3.6778 train_time:425801ms step_avg:301.77ms
step:1422/5100 train_loss:3.6663 train_time:426001ms step_avg:301.70ms
step:1423/5100 train_loss:3.6470 train_time:426196ms step_avg:301.62ms
step:1424/5100 train_loss:3.6371 train_time:426391ms step_avg:301.55ms
step:1425/5100 train_loss:3.6312 train_time:426585ms step_avg:301.47ms
step:1426/5100 train_loss:3.4994 train_time:426781ms step_avg:301.40ms
step:1427/5100 train_loss:3.6197 train_time:426978ms step_avg:301.33ms
step:1428/5100 train_loss:3.5581 train_time:427173ms step_avg:301.25ms
step:1429/5100 train_loss:3.6734 train_time:427368ms step_avg:301.18ms
step:1430/5100 train_loss:3.6420 train_time:427563ms step_avg:301.10ms
step:1431/5100 train_loss:3.5717 train_time:428795ms step_avg:301.76ms
step:1432/5100 train_loss:3.6158 train_time:428997ms step_avg:301.69ms
step:1433/5100 train_loss:3.6520 train_time:429192ms step_avg:301.61ms
step:1434/5100 train_loss:3.5130 train_time:429386ms step_avg:301.54ms
step:1435/5100 train_loss:3.6188 train_time:429581ms step_avg:301.46ms
step:1436/5100 train_loss:3.4495 train_time:429776ms step_avg:301.39ms
step:1437/5100 train_loss:3.5095 train_time:429972ms step_avg:301.31ms
step:1438/5100 train_loss:3.7113 train_time:430166ms step_avg:301.24ms
step:1439/5100 train_loss:3.6673 train_time:430362ms step_avg:301.16ms
step:1440/5100 train_loss:3.6223 train_time:430557ms step_avg:301.09ms
step:1441/5100 train_loss:3.4724 train_time:431788ms step_avg:301.74ms
step:1442/5100 train_loss:3.6513 train_time:431989ms step_avg:301.67ms
step:1443/5100 train_loss:3.7020 train_time:432183ms step_avg:301.59ms
step:1444/5100 train_loss:3.7794 train_time:432379ms step_avg:301.52ms
step:1445/5100 train_loss:3.7462 train_time:432575ms step_avg:301.45ms
step:1446/5100 train_loss:3.6340 train_time:432770ms step_avg:301.37ms
step:1447/5100 train_loss:3.5087 train_time:432965ms step_avg:301.30ms
step:1448/5100 train_loss:3.5801 train_time:433160ms step_avg:301.22ms
step:1449/5100 train_loss:3.5991 train_time:433356ms step_avg:301.15ms
step:1450/5100 train_loss:3.7232 train_time:433551ms step_avg:301.08ms
step:1451/5100 train_loss:3.7086 train_time:434780ms step_avg:301.72ms
step:1452/5100 train_loss:3.5269 train_time:434984ms step_avg:301.65ms
step:1453/5100 train_loss:3.6364 train_time:435180ms step_avg:301.58ms
step:1454/5100 train_loss:3.5519 train_time:435375ms step_avg:301.51ms
step:1455/5100 train_loss:3.5805 train_time:435570ms step_avg:301.43ms
step:1456/5100 train_loss:3.6256 train_time:435765ms step_avg:301.36ms
step:1457/5100 train_loss:3.5625 train_time:435961ms step_avg:301.29ms
step:1458/5100 train_loss:3.4619 train_time:436157ms step_avg:301.21ms
step:1459/5100 train_loss:3.7027 train_time:436352ms step_avg:301.14ms
step:1460/5100 train_loss:3.5755 train_time:436548ms step_avg:301.07ms
step:1461/5100 train_loss:3.6202 train_time:437779ms step_avg:301.71ms
step:1462/5100 train_loss:3.7498 train_time:437978ms step_avg:301.64ms
step:1463/5100 train_loss:3.5710 train_time:438174ms step_avg:301.56ms
step:1464/5100 train_loss:3.7623 train_time:438367ms step_avg:301.49ms
step:1465/5100 train_loss:3.6505 train_time:438563ms step_avg:301.42ms
step:1466/5100 train_loss:3.6630 train_time:438758ms step_avg:301.34ms
step:1467/5100 train_loss:3.5768 train_time:438953ms step_avg:301.27ms
step:1468/5100 train_loss:3.7336 train_time:439148ms step_avg:301.20ms
step:1469/5100 train_loss:3.5959 train_time:439343ms step_avg:301.13ms
step:1470/5100 train_loss:3.5724 train_time:439539ms step_avg:301.05ms
step:1471/5100 train_loss:3.6233 train_time:440770ms step_avg:301.69ms
step:1472/5100 train_loss:3.5482 train_time:440973ms step_avg:301.62ms
step:1473/5100 train_loss:3.6384 train_time:441167ms step_avg:301.55ms
step:1474/5100 train_loss:3.7275 train_time:441362ms step_avg:301.48ms
step:1475/5100 train_loss:3.6060 train_time:441556ms step_avg:301.40ms
step:1476/5100 train_loss:3.4325 train_time:441751ms step_avg:301.33ms
step:1477/5100 train_loss:3.5604 train_time:441945ms step_avg:301.26ms
step:1478/5100 train_loss:3.5386 train_time:442141ms step_avg:301.19ms
step:1479/5100 train_loss:3.6183 train_time:442336ms step_avg:301.11ms
step:1480/5100 train_loss:3.7012 train_time:442530ms step_avg:301.04ms
step:1481/5100 train_loss:3.5750 train_time:443761ms step_avg:301.67ms
step:1482/5100 train_loss:3.7504 train_time:443962ms step_avg:301.60ms
step:1483/5100 train_loss:3.6741 train_time:444157ms step_avg:301.53ms
step:1484/5100 train_loss:3.5729 train_time:444352ms step_avg:301.46ms
step:1485/5100 train_loss:3.5640 train_time:444546ms step_avg:301.39ms
step:1486/5100 train_loss:3.5625 train_time:444742ms step_avg:301.32ms
step:1487/5100 train_loss:3.5362 train_time:444936ms step_avg:301.24ms
step:1488/5100 train_loss:3.6252 train_time:445131ms step_avg:301.17ms
step:1489/5100 train_loss:3.5342 train_time:445325ms step_avg:301.10ms
step:1490/5100 train_loss:3.6246 train_time:445520ms step_avg:301.03ms
step:1491/5100 train_loss:3.5652 train_time:446751ms step_avg:301.65ms
step:1492/5100 train_loss:3.4876 train_time:446952ms step_avg:301.59ms
step:1493/5100 train_loss:3.5586 train_time:447146ms step_avg:301.51ms
step:1494/5100 train_loss:3.7334 train_time:447342ms step_avg:301.44ms
step:1495/5100 train_loss:3.5875 train_time:447538ms step_avg:301.37ms
step:1496/5100 train_loss:3.3446 train_time:447731ms step_avg:301.30ms
step:1497/5100 train_loss:3.6519 train_time:447927ms step_avg:301.23ms
step:1498/5100 train_loss:3.6170 train_time:448122ms step_avg:301.16ms
step:1499/5100 train_loss:3.6603 train_time:448317ms step_avg:301.09ms
step:1500/5100 train_loss:3.6122 train_time:448512ms step_avg:301.01ms
step:1500/5100 val_loss:3.5986 train_time:448544ms step_avg:301.04ms
step:1501/5100 train_loss:3.5919 train_time:449763ms step_avg:301.65ms
step:1502/5100 train_loss:3.3909 train_time:449965ms step_avg:301.59ms
step:1503/5100 train_loss:3.6646 train_time:450161ms step_avg:301.51ms
step:1504/5100 train_loss:3.5437 train_time:450357ms step_avg:301.44ms
step:1505/5100 train_loss:3.5489 train_time:450551ms step_avg:301.37ms
step:1506/5100 train_loss:3.5077 train_time:450745ms step_avg:301.30ms
step:1507/5100 train_loss:3.5924 train_time:450940ms step_avg:301.23ms
step:1508/5100 train_loss:3.5108 train_time:451134ms step_avg:301.16ms
step:1509/5100 train_loss:3.8244 train_time:451329ms step_avg:301.09ms
step:1510/5100 train_loss:3.5612 train_time:451524ms step_avg:301.02ms
step:1511/5100 train_loss:3.5754 train_time:452754ms step_avg:301.63ms
step:1512/5100 train_loss:3.6971 train_time:453086ms step_avg:301.66ms
step:1513/5100 train_loss:3.7232 train_time:453281ms step_avg:301.58ms
step:1514/5100 train_loss:3.5797 train_time:453478ms step_avg:301.51ms
step:1515/5100 train_loss:3.4133 train_time:453674ms step_avg:301.44ms
step:1516/5100 train_loss:3.5376 train_time:453869ms step_avg:301.37ms
step:1517/5100 train_loss:3.5525 train_time:454063ms step_avg:301.30ms
step:1518/5100 train_loss:3.6299 train_time:454259ms step_avg:301.23ms
step:1519/5100 train_loss:3.5231 train_time:454455ms step_avg:301.16ms
step:1520/5100 train_loss:3.8172 train_time:454844ms step_avg:301.22ms
step:1521/5100 train_loss:3.4766 train_time:456074ms step_avg:301.84ms
step:1522/5100 train_loss:3.5366 train_time:456275ms step_avg:301.77ms
step:1523/5100 train_loss:3.6722 train_time:456470ms step_avg:301.70ms
step:1524/5100 train_loss:3.5391 train_time:456664ms step_avg:301.63ms
step:1525/5100 train_loss:3.6289 train_time:456859ms step_avg:301.56ms
step:1526/5100 train_loss:3.6233 train_time:457055ms step_avg:301.49ms
step:1527/5100 train_loss:3.5909 train_time:457249ms step_avg:301.42ms
step:1528/5100 train_loss:3.5854 train_time:457444ms step_avg:301.35ms
step:1529/5100 train_loss:3.7428 train_time:457639ms step_avg:301.28ms
step:1530/5100 train_loss:3.7073 train_time:457834ms step_avg:301.21ms
step:1531/5100 train_loss:3.5417 train_time:459065ms step_avg:301.82ms
step:1532/5100 train_loss:3.5076 train_time:459267ms step_avg:301.75ms
step:1533/5100 train_loss:3.6491 train_time:459461ms step_avg:301.68ms
step:1534/5100 train_loss:3.6025 train_time:459658ms step_avg:301.61ms
step:1535/5100 train_loss:3.5947 train_time:459854ms step_avg:301.54ms
step:1536/5100 train_loss:3.5874 train_time:460048ms step_avg:301.47ms
step:1537/5100 train_loss:3.5310 train_time:460242ms step_avg:301.40ms
step:1538/5100 train_loss:3.5894 train_time:460436ms step_avg:301.33ms
step:1539/5100 train_loss:3.7657 train_time:460631ms step_avg:301.26ms
step:1540/5100 train_loss:3.6937 train_time:460826ms step_avg:301.19ms
step:1541/5100 train_loss:3.6044 train_time:462056ms step_avg:301.80ms
step:1542/5100 train_loss:3.5602 train_time:462257ms step_avg:301.73ms
step:1543/5100 train_loss:3.5495 train_time:462453ms step_avg:301.67ms
step:1544/5100 train_loss:3.5186 train_time:462649ms step_avg:301.60ms
step:1545/5100 train_loss:3.6088 train_time:462844ms step_avg:301.53ms
step:1546/5100 train_loss:3.5721 train_time:463039ms step_avg:301.46ms
step:1547/5100 train_loss:3.5557 train_time:463234ms step_avg:301.39ms
step:1548/5100 train_loss:3.5153 train_time:463428ms step_avg:301.32ms
step:1549/5100 train_loss:3.5456 train_time:463622ms step_avg:301.25ms
step:1550/5100 train_loss:3.6599 train_time:463818ms step_avg:301.18ms
step:1551/5100 train_loss:3.5903 train_time:465050ms step_avg:301.78ms
step:1552/5100 train_loss:3.5296 train_time:465249ms step_avg:301.72ms
step:1553/5100 train_loss:3.5236 train_time:465446ms step_avg:301.65ms
step:1554/5100 train_loss:3.5117 train_time:465640ms step_avg:301.58ms
step:1555/5100 train_loss:3.6379 train_time:465836ms step_avg:301.51ms
step:1556/5100 train_loss:3.6475 train_time:466030ms step_avg:301.44ms
step:1557/5100 train_loss:3.5842 train_time:466225ms step_avg:301.37ms
step:1558/5100 train_loss:3.6329 train_time:466419ms step_avg:301.30ms
step:1559/5100 train_loss:3.5602 train_time:466613ms step_avg:301.24ms
step:1560/5100 train_loss:3.4725 train_time:466809ms step_avg:301.17ms
step:1561/5100 train_loss:3.7242 train_time:468038ms step_avg:301.77ms
step:1562/5100 train_loss:3.5377 train_time:468240ms step_avg:301.70ms
step:1563/5100 train_loss:3.5145 train_time:468435ms step_avg:301.63ms
step:1564/5100 train_loss:3.6417 train_time:468630ms step_avg:301.56ms
step:1565/5100 train_loss:3.4645 train_time:468825ms step_avg:301.49ms
step:1566/5100 train_loss:3.5256 train_time:469019ms step_avg:301.43ms
step:1567/5100 train_loss:3.6748 train_time:469214ms step_avg:301.36ms
step:1568/5100 train_loss:3.5501 train_time:469409ms step_avg:301.29ms
step:1569/5100 train_loss:3.5365 train_time:469603ms step_avg:301.22ms
step:1570/5100 train_loss:3.6321 train_time:469798ms step_avg:301.15ms
step:1571/5100 train_loss:3.6410 train_time:471030ms step_avg:301.75ms
step:1572/5100 train_loss:3.4677 train_time:471231ms step_avg:301.68ms
step:1573/5100 train_loss:3.4964 train_time:471426ms step_avg:301.62ms
step:1574/5100 train_loss:3.6161 train_time:471621ms step_avg:301.55ms
step:1575/5100 train_loss:3.4877 train_time:471815ms step_avg:301.48ms
step:1576/5100 train_loss:3.6346 train_time:472010ms step_avg:301.41ms
step:1577/5100 train_loss:3.5380 train_time:472205ms step_avg:301.34ms
step:1578/5100 train_loss:3.5940 train_time:472399ms step_avg:301.28ms
step:1579/5100 train_loss:3.5684 train_time:472595ms step_avg:301.21ms
step:1580/5100 train_loss:3.5300 train_time:472789ms step_avg:301.14ms
step:1581/5100 train_loss:3.5065 train_time:474019ms step_avg:301.73ms
step:1582/5100 train_loss:3.7430 train_time:474219ms step_avg:301.67ms
step:1583/5100 train_loss:3.5187 train_time:474415ms step_avg:301.60ms
step:1584/5100 train_loss:3.6758 train_time:474610ms step_avg:301.53ms
step:1585/5100 train_loss:3.5082 train_time:474804ms step_avg:301.46ms
step:1586/5100 train_loss:3.6618 train_time:474998ms step_avg:301.39ms
step:1587/5100 train_loss:3.4526 train_time:475194ms step_avg:301.33ms
step:1588/5100 train_loss:3.6441 train_time:475389ms step_avg:301.26ms
step:1589/5100 train_loss:3.5571 train_time:475584ms step_avg:301.19ms
step:1590/5100 train_loss:3.7176 train_time:475778ms step_avg:301.13ms
step:1591/5100 train_loss:3.5293 train_time:477010ms step_avg:301.71ms
step:1592/5100 train_loss:3.5552 train_time:477210ms step_avg:301.65ms
step:1593/5100 train_loss:3.6221 train_time:477405ms step_avg:301.58ms
step:1594/5100 train_loss:3.5929 train_time:477600ms step_avg:301.51ms
step:1595/5100 train_loss:3.5668 train_time:477795ms step_avg:301.45ms
step:1596/5100 train_loss:3.7133 train_time:477988ms step_avg:301.38ms
step:1597/5100 train_loss:3.4366 train_time:478182ms step_avg:301.31ms
step:1598/5100 train_loss:3.6027 train_time:478378ms step_avg:301.25ms
step:1599/5100 train_loss:3.6512 train_time:478574ms step_avg:301.18ms
step:1600/5100 train_loss:3.6948 train_time:478769ms step_avg:301.11ms
step:1601/5100 train_loss:3.5389 train_time:479999ms step_avg:301.70ms
step:1602/5100 train_loss:3.8343 train_time:480201ms step_avg:301.63ms
step:1603/5100 train_loss:3.7337 train_time:480398ms step_avg:301.57ms
step:1604/5100 train_loss:3.5073 train_time:480593ms step_avg:301.50ms
step:1605/5100 train_loss:3.5527 train_time:480787ms step_avg:301.43ms
step:1606/5100 train_loss:3.4291 train_time:480982ms step_avg:301.37ms
step:1607/5100 train_loss:3.7469 train_time:481177ms step_avg:301.30ms
step:1608/5100 train_loss:3.5528 train_time:481372ms step_avg:301.23ms
step:1609/5100 train_loss:3.5761 train_time:481566ms step_avg:301.17ms
step:1610/5100 train_loss:3.5254 train_time:481761ms step_avg:301.10ms
step:1611/5100 train_loss:4.1390 train_time:482991ms step_avg:301.68ms
step:1612/5100 train_loss:3.7607 train_time:483194ms step_avg:301.62ms
step:1613/5100 train_loss:3.6702 train_time:483390ms step_avg:301.55ms
step:1614/5100 train_loss:3.5473 train_time:483584ms step_avg:301.49ms
step:1615/5100 train_loss:3.5813 train_time:483778ms step_avg:301.42ms
step:1616/5100 train_loss:3.5777 train_time:483973ms step_avg:301.35ms
step:1617/5100 train_loss:3.5375 train_time:484168ms step_avg:301.29ms
step:1618/5100 train_loss:3.6106 train_time:484362ms step_avg:301.22ms
step:1619/5100 train_loss:3.5725 train_time:484557ms step_avg:301.15ms
step:1620/5100 train_loss:3.4621 train_time:484752ms step_avg:301.09ms
step:1621/5100 train_loss:3.7356 train_time:485982ms step_avg:301.67ms
step:1622/5100 train_loss:3.6361 train_time:486183ms step_avg:301.60ms
step:1623/5100 train_loss:3.4294 train_time:486379ms step_avg:301.54ms
step:1624/5100 train_loss:3.5403 train_time:486575ms step_avg:301.47ms
step:1625/5100 train_loss:3.5055 train_time:486770ms step_avg:301.41ms
step:1625/5100 val_loss:3.5749 train_time:486802ms step_avg:301.43ms
step:1626/5100 train_loss:3.5760 train_time:486982ms step_avg:301.35ms
step:1627/5100 train_loss:3.5495 train_time:487178ms step_avg:301.28ms
step:1628/5100 train_loss:3.5099 train_time:487374ms step_avg:301.22ms
step:1629/5100 train_loss:3.6136 train_time:487569ms step_avg:301.15ms
step:1630/5100 train_loss:3.5167 train_time:487763ms step_avg:301.09ms
step:1631/5100 train_loss:3.5729 train_time:488993ms step_avg:301.66ms
step:1632/5100 train_loss:3.4455 train_time:489195ms step_avg:301.60ms
step:1633/5100 train_loss:3.4144 train_time:489392ms step_avg:301.54ms
step:1634/5100 train_loss:3.5849 train_time:489585ms step_avg:301.47ms
step:1635/5100 train_loss:3.5716 train_time:489780ms step_avg:301.40ms
step:1636/5100 train_loss:3.5086 train_time:489975ms step_avg:301.34ms
step:1637/5100 train_loss:3.5972 train_time:490170ms step_avg:301.27ms
step:1638/5100 train_loss:3.6475 train_time:490365ms step_avg:301.21ms
step:1639/5100 train_loss:3.6775 train_time:490560ms step_avg:301.14ms
step:1640/5100 train_loss:3.8476 train_time:490753ms step_avg:301.08ms
step:1641/5100 train_loss:3.6656 train_time:491984ms step_avg:301.65ms
step:1642/5100 train_loss:3.5689 train_time:492187ms step_avg:301.59ms
step:1643/5100 train_loss:3.6515 train_time:492383ms step_avg:301.52ms
step:1644/5100 train_loss:3.5532 train_time:492577ms step_avg:301.45ms
step:1645/5100 train_loss:3.5771 train_time:492773ms step_avg:301.39ms
step:1646/5100 train_loss:3.5792 train_time:492968ms step_avg:301.32ms
step:1647/5100 train_loss:3.3487 train_time:493162ms step_avg:301.26ms
step:1648/5100 train_loss:3.6062 train_time:493355ms step_avg:301.19ms
step:1649/5100 train_loss:3.4749 train_time:493550ms step_avg:301.13ms
step:1650/5100 train_loss:3.5552 train_time:493747ms step_avg:301.07ms
step:1651/5100 train_loss:3.5307 train_time:494977ms step_avg:301.63ms
step:1652/5100 train_loss:3.6031 train_time:495178ms step_avg:301.57ms
step:1653/5100 train_loss:3.5283 train_time:495373ms step_avg:301.50ms
step:1654/5100 train_loss:3.6594 train_time:495568ms step_avg:301.44ms
step:1655/5100 train_loss:3.6485 train_time:495763ms step_avg:301.38ms
step:1656/5100 train_loss:3.4635 train_time:495957ms step_avg:301.31ms
step:1657/5100 train_loss:3.6165 train_time:496152ms step_avg:301.25ms
step:1658/5100 train_loss:3.5172 train_time:496347ms step_avg:301.18ms
step:1659/5100 train_loss:3.4987 train_time:496543ms step_avg:301.12ms
step:1660/5100 train_loss:3.5866 train_time:496736ms step_avg:301.05ms
step:1661/5100 train_loss:3.6062 train_time:497968ms step_avg:301.62ms
step:1662/5100 train_loss:3.5238 train_time:498170ms step_avg:301.56ms
step:1663/5100 train_loss:3.6179 train_time:498365ms step_avg:301.49ms
step:1664/5100 train_loss:3.6253 train_time:498560ms step_avg:301.43ms
step:1665/5100 train_loss:3.6528 train_time:498754ms step_avg:301.36ms
step:1666/5100 train_loss:3.6280 train_time:498950ms step_avg:301.30ms
step:1667/5100 train_loss:3.7743 train_time:499145ms step_avg:301.23ms
step:1668/5100 train_loss:3.4770 train_time:499340ms step_avg:301.17ms
step:1669/5100 train_loss:3.5608 train_time:499534ms step_avg:301.11ms
step:1670/5100 train_loss:3.4867 train_time:499729ms step_avg:301.04ms
step:1671/5100 train_loss:3.4899 train_time:500960ms step_avg:301.60ms
step:1672/5100 train_loss:3.6537 train_time:501162ms step_avg:301.54ms
step:1673/5100 train_loss:3.8321 train_time:501356ms step_avg:301.48ms
step:1674/5100 train_loss:3.5422 train_time:501551ms step_avg:301.41ms
step:1675/5100 train_loss:3.5298 train_time:501746ms step_avg:301.35ms
step:1676/5100 train_loss:3.4169 train_time:501940ms step_avg:301.28ms
step:1677/5100 train_loss:3.6226 train_time:502135ms step_avg:301.22ms
step:1678/5100 train_loss:3.5354 train_time:502331ms step_avg:301.16ms
step:1679/5100 train_loss:3.5640 train_time:502525ms step_avg:301.09ms
step:1680/5100 train_loss:3.5494 train_time:502721ms step_avg:301.03ms
step:1681/5100 train_loss:3.3729 train_time:503950ms step_avg:301.59ms
step:1682/5100 train_loss:3.5543 train_time:504150ms step_avg:301.53ms
step:1683/5100 train_loss:3.5674 train_time:504344ms step_avg:301.46ms
step:1684/5100 train_loss:3.6038 train_time:504539ms step_avg:301.40ms
step:1685/5100 train_loss:3.6138 train_time:504734ms step_avg:301.33ms
step:1686/5100 train_loss:3.5211 train_time:504928ms step_avg:301.27ms
step:1687/5100 train_loss:3.6300 train_time:505123ms step_avg:301.21ms
step:1688/5100 train_loss:3.5075 train_time:505318ms step_avg:301.14ms
step:1689/5100 train_loss:3.5921 train_time:505512ms step_avg:301.08ms
step:1690/5100 train_loss:3.5043 train_time:505709ms step_avg:301.02ms
step:1691/5100 train_loss:3.4060 train_time:506940ms step_avg:301.57ms
step:1692/5100 train_loss:3.5602 train_time:507141ms step_avg:301.51ms
step:1693/5100 train_loss:3.5507 train_time:507335ms step_avg:301.45ms
step:1694/5100 train_loss:3.4688 train_time:507531ms step_avg:301.38ms
step:1695/5100 train_loss:3.9177 train_time:507726ms step_avg:301.32ms
step:1696/5100 train_loss:3.6259 train_time:507920ms step_avg:301.26ms
step:1697/5100 train_loss:3.6065 train_time:508114ms step_avg:301.19ms
step:1698/5100 train_loss:3.5134 train_time:508310ms step_avg:301.13ms
step:1699/5100 train_loss:3.4355 train_time:508505ms step_avg:301.07ms
step:1700/5100 train_loss:3.5215 train_time:508700ms step_avg:301.01ms
step:1701/5100 train_loss:3.5111 train_time:510062ms step_avg:301.63ms
step:1702/5100 train_loss:3.5870 train_time:510264ms step_avg:301.57ms
step:1703/5100 train_loss:3.5124 train_time:510459ms step_avg:301.51ms
step:1704/5100 train_loss:3.7058 train_time:510653ms step_avg:301.45ms
step:1705/5100 train_loss:3.4742 train_time:510849ms step_avg:301.39ms
step:1706/5100 train_loss:3.7057 train_time:511042ms step_avg:301.32ms
step:1707/5100 train_loss:3.5528 train_time:511236ms step_avg:301.26ms
step:1708/5100 train_loss:3.3264 train_time:511431ms step_avg:301.20ms
step:1709/5100 train_loss:3.6633 train_time:511626ms step_avg:301.13ms
step:1710/5100 train_loss:3.5731 train_time:511981ms step_avg:301.17ms
step:1711/5100 train_loss:3.5689 train_time:513210ms step_avg:301.71ms
step:1712/5100 train_loss:3.5493 train_time:513411ms step_avg:301.65ms
step:1713/5100 train_loss:3.5881 train_time:513607ms step_avg:301.59ms
step:1714/5100 train_loss:3.6196 train_time:513803ms step_avg:301.53ms
step:1715/5100 train_loss:3.5320 train_time:513997ms step_avg:301.46ms
step:1716/5100 train_loss:3.5356 train_time:514191ms step_avg:301.40ms
step:1717/5100 train_loss:3.3775 train_time:514386ms step_avg:301.34ms
step:1718/5100 train_loss:3.5142 train_time:514582ms step_avg:301.28ms
step:1719/5100 train_loss:3.5417 train_time:514778ms step_avg:301.22ms
step:1720/5100 train_loss:3.4848 train_time:514972ms step_avg:301.15ms
step:1721/5100 train_loss:3.6374 train_time:516202ms step_avg:301.70ms
step:1722/5100 train_loss:3.4518 train_time:516404ms step_avg:301.64ms
step:1723/5100 train_loss:3.5853 train_time:516600ms step_avg:301.58ms
step:1724/5100 train_loss:3.6757 train_time:516794ms step_avg:301.51ms
step:1725/5100 train_loss:3.5241 train_time:516991ms step_avg:301.45ms
step:1726/5100 train_loss:3.7503 train_time:517186ms step_avg:301.39ms
step:1727/5100 train_loss:3.5460 train_time:517381ms step_avg:301.33ms
step:1728/5100 train_loss:3.5947 train_time:517575ms step_avg:301.27ms
step:1729/5100 train_loss:3.5735 train_time:517771ms step_avg:301.20ms
step:1730/5100 train_loss:3.5820 train_time:517967ms step_avg:301.14ms
step:1731/5100 train_loss:3.9543 train_time:519199ms step_avg:301.68ms
step:1732/5100 train_loss:3.5640 train_time:519398ms step_avg:301.62ms
step:1733/5100 train_loss:3.6879 train_time:519593ms step_avg:301.56ms
step:1734/5100 train_loss:3.4683 train_time:519789ms step_avg:301.50ms
step:1735/5100 train_loss:3.5161 train_time:519984ms step_avg:301.44ms
step:1736/5100 train_loss:3.5349 train_time:520178ms step_avg:301.38ms
step:1737/5100 train_loss:3.5138 train_time:520373ms step_avg:301.32ms
step:1738/5100 train_loss:3.6591 train_time:520569ms step_avg:301.25ms
step:1739/5100 train_loss:3.5239 train_time:520763ms step_avg:301.19ms
step:1740/5100 train_loss:3.5825 train_time:520957ms step_avg:301.13ms
step:1741/5100 train_loss:3.6415 train_time:522187ms step_avg:301.67ms
step:1742/5100 train_loss:3.4391 train_time:522390ms step_avg:301.61ms
step:1743/5100 train_loss:3.3307 train_time:522586ms step_avg:301.55ms
step:1744/5100 train_loss:3.2767 train_time:522780ms step_avg:301.49ms
step:1745/5100 train_loss:3.5597 train_time:522975ms step_avg:301.43ms
step:1746/5100 train_loss:3.5706 train_time:523170ms step_avg:301.37ms
step:1747/5100 train_loss:3.5417 train_time:523365ms step_avg:301.30ms
step:1748/5100 train_loss:3.5463 train_time:523560ms step_avg:301.24ms
step:1749/5100 train_loss:3.8013 train_time:523754ms step_avg:301.18ms
step:1750/5100 train_loss:3.5077 train_time:523950ms step_avg:301.12ms
step:1750/5100 val_loss:3.5572 train_time:523982ms step_avg:301.14ms
step:1751/5100 train_loss:3.5694 train_time:525204ms step_avg:301.67ms
step:1752/5100 train_loss:3.5588 train_time:525404ms step_avg:301.61ms
step:1753/5100 train_loss:3.1938 train_time:525599ms step_avg:301.55ms
step:1754/5100 train_loss:3.3122 train_time:525795ms step_avg:301.49ms
step:1755/5100 train_loss:3.4152 train_time:525990ms step_avg:301.43ms
step:1756/5100 train_loss:3.3662 train_time:526185ms step_avg:301.37ms
step:1757/5100 train_loss:3.5245 train_time:526379ms step_avg:301.30ms
step:1758/5100 train_loss:3.4104 train_time:526574ms step_avg:301.24ms
step:1759/5100 train_loss:3.4008 train_time:526768ms step_avg:301.18ms
step:1760/5100 train_loss:4.4847 train_time:526963ms step_avg:301.12ms
step:1761/5100 train_loss:3.5324 train_time:528193ms step_avg:301.65ms
step:1762/5100 train_loss:3.5734 train_time:528395ms step_avg:301.60ms
step:1763/5100 train_loss:3.5771 train_time:528591ms step_avg:301.54ms
step:1764/5100 train_loss:3.5956 train_time:528786ms step_avg:301.47ms
step:1765/5100 train_loss:3.5068 train_time:528981ms step_avg:301.41ms
step:1766/5100 train_loss:3.5452 train_time:529176ms step_avg:301.35ms
step:1767/5100 train_loss:3.5639 train_time:529372ms step_avg:301.29ms
step:1768/5100 train_loss:3.8144 train_time:529567ms step_avg:301.23ms
step:1769/5100 train_loss:3.5451 train_time:529762ms step_avg:301.17ms
step:1770/5100 train_loss:3.6133 train_time:529957ms step_avg:301.11ms
step:1771/5100 train_loss:4.0038 train_time:531188ms step_avg:301.64ms
step:1772/5100 train_loss:3.5524 train_time:531390ms step_avg:301.58ms
step:1773/5100 train_loss:3.4525 train_time:531585ms step_avg:301.52ms
step:1774/5100 train_loss:3.7043 train_time:531780ms step_avg:301.46ms
step:1775/5100 train_loss:3.4282 train_time:531974ms step_avg:301.40ms
step:1776/5100 train_loss:3.6036 train_time:532170ms step_avg:301.34ms
step:1777/5100 train_loss:3.6576 train_time:532365ms step_avg:301.28ms
step:1778/5100 train_loss:3.7469 train_time:532558ms step_avg:301.22ms
step:1779/5100 train_loss:3.5547 train_time:532753ms step_avg:301.16ms
step:1780/5100 train_loss:3.8547 train_time:532948ms step_avg:301.10ms
step:1781/5100 train_loss:3.6219 train_time:534178ms step_avg:301.63ms
step:1782/5100 train_loss:3.6371 train_time:534382ms step_avg:301.57ms
step:1783/5100 train_loss:3.4214 train_time:534576ms step_avg:301.51ms
step:1784/5100 train_loss:3.5047 train_time:534771ms step_avg:301.45ms
step:1785/5100 train_loss:3.6449 train_time:534965ms step_avg:301.39ms
step:1786/5100 train_loss:3.5336 train_time:535159ms step_avg:301.33ms
step:1787/5100 train_loss:3.7032 train_time:535354ms step_avg:301.27ms
step:1788/5100 train_loss:3.5197 train_time:535549ms step_avg:301.21ms
step:1789/5100 train_loss:3.4927 train_time:535744ms step_avg:301.15ms
step:1790/5100 train_loss:3.6374 train_time:535938ms step_avg:301.09ms
step:1791/5100 train_loss:3.5357 train_time:537170ms step_avg:301.61ms
step:1792/5100 train_loss:3.4899 train_time:537372ms step_avg:301.56ms
step:1793/5100 train_loss:3.6177 train_time:537568ms step_avg:301.50ms
step:1794/5100 train_loss:3.4981 train_time:537762ms step_avg:301.44ms
step:1795/5100 train_loss:3.4871 train_time:537957ms step_avg:301.38ms
step:1796/5100 train_loss:3.5478 train_time:538153ms step_avg:301.32ms
step:1797/5100 train_loss:3.5079 train_time:538348ms step_avg:301.26ms
step:1798/5100 train_loss:3.6456 train_time:538543ms step_avg:301.20ms
step:1799/5100 train_loss:3.5290 train_time:538737ms step_avg:301.14ms
step:1800/5100 train_loss:3.6070 train_time:538933ms step_avg:301.08ms
step:1801/5100 train_loss:3.5388 train_time:540165ms step_avg:301.60ms
step:1802/5100 train_loss:3.5688 train_time:540365ms step_avg:301.54ms
step:1803/5100 train_loss:3.4888 train_time:540559ms step_avg:301.48ms
step:1804/5100 train_loss:3.4140 train_time:540754ms step_avg:301.42ms
step:1805/5100 train_loss:3.6650 train_time:540948ms step_avg:301.36ms
step:1806/5100 train_loss:3.5845 train_time:541143ms step_avg:301.30ms
step:1807/5100 train_loss:3.5886 train_time:541337ms step_avg:301.25ms
step:1808/5100 train_loss:3.7061 train_time:541533ms step_avg:301.19ms
step:1809/5100 train_loss:3.5044 train_time:541728ms step_avg:301.13ms
step:1810/5100 train_loss:3.6014 train_time:541923ms step_avg:301.07ms
step:1811/5100 train_loss:3.7421 train_time:543152ms step_avg:301.58ms
step:1812/5100 train_loss:3.5926 train_time:543354ms step_avg:301.53ms
step:1813/5100 train_loss:3.6277 train_time:543550ms step_avg:301.47ms
step:1814/5100 train_loss:3.6581 train_time:543745ms step_avg:301.41ms
step:1815/5100 train_loss:3.6021 train_time:543939ms step_avg:301.35ms
step:1816/5100 train_loss:3.6353 train_time:544134ms step_avg:301.29ms
step:1817/5100 train_loss:3.5868 train_time:544330ms step_avg:301.23ms
step:1818/5100 train_loss:3.6461 train_time:544525ms step_avg:301.18ms
step:1819/5100 train_loss:3.5655 train_time:544720ms step_avg:301.12ms
step:1820/5100 train_loss:3.5597 train_time:544915ms step_avg:301.06ms
step:1821/5100 train_loss:3.5112 train_time:546148ms step_avg:301.57ms
step:1822/5100 train_loss:3.4895 train_time:546348ms step_avg:301.52ms
step:1823/5100 train_loss:3.4105 train_time:546543ms step_avg:301.46ms
step:1824/5100 train_loss:3.5705 train_time:546737ms step_avg:301.40ms
step:1825/5100 train_loss:3.6876 train_time:546934ms step_avg:301.34ms
step:1826/5100 train_loss:3.6505 train_time:547130ms step_avg:301.28ms
step:1827/5100 train_loss:3.6250 train_time:547325ms step_avg:301.22ms
step:1828/5100 train_loss:3.4967 train_time:547519ms step_avg:301.17ms
step:1829/5100 train_loss:3.5176 train_time:547715ms step_avg:301.11ms
step:1830/5100 train_loss:3.6513 train_time:547910ms step_avg:301.05ms
step:1831/5100 train_loss:3.4331 train_time:549141ms step_avg:301.56ms
step:1832/5100 train_loss:3.5835 train_time:549341ms step_avg:301.50ms
step:1833/5100 train_loss:3.4543 train_time:549536ms step_avg:301.45ms
step:1834/5100 train_loss:3.7762 train_time:549732ms step_avg:301.39ms
step:1835/5100 train_loss:3.6176 train_time:549927ms step_avg:301.33ms
step:1836/5100 train_loss:3.5937 train_time:550122ms step_avg:301.27ms
step:1837/5100 train_loss:3.7204 train_time:550318ms step_avg:301.21ms
step:1838/5100 train_loss:3.5832 train_time:550514ms step_avg:301.16ms
step:1839/5100 train_loss:3.4556 train_time:550709ms step_avg:301.10ms
step:1840/5100 train_loss:3.5819 train_time:550903ms step_avg:301.04ms
step:1841/5100 train_loss:3.4697 train_time:552133ms step_avg:301.55ms
step:1842/5100 train_loss:3.5747 train_time:552334ms step_avg:301.49ms
step:1843/5100 train_loss:3.6320 train_time:552530ms step_avg:301.43ms
step:1844/5100 train_loss:3.3876 train_time:552726ms step_avg:301.38ms
step:1845/5100 train_loss:3.5010 train_time:552922ms step_avg:301.32ms
step:1846/5100 train_loss:3.5650 train_time:553116ms step_avg:301.26ms
step:1847/5100 train_loss:3.5059 train_time:553311ms step_avg:301.20ms
step:1848/5100 train_loss:3.3999 train_time:553506ms step_avg:301.15ms
step:1849/5100 train_loss:3.6720 train_time:553703ms step_avg:301.09ms
step:1850/5100 train_loss:3.4368 train_time:553897ms step_avg:301.03ms
step:1851/5100 train_loss:3.5199 train_time:555128ms step_avg:301.54ms
step:1852/5100 train_loss:3.4906 train_time:555330ms step_avg:301.48ms
step:1853/5100 train_loss:3.6822 train_time:555527ms step_avg:301.43ms
step:1854/5100 train_loss:3.6577 train_time:555721ms step_avg:301.37ms
step:1855/5100 train_loss:3.5222 train_time:555915ms step_avg:301.31ms
step:1856/5100 train_loss:3.4867 train_time:556110ms step_avg:301.25ms
step:1857/5100 train_loss:3.5116 train_time:556305ms step_avg:301.19ms
step:1858/5100 train_loss:3.7561 train_time:556499ms step_avg:301.14ms
step:1859/5100 train_loss:3.5941 train_time:556694ms step_avg:301.08ms
step:1860/5100 train_loss:3.5412 train_time:556890ms step_avg:301.02ms
step:1861/5100 train_loss:3.5850 train_time:558120ms step_avg:301.52ms
step:1862/5100 train_loss:3.4807 train_time:558323ms step_avg:301.47ms
step:1863/5100 train_loss:3.4727 train_time:558517ms step_avg:301.41ms
step:1864/5100 train_loss:3.5435 train_time:558713ms step_avg:301.36ms
step:1865/5100 train_loss:3.5830 train_time:558908ms step_avg:301.30ms
step:1866/5100 train_loss:3.3444 train_time:559103ms step_avg:301.24ms
step:1867/5100 train_loss:3.4761 train_time:559297ms step_avg:301.18ms
step:1868/5100 train_loss:3.4302 train_time:559492ms step_avg:301.13ms
step:1869/5100 train_loss:3.4328 train_time:559687ms step_avg:301.07ms
step:1870/5100 train_loss:3.5922 train_time:559881ms step_avg:301.01ms
step:1871/5100 train_loss:3.5732 train_time:561112ms step_avg:301.51ms
step:1872/5100 train_loss:3.5259 train_time:561315ms step_avg:301.46ms
step:1873/5100 train_loss:3.5343 train_time:561510ms step_avg:301.40ms
step:1874/5100 train_loss:3.4648 train_time:561705ms step_avg:301.34ms
step:1875/5100 train_loss:3.5589 train_time:561898ms step_avg:301.29ms
step:1875/5100 val_loss:3.5392 train_time:561930ms step_avg:301.30ms
step:1876/5100 train_loss:3.5608 train_time:562110ms step_avg:301.24ms
step:1877/5100 train_loss:3.4904 train_time:562307ms step_avg:301.18ms
step:1878/5100 train_loss:3.5329 train_time:562503ms step_avg:301.13ms
step:1879/5100 train_loss:3.6454 train_time:562697ms step_avg:301.07ms
step:1880/5100 train_loss:3.5243 train_time:562891ms step_avg:301.01ms
step:1881/5100 train_loss:3.5792 train_time:564122ms step_avg:301.51ms
step:1882/5100 train_loss:3.4893 train_time:564324ms step_avg:301.45ms
step:1883/5100 train_loss:3.5672 train_time:564519ms step_avg:301.40ms
