==================================================================================================== #loader.py ### canonically ### torchrun --standalone --nproc_per_node=8 loader.py ### but for us, probably ### set USE_LIBUV=0 ### set RANK ### set TORCH_CUDNN_SDPA_ENABLED=1 ### torchrun --standalone --nproc_per_node=1 loader.py 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 import bitsandbytes as bnb 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 import pgptlformer ### modded-nanogpt distributed dataset loader # ----------------------------------------------------------------------------- # their 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() # ----------------------------------------------------------------------------- # downgrade to poor man's data loader: # maybe superfluous bc distributed data loader started working # delete? [ ] def get_batch(split): # We recreate np.memmap every batch to avoid a memory leak, as per # https://stackoverflow.com/questions/45132940/numpy-memmap-memory-usage-want-to-iterate-once/61472122#61472122 block_size = args.sequence_length batch_size = args.batch_size if split == 'train': data = np.memmap(os.path.join(data_dir, 'train.bin'), dtype=np.uint16, mode='r') else: data = np.memmap(os.path.join(data_dir, 'val.bin'), dtype=np.uint16, mode='r') ix = torch.randint(len(data) - block_size, (batch_size,)) x = torch.stack([torch.from_numpy((data[i:i+block_size]).astype(np.int64)) for i in ix]) y = torch.stack([torch.from_numpy((data[i+1:i+1+block_size]).astype(np.int64)) for i in ix]) if device_type == 'cuda': # pin arrays x,y, which allows us to move them to GPU asynchronously (non_blocking=True) x, y = x.pin_memory().to(device, non_blocking=True), y.pin_memory().to(device, non_blocking=True) else: x, y = x.to(device), y.to(device) return x, y ### modded-nanogpt ### either 24/16*20=30 batches per 4090 or 24/32*20=15 batches per 4090, ### depending on what kind of v100 tinystories used. @dataclass class Hyperparameters: # data hyperparams input_bin : str = 'data/TinyStoriesV2-GPT4/tinystories-gpt4_train_*.bin' # input .bin to train on input_val_bin : str = 'data/TinyStoriesV2-GPT4/tinystories-gpt4_val_*.bin' # input .bin to eval validation loss on # optimization hyperparams batch_size : int = 4*32 # macrobatch size, in sequences, across all devices device_batch_size : int = 32 # batch size, in sequences, per device. try to increase/decrease by powers of 2 sequence_length : int = 512 # sequence length, in tokens num_iterations : int = 6250 # number of iterations to run attack : int = 40 # 2*(1-betas)^-1 release : int = 256 # number of iterations of linear warmup/warmdown for triangular or trapezoidal schedule weight_decay : float = 0 # evaluation and logging hyperparams val_loss_every : int = 2000 # every how many steps to evaluate val loss? 0 for only at the end val_tokens : int = 5242880 # 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 run_name : str = "dyn_qkrmsnorm" # supercompute boilerplate ddp_run : bool = False #this stuff is so nyannoying device = "cuda" # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1' etc., or try 'mps' on macbooks torch_compile = False #hahahaha args = Hyperparameters() # convenience variables B, T = args.device_batch_size, args.sequence_length # set up DDP (distributed data parallel). torchrun sets this env variable assert torch.cuda.is_available() if args.ddp_run == True: 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. else: # if not ddp, we are running on a single gpu, and one process master_process = True seed_offset = 0 ddp_world_size = 1 ddp_rank = 0 device = args.device #tokens_per_iter = train_accumulation_steps * ddp_world_size * batch_size * block_size #print(f"tokens per iteration will be: {tokens_per_iter:,}") # 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() if master_process: print("Building model...") #tinystories #num_vocab=50304 for non-tinystories models #qknorm="identitynorm" for nonqknorm models layer_prefab = {"dim":256,"dim_head":32,"headcount":8,"ff_mult":4, "lambda":True,"layerwisenorm":"rmsnorm","qknorm":"dynamic_shape_rmsnorm", "training_seqlen":args.sequence_length} #global_prefab = {"vocab_size":8192, "num_layers":4} #weird errors global_prefab = {"vocab_size":50304, "num_layers":4} config = {} config.update(layer_prefab) config.update(global_prefab) model = pgptlformer.PGPT_Lformer(config) if hasattr(config, "coordinate_descent_tuning"): config.coordinate_descent_tuning = True # suggested by @Chillee model = model.to(device) if args.torch_compile: model = torch.compile(model) # here we wrap model into DDP container if args.ddp_run: model = DDP(model, device_ids=[ddp_local_rank]) #raw_model = model.modules() # always contains the "raw" unwrapped model ctx = torch.amp.autocast(device_type='cuda', dtype=torch.bfloat16) if master_process: print("Model built.") # CUDNN attention is ~4ms faster than Flash, but doesn't get selected by default in PyTorch 2.5.1 from torch.backends.cuda import enable_cudnn_sdp, enable_flash_sdp, enable_math_sdp, enable_mem_efficient_sdp enable_cudnn_sdp(True) enable_flash_sdp(True) enable_mem_efficient_sdp(True) enable_math_sdp(False) # modded-nanogpt optimizer inits adam1 = torch.optim.Adam([model.lambdaformer.what_the_embedder_doin.weight], lr=0.3, betas=(0.9, 0.95) ) adam2 = torch.optim.Adam([model.tokenpicker_head.weight], lr=0.002, betas=(0.9, 0.95) ) params = list(model.lambdaformer.blocks.parameters()) matrix_params = [p for p in params if p.ndim == 2] scalar_params = [p for p in params if p.ndim < 2] adam3 = bnb.optim.Adam8bit(matrix_params, lr=0.02, betas=(0.9, 0.95) ) #tune this, sensitive adam4 = bnb.optim.Adam8bit(scalar_params, lr=0.02, betas=(0.9, 0.95) ) #???, less sensitive optim_ensemble = [adam1, adam2, adam3, adam4] # lr scheduler def get_ASR_env(it): assert it <= args.num_iterations # A) the famous linear warmup back at it again if it < args.attack: return (it+1) / args.attack # S) constant sustain elif it < args.num_iterations - args.release: return 1.0 # R) release else: release_ratio = (args.num_iterations - it) / args.release return release_ratio schedulers = [torch.optim.lr_scheduler.LambdaLR(opt, get_ASR_env) for opt in optim_ensemble] # begin logging if master_process: run_id = str(uuid.uuid4()) if args.run_name is not None: sep="-" run_id = sep.join([args.run_name, run_id]) logdir = 'logs/%s/' % run_id os.makedirs(logdir, exist_ok=True) logfile = 'logs/%s.txt' % run_id # create the log file with open(logfile, "w") as f: # begin the log by printing this file (the Python code) f.write('='*100 + '\n') f.write(code) f.write('='*100 + '\n') # log information about the hardware/software environment this is running on # and print the full `nvidia-smi` to file f.write(f"Running pytorch {torch.version.__version__} compiled for CUDA {torch.version.cuda}\nnvidia-smi:\n") import subprocess result = subprocess.run(['nvidia-smi'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True) f.write(f'{result.stdout}\n') f.write('='*100 + '\n') training_time_ms = 0 # start the clock torch.cuda.synchronize() t0 = time.time() # begin training train_loader.reset() for step in range(args.num_iterations + 1): last_step = (step == args.num_iterations) # This effectively ignores timing first 10 steps, which are slower for weird reasons. # Alternately, and slightly more correctly in terms of benchmarking, we could do 10 # steps with dummy data first, and then re-initialize the model and reset the loader. if step == 10: training_time_ms = 0 t0 = time.time() timed_steps = float('nan') if step <= 11 else (step - 10) + 1 # <= 11 to avoid bug in val # once in a while evaluate the validation dataset if (last_step or (args.val_loss_every > 0 and step % args.val_loss_every == 0)): # stop the clock torch.cuda.synchronize() training_time_ms += 1000 * (time.time() - t0) # run validation batches model.eval() val_loader.reset() val_loss = 0.0 for _ in range(val_steps): x_val, y_val = val_loader.next_batch() with ctx: # of course, we'd like to use no_grad() here too, but that creates a torch.compile error for some reason _, loss = model(x_val, y_val, return_logits=False) val_loss += loss.detach() del loss if args.ddp_run: 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=model.state_dict(), model_args=config, optim_ensemble=[opt.state_dict() for opt in optim_ensemble]) 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 # --- train time --- 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 args.ddp_run: 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(): #grad accum normalization? p.grad /= train_accumulation_steps # skip muon momentum warmup since we're adaming it #... # step the optimizers and schedulers for opt, sched in zip(optim_ensemble, schedulers): opt.step() sched.step() # null the gradients model.zero_grad(set_to_none=True) # --- train time is already over --- #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 if args.ddp_run: dist.destroy_process_group()==================================================================================================== Running pytorch 2.4.0+cu124 compiled for CUDA 12.4 nvidia-smi: Sat Jan 25 19:06:51 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 551.61 Driver Version: 551.61 CUDA Version: 12.4 | |-----------------------------------------+------------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 4090 WDDM | 00000000:01:00.0 On | Off | | 30% 40C P2 66W / 350W | 3571MiB / 24564MiB | 10% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 15616 C+G C:\Program Files\VSCodium\VSCodium.exe N/A | | 0 N/A N/A 15884 C+G ...aming\Telegram Desktop\Telegram.exe N/A | | 0 N/A N/A 16300 C+G ...B\system_tray\lghub_system_tray.exe N/A | | 0 N/A N/A 32740 C+G ....Search_cw5n1h2txyewy\SearchApp.exe N/A | | 0 N/A N/A 35272 C+G ...a\Local\Mozilla Firefox\firefox.exe N/A | | 0 N/A N/A 41308 C+G C:\Windows\explorer.exe N/A | | 0 N/A N/A 42544 C+G ...IP STUDIO PAINT\CLIPStudioPaint.exe N/A | | 0 N/A N/A 49400 C+G ...al\Discord\app-1.0.9179\Discord.exe N/A | | 0 N/A N/A 62540 C+G ...1.0_x64__8wekyb3d8bbwe\Video.UI.exe N/A | | 0 N/A N/A 68380 C ...rograms\Python\Python310\python.exe N/A | | 0 N/A N/A 73872 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A | | 0 N/A N/A 80476 C+G C:\Hydrus\client.exe N/A | | 0 N/A N/A 81528 C+G ...les (x86)\foobar2000\foobar2000.exe N/A | | 0 N/A N/A 84480 C+G ...siveControlPanel\SystemSettings.exe N/A | | 0 N/A N/A 84668 C+G ...64__8wekyb3d8bbwe\CalculatorApp.exe N/A | | 0 N/A N/A 85528 C+G ...CBS_cw5n1h2txyewy\TextInputHost.exe N/A | | 0 N/A N/A 94588 C+G ...\cef\cef.win7x64\steamwebhelper.exe N/A | | 0 N/A N/A 100784 C+G ...cal\Microsoft\OneDrive\OneDrive.exe N/A | | 0 N/A N/A 104652 C+G ...0\Ultimate Admiral Dreadnoughts.exe N/A | | 0 N/A N/A 117496 C+G ...t.LockApp_cw5n1h2txyewy\LockApp.exe N/A | +-----------------------------------------------------------------------------------------+ ==================================================================================================== step:0/6250 val_loss:10.8259 train_time:84ms step_avg:nanms step:1/6250 train_loss:10.8258 train_time:648ms step_avg:nanms step:2/6250 train_loss:10.8205 train_time:1048ms step_avg:nanms step:3/6250 train_loss:10.7995 train_time:1447ms step_avg:nanms step:4/6250 train_loss:10.7456 train_time:1848ms step_avg:nanms step:5/6250 train_loss:10.6662 train_time:2245ms step_avg:nanms step:6/6250 train_loss:10.5760 train_time:2645ms step_avg:nanms step:7/6250 train_loss:10.4587 train_time:3045ms step_avg:nanms step:8/6250 train_loss:10.3224 train_time:3441ms step_avg:nanms step:9/6250 train_loss:10.1588 train_time:3840ms step_avg:nanms step:10/6250 train_loss:9.9677 train_time:4237ms step_avg:nanms step:11/6250 train_loss:9.7664 train_time:398ms step_avg:nanms step:12/6250 train_loss:9.5413 train_time:792ms step_avg:nanms step:13/6250 train_loss:9.2948 train_time:1191ms step_avg:397.08ms step:14/6250 train_loss:9.0391 train_time:1589ms step_avg:397.31ms step:15/6250 train_loss:8.7813 train_time:1989ms step_avg:397.89ms step:16/6250 train_loss:8.5072 train_time:2391ms step_avg:398.43ms step:17/6250 train_loss:8.2239 train_time:2789ms step_avg:398.39ms step:18/6250 train_loss:7.9609 train_time:3185ms step_avg:398.18ms step:19/6250 train_loss:7.7049 train_time:3584ms step_avg:398.27ms step:20/6250 train_loss:7.4483 train_time:3985ms step_avg:398.53ms step:21/6250 train_loss:7.2281 train_time:4381ms step_avg:398.32ms step:22/6250 train_loss:7.0157 train_time:4783ms step_avg:398.56ms step:23/6250 train_loss:6.8651 train_time:5190ms step_avg:399.22ms step:24/6250 train_loss:6.6069 train_time:5588ms step_avg:399.14ms step:25/6250 train_loss:6.5109 train_time:6020ms step_avg:401.34ms step:26/6250 train_loss:6.3153 train_time:6455ms step_avg:403.44ms step:27/6250 train_loss:6.2421 train_time:6881ms step_avg:404.77ms step:28/6250 train_loss:6.1831 train_time:7301ms step_avg:405.62ms step:29/6250 train_loss:6.0572 train_time:7728ms step_avg:406.75ms step:30/6250 train_loss:5.9984 train_time:8154ms step_avg:407.72ms step:31/6250 train_loss:5.8712 train_time:8561ms step_avg:407.68ms step:32/6250 train_loss:5.7786 train_time:8970ms step_avg:407.73ms step:33/6250 train_loss:5.7132 train_time:9369ms step_avg:407.35ms step:34/6250 train_loss:5.6255 train_time:9768ms step_avg:407.01ms step:35/6250 train_loss:5.6377 train_time:10189ms step_avg:407.58ms step:36/6250 train_loss:5.6245 train_time:10607ms step_avg:407.95ms step:37/6250 train_loss:5.4088 train_time:11023ms step_avg:408.24ms step:38/6250 train_loss:5.2760 train_time:11434ms step_avg:408.35ms step:39/6250 train_loss:5.1674 train_time:11837ms step_avg:408.16ms step:40/6250 train_loss:5.1650 train_time:12241ms step_avg:408.02ms step:41/6250 train_loss:5.1094 train_time:12643ms step_avg:407.83ms step:42/6250 train_loss:4.9979 train_time:13047ms step_avg:407.71ms step:43/6250 train_loss:5.0124 train_time:13450ms step_avg:407.57ms step:44/6250 train_loss:4.9037 train_time:13853ms step_avg:407.44ms step:45/6250 train_loss:4.8449 train_time:14252ms step_avg:407.20ms step:46/6250 train_loss:4.6674 train_time:14652ms step_avg:407.00ms step:47/6250 train_loss:4.6168 train_time:15052ms step_avg:406.81ms step:48/6250 train_loss:4.6249 train_time:15452ms step_avg:406.64ms step:49/6250 train_loss:4.5035 train_time:15856ms step_avg:406.57ms step:50/6250 train_loss:4.5117 train_time:16264ms step_avg:406.61ms step:51/6250 train_loss:4.4788 train_time:16673ms step_avg:406.67ms step:52/6250 train_loss:4.3937 train_time:17071ms step_avg:406.44ms step:53/6250 train_loss:4.3557 train_time:17471ms step_avg:406.29ms step:54/6250 train_loss:4.2551 train_time:17876ms step_avg:406.26ms step:55/6250 train_loss:4.3070 train_time:18276ms step_avg:406.13ms step:56/6250 train_loss:4.2308 train_time:18675ms step_avg:405.97ms step:57/6250 train_loss:4.2479 train_time:19074ms step_avg:405.83ms step:58/6250 train_loss:4.2177 train_time:19471ms step_avg:405.64ms step:59/6250 train_loss:4.1888 train_time:19878ms step_avg:405.68ms step:60/6250 train_loss:4.0998 train_time:20276ms step_avg:405.51ms step:61/6250 train_loss:4.1449 train_time:20676ms step_avg:405.40ms step:62/6250 train_loss:4.1815 train_time:21081ms step_avg:405.41ms step:63/6250 train_loss:4.0622 train_time:21512ms step_avg:405.89ms step:64/6250 train_loss:3.9787 train_time:21928ms step_avg:406.08ms step:65/6250 train_loss:4.0437 train_time:22328ms step_avg:405.96ms step:66/6250 train_loss:4.0378 train_time:22729ms step_avg:405.87ms step:67/6250 train_loss:4.0590 train_time:23131ms step_avg:405.80ms step:68/6250 train_loss:3.9920 train_time:23527ms step_avg:405.63ms step:69/6250 train_loss:3.9812 train_time:23929ms step_avg:405.58ms step:70/6250 train_loss:4.0430 train_time:24330ms step_avg:405.51ms step:71/6250 train_loss:3.9668 train_time:24734ms step_avg:405.47ms step:72/6250 train_loss:3.9072 train_time:25138ms step_avg:405.45ms step:73/6250 train_loss:3.8840 train_time:25542ms step_avg:405.43ms step:74/6250 train_loss:3.8941 train_time:25946ms step_avg:405.41ms step:75/6250 train_loss:3.8034 train_time:26351ms step_avg:405.40ms step:76/6250 train_loss:3.9819 train_time:26754ms step_avg:405.36ms step:77/6250 train_loss:3.8661 train_time:27157ms step_avg:405.33ms step:78/6250 train_loss:3.8777 train_time:27559ms step_avg:405.28ms step:79/6250 train_loss:3.8463 train_time:27965ms step_avg:405.29ms step:80/6250 train_loss:3.8388 train_time:28370ms step_avg:405.28ms step:81/6250 train_loss:3.7534 train_time:28772ms step_avg:405.25ms step:82/6250 train_loss:3.7731 train_time:29175ms step_avg:405.21ms step:83/6250 train_loss:3.7740 train_time:29576ms step_avg:405.15ms step:84/6250 train_loss:3.8524 train_time:29978ms step_avg:405.11ms step:85/6250 train_loss:3.9209 train_time:30383ms step_avg:405.10ms step:86/6250 train_loss:3.7547 train_time:30784ms step_avg:405.05ms step:87/6250 train_loss:3.7407 train_time:31183ms step_avg:404.98ms step:88/6250 train_loss:3.7431 train_time:31586ms step_avg:404.95ms step:89/6250 train_loss:3.7135 train_time:31991ms step_avg:404.95ms step:90/6250 train_loss:3.7742 train_time:32396ms step_avg:404.95ms step:91/6250 train_loss:3.7581 train_time:32800ms step_avg:404.94ms step:92/6250 train_loss:3.7661 train_time:33202ms step_avg:404.91ms step:93/6250 train_loss:3.7067 train_time:33604ms step_avg:404.86ms step:94/6250 train_loss:3.7076 train_time:34005ms step_avg:404.82ms step:95/6250 train_loss:3.6626 train_time:34408ms step_avg:404.80ms step:96/6250 train_loss:3.7563 train_time:34809ms step_avg:404.75ms step:97/6250 train_loss:3.6902 train_time:35211ms step_avg:404.72ms step:98/6250 train_loss:3.7119 train_time:35611ms step_avg:404.67ms step:99/6250 train_loss:3.7147 train_time:36013ms step_avg:404.65ms step:100/6250 train_loss:3.5716 train_time:36418ms step_avg:404.64ms step:101/6250 train_loss:3.7463 train_time:36819ms step_avg:404.60ms step:102/6250 train_loss:3.7008 train_time:37223ms step_avg:404.60ms step:103/6250 train_loss:3.6914 train_time:37624ms step_avg:404.56ms step:104/6250 train_loss:3.6477 train_time:38025ms step_avg:404.52ms step:105/6250 train_loss:3.5483 train_time:38427ms step_avg:404.50ms step:106/6250 train_loss:3.5791 train_time:38831ms step_avg:404.49ms step:107/6250 train_loss:3.6859 train_time:39236ms step_avg:404.50ms step:108/6250 train_loss:3.7017 train_time:39643ms step_avg:404.52ms step:109/6250 train_loss:3.7413 train_time:40049ms step_avg:404.53ms step:110/6250 train_loss:3.5576 train_time:40451ms step_avg:404.51ms step:111/6250 train_loss:3.6332 train_time:40850ms step_avg:404.45ms step:112/6250 train_loss:3.6456 train_time:41250ms step_avg:404.41ms step:113/6250 train_loss:3.5208 train_time:41652ms step_avg:404.39ms step:114/6250 train_loss:3.6329 train_time:42052ms step_avg:404.35ms step:115/6250 train_loss:3.6096 train_time:42456ms step_avg:404.34ms step:116/6250 train_loss:3.6488 train_time:42857ms step_avg:404.31ms step:117/6250 train_loss:3.6334 train_time:43258ms step_avg:404.28ms step:118/6250 train_loss:3.6585 train_time:43667ms step_avg:404.33ms step:119/6250 train_loss:3.5793 train_time:44083ms step_avg:404.43ms step:120/6250 train_loss:3.6235 train_time:44489ms step_avg:404.45ms step:121/6250 train_loss:3.5871 train_time:44899ms step_avg:404.50ms step:122/6250 train_loss:3.6067 train_time:45301ms step_avg:404.47ms step:123/6250 train_loss:3.5297 train_time:45707ms step_avg:404.49ms step:124/6250 train_loss:3.6274 train_time:46118ms step_avg:404.55ms step:125/6250 train_loss:3.5442 train_time:46526ms step_avg:404.58ms step:126/6250 train_loss:3.5322 train_time:46934ms step_avg:404.61ms step:127/6250 train_loss:3.5354 train_time:47341ms step_avg:404.63ms step:128/6250 train_loss:3.4965 train_time:47750ms step_avg:404.66ms step:129/6250 train_loss:3.5755 train_time:48159ms step_avg:404.70ms step:130/6250 train_loss:3.5015 train_time:48571ms step_avg:404.76ms step:131/6250 train_loss:3.5110 train_time:48985ms step_avg:404.84ms step:132/6250 train_loss:3.4786 train_time:49388ms step_avg:404.82ms step:133/6250 train_loss:3.5976 train_time:49794ms step_avg:404.83ms step:134/6250 train_loss:3.6289 train_time:50197ms step_avg:404.82ms step:135/6250 train_loss:3.4229 train_time:50600ms step_avg:404.80ms step:136/6250 train_loss:3.5043 train_time:51008ms step_avg:404.83ms step:137/6250 train_loss:3.6073 train_time:51415ms step_avg:404.85ms step:138/6250 train_loss:3.4646 train_time:51829ms step_avg:404.91ms step:139/6250 train_loss:3.4337 train_time:52239ms step_avg:404.95ms step:140/6250 train_loss:3.5238 train_time:52649ms step_avg:404.99ms step:141/6250 train_loss:3.4454 train_time:53067ms step_avg:405.09ms step:142/6250 train_loss:3.5062 train_time:53493ms step_avg:405.25ms step:143/6250 train_loss:3.4623 train_time:53912ms step_avg:405.35ms step:144/6250 train_loss:3.5248 train_time:54313ms step_avg:405.32ms step:145/6250 train_loss:3.4804 train_time:54714ms step_avg:405.29ms step:146/6250 train_loss:3.4837 train_time:55120ms step_avg:405.29ms step:147/6250 train_loss:3.4755 train_time:55521ms step_avg:405.26ms step:148/6250 train_loss:3.6336 train_time:55921ms step_avg:405.23ms step:149/6250 train_loss:3.4676 train_time:56329ms step_avg:405.25ms step:150/6250 train_loss:3.4735 train_time:56729ms step_avg:405.21ms step:151/6250 train_loss:3.4608 train_time:57130ms step_avg:405.18ms step:152/6250 train_loss:3.4702 train_time:57528ms step_avg:405.13ms step:153/6250 train_loss:3.5097 train_time:57930ms step_avg:405.10ms step:154/6250 train_loss:3.4380 train_time:58332ms step_avg:405.08ms step:155/6250 train_loss:3.5263 train_time:58732ms step_avg:405.05ms step:156/6250 train_loss:3.4993 train_time:59135ms step_avg:405.03ms step:157/6250 train_loss:3.3676 train_time:59540ms step_avg:405.03ms step:158/6250 train_loss:3.4683 train_time:59940ms step_avg:405.00ms step:159/6250 train_loss:3.4641 train_time:60342ms step_avg:404.98ms step:160/6250 train_loss:3.3601 train_time:60744ms step_avg:404.96ms step:161/6250 train_loss:3.4592 train_time:61145ms step_avg:404.94ms step:162/6250 train_loss:3.4280 train_time:61549ms step_avg:404.93ms step:163/6250 train_loss:3.4195 train_time:61952ms step_avg:404.92ms step:164/6250 train_loss:3.4279 train_time:62356ms step_avg:404.91ms step:165/6250 train_loss:3.4048 train_time:62756ms step_avg:404.88ms step:166/6250 train_loss:3.3956 train_time:63159ms step_avg:404.87ms step:167/6250 train_loss:3.4129 train_time:63565ms step_avg:404.87ms step:168/6250 train_loss:3.4123 train_time:63965ms step_avg:404.84ms step:169/6250 train_loss:3.4167 train_time:64363ms step_avg:404.80ms step:170/6250 train_loss:3.4987 train_time:64765ms step_avg:404.78ms step:171/6250 train_loss:3.3526 train_time:65168ms step_avg:404.77ms step:172/6250 train_loss:3.4979 train_time:65571ms step_avg:404.76ms step:173/6250 train_loss:3.4027 train_time:65976ms step_avg:404.76ms step:174/6250 train_loss:3.4464 train_time:66381ms step_avg:404.76ms step:175/6250 train_loss:3.3268 train_time:66789ms step_avg:404.78ms step:176/6250 train_loss:3.3736 train_time:67191ms step_avg:404.77ms step:177/6250 train_loss:3.3508 train_time:67594ms step_avg:404.76ms step:178/6250 train_loss:3.2842 train_time:67995ms step_avg:404.73ms step:179/6250 train_loss:3.3765 train_time:68394ms step_avg:404.70ms step:180/6250 train_loss:3.4431 train_time:68795ms step_avg:404.67ms step:181/6250 train_loss:3.3746 train_time:69197ms step_avg:404.66ms step:182/6250 train_loss:3.4161 train_time:69601ms step_avg:404.66ms step:183/6250 train_loss:3.3741 train_time:70015ms step_avg:404.71ms step:184/6250 train_loss:3.4016 train_time:70413ms step_avg:404.67ms step:185/6250 train_loss:3.4371 train_time:70821ms step_avg:404.69ms step:186/6250 train_loss:3.2941 train_time:71219ms step_avg:404.65ms step:187/6250 train_loss:3.3899 train_time:71619ms step_avg:404.63ms step:188/6250 train_loss:3.3358 train_time:72020ms step_avg:404.60ms step:189/6250 train_loss:3.3763 train_time:72421ms step_avg:404.58ms step:190/6250 train_loss:3.4864 train_time:72822ms step_avg:404.57ms step:191/6250 train_loss:3.2912 train_time:73222ms step_avg:404.54ms step:192/6250 train_loss:3.2887 train_time:73623ms step_avg:404.52ms step:193/6250 train_loss:3.3309 train_time:74021ms step_avg:404.49ms step:194/6250 train_loss:3.3281 train_time:74423ms step_avg:404.47ms step:195/6250 train_loss:3.2690 train_time:74825ms step_avg:404.46ms step:196/6250 train_loss:3.3285 train_time:75226ms step_avg:404.44ms step:197/6250 train_loss:3.4211 train_time:75628ms step_avg:404.43ms step:198/6250 train_loss:3.3285 train_time:76030ms step_avg:404.42ms step:199/6250 train_loss:3.3425 train_time:76428ms step_avg:404.38ms step:200/6250 train_loss:3.3588 train_time:76832ms step_avg:404.38ms step:201/6250 train_loss:3.2553 train_time:77232ms step_avg:404.35ms step:202/6250 train_loss:3.2954 train_time:77634ms step_avg:404.34ms step:203/6250 train_loss:3.3948 train_time:78036ms step_avg:404.33ms step:204/6250 train_loss:3.3768 train_time:78438ms step_avg:404.32ms step:205/6250 train_loss:3.2732 train_time:78840ms step_avg:404.31ms step:206/6250 train_loss:3.2344 train_time:79239ms step_avg:404.28ms step:207/6250 train_loss:3.3574 train_time:79645ms step_avg:404.29ms step:208/6250 train_loss:3.2886 train_time:80046ms step_avg:404.27ms step:209/6250 train_loss:3.2621 train_time:80445ms step_avg:404.25ms step:210/6250 train_loss:3.2731 train_time:80846ms step_avg:404.23ms step:211/6250 train_loss:3.3363 train_time:81250ms step_avg:404.23ms step:212/6250 train_loss:3.3881 train_time:81651ms step_avg:404.22ms step:213/6250 train_loss:3.3285 train_time:82054ms step_avg:404.20ms step:214/6250 train_loss:3.3594 train_time:82451ms step_avg:404.17ms step:215/6250 train_loss:3.3566 train_time:82853ms step_avg:404.16ms step:216/6250 train_loss:3.3679 train_time:83255ms step_avg:404.15ms step:217/6250 train_loss:3.2809 train_time:83660ms step_avg:404.16ms step:218/6250 train_loss:3.1686 train_time:84085ms step_avg:404.26ms step:219/6250 train_loss:3.1742 train_time:84500ms step_avg:404.31ms step:220/6250 train_loss:3.2158 train_time:84922ms step_avg:404.39ms step:221/6250 train_loss:3.2463 train_time:85325ms step_avg:404.38ms step:222/6250 train_loss:3.2964 train_time:85729ms step_avg:404.38ms step:223/6250 train_loss:3.1995 train_time:86132ms step_avg:404.37ms step:224/6250 train_loss:3.2829 train_time:86536ms step_avg:404.37ms step:225/6250 train_loss:3.2550 train_time:86936ms step_avg:404.35ms step:226/6250 train_loss:3.2134 train_time:87334ms step_avg:404.32ms step:227/6250 train_loss:3.3536 train_time:87737ms step_avg:404.32ms step:228/6250 train_loss:3.2674 train_time:88138ms step_avg:404.30ms step:229/6250 train_loss:3.2907 train_time:88539ms step_avg:404.29ms step:230/6250 train_loss:3.2072 train_time:88939ms step_avg:404.27ms step:231/6250 train_loss:3.2707 train_time:89339ms step_avg:404.25ms step:232/6250 train_loss:3.4124 train_time:89738ms step_avg:404.23ms step:233/6250 train_loss:3.2133 train_time:90140ms step_avg:404.22ms step:234/6250 train_loss:3.3009 train_time:90542ms step_avg:404.20ms step:235/6250 train_loss:3.2571 train_time:90943ms step_avg:404.19ms step:236/6250 train_loss:3.1429 train_time:91342ms step_avg:404.17ms step:237/6250 train_loss:3.2116 train_time:91743ms step_avg:404.16ms step:238/6250 train_loss:3.2598 train_time:92141ms step_avg:404.13ms step:239/6250 train_loss:3.2416 train_time:92543ms step_avg:404.12ms step:240/6250 train_loss:3.2662 train_time:92944ms step_avg:404.11ms step:241/6250 train_loss:3.3052 train_time:93345ms step_avg:404.09ms step:242/6250 train_loss:3.2329 train_time:93743ms step_avg:404.06ms step:243/6250 train_loss:3.2112 train_time:94141ms step_avg:404.04ms step:244/6250 train_loss:3.2130 train_time:94541ms step_avg:404.02ms step:245/6250 train_loss:3.2242 train_time:94942ms step_avg:404.01ms step:246/6250 train_loss:3.2301 train_time:95340ms step_avg:403.98ms step:247/6250 train_loss:3.1838 train_time:95741ms step_avg:403.97ms step:248/6250 train_loss:3.2065 train_time:96141ms step_avg:403.95ms step:249/6250 train_loss:3.2213 train_time:96540ms step_avg:403.93ms step:250/6250 train_loss:3.2255 train_time:96943ms step_avg:403.93ms step:251/6250 train_loss:3.3067 train_time:97345ms step_avg:403.92ms step:252/6250 train_loss:3.1678 train_time:97747ms step_avg:403.91ms step:253/6250 train_loss:3.2160 train_time:98147ms step_avg:403.90ms step:254/6250 train_loss:3.2204 train_time:98558ms step_avg:403.93ms step:255/6250 train_loss:3.2393 train_time:98970ms step_avg:403.96ms step:256/6250 train_loss:3.2170 train_time:99372ms step_avg:403.95ms step:257/6250 train_loss:3.2728 train_time:99799ms step_avg:404.04ms step:258/6250 train_loss:3.2084 train_time:100208ms step_avg:404.06ms step:259/6250 train_loss:3.4566 train_time:100607ms step_avg:404.04ms step:260/6250 train_loss:3.2220 train_time:101008ms step_avg:404.03ms step:261/6250 train_loss:3.2105 train_time:101409ms step_avg:404.02ms step:262/6250 train_loss:3.2482 train_time:101813ms step_avg:404.02ms step:263/6250 train_loss:3.2644 train_time:102244ms step_avg:404.13ms step:264/6250 train_loss:3.2146 train_time:102671ms step_avg:404.22ms step:265/6250 train_loss:3.2493 train_time:103086ms step_avg:404.26ms step:266/6250 train_loss:3.2399 train_time:103487ms step_avg:404.25ms step:267/6250 train_loss:3.1676 train_time:103894ms step_avg:404.26ms step:268/6250 train_loss:3.1513 train_time:104304ms step_avg:404.28ms step:269/6250 train_loss:3.2661 train_time:104713ms step_avg:404.30ms step:270/6250 train_loss:3.1706 train_time:105122ms step_avg:404.32ms step:271/6250 train_loss:3.1581 train_time:105530ms step_avg:404.33ms step:272/6250 train_loss:3.1857 train_time:105941ms step_avg:404.36ms step:273/6250 train_loss:3.2557 train_time:106348ms step_avg:404.37ms step:274/6250 train_loss:3.1591 train_time:106758ms step_avg:404.39ms step:275/6250 train_loss:3.1477 train_time:107167ms step_avg:404.40ms step:276/6250 train_loss:3.1543 train_time:107577ms step_avg:404.42ms step:277/6250 train_loss:3.1712 train_time:107984ms step_avg:404.43ms step:278/6250 train_loss:3.1921 train_time:108400ms step_avg:404.48ms step:279/6250 train_loss:3.2464 train_time:108808ms step_avg:404.49ms step:280/6250 train_loss:3.1274 train_time:109218ms step_avg:404.51ms step:281/6250 train_loss:3.2576 train_time:109625ms step_avg:404.52ms step:282/6250 train_loss:3.1676 train_time:110035ms step_avg:404.54ms step:283/6250 train_loss:3.2610 train_time:110445ms step_avg:404.56ms step:284/6250 train_loss:3.1127 train_time:110855ms step_avg:404.58ms step:285/6250 train_loss:3.1646 train_time:111266ms step_avg:404.60ms step:286/6250 train_loss:3.1879 train_time:111674ms step_avg:404.61ms step:287/6250 train_loss:3.2364 train_time:112084ms step_avg:404.63ms step:288/6250 train_loss:3.0918 train_time:112493ms step_avg:404.65ms step:289/6250 train_loss:3.3855 train_time:112902ms step_avg:404.67ms step:290/6250 train_loss:3.1389 train_time:113310ms step_avg:404.68ms step:291/6250 train_loss:3.1148 train_time:113717ms step_avg:404.69ms step:292/6250 train_loss:3.0462 train_time:114127ms step_avg:404.71ms step:293/6250 train_loss:3.1180 train_time:114536ms step_avg:404.72ms step:294/6250 train_loss:3.1707 train_time:114941ms step_avg:404.72ms step:295/6250 train_loss:3.2081 train_time:115349ms step_avg:404.73ms step:296/6250 train_loss:3.3150 train_time:115757ms step_avg:404.74ms step:297/6250 train_loss:3.1025 train_time:116164ms step_avg:404.75ms step:298/6250 train_loss:3.1131 train_time:116574ms step_avg:404.77ms step:299/6250 train_loss:3.1097 train_time:116984ms step_avg:404.79ms step:300/6250 train_loss:3.1465 train_time:117394ms step_avg:404.81ms step:301/6250 train_loss:3.2030 train_time:117802ms step_avg:404.82ms step:302/6250 train_loss:3.1846 train_time:118214ms step_avg:404.84ms step:303/6250 train_loss:3.1544 train_time:118623ms step_avg:404.86ms step:304/6250 train_loss:3.1373 train_time:119030ms step_avg:404.86ms step:305/6250 train_loss:3.1252 train_time:119438ms step_avg:404.88ms step:306/6250 train_loss:3.1775 train_time:119848ms step_avg:404.89ms step:307/6250 train_loss:3.2115 train_time:120255ms step_avg:404.90ms step:308/6250 train_loss:3.1808 train_time:120667ms step_avg:404.92ms step:309/6250 train_loss:3.2357 train_time:121073ms step_avg:404.93ms step:310/6250 train_loss:3.2227 train_time:121481ms step_avg:404.94ms step:311/6250 train_loss:3.1056 train_time:121890ms step_avg:404.95ms step:312/6250 train_loss:3.0653 train_time:122298ms step_avg:404.96ms step:313/6250 train_loss:3.0011 train_time:122707ms step_avg:404.97ms step:314/6250 train_loss:3.1357 train_time:123115ms step_avg:404.98ms step:315/6250 train_loss:3.1130 train_time:123522ms step_avg:404.99ms step:316/6250 train_loss:3.1312 train_time:123928ms step_avg:404.99ms step:317/6250 train_loss:3.1588 train_time:124338ms step_avg:405.01ms step:318/6250 train_loss:3.0416 train_time:124744ms step_avg:405.01ms step:319/6250 train_loss:3.0569 train_time:125151ms step_avg:405.02ms step:320/6250 train_loss:3.1145 train_time:125560ms step_avg:405.03ms step:321/6250 train_loss:3.2443 train_time:125971ms step_avg:405.05ms step:322/6250 train_loss:3.2898 train_time:126380ms step_avg:405.07ms step:323/6250 train_loss:3.1311 train_time:126789ms step_avg:405.08ms step:324/6250 train_loss:3.1947 train_time:127198ms step_avg:405.09ms step:325/6250 train_loss:3.1105 train_time:127615ms step_avg:405.13ms step:326/6250 train_loss:3.1403 train_time:128016ms step_avg:405.11ms step:327/6250 train_loss:3.0767 train_time:128413ms step_avg:405.09ms step:328/6250 train_loss:3.0416 train_time:128814ms step_avg:405.07ms step:329/6250 train_loss:3.1648 train_time:129224ms step_avg:405.09ms step:330/6250 train_loss:3.0176 train_time:129639ms step_avg:405.12ms step:331/6250 train_loss:3.0790 train_time:130049ms step_avg:405.14ms step:332/6250 train_loss:3.1617 train_time:130464ms step_avg:405.17ms step:333/6250 train_loss:3.0979 train_time:130876ms step_avg:405.19ms step:334/6250 train_loss:3.1400 train_time:131287ms step_avg:405.21ms step:335/6250 train_loss:3.0446 train_time:131702ms step_avg:405.24ms step:336/6250 train_loss:3.0801 train_time:132114ms step_avg:405.26ms step:337/6250 train_loss:3.2209 train_time:132528ms step_avg:405.28ms step:338/6250 train_loss:3.0857 train_time:132944ms step_avg:405.32ms step:339/6250 train_loss:3.0885 train_time:133357ms step_avg:405.34ms step:340/6250 train_loss:3.0591 train_time:133771ms step_avg:405.37ms step:341/6250 train_loss:3.0715 train_time:134184ms step_avg:405.39ms step:342/6250 train_loss:3.3344 train_time:134599ms step_avg:405.42ms step:343/6250 train_loss:3.1368 train_time:135014ms step_avg:405.45ms step:344/6250 train_loss:3.1348 train_time:135412ms step_avg:405.42ms step:345/6250 train_loss:3.1274 train_time:135816ms step_avg:405.42ms step:346/6250 train_loss:3.1052 train_time:136229ms step_avg:405.44ms step:347/6250 train_loss:3.1050 train_time:136630ms step_avg:405.43ms step:348/6250 train_loss:3.0364 train_time:137047ms step_avg:405.46ms step:349/6250 train_loss:3.1595 train_time:137445ms step_avg:405.44ms step:350/6250 train_loss:3.0893 train_time:137844ms step_avg:405.42ms step:351/6250 train_loss:2.9825 train_time:138245ms step_avg:405.41ms step:352/6250 train_loss:3.1115 train_time:138654ms step_avg:405.42ms step:353/6250 train_loss:3.1777 train_time:139055ms step_avg:405.41ms step:354/6250 train_loss:3.1285 train_time:139460ms step_avg:405.41ms step:355/6250 train_loss:3.1433 train_time:139864ms step_avg:405.40ms step:356/6250 train_loss:3.1400 train_time:140271ms step_avg:405.41ms step:357/6250 train_loss:3.0141 train_time:140672ms step_avg:405.39ms step:358/6250 train_loss:3.1119 train_time:141076ms step_avg:405.39ms step:359/6250 train_loss:3.0802 train_time:141477ms step_avg:405.38ms step:360/6250 train_loss:3.1136 train_time:141878ms step_avg:405.37ms step:361/6250 train_loss:3.1001 train_time:142284ms step_avg:405.37ms step:362/6250 train_loss:3.1505 train_time:142684ms step_avg:405.35ms step:363/6250 train_loss:3.0927 train_time:143094ms step_avg:405.37ms step:364/6250 train_loss:3.0990 train_time:143507ms step_avg:405.39ms step:365/6250 train_loss:3.1026 train_time:143907ms step_avg:405.37ms step:366/6250 train_loss:3.0559 train_time:144322ms step_avg:405.40ms step:367/6250 train_loss:3.1599 train_time:144726ms step_avg:405.39ms step:368/6250 train_loss:3.0820 train_time:145131ms step_avg:405.39ms step:369/6250 train_loss:3.1501 train_time:145543ms step_avg:405.41ms step:370/6250 train_loss:3.1085 train_time:145947ms step_avg:405.41ms step:371/6250 train_loss:3.0267 train_time:146346ms step_avg:405.39ms step:372/6250 train_loss:3.0682 train_time:146746ms step_avg:405.38ms step:373/6250 train_loss:3.0403 train_time:147159ms step_avg:405.40ms step:374/6250 train_loss:3.0040 train_time:147584ms step_avg:405.45ms step:375/6250 train_loss:3.0973 train_time:148003ms step_avg:405.49ms step:376/6250 train_loss:3.1095 train_time:148403ms step_avg:405.47ms step:377/6250 train_loss:3.0926 train_time:148804ms step_avg:405.46ms step:378/6250 train_loss:3.0414 train_time:149207ms step_avg:405.45ms step:379/6250 train_loss:3.1591 train_time:149606ms step_avg:405.44ms step:380/6250 train_loss:3.0806 train_time:150023ms step_avg:405.47ms step:381/6250 train_loss:3.0339 train_time:150439ms step_avg:405.50ms step:382/6250 train_loss:3.0319 train_time:150842ms step_avg:405.49ms step:383/6250 train_loss:3.1515 train_time:151244ms step_avg:405.48ms step:384/6250 train_loss:3.0433 train_time:151647ms step_avg:405.47ms step:385/6250 train_loss:2.9788 train_time:152044ms step_avg:405.45ms step:386/6250 train_loss:3.0761 train_time:152446ms step_avg:405.44ms step:387/6250 train_loss:3.0992 train_time:152848ms step_avg:405.43ms step:388/6250 train_loss:3.1066 train_time:153250ms step_avg:405.42ms step:389/6250 train_loss:3.0632 train_time:153653ms step_avg:405.42ms step:390/6250 train_loss:3.0423 train_time:154054ms step_avg:405.41ms step:391/6250 train_loss:3.0840 train_time:154452ms step_avg:405.39ms step:392/6250 train_loss:3.0256 train_time:154851ms step_avg:405.37ms step:393/6250 train_loss:2.9720 train_time:155251ms step_avg:405.36ms step:394/6250 train_loss:3.0443 train_time:155650ms step_avg:405.34ms step:395/6250 train_loss:2.9383 train_time:156050ms step_avg:405.32ms step:396/6250 train_loss:2.9311 train_time:156450ms step_avg:405.31ms step:397/6250 train_loss:3.0211 train_time:156852ms step_avg:405.30ms step:398/6250 train_loss:3.1401 train_time:157284ms step_avg:405.37ms step:399/6250 train_loss:3.0597 train_time:157711ms step_avg:405.43ms step:400/6250 train_loss:3.1593 train_time:158113ms step_avg:405.42ms step:401/6250 train_loss:3.1466 train_time:158514ms step_avg:405.41ms step:402/6250 train_loss:3.0291 train_time:158915ms step_avg:405.40ms step:403/6250 train_loss:3.0533 train_time:159320ms step_avg:405.39ms step:404/6250 train_loss:3.0924 train_time:159721ms step_avg:405.38ms step:405/6250 train_loss:3.0300 train_time:160123ms step_avg:405.38ms step:406/6250 train_loss:3.0335 train_time:160526ms step_avg:405.37ms step:407/6250 train_loss:3.1004 train_time:160927ms step_avg:405.36ms step:408/6250 train_loss:2.9689 train_time:161330ms step_avg:405.35ms step:409/6250 train_loss:3.0616 train_time:161728ms step_avg:405.33ms step:410/6250 train_loss:3.0581 train_time:162127ms step_avg:405.32ms step:411/6250 train_loss:3.0641 train_time:162527ms step_avg:405.30ms step:412/6250 train_loss:3.0515 train_time:162928ms step_avg:405.29ms step:413/6250 train_loss:3.0095 train_time:163326ms step_avg:405.27ms step:414/6250 train_loss:2.9337 train_time:163730ms step_avg:405.27ms step:415/6250 train_loss:3.1180 train_time:164131ms step_avg:405.26ms step:416/6250 train_loss:2.9696 train_time:164533ms step_avg:405.25ms step:417/6250 train_loss:2.9750 train_time:164947ms step_avg:405.28ms step:418/6250 train_loss:3.0016 train_time:165351ms step_avg:405.27ms step:419/6250 train_loss:3.0698 train_time:165749ms step_avg:405.26ms step:420/6250 train_loss:3.0500 train_time:166151ms step_avg:405.25ms step:421/6250 train_loss:3.1055 train_time:166552ms step_avg:405.24ms step:422/6250 train_loss:2.9558 train_time:166962ms step_avg:405.25ms step:423/6250 train_loss:3.0161 train_time:167364ms step_avg:405.24ms step:424/6250 train_loss:2.9946 train_time:167766ms step_avg:405.23ms step:425/6250 train_loss:3.0836 train_time:168166ms step_avg:405.22ms step:426/6250 train_loss:3.0235 train_time:168567ms step_avg:405.21ms step:427/6250 train_loss:3.0473 train_time:168996ms step_avg:405.27ms step:428/6250 train_loss:2.9843 train_time:169410ms step_avg:405.29ms step:429/6250 train_loss:3.0139 train_time:169811ms step_avg:405.28ms step:430/6250 train_loss:2.9722 train_time:170214ms step_avg:405.27ms step:431/6250 train_loss:3.0191 train_time:170611ms step_avg:405.25ms step:432/6250 train_loss:3.0128 train_time:171010ms step_avg:405.24ms step:433/6250 train_loss:2.9744 train_time:171412ms step_avg:405.23ms step:434/6250 train_loss:2.9995 train_time:171813ms step_avg:405.22ms step:435/6250 train_loss:2.9106 train_time:172213ms step_avg:405.21ms step:436/6250 train_loss:3.0842 train_time:172614ms step_avg:405.20ms step:437/6250 train_loss:2.9603 train_time:173015ms step_avg:405.19ms step:438/6250 train_loss:3.0944 train_time:173414ms step_avg:405.17ms step:439/6250 train_loss:3.1006 train_time:173812ms step_avg:405.16ms step:440/6250 train_loss:3.1369 train_time:174213ms step_avg:405.15ms step:441/6250 train_loss:2.9406 train_time:174614ms step_avg:405.14ms step:442/6250 train_loss:3.0004 train_time:175016ms step_avg:405.13ms step:443/6250 train_loss:3.1537 train_time:175415ms step_avg:405.12ms step:444/6250 train_loss:2.9686 train_time:175815ms step_avg:405.10ms step:445/6250 train_loss:3.0598 train_time:176217ms step_avg:405.10ms step:446/6250 train_loss:3.0058 train_time:176616ms step_avg:405.08ms step:447/6250 train_loss:2.9228 train_time:177015ms step_avg:405.07ms step:448/6250 train_loss:3.0737 train_time:177415ms step_avg:405.06ms step:449/6250 train_loss:2.9620 train_time:177818ms step_avg:405.05ms step:450/6250 train_loss:3.1306 train_time:178221ms step_avg:405.05ms step:451/6250 train_loss:3.0479 train_time:178623ms step_avg:405.04ms step:452/6250 train_loss:3.0077 train_time:179026ms step_avg:405.04ms step:453/6250 train_loss:2.9730 train_time:179430ms step_avg:405.03ms step:454/6250 train_loss:2.9894 train_time:179832ms step_avg:405.03ms step:455/6250 train_loss:3.0014 train_time:180238ms step_avg:405.03ms step:456/6250 train_loss:2.9498 train_time:180640ms step_avg:405.02ms step:457/6250 train_loss:3.0763 train_time:181043ms step_avg:405.02ms step:458/6250 train_loss:2.9571 train_time:181444ms step_avg:405.01ms step:459/6250 train_loss:2.9397 train_time:181845ms step_avg:405.00ms step:460/6250 train_loss:3.0321 train_time:182247ms step_avg:404.99ms step:461/6250 train_loss:3.0189 train_time:182649ms step_avg:404.99ms step:462/6250 train_loss:2.9670 train_time:183053ms step_avg:404.98ms step:463/6250 train_loss:2.9989 train_time:183455ms step_avg:404.98ms step:464/6250 train_loss:2.9497 train_time:183858ms step_avg:404.97ms step:465/6250 train_loss:2.9394 train_time:184260ms step_avg:404.97ms step:466/6250 train_loss:2.9537 train_time:184661ms step_avg:404.96ms step:467/6250 train_loss:2.9176 train_time:185062ms step_avg:404.95ms step:468/6250 train_loss:2.9086 train_time:185464ms step_avg:404.94ms step:469/6250 train_loss:2.9782 train_time:185867ms step_avg:404.94ms step:470/6250 train_loss:3.0021 train_time:186265ms step_avg:404.92ms step:471/6250 train_loss:2.9851 train_time:186667ms step_avg:404.92ms step:472/6250 train_loss:2.9508 train_time:187068ms step_avg:404.91ms step:473/6250 train_loss:2.8619 train_time:187469ms step_avg:404.90ms step:474/6250 train_loss:2.9874 train_time:187870ms step_avg:404.89ms step:475/6250 train_loss:2.9565 train_time:188272ms step_avg:404.89ms step:476/6250 train_loss:2.9435 train_time:188672ms step_avg:404.88ms step:477/6250 train_loss:2.9619 train_time:189071ms step_avg:404.86ms step:478/6250 train_loss:2.9563 train_time:189473ms step_avg:404.86ms step:479/6250 train_loss:2.8963 train_time:189877ms step_avg:404.86ms step:480/6250 train_loss:2.9315 train_time:190282ms step_avg:404.85ms step:481/6250 train_loss:2.9590 train_time:190688ms step_avg:404.86ms step:482/6250 train_loss:2.9659 train_time:191090ms step_avg:404.85ms step:483/6250 train_loss:2.9768 train_time:191492ms step_avg:404.85ms step:484/6250 train_loss:2.9892 train_time:191894ms step_avg:404.84ms step:485/6250 train_loss:2.9695 train_time:192299ms step_avg:404.84ms step:486/6250 train_loss:2.8897 train_time:192704ms step_avg:404.84ms step:487/6250 train_loss:3.0375 train_time:193108ms step_avg:404.84ms step:488/6250 train_loss:3.0805 train_time:193509ms step_avg:404.83ms step:489/6250 train_loss:2.9511 train_time:193911ms step_avg:404.82ms step:490/6250 train_loss:2.9387 train_time:194314ms step_avg:404.82ms step:491/6250 train_loss:2.9403 train_time:194716ms step_avg:404.82ms step:492/6250 train_loss:2.9223 train_time:195120ms step_avg:404.81ms step:493/6250 train_loss:3.0134 train_time:195524ms step_avg:404.81ms step:494/6250 train_loss:2.9938 train_time:195926ms step_avg:404.81ms step:495/6250 train_loss:2.9221 train_time:196326ms step_avg:404.80ms step:496/6250 train_loss:2.9367 train_time:196728ms step_avg:404.79ms step:497/6250 train_loss:2.9096 train_time:197127ms step_avg:404.78ms step:498/6250 train_loss:2.9705 train_time:197528ms step_avg:404.77ms step:499/6250 train_loss:2.8899 train_time:197929ms step_avg:404.76ms step:500/6250 train_loss:2.9648 train_time:198328ms step_avg:404.75ms step:501/6250 train_loss:2.9489 train_time:198727ms step_avg:404.74ms step:502/6250 train_loss:2.9786 train_time:199127ms step_avg:404.73ms step:503/6250 train_loss:3.0059 train_time:199530ms step_avg:404.73ms step:504/6250 train_loss:2.9562 train_time:199932ms step_avg:404.72ms step:505/6250 train_loss:2.9627 train_time:200334ms step_avg:404.72ms step:506/6250 train_loss:2.9162 train_time:200735ms step_avg:404.71ms step:507/6250 train_loss:2.9737 train_time:201135ms step_avg:404.70ms step:508/6250 train_loss:2.9081 train_time:201535ms step_avg:404.69ms step:509/6250 train_loss:3.0439 train_time:201937ms step_avg:404.68ms step:510/6250 train_loss:3.0132 train_time:202337ms step_avg:404.67ms step:511/6250 train_loss:2.9817 train_time:202739ms step_avg:404.67ms step:512/6250 train_loss:2.9643 train_time:203141ms step_avg:404.66ms step:513/6250 train_loss:3.0220 train_time:203540ms step_avg:404.65ms step:514/6250 train_loss:2.9470 train_time:203941ms step_avg:404.64ms step:515/6250 train_loss:2.9795 train_time:204343ms step_avg:404.64ms step:516/6250 train_loss:2.9636 train_time:204745ms step_avg:404.63ms step:517/6250 train_loss:2.9890 train_time:205147ms step_avg:404.63ms step:518/6250 train_loss:2.9177 train_time:205550ms step_avg:404.63ms step:519/6250 train_loss:3.0305 train_time:205954ms step_avg:404.63ms step:520/6250 train_loss:2.9887 train_time:206358ms step_avg:404.62ms step:521/6250 train_loss:2.9492 train_time:206762ms step_avg:404.62ms step:522/6250 train_loss:2.9470 train_time:207162ms step_avg:404.61ms step:523/6250 train_loss:2.9193 train_time:207563ms step_avg:404.61ms step:524/6250 train_loss:2.8964 train_time:207964ms step_avg:404.60ms step:525/6250 train_loss:2.9962 train_time:208365ms step_avg:404.59ms step:526/6250 train_loss:2.9598 train_time:208764ms step_avg:404.58ms step:527/6250 train_loss:2.9937 train_time:209165ms step_avg:404.57ms step:528/6250 train_loss:2.9657 train_time:209566ms step_avg:404.57ms step:529/6250 train_loss:2.9721 train_time:209968ms step_avg:404.56ms step:530/6250 train_loss:2.9646 train_time:210370ms step_avg:404.56ms step:531/6250 train_loss:2.9239 train_time:210768ms step_avg:404.55ms step:532/6250 train_loss:2.9350 train_time:211167ms step_avg:404.53ms step:533/6250 train_loss:2.9010 train_time:211566ms step_avg:404.52ms step:534/6250 train_loss:2.9084 train_time:211967ms step_avg:404.52ms step:535/6250 train_loss:2.8911 train_time:212367ms step_avg:404.51ms step:536/6250 train_loss:2.9837 train_time:212765ms step_avg:404.50ms step:537/6250 train_loss:2.8610 train_time:213166ms step_avg:404.49ms step:538/6250 train_loss:2.8956 train_time:213566ms step_avg:404.48ms step:539/6250 train_loss:2.9589 train_time:213968ms step_avg:404.48ms step:540/6250 train_loss:2.9714 train_time:214365ms step_avg:404.46ms step:541/6250 train_loss:2.9246 train_time:214765ms step_avg:404.45ms step:542/6250 train_loss:2.9285 train_time:215166ms step_avg:404.45ms step:543/6250 train_loss:2.8963 train_time:215568ms step_avg:404.44ms step:544/6250 train_loss:3.0240 train_time:215968ms step_avg:404.44ms step:545/6250 train_loss:2.8870 train_time:216366ms step_avg:404.42ms step:546/6250 train_loss:3.0249 train_time:216764ms step_avg:404.41ms step:547/6250 train_loss:2.8164 train_time:217165ms step_avg:404.40ms step:548/6250 train_loss:2.8945 train_time:217568ms step_avg:404.40ms step:549/6250 train_loss:3.0114 train_time:217969ms step_avg:404.39ms step:550/6250 train_loss:2.9985 train_time:218367ms step_avg:404.38ms step:551/6250 train_loss:2.9745 train_time:218769ms step_avg:404.38ms step:552/6250 train_loss:3.0017 train_time:219174ms step_avg:404.38ms step:553/6250 train_loss:2.9084 train_time:219583ms step_avg:404.39ms step:554/6250 train_loss:2.9654 train_time:219987ms step_avg:404.39ms step:555/6250 train_loss:3.0125 train_time:220396ms step_avg:404.40ms step:556/6250 train_loss:2.9235 train_time:220798ms step_avg:404.39ms step:557/6250 train_loss:2.8846 train_time:221201ms step_avg:404.39ms step:558/6250 train_loss:2.9808 train_time:221602ms step_avg:404.38ms step:559/6250 train_loss:2.8813 train_time:222003ms step_avg:404.38ms step:560/6250 train_loss:2.9056 train_time:222405ms step_avg:404.37ms step:561/6250 train_loss:2.9751 train_time:222804ms step_avg:404.36ms step:562/6250 train_loss:2.9683 train_time:223208ms step_avg:404.36ms step:563/6250 train_loss:2.9735 train_time:223621ms step_avg:404.38ms step:564/6250 train_loss:2.9510 train_time:224031ms step_avg:404.39ms step:565/6250 train_loss:2.8952 train_time:224432ms step_avg:404.38ms step:566/6250 train_loss:2.9041 train_time:224855ms step_avg:404.41ms step:567/6250 train_loss:2.8773 train_time:225256ms step_avg:404.41ms step:568/6250 train_loss:2.9431 train_time:225707ms step_avg:404.49ms step:569/6250 train_loss:2.9057 train_time:226164ms step_avg:404.59ms step:570/6250 train_loss:2.9237 train_time:226620ms step_avg:404.68ms step:571/6250 train_loss:2.9579 train_time:227072ms step_avg:404.76ms step:572/6250 train_loss:2.9273 train_time:227521ms step_avg:404.84ms step:573/6250 train_loss:2.9088 train_time:227970ms step_avg:404.92ms step:574/6250 train_loss:2.8823 train_time:228422ms step_avg:405.00ms step:575/6250 train_loss:2.9004 train_time:228875ms step_avg:405.09ms step:576/6250 train_loss:2.9146 train_time:229337ms step_avg:405.19ms step:577/6250 train_loss:2.8592 train_time:229796ms step_avg:405.28ms step:578/6250 train_loss:2.8896 train_time:230263ms step_avg:405.39ms step:579/6250 train_loss:2.8430 train_time:230724ms step_avg:405.49ms step:580/6250 train_loss:2.8477 train_time:231186ms step_avg:405.59ms step:581/6250 train_loss:2.8444 train_time:231651ms step_avg:405.69ms step:582/6250 train_loss:2.8538 train_time:232113ms step_avg:405.79ms step:583/6250 train_loss:2.9814 train_time:232578ms step_avg:405.89ms step:584/6250 train_loss:2.9763 train_time:233028ms step_avg:405.97ms step:585/6250 train_loss:2.9541 train_time:233478ms step_avg:406.05ms step:586/6250 train_loss:2.8287 train_time:233929ms step_avg:406.13ms step:587/6250 train_loss:2.9479 train_time:234380ms step_avg:406.20ms step:588/6250 train_loss:3.0034 train_time:234837ms step_avg:406.29ms step:589/6250 train_loss:2.9716 train_time:235269ms step_avg:406.34ms step:590/6250 train_loss:2.9194 train_time:235705ms step_avg:406.39ms step:591/6250 train_loss:2.8964 train_time:236130ms step_avg:406.42ms step:592/6250 train_loss:2.9143 train_time:236547ms step_avg:406.44ms step:593/6250 train_loss:2.9363 train_time:236955ms step_avg:406.44ms step:594/6250 train_loss:2.9814 train_time:237364ms step_avg:406.45ms step:595/6250 train_loss:2.8533 train_time:237766ms step_avg:406.44ms step:596/6250 train_loss:2.8550 train_time:238172ms step_avg:406.44ms step:597/6250 train_loss:2.9766 train_time:238587ms step_avg:406.45ms step:598/6250 train_loss:2.9679 train_time:239015ms step_avg:406.49ms step:599/6250 train_loss:2.8753 train_time:239433ms step_avg:406.51ms step:600/6250 train_loss:2.8361 train_time:239843ms step_avg:406.51ms step:601/6250 train_loss:2.8103 train_time:240261ms step_avg:406.53ms step:602/6250 train_loss:2.8670 train_time:240699ms step_avg:406.59ms step:603/6250 train_loss:2.8990 train_time:241118ms step_avg:406.61ms step:604/6250 train_loss:2.9472 train_time:241556ms step_avg:406.66ms step:605/6250 train_loss:2.9871 train_time:242004ms step_avg:406.73ms step:606/6250 train_loss:2.9089 train_time:242422ms step_avg:406.75ms step:607/6250 train_loss:2.9500 train_time:242843ms step_avg:406.77ms step:608/6250 train_loss:2.9478 train_time:243247ms step_avg:406.77ms step:609/6250 train_loss:2.8712 train_time:243662ms step_avg:406.78ms step:610/6250 train_loss:2.9097 train_time:244072ms step_avg:406.79ms step:611/6250 train_loss:2.8165 train_time:244491ms step_avg:406.81ms step:612/6250 train_loss:2.9179 train_time:244908ms step_avg:406.82ms step:613/6250 train_loss:2.8797 train_time:245325ms step_avg:406.84ms step:614/6250 train_loss:2.9384 train_time:245741ms step_avg:406.86ms step:615/6250 train_loss:2.9000 train_time:246158ms step_avg:406.87ms step:616/6250 train_loss:2.9149 train_time:246576ms step_avg:406.89ms step:617/6250 train_loss:2.8323 train_time:246994ms step_avg:406.91ms step:618/6250 train_loss:2.9213 train_time:247413ms step_avg:406.93ms step:619/6250 train_loss:2.8870 train_time:247830ms step_avg:406.95ms step:620/6250 train_loss:2.8963 train_time:248232ms step_avg:406.94ms step:621/6250 train_loss:2.8593 train_time:248632ms step_avg:406.93ms step:622/6250 train_loss:2.9127 train_time:249034ms step_avg:406.92ms step:623/6250 train_loss:2.8294 train_time:249436ms step_avg:406.91ms step:624/6250 train_loss:2.8796 train_time:249837ms step_avg:406.90ms step:625/6250 train_loss:2.8651 train_time:250237ms step_avg:406.89ms step:626/6250 train_loss:2.9090 train_time:250639ms step_avg:406.88ms step:627/6250 train_loss:3.0020 train_time:251040ms step_avg:406.87ms step:628/6250 train_loss:2.9533 train_time:251442ms step_avg:406.86ms step:629/6250 train_loss:2.8344 train_time:251843ms step_avg:406.86ms step:630/6250 train_loss:2.9485 train_time:252245ms step_avg:406.85ms step:631/6250 train_loss:2.9348 train_time:252647ms step_avg:406.84ms step:632/6250 train_loss:2.9339 train_time:253052ms step_avg:406.84ms step:633/6250 train_loss:2.9070 train_time:253454ms step_avg:406.83ms step:634/6250 train_loss:2.9598 train_time:253854ms step_avg:406.82ms step:635/6250 train_loss:2.9737 train_time:254256ms step_avg:406.81ms step:636/6250 train_loss:2.8918 train_time:254659ms step_avg:406.80ms step:637/6250 train_loss:2.8814 train_time:255058ms step_avg:406.79ms step:638/6250 train_loss:2.8827 train_time:255463ms step_avg:406.79ms step:639/6250 train_loss:2.8155 train_time:255867ms step_avg:406.78ms step:640/6250 train_loss:2.8324 train_time:256270ms step_avg:406.78ms step:641/6250 train_loss:2.8738 train_time:256672ms step_avg:406.77ms step:642/6250 train_loss:2.8503 train_time:257074ms step_avg:406.76ms step:643/6250 train_loss:2.9363 train_time:257477ms step_avg:406.76ms step:644/6250 train_loss:2.9203 train_time:257879ms step_avg:406.75ms step:645/6250 train_loss:2.8091 train_time:258279ms step_avg:406.74ms step:646/6250 train_loss:2.9207 train_time:258679ms step_avg:406.73ms step:647/6250 train_loss:2.9090 train_time:259080ms step_avg:406.72ms step:648/6250 train_loss:2.8419 train_time:259482ms step_avg:406.71ms step:649/6250 train_loss:2.9040 train_time:259884ms step_avg:406.70ms step:650/6250 train_loss:2.8638 train_time:260286ms step_avg:406.70ms step:651/6250 train_loss:2.8073 train_time:260688ms step_avg:406.69ms step:652/6250 train_loss:2.8268 train_time:261090ms step_avg:406.68ms step:653/6250 train_loss:2.9680 train_time:261509ms step_avg:406.70ms step:654/6250 train_loss:2.8224 train_time:261933ms step_avg:406.73ms step:655/6250 train_loss:2.8644 train_time:262352ms step_avg:406.75ms step:656/6250 train_loss:2.8179 train_time:262757ms step_avg:406.75ms step:657/6250 train_loss:2.8140 train_time:263185ms step_avg:406.78ms step:658/6250 train_loss:2.7514 train_time:263599ms step_avg:406.79ms step:659/6250 train_loss:2.9301 train_time:264011ms step_avg:406.80ms step:660/6250 train_loss:2.8836 train_time:264415ms step_avg:406.79ms step:661/6250 train_loss:2.8640 train_time:264818ms step_avg:406.79ms step:662/6250 train_loss:2.9647 train_time:265233ms step_avg:406.80ms step:663/6250 train_loss:2.9433 train_time:265639ms step_avg:406.80ms step:664/6250 train_loss:2.9896 train_time:266039ms step_avg:406.79ms step:665/6250 train_loss:2.8796 