====================================================================================================
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)
optimizer2 = torch.optim.AdamW(raw_model.transformer.h.parameters(), lr=0.5*args.embed_learning_rate, betas=(0.9, 0.95),
                               weight_decay=args.weight_decay, fused=True)
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 10:47:10 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   39C    P0             116W / 700W |   4855MiB / 81559MiB |      7%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   1  NVIDIA H100 80GB HBM3          Off | 00000000:06:00.0 Off |                  Off |
| N/A   43C    P0             121W / 700W |   4903MiB / 81559MiB |      6%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   2  NVIDIA H100 80GB HBM3          Off | 00000000:65:00.0 Off |                  Off |
| N/A   44C    P0             122W / 700W |   4903MiB / 81559MiB |      3%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   3  NVIDIA H100 80GB HBM3          Off | 00000000:68:00.0 Off |                  Off |
| N/A   38C    P0             121W / 700W |   4903MiB / 81559MiB |      3%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   4  NVIDIA H100 80GB HBM3          Off | 00000000:85:00.0 Off |                  Off |
| N/A   37C    P0             114W / 700W |   4903MiB / 81559MiB |      8%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   5  NVIDIA H100 80GB HBM3          Off | 00000000:86:00.0 Off |                  Off |
| N/A   44C    P0             124W / 700W |   4903MiB / 81559MiB |      2%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   6  NVIDIA H100 80GB HBM3          Off | 00000000:E5:00.0 Off |                  Off |
| N/A   44C    P0             127W / 700W |   4903MiB / 81559MiB |     10%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   7  NVIDIA H100 80GB HBM3          Off | 00000000:E8:00.0 Off |                  Off |
| N/A   39C    P0             117W / 700W |   4663MiB / 81559MiB |     11%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

====================================================================================================
step:0/5100 val_loss:15.9936 train_time:227ms step_avg:nanms
step:1/5100 train_loss:15.9929 train_time:1368ms step_avg:nanms
step:2/5100 train_loss:9.8606 train_time:1429ms step_avg:nanms
step:3/5100 train_loss:9.6651 train_time:1560ms step_avg:nanms
step:4/5100 train_loss:9.6275 train_time:1694ms step_avg:nanms
step:5/5100 train_loss:9.5568 train_time:1828ms step_avg:nanms
step:6/5100 train_loss:9.5333 train_time:1966ms step_avg:nanms
step:7/5100 train_loss:9.4081 train_time:2101ms step_avg:nanms
step:8/5100 train_loss:9.3789 train_time:2234ms step_avg:nanms
step:9/5100 train_loss:9.3127 train_time:2385ms step_avg:nanms
step:10/5100 train_loss:9.1975 train_time:2527ms step_avg:nanms
step:11/5100 train_loss:9.0875 train_time:65ms step_avg:nanms
step:12/5100 train_loss:8.9719 train_time:200ms step_avg:nanms
step:13/5100 train_loss:8.7851 train_time:336ms step_avg:112.12ms
step:14/5100 train_loss:8.6973 train_time:473ms step_avg:118.22ms
step:15/5100 train_loss:8.5644 train_time:606ms step_avg:121.22ms
step:16/5100 train_loss:8.4258 train_time:748ms step_avg:124.59ms
step:17/5100 train_loss:8.3425 train_time:888ms step_avg:126.83ms
step:18/5100 train_loss:8.2044 train_time:1024ms step_avg:128.03ms
step:19/5100 train_loss:8.0551 train_time:1160ms step_avg:128.91ms
step:20/5100 train_loss:7.9883 train_time:1297ms step_avg:129.65ms
step:21/5100 train_loss:7.6848 train_time:1433ms step_avg:130.26ms
step:22/5100 train_loss:7.8654 train_time:1569ms step_avg:130.79ms
step:23/5100 train_loss:7.9692 train_time:1704ms step_avg:131.09ms
step:24/5100 train_loss:7.6887 train_time:1844ms step_avg:131.72ms
step:25/5100 train_loss:7.7231 train_time:1981ms step_avg:132.10ms
step:26/5100 train_loss:7.5356 train_time:2121ms step_avg:132.53ms
step:27/5100 train_loss:7.4321 train_time:2257ms step_avg:132.75ms
step:28/5100 train_loss:7.5281 train_time:2393ms step_avg:132.93ms
step:29/5100 train_loss:7.2821 train_time:2527ms step_avg:132.98ms
step:30/5100 train_loss:7.4825 train_time:2665ms step_avg:133.23ms
step:31/5100 train_loss:7.4085 train_time:2803ms step_avg:133.46ms
step:32/5100 train_loss:7.3238 train_time:2939ms step_avg:133.61ms
step:33/5100 train_loss:7.1671 train_time:3077ms step_avg:133.79ms
step:34/5100 train_loss:7.5215 train_time:3216ms step_avg:134.00ms
step:35/5100 train_loss:7.3098 train_time:3354ms step_avg:134.15ms
step:36/5100 train_loss:7.5228 train_time:3490ms step_avg:134.23ms
step:37/5100 train_loss:7.4310 train_time:3626ms step_avg:134.28ms
step:38/5100 train_loss:7.2857 train_time:3763ms step_avg:134.39ms
step:39/5100 train_loss:7.1573 train_time:3901ms step_avg:134.53ms
step:40/5100 train_loss:7.2549 train_time:4041ms step_avg:134.68ms
step:41/5100 train_loss:7.1024 train_time:4179ms step_avg:134.79ms
step:42/5100 train_loss:7.1575 train_time:4316ms step_avg:134.87ms
step:43/5100 train_loss:6.9403 train_time:4455ms step_avg:135.00ms
step:44/5100 train_loss:7.0514 train_time:4592ms step_avg:135.07ms
step:45/5100 train_loss:7.0132 train_time:4726ms step_avg:135.04ms
step:46/5100 train_loss:7.2142 train_time:4864ms step_avg:135.10ms
step:47/5100 train_loss:7.0113 train_time:5005ms step_avg:135.26ms
step:48/5100 train_loss:6.8627 train_time:5143ms step_avg:135.35ms
step:49/5100 train_loss:7.0713 train_time:5283ms step_avg:135.45ms
step:50/5100 train_loss:6.9168 train_time:5422ms step_avg:135.54ms
step:51/5100 train_loss:7.0538 train_time:5557ms step_avg:135.53ms
step:52/5100 train_loss:6.9098 train_time:5695ms step_avg:135.59ms
step:53/5100 train_loss:6.7173 train_time:5834ms step_avg:135.67ms
step:54/5100 train_loss:6.8447 train_time:5971ms step_avg:135.69ms
step:55/5100 train_loss:6.7647 train_time:6107ms step_avg:135.72ms
step:56/5100 train_loss:7.0354 train_time:6245ms step_avg:135.75ms
step:57/5100 train_loss:6.7191 train_time:6383ms step_avg:135.81ms
step:58/5100 train_loss:6.6101 train_time:6522ms step_avg:135.87ms
step:59/5100 train_loss:6.7928 train_time:6659ms step_avg:135.90ms
step:60/5100 train_loss:6.6689 train_time:6798ms step_avg:135.95ms
step:61/5100 train_loss:6.7890 train_time:6935ms step_avg:135.99ms
step:62/5100 train_loss:6.5882 train_time:7073ms step_avg:136.01ms
step:63/5100 train_loss:6.6336 train_time:7209ms step_avg:136.02ms
step:64/5100 train_loss:6.5830 train_time:7347ms step_avg:136.06ms
step:65/5100 train_loss:7.2640 train_time:7484ms step_avg:136.07ms
step:66/5100 train_loss:6.4143 train_time:7623ms step_avg:136.12ms
step:67/5100 train_loss:6.5635 train_time:7760ms step_avg:136.15ms
step:68/5100 train_loss:6.4520 train_time:7899ms step_avg:136.19ms
step:69/5100 train_loss:6.7895 train_time:8037ms step_avg:136.22ms
step:70/5100 train_loss:6.3459 train_time:8174ms step_avg:136.23ms
step:71/5100 train_loss:6.4210 train_time:8312ms step_avg:136.26ms
step:72/5100 train_loss:6.6308 train_time:8448ms step_avg:136.25ms
step:73/5100 train_loss:6.5465 train_time:8585ms step_avg:136.27ms
step:74/5100 train_loss:6.4194 train_time:8724ms step_avg:136.31ms
step:75/5100 train_loss:6.5079 train_time:8863ms step_avg:136.35ms
step:76/5100 train_loss:6.5437 train_time:9001ms step_avg:136.38ms
step:77/5100 train_loss:6.4774 train_time:9139ms step_avg:136.41ms
step:78/5100 train_loss:6.5143 train_time:9276ms step_avg:136.41ms
step:79/5100 train_loss:6.6251 train_time:9412ms step_avg:136.41ms
step:80/5100 train_loss:6.4665 train_time:9550ms step_avg:136.43ms
step:81/5100 train_loss:6.5188 train_time:9685ms step_avg:136.41ms
step:82/5100 train_loss:6.2278 train_time:9823ms step_avg:136.42ms
step:83/5100 train_loss:6.4555 train_time:9960ms step_avg:136.44ms
step:84/5100 train_loss:6.4328 train_time:10096ms step_avg:136.44ms
step:85/5100 train_loss:6.2778 train_time:10238ms step_avg:136.50ms
step:86/5100 train_loss:6.1739 train_time:10373ms step_avg:136.49ms
step:87/5100 train_loss:6.3760 train_time:10512ms step_avg:136.52ms
step:88/5100 train_loss:6.2810 train_time:10647ms step_avg:136.50ms
step:89/5100 train_loss:6.4664 train_time:10785ms step_avg:136.51ms
step:90/5100 train_loss:6.4178 train_time:10923ms step_avg:136.54ms
step:91/5100 train_loss:6.2953 train_time:11061ms step_avg:136.55ms
step:92/5100 train_loss:6.2631 train_time:11198ms step_avg:136.57ms
step:93/5100 train_loss:6.4045 train_time:11336ms step_avg:136.58ms
step:94/5100 train_loss:6.2567 train_time:11476ms step_avg:136.62ms
step:95/5100 train_loss:6.2569 train_time:11612ms step_avg:136.61ms
step:96/5100 train_loss:6.2125 train_time:11746ms step_avg:136.58ms
step:97/5100 train_loss:6.0950 train_time:11885ms step_avg:136.61ms
step:98/5100 train_loss:6.1941 train_time:12024ms step_avg:136.63ms
step:99/5100 train_loss:6.0604 train_time:12162ms step_avg:136.65ms
step:100/5100 train_loss:6.2433 train_time:12300ms step_avg:136.66ms
step:101/5100 train_loss:6.1717 train_time:12437ms step_avg:136.67ms
step:102/5100 train_loss:6.0743 train_time:12575ms step_avg:136.69ms
step:103/5100 train_loss:6.1781 train_time:12714ms step_avg:136.71ms
step:104/5100 train_loss:6.2318 train_time:12851ms step_avg:136.72ms
step:105/5100 train_loss:5.9811 train_time:12987ms step_avg:136.71ms
step:106/5100 train_loss:6.1753 train_time:13126ms step_avg:136.73ms
step:107/5100 train_loss:6.4377 train_time:13264ms step_avg:136.74ms
step:108/5100 train_loss:6.1063 train_time:13402ms step_avg:136.75ms
step:109/5100 train_loss:5.8265 train_time:13539ms step_avg:136.76ms
step:110/5100 train_loss:6.1293 train_time:13678ms step_avg:136.78ms
step:111/5100 train_loss:6.0444 train_time:13814ms step_avg:136.78ms
step:112/5100 train_loss:6.0454 train_time:13951ms step_avg:136.78ms
step:113/5100 train_loss:6.0741 train_time:14087ms step_avg:136.76ms
step:114/5100 train_loss:6.0257 train_time:14222ms step_avg:136.75ms
step:115/5100 train_loss:5.8467 train_time:14360ms step_avg:136.76ms
step:116/5100 train_loss:6.0559 train_time:14498ms step_avg:136.77ms
step:117/5100 train_loss:5.8305 train_time:14636ms step_avg:136.79ms
step:118/5100 train_loss:5.8666 train_time:14771ms step_avg:136.77ms
step:119/5100 train_loss:5.9469 train_time:14910ms step_avg:136.78ms
step:120/5100 train_loss:6.0926 train_time:15045ms step_avg:136.77ms
step:121/5100 train_loss:5.9656 train_time:15182ms step_avg:136.78ms
step:122/5100 train_loss:5.8397 train_time:15320ms step_avg:136.79ms
step:123/5100 train_loss:5.9012 train_time:15459ms step_avg:136.81ms
step:124/5100 train_loss:5.8125 train_time:15597ms step_avg:136.81ms
step:125/5100 train_loss:6.1234 train_time:15736ms step_avg:136.84ms
step:125/5100 val_loss:5.9598 train_time:15807ms step_avg:137.46ms
step:126/5100 train_loss:5.9287 train_time:15879ms step_avg:136.89ms
step:127/5100 train_loss:5.9318 train_time:16023ms step_avg:136.95ms
step:128/5100 train_loss:5.9773 train_time:16160ms step_avg:136.95ms
step:129/5100 train_loss:5.8064 train_time:16297ms step_avg:136.95ms
step:130/5100 train_loss:6.0525 train_time:16431ms step_avg:136.93ms
step:131/5100 train_loss:5.8687 train_time:16565ms step_avg:136.90ms
step:132/5100 train_loss:5.9046 train_time:16700ms step_avg:136.88ms
step:133/5100 train_loss:5.7931 train_time:16838ms step_avg:136.90ms
step:134/5100 train_loss:5.8235 train_time:16979ms step_avg:136.93ms
step:135/5100 train_loss:5.8042 train_time:17119ms step_avg:136.95ms
step:136/5100 train_loss:5.8123 train_time:17255ms step_avg:136.95ms
step:137/5100 train_loss:5.6282 train_time:17391ms step_avg:136.94ms
step:138/5100 train_loss:5.7442 train_time:17526ms step_avg:136.92ms
step:139/5100 train_loss:5.7394 train_time:17662ms step_avg:136.91ms
step:140/5100 train_loss:5.7467 train_time:17799ms step_avg:136.92ms
step:141/5100 train_loss:5.7048 train_time:17939ms step_avg:136.94ms
step:142/5100 train_loss:5.6506 train_time:18076ms step_avg:136.94ms
step:143/5100 train_loss:5.7439 train_time:18214ms step_avg:136.95ms
step:144/5100 train_loss:5.5066 train_time:18349ms step_avg:136.93ms
step:145/5100 train_loss:5.7210 train_time:18486ms step_avg:136.93ms
step:146/5100 train_loss:5.6769 train_time:18623ms step_avg:136.93ms
step:147/5100 train_loss:5.6517 train_time:18759ms step_avg:136.93ms
step:148/5100 train_loss:5.6963 train_time:18895ms step_avg:136.92ms
step:149/5100 train_loss:5.6731 train_time:19035ms step_avg:136.94ms
step:150/5100 train_loss:5.8195 train_time:19172ms step_avg:136.95ms
step:151/5100 train_loss:5.8181 train_time:19308ms step_avg:136.93ms
step:152/5100 train_loss:5.7005 train_time:19444ms step_avg:136.93ms
step:153/5100 train_loss:5.6547 train_time:19581ms step_avg:136.93ms
step:154/5100 train_loss:5.6988 train_time:19719ms step_avg:136.94ms
step:155/5100 train_loss:5.6445 train_time:19852ms step_avg:136.91ms
step:156/5100 train_loss:5.6454 train_time:19991ms step_avg:136.93ms
step:157/5100 train_loss:5.6260 train_time:20127ms step_avg:136.92ms
step:158/5100 train_loss:5.7543 train_time:20265ms step_avg:136.93ms
step:159/5100 train_loss:5.5136 train_time:20401ms step_avg:136.92ms
step:160/5100 train_loss:5.5833 train_time:20537ms step_avg:136.92ms
step:161/5100 train_loss:5.4597 train_time:20676ms step_avg:136.93ms
step:162/5100 train_loss:5.5506 train_time:20812ms step_avg:136.92ms
step:163/5100 train_loss:5.6304 train_time:20948ms step_avg:136.92ms
step:164/5100 train_loss:5.6346 train_time:21085ms step_avg:136.92ms
step:165/5100 train_loss:5.4714 train_time:21223ms step_avg:136.92ms
step:166/5100 train_loss:5.5617 train_time:21360ms step_avg:136.92ms
step:167/5100 train_loss:5.7661 train_time:21496ms step_avg:136.92ms
step:168/5100 train_loss:5.4976 train_time:21632ms step_avg:136.91ms
step:169/5100 train_loss:5.5395 train_time:21769ms step_avg:136.91ms
step:170/5100 train_loss:5.4598 train_time:21905ms step_avg:136.91ms
step:171/5100 train_loss:5.4484 train_time:22042ms step_avg:136.91ms
step:172/5100 train_loss:5.4604 train_time:22179ms step_avg:136.91ms
step:173/5100 train_loss:5.4265 train_time:22319ms step_avg:136.92ms
step:174/5100 train_loss:5.5094 train_time:22456ms step_avg:136.93ms
step:175/5100 train_loss:5.6278 train_time:22590ms step_avg:136.91ms
step:176/5100 train_loss:5.5357 train_time:22725ms step_avg:136.90ms
step:177/5100 train_loss:5.3895 train_time:22865ms step_avg:136.92ms
step:178/5100 train_loss:5.3665 train_time:22999ms step_avg:136.90ms
step:179/5100 train_loss:5.3710 train_time:23136ms step_avg:136.90ms
step:180/5100 train_loss:5.4385 train_time:23278ms step_avg:136.93ms
step:181/5100 train_loss:5.4020 train_time:23413ms step_avg:136.92ms
step:182/5100 train_loss:5.4946 train_time:23548ms step_avg:136.90ms
step:183/5100 train_loss:5.4006 train_time:23685ms step_avg:136.91ms
step:184/5100 train_loss:5.3288 train_time:23824ms step_avg:136.92ms
step:185/5100 train_loss:5.3233 train_time:23961ms step_avg:136.92ms
step:186/5100 train_loss:5.4928 train_time:24099ms step_avg:136.93ms
step:187/5100 train_loss:5.3552 train_time:24239ms step_avg:136.95ms
step:188/5100 train_loss:5.6427 train_time:24376ms step_avg:136.94ms
step:189/5100 train_loss:5.3951 train_time:24598ms step_avg:137.42ms
step:190/5100 train_loss:5.3201 train_time:24887ms step_avg:138.26ms
step:191/5100 train_loss:5.4923 train_time:25018ms step_avg:138.22ms
step:192/5100 train_loss:5.3036 train_time:25152ms step_avg:138.20ms
step:193/5100 train_loss:5.2344 train_time:25292ms step_avg:138.21ms
step:194/5100 train_loss:5.4118 train_time:25427ms step_avg:138.19ms
step:195/5100 train_loss:5.3504 train_time:25565ms step_avg:138.19ms
step:196/5100 train_loss:5.5667 train_time:25703ms step_avg:138.19ms
step:197/5100 train_loss:5.4415 train_time:25838ms step_avg:138.17ms
step:198/5100 train_loss:5.2933 train_time:25983ms step_avg:138.21ms
step:199/5100 train_loss:5.3074 train_time:26122ms step_avg:138.21ms
step:200/5100 train_loss:5.2223 train_time:26258ms step_avg:138.20ms
step:201/5100 train_loss:5.3096 train_time:26393ms step_avg:138.18ms
step:202/5100 train_loss:5.2673 train_time:26527ms step_avg:138.16ms
step:203/5100 train_loss:5.4420 train_time:26663ms step_avg:138.15ms
step:204/5100 train_loss:5.3553 train_time:26799ms step_avg:138.14ms
step:205/5100 train_loss:5.2945 train_time:26939ms step_avg:138.15ms
step:206/5100 train_loss:5.4981 train_time:27080ms step_avg:138.16ms
step:207/5100 train_loss:5.1532 train_time:27216ms step_avg:138.15ms
step:208/5100 train_loss:5.2763 train_time:27352ms step_avg:138.14ms
step:209/5100 train_loss:5.2368 train_time:27486ms step_avg:138.12ms
step:210/5100 train_loss:5.3863 train_time:27622ms step_avg:138.11ms
step:211/5100 train_loss:5.2599 train_time:27759ms step_avg:138.10ms
step:212/5100 train_loss:5.1796 train_time:27897ms step_avg:138.11ms
step:213/5100 train_loss:5.3869 train_time:28037ms step_avg:138.11ms
step:214/5100 train_loss:5.1324 train_time:28176ms step_avg:138.12ms
step:215/5100 train_loss:5.2377 train_time:28311ms step_avg:138.10ms
step:216/5100 train_loss:5.0882 train_time:28446ms step_avg:138.09ms
step:217/5100 train_loss:5.2403 train_time:28584ms step_avg:138.09ms
step:218/5100 train_loss:5.1851 train_time:28721ms step_avg:138.08ms
step:219/5100 train_loss:5.1287 train_time:28859ms step_avg:138.08ms
step:220/5100 train_loss:5.1615 train_time:28996ms step_avg:138.08ms
step:221/5100 train_loss:5.1600 train_time:29135ms step_avg:138.08ms
step:222/5100 train_loss:5.2320 train_time:29275ms step_avg:138.09ms
step:223/5100 train_loss:5.2016 train_time:29409ms step_avg:138.07ms
step:224/5100 train_loss:5.1778 train_time:29546ms step_avg:138.07ms
step:225/5100 train_loss:5.2770 train_time:29685ms step_avg:138.07ms
step:226/5100 train_loss:5.0151 train_time:29821ms step_avg:138.06ms
step:227/5100 train_loss:5.0538 train_time:29958ms step_avg:138.06ms
step:228/5100 train_loss:5.0501 train_time:30096ms step_avg:138.06ms
step:229/5100 train_loss:5.2155 train_time:30235ms step_avg:138.06ms
step:230/5100 train_loss:5.0953 train_time:30370ms step_avg:138.04ms
step:231/5100 train_loss:5.2182 train_time:30506ms step_avg:138.04ms
step:232/5100 train_loss:5.0928 train_time:30640ms step_avg:138.02ms
step:233/5100 train_loss:5.0359 train_time:30780ms step_avg:138.03ms
step:234/5100 train_loss:5.2374 train_time:30916ms step_avg:138.02ms
step:235/5100 train_loss:5.1196 train_time:31055ms step_avg:138.02ms
step:236/5100 train_loss:4.9769 train_time:31195ms step_avg:138.03ms
step:237/5100 train_loss:5.2889 train_time:31327ms step_avg:138.01ms
step:238/5100 train_loss:5.1727 train_time:31466ms step_avg:138.01ms
step:239/5100 train_loss:5.1307 train_time:31603ms step_avg:138.00ms
step:240/5100 train_loss:5.2780 train_time:31741ms step_avg:138.01ms
step:241/5100 train_loss:5.2236 train_time:31878ms step_avg:138.00ms
step:242/5100 train_loss:5.1403 train_time:32017ms step_avg:138.00ms
step:243/5100 train_loss:5.2756 train_time:32155ms step_avg:138.00ms
step:244/5100 train_loss:5.0920 train_time:32289ms step_avg:137.99ms
step:245/5100 train_loss:5.0798 train_time:32424ms step_avg:137.98ms
step:246/5100 train_loss:5.1544 train_time:32562ms step_avg:137.97ms
step:247/5100 train_loss:5.1067 train_time:32699ms step_avg:137.97ms
step:248/5100 train_loss:5.0518 train_time:32835ms step_avg:137.96ms
step:249/5100 train_loss:5.2311 train_time:32972ms step_avg:137.96ms
step:250/5100 train_loss:4.9545 train_time:33110ms step_avg:137.96ms
step:250/5100 val_loss:5.0586 train_time:33178ms step_avg:138.24ms
step:251/5100 train_loss:4.9837 train_time:33251ms step_avg:137.97ms
step:252/5100 train_loss:5.1033 train_time:33394ms step_avg:137.99ms
step:253/5100 train_loss:5.0940 train_time:33532ms step_avg:137.99ms
step:254/5100 train_loss:4.9728 train_time:33670ms step_avg:137.99ms
step:255/5100 train_loss:4.9754 train_time:33804ms step_avg:137.98ms
step:256/5100 train_loss:5.1270 train_time:33938ms step_avg:137.96ms
step:257/5100 train_loss:5.1051 train_time:34074ms step_avg:137.95ms
step:258/5100 train_loss:5.0600 train_time:34210ms step_avg:137.94ms
step:259/5100 train_loss:4.9645 train_time:34352ms step_avg:137.96ms
step:260/5100 train_loss:4.9934 train_time:34489ms step_avg:137.96ms
step:261/5100 train_loss:5.0541 train_time:34629ms step_avg:137.96ms
step:262/5100 train_loss:5.0877 train_time:34764ms step_avg:137.95ms
step:263/5100 train_loss:5.0057 train_time:34899ms step_avg:137.94ms
step:264/5100 train_loss:4.9518 train_time:35034ms step_avg:137.93ms
step:265/5100 train_loss:4.9816 train_time:35171ms step_avg:137.92ms
step:266/5100 train_loss:4.8101 train_time:35308ms step_avg:137.92ms
step:267/5100 train_loss:4.8656 train_time:35447ms step_avg:137.93ms
step:268/5100 train_loss:4.9090 train_time:35587ms step_avg:137.93ms
step:269/5100 train_loss:4.8382 train_time:35723ms step_avg:137.93ms
step:270/5100 train_loss:4.8575 train_time:35860ms step_avg:137.92ms
step:271/5100 train_loss:5.0499 train_time:35995ms step_avg:137.91ms
step:272/5100 train_loss:4.9771 train_time:36129ms step_avg:137.90ms
step:273/5100 train_loss:4.8042 train_time:36267ms step_avg:137.90ms
step:274/5100 train_loss:4.8584 train_time:36405ms step_avg:137.90ms
step:275/5100 train_loss:4.9774 train_time:36544ms step_avg:137.90ms
step:276/5100 train_loss:4.9642 train_time:36681ms step_avg:137.90ms
step:277/5100 train_loss:5.1531 train_time:36819ms step_avg:137.90ms
step:278/5100 train_loss:4.9044 train_time:36954ms step_avg:137.89ms
step:279/5100 train_loss:5.0267 train_time:37091ms step_avg:137.88ms
step:280/5100 train_loss:4.8585 train_time:37228ms step_avg:137.88ms
step:281/5100 train_loss:4.8959 train_time:37367ms step_avg:137.89ms
step:282/5100 train_loss:4.8397 train_time:37504ms step_avg:137.88ms
step:283/5100 train_loss:4.9438 train_time:37644ms step_avg:137.89ms
step:284/5100 train_loss:4.7891 train_time:37782ms step_avg:137.89ms
step:285/5100 train_loss:4.9339 train_time:37920ms step_avg:137.89ms
step:286/5100 train_loss:4.9289 train_time:38054ms step_avg:137.88ms
step:287/5100 train_loss:4.9654 train_time:38192ms step_avg:137.88ms
step:288/5100 train_loss:4.7932 train_time:38331ms step_avg:137.88ms
step:289/5100 train_loss:4.8589 train_time:38469ms step_avg:137.88ms
step:290/5100 train_loss:4.7077 train_time:38605ms step_avg:137.88ms
step:291/5100 train_loss:4.7159 train_time:38744ms step_avg:137.88ms
step:292/5100 train_loss:4.8181 train_time:38882ms step_avg:137.88ms
step:293/5100 train_loss:4.7095 train_time:39018ms step_avg:137.87ms
step:294/5100 train_loss:4.7326 train_time:39154ms step_avg:137.87ms
step:295/5100 train_loss:4.7582 train_time:39289ms step_avg:137.86ms
step:296/5100 train_loss:4.6471 train_time:39428ms step_avg:137.86ms
step:297/5100 train_loss:4.6261 train_time:39566ms step_avg:137.86ms
step:298/5100 train_loss:4.6707 train_time:39707ms step_avg:137.87ms
step:299/5100 train_loss:4.7861 train_time:39842ms step_avg:137.86ms
step:300/5100 train_loss:4.6820 train_time:39980ms step_avg:137.86ms
step:301/5100 train_loss:4.8361 train_time:40115ms step_avg:137.85ms
step:302/5100 train_loss:4.8130 train_time:40252ms step_avg:137.85ms
step:303/5100 train_loss:4.7308 train_time:40389ms step_avg:137.85ms
step:304/5100 train_loss:4.7968 train_time:40526ms step_avg:137.84ms
step:305/5100 train_loss:4.7935 train_time:40664ms step_avg:137.84ms
step:306/5100 train_loss:5.2569 train_time:40802ms step_avg:137.84ms
step:307/5100 train_loss:4.7338 train_time:40939ms step_avg:137.84ms
step:308/5100 train_loss:4.6501 train_time:41076ms step_avg:137.84ms
step:309/5100 train_loss:4.8348 train_time:41209ms step_avg:137.82ms
step:310/5100 train_loss:4.6144 train_time:41346ms step_avg:137.82ms
step:311/5100 train_loss:4.8524 train_time:41483ms step_avg:137.82ms
step:312/5100 train_loss:4.7519 train_time:41620ms step_avg:137.82ms
step:313/5100 train_loss:4.6629 train_time:41756ms step_avg:137.81ms
step:314/5100 train_loss:4.8174 train_time:41890ms step_avg:137.80ms
step:315/5100 train_loss:4.8807 train_time:42027ms step_avg:137.79ms
step:316/5100 train_loss:4.7464 train_time:42163ms step_avg:137.79ms
step:317/5100 train_loss:4.6041 train_time:42301ms step_avg:137.79ms
step:318/5100 train_loss:4.6403 train_time:42437ms step_avg:137.78ms
step:319/5100 train_loss:4.6475 train_time:42572ms step_avg:137.77ms
step:320/5100 train_loss:4.5988 train_time:42709ms step_avg:137.77ms
step:321/5100 train_loss:4.6883 train_time:42845ms step_avg:137.76ms
step:322/5100 train_loss:4.6965 train_time:42981ms step_avg:137.76ms
step:323/5100 train_loss:4.6386 train_time:43119ms step_avg:137.76ms
step:324/5100 train_loss:4.7155 train_time:43256ms step_avg:137.76ms
step:325/5100 train_loss:4.7235 train_time:43392ms step_avg:137.75ms
step:326/5100 train_loss:4.7585 train_time:43529ms step_avg:137.75ms
step:327/5100 train_loss:4.6115 train_time:43666ms step_avg:137.75ms
step:328/5100 train_loss:5.1053 train_time:43804ms step_avg:137.75ms
step:329/5100 train_loss:4.7756 train_time:43940ms step_avg:137.74ms
step:330/5100 train_loss:4.5416 train_time:44079ms step_avg:137.75ms
step:331/5100 train_loss:4.5163 train_time:44214ms step_avg:137.74ms
step:332/5100 train_loss:4.6805 train_time:44350ms step_avg:137.73ms
step:333/5100 train_loss:4.5910 train_time:44486ms step_avg:137.73ms
step:334/5100 train_loss:4.5854 train_time:44625ms step_avg:137.73ms
step:335/5100 train_loss:4.5377 train_time:44763ms step_avg:137.73ms
step:336/5100 train_loss:4.7216 train_time:44900ms step_avg:137.73ms
step:337/5100 train_loss:4.6587 train_time:45037ms step_avg:137.73ms
step:338/5100 train_loss:5.1801 train_time:45172ms step_avg:137.72ms
step:339/5100 train_loss:4.6661 train_time:45308ms step_avg:137.71ms
step:340/5100 train_loss:4.6623 train_time:45447ms step_avg:137.72ms
step:341/5100 train_loss:4.6475 train_time:45583ms step_avg:137.71ms
step:342/5100 train_loss:4.5613 train_time:45721ms step_avg:137.71ms
step:343/5100 train_loss:4.5216 train_time:45858ms step_avg:137.71ms
step:344/5100 train_loss:4.5801 train_time:45993ms step_avg:137.70ms
step:345/5100 train_loss:4.7009 train_time:46129ms step_avg:137.70ms
step:346/5100 train_loss:4.5597 train_time:46266ms step_avg:137.70ms
step:347/5100 train_loss:4.4842 train_time:46403ms step_avg:137.69ms
step:348/5100 train_loss:4.5347 train_time:46540ms step_avg:137.69ms
step:349/5100 train_loss:4.5498 train_time:46676ms step_avg:137.69ms
step:350/5100 train_loss:4.4994 train_time:46811ms step_avg:137.68ms
step:351/5100 train_loss:4.1976 train_time:46948ms step_avg:137.68ms
step:352/5100 train_loss:4.4778 train_time:47084ms step_avg:137.67ms
step:353/5100 train_loss:4.8330 train_time:47222ms step_avg:137.67ms
step:354/5100 train_loss:4.3402 train_time:47360ms step_avg:137.67ms
step:355/5100 train_loss:4.5809 train_time:47495ms step_avg:137.67ms
step:356/5100 train_loss:4.4556 train_time:47630ms step_avg:137.66ms
step:357/5100 train_loss:4.5465 train_time:47767ms step_avg:137.66ms
step:358/5100 train_loss:4.5331 train_time:47904ms step_avg:137.66ms
step:359/5100 train_loss:4.4911 train_time:48042ms step_avg:137.66ms
step:360/5100 train_loss:4.5218 train_time:48183ms step_avg:137.66ms
step:361/5100 train_loss:4.1738 train_time:48319ms step_avg:137.66ms
step:362/5100 train_loss:4.7218 train_time:48454ms step_avg:137.65ms
step:363/5100 train_loss:4.6101 train_time:48590ms step_avg:137.65ms
step:364/5100 train_loss:4.5055 train_time:48727ms step_avg:137.65ms
step:365/5100 train_loss:4.4378 train_time:48866ms step_avg:137.65ms
step:366/5100 train_loss:4.5871 train_time:49004ms step_avg:137.65ms
step:367/5100 train_loss:4.5347 train_time:49139ms step_avg:137.64ms
step:368/5100 train_loss:4.5045 train_time:49278ms step_avg:137.65ms
step:369/5100 train_loss:4.4880 train_time:49413ms step_avg:137.64ms
step:370/5100 train_loss:4.3738 train_time:49551ms step_avg:137.64ms
step:371/5100 train_loss:4.5598 train_time:49687ms step_avg:137.64ms
step:372/5100 train_loss:4.4511 train_time:49825ms step_avg:137.64ms
step:373/5100 train_loss:4.3241 train_time:49963ms step_avg:137.64ms
step:374/5100 train_loss:4.5316 train_time:50102ms step_avg:137.64ms
step:375/5100 train_loss:4.4596 train_time:50241ms step_avg:137.65ms
step:375/5100 val_loss:4.4649 train_time:50312ms step_avg:137.84ms
step:376/5100 train_loss:4.4343 train_time:50385ms step_avg:137.66ms
step:377/5100 train_loss:4.4996 train_time:50527ms step_avg:137.68ms
step:378/5100 train_loss:4.4064 train_time:50748ms step_avg:137.90ms
step:379/5100 train_loss:4.4746 train_time:50877ms step_avg:137.88ms
step:380/5100 train_loss:4.5546 train_time:51174ms step_avg:138.31ms
step:381/5100 train_loss:4.5774 train_time:51303ms step_avg:138.28ms
step:382/5100 train_loss:4.5052 train_time:51443ms step_avg:138.29ms
step:383/5100 train_loss:4.4808 train_time:51577ms step_avg:138.28ms
step:384/5100 train_loss:4.3966 train_time:51711ms step_avg:138.26ms
step:385/5100 train_loss:4.4927 train_time:51852ms step_avg:138.27ms
step:386/5100 train_loss:4.3998 train_time:51988ms step_avg:138.26ms
step:387/5100 train_loss:4.5127 train_time:52124ms step_avg:138.26ms
step:388/5100 train_loss:4.7072 train_time:52264ms step_avg:138.27ms
step:389/5100 train_loss:4.4154 train_time:52401ms step_avg:138.26ms
step:390/5100 train_loss:4.3849 train_time:52536ms step_avg:138.25ms
step:391/5100 train_loss:4.5053 train_time:52672ms step_avg:138.25ms
step:392/5100 train_loss:4.4194 train_time:52809ms step_avg:138.24ms
step:393/5100 train_loss:4.5009 train_time:52942ms step_avg:138.23ms
step:394/5100 train_loss:4.3362 train_time:53080ms step_avg:138.23ms
step:395/5100 train_loss:4.4807 train_time:53218ms step_avg:138.23ms
step:396/5100 train_loss:4.2420 train_time:53354ms step_avg:138.22ms
step:397/5100 train_loss:4.4135 train_time:53491ms step_avg:138.22ms
step:398/5100 train_loss:4.4959 train_time:53630ms step_avg:138.22ms
step:399/5100 train_loss:4.4607 train_time:53767ms step_avg:138.22ms
step:400/5100 train_loss:4.3758 train_time:53904ms step_avg:138.21ms
step:401/5100 train_loss:4.4340 train_time:54040ms step_avg:138.21ms
step:402/5100 train_loss:4.4768 train_time:54180ms step_avg:138.21ms
step:403/5100 train_loss:4.4196 train_time:54318ms step_avg:138.21ms
step:404/5100 train_loss:4.5174 train_time:54454ms step_avg:138.21ms
step:405/5100 train_loss:4.3124 train_time:54592ms step_avg:138.21ms
step:406/5100 train_loss:4.3838 train_time:54731ms step_avg:138.21ms
step:407/5100 train_loss:4.6661 train_time:54868ms step_avg:138.21ms
step:408/5100 train_loss:4.3993 train_time:55003ms step_avg:138.20ms
step:409/5100 train_loss:4.4276 train_time:55140ms step_avg:138.20ms
step:410/5100 train_loss:4.4733 train_time:55279ms step_avg:138.20ms
step:411/5100 train_loss:4.3402 train_time:55408ms step_avg:138.18ms
step:412/5100 train_loss:4.3902 train_time:55550ms step_avg:138.19ms
step:413/5100 train_loss:4.8040 train_time:55688ms step_avg:138.18ms
step:414/5100 train_loss:4.2438 train_time:55829ms step_avg:138.19ms
step:415/5100 train_loss:4.6136 train_time:55965ms step_avg:138.19ms
step:416/5100 train_loss:4.3439 train_time:56100ms step_avg:138.18ms
step:417/5100 train_loss:4.3516 train_time:56237ms step_avg:138.17ms
step:418/5100 train_loss:4.5345 train_time:56374ms step_avg:138.17ms
step:419/5100 train_loss:4.2587 train_time:56512ms step_avg:138.17ms
step:420/5100 train_loss:4.3590 train_time:56649ms step_avg:138.17ms
step:421/5100 train_loss:4.3242 train_time:56785ms step_avg:138.16ms
step:422/5100 train_loss:4.2029 train_time:56920ms step_avg:138.16ms
step:423/5100 train_loss:4.3193 train_time:57056ms step_avg:138.15ms
step:424/5100 train_loss:4.4283 train_time:57194ms step_avg:138.15ms
step:425/5100 train_loss:4.2155 train_time:57331ms step_avg:138.15ms
step:426/5100 train_loss:4.3937 train_time:57469ms step_avg:138.15ms
step:427/5100 train_loss:4.2799 train_time:57606ms step_avg:138.14ms
step:428/5100 train_loss:4.4723 train_time:57745ms step_avg:138.15ms
step:429/5100 train_loss:4.4143 train_time:57879ms step_avg:138.14ms
step:430/5100 train_loss:4.3233 train_time:58016ms step_avg:138.13ms
step:431/5100 train_loss:4.2971 train_time:58152ms step_avg:138.13ms
step:432/5100 train_loss:4.2144 train_time:58288ms step_avg:138.12ms
step:433/5100 train_loss:4.3232 train_time:58427ms step_avg:138.12ms
step:434/5100 train_loss:4.3988 train_time:58562ms step_avg:138.12ms
step:435/5100 train_loss:4.3195 train_time:58699ms step_avg:138.11ms
step:436/5100 train_loss:4.3698 train_time:58835ms step_avg:138.11ms
step:437/5100 train_loss:4.3793 train_time:58974ms step_avg:138.11ms
step:438/5100 train_loss:4.2873 train_time:59108ms step_avg:138.10ms
step:439/5100 train_loss:4.2656 train_time:59245ms step_avg:138.10ms
step:440/5100 train_loss:4.2331 train_time:59381ms step_avg:138.09ms
step:441/5100 train_loss:4.4105 train_time:59516ms step_avg:138.09ms
step:442/5100 train_loss:4.3062 train_time:59653ms step_avg:138.09ms
step:443/5100 train_loss:4.2974 train_time:59790ms step_avg:138.08ms
step:444/5100 train_loss:4.1830 train_time:59929ms step_avg:138.09ms
step:445/5100 train_loss:4.4450 train_time:60067ms step_avg:138.08ms
step:446/5100 train_loss:4.3731 train_time:60204ms step_avg:138.08ms
step:447/5100 train_loss:4.3742 train_time:60340ms step_avg:138.08ms
step:448/5100 train_loss:4.2817 train_time:60477ms step_avg:138.07ms
step:449/5100 train_loss:4.3790 train_time:60614ms step_avg:138.07ms
step:450/5100 train_loss:4.1934 train_time:60752ms step_avg:138.07ms
step:451/5100 train_loss:4.2488 train_time:60890ms step_avg:138.07ms
step:452/5100 train_loss:4.1121 train_time:61027ms step_avg:138.07ms
step:453/5100 train_loss:4.2598 train_time:61163ms step_avg:138.07ms
step:454/5100 train_loss:4.2373 train_time:61297ms step_avg:138.06ms
step:455/5100 train_loss:4.2008 train_time:61435ms step_avg:138.06ms
step:456/5100 train_loss:4.3947 train_time:61572ms step_avg:138.05ms
step:457/5100 train_loss:4.2581 train_time:61709ms step_avg:138.05ms
step:458/5100 train_loss:4.3342 train_time:61846ms step_avg:138.05ms
step:459/5100 train_loss:4.3683 train_time:61983ms step_avg:138.05ms
step:460/5100 train_loss:4.1583 train_time:62117ms step_avg:138.04ms
step:461/5100 train_loss:4.3349 train_time:62253ms step_avg:138.03ms
step:462/5100 train_loss:4.2358 train_time:62392ms step_avg:138.04ms
step:463/5100 train_loss:4.2229 train_time:62530ms step_avg:138.03ms
step:464/5100 train_loss:4.3140 train_time:62667ms step_avg:138.03ms
step:465/5100 train_loss:4.2518 train_time:62802ms step_avg:138.03ms
step:466/5100 train_loss:4.2496 train_time:62937ms step_avg:138.02ms
step:467/5100 train_loss:4.3500 train_time:63074ms step_avg:138.02ms
step:468/5100 train_loss:4.3523 train_time:63212ms step_avg:138.02ms
step:469/5100 train_loss:4.3153 train_time:63351ms step_avg:138.02ms
step:470/5100 train_loss:4.2123 train_time:63489ms step_avg:138.02ms
step:471/5100 train_loss:4.2926 train_time:63625ms step_avg:138.01ms
step:472/5100 train_loss:4.3377 train_time:63759ms step_avg:138.01ms
step:473/5100 train_loss:4.2703 train_time:63896ms step_avg:138.01ms
step:474/5100 train_loss:4.2399 train_time:64033ms step_avg:138.00ms
step:475/5100 train_loss:4.1047 train_time:64170ms step_avg:138.00ms
step:476/5100 train_loss:4.5551 train_time:64310ms step_avg:138.00ms
step:477/5100 train_loss:4.3136 train_time:64447ms step_avg:138.00ms
step:478/5100 train_loss:4.1167 train_time:64581ms step_avg:137.99ms
step:479/5100 train_loss:4.3236 train_time:64717ms step_avg:137.99ms
step:480/5100 train_loss:4.2915 train_time:64855ms step_avg:137.99ms
step:481/5100 train_loss:4.4299 train_time:64992ms step_avg:137.99ms
step:482/5100 train_loss:4.2463 train_time:65130ms step_avg:137.99ms
step:483/5100 train_loss:4.0620 train_time:65269ms step_avg:137.99ms
step:484/5100 train_loss:4.3269 train_time:65407ms step_avg:137.99ms
step:485/5100 train_loss:4.1779 train_time:65543ms step_avg:137.98ms
step:486/5100 train_loss:4.1923 train_time:65679ms step_avg:137.98ms
step:487/5100 train_loss:4.1170 train_time:65816ms step_avg:137.98ms
step:488/5100 train_loss:4.1747 train_time:65953ms step_avg:137.98ms
step:489/5100 train_loss:4.3816 train_time:66092ms step_avg:137.98ms
step:490/5100 train_loss:4.2186 train_time:66230ms step_avg:137.98ms
step:491/5100 train_loss:4.1202 train_time:66369ms step_avg:137.98ms
step:492/5100 train_loss:4.1252 train_time:66507ms step_avg:137.98ms
step:493/5100 train_loss:4.2371 train_time:66642ms step_avg:137.97ms
step:494/5100 train_loss:4.0808 train_time:66778ms step_avg:137.97ms
step:495/5100 train_loss:4.2178 train_time:66913ms step_avg:137.97ms
step:496/5100 train_loss:4.1434 train_time:67052ms step_avg:137.97ms
step:497/5100 train_loss:4.0605 train_time:67189ms step_avg:137.97ms
step:498/5100 train_loss:4.2328 train_time:67328ms step_avg:137.97ms
step:499/5100 train_loss:4.3284 train_time:67465ms step_avg:137.97ms
step:500/5100 train_loss:4.3510 train_time:67600ms step_avg:137.96ms
step:500/5100 val_loss:4.2164 train_time:67670ms step_avg:138.10ms
step:501/5100 train_loss:4.2515 train_time:67743ms step_avg:137.97ms
step:502/5100 train_loss:4.2957 train_time:67890ms step_avg:137.99ms
step:503/5100 train_loss:4.2450 train_time:68025ms step_avg:137.98ms
step:504/5100 train_loss:4.2753 train_time:68159ms step_avg:137.97ms
step:505/5100 train_loss:4.2435 train_time:68294ms step_avg:137.97ms
step:506/5100 train_loss:4.3264 train_time:68430ms step_avg:137.96ms
step:507/5100 train_loss:4.1058 train_time:68563ms step_avg:137.95ms
step:508/5100 train_loss:4.2496 train_time:68698ms step_avg:137.95ms
step:509/5100 train_loss:4.3278 train_time:68838ms step_avg:137.95ms
step:510/5100 train_loss:4.2632 train_time:68979ms step_avg:137.96ms
step:511/5100 train_loss:4.0689 train_time:69116ms step_avg:137.96ms
step:512/5100 train_loss:4.2709 train_time:69253ms step_avg:137.96ms
step:513/5100 train_loss:4.2045 train_time:69389ms step_avg:137.95ms
step:514/5100 train_loss:4.1812 train_time:69523ms step_avg:137.94ms
step:515/5100 train_loss:4.2327 train_time:69657ms step_avg:137.93ms
step:516/5100 train_loss:4.2481 train_time:69796ms step_avg:137.94ms
step:517/5100 train_loss:4.5686 train_time:69934ms step_avg:137.94ms
step:518/5100 train_loss:4.1664 train_time:70072ms step_avg:137.94ms
step:519/5100 train_loss:4.2859 train_time:70211ms step_avg:137.94ms
step:520/5100 train_loss:4.1908 train_time:70348ms step_avg:137.94ms
step:521/5100 train_loss:4.1740 train_time:70483ms step_avg:137.93ms
step:522/5100 train_loss:4.1185 train_time:70618ms step_avg:137.93ms
step:523/5100 train_loss:4.1412 train_time:70756ms step_avg:137.92ms
step:524/5100 train_loss:4.7603 train_time:70894ms step_avg:137.93ms
step:525/5100 train_loss:4.2366 train_time:71032ms step_avg:137.93ms
step:526/5100 train_loss:4.1933 train_time:71171ms step_avg:137.93ms
step:527/5100 train_loss:4.1820 train_time:71309ms step_avg:137.93ms
step:528/5100 train_loss:4.1410 train_time:71447ms step_avg:137.93ms
step:529/5100 train_loss:4.1160 train_time:71581ms step_avg:137.92ms
step:530/5100 train_loss:4.3146 train_time:71717ms step_avg:137.92ms
step:531/5100 train_loss:4.1149 train_time:71854ms step_avg:137.92ms
step:532/5100 train_loss:4.4043 train_time:71992ms step_avg:137.92ms
step:533/5100 train_loss:4.2110 train_time:72132ms step_avg:137.92ms
step:534/5100 train_loss:4.1476 train_time:72271ms step_avg:137.92ms
step:535/5100 train_loss:4.1584 train_time:72409ms step_avg:137.92ms
step:536/5100 train_loss:4.0868 train_time:72546ms step_avg:137.92ms
step:537/5100 train_loss:4.2162 train_time:72680ms step_avg:137.91ms
step:538/5100 train_loss:4.2286 train_time:72817ms step_avg:137.91ms
step:539/5100 train_loss:4.1353 train_time:72955ms step_avg:137.91ms
step:540/5100 train_loss:4.6286 train_time:73093ms step_avg:137.91ms
step:541/5100 train_loss:4.1584 train_time:73232ms step_avg:137.91ms
step:542/5100 train_loss:4.2623 train_time:73370ms step_avg:137.91ms
step:543/5100 train_loss:4.1031 train_time:73507ms step_avg:137.91ms
step:544/5100 train_loss:4.0727 train_time:73641ms step_avg:137.90ms
step:545/5100 train_loss:4.1739 train_time:73782ms step_avg:137.91ms
step:546/5100 train_loss:4.0793 train_time:73915ms step_avg:137.90ms
step:547/5100 train_loss:4.1265 train_time:74055ms step_avg:137.91ms
step:548/5100 train_loss:4.1465 train_time:74192ms step_avg:137.90ms
step:549/5100 train_loss:4.1161 train_time:74328ms step_avg:137.90ms
step:550/5100 train_loss:4.1987 train_time:74464ms step_avg:137.90ms
step:551/5100 train_loss:4.0691 train_time:74598ms step_avg:137.89ms
step:552/5100 train_loss:4.1059 train_time:74733ms step_avg:137.88ms
step:553/5100 train_loss:4.4260 train_time:74873ms step_avg:137.89ms
step:554/5100 train_loss:4.2131 train_time:75012ms step_avg:137.89ms
step:555/5100 train_loss:4.1770 train_time:75147ms step_avg:137.88ms
step:556/5100 train_loss:4.1587 train_time:75284ms step_avg:137.88ms
step:557/5100 train_loss:4.1596 train_time:75419ms step_avg:137.88ms
step:558/5100 train_loss:3.8338 train_time:75556ms step_avg:137.88ms
step:559/5100 train_loss:4.0603 train_time:75694ms step_avg:137.88ms
step:560/5100 train_loss:4.1088 train_time:75830ms step_avg:137.87ms
step:561/5100 train_loss:4.1673 train_time:75969ms step_avg:137.87ms
step:562/5100 train_loss:4.0796 train_time:76107ms step_avg:137.87ms
step:563/5100 train_loss:4.0241 train_time:76243ms step_avg:137.87ms
step:564/5100 train_loss:4.2218 train_time:76378ms step_avg:137.87ms
step:565/5100 train_loss:4.0361 train_time:76515ms step_avg:137.86ms
step:566/5100 train_loss:4.1581 train_time:76653ms step_avg:137.87ms
step:567/5100 train_loss:4.0847 train_time:76924ms step_avg:138.10ms
step:568/5100 train_loss:4.0348 train_time:77054ms step_avg:138.09ms
step:569/5100 train_loss:4.1356 train_time:77192ms step_avg:138.09ms
step:570/5100 train_loss:4.1166 train_time:77491ms step_avg:138.38ms
step:571/5100 train_loss:4.1395 train_time:77621ms step_avg:138.36ms
step:572/5100 train_loss:4.2367 train_time:77760ms step_avg:138.36ms
step:573/5100 train_loss:4.1635 train_time:77894ms step_avg:138.36ms
step:574/5100 train_loss:4.1640 train_time:78029ms step_avg:138.35ms
step:575/5100 train_loss:4.2357 train_time:78169ms step_avg:138.35ms
step:576/5100 train_loss:4.1998 train_time:78303ms step_avg:138.35ms
step:577/5100 train_loss:4.2067 train_time:78438ms step_avg:138.34ms
step:578/5100 train_loss:4.1587 train_time:78583ms step_avg:138.35ms
step:579/5100 train_loss:4.1224 train_time:78720ms step_avg:138.35ms
step:580/5100 train_loss:4.1051 train_time:78857ms step_avg:138.35ms
step:581/5100 train_loss:4.0549 train_time:78996ms step_avg:138.35ms
step:582/5100 train_loss:4.0817 train_time:79130ms step_avg:138.34ms
step:583/5100 train_loss:4.3187 train_time:79266ms step_avg:138.34ms
step:584/5100 train_loss:4.0859 train_time:79399ms step_avg:138.33ms
step:585/5100 train_loss:4.0491 train_time:79538ms step_avg:138.33ms
step:586/5100 train_loss:4.2229 train_time:79677ms step_avg:138.33ms
step:587/5100 train_loss:3.9800 train_time:79814ms step_avg:138.33ms
step:588/5100 train_loss:4.1172 train_time:79951ms step_avg:138.32ms
step:589/5100 train_loss:4.1092 train_time:80088ms step_avg:138.32ms
step:590/5100 train_loss:4.4512 train_time:80223ms step_avg:138.32ms
step:591/5100 train_loss:4.2170 train_time:80357ms step_avg:138.31ms
step:592/5100 train_loss:3.9646 train_time:80495ms step_avg:138.31ms
step:593/5100 train_loss:3.9818 train_time:80635ms step_avg:138.31ms
step:594/5100 train_loss:3.9812 train_time:80773ms step_avg:138.31ms
step:595/5100 train_loss:4.0248 train_time:80911ms step_avg:138.31ms
step:596/5100 train_loss:4.3475 train_time:81049ms step_avg:138.31ms
step:597/5100 train_loss:4.0794 train_time:81187ms step_avg:138.31ms
step:598/5100 train_loss:4.0311 train_time:81321ms step_avg:138.30ms
step:599/5100 train_loss:4.0963 train_time:81458ms step_avg:138.30ms
step:600/5100 train_loss:3.9139 train_time:81594ms step_avg:138.30ms
step:601/5100 train_loss:4.0397 train_time:81733ms step_avg:138.30ms
step:602/5100 train_loss:4.0597 train_time:81870ms step_avg:138.29ms
step:603/5100 train_loss:4.0870 train_time:82007ms step_avg:138.29ms
step:604/5100 train_loss:4.2347 train_time:82143ms step_avg:138.29ms
step:605/5100 train_loss:4.1264 train_time:82279ms step_avg:138.28ms
step:606/5100 train_loss:4.0764 train_time:82416ms step_avg:138.28ms
step:607/5100 train_loss:4.0282 train_time:82554ms step_avg:138.28ms
step:608/5100 train_loss:4.2495 train_time:82692ms step_avg:138.28ms
step:609/5100 train_loss:4.1149 train_time:82830ms step_avg:138.28ms
step:610/5100 train_loss:4.0749 train_time:82968ms step_avg:138.28ms
step:611/5100 train_loss:4.1777 train_time:83104ms step_avg:138.28ms
step:612/5100 train_loss:4.0775 train_time:83239ms step_avg:138.27ms
step:613/5100 train_loss:4.0369 train_time:83376ms step_avg:138.27ms
step:614/5100 train_loss:4.2162 train_time:83512ms step_avg:138.27ms
step:615/5100 train_loss:4.2007 train_time:83650ms step_avg:138.26ms
step:616/5100 train_loss:4.1437 train_time:83789ms step_avg:138.26ms
step:617/5100 train_loss:4.0509 train_time:83925ms step_avg:138.26ms
step:618/5100 train_loss:4.0114 train_time:84065ms step_avg:138.26ms
step:619/5100 train_loss:4.1056 train_time:84197ms step_avg:138.25ms
step:620/5100 train_loss:4.0337 train_time:84333ms step_avg:138.25ms
step:621/5100 train_loss:4.0297 train_time:84471ms step_avg:138.25ms
step:622/5100 train_loss:4.3145 train_time:84609ms step_avg:138.25ms
step:623/5100 train_loss:4.0163 train_time:84747ms step_avg:138.25ms
step:624/5100 train_loss:4.0578 train_time:84883ms step_avg:138.25ms
step:625/5100 train_loss:4.1282 train_time:85020ms step_avg:138.24ms
step:625/5100 val_loss:4.0617 train_time:85090ms step_avg:138.36ms
step:626/5100 train_loss:4.1678 train_time:85161ms step_avg:138.25ms
step:627/5100 train_loss:4.1838 train_time:85310ms step_avg:138.27ms