step:1884/5100 train_loss:3.5550 train_time:564714ms step_avg:301.34ms
step:1885/5100 train_loss:3.3145 train_time:564909ms step_avg:301.28ms
step:1886/5100 train_loss:3.7146 train_time:565105ms step_avg:301.23ms
step:1887/5100 train_loss:3.4461 train_time:565301ms step_avg:301.17ms
step:1888/5100 train_loss:3.4682 train_time:565496ms step_avg:301.12ms
step:1889/5100 train_loss:3.5364 train_time:565690ms step_avg:301.06ms
step:1890/5100 train_loss:3.5809 train_time:566030ms step_avg:301.08ms
step:1891/5100 train_loss:3.4030 train_time:567260ms step_avg:301.57ms
step:1892/5100 train_loss:3.6816 train_time:567461ms step_avg:301.52ms
step:1893/5100 train_loss:3.4325 train_time:567657ms step_avg:301.46ms
step:1894/5100 train_loss:3.5655 train_time:567851ms step_avg:301.41ms
step:1895/5100 train_loss:3.6043 train_time:568046ms step_avg:301.35ms
step:1896/5100 train_loss:3.4015 train_time:568242ms step_avg:301.30ms
step:1897/5100 train_loss:3.5643 train_time:568437ms step_avg:301.24ms
step:1898/5100 train_loss:3.5365 train_time:568632ms step_avg:301.18ms
step:1899/5100 train_loss:3.6108 train_time:568827ms step_avg:301.13ms
step:1900/5100 train_loss:3.3902 train_time:569191ms step_avg:301.16ms
step:1901/5100 train_loss:3.6263 train_time:570421ms step_avg:301.65ms
step:1902/5100 train_loss:3.5151 train_time:570621ms step_avg:301.60ms
step:1903/5100 train_loss:3.6748 train_time:570816ms step_avg:301.54ms
step:1904/5100 train_loss:3.4735 train_time:571010ms step_avg:301.48ms
step:1905/5100 train_loss:3.7657 train_time:571206ms step_avg:301.43ms
step:1906/5100 train_loss:3.4925 train_time:571400ms step_avg:301.37ms
step:1907/5100 train_loss:3.4878 train_time:571595ms step_avg:301.32ms
step:1908/5100 train_loss:3.5625 train_time:571790ms step_avg:301.26ms
step:1909/5100 train_loss:3.4424 train_time:571985ms step_avg:301.20ms
step:1910/5100 train_loss:3.5134 train_time:572180ms step_avg:301.15ms
step:1911/5100 train_loss:3.6029 train_time:573411ms step_avg:301.64ms
step:1912/5100 train_loss:3.5287 train_time:573612ms step_avg:301.58ms
step:1913/5100 train_loss:3.4085 train_time:573807ms step_avg:301.53ms
step:1914/5100 train_loss:3.2777 train_time:574003ms step_avg:301.47ms
step:1915/5100 train_loss:3.4757 train_time:574199ms step_avg:301.42ms
step:1916/5100 train_loss:3.6940 train_time:574393ms step_avg:301.36ms
step:1917/5100 train_loss:3.6934 train_time:574588ms step_avg:301.30ms
step:1918/5100 train_loss:3.6512 train_time:574784ms step_avg:301.25ms
step:1919/5100 train_loss:3.4746 train_time:574980ms step_avg:301.19ms
step:1920/5100 train_loss:3.7167 train_time:575175ms step_avg:301.14ms
step:1921/5100 train_loss:3.5416 train_time:576405ms step_avg:301.62ms
step:1922/5100 train_loss:3.4655 train_time:576606ms step_avg:301.57ms
step:1923/5100 train_loss:3.6509 train_time:576800ms step_avg:301.52ms
step:1924/5100 train_loss:3.6159 train_time:576995ms step_avg:301.46ms
step:1925/5100 train_loss:3.4526 train_time:577191ms step_avg:301.41ms
step:1926/5100 train_loss:3.4876 train_time:577386ms step_avg:301.35ms
step:1927/5100 train_loss:3.3993 train_time:577581ms step_avg:301.29ms
step:1928/5100 train_loss:3.5077 train_time:577776ms step_avg:301.24ms
step:1929/5100 train_loss:3.3681 train_time:577970ms step_avg:301.18ms
step:1930/5100 train_loss:3.4796 train_time:578166ms step_avg:301.13ms
step:1931/5100 train_loss:3.6137 train_time:579396ms step_avg:301.61ms
step:1932/5100 train_loss:3.4831 train_time:579596ms step_avg:301.56ms
step:1933/5100 train_loss:3.6186 train_time:579791ms step_avg:301.50ms
step:1934/5100 train_loss:3.5006 train_time:579986ms step_avg:301.45ms
step:1935/5100 train_loss:3.5488 train_time:580180ms step_avg:301.39ms
step:1936/5100 train_loss:3.5843 train_time:580374ms step_avg:301.34ms
step:1937/5100 train_loss:3.5365 train_time:580568ms step_avg:301.28ms
step:1938/5100 train_loss:3.5643 train_time:580764ms step_avg:301.23ms
step:1939/5100 train_loss:3.4912 train_time:580959ms step_avg:301.17ms
step:1940/5100 train_loss:3.5843 train_time:581153ms step_avg:301.12ms
step:1941/5100 train_loss:3.6170 train_time:582383ms step_avg:301.60ms
step:1942/5100 train_loss:3.4544 train_time:582585ms step_avg:301.55ms
step:1943/5100 train_loss:3.4906 train_time:582782ms step_avg:301.49ms
step:1944/5100 train_loss:3.5592 train_time:582976ms step_avg:301.44ms
step:1945/5100 train_loss:3.3996 train_time:583169ms step_avg:301.38ms
step:1946/5100 train_loss:3.6744 train_time:583365ms step_avg:301.32ms
step:1947/5100 train_loss:3.5484 train_time:583560ms step_avg:301.27ms
step:1948/5100 train_loss:3.5230 train_time:583755ms step_avg:301.22ms
step:1949/5100 train_loss:3.5262 train_time:583950ms step_avg:301.16ms
step:1950/5100 train_loss:3.4059 train_time:584145ms step_avg:301.11ms
step:1951/5100 train_loss:3.5293 train_time:585376ms step_avg:301.58ms
step:1952/5100 train_loss:3.3745 train_time:585577ms step_avg:301.53ms
step:1953/5100 train_loss:3.5857 train_time:585771ms step_avg:301.48ms
step:1954/5100 train_loss:3.5709 train_time:585967ms step_avg:301.42ms
step:1955/5100 train_loss:3.5245 train_time:586162ms step_avg:301.37ms
step:1956/5100 train_loss:3.4161 train_time:586356ms step_avg:301.31ms
step:1957/5100 train_loss:3.5048 train_time:586551ms step_avg:301.26ms
step:1958/5100 train_loss:3.6933 train_time:586745ms step_avg:301.20ms
step:1959/5100 train_loss:3.6084 train_time:586940ms step_avg:301.15ms
step:1960/5100 train_loss:3.6306 train_time:587135ms step_avg:301.09ms
step:1961/5100 train_loss:3.4323 train_time:588365ms step_avg:301.57ms
step:1962/5100 train_loss:3.5544 train_time:588565ms step_avg:301.52ms
step:1963/5100 train_loss:3.5993 train_time:588761ms step_avg:301.46ms
step:1964/5100 train_loss:3.5455 train_time:588956ms step_avg:301.41ms
step:1965/5100 train_loss:3.4517 train_time:589151ms step_avg:301.36ms
step:1966/5100 train_loss:3.8523 train_time:589347ms step_avg:301.30ms
step:1967/5100 train_loss:3.4755 train_time:589542ms step_avg:301.25ms
step:1968/5100 train_loss:3.5111 train_time:589737ms step_avg:301.19ms
step:1969/5100 train_loss:3.5636 train_time:589932ms step_avg:301.14ms
step:1970/5100 train_loss:3.5227 train_time:590128ms step_avg:301.09ms
step:1971/5100 train_loss:3.4100 train_time:591360ms step_avg:301.56ms
step:1972/5100 train_loss:3.3855 train_time:591561ms step_avg:301.51ms
step:1973/5100 train_loss:3.5141 train_time:591757ms step_avg:301.46ms
step:1974/5100 train_loss:3.4859 train_time:591951ms step_avg:301.40ms
step:1975/5100 train_loss:3.4498 train_time:592147ms step_avg:301.35ms
step:1976/5100 train_loss:3.6072 train_time:592342ms step_avg:301.29ms
step:1977/5100 train_loss:3.4804 train_time:592537ms step_avg:301.24ms
step:1978/5100 train_loss:3.8472 train_time:592731ms step_avg:301.18ms
step:1979/5100 train_loss:3.5312 train_time:592926ms step_avg:301.13ms
step:1980/5100 train_loss:3.5337 train_time:593123ms step_avg:301.08ms
step:1981/5100 train_loss:3.5426 train_time:594354ms step_avg:301.55ms
step:1982/5100 train_loss:3.5679 train_time:594556ms step_avg:301.50ms
step:1983/5100 train_loss:3.4929 train_time:594752ms step_avg:301.45ms
step:1984/5100 train_loss:3.4536 train_time:594946ms step_avg:301.39ms
step:1985/5100 train_loss:3.5134 train_time:595142ms step_avg:301.34ms
step:1986/5100 train_loss:3.5770 train_time:595337ms step_avg:301.28ms
step:1987/5100 train_loss:3.5532 train_time:595532ms step_avg:301.23ms
step:1988/5100 train_loss:3.5174 train_time:595727ms step_avg:301.18ms
step:1989/5100 train_loss:3.6033 train_time:595923ms step_avg:301.12ms
step:1990/5100 train_loss:3.6328 train_time:596117ms step_avg:301.07ms
step:1991/5100 train_loss:3.4080 train_time:597348ms step_avg:301.54ms
step:1992/5100 train_loss:3.4126 train_time:597550ms step_avg:301.49ms
step:1993/5100 train_loss:3.5932 train_time:597745ms step_avg:301.43ms
step:1994/5100 train_loss:3.4167 train_time:597940ms step_avg:301.38ms
step:1995/5100 train_loss:3.5117 train_time:598134ms step_avg:301.33ms
step:1996/5100 train_loss:3.5854 train_time:598329ms step_avg:301.27ms
step:1997/5100 train_loss:3.4463 train_time:598526ms step_avg:301.22ms
step:1998/5100 train_loss:3.5465 train_time:598722ms step_avg:301.17ms
step:1999/5100 train_loss:3.5460 train_time:598916ms step_avg:301.11ms
step:2000/5100 train_loss:3.4705 train_time:599111ms step_avg:301.06ms
step:2000/5100 val_loss:3.5255 train_time:599143ms step_avg:301.08ms
step:2001/5100 train_loss:3.6138 train_time:600359ms step_avg:301.54ms
step:2002/5100 train_loss:3.5627 train_time:600559ms step_avg:301.49ms
step:2003/5100 train_loss:3.6430 train_time:600755ms step_avg:301.43ms
step:2004/5100 train_loss:3.5639 train_time:600951ms step_avg:301.38ms
step:2005/5100 train_loss:3.5794 train_time:601145ms step_avg:301.33ms
step:2006/5100 train_loss:3.4656 train_time:601340ms step_avg:301.27ms
step:2007/5100 train_loss:3.4981 train_time:601536ms step_avg:301.22ms
step:2008/5100 train_loss:3.5338 train_time:601732ms step_avg:301.17ms
step:2009/5100 train_loss:3.5742 train_time:601925ms step_avg:301.11ms
step:2010/5100 train_loss:3.4819 train_time:602120ms step_avg:301.06ms
step:2011/5100 train_loss:3.5603 train_time:603352ms step_avg:301.53ms
step:2012/5100 train_loss:3.5347 train_time:603554ms step_avg:301.48ms
step:2013/5100 train_loss:3.5354 train_time:603749ms step_avg:301.42ms
step:2014/5100 train_loss:3.4538 train_time:603943ms step_avg:301.37ms
step:2015/5100 train_loss:3.5028 train_time:604139ms step_avg:301.32ms
step:2016/5100 train_loss:3.5129 train_time:604335ms step_avg:301.26ms
step:2017/5100 train_loss:3.6538 train_time:604530ms step_avg:301.21ms
step:2018/5100 train_loss:3.4948 train_time:604725ms step_avg:301.16ms
step:2019/5100 train_loss:3.6506 train_time:604921ms step_avg:301.11ms
step:2020/5100 train_loss:3.6615 train_time:605117ms step_avg:301.05ms
step:2021/5100 train_loss:3.3756 train_time:606348ms step_avg:301.52ms
step:2022/5100 train_loss:3.6018 train_time:606551ms step_avg:301.47ms
step:2023/5100 train_loss:3.5230 train_time:606745ms step_avg:301.41ms
step:2024/5100 train_loss:3.6164 train_time:606940ms step_avg:301.36ms
step:2025/5100 train_loss:3.6688 train_time:607135ms step_avg:301.31ms
step:2026/5100 train_loss:3.4492 train_time:607330ms step_avg:301.25ms
step:2027/5100 train_loss:3.4923 train_time:607524ms step_avg:301.20ms
step:2028/5100 train_loss:3.3917 train_time:607719ms step_avg:301.15ms
step:2029/5100 train_loss:3.5049 train_time:607914ms step_avg:301.10ms
step:2030/5100 train_loss:3.4279 train_time:608109ms step_avg:301.04ms
step:2031/5100 train_loss:3.5136 train_time:609339ms step_avg:301.50ms
step:2032/5100 train_loss:3.5129 train_time:609541ms step_avg:301.45ms
step:2033/5100 train_loss:3.5215 train_time:609735ms step_avg:301.40ms
step:2034/5100 train_loss:3.4211 train_time:609931ms step_avg:301.35ms
step:2035/5100 train_loss:3.5846 train_time:610125ms step_avg:301.30ms
step:2036/5100 train_loss:3.5816 train_time:610320ms step_avg:301.24ms
step:2037/5100 train_loss:3.5709 train_time:610515ms step_avg:301.19ms
step:2038/5100 train_loss:3.4415 train_time:610709ms step_avg:301.14ms
step:2039/5100 train_loss:3.7010 train_time:610904ms step_avg:301.09ms
step:2040/5100 train_loss:3.5353 train_time:611098ms step_avg:301.03ms
step:2041/5100 train_loss:3.5526 train_time:612329ms step_avg:301.49ms
step:2042/5100 train_loss:3.5026 train_time:612530ms step_avg:301.44ms
step:2043/5100 train_loss:3.3947 train_time:612725ms step_avg:301.39ms
step:2044/5100 train_loss:3.5316 train_time:612920ms step_avg:301.34ms
step:2045/5100 train_loss:3.5261 train_time:613116ms step_avg:301.29ms
step:2046/5100 train_loss:3.3889 train_time:613311ms step_avg:301.23ms
step:2047/5100 train_loss:3.4679 train_time:613505ms step_avg:301.18ms
step:2048/5100 train_loss:3.5422 train_time:613701ms step_avg:301.13ms
step:2049/5100 train_loss:3.4931 train_time:613897ms step_avg:301.08ms
step:2050/5100 train_loss:3.5302 train_time:614092ms step_avg:301.03ms
step:2051/5100 train_loss:3.6829 train_time:615323ms step_avg:301.48ms
step:2052/5100 train_loss:3.5560 train_time:615524ms step_avg:301.43ms
step:2053/5100 train_loss:3.4989 train_time:615720ms step_avg:301.38ms
step:2054/5100 train_loss:3.4837 train_time:615914ms step_avg:301.33ms
step:2055/5100 train_loss:3.3503 train_time:616109ms step_avg:301.28ms
step:2056/5100 train_loss:3.4586 train_time:616303ms step_avg:301.22ms
step:2057/5100 train_loss:3.6403 train_time:616499ms step_avg:301.17ms
step:2058/5100 train_loss:3.6588 train_time:616695ms step_avg:301.12ms
step:2059/5100 train_loss:3.5221 train_time:616890ms step_avg:301.07ms
step:2060/5100 train_loss:3.5649 train_time:617084ms step_avg:301.02ms
step:2061/5100 train_loss:3.5488 train_time:618314ms step_avg:301.47ms
step:2062/5100 train_loss:3.5042 train_time:618517ms step_avg:301.42ms
step:2063/5100 train_loss:3.4148 train_time:618712ms step_avg:301.37ms
step:2064/5100 train_loss:3.7228 train_time:618907ms step_avg:301.32ms
step:2065/5100 train_loss:3.5812 train_time:619101ms step_avg:301.27ms
step:2066/5100 train_loss:3.5284 train_time:619297ms step_avg:301.21ms
step:2067/5100 train_loss:3.5734 train_time:619491ms step_avg:301.16ms
step:2068/5100 train_loss:3.4790 train_time:619684ms step_avg:301.11ms
step:2069/5100 train_loss:3.5323 train_time:619879ms step_avg:301.06ms
step:2070/5100 train_loss:3.6632 train_time:620074ms step_avg:301.01ms
step:2071/5100 train_loss:3.6695 train_time:621304ms step_avg:301.46ms
step:2072/5100 train_loss:3.5246 train_time:621505ms step_avg:301.41ms
step:2073/5100 train_loss:3.5546 train_time:621700ms step_avg:301.36ms
step:2074/5100 train_loss:3.4364 train_time:621896ms step_avg:301.31ms
step:2075/5100 train_loss:3.9615 train_time:622091ms step_avg:301.25ms
step:2076/5100 train_loss:3.3954 train_time:622285ms step_avg:301.20ms
step:2077/5100 train_loss:3.5670 train_time:622480ms step_avg:301.15ms
step:2078/5100 train_loss:3.4602 train_time:622675ms step_avg:301.10ms
step:2079/5100 train_loss:3.4265 train_time:623019ms step_avg:301.12ms
step:2080/5100 train_loss:3.5261 train_time:623213ms step_avg:301.07ms
step:2081/5100 train_loss:3.7688 train_time:624444ms step_avg:301.52ms
step:2082/5100 train_loss:3.4070 train_time:624643ms step_avg:301.47ms
step:2083/5100 train_loss:3.7399 train_time:624839ms step_avg:301.42ms
step:2084/5100 train_loss:3.4453 train_time:625034ms step_avg:301.37ms
step:2085/5100 train_loss:3.4264 train_time:625229ms step_avg:301.32ms
step:2086/5100 train_loss:3.6723 train_time:625423ms step_avg:301.26ms
step:2087/5100 train_loss:3.6039 train_time:625620ms step_avg:301.21ms
step:2088/5100 train_loss:3.5871 train_time:625814ms step_avg:301.16ms
step:2089/5100 train_loss:3.6490 train_time:626008ms step_avg:301.11ms
step:2090/5100 train_loss:3.5670 train_time:626374ms step_avg:301.14ms
step:2091/5100 train_loss:3.5606 train_time:627603ms step_avg:301.59ms
step:2092/5100 train_loss:3.5127 train_time:627803ms step_avg:301.54ms
step:2093/5100 train_loss:3.5803 train_time:627999ms step_avg:301.49ms
step:2094/5100 train_loss:3.4740 train_time:628193ms step_avg:301.44ms
step:2095/5100 train_loss:3.2704 train_time:628387ms step_avg:301.38ms
step:2096/5100 train_loss:3.5010 train_time:628582ms step_avg:301.33ms
step:2097/5100 train_loss:3.6714 train_time:628778ms step_avg:301.28ms
step:2098/5100 train_loss:3.5095 train_time:628973ms step_avg:301.23ms
step:2099/5100 train_loss:3.3936 train_time:629169ms step_avg:301.18ms
step:2100/5100 train_loss:3.4971 train_time:629362ms step_avg:301.13ms
step:2101/5100 train_loss:3.4569 train_time:630592ms step_avg:301.57ms
step:2102/5100 train_loss:3.5966 train_time:630795ms step_avg:301.53ms
step:2103/5100 train_loss:3.4286 train_time:630991ms step_avg:301.48ms
step:2104/5100 train_loss:3.3874 train_time:631186ms step_avg:301.43ms
step:2105/5100 train_loss:3.6535 train_time:631379ms step_avg:301.37ms
step:2106/5100 train_loss:3.3837 train_time:631575ms step_avg:301.32ms
step:2107/5100 train_loss:3.7791 train_time:631770ms step_avg:301.27ms
step:2108/5100 train_loss:3.6194 train_time:631965ms step_avg:301.22ms
step:2109/5100 train_loss:3.5260 train_time:632160ms step_avg:301.17ms
step:2110/5100 train_loss:3.5423 train_time:632353ms step_avg:301.12ms
step:2111/5100 train_loss:3.3677 train_time:633584ms step_avg:301.56ms
step:2112/5100 train_loss:3.8502 train_time:633787ms step_avg:301.52ms
step:2113/5100 train_loss:3.5340 train_time:633982ms step_avg:301.47ms
step:2114/5100 train_loss:3.4644 train_time:634175ms step_avg:301.41ms
step:2115/5100 train_loss:3.5852 train_time:634369ms step_avg:301.36ms
step:2116/5100 train_loss:3.5442 train_time:634563ms step_avg:301.31ms
step:2117/5100 train_loss:3.5275 train_time:634759ms step_avg:301.26ms
step:2118/5100 train_loss:3.5811 train_time:634955ms step_avg:301.21ms
step:2119/5100 train_loss:3.4409 train_time:635150ms step_avg:301.16ms
step:2120/5100 train_loss:3.5042 train_time:635344ms step_avg:301.11ms
step:2121/5100 train_loss:3.2068 train_time:636574ms step_avg:301.55ms
step:2122/5100 train_loss:3.4053 train_time:636775ms step_avg:301.50ms
step:2123/5100 train_loss:3.5669 train_time:636969ms step_avg:301.45ms
step:2124/5100 train_loss:3.4810 train_time:637163ms step_avg:301.40ms
step:2125/5100 train_loss:3.6355 train_time:637359ms step_avg:301.35ms
step:2125/5100 val_loss:3.5141 train_time:637391ms step_avg:301.37ms
step:2126/5100 train_loss:3.4977 train_time:637573ms step_avg:301.31ms
step:2127/5100 train_loss:3.6120 train_time:637769ms step_avg:301.26ms
step:2128/5100 train_loss:3.5944 train_time:637965ms step_avg:301.21ms
step:2129/5100 train_loss:3.4578 train_time:638160ms step_avg:301.16ms
step:2130/5100 train_loss:3.4389 train_time:638354ms step_avg:301.11ms
step:2131/5100 train_loss:3.4654 train_time:639586ms step_avg:301.55ms
step:2132/5100 train_loss:3.6244 train_time:639785ms step_avg:301.50ms
step:2133/5100 train_loss:3.5003 train_time:639980ms step_avg:301.45ms
step:2134/5100 train_loss:3.4071 train_time:640175ms step_avg:301.40ms
step:2135/5100 train_loss:3.4719 train_time:640371ms step_avg:301.35ms
step:2136/5100 train_loss:3.5893 train_time:640567ms step_avg:301.30ms
step:2137/5100 train_loss:3.5985 train_time:640762ms step_avg:301.25ms
step:2138/5100 train_loss:3.5496 train_time:640957ms step_avg:301.20ms
step:2139/5100 train_loss:3.5395 train_time:641153ms step_avg:301.15ms
step:2140/5100 train_loss:3.5294 train_time:641347ms step_avg:301.10ms
step:2141/5100 train_loss:3.6113 train_time:642578ms step_avg:301.54ms
step:2142/5100 train_loss:3.9211 train_time:642780ms step_avg:301.49ms
step:2143/5100 train_loss:3.4402 train_time:642974ms step_avg:301.44ms
step:2144/5100 train_loss:3.4726 train_time:643170ms step_avg:301.39ms
step:2145/5100 train_loss:3.5050 train_time:643365ms step_avg:301.34ms
step:2146/5100 train_loss:3.6351 train_time:643560ms step_avg:301.29ms
step:2147/5100 train_loss:3.5673 train_time:643756ms step_avg:301.24ms
step:2148/5100 train_loss:3.9773 train_time:643952ms step_avg:301.19ms
step:2149/5100 train_loss:3.4919 train_time:644147ms step_avg:301.14ms
step:2150/5100 train_loss:3.4720 train_time:644341ms step_avg:301.09ms
step:2151/5100 train_loss:3.5371 train_time:645573ms step_avg:301.53ms
step:2152/5100 train_loss:3.5647 train_time:645775ms step_avg:301.48ms
step:2153/5100 train_loss:3.5222 train_time:645970ms step_avg:301.43ms
step:2154/5100 train_loss:3.4559 train_time:646164ms step_avg:301.38ms
step:2155/5100 train_loss:3.6684 train_time:646358ms step_avg:301.33ms
step:2156/5100 train_loss:3.2869 train_time:646554ms step_avg:301.28ms
step:2157/5100 train_loss:3.4514 train_time:646749ms step_avg:301.23ms
step:2158/5100 train_loss:3.5819 train_time:646944ms step_avg:301.18ms
step:2159/5100 train_loss:3.5237 train_time:647138ms step_avg:301.13ms
step:2160/5100 train_loss:3.6796 train_time:647334ms step_avg:301.09ms
step:2161/5100 train_loss:3.5995 train_time:648565ms step_avg:301.52ms
step:2162/5100 train_loss:3.5265 train_time:648766ms step_avg:301.47ms
step:2163/5100 train_loss:3.4849 train_time:648962ms step_avg:301.42ms
step:2164/5100 train_loss:3.4842 train_time:649156ms step_avg:301.37ms
step:2165/5100 train_loss:3.5761 train_time:649352ms step_avg:301.32ms
step:2166/5100 train_loss:3.5971 train_time:649547ms step_avg:301.27ms
step:2167/5100 train_loss:3.5284 train_time:649740ms step_avg:301.22ms
step:2168/5100 train_loss:3.4153 train_time:649935ms step_avg:301.17ms
step:2169/5100 train_loss:3.5027 train_time:650130ms step_avg:301.13ms
step:2170/5100 train_loss:3.5488 train_time:650326ms step_avg:301.08ms
step:2171/5100 train_loss:3.6630 train_time:651557ms step_avg:301.51ms
step:2172/5100 train_loss:3.4674 train_time:651758ms step_avg:301.46ms
step:2173/5100 train_loss:3.4534 train_time:651953ms step_avg:301.41ms
step:2174/5100 train_loss:3.4597 train_time:652148ms step_avg:301.36ms
step:2175/5100 train_loss:3.5196 train_time:652342ms step_avg:301.31ms
step:2176/5100 train_loss:3.4725 train_time:652537ms step_avg:301.26ms
step:2177/5100 train_loss:3.4494 train_time:652731ms step_avg:301.21ms
step:2178/5100 train_loss:3.6662 train_time:652926ms step_avg:301.17ms
step:2179/5100 train_loss:3.4887 train_time:653121ms step_avg:301.12ms
step:2180/5100 train_loss:3.4981 train_time:653315ms step_avg:301.07ms
step:2181/5100 train_loss:3.5596 train_time:654547ms step_avg:301.50ms
step:2182/5100 train_loss:3.5385 train_time:654750ms step_avg:301.45ms
step:2183/5100 train_loss:3.5115 train_time:654946ms step_avg:301.40ms
step:2184/5100 train_loss:3.4049 train_time:655142ms step_avg:301.35ms
step:2185/5100 train_loss:3.5736 train_time:655336ms step_avg:301.30ms
step:2186/5100 train_loss:3.7441 train_time:655532ms step_avg:301.26ms
step:2187/5100 train_loss:3.3833 train_time:655726ms step_avg:301.21ms
step:2188/5100 train_loss:3.4343 train_time:655920ms step_avg:301.16ms
step:2189/5100 train_loss:3.2887 train_time:656115ms step_avg:301.11ms
step:2190/5100 train_loss:3.4286 train_time:656310ms step_avg:301.06ms
step:2191/5100 train_loss:3.5794 train_time:657542ms step_avg:301.49ms
step:2192/5100 train_loss:3.5158 train_time:657745ms step_avg:301.44ms
step:2193/5100 train_loss:3.7445 train_time:657940ms step_avg:301.39ms
step:2194/5100 train_loss:3.5138 train_time:658135ms step_avg:301.34ms
step:2195/5100 train_loss:3.5801 train_time:658330ms step_avg:301.30ms
step:2196/5100 train_loss:3.5159 train_time:658525ms step_avg:301.25ms
step:2197/5100 train_loss:3.4376 train_time:658719ms step_avg:301.20ms
step:2198/5100 train_loss:3.5155 train_time:658914ms step_avg:301.15ms
step:2199/5100 train_loss:3.4578 train_time:659109ms step_avg:301.10ms
step:2200/5100 train_loss:3.4661 train_time:659303ms step_avg:301.05ms
step:2201/5100 train_loss:3.5176 train_time:660533ms step_avg:301.48ms
step:2202/5100 train_loss:3.4931 train_time:660734ms step_avg:301.43ms
step:2203/5100 train_loss:3.4793 train_time:660929ms step_avg:301.38ms
step:2204/5100 train_loss:3.9793 train_time:661125ms step_avg:301.33ms
step:2205/5100 train_loss:3.3868 train_time:661320ms step_avg:301.28ms
step:2206/5100 train_loss:3.5184 train_time:661515ms step_avg:301.24ms
step:2207/5100 train_loss:3.5283 train_time:661710ms step_avg:301.19ms
step:2208/5100 train_loss:3.5483 train_time:661905ms step_avg:301.14ms
step:2209/5100 train_loss:3.4410 train_time:662099ms step_avg:301.09ms
step:2210/5100 train_loss:3.5181 train_time:662294ms step_avg:301.04ms
step:2211/5100 train_loss:3.5317 train_time:663526ms step_avg:301.47ms
step:2212/5100 train_loss:3.5192 train_time:663725ms step_avg:301.42ms
step:2213/5100 train_loss:3.5524 train_time:663920ms step_avg:301.37ms
step:2214/5100 train_loss:3.4061 train_time:664114ms step_avg:301.32ms
step:2215/5100 train_loss:3.4764 train_time:664309ms step_avg:301.27ms
step:2216/5100 train_loss:3.6121 train_time:664502ms step_avg:301.23ms
step:2217/5100 train_loss:3.5685 train_time:664697ms step_avg:301.18ms
step:2218/5100 train_loss:3.5237 train_time:664893ms step_avg:301.13ms
step:2219/5100 train_loss:3.5344 train_time:665088ms step_avg:301.08ms
step:2220/5100 train_loss:3.4418 train_time:665283ms step_avg:301.03ms
step:2221/5100 train_loss:3.7003 train_time:666513ms step_avg:301.45ms
step:2222/5100 train_loss:3.5915 train_time:666715ms step_avg:301.41ms
step:2223/5100 train_loss:3.6087 train_time:666909ms step_avg:301.36ms
step:2224/5100 train_loss:3.5061 train_time:667103ms step_avg:301.31ms
step:2225/5100 train_loss:3.6201 train_time:667297ms step_avg:301.26ms
step:2226/5100 train_loss:3.3653 train_time:667493ms step_avg:301.22ms
step:2227/5100 train_loss:3.6389 train_time:667688ms step_avg:301.17ms
step:2228/5100 train_loss:3.5763 train_time:667883ms step_avg:301.12ms
step:2229/5100 train_loss:3.3809 train_time:668076ms step_avg:301.07ms
step:2230/5100 train_loss:3.7181 train_time:668273ms step_avg:301.02ms
step:2231/5100 train_loss:3.4153 train_time:669505ms step_avg:301.44ms
step:2232/5100 train_loss:3.8874 train_time:669705ms step_avg:301.40ms
step:2233/5100 train_loss:3.5754 train_time:669900ms step_avg:301.35ms
step:2234/5100 train_loss:3.5222 train_time:670095ms step_avg:301.30ms
step:2235/5100 train_loss:3.5540 train_time:670290ms step_avg:301.25ms
step:2236/5100 train_loss:3.3299 train_time:670485ms step_avg:301.21ms
step:2237/5100 train_loss:3.3315 train_time:670680ms step_avg:301.16ms
step:2238/5100 train_loss:3.5593 train_time:670875ms step_avg:301.11ms
step:2239/5100 train_loss:3.6502 train_time:671071ms step_avg:301.06ms
step:2240/5100 train_loss:3.3794 train_time:671267ms step_avg:301.02ms
step:2241/5100 train_loss:3.4506 train_time:672497ms step_avg:301.43ms
step:2242/5100 train_loss:3.6216 train_time:672698ms step_avg:301.39ms
step:2243/5100 train_loss:3.5947 train_time:672893ms step_avg:301.34ms
step:2244/5100 train_loss:3.4482 train_time:673089ms step_avg:301.29ms
step:2245/5100 train_loss:3.5195 train_time:673284ms step_avg:301.25ms
step:2246/5100 train_loss:3.5446 train_time:673479ms step_avg:301.20ms
step:2247/5100 train_loss:3.3777 train_time:673674ms step_avg:301.15ms
step:2248/5100 train_loss:3.3895 train_time:673870ms step_avg:301.10ms
step:2249/5100 train_loss:3.6443 train_time:674067ms step_avg:301.06ms
step:2250/5100 train_loss:3.3772 train_time:674263ms step_avg:301.01ms
step:2250/5100 val_loss:3.5023 train_time:674295ms step_avg:301.02ms
step:2251/5100 train_loss:3.3762 train_time:675510ms step_avg:301.43ms
step:2252/5100 train_loss:3.4539 train_time:675712ms step_avg:301.39ms
step:2253/5100 train_loss:3.4256 train_time:675906ms step_avg:301.34ms
step:2254/5100 train_loss:3.4735 train_time:676101ms step_avg:301.29ms
step:2255/5100 train_loss:3.5265 train_time:676296ms step_avg:301.25ms
step:2256/5100 train_loss:3.4040 train_time:676491ms step_avg:301.20ms
step:2257/5100 train_loss:3.6850 train_time:676686ms step_avg:301.15ms
step:2258/5100 train_loss:3.5731 train_time:676882ms step_avg:301.10ms
step:2259/5100 train_loss:3.8814 train_time:677077ms step_avg:301.06ms
step:2260/5100 train_loss:3.5672 train_time:677272ms step_avg:301.01ms
step:2261/5100 train_loss:3.6212 train_time:678503ms step_avg:301.42ms
step:2262/5100 train_loss:3.5295 train_time:678704ms step_avg:301.38ms
step:2263/5100 train_loss:3.5368 train_time:678899ms step_avg:301.33ms
step:2264/5100 train_loss:3.2902 train_time:679092ms step_avg:301.28ms
step:2265/5100 train_loss:3.4143 train_time:679287ms step_avg:301.24ms
step:2266/5100 train_loss:3.6262 train_time:679482ms step_avg:301.19ms
step:2267/5100 train_loss:3.3623 train_time:679679ms step_avg:301.14ms
step:2268/5100 train_loss:3.4337 train_time:680021ms step_avg:301.16ms
step:2269/5100 train_loss:3.4100 train_time:680215ms step_avg:301.11ms
step:2270/5100 train_loss:3.3840 train_time:680410ms step_avg:301.07ms
step:2271/5100 train_loss:3.7733 train_time:681640ms step_avg:301.48ms
step:2272/5100 train_loss:3.4339 train_time:681843ms step_avg:301.43ms
step:2273/5100 train_loss:3.4443 train_time:682039ms step_avg:301.39ms
step:2274/5100 train_loss:3.5189 train_time:682234ms step_avg:301.34ms
step:2275/5100 train_loss:3.4756 train_time:682429ms step_avg:301.29ms
step:2276/5100 train_loss:3.4821 train_time:682623ms step_avg:301.25ms
step:2277/5100 train_loss:3.3682 train_time:682817ms step_avg:301.20ms
step:2278/5100 train_loss:3.4741 train_time:683013ms step_avg:301.15ms
step:2279/5100 train_loss:3.6038 train_time:683207ms step_avg:301.11ms
step:2280/5100 train_loss:3.4026 train_time:683573ms step_avg:301.13ms
step:2281/5100 train_loss:3.4644 train_time:684803ms step_avg:301.54ms
step:2282/5100 train_loss:3.4747 train_time:685004ms step_avg:301.50ms
step:2283/5100 train_loss:3.6139 train_time:685197ms step_avg:301.45ms
step:2284/5100 train_loss:3.4929 train_time:685391ms step_avg:301.40ms
step:2285/5100 train_loss:3.5108 train_time:685586ms step_avg:301.36ms
step:2286/5100 train_loss:3.5166 train_time:685781ms step_avg:301.31ms
step:2287/5100 train_loss:3.5094 train_time:685977ms step_avg:301.26ms
step:2288/5100 train_loss:3.4613 train_time:686173ms step_avg:301.22ms
step:2289/5100 train_loss:3.5993 train_time:686368ms step_avg:301.17ms
step:2290/5100 train_loss:3.5743 train_time:686563ms step_avg:301.12ms
step:2291/5100 train_loss:3.4528 train_time:687795ms step_avg:301.53ms
step:2292/5100 train_loss:3.7984 train_time:687995ms step_avg:301.49ms
step:2293/5100 train_loss:3.4502 train_time:688191ms step_avg:301.44ms
step:2294/5100 train_loss:3.4031 train_time:688385ms step_avg:301.39ms
step:2295/5100 train_loss:3.5878 train_time:688580ms step_avg:301.35ms
step:2296/5100 train_loss:3.5379 train_time:688777ms step_avg:301.30ms
step:2297/5100 train_loss:3.5563 train_time:688971ms step_avg:301.26ms
step:2298/5100 train_loss:3.8878 train_time:689166ms step_avg:301.21ms
step:2299/5100 train_loss:3.4155 train_time:689360ms step_avg:301.16ms
step:2300/5100 train_loss:3.4069 train_time:689555ms step_avg:301.12ms
step:2301/5100 train_loss:3.7486 train_time:690787ms step_avg:301.52ms
step:2302/5100 train_loss:3.4752 train_time:690986ms step_avg:301.48ms
step:2303/5100 train_loss:3.4830 train_time:691182ms step_avg:301.43ms
step:2304/5100 train_loss:3.4709 train_time:691377ms step_avg:301.39ms
step:2305/5100 train_loss:3.4107 train_time:691573ms step_avg:301.34ms
step:2306/5100 train_loss:3.5719 train_time:691767ms step_avg:301.29ms
step:2307/5100 train_loss:3.4334 train_time:691962ms step_avg:301.25ms
step:2308/5100 train_loss:3.4458 train_time:692158ms step_avg:301.20ms
step:2309/5100 train_loss:3.5741 train_time:692352ms step_avg:301.15ms
step:2310/5100 train_loss:3.5344 train_time:692547ms step_avg:301.11ms
step:2311/5100 train_loss:3.4116 train_time:693778ms step_avg:301.51ms
step:2312/5100 train_loss:3.5182 train_time:693978ms step_avg:301.47ms
step:2313/5100 train_loss:3.6474 train_time:694174ms step_avg:301.42ms
step:2314/5100 train_loss:3.4627 train_time:694368ms step_avg:301.38ms
step:2315/5100 train_loss:3.3885 train_time:694562ms step_avg:301.33ms
step:2316/5100 train_loss:3.4810 train_time:694758ms step_avg:301.28ms
step:2317/5100 train_loss:3.3640 train_time:694954ms step_avg:301.24ms
step:2318/5100 train_loss:3.4652 train_time:695149ms step_avg:301.19ms
step:2319/5100 train_loss:3.4859 train_time:695343ms step_avg:301.14ms
step:2320/5100 train_loss:3.3302 train_time:695540ms step_avg:301.10ms
step:2321/5100 train_loss:3.4767 train_time:696771ms step_avg:301.50ms
step:2322/5100 train_loss:3.5253 train_time:696975ms step_avg:301.46ms
step:2323/5100 train_loss:3.4381 train_time:697171ms step_avg:301.41ms
step:2324/5100 train_loss:3.4844 train_time:697366ms step_avg:301.37ms
step:2325/5100 train_loss:3.4022 train_time:697560ms step_avg:301.32ms
step:2326/5100 train_loss:3.5455 train_time:697756ms step_avg:301.28ms
step:2327/5100 train_loss:3.5559 train_time:697952ms step_avg:301.23ms
step:2328/5100 train_loss:3.3260 train_time:698146ms step_avg:301.18ms
step:2329/5100 train_loss:3.4364 train_time:698341ms step_avg:301.14ms
step:2330/5100 train_loss:3.4652 train_time:698537ms step_avg:301.09ms
step:2331/5100 train_loss:3.4336 train_time:699767ms step_avg:301.49ms
step:2332/5100 train_loss:3.6364 train_time:699970ms step_avg:301.45ms
step:2333/5100 train_loss:3.4932 train_time:700165ms step_avg:301.41ms
step:2334/5100 train_loss:3.4745 train_time:700361ms step_avg:301.36ms
step:2335/5100 train_loss:3.5578 train_time:700556ms step_avg:301.31ms
step:2336/5100 train_loss:3.4005 train_time:700750ms step_avg:301.27ms
step:2337/5100 train_loss:3.5521 train_time:700944ms step_avg:301.22ms
step:2338/5100 train_loss:3.5114 train_time:701141ms step_avg:301.18ms
step:2339/5100 train_loss:3.4575 train_time:701335ms step_avg:301.13ms
step:2340/5100 train_loss:3.5288 train_time:701529ms step_avg:301.09ms
step:2341/5100 train_loss:3.5849 train_time:702760ms step_avg:301.48ms
step:2342/5100 train_loss:3.4514 train_time:702961ms step_avg:301.44ms
step:2343/5100 train_loss:3.4608 train_time:703158ms step_avg:301.40ms
step:2344/5100 train_loss:3.5275 train_time:703353ms step_avg:301.35ms
step:2345/5100 train_loss:3.4756 train_time:703548ms step_avg:301.31ms
step:2346/5100 train_loss:3.5949 train_time:703743ms step_avg:301.26ms
step:2347/5100 train_loss:3.4952 train_time:703940ms step_avg:301.22ms