train_time:266464ms step_avg:406.81ms step:666/6250 train_loss:2.9344 train_time:266886ms step_avg:406.84ms step:667/6250 train_loss:2.8392 train_time:267312ms step_avg:406.87ms step:668/6250 train_loss:2.8469 train_time:267729ms step_avg:406.88ms step:669/6250 train_loss:2.8723 train_time:268151ms step_avg:406.91ms step:670/6250 train_loss:2.9192 train_time:268573ms step_avg:406.93ms step:671/6250 train_loss:2.9697 train_time:268988ms step_avg:406.94ms step:672/6250 train_loss:2.8834 train_time:269409ms step_avg:406.96ms step:673/6250 train_loss:2.9415 train_time:269827ms step_avg:406.98ms step:674/6250 train_loss:2.8728 train_time:270248ms step_avg:407.00ms step:675/6250 train_loss:2.9754 train_time:270670ms step_avg:407.02ms step:676/6250 train_loss:2.8493 train_time:271089ms step_avg:407.04ms step:677/6250 train_loss:2.8612 train_time:271509ms step_avg:407.06ms step:678/6250 train_loss:2.8377 train_time:271930ms step_avg:407.08ms step:679/6250 train_loss:2.9627 train_time:272334ms step_avg:407.08ms step:680/6250 train_loss:2.8822 train_time:272742ms step_avg:407.08ms step:681/6250 train_loss:2.8167 train_time:273147ms step_avg:407.07ms step:682/6250 train_loss:2.8264 train_time:273564ms step_avg:407.09ms step:683/6250 train_loss:2.9783 train_time:273978ms step_avg:407.10ms step:684/6250 train_loss:2.8564 train_time:274392ms step_avg:407.11ms step:685/6250 train_loss:2.8121 train_time:274835ms step_avg:407.16ms step:686/6250 train_loss:2.8113 train_time:275260ms step_avg:407.19ms step:687/6250 train_loss:2.8813 train_time:275685ms step_avg:407.22ms step:688/6250 train_loss:2.8697 train_time:276119ms step_avg:407.25ms step:689/6250 train_loss:2.8815 train_time:276539ms step_avg:407.27ms step:690/6250 train_loss:2.8908 train_time:276961ms step_avg:407.30ms step:691/6250 train_loss:2.8220 train_time:277381ms step_avg:407.31ms step:692/6250 train_loss:2.8531 train_time:277800ms step_avg:407.33ms step:693/6250 train_loss:2.8976 train_time:278221ms step_avg:407.35ms step:694/6250 train_loss:2.7934 train_time:278641ms step_avg:407.37ms step:695/6250 train_loss:2.8146 train_time:279056ms step_avg:407.38ms step:696/6250 train_loss:2.9584 train_time:279458ms step_avg:407.37ms step:697/6250 train_loss:2.8143 train_time:279859ms step_avg:407.36ms step:698/6250 train_loss:2.9013 train_time:280260ms step_avg:407.35ms step:699/6250 train_loss:2.9970 train_time:280662ms step_avg:407.35ms step:700/6250 train_loss:2.8375 train_time:281066ms step_avg:407.34ms step:701/6250 train_loss:2.8616 train_time:281478ms step_avg:407.35ms step:702/6250 train_loss:2.8320 train_time:281892ms step_avg:407.36ms step:703/6250 train_loss:2.8165 train_time:282308ms step_avg:407.37ms step:704/6250 train_loss:2.9177 train_time:282726ms step_avg:407.39ms step:705/6250 train_loss:2.8046 train_time:283145ms step_avg:407.40ms step:706/6250 train_loss:2.8583 train_time:283564ms step_avg:407.42ms step:707/6250 train_loss:2.8303 train_time:283987ms step_avg:407.44ms step:708/6250 train_loss:2.8282 train_time:284408ms step_avg:407.46ms step:709/6250 train_loss:2.8595 train_time:284828ms step_avg:407.48ms step:710/6250 train_loss:2.8802 train_time:285246ms step_avg:407.49ms step:711/6250 train_loss:2.8327 train_time:285644ms step_avg:407.48ms step:712/6250 train_loss:2.9265 train_time:286048ms step_avg:407.48ms step:713/6250 train_loss:2.8211 train_time:286451ms step_avg:407.47ms step:714/6250 train_loss:2.8349 train_time:286853ms step_avg:407.46ms step:715/6250 train_loss:2.9267 train_time:287253ms step_avg:407.45ms step:716/6250 train_loss:2.8244 train_time:287655ms step_avg:407.44ms step:717/6250 train_loss:2.8756 train_time:288055ms step_avg:407.43ms step:718/6250 train_loss:2.8877 train_time:288460ms step_avg:407.43ms step:719/6250 train_loss:2.7019 train_time:288859ms step_avg:407.42ms step:720/6250 train_loss:2.8038 train_time:289263ms step_avg:407.41ms step:721/6250 train_loss:2.8039 train_time:289666ms step_avg:407.41ms step:722/6250 train_loss:2.8200 train_time:290065ms step_avg:407.39ms step:723/6250 train_loss:2.7677 train_time:290468ms step_avg:407.39ms step:724/6250 train_loss:2.7960 train_time:290872ms step_avg:407.38ms step:725/6250 train_loss:2.8284 train_time:291276ms step_avg:407.38ms step:726/6250 train_loss:2.7479 train_time:291678ms step_avg:407.37ms step:727/6250 train_loss:2.8310 train_time:292080ms step_avg:407.36ms step:728/6250 train_loss:2.7673 train_time:292482ms step_avg:407.36ms step:729/6250 train_loss:2.8811 train_time:292885ms step_avg:407.35ms step:730/6250 train_loss:2.8550 train_time:293288ms step_avg:407.34ms step:731/6250 train_loss:2.8411 train_time:293691ms step_avg:407.34ms step:732/6250 train_loss:2.8160 train_time:294092ms step_avg:407.33ms step:733/6250 train_loss:2.8229 train_time:294494ms step_avg:407.32ms step:734/6250 train_loss:2.7119 train_time:294898ms step_avg:407.32ms step:735/6250 train_loss:2.7802 train_time:295301ms step_avg:407.31ms step:736/6250 train_loss:2.8610 train_time:295703ms step_avg:407.30ms step:737/6250 train_loss:2.8411 train_time:296105ms step_avg:407.30ms step:738/6250 train_loss:2.7596 train_time:296505ms step_avg:407.29ms step:739/6250 train_loss:2.8446 train_time:296907ms step_avg:407.28ms step:740/6250 train_loss:2.8027 train_time:297305ms step_avg:407.27ms step:741/6250 train_loss:2.7781 train_time:297704ms step_avg:407.26ms step:742/6250 train_loss:2.9114 train_time:298105ms step_avg:407.25ms step:743/6250 train_loss:2.8503 train_time:298503ms step_avg:407.23ms step:744/6250 train_loss:2.9384 train_time:298905ms step_avg:407.23ms step:745/6250 train_loss:2.8716 train_time:299307ms step_avg:407.22ms step:746/6250 train_loss:2.7609 train_time:299709ms step_avg:407.21ms step:747/6250 train_loss:2.8212 train_time:300110ms step_avg:407.21ms step:748/6250 train_loss:2.8103 train_time:300512ms step_avg:407.20ms step:749/6250 train_loss:2.8714 train_time:300914ms step_avg:407.19ms step:750/6250 train_loss:2.8613 train_time:301313ms step_avg:407.18ms step:751/6250 train_loss:2.8086 train_time:301713ms step_avg:407.17ms step:752/6250 train_loss:2.8324 train_time:302114ms step_avg:407.16ms step:753/6250 train_loss:2.9040 train_time:302516ms step_avg:407.15ms step:754/6250 train_loss:2.8166 train_time:302918ms step_avg:407.15ms step:755/6250 train_loss:2.8330 train_time:303316ms step_avg:407.14ms step:756/6250 train_loss:2.8586 train_time:303716ms step_avg:407.13ms step:757/6250 train_loss:2.9276 train_time:304118ms step_avg:407.12ms step:758/6250 train_loss:2.7907 train_time:304521ms step_avg:407.11ms step:759/6250 train_loss:2.7792 train_time:304940ms step_avg:407.13ms step:760/6250 train_loss:2.8422 train_time:305343ms step_avg:407.12ms step:761/6250 train_loss:2.7770 train_time:305743ms step_avg:407.11ms step:762/6250 train_loss:2.8015 train_time:306142ms step_avg:407.10ms step:763/6250 train_loss:2.8495 train_time:306543ms step_avg:407.10ms step:764/6250 train_loss:2.8020 train_time:306945ms step_avg:407.09ms step:765/6250 train_loss:2.9461 train_time:307354ms step_avg:407.09ms step:766/6250 train_loss:2.8020 train_time:307761ms step_avg:407.09ms step:767/6250 train_loss:2.8283 train_time:308165ms step_avg:407.09ms step:768/6250 train_loss:2.7719 train_time:308568ms step_avg:407.08ms step:769/6250 train_loss:2.8264 train_time:308972ms step_avg:407.08ms step:770/6250 train_loss:2.8203 train_time:309373ms step_avg:407.07ms step:771/6250 train_loss:2.7701 train_time:309772ms step_avg:407.06ms step:772/6250 train_loss:2.7496 train_time:310173ms step_avg:407.05ms step:773/6250 train_loss:2.8154 train_time:310577ms step_avg:407.05ms step:774/6250 train_loss:2.7842 train_time:310982ms step_avg:407.04ms step:775/6250 train_loss:2.8682 train_time:311385ms step_avg:407.04ms step:776/6250 train_loss:2.7916 train_time:311785ms step_avg:407.03ms step:777/6250 train_loss:2.8888 train_time:312187ms step_avg:407.02ms step:778/6250 train_loss:2.8425 train_time:312589ms step_avg:407.02ms step:779/6250 train_loss:2.8913 train_time:313010ms step_avg:407.04ms step:780/6250 train_loss:2.7904 train_time:313439ms step_avg:407.06ms step:781/6250 train_loss:2.8121 train_time:313859ms step_avg:407.08ms step:782/6250 train_loss:2.7811 train_time:314284ms step_avg:407.10ms step:783/6250 train_loss:2.7282 train_time:314688ms step_avg:407.10ms step:784/6250 train_loss:2.8332 train_time:315093ms step_avg:407.10ms step:785/6250 train_loss:2.7728 train_time:315497ms step_avg:407.09ms step:786/6250 train_loss:2.7556 train_time:315895ms step_avg:407.08ms step:787/6250 train_loss:2.8476 train_time:316299ms step_avg:407.08ms step:788/6250 train_loss:2.9154 train_time:316704ms step_avg:407.07ms step:789/6250 train_loss:2.7690 train_time:317105ms step_avg:407.07ms step:790/6250 train_loss:2.7924 train_time:317507ms step_avg:407.06ms step:791/6250 train_loss:2.8838 train_time:317909ms step_avg:407.05ms step:792/6250 train_loss:2.8282 train_time:318312ms step_avg:407.05ms step:793/6250 train_loss:2.8219 train_time:318719ms step_avg:407.05ms step:794/6250 train_loss:2.7978 train_time:319120ms step_avg:407.04ms step:795/6250 train_loss:2.8125 train_time:319522ms step_avg:407.03ms step:796/6250 train_loss:3.0020 train_time:319923ms step_avg:407.03ms step:797/6250 train_loss:2.7873 train_time:320325ms step_avg:407.02ms step:798/6250 train_loss:2.8116 train_time:320726ms step_avg:407.01ms step:799/6250 train_loss:2.7473 train_time:321128ms step_avg:407.01ms step:800/6250 train_loss:2.8377 train_time:321527ms step_avg:407.00ms step:801/6250 train_loss:2.7592 train_time:321929ms step_avg:406.99ms step:802/6250 train_loss:2.8183 train_time:322335ms step_avg:406.99ms step:803/6250 train_loss:2.7492 train_time:322740ms step_avg:406.99ms step:804/6250 train_loss:2.8393 train_time:323142ms step_avg:406.98ms step:805/6250 train_loss:2.7688 train_time:323543ms step_avg:406.97ms step:806/6250 train_loss:2.7920 train_time:323946ms step_avg:406.97ms step:807/6250 train_loss:2.8009 train_time:324365ms step_avg:406.98ms step:808/6250 train_loss:2.8493 train_time:324786ms step_avg:407.00ms step:809/6250 train_loss:2.7372 train_time:325199ms step_avg:407.01ms step:810/6250 train_loss:2.7168 train_time:325624ms step_avg:407.03ms step:811/6250 train_loss:2.9052 train_time:326033ms step_avg:407.03ms step:812/6250 train_loss:2.9227 train_time:326434ms step_avg:407.02ms step:813/6250 train_loss:2.8477 train_time:326837ms step_avg:407.02ms step:814/6250 train_loss:2.7982 train_time:327240ms step_avg:407.01ms step:815/6250 train_loss:2.7926 train_time:327647ms step_avg:407.01ms step:816/6250 train_loss:2.8534 train_time:328048ms step_avg:407.01ms step:817/6250 train_loss:2.8077 train_time:328449ms step_avg:407.00ms step:818/6250 train_loss:2.7574 train_time:328851ms step_avg:406.99ms step:819/6250 train_loss:2.7648 train_time:329255ms step_avg:406.99ms step:820/6250 train_loss:2.7916 train_time:329655ms step_avg:406.98ms step:821/6250 train_loss:2.7363 train_time:330054ms step_avg:406.97ms step:822/6250 train_loss:2.7828 train_time:330458ms step_avg:406.97ms step:823/6250 train_loss:2.7923 train_time:330861ms step_avg:406.96ms step:824/6250 train_loss:2.8125 train_time:331265ms step_avg:406.96ms step:825/6250 train_loss:2.8006 train_time:331667ms step_avg:406.95ms step:826/6250 train_loss:2.7434 train_time:332070ms step_avg:406.95ms step:827/6250 train_loss:2.8237 train_time:332472ms step_avg:406.94ms step:828/6250 train_loss:2.8885 train_time:332871ms step_avg:406.93ms step:829/6250 train_loss:2.8630 train_time:333273ms step_avg:406.93ms step:830/6250 train_loss:2.7742 train_time:333673ms step_avg:406.92ms step:831/6250 train_loss:2.8804 train_time:334075ms step_avg:406.91ms step:832/6250 train_loss:2.7934 train_time:334476ms step_avg:406.90ms step:833/6250 train_loss:2.8092 train_time:334882ms step_avg:406.90ms step:834/6250 train_loss:2.8771 train_time:335285ms step_avg:406.90ms step:835/6250 train_loss:2.7892 train_time:335683ms step_avg:406.89ms step:836/6250 train_loss:2.8674 train_time:336085ms step_avg:406.88ms step:837/6250 train_loss:2.7842 train_time:336489ms step_avg:406.88ms step:838/6250 train_loss:2.8343 train_time:336891ms step_avg:406.87ms step:839/6250 train_loss:2.8446 train_time:337293ms step_avg:406.87ms step:840/6250 train_loss:2.8299 train_time:337696ms step_avg:406.86ms step:841/6250 train_loss:2.9357 train_time:338094ms step_avg:406.85ms step:842/6250 train_loss:2.8032 train_time:338496ms step_avg:406.85ms step:843/6250 train_loss:2.8110 train_time:338898ms step_avg:406.84ms step:844/6250 train_loss:2.7069 train_time:339300ms step_avg:406.83ms step:845/6250 train_loss:2.8528 train_time:339720ms step_avg:406.85ms step:846/6250 train_loss:2.8801 train_time:340159ms step_avg:406.89ms step:847/6250 train_loss:2.7848 train_time:340578ms step_avg:406.90ms step:848/6250 train_loss:2.9107 train_time:341002ms step_avg:406.92ms step:849/6250 train_loss:2.8201 train_time:341404ms step_avg:406.92ms step:850/6250 train_loss:2.9074 train_time:341805ms step_avg:406.91ms step:851/6250 train_loss:2.6952 train_time:342207ms step_avg:406.90ms step:852/6250 train_loss:2.9070 train_time:342608ms step_avg:406.90ms step:853/6250 train_loss:2.7248 train_time:343005ms step_avg:406.89ms step:854/6250 train_loss:2.8767 train_time:343406ms step_avg:406.88ms step:855/6250 train_loss:2.8035 train_time:343808ms step_avg:406.87ms step:856/6250 train_loss:2.7683 train_time:344220ms step_avg:406.88ms step:857/6250 train_loss:2.7521 train_time:344632ms step_avg:406.89ms step:858/6250 train_loss:2.8875 train_time:345033ms step_avg:406.88ms step:859/6250 train_loss:2.8047 train_time:345440ms step_avg:406.88ms step:860/6250 train_loss:2.7552 train_time:345843ms step_avg:406.87ms step:861/6250 train_loss:2.7755 train_time:346243ms step_avg:406.87ms step:862/6250 train_loss:2.8090 train_time:346643ms step_avg:406.86ms step:863/6250 train_loss:2.7756 train_time:347042ms step_avg:406.85ms step:864/6250 train_loss:2.7538 train_time:347441ms step_avg:406.84ms step:865/6250 train_loss:2.7991 train_time:347846ms step_avg:406.84ms step:866/6250 train_loss:2.7668 train_time:348252ms step_avg:406.84ms step:867/6250 train_loss:2.7248 train_time:348656ms step_avg:406.83ms step:868/6250 train_loss:2.8125 train_time:349058ms step_avg:406.83ms step:869/6250 train_loss:2.7576 train_time:349461ms step_avg:406.82ms step:870/6250 train_loss:2.7675 train_time:349861ms step_avg:406.82ms step:871/6250 train_loss:2.8468 train_time:350264ms step_avg:406.81ms step:872/6250 train_loss:2.8709 train_time:350667ms step_avg:406.81ms step:873/6250 train_loss:2.7986 train_time:351067ms step_avg:406.80ms step:874/6250 train_loss:2.7663 train_time:351465ms step_avg:406.79ms step:875/6250 train_loss:2.7623 train_time:351869ms step_avg:406.79ms step:876/6250 train_loss:2.7975 train_time:352273ms step_avg:406.78ms step:877/6250 train_loss:2.8674 train_time:352676ms step_avg:406.78ms step:878/6250 train_loss:2.7311 train_time:353077ms step_avg:406.77ms step:879/6250 train_loss:2.6730 train_time:353478ms step_avg:406.76ms step:880/6250 train_loss:2.7508 train_time:353880ms step_avg:406.76ms step:881/6250 train_loss:2.8472 train_time:354282ms step_avg:406.75ms step:882/6250 train_loss:2.7898 train_time:354680ms step_avg:406.74ms step:883/6250 train_loss:2.8339 train_time:355083ms step_avg:406.74ms step:884/6250 train_loss:2.7398 train_time:355484ms step_avg:406.73ms step:885/6250 train_loss:2.7084 train_time:355884ms step_avg:406.72ms step:886/6250 train_loss:2.8055 train_time:356286ms step_avg:406.72ms step:887/6250 train_loss:2.7947 train_time:356685ms step_avg:406.71ms step:888/6250 train_loss:2.8346 train_time:357086ms step_avg:406.70ms step:889/6250 train_loss:2.8094 train_time:357489ms step_avg:406.70ms step:890/6250 train_loss:2.8170 train_time:357890ms step_avg:406.69ms step:891/6250 train_loss:2.7919 train_time:358291ms step_avg:406.69ms step:892/6250 train_loss:2.8611 train_time:358692ms step_avg:406.68ms step:893/6250 train_loss:2.8496 train_time:359091ms step_avg:406.67ms step:894/6250 train_loss:2.7140 train_time:359494ms step_avg:406.67ms step:895/6250 train_loss:2.7870 train_time:359895ms step_avg:406.66ms step:896/6250 train_loss:2.7556 train_time:360298ms step_avg:406.66ms step:897/6250 train_loss:2.7328 train_time:360700ms step_avg:406.65ms step:898/6250 train_loss:2.7617 train_time:361139ms step_avg:406.69ms step:899/6250 train_loss:2.7353 train_time:361583ms step_avg:406.73ms step:900/6250 train_loss:2.7475 train_time:361985ms step_avg:406.72ms step:901/6250 train_loss:2.7317 train_time:362383ms step_avg:406.72ms step:902/6250 train_loss:2.7839 train_time:362809ms step_avg:406.74ms step:903/6250 train_loss:2.8557 train_time:363241ms step_avg:406.77ms step:904/6250 train_loss:2.7106 train_time:363650ms step_avg:406.77ms step:905/6250 train_loss:2.6532 train_time:364051ms step_avg:406.76ms step:906/6250 train_loss:2.7515 train_time:364464ms step_avg:406.77ms step:907/6250 train_loss:2.8161 train_time:364874ms step_avg:406.77ms step:908/6250 train_loss:2.8657 train_time:365278ms step_avg:406.77ms step:909/6250 train_loss:2.7422 train_time:365683ms step_avg:406.77ms step:910/6250 train_loss:2.7880 train_time:366093ms step_avg:406.77ms step:911/6250 train_loss:2.7506 train_time:366523ms step_avg:406.80ms step:912/6250 train_loss:2.7552 train_time:366961ms step_avg:406.83ms step:913/6250 train_loss:2.8485 train_time:367403ms step_avg:406.87ms step:914/6250 train_loss:2.7303 train_time:367809ms step_avg:406.87ms step:915/6250 train_loss:2.7877 train_time:368217ms step_avg:406.87ms step:916/6250 train_loss:2.7719 train_time:368622ms step_avg:406.87ms step:917/6250 train_loss:2.6670 train_time:369034ms step_avg:406.87ms step:918/6250 train_loss:2.7669 train_time:369443ms step_avg:406.88ms step:919/6250 train_loss:2.7416 train_time:369849ms step_avg:406.87ms step:920/6250 train_loss:2.8054 train_time:370251ms step_avg:406.87ms step:921/6250 train_loss:2.7742 train_time:370654ms step_avg:406.86ms step:922/6250 train_loss:2.7346 train_time:371058ms step_avg:406.86ms step:923/6250 train_loss:2.7243 train_time:371466ms step_avg:406.86ms step:924/6250 train_loss:2.8156 train_time:371899ms step_avg:406.89ms step:925/6250 train_loss:2.7707 train_time:372303ms step_avg:406.89ms step:926/6250 train_loss:2.8590 train_time:372709ms step_avg:406.89ms step:927/6250 train_loss:2.8275 train_time:373154ms step_avg:406.93ms step:928/6250 train_loss:2.7674 train_time:373607ms step_avg:406.98ms step:929/6250 train_loss:2.7915 train_time:374053ms step_avg:407.02ms step:930/6250 train_loss:2.8614 train_time:374471ms step_avg:407.03ms step:931/6250 train_loss:2.7716 train_time:374872ms step_avg:407.03ms step:932/6250 train_loss:2.7799 train_time:375280ms step_avg:407.03ms step:933/6250 train_loss:2.7817 train_time:375686ms step_avg:407.03ms step:934/6250 train_loss:2.7980 train_time:376095ms step_avg:407.03ms step:935/6250 train_loss:2.7039 train_time:376504ms step_avg:407.03ms step:936/6250 train_loss:2.7847 train_time:376911ms step_avg:407.03ms step:937/6250 train_loss:2.7548 train_time:377318ms step_avg:407.03ms step:938/6250 train_loss:2.7046 train_time:377728ms step_avg:407.03ms step:939/6250 train_loss:2.7324 train_time:378135ms step_avg:407.03ms step:940/6250 train_loss:2.8248 train_time:378543ms step_avg:407.04ms step:941/6250 train_loss:2.8098 train_time:378951ms step_avg:407.04ms step:942/6250 train_loss:2.7815 train_time:379361ms step_avg:407.04ms step:943/6250 train_loss:2.7977 train_time:379771ms step_avg:407.04ms step:944/6250 train_loss:2.7404 train_time:380177ms step_avg:407.04ms step:945/6250 train_loss:2.8161 train_time:380589ms step_avg:407.05ms step:946/6250 train_loss:2.7766 train_time:380995ms step_avg:407.05ms step:947/6250 train_loss:2.7248 train_time:381402ms step_avg:407.05ms step:948/6250 train_loss:2.7157 train_time:381810ms step_avg:407.05ms step:949/6250 train_loss:2.7412 train_time:382217ms step_avg:407.05ms step:950/6250 train_loss:2.6525 train_time:382623ms step_avg:407.05ms step:951/6250 train_loss:2.7155 train_time:383032ms step_avg:407.05ms step:952/6250 train_loss:2.9166 train_time:383442ms step_avg:407.05ms step:953/6250 train_loss:2.7449 train_time:383852ms step_avg:407.05ms step:954/6250 train_loss:2.7290 train_time:384260ms step_avg:407.06ms step:955/6250 train_loss:2.7884 train_time:384668ms step_avg:407.06ms step:956/6250 train_loss:2.8462 train_time:385076ms step_avg:407.06ms step:957/6250 train_loss:2.7285 train_time:385482ms step_avg:407.06ms step:958/6250 train_loss:2.6743 train_time:385890ms step_avg:407.06ms step:959/6250 train_loss:2.7028 train_time:386298ms step_avg:407.06ms step:960/6250 train_loss:2.7792 train_time:386708ms step_avg:407.06ms step:961/6250 train_loss:2.7280 train_time:387116ms step_avg:407.06ms step:962/6250 train_loss:2.7632 train_time:387515ms step_avg:407.05ms step:963/6250 train_loss:2.7310 train_time:387918ms step_avg:407.05ms step:964/6250 train_loss:2.8315 train_time:388322ms step_avg:407.05ms step:965/6250 train_loss:2.7961 train_time:388731ms step_avg:407.05ms step:966/6250 train_loss:2.7423 train_time:389138ms step_avg:407.05ms step:967/6250 train_loss:2.7941 train_time:389545ms step_avg:407.05ms step:968/6250 train_loss:2.7749 train_time:389951ms step_avg:407.05ms step:969/6250 train_loss:2.6622 train_time:390362ms step_avg:407.05ms step:970/6250 train_loss:2.7760 train_time:390769ms step_avg:407.05ms step:971/6250 train_loss:2.8160 train_time:391200ms step_avg:407.08ms step:972/6250 train_loss:2.6872 train_time:391620ms step_avg:407.09ms step:973/6250 train_loss:2.7983 train_time:392024ms step_avg:407.09ms step:974/6250 train_loss:2.7300 train_time:392436ms step_avg:407.09ms step:975/6250 train_loss:2.7648 train_time:392839ms step_avg:407.09ms step:976/6250 train_loss:2.7596 train_time:393242ms step_avg:407.08ms step:977/6250 train_loss:2.8009 train_time:393646ms step_avg:407.08ms step:978/6250 train_loss:2.7879 train_time:394047ms step_avg:407.07ms step:979/6250 train_loss:2.7528 train_time:394446ms step_avg:407.07ms step:980/6250 train_loss:2.6668 train_time:394855ms step_avg:407.07ms step:981/6250 train_loss:2.8235 train_time:395270ms step_avg:407.07ms step:982/6250 train_loss:2.7805 train_time:395672ms step_avg:407.07ms step:983/6250 train_loss:2.7858 train_time:396072ms step_avg:407.06ms step:984/6250 train_loss:2.8952 train_time:396474ms step_avg:407.06ms step:985/6250 train_loss:2.7217 train_time:396874ms step_avg:407.05ms step:986/6250 train_loss:2.8340 train_time:397275ms step_avg:407.04ms step:987/6250 train_loss:2.7298 train_time:397676ms step_avg:407.04ms step:988/6250 train_loss:2.7180 train_time:398091ms step_avg:407.05ms step:989/6250 train_loss:2.6425 train_time:398520ms step_avg:407.07ms step:990/6250 train_loss:2.7984 train_time:398947ms step_avg:407.09ms step:991/6250 train_loss:2.7295 train_time:399363ms step_avg:407.10ms step:992/6250 train_loss:2.7376 train_time:399799ms step_avg:407.13ms step:993/6250 train_loss:2.7674 train_time:400240ms step_avg:407.16ms step:994/6250 train_loss:2.7727 train_time:400667ms step_avg:407.18ms step:995/6250 train_loss:2.7707 train_time:401068ms step_avg:407.18ms step:996/6250 train_loss:2.8167 train_time:401471ms step_avg:407.17ms step:997/6250 train_loss:2.8556 train_time:401874ms step_avg:407.17ms step:998/6250 train_loss:2.7582 train_time:402275ms step_avg:407.16ms step:999/6250 train_loss:2.6622 train_time:402677ms step_avg:407.16ms step:1000/6250 train_loss:2.7493 train_time:403080ms step_avg:407.15ms step:1001/6250 train_loss:2.7253 train_time:403483ms step_avg:407.15ms step:1002/6250 train_loss:2.6959 train_time:403884ms step_avg:407.14ms step:1003/6250 train_loss:2.7470 train_time:404281ms step_avg:407.13ms step:1004/6250 train_loss:2.7384 train_time:404683ms step_avg:407.13ms step:1005/6250 train_loss:2.7629 train_time:405083ms step_avg:407.12ms step:1006/6250 train_loss:2.7980 train_time:405485ms step_avg:407.11ms step:1007/6250 train_loss:2.7806 train_time:405882ms step_avg:407.10ms step:1008/6250 train_loss:2.7244 train_time:406281ms step_avg:407.10ms step:1009/6250 train_loss:2.7483 train_time:406681ms step_avg:407.09ms step:1010/6250 train_loss:2.7463 train_time:407084ms step_avg:407.08ms step:1011/6250 train_loss:2.7041 train_time:407486ms step_avg:407.08ms step:1012/6250 train_loss:2.7087 train_time:407884ms step_avg:407.07ms step:1013/6250 train_loss:2.7951 train_time:408283ms step_avg:407.06ms step:1014/6250 train_loss:2.8134 train_time:408683ms step_avg:407.05ms step:1015/6250 train_loss:2.7979 train_time:409083ms step_avg:407.05ms step:1016/6250 train_loss:2.8113 train_time:409483ms step_avg:407.04ms step:1017/6250 train_loss:2.7387 train_time:409880ms step_avg:407.03ms step:1018/6250 train_loss:2.7784 train_time:410283ms step_avg:407.03ms step:1019/6250 train_loss:2.7598 train_time:410697ms step_avg:407.03ms step:1020/6250 train_loss:2.7653 train_time:411110ms step_avg:407.04ms step:1021/6250 train_loss:2.7309 train_time:411524ms step_avg:407.05ms step:1022/6250 train_loss:2.7804 train_time:411938ms step_avg:407.05ms step:1023/6250 train_loss:2.7677 train_time:412350ms step_avg:407.06ms step:1024/6250 train_loss:2.8887 train_time:412766ms step_avg:407.07ms step:1025/6250 train_loss:2.7946 train_time:413178ms step_avg:407.07ms step:1026/6250 train_loss:2.7496 train_time:413590ms step_avg:407.08ms step:1027/6250 train_loss:2.6828 train_time:413995ms step_avg:407.07ms step:1028/6250 train_loss:2.7066 train_time:414400ms step_avg:407.07ms step:1029/6250 train_loss:2.6910 train_time:414802ms step_avg:407.07ms step:1030/6250 train_loss:2.7630 train_time:415206ms step_avg:407.07ms step:1031/6250 train_loss:2.7559 train_time:415608ms step_avg:407.06ms step:1032/6250 train_loss:2.8210 train_time:416011ms step_avg:407.06ms step:1033/6250 train_loss:2.7391 train_time:416416ms step_avg:407.05ms step:1034/6250 train_loss:2.7938 train_time:416820ms step_avg:407.05ms step:1035/6250 train_loss:2.7192 train_time:417222ms step_avg:407.05ms step:1036/6250 train_loss:2.8276 train_time:417627ms step_avg:407.04ms step:1037/6250 train_loss:2.8493 train_time:418034ms step_avg:407.04ms step:1038/6250 train_loss:2.6932 train_time:418437ms step_avg:407.04ms step:1039/6250 train_loss:2.7562 train_time:418844ms step_avg:407.04ms step:1040/6250 train_loss:2.7161 train_time:419246ms step_avg:407.04ms step:1041/6250 train_loss:2.7258 train_time:419649ms step_avg:407.03ms step:1042/6250 train_loss:2.7522 train_time:420053ms step_avg:407.03ms step:1043/6250 train_loss:2.7332 train_time:420455ms step_avg:407.02ms step:1044/6250 train_loss:2.8261 train_time:420857ms step_avg:407.02ms step:1045/6250 train_loss:2.8150 train_time:421260ms step_avg:407.01ms step:1046/6250 train_loss:2.7648 train_time:421667ms step_avg:407.01ms step:1047/6250 train_loss:2.7877 train_time:422072ms step_avg:407.01ms step:1048/6250 train_loss:2.7365 train_time:422478ms step_avg:407.01ms step:1049/6250 train_loss:2.7385 train_time:422879ms step_avg:407.01ms step:1050/6250 train_loss:2.7344 train_time:423283ms step_avg:407.00ms step:1051/6250 train_loss:2.7210 train_time:423683ms step_avg:407.00ms step:1052/6250 train_loss:2.7481 train_time:424083ms step_avg:406.99ms step:1053/6250 train_loss:2.6652 train_time:424484ms step_avg:406.98ms step:1054/6250 train_loss:2.7453 train_time:424882ms step_avg:406.97ms step:1055/6250 train_loss:2.6761 train_time:425280ms step_avg:406.97ms step:1056/6250 train_loss:2.7032 train_time:425680ms step_avg:406.96ms step:1057/6250 train_loss:2.7180 train_time:426080ms step_avg:406.95ms step:1058/6250 train_loss:2.7553 train_time:426480ms step_avg:406.95ms step:1059/6250 train_loss:2.8244 train_time:426877ms step_avg:406.94ms step:1060/6250 train_loss:2.6977 train_time:427277ms step_avg:406.93ms step:1061/6250 train_loss:2.7799 train_time:427677ms step_avg:406.92ms step:1062/6250 train_loss:2.7664 train_time:428077ms step_avg:406.92ms step:1063/6250 train_loss:2.7759 train_time:428477ms step_avg:406.91ms step:1064/6250 train_loss:2.7355 train_time:428875ms step_avg:406.90ms step:1065/6250 train_loss:2.7610 train_time:429274ms step_avg:406.89ms step:1066/6250 train_loss:2.7652 train_time:429674ms step_avg:406.89ms step:1067/6250 train_loss:2.7087 train_time:430071ms step_avg:406.88ms step:1068/6250 train_loss:2.8229 train_time:430468ms step_avg:406.87ms step:1069/6250 train_loss:2.7372 train_time:430868ms step_avg:406.86ms step:1070/6250 train_loss:2.7544 train_time:431268ms step_avg:406.86ms step:1071/6250 train_loss:2.8223 train_time:431667ms step_avg:406.85ms step:1072/6250 train_loss:2.7433 train_time:432066ms step_avg:406.84ms step:1073/6250 train_loss:2.7341 train_time:432466ms step_avg:406.84ms step:1074/6250 train_loss:2.7129 train_time:432870ms step_avg:406.83ms step:1075/6250 train_loss:2.6672 train_time:433274ms step_avg:406.83ms step:1076/6250 train_loss:2.6684 train_time:433679ms step_avg:406.83ms step:1077/6250 train_loss:2.6722 train_time:434082ms step_avg:406.82ms step:1078/6250 train_loss:2.7392 train_time:434488ms step_avg:406.82ms step:1079/6250 train_loss:2.7243 train_time:434891ms step_avg:406.82ms step:1080/6250 train_loss:2.6373 train_time:435294ms step_avg:406.82ms step:1081/6250 train_loss:2.6692 train_time:435698ms step_avg:406.81ms step:1082/6250 train_loss:2.7411 train_time:436100ms step_avg:406.81ms step:1083/6250 train_loss:2.6586 train_time:436501ms step_avg:406.80ms step:1084/6250 train_loss:2.8272 train_time:436897ms step_avg:406.79ms step:1085/6250 train_loss:2.7352 train_time:437297ms step_avg:406.79ms step:1086/6250 train_loss:2.6867 train_time:437699ms step_avg:406.78ms step:1087/6250 train_loss:2.7006 train_time:438100ms step_avg:406.78ms step:1088/6250 train_loss:2.7893 train_time:438500ms step_avg:406.77ms step:1089/6250 train_loss:2.6787 train_time:438903ms step_avg:406.77ms step:1090/6250 train_loss:2.8149 train_time:439308ms step_avg:406.77ms step:1091/6250 train_loss:2.7950 train_time:439710ms step_avg:406.76ms step:1092/6250 train_loss:2.6615 train_time:440118ms step_avg:406.76ms step:1093/6250 train_loss:2.7291 train_time:440522ms step_avg:406.76ms step:1094/6250 train_loss:2.6743 train_time:440924ms step_avg:406.76ms step:1095/6250 train_loss:2.7499 train_time:441327ms step_avg:406.75ms step:1096/6250 train_loss:2.7139 train_time:441728ms step_avg:406.75ms step:1097/6250 train_loss:2.7588 train_time:442129ms step_avg:406.74ms step:1098/6250 train_loss:2.7395 train_time:442529ms step_avg:406.74ms step:1099/6250 train_loss:2.8096 train_time:442925ms step_avg:406.73ms step:1100/6250 train_loss:2.7518 train_time:443327ms step_avg:406.72ms step:1101/6250 train_loss:2.7629 train_time:443726ms step_avg:406.71ms step:1102/6250 train_loss:2.7321 train_time:444123ms step_avg:406.71ms step:1103/6250 train_loss:2.6769 train_time:444522ms step_avg:406.70ms step:1104/6250 train_loss:2.7329 train_time:444921ms step_avg:406.69ms step:1105/6250 train_loss:2.7142 train_time:445323ms step_avg:406.69ms step:1106/6250 train_loss:2.8145 train_time:445720ms step_avg:406.68ms step:1107/6250 train_loss:2.7631 train_time:446121ms step_avg:406.67ms step:1108/6250 train_loss:2.6862 train_time:446522ms step_avg:406.67ms step:1109/6250 train_loss:2.7424 train_time:446922ms step_avg:406.66ms step:1110/6250 train_loss:2.6964 train_time:447324ms step_avg:406.66ms step:1111/6250 train_loss:2.7054 train_time:447725ms step_avg:406.65ms step:1112/6250 train_loss:2.8125 train_time:448123ms step_avg:406.65ms step:1113/6250 train_loss:2.7156 train_time:448524ms step_avg:406.64ms step:1114/6250 train_loss:2.7106 train_time:448922ms step_avg:406.63ms step:1115/6250 train_loss:2.6788 train_time:449321ms step_avg:406.63ms step:1116/6250 train_loss:2.5725 train_time:449720ms step_avg:406.62ms step:1117/6250 train_loss:2.6895 train_time:450123ms step_avg:406.61ms step:1118/6250 train_loss:2.6502 train_time:450524ms step_avg:406.61ms step:1119/6250 train_loss:2.6406 train_time:450926ms step_avg:406.61ms step:1120/6250 train_loss:2.6698 train_time:451326ms step_avg:406.60ms step:1121/6250 train_loss:2.8073 train_time:451725ms step_avg:406.59ms step:1122/6250 train_loss:2.7084 train_time:452125ms step_avg:406.59ms step:1123/6250 train_loss:2.6158 train_time:452528ms step_avg:406.58ms step:1124/6250 train_loss:2.7380 train_time:452952ms step_avg:406.60ms step:1125/6250 train_loss:2.7809 train_time:453357ms step_avg:406.60ms step:1126/6250 train_loss:2.6185 train_time:453760ms step_avg:406.60ms step:1127/6250 train_loss:2.8149 train_time:454159ms step_avg:406.59ms step:1128/6250 train_loss:2.6240 train_time:454560ms step_avg:406.58ms step:1129/6250 train_loss:2.8060 train_time:454960ms step_avg:406.58ms step:1130/6250 train_loss:2.7101 train_time:455360ms step_avg:406.57ms step:1131/6250 train_loss:2.7550 train_time:455765ms step_avg:406.57ms step:1132/6250 train_loss:2.7400 train_time:456170ms step_avg:406.57ms step:1133/6250 train_loss:2.7301 train_time:456573ms step_avg:406.57ms step:1134/6250 train_loss:2.6637 train_time:456968ms step_avg:406.56ms step:1135/6250 train_loss:2.7853 train_time:457369ms step_avg:406.55ms step:1136/6250 train_loss:2.7183 train_time:457769ms step_avg:406.54ms step:1137/6250 train_loss:2.7580 train_time:458167ms step_avg:406.54ms step:1138/6250 train_loss:2.8212 train_time:458571ms step_avg:406.53ms step:1139/6250 train_loss:2.7596 train_time:458987ms step_avg:406.54ms step:1140/6250 train_loss:2.7567 train_time:459385ms step_avg:406.54ms step:1141/6250 train_loss:2.7059 train_time:459786ms step_avg:406.53ms step:1142/6250 train_loss:2.6537 train_time:460183ms step_avg:406.52ms step:1143/6250 train_loss:2.7152 train_time:460584ms step_avg:406.52ms step:1144/6250 train_loss:2.7115 train_time:460984ms step_avg:406.51ms step:1145/6250 train_loss:2.6729 train_time:461391ms step_avg:406.51ms step:1146/6250 train_loss:2.7683 train_time:461805ms step_avg:406.52ms step:1147/6250 train_loss:2.7315 train_time:462224ms step_avg:406.53ms step:1148/6250 train_loss:2.7646 train_time:462642ms step_avg:406.54ms step:1149/6250 train_loss:2.6602 train_time:463045ms step_avg:406.54ms step:1150/6250 train_loss:2.6485 train_time:463480ms step_avg:406.56ms step:1151/6250 train_loss:2.6478 train_time:463911ms step_avg:406.58ms step:1152/6250 train_loss:2.7228 train_time:464333ms step_avg:406.60ms step:1153/6250 train_loss:2.7168 train_time:464742ms step_avg:406.60ms step:1154/6250 train_loss:2.7314 train_time:465152ms step_avg:406.60ms step:1155/6250 train_loss:2.7130 train_time:465583ms step_avg:406.62ms step:1156/6250 train_loss:2.7437 train_time:466023ms step_avg:406.65ms step:1157/6250 train_loss:2.6880 train_time:466462ms step_avg:406.68ms step:1158/6250 train_loss:2.6920 train_time:466896ms step_avg:406.70ms step:1159/6250 train_loss:2.8036 train_time:467343ms step_avg:406.74ms step:1160/6250 train_loss:2.6946 train_time:467786ms step_avg:406.77ms step:1161/6250 train_loss:2.7902 train_time:468223ms step_avg:406.80ms step:1162/6250 train_loss:2.6723 train_time:468632ms step_avg:406.80ms step:1163/6250 train_loss:2.7512 train_time:469048ms step_avg:406.81ms step:1164/6250 train_loss:2.5979 train_time:469461ms step_avg:406.81ms step:1165/6250 train_loss:2.7478 train_time:469876ms step_avg:406.82ms step:1166/6250 train_loss:2.6570 train_time:470298ms step_avg:406.83ms step:1167/6250 train_loss:2.7433 train_time:470715ms step_avg:406.84ms step:1168/6250 train_loss:2.7272 train_time:471129ms step_avg:406.85ms step:1169/6250 train_loss:2.6998 train_time:471542ms step_avg:406.85ms step:1170/6250 train_loss:2.7348 train_time:471963ms step_avg:406.86ms step:1171/6250 train_loss:2.6979 train_time:472384ms step_avg:406.88ms step:1172/6250 train_loss:2.6554 train_time:472798ms step_avg:406.88ms step:1173/6250 train_loss:2.7904 train_time:473215ms step_avg:406.89ms step:1174/6250 train_loss:2.7701 train_time:473632ms step_avg:406.90ms step:1175/6250 train_loss:2.7588 train_time:474048ms step_avg:406.91ms step:1176/6250 train_loss:2.6515 train_time:474461ms step_avg:406.91ms step:1177/6250 train_loss:2.7430 train_time:474884ms step_avg:406.93ms step:1178/6250 train_loss:2.7167 train_time:475327ms step_avg:406.96ms step:1179/6250 train_loss:2.7341 train_time:475754ms step_avg:406.97ms step:1180/6250 train_loss:2.6854 train_time:476177ms step_avg:406.99ms step:1181/6250 train_loss:2.7773 train_time:476601ms step_avg:407.00ms step:1182/6250 train_loss:2.7541 train_time:477030ms step_avg:407.02ms step:1183/6250 train_loss:2.6496 train_time:477462ms step_avg:407.04ms step:1184/6250 train_loss:2.6647 train_time:477887ms step_avg:407.06ms step:1185/6250 train_loss:2.6920 train_time:478320ms step_avg:407.08ms step:1186/6250 train_loss:2.7092 train_time:478747ms step_avg:407.10ms step:1187/6250 train_loss:2.6487 train_time:479174ms step_avg:407.11ms step:1188/6250 train_loss:2.5685 train_time:479607ms step_avg:407.14ms step:1189/6250 train_loss:2.7443 train_time:480030ms step_avg:407.15ms step:1190/6250 train_loss:2.7411 train_time:480454ms step_avg:407.16ms step:1191/6250 train_loss:2.7012 train_time:480883ms step_avg:407.18ms step:1192/6250 train_loss:2.6853 train_time:481307ms step_avg:407.20ms step:1193/6250 train_loss:2.7555 train_time:481730ms step_avg:407.21ms step:1194/6250 train_loss:2.8077 train_time:482156ms step_avg:407.23ms step:1195/6250 train_loss:2.8542 train_time:482587ms step_avg:407.25ms step:1196/6250 train_loss:2.6438 train_time:483011ms step_avg:407.26ms step:1197/6250 train_loss:2.6557 train_time:483435ms step_avg:407.27ms step:1198/6250 train_loss:2.6889 train_time:483863ms step_avg:407.29ms step:1199/6250 train_loss:2.6194 train_time:484289ms step_avg:407.31ms step:1200/6250 train_loss:2.6456 train_time:484711ms step_avg:407.32ms step:1201/6250 train_loss:2.8109 train_time:485133ms step_avg:407.33ms step:1202/6250 train_loss:2.6920 train_time:485553ms step_avg:407.34ms step:1203/6250 train_loss:2.6569 train_time:485990ms step_avg:407.37ms step:1204/6250 train_loss:2.7338 train_time:486408ms step_avg:407.38ms step:1205/6250 train_loss:2.7298 train_time:486824ms step_avg:407.38ms step:1206/6250 train_loss:2.7456 train_time:487239ms step_avg:407.39ms step:1207/6250 train_loss:2.6825 train_time:487656ms step_avg:407.40ms step:1208/6250 train_loss:2.6740 train_time:488068ms step_avg:407.40ms step:1209/6250 train_loss:2.7565 train_time:488486ms step_avg:407.41ms step:1210/6250 train_loss:2.6707 train_time:488905ms step_avg:407.42ms step:1211/6250 train_loss:2.7363 train_time:489319ms step_avg:407.43ms step:1212/6250 train_loss:2.7753 train_time:489737ms step_avg:407.44ms step:1213/6250 train_loss:2.6689 train_time:490150ms step_avg:407.44ms step:1214/6250 train_loss:2.7155 train_time:490563ms step_avg:407.44ms step:1215/6250 train_loss:2.7026 train_time:490973ms step_avg:407.45ms step:1216/6250 train_loss:2.6417 train_time:491384ms step_avg:407.45ms step:1217/6250 train_loss:2.7686 train_time:491793ms step_avg:407.45ms step:1218/6250 train_loss:2.6973 train_time:492205ms step_avg:407.45ms step:1219/6250 train_loss:2.7391 train_time:492617ms step_avg:407.46ms step:1220/6250 train_loss:2.7794 train_time:493030ms step_avg:407.46ms step:1221/6250 train_loss:2.7590 train_time:493441ms step_avg:407.47ms step:1222/6250 train_loss:2.7032 train_time:493850ms step_avg:407.47ms step:1223/6250 train_loss:2.6736 train_time:494261ms step_avg:407.47ms step:1224/6250 train_loss:2.6941 train_time:494676ms step_avg:407.48ms step:1225/6250 train_loss:2.7298 train_time:495084ms step_avg:407.48ms step:1226/6250 train_loss:2.5740 train_time:495496ms step_avg:407.48ms step:1227/6250 train_loss:2.6346 train_time:495935ms step_avg:407.51ms step:1228/6250 train_loss:2.7777 train_time:496367ms step_avg:407.53ms step:1229/6250 train_loss:2.7168 train_time:496797ms step_avg:407.54ms step:1230/6250 train_loss:2.7302 train_time:497222ms step_avg:407.56ms step:1231/6250 train_loss:2.7430 train_time:497644ms step_avg:407.57ms step:1232/6250 train_loss:2.7201 train_time:498056ms step_avg:407.57ms step:1233/6250 train_loss:2.8477 train_time:498472ms step_avg:407.58ms step:1234/6250 train_loss:2.6773 train_time:498884ms step_avg:407.59ms step:1235/6250 train_loss:2.6734 train_time:499321ms step_avg:407.61ms step:1236/6250 train_loss:2.7637 train_time:499748ms step_avg:407.63ms step:1237/6250 train_loss:2.6318 train_time:500156ms step_avg:407.63ms step:1238/6250 train_loss:2.6643 train_time:500602ms step_avg:407.66ms step:1239/6250 train_loss:2.7786 train_time:501044ms step_avg:407.68ms step:1240/6250 train_loss:2.6201 train_time:501477ms step_avg:407.70ms step:1241/6250 train_loss:2.7533 train_time:501928ms step_avg:407.74ms step:1242/6250 train_loss:2.7938 train_time:502349ms step_avg:407.75ms step:1243/6250 train_loss:2.6909 train_time:502760ms step_avg:407.75ms step:1244/6250 train_loss:2.6860 train_time:503173ms step_avg:407.76ms step:1245/6250 train_loss:2.6420 train_time:503582ms step_avg:407.76ms step:1246/6250 train_loss:2.7109 train_time:503994ms step_avg:407.76ms step:1247/6250 train_loss:2.6331 train_time:504406ms step_avg:407.77ms step:1248/6250 train_loss:2.7493 train_time:504816ms step_avg:407.77ms step:1249/6250 train_loss:2.8089 train_time:505226ms step_avg:407.77ms step:1250/6250 train_loss:2.7694 train_time:505637ms step_avg:407.77ms step:1251/6250 train_loss:2.6868 train_time:506047ms step_avg:407.77ms step:1252/6250 train_loss:2.7846 train_time:506459ms step_avg:407.78ms step:1253/6250 train_loss:2.7376 train_time:506869ms step_avg:407.78ms step:1254/6250 train_loss:2.8018 train_time:507279ms step_avg:407.78ms step:1255/6250 train_loss:2.8002 train_time:507694ms step_avg:407.79ms step:1256/6250 train_loss:2.7206 train_time:508124ms step_avg:407.80ms step:1257/6250 train_loss:2.6809 train_time:508534ms step_avg:407.81ms step:1258/6250 train_loss:2.7666 train_time:508964ms step_avg:407.82ms step:1259/6250 train_loss:2.7036 train_time:509375ms step_avg:407.83ms step:1260/6250 train_loss:2.6459 train_time:509786ms step_avg:407.83ms step:1261/6250 train_loss:2.7435 train_time:510197ms step_avg:407.83ms step:1262/6250 train_loss:2.8070 train_time:510612ms step_avg:407.84ms step:1263/6250 train_loss:2.7333 train_time:511024ms step_avg:407.84ms step:1264/6250 train_loss:2.7301 train_time:511437ms step_avg:407.84ms step:1265/6250 train_loss:2.7556 train_time:511845ms step_avg:407.84ms step:1266/6250 train_loss:2.6365 train_time:512258ms step_avg:407.85ms step:1267/6250 train_loss:2.7428 train_time:512668ms step_avg:407.85ms step:1268/6250 train_loss:2.6995 train_time:513083ms step_avg:407.86ms step:1269/6250 train_loss:2.6544 train_time:513492ms step_avg:407.86ms step:1270/6250 train_loss:2.6465 train_time:513902ms step_avg:407.86ms step:1271/6250 train_loss:2.7323 train_time:514312ms step_avg:407.86ms step:1272/6250 train_loss:2.7019 train_time:514722ms step_avg:407.86ms step:1273/6250 train_loss:2.7075 train_time:515133ms step_avg:407.86ms step:1274/6250 train_loss:2.7277 train_time:515542ms step_avg:407.87ms step:1275/6250 train_loss:2.7232 train_time:515956ms step_avg:407.87ms step:1276/6250 train_loss:2.6019 train_time:516365ms step_avg:407.87ms step:1277/6250 train_loss:2.6830 train_time:516778ms step_avg:407.88ms step:1278/6250 train_loss:2.8084 train_time:517190ms step_avg:407.88ms step:1279/6250 train_loss:2.6584 train_time:517600ms step_avg:407.88ms step:1280/6250 train_loss:2.7844 train_time:518010ms step_avg:407.88ms step:1281/6250 train_loss:2.7302 train_time:518420ms step_avg:407.88ms step:1282/6250 train_loss:2.7207 train_time:518833ms step_avg:407.89ms step:1283/6250 train_loss:2.7386 train_time:519244ms step_avg:407.89ms step:1284/6250 train_loss:2.6607 train_time:519656ms step_avg:407.89ms step:1285/6250 train_loss:2.7104 train_time:520064ms step_avg:407.89ms step:1286/6250 train_loss:2.7721 train_time:520473ms step_avg:407.89ms step:1287/6250 train_loss:2.7507 train_time:520881ms step_avg:407.89ms step:1288/6250 train_loss:2.7569 train_time:521292ms step_avg:407.90ms step:1289/6250 train_loss:2.6709 train_time:521706ms step_avg:407.90ms step:1290/6250 train_loss:2.6820 train_time:522115ms step_avg:407.90ms step:1291/6250 train_loss:2.7647 train_time:522525ms step_avg:407.90ms step:1292/6250 train_loss:2.6149 train_time:522936ms step_avg:407.91ms step:1293/6250 train_loss:2.6833 train_time:523346ms step_avg:407.91ms step:1294/6250 train_loss:2.7921 train_time:523760ms step_avg:407.91ms step:1295/6250 train_loss:2.7421 train_time:524171ms step_avg:407.91ms step:1296/6250 train_loss:2.7031 train_time:524583ms step_avg:407.92ms step:1297/6250 train_loss:2.6486 train_time:524992ms step_avg:407.92ms step:1298/6250 train_loss:2.7434 train_time:525401ms step_avg:407.92ms step:1299/6250 train_loss:2.6792 train_time:525810ms step_avg:407.92ms step:1300/6250 train_loss:2.6783 train_time:526220ms step_avg:407.92ms step:1301/6250 train_loss:2.7267 train_time:526629ms step_avg:407.92ms step:1302/6250 train_loss:2.7109 train_time:527038ms step_avg:407.92ms step:1303/6250 train_loss:2.7745 train_time:527452ms step_avg:407.93ms step:1304/6250 train_loss:2.7090 train_time:527861ms step_avg:407.93ms step:1305/6250 train_loss:2.6471 train_time:528275ms step_avg:407.93ms step:1306/6250 train_loss:2.6314 train_time:528688ms step_avg:407.94ms step:1307/6250 train_loss:2.7864 train_time:529096ms step_avg:407.94ms step:1308/6250 train_loss:2.7563 train_time:529506ms step_avg:407.94ms step:1309/6250 train_loss:2.7478 train_time:529913ms step_avg:407.94ms step:1310/6250 train_loss:2.7022 train_time:530326ms step_avg:407.94ms step:1311/6250 train_loss:2.7000 train_time:530736ms step_avg:407.94ms step:1312/6250 train_loss:2.7643 train_time:531145ms step_avg:407.95ms step:1313/6250 train_loss:2.6656 train_time:531557ms step_avg:407.95ms step:1314/6250 train_loss:2.6978 train_time:531967ms step_avg:407.95ms step:1315/6250 train_loss:2.7055 train_time:532380ms step_avg:407.95ms step:1316/6250 train_loss:2.6208 train_time:532790ms step_avg:407.96ms step:1317/6250 train_loss:2.6791 train_time:533197ms step_avg:407.95ms step:1318/6250 train_loss:2.6341 train_time:533608ms step_avg:407.96ms step:1319/6250 train_loss:2.7345 train_time:534020ms step_avg:407.96ms step:1320/6250 train_loss:2.7440 train_time:534432ms step_avg:407.96ms step:1321/6250 train_loss:2.6890 train_time:534842ms step_avg:407.96ms step:1322/6250 train_loss:2.6811 train_time:535252ms step_avg:407.97ms step:1323/6250 train_loss:2.6556 train_time:535662ms step_avg:407.97ms step:1324/6250 train_loss:2.7845 train_time:536073ms step_avg:407.97ms step:1325/6250 train_loss:2.7500 train_time:536484ms step_avg:407.97ms step:1326/6250 train_loss:2.7772 train_time:536892ms step_avg:407.97ms step:1327/6250 train_loss:2.6053 train_time:537302ms step_avg:407.97ms step:1328/6250 train_loss:2.7109 train_time:537714ms step_avg:407.98ms step:1329/6250 train_loss:2.6908 train_time:538123ms step_avg:407.98ms step:1330/6250 train_loss:2.5995 train_time:538535ms step_avg:407.98ms step:1331/6250 train_loss:2.6351 train_time:538944ms step_avg:407.98ms step:1332/6250 train_loss:2.6935 train_time:539355ms step_avg:407.98ms step:1333/6250 train_loss:2.6664 train_time:539765ms step_avg:407.99ms step:1334/6250 train_loss:2.6965 train_time:540173ms step_avg:407.99ms step:1335/6250 train_loss:2.7189 train_time:540585ms step_avg:407.99ms step:1336/6250 train_loss:2.6534 train_time:540997ms step_avg:407.99ms step:1337/6250 train_loss:2.7515 train_time:541416ms step_avg:408.00ms step:1338/6250 train_loss:2.6177 train_time:541844ms step_avg:408.02ms step:1339/6250 train_loss:2.6548 train_time:542272ms step_avg:408.03ms step:1340/6250 train_loss:2.6756 train_time:542685ms step_avg:408.03ms step:1341/6250 train_loss:2.7765 train_time:543097ms step_avg:408.04ms step:1342/6250 train_loss:2.6094 train_time:543507ms step_avg:408.04ms step:1343/6250 train_loss:2.7002 train_time:543939ms step_avg:408.06ms step:1344/6250 train_loss:2.7740 train_time:544370ms step_avg:408.07ms step:1345/6250 train_loss:2.6924 train_time:544780ms step_avg:408.07ms step:1346/6250 train_loss:2.6596 train_time:545195ms step_avg:408.08ms step:1347/6250 train_loss:2.7065 train_time:545610ms step_avg:408.09ms step:1348/6250 train_loss:2.7056 train_time:546023ms step_avg:408.09ms step:1349/6250 train_loss:2.6539 train_time:546442ms step_avg:408.10ms step:1350/6250 train_loss:2.7294 train_time:546857ms step_avg:408.10ms step:1351/6250 train_loss:2.7129 train_time:547268ms step_avg:408.10ms step:1352/6250 train_loss:2.7888 train_time:547680ms step_avg:408.11ms step:1353/6250 train_loss:2.7092 train_time:548114ms step_avg:408.13ms step:1354/6250 train_loss:2.6628 train_time:548546ms step_avg:408.14ms step:1355/6250 train_loss:2.7043 train_time:548958ms step_avg:408.15ms step:1356/6250 train_loss:2.6710 train_time:549367ms step_avg:408.15ms step:1357/6250 train_loss:2.6607 train_time:549778ms step_avg:408.15ms step:1358/6250 train_loss:2.7691 train_time:550191ms step_avg:408.15ms step:1359/6250 train_loss:2.6385 train_time:550613ms step_avg:408.16ms step:1360/6250 train_loss:2.6524 train_time:551028ms step_avg:408.17ms step:1361/6250 train_loss:2.6136 train_time:551443ms step_avg:408.17ms step:1362/6250 train_loss:2.6357 train_time:551850ms step_avg:408.17ms step:1363/6250 train_loss:2.8311 train_time:552271ms step_avg:408.18ms step:1364/6250 train_loss:2.7347 train_time:552691ms step_avg:408.19ms step:1365/6250 train_loss:2.6658 train_time:553110ms step_avg:408.20ms step:1366/6250 train_loss:2.6221 train_time:553533ms step_avg:408.21ms step:1367/6250 train_loss:2.6404 train_time:553950ms step_avg:408.22ms step:1368/6250 train_loss:2.6501 train_time:554362ms step_avg:408.22ms step:1369/6250 train_loss:2.6405 train_time:554778ms step_avg:408.23ms step:1370/6250 train_loss:2.6627 train_time:555188ms step_avg:408.23ms step:1371/6250 train_loss:2.5990 train_time:555600ms step_avg:408.23ms step:1372/6250 train_loss:2.6512 train_time:556011ms step_avg:408.23ms step:1373/6250 train_loss:2.7267 train_time:556426ms step_avg:408.24ms step:1374/6250 train_loss:2.6587 train_time:556840ms step_avg:408.24ms step:1375/6250 train_loss:2.6861 train_time:557258ms step_avg:408.25ms step:1376/6250 train_loss:2.7470 train_time:557672ms step_avg:408.25ms step:1377/6250 train_loss:2.6575 train_time:558092ms step_avg:408.26ms step:1378/6250 train_loss:2.7335 train_time:558511ms step_avg:408.27ms step:1379/6250 train_loss:2.7791 train_time:558927ms step_avg:408.27ms step:1380/6250 train_loss:2.6914 train_time:559348ms step_avg:408.28ms step:1381/6250 train_loss:2.6954 train_time:559764ms step_avg:408.29ms step:1382/6250 train_loss:2.5810 train_time:560178ms step_avg:408.29ms step:1383/6250 train_loss:2.6936 train_time:560595ms step_avg:408.30ms step:1384/6250 train_loss:2.7315 train_time:561008ms step_avg:408.30ms step:1385/6250 train_loss:2.6807 train_time:561420ms step_avg:408.31ms step:1386/6250 train_loss:2.6368 train_time:561838ms step_avg:408.31ms step:1387/6250 train_loss:2.7131 train_time:562250ms step_avg:408.32ms step:1388/6250 train_loss:2.6879 train_time:562675ms step_avg:408.33ms step:1389/6250 train_loss:2.7002 train_time:563087ms step_avg:408.33ms step:1390/6250 train_loss:2.6105 train_time:563507ms step_avg:408.34ms step:1391/6250 train_loss:2.6784 train_time:563920ms step_avg:408.34ms step:1392/6250 train_loss:2.6982 train_time:564338ms step_avg:408.35ms step:1393/6250 train_loss:2.5902 train_time:564769ms step_avg:408.37ms step:1394/6250 train_loss:2.7082 train_time:565196ms step_avg:408.38ms step:1395/6250 train_loss:2.7020 train_time:565635ms step_avg:408.40ms step:1396/6250 train_loss:2.7805 train_time:566062ms step_avg:408.41ms step:1397/6250 train_loss:2.7300 train_time:566501ms step_avg:408.44ms step:1398/6250 train_loss:2.6918 train_time:566911ms step_avg:408.44ms step:1399/6250 train_loss:2.6457 train_time:567323ms step_avg:408.44ms step:1400/6250 train_loss:2.7356 train_time:567733ms step_avg:408.44ms step:1401/6250 train_loss:2.5249 train_time:568178ms step_avg:408.47ms step:1402/6250 train_loss:2.6886 train_time:568591ms step_avg:408.47ms step:1403/6250 train_loss:2.6799 train_time:569006ms step_avg:408.47ms step:1404/6250 train_loss:2.7079 train_time:569420ms step_avg:408.48ms step:1405/6250 train_loss:2.7061 train_time:569829ms step_avg:408.48ms step:1406/6250 train_loss:2.6172 train_time:570239ms step_avg:408.48ms step:1407/6250 train_loss:2.7029 train_time:570649ms step_avg:408.48ms step:1408/6250 train_loss:2.6614 train_time:571059ms step_avg:408.48ms step:1409/6250 train_loss:2.7298 train_time:571472ms step_avg:408.49ms step:1410/6250 train_loss:2.7505 train_time:571885ms step_avg:408.49ms step:1411/6250 train_loss:2.7073 train_time:572304ms step_avg:408.50ms step:1412/6250 train_loss:2.6606 train_time:572731ms step_avg:408.51ms step:1413/6250 train_loss:2.6456 train_time:573145ms step_avg:408.51ms step:1414/6250 train_loss:2.6974 train_time:573557ms step_avg:408.52ms step:1415/6250 train_loss:2.6806 train_time:573968ms step_avg:408.52ms step:1416/6250 train_loss:2.7630 train_time:574379ms step_avg:408.52ms step:1417/6250 train_loss:2.7699 train_time:574788ms step_avg:408.52ms step:1418/6250 train_loss:2.5479 train_time:575199ms step_avg:408.52ms step:1419/6250 train_loss:2.7407 train_time:575615ms step_avg:408.53ms step:1420/6250 train_loss:2.6000 train_time:576025ms step_avg:408.53ms step:1421/6250 train_loss:2.7429 train_time:576435ms step_avg:408.53ms step:1422/6250 train_loss:2.6894 train_time:576847ms step_avg:408.53ms step:1423/6250 train_loss:2.7488 train_time:577257ms step_avg:408.53ms step:1424/6250 train_loss:2.7767 train_time:577664ms step_avg:408.53ms step:1425/6250 train_loss:2.7174 train_time:578075ms step_avg:408.53ms step:1426/6250 train_loss:2.6593 train_time:578486ms step_avg:408.54ms step:1427/6250 train_loss:2.6386 train_time:578897ms step_avg:408.54ms step:1428/6250 train_loss:2.6243 train_time:579309ms step_avg:408.54ms step:1429/6250 train_loss:2.6478 train_time:579721ms step_avg:408.54ms step:1430/6250 train_loss:2.6603 train_time:580133ms step_avg:408.54ms step:1431/6250 train_loss:2.7871 train_time:580570ms step_avg:408.56ms step:1432/6250 train_loss:2.6682 train_time:581004ms step_avg:408.58ms step:1433/6250 train_loss:2.7247 train_time:581427ms step_avg:408.59ms step:1434/6250 train_loss:2.5876 train_time:581843ms step_avg:408.60ms step:1435/6250 train_loss:2.6828 train_time:582252ms step_avg:408.60ms step:1436/6250 train_loss:2.7104 train_time:582666ms step_avg:408.60ms step:1437/6250 train_loss:2.7031 train_time:583076ms step_avg:408.60ms step:1438/6250 train_loss:2.7158 train_time:583490ms step_avg:408.61ms step:1439/6250 train_loss:2.7554 train_time:583901ms step_avg:408.61ms step:1440/6250 train_loss:2.6585 train_time:584315ms step_avg:408.61ms step:1441/6250 train_loss:2.6140 train_time:584725ms step_avg:408.61ms step:1442/6250 train_loss:2.5729 train_time:585138ms step_avg:408.62ms step:1443/6250 train_loss:2.6938 train_time:585548ms step_avg:408.62ms step:1444/6250 train_loss:2.6343 train_time:585961ms step_avg:408.62ms step:1445/6250 train_loss:2.6596 train_time:586373ms step_avg:408.62ms step:1446/6250 train_loss:2.6662 train_time:586784ms step_avg:408.62ms step:1447/6250 train_loss:2.7045 train_time:587198ms step_avg:408.63ms step:1448/6250 train_loss:2.7225 train_time:587611ms step_avg:408.63ms step:1449/6250 train_loss:2.6461 train_time:588023ms step_avg:408.63ms step:1450/6250 train_loss:2.6750 train_time:588434ms step_avg:408.63ms step:1451/6250 train_loss:2.6448 train_time:588847ms step_avg:408.64ms step:1452/6250 train_loss:2.6379 train_time:589258ms step_avg:408.64ms step:1453/6250 train_loss:2.5673 train_time:589670ms step_avg:408.64ms step:1454/6250 train_loss:2.7421 train_time:590078ms step_avg:408.64ms step:1455/6250 train_loss:2.6351 train_time:590492ms step_avg:408.65ms step:1456/6250 train_loss:2.6060 train_time:590904ms step_avg:408.65ms step:1457/6250 train_loss:2.6869 train_time:591316ms step_avg:408.65ms step:1458/6250 train_loss:2.6728 train_time:591727ms step_avg:408.65ms step:1459/6250 train_loss:2.6252 train_time:592139ms step_avg:408.65ms step:1460/6250 train_loss:2.6852 train_time:592550ms step_avg:408.66ms step:1461/6250 train_loss:2.6120 train_time:592962ms step_avg:408.66ms step:1462/6250 train_loss:2.6099 train_time:593374ms step_avg:408.66ms step:1463/6250 train_loss:2.6082 train_time:593786ms step_avg:408.66ms step:1464/6250 train_loss:2.6576 train_time:594195ms step_avg:408.66ms step:1465/6250 train_loss:2.6142 train_time:594608ms step_avg:408.67ms step:1466/6250 train_loss:2.5987 train_time:595021ms step_avg:408.67ms step:1467/6250 train_loss:2.6057 train_time:595450ms step_avg:408.68ms step:1468/6250 train_loss:2.6061 train_time:595870ms step_avg:408.69ms step:1469/6250 train_loss:2.6843 train_time:596293ms step_avg:408.70ms step:1470/6250 train_loss:2.6575 train_time:596729ms step_avg:408.72ms step:1471/6250 train_loss:2.7659 train_time:597161ms step_avg:408.73ms step:1472/6250 train_loss:2.5934 train_time:597587ms step_avg:408.75ms step:1473/6250 train_loss:2.6401 train_time:598011ms step_avg:408.76ms step:1474/6250 train_loss:2.6484 train_time:598436ms step_avg:408.77ms step:1475/6250 train_loss:2.6048 train_time:598881ms