step:628/5100 train_loss:4.1381 train_time:85448ms step_avg:138.27ms
step:629/5100 train_loss:4.2106 train_time:85584ms step_avg:138.26ms
step:630/5100 train_loss:4.0144 train_time:85719ms step_avg:138.26ms
step:631/5100 train_loss:4.1360 train_time:85851ms step_avg:138.25ms
step:632/5100 train_loss:4.1875 train_time:85986ms step_avg:138.24ms
step:633/5100 train_loss:4.0950 train_time:86121ms step_avg:138.24ms
step:634/5100 train_loss:4.0113 train_time:86264ms step_avg:138.24ms
step:635/5100 train_loss:4.1234 train_time:86403ms step_avg:138.24ms
step:636/5100 train_loss:4.3711 train_time:86541ms step_avg:138.24ms
step:637/5100 train_loss:3.9646 train_time:86678ms step_avg:138.24ms
step:638/5100 train_loss:3.7987 train_time:86813ms step_avg:138.24ms
step:639/5100 train_loss:4.0057 train_time:86947ms step_avg:138.23ms
step:640/5100 train_loss:4.0517 train_time:87083ms step_avg:138.23ms
step:641/5100 train_loss:4.0149 train_time:87223ms step_avg:138.23ms
step:642/5100 train_loss:4.0125 train_time:87363ms step_avg:138.23ms
step:643/5100 train_loss:4.0416 train_time:87502ms step_avg:138.23ms
step:644/5100 train_loss:4.0770 train_time:87639ms step_avg:138.23ms
step:645/5100 train_loss:3.9782 train_time:87776ms step_avg:138.23ms
step:646/5100 train_loss:4.1865 train_time:87911ms step_avg:138.22ms
step:647/5100 train_loss:4.1035 train_time:88047ms step_avg:138.22ms
step:648/5100 train_loss:4.0956 train_time:88185ms step_avg:138.22ms
step:649/5100 train_loss:4.1103 train_time:88323ms step_avg:138.22ms
step:650/5100 train_loss:4.1801 train_time:88462ms step_avg:138.22ms
step:651/5100 train_loss:4.0448 train_time:88600ms step_avg:138.22ms
step:652/5100 train_loss:4.1791 train_time:88737ms step_avg:138.22ms
step:653/5100 train_loss:4.0116 train_time:88873ms step_avg:138.22ms
step:654/5100 train_loss:4.0927 train_time:89009ms step_avg:138.21ms
step:655/5100 train_loss:3.8643 train_time:89145ms step_avg:138.21ms
step:656/5100 train_loss:4.0030 train_time:89282ms step_avg:138.21ms
step:657/5100 train_loss:4.0110 train_time:89420ms step_avg:138.21ms
step:658/5100 train_loss:3.9393 train_time:89559ms step_avg:138.21ms
step:659/5100 train_loss:4.1275 train_time:89698ms step_avg:138.21ms
step:660/5100 train_loss:4.0212 train_time:89836ms step_avg:138.21ms
step:661/5100 train_loss:4.0990 train_time:89971ms step_avg:138.20ms
step:662/5100 train_loss:4.1758 train_time:90107ms step_avg:138.20ms
step:663/5100 train_loss:4.0857 train_time:90243ms step_avg:138.20ms
step:664/5100 train_loss:3.9572 train_time:90381ms step_avg:138.20ms
step:665/5100 train_loss:4.0505 train_time:90519ms step_avg:138.20ms
step:666/5100 train_loss:3.9149 train_time:90657ms step_avg:138.20ms
step:667/5100 train_loss:4.2100 train_time:90794ms step_avg:138.20ms
step:668/5100 train_loss:4.0453 train_time:90931ms step_avg:138.19ms
step:669/5100 train_loss:4.0321 train_time:91067ms step_avg:138.19ms
step:670/5100 train_loss:3.8924 train_time:91204ms step_avg:138.19ms
step:671/5100 train_loss:4.0059 train_time:91342ms step_avg:138.19ms
step:672/5100 train_loss:3.9676 train_time:91480ms step_avg:138.19ms
step:673/5100 train_loss:3.9896 train_time:91619ms step_avg:138.19ms
step:674/5100 train_loss:4.2637 train_time:91756ms step_avg:138.19ms
step:675/5100 train_loss:4.0667 train_time:91890ms step_avg:138.18ms
step:676/5100 train_loss:4.1171 train_time:92026ms step_avg:138.18ms
step:677/5100 train_loss:3.8921 train_time:92163ms step_avg:138.18ms
step:678/5100 train_loss:4.0084 train_time:92301ms step_avg:138.18ms
step:679/5100 train_loss:3.9456 train_time:92438ms step_avg:138.17ms
step:680/5100 train_loss:4.1000 train_time:92577ms step_avg:138.17ms
step:681/5100 train_loss:4.0045 train_time:92714ms step_avg:138.17ms
step:682/5100 train_loss:4.0283 train_time:92849ms step_avg:138.17ms
step:683/5100 train_loss:4.1127 train_time:92986ms step_avg:138.17ms
step:684/5100 train_loss:4.1615 train_time:93123ms step_avg:138.16ms
step:685/5100 train_loss:4.0403 train_time:93260ms step_avg:138.16ms
step:686/5100 train_loss:4.1335 train_time:93397ms step_avg:138.16ms
step:687/5100 train_loss:4.0474 train_time:93533ms step_avg:138.16ms
step:688/5100 train_loss:4.0964 train_time:93669ms step_avg:138.15ms
step:689/5100 train_loss:3.7657 train_time:93806ms step_avg:138.15ms
step:690/5100 train_loss:3.8437 train_time:93943ms step_avg:138.15ms
step:691/5100 train_loss:3.9713 train_time:94080ms step_avg:138.15ms
step:692/5100 train_loss:3.8621 train_time:94217ms step_avg:138.15ms
step:693/5100 train_loss:4.0725 train_time:94355ms step_avg:138.15ms
step:694/5100 train_loss:4.0906 train_time:94491ms step_avg:138.14ms
step:695/5100 train_loss:3.9737 train_time:94628ms step_avg:138.14ms
step:696/5100 train_loss:3.9502 train_time:94765ms step_avg:138.14ms
step:697/5100 train_loss:4.2684 train_time:94904ms step_avg:138.14ms
step:698/5100 train_loss:4.0251 train_time:95040ms step_avg:138.14ms
step:699/5100 train_loss:4.0564 train_time:95178ms step_avg:138.14ms
step:700/5100 train_loss:4.2319 train_time:95311ms step_avg:138.13ms
step:701/5100 train_loss:3.9918 train_time:95448ms step_avg:138.13ms
step:702/5100 train_loss:3.9417 train_time:95584ms step_avg:138.13ms
step:703/5100 train_loss:3.9394 train_time:95722ms step_avg:138.13ms
step:704/5100 train_loss:3.8820 train_time:95860ms step_avg:138.13ms
step:705/5100 train_loss:3.9768 train_time:95999ms step_avg:138.13ms
step:706/5100 train_loss:3.9752 train_time:96138ms step_avg:138.13ms
step:707/5100 train_loss:3.9913 train_time:96279ms step_avg:138.13ms
step:708/5100 train_loss:4.0634 train_time:96415ms step_avg:138.13ms
step:709/5100 train_loss:3.9986 train_time:96549ms step_avg:138.12ms
step:710/5100 train_loss:3.9915 train_time:96687ms step_avg:138.12ms
step:711/5100 train_loss:3.9645 train_time:96823ms step_avg:138.12ms
step:712/5100 train_loss:3.9971 train_time:96962ms step_avg:138.12ms
step:713/5100 train_loss:4.0549 train_time:97100ms step_avg:138.12ms
step:714/5100 train_loss:4.0688 train_time:97237ms step_avg:138.12ms
step:715/5100 train_loss:3.9848 train_time:97374ms step_avg:138.12ms
step:716/5100 train_loss:3.9861 train_time:97512ms step_avg:138.12ms
step:717/5100 train_loss:3.9966 train_time:97648ms step_avg:138.12ms
step:718/5100 train_loss:4.1441 train_time:97786ms step_avg:138.12ms
step:719/5100 train_loss:4.0086 train_time:97923ms step_avg:138.11ms
step:720/5100 train_loss:4.0732 train_time:98060ms step_avg:138.11ms
step:721/5100 train_loss:4.2090 train_time:98198ms step_avg:138.11ms
step:722/5100 train_loss:3.8651 train_time:98335ms step_avg:138.11ms
step:723/5100 train_loss:4.1211 train_time:98471ms step_avg:138.11ms
step:724/5100 train_loss:4.1876 train_time:98606ms step_avg:138.10ms
step:725/5100 train_loss:3.9658 train_time:98742ms step_avg:138.10ms
step:726/5100 train_loss:4.0574 train_time:98880ms step_avg:138.10ms
step:727/5100 train_loss:3.9569 train_time:99017ms step_avg:138.10ms
step:728/5100 train_loss:3.9444 train_time:99154ms step_avg:138.10ms
step:729/5100 train_loss:4.1333 train_time:99290ms step_avg:138.09ms
step:730/5100 train_loss:4.0843 train_time:99427ms step_avg:138.09ms
step:731/5100 train_loss:4.0766 train_time:99564ms step_avg:138.09ms
step:732/5100 train_loss:3.9649 train_time:99701ms step_avg:138.09ms
step:733/5100 train_loss:3.9944 train_time:99838ms step_avg:138.09ms
step:734/5100 train_loss:4.2260 train_time:99976ms step_avg:138.09ms
step:735/5100 train_loss:3.9479 train_time:100111ms step_avg:138.08ms
step:736/5100 train_loss:4.0200 train_time:100245ms step_avg:138.08ms
step:737/5100 train_loss:4.1364 train_time:100384ms step_avg:138.08ms
step:738/5100 train_loss:4.0474 train_time:100522ms step_avg:138.08ms
step:739/5100 train_loss:4.0054 train_time:100658ms step_avg:138.08ms
step:740/5100 train_loss:3.9106 train_time:100795ms step_avg:138.08ms
step:741/5100 train_loss:4.5427 train_time:100932ms step_avg:138.07ms
step:742/5100 train_loss:3.9102 train_time:101067ms step_avg:138.07ms
step:743/5100 train_loss:4.0060 train_time:101204ms step_avg:138.07ms
step:744/5100 train_loss:3.9809 train_time:101342ms step_avg:138.07ms
step:745/5100 train_loss:4.0369 train_time:101481ms step_avg:138.07ms
step:746/5100 train_loss:4.0288 train_time:101618ms step_avg:138.07ms
step:747/5100 train_loss:3.9990 train_time:101758ms step_avg:138.07ms
step:748/5100 train_loss:4.0277 train_time:101890ms step_avg:138.06ms
step:749/5100 train_loss:3.9545 train_time:102027ms step_avg:138.06ms
step:750/5100 train_loss:3.9648 train_time:102165ms step_avg:138.06ms
step:750/5100 val_loss:3.9743 train_time:102236ms step_avg:138.16ms
step:751/5100 train_loss:4.0031 train_time:102307ms step_avg:138.07ms
step:752/5100 train_loss:3.9607 train_time:102452ms step_avg:138.07ms
step:753/5100 train_loss:3.9884 train_time:102588ms step_avg:138.07ms
step:754/5100 train_loss:4.0116 train_time:102725ms step_avg:138.07ms
step:755/5100 train_loss:3.9769 train_time:102860ms step_avg:138.07ms
step:756/5100 train_loss:4.0505 train_time:103085ms step_avg:138.18ms
step:757/5100 train_loss:3.8927 train_time:103215ms step_avg:138.17ms
step:758/5100 train_loss:4.1195 train_time:103349ms step_avg:138.17ms
step:759/5100 train_loss:4.0481 train_time:103484ms step_avg:138.16ms
step:760/5100 train_loss:3.9655 train_time:103777ms step_avg:138.37ms
step:761/5100 train_loss:4.0749 train_time:103912ms step_avg:138.36ms
step:762/5100 train_loss:3.7956 train_time:104046ms step_avg:138.36ms
step:763/5100 train_loss:3.9496 train_time:104180ms step_avg:138.35ms
step:764/5100 train_loss:4.0709 train_time:104321ms step_avg:138.36ms
step:765/5100 train_loss:3.7204 train_time:104456ms step_avg:138.35ms
step:766/5100 train_loss:4.1334 train_time:104589ms step_avg:138.35ms
step:767/5100 train_loss:4.0040 train_time:104724ms step_avg:138.34ms
step:768/5100 train_loss:3.9551 train_time:104868ms step_avg:138.35ms
step:769/5100 train_loss:3.9613 train_time:105006ms step_avg:138.35ms
step:770/5100 train_loss:3.9918 train_time:105143ms step_avg:138.35ms
step:771/5100 train_loss:4.0556 train_time:105278ms step_avg:138.34ms
step:772/5100 train_loss:4.2775 train_time:105415ms step_avg:138.34ms
step:773/5100 train_loss:3.8467 train_time:105549ms step_avg:138.33ms
step:774/5100 train_loss:4.0554 train_time:105683ms step_avg:138.33ms
step:775/5100 train_loss:4.0298 train_time:105824ms step_avg:138.33ms
step:776/5100 train_loss:3.9936 train_time:105963ms step_avg:138.33ms
step:777/5100 train_loss:3.8026 train_time:106101ms step_avg:138.33ms
step:778/5100 train_loss:3.7946 train_time:106238ms step_avg:138.33ms
step:779/5100 train_loss:3.8682 train_time:106374ms step_avg:138.33ms
step:780/5100 train_loss:3.9499 train_time:106510ms step_avg:138.32ms
step:781/5100 train_loss:3.9890 train_time:106644ms step_avg:138.32ms
step:782/5100 train_loss:4.0378 train_time:106781ms step_avg:138.32ms
step:783/5100 train_loss:3.9456 train_time:106920ms step_avg:138.32ms
step:784/5100 train_loss:3.9601 train_time:107059ms step_avg:138.32ms
step:785/5100 train_loss:3.9458 train_time:107197ms step_avg:138.32ms
step:786/5100 train_loss:3.9339 train_time:107334ms step_avg:138.32ms
step:787/5100 train_loss:3.8459 train_time:107468ms step_avg:138.31ms
step:788/5100 train_loss:4.1303 train_time:107605ms step_avg:138.31ms
step:789/5100 train_loss:3.8808 train_time:107742ms step_avg:138.31ms
step:790/5100 train_loss:3.9502 train_time:107881ms step_avg:138.31ms
step:791/5100 train_loss:4.0150 train_time:108017ms step_avg:138.31ms
step:792/5100 train_loss:4.1529 train_time:108153ms step_avg:138.30ms
step:793/5100 train_loss:4.1689 train_time:108286ms step_avg:138.30ms
step:794/5100 train_loss:3.8996 train_time:108424ms step_avg:138.30ms
step:795/5100 train_loss:3.9908 train_time:108559ms step_avg:138.29ms
step:796/5100 train_loss:4.0384 train_time:108697ms step_avg:138.29ms
step:797/5100 train_loss:4.1341 train_time:108835ms step_avg:138.29ms
step:798/5100 train_loss:3.8973 train_time:108971ms step_avg:138.29ms
step:799/5100 train_loss:4.0456 train_time:109110ms step_avg:138.29ms
step:800/5100 train_loss:3.9554 train_time:109244ms step_avg:138.28ms
step:801/5100 train_loss:3.9620 train_time:109382ms step_avg:138.28ms
step:802/5100 train_loss:4.0491 train_time:109518ms step_avg:138.28ms
step:803/5100 train_loss:3.8952 train_time:109653ms step_avg:138.28ms
step:804/5100 train_loss:3.9485 train_time:109790ms step_avg:138.27ms
step:805/5100 train_loss:4.0410 train_time:109925ms step_avg:138.27ms
step:806/5100 train_loss:3.9260 train_time:110067ms step_avg:138.27ms
step:807/5100 train_loss:3.9287 train_time:110205ms step_avg:138.27ms
step:808/5100 train_loss:4.0359 train_time:110342ms step_avg:138.27ms
step:809/5100 train_loss:3.9511 train_time:110480ms step_avg:138.27ms
step:810/5100 train_loss:3.8713 train_time:110618ms step_avg:138.27ms
step:811/5100 train_loss:3.9661 train_time:110755ms step_avg:138.27ms
step:812/5100 train_loss:4.0007 train_time:110891ms step_avg:138.27ms
step:813/5100 train_loss:3.9839 train_time:111028ms step_avg:138.27ms
step:814/5100 train_loss:4.0250 train_time:111165ms step_avg:138.26ms
step:815/5100 train_loss:3.9720 train_time:111304ms step_avg:138.27ms
step:816/5100 train_loss:3.9555 train_time:111441ms step_avg:138.26ms
step:817/5100 train_loss:4.0379 train_time:111579ms step_avg:138.26ms
step:818/5100 train_loss:4.1375 train_time:111715ms step_avg:138.26ms
step:819/5100 train_loss:3.9189 train_time:111851ms step_avg:138.26ms
step:820/5100 train_loss:4.1149 train_time:111984ms step_avg:138.25ms
step:821/5100 train_loss:3.8894 train_time:112123ms step_avg:138.25ms
step:822/5100 train_loss:3.9224 train_time:112261ms step_avg:138.25ms
step:823/5100 train_loss:4.0321 train_time:112400ms step_avg:138.25ms
step:824/5100 train_loss:3.9596 train_time:112535ms step_avg:138.25ms
step:825/5100 train_loss:3.8913 train_time:112672ms step_avg:138.25ms
step:826/5100 train_loss:3.9800 train_time:112809ms step_avg:138.25ms
step:827/5100 train_loss:3.8901 train_time:112944ms step_avg:138.24ms
step:828/5100 train_loss:4.1093 train_time:113082ms step_avg:138.24ms
step:829/5100 train_loss:4.0065 train_time:113221ms step_avg:138.24ms
step:830/5100 train_loss:4.0733 train_time:113359ms step_avg:138.24ms
step:831/5100 train_loss:3.8983 train_time:113495ms step_avg:138.24ms
step:832/5100 train_loss:3.9583 train_time:113632ms step_avg:138.24ms
step:833/5100 train_loss:3.8951 train_time:113769ms step_avg:138.24ms
step:834/5100 train_loss:4.0110 train_time:113906ms step_avg:138.24ms
step:835/5100 train_loss:3.8868 train_time:114042ms step_avg:138.23ms
step:836/5100 train_loss:3.8408 train_time:114180ms step_avg:138.23ms
step:837/5100 train_loss:4.1197 train_time:114318ms step_avg:138.23ms
step:838/5100 train_loss:3.8095 train_time:114454ms step_avg:138.23ms
step:839/5100 train_loss:3.9685 train_time:114587ms step_avg:138.22ms
step:840/5100 train_loss:3.8121 train_time:114724ms step_avg:138.22ms
step:841/5100 train_loss:3.8550 train_time:114863ms step_avg:138.22ms
step:842/5100 train_loss:3.9392 train_time:114999ms step_avg:138.22ms
step:843/5100 train_loss:3.9575 train_time:115136ms step_avg:138.22ms
step:844/5100 train_loss:3.9553 train_time:115272ms step_avg:138.22ms
step:845/5100 train_loss:3.8072 train_time:115408ms step_avg:138.21ms
step:846/5100 train_loss:4.0371 train_time:115544ms step_avg:138.21ms
step:847/5100 train_loss:3.8994 train_time:115682ms step_avg:138.21ms
step:848/5100 train_loss:3.8671 train_time:115819ms step_avg:138.21ms
step:849/5100 train_loss:3.9996 train_time:115957ms step_avg:138.21ms
step:850/5100 train_loss:3.8618 train_time:116092ms step_avg:138.20ms
step:851/5100 train_loss:3.8196 train_time:116229ms step_avg:138.20ms
step:852/5100 train_loss:4.1293 train_time:116367ms step_avg:138.20ms
step:853/5100 train_loss:3.8332 train_time:116504ms step_avg:138.20ms
step:854/5100 train_loss:3.9354 train_time:116641ms step_avg:138.20ms
step:855/5100 train_loss:4.0178 train_time:116779ms step_avg:138.20ms
step:856/5100 train_loss:3.9191 train_time:116917ms step_avg:138.20ms
step:857/5100 train_loss:3.9146 train_time:117053ms step_avg:138.20ms
step:858/5100 train_loss:3.9640 train_time:117187ms step_avg:138.19ms
step:859/5100 train_loss:3.8707 train_time:117325ms step_avg:138.19ms
step:860/5100 train_loss:3.9433 train_time:117460ms step_avg:138.19ms
step:861/5100 train_loss:3.9824 train_time:117597ms step_avg:138.19ms
step:862/5100 train_loss:4.0367 train_time:117735ms step_avg:138.19ms
step:863/5100 train_loss:3.9591 train_time:117872ms step_avg:138.19ms
step:864/5100 train_loss:3.9569 train_time:118007ms step_avg:138.18ms
step:865/5100 train_loss:3.7972 train_time:118142ms step_avg:138.18ms
step:866/5100 train_loss:3.9761 train_time:118279ms step_avg:138.18ms
step:867/5100 train_loss:4.2390 train_time:118415ms step_avg:138.17ms
step:868/5100 train_loss:3.8124 train_time:118555ms step_avg:138.18ms
step:869/5100 train_loss:4.0027 train_time:118691ms step_avg:138.17ms
step:870/5100 train_loss:3.9877 train_time:118831ms step_avg:138.18ms
step:871/5100 train_loss:3.8193 train_time:118964ms step_avg:138.17ms
step:872/5100 train_loss:3.8219 train_time:119102ms step_avg:138.17ms
step:873/5100 train_loss:4.0434 train_time:119239ms step_avg:138.17ms
step:874/5100 train_loss:3.8132 train_time:119375ms step_avg:138.17ms
step:875/5100 train_loss:3.5090 train_time:119510ms step_avg:138.16ms
step:875/5100 val_loss:3.8966 train_time:119579ms step_avg:138.24ms
step:876/5100 train_loss:4.0115 train_time:119652ms step_avg:138.17ms
step:877/5100 train_loss:3.8363 train_time:119795ms step_avg:138.17ms
step:878/5100 train_loss:4.0056 train_time:119933ms step_avg:138.17ms
step:879/5100 train_loss:3.8534 train_time:120070ms step_avg:138.17ms
step:880/5100 train_loss:4.0264 train_time:120205ms step_avg:138.17ms
step:881/5100 train_loss:3.6854 train_time:120339ms step_avg:138.16ms
step:882/5100 train_loss:3.8739 train_time:120474ms step_avg:138.16ms
step:883/5100 train_loss:4.0504 train_time:120612ms step_avg:138.16ms
step:884/5100 train_loss:4.2160 train_time:120752ms step_avg:138.16ms
step:885/5100 train_loss:3.9510 train_time:120892ms step_avg:138.16ms
step:886/5100 train_loss:3.8489 train_time:121030ms step_avg:138.16ms
step:887/5100 train_loss:3.9642 train_time:121168ms step_avg:138.16ms
step:888/5100 train_loss:4.4433 train_time:121302ms step_avg:138.16ms
step:889/5100 train_loss:4.1926 train_time:121435ms step_avg:138.15ms
step:890/5100 train_loss:3.8970 train_time:121572ms step_avg:138.15ms
step:891/5100 train_loss:3.9086 train_time:121712ms step_avg:138.15ms
step:892/5100 train_loss:3.7310 train_time:121850ms step_avg:138.15ms
step:893/5100 train_loss:4.0633 train_time:121989ms step_avg:138.15ms
step:894/5100 train_loss:3.8008 train_time:122126ms step_avg:138.15ms
step:895/5100 train_loss:4.0702 train_time:122260ms step_avg:138.15ms
step:896/5100 train_loss:4.0701 train_time:122396ms step_avg:138.14ms
step:897/5100 train_loss:3.8760 train_time:122531ms step_avg:138.14ms
step:898/5100 train_loss:3.9107 train_time:122670ms step_avg:138.14ms
step:899/5100 train_loss:3.9581 train_time:122808ms step_avg:138.14ms
step:900/5100 train_loss:3.8537 train_time:122946ms step_avg:138.14ms
step:901/5100 train_loss:3.7876 train_time:123084ms step_avg:138.14ms
step:902/5100 train_loss:4.0039 train_time:123218ms step_avg:138.14ms
step:903/5100 train_loss:4.0144 train_time:123356ms step_avg:138.14ms
step:904/5100 train_loss:3.8996 train_time:123492ms step_avg:138.13ms
step:905/5100 train_loss:3.8682 train_time:123628ms step_avg:138.13ms
step:906/5100 train_loss:3.8689 train_time:123768ms step_avg:138.13ms
step:907/5100 train_loss:4.0804 train_time:123906ms step_avg:138.13ms
step:908/5100 train_loss:3.8810 train_time:124042ms step_avg:138.13ms
step:909/5100 train_loss:3.9203 train_time:124178ms step_avg:138.13ms
step:910/5100 train_loss:3.8270 train_time:124315ms step_avg:138.13ms
step:911/5100 train_loss:3.9225 train_time:124451ms step_avg:138.13ms
step:912/5100 train_loss:3.9830 train_time:124589ms step_avg:138.13ms
step:913/5100 train_loss:3.9753 train_time:124726ms step_avg:138.12ms
step:914/5100 train_loss:3.8552 train_time:124863ms step_avg:138.12ms
step:915/5100 train_loss:4.0995 train_time:124999ms step_avg:138.12ms
step:916/5100 train_loss:3.8996 train_time:125135ms step_avg:138.12ms
step:917/5100 train_loss:3.9977 train_time:125272ms step_avg:138.12ms
step:918/5100 train_loss:3.9709 train_time:125409ms step_avg:138.12ms
step:919/5100 train_loss:5.1976 train_time:125547ms step_avg:138.11ms
step:920/5100 train_loss:3.9155 train_time:125683ms step_avg:138.11ms
step:921/5100 train_loss:3.9698 train_time:125819ms step_avg:138.11ms
step:922/5100 train_loss:3.9291 train_time:125954ms step_avg:138.11ms
step:923/5100 train_loss:3.9690 train_time:126094ms step_avg:138.11ms
step:924/5100 train_loss:3.9733 train_time:126231ms step_avg:138.11ms
step:925/5100 train_loss:4.0518 train_time:126367ms step_avg:138.11ms
step:926/5100 train_loss:4.0408 train_time:126505ms step_avg:138.11ms
step:927/5100 train_loss:3.9230 train_time:126640ms step_avg:138.10ms
step:928/5100 train_loss:3.9153 train_time:126778ms step_avg:138.10ms
step:929/5100 train_loss:4.1251 train_time:126914ms step_avg:138.10ms
step:930/5100 train_loss:3.9810 train_time:127052ms step_avg:138.10ms
step:931/5100 train_loss:3.7539 train_time:127191ms step_avg:138.10ms
step:932/5100 train_loss:3.8575 train_time:127328ms step_avg:138.10ms
step:933/5100 train_loss:4.0392 train_time:127465ms step_avg:138.10ms
step:934/5100 train_loss:3.7860 train_time:127600ms step_avg:138.10ms
step:935/5100 train_loss:3.9281 train_time:127737ms step_avg:138.09ms
step:936/5100 train_loss:3.8236 train_time:127873ms step_avg:138.09ms
step:937/5100 train_loss:3.8810 train_time:128013ms step_avg:138.09ms
step:938/5100 train_loss:3.9731 train_time:128150ms step_avg:138.09ms
step:939/5100 train_loss:3.8894 train_time:128287ms step_avg:138.09ms
step:940/5100 train_loss:4.0609 train_time:128423ms step_avg:138.09ms
step:941/5100 train_loss:3.8519 train_time:128558ms step_avg:138.09ms
step:942/5100 train_loss:3.9109 train_time:128698ms step_avg:138.09ms
step:943/5100 train_loss:3.7150 train_time:128830ms step_avg:138.08ms
step:944/5100 train_loss:4.0489 train_time:128971ms step_avg:138.08ms
step:945/5100 train_loss:3.7672 train_time:129197ms step_avg:138.18ms
step:946/5100 train_loss:3.7859 train_time:129326ms step_avg:138.17ms
step:947/5100 train_loss:5.3928 train_time:129460ms step_avg:138.16ms
step:948/5100 train_loss:3.9482 train_time:129595ms step_avg:138.16ms
step:949/5100 train_loss:3.8597 train_time:129729ms step_avg:138.16ms
step:950/5100 train_loss:3.7621 train_time:130023ms step_avg:138.32ms
step:951/5100 train_loss:3.8131 train_time:130161ms step_avg:138.32ms
step:952/5100 train_loss:3.7715 train_time:130300ms step_avg:138.32ms
step:953/5100 train_loss:3.8331 train_time:130434ms step_avg:138.32ms
step:954/5100 train_loss:3.9113 train_time:130568ms step_avg:138.31ms
step:955/5100 train_loss:3.7854 train_time:130702ms step_avg:138.31ms
step:956/5100 train_loss:3.8317 train_time:130838ms step_avg:138.31ms
step:957/5100 train_loss:3.7940 train_time:130975ms step_avg:138.31ms
step:958/5100 train_loss:3.8641 train_time:131118ms step_avg:138.31ms
step:959/5100 train_loss:3.8570 train_time:131254ms step_avg:138.31ms
step:960/5100 train_loss:3.8722 train_time:131393ms step_avg:138.31ms
step:961/5100 train_loss:3.7488 train_time:131528ms step_avg:138.30ms
step:962/5100 train_loss:4.0174 train_time:131665ms step_avg:138.30ms
step:963/5100 train_loss:3.9756 train_time:131799ms step_avg:138.30ms
step:964/5100 train_loss:3.8308 train_time:131936ms step_avg:138.30ms
step:965/5100 train_loss:3.8036 train_time:132076ms step_avg:138.30ms
step:966/5100 train_loss:3.8512 train_time:132215ms step_avg:138.30ms
step:967/5100 train_loss:4.0720 train_time:132352ms step_avg:138.30ms
step:968/5100 train_loss:3.9040 train_time:132488ms step_avg:138.30ms
step:969/5100 train_loss:3.8972 train_time:132624ms step_avg:138.29ms
step:970/5100 train_loss:3.9294 train_time:132760ms step_avg:138.29ms
step:971/5100 train_loss:3.7431 train_time:132896ms step_avg:138.29ms
step:972/5100 train_loss:3.9058 train_time:133036ms step_avg:138.29ms
step:973/5100 train_loss:3.8586 train_time:133172ms step_avg:138.29ms
step:974/5100 train_loss:3.9084 train_time:133309ms step_avg:138.29ms
step:975/5100 train_loss:3.9818 train_time:133448ms step_avg:138.29ms
step:976/5100 train_loss:3.8523 train_time:133581ms step_avg:138.28ms
step:977/5100 train_loss:4.0446 train_time:133717ms step_avg:138.28ms
step:978/5100 train_loss:3.9255 train_time:133854ms step_avg:138.28ms
step:979/5100 train_loss:3.7665 train_time:133991ms step_avg:138.28ms
step:980/5100 train_loss:4.0547 train_time:134126ms step_avg:138.27ms
step:981/5100 train_loss:3.7780 train_time:134266ms step_avg:138.28ms
step:982/5100 train_loss:3.9469 train_time:134406ms step_avg:138.28ms
step:983/5100 train_loss:3.9280 train_time:134543ms step_avg:138.28ms
step:984/5100 train_loss:3.9494 train_time:134678ms step_avg:138.27ms
step:985/5100 train_loss:3.8706 train_time:134816ms step_avg:138.27ms
step:986/5100 train_loss:3.9623 train_time:134953ms step_avg:138.27ms
step:987/5100 train_loss:3.7724 train_time:135089ms step_avg:138.27ms
step:988/5100 train_loss:3.8478 train_time:135226ms step_avg:138.27ms
step:989/5100 train_loss:3.8294 train_time:135366ms step_avg:138.27ms
step:990/5100 train_loss:3.7873 train_time:135499ms step_avg:138.26ms
step:991/5100 train_loss:3.9794 train_time:135634ms step_avg:138.26ms
step:992/5100 train_loss:3.8237 train_time:135772ms step_avg:138.26ms
step:993/5100 train_loss:3.7887 train_time:135911ms step_avg:138.26ms
step:994/5100 train_loss:3.8747 train_time:136049ms step_avg:138.26ms
step:995/5100 train_loss:3.9526 train_time:136187ms step_avg:138.26ms
step:996/5100 train_loss:3.9025 train_time:136323ms step_avg:138.26ms
step:997/5100 train_loss:3.8064 train_time:136456ms step_avg:138.25ms
step:998/5100 train_loss:4.1694 train_time:136594ms step_avg:138.25ms
step:999/5100 train_loss:3.8163 train_time:136731ms step_avg:138.25ms
step:1000/5100 train_loss:3.9363 train_time:136869ms step_avg:138.25ms
step:1000/5100 val_loss:3.8430 train_time:136940ms step_avg:138.32ms
step:1001/5100 train_loss:3.8144 train_time:137012ms step_avg:138.26ms
step:1002/5100 train_loss:3.8706 train_time:137157ms step_avg:138.26ms
step:1003/5100 train_loss:3.7564 train_time:137296ms step_avg:138.26ms
step:1004/5100 train_loss:3.9393 train_time:137432ms step_avg:138.26ms
step:1005/5100 train_loss:3.9866 train_time:137566ms step_avg:138.26ms
step:1006/5100 train_loss:3.7513 train_time:137700ms step_avg:138.25ms
step:1007/5100 train_loss:3.8391 train_time:137836ms step_avg:138.25ms
step:1008/5100 train_loss:3.8101 train_time:137975ms step_avg:138.25ms
step:1009/5100 train_loss:3.9247 train_time:138114ms step_avg:138.25ms
step:1010/5100 train_loss:4.0319 train_time:138253ms step_avg:138.25ms
step:1011/5100 train_loss:3.9210 train_time:138390ms step_avg:138.25ms
step:1012/5100 train_loss:3.8774 train_time:138525ms step_avg:138.25ms
step:1013/5100 train_loss:3.7440 train_time:138661ms step_avg:138.25ms
step:1014/5100 train_loss:3.8897 train_time:138797ms step_avg:138.24ms
step:1015/5100 train_loss:4.0078 train_time:138935ms step_avg:138.24ms
step:1016/5100 train_loss:3.7061 train_time:139071ms step_avg:138.24ms
step:1017/5100 train_loss:3.8159 train_time:139208ms step_avg:138.24ms
step:1018/5100 train_loss:3.8247 train_time:139346ms step_avg:138.24ms
step:1019/5100 train_loss:3.7489 train_time:139483ms step_avg:138.24ms
step:1020/5100 train_loss:3.8995 train_time:139620ms step_avg:138.24ms
step:1021/5100 train_loss:3.8122 train_time:139757ms step_avg:138.24ms
step:1022/5100 train_loss:3.7416 train_time:139895ms step_avg:138.24ms
step:1023/5100 train_loss:3.8431 train_time:140031ms step_avg:138.23ms
step:1024/5100 train_loss:3.8790 train_time:140167ms step_avg:138.23ms
step:1025/5100 train_loss:3.8434 train_time:140305ms step_avg:138.23ms
step:1026/5100 train_loss:3.8692 train_time:140441ms step_avg:138.23ms
step:1027/5100 train_loss:4.0296 train_time:140580ms step_avg:138.23ms
step:1028/5100 train_loss:3.7002 train_time:140717ms step_avg:138.23ms
step:1029/5100 train_loss:3.7515 train_time:140853ms step_avg:138.23ms
step:1030/5100 train_loss:3.7271 train_time:140987ms step_avg:138.22ms
step:1031/5100 train_loss:3.8703 train_time:141124ms step_avg:138.22ms
step:1032/5100 train_loss:3.8731 train_time:141260ms step_avg:138.22ms
step:1033/5100 train_loss:4.0490 train_time:141397ms step_avg:138.22ms
step:1034/5100 train_loss:3.8595 train_time:141536ms step_avg:138.22ms
step:1035/5100 train_loss:3.8240 train_time:141674ms step_avg:138.22ms
step:1036/5100 train_loss:3.8018 train_time:141809ms step_avg:138.21ms
step:1037/5100 train_loss:3.8667 train_time:141944ms step_avg:138.21ms
step:1038/5100 train_loss:4.1769 train_time:142082ms step_avg:138.21ms
step:1039/5100 train_loss:3.9856 train_time:142219ms step_avg:138.21ms
step:1040/5100 train_loss:3.8788 train_time:142356ms step_avg:138.21ms
step:1041/5100 train_loss:3.7855 train_time:142492ms step_avg:138.21ms
step:1042/5100 train_loss:3.8498 train_time:142628ms step_avg:138.21ms
step:1043/5100 train_loss:3.8865 train_time:142764ms step_avg:138.20ms
step:1044/5100 train_loss:3.8053 train_time:142902ms step_avg:138.20ms
step:1045/5100 train_loss:3.8188 train_time:143039ms step_avg:138.20ms
step:1046/5100 train_loss:3.9019 train_time:143176ms step_avg:138.20ms
step:1047/5100 train_loss:3.8075 train_time:143315ms step_avg:138.20ms
step:1048/5100 train_loss:4.0232 train_time:143451ms step_avg:138.20ms
step:1049/5100 train_loss:3.8686 train_time:143587ms step_avg:138.20ms
step:1050/5100 train_loss:3.7963 train_time:143725ms step_avg:138.20ms
step:1051/5100 train_loss:3.7526 train_time:143862ms step_avg:138.20ms
step:1052/5100 train_loss:3.8912 train_time:143999ms step_avg:138.19ms
step:1053/5100 train_loss:3.7577 train_time:144137ms step_avg:138.19ms
step:1054/5100 train_loss:4.0855 train_time:144276ms step_avg:138.20ms
step:1055/5100 train_loss:3.9238 train_time:144411ms step_avg:138.19ms
step:1056/5100 train_loss:3.7672 train_time:144546ms step_avg:138.19ms
step:1057/5100 train_loss:3.8774 train_time:144683ms step_avg:138.19ms
step:1058/5100 train_loss:3.9510 train_time:144822ms step_avg:138.19ms
step:1059/5100 train_loss:3.6778 train_time:144958ms step_avg:138.19ms
step:1060/5100 train_loss:3.8085 train_time:145098ms step_avg:138.19ms
step:1061/5100 train_loss:3.8295 train_time:145235ms step_avg:138.19ms
step:1062/5100 train_loss:3.7838 train_time:145372ms step_avg:138.19ms
step:1063/5100 train_loss:3.7546 train_time:145507ms step_avg:138.18ms
step:1064/5100 train_loss:3.8666 train_time:145643ms step_avg:138.18ms
step:1065/5100 train_loss:3.7665 train_time:145782ms step_avg:138.18ms
step:1066/5100 train_loss:3.7358 train_time:145917ms step_avg:138.18ms
step:1067/5100 train_loss:3.7551 train_time:146055ms step_avg:138.18ms
step:1068/5100 train_loss:3.6812 train_time:146192ms step_avg:138.18ms
step:1069/5100 train_loss:3.7877 train_time:146329ms step_avg:138.18ms
step:1070/5100 train_loss:3.6920 train_time:146465ms step_avg:138.17ms
step:1071/5100 train_loss:3.9118 train_time:146602ms step_avg:138.17ms
step:1072/5100 train_loss:3.8708 train_time:146740ms step_avg:138.17ms
step:1073/5100 train_loss:3.8205 train_time:146878ms step_avg:138.17ms
step:1074/5100 train_loss:3.8871 train_time:147017ms step_avg:138.17ms
step:1075/5100 train_loss:3.8458 train_time:147155ms step_avg:138.17ms
step:1076/5100 train_loss:3.7729 train_time:147291ms step_avg:138.17ms
step:1077/5100 train_loss:4.1483 train_time:147426ms step_avg:138.17ms
step:1078/5100 train_loss:3.8658 train_time:147564ms step_avg:138.17ms
step:1079/5100 train_loss:3.5108 train_time:147701ms step_avg:138.17ms
step:1080/5100 train_loss:3.8995 train_time:147839ms step_avg:138.17ms
step:1081/5100 train_loss:3.8301 train_time:147976ms step_avg:138.17ms
step:1082/5100 train_loss:3.8959 train_time:148114ms step_avg:138.17ms
step:1083/5100 train_loss:3.9934 train_time:148250ms step_avg:138.16ms
step:1084/5100 train_loss:3.8819 train_time:148385ms step_avg:138.16ms
step:1085/5100 train_loss:3.8585 train_time:148523ms step_avg:138.16ms
step:1086/5100 train_loss:3.8099 train_time:148660ms step_avg:138.16ms
step:1087/5100 train_loss:4.0154 train_time:148798ms step_avg:138.16ms
step:1088/5100 train_loss:3.9238 train_time:148935ms step_avg:138.16ms
step:1089/5100 train_loss:3.7315 train_time:149073ms step_avg:138.16ms
step:1090/5100 train_loss:3.7654 train_time:149210ms step_avg:138.16ms
step:1091/5100 train_loss:3.8768 train_time:149344ms step_avg:138.15ms
step:1092/5100 train_loss:3.6730 train_time:149481ms step_avg:138.15ms
step:1093/5100 train_loss:3.8699 train_time:149619ms step_avg:138.15ms
step:1094/5100 train_loss:3.9949 train_time:149756ms step_avg:138.15ms
step:1095/5100 train_loss:3.8391 train_time:149892ms step_avg:138.15ms
step:1096/5100 train_loss:3.7896 train_time:150028ms step_avg:138.15ms
step:1097/5100 train_loss:3.8113 train_time:150165ms step_avg:138.15ms
step:1098/5100 train_loss:3.8597 train_time:150303ms step_avg:138.15ms
step:1099/5100 train_loss:3.9273 train_time:150439ms step_avg:138.14ms
step:1100/5100 train_loss:3.8896 train_time:150577ms step_avg:138.14ms
step:1101/5100 train_loss:3.8308 train_time:150715ms step_avg:138.14ms
step:1102/5100 train_loss:3.6736 train_time:150850ms step_avg:138.14ms
step:1103/5100 train_loss:3.7462 train_time:150985ms step_avg:138.14ms
step:1104/5100 train_loss:3.8252 train_time:151122ms step_avg:138.14ms
step:1105/5100 train_loss:3.7055 train_time:151259ms step_avg:138.14ms
step:1106/5100 train_loss:4.4433 train_time:151396ms step_avg:138.14ms
step:1107/5100 train_loss:3.6142 train_time:151533ms step_avg:138.13ms
step:1108/5100 train_loss:3.9451 train_time:151668ms step_avg:138.13ms
step:1109/5100 train_loss:3.7355 train_time:151804ms step_avg:138.13ms
step:1110/5100 train_loss:3.8759 train_time:151941ms step_avg:138.13ms
step:1111/5100 train_loss:3.8104 train_time:152078ms step_avg:138.13ms
step:1112/5100 train_loss:3.8467 train_time:152216ms step_avg:138.13ms
step:1113/5100 train_loss:3.9491 train_time:152353ms step_avg:138.13ms
step:1114/5100 train_loss:3.8288 train_time:152489ms step_avg:138.12ms
step:1115/5100 train_loss:3.7476 train_time:152624ms step_avg:138.12ms
step:1116/5100 train_loss:3.6701 train_time:152761ms step_avg:138.12ms
step:1117/5100 train_loss:3.8209 train_time:152898ms step_avg:138.12ms
step:1118/5100 train_loss:3.9791 train_time:153036ms step_avg:138.12ms
step:1119/5100 train_loss:4.0140 train_time:153175ms step_avg:138.12ms
step:1120/5100 train_loss:3.8526 train_time:153312ms step_avg:138.12ms
step:1121/5100 train_loss:3.8787 train_time:153446ms step_avg:138.12ms
step:1122/5100 train_loss:3.7813 train_time:153584ms step_avg:138.11ms
step:1123/5100 train_loss:3.8337 train_time:153722ms step_avg:138.11ms
step:1124/5100 train_loss:3.9788 train_time:153860ms step_avg:138.11ms
step:1125/5100 train_loss:3.7494 train_time:153998ms step_avg:138.11ms
step:1125/5100 val_loss:3.8028 train_time:154068ms step_avg:138.18ms
step:1126/5100 train_loss:3.6305 train_time:154141ms step_avg:138.12ms
step:1127/5100 train_loss:3.8635 train_time:154286ms step_avg:138.12ms
step:1128/5100 train_loss:4.0815 train_time:154422ms step_avg:138.12ms
step:1129/5100 train_loss:3.6177 train_time:154558ms step_avg:138.12ms
step:1130/5100 train_loss:3.9369 train_time:154694ms step_avg:138.12ms
step:1131/5100 train_loss:3.7786 train_time:154828ms step_avg:138.12ms
step:1132/5100 train_loss:3.7863 train_time:154962ms step_avg:138.11ms
step:1133/5100 train_loss:3.7519 train_time:155097ms step_avg:138.11ms
step:1134/5100 train_loss:3.9206 train_time:155335ms step_avg:138.20ms
step:1135/5100 train_loss:3.8411 train_time:155464ms step_avg:138.19ms
step:1136/5100 train_loss:3.8923 train_time:155597ms step_avg:138.19ms
step:1137/5100 train_loss:3.9208 train_time:155733ms step_avg:138.18ms
step:1138/5100 train_loss:3.8432 train_time:155868ms step_avg:138.18ms
step:1139/5100 train_loss:3.7456 train_time:156002ms step_avg:138.18ms
step:1140/5100 train_loss:4.0528 train_time:156294ms step_avg:138.31ms
step:1141/5100 train_loss:3.8532 train_time:156424ms step_avg:138.31ms
step:1142/5100 train_loss:3.9474 train_time:156563ms step_avg:138.31ms
step:1143/5100 train_loss:3.8426 train_time:156697ms step_avg:138.30ms
step:1144/5100 train_loss:3.7552 train_time:156838ms step_avg:138.31ms
step:1145/5100 train_loss:3.8503 train_time:156972ms step_avg:138.30ms
step:1146/5100 train_loss:3.9767 train_time:157107ms step_avg:138.30ms
step:1147/5100 train_loss:3.9301 train_time:157243ms step_avg:138.30ms
step:1148/5100 train_loss:3.8622 train_time:157384ms step_avg:138.30ms
step:1149/5100 train_loss:3.8812 train_time:157521ms step_avg:138.30ms
step:1150/5100 train_loss:3.7420 train_time:157658ms step_avg:138.30ms
step:1151/5100 train_loss:3.7557 train_time:157795ms step_avg:138.30ms
step:1152/5100 train_loss:3.7214 train_time:157932ms step_avg:138.29ms
step:1153/5100 train_loss:3.8862 train_time:158067ms step_avg:138.29ms
step:1154/5100 train_loss:3.8363 train_time:158201ms step_avg:138.29ms
step:1155/5100 train_loss:3.8950 train_time:158340ms step_avg:138.29ms
step:1156/5100 train_loss:3.7486 train_time:158479ms step_avg:138.29ms
step:1157/5100 train_loss:3.9176 train_time:158616ms step_avg:138.29ms
step:1158/5100 train_loss:3.8743 train_time:158753ms step_avg:138.29ms
step:1159/5100 train_loss:3.7066 train_time:158891ms step_avg:138.29ms
step:1160/5100 train_loss:3.7130 train_time:159026ms step_avg:138.28ms
step:1161/5100 train_loss:3.7078 train_time:159154ms step_avg:138.27ms
step:1162/5100 train_loss:3.5458 train_time:159296ms step_avg:138.28ms
step:1163/5100 train_loss:3.8416 train_time:159438ms step_avg:138.28ms
step:1164/5100 train_loss:3.8063 train_time:159572ms step_avg:138.28ms
step:1165/5100 train_loss:3.6593 train_time:159711ms step_avg:138.28ms
step:1166/5100 train_loss:3.6708 train_time:159849ms step_avg:138.28ms
step:1167/5100 train_loss:3.7608 train_time:159985ms step_avg:138.28ms
step:1168/5100 train_loss:3.7642 train_time:160121ms step_avg:138.27ms
step:1169/5100 train_loss:4.0896 train_time:160258ms step_avg:138.27ms
step:1170/5100 train_loss:3.7785 train_time:160396ms step_avg:138.27ms
step:1171/5100 train_loss:3.7860 train_time:160534ms step_avg:138.27ms
step:1172/5100 train_loss:3.7278 train_time:160671ms step_avg:138.27ms
step:1173/5100 train_loss:3.7773 train_time:160810ms step_avg:138.27ms
step:1174/5100 train_loss:3.9246 train_time:160944ms step_avg:138.27ms
step:1175/5100 train_loss:3.7671 train_time:161080ms step_avg:138.27ms
step:1176/5100 train_loss:3.7992 train_time:161217ms step_avg:138.26ms
step:1177/5100 train_loss:3.8344 train_time:161352ms step_avg:138.26ms
step:1178/5100 train_loss:3.8136 train_time:161490ms step_avg:138.26ms
step:1179/5100 train_loss:3.8742 train_time:161626ms step_avg:138.26ms
step:1180/5100 train_loss:3.7949 train_time:161763ms step_avg:138.26ms
step:1181/5100 train_loss:3.7958 train_time:161898ms step_avg:138.26ms
step:1182/5100 train_loss:3.7416 train_time:162036ms step_avg:138.26ms
step:1183/5100 train_loss:3.8001 train_time:162171ms step_avg:138.25ms
step:1184/5100 train_loss:3.7196 train_time:162308ms step_avg:138.25ms
step:1185/5100 train_loss:3.8821 train_time:162445ms step_avg:138.25ms
step:1186/5100 train_loss:3.9460 train_time:162581ms step_avg:138.25ms
step:1187/5100 train_loss:3.7324 train_time:162719ms step_avg:138.25ms
step:1188/5100 train_loss:3.7979 train_time:162856ms step_avg:138.25ms
step:1189/5100 train_loss:3.8299 train_time:162994ms step_avg:138.25ms
step:1190/5100 train_loss:3.6692 train_time:163132ms step_avg:138.25ms
step:1191/5100 train_loss:3.8490 train_time:163268ms step_avg:138.25ms
step:1192/5100 train_loss:3.9813 train_time:163404ms step_avg:138.24ms
step:1193/5100 train_loss:3.7861 train_time:163541ms step_avg:138.24ms
step:1194/5100 train_loss:3.6723 train_time:163678ms step_avg:138.24ms
step:1195/5100 train_loss:3.9647 train_time:163816ms step_avg:138.24ms
step:1196/5100 train_loss:3.7588 train_time:163954ms step_avg:138.24ms
step:1197/5100 train_loss:3.7675 train_time:164091ms step_avg:138.24ms
step:1198/5100 train_loss:3.6671 train_time:164224ms step_avg:138.24ms
step:1199/5100 train_loss:3.6715 train_time:164360ms step_avg:138.23ms
step:1200/5100 train_loss:3.7276 train_time:164497ms step_avg:138.23ms
step:1201/5100 train_loss:3.8070 train_time:164636ms step_avg:138.23ms
step:1202/5100 train_loss:3.8881 train_time:164774ms step_avg:138.23ms
step:1203/5100 train_loss:3.9631 train_time:164911ms step_avg:138.23ms
step:1204/5100 train_loss:3.8106 train_time:165048ms step_avg:138.23ms
step:1205/5100 train_loss:3.7524 train_time:165187ms step_avg:138.23ms
step:1206/5100 train_loss:3.8069 train_time:165322ms step_avg:138.23ms
step:1207/5100 train_loss:3.8631 train_time:165460ms step_avg:138.23ms
step:1208/5100 train_loss:3.9072 train_time:165597ms step_avg:138.23ms
step:1209/5100 train_loss:3.7864 train_time:165734ms step_avg:138.23ms
step:1210/5100 train_loss:3.6447 train_time:165874ms step_avg:138.23ms
step:1211/5100 train_loss:3.6907 train_time:166012ms step_avg:138.23ms
step:1212/5100 train_loss:3.7962 train_time:166149ms step_avg:138.23ms
step:1213/5100 train_loss:3.8097 train_time:166285ms step_avg:138.22ms
step:1214/5100 train_loss:3.8451 train_time:166421ms step_avg:138.22ms
step:1215/5100 train_loss:3.7549 train_time:166559ms step_avg:138.22ms
step:1216/5100 train_loss:3.7986 train_time:166698ms step_avg:138.22ms
step:1217/5100 train_loss:3.7367 train_time:166837ms step_avg:138.22ms
step:1218/5100 train_loss:3.7404 train_time:166974ms step_avg:138.22ms
step:1219/5100 train_loss:3.8259 train_time:167113ms step_avg:138.22ms
step:1220/5100 train_loss:3.6858 train_time:167250ms step_avg:138.22ms
step:1221/5100 train_loss:3.8828 train_time:167385ms step_avg:138.22ms
step:1222/5100 train_loss:3.9103 train_time:167521ms step_avg:138.22ms
step:1223/5100 train_loss:3.8638 train_time:167658ms step_avg:138.22ms
step:1224/5100 train_loss:3.6822 train_time:167796ms step_avg:138.22ms
step:1225/5100 train_loss:3.6953 train_time:167934ms step_avg:138.22ms
step:1226/5100 train_loss:3.7690 train_time:168071ms step_avg:138.22ms
step:1227/5100 train_loss:3.7428 train_time:168209ms step_avg:138.22ms
step:1228/5100 train_loss:3.6642 train_time:168345ms step_avg:138.21ms
step:1229/5100 train_loss:3.8493 train_time:168481ms step_avg:138.21ms
step:1230/5100 train_loss:3.7751 train_time:168618ms step_avg:138.21ms
step:1231/5100 train_loss:3.8307 train_time:168757ms step_avg:138.21ms
step:1232/5100 train_loss:3.9893 train_time:168895ms step_avg:138.21ms
step:1233/5100 train_loss:3.8882 train_time:169033ms step_avg:138.21ms
step:1234/5100 train_loss:3.8212 train_time:169171ms step_avg:138.21ms
step:1235/5100 train_loss:3.9784 train_time:169306ms step_avg:138.21ms
step:1236/5100 train_loss:3.7539 train_time:169443ms step_avg:138.21ms
step:1237/5100 train_loss:3.6969 train_time:169578ms step_avg:138.21ms
step:1238/5100 train_loss:3.6508 train_time:169717ms step_avg:138.21ms
step:1239/5100 train_loss:3.7448 train_time:169854ms step_avg:138.21ms
step:1240/5100 train_loss:3.7290 train_time:169993ms step_avg:138.21ms
step:1241/5100 train_loss:3.7826 train_time:170130ms step_avg:138.21ms
step:1242/5100 train_loss:3.8277 train_time:170269ms step_avg:138.21ms
step:1243/5100 train_loss:3.6978 train_time:170406ms step_avg:138.20ms
step:1244/5100 train_loss:3.8049 train_time:170541ms step_avg:138.20ms
step:1245/5100 train_loss:3.8127 train_time:170678ms step_avg:138.20ms
step:1246/5100 train_loss:3.8102 train_time:170816ms step_avg:138.20ms
step:1247/5100 train_loss:3.6346 train_time:170952ms step_avg:138.20ms
step:1248/5100 train_loss:3.7900 train_time:171091ms step_avg:138.20ms
step:1249/5100 train_loss:3.8505 train_time:171229ms step_avg:138.20ms
step:1250/5100 train_loss:3.8067 train_time:171362ms step_avg:138.20ms
step:1250/5100 val_loss:3.7627 train_time:171432ms step_avg:138.25ms
step:1251/5100 train_loss:3.7078 train_time:171507ms step_avg:138.20ms
step:1252/5100 train_loss:3.9228 train_time:171651ms step_avg:138.21ms
step:1253/5100 train_loss:3.7892 train_time:171787ms step_avg:138.20ms
step:1254/5100 train_loss:3.7111 train_time:171920ms step_avg:138.20ms
step:1255/5100 train_loss:3.8475 train_time:172055ms step_avg:138.20ms
step:1256/5100 train_loss:3.9170 train_time:172191ms step_avg:138.19ms
step:1257/5100 train_loss:3.7260 train_time:172324ms step_avg:138.19ms
step:1258/5100 train_loss:3.7398 train_time:172461ms step_avg:138.19ms
step:1259/5100 train_loss:3.7600 train_time:172601ms step_avg:138.19ms
step:1260/5100 train_loss:3.7545 train_time:172739ms step_avg:138.19ms
step:1261/5100 train_loss:3.6084 train_time:172879ms step_avg:138.19ms
step:1262/5100 train_loss:3.6970 train_time:173012ms step_avg:138.19ms
step:1263/5100 train_loss:3.7738 train_time:173147ms step_avg:138.19ms
step:1264/5100 train_loss:3.6145 train_time:173281ms step_avg:138.18ms
step:1265/5100 train_loss:3.8414 train_time:173414ms step_avg:138.18ms
step:1266/5100 train_loss:3.8265 train_time:173558ms step_avg:138.18ms
step:1267/5100 train_loss:3.8364 train_time:173695ms step_avg:138.18ms
step:1268/5100 train_loss:3.7721 train_time:173832ms step_avg:138.18ms
step:1269/5100 train_loss:3.8129 train_time:173972ms step_avg:138.18ms
step:1270/5100 train_loss:3.6612 train_time:174109ms step_avg:138.18ms
step:1271/5100 train_loss:3.5131 train_time:174243ms step_avg:138.18ms
step:1272/5100 train_loss:3.7893 train_time:174378ms step_avg:138.18ms