step:2348/5100 train_loss:3.5958 train_time:704135ms step_avg:301.17ms
step:2349/5100 train_loss:3.5617 train_time:704330ms step_avg:301.12ms
step:2350/5100 train_loss:3.6043 train_time:704524ms step_avg:301.08ms
step:2351/5100 train_loss:3.2981 train_time:705754ms step_avg:301.48ms
step:2352/5100 train_loss:3.4195 train_time:705955ms step_avg:301.43ms
step:2353/5100 train_loss:3.4114 train_time:706151ms step_avg:301.39ms
step:2354/5100 train_loss:3.6293 train_time:706346ms step_avg:301.34ms
step:2355/5100 train_loss:3.4260 train_time:706541ms step_avg:301.30ms
step:2356/5100 train_loss:3.4198 train_time:706736ms step_avg:301.25ms
step:2357/5100 train_loss:3.5746 train_time:706930ms step_avg:301.21ms
step:2358/5100 train_loss:3.4211 train_time:707125ms step_avg:301.16ms
step:2359/5100 train_loss:3.5304 train_time:707319ms step_avg:301.12ms
step:2360/5100 train_loss:3.4262 train_time:707515ms step_avg:301.07ms
step:2361/5100 train_loss:3.4389 train_time:708745ms step_avg:301.47ms
step:2362/5100 train_loss:3.4795 train_time:708946ms step_avg:301.42ms
step:2363/5100 train_loss:3.5374 train_time:709142ms step_avg:301.38ms
step:2364/5100 train_loss:3.4774 train_time:709338ms step_avg:301.33ms
step:2365/5100 train_loss:3.9094 train_time:709533ms step_avg:301.29ms
step:2366/5100 train_loss:3.5406 train_time:709728ms step_avg:301.24ms
step:2367/5100 train_loss:3.6873 train_time:709923ms step_avg:301.20ms
step:2368/5100 train_loss:3.5177 train_time:710118ms step_avg:301.15ms
step:2369/5100 train_loss:3.5123 train_time:710313ms step_avg:301.11ms
step:2370/5100 train_loss:3.5504 train_time:710507ms step_avg:301.06ms
step:2371/5100 train_loss:3.4261 train_time:711737ms step_avg:301.46ms
step:2372/5100 train_loss:3.6663 train_time:711941ms step_avg:301.41ms
step:2373/5100 train_loss:3.5081 train_time:712135ms step_avg:301.37ms
step:2374/5100 train_loss:4.0542 train_time:712331ms step_avg:301.32ms
step:2375/5100 train_loss:3.4845 train_time:712525ms step_avg:301.28ms
step:2375/5100 val_loss:3.4935 train_time:712557ms step_avg:301.29ms
step:2376/5100 train_loss:3.3943 train_time:712736ms step_avg:301.24ms
step:2377/5100 train_loss:3.5507 train_time:712935ms step_avg:301.20ms
step:2378/5100 train_loss:3.5204 train_time:713130ms step_avg:301.15ms
step:2379/5100 train_loss:3.5346 train_time:713326ms step_avg:301.11ms
step:2380/5100 train_loss:3.5233 train_time:713521ms step_avg:301.06ms
step:2381/5100 train_loss:3.4171 train_time:714751ms step_avg:301.46ms
step:2382/5100 train_loss:3.5167 train_time:714952ms step_avg:301.41ms
step:2383/5100 train_loss:3.5361 train_time:715148ms step_avg:301.37ms
step:2384/5100 train_loss:3.4819 train_time:715343ms step_avg:301.32ms
step:2385/5100 train_loss:3.4073 train_time:715537ms step_avg:301.28ms
step:2386/5100 train_loss:3.5254 train_time:715732ms step_avg:301.23ms
step:2387/5100 train_loss:3.4824 train_time:715928ms step_avg:301.19ms
step:2388/5100 train_loss:3.4839 train_time:716122ms step_avg:301.14ms
step:2389/5100 train_loss:3.5155 train_time:716317ms step_avg:301.10ms
step:2390/5100 train_loss:3.5030 train_time:716512ms step_avg:301.06ms
step:2391/5100 train_loss:3.5003 train_time:717743ms step_avg:301.45ms
step:2392/5100 train_loss:3.3786 train_time:717945ms step_avg:301.40ms
step:2393/5100 train_loss:3.5935 train_time:718139ms step_avg:301.36ms
step:2394/5100 train_loss:3.4393 train_time:718333ms step_avg:301.31ms
step:2395/5100 train_loss:3.5360 train_time:718528ms step_avg:301.27ms
step:2396/5100 train_loss:3.6482 train_time:718723ms step_avg:301.23ms
step:2397/5100 train_loss:3.6626 train_time:718917ms step_avg:301.18ms
step:2398/5100 train_loss:3.6119 train_time:719112ms step_avg:301.14ms
step:2399/5100 train_loss:3.5748 train_time:719308ms step_avg:301.09ms
step:2400/5100 train_loss:3.4552 train_time:719504ms step_avg:301.05ms
step:2401/5100 train_loss:3.4591 train_time:720736ms step_avg:301.44ms
step:2402/5100 train_loss:3.5664 train_time:720937ms step_avg:301.40ms
step:2403/5100 train_loss:3.3993 train_time:721132ms step_avg:301.35ms
step:2404/5100 train_loss:3.5297 train_time:721327ms step_avg:301.31ms
step:2405/5100 train_loss:3.7456 train_time:721523ms step_avg:301.26ms
step:2406/5100 train_loss:3.4702 train_time:721719ms step_avg:301.22ms
step:2407/5100 train_loss:3.6286 train_time:721913ms step_avg:301.17ms
step:2408/5100 train_loss:3.4836 train_time:722108ms step_avg:301.13ms
step:2409/5100 train_loss:3.4143 train_time:722302ms step_avg:301.08ms
step:2410/5100 train_loss:3.5512 train_time:722496ms step_avg:301.04ms
step:2411/5100 train_loss:3.3398 train_time:723727ms step_avg:301.43ms
step:2412/5100 train_loss:3.7686 train_time:723927ms step_avg:301.39ms
step:2413/5100 train_loss:3.4589 train_time:724123ms step_avg:301.34ms
step:2414/5100 train_loss:3.5312 train_time:724317ms step_avg:301.30ms
step:2415/5100 train_loss:3.4566 train_time:724513ms step_avg:301.25ms
step:2416/5100 train_loss:3.5240 train_time:724708ms step_avg:301.21ms
step:2417/5100 train_loss:3.3339 train_time:724903ms step_avg:301.16ms
step:2418/5100 train_loss:3.2701 train_time:725097ms step_avg:301.12ms
step:2419/5100 train_loss:3.5646 train_time:725292ms step_avg:301.08ms
step:2420/5100 train_loss:3.4479 train_time:725487ms step_avg:301.03ms
step:2421/5100 train_loss:3.4809 train_time:726718ms step_avg:301.42ms
step:2422/5100 train_loss:3.5746 train_time:726918ms step_avg:301.38ms
step:2423/5100 train_loss:3.6276 train_time:727113ms step_avg:301.33ms
step:2424/5100 train_loss:3.4438 train_time:727308ms step_avg:301.29ms
step:2425/5100 train_loss:3.5330 train_time:727503ms step_avg:301.24ms
step:2426/5100 train_loss:3.5336 train_time:727698ms step_avg:301.20ms
step:2427/5100 train_loss:3.4624 train_time:727892ms step_avg:301.16ms
step:2428/5100 train_loss:3.4107 train_time:728088ms step_avg:301.11ms
step:2429/5100 train_loss:3.5375 train_time:728283ms step_avg:301.07ms
step:2430/5100 train_loss:3.4352 train_time:728478ms step_avg:301.02ms
step:2431/5100 train_loss:3.4867 train_time:729708ms step_avg:301.41ms
step:2432/5100 train_loss:3.5484 train_time:729909ms step_avg:301.37ms
step:2433/5100 train_loss:3.5082 train_time:730104ms step_avg:301.32ms
step:2434/5100 train_loss:3.3877 train_time:730298ms step_avg:301.28ms
step:2435/5100 train_loss:3.3445 train_time:730492ms step_avg:301.23ms
step:2436/5100 train_loss:3.5149 train_time:730689ms step_avg:301.19ms
step:2437/5100 train_loss:3.3704 train_time:730884ms step_avg:301.15ms
step:2438/5100 train_loss:3.4499 train_time:731079ms step_avg:301.10ms
step:2439/5100 train_loss:3.5342 train_time:731274ms step_avg:301.06ms
step:2440/5100 train_loss:3.4587 train_time:731469ms step_avg:301.02ms
step:2441/5100 train_loss:3.5459 train_time:732701ms step_avg:301.40ms
step:2442/5100 train_loss:3.4320 train_time:732903ms step_avg:301.36ms
step:2443/5100 train_loss:3.4954 train_time:733098ms step_avg:301.31ms
step:2444/5100 train_loss:3.3722 train_time:733293ms step_avg:301.27ms
step:2445/5100 train_loss:3.3778 train_time:733488ms step_avg:301.23ms
step:2446/5100 train_loss:3.5508 train_time:733684ms step_avg:301.18ms
step:2447/5100 train_loss:3.4120 train_time:733879ms step_avg:301.14ms
step:2448/5100 train_loss:3.4875 train_time:734073ms step_avg:301.10ms
step:2449/5100 train_loss:3.6402 train_time:734268ms step_avg:301.05ms
step:2450/5100 train_loss:3.4761 train_time:734463ms step_avg:301.01ms
step:2451/5100 train_loss:3.5478 train_time:735694ms step_avg:301.39ms
step:2452/5100 train_loss:3.4497 train_time:735894ms step_avg:301.35ms
step:2453/5100 train_loss:3.5494 train_time:736089ms step_avg:301.31ms
step:2454/5100 train_loss:3.4435 train_time:736285ms step_avg:301.26ms
step:2455/5100 train_loss:3.5763 train_time:736479ms step_avg:301.22ms
step:2456/5100 train_loss:3.5064 train_time:736673ms step_avg:301.17ms
step:2457/5100 train_loss:3.4285 train_time:737012ms step_avg:301.19ms
step:2458/5100 train_loss:3.3575 train_time:737207ms step_avg:301.15ms
step:2459/5100 train_loss:3.4847 train_time:737402ms step_avg:301.10ms
step:2460/5100 train_loss:4.0934 train_time:737596ms step_avg:301.06ms
step:2461/5100 train_loss:3.5532 train_time:738827ms step_avg:301.44ms
step:2462/5100 train_loss:3.3652 train_time:739027ms step_avg:301.40ms
step:2463/5100 train_loss:3.5641 train_time:739223ms step_avg:301.35ms
step:2464/5100 train_loss:3.4768 train_time:739418ms step_avg:301.31ms
step:2465/5100 train_loss:3.6771 train_time:739612ms step_avg:301.27ms
step:2466/5100 train_loss:3.8778 train_time:739809ms step_avg:301.23ms
step:2467/5100 train_loss:3.5873 train_time:740003ms step_avg:301.18ms
step:2468/5100 train_loss:3.4638 train_time:740197ms step_avg:301.14ms
step:2469/5100 train_loss:3.5814 train_time:740392ms step_avg:301.09ms
step:2470/5100 train_loss:3.5954 train_time:740756ms step_avg:301.12ms
step:2471/5100 train_loss:3.3975 train_time:741986ms step_avg:301.50ms
step:2472/5100 train_loss:3.4843 train_time:742187ms step_avg:301.46ms
step:2473/5100 train_loss:3.4827 train_time:742383ms step_avg:301.41ms
step:2474/5100 train_loss:3.6335 train_time:742579ms step_avg:301.37ms
step:2475/5100 train_loss:3.7541 train_time:742773ms step_avg:301.33ms
step:2476/5100 train_loss:3.3562 train_time:742970ms step_avg:301.29ms
step:2477/5100 train_loss:3.5549 train_time:743164ms step_avg:301.24ms
step:2478/5100 train_loss:3.5171 train_time:743359ms step_avg:301.20ms
step:2479/5100 train_loss:3.3622 train_time:743554ms step_avg:301.16ms
step:2480/5100 train_loss:3.3496 train_time:743748ms step_avg:301.11ms
step:2481/5100 train_loss:3.5009 train_time:744980ms step_avg:301.49ms
step:2482/5100 train_loss:3.5187 train_time:745183ms step_avg:301.45ms
step:2483/5100 train_loss:3.5275 train_time:745378ms step_avg:301.41ms
step:2484/5100 train_loss:3.4839 train_time:745573ms step_avg:301.36ms
step:2485/5100 train_loss:3.4929 train_time:745768ms step_avg:301.32ms
step:2486/5100 train_loss:3.3768 train_time:745963ms step_avg:301.28ms
step:2487/5100 train_loss:3.5759 train_time:746158ms step_avg:301.23ms
step:2488/5100 train_loss:3.5341 train_time:746353ms step_avg:301.19ms
step:2489/5100 train_loss:3.4348 train_time:746548ms step_avg:301.15ms
step:2490/5100 train_loss:3.5551 train_time:746743ms step_avg:301.11ms
step:2491/5100 train_loss:3.6005 train_time:747975ms step_avg:301.48ms
step:2492/5100 train_loss:3.6791 train_time:748177ms step_avg:301.44ms
step:2493/5100 train_loss:3.5323 train_time:748372ms step_avg:301.40ms
step:2494/5100 train_loss:3.4545 train_time:748568ms step_avg:301.36ms
step:2495/5100 train_loss:3.5877 train_time:748763ms step_avg:301.31ms
step:2496/5100 train_loss:3.5255 train_time:748958ms step_avg:301.27ms
step:2497/5100 train_loss:3.4389 train_time:749152ms step_avg:301.23ms
step:2498/5100 train_loss:3.5338 train_time:749347ms step_avg:301.18ms
step:2499/5100 train_loss:3.5832 train_time:749542ms step_avg:301.14ms
step:2500/5100 train_loss:3.6078 train_time:749736ms step_avg:301.10ms
step:2500/5100 val_loss:3.4840 train_time:749769ms step_avg:301.11ms
step:2501/5100 train_loss:3.5549 train_time:750988ms step_avg:301.48ms
step:2502/5100 train_loss:3.5095 train_time:751187ms step_avg:301.44ms
step:2503/5100 train_loss:3.5252 train_time:751383ms step_avg:301.40ms
step:2504/5100 train_loss:3.3907 train_time:751578ms step_avg:301.35ms
step:2505/5100 train_loss:3.5896 train_time:751773ms step_avg:301.31ms
step:2506/5100 train_loss:3.5384 train_time:751968ms step_avg:301.27ms
step:2507/5100 train_loss:3.4793 train_time:752164ms step_avg:301.23ms
step:2508/5100 train_loss:3.4897 train_time:752360ms step_avg:301.19ms
step:2509/5100 train_loss:3.4558 train_time:752555ms step_avg:301.14ms
step:2510/5100 train_loss:3.5977 train_time:752750ms step_avg:301.10ms
step:2511/5100 train_loss:3.4472 train_time:753981ms step_avg:301.47ms
step:2512/5100 train_loss:3.4414 train_time:754183ms step_avg:301.43ms
step:2513/5100 train_loss:3.5111 train_time:754378ms step_avg:301.39ms
step:2514/5100 train_loss:3.5473 train_time:754573ms step_avg:301.35ms
step:2515/5100 train_loss:3.4411 train_time:754767ms step_avg:301.30ms
step:2516/5100 train_loss:3.5358 train_time:754964ms step_avg:301.26ms
step:2517/5100 train_loss:3.5298 train_time:755159ms step_avg:301.22ms
step:2518/5100 train_loss:3.4045 train_time:755353ms step_avg:301.18ms
step:2519/5100 train_loss:3.4310 train_time:755547ms step_avg:301.13ms
step:2520/5100 train_loss:3.5575 train_time:755742ms step_avg:301.09ms
step:2521/5100 train_loss:3.5463 train_time:756973ms step_avg:301.46ms
step:2522/5100 train_loss:3.4312 train_time:757175ms step_avg:301.42ms
step:2523/5100 train_loss:3.4103 train_time:757369ms step_avg:301.38ms
step:2524/5100 train_loss:3.5102 train_time:757564ms step_avg:301.34ms
step:2525/5100 train_loss:3.3478 train_time:757760ms step_avg:301.30ms
step:2526/5100 train_loss:3.5727 train_time:757955ms step_avg:301.25ms
step:2527/5100 train_loss:3.4828 train_time:758149ms step_avg:301.21ms
step:2528/5100 train_loss:3.4816 train_time:758342ms step_avg:301.17ms
step:2529/5100 train_loss:3.4645 train_time:758538ms step_avg:301.13ms
step:2530/5100 train_loss:3.4944 train_time:758732ms step_avg:301.08ms
step:2531/5100 train_loss:3.5269 train_time:759961ms step_avg:301.45ms
step:2532/5100 train_loss:3.3468 train_time:760165ms step_avg:301.41ms
step:2533/5100 train_loss:3.5095 train_time:760359ms step_avg:301.37ms
step:2534/5100 train_loss:3.4084 train_time:760554ms step_avg:301.33ms
step:2535/5100 train_loss:3.4349 train_time:760749ms step_avg:301.29ms
step:2536/5100 train_loss:3.4937 train_time:760943ms step_avg:301.24ms
step:2537/5100 train_loss:3.5036 train_time:761138ms step_avg:301.20ms
step:2538/5100 train_loss:3.3301 train_time:761333ms step_avg:301.16ms
step:2539/5100 train_loss:3.6376 train_time:761527ms step_avg:301.12ms
step:2540/5100 train_loss:3.3204 train_time:761724ms step_avg:301.08ms
step:2541/5100 train_loss:3.5036 train_time:762955ms step_avg:301.44ms
step:2542/5100 train_loss:3.2770 train_time:763155ms step_avg:301.40ms
step:2543/5100 train_loss:3.7049 train_time:763350ms step_avg:301.36ms
step:2544/5100 train_loss:3.4781 train_time:763545ms step_avg:301.32ms
step:2545/5100 train_loss:3.6341 train_time:763740ms step_avg:301.28ms
step:2546/5100 train_loss:3.4665 train_time:763935ms step_avg:301.24ms
step:2547/5100 train_loss:3.4519 train_time:764129ms step_avg:301.19ms
step:2548/5100 train_loss:3.4592 train_time:764324ms step_avg:301.15ms
step:2549/5100 train_loss:3.6181 train_time:764518ms step_avg:301.11ms
step:2550/5100 train_loss:3.4712 train_time:764713ms step_avg:301.07ms
step:2551/5100 train_loss:3.4710 train_time:765943ms step_avg:301.43ms
step:2552/5100 train_loss:3.5064 train_time:766145ms step_avg:301.39ms
step:2553/5100 train_loss:3.5197 train_time:766340ms step_avg:301.35ms
step:2554/5100 train_loss:3.4358 train_time:766535ms step_avg:301.31ms
step:2555/5100 train_loss:3.5363 train_time:766729ms step_avg:301.27ms
step:2556/5100 train_loss:3.5971 train_time:766924ms step_avg:301.23ms
step:2557/5100 train_loss:3.5859 train_time:767119ms step_avg:301.19ms
step:2558/5100 train_loss:3.4250 train_time:767313ms step_avg:301.14ms
step:2559/5100 train_loss:3.4208 train_time:767507ms step_avg:301.10ms
step:2560/5100 train_loss:3.4373 train_time:767703ms step_avg:301.06ms
step:2561/5100 train_loss:3.5564 train_time:768935ms step_avg:301.43ms
step:2562/5100 train_loss:3.5956 train_time:769137ms step_avg:301.39ms
step:2563/5100 train_loss:3.4739 train_time:769332ms step_avg:301.34ms
step:2564/5100 train_loss:3.5068 train_time:769526ms step_avg:301.30ms
step:2565/5100 train_loss:3.4189 train_time:769722ms step_avg:301.26ms
step:2566/5100 train_loss:3.4339 train_time:769916ms step_avg:301.22ms
step:2567/5100 train_loss:3.4268 train_time:770110ms step_avg:301.18ms
step:2568/5100 train_loss:3.4772 train_time:770305ms step_avg:301.14ms
step:2569/5100 train_loss:3.6177 train_time:770501ms step_avg:301.09ms
step:2570/5100 train_loss:3.5210 train_time:770696ms step_avg:301.05ms
step:2571/5100 train_loss:3.6025 train_time:771926ms step_avg:301.42ms
step:2572/5100 train_loss:3.3586 train_time:772127ms step_avg:301.38ms
step:2573/5100 train_loss:3.4665 train_time:772324ms step_avg:301.34ms
step:2574/5100 train_loss:3.1392 train_time:772519ms step_avg:301.29ms
step:2575/5100 train_loss:3.3797 train_time:772713ms step_avg:301.25ms
step:2576/5100 train_loss:3.3122 train_time:772908ms step_avg:301.21ms
step:2577/5100 train_loss:3.4280 train_time:773104ms step_avg:301.17ms
step:2578/5100 train_loss:3.4852 train_time:773299ms step_avg:301.13ms
step:2579/5100 train_loss:3.3931 train_time:773494ms step_avg:301.09ms
step:2580/5100 train_loss:3.4452 train_time:773688ms step_avg:301.05ms
step:2581/5100 train_loss:3.4030 train_time:774920ms step_avg:301.41ms
step:2582/5100 train_loss:3.4996 train_time:775121ms step_avg:301.37ms
step:2583/5100 train_loss:3.3757 train_time:775316ms step_avg:301.33ms
step:2584/5100 train_loss:3.5674 train_time:775511ms step_avg:301.29ms
step:2585/5100 train_loss:3.4875 train_time:775706ms step_avg:301.25ms
step:2586/5100 train_loss:3.4978 train_time:775902ms step_avg:301.20ms
step:2587/5100 train_loss:3.6230 train_time:776097ms step_avg:301.16ms
step:2588/5100 train_loss:3.5099 train_time:776293ms step_avg:301.12ms
step:2589/5100 train_loss:3.3655 train_time:776488ms step_avg:301.08ms
step:2590/5100 train_loss:3.5398 train_time:776683ms step_avg:301.04ms
step:2591/5100 train_loss:3.4388 train_time:777914ms step_avg:301.40ms
step:2592/5100 train_loss:3.6488 train_time:778116ms step_avg:301.36ms
step:2593/5100 train_loss:3.5225 train_time:778312ms step_avg:301.32ms
step:2594/5100 train_loss:3.3401 train_time:778506ms step_avg:301.28ms
step:2595/5100 train_loss:3.4095 train_time:778701ms step_avg:301.24ms
step:2596/5100 train_loss:3.8597 train_time:778895ms step_avg:301.20ms
step:2597/5100 train_loss:3.4973 train_time:779090ms step_avg:301.16ms
step:2598/5100 train_loss:3.4937 train_time:779284ms step_avg:301.11ms
step:2599/5100 train_loss:3.3551 train_time:779481ms step_avg:301.07ms
step:2600/5100 train_loss:3.6024 train_time:779675ms step_avg:301.03ms
step:2601/5100 train_loss:3.7590 train_time:780906ms step_avg:301.39ms
step:2602/5100 train_loss:3.3384 train_time:781108ms step_avg:301.35ms
step:2603/5100 train_loss:3.4816 train_time:781304ms step_avg:301.31ms
step:2604/5100 train_loss:3.3109 train_time:781499ms step_avg:301.27ms
step:2605/5100 train_loss:3.6012 train_time:781694ms step_avg:301.23ms
step:2606/5100 train_loss:3.4771 train_time:781889ms step_avg:301.19ms
step:2607/5100 train_loss:3.3792 train_time:782085ms step_avg:301.15ms
step:2608/5100 train_loss:3.3272 train_time:782280ms step_avg:301.11ms
step:2609/5100 train_loss:3.4456 train_time:782475ms step_avg:301.07ms
step:2610/5100 train_loss:3.6259 train_time:782670ms step_avg:301.03ms
step:2611/5100 train_loss:3.4947 train_time:783902ms step_avg:301.38ms
step:2612/5100 train_loss:3.3185 train_time:784102ms step_avg:301.35ms
step:2613/5100 train_loss:3.4216 train_time:784296ms step_avg:301.30ms
step:2614/5100 train_loss:3.5352 train_time:784492ms step_avg:301.26ms
step:2615/5100 train_loss:3.4643 train_time:784686ms step_avg:301.22ms
step:2616/5100 train_loss:3.4568 train_time:784882ms step_avg:301.18ms
step:2617/5100 train_loss:3.5018 train_time:785077ms step_avg:301.14ms
step:2618/5100 train_loss:3.5485 train_time:785271ms step_avg:301.10ms
step:2619/5100 train_loss:3.3900 train_time:785466ms step_avg:301.06ms
step:2620/5100 train_loss:3.5690 train_time:785663ms step_avg:301.02ms
step:2621/5100 train_loss:3.5331 train_time:786894ms step_avg:301.38ms
step:2622/5100 train_loss:3.6545 train_time:787094ms step_avg:301.34ms
step:2623/5100 train_loss:3.5608 train_time:787288ms step_avg:301.30ms
step:2624/5100 train_loss:3.4847 train_time:787483ms step_avg:301.26ms
step:2625/5100 train_loss:3.4430 train_time:787679ms step_avg:301.22ms
step:2625/5100 val_loss:3.4728 train_time:787711ms step_avg:301.23ms
step:2626/5100 train_loss:3.4656 train_time:787893ms step_avg:301.18ms
step:2627/5100 train_loss:3.5228 train_time:788089ms step_avg:301.14ms
step:2628/5100 train_loss:3.3538 train_time:788284ms step_avg:301.10ms
step:2629/5100 train_loss:3.6063 train_time:788480ms step_avg:301.06ms
step:2630/5100 train_loss:3.4936 train_time:788674ms step_avg:301.02ms
step:2631/5100 train_loss:3.5473 train_time:789906ms step_avg:301.38ms
step:2632/5100 train_loss:3.7796 train_time:790108ms step_avg:301.34ms
step:2633/5100 train_loss:3.5170 train_time:790304ms step_avg:301.30ms
step:2634/5100 train_loss:3.4330 train_time:790499ms step_avg:301.26ms
step:2635/5100 train_loss:3.4065 train_time:790693ms step_avg:301.22ms
step:2636/5100 train_loss:3.4541 train_time:790890ms step_avg:301.18ms
step:2637/5100 train_loss:3.2364 train_time:791085ms step_avg:301.14ms
step:2638/5100 train_loss:3.5472 train_time:791279ms step_avg:301.10ms
step:2639/5100 train_loss:3.5186 train_time:791474ms step_avg:301.06ms
step:2640/5100 train_loss:3.4274 train_time:791669ms step_avg:301.01ms
step:2641/5100 train_loss:3.5018 train_time:792899ms step_avg:301.37ms
step:2642/5100 train_loss:3.5388 train_time:793102ms step_avg:301.33ms
step:2643/5100 train_loss:3.3264 train_time:793297ms step_avg:301.29ms
step:2644/5100 train_loss:3.4489 train_time:793492ms step_avg:301.25ms
step:2645/5100 train_loss:3.5147 train_time:793688ms step_avg:301.21ms
step:2646/5100 train_loss:3.4842 train_time:794029ms step_avg:301.23ms
step:2647/5100 train_loss:3.3728 train_time:794224ms step_avg:301.18ms
step:2648/5100 train_loss:3.6046 train_time:794418ms step_avg:301.14ms
step:2649/5100 train_loss:3.8525 train_time:794612ms step_avg:301.10ms
step:2650/5100 train_loss:3.4865 train_time:794808ms step_avg:301.06ms
step:2651/5100 train_loss:3.4540 train_time:796039ms step_avg:301.42ms
step:2652/5100 train_loss:3.5898 train_time:796239ms step_avg:301.38ms
step:2653/5100 train_loss:3.4315 train_time:796433ms step_avg:301.34ms
step:2654/5100 train_loss:3.4114 train_time:796628ms step_avg:301.30ms
step:2655/5100 train_loss:3.4827 train_time:796823ms step_avg:301.26ms
step:2656/5100 train_loss:3.3981 train_time:797017ms step_avg:301.22ms
step:2657/5100 train_loss:3.4369 train_time:797212ms step_avg:301.18ms
step:2658/5100 train_loss:3.4038 train_time:797407ms step_avg:301.14ms
step:2659/5100 train_loss:3.4917 train_time:797604ms step_avg:301.10ms
step:2660/5100 train_loss:3.6328 train_time:797967ms step_avg:301.12ms
step:2661/5100 train_loss:3.4334 train_time:799197ms step_avg:301.47ms
step:2662/5100 train_loss:3.5825 train_time:799398ms step_avg:301.43ms
step:2663/5100 train_loss:3.4418 train_time:799593ms step_avg:301.39ms
step:2664/5100 train_loss:3.4397 train_time:799789ms step_avg:301.35ms
step:2665/5100 train_loss:3.3722 train_time:799984ms step_avg:301.31ms
step:2666/5100 train_loss:3.4187 train_time:800178ms step_avg:301.27ms
step:2667/5100 train_loss:3.4582 train_time:800373ms step_avg:301.23ms
step:2668/5100 train_loss:3.4990 train_time:800568ms step_avg:301.19ms
step:2669/5100 train_loss:3.4178 train_time:800762ms step_avg:301.15ms
step:2670/5100 train_loss:3.4744 train_time:800956ms step_avg:301.11ms
step:2671/5100 train_loss:3.3618 train_time:802187ms step_avg:301.46ms
step:2672/5100 train_loss:3.4363 train_time:802387ms step_avg:301.42ms
step:2673/5100 train_loss:3.4169 train_time:802583ms step_avg:301.38ms
step:2674/5100 train_loss:3.4768 train_time:802778ms step_avg:301.34ms
step:2675/5100 train_loss:3.5028 train_time:802973ms step_avg:301.30ms
step:2676/5100 train_loss:3.4681 train_time:803168ms step_avg:301.26ms
step:2677/5100 train_loss:3.4609 train_time:803363ms step_avg:301.22ms
step:2678/5100 train_loss:3.4964 train_time:803557ms step_avg:301.18ms
step:2679/5100 train_loss:3.5401 train_time:803752ms step_avg:301.14ms
step:2680/5100 train_loss:3.4514 train_time:803948ms step_avg:301.10ms
step:2681/5100 train_loss:3.3725 train_time:805179ms step_avg:301.45ms
step:2682/5100 train_loss:3.4180 train_time:805380ms step_avg:301.41ms
step:2683/5100 train_loss:3.8878 train_time:805575ms step_avg:301.37ms
step:2684/5100 train_loss:3.4768 train_time:805770ms step_avg:301.34ms
step:2685/5100 train_loss:3.5061 train_time:805965ms step_avg:301.30ms
step:2686/5100 train_loss:3.5520 train_time:806158ms step_avg:301.26ms
step:2687/5100 train_loss:3.4665 train_time:806354ms step_avg:301.22ms
step:2688/5100 train_loss:3.5535 train_time:806549ms step_avg:301.18ms
step:2689/5100 train_loss:3.4737 train_time:806745ms step_avg:301.14ms
step:2690/5100 train_loss:3.4685 train_time:806938ms step_avg:301.10ms
step:2691/5100 train_loss:3.4956 train_time:808168ms step_avg:301.44ms
step:2692/5100 train_loss:3.5673 train_time:808372ms step_avg:301.41ms
step:2693/5100 train_loss:3.3702 train_time:808568ms step_avg:301.37ms
step:2694/5100 train_loss:3.7429 train_time:808763ms step_avg:301.33ms
step:2695/5100 train_loss:3.5477 train_time:808957ms step_avg:301.29ms
step:2696/5100 train_loss:3.3687 train_time:809151ms step_avg:301.25ms
step:2697/5100 train_loss:3.5286 train_time:809346ms step_avg:301.21ms
step:2698/5100 train_loss:3.4915 train_time:809541ms step_avg:301.17ms
step:2699/5100 train_loss:3.4407 train_time:809735ms step_avg:301.13ms
step:2700/5100 train_loss:3.5476 train_time:809931ms step_avg:301.09ms
step:2701/5100 train_loss:3.5113 train_time:811161ms step_avg:301.43ms
step:2702/5100 train_loss:3.4200 train_time:811363ms step_avg:301.40ms
step:2703/5100 train_loss:3.4490 train_time:811559ms step_avg:301.36ms
step:2704/5100 train_loss:3.4601 train_time:811753ms step_avg:301.32ms
step:2705/5100 train_loss:3.4187 train_time:811948ms step_avg:301.28ms
step:2706/5100 train_loss:3.6092 train_time:812144ms step_avg:301.24ms
step:2707/5100 train_loss:3.5592 train_time:812338ms step_avg:301.20ms
step:2708/5100 train_loss:3.4709 train_time:812533ms step_avg:301.16ms
step:2709/5100 train_loss:3.4592 train_time:812727ms step_avg:301.12ms
step:2710/5100 train_loss:3.5643 train_time:812922ms step_avg:301.08ms
step:2711/5100 train_loss:3.4442 train_time:814151ms step_avg:301.43ms
step:2712/5100 train_loss:3.5557 train_time:814354ms step_avg:301.39ms
step:2713/5100 train_loss:3.2962 train_time:814549ms step_avg:301.35ms
step:2714/5100 train_loss:3.4929 train_time:814744ms step_avg:301.31ms
step:2715/5100 train_loss:3.3843 train_time:814939ms step_avg:301.27ms
step:2716/5100 train_loss:3.3899 train_time:815134ms step_avg:301.23ms
step:2717/5100 train_loss:3.5771 train_time:815329ms step_avg:301.19ms
step:2718/5100 train_loss:3.4823 train_time:815524ms step_avg:301.15ms
step:2719/5100 train_loss:3.7098 train_time:815718ms step_avg:301.11ms
step:2720/5100 train_loss:3.4515 train_time:815912ms step_avg:301.07ms
step:2721/5100 train_loss:3.4534 train_time:817143ms step_avg:301.42ms
step:2722/5100 train_loss:3.6791 train_time:817346ms step_avg:301.38ms
step:2723/5100 train_loss:3.4436 train_time:817541ms step_avg:301.34ms
step:2724/5100 train_loss:3.6309 train_time:817736ms step_avg:301.30ms
step:2725/5100 train_loss:3.4944 train_time:817931ms step_avg:301.26ms
step:2726/5100 train_loss:3.4593 train_time:818126ms step_avg:301.22ms
step:2727/5100 train_loss:3.4608 train_time:818321ms step_avg:301.19ms
step:2728/5100 train_loss:3.8088 train_time:818516ms step_avg:301.15ms
step:2729/5100 train_loss:3.5334 train_time:818711ms step_avg:301.11ms
step:2730/5100 train_loss:3.4099 train_time:818906ms step_avg:301.07ms
step:2731/5100 train_loss:3.5090 train_time:820137ms step_avg:301.41ms
step:2732/5100 train_loss:3.4194 train_time:820339ms step_avg:301.37ms
step:2733/5100 train_loss:3.3096 train_time:820534ms step_avg:301.33ms
step:2734/5100 train_loss:3.4162 train_time:820728ms step_avg:301.30ms
step:2735/5100 train_loss:3.4937 train_time:820924ms step_avg:301.26ms
step:2736/5100 train_loss:3.3892 train_time:821118ms step_avg:301.22ms
step:2737/5100 train_loss:3.7910 train_time:821312ms step_avg:301.18ms
step:2738/5100 train_loss:3.5292 train_time:821507ms step_avg:301.14ms
step:2739/5100 train_loss:3.7276 train_time:821702ms step_avg:301.10ms
step:2740/5100 train_loss:3.4745 train_time:821897ms step_avg:301.06ms
step:2741/5100 train_loss:3.4781 train_time:823128ms step_avg:301.40ms
step:2742/5100 train_loss:3.4096 train_time:823329ms step_avg:301.37ms
step:2743/5100 train_loss:3.4791 train_time:823525ms step_avg:301.33ms
step:2744/5100 train_loss:3.4995 train_time:823720ms step_avg:301.29ms
step:2745/5100 train_loss:3.6034 train_time:823915ms step_avg:301.25ms
step:2746/5100 train_loss:3.3601 train_time:824110ms step_avg:301.21ms
step:2747/5100 train_loss:3.4565 train_time:824305ms step_avg:301.17ms
step:2748/5100 train_loss:3.4962 train_time:824499ms step_avg:301.13ms
step:2749/5100 train_loss:3.6119 train_time:824693ms step_avg:301.09ms
step:2750/5100 train_loss:3.4462 train_time:824889ms step_avg:301.05ms
step:2750/5100 val_loss:3.4661 train_time:824921ms step_avg:301.07ms
step:2751/5100 train_loss:3.5151 train_time:826136ms step_avg:301.40ms
step:2752/5100 train_loss:3.5767 train_time:826341ms step_avg:301.36ms
step:2753/5100 train_loss:3.4864 train_time:826537ms step_avg:301.33ms
step:2754/5100 train_loss:3.4119 train_time:826731ms step_avg:301.29ms
step:2755/5100 train_loss:3.4107 train_time:826925ms step_avg:301.25ms
step:2756/5100 train_loss:3.5002 train_time:827120ms step_avg:301.21ms
step:2757/5100 train_loss:3.4381 train_time:827317ms step_avg:301.17ms
step:2758/5100 train_loss:3.3118 train_time:827512ms step_avg:301.13ms
step:2759/5100 train_loss:3.7067 train_time:827706ms step_avg:301.09ms
step:2760/5100 train_loss:3.5145 train_time:827901ms step_avg:301.05ms
step:2761/5100 train_loss:3.4750 train_time:829131ms step_avg:301.39ms
step:2762/5100 train_loss:3.4488 train_time:829333ms step_avg:301.36ms
step:2763/5100 train_loss:3.3723 train_time:829528ms step_avg:301.32ms
step:2764/5100 train_loss:3.5307 train_time:829722ms step_avg:301.28ms
step:2765/5100 train_loss:3.4554 train_time:829917ms step_avg:301.24ms
step:2766/5100 train_loss:3.3513 train_time:830113ms step_avg:301.20ms
step:2767/5100 train_loss:3.4399 train_time:830306ms step_avg:301.16ms
step:2768/5100 train_loss:3.5200 train_time:830500ms step_avg:301.12ms
step:2769/5100 train_loss:3.4033 train_time:830695ms step_avg:301.09ms
step:2770/5100 train_loss:3.4749 train_time:830889ms step_avg:301.05ms
step:2771/5100 train_loss:3.4544 train_time:832119ms step_avg:301.38ms
step:2772/5100 train_loss:3.8943 train_time:832321ms step_avg:301.35ms
step:2773/5100 train_loss:3.3619 train_time:832516ms step_avg:301.31ms
step:2774/5100 train_loss:3.4937 train_time:832712ms step_avg:301.27ms
step:2775/5100 train_loss:3.5575 train_time:832906ms step_avg:301.23ms
step:2776/5100 train_loss:3.5220 train_time:833102ms step_avg:301.19ms
step:2777/5100 train_loss:3.6020 train_time:833298ms step_avg:301.16ms
step:2778/5100 train_loss:3.6108 train_time:833492ms step_avg:301.12ms
step:2779/5100 train_loss:3.4680 train_time:833687ms step_avg:301.08ms
step:2780/5100 train_loss:3.3390 train_time:833883ms step_avg:301.04ms
step:2781/5100 train_loss:3.4864 train_time:835115ms step_avg:301.38ms
step:2782/5100 train_loss:3.5109 train_time:835315ms step_avg:301.34ms
step:2783/5100 train_loss:3.3684 train_time:835511ms step_avg:301.30ms
step:2784/5100 train_loss:3.4891 train_time:835705ms step_avg:301.26ms
step:2785/5100 train_loss:3.5391 train_time:835900ms step_avg:301.23ms
step:2786/5100 train_loss:3.4107 train_time:836095ms step_avg:301.19ms
step:2787/5100 train_loss:3.5457 train_time:836290ms step_avg:301.15ms
step:2788/5100 train_loss:3.4966 train_time:836484ms step_avg:301.11ms
step:2789/5100 train_loss:3.4379 train_time:836681ms step_avg:301.07ms
step:2790/5100 train_loss:3.5130 train_time:836875ms step_avg:301.03ms
step:2791/5100 train_loss:3.4434 train_time:838107ms step_avg:301.37ms
step:2792/5100 train_loss:3.3464 train_time:838307ms step_avg:301.33ms
step:2793/5100 train_loss:3.4468 train_time:838503ms step_avg:301.29ms
step:2794/5100 train_loss:3.4852 train_time:838700ms step_avg:301.26ms
step:2795/5100 train_loss:3.4029 train_time:838895ms step_avg:301.22ms
step:2796/5100 train_loss:3.4413 train_time:839090ms step_avg:301.18ms
step:2797/5100 train_loss:3.3630 train_time:839284ms step_avg:301.14ms
step:2798/5100 train_loss:3.4671 train_time:839479ms step_avg:301.10ms
step:2799/5100 train_loss:3.4261 train_time:839674ms step_avg:301.07ms
step:2800/5100 train_loss:3.5975 train_time:839868ms step_avg:301.03ms
step:2801/5100 train_loss:3.5383 train_time:841099ms step_avg:301.36ms
step:2802/5100 train_loss:3.5077 train_time:841299ms step_avg:301.33ms
step:2803/5100 train_loss:3.4557 train_time:841495ms step_avg:301.29ms
step:2804/5100 train_loss:3.6394 train_time:841689ms step_avg:301.25ms
step:2805/5100 train_loss:3.6026 train_time:841885ms step_avg:301.21ms
step:2806/5100 train_loss:3.3284 train_time:842081ms step_avg:301.17ms
step:2807/5100 train_loss:3.7322 train_time:842276ms step_avg:301.14ms
step:2808/5100 train_loss:3.4783 train_time:842470ms step_avg:301.10ms
step:2809/5100 train_loss:3.4006 train_time:842665ms step_avg:301.06ms
step:2810/5100 train_loss:3.4331 train_time:842860ms step_avg:301.02ms