step_avg:408.79ms step:1476/6250 train_loss:2.7043 train_time:599292ms step_avg:408.79ms step:1477/6250 train_loss:2.6539 train_time:599703ms step_avg:408.80ms step:1478/6250 train_loss:2.6061 train_time:600138ms step_avg:408.81ms step:1479/6250 train_loss:2.6288 train_time:600551ms step_avg:408.82ms step:1480/6250 train_loss:2.6583 train_time:600960ms step_avg:408.82ms step:1481/6250 train_loss:2.6727 train_time:601370ms step_avg:408.82ms step:1482/6250 train_loss:2.6190 train_time:601782ms step_avg:408.82ms step:1483/6250 train_loss:2.7423 train_time:602193ms step_avg:408.82ms step:1484/6250 train_loss:2.5914 train_time:602606ms step_avg:408.82ms step:1485/6250 train_loss:2.5748 train_time:603016ms step_avg:408.82ms step:1486/6250 train_loss:2.6186 train_time:603427ms step_avg:408.83ms step:1487/6250 train_loss:2.6393 train_time:603838ms step_avg:408.83ms step:1488/6250 train_loss:2.5557 train_time:604251ms step_avg:408.83ms step:1489/6250 train_loss:2.7142 train_time:604666ms step_avg:408.83ms step:1490/6250 train_loss:2.6499 train_time:605077ms step_avg:408.84ms step:1491/6250 train_loss:2.7204 train_time:605490ms step_avg:408.84ms step:1492/6250 train_loss:2.6493 train_time:605904ms step_avg:408.84ms step:1493/6250 train_loss:2.6837 train_time:606315ms step_avg:408.84ms step:1494/6250 train_loss:2.5499 train_time:606727ms step_avg:408.85ms step:1495/6250 train_loss:2.6435 train_time:607137ms step_avg:408.85ms step:1496/6250 train_loss:2.5582 train_time:607555ms step_avg:408.85ms step:1497/6250 train_loss:2.6520 train_time:607965ms step_avg:408.85ms step:1498/6250 train_loss:2.7415 train_time:608378ms step_avg:408.86ms step:1499/6250 train_loss:2.6876 train_time:608791ms step_avg:408.86ms step:1500/6250 train_loss:2.7049 train_time:609202ms step_avg:408.86ms step:1501/6250 train_loss:2.5825 train_time:609613ms step_avg:408.86ms step:1502/6250 train_loss:2.6215 train_time:610023ms step_avg:408.86ms step:1503/6250 train_loss:2.5699 train_time:610451ms step_avg:408.88ms step:1504/6250 train_loss:2.7371 train_time:610888ms step_avg:408.89ms step:1505/6250 train_loss:2.6383 train_time:611298ms step_avg:408.90ms step:1506/6250 train_loss:2.6252 train_time:611713ms step_avg:408.90ms step:1507/6250 train_loss:2.5657 train_time:612126ms step_avg:408.90ms step:1508/6250 train_loss:2.6339 train_time:612538ms step_avg:408.90ms step:1509/6250 train_loss:2.6729 train_time:612951ms step_avg:408.91ms step:1510/6250 train_loss:2.6017 train_time:613364ms step_avg:408.91ms step:1511/6250 train_loss:2.6430 train_time:613779ms step_avg:408.91ms step:1512/6250 train_loss:2.6291 train_time:614192ms step_avg:408.92ms step:1513/6250 train_loss:2.6393 train_time:614606ms step_avg:408.92ms step:1514/6250 train_loss:2.7273 train_time:615016ms step_avg:408.92ms step:1515/6250 train_loss:2.5516 train_time:615430ms step_avg:408.92ms step:1516/6250 train_loss:2.7023 train_time:615853ms step_avg:408.93ms step:1517/6250 train_loss:2.6007 train_time:616298ms step_avg:408.96ms step:1518/6250 train_loss:2.6405 train_time:616712ms step_avg:408.96ms step:1519/6250 train_loss:2.5712 train_time:617127ms step_avg:408.96ms step:1520/6250 train_loss:2.6193 train_time:617539ms step_avg:408.97ms step:1521/6250 train_loss:2.6860 train_time:617952ms step_avg:408.97ms step:1522/6250 train_loss:2.6202 train_time:618366ms step_avg:408.97ms step:1523/6250 train_loss:2.7085 train_time:618782ms step_avg:408.98ms step:1524/6250 train_loss:2.6040 train_time:619193ms step_avg:408.98ms step:1525/6250 train_loss:2.6452 train_time:619610ms step_avg:408.98ms step:1526/6250 train_loss:2.6532 train_time:620027ms step_avg:408.99ms step:1527/6250 train_loss:2.6261 train_time:620445ms step_avg:408.99ms step:1528/6250 train_loss:2.6786 train_time:620854ms step_avg:408.99ms step:1529/6250 train_loss:2.6624 train_time:621282ms step_avg:409.01ms step:1530/6250 train_loss:2.6587 train_time:621692ms step_avg:409.01ms step:1531/6250 train_loss:2.5902 train_time:622105ms step_avg:409.01ms step:1532/6250 train_loss:2.6791 train_time:622516ms step_avg:409.01ms step:1533/6250 train_loss:2.6224 train_time:622928ms step_avg:409.01ms step:1534/6250 train_loss:2.6383 train_time:623340ms step_avg:409.02ms step:1535/6250 train_loss:2.6104 train_time:623755ms step_avg:409.02ms step:1536/6250 train_loss:2.6405 train_time:624165ms step_avg:409.02ms step:1537/6250 train_loss:2.6294 train_time:624579ms step_avg:409.02ms step:1538/6250 train_loss:2.6027 train_time:625003ms step_avg:409.03ms step:1539/6250 train_loss:2.7192 train_time:625412ms step_avg:409.03ms step:1540/6250 train_loss:2.5468 train_time:625823ms step_avg:409.03ms step:1541/6250 train_loss:2.6589 train_time:626235ms step_avg:409.04ms step:1542/6250 train_loss:2.6167 train_time:626646ms step_avg:409.04ms step:1543/6250 train_loss:2.7528 train_time:627054ms step_avg:409.04ms step:1544/6250 train_loss:2.6187 train_time:627463ms step_avg:409.04ms step:1545/6250 train_loss:2.5909 train_time:627886ms step_avg:409.05ms step:1546/6250 train_loss:2.6485 train_time:628310ms step_avg:409.06ms step:1547/6250 train_loss:2.6566 train_time:628730ms step_avg:409.06ms step:1548/6250 train_loss:2.6418 train_time:629194ms step_avg:409.10ms step:1549/6250 train_loss:2.6265 train_time:629646ms step_avg:409.13ms step:1550/6250 train_loss:2.6680 train_time:630098ms step_avg:409.15ms step:1551/6250 train_loss:2.6978 train_time:630548ms step_avg:409.18ms step:1552/6250 train_loss:2.6727 train_time:630999ms step_avg:409.21ms step:1553/6250 train_loss:2.6480 train_time:631454ms step_avg:409.24ms step:1554/6250 train_loss:2.6233 train_time:631905ms step_avg:409.27ms step:1555/6250 train_loss:2.6334 train_time:632353ms step_avg:409.29ms step:1556/6250 train_loss:2.6816 train_time:632804ms step_avg:409.32ms step:1557/6250 train_loss:2.6471 train_time:633256ms step_avg:409.34ms step:1558/6250 train_loss:2.6909 train_time:633706ms step_avg:409.37ms step:1559/6250 train_loss:2.6181 train_time:634157ms step_avg:409.40ms step:1560/6250 train_loss:2.6510 train_time:634605ms step_avg:409.42ms step:1561/6250 train_loss:2.6860 train_time:635057ms step_avg:409.45ms step:1562/6250 train_loss:2.7328 train_time:635509ms step_avg:409.48ms step:1563/6250 train_loss:2.7349 train_time:635959ms step_avg:409.50ms step:1564/6250 train_loss:2.6310 train_time:636411ms step_avg:409.53ms step:1565/6250 train_loss:2.6180 train_time:636859ms step_avg:409.56ms step:1566/6250 train_loss:2.5599 train_time:637310ms step_avg:409.58ms step:1567/6250 train_loss:2.6606 train_time:637731ms step_avg:409.59ms step:1568/6250 train_loss:2.6397 train_time:638146ms step_avg:409.59ms step:1569/6250 train_loss:2.6408 train_time:638561ms step_avg:409.60ms step:1570/6250 train_loss:2.5541 train_time:638980ms step_avg:409.60ms step:1571/6250 train_loss:2.6013 train_time:639396ms step_avg:409.61ms step:1572/6250 train_loss:2.6671 train_time:639808ms step_avg:409.61ms step:1573/6250 train_loss:2.6353 train_time:640226ms step_avg:409.61ms step:1574/6250 train_loss:2.6074 train_time:640646ms step_avg:409.62ms step:1575/6250 train_loss:2.6715 train_time:641059ms step_avg:409.62ms step:1576/6250 train_loss:2.6066 train_time:641472ms step_avg:409.62ms step:1577/6250 train_loss:2.6970 train_time:641881ms step_avg:409.62ms step:1578/6250 train_loss:2.5904 train_time:642293ms step_avg:409.63ms step:1579/6250 train_loss:2.6102 train_time:642704ms step_avg:409.63ms step:1580/6250 train_loss:2.7225 train_time:643113ms step_avg:409.63ms step:1581/6250 train_loss:2.5758 train_time:643526ms step_avg:409.63ms step:1582/6250 train_loss:2.6151 train_time:643940ms step_avg:409.63ms step:1583/6250 train_loss:2.6035 train_time:644353ms step_avg:409.63ms step:1584/6250 train_loss:2.6871 train_time:644762ms step_avg:409.63ms step:1585/6250 train_loss:2.7028 train_time:645173ms step_avg:409.63ms step:1586/6250 train_loss:2.5723 train_time:645583ms step_avg:409.63ms step:1587/6250 train_loss:2.6686 train_time:645992ms step_avg:409.63ms step:1588/6250 train_loss:2.5655 train_time:646407ms step_avg:409.64ms step:1589/6250 train_loss:2.8149 train_time:646815ms step_avg:409.64ms step:1590/6250 train_loss:2.5905 train_time:647226ms step_avg:409.64ms step:1591/6250 train_loss:2.6262 train_time:647637ms step_avg:409.64ms step:1592/6250 train_loss:2.5303 train_time:648052ms step_avg:409.64ms step:1593/6250 train_loss:2.6510 train_time:648466ms step_avg:409.64ms step:1594/6250 train_loss:2.6837 train_time:648878ms step_avg:409.65ms step:1595/6250 train_loss:2.7410 train_time:649290ms step_avg:409.65ms step:1596/6250 train_loss:2.5864 train_time:649700ms step_avg:409.65ms step:1597/6250 train_loss:2.6528 train_time:650111ms step_avg:409.65ms step:1598/6250 train_loss:2.6140 train_time:650524ms step_avg:409.65ms step:1599/6250 train_loss:2.6758 train_time:650937ms step_avg:409.65ms step:1600/6250 train_loss:2.7281 train_time:651347ms step_avg:409.65ms step:1601/6250 train_loss:2.5357 train_time:651760ms step_avg:409.65ms step:1602/6250 train_loss:2.6473 train_time:652171ms step_avg:409.66ms step:1603/6250 train_loss:2.5305 train_time:652586ms step_avg:409.66ms step:1604/6250 train_loss:2.6239 train_time:652994ms step_avg:409.66ms step:1605/6250 train_loss:2.6594 train_time:653405ms step_avg:409.66ms step:1606/6250 train_loss:2.5737 train_time:653818ms step_avg:409.66ms step:1607/6250 train_loss:2.6999 train_time:654228ms step_avg:409.66ms step:1608/6250 train_loss:2.7174 train_time:654641ms step_avg:409.66ms step:1609/6250 train_loss:2.6040 train_time:655050ms step_avg:409.66ms step:1610/6250 train_loss:2.6112 train_time:655462ms step_avg:409.66ms step:1611/6250 train_loss:2.5673 train_time:655870ms step_avg:409.66ms step:1612/6250 train_loss:2.5766 train_time:656282ms step_avg:409.66ms step:1613/6250 train_loss:2.6691 train_time:656695ms step_avg:409.67ms step:1614/6250 train_loss:2.6154 train_time:657105ms step_avg:409.67ms step:1615/6250 train_loss:2.6083 train_time:657517ms step_avg:409.67ms step:1616/6250 train_loss:2.6296 train_time:657927ms step_avg:409.67ms step:1617/6250 train_loss:2.6651 train_time:658337ms step_avg:409.67ms step:1618/6250 train_loss:2.5556 train_time:658748ms step_avg:409.67ms step:1619/6250 train_loss:2.5737 train_time:659158ms step_avg:409.67ms step:1620/6250 train_loss:2.5748 train_time:659571ms step_avg:409.67ms step:1621/6250 train_loss:2.6256 train_time:659981ms step_avg:409.67ms step:1622/6250 train_loss:2.5804 train_time:660392ms step_avg:409.67ms step:1623/6250 train_loss:2.5740 train_time:660803ms step_avg:409.67ms step:1624/6250 train_loss:2.5091 train_time:661217ms step_avg:409.68ms step:1625/6250 train_loss:2.7710 train_time:661626ms step_avg:409.68ms step:1626/6250 train_loss:2.6945 train_time:662040ms step_avg:409.68ms step:1627/6250 train_loss:2.6705 train_time:662454ms step_avg:409.68ms step:1628/6250 train_loss:2.7089 train_time:662863ms step_avg:409.68ms step:1629/6250 train_loss:2.6359 train_time:663273ms step_avg:409.68ms step:1630/6250 train_loss:2.6286 train_time:663685ms step_avg:409.68ms step:1631/6250 train_loss:2.7561 train_time:664094ms step_avg:409.68ms step:1632/6250 train_loss:2.6529 train_time:664503ms step_avg:409.68ms step:1633/6250 train_loss:2.5871 train_time:664915ms step_avg:409.68ms step:1634/6250 train_loss:2.6326 train_time:665327ms step_avg:409.68ms step:1635/6250 train_loss:2.6866 train_time:665734ms step_avg:409.68ms step:1636/6250 train_loss:2.5846 train_time:666147ms step_avg:409.68ms step:1637/6250 train_loss:2.7136 train_time:666557ms step_avg:409.68ms step:1638/6250 train_loss:2.5404 train_time:666968ms step_avg:409.69ms step:1639/6250 train_loss:2.5651 train_time:667380ms step_avg:409.69ms step:1640/6250 train_loss:2.7042 train_time:667792ms step_avg:409.69ms step:1641/6250 train_loss:2.6894 train_time:668203ms step_avg:409.69ms step:1642/6250 train_loss:2.5548 train_time:668612ms step_avg:409.69ms step:1643/6250 train_loss:2.6308 train_time:669024ms step_avg:409.69ms step:1644/6250 train_loss:2.6014 train_time:669435ms step_avg:409.69ms step:1645/6250 train_loss:2.6298 train_time:669849ms step_avg:409.69ms step:1646/6250 train_loss:2.6164 train_time:670260ms step_avg:409.69ms step:1647/6250 train_loss:2.6696 train_time:670675ms step_avg:409.70ms step:1648/6250 train_loss:2.6052 train_time:671083ms step_avg:409.70ms step:1649/6250 train_loss:2.6976 train_time:671494ms step_avg:409.70ms step:1650/6250 train_loss:2.5283 train_time:671906ms step_avg:409.70ms step:1651/6250 train_loss:2.6793 train_time:672316ms step_avg:409.70ms step:1652/6250 train_loss:2.6600 train_time:672726ms step_avg:409.70ms step:1653/6250 train_loss:2.6969 train_time:673137ms step_avg:409.70ms step:1654/6250 train_loss:2.6703 train_time:673549ms step_avg:409.70ms step:1655/6250 train_loss:2.6132 train_time:673960ms step_avg:409.70ms step:1656/6250 train_loss:2.5705 train_time:674372ms step_avg:409.70ms step:1657/6250 train_loss:2.5288 train_time:674783ms step_avg:409.70ms step:1658/6250 train_loss:2.6991 train_time:675194ms step_avg:409.71ms step:1659/6250 train_loss:2.7897 train_time:675603ms step_avg:409.70ms step:1660/6250 train_loss:2.6441 train_time:676013ms step_avg:409.71ms step:1661/6250 train_loss:2.5339 train_time:676430ms step_avg:409.71ms step:1662/6250 train_loss:2.7584 train_time:676838ms step_avg:409.71ms step:1663/6250 train_loss:2.6032 train_time:677249ms step_avg:409.71ms step:1664/6250 train_loss:2.6892 train_time:677659ms step_avg:409.71ms step:1665/6250 train_loss:2.5798 train_time:678069ms step_avg:409.71ms step:1666/6250 train_loss:2.5275 train_time:678482ms step_avg:409.71ms step:1667/6250 train_loss:2.7156 train_time:678894ms step_avg:409.71ms step:1668/6250 train_loss:2.7489 train_time:679306ms step_avg:409.71ms step:1669/6250 train_loss:2.6927 train_time:679715ms step_avg:409.71ms step:1670/6250 train_loss:2.6367 train_time:680123ms step_avg:409.71ms step:1671/6250 train_loss:2.7013 train_time:680536ms step_avg:409.71ms step:1672/6250 train_loss:2.7068 train_time:680945ms step_avg:409.71ms step:1673/6250 train_loss:2.6087 train_time:681356ms step_avg:409.72ms step:1674/6250 train_loss:2.6451 train_time:681765ms step_avg:409.71ms step:1675/6250 train_loss:2.6254 train_time:682177ms step_avg:409.72ms step:1676/6250 train_loss:2.5648 train_time:682588ms step_avg:409.72ms step:1677/6250 train_loss:2.5488 train_time:682998ms step_avg:409.72ms step:1678/6250 train_loss:2.5840 train_time:683410ms step_avg:409.72ms step:1679/6250 train_loss:2.6651 train_time:683819ms step_avg:409.72ms step:1680/6250 train_loss:2.6852 train_time:684229ms step_avg:409.72ms step:1681/6250 train_loss:2.6849 train_time:684642ms step_avg:409.72ms step:1682/6250 train_loss:2.5443 train_time:685052ms step_avg:409.72ms step:1683/6250 train_loss:2.6788 train_time:685463ms step_avg:409.72ms step:1684/6250 train_loss:2.5906 train_time:685870ms step_avg:409.72ms step:1685/6250 train_loss:2.5436 train_time:686281ms step_avg:409.72ms step:1686/6250 train_loss:2.7398 train_time:686695ms step_avg:409.72ms step:1687/6250 train_loss:2.6625 train_time:687105ms step_avg:409.72ms step:1688/6250 train_loss:2.6822 train_time:687516ms step_avg:409.72ms step:1689/6250 train_loss:2.5833 train_time:687925ms step_avg:409.72ms step:1690/6250 train_loss:2.6223 train_time:688337ms step_avg:409.72ms step:1691/6250 train_loss:2.5266 train_time:688748ms step_avg:409.73ms step:1692/6250 train_loss:2.6009 train_time:689162ms step_avg:409.73ms step:1693/6250 train_loss:2.6809 train_time:689571ms step_avg:409.73ms step:1694/6250 train_loss:2.6735 train_time:689980ms step_avg:409.73ms step:1695/6250 train_loss:2.6054 train_time:690392ms step_avg:409.73ms step:1696/6250 train_loss:2.6606 train_time:690804ms step_avg:409.73ms step:1697/6250 train_loss:2.6547 train_time:691217ms step_avg:409.73ms step:1698/6250 train_loss:2.6215 train_time:691627ms step_avg:409.73ms step:1699/6250 train_loss:2.5656 train_time:692037ms step_avg:409.73ms step:1700/6250 train_loss:2.6067 train_time:692448ms step_avg:409.73ms step:1701/6250 train_loss:2.6405 train_time:692858ms step_avg:409.73ms step:1702/6250 train_loss:2.5991 train_time:693269ms step_avg:409.73ms step:1703/6250 train_loss:2.6189 train_time:693681ms step_avg:409.73ms step:1704/6250 train_loss:2.5919 train_time:694090ms step_avg:409.73ms step:1705/6250 train_loss:2.6011 train_time:694503ms step_avg:409.74ms step:1706/6250 train_loss:2.5971 train_time:694918ms step_avg:409.74ms step:1707/6250 train_loss:2.6612 train_time:695332ms step_avg:409.74ms step:1708/6250 train_loss:2.5613 train_time:695741ms step_avg:409.74ms step:1709/6250 train_loss:2.6148 train_time:696150ms step_avg:409.74ms step:1710/6250 train_loss:2.6801 train_time:696564ms step_avg:409.74ms step:1711/6250 train_loss:2.6745 train_time:696974ms step_avg:409.74ms step:1712/6250 train_loss:2.6672 train_time:697386ms step_avg:409.75ms step:1713/6250 train_loss:2.6745 train_time:697795ms step_avg:409.74ms step:1714/6250 train_loss:2.5970 train_time:698236ms step_avg:409.76ms step:1715/6250 train_loss:2.5663 train_time:698645ms step_avg:409.76ms step:1716/6250 train_loss:2.6274 train_time:699055ms step_avg:409.76ms step:1717/6250 train_loss:2.6300 train_time:699466ms step_avg:409.76ms step:1718/6250 train_loss:2.5944 train_time:699879ms step_avg:409.76ms step:1719/6250 train_loss:2.7166 train_time:700289ms step_avg:409.77ms step:1720/6250 train_loss:2.6066 train_time:700698ms step_avg:409.76ms step:1721/6250 train_loss:2.6686 train_time:701108ms step_avg:409.76ms step:1722/6250 train_loss:2.6456 train_time:701518ms step_avg:409.77ms step:1723/6250 train_loss:2.6752 train_time:701927ms step_avg:409.76ms step:1724/6250 train_loss:2.7105 train_time:702337ms step_avg:409.76ms step:1725/6250 train_loss:2.6845 train_time:702747ms step_avg:409.77ms step:1726/6250 train_loss:2.6396 train_time:703155ms step_avg:409.76ms step:1727/6250 train_loss:2.7174 train_time:703565ms step_avg:409.76ms step:1728/6250 train_loss:2.6413 train_time:703980ms step_avg:409.77ms step:1729/6250 train_loss:2.6220 train_time:704391ms step_avg:409.77ms step:1730/6250 train_loss:2.6792 train_time:704804ms step_avg:409.77ms step:1731/6250 train_loss:2.7224 train_time:705214ms step_avg:409.77ms step:1732/6250 train_loss:2.6133 train_time:705628ms step_avg:409.77ms step:1733/6250 train_loss:2.6258 train_time:706038ms step_avg:409.77ms step:1734/6250 train_loss:2.6071 train_time:706451ms step_avg:409.77ms step:1735/6250 train_loss:2.5879 train_time:706859ms step_avg:409.77ms step:1736/6250 train_loss:2.6813 train_time:707269ms step_avg:409.77ms step:1737/6250 train_loss:2.6983 train_time:707680ms step_avg:409.77ms step:1738/6250 train_loss:2.5481 train_time:708090ms step_avg:409.77ms step:1739/6250 train_loss:2.5442 train_time:708501ms step_avg:409.78ms step:1740/6250 train_loss:2.7017 train_time:708911ms step_avg:409.78ms step:1741/6250 train_loss:2.6496 train_time:709320ms step_avg:409.77ms step:1742/6250 train_loss:2.6276 train_time:709734ms step_avg:409.78ms step:1743/6250 train_loss:2.5574 train_time:710145ms step_avg:409.78ms step:1744/6250 train_loss:2.5639 train_time:710563ms step_avg:409.78ms step:1745/6250 train_loss:2.5950 train_time:710982ms step_avg:409.79ms step:1746/6250 train_loss:2.7168 train_time:711396ms step_avg:409.79ms step:1747/6250 train_loss:2.5906 train_time:711808ms step_avg:409.79ms step:1748/6250 train_loss:2.6063 train_time:712224ms step_avg:409.80ms step:1749/6250 train_loss:2.6565 train_time:712635ms step_avg:409.80ms step:1750/6250 train_loss:2.7147 train_time:713046ms step_avg:409.80ms step:1751/6250 train_loss:2.7256 train_time:713485ms step_avg:409.81ms step:1752/6250 train_loss:2.6480 train_time:713918ms step_avg:409.83ms step:1753/6250 train_loss:2.6804 train_time:714331ms step_avg:409.83ms step:1754/6250 train_loss:2.6524 train_time:714743ms step_avg:409.83ms step:1755/6250 train_loss:2.5288 train_time:715153ms step_avg:409.83ms step:1756/6250 train_loss:2.6374 train_time:715564ms step_avg:409.83ms step:1757/6250 train_loss:2.7606 train_time:715977ms step_avg:409.83ms step:1758/6250 train_loss:2.5827 train_time:716387ms step_avg:409.83ms step:1759/6250 train_loss:2.5754 train_time:716799ms step_avg:409.83ms step:1760/6250 train_loss:2.5678 train_time:717211ms step_avg:409.84ms step:1761/6250 train_loss:2.6615 train_time:717625ms step_avg:409.84ms step:1762/6250 train_loss:2.6243 train_time:718036ms step_avg:409.84ms step:1763/6250 train_loss:2.5886 train_time:718460ms step_avg:409.85ms step:1764/6250 train_loss:2.5950 train_time:718875ms step_avg:409.85ms step:1765/6250 train_loss:2.6301 train_time:719286ms step_avg:409.85ms step:1766/6250 train_loss:2.6259 train_time:719698ms step_avg:409.85ms step:1767/6250 train_loss:2.6051 train_time:720112ms step_avg:409.85ms step:1768/6250 train_loss:2.5816 train_time:720527ms step_avg:409.86ms step:1769/6250 train_loss:2.5497 train_time:720938ms step_avg:409.86ms step:1770/6250 train_loss:2.6488 train_time:721350ms step_avg:409.86ms step:1771/6250 train_loss:2.5957 train_time:721763ms step_avg:409.86ms step:1772/6250 train_loss:2.6766 train_time:722174ms step_avg:409.86ms step:1773/6250 train_loss:2.6034 train_time:722587ms step_avg:409.86ms step:1774/6250 train_loss:2.6323 train_time:722997ms step_avg:409.86ms step:1775/6250 train_loss:2.6305 train_time:723410ms step_avg:409.86ms step:1776/6250 train_loss:2.6412 train_time:723821ms step_avg:409.86ms step:1777/6250 train_loss:2.6261 train_time:724237ms step_avg:409.87ms step:1778/6250 train_loss:2.5656 train_time:724648ms step_avg:409.87ms step:1779/6250 train_loss:2.5293 train_time:725061ms step_avg:409.87ms step:1780/6250 train_loss:2.5986 train_time:725473ms step_avg:409.87ms step:1781/6250 train_loss:2.6394 train_time:725887ms step_avg:409.87ms step:1782/6250 train_loss:2.6394 train_time:726302ms step_avg:409.88ms step:1783/6250 train_loss:2.5929 train_time:726717ms step_avg:409.88ms step:1784/6250 train_loss:2.6711 train_time:727131ms step_avg:409.88ms step:1785/6250 train_loss:2.6853 train_time:727539ms step_avg:409.88ms step:1786/6250 train_loss:2.5517 train_time:727953ms step_avg:409.88ms step:1787/6250 train_loss:2.5363 train_time:728365ms step_avg:409.88ms step:1788/6250 train_loss:2.5823 train_time:728776ms step_avg:409.89ms step:1789/6250 train_loss:2.5943 train_time:729188ms step_avg:409.89ms step:1790/6250 train_loss:2.6000 train_time:729603ms step_avg:409.89ms step:1791/6250 train_loss:2.6154 train_time:730016ms step_avg:409.89ms step:1792/6250 train_loss:2.6356 train_time:730428ms step_avg:409.89ms step:1793/6250 train_loss:2.6335 train_time:730842ms step_avg:409.89ms step:1794/6250 train_loss:2.6215 train_time:731255ms step_avg:409.90ms step:1795/6250 train_loss:2.5679 train_time:731669ms step_avg:409.90ms step:1796/6250 train_loss:2.6234 train_time:732082ms step_avg:409.90ms step:1797/6250 train_loss:2.5615 train_time:732497ms step_avg:409.90ms step:1798/6250 train_loss:2.6939 train_time:732908ms step_avg:409.90ms step:1799/6250 train_loss:2.6477 train_time:733321ms step_avg:409.91ms step:1800/6250 train_loss:2.6718 train_time:733733ms step_avg:409.91ms step:1801/6250 train_loss:2.5681 train_time:734144ms step_avg:409.91ms step:1802/6250 train_loss:2.6654 train_time:734558ms step_avg:409.91ms step:1803/6250 train_loss:2.5273 train_time:734969ms step_avg:409.91ms step:1804/6250 train_loss:2.5880 train_time:735385ms step_avg:409.91ms step:1805/6250 train_loss:2.5703 train_time:735798ms step_avg:409.92ms step:1806/6250 train_loss:2.6520 train_time:736212ms step_avg:409.92ms step:1807/6250 train_loss:2.6457 train_time:736628ms step_avg:409.92ms step:1808/6250 train_loss:2.5925 train_time:737041ms step_avg:409.92ms step:1809/6250 train_loss:2.6306 train_time:737455ms step_avg:409.93ms step:1810/6250 train_loss:2.6106 train_time:737864ms step_avg:409.92ms step:1811/6250 train_loss:2.5444 train_time:738279ms step_avg:409.93ms step:1812/6250 train_loss:2.5866 train_time:738690ms step_avg:409.93ms step:1813/6250 train_loss:2.5620 train_time:739104ms step_avg:409.93ms step:1814/6250 train_loss:2.6358 train_time:739518ms step_avg:409.93ms step:1815/6250 train_loss:2.5673 train_time:739932ms step_avg:409.93ms step:1816/6250 train_loss:2.5947 train_time:740346ms step_avg:409.94ms step:1817/6250 train_loss:2.5275 train_time:740760ms step_avg:409.94ms step:1818/6250 train_loss:2.6010 train_time:741172ms step_avg:409.94ms step:1819/6250 train_loss:2.5507 train_time:741587ms step_avg:409.94ms step:1820/6250 train_loss:2.5677 train_time:741998ms step_avg:409.94ms step:1821/6250 train_loss:2.5541 train_time:742413ms step_avg:409.95ms step:1822/6250 train_loss:2.6244 train_time:742825ms step_avg:409.95ms step:1823/6250 train_loss:2.6120 train_time:743237ms step_avg:409.95ms step:1824/6250 train_loss:2.6397 train_time:743650ms step_avg:409.95ms step:1825/6250 train_loss:2.5949 train_time:744063ms step_avg:409.95ms step:1826/6250 train_loss:2.5560 train_time:744477ms step_avg:409.95ms step:1827/6250 train_loss:2.5847 train_time:744887ms step_avg:409.95ms step:1828/6250 train_loss:2.5917 train_time:745299ms step_avg:409.96ms step:1829/6250 train_loss:2.6744 train_time:745709ms step_avg:409.96ms step:1830/6250 train_loss:2.5735 train_time:746120ms step_avg:409.96ms step:1831/6250 train_loss:2.6048 train_time:746532ms step_avg:409.96ms step:1832/6250 train_loss:2.6431 train_time:746943ms step_avg:409.96ms step:1833/6250 train_loss:2.5815 train_time:747359ms step_avg:409.96ms step:1834/6250 train_loss:2.7569 train_time:747776ms step_avg:409.96ms step:1835/6250 train_loss:2.6385 train_time:748187ms step_avg:409.97ms step:1836/6250 train_loss:2.6120 train_time:748604ms step_avg:409.97ms step:1837/6250 train_loss:2.6099 train_time:749018ms step_avg:409.97ms step:1838/6250 train_loss:2.6536 train_time:749431ms step_avg:409.97ms step:1839/6250 train_loss:2.6835 train_time:749843ms step_avg:409.97ms step:1840/6250 train_loss:2.5875 train_time:750257ms step_avg:409.98ms step:1841/6250 train_loss:2.6154 train_time:750672ms step_avg:409.98ms step:1842/6250 train_loss:2.4964 train_time:751089ms step_avg:409.98ms step:1843/6250 train_loss:2.5308 train_time:751506ms step_avg:409.99ms step:1844/6250 train_loss:2.5263 train_time:751918ms step_avg:409.99ms step:1845/6250 train_loss:2.6720 train_time:752331ms step_avg:409.99ms step:1846/6250 train_loss:2.5608 train_time:752740ms step_avg:409.99ms step:1847/6250 train_loss:2.5200 train_time:753150ms step_avg:409.99ms step:1848/6250 train_loss:2.6632 train_time:753562ms step_avg:409.99ms step:1849/6250 train_loss:2.5688 train_time:753981ms step_avg:410.00ms step:1850/6250 train_loss:2.6091 train_time:754395ms step_avg:410.00ms step:1851/6250 train_loss:2.7193 train_time:754836ms step_avg:410.01ms step:1852/6250 train_loss:2.5821 train_time:755285ms step_avg:410.04ms step:1853/6250 train_loss:2.6413 train_time:755736ms step_avg:410.06ms step:1854/6250 train_loss:2.6162 train_time:756193ms step_avg:410.08ms step:1855/6250 train_loss:2.5376 train_time:756642ms step_avg:410.10ms step:1856/6250 train_loss:2.6825 train_time:757093ms step_avg:410.13ms step:1857/6250 train_loss:2.6089 train_time:757545ms step_avg:410.15ms step:1858/6250 train_loss:2.6208 train_time:757964ms step_avg:410.15ms step:1859/6250 train_loss:2.5920 train_time:758381ms step_avg:410.16ms step:1860/6250 train_loss:2.5880 train_time:758816ms step_avg:410.17ms step:1861/6250 train_loss:2.6037 train_time:759246ms step_avg:410.18ms step:1862/6250 train_loss:2.6340 train_time:759664ms step_avg:410.19ms step:1863/6250 train_loss:2.5479 train_time:760075ms step_avg:410.19ms step:1864/6250 train_loss:2.5197 train_time:760488ms step_avg:410.19ms step:1865/6250 train_loss:2.4693 train_time:760909ms step_avg:410.19ms step:1866/6250 train_loss:2.5642 train_time:761325ms step_avg:410.20ms step:1867/6250 train_loss:2.5744 train_time:761739ms step_avg:410.20ms step:1868/6250 train_loss:2.6564 train_time:762156ms step_avg:410.20ms step:1869/6250 train_loss:2.6127 train_time:762574ms step_avg:410.21ms step:1870/6250 train_loss:2.6057 train_time:762986ms step_avg:410.21ms step:1871/6250 train_loss:2.5712 train_time:763407ms step_avg:410.21ms step:1872/6250 train_loss:2.5990 train_time:763820ms step_avg:410.21ms step:1873/6250 train_loss:2.6890 train_time:764247ms step_avg:410.22ms step:1874/6250 train_loss:2.5613 train_time:764670ms step_avg:410.23ms step:1875/6250 train_loss:2.5270 train_time:765096ms step_avg:410.24ms step:1876/6250 train_loss:2.5695 train_time:765535ms step_avg:410.25ms step:1877/6250 train_loss:2.7176 train_time:765948ms step_avg:410.26ms step:1878/6250 train_loss:2.6472 train_time:766363ms step_avg:410.26ms step:1879/6250 train_loss:2.5641 train_time:766795ms step_avg:410.27ms step:1880/6250 train_loss:2.5918 train_time:767228ms step_avg:410.28ms step:1881/6250 train_loss:2.5264 train_time:767658ms step_avg:410.29ms step:1882/6250 train_loss:2.5934 train_time:768074ms step_avg:410.30ms step:1883/6250 train_loss:2.6536 train_time:768499ms step_avg:410.30ms step:1884/6250 train_loss:2.6183 train_time:768912ms step_avg:410.30ms step:1885/6250 train_loss:2.5884 train_time:769336ms step_avg:410.31ms step:1886/6250 train_loss:2.5864 train_time:769761ms step_avg:410.32ms step:1887/6250 train_loss:2.5982 train_time:770195ms step_avg:410.33ms step:1888/6250 train_loss:2.6569 train_time:770634ms step_avg:410.35ms step:1889/6250 train_loss:2.6197 train_time:771071ms step_avg:410.36ms step:1890/6250 train_loss:2.5371 train_time:771501ms step_avg:410.37ms step:1891/6250 train_loss:2.6133 train_time:771930ms step_avg:410.38ms step:1892/6250 train_loss:2.5218 train_time:772348ms step_avg:410.39ms step:1893/6250 train_loss:2.5645 train_time:772764ms step_avg:410.39ms step:1894/6250 train_loss:2.6648 train_time:773196ms step_avg:410.40ms step:1895/6250 train_loss:2.6606 train_time:773627ms step_avg:410.41ms step:1896/6250 train_loss:2.4952 train_time:774060ms step_avg:410.42ms step:1897/6250 train_loss:2.6437 train_time:774487ms step_avg:410.43ms step:1898/6250 train_loss:2.7102 train_time:774911ms step_avg:410.44ms step:1899/6250 train_loss:2.6034 train_time:775333ms step_avg:410.45ms step:1900/6250 train_loss:2.5808 train_time:775752ms step_avg:410.45ms step:1901/6250 train_loss:2.4719 train_time:776174ms step_avg:410.46ms step:1902/6250 train_loss:2.5955 train_time:776599ms step_avg:410.46ms step:1903/6250 train_loss:2.5842 train_time:777011ms step_avg:410.47ms step:1904/6250 train_loss:2.4856 train_time:777435ms step_avg:410.47ms step:1905/6250 train_loss:2.5848 train_time:777858ms step_avg:410.48ms step:1906/6250 train_loss:2.5927 train_time:778285ms step_avg:410.49ms step:1907/6250 train_loss:2.5455 train_time:778700ms step_avg:410.49ms step:1908/6250 train_loss:2.6067 train_time:779126ms step_avg:410.50ms step:1909/6250 train_loss:2.4996 train_time:779542ms step_avg:410.50ms step:1910/6250 train_loss:2.5746 train_time:779951ms step_avg:410.50ms step:1911/6250 train_loss:2.6221 train_time:780366ms step_avg:410.50ms step:1912/6250 train_loss:2.5544 train_time:780781ms step_avg:410.51ms step:1913/6250 train_loss:2.6479 train_time:781208ms step_avg:410.51ms step:1914/6250 train_loss:2.6176 train_time:781632ms step_avg:410.52ms step:1915/6250 train_loss:2.5385 train_time:782044ms step_avg:410.52ms step:1916/6250 train_loss:2.4232 train_time:782459ms step_avg:410.52ms step:1917/6250 train_loss:2.5756 train_time:782870ms step_avg:410.52ms step:1918/6250 train_loss:2.5219 train_time:783282ms step_avg:410.53ms step:1919/6250 train_loss:2.6364 train_time:783693ms step_avg:410.53ms step:1920/6250 train_loss:2.5951 train_time:784107ms step_avg:410.53ms step:1921/6250 train_loss:2.5432 train_time:784519ms step_avg:410.53ms step:1922/6250 train_loss:2.4904 train_time:784931ms step_avg:410.53ms step:1923/6250 train_loss:2.5625 train_time:785343ms step_avg:410.53ms step:1924/6250 train_loss:2.6143 train_time:785753ms step_avg:410.53ms step:1925/6250 train_loss:2.5962 train_time:786166ms step_avg:410.53ms step:1926/6250 train_loss:2.6314 train_time:786581ms step_avg:410.53ms step:1927/6250 train_loss:2.6045 train_time:786991ms step_avg:410.53ms step:1928/6250 train_loss:2.6420 train_time:787400ms step_avg:410.53ms step:1929/6250 train_loss:2.5960 train_time:787813ms step_avg:410.53ms step:1930/6250 train_loss:2.5852 train_time:788225ms step_avg:410.53ms step:1931/6250 train_loss:2.5300 train_time:788646ms step_avg:410.54ms step:1932/6250 train_loss:2.5630 train_time:789063ms step_avg:410.54ms step:1933/6250 train_loss:2.6987 train_time:789496ms step_avg:410.55ms step:1934/6250 train_loss:2.5844 train_time:789917ms step_avg:410.56ms step:1935/6250 train_loss:2.6129 train_time:790341ms step_avg:410.57ms step:1936/6250 train_loss:2.6098 train_time:790776ms step_avg:410.58ms step:1937/6250 train_loss:2.5701 train_time:791204ms step_avg:410.59ms step:1938/6250 train_loss:2.7162 train_time:791615ms step_avg:410.59ms step:1939/6250 train_loss:2.5435 train_time:792033ms step_avg:410.59ms step:1940/6250 train_loss:2.5624 train_time:792461ms step_avg:410.60ms step:1941/6250 train_loss:2.6477 train_time:792885ms step_avg:410.61ms step:1942/6250 train_loss:2.5197 train_time:793308ms step_avg:410.61ms step:1943/6250 train_loss:2.5116 train_time:793740ms step_avg:410.63ms step:1944/6250 train_loss:2.7374 train_time:794157ms step_avg:410.63ms step:1945/6250 train_loss:2.6313 train_time:794577ms step_avg:410.63ms step:1946/6250 train_loss:2.5490 train_time:795006ms step_avg:410.64ms step:1947/6250 train_loss:2.5181 train_time:795427ms step_avg:410.65ms step:1948/6250 train_loss:2.6218 train_time:795844ms step_avg:410.65ms step:1949/6250 train_loss:2.6113 train_time:796266ms step_avg:410.66ms step:1950/6250 train_loss:2.5507 train_time:796682ms step_avg:410.66ms step:1951/6250 train_loss:2.6784 train_time:797095ms step_avg:410.66ms step:1952/6250 train_loss:2.6018 train_time:797511ms step_avg:410.66ms step:1953/6250 train_loss:2.6035 train_time:797928ms step_avg:410.67ms step:1954/6250 train_loss:2.5508 train_time:798360ms step_avg:410.68ms step:1955/6250 train_loss:2.5767 train_time:798780ms step_avg:410.68ms step:1956/6250 train_loss:2.5363 train_time:799190ms step_avg:410.68ms step:1957/6250 train_loss:2.6668 train_time:799602ms step_avg:410.68ms step:1958/6250 train_loss:2.6343 train_time:800013ms step_avg:410.68ms step:1959/6250 train_loss:2.5238 train_time:800428ms step_avg:410.69ms step:1960/6250 train_loss:2.5764 train_time:800850ms step_avg:410.69ms step:1961/6250 train_loss:2.5620 train_time:801266ms step_avg:410.70ms step:1962/6250 train_loss:2.6044 train_time:801707ms step_avg:410.71ms step:1963/6250 train_loss:2.5724 train_time:802135ms step_avg:410.72ms step:1964/6250 train_loss:2.5872 train_time:802554ms step_avg:410.72ms step:1965/6250 train_loss:2.6097 train_time:802961ms step_avg:410.72ms step:1966/6250 train_loss:2.6374 train_time:803375ms step_avg:410.72ms step:1967/6250 train_loss:2.6332 train_time:803784ms step_avg:410.72ms step:1968/6250 train_loss:2.5283 train_time:804198ms step_avg:410.72ms step:1969/6250 train_loss:2.6897 train_time:804608ms step_avg:410.72ms step:1970/6250 train_loss:2.5022 train_time:805020ms step_avg:410.72ms step:1971/6250 train_loss:2.6394 train_time:805429ms step_avg:410.72ms step:1972/6250 train_loss:2.5592 train_time:805841ms step_avg:410.72ms step:1973/6250 train_loss:2.6084 train_time:806263ms step_avg:410.73ms step:1974/6250 train_loss:2.5692 train_time:806686ms step_avg:410.74ms step:1975/6250 train_loss:2.4437 train_time:807103ms step_avg:410.74ms step:1976/6250 train_loss:2.5394 train_time:807514ms step_avg:410.74ms step:1977/6250 train_loss:2.6396 train_time:807927ms step_avg:410.74ms step:1978/6250 train_loss:2.7139 train_time:808338ms step_avg:410.74ms step:1979/6250 train_loss:2.6156 train_time:808763ms step_avg:410.75ms step:1980/6250 train_loss:2.6037 train_time:809175ms step_avg:410.75ms step:1981/6250 train_loss:2.6212 train_time:809606ms step_avg:410.76ms step:1982/6250 train_loss:2.6295 train_time:810025ms step_avg:410.76ms step:1983/6250 train_loss:2.4815 train_time:810453ms step_avg:410.77ms step:1984/6250 train_loss:2.6479 train_time:810872ms step_avg:410.78ms step:1985/6250 train_loss:2.5905 train_time:811294ms step_avg:410.78ms step:1986/6250 train_loss:2.5735 train_time:811707ms step_avg:410.78ms step:1987/6250 train_loss:2.6844 train_time:812118ms step_avg:410.78ms step:1988/6250 train_loss:2.5587 train_time:812537ms step_avg:410.79ms step:1989/6250 train_loss:2.5067 train_time:812951ms step_avg:410.79ms step:1990/6250 train_loss:2.6948 train_time:813362ms step_avg:410.79ms step:1991/6250 train_loss:2.5403 train_time:813775ms step_avg:410.79ms step:1992/6250 train_loss:2.6135 train_time:814187ms step_avg:410.79ms step:1993/6250 train_loss:2.6244 train_time:814601ms step_avg:410.79ms step:1994/6250 train_loss:2.6212 train_time:815012ms step_avg:410.79ms step:1995/6250 train_loss:2.5318 train_time:815424ms step_avg:410.79ms step:1996/6250 train_loss:2.6665 train_time:815840ms step_avg:410.80ms step:1997/6250 train_loss:2.5841 train_time:816252ms step_avg:410.80ms step:1998/6250 train_loss:2.5111 train_time:816666ms step_avg:410.80ms step:1999/6250 train_loss:2.6909 train_time:817081ms step_avg:410.80ms step:2000/6250 train_loss:2.5921 train_time:817505ms step_avg:410.81ms step:2000/6250 val_loss:2.5915 train_time:817506ms step_avg:410.81ms step:2001/6250 train_loss:2.6329 train_time:817932ms step_avg:410.81ms step:2002/6250 train_loss:2.6174 train_time:818357ms step_avg:410.82ms step:2003/6250 train_loss:2.6456 train_time:818780ms step_avg:410.83ms step:2004/6250 train_loss:2.6196 train_time:819199ms step_avg:410.83ms step:2005/6250 train_loss:2.6454 train_time:819621ms step_avg:410.84ms step:2006/6250 train_loss:2.5775 train_time:820041ms step_avg:410.84ms step:2007/6250 train_loss:2.6508 train_time:820462ms step_avg:410.85ms step:2008/6250 train_loss:2.6326 train_time:820885ms step_avg:410.85ms step:2009/6250 train_loss:2.5447 train_time:821303ms step_avg:410.86ms step:2010/6250 train_loss:2.6194 train_time:821719ms step_avg:410.86ms step:2011/6250 train_loss:2.5747 train_time:822130ms step_avg:410.86ms step:2012/6250 train_loss:2.5614 train_time:822543ms step_avg:410.86ms step:2013/6250 train_loss:2.6049 train_time:822955ms step_avg:410.86ms step:2014/6250 train_loss:2.6298 train_time:823369ms step_avg:410.86ms step:2015/6250 train_loss:2.5145 train_time:823783ms step_avg:410.86ms step:2016/6250 train_loss:2.5488 train_time:824198ms step_avg:410.87ms step:2017/6250 train_loss:2.6354 train_time:824609ms step_avg:410.87ms step:2018/6250 train_loss:2.4894 train_time:825024ms step_avg:410.87ms step:2019/6250 train_loss:2.5666 train_time:825462ms step_avg:410.88ms step:2020/6250 train_loss:2.6148 train_time:825880ms step_avg:410.89ms step:2021/6250 train_loss:2.6304 train_time:826291ms step_avg:410.89ms step:2022/6250 train_loss:2.6032 train_time:826704ms step_avg:410.89ms step:2023/6250 train_loss:2.5606 train_time:827114ms step_avg:410.89ms step:2024/6250 train_loss:2.5825 train_time:827528ms step_avg:410.89ms step:2025/6250 train_loss:2.6821 train_time:827946ms step_avg:410.89ms step:2026/6250 train_loss:2.6145 train_time:828370ms step_avg:410.90ms step:2027/6250 train_loss:2.6192 train_time:828795ms step_avg:410.90ms step:2028/6250 train_loss:2.6723 train_time:829223ms step_avg:410.91ms step:2029/6250 train_loss:2.5437 train_time:829648ms step_avg:410.92ms step:2030/6250 train_loss:2.5861 train_time:830069ms step_avg:410.93ms step:2031/6250 train_loss:2.5484 train_time:830481ms step_avg:410.93ms step:2032/6250 train_loss:2.5199 train_time:830899ms step_avg:410.93ms step:2033/6250 train_loss:2.6250 train_time:831313ms step_avg:410.93ms step:2034/6250 train_loss:2.6725 train_time:831726ms step_avg:410.93ms step:2035/6250 train_loss:2.6142 train_time:832137ms step_avg:410.93ms step:2036/6250 train_loss:2.5335 train_time:832553ms step_avg:410.93ms step:2037/6250 train_loss:2.5814 train_time:832964ms step_avg:410.93ms step:2038/6250 train_loss:2.5571 train_time:833400ms step_avg:410.95ms step:2039/6250 train_loss:2.6591 train_time:833821ms step_avg:410.95ms step:2040/6250 train_loss:2.5680 train_time:834266ms step_avg:410.97ms step:2041/6250 train_loss:2.6384 train_time:834699ms step_avg:410.98ms step:2042/6250 train_loss:2.5786 train_time:835118ms step_avg:410.98ms step:2043/6250 train_loss:2.5322 train_time:835554ms step_avg:411.00ms step:2044/6250 train_loss:2.5819 train_time:835990ms step_avg:411.01ms step:2045/6250 train_loss:2.6635 train_time:836409ms step_avg:411.01ms step:2046/6250 train_loss:2.6794 train_time:836830ms step_avg:411.02ms step:2047/6250 train_loss:2.5490 train_time:837242ms step_avg:411.02ms step:2048/6250 train_loss:2.6181 train_time:837663ms step_avg:411.02ms step:2049/6250 train_loss:2.7479 train_time:838093ms step_avg:411.03ms step:2050/6250 train_loss:2.6547 train_time:838524ms step_avg:411.04ms step:2051/6250 train_loss:2.4645 train_time:838954ms step_avg:411.05ms step:2052/6250 train_loss:2.6085 train_time:839383ms step_avg:411.06ms step:2053/6250 train_loss:2.6466 train_time:839805ms step_avg:411.06ms step:2054/6250 train_loss:2.6212 train_time:840227ms step_avg:411.07ms step:2055/6250 train_loss:2.6584 train_time:840661ms step_avg:411.08ms step:2056/6250 train_loss:2.5685 train_time:841088ms step_avg:411.09ms step:2057/6250 train_loss:2.6418 train_time:841505ms step_avg:411.09ms step:2058/6250 train_loss:2.6927 train_time:841924ms step_avg:411.10ms step:2059/6250 train_loss:2.6195 train_time:842343ms step_avg:411.10ms step:2060/6250 train_loss:2.5049 train_time:842761ms step_avg:411.10ms step:2061/6250 train_loss:2.5575 train_time:843174ms step_avg:411.10ms step:2062/6250 train_loss:2.5915 train_time:843591ms step_avg:411.11ms step:2063/6250 train_loss:2.6160 train_time:844005ms step_avg:411.11ms step:2064/6250 train_loss:2.6187 train_time:844417ms step_avg:411.11ms step:2065/6250 train_loss:2.6420 train_time:844829ms step_avg:411.11ms step:2066/6250 train_loss:2.6434 train_time:845240ms step_avg:411.11ms step:2067/6250 train_loss:2.6540 train_time:845653ms step_avg:411.11ms step:2068/6250 train_loss:2.5912 train_time:846063ms step_avg:411.11ms step:2069/6250 train_loss:2.6006 train_time:846477ms step_avg:411.11ms step:2070/6250 train_loss:2.5283 train_time:846888ms step_avg:411.11ms step:2071/6250 train_loss:2.4476 train_time:847304ms step_avg:411.11ms step:2072/6250 train_loss:2.5800 train_time:847720ms step_avg:411.12ms step:2073/6250 train_loss:2.5491 train_time:848130ms step_avg:411.12ms step:2074/6250 train_loss:2.5592 train_time:848542ms step_avg:411.12ms step:2075/6250 train_loss:2.5825 train_time:848951ms step_avg:411.11ms step:2076/6250 train_loss:2.6456 train_time:849364ms step_avg:411.11ms step:2077/6250 train_loss:2.5929 train_time:849776ms step_avg:411.12ms step:2078/6250 train_loss:2.5427 train_time:850194ms step_avg:411.12ms step:2079/6250 train_loss:2.6199 train_time:850612ms step_avg:411.12ms step:2080/6250 train_loss:2.5659 train_time:851029ms step_avg:411.13ms step:2081/6250 train_loss:2.5339 train_time:851441ms step_avg:411.13ms step:2082/6250 train_loss:2.5449 train_time:851853ms step_avg:411.13ms step:2083/6250 train_loss:2.5605 train_time:852267ms step_avg:411.13ms step:2084/6250 train_loss:2.4285 train_time:852679ms step_avg:411.13ms step:2085/6250 train_loss:2.5793 train_time:853129ms step_avg:411.15ms step:2086/6250 train_loss:2.6171 train_time:853582ms step_avg:411.17ms step:2087/6250 train_loss:2.5709 train_time:854031ms step_avg:411.18ms step:2088/6250 train_loss:2.5822 train_time:854483ms step_avg:411.20ms step:2089/6250 train_loss:2.6161 train_time:854932ms step_avg:411.22ms step:2090/6250 train_loss:2.6440 train_time:855380ms step_avg:411.24ms step:2091/6250 train_loss:2.6178 train_time:855830ms step_avg:411.26ms step:2092/6250 train_loss:2.6740 train_time:856280ms step_avg:411.28ms step:2093/6250 train_loss:2.4742 train_time:856732ms step_avg:411.30ms step:2094/6250 train_loss:2.5753 train_time:857175ms step_avg:411.31ms step:2095/6250 train_loss:2.6951 train_time:857599ms step_avg:411.32ms step:2096/6250 train_loss:2.6051 train_time:858022ms step_avg:411.32ms step:2097/6250 train_loss:2.4695 train_time:858435ms step_avg:411.32ms step:2098/6250 train_loss:2.6459 train_time:858847ms step_avg:411.33ms step:2099/6250 train_loss:2.6735 train_time:859282ms step_avg:411.34ms step:2100/6250 train_loss:2.5055 train_time:859721ms step_avg:411.35ms step:2101/6250 train_loss:2.6569 train_time:860137ms step_avg:411.35ms step:2102/6250 train_loss:2.5700 train_time:860550ms step_avg:411.35ms step:2103/6250 train_loss:2.5718 train_time:860968ms step_avg:411.36ms step:2104/6250 train_loss:2.5990 train_time:861384ms step_avg:411.36ms step:2105/6250 train_loss:2.5034 train_time:861803ms step_avg:411.36ms step:2106/6250 train_loss:2.7052 train_time:862214ms step_avg:411.36ms step:2107/6250 train_loss:2.4831 train_time:862633ms step_avg:411.37ms step:2108/6250 train_loss:2.6640 train_time:863046ms step_avg:411.37ms step:2109/6250 train_loss:2.5787 train_time:863458ms step_avg:411.37ms step:2110/6250 train_loss:2.5529 train_time:863871ms step_avg:411.37ms step:2111/6250 train_loss:2.5342 train_time:864286ms step_avg:411.37ms step:2112/6250 train_loss:2.5673 train_time:864698ms step_avg:411.37ms step:2113/6250 train_loss:2.5690 train_time:865114ms step_avg:411.37ms step:2114/6250 train_loss:2.5572 train_time:865531ms step_avg:411.37ms step:2115/6250 train_loss:2.6123 train_time:865943ms step_avg:411.37ms step:2116/6250 train_loss:2.4881 train_time:866359ms step_avg:411.38ms step:2117/6250 train_loss:2.5296 train_time:866771ms step_avg:411.38ms step:2118/6250 train_loss:2.5270 train_time:867187ms step_avg:411.38ms step:2119/6250 train_loss:2.5580 train_time:867602ms step_avg:411.38ms step:2120/6250 train_loss:2.5507 train_time:868016ms step_avg:411.38ms step:2121/6250 train_loss:2.6216 train_time:868428ms step_avg:411.38ms step:2122/6250 train_loss:2.6016 train_time:868841ms step_avg:411.38ms step:2123/6250 train_loss:2.5682 train_time:869253ms step_avg:411.38ms step:2124/6250 train_loss:2.5449 train_time:869667ms step_avg:411.38ms step:2125/6250 train_loss:2.5552 train_time:870083ms step_avg:411.39ms step:2126/6250 train_loss:2.5165 train_time:870495ms step_avg:411.39ms step:2127/6250 train_loss:2.6149 train_time:870907ms step_avg:411.39ms step:2128/6250 train_loss:2.6598 train_time:871319ms step_avg:411.39ms step:2129/6250 train_loss:2.5521 train_time:871734ms step_avg:411.39ms step:2130/6250 train_loss:2.5854 train_time:872145ms step_avg:411.39ms step:2131/6250 train_loss:2.5425 train_time:872556ms step_avg:411.39ms step:2132/6250 train_loss:2.5465 train_time:872967ms step_avg:411.39ms step:2133/6250 train_loss:2.5122 train_time:873377ms step_avg:411.39ms step:2134/6250 train_loss:2.5122 train_time:873792ms step_avg:411.39ms step:2135/6250 train_loss:2.5828 train_time:874211ms step_avg:411.39ms step:2136/6250 train_loss:2.5562 train_time:874622ms step_avg:411.39ms step:2137/6250 train_loss:2.6316 train_time:875034ms step_avg:411.39ms step:2138/6250 train_loss:2.4951 train_time:875446ms step_avg:411.39ms step:2139/6250 train_loss:2.4919 train_time:875859ms step_avg:411.39ms step:2140/6250 train_loss:2.4556 train_time:876271ms step_avg:411.39ms step:2141/6250 train_loss:2.6151 train_time:876686ms step_avg:411.40ms step:2142/6250 train_loss:2.5375 train_time:877095ms step_avg:411.40ms step:2143/6250 train_loss:2.5093 train_time:877508ms step_avg:411.40ms step:2144/6250 train_loss:2.6133 train_time:877921ms step_avg:411.40ms step:2145/6250 train_loss:2.4351 train_time:878332ms step_avg:411.40ms step:2146/6250 train_loss:2.5294 train_time:878751ms step_avg:411.40ms step:2147/6250 train_loss:2.5169 train_time:879174ms step_avg:411.41ms step:2148/6250 train_loss:2.5717 train_time:879591ms step_avg:411.41ms step:2149/6250 train_loss:2.6849 train_time:880001ms step_avg:411.41ms step:2150/6250 train_loss:2.6574 train_time:880412ms step_avg:411.41ms step:2151/6250 train_loss:2.4930 train_time:880825ms step_avg:411.41ms step:2152/6250 train_loss:2.5963 train_time:881235ms step_avg:411.41ms step:2153/6250 train_loss:2.5760 train_time:881646ms step_avg:411.41ms step:2154/6250 train_loss:2.6882 train_time:882060ms step_avg:411.41ms step:2155/6250 train_loss:2.6355 train_time:882473ms step_avg:411.41ms step:2156/6250 train_loss:2.5523 train_time:882887ms step_avg:411.41ms step:2157/6250 train_loss:2.5808 train_time:883298ms step_avg:411.41ms step:2158/6250 train_loss:2.5773 train_time:883712ms step_avg:411.41ms step:2159/6250 train_loss:2.5713 train_time:884147ms step_avg:411.42ms step:2160/6250 train_loss:2.5205 train_time:884562ms step_avg:411.42ms step:2161/6250 train_loss:2.4500 train_time:885003ms step_avg:411.44ms step:2162/6250 train_loss:2.5114 train_time:885452ms step_avg:411.46ms step:2163/6250 train_loss:2.5932 train_time:885864ms step_avg:411.46ms step:2164/6250 train_loss:2.5753 train_time:886275ms step_avg:411.46ms step:2165/6250 train_loss:2.5056 train_time:886690ms step_avg:411.46ms step:2166/6250 train_loss:2.4753 train_time:887099ms step_avg:411.46ms step:2167/6250 train_loss:2.5769 train_time:887513ms step_avg:411.46ms step:2168/6250 train_loss:2.4371 train_time:887924ms step_avg:411.46ms step:2169/6250 train_loss:2.5159 train_time:888342ms step_avg:411.46ms step:2170/6250 train_loss:2.5417 train_time:888773ms step_avg:411.47ms step:2171/6250 train_loss:2.5433 train_time:889191ms step_avg:411.47ms step:2172/6250 train_loss:2.5624 train_time:889612ms step_avg:411.48ms step:2173/6250 train_loss:2.5074 train_time:890033ms step_avg:411.48ms step:2174/6250 train_loss:2.5148 train_time:890446ms step_avg:411.48ms step:2175/6250 train_loss:2.6245 train_time:890860ms step_avg:411.48ms step:2176/6250 train_loss:2.6390 train_time:891270ms step_avg:411.48ms step:2177/6250 train_loss:2.6114 train_time:891681ms step_avg:411.48ms step:2178/6250 train_loss:2.5439 train_time:892094ms step_avg:411.48ms step:2179/6250 train_loss:2.5076 train_time:892509ms step_avg:411.48ms step:2180/6250 train_loss:2.5905 train_time:892919ms step_avg:411.48ms step:2181/6250 train_loss:2.5512 train_time:893328ms step_avg:411.48ms step:2182/6250 train_loss:2.5371 train_time:893741ms step_avg:411.48ms step:2183/6250 train_loss:2.5086 train_time:894152ms step_avg:411.48ms step:2184/6250 train_loss:2.6077 train_time:894564ms step_avg:411.48ms step:2185/6250 train_loss:2.5362 train_time:894976ms step_avg:411.48ms step:2186/6250 train_loss:2.5630 train_time:895388ms step_avg:411.48ms step:2187/6250 train_loss:2.5045 train_time:895801ms step_avg:411.48ms step:2188/6250 train_loss:2.6069 train_time:896211ms step_avg:411.48ms step:2189/6250 train_loss:2.5849 train_time:896623ms step_avg:411.48ms step:2190/6250 train_loss:2.6156 train_time:897035ms step_avg:411.48ms step:2191/6250 train_loss:2.5982 train_time:897449ms step_avg:411.49ms step:2192/6250 train_loss:2.5524 train_time:897861ms step_avg:411.49ms step:2193/6250 train_loss:2.6169 train_time:898274ms step_avg:411.49ms step:2194/6250 train_loss:2.6327 train_time:898686ms step_avg:411.49ms step:2195/6250 train_loss:2.5254 train_time:899099ms step_avg:411.49ms step:2196/6250 train_loss:2.4638 train_time:899515ms step_avg:411.49ms step:2197/6250 train_loss:2.6169 train_time:899931ms step_avg:411.49ms step:2198/6250 train_loss:2.6642 train_time:900343ms step_avg:411.49ms step:2199/6250 train_loss:2.4863 train_time:900755ms step_avg:411.49ms step:2200/6250 train_loss:2.6415 train_time:901168ms step_avg:411.49ms step:2201/6250 train_loss:2.5652 train_time:901583ms step_avg:411.49ms step:2202/6250 train_loss:2.6242 train_time:901995ms step_avg:411.49ms step:2203/6250 train_loss:2.5828 train_time:902407ms step_avg:411.49ms step:2204/6250 train_loss:2.5349 train_time:902816ms step_avg:411.49ms step:2205/6250 train_loss:2.5381 train_time:903227ms step_avg:411.49ms step:2206/6250 train_loss:2.5195 train_time:903637ms step_avg:411.49ms step:2207/6250 train_loss:2.5144 train_time:904052ms step_avg:411.49ms step:2208/6250 train_loss:2.5713 train_time:904462ms step_avg:411.49ms step:2209/6250 train_loss:2.6407 train_time:904871ms step_avg:411.49ms step:2210/6250 train_loss:2.5973 train_time:905283ms step_avg:411.49ms step:2211/6250 train_loss:2.6473 train_time:905694ms step_avg:411.49ms step:2212/6250 train_loss:2.4508 train_time:906106ms step_avg:411.49ms step:2213/6250 train_loss:2.5832 train_time:906516ms step_avg:411.49ms step:2214/6250 train_loss:2.5357 train_time:906925ms step_avg:411.49ms step:2215/6250 train_loss:2.5387 train_time:907339ms step_avg:411.49ms step:2216/6250 train_loss:2.4327 train_time:907749ms step_avg:411.49ms step:2217/6250 train_loss:2.4802 train_time:908161ms step_avg:411.49ms step:2218/6250 train_loss:2.5049 train_time:908572ms step_avg:411.49ms step:2219/6250 train_loss:2.5824 train_time:908983ms step_avg:411.49ms step:2220/6250 train_loss:2.5586 train_time:909395ms step_avg:411.49ms step:2221/6250 train_loss:2.5198 train_time:909805ms step_avg:411.49ms step:2222/6250 train_loss:2.5897 train_time:910216ms step_avg:411.49ms step:2223/6250 train_loss:2.5226 train_time:910627ms step_avg:411.49ms step:2224/6250 train_loss:2.4579 train_time:911041ms step_avg:411.49ms step:2225/6250 train_loss:2.5654 train_time:911454ms step_avg:411.49ms step:2226/6250 train_loss:2.5728 train_time:911866ms step_avg:411.49ms step:2227/6250 train_loss:2.5070 train_time:912280ms step_avg:411.49ms step:2228/6250 train_loss:2.6044 train_time:912692ms step_avg:411.49ms step:2229/6250 train_loss:2.5518 train_time:913107ms step_avg:411.50ms step:2230/6250 train_loss:2.5329 train_time:913523ms step_avg:411.50ms step:2231/6250 train_loss:2.6196 train_time:913938ms step_avg:411.50ms step:2232/6250 train_loss:2.5116 train_time:914353ms step_avg:411.50ms step:2233/6250 train_loss:2.5905 train_time:914792ms step_avg:411.51ms step:2234/6250 train_loss:2.5554 train_time:915207ms step_avg:411.51ms step:2235/6250 train_loss:2.6902 train_time:915620ms step_avg:411.51ms step:2236/6250 train_loss:2.6690 train_time:916036ms step_avg:411.52ms step:2237/6250 train_loss:2.6042 train_time:916450ms step_avg:411.52ms step:2238/6250 train_loss:2.5362 train_time:916864ms step_avg:411.52ms step:2239/6250 train_loss:2.6013 train_time:917277ms step_avg:411.52ms step:2240/6250 train_loss:2.5587 train_time:917693ms step_avg:411.52ms step:2241/6250 train_loss:2.6009 train_time:918108ms step_avg:411.52ms step:2242/6250 train_loss:2.5789 train_time:918530ms step_avg:411.53ms step:2243/6250 train_loss:2.4565 train_time:918944ms step_avg:411.53ms step:2244/6250 train_loss:2.4983 train_time:919358ms step_avg:411.53ms step:2245/6250 train_loss:2.4771 train_time:919771ms step_avg:411.53ms step:2246/6250 train_loss:2.5895 train_time:920180ms step_avg:411.53ms step:2247/6250 train_loss:2.5496 train_time:920596ms step_avg:411.53ms step:2248/6250 train_loss:2.5532 train_time:921023ms step_avg:411.54ms step:2249/6250 train_loss:2.5006 train_time:921441ms step_avg:411.54ms step:2250/6250 train_loss:2.5723 train_time:921852ms step_avg:411.54ms step:2251/6250 train_loss:2.4815 train_time:922262ms step_avg:411.54ms step:2252/6250 train_loss:2.5618 train_time:922674ms step_avg:411.54ms step:2253/6250 train_loss:2.6382 train_time:923089ms step_avg:411.54ms step:2254/6250 train_loss:2.4958 train_time:923528ms step_avg:411.55ms step:2255/6250 train_loss:2.5551 train_time:923957ms step_avg:411.56ms step:2256/6250 train_loss:2.4924 train_time:924373ms step_avg:411.56ms step:2257/6250 train_loss:2.6606 train_time:924790ms step_avg:411.57ms step:2258/6250 train_loss:2.5557 train_time:925202ms step_avg:411.57ms step:2259/6250 train_loss:2.5728 train_time:925629ms step_avg:411.57ms step:2260/6250 train_loss:2.6004 train_time:926052ms step_avg:411.58ms step:2261/6250 train_loss:2.5888 train_time:926476ms step_avg:411.58ms step:2262/6250 train_loss:2.5178 train_time:926902ms step_avg:411.59ms step:2263/6250 train_loss:2.5887 train_time:927324ms step_avg:411.59ms step:2264/6250 train_loss:2.4967 train_time:927735ms step_avg:411.60ms step:2265/6250 train_loss:2.4882 train_time:928145ms step_avg:411.59ms step:2266/6250 train_loss:2.5267 train_time:928558ms step_avg:411.59ms step:2267/6250 train_loss:2.5523 train_time:928988ms step_avg:411.60ms step:2268/6250 train_loss:2.5864 train_time:929491ms step_avg:411.64ms step:2269/6250 train_loss:2.4995 train_time:929975ms step_avg:411.68ms step:2270/6250 train_loss:2.6143 train_time:930388ms step_avg:411.68ms step:2271/6250 train_loss:2.5516 train_time:930799ms step_avg:411.68ms step:2272/6250 train_loss:2.5007 train_time:931209ms step_avg:411.68ms step:2273/6250 train_loss:2.7200 train_time:931622ms step_avg:411.68ms step:2274/6250 train_loss:2.5724 train_time:932032ms step_avg:411.67ms step:2275/6250 train_loss:2.4876 train_time:932443ms step_avg:411.67ms step:2276/6250 train_loss:2.4232 train_time:932854ms step_avg:411.67ms step:2277/6250 train_loss:2.5243 train_time:933266ms step_avg:411.67ms step:2278/6250 train_loss:2.6406 train_time:933675ms step_avg:411.67ms step:2279/6250 train_loss:2.5276 train_time:934117ms step_avg:411.69ms step:2280/6250 