==================================================================================================== 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() / (G.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.to(G.dtype) 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): defaults = dict(lr=lr, momentum=momentum, nesterov=nesterov, backend=backend, backend_steps=backend_steps) super().__init__(params, defaults) def step(self): for group in self.param_groups: lr = group['lr'] momentum = group['momentum'] zeropower_backend = zeropower_backends[group['backend']] for p in group['params']: 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) if g.size(0) == 3 * g.size(1): # split grouped QKV parameters g = torch.cat([zeropower_backend(g1, steps=group['backend_steps']) for g1 in g.split(g.size(1))]) scale = g.size(1)**0.5 else: g = zeropower_backend(g, steps=group['backend_steps']) scale = max(g.size(0), g.size(1))**0.5 # scale to have update.square().mean() == 1 p.data.add_(g, alpha=-lr * scale) # ----------------------------------------------------------------------------- # PyTorch nn.Module definitions for the GPT-2 model class Rotary(torch.nn.Module): def __init__(self, dim, base=10000): super().__init__() inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / dim)) self.register_buffer("inv_freq", inv_freq) 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() self.sin_cached = freqs.sin() 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) def rmsnorm(x0, eps=1e-6): x = x0.float() x = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps) return x.type_as(x0) 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 # key, query, value projections for all heads, but in a batch self.c_attn = nn.Linear(self.n_embd, 3 * self.n_embd, bias=False) # output projection self.c_proj = nn.Linear(self.n_embd, self.n_embd, bias=False) self.rotary = Rotary(self.head_dim) def forward(self, x): B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd) # calculate query, key, values for all heads in batch and move head forward to be the batch dim qkv = self.c_attn(x) q, k, v = qkv.split(self.n_embd, dim=2) k = k.view(B, T, self.n_head, self.head_dim) q = q.view(B, T, self.n_head, self.head_dim) v = v.view(B, T, self.n_head, self.head_dim) cos, sin = self.rotary(q) q = apply_rotary_emb(q, cos, sin) k = 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(B, T, C) # re-assemble all head outputs side by side # output projection 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) def forward(self, x): x = self.c_fc(x) x = F.gelu(x) 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) self.attn_scale = (1 / (2 * config.n_layer)**0.5) def forward(self, x): x = x + self.attn_scale * self.attn(rmsnorm(x)) x = x + self.mlp(rmsnorm(x)) return x # ----------------------------------------------------------------------------- # The main GPT-2 model @dataclass class GPTConfig: vocab_size : int = 50257 n_layer : int = 12 n_head : int = 12 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): b, t = idx.size() pos = torch.arange(0, t, dtype=torch.long, device=idx.device) # shape (t) # 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 = rmsnorm(x) 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 = 6200 # number of iterations to run learning_rate : float = 0.0036 warmup_iters : int = 0 warmdown_iters : int = 1800 # 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() # init the model from scratch num_vocab = 50257 model = GPT(GPTConfig(vocab_size=num_vocab, n_layer=12, n_head=12, n_embd=768)) model = model.cuda() if hasattr(config, "coordinate_descent_tuning"): config.coordinate_descent_tuning = True # suggested by @Chillee model = torch.compile(model) # here we wrap model into DDP container model = DDP(model, device_ids=[ddp_local_rank]) raw_model = model.module # always contains the "raw" unwrapped model ctx = torch.amp.autocast(device_type='cuda', dtype=torch.bfloat16) # init the optimizer(s) optimizer1 = torch.optim.AdamW(raw_model.lm_head.parameters(), lr=args.learning_rate, betas=(0.9, 0.95), weight_decay=args.weight_decay, fused=True) optimizer2 = Muon(raw_model.transformer.h.parameters(), lr=0.1*args.learning_rate, momentum=0.95) 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 torch.no_grad(): # of course, we'd like to use ctx here too, but that creates a torch.compile error for some reason _, loss = model(x_val, y_val, return_logits=False) val_loss += 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 2.4.1+cu121 compiled for CUDA 12.1 nvidia-smi: Thu Oct 10 23:58:24 2024 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.129.03 Driver Version: 535.129.03 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA H100 80GB HBM3 On | 00000000:61:00.0 Off | 0 | | N/A 33C P0 111W / 700W | 5789MiB / 81559MiB | 5% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 1 NVIDIA H100 80GB HBM3 On | 00000000:62:00.0 Off | 0 | | N/A 30C P0 112W / 700W | 5837MiB / 81559MiB | 1% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 2 NVIDIA H100 80GB HBM3 On | 00000000:63:00.0 Off | 0 | | N/A 29C P0 116W / 700W | 5837MiB / 81559MiB | 6% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 3 NVIDIA H100 80GB HBM3 On | 00000000:64:00.0 Off | 0 | | N/A 32C P0 119W / 700W | 5837MiB / 81559MiB | 2% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 4 NVIDIA H100 80GB HBM3 On | 00000000:6A:00.0 Off | 0 | | N/A 35C P0 115W / 700W | 5837MiB / 81559MiB | 4% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 5 NVIDIA H100 80GB HBM3 On | 00000000:6B:00.0 Off | 0 | | N/A 31C P0 115W / 700W | 5837MiB / 81559MiB | 3% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 6 NVIDIA H100 80GB HBM3 On | 00000000:6C:00.0 Off | 0 | | N/A 33C P0 117W / 700W | 5837MiB / 81559MiB | 3% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 7 NVIDIA H100 80GB HBM3 On | 00000000:6D:00.0 Off | 0 | | N/A 29C P0 113W / 700W | 5597MiB / 81559MiB | 5% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 6718 C /usr/bin/python3 5776MiB | | 1 N/A N/A 6719 C /usr/bin/python3 5824MiB | | 2 N/A N/A 6720 C /usr/bin/python3 5824MiB | | 3 N/A N/A 6721 C /usr/bin/python3 5824MiB | | 4 N/A N/A 6722 C /usr/bin/python3 5824MiB | | 5 N/A N/A 6723 C /usr/bin/python3 5824MiB | | 6 N/A N/A 6724 C /usr/bin/python3 5824MiB | | 7 N/A N/A 6725 C /usr/bin/python3 5584MiB | +---------------------------------------------------------------------------------------+ ==================================================================================================== step:0/6200 val_loss:10.9264 train_time:285ms step_avg:nanms step:1/6200 train_loss:10.9184 train_time:74701ms step_avg:nanms step:2/6200 train_loss:8.6834 train_time:75965ms step_avg:nanms step:3/6200 train_loss:7.7596 train_time:76178ms step_avg:nanms step:4/6200 train_loss:7.5281 train_time:76393ms step_avg:nanms step:5/6200 train_loss:7.2838 train_time:76607ms step_avg:nanms step:6/6200 train_loss:7.4058 train_time:76822ms step_avg:nanms step:7/6200 train_loss:7.1525 train_time:77034ms step_avg:nanms step:8/6200 train_loss:7.2096 train_time:77248ms step_avg:nanms step:9/6200 train_loss:6.9016 train_time:77462ms step_avg:nanms step:10/6200 train_loss:6.7231 train_time:77676ms step_avg:nanms step:11/6200 train_loss:6.6933 train_time:214ms step_avg:nanms step:12/6200 train_loss:6.6519 train_time:428ms step_avg:nanms step:13/6200 train_loss:6.5125 train_time:641ms step_avg:213.66ms step:14/6200 train_loss:6.4803 train_time:854ms step_avg:213.44ms step:15/6200 train_loss:6.4443 train_time:1067ms step_avg:213.35ms step:16/6200 train_loss:6.3833 train_time:1280ms step_avg:213.27ms step:17/6200 train_loss:6.3940 train_time:1494ms step_avg:213.38ms step:18/6200 train_loss:6.4317 train_time:1706ms step_avg:213.31ms step:19/6200 train_loss:6.2612 train_time:1920ms step_avg:213.34ms step:20/6200 train_loss:6.2872 train_time:2134ms step_avg:213.39ms step:21/6200 train_loss:5.9681 train_time:2348ms step_avg:213.42ms step:22/6200 train_loss:6.3227 train_time:2559ms step_avg:213.28ms step:23/6200 train_loss:6.5254 train_time:2771ms step_avg:213.18ms step:24/6200 train_loss:6.2246 train_time:2984ms step_avg:213.17ms step:25/6200 train_loss:6.3684 train_time:3197ms step_avg:213.12ms step:26/6200 train_loss:6.0852 train_time:3417ms step_avg:213.54ms step:27/6200 train_loss:5.9964 train_time:3631ms step_avg:213.58ms step:28/6200 train_loss:6.1392 train_time:3843ms step_avg:213.52ms step:29/6200 train_loss:5.8375 train_time:4055ms step_avg:213.43ms step:30/6200 train_loss:6.1211 train_time:4268ms step_avg:213.40ms step:31/6200 train_loss:5.9554 train_time:4481ms step_avg:213.38ms step:32/6200 train_loss:5.9318 train_time:4695ms step_avg:213.40ms step:33/6200 train_loss:5.7680 train_time:4909ms step_avg:213.43ms step:34/6200 train_loss:6.0188 train_time:5122ms step_avg:213.41ms step:35/6200 train_loss:5.9832 train_time:5336ms step_avg:213.43ms step:36/6200 train_loss:6.1210 train_time:5548ms step_avg:213.40ms step:37/6200 train_loss:6.0830 train_time:5760ms step_avg:213.35ms step:38/6200 train_loss:5.9960 train_time:5974ms step_avg:213.35ms step:39/6200 train_loss:5.8868 train_time:6187ms step_avg:213.35ms step:40/6200 train_loss:5.9095 train_time:6399ms step_avg:213.31ms step:41/6200 train_loss:5.8334 train_time:6614ms step_avg:213.35ms step:42/6200 train_loss:5.8682 train_time:6827ms step_avg:213.34ms step:43/6200 train_loss:5.7484 train_time:7039ms step_avg:213.30ms step:44/6200 train_loss:5.8581 train_time:7252ms step_avg:213.29ms step:45/6200 train_loss:5.8271 train_time:7464ms step_avg:213.26ms step:46/6200 train_loss:5.9973 train_time:7677ms step_avg:213.26ms step:47/6200 train_loss:5.7899 train_time:7891ms step_avg:213.26ms step:48/6200 train_loss:5.6798 train_time:8103ms step_avg:213.24ms step:49/6200 train_loss:5.8951 train_time:8317ms step_avg:213.27ms step:50/6200 train_loss:5.7791 train_time:8532ms step_avg:213.31ms step:51/6200 train_loss:5.9207 train_time:8746ms step_avg:213.31ms step:52/6200 train_loss:5.8023 train_time:8957ms step_avg:213.27ms step:53/6200 train_loss:5.6707 train_time:9170ms step_avg:213.27ms step:54/6200 train_loss:5.7927 train_time:9383ms step_avg:213.24ms step:55/6200 train_loss:5.7075 train_time:9597ms step_avg:213.26ms step:56/6200 train_loss:6.0326 train_time:9810ms step_avg:213.26ms step:57/6200 train_loss:5.7168 train_time:10024ms step_avg:213.27ms step:58/6200 train_loss:5.5910 train_time:10237ms step_avg:213.27ms step:59/6200 train_loss:5.7355 train_time:10451ms step_avg:213.28ms step:60/6200 train_loss:5.7158 train_time:10665ms step_avg:213.30ms step:61/6200 train_loss:5.7815 train_time:10878ms step_avg:213.29ms step:62/6200 train_loss:5.6071 train_time:11091ms step_avg:213.29ms step:63/6200 train_loss:5.7061 train_time:11305ms step_avg:213.30ms step:64/6200 train_loss:5.6819 train_time:11519ms step_avg:213.32ms step:65/6200 train_loss:5.2590 train_time:11735ms step_avg:213.36ms step:66/6200 train_loss:5.5274 train_time:11948ms step_avg:213.35ms step:67/6200 train_loss:5.6988 train_time:12160ms step_avg:213.34ms step:68/6200 train_loss:5.5595 train_time:12374ms step_avg:213.34ms step:69/6200 train_loss:5.7931 train_time:12587ms step_avg:213.34ms step:70/6200 train_loss:5.4703 train_time:12799ms step_avg:213.32ms step:71/6200 train_loss:5.4531 train_time:13014ms step_avg:213.34ms step:72/6200 train_loss:5.7001 train_time:13228ms step_avg:213.36ms step:73/6200 train_loss:5.6453 train_time:13441ms step_avg:213.35ms step:74/6200 train_loss:5.5233 train_time:13654ms step_avg:213.34ms step:75/6200 train_loss:5.6561 train_time:13867ms step_avg:213.34ms step:76/6200 train_loss:5.5948 train_time:14080ms step_avg:213.33ms step:77/6200 train_loss:5.5993 train_time:14294ms step_avg:213.34ms step:78/6200 train_loss:5.6833 train_time:14508ms step_avg:213.36ms step:79/6200 train_loss:5.7076 train_time:14721ms step_avg:213.35ms step:80/6200 train_loss:5.5476 train_time:14935ms step_avg:213.36ms step:81/6200 train_loss:5.6539 train_time:15149ms step_avg:213.37ms step:82/6200 train_loss:5.4393 train_time:15362ms step_avg:213.36ms step:83/6200 train_loss:5.6025 train_time:15576ms step_avg:213.36ms step:84/6200 train_loss:5.5677 train_time:15790ms step_avg:213.37ms step:85/6200 train_loss:5.5537 train_time:16003ms step_avg:213.38ms step:86/6200 train_loss:5.4043 train_time:16217ms step_avg:213.39ms step:87/6200 train_loss:5.6360 train_time:16432ms step_avg:213.41ms step:88/6200 train_loss:5.5470 train_time:16646ms step_avg:213.41ms step:89/6200 train_loss:5.5636 train_time:16859ms step_avg:213.41ms step:90/6200 train_loss:5.5475 train_time:17072ms step_avg:213.40ms step:91/6200 train_loss:5.4898 train_time:17286ms step_avg:213.41ms step:92/6200 train_loss:5.4718 train_time:17500ms step_avg:213.41ms step:93/6200 train_loss:5.5898 train_time:17714ms step_avg:213.42ms step:94/6200 train_loss:5.4221 train_time:17930ms step_avg:213.45ms step:95/6200 train_loss:5.4295 train_time:18144ms step_avg:213.46ms step:96/6200 train_loss:5.4585 train_time:18356ms step_avg:213.45ms step:97/6200 train_loss:5.3823 train_time:18570ms step_avg:213.45ms step:98/6200 train_loss:5.4619 train_time:18784ms step_avg:213.45ms step:99/6200 train_loss:5.3740 train_time:18997ms step_avg:213.45ms step:100/6200 train_loss:5.4941 train_time:19212ms step_avg:213.47ms step:101/6200 train_loss:5.4627 train_time:19427ms step_avg:213.48ms step:102/6200 train_loss:5.3584 train_time:19639ms step_avg:213.47ms step:103/6200 train_loss:5.4707 train_time:19853ms step_avg:213.47ms step:104/6200 train_loss:5.3986 train_time:20066ms step_avg:213.47ms step:105/6200 train_loss:5.2556 train_time:20280ms step_avg:213.47ms step:106/6200 train_loss:5.3758 train_time:20495ms step_avg:213.49ms step:107/6200 train_loss:5.5572 train_time:20709ms step_avg:213.50ms step:108/6200 train_loss:5.3541 train_time:20923ms step_avg:213.50ms step:109/6200 train_loss:5.1235 train_time:21137ms step_avg:213.50ms step:110/6200 train_loss:5.3207 train_time:21351ms step_avg:213.51ms step:111/6200 train_loss:5.2965 train_time:21564ms step_avg:213.50ms step:112/6200 train_loss:5.2638 train_time:21778ms step_avg:213.51ms step:113/6200 train_loss:5.3656 train_time:21992ms step_avg:213.52ms step:114/6200 train_loss:5.2965 train_time:22207ms step_avg:213.53ms step:115/6200 train_loss:5.1582 train_time:22421ms step_avg:213.54ms step:116/6200 train_loss:5.3360 train_time:22636ms step_avg:213.55ms step:117/6200 train_loss:5.2026 train_time:22850ms step_avg:213.55ms step:118/6200 train_loss:5.1728 train_time:23063ms step_avg:213.55ms step:119/6200 train_loss:5.2965 train_time:23278ms step_avg:213.56ms step:120/6200 train_loss:5.2795 train_time:23494ms step_avg:213.58ms step:121/6200 train_loss:5.2036 train_time:23708ms step_avg:213.59ms step:122/6200 train_loss:5.1102 train_time:23921ms step_avg:213.58ms step:123/6200 train_loss:5.2210 train_time:24137ms step_avg:213.60ms step:124/6200 train_loss:5.0597 train_time:24349ms step_avg:213.59ms step:125/6200 train_loss:5.3717 train_time:24562ms step_avg:213.58ms step:125/6200 val_loss:5.2017 train_time:24564ms step_avg:213.60ms step:126/6200 train_loss:5.2399 train_time:24781ms step_avg:213.63ms step:127/6200 train_loss:5.1921 train_time:24997ms step_avg:213.65ms step:128/6200 train_loss:5.2629 train_time:25211ms step_avg:213.65ms step:129/6200 train_loss:5.1224 train_time:25425ms step_avg:213.65ms step:130/6200 train_loss:5.4064 train_time:25638ms step_avg:213.65ms step:131/6200 train_loss:5.1800 train_time:25852ms step_avg:213.65ms step:132/6200 train_loss:5.1772 train_time:26065ms step_avg:213.65ms step:133/6200 train_loss:5.1321 train_time:26280ms step_avg:213.66ms step:134/6200 train_loss:5.1733 train_time:26495ms step_avg:213.67ms step:135/6200 train_loss:5.0687 train_time:26709ms step_avg:213.68ms step:136/6200 train_loss:5.1770 train_time:26924ms step_avg:213.68ms step:137/6200 train_loss:4.9614 train_time:27138ms step_avg:213.69ms step:138/6200 train_loss:5.1265 train_time:27352ms step_avg:213.69ms step:139/6200 train_loss:5.0653 train_time:27568ms step_avg:213.70ms step:140/6200 train_loss:5.1074 train_time:27782ms step_avg:213.71ms step:141/6200 train_loss:5.1656 train_time:27998ms step_avg:213.72ms step:142/6200 train_loss:5.0510 train_time:28211ms step_avg:213.72ms step:143/6200 train_loss:5.1072 train_time:28425ms step_avg:213.72ms step:144/6200 train_loss:4.9479 train_time:28639ms step_avg:213.72ms step:145/6200 train_loss:5.1043 train_time:28853ms step_avg:213.73ms step:146/6200 train_loss:5.0387 train_time:29068ms step_avg:213.74ms step:147/6200 train_loss:4.9190 train_time:29283ms step_avg:213.75ms step:148/6200 train_loss:5.0692 train_time:29499ms step_avg:213.76ms step:149/6200 train_loss:5.0601 train_time:29714ms step_avg:213.77ms step:150/6200 train_loss:5.0808 train_time:29927ms step_avg:213.76ms step:151/6200 train_loss:5.1169 train_time:30140ms step_avg:213.76ms step:152/6200 train_loss:5.0243 train_time:30354ms step_avg:213.76ms step:153/6200 train_loss:5.0093 train_time:30568ms step_avg:213.76ms step:154/6200 train_loss:5.1044 train_time:30782ms step_avg:213.77ms step:155/6200 train_loss:5.0418 train_time:30998ms step_avg:213.78ms step:156/6200 train_loss:5.0039 train_time:31211ms step_avg:213.77ms step:157/6200 train_loss:5.0335 train_time:31425ms step_avg:213.77ms step:158/6200 train_loss:5.1590 train_time:31638ms step_avg:213.77ms step:159/6200 train_loss:4.9323 train_time:31851ms step_avg:213.77ms step:160/6200 train_loss:4.9939 train_time:32065ms step_avg:213.77ms step:161/6200 train_loss:4.8373 train_time:32281ms step_avg:213.78ms step:162/6200 train_loss:5.0129 train_time:32495ms step_avg:213.78ms step:163/6200 train_loss:5.0512 train_time:32708ms step_avg:213.78ms step:164/6200 train_loss:5.0302 train_time:32921ms step_avg:213.77ms step:165/6200 train_loss:4.8465 train_time:33135ms step_avg:213.77ms step:166/6200 train_loss:4.9743 train_time:33349ms step_avg:213.78ms step:167/6200 train_loss:5.1055 train_time:33564ms step_avg:213.78ms step:168/6200 train_loss:4.8925 train_time:33779ms step_avg:213.79ms step:169/6200 train_loss:4.9942 train_time:33996ms step_avg:213.81ms step:170/6200 train_loss:4.8351 train_time:34209ms step_avg:213.81ms step:171/6200 train_loss:4.7438 train_time:34422ms step_avg:213.80ms step:172/6200 train_loss:4.8904 train_time:34637ms step_avg:213.81ms step:173/6200 train_loss:4.8800 train_time:34850ms step_avg:213.81ms step:174/6200 train_loss:4.9316 train_time:35065ms step_avg:213.81ms step:175/6200 train_loss:5.0703 train_time:35280ms step_avg:213.82ms step:176/6200 train_loss:4.9360 train_time:35493ms step_avg:213.82ms step:177/6200 train_loss:4.7875 train_time:35707ms step_avg:213.82ms step:178/6200 train_loss:4.7673 train_time:35921ms step_avg:213.81ms step:179/6200 train_loss:4.8106 train_time:36134ms step_avg:213.81ms step:180/6200 train_loss:4.8333 train_time:36349ms step_avg:213.81ms step:181/6200 train_loss:4.8279 train_time:36564ms step_avg:213.82ms step:182/6200 train_loss:4.9477 train_time:36779ms step_avg:213.83ms step:183/6200 train_loss:4.8408 train_time:36993ms step_avg:213.83ms step:184/6200 train_loss:4.7580 train_time:37207ms step_avg:213.84ms step:185/6200 train_loss:4.7972 train_time:37421ms step_avg:213.83ms step:186/6200 train_loss:4.9072 train_time:37634ms step_avg:213.83ms step:187/6200 train_loss:4.8109 train_time:37849ms step_avg:213.83ms step:188/6200 train_loss:5.0394 train_time:38065ms step_avg:213.85ms step:189/6200 train_loss:4.8372 train_time:38526ms step_avg:215.23ms step:190/6200 train_loss:4.7508 train_time:38989ms step_avg:216.61ms step:191/6200 train_loss:4.9076 train_time:39205ms step_avg:216.60ms step:192/6200 train_loss:4.7564 train_time:39419ms step_avg:216.59ms step:193/6200 train_loss:4.6693 train_time:39634ms step_avg:216.58ms step:194/6200 train_loss:4.8827 train_time:39849ms step_avg:216.57ms step:195/6200 train_loss:4.8262 train_time:40063ms step_avg:216.56ms step:196/6200 train_loss:5.0026 train_time:40278ms step_avg:216.55ms step:197/6200 train_loss:4.8898 train_time:40493ms step_avg:216.54ms step:198/6200 train_loss:4.7291 train_time:40707ms step_avg:216.53ms step:199/6200 train_loss:4.7881 train_time:40921ms step_avg:216.51ms step:200/6200 train_loss:4.6653 train_time:41135ms step_avg:216.50ms step:201/6200 train_loss:4.7457 train_time:41349ms step_avg:216.49ms step:202/6200 train_loss:4.6478 train_time:41563ms step_avg:216.48ms step:203/6200 train_loss:4.9032 train_time:41779ms step_avg:216.47ms step:204/6200 train_loss:4.7975 train_time:41993ms step_avg:216.46ms step:205/6200 train_loss:4.7753 train_time:42207ms step_avg:216.45ms step:206/6200 train_loss:4.9187 train_time:42421ms step_avg:216.43ms step:207/6200 train_loss:4.5771 train_time:42634ms step_avg:216.42ms step:208/6200 train_loss:4.7399 train_time:42849ms step_avg:216.41ms step:209/6200 train_loss:4.6904 train_time:43064ms step_avg:216.40ms step:210/6200 train_loss:4.8590 train_time:43279ms step_avg:216.39ms step:211/6200 train_loss:4.7850 train_time:43493ms step_avg:216.38ms step:212/6200 train_loss:4.6588 train_time:43707ms step_avg:216.37ms step:213/6200 train_loss:4.8168 train_time:43921ms step_avg:216.36ms step:214/6200 train_loss:4.6370 train_time:44134ms step_avg:216.34ms step:215/6200 train_loss:4.7172 train_time:44349ms step_avg:216.33ms step:216/6200 train_loss:4.5746 train_time:44563ms step_avg:216.33ms step:217/6200 train_loss:4.7150 train_time:44779ms step_avg:216.32ms step:218/6200 train_loss:4.6749 train_time:44994ms step_avg:216.32ms step:219/6200 train_loss:4.6666 train_time:45208ms step_avg:216.30ms step:220/6200 train_loss:4.6734 train_time:45420ms step_avg:216.29ms step:221/6200 train_loss:4.7200 train_time:45634ms step_avg:216.27ms step:222/6200 train_loss:4.7403 train_time:45849ms step_avg:216.27ms step:223/6200 train_loss:4.6556 train_time:46063ms step_avg:216.26ms step:224/6200 train_loss:4.6782 train_time:46278ms step_avg:216.25ms step:225/6200 train_loss:4.8179 train_time:46492ms step_avg:216.24ms step:226/6200 train_loss:4.5556 train_time:46706ms step_avg:216.23ms step:227/6200 train_loss:4.5680 train_time:46920ms step_avg:216.22ms step:228/6200 train_loss:4.5619 train_time:47134ms step_avg:216.21ms step:229/6200 train_loss:4.7298 train_time:47348ms step_avg:216.20ms step:230/6200 train_loss:4.5533 train_time:47563ms step_avg:216.20ms step:231/6200 train_loss:4.6905 train_time:47779ms step_avg:216.19ms step:232/6200 train_loss:4.5586 train_time:47992ms step_avg:216.18ms step:233/6200 train_loss:4.5362 train_time:48206ms step_avg:216.17ms step:234/6200 train_loss:4.7408 train_time:48421ms step_avg:216.16ms step:235/6200 train_loss:4.5758 train_time:48634ms step_avg:216.15ms step:236/6200 train_loss:4.5213 train_time:48848ms step_avg:216.14ms step:237/6200 train_loss:4.7476 train_time:49063ms step_avg:216.14ms step:238/6200 train_loss:4.6531 train_time:49277ms step_avg:216.13ms step:239/6200 train_loss:4.5491 train_time:49491ms step_avg:216.12ms step:240/6200 train_loss:4.7010 train_time:49705ms step_avg:216.11ms step:241/6200 train_loss:4.6761 train_time:49919ms step_avg:216.10ms step:242/6200 train_loss:4.5845 train_time:50133ms step_avg:216.09ms step:243/6200 train_loss:4.7437 train_time:50347ms step_avg:216.08ms step:244/6200 train_loss:4.5735 train_time:50562ms step_avg:216.08ms step:245/6200 train_loss:4.6053 train_time:50777ms step_avg:216.07ms step:246/6200 train_loss:4.6616 train_time:50991ms step_avg:216.06ms step:247/6200 train_loss:4.6211 train_time:51205ms step_avg:216.06ms step:248/6200 train_loss:4.5680 train_time:51422ms step_avg:216.06ms step:249/6200 train_loss:4.7262 train_time:51634ms step_avg:216.04ms step:250/6200 train_loss:4.4653 train_time:51849ms step_avg:216.04ms step:250/6200 val_loss:4.5819 train_time:51851ms step_avg:216.04ms step:251/6200 train_loss:4.5217 train_time:52066ms step_avg:216.04ms step:252/6200 train_loss:4.6475 train_time:52279ms step_avg:216.03ms step:253/6200 train_loss:4.6471 train_time:52493ms step_avg:216.02ms step:254/6200 train_loss:4.5112 train_time:52707ms step_avg:216.01ms step:255/6200 train_loss:4.5158 train_time:52923ms step_avg:216.01ms step:256/6200 train_loss:4.6784 train_time:53139ms step_avg:216.01ms step:257/6200 train_loss:4.6019 train_time:53353ms step_avg:216.01ms step:258/6200 train_loss:4.5689 train_time:53567ms step_avg:216.00ms step:259/6200 train_loss:4.5131 train_time:53781ms step_avg:215.99ms step:260/6200 train_loss:4.5425 train_time:53997ms step_avg:215.99ms step:261/6200 train_loss:4.6066 train_time:54211ms step_avg:215.98ms step:262/6200 train_loss:4.5973 train_time:54424ms step_avg:215.97ms step:263/6200 train_loss:4.5266 train_time:54640ms step_avg:215.97ms step:264/6200 train_loss:4.4474 train_time:54855ms step_avg:215.97ms step:265/6200 train_loss:4.5160 train_time:55069ms step_avg:215.96ms step:266/6200 train_loss:4.3566 train_time:55283ms step_avg:215.95ms step:267/6200 train_loss:4.4277 train_time:55497ms step_avg:215.94ms step:268/6200 train_loss:4.4618 train_time:55713ms step_avg:215.94ms step:269/6200 train_loss:4.4411 train_time:55928ms step_avg:215.94ms step:270/6200 train_loss:4.3782 train_time:56143ms step_avg:215.93ms step:271/6200 train_loss:4.6304 train_time:56358ms step_avg:215.93ms step:272/6200 train_loss:4.5307 train_time:56571ms step_avg:215.92ms step:273/6200 train_loss:4.4100 train_time:56785ms step_avg:215.91ms step:274/6200 train_loss:4.4493 train_time:57000ms step_avg:215.91ms step:275/6200 train_loss:4.5645 train_time:57215ms step_avg:215.91ms step:276/6200 train_loss:4.5687 train_time:57429ms step_avg:215.90ms step:277/6200 train_loss:4.7986 train_time:57643ms step_avg:215.89ms step:278/6200 train_loss:4.5276 train_time:57861ms step_avg:215.90ms step:279/6200 train_loss:4.6538 train_time:58075ms step_avg:215.89ms step:280/6200 train_loss:4.5040 train_time:58288ms step_avg:215.88ms step:281/6200 train_loss:4.5974 train_time:58503ms step_avg:215.88ms step:282/6200 train_loss:4.4633 train_time:58718ms step_avg:215.87ms step:283/6200 train_loss:4.5411 train_time:58932ms step_avg:215.87ms step:284/6200 train_loss:4.3905 train_time:59147ms step_avg:215.86ms step:285/6200 train_loss:4.5661 train_time:59361ms step_avg:215.86ms step:286/6200 train_loss:4.5567 train_time:59576ms step_avg:215.86ms step:287/6200 train_loss:4.5842 train_time:59789ms step_avg:215.84ms step:288/6200 train_loss:4.4474 train_time:60003ms step_avg:215.84ms step:289/6200 train_loss:4.5033 train_time:60218ms step_avg:215.84ms step:290/6200 train_loss:4.3760 train_time:60436ms step_avg:215.84ms step:291/6200 train_loss:4.3604 train_time:60650ms step_avg:215.84ms step:292/6200 train_loss:4.4704 train_time:60865ms step_avg:215.83ms step:293/6200 train_loss:4.3692 train_time:61078ms step_avg:215.82ms step:294/6200 train_loss:4.4265 train_time:61292ms step_avg:215.82ms step:295/6200 train_loss:4.4373 train_time:61506ms step_avg:215.81ms step:296/6200 train_loss:4.3125 train_time:61720ms step_avg:215.81ms step:297/6200 train_loss:4.2993 train_time:61935ms step_avg:215.80ms step:298/6200 train_loss:4.3241 train_time:62150ms step_avg:215.80ms step:299/6200 train_loss:4.4313 train_time:62364ms step_avg:215.79ms step:300/6200 train_loss:4.3087 train_time:62578ms step_avg:215.79ms step:301/6200 train_loss:4.4787 train_time:62791ms step_avg:215.78ms step:302/6200 train_loss:4.4615 train_time:63007ms step_avg:215.78ms step:303/6200 train_loss:4.3868 train_time:63222ms step_avg:215.77ms step:304/6200 train_loss:4.4663 train_time:63437ms step_avg:215.77ms step:305/6200 train_loss:4.4402 train_time:63650ms step_avg:215.76ms step:306/6200 train_loss:4.9214 train_time:63864ms step_avg:215.76ms step:307/6200 train_loss:4.3958 train_time:64078ms step_avg:215.75ms step:308/6200 train_loss:4.2926 train_time:64292ms step_avg:215.74ms step:309/6200 train_loss:4.4803 train_time:64506ms step_avg:215.74ms step:310/6200 train_loss:4.2876 train_time:64720ms step_avg:215.73ms step:311/6200 train_loss:4.5223 train_time:64935ms step_avg:215.73ms step:312/6200 train_loss:4.4093 train_time:65150ms step_avg:215.73ms step:313/6200 train_loss:4.3311 train_time:65364ms step_avg:215.72ms step:314/6200 train_loss:4.4214 train_time:65579ms step_avg:215.72ms step:315/6200 train_loss:4.5724 train_time:65792ms step_avg:215.71ms step:316/6200 train_loss:4.4249 train_time:66006ms step_avg:215.71ms step:317/6200 train_loss:4.2896 train_time:66220ms step_avg:215.70ms step:318/6200 train_loss:4.3191 train_time:66435ms step_avg:215.70ms step:319/6200 train_loss:4.3480 train_time:66650ms step_avg:215.70ms step:320/6200 train_loss:4.3070 train_time:66865ms step_avg:215.69ms step:321/6200 train_loss:4.3968 train_time:67079ms step_avg:215.69ms step:322/6200 train_loss:4.3938 train_time:67292ms step_avg:215.68ms step:323/6200 train_loss:4.3494 train_time:67506ms step_avg:215.67ms step:324/6200 train_loss:4.4331 train_time:67720ms step_avg:215.67ms step:325/6200 train_loss:4.4043 train_time:67941ms step_avg:215.68ms step:326/6200 train_loss:4.4620 train_time:68156ms step_avg:215.68ms step:327/6200 train_loss:4.3255 train_time:68371ms step_avg:215.68ms step:328/6200 train_loss:4.8162 train_time:68584ms step_avg:215.67ms step:329/6200 train_loss:4.4895 train_time:68798ms step_avg:215.67ms step:330/6200 train_loss:4.2489 train_time:69011ms step_avg:215.66ms step:331/6200 train_loss:4.2061 train_time:69225ms step_avg:215.65ms step:332/6200 train_loss:4.3983 train_time:69440ms step_avg:215.65ms step:333/6200 train_loss:4.3157 train_time:69655ms step_avg:215.65ms step:334/6200 train_loss:4.2998 train_time:69868ms step_avg:215.64ms step:335/6200 train_loss:4.2619 train_time:70082ms step_avg:215.64ms step:336/6200 train_loss:4.4407 train_time:70298ms step_avg:215.64ms step:337/6200 train_loss:4.3790 train_time:70512ms step_avg:215.63ms step:338/6200 train_loss:4.9143 train_time:70727ms step_avg:215.63ms step:339/6200 train_loss:4.3475 train_time:70941ms step_avg:215.63ms step:340/6200 train_loss:4.3131 train_time:71157ms step_avg:215.63ms step:341/6200 train_loss:4.3150 train_time:71371ms step_avg:215.62ms step:342/6200 train_loss:4.2503 train_time:71585ms step_avg:215.62ms step:343/6200 train_loss:4.2176 train_time:71799ms step_avg:215.61ms step:344/6200 train_loss:4.2804 train_time:72013ms step_avg:215.61ms step:345/6200 train_loss:4.3851 train_time:72227ms step_avg:215.60ms step:346/6200 train_loss:4.2452 train_time:72442ms step_avg:215.60ms step:347/6200 train_loss:4.1847 train_time:72657ms step_avg:215.60ms step:348/6200 train_loss:4.2397 train_time:72870ms step_avg:215.59ms step:349/6200 train_loss:4.2508 train_time:73088ms step_avg:215.60ms step:350/6200 train_loss:4.1974 train_time:73302ms step_avg:215.60ms step:351/6200 train_loss:3.9017 train_time:73519ms step_avg:215.60ms step:352/6200 train_loss:4.1872 train_time:73734ms step_avg:215.60ms step:353/6200 train_loss:4.5296 train_time:73948ms step_avg:215.59ms step:354/6200 train_loss:4.0563 train_time:74161ms step_avg:215.59ms step:355/6200 train_loss:4.3017 train_time:74377ms step_avg:215.58ms step:356/6200 train_loss:4.1954 train_time:74590ms step_avg:215.58ms step:357/6200 train_loss:4.2777 train_time:74804ms step_avg:215.57ms step:358/6200 train_loss:4.2728 train_time:75020ms step_avg:215.58ms step:359/6200 train_loss:4.2246 train_time:75235ms step_avg:215.57ms step:360/6200 train_loss:4.4278 train_time:75449ms step_avg:215.57ms step:361/6200 train_loss:3.8887 train_time:75664ms step_avg:215.57ms step:362/6200 train_loss:4.4090 train_time:75877ms step_avg:215.56ms step:363/6200 train_loss:4.3100 train_time:76091ms step_avg:215.56ms step:364/6200 train_loss:4.2067 train_time:76307ms step_avg:215.56ms step:365/6200 train_loss:4.1359 train_time:76521ms step_avg:215.55ms step:366/6200 train_loss:4.2958 train_time:76736ms step_avg:215.55ms step:367/6200 train_loss:4.2354 train_time:76950ms step_avg:215.55ms step:368/6200 train_loss:4.2165 train_time:77164ms step_avg:215.54ms step:369/6200 train_loss:4.2089 train_time:77378ms step_avg:215.54ms step:370/6200 train_loss:4.1071 train_time:77592ms step_avg:215.53ms step:371/6200 train_loss:4.2455 train_time:77806ms step_avg:215.53ms step:372/6200 train_loss:4.1458 train_time:78021ms step_avg:215.53ms step:373/6200 train_loss:4.0545 train_time:78235ms step_avg:215.52ms step:374/6200 train_loss:4.2650 train_time:78449ms step_avg:215.52ms step:375/6200 train_loss:4.1909 train_time:78664ms step_avg:215.52ms step:375/6200 val_loss:4.1992 train_time:78666ms step_avg:215.52ms step:376/6200 train_loss:4.1725 train_time:78882ms step_avg:215.52ms step:377/6200 train_loss:4.2353 train_time:79097ms step_avg:215.52ms step:378/6200 train_loss:4.1450 train_time:79561ms step_avg:216.20ms step:379/6200 train_loss:4.2014 train_time:79775ms step_avg:216.19ms step:380/6200 train_loss:4.2431 train_time:80238ms step_avg:216.86ms step:381/6200 train_loss:4.2982 train_time:80452ms step_avg:216.85ms step:382/6200 train_loss:4.2087 train_time:80665ms step_avg:216.84ms step:383/6200 train_loss:4.1964 train_time:80879ms step_avg:216.83ms step:384/6200 train_loss:4.1321 train_time:81094ms step_avg:216.83ms step:385/6200 train_loss:4.2195 train_time:81309ms step_avg:216.82ms step:386/6200 train_loss:4.1309 train_time:81523ms step_avg:216.82ms step:387/6200 train_loss:4.2607 train_time:81737ms step_avg:216.81ms step:388/6200 train_loss:4.4492 train_time:81951ms step_avg:216.80ms step:389/6200 train_loss:4.1444 train_time:82165ms step_avg:216.80ms step:390/6200 train_loss:4.1330 train_time:82379ms step_avg:216.79ms step:391/6200 train_loss:4.2370 train_time:82594ms step_avg:216.78ms step:392/6200 train_loss:4.1600 train_time:82809ms step_avg:216.78ms step:393/6200 train_loss:4.2674 train_time:83023ms step_avg:216.77ms step:394/6200 train_loss:4.0897 train_time:83236ms step_avg:216.76ms step:395/6200 train_loss:4.2283 train_time:83451ms step_avg:216.76ms step:396/6200 train_loss:3.9827 train_time:83665ms step_avg:216.75ms step:397/6200 train_loss:4.1742 train_time:83878ms step_avg:216.74ms step:398/6200 train_loss:4.2463 train_time:84093ms step_avg:216.73ms step:399/6200 train_loss:4.2290 train_time:84307ms step_avg:216.73ms step:400/6200 train_loss:4.1227 train_time:84521ms step_avg:216.72ms step:401/6200 train_loss:4.2022 train_time:84735ms step_avg:216.71ms step:402/6200 train_loss:4.2377 train_time:84949ms step_avg:216.71ms step:403/6200 train_loss:4.1906 train_time:85163ms step_avg:216.70ms step:404/6200 train_loss:4.2942 train_time:85378ms step_avg:216.70ms step:405/6200 train_loss:4.0573 train_time:85593ms step_avg:216.69ms step:406/6200 train_loss:4.1292 train_time:85808ms step_avg:216.69ms step:407/6200 train_loss:4.4128 train_time:86021ms step_avg:216.68ms step:408/6200 train_loss:4.1440 train_time:86235ms step_avg:216.67ms step:409/6200 train_loss:4.1575 train_time:86449ms step_avg:216.66ms step:410/6200 train_loss:4.2027 train_time:86662ms step_avg:216.66ms step:411/6200 train_loss:4.0809 train_time:86877ms step_avg:216.65ms step:412/6200 train_loss:4.0959 train_time:87091ms step_avg:216.64ms step:413/6200 train_loss:4.5234 train_time:87305ms step_avg:216.64ms step:414/6200 train_loss:3.9885 train_time:87519ms step_avg:216.63ms step:415/6200 train_loss:4.3510 train_time:87733ms step_avg:216.62ms step:416/6200 train_loss:4.1004 train_time:87948ms step_avg:216.62ms step:417/6200 train_loss:4.0971 train_time:88163ms step_avg:216.62ms step:418/6200 train_loss:4.2987 train_time:88378ms step_avg:216.61ms step:419/6200 train_loss:4.0154 train_time:88593ms step_avg:216.61ms step:420/6200 train_loss:4.1256 train_time:88807ms step_avg:216.60ms step:421/6200 train_loss:4.0662 train_time:89022ms step_avg:216.60ms step:422/6200 train_loss:3.9722 train_time:89235ms step_avg:216.59ms step:423/6200 train_loss:4.1012 train_time:89449ms step_avg:216.58ms step:424/6200 train_loss:4.1979 train_time:89664ms step_avg:216.58ms step:425/6200 train_loss:3.9713 train_time:89878ms step_avg:216.57ms step:426/6200 train_loss:4.1453 train_time:90093ms step_avg:216.57ms step:427/6200 train_loss:4.0301 train_time:90308ms step_avg:216.57ms step:428/6200 train_loss:4.2315 train_time:90521ms step_avg:216.56ms step:429/6200 train_loss:4.1489 train_time:90735ms step_avg:216.55ms step:430/6200 train_loss:4.0774 train_time:90948ms step_avg:216.54ms step:431/6200 train_loss:4.0532 train_time:91163ms step_avg:216.54ms step:432/6200 train_loss:3.9690 train_time:91377ms step_avg:216.53ms step:433/6200 train_loss:4.0837 train_time:91592ms step_avg:216.53ms step:434/6200 train_loss:4.1571 train_time:91807ms step_avg:216.52ms step:435/6200 train_loss:4.0820 train_time:92021ms step_avg:216.52ms step:436/6200 train_loss:4.1441 train_time:92234ms step_avg:216.51ms step:437/6200 train_loss:4.1461 train_time:92448ms step_avg:216.51ms step:438/6200 train_loss:4.0248 train_time:92663ms step_avg:216.50ms step:439/6200 train_loss:4.0470 train_time:92877ms step_avg:216.50ms step:440/6200 train_loss:4.0294 train_time:93092ms step_avg:216.49ms step:441/6200 train_loss:4.2001 train_time:93306ms step_avg:216.49ms step:442/6200 train_loss:4.0905 train_time:93520ms step_avg:216.48ms step:443/6200 train_loss:4.0784 train_time:93734ms step_avg:216.48ms step:444/6200 train_loss:3.9654 train_time:93948ms step_avg:216.47ms step:445/6200 train_loss:4.2333 train_time:94162ms step_avg:216.46ms step:446/6200 train_loss:4.1600 train_time:94377ms step_avg:216.46ms step:447/6200 train_loss:4.1574 train_time:94592ms step_avg:216.46ms step:448/6200 train_loss:4.0626 train_time:94805ms step_avg:216.45ms step:449/6200 train_loss:4.1613 train_time:95019ms step_avg:216.44ms step:450/6200 train_loss:3.9835 train_time:95233ms step_avg:216.44ms step:451/6200 train_loss:4.0399 train_time:95446ms step_avg:216.43ms step:452/6200 train_loss:3.9061 train_time:95659ms step_avg:216.42ms step:453/6200 train_loss:4.0133 train_time:95874ms step_avg:216.42ms step:454/6200 train_loss:3.9962 train_time:96089ms step_avg:216.42ms step:455/6200 train_loss:3.9592 train_time:96304ms step_avg:216.41ms step:456/6200 train_loss:4.1724 train_time:96518ms step_avg:216.41ms step:457/6200 train_loss:4.0328 train_time:96732ms step_avg:216.40ms step:458/6200 train_loss:4.1135 train_time:96945ms step_avg:216.40ms step:459/6200 train_loss:4.1501 train_time:97159ms step_avg:216.39ms step:460/6200 train_loss:3.9546 train_time:97374ms step_avg:216.39ms step:461/6200 train_loss:4.1161 train_time:97589ms step_avg:216.38ms step:462/6200 train_loss:4.0146 train_time:97804ms step_avg:216.38ms step:463/6200 train_loss:4.0228 train_time:98019ms step_avg:216.38ms step:464/6200 train_loss:4.0999 train_time:98233ms step_avg:216.37ms step:465/6200 train_loss:4.0329 train_time:98446ms step_avg:216.37ms step:466/6200 train_loss:4.0322 train_time:98660ms step_avg:216.36ms step:467/6200 train_loss:4.1360 train_time:98875ms step_avg:216.36ms step:468/6200 train_loss:4.1465 train_time:99089ms step_avg:216.35ms step:469/6200 train_loss:4.1119 train_time:99303ms step_avg:216.35ms step:470/6200 train_loss:4.0086 train_time:99517ms step_avg:216.34ms step:471/6200 train_loss:4.0814 train_time:99731ms step_avg:216.34ms step:472/6200 train_loss:4.1511 train_time:99945ms step_avg:216.33ms step:473/6200 train_loss:4.0763 train_time:100158ms step_avg:216.32ms step:474/6200 train_loss:4.0342 train_time:100374ms step_avg:216.32ms step:475/6200 train_loss:3.8962 train_time:100588ms step_avg:216.32ms step:476/6200 train_loss:4.3323 train_time:100802ms step_avg:216.31ms step:477/6200 train_loss:4.0812 train_time:101017ms step_avg:216.31ms step:478/6200 train_loss:3.8937 train_time:101231ms step_avg:216.30ms step:479/6200 train_loss:4.1107 train_time:101443ms step_avg:216.30ms step:480/6200 train_loss:4.0815 train_time:101657ms step_avg:216.29ms step:481/6200 train_loss:4.2072 train_time:101871ms step_avg:216.29ms step:482/6200 train_loss:4.0263 train_time:102084ms step_avg:216.28ms step:483/6200 train_loss:3.8385 train_time:102298ms step_avg:216.27ms step:484/6200 train_loss:4.1152 train_time:102515ms step_avg:216.28ms step:485/6200 train_loss:3.9836 train_time:102729ms step_avg:216.27ms step:486/6200 train_loss:3.9856 train_time:102943ms step_avg:216.27ms step:487/6200 train_loss:3.9233 train_time:103156ms step_avg:216.26ms step:488/6200 train_loss:3.9695 train_time:103371ms step_avg:216.26ms step:489/6200 train_loss:4.1795 train_time:103585ms step_avg:216.25ms step:490/6200 train_loss:4.0222 train_time:103799ms step_avg:216.25ms step:491/6200 train_loss:3.9153 train_time:104015ms step_avg:216.25ms step:492/6200 train_loss:3.9259 train_time:104228ms step_avg:216.24ms step:493/6200 train_loss:4.0405 train_time:104441ms step_avg:216.23ms step:494/6200 train_loss:3.8827 train_time:104656ms step_avg:216.23ms step:495/6200 train_loss:4.0220 train_time:104870ms step_avg:216.23ms step:496/6200 train_loss:3.9564 train_time:105084ms step_avg:216.22ms step:497/6200 train_loss:3.8480 train_time:105299ms step_avg:216.22ms step:498/6200 train_loss:4.0302 train_time:105515ms step_avg:216.22ms step:499/6200 train_loss:4.1186 train_time:105729ms step_avg:216.21ms step:500/6200 train_loss:4.1511 train_time:105942ms step_avg:216.21ms step:500/6200 val_loss:4.0168 train_time:105944ms step_avg:216.21ms step:501/6200 train_loss:4.0462 train_time:106160ms step_avg:216.21ms step:502/6200 train_loss:4.1031 train_time:106374ms step_avg:216.21ms step:503/6200 train_loss:4.0447 train_time:106589ms step_avg:216.21ms step:504/6200 train_loss:4.0833 train_time:106803ms step_avg:216.20ms step:505/6200 train_loss:4.0358 train_time:107016ms step_avg:216.19ms step:506/6200 train_loss:4.1280 train_time:107231ms step_avg:216.19ms step:507/6200 train_loss:3.9313 train_time:107445ms step_avg:216.19ms step:508/6200 train_loss:4.0623 train_time:107659ms step_avg:216.18ms step:509/6200 train_loss:4.1428 train_time:107873ms step_avg:216.18ms step:510/6200 train_loss:4.0814 train_time:108089ms step_avg:216.18ms step:511/6200 train_loss:3.8876 train_time:108303ms step_avg:216.17ms step:512/6200 train_loss:4.0840 train_time:108516ms step_avg:216.17ms step:513/6200 train_loss:4.0207 train_time:108731ms step_avg:216.16ms step:514/6200 train_loss:3.9851 train_time:108945ms step_avg:216.16ms step:515/6200 train_loss:4.0677 train_time:109159ms step_avg:216.16ms step:516/6200 train_loss:4.0606 train_time:109373ms step_avg:216.15ms step:517/6200 train_loss:4.3965 train_time:109589ms step_avg:216.15ms step:518/6200 train_loss:3.9798 train_time:109803ms step_avg:216.15ms step:519/6200 train_loss:4.0925 train_time:110016ms step_avg:216.14ms step:520/6200 train_loss:4.0164 train_time:110231ms step_avg:216.14ms step:521/6200 train_loss:3.9892 train_time:110445ms step_avg:216.14ms step:522/6200 train_loss:3.9352 train_time:110659ms step_avg:216.13ms step:523/6200 train_loss:3.9503 train_time:110873ms step_avg:216.13ms step:524/6200 train_loss:4.5882 train_time:111090ms step_avg:216.13ms step:525/6200 train_loss:4.0525 train_time:111303ms step_avg:216.12ms step:526/6200 train_loss:3.9873 train_time:111517ms step_avg:216.12ms step:527/6200 train_loss:3.9910 train_time:111731ms step_avg:216.12ms step:528/6200 train_loss:3.9452 train_time:111946ms step_avg:216.11ms step:529/6200 train_loss:3.9202 train_time:112160ms step_avg:216.11ms step:530/6200 train_loss:4.1408 train_time:112375ms step_avg:216.11ms step:531/6200 train_loss:3.9389 train_time:112592ms step_avg:216.11ms step:532/6200 train_loss:4.2242 train_time:112807ms step_avg:216.11ms step:533/6200 train_loss:4.0303 train_time:113020ms step_avg:216.10ms step:534/6200 train_loss:3.9614 train_time:113234ms step_avg:216.10ms step:535/6200 train_loss:3.9811 train_time:113449ms step_avg:216.09ms step:536/6200 train_loss:3.9084 train_time:113664ms step_avg:216.09ms step:537/6200 train_loss:4.0337 train_time:113877ms step_avg:216.09ms step:538/6200 train_loss:4.0412 train_time:114092ms step_avg:216.08ms step:539/6200 train_loss:3.9277 train_time:114306ms step_avg:216.08ms step:540/6200 train_loss:4.4243 train_time:114520ms step_avg:216.07ms step:541/6200 train_loss:3.9712 train_time:114734ms step_avg:216.07ms step:542/6200 train_loss:4.0732 train_time:114948ms step_avg:216.07ms step:543/6200 train_loss:3.9062 train_time:115162ms step_avg:216.06ms step:544/6200 train_loss:3.8801 train_time:115376ms step_avg:216.06ms step:545/6200 train_loss:3.9779 train_time:115591ms step_avg:216.06ms step:546/6200 train_loss:3.8897 train_time:115805ms step_avg:216.05ms step:547/6200 train_loss:3.9444 train_time:116018ms step_avg:216.05ms step:548/6200 train_loss:3.9529 train_time:116232ms step_avg:216.05ms step:549/6200 train_loss:3.9305 train_time:116447ms step_avg:216.04ms step:550/6200 train_loss:4.0196 train_time:116661ms step_avg:216.04ms step:551/6200 train_loss:3.8901 train_time:116875ms step_avg:216.04ms step:552/6200 train_loss:3.9209 train_time:117090ms step_avg:216.03ms step:553/6200 train_loss:4.2495 train_time:117303ms step_avg:216.03ms step:554/6200 train_loss:4.0433 train_time:117517ms step_avg:216.02ms step:555/6200 train_loss:4.0047 train_time:117731ms step_avg:216.02ms step:556/6200 train_loss:3.9642 train_time:117945ms step_avg:216.02ms step:557/6200 train_loss:3.9785 train_time:118159ms step_avg:216.01ms step:558/6200 train_loss:3.6551 train_time:118373ms step_avg:216.01ms step:559/6200 train_loss:3.8991 train_time:118589ms step_avg:216.01ms step:560/6200 train_loss:3.9476 train_time:118802ms step_avg:216.00ms step:561/6200 train_loss:3.9936 train_time:119016ms step_avg:216.00ms step:562/6200 train_loss:3.8941 train_time:119230ms step_avg:216.00ms step:563/6200 train_loss:3.8435 train_time:119445ms step_avg:215.99ms step:564/6200 train_loss:4.0510 train_time:119659ms step_avg:215.99ms step:565/6200 train_loss:3.8542 train_time:119873ms step_avg:215.99ms step:566/6200 train_loss:3.9830 train_time:120090ms step_avg:215.99ms step:567/6200 train_loss:3.9201 train_time:120559ms step_avg:216.44ms step:568/6200 train_loss:3.8725 train_time:120773ms step_avg:216.44ms step:569/6200 train_loss:3.9711 train_time:120988ms step_avg:216.44ms step:570/6200 train_loss:3.9397 train_time:121451ms step_avg:216.88ms step:571/6200 train_loss:3.9697 train_time:121665ms step_avg:216.87ms step:572/6200 train_loss:4.0590 train_time:121878ms step_avg:216.87ms step:573/6200 train_loss:4.0045 train_time:122092ms step_avg:216.86ms step:574/6200 train_loss:4.0058 train_time:122306ms step_avg:216.85ms step:575/6200 train_loss:4.0692 train_time:122519ms step_avg:216.85ms step:576/6200 train_loss:4.0270 train_time:122732ms step_avg:216.84ms step:577/6200 train_loss:4.0371 train_time:122946ms step_avg:216.84ms step:578/6200 train_loss:3.9759 train_time:123159ms step_avg:216.83ms step:579/6200 train_loss:3.9600 train_time:123373ms step_avg:216.82ms step:580/6200 train_loss:3.9484 train_time:123588ms step_avg:216.82ms step:581/6200 train_loss:3.8893 train_time:123802ms step_avg:216.82ms step:582/6200 train_loss:3.9213 train_time:124015ms step_avg:216.81ms step:583/6200 train_loss:4.1508 train_time:124229ms step_avg:216.80ms step:584/6200 train_loss:3.9144 train_time:124442ms step_avg:216.80ms step:585/6200 train_loss:3.8749 train_time:124656ms step_avg:216.79ms step:586/6200 train_loss:4.0642 train_time:124870ms step_avg:216.79ms step:587/6200 train_loss:3.8247 train_time:125085ms step_avg:216.78ms step:588/6200 train_loss:3.9524 train_time:125299ms step_avg:216.78ms step:589/6200 train_loss:3.9421 train_time:125512ms step_avg:216.77ms step:590/6200 train_loss:4.2926 train_time:125727ms step_avg:216.77ms step:591/6200 train_loss:4.0707 train_time:125941ms step_avg:216.77ms step:592/6200 train_loss:3.8041 train_time:126155ms step_avg:216.76ms step:593/6200 train_loss:3.8152 train_time:126370ms step_avg:216.76ms step:594/6200 train_loss:3.8255 train_time:126585ms step_avg:216.75ms step:595/6200 train_loss:3.8540 train_time:126799ms step_avg:216.75ms step:596/6200 train_loss:4.2097 train_time:127013ms step_avg:216.75ms step:597/6200 train_loss:3.9393 train_time:127228ms step_avg:216.74ms step:598/6200 train_loss:3.8743 train_time:127441ms step_avg:216.74ms step:599/6200 train_loss:3.9438 train_time:127655ms step_avg:216.73ms step:600/6200 train_loss:3.7657 train_time:127870ms step_avg:216.73ms step:601/6200 train_loss:3.8838 train_time:128083ms step_avg:216.72ms step:602/6200 train_loss:3.9215 train_time:128298ms step_avg:216.72ms step:603/6200 train_loss:3.9415 train_time:128510ms step_avg:216.71ms step:604/6200 train_loss:4.0624 train_time:128725ms step_avg:216.71ms step:605/6200 train_loss:3.9293 train_time:128938ms step_avg:216.70ms step:606/6200 train_loss:3.8983 train_time:129152ms step_avg:216.70ms step:607/6200 train_loss:3.8390 train_time:129368ms step_avg:216.70ms step:608/6200 train_loss:4.0874 train_time:129583ms step_avg:216.69ms step:609/6200 train_loss:3.9277 train_time:129796ms step_avg:216.69ms step:610/6200 train_loss:3.9135 train_time:130009ms step_avg:216.68ms step:611/6200 train_loss:4.0077 train_time:130223ms step_avg:216.68ms step:612/6200 train_loss:3.9013 train_time:130437ms step_avg:216.67ms step:613/6200 train_loss:3.8846 train_time:130652ms step_avg:216.67ms step:614/6200 train_loss:4.0466 train_time:130866ms step_avg:216.67ms step:615/6200 train_loss:4.0174 train_time:131080ms step_avg:216.66ms step:616/6200 train_loss:3.9811 train_time:131293ms step_avg:216.66ms step:617/6200 train_loss:3.8947 train_time:131508ms step_avg:216.65ms step:618/6200 train_loss:3.8623 train_time:131719ms step_avg:216.64ms step:619/6200 train_loss:3.9571 train_time:131935ms step_avg:216.64ms step:620/6200 train_loss:3.8687 train_time:132150ms step_avg:216.64ms step:621/6200 train_loss:3.8747 train_time:132365ms step_avg:216.64ms step:622/6200 train_loss:4.1784 train_time:132578ms step_avg:216.63ms step:623/6200 train_loss:3.8739 train_time:132792ms step_avg:216.63ms step:624/6200 train_loss:3.9042 train_time:133007ms step_avg:216.62ms step:625/6200 train_loss:3.9749 train_time:133220ms step_avg:216.62ms step:625/6200 val_loss:3.9114 train_time:133222ms step_avg:216.62ms step:626/6200 train_loss:4.0071 train_time:133438ms step_avg:216.62ms step:627/6200 train_loss:4.0315 train_time:133652ms step_avg:216.62ms step:628/6200 train_loss:4.0073 train_time:133865ms step_avg:216.61ms step:629/6200 train_loss:4.0593 train_time:134080ms step_avg:216.61ms step:630/6200 train_loss:3.8731 train_time:134292ms step_avg:216.60ms step:631/6200 train_loss:4.0040 train_time:134506ms step_avg:216.60ms step:632/6200 train_loss:4.0396 train_time:134722ms step_avg:216.59ms step:633/6200 train_loss:3.9388 train_time:134937ms step_avg:216.59ms step:634/6200 train_loss:3.8601 train_time:135151ms step_avg:216.59ms step:635/6200 train_loss:3.9698 train_time:135365ms step_avg:216.58ms step:636/6200 train_loss:4.2192 train_time:135579ms step_avg:216.58ms step:637/6200 train_loss:3.8134 train_time:135793ms step_avg:216.58ms step:638/6200 train_loss:3.6360 train_time:136007ms step_avg:216.57ms step:639/6200 train_loss:3.8580 train_time:136222ms step_avg:216.57ms step:640/6200 train_loss:3.8934 train_time:136436ms step_avg:216.56ms step:641/6200 train_loss:3.8590 train_time:136650ms step_avg:216.56ms step:642/6200 train_loss:3.8570 train_time:136864ms step_avg:216.56ms step:643/6200 train_loss:3.8972 train_time:137078ms step_avg:216.55ms step:644/6200 train_loss:3.9178 train_time:137291ms step_avg:216.55ms step:645/6200 train_loss:3.8378 train_time:137504ms step_avg:216.54ms step:646/6200 train_loss:4.0593 train_time:137721ms step_avg:216.54ms step:647/6200 train_loss:3.9529 train_time:137935ms step_avg:216.54ms step:648/6200 train_loss:3.9523 train_time:138150ms step_avg:216.54ms step:649/6200 train_loss:3.9759 train_time:138364ms step_avg:216.53ms step:650/6200 train_loss:4.0415 train_time:138578ms step_avg:216.53ms step:651/6200 train_loss:3.8954 train_time:138790ms step_avg:216.52ms step:652/6200 train_loss:4.0385 train_time:139004ms step_avg:216.52ms step:653/6200 train_loss:3.8705 train_time:139218ms step_avg:216.51ms step:654/6200 train_loss:3.9359 train_time:139432ms step_avg:216.51ms step:655/6200 train_loss:3.7101 train_time:139646ms step_avg:216.50ms step:656/6200 train_loss:3.8539 train_time:139862ms step_avg:216.50ms step:657/6200 train_loss:3.8600 train_time:140075ms step_avg:216.50ms step:658/6200 train_loss:3.7974 train_time:140288ms step_avg:216.49ms step:659/6200 train_loss:3.9702 train_time:140502ms step_avg:216.49ms step:660/6200 train_loss:3.8731 train_time:140716ms step_avg:216.49ms step:661/6200 train_loss:3.9633 train_time:140930ms step_avg:216.48ms step:662/6200 train_loss:4.0355 train_time:141145ms step_avg:216.48ms step:663/6200 train_loss:3.9410 train_time:141360ms step_avg:216.48ms step:664/6200 train_loss:3.8221 train_time:141572ms step_avg:216.47ms step:665/6200 train_loss:3.9070 train_time:141785ms step_avg:216.47ms step:666/6200 train_loss:3.7774 train_time:141999ms step_avg:216.46ms step:667/6200 train_loss:4.0618 train_time:142213ms step_avg:216.46ms step:668/6200 train_loss:3.9060 train_time:142426ms step_avg:216.45ms step:669/6200 train_loss:3.9006 train_time:142641ms step_avg:216.45ms step:670/6200 train_loss:3.7609 train_time:142855ms step_avg:216.45ms step:671/6200 train_loss:3.8731 train_time:143069ms step_avg:216.44ms step:672/6200 train_loss:3.8299 train_time:143282ms step_avg:216.44ms step:673/6200 train_loss:3.8560 train_time:143495ms step_avg:216.43ms step:674/6200 train_loss:4.1232 train_time:143709ms step_avg:216.43ms step:675/6200 train_loss:3.9235 train_time:143923ms step_avg:216.42ms step:676/6200 train_loss:3.9958 train_time:144137ms step_avg:216.42ms step:677/6200 train_loss:3.7634 train_time:144351ms step_avg:216.42ms step:678/6200 train_loss:3.8677 train_time:144564ms step_avg:216.41ms step:679/6200 train_loss:3.8097 train_time:144778ms step_avg:216.41ms step:680/6200 train_loss:3.9593 train_time:144991ms step_avg:216.40ms step:681/6200 train_loss:3.8587 train_time:145204ms step_avg:216.40ms step:682/6200 train_loss:3.8897 train_time:145418ms step_avg:216.40ms step:683/6200 train_loss:3.9696 train_time:145631ms step_avg:216.39ms step:684/6200 train_loss:4.0141 train_time:145844ms step_avg:216.39ms step:685/6200 train_loss:3.9049 train_time:146060ms step_avg:216.38ms step:686/6200 train_loss:3.9787 train_time:146273ms step_avg:216.38ms step:687/6200 train_loss:3.9093 train_time:146487ms step_avg:216.38ms step:688/6200 train_loss:3.9509 train_time:146700ms step_avg:216.37ms step:689/6200 train_loss:3.6030 train_time:146914ms step_avg:216.37ms step:690/6200 train_loss:3.6968 train_time:147128ms step_avg:216.36ms step:691/6200 train_loss:3.8311 train_time:147342ms step_avg:216.36ms step:692/6200 train_loss:3.7138 train_time:147557ms step_avg:216.36ms step:693/6200 train_loss:3.9262 train_time:147771ms step_avg:216.36ms step:694/6200 train_loss:3.9397 train_time:147984ms step_avg:216.35ms step:695/6200 train_loss:3.8246 train_time:148198ms step_avg:216.35ms step:696/6200 train_loss:3.8044 train_time:148411ms step_avg:216.34ms step:697/6200 train_loss:4.1290 train_time:148625ms step_avg:216.34ms step:698/6200 train_loss:3.8782 train_time:148839ms step_avg:216.34ms step:699/6200 train_loss:3.9176 train_time:149053ms step_avg:216.33ms step:700/6200 train_loss:4.0927 train_time:149266ms step_avg:216.33ms step:701/6200 train_loss:3.8425 train_time:149481ms step_avg:216.33ms step:702/6200 train_loss:3.7977 train_time:149693ms step_avg:216.32ms step:703/6200 train_loss:3.7914 train_time:149908ms step_avg:216.32ms step:704/6200 train_loss:3.7506 train_time:150121ms step_avg:216.31ms step:705/6200 train_loss:3.8433 train_time:150335ms step_avg:216.31ms step:706/6200 train_loss:3.8326 train_time:150549ms step_avg:216.31ms step:707/6200 train_loss:3.8453 train_time:150764ms step_avg:216.30ms step:708/6200 train_loss:3.9205 train_time:150978ms step_avg:216.30ms step:709/6200 train_loss:3.8613 train_time:151191ms step_avg:216.30ms step:710/6200 train_loss:3.8495 train_time:151406ms step_avg:216.29ms step:711/6200 train_loss:3.8212 train_time:151620ms step_avg:216.29ms step:712/6200 train_loss:3.8639 train_time:151833ms step_avg:216.29ms step:713/6200 train_loss:3.9219 train_time:152046ms step_avg:216.28ms step:714/6200 train_loss:3.9318 train_time:152263ms step_avg:216.28ms step:715/6200 