step:2811/5100 train_loss:3.5848 train_time:844091ms step_avg:301.35ms
step:2812/5100 train_loss:3.5738 train_time:844292ms step_avg:301.32ms
step:2813/5100 train_loss:3.3248 train_time:844487ms step_avg:301.28ms
step:2814/5100 train_loss:3.5395 train_time:844682ms step_avg:301.24ms
step:2815/5100 train_loss:3.6133 train_time:844876ms step_avg:301.20ms
step:2816/5100 train_loss:3.4267 train_time:845071ms step_avg:301.17ms
step:2817/5100 train_loss:2.9966 train_time:845265ms step_avg:301.13ms
step:2818/5100 train_loss:3.4536 train_time:845460ms step_avg:301.09ms
step:2819/5100 train_loss:3.4235 train_time:845656ms step_avg:301.05ms
step:2820/5100 train_loss:3.6097 train_time:845850ms step_avg:301.01ms
step:2821/5100 train_loss:3.6624 train_time:847081ms step_avg:301.35ms
step:2822/5100 train_loss:3.5373 train_time:847281ms step_avg:301.31ms
step:2823/5100 train_loss:3.4755 train_time:847475ms step_avg:301.27ms
step:2824/5100 train_loss:3.4341 train_time:847670ms step_avg:301.23ms
step:2825/5100 train_loss:3.3334 train_time:847864ms step_avg:301.19ms
step:2826/5100 train_loss:3.5939 train_time:848059ms step_avg:301.16ms
step:2827/5100 train_loss:3.4996 train_time:848254ms step_avg:301.12ms
step:2828/5100 train_loss:3.3699 train_time:848449ms step_avg:301.08ms
step:2829/5100 train_loss:3.5055 train_time:848643ms step_avg:301.04ms
step:2830/5100 train_loss:3.5003 train_time:848838ms step_avg:301.01ms
step:2831/5100 train_loss:3.4400 train_time:850069ms step_avg:301.34ms
step:2832/5100 train_loss:3.5895 train_time:850270ms step_avg:301.30ms
step:2833/5100 train_loss:3.5018 train_time:850464ms step_avg:301.26ms
step:2834/5100 train_loss:3.4878 train_time:850660ms step_avg:301.23ms
step:2835/5100 train_loss:3.2975 train_time:851001ms step_avg:301.24ms
step:2836/5100 train_loss:3.5321 train_time:851195ms step_avg:301.20ms
step:2837/5100 train_loss:3.4613 train_time:851390ms step_avg:301.16ms
step:2838/5100 train_loss:3.7702 train_time:851584ms step_avg:301.13ms
step:2839/5100 train_loss:3.4148 train_time:851780ms step_avg:301.09ms
step:2840/5100 train_loss:3.4218 train_time:851974ms step_avg:301.05ms
step:2841/5100 train_loss:3.4818 train_time:853207ms step_avg:301.38ms
step:2842/5100 train_loss:3.4124 train_time:853409ms step_avg:301.34ms
step:2843/5100 train_loss:3.3987 train_time:853603ms step_avg:301.31ms
step:2844/5100 train_loss:3.5812 train_time:853799ms step_avg:301.27ms
step:2845/5100 train_loss:3.4673 train_time:853996ms step_avg:301.23ms
step:2846/5100 train_loss:3.4930 train_time:854191ms step_avg:301.20ms
step:2847/5100 train_loss:3.4517 train_time:854384ms step_avg:301.16ms
step:2848/5100 train_loss:3.7148 train_time:854579ms step_avg:301.12ms
step:2849/5100 train_loss:3.3841 train_time:854774ms step_avg:301.08ms
step:2850/5100 train_loss:3.4120 train_time:855138ms step_avg:301.10ms
step:2851/5100 train_loss:3.5150 train_time:856366ms step_avg:301.43ms
step:2852/5100 train_loss:3.4853 train_time:856566ms step_avg:301.40ms
step:2853/5100 train_loss:3.4546 train_time:856762ms step_avg:301.36ms
step:2854/5100 train_loss:3.5282 train_time:856957ms step_avg:301.32ms
step:2855/5100 train_loss:3.3521 train_time:857152ms step_avg:301.28ms
step:2856/5100 train_loss:3.3693 train_time:857346ms step_avg:301.25ms
step:2857/5100 train_loss:3.4637 train_time:857541ms step_avg:301.21ms
step:2858/5100 train_loss:3.4660 train_time:857736ms step_avg:301.17ms
step:2859/5100 train_loss:3.3495 train_time:857930ms step_avg:301.13ms
step:2860/5100 train_loss:3.4551 train_time:858125ms step_avg:301.10ms
step:2861/5100 train_loss:3.4214 train_time:859355ms step_avg:301.42ms
step:2862/5100 train_loss:3.4618 train_time:859555ms step_avg:301.39ms
step:2863/5100 train_loss:3.4989 train_time:859750ms step_avg:301.35ms
step:2864/5100 train_loss:3.7669 train_time:859944ms step_avg:301.31ms
step:2865/5100 train_loss:3.5809 train_time:860140ms step_avg:301.27ms
step:2866/5100 train_loss:3.4638 train_time:860335ms step_avg:301.24ms
step:2867/5100 train_loss:3.3599 train_time:860528ms step_avg:301.20ms
step:2868/5100 train_loss:3.5433 train_time:860724ms step_avg:301.16ms
step:2869/5100 train_loss:3.4998 train_time:860919ms step_avg:301.13ms
step:2870/5100 train_loss:3.4614 train_time:861115ms step_avg:301.09ms
step:2871/5100 train_loss:3.5989 train_time:862346ms step_avg:301.41ms
step:2872/5100 train_loss:3.3783 train_time:862546ms step_avg:301.38ms
step:2873/5100 train_loss:3.4343 train_time:862742ms step_avg:301.34ms
step:2874/5100 train_loss:3.3033 train_time:862936ms step_avg:301.30ms
step:2875/5100 train_loss:3.4588 train_time:863130ms step_avg:301.27ms
step:2875/5100 val_loss:3.4585 train_time:863162ms step_avg:301.28ms
step:2876/5100 train_loss:3.3785 train_time:863342ms step_avg:301.24ms
step:2877/5100 train_loss:3.3574 train_time:863537ms step_avg:301.20ms
step:2878/5100 train_loss:3.4421 train_time:863732ms step_avg:301.16ms
step:2879/5100 train_loss:3.5639 train_time:863927ms step_avg:301.12ms
step:2880/5100 train_loss:3.5169 train_time:864122ms step_avg:301.09ms
step:2881/5100 train_loss:3.4530 train_time:865353ms step_avg:301.41ms
step:2882/5100 train_loss:3.4510 train_time:865552ms step_avg:301.38ms
step:2883/5100 train_loss:3.5674 train_time:865748ms step_avg:301.34ms
step:2884/5100 train_loss:3.3558 train_time:865942ms step_avg:301.30ms
step:2885/5100 train_loss:3.3742 train_time:866136ms step_avg:301.26ms
step:2886/5100 train_loss:3.4194 train_time:866333ms step_avg:301.23ms
step:2887/5100 train_loss:3.4169 train_time:866527ms step_avg:301.19ms
step:2888/5100 train_loss:3.4341 train_time:866723ms step_avg:301.15ms
step:2889/5100 train_loss:3.4529 train_time:866917ms step_avg:301.12ms
step:2890/5100 train_loss:3.6329 train_time:867113ms step_avg:301.08ms
step:2891/5100 train_loss:3.4882 train_time:868345ms step_avg:301.40ms
step:2892/5100 train_loss:3.3183 train_time:868546ms step_avg:301.37ms
step:2893/5100 train_loss:3.2494 train_time:868742ms step_avg:301.33ms
step:2894/5100 train_loss:3.3883 train_time:868936ms step_avg:301.30ms
step:2895/5100 train_loss:3.2609 train_time:869132ms step_avg:301.26ms
step:2896/5100 train_loss:3.4525 train_time:869326ms step_avg:301.22ms
step:2897/5100 train_loss:3.5774 train_time:869521ms step_avg:301.18ms
step:2898/5100 train_loss:3.4039 train_time:869716ms step_avg:301.15ms
step:2899/5100 train_loss:3.4988 train_time:869911ms step_avg:301.11ms
step:2900/5100 train_loss:3.3849 train_time:870106ms step_avg:301.07ms
step:2901/5100 train_loss:3.5709 train_time:871336ms step_avg:301.40ms
step:2902/5100 train_loss:3.5576 train_time:871535ms step_avg:301.36ms
step:2903/5100 train_loss:3.5977 train_time:871731ms step_avg:301.32ms
step:2904/5100 train_loss:3.3050 train_time:871927ms step_avg:301.29ms
step:2905/5100 train_loss:3.4472 train_time:872122ms step_avg:301.25ms
step:2906/5100 train_loss:3.4297 train_time:872316ms step_avg:301.21ms
step:2907/5100 train_loss:3.5148 train_time:872512ms step_avg:301.18ms
step:2908/5100 train_loss:3.4493 train_time:872707ms step_avg:301.14ms
step:2909/5100 train_loss:3.4069 train_time:872902ms step_avg:301.10ms
step:2910/5100 train_loss:3.7523 train_time:873096ms step_avg:301.07ms
step:2911/5100 train_loss:3.4656 train_time:874326ms step_avg:301.39ms
step:2912/5100 train_loss:3.3625 train_time:874529ms step_avg:301.35ms
step:2913/5100 train_loss:3.3527 train_time:874725ms step_avg:301.32ms
step:2914/5100 train_loss:3.8399 train_time:874920ms step_avg:301.28ms
step:2915/5100 train_loss:3.4263 train_time:875114ms step_avg:301.24ms
step:2916/5100 train_loss:3.3722 train_time:875310ms step_avg:301.21ms
step:2917/5100 train_loss:3.3616 train_time:875506ms step_avg:301.17ms
step:2918/5100 train_loss:3.6534 train_time:875701ms step_avg:301.14ms
step:2919/5100 train_loss:3.1425 train_time:875895ms step_avg:301.10ms
step:2920/5100 train_loss:3.3584 train_time:876091ms step_avg:301.06ms
step:2921/5100 train_loss:3.3727 train_time:877321ms step_avg:301.38ms
step:2922/5100 train_loss:3.4659 train_time:877524ms step_avg:301.35ms
step:2923/5100 train_loss:3.5152 train_time:877720ms step_avg:301.31ms
step:2924/5100 train_loss:3.5386 train_time:877914ms step_avg:301.27ms
step:2925/5100 train_loss:3.5521 train_time:878110ms step_avg:301.24ms
step:2926/5100 train_loss:3.4241 train_time:878305ms step_avg:301.20ms
step:2927/5100 train_loss:3.4456 train_time:878500ms step_avg:301.17ms
step:2928/5100 train_loss:3.4312 train_time:878694ms step_avg:301.13ms
step:2929/5100 train_loss:3.4262 train_time:878889ms step_avg:301.09ms
step:2930/5100 train_loss:3.3940 train_time:879085ms step_avg:301.06ms
step:2931/5100 train_loss:3.4257 train_time:880314ms step_avg:301.37ms
step:2932/5100 train_loss:3.5660 train_time:880518ms step_avg:301.34ms
step:2933/5100 train_loss:3.5981 train_time:880713ms step_avg:301.30ms
step:2934/5100 train_loss:3.5676 train_time:880908ms step_avg:301.27ms
step:2935/5100 train_loss:3.4128 train_time:881103ms step_avg:301.23ms
step:2936/5100 train_loss:3.4717 train_time:881297ms step_avg:301.20ms
step:2937/5100 train_loss:3.3929 train_time:881493ms step_avg:301.16ms
step:2938/5100 train_loss:3.4286 train_time:881690ms step_avg:301.12ms
step:2939/5100 train_loss:3.4505 train_time:881885ms step_avg:301.09ms
step:2940/5100 train_loss:3.4927 train_time:882079ms step_avg:301.05ms
step:2941/5100 train_loss:3.5392 train_time:883310ms step_avg:301.37ms
step:2942/5100 train_loss:3.5254 train_time:883511ms step_avg:301.33ms
step:2943/5100 train_loss:3.4570 train_time:883706ms step_avg:301.30ms
step:2944/5100 train_loss:3.3325 train_time:883902ms step_avg:301.26ms
step:2945/5100 train_loss:3.2706 train_time:884096ms step_avg:301.23ms
step:2946/5100 train_loss:3.4790 train_time:884291ms step_avg:301.19ms
step:2947/5100 train_loss:3.5471 train_time:884486ms step_avg:301.15ms
step:2948/5100 train_loss:3.4754 train_time:884680ms step_avg:301.12ms
step:2949/5100 train_loss:3.6532 train_time:884874ms step_avg:301.08ms
step:2950/5100 train_loss:3.4756 train_time:885069ms step_avg:301.04ms
step:2951/5100 train_loss:3.4844 train_time:886300ms step_avg:301.36ms
step:2952/5100 train_loss:3.8942 train_time:886501ms step_avg:301.33ms
step:2953/5100 train_loss:3.5675 train_time:886696ms step_avg:301.29ms
step:2954/5100 train_loss:3.5053 train_time:886892ms step_avg:301.25ms
step:2955/5100 train_loss:3.5139 train_time:887087ms step_avg:301.22ms
step:2956/5100 train_loss:3.4486 train_time:887282ms step_avg:301.18ms
step:2957/5100 train_loss:3.4733 train_time:887476ms step_avg:301.15ms
step:2958/5100 train_loss:3.3442 train_time:887671ms step_avg:301.11ms
step:2959/5100 train_loss:3.4326 train_time:887865ms step_avg:301.07ms
step:2960/5100 train_loss:3.5684 train_time:888059ms step_avg:301.04ms
step:2961/5100 train_loss:3.3831 train_time:889289ms step_avg:301.35ms
step:2962/5100 train_loss:3.5093 train_time:889492ms step_avg:301.32ms
step:2963/5100 train_loss:3.3671 train_time:889688ms step_avg:301.28ms
step:2964/5100 train_loss:3.4203 train_time:889882ms step_avg:301.25ms
step:2965/5100 train_loss:3.4095 train_time:890077ms step_avg:301.21ms
step:2966/5100 train_loss:3.5219 train_time:890272ms step_avg:301.17ms
step:2967/5100 train_loss:3.3890 train_time:890467ms step_avg:301.14ms
step:2968/5100 train_loss:3.6409 train_time:890662ms step_avg:301.10ms
step:2969/5100 train_loss:3.4923 train_time:890856ms step_avg:301.07ms
step:2970/5100 train_loss:3.5101 train_time:891051ms step_avg:301.03ms
step:2971/5100 train_loss:3.4945 train_time:892281ms step_avg:301.34ms
step:2972/5100 train_loss:3.5673 train_time:892482ms step_avg:301.31ms
step:2973/5100 train_loss:3.3956 train_time:892677ms step_avg:301.27ms
step:2974/5100 train_loss:3.4004 train_time:892873ms step_avg:301.24ms
step:2975/5100 train_loss:3.3167 train_time:893068ms step_avg:301.20ms
step:2976/5100 train_loss:3.3976 train_time:893262ms step_avg:301.17ms
step:2977/5100 train_loss:3.3925 train_time:893456ms step_avg:301.13ms
step:2978/5100 train_loss:3.4006 train_time:893651ms step_avg:301.10ms
step:2979/5100 train_loss:3.6797 train_time:893846ms step_avg:301.06ms
step:2980/5100 train_loss:3.4924 train_time:894041ms step_avg:301.02ms
step:2981/5100 train_loss:3.5332 train_time:895272ms step_avg:301.34ms
step:2982/5100 train_loss:3.5493 train_time:895472ms step_avg:301.30ms
step:2983/5100 train_loss:3.6305 train_time:895667ms step_avg:301.27ms
step:2984/5100 train_loss:3.4291 train_time:895862ms step_avg:301.23ms
step:2985/5100 train_loss:3.5247 train_time:896056ms step_avg:301.20ms
step:2986/5100 train_loss:3.5278 train_time:896251ms step_avg:301.16ms
step:2987/5100 train_loss:3.4807 train_time:896446ms step_avg:301.12ms
step:2988/5100 train_loss:3.6047 train_time:896642ms step_avg:301.09ms
step:2989/5100 train_loss:3.1939 train_time:896836ms step_avg:301.05ms
step:2990/5100 train_loss:3.5393 train_time:897030ms step_avg:301.02ms
step:2991/5100 train_loss:3.4961 train_time:898260ms step_avg:301.33ms
step:2992/5100 train_loss:3.4746 train_time:898463ms step_avg:301.30ms
step:2993/5100 train_loss:3.3869 train_time:898658ms step_avg:301.26ms
step:2994/5100 train_loss:3.5304 train_time:898854ms step_avg:301.22ms
step:2995/5100 train_loss:3.3408 train_time:899049ms step_avg:301.19ms
step:2996/5100 train_loss:3.3805 train_time:899243ms step_avg:301.15ms
step:2997/5100 train_loss:3.4486 train_time:899438ms step_avg:301.12ms
step:2998/5100 train_loss:3.3895 train_time:899634ms step_avg:301.08ms
step:2999/5100 train_loss:3.5138 train_time:899830ms step_avg:301.05ms
step:3000/5100 train_loss:3.4125 train_time:900025ms step_avg:301.01ms
step:3000/5100 val_loss:3.4537 train_time:900058ms step_avg:301.02ms
step:3001/5100 train_loss:3.4051 train_time:901276ms step_avg:301.33ms
step:3002/5100 train_loss:3.3470 train_time:901477ms step_avg:301.30ms
step:3003/5100 train_loss:3.3953 train_time:901672ms step_avg:301.26ms
step:3004/5100 train_loss:3.5255 train_time:901866ms step_avg:301.22ms
step:3005/5100 train_loss:3.8645 train_time:902061ms step_avg:301.19ms
step:3006/5100 train_loss:3.4355 train_time:902256ms step_avg:301.15ms
step:3007/5100 train_loss:3.5011 train_time:902450ms step_avg:301.12ms
step:3008/5100 train_loss:3.3161 train_time:902646ms step_avg:301.08ms
step:3009/5100 train_loss:3.5255 train_time:902842ms step_avg:301.05ms
step:3010/5100 train_loss:3.4248 train_time:903037ms step_avg:301.01ms
step:3011/5100 train_loss:3.4917 train_time:904269ms step_avg:301.32ms
step:3012/5100 train_loss:3.4910 train_time:904468ms step_avg:301.29ms
step:3013/5100 train_loss:3.3726 train_time:904665ms step_avg:301.25ms
step:3014/5100 train_loss:3.5777 train_time:904860ms step_avg:301.22ms
step:3015/5100 train_loss:3.5398 train_time:905054ms step_avg:301.18ms
step:3016/5100 train_loss:3.4010 train_time:905249ms step_avg:301.15ms
step:3017/5100 train_loss:3.4328 train_time:905444ms step_avg:301.11ms
step:3018/5100 train_loss:3.4807 train_time:905640ms step_avg:301.08ms
step:3019/5100 train_loss:3.5132 train_time:905836ms step_avg:301.04ms
step:3020/5100 train_loss:3.3045 train_time:906030ms step_avg:301.01ms
step:3021/5100 train_loss:3.6027 train_time:907262ms step_avg:301.32ms
step:3022/5100 train_loss:3.4368 train_time:907463ms step_avg:301.28ms
step:3023/5100 train_loss:3.3579 train_time:907658ms step_avg:301.25ms
step:3024/5100 train_loss:3.4462 train_time:907997ms step_avg:301.26ms
step:3025/5100 train_loss:3.4362 train_time:908192ms step_avg:301.22ms
step:3026/5100 train_loss:3.4826 train_time:908387ms step_avg:301.19ms
step:3027/5100 train_loss:3.5056 train_time:908583ms step_avg:301.15ms
step:3028/5100 train_loss:3.4156 train_time:908778ms step_avg:301.12ms
step:3029/5100 train_loss:3.2164 train_time:908971ms step_avg:301.08ms
step:3030/5100 train_loss:3.5640 train_time:909167ms step_avg:301.05ms
step:3031/5100 train_loss:3.3205 train_time:910398ms step_avg:301.36ms
step:3032/5100 train_loss:3.3112 train_time:910600ms step_avg:301.32ms
step:3033/5100 train_loss:3.6580 train_time:910795ms step_avg:301.29ms
step:3034/5100 train_loss:3.6502 train_time:910989ms step_avg:301.25ms
step:3035/5100 train_loss:3.4146 train_time:911184ms step_avg:301.22ms
step:3036/5100 train_loss:3.4932 train_time:911380ms step_avg:301.18ms
step:3037/5100 train_loss:3.4458 train_time:911574ms step_avg:301.15ms
step:3038/5100 train_loss:3.3395 train_time:911768ms step_avg:301.11ms
step:3039/5100 train_loss:3.4006 train_time:911964ms step_avg:301.08ms
step:3040/5100 train_loss:3.4963 train_time:912332ms step_avg:301.10ms
step:3041/5100 train_loss:3.4920 train_time:913561ms step_avg:301.41ms
step:3042/5100 train_loss:3.2979 train_time:913762ms step_avg:301.37ms
step:3043/5100 train_loss:3.4444 train_time:913956ms step_avg:301.34ms
step:3044/5100 train_loss:3.4715 train_time:914150ms step_avg:301.30ms
step:3045/5100 train_loss:3.4758 train_time:914345ms step_avg:301.27ms
step:3046/5100 train_loss:3.5585 train_time:914540ms step_avg:301.23ms
step:3047/5100 train_loss:3.3695 train_time:914735ms step_avg:301.20ms
step:3048/5100 train_loss:3.4964 train_time:914930ms step_avg:301.16ms
step:3049/5100 train_loss:3.4481 train_time:915125ms step_avg:301.13ms
step:3050/5100 train_loss:3.3767 train_time:915321ms step_avg:301.09ms
step:3051/5100 train_loss:3.5047 train_time:916552ms step_avg:301.40ms
step:3052/5100 train_loss:3.3466 train_time:916753ms step_avg:301.37ms
step:3053/5100 train_loss:3.5884 train_time:916948ms step_avg:301.33ms
step:3054/5100 train_loss:3.5276 train_time:917143ms step_avg:301.30ms
step:3055/5100 train_loss:3.5104 train_time:917339ms step_avg:301.26ms
step:3056/5100 train_loss:3.5026 train_time:917534ms step_avg:301.23ms
step:3057/5100 train_loss:3.4024 train_time:917728ms step_avg:301.19ms
step:3058/5100 train_loss:3.4309 train_time:917923ms step_avg:301.16ms
step:3059/5100 train_loss:3.5049 train_time:918118ms step_avg:301.12ms
step:3060/5100 train_loss:3.4002 train_time:918312ms step_avg:301.09ms
step:3061/5100 train_loss:3.4590 train_time:919543ms step_avg:301.39ms
step:3062/5100 train_loss:3.4656 train_time:919744ms step_avg:301.36ms
step:3063/5100 train_loss:3.3992 train_time:919940ms step_avg:301.32ms
step:3064/5100 train_loss:3.3703 train_time:920135ms step_avg:301.29ms
step:3065/5100 train_loss:3.3902 train_time:920330ms step_avg:301.25ms
step:3066/5100 train_loss:3.3734 train_time:920525ms step_avg:301.22ms
step:3067/5100 train_loss:3.3601 train_time:920720ms step_avg:301.18ms
step:3068/5100 train_loss:3.3189 train_time:920915ms step_avg:301.15ms
step:3069/5100 train_loss:3.3604 train_time:921110ms step_avg:301.11ms
step:3070/5100 train_loss:3.3557 train_time:921305ms step_avg:301.08ms
step:3071/5100 train_loss:3.5416 train_time:922536ms step_avg:301.38ms
step:3072/5100 train_loss:3.4727 train_time:922736ms step_avg:301.35ms
step:3073/5100 train_loss:3.5115 train_time:922930ms step_avg:301.32ms
step:3074/5100 train_loss:3.5006 train_time:923126ms step_avg:301.28ms
step:3075/5100 train_loss:3.4498 train_time:923322ms step_avg:301.25ms
step:3076/5100 train_loss:3.4940 train_time:923517ms step_avg:301.21ms
step:3077/5100 train_loss:3.5548 train_time:923712ms step_avg:301.18ms
step:3078/5100 train_loss:3.3549 train_time:923907ms step_avg:301.14ms
step:3079/5100 train_loss:3.8910 train_time:924102ms step_avg:301.11ms
step:3080/5100 train_loss:3.4455 train_time:924297ms step_avg:301.07ms
step:3081/5100 train_loss:3.4141 train_time:925527ms step_avg:301.38ms
step:3082/5100 train_loss:3.5483 train_time:925728ms step_avg:301.34ms
step:3083/5100 train_loss:3.3730 train_time:925924ms step_avg:301.31ms
step:3084/5100 train_loss:3.3959 train_time:926120ms step_avg:301.28ms
step:3085/5100 train_loss:3.4451 train_time:926314ms step_avg:301.24ms
step:3086/5100 train_loss:3.5373 train_time:926509ms step_avg:301.21ms
step:3087/5100 train_loss:3.4495 train_time:926704ms step_avg:301.17ms
step:3088/5100 train_loss:3.3614 train_time:926898ms step_avg:301.14ms
step:3089/5100 train_loss:3.5192 train_time:927093ms step_avg:301.10ms
step:3090/5100 train_loss:3.3851 train_time:927287ms step_avg:301.07ms
step:3091/5100 train_loss:3.6396 train_time:928518ms step_avg:301.37ms
step:3092/5100 train_loss:4.2131 train_time:928720ms step_avg:301.34ms
step:3093/5100 train_loss:3.4778 train_time:928916ms step_avg:301.30ms
step:3094/5100 train_loss:3.3637 train_time:929110ms step_avg:301.27ms
step:3095/5100 train_loss:3.3252 train_time:929305ms step_avg:301.23ms
step:3096/5100 train_loss:3.4936 train_time:929500ms step_avg:301.20ms
step:3097/5100 train_loss:3.6130 train_time:929695ms step_avg:301.16ms
step:3098/5100 train_loss:3.3953 train_time:929889ms step_avg:301.13ms
step:3099/5100 train_loss:3.4318 train_time:930085ms step_avg:301.10ms
step:3100/5100 train_loss:3.6189 train_time:930280ms step_avg:301.06ms
step:3101/5100 train_loss:3.5050 train_time:931511ms step_avg:301.36ms
step:3102/5100 train_loss:3.5060 train_time:931711ms step_avg:301.33ms
step:3103/5100 train_loss:3.4094 train_time:931906ms step_avg:301.30ms
step:3104/5100 train_loss:3.6585 train_time:932102ms step_avg:301.26ms
step:3105/5100 train_loss:3.4809 train_time:932296ms step_avg:301.23ms
step:3106/5100 train_loss:3.3384 train_time:932489ms step_avg:301.19ms
step:3107/5100 train_loss:3.3684 train_time:932684ms step_avg:301.16ms
step:3108/5100 train_loss:3.3282 train_time:932879ms step_avg:301.12ms
step:3109/5100 train_loss:3.5497 train_time:933074ms step_avg:301.09ms
step:3110/5100 train_loss:3.4333 train_time:933268ms step_avg:301.05ms
step:3111/5100 train_loss:3.4745 train_time:934499ms step_avg:301.35ms
step:3112/5100 train_loss:3.4546 train_time:934699ms step_avg:301.32ms
step:3113/5100 train_loss:3.5093 train_time:934894ms step_avg:301.29ms
step:3114/5100 train_loss:3.4562 train_time:935088ms step_avg:301.25ms
step:3115/5100 train_loss:3.4685 train_time:935283ms step_avg:301.22ms
step:3116/5100 train_loss:3.4916 train_time:935478ms step_avg:301.18ms
step:3117/5100 train_loss:3.3498 train_time:935672ms step_avg:301.15ms
step:3118/5100 train_loss:3.3701 train_time:935867ms step_avg:301.12ms
step:3119/5100 train_loss:3.5591 train_time:936062ms step_avg:301.08ms
step:3120/5100 train_loss:3.5370 train_time:936258ms step_avg:301.05ms
step:3121/5100 train_loss:3.3283 train_time:937489ms step_avg:301.35ms
step:3122/5100 train_loss:3.5140 train_time:937689ms step_avg:301.31ms
step:3123/5100 train_loss:3.5764 train_time:937884ms step_avg:301.28ms
step:3124/5100 train_loss:3.5417 train_time:938079ms step_avg:301.25ms
step:3125/5100 train_loss:3.3312 train_time:938272ms step_avg:301.21ms
step:3125/5100 val_loss:3.4431 train_time:938304ms step_avg:301.22ms
step:3126/5100 train_loss:3.4103 train_time:938483ms step_avg:301.18ms
step:3127/5100 train_loss:3.4567 train_time:938678ms step_avg:301.15ms
step:3128/5100 train_loss:3.5390 train_time:938872ms step_avg:301.11ms
step:3129/5100 train_loss:3.6036 train_time:939067ms step_avg:301.08ms
step:3130/5100 train_loss:3.3218 train_time:939263ms step_avg:301.05ms
step:3131/5100 train_loss:3.4838 train_time:940493ms step_avg:301.34ms
step:3132/5100 train_loss:3.4820 train_time:940692ms step_avg:301.31ms
step:3133/5100 train_loss:3.4995 train_time:940889ms step_avg:301.28ms
step:3134/5100 train_loss:3.4076 train_time:941085ms step_avg:301.24ms
step:3135/5100 train_loss:3.5165 train_time:941280ms step_avg:301.21ms
step:3136/5100 train_loss:3.4313 train_time:941474ms step_avg:301.18ms
step:3137/5100 train_loss:3.5012 train_time:941669ms step_avg:301.14ms
step:3138/5100 train_loss:3.6876 train_time:941863ms step_avg:301.11ms
step:3139/5100 train_loss:3.6527 train_time:942058ms step_avg:301.07ms
step:3140/5100 train_loss:3.4173 train_time:942254ms step_avg:301.04ms
step:3141/5100 train_loss:3.4397 train_time:943485ms step_avg:301.34ms
step:3142/5100 train_loss:3.3637 train_time:943686ms step_avg:301.30ms
step:3143/5100 train_loss:3.4544 train_time:943880ms step_avg:301.27ms
step:3144/5100 train_loss:3.2519 train_time:944075ms step_avg:301.24ms
step:3145/5100 train_loss:3.4933 train_time:944271ms step_avg:301.20ms
step:3146/5100 train_loss:3.4036 train_time:944466ms step_avg:301.17ms
step:3147/5100 train_loss:3.4248 train_time:944660ms step_avg:301.13ms
step:3148/5100 train_loss:3.6003 train_time:944856ms step_avg:301.10ms
step:3149/5100 train_loss:3.6920 train_time:945052ms step_avg:301.07ms
step:3150/5100 train_loss:3.5564 train_time:945247ms step_avg:301.03ms
step:3151/5100 train_loss:3.3662 train_time:946477ms step_avg:301.33ms
step:3152/5100 train_loss:3.4125 train_time:946679ms step_avg:301.30ms
step:3153/5100 train_loss:3.3938 train_time:946875ms step_avg:301.26ms
step:3154/5100 train_loss:3.5095 train_time:947072ms step_avg:301.23ms
step:3155/5100 train_loss:3.3248 train_time:947267ms step_avg:301.20ms
step:3156/5100 train_loss:3.4745 train_time:947462ms step_avg:301.16ms
step:3157/5100 train_loss:3.4156 train_time:947657ms step_avg:301.13ms
step:3158/5100 train_loss:3.5272 train_time:947853ms step_avg:301.10ms
step:3159/5100 train_loss:3.5986 train_time:948049ms step_avg:301.06ms
step:3160/5100 train_loss:3.4399 train_time:948245ms step_avg:301.03ms
step:3161/5100 train_loss:3.5017 train_time:949474ms step_avg:301.32ms
step:3162/5100 train_loss:3.5776 train_time:949677ms step_avg:301.29ms
step:3163/5100 train_loss:3.4802 train_time:949873ms step_avg:301.26ms
step:3164/5100 train_loss:3.5380 train_time:950068ms step_avg:301.23ms
step:3165/5100 train_loss:3.3590 train_time:950265ms step_avg:301.19ms
step:3166/5100 train_loss:3.3413 train_time:950460ms step_avg:301.16ms
step:3167/5100 train_loss:3.3833 train_time:950655ms step_avg:301.13ms
step:3168/5100 train_loss:3.2089 train_time:950851ms step_avg:301.09ms
step:3169/5100 train_loss:3.3738 train_time:951046ms step_avg:301.06ms
step:3170/5100 train_loss:3.5185 train_time:951241ms step_avg:301.03ms
step:3171/5100 train_loss:3.5545 train_time:952472ms step_avg:301.32ms
step:3172/5100 train_loss:3.5115 train_time:952673ms step_avg:301.29ms
step:3173/5100 train_loss:3.4773 train_time:952868ms step_avg:301.25ms
step:3174/5100 train_loss:3.4501 train_time:953064ms step_avg:301.22ms
step:3175/5100 train_loss:3.4508 train_time:953259ms step_avg:301.19ms
step:3176/5100 train_loss:3.4517 train_time:953454ms step_avg:301.15ms
step:3177/5100 train_loss:3.3803 train_time:953650ms step_avg:301.12ms
step:3178/5100 train_loss:3.5091 train_time:953845ms step_avg:301.09ms
step:3179/5100 train_loss:3.5781 train_time:954038ms step_avg:301.05ms
step:3180/5100 train_loss:3.4267 train_time:954235ms step_avg:301.02ms
step:3181/5100 train_loss:3.4141 train_time:955465ms step_avg:301.31ms
step:3182/5100 train_loss:3.4629 train_time:955666ms step_avg:301.28ms
step:3183/5100 train_loss:3.5572 train_time:955860ms step_avg:301.25ms
step:3184/5100 train_loss:3.5704 train_time:956055ms step_avg:301.21ms
step:3185/5100 train_loss:3.4750 train_time:956251ms step_avg:301.18ms
step:3186/5100 train_loss:3.5449 train_time:956446ms step_avg:301.15ms
step:3187/5100 train_loss:3.5310 train_time:956641ms step_avg:301.11ms
step:3188/5100 train_loss:3.3229 train_time:956835ms step_avg:301.08ms
step:3189/5100 train_loss:3.4686 train_time:957031ms step_avg:301.05ms
step:3190/5100 train_loss:3.4384 train_time:957226ms step_avg:301.01ms
step:3191/5100 train_loss:3.4631 train_time:958457ms step_avg:301.31ms
step:3192/5100 train_loss:3.4184 train_time:958658ms step_avg:301.28ms
step:3193/5100 train_loss:3.3475 train_time:958853ms step_avg:301.24ms
step:3194/5100 train_loss:4.3892 train_time:959049ms step_avg:301.21ms
step:3195/5100 train_loss:3.4755 train_time:959243ms step_avg:301.18ms
step:3196/5100 train_loss:3.2596 train_time:959438ms step_avg:301.14ms
step:3197/5100 train_loss:3.4224 train_time:959634ms step_avg:301.11ms
step:3198/5100 train_loss:3.3071 train_time:959829ms step_avg:301.08ms
step:3199/5100 train_loss:3.4043 train_time:960024ms step_avg:301.04ms
step:3200/5100 train_loss:3.3373 train_time:960218ms step_avg:301.01ms
step:3201/5100 train_loss:3.4308 train_time:961450ms step_avg:301.30ms
step:3202/5100 train_loss:3.5177 train_time:961652ms step_avg:301.27ms
step:3203/5100 train_loss:3.3666 train_time:961848ms step_avg:301.24ms
step:3204/5100 train_loss:3.4106 train_time:962042ms step_avg:301.20ms
step:3205/5100 train_loss:3.4915 train_time:962237ms step_avg:301.17ms
step:3206/5100 train_loss:3.6579 train_time:962433ms step_avg:301.14ms
step:3207/5100 train_loss:3.2500 train_time:962629ms step_avg:301.10ms
step:3208/5100 train_loss:3.6103 train_time:962825ms step_avg:301.07ms
step:3209/5100 train_loss:3.4537 train_time:963019ms step_avg:301.04ms
step:3210/5100 train_loss:3.5240 train_time:963214ms step_avg:301.00ms
step:3211/5100 train_loss:3.6149 train_time:964446ms step_avg:301.30ms
step:3212/5100 train_loss:3.2980 train_time:964647ms step_avg:301.26ms
step:3213/5100 train_loss:3.3472 train_time:964988ms step_avg:301.28ms
step:3214/5100 train_loss:3.5586 train_time:965182ms step_avg:301.24ms
step:3215/5100 train_loss:3.3535 train_time:965376ms step_avg:301.21ms
step:3216/5100 train_loss:3.4189 train_time:965572ms step_avg:301.18ms
step:3217/5100 train_loss:3.3156 train_time:965766ms step_avg:301.14ms
step:3218/5100 train_loss:3.4554 train_time:965960ms step_avg:301.11ms
step:3219/5100 train_loss:3.4913 train_time:966155ms step_avg:301.08ms
step:3220/5100 train_loss:3.5413 train_time:966352ms step_avg:301.04ms
step:3221/5100 train_loss:3.4835 train_time:967582ms step_avg:301.33ms
step:3222/5100 train_loss:3.4825 train_time:967785ms step_avg:301.30ms
step:3223/5100 train_loss:3.3529 train_time:967979ms step_avg:301.27ms
step:3224/5100 train_loss:3.3739 train_time:968174ms step_avg:301.24ms
step:3225/5100 train_loss:3.3698 train_time:968369ms step_avg:301.20ms
step:3226/5100 train_loss:3.4146 train_time:968566ms step_avg:301.17ms
step:3227/5100 train_loss:3.3516 train_time:968759ms step_avg:301.14ms
step:3228/5100 train_loss:3.2679 train_time:968955ms step_avg:301.10ms
step:3229/5100 train_loss:3.3901 train_time:969151ms step_avg:301.07ms
step:3230/5100 train_loss:3.1639 train_time:969517ms step_avg:301.09ms
step:3231/5100 train_loss:3.3454 train_time:970748ms step_avg:301.38ms
step:3232/5100 train_loss:3.3430 train_time:970951ms step_avg:301.35ms
step:3233/5100 train_loss:3.5801 train_time:971147ms step_avg:301.32ms
step:3234/5100 train_loss:3.5607 train_time:971341ms step_avg:301.28ms
step:3235/5100 train_loss:3.5278 train_time:971536ms step_avg:301.25ms
step:3236/5100 train_loss:3.4152 train_time:971733ms step_avg:301.22ms
step:3237/5100 train_loss:3.5720 train_time:971928ms step_avg:301.19ms
step:3238/5100 train_loss:3.4322 train_time:972124ms step_avg:301.15ms
step:3239/5100 train_loss:3.5649 train_time:972318ms step_avg:301.12ms
step:3240/5100 train_loss:3.5298 train_time:972514ms step_avg:301.09ms
step:3241/5100 train_loss:3.4276 train_time:973745ms step_avg:301.38ms
step:3242/5100 train_loss:3.3825 train_time:973946ms step_avg:301.34ms
step:3243/5100 train_loss:3.6133 train_time:974141ms step_avg:301.31ms
step:3244/5100 train_loss:3.4826 train_time:974335ms step_avg:301.28ms
step:3245/5100 train_loss:3.5227 train_time:974532ms step_avg:301.25ms
step:3246/5100 train_loss:3.4129 train_time:974728ms step_avg:301.21ms
step:3247/5100 train_loss:3.5488 train_time:974924ms step_avg:301.18ms
step:3248/5100 train_loss:3.4710 train_time:975119ms step_avg:301.15ms
step:3249/5100 train_loss:3.4209 train_time:975315ms step_avg:301.12ms
step:3250/5100 train_loss:3.2893 train_time:975510ms step_avg:301.08ms
step:3250/5100 val_loss:3.4349 train_time:975543ms step_avg:301.09ms
step:3251/5100 train_loss:3.4917 train_time:976759ms step_avg:301.38ms
step:3252/5100 train_loss:3.4867 train_time:976961ms step_avg:301.35ms
step:3253/5100 train_loss:3.4445 train_time:977157ms step_avg:301.31ms
step:3254/5100 train_loss:3.3696 train_time:977352ms step_avg:301.28ms
step:3255/5100 train_loss:3.5139 train_time:977545ms step_avg:301.25ms
step:3256/5100 train_loss:3.5457 train_time:977741ms step_avg:301.21ms
step:3257/5100 train_loss:3.4844 train_time:977938ms step_avg:301.18ms
step:3258/5100 train_loss:3.5202 train_time:978132ms step_avg:301.15ms
step:3259/5100 train_loss:3.3565 train_time:978327ms step_avg:301.12ms
step:3260/5100 train_loss:3.4409 train_time:978522ms step_avg:301.08ms
step:3261/5100 train_loss:3.3111 train_time:979754ms step_avg:301.37ms
step:3262/5100 train_loss:3.3434 train_time:979958ms step_avg:301.34ms
step:3263/5100 train_loss:3.3793 train_time:980154ms step_avg:301.31ms
step:3264/5100 train_loss:3.5319 train_time:980349ms step_avg:301.27ms
step:3265/5100 train_loss:3.4115 train_time:980542ms step_avg:301.24ms
step:3266/5100 train_loss:3.4708 train_time:980738ms step_avg:301.21ms
step:3267/5100 train_loss:3.4826 train_time:980933ms step_avg:301.18ms
step:3268/5100 train_loss:3.5662 train_time:981128ms step_avg:301.14ms
step:3269/5100 train_loss:3.3782 train_time:981323ms step_avg:301.11ms
step:3270/5100 train_loss:3.5076 train_time:981519ms step_avg:301.08ms
step:3271/5100 train_loss:3.3802 train_time:982750ms step_avg:301.36ms
step:3272/5100 train_loss:3.2750 train_time:982952ms step_avg:301.33ms
step:3273/5100 train_loss:3.3901 train_time:983148ms step_avg:301.30ms
