==================================================================================================== #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: 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 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() #tinystories if master_process: print("Building model...") #num_vocab=50304 for non-tinystories models layer_prefab = {"dim":256,"dim_head":32,"headcount":8,"ff_mult":4, "lambda":True,"layerwisenorm":"rmsnorm","qknorm":"identitynorm", "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.block.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()) 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 00:13:17 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 62W / 350W | 3043MiB / 24564MiB | 8% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 4256 C+G ...64__8wekyb3d8bbwe\CalculatorApp.exe N/A | | 0 N/A N/A 10912 C+G ...64__8wekyb3d8bbwe\CalculatorApp.exe N/A | | 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 27064 C+G ...64__8wekyb3d8bbwe\CalculatorApp.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 37492 C+G ...64__8wekyb3d8bbwe\CalculatorApp.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 49144 C ...rograms\Python\Python310\python.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 51220 C+G ...0\Ultimate Admiral Dreadnoughts.exe N/A | | 0 N/A N/A 51896 C+G ...ekyb3d8bbwe\PhoneExperienceHost.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 72680 C+G ...64__8wekyb3d8bbwe\CalculatorApp.exe N/A | | 0 N/A N/A 73204 C+G ...64__8wekyb3d8bbwe\CalculatorApp.exe N/A | | 0 N/A N/A 73872 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A | | 0 N/A N/A 75380 C+G ...64__8wekyb3d8bbwe\CalculatorApp.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 109360 C+G ...64__8wekyb3d8bbwe\CalculatorApp.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:82ms step_avg:nanms step:1/6250 train_loss:10.8258 train_time:655ms step_avg:nanms step:2/6250 train_loss:10.8209 train_time:1059ms step_avg:nanms step:3/6250 train_loss:10.8022 train_time:1463ms step_avg:nanms step:4/6250 train_loss:10.7520 train_time:1863ms step_avg:nanms step:5/6250 train_loss:10.6737 train_time:2266ms step_avg:nanms step:6/6250 train_loss:10.5852 train_time:2669ms step_avg:nanms step:7/6250 train_loss:10.4706 train_time:3071ms step_avg:nanms step:8/6250 train_loss:10.3366 train_time:3473ms step_avg:nanms step:9/6250 train_loss:10.1735 train_time:3872ms step_avg:nanms step:10/6250 train_loss:9.9831 train_time:4272ms step_avg:nanms step:11/6250 train_loss:9.7842 train_time:400ms step_avg:nanms step:12/6250 train_loss:9.5624 train_time:805ms step_avg:nanms step:13/6250 train_loss:9.3151 train_time:1204ms step_avg:401.33ms step:14/6250 train_loss:9.0592 train_time:1601ms step_avg:400.29ms step:15/6250 train_loss:8.7990 train_time:2005ms step_avg:401.06ms step:16/6250 train_loss:8.5237 train_time:2405ms step_avg:400.88ms step:17/6250 train_loss:8.2409 train_time:2806ms step_avg:400.92ms step:18/6250 train_loss:7.9768 train_time:3209ms step_avg:401.18ms step:19/6250 train_loss:7.7154 train_time:3612ms step_avg:401.38ms step:20/6250 train_loss:7.4598 train_time:4015ms step_avg:401.46ms step:21/6250 train_loss:7.2348 train_time:4416ms step_avg:401.43ms step:22/6250 train_loss:7.0232 train_time:4819ms step_avg:401.58ms step:23/6250 train_loss:6.8688 train_time:5220ms step_avg:401.53ms step:24/6250 train_loss:6.6102 train_time:5621ms step_avg:401.51ms step:25/6250 train_loss:6.5130 train_time:6025ms step_avg:401.67ms step:26/6250 train_loss:6.3142 train_time:6427ms step_avg:401.69ms step:27/6250 train_loss:6.2392 train_time:6832ms step_avg:401.89ms step:28/6250 train_loss:6.1784 train_time:7235ms step_avg:401.97ms step:29/6250 train_loss:6.0472 train_time:7636ms step_avg:401.92ms step:30/6250 train_loss:5.9894 train_time:8039ms step_avg:401.97ms step:31/6250 train_loss:5.8595 train_time:8442ms step_avg:401.98ms step:32/6250 train_loss:5.7685 train_time:8844ms step_avg:401.98ms step:33/6250 train_loss:5.7008 train_time:9245ms step_avg:401.94ms step:34/6250 train_loss:5.5922 train_time:9646ms step_avg:401.90ms step:35/6250 train_loss:5.5672 train_time:10048ms step_avg:401.91ms step:36/6250 train_loss:5.5302 train_time:10450ms step_avg:401.91ms step:37/6250 train_loss:5.3261 train_time:10852ms step_avg:401.91ms step:38/6250 train_loss:5.2349 train_time:11255ms step_avg:401.96ms step:39/6250 train_loss:5.1495 train_time:11662ms step_avg:402.14ms step:40/6250 train_loss:5.1431 train_time:12067ms step_avg:402.23ms step:41/6250 train_loss:5.0687 train_time:12492ms step_avg:402.96ms step:42/6250 train_loss:4.9771 train_time:12895ms step_avg:402.96ms step:43/6250 train_loss:4.9791 train_time:13298ms step_avg:402.96ms step:44/6250 train_loss:4.8658 train_time:13700ms step_avg:402.94ms step:45/6250 train_loss:4.8119 train_time:14100ms step_avg:402.85ms step:46/6250 train_loss:4.6350 train_time:14513ms step_avg:403.13ms step:47/6250 train_loss:4.5836 train_time:14934ms step_avg:403.62ms step:48/6250 train_loss:4.5890 train_time:15339ms step_avg:403.66ms step:49/6250 train_loss:4.4628 train_time:15743ms step_avg:403.67ms step:50/6250 train_loss:4.4744 train_time:16147ms step_avg:403.68ms step:51/6250 train_loss:4.4386 train_time:16565ms step_avg:404.03ms step:52/6250 train_loss:4.3585 train_time:16968ms step_avg:404.01ms step:53/6250 train_loss:4.3176 train_time:17370ms step_avg:403.96ms step:54/6250 train_loss:4.2136 train_time:17788ms step_avg:404.28ms step:55/6250 train_loss:4.2651 train_time:18190ms step_avg:404.23ms step:56/6250 train_loss:4.1793 train_time:18590ms step_avg:404.14ms step:57/6250 train_loss:4.2031 train_time:18996ms step_avg:404.18ms step:58/6250 train_loss:4.1691 train_time:19413ms step_avg:404.43ms step:59/6250 train_loss:4.1401 train_time:19842ms step_avg:404.93ms step:60/6250 train_loss:4.0497 train_time:20276ms step_avg:405.52ms step:61/6250 train_loss:4.0965 train_time:20706ms step_avg:406.00ms step:62/6250 train_loss:4.1291 train_time:21132ms step_avg:406.39ms step:63/6250 train_loss:4.0076 train_time:21546ms step_avg:406.52ms step:64/6250 train_loss:3.9269 train_time:21950ms step_avg:406.48ms step:65/6250 train_loss:3.9997 train_time:22361ms step_avg:406.57ms step:66/6250 train_loss:3.9854 train_time:22771ms step_avg:406.63ms step:67/6250 train_loss:4.0063 train_time:23177ms step_avg:406.62ms step:68/6250 train_loss:3.9437 train_time:23596ms step_avg:406.83ms step:69/6250 train_loss:3.9248 train_time:24005ms step_avg:406.87ms step:70/6250 train_loss:3.9864 train_time:24412ms step_avg:406.86ms step:71/6250 train_loss:3.9161 train_time:24815ms step_avg:406.80ms step:72/6250 train_loss:3.8531 train_time:25223ms step_avg:406.82ms step:73/6250 train_loss:3.8285 train_time:25625ms step_avg:406.74ms step:74/6250 train_loss:3.8403 train_time:26034ms step_avg:406.78ms step:75/6250 train_loss:3.7497 train_time:26437ms step_avg:406.72ms step:76/6250 train_loss:3.9243 train_time:26841ms step_avg:406.68ms step:77/6250 train_loss:3.8073 train_time:27246ms step_avg:406.66ms step:78/6250 train_loss:3.8322 train_time:27648ms step_avg:406.60ms step:79/6250 train_loss:3.7930 train_time:28050ms step_avg:406.52ms step:80/6250 train_loss:3.7860 train_time:28455ms step_avg:406.50ms step:81/6250 train_loss:3.6917 train_time:28860ms step_avg:406.48ms step:82/6250 train_loss:3.7049 train_time:29263ms step_avg:406.43ms step:83/6250 train_loss:3.7118 train_time:29666ms step_avg:406.39ms step:84/6250 train_loss:3.7976 train_time:30070ms step_avg:406.34ms step:85/6250 train_loss:3.8666 train_time:30474ms step_avg:406.31ms step:86/6250 train_loss:3.6984 train_time:30878ms step_avg:406.28ms step:87/6250 train_loss:3.6773 train_time:31287ms step_avg:406.32ms step:88/6250 train_loss:3.6716 train_time:31694ms step_avg:406.33ms step:89/6250 train_loss:3.6614 train_time:32109ms step_avg:406.44ms step:90/6250 train_loss:3.7146 train_time:32512ms step_avg:406.40ms step:91/6250 train_loss:3.6973 train_time:32922ms step_avg:406.44ms step:92/6250 train_loss:3.6967 train_time:33333ms step_avg:406.50ms step:93/6250 train_loss:3.6431 train_time:33746ms step_avg:406.58ms step:94/6250 train_loss:3.6484 train_time:34158ms step_avg:406.65ms step:95/6250 train_loss:3.6016 train_time:34562ms step_avg:406.61ms step:96/6250 train_loss:3.6917 train_time:34966ms step_avg:406.58ms step:97/6250 train_loss:3.6277 train_time:35368ms step_avg:406.52ms step:98/6250 train_loss:3.6428 train_time:35773ms step_avg:406.51ms step:99/6250 train_loss:3.6515 train_time:36178ms step_avg:406.49ms step:100/6250 train_loss:3.4944 train_time:36583ms step_avg:406.48ms step:101/6250 train_loss:3.6896 train_time:36988ms step_avg:406.46ms step:102/6250 train_loss:3.6251 train_time:37399ms step_avg:406.51ms step:103/6250 train_loss:3.6234 train_time:37806ms step_avg:406.52ms step:104/6250 train_loss:3.5782 train_time:38211ms step_avg:406.50ms step:105/6250 train_loss:3.4723 train_time:38635ms step_avg:406.68ms step:106/6250 train_loss:3.5064 train_time:39043ms step_avg:406.69ms step:107/6250 train_loss:3.6124 train_time:39447ms step_avg:406.66ms step:108/6250 train_loss:3.6260 train_time:39872ms step_avg:406.85ms step:109/6250 train_loss:3.6664 train_time:40298ms step_avg:407.05ms step:110/6250 train_loss:3.4740 train_time:40712ms step_avg:407.12ms step:111/6250 train_loss:3.5496 train_time:41138ms step_avg:407.31ms step:112/6250 train_loss:3.5757 train_time:41549ms step_avg:407.35ms step:113/6250 train_loss:3.4383 train_time:41955ms step_avg:407.33ms step:114/6250 train_loss:3.5623 train_time:42368ms step_avg:407.38ms step:115/6250 train_loss:3.5250 train_time:42776ms step_avg:407.39ms step:116/6250 train_loss:3.5875 train_time:43182ms step_avg:407.37ms step:117/6250 train_loss:3.5707 train_time:43587ms step_avg:407.35ms step:118/6250 train_loss:3.5962 train_time:43999ms step_avg:407.40ms step:119/6250 train_loss:3.5160 train_time:44427ms step_avg:407.59ms step:120/6250 train_loss:3.5609 train_time:44842ms step_avg:407.65ms step:121/6250 train_loss:3.5103 train_time:45250ms step_avg:407.66ms step:122/6250 train_loss:3.5270 train_time:45673ms step_avg:407.79ms step:123/6250 train_loss:3.4411 train_time:46079ms step_avg:407.78ms step:124/6250 train_loss:3.5381 train_time:46484ms step_avg:407.75ms step:125/6250 train_loss:3.4593 train_time:46889ms step_avg:407.73ms step:126/6250 train_loss:3.4464 train_time:47294ms step_avg:407.71ms step:127/6250 train_loss:3.4501 train_time:47696ms step_avg:407.66ms step:128/6250 train_loss:3.4095 train_time:48101ms step_avg:407.63ms step:129/6250 train_loss:3.4795 train_time:48502ms step_avg:407.58ms step:130/6250 train_loss:3.4131 train_time:48903ms step_avg:407.52ms step:131/6250 train_loss:3.4399 train_time:49306ms step_avg:407.49ms step:132/6250 train_loss:3.3906 train_time:49712ms step_avg:407.48ms step:133/6250 train_loss:3.5018 train_time:50121ms step_avg:407.48ms step:134/6250 train_loss:3.5482 train_time:50532ms step_avg:407.52ms step:135/6250 train_loss:3.3535 train_time:50944ms step_avg:407.55ms step:136/6250 train_loss:3.4351 train_time:51358ms step_avg:407.60ms step:137/6250 train_loss:3.5378 train_time:51775ms step_avg:407.68ms step:138/6250 train_loss:3.4077 train_time:52182ms step_avg:407.67ms step:139/6250 train_loss:3.3651 train_time:52593ms step_avg:407.70ms step:140/6250 train_loss:3.4626 train_time:53003ms step_avg:407.72ms step:141/6250 train_loss:3.3843 train_time:53414ms step_avg:407.74ms step:142/6250 train_loss:3.4293 train_time:53821ms step_avg:407.74ms step:143/6250 train_loss:3.4038 train_time:54225ms step_avg:407.71ms step:144/6250 train_loss:3.4540 train_time:54636ms step_avg:407.73ms step:145/6250 train_loss:3.4260 train_time:55045ms step_avg:407.74ms step:146/6250 train_loss:3.4091 train_time:55450ms step_avg:407.72ms step:147/6250 train_loss:3.4153 train_time:55858ms step_avg:407.73ms step:148/6250 train_loss:3.5374 train_time:56272ms step_avg:407.77ms step:149/6250 train_loss:3.3975 train_time:56690ms step_avg:407.84ms step:150/6250 train_loss:3.4099 train_time:57141ms step_avg:408.15ms step:151/6250 train_loss:3.3964 train_time:57549ms step_avg:408.15ms step:152/6250 train_loss:3.4159 train_time:57961ms step_avg:408.18ms step:153/6250 train_loss:3.4394 train_time:58380ms step_avg:408.25ms step:154/6250 train_loss:3.3880 train_time:58799ms step_avg:408.32ms step:155/6250 train_loss:3.4761 train_time:59218ms step_avg:408.40ms step:156/6250 train_loss:3.4337 train_time:59638ms step_avg:408.48ms step:157/6250 train_loss:3.3245 train_time:60051ms step_avg:408.51ms step:158/6250 train_loss:3.3954 train_time:60457ms step_avg:408.50ms step:159/6250 train_loss:3.4121 train_time:60868ms step_avg:408.51ms step:160/6250 train_loss:3.3153 train_time:61274ms step_avg:408.50ms step:161/6250 train_loss:3.4050 train_time:61678ms step_avg:408.46ms step:162/6250 train_loss:3.3957 train_time:62086ms step_avg:408.46ms step:163/6250 train_loss:3.4016 train_time:62491ms step_avg:408.44ms step:164/6250 train_loss:3.4040 train_time:62897ms step_avg:408.42ms step:165/6250 train_loss:3.3591 train_time:63313ms step_avg:408.47ms step:166/6250 train_loss:3.3576 train_time:63729ms step_avg:408.52ms step:167/6250 train_loss:3.3745 train_time:64145ms step_avg:408.56ms step:168/6250 train_loss:3.3765 train_time:64563ms step_avg:408.62ms step:169/6250 train_loss:3.3737 train_time:64981ms step_avg:408.68ms step:170/6250 train_loss:3.4588 train_time:65397ms step_avg:408.73ms step:171/6250 train_loss:3.3038 train_time:65816ms step_avg:408.80ms step:172/6250 train_loss:3.4367 train_time:66234ms step_avg:408.85ms step:173/6250 train_loss:3.3647 train_time:66651ms step_avg:408.90ms step:174/6250 train_loss:3.3794 train_time:67068ms step_avg:408.95ms step:175/6250 train_loss:3.2693 train_time:67483ms step_avg:408.99ms step:176/6250 train_loss:3.3294 train_time:67900ms step_avg:409.04ms step:177/6250 train_loss:3.2968 train_time:68316ms step_avg:409.08ms step:178/6250 train_loss:3.2375 train_time:68736ms step_avg:409.15ms step:179/6250 train_loss:3.3159 train_time:69152ms step_avg:409.19ms step:180/6250 train_loss:3.3824 train_time:69569ms step_avg:409.23ms step:181/6250 train_loss:3.3180 train_time:69992ms step_avg:409.31ms step:182/6250 train_loss:3.3653 train_time:70416ms step_avg:409.40ms step:183/6250 train_loss:3.3273 train_time:70839ms step_avg:409.47ms step:184/6250 train_loss:3.3514 train_time:71258ms step_avg:409.53ms step:185/6250 train_loss:3.4038 train_time:71677ms step_avg:409.58ms step:186/6250 train_loss:3.2593 train_time:72109ms step_avg:409.71ms step:187/6250 train_loss:3.3600 train_time:72543ms step_avg:409.85ms step:188/6250 train_loss:3.3113 train_time:72962ms step_avg:409.90ms step:189/6250 train_loss:3.3520 train_time:73378ms step_avg:409.93ms step:190/6250 train_loss:3.4619 train_time:73800ms step_avg:410.00ms step:191/6250 train_loss:3.2814 train_time:74219ms step_avg:410.05ms step:192/6250 train_loss:3.2660 train_time:74641ms step_avg:410.12ms step:193/6250 train_loss:3.3113 train_time:75059ms step_avg:410.16ms step:194/6250 train_loss:3.3174 train_time:75507ms step_avg:410.37ms step:195/6250 train_loss:3.2668 train_time:75968ms step_avg:410.64ms step:196/6250 train_loss:3.3043 train_time:76389ms step_avg:410.69ms step:197/6250 train_loss:3.3995 train_time:76827ms step_avg:410.84ms step:198/6250 train_loss:3.3129 train_time:77252ms step_avg:410.91ms step:199/6250 train_loss:3.3415 train_time:77671ms step_avg:410.96ms step:200/6250 train_loss:3.3345 train_time:78098ms step_avg:411.04ms step:201/6250 train_loss:3.2548 train_time:78522ms step_avg:411.11ms step:202/6250 train_loss:3.2783 train_time:78941ms step_avg:411.15ms step:203/6250 train_loss:3.3864 train_time:79366ms step_avg:411.22ms step:204/6250 train_loss:3.3478 train_time:79784ms step_avg:411.26ms step:205/6250 train_loss:3.2605 train_time:80204ms step_avg:411.30ms step:206/6250 train_loss:3.2210 train_time:80644ms step_avg:411.45ms step:207/6250 train_loss:3.3556 train_time:81063ms step_avg:411.49ms step:208/6250 train_loss:3.2801 train_time:81493ms step_avg:411.58ms step:209/6250 train_loss:3.2437 train_time:81930ms step_avg:411.71ms step:210/6250 train_loss:3.2842 train_time:82333ms step_avg:411.67ms step:211/6250 train_loss:3.3283 train_time:82744ms step_avg:411.66ms step:212/6250 train_loss:3.3811 train_time:83147ms step_avg:411.62ms step:213/6250 train_loss:3.3146 train_time:83551ms step_avg:411.58ms step:214/6250 train_loss:3.3396 train_time:83954ms step_avg:411.54ms step:215/6250 train_loss:3.3540 train_time:84365ms step_avg:411.54ms step:216/6250 train_loss:3.3744 train_time:84787ms step_avg:411.58ms step:217/6250 train_loss:3.2473 train_time:85223ms step_avg:411.70ms step:218/6250 train_loss:3.1494 train_time:85655ms step_avg:411.81ms step:219/6250 train_loss:3.1570 train_time:86076ms step_avg:411.85ms step:220/6250 train_loss:3.2060 train_time:86501ms step_avg:411.91ms step:221/6250 train_loss:3.2390 train_time:86927ms step_avg:411.98ms step:222/6250 train_loss:3.2930 train_time:87364ms step_avg:412.09ms step:223/6250 train_loss:3.1882 train_time:87827ms step_avg:412.33ms step:224/6250 train_loss:3.2867 train_time:88288ms step_avg:412.56ms step:225/6250 train_loss:3.2504 train_time:88708ms step_avg:412.60ms step:226/6250 train_loss:3.2108 train_time:89130ms step_avg:412.64ms step:227/6250 train_loss:3.3303 train_time:89548ms step_avg:412.66ms step:228/6250 train_loss:3.2462 train_time:89965ms step_avg:412.68ms step:229/6250 train_loss:3.2814 train_time:90389ms step_avg:412.74ms step:230/6250 train_loss:3.2000 train_time:90811ms step_avg:412.78ms step:231/6250 train_loss:3.2627 train_time:91242ms step_avg:412.86ms step:232/6250 train_loss:3.4083 train_time:91662ms step_avg:412.89ms step:233/6250 train_loss:3.2158 train_time:92076ms step_avg:412.90ms step:234/6250 train_loss:3.3030 train_time:92493ms step_avg:412.91ms step:235/6250 train_loss:3.2647 train_time:92913ms step_avg:412.95ms step:236/6250 train_loss:3.1237 train_time:93342ms step_avg:413.02ms step:237/6250 train_loss:3.2081 train_time:93761ms step_avg:413.05ms step:238/6250 train_loss:3.2558 train_time:94202ms step_avg:413.17ms step:239/6250 train_loss:3.2305 train_time:94625ms step_avg:413.21ms step:240/6250 train_loss:3.2668 train_time:95071ms step_avg:413.35ms step:241/6250 train_loss:3.2760 train_time:95487ms step_avg:413.36ms step:242/6250 train_loss:3.2249 train_time:95892ms step_avg:413.33ms step:243/6250 train_loss:3.1822 train_time:96285ms step_avg:413.24ms step:244/6250 train_loss:3.1960 train_time:96688ms step_avg:413.19ms step:245/6250 train_loss:3.2182 train_time:97082ms step_avg:413.11ms step:246/6250 train_loss:3.1993 train_time:97513ms step_avg:413.19ms step:247/6250 train_loss:3.1414 train_time:97930ms step_avg:413.21ms step:248/6250 train_loss:3.1713 train_time:98366ms step_avg:413.30ms step:249/6250 train_loss:3.1869 train_time:98821ms step_avg:413.48ms step:250/6250 train_loss:3.1763 train_time:99244ms step_avg:413.51ms step:251/6250 train_loss:3.2504 train_time:99660ms step_avg:413.53ms step:252/6250 train_loss:3.1327 train_time:100071ms step_avg:413.52ms step:253/6250 train_loss:3.1538 train_time:100481ms step_avg:413.50ms step:254/6250 train_loss:3.1687 train_time:100894ms step_avg:413.50ms step:255/6250 train_loss:3.1886 train_time:101340ms step_avg:413.63ms step:256/6250 train_loss:3.1757 train_time:101785ms step_avg:413.76ms step:257/6250 train_loss:3.2155 train_time:102235ms step_avg:413.91ms step:258/6250 train_loss:3.1436 train_time:102684ms step_avg:414.05ms step:259/6250 train_loss:3.3737 train_time:103118ms step_avg:414.13ms step:260/6250 train_loss:3.1660 train_time:103564ms step_avg:414.25ms step:261/6250 train_loss:3.1453 train_time:104011ms step_avg:414.39ms step:262/6250 train_loss:3.1940 train_time:104455ms step_avg:414.50ms step:263/6250 train_loss:3.1946 train_time:104904ms step_avg:414.64ms step:264/6250 train_loss:3.1476 train_time:105348ms step_avg:414.75ms step:265/6250 train_loss:3.1786 train_time:105795ms step_avg:414.88ms step:266/6250 train_loss:3.1815 train_time:106240ms step_avg:415.00ms step:267/6250 train_loss:3.1012 train_time:106682ms step_avg:415.10ms step:268/6250 train_loss:3.0944 train_time:107102ms step_avg:415.12ms step:269/6250 train_loss:3.2109 train_time:107517ms step_avg:415.12ms step:270/6250 train_loss:3.1134 train_time:107916ms step_avg:415.06ms step:271/6250 train_loss:3.1054 train_time:108327ms step_avg:415.05ms step:272/6250 train_loss:3.1547 train_time:108771ms step_avg:415.16ms step:273/6250 train_loss:3.2017 train_time:109213ms step_avg:415.26ms step:274/6250 train_loss:3.0978 train_time:109603ms step_avg:415.16ms step:275/6250 train_loss:3.0760 train_time:110031ms step_avg:415.21ms step:276/6250 train_loss:3.1033 train_time:110494ms step_avg:415.39ms step:277/6250 train_loss:3.1051 train_time:110957ms step_avg:415.57ms step:278/6250 train_loss:3.1357 train_time:111409ms step_avg:415.70ms step:279/6250 train_loss:3.1951 train_time:111839ms step_avg:415.76ms step:280/6250 train_loss:3.0642 train_time:112263ms step_avg:415.79ms step:281/6250 train_loss:3.1851 train_time:112740ms step_avg:416.01ms step:282/6250 train_loss:3.1024 train_time:113215ms step_avg:416.23ms step:283/6250 train_loss:3.1936 train_time:113638ms step_avg:416.26ms step:284/6250 train_loss:3.0456 train_time:114064ms step_avg:416.29ms step:285/6250 train_loss:3.0951 train_time:114494ms step_avg:416.34ms step:286/6250 train_loss:3.1417 train_time:114932ms step_avg:416.42ms step:287/6250 train_loss:3.1757 train_time:115369ms step_avg:416.50ms step:288/6250 train_loss:3.0283 train_time:115822ms step_avg:416.62ms step:289/6250 train_loss:3.3211 train_time:116267ms step_avg:416.73ms step:290/6250 train_loss:3.0814 train_time:116684ms step_avg:416.73ms step:291/6250 train_loss:3.0628 train_time:117148ms step_avg:416.90ms step:292/6250 train_loss:2.9948 train_time:117564ms step_avg:416.89ms step:293/6250 train_loss:3.0544 train_time:118007ms step_avg:416.99ms step:294/6250 train_loss:3.1252 train_time:118430ms step_avg:417.01ms step:295/6250 train_loss:3.1731 train_time:118855ms step_avg:417.04ms step:296/6250 train_loss:3.2783 train_time:119272ms step_avg:417.04ms step:297/6250 train_loss:3.0626 train_time:119696ms step_avg:417.06ms step:298/6250 train_loss:3.0532 train_time:120084ms step_avg:416.96ms step:299/6250 train_loss:3.0837 train_time:120445ms step_avg:416.77ms step:300/6250 train_loss:3.0904 train_time:120812ms step_avg:416.59ms step:301/6250 train_loss:3.1452 train_time:121177ms step_avg:416.42ms step:302/6250 train_loss:3.1363 train_time:121558ms step_avg:416.30ms step:303/6250 train_loss:3.1082 train_time:121983ms step_avg:416.33ms step:304/6250 train_loss:3.0942 train_time:122388ms step_avg:416.29ms step:305/6250 train_loss:3.0823 train_time:122796ms step_avg:416.26ms step:306/6250 train_loss:3.1343 train_time:123253ms step_avg:416.40ms step:307/6250 train_loss:3.1750 train_time:123734ms step_avg:416.61ms step:308/6250 train_loss:3.1335 train_time:124159ms step_avg:416.64ms step:309/6250 train_loss:3.1827 train_time:124580ms step_avg:416.66ms step:310/6250 train_loss:3.1853 train_time:125013ms step_avg:416.71ms step:311/6250 train_loss:3.0621 train_time:125440ms step_avg:416.75ms step:312/6250 train_loss:3.0230 train_time:125890ms step_avg:416.85ms step:313/6250 train_loss:2.9660 train_time:126338ms step_avg:416.96ms step:314/6250 train_loss:3.1188 train_time:126769ms step_avg:417.00ms step:315/6250 train_loss:3.0903 train_time:127238ms step_avg:417.17ms step:316/6250 train_loss:3.0970 train_time:127717ms step_avg:417.38ms step:317/6250 train_loss:3.1182 train_time:128136ms step_avg:417.38ms step:318/6250 train_loss:3.0203 train_time:128580ms step_avg:417.47ms step:319/6250 train_loss:3.0333 train_time:128996ms step_avg:417.46ms step:320/6250 train_loss:3.0819 train_time:129424ms step_avg:417.50ms step:321/6250 train_loss:3.2205 train_time:129825ms step_avg:417.44ms step:322/6250 train_loss:3.2661 train_time:130249ms step_avg:417.46ms step:323/6250 train_loss:3.1134 train_time:130682ms step_avg:417.51ms step:324/6250 train_loss:3.1629 train_time:131118ms step_avg:417.57ms step:325/6250 train_loss:3.0968 train_time:131499ms step_avg:417.46ms step:326/6250 train_loss:3.1196 train_time:131886ms step_avg:417.36ms step:327/6250 train_loss:3.0607 train_time:132276ms step_avg:417.28ms step:328/6250 train_loss:3.0196 train_time:132694ms step_avg:417.28ms step:329/6250 train_loss:3.1195 train_time:133110ms step_avg:417.27ms step:330/6250 train_loss:2.9921 train_time:133533ms step_avg:417.29ms step:331/6250 train_loss:3.0520 train_time:133995ms step_avg:417.43ms step:332/6250 train_loss:3.1333 train_time:134406ms step_avg:417.41ms step:333/6250 train_loss:3.0816 train_time:134812ms step_avg:417.38ms step:334/6250 train_loss:3.1292 train_time:135239ms step_avg:417.41ms step:335/6250 train_loss:3.0162 train_time:135659ms step_avg:417.41ms step:336/6250 train_loss:3.0456 train_time:136086ms step_avg:417.44ms step:337/6250 train_loss:3.1925 train_time:136487ms step_avg:417.39ms step:338/6250 train_loss:3.0488 train_time:136880ms step_avg:417.32ms step:339/6250 train_loss:3.0476 train_time:137264ms step_avg:417.22ms step:340/6250 train_loss:3.0341 train_time:137650ms step_avg:417.12ms step:341/6250 train_loss:3.0427 train_time:138023ms step_avg:416.99ms step:342/6250 train_loss:3.2734 train_time:138464ms step_avg:417.06ms step:343/6250 train_loss:3.0889 train_time:138889ms step_avg:417.08ms step:344/6250 train_loss:3.0836 train_time:139308ms step_avg:417.09ms step:345/6250 train_loss:3.0870 train_time:139722ms step_avg:417.08ms step:346/6250 train_loss:3.0700 train_time:140148ms step_avg:417.11ms step:347/6250 train_loss:3.0503 train_time:140549ms step_avg:417.06ms step:348/6250 train_loss:2.9896 train_time:140927ms step_avg:416.95ms step:349/6250 train_loss:3.1260 train_time:141306ms step_avg:416.83ms step:350/6250 train_loss:3.0271 train_time:141685ms step_avg:416.72ms step:351/6250 train_loss:2.9388 train_time:142096ms step_avg:416.70ms step:352/6250 train_loss:3.0489 train_time:142509ms step_avg:416.69ms step:353/6250 train_loss:3.1362 train_time:142900ms step_avg:416.62ms step:354/6250 train_loss:3.1062 train_time:143285ms step_avg:416.53ms step:355/6250 train_loss:3.1184 train_time:143708ms step_avg:416.55ms step:356/6250 train_loss:3.1230 train_time:144118ms step_avg:416.53ms step:357/6250 train_loss:2.9866 train_time:144539ms step_avg:416.54ms step:358/6250 train_loss:3.0933 train_time:144970ms step_avg:416.58ms step:359/6250 train_loss:3.0456 train_time:145420ms step_avg:416.68ms step:360/6250 train_loss:3.0868 train_time:145831ms step_avg:416.66ms step:361/6250 train_loss:3.0850 train_time:146250ms step_avg:416.67ms step:362/6250 train_loss:3.1282 train_time:146689ms step_avg:416.73ms step:363/6250 train_loss:3.0590 train_time:147128ms step_avg:416.79ms step:364/6250 train_loss:3.0702 train_time:147584ms step_avg:416.91ms step:365/6250 train_loss:3.0701 train_time:148066ms step_avg:417.09ms step:366/6250 train_loss:3.0238 train_time:148500ms step_avg:417.14ms step:367/6250 train_loss:3.1230 train_time:148953ms step_avg:417.24ms step:368/6250 train_loss:3.0285 train_time:149376ms step_avg:417.25ms step:369/6250 train_loss:3.1200 train_time:149791ms step_avg:417.24ms step:370/6250 train_loss:3.0765 train_time:150199ms step_avg:417.22ms step:371/6250 train_loss:2.9941 train_time:150619ms step_avg:417.23ms step:372/6250 train_loss:3.0435 train_time:151049ms step_avg:417.26ms step:373/6250 train_loss:2.9932 train_time:151461ms step_avg:417.25ms step:374/6250 train_loss:2.9529 train_time:151888ms step_avg:417.27ms step:375/6250 train_loss:3.0501 train_time:152315ms step_avg:417.30ms step:376/6250 train_loss:3.0829 train_time:152748ms step_avg:417.34ms step:377/6250 train_loss:3.0539 train_time:153174ms step_avg:417.37ms step:378/6250 train_loss:3.0035 train_time:153580ms step_avg:417.34ms step:379/6250 train_loss:3.1290 train_time:154026ms step_avg:417.41ms step:380/6250 train_loss:3.0338 train_time:154416ms step_avg:417.34ms step:381/6250 train_loss:2.9942 train_time:154836ms step_avg:417.35ms step:382/6250 train_loss:2.9870 train_time:155251ms step_avg:417.34ms step:383/6250 train_loss:3.1156 train_time:155650ms step_avg:417.29ms step:384/6250 train_loss:2.9968 train_time:156054ms step_avg:417.26ms step:385/6250 train_loss:2.9294 train_time:156464ms step_avg:417.24ms step:386/6250 train_loss:3.0389 train_time:156860ms step_avg:417.18ms step:387/6250 train_loss:3.0557 train_time:157285ms step_avg:417.20ms step:388/6250 train_loss:3.0686 train_time:157700ms step_avg:417.20ms step:389/6250 train_loss:3.0293 train_time:158089ms step_avg:417.12ms step:390/6250 train_loss:3.0078 train_time:158473ms step_avg:417.03ms step:391/6250 train_loss:3.0376 train_time:158872ms step_avg:416.99ms step:392/6250 train_loss:2.9966 train_time:159294ms step_avg:417.00ms step:393/6250 train_loss:2.9437 train_time:159734ms step_avg:417.06ms step:394/6250 train_loss:3.0037 train_time:160155ms step_avg:417.07ms step:395/6250 train_loss:2.8972 train_time:160592ms step_avg:417.12ms step:396/6250 train_loss:2.8857 train_time:161016ms step_avg:417.14ms step:397/6250 train_loss:2.9870 train_time:161453ms step_avg:417.19ms step:398/6250 train_loss:3.1065 train_time:161897ms step_avg:417.26ms step:399/6250 train_loss:3.0288 train_time:162331ms step_avg:417.30ms step:400/6250 train_loss:3.1296 train_time:162757ms step_avg:417.32ms step:401/6250 train_loss:3.1330 train_time:163181ms step_avg:417.34ms step:402/6250 train_loss:2.9999 train_time:163583ms step_avg:417.30ms step:403/6250 train_loss:3.0194 train_time:163966ms step_avg:417.22ms step:404/6250 train_loss:3.0655 train_time:164404ms step_avg:417.27ms step:405/6250 train_loss:3.0052 train_time:164827ms step_avg:417.28ms step:406/6250 train_loss:3.0094 train_time:165236ms step_avg:417.26ms step:407/6250 train_loss:3.0797 train_time:165637ms step_avg:417.22ms step:408/6250 train_loss:2.9342 train_time:166035ms step_avg:417.17ms step:409/6250 train_loss:3.0359 train_time:166433ms step_avg:417.13ms step:410/6250 train_loss:3.0404 train_time:166867ms step_avg:417.17ms step:411/6250 train_loss:3.0434 train_time:167294ms step_avg:417.19ms step:412/6250 train_loss:3.0271 train_time:167725ms step_avg:417.23ms step:413/6250 train_loss:2.9951 train_time:168159ms step_avg:417.27ms step:414/6250 train_loss:2.9225 train_time:168568ms step_avg:417.25ms step:415/6250 train_loss:3.1162 train_time:168982ms step_avg:417.24ms step:416/6250 train_loss:2.9745 train_time:169389ms step_avg:417.22ms step:417/6250 train_loss:2.9742 train_time:169789ms step_avg:417.17ms step:418/6250 train_loss:2.9948 train_time:170187ms step_avg:417.13ms step:419/6250 train_loss:3.0771 train_time:170578ms step_avg:417.06ms step:420/6250 train_loss:3.0529 train_time:170984ms step_avg:417.03ms step:421/6250 train_loss:3.0990 train_time:171411ms step_avg:417.06ms step:422/6250 train_loss:2.9646 train_time:171843ms step_avg:417.09ms step:423/6250 train_loss:3.0106 train_time:172243ms step_avg:417.05ms step:424/6250 train_loss:2.9999 train_time:172642ms step_avg:417.01ms step:425/6250 train_loss:3.0699 train_time:173058ms step_avg:417.01ms step:426/6250 train_loss:3.0070 train_time:173461ms step_avg:416.97ms step:427/6250 train_loss:3.0555 train_time:173919ms step_avg:417.07ms step:428/6250 train_loss:2.9800 train_time:174303ms step_avg:416.99ms step:429/6250 train_loss:3.0175 train_time:174760ms step_avg:417.09ms step:430/6250 train_loss:2.9598 train_time:175226ms step_avg:417.21ms step:431/6250 train_loss:3.0105 train_time:175608ms step_avg:417.12ms step:432/6250 train_loss:2.9981 train_time:176049ms step_avg:417.18ms step:433/6250 train_loss:2.9600 train_time:176468ms step_avg:417.18ms step:434/6250 train_loss:2.9918 train_time:176884ms step_avg:417.18ms step:435/6250 train_loss:2.8927 train_time:177318ms step_avg:417.22ms step:436/6250 train_loss:3.0795 train_time:177733ms step_avg:417.21ms step:437/6250 train_loss:2.9337 train_time:178132ms step_avg:417.17ms step:438/6250 train_loss:3.0781 train_time:178566ms step_avg:417.21ms step:439/6250 train_loss:3.0900 train_time:179004ms step_avg:417.26ms step:440/6250 train_loss:3.1244 train_time:179434ms step_avg:417.29ms step:441/6250 train_loss:2.9406 train_time:179874ms step_avg:417.34ms step:442/6250 train_loss:2.9935 train_time:180310ms step_avg:417.38ms step:443/6250 train_loss:3.1330 train_time:180722ms step_avg:417.37ms step:444/6250 train_loss:2.9705 train_time:181158ms step_avg:417.42ms step:445/6250 train_loss:3.0517 train_time:181606ms step_avg:417.49ms step:446/6250 train_loss:2.9956 train_time:181984ms step_avg:417.40ms step:447/6250 train_loss:2.9261 train_time:182424ms step_avg:417.45ms step:448/6250 train_loss:3.0809 train_time:182856ms step_avg:417.48ms step:449/6250 train_loss:2.9727 train_time:183265ms step_avg:417.46ms step:450/6250 train_loss:3.1213 train_time:183697ms step_avg:417.49ms step:451/6250 train_loss:3.0442 train_time:184146ms step_avg:417.57ms step:452/6250 train_loss:2.9925 train_time:184557ms step_avg:417.55ms step:453/6250 train_loss:2.9643 train_time:184997ms step_avg:417.60ms step:454/6250 train_loss:2.9882 train_time:185451ms step_avg:417.68ms step:455/6250 train_loss:2.9912 train_time:185902ms step_avg:417.76ms step:456/6250 train_loss:2.9625 train_time:186284ms step_avg:417.68ms step:457/6250 train_loss:3.0576 train_time:186623ms step_avg:417.50ms step:458/6250 train_loss:2.9531 train_time:186971ms step_avg:417.35ms step:459/6250 train_loss:2.9403 train_time:187309ms step_avg:417.17ms step:460/6250 train_loss:3.0277 train_time:187744ms step_avg:417.21ms step:461/6250 train_loss:3.0137 train_time:188176ms step_avg:417.24ms step:462/6250 train_loss:2.9579 train_time:188633ms step_avg:417.33ms step:463/6250 train_loss:2.9861 train_time:189041ms step_avg:417.31ms step:464/6250 train_loss:2.9476 train_time:189380ms step_avg:417.14ms step:465/6250 train_loss:2.9342 train_time:189725ms step_avg:416.98ms step:466/6250 train_loss:2.9432 train_time:190063ms step_avg:416.81ms step:467/6250 train_loss:2.9113 train_time:190442ms step_avg:416.72ms step:468/6250 train_loss:2.8910 train_time:190874ms step_avg:416.76ms step:469/6250 train_loss:2.9807 train_time:191211ms step_avg:416.58ms step:470/6250 train_loss:3.0013 train_time:191557ms step_avg:416.43ms step:471/6250 train_loss:2.9977 train_time:191896ms step_avg:416.26ms step:472/6250 train_loss:2.9609 train_time:192268ms step_avg:416.16ms step:473/6250 train_loss:2.8606 train_time:192728ms step_avg:416.26ms step:474/6250 train_loss:2.9806 train_time:193141ms step_avg:416.25ms step:475/6250 train_loss:2.9474 train_time:193560ms step_avg:416.26ms step:476/6250 train_loss:2.9432 train_time:193908ms step_avg:416.11ms step:477/6250 train_loss:2.9526 train_time:194251ms step_avg:415.96ms step:478/6250 train_loss:2.9548 train_time:194595ms step_avg:415.80ms step:479/6250 train_loss:2.8884 train_time:194936ms step_avg:415.64ms step:480/6250 train_loss:2.9200 train_time:195393ms step_avg:415.73ms step:481/6250 train_loss:2.9482 train_time:195829ms step_avg:415.77ms step:482/6250 train_loss:2.9604 train_time:196265ms step_avg:415.82ms step:483/6250 train_loss:2.9799 train_time:196603ms step_avg:415.65ms step:484/6250 train_loss:2.9942 train_time:196951ms step_avg:415.51ms step:485/6250 train_loss:2.9549 train_time:197291ms step_avg:415.35ms step:486/6250 train_loss:2.8931 train_time:197666ms step_avg:415.26ms step:487/6250 train_loss:3.0312 train_time:198123ms step_avg:415.35ms step:488/6250 train_loss:3.0858 train_time:198533ms step_avg:415.34ms step:489/6250 train_loss:2.9519 train_time:198874ms step_avg:415.19ms step:490/6250 train_loss:2.9476 train_time:199219ms step_avg:415.04ms step:491/6250 train_loss:2.9455 train_time:199558ms step_avg:414.88ms step:492/6250 train_loss:2.9427 train_time:199910ms step_avg:414.75ms step:493/6250 train_loss:3.0294 train_time:200249ms step_avg:414.59ms step:494/6250 train_loss:2.9960 train_time:200637ms step_avg:414.54ms step:495/6250 train_loss:2.9496 train_time:201091ms step_avg:414.62ms step:496/6250 train_loss:2.9535 train_time:201496ms step_avg:414.60ms step:497/6250 train_loss:2.9404 train_time:201932ms step_avg:414.65ms step:498/6250 train_loss:2.9873 train_time:202375ms step_avg:414.70ms step:499/6250 train_loss:2.8951 train_time:202838ms step_avg:414.80ms step:500/6250 train_loss:2.9836 train_time:203297ms step_avg:414.89ms step:501/6250 train_loss:2.9465 train_time:203723ms step_avg:414.91ms step:502/6250 train_loss:2.9916 train_time:204161ms step_avg:414.96ms step:503/6250 train_loss:3.0183 train_time:204575ms step_avg:414.96ms step:504/6250 train_loss:2.9689 train_time:205015ms step_avg:415.01ms step:505/6250 train_loss:2.9801 train_time:205408ms step_avg:414.97ms step:506/6250 train_loss:2.9183 train_time:205884ms step_avg:415.09ms step:507/6250 train_loss:2.9889 train_time:206378ms step_avg:415.25ms step:508/6250 train_loss:2.9195 train_time:206816ms step_avg:415.29ms step:509/6250 train_loss:3.0468 train_time:207280ms step_avg:415.39ms step:510/6250 train_loss:3.0209 train_time:207706ms step_avg:415.41ms step:511/6250 train_loss:2.9815 train_time:208157ms step_avg:415.48ms step:512/6250 train_loss:2.9690 train_time:208616ms step_avg:415.57ms step:513/6250 train_loss:3.0336 train_time:209042ms step_avg:415.59ms step:514/6250 train_loss:2.9543 train_time:209485ms step_avg:415.65ms step:515/6250 train_loss:2.9854 train_time:209947ms step_avg:415.74ms step:516/6250 train_loss:2.9674 train_time:210360ms step_avg:415.73ms step:517/6250 train_loss:3.0132 train_time:210787ms step_avg:415.75ms step:518/6250 train_loss:2.9229 train_time:211207ms step_avg:415.76ms step:519/6250 train_loss:3.0282 train_time:211670ms step_avg:415.86ms step:520/6250 train_loss:2.9841 train_time:212056ms step_avg:415.80ms step:521/6250 train_loss:2.9294 train_time:212466ms step_avg:415.79ms step:522/6250 train_loss:2.9402 train_time:212879ms step_avg:415.78ms step:523/6250 train_loss:2.8988 train_time:213318ms step_avg:415.82ms step:524/6250 train_loss:2.8800 train_time:213818ms step_avg:415.99ms step:525/6250 train_loss:2.9992 train_time:214275ms step_avg:416.07ms step:526/6250 train_loss:2.9346 train_time:214739ms step_avg:416.16ms step:527/6250 train_loss:2.9628 train_time:215184ms step_avg:416.22ms step:528/6250 train_loss:2.9498 train_time:215599ms step_avg:416.22ms step:529/6250 train_loss:2.9610 train_time:216046ms step_avg:416.27ms step:530/6250 train_loss:2.9638 train_time:216463ms step_avg:416.27ms step:531/6250 train_loss:2.9006 train_time:216880ms step_avg:416.28ms step:532/6250 train_loss:2.9178 train_time:217297ms step_avg:416.28ms step:533/6250 train_loss:2.8887 train_time:217717ms step_avg:416.28ms step:534/6250 train_loss:2.8902 train_time:218136ms step_avg:416.29ms step:535/6250 train_loss:2.8782 train_time:218544ms step_avg:416.27ms step:536/6250 train_loss:2.9667 train_time:218952ms step_avg:416.26ms step:537/6250 train_loss:2.8642 train_time:219361ms step_avg:416.25ms step:538/6250 train_loss:2.8894 train_time:219743ms step_avg:416.18ms step:539/6250 train_loss:2.9452 train_time:220178ms step_avg:416.22ms step:540/6250 train_loss:2.9657 train_time:220599ms step_avg:416.23ms step:541/6250 train_loss:2.9350 train_time:221004ms step_avg:416.20ms step:542/6250 train_loss:2.9296 train_time:221499ms step_avg:416.35ms step:543/6250 train_loss:2.9010 train_time:221991ms step_avg:416.49ms step:544/6250 train_loss:3.0352 train_time:222459ms step_avg:416.59ms step:545/6250 train_loss:2.8829 train_time:222907ms step_avg:416.65ms step:546/6250 train_loss:3.0113 train_time:223320ms step_avg:416.64ms step:547/6250 train_loss:2.8133 train_time:223798ms step_avg:416.76ms step:548/6250 train_loss:2.8792 train_time:224255ms step_avg:416.83ms step:549/6250 train_loss:2.9865 train_time:224692ms step_avg:416.87ms step:550/6250 train_loss:2.9910 train_time:225162ms step_avg:416.97ms step:551/6250 train_loss:2.9684 train_time:225620ms step_avg:417.04ms step:552/6250 train_loss:2.9962 train_time:226059ms step_avg:417.08ms step:553/6250 train_loss:2.8829 train_time:226494ms step_avg:417.12ms step:554/6250 train_loss:2.9583 train_time:226953ms step_avg:417.19ms step:555/6250 train_loss:3.0063 train_time:227393ms step_avg:417.24ms step:556/6250 train_loss:2.9103 train_time:227813ms step_avg:417.24ms step:557/6250 train_loss:2.8817 train_time:228213ms step_avg:417.21ms step:558/6250 train_loss:2.9732 train_time:228656ms step_avg:417.26ms step:559/6250 train_loss:2.8751 train_time:229106ms step_avg:417.32ms step:560/6250 train_loss:2.9024 train_time:229541ms step_avg:417.35ms step:561/6250 train_loss:2.9827 train_time:229942ms step_avg:417.32ms step:562/6250 train_loss:2.9650 train_time:230352ms step_avg:417.30ms step:563/6250 train_loss:2.9769 train_time:230741ms step_avg:417.25ms step:564/6250 train_loss:2.9605 train_time:231111ms step_avg:417.17ms step:565/6250 train_loss:2.8831 train_time:231493ms step_avg:417.10ms step:566/6250 train_loss:2.9036 train_time:231879ms step_avg:417.05ms step:567/6250 train_loss:2.8734 train_time:232340ms step_avg:417.13ms step:568/6250 train_loss:2.9627 train_time:232735ms step_avg:417.09ms step:569/6250 train_loss:2.9241 train_time:233177ms step_avg:417.13ms step:570/6250 train_loss:2.9047 train_time:233609ms step_avg:417.16ms step:571/6250 train_loss:2.9698 train_time:234034ms step_avg:417.17ms step:572/6250 train_loss:2.9340 train_time:234473ms step_avg:417.21ms step:573/6250 train_loss:2.8944 train_time:234912ms step_avg:417.25ms step:574/6250 train_loss:2.9005 train_time:235290ms step_avg:417.18ms step:575/6250 train_loss:2.9124 train_time:235654ms step_avg:417.09ms step:576/6250 train_loss:2.9211 train_time:236091ms step_avg:417.12ms step:577/6250 train_loss:2.8597 train_time:236490ms step_avg:417.09ms step:578/6250 train_loss:2.8803 train_time:236885ms step_avg:417.05ms step:579/6250 train_loss:2.8428 train_time:237273ms step_avg:417.00ms step:580/6250 train_loss:2.8516 train_time:237699ms step_avg:417.02ms step:581/6250 train_loss:2.8495 train_time:238139ms step_avg:417.06ms step:582/6250 train_loss:2.8664 train_time:238516ms step_avg:416.99ms step:583/6250 train_loss:2.9856 train_time:238943ms step_avg:417.00ms step:584/6250 train_loss:2.9886 train_time:239358ms step_avg:417.00ms step:585/6250 train_loss:2.9567 train_time:239728ms step_avg:416.92ms step:586/6250 train_loss:2.8264 train_time:240118ms step_avg:416.87ms step:587/6250 train_loss:2.9501 train_time:240501ms step_avg:416.81ms step:588/6250 train_loss:2.9892 train_time:240872ms step_avg:416.73ms step:589/6250 train_loss:2.9578 train_time:241251ms step_avg:416.67ms step:590/6250 train_loss:2.8945 train_time:241639ms step_avg:416.62ms step:591/6250 train_loss:2.8791 train_time:242028ms step_avg:416.57ms step:592/6250 train_loss:2.8981 train_time:242444ms step_avg:416.57ms step:593/6250 train_loss:2.9182 train_time:242898ms step_avg:416.64ms step:594/6250 train_loss:2.9732 train_time:243288ms step_avg:416.59ms step:595/6250 train_loss:2.8382 train_time:243663ms step_avg:416.52ms step:596/6250 train_loss:2.8459 train_time:244108ms step_avg:416.57ms step:597/6250 train_loss:2.9624 train_time:244557ms step_avg:416.62ms step:598/6250 train_loss:2.9550 train_time:244986ms step_avg:416.64ms step:599/6250 train_loss:2.8511 train_time:245451ms step_avg:416.73ms step:600/6250 train_loss:2.8140 train_time:245871ms step_avg:416.73ms step:601/6250 train_loss:2.7992 train_time:246254ms step_avg:416.67ms step:602/6250 train_loss:2.8617 train_time:246659ms step_avg:416.65ms step:603/6250 train_loss:2.8721 train_time:247080ms step_avg:416.66ms step:604/6250 train_loss:2.9395 train_time:247485ms step_avg:416.64ms step:605/6250 train_loss:2.9844 train_time:247891ms step_avg:416.62ms step:606/6250 train_loss:2.8892 train_time:248281ms step_avg:416.58ms step:607/6250 train_loss:2.9313 train_time:248657ms step_avg:416.51ms step:608/6250 train_loss:2.9285 train_time:249045ms step_avg:416.46ms step:609/6250 train_loss:2.8469 train_time:249434ms step_avg:416.42ms step:610/6250 train_loss:2.8792 train_time:249812ms step_avg:416.35ms step:611/6250 train_loss:2.7996 train_time:250234ms step_avg:416.36ms step:612/6250 train_loss:2.8993 train_time:250607ms step_avg:416.29ms step:613/6250 train_loss:2.8572 train_time:251022ms step_avg:416.29ms step:614/6250 train_loss:2.9079 train_time:251401ms step_avg:416.23ms step:615/6250 train_loss:2.8805 train_time:251817ms step_avg:416.23ms step:616/6250 train_loss:2.8944 train_time:252217ms step_avg:416.20ms step:617/6250 train_loss:2.8159 train_time:252646ms step_avg:416.22ms step:618/6250 train_loss:2.8911 train_time:253090ms step_avg:416.27ms step:619/6250 train_loss:2.8678 train_time:253537ms step_avg:416.32ms step:620/6250 train_loss:2.8655 train_time:253923ms step_avg:416.27ms step:621/6250 train_loss:2.8396 train_time:254324ms step_avg:416.24ms step:622/6250 train_loss:2.9040 train_time:254754ms step_avg:416.26ms step:623/6250 train_loss:2.8154 train_time:255199ms step_avg:416.31ms step:624/6250 train_loss:2.8761 train_time:255655ms step_avg:416.38ms step:625/6250 train_loss:2.8608 train_time:256113ms step_avg:416.44ms step:626/6250 train_loss:2.9231 train_time:256517ms step_avg:416.42ms step:627/6250 train_loss:2.9838 train_time:256953ms step_avg:416.46ms step:628/6250 train_loss:2.9414 train_time:257352ms step_avg:416.43ms step:629/6250 train_loss:2.8347 train_time:257743ms step_avg:416.39ms step:630/6250 train_loss:2.9388 train_time:258136ms step_avg:416.35ms step:631/6250 train_loss:2.9253 train_time:258534ms step_avg:416.32ms step:632/6250 train_loss:2.9328 train_time:258967ms step_avg:416.35ms step:633/6250 train_loss:2.8910 train_time:259424ms step_avg:416.41ms step:634/6250 train_loss:2.9411 train_time:259820ms step_avg:416.38ms step:635/6250 train_loss:2.9549 train_time:260220ms step_avg:416.35ms step:636/6250 train_loss:2.8794 train_time:260647ms step_avg:416.37ms step:637/6250 train_loss:2.8675 train_time:261067ms step_avg:416.38ms step:638/6250 train_loss:2.8619 train_time:261498ms step_avg:416.40ms step:639/6250 train_loss:2.7931 train_time:261886ms step_avg:416.35ms step:640/6250 train_loss:2.8145 train_time:262279ms step_avg:416.32ms step:641/6250 train_loss:2.8750 train_time:262669ms step_avg:416.27ms step:642/6250 train_loss:2.8544 train_time:263121ms step_avg:416.33ms step:643/6250 train_loss:2.9330 train_time:263535ms step_avg:416.33ms step:644/6250 train_loss:2.9230 train_time:263950ms step_avg:416.32ms step:645/6250 train_loss:2.8019 train_time:264341ms step_avg:416.28ms step:646/6250 train_loss:2.9092 train_time:264794ms step_avg:416.34ms step:647/6250 train_loss:2.8967 train_time:265251ms step_avg:416.41ms step:648/6250 train_loss:2.8477 train_time:265697ms step_avg:416.45ms step:649/6250 train_loss:2.9064 train_time:266155ms step_avg:416.52ms step:650/6250 train_loss:2.8772 train_time:266612ms step_avg:416.58ms step:651/6250 train_loss:2.7936 train_time:267070ms step_avg:416.65ms step:652/6250 train_loss:2.8107 train_time:267529ms step_avg:416.71ms step:653/6250 train_loss:2.9494 train_time:267983ms step_avg:416.77ms step:654/6250 train_loss:2.7923 train_time:268442ms step_avg:416.83ms step:655/6250 train_loss:2.8494 train_time:268839ms step_avg:416.80ms step:656/6250 train_loss:2.8040 train_time:269250ms step_avg:416.80ms step:657/6250 train_loss:2.8071 train_time:269644ms step_avg:416.76ms step:658/6250 train_loss:2.7351 train_time:270075ms step_avg:416.78ms step:659/6250 train_loss:2.9152 train_time:270489ms step_avg:416.78ms step:660/6250 train_loss:2.8618 train_time:270898ms step_avg:416.77ms step:661/6250 train_loss:2.8412 train_time:271309ms step_avg:416.76ms step:662/6250 train_loss:2.9442 train_time:271720ms step_avg:416.75ms step:663/6250 train_loss:2.9278 train_time:272118ms step_avg:416.72ms step:664/6250 train_loss:2.9641 train_time:272540ms step_avg:416.73ms step:665/6250 train_loss:2.8533 train_time:272986ms step_avg:416.77ms step:666/6250 train_loss:2.9139 train_time:273393ms step_avg:416.76ms step:667/6250 train_loss:2.8318 train_time:273802ms step_avg:416.75ms step:668/6250 train_loss:2.8225 train_time:274212ms step_avg:416.74ms step:669/6250 train_loss:2.8431 train_time:274598ms step_avg:416.69ms step:670/6250 train_loss:2.8965 train_time:275011ms step_avg:416.68ms step:671/6250 train_loss:2.9455 train_time:275441ms step_avg:416.70ms step:672/6250 train_loss:2.8648 train_time:275854ms step_avg:416.70ms step:673/6250 train_loss:2.9279 train_time:276264ms step_avg:416.69ms step:674/6250 train_loss:2.8698 train_time:276674ms step_avg:416.68ms step:675/6250 train_loss:2.9525 train_time:277080ms step_avg:416.66ms step:676/6250 train_loss:2.8399 train_time:277478ms step_avg:416.63ms step:677/6250 train_loss:2.8463 train_time:277889ms step_avg:416.62ms step:678/6250 train_loss:2.8266 train_time:278286ms step_avg:416.60ms step:679/6250 train_loss:2.9355 train_time:278701ms step_avg:416.59ms step:680/6250 train_loss:2.8523 train_time:279154ms step_avg:416.65ms step:681/6250 train_loss:2.7986 train_time:279610ms step_avg:416.71ms step:682/6250 train_loss:2.8021 train_time:280049ms step_avg:416.74ms step:683/6250 train_loss:2.9632 train_time:280506ms step_avg:416.80ms step:684/6250 train_loss:2.8334 train_time:280968ms step_avg:416.87ms step:685/6250 train_loss:2.7954 train_time:281408ms step_avg:416.90ms step:686/6250 train_loss:2.7918 train_time:281872ms step_avg:416.97ms step:687/6250 train_loss:2.8636 train_time:282331ms step_avg:417.03ms step:688/6250 train_loss:2.8603 train_time:282771ms step_avg:417.07ms step:689/6250 train_loss:2.8514 train_time:283187ms step_avg:417.06ms step:690/6250 train_loss:2.8652 train_time:283634ms step_avg:417.11ms step:691/6250 train_loss:2.7977 train_time:284077ms step_avg:417.15ms step:692/6250 train_loss:2.8318 train_time:284519ms step_avg:417.18ms step:693/6250 train_loss:2.8829 train_time:284931ms step_avg:417.18ms step:694/6250 train_loss:2.7685 train_time:285375ms step_avg:417.21ms step:695/6250 train_loss:2.8052 train_time:285815ms step_avg:417.25ms step:696/6250 train_loss:2.9514 train_time:286248ms step_avg:417.27ms step:697/6250 train_loss:2.7973 train_time:286707ms step_avg:417.33ms step:698/6250 train_loss:2.8791 train_time:287157ms step_avg:417.38ms step:699/6250 train_loss:2.9913 train_time:287577ms step_avg:417.38ms step:700/6250 train_loss:2.8309 train_time:288052ms step_avg:417.47ms step:701/6250 train_loss:2.8456 train_time:288532ms step_avg:417.56ms step:702/6250 train_loss:2.8216 train_time:288959ms step_avg:417.57ms step:703/6250 train_loss:2.7964 train_time:289404ms step_avg:417.61ms step:704/6250 train_loss:2.8997 train_time:289827ms step_avg:417.62ms step:705/6250 train_loss:2.8074 train_time:290233ms step_avg:417.60ms step:706/6250 train_loss:2.8442 train_time:290646ms step_avg:417.59ms step:707/6250 train_loss:2.8228 train_time:291089ms step_avg:417.63ms step:708/6250 train_loss:2.8078 train_time:291532ms step_avg:417.67ms step:709/6250 train_loss:2.8482 train_time:291974ms step_avg:417.70ms step:710/6250 train_loss:2.8690 train_time:292370ms step_avg:417.67ms step:711/6250 train_loss:2.8249 train_time:292803ms step_avg:417.69ms step:712/6250 train_loss:2.9022 train_time:293201ms step_avg:417.66ms step:713/6250 train_loss:2.8036 train_time:293599ms step_avg:417.64ms step:714/6250 train_loss:2.8217 train_time:293998ms step_avg:417.61ms step:715/6250 train_loss:2.9299 train_time:294452ms step_avg:417.66ms step:716/6250 train_loss:2.8106 train_time:294816ms step_avg:417.59ms step:717/6250 train_loss:2.8589 train_time:295205ms step_avg:417.55ms step:718/6250 train_loss:2.8780 train_time:295646ms step_avg:417.58ms step:719/6250 train_loss:2.7115 train_time:296049ms step_avg:417.56ms step:720/6250 train_loss:2.7940 train_time:296484ms step_avg:417.58ms step:721/6250 train_loss:2.7907 train_time:296937ms step_avg:417.63ms step:722/6250 train_loss:2.8139 train_time:297396ms step_avg:417.69ms step:723/6250 train_loss:2.7576 train_time:297843ms step_avg:417.73ms step:724/6250 train_loss:2.7912 train_time:298301ms step_avg:417.79ms step:725/6250 train_loss:2.8281 train_time:298764ms step_avg:417.85ms step:726/6250 train_loss:2.7401 train_time:299219ms step_avg:417.90ms step:727/6250 train_loss:2.8283 train_time:299679ms step_avg:417.96ms step:728/6250 train_loss:2.7661 train_time:300116ms step_avg:417.99ms step:729/6250 train_loss:2.8673 train_time:300540ms step_avg:418.00ms step:730/6250 train_loss:2.8462 train_time:301031ms step_avg:418.10ms step:731/6250 train_loss:2.8328 train_time:301462ms step_avg:418.12ms step:732/6250 train_loss:2.7920 train_time:301937ms step_avg:418.20ms step:733/6250 train_loss:2.8055 train_time:302429ms step_avg:418.30ms step:734/6250 train_loss:2.7073 train_time:302868ms step_avg:418.33ms step:735/6250 train_loss:2.7809 train_time:303361ms step_avg:418.43ms step:736/6250 train_loss:2.8390 train_time:303807ms step_avg:418.47ms step:737/6250 train_loss:2.8275 train_time:304190ms step_avg:418.42ms step:738/6250 train_loss:2.7597 train_time:304638ms step_avg:418.46ms step:739/6250 train_loss:2.8388 train_time:305084ms step_avg:418.50ms step:740/6250 train_loss:2.7813 train_time:305466ms step_avg:418.45ms step:741/6250 train_loss:2.7649 train_time:305945ms step_avg:418.53ms step:742/6250 train_loss:2.8802 train_time:306400ms step_avg:418.58ms step:743/6250 train_loss:2.8372 train_time:306842ms step_avg:418.61ms step:744/6250 train_loss:2.9025 train_time:307329ms step_avg:418.70ms step:745/6250 train_loss:2.8407 train_time:307750ms step_avg:418.71ms step:746/6250 train_loss:2.7525 train_time:308199ms step_avg:418.75ms step:747/6250 train_loss:2.7965 train_time:308679ms step_avg:418.83ms step:748/6250 train_loss:2.7859 train_time:309118ms step_avg:418.86ms step:749/6250 train_loss:2.8554 train_time:309614ms step_avg:418.96ms step:750/6250 train_loss:2.8298 train_time:310107ms step_avg:419.06ms step:751/6250 train_loss:2.7789 train_time:310542ms step_avg:419.08ms step:752/6250 train_loss:2.8216 train_time:311032ms step_avg:419.18ms step:753/6250 train_loss:2.8871 train_time:311507ms step_avg:419.26ms step:754/6250 train_loss:2.8081 train_time:311940ms step_avg:419.27ms step:755/6250 train_loss:2.8227 train_time:312365ms step_avg:419.28ms step:756/6250 train_loss:2.8543 train_time:312803ms step_avg:419.31ms step:757/6250 train_loss:2.8956 train_time:313232ms step_avg:419.32ms step:758/6250 train_loss:2.7775 train_time:313616ms step_avg:419.27ms step:759/6250 train_loss:2.7697 train_time:314024ms step_avg:419.26ms step:760/6250 train_loss:2.8262 train_time:314435ms step_avg:419.25ms step:761/6250 train_loss:2.7611 train_time:314805ms step_avg:419.18ms step:762/6250 train_loss:2.7856 train_time:315185ms step_avg:419.13ms step:763/6250 train_loss:2.8446 train_time:315558ms step_avg:419.07ms step:764/6250 train_loss:2.7958 train_time:315923ms step_avg:419.00ms step:765/6250 train_loss:2.9262 train_time:316304ms step_avg:418.95ms step:766/6250 train_loss:2.8074 train_time:316681ms step_avg:418.89ms step:767/6250 train_loss:2.8181 train_time:317056ms step_avg:418.83ms step:768/6250 train_loss:2.7650 train_time:317466ms step_avg:418.82ms step:769/6250 train_loss:2.8354 train_time:317860ms step_avg:418.79ms step:770/6250 train_loss:2.8232 train_time:318246ms step_avg:418.75ms step:771/6250 train_loss:2.7723 train_time:318657ms step_avg:418.73ms step:772/6250 train_loss:2.7477 train_time:319062ms step_avg:418.72ms step:773/6250 train_loss:2.8034 train_time:319492ms step_avg:418.73ms step:774/6250 train_loss:2.7862 train_time:319885ms step_avg:418.70ms step:775/6250 train_loss:2.8741 train_time:320256ms step_avg:418.63ms step:776/6250 train_loss:2.7979 train_time:320605ms step_avg:418.54ms step:777/6250 train_loss:2.8698 train_time:320961ms step_avg:418.46ms step:778/6250 train_loss:2.8318 train_time:321314ms step_avg:418.38ms step:779/6250 train_loss:2.8849 train_time:321663ms step_avg:418.29ms step:780/6250 train_loss:2.7757 