step:1273/5100 train_loss:3.7551 train_time:174517ms step_avg:138.18ms
step:1274/5100 train_loss:3.8077 train_time:174656ms step_avg:138.18ms
step:1275/5100 train_loss:3.7444 train_time:174794ms step_avg:138.18ms
step:1276/5100 train_loss:3.8453 train_time:174932ms step_avg:138.18ms
step:1277/5100 train_loss:3.8781 train_time:175069ms step_avg:138.18ms
step:1278/5100 train_loss:3.8288 train_time:175204ms step_avg:138.17ms
step:1279/5100 train_loss:3.8160 train_time:175341ms step_avg:138.17ms
step:1280/5100 train_loss:3.6446 train_time:175477ms step_avg:138.17ms
step:1281/5100 train_loss:3.7740 train_time:175616ms step_avg:138.17ms
step:1282/5100 train_loss:3.8326 train_time:175753ms step_avg:138.17ms
step:1283/5100 train_loss:3.8660 train_time:175893ms step_avg:138.17ms
step:1284/5100 train_loss:3.7558 train_time:176031ms step_avg:138.17ms
step:1285/5100 train_loss:3.7907 train_time:176167ms step_avg:138.17ms
step:1286/5100 train_loss:3.7621 train_time:176302ms step_avg:138.17ms
step:1287/5100 train_loss:3.7367 train_time:176437ms step_avg:138.17ms
step:1288/5100 train_loss:3.8669 train_time:176575ms step_avg:138.17ms
step:1289/5100 train_loss:3.7100 train_time:176713ms step_avg:138.17ms
step:1290/5100 train_loss:3.7845 train_time:176852ms step_avg:138.17ms
step:1291/5100 train_loss:3.8639 train_time:176990ms step_avg:138.17ms
step:1292/5100 train_loss:3.7884 train_time:177127ms step_avg:138.16ms
step:1293/5100 train_loss:3.8855 train_time:177262ms step_avg:138.16ms
step:1294/5100 train_loss:3.9101 train_time:177397ms step_avg:138.16ms
step:1295/5100 train_loss:3.8823 train_time:177535ms step_avg:138.16ms
step:1296/5100 train_loss:3.6943 train_time:177673ms step_avg:138.16ms
step:1297/5100 train_loss:3.7648 train_time:177811ms step_avg:138.16ms
step:1298/5100 train_loss:3.6620 train_time:177952ms step_avg:138.16ms
step:1299/5100 train_loss:3.7431 train_time:178088ms step_avg:138.16ms
step:1300/5100 train_loss:3.7988 train_time:178222ms step_avg:138.16ms
step:1301/5100 train_loss:3.8151 train_time:178358ms step_avg:138.15ms
step:1302/5100 train_loss:3.8216 train_time:178494ms step_avg:138.15ms
step:1303/5100 train_loss:3.9620 train_time:178631ms step_avg:138.15ms
step:1304/5100 train_loss:3.7482 train_time:178769ms step_avg:138.15ms
step:1305/5100 train_loss:3.9667 train_time:178907ms step_avg:138.15ms
step:1306/5100 train_loss:3.6846 train_time:179043ms step_avg:138.15ms
step:1307/5100 train_loss:3.8499 train_time:179178ms step_avg:138.15ms
step:1308/5100 train_loss:3.8643 train_time:179315ms step_avg:138.15ms
step:1309/5100 train_loss:3.7343 train_time:179452ms step_avg:138.15ms
step:1310/5100 train_loss:3.6812 train_time:179590ms step_avg:138.15ms
step:1311/5100 train_loss:3.7372 train_time:179726ms step_avg:138.14ms
step:1312/5100 train_loss:3.6808 train_time:179862ms step_avg:138.14ms
step:1313/5100 train_loss:3.8189 train_time:179998ms step_avg:138.14ms
step:1314/5100 train_loss:3.7628 train_time:180136ms step_avg:138.14ms
step:1315/5100 train_loss:3.4818 train_time:180273ms step_avg:138.14ms
step:1316/5100 train_loss:3.7130 train_time:180411ms step_avg:138.14ms
step:1317/5100 train_loss:3.7789 train_time:180549ms step_avg:138.14ms
step:1318/5100 train_loss:3.8071 train_time:180683ms step_avg:138.14ms
step:1319/5100 train_loss:3.6683 train_time:180822ms step_avg:138.14ms
step:1320/5100 train_loss:3.8248 train_time:180959ms step_avg:138.14ms
step:1321/5100 train_loss:3.8820 train_time:181095ms step_avg:138.14ms
step:1322/5100 train_loss:3.7607 train_time:181231ms step_avg:138.13ms
step:1323/5100 train_loss:3.7163 train_time:181456ms step_avg:138.20ms
step:1324/5100 train_loss:3.7481 train_time:181583ms step_avg:138.19ms
step:1325/5100 train_loss:3.8336 train_time:181718ms step_avg:138.19ms
step:1326/5100 train_loss:3.9039 train_time:181853ms step_avg:138.19ms
step:1327/5100 train_loss:3.6655 train_time:181988ms step_avg:138.18ms
step:1328/5100 train_loss:3.5737 train_time:182123ms step_avg:138.18ms
step:1329/5100 train_loss:3.8755 train_time:182257ms step_avg:138.18ms
step:1330/5100 train_loss:3.7452 train_time:182560ms step_avg:138.30ms
step:1331/5100 train_loss:3.8590 train_time:182691ms step_avg:138.30ms
step:1332/5100 train_loss:3.7715 train_time:182831ms step_avg:138.30ms
step:1333/5100 train_loss:4.1680 train_time:182966ms step_avg:138.30ms
step:1334/5100 train_loss:3.8431 train_time:183100ms step_avg:138.29ms
step:1335/5100 train_loss:3.7649 train_time:183235ms step_avg:138.29ms
step:1336/5100 train_loss:3.7303 train_time:183371ms step_avg:138.29ms
step:1337/5100 train_loss:3.7121 train_time:183507ms step_avg:138.29ms
step:1338/5100 train_loss:3.9657 train_time:183652ms step_avg:138.29ms
step:1339/5100 train_loss:3.8954 train_time:183790ms step_avg:138.29ms
step:1340/5100 train_loss:3.7487 train_time:183927ms step_avg:138.29ms
step:1341/5100 train_loss:3.7080 train_time:184062ms step_avg:138.29ms
step:1342/5100 train_loss:4.0141 train_time:184198ms step_avg:138.29ms
step:1343/5100 train_loss:3.7795 train_time:184334ms step_avg:138.28ms
step:1344/5100 train_loss:3.7732 train_time:184471ms step_avg:138.28ms
step:1345/5100 train_loss:3.8363 train_time:184609ms step_avg:138.28ms
step:1346/5100 train_loss:3.8022 train_time:184749ms step_avg:138.29ms
step:1347/5100 train_loss:3.7016 train_time:184886ms step_avg:138.28ms
step:1348/5100 train_loss:3.6330 train_time:185022ms step_avg:138.28ms
step:1349/5100 train_loss:3.7318 train_time:185158ms step_avg:138.28ms
step:1350/5100 train_loss:3.6759 train_time:185292ms step_avg:138.28ms
step:1351/5100 train_loss:3.8102 train_time:185431ms step_avg:138.28ms
step:1352/5100 train_loss:3.6555 train_time:185570ms step_avg:138.28ms
step:1353/5100 train_loss:3.7106 train_time:185707ms step_avg:138.28ms
step:1354/5100 train_loss:3.8248 train_time:185845ms step_avg:138.28ms
step:1355/5100 train_loss:3.6575 train_time:185982ms step_avg:138.28ms
step:1356/5100 train_loss:3.5831 train_time:186118ms step_avg:138.27ms
step:1357/5100 train_loss:3.9413 train_time:186255ms step_avg:138.27ms
step:1358/5100 train_loss:3.8704 train_time:186391ms step_avg:138.27ms
step:1359/5100 train_loss:3.5775 train_time:186532ms step_avg:138.27ms
step:1360/5100 train_loss:3.8651 train_time:186667ms step_avg:138.27ms
step:1361/5100 train_loss:3.7434 train_time:186805ms step_avg:138.27ms
step:1362/5100 train_loss:3.6233 train_time:186940ms step_avg:138.27ms
step:1363/5100 train_loss:3.7897 train_time:187078ms step_avg:138.27ms
step:1364/5100 train_loss:3.6823 train_time:187215ms step_avg:138.27ms
step:1365/5100 train_loss:3.7114 train_time:187352ms step_avg:138.27ms
step:1366/5100 train_loss:3.7307 train_time:187489ms step_avg:138.27ms
step:1367/5100 train_loss:3.8424 train_time:187625ms step_avg:138.26ms
step:1368/5100 train_loss:3.8122 train_time:187760ms step_avg:138.26ms
step:1369/5100 train_loss:3.7721 train_time:187898ms step_avg:138.26ms
step:1370/5100 train_loss:3.6589 train_time:188035ms step_avg:138.26ms
step:1371/5100 train_loss:3.9978 train_time:188172ms step_avg:138.26ms
step:1372/5100 train_loss:3.7479 train_time:188310ms step_avg:138.26ms
step:1373/5100 train_loss:3.7750 train_time:188448ms step_avg:138.26ms
step:1374/5100 train_loss:3.7662 train_time:188583ms step_avg:138.26ms
step:1375/5100 train_loss:3.5793 train_time:188715ms step_avg:138.25ms
step:1375/5100 val_loss:3.7408 train_time:188790ms step_avg:138.31ms
step:1376/5100 train_loss:3.9828 train_time:188861ms step_avg:138.26ms
step:1377/5100 train_loss:3.7514 train_time:189005ms step_avg:138.26ms
step:1378/5100 train_loss:3.9007 train_time:189143ms step_avg:138.26ms
step:1379/5100 train_loss:3.9543 train_time:189280ms step_avg:138.26ms
step:1380/5100 train_loss:3.6112 train_time:189414ms step_avg:138.26ms
step:1381/5100 train_loss:3.7454 train_time:189547ms step_avg:138.25ms
step:1382/5100 train_loss:4.2049 train_time:189682ms step_avg:138.25ms
step:1383/5100 train_loss:3.6713 train_time:189819ms step_avg:138.25ms
step:1384/5100 train_loss:3.8151 train_time:189958ms step_avg:138.25ms
step:1385/5100 train_loss:3.8927 train_time:190099ms step_avg:138.25ms
step:1386/5100 train_loss:3.7964 train_time:190234ms step_avg:138.25ms
step:1387/5100 train_loss:3.8394 train_time:190370ms step_avg:138.25ms
step:1388/5100 train_loss:3.6184 train_time:190504ms step_avg:138.25ms
step:1389/5100 train_loss:3.7655 train_time:190641ms step_avg:138.25ms
step:1390/5100 train_loss:3.7338 train_time:190776ms step_avg:138.24ms
step:1391/5100 train_loss:4.0012 train_time:190913ms step_avg:138.24ms
step:1392/5100 train_loss:3.7049 train_time:191052ms step_avg:138.24ms
step:1393/5100 train_loss:3.7079 train_time:191191ms step_avg:138.24ms
step:1394/5100 train_loss:3.6757 train_time:191330ms step_avg:138.24ms
step:1395/5100 train_loss:3.9594 train_time:191464ms step_avg:138.24ms
step:1396/5100 train_loss:3.8496 train_time:191602ms step_avg:138.24ms
step:1397/5100 train_loss:3.8516 train_time:191739ms step_avg:138.24ms
step:1398/5100 train_loss:3.7088 train_time:191874ms step_avg:138.24ms
step:1399/5100 train_loss:3.6944 train_time:192013ms step_avg:138.24ms
step:1400/5100 train_loss:3.7537 train_time:192149ms step_avg:138.24ms
step:1401/5100 train_loss:3.7169 train_time:192287ms step_avg:138.24ms
step:1402/5100 train_loss:3.7362 train_time:192424ms step_avg:138.24ms
step:1403/5100 train_loss:3.7143 train_time:192562ms step_avg:138.24ms
step:1404/5100 train_loss:3.9360 train_time:192700ms step_avg:138.23ms
step:1405/5100 train_loss:3.6757 train_time:192834ms step_avg:138.23ms
step:1406/5100 train_loss:3.7291 train_time:192971ms step_avg:138.23ms
step:1407/5100 train_loss:3.7340 train_time:193106ms step_avg:138.23ms
step:1408/5100 train_loss:3.6007 train_time:193246ms step_avg:138.23ms
step:1409/5100 train_loss:3.7063 train_time:193382ms step_avg:138.23ms
step:1410/5100 train_loss:3.6856 train_time:193520ms step_avg:138.23ms
step:1411/5100 train_loss:3.6855 train_time:193655ms step_avg:138.23ms
step:1412/5100 train_loss:3.7921 train_time:193791ms step_avg:138.22ms
step:1413/5100 train_loss:3.7114 train_time:193927ms step_avg:138.22ms
step:1414/5100 train_loss:3.7699 train_time:194065ms step_avg:138.22ms
step:1415/5100 train_loss:3.7659 train_time:194201ms step_avg:138.22ms
step:1416/5100 train_loss:3.8381 train_time:194339ms step_avg:138.22ms
step:1417/5100 train_loss:3.6406 train_time:194474ms step_avg:138.22ms
step:1418/5100 train_loss:3.7037 train_time:194612ms step_avg:138.22ms
step:1419/5100 train_loss:3.7915 train_time:194749ms step_avg:138.22ms
step:1420/5100 train_loss:3.8337 train_time:194885ms step_avg:138.22ms
step:1421/5100 train_loss:3.7972 train_time:195024ms step_avg:138.22ms
step:1422/5100 train_loss:3.7803 train_time:195162ms step_avg:138.22ms
step:1423/5100 train_loss:3.7763 train_time:195299ms step_avg:138.22ms
step:1424/5100 train_loss:3.7584 train_time:195437ms step_avg:138.22ms
step:1425/5100 train_loss:3.7445 train_time:195572ms step_avg:138.21ms
step:1426/5100 train_loss:3.6187 train_time:195709ms step_avg:138.21ms
step:1427/5100 train_loss:3.7392 train_time:195846ms step_avg:138.21ms
step:1428/5100 train_loss:3.6710 train_time:195984ms step_avg:138.21ms
step:1429/5100 train_loss:3.7895 train_time:196122ms step_avg:138.21ms
step:1430/5100 train_loss:3.7557 train_time:196261ms step_avg:138.21ms
step:1431/5100 train_loss:3.6853 train_time:196398ms step_avg:138.21ms
step:1432/5100 train_loss:3.7248 train_time:196531ms step_avg:138.21ms
step:1433/5100 train_loss:3.7698 train_time:196669ms step_avg:138.21ms
step:1434/5100 train_loss:3.6838 train_time:196807ms step_avg:138.21ms
step:1435/5100 train_loss:3.7453 train_time:196943ms step_avg:138.21ms
step:1436/5100 train_loss:3.5613 train_time:197080ms step_avg:138.21ms
step:1437/5100 train_loss:3.6263 train_time:197221ms step_avg:138.21ms
step:1438/5100 train_loss:3.8300 train_time:197358ms step_avg:138.21ms
step:1439/5100 train_loss:3.7745 train_time:197493ms step_avg:138.20ms
step:1440/5100 train_loss:3.7286 train_time:197629ms step_avg:138.20ms
step:1441/5100 train_loss:3.5850 train_time:197767ms step_avg:138.20ms
step:1442/5100 train_loss:3.7651 train_time:197905ms step_avg:138.20ms
step:1443/5100 train_loss:3.8215 train_time:198042ms step_avg:138.20ms
step:1444/5100 train_loss:3.8800 train_time:198181ms step_avg:138.20ms
step:1445/5100 train_loss:3.8634 train_time:198320ms step_avg:138.20ms
step:1446/5100 train_loss:3.7461 train_time:198456ms step_avg:138.20ms
step:1447/5100 train_loss:3.6282 train_time:198591ms step_avg:138.20ms
step:1448/5100 train_loss:3.6943 train_time:198728ms step_avg:138.20ms
step:1449/5100 train_loss:3.7116 train_time:198866ms step_avg:138.20ms
step:1450/5100 train_loss:3.8345 train_time:199004ms step_avg:138.20ms
step:1451/5100 train_loss:3.8223 train_time:199142ms step_avg:138.20ms
step:1452/5100 train_loss:3.6449 train_time:199281ms step_avg:138.20ms
step:1453/5100 train_loss:3.7494 train_time:199418ms step_avg:138.20ms
step:1454/5100 train_loss:3.6658 train_time:199552ms step_avg:138.19ms
step:1455/5100 train_loss:3.6926 train_time:199689ms step_avg:138.19ms
step:1456/5100 train_loss:3.7492 train_time:199829ms step_avg:138.19ms
step:1457/5100 train_loss:3.6700 train_time:199965ms step_avg:138.19ms
step:1458/5100 train_loss:3.5808 train_time:200103ms step_avg:138.19ms
step:1459/5100 train_loss:3.8104 train_time:200242ms step_avg:138.19ms
step:1460/5100 train_loss:3.6892 train_time:200380ms step_avg:138.19ms
step:1461/5100 train_loss:3.7331 train_time:200517ms step_avg:138.19ms
step:1462/5100 train_loss:3.8662 train_time:200653ms step_avg:138.19ms
step:1463/5100 train_loss:3.6870 train_time:200791ms step_avg:138.19ms
step:1464/5100 train_loss:3.8591 train_time:200928ms step_avg:138.19ms
step:1465/5100 train_loss:3.7609 train_time:201066ms step_avg:138.19ms
step:1466/5100 train_loss:3.8073 train_time:201203ms step_avg:138.19ms
step:1467/5100 train_loss:3.6912 train_time:201342ms step_avg:138.19ms
step:1468/5100 train_loss:3.8525 train_time:201479ms step_avg:138.19ms
step:1469/5100 train_loss:3.7114 train_time:201614ms step_avg:138.19ms
step:1470/5100 train_loss:3.6740 train_time:201750ms step_avg:138.18ms
step:1471/5100 train_loss:3.7342 train_time:201888ms step_avg:138.18ms
step:1472/5100 train_loss:3.6624 train_time:202025ms step_avg:138.18ms
step:1473/5100 train_loss:3.7611 train_time:202163ms step_avg:138.18ms
step:1474/5100 train_loss:3.8417 train_time:202302ms step_avg:138.18ms
step:1475/5100 train_loss:3.7257 train_time:202439ms step_avg:138.18ms
step:1476/5100 train_loss:3.5438 train_time:202576ms step_avg:138.18ms
step:1477/5100 train_loss:3.6682 train_time:202710ms step_avg:138.18ms
step:1478/5100 train_loss:3.6494 train_time:202850ms step_avg:138.18ms
step:1479/5100 train_loss:3.7373 train_time:202988ms step_avg:138.18ms
step:1480/5100 train_loss:3.8116 train_time:203126ms step_avg:138.18ms
step:1481/5100 train_loss:3.6858 train_time:203264ms step_avg:138.18ms
step:1482/5100 train_loss:3.8587 train_time:203402ms step_avg:138.18ms
step:1483/5100 train_loss:3.7884 train_time:203540ms step_avg:138.18ms
step:1484/5100 train_loss:3.6981 train_time:203675ms step_avg:138.18ms
step:1485/5100 train_loss:3.6782 train_time:203810ms step_avg:138.18ms
step:1486/5100 train_loss:3.6716 train_time:203948ms step_avg:138.18ms
step:1487/5100 train_loss:3.6506 train_time:204087ms step_avg:138.18ms
step:1488/5100 train_loss:3.7324 train_time:204226ms step_avg:138.18ms
step:1489/5100 train_loss:3.6380 train_time:204365ms step_avg:138.18ms
step:1490/5100 train_loss:3.7424 train_time:204503ms step_avg:138.18ms
step:1491/5100 train_loss:3.6718 train_time:204640ms step_avg:138.18ms
step:1492/5100 train_loss:3.6033 train_time:204779ms step_avg:138.18ms
step:1493/5100 train_loss:3.6623 train_time:204914ms step_avg:138.18ms
step:1494/5100 train_loss:3.8506 train_time:205050ms step_avg:138.17ms
step:1495/5100 train_loss:3.7140 train_time:205189ms step_avg:138.17ms
step:1496/5100 train_loss:3.4577 train_time:205328ms step_avg:138.18ms
step:1497/5100 train_loss:3.7582 train_time:205466ms step_avg:138.17ms
step:1498/5100 train_loss:3.7271 train_time:205604ms step_avg:138.17ms
step:1499/5100 train_loss:3.7593 train_time:205743ms step_avg:138.17ms
step:1500/5100 train_loss:3.7264 train_time:205879ms step_avg:138.17ms
step:1500/5100 val_loss:3.7029 train_time:205949ms step_avg:138.22ms
step:1501/5100 train_loss:3.6979 train_time:206019ms step_avg:138.18ms
step:1502/5100 train_loss:3.5073 train_time:206167ms step_avg:138.18ms
step:1503/5100 train_loss:3.7826 train_time:206302ms step_avg:138.18ms
step:1504/5100 train_loss:3.6539 train_time:206440ms step_avg:138.18ms
step:1505/5100 train_loss:3.6653 train_time:206573ms step_avg:138.18ms
step:1506/5100 train_loss:3.6165 train_time:206709ms step_avg:138.17ms
step:1507/5100 train_loss:3.7133 train_time:206843ms step_avg:138.17ms
step:1508/5100 train_loss:3.6290 train_time:206980ms step_avg:138.17ms
step:1509/5100 train_loss:3.9342 train_time:207123ms step_avg:138.17ms
step:1510/5100 train_loss:3.6706 train_time:207259ms step_avg:138.17ms
step:1511/5100 train_loss:3.6840 train_time:207396ms step_avg:138.17ms
step:1512/5100 train_loss:3.8000 train_time:207633ms step_avg:138.24ms
step:1513/5100 train_loss:3.8295 train_time:207763ms step_avg:138.23ms
step:1514/5100 train_loss:3.6854 train_time:207897ms step_avg:138.23ms
step:1515/5100 train_loss:3.5117 train_time:208031ms step_avg:138.23ms
step:1516/5100 train_loss:3.6510 train_time:208165ms step_avg:138.22ms
step:1517/5100 train_loss:3.6584 train_time:208300ms step_avg:138.22ms
step:1518/5100 train_loss:3.7425 train_time:208435ms step_avg:138.22ms
step:1519/5100 train_loss:3.6311 train_time:208576ms step_avg:138.22ms
step:1520/5100 train_loss:3.9215 train_time:208882ms step_avg:138.33ms
step:1521/5100 train_loss:3.5878 train_time:209017ms step_avg:138.33ms
step:1522/5100 train_loss:3.6540 train_time:209152ms step_avg:138.33ms
step:1523/5100 train_loss:3.7766 train_time:209287ms step_avg:138.33ms
step:1524/5100 train_loss:3.6422 train_time:209421ms step_avg:138.32ms
step:1525/5100 train_loss:3.7361 train_time:209556ms step_avg:138.32ms
step:1526/5100 train_loss:3.7263 train_time:209691ms step_avg:138.32ms
step:1527/5100 train_loss:3.7048 train_time:209828ms step_avg:138.32ms
step:1528/5100 train_loss:3.6969 train_time:209970ms step_avg:138.32ms
step:1529/5100 train_loss:3.8509 train_time:210109ms step_avg:138.32ms
step:1530/5100 train_loss:3.8216 train_time:210246ms step_avg:138.32ms
step:1531/5100 train_loss:3.6496 train_time:210382ms step_avg:138.32ms
step:1532/5100 train_loss:3.6205 train_time:210516ms step_avg:138.32ms
step:1533/5100 train_loss:3.7771 train_time:210654ms step_avg:138.32ms
step:1534/5100 train_loss:3.7144 train_time:210788ms step_avg:138.31ms
step:1535/5100 train_loss:3.7085 train_time:210925ms step_avg:138.31ms
step:1536/5100 train_loss:3.6969 train_time:211063ms step_avg:138.31ms
step:1537/5100 train_loss:3.6371 train_time:211200ms step_avg:138.31ms
step:1538/5100 train_loss:3.7104 train_time:211337ms step_avg:138.31ms
step:1539/5100 train_loss:3.8899 train_time:211476ms step_avg:138.31ms
step:1540/5100 train_loss:3.8117 train_time:211611ms step_avg:138.31ms
step:1541/5100 train_loss:3.7204 train_time:211746ms step_avg:138.31ms
step:1542/5100 train_loss:3.6740 train_time:211882ms step_avg:138.30ms
step:1543/5100 train_loss:3.6631 train_time:212020ms step_avg:138.30ms
step:1544/5100 train_loss:3.6354 train_time:212158ms step_avg:138.30ms
step:1545/5100 train_loss:3.7340 train_time:212296ms step_avg:138.30ms
step:1546/5100 train_loss:3.6964 train_time:212434ms step_avg:138.30ms
step:1547/5100 train_loss:3.6646 train_time:212572ms step_avg:138.30ms
step:1548/5100 train_loss:3.6280 train_time:212709ms step_avg:138.30ms
step:1549/5100 train_loss:3.6572 train_time:212844ms step_avg:138.30ms
step:1550/5100 train_loss:3.7737 train_time:212981ms step_avg:138.30ms
step:1551/5100 train_loss:3.6931 train_time:213119ms step_avg:138.30ms
step:1552/5100 train_loss:3.6456 train_time:213257ms step_avg:138.30ms
step:1553/5100 train_loss:3.6344 train_time:213394ms step_avg:138.30ms
step:1554/5100 train_loss:3.6241 train_time:213533ms step_avg:138.30ms
step:1555/5100 train_loss:3.7443 train_time:213670ms step_avg:138.30ms
step:1556/5100 train_loss:3.7524 train_time:213806ms step_avg:138.30ms
step:1557/5100 train_loss:3.6912 train_time:213941ms step_avg:138.29ms
step:1558/5100 train_loss:3.7498 train_time:214079ms step_avg:138.29ms
step:1559/5100 train_loss:3.6697 train_time:214217ms step_avg:138.29ms
step:1560/5100 train_loss:3.5905 train_time:214354ms step_avg:138.29ms
step:1561/5100 train_loss:3.8170 train_time:214492ms step_avg:138.29ms
step:1562/5100 train_loss:3.6511 train_time:214629ms step_avg:138.29ms
step:1563/5100 train_loss:3.6283 train_time:214765ms step_avg:138.29ms
step:1564/5100 train_loss:3.7538 train_time:214900ms step_avg:138.29ms
step:1565/5100 train_loss:3.5753 train_time:215037ms step_avg:138.29ms
step:1566/5100 train_loss:3.6461 train_time:215176ms step_avg:138.29ms
step:1567/5100 train_loss:3.7779 train_time:215313ms step_avg:138.29ms
step:1568/5100 train_loss:3.6617 train_time:215452ms step_avg:138.29ms
step:1569/5100 train_loss:3.6407 train_time:215586ms step_avg:138.29ms
step:1570/5100 train_loss:3.7467 train_time:215723ms step_avg:138.28ms
step:1571/5100 train_loss:3.7540 train_time:215860ms step_avg:138.28ms
step:1572/5100 train_loss:3.5751 train_time:215997ms step_avg:138.28ms
step:1573/5100 train_loss:3.6020 train_time:216136ms step_avg:138.28ms
step:1574/5100 train_loss:3.7213 train_time:216274ms step_avg:138.28ms
step:1575/5100 train_loss:3.5889 train_time:216413ms step_avg:138.28ms
step:1576/5100 train_loss:3.7394 train_time:216552ms step_avg:138.28ms
step:1577/5100 train_loss:3.6384 train_time:216689ms step_avg:138.28ms
step:1578/5100 train_loss:3.7007 train_time:216825ms step_avg:138.28ms
step:1579/5100 train_loss:3.6682 train_time:216961ms step_avg:138.28ms
step:1580/5100 train_loss:3.6308 train_time:217099ms step_avg:138.28ms
step:1581/5100 train_loss:3.6143 train_time:217238ms step_avg:138.28ms
step:1582/5100 train_loss:3.8448 train_time:217376ms step_avg:138.28ms
step:1583/5100 train_loss:3.6228 train_time:217513ms step_avg:138.28ms
step:1584/5100 train_loss:3.7800 train_time:217651ms step_avg:138.28ms
step:1585/5100 train_loss:3.6199 train_time:217788ms step_avg:138.28ms
step:1586/5100 train_loss:3.7713 train_time:217924ms step_avg:138.28ms
step:1587/5100 train_loss:3.5554 train_time:218060ms step_avg:138.28ms
step:1588/5100 train_loss:3.7503 train_time:218198ms step_avg:138.28ms
step:1589/5100 train_loss:3.6710 train_time:218335ms step_avg:138.27ms
step:1590/5100 train_loss:3.8261 train_time:218473ms step_avg:138.27ms
step:1591/5100 train_loss:3.6336 train_time:218610ms step_avg:138.27ms
step:1592/5100 train_loss:3.6564 train_time:218747ms step_avg:138.27ms
step:1593/5100 train_loss:3.7276 train_time:218883ms step_avg:138.27ms
step:1594/5100 train_loss:3.7011 train_time:219019ms step_avg:138.27ms
step:1595/5100 train_loss:3.6800 train_time:219159ms step_avg:138.27ms
step:1596/5100 train_loss:3.8157 train_time:219298ms step_avg:138.27ms
step:1597/5100 train_loss:3.5573 train_time:219436ms step_avg:138.27ms
step:1598/5100 train_loss:3.7062 train_time:219573ms step_avg:138.27ms
step:1599/5100 train_loss:3.7510 train_time:219710ms step_avg:138.27ms
step:1600/5100 train_loss:3.8004 train_time:219845ms step_avg:138.27ms
step:1601/5100 train_loss:3.6468 train_time:219980ms step_avg:138.27ms
step:1602/5100 train_loss:3.9394 train_time:220117ms step_avg:138.26ms
step:1603/5100 train_loss:3.8408 train_time:220257ms step_avg:138.27ms
step:1604/5100 train_loss:3.6498 train_time:220393ms step_avg:138.26ms
step:1605/5100 train_loss:3.6580 train_time:220533ms step_avg:138.27ms
step:1606/5100 train_loss:3.5359 train_time:220671ms step_avg:138.27ms
step:1607/5100 train_loss:3.8577 train_time:220807ms step_avg:138.26ms
step:1608/5100 train_loss:3.6545 train_time:220941ms step_avg:138.26ms
step:1609/5100 train_loss:3.6868 train_time:221082ms step_avg:138.26ms
step:1610/5100 train_loss:3.6365 train_time:221219ms step_avg:138.26ms
step:1611/5100 train_loss:4.2278 train_time:221357ms step_avg:138.26ms
step:1612/5100 train_loss:3.8693 train_time:221495ms step_avg:138.26ms
step:1613/5100 train_loss:3.7991 train_time:221631ms step_avg:138.26ms
step:1614/5100 train_loss:3.6608 train_time:221769ms step_avg:138.26ms
step:1615/5100 train_loss:3.7153 train_time:221904ms step_avg:138.26ms
step:1616/5100 train_loss:3.6850 train_time:222041ms step_avg:138.26ms
step:1617/5100 train_loss:3.6387 train_time:222180ms step_avg:138.26ms
step:1618/5100 train_loss:3.7336 train_time:222317ms step_avg:138.26ms
step:1619/5100 train_loss:3.6859 train_time:222455ms step_avg:138.26ms
step:1620/5100 train_loss:3.5747 train_time:222593ms step_avg:138.26ms
step:1621/5100 train_loss:3.8490 train_time:222731ms step_avg:138.26ms
step:1622/5100 train_loss:3.7354 train_time:222867ms step_avg:138.25ms
step:1623/5100 train_loss:3.5401 train_time:223002ms step_avg:138.25ms
step:1624/5100 train_loss:3.6451 train_time:223139ms step_avg:138.25ms
step:1625/5100 train_loss:3.6256 train_time:223279ms step_avg:138.25ms
step:1625/5100 val_loss:3.6826 train_time:223350ms step_avg:138.30ms
step:1626/5100 train_loss:3.6876 train_time:223420ms step_avg:138.26ms
step:1627/5100 train_loss:3.6526 train_time:223569ms step_avg:138.26ms
step:1628/5100 train_loss:3.6156 train_time:223705ms step_avg:138.26ms
step:1629/5100 train_loss:3.7234 train_time:223840ms step_avg:138.26ms
step:1630/5100 train_loss:3.6256 train_time:223975ms step_avg:138.26ms
step:1631/5100 train_loss:3.6740 train_time:224109ms step_avg:138.25ms
step:1632/5100 train_loss:3.5433 train_time:224243ms step_avg:138.25ms
step:1633/5100 train_loss:3.5250 train_time:224381ms step_avg:138.25ms
step:1634/5100 train_loss:3.6948 train_time:224523ms step_avg:138.25ms
step:1635/5100 train_loss:3.6724 train_time:224664ms step_avg:138.25ms
step:1636/5100 train_loss:3.6086 train_time:224801ms step_avg:138.25ms
step:1637/5100 train_loss:3.7027 train_time:224937ms step_avg:138.25ms
step:1638/5100 train_loss:3.7536 train_time:225072ms step_avg:138.25ms
step:1639/5100 train_loss:3.7778 train_time:225205ms step_avg:138.25ms
step:1640/5100 train_loss:3.9358 train_time:225342ms step_avg:138.25ms
step:1641/5100 train_loss:3.7752 train_time:225481ms step_avg:138.25ms
step:1642/5100 train_loss:3.6785 train_time:225621ms step_avg:138.25ms
step:1643/5100 train_loss:3.7555 train_time:225758ms step_avg:138.25ms
step:1644/5100 train_loss:3.6523 train_time:225896ms step_avg:138.25ms
step:1645/5100 train_loss:3.6774 train_time:226031ms step_avg:138.25ms
step:1646/5100 train_loss:3.6822 train_time:226166ms step_avg:138.24ms
step:1647/5100 train_loss:3.4635 train_time:226302ms step_avg:138.24ms
step:1648/5100 train_loss:3.7205 train_time:226441ms step_avg:138.24ms
step:1649/5100 train_loss:3.5776 train_time:226579ms step_avg:138.24ms
step:1650/5100 train_loss:3.6525 train_time:226718ms step_avg:138.24ms
step:1651/5100 train_loss:3.6271 train_time:226856ms step_avg:138.24ms
step:1652/5100 train_loss:3.6950 train_time:226993ms step_avg:138.24ms
step:1653/5100 train_loss:3.6389 train_time:227129ms step_avg:138.24ms
step:1654/5100 train_loss:3.7676 train_time:227265ms step_avg:138.24ms
step:1655/5100 train_loss:3.7514 train_time:227402ms step_avg:138.24ms
step:1656/5100 train_loss:3.5597 train_time:227540ms step_avg:138.24ms
step:1657/5100 train_loss:3.7093 train_time:227678ms step_avg:138.24ms
step:1658/5100 train_loss:3.6218 train_time:227816ms step_avg:138.24ms
step:1659/5100 train_loss:3.6022 train_time:227953ms step_avg:138.24ms
step:1660/5100 train_loss:3.6836 train_time:228088ms step_avg:138.24ms
step:1661/5100 train_loss:3.7044 train_time:228225ms step_avg:138.23ms
step:1662/5100 train_loss:3.6293 train_time:228363ms step_avg:138.23ms
step:1663/5100 train_loss:3.7173 train_time:228501ms step_avg:138.23ms
step:1664/5100 train_loss:3.7268 train_time:228639ms step_avg:138.23ms
step:1665/5100 train_loss:3.7537 train_time:228770ms step_avg:138.23ms
step:1666/5100 train_loss:3.7530 train_time:228912ms step_avg:138.23ms
step:1667/5100 train_loss:3.8724 train_time:229048ms step_avg:138.23ms
step:1668/5100 train_loss:3.5954 train_time:229185ms step_avg:138.23ms
step:1669/5100 train_loss:3.6653 train_time:229323ms step_avg:138.23ms
step:1670/5100 train_loss:3.6020 train_time:229462ms step_avg:138.23ms
step:1671/5100 train_loss:3.5891 train_time:229599ms step_avg:138.23ms
step:1672/5100 train_loss:3.7532 train_time:229736ms step_avg:138.23ms
step:1673/5100 train_loss:3.9210 train_time:229871ms step_avg:138.23ms
step:1674/5100 train_loss:3.6538 train_time:230006ms step_avg:138.22ms
step:1675/5100 train_loss:3.6331 train_time:230145ms step_avg:138.23ms
step:1676/5100 train_loss:3.5186 train_time:230282ms step_avg:138.22ms
step:1677/5100 train_loss:3.7233 train_time:230418ms step_avg:138.22ms
step:1678/5100 train_loss:3.6331 train_time:230555ms step_avg:138.22ms
step:1679/5100 train_loss:3.6744 train_time:230693ms step_avg:138.22ms
step:1680/5100 train_loss:3.6476 train_time:230827ms step_avg:138.22ms
step:1681/5100 train_loss:3.4824 train_time:230965ms step_avg:138.22ms
step:1682/5100 train_loss:3.6539 train_time:231102ms step_avg:138.22ms
step:1683/5100 train_loss:3.6670 train_time:231239ms step_avg:138.22ms
step:1684/5100 train_loss:3.7009 train_time:231377ms step_avg:138.22ms
step:1685/5100 train_loss:3.7126 train_time:231515ms step_avg:138.22ms
step:1686/5100 train_loss:3.6214 train_time:231651ms step_avg:138.22ms
step:1687/5100 train_loss:3.7196 train_time:231788ms step_avg:138.22ms
step:1688/5100 train_loss:3.6047 train_time:231923ms step_avg:138.21ms
step:1689/5100 train_loss:3.6929 train_time:232061ms step_avg:138.21ms
step:1690/5100 train_loss:3.6068 train_time:232199ms step_avg:138.21ms
step:1691/5100 train_loss:3.5209 train_time:232339ms step_avg:138.21ms
step:1692/5100 train_loss:3.6614 train_time:232474ms step_avg:138.21ms
step:1693/5100 train_loss:3.6495 train_time:232610ms step_avg:138.21ms
step:1694/5100 train_loss:3.5677 train_time:232747ms step_avg:138.21ms
step:1695/5100 train_loss:4.0190 train_time:232884ms step_avg:138.21ms
step:1696/5100 train_loss:3.7305 train_time:233022ms step_avg:138.21ms
step:1697/5100 train_loss:3.7133 train_time:233160ms step_avg:138.21ms
step:1698/5100 train_loss:3.6177 train_time:233298ms step_avg:138.21ms
step:1699/5100 train_loss:3.5669 train_time:233436ms step_avg:138.21ms
step:1700/5100 train_loss:3.6270 train_time:233573ms step_avg:138.21ms
step:1701/5100 train_loss:3.6058 train_time:233809ms step_avg:138.27ms
step:1702/5100 train_loss:3.6860 train_time:233939ms step_avg:138.26ms
step:1703/5100 train_loss:3.6121 train_time:234073ms step_avg:138.26ms
step:1704/5100 train_loss:3.8170 train_time:234207ms step_avg:138.26ms
step:1705/5100 train_loss:3.5780 train_time:234342ms step_avg:138.25ms
step:1706/5100 train_loss:3.7995 train_time:234477ms step_avg:138.25ms
step:1707/5100 train_loss:3.6569 train_time:234612ms step_avg:138.25ms
step:1708/5100 train_loss:3.4121 train_time:234753ms step_avg:138.25ms
step:1709/5100 train_loss:3.7602 train_time:234893ms step_avg:138.25ms
step:1710/5100 train_loss:3.6797 train_time:235199ms step_avg:138.35ms
step:1711/5100 train_loss:3.6724 train_time:235331ms step_avg:138.35ms
step:1712/5100 train_loss:3.6478 train_time:235465ms step_avg:138.35ms
step:1713/5100 train_loss:3.6961 train_time:235599ms step_avg:138.34ms
step:1714/5100 train_loss:3.7280 train_time:235734ms step_avg:138.34ms
step:1715/5100 train_loss:3.6540 train_time:235868ms step_avg:138.34ms
step:1716/5100 train_loss:3.6263 train_time:236006ms step_avg:138.34ms
step:1717/5100 train_loss:3.4838 train_time:236141ms step_avg:138.34ms
step:1718/5100 train_loss:3.6144 train_time:236286ms step_avg:138.34ms
step:1719/5100 train_loss:3.6421 train_time:236424ms step_avg:138.34ms
step:1720/5100 train_loss:3.5817 train_time:236562ms step_avg:138.34ms
step:1721/5100 train_loss:3.7346 train_time:236698ms step_avg:138.34ms
step:1722/5100 train_loss:3.5569 train_time:236834ms step_avg:138.34ms
step:1723/5100 train_loss:3.6918 train_time:236969ms step_avg:138.34ms
step:1724/5100 train_loss:3.7706 train_time:237105ms step_avg:138.33ms
step:1725/5100 train_loss:3.6251 train_time:237247ms step_avg:138.34ms
step:1726/5100 train_loss:3.8558 train_time:237385ms step_avg:138.34ms
step:1727/5100 train_loss:3.6409 train_time:237523ms step_avg:138.34ms
step:1728/5100 train_loss:3.6956 train_time:237661ms step_avg:138.34ms
step:1729/5100 train_loss:3.6736 train_time:237798ms step_avg:138.33ms
step:1730/5100 train_loss:3.6808 train_time:237936ms step_avg:138.33ms
step:1731/5100 train_loss:4.0517 train_time:238070ms step_avg:138.33ms
step:1732/5100 train_loss:3.6581 train_time:238207ms step_avg:138.33ms
step:1733/5100 train_loss:3.7907 train_time:238346ms step_avg:138.33ms
step:1734/5100 train_loss:3.5708 train_time:238485ms step_avg:138.33ms
step:1735/5100 train_loss:3.6095 train_time:238622ms step_avg:138.33ms
step:1736/5100 train_loss:3.6373 train_time:238761ms step_avg:138.33ms
step:1737/5100 train_loss:3.6144 train_time:238897ms step_avg:138.33ms
step:1738/5100 train_loss:3.7625 train_time:239034ms step_avg:138.33ms
step:1739/5100 train_loss:3.6262 train_time:239170ms step_avg:138.33ms
step:1740/5100 train_loss:3.6977 train_time:239309ms step_avg:138.33ms
step:1741/5100 train_loss:3.7379 train_time:239448ms step_avg:138.33ms
step:1742/5100 train_loss:3.5354 train_time:239585ms step_avg:138.33ms
step:1743/5100 train_loss:3.4205 train_time:239723ms step_avg:138.33ms
step:1744/5100 train_loss:3.3731 train_time:239860ms step_avg:138.33ms
step:1745/5100 train_loss:3.6609 train_time:239997ms step_avg:138.33ms
step:1746/5100 train_loss:3.6706 train_time:240134ms step_avg:138.33ms
step:1747/5100 train_loss:3.6502 train_time:240268ms step_avg:138.32ms
step:1748/5100 train_loss:3.6309 train_time:240405ms step_avg:138.32ms
step:1749/5100 train_loss:3.9010 train_time:240543ms step_avg:138.32ms
step:1750/5100 train_loss:3.6077 train_time:240681ms step_avg:138.32ms
step:1750/5100 val_loss:3.6573 train_time:240754ms step_avg:138.36ms
step:1751/5100 train_loss:3.6878 train_time:240827ms step_avg:138.33ms
step:1752/5100 train_loss:3.6567 train_time:240966ms step_avg:138.33ms
step:1753/5100 train_loss:3.3063 train_time:241103ms step_avg:138.33ms
step:1754/5100 train_loss:3.4239 train_time:241238ms step_avg:138.32ms
step:1755/5100 train_loss:3.5256 train_time:241374ms step_avg:138.32ms
step:1756/5100 train_loss:3.4637 train_time:241509ms step_avg:138.32ms
step:1757/5100 train_loss:3.6277 train_time:241644ms step_avg:138.32ms
step:1758/5100 train_loss:3.5162 train_time:241787ms step_avg:138.32ms
step:1759/5100 train_loss:3.5006 train_time:241926ms step_avg:138.32ms
step:1760/5100 train_loss:4.5587 train_time:242063ms step_avg:138.32ms
step:1761/5100 train_loss:3.6267 train_time:242201ms step_avg:138.32ms
step:1762/5100 train_loss:3.6731 train_time:242337ms step_avg:138.32ms
step:1763/5100 train_loss:3.6826 train_time:242474ms step_avg:138.32ms
step:1764/5100 train_loss:3.7082 train_time:242611ms step_avg:138.32ms
step:1765/5100 train_loss:3.6126 train_time:242745ms step_avg:138.32ms
step:1766/5100 train_loss:3.6397 train_time:242883ms step_avg:138.32ms
step:1767/5100 train_loss:3.6652 train_time:243023ms step_avg:138.32ms
step:1768/5100 train_loss:3.9231 train_time:243160ms step_avg:138.32ms
step:1769/5100 train_loss:3.6444 train_time:243297ms step_avg:138.32ms
step:1770/5100 train_loss:3.7153 train_time:243435ms step_avg:138.32ms
step:1771/5100 train_loss:4.1324 train_time:243573ms step_avg:138.32ms
step:1772/5100 train_loss:3.6743 train_time:243709ms step_avg:138.31ms
step:1773/5100 train_loss:3.5640 train_time:243846ms step_avg:138.31ms
step:1774/5100 train_loss:3.8214 train_time:243982ms step_avg:138.31ms
step:1775/5100 train_loss:3.5159 train_time:244120ms step_avg:138.31ms
step:1776/5100 train_loss:3.7009 train_time:244259ms step_avg:138.31ms
step:1777/5100 train_loss:3.7617 train_time:244397ms step_avg:138.31ms
step:1778/5100 train_loss:3.8492 train_time:244535ms step_avg:138.31ms
step:1779/5100 train_loss:3.6671 train_time:244675ms step_avg:138.31ms
step:1780/5100 train_loss:3.9548 train_time:244812ms step_avg:138.31ms
step:1781/5100 train_loss:3.7317 train_time:244947ms step_avg:138.31ms
step:1782/5100 train_loss:3.7398 train_time:245084ms step_avg:138.31ms
step:1783/5100 train_loss:3.5297 train_time:245223ms step_avg:138.31ms
step:1784/5100 train_loss:3.6011 train_time:245360ms step_avg:138.31ms
step:1785/5100 train_loss:3.7461 train_time:245498ms step_avg:138.31ms
step:1786/5100 train_loss:3.6374 train_time:245636ms step_avg:138.31ms
step:1787/5100 train_loss:3.8094 train_time:245775ms step_avg:138.31ms
step:1788/5100 train_loss:3.6359 train_time:245912ms step_avg:138.31ms
step:1789/5100 train_loss:3.5978 train_time:246047ms step_avg:138.31ms
step:1790/5100 train_loss:3.7483 train_time:246181ms step_avg:138.30ms
step:1791/5100 train_loss:3.6313 train_time:246320ms step_avg:138.30ms
step:1792/5100 train_loss:3.5917 train_time:246458ms step_avg:138.30ms
step:1793/5100 train_loss:3.7170 train_time:246597ms step_avg:138.30ms
step:1794/5100 train_loss:3.5962 train_time:246737ms step_avg:138.31ms
step:1795/5100 train_loss:3.5879 train_time:246874ms step_avg:138.31ms
step:1796/5100 train_loss:3.6393 train_time:247012ms step_avg:138.30ms
step:1797/5100 train_loss:3.6196 train_time:247148ms step_avg:138.30ms
step:1798/5100 train_loss:3.7403 train_time:247283ms step_avg:138.30ms
step:1799/5100 train_loss:3.6292 train_time:247422ms step_avg:138.30ms
step:1800/5100 train_loss:3.7019 train_time:247560ms step_avg:138.30ms
step:1801/5100 train_loss:3.6413 train_time:247698ms step_avg:138.30ms
step:1802/5100 train_loss:3.6665 train_time:247836ms step_avg:138.30ms
step:1803/5100 train_loss:3.6141 train_time:247975ms step_avg:138.30ms
step:1804/5100 train_loss:3.5183 train_time:248112ms step_avg:138.30ms
step:1805/5100 train_loss:3.7580 train_time:248248ms step_avg:138.30ms
step:1806/5100 train_loss:3.6907 train_time:248385ms step_avg:138.30ms
step:1807/5100 train_loss:3.6822 train_time:248527ms step_avg:138.30ms
step:1808/5100 train_loss:3.8045 train_time:248662ms step_avg:138.30ms
step:1809/5100 train_loss:3.5981 train_time:248800ms step_avg:138.30ms
step:1810/5100 train_loss:3.7047 train_time:248940ms step_avg:138.30ms
step:1811/5100 train_loss:3.8385 train_time:249086ms step_avg:138.30ms
step:1812/5100 train_loss:3.7000 train_time:249216ms step_avg:138.30ms
step:1813/5100 train_loss:3.7344 train_time:249353ms step_avg:138.30ms
step:1814/5100 train_loss:3.7536 train_time:249489ms step_avg:138.30ms
step:1815/5100 train_loss:3.6967 train_time:249625ms step_avg:138.30ms
step:1816/5100 train_loss:3.7384 train_time:249763ms step_avg:138.30ms
step:1817/5100 train_loss:3.6925 train_time:249901ms step_avg:138.30ms
step:1818/5100 train_loss:3.7385 train_time:250039ms step_avg:138.30ms
step:1819/5100 train_loss:3.6694 train_time:250177ms step_avg:138.30ms
step:1820/5100 train_loss:3.6703 train_time:250314ms step_avg:138.29ms
step:1821/5100 train_loss:3.6018 train_time:250450ms step_avg:138.29ms
step:1822/5100 train_loss:3.5874 train_time:250586ms step_avg:138.29ms
step:1823/5100 train_loss:3.5049 train_time:250723ms step_avg:138.29ms
step:1824/5100 train_loss:3.6719 train_time:250860ms step_avg:138.29ms
step:1825/5100 train_loss:3.7823 train_time:250999ms step_avg:138.29ms
step:1826/5100 train_loss:3.7447 train_time:251138ms step_avg:138.29ms
step:1827/5100 train_loss:3.7283 train_time:251277ms step_avg:138.29ms
step:1828/5100 train_loss:3.5900 train_time:251414ms step_avg:138.29ms
step:1829/5100 train_loss:3.6262 train_time:251552ms step_avg:138.29ms
step:1830/5100 train_loss:3.7444 train_time:251687ms step_avg:138.29ms
step:1831/5100 train_loss:3.5307 train_time:251823ms step_avg:138.29ms
step:1832/5100 train_loss:3.6794 train_time:251963ms step_avg:138.29ms
step:1833/5100 train_loss:3.5621 train_time:252099ms step_avg:138.29ms
step:1834/5100 train_loss:3.8817 train_time:252237ms step_avg:138.29ms
step:1835/5100 train_loss:3.7201 train_time:252376ms step_avg:138.29ms
step:1836/5100 train_loss:3.6999 train_time:252515ms step_avg:138.29ms
step:1837/5100 train_loss:3.8168 train_time:252650ms step_avg:138.29ms
step:1838/5100 train_loss:3.6837 train_time:252783ms step_avg:138.28ms
step:1839/5100 train_loss:3.5504 train_time:252921ms step_avg:138.28ms
step:1840/5100 train_loss:3.6840 train_time:253060ms step_avg:138.28ms
step:1841/5100 train_loss:3.5618 train_time:253199ms step_avg:138.28ms
step:1842/5100 train_loss:3.6763 train_time:253337ms step_avg:138.28ms
step:1843/5100 train_loss:3.7396 train_time:253475ms step_avg:138.28ms
step:1844/5100 train_loss:3.5081 train_time:253615ms step_avg:138.28ms
step:1845/5100 train_loss:3.6089 train_time:253751ms step_avg:138.28ms
step:1846/5100 train_loss:3.6481 train_time:253887ms step_avg:138.28ms
step:1847/5100 train_loss:3.6126 train_time:254023ms step_avg:138.28ms
step:1848/5100 train_loss:3.4987 train_time:254161ms step_avg:138.28ms
step:1849/5100 train_loss:3.7656 train_time:254299ms step_avg:138.28ms
step:1850/5100 train_loss:3.5402 train_time:254437ms step_avg:138.28ms
step:1851/5100 train_loss:3.6277 train_time:254576ms step_avg:138.28ms
step:1852/5100 train_loss:3.5839 train_time:254714ms step_avg:138.28ms
step:1853/5100 train_loss:3.7793 train_time:254852ms step_avg:138.28ms
step:1854/5100 train_loss:3.7483 train_time:254988ms step_avg:138.28ms
step:1855/5100 train_loss:3.6297 train_time:255124ms step_avg:138.28ms
step:1856/5100 train_loss:3.5778 train_time:255262ms step_avg:138.28ms
step:1857/5100 train_loss:3.6184 train_time:255400ms step_avg:138.28ms
step:1858/5100 train_loss:3.8507 train_time:255538ms step_avg:138.28ms
step:1859/5100 train_loss:3.6944 train_time:255676ms step_avg:138.28ms
step:1860/5100 train_loss:3.6452 train_time:255815ms step_avg:138.28ms
step:1861/5100 train_loss:3.6805 train_time:255952ms step_avg:138.28ms
step:1862/5100 train_loss:3.5733 train_time:256086ms step_avg:138.28ms
step:1863/5100 train_loss:3.5734 train_time:256224ms step_avg:138.28ms
step:1864/5100 train_loss:3.6410 train_time:256364ms step_avg:138.28ms
step:1865/5100 train_loss:3.6765 train_time:256502ms step_avg:138.28ms
step:1866/5100 train_loss:3.4405 train_time:256641ms step_avg:138.28ms
step:1867/5100 train_loss:3.5663 train_time:256780ms step_avg:138.28ms
step:1868/5100 train_loss:3.5210 train_time:256918ms step_avg:138.28ms
step:1869/5100 train_loss:3.5238 train_time:257055ms step_avg:138.28ms
step:1870/5100 train_loss:3.6959 train_time:257193ms step_avg:138.28ms
step:1871/5100 train_loss:3.6778 train_time:257328ms step_avg:138.27ms
step:1872/5100 train_loss:3.6255 train_time:257463ms step_avg:138.27ms
step:1873/5100 train_loss:3.6297 train_time:257602ms step_avg:138.27ms
step:1874/5100 train_loss:3.5676 train_time:257740ms step_avg:138.27ms
step:1875/5100 train_loss:3.6649 train_time:257878ms step_avg:138.27ms
step:1875/5100 val_loss:3.6385 train_time:257951ms step_avg:138.31ms
step:1876/5100 train_loss:3.6696 train_time:258021ms step_avg:138.27ms
step:1877/5100 train_loss:3.5899 train_time:258168ms step_avg:138.28ms
step:1878/5100 train_loss:3.6363 train_time:258304ms step_avg:138.28ms
step:1879/5100 train_loss:3.7478 train_time:258441ms step_avg:138.28ms
step:1880/5100 train_loss:3.6152 train_time:258575ms step_avg:138.28ms
step:1881/5100 train_loss:3.6726 train_time:258711ms step_avg:138.27ms
step:1882/5100 train_loss:3.5851 train_time:258845ms step_avg:138.27ms
step:1883/5100 train_loss:3.6563 train_time:258983ms step_avg:138.27ms
step:1884/5100 train_loss:3.6630 train_time:259123ms step_avg:138.27ms
step:1885/5100 train_loss:3.4029 train_time:259262ms step_avg:138.27ms
step:1886/5100 train_loss:3.8108 train_time:259401ms step_avg:138.27ms
step:1887/5100 train_loss:3.5376 train_time:259537ms step_avg:138.27ms
step:1888/5100 train_loss:3.5685 train_time:259673ms step_avg:138.27ms
step:1889/5100 train_loss:3.6258 train_time:259809ms step_avg:138.27ms
step:1890/5100 train_loss:3.6775 train_time:260044ms step_avg:138.32ms
step:1891/5100 train_loss:3.5101 train_time:260177ms step_avg:138.32ms
step:1892/5100 train_loss:3.7751 train_time:260311ms step_avg:138.32ms
step:1893/5100 train_loss:3.5320 train_time:260447ms step_avg:138.31ms
step:1894/5100 train_loss:3.6540 train_time:260581ms step_avg:138.31ms
step:1895/5100 train_loss:3.7104 train_time:260715ms step_avg:138.31ms
step:1896/5100 train_loss:3.5071 train_time:260850ms step_avg:138.31ms
step:1897/5100 train_loss:3.6628 train_time:260993ms step_avg:138.31ms
step:1898/5100 train_loss:3.6403 train_time:261133ms step_avg:138.31ms
step:1899/5100 train_loss:3.7069 train_time:261272ms step_avg:138.31ms
step:1900/5100 train_loss:3.4843 train_time:261591ms step_avg:138.41ms
step:1901/5100 train_loss:3.7275 train_time:261723ms step_avg:138.40ms
step:1902/5100 train_loss:3.6140 train_time:261859ms step_avg:138.40ms
step:1903/5100 train_loss:3.7729 train_time:261993ms step_avg:138.40ms
step:1904/5100 train_loss:3.5760 train_time:262128ms step_avg:138.40ms
step:1905/5100 train_loss:3.8585 train_time:262262ms step_avg:138.40ms
step:1906/5100 train_loss:3.5877 train_time:262396ms step_avg:138.39ms
step:1907/5100 train_loss:3.5812 train_time:262533ms step_avg:138.39ms
step:1908/5100 train_loss:3.6675 train_time:262676ms step_avg:138.40ms
step:1909/5100 train_loss:3.5469 train_time:262816ms step_avg:138.40ms
step:1910/5100 train_loss:3.6109 train_time:262953ms step_avg:138.40ms