step:3274/5100 train_loss:3.5312 train_time:983342ms step_avg:301.27ms
step:3275/5100 train_loss:3.3236 train_time:983539ms step_avg:301.24ms
step:3276/5100 train_loss:3.4705 train_time:983734ms step_avg:301.20ms
step:3277/5100 train_loss:3.4701 train_time:983929ms step_avg:301.17ms
step:3278/5100 train_loss:3.4642 train_time:984125ms step_avg:301.14ms
step:3279/5100 train_loss:3.4289 train_time:984320ms step_avg:301.11ms
step:3280/5100 train_loss:3.5872 train_time:984514ms step_avg:301.07ms
step:3281/5100 train_loss:3.4329 train_time:985745ms step_avg:301.36ms
step:3282/5100 train_loss:3.4859 train_time:985946ms step_avg:301.33ms
step:3283/5100 train_loss:3.3426 train_time:986142ms step_avg:301.30ms
step:3284/5100 train_loss:3.4712 train_time:986336ms step_avg:301.26ms
step:3285/5100 train_loss:3.5191 train_time:986531ms step_avg:301.23ms
step:3286/5100 train_loss:3.5043 train_time:986725ms step_avg:301.20ms
step:3287/5100 train_loss:3.5391 train_time:986922ms step_avg:301.17ms
step:3288/5100 train_loss:3.4144 train_time:987117ms step_avg:301.13ms
step:3289/5100 train_loss:3.5272 train_time:987312ms step_avg:301.10ms
step:3290/5100 train_loss:3.4494 train_time:987506ms step_avg:301.07ms
step:3291/5100 train_loss:3.3331 train_time:988736ms step_avg:301.35ms
step:3292/5100 train_loss:3.4623 train_time:988937ms step_avg:301.32ms
step:3293/5100 train_loss:3.4934 train_time:989132ms step_avg:301.29ms
step:3294/5100 train_loss:3.4770 train_time:989327ms step_avg:301.26ms
step:3295/5100 train_loss:3.3595 train_time:989522ms step_avg:301.22ms
step:3296/5100 train_loss:3.4230 train_time:989717ms step_avg:301.19ms
step:3297/5100 train_loss:3.4630 train_time:989911ms step_avg:301.16ms
step:3298/5100 train_loss:3.4578 train_time:990106ms step_avg:301.13ms
step:3299/5100 train_loss:3.4422 train_time:990302ms step_avg:301.10ms
step:3300/5100 train_loss:3.5010 train_time:990498ms step_avg:301.06ms
step:3301/5100 train_loss:3.4020 train_time:991727ms step_avg:301.35ms
step:3302/5100 train_loss:3.4717 train_time:991929ms step_avg:301.32ms
step:3303/5100 train_loss:3.4151 train_time:992123ms step_avg:301.28ms
step:3304/5100 train_loss:3.4317 train_time:992320ms step_avg:301.25ms
step:3305/5100 train_loss:3.4292 train_time:992514ms step_avg:301.22ms
step:3306/5100 train_loss:3.5269 train_time:992709ms step_avg:301.19ms
step:3307/5100 train_loss:3.4556 train_time:992903ms step_avg:301.15ms
step:3308/5100 train_loss:3.4186 train_time:993098ms step_avg:301.12ms
step:3309/5100 train_loss:3.5413 train_time:993294ms step_avg:301.09ms
step:3310/5100 train_loss:3.4124 train_time:993489ms step_avg:301.06ms
step:3311/5100 train_loss:3.3545 train_time:994720ms step_avg:301.34ms
step:3312/5100 train_loss:3.4727 train_time:994921ms step_avg:301.31ms
step:3313/5100 train_loss:3.4373 train_time:995117ms step_avg:301.28ms
step:3314/5100 train_loss:3.6373 train_time:995312ms step_avg:301.24ms
step:3315/5100 train_loss:3.4608 train_time:995505ms step_avg:301.21ms
step:3316/5100 train_loss:3.4269 train_time:995700ms step_avg:301.18ms
step:3317/5100 train_loss:3.0621 train_time:995894ms step_avg:301.15ms
step:3318/5100 train_loss:3.5678 train_time:996089ms step_avg:301.12ms
step:3319/5100 train_loss:3.4091 train_time:996283ms step_avg:301.08ms
step:3320/5100 train_loss:3.4863 train_time:996479ms step_avg:301.05ms
step:3321/5100 train_loss:3.4150 train_time:997711ms step_avg:301.33ms
step:3322/5100 train_loss:3.4924 train_time:997911ms step_avg:301.30ms
step:3323/5100 train_loss:3.4218 train_time:998105ms step_avg:301.27ms
step:3324/5100 train_loss:3.3470 train_time:998300ms step_avg:301.24ms
step:3325/5100 train_loss:3.2834 train_time:998496ms step_avg:301.21ms
step:3326/5100 train_loss:3.4471 train_time:998690ms step_avg:301.17ms
step:3327/5100 train_loss:3.4042 train_time:998883ms step_avg:301.14ms
step:3328/5100 train_loss:3.3349 train_time:999079ms step_avg:301.11ms
step:3329/5100 train_loss:3.3716 train_time:999276ms step_avg:301.08ms
step:3330/5100 train_loss:3.3224 train_time:999470ms step_avg:301.05ms
step:3331/5100 train_loss:3.5742 train_time:1000701ms step_avg:301.33ms
step:3332/5100 train_loss:3.4624 train_time:1000902ms step_avg:301.30ms
step:3333/5100 train_loss:3.4513 train_time:1001098ms step_avg:301.26ms
step:3334/5100 train_loss:3.3152 train_time:1001294ms step_avg:301.23ms
step:3335/5100 train_loss:3.3883 train_time:1001489ms step_avg:301.20ms
step:3336/5100 train_loss:3.4883 train_time:1001684ms step_avg:301.17ms
step:3337/5100 train_loss:3.4616 train_time:1001880ms step_avg:301.14ms
step:3338/5100 train_loss:3.4928 train_time:1002075ms step_avg:301.10ms
step:3339/5100 train_loss:3.4234 train_time:1002269ms step_avg:301.07ms
step:3340/5100 train_loss:3.4475 train_time:1002463ms step_avg:301.04ms
step:3341/5100 train_loss:3.4603 train_time:1003697ms step_avg:301.32ms
step:3342/5100 train_loss:3.4699 train_time:1003896ms step_avg:301.29ms
step:3343/5100 train_loss:3.4635 train_time:1004091ms step_avg:301.26ms
step:3344/5100 train_loss:3.3890 train_time:1004285ms step_avg:301.23ms
step:3345/5100 train_loss:3.3037 train_time:1004480ms step_avg:301.19ms
step:3346/5100 train_loss:3.6281 train_time:1004674ms step_avg:301.16ms
step:3347/5100 train_loss:3.3881 train_time:1004869ms step_avg:301.13ms
step:3348/5100 train_loss:3.5527 train_time:1005064ms step_avg:301.10ms
step:3349/5100 train_loss:3.4224 train_time:1005259ms step_avg:301.07ms
step:3350/5100 train_loss:3.5041 train_time:1005454ms step_avg:301.03ms
step:3351/5100 train_loss:3.2439 train_time:1006687ms step_avg:301.31ms
step:3352/5100 train_loss:3.2711 train_time:1006887ms step_avg:301.28ms
step:3353/5100 train_loss:3.4505 train_time:1007081ms step_avg:301.25ms
step:3354/5100 train_loss:3.3148 train_time:1007277ms step_avg:301.22ms
step:3355/5100 train_loss:3.4701 train_time:1007471ms step_avg:301.19ms
step:3356/5100 train_loss:3.3341 train_time:1007667ms step_avg:301.16ms
step:3357/5100 train_loss:3.5037 train_time:1007861ms step_avg:301.12ms
step:3358/5100 train_loss:3.3606 train_time:1008056ms step_avg:301.09ms
step:3359/5100 train_loss:3.5309 train_time:1008252ms step_avg:301.06ms
step:3360/5100 train_loss:3.3449 train_time:1008447ms step_avg:301.03ms
step:3361/5100 train_loss:4.0266 train_time:1009677ms step_avg:301.31ms
step:3362/5100 train_loss:3.5011 train_time:1009877ms step_avg:301.28ms
step:3363/5100 train_loss:3.5363 train_time:1010073ms step_avg:301.24ms
step:3364/5100 train_loss:3.4051 train_time:1010269ms step_avg:301.21ms
step:3365/5100 train_loss:3.5284 train_time:1010463ms step_avg:301.18ms
step:3366/5100 train_loss:3.4252 train_time:1010658ms step_avg:301.15ms
step:3367/5100 train_loss:3.6030 train_time:1010853ms step_avg:301.12ms
step:3368/5100 train_loss:3.4050 train_time:1011048ms step_avg:301.09ms
step:3369/5100 train_loss:3.4287 train_time:1011243ms step_avg:301.05ms
step:3370/5100 train_loss:3.3956 train_time:1011439ms step_avg:301.02ms
step:3371/5100 train_loss:3.3554 train_time:1012671ms step_avg:301.30ms
step:3372/5100 train_loss:3.3598 train_time:1012874ms step_avg:301.27ms
step:3373/5100 train_loss:3.4178 train_time:1013069ms step_avg:301.24ms
step:3374/5100 train_loss:3.4523 train_time:1013263ms step_avg:301.21ms
step:3375/5100 train_loss:3.4201 train_time:1013458ms step_avg:301.18ms
step:3375/5100 val_loss:3.4294 train_time:1013490ms step_avg:301.19ms
step:3376/5100 train_loss:3.4652 train_time:1013668ms step_avg:301.15ms
step:3377/5100 train_loss:3.4621 train_time:1013865ms step_avg:301.12ms
step:3378/5100 train_loss:3.5400 train_time:1014060ms step_avg:301.09ms
step:3379/5100 train_loss:3.4022 train_time:1014255ms step_avg:301.06ms
step:3380/5100 train_loss:3.4138 train_time:1014451ms step_avg:301.02ms
step:3381/5100 train_loss:3.4121 train_time:1015682ms step_avg:301.30ms
step:3382/5100 train_loss:3.5171 train_time:1015883ms step_avg:301.27ms
step:3383/5100 train_loss:3.3572 train_time:1016078ms step_avg:301.24ms
step:3384/5100 train_loss:3.5311 train_time:1016272ms step_avg:301.21ms
step:3385/5100 train_loss:3.3811 train_time:1016468ms step_avg:301.18ms
step:3386/5100 train_loss:3.4051 train_time:1016665ms step_avg:301.14ms
step:3387/5100 train_loss:3.3480 train_time:1016860ms step_avg:301.11ms
step:3388/5100 train_loss:3.5299 train_time:1017054ms step_avg:301.08ms
step:3389/5100 train_loss:3.4918 train_time:1017249ms step_avg:301.05ms
step:3390/5100 train_loss:3.5040 train_time:1017445ms step_avg:301.02ms
step:3391/5100 train_loss:3.4858 train_time:1018676ms step_avg:301.29ms
step:3392/5100 train_loss:3.4261 train_time:1018877ms step_avg:301.26ms
step:3393/5100 train_loss:3.5434 train_time:1019071ms step_avg:301.23ms
step:3394/5100 train_loss:3.5038 train_time:1019267ms step_avg:301.20ms
step:3395/5100 train_loss:3.5958 train_time:1019462ms step_avg:301.17ms
step:3396/5100 train_loss:3.4526 train_time:1019656ms step_avg:301.14ms
step:3397/5100 train_loss:3.4451 train_time:1019852ms step_avg:301.11ms
step:3398/5100 train_loss:3.3971 train_time:1020047ms step_avg:301.08ms
step:3399/5100 train_loss:3.4545 train_time:1020243ms step_avg:301.05ms
step:3400/5100 train_loss:3.4404 train_time:1020439ms step_avg:301.01ms
step:3401/5100 train_loss:3.5384 train_time:1021670ms step_avg:301.29ms
step:3402/5100 train_loss:3.4067 train_time:1022013ms step_avg:301.30ms
step:3403/5100 train_loss:3.5956 train_time:1022207ms step_avg:301.27ms
step:3404/5100 train_loss:3.4171 train_time:1022404ms step_avg:301.24ms
step:3405/5100 train_loss:3.4294 train_time:1022599ms step_avg:301.21ms
step:3406/5100 train_loss:3.3772 train_time:1022794ms step_avg:301.18ms
step:3407/5100 train_loss:3.4393 train_time:1022990ms step_avg:301.14ms
step:3408/5100 train_loss:3.4377 train_time:1023184ms step_avg:301.11ms
step:3409/5100 train_loss:3.4296 train_time:1023379ms step_avg:301.08ms
step:3410/5100 train_loss:3.4455 train_time:1023573ms step_avg:301.05ms
step:3411/5100 train_loss:3.4022 train_time:1024804ms step_avg:301.32ms
step:3412/5100 train_loss:3.4369 train_time:1025005ms step_avg:301.29ms
step:3413/5100 train_loss:3.3650 train_time:1025201ms step_avg:301.26ms
step:3414/5100 train_loss:3.5783 train_time:1025394ms step_avg:301.23ms
step:3415/5100 train_loss:3.3335 train_time:1025589ms step_avg:301.20ms
step:3416/5100 train_loss:3.4850 train_time:1025785ms step_avg:301.17ms
step:3417/5100 train_loss:3.3672 train_time:1025981ms step_avg:301.14ms
step:3418/5100 train_loss:3.4660 train_time:1026177ms step_avg:301.11ms
step:3419/5100 train_loss:3.4743 train_time:1026372ms step_avg:301.08ms
step:3420/5100 train_loss:3.4962 train_time:1026736ms step_avg:301.10ms
step:3421/5100 train_loss:3.3742 train_time:1027965ms step_avg:301.37ms
step:3422/5100 train_loss:3.4186 train_time:1028168ms step_avg:301.34ms
step:3423/5100 train_loss:3.3495 train_time:1028363ms step_avg:301.31ms
step:3424/5100 train_loss:3.6625 train_time:1028557ms step_avg:301.28ms
step:3425/5100 train_loss:3.5566 train_time:1028752ms step_avg:301.25ms
step:3426/5100 train_loss:3.4278 train_time:1028948ms step_avg:301.21ms
step:3427/5100 train_loss:3.3819 train_time:1029142ms step_avg:301.18ms
step:3428/5100 train_loss:3.3587 train_time:1029337ms step_avg:301.15ms
step:3429/5100 train_loss:3.3636 train_time:1029531ms step_avg:301.12ms
step:3430/5100 train_loss:3.4236 train_time:1029727ms step_avg:301.09ms
step:3431/5100 train_loss:3.4542 train_time:1030959ms step_avg:301.36ms
step:3432/5100 train_loss:3.5522 train_time:1031161ms step_avg:301.33ms
step:3433/5100 train_loss:3.3624 train_time:1031356ms step_avg:301.30ms
step:3434/5100 train_loss:3.5832 train_time:1031551ms step_avg:301.27ms
step:3435/5100 train_loss:3.5053 train_time:1031746ms step_avg:301.24ms
step:3436/5100 train_loss:3.3487 train_time:1031940ms step_avg:301.21ms
step:3437/5100 train_loss:3.3881 train_time:1032135ms step_avg:301.18ms
step:3438/5100 train_loss:3.4399 train_time:1032329ms step_avg:301.15ms
step:3439/5100 train_loss:3.5349 train_time:1032525ms step_avg:301.12ms
step:3440/5100 train_loss:3.3074 train_time:1032719ms step_avg:301.08ms
step:3441/5100 train_loss:3.4838 train_time:1033949ms step_avg:301.35ms
step:3442/5100 train_loss:3.3882 train_time:1034151ms step_avg:301.33ms
step:3443/5100 train_loss:3.5707 train_time:1034346ms step_avg:301.30ms
step:3444/5100 train_loss:3.4332 train_time:1034540ms step_avg:301.26ms
step:3445/5100 train_loss:3.3204 train_time:1034734ms step_avg:301.23ms
step:3446/5100 train_loss:3.5327 train_time:1034930ms step_avg:301.20ms
step:3447/5100 train_loss:3.6077 train_time:1035125ms step_avg:301.17ms
step:3448/5100 train_loss:3.4249 train_time:1035321ms step_avg:301.14ms
step:3449/5100 train_loss:3.4390 train_time:1035515ms step_avg:301.11ms
step:3450/5100 train_loss:3.5218 train_time:1035710ms step_avg:301.08ms
step:3451/5100 train_loss:3.5248 train_time:1036941ms step_avg:301.35ms
step:3452/5100 train_loss:3.5293 train_time:1037143ms step_avg:301.32ms
step:3453/5100 train_loss:3.3382 train_time:1037338ms step_avg:301.29ms
step:3454/5100 train_loss:3.4534 train_time:1037531ms step_avg:301.26ms
step:3455/5100 train_loss:3.3359 train_time:1037726ms step_avg:301.23ms
step:3456/5100 train_loss:3.6227 train_time:1037921ms step_avg:301.20ms
step:3457/5100 train_loss:3.2985 train_time:1038115ms step_avg:301.16ms
step:3458/5100 train_loss:3.4465 train_time:1038310ms step_avg:301.13ms
step:3459/5100 train_loss:3.3888 train_time:1038505ms step_avg:301.10ms
step:3460/5100 train_loss:3.3884 train_time:1038700ms step_avg:301.07ms
step:3461/5100 train_loss:3.3861 train_time:1039930ms step_avg:301.34ms
step:3462/5100 train_loss:3.3925 train_time:1040131ms step_avg:301.31ms
step:3463/5100 train_loss:3.5012 train_time:1040327ms step_avg:301.28ms
step:3464/5100 train_loss:3.3690 train_time:1040522ms step_avg:301.25ms
step:3465/5100 train_loss:3.3846 train_time:1040717ms step_avg:301.22ms
step:3466/5100 train_loss:3.3611 train_time:1040910ms step_avg:301.19ms
step:3467/5100 train_loss:3.5204 train_time:1041105ms step_avg:301.16ms
step:3468/5100 train_loss:3.4025 train_time:1041302ms step_avg:301.13ms
step:3469/5100 train_loss:3.4232 train_time:1041497ms step_avg:301.10ms
step:3470/5100 train_loss:3.6104 train_time:1041691ms step_avg:301.07ms
step:3471/5100 train_loss:3.5097 train_time:1042922ms step_avg:301.34ms
step:3472/5100 train_loss:3.5523 train_time:1043124ms step_avg:301.31ms
step:3473/5100 train_loss:4.1839 train_time:1043318ms step_avg:301.28ms
step:3474/5100 train_loss:3.4300 train_time:1043512ms step_avg:301.24ms
step:3475/5100 train_loss:3.4336 train_time:1043707ms step_avg:301.21ms
step:3476/5100 train_loss:3.4163 train_time:1043902ms step_avg:301.18ms
step:3477/5100 train_loss:3.3588 train_time:1044096ms step_avg:301.15ms
step:3478/5100 train_loss:3.4361 train_time:1044291ms step_avg:301.12ms
step:3479/5100 train_loss:3.4290 train_time:1044487ms step_avg:301.09ms
step:3480/5100 train_loss:3.3356 train_time:1044681ms step_avg:301.06ms
step:3481/5100 train_loss:3.6383 train_time:1045913ms step_avg:301.33ms
step:3482/5100 train_loss:3.4959 train_time:1046114ms step_avg:301.30ms
step:3483/5100 train_loss:3.4473 train_time:1046310ms step_avg:301.27ms
step:3484/5100 train_loss:3.4664 train_time:1046505ms step_avg:301.24ms
step:3485/5100 train_loss:3.4319 train_time:1046700ms step_avg:301.21ms
step:3486/5100 train_loss:3.6122 train_time:1046896ms step_avg:301.18ms
step:3487/5100 train_loss:3.6512 train_time:1047091ms step_avg:301.15ms
step:3488/5100 train_loss:3.5064 train_time:1047286ms step_avg:301.12ms
step:3489/5100 train_loss:3.3613 train_time:1047481ms step_avg:301.09ms
step:3490/5100 train_loss:3.5301 train_time:1047675ms step_avg:301.06ms
step:3491/5100 train_loss:3.4370 train_time:1048904ms step_avg:301.32ms
step:3492/5100 train_loss:3.4836 train_time:1049106ms step_avg:301.29ms
step:3493/5100 train_loss:3.3212 train_time:1049302ms step_avg:301.26ms
step:3494/5100 train_loss:3.4519 train_time:1049497ms step_avg:301.23ms
step:3495/5100 train_loss:3.4107 train_time:1049691ms step_avg:301.20ms
step:3496/5100 train_loss:3.4259 train_time:1049887ms step_avg:301.17ms
step:3497/5100 train_loss:3.5939 train_time:1050082ms step_avg:301.14ms
step:3498/5100 train_loss:3.4234 train_time:1050276ms step_avg:301.11ms
step:3499/5100 train_loss:3.4557 train_time:1050470ms step_avg:301.08ms
step:3500/5100 train_loss:3.4523 train_time:1050666ms step_avg:301.05ms
step:3500/5100 val_loss:3.4226 train_time:1050698ms step_avg:301.06ms
step:3501/5100 train_loss:3.4950 train_time:1051914ms step_avg:301.32ms
step:3502/5100 train_loss:3.5725 train_time:1052116ms step_avg:301.29ms
step:3503/5100 train_loss:3.2752 train_time:1052311ms step_avg:301.26ms
step:3504/5100 train_loss:3.4383 train_time:1052505ms step_avg:301.23ms
step:3505/5100 train_loss:3.4639 train_time:1052700ms step_avg:301.20ms
step:3506/5100 train_loss:3.4826 train_time:1052895ms step_avg:301.17ms
step:3507/5100 train_loss:3.3602 train_time:1053090ms step_avg:301.14ms
step:3508/5100 train_loss:3.5030 train_time:1053283ms step_avg:301.11ms
step:3509/5100 train_loss:3.4014 train_time:1053479ms step_avg:301.08ms
step:3510/5100 train_loss:3.6157 train_time:1053674ms step_avg:301.05ms
step:3511/5100 train_loss:3.4177 train_time:1054904ms step_avg:301.31ms
step:3512/5100 train_loss:3.3716 train_time:1055104ms step_avg:301.29ms
step:3513/5100 train_loss:3.4340 train_time:1055299ms step_avg:301.26ms
step:3514/5100 train_loss:3.3945 train_time:1055496ms step_avg:301.23ms
step:3515/5100 train_loss:3.4513 train_time:1055691ms step_avg:301.20ms
step:3516/5100 train_loss:3.4424 train_time:1055884ms step_avg:301.16ms
step:3517/5100 train_loss:3.4231 train_time:1056080ms step_avg:301.13ms
step:3518/5100 train_loss:3.4425 train_time:1056275ms step_avg:301.10ms
step:3519/5100 train_loss:3.4320 train_time:1056470ms step_avg:301.07ms
step:3520/5100 train_loss:3.4557 train_time:1056665ms step_avg:301.04ms
step:3521/5100 train_loss:3.5249 train_time:1057897ms step_avg:301.31ms
step:3522/5100 train_loss:3.4370 train_time:1058098ms step_avg:301.28ms
step:3523/5100 train_loss:3.3663 train_time:1058295ms step_avg:301.25ms
step:3524/5100 train_loss:3.4039 train_time:1058491ms step_avg:301.22ms
step:3525/5100 train_loss:3.4018 train_time:1058685ms step_avg:301.19ms
step:3526/5100 train_loss:3.4027 train_time:1058881ms step_avg:301.16ms
step:3527/5100 train_loss:3.5286 train_time:1059076ms step_avg:301.13ms
step:3528/5100 train_loss:3.3605 train_time:1059271ms step_avg:301.10ms
step:3529/5100 train_loss:3.2535 train_time:1059465ms step_avg:301.07ms
step:3530/5100 train_loss:3.5430 train_time:1059661ms step_avg:301.04ms
step:3531/5100 train_loss:3.3480 train_time:1060892ms step_avg:301.30ms
step:3532/5100 train_loss:3.3853 train_time:1061094ms step_avg:301.28ms
step:3533/5100 train_loss:3.3024 train_time:1061288ms step_avg:301.25ms
step:3534/5100 train_loss:3.3624 train_time:1061483ms step_avg:301.22ms
step:3535/5100 train_loss:3.3371 train_time:1061679ms step_avg:301.19ms
step:3536/5100 train_loss:3.5086 train_time:1061874ms step_avg:301.16ms
step:3537/5100 train_loss:3.4632 train_time:1062067ms step_avg:301.12ms
step:3538/5100 train_loss:3.4895 train_time:1062263ms step_avg:301.10ms
step:3539/5100 train_loss:3.3911 train_time:1062458ms step_avg:301.06ms
step:3540/5100 train_loss:3.3677 train_time:1062652ms step_avg:301.03ms
step:3541/5100 train_loss:3.5009 train_time:1063883ms step_avg:301.30ms
step:3542/5100 train_loss:3.3523 train_time:1064084ms step_avg:301.27ms
step:3543/5100 train_loss:3.5715 train_time:1064281ms step_avg:301.24ms
step:3544/5100 train_loss:3.6857 train_time:1064476ms step_avg:301.21ms
step:3545/5100 train_loss:3.5020 train_time:1064671ms step_avg:301.18ms
step:3546/5100 train_loss:3.5316 train_time:1064866ms step_avg:301.15ms
step:3547/5100 train_loss:3.3007 train_time:1065062ms step_avg:301.12ms
step:3548/5100 train_loss:3.3788 train_time:1065258ms step_avg:301.09ms
step:3549/5100 train_loss:3.4064 train_time:1065452ms step_avg:301.06ms
step:3550/5100 train_loss:3.4995 train_time:1065646ms step_avg:301.03ms
step:3551/5100 train_loss:3.4613 train_time:1066877ms step_avg:301.29ms
step:3552/5100 train_loss:3.3860 train_time:1067080ms step_avg:301.26ms
step:3553/5100 train_loss:3.4998 train_time:1067276ms step_avg:301.24ms
step:3554/5100 train_loss:3.4362 train_time:1067470ms step_avg:301.20ms
step:3555/5100 train_loss:3.3934 train_time:1067664ms step_avg:301.17ms
step:3556/5100 train_loss:3.3319 train_time:1067860ms step_avg:301.14ms
step:3557/5100 train_loss:3.2917 train_time:1068055ms step_avg:301.11ms
step:3558/5100 train_loss:3.4133 train_time:1068250ms step_avg:301.08ms
step:3559/5100 train_loss:3.4274 train_time:1068444ms step_avg:301.05ms
step:3560/5100 train_loss:3.6307 train_time:1068641ms step_avg:301.03ms
step:3561/5100 train_loss:3.5054 train_time:1069872ms step_avg:301.29ms
step:3562/5100 train_loss:3.4032 train_time:1070072ms step_avg:301.26ms
step:3563/5100 train_loss:3.2860 train_time:1070265ms step_avg:301.23ms
step:3564/5100 train_loss:3.7940 train_time:1070461ms step_avg:301.20ms
step:3565/5100 train_loss:3.3701 train_time:1070657ms step_avg:301.17ms
step:3566/5100 train_loss:3.3111 train_time:1070851ms step_avg:301.14ms
step:3567/5100 train_loss:3.3304 train_time:1071045ms step_avg:301.11ms
step:3568/5100 train_loss:3.4738 train_time:1071240ms step_avg:301.08ms
step:3569/5100 train_loss:3.4023 train_time:1071437ms step_avg:301.05ms
step:3570/5100 train_loss:3.5286 train_time:1071631ms step_avg:301.02ms
step:3571/5100 train_loss:3.4422 train_time:1072862ms step_avg:301.28ms
step:3572/5100 train_loss:3.7250 train_time:1073063ms step_avg:301.25ms
step:3573/5100 train_loss:3.3503 train_time:1073259ms step_avg:301.22ms
step:3574/5100 train_loss:3.4299 train_time:1073454ms step_avg:301.19ms
step:3575/5100 train_loss:3.5897 train_time:1073649ms step_avg:301.16ms
step:3576/5100 train_loss:3.4652 train_time:1073844ms step_avg:301.13ms
step:3577/5100 train_loss:3.4038 train_time:1074039ms step_avg:301.10ms
step:3578/5100 train_loss:3.3728 train_time:1074234ms step_avg:301.07ms
step:3579/5100 train_loss:3.4481 train_time:1074430ms step_avg:301.05ms
step:3580/5100 train_loss:3.4020 train_time:1074624ms step_avg:301.02ms
step:3581/5100 train_loss:3.2958 train_time:1075855ms step_avg:301.28ms
step:3582/5100 train_loss:3.3755 train_time:1076059ms step_avg:301.25ms
step:3583/5100 train_loss:3.3234 train_time:1076256ms step_avg:301.22ms
step:3584/5100 train_loss:3.4329 train_time:1076451ms step_avg:301.19ms
step:3585/5100 train_loss:3.5257 train_time:1076645ms step_avg:301.16ms
step:3586/5100 train_loss:3.3720 train_time:1076839ms step_avg:301.13ms
step:3587/5100 train_loss:3.4175 train_time:1077033ms step_avg:301.10ms
step:3588/5100 train_loss:3.4251 train_time:1077227ms step_avg:301.07ms
step:3589/5100 train_loss:3.4037 train_time:1077423ms step_avg:301.04ms
step:3590/5100 train_loss:3.4054 train_time:1077617ms step_avg:301.01ms
step:3591/5100 train_loss:3.5264 train_time:1078987ms step_avg:301.31ms
step:3592/5100 train_loss:3.3897 train_time:1079188ms step_avg:301.28ms
step:3593/5100 train_loss:3.4837 train_time:1079384ms step_avg:301.25ms
step:3594/5100 train_loss:3.4634 train_time:1079580ms step_avg:301.22ms
step:3595/5100 train_loss:3.4266 train_time:1079777ms step_avg:301.19ms
step:3596/5100 train_loss:3.3502 train_time:1079972ms step_avg:301.16ms
step:3597/5100 train_loss:3.3586 train_time:1080167ms step_avg:301.13ms
step:3598/5100 train_loss:3.6279 train_time:1080361ms step_avg:301.10ms
step:3599/5100 train_loss:3.4078 train_time:1080556ms step_avg:301.07ms
step:3600/5100 train_loss:3.4181 train_time:1080751ms step_avg:301.04ms
step:3601/5100 train_loss:3.2828 train_time:1081981ms step_avg:301.30ms
step:3602/5100 train_loss:3.4598 train_time:1082183ms step_avg:301.28ms
step:3603/5100 train_loss:3.4077 train_time:1082380ms step_avg:301.25ms
step:3604/5100 train_loss:3.5118 train_time:1082577ms step_avg:301.22ms
step:3605/5100 train_loss:3.6060 train_time:1082773ms step_avg:301.19ms
step:3606/5100 train_loss:3.4063 train_time:1082967ms step_avg:301.16ms
step:3607/5100 train_loss:3.4477 train_time:1083162ms step_avg:301.13ms
step:3608/5100 train_loss:3.7100 train_time:1083357ms step_avg:301.10ms
step:3609/5100 train_loss:3.4011 train_time:1083552ms step_avg:301.07ms
step:3610/5100 train_loss:3.5462 train_time:1083917ms step_avg:301.09ms
step:3611/5100 train_loss:3.2959 train_time:1085146ms step_avg:301.35ms
step:3612/5100 train_loss:3.4035 train_time:1085348ms step_avg:301.32ms
step:3613/5100 train_loss:3.4732 train_time:1085543ms step_avg:301.29ms
step:3614/5100 train_loss:3.6753 train_time:1085739ms step_avg:301.26ms
step:3615/5100 train_loss:3.6840 train_time:1085935ms step_avg:301.23ms
step:3616/5100 train_loss:3.3289 train_time:1086130ms step_avg:301.20ms
step:3617/5100 train_loss:3.4323 train_time:1086325ms step_avg:301.17ms
step:3618/5100 train_loss:3.3957 train_time:1086520ms step_avg:301.14ms
step:3619/5100 train_loss:3.5214 train_time:1086715ms step_avg:301.11ms
step:3620/5100 train_loss:3.4614 train_time:1086910ms step_avg:301.08ms
step:3621/5100 train_loss:3.2865 train_time:1088141ms step_avg:301.34ms
step:3622/5100 train_loss:3.4304 train_time:1088343ms step_avg:301.31ms
step:3623/5100 train_loss:3.4298 train_time:1088538ms step_avg:301.28ms
step:3624/5100 train_loss:3.3670 train_time:1088734ms step_avg:301.25ms
step:3625/5100 train_loss:3.4930 train_time:1088929ms step_avg:301.23ms
step:3625/5100 val_loss:3.4187 train_time:1088961ms step_avg:301.23ms
step:3626/5100 train_loss:3.5584 train_time:1089142ms step_avg:301.20ms
step:3627/5100 train_loss:3.5744 train_time:1089339ms step_avg:301.17ms
step:3628/5100 train_loss:3.4550 train_time:1089534ms step_avg:301.14ms
step:3629/5100 train_loss:3.5976 train_time:1089729ms step_avg:301.11ms
step:3630/5100 train_loss:3.4308 train_time:1089924ms step_avg:301.08ms
step:3631/5100 train_loss:3.4247 train_time:1091154ms step_avg:301.34ms
step:3632/5100 train_loss:3.5088 train_time:1091355ms step_avg:301.31ms
step:3633/5100 train_loss:3.4930 train_time:1091551ms step_avg:301.28ms
step:3634/5100 train_loss:3.4139 train_time:1091745ms step_avg:301.25ms
step:3635/5100 train_loss:3.4213 train_time:1091939ms step_avg:301.22ms
step:3636/5100 train_loss:3.4650 train_time:1092134ms step_avg:301.20ms
step:3637/5100 train_loss:3.6484 train_time:1092330ms step_avg:301.17ms
step:3638/5100 train_loss:3.4523 train_time:1092524ms step_avg:301.14ms
step:3639/5100 train_loss:3.4085 train_time:1092719ms step_avg:301.11ms
step:3640/5100 train_loss:3.4090 train_time:1092914ms step_avg:301.08ms
step:3641/5100 train_loss:3.6923 train_time:1094146ms step_avg:301.33ms
step:3642/5100 train_loss:3.4252 train_time:1094348ms step_avg:301.31ms
step:3643/5100 train_loss:3.4723 train_time:1094543ms step_avg:301.28ms
step:3644/5100 train_loss:3.4446 train_time:1094737ms step_avg:301.25ms
step:3645/5100 train_loss:3.3674 train_time:1094933ms step_avg:301.22ms
step:3646/5100 train_loss:3.5593 train_time:1095129ms step_avg:301.19ms
step:3647/5100 train_loss:3.3447 train_time:1095322ms step_avg:301.16ms
step:3648/5100 train_loss:3.4165 train_time:1095517ms step_avg:301.13ms
step:3649/5100 train_loss:3.4788 train_time:1095712ms step_avg:301.10ms
step:3650/5100 train_loss:3.4370 train_time:1095907ms step_avg:301.07ms
step:3651/5100 train_loss:3.4769 train_time:1097139ms step_avg:301.33ms
step:3652/5100 train_loss:3.5339 train_time:1097339ms step_avg:301.30ms
step:3653/5100 train_loss:3.3549 train_time:1097535ms step_avg:301.27ms
step:3654/5100 train_loss:3.4583 train_time:1097730ms step_avg:301.24ms
step:3655/5100 train_loss:3.4836 train_time:1097926ms step_avg:301.21ms
step:3656/5100 train_loss:4.1637 train_time:1098120ms step_avg:301.18ms
step:3657/5100 train_loss:3.5485 train_time:1098314ms step_avg:301.16ms
step:3658/5100 train_loss:3.4569 train_time:1098509ms step_avg:301.13ms
step:3659/5100 train_loss:3.4454 train_time:1098704ms step_avg:301.10ms
step:3660/5100 train_loss:3.3274 train_time:1098898ms step_avg:301.07ms
step:3661/5100 train_loss:3.4561 train_time:1100129ms step_avg:301.32ms
step:3662/5100 train_loss:3.3306 train_time:1100330ms step_avg:301.30ms
step:3663/5100 train_loss:3.4788 train_time:1100525ms step_avg:301.27ms
step:3664/5100 train_loss:3.4876 train_time:1100720ms step_avg:301.24ms
step:3665/5100 train_loss:3.3295 train_time:1100915ms step_avg:301.21ms
step:3666/5100 train_loss:3.2603 train_time:1101109ms step_avg:301.18ms
step:3667/5100 train_loss:3.6815 train_time:1101304ms step_avg:301.15ms
step:3668/5100 train_loss:3.4741 train_time:1101498ms step_avg:301.12ms
step:3669/5100 train_loss:3.4973 train_time:1101694ms step_avg:301.09ms
step:3670/5100 train_loss:3.4171 train_time:1101889ms step_avg:301.06ms
step:3671/5100 train_loss:3.4875 train_time:1103119ms step_avg:301.32ms
step:3672/5100 train_loss:3.3809 train_time:1103321ms step_avg:301.29ms
step:3673/5100 train_loss:3.3828 train_time:1103516ms step_avg:301.26ms
step:3674/5100 train_loss:3.2761 train_time:1103712ms step_avg:301.23ms
step:3675/5100 train_loss:3.3594 train_time:1103907ms step_avg:301.20ms
step:3676/5100 train_loss:3.5172 train_time:1104102ms step_avg:301.17ms
step:3677/5100 train_loss:3.3224 train_time:1104296ms step_avg:301.14ms
step:3678/5100 train_loss:3.4833 train_time:1104491ms step_avg:301.12ms
step:3679/5100 train_loss:3.4746 train_time:1104687ms step_avg:301.09ms
step:3680/5100 train_loss:3.3723 train_time:1104881ms step_avg:301.06ms
step:3681/5100 train_loss:3.4361 train_time:1106112ms step_avg:301.31ms
step:3682/5100 train_loss:3.5047 train_time:1106313ms step_avg:301.28ms
step:3683/5100 train_loss:3.6013 train_time:1106508ms step_avg:301.25ms
step:3684/5100 train_loss:3.3494 train_time:1106702ms step_avg:301.23ms
step:3685/5100 train_loss:3.4278 train_time:1106896ms step_avg:301.20ms
step:3686/5100 train_loss:3.5682 train_time:1107091ms step_avg:301.17ms
step:3687/5100 train_loss:3.3495 train_time:1107286ms step_avg:301.14ms
step:3688/5100 train_loss:3.5558 train_time:1107481ms step_avg:301.11ms
step:3689/5100 train_loss:3.2911 train_time:1107675ms step_avg:301.08ms
step:3690/5100 train_loss:3.3808 train_time:1107871ms step_avg:301.05ms
step:3691/5100 train_loss:3.5136 train_time:1109102ms step_avg:301.30ms
step:3692/5100 train_loss:3.2992 train_time:1109302ms step_avg:301.28ms
step:3693/5100 train_loss:3.4512 train_time:1109498ms step_avg:301.25ms
step:3694/5100 train_loss:3.4295 train_time:1109693ms step_avg:301.22ms
step:3695/5100 train_loss:3.4306 train_time:1109889ms step_avg:301.19ms
step:3696/5100 train_loss:3.4635 train_time:1110083ms step_avg:301.16ms
step:3697/5100 train_loss:3.3046 train_time:1110277ms step_avg:301.13ms
step:3698/5100 train_loss:3.4442 train_time:1110473ms step_avg:301.10ms
step:3699/5100 train_loss:3.4617 train_time:1110667ms step_avg:301.08ms
step:3700/5100 train_loss:3.4320 train_time:1110862ms step_avg:301.05ms
step:3701/5100 train_loss:3.4989 train_time:1112093ms step_avg:301.30ms
step:3702/5100 train_loss:3.4592 train_time:1112293ms step_avg:301.27ms
step:3703/5100 train_loss:3.3759 train_time:1112489ms step_avg:301.24ms
step:3704/5100 train_loss:3.3560 train_time:1112683ms step_avg:301.21ms
step:3705/5100 train_loss:3.4937 train_time:1112877ms step_avg:301.18ms
step:3706/5100 train_loss:3.4962 train_time:1113073ms step_avg:301.16ms
step:3707/5100 train_loss:3.4997 train_time:1113268ms step_avg:301.13ms
step:3708/5100 train_loss:3.4570 train_time:1113463ms step_avg:301.10ms
step:3709/5100 train_loss:3.3273 train_time:1113657ms step_avg:301.07ms
step:3710/5100 train_loss:3.6353 train_time:1113852ms step_avg:301.04ms
step:3711/5100 train_loss:3.2173 train_time:1115084ms step_avg:301.29ms
step:3712/5100 train_loss:3.4884 train_time:1115287ms step_avg:301.27ms
step:3713/5100 train_loss:3.3695 train_time:1115483ms step_avg:301.24ms
step:3714/5100 train_loss:3.4008 train_time:1115677ms step_avg:301.21ms
step:3715/5100 train_loss:3.7843 train_time:1115872ms step_avg:301.18ms
step:3716/5100 train_loss:3.6292 train_time:1116067ms step_avg:301.15ms
step:3717/5100 train_loss:3.8959 train_time:1116262ms step_avg:301.12ms
step:3718/5100 train_loss:3.4048 train_time:1116455ms step_avg:301.09ms
step:3719/5100 train_loss:3.3152 train_time:1116650ms step_avg:301.06ms
step:3720/5100 train_loss:3.5760 train_time:1116846ms step_avg:301.04ms
step:3721/5100 train_loss:3.3386 train_time:1118076ms step_avg:301.29ms
step:3722/5100 train_loss:3.4338 train_time:1118277ms step_avg:301.26ms
step:3723/5100 train_loss:3.3000 train_time:1118472ms step_avg:301.23ms
step:3724/5100 train_loss:3.2894 train_time:1118668ms step_avg:301.20ms
step:3725/5100 train_loss:3.4139 train_time:1118862ms step_avg:301.17ms
step:3726/5100 train_loss:3.3665 train_time:1119057ms step_avg:301.15ms
step:3727/5100 train_loss:3.6378 train_time:1119252ms step_avg:301.12ms
step:3728/5100 train_loss:3.3613 train_time:1119446ms step_avg:301.09ms
step:3729/5100 train_loss:3.3595 train_time:1119640ms step_avg:301.06ms
step:3730/5100 train_loss:3.7138 train_time:1119835ms step_avg:301.03ms
step:3731/5100 train_loss:3.4781 train_time:1121066ms step_avg:301.28ms