train_time:322019ms step_avg:418.21ms step:781/6250 train_loss:2.8067 train_time:322372ms step_avg:418.12ms step:782/6250 train_loss:2.7777 train_time:322723ms step_avg:418.04ms step:783/6250 train_loss:2.7157 train_time:323124ms step_avg:418.01ms step:784/6250 train_loss:2.8344 train_time:323512ms step_avg:417.97ms step:785/6250 train_loss:2.7629 train_time:323918ms step_avg:417.96ms step:786/6250 train_loss:2.7550 train_time:324317ms step_avg:417.93ms step:787/6250 train_loss:2.8422 train_time:324721ms step_avg:417.92ms step:788/6250 train_loss:2.9255 train_time:325103ms step_avg:417.87ms step:789/6250 train_loss:2.7545 train_time:325488ms step_avg:417.83ms step:790/6250 train_loss:2.7901 train_time:325857ms step_avg:417.77ms step:791/6250 train_loss:2.8598 train_time:326249ms step_avg:417.73ms step:792/6250 train_loss:2.8121 train_time:326635ms step_avg:417.69ms step:793/6250 train_loss:2.8040 train_time:327034ms step_avg:417.67ms step:794/6250 train_loss:2.7792 train_time:327463ms step_avg:417.68ms step:795/6250 train_loss:2.7959 train_time:327858ms step_avg:417.65ms step:796/6250 train_loss:2.9782 train_time:328255ms step_avg:417.63ms step:797/6250 train_loss:2.7858 train_time:328665ms step_avg:417.62ms step:798/6250 train_loss:2.7957 train_time:329031ms step_avg:417.55ms step:799/6250 train_loss:2.7346 train_time:329405ms step_avg:417.50ms step:800/6250 train_loss:2.8358 train_time:329825ms step_avg:417.50ms step:801/6250 train_loss:2.7473 train_time:330222ms step_avg:417.47ms step:802/6250 train_loss:2.8237 train_time:330642ms step_avg:417.48ms step:803/6250 train_loss:2.7591 train_time:331114ms step_avg:417.55ms step:804/6250 train_loss:2.8371 train_time:331552ms step_avg:417.57ms step:805/6250 train_loss:2.7879 train_time:331958ms step_avg:417.56ms step:806/6250 train_loss:2.7853 train_time:332399ms step_avg:417.59ms step:807/6250 train_loss:2.7872 train_time:332827ms step_avg:417.60ms step:808/6250 train_loss:2.8465 train_time:333231ms step_avg:417.58ms step:809/6250 train_loss:2.7528 train_time:333659ms step_avg:417.60ms step:810/6250 train_loss:2.7186 train_time:334070ms step_avg:417.59ms step:811/6250 train_loss:2.8981 train_time:334482ms step_avg:417.58ms step:812/6250 train_loss:2.9227 train_time:334916ms step_avg:417.60ms step:813/6250 train_loss:2.8568 train_time:335323ms step_avg:417.59ms step:814/6250 train_loss:2.7954 train_time:335741ms step_avg:417.59ms step:815/6250 train_loss:2.7859 train_time:336166ms step_avg:417.60ms step:816/6250 train_loss:2.8543 train_time:336606ms step_avg:417.63ms step:817/6250 train_loss:2.8197 train_time:337045ms step_avg:417.65ms step:818/6250 train_loss:2.7589 train_time:337481ms step_avg:417.67ms step:819/6250 train_loss:2.7751 train_time:337921ms step_avg:417.70ms step:820/6250 train_loss:2.7935 train_time:338358ms step_avg:417.73ms step:821/6250 train_loss:2.7261 train_time:338727ms step_avg:417.67ms step:822/6250 train_loss:2.7735 train_time:339181ms step_avg:417.71ms step:823/6250 train_loss:2.7899 train_time:339632ms step_avg:417.75ms step:824/6250 train_loss:2.8057 train_time:340021ms step_avg:417.72ms step:825/6250 train_loss:2.8009 train_time:340491ms step_avg:417.78ms step:826/6250 train_loss:2.7377 train_time:340944ms step_avg:417.82ms step:827/6250 train_loss:2.8252 train_time:341314ms step_avg:417.77ms step:828/6250 train_loss:2.8691 train_time:341775ms step_avg:417.82ms step:829/6250 train_loss:2.8429 train_time:342233ms step_avg:417.87ms step:830/6250 train_loss:2.7662 train_time:342640ms step_avg:417.85ms step:831/6250 train_loss:2.8509 train_time:343108ms step_avg:417.91ms step:832/6250 train_loss:2.7757 train_time:343522ms step_avg:417.91ms step:833/6250 train_loss:2.7985 train_time:343957ms step_avg:417.93ms step:834/6250 train_loss:2.8507 train_time:344421ms step_avg:417.99ms step:835/6250 train_loss:2.7700 train_time:344845ms step_avg:417.99ms step:836/6250 train_loss:2.8431 train_time:345239ms step_avg:417.97ms step:837/6250 train_loss:2.7576 train_time:345676ms step_avg:417.99ms step:838/6250 train_loss:2.8158 train_time:346082ms step_avg:417.97ms step:839/6250 train_loss:2.8154 train_time:346511ms step_avg:417.99ms step:840/6250 train_loss:2.8091 train_time:346951ms step_avg:418.01ms step:841/6250 train_loss:2.9095 train_time:347327ms step_avg:417.96ms step:842/6250 train_loss:2.7806 train_time:347791ms step_avg:418.02ms step:843/6250 train_loss:2.7908 train_time:348192ms step_avg:418.00ms step:844/6250 train_loss:2.6798 train_time:348596ms step_avg:417.98ms step:845/6250 train_loss:2.8127 train_time:349013ms step_avg:417.98ms step:846/6250 train_loss:2.8464 train_time:349411ms step_avg:417.96ms step:847/6250 train_loss:2.7547 train_time:349814ms step_avg:417.94ms step:848/6250 train_loss:2.8768 train_time:350219ms step_avg:417.92ms step:849/6250 train_loss:2.7887 train_time:350629ms step_avg:417.91ms step:850/6250 train_loss:2.8960 train_time:351025ms step_avg:417.89ms step:851/6250 train_loss:2.6829 train_time:351421ms step_avg:417.86ms step:852/6250 train_loss:2.8629 train_time:351828ms step_avg:417.85ms step:853/6250 train_loss:2.7063 train_time:352239ms step_avg:417.84ms step:854/6250 train_loss:2.8441 train_time:352653ms step_avg:417.84ms step:855/6250 train_loss:2.7730 train_time:353069ms step_avg:417.83ms step:856/6250 train_loss:2.7455 train_time:353521ms step_avg:417.87ms step:857/6250 train_loss:2.7292 train_time:353919ms step_avg:417.85ms step:858/6250 train_loss:2.8713 train_time:354354ms step_avg:417.87ms step:859/6250 train_loss:2.7821 train_time:354754ms step_avg:417.85ms step:860/6250 train_loss:2.7306 train_time:355183ms step_avg:417.86ms step:861/6250 train_loss:2.7605 train_time:355565ms step_avg:417.82ms step:862/6250 train_loss:2.7905 train_time:356009ms step_avg:417.85ms step:863/6250 train_loss:2.7681 train_time:356416ms step_avg:417.84ms step:864/6250 train_loss:2.7322 train_time:356855ms step_avg:417.86ms step:865/6250 train_loss:2.7662 train_time:357270ms step_avg:417.86ms step:866/6250 train_loss:2.7538 train_time:357713ms step_avg:417.89ms step:867/6250 train_loss:2.7100 train_time:358120ms step_avg:417.88ms step:868/6250 train_loss:2.8025 train_time:358530ms step_avg:417.87ms step:869/6250 train_loss:2.7496 train_time:358986ms step_avg:417.91ms step:870/6250 train_loss:2.7541 train_time:359499ms step_avg:418.02ms step:871/6250 train_loss:2.8273 train_time:359909ms step_avg:418.01ms step:872/6250 train_loss:2.8689 train_time:360390ms step_avg:418.09ms step:873/6250 train_loss:2.7783 train_time:360887ms step_avg:418.18ms step:874/6250 train_loss:2.7587 train_time:361254ms step_avg:418.12ms step:875/6250 train_loss:2.7450 train_time:361645ms step_avg:418.09ms step:876/6250 train_loss:2.7752 train_time:362107ms step_avg:418.14ms step:877/6250 train_loss:2.8391 train_time:362513ms step_avg:418.12ms step:878/6250 train_loss:2.7074 train_time:362946ms step_avg:418.14ms step:879/6250 train_loss:2.6499 train_time:363375ms step_avg:418.15ms step:880/6250 train_loss:2.7414 train_time:363748ms step_avg:418.10ms step:881/6250 train_loss:2.8082 train_time:364163ms step_avg:418.10ms step:882/6250 train_loss:2.7675 train_time:364617ms step_avg:418.14ms step:883/6250 train_loss:2.8049 train_time:365015ms step_avg:418.12ms step:884/6250 train_loss:2.7176 train_time:365409ms step_avg:418.09ms step:885/6250 train_loss:2.6820 train_time:365887ms step_avg:418.16ms step:886/6250 train_loss:2.7845 train_time:366271ms step_avg:418.12ms step:887/6250 train_loss:2.7728 train_time:366771ms step_avg:418.21ms step:888/6250 train_loss:2.7922 train_time:367283ms step_avg:418.32ms step:889/6250 train_loss:2.7913 train_time:367685ms step_avg:418.30ms step:890/6250 train_loss:2.8014 train_time:368159ms step_avg:418.36ms step:891/6250 train_loss:2.7683 train_time:368617ms step_avg:418.41ms step:892/6250 train_loss:2.8300 train_time:369050ms step_avg:418.42ms step:893/6250 train_loss:2.8298 train_time:369475ms step_avg:418.43ms step:894/6250 train_loss:2.6973 train_time:369912ms step_avg:418.45ms step:895/6250 train_loss:2.7576 train_time:370307ms step_avg:418.43ms step:896/6250 train_loss:2.7430 train_time:370676ms step_avg:418.37ms step:897/6250 train_loss:2.7135 train_time:371095ms step_avg:418.37ms step:898/6250 train_loss:2.7516 train_time:371451ms step_avg:418.30ms step:899/6250 train_loss:2.7053 train_time:371850ms step_avg:418.28ms step:900/6250 train_loss:2.7382 train_time:372256ms step_avg:418.27ms step:901/6250 train_loss:2.7166 train_time:372638ms step_avg:418.22ms step:902/6250 train_loss:2.7649 train_time:373012ms step_avg:418.18ms step:903/6250 train_loss:2.8191 train_time:373409ms step_avg:418.15ms step:904/6250 train_loss:2.6873 train_time:373819ms step_avg:418.14ms step:905/6250 train_loss:2.6421 train_time:374204ms step_avg:418.11ms step:906/6250 train_loss:2.7467 train_time:374588ms step_avg:418.07ms step:907/6250 train_loss:2.8020 train_time:374971ms step_avg:418.03ms step:908/6250 train_loss:2.8323 train_time:375355ms step_avg:417.99ms step:909/6250 train_loss:2.7541 train_time:375780ms step_avg:418.00ms step:910/6250 train_loss:2.7882 train_time:376251ms step_avg:418.06ms step:911/6250 train_loss:2.7468 train_time:376619ms step_avg:418.00ms step:912/6250 train_loss:2.7297 train_time:377080ms step_avg:418.05ms step:913/6250 train_loss:2.8333 train_time:377514ms step_avg:418.07ms step:914/6250 train_loss:2.7183 train_time:377913ms step_avg:418.05ms step:915/6250 train_loss:2.7762 train_time:378337ms step_avg:418.05ms step:916/6250 train_loss:2.7627 train_time:378753ms step_avg:418.05ms step:917/6250 train_loss:2.6771 train_time:379168ms step_avg:418.05ms step:918/6250 train_loss:2.7506 train_time:379579ms step_avg:418.04ms step:919/6250 train_loss:2.7228 train_time:379993ms step_avg:418.03ms step:920/6250 train_loss:2.7836 train_time:380406ms step_avg:418.03ms step:921/6250 train_loss:2.7718 train_time:380837ms step_avg:418.04ms step:922/6250 train_loss:2.7241 train_time:381288ms step_avg:418.08ms step:923/6250 train_loss:2.7095 train_time:381747ms step_avg:418.12ms step:924/6250 train_loss:2.7797 train_time:382174ms step_avg:418.13ms step:925/6250 train_loss:2.7641 train_time:382590ms step_avg:418.13ms step:926/6250 train_loss:2.8497 train_time:383037ms step_avg:418.16ms step:927/6250 train_loss:2.8183 train_time:383488ms step_avg:418.20ms step:928/6250 train_loss:2.7486 train_time:383939ms step_avg:418.23ms step:929/6250 train_loss:2.7770 train_time:384347ms step_avg:418.22ms step:930/6250 train_loss:2.8416 train_time:384808ms step_avg:418.27ms step:931/6250 train_loss:2.7472 train_time:385218ms step_avg:418.26ms step:932/6250 train_loss:2.7411 train_time:385669ms step_avg:418.30ms step:933/6250 train_loss:2.7581 train_time:386083ms step_avg:418.29ms step:934/6250 train_loss:2.7785 train_time:386537ms step_avg:418.33ms step:935/6250 train_loss:2.6677 train_time:386985ms step_avg:418.36ms step:936/6250 train_loss:2.7663 train_time:387408ms step_avg:418.37ms step:937/6250 train_loss:2.7310 train_time:387865ms step_avg:418.41ms step:938/6250 train_loss:2.6658 train_time:388280ms step_avg:418.40ms step:939/6250 train_loss:2.7182 train_time:388718ms step_avg:418.43ms step:940/6250 train_loss:2.8072 train_time:389144ms step_avg:418.43ms step:941/6250 train_loss:2.7821 train_time:389577ms step_avg:418.45ms step:942/6250 train_loss:2.7450 train_time:390007ms step_avg:418.46ms step:943/6250 train_loss:2.7707 train_time:390458ms step_avg:418.50ms step:944/6250 train_loss:2.7238 train_time:390903ms step_avg:418.53ms step:945/6250 train_loss:2.7938 train_time:391357ms step_avg:418.56ms step:946/6250 train_loss:2.7742 train_time:391809ms step_avg:418.60ms step:947/6250 train_loss:2.7027 train_time:392222ms step_avg:418.59ms step:948/6250 train_loss:2.7045 train_time:392651ms step_avg:418.60ms step:949/6250 train_loss:2.7141 train_time:393029ms step_avg:418.56ms step:950/6250 train_loss:2.6499 train_time:393410ms step_avg:418.52ms step:951/6250 train_loss:2.7102 train_time:393776ms step_avg:418.47ms step:952/6250 train_loss:2.8998 train_time:394145ms step_avg:418.41ms step:953/6250 train_loss:2.7567 train_time:394514ms step_avg:418.36ms step:954/6250 train_loss:2.7233 train_time:394905ms step_avg:418.33ms step:955/6250 train_loss:2.7798 train_time:395352ms step_avg:418.36ms step:956/6250 train_loss:2.8526 train_time:395768ms step_avg:418.36ms step:957/6250 train_loss:2.7316 train_time:396221ms step_avg:418.40ms step:958/6250 train_loss:2.6764 train_time:396632ms step_avg:418.39ms step:959/6250 train_loss:2.6982 train_time:397066ms step_avg:418.41ms step:960/6250 train_loss:2.7815 train_time:397483ms step_avg:418.40ms step:961/6250 train_loss:2.7282 train_time:397863ms step_avg:418.36ms step:962/6250 train_loss:2.7540 train_time:398246ms step_avg:418.33ms step:963/6250 train_loss:2.7406 train_time:398626ms step_avg:418.29ms step:964/6250 train_loss:2.8211 train_time:398997ms step_avg:418.24ms step:965/6250 train_loss:2.7995 train_time:399364ms step_avg:418.18ms step:966/6250 train_loss:2.7361 train_time:399736ms step_avg:418.13ms step:967/6250 train_loss:2.7966 train_time:400149ms step_avg:418.13ms step:968/6250 train_loss:2.7738 train_time:400601ms step_avg:418.16ms step:969/6250 train_loss:2.6694 train_time:401016ms step_avg:418.16ms step:970/6250 train_loss:2.7672 train_time:401481ms step_avg:418.21ms step:971/6250 train_loss:2.8044 train_time:401898ms step_avg:418.21ms step:972/6250 train_loss:2.6651 train_time:402357ms step_avg:418.25ms step:973/6250 train_loss:2.7942 train_time:402771ms step_avg:418.25ms step:974/6250 train_loss:2.7210 train_time:403160ms step_avg:418.22ms step:975/6250 train_loss:2.7598 train_time:403534ms step_avg:418.17ms step:976/6250 train_loss:2.7645 train_time:403919ms step_avg:418.14ms step:977/6250 train_loss:2.7801 train_time:404296ms step_avg:418.09ms step:978/6250 train_loss:2.7946 train_time:404716ms step_avg:418.09ms step:979/6250 train_loss:2.7662 train_time:405164ms step_avg:418.13ms step:980/6250 train_loss:2.6663 train_time:405581ms step_avg:418.12ms step:981/6250 train_loss:2.8106 train_time:406046ms step_avg:418.17ms step:982/6250 train_loss:2.8017 train_time:406464ms step_avg:418.17ms step:983/6250 train_loss:2.7834 train_time:406866ms step_avg:418.16ms step:984/6250 train_loss:2.8811 train_time:407238ms step_avg:418.11ms step:985/6250 train_loss:2.7259 train_time:407622ms step_avg:418.07ms step:986/6250 train_loss:2.8194 train_time:407998ms step_avg:418.03ms step:987/6250 train_loss:2.7340 train_time:408367ms step_avg:417.98ms step:988/6250 train_loss:2.7193 train_time:408744ms step_avg:417.94ms step:989/6250 train_loss:2.6578 train_time:409178ms step_avg:417.95ms step:990/6250 train_loss:2.7825 train_time:409618ms step_avg:417.98ms step:991/6250 train_loss:2.7191 train_time:410053ms step_avg:417.99ms step:992/6250 train_loss:2.7222 train_time:410515ms step_avg:418.04ms step:993/6250 train_loss:2.7705 train_time:410940ms step_avg:418.05ms step:994/6250 train_loss:2.7731 train_time:411370ms step_avg:418.06ms step:995/6250 train_loss:2.7647 train_time:411763ms step_avg:418.03ms step:996/6250 train_loss:2.8008 train_time:412144ms step_avg:418.00ms step:997/6250 train_loss:2.8488 train_time:412522ms step_avg:417.96ms step:998/6250 train_loss:2.7612 train_time:412909ms step_avg:417.92ms step:999/6250 train_loss:2.6723 train_time:413363ms step_avg:417.96ms step:1000/6250 train_loss:2.7597 train_time:413823ms step_avg:418.00ms step:1001/6250 train_loss:2.7219 train_time:414239ms step_avg:418.00ms step:1002/6250 train_loss:2.7063 train_time:414656ms step_avg:418.00ms step:1003/6250 train_loss:2.7556 train_time:415073ms step_avg:418.00ms step:1004/6250 train_loss:2.7220 train_time:415458ms step_avg:417.97ms step:1005/6250 train_loss:2.7390 train_time:415841ms step_avg:417.93ms step:1006/6250 train_loss:2.7662 train_time:416218ms step_avg:417.89ms step:1007/6250 train_loss:2.7575 train_time:416620ms step_avg:417.87ms step:1008/6250 train_loss:2.7023 train_time:417070ms step_avg:417.91ms step:1009/6250 train_loss:2.7291 train_time:417498ms step_avg:417.92ms step:1010/6250 train_loss:2.7241 train_time:417914ms step_avg:417.91ms step:1011/6250 train_loss:2.6960 train_time:418309ms step_avg:417.89ms step:1012/6250 train_loss:2.6855 train_time:418690ms step_avg:417.85ms step:1013/6250 train_loss:2.7866 train_time:419074ms step_avg:417.82ms step:1014/6250 train_loss:2.7936 train_time:419445ms step_avg:417.77ms step:1015/6250 train_loss:2.7813 train_time:419893ms step_avg:417.80ms step:1016/6250 train_loss:2.7902 train_time:420331ms step_avg:417.82ms step:1017/6250 train_loss:2.7061 train_time:420766ms step_avg:417.84ms step:1018/6250 train_loss:2.7507 train_time:421181ms step_avg:417.84ms step:1019/6250 train_loss:2.7137 train_time:421622ms step_avg:417.86ms step:1020/6250 train_loss:2.7257 train_time:422054ms step_avg:417.88ms step:1021/6250 train_loss:2.7020 train_time:422466ms step_avg:417.87ms step:1022/6250 train_loss:2.7393 train_time:422925ms step_avg:417.91ms step:1023/6250 train_loss:2.7391 train_time:423343ms step_avg:417.91ms step:1024/6250 train_loss:2.8655 train_time:423807ms step_avg:417.96ms step:1025/6250 train_loss:2.7671 train_time:424221ms step_avg:417.95ms step:1026/6250 train_loss:2.7207 train_time:424649ms step_avg:417.96ms step:1027/6250 train_loss:2.6700 train_time:425042ms step_avg:417.94ms step:1028/6250 train_loss:2.7011 train_time:425418ms step_avg:417.90ms step:1029/6250 train_loss:2.6863 train_time:425864ms step_avg:417.92ms step:1030/6250 train_loss:2.7290 train_time:426319ms step_avg:417.96ms step:1031/6250 train_loss:2.7478 train_time:426732ms step_avg:417.95ms step:1032/6250 train_loss:2.7952 train_time:427190ms step_avg:417.99ms step:1033/6250 train_loss:2.6993 train_time:427638ms step_avg:418.02ms step:1034/6250 train_loss:2.7515 train_time:428102ms step_avg:418.07ms step:1035/6250 train_loss:2.6916 train_time:428567ms step_avg:418.11ms step:1036/6250 train_loss:2.7841 train_time:429029ms step_avg:418.16ms step:1037/6250 train_loss:2.8119 train_time:429488ms step_avg:418.20ms step:1038/6250 train_loss:2.6663 train_time:429940ms step_avg:418.23ms step:1039/6250 train_loss:2.7147 train_time:430400ms step_avg:418.27ms step:1040/6250 train_loss:2.6881 train_time:430866ms step_avg:418.32ms step:1041/6250 train_loss:2.7082 train_time:431309ms step_avg:418.34ms step:1042/6250 train_loss:2.7287 train_time:431775ms step_avg:418.39ms step:1043/6250 train_loss:2.7063 train_time:432235ms step_avg:418.43ms step:1044/6250 train_loss:2.8018 train_time:432686ms step_avg:418.46ms step:1045/6250 train_loss:2.7830 train_time:433147ms step_avg:418.50ms step:1046/6250 train_loss:2.7417 train_time:433609ms step_avg:418.54ms step:1047/6250 train_loss:2.7695 train_time:434072ms step_avg:418.58ms step:1048/6250 train_loss:2.7121 train_time:434530ms step_avg:418.62ms step:1049/6250 train_loss:2.7158 train_time:434992ms step_avg:418.66ms step:1050/6250 train_loss:2.7093 train_time:435453ms step_avg:418.70ms step:1051/6250 train_loss:2.7031 train_time:435914ms step_avg:418.75ms step:1052/6250 train_loss:2.7140 train_time:436375ms step_avg:418.79ms step:1053/6250 train_loss:2.6647 train_time:436788ms step_avg:418.78ms step:1054/6250 train_loss:2.7442 train_time:437171ms step_avg:418.75ms step:1055/6250 train_loss:2.6723 train_time:437553ms step_avg:418.71ms step:1056/6250 train_loss:2.6954 train_time:437953ms step_avg:418.69ms step:1057/6250 train_loss:2.7019 train_time:438332ms step_avg:418.66ms step:1058/6250 train_loss:2.7238 train_time:438712ms step_avg:418.62ms step:1059/6250 train_loss:2.8331 train_time:439093ms step_avg:418.58ms step:1060/6250 train_loss:2.6963 train_time:439476ms step_avg:418.55ms step:1061/6250 train_loss:2.7740 train_time:439857ms step_avg:418.51ms step:1062/6250 train_loss:2.7532 train_time:440235ms step_avg:418.47ms step:1063/6250 train_loss:2.7792 train_time:440614ms step_avg:418.44ms step:1064/6250 train_loss:2.7232 train_time:440994ms step_avg:418.40ms step:1065/6250 train_loss:2.7489 train_time:441373ms step_avg:418.36ms step:1066/6250 train_loss:2.7614 train_time:441754ms step_avg:418.33ms step:1067/6250 train_loss:2.7150 train_time:442134ms step_avg:418.29ms step:1068/6250 train_loss:2.8403 train_time:442513ms step_avg:418.25ms step:1069/6250 train_loss:2.7579 train_time:442897ms step_avg:418.22ms step:1070/6250 train_loss:2.7664 train_time:443278ms step_avg:418.19ms step:1071/6250 train_loss:2.8326 train_time:443658ms step_avg:418.15ms step:1072/6250 train_loss:2.7560 train_time:444095ms step_avg:418.17ms step:1073/6250 train_loss:2.7648 train_time:444533ms step_avg:418.19ms step:1074/6250 train_loss:2.7329 train_time:444996ms step_avg:418.23ms step:1075/6250 train_loss:2.6896 train_time:445410ms step_avg:418.23ms step:1076/6250 train_loss:2.6870 train_time:445803ms step_avg:418.20ms step:1077/6250 train_loss:2.7000 train_time:446203ms step_avg:418.18ms step:1078/6250 train_loss:2.7583 train_time:446583ms step_avg:418.15ms step:1079/6250 train_loss:2.7296 train_time:446965ms step_avg:418.12ms step:1080/6250 train_loss:2.6660 train_time:447346ms step_avg:418.08ms step:1081/6250 train_loss:2.6995 train_time:447802ms step_avg:418.12ms step:1082/6250 train_loss:2.7654 train_time:448259ms step_avg:418.15ms step:1083/6250 train_loss:2.7003 train_time:448674ms step_avg:418.15ms step:1084/6250 train_loss:2.8467 train_time:449101ms step_avg:418.16ms step:1085/6250 train_loss:2.7552 train_time:449525ms step_avg:418.16ms step:1086/6250 train_loss:2.7021 train_time:449910ms step_avg:418.13ms step:1087/6250 train_loss:2.7268 train_time:450309ms step_avg:418.11ms step:1088/6250 train_loss:2.8094 train_time:450691ms step_avg:418.08ms step:1089/6250 train_loss:2.6990 train_time:451071ms step_avg:418.05ms step:1090/6250 train_loss:2.8368 train_time:451450ms step_avg:418.01ms step:1091/6250 train_loss:2.8107 train_time:451833ms step_avg:417.98ms step:1092/6250 train_loss:2.6856 train_time:452216ms step_avg:417.94ms step:1093/6250 train_loss:2.7492 train_time:452592ms step_avg:417.91ms step:1094/6250 train_loss:2.7148 train_time:453000ms step_avg:417.90ms step:1095/6250 train_loss:2.7723 train_time:453446ms step_avg:417.92ms step:1096/6250 train_loss:2.7475 train_time:453859ms step_avg:417.92ms step:1097/6250 train_loss:2.7846 train_time:454316ms step_avg:417.95ms step:1098/6250 train_loss:2.7742 train_time:454724ms step_avg:417.94ms step:1099/6250 train_loss:2.8289 train_time:455118ms step_avg:417.92ms step:1100/6250 train_loss:2.7695 train_time:455518ms step_avg:417.91ms step:1101/6250 train_loss:2.7996 train_time:455905ms step_avg:417.88ms step:1102/6250 train_loss:2.7590 train_time:456306ms step_avg:417.86ms step:1103/6250 train_loss:2.6956 train_time:456763ms step_avg:417.90ms step:1104/6250 train_loss:2.7508 train_time:457186ms step_avg:417.90ms step:1105/6250 train_loss:2.7204 train_time:457596ms step_avg:417.90ms step:1106/6250 train_loss:2.8221 train_time:458005ms step_avg:417.89ms step:1107/6250 train_loss:2.7868 train_time:458397ms step_avg:417.86ms step:1108/6250 train_loss:2.6814 train_time:458794ms step_avg:417.85ms step:1109/6250 train_loss:2.7687 train_time:459177ms step_avg:417.81ms step:1110/6250 train_loss:2.7184 train_time:459557ms step_avg:417.78ms step:1111/6250 train_loss:2.7141 train_time:459949ms step_avg:417.76ms step:1112/6250 train_loss:2.8260 train_time:460409ms step_avg:417.79ms step:1113/6250 train_loss:2.7162 train_time:460822ms step_avg:417.79ms step:1114/6250 train_loss:2.7350 train_time:461234ms step_avg:417.78ms step:1115/6250 train_loss:2.6778 train_time:461699ms step_avg:417.83ms step:1116/6250 train_loss:2.5861 train_time:462157ms step_avg:417.86ms step:1117/6250 train_loss:2.6819 train_time:462616ms step_avg:417.90ms step:1118/6250 train_loss:2.6588 train_time:463074ms step_avg:417.94ms step:1119/6250 train_loss:2.6487 train_time:463535ms step_avg:417.98ms step:1120/6250 train_loss:2.6744 train_time:463991ms step_avg:418.01ms step:1121/6250 train_loss:2.8131 train_time:464448ms step_avg:418.05ms step:1122/6250 train_loss:2.7100 train_time:464882ms step_avg:418.06ms step:1123/6250 train_loss:2.6250 train_time:465338ms step_avg:418.09ms step:1124/6250 train_loss:2.7446 train_time:465797ms step_avg:418.13ms step:1125/6250 train_loss:2.7939 train_time:466175ms step_avg:418.09ms step:1126/6250 train_loss:2.6255 train_time:466583ms step_avg:418.09ms step:1127/6250 train_loss:2.8069 train_time:467038ms step_avg:418.12ms step:1128/6250 train_loss:2.6265 train_time:467441ms step_avg:418.11ms step:1129/6250 train_loss:2.8010 train_time:467895ms step_avg:418.14ms step:1130/6250 train_loss:2.7066 train_time:468341ms step_avg:418.16ms step:1131/6250 train_loss:2.7379 train_time:468797ms step_avg:418.20ms step:1132/6250 train_loss:2.7410 train_time:469243ms step_avg:418.22ms step:1133/6250 train_loss:2.7405 train_time:469706ms step_avg:418.26ms step:1134/6250 train_loss:2.6573 train_time:470159ms step_avg:418.29ms step:1135/6250 train_loss:2.7714 train_time:470613ms step_avg:418.32ms step:1136/6250 train_loss:2.7168 train_time:471013ms step_avg:418.31ms step:1137/6250 train_loss:2.7421 train_time:471459ms step_avg:418.33ms step:1138/6250 train_loss:2.8207 train_time:471917ms step_avg:418.37ms step:1139/6250 train_loss:2.7397 train_time:472328ms step_avg:418.36ms step:1140/6250 train_loss:2.7493 train_time:472783ms step_avg:418.39ms step:1141/6250 train_loss:2.6891 train_time:473238ms step_avg:418.42ms step:1142/6250 train_loss:2.6549 train_time:473695ms step_avg:418.46ms step:1143/6250 train_loss:2.7063 train_time:474136ms step_avg:418.48ms step:1144/6250 train_loss:2.6929 train_time:474563ms step_avg:418.49ms step:1145/6250 train_loss:2.6599 train_time:475023ms step_avg:418.52ms step:1146/6250 train_loss:2.7694 train_time:475441ms step_avg:418.52ms step:1147/6250 train_loss:2.7355 train_time:475899ms step_avg:418.56ms step:1148/6250 train_loss:2.7552 train_time:476342ms step_avg:418.58ms step:1149/6250 train_loss:2.6665 train_time:476797ms step_avg:418.61ms step:1150/6250 train_loss:2.6638 train_time:477249ms step_avg:418.64ms step:1151/6250 train_loss:2.6517 train_time:477700ms step_avg:418.67ms step:1152/6250 train_loss:2.7064 train_time:478154ms step_avg:418.70ms step:1153/6250 train_loss:2.7162 train_time:478562ms step_avg:418.69ms step:1154/6250 train_loss:2.7293 train_time:479019ms step_avg:418.72ms step:1155/6250 train_loss:2.7097 train_time:479472ms step_avg:418.75ms step:1156/6250 train_loss:2.7545 train_time:479928ms step_avg:418.79ms step:1157/6250 train_loss:2.6845 train_time:480335ms step_avg:418.78ms step:1158/6250 train_loss:2.6774 train_time:480690ms step_avg:418.72ms step:1159/6250 train_loss:2.8053 train_time:481042ms step_avg:418.66ms step:1160/6250 train_loss:2.6975 train_time:481495ms step_avg:418.69ms step:1161/6250 train_loss:2.7910 train_time:481952ms step_avg:418.72ms step:1162/6250 train_loss:2.6677 train_time:482303ms step_avg:418.67ms step:1163/6250 train_loss:2.7307 train_time:482657ms step_avg:418.61ms step:1164/6250 train_loss:2.6177 train_time:483072ms step_avg:418.61ms step:1165/6250 train_loss:2.7510 train_time:483422ms step_avg:418.55ms step:1166/6250 train_loss:2.6592 train_time:483775ms step_avg:418.49ms step:1167/6250 train_loss:2.7420 train_time:484132ms step_avg:418.44ms step:1168/6250 train_loss:2.7258 train_time:484491ms step_avg:418.39ms step:1169/6250 train_loss:2.7057 train_time:484845ms step_avg:418.33ms step:1170/6250 train_loss:2.7521 train_time:485241ms step_avg:418.31ms step:1171/6250 train_loss:2.7003 train_time:485693ms step_avg:418.34ms step:1172/6250 train_loss:2.6536 train_time:486059ms step_avg:418.30ms step:1173/6250 train_loss:2.7988 train_time:486416ms step_avg:418.24ms step:1174/6250 train_loss:2.7944 train_time:486771ms step_avg:418.19ms step:1175/6250 train_loss:2.7542 train_time:487127ms step_avg:418.14ms step:1176/6250 train_loss:2.6842 train_time:487480ms step_avg:418.08ms step:1177/6250 train_loss:2.7617 train_time:487894ms step_avg:418.08ms step:1178/6250 train_loss:2.7317 train_time:488324ms step_avg:418.09ms step:1179/6250 train_loss:2.7518 train_time:488676ms step_avg:418.03ms step:1180/6250 train_loss:2.6962 train_time:489037ms step_avg:417.98ms step:1181/6250 train_loss:2.8059 train_time:489461ms step_avg:417.99ms step:1182/6250 train_loss:2.7536 train_time:489919ms step_avg:418.02ms step:1183/6250 train_loss:2.6577 train_time:490374ms step_avg:418.05ms step:1184/6250 train_loss:2.6769 train_time:490831ms step_avg:418.08ms step:1185/6250 train_loss:2.7076 train_time:491281ms step_avg:418.11ms step:1186/6250 train_loss:2.7124 train_time:491654ms step_avg:418.07ms step:1187/6250 train_loss:2.6511 train_time:492012ms step_avg:418.02ms step:1188/6250 train_loss:2.5843 train_time:492363ms step_avg:417.97ms step:1189/6250 train_loss:2.7352 train_time:492826ms step_avg:418.00ms step:1190/6250 train_loss:2.7346 train_time:493270ms step_avg:418.03ms step:1191/6250 train_loss:2.7109 train_time:493727ms step_avg:418.06ms step:1192/6250 train_loss:2.6922 train_time:494181ms step_avg:418.09ms step:1193/6250 train_loss:2.7715 train_time:494583ms step_avg:418.07ms step:1194/6250 train_loss:2.7962 train_time:494935ms step_avg:418.02ms step:1195/6250 train_loss:2.8460 train_time:495292ms step_avg:417.97ms step:1196/6250 train_loss:2.6274 train_time:495646ms step_avg:417.91ms step:1197/6250 train_loss:2.6441 train_time:496003ms step_avg:417.86ms step:1198/6250 train_loss:2.6930 train_time:496431ms step_avg:417.87ms step:1199/6250 train_loss:2.6173 train_time:496893ms step_avg:417.91ms step:1200/6250 train_loss:2.6584 train_time:497340ms step_avg:417.93ms step:1201/6250 train_loss:2.8010 train_time:497738ms step_avg:417.92ms step:1202/6250 train_loss:2.6859 train_time:498090ms step_avg:417.86ms step:1203/6250 train_loss:2.6503 train_time:498448ms step_avg:417.81ms step:1204/6250 train_loss:2.7211 train_time:498800ms step_avg:417.76ms step:1205/6250 train_loss:2.7407 train_time:499175ms step_avg:417.72ms step:1206/6250 train_loss:2.7663 train_time:499632ms step_avg:417.75ms step:1207/6250 train_loss:2.6949 train_time:500085ms step_avg:417.78ms step:1208/6250 train_loss:2.6985 train_time:500534ms step_avg:417.81ms step:1209/6250 train_loss:2.7491 train_time:500943ms step_avg:417.80ms step:1210/6250 train_loss:2.6782 train_time:501296ms step_avg:417.75ms step:1211/6250 train_loss:2.7270 train_time:501705ms step_avg:417.74ms step:1212/6250 train_loss:2.7798 train_time:502115ms step_avg:417.73ms step:1213/6250 train_loss:2.6664 train_time:502575ms step_avg:417.77ms step:1214/6250 train_loss:2.7109 train_time:503003ms step_avg:417.78ms step:1215/6250 train_loss:2.7208 train_time:503429ms step_avg:417.78ms step:1216/6250 train_loss:2.6536 train_time:503864ms step_avg:417.80ms step:1217/6250 train_loss:2.7767 train_time:504291ms step_avg:417.81ms step:1218/6250 train_loss:2.6949 train_time:504745ms step_avg:417.84ms step:1219/6250 train_loss:2.7341 train_time:505189ms step_avg:417.86ms step:1220/6250 train_loss:2.7725 train_time:505645ms step_avg:417.89ms step:1221/6250 train_loss:2.7598 train_time:506100ms step_avg:417.92ms step:1222/6250 train_loss:2.6839 train_time:506514ms step_avg:417.92ms step:1223/6250 train_loss:2.6816 train_time:506972ms step_avg:417.95ms step:1224/6250 train_loss:2.6924 train_time:507391ms step_avg:417.95ms step:1225/6250 train_loss:2.7335 train_time:507810ms step_avg:417.95ms step:1226/6250 train_loss:2.5907 train_time:508263ms step_avg:417.98ms step:1227/6250 train_loss:2.6375 train_time:508722ms step_avg:418.01ms step:1228/6250 train_loss:2.7696 train_time:509176ms step_avg:418.04ms step:1229/6250 train_loss:2.7206 train_time:509597ms step_avg:418.05ms step:1230/6250 train_loss:2.7183 train_time:510050ms step_avg:418.07ms step:1231/6250 train_loss:2.7396 train_time:510505ms step_avg:418.10ms step:1232/6250 train_loss:2.7323 train_time:510949ms step_avg:418.12ms step:1233/6250 train_loss:2.8476 train_time:511358ms step_avg:418.12ms step:1234/6250 train_loss:2.6657 train_time:511820ms step_avg:418.15ms step:1235/6250 train_loss:2.6616 train_time:512237ms step_avg:418.15ms step:1236/6250 train_loss:2.7540 train_time:512689ms step_avg:418.18ms step:1237/6250 train_loss:2.6253 train_time:513143ms step_avg:418.21ms step:1238/6250 train_loss:2.6449 train_time:513595ms step_avg:418.24ms step:1239/6250 train_loss:2.7466 train_time:514050ms step_avg:418.27ms step:1240/6250 train_loss:2.6103 train_time:514504ms step_avg:418.30ms step:1241/6250 train_loss:2.7417 train_time:514961ms step_avg:418.33ms step:1242/6250 train_loss:2.7913 train_time:515414ms step_avg:418.36ms step:1243/6250 train_loss:2.6763 train_time:515827ms step_avg:418.35ms step:1244/6250 train_loss:2.6763 train_time:516280ms step_avg:418.38ms step:1245/6250 train_loss:2.6458 train_time:516737ms step_avg:418.41ms step:1246/6250 train_loss:2.6980 train_time:517193ms step_avg:418.44ms step:1247/6250 train_loss:2.6078 train_time:517653ms step_avg:418.47ms step:1248/6250 train_loss:2.7070 train_time:518108ms step_avg:418.50ms step:1249/6250 train_loss:2.7765 train_time:518553ms step_avg:418.53ms step:1250/6250 train_loss:2.7407 train_time:519010ms step_avg:418.56ms step:1251/6250 train_loss:2.6677 train_time:519467ms step_avg:418.59ms step:1252/6250 train_loss:2.7562 train_time:519913ms step_avg:418.61ms step:1253/6250 train_loss:2.7286 train_time:520367ms step_avg:418.64ms step:1254/6250 train_loss:2.7853 train_time:520824ms step_avg:418.67ms step:1255/6250 train_loss:2.7860 train_time:521241ms step_avg:418.67ms step:1256/6250 train_loss:2.7101 train_time:521696ms step_avg:418.70ms step:1257/6250 train_loss:2.6591 train_time:522100ms step_avg:418.68ms step:1258/6250 train_loss:2.7595 train_time:522551ms step_avg:418.71ms step:1259/6250 train_loss:2.6759 train_time:523002ms step_avg:418.74ms step:1260/6250 train_loss:2.6277 train_time:523417ms step_avg:418.73ms step:1261/6250 train_loss:2.7187 train_time:523867ms step_avg:418.76ms step:1262/6250 train_loss:2.7724 train_time:524292ms step_avg:418.76ms step:1263/6250 train_loss:2.7237 train_time:524750ms step_avg:418.80ms step:1264/6250 train_loss:2.7148 train_time:525200ms step_avg:418.82ms step:1265/6250 train_loss:2.7329 train_time:525627ms step_avg:418.83ms step:1266/6250 train_loss:2.6408 train_time:526080ms step_avg:418.85ms step:1267/6250 train_loss:2.7103 train_time:526539ms step_avg:418.89ms step:1268/6250 train_loss:2.7026 train_time:526952ms step_avg:418.88ms step:1269/6250 train_loss:2.6360 train_time:527409ms step_avg:418.91ms step:1270/6250 train_loss:2.6316 train_time:527866ms step_avg:418.94ms step:1271/6250 train_loss:2.7344 train_time:528319ms step_avg:418.97ms step:1272/6250 train_loss:2.6876 train_time:528775ms step_avg:419.00ms step:1273/6250 train_loss:2.6981 train_time:529230ms step_avg:419.03ms step:1274/6250 train_loss:2.7239 train_time:529682ms step_avg:419.05ms step:1275/6250 train_loss:2.7252 train_time:530135ms step_avg:419.08ms step:1276/6250 train_loss:2.6006 train_time:530545ms step_avg:419.07ms step:1277/6250 train_loss:2.6746 train_time:531002ms step_avg:419.10ms step:1278/6250 train_loss:2.7941 train_time:531441ms step_avg:419.12ms step:1279/6250 train_loss:2.6561 train_time:531869ms step_avg:419.12ms step:1280/6250 train_loss:2.7702 train_time:532322ms step_avg:419.15ms step:1281/6250 train_loss:2.7280 train_time:532770ms step_avg:419.17ms step:1282/6250 train_loss:2.7058 train_time:533226ms step_avg:419.20ms step:1283/6250 train_loss:2.7488 train_time:533624ms step_avg:419.19ms step:1284/6250 train_loss:2.6510 train_time:534078ms step_avg:419.21ms step:1285/6250 train_loss:2.7109 train_time:534535ms step_avg:419.24ms step:1286/6250 train_loss:2.7693 train_time:534989ms step_avg:419.27ms step:1287/6250 train_loss:2.7511 train_time:535441ms step_avg:419.30ms step:1288/6250 train_loss:2.7567 train_time:535859ms step_avg:419.30ms step:1289/6250 train_loss:2.6669 train_time:536272ms step_avg:419.29ms step:1290/6250 train_loss:2.6802 train_time:536721ms step_avg:419.31ms step:1291/6250 train_loss:2.7645 train_time:537166ms step_avg:419.33ms step:1292/6250 train_loss:2.6350 train_time:537620ms step_avg:419.36ms step:1293/6250 train_loss:2.6898 train_time:538074ms step_avg:419.39ms step:1294/6250 train_loss:2.7986 train_time:538512ms step_avg:419.40ms step:1295/6250 train_loss:2.7363 train_time:538964ms step_avg:419.43ms step:1296/6250 train_loss:2.7211 train_time:539416ms step_avg:419.45ms step:1297/6250 train_loss:2.6543 train_time:539859ms step_avg:419.47ms step:1298/6250 train_loss:2.7653 train_time:540314ms step_avg:419.50ms step:1299/6250 train_loss:2.6973 train_time:540757ms step_avg:419.52ms step:1300/6250 train_loss:2.6899 train_time:541210ms step_avg:419.54ms step:1301/6250 train_loss:2.7361 train_time:541663ms step_avg:419.57ms step:1302/6250 train_loss:2.7201 train_time:542113ms step_avg:419.59ms step:1303/6250 train_loss:2.7791 train_time:542561ms step_avg:419.61ms step:1304/6250 train_loss:2.7115 train_time:543016ms step_avg:419.64ms step:1305/6250 train_loss:2.6528 train_time:543469ms step_avg:419.67ms step:1306/6250 train_loss:2.6205 train_time:543882ms step_avg:419.66ms step:1307/6250 train_loss:2.7771 train_time:544327ms step_avg:419.68ms step:1308/6250 train_loss:2.7631 train_time:544786ms step_avg:419.71ms step:1309/6250 train_loss:2.7433 train_time:545245ms step_avg:419.74ms step:1310/6250 train_loss:2.6928 train_time:545655ms step_avg:419.73ms step:1311/6250 train_loss:2.6972 train_time:546090ms step_avg:419.75ms step:1312/6250 train_loss:2.7554 train_time:546539ms step_avg:419.77ms step:1313/6250 train_loss:2.6785 train_time:546961ms step_avg:419.77ms step:1314/6250 train_loss:2.6945 train_time:547419ms step_avg:419.80ms step:1315/6250 train_loss:2.7120 train_time:547829ms step_avg:419.79ms step:1316/6250 train_loss:2.6302 train_time:548266ms step_avg:419.81ms step:1317/6250 train_loss:2.6890 train_time:548701ms step_avg:419.82ms step:1318/6250 train_loss:2.6447 train_time:549128ms step_avg:419.82ms step:1319/6250 train_loss:2.7500 train_time:549589ms step_avg:419.85ms step:1320/6250 train_loss:2.7467 train_time:550012ms step_avg:419.86ms step:1321/6250 train_loss:2.7014 train_time:550438ms step_avg:419.86ms step:1322/6250 train_loss:2.6827 train_time:550868ms step_avg:419.87ms step:1323/6250 train_loss:2.6588 train_time:551298ms step_avg:419.88ms step:1324/6250 train_loss:2.7783 train_time:551748ms step_avg:419.90ms step:1325/6250 train_loss:2.7493 train_time:552167ms step_avg:419.90ms step:1326/6250 train_loss:2.7913 train_time:552610ms step_avg:419.92ms step:1327/6250 train_loss:2.6077 train_time:553065ms step_avg:419.94ms step:1328/6250 train_loss:2.7047 train_time:553519ms step_avg:419.97ms step:1329/6250 train_loss:2.6748 train_time:553878ms step_avg:419.92ms step:1330/6250 train_loss:2.6036 train_time:554216ms step_avg:419.86ms step:1331/6250 train_loss:2.6359 train_time:554563ms step_avg:419.81ms step:1332/6250 train_loss:2.6954 train_time:554902ms step_avg:419.74ms step:1333/6250 train_loss:2.6661 train_time:555287ms step_avg:419.72ms step:1334/6250 train_loss:2.6981 train_time:555747ms step_avg:419.75ms step:1335/6250 train_loss:2.7257 train_time:556148ms step_avg:419.73ms step:1336/6250 train_loss:2.6410 train_time:556555ms step_avg:419.72ms step:1337/6250 train_loss:2.7374 train_time:556894ms step_avg:419.66ms step:1338/6250 train_loss:2.6229 train_time:557239ms step_avg:419.61ms step:1339/6250 train_loss:2.6451 train_time:557579ms step_avg:419.55ms step:1340/6250 train_loss:2.6824 train_time:557950ms step_avg:419.51ms step:1341/6250 train_loss:2.7679 train_time:558383ms step_avg:419.52ms step:1342/6250 train_loss:2.6175 train_time:558845ms step_avg:419.55ms step:1343/6250 train_loss:2.6936 train_time:559212ms step_avg:419.51ms step:1344/6250 train_loss:2.7633 train_time:559552ms step_avg:419.45ms step:1345/6250 train_loss:2.7024 train_time:559899ms step_avg:419.40ms step:1346/6250 train_loss:2.6524 train_time:560240ms step_avg:419.34ms step:1347/6250 train_loss:2.7147 train_time:560596ms step_avg:419.29ms step:1348/6250 train_loss:2.7014 train_time:561035ms step_avg:419.31ms step:1349/6250 train_loss:2.6644 train_time:561451ms step_avg:419.31ms step:1350/6250 train_loss:2.7205 train_time:561863ms step_avg:419.30ms step:1351/6250 train_loss:2.6896 train_time:562313ms step_avg:419.32ms step:1352/6250 train_loss:2.7791 train_time:562772ms step_avg:419.35ms step:1353/6250 train_loss:2.6905 train_time:563223ms step_avg:419.38ms step:1354/6250 train_loss:2.6755 train_time:563679ms step_avg:419.40ms step:1355/6250 train_loss:2.7058 train_time:564119ms step_avg:419.42ms step:1356/6250 train_loss:2.6502 train_time:564469ms step_avg:419.37ms step:1357/6250 train_loss:2.6463 train_time:564810ms step_avg:419.31ms step:1358/6250 train_loss:2.7557 train_time:565248ms step_avg:419.32ms step:1359/6250 train_loss:2.6419 train_time:565711ms step_avg:419.36ms step:1360/6250 train_loss:2.6423 train_time:566135ms step_avg:419.36ms step:1361/6250 train_loss:2.5951 train_time:566474ms step_avg:419.30ms step:1362/6250 train_loss:2.6304 train_time:566816ms step_avg:419.24ms step:1363/6250 train_loss:2.8072 train_time:567160ms step_avg:419.19ms step:1364/6250 train_loss:2.7199 train_time:567500ms step_avg:419.13ms step:1365/6250 train_loss:2.6712 train_time:567961ms step_avg:419.16ms step:1366/6250 train_loss:2.6189 train_time:568361ms step_avg:419.15ms step:1367/6250 train_loss:2.6187 train_time:568819ms step_avg:419.17ms step:1368/6250 train_loss:2.6405 train_time:569237ms step_avg:419.17ms step:1369/6250 train_loss:2.6309 train_time:569685ms step_avg:419.19ms step:1370/6250 train_loss:2.6613 train_time:570139ms step_avg:419.22ms step:1371/6250 train_loss:2.5790 train_time:570584ms step_avg:419.24ms step:1372/6250 train_loss:2.6348 train_time:571031ms step_avg:419.26ms step:1373/6250 train_loss:2.7231 train_time:571480ms step_avg:419.28ms step:1374/6250 train_loss:2.6500 train_time:571915ms step_avg:419.29ms step:1375/6250 train_loss:2.6708 train_time:572348ms step_avg:419.30ms step:1376/6250 train_loss:2.7361 train_time:572804ms step_avg:419.33ms step:1377/6250 train_loss:2.6363 train_time:573275ms step_avg:419.37ms step:1378/6250 train_loss:2.7213 train_time:573736ms step_avg:419.40ms step:1379/6250 train_loss:2.7625 train_time:574137ms step_avg:419.38ms step:1380/6250 train_loss:2.6683 train_time:574590ms step_avg:419.41ms step:1381/6250 train_loss:2.6687 train_time:575001ms step_avg:419.40ms step:1382/6250 train_loss:2.5866 train_time:575464ms step_avg:419.43ms step:1383/6250 train_loss:2.6782 train_time:575892ms step_avg:419.44ms step:1384/6250 train_loss:2.7233 train_time:576343ms step_avg:419.46ms step:1385/6250 train_loss:2.6679 train_time:576806ms step_avg:419.50ms step:1386/6250 train_loss:2.6290 train_time:577232ms step_avg:419.50ms step:1387/6250 train_loss:2.7078 train_time:577680ms step_avg:419.52ms step:1388/6250 train_loss:2.6752 train_time:578110ms step_avg:419.53ms step:1389/6250 train_loss:2.6822 train_time:578537ms step_avg:419.53ms step:1390/6250 train_loss:2.5980 train_time:578990ms step_avg:419.56ms step:1391/6250 train_loss:2.6715 train_time:579421ms step_avg:419.57ms step:1392/6250 train_loss:2.6998 train_time:579878ms step_avg:419.59ms step:1393/6250 train_loss:2.5910 train_time:580290ms step_avg:419.59ms step:1394/6250 train_loss:2.6995 train_time:580745ms step_avg:419.61ms step:1395/6250 train_loss:2.6979 train_time:581160ms step_avg:419.61ms step:1396/6250 train_loss:2.7765 train_time:581611ms step_avg:419.63ms step:1397/6250 train_loss:2.7084 train_time:582041ms step_avg:419.64ms step:1398/6250 train_loss:2.6928 train_time:582478ms step_avg:419.65ms step:1399/6250 train_loss:2.6268 train_time:582907ms step_avg:419.66ms step:1400/6250 train_loss:2.7256 train_time:583369ms step_avg:419.69ms step:1401/6250 train_loss:2.5222 train_time:583783ms step_avg:419.69ms step:1402/6250 train_loss:2.6604 train_time:584240ms step_avg:419.71ms step:1403/6250 train_loss:2.6728 train_time:584691ms step_avg:419.74ms step:1404/6250 train_loss:2.6941 train_time:585135ms step_avg:419.75ms step:1405/6250 train_loss:2.6908 train_time:585590ms step_avg:419.78ms step:1406/6250 train_loss:2.5878 train_time:586042ms step_avg:419.80ms step:1407/6250 train_loss:2.6881 train_time:586487ms step_avg:419.82ms step:1408/6250 train_loss:2.6450 train_time:586941ms step_avg:419.84ms step:1409/6250 train_loss:2.7094 train_time:587391ms step_avg:419.86ms step:1410/6250 train_loss:2.7451 train_time:587837ms step_avg:419.88ms step:1411/6250 train_loss:2.6721 train_time:588280ms step_avg:419.90ms step:1412/6250 train_loss:2.6362 train_time:588734ms step_avg:419.92ms step:1413/6250 train_loss:2.6437 train_time:589186ms step_avg:419.95ms step:1414/6250 train_loss:2.6850 train_time:589607ms step_avg:419.95ms step:1415/6250 train_loss:2.6656 train_time:590043ms step_avg:419.96ms step:1416/6250 train_loss:2.7310 train_time:590404ms step_avg:419.92ms step:1417/6250 train_loss:2.7626 train_time:590743ms step_avg:419.86ms step:1418/6250 train_loss:2.5386 train_time:591080ms step_avg:419.80ms step:1419/6250 train_loss:2.7183 train_time:591423ms step_avg:419.75ms step:1420/6250 train_loss:2.5690 train_time:591762ms step_avg:419.69ms step:1421/6250 train_loss:2.7286 train_time:592101ms step_avg:419.63ms step:1422/6250 train_loss:2.6817 train_time:592439ms step_avg:419.57ms step:1423/6250 train_loss:2.7418 train_time:592778ms step_avg:419.52ms step:1424/6250 train_loss:2.7621 train_time:593119ms step_avg:419.46ms step:1425/6250 train_loss:2.6897 train_time:593467ms step_avg:419.41ms step:1426/6250 train_loss:2.6367 train_time:593815ms step_avg:419.36ms step:1427/6250 train_loss:2.6223 train_time:594161ms step_avg:419.31ms step:1428/6250 train_loss:2.6271 train_time:594531ms step_avg:419.27ms step:1429/6250 train_loss:2.6412 train_time:594881ms step_avg:419.23ms step:1430/6250 train_loss:2.6589 train_time:595239ms step_avg:419.18ms step:1431/6250 train_loss:2.7765 train_time:595589ms step_avg:419.13ms step:1432/6250 train_loss:2.6395 train_time:595942ms step_avg:419.09ms step:1433/6250 train_loss:2.7060 train_time:596301ms step_avg:419.04ms step:1434/6250 train_loss:2.5846 train_time:596662ms step_avg:419.00ms step:1435/6250 train_loss:2.6600 train_time:597022ms step_avg:418.96ms step:1436/6250 train_loss:2.7078 train_time:597368ms step_avg:418.91ms step:1437/6250 train_loss:2.7113 train_time:597727ms step_avg:418.87ms step:1438/6250 train_loss:2.7280 train_time:598074ms step_avg:418.82ms step:1439/6250 train_loss:2.7519 train_time:598432ms step_avg:418.78ms step:1440/6250 train_loss:2.6449 train_time:598787ms step_avg:418.73ms step:1441/6250 train_loss:2.6038 train_time:599164ms step_avg:418.70ms step:1442/6250 train_loss:2.5679 train_time:599530ms step_avg:418.67ms step:1443/6250 train_loss:2.6975 train_time:599883ms step_avg:418.62ms step:1444/6250 train_loss:2.6203 train_time:600230ms step_avg:418.57ms step:1445/6250 train_loss:2.6370 train_time:600576ms step_avg:418.52ms step:1446/6250 train_loss:2.6650 train_time:600923ms step_avg:418.47ms step:1447/6250 train_loss:2.7001 train_time:601270ms step_avg:418.42ms step:1448/6250 train_loss:2.7085 train_time:601617ms step_avg:418.37ms step:1449/6250 train_loss:2.6480 train_time:601965ms step_avg:418.32ms step:1450/6250 train_loss:2.6637 train_time:602304ms step_avg:418.27ms step:1451/6250 train_loss:2.6382 train_time:602647ms step_avg:418.21ms step:1452/6250 train_loss:2.6255 train_time:602993ms step_avg:418.16ms step:1453/6250 train_loss:2.5653 train_time:603362ms step_avg:418.13ms step:1454/6250 train_loss:2.7337 train_time:603713ms step_avg:418.08ms step:1455/6250 train_loss:2.6273 train_time:604063ms step_avg:418.04ms step:1456/6250 train_loss:2.6065 train_time:604413ms step_avg:417.99ms step:1457/6250 train_loss:2.6825 train_time:604763ms step_avg:417.94ms step:1458/6250 train_loss:2.6702 train_time:605117ms step_avg:417.90ms step:1459/6250 train_loss:2.6252 train_time:605467ms step_avg:417.85ms step:1460/6250 train_loss:2.6815 train_time:605821ms step_avg:417.81ms step:1461/6250 train_loss:2.6093 train_time:606172ms step_avg:417.76ms step:1462/6250 train_loss:2.6076 train_time:606526ms step_avg:417.72ms step:1463/6250 train_loss:2.6090 train_time:606876ms step_avg:417.67ms step:1464/6250 train_loss:2.6649 train_time:607217ms step_avg:417.62ms step:1465/6250 train_loss:2.6256 train_time:607569ms step_avg:417.57ms step:1466/6250 train_loss:2.6150 train_time:607929ms step_avg:417.53ms step:1467/6250 train_loss:2.6114 train_time:608283ms step_avg:417.49ms step:1468/6250 train_loss:2.6018 train_time:608636ms step_avg:417.45ms step:1469/6250 train_loss:2.6883 train_time:608992ms step_avg:417.40ms step:1470/6250 train_loss:2.6717 train_time:609335ms step_avg:417.35ms step:1471/6250 train_loss:2.7630 train_time:609679ms step_avg:417.30ms step:1472/6250 train_loss:2.6004 train_time:610033ms step_avg:417.26ms step:1473/6250 train_loss:2.6668 train_time:610376ms step_avg:417.21ms step:1474/6250 train_loss:2.6631 train_time:610723ms step_avg:417.16ms step:1475/6250 train_loss:2.6327 train_time:611067ms step_avg:417.11ms step:1476/6250 train_loss:2.7067 train_time:611409ms step_avg:417.06ms step:1477/6250 train_loss:2.6567 train_time:611763ms step_avg:417.02ms step:1478/6250 train_loss:2.6240 train_time:612110ms step_avg:416.97ms step:1479/6250 train_loss:2.6376 train_time:612457ms step_avg:416.92ms step:1480/6250 train_loss:2.6934 train_time:612814ms step_avg:416.88ms step:1481/6250 train_loss:2.6810 train_time:613165ms step_avg:416.84ms step:1482/6250 train_loss:2.6379 train_time:613511ms step_avg:416.79ms step:1483/6250 train_loss:2.7625 train_time:613851ms step_avg:416.74ms step:1484/6250 train_loss:2.6022 train_time:614191ms step_avg:416.68ms step:1485/6250 train_loss:2.5905 train_time:614534ms step_avg:416.63ms step:1486/6250 train_loss:2.6166 train_time:614874ms step_avg:416.58ms step:1487/6250 train_loss:2.6558 train_time:615215ms step_avg:416.53ms step:1488/6250 train_loss:2.5773 train_time:615558ms step_avg:416.48ms step:1489/6250 train_loss:2.7090 train_time:615901ms step_avg:416.43ms step:1490/6250 train_loss:2.6661 train_time:616262ms step_avg:416.39ms step:1491/6250 train_loss:2.7201 train_time:616611ms step_avg:416.35ms step:1492/6250 train_loss:2.6633 train_time:616965ms step_avg:416.31ms step:1493/6250 train_loss:2.6704 train_time:617315ms step_avg:416.26ms step:1494/6250 train_loss:2.5550 train_time:617661ms step_avg:416.21ms step:1495/6250 train_loss:2.6335 train_time:618014ms step_avg:416.17ms step:1496/6250 train_loss:2.5777 train_time:618365ms step_avg:416.13ms step:1497/6250 train_loss:2.6627 train_time:618721ms step_avg:416.09ms step:1498/6250 train_loss:2.7546 train_time:619074ms step_avg:416.04ms step:1499/6250 train_loss:2.7023 train_time:619426ms step_avg:416.00ms step:1500/6250 train_loss:2.7029 train_time:619778ms step_avg:415.96ms step:1501/6250 train_loss:2.5932 train_time:620126ms step_avg:415.91ms step:1502/6250 train_loss:2.6309 train_time:620481ms step_avg:415.87ms step:1503/6250 train_loss:2.5811 train_time:620826ms step_avg:415.82ms step:1504/6250 train_loss:2.7350 train_time:621175ms step_avg:415.78ms step:1505/6250 train_loss:2.6560 train_time:621529ms step_avg:415.74ms step:1506/6250 train_loss:2.6375 train_time:621886ms step_avg:415.70ms step:1507/6250 train_loss:2.5784 train_time:622227ms step_avg:415.65ms step:1508/6250 train_loss:2.6630 train_time:622576ms step_avg:415.60ms step:1509/6250 train_loss:2.6788 train_time:622918ms step_avg:415.56ms step:1510/6250 train_loss:2.6037 train_time:623259ms step_avg:415.51ms step:1511/6250 train_loss:2.6404 train_time:623615ms step_avg:415.47ms step:1512/6250 train_loss:2.6308 train_time:623956ms step_avg:415.42ms step:1513/6250 train_loss:2.6533 train_time:624298ms step_avg:415.37ms step:1514/6250 train_loss:2.7280 train_time:624639ms step_avg:415.32ms step:1515/6250 train_loss:2.5581 train_time:624978ms step_avg:415.27ms step:1516/6250 train_loss:2.7040 train_time:625319ms step_avg:415.22ms step:1517/6250 train_loss:2.5998 train_time:625662ms step_avg:415.17ms step:1518/6250 train_loss:2.6411 train_time:625999ms step_avg:415.12ms step:1519/6250 train_loss:2.5833 train_time:626337ms step_avg:415.07ms step:1520/6250 train_loss:2.6326 train_time:626699ms step_avg:415.03ms step:1521/6250 train_loss:2.6869 train_time:627051ms step_avg:414.99ms step:1522/6250 train_loss:2.6403 train_time:627405ms step_avg:414.95ms step:1523/6250 train_loss:2.7110 train_time:627748ms step_avg:414.90ms step:1524/6250 train_loss:2.6073 train_time:628100ms step_avg:414.86ms step:1525/6250 train_loss:2.6501 train_time:628452ms step_avg:414.82ms step:1526/6250 train_loss:2.6612 train_time:628816ms step_avg:414.79ms step:1527/6250 train_loss:2.6419 train_time:629165ms step_avg:414.74ms step:1528/6250 train_loss:2.6984 train_time:629515ms step_avg:414.70ms step:1529/6250 train_loss:2.6572 train_time:629868ms step_avg:414.66ms step:1530/6250 train_loss:2.6603 train_time:630210ms step_avg:414.61ms step:1531/6250 train_loss:2.5897 train_time:630560ms step_avg:414.57ms step:1532/6250 train_loss:2.6908 train_time:630906ms step_avg:414.52ms step:1533/6250 train_loss:2.6335 train_time:631250ms step_avg:414.48ms step:1534/6250 train_loss:2.6398 train_time:631595ms step_avg:414.43ms step:1535/6250 train_loss:2.6290 train_time:631940ms step_avg:414.39ms step:1536/6250 train_loss:2.6418 train_time:632284ms step_avg:414.34ms step:1537/6250 train_loss:2.6363 train_time:632629ms step_avg:414.30ms step:1538/6250 train_loss:2.6077 train_time:632978ms step_avg:414.25ms step:1539/6250 train_loss:2.7330 train_time:633320ms step_avg:414.21ms step:1540/6250 train_loss:2.5596 train_time:633675ms step_avg:414.17ms step:1541/6250 train_loss:2.6418 train_time:634020ms step_avg:414.12ms step:1542/6250 train_loss:2.6277 train_time:634371ms step_avg:414.08ms step:1543/6250 train_loss:2.7558 train_time:634723ms step_avg:414.04ms step:1544/6250 train_loss:2.6405 train_time:635067ms step_avg:413.99ms step:1545/6250 train_loss:2.6037 train_time:635418ms step_avg:413.95ms step:1546/6250 train_loss:2.6602 train_time:635758ms step_avg:413.91ms step:1547/6250 train_loss:2.6693 train_time:636096ms step_avg:413.86ms step:1548/6250 train_loss:2.6571 train_time:636438ms step_avg:413.81ms step:1549/6250 train_loss:2.6311 train_time:636784ms step_avg:413.76ms step:1550/6250 train_loss:2.6691 train_time:637122ms step_avg:413.72ms step:1551/6250 train_loss:2.6844 train_time:637469ms step_avg:413.67ms step:1552/6250 train_loss:2.6722 train_time:637808ms step_avg:413.62ms step:1553/6250 train_loss:2.6615 train_time:638147ms step_avg:413.58ms step:1554/6250 train_loss:2.6259 train_time:638489ms step_avg:413.53ms step:1555/6250 train_loss:2.6517 train_time:638829ms step_avg:413.48ms step:1556/6250 train_loss:2.6970 train_time:639167ms step_avg:413.43ms step:1557/6250 train_loss:2.6616 train_time:639512ms step_avg:413.39ms step:1558/6250 train_loss:2.7122 train_time:639857ms step_avg:413.34ms step:1559/6250 train_loss:2.6319 train_time:640200ms step_avg:413.30ms step:1560/6250 train_loss:2.6738 train_time:640557ms step_avg:413.26ms step:1561/6250 train_loss:2.7106 train_time:640907ms step_avg:413.22ms step:1562/6250 train_loss:2.7563 train_time:641262ms step_avg:413.18ms step:1563/6250 train_loss:2.7621 train_time:641612ms step_avg:413.14ms step:1564/6250 train_loss:2.6372 train_time:641962ms step_avg:413.10ms step:1565/6250 train_loss:2.6408 train_time:642313ms step_avg:413.06ms step:1566/6250 train_loss:2.6194 train_time:642669ms step_avg:413.03ms step:1567/6250 train_loss:2.7000 train_time:643021ms step_avg:412.99ms step:1568/6250 train_loss:2.6900 train_time:643376ms step_avg:412.95ms step:1569/6250 train_loss:2.6656 train_time:643722ms step_avg:412.91ms step:1570/6250 train_loss:2.5802 train_time:644066ms step_avg:412.86ms step:1571/6250 train_loss:2.6301 train_time:644409ms step_avg:412.82ms step:1572/6250 train_loss:2.7096 train_time:644751ms