step:1911/5100 train_loss:3.7094 train_time:263090ms step_avg:138.40ms
step:1912/5100 train_loss:3.6240 train_time:263223ms step_avg:138.39ms
step:1913/5100 train_loss:3.4994 train_time:263358ms step_avg:138.39ms
step:1914/5100 train_loss:3.3752 train_time:263496ms step_avg:138.39ms
step:1915/5100 train_loss:3.5831 train_time:263636ms step_avg:138.39ms
step:1916/5100 train_loss:3.8024 train_time:263775ms step_avg:138.39ms
step:1917/5100 train_loss:3.7961 train_time:263914ms step_avg:138.39ms
step:1918/5100 train_loss:3.7434 train_time:264050ms step_avg:138.39ms
step:1919/5100 train_loss:3.5929 train_time:264185ms step_avg:138.39ms
step:1920/5100 train_loss:3.8172 train_time:264322ms step_avg:138.39ms
step:1921/5100 train_loss:3.6428 train_time:264458ms step_avg:138.39ms
step:1922/5100 train_loss:3.5646 train_time:264596ms step_avg:138.39ms
step:1923/5100 train_loss:3.7529 train_time:264735ms step_avg:138.39ms
step:1924/5100 train_loss:3.7180 train_time:264874ms step_avg:138.39ms
step:1925/5100 train_loss:3.5484 train_time:265013ms step_avg:138.39ms
step:1926/5100 train_loss:3.5911 train_time:265149ms step_avg:138.39ms
step:1927/5100 train_loss:3.5025 train_time:265284ms step_avg:138.38ms
step:1928/5100 train_loss:3.5958 train_time:265419ms step_avg:138.38ms
step:1929/5100 train_loss:3.4764 train_time:265559ms step_avg:138.38ms
step:1930/5100 train_loss:3.5697 train_time:265696ms step_avg:138.38ms
step:1931/5100 train_loss:3.7031 train_time:265833ms step_avg:138.38ms
step:1932/5100 train_loss:3.5837 train_time:265973ms step_avg:138.38ms
step:1933/5100 train_loss:3.7184 train_time:266111ms step_avg:138.38ms
step:1934/5100 train_loss:3.6039 train_time:266248ms step_avg:138.38ms
step:1935/5100 train_loss:3.6385 train_time:266382ms step_avg:138.38ms
step:1936/5100 train_loss:3.6815 train_time:266520ms step_avg:138.38ms
step:1937/5100 train_loss:3.6391 train_time:266658ms step_avg:138.38ms
step:1938/5100 train_loss:3.6607 train_time:266796ms step_avg:138.38ms
step:1939/5100 train_loss:3.5876 train_time:266934ms step_avg:138.38ms
step:1940/5100 train_loss:3.6901 train_time:267072ms step_avg:138.38ms
step:1941/5100 train_loss:3.7115 train_time:267210ms step_avg:138.38ms
step:1942/5100 train_loss:3.5494 train_time:267344ms step_avg:138.38ms
step:1943/5100 train_loss:3.5843 train_time:267480ms step_avg:138.38ms
step:1944/5100 train_loss:3.6556 train_time:267617ms step_avg:138.37ms
step:1945/5100 train_loss:3.5017 train_time:267755ms step_avg:138.37ms
step:1946/5100 train_loss:3.7646 train_time:267894ms step_avg:138.38ms
step:1947/5100 train_loss:3.6421 train_time:268033ms step_avg:138.38ms
step:1948/5100 train_loss:3.6239 train_time:268172ms step_avg:138.38ms
step:1949/5100 train_loss:3.6253 train_time:268309ms step_avg:138.37ms
step:1950/5100 train_loss:3.5093 train_time:268445ms step_avg:138.37ms
step:1951/5100 train_loss:3.6245 train_time:268582ms step_avg:138.37ms
step:1952/5100 train_loss:3.4696 train_time:268720ms step_avg:138.37ms
step:1953/5100 train_loss:3.6757 train_time:268858ms step_avg:138.37ms
step:1954/5100 train_loss:3.6807 train_time:268998ms step_avg:138.37ms
step:1955/5100 train_loss:3.6306 train_time:269136ms step_avg:138.37ms
step:1956/5100 train_loss:3.5197 train_time:269274ms step_avg:138.37ms
step:1957/5100 train_loss:3.6051 train_time:269411ms step_avg:138.37ms
step:1958/5100 train_loss:3.7895 train_time:269546ms step_avg:138.37ms
step:1959/5100 train_loss:3.7087 train_time:269680ms step_avg:138.37ms
step:1960/5100 train_loss:3.7291 train_time:269818ms step_avg:138.37ms
step:1961/5100 train_loss:3.5295 train_time:269958ms step_avg:138.37ms
step:1962/5100 train_loss:3.6448 train_time:270097ms step_avg:138.37ms
step:1963/5100 train_loss:3.6863 train_time:270235ms step_avg:138.37ms
step:1964/5100 train_loss:3.6479 train_time:270373ms step_avg:138.37ms
step:1965/5100 train_loss:3.5453 train_time:270510ms step_avg:138.37ms
step:1966/5100 train_loss:3.9500 train_time:270644ms step_avg:138.37ms
step:1967/5100 train_loss:3.5764 train_time:270780ms step_avg:138.36ms
step:1968/5100 train_loss:3.5961 train_time:270919ms step_avg:138.37ms
step:1969/5100 train_loss:3.6512 train_time:271058ms step_avg:138.37ms
step:1970/5100 train_loss:3.6139 train_time:271196ms step_avg:138.37ms
step:1971/5100 train_loss:3.4996 train_time:271335ms step_avg:138.37ms
step:1972/5100 train_loss:3.4830 train_time:271473ms step_avg:138.37ms
step:1973/5100 train_loss:3.6035 train_time:271610ms step_avg:138.36ms
step:1974/5100 train_loss:3.5879 train_time:271745ms step_avg:138.36ms
step:1975/5100 train_loss:3.5433 train_time:271880ms step_avg:138.36ms
step:1976/5100 train_loss:3.6989 train_time:272020ms step_avg:138.36ms
step:1977/5100 train_loss:3.5697 train_time:272160ms step_avg:138.36ms
step:1978/5100 train_loss:3.9498 train_time:272298ms step_avg:138.36ms
step:1979/5100 train_loss:3.6354 train_time:272436ms step_avg:138.36ms
step:1980/5100 train_loss:3.6260 train_time:272573ms step_avg:138.36ms
step:1981/5100 train_loss:3.6280 train_time:272710ms step_avg:138.36ms
step:1982/5100 train_loss:3.6576 train_time:272846ms step_avg:138.36ms
step:1983/5100 train_loss:3.5848 train_time:272981ms step_avg:138.36ms
step:1984/5100 train_loss:3.5549 train_time:273119ms step_avg:138.36ms
step:1985/5100 train_loss:3.6072 train_time:273258ms step_avg:138.36ms
step:1986/5100 train_loss:3.6693 train_time:273396ms step_avg:138.36ms
step:1987/5100 train_loss:3.6449 train_time:273536ms step_avg:138.36ms
step:1988/5100 train_loss:3.6118 train_time:273673ms step_avg:138.36ms
step:1989/5100 train_loss:3.6955 train_time:273812ms step_avg:138.36ms
step:1990/5100 train_loss:3.7359 train_time:273949ms step_avg:138.36ms
step:1991/5100 train_loss:3.4949 train_time:274083ms step_avg:138.36ms
step:1992/5100 train_loss:3.5120 train_time:274222ms step_avg:138.36ms
step:1993/5100 train_loss:3.6973 train_time:274359ms step_avg:138.36ms
step:1994/5100 train_loss:3.5074 train_time:274498ms step_avg:138.36ms
step:1995/5100 train_loss:3.6126 train_time:274636ms step_avg:138.36ms
step:1996/5100 train_loss:3.6799 train_time:274776ms step_avg:138.36ms
step:1997/5100 train_loss:3.5432 train_time:274912ms step_avg:138.36ms
step:1998/5100 train_loss:3.6490 train_time:275049ms step_avg:138.35ms
step:1999/5100 train_loss:3.6518 train_time:275186ms step_avg:138.35ms
step:2000/5100 train_loss:3.5692 train_time:275321ms step_avg:138.35ms
step:2000/5100 val_loss:3.6210 train_time:275394ms step_avg:138.39ms
step:2001/5100 train_loss:3.7115 train_time:275466ms step_avg:138.36ms
step:2002/5100 train_loss:3.6614 train_time:275611ms step_avg:138.36ms
step:2003/5100 train_loss:3.7372 train_time:275750ms step_avg:138.36ms
step:2004/5100 train_loss:3.6549 train_time:275884ms step_avg:138.36ms
step:2005/5100 train_loss:3.6884 train_time:276021ms step_avg:138.36ms
step:2006/5100 train_loss:3.5646 train_time:276149ms step_avg:138.35ms
step:2007/5100 train_loss:3.5923 train_time:276287ms step_avg:138.35ms
step:2008/5100 train_loss:3.6195 train_time:276427ms step_avg:138.35ms
step:2009/5100 train_loss:3.6671 train_time:276567ms step_avg:138.35ms
step:2010/5100 train_loss:3.5815 train_time:276707ms step_avg:138.35ms
step:2011/5100 train_loss:3.6596 train_time:276845ms step_avg:138.35ms
step:2012/5100 train_loss:3.6246 train_time:276983ms step_avg:138.35ms
step:2013/5100 train_loss:3.6375 train_time:277121ms step_avg:138.35ms
step:2014/5100 train_loss:3.5597 train_time:277257ms step_avg:138.35ms
step:2015/5100 train_loss:3.6073 train_time:277392ms step_avg:138.35ms
step:2016/5100 train_loss:3.6126 train_time:277530ms step_avg:138.35ms
step:2017/5100 train_loss:3.7492 train_time:277670ms step_avg:138.35ms
step:2018/5100 train_loss:3.5931 train_time:277808ms step_avg:138.35ms
step:2019/5100 train_loss:3.7497 train_time:277947ms step_avg:138.35ms
step:2020/5100 train_loss:3.7478 train_time:278086ms step_avg:138.35ms
step:2021/5100 train_loss:3.4888 train_time:278223ms step_avg:138.35ms
step:2022/5100 train_loss:3.7020 train_time:278359ms step_avg:138.35ms
step:2023/5100 train_loss:3.6159 train_time:278496ms step_avg:138.35ms
step:2024/5100 train_loss:3.7105 train_time:278632ms step_avg:138.35ms
step:2025/5100 train_loss:3.7675 train_time:278770ms step_avg:138.35ms
step:2026/5100 train_loss:3.5453 train_time:278908ms step_avg:138.35ms
step:2027/5100 train_loss:3.5902 train_time:279048ms step_avg:138.35ms
step:2028/5100 train_loss:3.4885 train_time:279185ms step_avg:138.35ms
step:2029/5100 train_loss:3.6032 train_time:279326ms step_avg:138.35ms
step:2030/5100 train_loss:3.5224 train_time:279461ms step_avg:138.35ms
step:2031/5100 train_loss:3.6117 train_time:279598ms step_avg:138.35ms
step:2032/5100 train_loss:3.6052 train_time:279735ms step_avg:138.35ms
step:2033/5100 train_loss:3.6230 train_time:279872ms step_avg:138.34ms
step:2034/5100 train_loss:3.5248 train_time:280010ms step_avg:138.34ms
step:2035/5100 train_loss:3.6798 train_time:280148ms step_avg:138.34ms
step:2036/5100 train_loss:3.6758 train_time:280286ms step_avg:138.34ms
step:2037/5100 train_loss:3.6652 train_time:280424ms step_avg:138.34ms
step:2038/5100 train_loss:3.5299 train_time:280562ms step_avg:138.34ms
step:2039/5100 train_loss:3.7958 train_time:280700ms step_avg:138.34ms
step:2040/5100 train_loss:3.6223 train_time:280835ms step_avg:138.34ms
step:2041/5100 train_loss:3.6488 train_time:280971ms step_avg:138.34ms
step:2042/5100 train_loss:3.5983 train_time:281111ms step_avg:138.34ms
step:2043/5100 train_loss:3.4894 train_time:281249ms step_avg:138.34ms
step:2044/5100 train_loss:3.6285 train_time:281387ms step_avg:138.34ms
step:2045/5100 train_loss:3.6288 train_time:281524ms step_avg:138.34ms
step:2046/5100 train_loss:3.4811 train_time:281662ms step_avg:138.34ms
step:2047/5100 train_loss:3.5505 train_time:281801ms step_avg:138.34ms
step:2048/5100 train_loss:3.6334 train_time:281935ms step_avg:138.34ms
step:2049/5100 train_loss:3.5860 train_time:282071ms step_avg:138.34ms
step:2050/5100 train_loss:3.6225 train_time:282209ms step_avg:138.34ms
step:2051/5100 train_loss:3.7836 train_time:282348ms step_avg:138.34ms
step:2052/5100 train_loss:3.6412 train_time:282486ms step_avg:138.34ms
step:2053/5100 train_loss:3.5956 train_time:282625ms step_avg:138.34ms
step:2054/5100 train_loss:3.5754 train_time:282763ms step_avg:138.34ms
step:2055/5100 train_loss:3.4436 train_time:282900ms step_avg:138.34ms
step:2056/5100 train_loss:3.5514 train_time:283035ms step_avg:138.34ms
step:2057/5100 train_loss:3.7316 train_time:283171ms step_avg:138.33ms
step:2058/5100 train_loss:3.7421 train_time:283309ms step_avg:138.33ms
step:2059/5100 train_loss:3.6194 train_time:283447ms step_avg:138.33ms
step:2060/5100 train_loss:3.6599 train_time:283586ms step_avg:138.33ms
step:2061/5100 train_loss:3.6413 train_time:283723ms step_avg:138.33ms
step:2062/5100 train_loss:3.5886 train_time:283863ms step_avg:138.33ms
step:2063/5100 train_loss:3.5133 train_time:283999ms step_avg:138.33ms
step:2064/5100 train_loss:3.8124 train_time:284134ms step_avg:138.33ms
step:2065/5100 train_loss:3.6740 train_time:284271ms step_avg:138.33ms
step:2066/5100 train_loss:3.6177 train_time:284410ms step_avg:138.33ms
step:2067/5100 train_loss:3.6693 train_time:284548ms step_avg:138.33ms
step:2068/5100 train_loss:3.5733 train_time:284687ms step_avg:138.33ms
step:2069/5100 train_loss:3.6277 train_time:284825ms step_avg:138.33ms
step:2070/5100 train_loss:3.7618 train_time:284964ms step_avg:138.33ms
step:2071/5100 train_loss:3.7637 train_time:285101ms step_avg:138.33ms
step:2072/5100 train_loss:3.6145 train_time:285238ms step_avg:138.33ms
step:2073/5100 train_loss:3.6485 train_time:285373ms step_avg:138.33ms
step:2074/5100 train_loss:3.5350 train_time:285513ms step_avg:138.33ms
step:2075/5100 train_loss:4.0654 train_time:285649ms step_avg:138.33ms
step:2076/5100 train_loss:3.4868 train_time:285787ms step_avg:138.33ms
step:2077/5100 train_loss:3.6608 train_time:285925ms step_avg:138.33ms
step:2078/5100 train_loss:3.5497 train_time:286064ms step_avg:138.33ms
step:2079/5100 train_loss:3.5174 train_time:286300ms step_avg:138.38ms
step:2080/5100 train_loss:3.6102 train_time:286430ms step_avg:138.37ms
step:2081/5100 train_loss:3.8880 train_time:286565ms step_avg:138.37ms
step:2082/5100 train_loss:3.4958 train_time:286690ms step_avg:138.36ms
step:2083/5100 train_loss:3.8276 train_time:286833ms step_avg:138.37ms
step:2084/5100 train_loss:3.5439 train_time:286969ms step_avg:138.37ms
step:2085/5100 train_loss:3.5161 train_time:287103ms step_avg:138.36ms
step:2086/5100 train_loss:3.7713 train_time:287241ms step_avg:138.36ms
step:2087/5100 train_loss:3.6990 train_time:287387ms step_avg:138.37ms
step:2088/5100 train_loss:3.6784 train_time:287528ms step_avg:138.37ms
step:2089/5100 train_loss:3.7386 train_time:287665ms step_avg:138.37ms
step:2090/5100 train_loss:3.6563 train_time:287982ms step_avg:138.45ms
step:2091/5100 train_loss:3.6453 train_time:288115ms step_avg:138.45ms
step:2092/5100 train_loss:3.5983 train_time:288250ms step_avg:138.45ms
step:2093/5100 train_loss:3.6772 train_time:288384ms step_avg:138.45ms
step:2094/5100 train_loss:3.5496 train_time:288520ms step_avg:138.45ms
step:2095/5100 train_loss:3.3617 train_time:288655ms step_avg:138.44ms
step:2096/5100 train_loss:3.5886 train_time:288789ms step_avg:138.44ms
step:2097/5100 train_loss:3.7658 train_time:288926ms step_avg:138.44ms
step:2098/5100 train_loss:3.6103 train_time:289072ms step_avg:138.44ms
step:2099/5100 train_loss:3.4758 train_time:289208ms step_avg:138.44ms
step:2100/5100 train_loss:3.5870 train_time:289347ms step_avg:138.44ms
step:2101/5100 train_loss:3.5552 train_time:289483ms step_avg:138.44ms
step:2102/5100 train_loss:3.6891 train_time:289619ms step_avg:138.44ms
step:2103/5100 train_loss:3.5229 train_time:289753ms step_avg:138.44ms
step:2104/5100 train_loss:3.4844 train_time:289887ms step_avg:138.44ms
step:2105/5100 train_loss:3.7490 train_time:290027ms step_avg:138.44ms
step:2106/5100 train_loss:3.4904 train_time:290166ms step_avg:138.44ms
step:2107/5100 train_loss:3.8680 train_time:290304ms step_avg:138.44ms
step:2108/5100 train_loss:3.7129 train_time:290442ms step_avg:138.44ms
step:2109/5100 train_loss:3.6261 train_time:290579ms step_avg:138.44ms
step:2110/5100 train_loss:3.6396 train_time:290714ms step_avg:138.44ms
step:2111/5100 train_loss:3.4703 train_time:290850ms step_avg:138.43ms
step:2112/5100 train_loss:3.9441 train_time:290987ms step_avg:138.43ms
step:2113/5100 train_loss:3.6320 train_time:291126ms step_avg:138.43ms
step:2114/5100 train_loss:3.5564 train_time:291264ms step_avg:138.43ms
step:2115/5100 train_loss:3.6855 train_time:291404ms step_avg:138.43ms
step:2116/5100 train_loss:3.6421 train_time:291541ms step_avg:138.43ms
step:2117/5100 train_loss:3.6201 train_time:291679ms step_avg:138.43ms
step:2118/5100 train_loss:3.6740 train_time:291814ms step_avg:138.43ms
step:2119/5100 train_loss:3.5450 train_time:291950ms step_avg:138.43ms
step:2120/5100 train_loss:3.5935 train_time:292088ms step_avg:138.43ms
step:2121/5100 train_loss:3.3064 train_time:292226ms step_avg:138.43ms
step:2122/5100 train_loss:3.4998 train_time:292366ms step_avg:138.43ms
step:2123/5100 train_loss:3.6584 train_time:292504ms step_avg:138.43ms
step:2124/5100 train_loss:3.5802 train_time:292642ms step_avg:138.43ms
step:2125/5100 train_loss:3.7293 train_time:292778ms step_avg:138.43ms
step:2125/5100 val_loss:3.6093 train_time:292849ms step_avg:138.46ms
step:2126/5100 train_loss:3.5928 train_time:292921ms step_avg:138.43ms
step:2127/5100 train_loss:3.7148 train_time:293067ms step_avg:138.44ms
step:2128/5100 train_loss:3.6867 train_time:293208ms step_avg:138.44ms
step:2129/5100 train_loss:3.5425 train_time:293343ms step_avg:138.43ms
step:2130/5100 train_loss:3.5246 train_time:293477ms step_avg:138.43ms
step:2131/5100 train_loss:3.5512 train_time:293612ms step_avg:138.43ms
step:2132/5100 train_loss:3.7112 train_time:293747ms step_avg:138.43ms
step:2133/5100 train_loss:3.5933 train_time:293882ms step_avg:138.43ms
step:2134/5100 train_loss:3.4972 train_time:294025ms step_avg:138.43ms
step:2135/5100 train_loss:3.5769 train_time:294165ms step_avg:138.43ms
step:2136/5100 train_loss:3.6846 train_time:294303ms step_avg:138.43ms
step:2137/5100 train_loss:3.6987 train_time:294440ms step_avg:138.43ms
step:2138/5100 train_loss:3.6468 train_time:294572ms step_avg:138.43ms
step:2139/5100 train_loss:3.6272 train_time:294710ms step_avg:138.43ms
step:2140/5100 train_loss:3.6219 train_time:294845ms step_avg:138.42ms
step:2141/5100 train_loss:3.7018 train_time:294983ms step_avg:138.42ms
step:2142/5100 train_loss:4.0093 train_time:295123ms step_avg:138.43ms
step:2143/5100 train_loss:3.5286 train_time:295262ms step_avg:138.43ms
step:2144/5100 train_loss:3.5647 train_time:295401ms step_avg:138.43ms
step:2145/5100 train_loss:3.6013 train_time:295534ms step_avg:138.42ms
step:2146/5100 train_loss:3.7284 train_time:295670ms step_avg:138.42ms
step:2147/5100 train_loss:3.6650 train_time:295807ms step_avg:138.42ms
step:2148/5100 train_loss:4.0771 train_time:295947ms step_avg:138.42ms
step:2149/5100 train_loss:3.5805 train_time:296086ms step_avg:138.42ms
step:2150/5100 train_loss:3.5737 train_time:296222ms step_avg:138.42ms
step:2151/5100 train_loss:3.6180 train_time:296360ms step_avg:138.42ms
step:2152/5100 train_loss:3.6601 train_time:296498ms step_avg:138.42ms
step:2153/5100 train_loss:3.6190 train_time:296632ms step_avg:138.42ms
step:2154/5100 train_loss:3.5481 train_time:296767ms step_avg:138.42ms
step:2155/5100 train_loss:3.7717 train_time:296905ms step_avg:138.42ms
step:2156/5100 train_loss:3.3828 train_time:297044ms step_avg:138.42ms
step:2157/5100 train_loss:3.5396 train_time:297184ms step_avg:138.42ms
step:2158/5100 train_loss:3.6792 train_time:297322ms step_avg:138.42ms
step:2159/5100 train_loss:3.6110 train_time:297460ms step_avg:138.42ms
step:2160/5100 train_loss:3.7663 train_time:297596ms step_avg:138.42ms
step:2161/5100 train_loss:3.6908 train_time:297731ms step_avg:138.42ms
step:2162/5100 train_loss:3.6124 train_time:297869ms step_avg:138.41ms
step:2163/5100 train_loss:3.5741 train_time:298007ms step_avg:138.41ms
step:2164/5100 train_loss:3.5808 train_time:298146ms step_avg:138.41ms
step:2165/5100 train_loss:3.6606 train_time:298284ms step_avg:138.41ms
step:2166/5100 train_loss:3.6840 train_time:298423ms step_avg:138.42ms
step:2167/5100 train_loss:3.6246 train_time:298562ms step_avg:138.42ms
step:2168/5100 train_loss:3.5057 train_time:298696ms step_avg:138.41ms
step:2169/5100 train_loss:3.5904 train_time:298831ms step_avg:138.41ms
step:2170/5100 train_loss:3.6431 train_time:298969ms step_avg:138.41ms
step:2171/5100 train_loss:3.7563 train_time:299108ms step_avg:138.41ms
step:2172/5100 train_loss:3.5585 train_time:299247ms step_avg:138.41ms
step:2173/5100 train_loss:3.5446 train_time:299385ms step_avg:138.41ms
step:2174/5100 train_loss:3.5407 train_time:299524ms step_avg:138.41ms
step:2175/5100 train_loss:3.6052 train_time:299661ms step_avg:138.41ms
step:2176/5100 train_loss:3.5672 train_time:299798ms step_avg:138.41ms
step:2177/5100 train_loss:3.5416 train_time:299932ms step_avg:138.41ms
step:2178/5100 train_loss:3.7595 train_time:300071ms step_avg:138.41ms
step:2179/5100 train_loss:3.5795 train_time:300210ms step_avg:138.41ms
step:2180/5100 train_loss:3.5868 train_time:300347ms step_avg:138.41ms
step:2181/5100 train_loss:3.6566 train_time:300486ms step_avg:138.41ms
step:2182/5100 train_loss:3.6214 train_time:300625ms step_avg:138.41ms
step:2183/5100 train_loss:3.6047 train_time:300763ms step_avg:138.41ms
step:2184/5100 train_loss:3.4925 train_time:300900ms step_avg:138.41ms
step:2185/5100 train_loss:3.6607 train_time:301037ms step_avg:138.41ms
step:2186/5100 train_loss:3.8471 train_time:301172ms step_avg:138.41ms
step:2187/5100 train_loss:3.4736 train_time:301310ms step_avg:138.41ms
step:2188/5100 train_loss:3.5270 train_time:301449ms step_avg:138.41ms
step:2189/5100 train_loss:3.3895 train_time:301587ms step_avg:138.41ms
step:2190/5100 train_loss:3.5171 train_time:301725ms step_avg:138.41ms
step:2191/5100 train_loss:3.6616 train_time:301862ms step_avg:138.41ms
step:2192/5100 train_loss:3.6051 train_time:302001ms step_avg:138.41ms
step:2193/5100 train_loss:3.8350 train_time:302136ms step_avg:138.40ms
step:2194/5100 train_loss:3.6046 train_time:302271ms step_avg:138.40ms
step:2195/5100 train_loss:3.6724 train_time:302409ms step_avg:138.40ms
step:2196/5100 train_loss:3.6068 train_time:302549ms step_avg:138.40ms
step:2197/5100 train_loss:3.5266 train_time:302688ms step_avg:138.40ms
step:2198/5100 train_loss:3.6112 train_time:302826ms step_avg:138.40ms
step:2199/5100 train_loss:3.5508 train_time:302963ms step_avg:138.40ms
step:2200/5100 train_loss:3.5585 train_time:303101ms step_avg:138.40ms
step:2201/5100 train_loss:3.6088 train_time:303239ms step_avg:138.40ms
step:2202/5100 train_loss:3.5866 train_time:303374ms step_avg:138.40ms
step:2203/5100 train_loss:3.5622 train_time:303511ms step_avg:138.40ms
step:2204/5100 train_loss:4.0630 train_time:303650ms step_avg:138.40ms
step:2205/5100 train_loss:3.4809 train_time:303787ms step_avg:138.40ms
step:2206/5100 train_loss:3.6045 train_time:303925ms step_avg:138.40ms
step:2207/5100 train_loss:3.6120 train_time:304064ms step_avg:138.40ms
step:2208/5100 train_loss:3.6382 train_time:304202ms step_avg:138.40ms
step:2209/5100 train_loss:3.5231 train_time:304340ms step_avg:138.40ms
step:2210/5100 train_loss:3.6045 train_time:304475ms step_avg:138.40ms
step:2211/5100 train_loss:3.6165 train_time:304611ms step_avg:138.40ms
step:2212/5100 train_loss:3.6220 train_time:304750ms step_avg:138.40ms
step:2213/5100 train_loss:3.6441 train_time:304887ms step_avg:138.40ms
step:2214/5100 train_loss:3.5049 train_time:305026ms step_avg:138.40ms
step:2215/5100 train_loss:3.5646 train_time:305164ms step_avg:138.40ms
step:2216/5100 train_loss:3.7056 train_time:305302ms step_avg:138.40ms
step:2217/5100 train_loss:3.6588 train_time:305439ms step_avg:138.40ms
step:2218/5100 train_loss:3.6130 train_time:305573ms step_avg:138.39ms
step:2219/5100 train_loss:3.6226 train_time:305708ms step_avg:138.39ms
step:2220/5100 train_loss:3.5252 train_time:305849ms step_avg:138.39ms
step:2221/5100 train_loss:3.7927 train_time:305987ms step_avg:138.39ms
step:2222/5100 train_loss:3.6806 train_time:306124ms step_avg:138.39ms
step:2223/5100 train_loss:3.7125 train_time:306262ms step_avg:138.39ms
step:2224/5100 train_loss:3.5765 train_time:306401ms step_avg:138.39ms
step:2225/5100 train_loss:3.7073 train_time:306538ms step_avg:138.39ms
step:2226/5100 train_loss:3.4613 train_time:306673ms step_avg:138.39ms
step:2227/5100 train_loss:3.7249 train_time:306809ms step_avg:138.39ms
step:2228/5100 train_loss:3.6718 train_time:306947ms step_avg:138.39ms
step:2229/5100 train_loss:3.4696 train_time:307086ms step_avg:138.39ms
step:2230/5100 train_loss:3.8149 train_time:307225ms step_avg:138.39ms
step:2231/5100 train_loss:3.5166 train_time:307363ms step_avg:138.39ms
step:2232/5100 train_loss:3.9769 train_time:307500ms step_avg:138.39ms
step:2233/5100 train_loss:3.6663 train_time:307636ms step_avg:138.39ms
step:2234/5100 train_loss:3.6018 train_time:307771ms step_avg:138.39ms
step:2235/5100 train_loss:3.6606 train_time:307910ms step_avg:138.39ms
step:2236/5100 train_loss:3.4256 train_time:308049ms step_avg:138.39ms
step:2237/5100 train_loss:3.4202 train_time:308187ms step_avg:138.39ms
step:2238/5100 train_loss:3.6530 train_time:308326ms step_avg:138.39ms
step:2239/5100 train_loss:3.7387 train_time:308464ms step_avg:138.39ms
step:2240/5100 train_loss:3.4635 train_time:308602ms step_avg:138.39ms
step:2241/5100 train_loss:3.5380 train_time:308739ms step_avg:138.39ms
step:2242/5100 train_loss:3.7045 train_time:308874ms step_avg:138.38ms
step:2243/5100 train_loss:3.6836 train_time:309011ms step_avg:138.38ms
step:2244/5100 train_loss:3.5432 train_time:309149ms step_avg:138.38ms
step:2245/5100 train_loss:3.6017 train_time:309287ms step_avg:138.38ms
step:2246/5100 train_loss:3.6257 train_time:309426ms step_avg:138.38ms
step:2247/5100 train_loss:3.4768 train_time:309563ms step_avg:138.38ms
step:2248/5100 train_loss:3.4770 train_time:309702ms step_avg:138.38ms
step:2249/5100 train_loss:3.7256 train_time:309839ms step_avg:138.38ms
step:2250/5100 train_loss:3.4658 train_time:309973ms step_avg:138.38ms
step:2250/5100 val_loss:3.5914 train_time:310046ms step_avg:138.41ms
step:2251/5100 train_loss:3.4604 train_time:310118ms step_avg:138.38ms
step:2252/5100 train_loss:3.5359 train_time:310270ms step_avg:138.39ms
step:2253/5100 train_loss:3.5198 train_time:310403ms step_avg:138.39ms
step:2254/5100 train_loss:3.5578 train_time:310537ms step_avg:138.39ms
step:2255/5100 train_loss:3.6133 train_time:310672ms step_avg:138.38ms
step:2256/5100 train_loss:3.5024 train_time:310808ms step_avg:138.38ms
step:2257/5100 train_loss:3.7796 train_time:310942ms step_avg:138.38ms
step:2258/5100 train_loss:3.6550 train_time:311082ms step_avg:138.38ms
step:2259/5100 train_loss:3.9648 train_time:311223ms step_avg:138.38ms
step:2260/5100 train_loss:3.6577 train_time:311361ms step_avg:138.38ms
step:2261/5100 train_loss:3.7139 train_time:311499ms step_avg:138.38ms
step:2262/5100 train_loss:3.6215 train_time:311637ms step_avg:138.38ms
step:2263/5100 train_loss:3.6262 train_time:311772ms step_avg:138.38ms
step:2264/5100 train_loss:3.3762 train_time:311910ms step_avg:138.38ms
step:2265/5100 train_loss:3.5096 train_time:312044ms step_avg:138.38ms
step:2266/5100 train_loss:3.7168 train_time:312182ms step_avg:138.38ms
step:2267/5100 train_loss:3.4455 train_time:312320ms step_avg:138.38ms
step:2268/5100 train_loss:3.5245 train_time:312559ms step_avg:138.42ms
step:2269/5100 train_loss:3.4953 train_time:312688ms step_avg:138.42ms
step:2270/5100 train_loss:3.4637 train_time:312820ms step_avg:138.42ms
step:2271/5100 train_loss:3.8685 train_time:312956ms step_avg:138.42ms
step:2272/5100 train_loss:3.5170 train_time:313091ms step_avg:138.41ms
step:2273/5100 train_loss:3.5296 train_time:313226ms step_avg:138.41ms
step:2274/5100 train_loss:3.6091 train_time:313360ms step_avg:138.41ms
step:2275/5100 train_loss:3.5589 train_time:313499ms step_avg:138.41ms
step:2276/5100 train_loss:3.5735 train_time:313642ms step_avg:138.41ms
step:2277/5100 train_loss:3.4546 train_time:313780ms step_avg:138.41ms
step:2278/5100 train_loss:3.5679 train_time:313919ms step_avg:138.41ms
step:2279/5100 train_loss:3.6915 train_time:314055ms step_avg:138.41ms
step:2280/5100 train_loss:3.4901 train_time:314370ms step_avg:138.49ms
step:2281/5100 train_loss:3.5473 train_time:314501ms step_avg:138.49ms
step:2282/5100 train_loss:3.5603 train_time:314636ms step_avg:138.48ms
step:2283/5100 train_loss:3.7061 train_time:314770ms step_avg:138.48ms
step:2284/5100 train_loss:3.5809 train_time:314898ms step_avg:138.48ms
step:2285/5100 train_loss:3.5998 train_time:315033ms step_avg:138.48ms
step:2286/5100 train_loss:3.6080 train_time:315168ms step_avg:138.47ms
step:2287/5100 train_loss:3.5998 train_time:315305ms step_avg:138.47ms
step:2288/5100 train_loss:3.5528 train_time:315452ms step_avg:138.48ms
step:2289/5100 train_loss:3.6868 train_time:315589ms step_avg:138.48ms
step:2290/5100 train_loss:3.6666 train_time:315726ms step_avg:138.48ms
step:2291/5100 train_loss:3.5401 train_time:315863ms step_avg:138.48ms
step:2292/5100 train_loss:3.8731 train_time:315998ms step_avg:138.47ms
step:2293/5100 train_loss:3.5356 train_time:316135ms step_avg:138.47ms
step:2294/5100 train_loss:3.4900 train_time:316273ms step_avg:138.47ms
step:2295/5100 train_loss:3.6688 train_time:316410ms step_avg:138.47ms
step:2296/5100 train_loss:3.6262 train_time:316548ms step_avg:138.47ms
step:2297/5100 train_loss:3.5672 train_time:316683ms step_avg:138.47ms
step:2298/5100 train_loss:3.9574 train_time:316819ms step_avg:138.47ms
step:2299/5100 train_loss:3.4955 train_time:316957ms step_avg:138.47ms
step:2300/5100 train_loss:3.5121 train_time:317094ms step_avg:138.47ms
step:2301/5100 train_loss:3.8388 train_time:317230ms step_avg:138.47ms
step:2302/5100 train_loss:3.5619 train_time:317367ms step_avg:138.47ms
step:2303/5100 train_loss:3.5745 train_time:317503ms step_avg:138.47ms
step:2304/5100 train_loss:3.5602 train_time:317642ms step_avg:138.47ms
step:2305/5100 train_loss:3.5008 train_time:317780ms step_avg:138.47ms
step:2306/5100 train_loss:3.6499 train_time:317917ms step_avg:138.47ms
step:2307/5100 train_loss:3.5175 train_time:318053ms step_avg:138.46ms
step:2308/5100 train_loss:3.5416 train_time:318191ms step_avg:138.46ms
step:2309/5100 train_loss:3.6709 train_time:318326ms step_avg:138.46ms
step:2310/5100 train_loss:3.6240 train_time:318463ms step_avg:138.46ms
step:2311/5100 train_loss:3.4908 train_time:318600ms step_avg:138.46ms
step:2312/5100 train_loss:3.6045 train_time:318741ms step_avg:138.46ms
step:2313/5100 train_loss:3.7380 train_time:318878ms step_avg:138.46ms
step:2314/5100 train_loss:3.5528 train_time:319015ms step_avg:138.46ms
step:2315/5100 train_loss:3.4723 train_time:319153ms step_avg:138.46ms
step:2316/5100 train_loss:3.5633 train_time:319290ms step_avg:138.46ms
step:2317/5100 train_loss:3.4564 train_time:319426ms step_avg:138.46ms
step:2318/5100 train_loss:3.5502 train_time:319561ms step_avg:138.46ms
step:2319/5100 train_loss:3.5783 train_time:319700ms step_avg:138.46ms
step:2320/5100 train_loss:3.4127 train_time:319836ms step_avg:138.46ms
step:2321/5100 train_loss:3.5562 train_time:319975ms step_avg:138.46ms
step:2322/5100 train_loss:3.6196 train_time:320113ms step_avg:138.46ms
step:2323/5100 train_loss:3.5234 train_time:320251ms step_avg:138.46ms
step:2324/5100 train_loss:3.5668 train_time:320389ms step_avg:138.46ms
step:2325/5100 train_loss:3.4977 train_time:320525ms step_avg:138.46ms
step:2326/5100 train_loss:3.6287 train_time:320659ms step_avg:138.45ms
step:2327/5100 train_loss:3.6381 train_time:320796ms step_avg:138.45ms
step:2328/5100 train_loss:3.4126 train_time:320936ms step_avg:138.45ms
step:2329/5100 train_loss:3.5275 train_time:321074ms step_avg:138.45ms
step:2330/5100 train_loss:3.5556 train_time:321212ms step_avg:138.45ms
step:2331/5100 train_loss:3.5119 train_time:321350ms step_avg:138.45ms
step:2332/5100 train_loss:3.7033 train_time:321485ms step_avg:138.45ms
step:2333/5100 train_loss:3.5966 train_time:321620ms step_avg:138.45ms
step:2334/5100 train_loss:3.5598 train_time:321758ms step_avg:138.45ms
step:2335/5100 train_loss:3.6497 train_time:321893ms step_avg:138.45ms
step:2336/5100 train_loss:3.4862 train_time:322035ms step_avg:138.45ms
step:2337/5100 train_loss:3.6378 train_time:322172ms step_avg:138.45ms
step:2338/5100 train_loss:3.5911 train_time:322312ms step_avg:138.45ms
step:2339/5100 train_loss:3.5448 train_time:322447ms step_avg:138.45ms
step:2340/5100 train_loss:3.6181 train_time:322583ms step_avg:138.45ms
step:2341/5100 train_loss:3.6668 train_time:322720ms step_avg:138.45ms
step:2342/5100 train_loss:3.5395 train_time:322857ms step_avg:138.45ms
step:2343/5100 train_loss:3.5434 train_time:322995ms step_avg:138.45ms
step:2344/5100 train_loss:3.6092 train_time:323133ms step_avg:138.45ms
step:2345/5100 train_loss:3.5588 train_time:323272ms step_avg:138.45ms
step:2346/5100 train_loss:3.6863 train_time:323410ms step_avg:138.45ms
step:2347/5100 train_loss:3.5946 train_time:323546ms step_avg:138.44ms
step:2348/5100 train_loss:3.6921 train_time:323682ms step_avg:138.44ms
step:2349/5100 train_loss:3.6521 train_time:323819ms step_avg:138.44ms
step:2350/5100 train_loss:3.6898 train_time:323956ms step_avg:138.44ms
step:2351/5100 train_loss:3.3822 train_time:324096ms step_avg:138.44ms
step:2352/5100 train_loss:3.5071 train_time:324233ms step_avg:138.44ms
step:2353/5100 train_loss:3.5005 train_time:324371ms step_avg:138.44ms
step:2354/5100 train_loss:3.7165 train_time:324508ms step_avg:138.44ms
step:2355/5100 train_loss:3.5148 train_time:324644ms step_avg:138.44ms
step:2356/5100 train_loss:3.4999 train_time:324781ms step_avg:138.44ms
step:2357/5100 train_loss:3.6601 train_time:324918ms step_avg:138.44ms
step:2358/5100 train_loss:3.5135 train_time:325057ms step_avg:138.44ms
step:2359/5100 train_loss:3.6318 train_time:325195ms step_avg:138.44ms
step:2360/5100 train_loss:3.5139 train_time:325333ms step_avg:138.44ms
step:2361/5100 train_loss:3.5215 train_time:325470ms step_avg:138.44ms
step:2362/5100 train_loss:3.5762 train_time:325609ms step_avg:138.44ms
step:2363/5100 train_loss:3.6153 train_time:325743ms step_avg:138.44ms
step:2364/5100 train_loss:3.5636 train_time:325879ms step_avg:138.44ms
step:2365/5100 train_loss:3.9990 train_time:326018ms step_avg:138.44ms
step:2366/5100 train_loss:3.6264 train_time:326156ms step_avg:138.44ms
step:2367/5100 train_loss:3.7799 train_time:326294ms step_avg:138.44ms
step:2368/5100 train_loss:3.6106 train_time:326432ms step_avg:138.44ms
step:2369/5100 train_loss:3.6024 train_time:326571ms step_avg:138.44ms
step:2370/5100 train_loss:3.6333 train_time:326708ms step_avg:138.44ms
step:2371/5100 train_loss:3.5226 train_time:326842ms step_avg:138.43ms
step:2372/5100 train_loss:3.7442 train_time:326980ms step_avg:138.43ms
step:2373/5100 train_loss:3.5946 train_time:327119ms step_avg:138.43ms
step:2374/5100 train_loss:4.1412 train_time:327257ms step_avg:138.43ms
step:2375/5100 train_loss:3.5657 train_time:327395ms step_avg:138.43ms
step:2375/5100 val_loss:3.5831 train_time:327470ms step_avg:138.46ms
step:2376/5100 train_loss:3.4882 train_time:327544ms step_avg:138.44ms
step:2377/5100 train_loss:3.6497 train_time:327688ms step_avg:138.44ms
step:2378/5100 train_loss:3.6092 train_time:327825ms step_avg:138.44ms
step:2379/5100 train_loss:3.6208 train_time:327960ms step_avg:138.44ms
step:2380/5100 train_loss:3.6132 train_time:328093ms step_avg:138.44ms
step:2381/5100 train_loss:3.5063 train_time:328228ms step_avg:138.43ms
step:2382/5100 train_loss:3.5969 train_time:328364ms step_avg:138.43ms
step:2383/5100 train_loss:3.6116 train_time:328503ms step_avg:138.43ms
step:2384/5100 train_loss:3.5712 train_time:328644ms step_avg:138.43ms
step:2385/5100 train_loss:3.4952 train_time:328779ms step_avg:138.43ms
step:2386/5100 train_loss:3.6099 train_time:328915ms step_avg:138.43ms
step:2387/5100 train_loss:3.5714 train_time:329053ms step_avg:138.43ms
step:2388/5100 train_loss:3.5638 train_time:329188ms step_avg:138.43ms
step:2389/5100 train_loss:3.5985 train_time:329324ms step_avg:138.43ms
step:2390/5100 train_loss:3.5791 train_time:329461ms step_avg:138.43ms
step:2391/5100 train_loss:3.5850 train_time:329600ms step_avg:138.43ms
step:2392/5100 train_loss:3.4590 train_time:329736ms step_avg:138.43ms
step:2393/5100 train_loss:3.6719 train_time:329872ms step_avg:138.43ms
step:2394/5100 train_loss:3.5311 train_time:330010ms step_avg:138.43ms
step:2395/5100 train_loss:3.6148 train_time:330147ms step_avg:138.43ms
step:2396/5100 train_loss:3.7401 train_time:330284ms step_avg:138.43ms
step:2397/5100 train_loss:3.7467 train_time:330420ms step_avg:138.42ms
step:2398/5100 train_loss:3.6836 train_time:330557ms step_avg:138.42ms
step:2399/5100 train_loss:3.6688 train_time:330693ms step_avg:138.42ms
step:2400/5100 train_loss:3.5419 train_time:330831ms step_avg:138.42ms
step:2401/5100 train_loss:3.5360 train_time:330972ms step_avg:138.42ms
step:2402/5100 train_loss:3.6496 train_time:331109ms step_avg:138.42ms
step:2403/5100 train_loss:3.4816 train_time:331245ms step_avg:138.42ms
step:2404/5100 train_loss:3.6223 train_time:331380ms step_avg:138.42ms
step:2405/5100 train_loss:3.8275 train_time:331515ms step_avg:138.42ms
step:2406/5100 train_loss:3.5653 train_time:331651ms step_avg:138.42ms
step:2407/5100 train_loss:3.7081 train_time:331791ms step_avg:138.42ms
step:2408/5100 train_loss:3.5715 train_time:331928ms step_avg:138.42ms
step:2409/5100 train_loss:3.5010 train_time:332065ms step_avg:138.42ms
step:2410/5100 train_loss:3.6386 train_time:332204ms step_avg:138.42ms
step:2411/5100 train_loss:3.4374 train_time:332340ms step_avg:138.42ms
step:2412/5100 train_loss:3.8655 train_time:332473ms step_avg:138.42ms
step:2413/5100 train_loss:3.5428 train_time:332611ms step_avg:138.41ms
step:2414/5100 train_loss:3.6142 train_time:332748ms step_avg:138.41ms
step:2415/5100 train_loss:3.5365 train_time:332886ms step_avg:138.41ms
step:2416/5100 train_loss:3.6070 train_time:333025ms step_avg:138.41ms
step:2417/5100 train_loss:3.4407 train_time:333162ms step_avg:138.41ms
step:2418/5100 train_loss:3.3646 train_time:333296ms step_avg:138.41ms
step:2419/5100 train_loss:3.6555 train_time:333432ms step_avg:138.41ms
step:2420/5100 train_loss:3.5335 train_time:333569ms step_avg:138.41ms
step:2421/5100 train_loss:3.5693 train_time:333707ms step_avg:138.41ms
step:2422/5100 train_loss:3.6645 train_time:333841ms step_avg:138.41ms
step:2423/5100 train_loss:3.7077 train_time:333979ms step_avg:138.41ms
step:2424/5100 train_loss:3.5307 train_time:334116ms step_avg:138.41ms
step:2425/5100 train_loss:3.6187 train_time:334254ms step_avg:138.41ms
step:2426/5100 train_loss:3.6213 train_time:334391ms step_avg:138.41ms
step:2427/5100 train_loss:3.5466 train_time:334529ms step_avg:138.41ms
step:2428/5100 train_loss:3.5034 train_time:334667ms step_avg:138.41ms
step:2429/5100 train_loss:3.6214 train_time:334805ms step_avg:138.41ms
step:2430/5100 train_loss:3.5210 train_time:334943ms step_avg:138.41ms
step:2431/5100 train_loss:3.5743 train_time:335075ms step_avg:138.40ms
step:2432/5100 train_loss:3.6311 train_time:335211ms step_avg:138.40ms
step:2433/5100 train_loss:3.5906 train_time:335348ms step_avg:138.40ms
step:2434/5100 train_loss:3.4745 train_time:335489ms step_avg:138.40ms
step:2435/5100 train_loss:3.4332 train_time:335624ms step_avg:138.40ms
step:2436/5100 train_loss:3.5987 train_time:335761ms step_avg:138.40ms
step:2437/5100 train_loss:3.4691 train_time:335898ms step_avg:138.40ms
step:2438/5100 train_loss:3.5375 train_time:336034ms step_avg:138.40ms
step:2439/5100 train_loss:3.6235 train_time:336172ms step_avg:138.40ms
step:2440/5100 train_loss:3.5424 train_time:336310ms step_avg:138.40ms
step:2441/5100 train_loss:3.6321 train_time:336448ms step_avg:138.40ms
step:2442/5100 train_loss:3.5121 train_time:336585ms step_avg:138.40ms
step:2443/5100 train_loss:3.5821 train_time:336721ms step_avg:138.40ms
step:2444/5100 train_loss:3.4597 train_time:336857ms step_avg:138.40ms
step:2445/5100 train_loss:3.4678 train_time:336994ms step_avg:138.40ms
step:2446/5100 train_loss:3.6424 train_time:337132ms step_avg:138.40ms
step:2447/5100 train_loss:3.4931 train_time:337269ms step_avg:138.40ms
step:2448/5100 train_loss:3.5624 train_time:337407ms step_avg:138.39ms
step:2449/5100 train_loss:3.7286 train_time:337544ms step_avg:138.39ms
step:2450/5100 train_loss:3.5525 train_time:337679ms step_avg:138.39ms
step:2451/5100 train_loss:3.6278 train_time:337815ms step_avg:138.39ms
step:2452/5100 train_loss:3.5331 train_time:337953ms step_avg:138.39ms
step:2453/5100 train_loss:3.6379 train_time:338092ms step_avg:138.39ms
step:2454/5100 train_loss:3.5341 train_time:338229ms step_avg:138.39ms
step:2455/5100 train_loss:3.6663 train_time:338366ms step_avg:138.39ms
step:2456/5100 train_loss:3.5913 train_time:338507ms step_avg:138.39ms
step:2457/5100 train_loss:3.5166 train_time:338736ms step_avg:138.43ms
step:2458/5100 train_loss:3.4557 train_time:338866ms step_avg:138.43ms
step:2459/5100 train_loss:3.5736 train_time:339000ms step_avg:138.42ms
step:2460/5100 train_loss:4.1646 train_time:339135ms step_avg:138.42ms
step:2461/5100 train_loss:3.6391 train_time:339270ms step_avg:138.42ms
step:2462/5100 train_loss:3.4512 train_time:339405ms step_avg:138.42ms
step:2463/5100 train_loss:3.6504 train_time:339540ms step_avg:138.42ms
step:2464/5100 train_loss:3.5652 train_time:339684ms step_avg:138.42ms
step:2465/5100 train_loss:3.7649 train_time:339824ms step_avg:138.42ms
step:2466/5100 train_loss:3.9673 train_time:339961ms step_avg:138.42ms
step:2467/5100 train_loss:3.6880 train_time:340096ms step_avg:138.42ms
step:2468/5100 train_loss:3.5538 train_time:340233ms step_avg:138.42ms
step:2469/5100 train_loss:3.6669 train_time:340368ms step_avg:138.42ms
step:2470/5100 train_loss:3.6875 train_time:340680ms step_avg:138.49ms
step:2471/5100 train_loss:3.4841 train_time:340805ms step_avg:138.48ms
step:2472/5100 train_loss:3.5751 train_time:340945ms step_avg:138.48ms
step:2473/5100 train_loss:3.5708 train_time:341079ms step_avg:138.48ms
step:2474/5100 train_loss:3.7189 train_time:341213ms step_avg:138.48ms
step:2475/5100 train_loss:3.8343 train_time:341347ms step_avg:138.48ms
step:2476/5100 train_loss:3.4465 train_time:341481ms step_avg:138.48ms
step:2477/5100 train_loss:3.6378 train_time:341618ms step_avg:138.47ms
step:2478/5100 train_loss:3.6028 train_time:341759ms step_avg:138.48ms
step:2479/5100 train_loss:3.4413 train_time:341895ms step_avg:138.48ms
step:2480/5100 train_loss:3.4337 train_time:342032ms step_avg:138.47ms
step:2481/5100 train_loss:3.5837 train_time:342170ms step_avg:138.47ms
step:2482/5100 train_loss:3.5983 train_time:342305ms step_avg:138.47ms
step:2483/5100 train_loss:3.6052 train_time:342440ms step_avg:138.47ms
step:2484/5100 train_loss:3.5618 train_time:342575ms step_avg:138.47ms
step:2485/5100 train_loss:3.5782 train_time:342713ms step_avg:138.47ms
step:2486/5100 train_loss:3.4641 train_time:342854ms step_avg:138.47ms
step:2487/5100 train_loss:3.6537 train_time:342990ms step_avg:138.47ms
step:2488/5100 train_loss:3.6189 train_time:343131ms step_avg:138.47ms
step:2489/5100 train_loss:3.5221 train_time:343265ms step_avg:138.47ms
step:2490/5100 train_loss:3.6279 train_time:343404ms step_avg:138.47ms
step:2491/5100 train_loss:3.6848 train_time:343538ms step_avg:138.47ms
step:2492/5100 train_loss:3.7673 train_time:343676ms step_avg:138.47ms
step:2493/5100 train_loss:3.6154 train_time:343815ms step_avg:138.47ms
step:2494/5100 train_loss:3.5419 train_time:343953ms step_avg:138.47ms
step:2495/5100 train_loss:3.6727 train_time:344091ms step_avg:138.47ms
step:2496/5100 train_loss:3.6158 train_time:344228ms step_avg:138.47ms
step:2497/5100 train_loss:3.5327 train_time:344366ms step_avg:138.47ms
step:2498/5100 train_loss:3.6281 train_time:344503ms step_avg:138.47ms
step:2499/5100 train_loss:3.6722 train_time:344637ms step_avg:138.46ms
step:2500/5100 train_loss:3.6892 train_time:344776ms step_avg:138.46ms
step:2500/5100 val_loss:3.5688 train_time:344847ms step_avg:138.49ms
step:2501/5100 train_loss:3.6349 train_time:344920ms step_avg:138.47ms
step:2502/5100 train_loss:3.5876 train_time:345066ms step_avg:138.47ms
step:2503/5100 train_loss:3.6057 train_time:345202ms step_avg:138.47ms
step:2504/5100 train_loss:3.4824 train_time:345338ms step_avg:138.47ms
step:2505/5100 train_loss:3.6631 train_time:345474ms step_avg:138.47ms
step:2506/5100 train_loss:3.6271 train_time:345610ms step_avg:138.47ms
step:2507/5100 train_loss:3.5684 train_time:345743ms step_avg:138.46ms
step:2508/5100 train_loss:3.5781 train_time:345880ms step_avg:138.46ms
step:2509/5100 train_loss:3.5456 train_time:346021ms step_avg:138.46ms
step:2510/5100 train_loss:3.7049 train_time:346160ms step_avg:138.46ms
step:2511/5100 train_loss:3.5457 train_time:346298ms step_avg:138.46ms
step:2512/5100 train_loss:3.5316 train_time:346435ms step_avg:138.46ms
step:2513/5100 train_loss:3.5908 train_time:346572ms step_avg:138.46ms
step:2514/5100 train_loss:3.6488 train_time:346706ms step_avg:138.46ms
step:2515/5100 train_loss:3.5317 train_time:346841ms step_avg:138.46ms
step:2516/5100 train_loss:3.6267 train_time:346979ms step_avg:138.46ms
step:2517/5100 train_loss:3.6299 train_time:347119ms step_avg:138.46ms
step:2518/5100 train_loss:3.4931 train_time:347257ms step_avg:138.46ms
step:2519/5100 train_loss:3.5171 train_time:347395ms step_avg:138.46ms
step:2520/5100 train_loss:3.6579 train_time:347533ms step_avg:138.46ms
step:2521/5100 train_loss:3.6420 train_time:347669ms step_avg:138.46ms
step:2522/5100 train_loss:3.5083 train_time:347803ms step_avg:138.46ms
step:2523/5100 train_loss:3.5055 train_time:347939ms step_avg:138.46ms
step:2524/5100 train_loss:3.6069 train_time:348078ms step_avg:138.46ms
step:2525/5100 train_loss:3.4260 train_time:348216ms step_avg:138.46ms
step:2526/5100 train_loss:3.6624 train_time:348354ms step_avg:138.46ms
step:2527/5100 train_loss:3.5744 train_time:348494ms step_avg:138.46ms
step:2528/5100 train_loss:3.5702 train_time:348629ms step_avg:138.45ms
step:2529/5100 train_loss:3.5494 train_time:348765ms step_avg:138.45ms
step:2530/5100 train_loss:3.5730 train_time:348900ms step_avg:138.45ms
step:2531/5100 train_loss:3.6140 train_time:349039ms step_avg:138.45ms
step:2532/5100 train_loss:3.4369 train_time:349177ms step_avg:138.45ms
step:2533/5100 train_loss:3.5963 train_time:349315ms step_avg:138.45ms
step:2534/5100 train_loss:3.4979 train_time:349444ms step_avg:138.45ms
step:2535/5100 train_loss:3.5229 train_time:349587ms step_avg:138.45ms
step:2536/5100 train_loss:3.5780 train_time:349723ms step_avg:138.45ms
step:2537/5100 train_loss:3.5919 train_time:349860ms step_avg:138.45ms
step:2538/5100 train_loss:3.4165 train_time:349997ms step_avg:138.45ms
step:2539/5100 train_loss:3.7237 train_time:350135ms step_avg:138.45ms
step:2540/5100 train_loss:3.3987 train_time:350274ms step_avg:138.45ms
step:2541/5100 train_loss:3.5864 train_time:350414ms step_avg:138.45ms
step:2542/5100 train_loss:3.3859 train_time:350551ms step_avg:138.45ms
step:2543/5100 train_loss:3.8000 train_time:350688ms step_avg:138.45ms
step:2544/5100 train_loss:3.5574 train_time:350823ms step_avg:138.45ms
step:2545/5100 train_loss:3.7124 train_time:350960ms step_avg:138.45ms
step:2546/5100 train_loss:3.5480 train_time:351098ms step_avg:138.45ms
step:2547/5100 train_loss:3.5414 train_time:351236ms step_avg:138.45ms
step:2548/5100 train_loss:3.5368 train_time:351375ms step_avg:138.45ms