step:3732/5100 train_loss:3.3806 train_time:1121266ms step_avg:301.25ms
step:3733/5100 train_loss:3.2502 train_time:1121460ms step_avg:301.22ms
step:3734/5100 train_loss:3.4837 train_time:1121656ms step_avg:301.20ms
step:3735/5100 train_loss:3.3458 train_time:1121851ms step_avg:301.17ms
step:3736/5100 train_loss:3.4455 train_time:1122046ms step_avg:301.14ms
step:3737/5100 train_loss:3.3594 train_time:1122240ms step_avg:301.11ms
step:3738/5100 train_loss:3.4511 train_time:1122435ms step_avg:301.08ms
step:3739/5100 train_loss:3.3629 train_time:1122630ms step_avg:301.05ms
step:3740/5100 train_loss:3.4109 train_time:1122824ms step_avg:301.03ms
step:3741/5100 train_loss:3.7076 train_time:1124054ms step_avg:301.27ms
step:3742/5100 train_loss:3.3623 train_time:1124255ms step_avg:301.25ms
step:3743/5100 train_loss:3.4095 train_time:1124450ms step_avg:301.22ms
step:3744/5100 train_loss:3.6237 train_time:1124645ms step_avg:301.19ms
step:3745/5100 train_loss:3.3375 train_time:1124841ms step_avg:301.16ms
step:3746/5100 train_loss:3.2757 train_time:1125036ms step_avg:301.13ms
step:3747/5100 train_loss:3.4602 train_time:1125232ms step_avg:301.11ms
step:3748/5100 train_loss:3.3082 train_time:1125427ms step_avg:301.08ms
step:3749/5100 train_loss:3.3538 train_time:1125623ms step_avg:301.05ms
step:3750/5100 train_loss:3.5485 train_time:1125816ms step_avg:301.02ms
step:3750/5100 val_loss:3.4068 train_time:1125849ms step_avg:301.03ms
step:3751/5100 train_loss:3.4322 train_time:1127065ms step_avg:301.27ms
step:3752/5100 train_loss:3.6739 train_time:1127269ms step_avg:301.25ms
step:3753/5100 train_loss:3.3829 train_time:1127465ms step_avg:301.22ms
step:3754/5100 train_loss:3.3870 train_time:1127661ms step_avg:301.19ms
step:3755/5100 train_loss:3.3537 train_time:1127857ms step_avg:301.16ms
step:3756/5100 train_loss:3.4533 train_time:1128052ms step_avg:301.14ms
step:3757/5100 train_loss:3.4044 train_time:1128246ms step_avg:301.11ms
step:3758/5100 train_loss:3.4119 train_time:1128440ms step_avg:301.08ms
step:3759/5100 train_loss:3.5944 train_time:1128635ms step_avg:301.05ms
step:3760/5100 train_loss:3.4768 train_time:1128831ms step_avg:301.02ms
step:3761/5100 train_loss:3.5825 train_time:1130060ms step_avg:301.27ms
step:3762/5100 train_loss:3.3639 train_time:1130260ms step_avg:301.24ms
step:3763/5100 train_loss:3.3713 train_time:1130457ms step_avg:301.21ms
step:3764/5100 train_loss:3.5399 train_time:1130652ms step_avg:301.19ms
step:3765/5100 train_loss:3.2939 train_time:1130846ms step_avg:301.16ms
step:3766/5100 train_loss:3.3845 train_time:1131042ms step_avg:301.13ms
step:3767/5100 train_loss:3.4782 train_time:1131237ms step_avg:301.10ms
step:3768/5100 train_loss:3.2835 train_time:1131432ms step_avg:301.07ms
step:3769/5100 train_loss:3.5527 train_time:1131626ms step_avg:301.04ms
step:3770/5100 train_loss:3.3695 train_time:1131821ms step_avg:301.02ms
step:3771/5100 train_loss:3.2425 train_time:1133053ms step_avg:301.26ms
step:3772/5100 train_loss:3.4921 train_time:1133253ms step_avg:301.24ms
step:3773/5100 train_loss:3.4149 train_time:1133447ms step_avg:301.21ms
step:3774/5100 train_loss:3.4131 train_time:1133642ms step_avg:301.18ms
step:3775/5100 train_loss:3.4017 train_time:1133837ms step_avg:301.15ms
step:3776/5100 train_loss:3.4563 train_time:1134032ms step_avg:301.12ms
step:3777/5100 train_loss:3.2866 train_time:1134226ms step_avg:301.10ms
step:3778/5100 train_loss:3.4005 train_time:1134422ms step_avg:301.07ms
step:3779/5100 train_loss:3.5172 train_time:1134617ms step_avg:301.04ms
step:3780/5100 train_loss:3.4927 train_time:1134957ms step_avg:301.05ms
step:3781/5100 train_loss:3.4893 train_time:1136187ms step_avg:301.30ms
step:3782/5100 train_loss:3.4396 train_time:1136390ms step_avg:301.27ms
step:3783/5100 train_loss:3.4420 train_time:1136584ms step_avg:301.24ms
step:3784/5100 train_loss:3.4066 train_time:1136779ms step_avg:301.21ms
step:3785/5100 train_loss:3.2969 train_time:1136973ms step_avg:301.18ms
step:3786/5100 train_loss:3.3784 train_time:1137167ms step_avg:301.16ms
step:3787/5100 train_loss:3.4220 train_time:1137362ms step_avg:301.13ms
step:3788/5100 train_loss:3.4029 train_time:1137558ms step_avg:301.10ms
step:3789/5100 train_loss:3.3580 train_time:1137753ms step_avg:301.07ms
step:3790/5100 train_loss:3.3831 train_time:1137948ms step_avg:301.04ms
step:3791/5100 train_loss:3.2496 train_time:1139178ms step_avg:301.29ms
step:3792/5100 train_loss:3.4713 train_time:1139381ms step_avg:301.26ms
step:3793/5100 train_loss:3.4583 train_time:1139576ms step_avg:301.24ms
step:3794/5100 train_loss:3.3828 train_time:1139771ms step_avg:301.21ms
step:3795/5100 train_loss:3.3423 train_time:1139966ms step_avg:301.18ms
step:3796/5100 train_loss:3.1923 train_time:1140161ms step_avg:301.15ms
step:3797/5100 train_loss:3.3849 train_time:1140357ms step_avg:301.12ms
step:3798/5100 train_loss:3.3880 train_time:1140553ms step_avg:301.10ms
step:3799/5100 train_loss:3.4541 train_time:1140747ms step_avg:301.07ms
step:3800/5100 train_loss:3.3565 train_time:1141110ms step_avg:301.08ms
step:3801/5100 train_loss:3.3384 train_time:1142340ms step_avg:301.33ms
step:3802/5100 train_loss:3.2942 train_time:1142540ms step_avg:301.30ms
step:3803/5100 train_loss:3.5996 train_time:1142735ms step_avg:301.27ms
step:3804/5100 train_loss:3.4544 train_time:1142930ms step_avg:301.25ms
step:3805/5100 train_loss:3.3076 train_time:1143124ms step_avg:301.22ms
step:3806/5100 train_loss:3.5430 train_time:1143318ms step_avg:301.19ms
step:3807/5100 train_loss:3.5124 train_time:1143514ms step_avg:301.16ms
step:3808/5100 train_loss:3.3756 train_time:1143709ms step_avg:301.13ms
step:3809/5100 train_loss:3.4422 train_time:1143904ms step_avg:301.11ms
step:3810/5100 train_loss:3.3499 train_time:1144100ms step_avg:301.08ms
step:3811/5100 train_loss:3.4226 train_time:1145332ms step_avg:301.32ms
step:3812/5100 train_loss:3.3998 train_time:1145531ms step_avg:301.30ms
step:3813/5100 train_loss:3.4295 train_time:1145727ms step_avg:301.27ms
step:3814/5100 train_loss:3.4293 train_time:1145921ms step_avg:301.24ms
step:3815/5100 train_loss:3.4536 train_time:1146116ms step_avg:301.21ms
step:3816/5100 train_loss:3.6507 train_time:1146311ms step_avg:301.19ms
step:3817/5100 train_loss:3.2537 train_time:1146505ms step_avg:301.16ms
step:3818/5100 train_loss:3.4416 train_time:1146701ms step_avg:301.13ms
step:3819/5100 train_loss:3.4101 train_time:1146897ms step_avg:301.10ms
step:3820/5100 train_loss:3.3909 train_time:1147092ms step_avg:301.07ms
step:3821/5100 train_loss:3.3282 train_time:1148322ms step_avg:301.32ms
step:3822/5100 train_loss:3.5029 train_time:1148523ms step_avg:301.29ms
step:3823/5100 train_loss:3.2288 train_time:1148719ms step_avg:301.26ms
step:3824/5100 train_loss:3.3444 train_time:1148915ms step_avg:301.24ms
step:3825/5100 train_loss:3.3955 train_time:1149110ms step_avg:301.21ms
step:3826/5100 train_loss:3.5438 train_time:1149304ms step_avg:301.18ms
step:3827/5100 train_loss:3.4826 train_time:1149499ms step_avg:301.15ms
step:3828/5100 train_loss:3.8459 train_time:1149695ms step_avg:301.13ms
step:3829/5100 train_loss:3.4769 train_time:1149891ms step_avg:301.10ms
step:3830/5100 train_loss:3.2983 train_time:1150085ms step_avg:301.07ms
step:3831/5100 train_loss:3.3452 train_time:1151317ms step_avg:301.31ms
step:3832/5100 train_loss:3.5522 train_time:1151517ms step_avg:301.29ms
step:3833/5100 train_loss:3.3653 train_time:1151712ms step_avg:301.26ms
step:3834/5100 train_loss:3.4891 train_time:1151907ms step_avg:301.23ms
step:3835/5100 train_loss:3.4195 train_time:1152101ms step_avg:301.20ms
step:3836/5100 train_loss:3.2287 train_time:1152297ms step_avg:301.18ms
step:3837/5100 train_loss:3.5087 train_time:1152494ms step_avg:301.15ms
step:3838/5100 train_loss:3.4764 train_time:1152689ms step_avg:301.12ms
step:3839/5100 train_loss:3.4408 train_time:1152884ms step_avg:301.09ms
step:3840/5100 train_loss:3.4969 train_time:1153079ms step_avg:301.07ms
step:3841/5100 train_loss:3.6225 train_time:1154310ms step_avg:301.31ms
step:3842/5100 train_loss:3.3757 train_time:1154512ms step_avg:301.28ms
step:3843/5100 train_loss:3.4270 train_time:1154707ms step_avg:301.25ms
step:3844/5100 train_loss:3.5670 train_time:1154903ms step_avg:301.23ms
step:3845/5100 train_loss:3.3704 train_time:1155098ms step_avg:301.20ms
step:3846/5100 train_loss:3.2395 train_time:1155293ms step_avg:301.17ms
step:3847/5100 train_loss:3.4733 train_time:1155489ms step_avg:301.14ms
step:3848/5100 train_loss:3.3978 train_time:1155683ms step_avg:301.12ms
step:3849/5100 train_loss:3.4401 train_time:1155879ms step_avg:301.09ms
step:3850/5100 train_loss:3.3319 train_time:1156074ms step_avg:301.06ms
step:3851/5100 train_loss:3.3225 train_time:1157305ms step_avg:301.30ms
step:3852/5100 train_loss:3.4818 train_time:1157506ms step_avg:301.28ms
step:3853/5100 train_loss:3.3325 train_time:1157701ms step_avg:301.25ms
step:3854/5100 train_loss:3.2981 train_time:1157897ms step_avg:301.22ms
step:3855/5100 train_loss:3.3791 train_time:1158093ms step_avg:301.19ms
step:3856/5100 train_loss:3.4181 train_time:1158288ms step_avg:301.17ms
step:3857/5100 train_loss:3.3893 train_time:1158484ms step_avg:301.14ms
step:3858/5100 train_loss:3.4138 train_time:1158679ms step_avg:301.11ms
step:3859/5100 train_loss:3.3981 train_time:1158874ms step_avg:301.08ms
step:3860/5100 train_loss:3.4113 train_time:1159069ms step_avg:301.06ms
step:3861/5100 train_loss:3.5646 train_time:1160300ms step_avg:301.30ms
step:3862/5100 train_loss:3.3719 train_time:1160501ms step_avg:301.27ms
step:3863/5100 train_loss:3.4954 train_time:1160697ms step_avg:301.25ms
step:3864/5100 train_loss:3.4471 train_time:1160893ms step_avg:301.22ms
step:3865/5100 train_loss:3.4957 train_time:1161088ms step_avg:301.19ms
step:3866/5100 train_loss:3.4679 train_time:1161282ms step_avg:301.16ms
step:3867/5100 train_loss:3.4046 train_time:1161478ms step_avg:301.14ms
step:3868/5100 train_loss:3.4948 train_time:1161673ms step_avg:301.11ms
step:3869/5100 train_loss:3.6538 train_time:1161868ms step_avg:301.08ms
step:3870/5100 train_loss:3.4955 train_time:1162062ms step_avg:301.05ms
step:3871/5100 train_loss:3.3855 train_time:1163293ms step_avg:301.29ms
step:3872/5100 train_loss:3.5322 train_time:1163494ms step_avg:301.27ms
step:3873/5100 train_loss:3.4326 train_time:1163691ms step_avg:301.24ms
step:3874/5100 train_loss:3.3770 train_time:1163884ms step_avg:301.21ms
step:3875/5100 train_loss:3.4772 train_time:1164080ms step_avg:301.19ms
step:3875/5100 val_loss:3.3934 train_time:1164112ms step_avg:301.19ms
step:3876/5100 train_loss:4.0055 train_time:1164294ms step_avg:301.16ms
step:3877/5100 train_loss:3.4155 train_time:1164490ms step_avg:301.14ms
step:3878/5100 train_loss:3.4156 train_time:1164686ms step_avg:301.11ms
step:3879/5100 train_loss:3.3927 train_time:1164880ms step_avg:301.08ms
step:3880/5100 train_loss:3.5931 train_time:1165075ms step_avg:301.05ms
step:3881/5100 train_loss:3.4063 train_time:1166307ms step_avg:301.29ms
step:3882/5100 train_loss:3.4699 train_time:1166509ms step_avg:301.27ms
step:3883/5100 train_loss:3.5098 train_time:1166705ms step_avg:301.24ms
step:3884/5100 train_loss:3.3360 train_time:1166899ms step_avg:301.21ms
step:3885/5100 train_loss:3.3257 train_time:1167093ms step_avg:301.19ms
step:3886/5100 train_loss:3.3626 train_time:1167289ms step_avg:301.16ms
step:3887/5100 train_loss:3.3941 train_time:1167484ms step_avg:301.13ms
step:3888/5100 train_loss:3.5803 train_time:1167679ms step_avg:301.10ms
step:3889/5100 train_loss:3.4279 train_time:1167874ms step_avg:301.08ms
step:3890/5100 train_loss:3.3617 train_time:1168070ms step_avg:301.05ms
step:3891/5100 train_loss:3.5061 train_time:1169301ms step_avg:301.29ms
step:3892/5100 train_loss:3.3608 train_time:1169503ms step_avg:301.26ms
step:3893/5100 train_loss:3.6096 train_time:1169698ms step_avg:301.24ms
step:3894/5100 train_loss:3.3521 train_time:1169894ms step_avg:301.21ms
step:3895/5100 train_loss:3.3586 train_time:1170090ms step_avg:301.18ms
step:3896/5100 train_loss:3.4445 train_time:1170285ms step_avg:301.15ms
step:3897/5100 train_loss:3.6838 train_time:1170481ms step_avg:301.13ms
step:3898/5100 train_loss:3.2397 train_time:1170675ms step_avg:301.10ms
step:3899/5100 train_loss:3.3669 train_time:1170871ms step_avg:301.07ms
step:3900/5100 train_loss:3.5042 train_time:1171067ms step_avg:301.05ms
step:3901/5100 train_loss:3.4297 train_time:1172298ms step_avg:301.28ms
step:3902/5100 train_loss:3.4719 train_time:1172499ms step_avg:301.26ms
step:3903/5100 train_loss:3.7532 train_time:1172694ms step_avg:301.23ms
step:3904/5100 train_loss:3.3588 train_time:1172890ms step_avg:301.20ms
step:3905/5100 train_loss:3.3710 train_time:1173085ms step_avg:301.18ms
step:3906/5100 train_loss:3.3216 train_time:1173281ms step_avg:301.15ms
step:3907/5100 train_loss:3.4853 train_time:1173475ms step_avg:301.12ms
step:3908/5100 train_loss:3.4977 train_time:1173671ms step_avg:301.10ms
step:3909/5100 train_loss:3.4876 train_time:1173867ms step_avg:301.07ms
step:3910/5100 train_loss:3.4324 train_time:1174062ms step_avg:301.04ms
step:3911/5100 train_loss:3.3671 train_time:1175292ms step_avg:301.28ms
step:3912/5100 train_loss:3.3950 train_time:1175492ms step_avg:301.25ms
step:3913/5100 train_loss:3.3815 train_time:1175688ms step_avg:301.23ms
step:3914/5100 train_loss:3.5054 train_time:1175883ms step_avg:301.20ms
step:3915/5100 train_loss:3.3417 train_time:1176077ms step_avg:301.17ms
step:3916/5100 train_loss:3.3183 train_time:1176272ms step_avg:301.15ms
step:3917/5100 train_loss:3.3123 train_time:1176468ms step_avg:301.12ms
step:3918/5100 train_loss:3.4326 train_time:1176663ms step_avg:301.09ms
step:3919/5100 train_loss:3.5656 train_time:1176857ms step_avg:301.06ms
step:3920/5100 train_loss:3.3319 train_time:1177051ms step_avg:301.04ms
step:3921/5100 train_loss:3.3106 train_time:1178283ms step_avg:301.27ms
step:3922/5100 train_loss:3.3957 train_time:1178486ms step_avg:301.25ms
step:3923/5100 train_loss:3.3839 train_time:1178682ms step_avg:301.22ms
step:3924/5100 train_loss:3.3986 train_time:1178877ms step_avg:301.19ms
step:3925/5100 train_loss:3.4719 train_time:1179072ms step_avg:301.17ms
step:3926/5100 train_loss:3.4375 train_time:1179267ms step_avg:301.14ms
step:3927/5100 train_loss:3.5341 train_time:1179462ms step_avg:301.11ms
step:3928/5100 train_loss:3.4177 train_time:1179657ms step_avg:301.09ms
step:3929/5100 train_loss:3.2767 train_time:1179851ms step_avg:301.06ms
step:3930/5100 train_loss:3.6043 train_time:1180046ms step_avg:301.03ms
step:3931/5100 train_loss:3.3852 train_time:1181278ms step_avg:301.27ms
step:3932/5100 train_loss:3.4428 train_time:1181480ms step_avg:301.24ms
step:3933/5100 train_loss:3.4685 train_time:1181675ms step_avg:301.22ms
step:3934/5100 train_loss:3.3495 train_time:1181872ms step_avg:301.19ms
step:3935/5100 train_loss:3.4785 train_time:1182067ms step_avg:301.16ms
step:3936/5100 train_loss:3.4868 train_time:1182262ms step_avg:301.14ms
step:3937/5100 train_loss:3.4094 train_time:1182457ms step_avg:301.11ms
step:3938/5100 train_loss:3.4725 train_time:1182651ms step_avg:301.08ms
step:3939/5100 train_loss:3.3920 train_time:1182845ms step_avg:301.06ms
step:3940/5100 train_loss:3.2197 train_time:1183040ms step_avg:301.03ms
step:3941/5100 train_loss:3.3612 train_time:1184269ms step_avg:301.26ms
step:3942/5100 train_loss:3.4681 train_time:1184469ms step_avg:301.24ms
step:3943/5100 train_loss:3.5694 train_time:1184664ms step_avg:301.21ms
step:3944/5100 train_loss:3.6014 train_time:1184859ms step_avg:301.18ms
step:3945/5100 train_loss:3.4436 train_time:1185054ms step_avg:301.16ms
step:3946/5100 train_loss:3.3495 train_time:1185248ms step_avg:301.13ms
step:3947/5100 train_loss:3.3695 train_time:1185444ms step_avg:301.10ms
step:3948/5100 train_loss:3.4455 train_time:1185639ms step_avg:301.08ms
step:3949/5100 train_loss:3.2510 train_time:1185833ms step_avg:301.05ms
step:3950/5100 train_loss:3.4530 train_time:1186028ms step_avg:301.02ms
step:3951/5100 train_loss:3.3869 train_time:1187259ms step_avg:301.26ms
step:3952/5100 train_loss:3.1902 train_time:1187460ms step_avg:301.23ms
step:3953/5100 train_loss:3.2664 train_time:1187654ms step_avg:301.21ms
step:3954/5100 train_loss:3.5363 train_time:1187849ms step_avg:301.18ms
step:3955/5100 train_loss:3.4398 train_time:1188045ms step_avg:301.15ms
step:3956/5100 train_loss:3.3853 train_time:1188239ms step_avg:301.13ms
step:3957/5100 train_loss:3.4439 train_time:1188433ms step_avg:301.10ms
step:3958/5100 train_loss:3.1666 train_time:1188630ms step_avg:301.07ms
step:3959/5100 train_loss:3.4553 train_time:1188824ms step_avg:301.04ms
step:3960/5100 train_loss:3.3999 train_time:1189018ms step_avg:301.02ms
step:3961/5100 train_loss:3.3665 train_time:1190248ms step_avg:301.25ms
step:3962/5100 train_loss:3.3845 train_time:1190449ms step_avg:301.23ms
step:3963/5100 train_loss:3.4071 train_time:1190645ms step_avg:301.20ms
step:3964/5100 train_loss:3.4392 train_time:1190840ms step_avg:301.17ms
step:3965/5100 train_loss:3.2809 train_time:1191034ms step_avg:301.15ms
step:3966/5100 train_loss:3.4042 train_time:1191230ms step_avg:301.12ms
step:3967/5100 train_loss:3.4742 train_time:1191425ms step_avg:301.09ms
step:3968/5100 train_loss:3.3892 train_time:1191619ms step_avg:301.07ms
step:3969/5100 train_loss:3.4768 train_time:1191955ms step_avg:301.07ms
step:3970/5100 train_loss:3.3651 train_time:1192148ms step_avg:301.05ms
step:3971/5100 train_loss:3.5576 train_time:1193379ms step_avg:301.28ms
step:3972/5100 train_loss:3.4902 train_time:1193580ms step_avg:301.26ms
step:3973/5100 train_loss:3.4356 train_time:1193775ms step_avg:301.23ms
step:3974/5100 train_loss:3.3236 train_time:1193971ms step_avg:301.20ms
step:3975/5100 train_loss:3.3764 train_time:1194167ms step_avg:301.18ms
step:3976/5100 train_loss:3.4466 train_time:1194360ms step_avg:301.15ms
step:3977/5100 train_loss:3.3484 train_time:1194555ms step_avg:301.12ms
step:3978/5100 train_loss:3.4196 train_time:1194750ms step_avg:301.10ms
step:3979/5100 train_loss:3.5015 train_time:1194946ms step_avg:301.07ms
step:3980/5100 train_loss:3.4336 train_time:1195142ms step_avg:301.04ms
step:3981/5100 train_loss:3.4447 train_time:1196373ms step_avg:301.28ms
step:3982/5100 train_loss:3.6389 train_time:1196575ms step_avg:301.25ms
step:3983/5100 train_loss:3.3736 train_time:1196770ms step_avg:301.23ms
step:3984/5100 train_loss:3.4418 train_time:1196966ms step_avg:301.20ms
step:3985/5100 train_loss:3.3730 train_time:1197161ms step_avg:301.17ms
step:3986/5100 train_loss:3.3007 train_time:1197355ms step_avg:301.15ms
step:3987/5100 train_loss:3.3422 train_time:1197550ms step_avg:301.12ms
step:3988/5100 train_loss:3.3658 train_time:1197745ms step_avg:301.09ms
step:3989/5100 train_loss:3.0916 train_time:1197941ms step_avg:301.07ms
step:3990/5100 train_loss:3.4199 train_time:1198303ms step_avg:301.08ms
step:3991/5100 train_loss:3.3929 train_time:1199533ms step_avg:301.31ms
step:3992/5100 train_loss:3.2431 train_time:1199734ms step_avg:301.29ms
step:3993/5100 train_loss:3.3434 train_time:1199927ms step_avg:301.26ms
step:3994/5100 train_loss:3.5400 train_time:1200123ms step_avg:301.24ms
step:3995/5100 train_loss:3.3627 train_time:1200318ms step_avg:301.21ms
step:3996/5100 train_loss:3.2778 train_time:1200511ms step_avg:301.18ms
step:3997/5100 train_loss:3.4320 train_time:1200707ms step_avg:301.16ms
step:3998/5100 train_loss:3.3395 train_time:1200902ms step_avg:301.13ms
step:3999/5100 train_loss:3.3038 train_time:1201096ms step_avg:301.10ms
step:4000/5100 train_loss:3.3729 train_time:1201291ms step_avg:301.08ms
step:4000/5100 val_loss:3.3779 train_time:1201323ms step_avg:301.08ms
step:4001/5100 train_loss:3.4982 train_time:1202541ms step_avg:301.31ms
step:4002/5100 train_loss:3.5669 train_time:1202744ms step_avg:301.29ms
step:4003/5100 train_loss:3.2361 train_time:1202940ms step_avg:301.26ms
step:4004/5100 train_loss:3.4350 train_time:1203135ms step_avg:301.24ms
step:4005/5100 train_loss:3.3389 train_time:1203329ms step_avg:301.21ms
step:4006/5100 train_loss:3.3923 train_time:1203523ms step_avg:301.18ms
step:4007/5100 train_loss:3.3755 train_time:1203720ms step_avg:301.16ms
step:4008/5100 train_loss:3.5706 train_time:1203915ms step_avg:301.13ms
step:4009/5100 train_loss:3.1602 train_time:1204109ms step_avg:301.10ms
step:4010/5100 train_loss:3.3629 train_time:1204304ms step_avg:301.08ms
step:4011/5100 train_loss:3.3388 train_time:1205535ms step_avg:301.31ms
step:4012/5100 train_loss:3.3097 train_time:1205735ms step_avg:301.28ms
step:4013/5100 train_loss:3.4819 train_time:1205931ms step_avg:301.26ms
step:4014/5100 train_loss:3.3392 train_time:1206126ms step_avg:301.23ms
step:4015/5100 train_loss:3.4401 train_time:1206322ms step_avg:301.20ms
step:4016/5100 train_loss:3.5328 train_time:1206518ms step_avg:301.18ms
step:4017/5100 train_loss:3.5178 train_time:1206713ms step_avg:301.15ms
step:4018/5100 train_loss:3.2826 train_time:1206907ms step_avg:301.12ms
step:4019/5100 train_loss:3.4080 train_time:1207102ms step_avg:301.10ms
step:4020/5100 train_loss:3.3322 train_time:1207298ms step_avg:301.07ms
step:4021/5100 train_loss:3.5989 train_time:1208529ms step_avg:301.30ms
step:4022/5100 train_loss:3.4737 train_time:1208731ms step_avg:301.28ms
step:4023/5100 train_loss:3.4604 train_time:1208925ms step_avg:301.25ms
step:4024/5100 train_loss:3.4308 train_time:1209120ms step_avg:301.23ms
step:4025/5100 train_loss:3.4589 train_time:1209315ms step_avg:301.20ms
step:4026/5100 train_loss:3.2182 train_time:1209510ms step_avg:301.17ms
step:4027/5100 train_loss:3.4330 train_time:1209704ms step_avg:301.15ms
step:4028/5100 train_loss:3.3844 train_time:1209900ms step_avg:301.12ms
step:4029/5100 train_loss:3.2680 train_time:1210096ms step_avg:301.09ms
step:4030/5100 train_loss:3.3027 train_time:1210291ms step_avg:301.07ms
step:4031/5100 train_loss:3.3492 train_time:1211521ms step_avg:301.30ms
step:4032/5100 train_loss:3.4406 train_time:1211721ms step_avg:301.27ms
step:4033/5100 train_loss:3.4089 train_time:1211917ms step_avg:301.25ms
step:4034/5100 train_loss:3.3846 train_time:1212112ms step_avg:301.22ms
step:4035/5100 train_loss:3.3791 train_time:1212306ms step_avg:301.19ms
step:4036/5100 train_loss:3.3142 train_time:1212502ms step_avg:301.17ms
step:4037/5100 train_loss:3.4812 train_time:1212697ms step_avg:301.14ms
step:4038/5100 train_loss:3.4156 train_time:1212892ms step_avg:301.12ms
step:4039/5100 train_loss:3.3989 train_time:1213086ms step_avg:301.09ms
step:4040/5100 train_loss:3.3921 train_time:1213281ms step_avg:301.06ms
step:4041/5100 train_loss:3.4391 train_time:1214513ms step_avg:301.29ms
step:4042/5100 train_loss:3.6250 train_time:1214713ms step_avg:301.27ms
step:4043/5100 train_loss:3.5249 train_time:1214909ms step_avg:301.24ms
step:4044/5100 train_loss:3.3136 train_time:1215104ms step_avg:301.22ms
step:4045/5100 train_loss:3.4787 train_time:1215299ms step_avg:301.19ms
step:4046/5100 train_loss:3.1830 train_time:1215494ms step_avg:301.16ms
step:4047/5100 train_loss:3.4437 train_time:1215689ms step_avg:301.14ms
step:4048/5100 train_loss:3.5243 train_time:1215883ms step_avg:301.11ms
step:4049/5100 train_loss:3.4041 train_time:1216079ms step_avg:301.08ms
step:4050/5100 train_loss:3.3347 train_time:1216274ms step_avg:301.06ms
step:4051/5100 train_loss:3.3695 train_time:1217504ms step_avg:301.29ms
step:4052/5100 train_loss:3.3045 train_time:1217707ms step_avg:301.26ms
step:4053/5100 train_loss:3.5140 train_time:1217903ms step_avg:301.24ms
step:4054/5100 train_loss:3.3678 train_time:1218098ms step_avg:301.21ms
step:4055/5100 train_loss:3.4522 train_time:1218293ms step_avg:301.18ms
step:4056/5100 train_loss:3.4316 train_time:1218488ms step_avg:301.16ms
step:4057/5100 train_loss:3.4145 train_time:1218683ms step_avg:301.13ms
step:4058/5100 train_loss:3.2749 train_time:1218879ms step_avg:301.11ms
step:4059/5100 train_loss:3.4342 train_time:1219074ms step_avg:301.08ms
step:4060/5100 train_loss:3.2902 train_time:1219269ms step_avg:301.05ms
step:4061/5100 train_loss:3.3785 train_time:1220500ms step_avg:301.28ms
step:4062/5100 train_loss:3.4907 train_time:1220699ms step_avg:301.26ms
step:4063/5100 train_loss:3.6644 train_time:1220894ms step_avg:301.23ms
step:4064/5100 train_loss:3.0636 train_time:1221090ms step_avg:301.21ms
step:4065/5100 train_loss:3.4099 train_time:1221285ms step_avg:301.18ms
step:4066/5100 train_loss:3.3019 train_time:1221480ms step_avg:301.15ms
step:4067/5100 train_loss:3.4542 train_time:1221675ms step_avg:301.13ms
step:4068/5100 train_loss:3.4557 train_time:1221870ms step_avg:301.10ms
step:4069/5100 train_loss:3.2612 train_time:1222065ms step_avg:301.08ms
step:4070/5100 train_loss:3.4314 train_time:1222260ms step_avg:301.05ms
step:4071/5100 train_loss:3.2472 train_time:1223490ms step_avg:301.28ms
step:4072/5100 train_loss:3.4329 train_time:1223689ms step_avg:301.25ms
step:4073/5100 train_loss:3.5359 train_time:1223886ms step_avg:301.23ms
step:4074/5100 train_loss:3.4594 train_time:1224081ms step_avg:301.20ms
step:4075/5100 train_loss:3.3705 train_time:1224276ms step_avg:301.17ms
step:4076/5100 train_loss:3.3696 train_time:1224471ms step_avg:301.15ms
step:4077/5100 train_loss:3.2420 train_time:1224665ms step_avg:301.12ms
step:4078/5100 train_loss:3.4063 train_time:1224860ms step_avg:301.10ms
step:4079/5100 train_loss:3.4297 train_time:1225056ms step_avg:301.07ms
step:4080/5100 train_loss:3.2133 train_time:1225250ms step_avg:301.04ms
step:4081/5100 train_loss:3.3957 train_time:1226479ms step_avg:301.27ms
step:4082/5100 train_loss:3.3419 train_time:1226680ms step_avg:301.25ms
step:4083/5100 train_loss:3.3995 train_time:1226876ms step_avg:301.22ms
step:4084/5100 train_loss:3.4034 train_time:1227070ms step_avg:301.20ms
step:4085/5100 train_loss:3.4275 train_time:1227265ms step_avg:301.17ms
step:4086/5100 train_loss:3.3884 train_time:1227459ms step_avg:301.14ms
step:4087/5100 train_loss:3.3624 train_time:1227653ms step_avg:301.12ms
step:4088/5100 train_loss:3.4834 train_time:1227848ms step_avg:301.09ms
step:4089/5100 train_loss:3.3174 train_time:1228042ms step_avg:301.06ms
step:4090/5100 train_loss:3.3445 train_time:1228237ms step_avg:301.04ms
step:4091/5100 train_loss:3.3588 train_time:1229469ms step_avg:301.27ms
step:4092/5100 train_loss:3.3088 train_time:1229669ms step_avg:301.24ms
step:4093/5100 train_loss:3.3034 train_time:1229863ms step_avg:301.22ms
step:4094/5100 train_loss:3.4841 train_time:1230059ms step_avg:301.19ms
step:4095/5100 train_loss:3.4759 train_time:1230254ms step_avg:301.16ms
step:4096/5100 train_loss:3.3854 train_time:1230448ms step_avg:301.14ms
step:4097/5100 train_loss:3.4455 train_time:1230643ms step_avg:301.11ms
step:4098/5100 train_loss:3.2260 train_time:1230838ms step_avg:301.09ms
step:4099/5100 train_loss:3.3603 train_time:1231032ms step_avg:301.06ms
step:4100/5100 train_loss:3.3321 train_time:1231226ms step_avg:301.03ms
step:4101/5100 train_loss:3.1308 train_time:1232457ms step_avg:301.26ms
step:4102/5100 train_loss:3.4088 train_time:1232658ms step_avg:301.24ms
step:4103/5100 train_loss:3.3767 train_time:1232854ms step_avg:301.21ms
step:4104/5100 train_loss:3.2072 train_time:1233049ms step_avg:301.18ms
step:4105/5100 train_loss:3.2987 train_time:1233243ms step_avg:301.16ms
step:4106/5100 train_loss:3.4472 train_time:1233438ms step_avg:301.13ms
step:4107/5100 train_loss:3.5040 train_time:1233634ms step_avg:301.11ms
step:4108/5100 train_loss:3.3988 train_time:1233829ms step_avg:301.08ms
step:4109/5100 train_loss:3.4869 train_time:1234024ms step_avg:301.05ms
step:4110/5100 train_loss:3.4794 train_time:1234218ms step_avg:301.03ms
step:4111/5100 train_loss:3.6482 train_time:1235450ms step_avg:301.26ms
step:4112/5100 train_loss:3.2991 train_time:1235650ms step_avg:301.23ms
step:4113/5100 train_loss:3.4336 train_time:1235845ms step_avg:301.21ms
step:4114/5100 train_loss:3.3244 train_time:1236040ms step_avg:301.18ms
step:4115/5100 train_loss:3.4358 train_time:1236235ms step_avg:301.15ms
step:4116/5100 train_loss:3.4369 train_time:1236429ms step_avg:301.13ms
step:4117/5100 train_loss:3.6746 train_time:1236623ms step_avg:301.10ms
step:4118/5100 train_loss:3.2431 train_time:1236819ms step_avg:301.08ms
step:4119/5100 train_loss:3.4239 train_time:1237014ms step_avg:301.05ms
step:4120/5100 train_loss:3.3220 train_time:1237210ms step_avg:301.02ms
step:4121/5100 train_loss:3.4402 train_time:1238440ms step_avg:301.25ms
step:4122/5100 train_loss:3.4291 train_time:1238641ms step_avg:301.23ms
step:4123/5100 train_loss:3.4165 train_time:1238836ms step_avg:301.20ms
step:4124/5100 train_loss:3.2531 train_time:1239031ms step_avg:301.17ms
step:4125/5100 train_loss:3.2628 train_time:1239225ms step_avg:301.15ms
step:4125/5100 val_loss:3.3645 train_time:1239257ms step_avg:301.16ms
step:4126/5100 train_loss:3.3816 train_time:1239440ms step_avg:301.13ms
step:4127/5100 train_loss:3.3228 train_time:1239635ms step_avg:301.10ms
step:4128/5100 train_loss:3.3934 train_time:1239830ms step_avg:301.08ms
step:4129/5100 train_loss:3.3876 train_time:1240026ms step_avg:301.05ms
step:4130/5100 train_loss:3.1687 train_time:1240221ms step_avg:301.02ms
step:4131/5100 train_loss:3.4640 train_time:1241451ms step_avg:301.25ms
step:4132/5100 train_loss:3.4140 train_time:1241651ms step_avg:301.23ms
step:4133/5100 train_loss:3.3416 train_time:1241847ms step_avg:301.20ms
step:4134/5100 train_loss:3.5389 train_time:1242042ms step_avg:301.17ms
step:4135/5100 train_loss:3.3711 train_time:1242236ms step_avg:301.15ms
step:4136/5100 train_loss:3.3518 train_time:1242430ms step_avg:301.12ms
step:4137/5100 train_loss:3.5060 train_time:1242626ms step_avg:301.10ms
step:4138/5100 train_loss:3.3374 train_time:1242821ms step_avg:301.07ms
step:4139/5100 train_loss:3.3981 train_time:1243016ms step_avg:301.05ms
step:4140/5100 train_loss:3.4886 train_time:1243212ms step_avg:301.02ms
step:4141/5100 train_loss:3.5218 train_time:1244443ms step_avg:301.24ms
step:4142/5100 train_loss:3.4860 train_time:1244644ms step_avg:301.22ms
step:4143/5100 train_loss:3.4611 train_time:1244839ms step_avg:301.20ms
step:4144/5100 train_loss:3.3673 train_time:1245034ms step_avg:301.17ms
step:4145/5100 train_loss:3.3396 train_time:1245228ms step_avg:301.14ms
step:4146/5100 train_loss:3.4411 train_time:1245424ms step_avg:301.12ms
step:4147/5100 train_loss:3.0035 train_time:1245619ms step_avg:301.09ms
step:4148/5100 train_loss:3.3604 train_time:1245813ms step_avg:301.07ms
step:4149/5100 train_loss:3.3960 train_time:1246009ms step_avg:301.04ms
step:4150/5100 train_loss:3.2045 train_time:1246205ms step_avg:301.02ms
step:4151/5100 train_loss:3.2421 train_time:1247435ms step_avg:301.24ms
step:4152/5100 train_loss:3.2789 train_time:1247638ms step_avg:301.22ms
step:4153/5100 train_loss:3.3360 train_time:1247833ms step_avg:301.19ms
step:4154/5100 train_loss:3.3915 train_time:1248028ms step_avg:301.17ms
step:4155/5100 train_loss:3.5043 train_time:1248224ms step_avg:301.14ms
step:4156/5100 train_loss:3.3015 train_time:1248420ms step_avg:301.11ms
step:4157/5100 train_loss:3.2537 train_time:1248613ms step_avg:301.09ms
step:4158/5100 train_loss:3.3730 train_time:1248949ms step_avg:301.10ms
step:4159/5100 train_loss:3.3833 train_time:1249143ms step_avg:301.07ms
step:4160/5100 train_loss:3.2990 train_time:1249338ms step_avg:301.05ms
step:4161/5100 train_loss:3.3842 train_time:1250566ms step_avg:301.27ms
step:4162/5100 train_loss:3.3193 train_time:1250767ms step_avg:301.24ms
step:4163/5100 train_loss:3.5417 train_time:1250962ms step_avg:301.22ms
step:4164/5100 train_loss:3.2311 train_time:1251156ms step_avg:301.19ms
step:4165/5100 train_loss:3.3377 train_time:1251350ms step_avg:301.17ms
step:4166/5100 train_loss:3.3165 train_time:1251546ms step_avg:301.14ms
step:4167/5100 train_loss:3.3666 train_time:1251741ms step_avg:301.12ms
step:4168/5100 train_loss:3.3539 train_time:1251934ms step_avg:301.09ms
step:4169/5100 train_loss:3.3775 train_time:1252129ms step_avg:301.06ms
step:4170/5100 train_loss:3.2167 train_time:1252325ms step_avg:301.04ms
step:4171/5100 train_loss:3.3179 train_time:1253556ms step_avg:301.26ms
step:4172/5100 train_loss:3.4442 train_time:1253755ms step_avg:301.24ms
step:4173/5100 train_loss:3.5132 train_time:1253952ms step_avg:301.21ms
step:4174/5100 train_loss:3.8935 train_time:1254147ms step_avg:301.19ms
step:4175/5100 train_loss:3.3222 train_time:1254342ms step_avg:301.16ms
step:4176/5100 train_loss:3.4799 train_time:1254536ms step_avg:301.14ms
step:4177/5100 train_loss:3.2809 train_time:1254731ms step_avg:301.11ms
step:4178/5100 train_loss:3.3070 train_time:1254927ms step_avg:301.09ms
step:4179/5100 train_loss:3.4655 train_time:1255122ms step_avg:301.06ms
step:4180/5100 train_loss:3.4103 train_time:1255484ms step_avg:301.08ms
step:4181/5100 train_loss:3.3969 train_time:1256715ms step_avg:301.30ms
step:4182/5100 train_loss:3.4030 train_time:1256915ms step_avg:301.27ms
step:4183/5100 train_loss:3.4349 train_time:1257110ms step_avg:301.25ms
step:4184/5100 train_loss:3.8683 train_time:1257305ms step_avg:301.22ms
step:4185/5100 train_loss:3.3820 train_time:1257500ms step_avg:301.20ms
step:4186/5100 train_loss:3.4249 train_time:1257694ms step_avg:301.17ms
step:4187/5100 train_loss:3.4699 train_time:1257890ms step_avg:301.15ms