train_loss:3.8439 train_time:152477ms step_avg:216.28ms step:716/6200 train_loss:3.8485 train_time:152690ms step_avg:216.27ms step:717/6200 train_loss:3.8629 train_time:152904ms step_avg:216.27ms step:718/6200 train_loss:4.0083 train_time:153121ms step_avg:216.27ms step:719/6200 train_loss:3.8639 train_time:153335ms step_avg:216.27ms step:720/6200 train_loss:3.9357 train_time:153549ms step_avg:216.27ms step:721/6200 train_loss:4.0913 train_time:153763ms step_avg:216.26ms step:722/6200 train_loss:3.7315 train_time:153978ms step_avg:216.26ms step:723/6200 train_loss:3.9948 train_time:154191ms step_avg:216.26ms step:724/6200 train_loss:4.0487 train_time:154405ms step_avg:216.25ms step:725/6200 train_loss:3.8329 train_time:154620ms step_avg:216.25ms step:726/6200 train_loss:3.9121 train_time:154833ms step_avg:216.25ms step:727/6200 train_loss:3.8247 train_time:155048ms step_avg:216.25ms step:728/6200 train_loss:3.8257 train_time:155262ms step_avg:216.24ms step:729/6200 train_loss:4.0047 train_time:155476ms step_avg:216.24ms step:730/6200 train_loss:3.9609 train_time:155689ms step_avg:216.23ms step:731/6200 train_loss:3.9614 train_time:155903ms step_avg:216.23ms step:732/6200 train_loss:3.8335 train_time:156117ms step_avg:216.23ms step:733/6200 train_loss:3.8563 train_time:156331ms step_avg:216.22ms step:734/6200 train_loss:4.0984 train_time:156545ms step_avg:216.22ms step:735/6200 train_loss:3.8351 train_time:156763ms step_avg:216.22ms step:736/6200 train_loss:3.8986 train_time:156977ms step_avg:216.22ms step:737/6200 train_loss:4.0157 train_time:157190ms step_avg:216.22ms step:738/6200 train_loss:3.9286 train_time:157404ms step_avg:216.21ms step:739/6200 train_loss:3.8731 train_time:157619ms step_avg:216.21ms step:740/6200 train_loss:3.7691 train_time:157832ms step_avg:216.21ms step:741/6200 train_loss:4.4143 train_time:158046ms step_avg:216.20ms step:742/6200 train_loss:3.7657 train_time:158262ms step_avg:216.21ms step:743/6200 train_loss:3.8540 train_time:158475ms step_avg:216.20ms step:744/6200 train_loss:3.8521 train_time:158689ms step_avg:216.20ms step:745/6200 train_loss:3.9088 train_time:158903ms step_avg:216.19ms step:746/6200 train_loss:3.8914 train_time:159116ms step_avg:216.19ms step:747/6200 train_loss:3.8693 train_time:159329ms step_avg:216.19ms step:748/6200 train_loss:3.8962 train_time:159544ms step_avg:216.18ms step:749/6200 train_loss:3.8300 train_time:159761ms step_avg:216.19ms step:750/6200 train_loss:3.8368 train_time:159977ms step_avg:216.19ms step:750/6200 val_loss:3.8448 train_time:159979ms step_avg:216.19ms step:751/6200 train_loss:3.8650 train_time:160198ms step_avg:216.19ms step:752/6200 train_loss:3.8342 train_time:160412ms step_avg:216.19ms step:753/6200 train_loss:3.8711 train_time:160632ms step_avg:216.19ms step:754/6200 train_loss:3.8875 train_time:160847ms step_avg:216.19ms step:755/6200 train_loss:3.8565 train_time:161061ms step_avg:216.19ms step:756/6200 train_loss:3.9312 train_time:161529ms step_avg:216.53ms step:757/6200 train_loss:3.7685 train_time:161744ms step_avg:216.52ms step:758/6200 train_loss:4.0048 train_time:161958ms step_avg:216.52ms step:759/6200 train_loss:3.9241 train_time:162171ms step_avg:216.52ms step:760/6200 train_loss:3.8411 train_time:162633ms step_avg:216.84ms step:761/6200 train_loss:3.9570 train_time:162849ms step_avg:216.84ms step:762/6200 train_loss:3.6678 train_time:163063ms step_avg:216.84ms step:763/6200 train_loss:3.8277 train_time:163276ms step_avg:216.83ms step:764/6200 train_loss:3.9448 train_time:163489ms step_avg:216.83ms step:765/6200 train_loss:3.5883 train_time:163703ms step_avg:216.83ms step:766/6200 train_loss:4.0182 train_time:163917ms step_avg:216.82ms step:767/6200 train_loss:3.8755 train_time:164131ms step_avg:216.82ms step:768/6200 train_loss:3.8190 train_time:164346ms step_avg:216.82ms step:769/6200 train_loss:3.8445 train_time:164560ms step_avg:216.81ms step:770/6200 train_loss:3.8660 train_time:164774ms step_avg:216.81ms step:771/6200 train_loss:3.9277 train_time:164988ms step_avg:216.80ms step:772/6200 train_loss:4.1496 train_time:165200ms step_avg:216.80ms step:773/6200 train_loss:3.7285 train_time:165413ms step_avg:216.79ms step:774/6200 train_loss:3.9276 train_time:165627ms step_avg:216.79ms step:775/6200 train_loss:3.9092 train_time:165843ms step_avg:216.79ms step:776/6200 train_loss:3.8686 train_time:166057ms step_avg:216.78ms step:777/6200 train_loss:3.6734 train_time:166269ms step_avg:216.78ms step:778/6200 train_loss:3.6728 train_time:166483ms step_avg:216.77ms step:779/6200 train_loss:3.7437 train_time:166696ms step_avg:216.77ms step:780/6200 train_loss:3.8339 train_time:166910ms step_avg:216.77ms step:781/6200 train_loss:3.8710 train_time:167125ms step_avg:216.76ms step:782/6200 train_loss:3.9274 train_time:167339ms step_avg:216.76ms step:783/6200 train_loss:3.8373 train_time:167551ms step_avg:216.75ms step:784/6200 train_loss:3.8464 train_time:167766ms step_avg:216.75ms step:785/6200 train_loss:3.8334 train_time:167978ms step_avg:216.75ms step:786/6200 train_loss:3.8235 train_time:168192ms step_avg:216.74ms step:787/6200 train_loss:3.7245 train_time:168407ms step_avg:216.74ms step:788/6200 train_loss:3.9747 train_time:168621ms step_avg:216.74ms step:789/6200 train_loss:3.7640 train_time:168835ms step_avg:216.73ms step:790/6200 train_loss:3.8320 train_time:169048ms step_avg:216.73ms step:791/6200 train_loss:3.8947 train_time:169262ms step_avg:216.73ms step:792/6200 train_loss:4.0194 train_time:169475ms step_avg:216.72ms step:793/6200 train_loss:4.0413 train_time:169689ms step_avg:216.72ms step:794/6200 train_loss:3.7376 train_time:169903ms step_avg:216.71ms step:795/6200 train_loss:3.8712 train_time:170116ms step_avg:216.71ms step:796/6200 train_loss:3.9236 train_time:170330ms step_avg:216.70ms step:797/6200 train_loss:4.0477 train_time:170547ms step_avg:216.70ms step:798/6200 train_loss:3.7773 train_time:170761ms step_avg:216.70ms step:799/6200 train_loss:3.9295 train_time:170974ms step_avg:216.70ms step:800/6200 train_loss:3.8204 train_time:171187ms step_avg:216.69ms step:801/6200 train_loss:3.8137 train_time:171401ms step_avg:216.69ms step:802/6200 train_loss:3.9061 train_time:171615ms step_avg:216.68ms step:803/6200 train_loss:3.7641 train_time:171830ms step_avg:216.68ms step:804/6200 train_loss:3.7860 train_time:172045ms step_avg:216.68ms step:805/6200 train_loss:3.8968 train_time:172259ms step_avg:216.68ms step:806/6200 train_loss:3.7984 train_time:172471ms step_avg:216.67ms step:807/6200 train_loss:3.8086 train_time:172686ms step_avg:216.67ms step:808/6200 train_loss:3.9049 train_time:172899ms step_avg:216.67ms step:809/6200 train_loss:3.8236 train_time:173113ms step_avg:216.66ms step:810/6200 train_loss:3.7477 train_time:173327ms step_avg:216.66ms step:811/6200 train_loss:3.8333 train_time:173542ms step_avg:216.66ms step:812/6200 train_loss:3.8654 train_time:173755ms step_avg:216.65ms step:813/6200 train_loss:3.8521 train_time:173968ms step_avg:216.65ms step:814/6200 train_loss:3.8969 train_time:174182ms step_avg:216.64ms step:815/6200 train_loss:3.8472 train_time:174396ms step_avg:216.64ms step:816/6200 train_loss:3.8184 train_time:174610ms step_avg:216.64ms step:817/6200 train_loss:3.9217 train_time:174824ms step_avg:216.63ms step:818/6200 train_loss:4.0246 train_time:175038ms step_avg:216.63ms step:819/6200 train_loss:3.7918 train_time:175252ms step_avg:216.63ms step:820/6200 train_loss:3.9944 train_time:175466ms step_avg:216.62ms step:821/6200 train_loss:3.7762 train_time:175679ms step_avg:216.62ms step:822/6200 train_loss:3.8108 train_time:175893ms step_avg:216.62ms step:823/6200 train_loss:3.9264 train_time:176108ms step_avg:216.61ms step:824/6200 train_loss:3.8503 train_time:176322ms step_avg:216.61ms step:825/6200 train_loss:3.7763 train_time:176536ms step_avg:216.61ms step:826/6200 train_loss:3.8731 train_time:176749ms step_avg:216.60ms step:827/6200 train_loss:3.7704 train_time:176963ms step_avg:216.60ms step:828/6200 train_loss:3.9913 train_time:177176ms step_avg:216.60ms step:829/6200 train_loss:3.8872 train_time:177391ms step_avg:216.59ms step:830/6200 train_loss:3.9475 train_time:177605ms step_avg:216.59ms step:831/6200 train_loss:3.7997 train_time:177818ms step_avg:216.59ms step:832/6200 train_loss:3.8504 train_time:178032ms step_avg:216.58ms step:833/6200 train_loss:3.7880 train_time:178248ms step_avg:216.58ms step:834/6200 train_loss:3.9024 train_time:178461ms step_avg:216.58ms step:835/6200 train_loss:3.7506 train_time:178674ms step_avg:216.57ms step:836/6200 train_loss:3.7269 train_time:178887ms step_avg:216.57ms step:837/6200 train_loss:3.9977 train_time:179101ms step_avg:216.57ms step:838/6200 train_loss:3.6983 train_time:179313ms step_avg:216.56ms step:839/6200 train_loss:3.8530 train_time:179528ms step_avg:216.56ms step:840/6200 train_loss:3.7026 train_time:179743ms step_avg:216.56ms step:841/6200 train_loss:3.7398 train_time:179957ms step_avg:216.55ms step:842/6200 train_loss:3.8268 train_time:180169ms step_avg:216.55ms step:843/6200 train_loss:3.8409 train_time:180383ms step_avg:216.55ms step:844/6200 train_loss:3.8473 train_time:180596ms step_avg:216.54ms step:845/6200 train_loss:3.6866 train_time:180811ms step_avg:216.54ms step:846/6200 train_loss:3.9367 train_time:181025ms step_avg:216.54ms step:847/6200 train_loss:3.7971 train_time:181238ms step_avg:216.53ms step:848/6200 train_loss:3.7578 train_time:181451ms step_avg:216.53ms step:849/6200 train_loss:3.8879 train_time:181666ms step_avg:216.53ms step:850/6200 train_loss:3.7569 train_time:181878ms step_avg:216.52ms step:851/6200 train_loss:3.7076 train_time:182092ms step_avg:216.52ms step:852/6200 train_loss:4.0101 train_time:182307ms step_avg:216.52ms step:853/6200 train_loss:3.7193 train_time:182521ms step_avg:216.51ms step:854/6200 train_loss:3.8311 train_time:182735ms step_avg:216.51ms step:855/6200 train_loss:3.9194 train_time:182949ms step_avg:216.51ms step:856/6200 train_loss:3.7973 train_time:183163ms step_avg:216.50ms step:857/6200 train_loss:3.8117 train_time:183375ms step_avg:216.50ms step:858/6200 train_loss:3.8631 train_time:183589ms step_avg:216.50ms step:859/6200 train_loss:3.7674 train_time:183803ms step_avg:216.49ms step:860/6200 train_loss:3.8281 train_time:184016ms step_avg:216.49ms step:861/6200 train_loss:3.8559 train_time:184230ms step_avg:216.49ms step:862/6200 train_loss:3.9158 train_time:184444ms step_avg:216.48ms step:863/6200 train_loss:3.8442 train_time:184658ms step_avg:216.48ms step:864/6200 train_loss:3.8333 train_time:184870ms step_avg:216.48ms step:865/6200 train_loss:3.6640 train_time:185083ms step_avg:216.47ms step:866/6200 train_loss:3.8513 train_time:185296ms step_avg:216.47ms step:867/6200 train_loss:4.1227 train_time:185510ms step_avg:216.46ms step:868/6200 train_loss:3.7069 train_time:185724ms step_avg:216.46ms step:869/6200 train_loss:3.8961 train_time:185939ms step_avg:216.46ms step:870/6200 train_loss:3.8752 train_time:186152ms step_avg:216.46ms step:871/6200 train_loss:3.7112 train_time:186365ms step_avg:216.45ms step:872/6200 train_loss:3.6816 train_time:186579ms step_avg:216.45ms step:873/6200 train_loss:3.9307 train_time:186793ms step_avg:216.45ms step:874/6200 train_loss:3.7137 train_time:187008ms step_avg:216.44ms step:875/6200 train_loss:3.4160 train_time:187222ms step_avg:216.44ms step:875/6200 val_loss:3.7912 train_time:187224ms step_avg:216.44ms step:876/6200 train_loss:3.9032 train_time:187444ms step_avg:216.45ms step:877/6200 train_loss:3.7129 train_time:187657ms step_avg:216.44ms step:878/6200 train_loss:3.8875 train_time:187872ms step_avg:216.44ms step:879/6200 train_loss:3.7454 train_time:188085ms step_avg:216.44ms step:880/6200 train_loss:3.9214 train_time:188299ms step_avg:216.44ms step:881/6200 train_loss:3.5823 train_time:188514ms step_avg:216.43ms step:882/6200 train_loss:3.7608 train_time:188729ms step_avg:216.43ms step:883/6200 train_loss:3.9527 train_time:188944ms step_avg:216.43ms step:884/6200 train_loss:4.1090 train_time:189156ms step_avg:216.43ms step:885/6200 train_loss:3.8352 train_time:189370ms step_avg:216.42ms step:886/6200 train_loss:3.7461 train_time:189583ms step_avg:216.42ms step:887/6200 train_loss:3.8460 train_time:189797ms step_avg:216.42ms step:888/6200 train_loss:4.3603 train_time:190013ms step_avg:216.42ms step:889/6200 train_loss:4.1161 train_time:190226ms step_avg:216.41ms step:890/6200 train_loss:3.7844 train_time:190439ms step_avg:216.41ms step:891/6200 train_loss:3.8032 train_time:190653ms step_avg:216.41ms step:892/6200 train_loss:3.6185 train_time:190866ms step_avg:216.40ms step:893/6200 train_loss:3.9595 train_time:191080ms step_avg:216.40ms step:894/6200 train_loss:3.6936 train_time:191295ms step_avg:216.40ms step:895/6200 train_loss:3.9722 train_time:191509ms step_avg:216.39ms step:896/6200 train_loss:3.9559 train_time:191722ms step_avg:216.39ms step:897/6200 train_loss:3.7608 train_time:191937ms step_avg:216.39ms step:898/6200 train_loss:3.7965 train_time:192151ms step_avg:216.39ms step:899/6200 train_loss:3.8497 train_time:192364ms step_avg:216.38ms step:900/6200 train_loss:3.7413 train_time:192577ms step_avg:216.38ms step:901/6200 train_loss:3.6815 train_time:192792ms step_avg:216.38ms step:902/6200 train_loss:3.8888 train_time:193007ms step_avg:216.38ms step:903/6200 train_loss:3.9068 train_time:193221ms step_avg:216.37ms step:904/6200 train_loss:3.7940 train_time:193435ms step_avg:216.37ms step:905/6200 train_loss:3.7711 train_time:193649ms step_avg:216.37ms step:906/6200 train_loss:3.7580 train_time:193862ms step_avg:216.36ms step:907/6200 train_loss:3.9844 train_time:194076ms step_avg:216.36ms step:908/6200 train_loss:3.7692 train_time:194291ms step_avg:216.36ms step:909/6200 train_loss:3.8157 train_time:194505ms step_avg:216.36ms step:910/6200 train_loss:3.7222 train_time:194719ms step_avg:216.35ms step:911/6200 train_loss:3.8231 train_time:194935ms step_avg:216.35ms step:912/6200 train_loss:3.8742 train_time:195149ms step_avg:216.35ms step:913/6200 train_loss:3.8696 train_time:195362ms step_avg:216.35ms step:914/6200 train_loss:3.7554 train_time:195576ms step_avg:216.35ms step:915/6200 train_loss:3.9949 train_time:195791ms step_avg:216.34ms step:916/6200 train_loss:3.7937 train_time:196004ms step_avg:216.34ms step:917/6200 train_loss:3.8843 train_time:196218ms step_avg:216.34ms step:918/6200 train_loss:3.8614 train_time:196435ms step_avg:216.34ms step:919/6200 train_loss:5.0597 train_time:196649ms step_avg:216.34ms step:920/6200 train_loss:3.7873 train_time:196862ms step_avg:216.33ms step:921/6200 train_loss:3.8309 train_time:197076ms step_avg:216.33ms step:922/6200 train_loss:3.7942 train_time:197290ms step_avg:216.33ms step:923/6200 train_loss:3.8486 train_time:197504ms step_avg:216.32ms step:924/6200 train_loss:3.8565 train_time:197717ms step_avg:216.32ms step:925/6200 train_loss:3.9409 train_time:197933ms step_avg:216.32ms step:926/6200 train_loss:3.9204 train_time:198146ms step_avg:216.32ms step:927/6200 train_loss:3.8152 train_time:198359ms step_avg:216.31ms step:928/6200 train_loss:3.8057 train_time:198573ms step_avg:216.31ms step:929/6200 train_loss:4.0309 train_time:198787ms step_avg:216.31ms step:930/6200 train_loss:3.8690 train_time:199001ms step_avg:216.31ms step:931/6200 train_loss:3.6497 train_time:199216ms step_avg:216.30ms step:932/6200 train_loss:3.7518 train_time:199431ms step_avg:216.30ms step:933/6200 train_loss:3.9461 train_time:199644ms step_avg:216.30ms step:934/6200 train_loss:3.6466 train_time:199857ms step_avg:216.30ms step:935/6200 train_loss:3.8290 train_time:200071ms step_avg:216.29ms step:936/6200 train_loss:3.7147 train_time:200284ms step_avg:216.29ms step:937/6200 train_loss:3.7686 train_time:200499ms step_avg:216.29ms step:938/6200 train_loss:3.8720 train_time:200713ms step_avg:216.29ms step:939/6200 train_loss:3.7953 train_time:200929ms step_avg:216.28ms step:940/6200 train_loss:3.9652 train_time:201143ms step_avg:216.28ms step:941/6200 train_loss:3.7502 train_time:201356ms step_avg:216.28ms step:942/6200 train_loss:3.8093 train_time:201569ms step_avg:216.28ms step:943/6200 train_loss:3.6054 train_time:201783ms step_avg:216.27ms step:944/6200 train_loss:3.9582 train_time:201997ms step_avg:216.27ms step:945/6200 train_loss:3.6669 train_time:202464ms step_avg:216.54ms step:946/6200 train_loss:3.6814 train_time:202676ms step_avg:216.53ms step:947/6200 train_loss:5.2839 train_time:202890ms step_avg:216.53ms step:948/6200 train_loss:3.8583 train_time:203103ms step_avg:216.53ms step:949/6200 train_loss:3.7663 train_time:203316ms step_avg:216.52ms step:950/6200 train_loss:3.6581 train_time:203780ms step_avg:216.79ms step:951/6200 train_loss:3.7168 train_time:203992ms step_avg:216.78ms step:952/6200 train_loss:3.6664 train_time:204205ms step_avg:216.78ms step:953/6200 train_loss:3.7366 train_time:204419ms step_avg:216.78ms step:954/6200 train_loss:3.8072 train_time:204635ms step_avg:216.77ms step:955/6200 train_loss:3.6869 train_time:204848ms step_avg:216.77ms step:956/6200 train_loss:3.7325 train_time:205061ms step_avg:216.77ms step:957/6200 train_loss:3.6996 train_time:205275ms step_avg:216.76ms step:958/6200 train_loss:3.7633 train_time:205489ms step_avg:216.76ms step:959/6200 train_loss:3.7531 train_time:205702ms step_avg:216.76ms step:960/6200 train_loss:3.7632 train_time:205917ms step_avg:216.75ms step:961/6200 train_loss:3.6416 train_time:206133ms step_avg:216.75ms step:962/6200 train_loss:3.9188 train_time:206345ms step_avg:216.75ms step:963/6200 train_loss:3.8642 train_time:206558ms step_avg:216.74ms step:964/6200 train_loss:3.7465 train_time:206772ms step_avg:216.74ms step:965/6200 train_loss:3.7117 train_time:206985ms step_avg:216.74ms step:966/6200 train_loss:3.7392 train_time:207198ms step_avg:216.73ms step:967/6200 train_loss:3.9675 train_time:207414ms step_avg:216.73ms step:968/6200 train_loss:3.7916 train_time:207628ms step_avg:216.73ms step:969/6200 train_loss:3.7759 train_time:207841ms step_avg:216.73ms step:970/6200 train_loss:3.8231 train_time:208055ms step_avg:216.72ms step:971/6200 train_loss:3.6435 train_time:208268ms step_avg:216.72ms step:972/6200 train_loss:3.7994 train_time:208482ms step_avg:216.72ms step:973/6200 train_loss:3.7622 train_time:208696ms step_avg:216.71ms step:974/6200 train_loss:3.7982 train_time:208910ms step_avg:216.71ms step:975/6200 train_loss:3.8766 train_time:209124ms step_avg:216.71ms step:976/6200 train_loss:3.7477 train_time:209338ms step_avg:216.71ms step:977/6200 train_loss:3.9432 train_time:209551ms step_avg:216.70ms step:978/6200 train_loss:3.8226 train_time:209764ms step_avg:216.70ms step:979/6200 train_loss:3.6616 train_time:209977ms step_avg:216.69ms step:980/6200 train_loss:3.9549 train_time:210191ms step_avg:216.69ms step:981/6200 train_loss:3.6833 train_time:210405ms step_avg:216.69ms step:982/6200 train_loss:3.8377 train_time:210618ms step_avg:216.68ms step:983/6200 train_loss:3.8212 train_time:210833ms step_avg:216.68ms step:984/6200 train_loss:3.8305 train_time:211046ms step_avg:216.68ms step:985/6200 train_loss:3.7697 train_time:211260ms step_avg:216.68ms step:986/6200 train_loss:3.8513 train_time:211474ms step_avg:216.67ms step:987/6200 train_loss:3.6719 train_time:211687ms step_avg:216.67ms step:988/6200 train_loss:3.7500 train_time:211901ms step_avg:216.67ms step:989/6200 train_loss:3.7826 train_time:212116ms step_avg:216.67ms step:990/6200 train_loss:3.6962 train_time:212331ms step_avg:216.66ms step:991/6200 train_loss:3.8949 train_time:212545ms step_avg:216.66ms step:992/6200 train_loss:3.7216 train_time:212757ms step_avg:216.66ms step:993/6200 train_loss:3.6973 train_time:212971ms step_avg:216.65ms step:994/6200 train_loss:3.7718 train_time:213185ms step_avg:216.65ms step:995/6200 train_loss:3.8620 train_time:213398ms step_avg:216.65ms step:996/6200 train_loss:3.7989 train_time:213612ms step_avg:216.65ms step:997/6200 train_loss:3.7054 train_time:213826ms step_avg:216.64ms step:998/6200 train_loss:4.0735 train_time:214039ms step_avg:216.64ms step:999/6200 train_loss:3.7230 train_time:214253ms step_avg:216.64ms step:1000/6200 train_loss:3.8490 train_time:214465ms step_avg:216.63ms step:1000/6200 val_loss:3.7447 train_time:214466ms step_avg:216.63ms step:1001/6200 train_loss:3.7154 train_time:214682ms step_avg:216.63ms step:1002/6200 train_loss:3.7666 train_time:214895ms step_avg:216.63ms step:1003/6200 train_loss:3.6525 train_time:215110ms step_avg:216.63ms step:1004/6200 train_loss:3.8370 train_time:215325ms step_avg:216.62ms step:1005/6200 train_loss:3.8899 train_time:215539ms step_avg:216.62ms step:1006/6200 train_loss:3.6604 train_time:215751ms step_avg:216.62ms step:1007/6200 train_loss:3.7439 train_time:215966ms step_avg:216.62ms step:1008/6200 train_loss:3.7141 train_time:216180ms step_avg:216.61ms step:1009/6200 train_loss:3.8313 train_time:216394ms step_avg:216.61ms step:1010/6200 train_loss:3.9267 train_time:216609ms step_avg:216.61ms step:1011/6200 train_loss:3.8236 train_time:216823ms step_avg:216.61ms step:1012/6200 train_loss:3.7902 train_time:217037ms step_avg:216.60ms step:1013/6200 train_loss:3.6544 train_time:217250ms step_avg:216.60ms step:1014/6200 train_loss:3.7950 train_time:217463ms step_avg:216.60ms step:1015/6200 train_loss:3.9130 train_time:217677ms step_avg:216.59ms step:1016/6200 train_loss:3.6141 train_time:217891ms step_avg:216.59ms step:1017/6200 train_loss:3.7063 train_time:218106ms step_avg:216.59ms step:1018/6200 train_loss:3.7109 train_time:218321ms step_avg:216.59ms step:1019/6200 train_loss:3.6543 train_time:218534ms step_avg:216.58ms step:1020/6200 train_loss:3.7918 train_time:218748ms step_avg:216.58ms step:1021/6200 train_loss:3.7074 train_time:218961ms step_avg:216.58ms step:1022/6200 train_loss:3.6363 train_time:219174ms step_avg:216.58ms step:1023/6200 train_loss:3.7406 train_time:219389ms step_avg:216.57ms step:1024/6200 train_loss:3.7763 train_time:219603ms step_avg:216.57ms step:1025/6200 train_loss:3.7449 train_time:219817ms step_avg:216.57ms step:1026/6200 train_loss:3.7619 train_time:220032ms step_avg:216.57ms step:1027/6200 train_loss:3.9268 train_time:220246ms step_avg:216.56ms step:1028/6200 train_loss:3.6018 train_time:220459ms step_avg:216.56ms step:1029/6200 train_loss:3.6635 train_time:220673ms step_avg:216.56ms step:1030/6200 train_loss:3.6259 train_time:220888ms step_avg:216.56ms step:1031/6200 train_loss:3.7809 train_time:221101ms step_avg:216.55ms step:1032/6200 train_loss:3.7744 train_time:221314ms step_avg:216.55ms step:1033/6200 train_loss:3.9528 train_time:221529ms step_avg:216.55ms step:1034/6200 train_loss:3.7628 train_time:221742ms step_avg:216.55ms step:1035/6200 train_loss:3.6881 train_time:221955ms step_avg:216.54ms step:1036/6200 train_loss:3.6998 train_time:222169ms step_avg:216.54ms step:1037/6200 train_loss:3.7686 train_time:222383ms step_avg:216.54ms step:1038/6200 train_loss:4.0747 train_time:222597ms step_avg:216.53ms step:1039/6200 train_loss:3.8985 train_time:222811ms step_avg:216.53ms step:1040/6200 train_loss:3.7901 train_time:223026ms step_avg:216.53ms step:1041/6200 train_loss:3.6867 train_time:223241ms step_avg:216.53ms step:1042/6200 train_loss:3.7604 train_time:223454ms step_avg:216.52ms step:1043/6200 train_loss:3.8037 train_time:223668ms step_avg:216.52ms step:1044/6200 train_loss:3.7132 train_time:223882ms step_avg:216.52ms step:1045/6200 train_loss:3.7311 train_time:224095ms step_avg:216.52ms step:1046/6200 train_loss:3.8098 train_time:224310ms step_avg:216.51ms step:1047/6200 train_loss:3.7164 train_time:224524ms step_avg:216.51ms step:1048/6200 train_loss:3.9271 train_time:224737ms step_avg:216.51ms step:1049/6200 train_loss:3.7705 train_time:224950ms step_avg:216.51ms step:1050/6200 train_loss:3.7033 train_time:225162ms step_avg:216.50ms step:1051/6200 train_loss:3.6632 train_time:225376ms step_avg:216.50ms step:1052/6200 train_loss:3.7869 train_time:225590ms step_avg:216.50ms step:1053/6200 train_loss:3.6618 train_time:225805ms step_avg:216.50ms step:1054/6200 train_loss:3.9745 train_time:226018ms step_avg:216.49ms step:1055/6200 train_loss:3.8201 train_time:226231ms step_avg:216.49ms step:1056/6200 train_loss:3.6774 train_time:226445ms step_avg:216.49ms step:1057/6200 train_loss:3.7809 train_time:226659ms step_avg:216.48ms step:1058/6200 train_loss:3.8551 train_time:226872ms step_avg:216.48ms step:1059/6200 train_loss:3.5797 train_time:227088ms step_avg:216.48ms step:1060/6200 train_loss:3.7030 train_time:227303ms step_avg:216.48ms step:1061/6200 train_loss:3.7269 train_time:227515ms step_avg:216.48ms step:1062/6200 train_loss:3.6915 train_time:227733ms step_avg:216.48ms step:1063/6200 train_loss:3.6601 train_time:227945ms step_avg:216.47ms step:1064/6200 train_loss:3.7705 train_time:228158ms step_avg:216.47ms step:1065/6200 train_loss:3.6672 train_time:228371ms step_avg:216.47ms step:1066/6200 train_loss:3.6550 train_time:228586ms step_avg:216.46ms step:1067/6200 train_loss:3.6754 train_time:228799ms step_avg:216.46ms step:1068/6200 train_loss:3.5923 train_time:229013ms step_avg:216.46ms step:1069/6200 train_loss:3.7027 train_time:229228ms step_avg:216.46ms step:1070/6200 train_loss:3.5682 train_time:229442ms step_avg:216.45ms step:1071/6200 train_loss:3.8214 train_time:229654ms step_avg:216.45ms step:1072/6200 train_loss:3.7773 train_time:229867ms step_avg:216.45ms step:1073/6200 train_loss:3.7293 train_time:230081ms step_avg:216.44ms step:1074/6200 train_loss:3.7959 train_time:230295ms step_avg:216.44ms step:1075/6200 train_loss:3.7445 train_time:230511ms step_avg:216.44ms step:1076/6200 train_loss:3.6780 train_time:230727ms step_avg:216.44ms step:1077/6200 train_loss:4.0636 train_time:230940ms step_avg:216.44ms step:1078/6200 train_loss:3.7597 train_time:231153ms step_avg:216.44ms step:1079/6200 train_loss:3.4287 train_time:231367ms step_avg:216.43ms step:1080/6200 train_loss:3.8080 train_time:231581ms step_avg:216.43ms step:1081/6200 train_loss:3.7341 train_time:231794ms step_avg:216.43ms step:1082/6200 train_loss:3.7924 train_time:232009ms step_avg:216.43ms step:1083/6200 train_loss:3.8893 train_time:232224ms step_avg:216.43ms step:1084/6200 train_loss:3.7817 train_time:232437ms step_avg:216.42ms step:1085/6200 train_loss:3.7620 train_time:232650ms step_avg:216.42ms step:1086/6200 train_loss:3.7225 train_time:232864ms step_avg:216.42ms step:1087/6200 train_loss:3.9199 train_time:233076ms step_avg:216.41ms step:1088/6200 train_loss:3.8221 train_time:233290ms step_avg:216.41ms step:1089/6200 train_loss:3.6397 train_time:233505ms step_avg:216.41ms step:1090/6200 train_loss:3.6666 train_time:233718ms step_avg:216.41ms step:1091/6200 train_loss:3.7790 train_time:233932ms step_avg:216.40ms step:1092/6200 train_loss:3.5742 train_time:234146ms step_avg:216.40ms step:1093/6200 train_loss:3.7763 train_time:234361ms step_avg:216.40ms step:1094/6200 train_loss:3.9122 train_time:234575ms step_avg:216.40ms step:1095/6200 train_loss:3.7496 train_time:234790ms step_avg:216.40ms step:1096/6200 train_loss:3.6981 train_time:235009ms step_avg:216.40ms step:1097/6200 train_loss:3.7232 train_time:235224ms step_avg:216.40ms step:1098/6200 train_loss:3.7708 train_time:235438ms step_avg:216.39ms step:1099/6200 train_loss:3.8449 train_time:235650ms step_avg:216.39ms step:1100/6200 train_loss:3.7922 train_time:235864ms step_avg:216.39ms step:1101/6200 train_loss:3.7336 train_time:236078ms step_avg:216.39ms step:1102/6200 train_loss:3.5863 train_time:236291ms step_avg:216.38ms step:1103/6200 train_loss:3.6532 train_time:236506ms step_avg:216.38ms step:1104/6200 train_loss:3.7409 train_time:236721ms step_avg:216.38ms step:1105/6200 train_loss:3.6139 train_time:236933ms step_avg:216.38ms step:1106/6200 train_loss:4.3608 train_time:237147ms step_avg:216.37ms step:1107/6200 train_loss:3.5138 train_time:237359ms step_avg:216.37ms step:1108/6200 train_loss:3.8564 train_time:237573ms step_avg:216.37ms step:1109/6200 train_loss:3.6417 train_time:237787ms step_avg:216.37ms step:1110/6200 train_loss:3.7866 train_time:238001ms step_avg:216.36ms step:1111/6200 train_loss:3.7251 train_time:238215ms step_avg:216.36ms step:1112/6200 train_loss:3.7577 train_time:238431ms step_avg:216.36ms step:1113/6200 train_loss:3.8580 train_time:238645ms step_avg:216.36ms step:1114/6200 train_loss:3.7156 train_time:238857ms step_avg:216.36ms step:1115/6200 train_loss:3.6520 train_time:239072ms step_avg:216.35ms step:1116/6200 train_loss:3.5660 train_time:239286ms step_avg:216.35ms step:1117/6200 train_loss:3.7280 train_time:239500ms step_avg:216.35ms step:1118/6200 train_loss:3.8808 train_time:239713ms step_avg:216.35ms step:1119/6200 train_loss:3.9147 train_time:239928ms step_avg:216.35ms step:1120/6200 train_loss:3.7532 train_time:240142ms step_avg:216.34ms step:1121/6200 train_loss:3.7820 train_time:240354ms step_avg:216.34ms step:1122/6200 train_loss:3.6856 train_time:240568ms step_avg:216.34ms step:1123/6200 train_loss:3.7414 train_time:240782ms step_avg:216.34ms step:1124/6200 train_loss:3.8882 train_time:240996ms step_avg:216.33ms step:1125/6200 train_loss:3.6476 train_time:241210ms step_avg:216.33ms step:1125/6200 val_loss:3.7115 train_time:241212ms step_avg:216.33ms step:1126/6200 train_loss:3.5432 train_time:241427ms step_avg:216.33ms step:1127/6200 train_loss:3.7731 train_time:241641ms step_avg:216.33ms step:1128/6200 train_loss:3.9913 train_time:241855ms step_avg:216.33ms step:1129/6200 train_loss:3.5255 train_time:242070ms step_avg:216.33ms step:1130/6200 train_loss:3.8412 train_time:242283ms step_avg:216.32ms step:1131/6200 train_loss:3.6843 train_time:242495ms step_avg:216.32ms step:1132/6200 train_loss:3.7025 train_time:242707ms step_avg:216.32ms step:1133/6200 train_loss:3.6601 train_time:242920ms step_avg:216.31ms step:1134/6200 train_loss:3.8286 train_time:243387ms step_avg:216.54ms step:1135/6200 train_loss:3.7577 train_time:243600ms step_avg:216.53ms step:1136/6200 train_loss:3.8028 train_time:243813ms step_avg:216.53ms step:1137/6200 train_loss:3.8376 train_time:244026ms step_avg:216.53ms step:1138/6200 train_loss:3.7559 train_time:244240ms step_avg:216.53ms step:1139/6200 train_loss:3.6513 train_time:244456ms step_avg:216.52ms step:1140/6200 train_loss:3.9598 train_time:244920ms step_avg:216.74ms step:1141/6200 train_loss:3.7608 train_time:245134ms step_avg:216.74ms step:1142/6200 train_loss:3.8472 train_time:245348ms step_avg:216.74ms step:1143/6200 train_loss:3.7537 train_time:245563ms step_avg:216.74ms step:1144/6200 train_loss:3.6658 train_time:245776ms step_avg:216.73ms step:1145/6200 train_loss:3.7689 train_time:245989ms step_avg:216.73ms step:1146/6200 train_loss:3.8932 train_time:246202ms step_avg:216.73ms step:1147/6200 train_loss:3.8524 train_time:246415ms step_avg:216.72ms step:1148/6200 train_loss:3.7814 train_time:246628ms step_avg:216.72ms step:1149/6200 train_loss:3.7960 train_time:246841ms step_avg:216.72ms step:1150/6200 train_loss:3.6453 train_time:247056ms step_avg:216.72ms step:1151/6200 train_loss:3.6629 train_time:247271ms step_avg:216.71ms step:1152/6200 train_loss:3.6283 train_time:247485ms step_avg:216.71ms step:1153/6200 train_loss:3.7863 train_time:247697ms step_avg:216.71ms step:1154/6200 train_loss:3.7460 train_time:247912ms step_avg:216.71ms step:1155/6200 train_loss:3.8143 train_time:248125ms step_avg:216.70ms step:1156/6200 train_loss:3.6650 train_time:248339ms step_avg:216.70ms step:1157/6200 train_loss:3.8299 train_time:248555ms step_avg:216.70ms step:1158/6200 train_loss:3.7916 train_time:248769ms step_avg:216.70ms step:1159/6200 train_loss:3.6092 train_time:248983ms step_avg:216.70ms step:1160/6200 train_loss:3.6274 train_time:249195ms step_avg:216.69ms step:1161/6200 train_loss:3.6190 train_time:249408ms step_avg:216.69ms step:1162/6200 train_loss:3.4363 train_time:249621ms step_avg:216.69ms step:1163/6200 train_loss:3.7466 train_time:249835ms step_avg:216.68ms step:1164/6200 train_loss:3.7081 train_time:250049ms step_avg:216.68ms step:1165/6200 train_loss:3.5701 train_time:250263ms step_avg:216.68ms step:1166/6200 train_loss:3.5804 train_time:250476ms step_avg:216.68ms step:1167/6200 train_loss:3.6757 train_time:250690ms step_avg:216.67ms step:1168/6200 train_loss:3.6797 train_time:250903ms step_avg:216.67ms step:1169/6200 train_loss:4.0036 train_time:251118ms step_avg:216.67ms step:1170/6200 train_loss:3.6910 train_time:251332ms step_avg:216.67ms step:1171/6200 train_loss:3.7040 train_time:251545ms step_avg:216.66ms step:1172/6200 train_loss:3.6194 train_time:251759ms step_avg:216.66ms step:1173/6200 train_loss:3.6966 train_time:251974ms step_avg:216.66ms step:1174/6200 train_loss:3.8450 train_time:252188ms step_avg:216.66ms step:1175/6200 train_loss:3.6823 train_time:252403ms step_avg:216.65ms step:1176/6200 train_loss:3.7087 train_time:252617ms step_avg:216.65ms step:1177/6200 train_loss:3.7561 train_time:252830ms step_avg:216.65ms step:1178/6200 train_loss:3.7311 train_time:253044ms step_avg:216.65ms step:1179/6200 train_loss:3.7860 train_time:253257ms step_avg:216.64ms step:1180/6200 train_loss:3.7007 train_time:253474ms step_avg:216.64ms step:1181/6200 train_loss:3.7160 train_time:253688ms step_avg:216.64ms step:1182/6200 train_loss:3.6531 train_time:253900ms step_avg:216.64ms step:1183/6200 train_loss:3.7054 train_time:254113ms step_avg:216.64ms step:1184/6200 train_loss:3.6370 train_time:254328ms step_avg:216.63ms step:1185/6200 train_loss:3.8005 train_time:254542ms step_avg:216.63ms step:1186/6200 train_loss:3.8641 train_time:254756ms step_avg:216.63ms step:1187/6200 train_loss:3.6538 train_time:254971ms step_avg:216.63ms step:1188/6200 train_loss:3.7145 train_time:255185ms step_avg:216.63ms step:1189/6200 train_loss:3.7351 train_time:255397ms step_avg:216.62ms step:1190/6200 train_loss:3.5796 train_time:255613ms step_avg:216.62ms step:1191/6200 train_loss:3.7521 train_time:255827ms step_avg:216.62ms step:1192/6200 train_loss:3.8997 train_time:256041ms step_avg:216.62ms step:1193/6200 train_loss:3.6940 train_time:256255ms step_avg:216.61ms step:1194/6200 train_loss:3.5866 train_time:256469ms step_avg:216.61ms step:1195/6200 train_loss:3.8703 train_time:256681ms step_avg:216.61ms step:1196/6200 train_loss:3.6795 train_time:256896ms step_avg:216.61ms step:1197/6200 train_loss:3.6809 train_time:257110ms step_avg:216.60ms step:1198/6200 train_loss:3.5764 train_time:257323ms step_avg:216.60ms step:1199/6200 train_loss:3.5927 train_time:257537ms step_avg:216.60ms step:1200/6200 train_loss:3.6465 train_time:257752ms step_avg:216.60ms step:1201/6200 train_loss:3.7247 train_time:257966ms step_avg:216.60ms step:1202/6200 train_loss:3.7999 train_time:258180ms step_avg:216.59ms step:1203/6200 train_loss:3.8723 train_time:258393ms step_avg:216.59ms step:1204/6200 train_loss:3.7174 train_time:258605ms step_avg:216.59ms step:1205/6200 train_loss:3.6395 train_time:258820ms step_avg:216.59ms step:1206/6200 train_loss:3.7206 train_time:259034ms step_avg:216.58ms step:1207/6200 train_loss:3.7764 train_time:259249ms step_avg:216.58ms step:1208/6200 train_loss:3.8185 train_time:259463ms step_avg:216.58ms step:1209/6200 train_loss:3.6994 train_time:259676ms step_avg:216.58ms step:1210/6200 train_loss:3.5600 train_time:259890ms step_avg:216.58ms step:1211/6200 train_loss:3.6061 train_time:260103ms step_avg:216.57ms step:1212/6200 train_loss:3.7082 train_time:260315ms step_avg:216.57ms step:1213/6200 train_loss:3.7193 train_time:260530ms step_avg:216.57ms step:1214/6200 train_loss:3.7549 train_time:260744ms step_avg:216.56ms step:1215/6200 train_loss:3.6517 train_time:260957ms step_avg:216.56ms step:1216/6200 train_loss:3.7067 train_time:261172ms step_avg:216.56ms step:1217/6200 train_loss:3.6470 train_time:261385ms step_avg:216.56ms step:1218/6200 train_loss:3.6454 train_time:261598ms step_avg:216.55ms step:1219/6200 train_loss:3.7360 train_time:261811ms step_avg:216.55ms step:1220/6200 train_loss:3.5745 train_time:262025ms step_avg:216.55ms step:1221/6200 train_loss:3.7974 train_time:262239ms step_avg:216.55ms step:1222/6200 train_loss:3.8258 train_time:262453ms step_avg:216.55ms step:1223/6200 train_loss:3.7600 train_time:262667ms step_avg:216.54ms step:1224/6200 train_loss:3.6035 train_time:262881ms step_avg:216.54ms step:1225/6200 train_loss:3.6058 train_time:263093ms step_avg:216.54ms step:1226/6200 train_loss:3.6723 train_time:263307ms step_avg:216.54ms step:1227/6200 train_loss:3.6621 train_time:263521ms step_avg:216.53ms step:1228/6200 train_loss:3.5888 train_time:263734ms step_avg:216.53ms step:1229/6200 train_loss:3.7613 train_time:263949ms step_avg:216.53ms step:1230/6200 train_loss:3.6872 train_time:264162ms step_avg:216.53ms step:1231/6200 train_loss:3.7471 train_time:264375ms step_avg:216.52ms step:1232/6200 train_loss:3.9039 train_time:264589ms step_avg:216.52ms step:1233/6200 train_loss:3.8056 train_time:264801ms step_avg:216.52ms step:1234/6200 train_loss:3.7387 train_time:265016ms step_avg:216.52ms step:1235/6200 train_loss:3.8898 train_time:265230ms step_avg:216.51ms step:1236/6200 train_loss:3.6561 train_time:265443ms step_avg:216.51ms step:1237/6200 train_loss:3.6125 train_time:265657ms step_avg:216.51ms step:1238/6200 train_loss:3.5657 train_time:265872ms step_avg:216.51ms step:1239/6200 train_loss:3.6449 train_time:266086ms step_avg:216.51ms step:1240/6200 train_loss:3.6450 train_time:266299ms step_avg:216.50ms step:1241/6200 train_loss:3.6898 train_time:266513ms step_avg:216.50ms step:1242/6200 train_loss:3.7462 train_time:266728ms step_avg:216.50ms step:1243/6200 train_loss:3.6145 train_time:266942ms step_avg:216.50ms step:1244/6200 train_loss:3.7135 train_time:267155ms step_avg:216.50ms step:1245/6200 train_loss:3.7294 train_time:267369ms step_avg:216.49ms step:1246/6200 train_loss:3.7302 train_time:267582ms step_avg:216.49ms step:1247/6200 train_loss:3.5552 train_time:267795ms step_avg:216.49ms step:1248/6200 train_loss:3.7010 train_time:268008ms step_avg:216.48ms step:1249/6200 train_loss:3.7596 train_time:268221ms step_avg:216.48ms step:1250/6200 train_loss:3.7283 train_time:268436ms step_avg:216.48ms step:1250/6200 val_loss:3.6795 train_time:268437ms step_avg:216.48ms step:1251/6200 train_loss:3.6191 train_time:268655ms step_avg:216.48ms step:1252/6200 train_loss:3.8434 train_time:268873ms step_avg:216.48ms step:1253/6200 train_loss:3.7019 train_time:269087ms step_avg:216.48ms step:1254/6200 train_loss:3.6222 train_time:269299ms step_avg:216.48ms step:1255/6200 train_loss:3.7674 train_time:269514ms step_avg:216.48ms step:1256/6200 train_loss:3.8289 train_time:269727ms step_avg:216.47ms step:1257/6200 train_loss:3.6360 train_time:269941ms step_avg:216.47ms step:1258/6200 train_loss:3.6511 train_time:270155ms step_avg:216.47ms step:1259/6200 train_loss:3.6863 train_time:270370ms step_avg:216.47ms step:1260/6200 train_loss:3.6578 train_time:270583ms step_avg:216.47ms step:1261/6200 train_loss:3.5196 train_time:270796ms step_avg:216.46ms step:1262/6200 train_loss:3.6198 train_time:271009ms step_avg:216.46ms step:1263/6200 train_loss:3.6980 train_time:271224ms step_avg:216.46ms step:1264/6200 train_loss:3.5312 train_time:271436ms step_avg:216.46ms step:1265/6200 train_loss:3.7618 train_time:271651ms step_avg:216.46ms step:1266/6200 train_loss:3.7439 train_time:271865ms step_avg:216.45ms step:1267/6200 train_loss:3.7482 train_time:272077ms step_avg:216.45ms step:1268/6200 train_loss:3.6868 train_time:272292ms step_avg:216.45ms step:1269/6200 train_loss:3.7290 train_time:272504ms step_avg:216.44ms step:1270/6200 train_loss:3.5842 train_time:272717ms step_avg:216.44ms step:1271/6200 train_loss:3.4253 train_time:272932ms step_avg:216.44ms step:1272/6200 train_loss:3.7050 train_time:273146ms step_avg:216.44ms step:1273/6200 train_loss:3.6750 train_time:273360ms step_avg:216.44ms step:1274/6200 train_loss:3.7335 train_time:273576ms step_avg:216.44ms step:1275/6200 train_loss:3.6675 train_time:273790ms step_avg:216.43ms step:1276/6200 train_loss:3.7636 train_time:274003ms step_avg:216.43ms step:1277/6200 train_loss:3.7878 train_time:274216ms step_avg:216.43ms step:1278/6200 train_loss:3.7479 train_time:274430ms step_avg:216.43ms step:1279/6200 train_loss:3.7394 train_time:274644ms step_avg:216.43ms step:1280/6200 train_loss:3.5658 train_time:274858ms step_avg:216.42ms step:1281/6200 train_loss:3.6860 train_time:275073ms step_avg:216.42ms step:1282/6200 train_loss:3.7497 train_time:275286ms step_avg:216.42ms step:1283/6200 train_loss:3.7853 train_time:275499ms step_avg:216.42ms step:1284/6200 train_loss:3.6708 train_time:275712ms step_avg:216.41ms step:1285/6200 train_loss:3.7082 train_time:275925ms step_avg:216.41ms step:1286/6200 train_loss:3.6819 train_time:276138ms step_avg:216.41ms step:1287/6200 train_loss:3.6593 train_time:276353ms step_avg:216.41ms step:1288/6200 train_loss:3.7915 train_time:276568ms step_avg:216.41ms step:1289/6200 train_loss:3.6250 train_time:276781ms step_avg:216.40ms step:1290/6200 train_loss:3.7112 train_time:276993ms step_avg:216.40ms step:1291/6200 train_loss:3.7866 train_time:277208ms step_avg:216.40ms step:1292/6200 train_loss:3.7111 train_time:277421ms step_avg:216.40ms step:1293/6200 train_loss:3.8040 train_time:277635ms step_avg:216.39ms step:1294/6200 train_loss:3.8294 train_time:277849ms step_avg:216.39ms step:1295/6200 train_loss:3.8038 train_time:278062ms step_avg:216.39ms step:1296/6200 train_loss:3.6040 train_time:278276ms step_avg:216.39ms step:1297/6200 train_loss:3.6780 train_time:278489ms step_avg:216.39ms step:1298/6200 train_loss:3.5748 train_time:278702ms step_avg:216.38ms step:1299/6200 train_loss:3.6518 train_time:278915ms step_avg:216.38ms step:1300/6200 train_loss:3.7172 train_time:279130ms step_avg:216.38ms step:1301/6200 train_loss:3.7278 train_time:279345ms step_avg:216.38ms step:1302/6200 train_loss:3.7386 train_time:279557ms step_avg:216.38ms step:1303/6200 train_loss:3.8807 train_time:279773ms step_avg:216.38ms step:1304/6200 train_loss:3.6704 train_time:279987ms step_avg:216.37ms step:1305/6200 train_loss:3.8739 train_time:280200ms step_avg:216.37ms step:1306/6200 train_loss:3.5956 train_time:280414ms step_avg:216.37ms step:1307/6200 train_loss:3.7864 train_time:280628ms step_avg:216.37ms step:1308/6200 train_loss:3.7801 train_time:280842ms step_avg:216.36ms step:1309/6200 train_loss:3.6516 train_time:281055ms step_avg:216.36ms step:1310/6200 train_loss:3.6085 train_time:281269ms step_avg:216.36ms step:1311/6200 train_loss:3.6514 train_time:281483ms step_avg:216.36ms step:1312/6200 train_loss:3.6063 train_time:281695ms step_avg:216.36ms step:1313/6200 train_loss:3.7331 train_time:281909ms step_avg:216.35ms step:1314/6200 train_loss:3.6827 train_time:282124ms step_avg:216.35ms step:1315/6200 train_loss:3.3998 train_time:282337ms step_avg:216.35ms step:1316/6200 train_loss:3.6259 train_time:282552ms step_avg:216.35ms step:1317/6200 train_loss:3.6990 train_time:282767ms step_avg:216.35ms step:1318/6200 train_loss:3.7353 train_time:282980ms step_avg:216.35ms step:1319/6200 train_loss:3.5962 train_time:283193ms step_avg:216.34ms step:1320/6200 train_loss:3.7449 train_time:283405ms step_avg:216.34ms step:1321/6200 train_loss:3.7975 train_time:283618ms step_avg:216.34ms step:1322/6200 train_loss:3.6831 train_time:283833ms step_avg:216.34ms step:1323/6200 train_loss:3.6330 train_time:284301ms step_avg:216.53ms step:1324/6200 train_loss:3.6711 train_time:284515ms step_avg:216.53ms step:1325/6200 train_loss:3.7630 train_time:284729ms step_avg:216.52ms step:1326/6200 train_loss:3.8190 train_time:284942ms step_avg:216.52ms step:1327/6200 train_loss:3.5789 train_time:285154ms step_avg:216.52ms step:1328/6200 train_loss:3.4973 train_time:285368ms step_avg:216.52ms step:1329/6200 train_loss:3.7970 train_time:285582ms step_avg:216.51ms step:1330/6200 train_loss:3.6555 train_time:286046ms step_avg:216.70ms step:1331/6200 train_loss:3.7743 train_time:286261ms step_avg:216.70ms step:1332/6200 train_loss:3.6819 train_time:286475ms step_avg:216.70ms step:1333/6200 train_loss:4.0862 train_time:286688ms step_avg:216.70ms step:1334/6200 train_loss:3.7696 train_time:286900ms step_avg:216.69ms step:1335/6200 train_loss:3.6833 train_time:287114ms step_avg:216.69ms step:1336/6200 train_loss:3.6393 train_time:287327ms step_avg:216.69ms step:1337/6200 train_loss:3.6253 train_time:287540ms step_avg:216.68ms step:1338/6200 train_loss:3.8868 train_time:287754ms step_avg:216.68ms step:1339/6200 train_loss:3.8216 train_time:287969ms step_avg:216.68ms step:1340/6200 train_loss:3.6675 train_time:288182ms step_avg:216.68ms step:1341/6200 train_loss:3.6250 train_time:288394ms step_avg:216.68ms step:1342/6200 train_loss:3.9338 train_time:288608ms step_avg:216.67ms step:1343/6200 train_loss:3.6935 train_time:288822ms step_avg:216.67ms step:1344/6200 train_loss:3.6956 train_time:289035ms step_avg:216.67ms step:1345/6200 train_loss:3.7545 train_time:289249ms step_avg:216.67ms step:1346/6200 train_loss:3.7200 train_time:289463ms step_avg:216.66ms step:1347/6200 train_loss:3.6211 train_time:289677ms step_avg:216.66ms step:1348/6200 train_loss:3.5616 train_time:289890ms step_avg:216.66ms step:1349/6200 train_loss:3.6616 train_time:290102ms step_avg:216.66ms step:1350/6200 train_loss:3.5962 train_time:290316ms step_avg:216.65ms step:1351/6200 train_loss:3.7299 train_time:290530ms step_avg:216.65ms step:1352/6200 train_loss:3.5803 train_time:290743ms step_avg:216.65ms step:1353/6200 train_loss:3.6403 train_time:290956ms step_avg:216.65ms step:1354/6200 train_loss:3.7486 train_time:291171ms step_avg:216.65ms step:1355/6200 train_loss:3.5801 train_time:291386ms step_avg:216.64ms step:1356/6200 train_loss:3.5082 train_time:291598ms step_avg:216.64ms step:1357/6200 train_loss:3.8638 train_time:291812ms step_avg:216.64ms step:1358/6200 train_loss:3.7915 train_time:292026ms step_avg:216.64ms step:1359/6200 train_loss:3.5031 train_time:292239ms step_avg:216.63ms step:1360/6200 train_loss:3.7890 train_time:292453ms step_avg:216.63ms step:1361/6200 train_loss:3.6728 train_time:292667ms step_avg:216.63ms step:1362/6200 train_loss:3.5488 train_time:292881ms step_avg:216.63ms step:1363/6200 train_loss:3.7129 train_time:293093ms step_avg:216.62ms step:1364/6200 train_loss:3.6010 train_time:293306ms step_avg:216.62ms step:1365/6200 train_loss:3.6291 train_time:293519ms step_avg:216.62ms step:1366/6200 train_loss:3.6529 train_time:293733ms step_avg:216.62ms step:1367/6200 train_loss:3.7552 train_time:293947ms step_avg:216.62ms step:1368/6200 train_loss:3.7324 train_time:294161ms step_avg:216.61ms step:1369/6200 train_loss:3.6937 train_time:294375ms step_avg:216.61ms step:1370/6200 train_loss:3.5941 train_time:294589ms step_avg:216.61ms step:1371/6200 train_loss:3.9204 train_time:294801ms step_avg:216.61ms step:1372/6200 train_loss:3.6658 train_time:295015ms step_avg:216.60ms step:1373/6200 train_loss:3.6952 train_time:295229ms step_avg:216.60ms step:1374/6200 train_loss:3.6972 train_time:295442ms step_avg:216.60ms step:1375/6200 train_loss:3.4906 train_time:295656ms step_avg:216.60ms step:1375/6200 val_loss:3.6574 train_time:295657ms step_avg:216.60ms step:1376/6200 train_loss:3.8996 train_time:295877ms step_avg:216.60ms step:1377/6200 train_loss:3.6741 train_time:296095ms step_avg:216.60ms step:1378/6200 train_loss:3.8168 train_time:296311ms step_avg:216.60ms step:1379/6200 train_loss:3.8737 train_time:296523ms step_avg:216.60ms step:1380/6200 train_loss:3.5251 train_time:296736ms step_avg:216.60ms step:1381/6200 train_loss:3.6678 train_time:296950ms step_avg:216.59ms step:1382/6200 train_loss:4.1185 train_time:297164ms step_avg:216.59ms step:1383/6200 train_loss:3.5758 train_time:297377ms step_avg:216.59ms step:1384/6200 train_loss:3.7353 train_time:297592ms step_avg:216.59ms step:1385/6200 train_loss:3.8085 train_time:297805ms step_avg:216.59ms step:1386/6200 train_loss:3.7165 train_time:298017ms step_avg:216.58ms step:1387/6200 train_loss:3.7370 train_time:298231ms step_avg:216.58ms step:1388/6200 train_loss:3.5367 train_time:298445ms step_avg:216.58ms step:1389/6200 train_loss:3.6842 train_time:298658ms step_avg:216.58ms step:1390/6200 train_loss:3.6509 train_time:298874ms step_avg:216.58ms step:1391/6200 train_loss:3.9198 train_time:299087ms step_avg:216.57ms step:1392/6200 train_loss:3.6330 train_time:299301ms step_avg:216.57ms step:1393/6200 train_loss:3.6182 train_time:299513ms step_avg:216.57ms step:1394/6200 train_loss:3.5955 train_time:299726ms step_avg:216.57ms step:1395/6200 train_loss:3.8817 train_time:299940ms step_avg:216.56ms step:1396/6200 train_loss:3.7723 train_time:300156ms step_avg:216.56ms step:1397/6200 train_loss:3.7716 train_time:300372ms step_avg:216.56ms step:1398/6200 train_loss:3.6358 train_time:300585ms step_avg:216.56ms step:1399/6200 train_loss:3.6132 train_time:300798ms step_avg:216.56ms step:1400/6200 train_loss:3.6795 train_time:301011ms step_avg:216.55ms step:1401/6200 train_loss:3.6441 train_time:301224ms step_avg:216.55ms step:1402/6200 train_loss:3.6690 train_time:301437ms step_avg:216.55ms step:1403/6200 train_loss:3.6343 train_time:301652ms step_avg:216.55ms step:1404/6200 train_loss:3.8622 train_time:301865ms step_avg:216.55ms step:1405/6200 train_loss:3.6030 train_time:302079ms step_avg:216.54ms step:1406/6200 train_loss:3.6616 train_time:302294ms step_avg:216.54ms step:1407/6200 train_loss:3.6533 train_time:302506ms step_avg:216.54ms step:1408/6200 train_loss:3.5218 train_time:302719ms step_avg:216.54ms step:1409/6200 train_loss:3.6356 train_time:302933ms step_avg:216.54ms step:1410/6200 train_loss:3.6165 train_time:303146ms step_avg:216.53ms step:1411/6200 train_loss:3.6168 train_time:303359ms step_avg:216.53ms step:1412/6200 train_loss:3.7155 train_time:303574ms step_avg:216.53ms step:1413/6200 train_loss:3.6347 train_time:303789ms step_avg:216.53ms step:1414/6200 train_loss:3.6934 train_time:304002ms step_avg:216.53ms step:1415/6200 train_loss:3.6884 train_time:304214ms step_avg:216.52ms step:1416/6200 train_loss:3.7657 train_time:304428ms step_avg:216.52ms step:1417/6200 train_loss:3.5671 train_time:304641ms step_avg:216.52ms step:1418/6200 train_loss:3.6228 train_time:304855ms step_avg:216.52ms step:1419/6200 train_loss:3.7138 train_time:305069ms step_avg:216.51ms step:1420/6200 train_loss:3.7672 train_time:305283ms step_avg:216.51ms step:1421/6200 train_loss:3.7287 train_time:305496ms step_avg:216.51ms step:1422/6200 train_loss:3.7087 train_time:305709ms step_avg:216.51ms step:1423/6200 train_loss:3.6973 train_time:305921ms step_avg:216.50ms step:1424/6200 train_loss:3.6862 train_time:306135ms step_avg:216.50ms step:1425/6200 train_loss:3.6780 train_time:306349ms step_avg:216.50ms step:1426/6200 train_loss:3.5535 train_time:306562ms step_avg:216.50ms step:1427/6200 train_loss:3.6603 train_time:306776ms step_avg:216.50ms step:1428/6200 train_loss:3.6025 train_time:306990ms step_avg:216.50ms step:1429/6200 train_loss:3.7129 train_time:307203ms step_avg:216.49ms step:1430/6200 train_loss:3.6821 train_time:307415ms step_avg:216.49ms step:1431/6200 train_loss:3.6107 train_time:307628ms step_avg:216.49ms step:1432/6200 train_loss:3.6577 train_time:307841ms step_avg:216.48ms step:1433/6200 train_loss:3.7002 train_time:308055ms step_avg:216.48ms step:1434/6200 train_loss:3.5715 train_time:308269ms step_avg:216.48ms step:1435/6200 train_loss:3.6731 train_time:308483ms step_avg:216.48ms step:1436/6200 train_loss:3.4895 train_time:308696ms step_avg:216.48ms step:1437/6200 train_loss:3.5584 train_time:308910ms step_avg:216.48ms step:1438/6200 train_loss:3.7558 train_time:309123ms step_avg:216.47ms step:1439/6200 train_loss:3.7065 train_time:309337ms step_avg:216.47ms step:1440/6200 train_loss:3.6591 train_time:309551ms step_avg:216.47ms step:1441/6200 train_loss:3.5140 train_time:309765ms step_avg:216.47ms step:1442/6200 train_loss:3.6897 train_time:309978ms step_avg:216.46ms step:1443/6200 train_loss:3.7472 train_time:310193ms step_avg:216.46ms step:1444/6200 train_loss:3.8157 train_time:310406ms step_avg:216.46ms step:1445/6200 train_loss:3.7920 train_time:310620ms step_avg:216.46ms step:1446/6200 train_loss:3.6685 train_time:310834ms step_avg:216.46ms step:1447/6200 train_loss:3.5433 train_time:311048ms step_avg:216.46ms step:1448/6200 train_loss:3.6194 train_time:311262ms step_avg:216.45ms step:1449/6200 train_loss:3.6421 train_time:311476ms step_avg:216.45ms step:1450/6200 train_loss:3.7603 train_time:311692ms step_avg:216.45ms step:1451/6200 train_loss:3.7493 train_time:311904ms step_avg:216.45ms step:1452/6200 train_loss:3.5671 train_time:312116ms step_avg:216.45ms step:1453/6200 train_loss:3.6742 train_time:312330ms step_avg:216.44ms step:1454/6200 train_loss:3.5921 train_time:312543ms step_avg:216.44ms step:1455/6200 train_loss:3.6184 train_time:312757ms step_avg:216.44ms step:1456/6200 train_loss:3.6697 train_time:312976ms step_avg:216.44ms step:1457/6200 train_loss:3.5978 train_time:313189ms step_avg:216.44ms step:1458/6200 train_loss:3.4997 train_time:313402ms step_avg:216.44ms step:1459/6200 train_loss:3.7430 train_time:313614ms step_avg:216.44ms step:1460/6200 train_loss:3.6179 train_time:313828ms step_avg:216.43ms step:1461/6200 train_loss:3.6607 train_time:314041ms step_avg:216.43ms step:1462/6200 train_loss:3.7954 train_time:314255ms step_avg:216.43ms step:1463/6200 train_loss:3.6151 train_time:314470ms step_avg:216.43ms step:1464/6200 train_loss:3.8049 train_time:314683ms step_avg:216.43ms step:1465/6200 train_loss:3.6894 train_time:314896ms step_avg:216.42ms step:1466/6200 train_loss:3.7057 train_time:315110ms step_avg:216.42ms step:1467/6200 train_loss:3.6158 train_time:315322ms step_avg:216.42ms step:1468/6200 train_loss:3.7770 train_time:315536ms step_avg:216.42ms step:1469/6200 train_loss:3.6340 train_time:315749ms step_avg:216.41ms step:1470/6200 train_loss:3.6143 train_time:315963ms step_avg:216.41ms step:1471/6200 train_loss:3.6616 train_time:316175ms step_avg:216.41ms step:1472/6200 train_loss:3.5896 train_time:316391ms step_avg:216.41ms step:1473/6200 train_loss:3.6876 train_time:316604ms step_avg:216.41ms step:1474/6200 train_loss:3.7707 train_time:316817ms step_avg:216.40ms step:1475/6200 train_loss:3.6489 train_time:317030ms step_avg:216.40ms step:1476/6200 train_loss:3.4709 train_time:317243ms step_avg:216.40ms step:1477/6200 train_loss:3.5945 train_time:317456ms step_avg:216.40ms step:1478/6200 train_loss:3.5720 train_time:317671ms step_avg:216.40ms step:1479/6200 train_loss:3.6586 train_time:317884ms step_avg:216.39ms step:1480/6200 train_loss:3.7382 train_time:318097ms step_avg:216.39ms step:1481/6200 train_loss:3.6120 train_time:318310ms step_avg:216.39ms step:1482/6200 train_loss:3.7816 train_time:318522ms step_avg:216.39ms step:1483/6200 train_loss:3.7102 train_time:318735ms step_avg:216.39ms step:1484/6200 train_loss:3.6138 train_time:318947ms step_avg:216.38ms step:1485/6200 train_loss:3.6041 train_time:319162ms step_avg:216.38ms step:1486/6200 train_loss:3.5994 train_time:319376ms step_avg:216.38ms step:1487/6200 train_loss:3.5852 train_time:319591ms step_avg:216.38ms step:1488/6200 train_loss:3.6630 train_time:319805ms step_avg:216.38ms step:1489/6200 train_loss:3.5731 train_time:320017ms step_avg:216.37ms step:1490/6200 train_loss:3.6643 train_time:320233ms step_avg:216.37ms step:1491/6200 train_loss:3.6027 train_time:320446ms step_avg:216.37ms step:1492/6200 train_loss:3.5240 train_time:320659ms step_avg:216.37ms step:1493/6200 train_loss:3.5968 train_time:320874ms step_avg:216.37ms step:1494/6200 train_loss:3.7794 train_time:321088ms step_avg:216.37ms step:1495/6200 train_loss:3.6341 train_time:321303ms step_avg:216.37ms step:1496/6200 train_loss:3.3898 train_time:321515ms step_avg:216.36ms step:1497/6200 train_loss:3.6878 train_time:321733ms step_avg:216.36ms step:1498/6200 train_loss:3.6523 train_time:321946ms step_avg:216.36ms step:1499/6200 train_loss:3.6971 train_time:322159ms step_avg:216.36ms step:1500/6200 train_loss:3.6559 train_time:322373ms step_avg:216.36ms step:1500/6200 val_loss:3.6302 train_time:322375ms step_avg:216.36ms step:1501/6200 train_loss:3.6355 train_time:322594ms step_avg:216.36ms step:1502/6200 train_loss:3.4306 train_time:322808ms step_avg:216.36ms step:1503/6200 train_loss:3.7034 train_time:323022ms step_avg:216.36ms step:1504/6200 train_loss:3.5778 train_time:323235ms step_avg:216.36ms