train_loss:2.6529 train_time:934533ms step_avg:411.69ms step:2281/6250 train_loss:2.5651 train_time:934948ms step_avg:411.69ms step:2282/6250 train_loss:2.5216 train_time:935365ms step_avg:411.69ms step:2283/6250 train_loss:2.5052 train_time:935783ms step_avg:411.70ms step:2284/6250 train_loss:2.5747 train_time:936219ms step_avg:411.71ms step:2285/6250 train_loss:2.5619 train_time:936633ms step_avg:411.71ms step:2286/6250 train_loss:2.4868 train_time:937040ms step_avg:411.70ms step:2287/6250 train_loss:2.5173 train_time:937449ms step_avg:411.70ms step:2288/6250 train_loss:2.5831 train_time:937861ms step_avg:411.70ms step:2289/6250 train_loss:2.5051 train_time:938344ms step_avg:411.73ms step:2290/6250 train_loss:2.6475 train_time:938851ms step_avg:411.78ms step:2291/6250 train_loss:2.4521 train_time:939278ms step_avg:411.78ms step:2292/6250 train_loss:2.5231 train_time:939689ms step_avg:411.78ms step:2293/6250 train_loss:2.4383 train_time:940099ms step_avg:411.78ms step:2294/6250 train_loss:2.5607 train_time:940508ms step_avg:411.78ms step:2295/6250 train_loss:2.6006 train_time:940921ms step_avg:411.78ms step:2296/6250 train_loss:2.5945 train_time:941332ms step_avg:411.78ms step:2297/6250 train_loss:2.5612 train_time:941745ms step_avg:411.78ms step:2298/6250 train_loss:2.5837 train_time:942153ms step_avg:411.78ms step:2299/6250 train_loss:2.5862 train_time:942562ms step_avg:411.78ms step:2300/6250 train_loss:2.5081 train_time:942974ms step_avg:411.78ms step:2301/6250 train_loss:2.5090 train_time:943383ms step_avg:411.78ms step:2302/6250 train_loss:2.5615 train_time:943792ms step_avg:411.78ms step:2303/6250 train_loss:2.5255 train_time:944203ms step_avg:411.78ms step:2304/6250 train_loss:2.6033 train_time:944613ms step_avg:411.78ms step:2305/6250 train_loss:2.6425 train_time:945023ms step_avg:411.77ms step:2306/6250 train_loss:2.5841 train_time:945434ms step_avg:411.77ms step:2307/6250 train_loss:2.5255 train_time:945842ms step_avg:411.77ms step:2308/6250 train_loss:2.6178 train_time:946251ms step_avg:411.77ms step:2309/6250 train_loss:2.4497 train_time:946662ms step_avg:411.77ms step:2310/6250 train_loss:2.5114 train_time:947073ms step_avg:411.77ms step:2311/6250 train_loss:2.5303 train_time:947484ms step_avg:411.77ms step:2312/6250 train_loss:2.5703 train_time:947895ms step_avg:411.77ms step:2313/6250 train_loss:2.5259 train_time:948336ms step_avg:411.78ms step:2314/6250 train_loss:2.4870 train_time:948761ms step_avg:411.79ms step:2315/6250 train_loss:2.4732 train_time:949174ms step_avg:411.79ms step:2316/6250 train_loss:2.6297 train_time:949606ms step_avg:411.80ms step:2317/6250 train_loss:2.5179 train_time:950043ms step_avg:411.81ms step:2318/6250 train_loss:2.5759 train_time:950474ms step_avg:411.82ms step:2319/6250 train_loss:2.6746 train_time:950892ms step_avg:411.82ms step:2320/6250 train_loss:2.4288 train_time:951327ms step_avg:411.83ms step:2321/6250 train_loss:2.5611 train_time:951754ms step_avg:411.84ms step:2322/6250 train_loss:2.5538 train_time:952172ms step_avg:411.84ms step:2323/6250 train_loss:2.5722 train_time:952595ms step_avg:411.84ms step:2324/6250 train_loss:2.5179 train_time:953018ms step_avg:411.85ms step:2325/6250 train_loss:2.7089 train_time:953443ms step_avg:411.85ms step:2326/6250 train_loss:2.5484 train_time:953871ms step_avg:411.86ms step:2327/6250 train_loss:2.5187 train_time:954284ms step_avg:411.86ms step:2328/6250 train_loss:2.5283 train_time:954703ms step_avg:411.87ms step:2329/6250 train_loss:2.5053 train_time:955127ms step_avg:411.87ms step:2330/6250 train_loss:2.4768 train_time:955545ms step_avg:411.87ms step:2331/6250 train_loss:2.5592 train_time:955959ms step_avg:411.87ms step:2332/6250 train_loss:2.4964 train_time:956373ms step_avg:411.87ms step:2333/6250 train_loss:2.5392 train_time:956790ms step_avg:411.88ms step:2334/6250 train_loss:2.5603 train_time:957202ms step_avg:411.88ms step:2335/6250 train_loss:2.6659 train_time:957617ms step_avg:411.88ms step:2336/6250 train_loss:2.5600 train_time:958031ms step_avg:411.88ms step:2337/6250 train_loss:2.5525 train_time:958447ms step_avg:411.88ms step:2338/6250 train_loss:2.6186 train_time:958858ms step_avg:411.88ms step:2339/6250 train_loss:2.4636 train_time:959273ms step_avg:411.88ms step:2340/6250 train_loss:2.5149 train_time:959689ms step_avg:411.88ms step:2341/6250 train_loss:2.4610 train_time:960102ms step_avg:411.88ms step:2342/6250 train_loss:2.5065 train_time:960517ms step_avg:411.89ms step:2343/6250 train_loss:2.5615 train_time:960930ms step_avg:411.89ms step:2344/6250 train_loss:2.6047 train_time:961347ms step_avg:411.89ms step:2345/6250 train_loss:2.6081 train_time:961762ms step_avg:411.89ms step:2346/6250 train_loss:2.6214 train_time:962175ms step_avg:411.89ms step:2347/6250 train_loss:2.5937 train_time:962589ms step_avg:411.89ms step:2348/6250 train_loss:2.6164 train_time:963004ms step_avg:411.89ms step:2349/6250 train_loss:2.4968 train_time:963417ms step_avg:411.89ms step:2350/6250 train_loss:2.4619 train_time:963830ms step_avg:411.89ms step:2351/6250 train_loss:2.5482 train_time:964239ms step_avg:411.89ms step:2352/6250 train_loss:2.4450 train_time:964650ms step_avg:411.89ms step:2353/6250 train_loss:2.4619 train_time:965063ms step_avg:411.89ms step:2354/6250 train_loss:2.4941 train_time:965477ms step_avg:411.89ms step:2355/6250 train_loss:2.5136 train_time:965891ms step_avg:411.89ms step:2356/6250 train_loss:2.5448 train_time:966305ms step_avg:411.89ms step:2357/6250 train_loss:2.5973 train_time:966717ms step_avg:411.89ms step:2358/6250 train_loss:2.5553 train_time:967130ms step_avg:411.90ms step:2359/6250 train_loss:2.5744 train_time:967542ms step_avg:411.90ms step:2360/6250 train_loss:2.5466 train_time:967956ms step_avg:411.90ms step:2361/6250 train_loss:2.5014 train_time:968368ms step_avg:411.90ms step:2362/6250 train_loss:2.4349 train_time:968782ms step_avg:411.90ms step:2363/6250 train_loss:2.5690 train_time:969197ms step_avg:411.90ms step:2364/6250 train_loss:2.5206 train_time:969608ms step_avg:411.90ms step:2365/6250 train_loss:2.5641 train_time:970020ms step_avg:411.90ms step:2366/6250 train_loss:2.4863 train_time:970433ms step_avg:411.90ms step:2367/6250 train_loss:2.5796 train_time:970844ms step_avg:411.90ms step:2368/6250 train_loss:2.4890 train_time:971256ms step_avg:411.90ms step:2369/6250 train_loss:2.4269 train_time:971671ms step_avg:411.90ms step:2370/6250 train_loss:2.5554 train_time:972084ms step_avg:411.90ms step:2371/6250 train_loss:2.4650 train_time:972497ms step_avg:411.90ms step:2372/6250 train_loss:2.5657 train_time:972908ms step_avg:411.90ms step:2373/6250 train_loss:2.6305 train_time:973322ms step_avg:411.90ms step:2374/6250 train_loss:2.5832 train_time:973737ms step_avg:411.90ms step:2375/6250 train_loss:2.5400 train_time:974151ms step_avg:411.90ms step:2376/6250 train_loss:2.6338 train_time:974566ms step_avg:411.90ms step:2377/6250 train_loss:2.6185 train_time:974977ms step_avg:411.90ms step:2378/6250 train_loss:2.4818 train_time:975394ms step_avg:411.91ms step:2379/6250 train_loss:2.5277 train_time:975810ms step_avg:411.91ms step:2380/6250 train_loss:2.5148 train_time:976221ms step_avg:411.91ms step:2381/6250 train_loss:2.5871 train_time:976634ms step_avg:411.91ms step:2382/6250 train_loss:2.5506 train_time:977046ms step_avg:411.91ms step:2383/6250 train_loss:2.5487 train_time:977459ms step_avg:411.91ms step:2384/6250 train_loss:2.6053 train_time:977870ms step_avg:411.91ms step:2385/6250 train_loss:2.4848 train_time:978283ms step_avg:411.91ms step:2386/6250 train_loss:2.5883 train_time:978694ms step_avg:411.91ms step:2387/6250 train_loss:2.4936 train_time:979107ms step_avg:411.91ms step:2388/6250 train_loss:2.5567 train_time:979517ms step_avg:411.91ms step:2389/6250 train_loss:2.6121 train_time:979928ms step_avg:411.91ms step:2390/6250 train_loss:2.5345 train_time:980339ms step_avg:411.91ms step:2391/6250 train_loss:2.4887 train_time:980752ms step_avg:411.91ms step:2392/6250 train_loss:2.5906 train_time:981162ms step_avg:411.91ms step:2393/6250 train_loss:2.5474 train_time:981575ms step_avg:411.91ms step:2394/6250 train_loss:2.4450 train_time:981988ms step_avg:411.91ms step:2395/6250 train_loss:2.5063 train_time:982401ms step_avg:411.91ms step:2396/6250 train_loss:2.5448 train_time:982817ms step_avg:411.91ms step:2397/6250 train_loss:2.5797 train_time:983230ms step_avg:411.91ms step:2398/6250 train_loss:2.6150 train_time:983645ms step_avg:411.91ms step:2399/6250 train_loss:2.5184 train_time:984057ms step_avg:411.91ms step:2400/6250 train_loss:2.5818 train_time:984469ms step_avg:411.91ms step:2401/6250 train_loss:2.5055 train_time:984880ms step_avg:411.91ms step:2402/6250 train_loss:2.6291 train_time:985289ms step_avg:411.91ms step:2403/6250 train_loss:2.5095 train_time:985702ms step_avg:411.91ms step:2404/6250 train_loss:2.5848 train_time:986114ms step_avg:411.91ms step:2405/6250 train_loss:2.5849 train_time:986527ms step_avg:411.91ms step:2406/6250 train_loss:2.6249 train_time:986938ms step_avg:411.91ms step:2407/6250 train_loss:2.5366 train_time:987348ms step_avg:411.91ms step:2408/6250 train_loss:2.4653 train_time:987762ms step_avg:411.91ms step:2409/6250 train_loss:2.5897 train_time:988174ms step_avg:411.91ms step:2410/6250 train_loss:2.5720 train_time:988587ms step_avg:411.91ms step:2411/6250 train_loss:2.5252 train_time:988999ms step_avg:411.91ms step:2412/6250 train_loss:2.5177 train_time:989412ms step_avg:411.91ms step:2413/6250 train_loss:2.5992 train_time:989825ms step_avg:411.91ms step:2414/6250 train_loss:2.6267 train_time:990235ms step_avg:411.91ms step:2415/6250 train_loss:2.4760 train_time:990649ms step_avg:411.91ms step:2416/6250 train_loss:2.5607 train_time:991061ms step_avg:411.91ms step:2417/6250 train_loss:2.6203 train_time:991478ms step_avg:411.91ms step:2418/6250 train_loss:2.5164 train_time:991890ms step_avg:411.91ms step:2419/6250 train_loss:2.4719 train_time:992305ms step_avg:411.92ms step:2420/6250 train_loss:2.5234 train_time:992719ms step_avg:411.92ms step:2421/6250 train_loss:2.5272 train_time:993130ms step_avg:411.92ms step:2422/6250 train_loss:2.4523 train_time:993541ms step_avg:411.92ms step:2423/6250 train_loss:2.5473 train_time:993952ms step_avg:411.92ms step:2424/6250 train_loss:2.4044 train_time:994363ms step_avg:411.92ms step:2425/6250 train_loss:2.5094 train_time:994775ms step_avg:411.92ms step:2426/6250 train_loss:2.5137 train_time:995187ms step_avg:411.91ms step:2427/6250 train_loss:2.5353 train_time:995600ms step_avg:411.92ms step:2428/6250 train_loss:2.5772 train_time:996010ms step_avg:411.91ms step:2429/6250 train_loss:2.5839 train_time:996424ms step_avg:411.92ms step:2430/6250 train_loss:2.5660 train_time:996836ms step_avg:411.92ms step:2431/6250 train_loss:2.5222 train_time:997248ms step_avg:411.92ms step:2432/6250 train_loss:2.4648 train_time:997664ms step_avg:411.92ms step:2433/6250 train_loss:2.5330 train_time:998075ms step_avg:411.92ms step:2434/6250 train_loss:2.4757 train_time:998489ms step_avg:411.92ms step:2435/6250 train_loss:2.5481 train_time:998903ms step_avg:411.92ms step:2436/6250 train_loss:2.5255 train_time:999316ms step_avg:411.92ms step:2437/6250 train_loss:2.5330 train_time:999731ms step_avg:411.92ms step:2438/6250 train_loss:2.4875 train_time:1000143ms step_avg:411.92ms step:2439/6250 train_loss:2.4793 train_time:1000558ms step_avg:411.92ms step:2440/6250 train_loss:2.4415 train_time:1000971ms step_avg:411.92ms step:2441/6250 train_loss:2.4781 train_time:1001383ms step_avg:411.92ms step:2442/6250 train_loss:2.5656 train_time:1001804ms step_avg:411.93ms step:2443/6250 train_loss:2.5082 train_time:1002219ms step_avg:411.93ms step:2444/6250 train_loss:2.5811 train_time:1002633ms step_avg:411.93ms step:2445/6250 train_loss:2.4656 train_time:1003043ms step_avg:411.93ms step:2446/6250 train_loss:2.5501 train_time:1003460ms step_avg:411.93ms step:2447/6250 train_loss:2.5816 train_time:1003879ms step_avg:411.93ms step:2448/6250 train_loss:2.5705 train_time:1004290ms step_avg:411.93ms step:2449/6250 train_loss:2.4957 train_time:1004702ms step_avg:411.93ms step:2450/6250 train_loss:2.5615 train_time:1005114ms step_avg:411.93ms step:2451/6250 train_loss:2.5207 train_time:1005529ms step_avg:411.93ms step:2452/6250 train_loss:2.6040 train_time:1005943ms step_avg:411.93ms step:2453/6250 train_loss:2.5876 train_time:1006358ms step_avg:411.94ms step:2454/6250 train_loss:2.6088 train_time:1006772ms step_avg:411.94ms step:2455/6250 train_loss:2.5211 train_time:1007183ms step_avg:411.94ms step:2456/6250 train_loss:2.5272 train_time:1007597ms step_avg:411.94ms step:2457/6250 train_loss:2.5046 train_time:1008011ms step_avg:411.94ms step:2458/6250 train_loss:2.5441 train_time:1008427ms step_avg:411.94ms step:2459/6250 train_loss:2.5054 train_time:1008840ms step_avg:411.94ms step:2460/6250 train_loss:2.5801 train_time:1009253ms step_avg:411.94ms step:2461/6250 train_loss:2.4821 train_time:1009666ms step_avg:411.94ms step:2462/6250 train_loss:2.4662 train_time:1010075ms step_avg:411.94ms step:2463/6250 train_loss:2.5731 train_time:1010487ms step_avg:411.94ms step:2464/6250 train_loss:2.5115 train_time:1010901ms step_avg:411.94ms step:2465/6250 train_loss:2.5236 train_time:1011311ms step_avg:411.94ms step:2466/6250 train_loss:2.5308 train_time:1011723ms step_avg:411.94ms step:2467/6250 train_loss:2.5749 train_time:1012134ms step_avg:411.94ms step:2468/6250 train_loss:2.4860 train_time:1012544ms step_avg:411.94ms step:2469/6250 train_loss:2.5059 train_time:1012955ms step_avg:411.94ms step:2470/6250 train_loss:2.5968 train_time:1013366ms step_avg:411.94ms step:2471/6250 train_loss:2.4930 train_time:1013780ms step_avg:411.94ms step:2472/6250 train_loss:2.5249 train_time:1014190ms step_avg:411.94ms step:2473/6250 train_loss:2.4890 train_time:1014600ms step_avg:411.94ms step:2474/6250 train_loss:2.5310 train_time:1015009ms step_avg:411.94ms step:2475/6250 train_loss:2.5228 train_time:1015421ms step_avg:411.94ms step:2476/6250 train_loss:2.4553 train_time:1015834ms step_avg:411.94ms step:2477/6250 train_loss:2.6416 train_time:1016246ms step_avg:411.94ms step:2478/6250 train_loss:2.5856 train_time:1016659ms step_avg:411.94ms step:2479/6250 train_loss:2.4903 train_time:1017068ms step_avg:411.94ms step:2480/6250 train_loss:2.4716 train_time:1017483ms step_avg:411.94ms step:2481/6250 train_loss:2.4662 train_time:1017896ms step_avg:411.94ms step:2482/6250 train_loss:2.3931 train_time:1018312ms step_avg:411.94ms step:2483/6250 train_loss:2.5190 train_time:1018727ms step_avg:411.94ms step:2484/6250 train_loss:2.5703 train_time:1019142ms step_avg:411.94ms step:2485/6250 train_loss:2.5577 train_time:1019554ms step_avg:411.94ms step:2486/6250 train_loss:2.5710 train_time:1019967ms step_avg:411.94ms step:2487/6250 train_loss:2.5404 train_time:1020390ms step_avg:411.95ms step:2488/6250 train_loss:2.4852 train_time:1020827ms step_avg:411.96ms step:2489/6250 train_loss:2.6061 train_time:1021260ms step_avg:411.96ms step:2490/6250 train_loss:2.5336 train_time:1021675ms step_avg:411.97ms step:2491/6250 train_loss:2.7070 train_time:1022088ms step_avg:411.97ms step:2492/6250 train_loss:2.5818 train_time:1022505ms step_avg:411.97ms step:2493/6250 train_loss:2.5468 train_time:1022915ms step_avg:411.97ms step:2494/6250 train_loss:2.4743 train_time:1023330ms step_avg:411.97ms step:2495/6250 train_loss:2.5172 train_time:1023744ms step_avg:411.97ms step:2496/6250 train_loss:2.5059 train_time:1024154ms step_avg:411.97ms step:2497/6250 train_loss:2.5293 train_time:1024568ms step_avg:411.97ms step:2498/6250 train_loss:2.5003 train_time:1024978ms step_avg:411.97ms step:2499/6250 train_loss:2.5554 train_time:1025391ms step_avg:411.97ms step:2500/6250 train_loss:2.5330 train_time:1025803ms step_avg:411.97ms step:2501/6250 train_loss:2.5412 train_time:1026214ms step_avg:411.97ms step:2502/6250 train_loss:2.5953 train_time:1026625ms step_avg:411.97ms step:2503/6250 train_loss:2.5678 train_time:1027038ms step_avg:411.97ms step:2504/6250 train_loss:2.4733 train_time:1027449ms step_avg:411.97ms step:2505/6250 train_loss:2.5596 train_time:1027860ms step_avg:411.97ms step:2506/6250 train_loss:2.4039 train_time:1028272ms step_avg:411.97ms step:2507/6250 train_loss:2.6149 train_time:1028684ms step_avg:411.97ms step:2508/6250 train_loss:2.6281 train_time:1029110ms step_avg:411.97ms step:2509/6250 train_loss:2.5497 train_time:1029526ms step_avg:411.98ms step:2510/6250 train_loss:2.5837 train_time:1029944ms step_avg:411.98ms step:2511/6250 train_loss:2.5625 train_time:1030360ms step_avg:411.98ms step:2512/6250 train_loss:2.5471 train_time:1030771ms step_avg:411.98ms step:2513/6250 train_loss:2.4639 train_time:1031185ms step_avg:411.98ms step:2514/6250 train_loss:2.5550 train_time:1031595ms step_avg:411.98ms step:2515/6250 train_loss:2.5183 train_time:1032005ms step_avg:411.98ms step:2516/6250 train_loss:2.5737 train_time:1032415ms step_avg:411.98ms step:2517/6250 train_loss:2.5184 train_time:1032825ms step_avg:411.98ms step:2518/6250 train_loss:2.5434 train_time:1033237ms step_avg:411.98ms step:2519/6250 train_loss:2.5187 train_time:1033647ms step_avg:411.98ms step:2520/6250 train_loss:2.4536 train_time:1034058ms step_avg:411.98ms step:2521/6250 train_loss:2.5349 train_time:1034469ms step_avg:411.97ms step:2522/6250 train_loss:2.6337 train_time:1034880ms step_avg:411.97ms step:2523/6250 train_loss:2.5381 train_time:1035292ms step_avg:411.97ms step:2524/6250 train_loss:2.4034 train_time:1035710ms step_avg:411.98ms step:2525/6250 train_loss:2.5381 train_time:1036135ms step_avg:411.98ms step:2526/6250 train_loss:2.4837 train_time:1036558ms step_avg:411.99ms step:2527/6250 train_loss:2.5856 train_time:1036973ms step_avg:411.99ms step:2528/6250 train_loss:2.4780 train_time:1037383ms step_avg:411.99ms step:2529/6250 train_loss:2.5480 train_time:1037806ms step_avg:411.99ms step:2530/6250 train_loss:2.4940 train_time:1038234ms step_avg:412.00ms step:2531/6250 train_loss:2.4966 train_time:1038657ms step_avg:412.00ms step:2532/6250 train_loss:2.5025 train_time:1039068ms step_avg:412.00ms step:2533/6250 train_loss:2.5345 train_time:1039480ms step_avg:412.00ms step:2534/6250 train_loss:2.4568 train_time:1039890ms step_avg:412.00ms step:2535/6250 train_loss:2.6363 train_time:1040298ms step_avg:412.00ms step:2536/6250 train_loss:2.5943 train_time:1040712ms step_avg:412.00ms step:2537/6250 train_loss:2.4667 train_time:1041121ms step_avg:412.00ms step:2538/6250 train_loss:2.5088 train_time:1041535ms step_avg:412.00ms step:2539/6250 train_loss:2.5007 train_time:1041952ms step_avg:412.00ms step:2540/6250 train_loss:2.3938 train_time:1042372ms step_avg:412.00ms step:2541/6250 train_loss:2.5577 train_time:1042789ms step_avg:412.01ms step:2542/6250 train_loss:2.5758 train_time:1043202ms step_avg:412.01ms step:2543/6250 train_loss:2.5409 train_time:1043613ms step_avg:412.01ms step:2544/6250 train_loss:2.5634 train_time:1044027ms step_avg:412.01ms step:2545/6250 train_loss:2.5494 train_time:1044443ms step_avg:412.01ms step:2546/6250 train_loss:2.4256 train_time:1044857ms step_avg:412.01ms step:2547/6250 train_loss:2.5649 train_time:1045272ms step_avg:412.01ms step:2548/6250 train_loss:2.5210 train_time:1045687ms step_avg:412.01ms step:2549/6250 train_loss:2.5441 train_time:1046100ms step_avg:412.01ms step:2550/6250 train_loss:2.5439 train_time:1046514ms step_avg:412.01ms step:2551/6250 train_loss:2.4838 train_time:1046924ms step_avg:412.01ms step:2552/6250 train_loss:2.3996 train_time:1047345ms step_avg:412.02ms step:2553/6250 train_loss:2.4867 train_time:1047761ms step_avg:412.02ms step:2554/6250 train_loss:2.4300 train_time:1048184ms step_avg:412.02ms step:2555/6250 train_loss:2.5569 train_time:1048607ms step_avg:412.03ms step:2556/6250 train_loss:2.4194 train_time:1049031ms step_avg:412.03ms step:2557/6250 train_loss:2.5323 train_time:1049456ms step_avg:412.04ms step:2558/6250 train_loss:2.4903 train_time:1049875ms step_avg:412.04ms step:2559/6250 train_loss:2.5791 train_time:1050294ms step_avg:412.04ms step:2560/6250 train_loss:2.6609 train_time:1050716ms step_avg:412.05ms step:2561/6250 train_loss:2.5237 train_time:1051133ms step_avg:412.05ms step:2562/6250 train_loss:2.4964 train_time:1051563ms step_avg:412.05ms step:2563/6250 train_loss:2.5538 train_time:1051983ms step_avg:412.06ms step:2564/6250 train_loss:2.5856 train_time:1052404ms step_avg:412.06ms step:2565/6250 train_loss:2.4454 train_time:1052823ms step_avg:412.06ms step:2566/6250 train_loss:2.5249 train_time:1053258ms step_avg:412.07ms step:2567/6250 train_loss:2.5265 train_time:1053714ms step_avg:412.09ms step:2568/6250 train_loss:2.5297 train_time:1054164ms step_avg:412.10ms step:2569/6250 train_loss:2.5132 train_time:1054599ms step_avg:412.11ms step:2570/6250 train_loss:2.5013 train_time:1055035ms step_avg:412.12ms step:2571/6250 train_loss:2.4709 train_time:1055457ms step_avg:412.13ms step:2572/6250 train_loss:2.4388 train_time:1055868ms step_avg:412.13ms step:2573/6250 train_loss:2.4256 train_time:1056279ms step_avg:412.13ms step:2574/6250 train_loss:2.5624 train_time:1056691ms step_avg:412.13ms step:2575/6250 train_loss:2.4583 train_time:1057101ms step_avg:412.13ms step:2576/6250 train_loss:2.4996 train_time:1057512ms step_avg:412.12ms step:2577/6250 train_loss:2.4753 train_time:1057935ms step_avg:412.13ms step:2578/6250 train_loss:2.5266 train_time:1058357ms step_avg:412.13ms step:2579/6250 train_loss:2.3976 train_time:1058774ms step_avg:412.13ms step:2580/6250 train_loss:2.4337 train_time:1059196ms step_avg:412.14ms step:2581/6250 train_loss:2.5213 train_time:1059626ms step_avg:412.15ms step:2582/6250 train_loss:2.4553 train_time:1060048ms step_avg:412.15ms step:2583/6250 train_loss:2.4927 train_time:1060465ms step_avg:412.15ms step:2584/6250 train_loss:2.4163 train_time:1060876ms step_avg:412.15ms step:2585/6250 train_loss:2.5713 train_time:1061292ms step_avg:412.15ms step:2586/6250 train_loss:2.4967 train_time:1061708ms step_avg:412.15ms step:2587/6250 train_loss:2.4772 train_time:1062119ms step_avg:412.15ms step:2588/6250 train_loss:2.4237 train_time:1062535ms step_avg:412.15ms step:2589/6250 train_loss:2.5053 train_time:1062949ms step_avg:412.16ms step:2590/6250 train_loss:2.4847 train_time:1063364ms step_avg:412.16ms step:2591/6250 train_loss:2.4835 train_time:1063782ms step_avg:412.16ms step:2592/6250 train_loss:2.6293 train_time:1064193ms step_avg:412.16ms step:2593/6250 train_loss:2.5204 train_time:1064611ms step_avg:412.16ms step:2594/6250 train_loss:2.6084 train_time:1065025ms step_avg:412.16ms step:2595/6250 train_loss:2.4574 train_time:1065439ms step_avg:412.16ms step:2596/6250 train_loss:2.5327 train_time:1065854ms step_avg:412.16ms step:2597/6250 train_loss:2.4800 train_time:1066268ms step_avg:412.16ms step:2598/6250 train_loss:2.4846 train_time:1066680ms step_avg:412.16ms step:2599/6250 train_loss:2.5154 train_time:1067095ms step_avg:412.17ms step:2600/6250 train_loss:2.5678 train_time:1067512ms step_avg:412.17ms step:2601/6250 train_loss:2.5093 train_time:1067923ms step_avg:412.17ms step:2602/6250 train_loss:2.5140 train_time:1068334ms step_avg:412.17ms step:2603/6250 train_loss:2.5778 train_time:1068747ms step_avg:412.17ms step:2604/6250 train_loss:2.4636 train_time:1069157ms step_avg:412.17ms step:2605/6250 train_loss:2.4916 train_time:1069571ms step_avg:412.17ms step:2606/6250 train_loss:2.4411 train_time:1069983ms step_avg:412.17ms step:2607/6250 train_loss:2.4770 train_time:1070394ms step_avg:412.17ms step:2608/6250 train_loss:2.4587 train_time:1070806ms step_avg:412.17ms step:2609/6250 train_loss:2.6168 train_time:1071217ms step_avg:412.17ms step:2610/6250 train_loss:2.4808 train_time:1071627ms step_avg:412.16ms step:2611/6250 train_loss:2.5557 train_time:1072043ms step_avg:412.17ms step:2612/6250 train_loss:2.4759 train_time:1072456ms step_avg:412.17ms step:2613/6250 train_loss:2.5323 train_time:1072869ms step_avg:412.17ms step:2614/6250 train_loss:2.4774 train_time:1073279ms step_avg:412.17ms step:2615/6250 train_loss:2.4525 train_time:1073694ms step_avg:412.17ms step:2616/6250 train_loss:2.4177 train_time:1074109ms step_avg:412.17ms step:2617/6250 train_loss:2.4700 train_time:1074521ms step_avg:412.17ms step:2618/6250 train_loss:2.3889 train_time:1074934ms step_avg:412.17ms step:2619/6250 train_loss:2.5681 train_time:1075344ms step_avg:412.17ms step:2620/6250 train_loss:2.4314 train_time:1075764ms step_avg:412.17ms step:2621/6250 train_loss:2.5081 train_time:1076181ms step_avg:412.17ms step:2622/6250 train_loss:2.5501 train_time:1076599ms step_avg:412.17ms step:2623/6250 train_loss:2.5129 train_time:1077024ms step_avg:412.18ms step:2624/6250 train_loss:2.6167 train_time:1077433ms step_avg:412.18ms step:2625/6250 train_loss:2.4503 train_time:1077855ms step_avg:412.18ms step:2626/6250 train_loss:2.4627 train_time:1078293ms step_avg:412.19ms step:2627/6250 train_loss:2.4395 train_time:1078730ms step_avg:412.20ms step:2628/6250 train_loss:2.4754 train_time:1079171ms step_avg:412.21ms step:2629/6250 train_loss:2.5190 train_time:1079592ms step_avg:412.22ms step:2630/6250 train_loss:2.6360 train_time:1080003ms step_avg:412.21ms step:2631/6250 train_loss:2.4734 train_time:1080412ms step_avg:412.21ms step:2632/6250 train_loss:2.4471 train_time:1080840ms step_avg:412.22ms step:2633/6250 train_loss:2.5205 train_time:1081274ms step_avg:412.23ms step:2634/6250 train_loss:2.4481 train_time:1081705ms step_avg:412.23ms step:2635/6250 train_loss:2.4925 train_time:1082145ms step_avg:412.25ms step:2636/6250 train_loss:2.3647 train_time:1082579ms step_avg:412.25ms step:2637/6250 train_loss:2.4982 train_time:1083000ms step_avg:412.26ms step:2638/6250 train_loss:2.6141 train_time:1083411ms step_avg:412.26ms step:2639/6250 train_loss:2.4675 train_time:1083826ms step_avg:412.26ms step:2640/6250 train_loss:2.4948 train_time:1084235ms step_avg:412.26ms step:2641/6250 train_loss:2.5308 train_time:1084647ms step_avg:412.26ms step:2642/6250 train_loss:2.5675 train_time:1085058ms step_avg:412.26ms step:2643/6250 train_loss:2.4726 train_time:1085472ms step_avg:412.26ms step:2644/6250 train_loss:2.4980 train_time:1085883ms step_avg:412.26ms step:2645/6250 train_loss:2.5273 train_time:1086336ms step_avg:412.27ms step:2646/6250 train_loss:2.4450 train_time:1086759ms step_avg:412.28ms step:2647/6250 train_loss:2.5160 train_time:1087214ms step_avg:412.29ms step:2648/6250 train_loss:2.4219 train_time:1087664ms step_avg:412.31ms step:2649/6250 train_loss:2.4247 train_time:1088112ms step_avg:412.32ms step:2650/6250 train_loss:2.5090 train_time:1088543ms step_avg:412.33ms step:2651/6250 train_loss:2.5181 train_time:1088962ms step_avg:412.33ms step:2652/6250 train_loss:2.4444 train_time:1089375ms step_avg:412.33ms step:2653/6250 train_loss:2.4881 train_time:1089786ms step_avg:412.33ms step:2654/6250 train_loss:2.5724 train_time:1090204ms step_avg:412.33ms step:2655/6250 train_loss:2.6765 train_time:1090620ms step_avg:412.33ms step:2656/6250 train_loss:2.6466 train_time:1091030ms step_avg:412.33ms step:2657/6250 train_loss:2.5502 train_time:1091476ms step_avg:412.34ms step:2658/6250 train_loss:2.5307 train_time:1091906ms step_avg:412.35ms step:2659/6250 train_loss:2.5153 train_time:1092320ms step_avg:412.35ms step:2660/6250 train_loss:2.4208 train_time:1092734ms step_avg:412.35ms step:2661/6250 train_loss:2.5191 train_time:1093148ms step_avg:412.35ms step:2662/6250 train_loss:2.5729 train_time:1093563ms step_avg:412.35ms step:2663/6250 train_loss:2.4617 train_time:1093974ms step_avg:412.35ms step:2664/6250 train_loss:2.4663 train_time:1094387ms step_avg:412.35ms step:2665/6250 train_loss:2.5541 train_time:1094798ms step_avg:412.35ms step:2666/6250 train_loss:2.3985 train_time:1095209ms step_avg:412.35ms step:2667/6250 train_loss:2.5136 train_time:1095623ms step_avg:412.35ms step:2668/6250 train_loss:2.5823 train_time:1096033ms step_avg:412.35ms step:2669/6250 train_loss:2.5016 train_time:1096449ms step_avg:412.35ms step:2670/6250 train_loss:2.5205 train_time:1096877ms step_avg:412.36ms step:2671/6250 train_loss:2.5071 train_time:1097287ms step_avg:412.36ms step:2672/6250 train_loss:2.5214 train_time:1097713ms step_avg:412.36ms step:2673/6250 train_loss:2.4779 train_time:1098146ms step_avg:412.37ms step:2674/6250 train_loss:2.4864 train_time:1098570ms step_avg:412.38ms step:2675/6250 train_loss:2.5137 train_time:1098984ms step_avg:412.38ms step:2676/6250 train_loss:2.5416 train_time:1099399ms step_avg:412.38ms step:2677/6250 train_loss:2.4882 train_time:1099814ms step_avg:412.38ms step:2678/6250 train_loss:2.4654 train_time:1100229ms step_avg:412.38ms step:2679/6250 train_loss:2.6101 train_time:1100642ms step_avg:412.38ms step:2680/6250 train_loss:2.4755 train_time:1101053ms step_avg:412.38ms step:2681/6250 train_loss:2.4187 train_time:1101490ms step_avg:412.39ms step:2682/6250 train_loss:2.5346 train_time:1101930ms step_avg:412.40ms step:2683/6250 train_loss:2.4536 train_time:1102370ms step_avg:412.41ms step:2684/6250 train_loss:2.4748 train_time:1102783ms step_avg:412.41ms step:2685/6250 train_loss:2.5213 train_time:1103191ms step_avg:412.41ms step:2686/6250 train_loss:2.5647 train_time:1103603ms step_avg:412.41ms step:2687/6250 train_loss:2.4762 train_time:1104015ms step_avg:412.41ms step:2688/6250 train_loss:2.5067 train_time:1104426ms step_avg:412.41ms step:2689/6250 train_loss:2.4736 train_time:1104836ms step_avg:412.41ms step:2690/6250 train_loss:2.5099 train_time:1105247ms step_avg:412.41ms step:2691/6250 train_loss:2.5023 train_time:1105658ms step_avg:412.40ms step:2692/6250 train_loss:2.5465 train_time:1106067ms step_avg:412.40ms step:2693/6250 train_loss:2.4368 train_time:1106489ms step_avg:412.41ms step:2694/6250 train_loss:2.4934 train_time:1106905ms step_avg:412.41ms step:2695/6250 train_loss:2.4828 train_time:1107320ms step_avg:412.41ms step:2696/6250 train_loss:2.5466 train_time:1107739ms step_avg:412.41ms step:2697/6250 train_loss:2.5279 train_time:1108153ms step_avg:412.41ms step:2698/6250 train_loss:2.5913 train_time:1108567ms step_avg:412.41ms step:2699/6250 train_loss:2.4622 train_time:1108990ms step_avg:412.42ms step:2700/6250 train_loss:2.5489 train_time:1109401ms step_avg:412.42ms step:2701/6250 train_loss:2.5131 train_time:1109820ms step_avg:412.42ms step:2702/6250 train_loss:2.5483 train_time:1110241ms step_avg:412.42ms step:2703/6250 train_loss:2.4487 train_time:1110655ms step_avg:412.42ms step:2704/6250 train_loss:2.4521 train_time:1111070ms step_avg:412.42ms step:2705/6250 train_loss:2.5587 train_time:1111481ms step_avg:412.42ms step:2706/6250 train_loss:2.4755 train_time:1111899ms step_avg:412.43ms step:2707/6250 train_loss:2.4882 train_time:1112314ms step_avg:412.43ms step:2708/6250 train_loss:2.4928 train_time:1112737ms step_avg:412.43ms step:2709/6250 train_loss:2.4047 train_time:1113152ms step_avg:412.43ms step:2710/6250 train_loss:2.4916 train_time:1113565ms step_avg:412.43ms step:2711/6250 train_loss:2.4731 train_time:1113976ms step_avg:412.43ms step:2712/6250 train_loss:2.4437 train_time:1114389ms step_avg:412.43ms step:2713/6250 train_loss:2.5355 train_time:1114798ms step_avg:412.43ms step:2714/6250 train_loss:2.4766 train_time:1115209ms step_avg:412.43ms step:2715/6250 train_loss:2.4524 train_time:1115621ms step_avg:412.43ms step:2716/6250 train_loss:2.5169 train_time:1116031ms step_avg:412.43ms step:2717/6250 train_loss:2.5379 train_time:1116442ms step_avg:412.43ms step:2718/6250 train_loss:2.5703 train_time:1116854ms step_avg:412.43ms step:2719/6250 train_loss:2.5602 train_time:1117264ms step_avg:412.43ms step:2720/6250 train_loss:2.4203 train_time:1117674ms step_avg:412.43ms step:2721/6250 train_loss:2.3855 train_time:1118086ms step_avg:412.43ms step:2722/6250 train_loss:2.6142 train_time:1118497ms step_avg:412.42ms step:2723/6250 train_loss:2.3857 train_time:1118909ms step_avg:412.43ms step:2724/6250 train_loss:2.5248 train_time:1119322ms step_avg:412.43ms step:2725/6250 train_loss:2.5701 train_time:1119735ms step_avg:412.43ms step:2726/6250 train_loss:2.4901 train_time:1120146ms step_avg:412.43ms step:2727/6250 train_loss:2.5383 train_time:1120556ms step_avg:412.42ms step:2728/6250 train_loss:2.3580 train_time:1120968ms step_avg:412.42ms step:2729/6250 train_loss:2.4971 train_time:1121380ms step_avg:412.42ms step:2730/6250 train_loss:2.4623 train_time:1121792ms step_avg:412.42ms step:2731/6250 train_loss:2.5002 train_time:1122204ms step_avg:412.42ms step:2732/6250 train_loss:2.5335 train_time:1122617ms step_avg:412.42ms step:2733/6250 train_loss:2.4427 train_time:1123028ms step_avg:412.42ms step:2734/6250 train_loss:2.6158 train_time:1123441ms step_avg:412.42ms step:2735/6250 train_loss:2.4813 train_time:1123854ms step_avg:412.42ms step:2736/6250 train_loss:2.4895 train_time:1124270ms step_avg:412.42ms step:2737/6250 train_loss:2.5013 train_time:1124685ms step_avg:412.43ms step:2738/6250 train_loss:2.5687 train_time:1125098ms step_avg:412.43ms step:2739/6250 train_loss:2.5518 train_time:1125512ms step_avg:412.43ms step:2740/6250 train_loss:2.4858 train_time:1125925ms step_avg:412.43ms step:2741/6250 train_loss:2.5266 train_time:1126340ms step_avg:412.43ms step:2742/6250 train_loss:2.4675 train_time:1126756ms step_avg:412.43ms step:2743/6250 train_loss:2.4441 train_time:1127170ms step_avg:412.43ms step:2744/6250 train_loss:2.4915 train_time:1127584ms step_avg:412.43ms step:2745/6250 train_loss:2.5562 train_time:1127996ms step_avg:412.43ms step:2746/6250 train_loss:2.5138 train_time:1128410ms step_avg:412.43ms step:2747/6250 train_loss:2.5171 train_time:1128831ms step_avg:412.43ms step:2748/6250 train_loss:2.5049 train_time:1129263ms step_avg:412.44ms step:2749/6250 train_loss:2.5313 train_time:1129692ms step_avg:412.45ms step:2750/6250 train_loss:2.5084 train_time:1130107ms step_avg:412.45ms step:2751/6250 train_loss:2.4865 train_time:1130521ms step_avg:412.45ms step:2752/6250 train_loss:2.5663 train_time:1130930ms step_avg:412.45ms step:2753/6250 train_loss:2.4443 train_time:1131343ms step_avg:412.45ms step:2754/6250 train_loss:2.5201 train_time:1131756ms step_avg:412.45ms step:2755/6250 train_loss:2.5010 train_time:1132167ms step_avg:412.45ms step:2756/6250 train_loss:2.5086 train_time:1132581ms step_avg:412.45ms step:2757/6250 train_loss:2.4717 train_time:1132991ms step_avg:412.45ms step:2758/6250 train_loss:2.4870 train_time:1133401ms step_avg:412.45ms step:2759/6250 train_loss:2.4347 train_time:1133813ms step_avg:412.45ms step:2760/6250 train_loss:2.4987 train_time:1134229ms step_avg:412.45ms step:2761/6250 train_loss:2.4966 train_time:1134640ms step_avg:412.45ms step:2762/6250 train_loss:2.4338 train_time:1135053ms step_avg:412.45ms step:2763/6250 train_loss:2.3953 train_time:1135471ms step_avg:412.45ms step:2764/6250 train_loss:2.4097 train_time:1135887ms step_avg:412.45ms step:2765/6250 train_loss:2.4695 train_time:1136298ms step_avg:412.45ms step:2766/6250 train_loss:2.4795 train_time:1136710ms step_avg:412.45ms step:2767/6250 train_loss:2.5830 train_time:1137122ms step_avg:412.45ms step:2768/6250 train_loss:2.4423 train_time:1137536ms step_avg:412.45ms step:2769/6250 train_loss:2.5127 train_time:1137950ms step_avg:412.45ms step:2770/6250 train_loss:2.4444 train_time:1138361ms step_avg:412.45ms step:2771/6250 train_loss:2.4486 train_time:1138774ms step_avg:412.45ms step:2772/6250 train_loss:2.5141 train_time:1139190ms step_avg:412.45ms step:2773/6250 train_loss:2.5175 train_time:1139602ms step_avg:412.45ms step:2774/6250 train_loss:2.5346 train_time:1140016ms step_avg:412.45ms step:2775/6250 train_loss:2.6517 train_time:1140429ms step_avg:412.45ms step:2776/6250 train_loss:2.4759 train_time:1140844ms step_avg:412.45ms step:2777/6250 train_loss:2.5033 train_time:1141254ms step_avg:412.45ms step:2778/6250 train_loss:2.5053 train_time:1141666ms step_avg:412.45ms step:2779/6250 train_loss:2.4207 train_time:1142078ms step_avg:412.45ms step:2780/6250 train_loss:2.5641 train_time:1142493ms step_avg:412.45ms step:2781/6250 train_loss:2.4592 train_time:1142905ms step_avg:412.45ms step:2782/6250 train_loss:2.6013 train_time:1143317ms step_avg:412.45ms step:2783/6250 train_loss:2.5338 train_time:1143727ms step_avg:412.45ms step:2784/6250 train_loss:2.5277 train_time:1144136ms step_avg:412.45ms step:2785/6250 train_loss:2.5970 train_time:1144548ms step_avg:412.45ms step:2786/6250 train_loss:2.5338 train_time:1144961ms step_avg:412.45ms step:2787/6250 train_loss:2.5881 train_time:1145375ms step_avg:412.45ms step:2788/6250 train_loss:2.5375 train_time:1145785ms step_avg:412.45ms step:2789/6250 train_loss:2.3121 train_time:1146197ms step_avg:412.45ms step:2790/6250 train_loss:2.4270 train_time:1146608ms step_avg:412.45ms step:2791/6250 train_loss:2.4874 train_time:1147021ms step_avg:412.45ms step:2792/6250 train_loss:2.5033 train_time:1147431ms step_avg:412.45ms step:2793/6250 train_loss:2.5522 train_time:1147844ms step_avg:412.45ms step:2794/6250 train_loss:2.4503 train_time:1148254ms step_avg:412.45ms step:2795/6250 train_loss:2.5610 train_time:1148667ms step_avg:412.45ms step:2796/6250 train_loss:2.5153 train_time:1149078ms step_avg:412.45ms step:2797/6250 train_loss:2.5475 train_time:1149491ms step_avg:412.45ms step:2798/6250 train_loss:2.5060 train_time:1149902ms step_avg:412.45ms step:2799/6250 train_loss:2.4389 train_time:1150314ms step_avg:412.45ms step:2800/6250 train_loss:2.5342 train_time:1150727ms step_avg:412.45ms step:2801/6250 train_loss:2.4507 train_time:1151139ms step_avg:412.45ms step:2802/6250 train_loss:2.5140 train_time:1151551ms step_avg:412.45ms step:2803/6250 train_loss:2.4858 train_time:1151966ms step_avg:412.45ms step:2804/6250 train_loss:2.4971 train_time:1152379ms step_avg:412.45ms step:2805/6250 train_loss:2.6581 train_time:1152793ms step_avg:412.45ms step:2806/6250 train_loss:2.5530 train_time:1153206ms step_avg:412.45ms step:2807/6250 train_loss:2.4909 train_time:1153622ms step_avg:412.45ms step:2808/6250 train_loss:2.5105 train_time:1154036ms step_avg:412.45ms step:2809/6250 train_loss:2.4790 train_time:1154450ms step_avg:412.45ms step:2810/6250 train_loss:2.5126 train_time:1154860ms step_avg:412.45ms step:2811/6250 train_loss:2.6140 train_time:1155270ms step_avg:412.45ms step:2812/6250 train_loss:2.4743 train_time:1155686ms step_avg:412.45ms step:2813/6250 train_loss:2.4861 train_time:1156098ms step_avg:412.45ms step:2814/6250 train_loss:2.3863 train_time:1156511ms step_avg:412.45ms step:2815/6250 train_loss:2.4955 train_time:1156924ms step_avg:412.45ms step:2816/6250 train_loss:2.4441 train_time:1157336ms step_avg:412.45ms step:2817/6250 train_loss:2.4924 train_time:1157749ms step_avg:412.45ms step:2818/6250 train_loss:2.5496 train_time:1158159ms step_avg:412.45ms step:2819/6250 train_loss:2.4684 train_time:1158572ms step_avg:412.45ms step:2820/6250 train_loss:2.4565 train_time:1158984ms step_avg:412.45ms step:2821/6250 train_loss:2.4175 train_time:1159397ms step_avg:412.45ms step:2822/6250 train_loss:2.4118 train_time:1159814ms step_avg:412.45ms step:2823/6250 train_loss:2.4986 train_time:1160226ms step_avg:412.45ms step:2824/6250 train_loss:2.6217 train_time:1160643ms step_avg:412.45ms step:2825/6250 train_loss:2.5161 train_time:1161059ms step_avg:412.45ms step:2826/6250 train_loss:2.4287 train_time:1161471ms step_avg:412.45ms step:2827/6250 train_loss:2.5262 train_time:1161885ms step_avg:412.45ms step:2828/6250 train_loss:2.5547 train_time:1162294ms step_avg:412.45ms step:2829/6250 train_loss:2.5164 train_time:1162707ms step_avg:412.45ms step:2830/6250 train_loss:2.4344 train_time:1163117ms step_avg:412.45ms step:2831/6250 train_loss:2.6149 train_time:1163531ms step_avg:412.45ms step:2832/6250 train_loss:2.5526 train_time:1163942ms step_avg:412.45ms step:2833/6250 train_loss:2.4387 train_time:1164361ms step_avg:412.46ms step:2834/6250 train_loss:2.5037 train_time:1164776ms step_avg:412.46ms step:2835/6250 train_loss:2.4658 train_time:1165186ms step_avg:412.46ms step:2836/6250 train_loss:2.5301 train_time:1165599ms step_avg:412.46ms step:2837/6250 train_loss:2.5290 train_time:1166012ms step_avg:412.46ms step:2838/6250 train_loss:2.4876 train_time:1166430ms step_avg:412.46ms step:2839/6250 train_loss:2.4842 train_time:1166846ms step_avg:412.46ms step:2840/6250 train_loss:2.4807 train_time:1167257ms step_avg:412.46ms step:2841/6250 train_loss:2.5540 train_time:1167671ms step_avg:412.46ms step:2842/6250 train_loss:2.5023 train_time:1168083ms step_avg:412.46ms step:2843/6250 train_loss:2.4623 train_time:1168496ms step_avg:412.46ms step:2844/6250 train_loss:2.5090 train_time:1168907ms step_avg:412.46ms step:2845/6250 train_loss:2.4674 train_time:1169321ms step_avg:412.46ms step:2846/6250 train_loss:2.4118 train_time:1169734ms step_avg:412.46ms step:2847/6250 train_loss:2.4435 train_time:1170148ms step_avg:412.46ms step:2848/6250 train_loss:2.4706 train_time:1170563ms step_avg:412.46ms step:2849/6250 train_loss:2.4571 train_time:1170975ms step_avg:412.46ms step:2850/6250 train_loss:2.4364 train_time:1171388ms step_avg:412.46ms step:2851/6250 train_loss:2.5174 train_time:1171799ms step_avg:412.46ms step:2852/6250 train_loss:2.5136 train_time:1172213ms step_avg:412.46ms step:2853/6250 train_loss:2.5715 train_time:1172625ms step_avg:412.46ms step:2854/6250 train_loss:2.5484 train_time:1173037ms step_avg:412.46ms step:2855/6250 train_loss:2.5485 train_time:1173448ms step_avg:412.46ms step:2856/6250 train_loss:2.6541 train_time:1173861ms step_avg:412.46ms step:2857/6250 train_loss:2.4782 train_time:1174273ms step_avg:412.46ms step:2858/6250 train_loss:2.5728 train_time:1174686ms step_avg:412.46ms step:2859/6250 train_loss:2.4824 train_time:1175099ms step_avg:412.46ms step:2860/6250 train_loss:2.5251 train_time:1175513ms step_avg:412.46ms step:2861/6250 train_loss:2.4505 train_time:1175922ms step_avg:412.46ms step:2862/6250 train_loss:2.4792 train_time:1176338ms step_avg:412.46ms step:2863/6250 train_loss:2.6103 train_time:1176754ms step_avg:412.46ms step:2864/6250 train_loss:2.5416 train_time:1177166ms step_avg:412.46ms step:2865/6250 train_loss:2.4879 train_time:1177579ms step_avg:412.46ms step:2866/6250 train_loss:2.4666 train_time:1177989ms step_avg:412.46ms step:2867/6250 train_loss:2.5082 train_time:1178403ms step_avg:412.46ms step:2868/6250 train_loss:2.4385 train_time:1178814ms step_avg:412.46ms step:2869/6250 train_loss:2.4540 train_time:1179227ms step_avg:412.46ms step:2870/6250 train_loss:2.5180 train_time:1179645ms step_avg:412.46ms step:2871/6250 train_loss:2.5412 train_time:1180056ms step_avg:412.46ms step:2872/6250 train_loss:2.4454 train_time:1180472ms step_avg:412.46ms step:2873/6250 train_loss:2.5136 train_time:1180887ms step_avg:412.46ms step:2874/6250 train_loss:2.3492 train_time:1181298ms step_avg:412.46ms step:2875/6250 train_loss:2.4533 train_time:1181713ms step_avg:412.47ms step:2876/6250 train_loss:2.5341 train_time:1182123ms step_avg:412.46ms step:2877/6250 train_loss:2.4634 train_time:1182538ms step_avg:412.47ms step:2878/6250 train_loss:2.4615 train_time:1182948ms step_avg:412.46ms step:2879/6250 train_loss:2.4178 train_time:1183361ms step_avg:412.46ms step:2880/6250 train_loss:2.5417 train_time:1183772ms step_avg:412.46ms step:2881/6250 train_loss:2.4586 train_time:1184185ms step_avg:412.46ms step:2882/6250 train_loss:2.5733 train_time:1184597ms step_avg:412.46ms step:2883/6250 train_loss:2.3988 train_time:1185009ms step_avg:412.46ms step:2884/6250 train_loss:2.4644 train_time:1185421ms step_avg:412.46ms step:2885/6250 train_loss:2.3683 train_time:1185834ms step_avg:412.46ms step:2886/6250 train_loss:2.4752 train_time:1186244ms step_avg:412.46ms step:2887/6250 train_loss:2.3924 train_time:1186657ms step_avg:412.46ms step:2888/6250 train_loss:2.5081 train_time:1187069ms step_avg:412.46ms step:2889/6250 train_loss:2.3833 train_time:1187483ms step_avg:412.46ms step:2890/6250 train_loss:2.5008 train_time:1187898ms step_avg:412.46ms step:2891/6250 train_loss:2.5008 train_time:1188309ms step_avg:412.46ms step:2892/6250 train_loss:2.4840 train_time:1188721ms step_avg:412.46ms step:2893/6250 train_loss:2.5481 train_time:1189132ms step_avg:412.46ms step:2894/6250 train_loss:2.4950 train_time:1189545ms step_avg:412.46ms step:2895/6250 train_loss:2.4069 train_time:1189960ms step_avg:412.46ms step:2896/6250 train_loss:2.3513 train_time:1190376ms step_avg:412.47ms step:2897/6250 train_loss:2.4810 train_time:1190791ms step_avg:412.47ms step:2898/6250 train_loss:2.4765 train_time:1191203ms step_avg:412.47ms step:2899/6250 train_loss:2.4302 train_time:1191616ms step_avg:412.47ms step:2900/6250 train_loss:2.6339 train_time:1192028ms step_avg:412.47ms step:2901/6250 train_loss:2.3696 train_time:1192440ms step_avg:412.47ms step:2902/6250 train_loss:2.3870 train_time:1192853ms step_avg:412.47ms step:2903/6250 train_loss:2.5139 train_time:1193263ms step_avg:412.47ms step:2904/6250 train_loss:2.4056 train_time:1193677ms step_avg:412.47ms step:2905/6250 train_loss:2.5052 train_time:1194089ms step_avg:412.47ms step:2906/6250 train_loss:2.4035 train_time:1194504ms step_avg:412.47ms step:2907/6250 train_loss:2.4934 train_time:1194914ms step_avg:412.47ms step:2908/6250 train_loss:2.4730 train_time:1195327ms step_avg:412.47ms step:2909/6250 train_loss:2.4443 train_time:1195737ms step_avg:412.47ms step:2910/6250 train_loss:2.3960 train_time:1196148ms step_avg:412.46ms step:2911/6250 train_loss:2.5187 train_time:1196561ms step_avg:412.47ms step:2912/6250 train_loss:2.4439 train_time:1196976ms step_avg:412.47ms step:2913/6250 train_loss:2.4630 train_time:1197388ms step_avg:412.47ms step:2914/6250 train_loss:2.4759 train_time:1197804ms step_avg:412.47ms step:2915/6250 train_loss:2.4129 train_time:1198218ms step_avg:412.47ms step:2916/6250 train_loss:2.6518 train_time:1198633ms step_avg:412.47ms step:2917/6250 train_loss:2.4975 train_time:1199045ms step_avg:412.47ms step:2918/6250 train_loss:2.4993 train_time:1199458ms step_avg:412.47ms step:2919/6250 train_loss:2.4375 train_time:1199875ms step_avg:412.47ms step:2920/6250 train_loss:2.5641 train_time:1200291ms step_avg:412.47ms step:2921/6250 train_loss:2.5159 train_time:1200707ms step_avg:412.47ms step:2922/6250 train_loss:2.4692 train_time:1201118ms step_avg:412.47ms step:2923/6250 train_loss:2.4223 train_time:1201531ms step_avg:412.47ms step:2924/6250 train_loss:2.4851 train_time:1201943ms step_avg:412.47ms step:2925/6250 train_loss:2.4295 train_time:1202359ms step_avg:412.47ms step:2926/6250 train_loss:2.4921 train_time:1202775ms step_avg:412.47ms step:2927/6250 train_loss:2.4394 train_time:1203187ms step_avg:412.47ms step:2928/6250 train_loss:2.4907 train_time:1203602ms step_avg:412.48ms step:2929/6250 train_loss:2.4932 train_time:1204012ms step_avg:412.47ms step:2930/6250 train_loss:2.5694 train_time:1204426ms step_avg:412.47ms step:2931/6250 train_loss:2.4975 train_time:1204837ms step_avg:412.47ms step:2932/6250 train_loss:2.4794 train_time:1205251ms step_avg:412.47ms step:2933/6250 train_loss:2.5424 train_time:1205668ms step_avg:412.48ms step:2934/6250 train_loss:2.4588 train_time:1206080ms step_avg:412.48ms step:2935/6250 train_loss:2.3607 train_time:1206494ms step_avg:412.48ms step:2936/6250 train_loss:2.4745 train_time:1206907ms step_avg:412.48ms step:2937/6250 train_loss:2.4526 train_time:1207323ms step_avg:412.48ms step:2938/6250 train_loss:2.4919 train_time:1207735ms step_avg:412.48ms step:2939/6250 train_loss:2.4788 train_time:1208150ms step_avg:412.48ms step:2940/6250 train_loss:2.4778 train_time:1208565ms step_avg:412.48ms step:2941/6250 train_loss:2.3992 train_time:1208975ms step_avg:412.48ms step:2942/6250 train_loss:2.4175 train_time:1209389ms step_avg:412.48ms step:2943/6250 train_loss:2.4627 train_time:1209806ms step_avg:412.48ms step:2944/6250 train_loss:2.5727 train_time:1210217ms step_avg:412.48ms step:2945/6250 train_loss:2.5564 train_time:1210632ms step_avg:412.48ms step:2946/6250 train_loss:2.4868 train_time:1211044ms step_avg:412.48ms step:2947/6250 train_loss:2.4584 train_time:1211454ms step_avg:412.48ms step:2948/6250 train_loss:2.5598 train_time:1211863ms step_avg:412.48ms step:2949/6250 train_loss:2.3948 train_time:1212275ms step_avg:412.48ms step:2950/6250 train_loss:2.5238 train_time:1212688ms step_avg:412.48ms step:2951/6250 train_loss:2.4859 train_time:1213102ms step_avg:412.48ms step:2952/6250 train_loss:2.5572 train_time:1213513ms step_avg:412.48ms step:2953/6250 train_loss:2.4545 train_time:1213923ms step_avg:412.48ms step:2954/6250 train_loss:2.5062 train_time:1214336ms step_avg:412.48ms step:2955/6250 train_loss:2.4004 train_time:1214752ms step_avg:412.48ms step:2956/6250 train_loss:2.5108 train_time:1215164ms step_avg:412.48ms step:2957/6250 train_loss:2.4362 train_time:1215577ms step_avg:412.48ms step:2958/6250 train_loss:2.4883 train_time:1215988ms step_avg:412.48ms step:2959/6250 train_loss:2.4264 train_time:1216401ms step_avg:412.48ms step:2960/6250 train_loss:2.5179 train_time:1216813ms step_avg:412.48ms step:2961/6250 train_loss:2.4563 train_time:1217225ms step_avg:412.48ms step:2962/6250 train_loss:2.4794 train_time:1217636ms step_avg:412.48ms step:2963/6250 train_loss:2.6031 train_time:1218049ms step_avg:412.48ms step:2964/6250 train_loss:2.4657 train_time:1218460ms step_avg:412.48ms step:2965/6250 train_loss:2.4923 train_time:1218872ms step_avg:412.48ms step:2966/6250 train_loss:2.4748 train_time:1219285ms step_avg:412.48ms step:2967/6250 train_loss:2.6182 train_time:1219698ms step_avg:412.48ms step:2968/6250 train_loss:2.4977 train_time:1220108ms step_avg:412.48ms step:2969/6250 train_loss:2.3994 train_time:1220522ms step_avg:412.48ms step:2970/6250 train_loss:2.4215 train_time:1220948ms step_avg:412.48ms step:2971/6250 train_loss:2.5027 train_time:1221373ms step_avg:412.49ms step:2972/6250 train_loss:2.4119 train_time:1221785ms step_avg:412.49ms step:2973/6250 train_loss:2.4776 train_time:1222195ms step_avg:412.49ms step:2974/6250 train_loss:2.4513 train_time:1222611ms step_avg:412.49ms step:2975/6250 train_loss:2.4429 train_time:1223021ms step_avg:412.49ms step:2976/6250 train_loss:2.4768 train_time:1223433ms step_avg:412.49ms step:2977/6250 train_loss:2.4649 train_time:1223844ms step_avg:412.49ms step:2978/6250 train_loss:2.5587 train_time:1224254ms step_avg:412.48ms step:2979/6250 train_loss:2.5114 train_time:1224668ms step_avg:412.48ms step:2980/6250 train_loss:2.5061 train_time:1225087ms step_avg:412.49ms step:2981/6250 train_loss:2.4690 train_time:1225503ms step_avg:412.49ms step:2982/6250 train_loss:2.4276 train_time:1225915ms step_avg:412.49ms step:2983/6250 train_loss:2.5345 train_time:1226328ms step_avg:412.49ms step:2984/6250 train_loss:2.4290 train_time:1226746ms step_avg:412.49ms step:2985/6250 train_loss:2.4030 train_time:1227157ms step_avg:412.49ms step:2986/6250 train_loss:2.4644 train_time:1227571ms step_avg:412.49ms step:2987/6250 train_loss:2.4362 train_time:1227981ms step_avg:412.49ms step:2988/6250 train_loss:2.4112 train_time:1228393ms step_avg:412.49ms step:2989/6250 train_loss:2.4175 train_time:1228804ms step_avg:412.49ms step:2990/6250 train_loss:2.5085 train_time:1229215ms step_avg:412.49ms step:2991/6250 train_loss:2.5449 train_time:1229632ms step_avg:412.49ms step:2992/6250 train_loss:2.4304 train_time:1230044ms step_avg:412.49ms step:2993/6250 train_loss:2.4650 train_time:1230454ms step_avg:412.49ms step:2994/6250 train_loss:2.4962 train_time:1230867ms step_avg:412.49ms step:2995/6250 train_loss:2.4569 train_time:1231279ms step_avg:412.49ms step:2996/6250 train_loss:2.4504 train_time:1231691ms step_avg:412.49ms step:2997/6250 train_loss:2.5062 train_time:1232105ms step_avg:412.49ms step:2998/6250 train_loss:2.3961 train_time:1232520ms step_avg:412.49ms step:2999/6250 train_loss:2.5353 train_time:1232932ms step_avg:412.49ms step:3000/6250 train_loss:2.3722 train_time:1233344ms step_avg:412.49ms step:3001/6250 train_loss:2.4562 train_time:1233754ms step_avg:412.49ms step:3002/6250 train_loss:2.4920 train_time:1234170ms step_avg:412.49ms step:3003/6250 train_loss:2.4750 train_time:1234579ms step_avg:412.49ms step:3004/6250 train_loss:2.4910 train_time:1234993ms step_avg:412.49ms step:3005/6250 train_loss:2.5112 train_time:1235404ms step_avg:412.49ms step:3006/6250 train_loss:2.4844 train_time:1235821ms step_avg:412.49ms step:3007/6250 train_loss:2.4956 train_time:1236230ms step_avg:412.49ms step:3008/6250 train_loss:2.4231 train_time:1236642ms step_avg:412.49ms step:3009/6250 train_loss:2.4952 train_time:1237058ms step_avg:412.49ms step:3010/6250 train_loss:2.4708 train_time:1237469ms step_avg:412.49ms step:3011/6250 train_loss:2.4846 train_time:1237879ms step_avg:412.49ms step:3012/6250 train_loss:2.3929 train_time:1238290ms step_avg:412.49ms step:3013/6250 train_loss:2.5543 train_time:1238702ms step_avg:412.49ms step:3014/6250 train_loss:2.4920 train_time:1239116ms step_avg:412.49ms step:3015/6250 train_loss:2.3964 train_time:1239528ms step_avg:412.49ms step:3016/6250 train_loss:2.4214 train_time:1239940ms step_avg:412.49ms step:3017/6250 train_loss:2.4134 train_time:1240351ms step_avg:412.49ms step:3018/6250 train_loss:2.3884 train_time:1240764ms step_avg:412.49ms step:3019/6250 train_loss:2.5163 train_time:1241176ms step_avg:412.49ms step:3020/6250 train_loss:2.5128 train_time:1241616ms step_avg:412.50ms step:3021/6250 train_loss:2.5753 train_time:1242048ms step_avg:412.50ms step:3022/6250 train_loss:2.4386 train_time:1242467ms step_avg:412.51ms step:3023/6250 train_loss:2.5049 train_time:1242905ms step_avg:412.51ms step:3024/6250 train_loss:2.4295 train_time:1243344ms step_avg:412.52ms step:3025/6250 train_loss:2.4216 train_time:1243782ms step_avg:412.53ms step:3026/6250 train_loss:2.4011 train_time:1244210ms step_avg:412.54ms step:3027/6250 train_loss:2.4595 train_time:1244633ms step_avg:412.54ms step:3028/6250 train_loss:2.4334 train_time:1245071ms step_avg:412.55ms step:3029/6250 train_loss:2.4601 train_time:1245506ms step_avg:412.56ms step:3030/6250 train_loss:2.4394 train_time:1245944ms step_avg:412.56ms step:3031/6250 train_loss:2.5641 train_time:1246378ms step_avg:412.57ms step:3032/6250 train_loss:2.4795 train_time:1246809ms step_avg:412.58ms step:3033/6250 train_loss:2.4254 train_time:1247241ms step_avg:412.58ms step:3034/6250 train_loss:2.4235 train_time:1247673ms step_avg:412.59ms step:3035/6250 train_loss:2.5191 train_time:1248106ms step_avg:412.60ms step:3036/6250 train_loss:2.4599 train_time:1248526ms step_avg:412.60ms step:3037/6250 train_loss:2.4496 train_time:1248938ms step_avg:412.60ms step:3038/6250 train_loss:2.5297 train_time:1249348ms step_avg:412.60ms step:3039/6250 train_loss:2.4598 train_time:1249759ms step_avg:412.60ms step:3040/6250 train_loss:2.4479 train_time:1250172ms step_avg:412.60ms step:3041/6250 train_loss:2.3762 train_time:1250586ms step_avg:412.60ms step:3042/6250 train_loss:2.4444 train_time:1250998ms step_avg:412.60ms step:3043/6250 train_loss:2.3696 train_time:1251412ms step_avg:412.60ms step:3044/6250 train_loss:2.3930 train_time:1251829ms step_avg:412.60ms step:3045/6250 train_loss:2.5745 train_time:1252243ms step_avg:412.60ms step:3046/6250 train_loss:2.4747 train_time:1252684ms step_avg:412.61ms step:3047/6250 train_loss:2.4894 train_time:1253098ms step_avg:412.61ms step:3048/6250 train_loss:2.4696 train_time:1253525ms step_avg:412.62ms step:3049/6250 train_loss:2.4854 train_time:1253942ms step_avg:412.62ms step:3050/6250 train_loss:2.4923 train_time:1254368ms step_avg:412.62ms step:3051/6250 train_loss:2.4821 train_time:1254801ms step_avg:412.63ms step:3052/6250 train_loss:2.5451 train_time:1255235ms step_avg:412.63ms step:3053/6250 train_loss:2.5269 train_time:1255669ms step_avg:412.64ms step:3054/6250 train_loss:2.3707 train_time:1256096ms step_avg:412.65ms step:3055/6250 train_loss:2.4365 train_time:1256547ms step_avg:412.66ms step:3056/6250 train_loss:2.4914 train_time:1256982ms step_avg:412.67ms step:3057/6250 train_loss:2.4385 train_time:1257401ms step_avg:412.67ms step:3058/6250 train_loss:2.4739 train_time:1257820ms step_avg:412.67ms step:3059/6250 train_loss:2.4760 train_time:1258234ms step_avg:412.67ms step:3060/6250 train_loss:2.5465 train_time:1258655ms step_avg:412.67ms step:3061/6250 train_loss:2.5008 train_time:1259071ms step_avg:412.67ms step:3062/6250 train_loss:2.4784 train_time:1259488ms step_avg:412.68ms step:3063/6250 train_loss:2.4318 train_time:1259901ms step_avg:412.68ms step:3064/6250 train_loss:2.4321 train_time:1260318ms step_avg:412.68ms step:3065/6250 train_loss:2.4212 train_time:1260737ms step_avg:412.68ms step:3066/6250 train_loss:2.4435 train_time:1261149ms step_avg:412.68ms step:3067/6250 train_loss:2.5145 train_time:1261561ms step_avg:412.68ms step:3068/6250 train_loss:2.4448 train_time:1261969ms step_avg:412.68ms step:3069/6250 train_loss:2.4951 train_time:1262382ms step_avg:412.68ms step:3070/6250 train_loss:2.4485 train_time:1262795ms step_avg:412.68ms step:3071/6250 train_loss:2.4944 train_time:1263204ms step_avg:412.68ms step:3072/6250 train_loss:2.3850 train_time:1263616ms step_avg:412.68ms step:3073/6250 train_loss:2.4239 train_time:1264029ms step_avg:412.68ms step:3074/6250 train_loss:2.4860 train_time:1264441ms step_avg:412.68ms step:3075/6250 train_loss:2.5256 train_time:1264852ms step_avg:412.68ms step:3076/6250 train_loss:2.4341 train_time:1265263ms