step_avg:412.77ms step:1573/6250 train_loss:2.6847 train_time:645092ms step_avg:412.73ms step:1574/6250 train_loss:2.6474 train_time:645435ms step_avg:412.68ms step:1575/6250 train_loss:2.7134 train_time:645786ms step_avg:412.64ms step:1576/6250 train_loss:2.6534 train_time:646137ms step_avg:412.60ms step:1577/6250 train_loss:2.7321 train_time:646484ms step_avg:412.56ms step:1578/6250 train_loss:2.6256 train_time:646833ms step_avg:412.52ms step:1579/6250 train_loss:2.6383 train_time:647178ms step_avg:412.48ms step:1580/6250 train_loss:2.7654 train_time:647526ms step_avg:412.44ms step:1581/6250 train_loss:2.6124 train_time:647878ms step_avg:412.40ms step:1582/6250 train_loss:2.6216 train_time:648226ms step_avg:412.36ms step:1583/6250 train_loss:2.6385 train_time:648566ms step_avg:412.31ms step:1584/6250 train_loss:2.7228 train_time:648914ms step_avg:412.27ms step:1585/6250 train_loss:2.7389 train_time:649255ms step_avg:412.23ms step:1586/6250 train_loss:2.6228 train_time:649608ms step_avg:412.19ms step:1587/6250 train_loss:2.6829 train_time:649953ms step_avg:412.14ms step:1588/6250 train_loss:2.6052 train_time:650306ms step_avg:412.11ms step:1589/6250 train_loss:2.8722 train_time:650648ms step_avg:412.06ms step:1590/6250 train_loss:2.6284 train_time:650990ms step_avg:412.02ms step:1591/6250 train_loss:2.6726 train_time:651332ms step_avg:411.97ms step:1592/6250 train_loss:2.5548 train_time:651673ms step_avg:411.93ms step:1593/6250 train_loss:2.6846 train_time:652014ms step_avg:411.89ms step:1594/6250 train_loss:2.7111 train_time:652358ms step_avg:411.84ms step:1595/6250 train_loss:2.7684 train_time:652701ms step_avg:411.80ms step:1596/6250 train_loss:2.6223 train_time:653042ms step_avg:411.75ms step:1597/6250 train_loss:2.7039 train_time:653382ms step_avg:411.71ms step:1598/6250 train_loss:2.6446 train_time:653747ms step_avg:411.68ms step:1599/6250 train_loss:2.7182 train_time:654098ms step_avg:411.64ms step:1600/6250 train_loss:2.7697 train_time:654448ms step_avg:411.60ms step:1601/6250 train_loss:2.5592 train_time:654794ms step_avg:411.56ms step:1602/6250 train_loss:2.6849 train_time:655140ms step_avg:411.52ms step:1603/6250 train_loss:2.5721 train_time:655493ms step_avg:411.48ms step:1604/6250 train_loss:2.6584 train_time:655843ms step_avg:411.45ms step:1605/6250 train_loss:2.6776 train_time:656194ms step_avg:411.41ms step:1606/6250 train_loss:2.6070 train_time:656547ms step_avg:411.37ms step:1607/6250 train_loss:2.7352 train_time:656902ms step_avg:411.33ms step:1608/6250 train_loss:2.7383 train_time:657245ms step_avg:411.29ms step:1609/6250 train_loss:2.6149 train_time:657595ms step_avg:411.25ms step:1610/6250 train_loss:2.6341 train_time:657939ms step_avg:411.21ms step:1611/6250 train_loss:2.5918 train_time:658284ms step_avg:411.17ms step:1612/6250 train_loss:2.5822 train_time:658634ms step_avg:411.13ms step:1613/6250 train_loss:2.6876 train_time:658988ms step_avg:411.10ms step:1614/6250 train_loss:2.6483 train_time:659332ms step_avg:411.06ms step:1615/6250 train_loss:2.6312 train_time:659683ms step_avg:411.02ms step:1616/6250 train_loss:2.6490 train_time:660034ms step_avg:410.98ms step:1617/6250 train_loss:2.6926 train_time:660379ms step_avg:410.94ms step:1618/6250 train_loss:2.5660 train_time:660726ms step_avg:410.90ms step:1619/6250 train_loss:2.5969 train_time:661081ms step_avg:410.86ms step:1620/6250 train_loss:2.6024 train_time:661429ms step_avg:410.83ms step:1621/6250 train_loss:2.6534 train_time:661780ms step_avg:410.79ms step:1622/6250 train_loss:2.6037 train_time:662121ms step_avg:410.75ms step:1623/6250 train_loss:2.5808 train_time:662462ms step_avg:410.70ms step:1624/6250 train_loss:2.5284 train_time:662815ms step_avg:410.67ms step:1625/6250 train_loss:2.7698 train_time:663156ms step_avg:410.62ms step:1626/6250 train_loss:2.6923 train_time:663511ms step_avg:410.59ms step:1627/6250 train_loss:2.6694 train_time:663856ms step_avg:410.55ms step:1628/6250 train_loss:2.7229 train_time:664206ms step_avg:410.51ms step:1629/6250 train_loss:2.6338 train_time:664554ms step_avg:410.47ms step:1630/6250 train_loss:2.6373 train_time:664896ms step_avg:410.43ms step:1631/6250 train_loss:2.7584 train_time:665234ms step_avg:410.39ms step:1632/6250 train_loss:2.6312 train_time:665572ms step_avg:410.34ms step:1633/6250 train_loss:2.6110 train_time:665914ms step_avg:410.30ms step:1634/6250 train_loss:2.6537 train_time:666253ms step_avg:410.25ms step:1635/6250 train_loss:2.6855 train_time:666599ms step_avg:410.22ms step:1636/6250 train_loss:2.5919 train_time:666941ms step_avg:410.17ms step:1637/6250 train_loss:2.7196 train_time:667280ms step_avg:410.13ms step:1638/6250 train_loss:2.5654 train_time:667637ms step_avg:410.10ms step:1639/6250 train_loss:2.5770 train_time:667983ms step_avg:410.06ms step:1640/6250 train_loss:2.7017 train_time:668331ms step_avg:410.02ms step:1641/6250 train_loss:2.7059 train_time:668689ms step_avg:409.99ms step:1642/6250 train_loss:2.5698 train_time:669039ms step_avg:409.95ms step:1643/6250 train_loss:2.6621 train_time:669392ms step_avg:409.92ms step:1644/6250 train_loss:2.6238 train_time:669741ms step_avg:409.88ms step:1645/6250 train_loss:2.6493 train_time:670092ms step_avg:409.84ms step:1646/6250 train_loss:2.6453 train_time:670441ms step_avg:409.81ms step:1647/6250 train_loss:2.6947 train_time:670793ms step_avg:409.77ms step:1648/6250 train_loss:2.6412 train_time:671136ms step_avg:409.73ms step:1649/6250 train_loss:2.7295 train_time:671480ms step_avg:409.69ms step:1650/6250 train_loss:2.5651 train_time:671828ms step_avg:409.65ms step:1651/6250 train_loss:2.6993 train_time:672166ms step_avg:409.61ms step:1652/6250 train_loss:2.7035 train_time:672510ms step_avg:409.57ms step:1653/6250 train_loss:2.7100 train_time:672859ms step_avg:409.53ms step:1654/6250 train_loss:2.7047 train_time:673204ms step_avg:409.49ms step:1655/6250 train_loss:2.6493 train_time:673553ms step_avg:409.45ms step:1656/6250 train_loss:2.5987 train_time:673903ms step_avg:409.42ms step:1657/6250 train_loss:2.5676 train_time:674247ms step_avg:409.38ms step:1658/6250 train_loss:2.7229 train_time:674591ms step_avg:409.34ms step:1659/6250 train_loss:2.8100 train_time:674940ms step_avg:409.30ms step:1660/6250 train_loss:2.6613 train_time:675286ms step_avg:409.26ms step:1661/6250 train_loss:2.5515 train_time:675635ms step_avg:409.23ms step:1662/6250 train_loss:2.7733 train_time:675977ms step_avg:409.19ms step:1663/6250 train_loss:2.6116 train_time:676315ms step_avg:409.14ms step:1664/6250 train_loss:2.7119 train_time:676664ms step_avg:409.11ms step:1665/6250 train_loss:2.6083 train_time:677003ms step_avg:409.07ms step:1666/6250 train_loss:2.5485 train_time:677341ms step_avg:409.02ms step:1667/6250 train_loss:2.7498 train_time:677688ms step_avg:408.99ms step:1668/6250 train_loss:2.7608 train_time:678026ms step_avg:408.94ms step:1669/6250 train_loss:2.7029 train_time:678363ms step_avg:408.90ms step:1670/6250 train_loss:2.6619 train_time:678703ms step_avg:408.86ms step:1671/6250 train_loss:2.7180 train_time:679044ms step_avg:408.82ms step:1672/6250 train_loss:2.7156 train_time:679383ms step_avg:408.77ms step:1673/6250 train_loss:2.6213 train_time:679727ms step_avg:408.74ms step:1674/6250 train_loss:2.6627 train_time:680071ms step_avg:408.70ms step:1675/6250 train_loss:2.6356 train_time:680410ms step_avg:408.65ms step:1676/6250 train_loss:2.5746 train_time:680767ms step_avg:408.62ms step:1677/6250 train_loss:2.5639 train_time:681120ms step_avg:408.59ms step:1678/6250 train_loss:2.5930 train_time:681473ms step_avg:408.56ms step:1679/6250 train_loss:2.6791 train_time:681823ms step_avg:408.52ms step:1680/6250 train_loss:2.7009 train_time:682171ms step_avg:408.49ms step:1681/6250 train_loss:2.6826 train_time:682524ms step_avg:408.45ms step:1682/6250 train_loss:2.5719 train_time:682874ms step_avg:408.42ms step:1683/6250 train_loss:2.6878 train_time:683225ms step_avg:408.38ms step:1684/6250 train_loss:2.6069 train_time:683577ms step_avg:408.35ms step:1685/6250 train_loss:2.5791 train_time:683932ms step_avg:408.32ms step:1686/6250 train_loss:2.7630 train_time:684275ms step_avg:408.28ms step:1687/6250 train_loss:2.6751 train_time:684619ms step_avg:408.24ms step:1688/6250 train_loss:2.6982 train_time:684959ms step_avg:408.20ms step:1689/6250 train_loss:2.6032 train_time:685303ms step_avg:408.16ms step:1690/6250 train_loss:2.6375 train_time:685649ms step_avg:408.12ms step:1691/6250 train_loss:2.5524 train_time:685996ms step_avg:408.09ms step:1692/6250 train_loss:2.6088 train_time:686341ms step_avg:408.05ms step:1693/6250 train_loss:2.6928 train_time:686696ms step_avg:408.02ms step:1694/6250 train_loss:2.6909 train_time:687044ms step_avg:407.98ms step:1695/6250 train_loss:2.6209 train_time:687390ms step_avg:407.95ms step:1696/6250 train_loss:2.6907 train_time:687734ms step_avg:407.91ms step:1697/6250 train_loss:2.6555 train_time:688082ms step_avg:407.87ms step:1698/6250 train_loss:2.6489 train_time:688427ms step_avg:407.84ms step:1699/6250 train_loss:2.5629 train_time:688779ms step_avg:407.80ms step:1700/6250 train_loss:2.6110 train_time:689120ms step_avg:407.76ms step:1701/6250 train_loss:2.6622 train_time:689460ms step_avg:407.72ms step:1702/6250 train_loss:2.6061 train_time:689814ms step_avg:407.69ms step:1703/6250 train_loss:2.6415 train_time:690157ms step_avg:407.65ms step:1704/6250 train_loss:2.5930 train_time:690509ms step_avg:407.62ms step:1705/6250 train_loss:2.6188 train_time:690853ms step_avg:407.58ms step:1706/6250 train_loss:2.5993 train_time:691207ms step_avg:407.55ms step:1707/6250 train_loss:2.6740 train_time:691545ms step_avg:407.51ms step:1708/6250 train_loss:2.5526 train_time:691883ms step_avg:407.47ms step:1709/6250 train_loss:2.6138 train_time:692220ms step_avg:407.43ms step:1710/6250 train_loss:2.6903 train_time:692559ms step_avg:407.39ms step:1711/6250 train_loss:2.6694 train_time:692902ms step_avg:407.35ms step:1712/6250 train_loss:2.6633 train_time:693245ms step_avg:407.31ms step:1713/6250 train_loss:2.6761 train_time:693584ms step_avg:407.27ms step:1714/6250 train_loss:2.5974 train_time:693925ms step_avg:407.23ms step:1715/6250 train_loss:2.5745 train_time:694286ms step_avg:407.21ms step:1716/6250 train_loss:2.6198 train_time:694632ms step_avg:407.17ms step:1717/6250 train_loss:2.6283 train_time:694986ms step_avg:407.14ms step:1718/6250 train_loss:2.6078 train_time:695332ms step_avg:407.10ms step:1719/6250 train_loss:2.7090 train_time:695681ms step_avg:407.07ms step:1720/6250 train_loss:2.6192 train_time:696032ms step_avg:407.04ms step:1721/6250 train_loss:2.6738 train_time:696377ms step_avg:407.00ms step:1722/6250 train_loss:2.6355 train_time:696727ms step_avg:406.97ms step:1723/6250 train_loss:2.6717 train_time:697073ms step_avg:406.93ms step:1724/6250 train_loss:2.7125 train_time:697423ms step_avg:406.90ms step:1725/6250 train_loss:2.7082 train_time:697764ms step_avg:406.86ms step:1726/6250 train_loss:2.6371 train_time:698105ms step_avg:406.82ms step:1727/6250 train_loss:2.7210 train_time:698456ms step_avg:406.79ms step:1728/6250 train_loss:2.6597 train_time:698813ms step_avg:406.76ms step:1729/6250 train_loss:2.6378 train_time:699164ms step_avg:406.73ms step:1730/6250 train_loss:2.6880 train_time:699517ms step_avg:406.70ms step:1731/6250 train_loss:2.7449 train_time:699878ms step_avg:406.67ms step:1732/6250 train_loss:2.6256 train_time:700233ms step_avg:406.64ms step:1733/6250 train_loss:2.6433 train_time:700578ms step_avg:406.60ms step:1734/6250 train_loss:2.6095 train_time:700926ms step_avg:406.57ms step:1735/6250 train_loss:2.5954 train_time:701272ms step_avg:406.53ms step:1736/6250 train_loss:2.6801 train_time:701617ms step_avg:406.50ms step:1737/6250 train_loss:2.7179 train_time:701969ms step_avg:406.47ms step:1738/6250 train_loss:2.5561 train_time:702322ms step_avg:406.44ms step:1739/6250 train_loss:2.5483 train_time:702664ms step_avg:406.40ms step:1740/6250 train_loss:2.6961 train_time:703006ms step_avg:406.36ms step:1741/6250 train_loss:2.6746 train_time:703355ms step_avg:406.33ms step:1742/6250 train_loss:2.6331 train_time:703700ms step_avg:406.29ms step:1743/6250 train_loss:2.5732 train_time:704061ms step_avg:406.27ms step:1744/6250 train_loss:2.5767 train_time:704427ms step_avg:406.24ms step:1745/6250 train_loss:2.5983 train_time:704800ms step_avg:406.22ms step:1746/6250 train_loss:2.7339 train_time:705152ms step_avg:406.19ms step:1747/6250 train_loss:2.6028 train_time:705492ms step_avg:406.16ms step:1748/6250 train_loss:2.6059 train_time:705833ms step_avg:406.12ms step:1749/6250 train_loss:2.6773 train_time:706170ms step_avg:406.08ms step:1750/6250 train_loss:2.7262 train_time:706510ms step_avg:406.04ms step:1751/6250 train_loss:2.7233 train_time:706870ms step_avg:406.01ms step:1752/6250 train_loss:2.6466 train_time:707223ms step_avg:405.98ms step:1753/6250 train_loss:2.6903 train_time:707593ms step_avg:405.96ms step:1754/6250 train_loss:2.6446 train_time:707955ms step_avg:405.94ms step:1755/6250 train_loss:2.5152 train_time:708334ms step_avg:405.92ms step:1756/6250 train_loss:2.6499 train_time:708693ms step_avg:405.90ms step:1757/6250 train_loss:2.7573 train_time:709049ms step_avg:405.87ms step:1758/6250 train_loss:2.5867 train_time:709397ms step_avg:405.83ms step:1759/6250 train_loss:2.5951 train_time:709746ms step_avg:405.80ms step:1760/6250 train_loss:2.5513 train_time:710096ms step_avg:405.77ms step:1761/6250 train_loss:2.6502 train_time:710446ms step_avg:405.74ms step:1762/6250 train_loss:2.6302 train_time:710800ms step_avg:405.71ms step:1763/6250 train_loss:2.5734 train_time:711151ms step_avg:405.68ms step:1764/6250 train_loss:2.5948 train_time:711503ms step_avg:405.65ms step:1765/6250 train_loss:2.6178 train_time:711849ms step_avg:405.61ms step:1766/6250 train_loss:2.6248 train_time:712190ms step_avg:405.58ms step:1767/6250 train_loss:2.5986 train_time:712532ms step_avg:405.54ms step:1768/6250 train_loss:2.5668 train_time:712875ms step_avg:405.50ms step:1769/6250 train_loss:2.5518 train_time:713225ms step_avg:405.47ms step:1770/6250 train_loss:2.6353 train_time:713576ms step_avg:405.44ms step:1771/6250 train_loss:2.5968 train_time:713925ms step_avg:405.41ms step:1772/6250 train_loss:2.6729 train_time:714269ms step_avg:405.37ms step:1773/6250 train_loss:2.6140 train_time:714618ms step_avg:405.34ms step:1774/6250 train_loss:2.6590 train_time:714969ms step_avg:405.31ms step:1775/6250 train_loss:2.6262 train_time:715314ms step_avg:405.28ms step:1776/6250 train_loss:2.6351 train_time:715667ms step_avg:405.25ms step:1777/6250 train_loss:2.6435 train_time:716013ms step_avg:405.21ms step:1778/6250 train_loss:2.5853 train_time:716356ms step_avg:405.18ms step:1779/6250 train_loss:2.5403 train_time:716712ms step_avg:405.15ms step:1780/6250 train_loss:2.6145 train_time:717053ms step_avg:405.11ms step:1781/6250 train_loss:2.6587 train_time:717411ms step_avg:405.09ms step:1782/6250 train_loss:2.6553 train_time:717752ms step_avg:405.05ms step:1783/6250 train_loss:2.6064 train_time:718093ms step_avg:405.02ms step:1784/6250 train_loss:2.6825 train_time:718433ms step_avg:404.98ms step:1785/6250 train_loss:2.6891 train_time:718774ms step_avg:404.94ms step:1786/6250 train_loss:2.5747 train_time:719114ms step_avg:404.91ms step:1787/6250 train_loss:2.5477 train_time:719458ms step_avg:404.87ms step:1788/6250 train_loss:2.6037 train_time:719803ms step_avg:404.84ms step:1789/6250 train_loss:2.6013 train_time:720142ms step_avg:404.80ms step:1790/6250 train_loss:2.6134 train_time:720484ms step_avg:404.77ms step:1791/6250 train_loss:2.6225 train_time:720852ms step_avg:404.75ms step:1792/6250 train_loss:2.6356 train_time:721204ms step_avg:404.72ms step:1793/6250 train_loss:2.6401 train_time:721551ms step_avg:404.68ms step:1794/6250 train_loss:2.6407 train_time:721918ms step_avg:404.66ms step:1795/6250 train_loss:2.5772 train_time:722272ms step_avg:404.63ms step:1796/6250 train_loss:2.6472 train_time:722626ms step_avg:404.61ms step:1797/6250 train_loss:2.5829 train_time:722975ms step_avg:404.57ms step:1798/6250 train_loss:2.7017 train_time:723321ms step_avg:404.54ms step:1799/6250 train_loss:2.6409 train_time:723673ms step_avg:404.51ms step:1800/6250 train_loss:2.6962 train_time:724079ms step_avg:404.51ms step:1801/6250 train_loss:2.5559 train_time:724461ms step_avg:404.50ms step:1802/6250 train_loss:2.6537 train_time:724841ms step_avg:404.49ms step:1803/6250 train_loss:2.5235 train_time:725219ms step_avg:404.47ms step:1804/6250 train_loss:2.6048 train_time:725596ms step_avg:404.46ms step:1805/6250 train_loss:2.5745 train_time:725976ms step_avg:404.44ms step:1806/6250 train_loss:2.6697 train_time:726354ms step_avg:404.43ms step:1807/6250 train_loss:2.6325 train_time:726732ms step_avg:404.41ms step:1808/6250 train_loss:2.6080 train_time:727113ms step_avg:404.40ms step:1809/6250 train_loss:2.6330 train_time:727487ms step_avg:404.38ms step:1810/6250 train_loss:2.6117 train_time:727873ms step_avg:404.37ms step:1811/6250 train_loss:2.5486 train_time:728256ms step_avg:404.36ms step:1812/6250 train_loss:2.5971 train_time:728633ms step_avg:404.35ms step:1813/6250 train_loss:2.5659 train_time:729016ms step_avg:404.33ms step:1814/6250 train_loss:2.6456 train_time:729394ms step_avg:404.32ms step:1815/6250 train_loss:2.5647 train_time:729779ms step_avg:404.31ms step:1816/6250 train_loss:2.5933 train_time:730132ms step_avg:404.28ms step:1817/6250 train_loss:2.5450 train_time:730475ms step_avg:404.25ms step:1818/6250 train_loss:2.6268 train_time:730839ms step_avg:404.22ms step:1819/6250 train_loss:2.5473 train_time:731185ms step_avg:404.19ms step:1820/6250 train_loss:2.5827 train_time:731533ms step_avg:404.16ms step:1821/6250 train_loss:2.5727 train_time:731876ms step_avg:404.13ms step:1822/6250 train_loss:2.6358 train_time:732224ms step_avg:404.10ms step:1823/6250 train_loss:2.6245 train_time:732571ms step_avg:404.07ms step:1824/6250 train_loss:2.6527 train_time:732916ms step_avg:404.03ms step:1825/6250 train_loss:2.5952 train_time:733255ms step_avg:404.00ms step:1826/6250 train_loss:2.5648 train_time:733598ms step_avg:403.96ms step:1827/6250 train_loss:2.5927 train_time:733944ms step_avg:403.93ms step:1828/6250 train_loss:2.6015 train_time:734290ms step_avg:403.90ms step:1829/6250 train_loss:2.6949 train_time:734632ms step_avg:403.87ms step:1830/6250 train_loss:2.5830 train_time:734973ms step_avg:403.83ms step:1831/6250 train_loss:2.6349 train_time:735337ms step_avg:403.81ms step:1832/6250 train_loss:2.6633 train_time:735691ms step_avg:403.78ms step:1833/6250 train_loss:2.5938 train_time:736044ms step_avg:403.75ms step:1834/6250 train_loss:2.7686 train_time:736391ms step_avg:403.72ms step:1835/6250 train_loss:2.6467 train_time:736746ms step_avg:403.70ms step:1836/6250 train_loss:2.6248 train_time:737098ms step_avg:403.67ms step:1837/6250 train_loss:2.6083 train_time:737446ms step_avg:403.64ms step:1838/6250 train_loss:2.6665 train_time:737800ms step_avg:403.61ms step:1839/6250 train_loss:2.6861 train_time:738154ms step_avg:403.58ms step:1840/6250 train_loss:2.5848 train_time:738505ms step_avg:403.55ms step:1841/6250 train_loss:2.6171 train_time:738851ms step_avg:403.52ms step:1842/6250 train_loss:2.5024 train_time:739191ms step_avg:403.49ms step:1843/6250 train_loss:2.5269 train_time:739531ms step_avg:403.45ms step:1844/6250 train_loss:2.5245 train_time:739880ms step_avg:403.42ms step:1845/6250 train_loss:2.6752 train_time:740225ms step_avg:403.39ms step:1846/6250 train_loss:2.5719 train_time:740571ms step_avg:403.36ms step:1847/6250 train_loss:2.5254 train_time:740914ms step_avg:403.33ms step:1848/6250 train_loss:2.6666 train_time:741263ms step_avg:403.30ms step:1849/6250 train_loss:2.5551 train_time:741612ms step_avg:403.27ms step:1850/6250 train_loss:2.6004 train_time:741959ms step_avg:403.24ms step:1851/6250 train_loss:2.7020 train_time:742307ms step_avg:403.21ms step:1852/6250 train_loss:2.5846 train_time:742653ms step_avg:403.18ms step:1853/6250 train_loss:2.6397 train_time:743001ms step_avg:403.15ms step:1854/6250 train_loss:2.6103 train_time:743353ms step_avg:403.12ms step:1855/6250 train_loss:2.5408 train_time:743703ms step_avg:403.09ms step:1856/6250 train_loss:2.6811 train_time:744055ms step_avg:403.06ms step:1857/6250 train_loss:2.6065 train_time:744395ms step_avg:403.03ms step:1858/6250 train_loss:2.6351 train_time:744735ms step_avg:403.00ms step:1859/6250 train_loss:2.5885 train_time:745077ms step_avg:402.96ms step:1860/6250 train_loss:2.5936 train_time:745424ms step_avg:402.93ms step:1861/6250 train_loss:2.6132 train_time:745773ms step_avg:402.90ms step:1862/6250 train_loss:2.6399 train_time:746114ms step_avg:402.87ms step:1863/6250 train_loss:2.5534 train_time:746454ms step_avg:402.84ms step:1864/6250 train_loss:2.5359 train_time:746798ms step_avg:402.80ms step:1865/6250 train_loss:2.5052 train_time:747147ms step_avg:402.77ms step:1866/6250 train_loss:2.5753 train_time:747486ms step_avg:402.74ms step:1867/6250 train_loss:2.6008 train_time:747827ms step_avg:402.71ms step:1868/6250 train_loss:2.6632 train_time:748168ms step_avg:402.67ms step:1869/6250 train_loss:2.6347 train_time:748508ms step_avg:402.64ms step:1870/6250 train_loss:2.6242 train_time:748850ms step_avg:402.61ms step:1871/6250 train_loss:2.5776 train_time:749196ms step_avg:402.58ms step:1872/6250 train_loss:2.5997 train_time:749539ms step_avg:402.55ms step:1873/6250 train_loss:2.7060 train_time:749878ms step_avg:402.51ms step:1874/6250 train_loss:2.5625 train_time:750220ms step_avg:402.48ms step:1875/6250 train_loss:2.5352 train_time:750586ms step_avg:402.46ms step:1876/6250 train_loss:2.5919 train_time:750939ms step_avg:402.43ms step:1877/6250 train_loss:2.7140 train_time:751288ms step_avg:402.40ms step:1878/6250 train_loss:2.6460 train_time:751633ms step_avg:402.37ms step:1879/6250 train_loss:2.5931 train_time:751989ms step_avg:402.35ms step:1880/6250 train_loss:2.5960 train_time:752337ms step_avg:402.32ms step:1881/6250 train_loss:2.5270 train_time:752699ms step_avg:402.30ms step:1882/6250 train_loss:2.5942 train_time:753054ms step_avg:402.27ms step:1883/6250 train_loss:2.6632 train_time:753406ms step_avg:402.25ms step:1884/6250 train_loss:2.6395 train_time:753757ms step_avg:402.22ms step:1885/6250 train_loss:2.5925 train_time:754106ms step_avg:402.19ms step:1886/6250 train_loss:2.5826 train_time:754451ms step_avg:402.16ms step:1887/6250 train_loss:2.6303 train_time:754795ms step_avg:402.13ms step:1888/6250 train_loss:2.6637 train_time:755143ms step_avg:402.10ms step:1889/6250 train_loss:2.6407 train_time:755503ms step_avg:402.08ms step:1890/6250 train_loss:2.5589 train_time:755852ms step_avg:402.05ms step:1891/6250 train_loss:2.6319 train_time:756206ms step_avg:402.02ms step:1892/6250 train_loss:2.5247 train_time:756571ms step_avg:402.00ms step:1893/6250 train_loss:2.5770 train_time:756934ms step_avg:401.98ms step:1894/6250 train_loss:2.6722 train_time:757281ms step_avg:401.95ms step:1895/6250 train_loss:2.6422 train_time:757648ms step_avg:401.94ms step:1896/6250 train_loss:2.5138 train_time:758007ms step_avg:401.91ms step:1897/6250 train_loss:2.6451 train_time:758385ms step_avg:401.90ms step:1898/6250 train_loss:2.7062 train_time:758730ms step_avg:401.87ms step:1899/6250 train_loss:2.6238 train_time:759097ms step_avg:401.85ms step:1900/6250 train_loss:2.6018 train_time:759437ms step_avg:401.82ms step:1901/6250 train_loss:2.4808 train_time:759779ms step_avg:401.79ms step:1902/6250 train_loss:2.6127 train_time:760123ms step_avg:401.76ms step:1903/6250 train_loss:2.5902 train_time:760463ms step_avg:401.72ms step:1904/6250 train_loss:2.5151 train_time:760804ms step_avg:401.69ms step:1905/6250 train_loss:2.5909 train_time:761144ms step_avg:401.66ms step:1906/6250 train_loss:2.6242 train_time:761484ms step_avg:401.63ms step:1907/6250 train_loss:2.5702 train_time:761825ms step_avg:401.59ms step:1908/6250 train_loss:2.6113 train_time:762166ms step_avg:401.56ms step:1909/6250 train_loss:2.5279 train_time:762508ms step_avg:401.53ms step:1910/6250 train_loss:2.5849 train_time:762850ms step_avg:401.50ms step:1911/6250 train_loss:2.6451 train_time:763194ms step_avg:401.47ms step:1912/6250 train_loss:2.5572 train_time:763531ms step_avg:401.44ms step:1913/6250 train_loss:2.6424 train_time:763872ms step_avg:401.40ms step:1914/6250 train_loss:2.6210 train_time:764232ms step_avg:401.38ms step:1915/6250 train_loss:2.5677 train_time:764591ms step_avg:401.36ms step:1916/6250 train_loss:2.4375 train_time:764943ms step_avg:401.33ms step:1917/6250 train_loss:2.5740 train_time:765302ms step_avg:401.31ms step:1918/6250 train_loss:2.5394 train_time:765660ms step_avg:401.29ms step:1919/6250 train_loss:2.6669 train_time:766005ms step_avg:401.26ms step:1920/6250 train_loss:2.6111 train_time:766352ms step_avg:401.23ms step:1921/6250 train_loss:2.5660 train_time:766696ms step_avg:401.20ms step:1922/6250 train_loss:2.5189 train_time:767040ms step_avg:401.17ms step:1923/6250 train_loss:2.5756 train_time:767389ms step_avg:401.14ms step:1924/6250 train_loss:2.6483 train_time:767739ms step_avg:401.12ms step:1925/6250 train_loss:2.6096 train_time:768087ms step_avg:401.09ms step:1926/6250 train_loss:2.6481 train_time:768432ms step_avg:401.06ms step:1927/6250 train_loss:2.6311 train_time:768777ms step_avg:401.03ms step:1928/6250 train_loss:2.6554 train_time:769121ms step_avg:401.00ms step:1929/6250 train_loss:2.6091 train_time:769464ms step_avg:400.97ms step:1930/6250 train_loss:2.5999 train_time:769815ms step_avg:400.95ms step:1931/6250 train_loss:2.5502 train_time:770162ms step_avg:400.92ms step:1932/6250 train_loss:2.5731 train_time:770510ms step_avg:400.89ms step:1933/6250 train_loss:2.7119 train_time:770851ms step_avg:400.86ms step:1934/6250 train_loss:2.6088 train_time:771199ms step_avg:400.83ms step:1935/6250 train_loss:2.6296 train_time:771538ms step_avg:400.80ms step:1936/6250 train_loss:2.6206 train_time:771889ms step_avg:400.77ms step:1937/6250 train_loss:2.6019 train_time:772226ms step_avg:400.74ms step:1938/6250 train_loss:2.7410 train_time:772565ms step_avg:400.71ms step:1939/6250 train_loss:2.5433 train_time:772910ms step_avg:400.68ms step:1940/6250 train_loss:2.5574 train_time:773254ms step_avg:400.65ms step:1941/6250 train_loss:2.6766 train_time:773599ms step_avg:400.62ms step:1942/6250 train_loss:2.5277 train_time:773952ms step_avg:400.60ms step:1943/6250 train_loss:2.5288 train_time:774290ms step_avg:400.56ms step:1944/6250 train_loss:2.7517 train_time:774630ms step_avg:400.53ms step:1945/6250 train_loss:2.6444 train_time:774970ms step_avg:400.50ms step:1946/6250 train_loss:2.5542 train_time:775309ms step_avg:400.47ms step:1947/6250 train_loss:2.5298 train_time:775649ms step_avg:400.44ms step:1948/6250 train_loss:2.6343 train_time:775992ms step_avg:400.41ms step:1949/6250 train_loss:2.6183 train_time:776334ms step_avg:400.38ms step:1950/6250 train_loss:2.5636 train_time:776673ms step_avg:400.35ms step:1951/6250 train_loss:2.6901 train_time:777012ms step_avg:400.32ms step:1952/6250 train_loss:2.6182 train_time:777376ms step_avg:400.30ms step:1953/6250 train_loss:2.6216 train_time:777744ms step_avg:400.28ms step:1954/6250 train_loss:2.5467 train_time:778105ms step_avg:400.26ms step:1955/6250 train_loss:2.6060 train_time:778467ms step_avg:400.24ms step:1956/6250 train_loss:2.5392 train_time:778824ms step_avg:400.22ms step:1957/6250 train_loss:2.6631 train_time:779179ms step_avg:400.19ms step:1958/6250 train_loss:2.6512 train_time:779538ms step_avg:400.17ms step:1959/6250 train_loss:2.5354 train_time:779897ms step_avg:400.15ms step:1960/6250 train_loss:2.6068 train_time:780258ms step_avg:400.13ms step:1961/6250 train_loss:2.5755 train_time:780601ms step_avg:400.10ms step:1962/6250 train_loss:2.6130 train_time:780951ms step_avg:400.08ms step:1963/6250 train_loss:2.5888 train_time:781299ms step_avg:400.05ms step:1964/6250 train_loss:2.5987 train_time:781648ms step_avg:400.02ms step:1965/6250 train_loss:2.6402 train_time:781992ms step_avg:400.00ms step:1966/6250 train_loss:2.6546 train_time:782354ms step_avg:399.98ms step:1967/6250 train_loss:2.6513 train_time:782713ms step_avg:399.96ms step:1968/6250 train_loss:2.5611 train_time:783060ms step_avg:399.93ms step:1969/6250 train_loss:2.7100 train_time:783403ms step_avg:399.90ms step:1970/6250 train_loss:2.5173 train_time:783752ms step_avg:399.87ms step:1971/6250 train_loss:2.6560 train_time:784100ms step_avg:399.85ms step:1972/6250 train_loss:2.5589 train_time:784445ms step_avg:399.82ms step:1973/6250 train_loss:2.6207 train_time:784789ms step_avg:399.79ms step:1974/6250 train_loss:2.5885 train_time:785128ms step_avg:399.76ms step:1975/6250 train_loss:2.4801 train_time:785471ms step_avg:399.73ms step:1976/6250 train_loss:2.5500 train_time:785826ms step_avg:399.71ms step:1977/6250 train_loss:2.6560 train_time:786168ms step_avg:399.68ms step:1978/6250 train_loss:2.7314 train_time:786510ms step_avg:399.65ms step:1979/6250 train_loss:2.6285 train_time:786867ms step_avg:399.63ms step:1980/6250 train_loss:2.6141 train_time:787212ms step_avg:399.60ms step:1981/6250 train_loss:2.6174 train_time:787560ms step_avg:399.57ms step:1982/6250 train_loss:2.6357 train_time:787906ms step_avg:399.55ms step:1983/6250 train_loss:2.5133 train_time:788249ms step_avg:399.52ms step:1984/6250 train_loss:2.6389 train_time:788590ms step_avg:399.49ms step:1985/6250 train_loss:2.5981 train_time:788929ms step_avg:399.46ms step:1986/6250 train_loss:2.5912 train_time:789271ms step_avg:399.43ms step:1987/6250 train_loss:2.6705 train_time:789611ms step_avg:399.40ms step:1988/6250 train_loss:2.5673 train_time:789967ms step_avg:399.38ms step:1989/6250 train_loss:2.4865 train_time:790311ms step_avg:399.35ms step:1990/6250 train_loss:2.6843 train_time:790653ms step_avg:399.32ms step:1991/6250 train_loss:2.5452 train_time:791008ms step_avg:399.30ms step:1992/6250 train_loss:2.5977 train_time:791359ms step_avg:399.27ms step:1993/6250 train_loss:2.6266 train_time:791710ms step_avg:399.25ms step:1994/6250 train_loss:2.6305 train_time:792055ms step_avg:399.22ms step:1995/6250 train_loss:2.5119 train_time:792413ms step_avg:399.20ms step:1996/6250 train_loss:2.6763 train_time:792761ms step_avg:399.17ms step:1997/6250 train_loss:2.5863 train_time:793110ms step_avg:399.15ms step:1998/6250 train_loss:2.4974 train_time:793454ms step_avg:399.12ms step:1999/6250 train_loss:2.7141 train_time:793811ms step_avg:399.10ms step:2000/6250 train_loss:2.5789 train_time:794151ms step_avg:399.07ms step:2000/6250 val_loss:2.5794 train_time:794151ms step_avg:399.07ms step:2001/6250 train_loss:2.6203 train_time:794497ms step_avg:399.04ms step:2002/6250 train_loss:2.6009 train_time:794849ms step_avg:399.02ms step:2003/6250 train_loss:2.6388 train_time:795201ms step_avg:399.00ms step:2004/6250 train_loss:2.6191 train_time:795551ms step_avg:398.97ms step:2005/6250 train_loss:2.6477 train_time:795898ms step_avg:398.95ms step:2006/6250 train_loss:2.5755 train_time:796248ms step_avg:398.92ms step:2007/6250 train_loss:2.6377 train_time:796605ms step_avg:398.90ms step:2008/6250 train_loss:2.6279 train_time:796956ms step_avg:398.88ms step:2009/6250 train_loss:2.5387 train_time:797302ms step_avg:398.85ms step:2010/6250 train_loss:2.6292 train_time:797644ms step_avg:398.82ms step:2011/6250 train_loss:2.5739 train_time:798000ms step_avg:398.80ms step:2012/6250 train_loss:2.5648 train_time:798354ms step_avg:398.78ms step:2013/6250 train_loss:2.6032 train_time:798703ms step_avg:398.75ms step:2014/6250 train_loss:2.6503 train_time:799056ms step_avg:398.73ms step:2015/6250 train_loss:2.5057 train_time:799408ms step_avg:398.71ms step:2016/6250 train_loss:2.5592 train_time:799752ms step_avg:398.68ms step:2017/6250 train_loss:2.6444 train_time:800122ms step_avg:398.67ms step:2018/6250 train_loss:2.5073 train_time:800472ms step_avg:398.64ms step:2019/6250 train_loss:2.5665 train_time:800824ms step_avg:398.62ms step:2020/6250 train_loss:2.6321 train_time:801183ms step_avg:398.60ms step:2021/6250 train_loss:2.6378 train_time:801523ms step_avg:398.57ms step:2022/6250 train_loss:2.5952 train_time:801866ms step_avg:398.54ms step:2023/6250 train_loss:2.5431 train_time:802207ms step_avg:398.51ms step:2024/6250 train_loss:2.5837 train_time:802546ms step_avg:398.48ms step:2025/6250 train_loss:2.6785 train_time:802884ms step_avg:398.45ms step:2026/6250 train_loss:2.6275 train_time:803227ms step_avg:398.43ms step:2027/6250 train_loss:2.5960 train_time:803569ms step_avg:398.40ms step:2028/6250 train_loss:2.6679 train_time:803908ms step_avg:398.37ms step:2029/6250 train_loss:2.5287 train_time:804270ms step_avg:398.35ms step:2030/6250 train_loss:2.5852 train_time:804625ms step_avg:398.33ms step:2031/6250 train_loss:2.5504 train_time:804986ms step_avg:398.31ms step:2032/6250 train_loss:2.5171 train_time:805341ms step_avg:398.29ms step:2033/6250 train_loss:2.6386 train_time:805697ms step_avg:398.27ms step:2034/6250 train_loss:2.6786 train_time:806053ms step_avg:398.25ms step:2035/6250 train_loss:2.6258 train_time:806430ms step_avg:398.24ms step:2036/6250 train_loss:2.5372 train_time:806818ms step_avg:398.23ms step:2037/6250 train_loss:2.6012 train_time:807166ms step_avg:398.21ms step:2038/6250 train_loss:2.5645 train_time:807518ms step_avg:398.18ms step:2039/6250 train_loss:2.6749 train_time:807859ms step_avg:398.16ms step:2040/6250 train_loss:2.5740 train_time:808201ms step_avg:398.13ms step:2041/6250 train_loss:2.6534 train_time:808541ms step_avg:398.10ms step:2042/6250 train_loss:2.5883 train_time:808881ms step_avg:398.07ms step:2043/6250 train_loss:2.5133 train_time:809233ms step_avg:398.05ms step:2044/6250 train_loss:2.5962 train_time:809572ms step_avg:398.02ms step:2045/6250 train_loss:2.6693 train_time:809911ms step_avg:397.99ms step:2046/6250 train_loss:2.6717 train_time:810273ms step_avg:397.97ms step:2047/6250 train_loss:2.5376 train_time:810614ms step_avg:397.94ms step:2048/6250 train_loss:2.6261 train_time:810953ms step_avg:397.92ms step:2049/6250 train_loss:2.7517 train_time:811295ms step_avg:397.89ms step:2050/6250 train_loss:2.6521 train_time:811634ms step_avg:397.86ms step:2051/6250 train_loss:2.4569 train_time:811984ms step_avg:397.84ms step:2052/6250 train_loss:2.5712 train_time:812382ms step_avg:397.84ms step:2053/6250 train_loss:2.6177 train_time:812756ms step_avg:397.82ms step:2054/6250 train_loss:2.5950 train_time:813132ms step_avg:397.81ms step:2055/6250 train_loss:2.6224 train_time:813506ms step_avg:397.80ms step:2056/6250 train_loss:2.5201 train_time:813878ms step_avg:397.79ms step:2057/6250 train_loss:2.6059 train_time:814267ms step_avg:397.79ms step:2058/6250 train_loss:2.6621 train_time:814641ms step_avg:397.77ms step:2059/6250 train_loss:2.5905 train_time:815015ms step_avg:397.76ms step:2060/6250 train_loss:2.5040 train_time:815396ms step_avg:397.75ms step:2061/6250 train_loss:2.5393 train_time:815768ms step_avg:397.74ms step:2062/6250 train_loss:2.5762 train_time:816139ms step_avg:397.73ms step:2063/6250 train_loss:2.6054 train_time:816482ms step_avg:397.70ms step:2064/6250 train_loss:2.6069 train_time:816832ms step_avg:397.68ms step:2065/6250 train_loss:2.6371 train_time:817184ms step_avg:397.66ms step:2066/6250 train_loss:2.6409 train_time:817525ms step_avg:397.63ms step:2067/6250 train_loss:2.6291 train_time:817872ms step_avg:397.60ms step:2068/6250 train_loss:2.5592 train_time:818220ms step_avg:397.58ms step:2069/6250 train_loss:2.5929 train_time:818561ms step_avg:397.55ms step:2070/6250 train_loss:2.5099 train_time:818912ms step_avg:397.53ms step:2071/6250 train_loss:2.4423 train_time:819259ms step_avg:397.51ms step:2072/6250 train_loss:2.5788 train_time:819607ms step_avg:397.48ms step:2073/6250 train_loss:2.5378 train_time:819959ms step_avg:397.46ms step:2074/6250 train_loss:2.5491 train_time:820374ms step_avg:397.47ms step:2075/6250 train_loss:2.5760 train_time:820752ms step_avg:397.46ms step:2076/6250 train_loss:2.6468 train_time:821139ms step_avg:397.45ms step:2077/6250 train_loss:2.5922 train_time:821538ms step_avg:397.45ms step:2078/6250 train_loss:2.5501 train_time:821945ms step_avg:397.46ms step:2079/6250 train_loss:2.6260 train_time:822354ms step_avg:397.46ms step:2080/6250 train_loss:2.5675 train_time:822761ms step_avg:397.47ms step:2081/6250 train_loss:2.5362 train_time:823171ms step_avg:397.47ms step:2082/6250 train_loss:2.5374 train_time:823581ms step_avg:397.48ms step:2083/6250 train_loss:2.5604 train_time:823990ms step_avg:397.49ms step:2084/6250 train_loss:2.4332 train_time:824401ms step_avg:397.49ms step:2085/6250 train_loss:2.5794 train_time:824810ms step_avg:397.50ms step:2086/6250 train_loss:2.6169 train_time:825227ms step_avg:397.51ms step:2087/6250 train_loss:2.5640 train_time:825635ms step_avg:397.51ms step:2088/6250 train_loss:2.5701 train_time:826042ms step_avg:397.52ms step:2089/6250 train_loss:2.6081 train_time:826453ms step_avg:397.52ms step:2090/6250 train_loss:2.6136 train_time:826864ms step_avg:397.53ms step:2091/6250 train_loss:2.6269 train_time:827280ms step_avg:397.54ms step:2092/6250 train_loss:2.6569 train_time:827689ms step_avg:397.55ms step:2093/6250 train_loss:2.4738 train_time:828098ms step_avg:397.55ms step:2094/6250 train_loss:2.5759 train_time:828510ms step_avg:397.56ms step:2095/6250 train_loss:2.6923 train_time:828921ms step_avg:397.56ms step:2096/6250 train_loss:2.6072 train_time:829332ms step_avg:397.57ms step:2097/6250 train_loss:2.4730 train_time:829742ms step_avg:397.58ms step:2098/6250 train_loss:2.6670 train_time:830152ms step_avg:397.58ms step:2099/6250 train_loss:2.6556 train_time:830565ms step_avg:397.59ms step:2100/6250 train_loss:2.5002 train_time:830975ms step_avg:397.60ms step:2101/6250 train_loss:2.6416 train_time:831386ms step_avg:397.60ms step:2102/6250 train_loss:2.5589 train_time:831800ms step_avg:397.61ms step:2103/6250 train_loss:2.5781 train_time:832212ms step_avg:397.62ms step:2104/6250 train_loss:2.5805 train_time:832624ms step_avg:397.62ms step:2105/6250 train_loss:2.4866 train_time:833037ms step_avg:397.63ms step:2106/6250 train_loss:2.6852 train_time:833449ms step_avg:397.64ms step:2107/6250 train_loss:2.4800 train_time:833860ms step_avg:397.64ms step:2108/6250 train_loss:2.6506 train_time:834272ms step_avg:397.65ms step:2109/6250 train_loss:2.5938 train_time:834683ms step_avg:397.66ms step:2110/6250 train_loss:2.5567 train_time:835093ms step_avg:397.66ms step:2111/6250 train_loss:2.5268 train_time:835505ms step_avg:397.67ms step:2112/6250 train_loss:2.5619 train_time:835913ms step_avg:397.68ms step:2113/6250 train_loss:2.5658 train_time:836322ms step_avg:397.68ms step:2114/6250 train_loss:2.5552 train_time:836734ms step_avg:397.69ms step:2115/6250 train_loss:2.5860 train_time:837142ms step_avg:397.69ms step:2116/6250 train_loss:2.4912 train_time:837550ms step_avg:397.70ms step:2117/6250 train_loss:2.5254 train_time:837960ms step_avg:397.70ms step:2118/6250 train_loss:2.5259 train_time:838371ms step_avg:397.71ms step:2119/6250 train_loss:2.5658 train_time:838781ms step_avg:397.72ms step:2120/6250 train_loss:2.5638 train_time:839191ms step_avg:397.72ms step:2121/6250 train_loss:2.5926 train_time:839600ms step_avg:397.73ms step:2122/6250 train_loss:2.5982 train_time:840011ms step_avg:397.73ms step:2123/6250 train_loss:2.5581 train_time:840419ms step_avg:397.74ms step:2124/6250 train_loss:2.5714 train_time:840830ms step_avg:397.74ms step:2125/6250 train_loss:2.5481 train_time:841241ms step_avg:397.75ms step:2126/6250 train_loss:2.5311 train_time:841651ms step_avg:397.76ms step:2127/6250 train_loss:2.6030 train_time:842062ms step_avg:397.76ms step:2128/6250 train_loss:2.6410 train_time:842472ms step_avg:397.77ms step:2129/6250 train_loss:2.5413 train_time:842882ms step_avg:397.77ms step:2130/6250 train_loss:2.6032 train_time:843290ms step_avg:397.78ms step:2131/6250 train_loss:2.5475 train_time:843698ms step_avg:397.78ms step:2132/6250 train_loss:2.5417 train_time:844106ms step_avg:397.79ms step:2133/6250 train_loss:2.5055 train_time:844511ms step_avg:397.79ms step:2134/6250 train_loss:2.5274 train_time:844922ms step_avg:397.80ms step:2135/6250 train_loss:2.5717 train_time:845330ms step_avg:397.80ms step:2136/6250 train_loss:2.5603 train_time:845739ms step_avg:397.81ms step:2137/6250 train_loss:2.6411 train_time:846152ms step_avg:397.81ms step:2138/6250 train_loss:2.4851 train_time:846561ms step_avg:397.82ms step:2139/6250 train_loss:2.5104 train_time:846971ms step_avg:397.83ms step:2140/6250 train_loss:2.4616 train_time:847382ms step_avg:397.83ms step:2141/6250 train_loss:2.6172 train_time:847789ms step_avg:397.84ms step:2142/6250 train_loss:2.5320 train_time:848199ms step_avg:397.84ms step:2143/6250 train_loss:2.5023 train_time:848609ms step_avg:397.85ms step:2144/6250 train_loss:2.6152 train_time:849022ms step_avg:397.85ms step:2145/6250 train_loss:2.4422 train_time:849433ms step_avg:397.86ms step:2146/6250 train_loss:2.5183 train_time:849844ms step_avg:397.87ms step:2147/6250 train_loss:2.4979 train_time:850256ms step_avg:397.87ms step:2148/6250 train_loss:2.5621 train_time:850670ms step_avg:397.88ms step:2149/6250 train_loss:2.6749 train_time:851078ms step_avg:397.89ms step:2150/6250 train_loss:2.6405 train_time:851488ms step_avg:397.89ms step:2151/6250 train_loss:2.4826 train_time:851896ms step_avg:397.90ms step:2152/6250 train_loss:2.5706 train_time:852306ms step_avg:397.90ms step:2153/6250 train_loss:2.5714 train_time:852715ms step_avg:397.91ms step:2154/6250 train_loss:2.6639 train_time:853125ms step_avg:397.91ms step:2155/6250 train_loss:2.6207 train_time:853534ms step_avg:397.92ms step:2156/6250 train_loss:2.5319 train_time:853943ms step_avg:397.92ms step:2157/6250 train_loss:2.5722 train_time:854356ms step_avg:397.93ms step:2158/6250 train_loss:2.5515 train_time:854764ms step_avg:397.93ms step:2159/6250 train_loss:2.5624 train_time:855174ms step_avg:397.94ms step:2160/6250 train_loss:2.5076 train_time:855584ms step_avg:397.95ms step:2161/6250 train_loss:2.4479 train_time:855992ms step_avg:397.95ms step:2162/6250 train_loss:2.5055 train_time:856402ms step_avg:397.96ms step:2163/6250 train_loss:2.5885 train_time:856811ms step_avg:397.96ms step:2164/6250 train_loss:2.5721 train_time:857223ms step_avg:397.97ms step:2165/6250 train_loss:2.5096 train_time:857631ms step_avg:397.97ms step:2166/6250 train_loss:2.4738 train_time:858043ms step_avg:397.98ms step:2167/6250 train_loss:2.5696 train_time:858454ms step_avg:397.99ms step:2168/6250 train_loss:2.4380 train_time:858864ms step_avg:397.99ms step:2169/6250 train_loss:2.5143 train_time:859276ms step_avg:398.00ms step:2170/6250 train_loss:2.5569 train_time:859684ms step_avg:398.00ms step:2171/6250 train_loss:2.5345 train_time:860094ms step_avg:398.01ms step:2172/6250 train_loss:2.5468 train_time:860502ms step_avg:398.01ms step:2173/6250 train_loss:2.4984 train_time:860911ms step_avg:398.02ms step:2174/6250 train_loss:2.5077 train_time:861319ms step_avg:398.02ms step:2175/6250 train_loss:2.6093 train_time:861725ms step_avg:398.03ms step:2176/6250 train_loss:2.6219 train_time:862134ms step_avg:398.03ms step:2177/6250 train_loss:2.5985 train_time:862542ms step_avg:398.04ms step:2178/6250 train_loss:2.5220 train_time:862952ms step_avg:398.04ms step:2179/6250 train_loss:2.5156 train_time:863365ms step_avg:398.05ms step:2180/6250 train_loss:2.5718 train_time:863774ms step_avg:398.05ms step:2181/6250 train_loss:2.5512 train_time:864183ms step_avg:398.06ms step:2182/6250 train_loss:2.5265 train_time:864596ms step_avg:398.06ms step:2183/6250 train_loss:2.4771 train_time:865008ms step_avg:398.07ms step:2184/6250 train_loss:2.5852 train_time:865418ms step_avg:398.08ms step:2185/6250 train_loss:2.5285 train_time:865827ms step_avg:398.08ms step:2186/6250 train_loss:2.5477 train_time:866236ms step_avg:398.09ms step:2187/6250 train_loss:2.4988 train_time:866645ms step_avg:398.09ms step:2188/6250 train_loss:2.6003 train_time:867055ms step_avg:398.10ms step:2189/6250 train_loss:2.5730 train_time:867466ms step_avg:398.10ms step:2190/6250 train_loss:2.6049 train_time:867877ms step_avg:398.11ms step:2191/6250 train_loss:2.6033 train_time:868287ms step_avg:398.11ms step:2192/6250 train_loss:2.5378 train_time:868699ms step_avg:398.12ms step:2193/6250 train_loss:2.6099 train_time:869109ms step_avg:398.13ms step:2194/6250 train_loss:2.6312 train_time:869519ms step_avg:398.13ms step:2195/6250 train_loss:2.5307 train_time:869931ms step_avg:398.14ms step:2196/6250 train_loss:2.4522 train_time:870340ms step_avg:398.14ms step:2197/6250 train_loss:2.6120 train_time:870769ms step_avg:398.16ms step:2198/6250 train_loss:2.6450 train_time:871190ms step_avg:398.17ms step:2199/6250 train_loss:2.4768 train_time:871616ms step_avg:398.18ms step:2200/6250 train_loss:2.6492 train_time:872027ms step_avg:398.19ms step:2201/6250 train_loss:2.5607 train_time:872437ms step_avg:398.19ms step:2202/6250 train_loss:2.6229 train_time:872842ms step_avg:398.19ms step:2203/6250 train_loss:2.5749 train_time:873257ms step_avg:398.20ms step:2204/6250 train_loss:2.5409 train_time:873677ms step_avg:398.21ms step:2205/6250 train_loss:2.5282 train_time:874091ms step_avg:398.22ms step:2206/6250 train_loss:2.4970 train_time:874508ms step_avg:398.23ms step:2207/6250 train_loss:2.5175 train_time:874915ms step_avg:398.23ms step:2208/6250 train_loss:2.5615 train_time:875322ms step_avg:398.24ms step:2209/6250 train_loss:2.6189 train_time:875718ms step_avg:398.23ms step:2210/6250 train_loss:2.5871 train_time:876103ms step_avg:398.23ms step:2211/6250 train_loss:2.6368 train_time:876485ms step_avg:398.22ms step:2212/6250 train_loss:2.4446 train_time:876866ms step_avg:398.21ms step:2213/6250 train_loss:2.5779 train_time:877239ms step_avg:398.20ms step:2214/6250 train_loss:2.5387 train_time:877628ms step_avg:398.20ms step:2215/6250 train_loss:2.5396 train_time:878005ms step_avg:398.19ms step:2216/6250 train_loss:2.4254 train_time:878382ms step_avg:398.18ms step:2217/6250 train_loss:2.4731 train_time:878759ms step_avg:398.17ms step:2218/6250 train_loss:2.4816 train_time:879139ms step_avg:398.16ms step:2219/6250 train_loss:2.5848 train_time:879517ms step_avg:398.15ms step:2220/6250 train_loss:2.5336 train_time:879893ms step_avg:398.14ms step:2221/6250 train_loss:2.5042 train_time:880267ms step_avg:398.13ms step:2222/6250 train_loss:2.5865 train_time:880643ms step_avg:398.12ms step:2223/6250 train_loss:2.5165 train_time:881022ms step_avg:398.11ms step:2224/6250 train_loss:2.4401 train_time:881397ms step_avg:398.10ms step:2225/6250 train_loss:2.5725 train_time:881773ms step_avg:398.09ms step:2226/6250 train_loss:2.5684 train_time:882156ms step_avg:398.08ms step:2227/6250 train_loss:2.5023 train_time:882532ms step_avg:398.07ms step:2228/6250 train_loss:2.6028 train_time:882906ms step_avg:398.06ms step:2229/6250 train_loss:2.5511 train_time:883287ms step_avg:398.06ms step:2230/6250 train_loss:2.5166 train_time:883663ms step_avg:398.05ms step:2231/6250 train_loss:2.5967 train_time:884042ms step_avg:398.04ms step:2232/6250 train_loss:2.5171 train_time:884419ms step_avg:398.03ms step:2233/6250 train_loss:2.5796 train_time:884794ms step_avg:398.02ms step:2234/6250 train_loss:2.5441 train_time:885173ms step_avg:398.01ms step:2235/6250 train_loss:2.7052 train_time:885549ms step_avg:398.00ms step:2236/6250 train_loss:2.6856 train_time:885926ms step_avg:397.99ms step:2237/6250 train_loss:2.6024 train_time:886304ms step_avg:397.98ms step:2238/6250 train_loss:2.5440 train_time:886678ms step_avg:397.97ms step:2239/6250 train_loss:2.5812 train_time:887054ms step_avg:397.96ms step:2240/6250 train_loss:2.5570 train_time:887430ms step_avg:397.95ms step:2241/6250 train_loss:2.5755 train_time:887806ms step_avg:397.94ms step:2242/6250 train_loss:2.5557 train_time:888184ms step_avg:397.93ms step:2243/6250 train_loss:2.4501 train_time:888560ms step_avg:397.92ms step:2244/6250 train_loss:2.4685 train_time:888933ms step_avg:397.91ms step:2245/6250 train_loss:2.4667 train_time:889310ms step_avg:397.90ms step:2246/6250 train_loss:2.5735 train_time:889686ms step_avg:397.89ms step:2247/6250 train_loss:2.5532 train_time:890065ms step_avg:397.88ms step:2248/6250 train_loss:2.5224 train_time:890441ms step_avg:397.87ms step:2249/6250 train_loss:2.4958 train_time:890818ms step_avg:397.86ms step:2250/6250 train_loss:2.5405 train_time:891197ms step_avg:397.86ms step:2251/6250 train_loss:2.4712 train_time:891578ms step_avg:397.85ms step:2252/6250 train_loss:2.5526 train_time:891957ms step_avg:397.84ms step:2253/6250 train_loss:2.6171 train_time:892339ms step_avg:397.83ms step:2254/6250 train_loss:2.4579 train_time:892719ms step_avg:397.83ms step:2255/6250 train_loss:2.5496 train_time:893100ms step_avg:397.82ms step:2256/6250 train_loss:2.4895 train_time:893478ms step_avg:397.81ms step:2257/6250 train_loss:2.6529 train_time:893853ms step_avg:397.80ms step:2258/6250 train_loss:2.5530 train_time:894235ms step_avg:397.79ms step:2259/6250 train_loss:2.5620 train_time:894611ms step_avg:397.78ms step:2260/6250 train_loss:2.5848 train_time:895001ms step_avg:397.78ms step:2261/6250 train_loss:2.5678 train_time:895396ms step_avg:397.78ms step:2262/6250 train_loss:2.5020 train_time:895784ms step_avg:397.77ms step:2263/6250 train_loss:2.5843 train_time:896179ms step_avg:397.77ms step:2264/6250 train_loss:2.4706 train_time:896570ms step_avg:397.77ms step:2265/6250 train_loss:2.4798 train_time:896961ms step_avg:397.77ms step:2266/6250 train_loss:2.5016 train_time:897356ms step_avg:397.76ms step:2267/6250 train_loss:2.4909 train_time:897747ms step_avg:397.76ms step:2268/6250 train_loss:2.5775 train_time:898142ms step_avg:397.76ms step:2269/6250 train_loss:2.4983 train_time:898536ms step_avg:397.76ms step:2270/6250 train_loss:2.5974 train_time:898929ms step_avg:397.76ms step:2271/6250 train_loss:2.5367 train_time:899323ms step_avg:397.75ms step:2272/6250 train_loss:2.4863 train_time:899714ms step_avg:397.75ms step:2273/6250 train_loss:2.7129 train_time:900108ms step_avg:397.75ms step:2274/6250 train_loss:2.5792 train_time:900498ms step_avg:397.75ms step:2275/6250 train_loss:2.4693 train_time:900892ms step_avg:397.74ms step:2276/6250 train_loss:2.4023 train_time:901286ms step_avg:397.74ms step:2277/6250 train_loss:2.5274 train_time:901679ms step_avg:397.74ms step:2278/6250 train_loss:2.6374 train_time:902072ms step_avg:397.74ms step:2279/6250 train_loss:2.5223 train_time:902464ms step_avg:397.74ms step:2280/6250 train_loss:2.6519 train_time:902857ms step_avg:397.73ms step:2281/6250 train_loss:2.5490 train_time:903248ms step_avg:397.73ms step:2282/6250 train_loss:2.4986 train_time:903637ms step_avg:397.73ms step:2283/6250 train_loss:2.4710 train_time:904032ms step_avg:397.73ms step:2284/6250 train_loss:2.5496 train_time:904424ms step_avg:397.72ms step:2285/6250 train_loss:2.5458 train_time:904817ms step_avg:397.72ms step:2286/6250 train_loss:2.4605 train_time:905208ms step_avg:397.72ms step:2287/6250 train_loss:2.4851 train_time:905604ms step_avg:397.72ms step:2288/6250 train_loss:2.5656 train_time:905999ms step_avg:397.72ms step:2289/6250 train_loss:2.4778 train_time:906393ms step_avg:397.72ms step:2290/6250 train_loss:2.6212 train_time:906785ms step_avg:397.71ms step:2291/6250 train_loss:2.4197 train_time:907174ms step_avg:397.71ms step:2292/6250 train_loss:2.4985 train_time:907569ms step_avg:397.71ms step:2293/6250 train_loss:2.4217 train_time:907966ms step_avg:397.71ms step:2294/6250 train_loss:2.5452 train_time:908353ms step_avg:397.70ms step:2295/6250 train_loss:2.5592 train_time:908734ms step_avg:397.70ms step:2296/6250 train_loss:2.5728 train_time:909116ms step_avg:397.69ms step:2297/6250 train_loss:2.5516 train_time:909510ms step_avg:397.69ms step:2298/6250 train_loss:2.5473 train_time:909893ms step_avg:397.68ms step:2299/6250 train_loss:2.5556 train_time:910284ms step_avg:397.68ms step:2300/6250 train_loss:2.4979 train_time:910675ms step_avg:397.67ms step:2301/6250 train_loss:2.5027 train_time:911068ms step_avg:397.67ms step:2302/6250 train_loss:2.5395 train_time:911460ms step_avg:397.67ms step:2303/6250 train_loss:2.5151 train_time:911852ms step_avg:397.67ms step:2304/6250 train_loss:2.5674 train_time:912245ms step_avg:397.67ms step:2305/6250 train_loss:2.6127 train_time:912631ms step_avg:397.66ms step:2306/6250 train_loss:2.5589 train_time:913018ms step_avg:397.66ms step:2307/6250 train_loss:2.5003 train_time:913402ms step_avg:397.65ms step:2308/6250 train_loss:2.5874 train_time:913788ms step_avg:397.64ms step:2309/6250 train_loss:2.4337 train_time:914177ms step_avg:397.64ms step:2310/6250 train_loss:2.4943 train_time:914570ms step_avg:397.64ms step:2311/6250 train_loss:2.5055 train_time:914961ms step_avg:397.64ms step:2312/6250 train_loss:2.5512 train_time:915365ms step_avg:397.64ms step:2313/6250 train_loss:2.4915 train_time:915795ms step_avg:397.65ms step:2314/6250 train_loss:2.4764 train_time:916231ms step_avg:397.67ms step:2315/6250 train_loss:2.4489 train_time:916667ms step_avg:397.69ms step:2316/6250 train_loss:2.6178 train_time:917119ms step_avg:397.71ms step:2317/6250 train_loss:2.5265 train_time:917572ms step_avg:397.73ms step:2318/6250 train_loss:2.5648 train_time:918027ms step_avg:397.76ms step:2319/6250 train_loss:2.6766 train_time:918482ms step_avg:397.78ms step:2320/6250 train_loss:2.4257 train_time:918937ms step_avg:397.81ms step:2321/6250 train_loss:2.5480 train_time:919390ms step_avg:397.83ms step:2322/6250 train_loss:2.5445 train_time:919847ms step_avg:397.86ms step:2323/6250 train_loss:2.5703 train_time:920317ms step_avg:397.89ms step:2324/6250 train_loss:2.5096 train_time:920777ms step_avg:397.92ms step:2325/6250 train_loss:2.7133 train_time:921235ms step_avg:397.94ms step:2326/6250 train_loss:2.5480 train_time:921691ms step_avg:397.97ms step:2327/6250 train_loss:2.5085 train_time:922133ms step_avg:397.99ms step:2328/6250 train_loss:2.5086 train_time:922549ms step_avg:397.99ms step:2329/6250 train_loss:2.5164 train_time:922948ms step_avg:397.99ms step:2330/6250 train_loss:2.4725 train_time:923352ms step_avg:398.00ms step:2331/6250 train_loss:2.5521 train_time:923748ms step_avg:398.00ms step:2332/6250 train_loss:2.4926 train_time:924147ms step_avg:398.00ms step:2333/6250 train_loss:2.5178 train_time:924538ms step_avg:397.99ms step:2334/6250 train_loss:2.5449 train_time:924929ms step_avg:397.99ms step:2335/6250 train_loss:2.6500 train_time:925325ms step_avg:397.99ms step:2336/6250 train_loss:2.5383 train_time:925722ms step_avg:397.99ms step:2337/6250 train_loss:2.5102 train_time:926120ms step_avg:397.99ms step:2338/6250 train_loss:2.6164 train_time:926517ms step_avg:397.99ms step:2339/6250 train_loss:2.4520 train_time:926915ms step_avg:397.99ms step:2340/6250 train_loss:2.4767 train_time:927316ms step_avg:397.99ms step:2341/6250 train_loss:2.4334 train_time:927712ms step_avg:397.99ms step:2342/6250 train_loss:2.4836 train_time:928112ms step_avg:397.99ms step:2343/6250 train_loss:2.5375 train_time:928506ms step_avg:397.99ms step:2344/6250 train_loss:2.5912 train_time:928904ms step_avg:397.99ms step:2345/6250 train_loss:2.5760 train_time:929303ms step_avg:397.99ms step:2346/6250 train_loss:2.6030 train_time:929702ms step_avg:397.99ms step:2347/6250 train_loss:2.5892 train_time:930098ms step_avg:397.99ms step:2348/6250 train_loss:2.6045 train_time:930497ms step_avg:397.99ms step:2349/6250 train_loss:2.4673 train_time:930895ms step_avg:397.99ms step:2350/6250 train_loss:2.4342 train_time:931295ms step_avg:397.99ms step:2351/6250 train_loss:2.5308 train_time:931690ms step_avg:397.99ms step:2352/6250 train_loss:2.4380 train_time:932089ms step_avg:397.99ms step:2353/6250 train_loss:2.4405 train_time:932481ms step_avg:397.99ms step:2354/6250 train_loss:2.4801 train_time:932871ms step_avg:397.98ms step:2355/6250 train_loss:2.4975 train_time:933264ms step_avg:397.98ms step:2356/6250 train_loss:2.5346 train_time:933657ms step_avg:397.98ms step:2357/6250 train_loss:2.5558 train_time:934045ms step_avg:397.97ms step:2358/6250 train_loss:2.5386 train_time:934431ms step_avg:397.97ms step:2359/6250 train_loss:2.5528 train_time:934811ms step_avg:397.96ms step:2360/6250 train_loss:2.5244 train_time:935200ms