step:1505/6200 train_loss:3.5867 train_time:323447ms step_avg:216.35ms step:1506/6200 train_loss:3.5470 train_time:323661ms step_avg:216.35ms step:1507/6200 train_loss:3.6309 train_time:323875ms step_avg:216.35ms step:1508/6200 train_loss:3.5499 train_time:324089ms step_avg:216.35ms step:1509/6200 train_loss:3.8627 train_time:324304ms step_avg:216.35ms step:1510/6200 train_loss:3.6092 train_time:324518ms step_avg:216.35ms step:1511/6200 train_loss:3.6100 train_time:324730ms step_avg:216.34ms step:1512/6200 train_loss:3.7238 train_time:325198ms step_avg:216.51ms step:1513/6200 train_loss:3.7611 train_time:325411ms step_avg:216.51ms step:1514/6200 train_loss:3.6202 train_time:325623ms step_avg:216.50ms step:1515/6200 train_loss:3.4644 train_time:325837ms step_avg:216.50ms step:1516/6200 train_loss:3.5844 train_time:326051ms step_avg:216.50ms step:1517/6200 train_loss:3.5851 train_time:326268ms step_avg:216.50ms step:1518/6200 train_loss:3.6719 train_time:326482ms step_avg:216.50ms step:1519/6200 train_loss:3.5588 train_time:326695ms step_avg:216.50ms step:1520/6200 train_loss:3.8576 train_time:327158ms step_avg:216.66ms step:1521/6200 train_loss:3.5169 train_time:327372ms step_avg:216.66ms step:1522/6200 train_loss:3.5746 train_time:327586ms step_avg:216.66ms step:1523/6200 train_loss:3.7123 train_time:327800ms step_avg:216.66ms step:1524/6200 train_loss:3.5739 train_time:328013ms step_avg:216.65ms step:1525/6200 train_loss:3.6667 train_time:328226ms step_avg:216.65ms step:1526/6200 train_loss:3.6620 train_time:328439ms step_avg:216.65ms step:1527/6200 train_loss:3.6287 train_time:328653ms step_avg:216.65ms step:1528/6200 train_loss:3.6189 train_time:328866ms step_avg:216.64ms step:1529/6200 train_loss:3.7728 train_time:329080ms step_avg:216.64ms step:1530/6200 train_loss:3.7435 train_time:329294ms step_avg:216.64ms step:1531/6200 train_loss:3.5714 train_time:329507ms step_avg:216.64ms step:1532/6200 train_loss:3.5320 train_time:329721ms step_avg:216.64ms step:1533/6200 train_loss:3.6849 train_time:329933ms step_avg:216.63ms step:1534/6200 train_loss:3.6485 train_time:330146ms step_avg:216.63ms step:1535/6200 train_loss:3.6411 train_time:330359ms step_avg:216.63ms step:1536/6200 train_loss:3.6286 train_time:330573ms step_avg:216.63ms step:1537/6200 train_loss:3.5630 train_time:330787ms step_avg:216.63ms step:1538/6200 train_loss:3.6243 train_time:331001ms step_avg:216.62ms step:1539/6200 train_loss:3.8032 train_time:331213ms step_avg:216.62ms step:1540/6200 train_loss:3.7300 train_time:331425ms step_avg:216.62ms step:1541/6200 train_loss:3.6360 train_time:331638ms step_avg:216.62ms step:1542/6200 train_loss:3.5891 train_time:331851ms step_avg:216.61ms step:1543/6200 train_loss:3.5895 train_time:332065ms step_avg:216.61ms step:1544/6200 train_loss:3.5518 train_time:332281ms step_avg:216.61ms step:1545/6200 train_loss:3.6482 train_time:332496ms step_avg:216.61ms step:1546/6200 train_loss:3.6082 train_time:332708ms step_avg:216.61ms step:1547/6200 train_loss:3.5867 train_time:332922ms step_avg:216.60ms step:1548/6200 train_loss:3.5536 train_time:333134ms step_avg:216.60ms step:1549/6200 train_loss:3.5834 train_time:333347ms step_avg:216.60ms step:1550/6200 train_loss:3.6972 train_time:333561ms step_avg:216.60ms step:1551/6200 train_loss:3.6196 train_time:333774ms step_avg:216.60ms step:1552/6200 train_loss:3.5648 train_time:333987ms step_avg:216.59ms step:1553/6200 train_loss:3.5622 train_time:334205ms step_avg:216.59ms step:1554/6200 train_loss:3.5466 train_time:334418ms step_avg:216.59ms step:1555/6200 train_loss:3.6756 train_time:334630ms step_avg:216.59ms step:1556/6200 train_loss:3.6786 train_time:334844ms step_avg:216.59ms step:1557/6200 train_loss:3.6114 train_time:335059ms step_avg:216.59ms step:1558/6200 train_loss:3.6758 train_time:335273ms step_avg:216.58ms step:1559/6200 train_loss:3.5976 train_time:335486ms step_avg:216.58ms step:1560/6200 train_loss:3.5294 train_time:335700ms step_avg:216.58ms step:1561/6200 train_loss:3.7552 train_time:335913ms step_avg:216.58ms step:1562/6200 train_loss:3.5745 train_time:336125ms step_avg:216.58ms step:1563/6200 train_loss:3.5528 train_time:336338ms step_avg:216.57ms step:1564/6200 train_loss:3.6854 train_time:336551ms step_avg:216.57ms step:1565/6200 train_loss:3.5026 train_time:336765ms step_avg:216.57ms step:1566/6200 train_loss:3.5676 train_time:336979ms step_avg:216.57ms step:1567/6200 train_loss:3.7120 train_time:337192ms step_avg:216.57ms step:1568/6200 train_loss:3.5956 train_time:337406ms step_avg:216.56ms step:1569/6200 train_loss:3.5745 train_time:337619ms step_avg:216.56ms step:1570/6200 train_loss:3.6735 train_time:337832ms step_avg:216.56ms step:1571/6200 train_loss:3.6907 train_time:338045ms step_avg:216.56ms step:1572/6200 train_loss:3.5086 train_time:338259ms step_avg:216.55ms step:1573/6200 train_loss:3.5352 train_time:338471ms step_avg:216.55ms step:1574/6200 train_loss:3.6605 train_time:338686ms step_avg:216.55ms step:1575/6200 train_loss:3.5265 train_time:338901ms step_avg:216.55ms step:1576/6200 train_loss:3.6699 train_time:339114ms step_avg:216.55ms step:1577/6200 train_loss:3.5763 train_time:339326ms step_avg:216.54ms step:1578/6200 train_loss:3.6301 train_time:339539ms step_avg:216.54ms step:1579/6200 train_loss:3.5999 train_time:339752ms step_avg:216.54ms step:1580/6200 train_loss:3.5676 train_time:339966ms step_avg:216.54ms step:1581/6200 train_loss:3.5436 train_time:340180ms step_avg:216.54ms step:1582/6200 train_loss:3.7869 train_time:340393ms step_avg:216.54ms step:1583/6200 train_loss:3.5529 train_time:340606ms step_avg:216.53ms step:1584/6200 train_loss:3.7084 train_time:340821ms step_avg:216.53ms step:1585/6200 train_loss:3.5474 train_time:341034ms step_avg:216.53ms step:1586/6200 train_loss:3.7078 train_time:341247ms step_avg:216.53ms step:1587/6200 train_loss:3.4891 train_time:341461ms step_avg:216.53ms step:1588/6200 train_loss:3.6845 train_time:341674ms step_avg:216.52ms step:1589/6200 train_loss:3.5946 train_time:341888ms step_avg:216.52ms step:1590/6200 train_loss:3.7545 train_time:342104ms step_avg:216.52ms step:1591/6200 train_loss:3.5681 train_time:342317ms step_avg:216.52ms step:1592/6200 train_loss:3.5851 train_time:342530ms step_avg:216.52ms step:1593/6200 train_loss:3.6559 train_time:342744ms step_avg:216.52ms step:1594/6200 train_loss:3.6356 train_time:342958ms step_avg:216.51ms step:1595/6200 train_loss:3.6048 train_time:343171ms step_avg:216.51ms step:1596/6200 train_loss:3.7430 train_time:343386ms step_avg:216.51ms step:1597/6200 train_loss:3.4807 train_time:343600ms step_avg:216.51ms step:1598/6200 train_loss:3.6387 train_time:343813ms step_avg:216.51ms step:1599/6200 train_loss:3.6850 train_time:344025ms step_avg:216.50ms step:1600/6200 train_loss:3.7250 train_time:344239ms step_avg:216.50ms step:1601/6200 train_loss:3.5739 train_time:344452ms step_avg:216.50ms step:1602/6200 train_loss:3.8687 train_time:344666ms step_avg:216.50ms step:1603/6200 train_loss:3.7612 train_time:344880ms step_avg:216.50ms step:1604/6200 train_loss:3.5395 train_time:345093ms step_avg:216.49ms step:1605/6200 train_loss:3.5815 train_time:345306ms step_avg:216.49ms step:1606/6200 train_loss:3.4647 train_time:345520ms step_avg:216.49ms step:1607/6200 train_loss:3.7921 train_time:345732ms step_avg:216.49ms step:1608/6200 train_loss:3.5917 train_time:345947ms step_avg:216.49ms step:1609/6200 train_loss:3.6154 train_time:346160ms step_avg:216.49ms step:1610/6200 train_loss:3.5578 train_time:346373ms step_avg:216.48ms step:1611/6200 train_loss:4.1690 train_time:346589ms step_avg:216.48ms step:1612/6200 train_loss:3.7958 train_time:346804ms step_avg:216.48ms step:1613/6200 train_loss:3.7171 train_time:347018ms step_avg:216.48ms step:1614/6200 train_loss:3.5789 train_time:347231ms step_avg:216.48ms step:1615/6200 train_loss:3.6279 train_time:347445ms step_avg:216.48ms step:1616/6200 train_loss:3.6098 train_time:347659ms step_avg:216.47ms step:1617/6200 train_loss:3.5737 train_time:347872ms step_avg:216.47ms step:1618/6200 train_loss:3.6499 train_time:348086ms step_avg:216.47ms step:1619/6200 train_loss:3.6034 train_time:348301ms step_avg:216.47ms step:1620/6200 train_loss:3.5009 train_time:348513ms step_avg:216.47ms step:1621/6200 train_loss:3.7671 train_time:348727ms step_avg:216.47ms step:1622/6200 train_loss:3.6619 train_time:348940ms step_avg:216.46ms step:1623/6200 train_loss:3.4629 train_time:349165ms step_avg:216.47ms step:1624/6200 train_loss:3.5858 train_time:349378ms step_avg:216.47ms step:1625/6200 train_loss:3.5512 train_time:349592ms step_avg:216.47ms step:1625/6200 val_loss:3.6125 train_time:349594ms step_avg:216.47ms step:1626/6200 train_loss:3.6170 train_time:349809ms step_avg:216.47ms step:1627/6200 train_loss:3.5915 train_time:350022ms step_avg:216.46ms step:1628/6200 train_loss:3.5494 train_time:350235ms step_avg:216.46ms step:1629/6200 train_loss:3.6561 train_time:350451ms step_avg:216.46ms step:1630/6200 train_loss:3.5569 train_time:350665ms step_avg:216.46ms step:1631/6200 train_loss:3.6058 train_time:350877ms step_avg:216.46ms step:1632/6200 train_loss:3.4810 train_time:351091ms step_avg:216.46ms step:1633/6200 train_loss:3.4601 train_time:351303ms step_avg:216.45ms step:1634/6200 train_loss:3.6245 train_time:351517ms step_avg:216.45ms step:1635/6200 train_loss:3.6013 train_time:351731ms step_avg:216.45ms step:1636/6200 train_loss:3.5427 train_time:351945ms step_avg:216.45ms step:1637/6200 train_loss:3.6344 train_time:352159ms step_avg:216.45ms step:1638/6200 train_loss:3.6791 train_time:352371ms step_avg:216.44ms step:1639/6200 train_loss:3.7133 train_time:352584ms step_avg:216.44ms step:1640/6200 train_loss:3.8796 train_time:352795ms step_avg:216.44ms step:1641/6200 train_loss:3.7055 train_time:353008ms step_avg:216.44ms step:1642/6200 train_loss:3.6122 train_time:353222ms step_avg:216.43ms step:1643/6200 train_loss:3.6902 train_time:353434ms step_avg:216.43ms step:1644/6200 train_loss:3.5922 train_time:353650ms step_avg:216.43ms step:1645/6200 train_loss:3.6092 train_time:353864ms step_avg:216.43ms step:1646/6200 train_loss:3.6070 train_time:354077ms step_avg:216.43ms step:1647/6200 train_loss:3.3860 train_time:354291ms step_avg:216.43ms step:1648/6200 train_loss:3.6484 train_time:354504ms step_avg:216.42ms step:1649/6200 train_loss:3.5127 train_time:354717ms step_avg:216.42ms step:1650/6200 train_loss:3.5902 train_time:354931ms step_avg:216.42ms step:1651/6200 train_loss:3.5659 train_time:355145ms step_avg:216.42ms step:1652/6200 train_loss:3.6300 train_time:355358ms step_avg:216.42ms step:1653/6200 train_loss:3.5689 train_time:355576ms step_avg:216.42ms step:1654/6200 train_loss:3.6977 train_time:355790ms step_avg:216.42ms step:1655/6200 train_loss:3.6805 train_time:356002ms step_avg:216.41ms step:1656/6200 train_loss:3.5040 train_time:356215ms step_avg:216.41ms step:1657/6200 train_loss:3.6556 train_time:356430ms step_avg:216.41ms step:1658/6200 train_loss:3.5619 train_time:356643ms step_avg:216.41ms step:1659/6200 train_loss:3.5371 train_time:356857ms step_avg:216.41ms step:1660/6200 train_loss:3.6192 train_time:357072ms step_avg:216.41ms step:1661/6200 train_loss:3.6425 train_time:357285ms step_avg:216.41ms step:1662/6200 train_loss:3.5624 train_time:357497ms step_avg:216.40ms step:1663/6200 train_loss:3.6506 train_time:357711ms step_avg:216.40ms step:1664/6200 train_loss:3.6632 train_time:357924ms step_avg:216.40ms step:1665/6200 train_loss:3.6801 train_time:358137ms step_avg:216.40ms step:1666/6200 train_loss:3.6709 train_time:358352ms step_avg:216.40ms step:1667/6200 train_loss:3.8027 train_time:358566ms step_avg:216.39ms step:1668/6200 train_loss:3.5137 train_time:358779ms step_avg:216.39ms step:1669/6200 train_loss:3.5921 train_time:358992ms step_avg:216.39ms step:1670/6200 train_loss:3.5230 train_time:359205ms step_avg:216.39ms step:1671/6200 train_loss:3.5262 train_time:359418ms step_avg:216.39ms step:1672/6200 train_loss:3.6871 train_time:359633ms step_avg:216.39ms step:1673/6200 train_loss:3.8527 train_time:359847ms step_avg:216.38ms step:1674/6200 train_loss:3.5797 train_time:360060ms step_avg:216.38ms step:1675/6200 train_loss:3.5685 train_time:360274ms step_avg:216.38ms step:1676/6200 train_loss:3.4532 train_time:360488ms step_avg:216.38ms step:1677/6200 train_loss:3.6559 train_time:360701ms step_avg:216.38ms step:1678/6200 train_loss:3.5705 train_time:360913ms step_avg:216.37ms step:1679/6200 train_loss:3.5999 train_time:361128ms step_avg:216.37ms step:1680/6200 train_loss:3.5786 train_time:361341ms step_avg:216.37ms step:1681/6200 train_loss:3.4411 train_time:361555ms step_avg:216.37ms step:1682/6200 train_loss:3.5860 train_time:361770ms step_avg:216.37ms step:1683/6200 train_loss:3.6027 train_time:361983ms step_avg:216.37ms step:1684/6200 train_loss:3.6398 train_time:362196ms step_avg:216.37ms step:1685/6200 train_loss:3.6497 train_time:362410ms step_avg:216.36ms step:1686/6200 train_loss:3.5601 train_time:362623ms step_avg:216.36ms step:1687/6200 train_loss:3.6557 train_time:362836ms step_avg:216.36ms step:1688/6200 train_loss:3.5413 train_time:363050ms step_avg:216.36ms step:1689/6200 train_loss:3.6330 train_time:363264ms step_avg:216.36ms step:1690/6200 train_loss:3.5421 train_time:363479ms step_avg:216.36ms step:1691/6200 train_loss:3.4462 train_time:363691ms step_avg:216.35ms step:1692/6200 train_loss:3.5909 train_time:363905ms step_avg:216.35ms step:1693/6200 train_loss:3.5870 train_time:364118ms step_avg:216.35ms step:1694/6200 train_loss:3.5076 train_time:364331ms step_avg:216.35ms step:1695/6200 train_loss:3.9515 train_time:364545ms step_avg:216.35ms step:1696/6200 train_loss:3.6667 train_time:364759ms step_avg:216.35ms step:1697/6200 train_loss:3.6430 train_time:364974ms step_avg:216.34ms step:1698/6200 train_loss:3.5494 train_time:365187ms step_avg:216.34ms step:1699/6200 train_loss:3.4639 train_time:365400ms step_avg:216.34ms step:1700/6200 train_loss:3.5595 train_time:365614ms step_avg:216.34ms step:1701/6200 train_loss:3.5475 train_time:366080ms step_avg:216.49ms step:1702/6200 train_loss:3.6176 train_time:366292ms step_avg:216.48ms step:1703/6200 train_loss:3.5465 train_time:366504ms step_avg:216.48ms step:1704/6200 train_loss:3.7519 train_time:366718ms step_avg:216.48ms step:1705/6200 train_loss:3.5180 train_time:366932ms step_avg:216.48ms step:1706/6200 train_loss:3.7437 train_time:367144ms step_avg:216.48ms step:1707/6200 train_loss:3.5928 train_time:367356ms step_avg:216.47ms step:1708/6200 train_loss:3.3583 train_time:367572ms step_avg:216.47ms step:1709/6200 train_loss:3.6967 train_time:367785ms step_avg:216.47ms step:1710/6200 train_loss:3.6092 train_time:368248ms step_avg:216.62ms step:1711/6200 train_loss:3.5987 train_time:368462ms step_avg:216.62ms step:1712/6200 train_loss:3.5887 train_time:368675ms step_avg:216.61ms step:1713/6200 train_loss:3.6323 train_time:368889ms step_avg:216.61ms step:1714/6200 train_loss:3.6525 train_time:369101ms step_avg:216.61ms step:1715/6200 train_loss:3.5822 train_time:369314ms step_avg:216.61ms step:1716/6200 train_loss:3.5736 train_time:369528ms step_avg:216.60ms step:1717/6200 train_loss:3.4175 train_time:369741ms step_avg:216.60ms step:1718/6200 train_loss:3.5500 train_time:369954ms step_avg:216.60ms step:1719/6200 train_loss:3.5810 train_time:370169ms step_avg:216.60ms step:1720/6200 train_loss:3.5222 train_time:370381ms step_avg:216.60ms step:1721/6200 train_loss:3.6734 train_time:370594ms step_avg:216.59ms step:1722/6200 train_loss:3.4823 train_time:370808ms step_avg:216.59ms step:1723/6200 train_loss:3.6179 train_time:371020ms step_avg:216.59ms step:1724/6200 train_loss:3.7078 train_time:371234ms step_avg:216.59ms step:1725/6200 train_loss:3.5590 train_time:371448ms step_avg:216.59ms step:1726/6200 train_loss:3.7867 train_time:371661ms step_avg:216.59ms step:1727/6200 train_loss:3.5917 train_time:371874ms step_avg:216.58ms step:1728/6200 train_loss:3.6380 train_time:372090ms step_avg:216.58ms step:1729/6200 train_loss:3.6121 train_time:372302ms step_avg:216.58ms step:1730/6200 train_loss:3.6213 train_time:372515ms step_avg:216.58ms step:1731/6200 train_loss:3.9929 train_time:372729ms step_avg:216.58ms step:1732/6200 train_loss:3.6015 train_time:372944ms step_avg:216.58ms step:1733/6200 train_loss:3.7251 train_time:373158ms step_avg:216.57ms step:1734/6200 train_loss:3.5040 train_time:373372ms step_avg:216.57ms step:1735/6200 train_loss:3.5483 train_time:373585ms step_avg:216.57ms step:1736/6200 train_loss:3.5702 train_time:373798ms step_avg:216.57ms step:1737/6200 train_loss:3.5527 train_time:374012ms step_avg:216.57ms step:1738/6200 train_loss:3.6961 train_time:374226ms step_avg:216.57ms step:1739/6200 train_loss:3.5639 train_time:374439ms step_avg:216.56ms step:1740/6200 train_loss:3.6333 train_time:374653ms step_avg:216.56ms step:1741/6200 train_loss:3.6732 train_time:374867ms step_avg:216.56ms step:1742/6200 train_loss:3.4737 train_time:375080ms step_avg:216.56ms step:1743/6200 train_loss:3.3667 train_time:375292ms step_avg:216.56ms step:1744/6200 train_loss:3.3201 train_time:375506ms step_avg:216.55ms step:1745/6200 train_loss:3.5953 train_time:375720ms step_avg:216.55ms step:1746/6200 train_loss:3.6085 train_time:375934ms step_avg:216.55ms step:1747/6200 train_loss:3.5792 train_time:376148ms step_avg:216.55ms step:1748/6200 train_loss:3.5833 train_time:376361ms step_avg:216.55ms step:1749/6200 train_loss:3.8389 train_time:376574ms step_avg:216.55ms step:1750/6200 train_loss:3.5429 train_time:376788ms step_avg:216.54ms step:1750/6200 val_loss:3.5922 train_time:376789ms step_avg:216.55ms step:1751/6200 train_loss:3.6127 train_time:377006ms step_avg:216.55ms step:1752/6200 train_loss:3.6010 train_time:377219ms step_avg:216.54ms step:1753/6200 train_loss:3.2382 train_time:377433ms step_avg:216.54ms step:1754/6200 train_loss:3.3641 train_time:377647ms step_avg:216.54ms step:1755/6200 train_loss:3.4675 train_time:377863ms step_avg:216.54ms step:1756/6200 train_loss:3.4044 train_time:378077ms step_avg:216.54ms step:1757/6200 train_loss:3.5662 train_time:378289ms step_avg:216.54ms step:1758/6200 train_loss:3.4433 train_time:378505ms step_avg:216.54ms step:1759/6200 train_loss:3.4380 train_time:378719ms step_avg:216.53ms step:1760/6200 train_loss:4.4901 train_time:378932ms step_avg:216.53ms step:1761/6200 train_loss:3.5734 train_time:379146ms step_avg:216.53ms step:1762/6200 train_loss:3.6012 train_time:379360ms step_avg:216.53ms step:1763/6200 train_loss:3.6050 train_time:379573ms step_avg:216.53ms step:1764/6200 train_loss:3.6280 train_time:379787ms step_avg:216.53ms step:1765/6200 train_loss:3.5343 train_time:380002ms step_avg:216.53ms step:1766/6200 train_loss:3.5791 train_time:380213ms step_avg:216.52ms step:1767/6200 train_loss:3.6007 train_time:380427ms step_avg:216.52ms step:1768/6200 train_loss:3.8528 train_time:380641ms step_avg:216.52ms step:1769/6200 train_loss:3.5788 train_time:380855ms step_avg:216.52ms step:1770/6200 train_loss:3.6452 train_time:381069ms step_avg:216.52ms step:1771/6200 train_loss:3.9944 train_time:381285ms step_avg:216.52ms step:1772/6200 train_loss:3.5871 train_time:381498ms step_avg:216.51ms step:1773/6200 train_loss:3.4798 train_time:381710ms step_avg:216.51ms step:1774/6200 train_loss:3.7403 train_time:381925ms step_avg:216.51ms step:1775/6200 train_loss:3.4764 train_time:382139ms step_avg:216.51ms step:1776/6200 train_loss:3.6391 train_time:382351ms step_avg:216.51ms step:1777/6200 train_loss:3.6967 train_time:382570ms step_avg:216.51ms step:1778/6200 train_loss:3.7763 train_time:382784ms step_avg:216.51ms step:1779/6200 train_loss:3.5928 train_time:382998ms step_avg:216.51ms step:1780/6200 train_loss:3.8724 train_time:383211ms step_avg:216.50ms step:1781/6200 train_loss:3.6623 train_time:383424ms step_avg:216.50ms step:1782/6200 train_loss:3.6774 train_time:383637ms step_avg:216.50ms step:1783/6200 train_loss:3.4605 train_time:383852ms step_avg:216.50ms step:1784/6200 train_loss:3.5372 train_time:384066ms step_avg:216.50ms step:1785/6200 train_loss:3.6784 train_time:384280ms step_avg:216.50ms step:1786/6200 train_loss:3.5695 train_time:384494ms step_avg:216.49ms step:1787/6200 train_loss:3.7467 train_time:384706ms step_avg:216.49ms step:1788/6200 train_loss:3.5577 train_time:384919ms step_avg:216.49ms step:1789/6200 train_loss:3.5373 train_time:385133ms step_avg:216.49ms step:1790/6200 train_loss:3.6789 train_time:385350ms step_avg:216.49ms step:1791/6200 train_loss:3.5722 train_time:385566ms step_avg:216.49ms step:1792/6200 train_loss:3.5266 train_time:385780ms step_avg:216.49ms step:1793/6200 train_loss:3.6550 train_time:385993ms step_avg:216.49ms step:1794/6200 train_loss:3.5341 train_time:386205ms step_avg:216.48ms step:1795/6200 train_loss:3.5255 train_time:386419ms step_avg:216.48ms step:1796/6200 train_loss:3.5756 train_time:386632ms step_avg:216.48ms step:1797/6200 train_loss:3.5503 train_time:386847ms step_avg:216.48ms step:1798/6200 train_loss:3.6826 train_time:387062ms step_avg:216.48ms step:1799/6200 train_loss:3.5589 train_time:387276ms step_avg:216.48ms step:1800/6200 train_loss:3.6391 train_time:387489ms step_avg:216.47ms step:1801/6200 train_loss:3.5740 train_time:387703ms step_avg:216.47ms step:1802/6200 train_loss:3.6063 train_time:387916ms step_avg:216.47ms step:1803/6200 train_loss:3.5365 train_time:388130ms step_avg:216.47ms step:1804/6200 train_loss:3.4550 train_time:388344ms step_avg:216.47ms step:1805/6200 train_loss:3.6974 train_time:388558ms step_avg:216.47ms step:1806/6200 train_loss:3.6157 train_time:388771ms step_avg:216.47ms step:1807/6200 train_loss:3.6273 train_time:388987ms step_avg:216.46ms step:1808/6200 train_loss:3.7388 train_time:389202ms step_avg:216.46ms step:1809/6200 train_loss:3.5370 train_time:389414ms step_avg:216.46ms step:1810/6200 train_loss:3.6406 train_time:389629ms step_avg:216.46ms step:1811/6200 train_loss:3.7759 train_time:389846ms step_avg:216.46ms step:1812/6200 train_loss:3.6292 train_time:390059ms step_avg:216.46ms step:1813/6200 train_loss:3.6701 train_time:390273ms step_avg:216.46ms step:1814/6200 train_loss:3.6921 train_time:390487ms step_avg:216.46ms step:1815/6200 train_loss:3.6352 train_time:390703ms step_avg:216.46ms step:1816/6200 train_loss:3.6756 train_time:390915ms step_avg:216.45ms step:1817/6200 train_loss:3.6226 train_time:391129ms step_avg:216.45ms step:1818/6200 train_loss:3.6781 train_time:391343ms step_avg:216.45ms step:1819/6200 train_loss:3.6073 train_time:391556ms step_avg:216.45ms step:1820/6200 train_loss:3.5962 train_time:391770ms step_avg:216.45ms step:1821/6200 train_loss:3.5431 train_time:391985ms step_avg:216.45ms step:1822/6200 train_loss:3.5280 train_time:392199ms step_avg:216.45ms step:1823/6200 train_loss:3.4482 train_time:392411ms step_avg:216.44ms step:1824/6200 train_loss:3.6062 train_time:392627ms step_avg:216.44ms step:1825/6200 train_loss:3.7276 train_time:392840ms step_avg:216.44ms step:1826/6200 train_loss:3.6828 train_time:393054ms step_avg:216.44ms step:1827/6200 train_loss:3.6640 train_time:393268ms step_avg:216.44ms step:1828/6200 train_loss:3.5322 train_time:393483ms step_avg:216.44ms step:1829/6200 train_loss:3.5663 train_time:393696ms step_avg:216.44ms step:1830/6200 train_loss:3.6851 train_time:393909ms step_avg:216.43ms step:1831/6200 train_loss:3.4660 train_time:394123ms step_avg:216.43ms step:1832/6200 train_loss:3.6207 train_time:394335ms step_avg:216.43ms step:1833/6200 train_loss:3.4934 train_time:394549ms step_avg:216.43ms step:1834/6200 train_loss:3.8109 train_time:394763ms step_avg:216.43ms step:1835/6200 train_loss:3.6482 train_time:394976ms step_avg:216.42ms step:1836/6200 train_loss:3.6336 train_time:395192ms step_avg:216.43ms step:1837/6200 train_loss:3.7547 train_time:395404ms step_avg:216.42ms step:1838/6200 train_loss:3.6124 train_time:395618ms step_avg:216.42ms step:1839/6200 train_loss:3.4917 train_time:395833ms step_avg:216.42ms step:1840/6200 train_loss:3.6209 train_time:396046ms step_avg:216.42ms step:1841/6200 train_loss:3.5020 train_time:396261ms step_avg:216.42ms step:1842/6200 train_loss:3.6053 train_time:396475ms step_avg:216.42ms step:1843/6200 train_loss:3.6720 train_time:396687ms step_avg:216.41ms step:1844/6200 train_loss:3.4196 train_time:396901ms step_avg:216.41ms step:1845/6200 train_loss:3.5397 train_time:397113ms step_avg:216.41ms step:1846/6200 train_loss:3.5934 train_time:397326ms step_avg:216.41ms step:1847/6200 train_loss:3.5449 train_time:397541ms step_avg:216.41ms step:1848/6200 train_loss:3.4394 train_time:397755ms step_avg:216.41ms step:1849/6200 train_loss:3.7023 train_time:397968ms step_avg:216.40ms step:1850/6200 train_loss:3.4761 train_time:398183ms step_avg:216.40ms step:1851/6200 train_loss:3.5600 train_time:398396ms step_avg:216.40ms step:1852/6200 train_loss:3.5177 train_time:398608ms step_avg:216.40ms step:1853/6200 train_loss:3.7156 train_time:398821ms step_avg:216.40ms step:1854/6200 train_loss:3.6972 train_time:399034ms step_avg:216.40ms step:1855/6200 train_loss:3.5662 train_time:399247ms step_avg:216.39ms step:1856/6200 train_loss:3.5251 train_time:399462ms step_avg:216.39ms step:1857/6200 train_loss:3.5495 train_time:399675ms step_avg:216.39ms step:1858/6200 train_loss:3.7992 train_time:399889ms step_avg:216.39ms step:1859/6200 train_loss:3.6366 train_time:400102ms step_avg:216.39ms step:1860/6200 train_loss:3.5717 train_time:400315ms step_avg:216.39ms step:1861/6200 train_loss:3.6180 train_time:400528ms step_avg:216.38ms step:1862/6200 train_loss:3.5166 train_time:400742ms step_avg:216.38ms step:1863/6200 train_loss:3.5071 train_time:400956ms step_avg:216.38ms step:1864/6200 train_loss:3.5805 train_time:401170ms step_avg:216.38ms step:1865/6200 train_loss:3.6198 train_time:401385ms step_avg:216.38ms step:1866/6200 train_loss:3.3800 train_time:401601ms step_avg:216.38ms step:1867/6200 train_loss:3.5083 train_time:401815ms step_avg:216.38ms step:1868/6200 train_loss:3.4653 train_time:402028ms step_avg:216.38ms step:1869/6200 train_loss:3.4638 train_time:402242ms step_avg:216.38ms step:1870/6200 train_loss:3.6268 train_time:402455ms step_avg:216.37ms step:1871/6200 train_loss:3.6116 train_time:402668ms step_avg:216.37ms step:1872/6200 train_loss:3.5652 train_time:402885ms step_avg:216.37ms step:1873/6200 train_loss:3.5668 train_time:403097ms step_avg:216.37ms step:1874/6200 train_loss:3.5040 train_time:403308ms step_avg:216.37ms step:1875/6200 train_loss:3.6030 train_time:403522ms step_avg:216.37ms step:1875/6200 val_loss:3.5770 train_time:403524ms step_avg:216.37ms step:1876/6200 train_loss:3.5974 train_time:403741ms step_avg:216.37ms step:1877/6200 train_loss:3.5239 train_time:403956ms step_avg:216.37ms step:1878/6200 train_loss:3.5704 train_time:404169ms step_avg:216.36ms step:1879/6200 train_loss:3.6696 train_time:404383ms step_avg:216.36ms step:1880/6200 train_loss:3.5607 train_time:404598ms step_avg:216.36ms step:1881/6200 train_loss:3.6153 train_time:404812ms step_avg:216.36ms step:1882/6200 train_loss:3.5293 train_time:405024ms step_avg:216.36ms step:1883/6200 train_loss:3.6001 train_time:405238ms step_avg:216.36ms step:1884/6200 train_loss:3.5964 train_time:405451ms step_avg:216.36ms step:1885/6200 train_loss:3.3482 train_time:405665ms step_avg:216.35ms step:1886/6200 train_loss:3.7584 train_time:405879ms step_avg:216.35ms step:1887/6200 train_loss:3.4834 train_time:406095ms step_avg:216.35ms step:1888/6200 train_loss:3.5111 train_time:406308ms step_avg:216.35ms step:1889/6200 train_loss:3.5668 train_time:406520ms step_avg:216.35ms step:1890/6200 train_loss:3.6147 train_time:406989ms step_avg:216.48ms step:1891/6200 train_loss:3.4419 train_time:407203ms step_avg:216.48ms step:1892/6200 train_loss:3.7176 train_time:407417ms step_avg:216.48ms step:1893/6200 train_loss:3.4853 train_time:407629ms step_avg:216.48ms step:1894/6200 train_loss:3.5930 train_time:407842ms step_avg:216.48ms step:1895/6200 train_loss:3.6461 train_time:408057ms step_avg:216.48ms step:1896/6200 train_loss:3.4421 train_time:408271ms step_avg:216.47ms step:1897/6200 train_loss:3.5998 train_time:408486ms step_avg:216.47ms step:1898/6200 train_loss:3.5674 train_time:408700ms step_avg:216.47ms step:1899/6200 train_loss:3.6465 train_time:408914ms step_avg:216.47ms step:1900/6200 train_loss:3.4325 train_time:409378ms step_avg:216.60ms step:1901/6200 train_loss:3.6634 train_time:409591ms step_avg:216.60ms step:1902/6200 train_loss:3.5515 train_time:409804ms step_avg:216.60ms step:1903/6200 train_loss:3.7112 train_time:410017ms step_avg:216.60ms step:1904/6200 train_loss:3.5176 train_time:410229ms step_avg:216.59ms step:1905/6200 train_loss:3.7910 train_time:410444ms step_avg:216.59ms step:1906/6200 train_loss:3.5295 train_time:410658ms step_avg:216.59ms step:1907/6200 train_loss:3.5217 train_time:410872ms step_avg:216.59ms step:1908/6200 train_loss:3.5978 train_time:411086ms step_avg:216.59ms step:1909/6200 train_loss:3.4848 train_time:411299ms step_avg:216.59ms step:1910/6200 train_loss:3.5478 train_time:411512ms step_avg:216.59ms step:1911/6200 train_loss:3.6472 train_time:411724ms step_avg:216.58ms step:1912/6200 train_loss:3.5624 train_time:411937ms step_avg:216.58ms step:1913/6200 train_loss:3.4398 train_time:412151ms step_avg:216.58ms step:1914/6200 train_loss:3.3270 train_time:412370ms step_avg:216.58ms step:1915/6200 train_loss:3.5151 train_time:412583ms step_avg:216.58ms step:1916/6200 train_loss:3.7386 train_time:412799ms step_avg:216.58ms step:1917/6200 train_loss:3.7257 train_time:413011ms step_avg:216.58ms step:1918/6200 train_loss:3.6833 train_time:413223ms step_avg:216.57ms step:1919/6200 train_loss:3.5105 train_time:413437ms step_avg:216.57ms step:1920/6200 train_loss:3.7576 train_time:413650ms step_avg:216.57ms step:1921/6200 train_loss:3.5746 train_time:413863ms step_avg:216.57ms step:1922/6200 train_loss:3.5070 train_time:414078ms step_avg:216.57ms step:1923/6200 train_loss:3.6851 train_time:414291ms step_avg:216.57ms step:1924/6200 train_loss:3.6502 train_time:414504ms step_avg:216.56ms step:1925/6200 train_loss:3.4865 train_time:414717ms step_avg:216.56ms step:1926/6200 train_loss:3.5186 train_time:414930ms step_avg:216.56ms step:1927/6200 train_loss:3.4326 train_time:415144ms step_avg:216.56ms step:1928/6200 train_loss:3.5410 train_time:415357ms step_avg:216.56ms step:1929/6200 train_loss:3.4049 train_time:415571ms step_avg:216.56ms step:1930/6200 train_loss:3.5099 train_time:415784ms step_avg:216.55ms step:1931/6200 train_loss:3.6458 train_time:415998ms step_avg:216.55ms step:1932/6200 train_loss:3.5156 train_time:416212ms step_avg:216.55ms step:1933/6200 train_loss:3.6575 train_time:416424ms step_avg:216.55ms step:1934/6200 train_loss:3.5277 train_time:416637ms step_avg:216.55ms step:1935/6200 train_loss:3.5783 train_time:416850ms step_avg:216.55ms step:1936/6200 train_loss:3.6155 train_time:417063ms step_avg:216.54ms step:1937/6200 train_loss:3.5607 train_time:417277ms step_avg:216.54ms step:1938/6200 train_loss:3.5978 train_time:417488ms step_avg:216.54ms step:1939/6200 train_loss:3.5223 train_time:417701ms step_avg:216.54ms step:1940/6200 train_loss:3.6286 train_time:417914ms step_avg:216.54ms step:1941/6200 train_loss:3.6528 train_time:418126ms step_avg:216.53ms step:1942/6200 train_loss:3.4906 train_time:418339ms step_avg:216.53ms step:1943/6200 train_loss:3.5225 train_time:418552ms step_avg:216.53ms step:1944/6200 train_loss:3.5974 train_time:418765ms step_avg:216.53ms step:1945/6200 train_loss:3.4353 train_time:418979ms step_avg:216.53ms step:1946/6200 train_loss:3.7024 train_time:419193ms step_avg:216.53ms step:1947/6200 train_loss:3.5811 train_time:419406ms step_avg:216.52ms step:1948/6200 train_loss:3.5614 train_time:419619ms step_avg:216.52ms step:1949/6200 train_loss:3.5614 train_time:419832ms step_avg:216.52ms step:1950/6200 train_loss:3.4442 train_time:420045ms step_avg:216.52ms step:1951/6200 train_loss:3.5639 train_time:420259ms step_avg:216.52ms step:1952/6200 train_loss:3.4051 train_time:420473ms step_avg:216.52ms step:1953/6200 train_loss:3.6136 train_time:420686ms step_avg:216.51ms step:1954/6200 train_loss:3.6138 train_time:420899ms step_avg:216.51ms step:1955/6200 train_loss:3.5644 train_time:421112ms step_avg:216.51ms step:1956/6200 train_loss:3.4545 train_time:421324ms step_avg:216.51ms step:1957/6200 train_loss:3.5423 train_time:421537ms step_avg:216.51ms step:1958/6200 train_loss:3.7251 train_time:421751ms step_avg:216.50ms step:1959/6200 train_loss:3.6460 train_time:421964ms step_avg:216.50ms step:1960/6200 train_loss:3.6698 train_time:422179ms step_avg:216.50ms step:1961/6200 train_loss:3.4648 train_time:422391ms step_avg:216.50ms step:1962/6200 train_loss:3.5861 train_time:422604ms step_avg:216.50ms step:1963/6200 train_loss:3.6353 train_time:422816ms step_avg:216.50ms step:1964/6200 train_loss:3.5857 train_time:423028ms step_avg:216.49ms step:1965/6200 train_loss:3.4899 train_time:423240ms step_avg:216.49ms step:1966/6200 train_loss:3.8977 train_time:423454ms step_avg:216.49ms step:1967/6200 train_loss:3.5107 train_time:423667ms step_avg:216.49ms step:1968/6200 train_loss:3.5451 train_time:423880ms step_avg:216.49ms step:1969/6200 train_loss:3.5949 train_time:424094ms step_avg:216.48ms step:1970/6200 train_loss:3.5581 train_time:424307ms step_avg:216.48ms step:1971/6200 train_loss:3.4476 train_time:424518ms step_avg:216.48ms step:1972/6200 train_loss:3.4299 train_time:424731ms step_avg:216.48ms step:1973/6200 train_loss:3.5424 train_time:424944ms step_avg:216.48ms step:1974/6200 train_loss:3.5173 train_time:425159ms step_avg:216.48ms step:1975/6200 train_loss:3.4931 train_time:425372ms step_avg:216.47ms step:1976/6200 train_loss:3.6441 train_time:425585ms step_avg:216.47ms step:1977/6200 train_loss:3.5168 train_time:425801ms step_avg:216.47ms step:1978/6200 train_loss:3.8917 train_time:426014ms step_avg:216.47ms step:1979/6200 train_loss:3.5649 train_time:426227ms step_avg:216.47ms step:1980/6200 train_loss:3.5679 train_time:426442ms step_avg:216.47ms step:1981/6200 train_loss:3.5737 train_time:426656ms step_avg:216.47ms step:1982/6200 train_loss:3.6020 train_time:426869ms step_avg:216.47ms step:1983/6200 train_loss:3.5284 train_time:427082ms step_avg:216.46ms step:1984/6200 train_loss:3.4911 train_time:427297ms step_avg:216.46ms step:1985/6200 train_loss:3.5442 train_time:427510ms step_avg:216.46ms step:1986/6200 train_loss:3.6122 train_time:427722ms step_avg:216.46ms step:1987/6200 train_loss:3.5930 train_time:427935ms step_avg:216.46ms step:1988/6200 train_loss:3.5495 train_time:428150ms step_avg:216.46ms step:1989/6200 train_loss:3.6395 train_time:428362ms step_avg:216.45ms step:1990/6200 train_loss:3.6709 train_time:428576ms step_avg:216.45ms step:1991/6200 train_loss:3.4458 train_time:428790ms step_avg:216.45ms step:1992/6200 train_loss:3.4471 train_time:429001ms step_avg:216.45ms step:1993/6200 train_loss:3.6355 train_time:429216ms step_avg:216.45ms step:1994/6200 train_loss:3.4565 train_time:429428ms step_avg:216.45ms step:1995/6200 train_loss:3.5457 train_time:429640ms step_avg:216.44ms step:1996/6200 train_loss:3.6170 train_time:429853ms step_avg:216.44ms step:1997/6200 train_loss:3.4735 train_time:430065ms step_avg:216.44ms step:1998/6200 train_loss:3.5836 train_time:430284ms step_avg:216.44ms step:1999/6200 train_loss:3.5821 train_time:430498ms step_avg:216.44ms step:2000/6200 train_loss:3.5081 train_time:430711ms step_avg:216.44ms step:2000/6200 val_loss:3.5608 train_time:430713ms step_avg:216.44ms step:2001/6200 train_loss:3.6465 train_time:430929ms step_avg:216.44ms step:2002/6200 train_loss:3.5928 train_time:431142ms step_avg:216.44ms step:2003/6200 train_loss:3.6803 train_time:431355ms step_avg:216.44ms step:2004/6200 train_loss:3.5962 train_time:431569ms step_avg:216.43ms step:2005/6200 train_loss:3.6184 train_time:431783ms step_avg:216.43ms step:2006/6200 train_loss:3.5037 train_time:431997ms step_avg:216.43ms step:2007/6200 train_loss:3.5267 train_time:432211ms step_avg:216.43ms step:2008/6200 train_loss:3.5642 train_time:432425ms step_avg:216.43ms step:2009/6200 train_loss:3.6132 train_time:432639ms step_avg:216.43ms step:2010/6200 train_loss:3.5127 train_time:432851ms step_avg:216.43ms step:2011/6200 train_loss:3.5930 train_time:433065ms step_avg:216.42ms step:2012/6200 train_loss:3.5607 train_time:433280ms step_avg:216.42ms step:2013/6200 train_loss:3.5768 train_time:433493ms step_avg:216.42ms step:2014/6200 train_loss:3.4990 train_time:433707ms step_avg:216.42ms step:2015/6200 train_loss:3.5345 train_time:433922ms step_avg:216.42ms step:2016/6200 train_loss:3.5458 train_time:434137ms step_avg:216.42ms step:2017/6200 train_loss:3.6888 train_time:434349ms step_avg:216.42ms step:2018/6200 train_loss:3.5263 train_time:434563ms step_avg:216.42ms step:2019/6200 train_loss:3.7011 train_time:434777ms step_avg:216.41ms step:2020/6200 train_loss:3.6902 train_time:434991ms step_avg:216.41ms step:2021/6200 train_loss:3.4069 train_time:435204ms step_avg:216.41ms step:2022/6200 train_loss:3.6367 train_time:435418ms step_avg:216.41ms step:2023/6200 train_loss:3.5560 train_time:435632ms step_avg:216.41ms step:2024/6200 train_loss:3.6550 train_time:435844ms step_avg:216.41ms step:2025/6200 train_loss:3.7028 train_time:436056ms step_avg:216.41ms step:2026/6200 train_loss:3.4883 train_time:436269ms step_avg:216.40ms step:2027/6200 train_loss:3.5241 train_time:436484ms step_avg:216.40ms step:2028/6200 train_loss:3.4292 train_time:436698ms step_avg:216.40ms step:2029/6200 train_loss:3.5450 train_time:436911ms step_avg:216.40ms step:2030/6200 train_loss:3.4605 train_time:437125ms step_avg:216.40ms step:2031/6200 train_loss:3.5489 train_time:437338ms step_avg:216.40ms step:2032/6200 train_loss:3.5450 train_time:437550ms step_avg:216.39ms step:2033/6200 train_loss:3.5611 train_time:437764ms step_avg:216.39ms step:2034/6200 train_loss:3.4550 train_time:437977ms step_avg:216.39ms step:2035/6200 train_loss:3.6178 train_time:438190ms step_avg:216.39ms step:2036/6200 train_loss:3.6154 train_time:438404ms step_avg:216.39ms step:2037/6200 train_loss:3.6107 train_time:438618ms step_avg:216.39ms step:2038/6200 train_loss:3.4763 train_time:438831ms step_avg:216.39ms step:2039/6200 train_loss:3.7353 train_time:439043ms step_avg:216.38ms step:2040/6200 train_loss:3.5695 train_time:439256ms step_avg:216.38ms step:2041/6200 train_loss:3.5907 train_time:439469ms step_avg:216.38ms step:2042/6200 train_loss:3.5337 train_time:439683ms step_avg:216.38ms step:2043/6200 train_loss:3.4365 train_time:439897ms step_avg:216.38ms step:2044/6200 train_loss:3.5623 train_time:440111ms step_avg:216.38ms step:2045/6200 train_loss:3.5628 train_time:440325ms step_avg:216.38ms step:2046/6200 train_loss:3.4215 train_time:440538ms step_avg:216.37ms step:2047/6200 train_loss:3.4949 train_time:440750ms step_avg:216.37ms step:2048/6200 train_loss:3.5765 train_time:440964ms step_avg:216.37ms step:2049/6200 train_loss:3.5187 train_time:441178ms step_avg:216.37ms step:2050/6200 train_loss:3.5628 train_time:441392ms step_avg:216.37ms step:2051/6200 train_loss:3.7173 train_time:441606ms step_avg:216.37ms step:2052/6200 train_loss:3.5867 train_time:441821ms step_avg:216.37ms step:2053/6200 train_loss:3.5331 train_time:442033ms step_avg:216.36ms step:2054/6200 train_loss:3.5169 train_time:442246ms step_avg:216.36ms step:2055/6200 train_loss:3.3837 train_time:442459ms step_avg:216.36ms step:2056/6200 train_loss:3.4936 train_time:442672ms step_avg:216.36ms step:2057/6200 train_loss:3.6745 train_time:442886ms step_avg:216.36ms step:2058/6200 train_loss:3.6887 train_time:443100ms step_avg:216.36ms step:2059/6200 train_loss:3.5529 train_time:443314ms step_avg:216.36ms step:2060/6200 train_loss:3.5976 train_time:443526ms step_avg:216.35ms step:2061/6200 train_loss:3.5833 train_time:443740ms step_avg:216.35ms step:2062/6200 train_loss:3.5326 train_time:443952ms step_avg:216.35ms step:2063/6200 train_loss:3.4425 train_time:444165ms step_avg:216.35ms step:2064/6200 train_loss:3.7578 train_time:444379ms step_avg:216.35ms step:2065/6200 train_loss:3.6216 train_time:444592ms step_avg:216.35ms step:2066/6200 train_loss:3.5631 train_time:444806ms step_avg:216.35ms step:2067/6200 train_loss:3.6065 train_time:445021ms step_avg:216.34ms step:2068/6200 train_loss:3.5072 train_time:445235ms step_avg:216.34ms step:2069/6200 train_loss:3.5638 train_time:445447ms step_avg:216.34ms step:2070/6200 train_loss:3.7055 train_time:445661ms step_avg:216.34ms step:2071/6200 train_loss:3.7007 train_time:445874ms step_avg:216.34ms step:2072/6200 train_loss:3.5564 train_time:446087ms step_avg:216.34ms step:2073/6200 train_loss:3.5856 train_time:446302ms step_avg:216.34ms step:2074/6200 train_loss:3.4787 train_time:446516ms step_avg:216.34ms step:2075/6200 train_loss:4.0006 train_time:446729ms step_avg:216.33ms step:2076/6200 train_loss:3.4331 train_time:446943ms step_avg:216.33ms step:2077/6200 train_loss:3.5969 train_time:447155ms step_avg:216.33ms step:2078/6200 train_loss:3.4870 train_time:447368ms step_avg:216.33ms step:2079/6200 train_loss:3.4626 train_time:447837ms step_avg:216.45ms step:2080/6200 train_loss:3.5529 train_time:448050ms step_avg:216.45ms step:2081/6200 train_loss:3.8149 train_time:448263ms step_avg:216.45ms step:2082/6200 train_loss:3.4361 train_time:448477ms step_avg:216.45ms step:2083/6200 train_loss:3.7756 train_time:448690ms step_avg:216.44ms step:2084/6200 train_loss:3.4786 train_time:448904ms step_avg:216.44ms step:2085/6200 train_loss:3.4598 train_time:449122ms step_avg:216.44ms step:2086/6200 train_loss:3.7070 train_time:449336ms step_avg:216.44ms step:2087/6200 train_loss:3.6355 train_time:449548ms step_avg:216.44ms step:2088/6200 train_loss:3.6181 train_time:449762ms step_avg:216.44ms step:2089/6200 train_loss:3.6792 train_time:449975ms step_avg:216.44ms step:2090/6200 train_loss:3.5954 train_time:450437ms step_avg:216.56ms step:2091/6200 train_loss:3.5910 train_time:450648ms step_avg:216.55ms step:2092/6200 train_loss:3.5433 train_time:450862ms step_avg:216.55ms step:2093/6200 train_loss:3.6124 train_time:451075ms step_avg:216.55ms step:2094/6200 train_loss:3.5064 train_time:451289ms step_avg:216.55ms step:2095/6200 train_loss:3.3162 train_time:451503ms step_avg:216.55ms step:2096/6200 train_loss:3.5378 train_time:451717ms step_avg:216.55ms step:2097/6200 train_loss:3.7050 train_time:451929ms step_avg:216.55ms step:2098/6200 train_loss:3.5465 train_time:452143ms step_avg:216.54ms step:2099/6200 train_loss:3.4249 train_time:452354ms step_avg:216.54ms step:2100/6200 train_loss:3.5261 train_time:452568ms step_avg:216.54ms step:2101/6200 train_loss:3.4929 train_time:452783ms step_avg:216.54ms step:2102/6200 train_loss:3.6317 train_time:452996ms step_avg:216.54ms step:2103/6200 train_loss:3.4637 train_time:453210ms step_avg:216.54ms step:2104/6200 train_loss:3.4278 train_time:453425ms step_avg:216.54ms step:2105/6200 train_loss:3.6852 train_time:453638ms step_avg:216.53ms step:2106/6200 train_loss:3.4331 train_time:453851ms step_avg:216.53ms step:2107/6200 train_loss:3.8169 train_time:454064ms step_avg:216.53ms step:2108/6200 train_loss:3.6524 train_time:454277ms step_avg:216.53ms step:2109/6200 train_loss:3.5632 train_time:454490ms step_avg:216.53ms step:2110/6200 train_loss:3.5748 train_time:454704ms step_avg:216.53ms step:2111/6200 train_loss:3.4015 train_time:454918ms step_avg:216.52ms step:2112/6200 train_loss:3.8816 train_time:455132ms step_avg:216.52ms step:2113/6200 train_loss:3.5769 train_time:455344ms step_avg:216.52ms step:2114/6200 train_loss:3.4995 train_time:455557ms step_avg:216.52ms step:2115/6200 train_loss:3.6181 train_time:455771ms step_avg:216.52ms step:2116/6200 train_loss:3.5804 train_time:455985ms step_avg:216.52ms step:2117/6200 train_loss:3.5581 train_time:456198ms step_avg:216.52ms step:2118/6200 train_loss:3.6151 train_time:456412ms step_avg:216.51ms step:2119/6200 train_loss:3.4704 train_time:456626ms step_avg:216.51ms step:2120/6200 train_loss:3.5281 train_time:456839ms step_avg:216.51ms step:2121/6200 train_loss:3.2393 train_time:457051ms step_avg:216.51ms step:2122/6200 train_loss:3.4461 train_time:457265ms step_avg:216.51ms step:2123/6200 train_loss:3.6004 train_time:457480ms step_avg:216.51ms step:2124/6200 train_loss:3.5176 train_time:457692ms step_avg:216.51ms step:2125/6200 train_loss:3.6729 train_time:457906ms step_avg:216.50ms step:2125/6200 val_loss:3.5486 train_time:457907ms step_avg:216.50ms step:2126/6200 train_loss:3.5292 train_time:458124ms step_avg:216.50ms step:2127/6200 train_loss:3.6512 train_time:458337ms step_avg:216.50ms step:2128/6200 train_loss:3.6304 train_time:458552ms step_avg:216.50ms step:2129/6200 train_loss:3.5233 train_time:458764ms step_avg:216.50ms step:2130/6200 train_loss:3.4640 train_time:458976ms step_avg:216.50ms step:2131/6200 train_loss:3.5020 train_time:459191ms step_avg:216.50ms step:2132/6200 train_loss:3.6545 train_time:459405ms step_avg:216.50ms step:2133/6200 train_loss:3.5351 train_time:459619ms step_avg:216.49ms step:2134/6200 train_loss:3.4401 train_time:459833ms step_avg:216.49ms step:2135/6200 train_loss:3.5105 train_time:460047ms step_avg:216.49ms step:2136/6200 train_loss:3.6298 train_time:460259ms step_avg:216.49ms step:2137/6200 train_loss:3.6401 train_time:460473ms step_avg:216.49ms step:2138/6200 train_loss:3.5896 train_time:460687ms step_avg:216.49ms step:2139/6200 train_loss:3.5708 train_time:460900ms step_avg:216.49ms step:2140/6200 train_loss:3.5606 train_time:461114ms step_avg:216.49ms step:2141/6200 train_loss:3.6417 train_time:461328ms step_avg:216.48ms step:2142/6200 train_loss:3.9529 train_time:461542ms step_avg:216.48ms step:2143/6200 train_loss:3.4712 train_time:461754ms step_avg:216.48ms step:2144/6200 train_loss:3.5100 train_time:461968ms step_avg:216.48ms step:2145/6200 train_loss:3.5485 train_time:462180ms step_avg:216.48ms step:2146/6200 train_loss:3.6715 train_time:462395ms step_avg:216.48ms step:2147/6200 train_loss:3.6036 train_time:462609ms step_avg:216.48ms step:2148/6200 train_loss:4.0132 train_time:462823ms step_avg:216.47ms step:2149/6200 train_loss:3.5286 train_time:463036ms step_avg:216.47ms step:2150/6200 train_loss:3.5093 train_time:463249ms step_avg:216.47ms step:2151/6200 train_loss:3.5609 train_time:463462ms step_avg:216.47ms step:2152/6200 train_loss:3.5959 train_time:463675ms step_avg:216.47ms step:2153/6200 train_loss:3.5559 train_time:463889ms step_avg:216.47ms step:2154/6200 train_loss:3.4868 train_time:464102ms step_avg:216.47ms step:2155/6200 train_loss:3.7032 train_time:464316ms step_avg:216.46ms step:2156/6200 train_loss:3.3236 train_time:464530ms step_avg:216.46ms step:2157/6200 train_loss:3.4797 train_time:464742ms step_avg:216.46ms step:2158/6200 train_loss:3.6214 train_time:464955ms step_avg:216.46ms step:2159/6200 train_loss:3.5540 train_time:465168ms step_avg:216.46ms step:2160/6200 train_loss:3.7167 train_time:465382ms step_avg:216.46ms step:2161/6200 train_loss:3.6324 train_time:465596ms step_avg:216.46ms step:2162/6200 train_loss:3.5552 train_time:465810ms step_avg:216.45ms step:2163/6200 train_loss:3.5181 train_time:466023ms step_avg:216.45ms step:2164/6200 train_loss:3.5279 train_time:466235ms step_avg:216.45ms step:2165/6200 train_loss:3.6085 train_time:466449ms step_avg:216.45ms step:2166/6200 train_loss:3.6289 train_time:466663ms step_avg:216.45ms step:2167/6200 train_loss:3.5624 train_time:466876ms step_avg:216.45ms step:2168/6200 train_loss:3.4561 train_time:467090ms step_avg:216.45ms step:2169/6200 train_loss:3.5374 train_time:467304ms step_avg:216.44ms step:2170/6200 train_loss:3.5814 train_time:467517ms step_avg:216.44ms step:2171/6200 train_loss:3.6987 train_time:467732ms step_avg:216.44ms step:2172/6200 train_loss:3.5019 train_time:467945ms step_avg:216.44ms step:2173/6200 train_loss:3.4908 train_time:468158ms step_avg:216.44ms step:2174/6200 train_loss:3.4915 train_time:468371ms step_avg:216.44ms step:2175/6200 train_loss:3.5497 train_time:468584ms step_avg:216.44ms step:2176/6200 train_loss:3.5130 train_time:468799ms step_avg:216.44ms step:2177/6200 train_loss:3.4845 train_time:469013ms step_avg:216.43ms step:2178/6200 train_loss:3.6987 train_time:469228ms step_avg:216.43ms step:2179/6200 train_loss:3.5225 train_time:469441ms step_avg:216.43ms step:2180/6200 train_loss:3.5282 train_time:469653ms step_avg:216.43ms step:2181/6200 train_loss:3.5963 train_time:469866ms step_avg:216.43ms step:2182/6200 train_loss:3.5691 train_time:470079ms step_avg:216.43ms step:2183/6200 train_loss:3.5426 train_time:470293ms step_avg:216.43ms step:2184/6200 train_loss:3.4405 train_time:470507ms step_avg:216.42ms step:2185/6200 train_loss:3.6090 train_time:470721ms step_avg:216.42ms step:2186/6200 train_loss:3.7834 train_time:470934ms step_avg:216.42ms step:2187/6200 train_loss:3.4121 train_time:471148ms step_avg:216.42ms step:2188/6200 train_loss:3.4640 train_time:471361ms step_avg:216.42ms step:2189/6200 train_loss:3.3249 train_time:471574ms step_avg:216.42ms step:2190/6200 train_loss:3.4617 train_time:471788ms step_avg:216.42ms step:2191/6200 train_loss:3.6035 train_time:472002ms step_avg:216.42ms step:2192/6200 train_loss:3.5501 train_time:472215ms step_avg:216.41ms step:2193/6200 train_loss:3.7807 train_time:472431ms step_avg:216.41ms step:2194/6200 train_loss:3.5474 train_time:472644ms step_avg:216.41ms step:2195/6200 train_loss:3.6076 train_time:472856ms step_avg:216.41ms step:2196/6200 train_loss:3.5465 train_time:473068ms step_avg:216.41ms step:2197/6200 train_loss:3.4634 train_time:473282ms step_avg:216.41ms step:2198/6200 train_loss:3.5550 train_time:473496ms step_avg:216.41ms step:2199/6200 train_loss:3.4913 train_time:473710ms step_avg:216.40ms step:2200/6200 train_loss:3.4978 train_time:473924ms step_avg:216.40ms step:2201/6200 train_loss:3.5557 train_time:474136ms step_avg:216.40ms step:2202/6200 train_loss:3.5334 train_time:474350ms step_avg:216.40ms step:2203/6200 train_loss:3.5088 train_time:474563ms step_avg:216.40ms step:2204/6200 train_loss:4.0178 train_time:474776ms step_avg:216.40ms step:2205/6200 train_loss:3.4216 train_time:474990ms step_avg:216.40ms step:2206/6200 train_loss:3.5424 train_time:475203ms step_avg:216.39ms step:2207/6200 train_loss:3.5575 train_time:475417ms step_avg:216.39ms step:2208/6200 train_loss:3.5808 train_time:475632ms step_avg:216.39ms step:2209/6200 train_loss:3.4738 train_time:475846ms step_avg:216.39ms step:2210/6200 train_loss:3.5549 train_time:476058ms step_avg:216.39ms step:2211/6200 train_loss:3.5599 train_time:476272ms step_avg:216.39ms step:2212/6200 train_loss:3.5622 train_time:476485ms step_avg:216.39ms step:2213/6200 train_loss:3.5919 train_time:476698ms step_avg:216.39ms step:2214/6200 train_loss:3.4454 train_time:476912ms step_avg:216.38ms step:2215/6200 train_loss:3.5113 train_time:477126ms step_avg:216.38ms step:2216/6200 train_loss:3.6433 train_time:477338ms step_avg:216.38ms step:2217/6200 train_loss:3.6009 train_time:477551ms step_avg:216.38ms step:2218/6200 train_loss:3.5628 train_time:477765ms step_avg:216.38ms step:2219/6200 train_loss:3.5696 train_time:477978ms step_avg:216.38ms step:2220/6200 train_loss:3.4810 train_time:478192ms step_avg:216.38ms step:2221/6200 train_loss:3.7325 train_time:478406ms step_avg:216.38ms step:2222/6200 train_loss:3.6336 train_time:478620ms step_avg:216.37ms step:2223/6200 train_loss:3.6520 train_time:478835ms step_avg:216.37ms step:2224/6200 train_loss:3.5289 train_time:479048ms step_avg:216.37ms step:2225/6200 train_loss:3.6519 train_time:479261ms step_avg:216.37ms step:2226/6200 train_loss:3.4076 train_time:479475ms step_avg:216.37ms step:2227/6200 train_loss:3.6726 train_time:479688ms step_avg:216.37ms step:2228/6200 train_loss:3.6068 train_time:479903ms step_avg:216.37ms step:2229/6200 train_loss:3.4139 train_time:480116ms step_avg:216.37ms step:2230/6200 train_loss:3.7566 train_time:480331ms step_avg:216.37ms step:2231/6200 train_loss:3.4480 train_time:480545ms step_avg:216.36ms step:2232/6200 train_loss:3.9187 train_time:480757ms step_avg:216.36ms step:2233/6200 train_loss:3.6080 train_time:480970ms step_avg:216.36ms step:2234/6200 train_loss:3.5418 train_time:481184ms step_avg:216.36ms step:2235/6200 train_loss:3.5978 train_time:481397ms step_avg:216.36ms step:2236/6200 train_loss:3.3710 train_time:481613ms step_avg:216.36ms step:2237/6200 train_loss:3.3645 train_time:481827ms step_avg:216.36ms step:2238/6200 train_loss:3.5860 train_time:482040ms step_avg:216.36ms step:2239/6200 train_loss:3.6858 train_time:482253ms step_avg:216.35ms step:2240/6200 train_loss:3.4031 train_time:482466ms step_avg:216.35ms step:2241/6200 train_loss:3.4848 train_time:482679ms step_avg:216.35ms step:2242/6200 train_loss:3.6550 train_time:482893ms step_avg:216.35ms step:2243/6200 train_loss:3.6208 train_time:483107ms step_avg:216.35ms step:2244/6200 train_loss:3.4785 train_time:483320ms step_avg:216.35ms step:2245/6200 train_loss:3.5446 train_time:483535ms step_avg:216.35ms step:2246/6200 train_loss:3.5684 train_time:483749ms step_avg:216.35ms step:2247/6200 train_loss:3.4114 train_time:483961ms step_avg:216.34ms step:2248/6200 train_loss:3.4238 train_time:484174ms step_avg:216.34ms step:2249/6200 train_loss:3.6796 train_time:484388ms step_avg:216.34ms step:2250/6200 train_loss:3.4116 train_time:484601ms step_avg:216.34ms step:2250/6200 val_loss:3.5366 train_time:484603ms step_avg:216.34ms step:2251/6200 train_loss:3.4079 train_time:484821ms step_avg:216.34ms step:2252/6200 train_loss:3.4854 train_time:485034ms step_avg:216.34ms step:2253/6200 train_loss:3.4636 train_time:485247ms step_avg:216.34ms step:2254/6200 train_loss:3.5082 train_time:485460ms step_avg:216.34ms step:2255/6200 train_loss:3.5652 train_time:485672ms step_avg:216.34ms step:2256/6200 train_loss:3.4434 train_time:485887ms step_avg:216.33ms step:2257/6200 train_loss:3.7233 train_time:486100ms step_avg:216.33ms step:2258/6200 train_loss:3.6071 train_time:486315ms step_avg:216.33ms step:2259/6200 train_loss:3.9128 train_time:486528ms step_avg:216.33ms step:2260/6200 train_loss:3.6024 train_time:486741ms step_avg:216.33ms step:2261/6200 train_loss:3.6500 train_time:486957ms step_avg:216.33ms step:2262/6200 train_loss:3.5650 train_time:487170ms step_avg:216.33ms step:2263/6200 train_loss:3.5629 train_time:487383ms step_avg:216.33ms step:2264/6200 train_loss:3.3194 train_time:487598ms step_avg:216.33ms step:2265/6200 train_loss:3.4517 train_time:487812ms step_avg:216.32ms step:2266/6200 train_loss:3.6686 train_time:488026ms step_avg:216.32ms step:2267/6200 train_loss:3.3937 train_time:488240ms step_avg:216.32ms step:2268/6200 train_loss:3.4742 train_time:488714ms step_avg:216.44ms step:2269/6200 train_loss:3.4413 train_time:488928ms step_avg:216.44ms step:2270/6200 train_loss:3.4087 train_time:489141ms step_avg:216.43ms step:2271/6200 train_loss:3.8153 train_time:489354ms step_avg:216.43ms step:2272/6200 train_loss:3.4606 train_time:489566ms step_avg:216.43ms step:2273/6200 train_loss:3.4734 train_time:489780ms step_avg:216.43ms step:2274/6200 train_loss:3.5560 train_time:489994ms step_avg:216.43ms step:2275/6200 train_loss:3.5083 train_time:490206ms step_avg:216.43ms step:2276/6200 train_loss:3.5243 train_time:490421ms step_avg:216.43ms step:2277/6200 train_loss:3.4032 train_time:490635ms step_avg:216.42ms step:2278/6200 train_loss:3.5091 train_time:490848ms step_avg:216.42ms step:2279/6200 train_loss:3.6398 train_time:491060ms step_avg:216.42ms step:2280/6200 train_loss:3.4278 train_time:491523ms step_avg:216.53ms step:2281/6200 train_loss:3.4926 train_time:491741ms step_avg:216.53ms step:2282/6200 train_loss:3.5075 train_time:491954ms step_avg:216.53ms step:2283/6200 train_loss:3.6536 train_time:492167ms step_avg:216.53ms step:2284/6200 train_loss:3.5283 train_time:492381ms step_avg:216.53ms step:2285/6200 train_loss:3.5465 train_time:492594ms step_avg:216.52ms step:2286/6200 train_loss:3.5454 train_time:492808ms step_avg:216.52ms step:2287/6200 train_loss:3.5423 train_time:493022ms step_avg:216.52ms step:2288/6200 train_loss:3.4921 train_time:493236ms step_avg:216.52ms step:2289/6200 train_loss:3.6287 train_time:493449ms step_avg:216.52ms step:2290/6200 train_loss:3.6070 train_time:493661ms step_avg:216.52ms step:2291/6200 train_loss:3.4859 train_time:493874ms