step_avg:412.68ms step:3077/6250 train_loss:2.5261 train_time:1265677ms step_avg:412.68ms step:3078/6250 train_loss:2.4826 train_time:1266086ms step_avg:412.67ms step:3079/6250 train_loss:2.4896 train_time:1266497ms step_avg:412.67ms step:3080/6250 train_loss:2.4160 train_time:1266908ms step_avg:412.67ms step:3081/6250 train_loss:2.4982 train_time:1267333ms step_avg:412.68ms step:3082/6250 train_loss:2.4998 train_time:1267752ms step_avg:412.68ms step:3083/6250 train_loss:2.4245 train_time:1268168ms step_avg:412.68ms step:3084/6250 train_loss:2.4735 train_time:1268584ms step_avg:412.68ms step:3085/6250 train_loss:2.5353 train_time:1268998ms step_avg:412.68ms step:3086/6250 train_loss:2.3434 train_time:1269418ms step_avg:412.68ms step:3087/6250 train_loss:2.5304 train_time:1269837ms step_avg:412.69ms step:3088/6250 train_loss:2.4845 train_time:1270254ms step_avg:412.69ms step:3089/6250 train_loss:2.5597 train_time:1270670ms step_avg:412.69ms step:3090/6250 train_loss:2.4446 train_time:1271085ms step_avg:412.69ms step:3091/6250 train_loss:2.4481 train_time:1271496ms step_avg:412.69ms step:3092/6250 train_loss:2.4935 train_time:1271910ms step_avg:412.69ms step:3093/6250 train_loss:2.4863 train_time:1272319ms step_avg:412.69ms step:3094/6250 train_loss:2.4720 train_time:1272729ms step_avg:412.69ms step:3095/6250 train_loss:2.4722 train_time:1273140ms step_avg:412.69ms step:3096/6250 train_loss:2.4885 train_time:1273552ms step_avg:412.69ms step:3097/6250 train_loss:2.4013 train_time:1273970ms step_avg:412.69ms step:3098/6250 train_loss:2.4081 train_time:1274380ms step_avg:412.69ms step:3099/6250 train_loss:2.4676 train_time:1274792ms step_avg:412.69ms step:3100/6250 train_loss:2.5492 train_time:1275202ms step_avg:412.69ms step:3101/6250 train_loss:2.4420 train_time:1275614ms step_avg:412.69ms step:3102/6250 train_loss:2.4040 train_time:1276024ms step_avg:412.69ms step:3103/6250 train_loss:2.4545 train_time:1276436ms step_avg:412.69ms step:3104/6250 train_loss:2.4982 train_time:1276855ms step_avg:412.69ms step:3105/6250 train_loss:2.4443 train_time:1277270ms step_avg:412.69ms step:3106/6250 train_loss:2.4663 train_time:1277689ms step_avg:412.69ms step:3107/6250 train_loss:2.4225 train_time:1278115ms step_avg:412.69ms step:3108/6250 train_loss:2.5046 train_time:1278533ms step_avg:412.70ms step:3109/6250 train_loss:2.5384 train_time:1278959ms step_avg:412.70ms step:3110/6250 train_loss:2.4323 train_time:1279379ms step_avg:412.70ms step:3111/6250 train_loss:2.3632 train_time:1279789ms step_avg:412.70ms step:3112/6250 train_loss:2.4844 train_time:1280208ms step_avg:412.70ms step:3113/6250 train_loss:2.4670 train_time:1280649ms step_avg:412.71ms step:3114/6250 train_loss:2.5644 train_time:1281059ms step_avg:412.71ms step:3115/6250 train_loss:2.4328 train_time:1281476ms step_avg:412.71ms step:3116/6250 train_loss:2.4945 train_time:1281885ms step_avg:412.71ms step:3117/6250 train_loss:2.5323 train_time:1282298ms step_avg:412.71ms step:3118/6250 train_loss:2.4722 train_time:1282711ms step_avg:412.71ms step:3119/6250 train_loss:2.4787 train_time:1283127ms step_avg:412.71ms step:3120/6250 train_loss:2.4874 train_time:1283551ms step_avg:412.72ms step:3121/6250 train_loss:2.4423 train_time:1283963ms step_avg:412.72ms step:3122/6250 train_loss:2.4714 train_time:1284376ms step_avg:412.72ms step:3123/6250 train_loss:2.4998 train_time:1284794ms step_avg:412.72ms step:3124/6250 train_loss:2.4622 train_time:1285205ms step_avg:412.72ms step:3125/6250 train_loss:2.4061 train_time:1285617ms step_avg:412.72ms step:3126/6250 train_loss:2.4864 train_time:1286032ms step_avg:412.72ms step:3127/6250 train_loss:2.5105 train_time:1286454ms step_avg:412.72ms step:3128/6250 train_loss:2.5534 train_time:1286892ms step_avg:412.73ms step:3129/6250 train_loss:2.3798 train_time:1287342ms step_avg:412.74ms step:3130/6250 train_loss:2.3935 train_time:1287780ms step_avg:412.75ms step:3131/6250 train_loss:2.5006 train_time:1288196ms step_avg:412.75ms step:3132/6250 train_loss:2.4379 train_time:1288609ms step_avg:412.75ms step:3133/6250 train_loss:2.4815 train_time:1289019ms step_avg:412.75ms step:3134/6250 train_loss:2.5342 train_time:1289431ms step_avg:412.75ms step:3135/6250 train_loss:2.5757 train_time:1289843ms step_avg:412.75ms step:3136/6250 train_loss:2.4167 train_time:1290255ms step_avg:412.75ms step:3137/6250 train_loss:2.4835 train_time:1290666ms step_avg:412.75ms step:3138/6250 train_loss:2.4717 train_time:1291078ms step_avg:412.75ms step:3139/6250 train_loss:2.4405 train_time:1291489ms step_avg:412.75ms step:3140/6250 train_loss:2.4696 train_time:1291902ms step_avg:412.75ms step:3141/6250 train_loss:2.4507 train_time:1292313ms step_avg:412.75ms step:3142/6250 train_loss:2.4884 train_time:1292728ms step_avg:412.75ms step:3143/6250 train_loss:2.4648 train_time:1293143ms step_avg:412.75ms step:3144/6250 train_loss:2.4832 train_time:1293554ms step_avg:412.75ms step:3145/6250 train_loss:2.5165 train_time:1293965ms step_avg:412.75ms step:3146/6250 train_loss:2.5248 train_time:1294378ms step_avg:412.75ms step:3147/6250 train_loss:2.4234 train_time:1294792ms step_avg:412.75ms step:3148/6250 train_loss:2.5084 train_time:1295200ms step_avg:412.75ms step:3149/6250 train_loss:2.3524 train_time:1295611ms step_avg:412.75ms step:3150/6250 train_loss:2.5019 train_time:1296022ms step_avg:412.75ms step:3151/6250 train_loss:2.4263 train_time:1296433ms step_avg:412.75ms step:3152/6250 train_loss:2.4946 train_time:1296843ms step_avg:412.74ms step:3153/6250 train_loss:2.4434 train_time:1297256ms step_avg:412.74ms step:3154/6250 train_loss:2.5101 train_time:1297664ms step_avg:412.74ms step:3155/6250 train_loss:2.4710 train_time:1298072ms step_avg:412.74ms step:3156/6250 train_loss:2.3961 train_time:1298487ms step_avg:412.74ms step:3157/6250 train_loss:2.4223 train_time:1298912ms step_avg:412.75ms step:3158/6250 train_loss:2.5040 train_time:1299324ms step_avg:412.75ms step:3159/6250 train_loss:2.5765 train_time:1299734ms step_avg:412.74ms step:3160/6250 train_loss:2.4684 train_time:1300145ms step_avg:412.74ms step:3161/6250 train_loss:2.4707 train_time:1300568ms step_avg:412.75ms step:3162/6250 train_loss:2.3915 train_time:1300987ms step_avg:412.75ms step:3163/6250 train_loss:2.5194 train_time:1301403ms step_avg:412.75ms step:3164/6250 train_loss:2.4842 train_time:1301821ms step_avg:412.75ms step:3165/6250 train_loss:2.4461 train_time:1302231ms step_avg:412.75ms step:3166/6250 train_loss:2.5316 train_time:1302662ms step_avg:412.76ms step:3167/6250 train_loss:2.4931 train_time:1303086ms step_avg:412.76ms step:3168/6250 train_loss:2.3946 train_time:1303504ms step_avg:412.76ms step:3169/6250 train_loss:2.4751 train_time:1303921ms step_avg:412.76ms step:3170/6250 train_loss:2.4393 train_time:1304340ms step_avg:412.77ms step:3171/6250 train_loss:2.4462 train_time:1304766ms step_avg:412.77ms step:3172/6250 train_loss:2.4658 train_time:1305186ms step_avg:412.77ms step:3173/6250 train_loss:2.5192 train_time:1305601ms step_avg:412.77ms step:3174/6250 train_loss:2.4425 train_time:1306013ms step_avg:412.77ms step:3175/6250 train_loss:2.4891 train_time:1306424ms step_avg:412.77ms step:3176/6250 train_loss:2.4557 train_time:1306835ms step_avg:412.77ms step:3177/6250 train_loss:2.4290 train_time:1307248ms step_avg:412.77ms step:3178/6250 train_loss:2.5572 train_time:1307660ms step_avg:412.77ms step:3179/6250 train_loss:2.5536 train_time:1308075ms step_avg:412.77ms step:3180/6250 train_loss:2.3905 train_time:1308486ms step_avg:412.77ms step:3181/6250 train_loss:2.5271 train_time:1308899ms step_avg:412.77ms step:3182/6250 train_loss:2.3491 train_time:1309312ms step_avg:412.77ms step:3183/6250 train_loss:2.4633 train_time:1309726ms step_avg:412.77ms step:3184/6250 train_loss:2.5447 train_time:1310145ms step_avg:412.77ms step:3185/6250 train_loss:2.3512 train_time:1310560ms step_avg:412.77ms step:3186/6250 train_loss:2.3762 train_time:1310980ms step_avg:412.78ms step:3187/6250 train_loss:2.4182 train_time:1311398ms step_avg:412.78ms step:3188/6250 train_loss:2.3950 train_time:1311815ms step_avg:412.78ms step:3189/6250 train_loss:2.3856 train_time:1312233ms step_avg:412.78ms step:3190/6250 train_loss:2.3747 train_time:1312654ms step_avg:412.78ms step:3191/6250 train_loss:2.4544 train_time:1313070ms step_avg:412.79ms step:3192/6250 train_loss:2.5186 train_time:1313487ms step_avg:412.79ms step:3193/6250 train_loss:2.4680 train_time:1313906ms step_avg:412.79ms step:3194/6250 train_loss:2.4040 train_time:1314325ms step_avg:412.79ms step:3195/6250 train_loss:2.4151 train_time:1314746ms step_avg:412.79ms step:3196/6250 train_loss:2.4528 train_time:1315160ms step_avg:412.79ms step:3197/6250 train_loss:2.3935 train_time:1315577ms step_avg:412.79ms step:3198/6250 train_loss:2.4012 train_time:1315996ms step_avg:412.80ms step:3199/6250 train_loss:2.5484 train_time:1316417ms step_avg:412.80ms step:3200/6250 train_loss:2.3882 train_time:1316838ms step_avg:412.80ms step:3201/6250 train_loss:2.4354 train_time:1317254ms step_avg:412.80ms step:3202/6250 train_loss:2.3774 train_time:1317672ms step_avg:412.80ms step:3203/6250 train_loss:2.5358 train_time:1318089ms step_avg:412.81ms step:3204/6250 train_loss:2.4352 train_time:1318500ms step_avg:412.81ms step:3205/6250 train_loss:2.5011 train_time:1318913ms step_avg:412.81ms step:3206/6250 train_loss:2.4564 train_time:1319323ms step_avg:412.80ms step:3207/6250 train_loss:2.4856 train_time:1319736ms step_avg:412.80ms step:3208/6250 train_loss:2.3910 train_time:1320146ms step_avg:412.80ms step:3209/6250 train_loss:2.4146 train_time:1320559ms step_avg:412.80ms step:3210/6250 train_loss:2.4455 train_time:1320970ms step_avg:412.80ms step:3211/6250 train_loss:2.4341 train_time:1321381ms step_avg:412.80ms step:3212/6250 train_loss:2.3771 train_time:1321790ms step_avg:412.80ms step:3213/6250 train_loss:2.3955 train_time:1322201ms step_avg:412.80ms step:3214/6250 train_loss:2.3953 train_time:1322615ms step_avg:412.80ms step:3215/6250 train_loss:2.4145 train_time:1323028ms step_avg:412.80ms step:3216/6250 train_loss:2.4697 train_time:1323439ms step_avg:412.80ms step:3217/6250 train_loss:2.4676 train_time:1323849ms step_avg:412.80ms step:3218/6250 train_loss:2.5309 train_time:1324260ms step_avg:412.80ms step:3219/6250 train_loss:2.3286 train_time:1324671ms step_avg:412.80ms step:3220/6250 train_loss:2.5085 train_time:1325082ms step_avg:412.80ms step:3221/6250 train_loss:2.5300 train_time:1325493ms step_avg:412.80ms step:3222/6250 train_loss:2.4261 train_time:1325905ms step_avg:412.80ms step:3223/6250 train_loss:2.3752 train_time:1326316ms step_avg:412.80ms step:3224/6250 train_loss:2.5114 train_time:1326729ms step_avg:412.80ms step:3225/6250 train_loss:2.4044 train_time:1327139ms step_avg:412.80ms step:3226/6250 train_loss:2.5280 train_time:1327550ms step_avg:412.80ms step:3227/6250 train_loss:2.4989 train_time:1327961ms step_avg:412.79ms step:3228/6250 train_loss:2.3470 train_time:1328373ms step_avg:412.79ms step:3229/6250 train_loss:2.4992 train_time:1328784ms step_avg:412.79ms step:3230/6250 train_loss:2.4178 train_time:1329195ms step_avg:412.79ms step:3231/6250 train_loss:2.5769 train_time:1329606ms step_avg:412.79ms step:3232/6250 train_loss:2.4240 train_time:1330020ms step_avg:412.79ms step:3233/6250 train_loss:2.5289 train_time:1330433ms step_avg:412.79ms step:3234/6250 train_loss:2.4129 train_time:1330846ms step_avg:412.79ms step:3235/6250 train_loss:2.3824 train_time:1331257ms step_avg:412.79ms step:3236/6250 train_loss:2.4441 train_time:1331671ms step_avg:412.79ms step:3237/6250 train_loss:2.3809 train_time:1332080ms step_avg:412.79ms step:3238/6250 train_loss:2.4485 train_time:1332494ms step_avg:412.79ms step:3239/6250 train_loss:2.4252 train_time:1332907ms step_avg:412.79ms step:3240/6250 train_loss:2.3977 train_time:1333317ms step_avg:412.79ms step:3241/6250 train_loss:2.4604 train_time:1333726ms step_avg:412.79ms step:3242/6250 train_loss:2.4718 train_time:1334138ms step_avg:412.79ms step:3243/6250 train_loss:2.4535 train_time:1334549ms step_avg:412.79ms step:3244/6250 train_loss:2.4421 train_time:1334964ms step_avg:412.79ms step:3245/6250 train_loss:2.5383 train_time:1335374ms step_avg:412.79ms step:3246/6250 train_loss:2.4672 train_time:1335788ms step_avg:412.79ms step:3247/6250 train_loss:2.4643 train_time:1336197ms step_avg:412.79ms step:3248/6250 train_loss:2.3793 train_time:1336611ms step_avg:412.79ms step:3249/6250 train_loss:2.4895 train_time:1337022ms step_avg:412.79ms step:3250/6250 train_loss:2.4559 train_time:1337434ms step_avg:412.79ms step:3251/6250 train_loss:2.4774 train_time:1337847ms step_avg:412.79ms step:3252/6250 train_loss:2.5443 train_time:1338258ms step_avg:412.79ms step:3253/6250 train_loss:2.5052 train_time:1338670ms step_avg:412.79ms step:3254/6250 train_loss:2.4250 train_time:1339080ms step_avg:412.79ms step:3255/6250 train_loss:2.3452 train_time:1339493ms step_avg:412.79ms step:3256/6250 train_loss:2.4624 train_time:1339904ms step_avg:412.79ms step:3257/6250 train_loss:2.5186 train_time:1340316ms step_avg:412.79ms step:3258/6250 train_loss:2.5018 train_time:1340731ms step_avg:412.79ms step:3259/6250 train_loss:2.4881 train_time:1341141ms step_avg:412.79ms step:3260/6250 train_loss:2.4053 train_time:1341555ms step_avg:412.79ms step:3261/6250 train_loss:2.5274 train_time:1341968ms step_avg:412.79ms step:3262/6250 train_loss:2.3380 train_time:1342381ms step_avg:412.79ms step:3263/6250 train_loss:2.3959 train_time:1342792ms step_avg:412.79ms step:3264/6250 train_loss:2.4592 train_time:1343206ms step_avg:412.79ms step:3265/6250 train_loss:2.4085 train_time:1343618ms step_avg:412.79ms step:3266/6250 train_loss:2.4609 train_time:1344029ms step_avg:412.79ms step:3267/6250 train_loss:2.5426 train_time:1344439ms step_avg:412.78ms step:3268/6250 train_loss:2.5122 train_time:1344855ms step_avg:412.79ms step:3269/6250 train_loss:2.4581 train_time:1345265ms step_avg:412.78ms step:3270/6250 train_loss:2.4761 train_time:1345677ms step_avg:412.78ms step:3271/6250 train_loss:2.4638 train_time:1346086ms step_avg:412.78ms step:3272/6250 train_loss:2.4695 train_time:1346496ms step_avg:412.78ms step:3273/6250 train_loss:2.4853 train_time:1346909ms step_avg:412.78ms step:3274/6250 train_loss:2.4501 train_time:1347326ms step_avg:412.78ms step:3275/6250 train_loss:2.3830 train_time:1347747ms step_avg:412.79ms step:3276/6250 train_loss:2.5439 train_time:1348161ms step_avg:412.79ms step:3277/6250 train_loss:2.5219 train_time:1348575ms step_avg:412.79ms step:3278/6250 train_loss:2.3815 train_time:1348985ms step_avg:412.79ms step:3279/6250 train_loss:2.4033 train_time:1349399ms step_avg:412.79ms step:3280/6250 train_loss:2.4294 train_time:1349809ms step_avg:412.79ms step:3281/6250 train_loss:2.4105 train_time:1350222ms step_avg:412.79ms step:3282/6250 train_loss:2.5182 train_time:1350632ms step_avg:412.78ms step:3283/6250 train_loss:2.3720 train_time:1351046ms step_avg:412.79ms step:3284/6250 train_loss:2.4758 train_time:1351458ms step_avg:412.79ms step:3285/6250 train_loss:2.4412 train_time:1351873ms step_avg:412.79ms step:3286/6250 train_loss:2.5615 train_time:1352284ms step_avg:412.78ms step:3287/6250 train_loss:2.4953 train_time:1352696ms step_avg:412.78ms step:3288/6250 train_loss:2.3762 train_time:1353105ms step_avg:412.78ms step:3289/6250 train_loss:2.4780 train_time:1353517ms step_avg:412.78ms step:3290/6250 train_loss:2.4123 train_time:1353929ms step_avg:412.78ms step:3291/6250 train_loss:2.5045 train_time:1354342ms step_avg:412.78ms step:3292/6250 train_loss:2.5105 train_time:1354755ms step_avg:412.78ms step:3293/6250 train_loss:2.3945 train_time:1355165ms step_avg:412.78ms step:3294/6250 train_loss:2.4468 train_time:1355576ms step_avg:412.78ms step:3295/6250 train_loss:2.3580 train_time:1355989ms step_avg:412.78ms step:3296/6250 train_loss:2.4267 train_time:1356399ms step_avg:412.78ms step:3297/6250 train_loss:2.4789 train_time:1356809ms step_avg:412.78ms step:3298/6250 train_loss:2.5058 train_time:1357221ms step_avg:412.78ms step:3299/6250 train_loss:2.4386 train_time:1357632ms step_avg:412.78ms step:3300/6250 train_loss:2.4120 train_time:1358043ms step_avg:412.78ms step:3301/6250 train_loss:2.4074 train_time:1358455ms step_avg:412.78ms step:3302/6250 train_loss:2.3639 train_time:1358866ms step_avg:412.78ms step:3303/6250 train_loss:2.4167 train_time:1359281ms step_avg:412.78ms step:3304/6250 train_loss:2.4348 train_time:1359694ms step_avg:412.78ms step:3305/6250 train_loss:2.4763 train_time:1360107ms step_avg:412.78ms step:3306/6250 train_loss:2.3363 train_time:1360521ms step_avg:412.78ms step:3307/6250 train_loss:2.4023 train_time:1360932ms step_avg:412.78ms step:3308/6250 train_loss:2.4300 train_time:1361345ms step_avg:412.78ms step:3309/6250 train_loss:2.5383 train_time:1361756ms step_avg:412.78ms step:3310/6250 train_loss:2.4832 train_time:1362170ms step_avg:412.78ms step:3311/6250 train_loss:2.3911 train_time:1362582ms step_avg:412.78ms step:3312/6250 train_loss:2.4452 train_time:1362993ms step_avg:412.78ms step:3313/6250 train_loss:2.3273 train_time:1363405ms step_avg:412.78ms step:3314/6250 train_loss:2.5381 train_time:1363817ms step_avg:412.78ms step:3315/6250 train_loss:2.4069 train_time:1364228ms step_avg:412.78ms step:3316/6250 train_loss:2.4626 train_time:1364640ms step_avg:412.78ms step:3317/6250 train_loss:2.3905 train_time:1365050ms step_avg:412.78ms step:3318/6250 train_loss:2.4762 train_time:1365463ms step_avg:412.78ms step:3319/6250 train_loss:2.4590 train_time:1365874ms step_avg:412.78ms step:3320/6250 train_loss:2.4907 train_time:1366284ms step_avg:412.77ms step:3321/6250 train_loss:2.4407 train_time:1366698ms step_avg:412.77ms step:3322/6250 train_loss:2.5481 train_time:1367111ms step_avg:412.78ms step:3323/6250 train_loss:2.4693 train_time:1367522ms step_avg:412.77ms step:3324/6250 train_loss:2.4125 train_time:1367932ms step_avg:412.77ms step:3325/6250 train_loss:2.5958 train_time:1368345ms step_avg:412.77ms step:3326/6250 train_loss:2.4306 train_time:1368755ms step_avg:412.77ms step:3327/6250 train_loss:2.4351 train_time:1369168ms step_avg:412.77ms step:3328/6250 train_loss:2.3755 train_time:1369579ms step_avg:412.77ms step:3329/6250 train_loss:2.4399 train_time:1369989ms step_avg:412.77ms step:3330/6250 train_loss:2.4231 train_time:1370400ms step_avg:412.77ms step:3331/6250 train_loss:2.4155 train_time:1370812ms step_avg:412.77ms step:3332/6250 train_loss:2.3425 train_time:1371221ms step_avg:412.77ms step:3333/6250 train_loss:2.4557 train_time:1371631ms step_avg:412.77ms step:3334/6250 train_loss:2.5598 train_time:1372044ms step_avg:412.77ms step:3335/6250 train_loss:2.4338 train_time:1372453ms step_avg:412.77ms step:3336/6250 train_loss:2.4855 train_time:1372868ms step_avg:412.77ms step:3337/6250 train_loss:2.4929 train_time:1373277ms step_avg:412.77ms step:3338/6250 train_loss:2.4588 train_time:1373691ms step_avg:412.77ms step:3339/6250 train_loss:2.4278 train_time:1374101ms step_avg:412.77ms step:3340/6250 train_loss:2.3848 train_time:1374515ms step_avg:412.77ms step:3341/6250 train_loss:2.4483 train_time:1374925ms step_avg:412.77ms step:3342/6250 train_loss:2.4245 train_time:1375337ms step_avg:412.77ms step:3343/6250 train_loss:2.4271 train_time:1375750ms step_avg:412.77ms step:3344/6250 train_loss:2.4391 train_time:1376161ms step_avg:412.77ms step:3345/6250 train_loss:2.4244 train_time:1376574ms step_avg:412.77ms step:3346/6250 train_loss:2.4979 train_time:1376985ms step_avg:412.77ms step:3347/6250 train_loss:2.4553 train_time:1377398ms step_avg:412.77ms step:3348/6250 train_loss:2.5013 train_time:1377809ms step_avg:412.76ms step:3349/6250 train_loss:2.4658 train_time:1378222ms step_avg:412.76ms step:3350/6250 train_loss:2.4974 train_time:1378632ms step_avg:412.76ms step:3351/6250 train_loss:2.4846 train_time:1379044ms step_avg:412.76ms step:3352/6250 train_loss:2.4129 train_time:1379456ms step_avg:412.76ms step:3353/6250 train_loss:2.4383 train_time:1379868ms step_avg:412.76ms step:3354/6250 train_loss:2.5061 train_time:1380280ms step_avg:412.76ms step:3355/6250 train_loss:2.4130 train_time:1380690ms step_avg:412.76ms step:3356/6250 train_loss:2.4919 train_time:1381103ms step_avg:412.76ms step:3357/6250 train_loss:2.4590 train_time:1381515ms step_avg:412.76ms step:3358/6250 train_loss:2.5675 train_time:1381926ms step_avg:412.76ms step:3359/6250 train_loss:2.4092 train_time:1382338ms step_avg:412.76ms step:3360/6250 train_loss:2.4319 train_time:1382747ms step_avg:412.76ms step:3361/6250 train_loss:2.3748 train_time:1383158ms step_avg:412.76ms step:3362/6250 train_loss:2.4332 train_time:1383570ms step_avg:412.76ms step:3363/6250 train_loss:2.5121 train_time:1383980ms step_avg:412.76ms step:3364/6250 train_loss:2.3688 train_time:1384391ms step_avg:412.76ms step:3365/6250 train_loss:2.4013 train_time:1384803ms step_avg:412.76ms step:3366/6250 train_loss:2.3705 train_time:1385211ms step_avg:412.76ms step:3367/6250 train_loss:2.5147 train_time:1385623ms step_avg:412.76ms step:3368/6250 train_loss:2.4041 train_time:1386032ms step_avg:412.76ms step:3369/6250 train_loss:2.3633 train_time:1386442ms step_avg:412.75ms step:3370/6250 train_loss:2.4640 train_time:1386853ms step_avg:412.75ms step:3371/6250 train_loss:2.4537 train_time:1387264ms step_avg:412.75ms step:3372/6250 train_loss:2.3004 train_time:1387675ms step_avg:412.75ms step:3373/6250 train_loss:2.4426 train_time:1388088ms step_avg:412.75ms step:3374/6250 train_loss:2.5346 train_time:1388498ms step_avg:412.75ms step:3375/6250 train_loss:2.4496 train_time:1388911ms step_avg:412.75ms step:3376/6250 train_loss:2.5699 train_time:1389323ms step_avg:412.75ms step:3377/6250 train_loss:2.4131 train_time:1389738ms step_avg:412.75ms step:3378/6250 train_loss:2.4160 train_time:1390150ms step_avg:412.75ms step:3379/6250 train_loss:2.3939 train_time:1390562ms step_avg:412.75ms step:3380/6250 train_loss:2.4451 train_time:1390975ms step_avg:412.75ms step:3381/6250 train_loss:2.3650 train_time:1391384ms step_avg:412.75ms step:3382/6250 train_loss:2.4364 train_time:1391796ms step_avg:412.75ms step:3383/6250 train_loss:2.4138 train_time:1392208ms step_avg:412.75ms step:3384/6250 train_loss:2.4254 train_time:1392618ms step_avg:412.75ms step:3385/6250 train_loss:2.4733 train_time:1393026ms step_avg:412.75ms step:3386/6250 train_loss:2.4133 train_time:1393441ms step_avg:412.75ms step:3387/6250 train_loss:2.4076 train_time:1393852ms step_avg:412.75ms step:3388/6250 train_loss:2.3794 train_time:1394262ms step_avg:412.75ms step:3389/6250 train_loss:2.4642 train_time:1394673ms step_avg:412.75ms step:3390/6250 train_loss:2.3884 train_time:1395084ms step_avg:412.75ms step:3391/6250 train_loss:2.3713 train_time:1395495ms step_avg:412.75ms step:3392/6250 train_loss:2.4025 train_time:1395908ms step_avg:412.75ms step:3393/6250 train_loss:2.3410 train_time:1396320ms step_avg:412.75ms step:3394/6250 train_loss:2.5231 train_time:1396734ms step_avg:412.75ms step:3395/6250 train_loss:2.4426 train_time:1397144ms step_avg:412.75ms step:3396/6250 train_loss:2.5224 train_time:1397557ms step_avg:412.75ms step:3397/6250 train_loss:2.4668 train_time:1397972ms step_avg:412.75ms step:3398/6250 train_loss:2.4536 train_time:1398384ms step_avg:412.75ms step:3399/6250 train_loss:2.4614 train_time:1398793ms step_avg:412.75ms step:3400/6250 train_loss:2.5064 train_time:1399204ms step_avg:412.74ms step:3401/6250 train_loss:2.4856 train_time:1399615ms step_avg:412.74ms step:3402/6250 train_loss:2.4542 train_time:1400029ms step_avg:412.74ms step:3403/6250 train_loss:2.3997 train_time:1400440ms step_avg:412.74ms step:3404/6250 train_loss:2.4486 train_time:1400853ms step_avg:412.74ms step:3405/6250 train_loss:2.4036 train_time:1401262ms step_avg:412.74ms step:3406/6250 train_loss:2.4825 train_time:1401673ms step_avg:412.74ms step:3407/6250 train_loss:2.4748 train_time:1402087ms step_avg:412.74ms step:3408/6250 train_loss:2.4395 train_time:1402497ms step_avg:412.74ms step:3409/6250 train_loss:2.4886 train_time:1402911ms step_avg:412.74ms step:3410/6250 train_loss:2.4668 train_time:1403320ms step_avg:412.74ms step:3411/6250 train_loss:2.3877 train_time:1403732ms step_avg:412.74ms step:3412/6250 train_loss:2.4151 train_time:1404145ms step_avg:412.74ms step:3413/6250 train_loss:2.4614 train_time:1404557ms step_avg:412.74ms step:3414/6250 train_loss:2.3317 train_time:1404967ms step_avg:412.74ms step:3415/6250 train_loss:2.3822 train_time:1405378ms step_avg:412.74ms step:3416/6250 train_loss:2.3867 train_time:1405790ms step_avg:412.74ms step:3417/6250 train_loss:2.4334 train_time:1406199ms step_avg:412.74ms step:3418/6250 train_loss:2.4416 train_time:1406611ms step_avg:412.74ms step:3419/6250 train_loss:2.4903 train_time:1407025ms step_avg:412.74ms step:3420/6250 train_loss:2.3896 train_time:1407435ms step_avg:412.74ms step:3421/6250 train_loss:2.4762 train_time:1407846ms step_avg:412.74ms step:3422/6250 train_loss:2.5087 train_time:1408257ms step_avg:412.74ms step:3423/6250 train_loss:2.4114 train_time:1408667ms step_avg:412.74ms step:3424/6250 train_loss:2.4365 train_time:1409075ms step_avg:412.73ms step:3425/6250 train_loss:2.3809 train_time:1409487ms step_avg:412.73ms step:3426/6250 train_loss:2.3441 train_time:1409898ms step_avg:412.73ms step:3427/6250 train_loss:2.4479 train_time:1410309ms step_avg:412.73ms step:3428/6250 train_loss:2.4712 train_time:1410723ms step_avg:412.73ms step:3429/6250 train_loss:2.3735 train_time:1411134ms step_avg:412.73ms step:3430/6250 train_loss:2.4650 train_time:1411546ms step_avg:412.73ms step:3431/6250 train_loss:2.4202 train_time:1411957ms step_avg:412.73ms step:3432/6250 train_loss:2.3934 train_time:1412369ms step_avg:412.73ms step:3433/6250 train_loss:2.3173 train_time:1412783ms step_avg:412.73ms step:3434/6250 train_loss:2.4147 train_time:1413195ms step_avg:412.73ms step:3435/6250 train_loss:2.4480 train_time:1413607ms step_avg:412.73ms step:3436/6250 train_loss:2.4271 train_time:1414016ms step_avg:412.73ms step:3437/6250 train_loss:2.3818 train_time:1414429ms step_avg:412.73ms step:3438/6250 train_loss:2.4520 train_time:1414840ms step_avg:412.73ms step:3439/6250 train_loss:2.4317 train_time:1415253ms step_avg:412.73ms step:3440/6250 train_loss:2.4537 train_time:1415664ms step_avg:412.73ms step:3441/6250 train_loss:2.4030 train_time:1416075ms step_avg:412.73ms step:3442/6250 train_loss:2.4345 train_time:1416486ms step_avg:412.73ms step:3443/6250 train_loss:2.4656 train_time:1416898ms step_avg:412.73ms step:3444/6250 train_loss:2.4814 train_time:1417309ms step_avg:412.73ms step:3445/6250 train_loss:2.4537 train_time:1417723ms step_avg:412.73ms step:3446/6250 train_loss:2.4486 train_time:1418135ms step_avg:412.73ms step:3447/6250 train_loss:2.4136 train_time:1418548ms step_avg:412.73ms step:3448/6250 train_loss:2.3716 train_time:1418959ms step_avg:412.73ms step:3449/6250 train_loss:2.4685 train_time:1419370ms step_avg:412.73ms step:3450/6250 train_loss:2.4038 train_time:1419782ms step_avg:412.73ms step:3451/6250 train_loss:2.4387 train_time:1420194ms step_avg:412.73ms step:3452/6250 train_loss:2.4321 train_time:1420607ms step_avg:412.73ms step:3453/6250 train_loss:2.4427 train_time:1421020ms step_avg:412.73ms step:3454/6250 train_loss:2.4133 train_time:1421432ms step_avg:412.73ms step:3455/6250 train_loss:2.4735 train_time:1421845ms step_avg:412.73ms step:3456/6250 train_loss:2.4440 train_time:1422253ms step_avg:412.73ms step:3457/6250 train_loss:2.3968 train_time:1422666ms step_avg:412.73ms step:3458/6250 train_loss:2.4239 train_time:1423077ms step_avg:412.73ms step:3459/6250 train_loss:2.4734 train_time:1423488ms step_avg:412.72ms step:3460/6250 train_loss:2.4078 train_time:1423900ms step_avg:412.72ms step:3461/6250 train_loss:2.3930 train_time:1424310ms step_avg:412.72ms step:3462/6250 train_loss:2.3033 train_time:1424723ms step_avg:412.72ms step:3463/6250 train_loss:2.4175 train_time:1425133ms step_avg:412.72ms step:3464/6250 train_loss:2.4565 train_time:1425545ms step_avg:412.72ms step:3465/6250 train_loss:2.4204 train_time:1425957ms step_avg:412.72ms step:3466/6250 train_loss:2.3702 train_time:1426370ms step_avg:412.72ms step:3467/6250 train_loss:2.3839 train_time:1426782ms step_avg:412.72ms step:3468/6250 train_loss:2.4105 train_time:1427194ms step_avg:412.72ms step:3469/6250 train_loss:2.4579 train_time:1427606ms step_avg:412.72ms step:3470/6250 train_loss:2.3994 train_time:1428016ms step_avg:412.72ms step:3471/6250 train_loss:2.4391 train_time:1428430ms step_avg:412.72ms step:3472/6250 train_loss:2.4305 train_time:1428845ms step_avg:412.72ms step:3473/6250 train_loss:2.4720 train_time:1429271ms step_avg:412.73ms step:3474/6250 train_loss:2.4370 train_time:1429702ms step_avg:412.73ms step:3475/6250 train_loss:2.4489 train_time:1430115ms step_avg:412.73ms step:3476/6250 train_loss:2.4900 train_time:1430529ms step_avg:412.73ms step:3477/6250 train_loss:2.4152 train_time:1430941ms step_avg:412.73ms step:3478/6250 train_loss:2.5281 train_time:1431352ms step_avg:412.73ms step:3479/6250 train_loss:2.3890 train_time:1431765ms step_avg:412.73ms step:3480/6250 train_loss:2.4799 train_time:1432177ms step_avg:412.73ms step:3481/6250 train_loss:2.5067 train_time:1432588ms step_avg:412.73ms step:3482/6250 train_loss:2.4565 train_time:1432998ms step_avg:412.73ms step:3483/6250 train_loss:2.4190 train_time:1433410ms step_avg:412.73ms step:3484/6250 train_loss:2.4596 train_time:1433821ms step_avg:412.73ms step:3485/6250 train_loss:2.5231 train_time:1434235ms step_avg:412.73ms step:3486/6250 train_loss:2.4605 train_time:1434663ms step_avg:412.73ms step:3487/6250 train_loss:2.4200 train_time:1435083ms step_avg:412.74ms step:3488/6250 train_loss:2.4951 train_time:1435495ms step_avg:412.74ms step:3489/6250 train_loss:2.4632 train_time:1435919ms step_avg:412.74ms step:3490/6250 train_loss:2.4646 train_time:1436355ms step_avg:412.75ms step:3491/6250 train_loss:2.4590 train_time:1436771ms step_avg:412.75ms step:3492/6250 train_loss:2.4769 train_time:1437193ms step_avg:412.75ms step:3493/6250 train_loss:2.3952 train_time:1437607ms step_avg:412.75ms step:3494/6250 train_loss:2.3461 train_time:1438038ms step_avg:412.76ms step:3495/6250 train_loss:2.3744 train_time:1438480ms step_avg:412.76ms step:3496/6250 train_loss:2.4406 train_time:1438917ms step_avg:412.77ms step:3497/6250 train_loss:2.4431 train_time:1439354ms step_avg:412.78ms step:3498/6250 train_loss:2.3282 train_time:1439792ms step_avg:412.78ms step:3499/6250 train_loss:2.4212 train_time:1440253ms step_avg:412.80ms step:3500/6250 train_loss:2.3204 train_time:1440709ms step_avg:412.81ms step:3501/6250 train_loss:2.4661 train_time:1441139ms step_avg:412.82ms step:3502/6250 train_loss:2.3449 train_time:1441565ms step_avg:412.82ms step:3503/6250 train_loss:2.4166 train_time:1441992ms step_avg:412.82ms step:3504/6250 train_loss:2.3309 train_time:1442416ms step_avg:412.83ms step:3505/6250 train_loss:2.2896 train_time:1442834ms step_avg:412.83ms step:3506/6250 train_loss:2.3693 train_time:1443249ms step_avg:412.83ms step:3507/6250 train_loss:2.3740 train_time:1443681ms step_avg:412.83ms step:3508/6250 train_loss:2.4402 train_time:1444090ms step_avg:412.83ms step:3509/6250 train_loss:2.3678 train_time:1444500ms step_avg:412.83ms step:3510/6250 train_loss:2.3746 train_time:1444912ms step_avg:412.83ms step:3511/6250 train_loss:2.3663 train_time:1445330ms step_avg:412.83ms step:3512/6250 train_loss:2.3807 train_time:1445754ms step_avg:412.84ms step:3513/6250 train_loss:2.4415 train_time:1446195ms step_avg:412.84ms step:3514/6250 train_loss:2.4426 train_time:1446611ms step_avg:412.85ms step:3515/6250 train_loss:2.4095 train_time:1447020ms step_avg:412.84ms step:3516/6250 train_loss:2.3742 train_time:1447435ms step_avg:412.85ms step:3517/6250 train_loss:2.3656 train_time:1447846ms step_avg:412.84ms step:3518/6250 train_loss:2.3442 train_time:1448255ms step_avg:412.84ms step:3519/6250 train_loss:2.4678 train_time:1448670ms step_avg:412.84ms step:3520/6250 train_loss:2.4104 train_time:1449081ms step_avg:412.84ms step:3521/6250 train_loss:2.3872 train_time:1449491ms step_avg:412.84ms step:3522/6250 train_loss:2.4202 train_time:1449902ms step_avg:412.84ms step:3523/6250 train_loss:2.3275 train_time:1450312ms step_avg:412.84ms step:3524/6250 train_loss:2.4448 train_time:1450722ms step_avg:412.84ms step:3525/6250 train_loss:2.4734 train_time:1451135ms step_avg:412.84ms step:3526/6250 train_loss:2.4460 train_time:1451544ms step_avg:412.84ms step:3527/6250 train_loss:2.3796 train_time:1451954ms step_avg:412.84ms step:3528/6250 train_loss:2.4328 train_time:1452364ms step_avg:412.84ms step:3529/6250 train_loss:2.4043 train_time:1452774ms step_avg:412.84ms step:3530/6250 train_loss:2.4263 train_time:1453186ms step_avg:412.84ms step:3531/6250 train_loss:2.3498 train_time:1453596ms step_avg:412.84ms step:3532/6250 train_loss:2.4447 train_time:1454008ms step_avg:412.84ms step:3533/6250 train_loss:2.5500 train_time:1454434ms step_avg:412.84ms step:3534/6250 train_loss:2.4756 train_time:1454866ms step_avg:412.84ms step:3535/6250 train_loss:2.3485 train_time:1455297ms step_avg:412.85ms step:3536/6250 train_loss:2.4454 train_time:1455716ms step_avg:412.85ms step:3537/6250 train_loss:2.4912 train_time:1456127ms step_avg:412.85ms step:3538/6250 train_loss:2.4811 train_time:1456537ms step_avg:412.85ms step:3539/6250 train_loss:2.4279 train_time:1456956ms step_avg:412.85ms step:3540/6250 train_loss:2.4552 train_time:1457367ms step_avg:412.85ms step:3541/6250 train_loss:2.4286 train_time:1457779ms step_avg:412.85ms step:3542/6250 train_loss:2.5414 train_time:1458197ms step_avg:412.85ms step:3543/6250 train_loss:2.4633 train_time:1458628ms step_avg:412.86ms step:3544/6250 train_loss:2.3521 train_time:1459062ms step_avg:412.86ms step:3545/6250 train_loss:2.4259 train_time:1459492ms step_avg:412.87ms step:3546/6250 train_loss:2.3945 train_time:1459910ms step_avg:412.87ms step:3547/6250 train_loss:2.4770 train_time:1460321ms step_avg:412.87ms step:3548/6250 train_loss:2.4033 train_time:1460732ms step_avg:412.87ms step:3549/6250 train_loss:2.4522 train_time:1461141ms step_avg:412.87ms step:3550/6250 train_loss:2.4306 train_time:1461575ms step_avg:412.87ms step:3551/6250 train_loss:2.2923 train_time:1461984ms step_avg:412.87ms step:3552/6250 train_loss:2.4036 train_time:1462421ms step_avg:412.88ms step:3553/6250 train_loss:2.4053 train_time:1462851ms step_avg:412.88ms step:3554/6250 train_loss:2.4960 train_time:1463261ms step_avg:412.88ms step:3555/6250 train_loss:2.3316 train_time:1463673ms step_avg:412.88ms step:3556/6250 train_loss:2.3710 train_time:1464084ms step_avg:412.88ms step:3557/6250 train_loss:2.3938 train_time:1464495ms step_avg:412.88ms step:3558/6250 train_loss:2.4032 train_time:1464905ms step_avg:412.88ms step:3559/6250 train_loss:2.3757 train_time:1465315ms step_avg:412.88ms step:3560/6250 train_loss:2.4276 train_time:1465728ms step_avg:412.88ms step:3561/6250 train_loss:2.4446 train_time:1466137ms step_avg:412.88ms step:3562/6250 train_loss:2.4493 train_time:1466548ms step_avg:412.88ms step:3563/6250 train_loss:2.3446 train_time:1466977ms step_avg:412.88ms step:3564/6250 train_loss:2.3934 train_time:1467408ms step_avg:412.89ms step:3565/6250 train_loss:2.4331 train_time:1467832ms step_avg:412.89ms step:3566/6250 train_loss:2.4322 train_time:1468260ms step_avg:412.90ms step:3567/6250 train_loss:2.4618 train_time:1468687ms step_avg:412.90ms step:3568/6250 train_loss:2.5100 train_time:1469100ms step_avg:412.90ms step:3569/6250 train_loss:2.5007 train_time:1469510ms step_avg:412.90ms step:3570/6250 train_loss:2.3747 train_time:1469920ms step_avg:412.90ms step:3571/6250 train_loss:2.4326 train_time:1470340ms step_avg:412.90ms step:3572/6250 train_loss:2.4996 train_time:1470757ms step_avg:412.90ms step:3573/6250 train_loss:2.4502 train_time:1471166ms step_avg:412.90ms step:3574/6250 train_loss:2.3229 train_time:1471580ms step_avg:412.90ms step:3575/6250 train_loss:2.4420 train_time:1471991ms step_avg:412.90ms step:3576/6250 train_loss:2.4219 train_time:1472405ms step_avg:412.90ms step:3577/6250 train_loss:2.4164 train_time:1472817ms step_avg:412.90ms step:3578/6250 train_loss:2.4448 train_time:1473227ms step_avg:412.90ms step:3579/6250 train_loss:2.4107 train_time:1473637ms step_avg:412.90ms step:3580/6250 train_loss:2.3937 train_time:1474049ms step_avg:412.90ms step:3581/6250 train_loss:2.4508 train_time:1474461ms step_avg:412.90ms step:3582/6250 train_loss:2.4074 train_time:1474873ms step_avg:412.90ms step:3583/6250 train_loss:2.4830 train_time:1475284ms step_avg:412.90ms step:3584/6250 train_loss:2.4213 train_time:1475698ms step_avg:412.90ms step:3585/6250 train_loss:2.4401 train_time:1476108ms step_avg:412.90ms step:3586/6250 train_loss:2.4281 train_time:1476522ms step_avg:412.90ms step:3587/6250 train_loss:2.4748 train_time:1476936ms step_avg:412.90ms step:3588/6250 train_loss:2.4341 train_time:1477383ms step_avg:412.91ms step:3589/6250 train_loss:2.4205 train_time:1477795ms step_avg:412.91ms step:3590/6250 train_loss:2.3902 train_time:1478207ms step_avg:412.91ms step:3591/6250 train_loss:2.5075 train_time:1478618ms step_avg:412.91ms step:3592/6250 train_loss:2.3550 train_time:1479035ms step_avg:412.91ms step:3593/6250 train_loss:2.5036 train_time:1479448ms step_avg:412.91ms step:3594/6250 train_loss:2.4140 train_time:1479859ms step_avg:412.91ms step:3595/6250 train_loss:2.4588 train_time:1480271ms step_avg:412.91ms step:3596/6250 train_loss:2.4019 train_time:1480682ms step_avg:412.91ms step:3597/6250 train_loss:2.5040 train_time:1481095ms step_avg:412.91ms step:3598/6250 train_loss:2.5606 train_time:1481527ms step_avg:412.91ms step:3599/6250 train_loss:2.3625 train_time:1481938ms step_avg:412.91ms step:3600/6250 train_loss:2.4844 train_time:1482348ms step_avg:412.91ms step:3601/6250 train_loss:2.3796 train_time:1482762ms step_avg:412.91ms step:3602/6250 train_loss:2.3812 train_time:1483172ms step_avg:412.91ms step:3603/6250 train_loss:2.4215 train_time:1483593ms step_avg:412.91ms step:3604/6250 train_loss:2.4950 train_time:1484015ms step_avg:412.91ms step:3605/6250 train_loss:2.4495 train_time:1484429ms step_avg:412.92ms step:3606/6250 train_loss:2.5169 train_time:1484841ms step_avg:412.91ms step:3607/6250 train_loss:2.5063 train_time:1485250ms step_avg:412.91ms step:3608/6250 train_loss:2.4103 train_time:1485662ms step_avg:412.91ms step:3609/6250 train_loss:2.3804 train_time:1486074ms step_avg:412.91ms step:3610/6250 train_loss:2.4586 train_time:1486482ms step_avg:412.91ms step:3611/6250 train_loss:2.4063 train_time:1486895ms step_avg:412.91ms step:3612/6250 train_loss:2.4004 train_time:1487306ms step_avg:412.91ms step:3613/6250 train_loss:2.3551 train_time:1487718ms step_avg:412.91ms step:3614/6250 train_loss:2.3720 train_time:1488130ms step_avg:412.91ms step:3615/6250 train_loss:2.3887 train_time:1488540ms step_avg:412.91ms step:3616/6250 train_loss:2.4242 train_time:1488969ms step_avg:412.91ms step:3617/6250 train_loss:2.4306 train_time:1489387ms step_avg:412.92ms step:3618/6250 train_loss:2.3704 train_time:1489819ms step_avg:412.92ms step:3619/6250 train_loss:2.4023 train_time:1490231ms step_avg:412.92ms step:3620/6250 train_loss:2.3743 train_time:1490649ms step_avg:412.92ms step:3621/6250 train_loss:2.3565 train_time:1491060ms step_avg:412.92ms step:3622/6250 train_loss:2.4922 train_time:1491469ms step_avg:412.92ms step:3623/6250 train_loss:2.4175 train_time:1491879ms step_avg:412.92ms step:3624/6250 train_loss:2.4198 train_time:1492292ms step_avg:412.92ms step:3625/6250 train_loss:2.4485 train_time:1492706ms step_avg:412.92ms step:3626/6250 train_loss:2.5359 train_time:1493149ms step_avg:412.93ms step:3627/6250 train_loss:2.4909 train_time:1493564ms step_avg:412.93ms step:3628/6250 train_loss:2.3974 train_time:1493976ms step_avg:412.93ms step:3629/6250 train_loss:2.4250 train_time:1494388ms step_avg:412.93ms step:3630/6250 train_loss:2.5029 train_time:1494799ms step_avg:412.93ms step:3631/6250 train_loss:2.4593 train_time:1495209ms step_avg:412.93ms step:3632/6250 train_loss:2.3477 train_time:1495617ms step_avg:412.93ms step:3633/6250 train_loss:2.4168 train_time:1496028ms step_avg:412.93ms step:3634/6250 train_loss:2.3749 train_time:1496441ms step_avg:412.93ms step:3635/6250 train_loss:2.3251 train_time:1496853ms step_avg:412.93ms step:3636/6250 train_loss:2.4176 train_time:1497265ms step_avg:412.92ms step:3637/6250 train_loss:2.4782 train_time:1497677ms step_avg:412.92ms step:3638/6250 train_loss:2.3726 train_time:1498088ms step_avg:412.92ms step:3639/6250 train_loss:2.5225 train_time:1498499ms step_avg:412.92ms step:3640/6250 train_loss:2.3620 train_time:1498908ms step_avg:412.92ms step:3641/6250 train_loss:2.4964 train_time:1499319ms step_avg:412.92ms step:3642/6250 train_loss:2.3841 train_time:1499728ms step_avg:412.92ms step:3643/6250 train_loss:2.4454 train_time:1500141ms step_avg:412.92ms step:3644/6250 train_loss:2.3965 train_time:1500556ms step_avg:412.92ms step:3645/6250 train_loss:2.4438 train_time:1500967ms step_avg:412.92ms step:3646/6250 train_loss:2.4362 train_time:1501377ms step_avg:412.92ms step:3647/6250 train_loss:2.4208 train_time:1501790ms step_avg:412.92ms step:3648/6250 train_loss:2.4331 train_time:1502201ms step_avg:412.92ms step:3649/6250 train_loss:2.4440 train_time:1502613ms step_avg:412.92ms step:3650/6250 train_loss:2.4834 train_time:1503031ms step_avg:412.92ms step:3651/6250 train_loss:2.4602 train_time:1503441ms step_avg:412.92ms step:3652/6250 train_loss:2.4447 train_time:1503855ms step_avg:412.92ms step:3653/6250 train_loss:2.3673 train_time:1504271ms step_avg:412.92ms step:3654/6250 train_loss:2.5180 train_time:1504681ms step_avg:412.92ms step:3655/6250 train_loss:2.4111 train_time:1505095ms step_avg:412.92ms step:3656/6250 train_loss:2.4766 train_time:1505507ms step_avg:412.92ms step:3657/6250 train_loss:2.4420 train_time:1505917ms step_avg:412.92ms step:3658/6250 train_loss:2.4457 train_time:1506329ms step_avg:412.92ms step:3659/6250 train_loss:2.3933 train_time:1506740ms step_avg:412.92ms step:3660/6250 train_loss:2.4278 train_time:1507150ms step_avg:412.92ms step:3661/6250 train_loss:2.3628 train_time:1507561ms step_avg:412.92ms step:3662/6250 train_loss:2.4840 train_time:1507972ms step_avg:412.92ms step:3663/6250 train_loss:2.4711 train_time:1508385ms step_avg:412.92ms step:3664/6250 train_loss:2.3590 train_time:1508796ms step_avg:412.92ms step:3665/6250 train_loss:2.4134 train_time:1509209ms step_avg:412.92ms step:3666/6250 train_loss:2.3359 train_time:1509620ms step_avg:412.92ms step:3667/6250 train_loss:2.4177 train_time:1510031ms step_avg:412.92ms step:3668/6250 train_loss:2.5743 train_time:1510443ms step_avg:412.91ms step:3669/6250 train_loss:2.4770 train_time:1510854ms step_avg:412.91ms step:3670/6250 train_loss:2.4606 train_time:1511264ms step_avg:412.91ms step:3671/6250 train_loss:2.4372 train_time:1511674ms step_avg:412.91ms step:3672/6250 train_loss:2.4529 train_time:1512085ms step_avg:412.91ms step:3673/6250 train_loss:2.4784 train_time:1512498ms step_avg:412.91ms step:3674/6250 train_loss:2.4000 train_time:1512910ms step_avg:412.91ms step:3675/6250 train_loss:2.4906 train_time:1513321ms step_avg:412.91ms step:3676/6250 train_loss:2.4565 train_time:1513730ms step_avg:412.91ms step:3677/6250 train_loss:2.4167 train_time:1514143ms step_avg:412.91ms step:3678/6250 train_loss:2.4081 train_time:1514555ms step_avg:412.91ms step:3679/6250 train_loss:2.4054 train_time:1514967ms step_avg:412.91ms step:3680/6250 train_loss:2.3656 train_time:1515380ms step_avg:412.91ms step:3681/6250 train_loss:2.5361 train_time:1515797ms step_avg:412.91ms step:3682/6250 train_loss:2.4022 train_time:1516208ms step_avg:412.91ms step:3683/6250 train_loss:2.4347 train_time:1516619ms step_avg:412.91ms step:3684/6250 train_loss:2.4005 train_time:1517031ms step_avg:412.91ms step:3685/6250 train_loss:2.4673 train_time:1517442ms step_avg:412.91ms step:3686/6250 train_loss:2.3606 train_time:1517854ms step_avg:412.91ms step:3687/6250 train_loss:2.3101 train_time:1518266ms step_avg:412.91ms step:3688/6250 train_loss:2.3235 train_time:1518679ms step_avg:412.91ms step:3689/6250 train_loss:2.4903 train_time:1519090ms step_avg:412.91ms step:3690/6250 train_loss:2.4256 train_time:1519503ms step_avg:412.91ms step:3691/6250 train_loss:2.2675 train_time:1519913ms step_avg:412.91ms step:3692/6250 train_loss:2.4385 train_time:1520325ms step_avg:412.91ms step:3693/6250 train_loss:2.3692 train_time:1520738ms step_avg:412.91ms step:3694/6250 train_loss:2.4274 train_time:1521148ms step_avg:412.91ms step:3695/6250 train_loss:2.4380 train_time:1521559ms step_avg:412.91ms step:3696/6250 train_loss:2.3439 train_time:1521971ms step_avg:412.91ms step:3697/6250 train_loss:2.4301 train_time:1522381ms step_avg:412.91ms step:3698/6250 train_loss:2.4142 train_time:1522795ms step_avg:412.91ms step:3699/6250 train_loss:2.4196 train_time:1523207ms step_avg:412.91ms step:3700/6250 train_loss:2.3710 train_time:1523622ms step_avg:412.91ms step:3701/6250 train_loss:2.5038 train_time:1524034ms step_avg:412.91ms step:3702/6250 train_loss:2.4832 train_time:1524444ms step_avg:412.90ms step:3703/6250 train_loss:2.3803 train_time:1524855ms step_avg:412.90ms step:3704/6250 train_loss:2.3349 train_time:1525269ms step_avg:412.90ms step:3705/6250 train_loss:2.3832 train_time:1525686ms step_avg:412.91ms step:3706/6250 train_loss:2.3872 train_time:1526108ms step_avg:412.91ms step:3707/6250 train_loss:2.4150 train_time:1526522ms step_avg:412.91ms step:3708/6250 train_loss:2.4666 train_time:1526933ms step_avg:412.91ms step:3709/6250 train_loss:2.4515 train_time:1527347ms step_avg:412.91ms step:3710/6250 train_loss:2.3538 train_time:1527758ms step_avg:412.91ms step:3711/6250 train_loss:2.4357 train_time:1528175ms step_avg:412.91ms step:3712/6250 train_loss:2.4638 train_time:1528589ms step_avg:412.91ms step:3713/6250 train_loss:2.5207 train_time:1529000ms step_avg:412.91ms step:3714/6250 train_loss:2.3822 train_time:1529410ms step_avg:412.91ms step:3715/6250 train_loss:2.4152 train_time:1529821ms step_avg:412.91ms step:3716/6250 train_loss:2.3901 train_time:1530232ms step_avg:412.91ms step:3717/6250 train_loss:2.3660 train_time:1530645ms step_avg:412.91ms step:3718/6250 train_loss:2.4266 train_time:1531062ms step_avg:412.91ms step:3719/6250 train_loss:2.4641 train_time:1531475ms step_avg:412.91ms step:3720/6250 train_loss:2.3478 train_time:1531888ms step_avg:412.91ms step:3721/6250 train_loss:2.3777 train_time:1532300ms step_avg:412.91ms step:3722/6250 train_loss:2.3193 train_time:1532712ms step_avg:412.91ms step:3723/6250 train_loss:2.4613 train_time:1533124ms step_avg:412.91ms step:3724/6250 train_loss:2.4704 train_time:1533536ms step_avg:412.91ms step:3725/6250 train_loss:2.3938 train_time:1533946ms step_avg:412.91ms step:3726/6250 train_loss:2.3467 train_time:1534359ms step_avg:412.91ms step:3727/6250 train_loss:2.3564 train_time:1534769ms step_avg:412.91ms step:3728/6250 train_loss:2.4442 train_time:1535182ms step_avg:412.91ms step:3729/6250 train_loss:2.3597 train_time:1535594ms step_avg:412.91ms step:3730/6250 train_loss:2.3958 train_time:1536006ms step_avg:412.90ms step:3731/6250 train_loss:2.4217 train_time:1536416ms step_avg:412.90ms step:3732/6250 train_loss:2.4177 train_time:1536829ms step_avg:412.90ms step:3733/6250 train_loss:2.3369 train_time:1537239ms step_avg:412.90ms step:3734/6250 train_loss:2.5120 train_time:1537651ms step_avg:412.90ms step:3735/6250 train_loss:2.4126 train_time:1538061ms step_avg:412.90ms step:3736/6250 train_loss:2.4235 train_time:1538471ms step_avg:412.90ms step:3737/6250 train_loss:2.3600 train_time:1538882ms step_avg:412.90ms step:3738/6250 train_loss:2.3876 train_time:1539296ms step_avg:412.90ms step:3739/6250 train_loss:2.4115 train_time:1539711ms step_avg:412.90ms step:3740/6250 train_loss:2.4583 train_time:1540123ms step_avg:412.90ms step:3741/6250 train_loss:2.4464 train_time:1540536ms step_avg:412.90ms step:3742/6250 train_loss:2.4697 train_time:1540946ms step_avg:412.90ms step:3743/6250 train_loss:2.4247 train_time:1541360ms step_avg:412.90ms step:3744/6250 train_loss:2.4670 train_time:1541775ms step_avg:412.90ms step:3745/6250 train_loss:2.4979 train_time:1542186ms step_avg:412.90ms step:3746/6250 train_loss:2.3709 train_time:1542596ms step_avg:412.90ms step:3747/6250 train_loss:2.3937 train_time:1543011ms step_avg:412.90ms step:3748/6250 train_loss:2.4188 train_time:1543422ms step_avg:412.90ms step:3749/6250 train_loss:2.3906 train_time:1543837ms step_avg:412.90ms step:3750/6250 train_loss:2.4597 train_time:1544248ms step_avg:412.90ms step:3751/6250 train_loss:2.4002 train_time:1544657ms step_avg:412.90ms step:3752/6250 train_loss:2.4310 train_time:1545068ms step_avg:412.90ms step:3753/6250 train_loss:2.4839 train_time:1545479ms step_avg:412.90ms step:3754/6250 train_loss:2.5096 train_time:1545892ms step_avg:412.90ms step:3755/6250 train_loss:2.3998 train_time:1546303ms step_avg:412.90ms step:3756/6250 train_loss:2.3423 train_time:1546715ms step_avg:412.90ms step:3757/6250 train_loss:2.3896 train_time:1547128ms step_avg:412.90ms step:3758/6250 train_loss:2.4311 train_time:1547540ms step_avg:412.90ms step:3759/6250 train_loss:2.3783 train_time:1547953ms step_avg:412.90ms step:3760/6250 train_loss:2.3408 train_time:1548366ms step_avg:412.90ms step:3761/6250 train_loss:2.3469 train_time:1548778ms step_avg:412.90ms step:3762/6250 train_loss:2.4333 train_time:1549189ms step_avg:412.90ms step:3763/6250 train_loss:2.5225 train_time:1549602ms step_avg:412.90ms step:3764/6250 train_loss:2.4069 train_time:1550013ms step_avg:412.90ms step:3765/6250 train_loss:2.4000 train_time:1550424ms step_avg:412.90ms step:3766/6250 train_loss:2.4601 train_time:1550835ms step_avg:412.90ms step:3767/6250 train_loss:2.3728 train_time:1551249ms step_avg:412.90ms step:3768/6250 train_loss:2.3949 train_time:1551663ms step_avg:412.90ms step:3769/6250 train_loss:2.4094 train_time:1552071ms step_avg:412.89ms step:3770/6250 train_loss:2.4510 train_time:1552481ms step_avg:412.89ms step:3771/6250 train_loss:2.4947 train_time:1552894ms step_avg:412.89ms step:3772/6250 train_loss:2.4176 train_time:1553305ms step_avg:412.89ms step:3773/6250 train_loss:2.3642 train_time:1553718ms step_avg:412.89ms step:3774/6250 train_loss:2.3930 train_time:1554129ms step_avg:412.89ms step:3775/6250 train_loss:2.4429 train_time:1554540ms step_avg:412.89ms step:3776/6250 train_loss:2.4338 train_time:1554951ms step_avg:412.89ms step:3777/6250 train_loss:2.4779 train_time:1555361ms step_avg:412.89ms step:3778/6250 train_loss:2.4042 train_time:1555776ms step_avg:412.89ms step:3779/6250 train_loss:2.4043 train_time:1556185ms step_avg:412.89ms step:3780/6250 train_loss:2.4999 train_time:1556597ms step_avg:412.89ms step:3781/6250 train_loss:2.3792 train_time:1557009ms step_avg:412.89ms step:3782/6250 train_loss:2.3511 train_time:1557421ms step_avg:412.89ms step:3783/6250 train_loss:2.4207 train_time:1557831ms step_avg:412.89ms step:3784/6250 train_loss:2.4129 train_time:1558251ms step_avg:412.89ms step:3785/6250 train_loss:2.4249 train_time:1558673ms step_avg:412.89ms step:3786/6250 train_loss:2.4277 train_time:1559090ms step_avg:412.89ms step:3787/6250 train_loss:2.4088 train_time:1559510ms step_avg:412.90ms step:3788/6250 train_loss:2.3619 train_time:1559922ms step_avg:412.90ms step:3789/6250 train_loss:2.4211 train_time:1560334ms step_avg:412.90ms step:3790/6250 train_loss:2.3518 train_time:1560750ms step_avg:412.90ms step:3791/6250 train_loss:2.4482 train_time:1561161ms step_avg:412.90ms step:3792/6250 train_loss:2.4813 train_time:1561573ms step_avg:412.90ms step:3793/6250 train_loss:2.4276 train_time:1561985ms step_avg:412.90ms step:3794/6250 train_loss:2.3749 train_time:1562394ms step_avg:412.89ms step:3795/6250 train_loss:2.4287 train_time:1562805ms step_avg:412.89ms step:3796/6250 train_loss:2.4358 train_time:1563221ms step_avg:412.90ms step:3797/6250 train_loss:2.4062 train_time:1563632ms step_avg:412.89ms step:3798/6250 train_loss:2.3901 train_time:1564043ms step_avg:412.89ms step:3799/6250 train_loss:2.4935 train_time:1564455ms step_avg:412.89ms step:3800/6250 train_loss:2.4179 train_time:1564865ms step_avg:412.89ms step:3801/6250 train_loss:2.3209 train_time:1565274ms step_avg:412.89ms step:3802/6250 train_loss:2.4262 train_time:1565688ms step_avg:412.89ms step:3803/6250 train_loss:2.4725 train_time:1566099ms step_avg:412.89ms step:3804/6250 train_loss:2.4607 train_time:1566512ms step_avg:412.89ms step:3805/6250 train_loss:2.3666 train_time:1566925ms step_avg:412.89ms step:3806/6250 train_loss:2.5139 train_time:1567337ms step_avg:412.89ms step:3807/6250 train_loss:2.3767 train_time:1567747ms step_avg:412.89ms step:3808/6250 train_loss:2.4480 train_time:1568157ms step_avg:412.89ms step:3809/6250 train_loss:2.4973 train_time:1568571ms step_avg:412.89ms step:3810/6250 train_loss:2.4216 train_time:1568982ms step_avg:412.89ms step:3811/6250 train_loss:2.3701 train_time:1569394ms step_avg:412.89ms step:3812/6250 train_loss:2.3587 train_time:1569803ms step_avg:412.89ms step:3813/6250 train_loss:2.4363 train_time:1570217ms step_avg:412.89ms step:3814/6250 train_loss:2.4272 train_time:1570640ms step_avg:412.89ms step:3815/6250 train_loss:2.4510 train_time:1571049ms step_avg:412.89ms step:3816/6250 train_loss:2.4570 train_time:1571460ms step_avg:412.89ms step:3817/6250 train_loss:2.4078 train_time:1571873ms step_avg:412.89ms step:3818/6250 train_loss:2.4982 train_time:1572286ms step_avg:412.89ms step:3819/6250 train_loss:2.4541 train_time:1572702ms step_avg:412.89ms step:3820/6250 train_loss:2.4131 train_time:1573114ms step_avg:412.89ms step:3821/6250 train_loss:2.4038 train_time:1573526ms step_avg:412.89ms step:3822/6250 train_loss:2.4023 train_time:1573937ms step_avg:412.89ms step:3823/6250 train_loss:2.3904 train_time:1574346ms step_avg:412.89ms step:3824/6250 train_loss:2.4814 train_time:1574766ms step_avg:412.89ms step:3825/6250 train_loss:2.3373 train_time:1575182ms step_avg:412.89ms step:3826/6250 train_loss:2.4367 train_time:1575601ms step_avg:412.89ms step:3827/6250 train_loss:2.3605 train_time:1576014ms step_avg:412.89ms step:3828/6250 train_loss:2.3954 train_time:1576437ms step_avg:412.90ms step:3829/6250 train_loss:2.4367 train_time:1576873ms step_avg:412.90ms step:3830/6250 train_loss:2.3395 train_time:1577295ms step_avg:412.90ms step:3831/6250 train_loss:2.3938 train_time:1577718ms step_avg:412.91ms step:3832/6250 train_loss:2.4061 train_time:1578142ms step_avg:412.91ms step:3833/6250 train_loss:2.4019 train_time:1578569ms step_avg:412.91ms step:3834/6250 train_loss:2.4690 train_time:1579006ms step_avg:412.92ms step:3835/6250 train_loss:2.3219 train_time:1579427ms step_avg:412.92ms step:3836/6250 train_loss:2.3612 train_time:1579840ms step_avg:412.92ms step:3837/6250 train_loss:2.4233 train_time:1580251ms step_avg:412.92ms step:3838/6250 train_loss:2.4354 train_time:1580675ms step_avg:412.92ms step:3839/6250 train_loss:2.4245 train_time:1581093ms step_avg:412.93ms step:3840/6250 train_loss:2.3059 train_time:1581517ms step_avg:412.93ms step:3841/6250 train_loss:2.4721 train_time:1581944ms step_avg:412.93ms step:3842/6250 train_loss:2.4373 train_time:1582356ms step_avg:412.93ms step:3843/6250 train_loss:2.3635 train_time:1582780ms step_avg:412.94ms step:3844/6250 train_loss:2.4430 train_time:1583210ms step_avg:412.94ms step:3845/6250 train_loss:2.4222 train_time:1583622ms step_avg:412.94ms step:3846/6250 train_loss:2.4908 train_time:1584042ms step_avg:412.94ms step:3847/6250 train_loss:2.3671 train_time:1584463ms step_avg:412.94ms step:3848/6250 train_loss:2.3843 train_time:1584901ms step_avg:412.95ms step:3849/6250 train_loss:2.4604 train_time:1585336ms step_avg:412.96ms step:3850/6250 train_loss:2.4418 train_time:1585753ms step_avg:412.96ms step:3851/6250 train_loss:2.4716 train_time:1586183ms step_avg:412.96ms step:3852/6250 train_loss:2.4816 train_time:1586622ms step_avg:412.97ms step:3853/6250 train_loss:2.4609 train_time:1587051ms step_avg:412.97ms step:3854/6250 train_loss:2.4374 train_time:1587472ms step_avg:412.97ms step:3855/6250 train_loss:2.3959 train_time:1587893ms step_avg:412.98ms step:3856/6250 train_loss:2.4568 train_time:1588304ms step_avg:412.98ms step:3857/6250 train_loss:2.4939 train_time:1588721ms step_avg:412.98ms step:3858/6250 train_loss:2.5044 train_time:1589136ms step_avg:412.98ms step:3859/6250 train_loss:2.4592 train_time:1589548ms step_avg:412.98ms step:3860/6250 train_loss:2.4812 train_time:1589963ms step_avg:412.98ms step:3861/6250 train_loss:2.3995 train_time:1590374ms step_avg:412.98ms step:3862/6250 train_loss:2.4441 train_time:1590786ms step_avg:412.98ms step:3863/6250 train_loss:2.4103 train_time:1591206ms step_avg:412.98ms step:3864/6250 train_loss:2.3082 train_time:1591648ms step_avg:412.99ms step:3865/6250 train_loss:2.4681 train_time:1592082ms step_avg:412.99ms step:3866/6250 train_loss:2.3371 train_time:1592496ms step_avg:412.99ms step:3867/6250 train_loss:2.4109 train_time:1592908ms step_avg:412.99ms step:3868/6250 train_loss:2.4758 train_time:1593316ms step_avg:412.99ms step:3869/6250 train_loss:2.4250 train_time:1593729ms step_avg:412.99ms step:3870/6250 train_loss:2.3759 train_time:1594139ms step_avg:412.99ms