step:2549/5100 train_loss:3.6992 train_time:351515ms step_avg:138.45ms
step:2550/5100 train_loss:3.5576 train_time:351653ms step_avg:138.45ms
step:2551/5100 train_loss:3.5558 train_time:351790ms step_avg:138.45ms
step:2552/5100 train_loss:3.5758 train_time:351925ms step_avg:138.44ms
step:2553/5100 train_loss:3.6022 train_time:352062ms step_avg:138.44ms
step:2554/5100 train_loss:3.5196 train_time:352199ms step_avg:138.44ms
step:2555/5100 train_loss:3.6197 train_time:352338ms step_avg:138.44ms
step:2556/5100 train_loss:3.6767 train_time:352477ms step_avg:138.44ms
step:2557/5100 train_loss:3.6724 train_time:352616ms step_avg:138.44ms
step:2558/5100 train_loss:3.5103 train_time:352753ms step_avg:138.44ms
step:2559/5100 train_loss:3.5020 train_time:352891ms step_avg:138.44ms
step:2560/5100 train_loss:3.5245 train_time:353028ms step_avg:138.44ms
step:2561/5100 train_loss:3.6380 train_time:353163ms step_avg:138.44ms
step:2562/5100 train_loss:3.6712 train_time:353300ms step_avg:138.44ms
step:2563/5100 train_loss:3.5540 train_time:353440ms step_avg:138.44ms
step:2564/5100 train_loss:3.5854 train_time:353578ms step_avg:138.44ms
step:2565/5100 train_loss:3.5058 train_time:353716ms step_avg:138.44ms
step:2566/5100 train_loss:3.5080 train_time:353853ms step_avg:138.44ms
step:2567/5100 train_loss:3.4993 train_time:353990ms step_avg:138.44ms
step:2568/5100 train_loss:3.5556 train_time:354127ms step_avg:138.44ms
step:2569/5100 train_loss:3.7002 train_time:354261ms step_avg:138.44ms
step:2570/5100 train_loss:3.5975 train_time:354400ms step_avg:138.44ms
step:2571/5100 train_loss:3.6938 train_time:354538ms step_avg:138.44ms
step:2572/5100 train_loss:3.4386 train_time:354677ms step_avg:138.44ms
step:2573/5100 train_loss:3.5571 train_time:354817ms step_avg:138.44ms
step:2574/5100 train_loss:3.2221 train_time:354953ms step_avg:138.44ms
step:2575/5100 train_loss:3.4616 train_time:355091ms step_avg:138.44ms
step:2576/5100 train_loss:3.4013 train_time:355229ms step_avg:138.44ms
step:2577/5100 train_loss:3.5198 train_time:355364ms step_avg:138.44ms
step:2578/5100 train_loss:3.5750 train_time:355499ms step_avg:138.43ms
step:2579/5100 train_loss:3.4798 train_time:355638ms step_avg:138.43ms
step:2580/5100 train_loss:3.5298 train_time:355776ms step_avg:138.43ms
step:2581/5100 train_loss:3.4867 train_time:355916ms step_avg:138.43ms
step:2582/5100 train_loss:3.5792 train_time:356054ms step_avg:138.43ms
step:2583/5100 train_loss:3.4593 train_time:356192ms step_avg:138.43ms
step:2584/5100 train_loss:3.6522 train_time:356330ms step_avg:138.43ms
step:2585/5100 train_loss:3.5741 train_time:356466ms step_avg:138.43ms
step:2586/5100 train_loss:3.5799 train_time:356601ms step_avg:138.43ms
step:2587/5100 train_loss:3.7140 train_time:356740ms step_avg:138.43ms
step:2588/5100 train_loss:3.5936 train_time:356884ms step_avg:138.43ms
step:2589/5100 train_loss:3.4472 train_time:357017ms step_avg:138.43ms
step:2590/5100 train_loss:3.6158 train_time:357154ms step_avg:138.43ms
step:2591/5100 train_loss:3.5238 train_time:357292ms step_avg:138.43ms
step:2592/5100 train_loss:3.7290 train_time:357430ms step_avg:138.43ms
step:2593/5100 train_loss:3.6097 train_time:357564ms step_avg:138.43ms
step:2594/5100 train_loss:3.4288 train_time:357700ms step_avg:138.43ms
step:2595/5100 train_loss:3.4987 train_time:357839ms step_avg:138.43ms
step:2596/5100 train_loss:3.9790 train_time:357978ms step_avg:138.43ms
step:2597/5100 train_loss:3.5763 train_time:358115ms step_avg:138.43ms
step:2598/5100 train_loss:3.5911 train_time:358253ms step_avg:138.43ms
step:2599/5100 train_loss:3.4497 train_time:358392ms step_avg:138.43ms
step:2600/5100 train_loss:3.6921 train_time:358530ms step_avg:138.43ms
step:2601/5100 train_loss:3.8560 train_time:358665ms step_avg:138.43ms
step:2602/5100 train_loss:3.4212 train_time:358799ms step_avg:138.43ms
step:2603/5100 train_loss:3.5639 train_time:358938ms step_avg:138.43ms
step:2604/5100 train_loss:3.3931 train_time:359076ms step_avg:138.43ms
step:2605/5100 train_loss:3.6847 train_time:359214ms step_avg:138.43ms
step:2606/5100 train_loss:3.5630 train_time:359353ms step_avg:138.43ms
step:2607/5100 train_loss:3.4642 train_time:359492ms step_avg:138.43ms
step:2608/5100 train_loss:3.4050 train_time:359629ms step_avg:138.43ms
step:2609/5100 train_loss:3.5238 train_time:359764ms step_avg:138.42ms
step:2610/5100 train_loss:3.7075 train_time:359901ms step_avg:138.42ms
step:2611/5100 train_loss:3.5883 train_time:360039ms step_avg:138.42ms
step:2612/5100 train_loss:3.4012 train_time:360178ms step_avg:138.42ms
step:2613/5100 train_loss:3.5164 train_time:360317ms step_avg:138.42ms
step:2614/5100 train_loss:3.6200 train_time:360455ms step_avg:138.42ms
step:2615/5100 train_loss:3.5522 train_time:360593ms step_avg:138.42ms
step:2616/5100 train_loss:3.5427 train_time:360730ms step_avg:138.42ms
step:2617/5100 train_loss:3.5864 train_time:360866ms step_avg:138.42ms
step:2618/5100 train_loss:3.6289 train_time:361001ms step_avg:138.42ms
step:2619/5100 train_loss:3.4695 train_time:361141ms step_avg:138.42ms
step:2620/5100 train_loss:3.6609 train_time:361280ms step_avg:138.42ms
step:2621/5100 train_loss:3.6145 train_time:361418ms step_avg:138.42ms
step:2622/5100 train_loss:3.7394 train_time:361557ms step_avg:138.42ms
step:2623/5100 train_loss:3.6473 train_time:361695ms step_avg:138.42ms
step:2624/5100 train_loss:3.5658 train_time:361832ms step_avg:138.42ms
step:2625/5100 train_loss:3.5308 train_time:361970ms step_avg:138.42ms
step:2625/5100 val_loss:3.5561 train_time:362038ms step_avg:138.45ms
step:2626/5100 train_loss:3.5474 train_time:362110ms step_avg:138.42ms
step:2627/5100 train_loss:3.6136 train_time:362255ms step_avg:138.42ms
step:2628/5100 train_loss:3.4433 train_time:362391ms step_avg:138.42ms
step:2629/5100 train_loss:3.6894 train_time:362528ms step_avg:138.42ms
step:2630/5100 train_loss:3.5784 train_time:362664ms step_avg:138.42ms
step:2631/5100 train_loss:3.6352 train_time:362797ms step_avg:138.42ms
step:2632/5100 train_loss:3.8630 train_time:362931ms step_avg:138.42ms
step:2633/5100 train_loss:3.5991 train_time:363073ms step_avg:138.42ms
step:2634/5100 train_loss:3.5194 train_time:363213ms step_avg:138.42ms
step:2635/5100 train_loss:3.4905 train_time:363352ms step_avg:138.42ms
step:2636/5100 train_loss:3.5301 train_time:363489ms step_avg:138.42ms
step:2637/5100 train_loss:3.3233 train_time:363627ms step_avg:138.42ms
step:2638/5100 train_loss:3.6319 train_time:363763ms step_avg:138.42ms
step:2639/5100 train_loss:3.5986 train_time:363898ms step_avg:138.42ms
step:2640/5100 train_loss:3.5122 train_time:364033ms step_avg:138.42ms
step:2641/5100 train_loss:3.5797 train_time:364173ms step_avg:138.42ms
step:2642/5100 train_loss:3.6218 train_time:364311ms step_avg:138.42ms
step:2643/5100 train_loss:3.4094 train_time:364449ms step_avg:138.42ms
step:2644/5100 train_loss:3.5334 train_time:364588ms step_avg:138.42ms
step:2645/5100 train_loss:3.5981 train_time:364725ms step_avg:138.42ms
step:2646/5100 train_loss:3.5695 train_time:364961ms step_avg:138.45ms
step:2647/5100 train_loss:3.4537 train_time:365090ms step_avg:138.45ms
step:2648/5100 train_loss:3.6905 train_time:365223ms step_avg:138.45ms
step:2649/5100 train_loss:3.9427 train_time:365358ms step_avg:138.45ms
step:2650/5100 train_loss:3.5744 train_time:365492ms step_avg:138.44ms
step:2651/5100 train_loss:3.5329 train_time:365629ms step_avg:138.44ms
step:2652/5100 train_loss:3.6702 train_time:365764ms step_avg:138.44ms
step:2653/5100 train_loss:3.5158 train_time:365906ms step_avg:138.44ms
step:2654/5100 train_loss:3.4941 train_time:366045ms step_avg:138.44ms
step:2655/5100 train_loss:3.5567 train_time:366183ms step_avg:138.44ms
step:2656/5100 train_loss:3.4848 train_time:366316ms step_avg:138.44ms
step:2657/5100 train_loss:3.5233 train_time:366454ms step_avg:138.44ms
step:2658/5100 train_loss:3.4867 train_time:366590ms step_avg:138.44ms
step:2659/5100 train_loss:3.5724 train_time:366726ms step_avg:138.44ms
step:2660/5100 train_loss:3.7220 train_time:367037ms step_avg:138.50ms
step:2661/5100 train_loss:3.5129 train_time:367169ms step_avg:138.50ms
step:2662/5100 train_loss:3.6662 train_time:367303ms step_avg:138.50ms
step:2663/5100 train_loss:3.5285 train_time:367437ms step_avg:138.50ms
step:2664/5100 train_loss:3.5231 train_time:367572ms step_avg:138.50ms
step:2665/5100 train_loss:3.4509 train_time:367706ms step_avg:138.50ms
step:2666/5100 train_loss:3.5136 train_time:367841ms step_avg:138.49ms
step:2667/5100 train_loss:3.5386 train_time:367976ms step_avg:138.49ms
step:2668/5100 train_loss:3.5862 train_time:368120ms step_avg:138.50ms
step:2669/5100 train_loss:3.5057 train_time:368256ms step_avg:138.49ms
step:2670/5100 train_loss:3.5728 train_time:368393ms step_avg:138.49ms
step:2671/5100 train_loss:3.4341 train_time:368527ms step_avg:138.49ms
step:2672/5100 train_loss:3.5189 train_time:368664ms step_avg:138.49ms
step:2673/5100 train_loss:3.5016 train_time:368798ms step_avg:138.49ms
step:2674/5100 train_loss:3.5520 train_time:368934ms step_avg:138.49ms
step:2675/5100 train_loss:3.5885 train_time:369074ms step_avg:138.49ms
step:2676/5100 train_loss:3.5559 train_time:369213ms step_avg:138.49ms
step:2677/5100 train_loss:3.5454 train_time:369351ms step_avg:138.49ms
step:2678/5100 train_loss:3.5829 train_time:369488ms step_avg:138.49ms
step:2679/5100 train_loss:3.6215 train_time:369627ms step_avg:138.49ms
step:2680/5100 train_loss:3.5325 train_time:369763ms step_avg:138.49ms
step:2681/5100 train_loss:3.4624 train_time:369897ms step_avg:138.49ms
step:2682/5100 train_loss:3.5077 train_time:370035ms step_avg:138.49ms
step:2683/5100 train_loss:3.9715 train_time:370174ms step_avg:138.49ms
step:2684/5100 train_loss:3.5614 train_time:370312ms step_avg:138.49ms
step:2685/5100 train_loss:3.5812 train_time:370450ms step_avg:138.49ms
step:2686/5100 train_loss:3.6394 train_time:370589ms step_avg:138.49ms
step:2687/5100 train_loss:3.5503 train_time:370726ms step_avg:138.49ms
step:2688/5100 train_loss:3.6421 train_time:370862ms step_avg:138.48ms
step:2689/5100 train_loss:3.5649 train_time:370995ms step_avg:138.48ms
step:2690/5100 train_loss:3.5617 train_time:371132ms step_avg:138.48ms
step:2691/5100 train_loss:3.5738 train_time:371271ms step_avg:138.48ms
step:2692/5100 train_loss:3.6523 train_time:371410ms step_avg:138.48ms
step:2693/5100 train_loss:3.4643 train_time:371547ms step_avg:138.48ms
step:2694/5100 train_loss:3.8215 train_time:371686ms step_avg:138.48ms
step:2695/5100 train_loss:3.6287 train_time:371821ms step_avg:138.48ms
step:2696/5100 train_loss:3.4549 train_time:371955ms step_avg:138.48ms
step:2697/5100 train_loss:3.6176 train_time:372092ms step_avg:138.48ms
step:2698/5100 train_loss:3.5850 train_time:372229ms step_avg:138.48ms
step:2699/5100 train_loss:3.5292 train_time:372367ms step_avg:138.48ms
step:2700/5100 train_loss:3.6356 train_time:372506ms step_avg:138.48ms
step:2701/5100 train_loss:3.6002 train_time:372644ms step_avg:138.48ms
step:2702/5100 train_loss:3.5006 train_time:372779ms step_avg:138.48ms
step:2703/5100 train_loss:3.5375 train_time:372915ms step_avg:138.48ms
step:2704/5100 train_loss:3.5423 train_time:373053ms step_avg:138.48ms
step:2705/5100 train_loss:3.5040 train_time:373191ms step_avg:138.48ms
step:2706/5100 train_loss:3.6963 train_time:373334ms step_avg:138.48ms
step:2707/5100 train_loss:3.6406 train_time:373467ms step_avg:138.47ms
step:2708/5100 train_loss:3.5586 train_time:373606ms step_avg:138.48ms
step:2709/5100 train_loss:3.5408 train_time:373742ms step_avg:138.47ms
step:2710/5100 train_loss:3.6502 train_time:373877ms step_avg:138.47ms
step:2711/5100 train_loss:3.5220 train_time:374015ms step_avg:138.47ms
step:2712/5100 train_loss:3.6331 train_time:374152ms step_avg:138.47ms
step:2713/5100 train_loss:3.3757 train_time:374289ms step_avg:138.47ms
step:2714/5100 train_loss:3.5732 train_time:374429ms step_avg:138.47ms
step:2715/5100 train_loss:3.4720 train_time:374567ms step_avg:138.47ms
step:2716/5100 train_loss:3.4707 train_time:374707ms step_avg:138.47ms
step:2717/5100 train_loss:3.6587 train_time:374843ms step_avg:138.47ms
step:2718/5100 train_loss:3.5580 train_time:374977ms step_avg:138.47ms
step:2719/5100 train_loss:3.7932 train_time:375115ms step_avg:138.47ms
step:2720/5100 train_loss:3.5289 train_time:375253ms step_avg:138.47ms
step:2721/5100 train_loss:3.5335 train_time:375392ms step_avg:138.47ms
step:2722/5100 train_loss:3.7615 train_time:375530ms step_avg:138.47ms
step:2723/5100 train_loss:3.5267 train_time:375668ms step_avg:138.47ms
step:2724/5100 train_loss:3.7184 train_time:375805ms step_avg:138.47ms
step:2725/5100 train_loss:3.5776 train_time:375942ms step_avg:138.47ms
step:2726/5100 train_loss:3.5400 train_time:376076ms step_avg:138.47ms
step:2727/5100 train_loss:3.5500 train_time:376213ms step_avg:138.47ms
step:2728/5100 train_loss:3.8920 train_time:376352ms step_avg:138.47ms
step:2729/5100 train_loss:3.6154 train_time:376492ms step_avg:138.47ms
step:2730/5100 train_loss:3.4938 train_time:376630ms step_avg:138.47ms
step:2731/5100 train_loss:3.5912 train_time:376769ms step_avg:138.47ms
step:2732/5100 train_loss:3.4900 train_time:376906ms step_avg:138.47ms
step:2733/5100 train_loss:3.3846 train_time:377041ms step_avg:138.47ms
step:2734/5100 train_loss:3.4998 train_time:377175ms step_avg:138.46ms
step:2735/5100 train_loss:3.5778 train_time:377313ms step_avg:138.46ms
step:2736/5100 train_loss:3.4823 train_time:377452ms step_avg:138.46ms
step:2737/5100 train_loss:3.8745 train_time:377590ms step_avg:138.46ms
step:2738/5100 train_loss:3.6135 train_time:377727ms step_avg:138.46ms
step:2739/5100 train_loss:3.8101 train_time:377865ms step_avg:138.46ms
step:2740/5100 train_loss:3.5597 train_time:378002ms step_avg:138.46ms
step:2741/5100 train_loss:3.5573 train_time:378137ms step_avg:138.46ms
step:2742/5100 train_loss:3.4989 train_time:378273ms step_avg:138.46ms
step:2743/5100 train_loss:3.5669 train_time:378411ms step_avg:138.46ms
step:2744/5100 train_loss:3.5829 train_time:378551ms step_avg:138.46ms
step:2745/5100 train_loss:3.7032 train_time:378688ms step_avg:138.46ms
step:2746/5100 train_loss:3.4487 train_time:378827ms step_avg:138.46ms
step:2747/5100 train_loss:3.5364 train_time:378966ms step_avg:138.46ms
step:2748/5100 train_loss:3.5789 train_time:379101ms step_avg:138.46ms
step:2749/5100 train_loss:3.6918 train_time:379236ms step_avg:138.46ms
step:2750/5100 train_loss:3.5221 train_time:379374ms step_avg:138.46ms
step:2750/5100 val_loss:3.5487 train_time:379447ms step_avg:138.48ms
step:2751/5100 train_loss:3.5867 train_time:379518ms step_avg:138.46ms
step:2752/5100 train_loss:3.6556 train_time:379663ms step_avg:138.46ms
step:2753/5100 train_loss:3.5679 train_time:379799ms step_avg:138.46ms
step:2754/5100 train_loss:3.4991 train_time:379934ms step_avg:138.46ms
step:2755/5100 train_loss:3.4854 train_time:380068ms step_avg:138.46ms
step:2756/5100 train_loss:3.5814 train_time:380203ms step_avg:138.46ms
step:2757/5100 train_loss:3.5199 train_time:380337ms step_avg:138.46ms
step:2758/5100 train_loss:3.3898 train_time:380476ms step_avg:138.46ms
step:2759/5100 train_loss:3.7855 train_time:380617ms step_avg:138.46ms
step:2760/5100 train_loss:3.5962 train_time:380756ms step_avg:138.46ms
step:2761/5100 train_loss:3.5560 train_time:380893ms step_avg:138.46ms
step:2762/5100 train_loss:3.5351 train_time:381033ms step_avg:138.46ms
step:2763/5100 train_loss:3.4519 train_time:381169ms step_avg:138.46ms
step:2764/5100 train_loss:3.6183 train_time:381303ms step_avg:138.45ms
step:2765/5100 train_loss:3.5318 train_time:381439ms step_avg:138.45ms
step:2766/5100 train_loss:3.4338 train_time:381578ms step_avg:138.45ms
step:2767/5100 train_loss:3.5153 train_time:381718ms step_avg:138.45ms
step:2768/5100 train_loss:3.6069 train_time:381856ms step_avg:138.45ms
step:2769/5100 train_loss:3.4894 train_time:381994ms step_avg:138.45ms
step:2770/5100 train_loss:3.5631 train_time:382132ms step_avg:138.45ms
step:2771/5100 train_loss:3.5335 train_time:382268ms step_avg:138.45ms
step:2772/5100 train_loss:3.9731 train_time:382403ms step_avg:138.45ms
step:2773/5100 train_loss:3.4401 train_time:382537ms step_avg:138.45ms
step:2774/5100 train_loss:3.5802 train_time:382676ms step_avg:138.45ms
step:2775/5100 train_loss:3.6319 train_time:382816ms step_avg:138.45ms
step:2776/5100 train_loss:3.6011 train_time:382954ms step_avg:138.45ms
step:2777/5100 train_loss:3.6842 train_time:383092ms step_avg:138.45ms
step:2778/5100 train_loss:3.6846 train_time:383231ms step_avg:138.45ms
step:2779/5100 train_loss:3.5407 train_time:383368ms step_avg:138.45ms
step:2780/5100 train_loss:3.4244 train_time:383504ms step_avg:138.45ms
step:2781/5100 train_loss:3.5682 train_time:383641ms step_avg:138.45ms
step:2782/5100 train_loss:3.5933 train_time:383778ms step_avg:138.45ms
step:2783/5100 train_loss:3.4489 train_time:383918ms step_avg:138.45ms
step:2784/5100 train_loss:3.5696 train_time:384056ms step_avg:138.45ms
step:2785/5100 train_loss:3.6242 train_time:384195ms step_avg:138.45ms
step:2786/5100 train_loss:3.4908 train_time:384334ms step_avg:138.45ms
step:2787/5100 train_loss:3.6324 train_time:384473ms step_avg:138.45ms
step:2788/5100 train_loss:3.5889 train_time:384609ms step_avg:138.45ms
step:2789/5100 train_loss:3.5222 train_time:384745ms step_avg:138.45ms
step:2790/5100 train_loss:3.5995 train_time:384881ms step_avg:138.45ms
step:2791/5100 train_loss:3.5180 train_time:385019ms step_avg:138.45ms
step:2792/5100 train_loss:3.4248 train_time:385157ms step_avg:138.45ms
step:2793/5100 train_loss:3.5364 train_time:385295ms step_avg:138.45ms
step:2794/5100 train_loss:3.5562 train_time:385434ms step_avg:138.45ms
step:2795/5100 train_loss:3.4807 train_time:385574ms step_avg:138.45ms
step:2796/5100 train_loss:3.5248 train_time:385710ms step_avg:138.45ms
step:2797/5100 train_loss:3.4471 train_time:385848ms step_avg:138.45ms
step:2798/5100 train_loss:3.5516 train_time:385984ms step_avg:138.44ms
step:2799/5100 train_loss:3.4939 train_time:386120ms step_avg:138.44ms
step:2800/5100 train_loss:3.6708 train_time:386259ms step_avg:138.44ms
step:2801/5100 train_loss:3.6278 train_time:386397ms step_avg:138.44ms
step:2802/5100 train_loss:3.5846 train_time:386534ms step_avg:138.44ms
step:2803/5100 train_loss:3.5384 train_time:386672ms step_avg:138.44ms
step:2804/5100 train_loss:3.7211 train_time:386811ms step_avg:138.44ms
step:2805/5100 train_loss:3.6806 train_time:386948ms step_avg:138.44ms
step:2806/5100 train_loss:3.4173 train_time:387084ms step_avg:138.44ms
step:2807/5100 train_loss:3.8117 train_time:387220ms step_avg:138.44ms
step:2808/5100 train_loss:3.5636 train_time:387358ms step_avg:138.44ms
step:2809/5100 train_loss:3.4759 train_time:387496ms step_avg:138.44ms
step:2810/5100 train_loss:3.5511 train_time:387634ms step_avg:138.44ms
step:2811/5100 train_loss:3.6614 train_time:387765ms step_avg:138.44ms
step:2812/5100 train_loss:3.6582 train_time:387902ms step_avg:138.44ms
step:2813/5100 train_loss:3.4018 train_time:388045ms step_avg:138.44ms
step:2814/5100 train_loss:3.6201 train_time:388180ms step_avg:138.44ms
step:2815/5100 train_loss:3.6973 train_time:388316ms step_avg:138.44ms
step:2816/5100 train_loss:3.5072 train_time:388455ms step_avg:138.44ms
step:2817/5100 train_loss:3.0742 train_time:388597ms step_avg:138.44ms
step:2818/5100 train_loss:3.5467 train_time:388735ms step_avg:138.44ms
step:2819/5100 train_loss:3.5155 train_time:388871ms step_avg:138.44ms
step:2820/5100 train_loss:3.6975 train_time:389010ms step_avg:138.44ms
step:2821/5100 train_loss:3.7323 train_time:389147ms step_avg:138.44ms
step:2822/5100 train_loss:3.6329 train_time:389282ms step_avg:138.44ms
step:2823/5100 train_loss:3.5634 train_time:389419ms step_avg:138.44ms
step:2824/5100 train_loss:3.5070 train_time:389556ms step_avg:138.44ms
step:2825/5100 train_loss:3.4182 train_time:389695ms step_avg:138.44ms
step:2826/5100 train_loss:3.6816 train_time:389834ms step_avg:138.44ms
step:2827/5100 train_loss:3.5898 train_time:389971ms step_avg:138.43ms
step:2828/5100 train_loss:3.4581 train_time:390111ms step_avg:138.44ms
step:2829/5100 train_loss:3.5855 train_time:390250ms step_avg:138.44ms
step:2830/5100 train_loss:3.5885 train_time:390386ms step_avg:138.43ms
step:2831/5100 train_loss:3.5351 train_time:390521ms step_avg:138.43ms
step:2832/5100 train_loss:3.6791 train_time:390661ms step_avg:138.43ms
step:2833/5100 train_loss:3.5919 train_time:390798ms step_avg:138.43ms
step:2834/5100 train_loss:3.5754 train_time:390936ms step_avg:138.43ms
step:2835/5100 train_loss:3.3917 train_time:391168ms step_avg:138.47ms
step:2836/5100 train_loss:3.6149 train_time:391299ms step_avg:138.46ms
step:2837/5100 train_loss:3.5424 train_time:391431ms step_avg:138.46ms
step:2838/5100 train_loss:3.8708 train_time:391567ms step_avg:138.46ms
step:2839/5100 train_loss:3.4909 train_time:391702ms step_avg:138.46ms
step:2840/5100 train_loss:3.4991 train_time:391837ms step_avg:138.46ms
step:2841/5100 train_loss:3.5591 train_time:391972ms step_avg:138.46ms
step:2842/5100 train_loss:3.4876 train_time:392115ms step_avg:138.46ms
step:2843/5100 train_loss:3.4862 train_time:392257ms step_avg:138.46ms
step:2844/5100 train_loss:3.6632 train_time:392392ms step_avg:138.46ms
step:2845/5100 train_loss:3.5568 train_time:392530ms step_avg:138.46ms
step:2846/5100 train_loss:3.5724 train_time:392667ms step_avg:138.46ms
step:2847/5100 train_loss:3.5291 train_time:392800ms step_avg:138.46ms
step:2848/5100 train_loss:3.8117 train_time:392936ms step_avg:138.46ms
step:2849/5100 train_loss:3.4778 train_time:393074ms step_avg:138.46ms
step:2850/5100 train_loss:3.4944 train_time:393391ms step_avg:138.52ms
step:2851/5100 train_loss:3.5943 train_time:393523ms step_avg:138.52ms
step:2852/5100 train_loss:3.5687 train_time:393657ms step_avg:138.51ms
step:2853/5100 train_loss:3.5370 train_time:393792ms step_avg:138.51ms
step:2854/5100 train_loss:3.6182 train_time:393929ms step_avg:138.51ms
step:2855/5100 train_loss:3.4316 train_time:394062ms step_avg:138.51ms
step:2856/5100 train_loss:3.4512 train_time:394197ms step_avg:138.51ms
step:2857/5100 train_loss:3.5423 train_time:394334ms step_avg:138.51ms
step:2858/5100 train_loss:3.5476 train_time:394476ms step_avg:138.51ms
step:2859/5100 train_loss:3.4129 train_time:394615ms step_avg:138.51ms
step:2860/5100 train_loss:3.5377 train_time:394752ms step_avg:138.51ms
step:2861/5100 train_loss:3.5014 train_time:394889ms step_avg:138.51ms
step:2862/5100 train_loss:3.5429 train_time:395024ms step_avg:138.51ms
step:2863/5100 train_loss:3.5781 train_time:395158ms step_avg:138.51ms
step:2864/5100 train_loss:3.8416 train_time:395294ms step_avg:138.51ms
step:2865/5100 train_loss:3.6702 train_time:395434ms step_avg:138.51ms
step:2866/5100 train_loss:3.5415 train_time:395574ms step_avg:138.51ms
step:2867/5100 train_loss:3.4424 train_time:395711ms step_avg:138.51ms
step:2868/5100 train_loss:3.6298 train_time:395850ms step_avg:138.51ms
step:2869/5100 train_loss:3.5795 train_time:395986ms step_avg:138.51ms
step:2870/5100 train_loss:3.5475 train_time:396120ms step_avg:138.50ms
step:2871/5100 train_loss:3.6795 train_time:396258ms step_avg:138.50ms
step:2872/5100 train_loss:3.4667 train_time:396397ms step_avg:138.50ms
step:2873/5100 train_loss:3.5129 train_time:396536ms step_avg:138.50ms
step:2874/5100 train_loss:3.3779 train_time:396674ms step_avg:138.50ms
step:2875/5100 train_loss:3.5350 train_time:396812ms step_avg:138.50ms
step:2875/5100 val_loss:3.5431 train_time:396884ms step_avg:138.53ms
step:2876/5100 train_loss:3.4615 train_time:396956ms step_avg:138.51ms
step:2877/5100 train_loss:3.4333 train_time:397102ms step_avg:138.51ms
step:2878/5100 train_loss:3.5368 train_time:397241ms step_avg:138.51ms
step:2879/5100 train_loss:3.6493 train_time:397376ms step_avg:138.51ms
step:2880/5100 train_loss:3.6077 train_time:397511ms step_avg:138.51ms
step:2881/5100 train_loss:3.5307 train_time:397647ms step_avg:138.50ms
step:2882/5100 train_loss:3.5134 train_time:397784ms step_avg:138.50ms
step:2883/5100 train_loss:3.6508 train_time:397919ms step_avg:138.50ms
step:2884/5100 train_loss:3.4403 train_time:398061ms step_avg:138.50ms
step:2885/5100 train_loss:3.4619 train_time:398200ms step_avg:138.50ms
step:2886/5100 train_loss:3.5007 train_time:398338ms step_avg:138.50ms
step:2887/5100 train_loss:3.4953 train_time:398475ms step_avg:138.50ms
step:2888/5100 train_loss:3.5174 train_time:398610ms step_avg:138.50ms
step:2889/5100 train_loss:3.5314 train_time:398745ms step_avg:138.50ms
step:2890/5100 train_loss:3.7075 train_time:398880ms step_avg:138.50ms
step:2891/5100 train_loss:3.5648 train_time:399018ms step_avg:138.50ms
step:2892/5100 train_loss:3.3979 train_time:399158ms step_avg:138.50ms
step:2893/5100 train_loss:3.3266 train_time:399294ms step_avg:138.50ms
step:2894/5100 train_loss:3.4761 train_time:399433ms step_avg:138.50ms
step:2895/5100 train_loss:3.3407 train_time:399570ms step_avg:138.50ms
step:2896/5100 train_loss:3.5285 train_time:399706ms step_avg:138.50ms
step:2897/5100 train_loss:3.6560 train_time:399841ms step_avg:138.50ms
step:2898/5100 train_loss:3.4765 train_time:399979ms step_avg:138.50ms
step:2899/5100 train_loss:3.5728 train_time:400119ms step_avg:138.50ms
step:2900/5100 train_loss:3.4730 train_time:400257ms step_avg:138.50ms
step:2901/5100 train_loss:3.6664 train_time:400395ms step_avg:138.50ms
step:2902/5100 train_loss:3.6479 train_time:400534ms step_avg:138.50ms
step:2903/5100 train_loss:3.6977 train_time:400670ms step_avg:138.50ms
step:2904/5100 train_loss:3.3960 train_time:400804ms step_avg:138.49ms
step:2905/5100 train_loss:3.5374 train_time:400942ms step_avg:138.49ms
step:2906/5100 train_loss:3.5114 train_time:401079ms step_avg:138.49ms
step:2907/5100 train_loss:3.6029 train_time:401218ms step_avg:138.49ms
step:2908/5100 train_loss:3.5342 train_time:401356ms step_avg:138.49ms
step:2909/5100 train_loss:3.4883 train_time:401494ms step_avg:138.49ms
step:2910/5100 train_loss:3.8266 train_time:401634ms step_avg:138.49ms
step:2911/5100 train_loss:3.5533 train_time:401771ms step_avg:138.49ms
step:2912/5100 train_loss:3.4483 train_time:401907ms step_avg:138.49ms
step:2913/5100 train_loss:3.4330 train_time:402041ms step_avg:138.49ms
step:2914/5100 train_loss:3.9148 train_time:402180ms step_avg:138.49ms
step:2915/5100 train_loss:3.5083 train_time:402318ms step_avg:138.49ms
step:2916/5100 train_loss:3.4501 train_time:402456ms step_avg:138.49ms
step:2917/5100 train_loss:3.4420 train_time:402596ms step_avg:138.49ms
step:2918/5100 train_loss:3.7273 train_time:402735ms step_avg:138.49ms
step:2919/5100 train_loss:3.2239 train_time:402872ms step_avg:138.49ms
step:2920/5100 train_loss:3.4517 train_time:403009ms step_avg:138.49ms
step:2921/5100 train_loss:3.4610 train_time:403143ms step_avg:138.49ms
step:2922/5100 train_loss:3.5525 train_time:403282ms step_avg:138.49ms
step:2923/5100 train_loss:3.5934 train_time:403421ms step_avg:138.49ms
step:2924/5100 train_loss:3.6278 train_time:403558ms step_avg:138.49ms
step:2925/5100 train_loss:3.6362 train_time:403696ms step_avg:138.49ms
step:2926/5100 train_loss:3.5061 train_time:403835ms step_avg:138.49ms
step:2927/5100 train_loss:3.5371 train_time:403972ms step_avg:138.49ms
step:2928/5100 train_loss:3.5165 train_time:404108ms step_avg:138.49ms
step:2929/5100 train_loss:3.5128 train_time:404244ms step_avg:138.49ms
step:2930/5100 train_loss:3.4801 train_time:404381ms step_avg:138.49ms
step:2931/5100 train_loss:3.5103 train_time:404520ms step_avg:138.49ms
step:2932/5100 train_loss:3.6449 train_time:404659ms step_avg:138.49ms
step:2933/5100 train_loss:3.6772 train_time:404797ms step_avg:138.49ms
step:2934/5100 train_loss:3.6474 train_time:404936ms step_avg:138.49ms
step:2935/5100 train_loss:3.4873 train_time:405073ms step_avg:138.49ms
step:2936/5100 train_loss:3.5535 train_time:405209ms step_avg:138.49ms
step:2937/5100 train_loss:3.4721 train_time:405344ms step_avg:138.48ms
step:2938/5100 train_loss:3.5069 train_time:405480ms step_avg:138.48ms
step:2939/5100 train_loss:3.5356 train_time:405618ms step_avg:138.48ms
step:2940/5100 train_loss:3.5784 train_time:405755ms step_avg:138.48ms
step:2941/5100 train_loss:3.6228 train_time:405894ms step_avg:138.48ms
step:2942/5100 train_loss:3.5981 train_time:406032ms step_avg:138.48ms
step:2943/5100 train_loss:3.5336 train_time:406168ms step_avg:138.48ms
step:2944/5100 train_loss:3.4259 train_time:406304ms step_avg:138.48ms
step:2945/5100 train_loss:3.3517 train_time:406440ms step_avg:138.48ms
step:2946/5100 train_loss:3.5542 train_time:406578ms step_avg:138.48ms
step:2947/5100 train_loss:3.6324 train_time:406716ms step_avg:138.48ms
step:2948/5100 train_loss:3.5537 train_time:406854ms step_avg:138.48ms
step:2949/5100 train_loss:3.7254 train_time:406993ms step_avg:138.48ms
step:2950/5100 train_loss:3.5625 train_time:407132ms step_avg:138.48ms
step:2951/5100 train_loss:3.5638 train_time:407271ms step_avg:138.48ms
step:2952/5100 train_loss:3.9780 train_time:407406ms step_avg:138.48ms
step:2953/5100 train_loss:3.6419 train_time:407542ms step_avg:138.48ms
step:2954/5100 train_loss:3.5846 train_time:407680ms step_avg:138.48ms
step:2955/5100 train_loss:3.5872 train_time:407818ms step_avg:138.48ms
step:2956/5100 train_loss:3.5202 train_time:407957ms step_avg:138.48ms
step:2957/5100 train_loss:3.5523 train_time:408095ms step_avg:138.48ms
step:2958/5100 train_loss:3.4215 train_time:408234ms step_avg:138.48ms
step:2959/5100 train_loss:3.5082 train_time:408372ms step_avg:138.48ms
step:2960/5100 train_loss:3.6450 train_time:408509ms step_avg:138.48ms
step:2961/5100 train_loss:3.4557 train_time:408645ms step_avg:138.48ms
step:2962/5100 train_loss:3.5821 train_time:408782ms step_avg:138.48ms
step:2963/5100 train_loss:3.4437 train_time:408919ms step_avg:138.48ms
step:2964/5100 train_loss:3.5004 train_time:409059ms step_avg:138.48ms
step:2965/5100 train_loss:3.4898 train_time:409197ms step_avg:138.48ms
step:2966/5100 train_loss:3.6085 train_time:409335ms step_avg:138.48ms
step:2967/5100 train_loss:3.4735 train_time:409470ms step_avg:138.47ms
step:2968/5100 train_loss:3.7231 train_time:409607ms step_avg:138.47ms
step:2969/5100 train_loss:3.5674 train_time:409743ms step_avg:138.47ms
step:2970/5100 train_loss:3.5813 train_time:409881ms step_avg:138.47ms
step:2971/5100 train_loss:3.5818 train_time:410019ms step_avg:138.47ms
step:2972/5100 train_loss:3.6496 train_time:410158ms step_avg:138.47ms
step:2973/5100 train_loss:3.4735 train_time:410296ms step_avg:138.47ms
step:2974/5100 train_loss:3.4829 train_time:410434ms step_avg:138.47ms
step:2975/5100 train_loss:3.3963 train_time:410572ms step_avg:138.47ms
step:2976/5100 train_loss:3.4754 train_time:410709ms step_avg:138.47ms
step:2977/5100 train_loss:3.4755 train_time:410844ms step_avg:138.47ms
step:2978/5100 train_loss:3.4846 train_time:410980ms step_avg:138.47ms
step:2979/5100 train_loss:3.7650 train_time:411120ms step_avg:138.47ms
step:2980/5100 train_loss:3.5838 train_time:411258ms step_avg:138.47ms
step:2981/5100 train_loss:3.6194 train_time:411396ms step_avg:138.47ms
step:2982/5100 train_loss:3.6303 train_time:411534ms step_avg:138.47ms
step:2983/5100 train_loss:3.7186 train_time:411673ms step_avg:138.47ms
step:2984/5100 train_loss:3.5092 train_time:411810ms step_avg:138.47ms
step:2985/5100 train_loss:3.5981 train_time:411945ms step_avg:138.47ms
step:2986/5100 train_loss:3.6069 train_time:412081ms step_avg:138.47ms
step:2987/5100 train_loss:3.5532 train_time:412220ms step_avg:138.47ms
step:2988/5100 train_loss:3.6768 train_time:412359ms step_avg:138.47ms
step:2989/5100 train_loss:3.2797 train_time:412497ms step_avg:138.47ms
step:2990/5100 train_loss:3.6190 train_time:412636ms step_avg:138.47ms
step:2991/5100 train_loss:3.5705 train_time:412773ms step_avg:138.47ms
step:2992/5100 train_loss:3.5562 train_time:412910ms step_avg:138.47ms
step:2993/5100 train_loss:3.4703 train_time:413046ms step_avg:138.47ms
step:2994/5100 train_loss:3.6126 train_time:413182ms step_avg:138.47ms
step:2995/5100 train_loss:3.4321 train_time:413321ms step_avg:138.47ms
step:2996/5100 train_loss:3.4637 train_time:413458ms step_avg:138.47ms
step:2997/5100 train_loss:3.5332 train_time:413596ms step_avg:138.47ms
step:2998/5100 train_loss:3.4723 train_time:413734ms step_avg:138.47ms
step:2999/5100 train_loss:3.5939 train_time:413873ms step_avg:138.47ms
step:3000/5100 train_loss:3.5054 train_time:414010ms step_avg:138.46ms
step:3000/5100 val_loss:3.5345 train_time:414081ms step_avg:138.49ms
step:3001/5100 train_loss:3.4814 train_time:414152ms step_avg:138.47ms
step:3002/5100 train_loss:3.4264 train_time:414296ms step_avg:138.47ms
step:3003/5100 train_loss:3.4782 train_time:414433ms step_avg:138.47ms
step:3004/5100 train_loss:3.6063 train_time:414569ms step_avg:138.47ms
step:3005/5100 train_loss:3.9433 train_time:414704ms step_avg:138.47ms
step:3006/5100 train_loss:3.5148 train_time:414839ms step_avg:138.46ms
step:3007/5100 train_loss:3.5837 train_time:414973ms step_avg:138.46ms
step:3008/5100 train_loss:3.4063 train_time:415114ms step_avg:138.46ms
step:3009/5100 train_loss:3.6074 train_time:415253ms step_avg:138.46ms
step:3010/5100 train_loss:3.4972 train_time:415392ms step_avg:138.46ms
step:3011/5100 train_loss:3.5665 train_time:415529ms step_avg:138.46ms
step:3012/5100 train_loss:3.5727 train_time:415667ms step_avg:138.46ms
step:3013/5100 train_loss:3.4651 train_time:415802ms step_avg:138.46ms
step:3014/5100 train_loss:3.6617 train_time:415936ms step_avg:138.46ms
step:3015/5100 train_loss:3.6262 train_time:416074ms step_avg:138.46ms
step:3016/5100 train_loss:3.4876 train_time:416213ms step_avg:138.46ms
step:3017/5100 train_loss:3.5168 train_time:416352ms step_avg:138.46ms
step:3018/5100 train_loss:3.5716 train_time:416490ms step_avg:138.46ms
step:3019/5100 train_loss:3.5960 train_time:416628ms step_avg:138.46ms
step:3020/5100 train_loss:3.3959 train_time:416764ms step_avg:138.46ms
step:3021/5100 train_loss:3.6758 train_time:416900ms step_avg:138.46ms
step:3022/5100 train_loss:3.5107 train_time:417034ms step_avg:138.46ms
step:3023/5100 train_loss:3.4383 train_time:417172ms step_avg:138.46ms
step:3024/5100 train_loss:3.5310 train_time:417402ms step_avg:138.49ms
step:3025/5100 train_loss:3.5229 train_time:417532ms step_avg:138.48ms
step:3026/5100 train_loss:3.5657 train_time:417665ms step_avg:138.48ms
step:3027/5100 train_loss:3.5916 train_time:417802ms step_avg:138.48ms
step:3028/5100 train_loss:3.4972 train_time:417936ms step_avg:138.48ms
step:3029/5100 train_loss:3.3013 train_time:418073ms step_avg:138.48ms
step:3030/5100 train_loss:3.6422 train_time:418208ms step_avg:138.48ms
step:3031/5100 train_loss:3.4008 train_time:418346ms step_avg:138.48ms
step:3032/5100 train_loss:3.3987 train_time:418489ms step_avg:138.48ms
step:3033/5100 train_loss:3.7413 train_time:418627ms step_avg:138.48ms
step:3034/5100 train_loss:3.7243 train_time:418765ms step_avg:138.48ms
step:3035/5100 train_loss:3.4888 train_time:418902ms step_avg:138.48ms
step:3036/5100 train_loss:3.5659 train_time:419035ms step_avg:138.48ms
step:3037/5100 train_loss:3.5245 train_time:419170ms step_avg:138.48ms
step:3038/5100 train_loss:3.4214 train_time:419307ms step_avg:138.48ms
step:3039/5100 train_loss:3.4897 train_time:419449ms step_avg:138.48ms
step:3040/5100 train_loss:3.5871 train_time:419763ms step_avg:138.54ms
step:3041/5100 train_loss:3.5797 train_time:419893ms step_avg:138.53ms
step:3042/5100 train_loss:3.3976 train_time:420027ms step_avg:138.53ms
step:3043/5100 train_loss:3.5203 train_time:420163ms step_avg:138.53ms
step:3044/5100 train_loss:3.5590 train_time:420299ms step_avg:138.53ms
step:3045/5100 train_loss:3.5650 train_time:420433ms step_avg:138.53ms
step:3046/5100 train_loss:3.6419 train_time:420569ms step_avg:138.53ms
step:3047/5100 train_loss:3.4560 train_time:420706ms step_avg:138.53ms
step:3048/5100 train_loss:3.5721 train_time:420850ms step_avg:138.53ms
step:3049/5100 train_loss:3.5233 train_time:420989ms step_avg:138.53ms
step:3050/5100 train_loss:3.4570 train_time:421126ms step_avg:138.53ms
step:3051/5100 train_loss:3.5880 train_time:421262ms step_avg:138.53ms
step:3052/5100 train_loss:3.4301 train_time:421398ms step_avg:138.53ms
step:3053/5100 train_loss:3.6667 train_time:421526ms step_avg:138.52ms
step:3054/5100 train_loss:3.6038 train_time:421670ms step_avg:138.52ms
step:3055/5100 train_loss:3.5942 train_time:421808ms step_avg:138.52ms
step:3056/5100 train_loss:3.5825 train_time:421947ms step_avg:138.52ms
step:3057/5100 train_loss:3.4766 train_time:422085ms step_avg:138.52ms
step:3058/5100 train_loss:3.5018 train_time:422226ms step_avg:138.53ms
step:3059/5100 train_loss:3.5896 train_time:422360ms step_avg:138.52ms
step:3060/5100 train_loss:3.4780 train_time:422496ms step_avg:138.52ms
step:3061/5100 train_loss:3.5378 train_time:422631ms step_avg:138.52ms
step:3062/5100 train_loss:3.5377 train_time:422770ms step_avg:138.52ms
step:3063/5100 train_loss:3.4773 train_time:422910ms step_avg:138.52ms
step:3064/5100 train_loss:3.4573 train_time:423048ms step_avg:138.52ms
step:3065/5100 train_loss:3.4689 train_time:423187ms step_avg:138.52ms
step:3066/5100 train_loss:3.4528 train_time:423324ms step_avg:138.52ms
step:3067/5100 train_loss:3.4407 train_time:423460ms step_avg:138.52ms
step:3068/5100 train_loss:3.3922 train_time:423594ms step_avg:138.52ms
step:3069/5100 train_loss:3.4362 train_time:423732ms step_avg:138.52ms
step:3070/5100 train_loss:3.4381 train_time:423870ms step_avg:138.52ms
step:3071/5100 train_loss:3.6125 train_time:424009ms step_avg:138.52ms
step:3072/5100 train_loss:3.5488 train_time:424148ms step_avg:138.52ms
step:3073/5100 train_loss:3.5810 train_time:424287ms step_avg:138.52ms
step:3074/5100 train_loss:3.5734 train_time:424425ms step_avg:138.52ms
step:3075/5100 train_loss:3.5235 train_time:424561ms step_avg:138.52ms
step:3076/5100 train_loss:3.5684 train_time:424696ms step_avg:138.52ms
step:3077/5100 train_loss:3.6353 train_time:424833ms step_avg:138.52ms
step:3078/5100 train_loss:3.4361 train_time:424971ms step_avg:138.52ms
step:3079/5100 train_loss:3.9763 train_time:425110ms step_avg:138.52ms
step:3080/5100 train_loss:3.5308 train_time:425249ms step_avg:138.52ms
step:3081/5100 train_loss:3.4979 train_time:425388ms step_avg:138.52ms
step:3082/5100 train_loss:3.6271 train_time:425525ms step_avg:138.52ms
step:3083/5100 train_loss:3.4458 train_time:425662ms step_avg:138.52ms
step:3084/5100 train_loss:3.4768 train_time:425797ms step_avg:138.52ms
step:3085/5100 train_loss:3.5264 train_time:425934ms step_avg:138.52ms
step:3086/5100 train_loss:3.6177 train_time:426072ms step_avg:138.52ms
step:3087/5100 train_loss:3.5280 train_time:426211ms step_avg:138.51ms
step:3088/5100 train_loss:3.4441 train_time:426350ms step_avg:138.52ms
step:3089/5100 train_loss:3.5900 train_time:426486ms step_avg:138.51ms
step:3090/5100 train_loss:3.4622 train_time:426625ms step_avg:138.51ms
step:3091/5100 train_loss:3.7165 train_time:426761ms step_avg:138.51ms
step:3092/5100 train_loss:4.2813 train_time:426896ms step_avg:138.51ms
step:3093/5100 train_loss:3.5510 train_time:427034ms step_avg:138.51ms
step:3094/5100 train_loss:3.4501 train_time:427172ms step_avg:138.51ms
step:3095/5100 train_loss:3.4117 train_time:427311ms step_avg:138.51ms
step:3096/5100 train_loss:3.5862 train_time:427449ms step_avg:138.51ms
step:3097/5100 train_loss:3.6939 train_time:427588ms step_avg:138.51ms
step:3098/5100 train_loss:3.4787 train_time:427724ms step_avg:138.51ms
step:3099/5100 train_loss:3.5212 train_time:427859ms step_avg:138.51ms
step:3100/5100 train_loss:3.6934 train_time:427994ms step_avg:138.51ms
step:3101/5100 train_loss:3.5854 train_time:428132ms step_avg:138.51ms
step:3102/5100 train_loss:3.5774 train_time:428270ms step_avg:138.51ms
step:3103/5100 train_loss:3.4844 train_time:428409ms step_avg:138.51ms
step:3104/5100 train_loss:3.7394 train_time:428547ms step_avg:138.51ms
step:3105/5100 train_loss:3.5556 train_time:428687ms step_avg:138.51ms
step:3106/5100 train_loss:3.4157 train_time:428825ms step_avg:138.51ms
step:3107/5100 train_loss:3.4562 train_time:428962ms step_avg:138.51ms
step:3108/5100 train_loss:3.4013 train_time:429098ms step_avg:138.51ms
step:3109/5100 train_loss:3.6265 train_time:429234ms step_avg:138.51ms
step:3110/5100 train_loss:3.5128 train_time:429373ms step_avg:138.51ms
step:3111/5100 train_loss:3.5574 train_time:429511ms step_avg:138.51ms
step:3112/5100 train_loss:3.5312 train_time:429649ms step_avg:138.51ms
step:3113/5100 train_loss:3.5900 train_time:429787ms step_avg:138.51ms
step:3114/5100 train_loss:3.5301 train_time:429925ms step_avg:138.51ms
step:3115/5100 train_loss:3.5513 train_time:430061ms step_avg:138.51ms
step:3116/5100 train_loss:3.5746 train_time:430196ms step_avg:138.50ms
step:3117/5100 train_loss:3.4370 train_time:430333ms step_avg:138.50ms
step:3118/5100 train_loss:3.4487 train_time:430471ms step_avg:138.50ms
step:3119/5100 train_loss:3.6496 train_time:430610ms step_avg:138.50ms
step:3120/5100 train_loss:3.6194 train_time:430748ms step_avg:138.50ms
step:3121/5100 train_loss:3.4025 train_time:430886ms step_avg:138.50ms
step:3122/5100 train_loss:3.5921 train_time:431024ms step_avg:138.50ms
step:3123/5100 train_loss:3.6523 train_time:431161ms step_avg:138.50ms
step:3124/5100 train_loss:3.6195 train_time:431295ms step_avg:138.50ms
step:3125/5100 train_loss:3.4096 train_time:431433ms step_avg:138.50ms
step:3125/5100 val_loss:3.5223 train_time:431506ms step_avg:138.53ms
step:3126/5100 train_loss:3.4907 train_time:431576ms step_avg:138.50ms
step:3127/5100 train_loss:3.5347 train_time:431721ms step_avg:138.51ms
step:3128/5100 train_loss:3.6227 train_time:431857ms step_avg:138.50ms
step:3129/5100 train_loss:3.6835 train_time:431993ms step_avg:138.50ms
step:3130/5100 train_loss:3.3892 train_time:432127ms step_avg:138.50ms
step:3131/5100 train_loss:3.5503 train_time:432263ms step_avg:138.50ms
step:3132/5100 train_loss:3.5569 train_time:432396ms step_avg:138.50ms
step:3133/5100 train_loss:3.5708 train_time:432534ms step_avg:138.50ms
step:3134/5100 train_loss:3.4844 train_time:432677ms step_avg:138.50ms
step:3135/5100 train_loss:3.6001 train_time:432815ms step_avg:138.50ms
step:3136/5100 train_loss:3.5063 train_time:432952ms step_avg:138.50ms
step:3137/5100 train_loss:3.5731 train_time:433088ms step_avg:138.50ms
step:3138/5100 train_loss:3.7724 train_time:433225ms step_avg:138.50ms
step:3139/5100 train_loss:3.7298 train_time:433361ms step_avg:138.50ms
step:3140/5100 train_loss:3.4961 train_time:433494ms step_avg:138.50ms
step:3141/5100 train_loss:3.5135 train_time:433634ms step_avg:138.50ms
step:3142/5100 train_loss:3.4335 train_time:433772ms step_avg:138.50ms
step:3143/5100 train_loss:3.5271 train_time:433911ms step_avg:138.50ms
step:3144/5100 train_loss:3.3319 train_time:434047ms step_avg:138.50ms
step:3145/5100 train_loss:3.5658 train_time:434186ms step_avg:138.50ms
step:3146/5100 train_loss:3.4824 train_time:434324ms step_avg:138.50ms
step:3147/5100 train_loss:3.5090 train_time:434459ms step_avg:138.49ms
step:3148/5100 train_loss:3.6768 train_time:434596ms step_avg:138.49ms
step:3149/5100 train_loss:3.7683 train_time:434734ms step_avg:138.49ms
step:3150/5100 train_loss:3.6329 train_time:434872ms step_avg:138.49ms
step:3151/5100 train_loss:3.4499 train_time:435009ms step_avg:138.49ms
step:3152/5100 train_loss:3.4800 train_time:435148ms step_avg:138.49ms
step:3153/5100 train_loss:3.4686 train_time:435285ms step_avg:138.49ms
step:3154/5100 train_loss:3.5868 train_time:435421ms step_avg:138.49ms
step:3155/5100 train_loss:3.4026 train_time:435556ms step_avg:138.49ms
step:3156/5100 train_loss:3.5484 train_time:435692ms step_avg:138.49ms
step:3157/5100 train_loss:3.4987 train_time:435831ms step_avg:138.49ms
step:3158/5100 train_loss:3.6070 train_time:435969ms step_avg:138.49ms
step:3159/5100 train_loss:3.6754 train_time:436107ms step_avg:138.49ms
step:3160/5100 train_loss:3.5249 train_time:436246ms step_avg:138.49ms
step:3161/5100 train_loss:3.5820 train_time:436383ms step_avg:138.49ms
step:3162/5100 train_loss:3.6457 train_time:436519ms step_avg:138.49ms
step:3163/5100 train_loss:3.5578 train_time:436654ms step_avg:138.49ms
step:3164/5100 train_loss:3.6180 train_time:436792ms step_avg:138.49ms
step:3165/5100 train_loss:3.4365 train_time:436929ms step_avg:138.49ms
step:3166/5100 train_loss:3.4215 train_time:437068ms step_avg:138.49ms
step:3167/5100 train_loss:3.4574 train_time:437207ms step_avg:138.49ms
step:3168/5100 train_loss:3.2880 train_time:437344ms step_avg:138.49ms
step:3169/5100 train_loss:3.4491 train_time:437480ms step_avg:138.49ms
step:3170/5100 train_loss:3.5949 train_time:437617ms step_avg:138.49ms
step:3171/5100 train_loss:3.6134 train_time:437754ms step_avg:138.49ms
step:3172/5100 train_loss:3.5884 train_time:437892ms step_avg:138.49ms
step:3173/5100 train_loss:3.5467 train_time:438030ms step_avg:138.49ms
step:3174/5100 train_loss:3.5232 train_time:438169ms step_avg:138.49ms
step:3175/5100 train_loss:3.5270 train_time:438307ms step_avg:138.49ms
step:3176/5100 train_loss:3.5356 train_time:438445ms step_avg:138.49ms
step:3177/5100 train_loss:3.4568 train_time:438580ms step_avg:138.48ms
step:3178/5100 train_loss:3.5893 train_time:438714ms step_avg:138.48ms
step:3179/5100 train_loss:3.6573 train_time:438852ms step_avg:138.48ms
step:3180/5100 train_loss:3.5200 train_time:438990ms step_avg:138.48ms
step:3181/5100 train_loss:3.4937 train_time:439128ms step_avg:138.48ms
step:3182/5100 train_loss:3.5420 train_time:439266ms step_avg:138.48ms
step:3183/5100 train_loss:3.6451 train_time:439405ms step_avg:138.48ms
step:3184/5100 train_loss:3.6608 train_time:439541ms step_avg:138.48ms
step:3185/5100 train_loss:3.5496 train_time:439676ms step_avg:138.48ms
step:3186/5100 train_loss:3.6290 train_time:439812ms step_avg:138.48ms
step:3187/5100 train_loss:3.6057 train_time:439951ms step_avg:138.48ms