step:4188/5100 train_loss:3.4628 train_time:1258085ms step_avg:301.12ms
step:4189/5100 train_loss:3.1054 train_time:1258280ms step_avg:301.10ms
step:4190/5100 train_loss:3.4562 train_time:1258474ms step_avg:301.07ms
step:4191/5100 train_loss:3.4697 train_time:1259704ms step_avg:301.29ms
step:4192/5100 train_loss:3.4411 train_time:1259906ms step_avg:301.27ms
step:4193/5100 train_loss:3.3748 train_time:1260101ms step_avg:301.24ms
step:4194/5100 train_loss:3.3892 train_time:1260296ms step_avg:301.22ms
step:4195/5100 train_loss:3.3668 train_time:1260491ms step_avg:301.19ms
step:4196/5100 train_loss:3.3121 train_time:1260686ms step_avg:301.17ms
step:4197/5100 train_loss:3.6619 train_time:1260881ms step_avg:301.14ms
step:4198/5100 train_loss:3.1061 train_time:1261077ms step_avg:301.12ms
step:4199/5100 train_loss:3.5131 train_time:1261271ms step_avg:301.09ms
step:4200/5100 train_loss:3.3838 train_time:1261466ms step_avg:301.07ms
step:4201/5100 train_loss:3.2709 train_time:1262697ms step_avg:301.29ms
step:4202/5100 train_loss:3.4184 train_time:1262899ms step_avg:301.26ms
step:4203/5100 train_loss:3.2790 train_time:1263094ms step_avg:301.24ms
step:4204/5100 train_loss:3.2866 train_time:1263289ms step_avg:301.21ms
step:4205/5100 train_loss:3.3031 train_time:1263483ms step_avg:301.19ms
step:4206/5100 train_loss:3.2948 train_time:1263677ms step_avg:301.16ms
step:4207/5100 train_loss:3.7534 train_time:1263872ms step_avg:301.14ms
step:4208/5100 train_loss:3.3344 train_time:1264067ms step_avg:301.11ms
step:4209/5100 train_loss:3.4648 train_time:1264262ms step_avg:301.09ms
step:4210/5100 train_loss:3.3610 train_time:1264457ms step_avg:301.06ms
step:4211/5100 train_loss:3.7486 train_time:1265687ms step_avg:301.28ms
step:4212/5100 train_loss:3.4060 train_time:1265887ms step_avg:301.26ms
step:4213/5100 train_loss:3.4056 train_time:1266082ms step_avg:301.23ms
step:4214/5100 train_loss:3.2814 train_time:1266277ms step_avg:301.21ms
step:4215/5100 train_loss:3.3401 train_time:1266472ms step_avg:301.18ms
step:4216/5100 train_loss:3.4217 train_time:1266667ms step_avg:301.16ms
step:4217/5100 train_loss:3.2743 train_time:1266862ms step_avg:301.13ms
step:4218/5100 train_loss:3.3298 train_time:1267056ms step_avg:301.11ms
step:4219/5100 train_loss:3.3905 train_time:1267252ms step_avg:301.08ms
step:4220/5100 train_loss:3.2040 train_time:1267448ms step_avg:301.06ms
step:4221/5100 train_loss:3.3607 train_time:1268679ms step_avg:301.28ms
step:4222/5100 train_loss:3.3949 train_time:1268880ms step_avg:301.25ms
step:4223/5100 train_loss:3.3606 train_time:1269074ms step_avg:301.23ms
step:4224/5100 train_loss:3.5645 train_time:1269269ms step_avg:301.20ms
step:4225/5100 train_loss:3.4435 train_time:1269464ms step_avg:301.18ms
step:4226/5100 train_loss:3.4925 train_time:1269659ms step_avg:301.15ms
step:4227/5100 train_loss:3.2796 train_time:1269853ms step_avg:301.13ms
step:4228/5100 train_loss:3.3494 train_time:1270048ms step_avg:301.10ms
step:4229/5100 train_loss:3.3807 train_time:1270243ms step_avg:301.08ms
step:4230/5100 train_loss:3.2929 train_time:1270437ms step_avg:301.05ms
step:4231/5100 train_loss:3.4769 train_time:1271666ms step_avg:301.27ms
step:4232/5100 train_loss:3.4833 train_time:1271866ms step_avg:301.25ms
step:4233/5100 train_loss:3.4777 train_time:1272062ms step_avg:301.22ms
step:4234/5100 train_loss:3.5869 train_time:1272256ms step_avg:301.20ms
step:4235/5100 train_loss:3.4308 train_time:1272451ms step_avg:301.17ms
step:4236/5100 train_loss:3.3839 train_time:1272646ms step_avg:301.15ms
step:4237/5100 train_loss:3.2361 train_time:1272841ms step_avg:301.12ms
step:4238/5100 train_loss:3.4478 train_time:1273035ms step_avg:301.10ms
step:4239/5100 train_loss:3.3571 train_time:1273230ms step_avg:301.07ms
step:4240/5100 train_loss:3.2738 train_time:1273425ms step_avg:301.05ms
step:4241/5100 train_loss:3.3180 train_time:1274657ms step_avg:301.27ms
step:4242/5100 train_loss:3.2664 train_time:1274858ms step_avg:301.24ms
step:4243/5100 train_loss:3.3437 train_time:1275052ms step_avg:301.22ms
step:4244/5100 train_loss:3.2696 train_time:1275247ms step_avg:301.19ms
step:4245/5100 train_loss:3.1766 train_time:1275443ms step_avg:301.17ms
step:4246/5100 train_loss:3.4880 train_time:1275638ms step_avg:301.14ms
step:4247/5100 train_loss:3.2845 train_time:1275832ms step_avg:301.12ms
step:4248/5100 train_loss:3.2140 train_time:1276027ms step_avg:301.09ms
step:4249/5100 train_loss:3.4292 train_time:1276222ms step_avg:301.07ms
step:4250/5100 train_loss:3.7086 train_time:1276418ms step_avg:301.04ms
step:4250/5100 val_loss:3.3518 train_time:1276451ms step_avg:301.05ms
step:4251/5100 train_loss:3.3312 train_time:1277666ms step_avg:301.27ms
step:4252/5100 train_loss:3.5812 train_time:1277870ms step_avg:301.24ms
step:4253/5100 train_loss:3.4268 train_time:1278064ms step_avg:301.22ms
step:4254/5100 train_loss:3.2336 train_time:1278258ms step_avg:301.19ms
step:4255/5100 train_loss:3.3144 train_time:1278454ms step_avg:301.17ms
step:4256/5100 train_loss:3.2416 train_time:1278649ms step_avg:301.14ms
step:4257/5100 train_loss:3.4768 train_time:1278844ms step_avg:301.12ms
step:4258/5100 train_loss:3.3686 train_time:1279038ms step_avg:301.09ms
step:4259/5100 train_loss:3.4139 train_time:1279234ms step_avg:301.07ms
step:4260/5100 train_loss:3.2278 train_time:1279428ms step_avg:301.04ms
step:4261/5100 train_loss:3.5402 train_time:1280659ms step_avg:301.26ms
step:4262/5100 train_loss:3.3597 train_time:1280859ms step_avg:301.24ms
step:4263/5100 train_loss:3.3754 train_time:1281054ms step_avg:301.21ms
step:4264/5100 train_loss:3.4179 train_time:1281249ms step_avg:301.19ms
step:4265/5100 train_loss:3.3675 train_time:1281443ms step_avg:301.16ms
step:4266/5100 train_loss:3.3722 train_time:1281636ms step_avg:301.14ms
step:4267/5100 train_loss:3.4943 train_time:1281832ms step_avg:301.11ms
step:4268/5100 train_loss:3.3144 train_time:1282027ms step_avg:301.09ms
step:4269/5100 train_loss:3.8611 train_time:1282221ms step_avg:301.06ms
step:4270/5100 train_loss:3.2998 train_time:1282416ms step_avg:301.04ms
step:4271/5100 train_loss:3.4047 train_time:1283646ms step_avg:301.25ms
step:4272/5100 train_loss:3.3277 train_time:1283848ms step_avg:301.23ms
step:4273/5100 train_loss:3.5402 train_time:1284043ms step_avg:301.21ms
step:4274/5100 train_loss:3.4550 train_time:1284237ms step_avg:301.18ms
step:4275/5100 train_loss:3.3095 train_time:1284432ms step_avg:301.16ms
step:4276/5100 train_loss:3.3708 train_time:1284626ms step_avg:301.13ms
step:4277/5100 train_loss:3.2923 train_time:1284821ms step_avg:301.11ms
step:4278/5100 train_loss:3.3273 train_time:1285017ms step_avg:301.08ms
step:4279/5100 train_loss:3.3352 train_time:1285214ms step_avg:301.06ms
step:4280/5100 train_loss:3.3965 train_time:1285408ms step_avg:301.03ms
step:4281/5100 train_loss:3.3869 train_time:1286640ms step_avg:301.25ms
step:4282/5100 train_loss:3.4036 train_time:1286841ms step_avg:301.23ms
step:4283/5100 train_loss:3.3314 train_time:1287035ms step_avg:301.20ms
step:4284/5100 train_loss:3.3737 train_time:1287230ms step_avg:301.18ms
step:4285/5100 train_loss:3.4391 train_time:1287424ms step_avg:301.15ms
step:4286/5100 train_loss:3.3883 train_time:1287618ms step_avg:301.13ms
step:4287/5100 train_loss:3.2724 train_time:1287815ms step_avg:301.10ms
step:4288/5100 train_loss:3.3115 train_time:1288010ms step_avg:301.08ms
step:4289/5100 train_loss:3.4162 train_time:1288205ms step_avg:301.05ms
step:4290/5100 train_loss:3.3722 train_time:1288400ms step_avg:301.03ms
step:4291/5100 train_loss:3.2722 train_time:1289630ms step_avg:301.25ms
step:4292/5100 train_loss:3.2980 train_time:1289831ms step_avg:301.22ms
step:4293/5100 train_loss:3.3664 train_time:1290026ms step_avg:301.20ms
step:4294/5100 train_loss:3.1447 train_time:1290219ms step_avg:301.17ms
step:4295/5100 train_loss:3.5010 train_time:1290415ms step_avg:301.15ms
step:4296/5100 train_loss:3.3939 train_time:1290611ms step_avg:301.12ms
step:4297/5100 train_loss:3.3415 train_time:1290806ms step_avg:301.10ms
step:4298/5100 train_loss:3.5090 train_time:1291000ms step_avg:301.07ms
step:4299/5100 train_loss:3.4352 train_time:1291195ms step_avg:301.05ms
step:4300/5100 train_loss:3.2709 train_time:1291391ms step_avg:301.02ms
step:4301/5100 train_loss:3.2585 train_time:1292623ms step_avg:301.24ms
step:4302/5100 train_loss:3.4027 train_time:1292824ms step_avg:301.22ms
step:4303/5100 train_loss:3.2527 train_time:1293019ms step_avg:301.19ms
step:4304/5100 train_loss:3.3999 train_time:1293214ms step_avg:301.17ms
step:4305/5100 train_loss:3.4762 train_time:1293409ms step_avg:301.14ms
step:4306/5100 train_loss:3.2338 train_time:1293604ms step_avg:301.12ms
step:4307/5100 train_loss:3.7584 train_time:1293799ms step_avg:301.09ms
step:4308/5100 train_loss:3.3599 train_time:1293994ms step_avg:301.07ms
step:4309/5100 train_loss:3.2900 train_time:1294189ms step_avg:301.04ms
step:4310/5100 train_loss:3.2989 train_time:1294384ms step_avg:301.02ms
step:4311/5100 train_loss:3.5907 train_time:1295614ms step_avg:301.24ms
step:4312/5100 train_loss:3.4240 train_time:1295815ms step_avg:301.21ms
step:4313/5100 train_loss:3.2868 train_time:1296011ms step_avg:301.19ms
step:4314/5100 train_loss:3.4830 train_time:1296206ms step_avg:301.16ms
step:4315/5100 train_loss:3.4194 train_time:1296401ms step_avg:301.14ms
step:4316/5100 train_loss:3.3231 train_time:1296596ms step_avg:301.11ms
step:4317/5100 train_loss:3.3778 train_time:1296792ms step_avg:301.09ms
step:4318/5100 train_loss:3.3307 train_time:1296987ms step_avg:301.06ms
step:4319/5100 train_loss:3.4436 train_time:1297181ms step_avg:301.04ms
step:4320/5100 train_loss:3.4966 train_time:1297377ms step_avg:301.02ms
step:4321/5100 train_loss:3.3173 train_time:1298608ms step_avg:301.23ms
step:4322/5100 train_loss:3.4889 train_time:1298812ms step_avg:301.21ms
step:4323/5100 train_loss:3.3459 train_time:1299008ms step_avg:301.18ms
step:4324/5100 train_loss:3.2707 train_time:1299203ms step_avg:301.16ms
step:4325/5100 train_loss:3.2103 train_time:1299397ms step_avg:301.13ms
step:4326/5100 train_loss:3.3077 train_time:1299592ms step_avg:301.11ms
step:4327/5100 train_loss:3.1928 train_time:1299787ms step_avg:301.09ms
step:4328/5100 train_loss:3.3147 train_time:1299983ms step_avg:301.06ms
step:4329/5100 train_loss:3.3422 train_time:1300177ms step_avg:301.04ms
step:4330/5100 train_loss:3.2874 train_time:1300373ms step_avg:301.01ms
step:4331/5100 train_loss:3.5414 train_time:1301604ms step_avg:301.23ms
step:4332/5100 train_loss:3.3401 train_time:1301806ms step_avg:301.20ms
step:4333/5100 train_loss:3.4572 train_time:1302001ms step_avg:301.18ms
step:4334/5100 train_loss:3.8204 train_time:1302197ms step_avg:301.16ms
step:4335/5100 train_loss:3.3531 train_time:1302393ms step_avg:301.13ms
step:4336/5100 train_loss:3.4567 train_time:1302590ms step_avg:301.11ms
step:4337/5100 train_loss:3.3474 train_time:1302785ms step_avg:301.08ms
step:4338/5100 train_loss:3.2381 train_time:1302979ms step_avg:301.06ms
step:4339/5100 train_loss:3.3743 train_time:1303175ms step_avg:301.03ms
step:4340/5100 train_loss:3.2765 train_time:1303370ms step_avg:301.01ms
step:4341/5100 train_loss:3.3692 train_time:1304601ms step_avg:301.22ms
step:4342/5100 train_loss:3.3927 train_time:1304801ms step_avg:301.20ms
step:4343/5100 train_loss:3.3910 train_time:1304995ms step_avg:301.18ms
step:4344/5100 train_loss:3.3809 train_time:1305191ms step_avg:301.15ms
step:4345/5100 train_loss:4.0120 train_time:1305385ms step_avg:301.13ms
step:4346/5100 train_loss:3.4541 train_time:1305580ms step_avg:301.10ms
step:4347/5100 train_loss:3.2461 train_time:1305914ms step_avg:301.11ms
step:4348/5100 train_loss:3.3930 train_time:1306108ms step_avg:301.09ms
step:4349/5100 train_loss:3.3348 train_time:1306303ms step_avg:301.06ms
step:4350/5100 train_loss:3.2518 train_time:1306497ms step_avg:301.04ms
step:4351/5100 train_loss:3.4184 train_time:1307727ms step_avg:301.25ms
step:4352/5100 train_loss:3.3681 train_time:1307929ms step_avg:301.23ms
step:4353/5100 train_loss:3.4391 train_time:1308124ms step_avg:301.20ms
step:4354/5100 train_loss:3.4807 train_time:1308319ms step_avg:301.18ms
step:4355/5100 train_loss:3.3010 train_time:1308514ms step_avg:301.15ms
step:4356/5100 train_loss:3.2486 train_time:1308710ms step_avg:301.13ms
step:4357/5100 train_loss:3.3835 train_time:1308905ms step_avg:301.11ms
step:4358/5100 train_loss:3.3285 train_time:1309099ms step_avg:301.08ms
step:4359/5100 train_loss:3.5140 train_time:1309295ms step_avg:301.06ms
step:4360/5100 train_loss:3.3772 train_time:1309491ms step_avg:301.03ms
step:4361/5100 train_loss:3.4600 train_time:1310721ms step_avg:301.25ms
step:4362/5100 train_loss:3.6162 train_time:1310924ms step_avg:301.22ms
step:4363/5100 train_loss:3.4092 train_time:1311118ms step_avg:301.20ms
step:4364/5100 train_loss:3.3748 train_time:1311312ms step_avg:301.17ms
step:4365/5100 train_loss:3.5793 train_time:1311507ms step_avg:301.15ms
step:4366/5100 train_loss:3.4727 train_time:1311701ms step_avg:301.13ms
step:4367/5100 train_loss:3.2883 train_time:1311896ms step_avg:301.10ms
step:4368/5100 train_loss:3.3122 train_time:1312092ms step_avg:301.08ms
step:4369/5100 train_loss:3.4041 train_time:1312287ms step_avg:301.05ms
step:4370/5100 train_loss:3.4073 train_time:1312648ms step_avg:301.07ms
step:4371/5100 train_loss:3.5569 train_time:1313877ms step_avg:301.28ms
step:4372/5100 train_loss:3.2503 train_time:1314078ms step_avg:301.26ms
step:4373/5100 train_loss:3.2408 train_time:1314274ms step_avg:301.23ms
step:4374/5100 train_loss:3.3974 train_time:1314468ms step_avg:301.21ms
step:4375/5100 train_loss:3.4210 train_time:1314663ms step_avg:301.18ms
step:4375/5100 val_loss:3.3363 train_time:1314695ms step_avg:301.19ms
step:4376/5100 train_loss:3.4885 train_time:1314875ms step_avg:301.16ms
step:4377/5100 train_loss:3.2791 train_time:1315070ms step_avg:301.14ms
step:4378/5100 train_loss:3.3262 train_time:1315265ms step_avg:301.11ms
step:4379/5100 train_loss:3.3408 train_time:1315459ms step_avg:301.09ms
step:4380/5100 train_loss:3.3809 train_time:1315654ms step_avg:301.07ms
step:4381/5100 train_loss:3.2835 train_time:1316885ms step_avg:301.28ms
step:4382/5100 train_loss:3.5227 train_time:1317088ms step_avg:301.26ms
step:4383/5100 train_loss:3.4356 train_time:1317283ms step_avg:301.23ms
step:4384/5100 train_loss:3.4306 train_time:1317478ms step_avg:301.21ms
step:4385/5100 train_loss:3.3046 train_time:1317673ms step_avg:301.18ms
step:4386/5100 train_loss:3.4375 train_time:1317868ms step_avg:301.16ms
step:4387/5100 train_loss:3.3321 train_time:1318062ms step_avg:301.13ms
step:4388/5100 train_loss:3.4597 train_time:1318257ms step_avg:301.11ms
step:4389/5100 train_loss:3.2858 train_time:1318451ms step_avg:301.09ms
step:4390/5100 train_loss:3.4089 train_time:1318645ms step_avg:301.06ms
step:4391/5100 train_loss:3.4307 train_time:1319876ms step_avg:301.27ms
step:4392/5100 train_loss:3.2492 train_time:1320078ms step_avg:301.25ms
step:4393/5100 train_loss:3.9199 train_time:1320274ms step_avg:301.23ms
step:4394/5100 train_loss:3.3195 train_time:1320470ms step_avg:301.20ms
step:4395/5100 train_loss:3.5058 train_time:1320664ms step_avg:301.18ms
step:4396/5100 train_loss:3.2785 train_time:1320858ms step_avg:301.15ms
step:4397/5100 train_loss:3.4012 train_time:1321054ms step_avg:301.13ms
step:4398/5100 train_loss:3.2075 train_time:1321248ms step_avg:301.10ms
step:4399/5100 train_loss:3.4252 train_time:1321443ms step_avg:301.08ms
step:4400/5100 train_loss:3.2559 train_time:1321638ms step_avg:301.06ms
step:4401/5100 train_loss:3.3303 train_time:1322868ms step_avg:301.27ms
step:4402/5100 train_loss:3.4019 train_time:1323069ms step_avg:301.25ms
step:4403/5100 train_loss:3.2290 train_time:1323264ms step_avg:301.22ms
step:4404/5100 train_loss:3.2872 train_time:1323458ms step_avg:301.20ms
step:4405/5100 train_loss:3.4788 train_time:1323653ms step_avg:301.17ms
step:4406/5100 train_loss:3.3397 train_time:1323847ms step_avg:301.15ms
step:4407/5100 train_loss:3.3579 train_time:1324042ms step_avg:301.12ms
step:4408/5100 train_loss:3.3163 train_time:1324237ms step_avg:301.10ms
step:4409/5100 train_loss:3.4008 train_time:1324432ms step_avg:301.08ms
step:4410/5100 train_loss:3.3859 train_time:1324627ms step_avg:301.05ms
step:4411/5100 train_loss:3.5063 train_time:1325857ms step_avg:301.26ms
step:4412/5100 train_loss:3.3455 train_time:1326060ms step_avg:301.24ms
step:4413/5100 train_loss:3.3792 train_time:1326254ms step_avg:301.22ms
step:4414/5100 train_loss:3.3625 train_time:1326449ms step_avg:301.19ms
step:4415/5100 train_loss:3.4106 train_time:1326644ms step_avg:301.17ms
step:4416/5100 train_loss:3.3556 train_time:1326837ms step_avg:301.14ms
step:4417/5100 train_loss:3.4319 train_time:1327033ms step_avg:301.12ms
step:4418/5100 train_loss:3.3517 train_time:1327228ms step_avg:301.10ms
step:4419/5100 train_loss:3.2594 train_time:1327421ms step_avg:301.07ms
step:4420/5100 train_loss:3.3122 train_time:1327618ms step_avg:301.05ms
step:4421/5100 train_loss:3.5425 train_time:1328850ms step_avg:301.26ms
step:4422/5100 train_loss:3.3451 train_time:1329050ms step_avg:301.24ms
step:4423/5100 train_loss:3.2666 train_time:1329244ms step_avg:301.21ms
step:4424/5100 train_loss:3.2850 train_time:1329439ms step_avg:301.19ms
step:4425/5100 train_loss:3.4671 train_time:1329635ms step_avg:301.16ms
step:4426/5100 train_loss:3.4190 train_time:1329829ms step_avg:301.14ms
step:4427/5100 train_loss:3.3298 train_time:1330024ms step_avg:301.11ms
step:4428/5100 train_loss:3.5458 train_time:1330219ms step_avg:301.09ms
step:4429/5100 train_loss:3.4456 train_time:1330414ms step_avg:301.07ms
step:4430/5100 train_loss:3.2498 train_time:1330610ms step_avg:301.04ms
step:4431/5100 train_loss:3.2480 train_time:1331841ms step_avg:301.25ms
step:4432/5100 train_loss:3.3823 train_time:1332041ms step_avg:301.23ms
step:4433/5100 train_loss:3.2562 train_time:1332236ms step_avg:301.21ms
step:4434/5100 train_loss:3.3730 train_time:1332431ms step_avg:301.18ms
step:4435/5100 train_loss:3.4301 train_time:1332625ms step_avg:301.16ms
step:4436/5100 train_loss:3.3324 train_time:1332819ms step_avg:301.13ms
step:4437/5100 train_loss:3.2478 train_time:1333015ms step_avg:301.11ms
step:4438/5100 train_loss:3.4904 train_time:1333211ms step_avg:301.09ms
step:4439/5100 train_loss:3.4194 train_time:1333406ms step_avg:301.06ms
step:4440/5100 train_loss:3.3169 train_time:1333600ms step_avg:301.04ms
step:4441/5100 train_loss:3.4215 train_time:1334832ms step_avg:301.25ms
step:4442/5100 train_loss:3.4458 train_time:1335034ms step_avg:301.23ms
step:4443/5100 train_loss:3.5090 train_time:1335229ms step_avg:301.20ms
step:4444/5100 train_loss:3.3901 train_time:1335424ms step_avg:301.18ms
step:4445/5100 train_loss:3.2003 train_time:1335619ms step_avg:301.15ms
step:4446/5100 train_loss:3.4821 train_time:1335813ms step_avg:301.13ms
step:4447/5100 train_loss:3.3600 train_time:1336009ms step_avg:301.11ms
step:4448/5100 train_loss:3.2544 train_time:1336204ms step_avg:301.08ms
step:4449/5100 train_loss:3.3909 train_time:1336399ms step_avg:301.06ms
step:4450/5100 train_loss:3.3728 train_time:1336595ms step_avg:301.03ms
step:4451/5100 train_loss:3.3941 train_time:1337826ms step_avg:301.24ms
step:4452/5100 train_loss:3.4258 train_time:1338028ms step_avg:301.22ms
step:4453/5100 train_loss:3.2887 train_time:1338223ms step_avg:301.20ms
step:4454/5100 train_loss:3.3260 train_time:1338418ms step_avg:301.17ms
step:4455/5100 train_loss:3.3111 train_time:1338614ms step_avg:301.15ms
step:4456/5100 train_loss:3.2134 train_time:1338809ms step_avg:301.13ms
step:4457/5100 train_loss:3.4269 train_time:1339004ms step_avg:301.10ms
step:4458/5100 train_loss:3.2941 train_time:1339199ms step_avg:301.08ms
step:4459/5100 train_loss:3.2537 train_time:1339395ms step_avg:301.06ms
step:4460/5100 train_loss:3.3808 train_time:1339589ms step_avg:301.03ms
step:4461/5100 train_loss:3.8761 train_time:1340820ms step_avg:301.24ms
step:4462/5100 train_loss:3.3674 train_time:1341021ms step_avg:301.22ms
step:4463/5100 train_loss:3.4833 train_time:1341217ms step_avg:301.19ms
step:4464/5100 train_loss:3.3945 train_time:1341413ms step_avg:301.17ms
step:4465/5100 train_loss:3.3694 train_time:1341609ms step_avg:301.15ms
step:4466/5100 train_loss:3.4324 train_time:1341804ms step_avg:301.12ms
step:4467/5100 train_loss:3.2475 train_time:1341999ms step_avg:301.10ms
step:4468/5100 train_loss:3.2924 train_time:1342194ms step_avg:301.08ms
step:4469/5100 train_loss:3.4207 train_time:1342390ms step_avg:301.05ms
step:4470/5100 train_loss:3.3980 train_time:1342584ms step_avg:301.03ms
step:4471/5100 train_loss:3.3276 train_time:1343816ms step_avg:301.24ms
step:4472/5100 train_loss:3.2848 train_time:1344016ms step_avg:301.21ms
step:4473/5100 train_loss:3.3610 train_time:1344212ms step_avg:301.19ms
step:4474/5100 train_loss:3.2103 train_time:1344409ms step_avg:301.17ms
step:4475/5100 train_loss:3.2889 train_time:1344603ms step_avg:301.14ms
step:4476/5100 train_loss:3.3152 train_time:1344799ms step_avg:301.12ms
step:4477/5100 train_loss:3.4795 train_time:1344995ms step_avg:301.10ms
step:4478/5100 train_loss:3.2111 train_time:1345189ms step_avg:301.07ms
step:4479/5100 train_loss:3.3373 train_time:1345384ms step_avg:301.05ms
step:4480/5100 train_loss:3.3774 train_time:1345579ms step_avg:301.02ms
step:4481/5100 train_loss:3.3484 train_time:1346809ms step_avg:301.23ms
step:4482/5100 train_loss:3.3381 train_time:1347010ms step_avg:301.21ms
step:4483/5100 train_loss:3.1568 train_time:1347206ms step_avg:301.19ms
step:4484/5100 train_loss:3.3069 train_time:1347400ms step_avg:301.16ms
step:4485/5100 train_loss:3.2549 train_time:1347595ms step_avg:301.14ms
step:4486/5100 train_loss:3.3831 train_time:1347790ms step_avg:301.11ms
step:4487/5100 train_loss:3.2595 train_time:1347985ms step_avg:301.09ms
step:4488/5100 train_loss:3.3343 train_time:1348181ms step_avg:301.07ms
step:4489/5100 train_loss:3.4748 train_time:1348375ms step_avg:301.04ms
step:4490/5100 train_loss:3.4417 train_time:1348570ms step_avg:301.02ms
step:4491/5100 train_loss:3.3139 train_time:1349801ms step_avg:301.23ms
step:4492/5100 train_loss:3.2787 train_time:1350002ms step_avg:301.21ms
step:4493/5100 train_loss:3.3251 train_time:1350198ms step_avg:301.18ms
step:4494/5100 train_loss:3.3566 train_time:1350393ms step_avg:301.16ms
step:4495/5100 train_loss:3.3497 train_time:1350588ms step_avg:301.13ms
step:4496/5100 train_loss:3.2952 train_time:1350782ms step_avg:301.11ms
step:4497/5100 train_loss:3.4490 train_time:1350978ms step_avg:301.09ms
step:4498/5100 train_loss:3.3370 train_time:1351174ms step_avg:301.06ms
step:4499/5100 train_loss:3.1760 train_time:1351368ms step_avg:301.04ms
step:4500/5100 train_loss:3.4773 train_time:1351563ms step_avg:301.02ms
step:4500/5100 val_loss:3.3241 train_time:1351596ms step_avg:301.02ms
step:4501/5100 train_loss:3.2799 train_time:1352813ms step_avg:301.23ms
step:4502/5100 train_loss:3.2429 train_time:1353015ms step_avg:301.21ms
step:4503/5100 train_loss:3.4280 train_time:1353210ms step_avg:301.18ms
step:4504/5100 train_loss:3.3070 train_time:1353406ms step_avg:301.16ms
step:4505/5100 train_loss:3.4074 train_time:1353601ms step_avg:301.13ms
step:4506/5100 train_loss:3.3253 train_time:1353795ms step_avg:301.11ms
step:4507/5100 train_loss:3.4000 train_time:1353990ms step_avg:301.09ms
step:4508/5100 train_loss:3.1146 train_time:1354185ms step_avg:301.06ms
step:4509/5100 train_loss:3.4007 train_time:1354380ms step_avg:301.04ms
step:4510/5100 train_loss:3.2393 train_time:1354576ms step_avg:301.02ms
step:4511/5100 train_loss:3.3111 train_time:1355807ms step_avg:301.22ms
step:4512/5100 train_loss:3.2583 train_time:1356007ms step_avg:301.20ms
step:4513/5100 train_loss:3.2581 train_time:1356203ms step_avg:301.18ms
step:4514/5100 train_loss:3.2121 train_time:1356398ms step_avg:301.15ms
step:4515/5100 train_loss:3.3511 train_time:1356594ms step_avg:301.13ms
step:4516/5100 train_loss:3.2142 train_time:1356790ms step_avg:301.11ms
step:4517/5100 train_loss:3.3127 train_time:1356984ms step_avg:301.08ms
step:4518/5100 train_loss:3.3161 train_time:1357180ms step_avg:301.06ms
step:4519/5100 train_loss:3.3330 train_time:1357373ms step_avg:301.04ms
step:4520/5100 train_loss:3.2489 train_time:1357568ms step_avg:301.01ms
step:4521/5100 train_loss:3.4386 train_time:1358799ms step_avg:301.22ms
step:4522/5100 train_loss:3.5059 train_time:1359001ms step_avg:301.20ms
step:4523/5100 train_loss:3.8378 train_time:1359195ms step_avg:301.17ms
step:4524/5100 train_loss:3.5799 train_time:1359390ms step_avg:301.15ms
step:4525/5100 train_loss:3.3434 train_time:1359586ms step_avg:301.13ms
step:4526/5100 train_loss:3.2914 train_time:1359780ms step_avg:301.10ms
step:4527/5100 train_loss:3.3625 train_time:1359975ms step_avg:301.08ms
step:4528/5100 train_loss:3.3274 train_time:1360170ms step_avg:301.06ms
step:4529/5100 train_loss:3.2298 train_time:1360366ms step_avg:301.03ms
step:4530/5100 train_loss:3.9348 train_time:1360560ms step_avg:301.01ms
step:4531/5100 train_loss:3.4043 train_time:1361790ms step_avg:301.21ms
step:4532/5100 train_loss:3.1325 train_time:1361992ms step_avg:301.19ms
step:4533/5100 train_loss:3.2408 train_time:1362189ms step_avg:301.17ms
step:4534/5100 train_loss:3.3537 train_time:1362383ms step_avg:301.15ms
step:4535/5100 train_loss:3.5745 train_time:1362578ms step_avg:301.12ms
step:4536/5100 train_loss:3.5735 train_time:1362915ms step_avg:301.13ms
step:4537/5100 train_loss:3.3098 train_time:1363111ms step_avg:301.11ms
step:4538/5100 train_loss:3.3043 train_time:1363306ms step_avg:301.08ms
step:4539/5100 train_loss:3.3345 train_time:1363502ms step_avg:301.06ms
step:4540/5100 train_loss:3.9118 train_time:1363697ms step_avg:301.04ms
step:4541/5100 train_loss:3.3930 train_time:1364929ms step_avg:301.24ms
step:4542/5100 train_loss:3.3013 train_time:1365129ms step_avg:301.22ms
step:4543/5100 train_loss:3.4639 train_time:1365324ms step_avg:301.20ms
step:4544/5100 train_loss:3.2482 train_time:1365519ms step_avg:301.17ms
step:4545/5100 train_loss:3.3581 train_time:1365714ms step_avg:301.15ms
step:4546/5100 train_loss:3.5343 train_time:1365909ms step_avg:301.13ms
step:4547/5100 train_loss:3.3931 train_time:1366104ms step_avg:301.10ms
step:4548/5100 train_loss:3.3416 train_time:1366300ms step_avg:301.08ms
step:4549/5100 train_loss:3.3354 train_time:1366495ms step_avg:301.06ms
step:4550/5100 train_loss:3.2808 train_time:1366691ms step_avg:301.03ms
step:4551/5100 train_loss:3.2632 train_time:1367921ms step_avg:301.24ms
step:4552/5100 train_loss:3.2368 train_time:1368122ms step_avg:301.22ms
step:4553/5100 train_loss:3.3450 train_time:1368317ms step_avg:301.19ms
step:4554/5100 train_loss:3.5343 train_time:1368512ms step_avg:301.17ms
step:4555/5100 train_loss:3.4180 train_time:1368707ms step_avg:301.15ms
step:4556/5100 train_loss:3.1777 train_time:1368902ms step_avg:301.12ms
step:4557/5100 train_loss:3.3802 train_time:1369096ms step_avg:301.10ms
step:4558/5100 train_loss:3.3909 train_time:1369291ms step_avg:301.08ms
step:4559/5100 train_loss:3.3780 train_time:1369486ms step_avg:301.05ms
step:4560/5100 train_loss:3.4759 train_time:1369846ms step_avg:301.06ms
step:4561/5100 train_loss:3.3155 train_time:1371076ms step_avg:301.27ms
step:4562/5100 train_loss:3.3156 train_time:1371276ms step_avg:301.25ms
step:4563/5100 train_loss:3.3404 train_time:1371471ms step_avg:301.22ms
step:4564/5100 train_loss:3.3812 train_time:1371665ms step_avg:301.20ms
step:4565/5100 train_loss:3.4611 train_time:1371860ms step_avg:301.18ms
step:4566/5100 train_loss:3.5189 train_time:1372054ms step_avg:301.15ms
step:4567/5100 train_loss:3.3776 train_time:1372251ms step_avg:301.13ms
step:4568/5100 train_loss:3.2473 train_time:1372446ms step_avg:301.11ms
step:4569/5100 train_loss:3.3482 train_time:1372640ms step_avg:301.08ms
step:4570/5100 train_loss:3.2318 train_time:1372834ms step_avg:301.06ms
step:4571/5100 train_loss:3.2571 train_time:1374066ms step_avg:301.26ms
step:4572/5100 train_loss:3.4683 train_time:1374267ms step_avg:301.24ms
step:4573/5100 train_loss:3.1674 train_time:1374462ms step_avg:301.22ms
step:4574/5100 train_loss:3.2517 train_time:1374657ms step_avg:301.20ms
step:4575/5100 train_loss:3.3822 train_time:1374853ms step_avg:301.17ms
step:4576/5100 train_loss:3.4077 train_time:1375049ms step_avg:301.15ms
step:4577/5100 train_loss:3.3666 train_time:1375244ms step_avg:301.13ms
step:4578/5100 train_loss:3.3316 train_time:1375438ms step_avg:301.10ms
step:4579/5100 train_loss:3.3493 train_time:1375633ms step_avg:301.08ms
step:4580/5100 train_loss:3.4566 train_time:1375829ms step_avg:301.06ms
step:4581/5100 train_loss:3.2867 train_time:1377061ms step_avg:301.26ms
step:4582/5100 train_loss:3.3137 train_time:1377261ms step_avg:301.24ms
step:4583/5100 train_loss:3.4146 train_time:1377456ms step_avg:301.21ms
step:4584/5100 train_loss:3.2731 train_time:1377652ms step_avg:301.19ms
step:4585/5100 train_loss:3.3785 train_time:1377846ms step_avg:301.17ms
step:4586/5100 train_loss:3.3535 train_time:1378040ms step_avg:301.15ms
step:4587/5100 train_loss:3.3340 train_time:1378234ms step_avg:301.12ms
step:4588/5100 train_loss:3.1937 train_time:1378429ms step_avg:301.10ms
step:4589/5100 train_loss:3.3226 train_time:1378624ms step_avg:301.08ms
step:4590/5100 train_loss:3.5113 train_time:1378818ms step_avg:301.05ms
step:4591/5100 train_loss:3.3397 train_time:1380049ms step_avg:301.25ms
step:4592/5100 train_loss:3.3299 train_time:1380251ms step_avg:301.23ms
step:4593/5100 train_loss:3.2976 train_time:1380446ms step_avg:301.21ms
step:4594/5100 train_loss:3.4573 train_time:1380642ms step_avg:301.19ms
step:4595/5100 train_loss:3.3383 train_time:1380836ms step_avg:301.16ms
step:4596/5100 train_loss:3.2421 train_time:1381031ms step_avg:301.14ms
step:4597/5100 train_loss:3.2307 train_time:1381227ms step_avg:301.12ms
step:4598/5100 train_loss:3.4131 train_time:1381421ms step_avg:301.09ms
step:4599/5100 train_loss:3.3400 train_time:1381616ms step_avg:301.07ms
step:4600/5100 train_loss:3.4574 train_time:1381812ms step_avg:301.05ms
step:4601/5100 train_loss:3.3641 train_time:1383042ms step_avg:301.25ms
step:4602/5100 train_loss:3.1730 train_time:1383244ms step_avg:301.23ms
step:4603/5100 train_loss:3.2854 train_time:1383439ms step_avg:301.21ms
step:4604/5100 train_loss:3.3667 train_time:1383633ms step_avg:301.18ms
step:4605/5100 train_loss:3.3810 train_time:1383829ms step_avg:301.16ms
step:4606/5100 train_loss:3.2981 train_time:1384024ms step_avg:301.14ms
step:4607/5100 train_loss:3.4174 train_time:1384219ms step_avg:301.11ms
step:4608/5100 train_loss:3.2876 train_time:1384414ms step_avg:301.09ms
step:4609/5100 train_loss:3.4008 train_time:1384610ms step_avg:301.07ms
step:4610/5100 train_loss:3.3399 train_time:1384804ms step_avg:301.04ms
step:4611/5100 train_loss:3.3833 train_time:1386034ms step_avg:301.25ms
step:4612/5100 train_loss:3.5219 train_time:1386235ms step_avg:301.22ms
step:4613/5100 train_loss:3.2257 train_time:1386430ms step_avg:301.20ms
step:4614/5100 train_loss:3.0684 train_time:1386626ms step_avg:301.18ms
step:4615/5100 train_loss:3.2770 train_time:1386821ms step_avg:301.16ms
step:4616/5100 train_loss:3.1941 train_time:1387015ms step_avg:301.13ms
step:4617/5100 train_loss:3.3111 train_time:1387211ms step_avg:301.11ms
step:4618/5100 train_loss:3.1750 train_time:1387406ms step_avg:301.09ms
step:4619/5100 train_loss:3.3914 train_time:1387602ms step_avg:301.06ms
step:4620/5100 train_loss:3.4353 train_time:1387797ms step_avg:301.04ms
step:4621/5100 train_loss:3.4760 train_time:1389027ms step_avg:301.24ms
step:4622/5100 train_loss:3.2631 train_time:1389229ms step_avg:301.22ms
step:4623/5100 train_loss:3.2651 train_time:1389425ms step_avg:301.20ms
step:4624/5100 train_loss:3.3011 train_time:1389620ms step_avg:301.17ms
step:4625/5100 train_loss:3.2130 train_time:1389814ms step_avg:301.15ms
step:4625/5100 val_loss:3.3112 train_time:1389846ms step_avg:301.16ms
step:4626/5100 train_loss:3.3934 train_time:1390025ms step_avg:301.13ms
step:4627/5100 train_loss:3.2662 train_time:1390222ms step_avg:301.11ms
step:4628/5100 train_loss:3.3321 train_time:1390418ms step_avg:301.09ms
step:4629/5100 train_loss:3.5271 train_time:1390612ms step_avg:301.06ms
step:4630/5100 train_loss:3.3693 train_time:1390807ms step_avg:301.04ms
step:4631/5100 train_loss:3.4571 train_time:1392039ms step_avg:301.24ms
step:4632/5100 train_loss:3.2601 train_time:1392240ms step_avg:301.22ms
step:4633/5100 train_loss:3.4491 train_time:1392436ms step_avg:301.20ms
step:4634/5100 train_loss:3.3129 train_time:1392632ms step_avg:301.17ms
step:4635/5100 train_loss:3.3630 train_time:1392826ms step_avg:301.15ms
step:4636/5100 train_loss:3.3778 train_time:1393022ms step_avg:301.13ms
step:4637/5100 train_loss:3.2100 train_time:1393216ms step_avg:301.11ms
step:4638/5100 train_loss:3.3753 train_time:1393411ms step_avg:301.08ms
step:4639/5100 train_loss:3.3280 train_time:1393606ms step_avg:301.06ms
step:4640/5100 train_loss:3.3324 train_time:1393802ms step_avg:301.04ms
step:4641/5100 train_loss:3.2707 train_time:1395033ms step_avg:301.24ms
step:4642/5100 train_loss:3.3023 train_time:1395234ms step_avg:301.22ms
step:4643/5100 train_loss:3.3152 train_time:1395430ms step_avg:301.19ms
step:4644/5100 train_loss:3.5378 train_time:1395625ms step_avg:301.17ms