step:3871/6250 train_loss:2.3296 train_time:1594552ms step_avg:412.99ms step:3872/6250 train_loss:2.4458 train_time:1594961ms step_avg:412.99ms step:3873/6250 train_loss:2.4651 train_time:1595375ms step_avg:412.99ms step:3874/6250 train_loss:2.3698 train_time:1595789ms step_avg:412.99ms step:3875/6250 train_loss:2.3989 train_time:1596201ms step_avg:412.99ms step:3876/6250 train_loss:2.4639 train_time:1596612ms step_avg:412.99ms step:3877/6250 train_loss:2.3778 train_time:1597024ms step_avg:412.99ms step:3878/6250 train_loss:2.5172 train_time:1597436ms step_avg:412.99ms step:3879/6250 train_loss:2.3819 train_time:1597850ms step_avg:412.99ms step:3880/6250 train_loss:2.4358 train_time:1598261ms step_avg:412.99ms step:3881/6250 train_loss:2.3920 train_time:1598673ms step_avg:412.99ms step:3882/6250 train_loss:2.4236 train_time:1599086ms step_avg:412.99ms step:3883/6250 train_loss:2.4206 train_time:1599501ms step_avg:412.99ms step:3884/6250 train_loss:2.3595 train_time:1599914ms step_avg:412.99ms step:3885/6250 train_loss:2.4011 train_time:1600323ms step_avg:412.99ms step:3886/6250 train_loss:2.3879 train_time:1600735ms step_avg:412.99ms step:3887/6250 train_loss:2.3785 train_time:1601148ms step_avg:412.99ms step:3888/6250 train_loss:2.4407 train_time:1601558ms step_avg:412.99ms step:3889/6250 train_loss:2.4696 train_time:1601971ms step_avg:412.99ms step:3890/6250 train_loss:2.4467 train_time:1602383ms step_avg:412.99ms step:3891/6250 train_loss:2.3338 train_time:1602796ms step_avg:412.99ms step:3892/6250 train_loss:2.3523 train_time:1603207ms step_avg:412.98ms step:3893/6250 train_loss:2.3664 train_time:1603621ms step_avg:412.99ms step:3894/6250 train_loss:2.4969 train_time:1604034ms step_avg:412.99ms step:3895/6250 train_loss:2.3664 train_time:1604445ms step_avg:412.98ms step:3896/6250 train_loss:2.5285 train_time:1604859ms step_avg:412.98ms step:3897/6250 train_loss:2.3890 train_time:1605271ms step_avg:412.98ms step:3898/6250 train_loss:2.3362 train_time:1605682ms step_avg:412.98ms step:3899/6250 train_loss:2.4429 train_time:1606093ms step_avg:412.98ms step:3900/6250 train_loss:2.4491 train_time:1606506ms step_avg:412.98ms step:3901/6250 train_loss:2.3429 train_time:1606917ms step_avg:412.98ms step:3902/6250 train_loss:2.4682 train_time:1607326ms step_avg:412.98ms step:3903/6250 train_loss:2.3438 train_time:1607738ms step_avg:412.98ms step:3904/6250 train_loss:2.3478 train_time:1608149ms step_avg:412.98ms step:3905/6250 train_loss:2.3506 train_time:1608561ms step_avg:412.98ms step:3906/6250 train_loss:2.4512 train_time:1608972ms step_avg:412.98ms step:3907/6250 train_loss:2.4544 train_time:1609386ms step_avg:412.98ms step:3908/6250 train_loss:2.4507 train_time:1609799ms step_avg:412.98ms step:3909/6250 train_loss:2.3815 train_time:1610212ms step_avg:412.98ms step:3910/6250 train_loss:2.3518 train_time:1610622ms step_avg:412.98ms step:3911/6250 train_loss:2.3530 train_time:1611033ms step_avg:412.98ms step:3912/6250 train_loss:2.4015 train_time:1611445ms step_avg:412.98ms step:3913/6250 train_loss:2.4894 train_time:1611857ms step_avg:412.98ms step:3914/6250 train_loss:2.4080 train_time:1612268ms step_avg:412.98ms step:3915/6250 train_loss:2.4552 train_time:1612681ms step_avg:412.98ms step:3916/6250 train_loss:2.3967 train_time:1613090ms step_avg:412.98ms step:3917/6250 train_loss:2.4681 train_time:1613501ms step_avg:412.98ms step:3918/6250 train_loss:2.3754 train_time:1613913ms step_avg:412.98ms step:3919/6250 train_loss:2.3197 train_time:1614325ms step_avg:412.98ms step:3920/6250 train_loss:2.4379 train_time:1614736ms step_avg:412.98ms step:3921/6250 train_loss:2.4159 train_time:1615148ms step_avg:412.98ms step:3922/6250 train_loss:2.3670 train_time:1615562ms step_avg:412.98ms step:3923/6250 train_loss:2.3913 train_time:1615973ms step_avg:412.98ms step:3924/6250 train_loss:2.3676 train_time:1616386ms step_avg:412.98ms step:3925/6250 train_loss:2.4268 train_time:1616796ms step_avg:412.97ms step:3926/6250 train_loss:2.3424 train_time:1617207ms step_avg:412.97ms step:3927/6250 train_loss:2.4644 train_time:1617618ms step_avg:412.97ms step:3928/6250 train_loss:2.3765 train_time:1618031ms step_avg:412.97ms step:3929/6250 train_loss:2.3675 train_time:1618440ms step_avg:412.97ms step:3930/6250 train_loss:2.5585 train_time:1618851ms step_avg:412.97ms step:3931/6250 train_loss:2.3719 train_time:1619265ms step_avg:412.97ms step:3932/6250 train_loss:2.4630 train_time:1619675ms step_avg:412.97ms step:3933/6250 train_loss:2.4954 train_time:1620086ms step_avg:412.97ms step:3934/6250 train_loss:2.3551 train_time:1620498ms step_avg:412.97ms step:3935/6250 train_loss:2.4796 train_time:1620912ms step_avg:412.97ms step:3936/6250 train_loss:2.4379 train_time:1621322ms step_avg:412.97ms step:3937/6250 train_loss:2.4766 train_time:1621733ms step_avg:412.97ms step:3938/6250 train_loss:2.3846 train_time:1622143ms step_avg:412.97ms step:3939/6250 train_loss:2.4917 train_time:1622556ms step_avg:412.97ms step:3940/6250 train_loss:2.4998 train_time:1622966ms step_avg:412.97ms step:3941/6250 train_loss:2.4479 train_time:1623378ms step_avg:412.97ms step:3942/6250 train_loss:2.4625 train_time:1623788ms step_avg:412.97ms step:3943/6250 train_loss:2.4177 train_time:1624199ms step_avg:412.97ms step:3944/6250 train_loss:2.3966 train_time:1624610ms step_avg:412.97ms step:3945/6250 train_loss:2.4126 train_time:1625022ms step_avg:412.97ms step:3946/6250 train_loss:2.3674 train_time:1625433ms step_avg:412.97ms step:3947/6250 train_loss:2.3770 train_time:1625850ms step_avg:412.97ms step:3948/6250 train_loss:2.4367 train_time:1626262ms step_avg:412.97ms step:3949/6250 train_loss:2.3238 train_time:1626676ms step_avg:412.97ms step:3950/6250 train_loss:2.3665 train_time:1627087ms step_avg:412.97ms step:3951/6250 train_loss:2.4022 train_time:1627499ms step_avg:412.97ms step:3952/6250 train_loss:2.3897 train_time:1627914ms step_avg:412.97ms step:3953/6250 train_loss:2.3846 train_time:1628324ms step_avg:412.97ms step:3954/6250 train_loss:2.4108 train_time:1628740ms step_avg:412.97ms step:3955/6250 train_loss:2.3523 train_time:1629154ms step_avg:412.97ms step:3956/6250 train_loss:2.3797 train_time:1629567ms step_avg:412.97ms step:3957/6250 train_loss:2.3833 train_time:1629981ms step_avg:412.97ms step:3958/6250 train_loss:2.4428 train_time:1630395ms step_avg:412.97ms step:3959/6250 train_loss:2.3169 train_time:1630802ms step_avg:412.97ms step:3960/6250 train_loss:2.4574 train_time:1631210ms step_avg:412.96ms step:3961/6250 train_loss:2.4222 train_time:1631623ms step_avg:412.96ms step:3962/6250 train_loss:2.4251 train_time:1632032ms step_avg:412.96ms step:3963/6250 train_loss:2.4713 train_time:1632442ms step_avg:412.96ms step:3964/6250 train_loss:2.3013 train_time:1632852ms step_avg:412.96ms step:3965/6250 train_loss:2.4102 train_time:1633260ms step_avg:412.96ms step:3966/6250 train_loss:2.4232 train_time:1633671ms step_avg:412.96ms step:3967/6250 train_loss:2.4004 train_time:1634081ms step_avg:412.96ms step:3968/6250 train_loss:2.3358 train_time:1634490ms step_avg:412.96ms step:3969/6250 train_loss:2.3419 train_time:1634900ms step_avg:412.96ms step:3970/6250 train_loss:2.3417 train_time:1635308ms step_avg:412.96ms step:3971/6250 train_loss:2.4850 train_time:1635717ms step_avg:412.96ms step:3972/6250 train_loss:2.3876 train_time:1636128ms step_avg:412.96ms step:3973/6250 train_loss:2.2297 train_time:1636538ms step_avg:412.95ms step:3974/6250 train_loss:2.3943 train_time:1636949ms step_avg:412.95ms step:3975/6250 train_loss:2.5361 train_time:1637360ms step_avg:412.95ms step:3976/6250 train_loss:2.4224 train_time:1637771ms step_avg:412.95ms step:3977/6250 train_loss:2.4373 train_time:1638181ms step_avg:412.95ms step:3978/6250 train_loss:2.3387 train_time:1638592ms step_avg:412.95ms step:3979/6250 train_loss:2.4053 train_time:1639004ms step_avg:412.95ms step:3980/6250 train_loss:2.4882 train_time:1639416ms step_avg:412.95ms step:3981/6250 train_loss:2.4257 train_time:1639826ms step_avg:412.95ms step:3982/6250 train_loss:2.4058 train_time:1640239ms step_avg:412.95ms step:3983/6250 train_loss:2.4465 train_time:1640649ms step_avg:412.95ms step:3984/6250 train_loss:2.4558 train_time:1641057ms step_avg:412.95ms step:3985/6250 train_loss:2.4192 train_time:1641470ms step_avg:412.95ms step:3986/6250 train_loss:2.2858 train_time:1641877ms step_avg:412.95ms step:3987/6250 train_loss:2.3478 train_time:1642287ms step_avg:412.95ms step:3988/6250 train_loss:2.3913 train_time:1642695ms step_avg:412.95ms step:3989/6250 train_loss:2.3510 train_time:1643101ms step_avg:412.94ms step:3990/6250 train_loss:2.3856 train_time:1643513ms step_avg:412.94ms step:3991/6250 train_loss:2.3875 train_time:1643921ms step_avg:412.94ms step:3992/6250 train_loss:2.3973 train_time:1644330ms step_avg:412.94ms step:3993/6250 train_loss:2.4781 train_time:1644742ms step_avg:412.94ms step:3994/6250 train_loss:2.3951 train_time:1645151ms step_avg:412.94ms step:3995/6250 train_loss:2.3047 train_time:1645562ms step_avg:412.94ms step:3996/6250 train_loss:2.3980 train_time:1645974ms step_avg:412.94ms step:3997/6250 train_loss:2.4087 train_time:1646385ms step_avg:412.94ms step:3998/6250 train_loss:2.3437 train_time:1646798ms step_avg:412.94ms step:3999/6250 train_loss:2.4413 train_time:1647207ms step_avg:412.94ms step:4000/6250 train_loss:2.4824 train_time:1647619ms step_avg:412.94ms step:4000/6250 val_loss:2.3741 train_time:1647620ms step_avg:412.94ms step:4001/6250 train_loss:2.3702 train_time:1648044ms step_avg:412.94ms step:4002/6250 train_loss:2.4309 train_time:1648458ms step_avg:412.94ms step:4003/6250 train_loss:2.2905 train_time:1648871ms step_avg:412.94ms step:4004/6250 train_loss:2.3222 train_time:1649281ms step_avg:412.94ms step:4005/6250 train_loss:2.3462 train_time:1649691ms step_avg:412.94ms step:4006/6250 train_loss:2.3443 train_time:1650106ms step_avg:412.94ms step:4007/6250 train_loss:2.3159 train_time:1650519ms step_avg:412.94ms step:4008/6250 train_loss:2.3586 train_time:1650932ms step_avg:412.94ms step:4009/6250 train_loss:2.4775 train_time:1651342ms step_avg:412.94ms step:4010/6250 train_loss:2.3784 train_time:1651754ms step_avg:412.94ms step:4011/6250 train_loss:2.3608 train_time:1652160ms step_avg:412.94ms step:4012/6250 train_loss:2.3409 train_time:1652570ms step_avg:412.94ms step:4013/6250 train_loss:2.3299 train_time:1652981ms step_avg:412.94ms step:4014/6250 train_loss:2.4687 train_time:1653396ms step_avg:412.94ms step:4015/6250 train_loss:2.3482 train_time:1653810ms step_avg:412.94ms step:4016/6250 train_loss:2.3406 train_time:1654220ms step_avg:412.94ms step:4017/6250 train_loss:2.3918 train_time:1654628ms step_avg:412.93ms step:4018/6250 train_loss:2.3599 train_time:1655040ms step_avg:412.93ms step:4019/6250 train_loss:2.2942 train_time:1655454ms step_avg:412.93ms step:4020/6250 train_loss:2.3934 train_time:1655864ms step_avg:412.93ms step:4021/6250 train_loss:2.4146 train_time:1656276ms step_avg:412.93ms step:4022/6250 train_loss:2.3203 train_time:1656690ms step_avg:412.93ms step:4023/6250 train_loss:2.3109 train_time:1657100ms step_avg:412.93ms step:4024/6250 train_loss:2.3398 train_time:1657514ms step_avg:412.93ms step:4025/6250 train_loss:2.3895 train_time:1657924ms step_avg:412.93ms step:4026/6250 train_loss:2.3681 train_time:1658335ms step_avg:412.93ms step:4027/6250 train_loss:2.3930 train_time:1658744ms step_avg:412.93ms step:4028/6250 train_loss:2.3266 train_time:1659156ms step_avg:412.93ms step:4029/6250 train_loss:2.4780 train_time:1659566ms step_avg:412.93ms step:4030/6250 train_loss:2.3087 train_time:1659979ms step_avg:412.93ms step:4031/6250 train_loss:2.3176 train_time:1660390ms step_avg:412.93ms step:4032/6250 train_loss:2.3502 train_time:1660803ms step_avg:412.93ms step:4033/6250 train_loss:2.4215 train_time:1661215ms step_avg:412.93ms step:4034/6250 train_loss:2.3479 train_time:1661627ms step_avg:412.93ms step:4035/6250 train_loss:2.4484 train_time:1662039ms step_avg:412.93ms step:4036/6250 train_loss:2.3704 train_time:1662453ms step_avg:412.93ms step:4037/6250 train_loss:2.3463 train_time:1662869ms step_avg:412.93ms step:4038/6250 train_loss:2.3357 train_time:1663287ms step_avg:412.93ms step:4039/6250 train_loss:2.3379 train_time:1663703ms step_avg:412.93ms step:4040/6250 train_loss:2.3497 train_time:1664112ms step_avg:412.93ms step:4041/6250 train_loss:2.4090 train_time:1664525ms step_avg:412.93ms step:4042/6250 train_loss:2.3720 train_time:1664935ms step_avg:412.93ms step:4043/6250 train_loss:2.4458 train_time:1665346ms step_avg:412.93ms step:4044/6250 train_loss:2.3647 train_time:1665757ms step_avg:412.93ms step:4045/6250 train_loss:2.3472 train_time:1666166ms step_avg:412.93ms step:4046/6250 train_loss:2.3137 train_time:1666578ms step_avg:412.93ms step:4047/6250 train_loss:2.3556 train_time:1666990ms step_avg:412.93ms step:4048/6250 train_loss:2.3920 train_time:1667401ms step_avg:412.93ms step:4049/6250 train_loss:2.3744 train_time:1667814ms step_avg:412.93ms step:4050/6250 train_loss:2.3504 train_time:1668227ms step_avg:412.93ms step:4051/6250 train_loss:2.4728 train_time:1668637ms step_avg:412.93ms step:4052/6250 train_loss:2.4075 train_time:1669051ms step_avg:412.93ms step:4053/6250 train_loss:2.3646 train_time:1669461ms step_avg:412.93ms step:4054/6250 train_loss:2.3896 train_time:1669875ms step_avg:412.93ms step:4055/6250 train_loss:2.2552 train_time:1670284ms step_avg:412.93ms step:4056/6250 train_loss:2.4481 train_time:1670695ms step_avg:412.93ms step:4057/6250 train_loss:2.3485 train_time:1671107ms step_avg:412.92ms step:4058/6250 train_loss:2.4542 train_time:1671517ms step_avg:412.92ms step:4059/6250 train_loss:2.3799 train_time:1671927ms step_avg:412.92ms step:4060/6250 train_loss:2.3546 train_time:1672336ms step_avg:412.92ms step:4061/6250 train_loss:2.3626 train_time:1672747ms step_avg:412.92ms step:4062/6250 train_loss:2.4678 train_time:1673160ms step_avg:412.92ms step:4063/6250 train_loss:2.4338 train_time:1673571ms step_avg:412.92ms step:4064/6250 train_loss:2.3308 train_time:1673982ms step_avg:412.92ms step:4065/6250 train_loss:2.4071 train_time:1674391ms step_avg:412.92ms step:4066/6250 train_loss:2.3918 train_time:1674800ms step_avg:412.92ms step:4067/6250 train_loss:2.4023 train_time:1675213ms step_avg:412.92ms step:4068/6250 train_loss:2.3084 train_time:1675624ms step_avg:412.92ms step:4069/6250 train_loss:2.4672 train_time:1676037ms step_avg:412.92ms step:4070/6250 train_loss:2.3476 train_time:1676446ms step_avg:412.92ms step:4071/6250 train_loss:2.4301 train_time:1676854ms step_avg:412.92ms step:4072/6250 train_loss:2.4296 train_time:1677269ms step_avg:412.92ms step:4073/6250 train_loss:2.2992 train_time:1677679ms step_avg:412.92ms step:4074/6250 train_loss:2.3649 train_time:1678089ms step_avg:412.92ms step:4075/6250 train_loss:2.3784 train_time:1678499ms step_avg:412.91ms step:4076/6250 train_loss:2.3793 train_time:1678912ms step_avg:412.91ms step:4077/6250 train_loss:2.4567 train_time:1679323ms step_avg:412.91ms step:4078/6250 train_loss:2.3499 train_time:1679735ms step_avg:412.91ms step:4079/6250 train_loss:2.3365 train_time:1680146ms step_avg:412.91ms step:4080/6250 train_loss:2.3986 train_time:1680559ms step_avg:412.91ms step:4081/6250 train_loss:2.3948 train_time:1680970ms step_avg:412.91ms step:4082/6250 train_loss:2.4373 train_time:1681384ms step_avg:412.91ms step:4083/6250 train_loss:2.3910 train_time:1681796ms step_avg:412.91ms step:4084/6250 train_loss:2.4136 train_time:1682208ms step_avg:412.91ms step:4085/6250 train_loss:2.3967 train_time:1682618ms step_avg:412.91ms step:4086/6250 train_loss:2.4196 train_time:1683040ms step_avg:412.91ms step:4087/6250 train_loss:2.3491 train_time:1683455ms step_avg:412.92ms step:4088/6250 train_loss:2.4057 train_time:1683868ms step_avg:412.92ms step:4089/6250 train_loss:2.3979 train_time:1684280ms step_avg:412.92ms step:4090/6250 train_loss:2.3893 train_time:1684691ms step_avg:412.91ms step:4091/6250 train_loss:2.4541 train_time:1685102ms step_avg:412.91ms step:4092/6250 train_loss:2.3925 train_time:1685514ms step_avg:412.91ms step:4093/6250 train_loss:2.3989 train_time:1685928ms step_avg:412.91ms step:4094/6250 train_loss:2.2662 train_time:1686337ms step_avg:412.91ms step:4095/6250 train_loss:2.4034 train_time:1686751ms step_avg:412.91ms step:4096/6250 train_loss:2.3631 train_time:1687175ms step_avg:412.92ms step:4097/6250 train_loss:2.3222 train_time:1687587ms step_avg:412.92ms step:4098/6250 train_loss:2.4245 train_time:1687998ms step_avg:412.92ms step:4099/6250 train_loss:2.4121 train_time:1688411ms step_avg:412.92ms step:4100/6250 train_loss:2.4059 train_time:1688820ms step_avg:412.91ms step:4101/6250 train_loss:2.4362 train_time:1689239ms step_avg:412.92ms step:4102/6250 train_loss:2.4922 train_time:1689684ms step_avg:412.92ms step:4103/6250 train_loss:2.4030 train_time:1690114ms step_avg:412.93ms step:4104/6250 train_loss:2.4005 train_time:1690530ms step_avg:412.93ms step:4105/6250 train_loss:2.4518 train_time:1690950ms step_avg:412.93ms step:4106/6250 train_loss:2.4178 train_time:1691358ms step_avg:412.93ms step:4107/6250 train_loss:2.3630 train_time:1691768ms step_avg:412.93ms step:4108/6250 train_loss:2.4187 train_time:1692180ms step_avg:412.93ms step:4109/6250 train_loss:2.4001 train_time:1692591ms step_avg:412.93ms step:4110/6250 train_loss:2.3623 train_time:1693002ms step_avg:412.93ms step:4111/6250 train_loss:2.3816 train_time:1693411ms step_avg:412.93ms step:4112/6250 train_loss:2.3926 train_time:1693825ms step_avg:412.93ms step:4113/6250 train_loss:2.3842 train_time:1694236ms step_avg:412.93ms step:4114/6250 train_loss:2.4429 train_time:1694647ms step_avg:412.93ms step:4115/6250 train_loss:2.3828 train_time:1695056ms step_avg:412.92ms step:4116/6250 train_loss:2.3877 train_time:1695465ms step_avg:412.92ms step:4117/6250 train_loss:2.4526 train_time:1695878ms step_avg:412.92ms step:4118/6250 train_loss:2.2949 train_time:1696291ms step_avg:412.92ms step:4119/6250 train_loss:2.4711 train_time:1696701ms step_avg:412.92ms step:4120/6250 train_loss:2.4197 train_time:1697114ms step_avg:412.92ms step:4121/6250 train_loss:2.4440 train_time:1697525ms step_avg:412.92ms step:4122/6250 train_loss:2.3847 train_time:1697937ms step_avg:412.92ms step:4123/6250 train_loss:2.4310 train_time:1698348ms step_avg:412.92ms step:4124/6250 train_loss:2.4440 train_time:1698762ms step_avg:412.92ms step:4125/6250 train_loss:2.5043 train_time:1699172ms step_avg:412.92ms step:4126/6250 train_loss:2.4108 train_time:1699585ms step_avg:412.92ms step:4127/6250 train_loss:2.4168 train_time:1700009ms step_avg:412.92ms step:4128/6250 train_loss:2.4332 train_time:1700428ms step_avg:412.93ms step:4129/6250 train_loss:2.3588 train_time:1700838ms step_avg:412.93ms step:4130/6250 train_loss:2.5157 train_time:1701253ms step_avg:412.93ms step:4131/6250 train_loss:2.4524 train_time:1701666ms step_avg:412.93ms step:4132/6250 train_loss:2.3622 train_time:1702077ms step_avg:412.93ms step:4133/6250 train_loss:2.4002 train_time:1702489ms step_avg:412.92ms step:4134/6250 train_loss:2.4802 train_time:1702900ms step_avg:412.92ms step:4135/6250 train_loss:2.3258 train_time:1703310ms step_avg:412.92ms step:4136/6250 train_loss:2.3634 train_time:1703722ms step_avg:412.92ms step:4137/6250 train_loss:2.4397 train_time:1704134ms step_avg:412.92ms step:4138/6250 train_loss:2.4505 train_time:1704573ms step_avg:412.93ms step:4139/6250 train_loss:2.4149 train_time:1705018ms step_avg:412.94ms step:4140/6250 train_loss:2.4879 train_time:1705450ms step_avg:412.94ms step:4141/6250 train_loss:2.4038 train_time:1705863ms step_avg:412.94ms step:4142/6250 train_loss:2.3612 train_time:1706276ms step_avg:412.94ms step:4143/6250 train_loss:2.4547 train_time:1706691ms step_avg:412.94ms step:4144/6250 train_loss:2.4087 train_time:1707105ms step_avg:412.94ms step:4145/6250 train_loss:2.3766 train_time:1707518ms step_avg:412.94ms step:4146/6250 train_loss:2.3907 train_time:1707927ms step_avg:412.94ms step:4147/6250 train_loss:2.4011 train_time:1708338ms step_avg:412.94ms step:4148/6250 train_loss:2.3387 train_time:1708750ms step_avg:412.94ms step:4149/6250 train_loss:2.3247 train_time:1709161ms step_avg:412.94ms step:4150/6250 train_loss:2.4088 train_time:1709573ms step_avg:412.94ms step:4151/6250 train_loss:2.3816 train_time:1709981ms step_avg:412.94ms step:4152/6250 train_loss:2.3548 train_time:1710390ms step_avg:412.94ms step:4153/6250 train_loss:2.3724 train_time:1710802ms step_avg:412.94ms step:4154/6250 train_loss:2.3561 train_time:1711212ms step_avg:412.94ms step:4155/6250 train_loss:2.4657 train_time:1711623ms step_avg:412.94ms step:4156/6250 train_loss:2.5034 train_time:1712032ms step_avg:412.94ms step:4157/6250 train_loss:2.3810 train_time:1712445ms step_avg:412.94ms step:4158/6250 train_loss:2.3786 train_time:1712854ms step_avg:412.94ms step:4159/6250 train_loss:2.4166 train_time:1713264ms step_avg:412.93ms step:4160/6250 train_loss:2.4052 train_time:1713676ms step_avg:412.93ms step:4161/6250 train_loss:2.4036 train_time:1714084ms step_avg:412.93ms step:4162/6250 train_loss:2.3503 train_time:1714494ms step_avg:412.93ms step:4163/6250 train_loss:2.3664 train_time:1714907ms step_avg:412.93ms step:4164/6250 train_loss:2.3569 train_time:1715316ms step_avg:412.93ms step:4165/6250 train_loss:2.3781 train_time:1715726ms step_avg:412.93ms step:4166/6250 train_loss:2.3472 train_time:1716136ms step_avg:412.93ms step:4167/6250 train_loss:2.4544 train_time:1716555ms step_avg:412.93ms step:4168/6250 train_loss:2.3941 train_time:1716985ms step_avg:412.94ms step:4169/6250 train_loss:2.3932 train_time:1717404ms step_avg:412.94ms step:4170/6250 train_loss:2.4245 train_time:1717813ms step_avg:412.94ms step:4171/6250 train_loss:2.3472 train_time:1718224ms step_avg:412.94ms step:4172/6250 train_loss:2.3911 train_time:1718637ms step_avg:412.94ms step:4173/6250 train_loss:2.3694 train_time:1719048ms step_avg:412.93ms step:4174/6250 train_loss:2.3446 train_time:1719460ms step_avg:412.93ms step:4175/6250 train_loss:2.3450 train_time:1719870ms step_avg:412.93ms step:4176/6250 train_loss:2.3344 train_time:1720280ms step_avg:412.93ms step:4177/6250 train_loss:2.3814 train_time:1720690ms step_avg:412.93ms step:4178/6250 train_loss:2.3212 train_time:1721101ms step_avg:412.93ms step:4179/6250 train_loss:2.4223 train_time:1721514ms step_avg:412.93ms step:4180/6250 train_loss:2.4302 train_time:1721925ms step_avg:412.93ms step:4181/6250 train_loss:2.4096 train_time:1722338ms step_avg:412.93ms step:4182/6250 train_loss:2.3894 train_time:1722748ms step_avg:412.93ms step:4183/6250 train_loss:2.3682 train_time:1723160ms step_avg:412.93ms step:4184/6250 train_loss:2.3008 train_time:1723570ms step_avg:412.93ms step:4185/6250 train_loss:2.4229 train_time:1723978ms step_avg:412.93ms step:4186/6250 train_loss:2.3027 train_time:1724390ms step_avg:412.93ms step:4187/6250 train_loss:2.3164 train_time:1724801ms step_avg:412.93ms step:4188/6250 train_loss:2.3842 train_time:1725214ms step_avg:412.93ms step:4189/6250 train_loss:2.3789 train_time:1725624ms step_avg:412.93ms step:4190/6250 train_loss:2.3054 train_time:1726036ms step_avg:412.93ms step:4191/6250 train_loss:2.4227 train_time:1726446ms step_avg:412.93ms step:4192/6250 train_loss:2.4755 train_time:1726856ms step_avg:412.93ms step:4193/6250 train_loss:2.2987 train_time:1727269ms step_avg:412.93ms step:4194/6250 train_loss:2.4129 train_time:1727680ms step_avg:412.93ms step:4195/6250 train_loss:2.4121 train_time:1728096ms step_avg:412.93ms step:4196/6250 train_loss:2.4103 train_time:1728534ms step_avg:412.93ms step:4197/6250 train_loss:2.3904 train_time:1728960ms step_avg:412.94ms step:4198/6250 train_loss:2.4146 train_time:1729389ms step_avg:412.94ms step:4199/6250 train_loss:2.3688 train_time:1729801ms step_avg:412.94ms step:4200/6250 train_loss:2.4844 train_time:1730238ms step_avg:412.94ms step:4201/6250 train_loss:2.4603 train_time:1730650ms step_avg:412.94ms step:4202/6250 train_loss:2.3934 train_time:1731061ms step_avg:412.94ms step:4203/6250 train_loss:2.3934 train_time:1731477ms step_avg:412.94ms step:4204/6250 train_loss:2.3941 train_time:1731890ms step_avg:412.94ms step:4205/6250 train_loss:2.4016 train_time:1732299ms step_avg:412.94ms step:4206/6250 train_loss:2.4684 train_time:1732709ms step_avg:412.94ms step:4207/6250 train_loss:2.3444 train_time:1733121ms step_avg:412.94ms step:4208/6250 train_loss:2.5049 train_time:1733535ms step_avg:412.94ms step:4209/6250 train_loss:2.4039 train_time:1733947ms step_avg:412.94ms step:4210/6250 train_loss:2.3984 train_time:1734366ms step_avg:412.94ms step:4211/6250 train_loss:2.4107 train_time:1734781ms step_avg:412.94ms step:4212/6250 train_loss:2.3987 train_time:1735192ms step_avg:412.94ms step:4213/6250 train_loss:2.3986 train_time:1735604ms step_avg:412.94ms step:4214/6250 train_loss:2.3737 train_time:1736016ms step_avg:412.94ms step:4215/6250 train_loss:2.2860 train_time:1736427ms step_avg:412.94ms step:4216/6250 train_loss:2.3227 train_time:1736839ms step_avg:412.94ms step:4217/6250 train_loss:2.3633 train_time:1737249ms step_avg:412.94ms step:4218/6250 train_loss:2.3772 train_time:1737663ms step_avg:412.94ms step:4219/6250 train_loss:2.4395 train_time:1738077ms step_avg:412.94ms step:4220/6250 train_loss:2.4545 train_time:1738486ms step_avg:412.94ms step:4221/6250 train_loss:2.4455 train_time:1738897ms step_avg:412.94ms step:4222/6250 train_loss:2.3601 train_time:1739307ms step_avg:412.94ms step:4223/6250 train_loss:2.3488 train_time:1739715ms step_avg:412.94ms step:4224/6250 train_loss:2.4666 train_time:1740129ms step_avg:412.94ms step:4225/6250 train_loss:2.4166 train_time:1740540ms step_avg:412.94ms step:4226/6250 train_loss:2.3773 train_time:1740953ms step_avg:412.94ms step:4227/6250 train_loss:2.4153 train_time:1741363ms step_avg:412.94ms step:4228/6250 train_loss:2.3556 train_time:1741775ms step_avg:412.94ms step:4229/6250 train_loss:2.4206 train_time:1742185ms step_avg:412.94ms step:4230/6250 train_loss:2.4206 train_time:1742594ms step_avg:412.94ms step:4231/6250 train_loss:2.4082 train_time:1743004ms step_avg:412.94ms step:4232/6250 train_loss:2.3894 train_time:1743416ms step_avg:412.94ms step:4233/6250 train_loss:2.3816 train_time:1743827ms step_avg:412.94ms step:4234/6250 train_loss:2.4413 train_time:1744239ms step_avg:412.94ms step:4235/6250 train_loss:2.4508 train_time:1744649ms step_avg:412.93ms step:4236/6250 train_loss:2.4475 train_time:1745064ms step_avg:412.94ms step:4237/6250 train_loss:2.3680 train_time:1745478ms step_avg:412.94ms step:4238/6250 train_loss:2.4746 train_time:1745892ms step_avg:412.94ms step:4239/6250 train_loss:2.4703 train_time:1746308ms step_avg:412.94ms step:4240/6250 train_loss:2.3928 train_time:1746717ms step_avg:412.94ms step:4241/6250 train_loss:2.3574 train_time:1747130ms step_avg:412.94ms step:4242/6250 train_loss:2.3095 train_time:1747541ms step_avg:412.94ms step:4243/6250 train_loss:2.4686 train_time:1747950ms step_avg:412.93ms step:4244/6250 train_loss:2.4050 train_time:1748364ms step_avg:412.93ms step:4245/6250 train_loss:2.3657 train_time:1748776ms step_avg:412.93ms step:4246/6250 train_loss:2.3519 train_time:1749185ms step_avg:412.93ms step:4247/6250 train_loss:2.4178 train_time:1749598ms step_avg:412.93ms step:4248/6250 train_loss:2.4065 train_time:1750011ms step_avg:412.93ms step:4249/6250 train_loss:2.3361 train_time:1750421ms step_avg:412.93ms step:4250/6250 train_loss:2.4485 train_time:1750836ms step_avg:412.93ms step:4251/6250 train_loss:2.3646 train_time:1751248ms step_avg:412.93ms step:4252/6250 train_loss:2.3984 train_time:1751657ms step_avg:412.93ms step:4253/6250 train_loss:2.3613 train_time:1752068ms step_avg:412.93ms step:4254/6250 train_loss:2.4201 train_time:1752478ms step_avg:412.93ms step:4255/6250 train_loss:2.3641 train_time:1752890ms step_avg:412.93ms step:4256/6250 train_loss:2.3407 train_time:1753300ms step_avg:412.93ms step:4257/6250 train_loss:2.3546 train_time:1753715ms step_avg:412.93ms step:4258/6250 train_loss:2.4227 train_time:1754126ms step_avg:412.93ms step:4259/6250 train_loss:2.3255 train_time:1754537ms step_avg:412.93ms step:4260/6250 train_loss:2.4455 train_time:1754948ms step_avg:412.93ms step:4261/6250 train_loss:2.4241 train_time:1755359ms step_avg:412.93ms step:4262/6250 train_loss:2.3848 train_time:1755771ms step_avg:412.93ms step:4263/6250 train_loss:2.3698 train_time:1756183ms step_avg:412.93ms step:4264/6250 train_loss:2.4076 train_time:1756592ms step_avg:412.93ms step:4265/6250 train_loss:2.3432 train_time:1757003ms step_avg:412.93ms step:4266/6250 train_loss:2.4178 train_time:1757416ms step_avg:412.93ms step:4267/6250 train_loss:2.3225 train_time:1757827ms step_avg:412.93ms step:4268/6250 train_loss:2.4141 train_time:1758237ms step_avg:412.93ms step:4269/6250 train_loss:2.4726 train_time:1758648ms step_avg:412.93ms step:4270/6250 train_loss:2.3110 train_time:1759058ms step_avg:412.92ms step:4271/6250 train_loss:2.3633 train_time:1759470ms step_avg:412.92ms step:4272/6250 train_loss:2.4164 train_time:1759881ms step_avg:412.92ms step:4273/6250 train_loss:2.2731 train_time:1760293ms step_avg:412.92ms step:4274/6250 train_loss:2.4275 train_time:1760705ms step_avg:412.92ms step:4275/6250 train_loss:2.3782 train_time:1761116ms step_avg:412.92ms step:4276/6250 train_loss:2.3561 train_time:1761528ms step_avg:412.92ms step:4277/6250 train_loss:2.3679 train_time:1761940ms step_avg:412.92ms step:4278/6250 train_loss:2.3349 train_time:1762350ms step_avg:412.92ms step:4279/6250 train_loss:2.3907 train_time:1762762ms step_avg:412.92ms step:4280/6250 train_loss:2.4184 train_time:1763174ms step_avg:412.92ms step:4281/6250 train_loss:2.3873 train_time:1763588ms step_avg:412.92ms step:4282/6250 train_loss:2.4254 train_time:1763998ms step_avg:412.92ms step:4283/6250 train_loss:2.3972 train_time:1764412ms step_avg:412.92ms step:4284/6250 train_loss:2.3186 train_time:1764824ms step_avg:412.92ms step:4285/6250 train_loss:2.3499 train_time:1765238ms step_avg:412.92ms step:4286/6250 train_loss:2.4213 train_time:1765650ms step_avg:412.92ms step:4287/6250 train_loss:2.4295 train_time:1766062ms step_avg:412.92ms step:4288/6250 train_loss:2.3420 train_time:1766473ms step_avg:412.92ms step:4289/6250 train_loss:2.3768 train_time:1766885ms step_avg:412.92ms step:4290/6250 train_loss:2.3947 train_time:1767295ms step_avg:412.92ms step:4291/6250 train_loss:2.3482 train_time:1767709ms step_avg:412.92ms step:4292/6250 train_loss:2.3538 train_time:1768119ms step_avg:412.92ms step:4293/6250 train_loss:2.3194 train_time:1768532ms step_avg:412.92ms step:4294/6250 train_loss:2.3299 train_time:1768944ms step_avg:412.92ms step:4295/6250 train_loss:2.3904 train_time:1769355ms step_avg:412.92ms step:4296/6250 train_loss:2.3506 train_time:1769766ms step_avg:412.92ms step:4297/6250 train_loss:2.3928 train_time:1770175ms step_avg:412.92ms step:4298/6250 train_loss:2.3385 train_time:1770587ms step_avg:412.92ms step:4299/6250 train_loss:2.4521 train_time:1771000ms step_avg:412.92ms step:4300/6250 train_loss:2.2889 train_time:1771408ms step_avg:412.92ms step:4301/6250 train_loss:2.4936 train_time:1771822ms step_avg:412.92ms step:4302/6250 train_loss:2.4413 train_time:1772231ms step_avg:412.92ms step:4303/6250 train_loss:2.3029 train_time:1772643ms step_avg:412.91ms step:4304/6250 train_loss:2.3941 train_time:1773056ms step_avg:412.91ms step:4305/6250 train_loss:2.3777 train_time:1773467ms step_avg:412.91ms step:4306/6250 train_loss:2.4132 train_time:1773881ms step_avg:412.91ms step:4307/6250 train_loss:2.3505 train_time:1774293ms step_avg:412.91ms step:4308/6250 train_loss:2.4927 train_time:1774704ms step_avg:412.91ms step:4309/6250 train_loss:2.3796 train_time:1775115ms step_avg:412.91ms step:4310/6250 train_loss:2.3850 train_time:1775529ms step_avg:412.91ms step:4311/6250 train_loss:2.4603 train_time:1775941ms step_avg:412.91ms step:4312/6250 train_loss:2.3218 train_time:1776352ms step_avg:412.91ms step:4313/6250 train_loss:2.2987 train_time:1776764ms step_avg:412.91ms step:4314/6250 train_loss:2.3201 train_time:1777175ms step_avg:412.91ms step:4315/6250 train_loss:2.4021 train_time:1777587ms step_avg:412.91ms step:4316/6250 train_loss:2.3514 train_time:1777999ms step_avg:412.91ms step:4317/6250 train_loss:2.4255 train_time:1778411ms step_avg:412.91ms step:4318/6250 train_loss:2.3528 train_time:1778821ms step_avg:412.91ms step:4319/6250 train_loss:2.3729 train_time:1779233ms step_avg:412.91ms step:4320/6250 train_loss:2.2903 train_time:1779645ms step_avg:412.91ms step:4321/6250 train_loss:2.3609 train_time:1780058ms step_avg:412.91ms step:4322/6250 train_loss:2.4266 train_time:1780471ms step_avg:412.91ms step:4323/6250 train_loss:2.4376 train_time:1780880ms step_avg:412.91ms step:4324/6250 train_loss:2.3341 train_time:1781289ms step_avg:412.91ms step:4325/6250 train_loss:2.3928 train_time:1781704ms step_avg:412.91ms step:4326/6250 train_loss:2.2975 train_time:1782114ms step_avg:412.91ms step:4327/6250 train_loss:2.4122 train_time:1782523ms step_avg:412.91ms step:4328/6250 train_loss:2.3243 train_time:1782935ms step_avg:412.91ms step:4329/6250 train_loss:2.3858 train_time:1783346ms step_avg:412.91ms step:4330/6250 train_loss:2.3876 train_time:1783757ms step_avg:412.91ms step:4331/6250 train_loss:2.2958 train_time:1784169ms step_avg:412.91ms step:4332/6250 train_loss:2.3864 train_time:1784577ms step_avg:412.91ms step:4333/6250 train_loss:2.4292 train_time:1784989ms step_avg:412.91ms step:4334/6250 train_loss:2.3439 train_time:1785398ms step_avg:412.90ms step:4335/6250 train_loss:2.4640 train_time:1785812ms step_avg:412.90ms step:4336/6250 train_loss:2.4161 train_time:1786222ms step_avg:412.90ms step:4337/6250 train_loss:2.3324 train_time:1786638ms step_avg:412.90ms step:4338/6250 train_loss:2.3531 train_time:1787053ms step_avg:412.91ms step:4339/6250 train_loss:2.3740 train_time:1787461ms step_avg:412.90ms step:4340/6250 train_loss:2.3209 train_time:1787873ms step_avg:412.90ms step:4341/6250 train_loss:2.3094 train_time:1788290ms step_avg:412.90ms step:4342/6250 train_loss:2.3377 train_time:1788710ms step_avg:412.91ms step:4343/6250 train_loss:2.4116 train_time:1789129ms step_avg:412.91ms step:4344/6250 train_loss:2.3754 train_time:1789546ms step_avg:412.91ms step:4345/6250 train_loss:2.3344 train_time:1789957ms step_avg:412.91ms step:4346/6250 train_loss:2.3851 train_time:1790367ms step_avg:412.91ms step:4347/6250 train_loss:2.4583 train_time:1790780ms step_avg:412.91ms step:4348/6250 train_loss:2.3177 train_time:1791189ms step_avg:412.91ms step:4349/6250 train_loss:2.3893 train_time:1791600ms step_avg:412.91ms step:4350/6250 train_loss:2.3482 train_time:1792012ms step_avg:412.91ms step:4351/6250 train_loss:2.3788 train_time:1792428ms step_avg:412.91ms step:4352/6250 train_loss:2.3600 train_time:1792838ms step_avg:412.91ms step:4353/6250 train_loss:2.3777 train_time:1793258ms step_avg:412.91ms step:4354/6250 train_loss:2.3769 train_time:1793671ms step_avg:412.91ms step:4355/6250 train_loss:2.4369 train_time:1794086ms step_avg:412.91ms step:4356/6250 train_loss:2.4095 train_time:1794496ms step_avg:412.91ms step:4357/6250 train_loss:2.3506 train_time:1794906ms step_avg:412.91ms step:4358/6250 train_loss:2.4479 train_time:1795317ms step_avg:412.91ms step:4359/6250 train_loss:2.3492 train_time:1795728ms step_avg:412.91ms step:4360/6250 train_loss:2.4025 train_time:1796137ms step_avg:412.91ms step:4361/6250 train_loss:2.4075 train_time:1796548ms step_avg:412.90ms step:4362/6250 train_loss:2.2988 train_time:1796958ms step_avg:412.90ms step:4363/6250 train_loss:2.4183 train_time:1797372ms step_avg:412.90ms step:4364/6250 train_loss:2.2452 train_time:1797781ms step_avg:412.90ms step:4365/6250 train_loss:2.3533 train_time:1798191ms step_avg:412.90ms step:4366/6250 train_loss:2.4166 train_time:1798603ms step_avg:412.90ms step:4367/6250 train_loss:2.4662 train_time:1799015ms step_avg:412.90ms step:4368/6250 train_loss:2.3116 train_time:1799423ms step_avg:412.90ms step:4369/6250 train_loss:2.4165 train_time:1799832ms step_avg:412.90ms step:4370/6250 train_loss:2.3739 train_time:1800243ms step_avg:412.90ms step:4371/6250 train_loss:2.3292 train_time:1800657ms step_avg:412.90ms step:4372/6250 train_loss:2.4688 train_time:1801070ms step_avg:412.90ms step:4373/6250 train_loss:2.3627 train_time:1801483ms step_avg:412.90ms step:4374/6250 train_loss:2.4349 train_time:1801895ms step_avg:412.90ms step:4375/6250 train_loss:2.2997 train_time:1802308ms step_avg:412.90ms step:4376/6250 train_loss:2.4210 train_time:1802722ms step_avg:412.90ms step:4377/6250 train_loss:2.2543 train_time:1803136ms step_avg:412.90ms step:4378/6250 train_loss:2.3312 train_time:1803551ms step_avg:412.90ms step:4379/6250 train_loss:2.4094 train_time:1803960ms step_avg:412.90ms step:4380/6250 train_loss:2.4143 train_time:1804373ms step_avg:412.90ms step:4381/6250 train_loss:2.4282 train_time:1804787ms step_avg:412.90ms step:4382/6250 train_loss:2.3216 train_time:1805198ms step_avg:412.90ms step:4383/6250 train_loss:2.3263 train_time:1805613ms step_avg:412.90ms step:4384/6250 train_loss:2.3127 train_time:1806024ms step_avg:412.90ms step:4385/6250 train_loss:2.3479 train_time:1806438ms step_avg:412.90ms step:4386/6250 train_loss:2.3426 train_time:1806849ms step_avg:412.90ms step:4387/6250 train_loss:2.3632 train_time:1807261ms step_avg:412.90ms step:4388/6250 train_loss:2.3197 train_time:1807675ms step_avg:412.90ms step:4389/6250 train_loss:2.3432 train_time:1808087ms step_avg:412.90ms step:4390/6250 train_loss:2.3354 train_time:1808497ms step_avg:412.90ms step:4391/6250 train_loss:2.2546 train_time:1808910ms step_avg:412.90ms step:4392/6250 train_loss:2.3487 train_time:1809324ms step_avg:412.90ms step:4393/6250 train_loss:2.3558 train_time:1809734ms step_avg:412.90ms step:4394/6250 train_loss:2.3408 train_time:1810147ms step_avg:412.90ms step:4395/6250 train_loss:2.2273 train_time:1810558ms step_avg:412.90ms step:4396/6250 train_loss:2.4285 train_time:1810969ms step_avg:412.90ms step:4397/6250 train_loss:2.3416 train_time:1811377ms step_avg:412.90ms step:4398/6250 train_loss:2.3434 train_time:1811787ms step_avg:412.90ms step:4399/6250 train_loss:2.4198 train_time:1812200ms step_avg:412.90ms step:4400/6250 train_loss:2.3903 train_time:1812611ms step_avg:412.90ms step:4401/6250 train_loss:2.3481 train_time:1813023ms step_avg:412.90ms step:4402/6250 train_loss:2.4540 train_time:1813434ms step_avg:412.89ms step:4403/6250 train_loss:2.3880 train_time:1813847ms step_avg:412.89ms step:4404/6250 train_loss:2.3727 train_time:1814257ms step_avg:412.89ms step:4405/6250 train_loss:2.3533 train_time:1814669ms step_avg:412.89ms step:4406/6250 train_loss:2.3802 train_time:1815081ms step_avg:412.89ms step:4407/6250 train_loss:2.3420 train_time:1815493ms step_avg:412.89ms step:4408/6250 train_loss:2.3870 train_time:1815904ms step_avg:412.89ms step:4409/6250 train_loss:2.4136 train_time:1816314ms step_avg:412.89ms step:4410/6250 train_loss:2.3885 train_time:1816725ms step_avg:412.89ms step:4411/6250 train_loss:2.3065 train_time:1817137ms step_avg:412.89ms step:4412/6250 train_loss:2.3568 train_time:1817548ms step_avg:412.89ms step:4413/6250 train_loss:2.3410 train_time:1817961ms step_avg:412.89ms step:4414/6250 train_loss:2.4805 train_time:1818369ms step_avg:412.89ms step:4415/6250 train_loss:2.4199 train_time:1818779ms step_avg:412.89ms step:4416/6250 train_loss:2.3513 train_time:1819193ms step_avg:412.89ms step:4417/6250 train_loss:2.3422 train_time:1819608ms step_avg:412.89ms step:4418/6250 train_loss:2.3408 train_time:1820021ms step_avg:412.89ms step:4419/6250 train_loss:2.3991 train_time:1820432ms step_avg:412.89ms step:4420/6250 train_loss:2.4526 train_time:1820843ms step_avg:412.89ms step:4421/6250 train_loss:2.3281 train_time:1821256ms step_avg:412.89ms step:4422/6250 train_loss:2.3194 train_time:1821666ms step_avg:412.89ms step:4423/6250 train_loss:2.3817 train_time:1822079ms step_avg:412.89ms step:4424/6250 train_loss:2.2824 train_time:1822489ms step_avg:412.89ms step:4425/6250 train_loss:2.4144 train_time:1822899ms step_avg:412.89ms step:4426/6250 train_loss:2.3604 train_time:1823311ms step_avg:412.89ms step:4427/6250 train_loss:2.3464 train_time:1823723ms step_avg:412.89ms step:4428/6250 train_loss:2.5343 train_time:1824137ms step_avg:412.89ms step:4429/6250 train_loss:2.4461 train_time:1824547ms step_avg:412.89ms step:4430/6250 train_loss:2.4379 train_time:1824960ms step_avg:412.89ms step:4431/6250 train_loss:2.4163 train_time:1825367ms step_avg:412.89ms step:4432/6250 train_loss:2.3677 train_time:1825781ms step_avg:412.89ms step:4433/6250 train_loss:2.3397 train_time:1826195ms step_avg:412.89ms step:4434/6250 train_loss:2.2322 train_time:1826610ms step_avg:412.89ms step:4435/6250 train_loss:2.3527 train_time:1827024ms step_avg:412.89ms step:4436/6250 train_loss:2.3432 train_time:1827435ms step_avg:412.89ms step:4437/6250 train_loss:2.4246 train_time:1827847ms step_avg:412.89ms step:4438/6250 train_loss:2.3307 train_time:1828256ms step_avg:412.89ms step:4439/6250 train_loss:2.3203 train_time:1828668ms step_avg:412.89ms step:4440/6250 train_loss:2.3682 train_time:1829078ms step_avg:412.88ms step:4441/6250 train_loss:2.3058 train_time:1829490ms step_avg:412.88ms step:4442/6250 train_loss:2.3777 train_time:1829902ms step_avg:412.88ms step:4443/6250 train_loss:2.4057 train_time:1830312ms step_avg:412.88ms step:4444/6250 train_loss:2.3207 train_time:1830726ms step_avg:412.88ms step:4445/6250 train_loss:2.3503 train_time:1831135ms step_avg:412.88ms step:4446/6250 train_loss:2.3102 train_time:1831545ms step_avg:412.88ms step:4447/6250 train_loss:2.3060 train_time:1831956ms step_avg:412.88ms step:4448/6250 train_loss:2.4217 train_time:1832366ms step_avg:412.88ms step:4449/6250 train_loss:2.3570 train_time:1832779ms step_avg:412.88ms step:4450/6250 train_loss:2.2877 train_time:1833190ms step_avg:412.88ms step:4451/6250 train_loss:2.4452 train_time:1833603ms step_avg:412.88ms step:4452/6250 train_loss:2.4413 train_time:1834013ms step_avg:412.88ms step:4453/6250 train_loss:2.3624 train_time:1834425ms step_avg:412.88ms step:4454/6250 train_loss:2.3075 train_time:1834837ms step_avg:412.88ms step:4455/6250 train_loss:2.4088 train_time:1835251ms step_avg:412.88ms step:4456/6250 train_loss:2.3539 train_time:1835662ms step_avg:412.88ms step:4457/6250 train_loss:2.3822 train_time:1836076ms step_avg:412.88ms step:4458/6250 train_loss:2.3639 train_time:1836488ms step_avg:412.88ms step:4459/6250 train_loss:2.4580 train_time:1836898ms step_avg:412.88ms step:4460/6250 train_loss:2.5186 train_time:1837312ms step_avg:412.88ms step:4461/6250 train_loss:2.4253 train_time:1837723ms step_avg:412.88ms step:4462/6250 train_loss:2.4280 train_time:1838135ms step_avg:412.88ms step:4463/6250 train_loss:2.3851 train_time:1838545ms step_avg:412.88ms step:4464/6250 train_loss:2.4562 train_time:1838953ms step_avg:412.88ms step:4465/6250 train_loss:2.3813 train_time:1839366ms step_avg:412.88ms step:4466/6250 train_loss:2.4470 train_time:1839777ms step_avg:412.88ms step:4467/6250 train_loss:2.3168 train_time:1840188ms step_avg:412.88ms step:4468/6250 train_loss:2.3402 train_time:1840599ms step_avg:412.88ms step:4469/6250 train_loss:2.2971 train_time:1841013ms step_avg:412.88ms step:4470/6250 train_loss:2.4531 train_time:1841423ms step_avg:412.88ms step:4471/6250 train_loss:2.3952 train_time:1841834ms step_avg:412.87ms step:4472/6250 train_loss:2.3761 train_time:1842244ms step_avg:412.87ms step:4473/6250 train_loss:2.3748 train_time:1842656ms step_avg:412.87ms step:4474/6250 train_loss:2.3590 train_time:1843069ms step_avg:412.87ms step:4475/6250 train_loss:2.3400 train_time:1843480ms step_avg:412.87ms step:4476/6250 train_loss:2.4464 train_time:1843893ms step_avg:412.87ms step:4477/6250 train_loss:2.3503 train_time:1844304ms step_avg:412.87ms step:4478/6250 train_loss:2.3403 train_time:1844716ms step_avg:412.87ms step:4479/6250 train_loss:2.3632 train_time:1845129ms step_avg:412.87ms step:4480/6250 train_loss:2.4410 train_time:1845542ms step_avg:412.87ms step:4481/6250 train_loss:2.3435 train_time:1845953ms step_avg:412.87ms step:4482/6250 train_loss:2.3556 train_time:1846364ms step_avg:412.87ms step:4483/6250 train_loss:2.3665 train_time:1846775ms step_avg:412.87ms step:4484/6250 train_loss:2.3804 train_time:1847187ms step_avg:412.87ms step:4485/6250 train_loss:2.3692 train_time:1847599ms step_avg:412.87ms step:4486/6250 train_loss:2.3789 train_time:1848012ms step_avg:412.87ms step:4487/6250 train_loss:2.4193 train_time:1848423ms step_avg:412.87ms step:4488/6250 train_loss:2.3178 train_time:1848835ms step_avg:412.87ms step:4489/6250 train_loss:2.4884 train_time:1849246ms step_avg:412.87ms step:4490/6250 train_loss:2.5040 train_time:1849660ms step_avg:412.87ms step:4491/6250 train_loss:2.3756 train_time:1850070ms step_avg:412.87ms step:4492/6250 train_loss:2.3786 train_time:1850478ms step_avg:412.87ms step:4493/6250 train_loss:2.3619 train_time:1850891ms step_avg:412.87ms step:4494/6250 train_loss:2.3329 train_time:1851301ms step_avg:412.87ms step:4495/6250 train_loss:2.3718 train_time:1851715ms step_avg:412.87ms step:4496/6250 train_loss:2.3862 train_time:1852125ms step_avg:412.87ms step:4497/6250 train_loss:2.3597 train_time:1852538ms step_avg:412.87ms step:4498/6250 train_loss:2.4018 train_time:1852950ms step_avg:412.87ms step:4499/6250 train_loss:2.3956 train_time:1853365ms step_avg:412.87ms step:4500/6250 train_loss:2.4478 train_time:1853777ms step_avg:412.87ms step:4501/6250 train_loss:2.4372 train_time:1854185ms step_avg:412.87ms step:4502/6250 train_loss:2.4287 train_time:1854595ms step_avg:412.87ms step:4503/6250 train_loss:2.3277 train_time:1855007ms step_avg:412.87ms step:4504/6250 train_loss:2.3396 train_time:1855419ms step_avg:412.87ms step:4505/6250 train_loss:2.3948 train_time:1855833ms step_avg:412.87ms step:4506/6250 train_loss:2.3539 train_time:1856244ms step_avg:412.87ms step:4507/6250 train_loss:2.3178 train_time:1856657ms step_avg:412.87ms step:4508/6250 train_loss:2.3043 train_time:1857068ms step_avg:412.87ms step:4509/6250 train_loss:2.3629 train_time:1857480ms step_avg:412.87ms step:4510/6250 train_loss:2.3576 train_time:1857892ms step_avg:412.86ms step:4511/6250 train_loss:2.3858 train_time:1858305ms step_avg:412.87ms step:4512/6250 train_loss:2.4072 train_time:1858716ms step_avg:412.86ms step:4513/6250 train_loss:2.3471 train_time:1859128ms step_avg:412.86ms step:4514/6250 train_loss:2.3064 train_time:1859539ms step_avg:412.86ms step:4515/6250 train_loss:2.3977 train_time:1859949ms step_avg:412.86ms step:4516/6250 train_loss:2.3687 train_time:1860359ms step_avg:412.86ms step:4517/6250 train_loss:2.3796 train_time:1860771ms step_avg:412.86ms step:4518/6250 train_loss:2.3522 train_time:1861185ms step_avg:412.86ms step:4519/6250 train_loss:2.3920 train_time:1861595ms step_avg:412.86ms step:4520/6250 train_loss:2.3807 train_time:1862009ms step_avg:412.86ms step:4521/6250 train_loss:2.4668 train_time:1862417ms step_avg:412.86ms step:4522/6250 train_loss:2.3882 train_time:1862830ms step_avg:412.86ms step:4523/6250 train_loss:2.3429 train_time:1863243ms step_avg:412.86ms step:4524/6250 train_loss:2.3778 train_time:1863654ms step_avg:412.86ms step:4525/6250 train_loss:2.2883 train_time:1864064ms step_avg:412.86ms step:4526/6250 train_loss:2.3504 train_time:1864475ms step_avg:412.86ms step:4527/6250 train_loss:2.3424 train_time:1864889ms step_avg:412.86ms step:4528/6250 train_loss:2.2096 train_time:1865300ms step_avg:412.86ms step:4529/6250 train_loss:2.3275 train_time:1865712ms step_avg:412.86ms step:4530/6250 train_loss:2.4211 train_time:1866123ms step_avg:412.86ms step:4531/6250 train_loss:2.3961 train_time:1866535ms step_avg:412.86ms step:4532/6250 train_loss:2.3368 train_time:1866946ms step_avg:412.86ms step:4533/6250 train_loss:2.2883 train_time:1867360ms step_avg:412.86ms step:4534/6250 train_loss:2.2980 train_time:1867771ms step_avg:412.86ms step:4535/6250 train_loss:2.2936 train_time:1868183ms step_avg:412.86ms step:4536/6250 train_loss:2.2358 train_time:1868593ms step_avg:412.86ms step:4537/6250 train_loss:2.4122 train_time:1869005ms step_avg:412.86ms step:4538/6250 train_loss:2.3777 train_time:1869416ms step_avg:412.86ms step:4539/6250 train_loss:2.3988 train_time:1869829ms step_avg:412.86ms step:4540/6250 train_loss:2.4108 train_time:1870239ms step_avg:412.86ms step:4541/6250 train_loss:2.3261 train_time:1870649ms step_avg:412.86ms step:4542/6250 train_loss:2.3577 train_time:1871062ms step_avg:412.86ms step:4543/6250 train_loss:2.3821 train_time:1871475ms step_avg:412.86ms step:4544/6250 train_loss:2.3791 train_time:1871887ms step_avg:412.86ms step:4545/6250 train_loss:2.3293 train_time:1872298ms step_avg:412.86ms step:4546/6250 train_loss:2.2939 train_time:1872713ms step_avg:412.86ms step:4547/6250 train_loss:2.3934 train_time:1873125ms step_avg:412.86ms step:4548/6250 train_loss:2.3959 train_time:1873546ms step_avg:412.86ms step:4549/6250 train_loss:2.4127 train_time:1873962ms step_avg:412.86ms step:4550/6250 train_loss:2.3087 train_time:1874373ms step_avg:412.86ms step:4551/6250 train_loss:2.2651 train_time:1874785ms step_avg:412.86ms step:4552/6250 train_loss:2.3492 train_time:1875202ms step_avg:412.86ms step:4553/6250 train_loss:2.4079 train_time:1875616ms step_avg:412.86ms step:4554/6250 train_loss:2.2573 train_time:1876030ms step_avg:412.86ms step:4555/6250 train_loss:2.3088 train_time:1876440ms step_avg:412.86ms step:4556/6250 train_loss:2.3624 train_time:1876852ms step_avg:412.86ms step:4557/6250 train_loss:2.3598 train_time:1877262ms step_avg:412.86ms step:4558/6250 train_loss:2.3627 train_time:1877675ms step_avg:412.86ms step:4559/6250 train_loss:2.4088 train_time:1878086ms step_avg:412.86ms step:4560/6250 train_loss:2.2847 train_time:1878500ms step_avg:412.86ms step:4561/6250 train_loss:2.4305 train_time:1878913ms step_avg:412.86ms step:4562/6250 train_loss:2.3501 train_time:1879326ms step_avg:412.86ms step:4563/6250 train_loss:2.3976 train_time:1879738ms step_avg:412.86ms step:4564/6250 train_loss:2.3701 train_time:1880151ms step_avg:412.86ms step:4565/6250 train_loss:2.4078 train_time:1880563ms step_avg:412.86ms step:4566/6250 train_loss:2.3486 train_time:1880977ms step_avg:412.86ms step:4567/6250 train_loss:2.4646 train_time:1881388ms step_avg:412.86ms step:4568/6250 train_loss:2.4153 train_time:1881800ms step_avg:412.86ms step:4569/6250 train_loss:2.3768 train_time:1882210ms step_avg:412.86ms step:4570/6250 train_loss:2.4207 train_time:1882624ms step_avg:412.86ms step:4571/6250 train_loss:2.3944 train_time:1883036ms step_avg:412.86ms step:4572/6250 train_loss:2.3781 train_time:1883448ms step_avg:412.86ms step:4573/6250 train_loss:2.3535 train_time:1883859ms step_avg:412.86ms step:4574/6250 train_loss:2.2274 train_time:1884270ms step_avg:412.85ms step:4575/6250 train_loss:2.4219 train_time:1884681ms step_avg:412.85ms step:4576/6250 train_loss:2.2955 train_time:1885094ms step_avg:412.85ms step:4577/6250 train_loss:2.4252 train_time:1885504ms step_avg:412.85ms step:4578/6250 train_loss:2.3216 train_time:1885964ms step_avg:412.86ms step:4579/6250 train_loss:2.3691 train_time:1886376ms step_avg:412.86ms step:4580/6250 train_loss:2.3209 train_time:1886789ms step_avg:412.86ms step:4581/6250 train_loss:2.3452 train_time:1887201ms step_avg:412.86ms step:4582/6250 train_loss:2.3774 train_time:1887614ms step_avg:412.86ms step:4583/6250 train_loss:2.3485 train_time:1888026ms step_avg:412.86ms step:4584/6250 train_loss:2.3314 train_time:1888437ms step_avg:412.86ms step:4585/6250 train_loss:2.3511 train_time:1888847ms step_avg:412.86ms step:4586/6250 train_loss:2.4204 train_time:1889259ms step_avg:412.86ms step:4587/6250 train_loss:2.3187 train_time:1889669ms step_avg:412.86ms step:4588/6250 train_loss:2.3262 train_time:1890083ms step_avg:412.86ms step:4589/6250 train_loss:2.3444 train_time:1890493ms step_avg:412.86ms step:4590/6250 train_loss:2.3094 train_time:1890902ms step_avg:412.86ms step:4591/6250 train_loss:2.3262 train_time:1891313ms step_avg:412.86ms step:4592/6250 train_loss:2.3675 train_time:1891723ms step_avg:412.86ms step:4593/6250 train_loss:2.4415 train_time:1892139ms step_avg:412.86ms step:4594/6250 train_loss:2.3504 train_time:1892549ms step_avg:412.86ms step:4595/6250 train_loss:2.4007 train_time:1892961ms step_avg:412.86ms step:4596/6250 train_loss:2.2610 train_time:1893371ms step_avg:412.86ms step:4597/6250 train_loss:2.3578 train_time:1893785ms step_avg:412.86ms step:4598/6250 train_loss:2.3352 train_time:1894195ms step_avg:412.86ms step:4599/6250 train_loss:2.3883 train_time:1894609ms step_avg:412.86ms step:4600/6250 train_loss:2.2642 train_time:1895018ms step_avg:412.86ms step:4601/6250 train_loss:2.2593 train_time:1895427ms step_avg:412.86ms step:4602/6250 train_loss:2.3306 train_time:1895839ms step_avg:412.86ms step:4603/6250 train_loss:2.4009 train_time:1896250ms step_avg:412.86ms step:4604/6250 train_loss:2.3917 train_time:1896662ms step_avg:412.86ms step:4605/6250 train_loss:2.3353 train_time:1897078ms step_avg:412.86ms step:4606/6250 train_loss:2.3388 train_time:1897488ms step_avg:412.86ms step:4607/6250 train_loss:2.3732 train_time:1897900ms step_avg:412.86ms step:4608/6250 train_loss:2.3580 train_time:1898311ms step_avg:412.86ms step:4609/6250 train_loss:2.3622 train_time:1898725ms step_avg:412.86ms step:4610/6250 train_loss:2.3034 train_time:1899136ms step_avg:412.86ms step:4611/6250 train_loss:2.3519 train_time:1899546ms step_avg:412.86ms step:4612/6250 train_loss:2.2772 train_time:1899957ms step_avg:412.85ms step:4613/6250 train_loss:2.3605 train_time:1900367ms step_avg:412.85ms step:4614/6250 train_loss:2.4591 train_time:1900778ms step_avg:412.85ms step:4615/6250 train_loss:2.3288 train_time:1901192ms step_avg:412.85ms step:4616/6250 train_loss:2.4030 train_time:1901603ms step_avg:412.85ms step:4617/6250 train_loss:2.3557 train_time:1902013ms step_avg:412.85ms step:4618/6250 train_loss:2.2930 train_time:1902427ms step_avg:412.85ms step:4619/6250 train_loss:2.3675 train_time:1902841ms step_avg:412.85ms step:4620/6250 train_loss:2.2759 train_time:1903252ms step_avg:412.85ms step:4621/6250 train_loss:2.3950 train_time:1903666ms step_avg:412.85ms step:4622/6250 train_loss:2.4004 train_time:1904077ms step_avg:412.85ms step:4623/6250 train_loss:2.3104 train_time:1904490ms step_avg:412.85ms step:4624/6250 train_loss:2.3179 train_time:1904900ms step_avg:412.85ms step:4625/6250 train_loss:2.3490 train_time:1905312ms step_avg:412.85ms step:4626/6250 train_loss:2.3560 train_time:1905724ms step_avg:412.85ms step:4627/6250 train_loss:2.3964 train_time:1906137ms step_avg:412.85ms step:4628/6250 train_loss:2.4039 train_time:1906547ms step_avg:412.85ms step:4629/6250 train_loss:2.3613 train_time:1906957ms step_avg:412.85ms step:4630/6250 train_loss:2.2890 train_time:1907369ms step_avg:412.85ms step:4631/6250 train_loss:2.3721 train_time:1907780ms step_avg:412.85ms step:4632/6250 train_loss:2.3670 train_time:1908193ms step_avg:412.85ms step:4633/6250 train_loss:2.3288 train_time:1908602ms step_avg:412.85ms step:4634/6250 train_loss:2.3733 train_time:1909014ms step_avg:412.85ms step:4635/6250 train_loss:2.4851 train_time:1909425ms step_avg:412.85ms step:4636/6250 train_loss:2.3457 train_time:1909836ms step_avg:412.85ms step:4637/6250 train_loss:2.3507 train_time:1910249ms step_avg:412.85ms step:4638/6250 train_loss:2.3296 train_time:1910659ms step_avg:412.85ms step:4639/6250 train_loss:2.3077 train_time:1911073ms step_avg:412.85ms step:4640/6250 train_loss:2.3323 train_time:1911483ms step_avg:412.85ms step:4641/6250 train_loss:2.4362 train_time:1911894ms step_avg:412.85ms step:4642/6250 train_loss:2.2931 train_time:1912305ms step_avg:412.85ms step:4643/6250 train_loss:2.2472 train_time:1912715ms step_avg:412.85ms step:4644/6250 train_loss:2.3971 train_time:1913127ms step_avg:412.85ms step:4645/6250 train_loss:2.3169 train_time:1913538ms step_avg:412.85ms step:4646/6250 train_loss:2.3661 train_time:1913950ms step_avg:412.85ms step:4647/6250 train_loss:2.3229 train_time:1914361ms step_avg:412.84ms step:4648/6250 train_loss:2.3632 train_time:1914774ms step_avg:412.84ms step:4649/6250 train_loss:2.4500 train_time:1915185ms step_avg:412.84ms step:4650/6250 train_loss:2.3160 train_time:1915593ms step_avg:412.84ms step:4651/6250 train_loss:2.3967 train_time:1916008ms step_avg:412.84ms step:4652/6250 train_loss:2.3534 train_time:1916418ms step_avg:412.84ms step:4653/6250 train_loss:2.2974 train_time:1916829ms step_avg:412.84ms step:4654/6250 train_loss:2.2877 train_time:1917237ms step_avg:412.84ms step:4655/6250 train_loss:2.2826 train_time:1917646ms step_avg:412.84ms step:4656/6250 train_loss:2.4565 train_time:1918060ms step_avg:412.84ms step:4657/6250 train_loss:2.3638 train_time:1918469ms step_avg:412.84ms step:4658/6250 train_loss:2.4099 train_time:1918879ms step_avg:412.84ms step:4659/6250 train_loss:2.4150 train_time:1919290ms step_avg:412.84ms step:4660/6250 train_loss:2.3905 train_time:1919701ms step_avg:412.84ms step:4661/6250 train_loss:2.3790 train_time:1920114ms step_avg:412.84ms step:4662/6250 train_loss:2.3237 train_time:1920524ms step_avg:412.84ms step:4663/6250 train_loss:2.3211 train_time:1920938ms step_avg:412.84ms step:4664/6250 train_loss:2.4767 