step_avg:397.96ms step:2361/6250 train_loss:2.4869 train_time:935591ms step_avg:397.95ms step:2362/6250 train_loss:2.4168 train_time:935983ms step_avg:397.95ms step:2363/6250 train_loss:2.5481 train_time:936381ms step_avg:397.95ms step:2364/6250 train_loss:2.5050 train_time:936768ms step_avg:397.95ms step:2365/6250 train_loss:2.5484 train_time:937164ms step_avg:397.95ms step:2366/6250 train_loss:2.4689 train_time:937582ms step_avg:397.95ms step:2367/6250 train_loss:2.5777 train_time:937995ms step_avg:397.96ms step:2368/6250 train_loss:2.4870 train_time:938387ms step_avg:397.96ms step:2369/6250 train_loss:2.4096 train_time:938777ms step_avg:397.96ms step:2370/6250 train_loss:2.5543 train_time:939171ms step_avg:397.95ms step:2371/6250 train_loss:2.4558 train_time:939572ms step_avg:397.96ms step:2372/6250 train_loss:2.5660 train_time:939989ms step_avg:397.96ms step:2373/6250 train_loss:2.6221 train_time:940399ms step_avg:397.97ms step:2374/6250 train_loss:2.5717 train_time:940792ms step_avg:397.97ms step:2375/6250 train_loss:2.5290 train_time:941195ms step_avg:397.97ms step:2376/6250 train_loss:2.6378 train_time:941630ms step_avg:397.98ms step:2377/6250 train_loss:2.5878 train_time:942062ms step_avg:398.00ms step:2378/6250 train_loss:2.4725 train_time:942461ms step_avg:398.00ms step:2379/6250 train_loss:2.5315 train_time:942851ms step_avg:398.00ms step:2380/6250 train_loss:2.4807 train_time:943245ms step_avg:397.99ms step:2381/6250 train_loss:2.5791 train_time:943638ms step_avg:397.99ms step:2382/6250 train_loss:2.5423 train_time:944028ms step_avg:397.99ms step:2383/6250 train_loss:2.5317 train_time:944417ms step_avg:397.98ms step:2384/6250 train_loss:2.5999 train_time:944823ms step_avg:397.99ms step:2385/6250 train_loss:2.4835 train_time:945231ms step_avg:397.99ms step:2386/6250 train_loss:2.5814 train_time:945624ms step_avg:397.99ms step:2387/6250 train_loss:2.4909 train_time:946015ms step_avg:397.99ms step:2388/6250 train_loss:2.5592 train_time:946400ms step_avg:397.98ms step:2389/6250 train_loss:2.6025 train_time:946800ms step_avg:397.98ms step:2390/6250 train_loss:2.5213 train_time:947202ms step_avg:397.98ms step:2391/6250 train_loss:2.4890 train_time:947590ms step_avg:397.98ms step:2392/6250 train_loss:2.5840 train_time:947977ms step_avg:397.98ms step:2393/6250 train_loss:2.5426 train_time:948370ms step_avg:397.97ms step:2394/6250 train_loss:2.4337 train_time:948776ms step_avg:397.98ms step:2395/6250 train_loss:2.5002 train_time:949166ms step_avg:397.97ms step:2396/6250 train_loss:2.5472 train_time:949558ms step_avg:397.97ms step:2397/6250 train_loss:2.5877 train_time:949949ms step_avg:397.97ms step:2398/6250 train_loss:2.6057 train_time:950343ms step_avg:397.97ms step:2399/6250 train_loss:2.5134 train_time:950739ms step_avg:397.97ms step:2400/6250 train_loss:2.5806 train_time:951130ms step_avg:397.96ms step:2401/6250 train_loss:2.5080 train_time:951526ms step_avg:397.96ms step:2402/6250 train_loss:2.6350 train_time:951914ms step_avg:397.96ms step:2403/6250 train_loss:2.5061 train_time:952308ms step_avg:397.96ms step:2404/6250 train_loss:2.5934 train_time:952701ms step_avg:397.95ms step:2405/6250 train_loss:2.5900 train_time:953097ms step_avg:397.95ms step:2406/6250 train_loss:2.6200 train_time:953509ms step_avg:397.96ms step:2407/6250 train_loss:2.5420 train_time:953899ms step_avg:397.96ms step:2408/6250 train_loss:2.4522 train_time:954290ms step_avg:397.95ms step:2409/6250 train_loss:2.5779 train_time:954680ms step_avg:397.95ms step:2410/6250 train_loss:2.5598 train_time:955074ms step_avg:397.95ms step:2411/6250 train_loss:2.5086 train_time:955460ms step_avg:397.94ms step:2412/6250 train_loss:2.5062 train_time:955845ms step_avg:397.94ms step:2413/6250 train_loss:2.5679 train_time:956230ms step_avg:397.93ms step:2414/6250 train_loss:2.6054 train_time:956620ms step_avg:397.93ms step:2415/6250 train_loss:2.4611 train_time:957002ms step_avg:397.92ms step:2416/6250 train_loss:2.5280 train_time:957393ms step_avg:397.92ms step:2417/6250 train_loss:2.6073 train_time:957783ms step_avg:397.92ms step:2418/6250 train_loss:2.4912 train_time:958174ms step_avg:397.91ms step:2419/6250 train_loss:2.4458 train_time:958564ms step_avg:397.91ms step:2420/6250 train_loss:2.5160 train_time:958957ms step_avg:397.91ms step:2421/6250 train_loss:2.5120 train_time:959357ms step_avg:397.91ms step:2422/6250 train_loss:2.4444 train_time:959766ms step_avg:397.91ms step:2423/6250 train_loss:2.5264 train_time:960158ms step_avg:397.91ms step:2424/6250 train_loss:2.3985 train_time:960549ms step_avg:397.91ms step:2425/6250 train_loss:2.5050 train_time:960945ms step_avg:397.91ms step:2426/6250 train_loss:2.5225 train_time:961351ms step_avg:397.91ms step:2427/6250 train_loss:2.5130 train_time:961747ms step_avg:397.91ms step:2428/6250 train_loss:2.5678 train_time:962161ms step_avg:397.92ms step:2429/6250 train_loss:2.5764 train_time:962573ms step_avg:397.92ms step:2430/6250 train_loss:2.5436 train_time:962985ms step_avg:397.93ms step:2431/6250 train_loss:2.5190 train_time:963397ms step_avg:397.93ms step:2432/6250 train_loss:2.4831 train_time:963807ms step_avg:397.94ms step:2433/6250 train_loss:2.5463 train_time:964220ms step_avg:397.94ms step:2434/6250 train_loss:2.4869 train_time:964635ms step_avg:397.95ms step:2435/6250 train_loss:2.5581 train_time:965042ms step_avg:397.96ms step:2436/6250 train_loss:2.5433 train_time:965453ms step_avg:397.96ms step:2437/6250 train_loss:2.5409 train_time:965870ms step_avg:397.97ms step:2438/6250 train_loss:2.4856 train_time:966283ms step_avg:397.97ms step:2439/6250 train_loss:2.4900 train_time:966692ms step_avg:397.98ms step:2440/6250 train_loss:2.4493 train_time:967106ms step_avg:397.99ms step:2441/6250 train_loss:2.4894 train_time:967514ms step_avg:397.99ms step:2442/6250 train_loss:2.5558 train_time:967926ms step_avg:398.00ms step:2443/6250 train_loss:2.5029 train_time:968340ms step_avg:398.00ms step:2444/6250 train_loss:2.5833 train_time:968752ms step_avg:398.01ms step:2445/6250 train_loss:2.4887 train_time:969164ms step_avg:398.01ms step:2446/6250 train_loss:2.5395 train_time:969571ms step_avg:398.02ms step:2447/6250 train_loss:2.6019 train_time:969958ms step_avg:398.01ms step:2448/6250 train_loss:2.5697 train_time:970344ms step_avg:398.01ms step:2449/6250 train_loss:2.4892 train_time:970732ms step_avg:398.00ms step:2450/6250 train_loss:2.5679 train_time:971117ms step_avg:398.00ms step:2451/6250 train_loss:2.5183 train_time:971503ms step_avg:397.99ms step:2452/6250 train_loss:2.6025 train_time:971898ms step_avg:397.99ms step:2453/6250 train_loss:2.5885 train_time:972290ms step_avg:397.99ms step:2454/6250 train_loss:2.5925 train_time:972681ms step_avg:397.99ms step:2455/6250 train_loss:2.5318 train_time:973077ms step_avg:397.99ms step:2456/6250 train_loss:2.5236 train_time:973469ms step_avg:397.98ms step:2457/6250 train_loss:2.5228 train_time:973859ms step_avg:397.98ms step:2458/6250 train_loss:2.5180 train_time:974246ms step_avg:397.98ms step:2459/6250 train_loss:2.4950 train_time:974635ms step_avg:397.97ms step:2460/6250 train_loss:2.5805 train_time:975024ms step_avg:397.97ms step:2461/6250 train_loss:2.4776 train_time:975414ms step_avg:397.97ms step:2462/6250 train_loss:2.4934 train_time:975798ms step_avg:397.96ms step:2463/6250 train_loss:2.5698 train_time:976184ms step_avg:397.96ms step:2464/6250 train_loss:2.5446 train_time:976573ms step_avg:397.95ms step:2465/6250 train_loss:2.5289 train_time:976963ms step_avg:397.95ms step:2466/6250 train_loss:2.5486 train_time:977354ms step_avg:397.95ms step:2467/6250 train_loss:2.5965 train_time:977748ms step_avg:397.94ms step:2468/6250 train_loss:2.5113 train_time:978140ms step_avg:397.94ms step:2469/6250 train_loss:2.5162 train_time:978530ms step_avg:397.94ms step:2470/6250 train_loss:2.6161 train_time:978919ms step_avg:397.93ms step:2471/6250 train_loss:2.5138 train_time:979309ms step_avg:397.93ms step:2472/6250 train_loss:2.5362 train_time:979697ms step_avg:397.93ms step:2473/6250 train_loss:2.5056 train_time:980087ms step_avg:397.92ms step:2474/6250 train_loss:2.5509 train_time:980500ms step_avg:397.93ms step:2475/6250 train_loss:2.5335 train_time:980894ms step_avg:397.93ms step:2476/6250 train_loss:2.4541 train_time:981286ms step_avg:397.93ms step:2477/6250 train_loss:2.6195 train_time:981674ms step_avg:397.92ms step:2478/6250 train_loss:2.5848 train_time:982064ms step_avg:397.92ms step:2479/6250 train_loss:2.4734 train_time:982454ms step_avg:397.92ms step:2480/6250 train_loss:2.4744 train_time:982843ms step_avg:397.91ms step:2481/6250 train_loss:2.4676 train_time:983235ms step_avg:397.91ms step:2482/6250 train_loss:2.3852 train_time:983625ms step_avg:397.91ms step:2483/6250 train_loss:2.5420 train_time:984010ms step_avg:397.90ms step:2484/6250 train_loss:2.5762 train_time:984403ms step_avg:397.90ms step:2485/6250 train_loss:2.5733 train_time:984813ms step_avg:397.90ms step:2486/6250 train_loss:2.5700 train_time:985204ms step_avg:397.90ms step:2487/6250 train_loss:2.5514 train_time:985619ms step_avg:397.91ms step:2488/6250 train_loss:2.4772 train_time:986059ms step_avg:397.93ms step:2489/6250 train_loss:2.6054 train_time:986455ms step_avg:397.92ms step:2490/6250 train_loss:2.5335 train_time:986844ms step_avg:397.92ms step:2491/6250 train_loss:2.7068 train_time:987237ms step_avg:397.92ms step:2492/6250 train_loss:2.5953 train_time:987626ms step_avg:397.92ms step:2493/6250 train_loss:2.5569 train_time:988019ms step_avg:397.91ms step:2494/6250 train_loss:2.4929 train_time:988410ms step_avg:397.91ms step:2495/6250 train_loss:2.5158 train_time:988799ms step_avg:397.91ms step:2496/6250 train_loss:2.5286 train_time:989189ms step_avg:397.90ms step:2497/6250 train_loss:2.5231 train_time:989578ms step_avg:397.90ms step:2498/6250 train_loss:2.5095 train_time:989970ms step_avg:397.90ms step:2499/6250 train_loss:2.5612 train_time:990362ms step_avg:397.90ms step:2500/6250 train_loss:2.5346 train_time:990752ms step_avg:397.89ms step:2501/6250 train_loss:2.5613 train_time:991143ms step_avg:397.89ms step:2502/6250 train_loss:2.5927 train_time:991534ms step_avg:397.89ms step:2503/6250 train_loss:2.5847 train_time:991923ms step_avg:397.88ms step:2504/6250 train_loss:2.4842 train_time:992313ms step_avg:397.88ms step:2505/6250 train_loss:2.5661 train_time:992703ms step_avg:397.88ms step:2506/6250 train_loss:2.4112 train_time:993096ms step_avg:397.87ms step:2507/6250 train_loss:2.6230 train_time:993485ms step_avg:397.87ms step:2508/6250 train_loss:2.6346 train_time:993890ms step_avg:397.87ms step:2509/6250 train_loss:2.5636 train_time:994312ms step_avg:397.88ms step:2510/6250 train_loss:2.5722 train_time:994728ms step_avg:397.89ms step:2511/6250 train_loss:2.5708 train_time:995125ms step_avg:397.89ms step:2512/6250 train_loss:2.5370 train_time:995528ms step_avg:397.89ms step:2513/6250 train_loss:2.4746 train_time:995930ms step_avg:397.89ms step:2514/6250 train_loss:2.5588 train_time:996335ms step_avg:397.90ms step:2515/6250 train_loss:2.5285 train_time:996771ms step_avg:397.91ms step:2516/6250 train_loss:2.5806 train_time:997172ms step_avg:397.91ms step:2517/6250 train_loss:2.5266 train_time:997559ms step_avg:397.91ms step:2518/6250 train_loss:2.5436 train_time:997946ms step_avg:397.91ms step:2519/6250 train_loss:2.5246 train_time:998332ms step_avg:397.90ms step:2520/6250 train_loss:2.4399 train_time:998717ms step_avg:397.90ms step:2521/6250 train_loss:2.5395 train_time:999139ms step_avg:397.90ms step:2522/6250 train_loss:2.6363 train_time:999556ms step_avg:397.91ms step:2523/6250 train_loss:2.5480 train_time:999950ms step_avg:397.91ms step:2524/6250 train_loss:2.4104 train_time:1000371ms step_avg:397.92ms step:2525/6250 train_loss:2.5470 train_time:1000798ms step_avg:397.93ms step:2526/6250 train_loss:2.4922 train_time:1001218ms step_avg:397.94ms step:2527/6250 train_loss:2.6066 train_time:1001631ms step_avg:397.95ms step:2528/6250 train_loss:2.5024 train_time:1002042ms step_avg:397.95ms step:2529/6250 train_loss:2.5675 train_time:1002454ms step_avg:397.96ms step:2530/6250 train_loss:2.4976 train_time:1002867ms step_avg:397.96ms step:2531/6250 train_loss:2.5177 train_time:1003278ms step_avg:397.97ms step:2532/6250 train_loss:2.5107 train_time:1003700ms step_avg:397.98ms step:2533/6250 train_loss:2.5612 train_time:1004100ms step_avg:397.98ms step:2534/6250 train_loss:2.4655 train_time:1004500ms step_avg:397.98ms step:2535/6250 train_loss:2.6300 train_time:1004907ms step_avg:397.98ms step:2536/6250 train_loss:2.6132 train_time:1005331ms step_avg:397.99ms step:2537/6250 train_loss:2.4649 train_time:1005750ms step_avg:398.00ms step:2538/6250 train_loss:2.4995 train_time:1006171ms step_avg:398.01ms step:2539/6250 train_loss:2.4936 train_time:1006577ms step_avg:398.01ms step:2540/6250 train_loss:2.3914 train_time:1006988ms step_avg:398.02ms step:2541/6250 train_loss:2.5634 train_time:1007402ms step_avg:398.03ms step:2542/6250 train_loss:2.6050 train_time:1007843ms step_avg:398.04ms step:2543/6250 train_loss:2.5400 train_time:1008268ms step_avg:398.05ms step:2544/6250 train_loss:2.5779 train_time:1008676ms step_avg:398.06ms step:2545/6250 train_loss:2.5643 train_time:1009090ms step_avg:398.06ms step:2546/6250 train_loss:2.4262 train_time:1009508ms step_avg:398.07ms step:2547/6250 train_loss:2.5521 train_time:1009921ms step_avg:398.08ms step:2548/6250 train_loss:2.5588 train_time:1010326ms step_avg:398.08ms step:2549/6250 train_loss:2.5286 train_time:1010743ms step_avg:398.09ms step:2550/6250 train_loss:2.5591 train_time:1011151ms step_avg:398.09ms step:2551/6250 train_loss:2.4912 train_time:1011575ms step_avg:398.10ms step:2552/6250 train_loss:2.3973 train_time:1011993ms step_avg:398.11ms step:2553/6250 train_loss:2.4902 train_time:1012414ms step_avg:398.12ms step:2554/6250 train_loss:2.4406 train_time:1012817ms step_avg:398.12ms step:2555/6250 train_loss:2.5820 train_time:1013226ms step_avg:398.12ms step:2556/6250 train_loss:2.4292 train_time:1013637ms step_avg:398.13ms step:2557/6250 train_loss:2.5328 train_time:1014050ms step_avg:398.14ms step:2558/6250 train_loss:2.5103 train_time:1014448ms step_avg:398.14ms step:2559/6250 train_loss:2.5958 train_time:1014847ms step_avg:398.14ms step:2560/6250 train_loss:2.6825 train_time:1015261ms step_avg:398.14ms step:2561/6250 train_loss:2.5442 train_time:1015689ms step_avg:398.15ms step:2562/6250 train_loss:2.5215 train_time:1016113ms step_avg:398.16ms step:2563/6250 train_loss:2.5874 train_time:1016535ms step_avg:398.17ms step:2564/6250 train_loss:2.5903 train_time:1016948ms step_avg:398.18ms step:2565/6250 train_loss:2.4651 train_time:1017363ms step_avg:398.19ms step:2566/6250 train_loss:2.5450 train_time:1017770ms step_avg:398.19ms step:2567/6250 train_loss:2.5768 train_time:1018188ms step_avg:398.20ms step:2568/6250 train_loss:2.5530 train_time:1018598ms step_avg:398.20ms step:2569/6250 train_loss:2.5285 train_time:1019011ms step_avg:398.21ms step:2570/6250 train_loss:2.5175 train_time:1019412ms step_avg:398.21ms step:2571/6250 train_loss:2.4966 train_time:1019820ms step_avg:398.21ms step:2572/6250 train_loss:2.4623 train_time:1020229ms step_avg:398.22ms step:2573/6250 train_loss:2.4605 train_time:1020636ms step_avg:398.22ms step:2574/6250 train_loss:2.5912 train_time:1021038ms step_avg:398.22ms step:2575/6250 train_loss:2.4760 train_time:1021441ms step_avg:398.22ms step:2576/6250 train_loss:2.5224 train_time:1021845ms step_avg:398.23ms step:2577/6250 train_loss:2.4941 train_time:1022239ms step_avg:398.22ms step:2578/6250 train_loss:2.5571 train_time:1022631ms step_avg:398.22ms step:2579/6250 train_loss:2.4117 train_time:1023023ms step_avg:398.22ms step:2580/6250 train_loss:2.4509 train_time:1023419ms step_avg:398.22ms step:2581/6250 train_loss:2.5451 train_time:1023817ms step_avg:398.22ms step:2582/6250 train_loss:2.4693 train_time:1024214ms step_avg:398.22ms step:2583/6250 train_loss:2.5296 train_time:1024621ms step_avg:398.22ms step:2584/6250 train_loss:2.4488 train_time:1025026ms step_avg:398.22ms step:2585/6250 train_loss:2.5965 train_time:1025483ms step_avg:398.25ms step:2586/6250 train_loss:2.5105 train_time:1025905ms step_avg:398.26ms step:2587/6250 train_loss:2.4865 train_time:1026326ms step_avg:398.26ms step:2588/6250 train_loss:2.4508 train_time:1026743ms step_avg:398.27ms step:2589/6250 train_loss:2.5115 train_time:1027164ms step_avg:398.28ms step:2590/6250 train_loss:2.4915 train_time:1027588ms step_avg:398.29ms step:2591/6250 train_loss:2.4976 train_time:1028004ms step_avg:398.30ms step:2592/6250 train_loss:2.6241 train_time:1028425ms step_avg:398.31ms step:2593/6250 train_loss:2.5278 train_time:1028843ms step_avg:398.31ms step:2594/6250 train_loss:2.6267 train_time:1029255ms step_avg:398.32ms step:2595/6250 train_loss:2.4641 train_time:1029664ms step_avg:398.32ms step:2596/6250 train_loss:2.5300 train_time:1030066ms step_avg:398.32ms step:2597/6250 train_loss:2.4956 train_time:1030464ms step_avg:398.32ms step:2598/6250 train_loss:2.5021 train_time:1030852ms step_avg:398.32ms step:2599/6250 train_loss:2.5305 train_time:1031239ms step_avg:398.32ms step:2600/6250 train_loss:2.5807 train_time:1031627ms step_avg:398.31ms step:2601/6250 train_loss:2.5330 train_time:1032018ms step_avg:398.31ms step:2602/6250 train_loss:2.5167 train_time:1032408ms step_avg:398.31ms step:2603/6250 train_loss:2.5970 train_time:1032798ms step_avg:398.30ms step:2604/6250 train_loss:2.4729 train_time:1033185ms step_avg:398.30ms step:2605/6250 train_loss:2.5123 train_time:1033582ms step_avg:398.30ms step:2606/6250 train_loss:2.4470 train_time:1033971ms step_avg:398.29ms step:2607/6250 train_loss:2.4892 train_time:1034358ms step_avg:398.29ms step:2608/6250 train_loss:2.4718 train_time:1034754ms step_avg:398.29ms step:2609/6250 train_loss:2.6257 train_time:1035149ms step_avg:398.29ms step:2610/6250 train_loss:2.4933 train_time:1035547ms step_avg:398.29ms step:2611/6250 train_loss:2.5713 train_time:1035942ms step_avg:398.29ms step:2612/6250 train_loss:2.4948 train_time:1036332ms step_avg:398.28ms step:2613/6250 train_loss:2.5719 train_time:1036721ms step_avg:398.28ms step:2614/6250 train_loss:2.5114 train_time:1037117ms step_avg:398.28ms step:2615/6250 train_loss:2.4930 train_time:1037513ms step_avg:398.28ms step:2616/6250 train_loss:2.4480 train_time:1037908ms step_avg:398.28ms step:2617/6250 train_loss:2.5071 train_time:1038305ms step_avg:398.28ms step:2618/6250 train_loss:2.4263 train_time:1038700ms step_avg:398.27ms step:2619/6250 train_loss:2.5747 train_time:1039119ms step_avg:398.28ms step:2620/6250 train_loss:2.4590 train_time:1039520ms step_avg:398.28ms step:2621/6250 train_loss:2.5312 train_time:1039949ms step_avg:398.30ms step:2622/6250 train_loss:2.5728 train_time:1040353ms step_avg:398.30ms step:2623/6250 train_loss:2.5453 train_time:1040751ms step_avg:398.30ms step:2624/6250 train_loss:2.6441 train_time:1041149ms step_avg:398.30ms step:2625/6250 train_loss:2.4668 train_time:1041548ms step_avg:398.30ms step:2626/6250 train_loss:2.5099 train_time:1041953ms step_avg:398.30ms step:2627/6250 train_loss:2.4803 train_time:1042350ms step_avg:398.30ms step:2628/6250 train_loss:2.5083 train_time:1042750ms step_avg:398.30ms step:2629/6250 train_loss:2.5386 train_time:1043148ms step_avg:398.30ms step:2630/6250 train_loss:2.6672 train_time:1043547ms step_avg:398.30ms step:2631/6250 train_loss:2.4842 train_time:1043941ms step_avg:398.30ms step:2632/6250 train_loss:2.4853 train_time:1044340ms step_avg:398.30ms step:2633/6250 train_loss:2.5367 train_time:1044735ms step_avg:398.30ms step:2634/6250 train_loss:2.4522 train_time:1045134ms step_avg:398.30ms step:2635/6250 train_loss:2.4923 train_time:1045535ms step_avg:398.30ms step:2636/6250 train_loss:2.3904 train_time:1045937ms step_avg:398.30ms step:2637/6250 train_loss:2.5107 train_time:1046337ms step_avg:398.30ms step:2638/6250 train_loss:2.6113 train_time:1046734ms step_avg:398.30ms step:2639/6250 train_loss:2.4784 train_time:1047131ms step_avg:398.30ms step:2640/6250 train_loss:2.5121 train_time:1047529ms step_avg:398.30ms step:2641/6250 train_loss:2.5586 train_time:1047926ms step_avg:398.30ms step:2642/6250 train_loss:2.5799 train_time:1048325ms step_avg:398.30ms step:2643/6250 train_loss:2.5006 train_time:1048721ms step_avg:398.30ms step:2644/6250 train_loss:2.5094 train_time:1049114ms step_avg:398.30ms step:2645/6250 train_loss:2.5272 train_time:1049559ms step_avg:398.31ms step:2646/6250 train_loss:2.4510 train_time:1050003ms step_avg:398.33ms step:2647/6250 train_loss:2.5138 train_time:1050395ms step_avg:398.33ms step:2648/6250 train_loss:2.4398 train_time:1050795ms step_avg:398.33ms step:2649/6250 train_loss:2.4472 train_time:1051195ms step_avg:398.33ms step:2650/6250 train_loss:2.5337 train_time:1051590ms step_avg:398.33ms step:2651/6250 train_loss:2.5415 train_time:1051984ms step_avg:398.33ms step:2652/6250 train_loss:2.4773 train_time:1052395ms step_avg:398.33ms step:2653/6250 train_loss:2.5319 train_time:1052783ms step_avg:398.33ms step:2654/6250 train_loss:2.6307 train_time:1053166ms step_avg:398.32ms step:2655/6250 train_loss:2.7157 train_time:1053552ms step_avg:398.32ms step:2656/6250 train_loss:2.6712 train_time:1053938ms step_avg:398.31ms step:2657/6250 train_loss:2.5872 train_time:1054329ms step_avg:398.31ms step:2658/6250 train_loss:2.5341 train_time:1054715ms step_avg:398.31ms step:2659/6250 train_loss:2.5175 train_time:1055100ms step_avg:398.30ms step:2660/6250 train_loss:2.4280 train_time:1055494ms step_avg:398.30ms step:2661/6250 train_loss:2.5343 train_time:1055887ms step_avg:398.30ms step:2662/6250 train_loss:2.5875 train_time:1056288ms step_avg:398.30ms step:2663/6250 train_loss:2.4940 train_time:1056677ms step_avg:398.30ms step:2664/6250 train_loss:2.4876 train_time:1057071ms step_avg:398.29ms step:2665/6250 train_loss:2.5735 train_time:1057468ms step_avg:398.29ms step:2666/6250 train_loss:2.4164 train_time:1057853ms step_avg:398.29ms step:2667/6250 train_loss:2.5325 train_time:1058242ms step_avg:398.28ms step:2668/6250 train_loss:2.5925 train_time:1058629ms step_avg:398.28ms step:2669/6250 train_loss:2.5208 train_time:1059022ms step_avg:398.28ms step:2670/6250 train_loss:2.5296 train_time:1059409ms step_avg:398.27ms step:2671/6250 train_loss:2.5158 train_time:1059797ms step_avg:398.27ms step:2672/6250 train_loss:2.5377 train_time:1060186ms step_avg:398.27ms step:2673/6250 train_loss:2.5115 train_time:1060571ms step_avg:398.26ms step:2674/6250 train_loss:2.5186 train_time:1060960ms step_avg:398.26ms step:2675/6250 train_loss:2.5472 train_time:1061352ms step_avg:398.26ms step:2676/6250 train_loss:2.5561 train_time:1061737ms step_avg:398.25ms step:2677/6250 train_loss:2.4971 train_time:1062125ms step_avg:398.25ms step:2678/6250 train_loss:2.4991 train_time:1062513ms step_avg:398.24ms step:2679/6250 train_loss:2.6406 train_time:1062900ms step_avg:398.24ms step:2680/6250 train_loss:2.5141 train_time:1063288ms step_avg:398.24ms step:2681/6250 train_loss:2.4473 train_time:1063671ms step_avg:398.23ms step:2682/6250 train_loss:2.5741 train_time:1064056ms step_avg:398.22ms step:2683/6250 train_loss:2.4853 train_time:1064442ms step_avg:398.22ms step:2684/6250 train_loss:2.4967 train_time:1064830ms step_avg:398.22ms step:2685/6250 train_loss:2.5300 train_time:1065218ms step_avg:398.21ms step:2686/6250 train_loss:2.5949 train_time:1065607ms step_avg:398.21ms step:2687/6250 train_loss:2.4996 train_time:1065996ms step_avg:398.21ms step:2688/6250 train_loss:2.5345 train_time:1066384ms step_avg:398.20ms step:2689/6250 train_loss:2.5022 train_time:1066769ms step_avg:398.20ms step:2690/6250 train_loss:2.5257 train_time:1067158ms step_avg:398.19ms step:2691/6250 train_loss:2.5240 train_time:1067546ms step_avg:398.19ms step:2692/6250 train_loss:2.5364 train_time:1067933ms step_avg:398.19ms step:2693/6250 train_loss:2.4445 train_time:1068324ms step_avg:398.18ms step:2694/6250 train_loss:2.4997 train_time:1068713ms step_avg:398.18ms step:2695/6250 train_loss:2.4970 train_time:1069105ms step_avg:398.18ms step:2696/6250 train_loss:2.5499 train_time:1069494ms step_avg:398.17ms step:2697/6250 train_loss:2.5525 train_time:1069879ms step_avg:398.17ms step:2698/6250 train_loss:2.6004 train_time:1070270ms step_avg:398.17ms step:2699/6250 train_loss:2.4468 train_time:1070655ms step_avg:398.16ms step:2700/6250 train_loss:2.5567 train_time:1071043ms step_avg:398.16ms step:2701/6250 train_loss:2.5074 train_time:1071431ms step_avg:398.15ms step:2702/6250 train_loss:2.5678 train_time:1071823ms step_avg:398.15ms step:2703/6250 train_loss:2.4702 train_time:1072222ms step_avg:398.15ms step:2704/6250 train_loss:2.4795 train_time:1072618ms step_avg:398.15ms step:2705/6250 train_loss:2.5885 train_time:1073015ms step_avg:398.15ms step:2706/6250 train_loss:2.4854 train_time:1073415ms step_avg:398.15ms step:2707/6250 train_loss:2.4955 train_time:1073812ms step_avg:398.15ms step:2708/6250 train_loss:2.5290 train_time:1074219ms step_avg:398.15ms step:2709/6250 train_loss:2.4211 train_time:1074617ms step_avg:398.15ms step:2710/6250 train_loss:2.5143 train_time:1075019ms step_avg:398.16ms step:2711/6250 train_loss:2.4808 train_time:1075421ms step_avg:398.16ms step:2712/6250 train_loss:2.4598 train_time:1075817ms step_avg:398.16ms step:2713/6250 train_loss:2.5555 train_time:1076218ms step_avg:398.16ms step:2714/6250 train_loss:2.4903 train_time:1076614ms step_avg:398.16ms step:2715/6250 train_loss:2.4611 train_time:1077011ms step_avg:398.16ms step:2716/6250 train_loss:2.5040 train_time:1077412ms step_avg:398.16ms step:2717/6250 train_loss:2.5380 train_time:1077807ms step_avg:398.16ms step:2718/6250 train_loss:2.5877 train_time:1078207ms step_avg:398.16ms step:2719/6250 train_loss:2.5769 train_time:1078607ms step_avg:398.16ms step:2720/6250 train_loss:2.4338 train_time:1079004ms step_avg:398.16ms step:2721/6250 train_loss:2.4123 train_time:1079409ms step_avg:398.16ms step:2722/6250 train_loss:2.6060 train_time:1079805ms step_avg:398.16ms step:2723/6250 train_loss:2.3884 train_time:1080198ms step_avg:398.16ms step:2724/6250 train_loss:2.5252 train_time:1080591ms step_avg:398.15ms step:2725/6250 train_loss:2.5705 train_time:1080983ms step_avg:398.15ms step:2726/6250 train_loss:2.4898 train_time:1081379ms step_avg:398.15ms step:2727/6250 train_loss:2.5367 train_time:1081788ms step_avg:398.16ms step:2728/6250 train_loss:2.3564 train_time:1082194ms step_avg:398.16ms step:2729/6250 train_loss:2.4940 train_time:1082598ms step_avg:398.16ms step:2730/6250 train_loss:2.4533 train_time:1082999ms step_avg:398.16ms step:2731/6250 train_loss:2.4973 train_time:1083403ms step_avg:398.16ms step:2732/6250 train_loss:2.5320 train_time:1083805ms step_avg:398.17ms step:2733/6250 train_loss:2.4472 train_time:1084207ms step_avg:398.17ms step:2734/6250 train_loss:2.6075 train_time:1084608ms step_avg:398.17ms step:2735/6250 train_loss:2.4955 train_time:1085012ms step_avg:398.17ms step:2736/6250 train_loss:2.4928 train_time:1085415ms step_avg:398.17ms step:2737/6250 train_loss:2.5011 train_time:1085817ms step_avg:398.17ms step:2738/6250 train_loss:2.5736 train_time:1086224ms step_avg:398.18ms step:2739/6250 train_loss:2.5398 train_time:1086627ms step_avg:398.18ms step:2740/6250 train_loss:2.4912 train_time:1087032ms step_avg:398.18ms step:2741/6250 train_loss:2.4957 train_time:1087437ms step_avg:398.18ms step:2742/6250 train_loss:2.4632 train_time:1087841ms step_avg:398.18ms step:2743/6250 train_loss:2.4341 train_time:1088252ms step_avg:398.19ms step:2744/6250 train_loss:2.4868 train_time:1088652ms step_avg:398.19ms step:2745/6250 train_loss:2.5506 train_time:1089052ms step_avg:398.19ms step:2746/6250 train_loss:2.5079 train_time:1089455ms step_avg:398.19ms step:2747/6250 train_loss:2.5332 train_time:1089856ms step_avg:398.19ms step:2748/6250 train_loss:2.5126 train_time:1090266ms step_avg:398.20ms step:2749/6250 train_loss:2.5419 train_time:1090687ms step_avg:398.21ms step:2750/6250 train_loss:2.5029 train_time:1091109ms step_avg:398.22ms step:2751/6250 train_loss:2.4720 train_time:1091532ms step_avg:398.22ms step:2752/6250 train_loss:2.5552 train_time:1091945ms step_avg:398.23ms step:2753/6250 train_loss:2.4343 train_time:1092366ms step_avg:398.24ms step:2754/6250 train_loss:2.5137 train_time:1092779ms step_avg:398.24ms step:2755/6250 train_loss:2.4923 train_time:1093194ms step_avg:398.25ms step:2756/6250 train_loss:2.5168 train_time:1093620ms step_avg:398.26ms step:2757/6250 train_loss:2.4723 train_time:1094044ms step_avg:398.27ms step:2758/6250 train_loss:2.4752 train_time:1094474ms step_avg:398.28ms step:2759/6250 train_loss:2.4384 train_time:1094901ms step_avg:398.29ms step:2760/6250 train_loss:2.5004 train_time:1095328ms step_avg:398.30ms step:2761/6250 train_loss:2.4987 train_time:1095777ms step_avg:398.32ms step:2762/6250 train_loss:2.4306 train_time:1096219ms step_avg:398.34ms step:2763/6250 train_loss:2.3922 train_time:1096661ms step_avg:398.35ms step:2764/6250 train_loss:2.4048 train_time:1097089ms step_avg:398.36ms step:2765/6250 train_loss:2.4548 train_time:1097536ms step_avg:398.38ms step:2766/6250 train_loss:2.4671 train_time:1097951ms step_avg:398.39ms step:2767/6250 train_loss:2.5832 train_time:1098364ms step_avg:398.39ms step:2768/6250 train_loss:2.4384 train_time:1098779ms step_avg:398.40ms step:2769/6250 train_loss:2.5046 train_time:1099211ms step_avg:398.41ms step:2770/6250 train_loss:2.4427 train_time:1099627ms step_avg:398.42ms step:2771/6250 train_loss:2.4335 train_time:1100037ms step_avg:398.42ms step:2772/6250 train_loss:2.4953 train_time:1100456ms step_avg:398.43ms step:2773/6250 train_loss:2.5179 train_time:1100882ms step_avg:398.44ms step:2774/6250 train_loss:2.5268 train_time:1101312ms step_avg:398.45ms step:2775/6250 train_loss:2.6502 train_time:1101738ms step_avg:398.46ms step:2776/6250 train_loss:2.4849 train_time:1102166ms step_avg:398.47ms step:2777/6250 train_loss:2.5218 train_time:1102593ms step_avg:398.48ms step:2778/6250 train_loss:2.5170 train_time:1103023ms step_avg:398.49ms step:2779/6250 train_loss:2.4464 train_time:1103436ms step_avg:398.50ms step:2780/6250 train_loss:2.5679 train_time:1103854ms step_avg:398.50ms step:2781/6250 train_loss:2.4742 train_time:1104273ms step_avg:398.51ms step:2782/6250 train_loss:2.6100 train_time:1104696ms step_avg:398.52ms step:2783/6250 train_loss:2.5538 train_time:1105114ms step_avg:398.53ms step:2784/6250 train_loss:2.5377 train_time:1105530ms step_avg:398.53ms step:2785/6250 train_loss:2.6025 train_time:1105952ms step_avg:398.54ms step:2786/6250 train_loss:2.5302 train_time:1106374ms step_avg:398.55ms step:2787/6250 train_loss:2.6007 train_time:1106791ms step_avg:398.56ms step:2788/6250 train_loss:2.5555 train_time:1107207ms step_avg:398.56ms step:2789/6250 train_loss:2.3247 train_time:1107619ms step_avg:398.57ms step:2790/6250 train_loss:2.4410 train_time:1108034ms step_avg:398.57ms step:2791/6250 train_loss:2.5038 train_time:1108455ms step_avg:398.58ms step:2792/6250 train_loss:2.4931 train_time:1108870ms step_avg:398.59ms step:2793/6250 train_loss:2.5574 train_time:1109291ms step_avg:398.60ms step:2794/6250 train_loss:2.4720 train_time:1109718ms step_avg:398.61ms step:2795/6250 train_loss:2.5694 train_time:1110155ms step_avg:398.62ms step:2796/6250 train_loss:2.5300 train_time:1110579ms step_avg:398.63ms step:2797/6250 train_loss:2.5639 train_time:1110989ms step_avg:398.63ms step:2798/6250 train_loss:2.5183 train_time:1111390ms step_avg:398.63ms step:2799/6250 train_loss:2.4609 train_time:1111787ms step_avg:398.63ms step:2800/6250 train_loss:2.5507 train_time:1112201ms step_avg:398.64ms step:2801/6250 train_loss:2.4599 train_time:1112637ms step_avg:398.65ms step:2802/6250 train_loss:2.5176 train_time:1113066ms step_avg:398.66ms step:2803/6250 train_loss:2.4775 train_time:1113483ms step_avg:398.67ms step:2804/6250 train_loss:2.5038 train_time:1113897ms step_avg:398.67ms step:2805/6250 train_loss:2.6611 train_time:1114313ms step_avg:398.68ms step:2806/6250 train_loss:2.5622 train_time:1114725ms step_avg:398.69ms step:2807/6250 train_loss:2.4992 train_time:1115138ms step_avg:398.69ms step:2808/6250 train_loss:2.5207 train_time:1115554ms step_avg:398.70ms step:2809/6250 train_loss:2.5167 train_time:1115963ms step_avg:398.70ms step:2810/6250 train_loss:2.5274 train_time:1116377ms step_avg:398.71ms step:2811/6250 train_loss:2.6196 train_time:1116784ms step_avg:398.71ms step:2812/6250 train_loss:2.4910 train_time:1117194ms step_avg:398.71ms step:2813/6250 train_loss:2.4916 train_time:1117605ms step_avg:398.72ms step:2814/6250 train_loss:2.4016 train_time:1118020ms step_avg:398.72ms step:2815/6250 train_loss:2.4839 train_time:1118434ms step_avg:398.73ms step:2816/6250 train_loss:2.4439 train_time:1118845ms step_avg:398.73ms step:2817/6250 train_loss:2.4975 train_time:1119262ms step_avg:398.74ms step:2818/6250 train_loss:2.5332 train_time:1119671ms step_avg:398.74ms step:2819/6250 train_loss:2.4773 train_time:1120076ms step_avg:398.75ms step:2820/6250 train_loss:2.4623 train_time:1120486ms step_avg:398.75ms step:2821/6250 train_loss:2.4223 train_time:1120893ms step_avg:398.75ms step:2822/6250 train_loss:2.4068 train_time:1121304ms step_avg:398.76ms step:2823/6250 train_loss:2.4930 train_time:1121714ms step_avg:398.76ms step:2824/6250 train_loss:2.6244 train_time:1122123ms step_avg:398.76ms step:2825/6250 train_loss:2.5115 train_time:1122534ms step_avg:398.77ms step:2826/6250 train_loss:2.4149 train_time:1122940ms step_avg:398.77ms step:2827/6250 train_loss:2.5259 train_time:1123355ms step_avg:398.78ms step:2828/6250 train_loss:2.5521 train_time:1123767ms step_avg:398.78ms step:2829/6250 train_loss:2.5133 train_time:1124188ms step_avg:398.79ms step:2830/6250 train_loss:2.4362 train_time:1124607ms step_avg:398.80ms step:2831/6250 train_loss:2.6260 train_time:1125023ms step_avg:398.80ms step:2832/6250 train_loss:2.5465 train_time:1125430ms step_avg:398.81ms step:2833/6250 train_loss:2.4378 train_time:1125833ms step_avg:398.81ms step:2834/6250 train_loss:2.5193 train_time:1126241ms step_avg:398.81ms step:2835/6250 train_loss:2.4677 train_time:1126644ms step_avg:398.81ms step:2836/6250 train_loss:2.5117 train_time:1127050ms step_avg:398.81ms step:2837/6250 train_loss:2.5232 train_time:1127476ms step_avg:398.82ms step:2838/6250 train_loss:2.4860 train_time:1127886ms step_avg:398.83ms step:2839/6250 train_loss:2.4905 train_time:1128296ms step_avg:398.83ms step:2840/6250 train_loss:2.4719 train_time:1128704ms step_avg:398.84ms step:2841/6250 train_loss:2.5511 train_time:1129099ms step_avg:398.83ms step:2842/6250 train_loss:2.5077 train_time:1129504ms step_avg:398.84ms step:2843/6250 train_loss:2.4765 train_time:1129911ms step_avg:398.84ms step:2844/6250 train_loss:2.5112 train_time:1130322ms step_avg:398.84ms step:2845/6250 train_loss:2.4730 train_time:1130713ms step_avg:398.84ms step:2846/6250 train_loss:2.4301 train_time:1131107ms step_avg:398.84ms step:2847/6250 train_loss:2.4534 train_time:1131504ms step_avg:398.84ms step:2848/6250 train_loss:2.4642 train_time:1131896ms step_avg:398.84ms step:2849/6250 train_loss:2.4675 train_time:1132304ms step_avg:398.84ms step:2850/6250 train_loss:2.4527 train_time:1132714ms step_avg:398.84ms step:2851/6250 train_loss:2.5211 train_time:1133126ms step_avg:398.85ms step:2852/6250 train_loss:2.5090 train_time:1133552ms step_avg:398.86ms step:2853/6250 train_loss:2.5638 train_time:1133979ms step_avg:398.87ms step:2854/6250 train_loss:2.5675 train_time:1134407ms step_avg:398.88ms step:2855/6250 train_loss:2.5480 train_time:1134831ms step_avg:398.89ms step:2856/6250 train_loss:2.6536 train_time:1135261ms step_avg:398.90ms step:2857/6250 train_loss:2.4855 train_time:1135685ms step_avg:398.91ms step:2858/6250 train_loss:2.5841 train_time:1136108ms step_avg:398.91ms step:2859/6250 train_loss:2.4822 train_time:1136539ms step_avg:398.93ms step:2860/6250 train_loss:2.5419 train_time:1136967ms step_avg:398.94ms step:2861/6250 train_loss:2.4559 train_time:1137395ms step_avg:398.95ms step:2862/6250 train_loss:2.5054 train_time:1137818ms step_avg:398.95ms step:2863/6250 train_loss:2.6126 train_time:1138242ms step_avg:398.96ms step:2864/6250 train_loss:2.5687 train_time:1138663ms step_avg:398.97ms step:2865/6250 train_loss:2.4903 train_time:1139082ms step_avg:398.98ms step:2866/6250 train_loss:2.4904 train_time:1139492ms step_avg:398.98ms step:2867/6250 train_loss:2.5016 train_time:1139898ms step_avg:398.98ms step:2868/6250 train_loss:2.4625 train_time:1140300ms step_avg:398.99ms step:2869/6250 train_loss:2.4857 train_time:1140710ms step_avg:398.99ms step:2870/6250 train_loss:2.5510 train_time:1141110ms step_avg:398.99ms step:2871/6250 train_loss:2.5600 train_time:1141524ms step_avg:398.99ms step:2872/6250 train_loss:2.4733 train_time:1141947ms step_avg:399.00ms step:2873/6250 train_loss:2.5473 train_time:1142369ms step_avg:399.01ms step:2874/6250 train_loss:2.3981 train_time:1142779ms step_avg:399.01ms step:2875/6250 train_loss:2.4901 train_time:1143194ms step_avg:399.02ms step:2876/6250 train_loss:2.5407 train_time:1143612ms step_avg:399.03ms step:2877/6250 train_loss:2.4863 train_time:1144029ms step_avg:399.03ms step:2878/6250 train_loss:2.4912 train_time:1144451ms step_avg:399.04ms step:2879/6250 train_loss:2.4399 train_time:1144872ms step_avg:399.05ms step:2880/6250 train_loss:2.5672 train_time:1145294ms step_avg:399.06ms step:2881/6250 train_loss:2.4859 train_time:1145714ms step_avg:399.06ms step:2882/6250 train_loss:2.5968 train_time:1146138ms step_avg:399.07ms step:2883/6250 train_loss:2.4322 train_time:1146562ms step_avg:399.08ms step:2884/6250 train_loss:2.5099 train_time:1146985ms step_avg:399.09ms step:2885/6250 train_loss:2.3777 train_time:1147413ms step_avg:399.10ms step:2886/6250 train_loss:2.5075 train_time:1147839ms step_avg:399.11ms step:2887/6250 train_loss:2.4282 train_time:1148266ms step_avg:399.12ms step:2888/6250 train_loss:2.5487 train_time:1148697ms step_avg:399.13ms step:2889/6250 train_loss:2.4121 train_time:1149137ms step_avg:399.14ms step:2890/6250 train_loss:2.5375 train_time:1149562ms step_avg:399.15ms step:2891/6250 train_loss:2.5126 train_time:1149986ms step_avg:399.16ms step:2892/6250 train_loss:2.5090 train_time:1150411ms step_avg:399.17ms step:2893/6250 train_loss:2.5762 train_time:1150819ms step_avg:399.17ms step:2894/6250 train_loss:2.5207 train_time:1151227ms step_avg:399.18ms step:2895/6250 train_loss:2.4366 train_time:1151634ms step_avg:399.18ms step:2896/6250 train_loss:2.3957 train_time:1152035ms step_avg:399.18ms step:2897/6250 train_loss:2.4994 train_time:1152443ms step_avg:399.18ms step:2898/6250 train_loss:2.5112 train_time:1152843ms step_avg:399.18ms step:2899/6250 train_loss:2.4758 train_time:1153252ms step_avg:399.19ms step:2900/6250 train_loss:2.6610 train_time:1153656ms step_avg:399.19ms step:2901/6250 train_loss:2.4109 train_time:1154060ms step_avg:399.19ms step:2902/6250 train_loss:2.4238 train_time:1154466ms step_avg:399.19ms step:2903/6250 train_loss:2.5396 train_time:1154870ms step_avg:399.19ms step:2904/6250 train_loss:2.4261 train_time:1155278ms step_avg:399.20ms step:2905/6250 train_loss:2.5121 train_time:1155684ms step_avg:399.20ms step:2906/6250 train_loss:2.4228 train_time:1156089ms step_avg:399.20ms step:2907/6250 train_loss:2.5105 train_time:1156498ms step_avg:399.21ms step:2908/6250 train_loss:2.4829 train_time:1156901ms step_avg:399.21ms step:2909/6250 train_loss:2.4580 train_time:1157310ms step_avg:399.21ms step:2910/6250 train_loss:2.4341 train_time:1157720ms step_avg:399.21ms step:2911/6250 train_loss:2.5427 train_time:1158131ms step_avg:399.22ms step:2912/6250 train_loss:2.4599 train_time:1158534ms step_avg:399.22ms step:2913/6250 train_loss:2.4951 train_time:1158941ms step_avg:399.22ms step:2914/6250 train_loss:2.4972 train_time:1159345ms step_avg:399.22ms step:2915/6250 train_loss:2.4241 train_time:1159748ms step_avg:399.22ms step:2916/6250 train_loss:2.6815 train_time:1160154ms step_avg:399.23ms step:2917/6250 train_loss:2.5457 train_time:1160559ms step_avg:399.23ms step:2918/6250 train_loss:2.5505 train_time:1160982ms step_avg:399.24ms step:2919/6250 train_loss:2.4766 train_time:1161434ms step_avg:399.26ms step:2920/6250 train_loss:2.5938 train_time:1161898ms step_avg:399.28ms step:2921/6250 train_loss:2.5571 train_time:1162360ms step_avg:399.30ms step:2922/6250 train_loss:2.5031 train_time:1162823ms step_avg:399.32ms step:2923/6250 train_loss:2.4425 train_time:1163274ms step_avg:399.34ms step:2924/6250 train_loss:2.5099 train_time:1163712ms step_avg:399.35ms step:2925/6250 train_loss:2.4512 train_time:1164168ms step_avg:399.37ms step:2926/6250 train_loss:2.5078 train_time:1164642ms step_avg:399.40ms step:2927/6250 train_loss:2.4707 train_time:1165105ms step_avg:399.42ms step:2928/6250 train_loss:2.4969 train_time:1165557ms step_avg:399.44ms step:2929/6250 train_loss:2.5162 train_time:1166007ms step_avg:399.45ms step:2930/6250 train_loss:2.5830 train_time:1166452ms step_avg:399.47ms step:2931/6250 train_loss:2.5153 train_time:1166900ms step_avg:399.49ms step:2932/6250 train_loss:2.4987 train_time:1167351ms step_avg:399.50ms step:2933/6250 train_loss:2.5479 train_time:1167796ms step_avg:399.52ms step:2934/6250 train_loss:2.4923 train_time:1168242ms step_avg:399.54ms step:2935/6250 train_loss:2.3875 train_time:1168683ms step_avg:399.55ms step:2936/6250 train_loss:2.4936 train_time:1169129ms step_avg:399.57ms step:2937/6250 train_loss:2.4671 train_time:1169567ms step_avg:399.58ms step:2938/6250 train_loss:2.4972 train_time:1170006ms step_avg:399.59ms step:2939/6250 train_loss:2.4981 train_time:1170445ms step_avg:399.61ms step:2940/6250 train_loss:2.4937 train_time:1170886ms step_avg:399.62ms step:2941/6250 train_loss:2.4069 train_time:1171329ms step_avg:399.63ms step:2942/6250 train_loss:2.4315 train_time:1171769ms step_avg:399.65ms step:2943/6250 train_loss:2.4810 train_time:1172207ms step_avg:399.66ms step:2944/6250 train_loss:2.5963 train_time:1172645ms step_avg:399.67ms step:2945/6250 train_loss:2.5600 train_time:1173082ms step_avg:399.69ms step:2946/6250 train_loss:2.5061 train_time:1173534ms step_avg:399.71ms step:2947/6250 train_loss:2.4733 train_time:1173978ms step_avg:399.72ms step:2948/6250 train_loss:2.5701 train_time:1174419ms step_avg:399.73ms step:2949/6250 train_loss:2.4144 train_time:1174856ms step_avg:399.75ms step:2950/6250 train_loss:2.5406 train_time:1175295ms step_avg:399.76ms step:2951/6250 train_loss:2.5067 train_time:1175729ms step_avg:399.77ms step:2952/6250 train_loss:2.5744 train_time:1176173ms step_avg:399.79ms step:2953/6250 train_loss:2.4818 train_time:1176610ms step_avg:399.80ms step:2954/6250 train_loss:2.5239 train_time:1177046ms step_avg:399.81ms step:2955/6250 train_loss:2.4162 train_time:1177483ms step_avg:399.82ms step:2956/6250 train_loss:2.5200 train_time:1177918ms step_avg:399.84ms step:2957/6250 train_loss:2.4581 train_time:1178357ms step_avg:399.85ms step:2958/6250 train_loss:2.5106 train_time:1178793ms step_avg:399.86ms step:2959/6250 train_loss:2.4526 train_time:1179230ms step_avg:399.87ms step:2960/6250 train_loss:2.5327 train_time:1179670ms step_avg:399.89ms step:2961/6250 train_loss:2.4700 train_time:1180119ms step_avg:399.90ms step:2962/6250 train_loss:2.4970 train_time:1180564ms step_avg:399.92ms step:2963/6250 train_loss:2.6060 train_time:1180996ms step_avg:399.93ms step:2964/6250 train_loss:2.4665 train_time:1181401ms step_avg:399.93ms step:2965/6250 train_loss:2.5062 train_time:1181799ms step_avg:399.93ms step:2966/6250 train_loss:2.5014 train_time:1182197ms step_avg:399.93ms step:2967/6250 train_loss:2.6319 train_time:1182596ms step_avg:399.93ms step:2968/6250 train_loss:2.5344 train_time:1182998ms step_avg:399.93ms step:2969/6250 train_loss:2.4057 train_time:1183398ms step_avg:399.93ms step:2970/6250 train_loss:2.4320 train_time:1183796ms step_avg:399.93ms step:2971/6250 train_loss:2.4942 train_time:1184200ms step_avg:399.93ms step:2972/6250 train_loss:2.4193 train_time:1184600ms step_avg:399.93ms step:2973/6250 train_loss:2.4830 train_time:1185001ms step_avg:399.93ms step:2974/6250 train_loss:2.4661 train_time:1185405ms step_avg:399.93ms step:2975/6250 train_loss:2.4689 train_time:1185807ms step_avg:399.94ms step:2976/6250 train_loss:2.5121 train_time:1186211ms step_avg:399.94ms step:2977/6250 train_loss:2.4848 train_time:1186612ms step_avg:399.94ms step:2978/6250 train_loss:2.5873 train_time:1187010ms step_avg:399.94ms step:2979/6250 train_loss:2.5282 train_time:1187412ms step_avg:399.94ms step:2980/6250 train_loss:2.5340 train_time:1187816ms step_avg:399.94ms step:2981/6250 train_loss:2.4980 train_time:1188216ms step_avg:399.94ms step:2982/6250 train_loss:2.4666 train_time:1188621ms step_avg:399.94ms step:2983/6250 train_loss:2.5617 train_time:1189022ms step_avg:399.94ms step:2984/6250 train_loss:2.4402 train_time:1189425ms step_avg:399.94ms step:2985/6250 train_loss:2.4220 train_time:1189825ms step_avg:399.94ms step:2986/6250 train_loss:2.4888 train_time:1190229ms step_avg:399.94ms step:2987/6250 train_loss:2.4753 train_time:1190629ms step_avg:399.94ms step:2988/6250 train_loss:2.4381 train_time:1191023ms step_avg:399.94ms step:2989/6250 train_loss:2.4376 train_time:1191439ms step_avg:399.95ms step:2990/6250 train_loss:2.5198 train_time:1191854ms step_avg:399.95ms step:2991/6250 train_loss:2.5674 train_time:1192271ms step_avg:399.96ms step:2992/6250 train_loss:2.4523 train_time:1192688ms step_avg:399.96ms step:2993/6250 train_loss:2.4689 train_time:1193091ms step_avg:399.96ms step:2994/6250 train_loss:2.5195 train_time:1193495ms step_avg:399.96ms step:2995/6250 train_loss:2.4734 train_time:1193893ms step_avg:399.96ms step:2996/6250 train_loss:2.4582 train_time:1194303ms step_avg:399.97ms step:2997/6250 train_loss:2.5220 train_time:1194722ms step_avg:399.97ms step:2998/6250 train_loss:2.4269 train_time:1195140ms step_avg:399.98ms step:2999/6250 train_loss:2.5426 train_time:1195558ms step_avg:399.99ms step:3000/6250 train_loss:2.3957 train_time:1195978ms step_avg:399.99ms step:3001/6250 train_loss:2.4726 train_time:1196401ms step_avg:400.00ms step:3002/6250 train_loss:2.5032 train_time:1196817ms step_avg:400.01ms step:3003/6250 train_loss:2.4961 train_time:1197240ms step_avg:400.01ms step:3004/6250 train_loss:2.4892 train_time:1197659ms step_avg:400.02ms step:3005/6250 train_loss:2.5248 train_time:1198076ms step_avg:400.03ms step:3006/6250 train_loss:2.5002 train_time:1198496ms step_avg:400.03ms step:3007/6250 train_loss:2.4996 train_time:1198916ms step_avg:400.04ms step:3008/6250 train_loss:2.4333 train_time:1199339ms step_avg:400.05ms step:3009/6250 train_loss:2.4902 train_time:1199757ms step_avg:400.05ms step:3010/6250 train_loss:2.4798 train_time:1200178ms step_avg:400.06ms step:3011/6250 train_loss:2.5123 train_time:1200599ms step_avg:400.07ms step:3012/6250 train_loss:2.3916 train_time:1201017ms step_avg:400.07ms step:3013/6250 train_loss:2.5714 train_time:1201437ms step_avg:400.08ms step:3014/6250 train_loss:2.5122 train_time:1201839ms step_avg:400.08ms step:3015/6250 train_loss:2.3988 train_time:1202244ms step_avg:400.08ms step:3016/6250 train_loss:2.4071 train_time:1202647ms step_avg:400.08ms step:3017/6250 train_loss:2.4388 train_time:1203050ms step_avg:400.08ms step:3018/6250 train_loss:2.4114 train_time:1203452ms step_avg:400.08ms step:3019/6250 train_loss:2.5368 train_time:1203854ms step_avg:400.08ms step:3020/6250 train_loss:2.5274 train_time:1204254ms step_avg:400.08ms step:3021/6250 train_loss:2.5932 train_time:1204656ms step_avg:400.09ms step:3022/6250 train_loss:2.4618 train_time:1205058ms step_avg:400.09ms step:3023/6250 train_loss:2.5146 train_time:1205459ms step_avg:400.09ms step:3024/6250 train_loss:2.4566 train_time:1205862ms step_avg:400.09ms step:3025/6250 train_loss:2.4457 train_time:1206283ms step_avg:400.09ms step:3026/6250 train_loss:2.4129 train_time:1206703ms step_avg:400.10ms step:3027/6250 train_loss:2.4545 train_time:1207119ms step_avg:400.11ms step:3028/6250 train_loss:2.4485 train_time:1207537ms step_avg:400.11ms step:3029/6250 train_loss:2.4493 train_time:1207960ms step_avg:400.12ms step:3030/6250 train_loss:2.4515 train_time:1208381ms step_avg:400.13ms step:3031/6250 train_loss:2.5783 train_time:1208808ms step_avg:400.13ms step:3032/6250 train_loss:2.4976 train_time:1209230ms step_avg:400.14ms step:3033/6250 train_loss:2.4289 train_time:1209652ms step_avg:400.15ms step:3034/6250 train_loss:2.4387 train_time:1210073ms step_avg:400.16ms step:3035/6250 train_loss:2.5339 train_time:1210497ms step_avg:400.16ms step:3036/6250 train_loss:2.4599 train_time:1210919ms step_avg:400.17ms step:3037/6250 train_loss:2.4524 train_time:1211342ms step_avg:400.18ms step:3038/6250 train_loss:2.5140 train_time:1211763ms step_avg:400.19ms step:3039/6250 train_loss:2.4683 train_time:1212164ms step_avg:400.19ms step:3040/6250 train_loss:2.4599 train_time:1212566ms step_avg:400.19ms step:3041/6250 train_loss:2.3732 train_time:1212973ms step_avg:400.19ms step:3042/6250 train_loss:2.4804 train_time:1213383ms step_avg:400.19ms step:3043/6250 train_loss:2.3898 train_time:1213793ms step_avg:400.20ms step:3044/6250 train_loss:2.4246 train_time:1214204ms step_avg:400.20ms step:3045/6250 train_loss:2.5869 train_time:1214607ms step_avg:400.20ms step:3046/6250 train_loss:2.4812 train_time:1215015ms step_avg:400.20ms step:3047/6250 train_loss:2.5025 train_time:1215428ms step_avg:400.21ms step:3048/6250 train_loss:2.4881 train_time:1215856ms step_avg:400.22ms step:3049/6250 train_loss:2.4820 train_time:1216284ms step_avg:400.23ms step:3050/6250 train_loss:2.4877 train_time:1216712ms step_avg:400.23ms step:3051/6250 train_loss:2.4813 train_time:1217139ms step_avg:400.24ms step:3052/6250 train_loss:2.5336 train_time:1217566ms step_avg:400.25ms step:3053/6250 train_loss:2.5338 train_time:1217990ms step_avg:400.26ms step:3054/6250 train_loss:2.3795 train_time:1218414ms step_avg:400.27ms step:3055/6250 train_loss:2.4289 train_time:1218817ms step_avg:400.27ms step:3056/6250 train_loss:2.4961 train_time:1219221ms step_avg:400.27ms step:3057/6250 train_loss:2.4476 train_time:1219614ms step_avg:400.27ms step:3058/6250 train_loss:2.4856 train_time:1220001ms step_avg:400.26ms step:3059/6250 train_loss:2.4921 train_time:1220410ms step_avg:400.27ms step:3060/6250 train_loss:2.5553 train_time:1220815ms step_avg:400.27ms step:3061/6250 train_loss:2.5124 train_time:1221223ms step_avg:400.27ms step:3062/6250 train_loss:2.4928 train_time:1221627ms step_avg:400.27ms step:3063/6250 train_loss:2.4458 train_time:1222036ms step_avg:400.27ms step:3064/6250 train_loss:2.4427 train_time:1222441ms step_avg:400.28ms step:3065/6250 train_loss:2.4328 train_time:1222845ms step_avg:400.28ms step:3066/6250 train_loss:2.4498 train_time:1223252ms step_avg:400.28ms step:3067/6250 train_loss:2.5379 train_time:1223655ms step_avg:400.28ms step:3068/6250 train_loss:2.4354 train_time:1224058ms step_avg:400.28ms step:3069/6250 train_loss:2.5089 train_time:1224466ms step_avg:400.28ms step:3070/6250 train_loss:2.4663 train_time:1224872ms step_avg:400.29ms step:3071/6250 train_loss:2.5032 train_time:1225279ms step_avg:400.29ms step:3072/6250 train_loss:2.3936 train_time:1225684ms step_avg:400.29ms step:3073/6250 train_loss:2.4531 train_time:1226085ms step_avg:400.29ms step:3074/6250 train_loss:2.4934 train_time:1226488ms step_avg:400.29ms step:3075/6250 train_loss:2.5404 train_time:1226891ms step_avg:400.29ms step:3076/6250 train_loss:2.4417 train_time:1227297ms step_avg:400.29ms step:3077/6250 train_loss:2.5277 train_time:1227699ms step_avg:400.29ms step:3078/6250 train_loss:2.4785 train_time:1228101ms step_avg:400.29ms step:3079/6250 train_loss:2.5030 train_time:1228506ms step_avg:400.30ms step:3080/6250 train_loss:2.4250 train_time:1228912ms step_avg:400.30ms step:3081/6250 train_loss:2.5256 train_time:1229319ms step_avg:400.30ms step:3082/6250 train_loss:2.5186 train_time:1229724ms step_avg:400.30ms step:3083/6250 train_loss:2.4387 train_time:1230132ms step_avg:400.30ms step:3084/6250 train_loss:2.4887 train_time:1230538ms step_avg:400.31ms step:3085/6250 train_loss:2.5639 train_time:1230943ms step_avg:400.31ms step:3086/6250 train_loss:2.3685 train_time:1231348ms step_avg:400.31ms step:3087/6250 train_loss:2.5532 train_time:1231753ms step_avg:400.31ms step:3088/6250 train_loss:2.5101 train_time:1232158ms step_avg:400.31ms step:3089/6250 train_loss:2.5769 train_time:1232567ms step_avg:400.31ms step:3090/6250 train_loss:2.4518 train_time:1232970ms step_avg:400.31ms step:3091/6250 train_loss:2.4482 train_time:1233378ms step_avg:400.32ms step:3092/6250 train_loss:2.5107 train_time:1233781ms step_avg:400.32ms step:3093/6250 train_loss:2.4918 train_time:1234183ms step_avg:400.32ms step:3094/6250 train_loss:2.5017 train_time:1234590ms step_avg:400.32ms step:3095/6250 train_loss:2.4879 train_time:1234996ms step_avg:400.32ms step:3096/6250 train_loss:2.4983 train_time:1235399ms step_avg:400.32ms step:3097/6250 train_loss:2.4273 train_time:1235805ms step_avg:400.33ms step:3098/6250 train_loss:2.4242 train_time:1236211ms step_avg:400.33ms step:3099/6250 train_loss:2.4730 train_time:1236615ms step_avg:400.33ms step:3100/6250 train_loss:2.5730 train_time:1237020ms step_avg:400.33ms step:3101/6250 train_loss:2.4589 train_time:1237424ms step_avg:400.33ms step:3102/6250 train_loss:2.4084 train_time:1237819ms step_avg:400.33ms step:3103/6250 train_loss:2.4678 train_time:1238221ms step_avg:400.33ms step:3104/6250 train_loss:2.5041 train_time:1238619ms step_avg:400.33ms step:3105/6250 train_loss:2.4682 train_time:1239017ms step_avg:400.33ms step:3106/6250 train_loss:2.4704 train_time:1239416ms step_avg:400.33ms step:3107/6250 train_loss:2.4463 train_time:1239814ms step_avg:400.33ms step:3108/6250 train_loss:2.5178 train_time:1240214ms step_avg:400.33ms step:3109/6250 train_loss:2.5470 train_time:1240613ms step_avg:400.33ms step:3110/6250 train_loss:2.4453 train_time:1241012ms step_avg:400.33ms step:3111/6250 train_loss:2.3671 train_time:1241410ms step_avg:400.33ms step:3112/6250 train_loss:2.4780 train_time:1241810ms step_avg:400.33ms step:3113/6250 train_loss:2.4768 train_time:1242207ms step_avg:400.32ms step:3114/6250 train_loss:2.5710 train_time:1242592ms step_avg:400.32ms step:3115/6250 train_loss:2.4407 train_time:1242980ms step_avg:400.32ms step:3116/6250 train_loss:2.5153 train_time:1243369ms step_avg:400.31ms step:3117/6250 train_loss:2.5455 train_time:1243754ms step_avg:400.31ms step:3118/6250 train_loss:2.4863 train_time:1244141ms step_avg:400.30ms step:3119/6250 train_loss:2.4804 train_time:1244528ms step_avg:400.30ms step:3120/6250 train_loss:2.5036 train_time:1244909ms step_avg:400.29ms step:3121/6250 train_loss:2.4496 train_time:1245299ms step_avg:400.29ms step:3122/6250 train_loss:2.4765 train_time:1245681ms step_avg:400.28ms step:3123/6250 train_loss:2.5075 train_time:1246067ms step_avg:400.28ms step:3124/6250 train_loss:2.4784 train_time:1246455ms step_avg:400.27ms step:3125/6250 train_loss:2.4074 train_time:1246849ms step_avg:400.27ms step:3126/6250 train_loss:2.5053 train_time:1247243ms step_avg:400.27ms step:3127/6250 train_loss:2.5365 train_time:1247635ms step_avg:400.27ms step:3128/6250 train_loss:2.5495 train_time:1248026ms step_avg:400.27ms step:3129/6250 train_loss:2.4203 train_time:1248427ms step_avg:400.27ms step:3130/6250 train_loss:2.4234 train_time:1248832ms step_avg:400.27ms step:3131/6250 train_loss:2.5310 train_time:1249238ms step_avg:400.27ms step:3132/6250 train_loss:2.4501 train_time:1249639ms step_avg:400.27ms step:3133/6250 train_loss:2.5098 train_time:1250039ms step_avg:400.27ms step:3134/6250 train_loss:2.5509 train_time:1250442ms step_avg:400.27ms step:3135/6250 train_loss:2.5770 train_time:1250863ms step_avg:400.28ms step:3136/6250 train_loss:2.4312 train_time:1251327ms step_avg:400.30ms step:3137/6250 train_loss:2.5029 train_time:1251748ms step_avg:400.30ms step:3138/6250 train_loss:2.4806 train_time:1252152ms step_avg:400.30ms step:3139/6250 train_loss:2.4521 train_time:1252564ms step_avg:400.31ms step:3140/6250 train_loss:2.4762 train_time:1252985ms step_avg:400.31ms step:3141/6250 