step_avg:216.52ms step:2292/6200 train_loss:3.8230 train_time:494088ms step_avg:216.52ms step:2293/6200 train_loss:3.4873 train_time:494302ms step_avg:216.51ms step:2294/6200 train_loss:3.4362 train_time:494515ms step_avg:216.51ms step:2295/6200 train_loss:3.6160 train_time:494729ms step_avg:216.51ms step:2296/6200 train_loss:3.5662 train_time:494943ms step_avg:216.51ms step:2297/6200 train_loss:3.5304 train_time:495157ms step_avg:216.51ms step:2298/6200 train_loss:3.9202 train_time:495370ms step_avg:216.51ms step:2299/6200 train_loss:3.4371 train_time:495582ms step_avg:216.51ms step:2300/6200 train_loss:3.4366 train_time:495798ms step_avg:216.51ms step:2301/6200 train_loss:3.7868 train_time:496010ms step_avg:216.50ms step:2302/6200 train_loss:3.5069 train_time:496224ms step_avg:216.50ms step:2303/6200 train_loss:3.5101 train_time:496440ms step_avg:216.50ms step:2304/6200 train_loss:3.5070 train_time:496653ms step_avg:216.50ms step:2305/6200 train_loss:3.4413 train_time:496865ms step_avg:216.50ms step:2306/6200 train_loss:3.6048 train_time:497078ms step_avg:216.50ms step:2307/6200 train_loss:3.4566 train_time:497292ms step_avg:216.50ms step:2308/6200 train_loss:3.4790 train_time:497505ms step_avg:216.49ms step:2309/6200 train_loss:3.6230 train_time:497719ms step_avg:216.49ms step:2310/6200 train_loss:3.5635 train_time:497933ms step_avg:216.49ms step:2311/6200 train_loss:3.4368 train_time:498147ms step_avg:216.49ms step:2312/6200 train_loss:3.5479 train_time:498360ms step_avg:216.49ms step:2313/6200 train_loss:3.6744 train_time:498573ms step_avg:216.49ms step:2314/6200 train_loss:3.4953 train_time:498787ms step_avg:216.49ms step:2315/6200 train_loss:3.4170 train_time:499001ms step_avg:216.49ms step:2316/6200 train_loss:3.5109 train_time:499214ms step_avg:216.48ms step:2317/6200 train_loss:3.3943 train_time:499428ms step_avg:216.48ms step:2318/6200 train_loss:3.4990 train_time:499641ms step_avg:216.48ms step:2319/6200 train_loss:3.5194 train_time:499856ms step_avg:216.48ms step:2320/6200 train_loss:3.3598 train_time:500068ms step_avg:216.48ms step:2321/6200 train_loss:3.5061 train_time:500282ms step_avg:216.48ms step:2322/6200 train_loss:3.5620 train_time:500495ms step_avg:216.48ms step:2323/6200 train_loss:3.4674 train_time:500708ms step_avg:216.48ms step:2324/6200 train_loss:3.5168 train_time:500921ms step_avg:216.47ms step:2325/6200 train_loss:3.4398 train_time:501135ms step_avg:216.47ms step:2326/6200 train_loss:3.5695 train_time:501348ms step_avg:216.47ms step:2327/6200 train_loss:3.5843 train_time:501560ms step_avg:216.47ms step:2328/6200 train_loss:3.3545 train_time:501773ms step_avg:216.47ms step:2329/6200 train_loss:3.4692 train_time:501986ms step_avg:216.47ms step:2330/6200 train_loss:3.4986 train_time:502200ms step_avg:216.47ms step:2331/6200 train_loss:3.4598 train_time:502415ms step_avg:216.47ms step:2332/6200 train_loss:3.6327 train_time:502629ms step_avg:216.46ms step:2333/6200 train_loss:3.5371 train_time:502842ms step_avg:216.46ms step:2334/6200 train_loss:3.5160 train_time:503058ms step_avg:216.46ms step:2335/6200 train_loss:3.5859 train_time:503271ms step_avg:216.46ms step:2336/6200 train_loss:3.4331 train_time:503484ms step_avg:216.46ms step:2337/6200 train_loss:3.5844 train_time:503704ms step_avg:216.46ms step:2338/6200 train_loss:3.5393 train_time:503919ms step_avg:216.46ms step:2339/6200 train_loss:3.4879 train_time:504134ms step_avg:216.46ms step:2340/6200 train_loss:3.5649 train_time:504347ms step_avg:216.46ms step:2341/6200 train_loss:3.6204 train_time:504559ms step_avg:216.46ms step:2342/6200 train_loss:3.4915 train_time:504771ms step_avg:216.45ms step:2343/6200 train_loss:3.4918 train_time:504984ms step_avg:216.45ms step:2344/6200 train_loss:3.5604 train_time:505199ms step_avg:216.45ms step:2345/6200 train_loss:3.5026 train_time:505412ms step_avg:216.45ms step:2346/6200 train_loss:3.6244 train_time:505626ms step_avg:216.45ms step:2347/6200 train_loss:3.5313 train_time:505840ms step_avg:216.45ms step:2348/6200 train_loss:3.6403 train_time:506054ms step_avg:216.45ms step:2349/6200 train_loss:3.5949 train_time:506266ms step_avg:216.45ms step:2350/6200 train_loss:3.6383 train_time:506480ms step_avg:216.44ms step:2351/6200 train_loss:3.3309 train_time:506694ms step_avg:216.44ms step:2352/6200 train_loss:3.4559 train_time:506907ms step_avg:216.44ms step:2353/6200 train_loss:3.4409 train_time:507121ms step_avg:216.44ms step:2354/6200 train_loss:3.6578 train_time:507336ms step_avg:216.44ms step:2355/6200 train_loss:3.4595 train_time:507549ms step_avg:216.44ms step:2356/6200 train_loss:3.4526 train_time:507762ms step_avg:216.44ms step:2357/6200 train_loss:3.5996 train_time:507974ms step_avg:216.44ms step:2358/6200 train_loss:3.4593 train_time:508187ms step_avg:216.43ms step:2359/6200 train_loss:3.5637 train_time:508401ms step_avg:216.43ms step:2360/6200 train_loss:3.4604 train_time:508615ms step_avg:216.43ms step:2361/6200 train_loss:3.4709 train_time:508829ms step_avg:216.43ms step:2362/6200 train_loss:3.5142 train_time:509044ms step_avg:216.43ms step:2363/6200 train_loss:3.5668 train_time:509257ms step_avg:216.43ms step:2364/6200 train_loss:3.5116 train_time:509469ms step_avg:216.43ms step:2365/6200 train_loss:3.9495 train_time:509682ms step_avg:216.43ms step:2366/6200 train_loss:3.5726 train_time:509895ms step_avg:216.42ms step:2367/6200 train_loss:3.7261 train_time:510109ms step_avg:216.42ms step:2368/6200 train_loss:3.5427 train_time:510321ms step_avg:216.42ms step:2369/6200 train_loss:3.5441 train_time:510537ms step_avg:216.42ms step:2370/6200 train_loss:3.5788 train_time:510750ms step_avg:216.42ms step:2371/6200 train_loss:3.4653 train_time:510962ms step_avg:216.42ms step:2372/6200 train_loss:3.6931 train_time:511175ms step_avg:216.42ms step:2373/6200 train_loss:3.5329 train_time:511389ms step_avg:216.41ms step:2374/6200 train_loss:4.0919 train_time:511603ms step_avg:216.41ms step:2375/6200 train_loss:3.5116 train_time:511818ms step_avg:216.41ms step:2375/6200 val_loss:3.5261 train_time:511820ms step_avg:216.41ms step:2376/6200 train_loss:3.4226 train_time:512037ms step_avg:216.41ms step:2377/6200 train_loss:3.5858 train_time:512252ms step_avg:216.41ms step:2378/6200 train_loss:3.5514 train_time:512465ms step_avg:216.41ms step:2379/6200 train_loss:3.5712 train_time:512677ms step_avg:216.41ms step:2380/6200 train_loss:3.5545 train_time:512890ms step_avg:216.41ms step:2381/6200 train_loss:3.4434 train_time:513103ms step_avg:216.41ms step:2382/6200 train_loss:3.5516 train_time:513318ms step_avg:216.41ms step:2383/6200 train_loss:3.5621 train_time:513532ms step_avg:216.41ms step:2384/6200 train_loss:3.5160 train_time:513746ms step_avg:216.41ms step:2385/6200 train_loss:3.4446 train_time:513960ms step_avg:216.40ms step:2386/6200 train_loss:3.5530 train_time:514177ms step_avg:216.40ms step:2387/6200 train_loss:3.5106 train_time:514389ms step_avg:216.40ms step:2388/6200 train_loss:3.5084 train_time:514603ms step_avg:216.40ms step:2389/6200 train_loss:3.5422 train_time:514816ms step_avg:216.40ms step:2390/6200 train_loss:3.5328 train_time:515031ms step_avg:216.40ms step:2391/6200 train_loss:3.5272 train_time:515245ms step_avg:216.40ms step:2392/6200 train_loss:3.4060 train_time:515459ms step_avg:216.40ms step:2393/6200 train_loss:3.6251 train_time:515672ms step_avg:216.40ms step:2394/6200 train_loss:3.4706 train_time:515885ms step_avg:216.39ms step:2395/6200 train_loss:3.5677 train_time:516100ms step_avg:216.39ms step:2396/6200 train_loss:3.6780 train_time:516315ms step_avg:216.39ms step:2397/6200 train_loss:3.7054 train_time:516528ms step_avg:216.39ms step:2398/6200 train_loss:3.6407 train_time:516742ms step_avg:216.39ms step:2399/6200 train_loss:3.6110 train_time:516958ms step_avg:216.39ms step:2400/6200 train_loss:3.4895 train_time:517171ms step_avg:216.39ms step:2401/6200 train_loss:3.4817 train_time:517384ms step_avg:216.39ms step:2402/6200 train_loss:3.5975 train_time:517597ms step_avg:216.39ms step:2403/6200 train_loss:3.4358 train_time:517811ms step_avg:216.39ms step:2404/6200 train_loss:3.5690 train_time:518025ms step_avg:216.38ms step:2405/6200 train_loss:3.7770 train_time:518242ms step_avg:216.39ms step:2406/6200 train_loss:3.5080 train_time:518457ms step_avg:216.38ms step:2407/6200 train_loss:3.6584 train_time:518671ms step_avg:216.38ms step:2408/6200 train_loss:3.5080 train_time:518885ms step_avg:216.38ms step:2409/6200 train_loss:3.4487 train_time:519098ms step_avg:216.38ms step:2410/6200 train_loss:3.5756 train_time:519311ms step_avg:216.38ms step:2411/6200 train_loss:3.3720 train_time:519524ms step_avg:216.38ms step:2412/6200 train_loss:3.8089 train_time:519738ms step_avg:216.38ms step:2413/6200 train_loss:3.4881 train_time:519954ms step_avg:216.38ms step:2414/6200 train_loss:3.5588 train_time:520166ms step_avg:216.38ms step:2415/6200 train_loss:3.4820 train_time:520378ms step_avg:216.37ms step:2416/6200 train_loss:3.5556 train_time:520593ms step_avg:216.37ms step:2417/6200 train_loss:3.3770 train_time:520806ms step_avg:216.37ms step:2418/6200 train_loss:3.3094 train_time:521019ms step_avg:216.37ms step:2419/6200 train_loss:3.5956 train_time:521234ms step_avg:216.37ms step:2420/6200 train_loss:3.4774 train_time:521448ms step_avg:216.37ms step:2421/6200 train_loss:3.5098 train_time:521660ms step_avg:216.37ms step:2422/6200 train_loss:3.6138 train_time:521874ms step_avg:216.37ms step:2423/6200 train_loss:3.6545 train_time:522087ms step_avg:216.36ms step:2424/6200 train_loss:3.4762 train_time:522300ms step_avg:216.36ms step:2425/6200 train_loss:3.5678 train_time:522515ms step_avg:216.36ms step:2426/6200 train_loss:3.5674 train_time:522728ms step_avg:216.36ms step:2427/6200 train_loss:3.4978 train_time:522941ms step_avg:216.36ms step:2428/6200 train_loss:3.4449 train_time:523157ms step_avg:216.36ms step:2429/6200 train_loss:3.5702 train_time:523369ms step_avg:216.36ms step:2430/6200 train_loss:3.4687 train_time:523581ms step_avg:216.36ms step:2431/6200 train_loss:3.5197 train_time:523795ms step_avg:216.35ms step:2432/6200 train_loss:3.5800 train_time:524008ms step_avg:216.35ms step:2433/6200 train_loss:3.5425 train_time:524220ms step_avg:216.35ms step:2434/6200 train_loss:3.4210 train_time:524435ms step_avg:216.35ms step:2435/6200 train_loss:3.3800 train_time:524648ms step_avg:216.35ms step:2436/6200 train_loss:3.5470 train_time:524861ms step_avg:216.35ms step:2437/6200 train_loss:3.4043 train_time:525074ms step_avg:216.35ms step:2438/6200 train_loss:3.4829 train_time:525287ms step_avg:216.35ms step:2439/6200 train_loss:3.5676 train_time:525500ms step_avg:216.34ms step:2440/6200 train_loss:3.4872 train_time:525718ms step_avg:216.34ms step:2441/6200 train_loss:3.5786 train_time:525931ms step_avg:216.34ms step:2442/6200 train_loss:3.4623 train_time:526144ms step_avg:216.34ms step:2443/6200 train_loss:3.5246 train_time:526360ms step_avg:216.34ms step:2444/6200 train_loss:3.4096 train_time:526574ms step_avg:216.34ms step:2445/6200 train_loss:3.4186 train_time:526786ms step_avg:216.34ms step:2446/6200 train_loss:3.5833 train_time:526999ms step_avg:216.34ms step:2447/6200 train_loss:3.4426 train_time:527214ms step_avg:216.34ms step:2448/6200 train_loss:3.5167 train_time:527427ms step_avg:216.34ms step:2449/6200 train_loss:3.6748 train_time:527640ms step_avg:216.33ms step:2450/6200 train_loss:3.5046 train_time:527856ms step_avg:216.33ms step:2451/6200 train_loss:3.5720 train_time:528069ms step_avg:216.33ms step:2452/6200 train_loss:3.4803 train_time:528285ms step_avg:216.33ms step:2453/6200 train_loss:3.5792 train_time:528499ms step_avg:216.33ms step:2454/6200 train_loss:3.4742 train_time:528713ms step_avg:216.33ms step:2455/6200 train_loss:3.6075 train_time:528925ms step_avg:216.33ms step:2456/6200 train_loss:3.5335 train_time:529138ms step_avg:216.33ms step:2457/6200 train_loss:3.4576 train_time:529606ms step_avg:216.43ms step:2458/6200 train_loss:3.3915 train_time:529818ms step_avg:216.43ms step:2459/6200 train_loss:3.5118 train_time:530033ms step_avg:216.43ms step:2460/6200 train_loss:4.1076 train_time:530247ms step_avg:216.43ms step:2461/6200 train_loss:3.5803 train_time:530459ms step_avg:216.43ms step:2462/6200 train_loss:3.4008 train_time:530673ms step_avg:216.42ms step:2463/6200 train_loss:3.5909 train_time:530885ms step_avg:216.42ms step:2464/6200 train_loss:3.5112 train_time:531099ms step_avg:216.42ms step:2465/6200 train_loss:3.7112 train_time:531313ms step_avg:216.42ms step:2466/6200 train_loss:3.9398 train_time:531526ms step_avg:216.42ms step:2467/6200 train_loss:3.6291 train_time:531740ms step_avg:216.42ms step:2468/6200 train_loss:3.4939 train_time:531955ms step_avg:216.42ms step:2469/6200 train_loss:3.6060 train_time:532170ms step_avg:216.42ms step:2470/6200 train_loss:3.6226 train_time:532633ms step_avg:216.52ms step:2471/6200 train_loss:3.4245 train_time:532846ms step_avg:216.52ms step:2472/6200 train_loss:3.5149 train_time:533058ms step_avg:216.51ms step:2473/6200 train_loss:3.5085 train_time:533272ms step_avg:216.51ms step:2474/6200 train_loss:3.6556 train_time:533484ms step_avg:216.51ms step:2475/6200 train_loss:3.7817 train_time:533697ms step_avg:216.51ms step:2476/6200 train_loss:3.3792 train_time:533911ms step_avg:216.51ms step:2477/6200 train_loss:3.5817 train_time:534125ms step_avg:216.51ms step:2478/6200 train_loss:3.5498 train_time:534339ms step_avg:216.51ms step:2479/6200 train_loss:3.3898 train_time:534553ms step_avg:216.51ms step:2480/6200 train_loss:3.3852 train_time:534766ms step_avg:216.50ms step:2481/6200 train_loss:3.5318 train_time:534978ms step_avg:216.50ms step:2482/6200 train_loss:3.5467 train_time:535192ms step_avg:216.50ms step:2483/6200 train_loss:3.5564 train_time:535405ms step_avg:216.50ms step:2484/6200 train_loss:3.5064 train_time:535618ms step_avg:216.50ms step:2485/6200 train_loss:3.5326 train_time:535832ms step_avg:216.50ms step:2486/6200 train_loss:3.4104 train_time:536047ms step_avg:216.50ms step:2487/6200 train_loss:3.6037 train_time:536260ms step_avg:216.50ms step:2488/6200 train_loss:3.5668 train_time:536474ms step_avg:216.49ms step:2489/6200 train_loss:3.4732 train_time:536686ms step_avg:216.49ms step:2490/6200 train_loss:3.5785 train_time:536899ms step_avg:216.49ms step:2491/6200 train_loss:3.6337 train_time:537112ms step_avg:216.49ms step:2492/6200 train_loss:3.7125 train_time:537325ms step_avg:216.49ms step:2493/6200 train_loss:3.5582 train_time:537539ms step_avg:216.49ms step:2494/6200 train_loss:3.4807 train_time:537754ms step_avg:216.49ms step:2495/6200 train_loss:3.6152 train_time:537967ms step_avg:216.49ms step:2496/6200 train_loss:3.5554 train_time:538179ms step_avg:216.48ms step:2497/6200 train_loss:3.4729 train_time:538393ms step_avg:216.48ms step:2498/6200 train_loss:3.5710 train_time:538606ms step_avg:216.48ms step:2499/6200 train_loss:3.6170 train_time:538819ms step_avg:216.48ms step:2500/6200 train_loss:3.6381 train_time:539034ms step_avg:216.48ms step:2500/6200 val_loss:3.5171 train_time:539036ms step_avg:216.48ms step:2501/6200 train_loss:3.5849 train_time:539251ms step_avg:216.48ms step:2502/6200 train_loss:3.5359 train_time:539466ms step_avg:216.48ms step:2503/6200 train_loss:3.5570 train_time:539680ms step_avg:216.48ms step:2504/6200 train_loss:3.4288 train_time:539893ms step_avg:216.48ms step:2505/6200 train_loss:3.6203 train_time:540105ms step_avg:216.47ms step:2506/6200 train_loss:3.5688 train_time:540318ms step_avg:216.47ms step:2507/6200 train_loss:3.5148 train_time:540531ms step_avg:216.47ms step:2508/6200 train_loss:3.5223 train_time:540747ms step_avg:216.47ms step:2509/6200 train_loss:3.4869 train_time:540962ms step_avg:216.47ms step:2510/6200 train_loss:3.6614 train_time:541175ms step_avg:216.47ms step:2511/6200 train_loss:3.4834 train_time:541387ms step_avg:216.47ms step:2512/6200 train_loss:3.4641 train_time:541603ms step_avg:216.47ms step:2513/6200 train_loss:3.5384 train_time:541816ms step_avg:216.47ms step:2514/6200 train_loss:3.5666 train_time:542028ms step_avg:216.46ms step:2515/6200 train_loss:3.4679 train_time:542243ms step_avg:216.46ms step:2516/6200 train_loss:3.5646 train_time:542455ms step_avg:216.46ms step:2517/6200 train_loss:3.5584 train_time:542668ms step_avg:216.46ms step:2518/6200 train_loss:3.4337 train_time:542884ms step_avg:216.46ms step:2519/6200 train_loss:3.4646 train_time:543097ms step_avg:216.46ms step:2520/6200 train_loss:3.5893 train_time:543308ms step_avg:216.46ms step:2521/6200 train_loss:3.5813 train_time:543522ms step_avg:216.46ms step:2522/6200 train_loss:3.4572 train_time:543735ms step_avg:216.46ms step:2523/6200 train_loss:3.4455 train_time:543948ms step_avg:216.45ms step:2524/6200 train_loss:3.5467 train_time:544163ms step_avg:216.45ms step:2525/6200 train_loss:3.3832 train_time:544377ms step_avg:216.45ms step:2526/6200 train_loss:3.6049 train_time:544589ms step_avg:216.45ms step:2527/6200 train_loss:3.5158 train_time:544802ms step_avg:216.45ms step:2528/6200 train_loss:3.5091 train_time:545015ms step_avg:216.45ms step:2529/6200 train_loss:3.5030 train_time:545228ms step_avg:216.45ms step:2530/6200 train_loss:3.5243 train_time:545443ms step_avg:216.45ms step:2531/6200 train_loss:3.5582 train_time:545656ms step_avg:216.44ms step:2532/6200 train_loss:3.3843 train_time:545869ms step_avg:216.44ms step:2533/6200 train_loss:3.5434 train_time:546084ms step_avg:216.44ms step:2534/6200 train_loss:3.4386 train_time:546297ms step_avg:216.44ms step:2535/6200 train_loss:3.4745 train_time:546509ms step_avg:216.44ms step:2536/6200 train_loss:3.5225 train_time:546723ms step_avg:216.44ms step:2537/6200 train_loss:3.5440 train_time:546936ms step_avg:216.44ms step:2538/6200 train_loss:3.3640 train_time:547149ms step_avg:216.44ms step:2539/6200 train_loss:3.6802 train_time:547364ms step_avg:216.44ms step:2540/6200 train_loss:3.3526 train_time:547579ms step_avg:216.43ms step:2541/6200 train_loss:3.5379 train_time:547792ms step_avg:216.43ms step:2542/6200 train_loss:3.3725 train_time:548004ms step_avg:216.43ms step:2543/6200 train_loss:3.7421 train_time:548217ms step_avg:216.43ms step:2544/6200 train_loss:3.5175 train_time:548431ms step_avg:216.43ms step:2545/6200 train_loss:3.6707 train_time:548645ms step_avg:216.43ms step:2546/6200 train_loss:3.5010 train_time:548859ms step_avg:216.43ms step:2547/6200 train_loss:3.4865 train_time:549073ms step_avg:216.43ms step:2548/6200 train_loss:3.4899 train_time:549285ms step_avg:216.42ms step:2549/6200 train_loss:3.6504 train_time:549499ms step_avg:216.42ms step:2550/6200 train_loss:3.5112 train_time:549711ms step_avg:216.42ms step:2551/6200 train_loss:3.5087 train_time:549925ms step_avg:216.42ms step:2552/6200 train_loss:3.5347 train_time:550138ms step_avg:216.42ms step:2553/6200 train_loss:3.5557 train_time:550351ms step_avg:216.42ms step:2554/6200 train_loss:3.4715 train_time:550565ms step_avg:216.42ms step:2555/6200 train_loss:3.5755 train_time:550779ms step_avg:216.42ms step:2556/6200 train_loss:3.6296 train_time:550995ms step_avg:216.42ms step:2557/6200 train_loss:3.6229 train_time:551207ms step_avg:216.41ms step:2558/6200 train_loss:3.4554 train_time:551421ms step_avg:216.41ms step:2559/6200 train_loss:3.4567 train_time:551634ms step_avg:216.41ms step:2560/6200 train_loss:3.4672 train_time:551847ms step_avg:216.41ms step:2561/6200 train_loss:3.5873 train_time:552062ms step_avg:216.41ms step:2562/6200 train_loss:3.6255 train_time:552275ms step_avg:216.41ms step:2563/6200 train_loss:3.5097 train_time:552488ms step_avg:216.41ms step:2564/6200 train_loss:3.5422 train_time:552702ms step_avg:216.41ms step:2565/6200 train_loss:3.4547 train_time:552915ms step_avg:216.40ms step:2566/6200 train_loss:3.4624 train_time:553128ms step_avg:216.40ms step:2567/6200 train_loss:3.4553 train_time:553342ms step_avg:216.40ms step:2568/6200 train_loss:3.5074 train_time:553555ms step_avg:216.40ms step:2569/6200 train_loss:3.6503 train_time:553768ms step_avg:216.40ms step:2570/6200 train_loss:3.5551 train_time:553982ms step_avg:216.40ms step:2571/6200 train_loss:3.6423 train_time:554195ms step_avg:216.40ms step:2572/6200 train_loss:3.3907 train_time:554407ms step_avg:216.40ms step:2573/6200 train_loss:3.5065 train_time:554621ms step_avg:216.40ms step:2574/6200 train_loss:3.1833 train_time:554834ms step_avg:216.39ms step:2575/6200 train_loss:3.4080 train_time:555046ms step_avg:216.39ms step:2576/6200 train_loss:3.3470 train_time:555261ms step_avg:216.39ms step:2577/6200 train_loss:3.4653 train_time:555475ms step_avg:216.39ms step:2578/6200 train_loss:3.5202 train_time:555687ms step_avg:216.39ms step:2579/6200 train_loss:3.4261 train_time:555900ms step_avg:216.39ms step:2580/6200 train_loss:3.4739 train_time:556112ms step_avg:216.39ms step:2581/6200 train_loss:3.4363 train_time:556326ms step_avg:216.39ms step:2582/6200 train_loss:3.5349 train_time:556541ms step_avg:216.38ms step:2583/6200 train_loss:3.4109 train_time:556754ms step_avg:216.38ms step:2584/6200 train_loss:3.6046 train_time:556969ms step_avg:216.38ms step:2585/6200 train_loss:3.5275 train_time:557184ms step_avg:216.38ms step:2586/6200 train_loss:3.5310 train_time:557397ms step_avg:216.38ms step:2587/6200 train_loss:3.6616 train_time:557609ms step_avg:216.38ms step:2588/6200 train_loss:3.5445 train_time:557822ms step_avg:216.38ms step:2589/6200 train_loss:3.3992 train_time:558035ms step_avg:216.38ms step:2590/6200 train_loss:3.5707 train_time:558248ms step_avg:216.38ms step:2591/6200 train_loss:3.4724 train_time:558464ms step_avg:216.37ms step:2592/6200 train_loss:3.6779 train_time:558679ms step_avg:216.37ms step:2593/6200 train_loss:3.5581 train_time:558890ms step_avg:216.37ms step:2594/6200 train_loss:3.3684 train_time:559103ms step_avg:216.37ms step:2595/6200 train_loss:3.4504 train_time:559315ms step_avg:216.37ms step:2596/6200 train_loss:3.9325 train_time:559528ms step_avg:216.37ms step:2597/6200 train_loss:3.5245 train_time:559743ms step_avg:216.37ms step:2598/6200 train_loss:3.5343 train_time:559956ms step_avg:216.37ms step:2599/6200 train_loss:3.3948 train_time:560169ms step_avg:216.36ms step:2600/6200 train_loss:3.6313 train_time:560383ms step_avg:216.36ms step:2601/6200 train_loss:3.7908 train_time:560595ms step_avg:216.36ms step:2602/6200 train_loss:3.3741 train_time:560807ms step_avg:216.36ms step:2603/6200 train_loss:3.5160 train_time:561021ms step_avg:216.36ms step:2604/6200 train_loss:3.3402 train_time:561233ms step_avg:216.36ms step:2605/6200 train_loss:3.6356 train_time:561447ms step_avg:216.36ms step:2606/6200 train_loss:3.5118 train_time:561663ms step_avg:216.36ms step:2607/6200 train_loss:3.4110 train_time:561875ms step_avg:216.36ms step:2608/6200 train_loss:3.3526 train_time:562093ms step_avg:216.36ms step:2609/6200 train_loss:3.4746 train_time:562305ms step_avg:216.35ms step:2610/6200 train_loss:3.6518 train_time:562518ms step_avg:216.35ms step:2611/6200 train_loss:3.5351 train_time:562730ms step_avg:216.35ms step:2612/6200 train_loss:3.3500 train_time:562944ms step_avg:216.35ms step:2613/6200 train_loss:3.4651 train_time:563158ms step_avg:216.35ms step:2614/6200 train_loss:3.5665 train_time:563371ms step_avg:216.35ms step:2615/6200 train_loss:3.5071 train_time:563586ms step_avg:216.35ms step:2616/6200 train_loss:3.4930 train_time:563799ms step_avg:216.35ms step:2617/6200 train_loss:3.5301 train_time:564011ms step_avg:216.34ms step:2618/6200 train_loss:3.5750 train_time:564225ms step_avg:216.34ms step:2619/6200 train_loss:3.4203 train_time:564439ms step_avg:216.34ms step:2620/6200 train_loss:3.6010 train_time:564653ms step_avg:216.34ms step:2621/6200 train_loss:3.5591 train_time:564866ms step_avg:216.34ms step:2622/6200 train_loss:3.6863 train_time:565078ms step_avg:216.34ms step:2623/6200 train_loss:3.5940 train_time:565292ms step_avg:216.34ms step:2624/6200 train_loss:3.5147 train_time:565504ms step_avg:216.34ms step:2625/6200 train_loss:3.4752 train_time:565716ms step_avg:216.34ms step:2625/6200 val_loss:3.5052 train_time:565718ms step_avg:216.34ms step:2626/6200 train_loss:3.4996 train_time:565937ms step_avg:216.34ms step:2627/6200 train_loss:3.5628 train_time:566149ms step_avg:216.34ms step:2628/6200 train_loss:3.3908 train_time:566363ms step_avg:216.33ms step:2629/6200 train_loss:3.6470 train_time:566577ms step_avg:216.33ms step:2630/6200 train_loss:3.5303 train_time:566791ms step_avg:216.33ms step:2631/6200 train_loss:3.5879 train_time:567004ms step_avg:216.33ms step:2632/6200 train_loss:3.8072 train_time:567216ms step_avg:216.33ms step:2633/6200 train_loss:3.5481 train_time:567430ms step_avg:216.33ms step:2634/6200 train_loss:3.4704 train_time:567644ms step_avg:216.33ms step:2635/6200 train_loss:3.4395 train_time:567858ms step_avg:216.33ms step:2636/6200 train_loss:3.4841 train_time:568072ms step_avg:216.33ms step:2637/6200 train_loss:3.2711 train_time:568285ms step_avg:216.32ms step:2638/6200 train_loss:3.5706 train_time:568498ms step_avg:216.32ms step:2639/6200 train_loss:3.5646 train_time:568712ms step_avg:216.32ms step:2640/6200 train_loss:3.4528 train_time:568925ms step_avg:216.32ms step:2641/6200 train_loss:3.5291 train_time:569138ms step_avg:216.32ms step:2642/6200 train_loss:3.5702 train_time:569352ms step_avg:216.32ms step:2643/6200 train_loss:3.3565 train_time:569565ms step_avg:216.32ms step:2644/6200 train_loss:3.4781 train_time:569778ms step_avg:216.32ms step:2645/6200 train_loss:3.5498 train_time:569993ms step_avg:216.32ms step:2646/6200 train_loss:3.5149 train_time:570460ms step_avg:216.41ms step:2647/6200 train_loss:3.4066 train_time:570675ms step_avg:216.41ms step:2648/6200 train_loss:3.6367 train_time:570889ms step_avg:216.41ms step:2649/6200 train_loss:3.8912 train_time:571102ms step_avg:216.41ms step:2650/6200 train_loss:3.5319 train_time:571316ms step_avg:216.41ms step:2651/6200 train_loss:3.4833 train_time:571528ms step_avg:216.41ms step:2652/6200 train_loss:3.6208 train_time:571741ms step_avg:216.40ms step:2653/6200 train_loss:3.4651 train_time:571955ms step_avg:216.40ms step:2654/6200 train_loss:3.4456 train_time:572169ms step_avg:216.40ms step:2655/6200 train_loss:3.5124 train_time:572383ms step_avg:216.40ms step:2656/6200 train_loss:3.4346 train_time:572597ms step_avg:216.40ms step:2657/6200 train_loss:3.4703 train_time:572810ms step_avg:216.40ms step:2658/6200 train_loss:3.4405 train_time:573022ms step_avg:216.40ms step:2659/6200 train_loss:3.5159 train_time:573235ms step_avg:216.40ms step:2660/6200 train_loss:3.6652 train_time:573700ms step_avg:216.49ms step:2661/6200 train_loss:3.4659 train_time:573913ms step_avg:216.49ms step:2662/6200 train_loss:3.6127 train_time:574125ms step_avg:216.49ms step:2663/6200 train_loss:3.4757 train_time:574338ms step_avg:216.49ms step:2664/6200 train_loss:3.4704 train_time:574552ms step_avg:216.49ms step:2665/6200 train_loss:3.3956 train_time:574766ms step_avg:216.48ms step:2666/6200 train_loss:3.4536 train_time:574979ms step_avg:216.48ms step:2667/6200 train_loss:3.4885 train_time:575194ms step_avg:216.48ms step:2668/6200 train_loss:3.5381 train_time:575406ms step_avg:216.48ms step:2669/6200 train_loss:3.4539 train_time:575618ms step_avg:216.48ms step:2670/6200 train_loss:3.5159 train_time:575832ms step_avg:216.48ms step:2671/6200 train_loss:3.3877 train_time:576044ms step_avg:216.48ms step:2672/6200 train_loss:3.4635 train_time:576257ms step_avg:216.48ms step:2673/6200 train_loss:3.4523 train_time:576470ms step_avg:216.47ms step:2674/6200 train_loss:3.5085 train_time:576684ms step_avg:216.47ms step:2675/6200 train_loss:3.5296 train_time:576897ms step_avg:216.47ms step:2676/6200 train_loss:3.4979 train_time:577110ms step_avg:216.47ms step:2677/6200 train_loss:3.4909 train_time:577322ms step_avg:216.47ms step:2678/6200 train_loss:3.5381 train_time:577536ms step_avg:216.47ms step:2679/6200 train_loss:3.5672 train_time:577749ms step_avg:216.47ms step:2680/6200 train_loss:3.4787 train_time:577962ms step_avg:216.47ms step:2681/6200 train_loss:3.4063 train_time:578176ms step_avg:216.46ms step:2682/6200 train_loss:3.4481 train_time:578390ms step_avg:216.46ms step:2683/6200 train_loss:3.9247 train_time:578603ms step_avg:216.46ms step:2684/6200 train_loss:3.5081 train_time:578815ms step_avg:216.46ms step:2685/6200 train_loss:3.5326 train_time:579028ms step_avg:216.46ms step:2686/6200 train_loss:3.5847 train_time:579241ms step_avg:216.46ms step:2687/6200 train_loss:3.4998 train_time:579455ms step_avg:216.46ms step:2688/6200 train_loss:3.5781 train_time:579668ms step_avg:216.46ms step:2689/6200 train_loss:3.5095 train_time:579881ms step_avg:216.45ms step:2690/6200 train_loss:3.5040 train_time:580096ms step_avg:216.45ms step:2691/6200 train_loss:3.5240 train_time:580309ms step_avg:216.45ms step:2692/6200 train_loss:3.5990 train_time:580521ms step_avg:216.45ms step:2693/6200 train_loss:3.4054 train_time:580735ms step_avg:216.45ms step:2694/6200 train_loss:3.7766 train_time:580948ms step_avg:216.45ms step:2695/6200 train_loss:3.5764 train_time:581160ms step_avg:216.45ms step:2696/6200 train_loss:3.4214 train_time:581375ms step_avg:216.45ms step:2697/6200 train_loss:3.5670 train_time:581589ms step_avg:216.45ms step:2698/6200 train_loss:3.5293 train_time:581802ms step_avg:216.44ms step:2699/6200 train_loss:3.4758 train_time:582014ms step_avg:216.44ms step:2700/6200 train_loss:3.5817 train_time:582227ms step_avg:216.44ms step:2701/6200 train_loss:3.5402 train_time:582440ms step_avg:216.44ms step:2702/6200 train_loss:3.4480 train_time:582654ms step_avg:216.44ms step:2703/6200 train_loss:3.4823 train_time:582867ms step_avg:216.44ms step:2704/6200 train_loss:3.4933 train_time:583080ms step_avg:216.44ms step:2705/6200 train_loss:3.4495 train_time:583294ms step_avg:216.44ms step:2706/6200 train_loss:3.6385 train_time:583507ms step_avg:216.43ms step:2707/6200 train_loss:3.5935 train_time:583719ms step_avg:216.43ms step:2708/6200 train_loss:3.5054 train_time:583933ms step_avg:216.43ms step:2709/6200 train_loss:3.4976 train_time:584146ms step_avg:216.43ms step:2710/6200 train_loss:3.6014 train_time:584358ms step_avg:216.43ms step:2711/6200 train_loss:3.4699 train_time:584573ms step_avg:216.43ms step:2712/6200 train_loss:3.5887 train_time:584786ms step_avg:216.43ms step:2713/6200 train_loss:3.3261 train_time:584999ms step_avg:216.43ms step:2714/6200 train_loss:3.5149 train_time:585213ms step_avg:216.42ms step:2715/6200 train_loss:3.4197 train_time:585425ms step_avg:216.42ms step:2716/6200 train_loss:3.4181 train_time:585638ms step_avg:216.42ms step:2717/6200 train_loss:3.6133 train_time:585852ms step_avg:216.42ms step:2718/6200 train_loss:3.5116 train_time:586065ms step_avg:216.42ms step:2719/6200 train_loss:3.7445 train_time:586278ms step_avg:216.42ms step:2720/6200 train_loss:3.4847 train_time:586494ms step_avg:216.42ms step:2721/6200 train_loss:3.4819 train_time:586706ms step_avg:216.42ms step:2722/6200 train_loss:3.7134 train_time:586918ms step_avg:216.42ms step:2723/6200 train_loss:3.4771 train_time:587132ms step_avg:216.41ms step:2724/6200 train_loss:3.6507 train_time:587345ms step_avg:216.41ms step:2725/6200 train_loss:3.5312 train_time:587557ms step_avg:216.41ms step:2726/6200 train_loss:3.4923 train_time:587771ms step_avg:216.41ms step:2727/6200 train_loss:3.4971 train_time:587984ms step_avg:216.41ms step:2728/6200 train_loss:3.8346 train_time:588197ms step_avg:216.41ms step:2729/6200 train_loss:3.5672 train_time:588410ms step_avg:216.41ms step:2730/6200 train_loss:3.4388 train_time:588623ms step_avg:216.41ms step:2731/6200 train_loss:3.5411 train_time:588835ms step_avg:216.40ms step:2732/6200 train_loss:3.4442 train_time:589048ms step_avg:216.40ms step:2733/6200 train_loss:3.3398 train_time:589261ms step_avg:216.40ms step:2734/6200 train_loss:3.4511 train_time:589476ms step_avg:216.40ms step:2735/6200 train_loss:3.5210 train_time:589690ms step_avg:216.40ms step:2736/6200 train_loss:3.4212 train_time:589903ms step_avg:216.40ms step:2737/6200 train_loss:3.8259 train_time:590115ms step_avg:216.40ms step:2738/6200 train_loss:3.5597 train_time:590328ms step_avg:216.40ms step:2739/6200 train_loss:3.7592 train_time:590541ms step_avg:216.39ms step:2740/6200 train_loss:3.5096 train_time:590755ms step_avg:216.39ms step:2741/6200 train_loss:3.5029 train_time:590969ms step_avg:216.39ms step:2742/6200 train_loss:3.4437 train_time:591182ms step_avg:216.39ms step:2743/6200 train_loss:3.5098 train_time:591397ms step_avg:216.39ms step:2744/6200 train_loss:3.5248 train_time:591610ms step_avg:216.39ms step:2745/6200 train_loss:3.6240 train_time:591822ms step_avg:216.39ms step:2746/6200 train_loss:3.3966 train_time:592036ms step_avg:216.39ms step:2747/6200 train_loss:3.4836 train_time:592249ms step_avg:216.39ms step:2748/6200 train_loss:3.5301 train_time:592463ms step_avg:216.39ms step:2749/6200 train_loss:3.6384 train_time:592676ms step_avg:216.38ms step:2750/6200 train_loss:3.4787 train_time:592891ms step_avg:216.38ms step:2750/6200 val_loss:3.4968 train_time:592892ms step_avg:216.38ms step:2751/6200 train_loss:3.5426 train_time:593109ms step_avg:216.38ms step:2752/6200 train_loss:3.6044 train_time:593324ms step_avg:216.38ms step:2753/6200 train_loss:3.5213 train_time:593537ms step_avg:216.38ms step:2754/6200 train_loss:3.4468 train_time:593750ms step_avg:216.38ms step:2755/6200 train_loss:3.4393 train_time:593963ms step_avg:216.38ms step:2756/6200 train_loss:3.5309 train_time:594178ms step_avg:216.38ms step:2757/6200 train_loss:3.4651 train_time:594391ms step_avg:216.38ms step:2758/6200 train_loss:3.3467 train_time:594605ms step_avg:216.38ms step:2759/6200 train_loss:3.7373 train_time:594820ms step_avg:216.38ms step:2760/6200 train_loss:3.5530 train_time:595035ms step_avg:216.38ms step:2761/6200 train_loss:3.5085 train_time:595247ms step_avg:216.37ms step:2762/6200 train_loss:3.4825 train_time:595461ms step_avg:216.37ms step:2763/6200 train_loss:3.4052 train_time:595672ms step_avg:216.37ms step:2764/6200 train_loss:3.5647 train_time:595886ms step_avg:216.37ms step:2765/6200 train_loss:3.4890 train_time:596100ms step_avg:216.37ms step:2766/6200 train_loss:3.3851 train_time:596314ms step_avg:216.37ms step:2767/6200 train_loss:3.4700 train_time:596527ms step_avg:216.37ms step:2768/6200 train_loss:3.5640 train_time:596741ms step_avg:216.37ms step:2769/6200 train_loss:3.4325 train_time:596954ms step_avg:216.37ms step:2770/6200 train_loss:3.5109 train_time:597166ms step_avg:216.36ms step:2771/6200 train_loss:3.4839 train_time:597381ms step_avg:216.36ms step:2772/6200 train_loss:3.9292 train_time:597594ms step_avg:216.36ms step:2773/6200 train_loss:3.3933 train_time:597807ms step_avg:216.36ms step:2774/6200 train_loss:3.5270 train_time:598022ms step_avg:216.36ms step:2775/6200 train_loss:3.5869 train_time:598236ms step_avg:216.36ms step:2776/6200 train_loss:3.5570 train_time:598448ms step_avg:216.36ms step:2777/6200 train_loss:3.6354 train_time:598663ms step_avg:216.36ms step:2778/6200 train_loss:3.6357 train_time:598876ms step_avg:216.36ms step:2779/6200 train_loss:3.4985 train_time:599090ms step_avg:216.36ms step:2780/6200 train_loss:3.3706 train_time:599305ms step_avg:216.36ms step:2781/6200 train_loss:3.5133 train_time:599518ms step_avg:216.35ms step:2782/6200 train_loss:3.5395 train_time:599730ms step_avg:216.35ms step:2783/6200 train_loss:3.3988 train_time:599943ms step_avg:216.35ms step:2784/6200 train_loss:3.5134 train_time:600156ms step_avg:216.35ms step:2785/6200 train_loss:3.5672 train_time:600369ms step_avg:216.35ms step:2786/6200 train_loss:3.4407 train_time:600584ms step_avg:216.35ms step:2787/6200 train_loss:3.5780 train_time:600797ms step_avg:216.35ms step:2788/6200 train_loss:3.5305 train_time:601011ms step_avg:216.35ms step:2789/6200 train_loss:3.4652 train_time:601225ms step_avg:216.35ms step:2790/6200 train_loss:3.5505 train_time:601437ms step_avg:216.34ms step:2791/6200 train_loss:3.4787 train_time:601649ms step_avg:216.34ms step:2792/6200 train_loss:3.3757 train_time:601861ms step_avg:216.34ms step:2793/6200 train_loss:3.4766 train_time:602075ms step_avg:216.34ms step:2794/6200 train_loss:3.5109 train_time:602289ms step_avg:216.34ms step:2795/6200 train_loss:3.4313 train_time:602504ms step_avg:216.34ms step:2796/6200 train_loss:3.4695 train_time:602718ms step_avg:216.34ms step:2797/6200 train_loss:3.3974 train_time:602931ms step_avg:216.34ms step:2798/6200 train_loss:3.5059 train_time:603143ms step_avg:216.34ms step:2799/6200 train_loss:3.4466 train_time:603355ms step_avg:216.33ms step:2800/6200 train_loss:3.6259 train_time:603567ms step_avg:216.33ms step:2801/6200 train_loss:3.5810 train_time:603781ms step_avg:216.33ms step:2802/6200 train_loss:3.5403 train_time:603994ms step_avg:216.33ms step:2803/6200 train_loss:3.4843 train_time:604207ms step_avg:216.33ms step:2804/6200 train_loss:3.6678 train_time:604422ms step_avg:216.33ms step:2805/6200 train_loss:3.6296 train_time:604636ms step_avg:216.33ms step:2806/6200 train_loss:3.3616 train_time:604849ms step_avg:216.33ms step:2807/6200 train_loss:3.7579 train_time:605063ms step_avg:216.33ms step:2808/6200 train_loss:3.5048 train_time:605276ms step_avg:216.32ms step:2809/6200 train_loss:3.4281 train_time:605489ms step_avg:216.32ms step:2810/6200 train_loss:3.4688 train_time:605703ms step_avg:216.32ms step:2811/6200 train_loss:3.6111 train_time:605916ms step_avg:216.32ms step:2812/6200 train_loss:3.6080 train_time:606130ms step_avg:216.32ms step:2813/6200 train_loss:3.3556 train_time:606342ms step_avg:216.32ms step:2814/6200 train_loss:3.5766 train_time:606555ms step_avg:216.32ms step:2815/6200 train_loss:3.6463 train_time:606768ms step_avg:216.32ms step:2816/6200 train_loss:3.4617 train_time:606982ms step_avg:216.32ms step:2817/6200 train_loss:3.2779 train_time:607195ms step_avg:216.31ms step:2818/6200 train_loss:3.4855 train_time:607409ms step_avg:216.31ms step:2819/6200 train_loss:3.4593 train_time:607625ms step_avg:216.31ms step:2820/6200 train_loss:3.6454 train_time:607838ms step_avg:216.31ms step:2821/6200 train_loss:3.6695 train_time:608052ms step_avg:216.31ms step:2822/6200 train_loss:3.5733 train_time:608264ms step_avg:216.31ms step:2823/6200 train_loss:3.5096 train_time:608478ms step_avg:216.31ms step:2824/6200 train_loss:3.4631 train_time:608691ms step_avg:216.31ms step:2825/6200 train_loss:3.3630 train_time:608905ms step_avg:216.31ms step:2826/6200 train_loss:3.6342 train_time:609119ms step_avg:216.31ms step:2827/6200 train_loss:3.5314 train_time:609333ms step_avg:216.31ms step:2828/6200 train_loss:3.4052 train_time:609546ms step_avg:216.30ms step:2829/6200 train_loss:3.5346 train_time:609760ms step_avg:216.30ms step:2830/6200 train_loss:3.5356 train_time:609973ms step_avg:216.30ms step:2831/6200 train_loss:3.4830 train_time:610187ms step_avg:216.30ms step:2832/6200 train_loss:3.6170 train_time:610402ms step_avg:216.30ms step:2833/6200 train_loss:3.5467 train_time:610615ms step_avg:216.30ms step:2834/6200 train_loss:3.5234 train_time:610828ms step_avg:216.30ms step:2835/6200 train_loss:3.3393 train_time:611296ms step_avg:216.39ms step:2836/6200 train_loss:3.5581 train_time:611510ms step_avg:216.39ms step:2837/6200 train_loss:3.4902 train_time:611724ms step_avg:216.39ms step:2838/6200 train_loss:3.8070 train_time:611938ms step_avg:216.39ms step:2839/6200 train_loss:3.4424 train_time:612150ms step_avg:216.38ms step:2840/6200 train_loss:3.4433 train_time:612363ms step_avg:216.38ms step:2841/6200 train_loss:3.5137 train_time:612576ms step_avg:216.38ms step:2842/6200 train_loss:3.4393 train_time:612789ms step_avg:216.38ms step:2843/6200 train_loss:3.4374 train_time:613004ms step_avg:216.38ms step:2844/6200 train_loss:3.6121 train_time:613218ms step_avg:216.38ms step:2845/6200 train_loss:3.5034 train_time:613432ms step_avg:216.38ms step:2846/6200 train_loss:3.5288 train_time:613643ms step_avg:216.38ms step:2847/6200 train_loss:3.4773 train_time:613857ms step_avg:216.38ms step:2848/6200 train_loss:3.7551 train_time:614071ms step_avg:216.37ms step:2849/6200 train_loss:3.4226 train_time:614285ms step_avg:216.37ms step:2850/6200 train_loss:3.4498 train_time:614749ms step_avg:216.46ms step:2851/6200 train_loss:3.5538 train_time:614960ms step_avg:216.46ms step:2852/6200 train_loss:3.5198 train_time:615174ms step_avg:216.46ms step:2853/6200 train_loss:3.4818 train_time:615386ms step_avg:216.46ms step:2854/6200 train_loss:3.5628 train_time:615601ms step_avg:216.46ms step:2855/6200 train_loss:3.3818 train_time:615830ms step_avg:216.46ms step:2856/6200 train_loss:3.4053 train_time:616043ms step_avg:216.46ms step:2857/6200 train_loss:3.4943 train_time:616255ms step_avg:216.46ms step:2858/6200 train_loss:3.5012 train_time:616468ms step_avg:216.46ms step:2859/6200 train_loss:3.3685 train_time:616682ms step_avg:216.46ms step:2860/6200 train_loss:3.4821 train_time:616896ms step_avg:216.45ms step:2861/6200 train_loss:3.4469 train_time:617110ms step_avg:216.45ms step:2862/6200 train_loss:3.4970 train_time:617326ms step_avg:216.45ms step:2863/6200 train_loss:3.5289 train_time:617539ms step_avg:216.45ms step:2864/6200 train_loss:3.8015 train_time:617751ms step_avg:216.45ms step:2865/6200 train_loss:3.6157 train_time:617964ms step_avg:216.45ms step:2866/6200 train_loss:3.4879 train_time:618179ms step_avg:216.45ms step:2867/6200 train_loss:3.3904 train_time:618392ms step_avg:216.45ms step:2868/6200 train_loss:3.5849 train_time:618605ms step_avg:216.45ms step:2869/6200 train_loss:3.5271 train_time:618820ms step_avg:216.45ms step:2870/6200 train_loss:3.4944 train_time:619033ms step_avg:216.45ms step:2871/6200 train_loss:3.6258 train_time:619245ms step_avg:216.44ms step:2872/6200 train_loss:3.4155 train_time:619459ms step_avg:216.44ms step:2873/6200 train_loss:3.4681 train_time:619672ms step_avg:216.44ms step:2874/6200 train_loss:3.3381 train_time:619886ms step_avg:216.44ms step:2875/6200 train_loss:3.4874 train_time:620100ms step_avg:216.44ms step:2875/6200 val_loss:3.4929 train_time:620102ms step_avg:216.44ms step:2876/6200 train_loss:3.4098 train_time:620318ms step_avg:216.44ms step:2877/6200 train_loss:3.3910 train_time:620532ms step_avg:216.44ms step:2878/6200 train_loss:3.4772 train_time:620748ms step_avg:216.44ms step:2879/6200 train_loss:3.5980 train_time:620960ms step_avg:216.44ms step:2880/6200 train_loss:3.5474 train_time:621173ms step_avg:216.44ms step:2881/6200 train_loss:3.4883 train_time:621386ms step_avg:216.44ms step:2882/6200 train_loss:3.4731 train_time:621600ms step_avg:216.43ms step:2883/6200 train_loss:3.6088 train_time:621813ms step_avg:216.43ms step:2884/6200 train_loss:3.3925 train_time:622028ms step_avg:216.43ms step:2885/6200 train_loss:3.4184 train_time:622242ms step_avg:216.43ms step:2886/6200 train_loss:3.4517 train_time:622455ms step_avg:216.43ms step:2887/6200 train_loss:3.4535 train_time:622668ms step_avg:216.43ms step:2888/6200 train_loss:3.4642 train_time:622881ms step_avg:216.43ms step:2889/6200 train_loss:3.4796 train_time:623094ms step_avg:216.43ms step:2890/6200 train_loss:3.6644 train_time:623308ms step_avg:216.43ms step:2891/6200 train_loss:3.5124 train_time:623521ms step_avg:216.43ms step:2892/6200 train_loss:3.3514 train_time:623734ms step_avg:216.42ms step:2893/6200 train_loss:3.2806 train_time:623948ms step_avg:216.42ms step:2894/6200 train_loss:3.4216 train_time:624161ms step_avg:216.42ms step:2895/6200 train_loss:3.2951 train_time:624375ms step_avg:216.42ms step:2896/6200 train_loss:3.4809 train_time:624588ms step_avg:216.42ms step:2897/6200 train_loss:3.6047 train_time:624801ms step_avg:216.42ms step:2898/6200 train_loss:3.4327 train_time:625013ms step_avg:216.42ms step:2899/6200 train_loss:3.5290 train_time:625229ms step_avg:216.42ms step:2900/6200 train_loss:3.4177 train_time:625443ms step_avg:216.42ms step:2901/6200 train_loss:3.5927 train_time:625657ms step_avg:216.42ms step:2902/6200 train_loss:3.5864 train_time:625870ms step_avg:216.41ms step:2903/6200 train_loss:3.6324 train_time:626082ms step_avg:216.41ms step:2904/6200 train_loss:3.3398 train_time:626295ms step_avg:216.41ms step:2905/6200 train_loss:3.4835 train_time:626509ms step_avg:216.41ms step:2906/6200 train_loss:3.4583 train_time:626722ms step_avg:216.41ms step:2907/6200 train_loss:3.5527 train_time:626935ms step_avg:216.41ms step:2908/6200 train_loss:3.4781 train_time:627149ms step_avg:216.41ms step:2909/6200 train_loss:3.4374 train_time:627364ms step_avg:216.41ms step:2910/6200 train_loss:3.7798 train_time:627577ms step_avg:216.41ms step:2911/6200 train_loss:3.4934 train_time:627790ms step_avg:216.40ms step:2912/6200 train_loss:3.3965 train_time:628004ms step_avg:216.40ms step:2913/6200 train_loss:3.3859 train_time:628218ms step_avg:216.40ms step:2914/6200 train_loss:3.8715 train_time:628432ms step_avg:216.40ms step:2915/6200 train_loss:3.4590 train_time:628646ms step_avg:216.40ms step:2916/6200 train_loss:3.4050 train_time:628859ms step_avg:216.40ms step:2917/6200 train_loss:3.3945 train_time:629071ms step_avg:216.40ms step:2918/6200 train_loss:3.6808 train_time:629284ms step_avg:216.40ms step:2919/6200 train_loss:3.1850 train_time:629497ms step_avg:216.40ms step:2920/6200 train_loss:3.3954 train_time:629711ms step_avg:216.40ms step:2921/6200 train_loss:3.4028 train_time:629925ms step_avg:216.39ms step:2922/6200 train_loss:3.4961 train_time:630137ms step_avg:216.39ms step:2923/6200 train_loss:3.5438 train_time:630352ms step_avg:216.39ms step:2924/6200 train_loss:3.5785 train_time:630565ms step_avg:216.39ms step:2925/6200 train_loss:3.5797 train_time:630778ms step_avg:216.39ms step:2926/6200 train_loss:3.4617 train_time:630991ms step_avg:216.39ms step:2927/6200 train_loss:3.4755 train_time:631204ms step_avg:216.39ms step:2928/6200 train_loss:3.4592 train_time:631418ms step_avg:216.39ms step:2929/6200 train_loss:3.4590 train_time:631631ms step_avg:216.39ms step:2930/6200 train_loss:3.4251 train_time:631848ms step_avg:216.39ms step:2931/6200 train_loss:3.4517 train_time:632059ms step_avg:216.38ms step:2932/6200 train_loss:3.5906 train_time:632273ms step_avg:216.38ms step:2933/6200 train_loss:3.6232 train_time:632486ms step_avg:216.38ms step:2934/6200 train_loss:3.6019 train_time:632700ms step_avg:216.38ms step:2935/6200 train_loss:3.4408 train_time:632918ms step_avg:216.38ms step:2936/6200 train_loss:3.4929 train_time:633131ms step_avg:216.38ms step:2937/6200 train_loss:3.4243 train_time:633346ms step_avg:216.38ms step:2938/6200 train_loss:3.4605 train_time:633558ms step_avg:216.38ms step:2939/6200 train_loss:3.4822 train_time:633771ms step_avg:216.38ms step:2940/6200 train_loss:3.5241 train_time:633984ms step_avg:216.38ms step:2941/6200 train_loss:3.5710 train_time:634198ms step_avg:216.38ms step:2942/6200 train_loss:3.5508 train_time:634411ms step_avg:216.37ms step:2943/6200 train_loss:3.4939 train_time:634624ms step_avg:216.37ms step:2944/6200 train_loss:3.3684 train_time:634837ms step_avg:216.37ms step:2945/6200 train_loss:3.3061 train_time:635050ms step_avg:216.37ms step:2946/6200 train_loss:3.5082 train_time:635264ms step_avg:216.37ms step:2947/6200 train_loss:3.5791 train_time:635476ms step_avg:216.37ms step:2948/6200 train_loss:3.5090 train_time:635689ms step_avg:216.37ms step:2949/6200 train_loss:3.6830 train_time:635903ms step_avg:216.37ms step:2950/6200 train_loss:3.5143 train_time:636117ms step_avg:216.37ms step:2951/6200 train_loss:3.5134 train_time:636330ms step_avg:216.37ms step:2952/6200 train_loss:3.9271 train_time:636544ms step_avg:216.36ms step:2953/6200 train_loss:3.5967 train_time:636758ms step_avg:216.36ms step:2954/6200 train_loss:3.5328 train_time:636970ms step_avg:216.36ms step:2955/6200 train_loss:3.5382 train_time:637183ms step_avg:216.36ms step:2956/6200 train_loss:3.4761 train_time:637397ms step_avg:216.36ms step:2957/6200 train_loss:3.5064 train_time:637611ms step_avg:216.36ms step:2958/6200 train_loss:3.3739 train_time:637824ms step_avg:216.36ms step:2959/6200 train_loss:3.4580 train_time:638039ms step_avg:216.36ms step:2960/6200 train_loss:3.6004 train_time:638252ms step_avg:216.36ms step:2961/6200 train_loss:3.4119 train_time:638465ms step_avg:216.36ms step:2962/6200 train_loss:3.5382 train_time:638678ms step_avg:216.35ms step:2963/6200 train_loss:3.3912 train_time:638891ms step_avg:216.35ms step:2964/6200 train_loss:3.4499 train_time:639104ms step_avg:216.35ms step:2965/6200 train_loss:3.4429 train_time:639317ms step_avg:216.35ms step:2966/6200 train_loss:3.5563 train_time:639532ms step_avg:216.35ms step:2967/6200 train_loss:3.4242 train_time:639747ms step_avg:216.35ms step:2968/6200 train_loss:3.6718 train_time:639960ms step_avg:216.35ms step:2969/6200 train_loss:3.5189 train_time:640173ms step_avg:216.35ms step:2970/6200 train_loss:3.5315 train_time:640386ms step_avg:216.35ms step:2971/6200 train_loss:3.5226 train_time:640600ms step_avg:216.35ms step:2972/6200 train_loss:3.5931 train_time:640813ms step_avg:216.34ms step:2973/6200 train_loss:3.4249 train_time:641027ms step_avg:216.34ms step:2974/6200 train_loss:3.4299 train_time:641242ms step_avg:216.34ms step:2975/6200 train_loss:3.3444 train_time:641455ms step_avg:216.34ms step:2976/6200 train_loss:3.4247 train_time:641668ms step_avg:216.34ms step:2977/6200 train_loss:3.4268 train_time:641879ms step_avg:216.34ms step:2978/6200 train_loss:3.4312 train_time:642092ms step_avg:216.34ms step:2979/6200 train_loss:3.7136 train_time:642306ms step_avg:216.34ms step:2980/6200 train_loss:3.5265 train_time:642519ms step_avg:216.34ms step:2981/6200 train_loss:3.5660 train_time:642734ms step_avg:216.34ms step:2982/6200 train_loss:3.5770 train_time:642948ms step_avg:216.34ms step:2983/6200 train_loss:3.6618 train_time:643163ms step_avg:216.33ms step:2984/6200 train_loss:3.4634 train_time:643376ms step_avg:216.33ms step:2985/6200 train_loss:3.5536 train_time:643589ms step_avg:216.33ms step:2986/6200 train_loss:3.5657 train_time:643803ms step_avg:216.33ms step:2987/6200 train_loss:3.5108 train_time:644017ms step_avg:216.33ms step:2988/6200 train_loss:3.6285 train_time:644231ms step_avg:216.33ms step:2989/6200 train_loss:3.2326 train_time:644447ms step_avg:216.33ms step:2990/6200 train_loss:3.5719 train_time:644660ms step_avg:216.33ms step:2991/6200 train_loss:3.5250 train_time:644873ms step_avg:216.33ms step:2992/6200 train_loss:3.5115 train_time:645087ms step_avg:216.33ms step:2993/6200 train_loss:3.4188 train_time:645300ms step_avg:216.33ms step:2994/6200 train_loss:3.5633 train_time:645513ms step_avg:216.32ms step:2995/6200 train_loss:3.3743 train_time:645728ms step_avg:216.32ms step:2996/6200 train_loss:3.4138 train_time:645942ms step_avg:216.32ms step:2997/6200 train_loss:3.4818 train_time:646156ms step_avg:216.32ms step:2998/6200 train_loss:3.4151 train_time:646369ms step_avg:216.32ms step:2999/6200 train_loss:3.5415 train_time:646582ms step_avg:216.32ms step:3000/6200 train_loss:3.4469 train_time:646796ms step_avg:216.32ms step:3000/6200 val_loss:3.4817 train_time:646798ms step_avg:216.32ms step:3001/6200 train_loss:3.4354 train_time:647014ms step_avg:216.32ms step:3002/6200 train_loss:3.3743 train_time:647228ms step_avg:216.32ms step:3003/6200 train_loss:3.4187 train_time:647441ms step_avg:216.32ms step:3004/6200 train_loss:3.5490 train_time:647656ms step_avg:216.32ms step:3005/6200 train_loss:3.8962 train_time:647871ms step_avg:216.32ms step:3006/6200 train_loss:3.4658 train_time:648083ms step_avg:216.32ms step:3007/6200 train_loss:3.5343 train_time:648297ms step_avg:216.32ms step:3008/6200 train_loss:3.3473 train_time:648512ms step_avg:216.31ms step:3009/6200 train_loss:3.5639 train_time:648726ms step_avg:216.31ms step:3010/6200 train_loss:3.4528 train_time:648939ms step_avg:216.31ms step:3011/6200 train_loss:3.5158 train_time:649155ms step_avg:216.31ms step:3012/6200 train_loss:3.5178 train_time:649367ms step_avg:216.31ms step:3013/6200 train_loss:3.4119 train_time:649580ms step_avg:216.31ms step:3014/6200 train_loss:3.6066 train_time:649794ms step_avg:216.31ms step:3015/6200 train_loss:3.5764 train_time:650007ms step_avg:216.31ms step:3016/6200 train_loss:3.4300 train_time:650221ms step_avg:216.31ms step:3017/6200 train_loss:3.4662 train_time:650437ms step_avg:216.31ms step:3018/6200 train_loss:3.5166 train_time:650652ms step_avg:216.31ms step:3019/6200 train_loss:3.5395 train_time:650864ms step_avg:216.31ms step:3020/6200 train_loss:3.3453 train_time:651078ms step_avg:216.30ms step:3021/6200 train_loss:3.6303 train_time:651291ms step_avg:216.30ms step:3022/6200 train_loss:3.4670 train_time:651504ms step_avg:216.30ms step:3023/6200 train_loss:3.3892 train_time:651718ms step_avg:216.30ms step:3024/6200 train_loss:3.4815 train_time:652186ms step_avg:216.39ms step:3025/6200 train_loss:3.4674 train_time:652399ms step_avg:216.38ms step:3026/6200 train_loss:3.5169 train_time:652613ms step_avg:216.38ms step:3027/6200 train_loss:3.5398 train_time:652828ms step_avg:216.38ms step:3028/6200 train_loss:3.4451 train_time:653040ms step_avg:216.38ms step:3029/6200 train_loss:3.2512 train_time:653255ms step_avg:216.38ms step:3030/6200 train_loss:3.5911 train_time:653467ms step_avg:216.38ms step:3031/6200 train_loss:3.3497 train_time:653680ms step_avg:216.38ms step:3032/6200 train_loss:3.3452 train_time:653893ms step_avg:216.38ms step:3033/6200 train_loss:3.6880 train_time:654106ms step_avg:216.38ms step:3034/6200 train_loss:3.6769 train_time:654319ms step_avg:216.38ms step:3035/6200 train_loss:3.4444 train_time:654534ms step_avg:216.37ms step:3036/6200 train_loss:3.5222 train_time:654747ms step_avg:216.37ms step:3037/6200 train_loss:3.4828 train_time:654960ms step_avg:216.37ms step:3038/6200 train_loss:3.3741 train_time:655176ms step_avg:216.37ms step:3039/6200 train_loss:3.4346 train_time:655389ms step_avg:216.37ms step:3040/6200 train_loss:3.5341 train_time:655851ms step_avg:216.45ms step:3041/6200 train_loss:3.5216 train_time:656063ms step_avg:216.45ms step:3042/6200 train_loss:3.3230 train_time:656277ms step_avg:216.45ms step:3043/6200 train_loss:3.4677 train_time:656490ms step_avg:216.45ms step:3044/6200 train_loss:3.4982 train_time:656704ms step_avg:216.45ms step:3045/6200 train_loss:3.5103 train_time:656918ms step_avg:216.45ms step:3046/6200 train_loss:3.5911 train_time:657132ms step_avg:216.45ms step:3047/6200 train_loss:3.4030 train_time:657346ms step_avg:216.45ms step:3048/6200 train_loss:3.5207 train_time:657559ms step_avg:216.44ms step:3049/6200 train_loss:3.4742 train_time:657773ms step_avg:216.44ms step:3050/6200 train_loss:3.4076 train_time:657985ms step_avg:216.44ms step:3051/6200 train_loss:3.5335 train_time:658199ms step_avg:216.44ms step:3052/6200 train_loss:3.3726 train_time:658412ms step_avg:216.44ms step:3053/6200 train_loss:3.6231 train_time:658626ms step_avg:216.44ms step:3054/6200 train_loss:3.5668 train_time:658839ms step_avg:216.44ms step:3055/6200 train_loss:3.5450 train_time:659054ms step_avg:216.44ms step:3056/6200 train_loss:3.5398 train_time:659267ms step_avg:216.44ms step:3057/6200 train_loss:3.4258 train_time:659479ms step_avg:216.44ms step:3058/6200 train_loss:3.4586 train_time:659692ms step_avg:216.43ms step:3059/6200 train_loss:3.5378 train_time:659906ms step_avg:216.43ms step:3060/6200 train_loss:3.4290 train_time:660119ms step_avg:216.43ms step:3061/6200 train_loss:3.4913 train_time:660333ms step_avg:216.43ms step:3062/6200 train_loss:3.4881 train_time:660546ms step_avg:216.43ms step:3063/6200 train_loss:3.4207 train_time:660759ms step_avg:216.43ms step:3064/6200 train_loss:3.4069 train_time:660973ms step_avg:216.43ms step:3065/6200 train_loss:3.4229 train_time:661185ms step_avg:216.43ms step:3066/6200 train_loss:3.4036 train_time:661398ms step_avg:216.43ms step:3067/6200 train_loss:3.3967 train_time:661611ms step_avg:216.43ms step:3068/6200 train_loss:3.3498 train_time:661825ms step_avg:216.42ms step:3069/6200 train_loss:3.3936 train_time:662039ms step_avg:216.42ms step:3070/6200 train_loss:3.3896 train_time:662253ms step_avg:216.42ms step:3071/6200 train_loss:3.5705 train_time:662465ms step_avg:216.42ms step:3072/6200 train_loss:3.4970 train_time:662678ms step_avg:216.42ms step:3073/6200 train_loss:3.5384 train_time:662890ms step_avg:216.42ms step:3074/6200 train_loss:3.5324 train_time:663104ms step_avg:216.42ms step:3075/6200 train_loss:3.4796 train_time:663319ms step_avg:216.42ms step:3076/6200 train_loss:3.5264 train_time:663533ms step_avg:216.42ms step:3077/6200 train_loss:3.5803 train_time:663747ms step_avg:216.42ms step:3078/6200 train_loss:3.3825 