train_time:1921348ms step_avg:412.84ms step:4665/6250 train_loss:2.3449 train_time:1921760ms step_avg:412.84ms step:4666/6250 train_loss:2.3414 train_time:1922170ms step_avg:412.84ms step:4667/6250 train_loss:2.3403 train_time:1922579ms step_avg:412.84ms step:4668/6250 train_loss:2.4240 train_time:1922991ms step_avg:412.84ms step:4669/6250 train_loss:2.3704 train_time:1923402ms step_avg:412.84ms step:4670/6250 train_loss:2.3803 train_time:1923815ms step_avg:412.84ms step:4671/6250 train_loss:2.3836 train_time:1924227ms step_avg:412.84ms step:4672/6250 train_loss:2.3005 train_time:1924639ms step_avg:412.84ms step:4673/6250 train_loss:2.3118 train_time:1925049ms step_avg:412.83ms step:4674/6250 train_loss:2.2851 train_time:1925460ms step_avg:412.83ms step:4675/6250 train_loss:2.2955 train_time:1925873ms step_avg:412.83ms step:4676/6250 train_loss:2.3536 train_time:1926283ms step_avg:412.83ms step:4677/6250 train_loss:2.3448 train_time:1926694ms step_avg:412.83ms step:4678/6250 train_loss:2.3881 train_time:1927107ms step_avg:412.83ms step:4679/6250 train_loss:2.3564 train_time:1927516ms step_avg:412.83ms step:4680/6250 train_loss:2.2662 train_time:1927927ms step_avg:412.83ms step:4681/6250 train_loss:2.3716 train_time:1928337ms step_avg:412.83ms step:4682/6250 train_loss:2.3745 train_time:1928749ms step_avg:412.83ms step:4683/6250 train_loss:2.3949 train_time:1929160ms step_avg:412.83ms step:4684/6250 train_loss:2.4030 train_time:1929574ms step_avg:412.83ms step:4685/6250 train_loss:2.2815 train_time:1929988ms step_avg:412.83ms step:4686/6250 train_loss:2.3812 train_time:1930398ms step_avg:412.83ms step:4687/6250 train_loss:2.3595 train_time:1930812ms step_avg:412.83ms step:4688/6250 train_loss:2.3279 train_time:1931222ms step_avg:412.83ms step:4689/6250 train_loss:2.3746 train_time:1931633ms step_avg:412.83ms step:4690/6250 train_loss:2.4456 train_time:1932046ms step_avg:412.83ms step:4691/6250 train_loss:2.3438 train_time:1932457ms step_avg:412.83ms step:4692/6250 train_loss:2.3217 train_time:1932870ms step_avg:412.83ms step:4693/6250 train_loss:2.3245 train_time:1933280ms step_avg:412.83ms step:4694/6250 train_loss:2.2956 train_time:1933693ms step_avg:412.83ms step:4695/6250 train_loss:2.4128 train_time:1934105ms step_avg:412.83ms step:4696/6250 train_loss:2.3922 train_time:1934518ms step_avg:412.83ms step:4697/6250 train_loss:2.3316 train_time:1934927ms step_avg:412.83ms step:4698/6250 train_loss:2.3627 train_time:1935338ms step_avg:412.83ms step:4699/6250 train_loss:2.3133 train_time:1935749ms step_avg:412.83ms step:4700/6250 train_loss:2.3171 train_time:1936160ms step_avg:412.83ms step:4701/6250 train_loss:2.3974 train_time:1936569ms step_avg:412.83ms step:4702/6250 train_loss:2.3554 train_time:1936981ms step_avg:412.83ms step:4703/6250 train_loss:2.4081 train_time:1937392ms step_avg:412.83ms step:4704/6250 train_loss:2.4341 train_time:1937802ms step_avg:412.83ms step:4705/6250 train_loss:2.2729 train_time:1938212ms step_avg:412.82ms step:4706/6250 train_loss:2.3657 train_time:1938626ms step_avg:412.83ms step:4707/6250 train_loss:2.3921 train_time:1939037ms step_avg:412.82ms step:4708/6250 train_loss:2.2227 train_time:1939451ms step_avg:412.82ms step:4709/6250 train_loss:2.3556 train_time:1939863ms step_avg:412.82ms step:4710/6250 train_loss:2.4167 train_time:1940274ms step_avg:412.82ms step:4711/6250 train_loss:2.3988 train_time:1940684ms step_avg:412.82ms step:4712/6250 train_loss:2.3105 train_time:1941097ms step_avg:412.82ms step:4713/6250 train_loss:2.4106 train_time:1941506ms step_avg:412.82ms step:4714/6250 train_loss:2.3668 train_time:1941917ms step_avg:412.82ms step:4715/6250 train_loss:2.3776 train_time:1942327ms step_avg:412.82ms step:4716/6250 train_loss:2.3523 train_time:1942742ms step_avg:412.82ms step:4717/6250 train_loss:2.3207 train_time:1943156ms step_avg:412.82ms step:4718/6250 train_loss:2.4025 train_time:1943566ms step_avg:412.82ms step:4719/6250 train_loss:2.4771 train_time:1943978ms step_avg:412.82ms step:4720/6250 train_loss:2.4542 train_time:1944387ms step_avg:412.82ms step:4721/6250 train_loss:2.4300 train_time:1944800ms step_avg:412.82ms step:4722/6250 train_loss:2.2889 train_time:1945210ms step_avg:412.82ms step:4723/6250 train_loss:2.2912 train_time:1945622ms step_avg:412.82ms step:4724/6250 train_loss:2.3607 train_time:1946038ms step_avg:412.82ms step:4725/6250 train_loss:2.2644 train_time:1946450ms step_avg:412.82ms step:4726/6250 train_loss:2.3682 train_time:1946862ms step_avg:412.82ms step:4727/6250 train_loss:2.3668 train_time:1947270ms step_avg:412.82ms step:4728/6250 train_loss:2.3533 train_time:1947681ms step_avg:412.82ms step:4729/6250 train_loss:2.2480 train_time:1948092ms step_avg:412.82ms step:4730/6250 train_loss:2.2340 train_time:1948504ms step_avg:412.82ms step:4731/6250 train_loss:2.2702 train_time:1948917ms step_avg:412.82ms step:4732/6250 train_loss:2.3610 train_time:1949326ms step_avg:412.82ms step:4733/6250 train_loss:2.4162 train_time:1949742ms step_avg:412.82ms step:4734/6250 train_loss:2.3317 train_time:1950167ms step_avg:412.82ms step:4735/6250 train_loss:2.4470 train_time:1950598ms step_avg:412.82ms step:4736/6250 train_loss:2.2931 train_time:1951014ms step_avg:412.83ms step:4737/6250 train_loss:2.4147 train_time:1951431ms step_avg:412.83ms step:4738/6250 train_loss:2.3596 train_time:1951839ms step_avg:412.83ms step:4739/6250 train_loss:2.3598 train_time:1952252ms step_avg:412.83ms step:4740/6250 train_loss:2.3601 train_time:1952682ms step_avg:412.83ms step:4741/6250 train_loss:2.3929 train_time:1953116ms step_avg:412.83ms step:4742/6250 train_loss:2.3702 train_time:1953561ms step_avg:412.84ms step:4743/6250 train_loss:2.2729 train_time:1954000ms step_avg:412.85ms step:4744/6250 train_loss:2.3288 train_time:1954432ms step_avg:412.85ms step:4745/6250 train_loss:2.3725 train_time:1954867ms step_avg:412.85ms step:4746/6250 train_loss:2.3263 train_time:1955311ms step_avg:412.86ms step:4747/6250 train_loss:2.4052 train_time:1955749ms step_avg:412.87ms step:4748/6250 train_loss:2.4318 train_time:1956174ms step_avg:412.87ms step:4749/6250 train_loss:2.3956 train_time:1956586ms step_avg:412.87ms step:4750/6250 train_loss:2.4155 train_time:1956998ms step_avg:412.87ms step:4751/6250 train_loss:2.4113 train_time:1957409ms step_avg:412.87ms step:4752/6250 train_loss:2.3175 train_time:1957822ms step_avg:412.87ms step:4753/6250 train_loss:2.3746 train_time:1958236ms step_avg:412.87ms step:4754/6250 train_loss:2.4278 train_time:1958646ms step_avg:412.87ms step:4755/6250 train_loss:2.4009 train_time:1959055ms step_avg:412.87ms step:4756/6250 train_loss:2.4086 train_time:1959471ms step_avg:412.87ms step:4757/6250 train_loss:2.2927 train_time:1959890ms step_avg:412.87ms step:4758/6250 train_loss:2.4298 train_time:1960305ms step_avg:412.87ms step:4759/6250 train_loss:2.4273 train_time:1960717ms step_avg:412.87ms step:4760/6250 train_loss:2.4189 train_time:1961133ms step_avg:412.87ms step:4761/6250 train_loss:2.2993 train_time:1961555ms step_avg:412.87ms step:4762/6250 train_loss:2.2692 train_time:1961974ms step_avg:412.87ms step:4763/6250 train_loss:2.2330 train_time:1962395ms step_avg:412.87ms step:4764/6250 train_loss:2.3243 train_time:1962817ms step_avg:412.88ms step:4765/6250 train_loss:2.3297 train_time:1963237ms step_avg:412.88ms step:4766/6250 train_loss:2.2944 train_time:1963656ms step_avg:412.88ms step:4767/6250 train_loss:2.3564 train_time:1964073ms step_avg:412.88ms step:4768/6250 train_loss:2.4265 train_time:1964489ms step_avg:412.88ms step:4769/6250 train_loss:2.2933 train_time:1964905ms step_avg:412.88ms step:4770/6250 train_loss:2.3824 train_time:1965325ms step_avg:412.88ms step:4771/6250 train_loss:2.3287 train_time:1965743ms step_avg:412.88ms step:4772/6250 train_loss:2.3785 train_time:1966162ms step_avg:412.89ms step:4773/6250 train_loss:2.2792 train_time:1966582ms step_avg:412.89ms step:4774/6250 train_loss:2.3218 train_time:1967004ms step_avg:412.89ms step:4775/6250 train_loss:2.3031 train_time:1967424ms step_avg:412.89ms step:4776/6250 train_loss:2.3752 train_time:1967841ms step_avg:412.89ms step:4777/6250 train_loss:2.3794 train_time:1968262ms step_avg:412.89ms step:4778/6250 train_loss:2.2784 train_time:1968685ms step_avg:412.90ms step:4779/6250 train_loss:2.3694 train_time:1969106ms step_avg:412.90ms step:4780/6250 train_loss:2.3164 train_time:1969525ms step_avg:412.90ms step:4781/6250 train_loss:2.3731 train_time:1969945ms step_avg:412.90ms step:4782/6250 train_loss:2.3585 train_time:1970356ms step_avg:412.90ms step:4783/6250 train_loss:2.3028 train_time:1970782ms step_avg:412.90ms step:4784/6250 train_loss:2.3353 train_time:1971207ms step_avg:412.90ms step:4785/6250 train_loss:2.3353 train_time:1971613ms step_avg:412.90ms step:4786/6250 train_loss:2.4037 train_time:1972029ms step_avg:412.90ms step:4787/6250 train_loss:2.3420 train_time:1972444ms step_avg:412.90ms step:4788/6250 train_loss:2.3119 train_time:1972858ms step_avg:412.90ms step:4789/6250 train_loss:2.3330 train_time:1973277ms step_avg:412.91ms step:4790/6250 train_loss:2.4870 train_time:1973694ms step_avg:412.91ms step:4791/6250 train_loss:2.4654 train_time:1974112ms step_avg:412.91ms step:4792/6250 train_loss:2.3313 train_time:1974528ms step_avg:412.91ms step:4793/6250 train_loss:2.4425 train_time:1974944ms step_avg:412.91ms step:4794/6250 train_loss:2.4371 train_time:1975360ms step_avg:412.91ms step:4795/6250 train_loss:2.4292 train_time:1975779ms step_avg:412.91ms step:4796/6250 train_loss:2.4051 train_time:1976196ms step_avg:412.91ms step:4797/6250 train_loss:2.3350 train_time:1976614ms step_avg:412.91ms step:4798/6250 train_loss:2.3972 train_time:1977021ms step_avg:412.91ms step:4799/6250 train_loss:2.3358 train_time:1977438ms step_avg:412.91ms step:4800/6250 train_loss:2.4312 train_time:1977853ms step_avg:412.91ms step:4801/6250 train_loss:2.2958 train_time:1978268ms step_avg:412.91ms step:4802/6250 train_loss:2.3187 train_time:1978684ms step_avg:412.91ms step:4803/6250 train_loss:2.3434 train_time:1979097ms step_avg:412.91ms step:4804/6250 train_loss:2.2694 train_time:1979514ms step_avg:412.91ms step:4805/6250 train_loss:2.3393 train_time:1979931ms step_avg:412.92ms step:4806/6250 train_loss:2.3408 train_time:1980345ms step_avg:412.92ms step:4807/6250 train_loss:2.4098 train_time:1980764ms step_avg:412.92ms step:4808/6250 train_loss:2.3549 train_time:1981172ms step_avg:412.92ms step:4809/6250 train_loss:2.2845 train_time:1981574ms step_avg:412.91ms step:4810/6250 train_loss:2.3949 train_time:1981974ms step_avg:412.91ms step:4811/6250 train_loss:2.3068 train_time:1982372ms step_avg:412.91ms step:4812/6250 train_loss:2.2807 train_time:1982773ms step_avg:412.91ms step:4813/6250 train_loss:2.3536 train_time:1983175ms step_avg:412.90ms step:4814/6250 train_loss:2.3556 train_time:1983574ms step_avg:412.90ms step:4815/6250 train_loss:2.3290 train_time:1983977ms step_avg:412.90ms step:4816/6250 train_loss:2.3539 train_time:1984378ms step_avg:412.90ms step:4817/6250 train_loss:2.4919 train_time:1984781ms step_avg:412.89ms step:4818/6250 train_loss:2.4005 train_time:1985181ms step_avg:412.89ms step:4819/6250 train_loss:2.4391 train_time:1985582ms step_avg:412.89ms step:4820/6250 train_loss:2.3479 train_time:1985983ms step_avg:412.89ms step:4821/6250 train_loss:2.3687 train_time:1986383ms step_avg:412.88ms step:4822/6250 train_loss:2.3742 train_time:1986783ms step_avg:412.88ms step:4823/6250 train_loss:2.3526 train_time:1987185ms step_avg:412.88ms step:4824/6250 train_loss:2.3679 train_time:1987586ms step_avg:412.88ms step:4825/6250 train_loss:2.3830 train_time:1987989ms step_avg:412.87ms step:4826/6250 train_loss:2.3422 train_time:1988388ms step_avg:412.87ms step:4827/6250 train_loss:2.3506 train_time:1988790ms step_avg:412.87ms step:4828/6250 train_loss:2.4038 train_time:1989191ms step_avg:412.87ms step:4829/6250 train_loss:2.3745 train_time:1989588ms step_avg:412.86ms step:4830/6250 train_loss:2.3469 train_time:1989988ms step_avg:412.86ms step:4831/6250 train_loss:2.3870 train_time:1990389ms step_avg:412.86ms step:4832/6250 train_loss:2.2589 train_time:1990790ms step_avg:412.86ms step:4833/6250 train_loss:2.3341 train_time:1991190ms step_avg:412.85ms step:4834/6250 train_loss:2.3800 train_time:1991593ms step_avg:412.85ms step:4835/6250 train_loss:2.3694 train_time:1991993ms step_avg:412.85ms step:4836/6250 train_loss:2.3611 train_time:1992394ms step_avg:412.85ms step:4837/6250 train_loss:2.3965 train_time:1992796ms step_avg:412.84ms step:4838/6250 train_loss:2.3341 train_time:1993198ms step_avg:412.84ms step:4839/6250 train_loss:2.4795 train_time:1993598ms step_avg:412.84ms step:4840/6250 train_loss:2.3684 train_time:1993998ms step_avg:412.84ms step:4841/6250 train_loss:2.3942 train_time:1994399ms step_avg:412.83ms step:4842/6250 train_loss:2.3837 train_time:1994802ms step_avg:412.83ms step:4843/6250 train_loss:2.3291 train_time:1995203ms step_avg:412.83ms step:4844/6250 train_loss:2.3414 train_time:1995603ms step_avg:412.83ms step:4845/6250 train_loss:2.4043 train_time:1996007ms step_avg:412.82ms step:4846/6250 train_loss:2.3257 train_time:1996409ms step_avg:412.82ms step:4847/6250 train_loss:2.4514 train_time:1996812ms step_avg:412.82ms step:4848/6250 train_loss:2.3749 train_time:1997211ms step_avg:412.82ms step:4849/6250 train_loss:2.2657 train_time:1997613ms step_avg:412.82ms step:4850/6250 train_loss:2.2859 train_time:1998015ms step_avg:412.81ms step:4851/6250 train_loss:2.4224 train_time:1998417ms step_avg:412.81ms step:4852/6250 train_loss:2.3718 train_time:1998820ms step_avg:412.81ms step:4853/6250 train_loss:2.2777 train_time:1999219ms step_avg:412.81ms step:4854/6250 train_loss:2.5063 train_time:1999626ms step_avg:412.80ms step:4855/6250 train_loss:2.3420 train_time:2000023ms step_avg:412.80ms step:4856/6250 train_loss:2.2923 train_time:2000425ms step_avg:412.80ms step:4857/6250 train_loss:2.3121 train_time:2000830ms step_avg:412.80ms step:4858/6250 train_loss:2.3471 train_time:2001232ms step_avg:412.80ms step:4859/6250 train_loss:2.3369 train_time:2001632ms step_avg:412.79ms step:4860/6250 train_loss:2.3908 train_time:2002035ms step_avg:412.79ms step:4861/6250 train_loss:2.3748 train_time:2002436ms step_avg:412.79ms step:4862/6250 train_loss:2.2845 train_time:2002836ms step_avg:412.79ms step:4863/6250 train_loss:2.3805 train_time:2003238ms step_avg:412.78ms step:4864/6250 train_loss:2.3940 train_time:2003637ms step_avg:412.78ms step:4865/6250 train_loss:2.4102 train_time:2004041ms step_avg:412.78ms step:4866/6250 train_loss:2.4240 train_time:2004443ms step_avg:412.78ms step:4867/6250 train_loss:2.3669 train_time:2004845ms step_avg:412.77ms step:4868/6250 train_loss:2.4222 train_time:2005242ms step_avg:412.77ms step:4869/6250 train_loss:2.3833 train_time:2005643ms step_avg:412.77ms step:4870/6250 train_loss:2.3704 train_time:2006046ms step_avg:412.77ms step:4871/6250 train_loss:2.3578 train_time:2006450ms step_avg:412.76ms step:4872/6250 train_loss:2.3140 train_time:2006850ms step_avg:412.76ms step:4873/6250 train_loss:2.3883 train_time:2007251ms step_avg:412.76ms step:4874/6250 train_loss:2.4429 train_time:2007656ms step_avg:412.76ms step:4875/6250 train_loss:2.3677 train_time:2008061ms step_avg:412.76ms step:4876/6250 train_loss:2.4205 train_time:2008463ms step_avg:412.75ms step:4877/6250 train_loss:2.2968 train_time:2008864ms step_avg:412.75ms step:4878/6250 train_loss:2.3722 train_time:2009263ms step_avg:412.75ms step:4879/6250 train_loss:2.3141 train_time:2009664ms step_avg:412.75ms step:4880/6250 train_loss:2.3692 train_time:2010064ms step_avg:412.74ms step:4881/6250 train_loss:2.2993 train_time:2010465ms step_avg:412.74ms step:4882/6250 train_loss:2.4033 train_time:2010865ms step_avg:412.74ms step:4883/6250 train_loss:2.4413 train_time:2011266ms step_avg:412.74ms step:4884/6250 train_loss:2.4009 train_time:2011668ms step_avg:412.73ms step:4885/6250 train_loss:2.3131 train_time:2012069ms step_avg:412.73ms step:4886/6250 train_loss:2.3561 train_time:2012471ms step_avg:412.73ms step:4887/6250 train_loss:2.3550 train_time:2012873ms step_avg:412.73ms step:4888/6250 train_loss:2.3766 train_time:2013276ms step_avg:412.73ms step:4889/6250 train_loss:2.3290 train_time:2013681ms step_avg:412.72ms step:4890/6250 train_loss:2.3731 train_time:2014081ms step_avg:412.72ms step:4891/6250 train_loss:2.3155 train_time:2014479ms step_avg:412.72ms step:4892/6250 train_loss:2.3501 train_time:2014880ms step_avg:412.72ms step:4893/6250 train_loss:2.4003 train_time:2015281ms step_avg:412.71ms step:4894/6250 train_loss:2.3763 train_time:2015683ms step_avg:412.71ms step:4895/6250 train_loss:2.3039 train_time:2016081ms step_avg:412.71ms step:4896/6250 train_loss:2.3447 train_time:2016488ms step_avg:412.71ms step:4897/6250 train_loss:2.3267 train_time:2016907ms step_avg:412.71ms step:4898/6250 train_loss:2.3372 train_time:2017322ms step_avg:412.71ms step:4899/6250 train_loss:2.2989 train_time:2017726ms step_avg:412.71ms step:4900/6250 train_loss:2.3071 train_time:2018125ms step_avg:412.70ms step:4901/6250 train_loss:2.3691 train_time:2018528ms step_avg:412.70ms step:4902/6250 train_loss:2.3143 train_time:2018929ms step_avg:412.70ms step:4903/6250 train_loss:2.2894 train_time:2019327ms step_avg:412.70ms step:4904/6250 train_loss:2.2756 train_time:2019730ms step_avg:412.70ms step:4905/6250 train_loss:2.2649 train_time:2020130ms step_avg:412.69ms step:4906/6250 train_loss:2.3768 train_time:2020527ms step_avg:412.69ms step:4907/6250 train_loss:2.3370 train_time:2020928ms step_avg:412.69ms step:4908/6250 train_loss:2.4074 train_time:2021329ms step_avg:412.68ms step:4909/6250 train_loss:2.3320 train_time:2021732ms step_avg:412.68ms step:4910/6250 train_loss:2.4143 train_time:2022133ms step_avg:412.68ms step:4911/6250 train_loss:2.3395 train_time:2022533ms step_avg:412.68ms step:4912/6250 train_loss:2.3646 train_time:2022932ms step_avg:412.67ms step:4913/6250 train_loss:2.3938 train_time:2023333ms step_avg:412.67ms step:4914/6250 train_loss:2.3513 train_time:2023737ms step_avg:412.67ms step:4915/6250 train_loss:2.3191 train_time:2024138ms step_avg:412.67ms step:4916/6250 train_loss:2.2917 train_time:2024535ms step_avg:412.67ms step:4917/6250 train_loss:2.3248 train_time:2024937ms step_avg:412.66ms step:4918/6250 train_loss:2.3750 train_time:2025339ms step_avg:412.66ms step:4919/6250 train_loss:2.3872 train_time:2025740ms step_avg:412.66ms step:4920/6250 train_loss:2.3674 train_time:2026142ms step_avg:412.66ms step:4921/6250 train_loss:2.3059 train_time:2026539ms step_avg:412.65ms step:4922/6250 train_loss:2.4187 train_time:2026940ms step_avg:412.65ms step:4923/6250 train_loss:2.3014 train_time:2027340ms step_avg:412.65ms step:4924/6250 train_loss:2.3303 train_time:2027741ms step_avg:412.65ms step:4925/6250 train_loss:2.2617 train_time:2028142ms step_avg:412.64ms step:4926/6250 train_loss:2.3206 train_time:2028547ms step_avg:412.64ms step:4927/6250 train_loss:2.3357 train_time:2028951ms step_avg:412.64ms step:4928/6250 train_loss:2.4393 train_time:2029352ms step_avg:412.64ms step:4929/6250 train_loss:2.3075 train_time:2029756ms step_avg:412.64ms step:4930/6250 train_loss:2.3657 train_time:2030159ms step_avg:412.63ms step:4931/6250 train_loss:2.3677 train_time:2030561ms step_avg:412.63ms step:4932/6250 train_loss:2.3084 train_time:2030959ms step_avg:412.63ms step:4933/6250 train_loss:2.3592 train_time:2031360ms step_avg:412.63ms step:4934/6250 train_loss:2.3711 train_time:2031761ms step_avg:412.62ms step:4935/6250 train_loss:2.3066 train_time:2032163ms step_avg:412.62ms step:4936/6250 train_loss:2.3569 train_time:2032561ms step_avg:412.62ms step:4937/6250 train_loss:2.3376 train_time:2032963ms step_avg:412.62ms step:4938/6250 train_loss:2.3485 train_time:2033363ms step_avg:412.61ms step:4939/6250 train_loss:2.3650 train_time:2033766ms step_avg:412.61ms step:4940/6250 train_loss:2.4367 train_time:2034168ms step_avg:412.61ms step:4941/6250 train_loss:2.4791 train_time:2034568ms step_avg:412.61ms step:4942/6250 train_loss:2.3529 train_time:2034968ms step_avg:412.61ms step:4943/6250 train_loss:2.2968 train_time:2035370ms step_avg:412.60ms step:4944/6250 train_loss:2.3097 train_time:2035774ms step_avg:412.60ms step:4945/6250 train_loss:2.3112 train_time:2036177ms step_avg:412.60ms step:4946/6250 train_loss:2.3122 train_time:2036578ms step_avg:412.60ms step:4947/6250 train_loss:2.4191 train_time:2036981ms step_avg:412.59ms step:4948/6250 train_loss:2.3637 train_time:2037383ms step_avg:412.59ms step:4949/6250 train_loss:2.3124 train_time:2037786ms step_avg:412.59ms step:4950/6250 train_loss:2.3016 train_time:2038187ms step_avg:412.59ms step:4951/6250 train_loss:2.2905 train_time:2038585ms step_avg:412.59ms step:4952/6250 train_loss:2.3751 train_time:2038984ms step_avg:412.58ms step:4953/6250 train_loss:2.3181 train_time:2039385ms step_avg:412.58ms step:4954/6250 train_loss:2.5027 train_time:2039787ms step_avg:412.58ms step:4955/6250 train_loss:2.3767 train_time:2040188ms step_avg:412.58ms step:4956/6250 train_loss:2.4376 train_time:2040590ms step_avg:412.57ms step:4957/6250 train_loss:2.3456 train_time:2040989ms step_avg:412.57ms step:4958/6250 train_loss:2.2797 train_time:2041389ms step_avg:412.57ms step:4959/6250 train_loss:2.2906 train_time:2041791ms step_avg:412.57ms step:4960/6250 train_loss:2.3626 train_time:2042192ms step_avg:412.56ms step:4961/6250 train_loss:2.4949 train_time:2042593ms step_avg:412.56ms step:4962/6250 train_loss:2.3665 train_time:2042996ms step_avg:412.56ms step:4963/6250 train_loss:2.3820 train_time:2043395ms step_avg:412.56ms step:4964/6250 train_loss:2.3965 train_time:2043802ms step_avg:412.56ms step:4965/6250 train_loss:2.4106 train_time:2044206ms step_avg:412.55ms step:4966/6250 train_loss:2.3735 train_time:2044607ms step_avg:412.55ms step:4967/6250 train_loss:2.3044 train_time:2045011ms step_avg:412.55ms step:4968/6250 train_loss:2.3805 train_time:2045411ms step_avg:412.55ms step:4969/6250 train_loss:2.3778 train_time:2045810ms step_avg:412.54ms step:4970/6250 train_loss:2.3895 train_time:2046211ms step_avg:412.54ms step:4971/6250 train_loss:2.4330 train_time:2046614ms step_avg:412.54ms step:4972/6250 train_loss:2.3748 train_time:2047016ms step_avg:412.54ms step:4973/6250 train_loss:2.3465 train_time:2047416ms step_avg:412.54ms step:4974/6250 train_loss:2.2984 train_time:2047815ms step_avg:412.53ms step:4975/6250 train_loss:2.2716 train_time:2048218ms step_avg:412.53ms step:4976/6250 train_loss:2.3741 train_time:2048621ms step_avg:412.53ms step:4977/6250 train_loss:2.4145 train_time:2049022ms step_avg:412.53ms step:4978/6250 train_loss:2.3807 train_time:2049425ms step_avg:412.53ms step:4979/6250 train_loss:2.3824 train_time:2049827ms step_avg:412.52ms step:4980/6250 train_loss:2.2963 train_time:2050229ms step_avg:412.52ms step:4981/6250 train_loss:2.4198 train_time:2050629ms step_avg:412.52ms step:4982/6250 train_loss:2.2680 train_time:2051031ms step_avg:412.52ms step:4983/6250 train_loss:2.3091 train_time:2051432ms step_avg:412.51ms step:4984/6250 train_loss:2.3499 train_time:2051836ms step_avg:412.51ms step:4985/6250 train_loss:2.4887 train_time:2052238ms step_avg:412.51ms step:4986/6250 train_loss:2.4260 train_time:2052641ms step_avg:412.51ms step:4987/6250 train_loss:2.3788 train_time:2053043ms step_avg:412.51ms step:4988/6250 train_loss:2.3337 train_time:2053443ms step_avg:412.50ms step:4989/6250 train_loss:2.2848 train_time:2053847ms step_avg:412.50ms step:4990/6250 train_loss:2.2718 train_time:2054244ms step_avg:412.50ms step:4991/6250 train_loss:2.3021 train_time:2054647ms step_avg:412.50ms step:4992/6250 train_loss:2.3599 train_time:2055048ms step_avg:412.49ms step:4993/6250 train_loss:2.3113 train_time:2055448ms step_avg:412.49ms step:4994/6250 train_loss:2.3094 train_time:2055852ms step_avg:412.49ms step:4995/6250 train_loss:2.4548 train_time:2056260ms step_avg:412.49ms step:4996/6250 train_loss:2.2584 train_time:2056664ms step_avg:412.49ms step:4997/6250 train_loss:2.3090 train_time:2057067ms step_avg:412.49ms step:4998/6250 train_loss:2.2532 train_time:2057469ms step_avg:412.48ms step:4999/6250 train_loss:2.4198 train_time:2057873ms step_avg:412.48ms step:5000/6250 train_loss:2.3421 train_time:2058276ms step_avg:412.48ms step:5001/6250 train_loss:2.3416 train_time:2058678ms step_avg:412.48ms step:5002/6250 train_loss:2.3655 train_time:2059081ms step_avg:412.48ms step:5003/6250 train_loss:2.3724 train_time:2059482ms step_avg:412.47ms step:5004/6250 train_loss:2.4037 train_time:2059883ms step_avg:412.47ms step:5005/6250 train_loss:2.4092 train_time:2060281ms step_avg:412.47ms step:5006/6250 train_loss:2.3493 train_time:2060682ms step_avg:412.47ms step:5007/6250 train_loss:2.3179 train_time:2061086ms step_avg:412.46ms step:5008/6250 train_loss:2.3322 train_time:2061493ms step_avg:412.46ms step:5009/6250 train_loss:2.4294 train_time:2061897ms step_avg:412.46ms step:5010/6250 train_loss:2.3163 train_time:2062300ms step_avg:412.46ms step:5011/6250 train_loss:2.3215 train_time:2062701ms step_avg:412.46ms step:5012/6250 train_loss:2.3290 train_time:2063101ms step_avg:412.46ms step:5013/6250 train_loss:2.4031 train_time:2063500ms step_avg:412.45ms step:5014/6250 train_loss:2.3379 train_time:2063902ms step_avg:412.45ms step:5015/6250 train_loss:2.3786 train_time:2064302ms step_avg:412.45ms step:5016/6250 train_loss:2.3381 train_time:2064703ms step_avg:412.45ms step:5017/6250 train_loss:2.3833 train_time:2065104ms step_avg:412.44ms step:5018/6250 train_loss:2.4432 train_time:2065506ms step_avg:412.44ms step:5019/6250 train_loss:2.4146 train_time:2065907ms step_avg:412.44ms step:5020/6250 train_loss:2.4167 train_time:2066308ms step_avg:412.44ms step:5021/6250 train_loss:2.3936 train_time:2066707ms step_avg:412.43ms step:5022/6250 train_loss:2.3043 train_time:2067110ms step_avg:412.43ms step:5023/6250 train_loss:2.3647 train_time:2067512ms step_avg:412.43ms step:5024/6250 train_loss:2.3786 train_time:2067914ms step_avg:412.43ms step:5025/6250 train_loss:2.3809 train_time:2068315ms step_avg:412.43ms step:5026/6250 train_loss:2.3363 train_time:2068718ms step_avg:412.42ms step:5027/6250 train_loss:2.4107 train_time:2069119ms step_avg:412.42ms step:5028/6250 train_loss:2.3437 train_time:2069520ms step_avg:412.42ms step:5029/6250 train_loss:2.3315 train_time:2069922ms step_avg:412.42ms step:5030/6250 train_loss:2.3121 train_time:2070322ms step_avg:412.41ms step:5031/6250 train_loss:2.4055 train_time:2070723ms step_avg:412.41ms step:5032/6250 train_loss:2.3345 train_time:2071123ms step_avg:412.41ms step:5033/6250 train_loss:2.3390 train_time:2071523ms step_avg:412.41ms step:5034/6250 train_loss:2.3065 train_time:2071922ms step_avg:412.40ms step:5035/6250 train_loss:2.3184 train_time:2072320ms step_avg:412.40ms step:5036/6250 train_loss:2.4206 train_time:2072723ms step_avg:412.40ms step:5037/6250 train_loss:2.3889 train_time:2073125ms step_avg:412.40ms step:5038/6250 train_loss:2.4127 train_time:2073526ms step_avg:412.40ms step:5039/6250 train_loss:2.3640 train_time:2073929ms step_avg:412.39ms step:5040/6250 train_loss:2.2758 train_time:2074328ms step_avg:412.39ms step:5041/6250 train_loss:2.3488 train_time:2074727ms step_avg:412.39ms step:5042/6250 train_loss:2.4033 train_time:2075129ms step_avg:412.39ms step:5043/6250 train_loss:2.3541 train_time:2075531ms step_avg:412.38ms step:5044/6250 train_loss:2.3428 train_time:2075932ms step_avg:412.38ms step:5045/6250 train_loss:2.2943 train_time:2076334ms step_avg:412.38ms step:5046/6250 train_loss:2.2480 train_time:2076737ms step_avg:412.38ms step:5047/6250 train_loss:2.3331 train_time:2077133ms step_avg:412.38ms step:5048/6250 train_loss:2.3504 train_time:2077535ms step_avg:412.37ms step:5049/6250 train_loss:2.3451 train_time:2077936ms step_avg:412.37ms step:5050/6250 train_loss:2.1874 train_time:2078336ms step_avg:412.37ms step:5051/6250 train_loss:2.3948 train_time:2078738ms step_avg:412.37ms step:5052/6250 train_loss:2.4904 train_time:2079135ms step_avg:412.36ms step:5053/6250 train_loss:2.3123 train_time:2079536ms step_avg:412.36ms step:5054/6250 train_loss:2.3881 train_time:2079939ms step_avg:412.36ms step:5055/6250 train_loss:2.2616 train_time:2080339ms step_avg:412.36ms step:5056/6250 train_loss:2.3743 train_time:2080742ms step_avg:412.35ms step:5057/6250 train_loss:2.2685 train_time:2081138ms step_avg:412.35ms step:5058/6250 train_loss:2.4033 train_time:2081540ms step_avg:412.35ms step:5059/6250 train_loss:2.3349 train_time:2081942ms step_avg:412.35ms step:5060/6250 train_loss:2.3563 train_time:2082344ms step_avg:412.35ms step:5061/6250 train_loss:2.3074 train_time:2082744ms step_avg:412.34ms step:5062/6250 train_loss:2.2394 train_time:2083144ms step_avg:412.34ms step:5063/6250 train_loss:2.3554 train_time:2083546ms step_avg:412.34ms step:5064/6250 train_loss:2.2800 train_time:2083947ms step_avg:412.34ms step:5065/6250 train_loss:2.3868 train_time:2084348ms step_avg:412.33ms step:5066/6250 train_loss:2.4299 train_time:2084750ms step_avg:412.33ms step:5067/6250 train_loss:2.3154 train_time:2085148ms step_avg:412.33ms step:5068/6250 train_loss:2.3742 train_time:2085548ms step_avg:412.33ms step:5069/6250 train_loss:2.2729 train_time:2085950ms step_avg:412.32ms step:5070/6250 train_loss:2.3294 train_time:2086350ms step_avg:412.32ms step:5071/6250 train_loss:2.2929 train_time:2086754ms step_avg:412.32ms step:5072/6250 train_loss:2.3147 train_time:2087157ms step_avg:412.32ms step:5073/6250 train_loss:2.4096 train_time:2087558ms step_avg:412.32ms step:5074/6250 train_loss:2.4644 train_time:2087961ms step_avg:412.31ms step:5075/6250 train_loss:2.3142 train_time:2088363ms step_avg:412.31ms step:5076/6250 train_loss:2.3476 train_time:2088763ms step_avg:412.31ms step:5077/6250 train_loss:2.3380 train_time:2089163ms step_avg:412.31ms step:5078/6250 train_loss:2.2413 train_time:2089564ms step_avg:412.31ms step:5079/6250 train_loss:2.3882 train_time:2089965ms step_avg:412.30ms step:5080/6250 train_loss:2.3598 train_time:2090368ms step_avg:412.30ms step:5081/6250 train_loss:2.3684 train_time:2090770ms step_avg:412.30ms step:5082/6250 train_loss:2.3698 train_time:2091171ms step_avg:412.30ms step:5083/6250 train_loss:2.3046 train_time:2091573ms step_avg:412.30ms step:5084/6250 train_loss:2.4358 train_time:2091976ms step_avg:412.29ms step:5085/6250 train_loss:2.3304 train_time:2092375ms step_avg:412.29ms step:5086/6250 train_loss:2.3100 train_time:2092776ms step_avg:412.29ms step:5087/6250 train_loss:2.3671 train_time:2093178ms step_avg:412.29ms step:5088/6250 train_loss:2.4121 train_time:2093578ms step_avg:412.28ms step:5089/6250 train_loss:2.3462 train_time:2093978ms step_avg:412.28ms step:5090/6250 train_loss:2.3714 train_time:2094376ms step_avg:412.28ms step:5091/6250 train_loss:2.3593 train_time:2094778ms step_avg:412.28ms step:5092/6250 train_loss:2.2954 train_time:2095180ms step_avg:412.27ms step:5093/6250 train_loss:2.2962 train_time:2095580ms step_avg:412.27ms step:5094/6250 train_loss:2.2653 train_time:2095979ms step_avg:412.27ms step:5095/6250 train_loss:2.3252 train_time:2096380ms step_avg:412.27ms step:5096/6250 train_loss:2.3074 train_time:2096783ms step_avg:412.27ms step:5097/6250 train_loss:2.3418 train_time:2097185ms step_avg:412.26ms step:5098/6250 train_loss:2.3311 train_time:2097586ms step_avg:412.26ms step:5099/6250 train_loss:2.2416 train_time:2097988ms step_avg:412.26ms step:5100/6250 train_loss:2.2858 train_time:2098389ms step_avg:412.26ms step:5101/6250 train_loss:2.3048 train_time:2098790ms step_avg:412.25ms step:5102/6250 train_loss:2.3532 train_time:2099190ms step_avg:412.25ms step:5103/6250 train_loss:2.3406 train_time:2099589ms step_avg:412.25ms step:5104/6250 train_loss:2.3083 train_time:2099992ms step_avg:412.25ms step:5105/6250 train_loss:2.3567 train_time:2100393ms step_avg:412.25ms step:5106/6250 train_loss:2.3936 train_time:2100794ms step_avg:412.24ms step:5107/6250 train_loss:2.3999 train_time:2101194ms step_avg:412.24ms step:5108/6250 train_loss:2.4227 train_time:2101593ms step_avg:412.24ms step:5109/6250 train_loss:2.3563 train_time:2101992ms step_avg:412.24ms step:5110/6250 train_loss:2.4690 train_time:2102391ms step_avg:412.23ms step:5111/6250 train_loss:2.3261 train_time:2102792ms step_avg:412.23ms step:5112/6250 train_loss:2.3243 train_time:2103195ms step_avg:412.23ms step:5113/6250 train_loss:2.3450 train_time:2103595ms step_avg:412.23ms step:5114/6250 train_loss:2.3246 train_time:2103997ms step_avg:412.23ms step:5115/6250 train_loss:2.3282 train_time:2104399ms step_avg:412.22ms step:5116/6250 train_loss:2.4244 train_time:2104799ms step_avg:412.22ms step:5117/6250 train_loss:2.2882 train_time:2105199ms step_avg:412.22ms step:5118/6250 train_loss:2.4527 train_time:2105600ms step_avg:412.22ms step:5119/6250 train_loss:2.3794 train_time:2106001ms step_avg:412.21ms step:5120/6250 train_loss:2.3131 train_time:2106402ms step_avg:412.21ms step:5121/6250 train_loss:2.3797 train_time:2106806ms step_avg:412.21ms step:5122/6250 train_loss:2.3057 train_time:2107204ms step_avg:412.21ms step:5123/6250 train_loss:2.3487 train_time:2107605ms step_avg:412.21ms step:5124/6250 train_loss:2.3291 train_time:2108005ms step_avg:412.20ms step:5125/6250 train_loss:2.3532 train_time:2108405ms step_avg:412.20ms step:5126/6250 train_loss:2.3856 train_time:2108804ms step_avg:412.20ms step:5127/6250 train_loss:2.3607 train_time:2109204ms step_avg:412.20ms step:5128/6250 train_loss:2.3720 train_time:2109607ms step_avg:412.19ms step:5129/6250 train_loss:2.2857 train_time:2110010ms step_avg:412.19ms step:5130/6250 train_loss:2.2940 train_time:2110410ms step_avg:412.19ms step:5131/6250 train_loss:2.3238 train_time:2110811ms step_avg:412.19ms step:5132/6250 train_loss:2.2116 train_time:2111211ms step_avg:412.18ms step:5133/6250 train_loss:2.3689 train_time:2111615ms step_avg:412.18ms step:5134/6250 train_loss:2.3758 train_time:2112016ms step_avg:412.18ms step:5135/6250 train_loss:2.3479 train_time:2112417ms step_avg:412.18ms step:5136/6250 train_loss:2.2474 train_time:2112819ms step_avg:412.18ms step:5137/6250 train_loss:2.4616 train_time:2113219ms step_avg:412.17ms step:5138/6250 train_loss:2.2975 train_time:2113620ms step_avg:412.17ms step:5139/6250 train_loss:2.3236 train_time:2114026ms step_avg:412.17ms step:5140/6250 train_loss:2.3754 train_time:2114426ms step_avg:412.17ms step:5141/6250 train_loss:2.2898 train_time:2114829ms step_avg:412.17ms step:5142/6250 train_loss:2.3005 train_time:2115231ms step_avg:412.16ms step:5143/6250 train_loss:2.3248 train_time:2115633ms step_avg:412.16ms step:5144/6250 train_loss:2.4071 train_time:2116038ms step_avg:412.16ms step:5145/6250 train_loss:2.2998 train_time:2116442ms step_avg:412.16ms step:5146/6250 train_loss:2.2789 train_time:2116847ms step_avg:412.16ms step:5147/6250 train_loss:2.3367 train_time:2117246ms step_avg:412.16ms step:5148/6250 train_loss:2.3860 train_time:2117649ms step_avg:412.15ms step:5149/6250 train_loss:2.3253 train_time:2118050ms step_avg:412.15ms step:5150/6250 train_loss:2.3414 train_time:2118451ms step_avg:412.15ms step:5151/6250 train_loss:2.3098 train_time:2118852ms step_avg:412.15ms step:5152/6250 train_loss:2.2560 train_time:2119255ms step_avg:412.15ms step:5153/6250 train_loss:2.3202 train_time:2119669ms step_avg:412.15ms step:5154/6250 train_loss:2.4150 train_time:2120075ms step_avg:412.15ms step:5155/6250 train_loss:2.3506 train_time:2120481ms step_avg:412.14ms step:5156/6250 train_loss:2.3591 train_time:2120883ms step_avg:412.14ms step:5157/6250 train_loss:2.3198 train_time:2121285ms step_avg:412.14ms step:5158/6250 train_loss:2.3540 train_time:2121688ms step_avg:412.14ms step:5159/6250 train_loss:2.3886 train_time:2122088ms step_avg:412.14ms step:5160/6250 train_loss:2.2627 train_time:2122487ms step_avg:412.13ms step:5161/6250 train_loss:2.3605 train_time:2122891ms step_avg:412.13ms step:5162/6250 train_loss:2.4321 train_time:2123292ms step_avg:412.13ms step:5163/6250 train_loss:2.3450 train_time:2123694ms step_avg:412.13ms step:5164/6250 train_loss:2.3682 train_time:2124094ms step_avg:412.13ms step:5165/6250 train_loss:2.3200 train_time:2124494ms step_avg:412.12ms step:5166/6250 train_loss:2.3631 train_time:2124895ms step_avg:412.12ms step:5167/6250 train_loss:2.2226 train_time:2125295ms step_avg:412.12ms step:5168/6250 train_loss:2.2851 train_time:2125698ms step_avg:412.12ms step:5169/6250 train_loss:2.3026 train_time:2126098ms step_avg:412.11ms step:5170/6250 train_loss:2.3300 train_time:2126500ms step_avg:412.11ms step:5171/6250 train_loss:2.3926 train_time:2126900ms step_avg:412.11ms step:5172/6250 train_loss:2.2587 train_time:2127301ms step_avg:412.11ms step:5173/6250 train_loss:2.3263 train_time:2127703ms step_avg:412.11ms step:5174/6250 train_loss:2.2545 train_time:2128106ms step_avg:412.10ms step:5175/6250 train_loss:2.3200 train_time:2128506ms step_avg:412.10ms step:5176/6250 train_loss:2.3228 train_time:2128908ms step_avg:412.10ms step:5177/6250 train_loss:2.3191 train_time:2129309ms step_avg:412.10ms step:5178/6250 train_loss:2.4145 train_time:2129709ms step_avg:412.10ms step:5179/6250 train_loss:2.3761 train_time:2130111ms step_avg:412.09ms step:5180/6250 train_loss:2.2399 train_time:2130513ms step_avg:412.09ms step:5181/6250 train_loss:2.3969 train_time:2130916ms step_avg:412.09ms step:5182/6250 train_loss:2.3785 train_time:2131318ms step_avg:412.09ms step:5183/6250 train_loss:2.3458 train_time:2131721ms step_avg:412.09ms step:5184/6250 train_loss:2.3115 train_time:2132124ms step_avg:412.08ms step:5185/6250 train_loss:2.2558 train_time:2132525ms step_avg:412.08ms step:5186/6250 train_loss:2.2302 train_time:2132926ms step_avg:412.08ms step:5187/6250 train_loss:2.3178 train_time:2133326ms step_avg:412.08ms step:5188/6250 train_loss:2.3413 train_time:2133729ms step_avg:412.08ms step:5189/6250 train_loss:2.3631 train_time:2134132ms step_avg:412.07ms step:5190/6250 train_loss:2.3339 train_time:2134534ms step_avg:412.07ms step:5191/6250 train_loss:2.2941 train_time:2134936ms step_avg:412.07ms step:5192/6250 train_loss:2.3551 train_time:2135335ms step_avg:412.07ms step:5193/6250 train_loss:2.2698 train_time:2135736ms step_avg:412.07ms step:5194/6250 train_loss:2.4271 train_time:2136136ms step_avg:412.06ms step:5195/6250 train_loss:2.3156 train_time:2136541ms step_avg:412.06ms step:5196/6250 train_loss:2.3680 train_time:2136950ms step_avg:412.06ms step:5197/6250 train_loss:2.3051 train_time:2137357ms step_avg:412.06ms step:5198/6250 train_loss:2.3243 train_time:2137760ms step_avg:412.06ms step:5199/6250 train_loss:2.2982 train_time:2138161ms step_avg:412.06ms step:5200/6250 train_loss:2.3250 train_time:2138561ms step_avg:412.05ms step:5201/6250 train_loss:2.3699 train_time:2138965ms step_avg:412.05ms step:5202/6250 train_loss:2.3465 train_time:2139366ms step_avg:412.05ms step:5203/6250 train_loss:2.3578 train_time:2139770ms step_avg:412.05ms step:5204/6250 train_loss:2.3761 train_time:2140171ms step_avg:412.05ms step:5205/6250 train_loss:2.3514 train_time:2140573ms step_avg:412.04ms step:5206/6250 train_loss:2.3563 train_time:2140975ms step_avg:412.04ms step:5207/6250 train_loss:2.2584 train_time:2141377ms step_avg:412.04ms step:5208/6250 train_loss:2.3675 train_time:2141777ms step_avg:412.04ms step:5209/6250 train_loss:2.3772 train_time:2142177ms step_avg:412.04ms step:5210/6250 train_loss:2.3944 train_time:2142579ms step_avg:412.03ms step:5211/6250 train_loss:2.3062 train_time:2142981ms step_avg:412.03ms step:5212/6250 train_loss:2.3115 train_time:2143383ms step_avg:412.03ms step:5213/6250 train_loss:2.4006 train_time:2143787ms step_avg:412.03ms step:5214/6250 train_loss:2.3806 train_time:2144189ms step_avg:412.03ms step:5215/6250 train_loss:2.3060 train_time:2144589ms step_avg:412.02ms step:5216/6250 train_loss:2.3024 train_time:2144992ms step_avg:412.02ms step:5217/6250 train_loss:2.3846 train_time:2145391ms step_avg:412.02ms step:5218/6250 train_loss:2.3726 train_time:2145793ms step_avg:412.02ms step:5219/6250 train_loss:2.3575 train_time:2146194ms step_avg:412.02ms step:5220/6250 train_loss:2.3930 train_time:2146594ms step_avg:412.01ms step:5221/6250 train_loss:2.3457 train_time:2146995ms step_avg:412.01ms step:5222/6250 train_loss:2.3627 train_time:2147396ms step_avg:412.01ms step:5223/6250 train_loss:2.2914 train_time:2147794ms step_avg:412.01ms step:5224/6250 train_loss:2.2800 train_time:2148195ms step_avg:412.01ms step:5225/6250 train_loss:2.3878 train_time:2148596ms step_avg:412.00ms step:5226/6250 train_loss:2.3980 train_time:2148998ms step_avg:412.00ms step:5227/6250 train_loss:2.2770 train_time:2149398ms step_avg:412.00ms step:5228/6250 train_loss:2.3224 train_time:2149802ms step_avg:412.00ms step:5229/6250 train_loss:2.3698 train_time:2150203ms step_avg:412.00ms step:5230/6250 train_loss:2.2634 train_time:2150602ms step_avg:411.99ms step:5231/6250 train_loss:2.4543 train_time:2151003ms step_avg:411.99ms step:5232/6250 train_loss:2.3289 train_time:2151403ms step_avg:411.99ms step:5233/6250 train_loss:2.3879 train_time:2151806ms step_avg:411.99ms step:5234/6250 train_loss:2.2788 train_time:2152208ms step_avg:411.98ms step:5235/6250 train_loss:2.4023 train_time:2152609ms step_avg:411.98ms step:5236/6250 train_loss:2.3807 train_time:2153012ms step_avg:411.98ms step:5237/6250 train_loss:2.2614 train_time:2153411ms step_avg:411.98ms step:5238/6250 train_loss:2.2430 train_time:2153813ms step_avg:411.98ms step:5239/6250 train_loss:2.3317 train_time:2154215ms step_avg:411.97ms step:5240/6250 train_loss:2.3948 train_time:2154634ms step_avg:411.98ms step:5241/6250 train_loss:2.2992 train_time:2155035ms step_avg:411.97ms step:5242/6250 train_loss:2.3099 train_time:2155440ms step_avg:411.97ms step:5243/6250 train_loss:2.3436 train_time:2155848ms step_avg:411.97ms step:5244/6250 train_loss:2.2258 train_time:2156249ms step_avg:411.97ms step:5245/6250 train_loss:2.2871 train_time:2156647ms step_avg:411.97ms step:5246/6250 train_loss:2.2715 train_time:2157049ms step_avg:411.97ms step:5247/6250 train_loss:2.3133 train_time:2157452ms step_avg:411.96ms step:5248/6250 train_loss:2.3868 train_time:2157856ms step_avg:411.96ms step:5249/6250 train_loss:2.2975 train_time:2158257ms step_avg:411.96ms step:5250/6250 train_loss:2.3859 train_time:2158659ms step_avg:411.96ms step:5251/6250 train_loss:2.3819 train_time:2159061ms step_avg:411.96ms step:5252/6250 train_loss:2.3354 train_time:2159467ms step_avg:411.95ms step:5253/6250 train_loss:2.2817 train_time:2159874ms step_avg:411.95ms step:5254/6250 train_loss:2.3253 train_time:2160276ms step_avg:411.95ms step:5255/6250 train_loss:2.3135 train_time:2160676ms step_avg:411.95ms step:5256/6250 train_loss:2.2801 train_time:2161078ms step_avg:411.95ms step:5257/6250 train_loss:2.2716 train_time:2161480ms step_avg:411.95ms step:5258/6250 train_loss:2.3939 train_time:2161883ms step_avg:411.94ms step:5259/6250 train_loss:2.3054 train_time:2162285ms step_avg:411.94ms step:5260/6250 train_loss:2.3563 train_time:2162689ms step_avg:411.94ms step:5261/6250 train_loss:2.3748 train_time:2163092ms step_avg:411.94ms step:5262/6250 train_loss:2.3627 train_time:2163493ms step_avg:411.94ms step:5263/6250 train_loss:2.4060 train_time:2163898ms step_avg:411.94ms step:5264/6250 train_loss:2.3088 train_time:2164299ms step_avg:411.93ms step:5265/6250 train_loss:2.3419 train_time:2164698ms step_avg:411.93ms step:5266/6250 train_loss:2.3452 train_time:2165102ms step_avg:411.93ms step:5267/6250 train_loss:2.3937 train_time:2165500ms step_avg:411.93ms step:5268/6250 train_loss:2.3571 train_time:2165903ms step_avg:411.93ms step:5269/6250 train_loss:2.2731 train_time:2166304ms step_avg:411.92ms step:5270/6250 train_loss:2.3569 train_time:2166706ms step_avg:411.92ms step:5271/6250 train_loss:2.2769 train_time:2167108ms step_avg:411.92ms step:5272/6250 train_loss:2.2526 train_time:2167510ms step_avg:411.92ms step:5273/6250 train_loss:2.2022 train_time:2167913ms step_avg:411.92ms step:5274/6250 train_loss:2.3258 train_time:2168315ms step_avg:411.91ms step:5275/6250 train_loss:2.3354 train_time:2168714ms step_avg:411.91ms step:5276/6250 train_loss:2.3554 train_time:2169117ms step_avg:411.91ms step:5277/6250 train_loss:2.3366 train_time:2169517ms step_avg:411.91ms step:5278/6250 train_loss:2.3555 train_time:2169920ms step_avg:411.91ms step:5279/6250 train_loss:2.3612 train_time:2170319ms step_avg:411.90ms step:5280/6250 train_loss:2.3613 train_time:2170720ms step_avg:411.90ms step:5281/6250 train_loss:2.2877 train_time:2171120ms step_avg:411.90ms step:5282/6250 train_loss:2.3874 train_time:2171522ms step_avg:411.90ms step:5283/6250 train_loss:2.3079 train_time:2171926ms step_avg:411.90ms step:5284/6250 train_loss:2.3777 train_time:2172324ms step_avg:411.89ms step:5285/6250 train_loss:2.3200 train_time:2172724ms step_avg:411.89ms step:5286/6250 train_loss:2.2453 train_time:2173126ms step_avg:411.89ms step:5287/6250 train_loss:2.2377 train_time:2173529ms step_avg:411.89ms step:5288/6250 train_loss:2.3290 train_time:2173931ms step_avg:411.89ms step:5289/6250 train_loss:2.3088 train_time:2174334ms step_avg:411.88ms step:5290/6250 train_loss:2.3262 train_time:2174738ms step_avg:411.88ms step:5291/6250 train_loss:2.2479 train_time:2175142ms step_avg:411.88ms step:5292/6250 train_loss:2.3014 train_time:2175548ms step_avg:411.88ms step:5293/6250 train_loss:2.4176 train_time:2175955ms step_avg:411.88ms step:5294/6250 train_loss:2.2408 train_time:2176358ms step_avg:411.88ms step:5295/6250 train_loss:2.2989 train_time:2176764ms step_avg:411.88ms step:5296/6250 train_loss:2.2825 train_time:2177167ms step_avg:411.87ms step:5297/6250 train_loss:2.2737 train_time:2177570ms step_avg:411.87ms step:5298/6250 train_loss:2.4060 train_time:2177975ms step_avg:411.87ms step:5299/6250 train_loss:2.3552 train_time:2178377ms step_avg:411.87ms step:5300/6250 train_loss:2.2784 train_time:2178781ms step_avg:411.87ms step:5301/6250 train_loss:2.2598 train_time:2179183ms step_avg:411.87ms step:5302/6250 train_loss:2.3149 train_time:2179584ms step_avg:411.86ms step:5303/6250 train_loss:2.3492 train_time:2179987ms step_avg:411.86ms step:5304/6250 train_loss:2.3489 train_time:2180392ms step_avg:411.86ms step:5305/6250 train_loss:2.3327 train_time:2180793ms step_avg:411.86ms step:5306/6250 train_loss:2.3187 train_time:2181192ms step_avg:411.86ms step:5307/6250 train_loss:2.2962 train_time:2181595ms step_avg:411.85ms step:5308/6250 train_loss:2.3400 train_time:2181997ms step_avg:411.85ms step:5309/6250 train_loss:2.2202 train_time:2182400ms step_avg:411.85ms step:5310/6250 train_loss:2.4000 train_time:2182802ms step_avg:411.85ms step:5311/6250 train_loss:2.3299 train_time:2183201ms step_avg:411.85ms step:5312/6250 train_loss:2.3140 train_time:2183602ms step_avg:411.84ms step:5313/6250 train_loss:2.3322 train_time:2184004ms step_avg:411.84ms step:5314/6250 train_loss:2.2716 train_time:2184406ms step_avg:411.84ms step:5315/6250 train_loss:2.3102 train_time:2184811ms step_avg:411.84ms step:5316/6250 train_loss:2.2517 train_time:2185214ms step_avg:411.84ms step:5317/6250 train_loss:2.3916 train_time:2185616ms step_avg:411.84ms step:5318/6250 train_loss:2.3299 train_time:2186017ms step_avg:411.83ms step:5319/6250 train_loss:2.3251 train_time:2186420ms step_avg:411.83ms step:5320/6250 train_loss:2.2704 train_time:2186819ms step_avg:411.83ms step:5321/6250 train_loss:2.3209 train_time:2187219ms step_avg:411.83ms step:5322/6250 train_loss:2.3461 train_time:2187623ms step_avg:411.83ms step:5323/6250 train_loss:2.2847 train_time:2188025ms step_avg:411.82ms step:5324/6250 train_loss:2.3494 train_time:2188429ms step_avg:411.82ms step:5325/6250 train_loss:2.3525 train_time:2188832ms step_avg:411.82ms step:5326/6250 train_loss:2.3605 train_time:2189232ms step_avg:411.82ms step:5327/6250 train_loss:2.3044 train_time:2189633ms step_avg:411.82ms step:5328/6250 train_loss:2.3362 train_time:2190037ms step_avg:411.82ms step:5329/6250 train_loss:2.3797 train_time:2190438ms step_avg:411.81ms step:5330/6250 train_loss:2.3119 train_time:2190837ms step_avg:411.81ms step:5331/6250 train_loss:2.2884 train_time:2191238ms step_avg:411.81ms step:5332/6250 train_loss:2.3627 train_time:2191638ms step_avg:411.81ms step:5333/6250 train_loss:2.3654 train_time:2192040ms step_avg:411.81ms step:5334/6250 train_loss:2.3296 train_time:2192435ms step_avg:411.80ms step:5335/6250 train_loss:2.2625 train_time:2192836ms step_avg:411.80ms step:5336/6250 train_loss:2.2788 train_time:2193238ms step_avg:411.80ms step:5337/6250 train_loss:2.3224 train_time:2193642ms step_avg:411.80ms step:5338/6250 train_loss:2.2888 train_time:2194044ms step_avg:411.80ms step:5339/6250 train_loss:2.3319 train_time:2194445ms step_avg:411.79ms step:5340/6250 train_loss:2.3964 train_time:2194847ms step_avg:411.79ms step:5341/6250 train_loss:2.4352 train_time:2195248ms step_avg:411.79ms step:5342/6250 train_loss:2.3654 train_time:2195648ms step_avg:411.79ms step:5343/6250 train_loss:2.2883 train_time:2196047ms step_avg:411.78ms step:5344/6250 train_loss:2.2929 train_time:2196447ms step_avg:411.78ms step:5345/6250 train_loss:2.2494 train_time:2196850ms step_avg:411.78ms step:5346/6250 train_loss:2.3620 train_time:2197252ms step_avg:411.78ms step:5347/6250 train_loss:2.3713 train_time:2197651ms step_avg:411.78ms step:5348/6250 train_loss:2.3010 train_time:2198050ms step_avg:411.77ms step:5349/6250 train_loss:2.3651 train_time:2198451ms step_avg:411.77ms step:5350/6250 train_loss:2.4006 train_time:2198853ms step_avg:411.77ms step:5351/6250 train_loss:2.3762 train_time:2199254ms step_avg:411.77ms step:5352/6250 train_loss:2.2576 train_time:2199652ms step_avg:411.77ms step:5353/6250 train_loss:2.3157 train_time:2200053ms step_avg:411.76ms step:5354/6250 train_loss:2.2288 train_time:2200453ms step_avg:411.76ms step:5355/6250 train_loss:2.2861 train_time:2200855ms step_avg:411.76ms step:5356/6250 train_loss:2.3889 train_time:2201254ms step_avg:411.76ms step:5357/6250 train_loss:2.3266 train_time:2201655ms step_avg:411.76ms step:5358/6250 train_loss:2.2746 train_time:2202058ms step_avg:411.75ms step:5359/6250 train_loss:2.2812 train_time:2202457ms step_avg:411.75ms step:5360/6250 train_loss:2.2622 train_time:2202859ms step_avg:411.75ms step:5361/6250 train_loss:2.3458 train_time:2203260ms step_avg:411.75ms step:5362/6250 train_loss:2.3593 train_time:2203662ms step_avg:411.75ms step:5363/6250 train_loss:2.3074 train_time:2204064ms step_avg:411.74ms step:5364/6250 train_loss:2.3960 train_time:2204464ms step_avg:411.74ms step:5365/6250 train_loss:2.2704 train_time:2204867ms step_avg:411.74ms step:5366/6250 train_loss:2.3567 train_time:2205266ms step_avg:411.74ms step:5367/6250 train_loss:2.2934 train_time:2205671ms step_avg:411.74ms step:5368/6250 train_loss:2.3270 train_time:2206085ms step_avg:411.74ms step:5369/6250 train_loss:2.3699 train_time:2206495ms step_avg:411.74ms step:5370/6250 train_loss:2.3137 train_time:2206906ms step_avg:411.74ms step:5371/6250 train_loss:2.3577 train_time:2207308ms step_avg:411.73ms step:5372/6250 train_loss:2.2936 train_time:2207736ms step_avg:411.74ms step:5373/6250 train_loss:2.2844 train_time:2208135ms step_avg:411.74ms step:5374/6250 train_loss:2.3284 train_time:2208534ms step_avg:411.73ms step:5375/6250 train_loss:2.3540 train_time:2208961ms step_avg:411.74ms step:5376/6250 train_loss:2.3238 train_time:2209361ms step_avg:411.73ms step:5377/6250 train_loss:2.3552 train_time:2209764ms step_avg:411.73ms step:5378/6250 train_loss:2.3252 train_time:2210164ms step_avg:411.73ms step:5379/6250 train_loss:2.2593 train_time:2210565ms step_avg:411.73ms step:5380/6250 train_loss:2.3329 train_time:2210963ms step_avg:411.72ms step:5381/6250 train_loss:2.2616 train_time:2211364ms step_avg:411.72ms step:5382/6250 train_loss:2.2714 train_time:2211765ms step_avg:411.72ms step:5383/6250 train_loss:2.2935 train_time:2212166ms step_avg:411.72ms step:5384/6250 train_loss:2.3237 train_time:2212568ms step_avg:411.72ms step:5385/6250 train_loss:2.2821 train_time:2212970ms step_avg:411.72ms step:5386/6250 train_loss:2.3563 train_time:2213397ms step_avg:411.72ms step:5387/6250 train_loss:2.3434 train_time:2213800ms step_avg:411.72ms step:5388/6250 train_loss:2.3898 train_time:2214210ms step_avg:411.72ms step:5389/6250 train_loss:2.2949 train_time:2214621ms step_avg:411.72ms step:5390/6250 train_loss:2.2935 train_time:2215022ms step_avg:411.71ms step:5391/6250 train_loss:2.3286 train_time:2215422ms step_avg:411.71ms step:5392/6250 train_loss:2.2946 train_time:2215823ms step_avg:411.71ms step:5393/6250 train_loss:2.2888 train_time:2216222ms step_avg:411.71ms step:5394/6250 train_loss:2.4047 train_time:2216624ms step_avg:411.71ms step:5395/6250 train_loss:2.2969 train_time:2217024ms step_avg:411.70ms step:5396/6250 train_loss:2.3992 train_time:2217424ms step_avg:411.70ms step:5397/6250 train_loss:2.3268 train_time:2217825ms step_avg:411.70ms step:5398/6250 train_loss:2.3819 train_time:2218226ms step_avg:411.70ms step:5399/6250 train_loss:2.4277 train_time:2218627ms step_avg:411.70ms step:5400/6250 train_loss:2.3776 train_time:2219027ms step_avg:411.69ms step:5401/6250 train_loss:2.3450 train_time:2219446ms step_avg:411.69ms step:5402/6250 train_loss:2.3275 train_time:2219845ms step_avg:411.69ms step:5403/6250 train_loss:2.4337 train_time:2220268ms step_avg:411.69ms step:5404/6250 train_loss:2.3164 train_time:2220698ms step_avg:411.70ms step:5405/6250 train_loss:2.3947 train_time:2221100ms step_avg:411.70ms step:5406/6250 train_loss:2.3069 train_time:2221519ms step_avg:411.70ms step:5407/6250 train_loss:2.2604 train_time:2221921ms step_avg:411.70ms step:5408/6250 train_loss:2.3639 train_time:2222319ms step_avg:411.69ms step:5409/6250 train_loss:2.3458 train_time:2222722ms step_avg:411.69ms step:5410/6250 train_loss:2.3714 train_time:2223124ms step_avg:411.69ms step:5411/6250 train_loss:2.2627 train_time:2223524ms step_avg:411.69ms step:5412/6250 train_loss:2.3517 train_time:2223929ms step_avg:411.69ms step:5413/6250 train_loss:2.3645 train_time:2224330ms step_avg:411.68ms step:5414/6250 train_loss:2.3268 train_time:2224734ms step_avg:411.68ms step:5415/6250 train_loss:2.3097 train_time:2225135ms step_avg:411.68ms step:5416/6250 train_loss:2.3306 train_time:2225537ms step_avg:411.68ms step:5417/6250 train_loss:2.2786 train_time:2225940ms step_avg:411.68ms step:5418/6250 train_loss:2.2671 train_time:2226338ms step_avg:411.67ms step:5419/6250 train_loss:2.2803 train_time:2226738ms step_avg:411.67ms step:5420/6250 train_loss:2.2935 train_time:2227140ms step_avg:411.67ms step:5421/6250 train_loss:2.3253 train_time:2227541ms step_avg:411.67ms step:5422/6250 train_loss:2.4497 train_time:2227944ms step_avg:411.67ms step:5423/6250 train_loss:2.2073 train_time:2228342ms step_avg:411.66ms step:5424/6250 train_loss:2.3635 train_time:2228745ms step_avg:411.66ms step:5425/6250 train_loss:2.3026 train_time:2229146ms step_avg:411.66ms step:5426/6250 train_loss:2.2034 train_time:2229547ms step_avg:411.66ms step:5427/6250 train_loss:2.3104 train_time:2229948ms step_avg:411.66ms step:5428/6250 train_loss:2.3314 train_time:2230347ms step_avg:411.65ms step:5429/6250 train_loss:2.3599 train_time:2230745ms step_avg:411.65ms step:5430/6250 train_loss:2.3636 train_time:2231145ms step_avg:411.65ms step:5431/6250 train_loss:2.3833 train_time:2231546ms step_avg:411.65ms step:5432/6250 train_loss:2.2678 train_time:2231949ms step_avg:411.65ms step:5433/6250 train_loss:2.3014 train_time:2232349ms step_avg:411.64ms step:5434/6250 train_loss:2.3108 train_time:2232751ms step_avg:411.64ms step:5435/6250 train_loss:2.3822 train_time:2233149ms step_avg:411.64ms step:5436/6250 train_loss:2.3627 train_time:2233551ms step_avg:411.64ms step:5437/6250 train_loss:2.3468 train_time:2233953ms step_avg:411.64ms step:5438/6250 train_loss:2.3458 train_time:2234354ms step_avg:411.63ms step:5439/6250 train_loss:2.4020 train_time:2234757ms step_avg:411.63ms step:5440/6250 train_loss:2.2367 train_time:2235158ms step_avg:411.63ms step:5441/6250 train_loss:2.2735 train_time:2235556ms step_avg:411.63ms step:5442/6250 train_loss:2.3334 train_time:2235957ms step_avg:411.63ms step:5443/6250 train_loss:2.2880 train_time:2236357ms step_avg:411.62ms step:5444/6250 train_loss:2.4119 train_time:2236758ms step_avg:411.62ms step:5445/6250 train_loss:2.3333 train_time:2237158ms step_avg:411.62ms step:5446/6250 train_loss:2.3186 train_time:2237556ms step_avg:411.62ms step:5447/6250 train_loss:2.3791 train_time:2237958ms step_avg:411.62ms step:5448/6250 train_loss:2.3113 train_time:2238356ms step_avg:411.61ms step:5449/6250 train_loss:2.3091 train_time:2238756ms step_avg:411.61ms step:5450/6250 train_loss:2.2818 train_time:2239158ms step_avg:411.61ms step:5451/6250 train_loss:2.3235 train_time:2239557ms step_avg:411.61ms step:5452/6250 train_loss:2.3143 train_time:2239960ms step_avg:411.61ms step:5453/6250 train_loss:2.1611 train_time:2240358ms step_avg:411.60ms step:5454/6250 train_loss:2.2455 train_time:2240762ms step_avg:411.60ms step:5455/6250 train_loss:2.3108 train_time:2241167ms step_avg:411.60ms step:5456/6250 train_loss:2.2678 train_time:2241572ms step_avg:411.60ms step:5457/6250 train_loss:2.3852 train_time:2241973ms step_avg:411.60ms step:5458/6250 train_loss:2.3136 train_time:2242371ms