train_loss:2.4650 train_time:1253409ms step_avg:400.32ms step:3142/6250 train_loss:2.4976 train_time:1253814ms step_avg:400.32ms step:3143/6250 train_loss:2.4776 train_time:1254212ms step_avg:400.32ms step:3144/6250 train_loss:2.4782 train_time:1254602ms step_avg:400.32ms step:3145/6250 train_loss:2.5259 train_time:1254991ms step_avg:400.32ms step:3146/6250 train_loss:2.5480 train_time:1255382ms step_avg:400.31ms step:3147/6250 train_loss:2.4424 train_time:1255774ms step_avg:400.31ms step:3148/6250 train_loss:2.5401 train_time:1256206ms step_avg:400.32ms step:3149/6250 train_loss:2.3654 train_time:1256650ms step_avg:400.33ms step:3150/6250 train_loss:2.5167 train_time:1257060ms step_avg:400.34ms step:3151/6250 train_loss:2.4511 train_time:1257458ms step_avg:400.34ms step:3152/6250 train_loss:2.4938 train_time:1257885ms step_avg:400.35ms step:3153/6250 train_loss:2.4431 train_time:1258348ms step_avg:400.37ms step:3154/6250 train_loss:2.5306 train_time:1258797ms step_avg:400.38ms step:3155/6250 train_loss:2.4917 train_time:1259219ms step_avg:400.39ms step:3156/6250 train_loss:2.4057 train_time:1259641ms step_avg:400.39ms step:3157/6250 train_loss:2.4426 train_time:1260046ms step_avg:400.40ms step:3158/6250 train_loss:2.5170 train_time:1260451ms step_avg:400.40ms step:3159/6250 train_loss:2.5862 train_time:1260858ms step_avg:400.40ms step:3160/6250 train_loss:2.4904 train_time:1261262ms step_avg:400.40ms step:3161/6250 train_loss:2.4724 train_time:1261663ms step_avg:400.40ms step:3162/6250 train_loss:2.4098 train_time:1262069ms step_avg:400.40ms step:3163/6250 train_loss:2.5319 train_time:1262472ms step_avg:400.40ms step:3164/6250 train_loss:2.4945 train_time:1262876ms step_avg:400.40ms step:3165/6250 train_loss:2.4624 train_time:1263285ms step_avg:400.41ms step:3166/6250 train_loss:2.5392 train_time:1263689ms step_avg:400.41ms step:3167/6250 train_loss:2.5262 train_time:1264089ms step_avg:400.41ms step:3168/6250 train_loss:2.4217 train_time:1264489ms step_avg:400.41ms step:3169/6250 train_loss:2.5051 train_time:1264883ms step_avg:400.41ms step:3170/6250 train_loss:2.4710 train_time:1265267ms step_avg:400.40ms step:3171/6250 train_loss:2.4562 train_time:1265645ms step_avg:400.39ms step:3172/6250 train_loss:2.4876 train_time:1266029ms step_avg:400.39ms step:3173/6250 train_loss:2.5429 train_time:1266421ms step_avg:400.39ms step:3174/6250 train_loss:2.4609 train_time:1266811ms step_avg:400.38ms step:3175/6250 train_loss:2.5235 train_time:1267259ms step_avg:400.40ms step:3176/6250 train_loss:2.4871 train_time:1267709ms step_avg:400.41ms step:3177/6250 train_loss:2.4724 train_time:1268126ms step_avg:400.42ms step:3178/6250 train_loss:2.5988 train_time:1268533ms step_avg:400.42ms step:3179/6250 train_loss:2.5875 train_time:1268939ms step_avg:400.42ms step:3180/6250 train_loss:2.4362 train_time:1269345ms step_avg:400.42ms step:3181/6250 train_loss:2.5585 train_time:1269731ms step_avg:400.42ms step:3182/6250 train_loss:2.4060 train_time:1270114ms step_avg:400.41ms step:3183/6250 train_loss:2.4995 train_time:1270495ms step_avg:400.41ms step:3184/6250 train_loss:2.5434 train_time:1270875ms step_avg:400.40ms step:3185/6250 train_loss:2.3855 train_time:1271264ms step_avg:400.40ms step:3186/6250 train_loss:2.4010 train_time:1271655ms step_avg:400.40ms step:3187/6250 train_loss:2.4545 train_time:1272039ms step_avg:400.39ms step:3188/6250 train_loss:2.4305 train_time:1272428ms step_avg:400.39ms step:3189/6250 train_loss:2.4102 train_time:1272815ms step_avg:400.38ms step:3190/6250 train_loss:2.3894 train_time:1273200ms step_avg:400.38ms step:3191/6250 train_loss:2.4670 train_time:1273589ms step_avg:400.37ms step:3192/6250 train_loss:2.5429 train_time:1273994ms step_avg:400.38ms step:3193/6250 train_loss:2.4968 train_time:1274439ms step_avg:400.39ms step:3194/6250 train_loss:2.4246 train_time:1274874ms step_avg:400.40ms step:3195/6250 train_loss:2.4258 train_time:1275280ms step_avg:400.40ms step:3196/6250 train_loss:2.4880 train_time:1275683ms step_avg:400.40ms step:3197/6250 train_loss:2.4116 train_time:1276082ms step_avg:400.40ms step:3198/6250 train_loss:2.4359 train_time:1276468ms step_avg:400.40ms step:3199/6250 train_loss:2.5660 train_time:1276854ms step_avg:400.39ms step:3200/6250 train_loss:2.3934 train_time:1277241ms step_avg:400.39ms step:3201/6250 train_loss:2.4469 train_time:1277631ms step_avg:400.39ms step:3202/6250 train_loss:2.4096 train_time:1278016ms step_avg:400.38ms step:3203/6250 train_loss:2.5619 train_time:1278403ms step_avg:400.38ms step:3204/6250 train_loss:2.4403 train_time:1278791ms step_avg:400.37ms step:3205/6250 train_loss:2.5312 train_time:1279177ms step_avg:400.37ms step:3206/6250 train_loss:2.4853 train_time:1279563ms step_avg:400.36ms step:3207/6250 train_loss:2.5164 train_time:1279954ms step_avg:400.36ms step:3208/6250 train_loss:2.4318 train_time:1280364ms step_avg:400.36ms step:3209/6250 train_loss:2.4561 train_time:1280777ms step_avg:400.37ms step:3210/6250 train_loss:2.4941 train_time:1281176ms step_avg:400.37ms step:3211/6250 train_loss:2.4628 train_time:1281576ms step_avg:400.37ms step:3212/6250 train_loss:2.4076 train_time:1281977ms step_avg:400.37ms step:3213/6250 train_loss:2.4394 train_time:1282380ms step_avg:400.37ms step:3214/6250 train_loss:2.4376 train_time:1282785ms step_avg:400.37ms step:3215/6250 train_loss:2.4427 train_time:1283192ms step_avg:400.37ms step:3216/6250 train_loss:2.5001 train_time:1283602ms step_avg:400.37ms step:3217/6250 train_loss:2.5055 train_time:1284004ms step_avg:400.38ms step:3218/6250 train_loss:2.5451 train_time:1284409ms step_avg:400.38ms step:3219/6250 train_loss:2.3645 train_time:1284813ms step_avg:400.38ms step:3220/6250 train_loss:2.5476 train_time:1285217ms step_avg:400.38ms step:3221/6250 train_loss:2.5400 train_time:1285617ms step_avg:400.38ms step:3222/6250 train_loss:2.4622 train_time:1286019ms step_avg:400.38ms step:3223/6250 train_loss:2.4135 train_time:1286445ms step_avg:400.39ms step:3224/6250 train_loss:2.5286 train_time:1286857ms step_avg:400.39ms step:3225/6250 train_loss:2.4131 train_time:1287294ms step_avg:400.40ms step:3226/6250 train_loss:2.5489 train_time:1287720ms step_avg:400.41ms step:3227/6250 train_loss:2.5242 train_time:1288154ms step_avg:400.42ms step:3228/6250 train_loss:2.3624 train_time:1288576ms step_avg:400.43ms step:3229/6250 train_loss:2.5350 train_time:1289005ms step_avg:400.44ms step:3230/6250 train_loss:2.4456 train_time:1289410ms step_avg:400.44ms step:3231/6250 train_loss:2.5675 train_time:1289813ms step_avg:400.44ms step:3232/6250 train_loss:2.4509 train_time:1290219ms step_avg:400.44ms step:3233/6250 train_loss:2.5606 train_time:1290622ms step_avg:400.44ms step:3234/6250 train_loss:2.4362 train_time:1291027ms step_avg:400.44ms step:3235/6250 train_loss:2.4144 train_time:1291431ms step_avg:400.44ms step:3236/6250 train_loss:2.4603 train_time:1291833ms step_avg:400.44ms step:3237/6250 train_loss:2.4144 train_time:1292237ms step_avg:400.45ms step:3238/6250 train_loss:2.4803 train_time:1292648ms step_avg:400.45ms step:3239/6250 train_loss:2.4371 train_time:1293050ms step_avg:400.45ms step:3240/6250 train_loss:2.4351 train_time:1293454ms step_avg:400.45ms step:3241/6250 train_loss:2.4651 train_time:1293857ms step_avg:400.45ms step:3242/6250 train_loss:2.4754 train_time:1294265ms step_avg:400.45ms step:3243/6250 train_loss:2.4655 train_time:1294664ms step_avg:400.45ms step:3244/6250 train_loss:2.4562 train_time:1295069ms step_avg:400.45ms step:3245/6250 train_loss:2.5542 train_time:1295476ms step_avg:400.46ms step:3246/6250 train_loss:2.4823 train_time:1295879ms step_avg:400.46ms step:3247/6250 train_loss:2.4889 train_time:1296284ms step_avg:400.46ms step:3248/6250 train_loss:2.4223 train_time:1296688ms step_avg:400.46ms step:3249/6250 train_loss:2.5077 train_time:1297093ms step_avg:400.46ms step:3250/6250 train_loss:2.4842 train_time:1297497ms step_avg:400.46ms step:3251/6250 train_loss:2.4892 train_time:1297898ms step_avg:400.46ms step:3252/6250 train_loss:2.5524 train_time:1298305ms step_avg:400.46ms step:3253/6250 train_loss:2.5116 train_time:1298704ms step_avg:400.46ms step:3254/6250 train_loss:2.4466 train_time:1299108ms step_avg:400.46ms step:3255/6250 train_loss:2.3646 train_time:1299511ms step_avg:400.47ms step:3256/6250 train_loss:2.4625 train_time:1299913ms step_avg:400.47ms step:3257/6250 train_loss:2.5586 train_time:1300315ms step_avg:400.47ms step:3258/6250 train_loss:2.5118 train_time:1300713ms step_avg:400.47ms step:3259/6250 train_loss:2.4983 train_time:1301114ms step_avg:400.47ms step:3260/6250 train_loss:2.4601 train_time:1301514ms step_avg:400.47ms step:3261/6250 train_loss:2.5420 train_time:1301913ms step_avg:400.47ms step:3262/6250 train_loss:2.3782 train_time:1302320ms step_avg:400.47ms step:3263/6250 train_loss:2.4262 train_time:1302718ms step_avg:400.47ms step:3264/6250 train_loss:2.4963 train_time:1303116ms step_avg:400.47ms step:3265/6250 train_loss:2.4309 train_time:1303514ms step_avg:400.47ms step:3266/6250 train_loss:2.4960 train_time:1303914ms step_avg:400.47ms step:3267/6250 train_loss:2.5803 train_time:1304314ms step_avg:400.46ms step:3268/6250 train_loss:2.5212 train_time:1304714ms step_avg:400.46ms step:3269/6250 train_loss:2.4902 train_time:1305112ms step_avg:400.46ms step:3270/6250 train_loss:2.5221 train_time:1305509ms step_avg:400.46ms step:3271/6250 train_loss:2.4992 train_time:1305908ms step_avg:400.46ms step:3272/6250 train_loss:2.4897 train_time:1306308ms step_avg:400.46ms step:3273/6250 train_loss:2.5017 train_time:1306703ms step_avg:400.46ms step:3274/6250 train_loss:2.5008 train_time:1307102ms step_avg:400.46ms step:3275/6250 train_loss:2.4178 train_time:1307497ms step_avg:400.46ms step:3276/6250 train_loss:2.5376 train_time:1307895ms step_avg:400.46ms step:3277/6250 train_loss:2.5519 train_time:1308292ms step_avg:400.46ms step:3278/6250 train_loss:2.4255 train_time:1308688ms step_avg:400.46ms step:3279/6250 train_loss:2.4425 train_time:1309089ms step_avg:400.46ms step:3280/6250 train_loss:2.4581 train_time:1309488ms step_avg:400.46ms step:3281/6250 train_loss:2.4373 train_time:1309882ms step_avg:400.45ms step:3282/6250 train_loss:2.5498 train_time:1310278ms step_avg:400.45ms step:3283/6250 train_loss:2.4282 train_time:1310674ms step_avg:400.45ms step:3284/6250 train_loss:2.5100 train_time:1311070ms step_avg:400.45ms step:3285/6250 train_loss:2.4757 train_time:1311469ms step_avg:400.45ms step:3286/6250 train_loss:2.5910 train_time:1311866ms step_avg:400.45ms step:3287/6250 train_loss:2.5280 train_time:1312263ms step_avg:400.45ms step:3288/6250 train_loss:2.3909 train_time:1312660ms step_avg:400.45ms step:3289/6250 train_loss:2.4941 train_time:1313055ms step_avg:400.44ms step:3290/6250 train_loss:2.4511 train_time:1313455ms step_avg:400.44ms step:3291/6250 train_loss:2.5588 train_time:1313850ms step_avg:400.44ms step:3292/6250 train_loss:2.5431 train_time:1314246ms step_avg:400.44ms step:3293/6250 train_loss:2.4367 train_time:1314640ms step_avg:400.44ms step:3294/6250 train_loss:2.4931 train_time:1315038ms step_avg:400.44ms step:3295/6250 train_loss:2.3915 train_time:1315435ms step_avg:400.44ms step:3296/6250 train_loss:2.4628 train_time:1315830ms step_avg:400.44ms step:3297/6250 train_loss:2.5192 train_time:1316225ms step_avg:400.43ms step:3298/6250 train_loss:2.5127 train_time:1316622ms step_avg:400.43ms step:3299/6250 train_loss:2.4721 train_time:1317015ms step_avg:400.43ms step:3300/6250 train_loss:2.4269 train_time:1317412ms step_avg:400.43ms step:3301/6250 train_loss:2.4392 train_time:1317804ms step_avg:400.43ms step:3302/6250 train_loss:2.3833 train_time:1318201ms step_avg:400.43ms step:3303/6250 train_loss:2.4404 train_time:1318596ms step_avg:400.42ms step:3304/6250 train_loss:2.4525 train_time:1318990ms step_avg:400.42ms step:3305/6250 train_loss:2.5168 train_time:1319387ms step_avg:400.42ms step:3306/6250 train_loss:2.3468 train_time:1319779ms step_avg:400.42ms step:3307/6250 train_loss:2.4184 train_time:1320172ms step_avg:400.42ms step:3308/6250 train_loss:2.4549 train_time:1320569ms step_avg:400.42ms step:3309/6250 train_loss:2.5498 train_time:1320966ms step_avg:400.41ms step:3310/6250 train_loss:2.5186 train_time:1321364ms step_avg:400.41ms step:3311/6250 train_loss:2.4053 train_time:1321758ms step_avg:400.41ms step:3312/6250 train_loss:2.4633 train_time:1322153ms step_avg:400.41ms step:3313/6250 train_loss:2.3501 train_time:1322548ms step_avg:400.41ms step:3314/6250 train_loss:2.5669 train_time:1322940ms step_avg:400.41ms step:3315/6250 train_loss:2.4358 train_time:1323337ms step_avg:400.40ms step:3316/6250 train_loss:2.4828 train_time:1323735ms step_avg:400.40ms step:3317/6250 train_loss:2.4213 train_time:1324129ms step_avg:400.40ms step:3318/6250 train_loss:2.4870 train_time:1324523ms step_avg:400.40ms step:3319/6250 train_loss:2.4850 train_time:1324919ms step_avg:400.40ms step:3320/6250 train_loss:2.5273 train_time:1325314ms step_avg:400.40ms step:3321/6250 train_loss:2.4763 train_time:1325710ms step_avg:400.40ms step:3322/6250 train_loss:2.6024 train_time:1326118ms step_avg:400.40ms step:3323/6250 train_loss:2.5190 train_time:1326520ms step_avg:400.40ms step:3324/6250 train_loss:2.4498 train_time:1326919ms step_avg:400.40ms step:3325/6250 train_loss:2.6183 train_time:1327313ms step_avg:400.40ms step:3326/6250 train_loss:2.4477 train_time:1327702ms step_avg:400.39ms step:3327/6250 train_loss:2.4588 train_time:1328089ms step_avg:400.39ms step:3328/6250 train_loss:2.3947 train_time:1328479ms step_avg:400.39ms step:3329/6250 train_loss:2.4726 train_time:1328863ms step_avg:400.38ms step:3330/6250 train_loss:2.4504 train_time:1329249ms step_avg:400.38ms step:3331/6250 train_loss:2.4308 train_time:1329635ms step_avg:400.37ms step:3332/6250 train_loss:2.3588 train_time:1330023ms step_avg:400.37ms step:3333/6250 train_loss:2.4853 train_time:1330410ms step_avg:400.36ms step:3334/6250 train_loss:2.5999 train_time:1330799ms step_avg:400.36ms step:3335/6250 train_loss:2.4687 train_time:1331188ms step_avg:400.36ms step:3336/6250 train_loss:2.4816 train_time:1331576ms step_avg:400.35ms step:3337/6250 train_loss:2.5007 train_time:1331963ms step_avg:400.35ms step:3338/6250 train_loss:2.4676 train_time:1332348ms step_avg:400.34ms step:3339/6250 train_loss:2.4257 train_time:1332734ms step_avg:400.34ms step:3340/6250 train_loss:2.3933 train_time:1333120ms step_avg:400.34ms step:3341/6250 train_loss:2.4538 train_time:1333509ms step_avg:400.33ms step:3342/6250 train_loss:2.4322 train_time:1333893ms step_avg:400.33ms step:3343/6250 train_loss:2.4409 train_time:1334281ms step_avg:400.32ms step:3344/6250 train_loss:2.4593 train_time:1334668ms step_avg:400.32ms step:3345/6250 train_loss:2.4360 train_time:1335055ms step_avg:400.32ms step:3346/6250 train_loss:2.5168 train_time:1335440ms step_avg:400.31ms step:3347/6250 train_loss:2.4700 train_time:1335828ms step_avg:400.31ms step:3348/6250 train_loss:2.5013 train_time:1336213ms step_avg:400.30ms step:3349/6250 train_loss:2.5054 train_time:1336598ms step_avg:400.30ms step:3350/6250 train_loss:2.5178 train_time:1336984ms step_avg:400.29ms step:3351/6250 train_loss:2.4936 train_time:1337369ms step_avg:400.29ms step:3352/6250 train_loss:2.4137 train_time:1337756ms step_avg:400.29ms step:3353/6250 train_loss:2.4886 train_time:1338144ms step_avg:400.28ms step:3354/6250 train_loss:2.5262 train_time:1338529ms step_avg:400.28ms step:3355/6250 train_loss:2.4213 train_time:1338915ms step_avg:400.27ms step:3356/6250 train_loss:2.5090 train_time:1339300ms step_avg:400.27ms step:3357/6250 train_loss:2.4796 train_time:1339684ms step_avg:400.26ms step:3358/6250 train_loss:2.5899 train_time:1340072ms step_avg:400.26ms step:3359/6250 train_loss:2.4302 train_time:1340460ms step_avg:400.26ms step:3360/6250 train_loss:2.4538 train_time:1340844ms step_avg:400.25ms step:3361/6250 train_loss:2.4151 train_time:1341230ms step_avg:400.25ms step:3362/6250 train_loss:2.4416 train_time:1341616ms step_avg:400.24ms step:3363/6250 train_loss:2.5272 train_time:1342000ms step_avg:400.24ms step:3364/6250 train_loss:2.3862 train_time:1342386ms step_avg:400.23ms step:3365/6250 train_loss:2.4111 train_time:1342770ms step_avg:400.23ms step:3366/6250 train_loss:2.4032 train_time:1343158ms step_avg:400.23ms step:3367/6250 train_loss:2.5340 train_time:1343545ms step_avg:400.22ms step:3368/6250 train_loss:2.4294 train_time:1343930ms step_avg:400.22ms step:3369/6250 train_loss:2.3985 train_time:1344314ms step_avg:400.21ms step:3370/6250 train_loss:2.4979 train_time:1344705ms step_avg:400.21ms step:3371/6250 train_loss:2.4703 train_time:1345091ms step_avg:400.21ms step:3372/6250 train_loss:2.3352 train_time:1345482ms step_avg:400.20ms step:3373/6250 train_loss:2.4827 train_time:1345872ms step_avg:400.20ms step:3374/6250 train_loss:2.5648 train_time:1346260ms step_avg:400.20ms step:3375/6250 train_loss:2.4790 train_time:1346646ms step_avg:400.19ms step:3376/6250 train_loss:2.5984 train_time:1347030ms step_avg:400.19ms step:3377/6250 train_loss:2.4280 train_time:1347416ms step_avg:400.18ms step:3378/6250 train_loss:2.4473 train_time:1347801ms step_avg:400.18ms step:3379/6250 train_loss:2.4460 train_time:1348191ms step_avg:400.18ms step:3380/6250 train_loss:2.4732 train_time:1348578ms step_avg:400.17ms step:3381/6250 train_loss:2.4029 train_time:1348963ms step_avg:400.17ms step:3382/6250 train_loss:2.4433 train_time:1349351ms step_avg:400.16ms step:3383/6250 train_loss:2.4386 train_time:1349739ms step_avg:400.16ms step:3384/6250 train_loss:2.4535 train_time:1350127ms step_avg:400.16ms step:3385/6250 train_loss:2.5091 train_time:1350511ms step_avg:400.15ms step:3386/6250 train_loss:2.4318 train_time:1350897ms step_avg:400.15ms step:3387/6250 train_loss:2.4575 train_time:1351283ms step_avg:400.14ms step:3388/6250 train_loss:2.3983 train_time:1351662ms step_avg:400.14ms step:3389/6250 train_loss:2.5084 train_time:1352054ms step_avg:400.13ms step:3390/6250 train_loss:2.4116 train_time:1352460ms step_avg:400.14ms step:3391/6250 train_loss:2.3694 train_time:1352862ms step_avg:400.14ms step:3392/6250 train_loss:2.4247 train_time:1353266ms step_avg:400.14ms step:3393/6250 train_loss:2.3531 train_time:1353646ms step_avg:400.13ms step:3394/6250 train_loss:2.5438 train_time:1354026ms step_avg:400.13ms step:3395/6250 train_loss:2.4624 train_time:1354408ms step_avg:400.12ms step:3396/6250 train_loss:2.5409 train_time:1354787ms step_avg:400.11ms step:3397/6250 train_loss:2.4851 train_time:1355171ms step_avg:400.11ms step:3398/6250 train_loss:2.4677 train_time:1355553ms step_avg:400.10ms step:3399/6250 train_loss:2.4991 train_time:1355934ms step_avg:400.10ms step:3400/6250 train_loss:2.5349 train_time:1356318ms step_avg:400.09ms step:3401/6250 train_loss:2.4943 train_time:1356698ms step_avg:400.09ms step:3402/6250 train_loss:2.4701 train_time:1357082ms step_avg:400.08ms step:3403/6250 train_loss:2.4112 train_time:1357471ms step_avg:400.08ms step:3404/6250 train_loss:2.4668 train_time:1357862ms step_avg:400.08ms step:3405/6250 train_loss:2.4224 train_time:1358253ms step_avg:400.07ms step:3406/6250 train_loss:2.4990 train_time:1358641ms step_avg:400.07ms step:3407/6250 train_loss:2.4805 train_time:1359035ms step_avg:400.07ms step:3408/6250 train_loss:2.4587 train_time:1359428ms step_avg:400.07ms step:3409/6250 train_loss:2.5117 train_time:1359809ms step_avg:400.06ms step:3410/6250 train_loss:2.4821 train_time:1360202ms step_avg:400.06ms step:3411/6250 train_loss:2.3840 train_time:1360607ms step_avg:400.06ms step:3412/6250 train_loss:2.4205 train_time:1361011ms step_avg:400.06ms step:3413/6250 train_loss:2.4645 train_time:1361416ms step_avg:400.06ms step:3414/6250 train_loss:2.3256 train_time:1361823ms step_avg:400.07ms step:3415/6250 train_loss:2.4002 train_time:1362230ms step_avg:400.07ms step:3416/6250 train_loss:2.3970 train_time:1362634ms step_avg:400.07ms step:3417/6250 train_loss:2.4564 train_time:1363040ms step_avg:400.07ms step:3418/6250 train_loss:2.4387 train_time:1363447ms step_avg:400.07ms step:3419/6250 train_loss:2.5140 train_time:1363855ms step_avg:400.07ms step:3420/6250 train_loss:2.3887 train_time:1364255ms step_avg:400.07ms step:3421/6250 train_loss:2.4853 train_time:1364644ms step_avg:400.07ms step:3422/6250 train_loss:2.5357 train_time:1365034ms step_avg:400.07ms step:3423/6250 train_loss:2.4118 train_time:1365425ms step_avg:400.07ms step:3424/6250 train_loss:2.4591 train_time:1365811ms step_avg:400.06ms step:3425/6250 train_loss:2.4114 train_time:1366199ms step_avg:400.06ms step:3426/6250 train_loss:2.3610 train_time:1366594ms step_avg:400.06ms step:3427/6250 train_loss:2.4627 train_time:1366982ms step_avg:400.05ms step:3428/6250 train_loss:2.4687 train_time:1367371ms step_avg:400.05ms step:3429/6250 train_loss:2.3851 train_time:1367759ms step_avg:400.05ms step:3430/6250 train_loss:2.4770 train_time:1368147ms step_avg:400.04ms step:3431/6250 train_loss:2.4278 train_time:1368538ms step_avg:400.04ms step:3432/6250 train_loss:2.4016 train_time:1368928ms step_avg:400.04ms step:3433/6250 train_loss:2.3386 train_time:1369315ms step_avg:400.03ms step:3434/6250 train_loss:2.4269 train_time:1369722ms step_avg:400.04ms step:3435/6250 train_loss:2.4660 train_time:1370125ms step_avg:400.04ms step:3436/6250 train_loss:2.4380 train_time:1370527ms step_avg:400.04ms step:3437/6250 train_loss:2.3950 train_time:1370938ms step_avg:400.04ms step:3438/6250 train_loss:2.4598 train_time:1371344ms step_avg:400.04ms step:3439/6250 train_loss:2.4333 train_time:1371750ms step_avg:400.04ms step:3440/6250 train_loss:2.4406 train_time:1372150ms step_avg:400.04ms step:3441/6250 train_loss:2.4137 train_time:1372534ms step_avg:400.04ms step:3442/6250 train_loss:2.4189 train_time:1372914ms step_avg:400.03ms step:3443/6250 train_loss:2.4683 train_time:1373294ms step_avg:400.03ms step:3444/6250 train_loss:2.4966 train_time:1373675ms step_avg:400.02ms step:3445/6250 train_loss:2.4517 train_time:1374060ms step_avg:400.02ms step:3446/6250 train_loss:2.4438 train_time:1374448ms step_avg:400.01ms step:3447/6250 train_loss:2.4182 train_time:1374831ms step_avg:400.01ms step:3448/6250 train_loss:2.3938 train_time:1375219ms step_avg:400.01ms step:3449/6250 train_loss:2.4784 train_time:1375602ms step_avg:400.00ms step:3450/6250 train_loss:2.4181 train_time:1375980ms step_avg:399.99ms step:3451/6250 train_loss:2.4563 train_time:1376364ms step_avg:399.99ms step:3452/6250 train_loss:2.4463 train_time:1376746ms step_avg:399.98ms step:3453/6250 train_loss:2.4875 train_time:1377135ms step_avg:399.98ms step:3454/6250 train_loss:2.4319 train_time:1377524ms step_avg:399.98ms step:3455/6250 train_loss:2.4892 train_time:1377907ms step_avg:399.97ms step:3456/6250 train_loss:2.4648 train_time:1378325ms step_avg:399.98ms step:3457/6250 train_loss:2.4006 train_time:1378738ms step_avg:399.98ms step:3458/6250 train_loss:2.4566 train_time:1379153ms step_avg:399.99ms step:3459/6250 train_loss:2.4874 train_time:1379566ms step_avg:399.99ms step:3460/6250 train_loss:2.4043 train_time:1379982ms step_avg:399.99ms step:3461/6250 train_loss:2.4137 train_time:1380396ms step_avg:400.00ms step:3462/6250 train_loss:2.3313 train_time:1380806ms step_avg:400.00ms step:3463/6250 train_loss:2.4135 train_time:1381217ms step_avg:400.00ms step:3464/6250 train_loss:2.4419 train_time:1381632ms step_avg:400.01ms step:3465/6250 train_loss:2.4241 train_time:1382043ms step_avg:400.01ms step:3466/6250 train_loss:2.3557 train_time:1382457ms step_avg:400.02ms step:3467/6250 train_loss:2.3851 train_time:1382868ms step_avg:400.02ms step:3468/6250 train_loss:2.4150 train_time:1383270ms step_avg:400.02ms step:3469/6250 train_loss:2.4793 train_time:1383660ms step_avg:400.02ms step:3470/6250 train_loss:2.4135 train_time:1384054ms step_avg:400.02ms step:3471/6250 train_loss:2.4486 train_time:1384445ms step_avg:400.01ms step:3472/6250 train_loss:2.4352 train_time:1384835ms step_avg:400.01ms step:3473/6250 train_loss:2.4813 train_time:1385225ms step_avg:400.01ms step:3474/6250 train_loss:2.4511 train_time:1385614ms step_avg:400.00ms step:3475/6250 train_loss:2.4743 train_time:1386005ms step_avg:400.00ms step:3476/6250 train_loss:2.5079 train_time:1386395ms step_avg:400.00ms step:3477/6250 train_loss:2.4255 train_time:1386782ms step_avg:399.99ms step:3478/6250 train_loss:2.5352 train_time:1387171ms step_avg:399.99ms step:3479/6250 train_loss:2.4316 train_time:1387558ms step_avg:399.99ms step:3480/6250 train_loss:2.5164 train_time:1387995ms step_avg:400.00ms step:3481/6250 train_loss:2.5394 train_time:1388440ms step_avg:400.01ms step:3482/6250 train_loss:2.4756 train_time:1388849ms step_avg:400.01ms step:3483/6250 train_loss:2.4466 train_time:1389260ms step_avg:400.02ms step:3484/6250 train_loss:2.4766 train_time:1389670ms step_avg:400.02ms step:3485/6250 train_loss:2.5489 train_time:1390081ms step_avg:400.02ms step:3486/6250 train_loss:2.5064 train_time:1390489ms step_avg:400.03ms step:3487/6250 train_loss:2.4569 train_time:1390899ms step_avg:400.03ms step:3488/6250 train_loss:2.5309 train_time:1391311ms step_avg:400.03ms step:3489/6250 train_loss:2.5015 train_time:1391717ms step_avg:400.03ms step:3490/6250 train_loss:2.5150 train_time:1392126ms step_avg:400.04ms step:3491/6250 train_loss:2.5008 train_time:1392543ms step_avg:400.04ms step:3492/6250 train_loss:2.5203 train_time:1392950ms step_avg:400.04ms step:3493/6250 train_loss:2.4340 train_time:1393360ms step_avg:400.05ms step:3494/6250 train_loss:2.3996 train_time:1393772ms step_avg:400.05ms step:3495/6250 train_loss:2.4133 train_time:1394181ms step_avg:400.05ms step:3496/6250 train_loss:2.4802 train_time:1394591ms step_avg:400.05ms step:3497/6250 train_loss:2.4892 train_time:1395003ms step_avg:400.06ms step:3498/6250 train_loss:2.3651 train_time:1395416ms step_avg:400.06ms step:3499/6250 train_loss:2.4774 train_time:1395827ms step_avg:400.07ms step:3500/6250 train_loss:2.3737 train_time:1396241ms step_avg:400.07ms step:3501/6250 train_loss:2.5013 train_time:1396655ms step_avg:400.07ms step:3502/6250 train_loss:2.3815 train_time:1397064ms step_avg:400.08ms step:3503/6250 train_loss:2.4541 train_time:1397475ms step_avg:400.08ms step:3504/6250 train_loss:2.3610 train_time:1397885ms step_avg:400.08ms step:3505/6250 train_loss:2.3313 train_time:1398298ms step_avg:400.09ms step:3506/6250 train_loss:2.4166 train_time:1398707ms step_avg:400.09ms step:3507/6250 train_loss:2.4120 train_time:1399118ms step_avg:400.09ms step:3508/6250 train_loss:2.4900 train_time:1399527ms step_avg:400.09ms step:3509/6250 train_loss:2.4126 train_time:1399938ms step_avg:400.10ms step:3510/6250 train_loss:2.4213 train_time:1400347ms step_avg:400.10ms step:3511/6250 train_loss:2.4096 train_time:1400755ms step_avg:400.10ms step:3512/6250 train_loss:2.4209 train_time:1401170ms step_avg:400.11ms step:3513/6250 train_loss:2.4976 train_time:1401580ms step_avg:400.11ms step:3514/6250 train_loss:2.4902 train_time:1401991ms step_avg:400.11ms step:3515/6250 train_loss:2.4730 train_time:1402400ms step_avg:400.11ms step:3516/6250 train_loss:2.4256 train_time:1402814ms step_avg:400.12ms step:3517/6250 train_loss:2.4071 train_time:1403230ms step_avg:400.12ms step:3518/6250 train_loss:2.3734 train_time:1403642ms step_avg:400.13ms step:3519/6250 train_loss:2.5075 train_time:1404045ms step_avg:400.13ms step:3520/6250 train_loss:2.4517 train_time:1404458ms step_avg:400.13ms step:3521/6250 train_loss:2.4252 train_time:1404872ms step_avg:400.13ms step:3522/6250 train_loss:2.4575 train_time:1405287ms step_avg:400.14ms step:3523/6250 train_loss:2.3733 train_time:1405700ms step_avg:400.14ms step:3524/6250 train_loss:2.4692 train_time:1406109ms step_avg:400.14ms step:3525/6250 train_loss:2.5133 train_time:1406524ms step_avg:400.15ms step:3526/6250 train_loss:2.4847 train_time:1406934ms step_avg:400.15ms step:3527/6250 train_loss:2.4324 train_time:1407331ms step_avg:400.15ms step:3528/6250 train_loss:2.4861 train_time:1407746ms step_avg:400.16ms step:3529/6250 train_loss:2.4522 train_time:1408149ms step_avg:400.16ms step:3530/6250 train_loss:2.4569 train_time:1408559ms step_avg:400.16ms step:3531/6250 train_loss:2.3896 train_time:1408959ms step_avg:400.16ms step:3532/6250 train_loss:2.4895 train_time:1409373ms step_avg:400.16ms step:3533/6250 train_loss:2.5792 train_time:1409784ms step_avg:400.17ms step:3534/6250 train_loss:2.5114 train_time:1410189ms step_avg:400.17ms step:3535/6250 train_loss:2.3707 train_time:1410598ms step_avg:400.17ms step:3536/6250 train_loss:2.4664 train_time:1411001ms step_avg:400.17ms step:3537/6250 train_loss:2.5172 train_time:1411412ms step_avg:400.17ms step:3538/6250 train_loss:2.5223 train_time:1411806ms step_avg:400.17ms step:3539/6250 train_loss:2.4725 train_time:1412201ms step_avg:400.17ms step:3540/6250 train_loss:2.4888 train_time:1412611ms step_avg:400.17ms step:3541/6250 train_loss:2.4806 train_time:1413002ms step_avg:400.17ms step:3542/6250 train_loss:2.5709 train_time:1413400ms step_avg:400.17ms step:3543/6250 train_loss:2.4946 train_time:1413779ms step_avg:400.16ms step:3544/6250 train_loss:2.3903 train_time:1414177ms step_avg:400.16ms step:3545/6250 train_loss:2.4639 train_time:1414562ms step_avg:400.16ms step:3546/6250 train_loss:2.4325 train_time:1414951ms step_avg:400.16ms step:3547/6250 train_loss:2.5154 train_time:1415345ms step_avg:400.15ms step:3548/6250 train_loss:2.4336 train_time:1415738ms step_avg:400.15ms step:3549/6250 train_loss:2.4956 train_time:1416128ms step_avg:400.15ms step:3550/6250 train_loss:2.4740 train_time:1416524ms step_avg:400.15ms step:3551/6250 train_loss:2.3302 train_time:1416904ms step_avg:400.14ms step:3552/6250 train_loss:2.4353 train_time:1417293ms step_avg:400.14ms step:3553/6250 train_loss:2.4292 train_time:1417678ms step_avg:400.13ms step:3554/6250 train_loss:2.5083 train_time:1418058ms step_avg:400.13ms step:3555/6250 train_loss:2.3685 train_time:1418440ms step_avg:400.12ms step:3556/6250 train_loss:2.4043 train_time:1418838ms step_avg:400.12ms step:3557/6250 train_loss:2.4415 train_time:1419224ms step_avg:400.12ms step:3558/6250 train_loss:2.4395 train_time:1419613ms step_avg:400.12ms step:3559/6250 train_loss:2.4128 train_time:1420002ms step_avg:400.11ms step:3560/6250 train_loss:2.4397 train_time:1420387ms step_avg:400.11ms step:3561/6250 train_loss:2.4841 train_time:1420768ms step_avg:400.10ms step:3562/6250 train_loss:2.4687 train_time:1421153ms step_avg:400.10ms step:3563/6250 train_loss:2.3511 train_time:1421550ms step_avg:400.10ms step:3564/6250 train_loss:2.4018 train_time:1421955ms step_avg:400.10ms step:3565/6250 train_loss:2.4484 train_time:1422354ms step_avg:400.10ms step:3566/6250 train_loss:2.4592 train_time:1422735ms step_avg:400.09ms step:3567/6250 train_loss:2.4909 train_time:1423114ms step_avg:400.09ms step:3568/6250 train_loss:2.5227 train_time:1423493ms step_avg:400.08ms step:3569/6250 train_loss:2.5278 train_time:1423874ms step_avg:400.08ms step:3570/6250 train_loss:2.4176 train_time:1424257ms step_avg:400.07ms step:3571/6250 train_loss:2.4628 train_time:1424638ms step_avg:400.07ms step:3572/6250 train_loss:2.5206 train_time:1425019ms step_avg:400.06ms step:3573/6250 train_loss:2.4652 train_time:1425400ms step_avg:400.06ms step:3574/6250 train_loss:2.3608 train_time:1425779ms step_avg:400.05ms step:3575/6250 train_loss:2.4663 train_time:1426162ms step_avg:400.05ms step:3576/6250 train_loss:2.4540 train_time:1426546ms step_avg:400.04ms step:3577/6250 train_loss:2.4670 train_time:1426928ms step_avg:400.04ms step:3578/6250 train_loss:2.5106 train_time:1427310ms step_avg:400.03ms step:3579/6250 train_loss:2.4444 train_time:1427691ms step_avg:400.03ms step:3580/6250 train_loss:2.4321 train_time:1428072ms step_avg:400.02ms step:3581/6250 train_loss:2.4971 train_time:1428452ms step_avg:400.01ms step:3582/6250 train_loss:2.4468 train_time:1428834ms step_avg:400.01ms step:3583/6250 train_loss:2.5108 train_time:1429215ms step_avg:400.00ms step:3584/6250 train_loss:2.4643 train_time:1429595ms step_avg:400.00ms step:3585/6250 train_loss:2.4697 train_time:1429982ms step_avg:399.99ms step:3586/6250 train_loss:2.4746 train_time:1430372ms step_avg:399.99ms step:3587/6250 train_loss:2.4927 train_time:1430761ms step_avg:399.99ms step:3588/6250 train_loss:2.4558 train_time:1431154ms step_avg:399.99ms step:3589/6250 train_loss:2.4424 train_time:1431550ms step_avg:399.99ms step:3590/6250 train_loss:2.4056 train_time:1431944ms step_avg:399.98ms step:3591/6250 train_loss:2.5399 train_time:1432338ms step_avg:399.98ms step:3592/6250 train_loss:2.3875 train_time:1432735ms step_avg:399.98ms step:3593/6250 train_loss:2.5412 train_time:1433129ms step_avg:399.98ms step:3594/6250 train_loss:2.4607 train_time:1433522ms step_avg:399.98ms step:3595/6250 train_loss:2.4839 train_time:1433914ms step_avg:399.98ms step:3596/6250 train_loss:2.4337 train_time:1434310ms step_avg:399.97ms step:3597/6250 train_loss:2.5506 train_time:1434700ms step_avg:399.97ms step:3598/6250 train_loss:2.5982 train_time:1435091ms step_avg:399.97ms step:3599/6250 train_loss:2.4104 train_time:1435485ms step_avg:399.97ms step:3600/6250 train_loss:2.5007 train_time:1435875ms step_avg:399.97ms step:3601/6250 train_loss:2.3912 train_time:1436267ms step_avg:399.96ms step:3602/6250 train_loss:2.4185 train_time:1436664ms step_avg:399.96ms step:3603/6250 train_loss:2.4431 train_time:1437057ms step_avg:399.96ms step:3604/6250 train_loss:2.5054 train_time:1437446ms step_avg:399.96ms step:3605/6250 train_loss:2.4551 train_time:1437839ms step_avg:399.96ms step:3606/6250 train_loss:2.5016 train_time:1438230ms step_avg:399.95ms step:3607/6250 train_loss:2.5293 train_time:1438622ms step_avg:399.95ms step:3608/6250 train_loss:2.4245 train_time:1439014ms step_avg:399.95ms step:3609/6250 train_loss:2.4128 train_time:1439405ms step_avg:399.95ms step:3610/6250 train_loss:2.4802 train_time:1439794ms step_avg:399.94ms step:3611/6250 train_loss:2.4258 train_time:1440183ms step_avg:399.94ms step:3612/6250 train_loss:2.4371 train_time:1440570ms step_avg:399.94ms step:3613/6250 train_loss:2.3868 train_time:1440966ms step_avg:399.94ms step:3614/6250 train_loss:2.3911 train_time:1441361ms step_avg:399.93ms step:3615/6250 train_loss:2.4102 train_time:1441756ms step_avg:399.93ms step:3616/6250 train_loss:2.4471 train_time:1442146ms step_avg:399.93ms step:3617/6250 train_loss:2.4409 train_time:1442535ms step_avg:399.93ms step:3618/6250 train_loss:2.3909 train_time:1442924ms step_avg:399.92ms step:3619/6250 train_loss:2.4273 train_time:1443312ms step_avg:399.92ms step:3620/6250 train_loss:2.3995 train_time:1443701ms step_avg:399.92ms step:3621/6250 train_loss:2.3783 train_time:1444093ms step_avg:399.92ms step:3622/6250 train_loss:2.4944 train_time:1444483ms step_avg:399.91ms step:3623/6250 train_loss:2.4425 train_time:1444872ms step_avg:399.91ms step:3624/6250 train_loss:2.4245 train_time:1445263ms step_avg:399.91ms step:3625/6250 train_loss:2.4732 train_time:1445652ms step_avg:399.90ms step:3626/6250 train_loss:2.5666 train_time:1446044ms step_avg:399.90ms step:3627/6250 train_loss:2.5330 train_time:1446436ms step_avg:399.90ms step:3628/6250 train_loss:2.4302 train_time:1446825ms step_avg:399.90ms step:3629/6250 train_loss:2.4829 train_time:1447215ms step_avg:399.89ms step:3630/6250 train_loss:2.5219 train_time:1447602ms step_avg:399.89ms step:3631/6250 train_loss:2.4830 train_time:1447992ms step_avg:399.89ms step:3632/6250 train_loss:2.3761 train_time:1448378ms step_avg:399.88ms step:3633/6250 train_loss:2.4471 train_time:1448762ms step_avg:399.88ms step:3634/6250 train_loss:2.4196 train_time:1449145ms step_avg:399.87ms step:3635/6250 train_loss:2.3435 train_time:1449534ms step_avg:399.87ms step:3636/6250 train_loss:2.4407 train_time:1449915ms step_avg:399.87ms step:3637/6250 train_loss:2.5002 train_time:1450295ms step_avg:399.86ms step:3638/6250 train_loss:2.4181 train_time:1450670ms step_avg:399.85ms step:3639/6250 train_loss:2.5647 train_time:1451052ms step_avg:399.85ms step:3640/6250 train_loss:2.3957 train_time:1451436ms step_avg:399.84ms step:3641/6250 train_loss:2.5101 train_time:1451819ms step_avg:399.84ms step:3642/6250 train_loss:2.4295 train_time:1452205ms step_avg:399.84ms step:3643/6250 train_loss:2.4755 train_time:1452592ms step_avg:399.83ms step:3644/6250 train_loss:2.4128 train_time:1452980ms step_avg:399.83ms step:3645/6250 train_loss:2.4629 train_time:1453373ms step_avg:399.83ms step:3646/6250 train_loss:2.4502 train_time:1453766ms step_avg:399.83ms step:3647/6250 train_loss:2.4546 train_time:1454159ms step_avg:399.82ms step:3648/6250 train_loss:2.4716 train_time:1454562ms step_avg:399.82ms step:3649/6250 train_loss:2.4712 train_time:1454954ms step_avg:399.82ms step:3650/6250 train_loss:2.4941 train_time:1455344ms step_avg:399.82ms step:3651/6250 train_loss:2.4828 train_time:1455737ms step_avg:399.82ms step:3652/6250 train_loss:2.4766 train_time:1456129ms step_avg:399.82ms step:3653/6250 train_loss:2.3871 train_time:1456517ms step_avg:399.81ms step:3654/6250 train_loss:2.5413 train_time:1456895ms step_avg:399.81ms step:3655/6250 train_loss:2.4401 train_time:1457293ms step_avg:399.81ms step:3656/6250 train_loss:2.5229 train_time:1457679ms step_avg:399.80ms step:3657/6250 train_loss:2.4641 train_time:1458061ms step_avg:399.80ms step:3658/6250 train_loss:2.4725 train_time:1458449ms step_avg:399.79ms step:3659/6250 train_loss:2.4232 train_time:1458838ms step_avg:399.79ms step:3660/6250 train_loss:2.4452 train_time:1459234ms step_avg:399.79ms step:3661/6250 train_loss:2.3800 train_time:1459622ms step_avg:399.79ms step:3662/6250 train_loss:2.4968 train_time:1460028ms step_avg:399.79ms step:3663/6250 train_loss:2.5020 train_time:1460427ms step_avg:399.79ms step:3664/6250 train_loss:2.3625 train_time:1460821ms step_avg:399.79ms step:3665/6250 train_loss:2.4185 train_time:1461234ms step_avg:399.79ms step:3666/6250 train_loss:2.3723 train_time:1461632ms step_avg:399.79ms step:3667/6250 train_loss:2.4462 train_time:1462011ms step_avg:399.78ms step:3668/6250 train_loss:2.6025 train_time:1462390ms step_avg:399.78ms step:3669/6250 train_loss:2.4684 train_time:1462769ms step_avg:399.77ms step:3670/6250 train_loss:2.4897 train_time:1463150ms step_avg:399.77ms step:3671/6250 train_loss:2.4334 train_time:1463531ms step_avg:399.76ms step:3672/6250 train_loss:2.4651 train_time:1463911ms step_avg:399.76ms step:3673/6250 train_loss:2.5043 train_time:1464300ms step_avg:399.75ms step:3674/6250 train_loss:2.4122 train_time:1464689ms step_avg:399.75ms step:3675/6250 train_loss:2.5113 train_time:1465074ms step_avg:399.75ms step:3676/6250 train_loss:2.4676 train_time:1465466ms step_avg:399.75ms step:3677/6250 train_loss:2.4218 train_time:1465854ms step_avg:399.74ms step:3678/6250 train_loss:2.4306 train_time:1466243ms step_avg:399.74ms step:3679/6250 train_loss:2.4163 train_time:1466630ms step_avg:399.74ms step:3680/6250 train_loss:2.3852 train_time:1467018ms step_avg:399.73ms step:3681/6250 train_loss:2.5412 train_time:1467408ms step_avg:399.73ms step:3682/6250 train_loss:2.4246 train_time:1467796ms step_avg:399.73ms step:3683/6250 train_loss:2.4680 train_time:1468186ms step_avg:399.72ms step:3684/6250 train_loss:2.4201 train_time:1468576ms step_avg:399.72ms step:3685/6250 train_loss:2.4929 train_time:1468969ms step_avg:399.72ms step:3686/6250 train_loss:2.3835 train_time:1469359ms step_avg:399.72ms step:3687/6250 train_loss:2.3581 train_time:1469749ms step_avg:399.71ms step:3688/6250 train_loss:2.3419 train_time:1470138ms step_avg:399.71ms step:3689/6250 train_loss:2.5185 train_time:1470530ms step_avg:399.71ms step:3690/6250 train_loss:2.4537 train_time:1470918ms step_avg:399.71ms step:3691/6250 train_loss:2.2869 train_time:1471307ms step_avg:399.70ms step:3692/6250 train_loss:2.4680 train_time:1471699ms step_avg:399.70ms step:3693/6250 train_loss:2.4090 train_time:1472090ms step_avg:399.70ms step:3694/6250 train_loss:2.4694 train_time:1472479ms step_avg:399.70ms step:3695/6250 train_loss:2.4768 train_time:1472872ms step_avg:399.69ms step:3696/6250 train_loss:2.3967 train_time:1473260ms step_avg:399.69ms step:3697/6250 train_loss:2.4730 train_time:1473651ms step_avg:399.69ms step:3698/6250 train_loss:2.4543 train_time:1474040ms step_avg:399.69ms step:3699/6250 train_loss:2.4221 train_time:1474429ms step_avg:399.68ms step:3700/6250 train_loss:2.3891 train_time:1474816ms step_avg:399.68ms step:3701/6250 train_loss:2.5265 train_time:1475203ms step_avg:399.68ms step:3702/6250 train_loss:2.5052 train_time:1475590ms step_avg:399.67ms step:3703/6250 train_loss:2.4139 train_time:1475975ms step_avg:399.67ms step:3704/6250 train_loss:2.3689 train_time:1476363ms step_avg:399.67ms step:3705/6250 train_loss:2.4078 train_time:1476752ms step_avg:399.66ms step:3706/6250 train_loss:2.4198 train_time:1477140ms step_avg:399.66ms step:3707/6250 train_loss:2.4396 train_time:1477533ms step_avg:399.66ms step:3708/6250 train_loss:2.4748 train_time:1477921ms step_avg:399.65ms step:3709/6250 train_loss:2.4857 train_time:1478310ms step_avg:399.65ms step:3710/6250 train_loss:2.3935 train_time:1478700ms step_avg:399.65ms step:3711/6250 train_loss:2.4606 train_time:1479094ms step_avg:399.65ms step:3712/6250 train_loss:2.4908 train_time:1479487ms step_avg:399.65ms step:3713/6250 train_loss:2.5485 train_time:1479878ms step_avg:399.64ms step:3714/6250 train_loss:2.4313 train_time:1480272ms step_avg:399.64ms step:3715/6250 train_loss:2.4326 train_time:1480665ms step_avg:399.64ms step:3716/6250 train_loss:2.4152 train_time:1481059ms step_avg:399.64ms step:3717/6250 train_loss:2.4141 train_time:1481449ms step_avg:399.64ms step:3718/6250 train_loss:2.4548 train_time:1481840ms step_avg:399.63ms step:3719/6250 train_loss:2.4816 train_time:1482236ms step_avg:399.63ms step:3720/6250 train_loss:2.3770 train_time:1482629ms step_avg:399.63ms step:3721/6250 train_loss:2.3924 train_time:1483022ms step_avg:399.63ms step:3722/6250 train_loss:2.3364 train_time:1483417ms step_avg:399.63ms step:3723/6250 train_loss:2.4981 train_time:1483807ms step_avg:399.62ms step:3724/6250 train_loss:2.4987 train_time:1484268ms step_avg:399.64ms step:3725/6250 train_loss:2.4440 train_time:1484717ms step_avg:399.65ms step:3726/6250 train_loss:2.3757 train_time:1485115ms step_avg:399.65ms step:3727/6250 train_loss:2.3767 train_time:1485517ms step_avg:399.65ms step:3728/6250 train_loss:2.4861 train_time:1485921ms step_avg:399.66ms step:3729/6250 train_loss:2.3914 train_time:1486326ms step_avg:399.66ms step:3730/6250 train_loss:2.4145 train_time:1486730ms step_avg:399.66ms step:3731/6250 train_loss:2.4419 train_time:1487133ms step_avg:399.66ms step:3732/6250 train_loss:2.4481 train_time:1487538ms step_avg:399.66ms step:3733/6250 train_loss:2.3877 train_time:1487942ms step_avg:399.66ms step:3734/6250 train_loss:2.5349 train_time:1488345ms step_avg:399.66ms step:3735/6250 train_loss:2.4375 train_time:1488740ms step_avg:399.66ms step:3736/6250 train_loss:2.4310 train_time:1489136ms step_avg:399.66ms step:3737/6250 train_loss:2.3916 train_time:1489534ms step_avg:399.66ms step:3738/6250 train_loss:2.4295 train_time:1489930ms step_avg:399.66ms step:3739/6250 train_loss:2.4324 train_time:1490326ms step_avg:399.66ms step:3740/6250 train_loss:2.4760 train_time:1490721ms step_avg:399.66ms step:3741/6250 train_loss:2.4629 train_time:1491116ms step_avg:399.66ms step:3742/6250 train_loss:2.4914 train_time:1491508ms step_avg:399.65ms step:3743/6250 train_loss:2.4476 train_time:1491897ms step_avg:399.65ms step:3744/6250 train_loss:2.4971 train_time:1492289ms step_avg:399.65ms step:3745/6250 train_loss:2.5031 train_time:1492677ms step_avg:399.65ms step:3746/6250 train_loss:2.4008 train_time:1493068ms step_avg:399.64ms step:3747/6250 train_loss:2.4024 train_time:1493458ms step_avg:399.64ms step:3748/6250 train_loss:2.4463 train_time:1493849ms step_avg:399.64ms step:3749/6250 train_loss:2.4005 train_time:1494246ms step_avg:399.64ms step:3750/6250 train_loss:2.4839 train_time:1494636ms step_avg:399.64ms step:3751/6250 train_loss:2.4261 train_time:1495028ms step_avg:399.63ms step:3752/6250 train_loss:2.4425 train_time:1495422ms step_avg:399.63ms step:3753/6250 train_loss:2.5263 train_time:1495812ms step_avg:399.63ms step:3754/6250 train_loss:2.5205 train_time:1496214ms step_avg:399.63ms step:3755/6250 train_loss:2.4315 train_time:1496614ms step_avg:399.63ms step:3756/6250 train_loss:2.3824 train_time:1497017ms step_avg:399.63ms step:3757/6250 train_loss:2.3989 train_time:1497421ms step_avg:399.63ms step:3758/6250 train_loss:2.4455 train_time:1497836ms step_avg:399.64ms step:3759/6250 train_loss:2.4088 train_time:1498254ms step_avg:399.64ms step:3760/6250 train_loss:2.3921 train_time:1498662ms step_avg:399.64ms step:3761/6250 train_loss:2.3531 train_time:1499073ms step_avg:399.65ms step:3762/6250 train_loss:2.4596 train_time:1499481ms step_avg:399.65ms step:3763/6250 train_loss:2.5187 train_time:1499888ms step_avg:399.65ms step:3764/6250 train_loss:2.4216 train_time:1500296ms step_avg:399.65ms step:3765/6250 train_loss:2.4095 train_time:1500704ms step_avg:399.65ms step:3766/6250 train_loss:2.4701 train_time:1501116ms step_avg:399.66ms step:3767/6250 train_loss:2.4051 train_time:1501521ms step_avg:399.66ms step:3768/6250 train_loss:2.4037 train_time:1501927ms step_avg:399.66ms step:3769/6250 train_loss:2.4084 train_time:1502334ms step_avg:399.66ms step:3770/6250 train_loss:2.4919 train_time:1502742ms step_avg:399.67ms step:3771/6250 train_loss:2.5101 train_time:1503147ms step_avg:399.67ms step:3772/6250 train_loss:2.4418 train_time:1503553ms step_avg:399.67ms step:3773/6250 train_loss:2.4031 train_time:1503960ms step_avg:399.67ms step:3774/6250 train_loss:2.4227 train_time:1504367ms step_avg:399.67ms step:3775/6250 train_loss:2.4711 train_time:1504770ms step_avg:399.67ms step:3776/6250 train_loss:2.4677 train_time:1505171ms step_avg:399.67ms step:3777/6250 train_loss:2.4932 train_time:1505578ms step_avg:399.68ms step:3778/6250 train_loss:2.4346 train_time:1505989ms step_avg:399.68ms step:3779/6250 train_loss:2.4465 train_time:1506395ms step_avg:399.68ms step:3780/6250 train_loss:2.5172 train_time:1506800ms step_avg:399.68ms step:3781/6250 train_loss:2.4191 train_time:1507204ms step_avg:399.68ms step:3782/6250 train_loss:2.3772 train_time:1507607ms step_avg:399.68ms step:3783/6250 train_loss:2.4599 train_time:1508013ms step_avg:399.69ms step:3784/6250 train_loss:2.4437 train_time:1508421ms step_avg:399.69ms step:3785/6250 train_loss:2.4531 train_time:1508826ms step_avg:399.69ms step:3786/6250 train_loss:2.4477 train_time:1509233ms step_avg:399.69ms step:3787/6250 train_loss:2.4276 train_time:1509641ms step_avg:399.69ms step:3788/6250 train_loss:2.3875 train_time:1510055ms step_avg:399.70ms step:3789/6250 train_loss:2.4611 train_time:1510459ms step_avg:399.70ms step:3790/6250 train_loss:2.3703 train_time:1510865ms step_avg:399.70ms step:3791/6250 train_loss:2.4479 train_time:1511281ms step_avg:399.70ms step:3792/6250 train_loss:2.5080 train_time:1511687ms step_avg:399.71ms step:3793/6250 train_loss:2.4505 train_time:1512095ms step_avg:399.71ms step:3794/6250 train_loss:2.4088 train_time:1512500ms step_avg:399.71ms step:3795/6250 train_loss:2.4508 train_time:1512902ms step_avg:399.71ms step:3796/6250 train_loss:2.4621 train_time:1513308ms step_avg:399.71ms step:3797/6250 train_loss:2.4430 train_time:1513713ms step_avg:399.71ms step:3798/6250 train_loss:2.4277 train_time:1514117ms step_avg:399.71ms step:3799/6250 train_loss:2.5051 train_time:1514524ms step_avg:399.72ms step:3800/6250 train_loss:2.4874 train_time:1514930ms step_avg:399.72ms step:3801/6250 train_loss:2.3757 train_time:1515337ms step_avg:399.72ms step:3802/6250 train_loss:2.4769 train_time:1515740ms step_avg:399.72ms step:3803/6250 train_loss:2.5123 train_time:1516148ms step_avg:399.72ms step:3804/6250 train_loss:2.5090 train_time:1516556ms step_avg:399.72ms step:3805/6250 train_loss:2.4127 train_time:1516965ms step_avg:399.73ms step:3806/6250 train_loss:2.5488 train_time:1517370ms step_avg:399.73ms step:3807/6250 train_loss:2.4176 train_time:1517777ms step_avg:399.73ms step:3808/6250 train_loss:2.4924 train_time:1518186ms step_avg:399.73ms step:3809/6250 train_loss:2.5320 train_time:1518594ms step_avg:399.74ms step:3810/6250 train_loss:2.4818 train_time:1519001ms step_avg:399.74ms step:3811/6250 train_loss:2.4149 train_time:1519405ms step_avg:399.74ms step:3812/6250 train_loss:2.4259 train_time:1519811ms step_avg:399.74ms step:3813/6250 train_loss:2.4884 train_time:1520219ms step_avg:399.74ms step:3814/6250 train_loss:2.4696 train_time:1520621ms step_avg:399.74ms step:3815/6250 train_loss:2.4997 train_time:1521026ms step_avg:399.74ms step:3816/6250 train_loss:2.5179 train_time:1521432ms step_avg:399.75ms step:3817/6250 train_loss:2.4572 train_time:1521842ms step_avg:399.75ms step:3818/6250 train_loss:2.5490 train_time:1522249ms step_avg:399.75ms step:3819/6250 train_loss:2.4992 train_time:1522653ms step_avg:399.75ms step:3820/6250 train_loss:2.4292 train_time:1523056ms step_avg:399.75ms step:3821/6250 train_loss:2.4456 train_time:1523457ms step_avg:399.75ms step:3822/6250 train_loss:2.4437 train_time:1523857ms step_avg:399.75ms step:3823/6250 train_loss:2.4290 train_time:1524259ms step_avg:399.75ms step:3824/6250 train_loss:2.5249 train_time:1524663ms step_avg:399.75ms step:3825/6250 train_loss:2.3958 train_time:1525068ms step_avg:399.76ms step:3826/6250 train_loss:2.4838 train_time:1525473ms step_avg:399.76ms step:3827/6250 train_loss:2.4135 train_time:1525877ms step_avg:399.76ms step:3828/6250 train_loss:2.4462 train_time:1526283ms step_avg:399.76ms step:3829/6250 train_loss:2.4830 train_time:1526686ms step_avg:399.76ms step:3830/6250 train_loss:2.3827 train_time:1527088ms step_avg:399.76ms step:3831/6250 train_loss:2.4615 train_time:1527490ms step_avg:399.76ms step:3832/6250 train_loss:2.4503 train_time:1527890ms step_avg:399.76ms step:3833/6250 train_loss:2.4613 train_time:1528290ms step_avg:399.76ms step:3834/6250 train_loss:2.5171 train_time:1528693ms step_avg:399.76ms step:3835/6250 train_loss:2.3780 train_time:1529094ms step_avg:399.76ms step:3836/6250 train_loss:2.4127 train_time:1529498ms step_avg:399.76ms step:3837/6250 train_loss:2.4775 train_time:1529905ms step_avg:399.77ms step:3838/6250 train_loss:2.4759 train_time:1530314ms step_avg:399.77ms step:3839/6250 train_loss:2.4539 train_time:1530717ms step_avg:399.77ms step:3840/6250 train_loss:2.3592 train_time:1531117ms step_avg:399.77ms step:3841/6250 train_loss:2.5217 train_time:1531509ms step_avg:399.77ms step:3842/6250 train_loss:2.5007 train_time:1531902ms step_avg:399.77ms step:3843/6250 train_loss:2.4183 train_time:1532294ms step_avg:399.76ms step:3844/6250 train_loss:2.4891 train_time:1532688ms step_avg:399.76ms step:3845/6250 train_loss:2.4666 train_time:1533083ms step_avg:399.76ms step:3846/6250 train_loss:2.4974 train_time:1533476ms step_avg:399.76ms step:3847/6250 train_loss:2.4144 train_time:1533867ms step_avg:399.76ms step:3848/6250 train_loss:2.4137 train_time:1534255ms step_avg:399.75ms step:3849/6250 train_loss:2.5070 train_time:1534670ms step_avg:399.76ms step:3850/6250 train_loss:2.4790 train_time:1535093ms step_avg:399.76ms step:3851/6250 train_loss:2.5204 train_time:1535485ms step_avg:399.76ms step:3852/6250 train_loss:2.5089 train_time:1535872ms step_avg:399.76ms step:3853/6250 train_loss:2.4918 train_time:1536264ms step_avg:399.76ms step:3854/6250 train_loss:2.4728 train_time:1536655ms step_avg:399.75ms step:3855/6250 train_loss:2.4319 train_time:1537046ms step_avg:399.75ms step:3856/6250 train_loss:2.4844 train_time:1537438ms step_avg:399.75ms step:3857/6250 train_loss:2.5225 train_time:1537828ms step_avg:399.75ms step:3858/6250 train_loss:2.5374 train_time:1538223ms step_avg:399.75ms step:3859/6250 train_loss:2.5051 train_time:1538614ms step_avg:399.74ms step:3860/6250 train_loss:2.5398 train_time:1539005ms step_avg:399.74ms step:3861/6250 train_loss:2.4448 train_time:1539396ms step_avg:399.74ms step:3862/6250 train_loss:2.4916 train_time:1539790ms step_avg:399.74ms step:3863/6250 train_loss:2.4522 train_time:1540183ms step_avg:399.74ms step:3864/6250 train_loss:2.3584 train_time:1540576ms step_avg:399.73ms step:3865/6250 train_loss:2.5228 train_time:1540968ms step_avg:399.73ms step:3866/6250 train_loss:2.3901 train_time:1541362ms step_avg:399.73ms step:3867/6250 train_loss:2.4744 train_time:1541754ms step_avg:399.73ms step:3868/6250 train_loss:2.5112 train_time:1542144ms step_avg:399.73ms step:3869/6250 train_loss:2.4740 train_time:1542535ms step_avg:399.72ms step:3870/6250 train_loss:2.4279 train_time:1542916ms step_avg:399.72ms step:3871/6250 train_loss:2.3833 train_time:1543300ms step_avg:399.72ms step:3872/6250 train_loss:2.4644 train_time:1543679ms step_avg:399.71ms step:3873/6250 train_loss:2.5031 train_time:1544059ms step_avg:399.70ms step:3874/6250 train_loss:2.4314 train_time:1544444ms step_avg:399.70ms step:3875/6250 train_loss:2.4293 train_time:1544827ms step_avg:399.70ms step:3876/6250 train_loss:2.5038 train_time:1545219ms step_avg:399.69ms step:3877/6250 train_loss:2.4329 train_time:1545609ms step_avg:399.69ms step:3878/6250 train_loss:2.5511 train_time:1546002ms step_avg:399.69ms step:3879/6250 train_loss:2.4228 train_time:1546402ms step_avg:399.69ms step:3880/6250 train_loss:2.5023 train_time:1546795ms step_avg:399.69ms step:3881/6250 train_loss:2.4412 train_time:1547183ms step_avg:399.69ms step:3882/6250 train_loss:2.4646 train_time:1547598ms step_avg:399.69ms step:3883/6250 train_loss:2.4811 train_time:1548002ms step_avg:399.69ms step:3884/6250 train_loss:2.4045 train_time:1548389ms step_avg:399.69ms step:3885/6250 train_loss:2.4497 train_time:1548768ms step_avg:399.68ms step:3886/6250 train_loss:2.4370 train_time:1549149ms step_avg:399.68ms step:3887/6250 train_loss:2.4175 train_time:1549530ms step_avg:399.67ms step:3888/6250 train_loss:2.4817 train_time:1549914ms step_avg:399.67ms step:3889/6250 train_loss:2.5036 train_time:1550299ms step_avg:399.66ms step:3890/6250 train_loss:2.4706 train_time:1550683ms step_avg:399.66ms step:3891/6250 train_loss:2.3805 train_time:1551073ms step_avg:399.66ms step:3892/6250 train_loss:2.3883 train_time:1551465ms step_avg:399.66ms step:3893/6250 train_loss:2.4134 train_time:1551860ms step_avg:399.65ms step:3894/6250 train_loss:2.5533 train_time:1552253ms step_avg:399.65ms step:3895/6250 train_loss:2.4148 train_time:1552647ms step_avg:399.65ms step:3896/6250 train_loss:2.5731 train_time:1553037ms step_avg:399.65ms step:3897/6250 train_loss:2.4235 train_time:1553429ms step_avg:399.65ms step:3898/6250 train_loss:2.3736 train_time:1553822ms step_avg:399.65ms step:3899/6250 train_loss:2.4719 train_time:1554217ms step_avg:399.64ms step:3900/6250 train_loss:2.4761 train_time:1554609ms step_avg:399.64ms step:3901/6250 train_loss:2.3977 train_time:1555003ms step_avg:399.64ms step:3902/6250 train_loss:2.5071 train_time:1555398ms step_avg:399.64ms step:3903/6250 train_loss:2.3636 train_time:1555792ms step_avg:399.64ms step:3904/6250 train_loss:2.3829 train_time:1556184ms step_avg:399.64ms step:3905/6250 train_loss:2.3828 train_time:1556576ms step_avg:399.63ms step:3906/6250 train_loss:2.4886 train_time:1556968ms step_avg:399.63ms step:3907/6250 train_loss:2.5096 train_time:1557359ms step_avg:399.63ms step:3908/6250 train_loss:2.4903 train_time:1557753ms step_avg:399.63ms step:3909/6250 train_loss:2.4174 train_time:1558145ms step_avg:399.63ms step:3910/6250 train_loss:2.3914 train_time:1558536ms step_avg:399.62ms step:3911/6250 train_loss:2.3802 train_time:1558925ms step_avg:399.62ms step:3912/6250 train_loss:2.4421 train_time:1559318ms step_avg:399.62ms step:3913/6250 train_loss:2.5260 train_time:1559709ms step_avg:399.62ms step:3914/6250 train_loss:2.4451 train_time:1560101ms step_avg:399.62ms step:3915/6250 train_loss:2.4888 train_time:1560494ms step_avg:399.61ms step:3916/6250 train_loss:2.4418 train_time:1560888ms step_avg:399.61ms step:3917/6250 train_loss:2.5025 train_time:1561282ms step_avg:399.61ms step:3918/6250 train_loss:2.4074 train_time:1561673ms step_avg:399.61ms step:3919/6250 train_loss:2.3552 