step:4645/5100 train_loss:3.4036 train_time:1395822ms step_avg:301.15ms
step:4646/5100 train_loss:3.4414 train_time:1396017ms step_avg:301.13ms
step:4647/5100 train_loss:3.2641 train_time:1396211ms step_avg:301.10ms
step:4648/5100 train_loss:3.3776 train_time:1396407ms step_avg:301.08ms
step:4649/5100 train_loss:3.3253 train_time:1396602ms step_avg:301.06ms
step:4650/5100 train_loss:3.3750 train_time:1396797ms step_avg:301.03ms
step:4651/5100 train_loss:3.4843 train_time:1398027ms step_avg:301.23ms
step:4652/5100 train_loss:3.3203 train_time:1398230ms step_avg:301.21ms
step:4653/5100 train_loss:3.4321 train_time:1398426ms step_avg:301.19ms
step:4654/5100 train_loss:3.2836 train_time:1398621ms step_avg:301.17ms
step:4655/5100 train_loss:3.3176 train_time:1398816ms step_avg:301.14ms
step:4656/5100 train_loss:3.3464 train_time:1399011ms step_avg:301.12ms
step:4657/5100 train_loss:3.2869 train_time:1399207ms step_avg:301.10ms
step:4658/5100 train_loss:3.2168 train_time:1399403ms step_avg:301.08ms
step:4659/5100 train_loss:3.2597 train_time:1399598ms step_avg:301.05ms
step:4660/5100 train_loss:3.1912 train_time:1399793ms step_avg:301.03ms
step:4661/5100 train_loss:3.3625 train_time:1401023ms step_avg:301.23ms
step:4662/5100 train_loss:3.3422 train_time:1401225ms step_avg:301.21ms
step:4663/5100 train_loss:3.2996 train_time:1401421ms step_avg:301.19ms
step:4664/5100 train_loss:3.2346 train_time:1401616ms step_avg:301.16ms
step:4665/5100 train_loss:3.2411 train_time:1401810ms step_avg:301.14ms
step:4666/5100 train_loss:3.2879 train_time:1402004ms step_avg:301.12ms
step:4667/5100 train_loss:3.3814 train_time:1402199ms step_avg:301.09ms
step:4668/5100 train_loss:3.3029 train_time:1402394ms step_avg:301.07ms
step:4669/5100 train_loss:3.2753 train_time:1402590ms step_avg:301.05ms
step:4670/5100 train_loss:3.3309 train_time:1402784ms step_avg:301.03ms
step:4671/5100 train_loss:3.4242 train_time:1404015ms step_avg:301.23ms
step:4672/5100 train_loss:3.3140 train_time:1404217ms step_avg:301.20ms
step:4673/5100 train_loss:3.3621 train_time:1404412ms step_avg:301.18ms
step:4674/5100 train_loss:3.3019 train_time:1404606ms step_avg:301.16ms
step:4675/5100 train_loss:3.3340 train_time:1404803ms step_avg:301.14ms
step:4676/5100 train_loss:3.4195 train_time:1404998ms step_avg:301.11ms
step:4677/5100 train_loss:3.1448 train_time:1405192ms step_avg:301.09ms
step:4678/5100 train_loss:3.2010 train_time:1405386ms step_avg:301.07ms
step:4679/5100 train_loss:3.3336 train_time:1405582ms step_avg:301.05ms
step:4680/5100 train_loss:3.2941 train_time:1405777ms step_avg:301.02ms
step:4681/5100 train_loss:3.3137 train_time:1407007ms step_avg:301.22ms
step:4682/5100 train_loss:3.3060 train_time:1407208ms step_avg:301.20ms
step:4683/5100 train_loss:3.2395 train_time:1407403ms step_avg:301.18ms
step:4684/5100 train_loss:3.2128 train_time:1407598ms step_avg:301.15ms
step:4685/5100 train_loss:3.4674 train_time:1407792ms step_avg:301.13ms
step:4686/5100 train_loss:3.5419 train_time:1407986ms step_avg:301.11ms
step:4687/5100 train_loss:3.2289 train_time:1408181ms step_avg:301.09ms
step:4688/5100 train_loss:3.2452 train_time:1408377ms step_avg:301.06ms
step:4689/5100 train_loss:3.4243 train_time:1408571ms step_avg:301.04ms
step:4690/5100 train_loss:3.2607 train_time:1408766ms step_avg:301.02ms
step:4691/5100 train_loss:3.1165 train_time:1409997ms step_avg:301.22ms
step:4692/5100 train_loss:3.2176 train_time:1410200ms step_avg:301.20ms
step:4693/5100 train_loss:3.2328 train_time:1410394ms step_avg:301.17ms
step:4694/5100 train_loss:3.2530 train_time:1410589ms step_avg:301.15ms
step:4695/5100 train_loss:3.2660 train_time:1410784ms step_avg:301.13ms
step:4696/5100 train_loss:3.2805 train_time:1410980ms step_avg:301.11ms
step:4697/5100 train_loss:3.3423 train_time:1411175ms step_avg:301.08ms
step:4698/5100 train_loss:3.2590 train_time:1411370ms step_avg:301.06ms
step:4699/5100 train_loss:3.2837 train_time:1411565ms step_avg:301.04ms
step:4700/5100 train_loss:3.3827 train_time:1411760ms step_avg:301.01ms
step:4701/5100 train_loss:3.3058 train_time:1412991ms step_avg:301.21ms
step:4702/5100 train_loss:3.2887 train_time:1413193ms step_avg:301.19ms
step:4703/5100 train_loss:3.2482 train_time:1413387ms step_avg:301.17ms
step:4704/5100 train_loss:3.3321 train_time:1413583ms step_avg:301.15ms
step:4705/5100 train_loss:3.2864 train_time:1413778ms step_avg:301.12ms
step:4706/5100 train_loss:3.2118 train_time:1413973ms step_avg:301.10ms
step:4707/5100 train_loss:3.3398 train_time:1414167ms step_avg:301.08ms
step:4708/5100 train_loss:3.4356 train_time:1414362ms step_avg:301.06ms
step:4709/5100 train_loss:3.2438 train_time:1414557ms step_avg:301.03ms
step:4710/5100 train_loss:3.2264 train_time:1414751ms step_avg:301.01ms
step:4711/5100 train_loss:3.2449 train_time:1415982ms step_avg:301.21ms
step:4712/5100 train_loss:3.2667 train_time:1416182ms step_avg:301.19ms
step:4713/5100 train_loss:3.3858 train_time:1416378ms step_avg:301.16ms
step:4714/5100 train_loss:3.2276 train_time:1416574ms step_avg:301.14ms
step:4715/5100 train_loss:3.2958 train_time:1416768ms step_avg:301.12ms
step:4716/5100 train_loss:3.2215 train_time:1416964ms step_avg:301.10ms
step:4717/5100 train_loss:3.2976 train_time:1417160ms step_avg:301.07ms
step:4718/5100 train_loss:3.2234 train_time:1417354ms step_avg:301.05ms
step:4719/5100 train_loss:3.1855 train_time:1417549ms step_avg:301.03ms
step:4720/5100 train_loss:3.3535 train_time:1417744ms step_avg:301.01ms
step:4721/5100 train_loss:3.3414 train_time:1418975ms step_avg:301.20ms
step:4722/5100 train_loss:3.3426 train_time:1419177ms step_avg:301.18ms
step:4723/5100 train_loss:3.1926 train_time:1419373ms step_avg:301.16ms
step:4724/5100 train_loss:3.3782 train_time:1419567ms step_avg:301.14ms
step:4725/5100 train_loss:3.2623 train_time:1419899ms step_avg:301.15ms
step:4726/5100 train_loss:3.5316 train_time:1420094ms step_avg:301.12ms
step:4727/5100 train_loss:3.3858 train_time:1420288ms step_avg:301.10ms
step:4728/5100 train_loss:3.2578 train_time:1420483ms step_avg:301.08ms
step:4729/5100 train_loss:3.1970 train_time:1420678ms step_avg:301.05ms
step:4730/5100 train_loss:3.1472 train_time:1420873ms step_avg:301.03ms
step:4731/5100 train_loss:3.2467 train_time:1422103ms step_avg:301.23ms
step:4732/5100 train_loss:3.3148 train_time:1422305ms step_avg:301.21ms
step:4733/5100 train_loss:3.2195 train_time:1422501ms step_avg:301.19ms
step:4734/5100 train_loss:3.0991 train_time:1422696ms step_avg:301.16ms
step:4735/5100 train_loss:3.3881 train_time:1422891ms step_avg:301.14ms
step:4736/5100 train_loss:3.2658 train_time:1423085ms step_avg:301.12ms
step:4737/5100 train_loss:3.4349 train_time:1423280ms step_avg:301.10ms
step:4738/5100 train_loss:3.3581 train_time:1423475ms step_avg:301.07ms
step:4739/5100 train_loss:3.3076 train_time:1423670ms step_avg:301.05ms
step:4740/5100 train_loss:3.2772 train_time:1423864ms step_avg:301.03ms
step:4741/5100 train_loss:3.2894 train_time:1425097ms step_avg:301.23ms
step:4742/5100 train_loss:3.2906 train_time:1425298ms step_avg:301.20ms
step:4743/5100 train_loss:3.1719 train_time:1425493ms step_avg:301.18ms
step:4744/5100 train_loss:3.3015 train_time:1425689ms step_avg:301.16ms
step:4745/5100 train_loss:3.2675 train_time:1425884ms step_avg:301.14ms
step:4746/5100 train_loss:3.2707 train_time:1426080ms step_avg:301.11ms
step:4747/5100 train_loss:3.2405 train_time:1426275ms step_avg:301.09ms
step:4748/5100 train_loss:3.4310 train_time:1426470ms step_avg:301.07ms
step:4749/5100 train_loss:3.2747 train_time:1426665ms step_avg:301.05ms
step:4750/5100 train_loss:3.3800 train_time:1427023ms step_avg:301.06ms
step:4750/5100 val_loss:3.2989 train_time:1427055ms step_avg:301.07ms
step:4751/5100 train_loss:3.1891 train_time:1428272ms step_avg:301.26ms
step:4752/5100 train_loss:3.1156 train_time:1428475ms step_avg:301.24ms
step:4753/5100 train_loss:3.1980 train_time:1428671ms step_avg:301.22ms
step:4754/5100 train_loss:3.4027 train_time:1428868ms step_avg:301.19ms
step:4755/5100 train_loss:3.2800 train_time:1429063ms step_avg:301.17ms
step:4756/5100 train_loss:3.5187 train_time:1429258ms step_avg:301.15ms
step:4757/5100 train_loss:3.3822 train_time:1429454ms step_avg:301.13ms
step:4758/5100 train_loss:3.2913 train_time:1429650ms step_avg:301.11ms
step:4759/5100 train_loss:3.3476 train_time:1429845ms step_avg:301.08ms
step:4760/5100 train_loss:3.3296 train_time:1430039ms step_avg:301.06ms
step:4761/5100 train_loss:3.2692 train_time:1431269ms step_avg:301.26ms
step:4762/5100 train_loss:3.3133 train_time:1431470ms step_avg:301.24ms
step:4763/5100 train_loss:3.2876 train_time:1431667ms step_avg:301.21ms
step:4764/5100 train_loss:3.1407 train_time:1431863ms step_avg:301.19ms
step:4765/5100 train_loss:3.1570 train_time:1432058ms step_avg:301.17ms
step:4766/5100 train_loss:3.1513 train_time:1432254ms step_avg:301.15ms
step:4767/5100 train_loss:3.3933 train_time:1432450ms step_avg:301.12ms
step:4768/5100 train_loss:3.6511 train_time:1432644ms step_avg:301.10ms
step:4769/5100 train_loss:3.3683 train_time:1432838ms step_avg:301.08ms
step:4770/5100 train_loss:3.2733 train_time:1433035ms step_avg:301.06ms
step:4771/5100 train_loss:3.3403 train_time:1434266ms step_avg:301.25ms
step:4772/5100 train_loss:3.2972 train_time:1434467ms step_avg:301.23ms
step:4773/5100 train_loss:3.2685 train_time:1434662ms step_avg:301.21ms
step:4774/5100 train_loss:3.4579 train_time:1434856ms step_avg:301.19ms
step:4775/5100 train_loss:3.2694 train_time:1435051ms step_avg:301.16ms
step:4776/5100 train_loss:3.4107 train_time:1435245ms step_avg:301.14ms
step:4777/5100 train_loss:3.3160 train_time:1435439ms step_avg:301.12ms
step:4778/5100 train_loss:3.1557 train_time:1435635ms step_avg:301.10ms
step:4779/5100 train_loss:3.3345 train_time:1435831ms step_avg:301.08ms
step:4780/5100 train_loss:3.2671 train_time:1436026ms step_avg:301.05ms
step:4781/5100 train_loss:3.3353 train_time:1437256ms step_avg:301.25ms
step:4782/5100 train_loss:3.2614 train_time:1437459ms step_avg:301.23ms
step:4783/5100 train_loss:3.2092 train_time:1437655ms step_avg:301.21ms
step:4784/5100 train_loss:3.2671 train_time:1437849ms step_avg:301.18ms
step:4785/5100 train_loss:3.1967 train_time:1438044ms step_avg:301.16ms
step:4786/5100 train_loss:3.5267 train_time:1438238ms step_avg:301.14ms
step:4787/5100 train_loss:3.4123 train_time:1438434ms step_avg:301.12ms
step:4788/5100 train_loss:3.3331 train_time:1438630ms step_avg:301.09ms
step:4789/5100 train_loss:3.3109 train_time:1438824ms step_avg:301.07ms
step:4790/5100 train_loss:3.2345 train_time:1439019ms step_avg:301.05ms
step:4791/5100 train_loss:3.3427 train_time:1440251ms step_avg:301.24ms
step:4792/5100 train_loss:3.3513 train_time:1440453ms step_avg:301.22ms
step:4793/5100 train_loss:3.2657 train_time:1440649ms step_avg:301.20ms
step:4794/5100 train_loss:3.3430 train_time:1440843ms step_avg:301.18ms
step:4795/5100 train_loss:3.1805 train_time:1441037ms step_avg:301.16ms
step:4796/5100 train_loss:3.3308 train_time:1441232ms step_avg:301.14ms
step:4797/5100 train_loss:3.4032 train_time:1441427ms step_avg:301.11ms
step:4798/5100 train_loss:3.0683 train_time:1441622ms step_avg:301.09ms
step:4799/5100 train_loss:3.2496 train_time:1441817ms step_avg:301.07ms
step:4800/5100 train_loss:3.2303 train_time:1442013ms step_avg:301.05ms
step:4801/5100 train_loss:3.3266 train_time:1443244ms step_avg:301.24ms
step:4802/5100 train_loss:3.1480 train_time:1443445ms step_avg:301.22ms
step:4803/5100 train_loss:3.1880 train_time:1443640ms step_avg:301.20ms
step:4804/5100 train_loss:3.3823 train_time:1443836ms step_avg:301.18ms
step:4805/5100 train_loss:3.3328 train_time:1444032ms step_avg:301.15ms
step:4806/5100 train_loss:3.4007 train_time:1444228ms step_avg:301.13ms
step:4807/5100 train_loss:3.4112 train_time:1444423ms step_avg:301.11ms
step:4808/5100 train_loss:3.1828 train_time:1444617ms step_avg:301.09ms
step:4809/5100 train_loss:3.2981 train_time:1444812ms step_avg:301.07ms
step:4810/5100 train_loss:3.2450 train_time:1445007ms step_avg:301.04ms
step:4811/5100 train_loss:3.4742 train_time:1446238ms step_avg:301.24ms
step:4812/5100 train_loss:3.2766 train_time:1446439ms step_avg:301.22ms
step:4813/5100 train_loss:3.3119 train_time:1446634ms step_avg:301.19ms
step:4814/5100 train_loss:3.2099 train_time:1446829ms step_avg:301.17ms
step:4815/5100 train_loss:3.2558 train_time:1447025ms step_avg:301.15ms
step:4816/5100 train_loss:3.6915 train_time:1447220ms step_avg:301.13ms
step:4817/5100 train_loss:3.3729 train_time:1447415ms step_avg:301.11ms
step:4818/5100 train_loss:3.3048 train_time:1447611ms step_avg:301.08ms
step:4819/5100 train_loss:3.1555 train_time:1447806ms step_avg:301.06ms
step:4820/5100 train_loss:3.2894 train_time:1447999ms step_avg:301.04ms
step:4821/5100 train_loss:3.2951 train_time:1449231ms step_avg:301.23ms
step:4822/5100 train_loss:3.3461 train_time:1449433ms step_avg:301.21ms
step:4823/5100 train_loss:3.4016 train_time:1449629ms step_avg:301.19ms
step:4824/5100 train_loss:3.2827 train_time:1449824ms step_avg:301.17ms
step:4825/5100 train_loss:3.2656 train_time:1450019ms step_avg:301.15ms
step:4826/5100 train_loss:3.1870 train_time:1450215ms step_avg:301.12ms
step:4827/5100 train_loss:3.1503 train_time:1450411ms step_avg:301.10ms
step:4828/5100 train_loss:3.3339 train_time:1450605ms step_avg:301.08ms
step:4829/5100 train_loss:3.2213 train_time:1450801ms step_avg:301.06ms
step:4830/5100 train_loss:3.3380 train_time:1450995ms step_avg:301.04ms
step:4831/5100 train_loss:3.5033 train_time:1452225ms step_avg:301.23ms
step:4832/5100 train_loss:3.2355 train_time:1452426ms step_avg:301.21ms
step:4833/5100 train_loss:3.3244 train_time:1452622ms step_avg:301.19ms
step:4834/5100 train_loss:3.2853 train_time:1452817ms step_avg:301.16ms
step:4835/5100 train_loss:3.4712 train_time:1453013ms step_avg:301.14ms
step:4836/5100 train_loss:3.2830 train_time:1453208ms step_avg:301.12ms
step:4837/5100 train_loss:3.5379 train_time:1453403ms step_avg:301.10ms
step:4838/5100 train_loss:3.4904 train_time:1453597ms step_avg:301.08ms
step:4839/5100 train_loss:3.3139 train_time:1453793ms step_avg:301.05ms
step:4840/5100 train_loss:3.3135 train_time:1453989ms step_avg:301.03ms
step:4841/5100 train_loss:3.3013 train_time:1455220ms step_avg:301.23ms
step:4842/5100 train_loss:3.3373 train_time:1455421ms step_avg:301.20ms
step:4843/5100 train_loss:3.3314 train_time:1455617ms step_avg:301.18ms
step:4844/5100 train_loss:3.1951 train_time:1455813ms step_avg:301.16ms
step:4845/5100 train_loss:3.2246 train_time:1456008ms step_avg:301.14ms
step:4846/5100 train_loss:3.1988 train_time:1456202ms step_avg:301.12ms
step:4847/5100 train_loss:3.3564 train_time:1456397ms step_avg:301.10ms
step:4848/5100 train_loss:3.2295 train_time:1456593ms step_avg:301.07ms
step:4849/5100 train_loss:3.2686 train_time:1456787ms step_avg:301.05ms
step:4850/5100 train_loss:3.3961 train_time:1456984ms step_avg:301.03ms
step:4851/5100 train_loss:3.2827 train_time:1458215ms step_avg:301.22ms
step:4852/5100 train_loss:3.0915 train_time:1458415ms step_avg:301.20ms
step:4853/5100 train_loss:3.1837 train_time:1458610ms step_avg:301.18ms
step:4854/5100 train_loss:3.3253 train_time:1458805ms step_avg:301.16ms
step:4855/5100 train_loss:3.2711 train_time:1458999ms step_avg:301.14ms
step:4856/5100 train_loss:3.4133 train_time:1459194ms step_avg:301.11ms
step:4857/5100 train_loss:3.2504 train_time:1459391ms step_avg:301.09ms
step:4858/5100 train_loss:3.2846 train_time:1459587ms step_avg:301.07ms
step:4859/5100 train_loss:3.2336 train_time:1459782ms step_avg:301.05ms
step:4860/5100 train_loss:3.3643 train_time:1459977ms step_avg:301.03ms
step:4861/5100 train_loss:3.2307 train_time:1461208ms step_avg:301.22ms
step:4862/5100 train_loss:3.2846 train_time:1461410ms step_avg:301.20ms
step:4863/5100 train_loss:3.2933 train_time:1461605ms step_avg:301.18ms
step:4864/5100 train_loss:3.2558 train_time:1461799ms step_avg:301.15ms
step:4865/5100 train_loss:3.3299 train_time:1461994ms step_avg:301.13ms
step:4866/5100 train_loss:2.9788 train_time:1462189ms step_avg:301.11ms
step:4867/5100 train_loss:3.2044 train_time:1462384ms step_avg:301.09ms
step:4868/5100 train_loss:3.2559 train_time:1462578ms step_avg:301.07ms
step:4869/5100 train_loss:3.2777 train_time:1462773ms step_avg:301.04ms
step:4870/5100 train_loss:3.2790 train_time:1462967ms step_avg:301.02ms
step:4871/5100 train_loss:3.2818 train_time:1464198ms step_avg:301.21ms
step:4872/5100 train_loss:3.3979 train_time:1464398ms step_avg:301.19ms
step:4873/5100 train_loss:3.3821 train_time:1464593ms step_avg:301.17ms
step:4874/5100 train_loss:3.4162 train_time:1464787ms step_avg:301.15ms
step:4875/5100 train_loss:3.4907 train_time:1464982ms step_avg:301.13ms
step:4875/5100 val_loss:3.2878 train_time:1465015ms step_avg:301.13ms
step:4876/5100 train_loss:3.3128 train_time:1465196ms step_avg:301.11ms
step:4877/5100 train_loss:3.2198 train_time:1465393ms step_avg:301.09ms
step:4878/5100 train_loss:3.1823 train_time:1465589ms step_avg:301.07ms
step:4879/5100 train_loss:3.2361 train_time:1465784ms step_avg:301.04ms
step:4880/5100 train_loss:3.3699 train_time:1465979ms step_avg:301.02ms
step:4881/5100 train_loss:3.2127 train_time:1467209ms step_avg:301.21ms
step:4882/5100 train_loss:3.3393 train_time:1467408ms step_avg:301.19ms
step:4883/5100 train_loss:3.3494 train_time:1467604ms step_avg:301.17ms
step:4884/5100 train_loss:3.2554 train_time:1467799ms step_avg:301.15ms
step:4885/5100 train_loss:3.2595 train_time:1467995ms step_avg:301.13ms
step:4886/5100 train_loss:3.3688 train_time:1468191ms step_avg:301.11ms
step:4887/5100 train_loss:3.3923 train_time:1468386ms step_avg:301.08ms
step:4888/5100 train_loss:3.2618 train_time:1468581ms step_avg:301.06ms
step:4889/5100 train_loss:3.2283 train_time:1468776ms step_avg:301.04ms
step:4890/5100 train_loss:3.3158 train_time:1468972ms step_avg:301.02ms
step:4891/5100 train_loss:3.2277 train_time:1470205ms step_avg:301.21ms
step:4892/5100 train_loss:3.3189 train_time:1470406ms step_avg:301.19ms
step:4893/5100 train_loss:3.3152 train_time:1470601ms step_avg:301.17ms
step:4894/5100 train_loss:3.3468 train_time:1470796ms step_avg:301.15ms
step:4895/5100 train_loss:3.4084 train_time:1470991ms step_avg:301.12ms
step:4896/5100 train_loss:3.3108 train_time:1471186ms step_avg:301.10ms
step:4897/5100 train_loss:3.2629 train_time:1471381ms step_avg:301.08ms
step:4898/5100 train_loss:3.4589 train_time:1471576ms step_avg:301.06ms
step:4899/5100 train_loss:3.2189 train_time:1471772ms step_avg:301.04ms
step:4900/5100 train_loss:3.2742 train_time:1471967ms step_avg:301.02ms
step:4901/5100 train_loss:3.1820 train_time:1473199ms step_avg:301.21ms
step:4902/5100 train_loss:3.1492 train_time:1473400ms step_avg:301.19ms
step:4903/5100 train_loss:3.2874 train_time:1473595ms step_avg:301.16ms
step:4904/5100 train_loss:3.2324 train_time:1473791ms step_avg:301.14ms
step:4905/5100 train_loss:3.3061 train_time:1473985ms step_avg:301.12ms
step:4906/5100 train_loss:3.3443 train_time:1474181ms step_avg:301.10ms
step:4907/5100 train_loss:3.2253 train_time:1474375ms step_avg:301.08ms
step:4908/5100 train_loss:3.3139 train_time:1474571ms step_avg:301.06ms
step:4909/5100 train_loss:3.2135 train_time:1474766ms step_avg:301.03ms
step:4910/5100 train_loss:3.3265 train_time:1474962ms step_avg:301.01ms
step:4911/5100 train_loss:3.3645 train_time:1476192ms step_avg:301.20ms
step:4912/5100 train_loss:3.2721 train_time:1476391ms step_avg:301.18ms
step:4913/5100 train_loss:3.2330 train_time:1476587ms step_avg:301.16ms
step:4914/5100 train_loss:3.2338 train_time:1476919ms step_avg:301.17ms
step:4915/5100 train_loss:3.1523 train_time:1477112ms step_avg:301.14ms
step:4916/5100 train_loss:3.3572 train_time:1477308ms step_avg:301.12ms
step:4917/5100 train_loss:3.3318 train_time:1477502ms step_avg:301.10ms
step:4918/5100 train_loss:3.2619 train_time:1477698ms step_avg:301.08ms
step:4919/5100 train_loss:3.2729 train_time:1477892ms step_avg:301.06ms
step:4920/5100 train_loss:3.2719 train_time:1478088ms step_avg:301.04ms
step:4921/5100 train_loss:3.3554 train_time:1479319ms step_avg:301.23ms
step:4922/5100 train_loss:3.5165 train_time:1479517ms step_avg:301.20ms
step:4923/5100 train_loss:3.3725 train_time:1479713ms step_avg:301.18ms
step:4924/5100 train_loss:3.2430 train_time:1479908ms step_avg:301.16ms
step:4925/5100 train_loss:3.5445 train_time:1480104ms step_avg:301.14ms
step:4926/5100 train_loss:3.2826 train_time:1480298ms step_avg:301.12ms
step:4927/5100 train_loss:3.2665 train_time:1480494ms step_avg:301.10ms
step:4928/5100 train_loss:3.1860 train_time:1480691ms step_avg:301.08ms
step:4929/5100 train_loss:3.1974 train_time:1480885ms step_avg:301.05ms
step:4930/5100 train_loss:3.3356 train_time:1481080ms step_avg:301.03ms
step:4931/5100 train_loss:3.5893 train_time:1482310ms step_avg:301.22ms
step:4932/5100 train_loss:3.1979 train_time:1482510ms step_avg:301.20ms
step:4933/5100 train_loss:3.2954 train_time:1482705ms step_avg:301.18ms
step:4934/5100 train_loss:3.3599 train_time:1482899ms step_avg:301.16ms
step:4935/5100 train_loss:3.1432 train_time:1483093ms step_avg:301.14ms
step:4936/5100 train_loss:3.3001 train_time:1483288ms step_avg:301.11ms
step:4937/5100 train_loss:3.3508 train_time:1483483ms step_avg:301.09ms
step:4938/5100 train_loss:3.3297 train_time:1483678ms step_avg:301.07ms
step:4939/5100 train_loss:3.3298 train_time:1483874ms step_avg:301.05ms
step:4940/5100 train_loss:3.4483 train_time:1484232ms step_avg:301.06ms
step:4941/5100 train_loss:3.2922 train_time:1485462ms step_avg:301.25ms
step:4942/5100 train_loss:3.2982 train_time:1485665ms step_avg:301.23ms
step:4943/5100 train_loss:3.0469 train_time:1485860ms step_avg:301.21ms
step:4944/5100 train_loss:3.5383 train_time:1486054ms step_avg:301.19ms
step:4945/5100 train_loss:3.4966 train_time:1486250ms step_avg:301.17ms
step:4946/5100 train_loss:3.1157 train_time:1486445ms step_avg:301.14ms
step:4947/5100 train_loss:3.3635 train_time:1486639ms step_avg:301.12ms
step:4948/5100 train_loss:3.4013 train_time:1486834ms step_avg:301.10ms
step:4949/5100 train_loss:3.2349 train_time:1487029ms step_avg:301.08ms
step:4950/5100 train_loss:3.3554 train_time:1487224ms step_avg:301.06ms
step:4951/5100 train_loss:3.2227 train_time:1488455ms step_avg:301.25ms
step:4952/5100 train_loss:3.3451 train_time:1488655ms step_avg:301.23ms
step:4953/5100 train_loss:3.3036 train_time:1488852ms step_avg:301.20ms
step:4954/5100 train_loss:3.1944 train_time:1489045ms step_avg:301.18ms
step:4955/5100 train_loss:3.3365 train_time:1489240ms step_avg:301.16ms
step:4956/5100 train_loss:3.1617 train_time:1489435ms step_avg:301.14ms
step:4957/5100 train_loss:3.2541 train_time:1489631ms step_avg:301.12ms
step:4958/5100 train_loss:3.2351 train_time:1489827ms step_avg:301.10ms
step:4959/5100 train_loss:3.2498 train_time:1490022ms step_avg:301.08ms
step:4960/5100 train_loss:3.2920 train_time:1490217ms step_avg:301.05ms
step:4961/5100 train_loss:3.4407 train_time:1491449ms step_avg:301.24ms
step:4962/5100 train_loss:3.2044 train_time:1491649ms step_avg:301.22ms
step:4963/5100 train_loss:3.3400 train_time:1491844ms step_avg:301.20ms
step:4964/5100 train_loss:3.1757 train_time:1492038ms step_avg:301.18ms
step:4965/5100 train_loss:3.8960 train_time:1492233ms step_avg:301.16ms
step:4966/5100 train_loss:3.1703 train_time:1492429ms step_avg:301.14ms
step:4967/5100 train_loss:3.3048 train_time:1492625ms step_avg:301.11ms
step:4968/5100 train_loss:3.1301 train_time:1492819ms step_avg:301.09ms
step:4969/5100 train_loss:3.8429 train_time:1493014ms step_avg:301.07ms
step:4970/5100 train_loss:3.3709 train_time:1493210ms step_avg:301.05ms
step:4971/5100 train_loss:3.2924 train_time:1494440ms step_avg:301.24ms
step:4972/5100 train_loss:3.2359 train_time:1494642ms step_avg:301.22ms
step:4973/5100 train_loss:3.3237 train_time:1494837ms step_avg:301.20ms
step:4974/5100 train_loss:3.1953 train_time:1495032ms step_avg:301.17ms
step:4975/5100 train_loss:3.1957 train_time:1495227ms step_avg:301.15ms
step:4976/5100 train_loss:3.3428 train_time:1495423ms step_avg:301.13ms
step:4977/5100 train_loss:3.2700 train_time:1495617ms step_avg:301.11ms
step:4978/5100 train_loss:3.2278 train_time:1495813ms step_avg:301.09ms
step:4979/5100 train_loss:3.2862 train_time:1496008ms step_avg:301.07ms
step:4980/5100 train_loss:3.2196 train_time:1496204ms step_avg:301.05ms
step:4981/5100 train_loss:3.3661 train_time:1497435ms step_avg:301.23ms
step:4982/5100 train_loss:3.3289 train_time:1497636ms step_avg:301.21ms
step:4983/5100 train_loss:3.1392 train_time:1497832ms step_avg:301.19ms
step:4984/5100 train_loss:3.1638 train_time:1498027ms step_avg:301.17ms
step:4985/5100 train_loss:3.4494 train_time:1498223ms step_avg:301.15ms
step:4986/5100 train_loss:3.3316 train_time:1498417ms step_avg:301.13ms
step:4987/5100 train_loss:3.2490 train_time:1498613ms step_avg:301.11ms
step:4988/5100 train_loss:3.2831 train_time:1498809ms step_avg:301.09ms
step:4989/5100 train_loss:3.2629 train_time:1499004ms step_avg:301.07ms
step:4990/5100 train_loss:3.2436 train_time:1499198ms step_avg:301.04ms
step:4991/5100 train_loss:3.3016 train_time:1500429ms step_avg:301.23ms
step:4992/5100 train_loss:3.3392 train_time:1500630ms step_avg:301.21ms
step:4993/5100 train_loss:3.1654 train_time:1500826ms step_avg:301.19ms
step:4994/5100 train_loss:3.2947 train_time:1501021ms step_avg:301.17ms
step:4995/5100 train_loss:3.2255 train_time:1501215ms step_avg:301.15ms
step:4996/5100 train_loss:3.3714 train_time:1501411ms step_avg:301.13ms
step:4997/5100 train_loss:3.2433 train_time:1501606ms step_avg:301.10ms
step:4998/5100 train_loss:3.4028 train_time:1501801ms step_avg:301.08ms
step:4999/5100 train_loss:3.2604 train_time:1501995ms step_avg:301.06ms
step:5000/5100 train_loss:3.3898 train_time:1502191ms step_avg:301.04ms
step:5000/5100 val_loss:3.2790 train_time:1502223ms step_avg:301.05ms
step:5001/5100 train_loss:3.3135 train_time:1503438ms step_avg:301.23ms
step:5002/5100 train_loss:3.3158 train_time:1503640ms step_avg:301.21ms
step:5003/5100 train_loss:3.2068 train_time:1503836ms step_avg:301.19ms
step:5004/5100 train_loss:3.2807 train_time:1504032ms step_avg:301.17ms
step:5005/5100 train_loss:3.2897 train_time:1504227ms step_avg:301.15ms
step:5006/5100 train_loss:3.1631 train_time:1504420ms step_avg:301.12ms
step:5007/5100 train_loss:3.3930 train_time:1504616ms step_avg:301.10ms
step:5008/5100 train_loss:3.2414 train_time:1504811ms step_avg:301.08ms
step:5009/5100 train_loss:3.2714 train_time:1505006ms step_avg:301.06ms
step:5010/5100 train_loss:3.2343 train_time:1505202ms step_avg:301.04ms
step:5011/5100 train_loss:3.4488 train_time:1506434ms step_avg:301.23ms
step:5012/5100 train_loss:3.2422 train_time:1506635ms step_avg:301.21ms
step:5013/5100 train_loss:3.2261 train_time:1506830ms step_avg:301.19ms
step:5014/5100 train_loss:3.1710 train_time:1507024ms step_avg:301.16ms
step:5015/5100 train_loss:3.2935 train_time:1507219ms step_avg:301.14ms
step:5016/5100 train_loss:3.2716 train_time:1507415ms step_avg:301.12ms
step:5017/5100 train_loss:3.3106 train_time:1507610ms step_avg:301.10ms
step:5018/5100 train_loss:3.3295 train_time:1507806ms step_avg:301.08ms
step:5019/5100 train_loss:3.2876 train_time:1508001ms step_avg:301.06ms
step:5020/5100 train_loss:3.7968 train_time:1508196ms step_avg:301.04ms
step:5021/5100 train_loss:3.2349 train_time:1509427ms step_avg:301.22ms
step:5022/5100 train_loss:3.3379 train_time:1509629ms step_avg:301.20ms
step:5023/5100 train_loss:3.2639 train_time:1509824ms step_avg:301.18ms
step:5024/5100 train_loss:3.4044 train_time:1510018ms step_avg:301.16ms
step:5025/5100 train_loss:3.2013 train_time:1510213ms step_avg:301.14ms
step:5026/5100 train_loss:3.3620 train_time:1510409ms step_avg:301.12ms
step:5027/5100 train_loss:3.2145 train_time:1510604ms step_avg:301.10ms
step:5028/5100 train_loss:3.4264 train_time:1510799ms step_avg:301.08ms
step:5029/5100 train_loss:3.3268 train_time:1510993ms step_avg:301.05ms
step:5030/5100 train_loss:3.3655 train_time:1511188ms step_avg:301.03ms
step:5031/5100 train_loss:3.2134 train_time:1512419ms step_avg:301.22ms
step:5032/5100 train_loss:3.2518 train_time:1512619ms step_avg:301.20ms
step:5033/5100 train_loss:3.1941 train_time:1512814ms step_avg:301.18ms
step:5034/5100 train_loss:3.3855 train_time:1513008ms step_avg:301.16ms
step:5035/5100 train_loss:3.3799 train_time:1513203ms step_avg:301.13ms
step:5036/5100 train_loss:3.2348 train_time:1513398ms step_avg:301.11ms
step:5037/5100 train_loss:3.1625 train_time:1513593ms step_avg:301.09ms
step:5038/5100 train_loss:3.1991 train_time:1513788ms step_avg:301.07ms
step:5039/5100 train_loss:3.3306 train_time:1513982ms step_avg:301.05ms
step:5040/5100 train_loss:3.2631 train_time:1514177ms step_avg:301.03ms
step:5041/5100 train_loss:3.4332 train_time:1515409ms step_avg:301.21ms
step:5042/5100 train_loss:3.2267 train_time:1515608ms step_avg:301.19ms
step:5043/5100 train_loss:3.4156 train_time:1515802ms step_avg:301.17ms
step:5044/5100 train_loss:3.3230 train_time:1515998ms step_avg:301.15ms
step:5045/5100 train_loss:3.3832 train_time:1516194ms step_avg:301.13ms
step:5046/5100 train_loss:3.2130 train_time:1516389ms step_avg:301.11ms
step:5047/5100 train_loss:3.3519 train_time:1516583ms step_avg:301.09ms
step:5048/5100 train_loss:3.0991 train_time:1516777ms step_avg:301.07ms
step:5049/5100 train_loss:3.2628 train_time:1516974ms step_avg:301.05ms
step:5050/5100 train_loss:3.2687 train_time:1517170ms step_avg:301.03ms
step:5051/5100 train_loss:3.2086 train_time:1518399ms step_avg:301.21ms
step:5052/5100 train_loss:3.2481 train_time:1518600ms step_avg:301.19ms
step:5053/5100 train_loss:3.2943 train_time:1518796ms step_avg:301.17ms
step:5054/5100 train_loss:3.3364 train_time:1518991ms step_avg:301.15ms
step:5055/5100 train_loss:3.4090 train_time:1519186ms step_avg:301.13ms
step:5056/5100 train_loss:3.3558 train_time:1519380ms step_avg:301.11ms
step:5057/5100 train_loss:3.2402 train_time:1519576ms step_avg:301.09ms
step:5058/5100 train_loss:3.1426 train_time:1519772ms step_avg:301.06ms
step:5059/5100 train_loss:3.0571 train_time:1519967ms step_avg:301.04ms
step:5060/5100 train_loss:3.2713 train_time:1520162ms step_avg:301.02ms
step:5061/5100 train_loss:3.3589 train_time:1521392ms step_avg:301.21ms
step:5062/5100 train_loss:3.2858 train_time:1521594ms step_avg:301.19ms
step:5063/5100 train_loss:3.4077 train_time:1521789ms step_avg:301.17ms
step:5064/5100 train_loss:3.4139 train_time:1521984ms step_avg:301.14ms
step:5065/5100 train_loss:3.2707 train_time:1522179ms step_avg:301.12ms
step:5066/5100 train_loss:3.3751 train_time:1522374ms step_avg:301.10ms
step:5067/5100 train_loss:3.5771 train_time:1522569ms step_avg:301.08ms
step:5068/5100 train_loss:3.2293 train_time:1522764ms step_avg:301.06ms
step:5069/5100 train_loss:3.5747 train_time:1522958ms step_avg:301.04ms
step:5070/5100 train_loss:3.2817 train_time:1523153ms step_avg:301.02ms
step:5071/5100 train_loss:3.7025 train_time:1524384ms step_avg:301.20ms
step:5072/5100 train_loss:3.2310 train_time:1524586ms step_avg:301.18ms
step:5073/5100 train_loss:3.2831 train_time:1524782ms step_avg:301.16ms
step:5074/5100 train_loss:3.4254 train_time:1524977ms step_avg:301.14ms
step:5075/5100 train_loss:3.2627 train_time:1525173ms step_avg:301.12ms
step:5076/5100 train_loss:3.2537 train_time:1525369ms step_avg:301.10ms
step:5077/5100 train_loss:3.2243 train_time:1525564ms step_avg:301.08ms
step:5078/5100 train_loss:3.3029 train_time:1525759ms step_avg:301.06ms
step:5079/5100 train_loss:3.4370 train_time:1525955ms step_avg:301.04ms
step:5080/5100 train_loss:3.4071 train_time:1526151ms step_avg:301.02ms
step:5081/5100 train_loss:3.2331 train_time:1527384ms step_avg:301.20ms
step:5082/5100 train_loss:3.3588 train_time:1527584ms step_avg:301.18ms
step:5083/5100 train_loss:3.2199 train_time:1527778ms step_avg:301.16ms
step:5084/5100 train_loss:3.3084 train_time:1527975ms step_avg:301.14ms
step:5085/5100 train_loss:3.1923 train_time:1528171ms step_avg:301.12ms
step:5086/5100 train_loss:4.0512 train_time:1528366ms step_avg:301.10ms
step:5087/5100 train_loss:3.3311 train_time:1528560ms step_avg:301.08ms
step:5088/5100 train_loss:3.2495 train_time:1528755ms step_avg:301.05ms
step:5089/5100 train_loss:3.2573 train_time:1528952ms step_avg:301.03ms
step:5090/5100 train_loss:3.3928 train_time:1529148ms step_avg:301.01ms
step:5091/5100 train_loss:3.3131 train_time:1530378ms step_avg:301.20ms
step:5092/5100 train_loss:3.2128 train_time:1530580ms step_avg:301.18ms
step:5093/5100 train_loss:3.2381 train_time:1530776ms step_avg:301.16ms
step:5094/5100 train_loss:3.2335 train_time:1530972ms step_avg:301.14ms
step:5095/5100 train_loss:3.1563 train_time:1531166ms step_avg:301.11ms
step:5096/5100 train_loss:3.2751 train_time:1531361ms step_avg:301.09ms
step:5097/5100 train_loss:3.0626 train_time:1531557ms step_avg:301.07ms
step:5098/5100 train_loss:3.3615 train_time:1531753ms step_avg:301.05ms
step:5099/5100 train_loss:3.2183 train_time:1531949ms step_avg:301.03ms
step:5100/5100 train_loss:3.2656 train_time:1532145ms step_avg:301.01ms
step:5100/5100 val_loss:3.2752 train_time:1532177ms step_avg:301.02ms