train_time:663964ms step_avg:216.42ms step:3079/6200 train_loss:3.9302 train_time:664177ms step_avg:216.41ms step:3080/6200 train_loss:3.4818 train_time:664390ms step_avg:216.41ms step:3081/6200 train_loss:3.4375 train_time:664604ms step_avg:216.41ms step:3082/6200 train_loss:3.5834 train_time:664818ms step_avg:216.41ms step:3083/6200 train_loss:3.3991 train_time:665031ms step_avg:216.41ms step:3084/6200 train_loss:3.4233 train_time:665246ms step_avg:216.41ms step:3085/6200 train_loss:3.4736 train_time:665459ms step_avg:216.41ms step:3086/6200 train_loss:3.5706 train_time:665673ms step_avg:216.41ms step:3087/6200 train_loss:3.4799 train_time:665886ms step_avg:216.41ms step:3088/6200 train_loss:3.3962 train_time:666099ms step_avg:216.41ms step:3089/6200 train_loss:3.5472 train_time:666313ms step_avg:216.41ms step:3090/6200 train_loss:3.4079 train_time:666527ms step_avg:216.41ms step:3091/6200 train_loss:3.6687 train_time:666741ms step_avg:216.40ms step:3092/6200 train_loss:4.2269 train_time:666955ms step_avg:216.40ms step:3093/6200 train_loss:3.5067 train_time:667168ms step_avg:216.40ms step:3094/6200 train_loss:3.4005 train_time:667381ms step_avg:216.40ms step:3095/6200 train_loss:3.3522 train_time:667594ms step_avg:216.40ms step:3096/6200 train_loss:3.5287 train_time:667809ms step_avg:216.40ms step:3097/6200 train_loss:3.6454 train_time:668022ms step_avg:216.40ms step:3098/6200 train_loss:3.4254 train_time:668237ms step_avg:216.40ms step:3099/6200 train_loss:3.4648 train_time:668451ms step_avg:216.40ms step:3100/6200 train_loss:3.6369 train_time:668664ms step_avg:216.40ms step:3101/6200 train_loss:3.5396 train_time:668877ms step_avg:216.40ms step:3102/6200 train_loss:3.5350 train_time:669090ms step_avg:216.39ms step:3103/6200 train_loss:3.4353 train_time:669303ms step_avg:216.39ms step:3104/6200 train_loss:3.6954 train_time:669518ms step_avg:216.39ms step:3105/6200 train_loss:3.5119 train_time:669731ms step_avg:216.39ms step:3106/6200 train_loss:3.3683 train_time:669945ms step_avg:216.39ms step:3107/6200 train_loss:3.4010 train_time:670160ms step_avg:216.39ms step:3108/6200 train_loss:3.3591 train_time:670373ms step_avg:216.39ms step:3109/6200 train_loss:3.5802 train_time:670585ms step_avg:216.39ms step:3110/6200 train_loss:3.4687 train_time:670798ms step_avg:216.39ms step:3111/6200 train_loss:3.5039 train_time:671011ms step_avg:216.39ms step:3112/6200 train_loss:3.4861 train_time:671225ms step_avg:216.38ms step:3113/6200 train_loss:3.5415 train_time:671440ms step_avg:216.38ms step:3114/6200 train_loss:3.4814 train_time:671654ms step_avg:216.38ms step:3115/6200 train_loss:3.5010 train_time:671866ms step_avg:216.38ms step:3116/6200 train_loss:3.5212 train_time:672079ms step_avg:216.38ms step:3117/6200 train_loss:3.3882 train_time:672292ms step_avg:216.38ms step:3118/6200 train_loss:3.3980 train_time:672505ms step_avg:216.38ms step:3119/6200 train_loss:3.5924 train_time:672719ms step_avg:216.38ms step:3120/6200 train_loss:3.5649 train_time:672931ms step_avg:216.38ms step:3121/6200 train_loss:3.3503 train_time:673145ms step_avg:216.38ms step:3122/6200 train_loss:3.5429 train_time:673359ms step_avg:216.38ms step:3123/6200 train_loss:3.5980 train_time:673572ms step_avg:216.37ms step:3124/6200 train_loss:3.5697 train_time:673785ms step_avg:216.37ms step:3125/6200 train_loss:3.3612 train_time:673998ms step_avg:216.37ms step:3125/6200 val_loss:3.4752 train_time:674000ms step_avg:216.37ms step:3126/6200 train_loss:3.4428 train_time:674217ms step_avg:216.37ms step:3127/6200 train_loss:3.5043 train_time:674431ms step_avg:216.37ms step:3128/6200 train_loss:3.5740 train_time:674645ms step_avg:216.37ms step:3129/6200 train_loss:3.6382 train_time:674859ms step_avg:216.37ms step:3130/6200 train_loss:3.3469 train_time:675072ms step_avg:216.37ms step:3131/6200 train_loss:3.5144 train_time:675286ms step_avg:216.37ms step:3132/6200 train_loss:3.5094 train_time:675498ms step_avg:216.37ms step:3133/6200 train_loss:3.5267 train_time:675712ms step_avg:216.37ms step:3134/6200 train_loss:3.4380 train_time:675926ms step_avg:216.37ms step:3135/6200 train_loss:3.5475 train_time:676139ms step_avg:216.36ms step:3136/6200 train_loss:3.4640 train_time:676353ms step_avg:216.36ms step:3137/6200 train_loss:3.5222 train_time:676568ms step_avg:216.36ms step:3138/6200 train_loss:3.7221 train_time:676782ms step_avg:216.36ms step:3139/6200 train_loss:3.6788 train_time:676995ms step_avg:216.36ms step:3140/6200 train_loss:3.4512 train_time:677209ms step_avg:216.36ms step:3141/6200 train_loss:3.4702 train_time:677424ms step_avg:216.36ms step:3142/6200 train_loss:3.3892 train_time:677636ms step_avg:216.36ms step:3143/6200 train_loss:3.4846 train_time:677856ms step_avg:216.36ms step:3144/6200 train_loss:3.2847 train_time:678071ms step_avg:216.36ms step:3145/6200 train_loss:3.5279 train_time:678284ms step_avg:216.36ms step:3146/6200 train_loss:3.4396 train_time:678497ms step_avg:216.36ms step:3147/6200 train_loss:3.4594 train_time:678710ms step_avg:216.36ms step:3148/6200 train_loss:3.6316 train_time:678923ms step_avg:216.36ms step:3149/6200 train_loss:3.7207 train_time:679137ms step_avg:216.35ms step:3150/6200 train_loss:3.5848 train_time:679350ms step_avg:216.35ms step:3151/6200 train_loss:3.3973 train_time:679565ms step_avg:216.35ms step:3152/6200 train_loss:3.4407 train_time:679779ms step_avg:216.35ms step:3153/6200 train_loss:3.4269 train_time:679991ms step_avg:216.35ms step:3154/6200 train_loss:3.5395 train_time:680204ms step_avg:216.35ms step:3155/6200 train_loss:3.3596 train_time:680417ms step_avg:216.35ms step:3156/6200 train_loss:3.5008 train_time:680631ms step_avg:216.35ms step:3157/6200 train_loss:3.4478 train_time:680845ms step_avg:216.35ms step:3158/6200 train_loss:3.5657 train_time:681058ms step_avg:216.35ms step:3159/6200 train_loss:3.6213 train_time:681276ms step_avg:216.35ms step:3160/6200 train_loss:3.4701 train_time:681489ms step_avg:216.35ms step:3161/6200 train_loss:3.5352 train_time:681700ms step_avg:216.34ms step:3162/6200 train_loss:3.6035 train_time:681915ms step_avg:216.34ms step:3163/6200 train_loss:3.5080 train_time:682129ms step_avg:216.34ms step:3164/6200 train_loss:3.5664 train_time:682342ms step_avg:216.34ms step:3165/6200 train_loss:3.3864 train_time:682556ms step_avg:216.34ms step:3166/6200 train_loss:3.3729 train_time:682771ms step_avg:216.34ms step:3167/6200 train_loss:3.4085 train_time:682985ms step_avg:216.34ms step:3168/6200 train_loss:3.2403 train_time:683198ms step_avg:216.34ms step:3169/6200 train_loss:3.4022 train_time:683411ms step_avg:216.34ms step:3170/6200 train_loss:3.5485 train_time:683625ms step_avg:216.34ms step:3171/6200 train_loss:3.5729 train_time:683838ms step_avg:216.34ms step:3172/6200 train_loss:3.5389 train_time:684052ms step_avg:216.34ms step:3173/6200 train_loss:3.5071 train_time:684266ms step_avg:216.33ms step:3174/6200 train_loss:3.4819 train_time:684479ms step_avg:216.33ms step:3175/6200 train_loss:3.4791 train_time:684691ms step_avg:216.33ms step:3176/6200 train_loss:3.4848 train_time:684904ms step_avg:216.33ms step:3177/6200 train_loss:3.4088 train_time:685117ms step_avg:216.33ms step:3178/6200 train_loss:3.5397 train_time:685331ms step_avg:216.33ms step:3179/6200 train_loss:3.6155 train_time:685545ms step_avg:216.33ms step:3180/6200 train_loss:3.4582 train_time:685757ms step_avg:216.33ms step:3181/6200 train_loss:3.4450 train_time:685974ms step_avg:216.33ms step:3182/6200 train_loss:3.4830 train_time:686188ms step_avg:216.33ms step:3183/6200 train_loss:3.5904 train_time:686400ms step_avg:216.33ms step:3184/6200 train_loss:3.6085 train_time:686613ms step_avg:216.32ms step:3185/6200 train_loss:3.5064 train_time:686827ms step_avg:216.32ms step:3186/6200 train_loss:3.5755 train_time:687042ms step_avg:216.32ms step:3187/6200 train_loss:3.5590 train_time:687256ms step_avg:216.32ms step:3188/6200 train_loss:3.3490 train_time:687471ms step_avg:216.32ms step:3189/6200 train_loss:3.5175 train_time:687684ms step_avg:216.32ms step:3190/6200 train_loss:3.4633 train_time:687897ms step_avg:216.32ms step:3191/6200 train_loss:3.4911 train_time:688111ms step_avg:216.32ms step:3192/6200 train_loss:3.4478 train_time:688324ms step_avg:216.32ms step:3193/6200 train_loss:3.3836 train_time:688537ms step_avg:216.32ms step:3194/6200 train_loss:4.3995 train_time:688752ms step_avg:216.32ms step:3195/6200 train_loss:3.5047 train_time:688968ms step_avg:216.32ms step:3196/6200 train_loss:3.2871 train_time:689180ms step_avg:216.32ms step:3197/6200 train_loss:3.4541 train_time:689392ms step_avg:216.31ms step:3198/6200 train_loss:3.3306 train_time:689605ms step_avg:216.31ms step:3199/6200 train_loss:3.4390 train_time:689819ms step_avg:216.31ms step:3200/6200 train_loss:3.3660 train_time:690035ms step_avg:216.31ms step:3201/6200 train_loss:3.4504 train_time:690249ms step_avg:216.31ms step:3202/6200 train_loss:3.5469 train_time:690463ms step_avg:216.31ms step:3203/6200 train_loss:3.3962 train_time:690676ms step_avg:216.31ms step:3204/6200 train_loss:3.4431 train_time:690889ms step_avg:216.31ms step:3205/6200 train_loss:3.5229 train_time:691101ms step_avg:216.31ms step:3206/6200 train_loss:3.6788 train_time:691313ms step_avg:216.31ms step:3207/6200 train_loss:3.2873 train_time:691527ms step_avg:216.31ms step:3208/6200 train_loss:3.6353 train_time:691741ms step_avg:216.30ms step:3209/6200 train_loss:3.4859 train_time:691954ms step_avg:216.30ms step:3210/6200 train_loss:3.5583 train_time:692169ms step_avg:216.30ms step:3211/6200 train_loss:3.6543 train_time:692382ms step_avg:216.30ms step:3212/6200 train_loss:3.3268 train_time:692596ms step_avg:216.30ms step:3213/6200 train_loss:3.3804 train_time:693064ms step_avg:216.38ms step:3214/6200 train_loss:3.5913 train_time:693279ms step_avg:216.38ms step:3215/6200 train_loss:3.3893 train_time:693491ms step_avg:216.38ms step:3216/6200 train_loss:3.4530 train_time:693704ms step_avg:216.38ms step:3217/6200 train_loss:3.3462 train_time:693918ms step_avg:216.38ms step:3218/6200 train_loss:3.4841 train_time:694132ms step_avg:216.38ms step:3219/6200 train_loss:3.5259 train_time:694347ms step_avg:216.37ms step:3220/6200 train_loss:3.5740 train_time:694560ms step_avg:216.37ms step:3221/6200 train_loss:3.5219 train_time:694773ms step_avg:216.37ms step:3222/6200 train_loss:3.5078 train_time:694986ms step_avg:216.37ms step:3223/6200 train_loss:3.3811 train_time:695198ms step_avg:216.37ms step:3224/6200 train_loss:3.4066 train_time:695412ms step_avg:216.37ms step:3225/6200 train_loss:3.4127 train_time:695626ms step_avg:216.37ms step:3226/6200 train_loss:3.4456 train_time:695839ms step_avg:216.37ms step:3227/6200 train_loss:3.3753 train_time:696052ms step_avg:216.37ms step:3228/6200 train_loss:3.2947 train_time:696267ms step_avg:216.37ms step:3229/6200 train_loss:3.4200 train_time:696480ms step_avg:216.37ms step:3230/6200 train_loss:3.1957 train_time:696958ms step_avg:216.45ms step:3231/6200 train_loss:3.3762 train_time:697171ms step_avg:216.45ms step:3232/6200 train_loss:3.3642 train_time:697385ms step_avg:216.44ms step:3233/6200 train_loss:3.6113 train_time:697596ms step_avg:216.44ms step:3234/6200 train_loss:3.5870 train_time:697810ms step_avg:216.44ms step:3235/6200 train_loss:3.5526 train_time:698024ms step_avg:216.44ms step:3236/6200 train_loss:3.4468 train_time:698237ms step_avg:216.44ms step:3237/6200 train_loss:3.6037 train_time:698451ms step_avg:216.44ms step:3238/6200 train_loss:3.4653 train_time:698664ms step_avg:216.44ms step:3239/6200 train_loss:3.5950 train_time:698877ms step_avg:216.44ms step:3240/6200 train_loss:3.5568 train_time:699089ms step_avg:216.44ms step:3241/6200 train_loss:3.4618 train_time:699302ms step_avg:216.44ms step:3242/6200 train_loss:3.4122 train_time:699518ms step_avg:216.43ms step:3243/6200 train_loss:3.6415 train_time:699731ms step_avg:216.43ms step:3244/6200 train_loss:3.5038 train_time:699945ms step_avg:216.43ms step:3245/6200 train_loss:3.5582 train_time:700159ms step_avg:216.43ms step:3246/6200 train_loss:3.4427 train_time:700372ms step_avg:216.43ms step:3247/6200 train_loss:3.5765 train_time:700585ms step_avg:216.43ms step:3248/6200 train_loss:3.5083 train_time:700798ms step_avg:216.43ms step:3249/6200 train_loss:3.4523 train_time:701010ms step_avg:216.43ms step:3250/6200 train_loss:3.3303 train_time:701223ms step_avg:216.43ms step:3250/6200 val_loss:3.4650 train_time:701225ms step_avg:216.43ms step:3251/6200 train_loss:3.5215 train_time:701440ms step_avg:216.43ms step:3252/6200 train_loss:3.5190 train_time:701655ms step_avg:216.43ms step:3253/6200 train_loss:3.4744 train_time:701869ms step_avg:216.43ms step:3254/6200 train_loss:3.3998 train_time:702084ms step_avg:216.43ms step:3255/6200 train_loss:3.5480 train_time:702297ms step_avg:216.42ms step:3256/6200 train_loss:3.5770 train_time:702509ms step_avg:216.42ms step:3257/6200 train_loss:3.5184 train_time:702723ms step_avg:216.42ms step:3258/6200 train_loss:3.5432 train_time:702936ms step_avg:216.42ms step:3259/6200 train_loss:3.3909 train_time:703149ms step_avg:216.42ms step:3260/6200 train_loss:3.4712 train_time:703364ms step_avg:216.42ms step:3261/6200 train_loss:3.3356 train_time:703578ms step_avg:216.42ms step:3262/6200 train_loss:3.3761 train_time:703791ms step_avg:216.42ms step:3263/6200 train_loss:3.4124 train_time:704008ms step_avg:216.42ms step:3264/6200 train_loss:3.5624 train_time:704220ms step_avg:216.42ms step:3265/6200 train_loss:3.4417 train_time:704433ms step_avg:216.42ms step:3266/6200 train_loss:3.4984 train_time:704647ms step_avg:216.42ms step:3267/6200 train_loss:3.5205 train_time:704861ms step_avg:216.41ms step:3268/6200 train_loss:3.6066 train_time:705074ms step_avg:216.41ms step:3269/6200 train_loss:3.4101 train_time:705289ms step_avg:216.41ms step:3270/6200 train_loss:3.5376 train_time:705502ms step_avg:216.41ms step:3271/6200 train_loss:3.4066 train_time:705714ms step_avg:216.41ms step:3272/6200 train_loss:3.3091 train_time:705927ms step_avg:216.41ms step:3273/6200 train_loss:3.4149 train_time:706141ms step_avg:216.41ms step:3274/6200 train_loss:3.5598 train_time:706354ms step_avg:216.41ms step:3275/6200 train_loss:3.3507 train_time:706568ms step_avg:216.41ms step:3276/6200 train_loss:3.5018 train_time:706782ms step_avg:216.41ms step:3277/6200 train_loss:3.4953 train_time:706996ms step_avg:216.41ms step:3278/6200 train_loss:3.4882 train_time:707209ms step_avg:216.40ms step:3279/6200 train_loss:3.4626 train_time:707423ms step_avg:216.40ms step:3280/6200 train_loss:3.6113 train_time:707636ms step_avg:216.40ms step:3281/6200 train_loss:3.4579 train_time:707849ms step_avg:216.40ms step:3282/6200 train_loss:3.5148 train_time:708067ms step_avg:216.40ms step:3283/6200 train_loss:3.3642 train_time:708281ms step_avg:216.40ms step:3284/6200 train_loss:3.5014 train_time:708494ms step_avg:216.40ms step:3285/6200 train_loss:3.5555 train_time:708707ms step_avg:216.40ms step:3286/6200 train_loss:3.5355 train_time:708919ms step_avg:216.40ms step:3287/6200 train_loss:3.5737 train_time:709133ms step_avg:216.40ms step:3288/6200 train_loss:3.4434 train_time:709348ms step_avg:216.40ms step:3289/6200 train_loss:3.5491 train_time:709563ms step_avg:216.40ms step:3290/6200 train_loss:3.4767 train_time:709776ms step_avg:216.40ms step:3291/6200 train_loss:3.3608 train_time:709990ms step_avg:216.39ms step:3292/6200 train_loss:3.4866 train_time:710203ms step_avg:216.39ms step:3293/6200 train_loss:3.5248 train_time:710416ms step_avg:216.39ms step:3294/6200 train_loss:3.5042 train_time:710629ms step_avg:216.39ms step:3295/6200 train_loss:3.3837 train_time:710843ms step_avg:216.39ms step:3296/6200 train_loss:3.4491 train_time:711057ms step_avg:216.39ms step:3297/6200 train_loss:3.4875 train_time:711271ms step_avg:216.39ms step:3298/6200 train_loss:3.4846 train_time:711487ms step_avg:216.39ms step:3299/6200 train_loss:3.4742 train_time:711700ms step_avg:216.39ms step:3300/6200 train_loss:3.5313 train_time:711913ms step_avg:216.39ms step:3301/6200 train_loss:3.4321 train_time:712126ms step_avg:216.39ms step:3302/6200 train_loss:3.4988 train_time:712340ms step_avg:216.39ms step:3303/6200 train_loss:3.4536 train_time:712554ms step_avg:216.38ms step:3304/6200 train_loss:3.4623 train_time:712768ms step_avg:216.38ms step:3305/6200 train_loss:3.4550 train_time:712983ms step_avg:216.38ms step:3306/6200 train_loss:3.5588 train_time:713196ms step_avg:216.38ms step:3307/6200 train_loss:3.4831 train_time:713408ms step_avg:216.38ms step:3308/6200 train_loss:3.4493 train_time:713622ms step_avg:216.38ms step:3309/6200 train_loss:3.5714 train_time:713835ms step_avg:216.38ms step:3310/6200 train_loss:3.4493 train_time:714049ms step_avg:216.38ms step:3311/6200 train_loss:3.3841 train_time:714263ms step_avg:216.38ms step:3312/6200 train_loss:3.4979 train_time:714476ms step_avg:216.38ms step:3313/6200 train_loss:3.4648 train_time:714691ms step_avg:216.38ms step:3314/6200 train_loss:3.6652 train_time:714905ms step_avg:216.38ms step:3315/6200 train_loss:3.4967 train_time:715117ms step_avg:216.37ms step:3316/6200 train_loss:3.4659 train_time:715330ms step_avg:216.37ms step:3317/6200 train_loss:3.0964 train_time:715544ms step_avg:216.37ms step:3318/6200 train_loss:3.5976 train_time:715757ms step_avg:216.37ms step:3319/6200 train_loss:3.4421 train_time:715969ms step_avg:216.37ms step:3320/6200 train_loss:3.5107 train_time:716185ms step_avg:216.37ms step:3321/6200 train_loss:3.4457 train_time:716396ms step_avg:216.37ms step:3322/6200 train_loss:3.5163 train_time:716610ms step_avg:216.37ms step:3323/6200 train_loss:3.4530 train_time:716823ms step_avg:216.37ms step:3324/6200 train_loss:3.3777 train_time:717037ms step_avg:216.37ms step:3325/6200 train_loss:3.3195 train_time:717250ms step_avg:216.36ms step:3326/6200 train_loss:3.4733 train_time:717464ms step_avg:216.36ms step:3327/6200 train_loss:3.4349 train_time:717676ms step_avg:216.36ms step:3328/6200 train_loss:3.3614 train_time:717889ms step_avg:216.36ms step:3329/6200 train_loss:3.3978 train_time:718102ms step_avg:216.36ms step:3330/6200 train_loss:3.3556 train_time:718314ms step_avg:216.36ms step:3331/6200 train_loss:3.6004 train_time:718527ms step_avg:216.36ms step:3332/6200 train_loss:3.5090 train_time:718741ms step_avg:216.36ms step:3333/6200 train_loss:3.4851 train_time:718954ms step_avg:216.36ms step:3334/6200 train_loss:3.3416 train_time:719168ms step_avg:216.36ms step:3335/6200 train_loss:3.4098 train_time:719382ms step_avg:216.36ms step:3336/6200 train_loss:3.5195 train_time:719596ms step_avg:216.35ms step:3337/6200 train_loss:3.4887 train_time:719808ms step_avg:216.35ms step:3338/6200 train_loss:3.5168 train_time:720021ms step_avg:216.35ms step:3339/6200 train_loss:3.4541 train_time:720234ms step_avg:216.35ms step:3340/6200 train_loss:3.4797 train_time:720448ms step_avg:216.35ms step:3341/6200 train_loss:3.4912 train_time:720662ms step_avg:216.35ms step:3342/6200 train_loss:3.4987 train_time:720875ms step_avg:216.35ms step:3343/6200 train_loss:3.4903 train_time:721089ms step_avg:216.35ms step:3344/6200 train_loss:3.4203 train_time:721302ms step_avg:216.35ms step:3345/6200 train_loss:3.3313 train_time:721515ms step_avg:216.35ms step:3346/6200 train_loss:3.6595 train_time:721728ms step_avg:216.35ms step:3347/6200 train_loss:3.4181 train_time:721941ms step_avg:216.34ms step:3348/6200 train_loss:3.5844 train_time:722155ms step_avg:216.34ms step:3349/6200 train_loss:3.4579 train_time:722369ms step_avg:216.34ms step:3350/6200 train_loss:3.5318 train_time:722583ms step_avg:216.34ms step:3351/6200 train_loss:3.2716 train_time:722796ms step_avg:216.34ms step:3352/6200 train_loss:3.3070 train_time:723008ms step_avg:216.34ms step:3353/6200 train_loss:3.4739 train_time:723221ms step_avg:216.34ms step:3354/6200 train_loss:3.3405 train_time:723435ms step_avg:216.34ms step:3355/6200 train_loss:3.5021 train_time:723649ms step_avg:216.34ms step:3356/6200 train_loss:3.3628 train_time:723863ms step_avg:216.34ms step:3357/6200 train_loss:3.5388 train_time:724077ms step_avg:216.34ms step:3358/6200 train_loss:3.3888 train_time:724291ms step_avg:216.34ms step:3359/6200 train_loss:3.5597 train_time:724504ms step_avg:216.33ms step:3360/6200 train_loss:3.3764 train_time:724718ms step_avg:216.33ms step:3361/6200 train_loss:4.2843 train_time:724931ms step_avg:216.33ms step:3362/6200 train_loss:3.5292 train_time:725145ms step_avg:216.33ms step:3363/6200 train_loss:3.5668 train_time:725358ms step_avg:216.33ms step:3364/6200 train_loss:3.4359 train_time:725571ms step_avg:216.33ms step:3365/6200 train_loss:3.5544 train_time:725787ms step_avg:216.33ms step:3366/6200 train_loss:3.4560 train_time:726001ms step_avg:216.33ms step:3367/6200 train_loss:3.6232 train_time:726215ms step_avg:216.33ms step:3368/6200 train_loss:3.4386 train_time:726428ms step_avg:216.33ms step:3369/6200 train_loss:3.4512 train_time:726642ms step_avg:216.33ms step:3370/6200 train_loss:3.4208 train_time:726856ms step_avg:216.33ms step:3371/6200 train_loss:3.3886 train_time:727069ms step_avg:216.33ms step:3372/6200 train_loss:3.3915 train_time:727284ms step_avg:216.32ms step:3373/6200 train_loss:3.4474 train_time:727496ms step_avg:216.32ms step:3374/6200 train_loss:3.4815 train_time:727709ms step_avg:216.32ms step:3375/6200 train_loss:3.4486 train_time:727922ms step_avg:216.32ms step:3375/6200 val_loss:3.4607 train_time:727924ms step_avg:216.32ms step:3376/6200 train_loss:3.4965 train_time:728138ms step_avg:216.32ms step:3377/6200 train_loss:3.4960 train_time:728353ms step_avg:216.32ms step:3378/6200 train_loss:3.5705 train_time:728565ms step_avg:216.32ms step:3379/6200 train_loss:3.4333 train_time:728780ms step_avg:216.32ms step:3380/6200 train_loss:3.4408 train_time:728993ms step_avg:216.32ms step:3381/6200 train_loss:3.4442 train_time:729207ms step_avg:216.32ms step:3382/6200 train_loss:3.5465 train_time:729420ms step_avg:216.32ms step:3383/6200 train_loss:3.3851 train_time:729633ms step_avg:216.32ms step:3384/6200 train_loss:3.5611 train_time:729846ms step_avg:216.31ms step:3385/6200 train_loss:3.4128 train_time:730060ms step_avg:216.31ms step:3386/6200 train_loss:3.4390 train_time:730274ms step_avg:216.31ms step:3387/6200 train_loss:3.3771 train_time:730488ms step_avg:216.31ms step:3388/6200 train_loss:3.5561 train_time:730704ms step_avg:216.31ms step:3389/6200 train_loss:3.5243 train_time:730917ms step_avg:216.31ms step:3390/6200 train_loss:3.5385 train_time:731130ms step_avg:216.31ms step:3391/6200 train_loss:3.5191 train_time:731343ms step_avg:216.31ms step:3392/6200 train_loss:3.4541 train_time:731557ms step_avg:216.31ms step:3393/6200 train_loss:3.5795 train_time:731770ms step_avg:216.31ms step:3394/6200 train_loss:3.5362 train_time:731985ms step_avg:216.31ms step:3395/6200 train_loss:3.6258 train_time:732200ms step_avg:216.31ms step:3396/6200 train_loss:3.4806 train_time:732413ms step_avg:216.31ms step:3397/6200 train_loss:3.4755 train_time:732626ms step_avg:216.31ms step:3398/6200 train_loss:3.4244 train_time:732839ms step_avg:216.30ms step:3399/6200 train_loss:3.4840 train_time:733052ms step_avg:216.30ms step:3400/6200 train_loss:3.4736 train_time:733266ms step_avg:216.30ms step:3401/6200 train_loss:3.5666 train_time:733480ms step_avg:216.30ms step:3402/6200 train_loss:3.4331 train_time:733947ms step_avg:216.38ms step:3403/6200 train_loss:3.6209 train_time:734161ms step_avg:216.38ms step:3404/6200 train_loss:3.4461 train_time:734375ms step_avg:216.37ms step:3405/6200 train_loss:3.4584 train_time:734588ms step_avg:216.37ms step:3406/6200 train_loss:3.4073 train_time:734804ms step_avg:216.37ms step:3407/6200 train_loss:3.4723 train_time:735018ms step_avg:216.37ms step:3408/6200 train_loss:3.4663 train_time:735231ms step_avg:216.37ms step:3409/6200 train_loss:3.4556 train_time:735445ms step_avg:216.37ms step:3410/6200 train_loss:3.4654 train_time:735658ms step_avg:216.37ms step:3411/6200 train_loss:3.4328 train_time:735872ms step_avg:216.37ms step:3412/6200 train_loss:3.4684 train_time:736085ms step_avg:216.37ms step:3413/6200 train_loss:3.3943 train_time:736300ms step_avg:216.37ms step:3414/6200 train_loss:3.6164 train_time:736513ms step_avg:216.37ms step:3415/6200 train_loss:3.3655 train_time:736725ms step_avg:216.37ms step:3416/6200 train_loss:3.5182 train_time:736937ms step_avg:216.36ms step:3417/6200 train_loss:3.4007 train_time:737151ms step_avg:216.36ms step:3418/6200 train_loss:3.4960 train_time:737364ms step_avg:216.36ms step:3419/6200 train_loss:3.5047 train_time:737578ms step_avg:216.36ms step:3420/6200 train_loss:3.5285 train_time:738055ms step_avg:216.44ms step:3421/6200 train_loss:3.4105 train_time:738268ms step_avg:216.44ms step:3422/6200 train_loss:3.4431 train_time:738483ms step_avg:216.44ms step:3423/6200 train_loss:3.3772 train_time:738700ms step_avg:216.44ms step:3424/6200 train_loss:3.7038 train_time:738913ms step_avg:216.44ms step:3425/6200 train_loss:3.5909 train_time:739125ms step_avg:216.43ms step:3426/6200 train_loss:3.4588 train_time:739339ms step_avg:216.43ms step:3427/6200 train_loss:3.4142 train_time:739553ms step_avg:216.43ms step:3428/6200 train_loss:3.3879 train_time:739767ms step_avg:216.43ms step:3429/6200 train_loss:3.3919 train_time:739982ms step_avg:216.43ms step:3430/6200 train_loss:3.4499 train_time:740196ms step_avg:216.43ms step:3431/6200 train_loss:3.4790 train_time:740409ms step_avg:216.43ms step:3432/6200 train_loss:3.5721 train_time:740623ms step_avg:216.43ms step:3433/6200 train_loss:3.3904 train_time:740836ms step_avg:216.43ms step:3434/6200 train_loss:3.6085 train_time:741049ms step_avg:216.43ms step:3435/6200 train_loss:3.5270 train_time:741264ms step_avg:216.43ms step:3436/6200 train_loss:3.3742 train_time:741478ms step_avg:216.43ms step:3437/6200 train_loss:3.4167 train_time:741692ms step_avg:216.43ms step:3438/6200 train_loss:3.4632 train_time:741905ms step_avg:216.43ms step:3439/6200 train_loss:3.5613 train_time:742119ms step_avg:216.42ms step:3440/6200 train_loss:3.3381 train_time:742331ms step_avg:216.42ms step:3441/6200 train_loss:3.5130 train_time:742545ms step_avg:216.42ms step:3442/6200 train_loss:3.4200 train_time:742759ms step_avg:216.42ms step:3443/6200 train_loss:3.5985 train_time:742972ms step_avg:216.42ms step:3444/6200 train_loss:3.4641 train_time:743185ms step_avg:216.42ms step:3445/6200 train_loss:3.3507 train_time:743401ms step_avg:216.42ms step:3446/6200 train_loss:3.5588 train_time:743614ms step_avg:216.42ms step:3447/6200 train_loss:3.6422 train_time:743827ms step_avg:216.42ms step:3448/6200 train_loss:3.4494 train_time:744040ms step_avg:216.42ms step:3449/6200 train_loss:3.4729 train_time:744253ms step_avg:216.42ms step:3450/6200 train_loss:3.5475 train_time:744466ms step_avg:216.41ms step:3451/6200 train_loss:3.5556 train_time:744680ms step_avg:216.41ms step:3452/6200 train_loss:3.5537 train_time:744894ms step_avg:216.41ms step:3453/6200 train_loss:3.3707 train_time:745109ms step_avg:216.41ms step:3454/6200 train_loss:3.4852 train_time:745323ms step_avg:216.41ms step:3455/6200 train_loss:3.3704 train_time:745535ms step_avg:216.41ms step:3456/6200 train_loss:3.6497 train_time:745749ms step_avg:216.41ms step:3457/6200 train_loss:3.3293 train_time:745963ms step_avg:216.41ms step:3458/6200 train_loss:3.4840 train_time:746177ms step_avg:216.41ms step:3459/6200 train_loss:3.4192 train_time:746391ms step_avg:216.41ms step:3460/6200 train_loss:3.4216 train_time:746606ms step_avg:216.41ms step:3461/6200 train_loss:3.4228 train_time:746819ms step_avg:216.41ms step:3462/6200 train_loss:3.4247 train_time:747031ms step_avg:216.41ms step:3463/6200 train_loss:3.5275 train_time:747245ms step_avg:216.40ms step:3464/6200 train_loss:3.4036 train_time:747459ms step_avg:216.40ms step:3465/6200 train_loss:3.4186 train_time:747672ms step_avg:216.40ms step:3466/6200 train_loss:3.3903 train_time:747886ms step_avg:216.40ms step:3467/6200 train_loss:3.5456 train_time:748101ms step_avg:216.40ms step:3468/6200 train_loss:3.4314 train_time:748314ms step_avg:216.40ms step:3469/6200 train_loss:3.4511 train_time:748526ms step_avg:216.40ms step:3470/6200 train_loss:3.6447 train_time:748740ms step_avg:216.40ms step:3471/6200 train_loss:3.5399 train_time:748954ms step_avg:216.40ms step:3472/6200 train_loss:3.5777 train_time:749168ms step_avg:216.40ms step:3473/6200 train_loss:4.2214 train_time:749382ms step_avg:216.40ms step:3474/6200 train_loss:3.4563 train_time:749596ms step_avg:216.40ms step:3475/6200 train_loss:3.4634 train_time:749808ms step_avg:216.39ms step:3476/6200 train_loss:3.4515 train_time:750022ms step_avg:216.39ms step:3477/6200 train_loss:3.3852 train_time:750234ms step_avg:216.39ms step:3478/6200 train_loss:3.4659 train_time:750447ms step_avg:216.39ms step:3479/6200 train_loss:3.4584 train_time:750662ms step_avg:216.39ms step:3480/6200 train_loss:3.3653 train_time:750875ms step_avg:216.39ms step:3481/6200 train_loss:3.6694 train_time:751089ms step_avg:216.39ms step:3482/6200 train_loss:3.5281 train_time:751304ms step_avg:216.39ms step:3483/6200 train_loss:3.4769 train_time:751518ms step_avg:216.39ms step:3484/6200 train_loss:3.5023 train_time:751730ms step_avg:216.39ms step:3485/6200 train_loss:3.4656 train_time:751943ms step_avg:216.39ms step:3486/6200 train_loss:3.6470 train_time:752156ms step_avg:216.39ms step:3487/6200 train_loss:3.6775 train_time:752368ms step_avg:216.38ms step:3488/6200 train_loss:3.5359 train_time:752582ms step_avg:216.38ms step:3489/6200 train_loss:3.3877 train_time:752797ms step_avg:216.38ms step:3490/6200 train_loss:3.5582 train_time:753010ms step_avg:216.38ms step:3491/6200 train_loss:3.4681 train_time:753223ms step_avg:216.38ms step:3492/6200 train_loss:3.5159 train_time:753435ms step_avg:216.38ms step:3493/6200 train_loss:3.3510 train_time:753649ms step_avg:216.38ms step:3494/6200 train_loss:3.4851 train_time:753863ms step_avg:216.38ms step:3495/6200 train_loss:3.4390 train_time:754076ms step_avg:216.38ms step:3496/6200 train_loss:3.4609 train_time:754290ms step_avg:216.38ms step:3497/6200 train_loss:3.6142 train_time:754505ms step_avg:216.38ms step:3498/6200 train_loss:3.4665 train_time:754718ms step_avg:216.38ms step:3499/6200 train_loss:3.4880 train_time:754930ms step_avg:216.37ms step:3500/6200 train_loss:3.4842 train_time:755144ms step_avg:216.37ms step:3500/6200 val_loss:3.4520 train_time:755146ms step_avg:216.37ms step:3501/6200 train_loss:3.5237 train_time:755362ms step_avg:216.37ms step:3502/6200 train_loss:3.5989 train_time:755576ms step_avg:216.37ms step:3503/6200 train_loss:3.2978 train_time:755789ms step_avg:216.37ms step:3504/6200 train_loss:3.4650 train_time:756004ms step_avg:216.37ms step:3505/6200 train_loss:3.4972 train_time:756218ms step_avg:216.37ms step:3506/6200 train_loss:3.5104 train_time:756432ms step_avg:216.37ms step:3507/6200 train_loss:3.3906 train_time:756643ms step_avg:216.37ms step:3508/6200 train_loss:3.5439 train_time:756857ms step_avg:216.37ms step:3509/6200 train_loss:3.4288 train_time:757070ms step_avg:216.37ms step:3510/6200 train_loss:3.6425 train_time:757284ms step_avg:216.37ms step:3511/6200 train_loss:3.4531 train_time:757498ms step_avg:216.37ms step:3512/6200 train_loss:3.3977 train_time:757712ms step_avg:216.37ms step:3513/6200 train_loss:3.4608 train_time:757924ms step_avg:216.36ms step:3514/6200 train_loss:3.4248 train_time:758138ms step_avg:216.36ms step:3515/6200 train_loss:3.4782 train_time:758350ms step_avg:216.36ms step:3516/6200 train_loss:3.4745 train_time:758563ms step_avg:216.36ms step:3517/6200 train_loss:3.4494 train_time:758777ms step_avg:216.36ms step:3518/6200 train_loss:3.4706 train_time:758990ms step_avg:216.36ms step:3519/6200 train_loss:3.4664 train_time:759204ms step_avg:216.36ms step:3520/6200 train_loss:3.4886 train_time:759419ms step_avg:216.36ms step:3521/6200 train_loss:3.5531 train_time:759632ms step_avg:216.36ms step:3522/6200 train_loss:3.4629 train_time:759844ms step_avg:216.36ms step:3523/6200 train_loss:3.3938 train_time:760057ms step_avg:216.36ms step:3524/6200 train_loss:3.4320 train_time:760270ms step_avg:216.35ms step:3525/6200 train_loss:3.4317 train_time:760484ms step_avg:216.35ms step:3526/6200 train_loss:3.4320 train_time:760698ms step_avg:216.35ms step:3527/6200 train_loss:3.5561 train_time:760911ms step_avg:216.35ms step:3528/6200 train_loss:3.3908 train_time:761125ms step_avg:216.35ms step:3529/6200 train_loss:3.2833 train_time:761338ms step_avg:216.35ms step:3530/6200 train_loss:3.5721 train_time:761551ms step_avg:216.35ms step:3531/6200 train_loss:3.3771 train_time:761764ms step_avg:216.35ms step:3532/6200 train_loss:3.4158 train_time:761978ms step_avg:216.35ms step:3533/6200 train_loss:3.3270 train_time:762192ms step_avg:216.35ms step:3534/6200 train_loss:3.3869 train_time:762405ms step_avg:216.35ms step:3535/6200 train_loss:3.3586 train_time:762622ms step_avg:216.35ms step:3536/6200 train_loss:3.5390 train_time:762835ms step_avg:216.35ms step:3537/6200 train_loss:3.4912 train_time:763048ms step_avg:216.34ms step:3538/6200 train_loss:3.5170 train_time:763261ms step_avg:216.34ms step:3539/6200 train_loss:3.4181 train_time:763475ms step_avg:216.34ms step:3540/6200 train_loss:3.3935 train_time:763689ms step_avg:216.34ms step:3541/6200 train_loss:3.5278 train_time:763902ms step_avg:216.34ms step:3542/6200 train_loss:3.3801 train_time:764115ms step_avg:216.34ms step:3543/6200 train_loss:3.5928 train_time:764331ms step_avg:216.34ms step:3544/6200 train_loss:3.7219 train_time:764544ms step_avg:216.34ms step:3545/6200 train_loss:3.5278 train_time:764757ms step_avg:216.34ms step:3546/6200 train_loss:3.5663 train_time:764970ms step_avg:216.34ms step:3547/6200 train_loss:3.3222 train_time:765184ms step_avg:216.34ms step:3548/6200 train_loss:3.4075 train_time:765398ms step_avg:216.34ms step:3549/6200 train_loss:3.4364 train_time:765612ms step_avg:216.34ms step:3550/6200 train_loss:3.5200 train_time:765826ms step_avg:216.34ms step:3551/6200 train_loss:3.4890 train_time:766040ms step_avg:216.33ms step:3552/6200 train_loss:3.4212 train_time:766252ms step_avg:216.33ms step:3553/6200 train_loss:3.5297 train_time:766465ms step_avg:216.33ms step:3554/6200 train_loss:3.4615 train_time:766682ms step_avg:216.33ms step:3555/6200 train_loss:3.4265 train_time:766896ms step_avg:216.33ms step:3556/6200 train_loss:3.3610 train_time:767110ms step_avg:216.33ms step:3557/6200 train_loss:3.3168 train_time:767324ms step_avg:216.33ms step:3558/6200 train_loss:3.4375 train_time:767538ms step_avg:216.33ms step:3559/6200 train_loss:3.4513 train_time:767750ms step_avg:216.33ms step:3560/6200 train_loss:3.6606 train_time:767963ms step_avg:216.33ms step:3561/6200 train_loss:3.5316 train_time:768177ms step_avg:216.33ms step:3562/6200 train_loss:3.4389 train_time:768390ms step_avg:216.33ms step:3563/6200 train_loss:3.3126 train_time:768605ms step_avg:216.33ms step:3564/6200 train_loss:3.8243 train_time:768820ms step_avg:216.33ms step:3565/6200 train_loss:3.3933 train_time:769032ms step_avg:216.32ms step:3566/6200 train_loss:3.3403 train_time:769244ms step_avg:216.32ms step:3567/6200 train_loss:3.3604 train_time:769458ms step_avg:216.32ms step:3568/6200 train_loss:3.4996 train_time:769672ms step_avg:216.32ms step:3569/6200 train_loss:3.4306 train_time:769885ms step_avg:216.32ms step:3570/6200 train_loss:3.5491 train_time:770101ms step_avg:216.32ms step:3571/6200 train_loss:3.4760 train_time:770315ms step_avg:216.32ms step:3572/6200 train_loss:3.7534 train_time:770528ms step_avg:216.32ms step:3573/6200 train_loss:3.3793 train_time:770740ms step_avg:216.32ms step:3574/6200 train_loss:3.4594 train_time:770955ms step_avg:216.32ms step:3575/6200 train_loss:3.6217 train_time:771169ms step_avg:216.32ms step:3576/6200 train_loss:3.4982 train_time:771382ms step_avg:216.32ms step:3577/6200 train_loss:3.4344 train_time:771596ms step_avg:216.32ms step:3578/6200 train_loss:3.4014 train_time:771809ms step_avg:216.31ms step:3579/6200 train_loss:3.4815 train_time:772023ms step_avg:216.31ms step:3580/6200 train_loss:3.4247 train_time:772236ms step_avg:216.31ms step:3581/6200 train_loss:3.3226 train_time:772449ms step_avg:216.31ms step:3582/6200 train_loss:3.3959 train_time:772663ms step_avg:216.31ms step:3583/6200 train_loss:3.3550 train_time:772876ms step_avg:216.31ms step:3584/6200 train_loss:3.4566 train_time:773089ms step_avg:216.31ms step:3585/6200 train_loss:3.5570 train_time:773304ms step_avg:216.31ms step:3586/6200 train_loss:3.4034 train_time:773518ms step_avg:216.31ms step:3587/6200 train_loss:3.4484 train_time:773731ms step_avg:216.31ms step:3588/6200 train_loss:3.4473 train_time:773944ms step_avg:216.31ms step:3589/6200 train_loss:3.4302 train_time:774156ms step_avg:216.31ms step:3590/6200 train_loss:3.4301 train_time:774370ms step_avg:216.30ms step:3591/6200 train_loss:3.5562 train_time:774841ms step_avg:216.38ms step:3592/6200 train_loss:3.4286 train_time:775054ms step_avg:216.37ms step:3593/6200 train_loss:3.5137 train_time:775267ms step_avg:216.37ms step:3594/6200 train_loss:3.5008 train_time:775481ms step_avg:216.37ms step:3595/6200 train_loss:3.4612 train_time:775695ms step_avg:216.37ms step:3596/6200 train_loss:3.3859 train_time:775908ms step_avg:216.37ms step:3597/6200 train_loss:3.3861 train_time:776123ms step_avg:216.37ms step:3598/6200 train_loss:3.6628 train_time:776336ms step_avg:216.37ms step:3599/6200 train_loss:3.4319 train_time:776550ms step_avg:216.37ms step:3600/6200 train_loss:3.4549 train_time:776763ms step_avg:216.37ms step:3601/6200 train_loss:3.3152 train_time:776977ms step_avg:216.37ms step:3602/6200 train_loss:3.4892 train_time:777190ms step_avg:216.37ms step:3603/6200 train_loss:3.4386 train_time:777404ms step_avg:216.37ms step:3604/6200 train_loss:3.5154 train_time:777619ms step_avg:216.37ms step:3605/6200 train_loss:3.6399 train_time:777831ms step_avg:216.36ms step:3606/6200 train_loss:3.4302 train_time:778044ms step_avg:216.36ms step:3607/6200 train_loss:3.4644 train_time:778256ms step_avg:216.36ms step:3608/6200 train_loss:3.7359 train_time:778469ms step_avg:216.36ms step:3609/6200 train_loss:3.4253 train_time:778683ms step_avg:216.36ms step:3610/6200 train_loss:3.5761 train_time:779147ms step_avg:216.43ms step:3611/6200 train_loss:3.3213 train_time:779361ms step_avg:216.43ms step:3612/6200 train_loss:3.4312 train_time:779573ms step_avg:216.43ms step:3613/6200 train_loss:3.5012 train_time:779786ms step_avg:216.43ms step:3614/6200 train_loss:3.6966 train_time:780001ms step_avg:216.43ms step:3615/6200 train_loss:3.7041 train_time:780213ms step_avg:216.43ms step:3616/6200 train_loss:3.3661 train_time:780426ms step_avg:216.42ms step:3617/6200 train_loss:3.4515 train_time:780639ms step_avg:216.42ms step:3618/6200 train_loss:3.4310 train_time:780855ms step_avg:216.42ms step:3619/6200 train_loss:3.5582 train_time:781068ms step_avg:216.42ms step:3620/6200 train_loss:3.4912 train_time:781282ms step_avg:216.42ms step:3621/6200 train_loss:3.3144 train_time:781495ms step_avg:216.42ms step:3622/6200 train_loss:3.4537 train_time:781709ms step_avg:216.42ms step:3623/6200 train_loss:3.4559 train_time:781923ms step_avg:216.42ms step:3624/6200 train_loss:3.3941 train_time:782136ms step_avg:216.42ms step:3625/6200 train_loss:3.5223 train_time:782348ms step_avg:216.42ms step:3625/6200 val_loss:3.4492 train_time:782350ms step_avg:216.42ms step:3626/6200 train_loss:3.5906 train_time:782565ms step_avg:216.42ms step:3627/6200 train_loss:3.5954 train_time:782779ms step_avg:216.42ms step:3628/6200 train_loss:3.4763 train_time:782992ms step_avg:216.42ms step:3629/6200 train_loss:3.6309 train_time:783206ms step_avg:216.41ms step:3630/6200 train_loss:3.4589 train_time:783420ms step_avg:216.41ms step:3631/6200 train_loss:3.4573 train_time:783634ms step_avg:216.41ms step:3632/6200 train_loss:3.5305 train_time:783848ms step_avg:216.41ms step:3633/6200 train_loss:3.5207 train_time:784060ms step_avg:216.41ms step:3634/6200 train_loss:3.4447 train_time:784273ms step_avg:216.41ms step:3635/6200 train_loss:3.4483 train_time:784486ms step_avg:216.41ms step:3636/6200 train_loss:3.4976 train_time:784699ms step_avg:216.41ms step:3637/6200 train_loss:3.6752 train_time:784913ms step_avg:216.41ms step:3638/6200 train_loss:3.4685 train_time:785127ms step_avg:216.41ms step:3639/6200 train_loss:3.4398 train_time:785341ms step_avg:216.41ms step:3640/6200 train_loss:3.4313 train_time:785555ms step_avg:216.41ms step:3641/6200 train_loss:3.7148 train_time:785767ms step_avg:216.41ms step:3642/6200 train_loss:3.4503 train_time:785980ms step_avg:216.40ms step:3643/6200 train_loss:3.4995 train_time:786194ms step_avg:216.40ms step:3644/6200 train_loss:3.4759 train_time:786407ms step_avg:216.40ms step:3645/6200 train_loss:3.3979 train_time:786621ms step_avg:216.40ms step:3646/6200 train_loss:3.5943 train_time:786835ms step_avg:216.40ms step:3647/6200 train_loss:3.3735 train_time:787049ms step_avg:216.40ms step:3648/6200 train_loss:3.4503 train_time:787261ms step_avg:216.40ms step:3649/6200 train_loss:3.5072 train_time:787475ms step_avg:216.40ms step:3650/6200 train_loss:3.4675 train_time:787689ms step_avg:216.40ms step:3651/6200 train_loss:3.5037 train_time:787902ms step_avg:216.40ms step:3652/6200 train_loss:3.5551 train_time:788116ms step_avg:216.40ms step:3653/6200 train_loss:3.3907 train_time:788330ms step_avg:216.40ms step:3654/6200 train_loss:3.4902 train_time:788542ms step_avg:216.39ms step:3655/6200 train_loss:3.5244 train_time:788757ms step_avg:216.39ms step:3656/6200 train_loss:4.1883 train_time:788971ms step_avg:216.39ms step:3657/6200 train_loss:3.5740 train_time:789184ms step_avg:216.39ms step:3658/6200 train_loss:3.4844 train_time:789398ms step_avg:216.39ms step:3659/6200 train_loss:3.4779 train_time:789612ms step_avg:216.39ms step:3660/6200 train_loss:3.3531 train_time:789825ms step_avg:216.39ms step:3661/6200 train_loss:3.4828 train_time:790041ms step_avg:216.39ms step:3662/6200 train_loss:3.3572 train_time:790255ms step_avg:216.39ms step:3663/6200 train_loss:3.5095 train_time:790467ms step_avg:216.39ms step:3664/6200 train_loss:3.5199 train_time:790681ms step_avg:216.39ms step:3665/6200 train_loss:3.3546 train_time:790894ms step_avg:216.39ms step:3666/6200 train_loss:3.2914 train_time:791107ms step_avg:216.39ms step:3667/6200 train_loss:3.7173 train_time:791321ms step_avg:216.39ms step:3668/6200 train_loss:3.5029 train_time:791535ms step_avg:216.38ms step:3669/6200 train_loss:3.5302 train_time:791748ms step_avg:216.38ms step:3670/6200 train_loss:3.4488 train_time:791961ms step_avg:216.38ms step:3671/6200 train_loss:3.5166 train_time:792174ms step_avg:216.38ms step:3672/6200 train_loss:3.4143 train_time:792387ms step_avg:216.38ms step:3673/6200 train_loss:3.4212 train_time:792600ms step_avg:216.38ms step:3674/6200 train_loss:3.3159 train_time:792816ms step_avg:216.38ms step:3675/6200 train_loss:3.3952 train_time:793029ms step_avg:216.38ms step:3676/6200 train_loss:3.5461 train_time:793242ms step_avg:216.38ms step:3677/6200 train_loss:3.3589 train_time:793456ms step_avg:216.38ms step:3678/6200 train_loss:3.5136 train_time:793668ms step_avg:216.38ms step:3679/6200 train_loss:3.5018 train_time:793882ms step_avg:216.38ms step:3680/6200 train_loss:3.4004 train_time:794096ms step_avg:216.37ms step:3681/6200 train_loss:3.4639 train_time:794310ms step_avg:216.37ms step:3682/6200 train_loss:3.5326 train_time:794523ms step_avg:216.37ms step:3683/6200 train_loss:3.6346 train_time:794738ms step_avg:216.37ms step:3684/6200 train_loss:3.3791 train_time:794954ms step_avg:216.37ms step:3685/6200 train_loss:3.4555 train_time:795167ms step_avg:216.37ms step:3686/6200 train_loss:3.6032 train_time:795380ms step_avg:216.37ms step:3687/6200 train_loss:3.3791 train_time:795594ms step_avg:216.37ms step:3688/6200 train_loss:3.5905 train_time:795808ms step_avg:216.37ms step:3689/6200 train_loss:3.3190 train_time:796020ms step_avg:216.37ms step:3690/6200 train_loss:3.4068 train_time:796235ms step_avg:216.37ms step:3691/6200 train_loss:3.5431 train_time:796448ms step_avg:216.37ms step:3692/6200 train_loss:3.3351 train_time:796659ms step_avg:216.37ms step:3693/6200 train_loss:3.4802 train_time:796873ms step_avg:216.37ms step:3694/6200 train_loss:3.4703 train_time:797086ms step_avg:216.36ms step:3695/6200 train_loss:3.4575 train_time:797300ms step_avg:216.36ms step:3696/6200 train_loss:3.4926 train_time:797514ms step_avg:216.36ms step:3697/6200 train_loss:3.3412 train_time:797728ms step_avg:216.36ms step:3698/6200 train_loss:3.4762 train_time:797941ms step_avg:216.36ms step:3699/6200 train_loss:3.4867 train_time:798154ms step_avg:216.36ms step:3700/6200 train_loss:3.4571 train_time:798367ms step_avg:216.36ms step:3701/6200 train_loss:3.5264 train_time:798581ms step_avg:216.36ms step:3702/6200 train_loss:3.4859 train_time:798795ms step_avg:216.36ms step:3703/6200 train_loss:3.4081 train_time:799009ms step_avg:216.36ms step:3704/6200 train_loss:3.3827 train_time:799223ms step_avg:216.36ms step:3705/6200 train_loss:3.5241 train_time:799438ms step_avg:216.36ms step:3706/6200 train_loss:3.5274 train_time:799651ms step_avg:216.36ms step:3707/6200 train_loss:3.5318 train_time:799864ms step_avg:216.35ms step:3708/6200 train_loss:3.4859 train_time:800077ms step_avg:216.35ms step:3709/6200 train_loss:3.3545 train_time:800290ms step_avg:216.35ms step:3710/6200 train_loss:3.6584 train_time:800502ms step_avg:216.35ms step:3711/6200 train_loss:3.2435 train_time:800717ms step_avg:216.35ms step:3712/6200 train_loss:3.5171 train_time:800930ms step_avg:216.35ms step:3713/6200 train_loss:3.4010 train_time:801144ms step_avg:216.35ms step:3714/6200 train_loss:3.4410 train_time:801357ms step_avg:216.35ms step:3715/6200 train_loss:3.8166 train_time:801570ms step_avg:216.35ms step:3716/6200 train_loss:3.6591 train_time:801783ms step_avg:216.35ms step:3717/6200 train_loss:3.9237 train_time:801998ms step_avg:216.35ms step:3718/6200 train_loss:3.4352 train_time:802211ms step_avg:216.35ms step:3719/6200 train_loss:3.3446 train_time:802424ms step_avg:216.35ms step:3720/6200 train_loss:3.6125 train_time:802639ms step_avg:216.34ms step:3721/6200 train_loss:3.3699 train_time:802853ms step_avg:216.34ms step:3722/6200 train_loss:3.4675 train_time:803065ms step_avg:216.34ms step:3723/6200 train_loss:3.3367 train_time:803279ms step_avg:216.34ms step:3724/6200 train_loss:3.3193 train_time:803493ms step_avg:216.34ms step:3725/6200 train_loss:3.4459 train_time:803706ms step_avg:216.34ms step:3726/6200 train_loss:3.4031 train_time:803920ms step_avg:216.34ms step:3727/6200 train_loss:3.6688 train_time:804134ms step_avg:216.34ms step:3728/6200 train_loss:3.3999 train_time:804349ms step_avg:216.34ms step:3729/6200 train_loss:3.3923 train_time:804560ms step_avg:216.34ms step:3730/6200 train_loss:3.7500 train_time:804774ms step_avg:216.34ms step:3731/6200 train_loss:3.5034 train_time:804987ms step_avg:216.34ms step:3732/6200 train_loss:3.4131 train_time:805200ms step_avg:216.34ms step:3733/6200 train_loss:3.2928 train_time:805416ms step_avg:216.34ms step:3734/6200 train_loss:3.5228 train_time:805629ms step_avg:216.33ms step:3735/6200 train_loss:3.3801 train_time:805842ms step_avg:216.33ms step:3736/6200 train_loss:3.4796 train_time:806055ms step_avg:216.33ms step:3737/6200 train_loss:3.3878 train_time:806267ms step_avg:216.33ms step:3738/6200 train_loss:3.4831 train_time:806479ms step_avg:216.33ms step:3739/6200 train_loss:3.3866 train_time:806693ms step_avg:216.33ms step:3740/6200 train_loss:3.4351 train_time:806906ms step_avg:216.33ms step:3741/6200 train_loss:3.7217 train_time:807119ms step_avg:216.33ms step:3742/6200 train_loss:3.3874 train_time:807333ms step_avg:216.33ms step:3743/6200 train_loss:3.4473 train_time:807547ms step_avg:216.33ms step:3744/6200 train_loss:3.6570 train_time:807759ms step_avg:216.33ms step:3745/6200 train_loss:3.3852 train_time:807972ms step_avg:216.32ms step:3746/6200 train_loss:3.3151 train_time:808185ms step_avg:216.32ms step:3747/6200 train_loss:3.4914 train_time:808399ms step_avg:216.32ms step:3748/6200 train_loss:3.3495 train_time:808612ms step_avg:216.32ms step:3749/6200 train_loss:3.3889 train_time:808826ms step_avg:216.32ms step:3750/6200 train_loss:3.5750 train_time:809040ms step_avg:216.32ms step:3750/6200 val_loss:3.4425 train_time:809042ms step_avg:216.32ms step:3751/6200 train_loss:3.4688 train_time:809261ms step_avg:216.32ms step:3752/6200 train_loss:3.7034 train_time:809474ms step_avg:216.32ms step:3753/6200 train_loss:3.4174 train_time:809687ms step_avg:216.32ms step:3754/6200 train_loss:3.4211 train_time:809901ms step_avg:216.32ms step:3755/6200 train_loss:3.3890 train_time:810114ms step_avg:216.32ms step:3756/6200 train_loss:3.4896 train_time:810328ms step_avg:216.32ms step:3757/6200 train_loss:3.4396 train_time:810542ms step_avg:216.32ms step:3758/6200 train_loss:3.4420 train_time:810757ms step_avg:216.32ms step:3759/6200 train_loss:3.6262 train_time:810969ms step_avg:216.32ms step:3760/6200 train_loss:3.5150 train_time:811182ms step_avg:216.32ms step:3761/6200 train_loss:3.6228 train_time:811394ms step_avg:216.31ms step:3762/6200 train_loss:3.3930 train_time:811608ms step_avg:216.31ms step:3763/6200 train_loss:3.4094 train_time:811822ms step_avg:216.31ms step:3764/6200 train_loss:3.5712 train_time:812036ms step_avg:216.31ms step:3765/6200 train_loss:3.3342 train_time:812250ms step_avg:216.31ms step:3766/6200 train_loss:3.4167 train_time:812463ms step_avg:216.31ms step:3767/6200 train_loss:3.5190 train_time:812676ms step_avg:216.31ms step:3768/6200 train_loss:3.3209 train_time:812889ms step_avg:216.31ms step:3769/6200 train_loss:3.5829 train_time:813102ms step_avg:216.31ms step:3770/6200 train_loss:3.4056 train_time:813317ms step_avg:216.31ms step:3771/6200 train_loss:3.2831 train_time:813530ms step_avg:216.31ms step:3772/6200 train_loss:3.5293 train_time:813744ms step_avg:216.31ms step:3773/6200 train_loss:3.4547 train_time:813960ms step_avg:216.31ms step:3774/6200 train_loss:3.4465 train_time:814172ms step_avg:216.31ms step:3775/6200 train_loss:3.4374 train_time:814384ms step_avg:216.30ms step:3776/6200 train_loss:3.4893 train_time:814598ms step_avg:216.30ms step:3777/6200 train_loss:3.3261 train_time:814811ms step_avg:216.30ms step:3778/6200 train_loss:3.4368 train_time:815024ms step_avg:216.30ms step:3779/6200 train_loss:3.5594 train_time:815239ms step_avg:216.30ms step:3780/6200 train_loss:3.5234 train_time:815708ms step_avg:216.37ms step:3781/6200 train_loss:3.5222 train_time:815922ms step_avg:216.37ms step:3782/6200 train_loss:3.4761 train_time:816135ms step_avg:216.37ms step:3783/6200 train_loss:3.4851 train_time:816349ms step_avg:216.37ms step:3784/6200 train_loss:3.4474 train_time:816564ms step_avg:216.37ms step:3785/6200 train_loss:3.3397 train_time:816777ms step_avg:216.36ms step:3786/6200 train_loss:3.4053 train_time:816989ms step_avg:216.36ms step:3787/6200 train_loss:3.4585 train_time:817202ms step_avg:216.36ms step:3788/6200 train_loss:3.4433 train_time:817414ms step_avg:216.36ms step:3789/6200 train_loss:3.3862 train_time:817627ms step_avg:216.36ms step:3790/6200 train_loss:3.4223 train_time:817842ms step_avg:216.36ms step:3791/6200 train_loss:3.2867 train_time:818057ms step_avg:216.36ms step:3792/6200 train_loss:3.5102 train_time:818269ms step_avg:216.36ms step:3793/6200 train_loss:3.4949 train_time:818481ms step_avg:216.36ms step:3794/6200 train_loss:3.4185 train_time:818695ms step_avg:216.36ms step:3795/6200 train_loss:3.3852 train_time:818908ms step_avg:216.36ms step:3796/6200 train_loss:3.2294 train_time:819122ms step_avg:216.36ms step:3797/6200 train_loss:3.4183 train_time:819336ms step_avg:216.35ms step:3798/6200 train_loss:3.4239 train_time:819549ms step_avg:216.35ms step:3799/6200 train_loss:3.4846 train_time:819762ms step_avg:216.35ms step:3800/6200 train_loss:3.3948 train_time:820227ms step_avg:216.42ms step:3801/6200 train_loss:3.3802 train_time:820439ms step_avg:216.42ms step:3802/6200 train_loss:3.3306 train_time:820653ms step_avg:216.42ms step:3803/6200 train_loss:3.6373 train_time:820865ms step_avg:216.42ms step:3804/6200 train_loss:3.4875 train_time:821080ms step_avg:216.42ms step:3805/6200 train_loss:3.3458 train_time:821292ms step_avg:216.41ms step:3806/6200 train_loss:3.5764 train_time:821505ms step_avg:216.41ms step:3807/6200 train_loss:3.5452 train_time:821721ms step_avg:216.41ms step:3808/6200 train_loss:3.4175 train_time:821935ms step_avg:216.41ms step:3809/6200 train_loss:3.4775 train_time:822147ms step_avg:216.41ms step:3810/6200 train_loss:3.3884 train_time:822362ms step_avg:216.41ms step:3811/6200 train_loss:3.4618 train_time:822575ms step_avg:216.41ms step:3812/6200 train_loss:3.4409 train_time:822787ms step_avg:216.41ms step:3813/6200 train_loss:3.4676 train_time:823001ms step_avg:216.41ms step:3814/6200 train_loss:3.4656 train_time:823215ms step_avg:216.41ms step:3815/6200 train_loss:3.4497 train_time:823428ms step_avg:216.41ms step:3816/6200 train_loss:3.6912 train_time:823642ms step_avg:216.41ms step:3817/6200 train_loss:3.2963 train_time:823856ms step_avg:216.41ms step:3818/6200 train_loss:3.4730 train_time:824069ms step_avg:216.40ms step:3819/6200 train_loss:3.4468 train_time:824283ms step_avg:216.40ms step:3820/6200 train_loss:3.4252 train_time:824497ms step_avg:216.40ms step:3821/6200 train_loss:3.3651 train_time:824711ms step_avg:216.40ms step:3822/6200 train_loss:3.5364 train_time:824923ms step_avg:216.40ms step:3823/6200 train_loss:3.2703 train_time:825140ms step_avg:216.40ms step:3824/6200 train_loss:3.3845 train_time:825353ms step_avg:216.40ms step:3825/6200 train_loss:3.4323 train_time:825565ms step_avg:216.40ms step:3826/6200 train_loss:3.5798 train_time:825779ms step_avg:216.40ms step:3827/6200 train_loss:3.5141 train_time:825992ms step_avg:216.40ms step:3828/6200 train_loss:3.8872 train_time:826204ms step_avg:216.40ms step:3829/6200 train_loss:3.5109 train_time:826419ms step_avg:216.40ms step:3830/6200 train_loss:3.3413 train_time:826632ms step_avg:216.40ms step:3831/6200 train_loss:3.3877 train_time:826846ms step_avg:216.40ms step:3832/6200 train_loss:3.5836 train_time:827061ms step_avg:216.39ms step:3833/6200 train_loss:3.4018 train_time:827275ms step_avg:216.39ms step:3834/6200 train_loss:3.5294 train_time:827488ms step_avg:216.39ms step:3835/6200 train_loss:3.4649 train_time:827701ms step_avg:216.39ms step:3836/6200 train_loss:3.2669 train_time:827914ms step_avg:216.39ms step:3837/6200 train_loss:3.5530 train_time:828128ms step_avg:216.39ms step:3838/6200 train_loss:3.5259 train_time:828343ms step_avg:216.39ms step:3839/6200 train_loss:3.4845 train_time:828557ms step_avg:216.39ms step:3840/6200 train_loss:3.5493 train_time:828770ms step_avg:216.39ms step:3841/6200 train_loss:3.6653 train_time:828982ms step_avg:216.39ms step:3842/6200 train_loss:3.4229 train_time:829196ms step_avg:216.39ms step:3843/6200 train_loss:3.4635 train_time:829408ms step_avg:216.39ms step:3844/6200 train_loss:3.6068 train_time:829622ms step_avg:216.39ms step:3845/6200 train_loss:3.4053 train_time:829836ms step_avg:216.38ms step:3846/6200 train_loss:3.2725 train_time:830049ms step_avg:216.38ms step:3847/6200 train_loss:3.5185 train_time:830264ms step_avg:216.38ms step:3848/6200 train_loss:3.4340 train_time:830477ms step_avg:216.38ms step:3849/6200 train_loss:3.4766 train_time:830690ms step_avg:216.38ms step:3850/6200 train_loss:3.3684 train_time:830903ms step_avg:216.38ms step:3851/6200 train_loss:3.3639 train_time:831116ms step_avg:216.38ms step:3852/6200 train_loss:3.5206 train_time:831330ms step_avg:216.38ms step:3853/6200 train_loss:3.3658 train_time:831543ms step_avg:216.38ms step:3854/6200 train_loss:3.3434 train_time:831757ms step_avg:216.38ms step:3855/6200 train_loss:3.4239 train_time:831971ms step_avg:216.38ms step:3856/6200 train_loss:3.4591 train_time:832183ms step_avg:216.38ms step:3857/6200 train_loss:3.4298 train_time:832396ms step_avg:216.38ms step:3858/6200 train_loss:3.4583 train_time:832609ms step_avg:216.37ms step:3859/6200 train_loss:3.4395 train_time:832823ms step_avg:216.37ms step:3860/6200 train_loss:3.4390 train_time:833037ms step_avg:216.37ms step:3861/6200 train_loss:3.6085 train_time:833250ms step_avg:216.37ms step:3862/6200 train_loss:3.4178 train_time:833463ms step_avg:216.37ms step:3863/6200 train_loss:3.5401 train_time:833677ms step_avg:216.37ms step:3864/6200 train_loss:3.4833 train_time:833889ms step_avg:216.37ms step:3865/6200 