train_time:1562067ms step_avg:399.61ms step:3920/6250 train_loss:2.4576 train_time:1562461ms step_avg:399.61ms step:3921/6250 train_loss:2.4455 train_time:1562852ms step_avg:399.60ms step:3922/6250 train_loss:2.3929 train_time:1563247ms step_avg:399.60ms step:3923/6250 train_loss:2.4129 train_time:1563640ms step_avg:399.60ms step:3924/6250 train_loss:2.4036 train_time:1564034ms step_avg:399.60ms step:3925/6250 train_loss:2.4527 train_time:1564427ms step_avg:399.60ms step:3926/6250 train_loss:2.3791 train_time:1564820ms step_avg:399.60ms step:3927/6250 train_loss:2.5006 train_time:1565244ms step_avg:399.60ms step:3928/6250 train_loss:2.4155 train_time:1565684ms step_avg:399.61ms step:3929/6250 train_loss:2.3918 train_time:1566130ms step_avg:399.62ms step:3930/6250 train_loss:2.5889 train_time:1566574ms step_avg:399.64ms step:3931/6250 train_loss:2.4027 train_time:1567022ms step_avg:399.65ms step:3932/6250 train_loss:2.4958 train_time:1567464ms step_avg:399.66ms step:3933/6250 train_loss:2.5129 train_time:1567906ms step_avg:399.67ms step:3934/6250 train_loss:2.3741 train_time:1568354ms step_avg:399.68ms step:3935/6250 train_loss:2.5064 train_time:1568801ms step_avg:399.69ms step:3936/6250 train_loss:2.4629 train_time:1569246ms step_avg:399.71ms step:3937/6250 train_loss:2.4906 train_time:1569691ms step_avg:399.72ms step:3938/6250 train_loss:2.4136 train_time:1570139ms step_avg:399.73ms step:3939/6250 train_loss:2.4987 train_time:1570573ms step_avg:399.74ms step:3940/6250 train_loss:2.5139 train_time:1570987ms step_avg:399.74ms step:3941/6250 train_loss:2.4668 train_time:1571369ms step_avg:399.74ms step:3942/6250 train_loss:2.4733 train_time:1571751ms step_avg:399.73ms step:3943/6250 train_loss:2.4546 train_time:1572132ms step_avg:399.73ms step:3944/6250 train_loss:2.4156 train_time:1572512ms step_avg:399.72ms step:3945/6250 train_loss:2.4372 train_time:1572895ms step_avg:399.72ms step:3946/6250 train_loss:2.4068 train_time:1573302ms step_avg:399.72ms step:3947/6250 train_loss:2.4115 train_time:1573715ms step_avg:399.72ms step:3948/6250 train_loss:2.4612 train_time:1574137ms step_avg:399.73ms step:3949/6250 train_loss:2.3657 train_time:1574557ms step_avg:399.74ms step:3950/6250 train_loss:2.3929 train_time:1574978ms step_avg:399.74ms step:3951/6250 train_loss:2.4185 train_time:1575405ms step_avg:399.75ms step:3952/6250 train_loss:2.4341 train_time:1575822ms step_avg:399.75ms step:3953/6250 train_loss:2.4084 train_time:1576243ms step_avg:399.76ms step:3954/6250 train_loss:2.4312 train_time:1576672ms step_avg:399.76ms step:3955/6250 train_loss:2.3682 train_time:1577085ms step_avg:399.77ms step:3956/6250 train_loss:2.4324 train_time:1577509ms step_avg:399.77ms step:3957/6250 train_loss:2.4165 train_time:1577926ms step_avg:399.78ms step:3958/6250 train_loss:2.4622 train_time:1578344ms step_avg:399.78ms step:3959/6250 train_loss:2.3481 train_time:1578765ms step_avg:399.79ms step:3960/6250 train_loss:2.4798 train_time:1579181ms step_avg:399.79ms step:3961/6250 train_loss:2.4490 train_time:1579597ms step_avg:399.80ms step:3962/6250 train_loss:2.4634 train_time:1580010ms step_avg:399.80ms step:3963/6250 train_loss:2.5106 train_time:1580419ms step_avg:399.80ms step:3964/6250 train_loss:2.3417 train_time:1580829ms step_avg:399.80ms step:3965/6250 train_loss:2.4392 train_time:1581238ms step_avg:399.81ms step:3966/6250 train_loss:2.4458 train_time:1581650ms step_avg:399.81ms step:3967/6250 train_loss:2.4175 train_time:1582058ms step_avg:399.81ms step:3968/6250 train_loss:2.3811 train_time:1582471ms step_avg:399.82ms step:3969/6250 train_loss:2.3796 train_time:1582883ms step_avg:399.82ms step:3970/6250 train_loss:2.3892 train_time:1583295ms step_avg:399.82ms step:3971/6250 train_loss:2.5256 train_time:1583705ms step_avg:399.82ms step:3972/6250 train_loss:2.4310 train_time:1584112ms step_avg:399.83ms step:3973/6250 train_loss:2.2829 train_time:1584515ms step_avg:399.83ms step:3974/6250 train_loss:2.4567 train_time:1584926ms step_avg:399.83ms step:3975/6250 train_loss:2.5667 train_time:1585334ms step_avg:399.83ms step:3976/6250 train_loss:2.4684 train_time:1585740ms step_avg:399.83ms step:3977/6250 train_loss:2.4855 train_time:1586157ms step_avg:399.84ms step:3978/6250 train_loss:2.3837 train_time:1586571ms step_avg:399.84ms step:3979/6250 train_loss:2.4470 train_time:1586975ms step_avg:399.84ms step:3980/6250 train_loss:2.5369 train_time:1587389ms step_avg:399.85ms step:3981/6250 train_loss:2.4833 train_time:1587807ms step_avg:399.85ms step:3982/6250 train_loss:2.4482 train_time:1588248ms step_avg:399.86ms step:3983/6250 train_loss:2.4937 train_time:1588677ms step_avg:399.87ms step:3984/6250 train_loss:2.5016 train_time:1589085ms step_avg:399.87ms step:3985/6250 train_loss:2.4828 train_time:1589490ms step_avg:399.87ms step:3986/6250 train_loss:2.3517 train_time:1589920ms step_avg:399.88ms step:3987/6250 train_loss:2.4057 train_time:1590368ms step_avg:399.89ms step:3988/6250 train_loss:2.4396 train_time:1590780ms step_avg:399.89ms step:3989/6250 train_loss:2.3946 train_time:1591194ms step_avg:399.90ms step:3990/6250 train_loss:2.4381 train_time:1591606ms step_avg:399.90ms step:3991/6250 train_loss:2.4391 train_time:1592016ms step_avg:399.90ms step:3992/6250 train_loss:2.4376 train_time:1592427ms step_avg:399.91ms step:3993/6250 train_loss:2.5290 train_time:1592837ms step_avg:399.91ms step:3994/6250 train_loss:2.4271 train_time:1593247ms step_avg:399.91ms step:3995/6250 train_loss:2.3662 train_time:1593661ms step_avg:399.91ms step:3996/6250 train_loss:2.4603 train_time:1594071ms step_avg:399.92ms step:3997/6250 train_loss:2.4541 train_time:1594479ms step_avg:399.92ms step:3998/6250 train_loss:2.4034 train_time:1594896ms step_avg:399.92ms step:3999/6250 train_loss:2.4925 train_time:1595312ms step_avg:399.93ms step:4000/6250 train_loss:2.5452 train_time:1595720ms step_avg:399.93ms step:4000/6250 val_loss:2.4337 train_time:1595720ms step_avg:399.93ms step:4001/6250 train_loss:2.4259 train_time:1596143ms step_avg:399.94ms step:4002/6250 train_loss:2.4975 train_time:1596557ms step_avg:399.94ms step:4003/6250 train_loss:2.3446 train_time:1596973ms step_avg:399.94ms step:4004/6250 train_loss:2.3989 train_time:1597394ms step_avg:399.95ms step:4005/6250 train_loss:2.4060 train_time:1597815ms step_avg:399.95ms step:4006/6250 train_loss:2.4034 train_time:1598225ms step_avg:399.96ms step:4007/6250 train_loss:2.3945 train_time:1598634ms step_avg:399.96ms step:4008/6250 train_loss:2.4296 train_time:1599036ms step_avg:399.96ms step:4009/6250 train_loss:2.5350 train_time:1599434ms step_avg:399.96ms step:4010/6250 train_loss:2.4404 train_time:1599839ms step_avg:399.96ms step:4011/6250 train_loss:2.4242 train_time:1600241ms step_avg:399.96ms step:4012/6250 train_loss:2.4072 train_time:1600639ms step_avg:399.96ms step:4013/6250 train_loss:2.3710 train_time:1601038ms step_avg:399.96ms step:4014/6250 train_loss:2.5413 train_time:1601436ms step_avg:399.96ms step:4015/6250 train_loss:2.4082 train_time:1601829ms step_avg:399.96ms step:4016/6250 train_loss:2.4051 train_time:1602227ms step_avg:399.96ms step:4017/6250 train_loss:2.4597 train_time:1602639ms step_avg:399.96ms step:4018/6250 train_loss:2.4177 train_time:1603043ms step_avg:399.96ms step:4019/6250 train_loss:2.3481 train_time:1603436ms step_avg:399.96ms step:4020/6250 train_loss:2.4441 train_time:1603830ms step_avg:399.96ms step:4021/6250 train_loss:2.4433 train_time:1604226ms step_avg:399.96ms step:4022/6250 train_loss:2.3653 train_time:1604623ms step_avg:399.96ms step:4023/6250 train_loss:2.3574 train_time:1605025ms step_avg:399.96ms step:4024/6250 train_loss:2.3995 train_time:1605418ms step_avg:399.95ms step:4025/6250 train_loss:2.4161 train_time:1605825ms step_avg:399.96ms step:4026/6250 train_loss:2.4186 train_time:1606224ms step_avg:399.96ms step:4027/6250 train_loss:2.4380 train_time:1606619ms step_avg:399.95ms step:4028/6250 train_loss:2.3610 train_time:1607021ms step_avg:399.96ms step:4029/6250 train_loss:2.4961 train_time:1607419ms step_avg:399.95ms step:4030/6250 train_loss:2.3623 train_time:1607822ms step_avg:399.96ms step:4031/6250 train_loss:2.3432 train_time:1608222ms step_avg:399.96ms step:4032/6250 train_loss:2.3949 train_time:1608619ms step_avg:399.96ms step:4033/6250 train_loss:2.4625 train_time:1609020ms step_avg:399.96ms step:4034/6250 train_loss:2.4167 train_time:1609417ms step_avg:399.95ms step:4035/6250 train_loss:2.5036 train_time:1609818ms step_avg:399.95ms step:4036/6250 train_loss:2.4240 train_time:1610218ms step_avg:399.95ms step:4037/6250 train_loss:2.4057 train_time:1610617ms step_avg:399.95ms step:4038/6250 train_loss:2.4089 train_time:1611023ms step_avg:399.96ms step:4039/6250 train_loss:2.3922 train_time:1611426ms step_avg:399.96ms step:4040/6250 train_loss:2.4156 train_time:1611828ms step_avg:399.96ms step:4041/6250 train_loss:2.4804 train_time:1612223ms step_avg:399.96ms step:4042/6250 train_loss:2.4234 train_time:1612633ms step_avg:399.96ms step:4043/6250 train_loss:2.5064 train_time:1613037ms step_avg:399.96ms step:4044/6250 train_loss:2.4335 train_time:1613444ms step_avg:399.96ms step:4045/6250 train_loss:2.3787 train_time:1613847ms step_avg:399.96ms step:4046/6250 train_loss:2.3700 train_time:1614249ms step_avg:399.96ms step:4047/6250 train_loss:2.4140 train_time:1614650ms step_avg:399.96ms step:4048/6250 train_loss:2.4704 train_time:1615051ms step_avg:399.96ms step:4049/6250 train_loss:2.4301 train_time:1615441ms step_avg:399.96ms step:4050/6250 train_loss:2.4027 train_time:1615844ms step_avg:399.96ms step:4051/6250 train_loss:2.5299 train_time:1616244ms step_avg:399.96ms step:4052/6250 train_loss:2.4565 train_time:1616650ms step_avg:399.96ms step:4053/6250 train_loss:2.4106 train_time:1617050ms step_avg:399.96ms step:4054/6250 train_loss:2.4509 train_time:1617449ms step_avg:399.96ms step:4055/6250 train_loss:2.3179 train_time:1617845ms step_avg:399.96ms step:4056/6250 train_loss:2.5009 train_time:1618241ms step_avg:399.96ms step:4057/6250 train_loss:2.4082 train_time:1618636ms step_avg:399.96ms step:4058/6250 train_loss:2.5119 train_time:1619041ms step_avg:399.96ms step:4059/6250 train_loss:2.4327 train_time:1619437ms step_avg:399.96ms step:4060/6250 train_loss:2.3912 train_time:1619832ms step_avg:399.96ms step:4061/6250 train_loss:2.3852 train_time:1620229ms step_avg:399.96ms step:4062/6250 train_loss:2.5026 train_time:1620628ms step_avg:399.96ms step:4063/6250 train_loss:2.4798 train_time:1621020ms step_avg:399.96ms step:4064/6250 train_loss:2.3652 train_time:1621407ms step_avg:399.95ms step:4065/6250 train_loss:2.4228 train_time:1621810ms step_avg:399.95ms step:4066/6250 train_loss:2.4486 train_time:1622216ms step_avg:399.95ms step:4067/6250 train_loss:2.4185 train_time:1622618ms step_avg:399.96ms step:4068/6250 train_loss:2.3336 train_time:1623015ms step_avg:399.95ms step:4069/6250 train_loss:2.4947 train_time:1623415ms step_avg:399.95ms step:4070/6250 train_loss:2.3793 train_time:1623818ms step_avg:399.96ms step:4071/6250 train_loss:2.4911 train_time:1624217ms step_avg:399.95ms step:4072/6250 train_loss:2.4799 train_time:1624623ms step_avg:399.96ms step:4073/6250 train_loss:2.3302 train_time:1625024ms step_avg:399.96ms step:4074/6250 train_loss:2.4172 train_time:1625425ms step_avg:399.96ms step:4075/6250 train_loss:2.4010 train_time:1625826ms step_avg:399.96ms step:4076/6250 train_loss:2.4098 train_time:1626227ms step_avg:399.96ms step:4077/6250 train_loss:2.4882 train_time:1626633ms step_avg:399.96ms step:4078/6250 train_loss:2.3865 train_time:1627038ms step_avg:399.96ms step:4079/6250 train_loss:2.3776 train_time:1627437ms step_avg:399.96ms step:4080/6250 train_loss:2.4289 train_time:1627839ms step_avg:399.96ms step:4081/6250 train_loss:2.4421 train_time:1628239ms step_avg:399.96ms step:4082/6250 train_loss:2.4818 train_time:1628636ms step_avg:399.96ms step:4083/6250 train_loss:2.4267 train_time:1629045ms step_avg:399.96ms step:4084/6250 train_loss:2.4603 train_time:1629446ms step_avg:399.96ms step:4085/6250 train_loss:2.4266 train_time:1629851ms step_avg:399.96ms step:4086/6250 train_loss:2.4509 train_time:1630250ms step_avg:399.96ms step:4087/6250 train_loss:2.3852 train_time:1630647ms step_avg:399.96ms step:4088/6250 train_loss:2.4433 train_time:1631049ms step_avg:399.96ms step:4089/6250 train_loss:2.4359 train_time:1631459ms step_avg:399.97ms step:4090/6250 train_loss:2.4174 train_time:1631860ms step_avg:399.97ms step:4091/6250 train_loss:2.4960 train_time:1632269ms step_avg:399.97ms step:4092/6250 train_loss:2.4362 train_time:1632680ms step_avg:399.97ms step:4093/6250 train_loss:2.4417 train_time:1633082ms step_avg:399.97ms step:4094/6250 train_loss:2.3104 train_time:1633488ms step_avg:399.97ms step:4095/6250 train_loss:2.4544 train_time:1633892ms step_avg:399.97ms step:4096/6250 train_loss:2.4044 train_time:1634302ms step_avg:399.98ms step:4097/6250 train_loss:2.3486 train_time:1634711ms step_avg:399.98ms step:4098/6250 train_loss:2.4617 train_time:1635120ms step_avg:399.98ms step:4099/6250 train_loss:2.4321 train_time:1635525ms step_avg:399.98ms step:4100/6250 train_loss:2.4370 train_time:1635931ms step_avg:399.98ms step:4101/6250 train_loss:2.4692 train_time:1636346ms step_avg:399.99ms step:4102/6250 train_loss:2.5212 train_time:1636754ms step_avg:399.99ms step:4103/6250 train_loss:2.4368 train_time:1637159ms step_avg:399.99ms step:4104/6250 train_loss:2.4282 train_time:1637567ms step_avg:399.99ms step:4105/6250 train_loss:2.4896 train_time:1637974ms step_avg:399.99ms step:4106/6250 train_loss:2.4484 train_time:1638380ms step_avg:400.00ms step:4107/6250 train_loss:2.3957 train_time:1638775ms step_avg:399.99ms step:4108/6250 train_loss:2.4420 train_time:1639169ms step_avg:399.99ms step:4109/6250 train_loss:2.4453 train_time:1639570ms step_avg:399.99ms step:4110/6250 train_loss:2.4128 train_time:1639971ms step_avg:399.99ms step:4111/6250 train_loss:2.4021 train_time:1640375ms step_avg:399.99ms step:4112/6250 train_loss:2.4116 train_time:1640776ms step_avg:399.99ms step:4113/6250 train_loss:2.3848 train_time:1641173ms step_avg:399.99ms step:4114/6250 train_loss:2.4900 train_time:1641572ms step_avg:399.99ms step:4115/6250 train_loss:2.4066 train_time:1641970ms step_avg:399.99ms step:4116/6250 train_loss:2.4104 train_time:1642376ms step_avg:399.99ms step:4117/6250 train_loss:2.4915 train_time:1642783ms step_avg:400.00ms step:4118/6250 train_loss:2.3212 train_time:1643187ms step_avg:400.00ms step:4119/6250 train_loss:2.5027 train_time:1643578ms step_avg:399.99ms step:4120/6250 train_loss:2.4545 train_time:1643977ms step_avg:399.99ms step:4121/6250 train_loss:2.4785 train_time:1644365ms step_avg:399.99ms step:4122/6250 train_loss:2.4101 train_time:1644750ms step_avg:399.99ms step:4123/6250 train_loss:2.4602 train_time:1645135ms step_avg:399.98ms step:4124/6250 train_loss:2.4712 train_time:1645518ms step_avg:399.98ms step:4125/6250 train_loss:2.5253 train_time:1645903ms step_avg:399.98ms step:4126/6250 train_loss:2.4275 train_time:1646294ms step_avg:399.97ms step:4127/6250 train_loss:2.4720 train_time:1646699ms step_avg:399.98ms step:4128/6250 train_loss:2.4566 train_time:1647105ms step_avg:399.98ms step:4129/6250 train_loss:2.3777 train_time:1647512ms step_avg:399.98ms step:4130/6250 train_loss:2.5369 train_time:1647922ms step_avg:399.98ms step:4131/6250 train_loss:2.4784 train_time:1648325ms step_avg:399.98ms step:4132/6250 train_loss:2.3795 train_time:1648732ms step_avg:399.98ms step:4133/6250 train_loss:2.4225 train_time:1649139ms step_avg:399.99ms step:4134/6250 train_loss:2.5048 train_time:1649547ms step_avg:399.99ms step:4135/6250 train_loss:2.3596 train_time:1649956ms step_avg:399.99ms step:4136/6250 train_loss:2.3833 train_time:1650357ms step_avg:399.99ms step:4137/6250 train_loss:2.4765 train_time:1650760ms step_avg:399.99ms step:4138/6250 train_loss:2.4752 train_time:1651161ms step_avg:399.99ms step:4139/6250 train_loss:2.4503 train_time:1651569ms step_avg:399.99ms step:4140/6250 train_loss:2.5114 train_time:1651967ms step_avg:399.99ms step:4141/6250 train_loss:2.4455 train_time:1652375ms step_avg:399.99ms step:4142/6250 train_loss:2.4106 train_time:1652784ms step_avg:400.00ms step:4143/6250 train_loss:2.4826 train_time:1653188ms step_avg:400.00ms step:4144/6250 train_loss:2.4481 train_time:1653586ms step_avg:400.00ms step:4145/6250 train_loss:2.4135 train_time:1653986ms step_avg:400.00ms step:4146/6250 train_loss:2.4136 train_time:1654391ms step_avg:400.00ms step:4147/6250 train_loss:2.4323 train_time:1654806ms step_avg:400.00ms step:4148/6250 train_loss:2.3733 train_time:1655206ms step_avg:400.00ms step:4149/6250 train_loss:2.3556 train_time:1655596ms step_avg:400.00ms step:4150/6250 train_loss:2.4333 train_time:1655998ms step_avg:400.00ms step:4151/6250 train_loss:2.4250 train_time:1656397ms step_avg:400.00ms step:4152/6250 train_loss:2.4070 train_time:1656787ms step_avg:400.00ms step:4153/6250 train_loss:2.4006 train_time:1657176ms step_avg:399.99ms step:4154/6250 train_loss:2.3789 train_time:1657562ms step_avg:399.99ms step:4155/6250 train_loss:2.4885 train_time:1657947ms step_avg:399.99ms step:4156/6250 train_loss:2.5296 train_time:1658337ms step_avg:399.98ms step:4157/6250 train_loss:2.4222 train_time:1658736ms step_avg:399.98ms step:4158/6250 train_loss:2.4067 train_time:1659144ms step_avg:399.99ms step:4159/6250 train_loss:2.4513 train_time:1659640ms step_avg:400.01ms step:4160/6250 train_loss:2.4497 train_time:1660038ms step_avg:400.01ms step:4161/6250 train_loss:2.4357 train_time:1660433ms step_avg:400.01ms step:4162/6250 train_loss:2.3816 train_time:1660829ms step_avg:400.01ms step:4163/6250 train_loss:2.3859 train_time:1661223ms step_avg:400.01ms step:4164/6250 train_loss:2.3800 train_time:1661619ms step_avg:400.00ms step:4165/6250 train_loss:2.4027 train_time:1662018ms step_avg:400.00ms step:4166/6250 train_loss:2.3652 train_time:1662415ms step_avg:400.00ms step:4167/6250 train_loss:2.4692 train_time:1662808ms step_avg:400.00ms step:4168/6250 train_loss:2.4205 train_time:1663196ms step_avg:400.00ms step:4169/6250 train_loss:2.4194 train_time:1663595ms step_avg:400.00ms step:4170/6250 train_loss:2.4701 train_time:1663986ms step_avg:400.00ms step:4171/6250 train_loss:2.4000 train_time:1664386ms step_avg:400.00ms step:4172/6250 train_loss:2.4158 train_time:1664781ms step_avg:400.00ms step:4173/6250 train_loss:2.4119 train_time:1665175ms step_avg:399.99ms step:4174/6250 train_loss:2.3836 train_time:1665570ms step_avg:399.99ms step:4175/6250 train_loss:2.3758 train_time:1665967ms step_avg:399.99ms step:4176/6250 train_loss:2.3782 train_time:1666361ms step_avg:399.99ms step:4177/6250 train_loss:2.4044 train_time:1666758ms step_avg:399.99ms step:4178/6250 train_loss:2.3473 train_time:1667158ms step_avg:399.99ms step:4179/6250 train_loss:2.4631 train_time:1667553ms step_avg:399.99ms step:4180/6250 train_loss:2.4720 train_time:1667953ms step_avg:399.99ms step:4181/6250 train_loss:2.4415 train_time:1668355ms step_avg:399.99ms step:4182/6250 train_loss:2.4288 train_time:1668758ms step_avg:399.99ms step:4183/6250 train_loss:2.4143 train_time:1669152ms step_avg:399.99ms step:4184/6250 train_loss:2.3394 train_time:1669542ms step_avg:399.99ms step:4185/6250 train_loss:2.4376 train_time:1669937ms step_avg:399.98ms step:4186/6250 train_loss:2.3259 train_time:1670334ms step_avg:399.98ms step:4187/6250 train_loss:2.3519 train_time:1670732ms step_avg:399.98ms step:4188/6250 train_loss:2.4318 train_time:1671137ms step_avg:399.98ms step:4189/6250 train_loss:2.4017 train_time:1671534ms step_avg:399.98ms step:4190/6250 train_loss:2.3389 train_time:1671934ms step_avg:399.98ms step:4191/6250 train_loss:2.4551 train_time:1672326ms step_avg:399.98ms step:4192/6250 train_loss:2.4812 train_time:1672723ms step_avg:399.98ms step:4193/6250 train_loss:2.3018 train_time:1673137ms step_avg:399.99ms step:4194/6250 train_loss:2.4255 train_time:1673540ms step_avg:399.99ms step:4195/6250 train_loss:2.4264 train_time:1673956ms step_avg:399.99ms step:4196/6250 train_loss:2.4196 train_time:1674372ms step_avg:399.99ms step:4197/6250 train_loss:2.4039 train_time:1674780ms step_avg:400.00ms step:4198/6250 train_loss:2.4248 train_time:1675200ms step_avg:400.00ms step:4199/6250 train_loss:2.3852 train_time:1675594ms step_avg:400.00ms step:4200/6250 train_loss:2.5065 train_time:1675987ms step_avg:400.00ms step:4201/6250 train_loss:2.5033 train_time:1676378ms step_avg:399.99ms step:4202/6250 train_loss:2.4344 train_time:1676766ms step_avg:399.99ms step:4203/6250 train_loss:2.4175 train_time:1677157ms step_avg:399.99ms step:4204/6250 train_loss:2.4361 train_time:1677551ms step_avg:399.99ms step:4205/6250 train_loss:2.4272 train_time:1677949ms step_avg:399.99ms step:4206/6250 train_loss:2.5034 train_time:1678344ms step_avg:399.99ms step:4207/6250 train_loss:2.3895 train_time:1678740ms step_avg:399.99ms step:4208/6250 train_loss:2.5417 train_time:1679137ms step_avg:399.98ms step:4209/6250 train_loss:2.4440 train_time:1679537ms step_avg:399.98ms step:4210/6250 train_loss:2.4379 train_time:1679939ms step_avg:399.99ms step:4211/6250 train_loss:2.4505 train_time:1680337ms step_avg:399.99ms step:4212/6250 train_loss:2.4502 train_time:1680740ms step_avg:399.99ms step:4213/6250 train_loss:2.4278 train_time:1681140ms step_avg:399.99ms step:4214/6250 train_loss:2.3950 train_time:1681534ms step_avg:399.98ms step:4215/6250 train_loss:2.3226 train_time:1681932ms step_avg:399.98ms step:4216/6250 train_loss:2.3463 train_time:1682331ms step_avg:399.98ms step:4217/6250 train_loss:2.4173 train_time:1682725ms step_avg:399.98ms step:4218/6250 train_loss:2.4054 train_time:1683127ms step_avg:399.98ms step:4219/6250 train_loss:2.4888 train_time:1683524ms step_avg:399.98ms step:4220/6250 train_loss:2.4892 train_time:1683926ms step_avg:399.98ms step:4221/6250 train_loss:2.4699 train_time:1684322ms step_avg:399.98ms step:4222/6250 train_loss:2.3993 train_time:1684724ms step_avg:399.98ms step:4223/6250 train_loss:2.4003 train_time:1685122ms step_avg:399.98ms step:4224/6250 train_loss:2.4901 train_time:1685519ms step_avg:399.98ms step:4225/6250 train_loss:2.4651 train_time:1685913ms step_avg:399.98ms step:4226/6250 train_loss:2.4163 train_time:1686303ms step_avg:399.98ms step:4227/6250 train_loss:2.4645 train_time:1686701ms step_avg:399.98ms step:4228/6250 train_loss:2.3919 train_time:1687097ms step_avg:399.98ms step:4229/6250 train_loss:2.4537 train_time:1687496ms step_avg:399.98ms step:4230/6250 train_loss:2.4451 train_time:1687895ms step_avg:399.98ms step:4231/6250 train_loss:2.4312 train_time:1688290ms step_avg:399.97ms step:4232/6250 train_loss:2.4123 train_time:1688684ms step_avg:399.97ms step:4233/6250 train_loss:2.4066 train_time:1689081ms step_avg:399.97ms step:4234/6250 train_loss:2.4555 train_time:1689476ms step_avg:399.97ms step:4235/6250 train_loss:2.4697 train_time:1689871ms step_avg:399.97ms step:4236/6250 train_loss:2.4813 train_time:1690266ms step_avg:399.97ms step:4237/6250 train_loss:2.3964 train_time:1690665ms step_avg:399.97ms step:4238/6250 train_loss:2.4973 train_time:1691064ms step_avg:399.97ms step:4239/6250 train_loss:2.4924 train_time:1691458ms step_avg:399.97ms step:4240/6250 train_loss:2.4257 train_time:1691858ms step_avg:399.97ms step:4241/6250 train_loss:2.3688 train_time:1692256ms step_avg:399.97ms step:4242/6250 train_loss:2.3389 train_time:1692647ms step_avg:399.96ms step:4243/6250 train_loss:2.4716 train_time:1693037ms step_avg:399.96ms step:4244/6250 train_loss:2.4383 train_time:1693420ms step_avg:399.96ms step:4245/6250 train_loss:2.3923 train_time:1693808ms step_avg:399.95ms step:4246/6250 train_loss:2.3700 train_time:1694205ms step_avg:399.95ms step:4247/6250 train_loss:2.4510 train_time:1694586ms step_avg:399.95ms step:4248/6250 train_loss:2.4285 train_time:1694967ms step_avg:399.94ms step:4249/6250 train_loss:2.3883 train_time:1695352ms step_avg:399.94ms step:4250/6250 train_loss:2.4808 train_time:1695733ms step_avg:399.94ms step:4251/6250 train_loss:2.4079 train_time:1696121ms step_avg:399.93ms step:4252/6250 train_loss:2.4041 train_time:1696503ms step_avg:399.93ms step:4253/6250 train_loss:2.3947 train_time:1696888ms step_avg:399.93ms step:4254/6250 train_loss:2.4476 train_time:1697279ms step_avg:399.92ms step:4255/6250 train_loss:2.3889 train_time:1697675ms step_avg:399.92ms step:4256/6250 train_loss:2.3729 train_time:1698070ms step_avg:399.92ms step:4257/6250 train_loss:2.3703 train_time:1698463ms step_avg:399.92ms step:4258/6250 train_loss:2.4691 train_time:1698860ms step_avg:399.92ms step:4259/6250 train_loss:2.3627 train_time:1699256ms step_avg:399.92ms step:4260/6250 train_loss:2.4818 train_time:1699656ms step_avg:399.92ms step:4261/6250 train_loss:2.4403 train_time:1700027ms step_avg:399.91ms step:4262/6250 train_loss:2.4386 train_time:1700428ms step_avg:399.91ms step:4263/6250 train_loss:2.4145 train_time:1700826ms step_avg:399.91ms step:4264/6250 train_loss:2.4681 train_time:1701223ms step_avg:399.91ms step:4265/6250 train_loss:2.3849 train_time:1701617ms step_avg:399.91ms step:4266/6250 train_loss:2.4634 train_time:1702011ms step_avg:399.91ms step:4267/6250 train_loss:2.3385 train_time:1702405ms step_avg:399.91ms step:4268/6250 train_loss:2.4486 train_time:1702802ms step_avg:399.91ms step:4269/6250 train_loss:2.5136 train_time:1703198ms step_avg:399.91ms step:4270/6250 train_loss:2.3726 train_time:1703601ms step_avg:399.91ms step:4271/6250 train_loss:2.3962 train_time:1704005ms step_avg:399.91ms step:4272/6250 train_loss:2.4609 train_time:1704409ms step_avg:399.91ms step:4273/6250 train_loss:2.3053 train_time:1704813ms step_avg:399.91ms step:4274/6250 train_loss:2.4610 train_time:1705210ms step_avg:399.91ms step:4275/6250 train_loss:2.4219 train_time:1705611ms step_avg:399.91ms step:4276/6250 train_loss:2.3884 train_time:1706030ms step_avg:399.91ms step:4277/6250 train_loss:2.3898 train_time:1706456ms step_avg:399.92ms step:4278/6250 train_loss:2.3526 train_time:1706876ms step_avg:399.92ms step:4279/6250 train_loss:2.4343 train_time:1707300ms step_avg:399.93ms step:4280/6250 train_loss:2.4689 train_time:1707717ms step_avg:399.93ms step:4281/6250 train_loss:2.4318 train_time:1708137ms step_avg:399.94ms step:4282/6250 train_loss:2.4704 train_time:1708551ms step_avg:399.94ms step:4283/6250 train_loss:2.4449 train_time:1708969ms step_avg:399.95ms step:4284/6250 train_loss:2.3577 train_time:1709398ms step_avg:399.95ms step:4285/6250 train_loss:2.3989 train_time:1709833ms step_avg:399.96ms step:4286/6250 train_loss:2.4605 train_time:1710268ms step_avg:399.97ms step:4287/6250 train_loss:2.4835 train_time:1710703ms step_avg:399.98ms step:4288/6250 train_loss:2.3930 train_time:1711123ms step_avg:399.98ms step:4289/6250 train_loss:2.4127 train_time:1711540ms step_avg:399.99ms step:4290/6250 train_loss:2.4234 train_time:1711951ms step_avg:399.99ms step:4291/6250 train_loss:2.3731 train_time:1712380ms step_avg:400.00ms step:4292/6250 train_loss:2.4093 train_time:1712801ms step_avg:400.00ms step:4293/6250 train_loss:2.3560 train_time:1713226ms step_avg:400.01ms step:4294/6250 train_loss:2.3784 train_time:1713636ms step_avg:400.01ms step:4295/6250 train_loss:2.4198 train_time:1714057ms step_avg:400.01ms step:4296/6250 train_loss:2.4006 train_time:1714475ms step_avg:400.02ms step:4297/6250 train_loss:2.4368 train_time:1714894ms step_avg:400.02ms step:4298/6250 train_loss:2.3842 train_time:1715299ms step_avg:400.02ms step:4299/6250 train_loss:2.5018 train_time:1715694ms step_avg:400.02ms step:4300/6250 train_loss:2.3476 train_time:1716091ms step_avg:400.02ms step:4301/6250 train_loss:2.5469 train_time:1716491ms step_avg:400.02ms step:4302/6250 train_loss:2.4886 train_time:1716887ms step_avg:400.02ms step:4303/6250 train_loss:2.3479 train_time:1717291ms step_avg:400.02ms step:4304/6250 train_loss:2.4278 train_time:1717689ms step_avg:400.02ms step:4305/6250 train_loss:2.4096 train_time:1718085ms step_avg:400.02ms step:4306/6250 train_loss:2.4625 train_time:1718483ms step_avg:400.02ms step:4307/6250 train_loss:2.3846 train_time:1718873ms step_avg:400.02ms step:4308/6250 train_loss:2.5388 train_time:1719267ms step_avg:400.02ms step:4309/6250 train_loss:2.4212 train_time:1719661ms step_avg:400.01ms step:4310/6250 train_loss:2.4235 train_time:1720056ms step_avg:400.01ms step:4311/6250 train_loss:2.5042 train_time:1720450ms step_avg:400.01ms step:4312/6250 train_loss:2.3702 train_time:1720842ms step_avg:400.01ms step:4313/6250 train_loss:2.3332 train_time:1721235ms step_avg:400.01ms step:4314/6250 train_loss:2.3611 train_time:1721629ms step_avg:400.01ms step:4315/6250 train_loss:2.4471 train_time:1722022ms step_avg:400.01ms step:4316/6250 train_loss:2.4035 train_time:1722404ms step_avg:400.00ms step:4317/6250 train_loss:2.4827 train_time:1722803ms step_avg:400.00ms step:4318/6250 train_loss:2.3868 train_time:1723216ms step_avg:400.00ms step:4319/6250 train_loss:2.3960 train_time:1723612ms step_avg:400.00ms step:4320/6250 train_loss:2.3338 train_time:1724007ms step_avg:400.00ms step:4321/6250 train_loss:2.4092 train_time:1724400ms step_avg:400.00ms step:4322/6250 train_loss:2.4862 train_time:1724795ms step_avg:400.00ms step:4323/6250 train_loss:2.4990 train_time:1725189ms step_avg:400.00ms step:4324/6250 train_loss:2.3954 train_time:1725588ms step_avg:400.00ms step:4325/6250 train_loss:2.4343 train_time:1725981ms step_avg:400.00ms step:4326/6250 train_loss:2.3379 train_time:1726373ms step_avg:399.99ms step:4327/6250 train_loss:2.4571 train_time:1726768ms step_avg:399.99ms step:4328/6250 train_loss:2.3547 train_time:1727164ms step_avg:399.99ms step:4329/6250 train_loss:2.4299 train_time:1727554ms step_avg:399.99ms step:4330/6250 train_loss:2.4356 train_time:1727948ms step_avg:399.99ms step:4331/6250 train_loss:2.3415 train_time:1728341ms step_avg:399.99ms step:4332/6250 train_loss:2.4105 train_time:1728736ms step_avg:399.99ms step:4333/6250 train_loss:2.4600 train_time:1729131ms step_avg:399.98ms step:4334/6250 train_loss:2.3791 train_time:1729522ms step_avg:399.98ms step:4335/6250 train_loss:2.5147 train_time:1729912ms step_avg:399.98ms step:4336/6250 train_loss:2.4409 train_time:1730306ms step_avg:399.98ms step:4337/6250 train_loss:2.3921 train_time:1730699ms step_avg:399.98ms step:4338/6250 train_loss:2.4054 train_time:1731090ms step_avg:399.97ms step:4339/6250 train_loss:2.4199 train_time:1731483ms step_avg:399.97ms step:4340/6250 train_loss:2.3835 train_time:1731879ms step_avg:399.97ms step:4341/6250 train_loss:2.3712 train_time:1732270ms step_avg:399.97ms step:4342/6250 train_loss:2.3781 train_time:1732663ms step_avg:399.97ms step:4343/6250 train_loss:2.4354 train_time:1733056ms step_avg:399.97ms step:4344/6250 train_loss:2.4061 train_time:1733448ms step_avg:399.96ms step:4345/6250 train_loss:2.3607 train_time:1733841ms step_avg:399.96ms step:4346/6250 train_loss:2.4109 train_time:1734232ms step_avg:399.96ms step:4347/6250 train_loss:2.4891 train_time:1734626ms step_avg:399.96ms step:4348/6250 train_loss:2.3687 train_time:1735016ms step_avg:399.96ms step:4349/6250 train_loss:2.4260 train_time:1735406ms step_avg:399.96ms step:4350/6250 train_loss:2.3960 train_time:1735802ms step_avg:399.95ms step:4351/6250 train_loss:2.4047 train_time:1736197ms step_avg:399.95ms step:4352/6250 train_loss:2.4058 train_time:1736590ms step_avg:399.95ms step:4353/6250 train_loss:2.4137 train_time:1736983ms step_avg:399.95ms step:4354/6250 train_loss:2.4164 train_time:1737372ms step_avg:399.95ms step:4355/6250 train_loss:2.4366 train_time:1737762ms step_avg:399.95ms step:4356/6250 train_loss:2.4438 train_time:1738158ms step_avg:399.94ms step:4357/6250 train_loss:2.3854 train_time:1738551ms step_avg:399.94ms step:4358/6250 train_loss:2.4765 train_time:1738944ms step_avg:399.94ms step:4359/6250 train_loss:2.3804 train_time:1739335ms step_avg:399.94ms step:4360/6250 train_loss:2.4390 train_time:1739727ms step_avg:399.94ms step:4361/6250 train_loss:2.4451 train_time:1740120ms step_avg:399.94ms step:4362/6250 train_loss:2.3444 train_time:1740510ms step_avg:399.93ms step:4363/6250 train_loss:2.4355 train_time:1740902ms step_avg:399.93ms step:4364/6250 train_loss:2.2909 train_time:1741290ms step_avg:399.93ms step:4365/6250 train_loss:2.4021 train_time:1741682ms step_avg:399.93ms step:4366/6250 train_loss:2.4534 train_time:1742073ms step_avg:399.92ms step:4367/6250 train_loss:2.4998 train_time:1742462ms step_avg:399.92ms step:4368/6250 train_loss:2.3569 train_time:1742851ms step_avg:399.92ms step:4369/6250 train_loss:2.4464 train_time:1743259ms step_avg:399.92ms step:4370/6250 train_loss:2.3925 train_time:1743665ms step_avg:399.92ms step:4371/6250 train_loss:2.3702 train_time:1744076ms step_avg:399.93ms step:4372/6250 train_loss:2.4963 train_time:1744469ms step_avg:399.92ms step:4373/6250 train_loss:2.4083 train_time:1744861ms step_avg:399.92ms step:4374/6250 train_loss:2.4678 train_time:1745253ms step_avg:399.92ms step:4375/6250 train_loss:2.3390 train_time:1745642ms step_avg:399.92ms step:4376/6250 train_loss:2.4316 train_time:1746033ms step_avg:399.92ms step:4377/6250 train_loss:2.2877 train_time:1746422ms step_avg:399.91ms step:4378/6250 train_loss:2.3412 train_time:1746811ms step_avg:399.91ms step:4379/6250 train_loss:2.4403 train_time:1747198ms step_avg:399.91ms step:4380/6250 train_loss:2.4265 train_time:1747586ms step_avg:399.91ms step:4381/6250 train_loss:2.4634 train_time:1747973ms step_avg:399.90ms step:4382/6250 train_loss:2.3493 train_time:1748359ms step_avg:399.90ms step:4383/6250 train_loss:2.3573 train_time:1748745ms step_avg:399.90ms step:4384/6250 train_loss:2.3404 train_time:1749131ms step_avg:399.89ms step:4385/6250 train_loss:2.3832 train_time:1749511ms step_avg:399.89ms step:4386/6250 train_loss:2.3897 train_time:1749902ms step_avg:399.89ms step:4387/6250 train_loss:2.3943 train_time:1750294ms step_avg:399.88ms step:4388/6250 train_loss:2.3509 train_time:1750680ms step_avg:399.88ms step:4389/6250 train_loss:2.3732 train_time:1751070ms step_avg:399.88ms step:4390/6250 train_loss:2.3703 train_time:1751459ms step_avg:399.88ms step:4391/6250 train_loss:2.2886 train_time:1751849ms step_avg:399.87ms step:4392/6250 train_loss:2.3995 train_time:1752235ms step_avg:399.87ms step:4393/6250 train_loss:2.3642 train_time:1752625ms step_avg:399.87ms step:4394/6250 train_loss:2.3871 train_time:1753012ms step_avg:399.87ms step:4395/6250 train_loss:2.2711 train_time:1753395ms step_avg:399.86ms step:4396/6250 train_loss:2.4419 train_time:1753781ms step_avg:399.86ms step:4397/6250 train_loss:2.3728 train_time:1754170ms step_avg:399.86ms step:4398/6250 train_loss:2.3856 train_time:1754561ms step_avg:399.85ms step:4399/6250 train_loss:2.4420 train_time:1754947ms step_avg:399.85ms step:4400/6250 train_loss:2.4388 train_time:1755339ms step_avg:399.85ms step:4401/6250 train_loss:2.3898 train_time:1755728ms step_avg:399.85ms step:4402/6250 train_loss:2.5028 train_time:1756116ms step_avg:399.84ms step:4403/6250 train_loss:2.4261 train_time:1756504ms step_avg:399.84ms step:4404/6250 train_loss:2.3841 train_time:1756896ms step_avg:399.84ms step:4405/6250 train_loss:2.3961 train_time:1757285ms step_avg:399.84ms step:4406/6250 train_loss:2.4027 train_time:1757670ms step_avg:399.83ms step:4407/6250 train_loss:2.3857 train_time:1758055ms step_avg:399.83ms step:4408/6250 train_loss:2.4067 train_time:1758459ms step_avg:399.83ms step:4409/6250 train_loss:2.4515 train_time:1758850ms step_avg:399.83ms step:4410/6250 train_loss:2.4254 train_time:1759239ms step_avg:399.83ms step:4411/6250 train_loss:2.3627 train_time:1759643ms step_avg:399.83ms step:4412/6250 train_loss:2.4132 train_time:1760050ms step_avg:399.83ms step:4413/6250 train_loss:2.3845 train_time:1760478ms step_avg:399.84ms step:4414/6250 train_loss:2.5272 train_time:1760880ms step_avg:399.84ms step:4415/6250 train_loss:2.4809 train_time:1761293ms step_avg:399.84ms step:4416/6250 train_loss:2.4012 train_time:1761703ms step_avg:399.84ms step:4417/6250 train_loss:2.3980 train_time:1762106ms step_avg:399.84ms step:4418/6250 train_loss:2.4014 train_time:1762517ms step_avg:399.84ms step:4419/6250 train_loss:2.4422 train_time:1762925ms step_avg:399.85ms step:4420/6250 train_loss:2.4905 train_time:1763333ms step_avg:399.85ms step:4421/6250 train_loss:2.3697 train_time:1763746ms step_avg:399.85ms step:4422/6250 train_loss:2.3856 train_time:1764147ms step_avg:399.85ms step:4423/6250 train_loss:2.4178 train_time:1764531ms step_avg:399.85ms step:4424/6250 train_loss:2.3081 train_time:1764912ms step_avg:399.84ms step:4425/6250 train_loss:2.4538 train_time:1765291ms step_avg:399.84ms step:4426/6250 train_loss:2.3992 train_time:1765673ms step_avg:399.84ms step:4427/6250 train_loss:2.3869 train_time:1766055ms step_avg:399.83ms step:4428/6250 train_loss:2.5656 train_time:1766440ms step_avg:399.83ms step:4429/6250 train_loss:2.4938 train_time:1766825ms step_avg:399.82ms step:4430/6250 train_loss:2.4736 train_time:1767211ms step_avg:399.82ms step:4431/6250 train_loss:2.4626 train_time:1767595ms step_avg:399.82ms step:4432/6250 train_loss:2.4149 train_time:1767979ms step_avg:399.81ms step:4433/6250 train_loss:2.3842 train_time:1768360ms step_avg:399.81ms step:4434/6250 train_loss:2.2785 train_time:1768744ms step_avg:399.81ms step:4435/6250 train_loss:2.4007 train_time:1769130ms step_avg:399.80ms step:4436/6250 train_loss:2.3764 train_time:1769521ms step_avg:399.80ms step:4437/6250 train_loss:2.4540 train_time:1769917ms step_avg:399.80ms step:4438/6250 train_loss:2.3879 train_time:1770311ms step_avg:399.80ms step:4439/6250 train_loss:2.3757 train_time:1770702ms step_avg:399.80ms step:4440/6250 train_loss:2.4283 train_time:1771095ms step_avg:399.80ms step:4441/6250 train_loss:2.3628 train_time:1771485ms step_avg:399.79ms step:4442/6250 train_loss:2.4221 train_time:1771876ms step_avg:399.79ms step:4443/6250 train_loss:2.4271 train_time:1772268ms step_avg:399.79ms step:4444/6250 train_loss:2.3629 train_time:1772660ms step_avg:399.79ms step:4445/6250 train_loss:2.3756 train_time:1773051ms step_avg:399.79ms step:4446/6250 train_loss:2.3432 train_time:1773443ms step_avg:399.78ms step:4447/6250 train_loss:2.3371 train_time:1773836ms step_avg:399.78ms step:4448/6250 train_loss:2.4654 train_time:1774236ms step_avg:399.78ms step:4449/6250 train_loss:2.3941 train_time:1774636ms step_avg:399.78ms step:4450/6250 train_loss:2.3244 train_time:1775024ms step_avg:399.78ms step:4451/6250 train_loss:2.4705 train_time:1775403ms step_avg:399.78ms step:4452/6250 train_loss:2.4601 train_time:1775782ms step_avg:399.77ms step:4453/6250 train_loss:2.3780 train_time:1776164ms step_avg:399.77ms step:4454/6250 train_loss:2.3364 train_time:1776546ms step_avg:399.76ms step:4455/6250 train_loss:2.4462 train_time:1776933ms step_avg:399.76ms step:4456/6250 train_loss:2.3849 train_time:1777317ms step_avg:399.76ms step:4457/6250 train_loss:2.4255 train_time:1777706ms step_avg:399.75ms step:4458/6250 train_loss:2.3811 train_time:1778091ms step_avg:399.75ms step:4459/6250 train_loss:2.4915 train_time:1778474ms step_avg:399.75ms step:4460/6250 train_loss:2.5379 train_time:1778857ms step_avg:399.74ms step:4461/6250 train_loss:2.4695 train_time:1779237ms step_avg:399.74ms step:4462/6250 train_loss:2.4711 train_time:1779618ms step_avg:399.73ms step:4463/6250 train_loss:2.4113 train_time:1779998ms step_avg:399.73ms step:4464/6250 train_loss:2.5047 train_time:1780383ms step_avg:399.73ms step:4465/6250 train_loss:2.3927 train_time:1780774ms step_avg:399.72ms step:4466/6250 train_loss:2.4735 train_time:1781164ms step_avg:399.72ms step:4467/6250 train_loss:2.3405 train_time:1781555ms step_avg:399.72ms step:4468/6250 train_loss:2.3673 train_time:1781950ms step_avg:399.72ms step:4469/6250 train_loss:2.3176 train_time:1782342ms step_avg:399.72ms step:4470/6250 train_loss:2.4876 train_time:1782733ms step_avg:399.72ms step:4471/6250 train_loss:2.4160 train_time:1783122ms step_avg:399.71ms step:4472/6250 train_loss:2.4047 train_time:1783513ms step_avg:399.71ms step:4473/6250 train_loss:2.4101 train_time:1783901ms step_avg:399.71ms step:4474/6250 train_loss:2.3825 train_time:1784294ms step_avg:399.71ms step:4475/6250 train_loss:2.3795 train_time:1784687ms step_avg:399.71ms step:4476/6250 train_loss:2.4840 train_time:1785077ms step_avg:399.70ms step:4477/6250 train_loss:2.3685 train_time:1785468ms step_avg:399.70ms step:4478/6250 train_loss:2.3764 train_time:1785860ms step_avg:399.70ms step:4479/6250 train_loss:2.3918 train_time:1786255ms step_avg:399.70ms step:4480/6250 train_loss:2.4672 train_time:1786659ms step_avg:399.70ms step:4481/6250 train_loss:2.3623 train_time:1787057ms step_avg:399.70ms step:4482/6250 train_loss:2.3971 train_time:1787448ms step_avg:399.70ms step:4483/6250 train_loss:2.4002 train_time:1787842ms step_avg:399.70ms step:4484/6250 train_loss:2.4171 train_time:1788233ms step_avg:399.69ms step:4485/6250 train_loss:2.3982 train_time:1788620ms step_avg:399.69ms step:4486/6250 train_loss:2.4199 train_time:1789025ms step_avg:399.69ms step:4487/6250 train_loss:2.4545 train_time:1789412ms step_avg:399.69ms step:4488/6250 train_loss:2.3517 train_time:1789793ms step_avg:399.69ms step:4489/6250 train_loss:2.5050 train_time:1790178ms step_avg:399.68ms step:4490/6250 train_loss:2.5319 train_time:1790570ms step_avg:399.68ms step:4491/6250 train_loss:2.4109 train_time:1790965ms step_avg:399.68ms step:4492/6250 train_loss:2.4080 train_time:1791358ms step_avg:399.68ms step:4493/6250 train_loss:2.4039 train_time:1791767ms step_avg:399.68ms step:4494/6250 train_loss:2.3527 train_time:1792180ms step_avg:399.68ms step:4495/6250 train_loss:2.4029 train_time:1792589ms step_avg:399.69ms step:4496/6250 train_loss:2.4303 train_time:1793000ms step_avg:399.69ms step:4497/6250 train_loss:2.3927 train_time:1793404ms step_avg:399.69ms step:4498/6250 train_loss:2.4386 train_time:1793816ms step_avg:399.69ms step:4499/6250 train_loss:2.4350 train_time:1794233ms step_avg:399.70ms step:4500/6250 train_loss:2.4841 train_time:1794644ms step_avg:399.70ms step:4501/6250 train_loss:2.4499 train_time:1795055ms step_avg:399.70ms step:4502/6250 train_loss:2.4622 train_time:1795472ms step_avg:399.70ms step:4503/6250 train_loss:2.3584 train_time:1795878ms step_avg:399.71ms step:4504/6250 train_loss:2.3722 train_time:1796281ms step_avg:399.71ms step:4505/6250 train_loss:2.4209 train_time:1796685ms step_avg:399.71ms step:4506/6250 train_loss:2.3983 train_time:1797093ms step_avg:399.71ms step:4507/6250 train_loss:2.3615 train_time:1797500ms step_avg:399.71ms step:4508/6250 train_loss:2.3369 train_time:1797895ms step_avg:399.71ms step:4509/6250 train_loss:2.4144 train_time:1798284ms step_avg:399.71ms step:4510/6250 train_loss:2.4010 train_time:1798680ms step_avg:399.71ms step:4511/6250 train_loss:2.4756 train_time:1799066ms step_avg:399.70ms step:4512/6250 train_loss:2.4880 train_time:1799460ms step_avg:399.70ms step:4513/6250 train_loss:2.4150 train_time:1799855ms step_avg:399.70ms step:4514/6250 train_loss:2.3815 train_time:1800242ms step_avg:399.70ms step:4515/6250 train_loss:2.4668 train_time:1800638ms step_avg:399.70ms step:4516/6250 train_loss:2.4309 train_time:1801020ms step_avg:399.69ms step:4517/6250 train_loss:2.4425 train_time:1801398ms step_avg:399.69ms step:4518/6250 train_loss:2.4145 train_time:1801767ms step_avg:399.68ms step:4519/6250 train_loss:2.4324 train_time:1802149ms step_avg:399.68ms step:4520/6250 train_loss:2.4396 train_time:1802540ms step_avg:399.68ms step:4521/6250 train_loss:2.5183 train_time:1802933ms step_avg:399.67ms step:4522/6250 train_loss:2.4398 train_time:1803322ms step_avg:399.67ms step:4523/6250 train_loss:2.3977 train_time:1803716ms step_avg:399.67ms step:4524/6250 train_loss:2.4276 train_time:1804108ms step_avg:399.67ms step:4525/6250 train_loss:2.3444 train_time:1804501ms step_avg:399.67ms step:4526/6250 train_loss:2.3960 train_time:1804895ms step_avg:399.67ms step:4527/6250 train_loss:2.4097 train_time:1805284ms step_avg:399.66ms step:4528/6250 train_loss:2.2644 train_time:1805679ms step_avg:399.66ms step:4529/6250 train_loss:2.3778 train_time:1806071ms step_avg:399.66ms step:4530/6250 train_loss:2.4523 train_time:1806464ms step_avg:399.66ms step:4531/6250 train_loss:2.4662 train_time:1806855ms step_avg:399.66ms step:4532/6250 train_loss:2.3905 train_time:1807249ms step_avg:399.66ms step:4533/6250 train_loss:2.3524 train_time:1807641ms step_avg:399.66ms step:4534/6250 train_loss:2.3548 train_time:1808033ms step_avg:399.65ms step:4535/6250 train_loss:2.3579 train_time:1808428ms step_avg:399.65ms step:4536/6250 train_loss:2.3015 train_time:1808827ms step_avg:399.65ms step:4537/6250 train_loss:2.4703 train_time:1809240ms step_avg:399.66ms step:4538/6250 train_loss:2.4290 train_time:1809667ms step_avg:399.66ms step:4539/6250 train_loss:2.4461 train_time:1810092ms step_avg:399.67ms step:4540/6250 train_loss:2.4569 train_time:1810526ms step_avg:399.67ms step:4541/6250 train_loss:2.3641 train_time:1810954ms step_avg:399.68ms step:4542/6250 train_loss:2.4149 train_time:1811385ms step_avg:399.69ms step:4543/6250 train_loss:2.4154 train_time:1811815ms step_avg:399.69ms step:4544/6250 train_loss:2.4256 train_time:1812242ms step_avg:399.70ms step:4545/6250 train_loss:2.3817 train_time:1812667ms step_avg:399.71ms step:4546/6250 train_loss:2.3677 train_time:1813093ms step_avg:399.71ms step:4547/6250 train_loss:2.4380 train_time:1813525ms step_avg:399.72ms step:4548/6250 train_loss:2.4513 train_time:1813951ms step_avg:399.72ms step:4549/6250 train_loss:2.4891 train_time:1814377ms step_avg:399.73ms step:4550/6250 train_loss:2.3848 train_time:1814807ms step_avg:399.74ms step:4551/6250 train_loss:2.3392 train_time:1815232ms step_avg:399.74ms step:4552/6250 train_loss:2.4442 train_time:1815659ms step_avg:399.75ms step:4553/6250 train_loss:2.4794 train_time:1816070ms step_avg:399.75ms step:4554/6250 train_loss:2.3333 train_time:1816490ms step_avg:399.76ms step:4555/6250 train_loss:2.3805 train_time:1816922ms step_avg:399.76ms step:4556/6250 train_loss:2.4142 train_time:1817338ms step_avg:399.77ms step:4557/6250 train_loss:2.4518 train_time:1817759ms step_avg:399.77ms step:4558/6250 train_loss:2.4313 train_time:1818182ms step_avg:399.78ms step:4559/6250 train_loss:2.4870 train_time:1818605ms step_avg:399.78ms step:4560/6250 train_loss:2.3719 train_time:1819030ms step_avg:399.79ms step:4561/6250 train_loss:2.5203 train_time:1819455ms step_avg:399.79ms step:4562/6250 train_loss:2.4078 train_time:1819882ms step_avg:399.80ms step:4563/6250 train_loss:2.4589 train_time:1820303ms step_avg:399.80ms step:4564/6250 train_loss:2.4312 train_time:1820726ms step_avg:399.81ms step:4565/6250 train_loss:2.4744 train_time:1821149ms step_avg:399.81ms step:4566/6250 train_loss:2.4142 train_time:1821579ms step_avg:399.82ms step:4567/6250 train_loss:2.5184 train_time:1822005ms step_avg:399.83ms step:4568/6250 train_loss:2.4756 train_time:1822426ms step_avg:399.83ms step:4569/6250 train_loss:2.4370 train_time:1822852ms step_avg:399.84ms step:4570/6250 train_loss:2.4686 train_time:1823276ms step_avg:399.84ms step:4571/6250 train_loss:2.4661 train_time:1823700ms step_avg:399.85ms step:4572/6250 train_loss:2.4369 train_time:1824122ms step_avg:399.85ms step:4573/6250 train_loss:2.4306 train_time:1824548ms step_avg:399.86ms step:4574/6250 train_loss:2.3055 train_time:1824972ms step_avg:399.86ms step:4575/6250 train_loss:2.4943 train_time:1825397ms step_avg:399.87ms step:4576/6250 train_loss:2.3671 train_time:1825821ms step_avg:399.87ms step:4577/6250 train_loss:2.4909 train_time:1826250ms step_avg:399.88ms step:4578/6250 train_loss:2.4002 train_time:1826725ms step_avg:399.90ms step:4579/6250 train_loss:2.4447 train_time:1827158ms step_avg:399.90ms step:4580/6250 train_loss:2.3849 train_time:1827599ms step_avg:399.91ms step:4581/6250 train_loss:2.4148 train_time:1828027ms step_avg:399.92ms step:4582/6250 train_loss:2.4393 train_time:1828460ms step_avg:399.93ms step:4583/6250 train_loss:2.4130 train_time:1828893ms step_avg:399.93ms step:4584/6250 train_loss:2.3777 train_time:1829336ms step_avg:399.94ms step:4585/6250 train_loss:2.4263 train_time:1829775ms step_avg:399.95ms step:4586/6250 train_loss:2.4929 train_time:1830211ms step_avg:399.96ms step:4587/6250 train_loss:2.3759 train_time:1830650ms step_avg:399.97ms step:4588/6250 train_loss:2.3691 train_time:1831087ms step_avg:399.98ms step:4589/6250 train_loss:2.3921 train_time:1831523ms step_avg:399.98ms step:4590/6250 train_loss:2.3735 train_time:1831957ms step_avg:399.99ms step:4591/6250 train_loss:2.3892 train_time:1832392ms step_avg:400.00ms step:4592/6250 train_loss:2.4199 train_time:1832825ms step_avg:400.01ms step:4593/6250 train_loss:2.4791 train_time:1833259ms step_avg:400.01ms step:4594/6250 train_loss:2.3975 train_time:1833693ms step_avg:400.02ms step:4595/6250 train_loss:2.4468 train_time:1834128ms step_avg:400.03ms step:4596/6250 train_loss:2.3091 train_time:1834558ms step_avg:400.03ms step:4597/6250 train_loss:2.4047 train_time:1834989ms step_avg:400.04ms step:4598/6250 train_loss:2.3804 train_time:1835416ms step_avg:400.05ms step:4599/6250 train_loss:2.4242 train_time:1835844ms step_avg:400.05ms step:4600/6250 train_loss:2.3178 train_time:1836271ms step_avg:400.06ms step:4601/6250 train_loss:2.3126 train_time:1836707ms step_avg:400.07ms step:4602/6250 train_loss:2.3635 train_time:1837234ms step_avg:400.09ms step:4603/6250 train_loss:2.4358 train_time:1837670ms step_avg:400.10ms step:4604/6250 train_loss:2.4468 train_time:1838097ms step_avg:400.11ms step:4605/6250 train_loss:2.3945 train_time:1838525ms step_avg:400.11ms step:4606/6250 train_loss:2.3866 train_time:1838952ms step_avg:400.12ms step:4607/6250 train_loss:2.4244 train_time:1839381ms step_avg:400.13ms step:4608/6250 train_loss:2.4084 train_time:1839816ms step_avg:400.13ms step:4609/6250 train_loss:2.4070 train_time:1840261ms step_avg:400.14ms step:4610/6250 train_loss:2.3545 train_time:1840699ms step_avg:400.15ms step:4611/6250 train_loss:2.3921 train_time:1841127ms step_avg:400.16ms step:4612/6250 train_loss:2.3246 train_time:1841559ms step_avg:400.17ms step:4613/6250 train_loss:2.4258 train_time:1841990ms step_avg:400.17ms step:4614/6250 train_loss:2.5071 train_time:1842428ms step_avg:400.18ms step:4615/6250 train_loss:2.3887 train_time:1842868ms step_avg:400.19ms step:4616/6250 train_loss:2.4812 train_time:1843307ms step_avg:400.20ms step:4617/6250 train_loss:2.3956 train_time:1843744ms step_avg:400.20ms step:4618/6250 train_loss:2.3608 train_time:1844183ms step_avg:400.21ms step:4619/6250 train_loss:2.4155 train_time:1844637ms step_avg:400.23ms step:4620/6250 train_loss:2.3166 train_time:1845088ms step_avg:400.24ms step:4621/6250 train_loss:2.4497 train_time:1845525ms step_avg:400.24ms step:4622/6250 train_loss:2.4529 train_time:1845975ms step_avg:400.25ms step:4623/6250 train_loss:2.3527 train_time:1846428ms step_avg:400.27ms step:4624/6250 train_loss:2.3446 train_time:1846864ms step_avg:400.27ms step:4625/6250 train_loss:2.3911 train_time:1847299ms step_avg:400.28ms step:4626/6250 train_loss:2.3939 train_time:1847749ms step_avg:400.29ms step:4627/6250 train_loss:2.4218 train_time:1848183ms step_avg:400.30ms step:4628/6250 train_loss:2.4354 train_time:1848620ms step_avg:400.31ms step:4629/6250 train_loss:2.4037 train_time:1849056ms step_avg:400.32ms step:4630/6250 train_loss:2.3285 train_time:1849485ms step_avg:400.32ms step:4631/6250 train_loss:2.4284 train_time:1849925ms step_avg:400.33ms step:4632/6250 train_loss:2.4037 train_time:1850348ms step_avg:400.34ms step:4633/6250 train_loss:2.3678 train_time:1850762ms step_avg:400.34ms step:4634/6250 train_loss:2.4153 train_time:1851176ms step_avg:400.34ms step:4635/6250 train_loss:2.4956 train_time:1851588ms step_avg:400.34ms step:4636/6250 train_loss:2.3988 train_time:1852003ms step_avg:400.35ms step:4637/6250 train_loss:2.3810 train_time:1852413ms step_avg:400.35ms step:4638/6250 train_loss:2.3791 train_time:1852824ms step_avg:400.35ms step:4639/6250 train_loss:2.3391 train_time:1853249ms step_avg:400.36ms step:4640/6250 train_loss:2.3826 train_time:1853678ms step_avg:400.36ms step:4641/6250 train_loss:2.4623 train_time:1854105ms step_avg:400.37ms step:4642/6250 train_loss:2.3367 train_time:1854533ms step_avg:400.37ms step:4643/6250 train_loss:2.2973 train_time:1854957ms step_avg:400.38ms step:4644/6250 train_loss:2.4285 train_time:1855380ms step_avg:400.38ms step:4645/6250 train_loss:2.3484 train_time:1855804ms step_avg:400.39ms step:4646/6250 train_loss:2.3878 train_time:1856229ms step_avg:400.39ms step:4647/6250 train_loss:2.3645 train_time:1856657ms step_avg:400.40ms step:4648/6250 train_loss:2.3875 train_time:1857084ms step_avg:400.41ms step:4649/6250 train_loss:2.4932 train_time:1857507ms step_avg:400.41ms step:4650/6250 train_loss:2.3537 train_time:1857932ms step_avg:400.42ms step:4651/6250 train_loss:2.4340 train_time:1858356ms step_avg:400.42ms step:4652/6250 train_loss:2.3800 train_time:1858783ms step_avg:400.43ms step:4653/6250 train_loss:2.3352 train_time:1859211ms step_avg:400.43ms step:4654/6250 train_loss:2.3274 train_time:1859642ms step_avg:400.44ms step:4655/6250 train_loss:2.3373 train_time:1860071ms step_avg:400.45ms step:4656/6250 train_loss:2.4810 train_time:1860501ms step_avg:400.45ms step:4657/6250 train_loss:2.3893 train_time:1860929ms step_avg:400.46ms step:4658/6250 train_loss:2.4381 train_time:1861356ms step_avg:400.46ms step:4659/6250 train_loss:2.4434 train_time:1861787ms step_avg:400.47ms step:4660/6250 train_loss:2.4177 train_time:1862211ms step_avg:400.48ms step:4661/6250 train_loss:2.4132 train_time:1862628ms step_avg:400.48ms step:4662/6250 train_loss:2.3718 train_time:1863047ms step_avg:400.48ms step:4663/6250 train_loss:2.3516 train_time:1863464ms step_avg:400.49ms step:4664/6250 train_loss:2.5208 train_time:1863881ms step_avg:400.49ms step:4665/6250 train_loss:2.3650 train_time:1864303ms step_avg:400.49ms step:4666/6250 train_loss:2.3973 train_time:1864727ms step_avg:400.50ms step:4667/6250 train_loss:2.3746 train_time:1865149ms step_avg:400.50ms step:4668/6250 train_loss:2.4643 train_time:1865567ms step_avg:400.51ms step:4669/6250 train_loss:2.4090 train_time:1865988ms step_avg:400.51ms step:4670/6250 train_loss:2.4240 train_time:1866405ms step_avg:400.52ms step:4671/6250 train_loss:2.4103 train_time:1866826ms step_avg:400.52ms step:4672/6250 train_loss:2.3475 train_time:1867245ms step_avg:400.52ms step:4673/6250 train_loss:2.3577 train_time:1867672ms step_avg:400.53ms step:4674/6250 train_loss:2.3202 train_time:1868107ms step_avg:400.54ms step:4675/6250 train_loss:2.3414 train_time:1868538ms step_avg:400.54ms step:4676/6250 train_loss:2.3924 train_time:1868968ms step_avg:400.55ms step:4677/6250 train_loss:2.3847 train_time:1869396ms step_avg:400.56ms step:4678/6250 train_loss:2.4273 train_time:1869822ms step_avg:400.56ms step:4679/6250 train_loss:2.3784 train_time:1870249ms step_avg:400.57ms step:4680/6250 train_loss:2.3190 train_time:1870673ms step_avg:400.57ms step:4681/6250 train_loss:2.3992 train_time:1871103ms step_avg:400.58ms step:4682/6250 train_loss:2.4277 train_time:1871529ms step_avg:400.58ms step:4683/6250 train_loss:2.4427 train_time:1871960ms step_avg:400.59ms step:4684/6250 train_loss:2.4421 train_time:1872389ms step_avg:400.60ms step:4685/6250 train_loss:2.3246 train_time:1872820ms step_avg:400.60ms step:4686/6250 train_loss:2.4099 train_time:1873251ms step_avg:400.61ms step:4687/6250 train_loss:2.4133 train_time:1873685ms step_avg:400.62ms step:4688/6250 train_loss:2.3786 train_time:1874111ms step_avg:400.62ms step:4689/6250 train_loss:2.4068 train_time:1874562ms step_avg:400.63ms step:4690/6250 train_loss:2.4722 train_time:1875004ms step_avg:400.64ms step:4691/6250 train_loss:2.3873 train_time:1875456ms step_avg:400.65ms step:4692/6250 train_loss:2.3686 train_time:1875924ms step_avg:400.67ms step:4693/6250 train_loss:2.3709 train_time:1876389ms step_avg:400.68ms step:4694/6250 train_loss:2.3597 train_time:1876845ms step_avg:400.69ms step:4695/6250 train_loss:2.4766 train_time:1877295ms step_avg:400.70ms step:4696/6250 train_loss:2.4503 