step:3188/5100 train_loss:3.3916 train_time:440089ms step_avg:138.48ms
step:3189/5100 train_loss:3.5615 train_time:440227ms step_avg:138.48ms
step:3190/5100 train_loss:3.5179 train_time:440365ms step_avg:138.48ms
step:3191/5100 train_loss:3.5442 train_time:440504ms step_avg:138.48ms
step:3192/5100 train_loss:3.4969 train_time:440640ms step_avg:138.48ms
step:3193/5100 train_loss:3.4293 train_time:440775ms step_avg:138.48ms
step:3194/5100 train_loss:4.4506 train_time:440912ms step_avg:138.48ms
step:3195/5100 train_loss:3.5523 train_time:441051ms step_avg:138.48ms
step:3196/5100 train_loss:3.3416 train_time:441189ms step_avg:138.48ms
step:3197/5100 train_loss:3.5040 train_time:441327ms step_avg:138.48ms
step:3198/5100 train_loss:3.3883 train_time:441465ms step_avg:138.48ms
step:3199/5100 train_loss:3.4840 train_time:441599ms step_avg:138.48ms
step:3200/5100 train_loss:3.4130 train_time:441736ms step_avg:138.48ms
step:3201/5100 train_loss:3.5017 train_time:441874ms step_avg:138.48ms
step:3202/5100 train_loss:3.5913 train_time:442013ms step_avg:138.48ms
step:3203/5100 train_loss:3.4523 train_time:442151ms step_avg:138.48ms
step:3204/5100 train_loss:3.4819 train_time:442289ms step_avg:138.47ms
step:3205/5100 train_loss:3.5714 train_time:442427ms step_avg:138.47ms
step:3206/5100 train_loss:3.7367 train_time:442565ms step_avg:138.47ms
step:3207/5100 train_loss:3.3337 train_time:442703ms step_avg:138.47ms
step:3208/5100 train_loss:3.6825 train_time:442838ms step_avg:138.47ms
step:3209/5100 train_loss:3.5357 train_time:442976ms step_avg:138.47ms
step:3210/5100 train_loss:3.5992 train_time:443114ms step_avg:138.47ms
step:3211/5100 train_loss:3.6895 train_time:443254ms step_avg:138.47ms
step:3212/5100 train_loss:3.3791 train_time:443391ms step_avg:138.47ms
step:3213/5100 train_loss:3.4337 train_time:443627ms step_avg:138.50ms
step:3214/5100 train_loss:3.6334 train_time:443759ms step_avg:138.50ms
step:3215/5100 train_loss:3.4346 train_time:443891ms step_avg:138.50ms
step:3216/5100 train_loss:3.5003 train_time:444028ms step_avg:138.50ms
step:3217/5100 train_loss:3.3897 train_time:444162ms step_avg:138.50ms
step:3218/5100 train_loss:3.5316 train_time:444297ms step_avg:138.50ms
step:3219/5100 train_loss:3.5760 train_time:444431ms step_avg:138.50ms
step:3220/5100 train_loss:3.6265 train_time:444573ms step_avg:138.50ms
step:3221/5100 train_loss:3.5620 train_time:444717ms step_avg:138.50ms
step:3222/5100 train_loss:3.5581 train_time:444855ms step_avg:138.50ms
step:3223/5100 train_loss:3.4300 train_time:444992ms step_avg:138.50ms
step:3224/5100 train_loss:3.4461 train_time:445128ms step_avg:138.50ms
step:3225/5100 train_loss:3.4579 train_time:445265ms step_avg:138.50ms
step:3226/5100 train_loss:3.4925 train_time:445399ms step_avg:138.49ms
step:3227/5100 train_loss:3.4083 train_time:445535ms step_avg:138.49ms
step:3228/5100 train_loss:3.3422 train_time:445675ms step_avg:138.49ms
step:3229/5100 train_loss:3.4689 train_time:445815ms step_avg:138.49ms
step:3230/5100 train_loss:3.2573 train_time:446132ms step_avg:138.55ms
step:3231/5100 train_loss:3.4248 train_time:446264ms step_avg:138.55ms
step:3232/5100 train_loss:3.4163 train_time:446397ms step_avg:138.55ms
step:3233/5100 train_loss:3.6569 train_time:446531ms step_avg:138.55ms
step:3234/5100 train_loss:3.6391 train_time:446667ms step_avg:138.54ms
step:3235/5100 train_loss:3.6087 train_time:446802ms step_avg:138.54ms
step:3236/5100 train_loss:3.4933 train_time:446936ms step_avg:138.54ms
step:3237/5100 train_loss:3.6523 train_time:447074ms step_avg:138.54ms
step:3238/5100 train_loss:3.5150 train_time:447217ms step_avg:138.54ms
step:3239/5100 train_loss:3.6423 train_time:447353ms step_avg:138.54ms
step:3240/5100 train_loss:3.6146 train_time:447491ms step_avg:138.54ms
step:3241/5100 train_loss:3.5139 train_time:447628ms step_avg:138.54ms
step:3242/5100 train_loss:3.4554 train_time:447764ms step_avg:138.54ms
step:3243/5100 train_loss:3.6865 train_time:447897ms step_avg:138.54ms
step:3244/5100 train_loss:3.5624 train_time:448035ms step_avg:138.54ms
step:3245/5100 train_loss:3.6057 train_time:448175ms step_avg:138.54ms
step:3246/5100 train_loss:3.4921 train_time:448313ms step_avg:138.54ms
step:3247/5100 train_loss:3.6239 train_time:448452ms step_avg:138.54ms
step:3248/5100 train_loss:3.5654 train_time:448588ms step_avg:138.54ms
step:3249/5100 train_loss:3.4951 train_time:448725ms step_avg:138.54ms
step:3250/5100 train_loss:3.3713 train_time:448857ms step_avg:138.54ms
step:3250/5100 val_loss:3.5089 train_time:448928ms step_avg:138.56ms
step:3251/5100 train_loss:3.5715 train_time:449004ms step_avg:138.54ms
step:3252/5100 train_loss:3.5711 train_time:449147ms step_avg:138.54ms
step:3253/5100 train_loss:3.5232 train_time:449284ms step_avg:138.54ms
step:3254/5100 train_loss:3.4477 train_time:449418ms step_avg:138.54ms
step:3255/5100 train_loss:3.5991 train_time:449555ms step_avg:138.54ms
step:3256/5100 train_loss:3.6276 train_time:449688ms step_avg:138.54ms
step:3257/5100 train_loss:3.5721 train_time:449821ms step_avg:138.53ms
step:3258/5100 train_loss:3.5922 train_time:449963ms step_avg:138.54ms
step:3259/5100 train_loss:3.4285 train_time:450104ms step_avg:138.54ms
step:3260/5100 train_loss:3.5128 train_time:450242ms step_avg:138.54ms
step:3261/5100 train_loss:3.3823 train_time:450380ms step_avg:138.54ms
step:3262/5100 train_loss:3.4199 train_time:450518ms step_avg:138.54ms
step:3263/5100 train_loss:3.4523 train_time:450654ms step_avg:138.53ms
step:3264/5100 train_loss:3.6114 train_time:450789ms step_avg:138.53ms
step:3265/5100 train_loss:3.4893 train_time:450924ms step_avg:138.53ms
step:3266/5100 train_loss:3.5419 train_time:451063ms step_avg:138.53ms
step:3267/5100 train_loss:3.5552 train_time:451203ms step_avg:138.53ms
step:3268/5100 train_loss:3.6447 train_time:451341ms step_avg:138.53ms
step:3269/5100 train_loss:3.4525 train_time:451479ms step_avg:138.53ms
step:3270/5100 train_loss:3.5845 train_time:451617ms step_avg:138.53ms
step:3271/5100 train_loss:3.4613 train_time:451754ms step_avg:138.53ms
step:3272/5100 train_loss:3.3534 train_time:451890ms step_avg:138.53ms
step:3273/5100 train_loss:3.4647 train_time:452025ms step_avg:138.53ms
step:3274/5100 train_loss:3.6108 train_time:452163ms step_avg:138.53ms
step:3275/5100 train_loss:3.3992 train_time:452302ms step_avg:138.53ms
step:3276/5100 train_loss:3.5479 train_time:452441ms step_avg:138.53ms
step:3277/5100 train_loss:3.5480 train_time:452579ms step_avg:138.53ms
step:3278/5100 train_loss:3.5402 train_time:452716ms step_avg:138.53ms
step:3279/5100 train_loss:3.5029 train_time:452853ms step_avg:138.53ms
step:3280/5100 train_loss:3.6602 train_time:452992ms step_avg:138.53ms
step:3281/5100 train_loss:3.5006 train_time:453126ms step_avg:138.53ms
step:3282/5100 train_loss:3.5575 train_time:453265ms step_avg:138.53ms
step:3283/5100 train_loss:3.4078 train_time:453402ms step_avg:138.53ms
step:3284/5100 train_loss:3.5448 train_time:453541ms step_avg:138.53ms
step:3285/5100 train_loss:3.5959 train_time:453679ms step_avg:138.53ms
step:3286/5100 train_loss:3.5802 train_time:453818ms step_avg:138.53ms
step:3287/5100 train_loss:3.6213 train_time:453955ms step_avg:138.53ms
step:3288/5100 train_loss:3.4871 train_time:454094ms step_avg:138.53ms
step:3289/5100 train_loss:3.6003 train_time:454235ms step_avg:138.53ms
step:3290/5100 train_loss:3.5235 train_time:454367ms step_avg:138.53ms
step:3291/5100 train_loss:3.4071 train_time:454504ms step_avg:138.53ms
step:3292/5100 train_loss:3.5330 train_time:454643ms step_avg:138.53ms
step:3293/5100 train_loss:3.5652 train_time:454782ms step_avg:138.53ms
step:3294/5100 train_loss:3.5567 train_time:454919ms step_avg:138.53ms
step:3295/5100 train_loss:3.4533 train_time:455058ms step_avg:138.53ms
step:3296/5100 train_loss:3.4959 train_time:455195ms step_avg:138.53ms
step:3297/5100 train_loss:3.5492 train_time:455333ms step_avg:138.53ms
step:3298/5100 train_loss:3.5403 train_time:455468ms step_avg:138.52ms
step:3299/5100 train_loss:3.5225 train_time:455604ms step_avg:138.52ms
step:3300/5100 train_loss:3.5714 train_time:455742ms step_avg:138.52ms
step:3301/5100 train_loss:3.4872 train_time:455880ms step_avg:138.52ms
step:3302/5100 train_loss:3.5458 train_time:456018ms step_avg:138.52ms
step:3303/5100 train_loss:3.5034 train_time:456157ms step_avg:138.52ms
step:3304/5100 train_loss:3.5083 train_time:456294ms step_avg:138.52ms
step:3305/5100 train_loss:3.5088 train_time:456434ms step_avg:138.52ms
step:3306/5100 train_loss:3.6079 train_time:456571ms step_avg:138.52ms
step:3307/5100 train_loss:3.5279 train_time:456706ms step_avg:138.52ms
step:3308/5100 train_loss:3.4910 train_time:456844ms step_avg:138.52ms
step:3309/5100 train_loss:3.6119 train_time:456980ms step_avg:138.52ms
step:3310/5100 train_loss:3.4971 train_time:457121ms step_avg:138.52ms
step:3311/5100 train_loss:3.4274 train_time:457258ms step_avg:138.52ms
step:3312/5100 train_loss:3.5521 train_time:457399ms step_avg:138.52ms
step:3313/5100 train_loss:3.5097 train_time:457537ms step_avg:138.52ms
step:3314/5100 train_loss:3.7152 train_time:457674ms step_avg:138.52ms
step:3315/5100 train_loss:3.5411 train_time:457811ms step_avg:138.52ms
step:3316/5100 train_loss:3.5133 train_time:457948ms step_avg:138.52ms
step:3317/5100 train_loss:3.1444 train_time:458083ms step_avg:138.52ms
step:3318/5100 train_loss:3.6435 train_time:458222ms step_avg:138.52ms
step:3319/5100 train_loss:3.4896 train_time:458360ms step_avg:138.52ms
step:3320/5100 train_loss:3.5570 train_time:458499ms step_avg:138.52ms
step:3321/5100 train_loss:3.4876 train_time:458637ms step_avg:138.52ms
step:3322/5100 train_loss:3.5564 train_time:458775ms step_avg:138.52ms
step:3323/5100 train_loss:3.4961 train_time:458912ms step_avg:138.52ms
step:3324/5100 train_loss:3.4222 train_time:459048ms step_avg:138.52ms
step:3325/5100 train_loss:3.3607 train_time:459185ms step_avg:138.52ms
step:3326/5100 train_loss:3.5174 train_time:459322ms step_avg:138.52ms
step:3327/5100 train_loss:3.4791 train_time:459461ms step_avg:138.52ms
step:3328/5100 train_loss:3.4075 train_time:459600ms step_avg:138.52ms
step:3329/5100 train_loss:3.4462 train_time:459738ms step_avg:138.52ms
step:3330/5100 train_loss:3.3993 train_time:459878ms step_avg:138.52ms
step:3331/5100 train_loss:3.6445 train_time:460014ms step_avg:138.52ms
step:3332/5100 train_loss:3.5621 train_time:460151ms step_avg:138.52ms
step:3333/5100 train_loss:3.5343 train_time:460285ms step_avg:138.51ms
step:3334/5100 train_loss:3.3984 train_time:460425ms step_avg:138.52ms
step:3335/5100 train_loss:3.4582 train_time:460563ms step_avg:138.52ms
step:3336/5100 train_loss:3.5672 train_time:460701ms step_avg:138.52ms
step:3337/5100 train_loss:3.5339 train_time:460840ms step_avg:138.52ms
step:3338/5100 train_loss:3.5722 train_time:460977ms step_avg:138.51ms
step:3339/5100 train_loss:3.4941 train_time:461114ms step_avg:138.51ms
step:3340/5100 train_loss:3.5231 train_time:461251ms step_avg:138.51ms
step:3341/5100 train_loss:3.5284 train_time:461387ms step_avg:138.51ms
step:3342/5100 train_loss:3.5434 train_time:461522ms step_avg:138.51ms
step:3343/5100 train_loss:3.5386 train_time:461661ms step_avg:138.51ms
step:3344/5100 train_loss:3.4632 train_time:461800ms step_avg:138.51ms
step:3345/5100 train_loss:3.3753 train_time:461938ms step_avg:138.51ms
step:3346/5100 train_loss:3.7044 train_time:462076ms step_avg:138.51ms
step:3347/5100 train_loss:3.4686 train_time:462215ms step_avg:138.51ms
step:3348/5100 train_loss:3.6316 train_time:462352ms step_avg:138.51ms
step:3349/5100 train_loss:3.4958 train_time:462489ms step_avg:138.51ms
step:3350/5100 train_loss:3.5801 train_time:462628ms step_avg:138.51ms
step:3351/5100 train_loss:3.3113 train_time:462763ms step_avg:138.51ms
step:3352/5100 train_loss:3.3507 train_time:462903ms step_avg:138.51ms
step:3353/5100 train_loss:3.5299 train_time:463042ms step_avg:138.51ms
step:3354/5100 train_loss:3.3862 train_time:463179ms step_avg:138.51ms
step:3355/5100 train_loss:3.5404 train_time:463317ms step_avg:138.51ms
step:3356/5100 train_loss:3.4050 train_time:463454ms step_avg:138.51ms
step:3357/5100 train_loss:3.5827 train_time:463591ms step_avg:138.51ms
step:3358/5100 train_loss:3.4329 train_time:463726ms step_avg:138.51ms
step:3359/5100 train_loss:3.6061 train_time:463863ms step_avg:138.51ms
step:3360/5100 train_loss:3.4159 train_time:464001ms step_avg:138.51ms
step:3361/5100 train_loss:4.0490 train_time:464139ms step_avg:138.51ms
step:3362/5100 train_loss:3.5752 train_time:464277ms step_avg:138.51ms
step:3363/5100 train_loss:3.6272 train_time:464415ms step_avg:138.51ms
step:3364/5100 train_loss:3.4970 train_time:464552ms step_avg:138.51ms
step:3365/5100 train_loss:3.6185 train_time:464690ms step_avg:138.51ms
step:3366/5100 train_loss:3.5187 train_time:464825ms step_avg:138.51ms
step:3367/5100 train_loss:3.6839 train_time:464963ms step_avg:138.51ms
step:3368/5100 train_loss:3.4941 train_time:465101ms step_avg:138.51ms
step:3369/5100 train_loss:3.5084 train_time:465240ms step_avg:138.51ms
step:3370/5100 train_loss:3.4807 train_time:465378ms step_avg:138.51ms
step:3371/5100 train_loss:3.4332 train_time:465517ms step_avg:138.51ms
step:3372/5100 train_loss:3.4394 train_time:465655ms step_avg:138.51ms
step:3373/5100 train_loss:3.4963 train_time:465792ms step_avg:138.51ms
step:3374/5100 train_loss:3.5255 train_time:465930ms step_avg:138.50ms
step:3375/5100 train_loss:3.5066 train_time:466065ms step_avg:138.50ms
step:3375/5100 val_loss:3.5080 train_time:466137ms step_avg:138.53ms
step:3376/5100 train_loss:3.5409 train_time:466208ms step_avg:138.50ms
step:3377/5100 train_loss:3.5481 train_time:466353ms step_avg:138.51ms
step:3378/5100 train_loss:3.6273 train_time:466489ms step_avg:138.51ms
step:3379/5100 train_loss:3.4786 train_time:466625ms step_avg:138.51ms
step:3380/5100 train_loss:3.4857 train_time:466762ms step_avg:138.51ms
step:3381/5100 train_loss:3.4888 train_time:466894ms step_avg:138.50ms
step:3382/5100 train_loss:3.5901 train_time:467030ms step_avg:138.50ms
step:3383/5100 train_loss:3.4347 train_time:467170ms step_avg:138.50ms
step:3384/5100 train_loss:3.6122 train_time:467311ms step_avg:138.50ms
step:3385/5100 train_loss:3.4591 train_time:467450ms step_avg:138.50ms
step:3386/5100 train_loss:3.4837 train_time:467586ms step_avg:138.50ms
step:3387/5100 train_loss:3.4311 train_time:467723ms step_avg:138.50ms
step:3388/5100 train_loss:3.6043 train_time:467860ms step_avg:138.50ms
step:3389/5100 train_loss:3.5561 train_time:467994ms step_avg:138.50ms
step:3390/5100 train_loss:3.5789 train_time:468132ms step_avg:138.50ms
step:3391/5100 train_loss:3.5591 train_time:468272ms step_avg:138.50ms
step:3392/5100 train_loss:3.4991 train_time:468411ms step_avg:138.50ms
step:3393/5100 train_loss:3.6226 train_time:468549ms step_avg:138.50ms
step:3394/5100 train_loss:3.5804 train_time:468687ms step_avg:138.50ms
step:3395/5100 train_loss:3.6733 train_time:468824ms step_avg:138.50ms
step:3396/5100 train_loss:3.5316 train_time:468963ms step_avg:138.50ms
step:3397/5100 train_loss:3.5177 train_time:469095ms step_avg:138.50ms
step:3398/5100 train_loss:3.4676 train_time:469233ms step_avg:138.50ms
step:3399/5100 train_loss:3.5277 train_time:469372ms step_avg:138.50ms
step:3400/5100 train_loss:3.5231 train_time:469510ms step_avg:138.50ms
step:3401/5100 train_loss:3.6083 train_time:469648ms step_avg:138.50ms
step:3402/5100 train_loss:3.4789 train_time:469878ms step_avg:138.53ms
step:3403/5100 train_loss:3.6620 train_time:470008ms step_avg:138.52ms
step:3404/5100 train_loss:3.4882 train_time:470142ms step_avg:138.52ms
step:3405/5100 train_loss:3.4994 train_time:470278ms step_avg:138.52ms
step:3406/5100 train_loss:3.4669 train_time:470412ms step_avg:138.52ms
step:3407/5100 train_loss:3.5220 train_time:470547ms step_avg:138.52ms
step:3408/5100 train_loss:3.5231 train_time:470681ms step_avg:138.52ms
step:3409/5100 train_loss:3.4986 train_time:470820ms step_avg:138.52ms
step:3410/5100 train_loss:3.5248 train_time:470960ms step_avg:138.52ms
step:3411/5100 train_loss:3.4796 train_time:471098ms step_avg:138.52ms
step:3412/5100 train_loss:3.5110 train_time:471234ms step_avg:138.52ms
step:3413/5100 train_loss:3.4414 train_time:471372ms step_avg:138.52ms
step:3414/5100 train_loss:3.6568 train_time:471509ms step_avg:138.52ms
step:3415/5100 train_loss:3.4095 train_time:471645ms step_avg:138.52ms
step:3416/5100 train_loss:3.5669 train_time:471782ms step_avg:138.51ms
step:3417/5100 train_loss:3.4433 train_time:471922ms step_avg:138.52ms
step:3418/5100 train_loss:3.5476 train_time:472059ms step_avg:138.51ms
step:3419/5100 train_loss:3.5511 train_time:472194ms step_avg:138.51ms
step:3420/5100 train_loss:3.5690 train_time:472507ms step_avg:138.57ms
step:3421/5100 train_loss:3.4486 train_time:472640ms step_avg:138.56ms
step:3422/5100 train_loss:3.4894 train_time:472773ms step_avg:138.56ms
step:3423/5100 train_loss:3.4239 train_time:472908ms step_avg:138.56ms
step:3424/5100 train_loss:3.7367 train_time:473044ms step_avg:138.56ms
step:3425/5100 train_loss:3.6344 train_time:473179ms step_avg:138.56ms
step:3426/5100 train_loss:3.4923 train_time:473313ms step_avg:138.56ms
step:3427/5100 train_loss:3.4607 train_time:473451ms step_avg:138.56ms
step:3428/5100 train_loss:3.4342 train_time:473593ms step_avg:138.56ms
step:3429/5100 train_loss:3.4412 train_time:473729ms step_avg:138.56ms
step:3430/5100 train_loss:3.5024 train_time:473866ms step_avg:138.56ms
step:3431/5100 train_loss:3.5298 train_time:474003ms step_avg:138.56ms
step:3432/5100 train_loss:3.6320 train_time:474138ms step_avg:138.56ms
step:3433/5100 train_loss:3.4509 train_time:474272ms step_avg:138.55ms
step:3434/5100 train_loss:3.6637 train_time:474408ms step_avg:138.55ms
step:3435/5100 train_loss:3.5749 train_time:474549ms step_avg:138.55ms
step:3436/5100 train_loss:3.4205 train_time:474687ms step_avg:138.55ms
step:3437/5100 train_loss:3.4641 train_time:474825ms step_avg:138.55ms
step:3438/5100 train_loss:3.5175 train_time:474963ms step_avg:138.55ms
step:3439/5100 train_loss:3.6113 train_time:475101ms step_avg:138.55ms
step:3440/5100 train_loss:3.3888 train_time:475236ms step_avg:138.55ms
step:3441/5100 train_loss:3.5606 train_time:475371ms step_avg:138.55ms
step:3442/5100 train_loss:3.4628 train_time:475509ms step_avg:138.55ms
step:3443/5100 train_loss:3.6432 train_time:475647ms step_avg:138.55ms
step:3444/5100 train_loss:3.5133 train_time:475785ms step_avg:138.55ms
step:3445/5100 train_loss:3.3959 train_time:475924ms step_avg:138.55ms
step:3446/5100 train_loss:3.6077 train_time:476061ms step_avg:138.55ms
step:3447/5100 train_loss:3.6835 train_time:476197ms step_avg:138.55ms
step:3448/5100 train_loss:3.4965 train_time:476332ms step_avg:138.55ms
step:3449/5100 train_loss:3.5135 train_time:476470ms step_avg:138.55ms
step:3450/5100 train_loss:3.5925 train_time:476608ms step_avg:138.55ms
step:3451/5100 train_loss:3.5960 train_time:476746ms step_avg:138.55ms
step:3452/5100 train_loss:3.6113 train_time:476886ms step_avg:138.55ms
step:3453/5100 train_loss:3.4117 train_time:477024ms step_avg:138.55ms
step:3454/5100 train_loss:3.5253 train_time:477161ms step_avg:138.55ms
step:3455/5100 train_loss:3.4346 train_time:477297ms step_avg:138.55ms
step:3456/5100 train_loss:3.6942 train_time:477432ms step_avg:138.55ms
step:3457/5100 train_loss:3.3760 train_time:477569ms step_avg:138.55ms
step:3458/5100 train_loss:3.5255 train_time:477708ms step_avg:138.55ms
step:3459/5100 train_loss:3.4649 train_time:477845ms step_avg:138.55ms
step:3460/5100 train_loss:3.4602 train_time:477984ms step_avg:138.55ms
step:3461/5100 train_loss:3.4645 train_time:478121ms step_avg:138.55ms
step:3462/5100 train_loss:3.4713 train_time:478257ms step_avg:138.54ms
step:3463/5100 train_loss:3.5768 train_time:478392ms step_avg:138.54ms
step:3464/5100 train_loss:3.4578 train_time:478529ms step_avg:138.54ms
step:3465/5100 train_loss:3.4588 train_time:478667ms step_avg:138.54ms
step:3466/5100 train_loss:3.4352 train_time:478806ms step_avg:138.54ms
step:3467/5100 train_loss:3.5931 train_time:478945ms step_avg:138.54ms
step:3468/5100 train_loss:3.4747 train_time:479085ms step_avg:138.54ms
step:3469/5100 train_loss:3.4960 train_time:479223ms step_avg:138.54ms
step:3470/5100 train_loss:3.6824 train_time:479359ms step_avg:138.54ms
step:3471/5100 train_loss:3.5829 train_time:479494ms step_avg:138.54ms
step:3472/5100 train_loss:3.6228 train_time:479632ms step_avg:138.54ms
step:3473/5100 train_loss:4.2582 train_time:479770ms step_avg:138.54ms
step:3474/5100 train_loss:3.5007 train_time:479909ms step_avg:138.54ms
step:3475/5100 train_loss:3.5081 train_time:480050ms step_avg:138.54ms
step:3476/5100 train_loss:3.4910 train_time:480187ms step_avg:138.54ms
step:3477/5100 train_loss:3.4397 train_time:480325ms step_avg:138.54ms
step:3478/5100 train_loss:3.5013 train_time:480463ms step_avg:138.54ms
step:3479/5100 train_loss:3.5035 train_time:480599ms step_avg:138.54ms
step:3480/5100 train_loss:3.4167 train_time:480734ms step_avg:138.54ms
step:3481/5100 train_loss:3.7058 train_time:480872ms step_avg:138.54ms
step:3482/5100 train_loss:3.5765 train_time:481010ms step_avg:138.54ms
step:3483/5100 train_loss:3.5141 train_time:481148ms step_avg:138.54ms
step:3484/5100 train_loss:3.5450 train_time:481286ms step_avg:138.54ms
step:3485/5100 train_loss:3.5088 train_time:481425ms step_avg:138.54ms
step:3486/5100 train_loss:3.6914 train_time:481561ms step_avg:138.54ms
step:3487/5100 train_loss:3.7260 train_time:481697ms step_avg:138.54ms
step:3488/5100 train_loss:3.5799 train_time:481832ms step_avg:138.54ms
step:3489/5100 train_loss:3.4327 train_time:481970ms step_avg:138.54ms
step:3490/5100 train_loss:3.6021 train_time:482108ms step_avg:138.54ms
step:3491/5100 train_loss:3.5202 train_time:482247ms step_avg:138.54ms
step:3492/5100 train_loss:3.5560 train_time:482386ms step_avg:138.54ms
step:3493/5100 train_loss:3.3988 train_time:482526ms step_avg:138.54ms
step:3494/5100 train_loss:3.5261 train_time:482660ms step_avg:138.54ms
step:3495/5100 train_loss:3.4799 train_time:482795ms step_avg:138.54ms
step:3496/5100 train_loss:3.5015 train_time:482930ms step_avg:138.53ms
step:3497/5100 train_loss:3.6666 train_time:483069ms step_avg:138.53ms
step:3498/5100 train_loss:3.5165 train_time:483209ms step_avg:138.53ms
step:3499/5100 train_loss:3.5329 train_time:483347ms step_avg:138.53ms
step:3500/5100 train_loss:3.5205 train_time:483487ms step_avg:138.53ms
step:3500/5100 val_loss:3.4935 train_time:483560ms step_avg:138.56ms
step:3501/5100 train_loss:3.5654 train_time:483632ms step_avg:138.54ms
step:3502/5100 train_loss:3.6421 train_time:483773ms step_avg:138.54ms
step:3503/5100 train_loss:3.3599 train_time:483912ms step_avg:138.54ms
step:3504/5100 train_loss:3.5074 train_time:484048ms step_avg:138.54ms
step:3505/5100 train_loss:3.5329 train_time:484180ms step_avg:138.53ms
step:3506/5100 train_loss:3.5606 train_time:484314ms step_avg:138.53ms
step:3507/5100 train_loss:3.4378 train_time:484449ms step_avg:138.53ms
step:3508/5100 train_loss:3.5847 train_time:484586ms step_avg:138.53ms
step:3509/5100 train_loss:3.4755 train_time:484726ms step_avg:138.53ms
step:3510/5100 train_loss:3.6894 train_time:484863ms step_avg:138.53ms
step:3511/5100 train_loss:3.4995 train_time:485000ms step_avg:138.53ms
step:3512/5100 train_loss:3.4401 train_time:485137ms step_avg:138.53ms
step:3513/5100 train_loss:3.5009 train_time:485273ms step_avg:138.53ms
step:3514/5100 train_loss:3.4886 train_time:485410ms step_avg:138.53ms
step:3515/5100 train_loss:3.5209 train_time:485543ms step_avg:138.53ms
step:3516/5100 train_loss:3.5182 train_time:485680ms step_avg:138.53ms
step:3517/5100 train_loss:3.4886 train_time:485820ms step_avg:138.53ms
step:3518/5100 train_loss:3.5142 train_time:485958ms step_avg:138.53ms
step:3519/5100 train_loss:3.5177 train_time:486096ms step_avg:138.53ms
step:3520/5100 train_loss:3.5286 train_time:486235ms step_avg:138.53ms
step:3521/5100 train_loss:3.5967 train_time:486371ms step_avg:138.53ms
step:3522/5100 train_loss:3.5128 train_time:486508ms step_avg:138.53ms
step:3523/5100 train_loss:3.4417 train_time:486643ms step_avg:138.53ms
step:3524/5100 train_loss:3.4759 train_time:486780ms step_avg:138.53ms
step:3525/5100 train_loss:3.4769 train_time:486918ms step_avg:138.53ms
step:3526/5100 train_loss:3.4765 train_time:487057ms step_avg:138.53ms
step:3527/5100 train_loss:3.6008 train_time:487193ms step_avg:138.53ms
step:3528/5100 train_loss:3.4379 train_time:487331ms step_avg:138.52ms
step:3529/5100 train_loss:3.3342 train_time:487467ms step_avg:138.52ms
step:3530/5100 train_loss:3.6082 train_time:487603ms step_avg:138.52ms
step:3531/5100 train_loss:3.4189 train_time:487740ms step_avg:138.52ms
step:3532/5100 train_loss:3.4555 train_time:487878ms step_avg:138.52ms
step:3533/5100 train_loss:3.3728 train_time:488017ms step_avg:138.52ms
step:3534/5100 train_loss:3.4311 train_time:488154ms step_avg:138.52ms
step:3535/5100 train_loss:3.4047 train_time:488292ms step_avg:138.52ms
step:3536/5100 train_loss:3.5897 train_time:488428ms step_avg:138.52ms
step:3537/5100 train_loss:3.5350 train_time:488564ms step_avg:138.52ms
step:3538/5100 train_loss:3.5638 train_time:488699ms step_avg:138.52ms
step:3539/5100 train_loss:3.4653 train_time:488837ms step_avg:138.52ms
step:3540/5100 train_loss:3.4392 train_time:488975ms step_avg:138.52ms
step:3541/5100 train_loss:3.5764 train_time:489114ms step_avg:138.52ms
step:3542/5100 train_loss:3.4328 train_time:489251ms step_avg:138.52ms
step:3543/5100 train_loss:3.6377 train_time:489388ms step_avg:138.52ms
step:3544/5100 train_loss:3.7620 train_time:489524ms step_avg:138.52ms
step:3545/5100 train_loss:3.5839 train_time:489660ms step_avg:138.52ms
step:3546/5100 train_loss:3.6268 train_time:489797ms step_avg:138.52ms
step:3547/5100 train_loss:3.3740 train_time:489936ms step_avg:138.52ms
step:3548/5100 train_loss:3.4568 train_time:490074ms step_avg:138.52ms
step:3549/5100 train_loss:3.4826 train_time:490212ms step_avg:138.52ms
step:3550/5100 train_loss:3.5729 train_time:490350ms step_avg:138.52ms
step:3551/5100 train_loss:3.5293 train_time:490484ms step_avg:138.52ms
step:3552/5100 train_loss:3.4641 train_time:490619ms step_avg:138.51ms
step:3553/5100 train_loss:3.5784 train_time:490757ms step_avg:138.51ms
step:3554/5100 train_loss:3.5179 train_time:490896ms step_avg:138.51ms
step:3555/5100 train_loss:3.4724 train_time:491034ms step_avg:138.51ms
step:3556/5100 train_loss:3.4070 train_time:491173ms step_avg:138.51ms
step:3557/5100 train_loss:3.3687 train_time:491310ms step_avg:138.51ms
step:3558/5100 train_loss:3.4914 train_time:491446ms step_avg:138.51ms
step:3559/5100 train_loss:3.5037 train_time:491581ms step_avg:138.51ms
step:3560/5100 train_loss:3.7058 train_time:491717ms step_avg:138.51ms
step:3561/5100 train_loss:3.5796 train_time:491857ms step_avg:138.51ms
step:3562/5100 train_loss:3.4797 train_time:491993ms step_avg:138.51ms
step:3563/5100 train_loss:3.3677 train_time:492132ms step_avg:138.51ms
step:3564/5100 train_loss:3.8690 train_time:492269ms step_avg:138.51ms
step:3565/5100 train_loss:3.4399 train_time:492406ms step_avg:138.51ms
step:3566/5100 train_loss:3.3929 train_time:492541ms step_avg:138.51ms
step:3567/5100 train_loss:3.4139 train_time:492679ms step_avg:138.51ms
step:3568/5100 train_loss:3.5420 train_time:492817ms step_avg:138.51ms
step:3569/5100 train_loss:3.4854 train_time:492957ms step_avg:138.51ms
step:3570/5100 train_loss:3.5968 train_time:493095ms step_avg:138.51ms
step:3571/5100 train_loss:3.5168 train_time:493233ms step_avg:138.51ms
step:3572/5100 train_loss:3.8006 train_time:493371ms step_avg:138.51ms
step:3573/5100 train_loss:3.4288 train_time:493510ms step_avg:138.51ms
step:3574/5100 train_loss:3.4984 train_time:493644ms step_avg:138.51ms
step:3575/5100 train_loss:3.6694 train_time:493781ms step_avg:138.51ms
step:3576/5100 train_loss:3.5416 train_time:493919ms step_avg:138.51ms
step:3577/5100 train_loss:3.4778 train_time:494057ms step_avg:138.51ms
step:3578/5100 train_loss:3.4496 train_time:494196ms step_avg:138.51ms
step:3579/5100 train_loss:3.5193 train_time:494335ms step_avg:138.51ms
step:3580/5100 train_loss:3.4670 train_time:494472ms step_avg:138.51ms
step:3581/5100 train_loss:3.3728 train_time:494609ms step_avg:138.51ms
step:3582/5100 train_loss:3.4387 train_time:494744ms step_avg:138.51ms
step:3583/5100 train_loss:3.3895 train_time:494880ms step_avg:138.51ms
step:3584/5100 train_loss:3.4986 train_time:495018ms step_avg:138.51ms
step:3585/5100 train_loss:3.6025 train_time:495157ms step_avg:138.51ms
step:3586/5100 train_loss:3.4542 train_time:495294ms step_avg:138.51ms
step:3587/5100 train_loss:3.4924 train_time:495433ms step_avg:138.51ms
step:3588/5100 train_loss:3.4958 train_time:495570ms step_avg:138.50ms
step:3589/5100 train_loss:3.4759 train_time:495710ms step_avg:138.51ms
step:3590/5100 train_loss:3.4757 train_time:495843ms step_avg:138.50ms
step:3591/5100 train_loss:3.5947 train_time:496083ms step_avg:138.53ms
step:3592/5100 train_loss:3.4704 train_time:496214ms step_avg:138.53ms
step:3593/5100 train_loss:3.5521 train_time:496350ms step_avg:138.53ms
step:3594/5100 train_loss:3.5388 train_time:496482ms step_avg:138.53ms
step:3595/5100 train_loss:3.4992 train_time:496616ms step_avg:138.53ms
step:3596/5100 train_loss:3.4260 train_time:496751ms step_avg:138.53ms
step:3597/5100 train_loss:3.4317 train_time:496886ms step_avg:138.52ms
step:3598/5100 train_loss:3.7080 train_time:497023ms step_avg:138.52ms
step:3599/5100 train_loss:3.4769 train_time:497167ms step_avg:138.53ms
step:3600/5100 train_loss:3.4993 train_time:497303ms step_avg:138.52ms
step:3601/5100 train_loss:3.3533 train_time:497442ms step_avg:138.52ms
step:3602/5100 train_loss:3.5368 train_time:497580ms step_avg:138.52ms
step:3603/5100 train_loss:3.4840 train_time:497716ms step_avg:138.52ms
step:3604/5100 train_loss:3.6309 train_time:497852ms step_avg:138.52ms
step:3605/5100 train_loss:3.6758 train_time:497987ms step_avg:138.52ms
step:3606/5100 train_loss:3.4875 train_time:498126ms step_avg:138.52ms
step:3607/5100 train_loss:3.5310 train_time:498264ms step_avg:138.52ms
step:3608/5100 train_loss:3.8105 train_time:498402ms step_avg:138.52ms
step:3609/5100 train_loss:3.4865 train_time:498540ms step_avg:138.52ms
step:3610/5100 train_loss:3.6381 train_time:498849ms step_avg:138.57ms
step:3611/5100 train_loss:3.3802 train_time:498980ms step_avg:138.57ms
step:3612/5100 train_loss:3.4813 train_time:499115ms step_avg:138.57ms
step:3613/5100 train_loss:3.5626 train_time:499250ms step_avg:138.57ms
step:3614/5100 train_loss:3.7515 train_time:499384ms step_avg:138.56ms
step:3615/5100 train_loss:3.7583 train_time:499518ms step_avg:138.56ms
step:3616/5100 train_loss:3.4134 train_time:499653ms step_avg:138.56ms
step:3617/5100 train_loss:3.5022 train_time:499792ms step_avg:138.56ms
step:3618/5100 train_loss:3.4813 train_time:499935ms step_avg:138.56ms
step:3619/5100 train_loss:3.6076 train_time:500073ms step_avg:138.56ms
step:3620/5100 train_loss:3.5347 train_time:500210ms step_avg:138.56ms
step:3621/5100 train_loss:3.3719 train_time:500344ms step_avg:138.56ms
step:3622/5100 train_loss:3.5004 train_time:500477ms step_avg:138.56ms
step:3623/5100 train_loss:3.5071 train_time:500614ms step_avg:138.56ms
step:3624/5100 train_loss:3.4432 train_time:500752ms step_avg:138.56ms
step:3625/5100 train_loss:3.5734 train_time:500890ms step_avg:138.56ms
step:3625/5100 val_loss:3.4964 train_time:500964ms step_avg:138.58ms
step:3626/5100 train_loss:3.6366 train_time:501037ms step_avg:138.56ms
step:3627/5100 train_loss:3.6468 train_time:501181ms step_avg:138.56ms
step:3628/5100 train_loss:3.5260 train_time:501315ms step_avg:138.56ms
step:3629/5100 train_loss:3.6822 train_time:501451ms step_avg:138.56ms
step:3630/5100 train_loss:3.5131 train_time:501586ms step_avg:138.56ms
step:3631/5100 train_loss:3.5036 train_time:501721ms step_avg:138.56ms
step:3632/5100 train_loss:3.5793 train_time:501855ms step_avg:138.56ms
step:3633/5100 train_loss:3.5665 train_time:501994ms step_avg:138.56ms
step:3634/5100 train_loss:3.4926 train_time:502136ms step_avg:138.56ms
step:3635/5100 train_loss:3.4953 train_time:502271ms step_avg:138.56ms
step:3636/5100 train_loss:3.5405 train_time:502408ms step_avg:138.56ms
step:3637/5100 train_loss:3.7234 train_time:502546ms step_avg:138.56ms
step:3638/5100 train_loss:3.5212 train_time:502682ms step_avg:138.56ms
step:3639/5100 train_loss:3.4805 train_time:502819ms step_avg:138.56ms
step:3640/5100 train_loss:3.4751 train_time:502954ms step_avg:138.55ms
step:3641/5100 train_loss:3.7606 train_time:503092ms step_avg:138.55ms
step:3642/5100 train_loss:3.4966 train_time:503230ms step_avg:138.55ms
step:3643/5100 train_loss:3.5631 train_time:503367ms step_avg:138.55ms
step:3644/5100 train_loss:3.5327 train_time:503505ms step_avg:138.55ms
step:3645/5100 train_loss:3.4535 train_time:503643ms step_avg:138.55ms
step:3646/5100 train_loss:3.6587 train_time:503780ms step_avg:138.55ms
step:3647/5100 train_loss:3.4366 train_time:503916ms step_avg:138.55ms
step:3648/5100 train_loss:3.5031 train_time:504051ms step_avg:138.55ms
step:3649/5100 train_loss:3.5761 train_time:504189ms step_avg:138.55ms
step:3650/5100 train_loss:3.5163 train_time:504328ms step_avg:138.55ms
step:3651/5100 train_loss:3.5601 train_time:504468ms step_avg:138.55ms
step:3652/5100 train_loss:3.6206 train_time:504604ms step_avg:138.55ms
step:3653/5100 train_loss:3.4386 train_time:504742ms step_avg:138.55ms
step:3654/5100 train_loss:3.5361 train_time:504879ms step_avg:138.55ms
step:3655/5100 train_loss:3.5615 train_time:505015ms step_avg:138.55ms
step:3656/5100 train_loss:4.2385 train_time:505150ms step_avg:138.55ms
step:3657/5100 train_loss:3.6238 train_time:505288ms step_avg:138.55ms
step:3658/5100 train_loss:3.5349 train_time:505428ms step_avg:138.55ms
step:3659/5100 train_loss:3.5172 train_time:505566ms step_avg:138.55ms
step:3660/5100 train_loss:3.3983 train_time:505703ms step_avg:138.55ms
step:3661/5100 train_loss:3.5302 train_time:505841ms step_avg:138.55ms
step:3662/5100 train_loss:3.4053 train_time:505977ms step_avg:138.55ms
step:3663/5100 train_loss:3.5554 train_time:506114ms step_avg:138.55ms
step:3664/5100 train_loss:3.5570 train_time:506250ms step_avg:138.55ms
step:3665/5100 train_loss:3.3950 train_time:506388ms step_avg:138.55ms
step:3666/5100 train_loss:3.3332 train_time:506527ms step_avg:138.55ms
step:3667/5100 train_loss:3.7487 train_time:506667ms step_avg:138.55ms
step:3668/5100 train_loss:3.5424 train_time:506804ms step_avg:138.55ms
step:3669/5100 train_loss:3.5744 train_time:506942ms step_avg:138.55ms
step:3670/5100 train_loss:3.4912 train_time:507078ms step_avg:138.55ms
step:3671/5100 train_loss:3.5601 train_time:507214ms step_avg:138.55ms
step:3672/5100 train_loss:3.4623 train_time:507352ms step_avg:138.55ms
step:3673/5100 train_loss:3.4538 train_time:507490ms step_avg:138.54ms
step:3674/5100 train_loss:3.3615 train_time:507630ms step_avg:138.55ms
step:3675/5100 train_loss:3.4360 train_time:507768ms step_avg:138.55ms
step:3676/5100 train_loss:3.5891 train_time:507905ms step_avg:138.54ms
step:3677/5100 train_loss:3.3962 train_time:508043ms step_avg:138.54ms
step:3678/5100 train_loss:3.5643 train_time:508179ms step_avg:138.54ms
step:3679/5100 train_loss:3.5442 train_time:508316ms step_avg:138.54ms
step:3680/5100 train_loss:3.4405 train_time:508453ms step_avg:138.54ms
step:3681/5100 train_loss:3.5109 train_time:508592ms step_avg:138.54ms
step:3682/5100 train_loss:3.5817 train_time:508729ms step_avg:138.54ms
step:3683/5100 train_loss:3.6782 train_time:508867ms step_avg:138.54ms
step:3684/5100 train_loss:3.4215 train_time:509005ms step_avg:138.54ms
step:3685/5100 train_loss:3.5029 train_time:509144ms step_avg:138.54ms
step:3686/5100 train_loss:3.6391 train_time:509281ms step_avg:138.54ms
step:3687/5100 train_loss:3.4207 train_time:509416ms step_avg:138.54ms
step:3688/5100 train_loss:3.6328 train_time:509552ms step_avg:138.54ms
step:3689/5100 train_loss:3.3653 train_time:509688ms step_avg:138.54ms
step:3690/5100 train_loss:3.4558 train_time:509826ms step_avg:138.54ms
step:3691/5100 train_loss:3.5873 train_time:509964ms step_avg:138.54ms
step:3692/5100 train_loss:3.3723 train_time:510102ms step_avg:138.54ms
step:3693/5100 train_loss:3.5193 train_time:510240ms step_avg:138.54ms
step:3694/5100 train_loss:3.5081 train_time:510378ms step_avg:138.54ms
step:3695/5100 train_loss:3.5034 train_time:510514ms step_avg:138.54ms
step:3696/5100 train_loss:3.5423 train_time:510651ms step_avg:138.54ms
step:3697/5100 train_loss:3.3802 train_time:510788ms step_avg:138.54ms
step:3698/5100 train_loss:3.5158 train_time:510928ms step_avg:138.54ms
step:3699/5100 train_loss:3.5383 train_time:511066ms step_avg:138.54ms
step:3700/5100 train_loss:3.5006 train_time:511204ms step_avg:138.54ms
step:3701/5100 train_loss:3.5728 train_time:511342ms step_avg:138.54ms
step:3702/5100 train_loss:3.5257 train_time:511480ms step_avg:138.54ms
step:3703/5100 train_loss:3.4488 train_time:511618ms step_avg:138.54ms
step:3704/5100 train_loss:3.4279 train_time:511754ms step_avg:138.54ms
step:3705/5100 train_loss:3.5682 train_time:511892ms step_avg:138.54ms
step:3706/5100 train_loss:3.5692 train_time:512027ms step_avg:138.54ms
step:3707/5100 train_loss:3.5665 train_time:512166ms step_avg:138.54ms
step:3708/5100 train_loss:3.5308 train_time:512305ms step_avg:138.54ms
step:3709/5100 train_loss:3.3990 train_time:512442ms step_avg:138.54ms
step:3710/5100 train_loss:3.6992 train_time:512579ms step_avg:138.53ms
step:3711/5100 train_loss:3.2871 train_time:512721ms step_avg:138.54ms
step:3712/5100 train_loss:3.5637 train_time:512852ms step_avg:138.53ms
step:3713/5100 train_loss:3.4446 train_time:512989ms step_avg:138.53ms
step:3714/5100 train_loss:3.4797 train_time:513128ms step_avg:138.53ms
step:3715/5100 train_loss:3.8580 train_time:513266ms step_avg:138.53ms
step:3716/5100 train_loss:3.7125 train_time:513405ms step_avg:138.53ms
step:3717/5100 train_loss:3.9588 train_time:513544ms step_avg:138.53ms
step:3718/5100 train_loss:3.4748 train_time:513681ms step_avg:138.53ms
step:3719/5100 train_loss:3.3948 train_time:513819ms step_avg:138.53ms
step:3720/5100 train_loss:3.6541 train_time:513956ms step_avg:138.53ms
step:3721/5100 train_loss:3.4071 train_time:514090ms step_avg:138.53ms
step:3722/5100 train_loss:3.5155 train_time:514228ms step_avg:138.53ms
step:3723/5100 train_loss:3.3760 train_time:514366ms step_avg:138.53ms
step:3724/5100 train_loss:3.3565 train_time:514504ms step_avg:138.53ms
step:3725/5100 train_loss:3.4793 train_time:514642ms step_avg:138.53ms
step:3726/5100 train_loss:3.4382 train_time:514781ms step_avg:138.53ms
step:3727/5100 train_loss:3.7068 train_time:514919ms step_avg:138.53ms
step:3728/5100 train_loss:3.4505 train_time:515055ms step_avg:138.53ms
step:3729/5100 train_loss:3.4261 train_time:515190ms step_avg:138.53ms
step:3730/5100 train_loss:3.7819 train_time:515327ms step_avg:138.53ms
step:3731/5100 train_loss:3.5495 train_time:515467ms step_avg:138.53ms
step:3732/5100 train_loss:3.4474 train_time:515604ms step_avg:138.53ms
step:3733/5100 train_loss:3.5783 train_time:515742ms step_avg:138.53ms
step:3734/5100 train_loss:3.5644 train_time:515880ms step_avg:138.53ms
step:3735/5100 train_loss:3.4260 train_time:516019ms step_avg:138.53ms
step:3736/5100 train_loss:3.5267 train_time:516154ms step_avg:138.53ms
step:3737/5100 train_loss:3.4296 train_time:516290ms step_avg:138.53ms
step:3738/5100 train_loss:3.5319 train_time:516430ms step_avg:138.53ms
step:3739/5100 train_loss:3.4508 train_time:516568ms step_avg:138.53ms
step:3740/5100 train_loss:3.4864 train_time:516706ms step_avg:138.53ms
step:3741/5100 train_loss:3.7557 train_time:516844ms step_avg:138.53ms
step:3742/5100 train_loss:3.4345 train_time:516982ms step_avg:138.53ms
step:3743/5100 train_loss:3.4915 train_time:517121ms step_avg:138.53ms
step:3744/5100 train_loss:3.7033 train_time:517257ms step_avg:138.53ms
step:3745/5100 train_loss:3.4248 train_time:517393ms step_avg:138.53ms
step:3746/5100 train_loss:3.3555 train_time:517530ms step_avg:138.53ms
step:3747/5100 train_loss:3.5360 train_time:517669ms step_avg:138.53ms
step:3748/5100 train_loss:3.3944 train_time:517806ms step_avg:138.52ms
step:3749/5100 train_loss:3.4269 train_time:517945ms step_avg:138.52ms
step:3750/5100 train_loss:3.6182 train_time:518084ms step_avg:138.53ms
step:3750/5100 val_loss:3.4849 train_time:518156ms step_avg:138.54ms
step:3751/5100 train_loss:3.5042 train_time:518230ms step_avg:138.53ms
step:3752/5100 train_loss:3.7417 train_time:518372ms step_avg:138.53ms
step:3753/5100 train_loss:3.4608 train_time:518509ms step_avg:138.53ms
step:3754/5100 train_loss:3.4592 train_time:518645ms step_avg:138.53ms
step:3755/5100 train_loss:3.4288 train_time:518781ms step_avg:138.53ms
step:3756/5100 train_loss:3.5332 train_time:518917ms step_avg:138.53ms
step:3757/5100 train_loss:3.4746 train_time:519052ms step_avg:138.52ms
step:3758/5100 train_loss:3.4862 train_time:519191ms step_avg:138.52ms
step:3759/5100 train_loss:3.6597 train_time:519330ms step_avg:138.53ms
step:3760/5100 train_loss:3.5650 train_time:519468ms step_avg:138.52ms
step:3761/5100 train_loss:3.6547 train_time:519603ms step_avg:138.52ms
step:3762/5100 train_loss:3.4363 train_time:519740ms step_avg:138.52ms
step:3763/5100 train_loss:3.4451 train_time:519877ms step_avg:138.52ms
step:3764/5100 train_loss:3.6099 train_time:520013ms step_avg:138.52ms
step:3765/5100 train_loss:3.3679 train_time:520148ms step_avg:138.52ms
step:3766/5100 train_loss:3.4544 train_time:520287ms step_avg:138.52ms
step:3767/5100 train_loss:3.5597 train_time:520426ms step_avg:138.52ms
step:3768/5100 train_loss:3.3604 train_time:520564ms step_avg:138.52ms
step:3769/5100 train_loss:3.6208 train_time:520701ms step_avg:138.52ms
step:3770/5100 train_loss:3.4397 train_time:520839ms step_avg:138.52ms
step:3771/5100 train_loss:3.3164 train_time:520974ms step_avg:138.52ms
step:3772/5100 train_loss:3.5645 train_time:521112ms step_avg:138.52ms
step:3773/5100 train_loss:3.4946 train_time:521246ms step_avg:138.52ms
step:3774/5100 train_loss:3.4780 train_time:521384ms step_avg:138.52ms
step:3775/5100 train_loss:3.4752 train_time:521522ms step_avg:138.52ms
step:3776/5100 train_loss:3.5245 train_time:521660ms step_avg:138.52ms
step:3777/5100 train_loss:3.3666 train_time:521797ms step_avg:138.52ms
step:3778/5100 train_loss:3.4717 train_time:521935ms step_avg:138.52ms
step:3779/5100 train_loss:3.5999 train_time:522072ms step_avg:138.52ms
step:3780/5100 train_loss:3.5669 train_time:522306ms step_avg:138.54ms
step:3781/5100 train_loss:3.5626 train_time:522436ms step_avg:138.54ms
step:3782/5100 train_loss:3.5130 train_time:522570ms step_avg:138.54ms
step:3783/5100 train_loss:3.5215 train_time:522704ms step_avg:138.54ms
step:3784/5100 train_loss:3.4862 train_time:522839ms step_avg:138.54ms
step:3785/5100 train_loss:3.3706 train_time:522973ms step_avg:138.54ms
step:3786/5100 train_loss:3.4483 train_time:523109ms step_avg:138.54ms
step:3787/5100 train_loss:3.4952 train_time:523246ms step_avg:138.53ms
step:3788/5100 train_loss:3.4828 train_time:523387ms step_avg:138.54ms
step:3789/5100 train_loss:3.4248 train_time:523523ms step_avg:138.53ms
step:3790/5100 train_loss:3.4564 train_time:523661ms step_avg:138.53ms
step:3791/5100 train_loss:3.3186 train_time:523797ms step_avg:138.53ms
step:3792/5100 train_loss:3.5450 train_time:523934ms step_avg:138.53ms
step:3793/5100 train_loss:3.5344 train_time:524072ms step_avg:138.53ms
step:3794/5100 train_loss:3.4599 train_time:524206ms step_avg:138.53ms
step:3795/5100 train_loss:3.4232 train_time:524345ms step_avg:138.53ms
step:3796/5100 train_loss:3.2614 train_time:524485ms step_avg:138.53ms
step:3797/5100 train_loss:3.4621 train_time:524622ms step_avg:138.53ms
step:3798/5100 train_loss:3.4567 train_time:524761ms step_avg:138.53ms
step:3799/5100 train_loss:3.5208 train_time:524897ms step_avg:138.53ms
step:3800/5100 train_loss:3.4330 train_time:525204ms step_avg:138.58ms
step:3801/5100 train_loss:3.4229 train_time:525341ms step_avg:138.58ms
step:3802/5100 train_loss:3.3676 train_time:525475ms step_avg:138.57ms
step:3803/5100 train_loss:3.6762 train_time:525609ms step_avg:138.57ms
step:3804/5100 train_loss:3.5210 train_time:525743ms step_avg:138.57ms
step:3805/5100 train_loss:3.3791 train_time:525878ms step_avg:138.57ms
step:3806/5100 train_loss:3.6113 train_time:526013ms step_avg:138.57ms
step:3807/5100 train_loss:3.5842 train_time:526150ms step_avg:138.57ms
step:3808/5100 train_loss:3.4481 train_time:526291ms step_avg:138.57ms
step:3809/5100 train_loss:3.5112 train_time:526427ms step_avg:138.57ms
step:3810/5100 train_loss:3.4267 train_time:526564ms step_avg:138.57ms
step:3811/5100 train_loss:3.4989 train_time:526701ms step_avg:138.57ms
step:3812/5100 train_loss:3.4762 train_time:526837ms step_avg:138.57ms
step:3813/5100 train_loss:3.5012 train_time:526973ms step_avg:138.57ms
step:3814/5100 train_loss:3.5000 train_time:527108ms step_avg:138.57ms
step:3815/5100 train_loss:3.5753 train_time:527246ms step_avg:138.57ms
step:3816/5100 train_loss:3.7256 train_time:527385ms step_avg:138.57ms
step:3817/5100 train_loss:3.3278 train_time:527523ms step_avg:138.57ms
step:3818/5100 train_loss:3.5091 train_time:527660ms step_avg:138.57ms
step:3819/5100 train_loss:3.4855 train_time:527797ms step_avg:138.57ms
step:3820/5100 train_loss:3.4664 train_time:527934ms step_avg:138.57ms
step:3821/5100 train_loss:3.4015 train_time:528068ms step_avg:138.56ms
step:3822/5100 train_loss:3.5713 train_time:528205ms step_avg:138.56ms
step:3823/5100 train_loss:3.3046 train_time:528341ms step_avg:138.56ms
step:3824/5100 train_loss:3.4240 train_time:528479ms step_avg:138.56ms
step:3825/5100 train_loss:3.4739 train_time:528618ms step_avg:138.56ms