train_loss:3.5410 train_time:834102ms step_avg:216.37ms step:3866/6200 train_loss:3.5032 train_time:834315ms step_avg:216.37ms step:3867/6200 train_loss:3.4419 train_time:834529ms step_avg:216.37ms step:3868/6200 train_loss:3.5382 train_time:834743ms step_avg:216.37ms step:3869/6200 train_loss:3.6822 train_time:834957ms step_avg:216.37ms step:3870/6200 train_loss:3.5333 train_time:835170ms step_avg:216.37ms step:3871/6200 train_loss:3.4303 train_time:835382ms step_avg:216.36ms step:3872/6200 train_loss:3.5770 train_time:835595ms step_avg:216.36ms step:3873/6200 train_loss:3.4739 train_time:835808ms step_avg:216.36ms step:3874/6200 train_loss:3.4246 train_time:836022ms step_avg:216.36ms step:3875/6200 train_loss:3.5183 train_time:836236ms step_avg:216.36ms step:3875/6200 val_loss:3.4375 train_time:836238ms step_avg:216.36ms step:3876/6200 train_loss:4.0512 train_time:836454ms step_avg:216.36ms step:3877/6200 train_loss:3.4579 train_time:836668ms step_avg:216.36ms step:3878/6200 train_loss:3.4580 train_time:836880ms step_avg:216.36ms step:3879/6200 train_loss:3.4345 train_time:837094ms step_avg:216.36ms step:3880/6200 train_loss:3.6438 train_time:837307ms step_avg:216.36ms step:3881/6200 train_loss:3.4464 train_time:837520ms step_avg:216.36ms step:3882/6200 train_loss:3.5158 train_time:837734ms step_avg:216.36ms step:3883/6200 train_loss:3.5599 train_time:837948ms step_avg:216.36ms step:3884/6200 train_loss:3.3743 train_time:838162ms step_avg:216.36ms step:3885/6200 train_loss:3.3681 train_time:838377ms step_avg:216.36ms step:3886/6200 train_loss:3.4080 train_time:838590ms step_avg:216.35ms step:3887/6200 train_loss:3.4441 train_time:838803ms step_avg:216.35ms step:3888/6200 train_loss:3.6254 train_time:839017ms step_avg:216.35ms step:3889/6200 train_loss:3.4754 train_time:839230ms step_avg:216.35ms step:3890/6200 train_loss:3.4071 train_time:839444ms step_avg:216.35ms step:3891/6200 train_loss:3.5480 train_time:839659ms step_avg:216.35ms step:3892/6200 train_loss:3.4128 train_time:839873ms step_avg:216.35ms step:3893/6200 train_loss:3.6554 train_time:840086ms step_avg:216.35ms step:3894/6200 train_loss:3.3908 train_time:840298ms step_avg:216.35ms step:3895/6200 train_loss:3.4100 train_time:840512ms step_avg:216.35ms step:3896/6200 train_loss:3.4884 train_time:840726ms step_avg:216.35ms step:3897/6200 train_loss:3.7306 train_time:840940ms step_avg:216.35ms step:3898/6200 train_loss:3.2839 train_time:841154ms step_avg:216.35ms step:3899/6200 train_loss:3.4133 train_time:841368ms step_avg:216.35ms step:3900/6200 train_loss:3.5508 train_time:841581ms step_avg:216.34ms step:3901/6200 train_loss:3.4802 train_time:841795ms step_avg:216.34ms step:3902/6200 train_loss:3.5072 train_time:842008ms step_avg:216.34ms step:3903/6200 train_loss:3.8030 train_time:842220ms step_avg:216.34ms step:3904/6200 train_loss:3.3939 train_time:842435ms step_avg:216.34ms step:3905/6200 train_loss:3.4181 train_time:842648ms step_avg:216.34ms step:3906/6200 train_loss:3.3617 train_time:842861ms step_avg:216.34ms step:3907/6200 train_loss:3.5228 train_time:843076ms step_avg:216.34ms step:3908/6200 train_loss:3.5466 train_time:843290ms step_avg:216.34ms step:3909/6200 train_loss:3.5305 train_time:843502ms step_avg:216.34ms step:3910/6200 train_loss:3.4802 train_time:843716ms step_avg:216.34ms step:3911/6200 train_loss:3.4134 train_time:843929ms step_avg:216.34ms step:3912/6200 train_loss:3.4414 train_time:844141ms step_avg:216.34ms step:3913/6200 train_loss:3.4316 train_time:844356ms step_avg:216.34ms step:3914/6200 train_loss:3.5526 train_time:844570ms step_avg:216.33ms step:3915/6200 train_loss:3.3859 train_time:844783ms step_avg:216.33ms step:3916/6200 train_loss:3.3652 train_time:844996ms step_avg:216.33ms step:3917/6200 train_loss:3.3581 train_time:845209ms step_avg:216.33ms step:3918/6200 train_loss:3.4836 train_time:845422ms step_avg:216.33ms step:3919/6200 train_loss:3.5961 train_time:845637ms step_avg:216.33ms step:3920/6200 train_loss:3.3814 train_time:845851ms step_avg:216.33ms step:3921/6200 train_loss:3.3542 train_time:846066ms step_avg:216.33ms step:3922/6200 train_loss:3.4317 train_time:846279ms step_avg:216.33ms step:3923/6200 train_loss:3.4280 train_time:846493ms step_avg:216.33ms step:3924/6200 train_loss:3.4467 train_time:846705ms step_avg:216.33ms step:3925/6200 train_loss:3.5220 train_time:846919ms step_avg:216.33ms step:3926/6200 train_loss:3.4853 train_time:847133ms step_avg:216.33ms step:3927/6200 train_loss:3.5827 train_time:847347ms step_avg:216.33ms step:3928/6200 train_loss:3.4677 train_time:847561ms step_avg:216.32ms step:3929/6200 train_loss:3.3191 train_time:847776ms step_avg:216.32ms step:3930/6200 train_loss:3.6428 train_time:847989ms step_avg:216.32ms step:3931/6200 train_loss:3.4302 train_time:848202ms step_avg:216.32ms step:3932/6200 train_loss:3.4775 train_time:848416ms step_avg:216.32ms step:3933/6200 train_loss:3.5139 train_time:848629ms step_avg:216.32ms step:3934/6200 train_loss:3.3996 train_time:848843ms step_avg:216.32ms step:3935/6200 train_loss:3.5204 train_time:849057ms step_avg:216.32ms step:3936/6200 train_loss:3.5287 train_time:849272ms step_avg:216.32ms step:3937/6200 train_loss:3.4580 train_time:849486ms step_avg:216.32ms step:3938/6200 train_loss:3.5132 train_time:849697ms step_avg:216.32ms step:3939/6200 train_loss:3.4369 train_time:849910ms step_avg:216.32ms step:3940/6200 train_loss:3.1978 train_time:850124ms step_avg:216.32ms step:3941/6200 train_loss:3.4159 train_time:850339ms step_avg:216.32ms step:3942/6200 train_loss:3.5227 train_time:850553ms step_avg:216.32ms step:3943/6200 train_loss:3.6123 train_time:850767ms step_avg:216.31ms step:3944/6200 train_loss:3.6528 train_time:850980ms step_avg:216.31ms step:3945/6200 train_loss:3.4858 train_time:851194ms step_avg:216.31ms step:3946/6200 train_loss:3.4023 train_time:851406ms step_avg:216.31ms step:3947/6200 train_loss:3.4176 train_time:851620ms step_avg:216.31ms step:3948/6200 train_loss:3.4932 train_time:851833ms step_avg:216.31ms step:3949/6200 train_loss:3.3039 train_time:852047ms step_avg:216.31ms step:3950/6200 train_loss:3.5004 train_time:852260ms step_avg:216.31ms step:3951/6200 train_loss:3.4299 train_time:852475ms step_avg:216.31ms step:3952/6200 train_loss:3.2503 train_time:852688ms step_avg:216.31ms step:3953/6200 train_loss:3.3144 train_time:852901ms step_avg:216.31ms step:3954/6200 train_loss:3.5785 train_time:853115ms step_avg:216.31ms step:3955/6200 train_loss:3.4913 train_time:853328ms step_avg:216.31ms step:3956/6200 train_loss:3.4299 train_time:853542ms step_avg:216.31ms step:3957/6200 train_loss:3.4948 train_time:853757ms step_avg:216.31ms step:3958/6200 train_loss:3.2149 train_time:853972ms step_avg:216.30ms step:3959/6200 train_loss:3.5045 train_time:854185ms step_avg:216.30ms step:3960/6200 train_loss:3.4480 train_time:854397ms step_avg:216.30ms step:3961/6200 train_loss:3.4155 train_time:854610ms step_avg:216.30ms step:3962/6200 train_loss:3.4339 train_time:854824ms step_avg:216.30ms step:3963/6200 train_loss:3.4523 train_time:855038ms step_avg:216.30ms step:3964/6200 train_loss:3.4830 train_time:855252ms step_avg:216.30ms step:3965/6200 train_loss:3.3338 train_time:855467ms step_avg:216.30ms step:3966/6200 train_loss:3.4562 train_time:855680ms step_avg:216.30ms step:3967/6200 train_loss:3.5244 train_time:855894ms step_avg:216.30ms step:3968/6200 train_loss:3.4455 train_time:856107ms step_avg:216.30ms step:3969/6200 train_loss:3.5256 train_time:856575ms step_avg:216.36ms step:3970/6200 train_loss:3.4157 train_time:856789ms step_avg:216.36ms step:3971/6200 train_loss:3.6047 train_time:857001ms step_avg:216.36ms step:3972/6200 train_loss:3.5302 train_time:857215ms step_avg:216.36ms step:3973/6200 train_loss:3.4870 train_time:857428ms step_avg:216.36ms step:3974/6200 train_loss:3.3759 train_time:857642ms step_avg:216.36ms step:3975/6200 train_loss:3.4292 train_time:857857ms step_avg:216.36ms step:3976/6200 train_loss:3.4944 train_time:858070ms step_avg:216.36ms step:3977/6200 train_loss:3.4100 train_time:858284ms step_avg:216.36ms step:3978/6200 train_loss:3.4589 train_time:858496ms step_avg:216.35ms step:3979/6200 train_loss:3.5487 train_time:858709ms step_avg:216.35ms step:3980/6200 train_loss:3.4809 train_time:858922ms step_avg:216.35ms step:3981/6200 train_loss:3.4921 train_time:859137ms step_avg:216.35ms step:3982/6200 train_loss:3.6906 train_time:859351ms step_avg:216.35ms step:3983/6200 train_loss:3.4266 train_time:859564ms step_avg:216.35ms step:3984/6200 train_loss:3.4890 train_time:859779ms step_avg:216.35ms step:3985/6200 train_loss:3.4265 train_time:859992ms step_avg:216.35ms step:3986/6200 train_loss:3.3528 train_time:860204ms step_avg:216.35ms step:3987/6200 train_loss:3.3936 train_time:860418ms step_avg:216.35ms step:3988/6200 train_loss:3.4204 train_time:860631ms step_avg:216.35ms step:3989/6200 train_loss:3.1438 train_time:860845ms step_avg:216.35ms step:3990/6200 train_loss:3.4683 train_time:861308ms step_avg:216.41ms step:3991/6200 train_loss:3.4382 train_time:861521ms step_avg:216.41ms step:3992/6200 train_loss:3.2924 train_time:861737ms step_avg:216.41ms step:3993/6200 train_loss:3.3988 train_time:861952ms step_avg:216.41ms step:3994/6200 train_loss:3.5893 train_time:862164ms step_avg:216.41ms step:3995/6200 train_loss:3.4112 train_time:862380ms step_avg:216.41ms step:3996/6200 train_loss:3.3279 train_time:862595ms step_avg:216.41ms step:3997/6200 train_loss:3.4855 train_time:862807ms step_avg:216.41ms step:3998/6200 train_loss:3.3955 train_time:863020ms step_avg:216.40ms step:3999/6200 train_loss:3.3532 train_time:863235ms step_avg:216.40ms step:4000/6200 train_loss:3.4242 train_time:863448ms step_avg:216.40ms step:4000/6200 val_loss:3.4313 train_time:863450ms step_avg:216.40ms step:4001/6200 train_loss:3.5452 train_time:863666ms step_avg:216.40ms step:4002/6200 train_loss:3.6205 train_time:863881ms step_avg:216.40ms step:4003/6200 train_loss:3.2936 train_time:864094ms step_avg:216.40ms step:4004/6200 train_loss:3.4890 train_time:864307ms step_avg:216.40ms step:4005/6200 train_loss:3.3863 train_time:864520ms step_avg:216.40ms step:4006/6200 train_loss:3.4438 train_time:864735ms step_avg:216.40ms step:4007/6200 train_loss:3.4255 train_time:864948ms step_avg:216.40ms step:4008/6200 train_loss:3.6191 train_time:865162ms step_avg:216.40ms step:4009/6200 train_loss:3.2104 train_time:865375ms step_avg:216.40ms step:4010/6200 train_loss:3.4144 train_time:865590ms step_avg:216.40ms step:4011/6200 train_loss:3.4030 train_time:865802ms step_avg:216.40ms step:4012/6200 train_loss:3.3624 train_time:866015ms step_avg:216.40ms step:4013/6200 train_loss:3.5346 train_time:866230ms step_avg:216.40ms step:4014/6200 train_loss:3.3968 train_time:866443ms step_avg:216.39ms step:4015/6200 train_loss:3.4968 train_time:866657ms step_avg:216.39ms step:4016/6200 train_loss:3.5873 train_time:866872ms step_avg:216.39ms step:4017/6200 train_loss:3.5722 train_time:867086ms step_avg:216.39ms step:4018/6200 train_loss:3.3257 train_time:867299ms step_avg:216.39ms step:4019/6200 train_loss:3.4613 train_time:867511ms step_avg:216.39ms step:4020/6200 train_loss:3.3782 train_time:867726ms step_avg:216.39ms step:4021/6200 train_loss:3.6526 train_time:867940ms step_avg:216.39ms step:4022/6200 train_loss:3.5293 train_time:868154ms step_avg:216.39ms step:4023/6200 train_loss:3.5163 train_time:868368ms step_avg:216.39ms step:4024/6200 train_loss:3.4833 train_time:868580ms step_avg:216.39ms step:4025/6200 train_loss:3.5160 train_time:868796ms step_avg:216.39ms step:4026/6200 train_loss:3.2681 train_time:869011ms step_avg:216.39ms step:4027/6200 train_loss:3.4890 train_time:869224ms step_avg:216.39ms step:4028/6200 train_loss:3.4340 train_time:869438ms step_avg:216.39ms step:4029/6200 train_loss:3.3281 train_time:869652ms step_avg:216.39ms step:4030/6200 train_loss:3.3512 train_time:869867ms step_avg:216.38ms step:4031/6200 train_loss:3.4032 train_time:870080ms step_avg:216.38ms step:4032/6200 train_loss:3.4889 train_time:870295ms step_avg:216.38ms step:4033/6200 train_loss:3.4581 train_time:870509ms step_avg:216.38ms step:4034/6200 train_loss:3.4426 train_time:870721ms step_avg:216.38ms step:4035/6200 train_loss:3.4295 train_time:870934ms step_avg:216.38ms step:4036/6200 train_loss:3.3727 train_time:871147ms step_avg:216.38ms step:4037/6200 train_loss:3.5474 train_time:871361ms step_avg:216.38ms step:4038/6200 train_loss:3.4672 train_time:871580ms step_avg:216.38ms step:4039/6200 train_loss:3.4566 train_time:871794ms step_avg:216.38ms step:4040/6200 train_loss:3.4498 train_time:872011ms step_avg:216.38ms step:4041/6200 train_loss:3.4885 train_time:872223ms step_avg:216.38ms step:4042/6200 train_loss:3.6832 train_time:872437ms step_avg:216.38ms step:4043/6200 train_loss:3.5825 train_time:872652ms step_avg:216.38ms step:4044/6200 train_loss:3.3614 train_time:872866ms step_avg:216.38ms step:4045/6200 train_loss:3.5335 train_time:873079ms step_avg:216.38ms step:4046/6200 train_loss:3.2396 train_time:873294ms step_avg:216.38ms step:4047/6200 train_loss:3.4996 train_time:873507ms step_avg:216.38ms step:4048/6200 train_loss:3.5843 train_time:873720ms step_avg:216.37ms step:4049/6200 train_loss:3.4614 train_time:873934ms step_avg:216.37ms step:4050/6200 train_loss:3.3913 train_time:874148ms step_avg:216.37ms step:4051/6200 train_loss:3.4333 train_time:874362ms step_avg:216.37ms step:4052/6200 train_loss:3.3654 train_time:874576ms step_avg:216.37ms step:4053/6200 train_loss:3.5665 train_time:874791ms step_avg:216.37ms step:4054/6200 train_loss:3.4290 train_time:875005ms step_avg:216.37ms step:4055/6200 train_loss:3.5109 train_time:875218ms step_avg:216.37ms step:4056/6200 train_loss:3.5047 train_time:875432ms step_avg:216.37ms step:4057/6200 train_loss:3.4657 train_time:875646ms step_avg:216.37ms step:4058/6200 train_loss:3.3346 train_time:875860ms step_avg:216.37ms step:4059/6200 train_loss:3.4828 train_time:876074ms step_avg:216.37ms step:4060/6200 train_loss:3.3472 train_time:876288ms step_avg:216.37ms step:4061/6200 train_loss:3.4271 train_time:876501ms step_avg:216.37ms step:4062/6200 train_loss:3.5461 train_time:876713ms step_avg:216.37ms step:4063/6200 train_loss:3.7332 train_time:876927ms step_avg:216.36ms step:4064/6200 train_loss:3.0934 train_time:877140ms step_avg:216.36ms step:4065/6200 train_loss:3.4656 train_time:877354ms step_avg:216.36ms step:4066/6200 train_loss:3.3541 train_time:877568ms step_avg:216.36ms step:4067/6200 train_loss:3.5122 train_time:877782ms step_avg:216.36ms step:4068/6200 train_loss:3.5158 train_time:877995ms step_avg:216.36ms step:4069/6200 train_loss:3.3104 train_time:878210ms step_avg:216.36ms step:4070/6200 train_loss:3.4827 train_time:878423ms step_avg:216.36ms step:4071/6200 train_loss:3.3020 train_time:878637ms step_avg:216.36ms step:4072/6200 train_loss:3.4834 train_time:878851ms step_avg:216.36ms step:4073/6200 train_loss:3.5917 train_time:879065ms step_avg:216.36ms step:4074/6200 train_loss:3.5251 train_time:879279ms step_avg:216.36ms step:4075/6200 train_loss:3.4301 train_time:879494ms step_avg:216.36ms step:4076/6200 train_loss:3.4262 train_time:879709ms step_avg:216.36ms step:4077/6200 train_loss:3.2965 train_time:879920ms step_avg:216.36ms step:4078/6200 train_loss:3.4674 train_time:880134ms step_avg:216.36ms step:4079/6200 train_loss:3.4762 train_time:880347ms step_avg:216.35ms step:4080/6200 train_loss:3.2819 train_time:880562ms step_avg:216.35ms step:4081/6200 train_loss:3.4471 train_time:880775ms step_avg:216.35ms step:4082/6200 train_loss:3.3962 train_time:880991ms step_avg:216.35ms step:4083/6200 train_loss:3.4576 train_time:881204ms step_avg:216.35ms step:4084/6200 train_loss:3.4573 train_time:881417ms step_avg:216.35ms step:4085/6200 train_loss:3.4875 train_time:881631ms step_avg:216.35ms step:4086/6200 train_loss:3.4471 train_time:881845ms step_avg:216.35ms step:4087/6200 train_loss:3.4213 train_time:882058ms step_avg:216.35ms step:4088/6200 train_loss:3.5398 train_time:882273ms step_avg:216.35ms step:4089/6200 train_loss:3.3785 train_time:882488ms step_avg:216.35ms step:4090/6200 train_loss:3.4016 train_time:882702ms step_avg:216.35ms step:4091/6200 train_loss:3.4227 train_time:882914ms step_avg:216.35ms step:4092/6200 train_loss:3.3629 train_time:883127ms step_avg:216.35ms step:4093/6200 train_loss:3.3624 train_time:883341ms step_avg:216.35ms step:4094/6200 train_loss:3.5452 train_time:883554ms step_avg:216.35ms step:4095/6200 train_loss:3.5301 train_time:883769ms step_avg:216.34ms step:4096/6200 train_loss:3.4435 train_time:883982ms step_avg:216.34ms step:4097/6200 train_loss:3.5055 train_time:884195ms step_avg:216.34ms step:4098/6200 train_loss:3.2813 train_time:884409ms step_avg:216.34ms step:4099/6200 train_loss:3.4215 train_time:884621ms step_avg:216.34ms step:4100/6200 train_loss:3.3903 train_time:884835ms step_avg:216.34ms step:4101/6200 train_loss:3.1883 train_time:885050ms step_avg:216.34ms step:4102/6200 train_loss:3.4671 train_time:885263ms step_avg:216.34ms step:4103/6200 train_loss:3.4350 train_time:885476ms step_avg:216.34ms step:4104/6200 train_loss:3.2631 train_time:885692ms step_avg:216.34ms step:4105/6200 train_loss:3.3626 train_time:885906ms step_avg:216.34ms step:4106/6200 train_loss:3.5060 train_time:886119ms step_avg:216.34ms step:4107/6200 train_loss:3.5579 train_time:886333ms step_avg:216.34ms step:4108/6200 train_loss:3.4511 train_time:886551ms step_avg:216.34ms step:4109/6200 train_loss:3.5476 train_time:886766ms step_avg:216.34ms step:4110/6200 train_loss:3.5333 train_time:886979ms step_avg:216.34ms step:4111/6200 train_loss:3.6999 train_time:887194ms step_avg:216.34ms step:4112/6200 train_loss:3.3537 train_time:887408ms step_avg:216.34ms step:4113/6200 train_loss:3.4929 train_time:887620ms step_avg:216.33ms step:4114/6200 train_loss:3.3928 train_time:887834ms step_avg:216.33ms step:4115/6200 train_loss:3.4996 train_time:888047ms step_avg:216.33ms step:4116/6200 train_loss:3.4896 train_time:888261ms step_avg:216.33ms step:4117/6200 train_loss:3.7412 train_time:888474ms step_avg:216.33ms step:4118/6200 train_loss:3.3059 train_time:888689ms step_avg:216.33ms step:4119/6200 train_loss:3.4774 train_time:888902ms step_avg:216.33ms step:4120/6200 train_loss:3.3875 train_time:889114ms step_avg:216.33ms step:4121/6200 train_loss:3.4976 train_time:889327ms step_avg:216.33ms step:4122/6200 train_loss:3.4886 train_time:889540ms step_avg:216.33ms step:4123/6200 train_loss:3.4871 train_time:889754ms step_avg:216.33ms step:4124/6200 train_loss:3.3101 train_time:889970ms step_avg:216.33ms step:4125/6200 train_loss:3.3151 train_time:890184ms step_avg:216.33ms step:4125/6200 val_loss:3.4264 train_time:890186ms step_avg:216.33ms step:4126/6200 train_loss:3.4416 train_time:890402ms step_avg:216.33ms step:4127/6200 train_loss:3.3812 train_time:890616ms step_avg:216.33ms step:4128/6200 train_loss:3.4512 train_time:890828ms step_avg:216.33ms step:4129/6200 train_loss:3.4519 train_time:891041ms step_avg:216.32ms step:4130/6200 train_loss:3.2259 train_time:891256ms step_avg:216.32ms step:4131/6200 train_loss:3.5202 train_time:891470ms step_avg:216.32ms step:4132/6200 train_loss:3.4838 train_time:891683ms step_avg:216.32ms step:4133/6200 train_loss:3.4010 train_time:891898ms step_avg:216.32ms step:4134/6200 train_loss:3.6081 train_time:892111ms step_avg:216.32ms step:4135/6200 train_loss:3.4414 train_time:892324ms step_avg:216.32ms step:4136/6200 train_loss:3.4106 train_time:892538ms step_avg:216.32ms step:4137/6200 train_loss:3.5630 train_time:892752ms step_avg:216.32ms step:4138/6200 train_loss:3.4006 train_time:892965ms step_avg:216.32ms step:4139/6200 train_loss:3.4599 train_time:893179ms step_avg:216.32ms step:4140/6200 train_loss:3.5473 train_time:893394ms step_avg:216.32ms step:4141/6200 train_loss:3.5818 train_time:893608ms step_avg:216.32ms step:4142/6200 train_loss:3.5462 train_time:893819ms step_avg:216.32ms step:4143/6200 train_loss:3.5208 train_time:894033ms step_avg:216.32ms step:4144/6200 train_loss:3.4202 train_time:894246ms step_avg:216.31ms step:4145/6200 train_loss:3.3929 train_time:894460ms step_avg:216.31ms step:4146/6200 train_loss:3.5037 train_time:894675ms step_avg:216.31ms step:4147/6200 train_loss:3.0626 train_time:894888ms step_avg:216.31ms step:4148/6200 train_loss:3.4146 train_time:895102ms step_avg:216.31ms step:4149/6200 train_loss:3.4557 train_time:895316ms step_avg:216.31ms step:4150/6200 train_loss:3.2630 train_time:895528ms step_avg:216.31ms step:4151/6200 train_loss:3.3069 train_time:895741ms step_avg:216.31ms step:4152/6200 train_loss:3.3480 train_time:895955ms step_avg:216.31ms step:4153/6200 train_loss:3.3991 train_time:896168ms step_avg:216.31ms step:4154/6200 train_loss:3.4525 train_time:896382ms step_avg:216.31ms step:4155/6200 train_loss:3.5575 train_time:896598ms step_avg:216.31ms step:4156/6200 train_loss:3.3779 train_time:896812ms step_avg:216.31ms step:4157/6200 train_loss:3.3624 train_time:897025ms step_avg:216.31ms step:4158/6200 train_loss:3.4380 train_time:897495ms step_avg:216.37ms step:4159/6200 train_loss:3.4455 train_time:897709ms step_avg:216.37ms step:4160/6200 train_loss:3.3702 train_time:897922ms step_avg:216.37ms step:4161/6200 train_loss:3.4499 train_time:898136ms step_avg:216.37ms step:4162/6200 train_loss:3.3837 train_time:898350ms step_avg:216.37ms step:4163/6200 train_loss:3.6106 train_time:898564ms step_avg:216.36ms step:4164/6200 train_loss:3.2931 train_time:898778ms step_avg:216.36ms step:4165/6200 train_loss:3.4029 train_time:898993ms step_avg:216.36ms step:4166/6200 train_loss:3.3843 train_time:899207ms step_avg:216.36ms step:4167/6200 train_loss:3.4221 train_time:899419ms step_avg:216.36ms step:4168/6200 train_loss:3.4146 train_time:899632ms step_avg:216.36ms step:4169/6200 train_loss:3.4452 train_time:899845ms step_avg:216.36ms step:4170/6200 train_loss:3.2829 train_time:900059ms step_avg:216.36ms step:4171/6200 train_loss:3.3794 train_time:900274ms step_avg:216.36ms step:4172/6200 train_loss:3.5135 train_time:900488ms step_avg:216.36ms step:4173/6200 train_loss:3.5764 train_time:900701ms step_avg:216.36ms step:4174/6200 train_loss:3.9440 train_time:900916ms step_avg:216.36ms step:4175/6200 train_loss:3.3847 train_time:901128ms step_avg:216.36ms step:4176/6200 train_loss:3.5437 train_time:901341ms step_avg:216.36ms step:4177/6200 train_loss:3.3448 train_time:901556ms step_avg:216.36ms step:4178/6200 train_loss:3.3674 train_time:901769ms step_avg:216.36ms step:4179/6200 train_loss:3.5256 train_time:901982ms step_avg:216.35ms step:4180/6200 train_loss:3.4705 train_time:902446ms step_avg:216.41ms step:4181/6200 train_loss:3.4609 train_time:902660ms step_avg:216.41ms step:4182/6200 train_loss:3.4626 train_time:902874ms step_avg:216.41ms step:4183/6200 train_loss:3.5005 train_time:903090ms step_avg:216.41ms step:4184/6200 train_loss:3.9194 train_time:903303ms step_avg:216.41ms step:4185/6200 train_loss:3.4439 train_time:903517ms step_avg:216.41ms step:4186/6200 train_loss:3.4916 train_time:903730ms step_avg:216.41ms step:4187/6200 train_loss:3.5373 train_time:903943ms step_avg:216.41ms step:4188/6200 train_loss:3.5258 train_time:904158ms step_avg:216.41ms step:4189/6200 train_loss:3.1723 train_time:904372ms step_avg:216.41ms step:4190/6200 train_loss:3.5233 train_time:904586ms step_avg:216.41ms step:4191/6200 train_loss:3.5310 train_time:904800ms step_avg:216.41ms step:4192/6200 train_loss:3.5067 train_time:905013ms step_avg:216.41ms step:4193/6200 train_loss:3.4370 train_time:905226ms step_avg:216.41ms step:4194/6200 train_loss:3.4583 train_time:905440ms step_avg:216.41ms step:4195/6200 train_loss:3.4498 train_time:905655ms step_avg:216.40ms step:4196/6200 train_loss:3.3802 train_time:905868ms step_avg:216.40ms step:4197/6200 train_loss:3.7302 train_time:906082ms step_avg:216.40ms step:4198/6200 train_loss:3.1707 train_time:906297ms step_avg:216.40ms step:4199/6200 train_loss:3.5793 train_time:906511ms step_avg:216.40ms step:4200/6200 train_loss:3.4506 train_time:906724ms step_avg:216.40ms step:4201/6200 train_loss:3.3357 train_time:906937ms step_avg:216.40ms step:4202/6200 train_loss:3.4824 train_time:907151ms step_avg:216.40ms step:4203/6200 train_loss:3.3402 train_time:907364ms step_avg:216.40ms step:4204/6200 train_loss:3.3554 train_time:907578ms step_avg:216.40ms step:4205/6200 train_loss:3.3738 train_time:907792ms step_avg:216.40ms step:4206/6200 train_loss:3.3654 train_time:908005ms step_avg:216.40ms step:4207/6200 train_loss:3.8271 train_time:908218ms step_avg:216.40ms step:4208/6200 train_loss:3.3938 train_time:908432ms step_avg:216.40ms step:4209/6200 train_loss:3.5308 train_time:908645ms step_avg:216.40ms step:4210/6200 train_loss:3.4283 train_time:908859ms step_avg:216.39ms step:4211/6200 train_loss:3.8163 train_time:909073ms step_avg:216.39ms step:4212/6200 train_loss:3.4696 train_time:909287ms step_avg:216.39ms step:4213/6200 train_loss:3.4695 train_time:909499ms step_avg:216.39ms step:4214/6200 train_loss:3.3399 train_time:909713ms step_avg:216.39ms step:4215/6200 train_loss:3.4109 train_time:909926ms step_avg:216.39ms step:4216/6200 train_loss:3.4845 train_time:910139ms step_avg:216.39ms step:4217/6200 train_loss:3.3414 train_time:910353ms step_avg:216.39ms step:4218/6200 train_loss:3.4060 train_time:910571ms step_avg:216.39ms step:4219/6200 train_loss:3.4533 train_time:910784ms step_avg:216.39ms step:4220/6200 train_loss:3.2630 train_time:910999ms step_avg:216.39ms step:4221/6200 train_loss:3.4380 train_time:911213ms step_avg:216.39ms step:4222/6200 train_loss:3.4582 train_time:911428ms step_avg:216.39ms step:4223/6200 train_loss:3.4263 train_time:911640ms step_avg:216.39ms step:4224/6200 train_loss:3.6396 train_time:911854ms step_avg:216.39ms step:4225/6200 train_loss:3.5073 train_time:912067ms step_avg:216.39ms step:4226/6200 train_loss:3.5682 train_time:912280ms step_avg:216.39ms step:4227/6200 train_loss:3.3453 train_time:912496ms step_avg:216.39ms step:4228/6200 train_loss:3.4151 train_time:912709ms step_avg:216.38ms step:4229/6200 train_loss:3.4534 train_time:912922ms step_avg:216.38ms step:4230/6200 train_loss:3.3615 train_time:913135ms step_avg:216.38ms step:4231/6200 train_loss:3.5485 train_time:913349ms step_avg:216.38ms step:4232/6200 train_loss:3.5553 train_time:913562ms step_avg:216.38ms step:4233/6200 train_loss:3.5489 train_time:913777ms step_avg:216.38ms step:4234/6200 train_loss:3.6545 train_time:913992ms step_avg:216.38ms step:4235/6200 train_loss:3.5043 train_time:914204ms step_avg:216.38ms step:4236/6200 train_loss:3.4488 train_time:914417ms step_avg:216.38ms step:4237/6200 train_loss:3.3139 train_time:914630ms step_avg:216.38ms step:4238/6200 train_loss:3.5112 train_time:914844ms step_avg:216.38ms step:4239/6200 train_loss:3.4268 train_time:915058ms step_avg:216.38ms step:4240/6200 train_loss:3.3404 train_time:915272ms step_avg:216.38ms step:4241/6200 train_loss:3.3797 train_time:915486ms step_avg:216.38ms step:4242/6200 train_loss:3.3317 train_time:915700ms step_avg:216.38ms step:4243/6200 train_loss:3.4144 train_time:915913ms step_avg:216.37ms step:4244/6200 train_loss:3.3427 train_time:916125ms step_avg:216.37ms step:4245/6200 train_loss:3.2454 train_time:916339ms step_avg:216.37ms step:4246/6200 train_loss:3.5522 train_time:916553ms step_avg:216.37ms step:4247/6200 train_loss:3.3645 train_time:916767ms step_avg:216.37ms step:4248/6200 train_loss:3.2848 train_time:916979ms step_avg:216.37ms step:4249/6200 train_loss:3.4934 train_time:917194ms step_avg:216.37ms step:4250/6200 train_loss:3.8216 train_time:917407ms step_avg:216.37ms step:4250/6200 val_loss:3.4239 train_time:917408ms step_avg:216.37ms step:4251/6200 train_loss:3.4057 train_time:917625ms step_avg:216.37ms step:4252/6200 train_loss:3.6506 train_time:917837ms step_avg:216.37ms step:4253/6200 train_loss:3.4989 train_time:918052ms step_avg:216.37ms step:4254/6200 train_loss:3.3134 train_time:918265ms step_avg:216.37ms step:4255/6200 train_loss:3.3837 train_time:918480ms step_avg:216.37ms step:4256/6200 train_loss:3.3179 train_time:918696ms step_avg:216.37ms step:4257/6200 train_loss:3.5435 train_time:918910ms step_avg:216.37ms step:4258/6200 train_loss:3.4351 train_time:919123ms step_avg:216.37ms step:4259/6200 train_loss:3.4819 train_time:919335ms step_avg:216.37ms step:4260/6200 train_loss:3.3072 train_time:919549ms step_avg:216.36ms step:4261/6200 train_loss:3.6047 train_time:919762ms step_avg:216.36ms step:4262/6200 train_loss:3.4292 train_time:919977ms step_avg:216.36ms step:4263/6200 train_loss:3.4433 train_time:920191ms step_avg:216.36ms step:4264/6200 train_loss:3.4920 train_time:920406ms step_avg:216.36ms step:4265/6200 train_loss:3.4393 train_time:920618ms step_avg:216.36ms step:4266/6200 train_loss:3.4451 train_time:920832ms step_avg:216.36ms step:4267/6200 train_loss:3.5629 train_time:921046ms step_avg:216.36ms step:4268/6200 train_loss:3.4029 train_time:921259ms step_avg:216.36ms step:4269/6200 train_loss:3.9322 train_time:921474ms step_avg:216.36ms step:4270/6200 train_loss:3.3606 train_time:921689ms step_avg:216.36ms step:4271/6200 train_loss:3.4770 train_time:921903ms step_avg:216.36ms step:4272/6200 train_loss:3.4003 train_time:922118ms step_avg:216.36ms step:4273/6200 train_loss:3.6046 train_time:922332ms step_avg:216.36ms step:4274/6200 train_loss:3.5248 train_time:922544ms step_avg:216.36ms step:4275/6200 train_loss:3.3899 train_time:922759ms step_avg:216.36ms step:4276/6200 train_loss:3.4353 train_time:922974ms step_avg:216.36ms step:4277/6200 train_loss:3.3663 train_time:923188ms step_avg:216.36ms step:4278/6200 train_loss:3.3987 train_time:923403ms step_avg:216.36ms step:4279/6200 train_loss:3.3947 train_time:923620ms step_avg:216.36ms step:4280/6200 train_loss:3.4736 train_time:923833ms step_avg:216.35ms step:4281/6200 train_loss:3.4510 train_time:924045ms step_avg:216.35ms step:4282/6200 train_loss:3.4757 train_time:924259ms step_avg:216.35ms step:4283/6200 train_loss:3.4028 train_time:924474ms step_avg:216.35ms step:4284/6200 train_loss:3.4498 train_time:924688ms step_avg:216.35ms step:4285/6200 train_loss:3.5063 train_time:924902ms step_avg:216.35ms step:4286/6200 train_loss:3.4549 train_time:925116ms step_avg:216.35ms step:4287/6200 train_loss:3.3514 train_time:925330ms step_avg:216.35ms step:4288/6200 train_loss:3.3860 train_time:925543ms step_avg:216.35ms step:4289/6200 train_loss:3.4759 train_time:925757ms step_avg:216.35ms step:4290/6200 train_loss:3.4376 train_time:925971ms step_avg:216.35ms step:4291/6200 train_loss:3.3437 train_time:926185ms step_avg:216.35ms step:4292/6200 train_loss:3.3736 train_time:926399ms step_avg:216.35ms step:4293/6200 train_loss:3.4369 train_time:926615ms step_avg:216.35ms step:4294/6200 train_loss:3.2261 train_time:926828ms step_avg:216.35ms step:4295/6200 train_loss:3.5750 train_time:927040ms step_avg:216.35ms step:4296/6200 train_loss:3.4723 train_time:927255ms step_avg:216.35ms step:4297/6200 train_loss:3.4125 train_time:927469ms step_avg:216.34ms step:4298/6200 train_loss:3.5862 train_time:927683ms step_avg:216.34ms step:4299/6200 train_loss:3.5065 train_time:927897ms step_avg:216.34ms step:4300/6200 train_loss:3.3369 train_time:928111ms step_avg:216.34ms step:4301/6200 train_loss:3.3334 train_time:928324ms step_avg:216.34ms step:4302/6200 train_loss:3.4858 train_time:928536ms step_avg:216.34ms step:4303/6200 train_loss:3.3152 train_time:928749ms step_avg:216.34ms step:4304/6200 train_loss:3.4647 train_time:928963ms step_avg:216.34ms step:4305/6200 train_loss:3.5522 train_time:929177ms step_avg:216.34ms step:4306/6200 train_loss:3.2985 train_time:929391ms step_avg:216.34ms step:4307/6200 train_loss:3.8206 train_time:929605ms step_avg:216.34ms step:4308/6200 train_loss:3.4423 train_time:929818ms step_avg:216.34ms step:4309/6200 train_loss:3.3619 train_time:930032ms step_avg:216.34ms step:4310/6200 train_loss:3.3726 train_time:930245ms step_avg:216.34ms step:4311/6200 train_loss:3.6678 train_time:930458ms step_avg:216.34ms step:4312/6200 train_loss:3.5012 train_time:930672ms step_avg:216.33ms step:4313/6200 train_loss:3.3548 train_time:930885ms step_avg:216.33ms step:4314/6200 train_loss:3.5586 train_time:931100ms step_avg:216.33ms step:4315/6200 train_loss:3.4958 train_time:931318ms step_avg:216.33ms step:4316/6200 train_loss:3.3968 train_time:931531ms step_avg:216.33ms step:4317/6200 train_loss:3.4467 train_time:931745ms step_avg:216.33ms step:4318/6200 train_loss:3.4142 train_time:931958ms step_avg:216.33ms step:4319/6200 train_loss:3.5121 train_time:932173ms step_avg:216.33ms step:4320/6200 train_loss:3.5662 train_time:932386ms step_avg:216.33ms step:4321/6200 train_loss:3.3883 train_time:932598ms step_avg:216.33ms step:4322/6200 train_loss:3.5498 train_time:932813ms step_avg:216.33ms step:4323/6200 train_loss:3.4194 train_time:933026ms step_avg:216.33ms step:4324/6200 train_loss:3.3435 train_time:933238ms step_avg:216.33ms step:4325/6200 train_loss:3.2855 train_time:933452ms step_avg:216.33ms step:4326/6200 train_loss:3.3807 train_time:933665ms step_avg:216.33ms step:4327/6200 train_loss:3.2698 train_time:933880ms step_avg:216.33ms step:4328/6200 train_loss:3.3884 train_time:934095ms step_avg:216.33ms step:4329/6200 train_loss:3.4207 train_time:934309ms step_avg:216.33ms step:4330/6200 train_loss:3.3659 train_time:934523ms step_avg:216.32ms step:4331/6200 train_loss:3.6176 train_time:934735ms step_avg:216.32ms step:4332/6200 train_loss:3.4200 train_time:934952ms step_avg:216.32ms step:4333/6200 train_loss:3.5293 train_time:935166ms step_avg:216.32ms step:4334/6200 train_loss:3.8872 train_time:935378ms step_avg:216.32ms step:4335/6200 train_loss:3.4232 train_time:935594ms step_avg:216.32ms step:4336/6200 train_loss:3.5364 train_time:935807ms step_avg:216.32ms step:4337/6200 train_loss:3.4253 train_time:936020ms step_avg:216.32ms step:4338/6200 train_loss:3.3161 train_time:936234ms step_avg:216.32ms step:4339/6200 train_loss:3.4539 train_time:936446ms step_avg:216.32ms step:4340/6200 train_loss:3.3388 train_time:936660ms step_avg:216.32ms step:4341/6200 train_loss:3.4440 train_time:936875ms step_avg:216.32ms step:4342/6200 train_loss:3.4688 train_time:937087ms step_avg:216.32ms step:4343/6200 train_loss:3.4609 train_time:937301ms step_avg:216.32ms step:4344/6200 train_loss:3.4558 train_time:937517ms step_avg:216.32ms step:4345/6200 train_loss:4.0866 train_time:937730ms step_avg:216.32ms step:4346/6200 train_loss:3.5314 train_time:937942ms step_avg:216.32ms step:4347/6200 train_loss:3.3255 train_time:938411ms step_avg:216.37ms step:4348/6200 train_loss:3.4649 train_time:938625ms step_avg:216.37ms step:4349/6200 train_loss:3.4172 train_time:938836ms step_avg:216.37ms step:4350/6200 train_loss:3.3288 train_time:939049ms step_avg:216.37ms step:4351/6200 train_loss:3.4949 train_time:939263ms step_avg:216.37ms step:4352/6200 train_loss:3.4434 train_time:939477ms step_avg:216.37ms step:4353/6200 train_loss:3.5156 train_time:939691ms step_avg:216.37ms step:4354/6200 train_loss:3.5516 train_time:939905ms step_avg:216.37ms step:4355/6200 train_loss:3.3859 train_time:940118ms step_avg:216.37ms step:4356/6200 train_loss:3.3339 train_time:940332ms step_avg:216.37ms step:4357/6200 train_loss:3.4644 train_time:940544ms step_avg:216.37ms step:4358/6200 train_loss:3.4079 train_time:940758ms step_avg:216.37ms step:4359/6200 train_loss:3.5937 train_time:940971ms step_avg:216.37ms step:4360/6200 train_loss:3.4654 train_time:941185ms step_avg:216.36ms step:4361/6200 train_loss:3.5407 train_time:941398ms step_avg:216.36ms step:4362/6200 train_loss:3.6948 train_time:941613ms step_avg:216.36ms step:4363/6200 train_loss:3.4878 train_time:941826ms step_avg:216.36ms step:4364/6200 train_loss:3.4527 train_time:942039ms step_avg:216.36ms step:4365/6200 train_loss:3.6534 train_time:942253ms step_avg:216.36ms step:4366/6200 train_loss:3.5513 train_time:942466ms step_avg:216.36ms step:4367/6200 train_loss:3.3704 train_time:942678ms step_avg:216.36ms step:4368/6200 train_loss:3.3864 train_time:942893ms step_avg:216.36ms step:4369/6200 train_loss:3.4824 train_time:943106ms step_avg:216.36ms step:4370/6200 train_loss:3.4842 train_time:943571ms step_avg:216.42ms step:4371/6200 train_loss:3.6274 train_time:943786ms step_avg:216.42ms step:4372/6200 train_loss:3.3228 train_time:943999ms step_avg:216.41ms step:4373/6200 train_loss:3.3166 train_time:944213ms step_avg:216.41ms step:4374/6200 train_loss:3.4754 train_time:944426ms step_avg:216.41ms step:4375/6200 train_loss:3.5032 train_time:944638ms step_avg:216.41ms step:4375/6200 val_loss:3.4157 train_time:944640ms step_avg:216.41ms step:4376/6200 train_loss:3.5622 train_time:944857ms step_avg:216.41ms step:4377/6200 train_loss:3.3526 train_time:945070ms step_avg:216.41ms step:4378/6200 train_loss:3.4036 train_time:945283ms step_avg:216.41ms step:4379/6200 train_loss:3.4163 train_time:945498ms step_avg:216.41ms step:4380/6200 train_loss:3.4692 train_time:945716ms step_avg:216.41ms step:4381/6200 train_loss:3.3625 train_time:945930ms step_avg:216.41ms step:4382/6200 train_loss:3.5989 train_time:946143ms step_avg:216.41ms step:4383/6200 train_loss:3.5137 train_time:946357ms step_avg:216.41ms step:4384/6200 train_loss:3.5066 train_time:946570ms step_avg:216.41ms step:4385/6200 train_loss:3.3794 train_time:946785ms step_avg:216.41ms step:4386/6200 train_loss:3.5148 train_time:946998ms step_avg:216.41ms step:4387/6200 train_loss:3.4105 train_time:947212ms step_avg:216.41ms step:4388/6200 train_loss:3.5369 train_time:947425ms step_avg:216.41ms step:4389/6200 train_loss:3.3694 train_time:947639ms step_avg:216.41ms step:4390/6200 train_loss:3.4910 train_time:947852ms step_avg:216.40ms step:4391/6200 train_loss:3.5024 train_time:948065ms step_avg:216.40ms step:4392/6200 train_loss:3.3203 train_time:948278ms step_avg:216.40ms step:4393/6200 train_loss:4.0038 train_time:948491ms step_avg:216.40ms step:4394/6200 train_loss:3.3992 train_time:948705ms step_avg:216.40ms step:4395/6200 train_loss:3.5869 train_time:948920ms step_avg:216.40ms step:4396/6200 train_loss:3.3664 train_time:949135ms step_avg:216.40ms step:4397/6200 train_loss:3.4912 train_time:949348ms step_avg:216.40ms step:4398/6200 train_loss:3.2812 train_time:949560ms step_avg:216.40ms step:4399/6200 train_loss:3.5091 train_time:949775ms step_avg:216.40ms step:4400/6200 train_loss:3.3364 train_time:949988ms step_avg:216.40ms step:4401/6200 train_loss:3.4027 train_time:950202ms step_avg:216.40ms step:4402/6200 train_loss:3.4806 train_time:950416ms step_avg:216.40ms step:4403/6200 train_loss:3.3066 train_time:950631ms step_avg:216.40ms step:4404/6200 train_loss:3.3579 train_time:950844ms step_avg:216.40ms step:4405/6200 train_loss:3.5592 train_time:951057ms step_avg:216.40ms step:4406/6200 train_loss:3.4229 train_time:951270ms step_avg:216.39ms step:4407/6200 train_loss:3.4298 train_time:951482ms step_avg:216.39ms step:4408/6200 train_loss:3.3927 train_time:951697ms step_avg:216.39ms step:4409/6200 train_loss:3.4791 train_time:951910ms step_avg:216.39ms step:4410/6200 train_loss:3.4639 train_time:952122ms step_avg:216.39ms step:4411/6200 train_loss:3.5832 train_time:952338ms step_avg:216.39ms step:4412/6200 train_loss:3.4286 train_time:952550ms step_avg:216.39ms step:4413/6200 train_loss:3.4568 train_time:952763ms step_avg:216.39ms step:4414/6200 train_loss:3.4476 train_time:952976ms step_avg:216.39ms step:4415/6200 train_loss:3.4878 train_time:953190ms step_avg:216.39ms step:4416/6200 train_loss:3.4444 train_time:953402ms step_avg:216.39ms step:4417/6200 train_loss:3.5033 train_time:953618ms step_avg:216.39ms step:4418/6200 train_loss:3.4328 train_time:953831ms step_avg:216.39ms step:4419/6200 train_loss:3.3524 train_time:954045ms step_avg:216.39ms step:4420/6200 train_loss:3.3971 train_time:954258ms step_avg:216.38ms step:4421/6200 train_loss:3.6250 train_time:954470ms step_avg:216.38ms step:4422/6200 train_loss:3.4266 train_time:954684ms step_avg:216.38ms step:4423/6200 train_loss:3.3535 train_time:954898ms step_avg:216.38ms step:4424/6200 train_loss:3.3651 train_time:955112ms step_avg:216.38ms step:4425/6200 train_loss:3.5437 train_time:955325ms step_avg:216.38ms step:4426/6200 train_loss:3.5007 train_time:955539ms step_avg:216.38ms step:4427/6200 train_loss:3.4081 train_time:955752ms step_avg:216.38ms step:4428/6200 train_loss:3.6186 train_time:955964ms step_avg:216.38ms step:4429/6200 train_loss:3.5308 train_time:956177ms step_avg:216.38ms step:4430/6200 train_loss:3.3234 train_time:956389ms step_avg:216.38ms step:4431/6200 train_loss:3.3228 train_time:956601ms step_avg:216.38ms step:4432/6200 train_loss:3.4704 train_time:956817ms step_avg:216.38ms step:4433/6200 train_loss:3.3458 train_time:957031ms step_avg:216.38ms step:4434/6200 train_loss:3.4561 train_time:957244ms step_avg:216.38ms step:4435/6200 train_loss:3.5179 train_time:957457ms step_avg:216.37ms step:4436/6200 train_loss:3.4180 train_time:957670ms step_avg:216.37ms step:4437/6200 train_loss:3.3304 train_time:957882ms step_avg:216.37ms step:4438/6200 train_loss:3.5720 train_time:958097ms step_avg:216.37ms step:4439/6200 train_loss:3.5000 train_time:958311ms step_avg:216.37ms step:4440/6200 train_loss:3.3965 train_time:958524ms step_avg:216.37ms step:4441/6200 train_loss:3.5031 train_time:958740ms step_avg:216.37ms step:4442/6200 train_loss:3.5271 train_time:958953ms step_avg:216.37ms step:4443/6200 train_loss:3.5846 train_time:959165ms step_avg:216.37ms step:4444/6200 train_loss:3.4659 train_time:959378ms step_avg:216.37ms step:4445/6200 train_loss:3.2830 train_time:959592ms step_avg:216.37ms step:4446/6200 train_loss:3.5614 train_time:959807ms step_avg:216.37ms step:4447/6200 train_loss:3.4445 train_time:960019ms step_avg:216.37ms step:4448/6200 train_loss:3.3378 train_time:960233ms step_avg:216.37ms step:4449/6200 train_loss:3.4644 train_time:960446ms step_avg:216.37ms step:4450/6200 train_loss:3.4581 train_time:960659ms step_avg:216.36ms step:4451/6200 train_loss:3.4798 train_time:960871ms step_avg:216.36ms step:4452/6200 train_loss:3.4984 train_time:961085ms step_avg:216.36ms step:4453/6200 train_loss:3.3714 train_time:961299ms step_avg:216.36ms step:4454/6200 train_loss:3.4176 train_time:961513ms step_avg:216.36ms step:4455/6200 train_loss:3.4000 train_time:961727ms step_avg:216.36ms step:4456/6200 train_loss:3.2950 train_time:961940ms step_avg:216.36ms step:4457/6200 train_loss:3.5050 train_time:962154ms step_avg:216.36ms step:4458/6200 train_loss:3.3820 train_time:962367ms step_avg:216.36ms step:4459/6200 train_loss:3.3380 train_time:962580ms step_avg:216.36ms step:4460/6200 train_loss:3.4607 train_time:962794ms step_avg:216.36ms step:4461/6200 train_loss:3.9595 train_time:963007ms step_avg:216.36ms step:4462/6200 train_loss:3.4489 train_time:963220ms step_avg:216.36ms step:4463/6200 train_loss:3.5738 train_time:963434ms step_avg:216.36ms step:4464/6200 train_loss:3.4799 train_time:963646ms step_avg:216.36ms step:4465/6200 train_loss:3.4501 train_time:963859ms step_avg:216.35ms step:4466/6200 train_loss:3.5245 train_time:964072ms step_avg:216.35ms step:4467/6200 train_loss:3.3371 train_time:964285ms step_avg:216.35ms step:4468/6200 train_loss:3.3771 train_time:964499ms step_avg:216.35ms step:4469/6200 train_loss:3.5044 train_time:964712ms step_avg:216.35ms step:4470/6200 train_loss:3.4856 train_time:964926ms step_avg:216.35ms step:4471/6200 train_loss:3.4101 train_time:965141ms step_avg:216.35ms step:4472/6200 train_loss:3.3654 train_time:965352ms step_avg:216.35ms step:4473/6200 train_loss:3.4432 train_time:965565ms step_avg:216.35ms step:4474/6200 train_loss:3.2996 train_time:965778ms step_avg:216.35ms step:4475/6200 train_loss:3.3753 train_time:965992ms step_avg:216.35ms step:4476/6200 train_loss:3.3973 train_time:966205ms step_avg:216.35ms step:4477/6200 train_loss:3.5674 train_time:966420ms step_avg:216.35ms step:4478/6200 train_loss:3.2995 train_time:966638ms step_avg:216.35ms step:4479/6200 train_loss:3.4154 train_time:966853ms step_avg:216.35ms step:4480/6200 train_loss:3.4586 train_time:967065ms step_avg:216.35ms step:4481/6200 train_loss:3.4249 train_time:967278ms step_avg:216.34ms step:4482/6200 train_loss:3.4238 train_time:967492ms step_avg:216.34ms step:4483/6200 train_loss:3.2393 train_time:967706ms step_avg:216.34ms step:4484/6200 train_loss:3.3963 train_time:967920ms step_avg:216.34ms step:4485/6200 train_loss:3.3311 train_time:968134ms step_avg:216.34ms step:4486/6200 train_loss:3.4632 train_time:968347ms step_avg:216.34ms step:4487/6200 train_loss:3.3484 train_time:968559ms step_avg:216.34ms step:4488/6200 train_loss:3.4115 train_time:968772ms step_avg:216.34ms step:4489/6200 train_loss:3.5589 train_time:968985ms step_avg:216.34ms step:4490/6200 train_loss:3.5286 train_time:969199ms step_avg:216.34ms step:4491/6200 train_loss:3.3958 train_time:969412ms step_avg:216.34ms step:4492/6200 train_loss:3.3596 train_time:969626ms step_avg:216.34ms step:4493/6200 train_loss:3.4077 train_time:969839ms step_avg:216.34ms step:4494/6200 train_loss:3.4442 train_time:970052ms step_avg:216.34ms step:4495/6200 train_loss:3.4314 train_time:970268ms step_avg:216.34ms step:4496/6200 train_loss:3.3754 train_time:970481ms step_avg:216.34ms step:4497/6200 train_loss:3.5366 train_time:970697ms step_avg:216.34ms step:4498/6200 train_loss:3.4213 train_time:970910ms step_avg:216.33ms step:4499/6200 train_loss:3.2613 train_time:971122ms step_avg:216.33ms step:4500/6200 train_loss:3.5601 train_time:971337ms step_avg:216.33ms step:4500/6200 val_loss:3.4092 train_time:971339ms step_avg:216.33ms step:4501/6200 train_loss:3.3688 train_time:971555ms step_avg:216.33ms step:4502/6200 train_loss:3.3233 train_time:971768ms step_avg:216.33ms step:4503/6200 train_loss:3.5114 train_time:971983ms step_avg:216.33ms step:4504/6200 train_loss:3.3936 train_time:972198ms step_avg:216.33ms step:4505/6200 train_loss:3.4894 train_time:972410ms step_avg:216.33ms step:4506/6200 train_loss:3.4021 train_time:972623ms step_avg:216.33ms step:4507/6200 train_loss:3.4748 train_time:972836ms step_avg:216.33ms step:4508/6200 train_loss:3.2094 train_time:973049ms step_avg:216.33ms step:4509/6200 train_loss:3.4854 train_time:973263ms step_avg:216.33ms step:4510/6200 train_loss:3.3192 train_time:973477ms step_avg:216.33ms step:4511/6200 train_loss:3.3933 train_time:973689ms step_avg:216.33ms step:4512/6200 train_loss:3.3566 train_time:973903ms step_avg:216.33ms step:4513/6200 train_loss:3.3368 train_time:974115ms step_avg:216.33ms step:4514/6200 train_loss:3.2956 train_time:974328ms step_avg:216.33ms step:4515/6200 train_loss:3.4518 train_time:974542ms step_avg:216.32ms step:4516/6200 train_loss:3.2933 train_time:974755ms step_avg:216.32ms step:4517/6200 train_loss:3.3992 train_time:974968ms step_avg:216.32ms step:4518/6200 train_loss:3.4011 train_time:975187ms step_avg:216.32ms step:4519/6200 train_loss:3.4177 train_time:975399ms step_avg:216.32ms step:4520/6200 train_loss:3.3231 train_time:975612ms step_avg:216.32ms step:4521/6200 train_loss:3.5170 train_time:975825ms step_avg:216.32ms step:4522/6200 train_loss:3.5872 train_time:976038ms step_avg:216.32ms step:4523/6200 train_loss:3.9356 train_time:976251ms step_avg:216.32ms step:4524/6200 train_loss:3.6655 train_time:976465ms step_avg:216.32ms step:4525/6200 train_loss:3.4181 train_time:976679ms step_avg:216.32ms step:4526/6200 train_loss:3.3763 train_time:976892ms step_avg:216.32ms step:4527/6200 train_loss:3.4537 train_time:977105ms step_avg:216.32ms step:4528/6200 train_loss:3.4125 train_time:977318ms step_avg:216.32ms step:4529/6200 train_loss:3.3170 train_time:977532ms step_avg:216.32ms step:4530/6200 train_loss:4.0195 train_time:977747ms step_avg:216.32ms step:4531/6200 train_loss:3.4872 train_time:977960ms step_avg:216.32ms step:4532/6200 train_loss:3.2179 train_time:978174ms step_avg:216.31ms step:4533/6200 train_loss:3.3217 train_time:978388ms step_avg:216.31ms step:4534/6200 train_loss:3.4409 train_time:978601ms step_avg:216.31ms step:4535/6200 train_loss:3.6487 train_time:978813ms step_avg:216.31ms step:4536/6200 train_loss:3.6559 train_time:979284ms step_avg:216.37ms step:4537/6200 train_loss:3.4032 train_time:979497ms step_avg:216.37ms step:4538/6200 train_loss:3.3811 train_time:979709ms step_avg:216.37ms step:4539/6200 train_loss:3.4170 train_time:979922ms step_avg:216.37ms step:4540/6200 train_loss:4.0045 train_time:980135ms step_avg:216.37ms step:4541/6200 train_loss:3.4772 train_time:980348ms step_avg:216.36ms step:4542/6200 train_loss:3.3880 train_time:980563ms step_avg:216.36ms step:4543/6200 train_loss:3.5511 train_time:980777ms step_avg:216.36ms step:4544/6200 train_loss:3.3395 train_time:980989ms step_avg:216.36ms step:4545/6200 train_loss:3.4406 train_time:981203ms step_avg:216.36ms step:4546/6200 train_loss:3.6187 train_time:981415ms step_avg:216.36ms step:4547/6200 train_loss:3.4776 train_time:981628ms step_avg:216.36ms step:4548/6200 train_loss:3.4354 train_time:981841ms step_avg:216.36ms step:4549/6200 train_loss:3.4114 train_time:982055ms step_avg:216.36ms step:4550/6200 train_loss:3.3604 train_time:982267ms step_avg:216.36ms step:4551/6200 train_loss:3.3542 train_time:982481ms step_avg:216.36ms step:4552/6200 train_loss:3.3204 train_time:982695ms step_avg:216.36ms step:4553/6200 train_loss:3.4299 train_time:982907ms step_avg:216.36ms step:4554/6200 train_loss:3.6257 train_time:983119ms step_avg:216.36ms step:4555/6200 train_loss:3.5123 train_time:983333ms step_avg:216.35ms step:4556/6200 train_loss:3.2573 train_time:983547ms step_avg:216.35ms step:4557/6200 train_loss:3.4645 train_time:983761ms step_avg:216.35ms step:4558/6200 train_loss:3.4741 train_time:983975ms step_avg:216.35ms step:4559/6200 train_loss:3.4592 train_time:984188ms step_avg:216.35ms step:4560/6200 train_loss:3.5618 train_time:984651ms step_avg:216.41ms step:4561/6200 train_loss:3.3966 train_time:984866ms step_avg:216.41ms step:4562/6200 train_loss:3.3933 train_time:985079ms step_avg:216.41ms step:4563/6200 train_loss:3.4252 train_time:985292ms step_avg:216.41ms step:4564/6200 train_loss:3.4641 train_time:985505ms step_avg:216.40ms step:4565/6200 train_loss:3.5394 train_time:985718ms step_avg:216.40ms step:4566/6200 train_loss:3.6059 train_time:985932ms step_avg:216.40ms step:4567/6200 train_loss:3.4613 train_time:986146ms step_avg:216.40ms step:4568/6200 train_loss:3.3256 train_time:986360ms step_avg:216.40ms step:4569/6200 train_loss:3.4308 train_time:986574ms step_avg:216.40ms step:4570/6200 train_loss:3.3085 train_time:986787ms step_avg:216.40ms step:4571/6200 train_loss:3.3440 train_time:987000ms step_avg:216.40ms step:4572/6200 train_loss:3.5457 train_time:987213ms step_avg:216.40ms step:4573/6200 train_loss:3.2583 train_time:987426ms step_avg:216.40ms step:4574/6200 train_loss:3.3313 train_time:987640ms step_avg:216.40ms step:4575/6200 train_loss:3.4606 train_time:987854ms step_avg:216.40ms step:4576/6200 train_loss:3.4941 train_time:988067ms step_avg:216.40ms step:4577/6200 train_loss:3.4545 train_time:988281ms step_avg:216.40ms step:4578/6200 train_loss:3.4121 train_time:988494ms step_avg:216.40ms step:4579/6200 train_loss:3.4326 train_time:988706ms step_avg:216.39ms step:4580/6200 train_loss:3.5379 train_time:988921ms step_avg:216.39ms step:4581/6200 train_loss:3.3675 train_time:989134ms step_avg:216.39ms step:4582/6200 train_loss:3.3916 train_time:989348ms step_avg:216.39ms step:4583/6200 train_loss:3.5056 train_time:989562ms step_avg:216.39ms step:4584/6200 train_loss:3.3531 train_time:989775ms step_avg:216.39ms step:4585/6200 train_loss:3.4633 train_time:989988ms step_avg:216.39ms step:4586/6200 train_loss:3.4356 train_time:990201ms step_avg:216.39ms step:4587/6200 train_loss:3.4191 train_time:990414ms step_avg:216.39ms step:4588/6200 train_loss:3.2822 train_time:990627ms step_avg:216.39ms step:4589/6200 train_loss:3.4025 train_time:990839ms step_avg:216.39ms step:4590/6200 train_loss:3.5907 train_time:991052ms step_avg:216.39ms step:4591/6200 train_loss:3.4228 train_time:991266ms step_avg:216.39ms step:4592/6200 train_loss:3.4155 train_time:991480ms step_avg:216.39ms step:4593/6200 train_loss:3.3733 train_time:991693ms step_avg:216.39ms step:4594/6200 train_loss:3.5453 train_time:991905ms step_avg:216.38ms step:4595/6200 train_loss:3.4227 train_time:992119ms step_avg:216.38ms step:4596/6200 train_loss:3.3307 train_time:992332ms step_avg:216.38ms step:4597/6200 train_loss:3.3162 train_time:992547ms step_avg:216.38ms step:4598/6200 train_loss:3.5014 train_time:992760ms step_avg:216.38ms step:4599/6200 train_loss:3.4235 train_time:992974ms step_avg:216.38ms step:4600/6200 train_loss:3.5399 train_time:993188ms step_avg:216.38ms step:4601/6200 train_loss:3.4429 train_time:993401ms step_avg:216.38ms step:4602/6200 train_loss:3.2570 train_time:993613ms step_avg:216.38ms step:4603/6200 train_loss:3.3680 train_time:993827ms step_avg:216.38ms step:4604/6200 train_loss:3.4487 train_time:994040ms step_avg:216.38ms step:4605/6200 train_loss:3.4608 train_time:994254ms step_avg:216.38ms step:4606/6200 train_loss:3.3876 train_time:994468ms step_avg:216.38ms step:4607/6200 train_loss:3.4958 train_time:994682ms step_avg:216.38ms step:4608/6200 train_loss:3.3771 train_time:994895ms step_avg:216.38ms step:4609/6200 train_loss:3.4844 train_time:995107ms step_avg:216.37ms step:4610/6200 train_loss:3.4252 train_time:995320ms step_avg:216.37ms step:4611/6200 train_loss:3.4646 train_time:995534ms step_avg:216.37ms step:4612/6200 train_loss:3.6058 train_time:995748ms step_avg:216.37ms step:4613/6200 train_loss:3.3051 train_time:995962ms step_avg:216.37ms step:4614/6200 train_loss:3.1545 train_time:996175ms step_avg:216.37ms step:4615/6200 train_loss:3.3609 train_time:996388ms step_avg:216.37ms step:4616/6200 train_loss:3.2976 train_time:996602ms step_avg:216.37ms step:4617/6200 train_loss:3.3883 train_time:996814ms step_avg:216.37ms step:4618/6200 train_loss:3.2632 train_time:997027ms step_avg:216.37ms step:4619/6200 train_loss:3.4768 train_time:997240ms step_avg:216.37ms step:4620/6200 train_loss:3.5169 train_time:997453ms step_avg:216.37ms step:4621/6200 train_loss:3.5613 train_time:997667ms step_avg:216.37ms step:4622/6200 train_loss:3.3473 train_time:997882ms step_avg:216.37ms step:4623/6200 train_loss:3.3525 train_time:998094ms step_avg:216.37ms step:4624/6200 train_loss:3.3874 train_time:998307ms step_avg:216.36ms step:4625/6200 train_loss:3.2970 train_time:998521ms step_avg:216.36ms step:4625/6200 val_loss:3.3960 train_time:998522ms step_avg:216.36ms step:4626/6200 train_loss:3.4697 train_time:998738ms step_avg:216.36ms step:4627/6200 train_loss:3.3493 train_time:998954ms step_avg:216.36ms step:4628/6200 train_loss:3.4218 train_time:999169ms step_avg:216.36ms step:4629/6200 train_loss:3.6173 train_time:999383ms step_avg:216.36ms step:4630/6200 train_loss:3.4473 train_time:999596ms step_avg:216.36ms step:4631/6200 train_loss:3.5476 train_time:999811ms step_avg:216.36ms step:4632/6200 train_loss:3.3471 train_time:1000022ms step_avg:216.36ms step:4633/6200 train_loss:3.5343 train_time:1000234ms step_avg:216.36ms step:4634/6200 train_loss:3.3916 train_time:1000447ms step_avg:216.36ms step:4635/6200 train_loss:3.4552 train_time:1000660ms step_avg:216.36ms step:4636/6200 train_loss:3.4616 train_time:1000874ms step_avg:216.36ms step:4637/6200 train_loss:3.2875 train_time:1001088ms step_avg:216.36ms step:4638/6200 train_loss:3.4649 train_time:1001302ms step_avg:216.36ms step:4639/6200 train_loss:3.4134 train_time:1001516ms step_avg:216.36ms step:4640/6200 train_loss:3.4249 train_time:1001728ms step_avg:216.36ms step:4641/6200 train_loss:3.3506 train_time:1001941ms step_avg:216.36ms step:4642/6200 train_loss:3.3856 train_time:1002155ms step_avg:216.35ms step:4643/6200 train_loss:3.4020 train_time:1002368ms step_avg:216.35ms step:4644/6200 train_loss:3.6299 train_time:1002581ms step_avg:216.35ms step:4645/6200 train_loss:3.4866 train_time:1002796ms step_avg:216.35ms step:4646/6200 train_loss:3.5277 train_time:1003010ms step_avg:216.35ms step:4647/6200 train_loss:3.3476 train_time:1003223ms step_avg:216.35ms step:4648/6200 train_loss:3.4674 train_time:1003434ms step_avg:216.35ms step:4649/6200 train_loss:3.3995 train_time:1003647ms step_avg:216.35ms step:4650/6200 train_loss:3.4507 