train_time:1877746ms step_avg:400.71ms step:4697/6250 train_loss:2.3948 train_time:1878198ms step_avg:400.72ms step:4698/6250 train_loss:2.3945 train_time:1878647ms step_avg:400.74ms step:4699/6250 train_loss:2.3677 train_time:1879099ms step_avg:400.75ms step:4700/6250 train_loss:2.3662 train_time:1879569ms step_avg:400.76ms step:4701/6250 train_loss:2.4459 train_time:1880025ms step_avg:400.77ms step:4702/6250 train_loss:2.4083 train_time:1880496ms step_avg:400.79ms step:4703/6250 train_loss:2.4636 train_time:1880964ms step_avg:400.80ms step:4704/6250 train_loss:2.4732 train_time:1881433ms step_avg:400.82ms step:4705/6250 train_loss:2.3203 train_time:1881914ms step_avg:400.83ms step:4706/6250 train_loss:2.4009 train_time:1882371ms step_avg:400.85ms step:4707/6250 train_loss:2.4369 train_time:1882828ms step_avg:400.86ms step:4708/6250 train_loss:2.2723 train_time:1883286ms step_avg:400.87ms step:4709/6250 train_loss:2.4088 train_time:1883732ms step_avg:400.88ms step:4710/6250 train_loss:2.4510 train_time:1884184ms step_avg:400.89ms step:4711/6250 train_loss:2.4373 train_time:1884637ms step_avg:400.90ms step:4712/6250 train_loss:2.3670 train_time:1885092ms step_avg:400.91ms step:4713/6250 train_loss:2.4725 train_time:1885534ms step_avg:400.92ms step:4714/6250 train_loss:2.4194 train_time:1885991ms step_avg:400.93ms step:4715/6250 train_loss:2.4212 train_time:1886436ms step_avg:400.94ms step:4716/6250 train_loss:2.4027 train_time:1886877ms step_avg:400.95ms step:4717/6250 train_loss:2.3520 train_time:1887308ms step_avg:400.96ms step:4718/6250 train_loss:2.4796 train_time:1887752ms step_avg:400.97ms step:4719/6250 train_loss:2.5284 train_time:1888192ms step_avg:400.98ms step:4720/6250 train_loss:2.5054 train_time:1888633ms step_avg:400.98ms step:4721/6250 train_loss:2.4645 train_time:1889074ms step_avg:400.99ms step:4722/6250 train_loss:2.3409 train_time:1889511ms step_avg:401.00ms step:4723/6250 train_loss:2.3340 train_time:1889952ms step_avg:401.01ms step:4724/6250 train_loss:2.4170 train_time:1890390ms step_avg:401.02ms step:4725/6250 train_loss:2.3204 train_time:1890830ms step_avg:401.02ms step:4726/6250 train_loss:2.4079 train_time:1891268ms step_avg:401.03ms step:4727/6250 train_loss:2.3993 train_time:1891710ms step_avg:401.04ms step:4728/6250 train_loss:2.3948 train_time:1892148ms step_avg:401.05ms step:4729/6250 train_loss:2.3175 train_time:1892588ms step_avg:401.06ms step:4730/6250 train_loss:2.2712 train_time:1893026ms step_avg:401.06ms step:4731/6250 train_loss:2.3180 train_time:1893464ms step_avg:401.07ms step:4732/6250 train_loss:2.4036 train_time:1893899ms step_avg:401.08ms step:4733/6250 train_loss:2.4700 train_time:1894341ms step_avg:401.09ms step:4734/6250 train_loss:2.3858 train_time:1894780ms step_avg:401.10ms step:4735/6250 train_loss:2.4951 train_time:1895215ms step_avg:401.10ms step:4736/6250 train_loss:2.3649 train_time:1895658ms step_avg:401.11ms step:4737/6250 train_loss:2.4687 train_time:1896095ms step_avg:401.12ms step:4738/6250 train_loss:2.4138 train_time:1896533ms step_avg:401.13ms step:4739/6250 train_loss:2.4088 train_time:1896974ms step_avg:401.14ms step:4740/6250 train_loss:2.3999 train_time:1897418ms step_avg:401.15ms step:4741/6250 train_loss:2.4438 train_time:1897858ms step_avg:401.15ms step:4742/6250 train_loss:2.4314 train_time:1898297ms step_avg:401.16ms step:4743/6250 train_loss:2.3432 train_time:1898741ms step_avg:401.17ms step:4744/6250 train_loss:2.3693 train_time:1899177ms step_avg:401.18ms step:4745/6250 train_loss:2.4442 train_time:1899614ms step_avg:401.19ms step:4746/6250 train_loss:2.3902 train_time:1900050ms step_avg:401.19ms step:4747/6250 train_loss:2.4691 train_time:1900486ms step_avg:401.20ms step:4748/6250 train_loss:2.4938 train_time:1900928ms step_avg:401.21ms step:4749/6250 train_loss:2.4565 train_time:1901367ms step_avg:401.22ms step:4750/6250 train_loss:2.4876 train_time:1901805ms step_avg:401.22ms step:4751/6250 train_loss:2.4656 train_time:1902242ms step_avg:401.23ms step:4752/6250 train_loss:2.4073 train_time:1902681ms step_avg:401.24ms step:4753/6250 train_loss:2.4541 train_time:1903119ms step_avg:401.25ms step:4754/6250 train_loss:2.4793 train_time:1903554ms step_avg:401.26ms step:4755/6250 train_loss:2.4677 train_time:1903995ms step_avg:401.26ms step:4756/6250 train_loss:2.4426 train_time:1904434ms step_avg:401.27ms step:4757/6250 train_loss:2.3501 train_time:1904873ms step_avg:401.28ms step:4758/6250 train_loss:2.4807 train_time:1905312ms step_avg:401.29ms step:4759/6250 train_loss:2.4595 train_time:1905762ms step_avg:401.30ms step:4760/6250 train_loss:2.4826 train_time:1906209ms step_avg:401.31ms step:4761/6250 train_loss:2.3621 train_time:1906661ms step_avg:401.32ms step:4762/6250 train_loss:2.3219 train_time:1907115ms step_avg:401.33ms step:4763/6250 train_loss:2.2704 train_time:1907557ms step_avg:401.34ms step:4764/6250 train_loss:2.3883 train_time:1907997ms step_avg:401.35ms step:4765/6250 train_loss:2.3556 train_time:1908433ms step_avg:401.35ms step:4766/6250 train_loss:2.3572 train_time:1908873ms step_avg:401.36ms step:4767/6250 train_loss:2.3954 train_time:1909311ms step_avg:401.37ms step:4768/6250 train_loss:2.4734 train_time:1909746ms step_avg:401.38ms step:4769/6250 train_loss:2.3325 train_time:1910181ms step_avg:401.38ms step:4770/6250 train_loss:2.4321 train_time:1910619ms step_avg:401.39ms step:4771/6250 train_loss:2.3665 train_time:1911055ms step_avg:401.40ms step:4772/6250 train_loss:2.4063 train_time:1911492ms step_avg:401.41ms step:4773/6250 train_loss:2.3343 train_time:1911929ms step_avg:401.41ms step:4774/6250 train_loss:2.3569 train_time:1912373ms step_avg:401.42ms step:4775/6250 train_loss:2.3561 train_time:1912808ms step_avg:401.43ms step:4776/6250 train_loss:2.4249 train_time:1913243ms step_avg:401.44ms step:4777/6250 train_loss:2.4360 train_time:1913681ms step_avg:401.44ms step:4778/6250 train_loss:2.3212 train_time:1914119ms step_avg:401.45ms step:4779/6250 train_loss:2.3909 train_time:1914553ms step_avg:401.46ms step:4780/6250 train_loss:2.3415 train_time:1914990ms step_avg:401.47ms step:4781/6250 train_loss:2.4014 train_time:1915427ms step_avg:401.47ms step:4782/6250 train_loss:2.3971 train_time:1915866ms step_avg:401.48ms step:4783/6250 train_loss:2.3358 train_time:1916301ms step_avg:401.49ms step:4784/6250 train_loss:2.3835 train_time:1916739ms step_avg:401.50ms step:4785/6250 train_loss:2.3802 train_time:1917177ms step_avg:401.50ms step:4786/6250 train_loss:2.4452 train_time:1917616ms step_avg:401.51ms step:4787/6250 train_loss:2.3829 train_time:1918055ms step_avg:401.52ms step:4788/6250 train_loss:2.3646 train_time:1918490ms step_avg:401.53ms step:4789/6250 train_loss:2.3975 train_time:1918928ms step_avg:401.53ms step:4790/6250 train_loss:2.5265 train_time:1919368ms step_avg:401.54ms step:4791/6250 train_loss:2.5056 train_time:1919801ms step_avg:401.55ms step:4792/6250 train_loss:2.3889 train_time:1920241ms step_avg:401.56ms step:4793/6250 train_loss:2.4772 train_time:1920681ms step_avg:401.56ms step:4794/6250 train_loss:2.4717 train_time:1921113ms step_avg:401.57ms step:4795/6250 train_loss:2.4647 train_time:1921552ms step_avg:401.58ms step:4796/6250 train_loss:2.4295 train_time:1921989ms step_avg:401.59ms step:4797/6250 train_loss:2.3541 train_time:1922425ms step_avg:401.59ms step:4798/6250 train_loss:2.4346 train_time:1922862ms step_avg:401.60ms step:4799/6250 train_loss:2.3693 train_time:1923298ms step_avg:401.61ms step:4800/6250 train_loss:2.4583 train_time:1923744ms step_avg:401.62ms step:4801/6250 train_loss:2.3174 train_time:1924182ms step_avg:401.62ms step:4802/6250 train_loss:2.3458 train_time:1924616ms step_avg:401.63ms step:4803/6250 train_loss:2.3746 train_time:1925050ms step_avg:401.64ms step:4804/6250 train_loss:2.2939 train_time:1925488ms step_avg:401.65ms step:4805/6250 train_loss:2.3636 train_time:1925927ms step_avg:401.65ms step:4806/6250 train_loss:2.3723 train_time:1926362ms step_avg:401.66ms step:4807/6250 train_loss:2.4466 train_time:1926797ms step_avg:401.67ms step:4808/6250 train_loss:2.3799 train_time:1927232ms step_avg:401.67ms step:4809/6250 train_loss:2.3142 train_time:1927668ms step_avg:401.68ms step:4810/6250 train_loss:2.4062 train_time:1928104ms step_avg:401.69ms step:4811/6250 train_loss:2.3437 train_time:1928542ms step_avg:401.70ms step:4812/6250 train_loss:2.3159 train_time:1928978ms step_avg:401.70ms step:4813/6250 train_loss:2.3691 train_time:1929417ms step_avg:401.71ms step:4814/6250 train_loss:2.3888 train_time:1929855ms step_avg:401.72ms step:4815/6250 train_loss:2.3635 train_time:1930295ms step_avg:401.73ms step:4816/6250 train_loss:2.3735 train_time:1930734ms step_avg:401.73ms step:4817/6250 train_loss:2.5030 train_time:1931172ms step_avg:401.74ms step:4818/6250 train_loss:2.4133 train_time:1931609ms step_avg:401.75ms step:4819/6250 train_loss:2.4367 train_time:1932045ms step_avg:401.76ms step:4820/6250 train_loss:2.3636 train_time:1932478ms step_avg:401.76ms step:4821/6250 train_loss:2.3746 train_time:1932913ms step_avg:401.77ms step:4822/6250 train_loss:2.3778 train_time:1933349ms step_avg:401.78ms step:4823/6250 train_loss:2.3326 train_time:1933786ms step_avg:401.78ms step:4824/6250 train_loss:2.3695 train_time:1934223ms step_avg:401.79ms step:4825/6250 train_loss:2.3914 train_time:1934658ms step_avg:401.80ms step:4826/6250 train_loss:2.3566 train_time:1935094ms step_avg:401.81ms step:4827/6250 train_loss:2.3569 train_time:1935532ms step_avg:401.81ms step:4828/6250 train_loss:2.3962 train_time:1935968ms step_avg:401.82ms step:4829/6250 train_loss:2.3921 train_time:1936403ms step_avg:401.83ms step:4830/6250 train_loss:2.3530 train_time:1936841ms step_avg:401.83ms step:4831/6250 train_loss:2.4002 train_time:1937277ms step_avg:401.84ms step:4832/6250 train_loss:2.2624 train_time:1937716ms step_avg:401.85ms step:4833/6250 train_loss:2.3582 train_time:1938151ms step_avg:401.86ms step:4834/6250 train_loss:2.3833 train_time:1938588ms step_avg:401.86ms step:4835/6250 train_loss:2.3907 train_time:1939024ms step_avg:401.87ms step:4836/6250 train_loss:2.3748 train_time:1939464ms step_avg:401.88ms step:4837/6250 train_loss:2.3872 train_time:1939900ms step_avg:401.89ms step:4838/6250 train_loss:2.3316 train_time:1940337ms step_avg:401.89ms step:4839/6250 train_loss:2.4910 train_time:1940773ms step_avg:401.90ms step:4840/6250 train_loss:2.3650 train_time:1941209ms step_avg:401.91ms step:4841/6250 train_loss:2.4172 train_time:1941646ms step_avg:401.91ms step:4842/6250 train_loss:2.3870 train_time:1942081ms step_avg:401.92ms step:4843/6250 train_loss:2.3425 train_time:1942520ms step_avg:401.93ms step:4844/6250 train_loss:2.3600 train_time:1942957ms step_avg:401.94ms step:4845/6250 train_loss:2.4062 train_time:1943393ms step_avg:401.94ms step:4846/6250 train_loss:2.3327 train_time:1943830ms step_avg:401.95ms step:4847/6250 train_loss:2.4546 train_time:1944268ms step_avg:401.96ms step:4848/6250 train_loss:2.3927 train_time:1944705ms step_avg:401.96ms step:4849/6250 train_loss:2.2953 train_time:1945141ms step_avg:401.97ms step:4850/6250 train_loss:2.2976 train_time:1945579ms step_avg:401.98ms step:4851/6250 train_loss:2.4335 train_time:1946016ms step_avg:401.99ms step:4852/6250 train_loss:2.3812 train_time:1946455ms step_avg:401.99ms step:4853/6250 train_loss:2.3022 train_time:1946894ms step_avg:402.00ms step:4854/6250 train_loss:2.5111 train_time:1947327ms step_avg:402.01ms step:4855/6250 train_loss:2.3681 train_time:1947767ms step_avg:402.02ms step:4856/6250 train_loss:2.3176 train_time:1948201ms step_avg:402.02ms step:4857/6250 train_loss:2.3374 train_time:1948637ms step_avg:402.03ms step:4858/6250 train_loss:2.3590 train_time:1949071ms step_avg:402.04ms step:4859/6250 train_loss:2.4136 train_time:1949507ms step_avg:402.04ms step:4860/6250 train_loss:2.4704 train_time:1949943ms step_avg:402.05ms step:4861/6250 train_loss:2.4342 train_time:1950380ms step_avg:402.06ms step:4862/6250 train_loss:2.3696 train_time:1950816ms step_avg:402.06ms step:4863/6250 train_loss:2.4373 train_time:1951249ms step_avg:402.07ms step:4864/6250 train_loss:2.4421 train_time:1951686ms step_avg:402.08ms step:4865/6250 train_loss:2.4428 train_time:1952124ms step_avg:402.09ms step:4866/6250 train_loss:2.4611 train_time:1952561ms step_avg:402.09ms step:4867/6250 train_loss:2.4062 train_time:1952996ms step_avg:402.10ms step:4868/6250 train_loss:2.4353 train_time:1953430ms step_avg:402.11ms step:4869/6250 train_loss:2.4103 train_time:1953865ms step_avg:402.11ms step:4870/6250 train_loss:2.3912 train_time:1954300ms step_avg:402.12ms step:4871/6250 train_loss:2.3919 train_time:1954732ms step_avg:402.13ms step:4872/6250 train_loss:2.3398 train_time:1955169ms step_avg:402.13ms step:4873/6250 train_loss:2.4018 train_time:1955605ms step_avg:402.14ms step:4874/6250 train_loss:2.4700 train_time:1956042ms step_avg:402.15ms step:4875/6250 train_loss:2.3803 train_time:1956476ms step_avg:402.15ms step:4876/6250 train_loss:2.4388 train_time:1956911ms step_avg:402.16ms step:4877/6250 train_loss:2.3159 train_time:1957344ms step_avg:402.17ms step:4878/6250 train_loss:2.3872 train_time:1957778ms step_avg:402.17ms step:4879/6250 train_loss:2.3289 train_time:1958211ms step_avg:402.18ms step:4880/6250 train_loss:2.3663 train_time:1958651ms step_avg:402.19ms step:4881/6250 train_loss:2.3168 train_time:1959089ms step_avg:402.19ms step:4882/6250 train_loss:2.4163 train_time:1959524ms step_avg:402.20ms step:4883/6250 train_loss:2.4710 train_time:1959961ms step_avg:402.21ms step:4884/6250 train_loss:2.4086 train_time:1960398ms step_avg:402.22ms step:4885/6250 train_loss:2.3271 train_time:1960840ms step_avg:402.22ms step:4886/6250 train_loss:2.3685 train_time:1961275ms step_avg:402.23ms step:4887/6250 train_loss:2.3921 train_time:1961711ms step_avg:402.24ms step:4888/6250 train_loss:2.3844 train_time:1962147ms step_avg:402.24ms step:4889/6250 train_loss:2.3591 train_time:1962583ms step_avg:402.25ms step:4890/6250 train_loss:2.3589 train_time:1963019ms step_avg:402.26ms step:4891/6250 train_loss:2.3387 train_time:1963452ms step_avg:402.26ms step:4892/6250 train_loss:2.3849 train_time:1963888ms step_avg:402.27ms step:4893/6250 train_loss:2.4419 train_time:1964322ms step_avg:402.28ms step:4894/6250 train_loss:2.3802 train_time:1964760ms step_avg:402.29ms step:4895/6250 train_loss:2.3333 train_time:1965194ms step_avg:402.29ms step:4896/6250 train_loss:2.3704 train_time:1965627ms step_avg:402.30ms step:4897/6250 train_loss:2.3555 train_time:1966061ms step_avg:402.30ms step:4898/6250 train_loss:2.3616 train_time:1966494ms step_avg:402.31ms step:4899/6250 train_loss:2.3445 train_time:1966932ms step_avg:402.32ms step:4900/6250 train_loss:2.3355 train_time:1967368ms step_avg:402.32ms step:4901/6250 train_loss:2.3823 train_time:1967801ms step_avg:402.33ms step:4902/6250 train_loss:2.3419 train_time:1968236ms step_avg:402.34ms step:4903/6250 train_loss:2.3129 train_time:1968669ms step_avg:402.34ms step:4904/6250 train_loss:2.2953 train_time:1969103ms step_avg:402.35ms step:4905/6250 train_loss:2.2982 train_time:1969539ms step_avg:402.36ms step:4906/6250 train_loss:2.4026 train_time:1969973ms step_avg:402.36ms step:4907/6250 train_loss:2.3635 train_time:1970405ms step_avg:402.37ms step:4908/6250 train_loss:2.4350 train_time:1970841ms step_avg:402.38ms step:4909/6250 train_loss:2.3765 train_time:1971275ms step_avg:402.38ms step:4910/6250 train_loss:2.4414 train_time:1971709ms step_avg:402.39ms step:4911/6250 train_loss:2.3782 train_time:1972143ms step_avg:402.40ms step:4912/6250 train_loss:2.3985 train_time:1972578ms step_avg:402.40ms step:4913/6250 train_loss:2.4302 train_time:1973014ms step_avg:402.41ms step:4914/6250 train_loss:2.3856 train_time:1973448ms step_avg:402.42ms step:4915/6250 train_loss:2.3509 train_time:1973883ms step_avg:402.42ms step:4916/6250 train_loss:2.3131 train_time:1974320ms step_avg:402.43ms step:4917/6250 train_loss:2.3587 train_time:1974757ms step_avg:402.44ms step:4918/6250 train_loss:2.4075 train_time:1975192ms step_avg:402.44ms step:4919/6250 train_loss:2.3934 train_time:1975628ms step_avg:402.45ms step:4920/6250 train_loss:2.3924 train_time:1976065ms step_avg:402.46ms step:4921/6250 train_loss:2.3409 train_time:1976501ms step_avg:402.46ms step:4922/6250 train_loss:2.4690 train_time:1976941ms step_avg:402.47ms step:4923/6250 train_loss:2.3270 train_time:1977377ms step_avg:402.48ms step:4924/6250 train_loss:2.3841 train_time:1977815ms step_avg:402.49ms step:4925/6250 train_loss:2.2762 train_time:1978248ms step_avg:402.49ms step:4926/6250 train_loss:2.3433 train_time:1978683ms step_avg:402.50ms step:4927/6250 train_loss:2.3655 train_time:1979117ms step_avg:402.50ms step:4928/6250 train_loss:2.4670 train_time:1979554ms step_avg:402.51ms step:4929/6250 train_loss:2.3377 train_time:1979990ms step_avg:402.52ms step:4930/6250 train_loss:2.4103 train_time:1980427ms step_avg:402.53ms step:4931/6250 train_loss:2.4112 train_time:1980861ms step_avg:402.53ms step:4932/6250 train_loss:2.3401 train_time:1981298ms step_avg:402.54ms step:4933/6250 train_loss:2.3990 train_time:1981735ms step_avg:402.55ms step:4934/6250 train_loss:2.4022 train_time:1982169ms step_avg:402.55ms step:4935/6250 train_loss:2.3635 train_time:1982606ms step_avg:402.56ms step:4936/6250 train_loss:2.4071 train_time:1983046ms step_avg:402.57ms step:4937/6250 train_loss:2.3808 train_time:1983482ms step_avg:402.57ms step:4938/6250 train_loss:2.3942 train_time:1983915ms step_avg:402.58ms step:4939/6250 train_loss:2.4057 train_time:1984351ms step_avg:402.59ms step:4940/6250 train_loss:2.4661 train_time:1984791ms step_avg:402.59ms step:4941/6250 train_loss:2.5145 train_time:1985227ms step_avg:402.60ms step:4942/6250 train_loss:2.3913 train_time:1985665ms step_avg:402.61ms step:4943/6250 train_loss:2.3345 train_time:1986099ms step_avg:402.61ms step:4944/6250 train_loss:2.3470 train_time:1986535ms step_avg:402.62ms step:4945/6250 train_loss:2.3582 train_time:1986968ms step_avg:402.63ms step:4946/6250 train_loss:2.3687 train_time:1987401ms step_avg:402.63ms step:4947/6250 train_loss:2.4622 train_time:1987834ms step_avg:402.64ms step:4948/6250 train_loss:2.3689 train_time:1988264ms step_avg:402.65ms step:4949/6250 train_loss:2.3330 train_time:1988699ms step_avg:402.65ms step:4950/6250 train_loss:2.3218 train_time:1989135ms step_avg:402.66ms step:4951/6250 train_loss:2.3152 train_time:1989565ms step_avg:402.66ms step:4952/6250 train_loss:2.3879 train_time:1989998ms step_avg:402.67ms step:4953/6250 train_loss:2.3259 train_time:1990430ms step_avg:402.68ms step:4954/6250 train_loss:2.5271 train_time:1990866ms step_avg:402.68ms step:4955/6250 train_loss:2.3934 train_time:1991301ms step_avg:402.69ms step:4956/6250 train_loss:2.4595 train_time:1991734ms step_avg:402.70ms step:4957/6250 train_loss:2.3634 train_time:1992166ms step_avg:402.70ms step:4958/6250 train_loss:2.3096 train_time:1992601ms step_avg:402.71ms step:4959/6250 train_loss:2.3215 train_time:1993031ms step_avg:402.71ms step:4960/6250 train_loss:2.3964 train_time:1993465ms step_avg:402.72ms step:4961/6250 train_loss:2.5139 train_time:1993894ms step_avg:402.73ms step:4962/6250 train_loss:2.3974 train_time:1994331ms step_avg:402.73ms step:4963/6250 train_loss:2.4120 train_time:1994762ms step_avg:402.74ms step:4964/6250 train_loss:2.4048 train_time:1995194ms step_avg:402.74ms step:4965/6250 train_loss:2.4273 train_time:1995629ms step_avg:402.75ms step:4966/6250 train_loss:2.4188 train_time:1996062ms step_avg:402.76ms step:4967/6250 train_loss:2.3325 train_time:1996497ms step_avg:402.76ms step:4968/6250 train_loss:2.4067 train_time:1996927ms step_avg:402.77ms step:4969/6250 train_loss:2.4048 train_time:1997360ms step_avg:402.77ms step:4970/6250 train_loss:2.4028 train_time:1997792ms step_avg:402.78ms step:4971/6250 train_loss:2.4415 train_time:1998226ms step_avg:402.79ms step:4972/6250 train_loss:2.3859 train_time:1998662ms step_avg:402.79ms step:4973/6250 train_loss:2.3850 train_time:1999096ms step_avg:402.80ms step:4974/6250 train_loss:2.3162 train_time:1999530ms step_avg:402.81ms step:4975/6250 train_loss:2.3106 train_time:1999961ms step_avg:402.81ms step:4976/6250 train_loss:2.3822 train_time:2000395ms step_avg:402.82ms step:4977/6250 train_loss:2.4469 train_time:2000827ms step_avg:402.82ms step:4978/6250 train_loss:2.4052 train_time:2001259ms step_avg:402.83ms step:4979/6250 train_loss:2.4024 train_time:2001693ms step_avg:402.84ms step:4980/6250 train_loss:2.3066 train_time:2002126ms step_avg:402.84ms step:4981/6250 train_loss:2.4410 train_time:2002557ms step_avg:402.85ms step:4982/6250 train_loss:2.3028 train_time:2002991ms step_avg:402.85ms step:4983/6250 train_loss:2.3346 train_time:2003421ms step_avg:402.86ms step:4984/6250 train_loss:2.3701 train_time:2003854ms step_avg:402.87ms step:4985/6250 train_loss:2.4937 train_time:2004284ms step_avg:402.87ms step:4986/6250 train_loss:2.4594 train_time:2004719ms step_avg:402.88ms step:4987/6250 train_loss:2.4117 train_time:2005150ms step_avg:402.88ms step:4988/6250 train_loss:2.3678 train_time:2005585ms step_avg:402.89ms step:4989/6250 train_loss:2.3165 train_time:2006015ms step_avg:402.90ms step:4990/6250 train_loss:2.2943 train_time:2006445ms step_avg:402.90ms step:4991/6250 train_loss:2.3361 train_time:2006877ms step_avg:402.91ms step:4992/6250 train_loss:2.3972 train_time:2007308ms step_avg:402.91ms step:4993/6250 train_loss:2.3344 train_time:2007743ms step_avg:402.92ms step:4994/6250 train_loss:2.3455 train_time:2008176ms step_avg:402.92ms step:4995/6250 train_loss:2.4767 train_time:2008603ms step_avg:402.93ms step:4996/6250 train_loss:2.3131 train_time:2009035ms step_avg:402.94ms step:4997/6250 train_loss:2.3227 train_time:2009468ms step_avg:402.94ms step:4998/6250 train_loss:2.2785 train_time:2009900ms step_avg:402.95ms step:4999/6250 train_loss:2.4595 train_time:2010334ms step_avg:402.95ms step:5000/6250 train_loss:2.4060 train_time:2010769ms step_avg:402.96ms step:5001/6250 train_loss:2.3646 train_time:2011205ms step_avg:402.97ms step:5002/6250 train_loss:2.3853 train_time:2011639ms step_avg:402.97ms step:5003/6250 train_loss:2.4196 train_time:2012072ms step_avg:402.98ms step:5004/6250 train_loss:2.4194 train_time:2012508ms step_avg:402.99ms step:5005/6250 train_loss:2.4477 train_time:2012941ms step_avg:402.99ms step:5006/6250 train_loss:2.4114 train_time:2013375ms step_avg:403.00ms step:5007/6250 train_loss:2.3565 train_time:2013811ms step_avg:403.00ms step:5008/6250 train_loss:2.3737 train_time:2014242ms step_avg:403.01ms step:5009/6250 train_loss:2.4699 train_time:2014675ms step_avg:403.02ms step:5010/6250 train_loss:2.3672 train_time:2015104ms step_avg:403.02ms step:5011/6250 train_loss:2.3802 train_time:2015536ms step_avg:403.03ms step:5012/6250 train_loss:2.3661 train_time:2015970ms step_avg:403.03ms step:5013/6250 train_loss:2.4219 train_time:2016400ms step_avg:403.04ms step:5014/6250 train_loss:2.3754 train_time:2016833ms step_avg:403.04ms step:5015/6250 train_loss:2.4014 train_time:2017266ms step_avg:403.05ms step:5016/6250 train_loss:2.3782 train_time:2017700ms step_avg:403.06ms step:5017/6250 train_loss:2.4357 train_time:2018137ms step_avg:403.06ms step:5018/6250 train_loss:2.4780 train_time:2018574ms step_avg:403.07ms step:5019/6250 train_loss:2.4441 train_time:2019007ms step_avg:403.08ms step:5020/6250 train_loss:2.4472 train_time:2019439ms step_avg:403.08ms step:5021/6250 train_loss:2.4264 train_time:2019869ms step_avg:403.09ms step:5022/6250 train_loss:2.3312 train_time:2020301ms step_avg:403.09ms step:5023/6250 train_loss:2.3974 train_time:2020735ms step_avg:403.10ms step:5024/6250 train_loss:2.4209 train_time:2021165ms step_avg:403.10ms step:5025/6250 train_loss:2.4019 train_time:2021597ms step_avg:403.11ms step:5026/6250 train_loss:2.3808 train_time:2022029ms step_avg:403.12ms step:5027/6250 train_loss:2.4475 train_time:2022465ms step_avg:403.12ms step:5028/6250 train_loss:2.3775 train_time:2022898ms step_avg:403.13ms step:5029/6250 train_loss:2.3706 train_time:2023330ms step_avg:403.13ms step:5030/6250 train_loss:2.3749 train_time:2023765ms step_avg:403.14ms step:5031/6250 train_loss:2.4278 train_time:2024197ms step_avg:403.15ms step:5032/6250 train_loss:2.3682 train_time:2024629ms step_avg:403.15ms step:5033/6250 train_loss:2.3739 train_time:2025061ms step_avg:403.16ms step:5034/6250 train_loss:2.3354 train_time:2025492ms step_avg:403.16ms step:5035/6250 train_loss:2.3471 train_time:2025925ms step_avg:403.17ms step:5036/6250 train_loss:2.4502 train_time:2026355ms step_avg:403.17ms step:5037/6250 train_loss:2.4357 train_time:2026787ms step_avg:403.18ms step:5038/6250 train_loss:2.4581 train_time:2027219ms step_avg:403.19ms step:5039/6250 train_loss:2.4112 train_time:2027650ms step_avg:403.19ms step:5040/6250 train_loss:2.3547 train_time:2028082ms step_avg:403.20ms step:5041/6250 train_loss:2.3976 train_time:2028510ms step_avg:403.20ms step:5042/6250 train_loss:2.4462 train_time:2028943ms step_avg:403.21ms step:5043/6250 train_loss:2.4310 train_time:2029375ms step_avg:403.21ms step:5044/6250 train_loss:2.4219 train_time:2029806ms step_avg:403.22ms step:5045/6250 train_loss:2.3587 train_time:2030241ms step_avg:403.23ms step:5046/6250 train_loss:2.3109 train_time:2030673ms step_avg:403.23ms step:5047/6250 train_loss:2.3979 train_time:2031105ms step_avg:403.24ms step:5048/6250 train_loss:2.4053 train_time:2031537ms step_avg:403.24ms step:5049/6250 train_loss:2.4128 train_time:2031965ms step_avg:403.25ms step:5050/6250 train_loss:2.2513 train_time:2032399ms step_avg:403.25ms step:5051/6250 train_loss:2.4330 train_time:2032833ms step_avg:403.26ms step:5052/6250 train_loss:2.5157 train_time:2033266ms step_avg:403.27ms step:5053/6250 train_loss:2.3792 train_time:2033698ms step_avg:403.27ms step:5054/6250 train_loss:2.4282 train_time:2034129ms step_avg:403.28ms step:5055/6250 train_loss:2.2979 train_time:2034563ms step_avg:403.28ms step:5056/6250 train_loss:2.4067 train_time:2034994ms step_avg:403.29ms step:5057/6250 train_loss:2.3196 train_time:2035429ms step_avg:403.29ms step:5058/6250 train_loss:2.4495 train_time:2035865ms step_avg:403.30ms step:5059/6250 train_loss:2.3761 train_time:2036294ms step_avg:403.31ms step:5060/6250 train_loss:2.4106 train_time:2036726ms step_avg:403.31ms step:5061/6250 train_loss:2.3689 train_time:2037159ms step_avg:403.32ms step:5062/6250 train_loss:2.2912 train_time:2037590ms step_avg:403.32ms step:5063/6250 train_loss:2.4071 train_time:2038019ms step_avg:403.33ms step:5064/6250 train_loss:2.3175 train_time:2038450ms step_avg:403.33ms step:5065/6250 train_loss:2.4297 train_time:2038882ms step_avg:403.34ms step:5066/6250 train_loss:2.4758 train_time:2039313ms step_avg:403.35ms step:5067/6250 train_loss:2.3549 train_time:2039747ms step_avg:403.35ms step:5068/6250 train_loss:2.3960 train_time:2040177ms step_avg:403.36ms step:5069/6250 train_loss:2.3129 train_time:2040609ms step_avg:403.36ms step:5070/6250 train_loss:2.3563 train_time:2041039ms step_avg:403.37ms step:5071/6250 train_loss:2.3270 train_time:2041468ms step_avg:403.37ms step:5072/6250 train_loss:2.3633 train_time:2041899ms step_avg:403.38ms step:5073/6250 train_loss:2.4477 train_time:2042334ms step_avg:403.38ms step:5074/6250 train_loss:2.5203 train_time:2042769ms step_avg:403.39ms step:5075/6250 train_loss:2.3483 train_time:2043202ms step_avg:403.40ms step:5076/6250 train_loss:2.3729 train_time:2043636ms step_avg:403.40ms step:5077/6250 train_loss:2.3956 train_time:2044068ms step_avg:403.41ms step:5078/6250 train_loss:2.2933 train_time:2044499ms step_avg:403.41ms step:5079/6250 train_loss:2.4312 train_time:2044930ms step_avg:403.42ms step:5080/6250 train_loss:2.3896 train_time:2045361ms step_avg:403.42ms step:5081/6250 train_loss:2.4108 train_time:2045794ms step_avg:403.43ms step:5082/6250 train_loss:2.3979 train_time:2046225ms step_avg:403.44ms step:5083/6250 train_loss:2.3383 train_time:2046656ms step_avg:403.44ms step:5084/6250 train_loss:2.4731 train_time:2047084ms step_avg:403.45ms step:5085/6250 train_loss:2.3705 train_time:2047517ms step_avg:403.45ms step:5086/6250 train_loss:2.3351 train_time:2047951ms step_avg:403.46ms step:5087/6250 train_loss:2.4054 train_time:2048384ms step_avg:403.46ms step:5088/6250 train_loss:2.4410 train_time:2048815ms step_avg:403.47ms step:5089/6250 train_loss:2.4019 train_time:2049247ms step_avg:403.47ms step:5090/6250 train_loss:2.4287 train_time:2049680ms step_avg:403.48ms step:5091/6250 train_loss:2.4084 train_time:2050112ms step_avg:403.49ms step:5092/6250 train_loss:2.3567 train_time:2050543ms step_avg:403.49ms step:5093/6250 train_loss:2.3642 train_time:2050975ms step_avg:403.50ms step:5094/6250 train_loss:2.3142 train_time:2051407ms step_avg:403.50ms step:5095/6250 train_loss:2.3858 train_time:2051838ms step_avg:403.51ms step:5096/6250 train_loss:2.3653 train_time:2052268ms step_avg:403.51ms step:5097/6250 train_loss:2.4100 train_time:2052704ms step_avg:403.52ms step:5098/6250 train_loss:2.3870 train_time:2053135ms step_avg:403.52ms step:5099/6250 train_loss:2.2802 train_time:2053568ms step_avg:403.53ms step:5100/6250 train_loss:2.3339 train_time:2053997ms step_avg:403.54ms step:5101/6250 train_loss:2.3534 train_time:2054428ms step_avg:403.54ms step:5102/6250 train_loss:2.3968 train_time:2054861ms step_avg:403.55ms step:5103/6250 train_loss:2.3968 train_time:2055292ms step_avg:403.55ms step:5104/6250 train_loss:2.3617 train_time:2055723ms step_avg:403.56ms step:5105/6250 train_loss:2.4019 train_time:2056155ms step_avg:403.56ms step:5106/6250 train_loss:2.4556 train_time:2056590ms step_avg:403.57ms step:5107/6250 train_loss:2.4500 train_time:2057018ms step_avg:403.57ms step:5108/6250 train_loss:2.4763 train_time:2057451ms step_avg:403.58ms step:5109/6250 train_loss:2.4110 train_time:2057882ms step_avg:403.59ms step:5110/6250 train_loss:2.5197 train_time:2058313ms step_avg:403.59ms step:5111/6250 train_loss:2.3647 train_time:2058743ms step_avg:403.60ms step:5112/6250 train_loss:2.3687 train_time:2059174ms step_avg:403.60ms step:5113/6250 train_loss:2.3762 train_time:2059605ms step_avg:403.61ms step:5114/6250 train_loss:2.3739 train_time:2060033ms step_avg:403.61ms step:5115/6250 train_loss:2.3872 train_time:2060469ms step_avg:403.62ms step:5116/6250 train_loss:2.4724 train_time:2060904ms step_avg:403.62ms step:5117/6250 train_loss:2.3226 train_time:2061334ms step_avg:403.63ms step:5118/6250 train_loss:2.4920 train_time:2061767ms step_avg:403.63ms step:5119/6250 train_loss:2.4065 train_time:2062201ms step_avg:403.64ms step:5120/6250 train_loss:2.3562 train_time:2062635ms step_avg:403.65ms step:5121/6250 train_loss:2.4148 train_time:2063066ms step_avg:403.65ms step:5122/6250 train_loss:2.3614 train_time:2063498ms step_avg:403.66ms step:5123/6250 train_loss:2.3966 train_time:2063934ms step_avg:403.66ms step:5124/6250 train_loss:2.3728 train_time:2064366ms step_avg:403.67ms step:5125/6250 train_loss:2.3849 train_time:2064797ms step_avg:403.67ms step:5126/6250 train_loss:2.4249 train_time:2065228ms step_avg:403.68ms step:5127/6250 train_loss:2.4183 train_time:2065664ms step_avg:403.69ms step:5128/6250 train_loss:2.4031 train_time:2066093ms step_avg:403.69ms step:5129/6250 train_loss:2.3122 train_time:2066523ms step_avg:403.70ms step:5130/6250 train_loss:2.3409 train_time:2066954ms step_avg:403.70ms step:5131/6250 train_loss:2.3893 train_time:2067387ms step_avg:403.71ms step:5132/6250 train_loss:2.2588 train_time:2067818ms step_avg:403.71ms step:5133/6250 train_loss:2.4240 train_time:2068248ms step_avg:403.72ms step:5134/6250 train_loss:2.4293 train_time:2068682ms step_avg:403.72ms step:5135/6250 train_loss:2.3881 train_time:2069115ms step_avg:403.73ms step:5136/6250 train_loss:2.3053 train_time:2069543ms step_avg:403.73ms step:5137/6250 train_loss:2.5035 train_time:2069972ms step_avg:403.74ms step:5138/6250 train_loss:2.3665 train_time:2070402ms step_avg:403.74ms step:5139/6250 train_loss:2.3664 train_time:2070836ms step_avg:403.75ms step:5140/6250 train_loss:2.4201 train_time:2071265ms step_avg:403.76ms step:5141/6250 train_loss:2.3470 train_time:2071696ms step_avg:403.76ms step:5142/6250 train_loss:2.3477 train_time:2072128ms step_avg:403.77ms step:5143/6250 train_loss:2.3669 train_time:2072560ms step_avg:403.77ms step:5144/6250 train_loss:2.4520 train_time:2072992ms step_avg:403.78ms step:5145/6250 train_loss:2.3369 train_time:2073421ms step_avg:403.78ms step:5146/6250 train_loss:2.3126 train_time:2073849ms step_avg:403.79ms step:5147/6250 train_loss:2.3715 train_time:2074280ms step_avg:403.79ms step:5148/6250 train_loss:2.4334 train_time:2074707ms step_avg:403.80ms step:5149/6250 train_loss:2.3872 train_time:2075138ms step_avg:403.80ms step:5150/6250 train_loss:2.4065 train_time:2075565ms step_avg:403.81ms step:5151/6250 train_loss:2.3623 train_time:2075995ms step_avg:403.81ms step:5152/6250 train_loss:2.3090 train_time:2076424ms step_avg:403.82ms step:5153/6250 train_loss:2.4072 train_time:2076855ms step_avg:403.82ms step:5154/6250 train_loss:2.4880 train_time:2077289ms step_avg:403.83ms step:5155/6250 train_loss:2.4396 train_time:2077723ms step_avg:403.83ms step:5156/6250 train_loss:2.4249 train_time:2078152ms step_avg:403.84ms step:5157/6250 train_loss:2.4128 train_time:2078584ms step_avg:403.84ms step:5158/6250 train_loss:2.4069 train_time:2079012ms step_avg:403.85ms step:5159/6250 train_loss:2.4628 train_time:2079441ms step_avg:403.85ms step:5160/6250 train_loss:2.3421 train_time:2079873ms step_avg:403.86ms step:5161/6250 train_loss:2.4240 train_time:2080301ms step_avg:403.86ms step:5162/6250 train_loss:2.4965 train_time:2080729ms step_avg:403.87ms step:5163/6250 train_loss:2.4088 train_time:2081161ms step_avg:403.87ms step:5164/6250 train_loss:2.4225 train_time:2081591ms step_avg:403.88ms step:5165/6250 train_loss:2.3763 train_time:2082021ms step_avg:403.88ms step:5166/6250 train_loss:2.4142 train_time:2082456ms step_avg:403.89ms step:5167/6250 train_loss:2.2915 train_time:2082891ms step_avg:403.90ms step:5168/6250 train_loss:2.3571 train_time:2083322ms step_avg:403.90ms step:5169/6250 train_loss:2.3763 train_time:2083758ms step_avg:403.91ms step:5170/6250 train_loss:2.4155 train_time:2084193ms step_avg:403.91ms step:5171/6250 train_loss:2.4686 train_time:2084626ms step_avg:403.92ms step:5172/6250 train_loss:2.3329 train_time:2085056ms step_avg:403.92ms step:5173/6250 train_loss:2.4135 train_time:2085490ms step_avg:403.93ms step:5174/6250 train_loss:2.3453 train_time:2085920ms step_avg:403.93ms step:5175/6250 train_loss:2.3823 train_time:2086349ms step_avg:403.94ms step:5176/6250 train_loss:2.4022 train_time:2086786ms step_avg:403.95ms step:5177/6250 train_loss:2.4066 train_time:2087215ms step_avg:403.95ms step:5178/6250 train_loss:2.4913 train_time:2087648ms step_avg:403.96ms step:5179/6250 train_loss:2.4418 train_time:2088077ms step_avg:403.96ms step:5180/6250 train_loss:2.3143 train_time:2088508ms step_avg:403.97ms step:5181/6250 train_loss:2.4565 train_time:2088939ms step_avg:403.97ms step:5182/6250 train_loss:2.4324 train_time:2089371ms step_avg:403.98ms step:5183/6250 train_loss:2.3927 train_time:2089808ms step_avg:403.98ms step:5184/6250 train_loss:2.3752 train_time:2090237ms step_avg:403.99ms step:5185/6250 train_loss:2.3371 train_time:2090668ms step_avg:403.99ms step:5186/6250 train_loss:2.3035 train_time:2091101ms step_avg:404.00ms step:5187/6250 train_loss:2.3984 train_time:2091533ms step_avg:404.00ms step:5188/6250 train_loss:2.3886 train_time:2091961ms step_avg:404.01ms step:5189/6250 train_loss:2.4222 train_time:2092391ms step_avg:404.01ms step:5190/6250 train_loss:2.3947 train_time:2092824ms step_avg:404.02ms step:5191/6250 train_loss:2.3444 train_time:2093254ms step_avg:404.03ms step:5192/6250 train_loss:2.4007 train_time:2093683ms step_avg:404.03ms step:5193/6250 train_loss:2.3235 train_time:2094114ms step_avg:404.04ms step:5194/6250 train_loss:2.4646 train_time:2094545ms step_avg:404.04ms step:5195/6250 train_loss:2.3574 train_time:2094976ms step_avg:404.05ms step:5196/6250 train_loss:2.4314 train_time:2095406ms step_avg:404.05ms step:5197/6250 train_loss:2.3539 train_time:2095841ms step_avg:404.06ms step:5198/6250 train_loss:2.3738 train_time:2096271ms step_avg:404.06ms step:5199/6250 train_loss:2.3277 train_time:2096704ms step_avg:404.07ms step:5200/6250 train_loss:2.3723 train_time:2097137ms step_avg:404.07ms step:5201/6250 train_loss:2.4262 train_time:2097568ms step_avg:404.08ms step:5202/6250 train_loss:2.3905 train_time:2097996ms step_avg:404.08ms step:5203/6250 train_loss:2.4094 train_time:2098429ms step_avg:404.09ms step:5204/6250 train_loss:2.4231 train_time:2098863ms step_avg:404.09ms step:5205/6250 train_loss:2.3909 train_time:2099294ms step_avg:404.10ms step:5206/6250 train_loss:2.4069 train_time:2099726ms step_avg:404.10ms step:5207/6250 train_loss:2.3252 train_time:2100158ms step_avg:404.11ms step:5208/6250 train_loss:2.4212 train_time:2100586ms step_avg:404.11ms step:5209/6250 train_loss:2.4140 train_time:2101014ms step_avg:404.12ms step:5210/6250 train_loss:2.4299 train_time:2101444ms step_avg:404.12ms step:5211/6250 train_loss:2.3358 train_time:2101875ms step_avg:404.13ms step:5212/6250 train_loss:2.3398 train_time:2102306ms step_avg:404.13ms step:5213/6250 train_loss:2.4393 train_time:2102741ms step_avg:404.14ms step:5214/6250 train_loss:2.4276 train_time:2103172ms step_avg:404.15ms step:5215/6250 train_loss:2.3485 train_time:2103607ms step_avg:404.15ms step:5216/6250 train_loss:2.3362 train_time:2104036ms step_avg:404.16ms step:5217/6250 train_loss:2.4339 train_time:2104466ms step_avg:404.16ms step:5218/6250 train_loss:2.4250 train_time:2104884ms step_avg:404.16ms step:5219/6250 train_loss:2.4106 train_time:2105278ms step_avg:404.16ms step:5220/6250 train_loss:2.4344 train_time:2105672ms step_avg:404.16ms step:5221/6250 train_loss:2.3744 train_time:2106066ms step_avg:404.16ms step:5222/6250 train_loss:2.4054 train_time:2106459ms step_avg:404.16ms step:5223/6250 train_loss:2.3553 train_time:2106852ms step_avg:404.15ms step:5224/6250 train_loss:2.3231 train_time:2107245ms step_avg:404.15ms step:5225/6250 train_loss:2.4024 train_time:2107636ms step_avg:404.15ms step:5226/6250 train_loss:2.4375 train_time:2108026ms step_avg:404.15ms step:5227/6250 train_loss:2.3192 train_time:2108416ms step_avg:404.14ms step:5228/6250 train_loss:2.3603 train_time:2108809ms step_avg:404.14ms step:5229/6250 train_loss:2.4087 train_time:2109198ms step_avg:404.14ms step:5230/6250 train_loss:2.3060 train_time:2109586ms step_avg:404.14ms step:5231/6250 train_loss:2.4961 train_time:2109978ms step_avg:404.13ms step:5232/6250 train_loss:2.3744 train_time:2110365ms step_avg:404.13ms step:5233/6250 train_loss:2.4193 train_time:2110755ms step_avg:404.13ms step:5234/6250 train_loss:2.3201 train_time:2111143ms step_avg:404.12ms step:5235/6250 train_loss:2.4538 train_time:2111536ms step_avg:404.12ms step:5236/6250 train_loss:2.4184 train_time:2111926ms step_avg:404.12ms step:5237/6250 train_loss:2.3254 train_time:2112318ms step_avg:404.12ms step:5238/6250 train_loss:2.2836 train_time:2112711ms step_avg:404.11ms step:5239/6250 train_loss:2.4010 train_time:2113099ms step_avg:404.11ms step:5240/6250 train_loss:2.4463 train_time:2113488ms step_avg:404.11ms step:5241/6250 train_loss:2.3530 train_time:2113878ms step_avg:404.11ms step:5242/6250 train_loss:2.3426 train_time:2114270ms step_avg:404.10ms step:5243/6250 train_loss:2.3875 train_time:2114659ms step_avg:404.10ms step:5244/6250 train_loss:2.2797 train_time:2115048ms step_avg:404.10ms step:5245/6250 train_loss:2.3475 train_time:2115437ms step_avg:404.09ms step:5246/6250 train_loss:2.3203 train_time:2115830ms step_avg:404.09ms step:5247/6250 train_loss:2.3549 train_time:2116217ms step_avg:404.09ms step:5248/6250 train_loss:2.4038 train_time:2116608ms step_avg:404.09ms step:5249/6250 train_loss:2.3453 train_time:2116996ms step_avg:404.08ms step:5250/6250 train_loss:2.4220 train_time:2117385ms step_avg:404.08ms step:5251/6250 train_loss:2.4307 train_time:2117776ms step_avg:404.08ms step:5252/6250 train_loss:2.3938 train_time:2118167ms step_avg:404.08ms step:5253/6250 train_loss:2.3205 train_time:2118556ms step_avg:404.07ms step:5254/6250 train_loss:2.3876 train_time:2118943ms step_avg:404.07ms step:5255/6250 train_loss:2.3821 train_time:2119336ms step_avg:404.07ms step:5256/6250 train_loss:2.3318 train_time:2119724ms step_avg:404.06ms step:5257/6250 train_loss:2.3301 train_time:2120113ms step_avg:404.06ms step:5258/6250 train_loss:2.4480 train_time:2120502ms step_avg:404.06ms step:5259/6250 train_loss:2.3319 train_time:2120893ms step_avg:404.06ms step:5260/6250 train_loss:2.4021 train_time:2121284ms step_avg:404.05ms step:5261/6250 train_loss:2.4169 train_time:2121673ms step_avg:404.05ms step:5262/6250 train_loss:2.4124 train_time:2122063ms step_avg:404.05ms step:5263/6250 train_loss:2.4425 train_time:2122453ms step_avg:404.05ms step:5264/6250 train_loss:2.3599 train_time:2122843ms step_avg:404.04ms step:5265/6250 train_loss:2.3859 train_time:2123231ms step_avg:404.04ms step:5266/6250 train_loss:2.3889 train_time:2123622ms step_avg:404.04ms step:5267/6250 train_loss:2.4544 train_time:2124011ms step_avg:404.03ms step:5268/6250 train_loss:2.4102 train_time:2124400ms step_avg:404.03ms step:5269/6250 train_loss:2.3206 train_time:2124789ms step_avg:404.03ms step:5270/6250 train_loss:2.4185 train_time:2125180ms step_avg:404.03ms step:5271/6250 train_loss:2.3252 train_time:2125569ms step_avg:404.02ms step:5272/6250 train_loss:2.3112 train_time:2125957ms step_avg:404.02ms step:5273/6250 train_loss:2.2748 train_time:2126345ms step_avg:404.02ms step:5274/6250 train_loss:2.3774 train_time:2126734ms step_avg:404.01ms step:5275/6250 train_loss:2.3948 train_time:2127124ms step_avg:404.01ms step:5276/6250 train_loss:2.3938 train_time:2127512ms step_avg:404.01ms step:5277/6250 train_loss:2.4143 train_time:2127900ms step_avg:404.01ms step:5278/6250 train_loss:2.4171 train_time:2128288ms step_avg:404.00ms step:5279/6250 train_loss:2.4284 train_time:2128677ms step_avg:404.00ms step:5280/6250 train_loss:2.4341 train_time:2129065ms step_avg:404.00ms step:5281/6250 train_loss:2.3377 train_time:2129455ms step_avg:403.99ms step:5282/6250 train_loss:2.4349 train_time:2129846ms step_avg:403.99ms step:5283/6250 train_loss:2.3491 train_time:2130233ms step_avg:403.99ms step:5284/6250 train_loss:2.4322 train_time:2130621ms step_avg:403.99ms step:5285/6250 train_loss:2.3715 train_time:2131010ms step_avg:403.98ms step:5286/6250 train_loss:2.3004 train_time:2131399ms step_avg:403.98ms step:5287/6250 train_loss:2.3043 train_time:2131788ms step_avg:403.98ms step:5288/6250 train_loss:2.3855 train_time:2132175ms step_avg:403.97ms step:5289/6250 train_loss:2.3770 train_time:2132565ms step_avg:403.97ms step:5290/6250 train_loss:2.3796 train_time:2132950ms step_avg:403.97ms step:5291/6250 train_loss:2.3144 train_time:2133339ms step_avg:403.96ms step:5292/6250 train_loss:2.3597 train_time:2133727ms step_avg:403.96ms step:5293/6250 train_loss:2.4690 train_time:2134115ms step_avg:403.96ms step:5294/6250 train_loss:2.3142 train_time:2134503ms step_avg:403.96ms step:5295/6250 train_loss:2.3730 train_time:2134891ms step_avg:403.95ms step:5296/6250 train_loss:2.3541 train_time:2135279ms step_avg:403.95ms step:5297/6250 train_loss:2.3264 train_time:2135669ms step_avg:403.95ms step:5298/6250 train_loss:2.4573 train_time:2136055ms step_avg:403.94ms step:5299/6250 train_loss:2.4147 train_time:2136447ms step_avg:403.94ms step:5300/6250 train_loss:2.3466 train_time:2136835ms step_avg:403.94ms step:5301/6250 train_loss:2.3153 train_time:2137223ms step_avg:403.94ms step:5302/6250 train_loss:2.3637 train_time:2137613ms step_avg:403.93ms step:5303/6250 train_loss:2.3988 train_time:2138000ms step_avg:403.93ms step:5304/6250 train_loss:2.4225 train_time:2138389ms step_avg:403.93ms step:5305/6250 train_loss:2.3996 train_time:2138779ms step_avg:403.92ms step:5306/6250 train_loss:2.3754 train_time:2139166ms step_avg:403.92ms step:5307/6250 train_loss:2.3668 train_time:2139555ms step_avg:403.92ms step:5308/6250 train_loss:2.4049 train_time:2139942ms step_avg:403.92ms step:5309/6250 train_loss:2.2804 train_time:2140331ms step_avg:403.91ms step:5310/6250 train_loss:2.4565 train_time:2140719ms step_avg:403.91ms step:5311/6250 train_loss:2.3923 train_time:2141106ms step_avg:403.91ms step:5312/6250 train_loss:2.3723 train_time:2141493ms step_avg:403.90ms step:5313/6250 train_loss:2.3951 train_time:2141881ms step_avg:403.90ms step:5314/6250 train_loss:2.3251 train_time:2142273ms step_avg:403.90ms step:5315/6250 train_loss:2.3898 train_time:2142663ms step_avg:403.89ms step:5316/6250 train_loss:2.3135 train_time:2143052ms step_avg:403.89ms step:5317/6250 train_loss:2.4802 train_time:2143440ms step_avg:403.89ms step:5318/6250 train_loss:2.3856 train_time:2143829ms step_avg:403.89ms step:5319/6250 train_loss:2.3826 train_time:2144216ms step_avg:403.88ms step:5320/6250 train_loss:2.3438 train_time:2144604ms step_avg:403.88ms step:5321/6250 train_loss:2.3848 train_time:2144992ms step_avg:403.88ms step:5322/6250 train_loss:2.4142 train_time:2145381ms step_avg:403.87ms step:5323/6250 train_loss:2.3397 train_time:2145767ms step_avg:403.87ms step:5324/6250 train_loss:2.4077 train_time:2146157ms step_avg:403.87ms step:5325/6250 train_loss:2.4268 train_time:2146547ms step_avg:403.87ms step:5326/6250 train_loss:2.4225 train_time:2146934ms step_avg:403.86ms step:5327/6250 train_loss:2.3515 train_time:2147323ms step_avg:403.86ms step:5328/6250 train_loss:2.3962 train_time:2147713ms step_avg:403.86ms step:5329/6250 train_loss:2.4469 train_time:2148101ms step_avg:403.85ms step:5330/6250 train_loss:2.3645 train_time:2148491ms step_avg:403.85ms step:5331/6250 train_loss:2.3471 train_time:2148878ms step_avg:403.85ms step:5332/6250 train_loss:2.4065 train_time:2149269ms step_avg:403.85ms step:5333/6250 train_loss:2.4083 train_time:2149660ms step_avg:403.84ms step:5334/6250 train_loss:2.3943 train_time:2150047ms step_avg:403.84ms step:5335/6250 train_loss:2.2893 train_time:2150437ms step_avg:403.84ms step:5336/6250 train_loss:2.3248 train_time:2150828ms step_avg:403.84ms step:5337/6250 train_loss:2.3791 train_time:2151215ms step_avg:403.83ms step:5338/6250 train_loss:2.3453 train_time:2151606ms step_avg:403.83ms step:5339/6250 train_loss:2.3830 train_time:2151993ms step_avg:403.83ms step:5340/6250 train_loss:2.4558 train_time:2152381ms step_avg:403.82ms step:5341/6250 train_loss:2.5106 train_time:2152772ms step_avg:403.82ms step:5342/6250 train_loss:2.4084 train_time:2153159ms step_avg:403.82ms step:5343/6250 train_loss:2.3197 train_time:2153548ms step_avg:403.82ms step:5344/6250 train_loss:2.3261 train_time:2153936ms step_avg:403.81ms step:5345/6250 train_loss:2.2966 train_time:2154328ms step_avg:403.81ms step:5346/6250 train_loss:2.3822 train_time:2154717ms step_avg:403.81ms step:5347/6250 train_loss:2.3910 train_time:2155104ms step_avg:403.80ms step:5348/6250 train_loss:2.3586 train_time:2155495ms step_avg:403.80ms step:5349/6250 train_loss:2.4061 train_time:2155883ms step_avg:403.80ms step:5350/6250 train_loss:2.4572 train_time:2156271ms step_avg:403.80ms step:5351/6250 train_loss:2.4174 train_time:2156657ms step_avg:403.79ms step:5352/6250 train_loss:2.3043 train_time:2157046ms step_avg:403.79ms step:5353/6250 train_loss:2.3688 train_time:2157433ms step_avg:403.79ms step:5354/6250 train_loss:2.2770 train_time:2157822ms step_avg:403.78ms step:5355/6250 train_loss:2.3476 train_time:2158210ms step_avg:403.78ms step:5356/6250 train_loss:2.4187 train_time:2158599ms step_avg:403.78ms step:5357/6250 train_loss:2.3760 train_time:2158985ms step_avg:403.77ms step:5358/6250 train_loss:2.3194 train_time:2159373ms step_avg:403.77ms step:5359/6250 train_loss:2.3295 train_time:2159764ms step_avg:403.77ms step:5360/6250 train_loss:2.2913 train_time:2160150ms step_avg:403.77ms step:5361/6250 train_loss:2.3829 train_time:2160542ms step_avg:403.76ms step:5362/6250 train_loss:2.4260 train_time:2160929ms step_avg:403.76ms step:5363/6250 train_loss:2.3701 train_time:2161317ms step_avg:403.76ms step:5364/6250 train_loss:2.4350 train_time:2161707ms step_avg:403.76ms step:5365/6250 train_loss:2.3129 train_time:2162096ms step_avg:403.75ms step:5366/6250 train_loss:2.4171 train_time:2162488ms step_avg:403.75ms step:5367/6250 train_loss:2.3443 train_time:2162876ms step_avg:403.75ms step:5368/6250 train_loss:2.3807 train_time:2163265ms step_avg:403.74ms step:5369/6250 train_loss:2.4234 train_time:2163653ms step_avg:403.74ms step:5370/6250 train_loss:2.3820 train_time:2164040ms step_avg:403.74ms step:5371/6250 train_loss:2.4196 train_time:2164429ms step_avg:403.74ms step:5372/6250 train_loss:2.3804 train_time:2164819ms step_avg:403.73ms step:5373/6250 train_loss:2.3524 train_time:2165209ms step_avg:403.73ms step:5374/6250 train_loss:2.3884 train_time:2165599ms step_avg:403.73ms step:5375/6250 train_loss:2.4061 train_time:2165987ms step_avg:403.73ms step:5376/6250 train_loss:2.3724 train_time:2166375ms step_avg:403.72ms step:5377/6250 train_loss:2.4017 train_time:2166764ms step_avg:403.72ms step:5378/6250 train_loss:2.3783 train_time:2167153ms step_avg:403.72ms step:5379/6250 train_loss:2.3189 train_time:2167543ms step_avg:403.71ms step:5380/6250 train_loss:2.3881 train_time:2167928ms step_avg:403.71ms step:5381/6250 train_loss:2.3014 train_time:2168317ms step_avg:403.71ms step:5382/6250 train_loss:2.3267 train_time:2168706ms step_avg:403.71ms step:5383/6250 train_loss:2.3594 train_time:2169093ms step_avg:403.70ms step:5384/6250 train_loss:2.3770 train_time:2169482ms step_avg:403.70ms step:5385/6250 train_loss:2.3370 train_time:2169869ms step_avg:403.70ms step:5386/6250 train_loss:2.4170 train_time:2170257ms step_avg:403.69ms step:5387/6250 train_loss:2.3974 train_time:2170647ms step_avg:403.69ms step:5388/6250 train_loss:2.4482 train_time:2171034ms step_avg:403.69ms step:5389/6250 train_loss:2.3635 train_time:2171424ms step_avg:403.69ms step:5390/6250 train_loss:2.3481 train_time:2171812ms step_avg:403.68ms step:5391/6250 train_loss:2.4424 train_time:2172202ms step_avg:403.68ms step:5392/6250 train_loss:2.4065 train_time:2172590ms step_avg:403.68ms step:5393/6250 train_loss:2.3597 train_time:2172979ms step_avg:403.67ms step:5394/6250 train_loss:2.5165 train_time:2173369ms step_avg:403.67ms step:5395/6250 train_loss:2.3993 train_time:2173759ms step_avg:403.67ms step:5396/6250 train_loss:2.4918 train_time:2174147ms step_avg:403.67ms step:5397/6250 train_loss:2.4361 train_time:2174536ms step_avg:403.66ms step:5398/6250 train_loss:2.4606 train_time:2174924ms step_avg:403.66ms step:5399/6250 train_loss:2.5245 train_time:2175312ms step_avg:403.66ms step:5400/6250 train_loss:2.4679 train_time:2175701ms step_avg:403.66ms step:5401/6250 train_loss:2.4201 train_time:2176089ms step_avg:403.65ms step:5402/6250 train_loss:2.3982 train_time:2176482ms step_avg:403.65ms step:5403/6250 train_loss:2.4908 train_time:2176871ms step_avg:403.65ms step:5404/6250 train_loss:2.4004 train_time:2177260ms step_avg:403.64ms step:5405/6250 train_loss:2.4585 train_time:2177649ms step_avg:403.64ms step:5406/6250 train_loss:2.3778 train_time:2178036ms step_avg:403.64ms step:5407/6250 train_loss:2.3285 train_time:2178425ms step_avg:403.64ms step:5408/6250 train_loss:2.4096 train_time:2178813ms step_avg:403.63ms step:5409/6250 train_loss:2.4134 train_time:2179201ms step_avg:403.63ms step:5410/6250 train_loss:2.4349 train_time:2179592ms step_avg:403.63ms step:5411/6250 train_loss:2.3384 train_time:2179981ms step_avg:403.63ms step:5412/6250 train_loss:2.4083 train_time:2180371ms step_avg:403.62ms step:5413/6250 train_loss:2.4257 train_time:2180760ms step_avg:403.62ms step:5414/6250 train_loss:2.3970 train_time:2181149ms step_avg:403.62ms step:5415/6250 train_loss:2.4016 train_time:2181536ms step_avg:403.61ms step:5416/6250 train_loss:2.4045 train_time:2181925ms step_avg:403.61ms step:5417/6250 train_loss:2.3567 train_time:2182314ms step_avg:403.61ms step:5418/6250 train_loss:2.3576 train_time:2182705ms step_avg:403.61ms step:5419/6250 train_loss:2.3536 train_time:2183093ms step_avg:403.60ms step:5420/6250 train_loss:2.3804 train_time:2183483ms step_avg:403.60ms step:5421/6250 train_loss:2.3899 train_time:2183872ms step_avg:403.60ms step:5422/6250 train_loss:2.5318 train_time:2184260ms step_avg:403.60ms step:5423/6250 train_loss:2.2809 train_time:2184649ms step_avg:403.59ms step:5424/6250 train_loss:2.4389 train_time:2185035ms step_avg:403.59ms step:5425/6250 train_loss:2.3698 train_time:2185424ms step_avg:403.59ms step:5426/6250 train_loss:2.2800 train_time:2185815ms step_avg:403.58ms step:5427/6250 train_loss:2.3693 train_time:2186201ms step_avg:403.58ms step:5428/6250 train_loss:2.4055 train_time:2186594ms step_avg:403.58ms step:5429/6250 train_loss:2.4206 train_time:2186984ms step_avg:403.58ms step:5430/6250 train_loss:2.4385 train_time:2187373ms step_avg:403.57ms step:5431/6250 train_loss:2.4481 train_time:2187762ms step_avg:403.57ms step:5432/6250 train_loss:2.3388 train_time:2188152ms step_avg:403.57ms step:5433/6250 train_loss:2.3613 train_time:2188540ms step_avg:403.57ms step:5434/6250 train_loss:2.3703 train_time:2188927ms step_avg:403.56ms step:5435/6250 train_loss:2.4403 train_time:2189318ms step_avg:403.56ms step:5436/6250 train_loss:2.4331 train_time:2189708ms step_avg:403.56ms step:5437/6250 train_loss:2.4244 train_time:2190096ms step_avg:403.56ms step:5438/6250 train_loss:2.4008 train_time:2190485ms step_avg:403.55ms step:5439/6250 train_loss:2.4695 train_time:2190875ms step_avg:403.55ms step:5440/6250 train_loss:2.3029 train_time:2191262ms step_avg:403.55ms step:5441/6250 train_loss:2.3376 train_time:2191650ms step_avg:403.54ms step:5442/6250 train_loss:2.4011 train_time:2192036ms step_avg:403.54ms step:5443/6250 train_loss:2.3547 train_time:2192430ms step_avg:403.54ms step:5444/6250 train_loss:2.4844 train_time:2192821ms step_avg:403.54ms step:5445/6250 train_loss:2.4404 train_time:2193210ms step_avg:403.53ms step:5446/6250 train_loss:2.4237 train_time:2193599ms step_avg:403.53ms step:5447/6250 train_loss:2.4569 train_time:2193986ms step_avg:403.53ms step:5448/6250 train_loss:2.4037 train_time:2194373ms step_avg:403.53ms step:5449/6250 train_loss:2.3961 train_time:2194762ms step_avg:403.52ms step:5450/6250 train_loss:2.3564 train_time:2195149ms step_avg:403.52ms step:5451/6250 train_loss:2.4003 train_time:2195538ms step_avg:403.52ms step:5452/6250 train_loss:2.3811 train_time:2195927ms step_avg:403.51ms step:5453/6250 train_loss:2.2461 train_time:2196315ms step_avg:403.51ms step:5454/6250 train_loss:2.3230 train_time:2196705ms step_avg:403.51ms step:5455/6250 train_loss:2.3979 train_time:2197093ms step_avg:403.51ms step:5456/6250 train_loss:2.3483 train_time:2197483ms step_avg:403.50ms step:5457/6250 train_loss:2.4656 train_time:2197869ms step_avg:403.50ms step:5458/6250 train_loss:2.4092 train_time:2198258ms step_avg:403.50ms step:5459/6250 train_loss:2.3823 train_time:2198646ms step_avg:403.50ms step:5460/6250 train_loss:2.4882 train_time:2199034ms step_avg:403.49ms step:5461/6250 train_loss:2.4859 train_time:2199423ms step_avg:403.49ms step:5462/6250 train_loss:2.4456 train_time:2199813ms step_avg:403.49ms step:5463/6250 train_loss:2.3857 train_time:2200201ms step_avg:403.48ms step:5464/6250 train_loss:2.3896 train_time:2200588ms step_avg:403.48ms step:5465/6250 train_loss:2.3518 train_time:2200973ms step_avg:403.48ms step:5466/6250 train_loss:2.3637 train_time:2201361ms step_avg:403.48ms step:5467/6250 train_loss:2.3948 train_time:2201753ms step_avg:403.47ms step:5468/6250 train_loss:2.3281 train_time:2202141ms step_avg:403.47ms step:5469/6250 train_loss:2.3807 train_time:2202533ms step_avg:403.47ms step:5470/6250 train_loss:2.3948 train_time:2202921ms step_avg:403.47ms step:5471/6250 train_loss:2.4229 train_time:2203309ms step_avg:403.46ms step:5472/6250 train_loss:2.3356 train_time:2203700ms step_avg:403.46ms step:5473/6250 train_loss:2.3945 train_time:2204085ms step_avg:403.46ms step:5474/6250 train_loss:2.4173 train_time:2204473ms