step_avg:411.60ms step:5459/6250 train_loss:2.2922 train_time:2242773ms step_avg:411.59ms step:5460/6250 train_loss:2.3874 train_time:2243175ms step_avg:411.59ms step:5461/6250 train_loss:2.4198 train_time:2243576ms step_avg:411.59ms step:5462/6250 train_loss:2.3769 train_time:2243978ms step_avg:411.59ms step:5463/6250 train_loss:2.3147 train_time:2244379ms step_avg:411.59ms step:5464/6250 train_loss:2.3228 train_time:2244778ms step_avg:411.58ms step:5465/6250 train_loss:2.2674 train_time:2245181ms step_avg:411.58ms step:5466/6250 train_loss:2.2976 train_time:2245581ms step_avg:411.58ms step:5467/6250 train_loss:2.3006 train_time:2245985ms step_avg:411.58ms step:5468/6250 train_loss:2.2376 train_time:2246390ms step_avg:411.58ms step:5469/6250 train_loss:2.2962 train_time:2246794ms step_avg:411.58ms step:5470/6250 train_loss:2.3240 train_time:2247198ms step_avg:411.57ms step:5471/6250 train_loss:2.3576 train_time:2247601ms step_avg:411.57ms step:5472/6250 train_loss:2.2903 train_time:2248003ms step_avg:411.57ms step:5473/6250 train_loss:2.2987 train_time:2248404ms step_avg:411.57ms step:5474/6250 train_loss:2.3216 train_time:2248804ms step_avg:411.57ms step:5475/6250 train_loss:2.2859 train_time:2249206ms step_avg:411.57ms step:5476/6250 train_loss:2.2863 train_time:2249610ms step_avg:411.56ms step:5477/6250 train_loss:2.3932 train_time:2250013ms step_avg:411.56ms step:5478/6250 train_loss:2.2340 train_time:2250414ms step_avg:411.56ms step:5479/6250 train_loss:2.2849 train_time:2250815ms step_avg:411.56ms step:5480/6250 train_loss:2.2997 train_time:2251217ms step_avg:411.56ms step:5481/6250 train_loss:2.3003 train_time:2251616ms step_avg:411.55ms step:5482/6250 train_loss:2.3138 train_time:2252017ms step_avg:411.55ms step:5483/6250 train_loss:2.3627 train_time:2252420ms step_avg:411.55ms step:5484/6250 train_loss:2.3334 train_time:2252825ms step_avg:411.55ms step:5485/6250 train_loss:2.3497 train_time:2253225ms step_avg:411.55ms step:5486/6250 train_loss:2.3282 train_time:2253627ms step_avg:411.55ms step:5487/6250 train_loss:2.2849 train_time:2254030ms step_avg:411.54ms step:5488/6250 train_loss:2.4307 train_time:2254428ms step_avg:411.54ms step:5489/6250 train_loss:2.3431 train_time:2254830ms step_avg:411.54ms step:5490/6250 train_loss:2.2803 train_time:2255232ms step_avg:411.54ms step:5491/6250 train_loss:2.2878 train_time:2255634ms step_avg:411.54ms step:5492/6250 train_loss:2.3041 train_time:2256038ms step_avg:411.54ms step:5493/6250 train_loss:2.3296 train_time:2256439ms step_avg:411.53ms step:5494/6250 train_loss:2.1883 train_time:2256840ms step_avg:411.53ms step:5495/6250 train_loss:2.2232 train_time:2257242ms step_avg:411.53ms step:5496/6250 train_loss:2.2348 train_time:2257644ms step_avg:411.53ms step:5497/6250 train_loss:2.3727 train_time:2258042ms step_avg:411.53ms step:5498/6250 train_loss:2.3092 train_time:2258444ms step_avg:411.52ms step:5499/6250 train_loss:2.2761 train_time:2258847ms step_avg:411.52ms step:5500/6250 train_loss:2.2994 train_time:2259249ms step_avg:411.52ms step:5501/6250 train_loss:2.3663 train_time:2259652ms step_avg:411.52ms step:5502/6250 train_loss:2.3465 train_time:2260053ms step_avg:411.52ms step:5503/6250 train_loss:2.3593 train_time:2260454ms step_avg:411.52ms step:5504/6250 train_loss:2.3591 train_time:2260857ms step_avg:411.51ms step:5505/6250 train_loss:2.3191 train_time:2261259ms step_avg:411.51ms step:5506/6250 train_loss:2.3351 train_time:2261661ms step_avg:411.51ms step:5507/6250 train_loss:2.3089 train_time:2262066ms step_avg:411.51ms step:5508/6250 train_loss:2.2775 train_time:2262464ms step_avg:411.51ms step:5509/6250 train_loss:2.2469 train_time:2262870ms step_avg:411.51ms step:5510/6250 train_loss:2.3883 train_time:2263270ms step_avg:411.50ms step:5511/6250 train_loss:2.3441 train_time:2263671ms step_avg:411.50ms step:5512/6250 train_loss:2.2852 train_time:2264073ms step_avg:411.50ms step:5513/6250 train_loss:2.4053 train_time:2264473ms step_avg:411.50ms step:5514/6250 train_loss:2.3344 train_time:2264875ms step_avg:411.50ms step:5515/6250 train_loss:2.2800 train_time:2265273ms step_avg:411.49ms step:5516/6250 train_loss:2.3660 train_time:2265675ms step_avg:411.49ms step:5517/6250 train_loss:2.2794 train_time:2266078ms step_avg:411.49ms step:5518/6250 train_loss:2.3632 train_time:2266477ms step_avg:411.49ms step:5519/6250 train_loss:2.3956 train_time:2266880ms step_avg:411.49ms step:5520/6250 train_loss:2.2565 train_time:2267283ms step_avg:411.49ms step:5521/6250 train_loss:2.4095 train_time:2267685ms step_avg:411.48ms step:5522/6250 train_loss:2.2766 train_time:2268087ms step_avg:411.48ms step:5523/6250 train_loss:2.2333 train_time:2268490ms step_avg:411.48ms step:5524/6250 train_loss:2.4360 train_time:2268889ms step_avg:411.48ms step:5525/6250 train_loss:2.3794 train_time:2269291ms step_avg:411.48ms step:5526/6250 train_loss:2.3241 train_time:2269694ms step_avg:411.47ms step:5527/6250 train_loss:2.3550 train_time:2270096ms step_avg:411.47ms step:5528/6250 train_loss:2.2789 train_time:2270498ms step_avg:411.47ms step:5529/6250 train_loss:2.4257 train_time:2270901ms step_avg:411.47ms step:5530/6250 train_loss:2.3107 train_time:2271303ms step_avg:411.47ms step:5531/6250 train_loss:2.3047 train_time:2271707ms step_avg:411.47ms step:5532/6250 train_loss:2.3300 train_time:2272112ms step_avg:411.47ms step:5533/6250 train_loss:2.3253 train_time:2272513ms step_avg:411.46ms step:5534/6250 train_loss:2.3515 train_time:2272916ms step_avg:411.46ms step:5535/6250 train_loss:2.3278 train_time:2273319ms step_avg:411.46ms step:5536/6250 train_loss:2.2760 train_time:2273720ms step_avg:411.46ms step:5537/6250 train_loss:2.3370 train_time:2274122ms step_avg:411.46ms step:5538/6250 train_loss:2.3914 train_time:2274521ms step_avg:411.45ms step:5539/6250 train_loss:2.3155 train_time:2274923ms step_avg:411.45ms step:5540/6250 train_loss:2.2393 train_time:2275324ms step_avg:411.45ms step:5541/6250 train_loss:2.2907 train_time:2275726ms step_avg:411.45ms step:5542/6250 train_loss:2.3689 train_time:2276126ms step_avg:411.45ms step:5543/6250 train_loss:2.3174 train_time:2276527ms step_avg:411.45ms step:5544/6250 train_loss:2.3845 train_time:2276930ms step_avg:411.44ms step:5545/6250 train_loss:2.2973 train_time:2277332ms step_avg:411.44ms step:5546/6250 train_loss:2.3309 train_time:2277734ms step_avg:411.44ms step:5547/6250 train_loss:2.3242 train_time:2278137ms step_avg:411.44ms step:5548/6250 train_loss:2.3181 train_time:2278539ms step_avg:411.44ms step:5549/6250 train_loss:2.4046 train_time:2278942ms step_avg:411.44ms step:5550/6250 train_loss:2.4135 train_time:2279339ms step_avg:411.43ms step:5551/6250 train_loss:2.3033 train_time:2279740ms step_avg:411.43ms step:5552/6250 train_loss:2.3376 train_time:2280142ms step_avg:411.43ms step:5553/6250 train_loss:2.3828 train_time:2280544ms step_avg:411.43ms step:5554/6250 train_loss:2.3452 train_time:2280947ms step_avg:411.43ms step:5555/6250 train_loss:2.3793 train_time:2281343ms step_avg:411.42ms step:5556/6250 train_loss:2.2877 train_time:2281746ms step_avg:411.42ms step:5557/6250 train_loss:2.3135 train_time:2282150ms step_avg:411.42ms step:5558/6250 train_loss:2.4250 train_time:2282556ms step_avg:411.42ms step:5559/6250 train_loss:2.3051 train_time:2282967ms step_avg:411.42ms step:5560/6250 train_loss:2.2849 train_time:2283366ms step_avg:411.42ms step:5561/6250 train_loss:2.3317 train_time:2283769ms step_avg:411.42ms step:5562/6250 train_loss:2.3722 train_time:2284170ms step_avg:411.41ms step:5563/6250 train_loss:2.2589 train_time:2284573ms step_avg:411.41ms step:5564/6250 train_loss:2.3294 train_time:2284977ms step_avg:411.41ms step:5565/6250 train_loss:2.3806 train_time:2285379ms step_avg:411.41ms step:5566/6250 train_loss:2.2421 train_time:2285780ms step_avg:411.41ms step:5567/6250 train_loss:2.4718 train_time:2286179ms step_avg:411.41ms step:5568/6250 train_loss:2.2505 train_time:2286580ms step_avg:411.40ms step:5569/6250 train_loss:2.3895 train_time:2286982ms step_avg:411.40ms step:5570/6250 train_loss:2.2965 train_time:2287384ms step_avg:411.40ms step:5571/6250 train_loss:2.2301 train_time:2287784ms step_avg:411.40ms step:5572/6250 train_loss:2.3579 train_time:2288186ms step_avg:411.40ms step:5573/6250 train_loss:2.4393 train_time:2288584ms step_avg:411.39ms step:5574/6250 train_loss:2.3556 train_time:2288986ms step_avg:411.39ms step:5575/6250 train_loss:2.3640 train_time:2289388ms step_avg:411.39ms step:5576/6250 train_loss:2.3145 train_time:2289791ms step_avg:411.39ms step:5577/6250 train_loss:2.3355 train_time:2290192ms step_avg:411.39ms step:5578/6250 train_loss:2.4167 train_time:2290593ms step_avg:411.39ms step:5579/6250 train_loss:2.3329 train_time:2290996ms step_avg:411.38ms step:5580/6250 train_loss:2.3762 train_time:2291394ms step_avg:411.38ms step:5581/6250 train_loss:2.2819 train_time:2291797ms step_avg:411.38ms step:5582/6250 train_loss:2.3188 train_time:2292199ms step_avg:411.38ms step:5583/6250 train_loss:2.3282 train_time:2292600ms step_avg:411.38ms step:5584/6250 train_loss:2.3273 train_time:2293001ms step_avg:411.37ms step:5585/6250 train_loss:2.3711 train_time:2293402ms step_avg:411.37ms step:5586/6250 train_loss:2.2989 train_time:2293801ms step_avg:411.37ms step:5587/6250 train_loss:2.3036 train_time:2294203ms step_avg:411.37ms step:5588/6250 train_loss:2.3139 train_time:2294605ms step_avg:411.37ms step:5589/6250 train_loss:2.2115 train_time:2295008ms step_avg:411.37ms step:5590/6250 train_loss:2.3416 train_time:2295410ms step_avg:411.36ms step:5591/6250 train_loss:2.2626 train_time:2295813ms step_avg:411.36ms step:5592/6250 train_loss:2.3320 train_time:2296215ms step_avg:411.36ms step:5593/6250 train_loss:2.3264 train_time:2296617ms step_avg:411.36ms step:5594/6250 train_loss:2.3082 train_time:2297018ms step_avg:411.36ms step:5595/6250 train_loss:2.3196 train_time:2297419ms step_avg:411.36ms step:5596/6250 train_loss:2.3689 train_time:2297822ms step_avg:411.35ms step:5597/6250 train_loss:2.3959 train_time:2298222ms step_avg:411.35ms step:5598/6250 train_loss:2.3211 train_time:2298626ms step_avg:411.35ms step:5599/6250 train_loss:2.4124 train_time:2299029ms step_avg:411.35ms step:5600/6250 train_loss:2.3302 train_time:2299431ms step_avg:411.35ms step:5601/6250 train_loss:2.2870 train_time:2299831ms step_avg:411.35ms step:5602/6250 train_loss:2.3448 train_time:2300228ms step_avg:411.34ms step:5603/6250 train_loss:2.2714 train_time:2300636ms step_avg:411.34ms step:5604/6250 train_loss:2.4222 train_time:2301043ms step_avg:411.34ms step:5605/6250 train_loss:2.3654 train_time:2301442ms step_avg:411.34ms step:5606/6250 train_loss:2.2926 train_time:2301849ms step_avg:411.34ms step:5607/6250 train_loss:2.3887 train_time:2302251ms step_avg:411.34ms step:5608/6250 train_loss:2.2952 train_time:2302654ms step_avg:411.34ms step:5609/6250 train_loss:2.3525 train_time:2303054ms step_avg:411.33ms step:5610/6250 train_loss:2.3170 train_time:2303454ms step_avg:411.33ms step:5611/6250 train_loss:2.1984 train_time:2303857ms step_avg:411.33ms step:5612/6250 train_loss:2.3841 train_time:2304260ms step_avg:411.33ms step:5613/6250 train_loss:2.3620 train_time:2304662ms step_avg:411.33ms step:5614/6250 train_loss:2.3497 train_time:2305064ms step_avg:411.32ms step:5615/6250 train_loss:2.3025 train_time:2305465ms step_avg:411.32ms step:5616/6250 train_loss:2.3764 train_time:2305869ms step_avg:411.32ms step:5617/6250 train_loss:2.4781 train_time:2306270ms step_avg:411.32ms step:5618/6250 train_loss:2.2958 train_time:2306671ms step_avg:411.32ms step:5619/6250 train_loss:2.3509 train_time:2307074ms step_avg:411.32ms step:5620/6250 train_loss:2.2890 train_time:2307477ms step_avg:411.32ms step:5621/6250 train_loss:2.2130 train_time:2307879ms step_avg:411.31ms step:5622/6250 train_loss:2.3142 train_time:2308282ms step_avg:411.31ms step:5623/6250 train_loss:2.3154 train_time:2308685ms step_avg:411.31ms step:5624/6250 train_loss:2.2793 train_time:2309088ms step_avg:411.31ms step:5625/6250 train_loss:2.2446 train_time:2309488ms step_avg:411.31ms step:5626/6250 train_loss:2.3220 train_time:2309888ms step_avg:411.30ms step:5627/6250 train_loss:2.3323 train_time:2310290ms step_avg:411.30ms step:5628/6250 train_loss:2.3136 train_time:2310692ms step_avg:411.30ms step:5629/6250 train_loss:2.3437 train_time:2311094ms step_avg:411.30ms step:5630/6250 train_loss:2.4960 train_time:2311495ms step_avg:411.30ms step:5631/6250 train_loss:2.3020 train_time:2311899ms step_avg:411.30ms step:5632/6250 train_loss:2.2624 train_time:2312301ms step_avg:411.30ms step:5633/6250 train_loss:2.3301 train_time:2312705ms step_avg:411.29ms step:5634/6250 train_loss:2.3699 train_time:2313107ms step_avg:411.29ms step:5635/6250 train_loss:2.3181 train_time:2313506ms step_avg:411.29ms step:5636/6250 train_loss:2.3505 train_time:2313908ms step_avg:411.29ms step:5637/6250 train_loss:2.2794 train_time:2314309ms step_avg:411.29ms step:5638/6250 train_loss:2.3791 train_time:2314711ms step_avg:411.28ms step:5639/6250 train_loss:2.3836 train_time:2315113ms step_avg:411.28ms step:5640/6250 train_loss:2.3176 train_time:2315512ms step_avg:411.28ms step:5641/6250 train_loss:2.4017 train_time:2315914ms step_avg:411.28ms step:5642/6250 train_loss:2.3186 train_time:2316314ms step_avg:411.28ms step:5643/6250 train_loss:2.3353 train_time:2316725ms step_avg:411.28ms step:5644/6250 train_loss:2.3050 train_time:2317145ms step_avg:411.28ms step:5645/6250 train_loss:2.3672 train_time:2317562ms step_avg:411.28ms step:5646/6250 train_loss:2.3469 train_time:2317964ms step_avg:411.28ms step:5647/6250 train_loss:2.3212 train_time:2318365ms step_avg:411.28ms step:5648/6250 train_loss:2.3585 train_time:2318767ms step_avg:411.27ms step:5649/6250 train_loss:2.3397 train_time:2319164ms step_avg:411.27ms step:5650/6250 train_loss:2.2655 train_time:2319565ms step_avg:411.27ms step:5651/6250 train_loss:2.2861 train_time:2319967ms step_avg:411.27ms step:5652/6250 train_loss:2.3530 train_time:2320368ms step_avg:411.27ms step:5653/6250 train_loss:2.3008 train_time:2320770ms step_avg:411.27ms step:5654/6250 train_loss:2.3800 train_time:2321167ms step_avg:411.26ms step:5655/6250 train_loss:2.3201 train_time:2321567ms step_avg:411.26ms step:5656/6250 train_loss:2.3179 train_time:2321969ms step_avg:411.26ms step:5657/6250 train_loss:2.4303 train_time:2322371ms step_avg:411.26ms step:5658/6250 train_loss:2.3829 train_time:2322773ms step_avg:411.26ms step:5659/6250 train_loss:2.3582 train_time:2323174ms step_avg:411.25ms step:5660/6250 train_loss:2.4392 train_time:2323576ms step_avg:411.25ms step:5661/6250 train_loss:2.3191 train_time:2323975ms step_avg:411.25ms step:5662/6250 train_loss:2.3685 train_time:2324375ms step_avg:411.25ms step:5663/6250 train_loss:2.3550 train_time:2324777ms step_avg:411.25ms step:5664/6250 train_loss:2.2268 train_time:2325179ms step_avg:411.25ms step:5665/6250 train_loss:2.2689 train_time:2325582ms step_avg:411.24ms step:5666/6250 train_loss:2.3025 train_time:2325986ms step_avg:411.24ms step:5667/6250 train_loss:2.2268 train_time:2326385ms step_avg:411.24ms step:5668/6250 train_loss:2.3744 train_time:2326785ms step_avg:411.24ms step:5669/6250 train_loss:2.3547 train_time:2327188ms step_avg:411.24ms step:5670/6250 train_loss:2.2770 train_time:2327591ms step_avg:411.24ms step:5671/6250 train_loss:2.2945 train_time:2327995ms step_avg:411.23ms step:5672/6250 train_loss:2.3149 train_time:2328397ms step_avg:411.23ms step:5673/6250 train_loss:2.2376 train_time:2328799ms step_avg:411.23ms step:5674/6250 train_loss:2.3243 train_time:2329200ms step_avg:411.23ms step:5675/6250 train_loss:2.3524 train_time:2329600ms step_avg:411.23ms step:5676/6250 train_loss:2.2778 train_time:2330000ms step_avg:411.22ms step:5677/6250 train_loss:2.2452 train_time:2330400ms step_avg:411.22ms step:5678/6250 train_loss:2.3704 train_time:2330805ms step_avg:411.22ms step:5679/6250 train_loss:2.3208 train_time:2331206ms step_avg:411.22ms step:5680/6250 train_loss:2.3870 train_time:2331608ms step_avg:411.22ms step:5681/6250 train_loss:2.3814 train_time:2332006ms step_avg:411.22ms step:5682/6250 train_loss:2.2562 train_time:2332408ms step_avg:411.21ms step:5683/6250 train_loss:2.3393 train_time:2332810ms step_avg:411.21ms step:5684/6250 train_loss:2.3588 train_time:2333210ms step_avg:411.21ms step:5685/6250 train_loss:2.3053 train_time:2333611ms step_avg:411.21ms step:5686/6250 train_loss:2.3263 train_time:2334013ms step_avg:411.21ms step:5687/6250 train_loss:2.2754 train_time:2334413ms step_avg:411.21ms step:5688/6250 train_loss:2.3163 train_time:2334811ms step_avg:411.20ms step:5689/6250 train_loss:2.2966 train_time:2335212ms step_avg:411.20ms step:5690/6250 train_loss:2.2650 train_time:2335614ms step_avg:411.20ms step:5691/6250 train_loss:2.2813 train_time:2336016ms step_avg:411.20ms step:5692/6250 train_loss:2.3649 train_time:2336413ms step_avg:411.20ms step:5693/6250 train_loss:2.2991 train_time:2336815ms step_avg:411.19ms step:5694/6250 train_loss:2.3535 train_time:2337219ms step_avg:411.19ms step:5695/6250 train_loss:2.2891 train_time:2337624ms step_avg:411.19ms step:5696/6250 train_loss:2.2578 train_time:2338026ms step_avg:411.19ms step:5697/6250 train_loss:2.3671 train_time:2338427ms step_avg:411.19ms step:5698/6250 train_loss:2.3390 train_time:2338831ms step_avg:411.19ms step:5699/6250 train_loss:2.3638 train_time:2339233ms step_avg:411.19ms step:5700/6250 train_loss:2.3358 train_time:2339635ms step_avg:411.18ms step:5701/6250 train_loss:2.2420 train_time:2340037ms step_avg:411.18ms step:5702/6250 train_loss:2.3058 train_time:2340439ms step_avg:411.18ms step:5703/6250 train_loss:2.2707 train_time:2340842ms step_avg:411.18ms step:5704/6250 train_loss:2.3404 train_time:2341243ms step_avg:411.18ms step:5705/6250 train_loss:2.2432 train_time:2341645ms step_avg:411.18ms step:5706/6250 train_loss:2.3766 train_time:2342044ms step_avg:411.17ms step:5707/6250 train_loss:2.3480 train_time:2342444ms step_avg:411.17ms step:5708/6250 train_loss:2.3193 train_time:2342848ms step_avg:411.17ms step:5709/6250 train_loss:2.3092 train_time:2343250ms step_avg:411.17ms step:5710/6250 train_loss:2.2606 train_time:2343652ms step_avg:411.17ms step:5711/6250 train_loss:2.2956 train_time:2344055ms step_avg:411.17ms step:5712/6250 train_loss:2.2528 train_time:2344457ms step_avg:411.16ms step:5713/6250 train_loss:2.2800 train_time:2344860ms step_avg:411.16ms step:5714/6250 train_loss:2.3073 train_time:2345265ms step_avg:411.16ms step:5715/6250 train_loss:2.2374 train_time:2345676ms step_avg:411.16ms step:5716/6250 train_loss:2.3286 train_time:2346082ms step_avg:411.16ms step:5717/6250 train_loss:2.2442 train_time:2346480ms step_avg:411.16ms step:5718/6250 train_loss:2.3392 train_time:2346881ms step_avg:411.16ms step:5719/6250 train_loss:2.4308 train_time:2347283ms step_avg:411.15ms step:5720/6250 train_loss:2.2631 train_time:2347688ms step_avg:411.15ms step:5721/6250 train_loss:2.2844 train_time:2348091ms step_avg:411.15ms step:5722/6250 train_loss:2.3897 train_time:2348496ms step_avg:411.15ms step:5723/6250 train_loss:2.2746 train_time:2348900ms step_avg:411.15ms step:5724/6250 train_loss:2.3181 train_time:2349301ms step_avg:411.15ms step:5725/6250 train_loss:2.2514 train_time:2349704ms step_avg:411.15ms step:5726/6250 train_loss:2.2471 train_time:2350107ms step_avg:411.15ms step:5727/6250 train_loss:2.3370 train_time:2350508ms step_avg:411.14ms step:5728/6250 train_loss:2.3032 train_time:2350910ms step_avg:411.14ms step:5729/6250 train_loss:2.3131 train_time:2351310ms step_avg:411.14ms step:5730/6250 train_loss:2.3324 train_time:2351711ms step_avg:411.14ms step:5731/6250 train_loss:2.3464 train_time:2352112ms step_avg:411.14ms step:5732/6250 train_loss:2.4020 train_time:2352513ms step_avg:411.13ms step:5733/6250 train_loss:2.2322 train_time:2352915ms step_avg:411.13ms step:5734/6250 train_loss:2.3605 train_time:2353311ms step_avg:411.13ms step:5735/6250 train_loss:2.4063 train_time:2353712ms step_avg:411.13ms step:5736/6250 train_loss:2.3266 train_time:2354112ms step_avg:411.13ms step:5737/6250 train_loss:2.3690 train_time:2354508ms step_avg:411.12ms step:5738/6250 train_loss:2.3333 train_time:2354910ms step_avg:411.12ms step:5739/6250 train_loss:2.3265 train_time:2355312ms step_avg:411.12ms step:5740/6250 train_loss:2.3185 train_time:2355715ms step_avg:411.12ms step:5741/6250 train_loss:2.4211 train_time:2356118ms step_avg:411.12ms step:5742/6250 train_loss:2.3942 train_time:2356520ms step_avg:411.12ms step:5743/6250 train_loss:2.3744 train_time:2356922ms step_avg:411.11ms step:5744/6250 train_loss:2.2895 train_time:2357324ms step_avg:411.11ms step:5745/6250 train_loss:2.3056 train_time:2357723ms step_avg:411.11ms step:5746/6250 train_loss:2.3311 train_time:2358125ms step_avg:411.11ms step:5747/6250 train_loss:2.3864 train_time:2358527ms step_avg:411.11ms step:5748/6250 train_loss:2.3052 train_time:2358931ms step_avg:411.11ms step:5749/6250 train_loss:2.3860 train_time:2359332ms step_avg:411.11ms step:5750/6250 train_loss:2.3211 train_time:2359731ms step_avg:411.10ms step:5751/6250 train_loss:2.3383 train_time:2360132ms step_avg:411.10ms step:5752/6250 train_loss:2.3316 train_time:2360533ms step_avg:411.10ms step:5753/6250 train_loss:2.2661 train_time:2360936ms step_avg:411.10ms step:5754/6250 train_loss:2.2823 train_time:2361336ms step_avg:411.10ms step:5755/6250 train_loss:2.3714 train_time:2361740ms step_avg:411.09ms step:5756/6250 train_loss:2.3708 train_time:2362142ms step_avg:411.09ms step:5757/6250 train_loss:2.2953 train_time:2362544ms step_avg:411.09ms step:5758/6250 train_loss:2.3330 train_time:2362946ms step_avg:411.09ms step:5759/6250 train_loss:2.2940 train_time:2363345ms step_avg:411.09ms step:5760/6250 train_loss:2.4149 train_time:2363747ms step_avg:411.09ms step:5761/6250 train_loss:2.3755 train_time:2364149ms step_avg:411.08ms step:5762/6250 train_loss:2.2938 train_time:2364550ms step_avg:411.08ms step:5763/6250 train_loss:2.4068 train_time:2364953ms step_avg:411.08ms step:5764/6250 train_loss:2.4064 train_time:2365354ms step_avg:411.08ms step:5765/6250 train_loss:2.3029 train_time:2365753ms step_avg:411.08ms step:5766/6250 train_loss:2.3024 train_time:2366154ms step_avg:411.08ms step:5767/6250 train_loss:2.4077 train_time:2366557ms step_avg:411.07ms step:5768/6250 train_loss:2.5130 train_time:2366960ms step_avg:411.07ms step:5769/6250 train_loss:2.3612 train_time:2367362ms step_avg:411.07ms step:5770/6250 train_loss:2.2386 train_time:2367764ms step_avg:411.07ms step:5771/6250 train_loss:2.3468 train_time:2368163ms step_avg:411.07ms step:5772/6250 train_loss:2.3332 train_time:2368562ms step_avg:411.07ms step:5773/6250 train_loss:2.3255 train_time:2368964ms step_avg:411.06ms step:5774/6250 train_loss:2.3950 train_time:2369364ms step_avg:411.06ms step:5775/6250 train_loss:2.3327 train_time:2369763ms step_avg:411.06ms step:5776/6250 train_loss:2.3703 train_time:2370164ms step_avg:411.06ms step:5777/6250 train_loss:2.2856 train_time:2370567ms step_avg:411.06ms step:5778/6250 train_loss:2.3097 train_time:2370968ms step_avg:411.06ms step:5779/6250 train_loss:2.3523 train_time:2371370ms step_avg:411.05ms step:5780/6250 train_loss:2.2905 train_time:2371772ms step_avg:411.05ms step:5781/6250 train_loss:2.2714 train_time:2372170ms step_avg:411.05ms step:5782/6250 train_loss:2.3713 train_time:2372570ms step_avg:411.05ms step:5783/6250 train_loss:2.3372 train_time:2372974ms step_avg:411.05ms step:5784/6250 train_loss:2.2342 train_time:2373376ms step_avg:411.05ms step:5785/6250 train_loss:2.2966 train_time:2373778ms step_avg:411.04ms step:5786/6250 train_loss:2.3193 train_time:2374180ms step_avg:411.04ms step:5787/6250 train_loss:2.3456 train_time:2374577ms step_avg:411.04ms step:5788/6250 train_loss:2.4197 train_time:2374979ms step_avg:411.04ms step:5789/6250 train_loss:2.4550 train_time:2375380ms step_avg:411.04ms step:5790/6250 train_loss:2.2875 train_time:2375783ms step_avg:411.04ms step:5791/6250 train_loss:2.3167 train_time:2376183ms step_avg:411.03ms step:5792/6250 train_loss:2.2542 train_time:2376583ms step_avg:411.03ms step:5793/6250 train_loss:2.3530 train_time:2376983ms step_avg:411.03ms step:5794/6250 train_loss:2.3032 train_time:2377383ms step_avg:411.03ms step:5795/6250 train_loss:2.2691 train_time:2377787ms step_avg:411.03ms step:5796/6250 train_loss:2.3216 train_time:2378189ms step_avg:411.02ms step:5797/6250 train_loss:2.2901 train_time:2378589ms step_avg:411.02ms step:5798/6250 train_loss:2.3036 train_time:2378991ms step_avg:411.02ms step:5799/6250 train_loss:2.2206 train_time:2379390ms step_avg:411.02ms step:5800/6250 train_loss:2.2681 train_time:2379793ms step_avg:411.02ms step:5801/6250 train_loss:2.2826 train_time:2380194ms step_avg:411.02ms step:5802/6250 train_loss:2.3085 train_time:2380600ms step_avg:411.02ms step:5803/6250 train_loss:2.3664 train_time:2381010ms step_avg:411.02ms step:5804/6250 train_loss:2.2850 train_time:2381410ms step_avg:411.01ms step:5805/6250 train_loss:2.3928 train_time:2381810ms step_avg:411.01ms step:5806/6250 train_loss:2.3448 train_time:2382212ms step_avg:411.01ms step:5807/6250 train_loss:2.2837 train_time:2382614ms step_avg:411.01ms step:5808/6250 train_loss:2.2459 train_time:2383017ms step_avg:411.01ms step:5809/6250 train_loss:2.2859 train_time:2383417ms step_avg:411.00ms step:5810/6250 train_loss:2.2810 train_time:2383817ms step_avg:411.00ms step:5811/6250 train_loss:2.3337 train_time:2384218ms step_avg:411.00ms step:5812/6250 train_loss:2.3480 train_time:2384619ms step_avg:411.00ms step:5813/6250 train_loss:2.2972 train_time:2385020ms step_avg:411.00ms step:5814/6250 train_loss:2.3071 train_time:2385420ms step_avg:411.00ms step:5815/6250 train_loss:2.3104 train_time:2385824ms step_avg:410.99ms step:5816/6250 train_loss:2.2477 train_time:2386220ms step_avg:410.99ms step:5817/6250 train_loss:2.2837 train_time:2386623ms step_avg:410.99ms step:5818/6250 train_loss:2.3617 train_time:2387026ms step_avg:410.99ms step:5819/6250 train_loss:2.2373 train_time:2387428ms step_avg:410.99ms step:5820/6250 train_loss:2.3215 train_time:2387830ms step_avg:410.99ms step:5821/6250 train_loss:2.2612 train_time:2388233ms step_avg:410.98ms step:5822/6250 train_loss:2.4291 train_time:2388635ms step_avg:410.98ms step:5823/6250 train_loss:2.3239 train_time:2389037ms step_avg:410.98ms step:5824/6250 train_loss:2.3840 train_time:2389439ms step_avg:410.98ms step:5825/6250 train_loss:2.3250 train_time:2389841ms step_avg:410.98ms step:5826/6250 train_loss:2.3225 train_time:2390242ms step_avg:410.98ms step:5827/6250 train_loss:2.2749 train_time:2390643ms step_avg:410.98ms step:5828/6250 train_loss:2.2576 train_time:2391044ms step_avg:410.97ms step:5829/6250 train_loss:2.2497 train_time:2391445ms step_avg:410.97ms step:5830/6250 train_loss:2.3492 train_time:2391847ms step_avg:410.97ms step:5831/6250 train_loss:2.2307 train_time:2392249ms step_avg:410.97ms step:5832/6250 train_loss:2.2266 train_time:2392657ms step_avg:410.97ms step:5833/6250 train_loss:2.3000 train_time:2393060ms step_avg:410.97ms step:5834/6250 train_loss:2.2673 train_time:2393461ms step_avg:410.97ms step:5835/6250 train_loss:2.2437 train_time:2393863ms step_avg:410.96ms step:5836/6250 train_loss:2.2952 train_time:2394261ms step_avg:410.96ms step:5837/6250 train_loss:2.4047 train_time:2394662ms step_avg:410.96ms step:5838/6250 train_loss:2.3199 train_time:2395064ms step_avg:410.96ms step:5839/6250 train_loss:2.4117 train_time:2395465ms step_avg:410.96ms step:5840/6250 train_loss:2.2240 train_time:2395868ms step_avg:410.96ms step:5841/6250 train_loss:2.2847 train_time:2396268ms step_avg:410.95ms step:5842/6250 train_loss:2.3037 train_time:2396669ms step_avg:410.95ms step:5843/6250 train_loss:2.2805 train_time:2397069ms step_avg:410.95ms step:5844/6250 train_loss:2.2715 train_time:2397468ms step_avg:410.95ms step:5845/6250 train_loss:2.2831 train_time:2397870ms step_avg:410.95ms step:5846/6250 train_loss:2.3366 train_time:2398267ms step_avg:410.94ms step:5847/6250 train_loss:2.3726 train_time:2398670ms step_avg:410.94ms step:5848/6250 train_loss:2.2949 train_time:2399072ms step_avg:410.94ms step:5849/6250 train_loss:2.2670 train_time:2399477ms step_avg:410.94ms step:5850/6250 train_loss:2.3476 train_time:2399878ms step_avg:410.94ms step:5851/6250 train_loss:2.2402 train_time:2400279ms step_avg:410.94ms step:5852/6250 train_loss:2.3449 train_time:2400682ms step_avg:410.93ms step:5853/6250 train_loss:2.3082 train_time:2401085ms step_avg:410.93ms step:5854/6250 train_loss:2.2855 train_time:2401490ms step_avg:410.93ms step:5855/6250 train_loss:2.3930 train_time:2401897ms step_avg:410.93ms step:5856/6250 train_loss:2.2764 train_time:2402310ms step_avg:410.93ms step:5857/6250 train_loss:2.3135 train_time:2402743ms step_avg:410.94ms step:5858/6250 train_loss:2.3203 train_time:2403164ms step_avg:410.94ms step:5859/6250 train_loss:2.2857 train_time:2403566ms step_avg:410.94ms step:5860/6250 train_loss:2.2458 train_time:2403972ms step_avg:410.94ms step:5861/6250 train_loss:2.4708 train_time:2404374ms step_avg:410.93ms step:5862/6250 train_loss:2.2519 train_time:2404777ms step_avg:410.93ms step:5863/6250 train_loss:2.3141 train_time:2405177ms step_avg:410.93ms step:5864/6250 train_loss:2.2565 train_time:2405578ms step_avg:410.93ms step:5865/6250 train_loss:2.3503 train_time:2405985ms step_avg:410.93ms step:5866/6250 train_loss:2.3154 train_time:2406390ms step_avg:410.93ms step:5867/6250 train_loss:2.2957 train_time:2406794ms step_avg:410.93ms step:5868/6250 train_loss:2.3780 train_time:2407205ms step_avg:410.93ms step:5869/6250 train_loss:2.3855 train_time:2407615ms step_avg:410.93ms step:5870/6250 train_loss:2.3356 train_time:2408020ms step_avg:410.92ms step:5871/6250 train_loss:2.3153 train_time:2408423ms step_avg:410.92ms step:5872/6250 train_loss:2.3741 train_time:2408828ms step_avg:410.92ms step:5873/6250 train_loss:2.2930 train_time:2409260ms step_avg:410.93ms step:5874/6250 train_loss:2.3108 train_time:2409669ms step_avg:410.93ms step:5875/6250 train_loss:2.2703 train_time:2410095ms step_avg:410.93ms step:5876/6250 train_loss:2.3733 train_time:2410516ms step_avg:410.93ms step:5877/6250 train_loss:2.3530 train_time:2410934ms step_avg:410.93ms step:5878/6250 train_loss:2.3222 train_time:2411339ms step_avg:410.93ms step:5879/6250 train_loss:2.3080 train_time:2411741ms step_avg:410.93ms step:5880/6250 train_loss:2.2619 train_time:2412147ms step_avg:410.93ms step:5881/6250 train_loss:2.2863 train_time:2412547ms step_avg:410.93ms step:5882/6250 train_loss:2.3011 train_time:2412950ms step_avg:410.92ms step:5883/6250 train_loss:2.2586 train_time:2413364ms step_avg:410.93ms step:5884/6250 train_loss:2.3864 train_time:2413786ms step_avg:410.93ms step:5885/6250 train_loss:2.2202 train_time:2414197ms step_avg:410.93ms step:5886/6250 train_loss:2.4113 train_time:2414605ms step_avg:410.93ms step:5887/6250 train_loss:2.4358 train_time:2415015ms step_avg:410.93ms step:5888/6250 train_loss:2.3918 train_time:2415421ms step_avg:410.93ms step:5889/6250 train_loss:2.2767 train_time:2415826ms step_avg:410.92ms step:5890/6250 train_loss:2.3822 train_time:2416236ms step_avg:410.92ms step:5891/6250 train_loss:2.2569 train_time:2416642ms step_avg:410.92ms step:5892/6250 train_loss:2.2017 train_time:2417051ms step_avg:410.92ms step:5893/6250 train_loss:2.3939 train_time:2417457ms step_avg:410.92ms step:5894/6250 train_loss:2.2740 train_time:2417860ms step_avg:410.92ms step:5895/6250 train_loss:2.3560 train_time:2418261ms step_avg:410.92ms step:5896/6250 train_loss:2.3061 train_time:2418666ms step_avg:410.92ms step:5897/6250 train_loss:2.4486 train_time:2419078ms step_avg:410.92ms step:5898/6250 train_loss:2.3171 train_time:2419486ms step_avg:410.92ms step:5899/6250 train_loss:2.2863 train_time:2419894ms step_avg:410.92ms step:5900/6250 train_loss:2.3296 train_time:2420308ms step_avg:410.92ms step:5901/6250 train_loss:2.4022 train_time:2420735ms step_avg:410.92ms step:5902/6250 train_loss:2.3339 train_time:2421169ms step_avg:410.92ms step:5903/6250 train_loss:2.3080 train_time:2421606ms step_avg:410.93ms step:5904/6250 train_loss:2.3289 train_time:2422035ms step_avg:410.93ms step:5905/6250 train_loss:2.4378 train_time:2422473ms step_avg:410.94ms step:5906/6250 train_loss:2.3657 train_time:2422911ms step_avg:410.94ms step:5907/6250 train_loss:2.3903 train_time:2423327ms step_avg:410.94ms step:5908/6250 train_loss:2.2715 train_time:2423731ms step_avg:410.94ms step:5909/6250 train_loss:2.2646 train_time:2424153ms step_avg:410.94ms step:5910/6250 train_loss:2.2898 train_time:2424565ms step_avg:410.94ms step:5911/6250 train_loss:2.2122 train_time:2424973ms step_avg:410.94ms step:5912/6250 train_loss:2.2729 train_time:2425382ms step_avg:410.94ms step:5913/6250 train_loss:2.4721 train_time:2425790ms step_avg:410.94ms step:5914/6250 train_loss:2.4248 train_time:2426201ms step_avg:410.94ms step:5915/6250 train_loss:2.2160 train_time:2426615ms step_avg:410.94ms step:5916/6250 train_loss:2.3165 train_time:2427038ms step_avg:410.94ms step:5917/6250 train_loss:2.2932 train_time:2427466ms step_avg:410.95ms step:5918/6250 train_loss:2.3059 train_time:2427891ms step_avg:410.95ms step:5919/6250 train_loss:2.2647 train_time:2428292ms step_avg:410.95ms step:5920/6250 train_loss:2.2533 train_time:2428691ms step_avg:410.95ms step:5921/6250 train_loss:2.3477 train_time:2429092ms step_avg:410.94ms step:5922/6250 train_loss:2.2858 train_time:2429491ms step_avg:410.94ms step:5923/6250 train_loss:2.3030 train_time:2429907ms step_avg:410.94ms step:5924/6250 train_loss:2.3682 train_time:2430308ms step_avg:410.94ms step:5925/6250 train_loss:2.3375 train_time:2430710ms step_avg:410.94ms step:5926/6250 train_loss:2.3592 train_time:2431108ms step_avg:410.94ms step:5927/6250 train_loss:2.2652 train_time:2431508ms step_avg:410.94ms step:5928/6250 train_loss:2.3043 train_time:2431921ms step_avg:410.94ms step:5929/6250 train_loss:2.3300 train_time:2432340ms step_avg:410.94ms step:5930/6250 train_loss:2.2817 train_time:2432744ms step_avg:410.94ms step:5931/6250 train_loss:2.2846 train_time:2433142ms step_avg:410.93ms step:5932/6250 train_loss:2.2517 train_time:2433543ms step_avg:410.93ms step:5933/6250 train_loss:2.2981 train_time:2433945ms step_avg:410.93ms step:5934/6250 train_loss:2.3010 train_time:2434345ms step_avg:410.93ms step:5935/6250 train_loss:2.3853 train_time:2434746ms step_avg:410.93ms step:5936/6250 train_loss:2.2917 train_time:2435145ms step_avg:410.93ms step:5937/6250 train_loss:2.3705 train_time:2435543ms step_avg:410.92ms step:5938/6250 train_loss:2.2841 train_time:2435963ms step_avg:410.92ms step:5939/6250 train_loss:2.2682 train_time:2436364ms step_avg:410.92ms step:5940/6250 train_loss:2.2949 train_time:2436765ms step_avg:410.92ms step:5941/6250 train_loss:2.3391 train_time:2437163ms step_avg:410.92ms step:5942/6250 train_loss:2.2926 train_time:2437564ms step_avg:410.92ms step:5943/6250 train_loss:2.2943 train_time:2437966ms step_avg:410.92ms step:5944/6250 train_loss:2.3075 train_time:2438365ms step_avg:410.91ms step:5945/6250 train_loss:2.3437 train_time:2438767ms step_avg:410.91ms step:5946/6250 train_loss:2.3660 train_time:2439169ms step_avg:410.91ms step:5947/6250 train_loss:2.3184 train_time:2439565ms step_avg:410.91ms step:5948/6250 train_loss:2.2923 train_time:2439966ms step_avg:410.91ms step:5949/6250 train_loss:2.2867 train_time:2440369ms step_avg:410.91ms step:5950/6250 train_loss:2.3460 train_time:2440771ms step_avg:410.90ms step:5951/6250 train_loss:2.3087 train_time:2441178ms step_avg:410.90ms step:5952/6250 train_loss:2.2391 train_time:2441580ms step_avg:410.90ms step:5953/6250 train_loss:2.2586 train_time:2441982ms step_avg:410.90ms step:5954/6250 train_loss:2.2744 train_time:2442383ms step_avg:410.90ms step:5955/6250 train_loss:2.3135 train_time:2442785ms step_avg:410.90ms step:5956/6250 train_loss:2.2878 train_time:2443185ms step_avg:410.90ms step:5957/6250 train_loss:2.3016 train_time:2443584ms step_avg:410.89ms step:5958/6250 train_loss:2.2781 train_time:2443986ms step_avg:410.89ms step:5959/6250 train_loss:2.2556 train_time:2444386ms step_avg:410.89ms step:5960/6250 train_loss:2.4633 train_time:2444789ms step_avg:410.89ms step:5961/6250 train_loss:2.2481 train_time:2445190ms step_avg:410.89ms step:5962/6250 train_loss:2.2893 train_time:2445591ms step_avg:410.89ms step:5963/6250 train_loss:2.2354 train_time:2445993ms step_avg:410.88ms step:5964/6250 train_loss:2.3244 train_time:2446394ms step_avg:410.88ms step:5965/6250 train_loss:2.2938 train_time:2446798ms step_avg:410.88ms step:5966/6250 train_loss:2.2573 train_time:2447199ms step_avg:410.88ms step:5967/6250 train_loss:2.3449 train_time:2447599ms step_avg:410.88ms step:5968/6250 train_loss:2.3300 train_time:2448003ms step_avg:410.88ms step:5969/6250 train_loss:2.3789 train_time:2448401ms step_avg:410.87ms step:5970/6250 train_loss:2.2357 train_time:2448804ms step_avg:410.87ms step:5971/6250 train_loss:2.2822 train_time:2449205ms step_avg:410.87ms step:5972/6250 train_loss:2.2766 train_time:2449607ms step_avg:410.87ms step:5973/6250 train_loss:2.4030 train_time:2450030ms step_avg:410.87ms step:5974/6250 train_loss:2.2478 train_time:2450431ms step_avg:410.87ms step:5975/6250 train_loss:2.2560 train_time:2450834ms step_avg:410.87ms step:5976/6250 train_loss:2.3253 train_time:2451236ms step_avg:410.87ms step:5977/6250 train_loss:2.2843 train_time:2451638ms step_avg:410.87ms step:5978/6250 train_loss:2.3103 train_time:2452041ms step_avg:410.86ms step:5979/6250 train_loss:2.2835 train_time:2452442ms step_avg:410.86ms step:5980/6250 train_loss:2.2811 train_time:2452847ms step_avg:410.86ms step:5981/6250 train_loss:2.3517 train_time:2453249ms step_avg:410.86ms step:5982/6250 train_loss:2.3741 train_time:2453651ms step_avg:410.86ms step:5983/6250 train_loss:2.3701 train_time:2454050ms step_avg:410.86ms step:5984/6250 train_loss:2.2945 train_time:2454451ms step_avg:410.86ms step:5985/6250 train_loss:2.2802 train_time:2454853ms step_avg:410.85ms step:5986/6250 train_loss:2.3632 train_time:2455259ms step_avg:410.85ms step:5987/6250 train_loss:2.3105 train_time:2455673ms step_avg:410.85ms step:5988/6250 train_loss:2.4106 train_time:2456079ms step_avg:410.85ms step:5989/6250 train_loss:2.2424 train_time:2456484ms step_avg:410.85ms step:5990/6250 train_loss:2.2689 train_time:2456887ms step_avg:410.85ms step:5991/6250 train_loss:2.2668 train_time:2457286ms step_avg:410.85ms step:5992/6250 train_loss:2.3585 train_time:2457688ms step_avg:410.85ms step:5993/6250 train_loss:2.3028 train_time:2458088ms step_avg:410.85ms step:5994/6250 train_loss:2.2639 train_time:2458490ms step_avg:410.84ms step:5995/6250 train_loss:2.3515 train_time:2458895ms step_avg:410.84ms step:5996/6250 train_loss:2.2716 train_time:2459300ms step_avg:410.84ms step:5997/6250 train_loss:2.2100 train_time:2459702ms step_avg:410.84ms step:5998/6250 train_loss:2.3006 train_time:2460106ms step_avg:410.84ms step:5999/6250 train_loss:2.2630 train_time:2460508ms step_avg:410.84ms step:6000/6250 train_loss:2.3371 train_time:2460911ms step_avg:410.84ms step:6000/6250 val_loss:2.3029 train_time:2460912ms step_avg:410.84ms step:6001/6250 train_loss:2.3459 train_time:2461316ms step_avg:410.84ms step:6002/6250 train_loss:2.3326 train_time:2461736ms step_avg:410.84ms step:6003/6250 train_loss:2.2711 train_time:2462138ms step_avg:410.84ms step:6004/6250 train_loss:2.3647 train_time:2462539ms step_avg:410.83ms step:6005/6250 train_loss:2.3019 train_time:2462940ms step_avg:410.83ms step:6006/6250 train_loss:2.3601 train_time:2463339ms step_avg:410.83ms step:6007/6250 train_loss:2.4217 train_time:2463739ms step_avg:410.83ms step:6008/6250 train_loss:2.3950 train_time:2464146ms step_avg:410.83ms step:6009/6250 train_loss:2.4079 train_time:2464553ms step_avg:410.83ms step:6010/6250 train_loss:2.2648 train_time:2464953ms step_avg:410.83ms step:6011/6250 train_loss:2.3621 train_time:2465356ms step_avg:410.82ms step:6012/6250 train_loss:2.2756 train_time:2465755ms step_avg:410.82ms step:6013/6250 train_loss:2.3139 train_time:2466171ms step_avg:410.82ms step:6014/6250 train_loss:2.2750 train_time:2466574ms step_avg:410.82ms step:6015/6250 train_loss:2.2695 train_time:2466972ms step_avg:410.82ms step:6016/6250 train_loss:2.3976 train_time:2467376ms step_avg:410.82ms step:6017/6250 train_loss:2.2669 train_time:2467776ms step_avg:410.82ms step:6018/6250 train_loss:2.2545 train_time:2468179ms step_avg:410.82ms step:6019/6250 train_loss:2.3599 train_time:2468579ms step_avg:410.81ms step:6020/6250 train_loss:2.3213 train_time:2468977ms step_avg:410.81ms step:6021/6250 train_loss:2.3595 train_time:2469378ms step_avg:410.81ms step:6022/6250 train_loss:2.2470 train_time:2469778ms step_avg:410.81ms step:6023/6250 train_loss:2.3014 train_time:2470185ms step_avg:410.81ms step:6024/6250 train_loss:2.2812 train_time:2470587ms step_avg:410.81ms step:6025/6250 train_loss:2.3750 train_time:2470988ms step_avg:410.80ms step:6026/6250 train_loss:2.2743 train_time:2471391ms step_avg:410.80ms step:6027/6250 train_loss:2.3227 train_time:2471797ms step_avg:410.80ms step:6028/6250 train_loss:2.3620 train_time:2472199ms step_avg:410.80ms step:6029/6250 train_loss:2.3173 train_time:2472601ms step_avg:410.80ms step:6030/6250 train_loss:2.3335 train_time:2473000ms step_avg:410.80ms step:6031/6250 train_loss:2.3495 train_time:2473405ms step_avg:410.80ms step:6032/6250 train_loss:2.2934 train_time:2473825ms step_avg:410.80ms step:6033/6250 train_loss:2.3692 train_time:2474238ms step_avg:410.80ms step:6034/6250 train_loss:2.3024 train_time:2474653ms step_avg:410.80ms step:6035/6250 train_loss:2.3092 train_time:2475064ms step_avg:410.80ms step:6036/6250 train_loss:2.2956 train_time:2475483ms step_avg:410.80ms step:6037/6250 train_loss:2.4068 train_time:2475907ms step_avg:410.80ms step:6038/6250 train_loss:2.2765 train_time:2476319ms step_avg:410.80ms step:6039/6250 train_loss:2.3081 train_time:2476741ms step_avg:410.80ms step:6040/6250 train_loss:2.3194 train_time:2477162ms step_avg:410.81ms step:6041/6250 train_loss:2.2753 train_time:2477574ms step_avg:410.81ms step:6042/6250 train_loss:2.2025 train_time:2477978ms step_avg:410.81ms step:6043/6250 train_loss:2.3905 train_time:2478403ms step_avg:410.81ms step:6044/6250 train_loss:2.3668 train_time:2478814ms step_avg:410.81ms step:6045/6250 train_loss:2.3141 train_time:2479226ms step_avg:410.81ms step:6046/6250 train_loss:2.3439 train_time:2479637ms step_avg:410.81ms step:6047/6250 train_loss:2.3874 train_time:2480046ms step_avg:410.81ms step:6048/6250 train_loss:2.3084 train_time:2480454ms step_avg:410.81ms step:6049/6250 train_loss:2.3631 train_time:2480871ms step_avg:410.81ms step:6050/6250 train_loss:2.3121 train_time:2481289ms step_avg:410.81ms step:6051/6250 train_loss:2.3341 train_time:2481697ms step_avg:410.81ms step:6052/6250 train_loss:2.4017 train_time:2482102ms step_avg:410.81ms step:6053/6250 train_loss:2.3830 train_time:2482502ms step_avg:410.81ms step:6054/6250 train_loss:2.3657 train_time:2482900ms step_avg:410.80ms step:6055/6250 train_loss:2.3180 train_time:2483303ms step_avg:410.80ms step:6056/6250 train_loss:2.2013 train_time:2483703ms step_avg:410.80ms step:6057/6250 train_loss:2.2657 train_time:2484104ms step_avg:410.80ms step:6058/6250 train_loss:2.3222 train_time:2484506ms step_avg:410.80ms step:6059/6250 train_loss:2.2828 train_time:2484907ms step_avg:410.80ms step:6060/6250 train_loss:2.3269 train_time:2485319ms step_avg:410.80ms step:6061/6250 train_loss:2.2940 train_time:2485737ms step_avg:410.80ms step:6062/6250 train_loss:2.2375 train_time:2486161ms step_avg:410.80ms step:6063/6250 train_loss:2.2673 train_time:2486570ms step_avg:410.80ms step:6064/6250 train_loss:2.2958 train_time:2486974ms step_avg:410.80ms step:6065/6250 train_loss:2.2413 train_time:2487376ms step_avg:410.80ms step:6066/6250 train_loss:2.3147 train_time:2487776ms step_avg:410.80ms step:6067/6250 train_loss:2.2645 train_time:2488178ms step_avg:410.79ms step:6068/6250 train_loss:2.4010 train_time:2488580ms step_avg:410.79ms step:6069/6250 train_loss:2.1310 train_time:2488982ms step_avg:410.79ms step:6070/6250 train_loss:2.3249 train_time:2489384ms step_avg:410.79ms step:6071/6250 train_loss:2.3040 train_time:2489782ms step_avg:410.79ms step:6072/6250 train_loss:2.3150 train_time:2490185ms step_avg:410.79ms step:6073/6250 train_loss:2.3436 train_time:2490587ms step_avg:410.78ms step:6074/6250 train_loss:2.3261 train_time:2490990ms step_avg:410.78ms step:6075/6250 train_loss:2.2577 train_time:2491395ms step_avg:410.78ms step:6076/6250 train_loss:2.2815 train_time:2491797ms step_avg:410.78ms step:6077/6250 train_loss:2.3047 train_time:2492198ms step_avg:410.78ms step:6078/6250 train_loss:2.3018 train_time:2492600ms step_avg:410.78ms step:6079/6250 train_loss:2.2114 train_time:2492998ms step_avg:410.78ms step:6080/6250 train_loss:2.3108 train_time:2493399ms step_avg:410.77ms step:6081/6250 train_loss:2.2074 train_time:2493800ms step_avg:410.77ms step:6082/6250 train_loss:2.3523 train_time:2494203ms step_avg:410.77ms step:6083/6250 train_loss:2.2253 train_time:2494605ms step_avg:410.77ms step:6084/6250 train_loss:2.3010 train_time:2495008ms step_avg:410.77ms step:6085/6250 train_loss:2.3467 train_time:2495409ms step_avg:410.77ms step:6086/6250 train_loss:2.3027 train_time:2495809ms step_avg:410.77ms step:6087/6250 train_loss:2.3064 train_time:2496207ms step_avg:410.76ms step:6088/6250 train_loss:2.2829 train_time:2496610ms step_avg:410.76ms step:6089/6250 train_loss:2.2564 train_time:2497014ms step_avg:410.76ms step:6090/6250 train_loss:2.3129 train_time:2497415ms step_avg:410.76ms step:6091/6250 train_loss:2.3168 train_time:2497816ms step_avg:410.76ms step:6092/6250 train_loss:2.3192 train_time:2498220ms step_avg:410.76ms step:6093/6250 train_loss:2.2867 train_time:2498621ms step_avg:410.75ms step:6094/6250 train_loss:2.2421 train_time:2499022ms step_avg:410.75ms step:6095/6250 train_loss:2.3276 train_time:2499423ms step_avg:410.75ms step:6096/6250 train_loss:2.2714 train_time:2499821ms step_avg:410.75ms step:6097/6250 train_loss:2.3595 train_time:2500223ms step_avg:410.75ms step:6098/6250 train_loss:2.3659 train_time:2500625ms step_avg:410.75ms step:6099/6250 train_loss:2.3146 train_time:2501026ms step_avg:410.74ms step:6100/6250 train_loss:2.3310 train_time:2501427ms step_avg:410.74ms step:6101/6250 train_loss:2.3171 train_time:2501826ms step_avg:410.74ms step:6102/6250 train_loss:2.2583 train_time:2502231ms step_avg:410.74ms step:6103/6250 train_loss:2.2593 train_time:2502633ms step_avg:410.74ms step:6104/6250 train_loss:2.2657 train_time:2503034ms step_avg:410.74ms step:6105/6250 train_loss:2.3389 train_time:2503435ms step_avg:410.74ms step:6106/6250 train_loss:2.2679 train_time:2503834ms step_avg:410.73ms step:6107/6250 train_loss:2.3703 train_time:2504235ms step_avg:410.73ms step:6108/6250 train_loss:2.2406 train_time:2504634ms step_avg:410.73ms step:6109/6250 train_loss:2.2174 train_time:2505034ms step_avg:410.73ms step:6110/6250 train_loss:2.2603 train_time:2505436ms step_avg:410.73ms step:6111/6250 train_loss:2.3061 train_time:2505870ms step_avg:410.73ms step:6112/6250 train_loss:2.2628 train_time:2506278ms step_avg:410.73ms step:6113/6250 train_loss:2.2779 train_time:2506685ms step_avg:410.73ms step:6114/6250 train_loss:2.2222 train_time:2507088ms step_avg:410.73ms step:6115/6250 train_loss:2.3072 train_time:2507494ms step_avg:410.73ms step:6116/6250 train_loss:2.2601 train_time:2507892ms step_avg:410.73ms step:6117/6250 train_loss:2.4087 train_time:2508295ms step_avg:410.72ms step:6118/6250 train_loss:2.4736 train_time:2508697ms step_avg:410.72ms step:6119/6250 train_loss:2.3206 train_time:2509100ms step_avg:410.72ms step:6120/6250 train_loss:2.3149 train_time:2509501ms step_avg:410.72ms step:6121/6250 train_loss:2.2612 train_time:2509902ms step_avg:410.72ms step:6122/6250 train_loss:2.2737 train_time:2510306ms step_avg:410.72ms step:6123/6250 train_loss:2.2251 train_time:2510710ms step_avg:410.72ms step:6124/6250 train_loss:2.2722 train_time:2511112ms step_avg:410.72ms step:6125/6250 train_loss:2.3278 train_time:2511515ms step_avg:410.71ms step:6126/6250 train_loss:2.3433 train_time:2511914ms step_avg:410.71ms step:6127/6250 train_loss:2.2753 train_time:2512317ms step_avg:410.71ms step:6128/6250 train_loss:2.2815 train_time:2512717ms step_avg:410.71ms step:6129/6250 train_loss:2.2731 train_time:2513120ms step_avg:410.71ms step:6130/6250 train_loss:2.2858 train_time:2513521ms step_avg:410.71ms step:6131/6250 train_loss:2.2526 train_time:2513921ms step_avg:410.70ms step:6132/6250 train_loss:2.1964 train_time:2514321ms step_avg:410.70ms step:6133/6250 train_loss:2.2886 train_time:2514723ms step_avg:410.70ms step:6134/6250 train_loss:2.2482 train_time:2515125ms step_avg:410.70ms step:6135/6250 train_loss:2.2145 train_time:2515526ms step_avg:410.70ms step:6136/6250 train_loss:2.3007 train_time:2515928ms step_avg:410.70ms step:6137/6250 train_loss:2.2358 train_time:2516330ms step_avg:410.70ms step:6138/6250 train_loss:2.3293 train_time:2516732ms step_avg:410.69ms step:6139/6250 train_loss:2.2880 train_time:2517134ms step_avg:410.69ms step:6140/6250 train_loss:2.2408 train_time:2517536ms step_avg:410.69ms step:6141/6250 train_loss:2.3443 train_time:2517937ms step_avg:410.69ms step:6142/6250 train_loss:2.2640 train_time:2518338ms step_avg:410.69ms step:6143/6250 train_loss:2.2765 train_time:2518739ms step_avg:410.69ms step:6144/6250 train_loss:2.2187 train_time:2519142ms step_avg:410.69ms step:6145/6250 train_loss:2.3012 train_time:2519543ms step_avg:410.68ms step:6146/6250 train_loss:2.2489 train_time:2519946ms step_avg:410.68ms step:6147/6250 train_loss:2.1945 train_time:2520350ms step_avg:410.68ms step:6148/6250 train_loss:2.3169 train_time:2520746ms step_avg:410.68ms step:6149/6250 train_loss:2.2872 train_time:2521148ms step_avg:410.68ms step:6150/6250 train_loss:2.4296 train_time:2521551ms step_avg:410.68ms step:6151/6250 train_loss:2.2873 train_time:2521953ms step_avg:410.67ms step:6152/6250 train_loss:2.2953 train_time:2522357ms step_avg:410.67ms step:6153/6250 train_loss:2.2324 train_time:2522757ms step_avg:410.67ms step:6154/6250 train_loss:2.2754 train_time:2523159ms step_avg:410.67ms step:6155/6250 train_loss:2.3547 train_time:2523563ms step_avg:410.67ms step:6156/6250 train_loss:2.3316 train_time:2523965ms step_avg:410.67ms step:6157/6250 train_loss:2.2873 train_time:2524364ms step_avg:410.67ms step:6158/6250 train_loss:2.2330 train_time:2524765ms step_avg:410.66ms step:6159/6250 train_loss:2.2735 train_time:2525169ms step_avg:410.66ms step:6160/6250 train_loss:2.2821 train_time:2525571ms step_avg:410.66ms step:6161/6250 train_loss:2.3758 train_time:2525975ms step_avg:410.66ms step:6162/6250 train_loss:2.2230 train_time:2526382ms step_avg:410.66ms step:6163/6250 train_loss:2.3147 train_time:2526782ms step_avg:410.66ms step:6164/6250 train_loss:2.2825 train_time:2527187ms step_avg:410.66ms step:6165/6250 train_loss:2.1826 train_time:2527590ms step_avg:410.66ms step:6166/6250 train_loss:2.2334 train_time:2527991ms step_avg:410.65ms step:6167/6250 train_loss:2.2437 train_time:2528394ms step_avg:410.65ms step:6168/6250 train_loss:2.2626 train_time:2528797ms step_avg:410.65ms step:6169/6250 train_loss:2.3248 train_time:2529201ms step_avg:410.65ms step:6170/6250 train_loss:2.2872 train_time:2529603ms step_avg:410.65ms step:6171/6250 train_loss:2.2845 train_time:2530005ms step_avg:410.65ms step:6172/6250 train_loss:2.2142 train_time:2530408ms step_avg:410.65ms step:6173/6250 train_loss:2.3038 train_time:2530807ms step_avg:410.65ms step:6174/6250 train_loss:2.2319 train_time:2531208ms step_avg:410.64ms step:6175/6250 train_loss:2.2226 train_time:2531609ms step_avg:410.64ms step:6176/6250 train_loss:2.3388 train_time:2532011ms step_avg:410.64ms step:6177/6250 train_loss:2.1663 train_time:2532414ms step_avg:410.64ms step:6178/6250 train_loss:2.2410 train_time:2532814ms step_avg:410.64ms step:6179/6250 train_loss:2.3609 train_time:2533216ms step_avg:410.64ms step:6180/6250 train_loss:2.2682 train_time:2533620ms step_avg:410.64ms step:6181/6250 train_loss:2.2957 train_time:2534020ms step_avg:410.63ms step:6182/6250 train_loss:2.3237 train_time:2534420ms step_avg:410.63ms step:6183/6250 train_loss:2.2559 train_time:2534821ms step_avg:410.63ms step:6184/6250 train_loss:2.2735 train_time:2535221ms step_avg:410.63ms step:6185/6250 train_loss:2.2937 train_time:2535621ms step_avg:410.63ms step:6186/6250 train_loss:2.3436 train_time:2536023ms step_avg:410.63ms step:6187/6250 train_loss:2.1913 train_time:2536425ms step_avg:410.62ms step:6188/6250 train_loss:2.2332 train_time:2536826ms step_avg:410.62ms step:6189/6250 train_loss:2.3122 train_time:2537228ms step_avg:410.62ms step:6190/6250 train_loss:2.3224 train_time:2537630ms step_avg:410.62ms step:6191/6250 train_loss:2.2655 train_time:2538030ms step_avg:410.62ms step:6192/6250 train_loss:2.2812 train_time:2538430ms step_avg:410.62ms step:6193/6250 train_loss:2.2258 train_time:2538831ms step_avg:410.61ms step:6194/6250 train_loss:2.3083 train_time:2539237ms step_avg:410.61ms step:6195/6250 train_loss:2.3645 train_time:2539645ms step_avg:410.61ms step:6196/6250 train_loss:2.2660 train_time:2540045ms step_avg:410.61ms step:6197/6250 train_loss:2.2885 train_time:2540447ms step_avg:410.61ms step:6198/6250 train_loss:2.2862 train_time:2540849ms step_avg:410.61ms step:6199/6250 train_loss:2.2414 train_time:2541251ms step_avg:410.61ms step:6200/6250 train_loss:2.3494 train_time:2541652ms step_avg:410.61ms step:6201/6250 train_loss:2.3487 train_time:2542053ms step_avg:410.60ms step:6202/6250 train_loss:2.2208 train_time:2542455ms step_avg:410.60ms step:6203/6250 train_loss:2.2292 train_time:2542854ms step_avg:410.60ms step:6204/6250 train_loss:2.2280 train_time:2543254ms step_avg:410.60ms step:6205/6250 train_loss:2.3152 train_time:2543656ms step_avg:410.60ms step:6206/6250 train_loss:2.2541 train_time:2544056ms step_avg:410.60ms step:6207/6250 train_loss:2.3068 train_time:2544453ms step_avg:410.59ms step:6208/6250 train_loss:2.2620 train_time:2544856ms step_avg:410.59ms step:6209/6250 train_loss:2.2815 train_time:2545257ms step_avg:410.59ms step:6210/6250 train_loss:2.2893 train_time:2545654ms step_avg:410.59ms step:6211/6250 train_loss:2.2380 train_time:2546055ms step_avg:410.59ms step:6212/6250 train_loss:2.2782 train_time:2546455ms step_avg:410.59ms step:6213/6250 train_loss:2.2395 train_time:2546857ms step_avg:410.58ms step:6214/6250 train_loss:2.2684 train_time:2547259ms step_avg:410.58ms step:6215/6250 train_loss:2.1762 train_time:2547657ms step_avg:410.58ms step:6216/6250 train_loss:2.2193 train_time:2548058ms step_avg:410.58ms step:6217/6250 train_loss:2.2442 train_time:2548460ms step_avg:410.58ms step:6218/6250 train_loss:2.2598 train_time:2548861ms step_avg:410.58ms step:6219/6250 train_loss:2.3608 train_time:2549263ms step_avg:410.58ms step:6220/6250 train_loss:2.2441 train_time:2549661ms step_avg:410.57ms step:6221/6250 train_loss:2.2707 train_time:2550063ms step_avg:410.57ms step:6222/6250 train_loss:2.2571 train_time:2550464ms step_avg:410.57ms step:6223/6250 train_loss:2.2883 train_time:2550867ms step_avg:410.57ms step:6224/6250 train_loss:2.2392 train_time:2551266ms step_avg:410.57ms step:6225/6250 train_loss:2.3123 train_time:2551666ms step_avg:410.57ms step:6226/6250 train_loss:2.2182 train_time:2552067ms step_avg:410.56ms step:6227/6250 train_loss:2.2893 train_time:2552466ms step_avg:410.56ms step:6228/6250 train_loss:2.3026 train_time:2552869ms step_avg:410.56ms step:6229/6250 train_loss:2.2402 train_time:2553310ms step_avg:410.57ms step:6230/6250 train_loss:2.2766 train_time:2553731ms step_avg:410.57ms step:6231/6250 train_loss:2.1922 train_time:2554138ms step_avg:410.57ms step:6232/6250 train_loss:2.1303 train_time:2554543ms step_avg:410.57ms step:6233/6250 train_loss:2.2609 train_time:2554951ms step_avg:410.57ms step:6234/6250 train_loss:2.2239 train_time:2555356ms step_avg:410.56ms step:6235/6250 train_loss:2.2423 train_time:2555755ms step_avg:410.56ms step:6236/6250 train_loss:2.2660 train_time:2556154ms step_avg:410.56ms step:6237/6250 train_loss:2.2606 train_time:2556554ms step_avg:410.56ms step:6238/6250 train_loss:2.3158 train_time:2556956ms step_avg:410.56ms step:6239/6250 train_loss:2.1774 train_time:2557356ms step_avg:410.56ms step:6240/6250 train_loss:2.2582 train_time:2557754ms step_avg:410.55ms step:6241/6250 train_loss:2.2069 train_time:2558157ms step_avg:410.55ms step:6242/6250 train_loss:2.1973 train_time:2558559ms step_avg:410.55ms step:6243/6250 train_loss:2.3083 train_time:2558959ms step_avg:410.55ms step:6244/6250 train_loss:2.2867 train_time:2559362ms step_avg:410.55ms step:6245/6250 train_loss:2.2182 train_time:2559764ms step_avg:410.55ms step:6246/6250 train_loss:2.2314 train_time:2560163ms step_avg:410.55ms step:6247/6250 train_loss:2.3242 train_time:2560563ms step_avg:410.54ms step:6248/6250 train_loss:2.2020 train_time:2560965ms step_avg:410.54ms step:6249/6250 train_loss:2.1782 train_time:2561367ms step_avg:410.54ms step:6250/6250 train_loss:2.3536 train_time:2561769ms step_avg:410.54ms step:6250/6250 val_loss:2.2499 train_time:2561769ms step_avg:410.54ms