train_time:1003860ms step_avg:216.35ms step:4651/6200 train_loss:3.5802 train_time:1004074ms step_avg:216.35ms step:4652/6200 train_loss:3.4054 train_time:1004287ms step_avg:216.35ms step:4653/6200 train_loss:3.5136 train_time:1004500ms step_avg:216.35ms step:4654/6200 train_loss:3.3620 train_time:1004715ms step_avg:216.35ms step:4655/6200 train_loss:3.4032 train_time:1004928ms step_avg:216.35ms step:4656/6200 train_loss:3.4244 train_time:1005142ms step_avg:216.35ms step:4657/6200 train_loss:3.3739 train_time:1005355ms step_avg:216.34ms step:4658/6200 train_loss:3.3042 train_time:1005568ms step_avg:216.34ms step:4659/6200 train_loss:3.3434 train_time:1005781ms step_avg:216.34ms step:4660/6200 train_loss:3.2728 train_time:1005996ms step_avg:216.34ms step:4661/6200 train_loss:3.4474 train_time:1006210ms step_avg:216.34ms step:4662/6200 train_loss:3.4361 train_time:1006423ms step_avg:216.34ms step:4663/6200 train_loss:3.3843 train_time:1006635ms step_avg:216.34ms step:4664/6200 train_loss:3.3138 train_time:1006848ms step_avg:216.34ms step:4665/6200 train_loss:3.3314 train_time:1007063ms step_avg:216.34ms step:4666/6200 train_loss:3.3764 train_time:1007276ms step_avg:216.34ms step:4667/6200 train_loss:3.4727 train_time:1007493ms step_avg:216.34ms step:4668/6200 train_loss:3.3827 train_time:1007706ms step_avg:216.34ms step:4669/6200 train_loss:3.3563 train_time:1007920ms step_avg:216.34ms step:4670/6200 train_loss:3.4170 train_time:1008133ms step_avg:216.34ms step:4671/6200 train_loss:3.5097 train_time:1008346ms step_avg:216.34ms step:4672/6200 train_loss:3.3960 train_time:1008558ms step_avg:216.34ms step:4673/6200 train_loss:3.4438 train_time:1008774ms step_avg:216.34ms step:4674/6200 train_loss:3.3848 train_time:1008989ms step_avg:216.34ms step:4675/6200 train_loss:3.4195 train_time:1009203ms step_avg:216.34ms step:4676/6200 train_loss:3.5020 train_time:1009416ms step_avg:216.33ms step:4677/6200 train_loss:3.2326 train_time:1009629ms step_avg:216.33ms step:4678/6200 train_loss:3.2855 train_time:1009843ms step_avg:216.33ms step:4679/6200 train_loss:3.4173 train_time:1010055ms step_avg:216.33ms step:4680/6200 train_loss:3.3835 train_time:1010269ms step_avg:216.33ms step:4681/6200 train_loss:3.3882 train_time:1010483ms step_avg:216.33ms step:4682/6200 train_loss:3.3870 train_time:1010696ms step_avg:216.33ms step:4683/6200 train_loss:3.3252 train_time:1010911ms step_avg:216.33ms step:4684/6200 train_loss:3.2954 train_time:1011124ms step_avg:216.33ms step:4685/6200 train_loss:3.5558 train_time:1011336ms step_avg:216.33ms step:4686/6200 train_loss:3.6367 train_time:1011548ms step_avg:216.33ms step:4687/6200 train_loss:3.3221 train_time:1011763ms step_avg:216.33ms step:4688/6200 train_loss:3.3216 train_time:1011976ms step_avg:216.33ms step:4689/6200 train_loss:3.5196 train_time:1012191ms step_avg:216.33ms step:4690/6200 train_loss:3.3382 train_time:1012404ms step_avg:216.33ms step:4691/6200 train_loss:3.2137 train_time:1012618ms step_avg:216.33ms step:4692/6200 train_loss:3.3067 train_time:1012831ms step_avg:216.32ms step:4693/6200 train_loss:3.3052 train_time:1013043ms step_avg:216.32ms step:4694/6200 train_loss:3.3409 train_time:1013257ms step_avg:216.32ms step:4695/6200 train_loss:3.3409 train_time:1013471ms step_avg:216.32ms step:4696/6200 train_loss:3.3775 train_time:1013685ms step_avg:216.32ms step:4697/6200 train_loss:3.4309 train_time:1013898ms step_avg:216.32ms step:4698/6200 train_loss:3.3476 train_time:1014113ms step_avg:216.32ms step:4699/6200 train_loss:3.3730 train_time:1014325ms step_avg:216.32ms step:4700/6200 train_loss:3.4656 train_time:1014538ms step_avg:216.32ms step:4701/6200 train_loss:3.3873 train_time:1014751ms step_avg:216.32ms step:4702/6200 train_loss:3.3721 train_time:1014964ms step_avg:216.32ms step:4703/6200 train_loss:3.3291 train_time:1015177ms step_avg:216.32ms step:4704/6200 train_loss:3.4153 train_time:1015392ms step_avg:216.32ms step:4705/6200 train_loss:3.3697 train_time:1015606ms step_avg:216.32ms step:4706/6200 train_loss:3.2997 train_time:1015818ms step_avg:216.32ms step:4707/6200 train_loss:3.4356 train_time:1016032ms step_avg:216.32ms step:4708/6200 train_loss:3.5166 train_time:1016244ms step_avg:216.31ms step:4709/6200 train_loss:3.3232 train_time:1016456ms step_avg:216.31ms step:4710/6200 train_loss:3.3082 train_time:1016671ms step_avg:216.31ms step:4711/6200 train_loss:3.3333 train_time:1016884ms step_avg:216.31ms step:4712/6200 train_loss:3.3538 train_time:1017097ms step_avg:216.31ms step:4713/6200 train_loss:3.4690 train_time:1017315ms step_avg:216.31ms step:4714/6200 train_loss:3.3100 train_time:1017529ms step_avg:216.31ms step:4715/6200 train_loss:3.3830 train_time:1017741ms step_avg:216.31ms step:4716/6200 train_loss:3.3101 train_time:1017955ms step_avg:216.31ms step:4717/6200 train_loss:3.3778 train_time:1018168ms step_avg:216.31ms step:4718/6200 train_loss:3.3073 train_time:1018382ms step_avg:216.31ms step:4719/6200 train_loss:3.2630 train_time:1018596ms step_avg:216.31ms step:4720/6200 train_loss:3.4401 train_time:1018810ms step_avg:216.31ms step:4721/6200 train_loss:3.4296 train_time:1019023ms step_avg:216.31ms step:4722/6200 train_loss:3.4266 train_time:1019235ms step_avg:216.31ms step:4723/6200 train_loss:3.2819 train_time:1019448ms step_avg:216.31ms step:4724/6200 train_loss:3.4626 train_time:1019662ms step_avg:216.31ms step:4725/6200 train_loss:3.3389 train_time:1020133ms step_avg:216.36ms step:4726/6200 train_loss:3.6611 train_time:1020345ms step_avg:216.36ms step:4727/6200 train_loss:3.4716 train_time:1020559ms step_avg:216.36ms step:4728/6200 train_loss:3.3512 train_time:1020773ms step_avg:216.36ms step:4729/6200 train_loss:3.2814 train_time:1020987ms step_avg:216.36ms step:4730/6200 train_loss:3.2403 train_time:1021200ms step_avg:216.36ms step:4731/6200 train_loss:3.3315 train_time:1021415ms step_avg:216.36ms step:4732/6200 train_loss:3.4068 train_time:1021628ms step_avg:216.36ms step:4733/6200 train_loss:3.2980 train_time:1021841ms step_avg:216.35ms step:4734/6200 train_loss:3.1902 train_time:1022055ms step_avg:216.35ms step:4735/6200 train_loss:3.4665 train_time:1022269ms step_avg:216.35ms step:4736/6200 train_loss:3.3499 train_time:1022482ms step_avg:216.35ms step:4737/6200 train_loss:3.5219 train_time:1022697ms step_avg:216.35ms step:4738/6200 train_loss:3.4470 train_time:1022911ms step_avg:216.35ms step:4739/6200 train_loss:3.3987 train_time:1023124ms step_avg:216.35ms step:4740/6200 train_loss:3.3571 train_time:1023337ms step_avg:216.35ms step:4741/6200 train_loss:3.3818 train_time:1023549ms step_avg:216.35ms step:4742/6200 train_loss:3.3655 train_time:1023763ms step_avg:216.35ms step:4743/6200 train_loss:3.2534 train_time:1023978ms step_avg:216.35ms step:4744/6200 train_loss:3.3827 train_time:1024194ms step_avg:216.35ms step:4745/6200 train_loss:3.3528 train_time:1024407ms step_avg:216.35ms step:4746/6200 train_loss:3.3459 train_time:1024621ms step_avg:216.35ms step:4747/6200 train_loss:3.3328 train_time:1024834ms step_avg:216.35ms step:4748/6200 train_loss:3.5138 train_time:1025047ms step_avg:216.35ms step:4749/6200 train_loss:3.3640 train_time:1025261ms step_avg:216.35ms step:4750/6200 train_loss:3.4608 train_time:1025726ms step_avg:216.40ms step:4750/6200 val_loss:3.3842 train_time:1025727ms step_avg:216.40ms step:4751/6200 train_loss:3.2673 train_time:1025945ms step_avg:216.40ms step:4752/6200 train_loss:3.1962 train_time:1026159ms step_avg:216.40ms step:4753/6200 train_loss:3.2812 train_time:1026372ms step_avg:216.40ms step:4754/6200 train_loss:3.4831 train_time:1026585ms step_avg:216.40ms step:4755/6200 train_loss:3.3629 train_time:1026799ms step_avg:216.40ms step:4756/6200 train_loss:3.6050 train_time:1027014ms step_avg:216.40ms step:4757/6200 train_loss:3.4669 train_time:1027228ms step_avg:216.40ms step:4758/6200 train_loss:3.3723 train_time:1027442ms step_avg:216.39ms step:4759/6200 train_loss:3.4245 train_time:1027655ms step_avg:216.39ms step:4760/6200 train_loss:3.4310 train_time:1027869ms step_avg:216.39ms step:4761/6200 train_loss:3.3582 train_time:1028082ms step_avg:216.39ms step:4762/6200 train_loss:3.3980 train_time:1028296ms step_avg:216.39ms step:4763/6200 train_loss:3.3645 train_time:1028509ms step_avg:216.39ms step:4764/6200 train_loss:3.2301 train_time:1028723ms step_avg:216.39ms step:4765/6200 train_loss:3.2426 train_time:1028937ms step_avg:216.39ms step:4766/6200 train_loss:3.2393 train_time:1029150ms step_avg:216.39ms step:4767/6200 train_loss:3.4806 train_time:1029363ms step_avg:216.39ms step:4768/6200 train_loss:3.7389 train_time:1029576ms step_avg:216.39ms step:4769/6200 train_loss:3.4473 train_time:1029790ms step_avg:216.39ms step:4770/6200 train_loss:3.3530 train_time:1030003ms step_avg:216.39ms step:4771/6200 train_loss:3.4162 train_time:1030218ms step_avg:216.39ms step:4772/6200 train_loss:3.3733 train_time:1030433ms step_avg:216.39ms step:4773/6200 train_loss:3.3536 train_time:1030647ms step_avg:216.39ms step:4774/6200 train_loss:3.5468 train_time:1030860ms step_avg:216.39ms step:4775/6200 train_loss:3.3450 train_time:1031074ms step_avg:216.38ms step:4776/6200 train_loss:3.4940 train_time:1031287ms step_avg:216.38ms step:4777/6200 train_loss:3.4060 train_time:1031501ms step_avg:216.38ms step:4778/6200 train_loss:3.2381 train_time:1031715ms step_avg:216.38ms step:4779/6200 train_loss:3.4200 train_time:1031928ms step_avg:216.38ms step:4780/6200 train_loss:3.3570 train_time:1032143ms step_avg:216.38ms step:4781/6200 train_loss:3.4295 train_time:1032357ms step_avg:216.38ms step:4782/6200 train_loss:3.3382 train_time:1032569ms step_avg:216.38ms step:4783/6200 train_loss:3.3041 train_time:1032783ms step_avg:216.38ms step:4784/6200 train_loss:3.3471 train_time:1032998ms step_avg:216.38ms step:4785/6200 train_loss:3.2752 train_time:1033212ms step_avg:216.38ms step:4786/6200 train_loss:3.6064 train_time:1033426ms step_avg:216.38ms step:4787/6200 train_loss:3.4940 train_time:1033641ms step_avg:216.38ms step:4788/6200 train_loss:3.4148 train_time:1033854ms step_avg:216.38ms step:4789/6200 train_loss:3.3969 train_time:1034067ms step_avg:216.38ms step:4790/6200 train_loss:3.3152 train_time:1034280ms step_avg:216.38ms step:4791/6200 train_loss:3.4235 train_time:1034493ms step_avg:216.38ms step:4792/6200 train_loss:3.4342 train_time:1034706ms step_avg:216.38ms step:4793/6200 train_loss:3.3490 train_time:1034920ms step_avg:216.37ms step:4794/6200 train_loss:3.4341 train_time:1035134ms step_avg:216.37ms step:4795/6200 train_loss:3.2648 train_time:1035348ms step_avg:216.37ms step:4796/6200 train_loss:3.4230 train_time:1035562ms step_avg:216.37ms step:4797/6200 train_loss:3.4850 train_time:1035775ms step_avg:216.37ms step:4798/6200 train_loss:3.1613 train_time:1035988ms step_avg:216.37ms step:4799/6200 train_loss:3.3284 train_time:1036203ms step_avg:216.37ms step:4800/6200 train_loss:3.3132 train_time:1036417ms step_avg:216.37ms step:4801/6200 train_loss:3.4036 train_time:1036630ms step_avg:216.37ms step:4802/6200 train_loss:3.2404 train_time:1036843ms step_avg:216.37ms step:4803/6200 train_loss:3.2790 train_time:1037056ms step_avg:216.37ms step:4804/6200 train_loss:3.4659 train_time:1037269ms step_avg:216.37ms step:4805/6200 train_loss:3.4139 train_time:1037483ms step_avg:216.37ms step:4806/6200 train_loss:3.4744 train_time:1037696ms step_avg:216.37ms step:4807/6200 train_loss:3.4967 train_time:1037910ms step_avg:216.37ms step:4808/6200 train_loss:3.2641 train_time:1038124ms step_avg:216.37ms step:4809/6200 train_loss:3.3838 train_time:1038340ms step_avg:216.37ms step:4810/6200 train_loss:3.3254 train_time:1038553ms step_avg:216.37ms step:4811/6200 train_loss:3.5563 train_time:1038766ms step_avg:216.36ms step:4812/6200 train_loss:3.3596 train_time:1038980ms step_avg:216.36ms step:4813/6200 train_loss:3.4079 train_time:1039193ms step_avg:216.36ms step:4814/6200 train_loss:3.2883 train_time:1039406ms step_avg:216.36ms step:4815/6200 train_loss:3.3365 train_time:1039622ms step_avg:216.36ms step:4816/6200 train_loss:3.7611 train_time:1039836ms step_avg:216.36ms step:4817/6200 train_loss:3.4505 train_time:1040049ms step_avg:216.36ms step:4818/6200 train_loss:3.3837 train_time:1040262ms step_avg:216.36ms step:4819/6200 train_loss:3.2307 train_time:1040474ms step_avg:216.36ms step:4820/6200 train_loss:3.3675 train_time:1040687ms step_avg:216.36ms step:4821/6200 train_loss:3.3743 train_time:1040902ms step_avg:216.36ms step:4822/6200 train_loss:3.4388 train_time:1041115ms step_avg:216.36ms step:4823/6200 train_loss:3.4752 train_time:1041329ms step_avg:216.36ms step:4824/6200 train_loss:3.3632 train_time:1041543ms step_avg:216.36ms step:4825/6200 train_loss:3.3546 train_time:1041757ms step_avg:216.36ms step:4826/6200 train_loss:3.2722 train_time:1041969ms step_avg:216.36ms step:4827/6200 train_loss:3.2402 train_time:1042182ms step_avg:216.36ms step:4828/6200 train_loss:3.4245 train_time:1042397ms step_avg:216.35ms step:4829/6200 train_loss:3.3065 train_time:1042610ms step_avg:216.35ms step:4830/6200 train_loss:3.4248 train_time:1042823ms step_avg:216.35ms step:4831/6200 train_loss:3.5822 train_time:1043039ms step_avg:216.35ms step:4832/6200 train_loss:3.3218 train_time:1043251ms step_avg:216.35ms step:4833/6200 train_loss:3.4001 train_time:1043464ms step_avg:216.35ms step:4834/6200 train_loss:3.3651 train_time:1043678ms step_avg:216.35ms step:4835/6200 train_loss:3.5552 train_time:1043891ms step_avg:216.35ms step:4836/6200 train_loss:3.3655 train_time:1044104ms step_avg:216.35ms step:4837/6200 train_loss:3.6168 train_time:1044318ms step_avg:216.35ms step:4838/6200 train_loss:3.5730 train_time:1044532ms step_avg:216.35ms step:4839/6200 train_loss:3.4041 train_time:1044745ms step_avg:216.35ms step:4840/6200 train_loss:3.4020 train_time:1044959ms step_avg:216.35ms step:4841/6200 train_loss:3.3820 train_time:1045172ms step_avg:216.35ms step:4842/6200 train_loss:3.4248 train_time:1045385ms step_avg:216.35ms step:4843/6200 train_loss:3.4143 train_time:1045601ms step_avg:216.35ms step:4844/6200 train_loss:3.2755 train_time:1045814ms step_avg:216.35ms step:4845/6200 train_loss:3.3052 train_time:1046028ms step_avg:216.35ms step:4846/6200 train_loss:3.2850 train_time:1046244ms step_avg:216.34ms step:4847/6200 train_loss:3.4384 train_time:1046457ms step_avg:216.34ms step:4848/6200 train_loss:3.3149 train_time:1046670ms step_avg:216.34ms step:4849/6200 train_loss:3.3485 train_time:1046882ms step_avg:216.34ms step:4850/6200 train_loss:3.4755 train_time:1047096ms step_avg:216.34ms step:4851/6200 train_loss:3.3672 train_time:1047310ms step_avg:216.34ms step:4852/6200 train_loss:3.1752 train_time:1047523ms step_avg:216.34ms step:4853/6200 train_loss:3.2642 train_time:1047738ms step_avg:216.34ms step:4854/6200 train_loss:3.4082 train_time:1047951ms step_avg:216.34ms step:4855/6200 train_loss:3.3577 train_time:1048163ms step_avg:216.34ms step:4856/6200 train_loss:3.4971 train_time:1048376ms step_avg:216.34ms step:4857/6200 train_loss:3.3335 train_time:1048589ms step_avg:216.34ms step:4858/6200 train_loss:3.3718 train_time:1048803ms step_avg:216.34ms step:4859/6200 train_loss:3.3235 train_time:1049017ms step_avg:216.34ms step:4860/6200 train_loss:3.4461 train_time:1049230ms step_avg:216.34ms step:4861/6200 train_loss:3.3160 train_time:1049443ms step_avg:216.34ms step:4862/6200 train_loss:3.3721 train_time:1049656ms step_avg:216.33ms step:4863/6200 train_loss:3.3791 train_time:1049869ms step_avg:216.33ms step:4864/6200 train_loss:3.3374 train_time:1050082ms step_avg:216.33ms step:4865/6200 train_loss:3.4183 train_time:1050295ms step_avg:216.33ms step:4866/6200 train_loss:3.0732 train_time:1050509ms step_avg:216.33ms step:4867/6200 train_loss:3.2868 train_time:1050722ms step_avg:216.33ms step:4868/6200 train_loss:3.3366 train_time:1050936ms step_avg:216.33ms step:4869/6200 train_loss:3.3622 train_time:1051149ms step_avg:216.33ms step:4870/6200 train_loss:3.3638 train_time:1051361ms step_avg:216.33ms step:4871/6200 train_loss:3.3739 train_time:1051575ms step_avg:216.33ms step:4872/6200 train_loss:3.4821 train_time:1051788ms step_avg:216.33ms step:4873/6200 train_loss:3.4765 train_time:1052002ms step_avg:216.33ms step:4874/6200 train_loss:3.4936 train_time:1052216ms step_avg:216.33ms step:4875/6200 train_loss:3.5788 train_time:1052429ms step_avg:216.33ms step:4875/6200 val_loss:3.3724 train_time:1052431ms step_avg:216.33ms step:4876/6200 train_loss:3.3950 train_time:1052650ms step_avg:216.33ms step:4877/6200 train_loss:3.3066 train_time:1052865ms step_avg:216.33ms step:4878/6200 train_loss:3.2686 train_time:1053078ms step_avg:216.33ms step:4879/6200 train_loss:3.3196 train_time:1053291ms step_avg:216.33ms step:4880/6200 train_loss:3.4569 train_time:1053505ms step_avg:216.33ms step:4881/6200 train_loss:3.2958 train_time:1053719ms step_avg:216.32ms step:4882/6200 train_loss:3.4214 train_time:1053932ms step_avg:216.32ms step:4883/6200 train_loss:3.4319 train_time:1054148ms step_avg:216.32ms step:4884/6200 train_loss:3.3374 train_time:1054363ms step_avg:216.32ms step:4885/6200 train_loss:3.3418 train_time:1054577ms step_avg:216.32ms step:4886/6200 train_loss:3.4428 train_time:1054789ms step_avg:216.32ms step:4887/6200 train_loss:3.4677 train_time:1055003ms step_avg:216.32ms step:4888/6200 train_loss:3.3478 train_time:1055217ms step_avg:216.32ms step:4889/6200 train_loss:3.3074 train_time:1055430ms step_avg:216.32ms step:4890/6200 train_loss:3.3993 train_time:1055644ms step_avg:216.32ms step:4891/6200 train_loss:3.3106 train_time:1055858ms step_avg:216.32ms step:4892/6200 train_loss:3.4059 train_time:1056071ms step_avg:216.32ms step:4893/6200 train_loss:3.3970 train_time:1056283ms step_avg:216.32ms step:4894/6200 train_loss:3.4268 train_time:1056496ms step_avg:216.32ms step:4895/6200 train_loss:3.5057 train_time:1056710ms step_avg:216.32ms step:4896/6200 train_loss:3.3919 train_time:1056923ms step_avg:216.32ms step:4897/6200 train_loss:3.3517 train_time:1057137ms step_avg:216.32ms step:4898/6200 train_loss:3.5360 train_time:1057351ms step_avg:216.32ms step:4899/6200 train_loss:3.2967 train_time:1057564ms step_avg:216.32ms step:4900/6200 train_loss:3.3519 train_time:1057778ms step_avg:216.31ms step:4901/6200 train_loss:3.2647 train_time:1057991ms step_avg:216.31ms step:4902/6200 train_loss:3.2311 train_time:1058204ms step_avg:216.31ms step:4903/6200 train_loss:3.3684 train_time:1058418ms step_avg:216.31ms step:4904/6200 train_loss:3.3127 train_time:1058631ms step_avg:216.31ms step:4905/6200 train_loss:3.3892 train_time:1058844ms step_avg:216.31ms step:4906/6200 train_loss:3.4182 train_time:1059059ms step_avg:216.31ms step:4907/6200 train_loss:3.3093 train_time:1059271ms step_avg:216.31ms step:4908/6200 train_loss:3.3853 train_time:1059484ms step_avg:216.31ms step:4909/6200 train_loss:3.2952 train_time:1059697ms step_avg:216.31ms step:4910/6200 train_loss:3.4061 train_time:1059910ms step_avg:216.31ms step:4911/6200 train_loss:3.4387 train_time:1060124ms step_avg:216.31ms step:4912/6200 train_loss:3.3516 train_time:1060338ms step_avg:216.31ms step:4913/6200 train_loss:3.3193 train_time:1060553ms step_avg:216.31ms step:4914/6200 train_loss:3.3132 train_time:1061022ms step_avg:216.36ms step:4915/6200 train_loss:3.2476 train_time:1061236ms step_avg:216.36ms step:4916/6200 train_loss:3.4435 train_time:1061450ms step_avg:216.36ms step:4917/6200 train_loss:3.4202 train_time:1061664ms step_avg:216.36ms step:4918/6200 train_loss:3.3370 train_time:1061876ms step_avg:216.36ms step:4919/6200 train_loss:3.3568 train_time:1062089ms step_avg:216.36ms step:4920/6200 train_loss:3.3609 train_time:1062303ms step_avg:216.35ms step:4921/6200 train_loss:3.4323 train_time:1062516ms step_avg:216.35ms step:4922/6200 train_loss:3.5943 train_time:1062729ms step_avg:216.35ms step:4923/6200 train_loss:3.4534 train_time:1062943ms step_avg:216.35ms step:4924/6200 train_loss:3.3214 train_time:1063156ms step_avg:216.35ms step:4925/6200 train_loss:3.6267 train_time:1063370ms step_avg:216.35ms step:4926/6200 train_loss:3.3702 train_time:1063584ms step_avg:216.35ms step:4927/6200 train_loss:3.3455 train_time:1063797ms step_avg:216.35ms step:4928/6200 train_loss:3.2718 train_time:1064010ms step_avg:216.35ms step:4929/6200 train_loss:3.2906 train_time:1064224ms step_avg:216.35ms step:4930/6200 train_loss:3.4262 train_time:1064438ms step_avg:216.35ms step:4931/6200 train_loss:3.6655 train_time:1064652ms step_avg:216.35ms step:4932/6200 train_loss:3.2767 train_time:1064864ms step_avg:216.35ms step:4933/6200 train_loss:3.3694 train_time:1065078ms step_avg:216.35ms step:4934/6200 train_loss:3.4368 train_time:1065291ms step_avg:216.35ms step:4935/6200 train_loss:3.2329 train_time:1065504ms step_avg:216.35ms step:4936/6200 train_loss:3.3768 train_time:1065721ms step_avg:216.35ms step:4937/6200 train_loss:3.4339 train_time:1065935ms step_avg:216.35ms step:4938/6200 train_loss:3.4235 train_time:1066148ms step_avg:216.35ms step:4939/6200 train_loss:3.4141 train_time:1066363ms step_avg:216.34ms step:4940/6200 train_loss:3.5313 train_time:1066828ms step_avg:216.40ms step:4941/6200 train_loss:3.3712 train_time:1067042ms step_avg:216.39ms step:4942/6200 train_loss:3.3808 train_time:1067256ms step_avg:216.39ms step:4943/6200 train_loss:3.1325 train_time:1067473ms step_avg:216.39ms step:4944/6200 train_loss:3.6132 train_time:1067685ms step_avg:216.39ms step:4945/6200 train_loss:3.5670 train_time:1067898ms step_avg:216.39ms step:4946/6200 train_loss:3.2001 train_time:1068112ms step_avg:216.39ms step:4947/6200 train_loss:3.4636 train_time:1068324ms step_avg:216.39ms step:4948/6200 train_loss:3.4758 train_time:1068539ms step_avg:216.39ms step:4949/6200 train_loss:3.3104 train_time:1068752ms step_avg:216.39ms step:4950/6200 train_loss:3.4365 train_time:1068966ms step_avg:216.39ms step:4951/6200 train_loss:3.2917 train_time:1069180ms step_avg:216.39ms step:4952/6200 train_loss:3.4191 train_time:1069392ms step_avg:216.39ms step:4953/6200 train_loss:3.3864 train_time:1069605ms step_avg:216.39ms step:4954/6200 train_loss:3.2653 train_time:1069820ms step_avg:216.39ms step:4955/6200 train_loss:3.4123 train_time:1070033ms step_avg:216.39ms step:4956/6200 train_loss:3.2381 train_time:1070247ms step_avg:216.39ms step:4957/6200 train_loss:3.3414 train_time:1070462ms step_avg:216.39ms step:4958/6200 train_loss:3.3145 train_time:1070675ms step_avg:216.39ms step:4959/6200 train_loss:3.3367 train_time:1070888ms step_avg:216.38ms step:4960/6200 train_loss:3.3707 train_time:1071101ms step_avg:216.38ms step:4961/6200 train_loss:3.5180 train_time:1071314ms step_avg:216.38ms step:4962/6200 train_loss:3.2839 train_time:1071527ms step_avg:216.38ms step:4963/6200 train_loss:3.4192 train_time:1071749ms step_avg:216.38ms step:4964/6200 train_loss:3.2594 train_time:1071962ms step_avg:216.38ms step:4965/6200 train_loss:3.9783 train_time:1072176ms step_avg:216.38ms step:4966/6200 train_loss:3.2623 train_time:1072390ms step_avg:216.38ms step:4967/6200 train_loss:3.3908 train_time:1072603ms step_avg:216.38ms step:4968/6200 train_loss:3.2172 train_time:1072816ms step_avg:216.38ms step:4969/6200 train_loss:3.9203 train_time:1073029ms step_avg:216.38ms step:4970/6200 train_loss:3.4641 train_time:1073244ms step_avg:216.38ms step:4971/6200 train_loss:3.3768 train_time:1073458ms step_avg:216.38ms step:4972/6200 train_loss:3.3116 train_time:1073672ms step_avg:216.38ms step:4973/6200 train_loss:3.4012 train_time:1073883ms step_avg:216.38ms step:4974/6200 train_loss:3.2880 train_time:1074097ms step_avg:216.38ms step:4975/6200 train_loss:3.2805 train_time:1074311ms step_avg:216.38ms step:4976/6200 train_loss:3.4233 train_time:1074524ms step_avg:216.38ms step:4977/6200 train_loss:3.3571 train_time:1074741ms step_avg:216.38ms step:4978/6200 train_loss:3.3138 train_time:1074954ms step_avg:216.38ms step:4979/6200 train_loss:3.3609 train_time:1075166ms step_avg:216.37ms step:4980/6200 train_loss:3.3050 train_time:1075383ms step_avg:216.37ms step:4981/6200 train_loss:3.4466 train_time:1075596ms step_avg:216.37ms step:4982/6200 train_loss:3.4161 train_time:1075809ms step_avg:216.37ms step:4983/6200 train_loss:3.2128 train_time:1076023ms step_avg:216.37ms step:4984/6200 train_loss:3.2424 train_time:1076237ms step_avg:216.37ms step:4985/6200 train_loss:3.5221 train_time:1076450ms step_avg:216.37ms step:4986/6200 train_loss:3.4185 train_time:1076665ms step_avg:216.37ms step:4987/6200 train_loss:3.3319 train_time:1076879ms step_avg:216.37ms step:4988/6200 train_loss:3.3641 train_time:1077091ms step_avg:216.37ms step:4989/6200 train_loss:3.3456 train_time:1077304ms step_avg:216.37ms step:4990/6200 train_loss:3.3325 train_time:1077517ms step_avg:216.37ms step:4991/6200 train_loss:3.3842 train_time:1077731ms step_avg:216.37ms step:4992/6200 train_loss:3.4186 train_time:1077945ms step_avg:216.37ms step:4993/6200 train_loss:3.2482 train_time:1078160ms step_avg:216.37ms step:4994/6200 train_loss:3.3820 train_time:1078374ms step_avg:216.37ms step:4995/6200 train_loss:3.3056 train_time:1078589ms step_avg:216.37ms step:4996/6200 train_loss:3.4454 train_time:1078803ms step_avg:216.37ms step:4997/6200 train_loss:3.3258 train_time:1079016ms step_avg:216.37ms step:4998/6200 train_loss:3.4801 train_time:1079230ms step_avg:216.37ms step:4999/6200 train_loss:3.3481 train_time:1079444ms step_avg:216.36ms step:5000/6200 train_loss:3.4728 train_time:1079658ms step_avg:216.36ms step:5000/6200 val_loss:3.3608 train_time:1079660ms step_avg:216.36ms step:5001/6200 train_loss:3.3870 train_time:1079876ms step_avg:216.36ms step:5002/6200 train_loss:3.3964 train_time:1080090ms step_avg:216.36ms step:5003/6200 train_loss:3.2779 train_time:1080303ms step_avg:216.36ms step:5004/6200 train_loss:3.3512 train_time:1080516ms step_avg:216.36ms step:5005/6200 train_loss:3.3673 train_time:1080729ms step_avg:216.36ms step:5006/6200 train_loss:3.2403 train_time:1080941ms step_avg:216.36ms step:5007/6200 train_loss:3.4788 train_time:1081156ms step_avg:216.36ms step:5008/6200 train_loss:3.3194 train_time:1081369ms step_avg:216.36ms step:5009/6200 train_loss:3.3537 train_time:1081583ms step_avg:216.36ms step:5010/6200 train_loss:3.3203 train_time:1081796ms step_avg:216.36ms step:5011/6200 train_loss:3.5238 train_time:1082008ms step_avg:216.36ms step:5012/6200 train_loss:3.3248 train_time:1082222ms step_avg:216.36ms step:5013/6200 train_loss:3.3085 train_time:1082437ms step_avg:216.36ms step:5014/6200 train_loss:3.2738 train_time:1082651ms step_avg:216.36ms step:5015/6200 train_loss:3.3661 train_time:1082866ms step_avg:216.36ms step:5016/6200 train_loss:3.3518 train_time:1083079ms step_avg:216.36ms step:5017/6200 train_loss:3.3865 train_time:1083293ms step_avg:216.36ms step:5018/6200 train_loss:3.4056 train_time:1083506ms step_avg:216.36ms step:5019/6200 train_loss:3.3665 train_time:1083720ms step_avg:216.35ms step:5020/6200 train_loss:3.8743 train_time:1083933ms step_avg:216.35ms step:5021/6200 train_loss:3.3114 train_time:1084147ms step_avg:216.35ms step:5022/6200 train_loss:3.4154 train_time:1084360ms step_avg:216.35ms step:5023/6200 train_loss:3.3477 train_time:1084575ms step_avg:216.35ms step:5024/6200 train_loss:3.4826 train_time:1084788ms step_avg:216.35ms step:5025/6200 train_loss:3.2849 train_time:1085000ms step_avg:216.35ms step:5026/6200 train_loss:3.4408 train_time:1085214ms step_avg:216.35ms step:5027/6200 train_loss:3.2919 train_time:1085428ms step_avg:216.35ms step:5028/6200 train_loss:3.4986 train_time:1085640ms step_avg:216.35ms step:5029/6200 train_loss:3.4097 train_time:1085856ms step_avg:216.35ms step:5030/6200 train_loss:3.4381 train_time:1086070ms step_avg:216.35ms step:5031/6200 train_loss:3.2929 train_time:1086282ms step_avg:216.35ms step:5032/6200 train_loss:3.3360 train_time:1086496ms step_avg:216.35ms step:5033/6200 train_loss:3.2745 train_time:1086710ms step_avg:216.35ms step:5034/6200 train_loss:3.4659 train_time:1086923ms step_avg:216.35ms step:5035/6200 train_loss:3.4536 train_time:1087136ms step_avg:216.35ms step:5036/6200 train_loss:3.3077 train_time:1087351ms step_avg:216.35ms step:5037/6200 train_loss:3.2350 train_time:1087563ms step_avg:216.34ms step:5038/6200 train_loss:3.2743 train_time:1087778ms step_avg:216.34ms step:5039/6200 train_loss:3.4055 train_time:1087992ms step_avg:216.34ms step:5040/6200 train_loss:3.3362 train_time:1088204ms step_avg:216.34ms step:5041/6200 train_loss:3.5211 train_time:1088417ms step_avg:216.34ms step:5042/6200 train_loss:3.3106 train_time:1088631ms step_avg:216.34ms step:5043/6200 train_loss:3.4931 train_time:1088844ms step_avg:216.34ms step:5044/6200 train_loss:3.4098 train_time:1089059ms step_avg:216.34ms step:5045/6200 train_loss:3.4594 train_time:1089274ms step_avg:216.34ms step:5046/6200 train_loss:3.2930 train_time:1089487ms step_avg:216.34ms step:5047/6200 train_loss:3.4273 train_time:1089699ms step_avg:216.34ms step:5048/6200 train_loss:3.1756 train_time:1089912ms step_avg:216.34ms step:5049/6200 train_loss:3.3387 train_time:1090125ms step_avg:216.34ms step:5050/6200 train_loss:3.3454 train_time:1090339ms step_avg:216.34ms step:5051/6200 train_loss:3.2822 train_time:1090553ms step_avg:216.34ms step:5052/6200 train_loss:3.3266 train_time:1090767ms step_avg:216.34ms step:5053/6200 train_loss:3.3739 train_time:1090980ms step_avg:216.34ms step:5054/6200 train_loss:3.4170 train_time:1091193ms step_avg:216.33ms step:5055/6200 train_loss:3.5021 train_time:1091407ms step_avg:216.33ms step:5056/6200 train_loss:3.4297 train_time:1091621ms step_avg:216.33ms step:5057/6200 train_loss:3.3188 train_time:1091836ms step_avg:216.33ms step:5058/6200 train_loss:3.2114 train_time:1092048ms step_avg:216.33ms step:5059/6200 train_loss:3.1303 train_time:1092261ms step_avg:216.33ms step:5060/6200 train_loss:3.3576 train_time:1092476ms step_avg:216.33ms step:5061/6200 train_loss:3.4481 train_time:1092689ms step_avg:216.33ms step:5062/6200 train_loss:3.3649 train_time:1092901ms step_avg:216.33ms step:5063/6200 train_loss:3.4916 train_time:1093115ms step_avg:216.33ms step:5064/6200 train_loss:3.4933 train_time:1093328ms step_avg:216.33ms step:5065/6200 train_loss:3.3389 train_time:1093540ms step_avg:216.33ms step:5066/6200 train_loss:3.4572 train_time:1093755ms step_avg:216.33ms step:5067/6200 train_loss:3.6557 train_time:1093969ms step_avg:216.33ms step:5068/6200 train_loss:3.3125 train_time:1094181ms step_avg:216.33ms step:5069/6200 train_loss:3.6466 train_time:1094395ms step_avg:216.33ms step:5070/6200 train_loss:3.3658 train_time:1094608ms step_avg:216.33ms step:5071/6200 train_loss:3.7778 train_time:1094821ms step_avg:216.33ms step:5072/6200 train_loss:3.3086 train_time:1095035ms step_avg:216.32ms step:5073/6200 train_loss:3.3722 train_time:1095248ms step_avg:216.32ms step:5074/6200 train_loss:3.4967 train_time:1095462ms step_avg:216.32ms step:5075/6200 train_loss:3.3423 train_time:1095677ms step_avg:216.32ms step:5076/6200 train_loss:3.3258 train_time:1095891ms step_avg:216.32ms step:5077/6200 train_loss:3.2980 train_time:1096104ms step_avg:216.32ms step:5078/6200 train_loss:3.3785 train_time:1096317ms step_avg:216.32ms step:5079/6200 train_loss:3.5162 train_time:1096532ms step_avg:216.32ms step:5080/6200 train_loss:3.4892 train_time:1096746ms step_avg:216.32ms step:5081/6200 train_loss:3.3086 train_time:1096960ms step_avg:216.32ms step:5082/6200 train_loss:3.4386 train_time:1097174ms step_avg:216.32ms step:5083/6200 train_loss:3.2973 train_time:1097387ms step_avg:216.32ms step:5084/6200 train_loss:3.3788 train_time:1097599ms step_avg:216.32ms step:5085/6200 train_loss:3.2665 train_time:1097812ms step_avg:216.32ms step:5086/6200 train_loss:4.1082 train_time:1098026ms step_avg:216.32ms step:5087/6200 train_loss:3.4070 train_time:1098239ms step_avg:216.32ms step:5088/6200 train_loss:3.3233 train_time:1098455ms step_avg:216.32ms step:5089/6200 train_loss:3.3135 train_time:1098668ms step_avg:216.32ms step:5090/6200 train_loss:3.4671 train_time:1098881ms step_avg:216.32ms step:5091/6200 train_loss:3.3941 train_time:1099097ms step_avg:216.32ms step:5092/6200 train_loss:3.2888 train_time:1099310ms step_avg:216.31ms step:5093/6200 train_loss:3.3158 train_time:1099523ms step_avg:216.31ms step:5094/6200 train_loss:3.3060 train_time:1099737ms step_avg:216.31ms step:5095/6200 train_loss:3.2314 train_time:1099951ms step_avg:216.31ms step:5096/6200 train_loss:3.3588 train_time:1100164ms step_avg:216.31ms step:5097/6200 train_loss:3.1453 train_time:1100378ms step_avg:216.31ms step:5098/6200 train_loss:3.4326 train_time:1100592ms step_avg:216.31ms step:5099/6200 train_loss:3.3020 train_time:1100805ms step_avg:216.31ms step:5100/6200 train_loss:3.3462 train_time:1101019ms step_avg:216.31ms step:5101/6200 train_loss:3.3266 train_time:1101233ms step_avg:216.31ms step:5102/6200 train_loss:3.2226 train_time:1101446ms step_avg:216.31ms step:5103/6200 train_loss:3.3703 train_time:1101914ms step_avg:216.36ms step:5104/6200 train_loss:3.4110 train_time:1102127ms step_avg:216.36ms step:5105/6200 train_loss:3.4118 train_time:1102340ms step_avg:216.36ms step:5106/6200 train_loss:3.2975 train_time:1102555ms step_avg:216.36ms step:5107/6200 train_loss:3.3961 train_time:1102769ms step_avg:216.36ms step:5108/6200 train_loss:3.4441 train_time:1102981ms step_avg:216.36ms step:5109/6200 train_loss:3.3414 train_time:1103195ms step_avg:216.36ms step:5110/6200 train_loss:3.3803 train_time:1103407ms step_avg:216.35ms step:5111/6200 train_loss:3.3929 train_time:1103621ms step_avg:216.35ms step:5112/6200 train_loss:3.3649 train_time:1103836ms step_avg:216.35ms step:5113/6200 train_loss:3.4297 train_time:1104049ms step_avg:216.35ms step:5114/6200 train_loss:3.2961 train_time:1104262ms step_avg:216.35ms step:5115/6200 train_loss:3.4739 train_time:1104477ms step_avg:216.35ms step:5116/6200 train_loss:3.2557 train_time:1104691ms step_avg:216.35ms step:5117/6200 train_loss:3.4926 train_time:1104903ms step_avg:216.35ms step:5118/6200 train_loss:3.3524 train_time:1105118ms step_avg:216.35ms step:5119/6200 train_loss:3.3567 train_time:1105332ms step_avg:216.35ms step:5120/6200 train_loss:3.3586 train_time:1105545ms step_avg:216.35ms step:5121/6200 train_loss:3.5670 train_time:1105759ms step_avg:216.35ms step:5122/6200 train_loss:3.4022 train_time:1105973ms step_avg:216.35ms step:5123/6200 train_loss:3.3498 train_time:1106187ms step_avg:216.35ms step:5124/6200 train_loss:3.4096 train_time:1106399ms step_avg:216.35ms step:5125/6200 train_loss:3.3406 train_time:1106612ms step_avg:216.35ms step:5125/6200 val_loss:3.3505 train_time:1106614ms step_avg:216.35ms step:5126/6200 train_loss:3.3903 train_time:1106831ms step_avg:216.35ms step:5127/6200 train_loss:3.2989 train_time:1107044ms step_avg:216.35ms step:5128/6200 train_loss:3.5375 train_time:1107258ms step_avg:216.35ms step:5129/6200 train_loss:3.3025 train_time:1107472ms step_avg:216.35ms step:5130/6200 train_loss:3.3104 train_time:1107937ms step_avg:216.39ms step:5131/6200 train_loss:3.3213 train_time:1108151ms step_avg:216.39ms step:5132/6200 train_loss:3.2259 train_time:1108365ms step_avg:216.39ms step:5133/6200 train_loss:3.1767 train_time:1108578ms step_avg:216.39ms step:5134/6200 train_loss:3.4199 train_time:1108794ms step_avg:216.39ms step:5135/6200 train_loss:3.3091 train_time:1109007ms step_avg:216.39ms step:5136/6200 train_loss:3.3181 train_time:1109219ms step_avg:216.39ms step:5137/6200 train_loss:3.2877 train_time:1109433ms step_avg:216.39ms step:5138/6200 train_loss:3.4543 train_time:1109646ms step_avg:216.39ms step:5139/6200 train_loss:3.3201 train_time:1109860ms step_avg:216.39ms step:5140/6200 train_loss:3.4688 train_time:1110075ms step_avg:216.39ms step:5141/6200 train_loss:3.2595 train_time:1110288ms step_avg:216.39ms step:5142/6200 train_loss:3.3769 train_time:1110502ms step_avg:216.39ms step:5143/6200 train_loss:3.3107 train_time:1110713ms step_avg:216.39ms step:5144/6200 train_loss:3.9065 train_time:1110927ms step_avg:216.39ms step:5145/6200 train_loss:3.6412 train_time:1111141ms step_avg:216.39ms step:5146/6200 train_loss:3.3505 train_time:1111355ms step_avg:216.39ms step:5147/6200 train_loss:3.2640 train_time:1111569ms step_avg:216.38ms step:5148/6200 train_loss:3.3223 train_time:1111782ms step_avg:216.38ms step:5149/6200 train_loss:3.5854 train_time:1111995ms step_avg:216.38ms step:5150/6200 train_loss:3.2456 train_time:1112209ms step_avg:216.38ms step:5151/6200 train_loss:4.0264 train_time:1112421ms step_avg:216.38ms step:5152/6200 train_loss:3.3907 train_time:1112633ms step_avg:216.38ms step:5153/6200 train_loss:3.3724 train_time:1112847ms step_avg:216.38ms step:5154/6200 train_loss:3.4064 train_time:1113060ms step_avg:216.38ms step:5155/6200 train_loss:3.3592 train_time:1113275ms step_avg:216.38ms step:5156/6200 train_loss:3.2963 train_time:1113489ms step_avg:216.38ms step:5157/6200 train_loss:3.3246 train_time:1113703ms step_avg:216.38ms step:5158/6200 train_loss:3.3489 train_time:1113917ms step_avg:216.38ms step:5159/6200 train_loss:3.2547 train_time:1114130ms step_avg:216.38ms step:5160/6200 train_loss:3.4264 train_time:1114343ms step_avg:216.38ms step:5161/6200 train_loss:3.3430 train_time:1114557ms step_avg:216.38ms step:5162/6200 train_loss:3.4837 train_time:1114769ms step_avg:216.38ms step:5163/6200 train_loss:3.2277 train_time:1114982ms step_avg:216.38ms step:5164/6200 train_loss:3.5715 train_time:1115195ms step_avg:216.37ms step:5165/6200 train_loss:3.3609 train_time:1115408ms step_avg:216.37ms step:5166/6200 train_loss:3.3306 train_time:1115622ms step_avg:216.37ms step:5167/6200 train_loss:3.3742 train_time:1115834ms step_avg:216.37ms step:5168/6200 train_loss:3.2776 train_time:1116048ms step_avg:216.37ms step:5169/6200 train_loss:3.2831 train_time:1116261ms step_avg:216.37ms step:5170/6200 train_loss:3.3336 train_time:1116475ms step_avg:216.37ms step:5171/6200 train_loss:3.3608 train_time:1116691ms step_avg:216.37ms step:5172/6200 train_loss:3.4598 train_time:1116903ms step_avg:216.37ms step:5173/6200 train_loss:3.4081 train_time:1117115ms step_avg:216.37ms step:5174/6200 train_loss:3.3819 train_time:1117332ms step_avg:216.37ms step:5175/6200 train_loss:3.3487 train_time:1117546ms step_avg:216.37ms step:5176/6200 train_loss:3.3632 train_time:1117760ms step_avg:216.37ms step:5177/6200 train_loss:3.3272 train_time:1117973ms step_avg:216.37ms step:5178/6200 train_loss:3.3188 train_time:1118188ms step_avg:216.37ms step:5179/6200 train_loss:3.3822 train_time:1118401ms step_avg:216.37ms step:5180/6200 train_loss:3.4313 train_time:1118613ms step_avg:216.37ms step:5181/6200 train_loss:3.3245 train_time:1118826ms step_avg:216.37ms step:5182/6200 train_loss:3.2994 train_time:1119039ms step_avg:216.36ms step:5183/6200 train_loss:3.3619 train_time:1119254ms step_avg:216.36ms step:5184/6200 train_loss:3.3450 train_time:1119468ms step_avg:216.36ms step:5185/6200 train_loss:3.2891 train_time:1119683ms step_avg:216.36ms step:5186/6200 train_loss:3.3442 train_time:1119896ms step_avg:216.36ms step:5187/6200 train_loss:3.3764 train_time:1120110ms step_avg:216.36ms step:5188/6200 train_loss:3.3421 train_time:1120322ms step_avg:216.36ms step:5189/6200 train_loss:3.4798 train_time:1120534ms step_avg:216.36ms step:5190/6200 train_loss:3.2809 train_time:1120749ms step_avg:216.36ms step:5191/6200 train_loss:3.3364 train_time:1120962ms step_avg:216.36ms step:5192/6200 train_loss:3.4271 train_time:1121175ms step_avg:216.36ms step:5193/6200 train_loss:3.4256 train_time:1121390ms step_avg:216.36ms step:5194/6200 train_loss:3.3029 train_time:1121603ms step_avg:216.36ms step:5195/6200 train_loss:3.4077 train_time:1121816ms step_avg:216.36ms step:5196/6200 train_loss:3.3734 train_time:1122031ms step_avg:216.36ms step:5197/6200 train_loss:3.3394 train_time:1122244ms step_avg:216.36ms step:5198/6200 train_loss:3.5041 train_time:1122458ms step_avg:216.36ms step:5199/6200 train_loss:3.3617 train_time:1122673ms step_avg:216.36ms step:5200/6200 train_loss:3.3465 train_time:1122887ms step_avg:216.36ms step:5201/6200 train_loss:3.2874 train_time:1123100ms step_avg:216.36ms step:5202/6200 train_loss:3.2790 train_time:1123313ms step_avg:216.35ms step:5203/6200 train_loss:3.1188 train_time:1123526ms step_avg:216.35ms step:5204/6200 train_loss:3.3352 train_time:1123740ms step_avg:216.35ms step:5205/6200 train_loss:3.1867 train_time:1123954ms step_avg:216.35ms step:5206/6200 train_loss:3.1958 train_time:1124168ms step_avg:216.35ms step:5207/6200 train_loss:3.4985 train_time:1124382ms step_avg:216.35ms step:5208/6200 train_loss:3.2992 train_time:1124596ms step_avg:216.35ms step:5209/6200 train_loss:3.6000 train_time:1124809ms step_avg:216.35ms step:5210/6200 train_loss:3.3899 train_time:1125022ms step_avg:216.35ms step:5211/6200 train_loss:3.4183 train_time:1125233ms step_avg:216.35ms step:5212/6200 train_loss:3.3438 train_time:1125447ms step_avg:216.35ms step:5213/6200 train_loss:3.2271 train_time:1125662ms step_avg:216.35ms step:5214/6200 train_loss:3.3811 train_time:1125877ms step_avg:216.35ms step:5215/6200 train_loss:3.2670 train_time:1126092ms step_avg:216.35ms step:5216/6200 train_loss:3.6245 train_time:1126305ms step_avg:216.35ms step:5217/6200 train_loss:3.3448 train_time:1126517ms step_avg:216.35ms step:5218/6200 train_loss:3.4102 train_time:1126731ms step_avg:216.35ms step:5219/6200 train_loss:3.3202 train_time:1126943ms step_avg:216.35ms step:5220/6200 train_loss:3.1781 train_time:1127156ms step_avg:216.34ms step:5221/6200 train_loss:3.5224 train_time:1127370ms step_avg:216.34ms step:5222/6200 train_loss:3.2388 train_time:1127583ms step_avg:216.34ms step:5223/6200 train_loss:3.6673 train_time:1127796ms step_avg:216.34ms step:5224/6200 train_loss:3.3279 train_time:1128010ms step_avg:216.34ms step:5225/6200 train_loss:3.3396 train_time:1128222ms step_avg:216.34ms step:5226/6200 train_loss:3.2731 train_time:1128435ms step_avg:216.34ms step:5227/6200 train_loss:3.3742 train_time:1128648ms step_avg:216.34ms step:5228/6200 train_loss:3.3650 train_time:1128861ms step_avg:216.34ms step:5229/6200 train_loss:3.2539 train_time:1129075ms step_avg:216.34ms step:5230/6200 train_loss:3.3807 train_time:1129290ms step_avg:216.34ms step:5231/6200 train_loss:3.4343 train_time:1129503ms step_avg:216.34ms step:5232/6200 train_loss:3.2561 train_time:1129715ms step_avg:216.34ms step:5233/6200 train_loss:3.2917 train_time:1129929ms step_avg:216.34ms step:5234/6200 train_loss:3.3209 train_time:1130142ms step_avg:216.34ms step:5235/6200 train_loss:3.5589 train_time:1130356ms step_avg:216.34ms step:5236/6200 train_loss:3.3850 train_time:1130570ms step_avg:216.34ms step:5237/6200 train_loss:3.3411 train_time:1130783ms step_avg:216.34ms step:5238/6200 train_loss:3.2786 train_time:1130996ms step_avg:216.33ms step:5239/6200 train_loss:3.5373 train_time:1131210ms step_avg:216.33ms step:5240/6200 train_loss:3.3061 train_time:1131422ms step_avg:216.33ms step:5241/6200 train_loss:3.3819 train_time:1131636ms step_avg:216.33ms step:5242/6200 train_loss:3.2943 train_time:1131850ms step_avg:216.33ms step:5243/6200 train_loss:3.2523 train_time:1132062ms step_avg:216.33ms step:5244/6200 train_loss:3.3269 train_time:1132276ms step_avg:216.33ms step:5245/6200 train_loss:3.3686 train_time:1132491ms step_avg:216.33ms step:5246/6200 train_loss:3.3321 train_time:1132704ms step_avg:216.33ms step:5247/6200 train_loss:3.2855 train_time:1132916ms step_avg:216.33ms step:5248/6200 train_loss:3.1397 train_time:1133129ms step_avg:216.33ms step:5249/6200 train_loss:3.5133 train_time:1133342ms step_avg:216.33ms step:5250/6200 train_loss:3.3211 train_time:1133556ms step_avg:216.33ms step:5250/6200 val_loss:3.3392 train_time:1133557ms step_avg:216.33ms step:5251/6200 train_loss:3.3254 train_time:1133772ms step_avg:216.33ms step:5252/6200 train_loss:3.2625 train_time:1133986ms step_avg:216.33ms step:5253/6200 train_loss:3.4492 train_time:1134202ms step_avg:216.33ms step:5254/6200 train_loss:3.3401 train_time:1134416ms step_avg:216.33ms step:5255/6200 train_loss:3.2123 train_time:1134630ms step_avg:216.33ms step:5256/6200 train_loss:3.4404 train_time:1134844ms step_avg:216.33ms step:5257/6200 train_loss:3.3827 train_time:1135058ms step_avg:216.33ms step:5258/6200 train_loss:3.2175 train_time:1135273ms step_avg:216.32ms step:5259/6200 train_loss:3.3694 train_time:1135487ms step_avg:216.32ms step:5260/6200 train_loss:3.2280 train_time:1135703ms step_avg:216.32ms step:5261/6200 train_loss:3.4337 train_time:1135916ms step_avg:216.32ms step:5262/6200 train_loss:3.2781 train_time:1136128ms step_avg:216.32ms step:5263/6200 train_loss:3.3099 train_time:1136342ms step_avg:216.32ms step:5264/6200 train_loss:3.3087 train_time:1136555ms step_avg:216.32ms step:5265/6200 train_loss:3.3432 train_time:1136768ms step_avg:216.32ms step:5266/6200 train_loss:3.3268 train_time:1136984ms step_avg:216.32ms step:5267/6200 train_loss:3.3537 train_time:1137198ms step_avg:216.32ms step:5268/6200 train_loss:3.2641 train_time:1137411ms step_avg:216.32ms step:5269/6200 train_loss:3.3923 train_time:1137624ms step_avg:216.32ms step:5270/6200 train_loss:3.2798 train_time:1137836ms step_avg:216.32ms step:5271/6200 train_loss:3.3867 train_time:1138051ms step_avg:216.32ms step:5272/6200 train_loss:3.4066 train_time:1138265ms step_avg:216.32ms step:5273/6200 train_loss:3.2585 train_time:1138479ms step_avg:216.32ms step:5274/6200 train_loss:3.3221 train_time:1138692ms step_avg:216.32ms step:5275/6200 train_loss:3.3982 train_time:1138907ms step_avg:216.32ms step:5276/6200 train_loss:3.5063 train_time:1139121ms step_avg:216.32ms step:5277/6200 train_loss:3.3451 train_time:1139333ms step_avg:216.32ms step:5278/6200 train_loss:3.2604 train_time:1139546ms step_avg:216.31ms step:5279/6200 train_loss:3.4620 train_time:1139760ms step_avg:216.31ms step:5280/6200 train_loss:3.4950 train_time:1139974ms step_avg:216.31ms step:5281/6200 train_loss:3.3178 train_time:1140188ms step_avg:216.31ms step:5282/6200 train_loss:3.2099 train_time:1140406ms step_avg:216.31ms step:5283/6200 train_loss:3.3351 train_time:1140618ms step_avg:216.31ms step:5284/6200 train_loss:3.3375 train_time:1140831ms step_avg:216.31ms step:5285/6200 train_loss:3.3409 train_time:1141044ms step_avg:216.31ms step:5286/6200 train_loss:3.3346 train_time:1141258ms step_avg:216.31ms step:5287/6200 train_loss:3.2413 train_time:1141472ms step_avg:216.31ms step:5288/6200 train_loss:3.2494 train_time:1141686ms step_avg:216.31ms step:5289/6200 train_loss:3.2335 train_time:1141900ms step_avg:216.31ms step:5290/6200 train_loss:3.3692 train_time:1142114ms step_avg:216.31ms step:5291/6200 train_loss:3.4918 train_time:1142326ms step_avg:216.31ms step:5292/6200 train_loss:3.3180 train_time:1142794ms step_avg:216.36ms step:5293/6200 train_loss:3.4270 train_time:1143007ms step_avg:216.36ms step:5294/6200 train_loss:3.4103 train_time:1143221ms step_avg:216.36ms step:5295/6200 train_loss:3.4460 train_time:1143433ms step_avg:216.35ms step:5296/6200 train_loss:3.2882 train_time:1143645ms step_avg:216.35ms step:5297/6200 train_loss:3.3143 train_time:1143859ms step_avg:216.35ms step:5298/6200 train_loss:3.3023 train_time:1144072ms step_avg:216.35ms step:5299/6200 train_loss:3.2574 train_time:1144286ms step_avg:216.35ms step:5300/6200 train_loss:3.3965 train_time:1144500ms step_avg:216.35ms step:5301/6200 train_loss:3.3596 train_time:1144713ms step_avg:216.35ms step:5302/6200 train_loss:3.2258 train_time:1144925ms step_avg:216.35ms step:5303/6200 train_loss:3.4345 train_time:1145138ms step_avg:216.35ms step:5304/6200 train_loss:3.1768 train_time:1145351ms step_avg:216.35ms step:5305/6200 train_loss:3.1885 train_time:1145566ms step_avg:216.35ms step:5306/6200 train_loss:3.3802 train_time:1145779ms step_avg:216.35ms step:5307/6200 train_loss:3.2671 train_time:1145993ms step_avg:216.35ms step:5308/6200 train_loss:3.3054 train_time:1146207ms step_avg:216.35ms step:5309/6200 train_loss:3.1280 train_time:1146420ms step_avg:216.35ms step:5310/6200 train_loss:3.2935 train_time:1146632ms step_avg:216.35ms step:5311/6200 train_loss:3.2110 train_time:1146845ms step_avg:216.35ms step:5312/6200 train_loss:3.5460 train_time:1147059ms step_avg:216.34ms step:5313/6200 train_loss:3.3014 train_time:1147272ms step_avg:216.34ms step:5314/6200 train_loss:3.2795 train_time:1147486ms step_avg:216.34ms step:5315/6200 train_loss:3.4261 train_time:1147702ms step_avg:216.34ms step:5316/6200 train_loss:3.3637 train_time:1147915ms step_avg:216.34ms step:5317/6200 train_loss:3.5170 train_time:1148127ms step_avg:216.34ms step:5318/6200 train_loss:3.5288 train_time:1148340ms step_avg:216.34ms step:5319/6200 train_loss:3.9753 train_time:1148554ms step_avg:216.34ms step:5320/6200 train_loss:3.5212 train_time:1149030ms step_avg:216.39ms step:5321/6200 train_loss:3.2796 train_time:1149244ms step_avg:216.39ms step:5322/6200 train_loss:3.4948 train_time:1149456ms step_avg:216.39ms step:5323/6200 train_loss:3.5169 train_time:1149669ms step_avg:216.39ms step:5324/6200 train_loss:3.2078 train_time:1149884ms step_avg:216.39ms step:5325/6200 train_loss:3.1332 train_time:1150098ms step_avg:216.39ms step:5326/6200 train_loss:3.4263 train_time:1150312ms step_avg:216.39ms step:5327/6200 train_loss:3.2237 train_time:1150525ms step_avg:216.39ms step:5328/6200 train_loss:3.2836 train_time:1150739ms step_avg:216.39ms step:5329/6200 train_loss:3.2213 train_time:1150951ms step_avg:216.38ms step:5330/6200 train_loss:3.5364 train_time:1151167ms step_avg:216.38ms step:5331/6200 train_loss:3.3032 train_time:1151380ms step_avg:216.38ms step:5332/6200 train_loss:3.2677 train_time:1151593ms step_avg:216.38ms step:5333/6200 train_loss:3.3683 train_time:1151806ms step_avg:216.38ms step:5334/6200 train_loss:3.3573 train_time:1152022ms step_avg:216.38ms step:5335/6200 train_loss:4.6164 train_time:1152234ms step_avg:216.38ms step:5336/6200 train_loss:3.3153 train_time:1152446ms step_avg:216.38ms step:5337/6200 train_loss:3.5010 train_time:1152660ms step_avg:216.38ms step:5338/6200 train_loss:3.2951 train_time:1152873ms step_avg:216.38ms step:5339/6200 train_loss:3.2697 train_time:1153087ms step_avg:216.38ms step:5340/6200 train_loss:3.3757 train_time:1153301ms step_avg:216.38ms step:5341/6200 train_loss:3.2384 train_time:1153515ms step_avg:216.38ms step:5342/6200 train_loss:3.2857 train_time:1153726ms step_avg:216.38ms step:5343/6200 train_loss:3.5212 train_time:1153939ms step_avg:216.38ms step:5344/6200 train_loss:3.2500 train_time:1154153ms step_avg:216.38ms step:5345/6200 train_loss:3.3894 train_time:1154367ms step_avg:216.38ms step:5346/6200 train_loss:3.3315 train_time:1154580ms step_avg:216.38ms step:5347/6200 train_loss:3.2766 train_time:1154794ms step_avg:216.38ms step:5348/6200 train_loss:3.3114 train_time:1155008ms step_avg:216.37ms step:5349/6200 train_loss:3.3203 train_time:1155221ms step_avg:216.37ms step:5350/6200 train_loss:3.3643 train_time:1155434ms step_avg:216.37ms step:5351/6200 train_loss:3.2706 train_time:1155646ms step_avg:216.37ms step:5352/6200 train_loss:3.3594 train_time:1155860ms step_avg:216.37ms step:5353/6200 train_loss:3.3460 train_time:1156073ms step_avg:216.37ms step:5354/6200 train_loss:3.2938 train_time:1156287ms step_avg:216.37ms step:5355/6200 train_loss:3.2961 train_time:1156505ms step_avg:216.37ms step:5356/6200 train_loss:3.3384 train_time:1156716ms step_avg:216.37ms step:5357/6200 train_loss:3.2135 train_time:1156928ms step_avg:216.37ms step:5358/6200 train_loss:3.4391 train_time:1157142ms step_avg:216.37ms step:5359/6200 train_loss:3.2676 train_time:1157355ms step_avg:216.37ms step:5360/6200 train_loss:3.3653 train_time:1157568ms step_avg:216.37ms step:5361/6200 train_loss:2.9560 train_time:1157782ms step_avg:216.37ms step:5362/6200 train_loss:3.2649 train_time:1157995ms step_avg:216.37ms step:5363/6200 train_loss:3.4496 train_time:1158208ms step_avg:216.37ms step:5364/6200 train_loss:3.3426 train_time:1158421ms step_avg:216.37ms step:5365/6200 train_loss:3.2667 train_time:1158633ms step_avg:216.36ms step:5366/6200 train_loss:3.1811 train_time:1158846ms step_avg:216.36ms step:5367/6200 train_loss:3.4534 train_time:1159060ms step_avg:216.36ms step:5368/6200 train_loss:3.3613 train_time:1159273ms step_avg:216.36ms step:5369/6200 train_loss:3.3797 train_time:1159487ms step_avg:216.36ms step:5370/6200 train_loss:3.3079 train_time:1159702ms step_avg:216.36ms step:5371/6200 train_loss:3.2482 train_time:1159915ms step_avg:216.36ms step:5372/6200 train_loss:3.2657 train_time:1160127ms step_avg:216.36ms step:5373/6200 train_loss:3.5369 train_time:1160340ms step_avg:216.36ms step:5374/6200 train_loss:3.2187 train_time:1160554ms step_avg:216.36ms step:5375/6200 train_loss:3.3467 train_time:1160767ms step_avg:216.36ms step:5375/6200 val_loss:3.3296 train_time:1160768ms step_avg:216.36ms step:5376/6200 train_loss:3.0316 train_time:1160984ms step_avg:216.36ms step:5377/6200 train_loss:3.3843 train_time:1161200ms step_avg:216.36ms step:5378/6200 train_loss:3.3247 train_time:1161415ms step_avg:216.36ms step:5379/6200 train_loss:3.3553 train_time:1161627ms step_avg:216.36ms step:5380/6200 train_loss:3.5235 train_time:1161840ms step_avg:216.36ms step:5381/6200 train_loss:3.2825 train_time:1162054ms step_avg:216.36ms step:5382/6200 train_loss:3.4395 train_time:1162267ms step_avg:216.36ms step:5383/6200 train_loss:3.6809 train_time:1162480ms step_avg:216.36ms step:5384/6200 train_loss:3.2576 train_time:1162695ms step_avg:216.36ms step:5385/6200 train_loss:3.3422 train_time:1162909ms step_avg:216.36ms step:5386/6200 train_loss:3.3224 train_time:1163122ms step_avg:216.35ms step:5387/6200 train_loss:3.3553 train_time:1163338ms step_avg:216.35ms step:5388/6200 train_loss:3.3734 train_time:1163552ms step_avg:216.35ms step:5389/6200 train_loss:3.3215 train_time:1163764ms step_avg:216.35ms step:5390/6200 train_loss:3.5371 train_time:1163978ms step_avg:216.35ms step:5391/6200 train_loss:3.2191 train_time:1164192ms step_avg:216.35ms step:5392/6200 train_loss:3.1943 train_time:1164405ms step_avg:216.35ms step:5393/6200 train_loss:3.2227 train_time:1164620ms step_avg:216.35ms step:5394/6200 train_loss:3.4642 train_time:1164833ms step_avg:216.35ms step:5395/6200 train_loss:3.3853 train_time:1165045ms step_avg:216.35ms step:5396/6200 train_loss:3.5813 train_time:1165259ms step_avg:216.35ms step:5397/6200 train_loss:3.4630 train_time:1165473ms step_avg:216.35ms step:5398/6200 train_loss:3.2793 train_time:1165686ms step_avg:216.35ms step:5399/6200 train_loss:3.2119 train_time:1165901ms step_avg:216.35ms step:5400/6200 train_loss:3.5948 train_time:1166114ms step_avg:216.35ms step:5401/6200 train_loss:3.4632 train_time:1166327ms step_avg:216.35ms step:5402/6200 train_loss:3.3319 train_time:1166540ms step_avg:216.35ms step:5403/6200 train_loss:3.3158 train_time:1166753ms step_avg:216.35ms step:5404/6200 train_loss:3.2726 train_time:1166967ms step_avg:216.35ms step:5405/6200 train_loss:3.3612 train_time:1167181ms step_avg:216.34ms step:5406/6200 train_loss:3.3227 train_time:1167394ms step_avg:216.34ms step:5407/6200 train_loss:2.9839 train_time:1167609ms step_avg:216.34ms step:5408/6200 train_loss:3.4267 train_time:1167822ms step_avg:216.34ms step:5409/6200 train_loss:3.3212 train_time:1168037ms step_avg:216.34ms step:5410/6200 train_loss:3.3070 train_time:1168249ms step_avg:216.34ms step:5411/6200 train_loss:3.3062 train_time:1168463ms step_avg:216.34ms step:5412/6200 train_loss:3.3235 train_time:1168677ms step_avg:216.34ms step:5413/6200 train_loss:3.2860 train_time:1168890ms step_avg:216.34ms step:5414/6200 train_loss:3.4148 train_time:1169103ms step_avg:216.34ms step:5415/6200 train_loss:3.3432 train_time:1169320ms step_avg:216.34ms step:5416/6200 train_loss:3.3150 train_time:1169534ms step_avg:216.34ms step:5417/6200 train_loss:3.2650 train_time:1169746ms step_avg:216.34ms step:5418/6200 train_loss:3.3914 train_time:1169961ms step_avg:216.34ms step:5419/6200 train_loss:3.2742 train_time:1170174ms step_avg:216.34ms step:5420/6200 train_loss:3.4409 train_time:1170387ms step_avg:216.34ms step:5421/6200 train_loss:3.2946 train_time:1170602ms step_avg:216.34ms step:5422/6200 train_loss:3.3818 train_time:1170816ms step_avg:216.34ms step:5423/6200 train_loss:3.3751 train_time:1171030ms step_avg:216.34ms step:5424/6200 train_loss:2.9533 train_time:1171242ms step_avg:216.34ms step:5425/6200 train_loss:3.4176 train_time:1171455ms step_avg:216.34ms step:5426/6200 