step:3826/5100 train_loss:3.6097 train_time:528755ms step_avg:138.56ms
step:3827/5100 train_loss:3.5557 train_time:528894ms step_avg:138.56ms
step:3828/5100 train_loss:3.9225 train_time:529030ms step_avg:138.56ms
step:3829/5100 train_loss:3.5494 train_time:529165ms step_avg:138.56ms
step:3830/5100 train_loss:3.3715 train_time:529304ms step_avg:138.56ms
step:3831/5100 train_loss:3.4132 train_time:529441ms step_avg:138.56ms
step:3832/5100 train_loss:3.6304 train_time:529580ms step_avg:138.56ms
step:3833/5100 train_loss:3.4408 train_time:529718ms step_avg:138.56ms
step:3834/5100 train_loss:3.5487 train_time:529856ms step_avg:138.56ms
step:3835/5100 train_loss:3.4973 train_time:529993ms step_avg:138.56ms
step:3836/5100 train_loss:3.2969 train_time:530127ms step_avg:138.56ms
step:3837/5100 train_loss:3.5824 train_time:530265ms step_avg:138.56ms
step:3838/5100 train_loss:3.5546 train_time:530403ms step_avg:138.56ms
step:3839/5100 train_loss:3.5159 train_time:530542ms step_avg:138.56ms
step:3840/5100 train_loss:3.5797 train_time:530680ms step_avg:138.56ms
step:3841/5100 train_loss:3.6986 train_time:530819ms step_avg:138.56ms
step:3842/5100 train_loss:3.4540 train_time:530957ms step_avg:138.56ms
step:3843/5100 train_loss:3.4926 train_time:531092ms step_avg:138.56ms
step:3844/5100 train_loss:3.6485 train_time:531227ms step_avg:138.56ms
step:3845/5100 train_loss:3.4447 train_time:531365ms step_avg:138.56ms
step:3846/5100 train_loss:3.3053 train_time:531503ms step_avg:138.56ms
step:3847/5100 train_loss:3.5579 train_time:531641ms step_avg:138.56ms
step:3848/5100 train_loss:3.4737 train_time:531777ms step_avg:138.56ms
step:3849/5100 train_loss:3.5068 train_time:531920ms step_avg:138.56ms
step:3850/5100 train_loss:3.4067 train_time:532058ms step_avg:138.56ms
step:3851/5100 train_loss:3.3947 train_time:532191ms step_avg:138.56ms
step:3852/5100 train_loss:3.5536 train_time:532328ms step_avg:138.56ms
step:3853/5100 train_loss:3.3951 train_time:532464ms step_avg:138.55ms
step:3854/5100 train_loss:3.3716 train_time:532602ms step_avg:138.55ms
step:3855/5100 train_loss:3.4526 train_time:532741ms step_avg:138.55ms
step:3856/5100 train_loss:3.4917 train_time:532878ms step_avg:138.55ms
step:3857/5100 train_loss:3.4625 train_time:533016ms step_avg:138.55ms
step:3858/5100 train_loss:3.4832 train_time:533155ms step_avg:138.55ms
step:3859/5100 train_loss:3.4701 train_time:533294ms step_avg:138.55ms
step:3860/5100 train_loss:3.4973 train_time:533429ms step_avg:138.55ms
step:3861/5100 train_loss:3.6387 train_time:533565ms step_avg:138.55ms
step:3862/5100 train_loss:3.4419 train_time:533704ms step_avg:138.55ms
step:3863/5100 train_loss:3.5664 train_time:533844ms step_avg:138.55ms
step:3864/5100 train_loss:3.5174 train_time:533982ms step_avg:138.55ms
step:3865/5100 train_loss:3.5666 train_time:534121ms step_avg:138.55ms
step:3866/5100 train_loss:3.5377 train_time:534260ms step_avg:138.55ms
step:3867/5100 train_loss:3.4773 train_time:534397ms step_avg:138.55ms
step:3868/5100 train_loss:3.5683 train_time:534531ms step_avg:138.55ms
step:3869/5100 train_loss:3.7193 train_time:534666ms step_avg:138.55ms
step:3870/5100 train_loss:3.5685 train_time:534805ms step_avg:138.55ms
step:3871/5100 train_loss:3.4576 train_time:534946ms step_avg:138.55ms
step:3872/5100 train_loss:3.6070 train_time:535086ms step_avg:138.55ms
step:3873/5100 train_loss:3.5034 train_time:535223ms step_avg:138.55ms
step:3874/5100 train_loss:3.4525 train_time:535360ms step_avg:138.55ms
step:3875/5100 train_loss:3.5525 train_time:535498ms step_avg:138.55ms
step:3875/5100 val_loss:3.4663 train_time:535569ms step_avg:138.57ms
step:3876/5100 train_loss:4.0753 train_time:535643ms step_avg:138.55ms
step:3877/5100 train_loss:3.4846 train_time:535784ms step_avg:138.55ms
step:3878/5100 train_loss:3.4768 train_time:535922ms step_avg:138.55ms
step:3879/5100 train_loss:3.4660 train_time:536059ms step_avg:138.55ms
step:3880/5100 train_loss:3.6690 train_time:536194ms step_avg:138.55ms
step:3881/5100 train_loss:3.4786 train_time:536329ms step_avg:138.55ms
step:3882/5100 train_loss:3.5430 train_time:536463ms step_avg:138.55ms
step:3883/5100 train_loss:3.5840 train_time:536601ms step_avg:138.55ms
step:3884/5100 train_loss:3.4091 train_time:536743ms step_avg:138.55ms
step:3885/5100 train_loss:3.3974 train_time:536882ms step_avg:138.55ms
step:3886/5100 train_loss:3.4424 train_time:537020ms step_avg:138.55ms
step:3887/5100 train_loss:3.4752 train_time:537156ms step_avg:138.55ms
step:3888/5100 train_loss:3.6539 train_time:537294ms step_avg:138.55ms
step:3889/5100 train_loss:3.4971 train_time:537428ms step_avg:138.55ms
step:3890/5100 train_loss:3.4350 train_time:537564ms step_avg:138.55ms
step:3891/5100 train_loss:3.5769 train_time:537703ms step_avg:138.55ms
step:3892/5100 train_loss:3.4394 train_time:537843ms step_avg:138.55ms
step:3893/5100 train_loss:3.6719 train_time:537981ms step_avg:138.55ms
step:3894/5100 train_loss:3.4195 train_time:538120ms step_avg:138.55ms
step:3895/5100 train_loss:3.4353 train_time:538257ms step_avg:138.55ms
step:3896/5100 train_loss:3.5176 train_time:538393ms step_avg:138.55ms
step:3897/5100 train_loss:3.7587 train_time:538528ms step_avg:138.55ms
step:3898/5100 train_loss:3.3201 train_time:538666ms step_avg:138.55ms
step:3899/5100 train_loss:3.4437 train_time:538805ms step_avg:138.55ms
step:3900/5100 train_loss:3.5776 train_time:538943ms step_avg:138.55ms
step:3901/5100 train_loss:3.4960 train_time:539082ms step_avg:138.55ms
step:3902/5100 train_loss:3.5465 train_time:539220ms step_avg:138.55ms
step:3903/5100 train_loss:3.8281 train_time:539360ms step_avg:138.55ms
step:3904/5100 train_loss:3.4222 train_time:539496ms step_avg:138.55ms
step:3905/5100 train_loss:3.4440 train_time:539632ms step_avg:138.54ms
step:3906/5100 train_loss:3.3947 train_time:539766ms step_avg:138.54ms
step:3907/5100 train_loss:3.5553 train_time:539904ms step_avg:138.54ms
step:3908/5100 train_loss:3.5698 train_time:540042ms step_avg:138.54ms
step:3909/5100 train_loss:3.5571 train_time:540179ms step_avg:138.54ms
step:3910/5100 train_loss:3.5068 train_time:540319ms step_avg:138.54ms
step:3911/5100 train_loss:3.4421 train_time:540456ms step_avg:138.54ms
step:3912/5100 train_loss:3.4713 train_time:540592ms step_avg:138.54ms
step:3913/5100 train_loss:3.4541 train_time:540726ms step_avg:138.54ms
step:3914/5100 train_loss:3.5783 train_time:540865ms step_avg:138.54ms
step:3915/5100 train_loss:3.4145 train_time:541002ms step_avg:138.54ms
step:3916/5100 train_loss:3.3914 train_time:541144ms step_avg:138.54ms
step:3917/5100 train_loss:3.3847 train_time:541280ms step_avg:138.54ms
step:3918/5100 train_loss:3.5053 train_time:541418ms step_avg:138.54ms
step:3919/5100 train_loss:3.6316 train_time:541555ms step_avg:138.54ms
step:3920/5100 train_loss:3.4088 train_time:541691ms step_avg:138.54ms
step:3921/5100 train_loss:3.3868 train_time:541826ms step_avg:138.54ms
step:3922/5100 train_loss:3.4679 train_time:541964ms step_avg:138.54ms
step:3923/5100 train_loss:3.4614 train_time:542102ms step_avg:138.54ms
step:3924/5100 train_loss:3.4712 train_time:542242ms step_avg:138.54ms
step:3925/5100 train_loss:3.5530 train_time:542379ms step_avg:138.54ms
step:3926/5100 train_loss:3.5214 train_time:542517ms step_avg:138.54ms
step:3927/5100 train_loss:3.6167 train_time:542655ms step_avg:138.54ms
step:3928/5100 train_loss:3.5003 train_time:542790ms step_avg:138.54ms
step:3929/5100 train_loss:3.3462 train_time:542925ms step_avg:138.54ms
step:3930/5100 train_loss:3.6755 train_time:543063ms step_avg:138.54ms
step:3931/5100 train_loss:3.4564 train_time:543201ms step_avg:138.54ms
step:3932/5100 train_loss:3.5060 train_time:543341ms step_avg:138.54ms
step:3933/5100 train_loss:3.5427 train_time:543480ms step_avg:138.54ms
step:3934/5100 train_loss:3.4273 train_time:543619ms step_avg:138.54ms
step:3935/5100 train_loss:3.5459 train_time:543755ms step_avg:138.54ms
step:3936/5100 train_loss:3.5626 train_time:543891ms step_avg:138.54ms
step:3937/5100 train_loss:3.4836 train_time:544025ms step_avg:138.53ms
step:3938/5100 train_loss:3.5460 train_time:544163ms step_avg:138.53ms
step:3939/5100 train_loss:3.4688 train_time:544301ms step_avg:138.53ms
step:3940/5100 train_loss:3.2193 train_time:544441ms step_avg:138.53ms
step:3941/5100 train_loss:3.4360 train_time:544579ms step_avg:138.53ms
step:3942/5100 train_loss:3.5523 train_time:544717ms step_avg:138.53ms
step:3943/5100 train_loss:3.6367 train_time:544853ms step_avg:138.53ms
step:3944/5100 train_loss:3.6816 train_time:544988ms step_avg:138.53ms
step:3945/5100 train_loss:3.5138 train_time:545124ms step_avg:138.53ms
step:3946/5100 train_loss:3.4260 train_time:545262ms step_avg:138.53ms
step:3947/5100 train_loss:3.4396 train_time:545400ms step_avg:138.53ms
step:3948/5100 train_loss:3.5250 train_time:545538ms step_avg:138.53ms
step:3949/5100 train_loss:3.3277 train_time:545676ms step_avg:138.53ms
step:3950/5100 train_loss:3.5223 train_time:545817ms step_avg:138.53ms
step:3951/5100 train_loss:3.4637 train_time:545950ms step_avg:138.53ms
step:3952/5100 train_loss:3.2701 train_time:546085ms step_avg:138.53ms
step:3953/5100 train_loss:3.3346 train_time:546222ms step_avg:138.53ms
step:3954/5100 train_loss:3.6057 train_time:546361ms step_avg:138.53ms
step:3955/5100 train_loss:3.5197 train_time:546500ms step_avg:138.53ms
step:3956/5100 train_loss:3.4579 train_time:546639ms step_avg:138.53ms
step:3957/5100 train_loss:3.5213 train_time:546777ms step_avg:138.53ms
step:3958/5100 train_loss:3.2387 train_time:546914ms step_avg:138.53ms
step:3959/5100 train_loss:3.5353 train_time:547048ms step_avg:138.53ms
step:3960/5100 train_loss:3.4701 train_time:547183ms step_avg:138.53ms
step:3961/5100 train_loss:3.4346 train_time:547321ms step_avg:138.53ms
step:3962/5100 train_loss:3.4658 train_time:547461ms step_avg:138.53ms
step:3963/5100 train_loss:3.4780 train_time:547598ms step_avg:138.53ms
step:3964/5100 train_loss:3.5079 train_time:547736ms step_avg:138.53ms
step:3965/5100 train_loss:3.3561 train_time:547873ms step_avg:138.53ms
step:3966/5100 train_loss:3.4736 train_time:548009ms step_avg:138.53ms
step:3967/5100 train_loss:3.5522 train_time:548146ms step_avg:138.53ms
step:3968/5100 train_loss:3.4659 train_time:548283ms step_avg:138.53ms
step:3969/5100 train_loss:3.5469 train_time:548517ms step_avg:138.55ms
step:3970/5100 train_loss:3.4361 train_time:548646ms step_avg:138.55ms
step:3971/5100 train_loss:3.6231 train_time:548781ms step_avg:138.55ms
step:3972/5100 train_loss:3.5558 train_time:548916ms step_avg:138.55ms
step:3973/5100 train_loss:3.5042 train_time:549050ms step_avg:138.54ms
step:3974/5100 train_loss:3.4023 train_time:549184ms step_avg:138.54ms
step:3975/5100 train_loss:3.4545 train_time:549318ms step_avg:138.54ms
step:3976/5100 train_loss:3.5204 train_time:549462ms step_avg:138.54ms
step:3977/5100 train_loss:3.4265 train_time:549604ms step_avg:138.54ms
step:3978/5100 train_loss:3.4879 train_time:549743ms step_avg:138.54ms
step:3979/5100 train_loss:3.5699 train_time:549879ms step_avg:138.54ms
step:3980/5100 train_loss:3.4961 train_time:550015ms step_avg:138.54ms
step:3981/5100 train_loss:3.5115 train_time:550151ms step_avg:138.54ms
step:3982/5100 train_loss:3.7105 train_time:550285ms step_avg:138.54ms
step:3983/5100 train_loss:3.4413 train_time:550421ms step_avg:138.54ms
step:3984/5100 train_loss:3.5104 train_time:550565ms step_avg:138.54ms
step:3985/5100 train_loss:3.4489 train_time:550700ms step_avg:138.54ms
step:3986/5100 train_loss:3.3754 train_time:550840ms step_avg:138.54ms
step:3987/5100 train_loss:3.4181 train_time:550977ms step_avg:138.54ms
step:3988/5100 train_loss:3.4457 train_time:551116ms step_avg:138.54ms
step:3989/5100 train_loss:3.1775 train_time:551249ms step_avg:138.54ms
step:3990/5100 train_loss:3.4975 train_time:551559ms step_avg:138.58ms
step:3991/5100 train_loss:3.4667 train_time:551690ms step_avg:138.58ms
step:3992/5100 train_loss:3.3182 train_time:551825ms step_avg:138.58ms
step:3993/5100 train_loss:3.4181 train_time:551960ms step_avg:138.58ms
step:3994/5100 train_loss:3.6072 train_time:552094ms step_avg:138.58ms
step:3995/5100 train_loss:3.4359 train_time:552226ms step_avg:138.58ms
step:3996/5100 train_loss:3.3516 train_time:552361ms step_avg:138.58ms
step:3997/5100 train_loss:3.4998 train_time:552498ms step_avg:138.57ms
step:3998/5100 train_loss:3.4130 train_time:552641ms step_avg:138.58ms
step:3999/5100 train_loss:3.3768 train_time:552778ms step_avg:138.58ms
step:4000/5100 train_loss:3.4422 train_time:552915ms step_avg:138.58ms
step:4000/5100 val_loss:3.4490 train_time:552985ms step_avg:138.59ms
step:4001/5100 train_loss:3.5638 train_time:553059ms step_avg:138.58ms
step:4002/5100 train_loss:3.6375 train_time:553202ms step_avg:138.58ms
step:4003/5100 train_loss:3.3152 train_time:553340ms step_avg:138.58ms
step:4004/5100 train_loss:3.5078 train_time:553476ms step_avg:138.58ms
step:4005/5100 train_loss:3.4119 train_time:553610ms step_avg:138.58ms
step:4006/5100 train_loss:3.4666 train_time:553745ms step_avg:138.57ms
step:4007/5100 train_loss:3.4547 train_time:553881ms step_avg:138.57ms
step:4008/5100 train_loss:3.6373 train_time:554021ms step_avg:138.57ms
step:4009/5100 train_loss:3.2364 train_time:554162ms step_avg:138.58ms
step:4010/5100 train_loss:3.4316 train_time:554300ms step_avg:138.58ms
step:4011/5100 train_loss:3.4187 train_time:554438ms step_avg:138.57ms
step:4012/5100 train_loss:3.3844 train_time:554574ms step_avg:138.57ms
step:4013/5100 train_loss:3.5536 train_time:554709ms step_avg:138.57ms
step:4014/5100 train_loss:3.4165 train_time:554843ms step_avg:138.57ms
step:4015/5100 train_loss:3.5084 train_time:554981ms step_avg:138.57ms
step:4016/5100 train_loss:3.6072 train_time:555122ms step_avg:138.57ms
step:4017/5100 train_loss:3.5855 train_time:555262ms step_avg:138.57ms
step:4018/5100 train_loss:3.3569 train_time:555400ms step_avg:138.57ms
step:4019/5100 train_loss:3.4847 train_time:555538ms step_avg:138.57ms
step:4020/5100 train_loss:3.4033 train_time:555676ms step_avg:138.57ms
step:4021/5100 train_loss:3.6679 train_time:555812ms step_avg:138.57ms
step:4022/5100 train_loss:3.5449 train_time:555946ms step_avg:138.57ms
step:4023/5100 train_loss:3.5320 train_time:556084ms step_avg:138.57ms
step:4024/5100 train_loss:3.5007 train_time:556222ms step_avg:138.57ms
step:4025/5100 train_loss:3.5241 train_time:556361ms step_avg:138.57ms
step:4026/5100 train_loss:3.2884 train_time:556499ms step_avg:138.57ms
step:4027/5100 train_loss:3.5099 train_time:556639ms step_avg:138.57ms
step:4028/5100 train_loss:3.4551 train_time:556776ms step_avg:138.57ms
step:4029/5100 train_loss:3.3492 train_time:556912ms step_avg:138.57ms
step:4030/5100 train_loss:3.3641 train_time:557046ms step_avg:138.57ms
step:4031/5100 train_loss:3.4216 train_time:557183ms step_avg:138.57ms
step:4032/5100 train_loss:3.5110 train_time:557322ms step_avg:138.57ms
step:4033/5100 train_loss:3.4798 train_time:557461ms step_avg:138.57ms
step:4034/5100 train_loss:3.4596 train_time:557600ms step_avg:138.57ms
step:4035/5100 train_loss:3.4644 train_time:557740ms step_avg:138.57ms
step:4036/5100 train_loss:3.3931 train_time:557876ms step_avg:138.57ms
step:4037/5100 train_loss:3.5567 train_time:558013ms step_avg:138.57ms
step:4038/5100 train_loss:3.4833 train_time:558146ms step_avg:138.57ms
step:4039/5100 train_loss:3.4668 train_time:558283ms step_avg:138.57ms
step:4040/5100 train_loss:3.4677 train_time:558421ms step_avg:138.57ms
step:4041/5100 train_loss:3.5031 train_time:558561ms step_avg:138.57ms
step:4042/5100 train_loss:3.7014 train_time:558699ms step_avg:138.57ms
step:4043/5100 train_loss:3.5990 train_time:558837ms step_avg:138.57ms
step:4044/5100 train_loss:3.3818 train_time:558974ms step_avg:138.57ms
step:4045/5100 train_loss:3.5464 train_time:559111ms step_avg:138.57ms
step:4046/5100 train_loss:3.2545 train_time:559247ms step_avg:138.56ms
step:4047/5100 train_loss:3.5157 train_time:559384ms step_avg:138.56ms
step:4048/5100 train_loss:3.6053 train_time:559522ms step_avg:138.56ms
step:4049/5100 train_loss:3.4776 train_time:559660ms step_avg:138.56ms
step:4050/5100 train_loss:3.4040 train_time:559799ms step_avg:138.56ms
step:4051/5100 train_loss:3.4446 train_time:559938ms step_avg:138.56ms
step:4052/5100 train_loss:3.3729 train_time:560077ms step_avg:138.56ms
step:4053/5100 train_loss:3.5863 train_time:560214ms step_avg:138.56ms
step:4054/5100 train_loss:3.4448 train_time:560350ms step_avg:138.56ms
step:4055/5100 train_loss:3.5269 train_time:560485ms step_avg:138.56ms
step:4056/5100 train_loss:3.5111 train_time:560623ms step_avg:138.56ms
step:4057/5100 train_loss:3.4803 train_time:560763ms step_avg:138.56ms
step:4058/5100 train_loss:3.3463 train_time:560900ms step_avg:138.56ms
step:4059/5100 train_loss:3.4936 train_time:561039ms step_avg:138.56ms
step:4060/5100 train_loss:3.3609 train_time:561176ms step_avg:138.56ms
step:4061/5100 train_loss:3.4387 train_time:561313ms step_avg:138.56ms
step:4062/5100 train_loss:3.5577 train_time:561450ms step_avg:138.56ms
step:4063/5100 train_loss:3.7336 train_time:561584ms step_avg:138.56ms
step:4064/5100 train_loss:3.1265 train_time:561722ms step_avg:138.56ms
step:4065/5100 train_loss:3.4822 train_time:561861ms step_avg:138.56ms
step:4066/5100 train_loss:3.3678 train_time:561999ms step_avg:138.56ms
step:4067/5100 train_loss:3.5244 train_time:562137ms step_avg:138.56ms
step:4068/5100 train_loss:3.5327 train_time:562276ms step_avg:138.56ms
step:4069/5100 train_loss:3.3294 train_time:562415ms step_avg:138.56ms
step:4070/5100 train_loss:3.5015 train_time:562548ms step_avg:138.56ms
step:4071/5100 train_loss:3.3180 train_time:562684ms step_avg:138.56ms
step:4072/5100 train_loss:3.4997 train_time:562823ms step_avg:138.56ms
step:4073/5100 train_loss:3.6079 train_time:562962ms step_avg:138.56ms
step:4074/5100 train_loss:3.5307 train_time:563099ms step_avg:138.56ms
step:4075/5100 train_loss:3.4431 train_time:563238ms step_avg:138.56ms
step:4076/5100 train_loss:3.4350 train_time:563376ms step_avg:138.56ms
step:4077/5100 train_loss:3.3198 train_time:563514ms step_avg:138.56ms
step:4078/5100 train_loss:3.4787 train_time:563648ms step_avg:138.56ms
step:4079/5100 train_loss:3.4924 train_time:563784ms step_avg:138.56ms
step:4080/5100 train_loss:3.2908 train_time:563923ms step_avg:138.56ms
step:4081/5100 train_loss:3.4657 train_time:564062ms step_avg:138.56ms
step:4082/5100 train_loss:3.4097 train_time:564200ms step_avg:138.56ms
step:4083/5100 train_loss:3.4722 train_time:564338ms step_avg:138.56ms
step:4084/5100 train_loss:3.4749 train_time:564475ms step_avg:138.56ms
step:4085/5100 train_loss:3.5080 train_time:564613ms step_avg:138.56ms
step:4086/5100 train_loss:3.4605 train_time:564749ms step_avg:138.55ms
step:4087/5100 train_loss:3.4355 train_time:564885ms step_avg:138.55ms
step:4088/5100 train_loss:3.5471 train_time:565022ms step_avg:138.55ms
step:4089/5100 train_loss:3.3855 train_time:565161ms step_avg:138.55ms
step:4090/5100 train_loss:3.4068 train_time:565298ms step_avg:138.55ms
step:4091/5100 train_loss:3.4263 train_time:565437ms step_avg:138.55ms
step:4092/5100 train_loss:3.3734 train_time:565575ms step_avg:138.55ms
step:4093/5100 train_loss:3.3788 train_time:565712ms step_avg:138.55ms
step:4094/5100 train_loss:3.5502 train_time:565846ms step_avg:138.55ms
step:4095/5100 train_loss:3.5410 train_time:565983ms step_avg:138.55ms
step:4096/5100 train_loss:3.4585 train_time:566122ms step_avg:138.55ms
step:4097/5100 train_loss:3.5186 train_time:566260ms step_avg:138.55ms
step:4098/5100 train_loss:3.2878 train_time:566399ms step_avg:138.55ms
step:4099/5100 train_loss:3.4342 train_time:566537ms step_avg:138.55ms
step:4100/5100 train_loss:3.4068 train_time:566678ms step_avg:138.55ms
step:4101/5100 train_loss:3.2056 train_time:566813ms step_avg:138.55ms
step:4102/5100 train_loss:3.4808 train_time:566948ms step_avg:138.55ms
step:4103/5100 train_loss:3.4410 train_time:567085ms step_avg:138.55ms
step:4104/5100 train_loss:3.2735 train_time:567223ms step_avg:138.55ms
step:4105/5100 train_loss:3.3680 train_time:567362ms step_avg:138.55ms
step:4106/5100 train_loss:3.5232 train_time:567500ms step_avg:138.55ms
step:4107/5100 train_loss:3.5731 train_time:567638ms step_avg:138.55ms
step:4108/5100 train_loss:3.4669 train_time:567778ms step_avg:138.55ms
step:4109/5100 train_loss:3.5567 train_time:567916ms step_avg:138.55ms
step:4110/5100 train_loss:3.5493 train_time:568052ms step_avg:138.55ms
step:4111/5100 train_loss:3.7259 train_time:568187ms step_avg:138.55ms
step:4112/5100 train_loss:3.3622 train_time:568324ms step_avg:138.55ms
step:4113/5100 train_loss:3.5022 train_time:568463ms step_avg:138.55ms
step:4114/5100 train_loss:3.3973 train_time:568600ms step_avg:138.55ms
step:4115/5100 train_loss:3.5162 train_time:568739ms step_avg:138.55ms
step:4116/5100 train_loss:3.5000 train_time:568876ms step_avg:138.55ms
step:4117/5100 train_loss:3.7442 train_time:569015ms step_avg:138.55ms
step:4118/5100 train_loss:3.3119 train_time:569152ms step_avg:138.55ms
step:4119/5100 train_loss:3.4844 train_time:569291ms step_avg:138.55ms
step:4120/5100 train_loss:3.3988 train_time:569426ms step_avg:138.55ms
step:4121/5100 train_loss:3.5056 train_time:569562ms step_avg:138.55ms
step:4122/5100 train_loss:3.5004 train_time:569700ms step_avg:138.55ms
step:4123/5100 train_loss:3.4844 train_time:569841ms step_avg:138.55ms
step:4124/5100 train_loss:3.3224 train_time:569983ms step_avg:138.55ms
step:4125/5100 train_loss:3.3313 train_time:570117ms step_avg:138.55ms
step:4125/5100 val_loss:3.4348 train_time:570189ms step_avg:138.56ms
step:4126/5100 train_loss:3.4547 train_time:570260ms step_avg:138.55ms
step:4127/5100 train_loss:3.3912 train_time:570407ms step_avg:138.55ms
step:4128/5100 train_loss:3.4582 train_time:570545ms step_avg:138.55ms
step:4129/5100 train_loss:3.4630 train_time:570679ms step_avg:138.55ms
step:4130/5100 train_loss:3.2406 train_time:570815ms step_avg:138.55ms
step:4131/5100 train_loss:3.5283 train_time:570950ms step_avg:138.55ms
step:4132/5100 train_loss:3.4954 train_time:571086ms step_avg:138.55ms
step:4133/5100 train_loss:3.4114 train_time:571215ms step_avg:138.54ms
step:4134/5100 train_loss:3.6126 train_time:571360ms step_avg:138.55ms
step:4135/5100 train_loss:3.4435 train_time:571501ms step_avg:138.55ms
step:4136/5100 train_loss:3.4186 train_time:571638ms step_avg:138.55ms
step:4137/5100 train_loss:3.5751 train_time:571775ms step_avg:138.54ms
step:4138/5100 train_loss:3.4159 train_time:571912ms step_avg:138.54ms
step:4139/5100 train_loss:3.4682 train_time:572047ms step_avg:138.54ms
step:4140/5100 train_loss:3.5620 train_time:572184ms step_avg:138.54ms
step:4141/5100 train_loss:3.5870 train_time:572322ms step_avg:138.54ms
step:4142/5100 train_loss:3.5581 train_time:572462ms step_avg:138.54ms
step:4143/5100 train_loss:3.5337 train_time:572600ms step_avg:138.54ms
step:4144/5100 train_loss:3.4324 train_time:572738ms step_avg:138.54ms
step:4145/5100 train_loss:3.4047 train_time:572875ms step_avg:138.54ms
step:4146/5100 train_loss:3.5094 train_time:573011ms step_avg:138.54ms
step:4147/5100 train_loss:3.0708 train_time:573145ms step_avg:138.54ms
step:4148/5100 train_loss:3.4274 train_time:573284ms step_avg:138.54ms
step:4149/5100 train_loss:3.4635 train_time:573422ms step_avg:138.54ms
step:4150/5100 train_loss:3.2727 train_time:573561ms step_avg:138.54ms
step:4151/5100 train_loss:3.3082 train_time:573699ms step_avg:138.54ms
step:4152/5100 train_loss:3.3563 train_time:573836ms step_avg:138.54ms
step:4153/5100 train_loss:3.4060 train_time:573973ms step_avg:138.54ms
step:4154/5100 train_loss:3.4599 train_time:574108ms step_avg:138.54ms
step:4155/5100 train_loss:3.5618 train_time:574246ms step_avg:138.54ms
step:4156/5100 train_loss:3.3675 train_time:574384ms step_avg:138.54ms
step:4157/5100 train_loss:3.3077 train_time:574522ms step_avg:138.54ms
step:4158/5100 train_loss:3.4452 train_time:574753ms step_avg:138.56ms
step:4159/5100 train_loss:3.4553 train_time:574883ms step_avg:138.56ms
step:4160/5100 train_loss:3.3699 train_time:575018ms step_avg:138.56ms
step:4161/5100 train_loss:3.4605 train_time:575153ms step_avg:138.56ms
step:4162/5100 train_loss:3.3907 train_time:575287ms step_avg:138.56ms
step:4163/5100 train_loss:3.6087 train_time:575422ms step_avg:138.56ms
step:4164/5100 train_loss:3.3051 train_time:575557ms step_avg:138.55ms
step:4165/5100 train_loss:3.4091 train_time:575700ms step_avg:138.56ms
step:4166/5100 train_loss:3.3891 train_time:575840ms step_avg:138.56ms
step:4167/5100 train_loss:3.4373 train_time:575982ms step_avg:138.56ms
step:4168/5100 train_loss:3.4260 train_time:576120ms step_avg:138.56ms
step:4169/5100 train_loss:3.4427 train_time:576256ms step_avg:138.56ms
step:4170/5100 train_loss:3.2898 train_time:576390ms step_avg:138.56ms
step:4171/5100 train_loss:3.3931 train_time:576525ms step_avg:138.55ms
step:4172/5100 train_loss:3.5192 train_time:576663ms step_avg:138.55ms
step:4173/5100 train_loss:3.5837 train_time:576803ms step_avg:138.55ms
step:4174/5100 train_loss:3.9635 train_time:576942ms step_avg:138.55ms
step:4175/5100 train_loss:3.3956 train_time:577080ms step_avg:138.55ms
step:4176/5100 train_loss:3.5467 train_time:577218ms step_avg:138.55ms
step:4177/5100 train_loss:3.3586 train_time:577360ms step_avg:138.56ms
step:4178/5100 train_loss:3.3792 train_time:577486ms step_avg:138.55ms
step:4179/5100 train_loss:3.5364 train_time:577623ms step_avg:138.55ms
step:4180/5100 train_loss:3.4790 train_time:577929ms step_avg:138.59ms
step:4181/5100 train_loss:3.4687 train_time:578067ms step_avg:138.59ms
step:4182/5100 train_loss:3.4718 train_time:578202ms step_avg:138.59ms
step:4183/5100 train_loss:3.5042 train_time:578338ms step_avg:138.59ms
step:4184/5100 train_loss:3.9407 train_time:578466ms step_avg:138.59ms
step:4185/5100 train_loss:3.4550 train_time:578605ms step_avg:138.59ms
step:4186/5100 train_loss:3.4952 train_time:578742ms step_avg:138.59ms
step:4187/5100 train_loss:3.5418 train_time:578879ms step_avg:138.59ms
step:4188/5100 train_loss:3.5268 train_time:579025ms step_avg:138.59ms
step:4189/5100 train_loss:3.1738 train_time:579163ms step_avg:138.59ms
step:4190/5100 train_loss:3.5271 train_time:579299ms step_avg:138.59ms
step:4191/5100 train_loss:3.5375 train_time:579435ms step_avg:138.59ms
step:4192/5100 train_loss:3.5095 train_time:579571ms step_avg:138.59ms
step:4193/5100 train_loss:3.4419 train_time:579707ms step_avg:138.59ms
step:4194/5100 train_loss:3.4604 train_time:579843ms step_avg:138.59ms
step:4195/5100 train_loss:3.4416 train_time:579982ms step_avg:138.59ms
step:4196/5100 train_loss:3.3808 train_time:580123ms step_avg:138.59ms
step:4197/5100 train_loss:3.7355 train_time:580262ms step_avg:138.59ms
step:4198/5100 train_loss:3.1773 train_time:580397ms step_avg:138.59ms
step:4199/5100 train_loss:3.5784 train_time:580535ms step_avg:138.59ms
step:4200/5100 train_loss:3.4605 train_time:580669ms step_avg:138.58ms
step:4201/5100 train_loss:3.3469 train_time:580804ms step_avg:138.58ms
step:4202/5100 train_loss:3.4812 train_time:580942ms step_avg:138.58ms
step:4203/5100 train_loss:3.3468 train_time:581081ms step_avg:138.58ms
step:4204/5100 train_loss:3.3585 train_time:581220ms step_avg:138.58ms
step:4205/5100 train_loss:3.3718 train_time:581357ms step_avg:138.58ms
step:4206/5100 train_loss:3.3637 train_time:581492ms step_avg:138.58ms
step:4207/5100 train_loss:3.8341 train_time:581629ms step_avg:138.58ms
step:4208/5100 train_loss:3.3979 train_time:581764ms step_avg:138.58ms
step:4209/5100 train_loss:3.5378 train_time:581902ms step_avg:138.58ms
step:4210/5100 train_loss:3.4331 train_time:582040ms step_avg:138.58ms
step:4211/5100 train_loss:3.8294 train_time:582178ms step_avg:138.58ms
step:4212/5100 train_loss:3.4714 train_time:582316ms step_avg:138.58ms
step:4213/5100 train_loss:3.4844 train_time:582453ms step_avg:138.58ms
step:4214/5100 train_loss:3.3485 train_time:582591ms step_avg:138.58ms
step:4215/5100 train_loss:3.4062 train_time:582724ms step_avg:138.58ms
step:4216/5100 train_loss:3.4905 train_time:582863ms step_avg:138.58ms
step:4217/5100 train_loss:3.3407 train_time:582999ms step_avg:138.58ms
step:4218/5100 train_loss:3.4059 train_time:583138ms step_avg:138.58ms
step:4219/5100 train_loss:3.4656 train_time:583277ms step_avg:138.58ms
step:4220/5100 train_loss:3.2669 train_time:583414ms step_avg:138.58ms
step:4221/5100 train_loss:3.4364 train_time:583552ms step_avg:138.58ms
step:4222/5100 train_loss:3.4646 train_time:583687ms step_avg:138.58ms
step:4223/5100 train_loss:3.4336 train_time:583824ms step_avg:138.58ms
step:4224/5100 train_loss:3.6353 train_time:583962ms step_avg:138.58ms
step:4225/5100 train_loss:3.5137 train_time:584100ms step_avg:138.58ms
step:4226/5100 train_loss:3.5622 train_time:584238ms step_avg:138.58ms
step:4227/5100 train_loss:3.3458 train_time:584376ms step_avg:138.58ms
step:4228/5100 train_loss:3.4172 train_time:584515ms step_avg:138.58ms
step:4229/5100 train_loss:3.4467 train_time:584651ms step_avg:138.58ms
step:4230/5100 train_loss:3.3642 train_time:584786ms step_avg:138.57ms
step:4231/5100 train_loss:3.5510 train_time:584923ms step_avg:138.57ms
step:4232/5100 train_loss:3.5499 train_time:585061ms step_avg:138.57ms
step:4233/5100 train_loss:3.5479 train_time:585198ms step_avg:138.57ms
step:4234/5100 train_loss:3.6572 train_time:585338ms step_avg:138.57ms
step:4235/5100 train_loss:3.5054 train_time:585474ms step_avg:138.57ms
step:4236/5100 train_loss:3.4600 train_time:585613ms step_avg:138.57ms
step:4237/5100 train_loss:3.3001 train_time:585749ms step_avg:138.57ms
step:4238/5100 train_loss:3.5089 train_time:585886ms step_avg:138.57ms
step:4239/5100 train_loss:3.4317 train_time:586024ms step_avg:138.57ms
step:4240/5100 train_loss:3.3476 train_time:586163ms step_avg:138.57ms
step:4241/5100 train_loss:3.3859 train_time:586301ms step_avg:138.57ms
step:4242/5100 train_loss:3.3319 train_time:586439ms step_avg:138.57ms
step:4243/5100 train_loss:3.4177 train_time:586578ms step_avg:138.57ms
step:4244/5100 train_loss:3.3415 train_time:586716ms step_avg:138.57ms
step:4245/5100 train_loss:3.2499 train_time:586853ms step_avg:138.57ms
step:4246/5100 train_loss:3.5541 train_time:586987ms step_avg:138.57ms
step:4247/5100 train_loss:3.3565 train_time:587125ms step_avg:138.57ms
step:4248/5100 train_loss:3.2831 train_time:587264ms step_avg:138.57ms
step:4249/5100 train_loss:3.4954 train_time:587402ms step_avg:138.57ms
step:4250/5100 train_loss:3.8152 train_time:587540ms step_avg:138.57ms
step:4250/5100 val_loss:3.4226 train_time:587612ms step_avg:138.59ms
step:4251/5100 train_loss:3.4054 train_time:587682ms step_avg:138.57ms
step:4252/5100 train_loss:3.6485 train_time:587831ms step_avg:138.57ms
step:4253/5100 train_loss:3.4967 train_time:587968ms step_avg:138.57ms
step:4254/5100 train_loss:3.3088 train_time:588102ms step_avg:138.57ms
step:4255/5100 train_loss:3.3897 train_time:588238ms step_avg:138.57ms
step:4256/5100 train_loss:3.3088 train_time:588373ms step_avg:138.57ms
step:4257/5100 train_loss:3.5453 train_time:588507ms step_avg:138.57ms
step:4258/5100 train_loss:3.4372 train_time:588645ms step_avg:138.57ms
step:4259/5100 train_loss:3.4799 train_time:588788ms step_avg:138.57ms
step:4260/5100 train_loss:3.3103 train_time:588925ms step_avg:138.57ms
step:4261/5100 train_loss:3.6049 train_time:589063ms step_avg:138.57ms
step:4262/5100 train_loss:3.4363 train_time:589201ms step_avg:138.57ms
step:4263/5100 train_loss:3.4391 train_time:589338ms step_avg:138.57ms
step:4264/5100 train_loss:3.4916 train_time:589474ms step_avg:138.57ms
step:4265/5100 train_loss:3.4363 train_time:589610ms step_avg:138.57ms
step:4266/5100 train_loss:3.4435 train_time:589747ms step_avg:138.57ms
step:4267/5100 train_loss:3.5641 train_time:589886ms step_avg:138.57ms
step:4268/5100 train_loss:3.3966 train_time:590023ms step_avg:138.57ms
step:4269/5100 train_loss:3.9291 train_time:590162ms step_avg:138.57ms
step:4270/5100 train_loss:3.3648 train_time:590299ms step_avg:138.57ms
step:4271/5100 train_loss:3.4696 train_time:590436ms step_avg:138.57ms
step:4272/5100 train_loss:3.3969 train_time:590573ms step_avg:138.57ms
step:4273/5100 train_loss:3.6076 train_time:590709ms step_avg:138.57ms
step:4274/5100 train_loss:3.5230 train_time:590848ms step_avg:138.57ms
step:4275/5100 train_loss:3.3891 train_time:590985ms step_avg:138.57ms
step:4276/5100 train_loss:3.4414 train_time:591123ms step_avg:138.57ms
step:4277/5100 train_loss:3.3605 train_time:591262ms step_avg:138.57ms
step:4278/5100 train_loss:3.3996 train_time:591398ms step_avg:138.57ms
step:4279/5100 train_loss:3.4016 train_time:591536ms step_avg:138.57ms
step:4280/5100 train_loss:3.4699 train_time:591673ms step_avg:138.57ms
step:4281/5100 train_loss:3.4513 train_time:591808ms step_avg:138.56ms
step:4282/5100 train_loss:3.4764 train_time:591947ms step_avg:138.56ms
step:4283/5100 train_loss:3.3997 train_time:592084ms step_avg:138.56ms
step:4284/5100 train_loss:3.4484 train_time:592223ms step_avg:138.56ms
step:4285/5100 train_loss:3.5092 train_time:592361ms step_avg:138.56ms
step:4286/5100 train_loss:3.4540 train_time:592498ms step_avg:138.56ms
step:4287/5100 train_loss:3.3553 train_time:592636ms step_avg:138.56ms
step:4288/5100 train_loss:3.3848 train_time:592773ms step_avg:138.56ms
step:4289/5100 train_loss:3.4761 train_time:592910ms step_avg:138.56ms
step:4290/5100 train_loss:3.4390 train_time:593048ms step_avg:138.56ms
step:4291/5100 train_loss:3.3417 train_time:593185ms step_avg:138.56ms
step:4292/5100 train_loss:3.3701 train_time:593324ms step_avg:138.56ms
step:4293/5100 train_loss:3.4344 train_time:593463ms step_avg:138.56ms
step:4294/5100 train_loss:3.2351 train_time:593600ms step_avg:138.56ms
step:4295/5100 train_loss:3.5711 train_time:593738ms step_avg:138.56ms
step:4296/5100 train_loss:3.4652 train_time:593874ms step_avg:138.56ms
step:4297/5100 train_loss:3.4171 train_time:594011ms step_avg:138.56ms
step:4298/5100 train_loss:3.5906 train_time:594149ms step_avg:138.56ms
step:4299/5100 train_loss:3.5049 train_time:594288ms step_avg:138.56ms
step:4300/5100 train_loss:3.3344 train_time:594426ms step_avg:138.56ms
step:4301/5100 train_loss:3.3230 train_time:594565ms step_avg:138.56ms
step:4302/5100 train_loss:3.4750 train_time:594701ms step_avg:138.56ms
step:4303/5100 train_loss:3.3185 train_time:594839ms step_avg:138.56ms
step:4304/5100 train_loss:3.4690 train_time:594976ms step_avg:138.56ms
step:4305/5100 train_loss:3.5416 train_time:595114ms step_avg:138.56ms
step:4306/5100 train_loss:3.2994 train_time:595250ms step_avg:138.56ms
step:4307/5100 train_loss:3.8259 train_time:595386ms step_avg:138.56ms
step:4308/5100 train_loss:3.4382 train_time:595524ms step_avg:138.56ms
step:4309/5100 train_loss:3.3584 train_time:595663ms step_avg:138.56ms
step:4310/5100 train_loss:3.3692 train_time:595801ms step_avg:138.56ms
step:4311/5100 train_loss:3.6666 train_time:595939ms step_avg:138.56ms
step:4312/5100 train_loss:3.4991 train_time:596076ms step_avg:138.56ms
step:4313/5100 train_loss:3.3468 train_time:596215ms step_avg:138.56ms
step:4314/5100 train_loss:3.5541 train_time:596353ms step_avg:138.56ms
step:4315/5100 train_loss:3.4882 train_time:596488ms step_avg:138.56ms
step:4316/5100 train_loss:3.4002 train_time:596625ms step_avg:138.56ms
step:4317/5100 train_loss:3.4367 train_time:596763ms step_avg:138.56ms
step:4318/5100 train_loss:3.4055 train_time:596900ms step_avg:138.56ms
step:4319/5100 train_loss:3.5134 train_time:597038ms step_avg:138.56ms
step:4320/5100 train_loss:3.5581 train_time:597177ms step_avg:138.56ms
step:4321/5100 train_loss:3.3834 train_time:597314ms step_avg:138.56ms
step:4322/5100 train_loss:3.5507 train_time:597452ms step_avg:138.56ms
step:4323/5100 train_loss:3.4203 train_time:597588ms step_avg:138.56ms
step:4324/5100 train_loss:3.3321 train_time:597725ms step_avg:138.55ms
step:4325/5100 train_loss:3.2900 train_time:597864ms step_avg:138.55ms
step:4326/5100 train_loss:3.3799 train_time:598001ms step_avg:138.55ms
step:4327/5100 train_loss:3.2581 train_time:598140ms step_avg:138.55ms
step:4328/5100 train_loss:3.3901 train_time:598277ms step_avg:138.55ms
step:4329/5100 train_loss:3.4114 train_time:598417ms step_avg:138.55ms
step:4330/5100 train_loss:3.3517 train_time:598554ms step_avg:138.55ms
step:4331/5100 train_loss:3.6113 train_time:598691ms step_avg:138.55ms
step:4332/5100 train_loss:3.4139 train_time:598825ms step_avg:138.55ms
step:4333/5100 train_loss:3.5303 train_time:598966ms step_avg:138.55ms
step:4334/5100 train_loss:3.8949 train_time:599103ms step_avg:138.55ms
step:4335/5100 train_loss:3.4226 train_time:599241ms step_avg:138.55ms
step:4336/5100 train_loss:3.5252 train_time:599379ms step_avg:138.55ms
step:4337/5100 train_loss:3.4188 train_time:599518ms step_avg:138.55ms
step:4338/5100 train_loss:3.3104 train_time:599656ms step_avg:138.55ms
step:4339/5100 train_loss:3.4460 train_time:599794ms step_avg:138.55ms
step:4340/5100 train_loss:3.3455 train_time:599931ms step_avg:138.55ms
step:4341/5100 train_loss:3.4401 train_time:600067ms step_avg:138.55ms
step:4342/5100 train_loss:3.4606 train_time:600205ms step_avg:138.55ms
step:4343/5100 train_loss:3.4551 train_time:600343ms step_avg:138.55ms
step:4344/5100 train_loss:3.4493 train_time:600481ms step_avg:138.55ms
step:4345/5100 train_loss:4.0794 train_time:600619ms step_avg:138.55ms
step:4346/5100 train_loss:3.5205 train_time:600757ms step_avg:138.55ms
step:4347/5100 train_loss:3.3227 train_time:600989ms step_avg:138.57ms
step:4348/5100 train_loss:3.4583 train_time:601118ms step_avg:138.57ms
step:4349/5100 train_loss:3.4068 train_time:601251ms step_avg:138.57ms
step:4350/5100 train_loss:3.3167 train_time:601386ms step_avg:138.57ms
step:4351/5100 train_loss:3.4845 train_time:601520ms step_avg:138.57ms
step:4352/5100 train_loss:3.4382 train_time:601655ms step_avg:138.57ms
step:4353/5100 train_loss:3.5070 train_time:601790ms step_avg:138.57ms
step:4354/5100 train_loss:3.5408 train_time:601931ms step_avg:138.57ms
step:4355/5100 train_loss:3.3688 train_time:602074ms step_avg:138.57ms
step:4356/5100 train_loss:3.3149 train_time:602212ms step_avg:138.57ms
step:4357/5100 train_loss:3.4567 train_time:602347ms step_avg:138.57ms
step:4358/5100 train_loss:3.3947 train_time:602482ms step_avg:138.57ms
step:4359/5100 train_loss:3.5880 train_time:602618ms step_avg:138.56ms
step:4360/5100 train_loss:3.4469 train_time:602758ms step_avg:138.56ms
step:4361/5100 train_loss:3.5270 train_time:602894ms step_avg:138.56ms
step:4362/5100 train_loss:3.6899 train_time:603034ms step_avg:138.56ms
step:4363/5100 train_loss:3.4798 train_time:603171ms step_avg:138.56ms
step:4364/5100 train_loss:3.4450 train_time:603308ms step_avg:138.56ms
step:4365/5100 train_loss:3.6509 train_time:603445ms step_avg:138.56ms
step:4366/5100 train_loss:3.5405 train_time:603583ms step_avg:138.56ms
step:4367/5100 train_loss:3.3614 train_time:603719ms step_avg:138.56ms
step:4368/5100 train_loss:3.3742 train_time:603854ms step_avg:138.56ms
step:4369/5100 train_loss:3.4715 train_time:603991ms step_avg:138.56ms
step:4370/5100 train_loss:3.4713 train_time:604304ms step_avg:138.60ms
step:4371/5100 train_loss:3.6235 train_time:604439ms step_avg:138.60ms
step:4372/5100 train_loss:3.3145 train_time:604572ms step_avg:138.60ms
step:4373/5100 train_loss:3.3081 train_time:604706ms step_avg:138.60ms
step:4374/5100 train_loss:3.4661 train_time:604841ms step_avg:138.60ms
step:4375/5100 train_loss:3.4845 train_time:604976ms step_avg:138.60ms
step:4375/5100 val_loss:3.4048 train_time:605043ms step_avg:138.61ms
step:4376/5100 train_loss:3.5533 train_time:605117ms step_avg:138.60ms
step:4377/5100 train_loss:3.3466 train_time:605260ms step_avg:138.60ms
step:4378/5100 train_loss:3.3968 train_time:605398ms step_avg:138.60ms
step:4379/5100 train_loss:3.4113 train_time:605533ms step_avg:138.60ms
step:4380/5100 train_loss:3.4538 train_time:605666ms step_avg:138.60ms
step:4381/5100 train_loss:3.3502 train_time:605801ms step_avg:138.60ms
step:4382/5100 train_loss:3.5906 train_time:605937ms step_avg:138.59ms
step:4383/5100 train_loss:3.5073 train_time:606074ms step_avg:138.59ms
step:4384/5100 train_loss:3.4991 train_time:606215ms step_avg:138.60ms
step:4385/5100 train_loss:3.3795 train_time:606350ms step_avg:138.59ms
step:4386/5100 train_loss:3.5043 train_time:606486ms step_avg:138.59ms
step:4387/5100 train_loss:3.4024 train_time:606625ms step_avg:138.59ms
step:4388/5100 train_loss:3.5320 train_time:606762ms step_avg:138.59ms
step:4389/5100 train_loss:3.3567 train_time:606899ms step_avg:138.59ms
step:4390/5100 train_loss:3.4780 train_time:607035ms step_avg:138.59ms
step:4391/5100 train_loss:3.4922 train_time:607173ms step_avg:138.59ms
step:4392/5100 train_loss:3.3155 train_time:607311ms step_avg:138.59ms
step:4393/5100 train_loss:3.9848 train_time:607451ms step_avg:138.59ms
step:4394/5100 train_loss:3.3893 train_time:607589ms step_avg:138.59ms
step:4395/5100 train_loss:3.5746 train_time:607726ms step_avg:138.59ms
step:4396/5100 train_loss:3.3518 train_time:607861ms step_avg:138.59ms
step:4397/5100 train_loss:3.4691 train_time:607999ms step_avg:138.59ms
step:4398/5100 train_loss:3.2700 train_time:608135ms step_avg:138.59ms
step:4399/5100 train_loss:3.4931 train_time:608274ms step_avg:138.59ms
step:4400/5100 train_loss:3.3303 train_time:608411ms step_avg:138.59ms
step:4401/5100 train_loss:3.3956 train_time:608549ms step_avg:138.59ms
step:4402/5100 train_loss:3.4693 train_time:608687ms step_avg:138.59ms
step:4403/5100 train_loss:3.3056 train_time:608823ms step_avg:138.59ms
step:4404/5100 train_loss:3.3521 train_time:608962ms step_avg:138.59ms
step:4405/5100 train_loss:3.5578 train_time:609099ms step_avg:138.59ms
step:4406/5100 train_loss:3.4091 train_time:609237ms step_avg:138.59ms
step:4407/5100 train_loss:3.4195 train_time:609374ms step_avg:138.59ms
step:4408/5100 train_loss:3.3864 train_time:609511ms step_avg:138.59ms
step:4409/5100 train_loss:3.4659 train_time:609648ms step_avg:138.59ms
step:4410/5100 train_loss:3.4516 train_time:609787ms step_avg:138.59ms
step:4411/5100 train_loss:3.5709 train_time:609925ms step_avg:138.59ms
step:4412/5100 train_loss:3.4172 train_time:610064ms step_avg:138.59ms
step:4413/5100 train_loss:3.4487 train_time:610202ms step_avg:138.59ms
step:4414/5100 train_loss:3.4261 train_time:610340ms step_avg:138.59ms
step:4415/5100 train_loss:3.4845 train_time:610476ms step_avg:138.59ms
step:4416/5100 train_loss:3.4259 train_time:610613ms step_avg:138.59ms
step:4417/5100 train_loss:3.4949 train_time:610750ms step_avg:138.59ms
step:4418/5100 train_loss:3.4261 train_time:610888ms step_avg:138.59ms
step:4419/5100 train_loss:3.3377 train_time:611026ms step_avg:138.59ms
step:4420/5100 train_loss:3.3747 train_time:611165ms step_avg:138.59ms
step:4421/5100 train_loss:3.6124 train_time:611302ms step_avg:138.59ms
step:4422/5100 train_loss:3.4129 train_time:611440ms step_avg:138.59ms
step:4423/5100 train_loss:3.3295 train_time:611576ms step_avg:138.59ms
step:4424/5100 train_loss:3.3583 train_time:611713ms step_avg:138.58ms
step:4425/5100 train_loss:3.5289 train_time:611849ms step_avg:138.58ms
step:4426/5100 train_loss:3.4858 train_time:611988ms step_avg:138.58ms
step:4427/5100 train_loss:3.4010 train_time:612126ms step_avg:138.58ms
step:4428/5100 train_loss:3.6108 train_time:612265ms step_avg:138.58ms
step:4429/5100 train_loss:3.5229 train_time:612404ms step_avg:138.58ms
step:4430/5100 train_loss:3.3186 train_time:612541ms step_avg:138.58ms
step:4431/5100 train_loss:3.3134 train_time:612678ms step_avg:138.58ms
step:4432/5100 train_loss:3.4543 train_time:612815ms step_avg:138.58ms
step:4433/5100 train_loss:3.3322 train_time:612950ms step_avg:138.58ms
step:4434/5100 train_loss:3.4447 train_time:613089ms step_avg:138.58ms
step:4435/5100 train_loss:3.5049 train_time:613227ms step_avg:138.58ms
step:4436/5100 train_loss:3.4008 train_time:613365ms step_avg:138.58ms
step:4437/5100 train_loss:3.3091 train_time:613503ms step_avg:138.58ms
step:4438/5100 train_loss:3.5617 train_time:613642ms step_avg:138.58ms
step:4439/5100 train_loss:3.4888 train_time:613780ms step_avg:138.58ms
step:4440/5100 train_loss:3.3869 train_time:613918ms step_avg:138.58ms
step:4441/5100 train_loss:3.4893 train_time:614055ms step_avg:138.58ms
step:4442/5100 train_loss:3.5216 train_time:614190ms step_avg:138.58ms
step:4443/5100 train_loss:3.5768 train_time:614329ms step_avg:138.58ms
step:4444/5100 train_loss:3.4576 train_time:614467ms step_avg:138.58ms
step:4445/5100 train_loss:3.2805 train_time:614604ms step_avg:138.58ms
step:4446/5100 train_loss:3.5539 train_time:614743ms step_avg:138.58ms
step:4447/5100 train_loss:3.4356 train_time:614881ms step_avg:138.58ms
step:4448/5100 train_loss:3.3244 train_time:615018ms step_avg:138.58ms
step:4449/5100 train_loss:3.4578 train_time:615154ms step_avg:138.58ms
step:4450/5100 train_loss:3.4435 train_time:615290ms step_avg:138.58ms
step:4451/5100 train_loss:3.4540 train_time:615428ms step_avg:138.58ms
step:4452/5100 train_loss:3.4864 train_time:615570ms step_avg:138.58ms
step:4453/5100 train_loss:3.3560 train_time:615702ms step_avg:138.58ms
step:4454/5100 train_loss:3.3949 train_time:615840ms step_avg:138.58ms
step:4455/5100 train_loss:3.3849 train_time:615978ms step_avg:138.58ms
step:4456/5100 train_loss:3.2761 train_time:616117ms step_avg:138.58ms
step:4457/5100 train_loss:3.4894 train_time:616250ms step_avg:138.58ms
step:4458/5100 train_loss:3.3628 train_time:616387ms step_avg:138.58ms
step:4459/5100 train_loss:3.3264 train_time:616525ms step_avg:138.58ms
step:4460/5100 train_loss:3.4493 train_time:616667ms step_avg:138.58ms
step:4461/5100 train_loss:3.9441 train_time:616800ms step_avg:138.58ms
step:4462/5100 train_loss:3.4408 train_time:616940ms step_avg:138.58ms
step:4463/5100 train_loss:3.5603 train_time:617078ms step_avg:138.58ms