step_avg:403.45ms step:5475/6250 train_loss:2.3785 train_time:2204861ms step_avg:403.45ms step:5476/6250 train_loss:2.3720 train_time:2205250ms step_avg:403.45ms step:5477/6250 train_loss:2.4880 train_time:2205639ms step_avg:403.45ms step:5478/6250 train_loss:2.3216 train_time:2206030ms step_avg:403.44ms step:5479/6250 train_loss:2.3650 train_time:2206419ms step_avg:403.44ms step:5480/6250 train_loss:2.3860 train_time:2206809ms step_avg:403.44ms step:5481/6250 train_loss:2.3899 train_time:2207196ms step_avg:403.44ms step:5482/6250 train_loss:2.4103 train_time:2207583ms step_avg:403.43ms step:5483/6250 train_loss:2.4460 train_time:2207971ms step_avg:403.43ms step:5484/6250 train_loss:2.4006 train_time:2208361ms step_avg:403.43ms step:5485/6250 train_loss:2.4164 train_time:2208751ms step_avg:403.42ms step:5486/6250 train_loss:2.4157 train_time:2209139ms step_avg:403.42ms step:5487/6250 train_loss:2.3549 train_time:2209529ms step_avg:403.42ms step:5488/6250 train_loss:2.5027 train_time:2209917ms step_avg:403.42ms step:5489/6250 train_loss:2.4162 train_time:2210304ms step_avg:403.41ms step:5490/6250 train_loss:2.3546 train_time:2210692ms step_avg:403.41ms step:5491/6250 train_loss:2.3550 train_time:2211079ms step_avg:403.41ms step:5492/6250 train_loss:2.3708 train_time:2211470ms step_avg:403.41ms step:5493/6250 train_loss:2.4000 train_time:2211861ms step_avg:403.40ms step:5494/6250 train_loss:2.2586 train_time:2212249ms step_avg:403.40ms step:5495/6250 train_loss:2.2953 train_time:2212642ms step_avg:403.40ms step:5496/6250 train_loss:2.3000 train_time:2213030ms step_avg:403.40ms step:5497/6250 train_loss:2.4432 train_time:2213417ms step_avg:403.39ms step:5498/6250 train_loss:2.3966 train_time:2213804ms step_avg:403.39ms step:5499/6250 train_loss:2.3774 train_time:2214192ms step_avg:403.39ms step:5500/6250 train_loss:2.3902 train_time:2214582ms step_avg:403.38ms step:5501/6250 train_loss:2.4433 train_time:2214969ms step_avg:403.38ms step:5502/6250 train_loss:2.4245 train_time:2215360ms step_avg:403.38ms step:5503/6250 train_loss:2.4268 train_time:2215746ms step_avg:403.38ms step:5504/6250 train_loss:2.4266 train_time:2216136ms step_avg:403.37ms step:5505/6250 train_loss:2.3745 train_time:2216526ms step_avg:403.37ms step:5506/6250 train_loss:2.3965 train_time:2216916ms step_avg:403.37ms step:5507/6250 train_loss:2.4016 train_time:2217304ms step_avg:403.37ms step:5508/6250 train_loss:2.3619 train_time:2217694ms step_avg:403.36ms step:5509/6250 train_loss:2.3339 train_time:2218082ms step_avg:403.36ms step:5510/6250 train_loss:2.4834 train_time:2218471ms step_avg:403.36ms step:5511/6250 train_loss:2.4159 train_time:2218858ms step_avg:403.36ms step:5512/6250 train_loss:2.3864 train_time:2219248ms step_avg:403.35ms step:5513/6250 train_loss:2.5018 train_time:2219639ms step_avg:403.35ms step:5514/6250 train_loss:2.4317 train_time:2220026ms step_avg:403.35ms step:5515/6250 train_loss:2.3861 train_time:2220414ms step_avg:403.34ms step:5516/6250 train_loss:2.4661 train_time:2220803ms step_avg:403.34ms step:5517/6250 train_loss:2.3624 train_time:2221190ms step_avg:403.34ms step:5518/6250 train_loss:2.4376 train_time:2221578ms step_avg:403.34ms step:5519/6250 train_loss:2.4697 train_time:2221967ms step_avg:403.33ms step:5520/6250 train_loss:2.3177 train_time:2222355ms step_avg:403.33ms step:5521/6250 train_loss:2.4860 train_time:2222741ms step_avg:403.33ms step:5522/6250 train_loss:2.3376 train_time:2223128ms step_avg:403.33ms step:5523/6250 train_loss:2.3013 train_time:2223516ms step_avg:403.32ms step:5524/6250 train_loss:2.5040 train_time:2223904ms step_avg:403.32ms step:5525/6250 train_loss:2.4255 train_time:2224291ms step_avg:403.32ms step:5526/6250 train_loss:2.3677 train_time:2224680ms step_avg:403.31ms step:5527/6250 train_loss:2.4086 train_time:2225067ms step_avg:403.31ms step:5528/6250 train_loss:2.3221 train_time:2225457ms step_avg:403.31ms step:5529/6250 train_loss:2.4700 train_time:2225850ms step_avg:403.31ms step:5530/6250 train_loss:2.3551 train_time:2226238ms step_avg:403.30ms step:5531/6250 train_loss:2.3394 train_time:2226628ms step_avg:403.30ms step:5532/6250 train_loss:2.3876 train_time:2227015ms step_avg:403.30ms step:5533/6250 train_loss:2.3662 train_time:2227406ms step_avg:403.30ms step:5534/6250 train_loss:2.3765 train_time:2227796ms step_avg:403.29ms step:5535/6250 train_loss:2.3679 train_time:2228186ms step_avg:403.29ms step:5536/6250 train_loss:2.2987 train_time:2228575ms step_avg:403.29ms step:5537/6250 train_loss:2.3808 train_time:2228963ms step_avg:403.29ms step:5538/6250 train_loss:2.4337 train_time:2229352ms step_avg:403.28ms step:5539/6250 train_loss:2.3393 train_time:2229741ms step_avg:403.28ms step:5540/6250 train_loss:2.2751 train_time:2230130ms step_avg:403.28ms step:5541/6250 train_loss:2.3398 train_time:2230520ms step_avg:403.28ms step:5542/6250 train_loss:2.4215 train_time:2230910ms step_avg:403.27ms step:5543/6250 train_loss:2.3833 train_time:2231297ms step_avg:403.27ms step:5544/6250 train_loss:2.4128 train_time:2231686ms step_avg:403.27ms step:5545/6250 train_loss:2.3297 train_time:2232075ms step_avg:403.27ms step:5546/6250 train_loss:2.3658 train_time:2232464ms step_avg:403.26ms step:5547/6250 train_loss:2.3772 train_time:2232852ms step_avg:403.26ms step:5548/6250 train_loss:2.3648 train_time:2233238ms step_avg:403.26ms step:5549/6250 train_loss:2.4587 train_time:2233626ms step_avg:403.25ms step:5550/6250 train_loss:2.4839 train_time:2234017ms step_avg:403.25ms step:5551/6250 train_loss:2.3471 train_time:2234407ms step_avg:403.25ms step:5552/6250 train_loss:2.3691 train_time:2234794ms step_avg:403.25ms step:5553/6250 train_loss:2.4368 train_time:2235185ms step_avg:403.24ms step:5554/6250 train_loss:2.4057 train_time:2235575ms step_avg:403.24ms step:5555/6250 train_loss:2.4234 train_time:2235962ms step_avg:403.24ms step:5556/6250 train_loss:2.3635 train_time:2236352ms step_avg:403.24ms step:5557/6250 train_loss:2.3742 train_time:2236743ms step_avg:403.23ms step:5558/6250 train_loss:2.4772 train_time:2237128ms step_avg:403.23ms step:5559/6250 train_loss:2.3444 train_time:2237518ms step_avg:403.23ms step:5560/6250 train_loss:2.3222 train_time:2237909ms step_avg:403.23ms step:5561/6250 train_loss:2.3739 train_time:2238298ms step_avg:403.22ms step:5562/6250 train_loss:2.4195 train_time:2238687ms step_avg:403.22ms step:5563/6250 train_loss:2.3089 train_time:2239075ms step_avg:403.22ms step:5564/6250 train_loss:2.3761 train_time:2239465ms step_avg:403.22ms step:5565/6250 train_loss:2.4276 train_time:2239853ms step_avg:403.21ms step:5566/6250 train_loss:2.2928 train_time:2240243ms step_avg:403.21ms step:5567/6250 train_loss:2.5039 train_time:2240631ms step_avg:403.21ms step:5568/6250 train_loss:2.2811 train_time:2241019ms step_avg:403.21ms step:5569/6250 train_loss:2.4383 train_time:2241405ms step_avg:403.20ms step:5570/6250 train_loss:2.3514 train_time:2241790ms step_avg:403.20ms step:5571/6250 train_loss:2.2961 train_time:2242178ms step_avg:403.20ms step:5572/6250 train_loss:2.4003 train_time:2242570ms step_avg:403.19ms step:5573/6250 train_loss:2.4943 train_time:2242958ms step_avg:403.19ms step:5574/6250 train_loss:2.4023 train_time:2243347ms step_avg:403.19ms step:5575/6250 train_loss:2.4157 train_time:2243737ms step_avg:403.19ms step:5576/6250 train_loss:2.3613 train_time:2244124ms step_avg:403.18ms step:5577/6250 train_loss:2.3759 train_time:2244515ms step_avg:403.18ms step:5578/6250 train_loss:2.4685 train_time:2244904ms step_avg:403.18ms step:5579/6250 train_loss:2.3917 train_time:2245291ms step_avg:403.18ms step:5580/6250 train_loss:2.4432 train_time:2245681ms step_avg:403.17ms step:5581/6250 train_loss:2.3344 train_time:2246069ms step_avg:403.17ms step:5582/6250 train_loss:2.3911 train_time:2246459ms step_avg:403.17ms step:5583/6250 train_loss:2.3692 train_time:2246847ms step_avg:403.17ms step:5584/6250 train_loss:2.3799 train_time:2247236ms step_avg:403.16ms step:5585/6250 train_loss:2.4081 train_time:2247626ms step_avg:403.16ms step:5586/6250 train_loss:2.3388 train_time:2248013ms step_avg:403.16ms step:5587/6250 train_loss:2.3458 train_time:2248403ms step_avg:403.16ms step:5588/6250 train_loss:2.3755 train_time:2248794ms step_avg:403.15ms step:5589/6250 train_loss:2.2666 train_time:2249183ms step_avg:403.15ms step:5590/6250 train_loss:2.4127 train_time:2249573ms step_avg:403.15ms step:5591/6250 train_loss:2.3016 train_time:2249964ms step_avg:403.15ms step:5592/6250 train_loss:2.3844 train_time:2250356ms step_avg:403.15ms step:5593/6250 train_loss:2.3788 train_time:2250746ms step_avg:403.14ms step:5594/6250 train_loss:2.3487 train_time:2251134ms step_avg:403.14ms step:5595/6250 train_loss:2.3846 train_time:2251530ms step_avg:403.14ms step:5596/6250 train_loss:2.4288 train_time:2251920ms step_avg:403.14ms step:5597/6250 train_loss:2.4590 train_time:2252308ms step_avg:403.13ms step:5598/6250 train_loss:2.3653 train_time:2252698ms step_avg:403.13ms step:5599/6250 train_loss:2.4804 train_time:2253087ms step_avg:403.13ms step:5600/6250 train_loss:2.3939 train_time:2253477ms step_avg:403.13ms step:5601/6250 train_loss:2.3457 train_time:2253866ms step_avg:403.12ms step:5602/6250 train_loss:2.4025 train_time:2254254ms step_avg:403.12ms step:5603/6250 train_loss:2.3176 train_time:2254643ms step_avg:403.12ms step:5604/6250 train_loss:2.4671 train_time:2255031ms step_avg:403.12ms step:5605/6250 train_loss:2.4162 train_time:2255420ms step_avg:403.11ms step:5606/6250 train_loss:2.3418 train_time:2255809ms step_avg:403.11ms step:5607/6250 train_loss:2.4483 train_time:2256197ms step_avg:403.11ms step:5608/6250 train_loss:2.3499 train_time:2256589ms step_avg:403.11ms step:5609/6250 train_loss:2.4111 train_time:2256978ms step_avg:403.10ms step:5610/6250 train_loss:2.3754 train_time:2257367ms step_avg:403.10ms step:5611/6250 train_loss:2.2476 train_time:2257756ms step_avg:403.10ms step:5612/6250 train_loss:2.4339 train_time:2258145ms step_avg:403.10ms step:5613/6250 train_loss:2.4003 train_time:2258534ms step_avg:403.09ms step:5614/6250 train_loss:2.3928 train_time:2258923ms step_avg:403.09ms step:5615/6250 train_loss:2.3343 train_time:2259310ms step_avg:403.09ms step:5616/6250 train_loss:2.4128 train_time:2259701ms step_avg:403.09ms step:5617/6250 train_loss:2.5270 train_time:2260094ms step_avg:403.08ms step:5618/6250 train_loss:2.3481 train_time:2260489ms step_avg:403.08ms step:5619/6250 train_loss:2.4113 train_time:2260892ms step_avg:403.08ms step:5620/6250 train_loss:2.3319 train_time:2261293ms step_avg:403.08ms step:5621/6250 train_loss:2.2574 train_time:2261687ms step_avg:403.08ms step:5622/6250 train_loss:2.3659 train_time:2262093ms step_avg:403.08ms step:5623/6250 train_loss:2.3612 train_time:2262497ms step_avg:403.08ms step:5624/6250 train_loss:2.3258 train_time:2262900ms step_avg:403.08ms step:5625/6250 train_loss:2.2945 train_time:2263307ms step_avg:403.08ms step:5626/6250 train_loss:2.3609 train_time:2263701ms step_avg:403.08ms step:5627/6250 train_loss:2.3861 train_time:2264090ms step_avg:403.08ms step:5628/6250 train_loss:2.3496 train_time:2264480ms step_avg:403.08ms step:5629/6250 train_loss:2.3792 train_time:2264872ms step_avg:403.07ms step:5630/6250 train_loss:2.5111 train_time:2265256ms step_avg:403.07ms step:5631/6250 train_loss:2.3450 train_time:2265664ms step_avg:403.07ms step:5632/6250 train_loss:2.2924 train_time:2266060ms step_avg:403.07ms step:5633/6250 train_loss:2.3468 train_time:2266453ms step_avg:403.07ms step:5634/6250 train_loss:2.3991 train_time:2266840ms step_avg:403.07ms step:5635/6250 train_loss:2.3183 train_time:2267227ms step_avg:403.06ms step:5636/6250 train_loss:2.3813 train_time:2267623ms step_avg:403.06ms step:5637/6250 train_loss:2.3198 train_time:2268011ms step_avg:403.06ms step:5638/6250 train_loss:2.3930 train_time:2268399ms step_avg:403.06ms step:5639/6250 train_loss:2.4054 train_time:2268788ms step_avg:403.05ms step:5640/6250 train_loss:2.3189 train_time:2269175ms step_avg:403.05ms step:5641/6250 train_loss:2.4275 train_time:2269563ms step_avg:403.05ms step:5642/6250 train_loss:2.3269 train_time:2269952ms step_avg:403.05ms step:5643/6250 train_loss:2.3461 train_time:2270341ms step_avg:403.04ms step:5644/6250 train_loss:2.3367 train_time:2270729ms step_avg:403.04ms step:5645/6250 train_loss:2.3939 train_time:2271112ms step_avg:403.04ms step:5646/6250 train_loss:2.3954 train_time:2271503ms step_avg:403.03ms step:5647/6250 train_loss:2.3716 train_time:2271892ms step_avg:403.03ms step:5648/6250 train_loss:2.3755 train_time:2272279ms step_avg:403.03ms step:5649/6250 train_loss:2.3733 train_time:2272667ms step_avg:403.03ms step:5650/6250 train_loss:2.3145 train_time:2273055ms step_avg:403.02ms step:5651/6250 train_loss:2.3427 train_time:2273447ms step_avg:403.02ms step:5652/6250 train_loss:2.4178 train_time:2273837ms step_avg:403.02ms step:5653/6250 train_loss:2.3162 train_time:2274225ms step_avg:403.02ms step:5654/6250 train_loss:2.4228 train_time:2274613ms step_avg:403.01ms step:5655/6250 train_loss:2.3800 train_time:2275001ms step_avg:403.01ms step:5656/6250 train_loss:2.3588 train_time:2275388ms step_avg:403.01ms step:5657/6250 train_loss:2.4598 train_time:2275778ms step_avg:403.01ms step:5658/6250 train_loss:2.4355 train_time:2276166ms step_avg:403.00ms step:5659/6250 train_loss:2.3857 train_time:2276556ms step_avg:403.00ms step:5660/6250 train_loss:2.4632 train_time:2276945ms step_avg:403.00ms step:5661/6250 train_loss:2.3538 train_time:2277333ms step_avg:403.00ms step:5662/6250 train_loss:2.3992 train_time:2277724ms step_avg:402.99ms step:5663/6250 train_loss:2.3910 train_time:2278114ms step_avg:402.99ms step:5664/6250 train_loss:2.2814 train_time:2278503ms step_avg:402.99ms step:5665/6250 train_loss:2.3042 train_time:2278906ms step_avg:402.99ms step:5666/6250 train_loss:2.3453 train_time:2279301ms step_avg:402.99ms step:5667/6250 train_loss:2.2777 train_time:2279693ms step_avg:402.99ms step:5668/6250 train_loss:2.4013 train_time:2280090ms step_avg:402.99ms step:5669/6250 train_loss:2.3759 train_time:2280486ms step_avg:402.98ms step:5670/6250 train_loss:2.3193 train_time:2280886ms step_avg:402.98ms step:5671/6250 train_loss:2.3463 train_time:2281292ms step_avg:402.98ms step:5672/6250 train_loss:2.3680 train_time:2281697ms step_avg:402.98ms step:5673/6250 train_loss:2.2823 train_time:2282095ms step_avg:402.98ms step:5674/6250 train_loss:2.3593 train_time:2282494ms step_avg:402.98ms step:5675/6250 train_loss:2.3914 train_time:2282887ms step_avg:402.98ms step:5676/6250 train_loss:2.3059 train_time:2283286ms step_avg:402.98ms step:5677/6250 train_loss:2.2870 train_time:2283682ms step_avg:402.98ms step:5678/6250 train_loss:2.3849 train_time:2284072ms step_avg:402.98ms step:5679/6250 train_loss:2.3457 train_time:2284467ms step_avg:402.98ms step:5680/6250 train_loss:2.4204 train_time:2284862ms step_avg:402.97ms step:5681/6250 train_loss:2.4217 train_time:2285251ms step_avg:402.97ms step:5682/6250 train_loss:2.2750 train_time:2285651ms step_avg:402.97ms step:5683/6250 train_loss:2.3751 train_time:2286043ms step_avg:402.97ms step:5684/6250 train_loss:2.3980 train_time:2286442ms step_avg:402.97ms step:5685/6250 train_loss:2.3120 train_time:2286836ms step_avg:402.97ms step:5686/6250 train_loss:2.3537 train_time:2287227ms step_avg:402.96ms step:5687/6250 train_loss:2.3413 train_time:2287622ms step_avg:402.96ms step:5688/6250 train_loss:2.3660 train_time:2288020ms step_avg:402.96ms step:5689/6250 train_loss:2.3415 train_time:2288412ms step_avg:402.96ms step:5690/6250 train_loss:2.3105 train_time:2288804ms step_avg:402.96ms step:5691/6250 train_loss:2.3226 train_time:2289198ms step_avg:402.96ms step:5692/6250 train_loss:2.4092 train_time:2289592ms step_avg:402.96ms step:5693/6250 train_loss:2.3477 train_time:2289991ms step_avg:402.95ms step:5694/6250 train_loss:2.4087 train_time:2290387ms step_avg:402.95ms step:5695/6250 train_loss:2.3422 train_time:2290779ms step_avg:402.95ms step:5696/6250 train_loss:2.2917 train_time:2291170ms step_avg:402.95ms step:5697/6250 train_loss:2.3899 train_time:2291576ms step_avg:402.95ms step:5698/6250 train_loss:2.3862 train_time:2291970ms step_avg:402.95ms step:5699/6250 train_loss:2.3961 train_time:2292364ms step_avg:402.95ms step:5700/6250 train_loss:2.3883 train_time:2292763ms step_avg:402.95ms step:5701/6250 train_loss:2.2883 train_time:2293160ms step_avg:402.95ms step:5702/6250 train_loss:2.3497 train_time:2293554ms step_avg:402.94ms step:5703/6250 train_loss:2.3053 train_time:2293947ms step_avg:402.94ms step:5704/6250 train_loss:2.3721 train_time:2294338ms step_avg:402.94ms step:5705/6250 train_loss:2.2848 train_time:2294729ms step_avg:402.94ms step:5706/6250 train_loss:2.4331 train_time:2295120ms step_avg:402.94ms step:5707/6250 train_loss:2.3825 train_time:2295514ms step_avg:402.93ms step:5708/6250 train_loss:2.3674 train_time:2295904ms step_avg:402.93ms step:5709/6250 train_loss:2.3428 train_time:2296295ms step_avg:402.93ms step:5710/6250 train_loss:2.3017 train_time:2296685ms step_avg:402.93ms step:5711/6250 train_loss:2.3177 train_time:2297077ms step_avg:402.93ms step:5712/6250 train_loss:2.3130 train_time:2297474ms step_avg:402.92ms step:5713/6250 train_loss:2.3215 train_time:2297865ms step_avg:402.92ms step:5714/6250 train_loss:2.3455 train_time:2298255ms step_avg:402.92ms step:5715/6250 train_loss:2.2956 train_time:2298652ms step_avg:402.92ms step:5716/6250 train_loss:2.3650 train_time:2299043ms step_avg:402.92ms step:5717/6250 train_loss:2.2719 train_time:2299440ms step_avg:402.92ms step:5718/6250 train_loss:2.3784 train_time:2299835ms step_avg:402.91ms step:5719/6250 train_loss:2.4563 train_time:2300227ms step_avg:402.91ms step:5720/6250 train_loss:2.3132 train_time:2300618ms step_avg:402.91ms step:5721/6250 train_loss:2.3128 train_time:2301008ms step_avg:402.91ms step:5722/6250 train_loss:2.4370 train_time:2301400ms step_avg:402.91ms step:5723/6250 train_loss:2.3150 train_time:2301792ms step_avg:402.90ms step:5724/6250 train_loss:2.3677 train_time:2302184ms step_avg:402.90ms step:5725/6250 train_loss:2.3132 train_time:2302576ms step_avg:402.90ms step:5726/6250 train_loss:2.3042 train_time:2302966ms step_avg:402.90ms step:5727/6250 train_loss:2.3868 train_time:2303356ms step_avg:402.90ms step:5728/6250 train_loss:2.3422 train_time:2303744ms step_avg:402.89ms step:5729/6250 train_loss:2.3569 train_time:2304134ms step_avg:402.89ms step:5730/6250 train_loss:2.3766 train_time:2304527ms step_avg:402.89ms step:5731/6250 train_loss:2.3839 train_time:2304915ms step_avg:402.89ms step:5732/6250 train_loss:2.4562 train_time:2305305ms step_avg:402.88ms step:5733/6250 train_loss:2.2721 train_time:2305695ms step_avg:402.88ms step:5734/6250 train_loss:2.3816 train_time:2306086ms step_avg:402.88ms step:5735/6250 train_loss:2.4453 train_time:2306478ms step_avg:402.88ms step:5736/6250 train_loss:2.3641 train_time:2306872ms step_avg:402.88ms step:5737/6250 train_loss:2.4080 train_time:2307268ms step_avg:402.88ms step:5738/6250 train_loss:2.3756 train_time:2307661ms step_avg:402.87ms step:5739/6250 train_loss:2.3744 train_time:2308059ms step_avg:402.87ms step:5740/6250 train_loss:2.3452 train_time:2308451ms step_avg:402.87ms step:5741/6250 train_loss:2.4691 train_time:2308846ms step_avg:402.87ms step:5742/6250 train_loss:2.4253 train_time:2309236ms step_avg:402.87ms step:5743/6250 train_loss:2.4094 train_time:2309627ms step_avg:402.87ms step:5744/6250 train_loss:2.3248 train_time:2310015ms step_avg:402.86ms step:5745/6250 train_loss:2.3468 train_time:2310408ms step_avg:402.86ms step:5746/6250 train_loss:2.3553 train_time:2310800ms step_avg:402.86ms step:5747/6250 train_loss:2.4232 train_time:2311192ms step_avg:402.86ms step:5748/6250 train_loss:2.3343 train_time:2311585ms step_avg:402.86ms step:5749/6250 train_loss:2.4193 train_time:2311975ms step_avg:402.85ms step:5750/6250 train_loss:2.3521 train_time:2312371ms step_avg:402.85ms step:5751/6250 train_loss:2.3736 train_time:2312760ms step_avg:402.85ms step:5752/6250 train_loss:2.3684 train_time:2313148ms step_avg:402.85ms step:5753/6250 train_loss:2.3260 train_time:2313542ms step_avg:402.85ms step:5754/6250 train_loss:2.3591 train_time:2313939ms step_avg:402.84ms step:5755/6250 train_loss:2.4261 train_time:2314333ms step_avg:402.84ms step:5756/6250 train_loss:2.4323 train_time:2314724ms step_avg:402.84ms step:5757/6250 train_loss:2.3488 train_time:2315115ms step_avg:402.84ms step:5758/6250 train_loss:2.3925 train_time:2315509ms step_avg:402.84ms step:5759/6250 train_loss:2.3493 train_time:2315908ms step_avg:402.84ms step:5760/6250 train_loss:2.4635 train_time:2316301ms step_avg:402.84ms step:5761/6250 train_loss:2.4030 train_time:2316697ms step_avg:402.83ms step:5762/6250 train_loss:2.3331 train_time:2317089ms step_avg:402.83ms step:5763/6250 train_loss:2.4570 train_time:2317484ms step_avg:402.83ms step:5764/6250 train_loss:2.4236 train_time:2317879ms step_avg:402.83ms step:5765/6250 train_loss:2.3508 train_time:2318269ms step_avg:402.83ms step:5766/6250 train_loss:2.3237 train_time:2318666ms step_avg:402.83ms step:5767/6250 train_loss:2.4309 train_time:2319057ms step_avg:402.82ms step:5768/6250 train_loss:2.5230 train_time:2319448ms step_avg:402.82ms step:5769/6250 train_loss:2.3864 train_time:2319843ms step_avg:402.82ms step:5770/6250 train_loss:2.2564 train_time:2320234ms step_avg:402.82ms step:5771/6250 train_loss:2.3607 train_time:2320623ms step_avg:402.82ms step:5772/6250 train_loss:2.3362 train_time:2321018ms step_avg:402.81ms step:5773/6250 train_loss:2.3564 train_time:2321408ms step_avg:402.81ms step:5774/6250 train_loss:2.4138 train_time:2321800ms step_avg:402.81ms step:5775/6250 train_loss:2.3392 train_time:2322193ms step_avg:402.81ms step:5776/6250 train_loss:2.4072 train_time:2322587ms step_avg:402.81ms step:5777/6250 train_loss:2.3280 train_time:2322975ms step_avg:402.80ms step:5778/6250 train_loss:2.3261 train_time:2323365ms step_avg:402.80ms step:5779/6250 train_loss:2.3839 train_time:2323755ms step_avg:402.80ms step:5780/6250 train_loss:2.3310 train_time:2324145ms step_avg:402.80ms step:5781/6250 train_loss:2.3186 train_time:2324538ms step_avg:402.80ms step:5782/6250 train_loss:2.4071 train_time:2324928ms step_avg:402.79ms step:5783/6250 train_loss:2.3657 train_time:2325319ms step_avg:402.79ms step:5784/6250 train_loss:2.2624 train_time:2325710ms step_avg:402.79ms step:5785/6250 train_loss:2.3234 train_time:2326101ms step_avg:402.79ms step:5786/6250 train_loss:2.3342 train_time:2326493ms step_avg:402.79ms step:5787/6250 train_loss:2.3590 train_time:2326885ms step_avg:402.78ms step:5788/6250 train_loss:2.4314 train_time:2327278ms step_avg:402.78ms step:5789/6250 train_loss:2.4726 train_time:2327670ms step_avg:402.78ms step:5790/6250 train_loss:2.3176 train_time:2328062ms step_avg:402.78ms step:5791/6250 train_loss:2.3536 train_time:2328453ms step_avg:402.78ms step:5792/6250 train_loss:2.2994 train_time:2328842ms step_avg:402.77ms step:5793/6250 train_loss:2.3721 train_time:2329230ms step_avg:402.77ms step:5794/6250 train_loss:2.3510 train_time:2329621ms step_avg:402.77ms step:5795/6250 train_loss:2.3107 train_time:2330015ms step_avg:402.77ms step:5796/6250 train_loss:2.3476 train_time:2330409ms step_avg:402.77ms step:5797/6250 train_loss:2.3425 train_time:2330800ms step_avg:402.76ms step:5798/6250 train_loss:2.3369 train_time:2331188ms step_avg:402.76ms step:5799/6250 train_loss:2.2499 train_time:2331581ms step_avg:402.76ms step:5800/6250 train_loss:2.2805 train_time:2331972ms step_avg:402.76ms step:5801/6250 train_loss:2.2956 train_time:2332363ms step_avg:402.76ms step:5802/6250 train_loss:2.3451 train_time:2332758ms step_avg:402.76ms step:5803/6250 train_loss:2.4130 train_time:2333147ms step_avg:402.75ms step:5804/6250 train_loss:2.3287 train_time:2333539ms step_avg:402.75ms step:5805/6250 train_loss:2.4276 train_time:2333928ms step_avg:402.75ms step:5806/6250 train_loss:2.3841 train_time:2334320ms step_avg:402.75ms step:5807/6250 train_loss:2.3313 train_time:2334709ms step_avg:402.74ms step:5808/6250 train_loss:2.3097 train_time:2335101ms step_avg:402.74ms step:5809/6250 train_loss:2.3558 train_time:2335497ms step_avg:402.74ms step:5810/6250 train_loss:2.3450 train_time:2335887ms step_avg:402.74ms step:5811/6250 train_loss:2.3969 train_time:2336282ms step_avg:402.74ms step:5812/6250 train_loss:2.4059 train_time:2336676ms step_avg:402.74ms step:5813/6250 train_loss:2.3393 train_time:2337065ms step_avg:402.73ms step:5814/6250 train_loss:2.3547 train_time:2337458ms step_avg:402.73ms step:5815/6250 train_loss:2.3650 train_time:2337856ms step_avg:402.73ms step:5816/6250 train_loss:2.2905 train_time:2338247ms step_avg:402.73ms step:5817/6250 train_loss:2.3316 train_time:2338638ms step_avg:402.73ms step:5818/6250 train_loss:2.4175 train_time:2339031ms step_avg:402.73ms step:5819/6250 train_loss:2.2794 train_time:2339422ms step_avg:402.72ms step:5820/6250 train_loss:2.3731 train_time:2339819ms step_avg:402.72ms step:5821/6250 train_loss:2.2974 train_time:2340209ms step_avg:402.72ms step:5822/6250 train_loss:2.4788 train_time:2340601ms step_avg:402.72ms step:5823/6250 train_loss:2.3685 train_time:2340997ms step_avg:402.72ms step:5824/6250 train_loss:2.4253 train_time:2341388ms step_avg:402.72ms step:5825/6250 train_loss:2.3576 train_time:2341784ms step_avg:402.71ms step:5826/6250 train_loss:2.3677 train_time:2342176ms step_avg:402.71ms step:5827/6250 train_loss:2.3079 train_time:2342573ms step_avg:402.71ms step:5828/6250 train_loss:2.3059 train_time:2342970ms step_avg:402.71ms step:5829/6250 train_loss:2.3180 train_time:2343370ms step_avg:402.71ms step:5830/6250 train_loss:2.4044 train_time:2343772ms step_avg:402.71ms step:5831/6250 train_loss:2.2691 train_time:2344162ms step_avg:402.71ms step:5832/6250 train_loss:2.2926 train_time:2344562ms step_avg:402.71ms step:5833/6250 train_loss:2.3277 train_time:2344953ms step_avg:402.71ms step:5834/6250 train_loss:2.3200 train_time:2345353ms step_avg:402.70ms step:5835/6250 train_loss:2.2841 train_time:2345752ms step_avg:402.70ms step:5836/6250 train_loss:2.3457 train_time:2346155ms step_avg:402.70ms step:5837/6250 train_loss:2.4520 train_time:2346562ms step_avg:402.70ms step:5838/6250 train_loss:2.3523 train_time:2346966ms step_avg:402.71ms step:5839/6250 train_loss:2.4484 train_time:2347370ms step_avg:402.71ms step:5840/6250 train_loss:2.2890 train_time:2347778ms step_avg:402.71ms step:5841/6250 train_loss:2.3225 train_time:2348181ms step_avg:402.71ms step:5842/6250 train_loss:2.3412 train_time:2348585ms step_avg:402.71ms step:5843/6250 train_loss:2.3241 train_time:2348989ms step_avg:402.71ms step:5844/6250 train_loss:2.2983 train_time:2349393ms step_avg:402.71ms step:5845/6250 train_loss:2.3199 train_time:2349798ms step_avg:402.71ms step:5846/6250 train_loss:2.3784 train_time:2350202ms step_avg:402.71ms step:5847/6250 train_loss:2.4067 train_time:2350608ms step_avg:402.71ms step:5848/6250 train_loss:2.3292 train_time:2351011ms step_avg:402.71ms step:5849/6250 train_loss:2.3093 train_time:2351413ms step_avg:402.71ms step:5850/6250 train_loss:2.3715 train_time:2351817ms step_avg:402.71ms step:5851/6250 train_loss:2.2710 train_time:2352219ms step_avg:402.71ms step:5852/6250 train_loss:2.3794 train_time:2352624ms step_avg:402.71ms step:5853/6250 train_loss:2.3491 train_time:2353027ms step_avg:402.71ms step:5854/6250 train_loss:2.3020 train_time:2353433ms step_avg:402.71ms step:5855/6250 train_loss:2.4406 train_time:2353836ms step_avg:402.71ms step:5856/6250 train_loss:2.3135 train_time:2354240ms step_avg:402.71ms step:5857/6250 train_loss:2.3457 train_time:2354644ms step_avg:402.71ms step:5858/6250 train_loss:2.3707 train_time:2355047ms step_avg:402.71ms step:5859/6250 train_loss:2.3175 train_time:2355450ms step_avg:402.71ms step:5860/6250 train_loss:2.2845 train_time:2355853ms step_avg:402.71ms step:5861/6250 train_loss:2.4963 train_time:2356256ms step_avg:402.71ms step:5862/6250 train_loss:2.2839 train_time:2356661ms step_avg:402.71ms step:5863/6250 train_loss:2.3550 train_time:2357062ms step_avg:402.71ms step:5864/6250 train_loss:2.3060 train_time:2357460ms step_avg:402.71ms step:5865/6250 train_loss:2.3931 train_time:2357854ms step_avg:402.71ms step:5866/6250 train_loss:2.3721 train_time:2358248ms step_avg:402.71ms step:5867/6250 train_loss:2.3484 train_time:2358643ms step_avg:402.71ms step:5868/6250 train_loss:2.4195 train_time:2359033ms step_avg:402.70ms step:5869/6250 train_loss:2.4273 train_time:2359437ms step_avg:402.70ms step:5870/6250 train_loss:2.3532 train_time:2359885ms step_avg:402.71ms step:5871/6250 train_loss:2.3401 train_time:2360288ms step_avg:402.71ms step:5872/6250 train_loss:2.4114 train_time:2360692ms step_avg:402.71ms step:5873/6250 train_loss:2.3228 train_time:2361084ms step_avg:402.71ms step:5874/6250 train_loss:2.3332 train_time:2361473ms step_avg:402.71ms step:5875/6250 train_loss:2.3156 train_time:2361883ms step_avg:402.71ms step:5876/6250 train_loss:2.4048 train_time:2362272ms step_avg:402.71ms step:5877/6250 train_loss:2.3985 train_time:2362671ms step_avg:402.71ms step:5878/6250 train_loss:2.3831 train_time:2363065ms step_avg:402.70ms step:5879/6250 train_loss:2.3587 train_time:2363457ms step_avg:402.70ms step:5880/6250 train_loss:2.2883 train_time:2363851ms step_avg:402.70ms step:5881/6250 train_loss:2.3387 train_time:2364243ms step_avg:402.70ms step:5882/6250 train_loss:2.3434 train_time:2364637ms step_avg:402.70ms step:5883/6250 train_loss:2.3035 train_time:2365029ms step_avg:402.70ms step:5884/6250 train_loss:2.4285 train_time:2365422ms step_avg:402.69ms step:5885/6250 train_loss:2.2551 train_time:2365813ms step_avg:402.69ms step:5886/6250 train_loss:2.4718 train_time:2366207ms step_avg:402.69ms step:5887/6250 train_loss:2.4894 train_time:2366599ms step_avg:402.69ms step:5888/6250 train_loss:2.4591 train_time:2366993ms step_avg:402.69ms step:5889/6250 train_loss:2.3416 train_time:2367384ms step_avg:402.68ms step:5890/6250 train_loss:2.4549 train_time:2367782ms step_avg:402.68ms step:5891/6250 train_loss:2.3147 train_time:2368178ms step_avg:402.68ms step:5892/6250 train_loss:2.2601 train_time:2368559ms step_avg:402.68ms step:5893/6250 train_loss:2.4393 train_time:2368938ms step_avg:402.68ms step:5894/6250 train_loss:2.3350 train_time:2369315ms step_avg:402.67ms step:5895/6250 train_loss:2.4016 train_time:2369695ms step_avg:402.67ms step:5896/6250 train_loss:2.3498 train_time:2370057ms step_avg:402.66ms step:5897/6250 train_loss:2.4970 train_time:2370428ms step_avg:402.65ms step:5898/6250 train_loss:2.3805 train_time:2370783ms step_avg:402.65ms step:5899/6250 train_loss:2.3361 train_time:2371132ms step_avg:402.64ms step:5900/6250 train_loss:2.3981 train_time:2371481ms step_avg:402.63ms step:5901/6250 train_loss:2.4304 train_time:2371825ms step_avg:402.62ms step:5902/6250 train_loss:2.3735 train_time:2372168ms step_avg:402.61ms step:5903/6250 train_loss:2.3536 train_time:2372511ms step_avg:402.60ms step:5904/6250 train_loss:2.3622 train_time:2372855ms step_avg:402.59ms step:5905/6250 train_loss:2.4660 train_time:2373199ms step_avg:402.58ms step:5906/6250 train_loss:2.4172 train_time:2373542ms step_avg:402.57ms step:5907/6250 train_loss:2.4513 train_time:2373885ms step_avg:402.56ms step:5908/6250 train_loss:2.3269 train_time:2374227ms step_avg:402.55ms step:5909/6250 train_loss:2.2896 train_time:2374572ms step_avg:402.54ms step:5910/6250 train_loss:2.3361 train_time:2374916ms step_avg:402.53ms step:5911/6250 train_loss:2.2395 train_time:2375260ms step_avg:402.52ms step:5912/6250 train_loss:2.3178 train_time:2375610ms step_avg:402.51ms step:5913/6250 train_loss:2.4934 train_time:2375957ms step_avg:402.50ms step:5914/6250 train_loss:2.4625 train_time:2376310ms step_avg:402.49ms step:5915/6250 train_loss:2.2476 train_time:2376656ms step_avg:402.48ms step:5916/6250 train_loss:2.3441 train_time:2377003ms step_avg:402.47ms step:5917/6250 train_loss:2.3407 train_time:2377349ms step_avg:402.46ms step:5918/6250 train_loss:2.3620 train_time:2377701ms step_avg:402.45ms step:5919/6250 train_loss:2.3228 train_time:2378050ms step_avg:402.45ms step:5920/6250 train_loss:2.2908 train_time:2378396ms step_avg:402.44ms step:5921/6250 train_loss:2.4030 train_time:2378743ms step_avg:402.43ms step:5922/6250 train_loss:2.3237 train_time:2379087ms step_avg:402.42ms step:5923/6250 train_loss:2.3559 train_time:2379433ms step_avg:402.41ms step:5924/6250 train_loss:2.4073 train_time:2379780ms step_avg:402.40ms step:5925/6250 train_loss:2.3959 train_time:2380125ms step_avg:402.39ms step:5926/6250 train_loss:2.4064 train_time:2380470ms step_avg:402.38ms step:5927/6250 train_loss:2.3159 train_time:2380817ms step_avg:402.37ms step:5928/6250 train_loss:2.3532 train_time:2381169ms step_avg:402.36ms step:5929/6250 train_loss:2.3746 train_time:2381515ms step_avg:402.35ms step:5930/6250 train_loss:2.3581 train_time:2381859ms step_avg:402.34ms step:5931/6250 train_loss:2.3842 train_time:2382208ms step_avg:402.33ms step:5932/6250 train_loss:2.3335 train_time:2382556ms step_avg:402.32ms step:5933/6250 train_loss:2.3746 train_time:2382902ms step_avg:402.31ms step:5934/6250 train_loss:2.3830 train_time:2383247ms step_avg:402.30ms step:5935/6250 train_loss:2.4505 train_time:2383593ms step_avg:402.29ms step:5936/6250 train_loss:2.3700 train_time:2383937ms step_avg:402.28ms step:5937/6250 train_loss:2.4093 train_time:2384283ms step_avg:402.27ms step:5938/6250 train_loss:2.3556 train_time:2384642ms step_avg:402.27ms step:5939/6250 train_loss:2.3290 train_time:2384999ms step_avg:402.26ms step:5940/6250 train_loss:2.3510 train_time:2385358ms step_avg:402.25ms step:5941/6250 train_loss:2.3822 train_time:2385715ms step_avg:402.24ms step:5942/6250 train_loss:2.3697 train_time:2386072ms step_avg:402.24ms step:5943/6250 train_loss:2.3498 train_time:2386429ms step_avg:402.23ms step:5944/6250 train_loss:2.3501 train_time:2386794ms step_avg:402.22ms step:5945/6250 train_loss:2.4139 train_time:2387158ms step_avg:402.22ms step:5946/6250 train_loss:2.4363 train_time:2387522ms step_avg:402.21ms step:5947/6250 train_loss:2.3947 train_time:2387885ms step_avg:402.20ms step:5948/6250 train_loss:2.3582 train_time:2388245ms step_avg:402.20ms step:5949/6250 train_loss:2.3453 train_time:2388613ms step_avg:402.19ms step:5950/6250 train_loss:2.4103 train_time:2388974ms step_avg:402.18ms step:5951/6250 train_loss:2.3833 train_time:2389333ms step_avg:402.18ms step:5952/6250 train_loss:2.2926 train_time:2389694ms step_avg:402.17ms step:5953/6250 train_loss:2.3221 train_time:2390054ms step_avg:402.16ms step:5954/6250 train_loss:2.3161 train_time:2390410ms step_avg:402.16ms step:5955/6250 train_loss:2.3581 train_time:2390758ms step_avg:402.15ms step:5956/6250 train_loss:2.3525 train_time:2391112ms step_avg:402.14ms step:5957/6250 train_loss:2.3569 train_time:2391465ms step_avg:402.13ms step:5958/6250 train_loss:2.3257 train_time:2391818ms step_avg:402.12ms step:5959/6250 train_loss:2.3393 train_time:2392170ms step_avg:402.11ms step:5960/6250 train_loss:2.5509 train_time:2392523ms step_avg:402.10ms step:5961/6250 train_loss:2.3092 train_time:2392878ms step_avg:402.10ms step:5962/6250 train_loss:2.3378 train_time:2393231ms step_avg:402.09ms step:5963/6250 train_loss:2.3116 train_time:2393586ms step_avg:402.08ms step:5964/6250 train_loss:2.3841 train_time:2393941ms step_avg:402.07ms step:5965/6250 train_loss:2.3773 train_time:2394296ms step_avg:402.06ms step:5966/6250 train_loss:2.3406 train_time:2394649ms step_avg:402.06ms step:5967/6250 train_loss:2.4198 train_time:2395001ms step_avg:402.05ms step:5968/6250 train_loss:2.4275 train_time:2395357ms step_avg:402.04ms step:5969/6250 train_loss:2.4408 train_time:2395712ms step_avg:402.03ms step:5970/6250 train_loss:2.2818 train_time:2396061ms step_avg:402.02ms step:5971/6250 train_loss:2.3458 train_time:2396407ms step_avg:402.01ms step:5972/6250 train_loss:2.3207 train_time:2396753ms step_avg:402.00ms step:5973/6250 train_loss:2.4455 train_time:2397100ms step_avg:402.00ms step:5974/6250 train_loss:2.3072 train_time:2397463ms step_avg:401.99ms step:5975/6250 train_loss:2.3101 train_time:2397818ms step_avg:401.98ms step:5976/6250 train_loss:2.3682 train_time:2398165ms step_avg:401.97ms step:5977/6250 train_loss:2.3411 train_time:2398512ms step_avg:401.96ms step:5978/6250 train_loss:2.3444 train_time:2398862ms step_avg:401.95ms step:5979/6250 train_loss:2.3267 train_time:2399222ms step_avg:401.95ms step:5980/6250 train_loss:2.3070 train_time:2399578ms step_avg:401.94ms step:5981/6250 train_loss:2.4373 train_time:2399943ms step_avg:401.93ms step:5982/6250 train_loss:2.4541 train_time:2400307ms step_avg:401.93ms step:5983/6250 train_loss:2.4252 train_time:2400662ms step_avg:401.92ms step:5984/6250 train_loss:2.3518 train_time:2401017ms step_avg:401.91ms step:5985/6250 train_loss:2.3356 train_time:2401361ms step_avg:401.90ms step:5986/6250 train_loss:2.4125 train_time:2401714ms step_avg:401.89ms step:5987/6250 train_loss:2.3588 train_time:2402070ms step_avg:401.89ms step:5988/6250 train_loss:2.4645 train_time:2402424ms step_avg:401.88ms step:5989/6250 train_loss:2.2996 train_time:2402768ms step_avg:401.87ms step:5990/6250 train_loss:2.3208 train_time:2403111ms step_avg:401.86ms step:5991/6250 train_loss:2.3122 train_time:2403456ms step_avg:401.85ms step:5992/6250 train_loss:2.4120 train_time:2403808ms step_avg:401.84ms step:5993/6250 train_loss:2.3523 train_time:2404160ms step_avg:401.83ms step:5994/6250 train_loss:2.2987 train_time:2404510ms step_avg:401.82ms step:5995/6250 train_loss:2.3688 train_time:2404857ms step_avg:401.81ms step:5996/6250 train_loss:2.3373 train_time:2405201ms step_avg:401.80ms step:5997/6250 train_loss:2.2483 train_time:2405546ms step_avg:401.79ms step:5998/6250 train_loss:2.3322 train_time:2405891ms step_avg:401.79ms step:5999/6250 train_loss:2.3155 train_time:2406235ms step_avg:401.78ms step:6000/6250 train_loss:2.3880 train_time:2406580ms step_avg:401.77ms step:6000/6250 val_loss:2.3449 train_time:2406580ms step_avg:401.77ms step:6001/6250 train_loss:2.3722 train_time:2406932ms step_avg:401.76ms step:6002/6250 train_loss:2.3775 train_time:2407289ms step_avg:401.75ms step:6003/6250 train_loss:2.3229 train_time:2407642ms step_avg:401.74ms step:6004/6250 train_loss:2.4033 train_time:2408000ms step_avg:401.73ms step:6005/6250 train_loss:2.3512 train_time:2408351ms step_avg:401.73ms step:6006/6250 train_loss:2.3898 train_time:2408704ms step_avg:401.72ms step:6007/6250 train_loss:2.4589 train_time:2409060ms step_avg:401.71ms step:6008/6250 train_loss:2.4484 train_time:2409414ms step_avg:401.70ms step:6009/6250 train_loss:2.4281 train_time:2409769ms step_avg:401.70ms step:6010/6250 train_loss:2.2959 train_time:2410124ms step_avg:401.69ms step:6011/6250 train_loss:2.4011 train_time:2410478ms step_avg:401.68ms step:6012/6250 train_loss:2.3119 train_time:2410830ms step_avg:401.67ms step:6013/6250 train_loss:2.3715 train_time:2411186ms step_avg:401.66ms step:6014/6250 train_loss:2.3169 train_time:2411538ms step_avg:401.66ms step:6015/6250 train_loss:2.3181 train_time:2411893ms step_avg:401.65ms step:6016/6250 train_loss:2.4408 train_time:2412248ms step_avg:401.64ms step:6017/6250 train_loss:2.3083 train_time:2412602ms step_avg:401.63ms step:6018/6250 train_loss:2.2782 train_time:2412957ms step_avg:401.62ms step:6019/6250 train_loss:2.3788 train_time:2413313ms step_avg:401.62ms step:6020/6250 train_loss:2.3554 train_time:2413667ms step_avg:401.61ms step:6021/6250 train_loss:2.4088 train_time:2414023ms step_avg:401.60ms step:6022/6250 train_loss:2.2718 train_time:2414377ms step_avg:401.59ms step:6023/6250 train_loss:2.3350 train_time:2414730ms step_avg:401.58ms step:6024/6250 train_loss:2.3098 train_time:2415077ms step_avg:401.58ms step:6025/6250 train_loss:2.4167 train_time:2415414ms step_avg:401.57ms step:6026/6250 train_loss:2.3149 train_time:2415754ms step_avg:401.55ms step:6027/6250 train_loss:2.3589 train_time:2416106ms step_avg:401.55ms step:6028/6250 train_loss:2.3896 train_time:2416484ms step_avg:401.54ms step:6029/6250 train_loss:2.3521 train_time:2416859ms step_avg:401.54ms step:6030/6250 train_loss:2.3598 train_time:2417226ms step_avg:401.53ms step:6031/6250 train_loss:2.3874 train_time:2417639ms step_avg:401.53ms step:6032/6250 train_loss:2.3235 train_time:2418042ms step_avg:401.53ms step:6033/6250 train_loss:2.3896 train_time:2418437ms step_avg:401.53ms step:6034/6250 train_loss:2.3393 train_time:2418835ms step_avg:401.53ms step:6035/6250 train_loss:2.3301 train_time:2419232ms step_avg:401.53ms step:6036/6250 train_loss:2.3265 train_time:2419628ms step_avg:401.53ms step:6037/6250 train_loss:2.4279 train_time:2420027ms step_avg:401.53ms step:6038/6250 train_loss:2.2992 train_time:2420424ms step_avg:401.53ms step:6039/6250 train_loss:2.3171 train_time:2420819ms step_avg:401.53ms step:6040/6250 train_loss:2.3512 train_time:2421217ms step_avg:401.53ms step:6041/6250 train_loss:2.2967 train_time:2421611ms step_avg:401.53ms step:6042/6250 train_loss:2.2223 train_time:2422011ms step_avg:401.53ms step:6043/6250 train_loss:2.4271 train_time:2422406ms step_avg:401.53ms step:6044/6250 train_loss:2.3689 train_time:2422804ms step_avg:401.53ms step:6045/6250 train_loss:2.3503 train_time:2423204ms step_avg:401.53ms step:6046/6250 train_loss:2.3668 train_time:2423597ms step_avg:401.52ms step:6047/6250 train_loss:2.4313 train_time:2423997ms step_avg:401.52ms step:6048/6250 train_loss:2.3339 train_time:2424393ms step_avg:401.52ms step:6049/6250 train_loss:2.3974 train_time:2424793ms step_avg:401.52ms step:6050/6250 train_loss:2.3478 train_time:2425194ms step_avg:401.52ms step:6051/6250 train_loss:2.3853 train_time:2425588ms step_avg:401.52ms step:6052/6250 train_loss:2.4160 train_time:2425986ms step_avg:401.52ms step:6053/6250 train_loss:2.4061 train_time:2426416ms step_avg:401.53ms step:6054/6250 train_loss:2.3989 train_time:2426856ms step_avg:401.53ms step:6055/6250 train_loss:2.3462 train_time:2427295ms step_avg:401.54ms step:6056/6250 train_loss:2.2290 train_time:2427732ms step_avg:401.54ms step:6057/6250 train_loss:2.3089 train_time:2428170ms step_avg:401.55ms step:6058/6250 train_loss:2.3593 train_time:2428596ms step_avg:401.55ms step:6059/6250 train_loss:2.3275 train_time:2429029ms step_avg:401.56ms step:6060/6250 train_loss:2.3747 train_time:2429463ms step_avg:401.56ms step:6061/6250 train_loss:2.3370 train_time:2429904ms step_avg:401.57ms step:6062/6250 train_loss:2.2835 train_time:2430344ms step_avg:401.58ms step:6063/6250 train_loss:2.3149 train_time:2430783ms step_avg:401.58ms step:6064/6250 train_loss:2.3523 train_time:2431202ms step_avg:401.59ms step:6065/6250 train_loss:2.2702 train_time:2431644ms step_avg:401.59ms step:6066/6250 train_loss:2.3770 train_time:2432069ms step_avg:401.60ms step:6067/6250 train_loss:2.3128 train_time:2432533ms step_avg:401.61ms step:6068/6250 train_loss:2.4384 train_time:2432965ms step_avg:401.61ms step:6069/6250 train_loss:2.1719 train_time:2433404ms step_avg:401.62ms step:6070/6250 train_loss:2.3592 train_time:2433858ms step_avg:401.63ms step:6071/6250 train_loss:2.3196 train_time:2434282ms step_avg:401.63ms step:6072/6250 train_loss:2.3762 train_time:2434719ms step_avg:401.64ms step:6073/6250 train_loss:2.3889 train_time:2435172ms step_avg:401.64ms step:6074/6250 train_loss:2.3659 train_time:2435624ms step_avg:401.65ms step:6075/6250 train_loss:2.2976 train_time:2436082ms step_avg:401.66ms step:6076/6250 train_loss:2.3335 train_time:2436555ms step_avg:401.67ms step:6077/6250 train_loss:2.3365 train_time:2437012ms step_avg:401.68ms step:6078/6250 train_loss:2.3314 train_time:2437481ms step_avg:401.69ms step:6079/6250 train_loss:2.2436 train_time:2437950ms step_avg:401.71ms step:6080/6250 train_loss:2.3507 train_time:2438412ms step_avg:401.72ms step:6081/6250 train_loss:2.2339 train_time:2438856ms step_avg:401.72ms step:6082/6250 train_loss:2.3753 train_time:2439276ms step_avg:401.73ms step:6083/6250 train_loss:2.2685 train_time:2439733ms step_avg:401.73ms step:6084/6250 train_loss:2.3226 train_time:2440211ms step_avg:401.75ms step:6085/6250 train_loss:2.3808 train_time:2440648ms step_avg:401.75ms step:6086/6250 train_loss:2.3220 train_time:2441129ms step_avg:401.77ms step:6087/6250 train_loss:2.3338 train_time:2441608ms step_avg:401.78ms step:6088/6250 train_loss:2.3272 train_time:2442068ms step_avg:401.79ms step:6089/6250 train_loss:2.2873 train_time:2442497ms step_avg:401.79ms step:6090/6250 train_loss:2.3571 train_time:2442967ms step_avg:401.80ms step:6091/6250 train_loss:2.3416 train_time:2443419ms step_avg:401.81ms step:6092/6250 train_loss:2.3407 train_time:2443871ms step_avg:401.82ms step:6093/6250 train_loss:2.3176 train_time:2444306ms step_avg:401.83ms step:6094/6250 train_loss:2.2532 train_time:2444747ms step_avg:401.83ms step:6095/6250 train_loss:2.3639 train_time:2445188ms step_avg:401.84ms step:6096/6250 train_loss:2.2970 train_time:2445597ms step_avg:401.84ms step:6097/6250 train_loss:2.4032 train_time:2445937ms step_avg:401.83ms step:6098/6250 train_loss:2.3888 train_time:2446283ms step_avg:401.82ms step:6099/6250 train_loss:2.3463 train_time:2446640ms step_avg:401.81ms step:6100/6250 train_loss:2.3502 train_time:2447084ms step_avg:401.82ms step:6101/6250 train_loss:2.3565 train_time:2447530ms step_avg:401.83ms step:6102/6250 train_loss:2.2964 train_time:2447960ms step_avg:401.83ms step:6103/6250 train_loss:2.2867 train_time:2448401ms step_avg:401.84ms step:6104/6250 train_loss:2.2980 train_time:2448844ms step_avg:401.85ms step:6105/6250 train_loss:2.3824 train_time:2449228ms step_avg:401.84ms step:6106/6250 train_loss:2.3049 train_time:2449572ms step_avg:401.83ms step:6107/6250 train_loss:2.4256 train_time:2449912ms step_avg:401.82ms step:6108/6250 train_loss:2.2798 train_time:2450332ms step_avg:401.83ms step:6109/6250 train_loss:2.2742 train_time:2450763ms step_avg:401.83ms step:6110/6250 train_loss:2.3121 train_time:2451205ms step_avg:401.84ms step:6111/6250 train_loss:2.3523 train_time:2451588ms step_avg:401.83ms step:6112/6250 train_loss:2.3029 train_time:2451933ms step_avg:401.82ms step:6113/6250 train_loss:2.3291 train_time:2452273ms step_avg:401.81ms step:6114/6250 train_loss:2.2707 train_time:2452704ms step_avg:401.82ms step:6115/6250 train_loss:2.3542 train_time:2453151ms step_avg:401.83ms step:6116/6250 train_loss:2.3038 train_time:2453545ms step_avg:401.83ms step:6117/6250 train_loss:2.4373 train_time:2453890ms step_avg:401.82ms step:6118/6250 train_loss:2.5251 train_time:2454231ms step_avg:401.81ms step:6119/6250 train_loss:2.3520 train_time:2454665ms step_avg:401.81ms step:6120/6250 train_loss:2.3729 train_time:2455092ms step_avg:401.82ms step:6121/6250 train_loss:2.3051 train_time:2455470ms step_avg:401.81ms step:6122/6250 train_loss:2.3129 train_time:2455815ms step_avg:401.80ms step:6123/6250 train_loss:2.2775 train_time:2456157ms step_avg:401.79ms step:6124/6250 train_loss:2.3119 train_time:2456599ms step_avg:401.80ms step:6125/6250 train_loss:2.3955 train_time:2457021ms step_avg:401.80ms step:6126/6250 train_loss:2.3846 train_time:2457432ms step_avg:401.80ms step:6127/6250 train_loss:2.3233 train_time:2457771ms step_avg:401.79ms step:6128/6250 train_loss:2.3113 train_time:2458116ms step_avg:401.78ms step:6129/6250 train_loss:2.2989 train_time:2458529ms step_avg:401.79ms step:6130/6250 train_loss:2.3227 train_time:2458953ms step_avg:401.79ms step:6131/6250 train_loss:2.2917 train_time:2459294ms step_avg:401.78ms step:6132/6250 train_loss:2.2373 train_time:2459707ms step_avg:401.78ms step:6133/6250 train_loss:2.3206 train_time:2460154ms step_avg:401.79ms step:6134/6250 train_loss:2.2847 train_time:2460581ms step_avg:401.79ms step:6135/6250 train_loss:2.2513 train_time:2460928ms step_avg:401.78ms step:6136/6250 train_loss:2.3285 train_time:2461273ms step_avg:401.77ms step:6137/6250 train_loss:2.2861 train_time:2461649ms step_avg:401.77ms step:6138/6250 train_loss:2.3709 train_time:2462091ms step_avg:401.78ms step:6139/6250 train_loss:2.3131 train_time:2462523ms step_avg:401.78ms step:6140/6250 train_loss:2.2832 train_time:2462932ms step_avg:401.78ms step:6141/6250 train_loss:2.3724 train_time:2463372ms step_avg:401.79ms step:6142/6250 train_loss:2.2943 train_time:2463801ms step_avg:401.79ms step:6143/6250 train_loss:2.3158 train_time:2464242ms step_avg:401.80ms step:6144/6250 train_loss:2.2542 train_time:2464648ms step_avg:401.80ms step:6145/6250 train_loss:2.3242 train_time:2465060ms step_avg:401.80ms step:6146/6250 train_loss:2.2922 train_time:2465464ms step_avg:401.80ms step:6147/6250 train_loss:2.2332 train_time:2465869ms step_avg:401.80ms step:6148/6250 train_loss:2.3497 train_time:2466281ms step_avg:401.81ms step:6149/6250 train_loss:2.3126 train_time:2466681ms step_avg:401.81ms step:6150/6250 train_loss:2.4544 train_time:2467022ms step_avg:401.80ms step:6151/6250 train_loss:2.3159 train_time:2467366ms step_avg:401.79ms step:6152/6250 train_loss:2.3296 train_time:2467709ms step_avg:401.78ms step:6153/6250 train_loss:2.2595 train_time:2468053ms step_avg:401.77ms step:6154/6250 train_loss:2.3270 train_time:2468393ms step_avg:401.76ms step:6155/6250 train_loss:2.3803 train_time:2468805ms step_avg:401.76ms step:6156/6250 train_loss:2.3529 train_time:2469259ms step_avg:401.77ms step:6157/6250 train_loss:2.2953 train_time:2469699ms step_avg:401.77ms step:6158/6250 train_loss:2.2838 train_time:2470140ms step_avg:401.78ms step:6159/6250 train_loss:2.3073 train_time:2470587ms step_avg:401.79ms step:6160/6250 train_loss:2.2998 train_time:2471031ms step_avg:401.79ms step:6161/6250 train_loss:2.4098 train_time:2471479ms step_avg:401.80ms step:6162/6250 train_loss:2.2608 train_time:2471915ms step_avg:401.81ms step:6163/6250 train_loss:2.3360 train_time:2472363ms step_avg:401.81ms step:6164/6250 train_loss:2.3048 train_time:2472808ms step_avg:401.82ms step:6165/6250 train_loss:2.2155 train_time:2473259ms step_avg:401.83ms step:6166/6250 train_loss:2.2588 train_time:2473701ms step_avg:401.84ms step:6167/6250 train_loss:2.2764 train_time:2474150ms step_avg:401.84ms step:6168/6250 train_loss:2.3045 train_time:2474578ms step_avg:401.85ms step:6169/6250 train_loss:2.3497 train_time:2475008ms step_avg:401.85ms step:6170/6250 train_loss:2.3186 train_time:2475451ms step_avg:401.86ms step:6171/6250 train_loss:2.3108 train_time:2475844ms step_avg:401.86ms step:6172/6250 train_loss:2.2330 train_time:2476187ms step_avg:401.85ms step:6173/6250 train_loss:2.3203 train_time:2476531ms step_avg:401.84ms step:6174/6250 train_loss:2.2579 train_time:2476921ms step_avg:401.84ms step:6175/6250 train_loss:2.2536 train_time:2477341ms step_avg:401.84ms step:6176/6250 train_loss:2.3712 train_time:2477783ms step_avg:401.85ms step:6177/6250 train_loss:2.1978 train_time:2478123ms step_avg:401.84ms step:6178/6250 train_loss:2.2676 train_time:2478468ms step_avg:401.83ms step:6179/6250 train_loss:2.3890 train_time:2478806ms step_avg:401.82ms step:6180/6250 train_loss:2.3071 train_time:2479213ms step_avg:401.82ms step:6181/6250 train_loss:2.3345 train_time:2479639ms step_avg:401.82ms step:6182/6250 train_loss:2.3741 train_time:2479979ms step_avg:401.81ms step:6183/6250 train_loss:2.3072 train_time:2480324ms step_avg:401.80ms step:6184/6250 train_loss:2.3045 train_time:2480664ms step_avg:401.79ms step:6185/6250 train_loss:2.3378 train_time:2481097ms step_avg:401.80ms step:6186/6250 train_loss:2.3722 train_time:2481528ms step_avg:401.80ms step:6187/6250 train_loss:2.2244 train_time:2481976ms step_avg:401.81ms step:6188/6250 train_loss:2.2663 train_time:2482425ms step_avg:401.82ms step:6189/6250 train_loss:2.3417 train_time:2482808ms step_avg:401.81ms step:6190/6250 train_loss:2.3520 train_time:2483149ms step_avg:401.80ms step:6191/6250 train_loss:2.3079 train_time:2483582ms step_avg:401.81ms step:6192/6250 train_loss:2.3389 train_time:2484031ms step_avg:401.82ms step:6193/6250 train_loss:2.2729 train_time:2484469ms step_avg:401.82ms step:6194/6250 train_loss:2.3436 train_time:2484901ms step_avg:401.83ms step:6195/6250 train_loss:2.3887 train_time:2485349ms step_avg:401.83ms step:6196/6250 train_loss:2.3053 train_time:2485782ms step_avg:401.84ms step:6197/6250 train_loss:2.3109 train_time:2486226ms step_avg:401.85ms step:6198/6250 train_loss:2.3256 train_time:2486658ms step_avg:401.85ms step:6199/6250 train_loss:2.2718 train_time:2487102ms step_avg:401.86ms step:6200/6250 train_loss:2.3877 train_time:2487544ms step_avg:401.86ms step:6201/6250 train_loss:2.3766 train_time:2487989ms step_avg:401.87ms step:6202/6250 train_loss:2.2620 train_time:2488431ms step_avg:401.88ms step:6203/6250 train_loss:2.2712 train_time:2488873ms step_avg:401.88ms step:6204/6250 train_loss:2.2824 train_time:2489319ms step_avg:401.89ms step:6205/6250 train_loss:2.3416 train_time:2489682ms step_avg:401.89ms step:6206/6250 train_loss:2.2864 train_time:2490033ms step_avg:401.88ms step:6207/6250 train_loss:2.3388 train_time:2490475ms step_avg:401.88ms step:6208/6250 train_loss:2.3244 train_time:2490918ms step_avg:401.89ms step:6209/6250 train_loss:2.3328 train_time:2491361ms step_avg:401.90ms step:6210/6250 train_loss:2.3304 train_time:2491777ms step_avg:401.90ms step:6211/6250 train_loss:2.2831 train_time:2492189ms step_avg:401.90ms step:6212/6250 train_loss:2.3131 train_time:2492615ms step_avg:401.91ms step:6213/6250 train_loss:2.2877 train_time:2493062ms step_avg:401.91ms step:6214/6250 train_loss:2.3204 train_time:2493509ms step_avg:401.92ms step:6215/6250 train_loss:2.1981 train_time:2493942ms step_avg:401.92ms step:6216/6250 train_loss:2.2506 train_time:2494373ms step_avg:401.93ms step:6217/6250 train_loss:2.2769 train_time:2494816ms step_avg:401.94ms step:6218/6250 train_loss:2.2962 train_time:2495246ms step_avg:401.94ms step:6219/6250 train_loss:2.3977 train_time:2495692ms step_avg:401.95ms step:6220/6250 train_loss:2.2712 train_time:2496125ms step_avg:401.95ms step:6221/6250 train_loss:2.3194 train_time:2496566ms step_avg:401.96ms step:6222/6250 train_loss:2.2857 train_time:2497011ms step_avg:401.97ms step:6223/6250 train_loss:2.3270 train_time:2497454ms step_avg:401.97ms step:6224/6250 train_loss:2.2894 train_time:2497881ms step_avg:401.98ms step:6225/6250 train_loss:2.3447 train_time:2498326ms step_avg:401.98ms step:6226/6250 train_loss:2.2561 train_time:2498757ms step_avg:401.99ms step:6227/6250 train_loss:2.3207 train_time:2499197ms step_avg:401.99ms step:6228/6250 train_loss:2.3443 train_time:2499603ms step_avg:401.99ms step:6229/6250 train_loss:2.2680 train_time:2500009ms step_avg:402.00ms step:6230/6250 train_loss:2.3039 train_time:2500438ms step_avg:402.00ms step:6231/6250 train_loss:2.2300 train_time:2500879ms step_avg:402.01ms step:6232/6250 train_loss:2.1691 train_time:2501322ms step_avg:402.01ms step:6233/6250 train_loss:2.2942 train_time:2501757ms step_avg:402.02ms step:6234/6250 train_loss:2.2783 train_time:2502199ms step_avg:402.02ms step:6235/6250 train_loss:2.2949 train_time:2502641ms step_avg:402.03ms step:6236/6250 train_loss:2.2895 train_time:2503084ms step_avg:402.04ms step:6237/6250 train_loss:2.2938 train_time:2503524ms step_avg:402.04ms step:6238/6250 train_loss:2.3521 train_time:2503964ms step_avg:402.05ms step:6239/6250 train_loss:2.2269 train_time:2504406ms step_avg:402.06ms step:6240/6250 train_loss:2.3059 train_time:2504847ms step_avg:402.06ms step:6241/6250 train_loss:2.2441 train_time:2505292ms step_avg:402.07ms step:6242/6250 train_loss:2.2294 train_time:2505719ms step_avg:402.07ms step:6243/6250 train_loss:2.3474 train_time:2506166ms step_avg:402.08ms step:6244/6250 train_loss:2.3127 train_time:2506607ms step_avg:402.09ms step:6245/6250 train_loss:2.2663 train_time:2507026ms step_avg:402.09ms step:6246/6250 train_loss:2.2636 train_time:2507473ms step_avg:402.10ms step:6247/6250 train_loss:2.3486 train_time:2507911ms step_avg:402.10ms step:6248/6250 train_loss:2.2362 train_time:2508346ms step_avg:402.11ms step:6249/6250 train_loss:2.2175 train_time:2508779ms step_avg:402.11ms step:6250/6250 train_loss:2.3846 train_time:2509213ms step_avg:402.12ms step:6250/6250 val_loss:2.2853 train_time:2509213ms step_avg:402.12ms