train_loss:3.3420 train_time:1171669ms step_avg:216.33ms step:5427/6200 train_loss:3.3376 train_time:1171882ms step_avg:216.33ms step:5428/6200 train_loss:3.3447 train_time:1172096ms step_avg:216.33ms step:5429/6200 train_loss:3.3104 train_time:1172309ms step_avg:216.33ms step:5430/6200 train_loss:3.3063 train_time:1172522ms step_avg:216.33ms step:5431/6200 train_loss:3.3210 train_time:1172735ms step_avg:216.33ms step:5432/6200 train_loss:3.3204 train_time:1172949ms step_avg:216.33ms step:5433/6200 train_loss:3.4077 train_time:1173163ms step_avg:216.33ms step:5434/6200 train_loss:3.4023 train_time:1173375ms step_avg:216.33ms step:5435/6200 train_loss:3.3220 train_time:1173588ms step_avg:216.33ms step:5436/6200 train_loss:3.3426 train_time:1173802ms step_avg:216.33ms step:5437/6200 train_loss:3.2171 train_time:1174017ms step_avg:216.33ms step:5438/6200 train_loss:3.3577 train_time:1174230ms step_avg:216.33ms step:5439/6200 train_loss:3.4189 train_time:1174442ms step_avg:216.33ms step:5440/6200 train_loss:3.3606 train_time:1174656ms step_avg:216.33ms step:5441/6200 train_loss:3.2689 train_time:1174870ms step_avg:216.33ms step:5442/6200 train_loss:3.2866 train_time:1175083ms step_avg:216.33ms step:5443/6200 train_loss:3.1775 train_time:1175297ms step_avg:216.33ms step:5444/6200 train_loss:3.3558 train_time:1175511ms step_avg:216.33ms step:5445/6200 train_loss:3.2488 train_time:1175725ms step_avg:216.32ms step:5446/6200 train_loss:3.4978 train_time:1175939ms step_avg:216.32ms step:5447/6200 train_loss:3.2680 train_time:1176151ms step_avg:216.32ms step:5448/6200 train_loss:3.3676 train_time:1176365ms step_avg:216.32ms step:5449/6200 train_loss:3.3136 train_time:1176580ms step_avg:216.32ms step:5450/6200 train_loss:3.4328 train_time:1176794ms step_avg:216.32ms step:5451/6200 train_loss:3.4319 train_time:1177006ms step_avg:216.32ms step:5452/6200 train_loss:4.1378 train_time:1177221ms step_avg:216.32ms step:5453/6200 train_loss:3.3469 train_time:1177435ms step_avg:216.32ms step:5454/6200 train_loss:3.5195 train_time:1177647ms step_avg:216.32ms step:5455/6200 train_loss:3.2234 train_time:1177860ms step_avg:216.32ms step:5456/6200 train_loss:3.1577 train_time:1178073ms step_avg:216.32ms step:5457/6200 train_loss:3.2948 train_time:1178290ms step_avg:216.32ms step:5458/6200 train_loss:3.4747 train_time:1178503ms step_avg:216.32ms step:5459/6200 train_loss:3.3687 train_time:1178720ms step_avg:216.32ms step:5460/6200 train_loss:3.2817 train_time:1178935ms step_avg:216.32ms step:5461/6200 train_loss:3.2364 train_time:1179148ms step_avg:216.32ms step:5462/6200 train_loss:4.2193 train_time:1179362ms step_avg:216.32ms step:5463/6200 train_loss:3.2081 train_time:1179576ms step_avg:216.32ms step:5464/6200 train_loss:3.4140 train_time:1179789ms step_avg:216.32ms step:5465/6200 train_loss:3.3526 train_time:1180002ms step_avg:216.32ms step:5466/6200 train_loss:3.3275 train_time:1180217ms step_avg:216.32ms step:5467/6200 train_loss:3.4889 train_time:1180431ms step_avg:216.31ms step:5468/6200 train_loss:3.2737 train_time:1180642ms step_avg:216.31ms step:5469/6200 train_loss:3.1920 train_time:1180855ms step_avg:216.31ms step:5470/6200 train_loss:3.1443 train_time:1181069ms step_avg:216.31ms step:5471/6200 train_loss:3.2649 train_time:1181283ms step_avg:216.31ms step:5472/6200 train_loss:3.3378 train_time:1181496ms step_avg:216.31ms step:5473/6200 train_loss:3.2994 train_time:1181710ms step_avg:216.31ms step:5474/6200 train_loss:3.5073 train_time:1181923ms step_avg:216.31ms step:5475/6200 train_loss:3.4230 train_time:1182137ms step_avg:216.31ms step:5476/6200 train_loss:3.4772 train_time:1182350ms step_avg:216.31ms step:5477/6200 train_loss:3.4612 train_time:1182563ms step_avg:216.31ms step:5478/6200 train_loss:3.2408 train_time:1182777ms step_avg:216.31ms step:5479/6200 train_loss:3.3768 train_time:1182991ms step_avg:216.31ms step:5480/6200 train_loss:3.3401 train_time:1183204ms step_avg:216.31ms step:5481/6200 train_loss:3.3940 train_time:1183675ms step_avg:216.35ms step:5482/6200 train_loss:3.4564 train_time:1183890ms step_avg:216.35ms step:5483/6200 train_loss:3.2978 train_time:1184103ms step_avg:216.35ms step:5484/6200 train_loss:3.3562 train_time:1184319ms step_avg:216.35ms step:5485/6200 train_loss:3.2893 train_time:1184531ms step_avg:216.35ms step:5486/6200 train_loss:3.3853 train_time:1184743ms step_avg:216.35ms step:5487/6200 train_loss:3.4366 train_time:1184956ms step_avg:216.35ms step:5488/6200 train_loss:3.2967 train_time:1185171ms step_avg:216.35ms step:5489/6200 train_loss:3.6277 train_time:1185384ms step_avg:216.35ms step:5490/6200 train_loss:3.3216 train_time:1185599ms step_avg:216.35ms step:5491/6200 train_loss:3.3798 train_time:1185812ms step_avg:216.35ms step:5492/6200 train_loss:3.4430 train_time:1186024ms step_avg:216.35ms step:5493/6200 train_loss:3.1983 train_time:1186238ms step_avg:216.35ms step:5494/6200 train_loss:3.4370 train_time:1186451ms step_avg:216.35ms step:5495/6200 train_loss:3.2961 train_time:1186664ms step_avg:216.35ms step:5496/6200 train_loss:3.2450 train_time:1186878ms step_avg:216.35ms step:5497/6200 train_loss:3.2475 train_time:1187090ms step_avg:216.35ms step:5498/6200 train_loss:3.2692 train_time:1187305ms step_avg:216.35ms step:5499/6200 train_loss:3.4426 train_time:1187518ms step_avg:216.34ms step:5500/6200 train_loss:3.3305 train_time:1187730ms step_avg:216.34ms step:5500/6200 val_loss:3.3200 train_time:1187732ms step_avg:216.34ms step:5501/6200 train_loss:3.3657 train_time:1187948ms step_avg:216.34ms step:5502/6200 train_loss:3.2773 train_time:1188161ms step_avg:216.34ms step:5503/6200 train_loss:3.4462 train_time:1188373ms step_avg:216.34ms step:5504/6200 train_loss:3.2363 train_time:1188586ms step_avg:216.34ms step:5505/6200 train_loss:3.7969 train_time:1188799ms step_avg:216.34ms step:5506/6200 train_loss:3.3304 train_time:1189013ms step_avg:216.34ms step:5507/6200 train_loss:3.3514 train_time:1189227ms step_avg:216.34ms step:5508/6200 train_loss:3.2606 train_time:1189442ms step_avg:216.34ms step:5509/6200 train_loss:3.3369 train_time:1189654ms step_avg:216.34ms step:5510/6200 train_loss:3.3638 train_time:1190132ms step_avg:216.39ms step:5511/6200 train_loss:3.8107 train_time:1190348ms step_avg:216.39ms step:5512/6200 train_loss:3.4356 train_time:1190561ms step_avg:216.39ms step:5513/6200 train_loss:3.3110 train_time:1190773ms step_avg:216.39ms step:5514/6200 train_loss:3.3403 train_time:1190987ms step_avg:216.39ms step:5515/6200 train_loss:3.5584 train_time:1191201ms step_avg:216.39ms step:5516/6200 train_loss:3.3056 train_time:1191413ms step_avg:216.38ms step:5517/6200 train_loss:3.2886 train_time:1191628ms step_avg:216.38ms step:5518/6200 train_loss:3.4136 train_time:1191841ms step_avg:216.38ms step:5519/6200 train_loss:3.3481 train_time:1192054ms step_avg:216.38ms step:5520/6200 train_loss:3.2407 train_time:1192267ms step_avg:216.38ms step:5521/6200 train_loss:3.3139 train_time:1192480ms step_avg:216.38ms step:5522/6200 train_loss:3.3185 train_time:1192693ms step_avg:216.38ms step:5523/6200 train_loss:3.4019 train_time:1192907ms step_avg:216.38ms step:5524/6200 train_loss:3.3206 train_time:1193120ms step_avg:216.38ms step:5525/6200 train_loss:3.3717 train_time:1193334ms step_avg:216.38ms step:5526/6200 train_loss:3.4560 train_time:1193549ms step_avg:216.38ms step:5527/6200 train_loss:3.2980 train_time:1193761ms step_avg:216.38ms step:5528/6200 train_loss:3.2837 train_time:1193973ms step_avg:216.38ms step:5529/6200 train_loss:3.3478 train_time:1194186ms step_avg:216.38ms step:5530/6200 train_loss:3.3263 train_time:1194399ms step_avg:216.38ms step:5531/6200 train_loss:3.3199 train_time:1194613ms step_avg:216.38ms step:5532/6200 train_loss:3.3138 train_time:1194826ms step_avg:216.38ms step:5533/6200 train_loss:3.2367 train_time:1195040ms step_avg:216.38ms step:5534/6200 train_loss:3.2866 train_time:1195253ms step_avg:216.37ms step:5535/6200 train_loss:3.3783 train_time:1195466ms step_avg:216.37ms step:5536/6200 train_loss:3.2570 train_time:1195679ms step_avg:216.37ms step:5537/6200 train_loss:3.3889 train_time:1195892ms step_avg:216.37ms step:5538/6200 train_loss:3.3460 train_time:1196106ms step_avg:216.37ms step:5539/6200 train_loss:3.3423 train_time:1196319ms step_avg:216.37ms step:5540/6200 train_loss:3.4440 train_time:1196532ms step_avg:216.37ms step:5541/6200 train_loss:3.3087 train_time:1196747ms step_avg:216.37ms step:5542/6200 train_loss:3.2911 train_time:1196960ms step_avg:216.37ms step:5543/6200 train_loss:3.2434 train_time:1197172ms step_avg:216.37ms step:5544/6200 train_loss:3.5092 train_time:1197385ms step_avg:216.37ms step:5545/6200 train_loss:3.2925 train_time:1197598ms step_avg:216.37ms step:5546/6200 train_loss:3.4572 train_time:1197813ms step_avg:216.37ms step:5547/6200 train_loss:3.4368 train_time:1198026ms step_avg:216.37ms step:5548/6200 train_loss:3.2312 train_time:1198239ms step_avg:216.37ms step:5549/6200 train_loss:3.1905 train_time:1198453ms step_avg:216.37ms step:5550/6200 train_loss:3.9677 train_time:1198667ms step_avg:216.37ms step:5551/6200 train_loss:3.4032 train_time:1198879ms step_avg:216.37ms step:5552/6200 train_loss:3.2732 train_time:1199092ms step_avg:216.36ms step:5553/6200 train_loss:3.3315 train_time:1199305ms step_avg:216.36ms step:5554/6200 train_loss:3.2930 train_time:1199518ms step_avg:216.36ms step:5555/6200 train_loss:3.2958 train_time:1199734ms step_avg:216.36ms step:5556/6200 train_loss:3.1362 train_time:1199948ms step_avg:216.36ms step:5557/6200 train_loss:3.3324 train_time:1200161ms step_avg:216.36ms step:5558/6200 train_loss:3.3997 train_time:1200373ms step_avg:216.36ms step:5559/6200 train_loss:3.3349 train_time:1200586ms step_avg:216.36ms step:5560/6200 train_loss:3.4559 train_time:1200800ms step_avg:216.36ms step:5561/6200 train_loss:3.1817 train_time:1201014ms step_avg:216.36ms step:5562/6200 train_loss:3.2211 train_time:1201228ms step_avg:216.36ms step:5563/6200 train_loss:3.3406 train_time:1201441ms step_avg:216.36ms step:5564/6200 train_loss:3.4215 train_time:1201654ms step_avg:216.36ms step:5565/6200 train_loss:3.5462 train_time:1201867ms step_avg:216.36ms step:5566/6200 train_loss:3.3170 train_time:1202080ms step_avg:216.36ms step:5567/6200 train_loss:3.4605 train_time:1202296ms step_avg:216.36ms step:5568/6200 train_loss:3.5062 train_time:1202509ms step_avg:216.36ms step:5569/6200 train_loss:3.2829 train_time:1202722ms step_avg:216.36ms step:5570/6200 train_loss:3.3000 train_time:1202934ms step_avg:216.36ms step:5571/6200 train_loss:3.3910 train_time:1203150ms step_avg:216.35ms step:5572/6200 train_loss:3.2358 train_time:1203363ms step_avg:216.35ms step:5573/6200 train_loss:3.5248 train_time:1203575ms step_avg:216.35ms step:5574/6200 train_loss:3.2343 train_time:1203789ms step_avg:216.35ms step:5575/6200 train_loss:3.3648 train_time:1204002ms step_avg:216.35ms step:5576/6200 train_loss:3.3053 train_time:1204214ms step_avg:216.35ms step:5577/6200 train_loss:3.3851 train_time:1204428ms step_avg:216.35ms step:5578/6200 train_loss:3.2740 train_time:1204642ms step_avg:216.35ms step:5579/6200 train_loss:3.2153 train_time:1204855ms step_avg:216.35ms step:5580/6200 train_loss:3.1490 train_time:1205069ms step_avg:216.35ms step:5581/6200 train_loss:3.3701 train_time:1205281ms step_avg:216.35ms step:5582/6200 train_loss:3.6032 train_time:1205495ms step_avg:216.35ms step:5583/6200 train_loss:3.3656 train_time:1205709ms step_avg:216.35ms step:5584/6200 train_loss:3.2877 train_time:1205923ms step_avg:216.35ms step:5585/6200 train_loss:3.3346 train_time:1206137ms step_avg:216.35ms step:5586/6200 train_loss:3.3042 train_time:1206351ms step_avg:216.35ms step:5587/6200 train_loss:3.2283 train_time:1206567ms step_avg:216.35ms step:5588/6200 train_loss:3.4303 train_time:1206779ms step_avg:216.35ms step:5589/6200 train_loss:3.3093 train_time:1206993ms step_avg:216.35ms step:5590/6200 train_loss:3.3600 train_time:1207206ms step_avg:216.35ms step:5591/6200 train_loss:3.2309 train_time:1207421ms step_avg:216.34ms step:5592/6200 train_loss:3.3163 train_time:1207635ms step_avg:216.34ms step:5593/6200 train_loss:3.4095 train_time:1207850ms step_avg:216.34ms step:5594/6200 train_loss:3.1635 train_time:1208063ms step_avg:216.34ms step:5595/6200 train_loss:3.3657 train_time:1208277ms step_avg:216.34ms step:5596/6200 train_loss:3.3226 train_time:1208490ms step_avg:216.34ms step:5597/6200 train_loss:3.2976 train_time:1208704ms step_avg:216.34ms step:5598/6200 train_loss:3.5461 train_time:1208918ms step_avg:216.34ms step:5599/6200 train_loss:3.2802 train_time:1209131ms step_avg:216.34ms step:5600/6200 train_loss:3.2405 train_time:1209346ms step_avg:216.34ms step:5601/6200 train_loss:3.4352 train_time:1209559ms step_avg:216.34ms step:5602/6200 train_loss:3.3980 train_time:1209771ms step_avg:216.34ms step:5603/6200 train_loss:3.2797 train_time:1209984ms step_avg:216.34ms step:5604/6200 train_loss:3.2321 train_time:1210197ms step_avg:216.34ms step:5605/6200 train_loss:3.4583 train_time:1210411ms step_avg:216.34ms step:5606/6200 train_loss:3.3365 train_time:1210625ms step_avg:216.34ms step:5607/6200 train_loss:3.2243 train_time:1210839ms step_avg:216.34ms step:5608/6200 train_loss:3.3908 train_time:1211054ms step_avg:216.34ms step:5609/6200 train_loss:3.2608 train_time:1211268ms step_avg:216.34ms step:5610/6200 train_loss:3.3468 train_time:1211480ms step_avg:216.34ms step:5611/6200 train_loss:3.2776 train_time:1211693ms step_avg:216.34ms step:5612/6200 train_loss:3.2076 train_time:1211907ms step_avg:216.33ms step:5613/6200 train_loss:3.3706 train_time:1212121ms step_avg:216.33ms step:5614/6200 train_loss:3.4002 train_time:1212334ms step_avg:216.33ms step:5615/6200 train_loss:3.2572 train_time:1212549ms step_avg:216.33ms step:5616/6200 train_loss:3.3892 train_time:1212761ms step_avg:216.33ms step:5617/6200 train_loss:3.5121 train_time:1212973ms step_avg:216.33ms step:5618/6200 train_loss:3.2531 train_time:1213187ms step_avg:216.33ms step:5619/6200 train_loss:3.3579 train_time:1213400ms step_avg:216.33ms step:5620/6200 train_loss:3.3751 train_time:1213614ms step_avg:216.33ms step:5621/6200 train_loss:3.4938 train_time:1213828ms step_avg:216.33ms step:5622/6200 train_loss:3.3801 train_time:1214042ms step_avg:216.33ms step:5623/6200 train_loss:3.3489 train_time:1214254ms step_avg:216.33ms step:5624/6200 train_loss:3.3668 train_time:1214469ms step_avg:216.33ms step:5625/6200 train_loss:3.4706 train_time:1214681ms step_avg:216.33ms step:5625/6200 val_loss:3.3107 train_time:1214683ms step_avg:216.33ms step:5626/6200 train_loss:3.4231 train_time:1214898ms step_avg:216.33ms step:5627/6200 train_loss:3.5115 train_time:1215112ms step_avg:216.33ms step:5628/6200 train_loss:3.3308 train_time:1215326ms step_avg:216.33ms step:5629/6200 train_loss:3.2821 train_time:1215541ms step_avg:216.33ms step:5630/6200 train_loss:3.2675 train_time:1215754ms step_avg:216.33ms step:5631/6200 train_loss:3.2184 train_time:1215967ms step_avg:216.33ms step:5632/6200 train_loss:3.3175 train_time:1216180ms step_avg:216.33ms step:5633/6200 train_loss:3.3319 train_time:1216392ms step_avg:216.32ms step:5634/6200 train_loss:3.2791 train_time:1216606ms step_avg:216.32ms step:5635/6200 train_loss:3.4430 train_time:1216821ms step_avg:216.32ms step:5636/6200 train_loss:3.3999 train_time:1217033ms step_avg:216.32ms step:5637/6200 train_loss:3.3695 train_time:1217248ms step_avg:216.32ms step:5638/6200 train_loss:3.3043 train_time:1217463ms step_avg:216.32ms step:5639/6200 train_loss:3.2204 train_time:1217677ms step_avg:216.32ms step:5640/6200 train_loss:3.3784 train_time:1217889ms step_avg:216.32ms step:5641/6200 train_loss:3.0952 train_time:1218102ms step_avg:216.32ms step:5642/6200 train_loss:3.2893 train_time:1218316ms step_avg:216.32ms step:5643/6200 train_loss:3.3070 train_time:1218529ms step_avg:216.32ms step:5644/6200 train_loss:3.2501 train_time:1218743ms step_avg:216.32ms step:5645/6200 train_loss:3.4095 train_time:1218957ms step_avg:216.32ms step:5646/6200 train_loss:3.1980 train_time:1219170ms step_avg:216.32ms step:5647/6200 train_loss:3.2263 train_time:1219383ms step_avg:216.32ms step:5648/6200 train_loss:3.1902 train_time:1219596ms step_avg:216.32ms step:5649/6200 train_loss:3.6428 train_time:1219809ms step_avg:216.32ms step:5650/6200 train_loss:3.3282 train_time:1220024ms step_avg:216.32ms step:5651/6200 train_loss:3.2499 train_time:1220237ms step_avg:216.32ms step:5652/6200 train_loss:3.2948 train_time:1220450ms step_avg:216.32ms step:5653/6200 train_loss:3.2658 train_time:1220665ms step_avg:216.31ms step:5654/6200 train_loss:3.2253 train_time:1220878ms step_avg:216.31ms step:5655/6200 train_loss:3.3008 train_time:1221090ms step_avg:216.31ms step:5656/6200 train_loss:3.3637 train_time:1221303ms step_avg:216.31ms step:5657/6200 train_loss:3.5076 train_time:1221517ms step_avg:216.31ms step:5658/6200 train_loss:4.1098 train_time:1221731ms step_avg:216.31ms step:5659/6200 train_loss:3.2304 train_time:1221944ms step_avg:216.31ms step:5660/6200 train_loss:3.4387 train_time:1222159ms step_avg:216.31ms step:5661/6200 train_loss:3.3683 train_time:1222372ms step_avg:216.31ms step:5662/6200 train_loss:3.3106 train_time:1222583ms step_avg:216.31ms step:5663/6200 train_loss:3.3038 train_time:1222799ms step_avg:216.31ms step:5664/6200 train_loss:3.2119 train_time:1223011ms step_avg:216.31ms step:5665/6200 train_loss:3.2459 train_time:1223224ms step_avg:216.31ms step:5666/6200 train_loss:3.3539 train_time:1223438ms step_avg:216.31ms step:5667/6200 train_loss:3.3492 train_time:1223652ms step_avg:216.31ms step:5668/6200 train_loss:3.3718 train_time:1223865ms step_avg:216.31ms step:5669/6200 train_loss:3.3361 train_time:1224079ms step_avg:216.31ms step:5670/6200 train_loss:3.1863 train_time:1224546ms step_avg:216.35ms step:5671/6200 train_loss:3.3837 train_time:1224764ms step_avg:216.35ms step:5672/6200 train_loss:3.3084 train_time:1224978ms step_avg:216.35ms step:5673/6200 train_loss:3.2311 train_time:1225191ms step_avg:216.35ms step:5674/6200 train_loss:3.2950 train_time:1225403ms step_avg:216.35ms step:5675/6200 train_loss:3.2267 train_time:1225616ms step_avg:216.35ms step:5676/6200 train_loss:3.2253 train_time:1225830ms step_avg:216.35ms step:5677/6200 train_loss:3.3891 train_time:1226044ms step_avg:216.35ms step:5678/6200 train_loss:3.4542 train_time:1226258ms step_avg:216.35ms step:5679/6200 train_loss:3.2897 train_time:1226471ms step_avg:216.35ms step:5680/6200 train_loss:3.3769 train_time:1226683ms step_avg:216.35ms step:5681/6200 train_loss:3.3437 train_time:1226896ms step_avg:216.35ms step:5682/6200 train_loss:3.3016 train_time:1227110ms step_avg:216.35ms step:5683/6200 train_loss:3.2959 train_time:1227323ms step_avg:216.34ms step:5684/6200 train_loss:3.2767 train_time:1227537ms step_avg:216.34ms step:5685/6200 train_loss:3.6624 train_time:1227751ms step_avg:216.34ms step:5686/6200 train_loss:3.3942 train_time:1227964ms step_avg:216.34ms step:5687/6200 train_loss:3.4186 train_time:1228177ms step_avg:216.34ms step:5688/6200 train_loss:3.4636 train_time:1228390ms step_avg:216.34ms step:5689/6200 train_loss:3.3597 train_time:1228603ms step_avg:216.34ms step:5690/6200 train_loss:3.2059 train_time:1228816ms step_avg:216.34ms step:5691/6200 train_loss:3.3812 train_time:1229030ms step_avg:216.34ms step:5692/6200 train_loss:3.3682 train_time:1229244ms step_avg:216.34ms step:5693/6200 train_loss:3.3719 train_time:1229459ms step_avg:216.34ms step:5694/6200 train_loss:3.3270 train_time:1229672ms step_avg:216.34ms step:5695/6200 train_loss:3.2967 train_time:1229884ms step_avg:216.34ms step:5696/6200 train_loss:3.3939 train_time:1230097ms step_avg:216.34ms step:5697/6200 train_loss:3.3565 train_time:1230310ms step_avg:216.34ms step:5698/6200 train_loss:3.4861 train_time:1230524ms step_avg:216.34ms step:5699/6200 train_loss:3.4260 train_time:1230739ms step_avg:216.34ms step:5700/6200 train_loss:3.2570 train_time:1231216ms step_avg:216.38ms step:5701/6200 train_loss:3.3364 train_time:1231429ms step_avg:216.38ms step:5702/6200 train_loss:3.2620 train_time:1231643ms step_avg:216.38ms step:5703/6200 train_loss:3.2558 train_time:1231857ms step_avg:216.38ms step:5704/6200 train_loss:3.3498 train_time:1232070ms step_avg:216.38ms step:5705/6200 train_loss:3.5539 train_time:1232282ms step_avg:216.38ms step:5706/6200 train_loss:3.3874 train_time:1232495ms step_avg:216.38ms step:5707/6200 train_loss:3.2918 train_time:1232709ms step_avg:216.38ms step:5708/6200 train_loss:3.3422 train_time:1232923ms step_avg:216.38ms step:5709/6200 train_loss:3.2669 train_time:1233136ms step_avg:216.38ms step:5710/6200 train_loss:3.3349 train_time:1233350ms step_avg:216.38ms step:5711/6200 train_loss:3.4042 train_time:1233564ms step_avg:216.38ms step:5712/6200 train_loss:3.2259 train_time:1233777ms step_avg:216.38ms step:5713/6200 train_loss:3.0844 train_time:1233990ms step_avg:216.38ms step:5714/6200 train_loss:3.4401 train_time:1234204ms step_avg:216.38ms step:5715/6200 train_loss:3.5620 train_time:1234417ms step_avg:216.37ms step:5716/6200 train_loss:3.4574 train_time:1234631ms step_avg:216.37ms step:5717/6200 train_loss:3.2956 train_time:1234844ms step_avg:216.37ms step:5718/6200 train_loss:3.1958 train_time:1235059ms step_avg:216.37ms step:5719/6200 train_loss:3.4038 train_time:1235272ms step_avg:216.37ms step:5720/6200 train_loss:3.1723 train_time:1235484ms step_avg:216.37ms step:5721/6200 train_loss:3.3069 train_time:1235696ms step_avg:216.37ms step:5722/6200 train_loss:3.6829 train_time:1235910ms step_avg:216.37ms step:5723/6200 train_loss:3.3239 train_time:1236123ms step_avg:216.37ms step:5724/6200 train_loss:3.4746 train_time:1236337ms step_avg:216.37ms step:5725/6200 train_loss:3.3768 train_time:1236551ms step_avg:216.37ms step:5726/6200 train_loss:3.2111 train_time:1236764ms step_avg:216.37ms step:5727/6200 train_loss:3.3752 train_time:1236977ms step_avg:216.37ms step:5728/6200 train_loss:3.2829 train_time:1237189ms step_avg:216.37ms step:5729/6200 train_loss:3.2721 train_time:1237403ms step_avg:216.37ms step:5730/6200 train_loss:3.3742 train_time:1237617ms step_avg:216.37ms step:5731/6200 train_loss:3.2000 train_time:1237830ms step_avg:216.37ms step:5732/6200 train_loss:3.3368 train_time:1238044ms step_avg:216.37ms step:5733/6200 train_loss:3.1230 train_time:1238258ms step_avg:216.37ms step:5734/6200 train_loss:3.3016 train_time:1238471ms step_avg:216.36ms step:5735/6200 train_loss:3.1787 train_time:1238684ms step_avg:216.36ms step:5736/6200 train_loss:3.2979 train_time:1238896ms step_avg:216.36ms step:5737/6200 train_loss:3.3097 train_time:1239109ms step_avg:216.36ms step:5738/6200 train_loss:3.2667 train_time:1239323ms step_avg:216.36ms step:5739/6200 train_loss:3.2463 train_time:1239537ms step_avg:216.36ms step:5740/6200 train_loss:3.1865 train_time:1239750ms step_avg:216.36ms step:5741/6200 train_loss:3.4149 train_time:1239964ms step_avg:216.36ms step:5742/6200 train_loss:3.2604 train_time:1240177ms step_avg:216.36ms step:5743/6200 train_loss:3.2910 train_time:1240389ms step_avg:216.36ms step:5744/6200 train_loss:3.2191 train_time:1240602ms step_avg:216.36ms step:5745/6200 train_loss:3.4172 train_time:1240816ms step_avg:216.36ms step:5746/6200 train_loss:3.4074 train_time:1241029ms step_avg:216.36ms step:5747/6200 train_loss:3.2915 train_time:1241243ms step_avg:216.36ms step:5748/6200 train_loss:3.4459 train_time:1241456ms step_avg:216.36ms step:5749/6200 train_loss:3.3570 train_time:1241669ms step_avg:216.36ms step:5750/6200 train_loss:3.4095 train_time:1241882ms step_avg:216.36ms step:5750/6200 val_loss:3.3017 train_time:1241884ms step_avg:216.36ms step:5751/6200 train_loss:3.3587 train_time:1242102ms step_avg:216.36ms step:5752/6200 train_loss:3.3638 train_time:1242315ms step_avg:216.36ms step:5753/6200 train_loss:3.3044 train_time:1242528ms step_avg:216.36ms step:5754/6200 train_loss:3.3445 train_time:1242743ms step_avg:216.35ms step:5755/6200 train_loss:3.3136 train_time:1242957ms step_avg:216.35ms step:5756/6200 train_loss:3.1747 train_time:1243171ms step_avg:216.35ms step:5757/6200 train_loss:3.4119 train_time:1243384ms step_avg:216.35ms step:5758/6200 train_loss:3.3472 train_time:1243598ms step_avg:216.35ms step:5759/6200 train_loss:3.0777 train_time:1243810ms step_avg:216.35ms step:5760/6200 train_loss:3.2104 train_time:1244023ms step_avg:216.35ms step:5761/6200 train_loss:3.2606 train_time:1244236ms step_avg:216.35ms step:5762/6200 train_loss:3.3858 train_time:1244450ms step_avg:216.35ms step:5763/6200 train_loss:3.4370 train_time:1244664ms step_avg:216.35ms step:5764/6200 train_loss:3.4864 train_time:1244880ms step_avg:216.35ms step:5765/6200 train_loss:3.2068 train_time:1245094ms step_avg:216.35ms step:5766/6200 train_loss:3.3100 train_time:1245305ms step_avg:216.35ms step:5767/6200 train_loss:3.6105 train_time:1245519ms step_avg:216.35ms step:5768/6200 train_loss:3.2150 train_time:1245732ms step_avg:216.35ms step:5769/6200 train_loss:3.2063 train_time:1245945ms step_avg:216.35ms step:5770/6200 train_loss:3.3836 train_time:1246160ms step_avg:216.35ms step:5771/6200 train_loss:3.2988 train_time:1246374ms step_avg:216.35ms step:5772/6200 train_loss:3.3979 train_time:1246586ms step_avg:216.35ms step:5773/6200 train_loss:3.5502 train_time:1246800ms step_avg:216.35ms step:5774/6200 train_loss:3.5148 train_time:1247012ms step_avg:216.34ms step:5775/6200 train_loss:3.4006 train_time:1247226ms step_avg:216.34ms step:5776/6200 train_loss:3.3980 train_time:1247440ms step_avg:216.34ms step:5777/6200 train_loss:3.5638 train_time:1247654ms step_avg:216.34ms step:5778/6200 train_loss:3.3621 train_time:1247867ms step_avg:216.34ms step:5779/6200 train_loss:3.3362 train_time:1248082ms step_avg:216.34ms step:5780/6200 train_loss:3.3259 train_time:1248296ms step_avg:216.34ms step:5781/6200 train_loss:3.2448 train_time:1248508ms step_avg:216.34ms step:5782/6200 train_loss:3.5021 train_time:1248722ms step_avg:216.34ms step:5783/6200 train_loss:3.3207 train_time:1248936ms step_avg:216.34ms step:5784/6200 train_loss:3.4428 train_time:1249149ms step_avg:216.34ms step:5785/6200 train_loss:3.2262 train_time:1249363ms step_avg:216.34ms step:5786/6200 train_loss:3.2934 train_time:1249580ms step_avg:216.34ms step:5787/6200 train_loss:3.3792 train_time:1249793ms step_avg:216.34ms step:5788/6200 train_loss:3.4694 train_time:1250005ms step_avg:216.34ms step:5789/6200 train_loss:3.3244 train_time:1250219ms step_avg:216.34ms step:5790/6200 train_loss:3.1977 train_time:1250431ms step_avg:216.34ms step:5791/6200 train_loss:3.4920 train_time:1250644ms step_avg:216.34ms step:5792/6200 train_loss:3.2431 train_time:1250858ms step_avg:216.34ms step:5793/6200 train_loss:3.2639 train_time:1251071ms step_avg:216.34ms step:5794/6200 train_loss:3.2730 train_time:1251284ms step_avg:216.34ms step:5795/6200 train_loss:3.2639 train_time:1251497ms step_avg:216.33ms step:5796/6200 train_loss:3.2784 train_time:1251710ms step_avg:216.33ms step:5797/6200 train_loss:3.2647 train_time:1251922ms step_avg:216.33ms step:5798/6200 train_loss:3.4131 train_time:1252136ms step_avg:216.33ms step:5799/6200 train_loss:3.3360 train_time:1252351ms step_avg:216.33ms step:5800/6200 train_loss:3.2725 train_time:1252564ms step_avg:216.33ms step:5801/6200 train_loss:3.3405 train_time:1252780ms step_avg:216.33ms step:5802/6200 train_loss:3.3649 train_time:1252992ms step_avg:216.33ms step:5803/6200 train_loss:3.5925 train_time:1253204ms step_avg:216.33ms step:5804/6200 train_loss:3.4197 train_time:1253417ms step_avg:216.33ms step:5805/6200 train_loss:3.2859 train_time:1253630ms step_avg:216.33ms step:5806/6200 train_loss:3.2020 train_time:1253844ms step_avg:216.33ms step:5807/6200 train_loss:3.2716 train_time:1254058ms step_avg:216.33ms step:5808/6200 train_loss:3.4396 train_time:1254272ms step_avg:216.33ms step:5809/6200 train_loss:3.1832 train_time:1254485ms step_avg:216.33ms step:5810/6200 train_loss:3.1190 train_time:1254699ms step_avg:216.33ms step:5811/6200 train_loss:3.3039 train_time:1254911ms step_avg:216.33ms step:5812/6200 train_loss:3.2680 train_time:1255125ms step_avg:216.33ms step:5813/6200 train_loss:3.2464 train_time:1255338ms step_avg:216.33ms step:5814/6200 train_loss:3.5686 train_time:1255551ms step_avg:216.33ms step:5815/6200 train_loss:3.2987 train_time:1255765ms step_avg:216.32ms step:5816/6200 train_loss:3.4633 train_time:1255980ms step_avg:216.32ms step:5817/6200 train_loss:3.4191 train_time:1256194ms step_avg:216.32ms step:5818/6200 train_loss:3.1483 train_time:1256406ms step_avg:216.32ms step:5819/6200 train_loss:3.3665 train_time:1256620ms step_avg:216.32ms step:5820/6200 train_loss:3.4364 train_time:1256832ms step_avg:216.32ms step:5821/6200 train_loss:3.3544 train_time:1257045ms step_avg:216.32ms step:5822/6200 train_loss:3.1994 train_time:1257258ms step_avg:216.32ms step:5823/6200 train_loss:3.3087 train_time:1257472ms step_avg:216.32ms step:5824/6200 train_loss:3.3586 train_time:1257685ms step_avg:216.32ms step:5825/6200 train_loss:3.2585 train_time:1257899ms step_avg:216.32ms step:5826/6200 train_loss:3.1726 train_time:1258111ms step_avg:216.32ms step:5827/6200 train_loss:3.1845 train_time:1258324ms step_avg:216.32ms step:5828/6200 train_loss:3.1994 train_time:1258538ms step_avg:216.32ms step:5829/6200 train_loss:3.2610 train_time:1258751ms step_avg:216.32ms step:5830/6200 train_loss:3.2820 train_time:1258965ms step_avg:216.32ms step:5831/6200 train_loss:3.3537 train_time:1259180ms step_avg:216.32ms step:5832/6200 train_loss:3.3995 train_time:1259393ms step_avg:216.32ms step:5833/6200 train_loss:3.1602 train_time:1259605ms step_avg:216.32ms step:5834/6200 train_loss:3.8580 train_time:1259818ms step_avg:216.31ms step:5835/6200 train_loss:3.4256 train_time:1260031ms step_avg:216.31ms step:5836/6200 train_loss:3.3144 train_time:1260245ms step_avg:216.31ms step:5837/6200 train_loss:3.2806 train_time:1260458ms step_avg:216.31ms step:5838/6200 train_loss:3.3490 train_time:1260671ms step_avg:216.31ms step:5839/6200 train_loss:3.2682 train_time:1260884ms step_avg:216.31ms step:5840/6200 train_loss:3.2972 train_time:1261099ms step_avg:216.31ms step:5841/6200 train_loss:3.0656 train_time:1261311ms step_avg:216.31ms step:5842/6200 train_loss:3.4003 train_time:1261524ms step_avg:216.31ms step:5843/6200 train_loss:3.2487 train_time:1261738ms step_avg:216.31ms step:5844/6200 train_loss:3.5963 train_time:1261952ms step_avg:216.31ms step:5845/6200 train_loss:3.3800 train_time:1262165ms step_avg:216.31ms step:5846/6200 train_loss:3.3401 train_time:1262380ms step_avg:216.31ms step:5847/6200 train_loss:3.4562 train_time:1262594ms step_avg:216.31ms step:5848/6200 train_loss:3.4230 train_time:1262807ms step_avg:216.31ms step:5849/6200 train_loss:3.7917 train_time:1263018ms step_avg:216.31ms step:5850/6200 train_loss:3.3462 train_time:1263231ms step_avg:216.31ms step:5851/6200 train_loss:3.4187 train_time:1263444ms step_avg:216.31ms step:5852/6200 train_loss:3.3854 train_time:1263658ms step_avg:216.31ms step:5853/6200 train_loss:3.3013 train_time:1263873ms step_avg:216.31ms step:5854/6200 train_loss:3.2425 train_time:1264086ms step_avg:216.30ms step:5855/6200 train_loss:3.2162 train_time:1264300ms step_avg:216.30ms step:5856/6200 train_loss:3.3903 train_time:1264513ms step_avg:216.30ms step:5857/6200 train_loss:3.3345 train_time:1264727ms step_avg:216.30ms step:5858/6200 train_loss:3.3673 train_time:1264942ms step_avg:216.30ms step:5859/6200 train_loss:3.2658 train_time:1265409ms step_avg:216.35ms step:5860/6200 train_loss:3.4804 train_time:1265623ms step_avg:216.35ms step:5861/6200 train_loss:3.2265 train_time:1265836ms step_avg:216.35ms step:5862/6200 train_loss:3.1863 train_time:1266050ms step_avg:216.34ms step:5863/6200 train_loss:3.3876 train_time:1266263ms step_avg:216.34ms step:5864/6200 train_loss:3.2567 train_time:1266477ms step_avg:216.34ms step:5865/6200 train_loss:3.4292 train_time:1266690ms step_avg:216.34ms step:5866/6200 train_loss:3.2462 train_time:1266902ms step_avg:216.34ms step:5867/6200 train_loss:3.3699 train_time:1267114ms step_avg:216.34ms step:5868/6200 train_loss:3.2342 train_time:1267327ms step_avg:216.34ms step:5869/6200 train_loss:3.5123 train_time:1267542ms step_avg:216.34ms step:5870/6200 train_loss:3.2837 train_time:1267755ms step_avg:216.34ms step:5871/6200 train_loss:3.2160 train_time:1267967ms step_avg:216.34ms step:5872/6200 train_loss:3.3735 train_time:1268183ms step_avg:216.34ms step:5873/6200 train_loss:3.2930 train_time:1268397ms step_avg:216.34ms step:5874/6200 train_loss:3.3043 train_time:1268610ms step_avg:216.34ms step:5875/6200 train_loss:3.2553 train_time:1268825ms step_avg:216.34ms step:5875/6200 val_loss:3.2932 train_time:1268826ms step_avg:216.34ms step:5876/6200 train_loss:3.2787 train_time:1269043ms step_avg:216.34ms step:5877/6200 train_loss:3.3710 train_time:1269258ms step_avg:216.34ms step:5878/6200 train_loss:3.3568 train_time:1269472ms step_avg:216.34ms step:5879/6200 train_loss:3.3380 train_time:1269686ms step_avg:216.34ms step:5880/6200 train_loss:3.1375 train_time:1269901ms step_avg:216.34ms step:5881/6200 train_loss:3.2681 train_time:1270115ms step_avg:216.34ms step:5882/6200 train_loss:3.3137 train_time:1270327ms step_avg:216.34ms step:5883/6200 train_loss:3.3557 train_time:1270540ms step_avg:216.34ms step:5884/6200 train_loss:3.3861 train_time:1270754ms step_avg:216.34ms step:5885/6200 train_loss:3.3662 train_time:1270968ms step_avg:216.33ms step:5886/6200 train_loss:3.3163 train_time:1271182ms step_avg:216.33ms step:5887/6200 train_loss:3.6089 train_time:1271398ms step_avg:216.33ms step:5888/6200 train_loss:3.4109 train_time:1271611ms step_avg:216.33ms step:5889/6200 train_loss:3.3562 train_time:1271824ms step_avg:216.33ms step:5890/6200 train_loss:3.0724 train_time:1272301ms step_avg:216.38ms step:5891/6200 train_loss:3.3590 train_time:1272514ms step_avg:216.38ms step:5892/6200 train_loss:3.3070 train_time:1272727ms step_avg:216.38ms step:5893/6200 train_loss:3.0417 train_time:1272940ms step_avg:216.38ms step:5894/6200 train_loss:3.2018 train_time:1273154ms step_avg:216.38ms step:5895/6200 train_loss:3.3054 train_time:1273367ms step_avg:216.38ms step:5896/6200 train_loss:3.5443 train_time:1273582ms step_avg:216.37ms step:5897/6200 train_loss:3.3134 train_time:1273797ms step_avg:216.37ms step:5898/6200 train_loss:3.2249 train_time:1274010ms step_avg:216.37ms step:5899/6200 train_loss:3.2930 train_time:1274224ms step_avg:216.37ms step:5900/6200 train_loss:3.2102 train_time:1274439ms step_avg:216.37ms step:5901/6200 train_loss:3.1714 train_time:1274653ms step_avg:216.37ms step:5902/6200 train_loss:3.2396 train_time:1274866ms step_avg:216.37ms step:5903/6200 train_loss:3.4261 train_time:1275081ms step_avg:216.37ms step:5904/6200 train_loss:3.3320 train_time:1275297ms step_avg:216.37ms step:5905/6200 train_loss:3.2889 train_time:1275512ms step_avg:216.37ms step:5906/6200 train_loss:3.4370 train_time:1275725ms step_avg:216.37ms step:5907/6200 train_loss:3.3723 train_time:1275939ms step_avg:216.37ms step:5908/6200 train_loss:3.2852 train_time:1276153ms step_avg:216.37ms step:5909/6200 train_loss:3.7047 train_time:1276366ms step_avg:216.37ms step:5910/6200 train_loss:3.6089 train_time:1276581ms step_avg:216.37ms step:5911/6200 train_loss:3.3153 train_time:1276799ms step_avg:216.37ms step:5912/6200 train_loss:3.2240 train_time:1277013ms step_avg:216.37ms step:5913/6200 train_loss:3.4610 train_time:1277225ms step_avg:216.37ms step:5914/6200 train_loss:3.2671 train_time:1277439ms step_avg:216.37ms step:5915/6200 train_loss:3.4222 train_time:1277653ms step_avg:216.37ms step:5916/6200 train_loss:3.3013 train_time:1277866ms step_avg:216.37ms step:5917/6200 train_loss:3.3634 train_time:1278081ms step_avg:216.37ms step:5918/6200 train_loss:3.2083 train_time:1278294ms step_avg:216.37ms step:5919/6200 train_loss:3.3416 train_time:1278507ms step_avg:216.37ms step:5920/6200 train_loss:3.2272 train_time:1278719ms step_avg:216.37ms step:5921/6200 train_loss:3.4415 train_time:1278932ms step_avg:216.36ms step:5922/6200 train_loss:3.3219 train_time:1279146ms step_avg:216.36ms step:5923/6200 train_loss:3.3412 train_time:1279359ms step_avg:216.36ms step:5924/6200 train_loss:3.2411 train_time:1279575ms step_avg:216.36ms step:5925/6200 train_loss:3.3653 train_time:1279788ms step_avg:216.36ms step:5926/6200 train_loss:3.2364 train_time:1280001ms step_avg:216.36ms step:5927/6200 train_loss:3.2814 train_time:1280214ms step_avg:216.36ms step:5928/6200 train_loss:3.2991 train_time:1280426ms step_avg:216.36ms step:5929/6200 train_loss:3.4175 train_time:1280640ms step_avg:216.36ms step:5930/6200 train_loss:3.3148 train_time:1280854ms step_avg:216.36ms step:5931/6200 train_loss:3.4475 train_time:1281068ms step_avg:216.36ms step:5932/6200 train_loss:3.4433 train_time:1281282ms step_avg:216.36ms step:5933/6200 train_loss:3.0727 train_time:1281497ms step_avg:216.36ms step:5934/6200 train_loss:3.1975 train_time:1281711ms step_avg:216.36ms step:5935/6200 train_loss:3.2723 train_time:1281923ms step_avg:216.36ms step:5936/6200 train_loss:3.3375 train_time:1282137ms step_avg:216.36ms step:5937/6200 train_loss:3.1822 train_time:1282351ms step_avg:216.36ms step:5938/6200 train_loss:3.2682 train_time:1282565ms step_avg:216.36ms step:5939/6200 train_loss:3.3954 train_time:1282778ms step_avg:216.36ms step:5940/6200 train_loss:3.2965 train_time:1282993ms step_avg:216.36ms step:5941/6200 train_loss:3.2431 train_time:1283206ms step_avg:216.36ms step:5942/6200 train_loss:3.2353 train_time:1283419ms step_avg:216.36ms step:5943/6200 train_loss:3.2361 train_time:1283632ms step_avg:216.35ms step:5944/6200 train_loss:3.3392 train_time:1283846ms step_avg:216.35ms step:5945/6200 train_loss:3.2999 train_time:1284060ms step_avg:216.35ms step:5946/6200 train_loss:3.3061 train_time:1284274ms step_avg:216.35ms step:5947/6200 train_loss:3.2092 train_time:1284488ms step_avg:216.35ms step:5948/6200 train_loss:3.3591 train_time:1284702ms step_avg:216.35ms step:5949/6200 train_loss:3.4535 train_time:1284916ms step_avg:216.35ms step:5950/6200 train_loss:3.2448 train_time:1285128ms step_avg:216.35ms step:5951/6200 train_loss:3.2839 train_time:1285343ms step_avg:216.35ms step:5952/6200 train_loss:3.3186 train_time:1285558ms step_avg:216.35ms step:5953/6200 train_loss:3.4927 train_time:1285771ms step_avg:216.35ms step:5954/6200 train_loss:3.3046 train_time:1285984ms step_avg:216.35ms step:5955/6200 train_loss:3.1707 train_time:1286201ms step_avg:216.35ms step:5956/6200 train_loss:3.2401 train_time:1286415ms step_avg:216.35ms step:5957/6200 train_loss:3.3006 train_time:1286628ms step_avg:216.35ms step:5958/6200 train_loss:3.2489 train_time:1286842ms step_avg:216.35ms step:5959/6200 train_loss:3.3615 train_time:1287056ms step_avg:216.35ms step:5960/6200 train_loss:3.3350 train_time:1287269ms step_avg:216.35ms step:5961/6200 train_loss:3.3136 train_time:1287482ms step_avg:216.35ms step:5962/6200 train_loss:3.1380 train_time:1287699ms step_avg:216.35ms step:5963/6200 train_loss:3.2839 train_time:1287912ms step_avg:216.35ms step:5964/6200 train_loss:3.2965 train_time:1288125ms step_avg:216.35ms step:5965/6200 train_loss:3.1400 train_time:1288336ms step_avg:216.35ms step:5966/6200 train_loss:3.4801 train_time:1288549ms step_avg:216.34ms step:5967/6200 train_loss:3.1538 train_time:1288763ms step_avg:216.34ms step:5968/6200 train_loss:3.3033 train_time:1288978ms step_avg:216.34ms step:5969/6200 train_loss:3.2785 train_time:1289193ms step_avg:216.34ms step:5970/6200 train_loss:3.1859 train_time:1289406ms step_avg:216.34ms step:5971/6200 train_loss:3.1769 train_time:1289618ms step_avg:216.34ms step:5972/6200 train_loss:3.3111 train_time:1289831ms step_avg:216.34ms step:5973/6200 train_loss:3.4529 train_time:1290045ms step_avg:216.34ms step:5974/6200 train_loss:3.3299 train_time:1290259ms step_avg:216.34ms step:5975/6200 train_loss:3.1862 train_time:1290472ms step_avg:216.34ms step:5976/6200 train_loss:3.2193 train_time:1290686ms step_avg:216.34ms step:5977/6200 train_loss:3.2682 train_time:1290901ms step_avg:216.34ms step:5978/6200 train_loss:3.2622 train_time:1291115ms step_avg:216.34ms step:5979/6200 train_loss:3.2053 train_time:1291328ms step_avg:216.34ms step:5980/6200 train_loss:3.3735 train_time:1291541ms step_avg:216.34ms step:5981/6200 train_loss:3.3902 train_time:1291755ms step_avg:216.34ms step:5982/6200 train_loss:3.2350 train_time:1291968ms step_avg:216.34ms step:5983/6200 train_loss:3.2417 train_time:1292180ms step_avg:216.34ms step:5984/6200 train_loss:3.3356 train_time:1292395ms step_avg:216.34ms step:5985/6200 train_loss:3.2927 train_time:1292610ms step_avg:216.34ms step:5986/6200 train_loss:3.1946 train_time:1292822ms step_avg:216.34ms step:5987/6200 train_loss:3.2352 train_time:1293036ms step_avg:216.34ms step:5988/6200 train_loss:3.2304 train_time:1293249ms step_avg:216.33ms step:5989/6200 train_loss:3.3116 train_time:1293463ms step_avg:216.33ms step:5990/6200 train_loss:3.5188 train_time:1293677ms step_avg:216.33ms step:5991/6200 train_loss:3.1495 train_time:1293892ms step_avg:216.33ms step:5992/6200 train_loss:3.4208 train_time:1294105ms step_avg:216.33ms step:5993/6200 train_loss:3.2462 train_time:1294318ms step_avg:216.33ms step:5994/6200 train_loss:3.2683 train_time:1294531ms step_avg:216.33ms step:5995/6200 train_loss:3.3291 train_time:1294743ms step_avg:216.33ms step:5996/6200 train_loss:3.3655 train_time:1294959ms step_avg:216.33ms step:5997/6200 train_loss:3.3510 train_time:1295172ms step_avg:216.33ms step:5998/6200 train_loss:3.2598 train_time:1295386ms step_avg:216.33ms step:5999/6200 train_loss:3.1084 train_time:1295600ms step_avg:216.33ms step:6000/6200 train_loss:3.4383 train_time:1295813ms step_avg:216.33ms step:6000/6200 val_loss:3.2859 train_time:1295815ms step_avg:216.33ms step:6001/6200 train_loss:3.2563 train_time:1296031ms step_avg:216.33ms step:6002/6200 train_loss:3.3364 train_time:1296244ms step_avg:216.33ms step:6003/6200 train_loss:3.4883 train_time:1296458ms step_avg:216.33ms step:6004/6200 train_loss:3.2021 train_time:1296672ms step_avg:216.33ms step:6005/6200 train_loss:3.2926 train_time:1296885ms step_avg:216.33ms step:6006/6200 train_loss:3.2886 train_time:1297100ms step_avg:216.33ms step:6007/6200 train_loss:3.1867 train_time:1297313ms step_avg:216.33ms step:6008/6200 train_loss:3.4423 train_time:1297527ms step_avg:216.33ms step:6009/6200 train_loss:3.0972 train_time:1297740ms step_avg:216.33ms step:6010/6200 train_loss:3.7384 train_time:1297953ms step_avg:216.33ms step:6011/6200 train_loss:3.3082 train_time:1298168ms step_avg:216.33ms step:6012/6200 train_loss:3.3023 train_time:1298382ms step_avg:216.32ms step:6013/6200 train_loss:3.2909 train_time:1298595ms step_avg:216.32ms step:6014/6200 train_loss:3.3704 train_time:1298811ms step_avg:216.32ms step:6015/6200 train_loss:3.4034 train_time:1299024ms step_avg:216.32ms step:6016/6200 train_loss:3.3397 train_time:1299236ms step_avg:216.32ms step:6017/6200 train_loss:3.2677 train_time:1299449ms step_avg:216.32ms step:6018/6200 train_loss:3.2941 train_time:1299663ms step_avg:216.32ms step:6019/6200 train_loss:3.2797 train_time:1299877ms step_avg:216.32ms step:6020/6200 train_loss:3.3348 train_time:1300091ms step_avg:216.32ms step:6021/6200 train_loss:3.3764 train_time:1300305ms step_avg:216.32ms step:6022/6200 train_loss:3.2576 train_time:1300518ms step_avg:216.32ms step:6023/6200 train_loss:3.2438 train_time:1300731ms step_avg:216.32ms step:6024/6200 train_loss:3.2747 train_time:1300943ms step_avg:216.32ms step:6025/6200 train_loss:3.2670 train_time:1301156ms step_avg:216.32ms step:6026/6200 train_loss:3.3160 train_time:1301370ms step_avg:216.32ms step:6027/6200 train_loss:3.4594 train_time:1301583ms step_avg:216.32ms step:6028/6200 train_loss:3.3991 train_time:1301797ms step_avg:216.32ms step:6029/6200 train_loss:3.3153 train_time:1302012ms step_avg:216.32ms step:6030/6200 train_loss:3.1606 train_time:1302225ms step_avg:216.32ms step:6031/6200 train_loss:3.2263 train_time:1302437ms step_avg:216.32ms step:6032/6200 train_loss:3.2676 train_time:1302651ms step_avg:216.32ms step:6033/6200 train_loss:3.3088 train_time:1302864ms step_avg:216.31ms step:6034/6200 train_loss:3.3864 train_time:1303078ms step_avg:216.31ms step:6035/6200 train_loss:3.3939 train_time:1303292ms step_avg:216.31ms step:6036/6200 train_loss:3.2731 train_time:1303506ms step_avg:216.31ms step:6037/6200 train_loss:3.2066 train_time:1303719ms step_avg:216.31ms step:6038/6200 train_loss:3.2884 train_time:1303931ms step_avg:216.31ms step:6039/6200 train_loss:3.3134 train_time:1304145ms step_avg:216.31ms step:6040/6200 train_loss:3.2761 train_time:1304358ms step_avg:216.31ms step:6041/6200 train_loss:3.3490 train_time:1304572ms step_avg:216.31ms step:6042/6200 train_loss:3.2320 train_time:1304786ms step_avg:216.31ms step:6043/6200 train_loss:3.4061 train_time:1304999ms step_avg:216.31ms step:6044/6200 train_loss:3.2016 train_time:1305212ms step_avg:216.31ms step:6045/6200 train_loss:3.3465 train_time:1305426ms step_avg:216.31ms step:6046/6200 train_loss:3.2372 train_time:1305638ms step_avg:216.31ms step:6047/6200 train_loss:3.2600 train_time:1305852ms step_avg:216.31ms step:6048/6200 train_loss:3.2471 train_time:1306319ms step_avg:216.35ms step:6049/6200 train_loss:3.2116 train_time:1306531ms step_avg:216.35ms step:6050/6200 train_loss:3.2710 train_time:1306744ms step_avg:216.35ms step:6051/6200 train_loss:3.3700 train_time:1306957ms step_avg:216.35ms step:6052/6200 train_loss:3.6398 train_time:1307171ms step_avg:216.35ms step:6053/6200 train_loss:3.2930 train_time:1307385ms step_avg:216.35ms step:6054/6200 train_loss:3.2440 train_time:1307599ms step_avg:216.35ms step:6055/6200 train_loss:3.2426 train_time:1307813ms step_avg:216.35ms step:6056/6200 train_loss:3.2525 train_time:1308026ms step_avg:216.35ms step:6057/6200 train_loss:3.4726 train_time:1308239ms step_avg:216.35ms step:6058/6200 train_loss:3.2723 train_time:1308451ms step_avg:216.34ms step:6059/6200 train_loss:3.2688 train_time:1308665ms step_avg:216.34ms step:6060/6200 train_loss:3.2256 train_time:1308878ms step_avg:216.34ms step:6061/6200 train_loss:3.2979 train_time:1309092ms step_avg:216.34ms step:6062/6200 train_loss:3.3565 train_time:1309306ms step_avg:216.34ms step:6063/6200 train_loss:3.3001 train_time:1309519ms step_avg:216.34ms step:6064/6200 train_loss:3.3532 train_time:1309731ms step_avg:216.34ms step:6065/6200 train_loss:3.4568 train_time:1309944ms step_avg:216.34ms step:6066/6200 train_loss:3.1736 train_time:1310159ms step_avg:216.34ms step:6067/6200 train_loss:3.1589 train_time:1310372ms step_avg:216.34ms step:6068/6200 train_loss:3.3853 train_time:1310586ms step_avg:216.34ms step:6069/6200 train_loss:3.2834 train_time:1310800ms step_avg:216.34ms step:6070/6200 train_loss:3.3803 train_time:1311013ms step_avg:216.34ms step:6071/6200 train_loss:3.4159 train_time:1311225ms step_avg:216.34ms step:6072/6200 train_loss:3.3674 train_time:1311438ms step_avg:216.34ms step:6073/6200 train_loss:3.2605 train_time:1311650ms step_avg:216.34ms step:6074/6200 train_loss:3.3338 train_time:1311864ms step_avg:216.34ms step:6075/6200 train_loss:3.2664 train_time:1312078ms step_avg:216.34ms step:6076/6200 train_loss:3.5950 train_time:1312292ms step_avg:216.34ms step:6077/6200 train_loss:3.1955 train_time:1312506ms step_avg:216.34ms step:6078/6200 train_loss:3.2948 train_time:1312720ms step_avg:216.33ms step:6079/6200 train_loss:3.2556 train_time:1312931ms step_avg:216.33ms step:6080/6200 train_loss:3.4297 train_time:1313407ms step_avg:216.38ms step:6081/6200 train_loss:3.3494 train_time:1313622ms step_avg:216.38ms step:6082/6200 train_loss:3.8769 train_time:1313834ms step_avg:216.38ms step:6083/6200 train_loss:3.2027 train_time:1314048ms step_avg:216.38ms step:6084/6200 train_loss:3.9002 train_time:1314260ms step_avg:216.37ms step:6085/6200 train_loss:3.3379 train_time:1314473ms step_avg:216.37ms step:6086/6200 train_loss:3.3127 train_time:1314687ms step_avg:216.37ms step:6087/6200 train_loss:3.2997 train_time:1314901ms step_avg:216.37ms step:6088/6200 train_loss:3.1383 train_time:1315113ms step_avg:216.37ms step:6089/6200 train_loss:3.5241 train_time:1315327ms step_avg:216.37ms step:6090/6200 train_loss:3.3883 train_time:1315540ms step_avg:216.37ms step:6091/6200 train_loss:3.3727 train_time:1315753ms step_avg:216.37ms step:6092/6200 train_loss:3.4337 train_time:1315967ms step_avg:216.37ms step:6093/6200 train_loss:3.2162 train_time:1316180ms step_avg:216.37ms step:6094/6200 train_loss:3.3811 train_time:1316393ms step_avg:216.37ms step:6095/6200 train_loss:3.0928 train_time:1316608ms step_avg:216.37ms step:6096/6200 train_loss:3.3005 train_time:1316821ms step_avg:216.37ms step:6097/6200 train_loss:3.4046 train_time:1317033ms step_avg:216.37ms step:6098/6200 train_loss:3.3698 train_time:1317249ms step_avg:216.37ms step:6099/6200 train_loss:3.2303 train_time:1317462ms step_avg:216.37ms step:6100/6200 train_loss:3.6456 train_time:1317675ms step_avg:216.37ms step:6101/6200 train_loss:3.5677 train_time:1317890ms step_avg:216.37ms step:6102/6200 train_loss:3.3003 train_time:1318104ms step_avg:216.37ms step:6103/6200 train_loss:3.3001 train_time:1318316ms step_avg:216.37ms step:6104/6200 train_loss:3.2669 train_time:1318531ms step_avg:216.37ms step:6105/6200 train_loss:3.1965 train_time:1318744ms step_avg:216.36ms step:6106/6200 train_loss:3.3805 train_time:1318959ms step_avg:216.36ms step:6107/6200 train_loss:3.2488 train_time:1319175ms step_avg:216.36ms step:6108/6200 train_loss:3.1402 train_time:1319390ms step_avg:216.36ms step:6109/6200 train_loss:3.7032 train_time:1319603ms step_avg:216.36ms step:6110/6200 train_loss:3.2953 train_time:1319817ms step_avg:216.36ms step:6111/6200 train_loss:3.3276 train_time:1320030ms step_avg:216.36ms step:6112/6200 train_loss:3.1847 train_time:1320244ms step_avg:216.36ms step:6113/6200 train_loss:3.2556 train_time:1320457ms step_avg:216.36ms step:6114/6200 train_loss:3.3987 train_time:1320671ms step_avg:216.36ms step:6115/6200 train_loss:3.2670 train_time:1320885ms step_avg:216.36ms step:6116/6200 train_loss:3.7244 train_time:1321099ms step_avg:216.36ms step:6117/6200 train_loss:3.2926 train_time:1321313ms step_avg:216.36ms step:6118/6200 train_loss:3.2859 train_time:1321526ms step_avg:216.36ms step:6119/6200 train_loss:3.2697 train_time:1321738ms step_avg:216.36ms step:6120/6200 train_loss:3.4300 train_time:1321952ms step_avg:216.36ms step:6121/6200 train_loss:3.3077 train_time:1322166ms step_avg:216.36ms step:6122/6200 train_loss:3.4947 train_time:1322379ms step_avg:216.36ms step:6123/6200 train_loss:3.2412 train_time:1322593ms step_avg:216.36ms step:6124/6200 train_loss:3.3157 train_time:1322807ms step_avg:216.36ms step:6125/6200 train_loss:3.3238 train_time:1323020ms step_avg:216.36ms step:6125/6200 val_loss:3.2802 train_time:1323022ms step_avg:216.36ms step:6126/6200 train_loss:3.2568 train_time:1323244ms step_avg:216.36ms step:6127/6200 train_loss:4.5325 train_time:1323456ms step_avg:216.36ms step:6128/6200 train_loss:3.2747 train_time:1323669ms step_avg:216.36ms step:6129/6200 train_loss:3.3087 train_time:1323882ms step_avg:216.36ms step:6130/6200 train_loss:3.2617 train_time:1324097ms step_avg:216.36ms step:6131/6200 train_loss:3.1381 train_time:1324311ms step_avg:216.36ms step:6132/6200 train_loss:3.4426 train_time:1324525ms step_avg:216.35ms step:6133/6200 train_loss:3.3878 train_time:1324737ms step_avg:216.35ms step:6134/6200 train_loss:3.2624 train_time:1324951ms step_avg:216.35ms step:6135/6200 train_loss:3.2912 train_time:1325163ms step_avg:216.35ms step:6136/6200 train_loss:3.5043 train_time:1325376ms step_avg:216.35ms step:6137/6200 train_loss:3.2754 train_time:1325590ms step_avg:216.35ms step:6138/6200 train_loss:3.2089 train_time:1325809ms step_avg:216.35ms step:6139/6200 train_loss:3.2586 train_time:1326023ms step_avg:216.35ms step:6140/6200 train_loss:3.7207 train_time:1326237ms step_avg:216.35ms step:6141/6200 train_loss:3.3568 train_time:1326451ms step_avg:216.35ms step:6142/6200 train_loss:3.2233 train_time:1326664ms step_avg:216.35ms step:6143/6200 train_loss:3.1990 train_time:1326877ms step_avg:216.35ms step:6144/6200 train_loss:3.2736 train_time:1327090ms step_avg:216.35ms step:6145/6200 train_loss:3.3465 train_time:1327305ms step_avg:216.35ms step:6146/6200 train_loss:3.3031 train_time:1327518ms step_avg:216.35ms step:6147/6200 train_loss:3.3575 train_time:1327733ms step_avg:216.35ms step:6148/6200 train_loss:3.2961 train_time:1327946ms step_avg:216.35ms step:6149/6200 train_loss:3.1005 train_time:1328159ms step_avg:216.35ms step:6150/6200 train_loss:3.5433 train_time:1328373ms step_avg:216.35ms step:6151/6200 train_loss:3.3553 train_time:1328586ms step_avg:216.35ms step:6152/6200 train_loss:3.1785 train_time:1328799ms step_avg:216.35ms step:6153/6200 train_loss:3.2544 train_time:1329014ms step_avg:216.35ms step:6154/6200 train_loss:3.2698 train_time:1329228ms step_avg:216.35ms step:6155/6200 train_loss:3.2798 train_time:1329441ms step_avg:216.35ms step:6156/6200 train_loss:3.1662 train_time:1329654ms step_avg:216.34ms step:6157/6200 train_loss:3.3030 train_time:1329867ms step_avg:216.34ms step:6158/6200 train_loss:3.4019 train_time:1330080ms step_avg:216.34ms step:6159/6200 train_loss:3.4745 train_time:1330294ms step_avg:216.34ms step:6160/6200 train_loss:3.3131 train_time:1330508ms step_avg:216.34ms step:6161/6200 train_loss:3.2929 train_time:1330721ms step_avg:216.34ms step:6162/6200 train_loss:3.3338 train_time:1330939ms step_avg:216.34ms step:6163/6200 train_loss:3.3137 train_time:1331153ms step_avg:216.34ms step:6164/6200 train_loss:3.4035 train_time:1331365ms step_avg:216.34ms step:6165/6200 train_loss:3.1539 train_time:1331577ms step_avg:216.34ms step:6166/6200 train_loss:3.2721 train_time:1331792ms step_avg:216.34ms step:6167/6200 train_loss:3.4446 train_time:1332007ms step_avg:216.34ms step:6168/6200 train_loss:3.2282 train_time:1332220ms step_avg:216.34ms step:6169/6200 train_loss:3.1435 train_time:1332435ms step_avg:216.34ms step:6170/6200 train_loss:3.3260 train_time:1332648ms step_avg:216.34ms step:6171/6200 train_loss:3.4670 train_time:1332865ms step_avg:216.34ms step:6172/6200 train_loss:3.3121 train_time:1333079ms step_avg:216.34ms step:6173/6200 train_loss:3.3627 train_time:1333293ms step_avg:216.34ms step:6174/6200 train_loss:3.2451 train_time:1333506ms step_avg:216.34ms step:6175/6200 train_loss:3.3978 train_time:1333720ms step_avg:216.34ms step:6176/6200 train_loss:3.4608 train_time:1333940ms step_avg:216.34ms step:6177/6200 train_loss:3.2988 train_time:1334153ms step_avg:216.34ms step:6178/6200 train_loss:3.1409 train_time:1334365ms step_avg:216.34ms step:6179/6200 train_loss:3.2435 train_time:1334579ms step_avg:216.34ms step:6180/6200 train_loss:3.4250 train_time:1334793ms step_avg:216.34ms step:6181/6200 train_loss:3.5023 train_time:1335006ms step_avg:216.34ms step:6182/6200 train_loss:3.2874 train_time:1335218ms step_avg:216.33ms step:6183/6200 train_loss:3.2291 train_time:1335433ms step_avg:216.33ms step:6184/6200 train_loss:3.3585 train_time:1335647ms step_avg:216.33ms step:6185/6200 train_loss:3.4161 train_time:1335859ms step_avg:216.33ms step:6186/6200 train_loss:3.2621 train_time:1336073ms step_avg:216.33ms step:6187/6200 train_loss:3.2441 train_time:1336285ms step_avg:216.33ms step:6188/6200 train_loss:3.3405 train_time:1336499ms step_avg:216.33ms step:6189/6200 train_loss:3.2679 train_time:1336715ms step_avg:216.33ms step:6190/6200 train_loss:3.3724 train_time:1336929ms step_avg:216.33ms step:6191/6200 train_loss:3.4871 train_time:1337142ms step_avg:216.33ms step:6192/6200 train_loss:3.1770 train_time:1337355ms step_avg:216.33ms step:6193/6200 train_loss:3.4507 train_time:1337567ms step_avg:216.33ms step:6194/6200 train_loss:3.3755 train_time:1337781ms step_avg:216.33ms step:6195/6200 train_loss:3.4641 train_time:1337996ms step_avg:216.33ms step:6196/6200 train_loss:3.3158 train_time:1338213ms step_avg:216.33ms step:6197/6200 train_loss:3.2988 train_time:1338427ms step_avg:216.33ms step:6198/6200 train_loss:3.5308 train_time:1338639ms step_avg:216.33ms step:6199/6200 train_loss:3.2344 train_time:1338853ms step_avg:216.33ms step:6200/6200 train_loss:3.2533 train_time:1339065ms step_avg:216.33ms step:6200/6200 val_loss:3.2785 train_time:1339067ms step_avg:216.33ms