step:4464/5100 train_loss:3.4608 train_time:617217ms step_avg:138.58ms
step:4465/5100 train_loss:3.4380 train_time:617354ms step_avg:138.58ms
step:4466/5100 train_loss:3.5080 train_time:617489ms step_avg:138.57ms
step:4467/5100 train_loss:3.3164 train_time:617628ms step_avg:138.57ms
step:4468/5100 train_loss:3.3603 train_time:617765ms step_avg:138.57ms
step:4469/5100 train_loss:3.4941 train_time:617906ms step_avg:138.58ms
step:4470/5100 train_loss:3.4639 train_time:618044ms step_avg:138.57ms
step:4471/5100 train_loss:3.4006 train_time:618182ms step_avg:138.57ms
step:4472/5100 train_loss:3.3496 train_time:618321ms step_avg:138.57ms
step:4473/5100 train_loss:3.4314 train_time:618457ms step_avg:138.57ms
step:4474/5100 train_loss:3.2833 train_time:618592ms step_avg:138.57ms
step:4475/5100 train_loss:3.3629 train_time:618727ms step_avg:138.57ms
step:4476/5100 train_loss:3.3899 train_time:618866ms step_avg:138.57ms
step:4477/5100 train_loss:3.5462 train_time:619003ms step_avg:138.57ms
step:4478/5100 train_loss:3.2822 train_time:619141ms step_avg:138.57ms
step:4479/5100 train_loss:3.4036 train_time:619279ms step_avg:138.57ms
step:4480/5100 train_loss:3.4472 train_time:619416ms step_avg:138.57ms
step:4481/5100 train_loss:3.4177 train_time:619551ms step_avg:138.57ms
step:4482/5100 train_loss:3.4133 train_time:619686ms step_avg:138.57ms
step:4483/5100 train_loss:3.2240 train_time:619824ms step_avg:138.57ms
step:4484/5100 train_loss:3.3831 train_time:619962ms step_avg:138.57ms
step:4485/5100 train_loss:3.3189 train_time:620101ms step_avg:138.57ms
step:4486/5100 train_loss:3.4589 train_time:620240ms step_avg:138.57ms
step:4487/5100 train_loss:3.3351 train_time:620377ms step_avg:138.57ms
step:4488/5100 train_loss:3.4034 train_time:620513ms step_avg:138.57ms
step:4489/5100 train_loss:3.5400 train_time:620648ms step_avg:138.57ms
step:4490/5100 train_loss:3.5074 train_time:620786ms step_avg:138.57ms
step:4491/5100 train_loss:3.3875 train_time:620924ms step_avg:138.57ms
step:4492/5100 train_loss:3.3514 train_time:621061ms step_avg:138.57ms
step:4493/5100 train_loss:3.3956 train_time:621201ms step_avg:138.57ms
step:4494/5100 train_loss:3.4251 train_time:621339ms step_avg:138.57ms
step:4495/5100 train_loss:3.4160 train_time:621477ms step_avg:138.57ms
step:4496/5100 train_loss:3.3614 train_time:621614ms step_avg:138.57ms
step:4497/5100 train_loss:3.5184 train_time:621748ms step_avg:138.57ms
step:4498/5100 train_loss:3.4065 train_time:621886ms step_avg:138.57ms
step:4499/5100 train_loss:3.2476 train_time:622024ms step_avg:138.57ms
step:4500/5100 train_loss:3.5478 train_time:622164ms step_avg:138.57ms
step:4500/5100 val_loss:3.3930 train_time:622237ms step_avg:138.58ms
step:4501/5100 train_loss:3.3560 train_time:622309ms step_avg:138.57ms
step:4502/5100 train_loss:3.3086 train_time:622451ms step_avg:138.57ms
step:4503/5100 train_loss:3.4934 train_time:622588ms step_avg:138.57ms
step:4504/5100 train_loss:3.3750 train_time:622725ms step_avg:138.57ms
step:4505/5100 train_loss:3.4755 train_time:622861ms step_avg:138.57ms
step:4506/5100 train_loss:3.3868 train_time:622997ms step_avg:138.57ms
step:4507/5100 train_loss:3.4643 train_time:623131ms step_avg:138.57ms
step:4508/5100 train_loss:3.1914 train_time:623270ms step_avg:138.57ms
step:4509/5100 train_loss:3.4707 train_time:623409ms step_avg:138.57ms
step:4510/5100 train_loss:3.3064 train_time:623549ms step_avg:138.57ms
step:4511/5100 train_loss:3.3735 train_time:623688ms step_avg:138.57ms
step:4512/5100 train_loss:3.3385 train_time:623826ms step_avg:138.57ms
step:4513/5100 train_loss:3.3231 train_time:623962ms step_avg:138.57ms
step:4514/5100 train_loss:3.2853 train_time:624098ms step_avg:138.57ms
step:4515/5100 train_loss:3.4285 train_time:624234ms step_avg:138.56ms
step:4516/5100 train_loss:3.2813 train_time:624371ms step_avg:138.56ms
step:4517/5100 train_loss:3.3897 train_time:624510ms step_avg:138.56ms
step:4518/5100 train_loss:3.3886 train_time:624648ms step_avg:138.56ms
step:4519/5100 train_loss:3.4012 train_time:624785ms step_avg:138.56ms
step:4520/5100 train_loss:3.3174 train_time:624924ms step_avg:138.56ms
step:4521/5100 train_loss:3.4972 train_time:625061ms step_avg:138.56ms
step:4522/5100 train_loss:3.5736 train_time:625197ms step_avg:138.56ms
step:4523/5100 train_loss:3.9116 train_time:625333ms step_avg:138.56ms
step:4524/5100 train_loss:3.6409 train_time:625469ms step_avg:138.56ms
step:4525/5100 train_loss:3.4110 train_time:625609ms step_avg:138.56ms
step:4526/5100 train_loss:3.3584 train_time:625748ms step_avg:138.56ms
step:4527/5100 train_loss:3.4293 train_time:625885ms step_avg:138.56ms
step:4528/5100 train_loss:3.3911 train_time:626022ms step_avg:138.56ms
step:4529/5100 train_loss:3.3062 train_time:626158ms step_avg:138.56ms
step:4530/5100 train_loss:3.9952 train_time:626295ms step_avg:138.56ms
step:4531/5100 train_loss:3.4763 train_time:626431ms step_avg:138.56ms
step:4532/5100 train_loss:3.2045 train_time:626570ms step_avg:138.56ms
step:4533/5100 train_loss:3.3141 train_time:626707ms step_avg:138.56ms
step:4534/5100 train_loss:3.4247 train_time:626845ms step_avg:138.56ms
step:4535/5100 train_loss:3.6414 train_time:626987ms step_avg:138.56ms
step:4536/5100 train_loss:3.6414 train_time:627219ms step_avg:138.58ms
step:4537/5100 train_loss:3.3777 train_time:627348ms step_avg:138.58ms
step:4538/5100 train_loss:3.3733 train_time:627483ms step_avg:138.58ms
step:4539/5100 train_loss:3.4084 train_time:627619ms step_avg:138.58ms
step:4540/5100 train_loss:3.9786 train_time:627754ms step_avg:138.58ms
step:4541/5100 train_loss:3.4591 train_time:627888ms step_avg:138.58ms
step:4542/5100 train_loss:3.3684 train_time:628023ms step_avg:138.58ms
step:4543/5100 train_loss:3.5332 train_time:628162ms step_avg:138.58ms
step:4544/5100 train_loss:3.3222 train_time:628305ms step_avg:138.58ms
step:4545/5100 train_loss:3.4244 train_time:628443ms step_avg:138.58ms
step:4546/5100 train_loss:3.6018 train_time:628582ms step_avg:138.58ms
step:4547/5100 train_loss:3.4570 train_time:628720ms step_avg:138.58ms
step:4548/5100 train_loss:3.4129 train_time:628854ms step_avg:138.58ms
step:4549/5100 train_loss:3.3964 train_time:628988ms step_avg:138.57ms
step:4550/5100 train_loss:3.3489 train_time:629125ms step_avg:138.57ms
step:4551/5100 train_loss:3.3403 train_time:629264ms step_avg:138.57ms
step:4552/5100 train_loss:3.3031 train_time:629404ms step_avg:138.57ms
step:4553/5100 train_loss:3.4179 train_time:629542ms step_avg:138.57ms
step:4554/5100 train_loss:3.6074 train_time:629678ms step_avg:138.57ms
step:4555/5100 train_loss:3.4890 train_time:629813ms step_avg:138.57ms
step:4556/5100 train_loss:3.2410 train_time:629949ms step_avg:138.57ms
step:4557/5100 train_loss:3.4494 train_time:630086ms step_avg:138.57ms
step:4558/5100 train_loss:3.4609 train_time:630225ms step_avg:138.57ms
step:4559/5100 train_loss:3.4499 train_time:630365ms step_avg:138.57ms
step:4560/5100 train_loss:3.5377 train_time:630681ms step_avg:138.61ms
step:4561/5100 train_loss:3.3790 train_time:630812ms step_avg:138.61ms
step:4562/5100 train_loss:3.3852 train_time:630947ms step_avg:138.61ms
step:4563/5100 train_loss:3.4133 train_time:631081ms step_avg:138.61ms
step:4564/5100 train_loss:3.4494 train_time:631208ms step_avg:138.61ms
step:4565/5100 train_loss:3.5338 train_time:631342ms step_avg:138.60ms
step:4566/5100 train_loss:3.5895 train_time:631483ms step_avg:138.60ms
step:4567/5100 train_loss:3.4530 train_time:631621ms step_avg:138.60ms
step:4568/5100 train_loss:3.3149 train_time:631763ms step_avg:138.61ms
step:4569/5100 train_loss:3.4190 train_time:631903ms step_avg:138.61ms
step:4570/5100 train_loss:3.3011 train_time:632040ms step_avg:138.61ms
step:4571/5100 train_loss:3.3402 train_time:632178ms step_avg:138.61ms
step:4572/5100 train_loss:3.5315 train_time:632311ms step_avg:138.60ms
step:4573/5100 train_loss:3.2468 train_time:632446ms step_avg:138.60ms
step:4574/5100 train_loss:3.3223 train_time:632583ms step_avg:138.60ms
step:4575/5100 train_loss:3.4508 train_time:632725ms step_avg:138.60ms
step:4576/5100 train_loss:3.4785 train_time:632864ms step_avg:138.60ms
step:4577/5100 train_loss:3.4358 train_time:633002ms step_avg:138.60ms
step:4578/5100 train_loss:3.4036 train_time:633140ms step_avg:138.60ms
step:4579/5100 train_loss:3.4238 train_time:633275ms step_avg:138.60ms
step:4580/5100 train_loss:3.5185 train_time:633409ms step_avg:138.60ms
step:4581/5100 train_loss:3.3497 train_time:633546ms step_avg:138.60ms
step:4582/5100 train_loss:3.3751 train_time:633685ms step_avg:138.60ms
step:4583/5100 train_loss:3.4882 train_time:633824ms step_avg:138.60ms
step:4584/5100 train_loss:3.3318 train_time:633963ms step_avg:138.60ms
step:4585/5100 train_loss:3.4510 train_time:634100ms step_avg:138.60ms
step:4586/5100 train_loss:3.4251 train_time:634238ms step_avg:138.60ms
step:4587/5100 train_loss:3.4022 train_time:634374ms step_avg:138.60ms
step:4588/5100 train_loss:3.2628 train_time:634507ms step_avg:138.60ms
step:4589/5100 train_loss:3.3850 train_time:634646ms step_avg:138.60ms
step:4590/5100 train_loss:3.5850 train_time:634785ms step_avg:138.60ms
step:4591/5100 train_loss:3.4050 train_time:634926ms step_avg:138.60ms
step:4592/5100 train_loss:3.4032 train_time:635064ms step_avg:138.60ms
step:4593/5100 train_loss:3.3610 train_time:635198ms step_avg:138.60ms
step:4594/5100 train_loss:3.5232 train_time:635336ms step_avg:138.60ms
step:4595/5100 train_loss:3.4104 train_time:635472ms step_avg:138.60ms
step:4596/5100 train_loss:3.3098 train_time:635610ms step_avg:138.60ms
step:4597/5100 train_loss:3.3050 train_time:635748ms step_avg:138.60ms
step:4598/5100 train_loss:3.4810 train_time:635887ms step_avg:138.60ms
step:4599/5100 train_loss:3.4053 train_time:636026ms step_avg:138.60ms
step:4600/5100 train_loss:3.5262 train_time:636164ms step_avg:138.60ms
step:4601/5100 train_loss:3.4353 train_time:636301ms step_avg:138.60ms
step:4602/5100 train_loss:3.2430 train_time:636437ms step_avg:138.60ms
step:4603/5100 train_loss:3.3541 train_time:636576ms step_avg:138.60ms
step:4604/5100 train_loss:3.4387 train_time:636710ms step_avg:138.60ms
step:4605/5100 train_loss:3.4496 train_time:636851ms step_avg:138.60ms
step:4606/5100 train_loss:3.3672 train_time:636987ms step_avg:138.60ms
step:4607/5100 train_loss:3.4866 train_time:637126ms step_avg:138.60ms
step:4608/5100 train_loss:3.3563 train_time:637264ms step_avg:138.60ms
step:4609/5100 train_loss:3.4620 train_time:637403ms step_avg:138.60ms
step:4610/5100 train_loss:3.4099 train_time:637540ms step_avg:138.60ms
step:4611/5100 train_loss:3.4483 train_time:637677ms step_avg:138.60ms
step:4612/5100 train_loss:3.5895 train_time:637811ms step_avg:138.59ms
step:4613/5100 train_loss:3.2923 train_time:637949ms step_avg:138.59ms
step:4614/5100 train_loss:3.1426 train_time:638088ms step_avg:138.59ms
step:4615/5100 train_loss:3.3524 train_time:638227ms step_avg:138.59ms
step:4616/5100 train_loss:3.2692 train_time:638366ms step_avg:138.59ms
step:4617/5100 train_loss:3.3723 train_time:638504ms step_avg:138.59ms
step:4618/5100 train_loss:3.2413 train_time:638642ms step_avg:138.59ms
step:4619/5100 train_loss:3.4616 train_time:638779ms step_avg:138.59ms
step:4620/5100 train_loss:3.5021 train_time:638915ms step_avg:138.59ms
step:4621/5100 train_loss:3.5366 train_time:639050ms step_avg:138.59ms
step:4622/5100 train_loss:3.3289 train_time:639189ms step_avg:138.59ms
step:4623/5100 train_loss:3.3395 train_time:639328ms step_avg:138.59ms
step:4624/5100 train_loss:3.3689 train_time:639467ms step_avg:138.59ms
step:4625/5100 train_loss:3.2823 train_time:639604ms step_avg:138.59ms
step:4625/5100 val_loss:3.3796 train_time:639676ms step_avg:138.61ms
step:4626/5100 train_loss:3.4520 train_time:639750ms step_avg:138.59ms
step:4627/5100 train_loss:3.3390 train_time:639892ms step_avg:138.59ms
step:4628/5100 train_loss:3.4081 train_time:640029ms step_avg:138.59ms
step:4629/5100 train_loss:3.5984 train_time:640164ms step_avg:138.59ms
step:4630/5100 train_loss:3.4365 train_time:640301ms step_avg:138.59ms
step:4631/5100 train_loss:3.5304 train_time:640433ms step_avg:138.59ms
step:4632/5100 train_loss:3.3376 train_time:640568ms step_avg:138.59ms
step:4633/5100 train_loss:3.5205 train_time:640707ms step_avg:138.59ms
step:4634/5100 train_loss:3.3759 train_time:640848ms step_avg:138.59ms
step:4635/5100 train_loss:3.4394 train_time:640983ms step_avg:138.59ms
step:4636/5100 train_loss:3.4417 train_time:641121ms step_avg:138.59ms
step:4637/5100 train_loss:3.2711 train_time:641259ms step_avg:138.59ms
step:4638/5100 train_loss:3.4495 train_time:641395ms step_avg:138.59ms
step:4639/5100 train_loss:3.4035 train_time:641533ms step_avg:138.59ms
step:4640/5100 train_loss:3.4037 train_time:641671ms step_avg:138.59ms
step:4641/5100 train_loss:3.3369 train_time:641811ms step_avg:138.59ms
step:4642/5100 train_loss:3.3857 train_time:641948ms step_avg:138.59ms
step:4643/5100 train_loss:3.3846 train_time:642085ms step_avg:138.59ms
step:4644/5100 train_loss:3.6079 train_time:642222ms step_avg:138.59ms
step:4645/5100 train_loss:3.4690 train_time:642360ms step_avg:138.59ms
step:4646/5100 train_loss:3.5200 train_time:642499ms step_avg:138.59ms
step:4647/5100 train_loss:3.3443 train_time:642637ms step_avg:138.59ms
step:4648/5100 train_loss:3.4477 train_time:642776ms step_avg:138.59ms
step:4649/5100 train_loss:3.3905 train_time:642916ms step_avg:138.59ms
step:4650/5100 train_loss:3.4407 train_time:643053ms step_avg:138.59ms
step:4651/5100 train_loss:3.5572 train_time:643189ms step_avg:138.59ms
step:4652/5100 train_loss:3.3865 train_time:643324ms step_avg:138.59ms
step:4653/5100 train_loss:3.4963 train_time:643462ms step_avg:138.59ms
step:4654/5100 train_loss:3.3422 train_time:643600ms step_avg:138.59ms
step:4655/5100 train_loss:3.3830 train_time:643739ms step_avg:138.59ms
step:4656/5100 train_loss:3.4115 train_time:643878ms step_avg:138.59ms
step:4657/5100 train_loss:3.3579 train_time:644016ms step_avg:138.59ms
step:4658/5100 train_loss:3.2843 train_time:644152ms step_avg:138.59ms
step:4659/5100 train_loss:3.3299 train_time:644290ms step_avg:138.59ms
step:4660/5100 train_loss:3.2603 train_time:644426ms step_avg:138.59ms
step:4661/5100 train_loss:3.4289 train_time:644565ms step_avg:138.59ms
step:4662/5100 train_loss:3.4143 train_time:644701ms step_avg:138.59ms
step:4663/5100 train_loss:3.3685 train_time:644839ms step_avg:138.59ms
step:4664/5100 train_loss:3.3023 train_time:644976ms step_avg:138.59ms
step:4665/5100 train_loss:3.3145 train_time:645115ms step_avg:138.59ms
step:4666/5100 train_loss:3.3553 train_time:645253ms step_avg:138.59ms
step:4667/5100 train_loss:3.4569 train_time:645391ms step_avg:138.59ms
step:4668/5100 train_loss:3.3620 train_time:645528ms step_avg:138.58ms
step:4669/5100 train_loss:3.3453 train_time:645664ms step_avg:138.58ms
step:4670/5100 train_loss:3.3965 train_time:645802ms step_avg:138.58ms
step:4671/5100 train_loss:3.4880 train_time:645940ms step_avg:138.58ms
step:4672/5100 train_loss:3.3814 train_time:646076ms step_avg:138.58ms
step:4673/5100 train_loss:3.4294 train_time:646215ms step_avg:138.58ms
step:4674/5100 train_loss:3.3692 train_time:646353ms step_avg:138.58ms
step:4675/5100 train_loss:3.3986 train_time:646491ms step_avg:138.58ms
step:4676/5100 train_loss:3.4828 train_time:646628ms step_avg:138.58ms
step:4677/5100 train_loss:3.2184 train_time:646765ms step_avg:138.58ms
step:4678/5100 train_loss:3.2668 train_time:646901ms step_avg:138.58ms
step:4679/5100 train_loss:3.3985 train_time:647040ms step_avg:138.58ms
step:4680/5100 train_loss:3.3636 train_time:647180ms step_avg:138.58ms
step:4681/5100 train_loss:3.3831 train_time:647315ms step_avg:138.58ms
step:4682/5100 train_loss:3.3735 train_time:647454ms step_avg:138.58ms
step:4683/5100 train_loss:3.3067 train_time:647591ms step_avg:138.58ms
step:4684/5100 train_loss:3.2796 train_time:647725ms step_avg:138.58ms
step:4685/5100 train_loss:3.5328 train_time:647864ms step_avg:138.58ms
step:4686/5100 train_loss:3.6136 train_time:648001ms step_avg:138.58ms
step:4687/5100 train_loss:3.3033 train_time:648140ms step_avg:138.58ms
step:4688/5100 train_loss:3.3089 train_time:648277ms step_avg:138.58ms
step:4689/5100 train_loss:3.4939 train_time:648416ms step_avg:138.58ms
step:4690/5100 train_loss:3.3298 train_time:648554ms step_avg:138.58ms
step:4691/5100 train_loss:3.1895 train_time:648692ms step_avg:138.58ms
step:4692/5100 train_loss:3.2877 train_time:648829ms step_avg:138.58ms
step:4693/5100 train_loss:3.3041 train_time:648965ms step_avg:138.58ms
step:4694/5100 train_loss:3.3246 train_time:649105ms step_avg:138.58ms
step:4695/5100 train_loss:3.3336 train_time:649243ms step_avg:138.58ms
step:4696/5100 train_loss:3.3561 train_time:649380ms step_avg:138.58ms
step:4697/5100 train_loss:3.4134 train_time:649518ms step_avg:138.58ms
step:4698/5100 train_loss:3.3325 train_time:649657ms step_avg:138.58ms
step:4699/5100 train_loss:3.3560 train_time:649794ms step_avg:138.58ms
step:4700/5100 train_loss:3.4493 train_time:649929ms step_avg:138.58ms
step:4701/5100 train_loss:3.3725 train_time:650066ms step_avg:138.58ms
step:4702/5100 train_loss:3.3577 train_time:650204ms step_avg:138.58ms
step:4703/5100 train_loss:3.3202 train_time:650342ms step_avg:138.58ms
step:4704/5100 train_loss:3.4084 train_time:650481ms step_avg:138.58ms
step:4705/5100 train_loss:3.3499 train_time:650619ms step_avg:138.58ms
step:4706/5100 train_loss:3.2815 train_time:650756ms step_avg:138.58ms
step:4707/5100 train_loss:3.4076 train_time:650893ms step_avg:138.58ms
step:4708/5100 train_loss:3.4980 train_time:651031ms step_avg:138.58ms
step:4709/5100 train_loss:3.3118 train_time:651168ms step_avg:138.58ms
step:4710/5100 train_loss:3.2914 train_time:651303ms step_avg:138.58ms
step:4711/5100 train_loss:3.3160 train_time:651444ms step_avg:138.58ms
step:4712/5100 train_loss:3.3299 train_time:651582ms step_avg:138.58ms
step:4713/5100 train_loss:3.4489 train_time:651721ms step_avg:138.58ms
step:4714/5100 train_loss:3.2940 train_time:651859ms step_avg:138.58ms
step:4715/5100 train_loss:3.3693 train_time:651996ms step_avg:138.58ms
step:4716/5100 train_loss:3.2924 train_time:652134ms step_avg:138.57ms
step:4717/5100 train_loss:3.3640 train_time:652271ms step_avg:138.57ms
step:4718/5100 train_loss:3.2959 train_time:652407ms step_avg:138.57ms
step:4719/5100 train_loss:3.2587 train_time:652546ms step_avg:138.57ms
step:4720/5100 train_loss:3.4196 train_time:652683ms step_avg:138.57ms
step:4721/5100 train_loss:3.4120 train_time:652822ms step_avg:138.57ms
step:4722/5100 train_loss:3.4129 train_time:652958ms step_avg:138.57ms
step:4723/5100 train_loss:3.2700 train_time:653097ms step_avg:138.57ms
step:4724/5100 train_loss:3.4434 train_time:653235ms step_avg:138.57ms
step:4725/5100 train_loss:3.3231 train_time:653468ms step_avg:138.59ms
step:4726/5100 train_loss:3.6109 train_time:653598ms step_avg:138.59ms
step:4727/5100 train_loss:3.4537 train_time:653732ms step_avg:138.59ms
step:4728/5100 train_loss:3.3346 train_time:653867ms step_avg:138.59ms
step:4729/5100 train_loss:3.2618 train_time:654000ms step_avg:138.59ms
step:4730/5100 train_loss:3.2145 train_time:654136ms step_avg:138.59ms
step:4731/5100 train_loss:3.3198 train_time:654277ms step_avg:138.59ms
step:4732/5100 train_loss:3.3871 train_time:654422ms step_avg:138.59ms
step:4733/5100 train_loss:3.2820 train_time:654562ms step_avg:138.59ms
step:4734/5100 train_loss:3.1644 train_time:654700ms step_avg:138.59ms
step:4735/5100 train_loss:3.4585 train_time:654844ms step_avg:138.59ms
step:4736/5100 train_loss:3.3326 train_time:654981ms step_avg:138.59ms
step:4737/5100 train_loss:3.5084 train_time:655115ms step_avg:138.59ms
step:4738/5100 train_loss:3.4219 train_time:655252ms step_avg:138.59ms
step:4739/5100 train_loss:3.3815 train_time:655391ms step_avg:138.59ms
step:4740/5100 train_loss:3.3442 train_time:655533ms step_avg:138.59ms
step:4741/5100 train_loss:3.3628 train_time:655672ms step_avg:138.59ms
step:4742/5100 train_loss:3.3473 train_time:655809ms step_avg:138.59ms
step:4743/5100 train_loss:3.2381 train_time:655947ms step_avg:138.59ms
step:4744/5100 train_loss:3.3678 train_time:656067ms step_avg:138.59ms
step:4745/5100 train_loss:3.3357 train_time:656201ms step_avg:138.59ms
step:4746/5100 train_loss:3.3360 train_time:656338ms step_avg:138.58ms
step:4747/5100 train_loss:3.3104 train_time:656479ms step_avg:138.59ms
step:4748/5100 train_loss:3.4975 train_time:656619ms step_avg:138.59ms
step:4749/5100 train_loss:3.3453 train_time:656757ms step_avg:138.59ms
step:4750/5100 train_loss:3.4430 train_time:657066ms step_avg:138.62ms
step:4750/5100 val_loss:3.3665 train_time:657133ms step_avg:138.64ms
step:4751/5100 train_loss:3.2568 train_time:657205ms step_avg:138.62ms
step:4752/5100 train_loss:3.1772 train_time:657348ms step_avg:138.62ms
step:4753/5100 train_loss:3.2647 train_time:657487ms step_avg:138.62ms
step:4754/5100 train_loss:3.4650 train_time:657622ms step_avg:138.62ms
step:4755/5100 train_loss:3.3505 train_time:657757ms step_avg:138.62ms
step:4756/5100 train_loss:3.5876 train_time:657892ms step_avg:138.62ms
step:4757/5100 train_loss:3.4490 train_time:658027ms step_avg:138.62ms
step:4758/5100 train_loss:3.3625 train_time:658165ms step_avg:138.62ms
step:4759/5100 train_loss:3.4088 train_time:658306ms step_avg:138.62ms
step:4760/5100 train_loss:3.4128 train_time:658445ms step_avg:138.62ms
step:4761/5100 train_loss:3.3432 train_time:658584ms step_avg:138.62ms
step:4762/5100 train_loss:3.3806 train_time:658722ms step_avg:138.62ms
step:4763/5100 train_loss:3.3502 train_time:658857ms step_avg:138.62ms
step:4764/5100 train_loss:3.2088 train_time:658992ms step_avg:138.62ms
step:4765/5100 train_loss:3.2222 train_time:659128ms step_avg:138.62ms
step:4766/5100 train_loss:3.2206 train_time:659267ms step_avg:138.62ms
step:4767/5100 train_loss:3.4610 train_time:659406ms step_avg:138.62ms
step:4768/5100 train_loss:3.7157 train_time:659544ms step_avg:138.62ms
step:4769/5100 train_loss:3.4334 train_time:659685ms step_avg:138.62ms
step:4770/5100 train_loss:3.3399 train_time:659822ms step_avg:138.62ms
step:4771/5100 train_loss:3.4012 train_time:659958ms step_avg:138.62ms
step:4772/5100 train_loss:3.3602 train_time:660096ms step_avg:138.62ms
step:4773/5100 train_loss:3.3367 train_time:660231ms step_avg:138.62ms
step:4774/5100 train_loss:3.5281 train_time:660370ms step_avg:138.62ms
step:4775/5100 train_loss:3.3366 train_time:660508ms step_avg:138.62ms
step:4776/5100 train_loss:3.4664 train_time:660646ms step_avg:138.62ms
step:4777/5100 train_loss:3.3908 train_time:660783ms step_avg:138.62ms
step:4778/5100 train_loss:3.2251 train_time:660920ms step_avg:138.62ms
step:4779/5100 train_loss:3.4022 train_time:661058ms step_avg:138.62ms
step:4780/5100 train_loss:3.3360 train_time:661194ms step_avg:138.62ms
step:4781/5100 train_loss:3.4141 train_time:661332ms step_avg:138.61ms
step:4782/5100 train_loss:3.3285 train_time:661468ms step_avg:138.61ms
step:4783/5100 train_loss:3.2839 train_time:661607ms step_avg:138.61ms
step:4784/5100 train_loss:3.3376 train_time:661747ms step_avg:138.61ms
step:4785/5100 train_loss:3.2668 train_time:661885ms step_avg:138.61ms
step:4786/5100 train_loss:3.5922 train_time:662023ms step_avg:138.61ms
step:4787/5100 train_loss:3.4763 train_time:662161ms step_avg:138.61ms
step:4788/5100 train_loss:3.3976 train_time:662298ms step_avg:138.61ms
step:4789/5100 train_loss:3.3801 train_time:662437ms step_avg:138.61ms
step:4790/5100 train_loss:3.3037 train_time:662572ms step_avg:138.61ms
step:4791/5100 train_loss:3.4129 train_time:662710ms step_avg:138.61ms
step:4792/5100 train_loss:3.4225 train_time:662848ms step_avg:138.61ms
step:4793/5100 train_loss:3.3383 train_time:662988ms step_avg:138.61ms
step:4794/5100 train_loss:3.4239 train_time:663125ms step_avg:138.61ms
step:4795/5100 train_loss:3.2511 train_time:663262ms step_avg:138.61ms
step:4796/5100 train_loss:3.4000 train_time:663401ms step_avg:138.61ms
step:4797/5100 train_loss:3.4709 train_time:663538ms step_avg:138.61ms
step:4798/5100 train_loss:3.1378 train_time:663677ms step_avg:138.61ms
step:4799/5100 train_loss:3.3141 train_time:663811ms step_avg:138.61ms
step:4800/5100 train_loss:3.3014 train_time:663949ms step_avg:138.61ms
step:4801/5100 train_loss:3.3955 train_time:664088ms step_avg:138.61ms
step:4802/5100 train_loss:3.2192 train_time:664226ms step_avg:138.61ms
step:4803/5100 train_loss:3.2573 train_time:664364ms step_avg:138.61ms
step:4804/5100 train_loss:3.4507 train_time:664501ms step_avg:138.61ms
step:4805/5100 train_loss:3.4067 train_time:664639ms step_avg:138.61ms
step:4806/5100 train_loss:3.4624 train_time:664776ms step_avg:138.61ms
step:4807/5100 train_loss:3.4838 train_time:664913ms step_avg:138.61ms
step:4808/5100 train_loss:3.2502 train_time:665049ms step_avg:138.61ms
step:4809/5100 train_loss:3.3631 train_time:665187ms step_avg:138.61ms
step:4810/5100 train_loss:3.3129 train_time:665325ms step_avg:138.61ms
step:4811/5100 train_loss:3.5420 train_time:665464ms step_avg:138.61ms
step:4812/5100 train_loss:3.3428 train_time:665602ms step_avg:138.61ms
step:4813/5100 train_loss:3.3858 train_time:665742ms step_avg:138.61ms
step:4814/5100 train_loss:3.2667 train_time:665879ms step_avg:138.61ms
step:4815/5100 train_loss:3.3221 train_time:666016ms step_avg:138.61ms
step:4816/5100 train_loss:3.7556 train_time:666153ms step_avg:138.61ms
step:4817/5100 train_loss:3.4338 train_time:666289ms step_avg:138.61ms
step:4818/5100 train_loss:3.3721 train_time:666428ms step_avg:138.61ms
step:4819/5100 train_loss:3.2184 train_time:666568ms step_avg:138.61ms
step:4820/5100 train_loss:3.3583 train_time:666705ms step_avg:138.61ms
step:4821/5100 train_loss:3.3551 train_time:666843ms step_avg:138.61ms
step:4822/5100 train_loss:3.4171 train_time:666980ms step_avg:138.61ms
step:4823/5100 train_loss:3.4690 train_time:667119ms step_avg:138.61ms
step:4824/5100 train_loss:3.3487 train_time:667257ms step_avg:138.61ms
step:4825/5100 train_loss:3.3352 train_time:667392ms step_avg:138.61ms
step:4826/5100 train_loss:3.2602 train_time:667530ms step_avg:138.61ms
step:4827/5100 train_loss:3.2152 train_time:667670ms step_avg:138.61ms
step:4828/5100 train_loss:3.4071 train_time:667807ms step_avg:138.61ms
step:4829/5100 train_loss:3.2939 train_time:667946ms step_avg:138.61ms
step:4830/5100 train_loss:3.4063 train_time:668084ms step_avg:138.61ms
step:4831/5100 train_loss:3.5652 train_time:668222ms step_avg:138.61ms
step:4832/5100 train_loss:3.3078 train_time:668358ms step_avg:138.61ms
step:4833/5100 train_loss:3.3826 train_time:668497ms step_avg:138.61ms
step:4834/5100 train_loss:3.3533 train_time:668633ms step_avg:138.61ms
step:4835/5100 train_loss:3.5308 train_time:668771ms step_avg:138.61ms
step:4836/5100 train_loss:3.3520 train_time:668908ms step_avg:138.61ms
step:4837/5100 train_loss:3.6012 train_time:669047ms step_avg:138.61ms
step:4838/5100 train_loss:3.5524 train_time:669185ms step_avg:138.61ms
step:4839/5100 train_loss:3.3880 train_time:669324ms step_avg:138.61ms
step:4840/5100 train_loss:3.3772 train_time:669461ms step_avg:138.60ms
step:4841/5100 train_loss:3.3657 train_time:669598ms step_avg:138.60ms
step:4842/5100 train_loss:3.4033 train_time:669735ms step_avg:138.60ms
step:4843/5100 train_loss:3.4002 train_time:669871ms step_avg:138.60ms
step:4844/5100 train_loss:3.2595 train_time:670009ms step_avg:138.60ms
step:4845/5100 train_loss:3.2914 train_time:670149ms step_avg:138.60ms
step:4846/5100 train_loss:3.2626 train_time:670287ms step_avg:138.60ms
step:4847/5100 train_loss:3.4248 train_time:670427ms step_avg:138.60ms
step:4848/5100 train_loss:3.2959 train_time:670563ms step_avg:138.60ms
step:4849/5100 train_loss:3.3344 train_time:670699ms step_avg:138.60ms
step:4850/5100 train_loss:3.4672 train_time:670839ms step_avg:138.60ms
step:4851/5100 train_loss:3.3510 train_time:670976ms step_avg:138.60ms
step:4852/5100 train_loss:3.1509 train_time:671112ms step_avg:138.60ms
step:4853/5100 train_loss:3.2521 train_time:671252ms step_avg:138.60ms
step:4854/5100 train_loss:3.3867 train_time:671388ms step_avg:138.60ms
step:4855/5100 train_loss:3.3453 train_time:671527ms step_avg:138.60ms
step:4856/5100 train_loss:3.4776 train_time:671664ms step_avg:138.60ms
step:4857/5100 train_loss:3.3140 train_time:671802ms step_avg:138.60ms
step:4858/5100 train_loss:3.3555 train_time:671941ms step_avg:138.60ms
step:4859/5100 train_loss:3.3020 train_time:672078ms step_avg:138.60ms
step:4860/5100 train_loss:3.4267 train_time:672214ms step_avg:138.60ms
step:4861/5100 train_loss:3.3017 train_time:672351ms step_avg:138.60ms
step:4862/5100 train_loss:3.3549 train_time:672488ms step_avg:138.60ms
step:4863/5100 train_loss:3.3694 train_time:672626ms step_avg:138.60ms
step:4864/5100 train_loss:3.3200 train_time:672765ms step_avg:138.60ms
step:4865/5100 train_loss:3.3975 train_time:672904ms step_avg:138.60ms
step:4866/5100 train_loss:3.0473 train_time:673040ms step_avg:138.60ms
step:4867/5100 train_loss:3.2676 train_time:673176ms step_avg:138.60ms
step:4868/5100 train_loss:3.3198 train_time:673312ms step_avg:138.60ms
step:4869/5100 train_loss:3.3430 train_time:673450ms step_avg:138.60ms
step:4870/5100 train_loss:3.3472 train_time:673589ms step_avg:138.60ms
step:4871/5100 train_loss:3.3600 train_time:673727ms step_avg:138.60ms
step:4872/5100 train_loss:3.4631 train_time:673865ms step_avg:138.60ms
step:4873/5100 train_loss:3.4548 train_time:674003ms step_avg:138.60ms
step:4874/5100 train_loss:3.4827 train_time:674141ms step_avg:138.60ms
step:4875/5100 train_loss:3.5556 train_time:674280ms step_avg:138.60ms
step:4875/5100 val_loss:3.3548 train_time:674350ms step_avg:138.61ms
step:4876/5100 train_loss:3.3814 train_time:674422ms step_avg:138.60ms
step:4877/5100 train_loss:3.2881 train_time:674565ms step_avg:138.60ms
step:4878/5100 train_loss:3.2520 train_time:674701ms step_avg:138.60ms
step:4879/5100 train_loss:3.3036 train_time:674836ms step_avg:138.60ms
step:4880/5100 train_loss:3.4356 train_time:674971ms step_avg:138.60ms
step:4881/5100 train_loss:3.2857 train_time:675106ms step_avg:138.60ms
step:4882/5100 train_loss:3.4008 train_time:675242ms step_avg:138.60ms
step:4883/5100 train_loss:3.4133 train_time:675380ms step_avg:138.60ms
step:4884/5100 train_loss:3.3252 train_time:675519ms step_avg:138.60ms
step:4885/5100 train_loss:3.3228 train_time:675656ms step_avg:138.60ms
step:4886/5100 train_loss:3.4309 train_time:675791ms step_avg:138.60ms
step:4887/5100 train_loss:3.4531 train_time:675927ms step_avg:138.59ms
step:4888/5100 train_loss:3.3294 train_time:676065ms step_avg:138.59ms
step:4889/5100 train_loss:3.3023 train_time:676201ms step_avg:138.59ms
step:4890/5100 train_loss:3.3845 train_time:676339ms step_avg:138.59ms
step:4891/5100 train_loss:3.2909 train_time:676476ms step_avg:138.59ms
step:4892/5100 train_loss:3.3888 train_time:676614ms step_avg:138.59ms
step:4893/5100 train_loss:3.3784 train_time:676751ms step_avg:138.59ms
step:4894/5100 train_loss:3.4145 train_time:676889ms step_avg:138.59ms
step:4895/5100 train_loss:3.4785 train_time:677028ms step_avg:138.59ms
step:4896/5100 train_loss:3.3724 train_time:677165ms step_avg:138.59ms
step:4897/5100 train_loss:3.3270 train_time:677303ms step_avg:138.59ms
step:4898/5100 train_loss:3.5207 train_time:677442ms step_avg:138.59ms
step:4899/5100 train_loss:3.2871 train_time:677580ms step_avg:138.59ms
step:4900/5100 train_loss:3.3365 train_time:677718ms step_avg:138.59ms
step:4901/5100 train_loss:3.2517 train_time:677853ms step_avg:138.59ms
step:4902/5100 train_loss:3.2153 train_time:677991ms step_avg:138.59ms
step:4903/5100 train_loss:3.3495 train_time:678129ms step_avg:138.59ms
step:4904/5100 train_loss:3.2990 train_time:678267ms step_avg:138.59ms
step:4905/5100 train_loss:3.3738 train_time:678404ms step_avg:138.59ms
step:4906/5100 train_loss:3.4092 train_time:678543ms step_avg:138.59ms
step:4907/5100 train_loss:3.2882 train_time:678682ms step_avg:138.59ms
step:4908/5100 train_loss:3.3722 train_time:678818ms step_avg:138.59ms
step:4909/5100 train_loss:3.2832 train_time:678953ms step_avg:138.59ms
step:4910/5100 train_loss:3.3932 train_time:679090ms step_avg:138.59ms
step:4911/5100 train_loss:3.4434 train_time:679228ms step_avg:138.59ms
step:4912/5100 train_loss:3.3405 train_time:679368ms step_avg:138.59ms
step:4913/5100 train_loss:3.3088 train_time:679506ms step_avg:138.59ms
step:4914/5100 train_loss:3.3000 train_time:679732ms step_avg:138.61ms
step:4915/5100 train_loss:3.2235 train_time:679862ms step_avg:138.61ms
step:4916/5100 train_loss:3.4256 train_time:679997ms step_avg:138.61ms
step:4917/5100 train_loss:3.3980 train_time:680131ms step_avg:138.60ms
step:4918/5100 train_loss:3.3354 train_time:680266ms step_avg:138.60ms
step:4919/5100 train_loss:3.3455 train_time:680401ms step_avg:138.60ms
step:4920/5100 train_loss:3.3433 train_time:680537ms step_avg:138.60ms
step:4921/5100 train_loss:3.4212 train_time:680678ms step_avg:138.60ms
step:4922/5100 train_loss:3.5792 train_time:680820ms step_avg:138.60ms
step:4923/5100 train_loss:3.4367 train_time:680957ms step_avg:138.60ms
step:4924/5100 train_loss:3.3044 train_time:681093ms step_avg:138.60ms
step:4925/5100 train_loss:3.6123 train_time:681228ms step_avg:138.60ms
step:4926/5100 train_loss:3.3506 train_time:681367ms step_avg:138.60ms
step:4927/5100 train_loss:3.3236 train_time:681501ms step_avg:138.60ms
step:4928/5100 train_loss:3.2524 train_time:681638ms step_avg:138.60ms
step:4929/5100 train_loss:3.2753 train_time:681775ms step_avg:138.60ms
step:4930/5100 train_loss:3.4085 train_time:681911ms step_avg:138.60ms
step:4931/5100 train_loss:3.6535 train_time:682050ms step_avg:138.60ms
step:4932/5100 train_loss:3.2635 train_time:682189ms step_avg:138.60ms
step:4933/5100 train_loss:3.3545 train_time:682325ms step_avg:138.60ms
step:4934/5100 train_loss:3.4185 train_time:682461ms step_avg:138.60ms
step:4935/5100 train_loss:3.2076 train_time:682597ms step_avg:138.60ms
step:4936/5100 train_loss:3.3742 train_time:682734ms step_avg:138.60ms
step:4937/5100 train_loss:3.4176 train_time:682872ms step_avg:138.60ms
step:4938/5100 train_loss:3.4017 train_time:683009ms step_avg:138.60ms
step:4939/5100 train_loss:3.3962 train_time:683150ms step_avg:138.60ms
step:4940/5100 train_loss:3.5181 train_time:683456ms step_avg:138.63ms
step:4941/5100 train_loss:3.3533 train_time:683586ms step_avg:138.63ms
step:4942/5100 train_loss:3.3666 train_time:683720ms step_avg:138.63ms
step:4943/5100 train_loss:3.1206 train_time:683856ms step_avg:138.63ms
step:4944/5100 train_loss:3.5982 train_time:683989ms step_avg:138.63ms
step:4945/5100 train_loss:3.5634 train_time:684124ms step_avg:138.63ms
step:4946/5100 train_loss:3.1833 train_time:684260ms step_avg:138.63ms
step:4947/5100 train_loss:3.4360 train_time:684396ms step_avg:138.63ms
step:4948/5100 train_loss:3.4649 train_time:684538ms step_avg:138.63ms
step:4949/5100 train_loss:3.3011 train_time:684676ms step_avg:138.63ms
step:4950/5100 train_loss:3.4264 train_time:684811ms step_avg:138.63ms
step:4951/5100 train_loss:3.2880 train_time:684947ms step_avg:138.63ms
step:4952/5100 train_loss:3.4067 train_time:685083ms step_avg:138.62ms
step:4953/5100 train_loss:3.3832 train_time:685218ms step_avg:138.62ms
step:4954/5100 train_loss:3.2555 train_time:685355ms step_avg:138.62ms
step:4955/5100 train_loss:3.3970 train_time:685495ms step_avg:138.62ms
step:4956/5100 train_loss:3.2261 train_time:685631ms step_avg:138.62ms
step:4957/5100 train_loss:3.3232 train_time:685769ms step_avg:138.62ms
step:4958/5100 train_loss:3.3052 train_time:685907ms step_avg:138.62ms
step:4959/5100 train_loss:3.3247 train_time:686043ms step_avg:138.62ms
step:4960/5100 train_loss:3.3592 train_time:686180ms step_avg:138.62ms
step:4961/5100 train_loss:3.5010 train_time:686317ms step_avg:138.62ms
step:4962/5100 train_loss:3.2704 train_time:686453ms step_avg:138.62ms
step:4963/5100 train_loss:3.4055 train_time:686592ms step_avg:138.62ms
step:4964/5100 train_loss:3.2467 train_time:686730ms step_avg:138.62ms
step:4965/5100 train_loss:3.9544 train_time:686868ms step_avg:138.62ms
step:4966/5100 train_loss:3.2470 train_time:687006ms step_avg:138.62ms
step:4967/5100 train_loss:3.3832 train_time:687143ms step_avg:138.62ms
step:4968/5100 train_loss:3.1958 train_time:687281ms step_avg:138.62ms
step:4969/5100 train_loss:3.9181 train_time:687418ms step_avg:138.62ms
step:4970/5100 train_loss:3.4503 train_time:687552ms step_avg:138.62ms
step:4971/5100 train_loss:3.3623 train_time:687690ms step_avg:138.62ms
step:4972/5100 train_loss:3.2996 train_time:687829ms step_avg:138.62ms
step:4973/5100 train_loss:3.3890 train_time:687966ms step_avg:138.62ms
step:4974/5100 train_loss:3.2702 train_time:688105ms step_avg:138.62ms
step:4975/5100 train_loss:3.2598 train_time:688242ms step_avg:138.62ms
step:4976/5100 train_loss:3.4066 train_time:688379ms step_avg:138.62ms
step:4977/5100 train_loss:3.3461 train_time:688517ms step_avg:138.62ms
step:4978/5100 train_loss:3.2959 train_time:688653ms step_avg:138.62ms
step:4979/5100 train_loss:3.3513 train_time:688790ms step_avg:138.62ms
step:4980/5100 train_loss:3.2966 train_time:688928ms step_avg:138.62ms
step:4981/5100 train_loss:3.4270 train_time:689067ms step_avg:138.62ms
step:4982/5100 train_loss:3.3967 train_time:689206ms step_avg:138.62ms
step:4983/5100 train_loss:3.2014 train_time:689343ms step_avg:138.62ms
step:4984/5100 train_loss:3.2341 train_time:689480ms step_avg:138.62ms
step:4985/5100 train_loss:3.5113 train_time:689620ms step_avg:138.62ms
step:4986/5100 train_loss:3.4031 train_time:689755ms step_avg:138.62ms
step:4987/5100 train_loss:3.3119 train_time:689892ms step_avg:138.62ms
step:4988/5100 train_loss:3.3498 train_time:690030ms step_avg:138.62ms
step:4989/5100 train_loss:3.3326 train_time:690168ms step_avg:138.62ms
step:4990/5100 train_loss:3.3112 train_time:690307ms step_avg:138.62ms
step:4991/5100 train_loss:3.3695 train_time:690445ms step_avg:138.62ms
step:4992/5100 train_loss:3.4054 train_time:690582ms step_avg:138.62ms
step:4993/5100 train_loss:3.2307 train_time:690720ms step_avg:138.62ms
step:4994/5100 train_loss:3.3635 train_time:690858ms step_avg:138.62ms
step:4995/5100 train_loss:3.2837 train_time:690996ms step_avg:138.61ms
step:4996/5100 train_loss:3.4273 train_time:691131ms step_avg:138.61ms
step:4997/5100 train_loss:3.3107 train_time:691270ms step_avg:138.61ms
step:4998/5100 train_loss:3.4627 train_time:691408ms step_avg:138.61ms
step:4999/5100 train_loss:3.3268 train_time:691545ms step_avg:138.61ms
step:5000/5100 train_loss:3.4539 train_time:691683ms step_avg:138.61ms
step:5000/5100 val_loss:3.3452 train_time:691758ms step_avg:138.63ms
step:5001/5100 train_loss:3.3871 train_time:691828ms step_avg:138.62ms
step:5002/5100 train_loss:3.3772 train_time:691973ms step_avg:138.62ms
step:5003/5100 train_loss:3.2724 train_time:692108ms step_avg:138.62ms
step:5004/5100 train_loss:3.3381 train_time:692244ms step_avg:138.62ms
step:5005/5100 train_loss:3.3599 train_time:692379ms step_avg:138.61ms
step:5006/5100 train_loss:3.2323 train_time:692515ms step_avg:138.61ms
step:5007/5100 train_loss:3.4616 train_time:692649ms step_avg:138.61ms
step:5008/5100 train_loss:3.3065 train_time:692789ms step_avg:138.61ms
step:5009/5100 train_loss:3.3337 train_time:692932ms step_avg:138.61ms
step:5010/5100 train_loss:3.3047 train_time:693069ms step_avg:138.61ms
step:5011/5100 train_loss:3.5078 train_time:693206ms step_avg:138.61ms
step:5012/5100 train_loss:3.3118 train_time:693343ms step_avg:138.61ms
step:5013/5100 train_loss:3.2939 train_time:693480ms step_avg:138.61ms
step:5014/5100 train_loss:3.2549 train_time:693617ms step_avg:138.61ms
step:5015/5100 train_loss:3.3537 train_time:693750ms step_avg:138.61ms
step:5016/5100 train_loss:3.3475 train_time:693890ms step_avg:138.61ms
step:5017/5100 train_loss:3.3743 train_time:694029ms step_avg:138.61ms
step:5018/5100 train_loss:3.4031 train_time:694167ms step_avg:138.61ms
step:5019/5100 train_loss:3.3517 train_time:694306ms step_avg:138.61ms
step:5020/5100 train_loss:3.8583 train_time:694444ms step_avg:138.61ms
step:5021/5100 train_loss:3.2994 train_time:694580ms step_avg:138.61ms
step:5022/5100 train_loss:3.3978 train_time:694714ms step_avg:138.61ms
step:5023/5100 train_loss:3.3243 train_time:694850ms step_avg:138.61ms
step:5024/5100 train_loss:3.4688 train_time:694988ms step_avg:138.61ms
step:5025/5100 train_loss:3.2680 train_time:695127ms step_avg:138.61ms
step:5026/5100 train_loss:3.4229 train_time:695264ms step_avg:138.61ms
step:5027/5100 train_loss:3.2769 train_time:695402ms step_avg:138.61ms
step:5028/5100 train_loss:3.4952 train_time:695540ms step_avg:138.61ms
step:5029/5100 train_loss:3.3904 train_time:695678ms step_avg:138.61ms
step:5030/5100 train_loss:3.4256 train_time:695813ms step_avg:138.61ms
step:5031/5100 train_loss:3.2871 train_time:695950ms step_avg:138.61ms
step:5032/5100 train_loss:3.3240 train_time:696088ms step_avg:138.61ms
step:5033/5100 train_loss:3.2651 train_time:696227ms step_avg:138.61ms
step:5034/5100 train_loss:3.4516 train_time:696365ms step_avg:138.61ms
step:5035/5100 train_loss:3.4429 train_time:696503ms step_avg:138.61ms
step:5036/5100 train_loss:3.2974 train_time:696642ms step_avg:138.61ms
step:5037/5100 train_loss:3.2278 train_time:696779ms step_avg:138.61ms
step:5038/5100 train_loss:3.2655 train_time:696918ms step_avg:138.61ms
step:5039/5100 train_loss:3.4046 train_time:697054ms step_avg:138.61ms
step:5040/5100 train_loss:3.3274 train_time:697191ms step_avg:138.61ms
step:5041/5100 train_loss:3.5075 train_time:697329ms step_avg:138.61ms
step:5042/5100 train_loss:3.2996 train_time:697467ms step_avg:138.61ms
step:5043/5100 train_loss:3.4811 train_time:697604ms step_avg:138.61ms
step:5044/5100 train_loss:3.3927 train_time:697743ms step_avg:138.61ms
step:5045/5100 train_loss:3.4543 train_time:697880ms step_avg:138.61ms
step:5046/5100 train_loss:3.2806 train_time:698019ms step_avg:138.61ms
step:5047/5100 train_loss:3.4142 train_time:698157ms step_avg:138.61ms
step:5048/5100 train_loss:3.1677 train_time:698292ms step_avg:138.60ms
step:5049/5100 train_loss:3.3300 train_time:698429ms step_avg:138.60ms
step:5050/5100 train_loss:3.3356 train_time:698568ms step_avg:138.60ms
step:5051/5100 train_loss:3.2770 train_time:698705ms step_avg:138.60ms
step:5052/5100 train_loss:3.3091 train_time:698843ms step_avg:138.60ms
step:5053/5100 train_loss:3.3617 train_time:698981ms step_avg:138.60ms
step:5054/5100 train_loss:3.3969 train_time:699119ms step_avg:138.60ms
step:5055/5100 train_loss:3.4735 train_time:699257ms step_avg:138.60ms
step:5056/5100 train_loss:3.4170 train_time:699393ms step_avg:138.60ms
step:5057/5100 train_loss:3.3082 train_time:699530ms step_avg:138.60ms
step:5058/5100 train_loss:3.2015 train_time:699668ms step_avg:138.60ms
step:5059/5100 train_loss:3.1231 train_time:699809ms step_avg:138.60ms
step:5060/5100 train_loss:3.3433 train_time:699945ms step_avg:138.60ms
step:5061/5100 train_loss:3.4277 train_time:700087ms step_avg:138.60ms
step:5062/5100 train_loss:3.3478 train_time:700224ms step_avg:138.60ms
step:5063/5100 train_loss:3.4725 train_time:700359ms step_avg:138.60ms
step:5064/5100 train_loss:3.4796 train_time:700496ms step_avg:138.60ms
step:5065/5100 train_loss:3.3394 train_time:700633ms step_avg:138.60ms
step:5066/5100 train_loss:3.4482 train_time:700771ms step_avg:138.60ms
step:5067/5100 train_loss:3.6380 train_time:700908ms step_avg:138.60ms
step:5068/5100 train_loss:3.2947 train_time:701048ms step_avg:138.60ms
step:5069/5100 train_loss:3.6412 train_time:701187ms step_avg:138.60ms
step:5070/5100 train_loss:3.3449 train_time:701324ms step_avg:138.60ms
step:5071/5100 train_loss:3.7716 train_time:701460ms step_avg:138.60ms
step:5072/5100 train_loss:3.3016 train_time:701596ms step_avg:138.60ms
step:5073/5100 train_loss:3.3547 train_time:701732ms step_avg:138.60ms
step:5074/5100 train_loss:3.4936 train_time:701871ms step_avg:138.60ms
step:5075/5100 train_loss:3.3263 train_time:702009ms step_avg:138.60ms
step:5076/5100 train_loss:3.3194 train_time:702146ms step_avg:138.60ms
step:5077/5100 train_loss:3.2896 train_time:702283ms step_avg:138.60ms
step:5078/5100 train_loss:3.3680 train_time:702423ms step_avg:138.60ms
step:5079/5100 train_loss:3.5025 train_time:702560ms step_avg:138.60ms
step:5080/5100 train_loss:3.4759 train_time:702698ms step_avg:138.60ms
step:5081/5100 train_loss:3.2991 train_time:702835ms step_avg:138.60ms
step:5082/5100 train_loss:3.4261 train_time:702971ms step_avg:138.60ms
step:5083/5100 train_loss:3.2909 train_time:703109ms step_avg:138.60ms
step:5084/5100 train_loss:3.3638 train_time:703247ms step_avg:138.60ms
step:5085/5100 train_loss:3.2566 train_time:703385ms step_avg:138.60ms
step:5086/5100 train_loss:4.1139 train_time:703523ms step_avg:138.60ms
step:5087/5100 train_loss:3.3980 train_time:703660ms step_avg:138.60ms
step:5088/5100 train_loss:3.3094 train_time:703798ms step_avg:138.60ms
step:5089/5100 train_loss:3.3208 train_time:703936ms step_avg:138.60ms
step:5090/5100 train_loss:3.4533 train_time:704073ms step_avg:138.60ms
step:5091/5100 train_loss:3.3864 train_time:704209ms step_avg:138.60ms
step:5092/5100 train_loss:3.2753 train_time:704348ms step_avg:138.60ms
step:5093/5100 train_loss:3.2992 train_time:704486ms step_avg:138.60ms
step:5094/5100 train_loss:3.2945 train_time:704625ms step_avg:138.60ms
step:5095/5100 train_loss:3.2167 train_time:704765ms step_avg:138.60ms
step:5096/5100 train_loss:3.3497 train_time:704904ms step_avg:138.60ms
step:5097/5100 train_loss:3.1324 train_time:705040ms step_avg:138.60ms
step:5098/5100 train_loss:3.4321 train_time:705178ms step_avg:138.60ms
step:5099/5100 train_loss:3.2989 train_time:705314ms step_avg:138.60ms
step:5100/5100 train_loss:3.3302 train_time:705452ms step_avg:138.60ms
step:5100/5100 val_loss:3.3406 train_time:705525ms step_avg:138.61ms